diff options
| author | David S. Miller <davem@davemloft.net> | 2011-09-22 03:23:13 -0400 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2011-09-22 03:23:13 -0400 |
| commit | 8decf868790b48a727d7e7ca164f2bcd3c1389c0 (patch) | |
| tree | b759a5f861f842af7ea76f9011b579d06e9d5508 | |
| parent | 3fc72370186be2f9d4d6ef06d99e1caa5d92c564 (diff) | |
| parent | d93dc5c4478c1fd5de85a3e8aece9aad7bbae044 (diff) | |
| download | linux-linaro-stable-8decf868790b48a727d7e7ca164f2bcd3c1389c0.tar.gz | |
Merge branch 'master' of github.com:davem330/net
Conflicts:
MAINTAINERS
drivers/net/Kconfig
drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
drivers/net/ethernet/broadcom/tg3.c
drivers/net/wireless/iwlwifi/iwl-pci.c
drivers/net/wireless/iwlwifi/iwl-trans-tx-pcie.c
drivers/net/wireless/rt2x00/rt2800usb.c
drivers/net/wireless/wl12xx/main.c
947 files changed, 13246 insertions, 5718 deletions
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX index 1f89424c36a6..65bbd2622396 100644 --- a/Documentation/00-INDEX +++ b/Documentation/00-INDEX @@ -272,6 +272,8 @@ printk-formats.txt - how to get printk format specifiers right prio_tree.txt - info on radix-priority-search-tree use for indexing vmas. +ramoops.txt + - documentation of the ramoops oops/panic logging module. rbtree.txt - info on what red-black trees are and what they are for. robust-futex-ABI.txt diff --git a/Documentation/ABI/testing/sysfs-class-scsi_host b/Documentation/ABI/testing/sysfs-class-scsi_host new file mode 100644 index 000000000000..29a4f892e433 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-scsi_host @@ -0,0 +1,13 @@ +What: /sys/class/scsi_host/hostX/isci_id +Date: June 2011 +Contact: Dave Jiang <dave.jiang@intel.com> +Description: + This file contains the enumerated host ID for the Intel + SCU controller. The Intel(R) C600 Series Chipset SATA/SAS + Storage Control Unit embeds up to two 4-port controllers in + a single PCI device. The controllers are enumerated in order + which usually means the lowest number scsi_host corresponds + with the first controller, but this association is not + guaranteed. The 'isci_id' attribute unambiguously identifies + the controller index: '0' for the first controller, + '1' for the second. diff --git a/Documentation/DocBook/media/v4l/controls.xml b/Documentation/DocBook/media/v4l/controls.xml index 85164016ed26..23fdf79f8cf3 100644 --- a/Documentation/DocBook/media/v4l/controls.xml +++ b/Documentation/DocBook/media/v4l/controls.xml @@ -1455,7 +1455,7 @@ Applicable to the H264 encoder.</entry> </row> <row><entry></entry></row> - <row> + <row id="v4l2-mpeg-video-h264-vui-sar-idc"> <entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_H264_VUI_SAR_IDC</constant> </entry> <entry>enum v4l2_mpeg_video_h264_vui_sar_idc</entry> </row> @@ -1561,7 +1561,7 @@ Applicable to the H264 encoder.</entry> </row> <row><entry></entry></row> - <row> + <row id="v4l2-mpeg-video-h264-level"> <entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_H264_LEVEL</constant> </entry> <entry>enum v4l2_mpeg_video_h264_level</entry> </row> @@ -1641,7 +1641,7 @@ Possible values are:</entry> </row> <row><entry></entry></row> - <row> + <row id="v4l2-mpeg-video-mpeg4-level"> <entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_MPEG4_LEVEL</constant> </entry> <entry>enum v4l2_mpeg_video_mpeg4_level</entry> </row> @@ -1689,9 +1689,9 @@ Possible values are:</entry> </row> <row><entry></entry></row> - <row> + <row id="v4l2-mpeg-video-h264-profile"> <entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_H264_PROFILE</constant> </entry> - <entry>enum v4l2_mpeg_h264_profile</entry> + <entry>enum v4l2_mpeg_video_h264_profile</entry> </row> <row><entry spanname="descr">The profile information for H264. Applicable to the H264 encoder. @@ -1774,9 +1774,9 @@ Possible values are:</entry> </row> <row><entry></entry></row> - <row> + <row id="v4l2-mpeg-video-mpeg4-profile"> <entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_MPEG4_PROFILE</constant> </entry> - <entry>enum v4l2_mpeg_mpeg4_profile</entry> + <entry>enum v4l2_mpeg_video_mpeg4_profile</entry> </row> <row><entry spanname="descr">The profile information for MPEG4. Applicable to the MPEG4 encoder. @@ -1820,9 +1820,9 @@ Applicable to the encoder. </row> <row><entry></entry></row> - <row> + <row id="v4l2-mpeg-video-multi-slice-mode"> <entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MODE</constant> </entry> - <entry>enum v4l2_mpeg_multi_slice_mode</entry> + <entry>enum v4l2_mpeg_video_multi_slice_mode</entry> </row> <row><entry spanname="descr">Determines how the encoder should handle division of frame into slices. Applicable to the encoder. @@ -1868,9 +1868,9 @@ Applicable to the encoder.</entry> </row> <row><entry></entry></row> - <row> + <row id="v4l2-mpeg-video-h264-loop-filter-mode"> <entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_MODE</constant> </entry> - <entry>enum v4l2_mpeg_h264_loop_filter_mode</entry> + <entry>enum v4l2_mpeg_video_h264_loop_filter_mode</entry> </row> <row><entry spanname="descr">Loop filter mode for H264 encoder. Possible values are:</entry> @@ -1913,9 +1913,9 @@ Applicable to the H264 encoder.</entry> </row> <row><entry></entry></row> - <row> + <row id="v4l2-mpeg-video-h264-entropy-mode"> <entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_H264_ENTROPY_MODE</constant> </entry> - <entry>enum v4l2_mpeg_h264_symbol_mode</entry> + <entry>enum v4l2_mpeg_video_h264_entropy_mode</entry> </row> <row><entry spanname="descr">Entropy coding mode for H264 - CABAC/CAVALC. Applicable to the H264 encoder. @@ -2140,9 +2140,9 @@ previous frames. Applicable to the H264 encoder.</entry> </row> <row><entry></entry></row> - <row> + <row id="v4l2-mpeg-video-header-mode"> <entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_HEADER_MODE</constant> </entry> - <entry>enum v4l2_mpeg_header_mode</entry> + <entry>enum v4l2_mpeg_video_header_mode</entry> </row> <row><entry spanname="descr">Determines whether the header is returned as the first buffer or is it returned together with the first frame. Applicable to encoders. @@ -2320,9 +2320,9 @@ Valid only when H.264 and macroblock level RC is enabled (<constant>V4L2_CID_MPE Applicable to the H264 encoder.</entry> </row> <row><entry></entry></row> - <row> + <row id="v4l2-mpeg-mfc51-video-frame-skip-mode"> <entry spanname="id"><constant>V4L2_CID_MPEG_MFC51_VIDEO_FRAME_SKIP_MODE</constant> </entry> - <entry>enum v4l2_mpeg_mfc51_frame_skip_mode</entry> + <entry>enum v4l2_mpeg_mfc51_video_frame_skip_mode</entry> </row> <row><entry spanname="descr"> Indicates in what conditions the encoder should skip frames. If encoding a frame would cause the encoded stream to be larger then @@ -2361,9 +2361,9 @@ the stream will meet tight bandwidth contraints. Applicable to encoders. </entry> </row> <row><entry></entry></row> - <row> + <row id="v4l2-mpeg-mfc51-video-force-frame-type"> <entry spanname="id"><constant>V4L2_CID_MPEG_MFC51_VIDEO_FORCE_FRAME_TYPE</constant> </entry> - <entry>enum v4l2_mpeg_mfc51_force_frame_type</entry> + <entry>enum v4l2_mpeg_mfc51_video_force_frame_type</entry> </row> <row><entry spanname="descr">Force a frame type for the next queued buffer. Applicable to encoders. Possible values are:</entry> diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt index 3f5e0b09bed5..53e6fca146d7 100644 --- a/Documentation/PCI/MSI-HOWTO.txt +++ b/Documentation/PCI/MSI-HOWTO.txt @@ -45,7 +45,7 @@ arrived in memory (this becomes more likely with devices behind PCI-PCI bridges). In order to ensure that all the data has arrived in memory, the interrupt handler must read a register on the device which raised the interrupt. PCI transaction ordering rules require that all the data -arrives in memory before the value can be returned from the register. +arrive in memory before the value may be returned from the register. Using MSIs avoids this problem as the interrupt-generating write cannot pass the data writes, so by the time the interrupt is raised, the driver knows that all the data has arrived in memory. @@ -86,13 +86,13 @@ device. int pci_enable_msi(struct pci_dev *dev) -A successful call will allocate ONE interrupt to the device, regardless -of how many MSIs the device supports. The device will be switched from +A successful call allocates ONE interrupt to the device, regardless +of how many MSIs the device supports. The device is switched from pin-based interrupt mode to MSI mode. The dev->irq number is changed -to a new number which represents the message signaled interrupt. -This function should be called before the driver calls request_irq() -since enabling MSIs disables the pin-based IRQ and the driver will not -receive interrupts on the old interrupt. +to a new number which represents the message signaled interrupt; +consequently, this function should be called before the driver calls +request_irq(), because an MSI is delivered via a vector that is +different from the vector of a pin-based interrupt. 4.2.2 pci_enable_msi_block @@ -111,20 +111,20 @@ the device are in the range dev->irq to dev->irq + count - 1. If this function returns a negative number, it indicates an error and the driver should not attempt to request any more MSI interrupts for -this device. If this function returns a positive number, it will be -less than 'count' and indicate the number of interrupts that could have -been allocated. In neither case will the irq value have been -updated, nor will the device have been switched into MSI mode. +this device. If this function returns a positive number, it is +less than 'count' and indicates the number of interrupts that could have +been allocated. In neither case is the irq value updated or the device +switched into MSI mode. The device driver must decide what action to take if -pci_enable_msi_block() returns a value less than the number asked for. -Some devices can make use of fewer interrupts than the maximum they -request; in this case the driver should call pci_enable_msi_block() +pci_enable_msi_block() returns a value less than the number requested. +For instance, the driver could still make use of fewer interrupts; +in this case the driver should call pci_enable_msi_block() again. Note that it is not guaranteed to succeed, even when the 'count' has been reduced to the value returned from a previous call to pci_enable_msi_block(). This is because there are multiple constraints on the number of vectors that can be allocated; pci_enable_msi_block() -will return as soon as it finds any constraint that doesn't allow the +returns as soon as it finds any constraint that doesn't allow the call to succeed. 4.2.3 pci_disable_msi @@ -137,10 +137,10 @@ interrupt number and frees the previously allocated message signaled interrupt(s). The interrupt may subsequently be assigned to another device, so drivers should not cache the value of dev->irq. -A device driver must always call free_irq() on the interrupt(s) -for which it has called request_irq() before calling this function. -Failure to do so will result in a BUG_ON(), the device will be left with -MSI enabled and will leak its vector. +Before calling this function, a device driver must always call free_irq() +on any interrupt for which it previously called request_irq(). +Failure to do so results in a BUG_ON(), leaving the device with +MSI enabled and thus leaking its vector. 4.3 Using MSI-X @@ -155,10 +155,10 @@ struct msix_entry { }; This allows for the device to use these interrupts in a sparse fashion; -for example it could use interrupts 3 and 1027 and allocate only a +for example, it could use interrupts 3 and 1027 and yet allocate only a two-element array. The driver is expected to fill in the 'entry' value -in each element of the array to indicate which entries it wants the kernel -to assign interrupts for. It is invalid to fill in two entries with the +in each element of the array to indicate for which entries the kernel +should assign interrupts; it is invalid to fill in two entries with the same number. 4.3.1 pci_enable_msix @@ -168,10 +168,11 @@ int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec) Calling this function asks the PCI subsystem to allocate 'nvec' MSIs. The 'entries' argument is a pointer to an array of msix_entry structs which should be at least 'nvec' entries in size. On success, the -function will return 0 and the device will have been switched into -MSI-X interrupt mode. The 'vector' elements in each entry will have -been filled in with the interrupt number. The driver should then call -request_irq() for each 'vector' that it decides to use. +device is switched into MSI-X mode and the function returns 0. +The 'vector' member in each entry is populated with the interrupt number; +the driver should then call request_irq() for each 'vector' that it +decides to use. The device driver is responsible for keeping track of the +interrupts assigned to the MSI-X vectors so it can free them again later. If this function returns a negative number, it indicates an error and the driver should not attempt to allocate any more MSI-X interrupts for @@ -181,16 +182,14 @@ below. This function, in contrast with pci_enable_msi(), does not adjust dev->irq. The device will not generate interrupts for this interrupt -number once MSI-X is enabled. The device driver is responsible for -keeping track of the interrupts assigned to the MSI-X vectors so it can -free them again later. +number once MSI-X is enabled. Device drivers should normally call this function once per device during the initialization phase. -It is ideal if drivers can cope with a variable number of MSI-X interrupts, +It is ideal if drivers can cope with a variable number of MSI-X interrupts; there are many reasons why the platform may not be able to provide the -exact number a driver asks for. +exact number that a driver asks for. A request loop to achieve that might look like: @@ -212,15 +211,15 @@ static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec) void pci_disable_msix(struct pci_dev *dev) -This API should be used to undo the effect of pci_enable_msix(). It frees +This function should be used to undo the effect of pci_enable_msix(). It frees the previously allocated message signaled interrupts. The interrupts may subsequently be assigned to another device, so drivers should not cache the value of the 'vector' elements over a call to pci_disable_msix(). -A device driver must always call free_irq() on the interrupt(s) -for which it has called request_irq() before calling this function. -Failure to do so will result in a BUG_ON(), the device will be left with -MSI enabled and will leak its vector. +Before calling this function, a device driver must always call free_irq() +on any interrupt for which it previously called request_irq(). +Failure to do so results in a BUG_ON(), leaving the device with +MSI-X enabled and thus leaking its vector. 4.3.3 The MSI-X Table @@ -232,10 +231,10 @@ mask or unmask an interrupt, it should call disable_irq() / enable_irq(). 4.4 Handling devices implementing both MSI and MSI-X capabilities If a device implements both MSI and MSI-X capabilities, it can -run in either MSI mode or MSI-X mode but not both simultaneously. +run in either MSI mode or MSI-X mode, but not both simultaneously. This is a requirement of the PCI spec, and it is enforced by the PCI layer. Calling pci_enable_msi() when MSI-X is already enabled or -pci_enable_msix() when MSI is already enabled will result in an error. +pci_enable_msix() when MSI is already enabled results in an error. If a device driver wishes to switch between MSI and MSI-X at runtime, it must first quiesce the device, then switch it back to pin-interrupt mode, before calling pci_enable_msi() or pci_enable_msix() and resuming @@ -251,7 +250,7 @@ the MSI-X facilities in preference to the MSI facilities. As mentioned above, MSI-X supports any number of interrupts between 1 and 2048. In constrast, MSI is restricted to a maximum of 32 interrupts (and must be a power of two). In addition, the MSI interrupt vectors must -be allocated consecutively, so the system may not be able to allocate +be allocated consecutively, so the system might not be able to allocate as many vectors for MSI as it could for MSI-X. On some platforms, MSI interrupts must all be targeted at the same set of CPUs whereas MSI-X interrupts can all be targeted at different CPUs. @@ -281,7 +280,7 @@ disabled to enabled and back again. Using 'lspci -v' (as root) may show some devices with "MSI", "Message Signalled Interrupts" or "MSI-X" capabilities. Each of these capabilities -has an 'Enable' flag which will be followed with either "+" (enabled) +has an 'Enable' flag which is followed with either "+" (enabled) or "-" (disabled). @@ -298,7 +297,7 @@ The PCI stack provides three ways to disable MSIs: Some host chipsets simply don't support MSIs properly. If we're lucky, the manufacturer knows this and has indicated it in the ACPI -FADT table. In this case, Linux will automatically disable MSIs. +FADT table. In this case, Linux automatically disables MSIs. Some boards don't include this information in the table and so we have to detect them ourselves. The complete list of these is found near the quirk_disable_all_msi() function in drivers/pci/quirks.c. @@ -317,7 +316,7 @@ Some bridges allow you to enable MSIs by changing some bits in their PCI configuration space (especially the Hypertransport chipsets such as the nVidia nForce and Serverworks HT2000). As with host chipsets, Linux mostly knows about them and automatically enables MSIs if it can. -If you have a bridge which Linux doesn't yet know about, you can enable +If you have a bridge unknown to Linux, you can enable MSIs in configuration space using whatever method you know works, then enable MSIs on that bridge by doing: @@ -327,7 +326,7 @@ where $bridge is the PCI address of the bridge you've enabled (eg 0000:00:0e.0). To disable MSIs, echo 0 instead of 1. Changing this value should be -done with caution as it can break interrupt handling for all devices +done with caution as it could break interrupt handling for all devices below this bridge. Again, please notify linux-pci@vger.kernel.org of any bridges that need @@ -336,7 +335,7 @@ special handling. 5.3. Disabling MSIs on a single device Some devices are known to have faulty MSI implementations. Usually this -is handled in the individual device driver but occasionally it's necessary +is handled in the individual device driver, but occasionally it's necessary to handle this with a quirk. Some drivers have an option to disable use of MSI. While this is a convenient workaround for the driver author, it is not good practise, and should not be emulated. @@ -350,7 +349,7 @@ for your machine. You should also check your .config to be sure you have enabled CONFIG_PCI_MSI. Then, 'lspci -t' gives the list of bridges above a device. Reading -/sys/bus/pci/devices/*/msi_bus will tell you whether MSI are enabled (1) +/sys/bus/pci/devices/*/msi_bus will tell you whether MSIs are enabled (1) or disabled (0). If 0 is found in any of the msi_bus files belonging to bridges between the PCI root and the device, MSIs are disabled. diff --git a/Documentation/SubmittingDrivers b/Documentation/SubmittingDrivers index 319baa8b60dd..36d16bbf72c6 100644 --- a/Documentation/SubmittingDrivers +++ b/Documentation/SubmittingDrivers @@ -130,7 +130,7 @@ Linux kernel master tree: ftp.??.kernel.org:/pub/linux/kernel/... ?? == your country code, such as "us", "uk", "fr", etc. - http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git + http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git Linux kernel mailing list: linux-kernel@vger.kernel.org diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches index 569f3532e138..4468ce24427c 100644 --- a/Documentation/SubmittingPatches +++ b/Documentation/SubmittingPatches @@ -303,7 +303,7 @@ patches that are being emailed around. The sign-off is a simple line at the end of the explanation for the patch, which certifies that you wrote it or otherwise have the right to -pass it on as a open-source patch. The rules are pretty simple: if you +pass it on as an open-source patch. The rules are pretty simple: if you can certify the below: Developer's Certificate of Origin 1.1 diff --git a/Documentation/block/cfq-iosched.txt b/Documentation/block/cfq-iosched.txt index e578feed6d81..6d670f570451 100644 --- a/Documentation/block/cfq-iosched.txt +++ b/Documentation/block/cfq-iosched.txt @@ -43,3 +43,74 @@ If one sets slice_idle=0 and if storage supports NCQ, CFQ internally switches to IOPS mode and starts providing fairness in terms of number of requests dispatched. Note that this mode switching takes effect only for group scheduling. For non-cgroup users nothing should change. + +CFQ IO scheduler Idling Theory +=============================== +Idling on a queue is primarily about waiting for the next request to come +on same queue after completion of a request. In this process CFQ will not +dispatch requests from other cfq queues even if requests are pending there. + +The rationale behind idling is that it can cut down on number of seeks +on rotational media. For example, if a process is doing dependent +sequential reads (next read will come on only after completion of previous +one), then not dispatching request from other queue should help as we +did not move the disk head and kept on dispatching sequential IO from +one queue. + +CFQ has following service trees and various queues are put on these trees. + + sync-idle sync-noidle async + +All cfq queues doing synchronous sequential IO go on to sync-idle tree. +On this tree we idle on each queue individually. + +All synchronous non-sequential queues go on sync-noidle tree. Also any +request which are marked with REQ_NOIDLE go on this service tree. On this +tree we do not idle on individual queues instead idle on the whole group +of queues or the tree. So if there are 4 queues waiting for IO to dispatch +we will idle only once last queue has dispatched the IO and there is +no more IO on this service tree. + +All async writes go on async service tree. There is no idling on async +queues. + +CFQ has some optimizations for SSDs and if it detects a non-rotational +media which can support higher queue depth (multiple requests at in +flight at a time), then it cuts down on idling of individual queues and +all the queues move to sync-noidle tree and only tree idle remains. This +tree idling provides isolation with buffered write queues on async tree. + +FAQ +=== +Q1. Why to idle at all on queues marked with REQ_NOIDLE. + +A1. We only do tree idle (all queues on sync-noidle tree) on queues marked + with REQ_NOIDLE. This helps in providing isolation with all the sync-idle + queues. Otherwise in presence of many sequential readers, other + synchronous IO might not get fair share of disk. + + For example, if there are 10 sequential readers doing IO and they get + 100ms each. If a REQ_NOIDLE request comes in, it will be scheduled + roughly after 1 second. If after completion of REQ_NOIDLE request we + do not idle, and after a couple of milli seconds a another REQ_NOIDLE + request comes in, again it will be scheduled after 1second. Repeat it + and notice how a workload can lose its disk share and suffer due to + multiple sequential readers. + + fsync can generate dependent IO where bunch of data is written in the + context of fsync, and later some journaling data is written. Journaling + data comes in only after fsync has finished its IO (atleast for ext4 + that seemed to be the case). Now if one decides not to idle on fsync + thread due to REQ_NOIDLE, then next journaling write will not get + scheduled for another second. A process doing small fsync, will suffer + badly in presence of multiple sequential readers. + + Hence doing tree idling on threads using REQ_NOIDLE flag on requests + provides isolation from multiple sequential readers and at the same + time we do not idle on individual threads. + +Q2. When to specify REQ_NOIDLE +A2. I would think whenever one is doing synchronous write and not expecting + more writes to be dispatched from same context soon, should be able + to specify REQ_NOIDLE on writes and that probably should work well for + most of the cases. diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index 6f3c598971fc..06eb6d957c83 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -380,7 +380,7 @@ will be charged as a new owner of it. 5.2 stat file -5.2.1 memory.stat file includes following statistics +memory.stat file includes following statistics # per-memory cgroup local status cache - # of bytes of page cache memory. @@ -438,89 +438,6 @@ Note: file_mapped is accounted only when the memory cgroup is owner of page cache.) -5.2.2 memory.vmscan_stat - -memory.vmscan_stat includes statistics information for memory scanning and -freeing, reclaiming. The statistics shows memory scanning information since -memory cgroup creation and can be reset to 0 by writing 0 as - - #echo 0 > ../memory.vmscan_stat - -This file contains following statistics. - -[param]_[file_or_anon]_pages_by_[reason]_[under_heararchy] -[param]_elapsed_ns_by_[reason]_[under_hierarchy] - -For example, - - scanned_file_pages_by_limit indicates the number of scanned - file pages at vmscan. - -Now, 3 parameters are supported - - scanned - the number of pages scanned by vmscan - rotated - the number of pages activated at vmscan - freed - the number of pages freed by vmscan - -If "rotated" is high against scanned/freed, the memcg seems busy. - -Now, 2 reason are supported - - limit - the memory cgroup's limit - system - global memory pressure + softlimit - (global memory pressure not under softlimit is not handled now) - -When under_hierarchy is added in the tail, the number indicates the -total memcg scan of its children and itself. - -elapsed_ns is a elapsed time in nanosecond. This may include sleep time -and not indicates CPU usage. So, please take this as just showing -latency. - -Here is an example. - -# cat /cgroup/memory/A/memory.vmscan_stat -scanned_pages_by_limit 9471864 -scanned_anon_pages_by_limit 6640629 -scanned_file_pages_by_limit 2831235 -rotated_pages_by_limit 4243974 -rotated_anon_pages_by_limit 3971968 -rotated_file_pages_by_limit 272006 -freed_pages_by_limit 2318492 -freed_anon_pages_by_limit 962052 -freed_file_pages_by_limit 1356440 -elapsed_ns_by_limit 351386416101 -scanned_pages_by_system 0 -scanned_anon_pages_by_system 0 -scanned_file_pages_by_system 0 -rotated_pages_by_system 0 -rotated_anon_pages_by_system 0 -rotated_file_pages_by_system 0 -freed_pages_by_system 0 -freed_anon_pages_by_system 0 -freed_file_pages_by_system 0 -elapsed_ns_by_system 0 -scanned_pages_by_limit_under_hierarchy 9471864 -scanned_anon_pages_by_limit_under_hierarchy 6640629 -scanned_file_pages_by_limit_under_hierarchy 2831235 -rotated_pages_by_limit_under_hierarchy 4243974 -rotated_anon_pages_by_limit_under_hierarchy 3971968 -rotated_file_pages_by_limit_under_hierarchy 272006 -freed_pages_by_limit_under_hierarchy 2318492 -freed_anon_pages_by_limit_under_hierarchy 962052 -freed_file_pages_by_limit_under_hierarchy 1356440 -elapsed_ns_by_limit_under_hierarchy 351386416101 -scanned_pages_by_system_under_hierarchy 0 -scanned_anon_pages_by_system_under_hierarchy 0 -scanned_file_pages_by_system_under_hierarchy 0 -rotated_pages_by_system_under_hierarchy 0 -rotated_anon_pages_by_system_under_hierarchy 0 -rotated_file_pages_by_system_under_hierarchy 0 -freed_pages_by_system_under_hierarchy 0 -freed_anon_pages_by_system_under_hierarchy 0 -freed_file_pages_by_system_under_hierarchy 0 -elapsed_ns_by_system_under_hierarchy 0 - 5.3 swappiness Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only. diff --git a/Documentation/email-clients.txt b/Documentation/email-clients.txt index a0b58e29f911..860c29a472ad 100644 --- a/Documentation/email-clients.txt +++ b/Documentation/email-clients.txt @@ -199,18 +199,16 @@ to coerce it into behaving. To beat some sense out of the internal editor, do this: -- Under account settings, composition and addressing, uncheck "Compose - messages in HTML format". - - Edit your Thunderbird config settings so that it won't use format=flowed. Go to "edit->preferences->advanced->config editor" to bring up the thunderbird's registry editor, and set "mailnews.send_plaintext_flowed" to "false". -- Enable "preformat" mode: Shft-click on the Write icon to bring up the HTML - composer, select "Preformat" from the drop-down box just under the subject - line, then close the message without saving. (This setting also applies to - the text composer, but the only control for it is in the HTML composer.) +- Disable HTML Format: Set "mail.identity.id1.compose_html" to "false". + +- Enable "preformat" mode: Set "editor.quotesPreformatted" to "true". + +- Enable UTF8: Set "prefs.converted-to-utf8" to "true". - Install the "toggle wordwrap" extension. Download the file from: https://addons.mozilla.org/thunderbird/addon/2351/ diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index c4a6e148732a..4dc465477665 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -592,3 +592,11 @@ Why: In 3.0, we can now autodetect internal 3G device and already have interface that was used by acer-wmi driver. It will replaced by information log when acer-wmi initial. Who: Lee, Chun-Yi <jlee@novell.com> + +---------------------------- +What: The XFS nodelaylog mount option +When: 3.3 +Why: The delaylog mode that has been the default since 2.6.39 has proven + stable, and the old code is in the way of additional improvements in + the log code. +Who: Christoph Hellwig <hch@lst.de> diff --git a/Documentation/filesystems/befs.txt b/Documentation/filesystems/befs.txt index 6e49c363938e..da45e6c842b8 100644 --- a/Documentation/filesystems/befs.txt +++ b/Documentation/filesystems/befs.txt @@ -27,7 +27,7 @@ His original code can still be found at: Does anyone know of a more current email address for Makoto? He doesn't respond to the address given above... -Current maintainer: Sergey S. Kostyliov <rathamahata@php4.ru> +This filesystem doesn't have a maintainer. WHAT IS THIS DRIVER? ================== diff --git a/Documentation/hwmon/max16065 b/Documentation/hwmon/max16065 index 44b4f61e04f9..c11f64a1f2ad 100644 --- a/Documentation/hwmon/max16065 +++ b/Documentation/hwmon/max16065 @@ -62,6 +62,13 @@ can be safely used to identify the chip. You will have to instantiate the devices explicitly. Please see Documentation/i2c/instantiating-devices for details. +WARNING: Do not access chip registers using the i2cdump command, and do not use +any of the i2ctools commands on a command register (0xa5 to 0xac). The chips +supported by this driver interpret any access to a command register (including +read commands) as request to execute the command in question. This may result in +power loss, board resets, and/or Flash corruption. Worst case, your board may +turn into a brick. + Sysfs entries ------------- diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index 845a191004b1..54078ed96b37 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -319,4 +319,6 @@ Code Seq#(hex) Include File Comments <mailto:thomas@winischhofer.net> 0xF4 00-1F video/mbxfb.h mbxfb <mailto:raph@8d.com> +0xF6 all LTTng Linux Trace Toolkit Next Generation + <mailto:mathieu.desnoyers@efficios.com> 0xFD all linux/dm-ioctl.h diff --git a/Documentation/kernel-docs.txt b/Documentation/kernel-docs.txt index 9a8674629a07..0e0734b509d8 100644 --- a/Documentation/kernel-docs.txt +++ b/Documentation/kernel-docs.txt @@ -620,17 +620,6 @@ (including this document itself) have been moved there, and might be more up to date than the web version. - * Name: "Linux Source Driver" - URL: http://lsd.linux.cz - Keywords: Browsing source code. - Description: "Linux Source Driver (LSD) is an application, which - can make browsing source codes of Linux kernel easier than you can - imagine. You can select between multiple versions of kernel (e.g. - 0.01, 1.0.0, 2.0.33, 2.0.34pre13, 2.0.0, 2.1.101 etc.). With LSD - you can search Linux kernel (fulltext, macros, types, functions - and variables) and LSD can generate patches for you on the fly - (files, directories or kernel)". - * Name: "Linux Kernel Source Reference" Author: Thomas Graichen. URL: http://marc.info/?l=linux-kernel&m=96446640102205&w=4 diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 78926aa2531c..854ed5ca7e3f 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -40,6 +40,7 @@ parameter is applicable: ALSA ALSA sound support is enabled. APIC APIC support is enabled. APM Advanced Power Management support is enabled. + ARM ARM architecture is enabled. AVR32 AVR32 architecture is enabled. AX25 Appropriate AX.25 support is enabled. BLACKFIN Blackfin architecture is enabled. @@ -49,6 +50,7 @@ parameter is applicable: EFI EFI Partitioning (GPT) is enabled EIDE EIDE/ATAPI support is enabled. FB The frame buffer device is enabled. + FTRACE Function tracing enabled. GCOV GCOV profiling is enabled. HW Appropriate hardware is enabled. IA-64 IA-64 architecture is enabled. @@ -69,6 +71,7 @@ parameter is applicable: Documentation/m68k/kernel-options.txt. MCA MCA bus support is enabled. MDA MDA console support is enabled. + MIPS MIPS architecture is enabled. MOUSE Appropriate mouse support is enabled. MSI Message Signaled Interrupts (PCI). MTD MTD (Memory Technology Device) support is enabled. @@ -100,7 +103,6 @@ parameter is applicable: SPARC Sparc architecture is enabled. SWSUSP Software suspend (hibernation) is enabled. SUSPEND System suspend states are enabled. - FTRACE Function tracing enabled. TPM TPM drivers are enabled. TS Appropriate touchscreen support is enabled. UMS USB Mass Storage support is enabled. @@ -115,7 +117,7 @@ parameter is applicable: X86-64 X86-64 architecture is enabled. More X86-64 boot options can be found in Documentation/x86/x86_64/boot-options.txt . - X86 Either 32bit or 64bit x86 (same as X86-32+X86-64) + X86 Either 32-bit or 64-bit x86 (same as X86-32+X86-64) XEN Xen support is enabled In addition, the following text indicates that the option: @@ -376,7 +378,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. atkbd.softrepeat= [HW] Use software keyboard repeat - autotest [IA64] + autotest [IA-64] baycom_epp= [HW,AX25] Format: <io>,<mode> @@ -681,8 +683,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted. uart[8250],mmio32,<addr>[,options] Start an early, polled-mode console on the 8250/16550 UART at the specified I/O port or MMIO address. - MMIO inter-register address stride is either 8bit (mmio) - or 32bit (mmio32). + MMIO inter-register address stride is either 8-bit + (mmio) or 32-bit (mmio32). The options are the same as for ttyS, above. earlyprintk= [X86,SH,BLACKFIN] @@ -725,7 +727,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. See Documentation/block/as-iosched.txt and Documentation/block/deadline-iosched.txt for details. - elfcorehdr= [IA64,PPC,SH,X86] + elfcorehdr= [IA-64,PPC,SH,X86] Specifies physical address of start of kernel core image elf header. Generally kexec loader will pass this option to capture kernel. @@ -791,7 +793,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. tracer at boot up. function-list is a comma separated list of functions. This list can be changed at run time by the set_ftrace_filter file in the debugfs - tracing directory. + tracing directory. ftrace_notrace=[function-list] [FTRACE] Do not trace the functions specified in @@ -829,7 +831,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. hashdist= [KNL,NUMA] Large hashes allocated during boot are distributed across NUMA nodes. Defaults on - for 64bit NUMA, off otherwise. + for 64-bit NUMA, off otherwise. Format: 0 | 1 (for off | on) hcl= [IA-64] SGI's Hardware Graph compatibility layer @@ -998,10 +1000,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. DMA. forcedac [x86_64] With this option iommu will not optimize to look - for io virtual address below 32 bit forcing dual + for io virtual address below 32-bit forcing dual address cycle on pci bus for cards supporting greater - than 32 bit addressing. The default is to look - for translation below 32 bit and if not available + than 32-bit addressing. The default is to look + for translation below 32-bit and if not available then look in the higher range. strict [Default Off] With this option on every unmap_single operation will @@ -1017,7 +1019,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. off disable Interrupt Remapping nosid disable Source ID checking - inttest= [IA64] + inttest= [IA-64] iomem= Disable strict checking of access to MMIO memory strict regions from userspace. @@ -1034,7 +1036,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. nomerge forcesac soft - pt [x86, IA64] + pt [x86, IA-64] io7= [HW] IO7 for Marvel based alpha systems See comment before marvel_specify_io7 in @@ -1165,7 +1167,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. kvm-amd.npt= [KVM,AMD] Disable nested paging (virtualized MMU) for all guests. - Default is 1 (enabled) if in 64bit or 32bit-PAE mode + Default is 1 (enabled) if in 64-bit or 32-bit PAE mode. kvm-intel.ept= [KVM,Intel] Disable extended page tables (virtualized MMU) support on capable Intel chips. @@ -1202,10 +1204,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. libata.dma=0 Disable all PATA and SATA DMA libata.dma=1 PATA and SATA Disk DMA only libata.dma=2 ATAPI (CDROM) DMA only - libata.dma=4 Compact Flash DMA only + libata.dma=4 Compact Flash DMA only Combinations also work, so libata.dma=3 enables DMA for disks and CDROMs, but not CFs. - + libata.ignore_hpa= [LIBATA] Ignore HPA limit libata.ignore_hpa=0 keep BIOS limits (default) libata.ignore_hpa=1 ignore limits, using full disk @@ -1331,7 +1333,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. ltpc= [NET] Format: <io>,<irq>,<dma> - machvec= [IA64] Force the use of a particular machine-vector + machvec= [IA-64] Force the use of a particular machine-vector (machvec) in a generic kernel. Example: machvec=hpzx1_swiotlb @@ -1348,9 +1350,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted. it is equivalent to "nosmp", which also disables the IO APIC. - max_loop= [LOOP] Maximum number of loopback devices that can - be mounted - Format: <1-256> + max_loop= [LOOP] The number of loop block devices that get + (loop.max_loop) unconditionally pre-created at init time. The default + number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead + of statically allocating a predefined number, loop + devices can be requested on-demand with the + /dev/loop-control interface. mcatest= [IA-64] @@ -1734,7 +1739,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. nointroute [IA-64] - nojitter [IA64] Disables jitter checking for ITC timers. + nojitter [IA-64] Disables jitter checking for ITC timers. no-kvmclock [X86,KVM] Disable paravirtualized KVM clock driver @@ -1800,7 +1805,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. nox2apic [X86-64,APIC] Do not enable x2APIC mode. - nptcg= [IA64] Override max number of concurrent global TLB + nptcg= [IA-64] Override max number of concurrent global TLB purges which is reported from either PAL_VM_SUMMARY or SAL PALO. @@ -2077,13 +2082,16 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Format: { parport<nr> | timid | 0 } See also Documentation/parport.txt. - pmtmr= [X86] Manual setup of pmtmr I/O Port. + pmtmr= [X86] Manual setup of pmtmr I/O Port. Override pmtimer IOPort with a hex value. e.g. pmtmr=0x508 - pnp.debug [PNP] - Enable PNP debug messages. This depends on the - CONFIG_PNP_DEBUG_MESSAGES option. + pnp.debug=1 [PNP] + Enable PNP debug messages (depends on the + CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time + via /sys/module/pnp/parameters/debug. We always show + current resource usage; turning this on also shows + possible settings and some assignment information. pnpacpi= [ACPI] { off } @@ -2635,6 +2643,16 @@ bytes respectively. Such letter suffixes can also be entirely omitted. medium is write-protected). Example: quirks=0419:aaf5:rl,0421:0433:rc + user_debug= [KNL,ARM] + Format: <int> + See arch/arm/Kconfig.debug help text. + 1 - undefined instruction events + 2 - system calls + 4 - invalid data aborts + 8 - SIGSEGV faults + 16 - SIGBUS faults + Example: user_debug=31 + userpte= [X86] Flags controlling user PTE allocations. diff --git a/Documentation/networking/dmfe.txt b/Documentation/networking/dmfe.txt index 8006c227fda2..25320bf19c86 100644 --- a/Documentation/networking/dmfe.txt +++ b/Documentation/networking/dmfe.txt @@ -1,3 +1,5 @@ +Note: This driver doesn't have a maintainer. + Davicom DM9102(A)/DM9132/DM9801 fast ethernet driver for Linux. This program is free software; you can redistribute it and/or @@ -55,7 +57,6 @@ Test and make sure PCI latency is now correct for all cases. Authors: Sten Wang <sten_wang@davicom.com.tw > : Original Author -Tobias Ringstrom <tori@unhappy.mine.nu> : Current Maintainer Contributors: diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index f2716df05601..98c8d4229f0a 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -992,7 +992,7 @@ bindv6only - BOOLEAN TRUE: disable IPv4-mapped address feature FALSE: enable IPv4-mapped address feature - Default: FALSE (as specified in RFC2553bis) + Default: FALSE (as specified in RFC3493) IPv6 Fragmentation: diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt index 4ce5450ab6e8..6066e3a6b9a9 100644 --- a/Documentation/power/runtime_pm.txt +++ b/Documentation/power/runtime_pm.txt @@ -431,8 +431,7 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h: void pm_runtime_irq_safe(struct device *dev); - set the power.irq_safe flag for the device, causing the runtime-PM - suspend and resume callbacks (but not the idle callback) to be invoked - with interrupts disabled + callbacks to be invoked with interrupts off void pm_runtime_mark_last_busy(struct device *dev); - set the power.last_busy field to the current time diff --git a/Documentation/ramoops.txt b/Documentation/ramoops.txt new file mode 100644 index 000000000000..8fb1ba7fe7bf --- /dev/null +++ b/Documentation/ramoops.txt @@ -0,0 +1,76 @@ +Ramoops oops/panic logger +========================= + +Sergiu Iordache <sergiu@chromium.org> + +Updated: 8 August 2011 + +0. Introduction + +Ramoops is an oops/panic logger that writes its logs to RAM before the system +crashes. It works by logging oopses and panics in a circular buffer. Ramoops +needs a system with persistent RAM so that the content of that area can +survive after a restart. + +1. Ramoops concepts + +Ramoops uses a predefined memory area to store the dump. The start and size of +the memory area are set using two variables: + * "mem_address" for the start + * "mem_size" for the size. The memory size will be rounded down to a + power of two. + +The memory area is divided into "record_size" chunks (also rounded down to +power of two) and each oops/panic writes a "record_size" chunk of +information. + +Dumping both oopses and panics can be done by setting 1 in the "dump_oops" +variable while setting 0 in that variable dumps only the panics. + +The module uses a counter to record multiple dumps but the counter gets reset +on restart (i.e. new dumps after the restart will overwrite old ones). + +2. Setting the parameters + +Setting the ramoops parameters can be done in 2 different manners: + 1. Use the module parameters (which have the names of the variables described + as before). + 2. Use a platform device and set the platform data. The parameters can then + be set through that platform data. An example of doing that is: + +#include <linux/ramoops.h> +[...] + +static struct ramoops_platform_data ramoops_data = { + .mem_size = <...>, + .mem_address = <...>, + .record_size = <...>, + .dump_oops = <...>, +}; + +static struct platform_device ramoops_dev = { + .name = "ramoops", + .dev = { + .platform_data = &ramoops_data, + }, +}; + +[... inside a function ...] +int ret; + +ret = platform_device_register(&ramoops_dev); +if (ret) { + printk(KERN_ERR "unable to register platform device\n"); + return ret; +} + +3. Dump format + +The data dump begins with a header, currently defined as "====" followed by a +timestamp and a new line. The dump then continues with the actual data. + +4. Reading the data + +The dump data can be read from memory (through /dev/mem or other means). +Getting the module parameters, which are needed in order to parse the data, can +be done through /sys/module/ramoops/parameters/* . diff --git a/Documentation/virtual/00-INDEX b/Documentation/virtual/00-INDEX index fe0251c4cfb7..8e601991d91c 100644 --- a/Documentation/virtual/00-INDEX +++ b/Documentation/virtual/00-INDEX @@ -8,3 +8,6 @@ lguest/ - Extremely simple hypervisor for experimental/educational use. uml/ - User Mode Linux, builds/runs Linux kernel as a userspace program. +virtio.txt + - Text version of draft virtio spec. + See http://ozlabs.org/~rusty/virtio-spec diff --git a/Documentation/virtual/lguest/lguest.c b/Documentation/virtual/lguest/lguest.c index 043bd7df3139..d928c134dee6 100644 --- a/Documentation/virtual/lguest/lguest.c +++ b/Documentation/virtual/lguest/lguest.c @@ -1996,6 +1996,9 @@ int main(int argc, char *argv[]) /* We use a simple helper to copy the arguments separated by spaces. */ concat((char *)(boot + 1), argv+optind+2); + /* Set kernel alignment to 16M (CONFIG_PHYSICAL_ALIGN) */ + boot->hdr.kernel_alignment = 0x1000000; + /* Boot protocol version: 2.07 supports the fields for lguest. */ boot->hdr.version = 0x207; diff --git a/Documentation/virtual/virtio-spec.txt b/Documentation/virtual/virtio-spec.txt new file mode 100644 index 000000000000..a350ae135b8c --- /dev/null +++ b/Documentation/virtual/virtio-spec.txt @@ -0,0 +1,2200 @@ +[Generated file: see http://ozlabs.org/~rusty/virtio-spec/] +Virtio PCI Card Specification +v0.9.1 DRAFT +- + +Rusty Russell <rusty@rustcorp.com.au>IBM Corporation (Editor) + +2011 August 1. + +Purpose and Description + +This document describes the specifications of the “virtio” family +of PCI[LaTeX Command: nomenclature] devices. These are devices +are found in virtual environments[LaTeX Command: nomenclature], +yet by design they are not all that different from physical PCI +devices, and this document treats them as such. This allows the +guest to use standard PCI drivers and discovery mechanisms. + +The purpose of virtio and this specification is that virtual +environments and guests should have a straightforward, efficient, +standard and extensible mechanism for virtual devices, rather +than boutique per-environment or per-OS mechanisms. + + Straightforward: Virtio PCI devices use normal PCI mechanisms + of interrupts and DMA which should be familiar to any device + driver author. There is no exotic page-flipping or COW + mechanism: it's just a PCI device.[footnote: +This lack of page-sharing implies that the implementation of the +device (e.g. the hypervisor or host) needs full access to the +guest memory. Communication with untrusted parties (i.e. +inter-guest communication) requires copying. +] + + Efficient: Virtio PCI devices consist of rings of descriptors + for input and output, which are neatly separated to avoid cache + effects from both guest and device writing to the same cache + lines. + + Standard: Virtio PCI makes no assumptions about the environment + in which it operates, beyond supporting PCI. In fact the virtio + devices specified in the appendices do not require PCI at all: + they have been implemented on non-PCI buses.[footnote: +The Linux implementation further separates the PCI virtio code +from the specific virtio drivers: these drivers are shared with +the non-PCI implementations (currently lguest and S/390). +] + + Extensible: Virtio PCI devices contain feature bits which are + acknowledged by the guest operating system during device setup. + This allows forwards and backwards compatibility: the device + offers all the features it knows about, and the driver + acknowledges those it understands and wishes to use. + + Virtqueues + +The mechanism for bulk data transport on virtio PCI devices is +pretentiously called a virtqueue. Each device can have zero or +more virtqueues: for example, the network device has one for +transmit and one for receive. + +Each virtqueue occupies two or more physically-contiguous pages +(defined, for the purposes of this specification, as 4096 bytes), +and consists of three parts: + + ++-------------------+-----------------------------------+-----------+ +| Descriptor Table | Available Ring (padding) | Used Ring | ++-------------------+-----------------------------------+-----------+ + + +When the driver wants to send buffers to the device, it puts them +in one or more slots in the descriptor table, and writes the +descriptor indices into the available ring. It then notifies the +device. When the device has finished with the buffers, it writes +the descriptors into the used ring, and sends an interrupt. + +Specification + + PCI Discovery + +Any PCI device with Vendor ID 0x1AF4, and Device ID 0x1000 +through 0x103F inclusive is a virtio device[footnote: +The actual value within this range is ignored +]. The device must also have a Revision ID of 0 to match this +specification. + +The Subsystem Device ID indicates which virtio device is +supported by the device. The Subsystem Vendor ID should reflect +the PCI Vendor ID of the environment (it's currently only used +for informational purposes by the guest). + + ++----------------------+--------------------+---------------+ +| Subsystem Device ID | Virtio Device | Specification | ++----------------------+--------------------+---------------+ ++----------------------+--------------------+---------------+ +| 1 | network card | Appendix C | ++----------------------+--------------------+---------------+ +| 2 | block device | Appendix D | ++----------------------+--------------------+---------------+ +| 3 | console | Appendix E | ++----------------------+--------------------+---------------+ +| 4 | entropy source | Appendix F | ++----------------------+--------------------+---------------+ +| 5 | memory ballooning | Appendix G | ++----------------------+--------------------+---------------+ +| 6 | ioMemory | - | ++----------------------+--------------------+---------------+ +| 9 | 9P transport | - | ++----------------------+--------------------+---------------+ + + + Device Configuration + +To configure the device, we use the first I/O region of the PCI +device. This contains a virtio header followed by a +device-specific region. + +There may be different widths of accesses to the I/O region; the “ +natural” access method for each field in the virtio header must +be used (i.e. 32-bit accesses for 32-bit fields, etc), but the +device-specific region can be accessed using any width accesses, +and should obtain the same results. + +Note that this is possible because while the virtio header is PCI +(i.e. little) endian, the device-specific region is encoded in +the native endian of the guest (where such distinction is +applicable). + + Device Initialization Sequence + +We start with an overview of device initialization, then expand +on the details of the device and how each step is preformed. + + Reset the device. This is not required on initial start up. + + The ACKNOWLEDGE status bit is set: we have noticed the device. + + The DRIVER status bit is set: we know how to drive the device. + + Device-specific setup, including reading the Device Feature + Bits, discovery of virtqueues for the device, optional MSI-X + setup, and reading and possibly writing the virtio + configuration space. + + The subset of Device Feature Bits understood by the driver is + written to the device. + + The DRIVER_OK status bit is set. + + The device can now be used (ie. buffers added to the + virtqueues)[footnote: +Historically, drivers have used the device before steps 5 and 6. +This is only allowed if the driver does not use any features +which would alter this early use of the device. +] + +If any of these steps go irrecoverably wrong, the guest should +set the FAILED status bit to indicate that it has given up on the +device (it can reset the device later to restart if desired). + +We now cover the fields required for general setup in detail. + + Virtio Header + +The virtio header looks as follows: + + ++------------++---------------------+---------------------+----------+--------+---------+---------+---------+--------+ +| Bits || 32 | 32 | 32 | 16 | 16 | 16 | 8 | 8 | ++------------++---------------------+---------------------+----------+--------+---------+---------+---------+--------+ +| Read/Write || R | R+W | R+W | R | R+W | R+W | R+W | R | ++------------++---------------------+---------------------+----------+--------+---------+---------+---------+--------+ +| Purpose || Device | Guest | Queue | Queue | Queue | Queue | Device | ISR | +| || Features bits 0:31 | Features bits 0:31 | Address | Size | Select | Notify | Status | Status | ++------------++---------------------+---------------------+----------+--------+---------+---------+---------+--------+ + + +If MSI-X is enabled for the device, two additional fields +immediately follow this header: + + ++------------++----------------+--------+ +| Bits || 16 | 16 | + +----------------+--------+ ++------------++----------------+--------+ +| Read/Write || R+W | R+W | ++------------++----------------+--------+ +| Purpose || Configuration | Queue | +| (MSI-X) || Vector | Vector | ++------------++----------------+--------+ + + +Finally, if feature bits (VIRTIO_F_FEATURES_HI) this is +immediately followed by two additional fields: + + ++------------++----------------------+---------------------- +| Bits || 32 | 32 ++------------++----------------------+---------------------- +| Read/Write || R | R+W ++------------++----------------------+---------------------- +| Purpose || Device | Guest +| || Features bits 32:63 | Features bits 32:63 ++------------++----------------------+---------------------- + + +Immediately following these general headers, there may be +device-specific headers: + + ++------------++--------------------+ +| Bits || Device Specific | + +--------------------+ ++------------++--------------------+ +| Read/Write || Device Specific | ++------------++--------------------+ +| Purpose || Device Specific... | +| || | ++------------++--------------------+ + + + Device Status + +The Device Status field is updated by the guest to indicate its +progress. This provides a simple low-level diagnostic: it's most +useful to imagine them hooked up to traffic lights on the console +indicating the status of each device. + +The device can be reset by writing a 0 to this field, otherwise +at least one bit should be set: + + ACKNOWLEDGE (1) Indicates that the guest OS has found the + device and recognized it as a valid virtio device. + + DRIVER (2) Indicates that the guest OS knows how to drive the + device. Under Linux, drivers can be loadable modules so there + may be a significant (or infinite) delay before setting this + bit. + + DRIVER_OK (3) Indicates that the driver is set up and ready to + drive the device. + + FAILED (8) Indicates that something went wrong in the guest, + and it has given up on the device. This could be an internal + error, or the driver didn't like the device for some reason, or + even a fatal error during device operation. The device must be + reset before attempting to re-initialize. + + Feature Bits + +The least significant 31 bits of the first configuration field +indicates the features that the device supports (the high bit is +reserved, and will be used to indicate the presence of future +feature bits elsewhere). If more than 31 feature bits are +supported, the device indicates so by setting feature bit 31 (see +[cha:Reserved-Feature-Bits]). The bits are allocated as follows: + + 0 to 23 Feature bits for the specific device type + + 24 to 40 Feature bits reserved for extensions to the queue and + feature negotiation mechanisms + + 41 to 63 Feature bits reserved for future extensions + +For example, feature bit 0 for a network device (i.e. Subsystem +Device ID 1) indicates that the device supports checksumming of +packets. + +The feature bits are negotiated: the device lists all the +features it understands in the Device Features field, and the +guest writes the subset that it understands into the Guest +Features field. The only way to renegotiate is to reset the +device. + +In particular, new fields in the device configuration header are +indicated by offering a feature bit, so the guest can check +before accessing that part of the configuration space. + +This allows for forwards and backwards compatibility: if the +device is enhanced with a new feature bit, older guests will not +write that feature bit back to the Guest Features field and it +can go into backwards compatibility mode. Similarly, if a guest +is enhanced with a feature that the device doesn't support, it +will not see that feature bit in the Device Features field and +can go into backwards compatibility mode (or, for poor +implementations, set the FAILED Device Status bit). + +Access to feature bits 32 to 63 is enabled by Guest by setting +feature bit 31. If this bit is unset, Device must assume that all +feature bits > 31 are unset. + + Configuration/Queue Vectors + +When MSI-X capability is present and enabled in the device +(through standard PCI configuration space) 4 bytes at byte offset +20 are used to map configuration change and queue interrupts to +MSI-X vectors. In this case, the ISR Status field is unused, and +device specific configuration starts at byte offset 24 in virtio +header structure. When MSI-X capability is not enabled, device +specific configuration starts at byte offset 20 in virtio header. + +Writing a valid MSI-X Table entry number, 0 to 0x7FF, to one of +Configuration/Queue Vector registers, maps interrupts triggered +by the configuration change/selected queue events respectively to +the corresponding MSI-X vector. To disable interrupts for a +specific event type, unmap it by writing a special NO_VECTOR +value: + +/* Vector value used to disable MSI for queue */ + +#define VIRTIO_MSI_NO_VECTOR 0xffff + +Reading these registers returns vector mapped to a given event, +or NO_VECTOR if unmapped. All queue and configuration change +events are unmapped by default. + +Note that mapping an event to vector might require allocating +internal device resources, and might fail. Devices report such +failures by returning the NO_VECTOR value when the relevant +Vector field is read. After mapping an event to vector, the +driver must verify success by reading the Vector field value: on +success, the previously written value is returned, and on +failure, NO_VECTOR is returned. If a mapping failure is detected, +the driver can retry mapping with fewervectors, or disable MSI-X. + + Virtqueue Configuration + +As a device can have zero or more virtqueues for bulk data +transport (for example, the network driver has two), the driver +needs to configure them as part of the device-specific +configuration. + +This is done as follows, for each virtqueue a device has: + + Write the virtqueue index (first queue is 0) to the Queue + Select field. + + Read the virtqueue size from the Queue Size field, which is + always a power of 2. This controls how big the virtqueue is + (see below). If this field is 0, the virtqueue does not exist. + + Allocate and zero virtqueue in contiguous physical memory, on a + 4096 byte alignment. Write the physical address, divided by + 4096 to the Queue Address field.[footnote: +The 4096 is based on the x86 page size, but it's also large +enough to ensure that the separate parts of the virtqueue are on +separate cache lines. +] + + Optionally, if MSI-X capability is present and enabled on the + device, select a vector to use to request interrupts triggered + by virtqueue events. Write the MSI-X Table entry number + corresponding to this vector in Queue Vector field. Read the + Queue Vector field: on success, previously written value is + returned; on failure, NO_VECTOR value is returned. + +The Queue Size field controls the total number of bytes required +for the virtqueue according to the following formula: + +#define ALIGN(x) (((x) + 4095) & ~4095) + +static inline unsigned vring_size(unsigned int qsz) + +{ + + return ALIGN(sizeof(struct vring_desc)*qsz + sizeof(u16)*(2 ++ qsz)) + + + ALIGN(sizeof(struct vring_used_elem)*qsz); + +} + +This currently wastes some space with padding, but also allows +future extensions. The virtqueue layout structure looks like this +(qsz is the Queue Size field, which is a variable, so this code +won't compile): + +struct vring { + + /* The actual descriptors (16 bytes each) */ + + struct vring_desc desc[qsz]; + + + + /* A ring of available descriptor heads with free-running +index. */ + + struct vring_avail avail; + + + + // Padding to the next 4096 boundary. + + char pad[]; + + + + // A ring of used descriptor heads with free-running index. + + struct vring_used used; + +}; + + A Note on Virtqueue Endianness + +Note that the endian of these fields and everything else in the +virtqueue is the native endian of the guest, not little-endian as +PCI normally is. This makes for simpler guest code, and it is +assumed that the host already has to be deeply aware of the guest +endian so such an “endian-aware” device is not a significant +issue. + + Descriptor Table + +The descriptor table refers to the buffers the guest is using for +the device. The addresses are physical addresses, and the buffers +can be chained via the next field. Each descriptor describes a +buffer which is read-only or write-only, but a chain of +descriptors can contain both read-only and write-only buffers. + +No descriptor chain may be more than 2^32 bytes long in total.struct vring_desc { + + /* Address (guest-physical). */ + + u64 addr; + + /* Length. */ + + u32 len; + +/* This marks a buffer as continuing via the next field. */ + +#define VRING_DESC_F_NEXT 1 + +/* This marks a buffer as write-only (otherwise read-only). */ + +#define VRING_DESC_F_WRITE 2 + +/* This means the buffer contains a list of buffer descriptors. +*/ + +#define VRING_DESC_F_INDIRECT 4 + + /* The flags as indicated above. */ + + u16 flags; + + /* Next field if flags & NEXT */ + + u16 next; + +}; + +The number of descriptors in the table is specified by the Queue +Size field for this virtqueue. + + <sub:Indirect-Descriptors>Indirect Descriptors + +Some devices benefit by concurrently dispatching a large number +of large requests. The VIRTIO_RING_F_INDIRECT_DESC feature can be +used to allow this (see [cha:Reserved-Feature-Bits]). To increase +ring capacity it is possible to store a table of indirect +descriptors anywhere in memory, and insert a descriptor in main +virtqueue (with flags&INDIRECT on) that refers to memory buffer +containing this indirect descriptor table; fields addr and len +refer to the indirect table address and length in bytes, +respectively. The indirect table layout structure looks like this +(len is the length of the descriptor that refers to this table, +which is a variable, so this code won't compile): + +struct indirect_descriptor_table { + + /* The actual descriptors (16 bytes each) */ + + struct vring_desc desc[len / 16]; + +}; + +The first indirect descriptor is located at start of the indirect +descriptor table (index 0), additional indirect descriptors are +chained by next field. An indirect descriptor without next field +(with flags&NEXT off) signals the end of the indirect descriptor +table, and transfers control back to the main virtqueue. An +indirect descriptor can not refer to another indirect descriptor +table (flags&INDIRECT must be off). A single indirect descriptor +table can include both read-only and write-only descriptors; +write-only flag (flags&WRITE) in the descriptor that refers to it +is ignored. + + Available Ring + +The available ring refers to what descriptors we are offering the +device: it refers to the head of a descriptor chain. The “flags” +field is currently 0 or 1: 1 indicating that we do not need an +interrupt when the device consumes a descriptor from the +available ring. Alternatively, the guest can ask the device to +delay interrupts until an entry with an index specified by the “ +used_event” field is written in the used ring (equivalently, +until the idx field in the used ring will reach the value +used_event + 1). The method employed by the device is controlled +by the VIRTIO_RING_F_EVENT_IDX feature bit (see [cha:Reserved-Feature-Bits] +). This interrupt suppression is merely an optimization; it may +not suppress interrupts entirely. + +The “idx” field indicates where we would put the next descriptor +entry (modulo the ring size). This starts at 0, and increases. + +struct vring_avail { + +#define VRING_AVAIL_F_NO_INTERRUPT 1 + + u16 flags; + + u16 idx; + + u16 ring[qsz]; /* qsz is the Queue Size field read from device +*/ + + u16 used_event; + +}; + + Used Ring + +The used ring is where the device returns buffers once it is done +with them. The flags field can be used by the device to hint that +no notification is necessary when the guest adds to the available +ring. Alternatively, the “avail_event” field can be used by the +device to hint that no notification is necessary until an entry +with an index specified by the “avail_event” is written in the +available ring (equivalently, until the idx field in the +available ring will reach the value avail_event + 1). The method +employed by the device is controlled by the guest through the +VIRTIO_RING_F_EVENT_IDX feature bit (see [cha:Reserved-Feature-Bits] +). [footnote: +These fields are kept here because this is the only part of the +virtqueue written by the device +]. + +Each entry in the ring is a pair: the head entry of the +descriptor chain describing the buffer (this matches an entry +placed in the available ring by the guest earlier), and the total +of bytes written into the buffer. The latter is extremely useful +for guests using untrusted buffers: if you do not know exactly +how much has been written by the device, you usually have to zero +the buffer to ensure no data leakage occurs. + +/* u32 is used here for ids for padding reasons. */ + +struct vring_used_elem { + + /* Index of start of used descriptor chain. */ + + u32 id; + + /* Total length of the descriptor chain which was used +(written to) */ + + u32 len; + +}; + + + +struct vring_used { + +#define VRING_USED_F_NO_NOTIFY 1 + + u16 flags; + + u16 idx; + + struct vring_used_elem ring[qsz]; + + u16 avail_event; + +}; + + Helpers for Managing Virtqueues + +The Linux Kernel Source code contains the definitions above and +helper routines in a more usable form, in +include/linux/virtio_ring.h. This was explicitly licensed by IBM +and Red Hat under the (3-clause) BSD license so that it can be +freely used by all other projects, and is reproduced (with slight +variation to remove Linux assumptions) in Appendix A. + + Device Operation + +There are two parts to device operation: supplying new buffers to +the device, and processing used buffers from the device. As an +example, the virtio network device has two virtqueues: the +transmit virtqueue and the receive virtqueue. The driver adds +outgoing (read-only) packets to the transmit virtqueue, and then +frees them after they are used. Similarly, incoming (write-only) +buffers are added to the receive virtqueue, and processed after +they are used. + + Supplying Buffers to The Device + +Actual transfer of buffers from the guest OS to the device +operates as follows: + + Place the buffer(s) into free descriptor(s). + + If there are no free descriptors, the guest may choose to + notify the device even if notifications are suppressed (to + reduce latency).[footnote: +The Linux drivers do this only for read-only buffers: for +write-only buffers, it is assumed that the driver is merely +trying to keep the receive buffer ring full, and no notification +of this expected condition is necessary. +] + + Place the id of the buffer in the next ring entry of the + available ring. + + The steps (1) and (2) may be performed repeatedly if batching + is possible. + + A memory barrier should be executed to ensure the device sees + the updated descriptor table and available ring before the next + step. + + The available “idx” field should be increased by the number of + entries added to the available ring. + + A memory barrier should be executed to ensure that we update + the idx field before checking for notification suppression. + + If notifications are not suppressed, the device should be + notified of the new buffers. + +Note that the above code does not take precautions against the +available ring buffer wrapping around: this is not possible since +the ring buffer is the same size as the descriptor table, so step +(1) will prevent such a condition. + +In addition, the maximum queue size is 32768 (it must be a power +of 2 which fits in 16 bits), so the 16-bit “idx” value can always +distinguish between a full and empty buffer. + +Here is a description of each stage in more detail. + + Placing Buffers Into The Descriptor Table + +A buffer consists of zero or more read-only physically-contiguous +elements followed by zero or more physically-contiguous +write-only elements (it must have at least one element). This +algorithm maps it into the descriptor table: + + for each buffer element, b: + + Get the next free descriptor table entry, d + + Set d.addr to the physical address of the start of b + + Set d.len to the length of b. + + If b is write-only, set d.flags to VRING_DESC_F_WRITE, + otherwise 0. + + If there is a buffer element after this: + + Set d.next to the index of the next free descriptor element. + + Set the VRING_DESC_F_NEXT bit in d.flags. + +In practice, the d.next fields are usually used to chain free +descriptors, and a separate count kept to check there are enough +free descriptors before beginning the mappings. + + Updating The Available Ring + +The head of the buffer we mapped is the first d in the algorithm +above. A naive implementation would do the following: + +avail->ring[avail->idx % qsz] = head; + +However, in general we can add many descriptors before we update +the “idx” field (at which point they become visible to the +device), so we keep a counter of how many we've added: + +avail->ring[(avail->idx + added++) % qsz] = head; + + Updating The Index Field + +Once the idx field of the virtqueue is updated, the device will +be able to access the descriptor entries we've created and the +memory they refer to. This is why a memory barrier is generally +used before the idx update, to ensure it sees the most up-to-date +copy. + +The idx field always increments, and we let it wrap naturally at +65536: + +avail->idx += added; + + <sub:Notifying-The-Device>Notifying The Device + +Device notification occurs by writing the 16-bit virtqueue index +of this virtqueue to the Queue Notify field of the virtio header +in the first I/O region of the PCI device. This can be expensive, +however, so the device can suppress such notifications if it +doesn't need them. We have to be careful to expose the new idx +value before checking the suppression flag: it's OK to notify +gratuitously, but not to omit a required notification. So again, +we use a memory barrier here before reading the flags or the +avail_event field. + +If the VIRTIO_F_RING_EVENT_IDX feature is not negotiated, and if +the VRING_USED_F_NOTIFY flag is not set, we go ahead and write to +the PCI configuration space. + +If the VIRTIO_F_RING_EVENT_IDX feature is negotiated, we read the +avail_event field in the available ring structure. If the +available index crossed_the avail_event field value since the +last notification, we go ahead and write to the PCI configuration +space. The avail_event field wraps naturally at 65536 as well: + +(u16)(new_idx - avail_event - 1) < (u16)(new_idx - old_idx) + + <sub:Receiving-Used-Buffers>Receiving Used Buffers From The + Device + +Once the device has used a buffer (read from or written to it, or +parts of both, depending on the nature of the virtqueue and the +device), it sends an interrupt, following an algorithm very +similar to the algorithm used for the driver to send the device a +buffer: + + Write the head descriptor number to the next field in the used + ring. + + Update the used ring idx. + + Determine whether an interrupt is necessary: + + If the VIRTIO_F_RING_EVENT_IDX feature is not negotiated: check + if f the VRING_AVAIL_F_NO_INTERRUPT flag is not set in avail- + >flags + + If the VIRTIO_F_RING_EVENT_IDX feature is negotiated: check + whether the used index crossed the used_event field value + since the last update. The used_event field wraps naturally + at 65536 as well:(u16)(new_idx - used_event - 1) < (u16)(new_idx - old_idx) + + If an interrupt is necessary: + + If MSI-X capability is disabled: + + Set the lower bit of the ISR Status field for the device. + + Send the appropriate PCI interrupt for the device. + + If MSI-X capability is enabled: + + Request the appropriate MSI-X interrupt message for the + device, Queue Vector field sets the MSI-X Table entry + number. + + If Queue Vector field value is NO_VECTOR, no interrupt + message is requested for this event. + +The guest interrupt handler should: + + If MSI-X capability is disabled: read the ISR Status field, + which will reset it to zero. If the lower bit is zero, the + interrupt was not for this device. Otherwise, the guest driver + should look through the used rings of each virtqueue for the + device, to see if any progress has been made by the device + which requires servicing. + + If MSI-X capability is enabled: look through the used rings of + each virtqueue mapped to the specific MSI-X vector for the + device, to see if any progress has been made by the device + which requires servicing. + +For each ring, guest should then disable interrupts by writing +VRING_AVAIL_F_NO_INTERRUPT flag in avail structure, if required. +It can then process used ring entries finally enabling interrupts +by clearing the VRING_AVAIL_F_NO_INTERRUPT flag or updating the +EVENT_IDX field in the available structure, Guest should then +execute a memory barrier, and then recheck the ring empty +condition. This is necessary to handle the case where, after the +last check and before enabling interrupts, an interrupt has been +suppressed by the device: + +vring_disable_interrupts(vq); + +for (;;) { + + if (vq->last_seen_used != vring->used.idx) { + + vring_enable_interrupts(vq); + + mb(); + + if (vq->last_seen_used != vring->used.idx) + + break; + + } + + struct vring_used_elem *e = +vring.used->ring[vq->last_seen_used%vsz]; + + process_buffer(e); + + vq->last_seen_used++; + +} + + Dealing With Configuration Changes + +Some virtio PCI devices can change the device configuration +state, as reflected in the virtio header in the PCI configuration +space. In this case: + + If MSI-X capability is disabled: an interrupt is delivered and + the second highest bit is set in the ISR Status field to + indicate that the driver should re-examine the configuration + space.Note that a single interrupt can indicate both that one + or more virtqueue has been used and that the configuration + space has changed: even if the config bit is set, virtqueues + must be scanned. + + If MSI-X capability is enabled: an interrupt message is + requested. The Configuration Vector field sets the MSI-X Table + entry number to use. If Configuration Vector field value is + NO_VECTOR, no interrupt message is requested for this event. + +Creating New Device Types + +Various considerations are necessary when creating a new device +type: + + How Many Virtqueues? + +It is possible that a very simple device will operate entirely +through its configuration space, but most will need at least one +virtqueue in which it will place requests. A device with both +input and output (eg. console and network devices described here) +need two queues: one which the driver fills with buffers to +receive input, and one which the driver places buffers to +transmit output. + + What Configuration Space Layout? + +Configuration space is generally used for rarely-changing or +initialization-time parameters. But it is a limited resource, so +it might be better to use a virtqueue to update configuration +information (the network device does this for filtering, +otherwise the table in the config space could potentially be very +large). + +Note that this space is generally the guest's native endian, +rather than PCI's little-endian. + + What Device Number? + +Currently device numbers are assigned quite freely: a simple +request mail to the author of this document or the Linux +virtualization mailing list[footnote: + +https://lists.linux-foundation.org/mailman/listinfo/virtualization +] will be sufficient to secure a unique one. + +Meanwhile for experimental drivers, use 65535 and work backwards. + + How many MSI-X vectors? + +Using the optional MSI-X capability devices can speed up +interrupt processing by removing the need to read ISR Status +register by guest driver (which might be an expensive operation), +reducing interrupt sharing between devices and queues within the +device, and handling interrupts from multiple CPUs. However, some +systems impose a limit (which might be as low as 256) on the +total number of MSI-X vectors that can be allocated to all +devices. Devices and/or device drivers should take this into +account, limiting the number of vectors used unless the device is +expected to cause a high volume of interrupts. Devices can +control the number of vectors used by limiting the MSI-X Table +Size or not presenting MSI-X capability in PCI configuration +space. Drivers can control this by mapping events to as small +number of vectors as possible, or disabling MSI-X capability +altogether. + + Message Framing + +The descriptors used for a buffer should not effect the semantics +of the message, except for the total length of the buffer. For +example, a network buffer consists of a 10 byte header followed +by the network packet. Whether this is presented in the ring +descriptor chain as (say) a 10 byte buffer and a 1514 byte +buffer, or a single 1524 byte buffer, or even three buffers, +should have no effect. + +In particular, no implementation should use the descriptor +boundaries to determine the size of any header in a request.[footnote: +The current qemu device implementations mistakenly insist that +the first descriptor cover the header in these cases exactly, so +a cautious driver should arrange it so. +] + + Device Improvements + +Any change to configuration space, or new virtqueues, or +behavioural changes, should be indicated by negotiation of a new +feature bit. This establishes clarity[footnote: +Even if it does mean documenting design or implementation +mistakes! +] and avoids future expansion problems. + +Clusters of functionality which are always implemented together +can use a single bit, but if one feature makes sense without the +others they should not be gratuitously grouped together to +conserve feature bits. We can always extend the spec when the +first person needs more than 24 feature bits for their device. + +[LaTeX Command: printnomenclature] + +Appendix A: virtio_ring.h + +#ifndef VIRTIO_RING_H + +#define VIRTIO_RING_H + +/* An interface for efficient virtio implementation. + + * + + * This header is BSD licensed so anyone can use the definitions + + * to implement compatible drivers/servers. + + * + + * Copyright 2007, 2009, IBM Corporation + + * Copyright 2011, Red Hat, Inc + + * All rights reserved. + + * + + * Redistribution and use in source and binary forms, with or +without + + * modification, are permitted provided that the following +conditions + + * are met: + + * 1. Redistributions of source code must retain the above +copyright + + * notice, this list of conditions and the following +disclaimer. + + * 2. Redistributions in binary form must reproduce the above +copyright + + * notice, this list of conditions and the following +disclaimer in the + + * documentation and/or other materials provided with the +distribution. + + * 3. Neither the name of IBM nor the names of its contributors + + * may be used to endorse or promote products derived from +this software + + * without specific prior written permission. + + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND +CONTRIBUTORS ``AS IS'' AND + + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED +TO, THE + + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A +PARTICULAR PURPOSE + + * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE +LIABLE + + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL + + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS + + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) + + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT + + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING +IN ANY WAY + + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF + + * SUCH DAMAGE. + + */ + + + +/* This marks a buffer as continuing via the next field. */ + +#define VRING_DESC_F_NEXT 1 + +/* This marks a buffer as write-only (otherwise read-only). */ + +#define VRING_DESC_F_WRITE 2 + + + +/* The Host uses this in used->flags to advise the Guest: don't +kick me + + * when you add a buffer. It's unreliable, so it's simply an + + * optimization. Guest will still kick if it's out of buffers. +*/ + +#define VRING_USED_F_NO_NOTIFY 1 + +/* The Guest uses this in avail->flags to advise the Host: don't + + * interrupt me when you consume a buffer. It's unreliable, so +it's + + * simply an optimization. */ + +#define VRING_AVAIL_F_NO_INTERRUPT 1 + + + +/* Virtio ring descriptors: 16 bytes. + + * These can chain together via "next". */ + +struct vring_desc { + + /* Address (guest-physical). */ + + uint64_t addr; + + /* Length. */ + + uint32_t len; + + /* The flags as indicated above. */ + + uint16_t flags; + + /* We chain unused descriptors via this, too */ + + uint16_t next; + +}; + + + +struct vring_avail { + + uint16_t flags; + + uint16_t idx; + + uint16_t ring[]; + + uint16_t used_event; + +}; + + + +/* u32 is used here for ids for padding reasons. */ + +struct vring_used_elem { + + /* Index of start of used descriptor chain. */ + + uint32_t id; + + /* Total length of the descriptor chain which was written +to. */ + + uint32_t len; + +}; + + + +struct vring_used { + + uint16_t flags; + + uint16_t idx; + + struct vring_used_elem ring[]; + + uint16_t avail_event; + +}; + + + +struct vring { + + unsigned int num; + + + + struct vring_desc *desc; + + struct vring_avail *avail; + + struct vring_used *used; + +}; + + + +/* The standard layout for the ring is a continuous chunk of +memory which + + * looks like this. We assume num is a power of 2. + + * + + * struct vring { + + * // The actual descriptors (16 bytes each) + + * struct vring_desc desc[num]; + + * + + * // A ring of available descriptor heads with free-running +index. + + * __u16 avail_flags; + + * __u16 avail_idx; + + * __u16 available[num]; + + * + + * // Padding to the next align boundary. + + * char pad[]; + + * + + * // A ring of used descriptor heads with free-running +index. + + * __u16 used_flags; + + * __u16 EVENT_IDX; + + * struct vring_used_elem used[num]; + + * }; + + * Note: for virtio PCI, align is 4096. + + */ + +static inline void vring_init(struct vring *vr, unsigned int num, +void *p, + + unsigned long align) + +{ + + vr->num = num; + + vr->desc = p; + + vr->avail = p + num*sizeof(struct vring_desc); + + vr->used = (void *)(((unsigned long)&vr->avail->ring[num] + + + align-1) + + & ~(align - 1)); + +} + + + +static inline unsigned vring_size(unsigned int num, unsigned long +align) + +{ + + return ((sizeof(struct vring_desc)*num + +sizeof(uint16_t)*(2+num) + + + align - 1) & ~(align - 1)) + + + sizeof(uint16_t)*3 + sizeof(struct +vring_used_elem)*num; + +} + + + +static inline int vring_need_event(uint16_t event_idx, uint16_t +new_idx, uint16_t old_idx) + +{ + + return (uint16_t)(new_idx - event_idx - 1) < +(uint16_t)(new_idx - old_idx); + +} + +#endif /* VIRTIO_RING_H */ + +<cha:Reserved-Feature-Bits>Appendix B: Reserved Feature Bits + +Currently there are five device-independent feature bits defined: + + VIRTIO_F_NOTIFY_ON_EMPTY (24) Negotiating this feature + indicates that the driver wants an interrupt if the device runs + out of available descriptors on a virtqueue, even though + interrupts are suppressed using the VRING_AVAIL_F_NO_INTERRUPT + flag or the used_event field. An example of this is the + networking driver: it doesn't need to know every time a packet + is transmitted, but it does need to free the transmitted + packets a finite time after they are transmitted. It can avoid + using a timer if the device interrupts it when all the packets + are transmitted. + + VIRTIO_F_RING_INDIRECT_DESC (28) Negotiating this feature + indicates that the driver can use descriptors with the + VRING_DESC_F_INDIRECT flag set, as described in [sub:Indirect-Descriptors] + . + + VIRTIO_F_RING_EVENT_IDX(29) This feature enables the used_event + and the avail_event fields. If set, it indicates that the + device should ignore the flags field in the available ring + structure. Instead, the used_event field in this structure is + used by guest to suppress device interrupts. Further, the + driver should ignore the flags field in the used ring + structure. Instead, the avail_event field in this structure is + used by the device to suppress notifications. If unset, the + driver should ignore the used_event field; the device should + ignore the avail_event field; the flags field is used + + VIRTIO_F_BAD_FEATURE(30) This feature should never be + negotiated by the guest; doing so is an indication that the + guest is faulty[footnote: +An experimental virtio PCI driver contained in Linux version +2.6.25 had this problem, and this feature bit can be used to +detect it. +] + + VIRTIO_F_FEATURES_HIGH(31) This feature indicates that the + device supports feature bits 32:63. If unset, feature bits + 32:63 are unset. + +Appendix C: Network Device + +The virtio network device is a virtual ethernet card, and is the +most complex of the devices supported so far by virtio. It has +enhanced rapidly and demonstrates clearly how support for new +features should be added to an existing device. Empty buffers are +placed in one virtqueue for receiving packets, and outgoing +packets are enqueued into another for transmission in that order. +A third command queue is used to control advanced filtering +features. + + Configuration + + Subsystem Device ID 1 + + Virtqueues 0:receiveq. 1:transmitq. 2:controlq[footnote: +Only if VIRTIO_NET_F_CTRL_VQ set +] + + Feature bits + + VIRTIO_NET_F_CSUM (0) Device handles packets with partial + checksum + + VIRTIO_NET_F_GUEST_CSUM (1) Guest handles packets with partial + checksum + + VIRTIO_NET_F_MAC (5) Device has given MAC address. + + VIRTIO_NET_F_GSO (6) (Deprecated) device handles packets with + any GSO type.[footnote: +It was supposed to indicate segmentation offload support, but +upon further investigation it became clear that multiple bits +were required. +] + + VIRTIO_NET_F_GUEST_TSO4 (7) Guest can receive TSOv4. + + VIRTIO_NET_F_GUEST_TSO6 (8) Guest can receive TSOv6. + + VIRTIO_NET_F_GUEST_ECN (9) Guest can receive TSO with ECN. + + VIRTIO_NET_F_GUEST_UFO (10) Guest can receive UFO. + + VIRTIO_NET_F_HOST_TSO4 (11) Device can receive TSOv4. + + VIRTIO_NET_F_HOST_TSO6 (12) Device can receive TSOv6. + + VIRTIO_NET_F_HOST_ECN (13) Device can receive TSO with ECN. + + VIRTIO_NET_F_HOST_UFO (14) Device can receive UFO. + + VIRTIO_NET_F_MRG_RXBUF (15) Guest can merge receive buffers. + + VIRTIO_NET_F_STATUS (16) Configuration status field is + available. + + VIRTIO_NET_F_CTRL_VQ (17) Control channel is available. + + VIRTIO_NET_F_CTRL_RX (18) Control channel RX mode support. + + VIRTIO_NET_F_CTRL_VLAN (19) Control channel VLAN filtering. + + Device configuration layout Two configuration fields are + currently defined. The mac address field always exists (though + is only valid if VIRTIO_NET_F_MAC is set), and the status field + only exists if VIRTIO_NET_F_STATUS is set. Only one bit is + currently defined for the status field: VIRTIO_NET_S_LINK_UP. #define VIRTIO_NET_S_LINK_UP 1 + + + +struct virtio_net_config { + + u8 mac[6]; + + u16 status; + +}; + + Device Initialization + + The initialization routine should identify the receive and + transmission virtqueues. + + If the VIRTIO_NET_F_MAC feature bit is set, the configuration + space “mac” entry indicates the “physical” address of the the + network card, otherwise a private MAC address should be + assigned. All guests are expected to negotiate this feature if + it is set. + + If the VIRTIO_NET_F_CTRL_VQ feature bit is negotiated, identify + the control virtqueue. + + If the VIRTIO_NET_F_STATUS feature bit is negotiated, the link + status can be read from the bottom bit of the “status” config + field. Otherwise, the link should be assumed active. + + The receive virtqueue should be filled with receive buffers. + This is described in detail below in “Setting Up Receive + Buffers”. + + A driver can indicate that it will generate checksumless + packets by negotating the VIRTIO_NET_F_CSUM feature. This “ + checksum offload” is a common feature on modern network cards. + + If that feature is negotiated, a driver can use TCP or UDP + segmentation offload by negotiating the VIRTIO_NET_F_HOST_TSO4 + (IPv4 TCP), VIRTIO_NET_F_HOST_TSO6 (IPv6 TCP) and + VIRTIO_NET_F_HOST_UFO (UDP fragmentation) features. It should + not send TCP packets requiring segmentation offload which have + the Explicit Congestion Notification bit set, unless the + VIRTIO_NET_F_HOST_ECN feature is negotiated.[footnote: +This is a common restriction in real, older network cards. +] + + The converse features are also available: a driver can save the + virtual device some work by negotiating these features.[footnote: +For example, a network packet transported between two guests on +the same system may not require checksumming at all, nor +segmentation, if both guests are amenable. +] The VIRTIO_NET_F_GUEST_CSUM feature indicates that partially + checksummed packets can be received, and if it can do that then + the VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, + VIRTIO_NET_F_GUEST_UFO and VIRTIO_NET_F_GUEST_ECN are the input + equivalents of the features described above. See “Receiving + Packets” below. + + Device Operation + +Packets are transmitted by placing them in the transmitq, and +buffers for incoming packets are placed in the receiveq. In each +case, the packet itself is preceeded by a header: + +struct virtio_net_hdr { + +#define VIRTIO_NET_HDR_F_NEEDS_CSUM 1 + + u8 flags; + +#define VIRTIO_NET_HDR_GSO_NONE 0 + +#define VIRTIO_NET_HDR_GSO_TCPV4 1 + +#define VIRTIO_NET_HDR_GSO_UDP 3 + +#define VIRTIO_NET_HDR_GSO_TCPV6 4 + +#define VIRTIO_NET_HDR_GSO_ECN 0x80 + + u8 gso_type; + + u16 hdr_len; + + u16 gso_size; + + u16 csum_start; + + u16 csum_offset; + +/* Only if VIRTIO_NET_F_MRG_RXBUF: */ + + u16 num_buffers + +}; + +The controlq is used to control device features such as +filtering. + + Packet Transmission + +Transmitting a single packet is simple, but varies depending on +the different features the driver negotiated. + + If the driver negotiated VIRTIO_NET_F_CSUM, and the packet has + not been fully checksummed, then the virtio_net_hdr's fields + are set as follows. Otherwise, the packet must be fully + checksummed, and flags is zero. + + flags has the VIRTIO_NET_HDR_F_NEEDS_CSUM set, + + <ite:csum_start-is-set>csum_start is set to the offset within + the packet to begin checksumming, and + + csum_offset indicates how many bytes after the csum_start the + new (16 bit ones' complement) checksum should be placed.[footnote: +For example, consider a partially checksummed TCP (IPv4) packet. +It will have a 14 byte ethernet header and 20 byte IP header +followed by the TCP header (with the TCP checksum field 16 bytes +into that header). csum_start will be 14+20 = 34 (the TCP +checksum includes the header), and csum_offset will be 16. The +value in the TCP checksum field will be the sum of the TCP pseudo +header, so that replacing it by the ones' complement checksum of +the TCP header and body will give the correct result. +] + + <enu:If-the-driver>If the driver negotiated + VIRTIO_NET_F_HOST_TSO4, TSO6 or UFO, and the packet requires + TCP segmentation or UDP fragmentation, then the “gso_type” + field is set to VIRTIO_NET_HDR_GSO_TCPV4, TCPV6 or UDP. + (Otherwise, it is set to VIRTIO_NET_HDR_GSO_NONE). In this + case, packets larger than 1514 bytes can be transmitted: the + metadata indicates how to replicate the packet header to cut it + into smaller packets. The other gso fields are set: + + hdr_len is a hint to the device as to how much of the header + needs to be kept to copy into each packet, usually set to the + length of the headers, including the transport header.[footnote: +Due to various bugs in implementations, this field is not useful +as a guarantee of the transport header size. +] + + gso_size is the size of the packet beyond that header (ie. + MSS). + + If the driver negotiated the VIRTIO_NET_F_HOST_ECN feature, the + VIRTIO_NET_HDR_GSO_ECN bit may be set in “gso_type” as well, + indicating that the TCP packet has the ECN bit set.[footnote: +This case is not handled by some older hardware, so is called out +specifically in the protocol. +] + + If the driver negotiated the VIRTIO_NET_F_MRG_RXBUF feature, + the num_buffers field is set to zero. + + The header and packet are added as one output buffer to the + transmitq, and the device is notified of the new entry (see [sub:Notifying-The-Device] + ).[footnote: +Note that the header will be two bytes longer for the +VIRTIO_NET_F_MRG_RXBUF case. +] + + Packet Transmission Interrupt + +Often a driver will suppress transmission interrupts using the +VRING_AVAIL_F_NO_INTERRUPT flag (see [sub:Receiving-Used-Buffers] +) and check for used packets in the transmit path of following +packets. However, it will still receive interrupts if the +VIRTIO_F_NOTIFY_ON_EMPTY feature is negotiated, indicating that +the transmission queue is completely emptied. + +The normal behavior in this interrupt handler is to retrieve and +new descriptors from the used ring and free the corresponding +headers and packets. + + Setting Up Receive Buffers + +It is generally a good idea to keep the receive virtqueue as +fully populated as possible: if it runs out, network performance +will suffer. + +If the VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6 or +VIRTIO_NET_F_GUEST_UFO features are used, the Guest will need to +accept packets of up to 65550 bytes long (the maximum size of a +TCP or UDP packet, plus the 14 byte ethernet header), otherwise +1514 bytes. So unless VIRTIO_NET_F_MRG_RXBUF is negotiated, every +buffer in the receive queue needs to be at least this length [footnote: +Obviously each one can be split across multiple descriptor +elements. +]. + +If VIRTIO_NET_F_MRG_RXBUF is negotiated, each buffer must be at +least the size of the struct virtio_net_hdr. + + Packet Receive Interrupt + +When a packet is copied into a buffer in the receiveq, the +optimal path is to disable further interrupts for the receiveq +(see [sub:Receiving-Used-Buffers]) and process packets until no +more are found, then re-enable them. + +Processing packet involves: + + If the driver negotiated the VIRTIO_NET_F_MRG_RXBUF feature, + then the “num_buffers” field indicates how many descriptors + this packet is spread over (including this one). This allows + receipt of large packets without having to allocate large + buffers. In this case, there will be at least “num_buffers” in + the used ring, and they should be chained together to form a + single packet. The other buffers will not begin with a struct + virtio_net_hdr. + + If the VIRTIO_NET_F_MRG_RXBUF feature was not negotiated, or + the “num_buffers” field is one, then the entire packet will be + contained within this buffer, immediately following the struct + virtio_net_hdr. + + If the VIRTIO_NET_F_GUEST_CSUM feature was negotiated, the + VIRTIO_NET_HDR_F_NEEDS_CSUM bit in the “flags” field may be + set: if so, the checksum on the packet is incomplete and the “ + csum_start” and “csum_offset” fields indicate how to calculate + it (see [ite:csum_start-is-set]). + + If the VIRTIO_NET_F_GUEST_TSO4, TSO6 or UFO options were + negotiated, then the “gso_type” may be something other than + VIRTIO_NET_HDR_GSO_NONE, and the “gso_size” field indicates the + desired MSS (see [enu:If-the-driver]).Control Virtqueue + +The driver uses the control virtqueue (if VIRTIO_NET_F_VTRL_VQ is +negotiated) to send commands to manipulate various features of +the device which would not easily map into the configuration +space. + +All commands are of the following form: + +struct virtio_net_ctrl { + + u8 class; + + u8 command; + + u8 command-specific-data[]; + + u8 ack; + +}; + + + +/* ack values */ + +#define VIRTIO_NET_OK 0 + +#define VIRTIO_NET_ERR 1 + +The class, command and command-specific-data are set by the +driver, and the device sets the ack byte. There is little it can +do except issue a diagnostic if the ack byte is not +VIRTIO_NET_OK. + + Packet Receive Filtering + +If the VIRTIO_NET_F_CTRL_RX feature is negotiated, the driver can +send control commands for promiscuous mode, multicast receiving, +and filtering of MAC addresses. + +Note that in general, these commands are best-effort: unwanted +packets may still arrive. + + Setting Promiscuous Mode + +#define VIRTIO_NET_CTRL_RX 0 + + #define VIRTIO_NET_CTRL_RX_PROMISC 0 + + #define VIRTIO_NET_CTRL_RX_ALLMULTI 1 + +The class VIRTIO_NET_CTRL_RX has two commands: +VIRTIO_NET_CTRL_RX_PROMISC turns promiscuous mode on and off, and +VIRTIO_NET_CTRL_RX_ALLMULTI turns all-multicast receive on and +off. The command-specific-data is one byte containing 0 (off) or +1 (on). + + Setting MAC Address Filtering + +struct virtio_net_ctrl_mac { + + u32 entries; + + u8 macs[entries][ETH_ALEN]; + +}; + + + +#define VIRTIO_NET_CTRL_MAC 1 + + #define VIRTIO_NET_CTRL_MAC_TABLE_SET 0 + +The device can filter incoming packets by any number of +destination MAC addresses.[footnote: +Since there are no guarentees, it can use a hash filter +orsilently switch to allmulti or promiscuous mode if it is given +too many addresses. +] This table is set using the class VIRTIO_NET_CTRL_MAC and the +command VIRTIO_NET_CTRL_MAC_TABLE_SET. The command-specific-data +is two variable length tables of 6-byte MAC addresses. The first +table contains unicast addresses, and the second contains +multicast addresses. + + VLAN Filtering + +If the driver negotiates the VIRTION_NET_F_CTRL_VLAN feature, it +can control a VLAN filter table in the device. + +#define VIRTIO_NET_CTRL_VLAN 2 + + #define VIRTIO_NET_CTRL_VLAN_ADD 0 + + #define VIRTIO_NET_CTRL_VLAN_DEL 1 + +Both the VIRTIO_NET_CTRL_VLAN_ADD and VIRTIO_NET_CTRL_VLAN_DEL +command take a 16-bit VLAN id as the command-specific-data. + +Appendix D: Block Device + +The virtio block device is a simple virtual block device (ie. +disk). Read and write requests (and other exotic requests) are +placed in the queue, and serviced (probably out of order) by the +device except where noted. + + Configuration + + Subsystem Device ID 2 + + Virtqueues 0:requestq. + + Feature bits + + VIRTIO_BLK_F_BARRIER (0) Host supports request barriers. + + VIRTIO_BLK_F_SIZE_MAX (1) Maximum size of any single segment is + in “size_max”. + + VIRTIO_BLK_F_SEG_MAX (2) Maximum number of segments in a + request is in “seg_max”. + + VIRTIO_BLK_F_GEOMETRY (4) Disk-style geometry specified in “ + geometry”. + + VIRTIO_BLK_F_RO (5) Device is read-only. + + VIRTIO_BLK_F_BLK_SIZE (6) Block size of disk is in “blk_size”. + + VIRTIO_BLK_F_SCSI (7) Device supports scsi packet commands. + + VIRTIO_BLK_F_FLUSH (9) Cache flush command support. + + + + Device configuration layout The capacity of the device + (expressed in 512-byte sectors) is always present. The + availability of the others all depend on various feature bits + as indicated above. struct virtio_blk_config { + + u64 capacity; + + u32 size_max; + + u32 seg_max; + + struct virtio_blk_geometry { + + u16 cylinders; + + u8 heads; + + u8 sectors; + + } geometry; + + u32 blk_size; + + + +}; + + Device Initialization + + The device size should be read from the “capacity” + configuration field. No requests should be submitted which goes + beyond this limit. + + If the VIRTIO_BLK_F_BLK_SIZE feature is negotiated, the + blk_size field can be read to determine the optimal sector size + for the driver to use. This does not effect the units used in + the protocol (always 512 bytes), but awareness of the correct + value can effect performance. + + If the VIRTIO_BLK_F_RO feature is set by the device, any write + requests will fail. + + + + Device Operation + +The driver queues requests to the virtqueue, and they are used by +the device (not necessarily in order). Each request is of form: + +struct virtio_blk_req { + + + + u32 type; + + u32 ioprio; + + u64 sector; + + char data[][512]; + + u8 status; + +}; + +If the device has VIRTIO_BLK_F_SCSI feature, it can also support +scsi packet command requests, each of these requests is of form:struct virtio_scsi_pc_req { + + u32 type; + + u32 ioprio; + + u64 sector; + + char cmd[]; + + char data[][512]; + +#define SCSI_SENSE_BUFFERSIZE 96 + + u8 sense[SCSI_SENSE_BUFFERSIZE]; + + u32 errors; + + u32 data_len; + + u32 sense_len; + + u32 residual; + + u8 status; + +}; + +The type of the request is either a read (VIRTIO_BLK_T_IN), a +write (VIRTIO_BLK_T_OUT), a scsi packet command +(VIRTIO_BLK_T_SCSI_CMD or VIRTIO_BLK_T_SCSI_CMD_OUT[footnote: +the SCSI_CMD and SCSI_CMD_OUT types are equivalent, the device +does not distinguish between them +]) or a flush (VIRTIO_BLK_T_FLUSH or VIRTIO_BLK_T_FLUSH_OUT[footnote: +the FLUSH and FLUSH_OUT types are equivalent, the device does not +distinguish between them +]). If the device has VIRTIO_BLK_F_BARRIER feature the high bit +(VIRTIO_BLK_T_BARRIER) indicates that this request acts as a +barrier and that all preceeding requests must be complete before +this one, and all following requests must not be started until +this is complete. Note that a barrier does not flush caches in +the underlying backend device in host, and thus does not serve as +data consistency guarantee. Driver must use FLUSH request to +flush the host cache. + +#define VIRTIO_BLK_T_IN 0 + +#define VIRTIO_BLK_T_OUT 1 + +#define VIRTIO_BLK_T_SCSI_CMD 2 + +#define VIRTIO_BLK_T_SCSI_CMD_OUT 3 + +#define VIRTIO_BLK_T_FLUSH 4 + +#define VIRTIO_BLK_T_FLUSH_OUT 5 + +#define VIRTIO_BLK_T_BARRIER 0x80000000 + +The ioprio field is a hint about the relative priorities of +requests to the device: higher numbers indicate more important +requests. + +The sector number indicates the offset (multiplied by 512) where +the read or write is to occur. This field is unused and set to 0 +for scsi packet commands and for flush commands. + +The cmd field is only present for scsi packet command requests, +and indicates the command to perform. This field must reside in a +single, separate read-only buffer; command length can be derived +from the length of this buffer. + +Note that these first three (four for scsi packet commands) +fields are always read-only: the data field is either read-only +or write-only, depending on the request. The size of the read or +write can be derived from the total size of the request buffers. + +The sense field is only present for scsi packet command requests, +and indicates the buffer for scsi sense data. + +The data_len field is only present for scsi packet command +requests, this field is deprecated, and should be ignored by the +driver. Historically, devices copied data length there. + +The sense_len field is only present for scsi packet command +requests and indicates the number of bytes actually written to +the sense buffer. + +The residual field is only present for scsi packet command +requests and indicates the residual size, calculated as data +length - number of bytes actually transferred. + +The final status byte is written by the device: either +VIRTIO_BLK_S_OK for success, VIRTIO_BLK_S_IOERR for host or guest +error or VIRTIO_BLK_S_UNSUPP for a request unsupported by host:#define VIRTIO_BLK_S_OK 0 + +#define VIRTIO_BLK_S_IOERR 1 + +#define VIRTIO_BLK_S_UNSUPP 2 + +Historically, devices assumed that the fields type, ioprio and +sector reside in a single, separate read-only buffer; the fields +errors, data_len, sense_len and residual reside in a single, +separate write-only buffer; the sense field in a separate +write-only buffer of size 96 bytes, by itself; the fields errors, +data_len, sense_len and residual in a single write-only buffer; +and the status field is a separate read-only buffer of size 1 +byte, by itself. + +Appendix E: Console Device + +The virtio console device is a simple device for data input and +output. A device may have one or more ports. Each port has a pair +of input and output virtqueues. Moreover, a device has a pair of +control IO virtqueues. The control virtqueues are used to +communicate information between the device and the driver about +ports being opened and closed on either side of the connection, +indication from the host about whether a particular port is a +console port, adding new ports, port hot-plug/unplug, etc., and +indication from the guest about whether a port or a device was +successfully added, port open/close, etc.. For data IO, one or +more empty buffers are placed in the receive queue for incoming +data and outgoing characters are placed in the transmit queue. + + Configuration + + Subsystem Device ID 3 + + Virtqueues 0:receiveq(port0). 1:transmitq(port0), 2:control + receiveq[footnote: +Ports 2 onwards only if VIRTIO_CONSOLE_F_MULTIPORT is set +], 3:control transmitq, 4:receiveq(port1), 5:transmitq(port1), + ... + + Feature bits + + VIRTIO_CONSOLE_F_SIZE (0) Configuration cols and rows fields + are valid. + + VIRTIO_CONSOLE_F_MULTIPORT(1) Device has support for multiple + ports; configuration fields nr_ports and max_nr_ports are + valid and control virtqueues will be used. + + Device configuration layout The size of the console is supplied + in the configuration space if the VIRTIO_CONSOLE_F_SIZE feature + is set. Furthermore, if the VIRTIO_CONSOLE_F_MULTIPORT feature + is set, the maximum number of ports supported by the device can + be fetched.struct virtio_console_config { + + u16 cols; + + u16 rows; + + + + u32 max_nr_ports; + +}; + + Device Initialization + + If the VIRTIO_CONSOLE_F_SIZE feature is negotiated, the driver + can read the console dimensions from the configuration fields. + + If the VIRTIO_CONSOLE_F_MULTIPORT feature is negotiated, the + driver can spawn multiple ports, not all of which may be + attached to a console. Some could be generic ports. In this + case, the control virtqueues are enabled and according to the + max_nr_ports configuration-space value, the appropriate number + of virtqueues are created. A control message indicating the + driver is ready is sent to the host. The host can then send + control messages for adding new ports to the device. After + creating and initializing each port, a + VIRTIO_CONSOLE_PORT_READY control message is sent to the host + for that port so the host can let us know of any additional + configuration options set for that port. + + The receiveq for each port is populated with one or more + receive buffers. + + Device Operation + + For output, a buffer containing the characters is placed in the + port's transmitq.[footnote: +Because this is high importance and low bandwidth, the current +Linux implementation polls for the buffer to be used, rather than +waiting for an interrupt, simplifying the implementation +significantly. However, for generic serial ports with the +O_NONBLOCK flag set, the polling limitation is relaxed and the +consumed buffers are freed upon the next write or poll call or +when a port is closed or hot-unplugged. +] + + When a buffer is used in the receiveq (signalled by an + interrupt), the contents is the input to the port associated + with the virtqueue for which the notification was received. + + If the driver negotiated the VIRTIO_CONSOLE_F_SIZE feature, a + configuration change interrupt may occur. The updated size can + be read from the configuration fields. + + If the driver negotiated the VIRTIO_CONSOLE_F_MULTIPORT + feature, active ports are announced by the host using the + VIRTIO_CONSOLE_PORT_ADD control message. The same message is + used for port hot-plug as well. + + If the host specified a port `name', a sysfs attribute is + created with the name filled in, so that udev rules can be + written that can create a symlink from the port's name to the + char device for port discovery by applications in the guest. + + Changes to ports' state are effected by control messages. + Appropriate action is taken on the port indicated in the + control message. The layout of the structure of the control + buffer and the events associated are:struct virtio_console_control { + + uint32_t id; /* Port number */ + + uint16_t event; /* The kind of control event */ + + uint16_t value; /* Extra information for the event */ + +}; + + + +/* Some events for the internal messages (control packets) */ + + + +#define VIRTIO_CONSOLE_DEVICE_READY 0 + +#define VIRTIO_CONSOLE_PORT_ADD 1 + +#define VIRTIO_CONSOLE_PORT_REMOVE 2 + +#define VIRTIO_CONSOLE_PORT_READY 3 + +#define VIRTIO_CONSOLE_CONSOLE_PORT 4 + +#define VIRTIO_CONSOLE_RESIZE 5 + +#define VIRTIO_CONSOLE_PORT_OPEN 6 + +#define VIRTIO_CONSOLE_PORT_NAME 7 + +Appendix F: Entropy Device + +The virtio entropy device supplies high-quality randomness for +guest use. + + Configuration + + Subsystem Device ID 4 + + Virtqueues 0:requestq. + + Feature bits None currently defined + + Device configuration layout None currently defined. + + Device Initialization + + The virtqueue is initialized + + Device Operation + +When the driver requires random bytes, it places the descriptor +of one or more buffers in the queue. It will be completely filled +by random data by the device. + +Appendix G: Memory Balloon Device + +The virtio memory balloon device is a primitive device for +managing guest memory: the device asks for a certain amount of +memory, and the guest supplies it (or withdraws it, if the device +has more than it asks for). This allows the guest to adapt to +changes in allowance of underlying physical memory. If the +feature is negotiated, the device can also be used to communicate +guest memory statistics to the host. + + Configuration + + Subsystem Device ID 5 + + Virtqueues 0:inflateq. 1:deflateq. 2:statsq.[footnote: +Only if VIRTIO_BALLON_F_STATS_VQ set +] + + Feature bits + + VIRTIO_BALLOON_F_MUST_TELL_HOST (0) Host must be told before + pages from the balloon are used. + + VIRTIO_BALLOON_F_STATS_VQ (1) A virtqueue for reporting guest + memory statistics is present. + + Device configuration layout Both fields of this configuration + are always available. Note that they are little endian, despite + convention that device fields are guest endian:struct virtio_balloon_config { + + u32 num_pages; + + u32 actual; + +}; + + Device Initialization + + The inflate and deflate virtqueues are identified. + + If the VIRTIO_BALLOON_F_STATS_VQ feature bit is negotiated: + + Identify the stats virtqueue. + + Add one empty buffer to the stats virtqueue and notify the + host. + +Device operation begins immediately. + + Device Operation + + Memory Ballooning The device is driven by the receipt of a + configuration change interrupt. + + The “num_pages” configuration field is examined. If this is + greater than the “actual” number of pages, memory must be given + to the balloon. If it is less than the “actual” number of + pages, memory may be taken back from the balloon for general + use. + + To supply memory to the balloon (aka. inflate): + + The driver constructs an array of addresses of unused memory + pages. These addresses are divided by 4096[footnote: +This is historical, and independent of the guest page size +] and the descriptor describing the resulting 32-bit array is + added to the inflateq. + + To remove memory from the balloon (aka. deflate): + + The driver constructs an array of addresses of memory pages it + has previously given to the balloon, as described above. This + descriptor is added to the deflateq. + + If the VIRTIO_BALLOON_F_MUST_TELL_HOST feature is set, the + guest may not use these requested pages until that descriptor + in the deflateq has been used by the device. + + Otherwise, the guest may begin to re-use pages previously given + to the balloon before the device has acknowledged their + withdrawl. [footnote: +In this case, deflation advice is merely a courtesy +] + + In either case, once the device has completed the inflation or + deflation, the “actual” field of the configuration should be + updated to reflect the new number of pages in the balloon.[footnote: +As updates to configuration space are not atomic, this field +isn't particularly reliable, but can be used to diagnose buggy +guests. +] + + Memory Statistics + +The stats virtqueue is atypical because communication is driven +by the device (not the driver). The channel becomes active at +driver initialization time when the driver adds an empty buffer +and notifies the device. A request for memory statistics proceeds +as follows: + + The device pushes the buffer onto the used ring and sends an + interrupt. + + The driver pops the used buffer and discards it. + + The driver collects memory statistics and writes them into a + new buffer. + + The driver adds the buffer to the virtqueue and notifies the + device. + + The device pops the buffer (retaining it to initiate a + subsequent request) and consumes the statistics. + + Memory Statistics Format Each statistic consists of a 16 bit + tag and a 64 bit value. Both quantities are represented in the + native endian of the guest. All statistics are optional and the + driver may choose which ones to supply. To guarantee backwards + compatibility, unsupported statistics should be omitted. + + struct virtio_balloon_stat { + +#define VIRTIO_BALLOON_S_SWAP_IN 0 + +#define VIRTIO_BALLOON_S_SWAP_OUT 1 + +#define VIRTIO_BALLOON_S_MAJFLT 2 + +#define VIRTIO_BALLOON_S_MINFLT 3 + +#define VIRTIO_BALLOON_S_MEMFREE 4 + +#define VIRTIO_BALLOON_S_MEMTOT 5 + + u16 tag; + + u64 val; + +} __attribute__((packed)); + + Tags + + VIRTIO_BALLOON_S_SWAP_IN The amount of memory that has been + swapped in (in bytes). + + VIRTIO_BALLOON_S_SWAP_OUT The amount of memory that has been + swapped out to disk (in bytes). + + VIRTIO_BALLOON_S_MAJFLT The number of major page faults that + have occurred. + + VIRTIO_BALLOON_S_MINFLT The number of minor page faults that + have occurred. + + VIRTIO_BALLOON_S_MEMFREE The amount of memory not being used + for any purpose (in bytes). + + VIRTIO_BALLOON_S_MEMTOT The total amount of memory available + (in bytes). + diff --git a/MAINTAINERS b/MAINTAINERS index 3891a12eb6a7..5faf685ee6c2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1286,7 +1286,6 @@ F: drivers/input/misc/ati_remote2.c ATLX ETHERNET DRIVERS M: Jay Cliburn <jcliburn@gmail.com> M: Chris Snook <chris.snook@gmail.com> -M: Jie Yang <yangjie@qca.qualcomm.com> L: netdev@vger.kernel.org W: http://sourceforge.net/projects/atl1 W: http://atl1.sourceforge.net @@ -1582,7 +1581,6 @@ F: drivers/scsi/bfa/ BROCADE BNA 10 GIGABIT ETHERNET DRIVER M: Rasesh Mody <rmody@brocade.com> -M: Debashis Dutt <ddutt@brocade.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/brocade/bna/ @@ -1766,7 +1764,6 @@ F: Documentation/zh_CN/ CISCO VIC ETHERNET NIC DRIVER M: Christian Benvenuti <benve@cisco.com> -M: Vasanthy Kolluri <vkolluri@cisco.com> M: Roopa Prabhu <roprabhu@cisco.com> M: David Wang <dwang2@cisco.com> S: Supported @@ -1891,7 +1888,7 @@ S: Maintained F: drivers/connector/ CONTROL GROUPS (CGROUPS) -M: Paul Menage <menage@google.com> +M: Paul Menage <paul@paulmenage.org> M: Li Zefan <lizf@cn.fujitsu.com> L: containers@lists.linux-foundation.org S: Maintained @@ -1940,7 +1937,7 @@ S: Maintained F: tools/power/cpupower CPUSETS -M: Paul Menage <menage@google.com> +M: Paul Menage <paul@paulmenage.org> W: http://www.bullopensource.org/cpuset/ W: http://oss.sgi.com/projects/cpusets/ S: Supported @@ -2657,11 +2654,11 @@ F: drivers/net/wan/dlci.c F: drivers/net/wan/sdla.c FRAMEBUFFER LAYER -M: Paul Mundt <lethal@linux-sh.org> +M: Florian Tobias Schandinat <FlorianSchandinat@gmx.de> L: linux-fbdev@vger.kernel.org W: http://linux-fbdev.sourceforge.net/ Q: http://patchwork.kernel.org/project/linux-fbdev/list/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/lethal/fbdev-2.6.git +T: git git://github.com/schandinat/linux-2.6.git fbdev-next S: Maintained F: Documentation/fb/ F: Documentation/devicetree/bindings/fb/ @@ -3271,6 +3268,17 @@ F: Documentation/input/multi-touch-protocol.txt F: drivers/input/input-mt.c K: \b(ABS|SYN)_MT_ +INTEL C600 SERIES SAS CONTROLLER DRIVER +M: Intel SCU Linux support <intel-linux-scu@intel.com> +M: Dan Williams <dan.j.williams@intel.com> +M: Dave Jiang <dave.jiang@intel.com> +M: Ed Nadolski <edmund.nadolski@intel.com> +L: linux-scsi@vger.kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/djbw/isci.git +S: Maintained +F: drivers/scsi/isci/ +F: firmware/isci/ + INTEL IDLE DRIVER M: Len Brown <lenb@kernel.org> L: linux-pm@lists.linux-foundation.org @@ -4405,7 +4413,8 @@ L: netfilter@vger.kernel.org L: coreteam@netfilter.org W: http://www.netfilter.org/ W: http://www.iptables.org/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-2.6.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-2.6.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next-2.6.git S: Supported F: include/linux/netfilter* F: include/linux/netfilter/ @@ -4451,8 +4460,8 @@ M: "David S. Miller" <davem@davemloft.net> L: netdev@vger.kernel.org W: http://www.linuxfoundation.org/en/Net W: http://patchwork.ozlabs.org/project/netdev/list/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6.git -T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git S: Maintained F: net/ F: include/net/ @@ -4617,7 +4626,7 @@ F: arch/arm/mach-omap2/clockdomain2xxx_3xxx.c F: arch/arm/mach-omap2/clockdomain44xx.c OMAP AUDIO SUPPORT -M: Jarkko Nikula <jhnikula@gmail.com> +M: Jarkko Nikula <jarkko.nikula@bitmer.com> L: alsa-devel@alsa-project.org (subscribers-only) L: linux-omap@vger.kernel.org S: Maintained @@ -4787,7 +4796,7 @@ F: drivers/net/wireless/orinoco/ OSD LIBRARY and FILESYSTEM M: Boaz Harrosh <bharrosh@panasas.com> -M: Benny Halevy <bhalevy@panasas.com> +M: Benny Halevy <bhalevy@tonian.com> L: osd-dev@open-osd.org W: http://open-osd.org T: git git://git.open-osd.org/open-osd.git @@ -4984,7 +4993,7 @@ M: Paul Mackerras <paulus@samba.org> M: Ingo Molnar <mingo@elte.hu> M: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> S: Supported -F: kernel/perf_event*.c +F: kernel/events/* F: include/linux/perf_event.h F: arch/*/kernel/perf_event*.c F: arch/*/kernel/*/perf_event*.c @@ -5546,6 +5555,7 @@ F: include/media/*7146* SAMSUNG AUDIO (ASoC) DRIVERS M: Jassi Brar <jassisinghbrar@gmail.com> +M: Sangbeom Kim <sbkim73@samsung.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Supported F: sound/soc/samsung @@ -7095,7 +7105,7 @@ S: Supported F: drivers/mmc/host/vub300.c W1 DALLAS'S 1-WIRE BUS -M: Evgeniy Polyakov <johnpol@2ka.mipt.ru> +M: Evgeniy Polyakov <zbr@ioremap.net> S: Maintained F: Documentation/w1/ F: drivers/w1/ @@ -7207,6 +7217,9 @@ W: http://opensource.wolfsonmicro.com/content/linux-drivers-wolfson-devices S: Supported F: Documentation/hwmon/wm83?? F: drivers/leds/leds-wm83*.c +F: drivers/input/misc/wm831x-on.c +F: drivers/input/touchscreen/wm831x-ts.c +F: drivers/input/touchscreen/wm97*.c F: drivers/mfd/wm8*.c F: drivers/power/wm83*.c F: drivers/rtc/rtc-wm83*.c @@ -7216,6 +7229,7 @@ F: drivers/watchdog/wm83*_wdt.c F: include/linux/mfd/wm831x/ F: include/linux/mfd/wm8350/ F: include/linux/mfd/wm8400* +F: include/linux/wm97xx.h F: include/sound/wm????.h F: sound/soc/codecs/wm* @@ -1,8 +1,8 @@ VERSION = 3 PATCHLEVEL = 1 SUBLEVEL = 0 -EXTRAVERSION = -rc1 -NAME = Sneaky Weasel +EXTRAVERSION = -rc7 +NAME = "Divemaster Edition" # *DOCUMENTATION* # To see a list of typical targets execute "make help" diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 60cde53d266c..8bb936226dee 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -51,7 +51,7 @@ config GENERIC_CMOS_UPDATE def_bool y config GENERIC_GPIO - def_bool y + bool config ZONE_DMA bool diff --git a/arch/alpha/include/asm/sysinfo.h b/arch/alpha/include/asm/sysinfo.h index 086aba284df2..e77d77cd07b8 100644 --- a/arch/alpha/include/asm/sysinfo.h +++ b/arch/alpha/include/asm/sysinfo.h @@ -27,13 +27,4 @@ #define UAC_NOFIX 2 #define UAC_SIGBUS 4 - -#ifdef __KERNEL__ - -/* This is the shift that is applied to the UAC bits as stored in the - per-thread flags. See thread_info.h. */ -#define UAC_SHIFT 6 - -#endif - #endif /* __ASM_ALPHA_SYSINFO_H */ diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h index 6f32f9c84a2d..ff73db022342 100644 --- a/arch/alpha/include/asm/thread_info.h +++ b/arch/alpha/include/asm/thread_info.h @@ -74,9 +74,9 @@ register struct thread_info *__current_thread_info __asm__("$8"); #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_POLLING_NRFLAG 8 /* poll_idle is polling NEED_RESCHED */ #define TIF_DIE_IF_KERNEL 9 /* dik recursion lock */ -#define TIF_UAC_NOPRINT 10 /* see sysinfo.h */ -#define TIF_UAC_NOFIX 11 -#define TIF_UAC_SIGBUS 12 +#define TIF_UAC_NOPRINT 10 /* ! Preserve sequence of following */ +#define TIF_UAC_NOFIX 11 /* ! flags as they match */ +#define TIF_UAC_SIGBUS 12 /* ! userspace part of 'osf_sysinfo' */ #define TIF_MEMDIE 13 /* is terminating due to OOM killer */ #define TIF_RESTORE_SIGMASK 14 /* restore signal mask in do_signal */ #define TIF_FREEZE 16 /* is freezing for suspend */ @@ -97,7 +97,7 @@ register struct thread_info *__current_thread_info __asm__("$8"); #define _TIF_ALLWORK_MASK (_TIF_WORK_MASK \ | _TIF_SYSCALL_TRACE) -#define ALPHA_UAC_SHIFT 10 +#define ALPHA_UAC_SHIFT TIF_UAC_NOPRINT #define ALPHA_UAC_MASK (1 << TIF_UAC_NOPRINT | 1 << TIF_UAC_NOFIX | \ 1 << TIF_UAC_SIGBUS) diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 326f0a2d56e5..01e8715e26d9 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -42,6 +42,7 @@ #include <asm/uaccess.h> #include <asm/system.h> #include <asm/sysinfo.h> +#include <asm/thread_info.h> #include <asm/hwrpb.h> #include <asm/processor.h> @@ -633,9 +634,10 @@ SYSCALL_DEFINE5(osf_getsysinfo, unsigned long, op, void __user *, buffer, case GSI_UACPROC: if (nbytes < sizeof(unsigned int)) return -EINVAL; - w = (current_thread_info()->flags >> UAC_SHIFT) & UAC_BITMASK; - if (put_user(w, (unsigned int __user *)buffer)) - return -EFAULT; + w = (current_thread_info()->flags >> ALPHA_UAC_SHIFT) & + UAC_BITMASK; + if (put_user(w, (unsigned int __user *)buffer)) + return -EFAULT; return 1; case GSI_PROC_TYPE: @@ -756,8 +758,8 @@ SYSCALL_DEFINE5(osf_setsysinfo, unsigned long, op, void __user *, buffer, case SSIN_UACPROC: again: old = current_thread_info()->flags; - new = old & ~(UAC_BITMASK << UAC_SHIFT); - new = new | (w & UAC_BITMASK) << UAC_SHIFT; + new = old & ~(UAC_BITMASK << ALPHA_UAC_SHIFT); + new = new | (w & UAC_BITMASK) << ALPHA_UAC_SHIFT; if (cmpxchg(¤t_thread_info()->flags, old, new) != old) goto again; diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S index b9c28f3f1956..6acea1f96de3 100644 --- a/arch/alpha/kernel/systbls.S +++ b/arch/alpha/kernel/systbls.S @@ -360,7 +360,7 @@ sys_call_table: .quad sys_newuname .quad sys_nanosleep /* 340 */ .quad sys_mremap - .quad sys_nfsservctl + .quad sys_ni_syscall /* old nfsservctl */ .quad sys_setresuid .quad sys_getresuid .quad sys_pciconfig_read /* 345 */ diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 5ebc5d922ea1..3269576dbfa8 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1271,6 +1271,18 @@ config ARM_ERRATA_754327 This workaround defines cpu_relax() as smp_mb(), preventing correctly written polling loops from denying visibility of updates to memory. +config ARM_ERRATA_364296 + bool "ARM errata: Possible cache data corruption with hit-under-miss enabled" + depends on CPU_V6 && !SMP + help + This options enables the workaround for the 364296 ARM1136 + r0p2 erratum (possible cache data corruption with + hit-under-miss enabled). It sets the undocumented bit 31 in + the auxiliary control register and the FI bit in the control + register, thus disabling hit-under-miss without putting the + processor into full low interrupt latency mode. ARM11MPCore + is not affected. + endmenu source "arch/arm/common/Kconfig" diff --git a/arch/arm/boot/compressed/mmcif-sh7372.c b/arch/arm/boot/compressed/mmcif-sh7372.c index b6f61d9a5a1b..672ae95db5c3 100644 --- a/arch/arm/boot/compressed/mmcif-sh7372.c +++ b/arch/arm/boot/compressed/mmcif-sh7372.c @@ -82,7 +82,7 @@ asmlinkage void mmc_loader(unsigned char *buf, unsigned long len) /* Disable clock to MMC hardware block */ - __raw_writel(__raw_readl(SMSTPCR3) & (1 << 12), SMSTPCR3); + __raw_writel(__raw_readl(SMSTPCR3) | (1 << 12), SMSTPCR3); mmc_update_progress(MMC_PROGRESS_DONE); } diff --git a/arch/arm/boot/compressed/sdhi-sh7372.c b/arch/arm/boot/compressed/sdhi-sh7372.c index d403a8b24d7f..d279294f2381 100644 --- a/arch/arm/boot/compressed/sdhi-sh7372.c +++ b/arch/arm/boot/compressed/sdhi-sh7372.c @@ -85,7 +85,7 @@ asmlinkage void mmc_loader(unsigned short *buf, unsigned long len) goto err; /* Disable clock to SDHI1 hardware block */ - __raw_writel(__raw_readl(SMSTPCR3) & (1 << 13), SMSTPCR3); + __raw_writel(__raw_readl(SMSTPCR3) | (1 << 13), SMSTPCR3); mmc_update_progress(MMC_PROGRESS_DONE); diff --git a/arch/arm/boot/dts/tegra-harmony.dts b/arch/arm/boot/dts/tegra-harmony.dts index 4c053340ce33..e5818668d091 100644 --- a/arch/arm/boot/dts/tegra-harmony.dts +++ b/arch/arm/boot/dts/tegra-harmony.dts @@ -57,14 +57,14 @@ }; sdhci@c8000200 { - gpios = <&gpio 69 0>, /* cd, gpio PI5 */ - <&gpio 57 0>, /* wp, gpio PH1 */ - <&gpio 155 0>; /* power, gpio PT3 */ + cd-gpios = <&gpio 69 0>; /* gpio PI5 */ + wp-gpios = <&gpio 57 0>; /* gpio PH1 */ + power-gpios = <&gpio 155 0>; /* gpio PT3 */ }; sdhci@c8000600 { - gpios = <&gpio 58 0>, /* cd, gpio PH2 */ - <&gpio 59 0>, /* wp, gpio PH3 */ - <&gpio 70 0>; /* power, gpio PI6 */ + cd-gpios = <&gpio 58 0>; /* gpio PH2 */ + wp-gpios = <&gpio 59 0>; /* gpio PH3 */ + power-gpios = <&gpio 70 0>; /* gpio PI6 */ }; }; diff --git a/arch/arm/boot/dts/tegra-seaboard.dts b/arch/arm/boot/dts/tegra-seaboard.dts index 1940cae00748..64cedca6fc79 100644 --- a/arch/arm/boot/dts/tegra-seaboard.dts +++ b/arch/arm/boot/dts/tegra-seaboard.dts @@ -21,8 +21,8 @@ }; sdhci@c8000400 { - gpios = <&gpio 69 0>, /* cd, gpio PI5 */ - <&gpio 57 0>, /* wp, gpio PH1 */ - <&gpio 70 0>; /* power, gpio PI6 */ + cd-gpios = <&gpio 69 0>; /* gpio PI5 */ + wp-gpios = <&gpio 57 0>; /* gpio PH1 */ + power-gpios = <&gpio 70 0>; /* gpio PI6 */ }; }; diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h index 16bd48031583..99a6ed7e1bfd 100644 --- a/arch/arm/include/asm/hardware/cache-l2x0.h +++ b/arch/arm/include/asm/hardware/cache-l2x0.h @@ -45,8 +45,13 @@ #define L2X0_CLEAN_INV_LINE_PA 0x7F0 #define L2X0_CLEAN_INV_LINE_IDX 0x7F8 #define L2X0_CLEAN_INV_WAY 0x7FC -#define L2X0_LOCKDOWN_WAY_D 0x900 -#define L2X0_LOCKDOWN_WAY_I 0x904 +/* + * The lockdown registers repeat 8 times for L310, the L210 has only one + * D and one I lockdown register at 0x0900 and 0x0904. + */ +#define L2X0_LOCKDOWN_WAY_D_BASE 0x900 +#define L2X0_LOCKDOWN_WAY_I_BASE 0x904 +#define L2X0_LOCKDOWN_STRIDE 0x08 #define L2X0_TEST_OPERATION 0xF00 #define L2X0_LINE_DATA 0xF10 #define L2X0_LINE_TAG 0xF30 @@ -64,7 +69,7 @@ #define L2X0_AUX_CTRL_MASK 0xc0000fff #define L2X0_AUX_CTRL_ASSOCIATIVITY_SHIFT 16 #define L2X0_AUX_CTRL_WAY_SIZE_SHIFT 17 -#define L2X0_AUX_CTRL_WAY_SIZE_MASK (0x3 << 17) +#define L2X0_AUX_CTRL_WAY_SIZE_MASK (0x7 << 17) #define L2X0_AUX_CTRL_SHARE_OVERRIDE_SHIFT 22 #define L2X0_AUX_CTRL_NS_LOCKDOWN_SHIFT 26 #define L2X0_AUX_CTRL_NS_INT_CTRL_SHIFT 27 diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h index 67c70a31a1be..b7e82c4aced6 100644 --- a/arch/arm/include/asm/pmu.h +++ b/arch/arm/include/asm/pmu.h @@ -41,7 +41,7 @@ struct arm_pmu_platdata { * encoded error on failure. */ extern struct platform_device * -reserve_pmu(enum arm_pmu_type device); +reserve_pmu(enum arm_pmu_type type); /** * release_pmu() - Relinquish control of the performance counters @@ -62,26 +62,26 @@ release_pmu(enum arm_pmu_type type); * the actual hardware initialisation. */ extern int -init_pmu(enum arm_pmu_type device); +init_pmu(enum arm_pmu_type type); #else /* CONFIG_CPU_HAS_PMU */ #include <linux/err.h> static inline struct platform_device * -reserve_pmu(enum arm_pmu_type device) +reserve_pmu(enum arm_pmu_type type) { return ERR_PTR(-ENODEV); } static inline int -release_pmu(struct platform_device *pdev) +release_pmu(enum arm_pmu_type type) { return -ENODEV; } static inline int -init_pmu(enum arm_pmu_type device) +init_pmu(enum arm_pmu_type type) { return -ENODEV; } diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S index 80f7896cc016..9943e9e74a1b 100644 --- a/arch/arm/kernel/calls.S +++ b/arch/arm/kernel/calls.S @@ -178,7 +178,7 @@ CALL(sys_ni_syscall) /* vm86 */ CALL(sys_ni_syscall) /* was sys_query_module */ CALL(sys_poll) - CALL(sys_nfsservctl) + CALL(sys_ni_syscall) /* was nfsservctl */ /* 170 */ CALL(sys_setresgid16) CALL(sys_getresgid16) CALL(sys_prctl) diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c index 2b70709376c3..c53474fe84df 100644 --- a/arch/arm/kernel/pmu.c +++ b/arch/arm/kernel/pmu.c @@ -31,7 +31,7 @@ static int __devinit pmu_register(struct platform_device *pdev, { if (type < 0 || type >= ARM_NUM_PMU_DEVICES) { pr_warning("received registration request for unknown " - "device %d\n", type); + "PMU device type %d\n", type); return -EINVAL; } @@ -112,17 +112,17 @@ static int __init register_pmu_driver(void) device_initcall(register_pmu_driver); struct platform_device * -reserve_pmu(enum arm_pmu_type device) +reserve_pmu(enum arm_pmu_type type) { struct platform_device *pdev; - if (test_and_set_bit_lock(device, &pmu_lock)) { + if (test_and_set_bit_lock(type, &pmu_lock)) { pdev = ERR_PTR(-EBUSY); - } else if (pmu_devices[device] == NULL) { - clear_bit_unlock(device, &pmu_lock); + } else if (pmu_devices[type] == NULL) { + clear_bit_unlock(type, &pmu_lock); pdev = ERR_PTR(-ENODEV); } else { - pdev = pmu_devices[device]; + pdev = pmu_devices[type]; } return pdev; @@ -130,11 +130,11 @@ reserve_pmu(enum arm_pmu_type device) EXPORT_SYMBOL_GPL(reserve_pmu); int -release_pmu(enum arm_pmu_type device) +release_pmu(enum arm_pmu_type type) { - if (WARN_ON(!pmu_devices[device])) + if (WARN_ON(!pmu_devices[type])) return -EINVAL; - clear_bit_unlock(device, &pmu_lock); + clear_bit_unlock(type, &pmu_lock); return 0; } EXPORT_SYMBOL_GPL(release_pmu); @@ -182,17 +182,17 @@ init_cpu_pmu(void) } int -init_pmu(enum arm_pmu_type device) +init_pmu(enum arm_pmu_type type) { int err = 0; - switch (device) { + switch (type) { case ARM_PMU_DEVICE_CPU: err = init_cpu_pmu(); break; default: - pr_warning("attempt to initialise unknown device %d\n", - device); + pr_warning("attempt to initialise PMU of unknown " + "type %d\n", type); err = -EINVAL; } diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S index 9cf4cbf8f95b..d0cdedf4864d 100644 --- a/arch/arm/kernel/relocate_kernel.S +++ b/arch/arm/kernel/relocate_kernel.S @@ -57,7 +57,8 @@ relocate_new_kernel: mov r0,#0 ldr r1,kexec_mach_type ldr r2,kexec_boot_atags - mov pc,lr + ARM( mov pc, lr ) + THUMB( bx lr ) .align diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 70bca649e925..e514c76043b4 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -280,18 +280,19 @@ static void __init cacheid_init(void) if (arch >= CPU_ARCH_ARMv6) { if ((cachetype & (7 << 29)) == 4 << 29) { /* ARMv7 register format */ + arch = CPU_ARCH_ARMv7; cacheid = CACHEID_VIPT_NONALIASING; if ((cachetype & (3 << 14)) == 1 << 14) cacheid |= CACHEID_ASID_TAGGED; - else if (cpu_has_aliasing_icache(CPU_ARCH_ARMv7)) - cacheid |= CACHEID_VIPT_I_ALIASING; - } else if (cachetype & (1 << 23)) { - cacheid = CACHEID_VIPT_ALIASING; } else { - cacheid = CACHEID_VIPT_NONALIASING; - if (cpu_has_aliasing_icache(CPU_ARCH_ARMv6)) - cacheid |= CACHEID_VIPT_I_ALIASING; + arch = CPU_ARCH_ARMv6; + if (cachetype & (1 << 23)) + cacheid = CACHEID_VIPT_ALIASING; + else + cacheid = CACHEID_VIPT_NONALIASING; } + if (cpu_has_aliasing_icache(arch)) + cacheid |= CACHEID_VIPT_I_ALIASING; } else { cacheid = CACHEID_VIVT; } diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c index 2c277d40cee6..01c186222f3b 100644 --- a/arch/arm/kernel/smp_twd.c +++ b/arch/arm/kernel/smp_twd.c @@ -137,8 +137,8 @@ void __cpuinit twd_timer_setup(struct clock_event_device *clk) clk->max_delta_ns = clockevent_delta2ns(0xffffffff, clk); clk->min_delta_ns = clockevent_delta2ns(0xf, clk); + clockevents_register_device(clk); + /* Make sure our local interrupt controller has this enabled */ gic_enable_ppi(clk->irq); - - clockevents_register_device(clk); } diff --git a/arch/arm/mach-at91/at91sam9261.c b/arch/arm/mach-at91/at91sam9261.c index d522b47e30b5..6c8e3b5f669f 100644 --- a/arch/arm/mach-at91/at91sam9261.c +++ b/arch/arm/mach-at91/at91sam9261.c @@ -157,7 +157,7 @@ static struct clk_lookup periph_clocks_lookups[] = { CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.1", &spi1_clk), CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tc0_clk), CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.0", &tc1_clk), - CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.0", &tc1_clk), + CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.0", &tc2_clk), CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk), CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk), CLKDEV_CON_DEV_ID("pclk", "ssc.2", &ssc2_clk), diff --git a/arch/arm/mach-cns3xxx/include/mach/entry-macro.S b/arch/arm/mach-cns3xxx/include/mach/entry-macro.S index 6bd83ed90afe..d87bfc397d39 100644 --- a/arch/arm/mach-cns3xxx/include/mach/entry-macro.S +++ b/arch/arm/mach-cns3xxx/include/mach/entry-macro.S @@ -8,7 +8,6 @@ * published by the Free Software Foundation. */ -#include <mach/hardware.h> #include <asm/hardware/entry-macro-gic.S> .macro disable_fiq diff --git a/arch/arm/mach-cns3xxx/include/mach/system.h b/arch/arm/mach-cns3xxx/include/mach/system.h index 58bb03ae3cf4..4f16c9b79f78 100644 --- a/arch/arm/mach-cns3xxx/include/mach/system.h +++ b/arch/arm/mach-cns3xxx/include/mach/system.h @@ -13,7 +13,6 @@ #include <linux/io.h> #include <asm/proc-fns.h> -#include <mach/hardware.h> static inline void arch_idle(void) { diff --git a/arch/arm/mach-cns3xxx/include/mach/uncompress.h b/arch/arm/mach-cns3xxx/include/mach/uncompress.h index de8ead9b91f7..a91b6058ab4f 100644 --- a/arch/arm/mach-cns3xxx/include/mach/uncompress.h +++ b/arch/arm/mach-cns3xxx/include/mach/uncompress.h @@ -8,7 +8,6 @@ */ #include <asm/mach-types.h> -#include <mach/hardware.h> #include <mach/cns3xxx.h> #define AMBA_UART_DR(base) (*(volatile unsigned char *)((base) + 0x00)) diff --git a/arch/arm/mach-cns3xxx/pcie.c b/arch/arm/mach-cns3xxx/pcie.c index 06fd25d70aec..0f8fca48a5ed 100644 --- a/arch/arm/mach-cns3xxx/pcie.c +++ b/arch/arm/mach-cns3xxx/pcie.c @@ -49,7 +49,7 @@ static struct cns3xxx_pcie *sysdata_to_cnspci(void *sysdata) return &cns3xxx_pcie[root->domain]; } -static struct cns3xxx_pcie *pdev_to_cnspci(struct pci_dev *dev) +static struct cns3xxx_pcie *pdev_to_cnspci(const struct pci_dev *dev) { return sysdata_to_cnspci(dev->sysdata); } diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c index bd5394537c88..008d51407cd7 100644 --- a/arch/arm/mach-davinci/board-da850-evm.c +++ b/arch/arm/mach-davinci/board-da850-evm.c @@ -115,6 +115,32 @@ static struct spi_board_info da850evm_spi_info[] = { }, }; +#ifdef CONFIG_MTD +static void da850_evm_m25p80_notify_add(struct mtd_info *mtd) +{ + char *mac_addr = davinci_soc_info.emac_pdata->mac_addr; + size_t retlen; + + if (!strcmp(mtd->name, "MAC-Address")) { + mtd->read(mtd, 0, ETH_ALEN, &retlen, mac_addr); + if (retlen == ETH_ALEN) + pr_info("Read MAC addr from SPI Flash: %pM\n", + mac_addr); + } +} + +static struct mtd_notifier da850evm_spi_notifier = { + .add = da850_evm_m25p80_notify_add, +}; + +static void da850_evm_setup_mac_addr(void) +{ + register_mtd_user(&da850evm_spi_notifier); +} +#else +static void da850_evm_setup_mac_addr(void) { } +#endif + static struct mtd_partition da850_evm_norflash_partition[] = { { .name = "bootloaders + env", @@ -1244,6 +1270,8 @@ static __init void da850_evm_init(void) if (ret) pr_warning("da850_evm_init: sata registration failed: %d\n", ret); + + da850_evm_setup_mac_addr(); } #ifdef CONFIG_SERIAL_8250_CONSOLE diff --git a/arch/arm/mach-davinci/include/mach/psc.h b/arch/arm/mach-davinci/include/mach/psc.h index 47fd0bc3d3e7..fa59c097223d 100644 --- a/arch/arm/mach-davinci/include/mach/psc.h +++ b/arch/arm/mach-davinci/include/mach/psc.h @@ -243,7 +243,7 @@ #define PSC_STATE_DISABLE 2 #define PSC_STATE_ENABLE 3 -#define MDSTAT_STATE_MASK 0x1f +#define MDSTAT_STATE_MASK 0x3f #define MDCTL_FORCE BIT(31) #ifndef __ASSEMBLER__ diff --git a/arch/arm/mach-davinci/sleep.S b/arch/arm/mach-davinci/sleep.S index fb5e72b532b0..5f1e045a3ad1 100644 --- a/arch/arm/mach-davinci/sleep.S +++ b/arch/arm/mach-davinci/sleep.S @@ -217,7 +217,11 @@ ddr2clk_stop_done: ENDPROC(davinci_ddr_psc_config) CACHE_FLUSH: - .word arm926_flush_kern_cache_all +#ifdef CONFIG_CPU_V6 + .word v6_flush_kern_cache_all +#else + .word arm926_flush_kern_cache_all +#endif ENTRY(davinci_cpu_suspend_sz) .word . - davinci_cpu_suspend diff --git a/arch/arm/mach-dove/common.c b/arch/arm/mach-dove/common.c index 83dce859886d..a9e0dae86a26 100644 --- a/arch/arm/mach-dove/common.c +++ b/arch/arm/mach-dove/common.c @@ -158,7 +158,7 @@ void __init dove_spi0_init(void) void __init dove_spi1_init(void) { - orion_spi_init(DOVE_SPI1_PHYS_BASE, get_tclk()); + orion_spi_1_init(DOVE_SPI1_PHYS_BASE, get_tclk()); } /***************************************************************************** diff --git a/arch/arm/mach-ep93xx/include/mach/ts72xx.h b/arch/arm/mach-ep93xx/include/mach/ts72xx.h index 0eabec62cd9d..f1397a13e76b 100644 --- a/arch/arm/mach-ep93xx/include/mach/ts72xx.h +++ b/arch/arm/mach-ep93xx/include/mach/ts72xx.h @@ -6,7 +6,7 @@ * TS72xx memory map: * * virt phys size - * febff000 22000000 4K model number register + * febff000 22000000 4K model number register (bits 0-2) * febfe000 22400000 4K options register * febfd000 22800000 4K options register #2 * febf9000 10800000 4K TS-5620 RTC index register @@ -20,6 +20,9 @@ #define TS72XX_MODEL_TS7200 0x00 #define TS72XX_MODEL_TS7250 0x01 #define TS72XX_MODEL_TS7260 0x02 +#define TS72XX_MODEL_TS7300 0x03 +#define TS72XX_MODEL_TS7400 0x04 +#define TS72XX_MODEL_MASK 0x07 #define TS72XX_OPTIONS_PHYS_BASE 0x22400000 @@ -51,19 +54,34 @@ #ifndef __ASSEMBLY__ +static inline int ts72xx_model(void) +{ + return __raw_readb(TS72XX_MODEL_VIRT_BASE) & TS72XX_MODEL_MASK; +} + static inline int board_is_ts7200(void) { - return __raw_readb(TS72XX_MODEL_VIRT_BASE) == TS72XX_MODEL_TS7200; + return ts72xx_model() == TS72XX_MODEL_TS7200; } static inline int board_is_ts7250(void) { - return __raw_readb(TS72XX_MODEL_VIRT_BASE) == TS72XX_MODEL_TS7250; + return ts72xx_model() == TS72XX_MODEL_TS7250; } static inline int board_is_ts7260(void) { - return __raw_readb(TS72XX_MODEL_VIRT_BASE) == TS72XX_MODEL_TS7260; + return ts72xx_model() == TS72XX_MODEL_TS7260; +} + +static inline int board_is_ts7300(void) +{ + return ts72xx_model() == TS72XX_MODEL_TS7300; +} + +static inline int board_is_ts7400(void) +{ + return ts72xx_model() == TS72XX_MODEL_TS7400; } static inline int is_max197_installed(void) diff --git a/arch/arm/mach-exynos4/clock.c b/arch/arm/mach-exynos4/clock.c index 851dea018578..79d6cd0c8e7b 100644 --- a/arch/arm/mach-exynos4/clock.c +++ b/arch/arm/mach-exynos4/clock.c @@ -520,7 +520,7 @@ static struct clk init_clocks_off[] = { .ctrlbit = (1 << 21), }, { .name = "ac97", - .id = -1, + .devname = "samsung-ac97", .enable = exynos4_clk_ip_peril_ctrl, .ctrlbit = (1 << 27), }, { @@ -1160,7 +1160,7 @@ void __init_or_cpufreq exynos4_setup_clocks(void) vpllsrc = clk_get_rate(&clk_vpllsrc.clk); vpll = s5p_get_pll46xx(vpllsrc, __raw_readl(S5P_VPLL_CON0), - __raw_readl(S5P_VPLL_CON1), pll_4650); + __raw_readl(S5P_VPLL_CON1), pll_4650c); clk_fout_apll.ops = &exynos4_fout_apll_ops; clk_fout_mpll.rate = mpll; diff --git a/arch/arm/mach-exynos4/cpu.c b/arch/arm/mach-exynos4/cpu.c index 2d8a40c9e6e5..746d6fc6d397 100644 --- a/arch/arm/mach-exynos4/cpu.c +++ b/arch/arm/mach-exynos4/cpu.c @@ -24,12 +24,13 @@ #include <plat/exynos4.h> #include <plat/adc-core.h> #include <plat/sdhci.h> -#include <plat/devs.h> #include <plat/fb-core.h> #include <plat/fimc-core.h> #include <plat/iic-core.h> +#include <plat/reset.h> #include <mach/regs-irq.h> +#include <mach/regs-pmu.h> extern int combiner_init(unsigned int combiner_nr, void __iomem *base, unsigned int irq_start); @@ -128,6 +129,11 @@ static void exynos4_idle(void) local_irq_enable(); } +static void exynos4_sw_reset(void) +{ + __raw_writel(0x1, S5P_SWRESET); +} + /* * exynos4_map_io * @@ -241,5 +247,8 @@ int __init exynos4_init(void) /* set idle function */ pm_idle = exynos4_idle; + /* set sw_reset function */ + s5p_reset_hook = exynos4_sw_reset; + return sysdev_register(&exynos4_sysdev); } diff --git a/arch/arm/mach-exynos4/include/mach/irqs.h b/arch/arm/mach-exynos4/include/mach/irqs.h index 934d2a493982..f8952f8f3757 100644 --- a/arch/arm/mach-exynos4/include/mach/irqs.h +++ b/arch/arm/mach-exynos4/include/mach/irqs.h @@ -80,9 +80,8 @@ #define IRQ_HSMMC3 IRQ_SPI(76) #define IRQ_DWMCI IRQ_SPI(77) -#define IRQ_MIPICSI0 IRQ_SPI(78) - -#define IRQ_MIPICSI1 IRQ_SPI(80) +#define IRQ_MIPI_CSIS0 IRQ_SPI(78) +#define IRQ_MIPI_CSIS1 IRQ_SPI(80) #define IRQ_ONENAND_AUDI IRQ_SPI(82) #define IRQ_ROTATOR IRQ_SPI(83) diff --git a/arch/arm/mach-exynos4/include/mach/regs-pmu.h b/arch/arm/mach-exynos4/include/mach/regs-pmu.h index fa49bbb8e7b0..cdf9b47c303c 100644 --- a/arch/arm/mach-exynos4/include/mach/regs-pmu.h +++ b/arch/arm/mach-exynos4/include/mach/regs-pmu.h @@ -29,6 +29,8 @@ #define S5P_USE_STANDBY_WFE1 (1 << 25) #define S5P_USE_MASK ((0x3 << 16) | (0x3 << 24)) +#define S5P_SWRESET S5P_PMUREG(0x0400) + #define S5P_WAKEUP_STAT S5P_PMUREG(0x0600) #define S5P_EINT_WAKEUP_MASK S5P_PMUREG(0x0604) #define S5P_WAKEUP_MASK S5P_PMUREG(0x0608) diff --git a/arch/arm/mach-exynos4/irq-eint.c b/arch/arm/mach-exynos4/irq-eint.c index 9d87d2ac7f68..badb8c66fc9b 100644 --- a/arch/arm/mach-exynos4/irq-eint.c +++ b/arch/arm/mach-exynos4/irq-eint.c @@ -23,6 +23,8 @@ #include <mach/regs-gpio.h> +#include <asm/mach/irq.h> + static DEFINE_SPINLOCK(eint_lock); static unsigned int eint0_15_data[16]; @@ -184,8 +186,11 @@ static inline void exynos4_irq_demux_eint(unsigned int start) static void exynos4_irq_demux_eint16_31(unsigned int irq, struct irq_desc *desc) { + struct irq_chip *chip = irq_get_chip(irq); + chained_irq_enter(chip, desc); exynos4_irq_demux_eint(IRQ_EINT(16)); exynos4_irq_demux_eint(IRQ_EINT(24)); + chained_irq_exit(chip, desc); } static void exynos4_irq_eint0_15(unsigned int irq, struct irq_desc *desc) @@ -193,6 +198,7 @@ static void exynos4_irq_eint0_15(unsigned int irq, struct irq_desc *desc) u32 *irq_data = irq_get_handler_data(irq); struct irq_chip *chip = irq_get_chip(irq); + chained_irq_enter(chip, desc); chip->irq_mask(&desc->irq_data); if (chip->irq_ack) @@ -201,6 +207,7 @@ static void exynos4_irq_eint0_15(unsigned int irq, struct irq_desc *desc) generic_handle_irq(*irq_data); chip->irq_unmask(&desc->irq_data); + chained_irq_exit(chip, desc); } int __init exynos4_init_irq_eint(void) diff --git a/arch/arm/mach-exynos4/mach-universal_c210.c b/arch/arm/mach-exynos4/mach-universal_c210.c index 0e280d12301e..b3b5d8911004 100644 --- a/arch/arm/mach-exynos4/mach-universal_c210.c +++ b/arch/arm/mach-exynos4/mach-universal_c210.c @@ -79,7 +79,7 @@ static struct s3c2410_uartcfg universal_uartcfgs[] __initdata = { }; static struct regulator_consumer_supply max8952_consumer = - REGULATOR_SUPPLY("vddarm", NULL); + REGULATOR_SUPPLY("vdd_arm", NULL); static struct max8952_platform_data universal_max8952_pdata __initdata = { .gpio_vid0 = EXYNOS4_GPX0(3), @@ -105,7 +105,7 @@ static struct max8952_platform_data universal_max8952_pdata __initdata = { }; static struct regulator_consumer_supply lp3974_buck1_consumer = - REGULATOR_SUPPLY("vddint", NULL); + REGULATOR_SUPPLY("vdd_int", NULL); static struct regulator_consumer_supply lp3974_buck2_consumer = REGULATOR_SUPPLY("vddg3d", NULL); diff --git a/arch/arm/mach-exynos4/mct.c b/arch/arm/mach-exynos4/mct.c index 1ae059b7ad7b..ddd86864fb83 100644 --- a/arch/arm/mach-exynos4/mct.c +++ b/arch/arm/mach-exynos4/mct.c @@ -132,12 +132,18 @@ static cycle_t exynos4_frc_read(struct clocksource *cs) return ((cycle_t)hi << 32) | lo; } +static void exynos4_frc_resume(struct clocksource *cs) +{ + exynos4_mct_frc_start(0, 0); +} + struct clocksource mct_frc = { .name = "mct-frc", .rating = 400, .read = exynos4_frc_read, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .resume = exynos4_frc_resume, }; static void __init exynos4_clocksource_init(void) @@ -389,9 +395,11 @@ static void exynos4_mct_tick_init(struct clock_event_device *evt) } /* Setup the local clock events for a CPU */ -void __cpuinit local_timer_setup(struct clock_event_device *evt) +int __cpuinit local_timer_setup(struct clock_event_device *evt) { exynos4_mct_tick_init(evt); + + return 0; } int local_timer_ack(void) diff --git a/arch/arm/mach-exynos4/platsmp.c b/arch/arm/mach-exynos4/platsmp.c index 7c2282c6ba81..df6ef1b2f98b 100644 --- a/arch/arm/mach-exynos4/platsmp.c +++ b/arch/arm/mach-exynos4/platsmp.c @@ -106,6 +106,8 @@ void __cpuinit platform_secondary_init(unsigned int cpu) */ spin_lock(&boot_lock); spin_unlock(&boot_lock); + + set_cpu_online(cpu, true); } int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) diff --git a/arch/arm/mach-exynos4/setup-keypad.c b/arch/arm/mach-exynos4/setup-keypad.c index 1ee0ebff111f..7862bfb5933d 100644 --- a/arch/arm/mach-exynos4/setup-keypad.c +++ b/arch/arm/mach-exynos4/setup-keypad.c @@ -19,15 +19,16 @@ void samsung_keypad_cfg_gpio(unsigned int rows, unsigned int cols) if (rows > 8) { /* Set all the necessary GPX2 pins: KP_ROW[0~7] */ - s3c_gpio_cfgrange_nopull(EXYNOS4_GPX2(0), 8, S3C_GPIO_SFN(3)); + s3c_gpio_cfgall_range(EXYNOS4_GPX2(0), 8, S3C_GPIO_SFN(3), + S3C_GPIO_PULL_UP); /* Set all the necessary GPX3 pins: KP_ROW[8~] */ - s3c_gpio_cfgrange_nopull(EXYNOS4_GPX3(0), (rows - 8), - S3C_GPIO_SFN(3)); + s3c_gpio_cfgall_range(EXYNOS4_GPX3(0), (rows - 8), + S3C_GPIO_SFN(3), S3C_GPIO_PULL_UP); } else { /* Set all the necessary GPX2 pins: KP_ROW[x] */ - s3c_gpio_cfgrange_nopull(EXYNOS4_GPX2(0), rows, - S3C_GPIO_SFN(3)); + s3c_gpio_cfgall_range(EXYNOS4_GPX2(0), rows, S3C_GPIO_SFN(3), + S3C_GPIO_PULL_UP); } /* Set all the necessary GPX1 pins to special-function 3: KP_COL[x] */ diff --git a/arch/arm/mach-exynos4/setup-usb-phy.c b/arch/arm/mach-exynos4/setup-usb-phy.c index 0883c1b824b9..39aca045f660 100644 --- a/arch/arm/mach-exynos4/setup-usb-phy.c +++ b/arch/arm/mach-exynos4/setup-usb-phy.c @@ -82,7 +82,7 @@ static int exynos4_usb_phy1_init(struct platform_device *pdev) rstcon &= ~(HOST_LINK_PORT_SWRST_MASK | PHY1_SWRST_MASK); writel(rstcon, EXYNOS4_RSTCON); - udelay(50); + udelay(80); clk_disable(otg_clk); clk_put(otg_clk); diff --git a/arch/arm/mach-footbridge/Kconfig b/arch/arm/mach-footbridge/Kconfig index dc26fff22cf0..c8e7afcf14ec 100644 --- a/arch/arm/mach-footbridge/Kconfig +++ b/arch/arm/mach-footbridge/Kconfig @@ -62,6 +62,7 @@ config ARCH_EBSA285_HOST config ARCH_NETWINDER bool "NetWinder" select CLKSRC_I8253 + select CLKEVT_I8253 select FOOTBRIDGE_HOST select ISA select ISA_DMA diff --git a/arch/arm/mach-footbridge/dc21285.c b/arch/arm/mach-footbridge/dc21285.c index 1331fff51ae2..18c32a5541d9 100644 --- a/arch/arm/mach-footbridge/dc21285.c +++ b/arch/arm/mach-footbridge/dc21285.c @@ -18,6 +18,7 @@ #include <linux/irq.h> #include <linux/io.h> #include <linux/spinlock.h> +#include <video/vga.h> #include <asm/irq.h> #include <asm/system.h> diff --git a/arch/arm/mach-imx/mach-cpuimx27.c b/arch/arm/mach-imx/mach-cpuimx27.c index 87887ac5806b..f851fe903687 100644 --- a/arch/arm/mach-imx/mach-cpuimx27.c +++ b/arch/arm/mach-imx/mach-cpuimx27.c @@ -310,7 +310,7 @@ static struct sys_timer eukrea_cpuimx27_timer = { .init = eukrea_cpuimx27_timer_init, }; -MACHINE_START(CPUIMX27, "EUKREA CPUIMX27") +MACHINE_START(EUKREA_CPUIMX27, "EUKREA CPUIMX27") .boot_params = MX27_PHYS_OFFSET + 0x100, .map_io = mx27_map_io, .init_early = imx27_init_early, diff --git a/arch/arm/mach-imx/mach-cpuimx35.c b/arch/arm/mach-imx/mach-cpuimx35.c index f39a478ba1a6..4bd083ba9af2 100644 --- a/arch/arm/mach-imx/mach-cpuimx35.c +++ b/arch/arm/mach-imx/mach-cpuimx35.c @@ -192,7 +192,7 @@ struct sys_timer eukrea_cpuimx35_timer = { .init = eukrea_cpuimx35_timer_init, }; -MACHINE_START(EUKREA_CPUIMX35, "Eukrea CPUIMX35") +MACHINE_START(EUKREA_CPUIMX35SD, "Eukrea CPUIMX35") /* Maintainer: Eukrea Electromatique */ .boot_params = MX3x_PHYS_OFFSET + 0x100, .map_io = mx35_map_io, diff --git a/arch/arm/mach-imx/mach-eukrea_cpuimx25.c b/arch/arm/mach-imx/mach-eukrea_cpuimx25.c index da36da52969d..2442d5da883d 100644 --- a/arch/arm/mach-imx/mach-eukrea_cpuimx25.c +++ b/arch/arm/mach-imx/mach-eukrea_cpuimx25.c @@ -161,7 +161,7 @@ static struct sys_timer eukrea_cpuimx25_timer = { .init = eukrea_cpuimx25_timer_init, }; -MACHINE_START(EUKREA_CPUIMX25, "Eukrea CPUIMX25") +MACHINE_START(EUKREA_CPUIMX25SD, "Eukrea CPUIMX25") /* Maintainer: Eukrea Electromatique */ .boot_params = MX25_PHYS_OFFSET + 0x100, .map_io = mx25_map_io, diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c index 2fbbdd5eac35..8cdc730dcb3a 100644 --- a/arch/arm/mach-integrator/integrator_ap.c +++ b/arch/arm/mach-integrator/integrator_ap.c @@ -32,6 +32,7 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/mtd/physmap.h> +#include <video/vga.h> #include <mach/hardware.h> #include <mach/platform.h> @@ -154,6 +155,7 @@ static struct map_desc ap_io_desc[] __initdata = { static void __init ap_map_io(void) { iotable_init(ap_io_desc, ARRAY_SIZE(ap_io_desc)); + vga_base = PCI_MEMORY_VADDR; } #define INTEGRATOR_SC_VALID_INT 0x003fffff @@ -337,15 +339,15 @@ static unsigned long timer_reload; static void integrator_clocksource_init(u32 khz) { void __iomem *base = (void __iomem *)TIMER2_VA_BASE; - u32 ctrl = TIMER_CTRL_ENABLE; + u32 ctrl = TIMER_CTRL_ENABLE | TIMER_CTRL_PERIODIC; if (khz >= 1500) { khz /= 16; - ctrl = TIMER_CTRL_DIV16; + ctrl |= TIMER_CTRL_DIV16; } - writel(ctrl, base + TIMER_CTRL); writel(0xffff, base + TIMER_LOAD); + writel(ctrl, base + TIMER_CTRL); clocksource_mmio_init(base + TIMER_VALUE, "timer2", khz * 1000, 200, 16, clocksource_mmio_readl_down); diff --git a/arch/arm/mach-integrator/pci_v3.c b/arch/arm/mach-integrator/pci_v3.c index dd56bfb351e3..11b86e5b71c2 100644 --- a/arch/arm/mach-integrator/pci_v3.c +++ b/arch/arm/mach-integrator/pci_v3.c @@ -27,7 +27,6 @@ #include <linux/spinlock.h> #include <linux/init.h> #include <linux/io.h> -#include <video/vga.h> #include <mach/hardware.h> #include <mach/platform.h> @@ -505,7 +504,6 @@ void __init pci_v3_preinit(void) pcibios_min_io = 0x6000; pcibios_min_mem = 0x00100000; - vga_base = PCI_MEMORY_VADDR; /* * Hook in our fault handler for PCI errors diff --git a/arch/arm/mach-omap2/clock3xxx_data.c b/arch/arm/mach-omap2/clock3xxx_data.c index ffd55b1c4396..b9b844683147 100644 --- a/arch/arm/mach-omap2/clock3xxx_data.c +++ b/arch/arm/mach-omap2/clock3xxx_data.c @@ -3078,6 +3078,7 @@ static struct clk gpt12_fck = { .name = "gpt12_fck", .ops = &clkops_null, .parent = &secure_32k_fck, + .clkdm_name = "wkup_clkdm", .recalc = &followparent_recalc, }; @@ -3085,6 +3086,7 @@ static struct clk wdt1_fck = { .name = "wdt1_fck", .ops = &clkops_null, .parent = &secure_32k_fck, + .clkdm_name = "wkup_clkdm", .recalc = &followparent_recalc, }; diff --git a/arch/arm/mach-omap2/clock44xx_data.c b/arch/arm/mach-omap2/clock44xx_data.c index 2af0e3f00ce1..c0b6fbda3408 100644 --- a/arch/arm/mach-omap2/clock44xx_data.c +++ b/arch/arm/mach-omap2/clock44xx_data.c @@ -3376,10 +3376,18 @@ int __init omap4xxx_clk_init(void) } else if (cpu_is_omap446x()) { cpu_mask = RATE_IN_4460; cpu_clkflg = CK_446X; + } else { + return 0; } clk_init(&omap2_clk_functions); - omap2_clk_disable_clkdm_control(); + + /* + * Must stay commented until all OMAP SoC drivers are + * converted to runtime PM, or drivers may start crashing + * + * omap2_clk_disable_clkdm_control(); + */ for (c = omap44xx_clks; c < omap44xx_clks + ARRAY_SIZE(omap44xx_clks); c++) diff --git a/arch/arm/mach-omap2/clockdomain.c b/arch/arm/mach-omap2/clockdomain.c index ab7db083f97f..8f0890685d7b 100644 --- a/arch/arm/mach-omap2/clockdomain.c +++ b/arch/arm/mach-omap2/clockdomain.c @@ -747,6 +747,7 @@ int clkdm_wakeup(struct clockdomain *clkdm) spin_lock_irqsave(&clkdm->lock, flags); clkdm->_flags &= ~_CLKDM_FLAG_HWSUP_ENABLED; ret = arch_clkdm->clkdm_wakeup(clkdm); + ret |= pwrdm_state_switch(clkdm->pwrdm.ptr); spin_unlock_irqrestore(&clkdm->lock, flags); return ret; } @@ -818,6 +819,7 @@ void clkdm_deny_idle(struct clockdomain *clkdm) spin_lock_irqsave(&clkdm->lock, flags); clkdm->_flags &= ~_CLKDM_FLAG_HWSUP_ENABLED; arch_clkdm->clkdm_deny_idle(clkdm); + pwrdm_state_switch(clkdm->pwrdm.ptr); spin_unlock_irqrestore(&clkdm->lock, flags); } diff --git a/arch/arm/mach-omap2/omap_hwmod_2430_data.c b/arch/arm/mach-omap2/omap_hwmod_2430_data.c index 16743c7d6e8e..408193d8e044 100644 --- a/arch/arm/mach-omap2/omap_hwmod_2430_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_2430_data.c @@ -192,6 +192,7 @@ static struct omap_hwmod_addr_space omap2430_usbhsotg_addrs[] = { .pa_end = OMAP243X_HS_BASE + SZ_4K - 1, .flags = ADDR_TYPE_RT }, + { } }; /* l4_core ->usbhsotg interface */ diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c index 3feb35911a32..472bf22d5e84 100644 --- a/arch/arm/mach-omap2/pm.c +++ b/arch/arm/mach-omap2/pm.c @@ -130,7 +130,6 @@ int omap_set_pwrdm_state(struct powerdomain *pwrdm, u32 state) } else { hwsup = clkdm_in_hwsup(pwrdm->pwrdm_clkdms[0]); clkdm_wakeup(pwrdm->pwrdm_clkdms[0]); - pwrdm_wait_transition(pwrdm); sleep_switch = FORCEWAKEUP_SWITCH; } } @@ -156,7 +155,6 @@ int omap_set_pwrdm_state(struct powerdomain *pwrdm, u32 state) return ret; } - pwrdm_wait_transition(pwrdm); pwrdm_state_switch(pwrdm); err: return ret; diff --git a/arch/arm/mach-omap2/powerdomain.c b/arch/arm/mach-omap2/powerdomain.c index 9af08473bf10..ef71fdd40fc4 100644 --- a/arch/arm/mach-omap2/powerdomain.c +++ b/arch/arm/mach-omap2/powerdomain.c @@ -195,28 +195,35 @@ static int _pwrdm_post_transition_cb(struct powerdomain *pwrdm, void *unused) /** * pwrdm_init - set up the powerdomain layer - * @pwrdm_list: array of struct powerdomain pointers to register + * @pwrdms: array of struct powerdomain pointers to register * @custom_funcs: func pointers for arch specific implementations * - * Loop through the array of powerdomains @pwrdm_list, registering all - * that are available on the current CPU. If pwrdm_list is supplied - * and not null, all of the referenced powerdomains will be - * registered. No return value. XXX pwrdm_list is not really a - * "list"; it is an array. Rename appropriately. + * Loop through the array of powerdomains @pwrdms, registering all + * that are available on the current CPU. Also, program all + * powerdomain target state as ON; this is to prevent domains from + * hitting low power states (if bootloader has target states set to + * something other than ON) and potentially even losing context while + * PM is not fully initialized. The PM late init code can then program + * the desired target state for all the power domains. No return + * value. */ -void pwrdm_init(struct powerdomain **pwrdm_list, struct pwrdm_ops *custom_funcs) +void pwrdm_init(struct powerdomain **pwrdms, struct pwrdm_ops *custom_funcs) { struct powerdomain **p = NULL; + struct powerdomain *temp_p; if (!custom_funcs) WARN(1, "powerdomain: No custom pwrdm functions registered\n"); else arch_pwrdm = custom_funcs; - if (pwrdm_list) { - for (p = pwrdm_list; *p; p++) + if (pwrdms) { + for (p = pwrdms; *p; p++) _pwrdm_register(*p); } + + list_for_each_entry(temp_p, &pwrdm_list, node) + pwrdm_set_next_pwrst(temp_p, PWRDM_POWER_ON); } /** diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c index a6eddae82a0b..c105556a0ee1 100644 --- a/arch/arm/mach-orion5x/dns323-setup.c +++ b/arch/arm/mach-orion5x/dns323-setup.c @@ -77,7 +77,7 @@ static int __init dns323_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) /* * Check for devices with hard-wired IRQs. */ - irq = orion5x_pci_map_irq(const dev, slot, pin); + irq = orion5x_pci_map_irq(dev, slot, pin); if (irq != -1) return irq; diff --git a/arch/arm/mach-orion5x/pci.c b/arch/arm/mach-orion5x/pci.c index 28b8760ab9fa..bc4a920e26ee 100644 --- a/arch/arm/mach-orion5x/pci.c +++ b/arch/arm/mach-orion5x/pci.c @@ -14,6 +14,7 @@ #include <linux/pci.h> #include <linux/slab.h> #include <linux/mbus.h> +#include <video/vga.h> #include <asm/irq.h> #include <asm/mach/pci.h> #include <plat/pcie.h> diff --git a/arch/arm/mach-prima2/clock.c b/arch/arm/mach-prima2/clock.c index f9a2aaf63f71..615a4e75ceab 100644 --- a/arch/arm/mach-prima2/clock.c +++ b/arch/arm/mach-prima2/clock.c @@ -481,6 +481,7 @@ static void __init sirfsoc_clk_init(void) static struct of_device_id clkc_ids[] = { { .compatible = "sirf,prima2-clkc" }, + {}, }; void __init sirfsoc_of_clk_init(void) diff --git a/arch/arm/mach-prima2/irq.c b/arch/arm/mach-prima2/irq.c index c3404cbb6ff7..7af254d046ba 100644 --- a/arch/arm/mach-prima2/irq.c +++ b/arch/arm/mach-prima2/irq.c @@ -51,6 +51,7 @@ static __init void sirfsoc_irq_init(void) static struct of_device_id intc_ids[] = { { .compatible = "sirf,prima2-intc" }, + {}, }; void __init sirfsoc_of_irq_init(void) diff --git a/arch/arm/mach-prima2/rstc.c b/arch/arm/mach-prima2/rstc.c index d074786e83d4..492cfa8d2610 100644 --- a/arch/arm/mach-prima2/rstc.c +++ b/arch/arm/mach-prima2/rstc.c @@ -19,6 +19,7 @@ static DEFINE_MUTEX(rstc_lock); static struct of_device_id rstc_ids[] = { { .compatible = "sirf,prima2-rstc" }, + {}, }; static int __init sirfsoc_of_rstc_init(void) diff --git a/arch/arm/mach-prima2/timer.c b/arch/arm/mach-prima2/timer.c index 44027f34a88a..ed7ec48d11da 100644 --- a/arch/arm/mach-prima2/timer.c +++ b/arch/arm/mach-prima2/timer.c @@ -190,6 +190,7 @@ static void __init sirfsoc_timer_init(void) static struct of_device_id timer_ids[] = { { .compatible = "sirf,prima2-tick" }, + {}, }; static void __init sirfsoc_of_timer_map(void) diff --git a/arch/arm/mach-realview/include/mach/system.h b/arch/arm/mach-realview/include/mach/system.h index a30f2e3ec178..6657ff231161 100644 --- a/arch/arm/mach-realview/include/mach/system.h +++ b/arch/arm/mach-realview/include/mach/system.h @@ -44,6 +44,7 @@ static inline void arch_reset(char mode, const char *cmd) */ if (realview_reset) realview_reset(mode); + dsb(); } #endif diff --git a/arch/arm/mach-s3c64xx/mach-smdk6410.c b/arch/arm/mach-s3c64xx/mach-smdk6410.c index ecbea92bf83b..a9f3183e0290 100644 --- a/arch/arm/mach-s3c64xx/mach-smdk6410.c +++ b/arch/arm/mach-s3c64xx/mach-smdk6410.c @@ -262,45 +262,6 @@ static struct samsung_keypad_platdata smdk6410_keypad_data __initdata = { .cols = 8, }; -static int smdk6410_backlight_init(struct device *dev) -{ - int ret; - - ret = gpio_request(S3C64XX_GPF(15), "Backlight"); - if (ret) { - printk(KERN_ERR "failed to request GPF for PWM-OUT1\n"); - return ret; - } - - /* Configure GPIO pin with S3C64XX_GPF15_PWM_TOUT1 */ - s3c_gpio_cfgpin(S3C64XX_GPF(15), S3C_GPIO_SFN(2)); - - return 0; -} - -static void smdk6410_backlight_exit(struct device *dev) -{ - s3c_gpio_cfgpin(S3C64XX_GPF(15), S3C_GPIO_OUTPUT); - gpio_free(S3C64XX_GPF(15)); -} - -static struct platform_pwm_backlight_data smdk6410_backlight_data = { - .pwm_id = 1, - .max_brightness = 255, - .dft_brightness = 255, - .pwm_period_ns = 78770, - .init = smdk6410_backlight_init, - .exit = smdk6410_backlight_exit, -}; - -static struct platform_device smdk6410_backlight_device = { - .name = "pwm-backlight", - .dev = { - .parent = &s3c_device_timer[1].dev, - .platform_data = &smdk6410_backlight_data, - }, -}; - static struct map_desc smdk6410_iodesc[] = {}; static struct platform_device *smdk6410_devices[] __initdata = { diff --git a/arch/arm/mach-s3c64xx/pm.c b/arch/arm/mach-s3c64xx/pm.c index 8bad64370689..055e2858b0dd 100644 --- a/arch/arm/mach-s3c64xx/pm.c +++ b/arch/arm/mach-s3c64xx/pm.c @@ -16,6 +16,7 @@ #include <linux/suspend.h> #include <linux/serial_core.h> #include <linux/io.h> +#include <linux/gpio.h> #include <mach/map.h> #include <mach/irqs.h> diff --git a/arch/arm/mach-s5p64x0/irq-eint.c b/arch/arm/mach-s5p64x0/irq-eint.c index 69ed4545112b..fe7380f5c3cd 100644 --- a/arch/arm/mach-s5p64x0/irq-eint.c +++ b/arch/arm/mach-s5p64x0/irq-eint.c @@ -129,7 +129,7 @@ static int s5p64x0_alloc_gc(void) } ct = gc->chip_types; - ct->chip.irq_ack = irq_gc_ack; + ct->chip.irq_ack = irq_gc_ack_set_bit; ct->chip.irq_mask = irq_gc_mask_set_bit; ct->chip.irq_unmask = irq_gc_mask_clr_bit; ct->chip.irq_set_type = s5p64x0_irq_eint_set_type; diff --git a/arch/arm/mach-s5pv210/pm.c b/arch/arm/mach-s5pv210/pm.c index 309e388a8a83..f149d278377b 100644 --- a/arch/arm/mach-s5pv210/pm.c +++ b/arch/arm/mach-s5pv210/pm.c @@ -88,7 +88,7 @@ static struct sleep_save s5pv210_core_save[] = { SAVE_ITEM(S3C2410_TCNTO(0)), }; -void s5pv210_cpu_suspend(unsigned long arg) +static int s5pv210_cpu_suspend(unsigned long arg) { unsigned long tmp; diff --git a/arch/arm/mach-shmobile/board-ag5evm.c b/arch/arm/mach-shmobile/board-ag5evm.c index ce5c2513c6ce..cdfdd624d21d 100644 --- a/arch/arm/mach-shmobile/board-ag5evm.c +++ b/arch/arm/mach-shmobile/board-ag5evm.c @@ -341,6 +341,7 @@ static struct platform_device mipidsi0_device = { static struct sh_mobile_sdhi_info sdhi0_info = { .dma_slave_tx = SHDMA_SLAVE_SDHI0_TX, .dma_slave_rx = SHDMA_SLAVE_SDHI0_RX, + .tmio_flags = TMIO_MMC_HAS_IDLE_WAIT, .tmio_caps = MMC_CAP_SD_HIGHSPEED, .tmio_ocr_mask = MMC_VDD_27_28 | MMC_VDD_28_29, }; @@ -382,7 +383,7 @@ void ag5evm_sdhi1_set_pwr(struct platform_device *pdev, int state) } static struct sh_mobile_sdhi_info sh_sdhi1_info = { - .tmio_flags = TMIO_MMC_WRPROTECT_DISABLE, + .tmio_flags = TMIO_MMC_WRPROTECT_DISABLE | TMIO_MMC_HAS_IDLE_WAIT, .tmio_caps = MMC_CAP_NONREMOVABLE | MMC_CAP_SDIO_IRQ, .tmio_ocr_mask = MMC_VDD_32_33 | MMC_VDD_33_34, .set_pwr = ag5evm_sdhi1_set_pwr, diff --git a/arch/arm/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c index 9e0856b2f9e9..523f608eb8cf 100644 --- a/arch/arm/mach-shmobile/board-ap4evb.c +++ b/arch/arm/mach-shmobile/board-ap4evb.c @@ -1412,6 +1412,7 @@ static void __init ap4evb_init(void) fsi_init_pm_clock(); sh7372_pm_init(); pm_clk_add(&fsi_device.dev, "spu2"); + pm_clk_add(&lcdc1_device.dev, "hdmi"); } static void __init ap4evb_timer_init(void) diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c index d41c01f83f15..17c19dc25604 100644 --- a/arch/arm/mach-shmobile/board-mackerel.c +++ b/arch/arm/mach-shmobile/board-mackerel.c @@ -641,6 +641,8 @@ static struct usbhs_private usbhs0_private = { }, .driver_param = { .buswait_bwait = 4, + .d0_tx_id = SHDMA_SLAVE_USB0_TX, + .d1_rx_id = SHDMA_SLAVE_USB0_RX, }, }, }; @@ -810,6 +812,8 @@ static struct usbhs_private usbhs1_private = { .buswait_bwait = 4, .pipe_type = usbhs1_pipe_cfg, .pipe_size = ARRAY_SIZE(usbhs1_pipe_cfg), + .d0_tx_id = SHDMA_SLAVE_USB1_TX, + .d1_rx_id = SHDMA_SLAVE_USB1_RX, }, }, }; @@ -1588,6 +1592,7 @@ static void __init mackerel_init(void) hdmi_init_pm_clock(); sh7372_pm_init(); pm_clk_add(&fsi_device.dev, "spu2"); + pm_clk_add(&hdmi_lcdc_device.dev, "hdmi"); } static void __init mackerel_timer_init(void) diff --git a/arch/arm/mach-shmobile/clock-sh7372.c b/arch/arm/mach-shmobile/clock-sh7372.c index 6b1619a65dba..66975921e646 100644 --- a/arch/arm/mach-shmobile/clock-sh7372.c +++ b/arch/arm/mach-shmobile/clock-sh7372.c @@ -503,16 +503,17 @@ static struct clk *late_main_clks[] = { &sh7372_fsidivb_clk, }; -enum { MSTP001, +enum { MSTP001, MSTP000, MSTP131, MSTP130, MSTP129, MSTP128, MSTP127, MSTP126, MSTP125, MSTP118, MSTP117, MSTP116, MSTP113, MSTP106, MSTP101, MSTP100, MSTP223, - MSTP218, MSTP217, MSTP216, - MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200, - MSTP329, MSTP328, MSTP323, MSTP322, MSTP314, MSTP313, MSTP312, - MSTP423, MSTP415, MSTP413, MSTP411, MSTP410, MSTP406, MSTP403, + MSTP218, MSTP217, MSTP216, MSTP214, MSTP208, MSTP207, + MSTP206, MSTP205, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200, + MSTP328, MSTP323, MSTP322, MSTP314, MSTP313, MSTP312, + MSTP423, MSTP415, MSTP413, MSTP411, MSTP410, MSTP407, MSTP406, + MSTP405, MSTP404, MSTP403, MSTP400, MSTP_NR }; #define MSTP(_parent, _reg, _bit, _flags) \ @@ -520,6 +521,7 @@ enum { MSTP001, static struct clk mstp_clks[MSTP_NR] = { [MSTP001] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR0, 1, 0), /* IIC2 */ + [MSTP000] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR0, 0, 0), /* MSIOF0 */ [MSTP131] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 31, 0), /* VEU3 */ [MSTP130] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 30, 0), /* VEU2 */ [MSTP129] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 29, 0), /* VEU1 */ @@ -538,14 +540,16 @@ static struct clk mstp_clks[MSTP_NR] = { [MSTP218] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 18, 0), /* DMAC1 */ [MSTP217] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 17, 0), /* DMAC2 */ [MSTP216] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 16, 0), /* DMAC3 */ + [MSTP214] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 14, 0), /* USBDMAC */ + [MSTP208] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 8, 0), /* MSIOF1 */ [MSTP207] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 7, 0), /* SCIFA5 */ [MSTP206] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 6, 0), /* SCIFB */ + [MSTP205] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 5, 0), /* MSIOF2 */ [MSTP204] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 4, 0), /* SCIFA0 */ [MSTP203] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 3, 0), /* SCIFA1 */ [MSTP202] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 2, 0), /* SCIFA2 */ [MSTP201] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 1, 0), /* SCIFA3 */ [MSTP200] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 0, 0), /* SCIFA4 */ - [MSTP329] = MSTP(&r_clk, SMSTPCR3, 29, 0), /* CMT10 */ [MSTP328] = MSTP(&div6_clks[DIV6_SPU], SMSTPCR3, 28, 0), /* FSI2 */ [MSTP323] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 23, 0), /* IIC1 */ [MSTP322] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 22, 0), /* USB0 */ @@ -557,8 +561,12 @@ static struct clk mstp_clks[MSTP_NR] = { [MSTP413] = MSTP(&pllc1_div2_clk, SMSTPCR4, 13, 0), /* HDMI */ [MSTP411] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR4, 11, 0), /* IIC3 */ [MSTP410] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR4, 10, 0), /* IIC4 */ + [MSTP407] = MSTP(&div4_clks[DIV4_HP], SMSTPCR4, 7, 0), /* USB-DMAC1 */ [MSTP406] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR4, 6, 0), /* USB1 */ + [MSTP405] = MSTP(&r_clk, SMSTPCR4, 5, 0), /* CMT4 */ + [MSTP404] = MSTP(&r_clk, SMSTPCR4, 4, 0), /* CMT3 */ [MSTP403] = MSTP(&r_clk, SMSTPCR4, 3, 0), /* KEYSC */ + [MSTP400] = MSTP(&r_clk, SMSTPCR4, 0, 0), /* CMT2 */ }; static struct clk_lookup lookups[] = { @@ -609,6 +617,7 @@ static struct clk_lookup lookups[] = { /* MSTP32 clocks */ CLKDEV_DEV_ID("i2c-sh_mobile.2", &mstp_clks[MSTP001]), /* IIC2 */ + CLKDEV_DEV_ID("spi_sh_msiof.0", &mstp_clks[MSTP000]), /* MSIOF0 */ CLKDEV_DEV_ID("uio_pdrv_genirq.4", &mstp_clks[MSTP131]), /* VEU3 */ CLKDEV_DEV_ID("uio_pdrv_genirq.3", &mstp_clks[MSTP130]), /* VEU2 */ CLKDEV_DEV_ID("uio_pdrv_genirq.2", &mstp_clks[MSTP129]), /* VEU1 */ @@ -629,14 +638,16 @@ static struct clk_lookup lookups[] = { CLKDEV_DEV_ID("sh-dma-engine.0", &mstp_clks[MSTP218]), /* DMAC1 */ CLKDEV_DEV_ID("sh-dma-engine.1", &mstp_clks[MSTP217]), /* DMAC2 */ CLKDEV_DEV_ID("sh-dma-engine.2", &mstp_clks[MSTP216]), /* DMAC3 */ + CLKDEV_DEV_ID("sh-dma-engine.3", &mstp_clks[MSTP214]), /* USB-DMAC0 */ + CLKDEV_DEV_ID("spi_sh_msiof.1", &mstp_clks[MSTP208]), /* MSIOF1 */ CLKDEV_DEV_ID("sh-sci.5", &mstp_clks[MSTP207]), /* SCIFA5 */ CLKDEV_DEV_ID("sh-sci.6", &mstp_clks[MSTP206]), /* SCIFB */ + CLKDEV_DEV_ID("spi_sh_msiof.2", &mstp_clks[MSTP205]), /* MSIOF2 */ CLKDEV_DEV_ID("sh-sci.0", &mstp_clks[MSTP204]), /* SCIFA0 */ CLKDEV_DEV_ID("sh-sci.1", &mstp_clks[MSTP203]), /* SCIFA1 */ CLKDEV_DEV_ID("sh-sci.2", &mstp_clks[MSTP202]), /* SCIFA2 */ CLKDEV_DEV_ID("sh-sci.3", &mstp_clks[MSTP201]), /* SCIFA3 */ CLKDEV_DEV_ID("sh-sci.4", &mstp_clks[MSTP200]), /* SCIFA4 */ - CLKDEV_DEV_ID("sh_cmt.10", &mstp_clks[MSTP329]), /* CMT10 */ CLKDEV_DEV_ID("sh_fsi2", &mstp_clks[MSTP328]), /* FSI2 */ CLKDEV_DEV_ID("i2c-sh_mobile.1", &mstp_clks[MSTP323]), /* IIC1 */ CLKDEV_DEV_ID("r8a66597_hcd.0", &mstp_clks[MSTP322]), /* USB0 */ @@ -650,11 +661,17 @@ static struct clk_lookup lookups[] = { CLKDEV_DEV_ID("sh-mobile-hdmi", &mstp_clks[MSTP413]), /* HDMI */ CLKDEV_DEV_ID("i2c-sh_mobile.3", &mstp_clks[MSTP411]), /* IIC3 */ CLKDEV_DEV_ID("i2c-sh_mobile.4", &mstp_clks[MSTP410]), /* IIC4 */ + CLKDEV_DEV_ID("sh-dma-engine.4", &mstp_clks[MSTP407]), /* USB-DMAC1 */ CLKDEV_DEV_ID("r8a66597_hcd.1", &mstp_clks[MSTP406]), /* USB1 */ CLKDEV_DEV_ID("r8a66597_udc.1", &mstp_clks[MSTP406]), /* USB1 */ CLKDEV_DEV_ID("renesas_usbhs.1", &mstp_clks[MSTP406]), /* USB1 */ + CLKDEV_DEV_ID("sh_cmt.4", &mstp_clks[MSTP405]), /* CMT4 */ + CLKDEV_DEV_ID("sh_cmt.3", &mstp_clks[MSTP404]), /* CMT3 */ CLKDEV_DEV_ID("sh_keysc.0", &mstp_clks[MSTP403]), /* KEYSC */ + CLKDEV_DEV_ID("sh_cmt.2", &mstp_clks[MSTP400]), /* CMT2 */ + CLKDEV_ICK_ID("hdmi", "sh_mobile_lcdc_fb.1", + &div6_reparent_clks[DIV6_HDMI]), CLKDEV_ICK_ID("ick", "sh-mobile-hdmi", &div6_reparent_clks[DIV6_HDMI]), CLKDEV_ICK_ID("icka", "sh_fsi2", &div6_reparent_clks[DIV6_FSIA]), CLKDEV_ICK_ID("ickb", "sh_fsi2", &div6_reparent_clks[DIV6_FSIB]), diff --git a/arch/arm/mach-shmobile/clock-sh73a0.c b/arch/arm/mach-shmobile/clock-sh73a0.c index 6db2ccabc2bf..61a846bb30f2 100644 --- a/arch/arm/mach-shmobile/clock-sh73a0.c +++ b/arch/arm/mach-shmobile/clock-sh73a0.c @@ -365,7 +365,7 @@ void __init sh73a0_clock_init(void) __raw_writel(0x108, SD2CKCR); /* detect main clock parent */ - switch ((__raw_readl(CKSCR) >> 24) & 0x03) { + switch ((__raw_readl(CKSCR) >> 28) & 0x03) { case 0: main_clk.parent = &sh73a0_extal1_clk; break; diff --git a/arch/arm/mach-shmobile/include/mach/sh7372.h b/arch/arm/mach-shmobile/include/mach/sh7372.h index ce595cee86cd..24e63a85e669 100644 --- a/arch/arm/mach-shmobile/include/mach/sh7372.h +++ b/arch/arm/mach-shmobile/include/mach/sh7372.h @@ -459,6 +459,10 @@ enum { SHDMA_SLAVE_SDHI2_TX, SHDMA_SLAVE_MMCIF_RX, SHDMA_SLAVE_MMCIF_TX, + SHDMA_SLAVE_USB0_TX, + SHDMA_SLAVE_USB0_RX, + SHDMA_SLAVE_USB1_TX, + SHDMA_SLAVE_USB1_RX, }; extern struct clk sh7372_extal1_clk; diff --git a/arch/arm/mach-shmobile/intc-sh7372.c b/arch/arm/mach-shmobile/intc-sh7372.c index 3b28743c77eb..739315e30eb9 100644 --- a/arch/arm/mach-shmobile/intc-sh7372.c +++ b/arch/arm/mach-shmobile/intc-sh7372.c @@ -379,7 +379,7 @@ enum { /* BBIF2 */ VPU, TSIF1, - _3DG_SGX530, + /* 3DG */ _2DDMAC, IIC2_ALI2, IIC2_TACKI2, IIC2_WAITI2, IIC2_DTEI2, IPMMU_IPMMUR, IPMMU_IPMMUR2, @@ -436,7 +436,7 @@ static struct intc_vect intcs_vectors[] = { /* BBIF2 */ INTCS_VECT(VPU, 0x980), INTCS_VECT(TSIF1, 0x9a0), - INTCS_VECT(_3DG_SGX530, 0x9e0), + /* 3DG */ INTCS_VECT(_2DDMAC, 0xa00), INTCS_VECT(IIC2_ALI2, 0xa80), INTCS_VECT(IIC2_TACKI2, 0xaa0), INTCS_VECT(IIC2_WAITI2, 0xac0), INTCS_VECT(IIC2_DTEI2, 0xae0), @@ -521,7 +521,7 @@ static struct intc_mask_reg intcs_mask_registers[] = { RTDMAC_1_DEI3, RTDMAC_1_DEI2, RTDMAC_1_DEI1, RTDMAC_1_DEI0 } }, { 0xffd20198, 0xffd201d8, 8, /* IMR6SA / IMCR6SA */ { 0, 0, MSIOF, 0, - _3DG_SGX530, 0, 0, 0 } }, + 0, 0, 0, 0 } }, { 0xffd2019c, 0xffd201dc, 8, /* IMR7SA / IMCR7SA */ { 0, TMU_TUNI2, TMU_TUNI1, TMU_TUNI0, 0, 0, 0, 0 } }, @@ -561,7 +561,6 @@ static struct intc_prio_reg intcs_prio_registers[] = { TMU_TUNI2, TSIF1 } }, { 0xffd2001c, 0, 16, 4, /* IPRHS */ { 0, 0, VEU, BEU } }, { 0xffd20020, 0, 16, 4, /* IPRIS */ { 0, MSIOF, TSIF0, IIC0 } }, - { 0xffd20024, 0, 16, 4, /* IPRJS */ { 0, _3DG_SGX530, 0, 0 } }, { 0xffd20028, 0, 16, 4, /* IPRKS */ { 0, 0, LMB, 0 } }, { 0xffd2002c, 0, 16, 4, /* IPRLS */ { IPMMU, 0, 0, 0 } }, { 0xffd20030, 0, 16, 4, /* IPRMS */ { IIC2, 0, 0, 0 } }, diff --git a/arch/arm/mach-shmobile/setup-sh7372.c b/arch/arm/mach-shmobile/setup-sh7372.c index 79f0413d8725..2d9b1b1a2538 100644 --- a/arch/arm/mach-shmobile/setup-sh7372.c +++ b/arch/arm/mach-shmobile/setup-sh7372.c @@ -169,35 +169,35 @@ static struct platform_device scif6_device = { }; /* CMT */ -static struct sh_timer_config cmt10_platform_data = { - .name = "CMT10", - .channel_offset = 0x10, - .timer_bit = 0, +static struct sh_timer_config cmt2_platform_data = { + .name = "CMT2", + .channel_offset = 0x40, + .timer_bit = 5, .clockevent_rating = 125, .clocksource_rating = 125, }; -static struct resource cmt10_resources[] = { +static struct resource cmt2_resources[] = { [0] = { - .name = "CMT10", - .start = 0xe6138010, - .end = 0xe613801b, + .name = "CMT2", + .start = 0xe6130040, + .end = 0xe613004b, .flags = IORESOURCE_MEM, }, [1] = { - .start = evt2irq(0x0b00), /* CMT1_CMT10 */ + .start = evt2irq(0x0b80), /* CMT2 */ .flags = IORESOURCE_IRQ, }, }; -static struct platform_device cmt10_device = { +static struct platform_device cmt2_device = { .name = "sh_cmt", - .id = 10, + .id = 2, .dev = { - .platform_data = &cmt10_platform_data, + .platform_data = &cmt2_platform_data, }, - .resource = cmt10_resources, - .num_resources = ARRAY_SIZE(cmt10_resources), + .resource = cmt2_resources, + .num_resources = ARRAY_SIZE(cmt2_resources), }; /* TMU */ @@ -602,6 +602,150 @@ static struct platform_device dma2_device = { }, }; +/* + * USB-DMAC + */ + +unsigned int usbts_shift[] = {3, 4, 5}; + +enum { + XMIT_SZ_8BYTE = 0, + XMIT_SZ_16BYTE = 1, + XMIT_SZ_32BYTE = 2, +}; + +#define USBTS_INDEX2VAL(i) (((i) & 3) << 6) + +static const struct sh_dmae_channel sh7372_usb_dmae_channels[] = { + { + .offset = 0, + }, { + .offset = 0x20, + }, +}; + +/* USB DMAC0 */ +static const struct sh_dmae_slave_config sh7372_usb_dmae0_slaves[] = { + { + .slave_id = SHDMA_SLAVE_USB0_TX, + .chcr = USBTS_INDEX2VAL(XMIT_SZ_8BYTE), + }, { + .slave_id = SHDMA_SLAVE_USB0_RX, + .chcr = USBTS_INDEX2VAL(XMIT_SZ_8BYTE), + }, +}; + +static struct sh_dmae_pdata usb_dma0_platform_data = { + .slave = sh7372_usb_dmae0_slaves, + .slave_num = ARRAY_SIZE(sh7372_usb_dmae0_slaves), + .channel = sh7372_usb_dmae_channels, + .channel_num = ARRAY_SIZE(sh7372_usb_dmae_channels), + .ts_low_shift = 6, + .ts_low_mask = 0xc0, + .ts_high_shift = 0, + .ts_high_mask = 0, + .ts_shift = usbts_shift, + .ts_shift_num = ARRAY_SIZE(usbts_shift), + .dmaor_init = DMAOR_DME, + .chcr_offset = 0x14, + .chcr_ie_bit = 1 << 5, + .dmaor_is_32bit = 1, + .needs_tend_set = 1, + .no_dmars = 1, +}; + +static struct resource sh7372_usb_dmae0_resources[] = { + { + /* Channel registers and DMAOR */ + .start = 0xe68a0020, + .end = 0xe68a0064 - 1, + .flags = IORESOURCE_MEM, + }, + { + /* VCR/SWR/DMICR */ + .start = 0xe68a0000, + .end = 0xe68a0014 - 1, + .flags = IORESOURCE_MEM, + }, + { + /* IRQ for channels */ + .start = evt2irq(0x0a00), + .end = evt2irq(0x0a00), + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device usb_dma0_device = { + .name = "sh-dma-engine", + .id = 3, + .resource = sh7372_usb_dmae0_resources, + .num_resources = ARRAY_SIZE(sh7372_usb_dmae0_resources), + .dev = { + .platform_data = &usb_dma0_platform_data, + }, +}; + +/* USB DMAC1 */ +static const struct sh_dmae_slave_config sh7372_usb_dmae1_slaves[] = { + { + .slave_id = SHDMA_SLAVE_USB1_TX, + .chcr = USBTS_INDEX2VAL(XMIT_SZ_8BYTE), + }, { + .slave_id = SHDMA_SLAVE_USB1_RX, + .chcr = USBTS_INDEX2VAL(XMIT_SZ_8BYTE), + }, +}; + +static struct sh_dmae_pdata usb_dma1_platform_data = { + .slave = sh7372_usb_dmae1_slaves, + .slave_num = ARRAY_SIZE(sh7372_usb_dmae1_slaves), + .channel = sh7372_usb_dmae_channels, + .channel_num = ARRAY_SIZE(sh7372_usb_dmae_channels), + .ts_low_shift = 6, + .ts_low_mask = 0xc0, + .ts_high_shift = 0, + .ts_high_mask = 0, + .ts_shift = usbts_shift, + .ts_shift_num = ARRAY_SIZE(usbts_shift), + .dmaor_init = DMAOR_DME, + .chcr_offset = 0x14, + .chcr_ie_bit = 1 << 5, + .dmaor_is_32bit = 1, + .needs_tend_set = 1, + .no_dmars = 1, +}; + +static struct resource sh7372_usb_dmae1_resources[] = { + { + /* Channel registers and DMAOR */ + .start = 0xe68c0020, + .end = 0xe68c0064 - 1, + .flags = IORESOURCE_MEM, + }, + { + /* VCR/SWR/DMICR */ + .start = 0xe68c0000, + .end = 0xe68c0014 - 1, + .flags = IORESOURCE_MEM, + }, + { + /* IRQ for channels */ + .start = evt2irq(0x1d00), + .end = evt2irq(0x1d00), + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device usb_dma1_device = { + .name = "sh-dma-engine", + .id = 4, + .resource = sh7372_usb_dmae1_resources, + .num_resources = ARRAY_SIZE(sh7372_usb_dmae1_resources), + .dev = { + .platform_data = &usb_dma1_platform_data, + }, +}; + /* VPU */ static struct uio_info vpu_platform_data = { .name = "VPU5HG", @@ -818,7 +962,7 @@ static struct platform_device *sh7372_early_devices[] __initdata = { &scif4_device, &scif5_device, &scif6_device, - &cmt10_device, + &cmt2_device, &tmu00_device, &tmu01_device, }; @@ -829,6 +973,8 @@ static struct platform_device *sh7372_late_devices[] __initdata = { &dma0_device, &dma1_device, &dma2_device, + &usb_dma0_device, + &usb_dma1_device, &vpu_device, &veu0_device, &veu1_device, diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c index 9e6b93b1a043..d0d267a8d3f9 100644 --- a/arch/arm/mach-vexpress/v2m.c +++ b/arch/arm/mach-vexpress/v2m.c @@ -318,6 +318,10 @@ static struct clk v2m_sp804_clk = { .rate = 1000000, }; +static struct clk v2m_ref_clk = { + .rate = 32768, +}; + static struct clk dummy_apb_pclk; static struct clk_lookup v2m_lookups[] = { @@ -348,6 +352,9 @@ static struct clk_lookup v2m_lookups[] = { }, { /* CLCD */ .dev_id = "mb:clcd", .clk = &osc1_clk, + }, { /* SP805 WDT */ + .dev_id = "mb:wdt", + .clk = &v2m_ref_clk, }, { /* SP804 timers */ .dev_id = "sp804", .con_id = "v2m-timer0", diff --git a/arch/arm/mm/abort-macro.S b/arch/arm/mm/abort-macro.S index 52162d59407a..2cbf68ef0e83 100644 --- a/arch/arm/mm/abort-macro.S +++ b/arch/arm/mm/abort-macro.S @@ -17,7 +17,7 @@ cmp \tmp, # 0x5600 @ Is it ldrsb? orreq \tmp, \tmp, #1 << 11 @ Set L-bit if yes tst \tmp, #1 << 11 @ L = 0 -> write - orreq \psr, \psr, #1 << 11 @ yes. + orreq \fsr, \fsr, #1 << 11 @ yes. b do_DataAbort not_thumb: .endm diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 44c086710d2b..9ecfdb511951 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -277,6 +277,25 @@ static void l2x0_disable(void) spin_unlock_irqrestore(&l2x0_lock, flags); } +static void __init l2x0_unlock(__u32 cache_id) +{ + int lockregs; + int i; + + if (cache_id == L2X0_CACHE_ID_PART_L310) + lockregs = 8; + else + /* L210 and unknown types */ + lockregs = 1; + + for (i = 0; i < lockregs; i++) { + writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_D_BASE + + i * L2X0_LOCKDOWN_STRIDE); + writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_I_BASE + + i * L2X0_LOCKDOWN_STRIDE); + } +} + void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) { __u32 aux; @@ -328,6 +347,8 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) * accessing the below registers will fault. */ if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) { + /* Make sure that I&D is not locked down when starting */ + l2x0_unlock(cache_id); /* l2x0 controller is disabled */ writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL); diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 91bca355cd31..cc7e2d8be9aa 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -298,7 +298,7 @@ static void __init arm_bootmem_free(unsigned long min, unsigned long max_low, #ifdef CONFIG_HAVE_ARCH_PFN_VALID int pfn_valid(unsigned long pfn) { - return memblock_is_memory(pfn << PAGE_SHIFT); + return memblock_is_memory(__pfn_to_phys(pfn)); } EXPORT_SYMBOL(pfn_valid); #endif diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S index 92bd102e3982..2e6849b41f66 100644 --- a/arch/arm/mm/proc-arm920.S +++ b/arch/arm/mm/proc-arm920.S @@ -379,7 +379,7 @@ ENTRY(cpu_arm920_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm920_suspend_size -.equ cpu_arm920_suspend_size, 4 * 3 +.equ cpu_arm920_suspend_size, 4 * 4 #ifdef CONFIG_PM_SLEEP ENTRY(cpu_arm920_do_suspend) stmfd sp!, {r4 - r7, lr} diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S index 2bbcf053dffd..cd8f79c3a282 100644 --- a/arch/arm/mm/proc-arm926.S +++ b/arch/arm/mm/proc-arm926.S @@ -394,7 +394,7 @@ ENTRY(cpu_arm926_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm926_suspend_size -.equ cpu_arm926_suspend_size, 4 * 3 +.equ cpu_arm926_suspend_size, 4 * 4 #ifdef CONFIG_PM_SLEEP ENTRY(cpu_arm926_do_suspend) stmfd sp!, {r4 - r7, lr} diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S index 07219c2ae114..69e7f2ef7384 100644 --- a/arch/arm/mm/proc-sa1100.S +++ b/arch/arm/mm/proc-sa1100.S @@ -182,11 +182,11 @@ ENDPROC(cpu_sa1100_do_suspend) ENTRY(cpu_sa1100_do_resume) ldmia r0, {r4 - r7} @ load cp regs - mov r1, #0 - mcr p15, 0, r1, c8, c7, 0 @ flush I+D TLBs - mcr p15, 0, r1, c7, c7, 0 @ flush I&D cache - mcr p15, 0, r1, c9, c0, 0 @ invalidate RB - mcr p15, 0, r1, c9, c0, 5 @ allow user space to use RB + mov ip, #0 + mcr p15, 0, ip, c8, c7, 0 @ flush I+D TLBs + mcr p15, 0, ip, c7, c7, 0 @ flush I&D cache + mcr p15, 0, ip, c9, c0, 0 @ invalidate RB + mcr p15, 0, ip, c9, c0, 5 @ allow user space to use RB mcr p15, 0, r4, c3, c0, 0 @ domain ID mcr p15, 0, r5, c2, c0, 0 @ translation table base addr diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index 219138d2f158..a923aa0fd00d 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -223,6 +223,22 @@ __v6_setup: mrc p15, 0, r0, c1, c0, 0 @ read control register bic r0, r0, r5 @ clear bits them orr r0, r0, r6 @ set them +#ifdef CONFIG_ARM_ERRATA_364296 + /* + * Workaround for the 364296 ARM1136 r0p2 erratum (possible cache data + * corruption with hit-under-miss enabled). The conditional code below + * (setting the undocumented bit 31 in the auxiliary control register + * and the FI bit in the control register) disables hit-under-miss + * without putting the processor into full low interrupt latency mode. + */ + ldr r6, =0x4107b362 @ id for ARM1136 r0p2 + mrc p15, 0, r5, c0, c0, 0 @ get processor id + teq r5, r6 @ check for the faulty core + mrceq p15, 0, r5, c1, c0, 1 @ load aux control reg + orreq r5, r5, #(1 << 31) @ set the undocumented bit 31 + mcreq p15, 0, r5, c1, c0, 1 @ write aux control reg + orreq r0, r0, #(1 << 21) @ low interrupt latency configuration +#endif mov pc, lr @ return to head.S:__ret /* diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index a30e78542ccf..9049c0764db2 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -66,6 +66,7 @@ ENDPROC(cpu_v7_proc_fin) ENTRY(cpu_v7_reset) mrc p15, 0, r1, c1, c0, 0 @ ctrl register bic r1, r1, #0x1 @ ...............m + THUMB( bic r1, r1, #1 << 30 ) @ SCTLR.TE (Thumb exceptions) mcr p15, 0, r1, c1, c0, 0 @ disable MMU isb mov pc, r0 @@ -247,13 +248,16 @@ ENTRY(cpu_v7_do_resume) mcr p15, 0, r7, c2, c0, 0 @ TTB 0 mcr p15, 0, r8, c2, c0, 1 @ TTB 1 mcr p15, 0, ip, c2, c0, 2 @ TTB control register - mcr p15, 0, r10, c1, c0, 1 @ Auxiliary control register + mrc p15, 0, r4, c1, c0, 1 @ Read Auxiliary control register + teq r4, r10 @ Is it already set? + mcrne p15, 0, r10, c1, c0, 1 @ No, so write it mcr p15, 0, r11, c1, c0, 2 @ Co-processor access control ldr r4, =PRRR @ PRRR ldr r5, =NMRR @ NMRR mcr p15, 0, r4, c10, c2, 0 @ write PRRR mcr p15, 0, r5, c10, c2, 1 @ write NMRR isb + dsb mov r0, r9 @ control register mov r2, r7, lsr #14 @ get TTB0 base mov r2, r2, lsl #14 diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S index 28c72a2006a1..755e1bf22681 100644 --- a/arch/arm/mm/proc-xsc3.S +++ b/arch/arm/mm/proc-xsc3.S @@ -406,7 +406,7 @@ ENTRY(cpu_xsc3_set_pte_ext) .align .globl cpu_xsc3_suspend_size -.equ cpu_xsc3_suspend_size, 4 * 8 +.equ cpu_xsc3_suspend_size, 4 * 7 #ifdef CONFIG_PM_SLEEP ENTRY(cpu_xsc3_do_suspend) stmfd sp!, {r4 - r10, lr} @@ -418,12 +418,12 @@ ENTRY(cpu_xsc3_do_suspend) mrc p15, 0, r9, c1, c0, 1 @ auxiliary control reg mrc p15, 0, r10, c1, c0, 0 @ control reg bic r4, r4, #2 @ clear frequency change bit - stmia r0, {r1, r4 - r10} @ store v:p offset + cp regs + stmia r0, {r4 - r10} @ store cp regs ldmia sp!, {r4 - r10, pc} ENDPROC(cpu_xsc3_do_suspend) ENTRY(cpu_xsc3_do_resume) - ldmia r0, {r1, r4 - r10} @ load v:p offset + cp regs + ldmia r0, {r4 - r10} @ load cp regs mov ip, #0 mcr p15, 0, ip, c7, c7, 0 @ invalidate I & D caches, BTB mcr p15, 0, ip, c7, c10, 4 @ drain write (&fill) buffer diff --git a/arch/arm/plat-omap/omap_device.c b/arch/arm/plat-omap/omap_device.c index b6b409744954..02609eee0562 100644 --- a/arch/arm/plat-omap/omap_device.c +++ b/arch/arm/plat-omap/omap_device.c @@ -615,6 +615,9 @@ static int _od_resume_noirq(struct device *dev) return pm_generic_resume_noirq(dev); } +#else +#define _od_suspend_noirq NULL +#define _od_resume_noirq NULL #endif static struct dev_pm_domain omap_device_pm_domain = { @@ -622,7 +625,8 @@ static struct dev_pm_domain omap_device_pm_domain = { SET_RUNTIME_PM_OPS(_od_runtime_suspend, _od_runtime_resume, _od_runtime_idle) USE_PLATFORM_PM_SLEEP_OPS - SET_SYSTEM_SLEEP_PM_OPS(_od_suspend_noirq, _od_resume_noirq) + .suspend_noirq = _od_suspend_noirq, + .resume_noirq = _od_resume_noirq, } }; diff --git a/arch/arm/plat-s5p/clock.c b/arch/arm/plat-s5p/clock.c index 02af235298e2..5f84a3f13ef9 100644 --- a/arch/arm/plat-s5p/clock.c +++ b/arch/arm/plat-s5p/clock.c @@ -192,7 +192,7 @@ unsigned long s5p_spdif_get_rate(struct clk *clk) if (IS_ERR(pclk)) return -EINVAL; - rate = pclk->ops->get_rate(clk); + rate = pclk->ops->get_rate(pclk); clk_put(pclk); return rate; diff --git a/arch/arm/plat-s5p/irq-gpioint.c b/arch/arm/plat-s5p/irq-gpioint.c index 327ab9f662e8..f71078ef6bb5 100644 --- a/arch/arm/plat-s5p/irq-gpioint.c +++ b/arch/arm/plat-s5p/irq-gpioint.c @@ -23,6 +23,8 @@ #include <plat/gpio-core.h> #include <plat/gpio-cfg.h> +#include <asm/mach/irq.h> + #define GPIO_BASE(chip) (((unsigned long)(chip)->base) & 0xFFFFF000u) #define CON_OFFSET 0x700 @@ -81,6 +83,9 @@ static void s5p_gpioint_handler(unsigned int irq, struct irq_desc *desc) int group, pend_offset, mask_offset; unsigned int pend, mask; + struct irq_chip *chip = irq_get_chip(irq); + chained_irq_enter(chip, desc); + for (group = 0; group < bank->nr_groups; group++) { struct s3c_gpio_chip *chip = bank->chips[group]; if (!chip) @@ -102,6 +107,7 @@ static void s5p_gpioint_handler(unsigned int irq, struct irq_desc *desc) pend &= ~BIT(offset); } } + chained_irq_exit(chip, desc); } static __init int s5p_gpioint_add(struct s3c_gpio_chip *chip) diff --git a/arch/arm/plat-samsung/clock.c b/arch/arm/plat-samsung/clock.c index 302c42670bd1..3b4451979d1b 100644 --- a/arch/arm/plat-samsung/clock.c +++ b/arch/arm/plat-samsung/clock.c @@ -64,6 +64,17 @@ static LIST_HEAD(clocks); */ DEFINE_SPINLOCK(clocks_lock); +/* Global watchdog clock used by arch_wtd_reset() callback */ +struct clk *s3c2410_wdtclk; +static int __init s3c_wdt_reset_init(void) +{ + s3c2410_wdtclk = clk_get(NULL, "watchdog"); + if (IS_ERR(s3c2410_wdtclk)) + printk(KERN_WARNING "%s: warning: cannot get watchdog clock\n", __func__); + return 0; +} +arch_initcall(s3c_wdt_reset_init); + /* enable and disable calls for use with the clk struct */ static int clk_null_enable(struct clk *clk, int enable) diff --git a/arch/arm/plat-samsung/include/plat/backlight.h b/arch/arm/plat-samsung/include/plat/backlight.h index 51d8da846a62..ad530c78fe8c 100644 --- a/arch/arm/plat-samsung/include/plat/backlight.h +++ b/arch/arm/plat-samsung/include/plat/backlight.h @@ -20,7 +20,7 @@ struct samsung_bl_gpio_info { int func; }; -extern void samsung_bl_set(struct samsung_bl_gpio_info *gpio_info, +extern void __init samsung_bl_set(struct samsung_bl_gpio_info *gpio_info, struct platform_pwm_backlight_data *bl_data); #endif /* __ASM_PLAT_BACKLIGHT_H */ diff --git a/arch/arm/plat-samsung/include/plat/clock.h b/arch/arm/plat-samsung/include/plat/clock.h index 87d5b38a86fb..73c66d4d10fa 100644 --- a/arch/arm/plat-samsung/include/plat/clock.h +++ b/arch/arm/plat-samsung/include/plat/clock.h @@ -9,6 +9,9 @@ * published by the Free Software Foundation. */ +#ifndef __ASM_PLAT_CLOCK_H +#define __ASM_PLAT_CLOCK_H __FILE__ + #include <linux/spinlock.h> #include <linux/clkdev.h> @@ -121,3 +124,8 @@ extern int s3c64xx_sclk_ctrl(struct clk *clk, int enable); extern void s3c_pwmclk_init(void); +/* Global watchdog clock used by arch_wtd_reset() callback */ + +extern struct clk *s3c2410_wdtclk; + +#endif /* __ASM_PLAT_CLOCK_H */ diff --git a/arch/arm/plat-samsung/include/plat/watchdog-reset.h b/arch/arm/plat-samsung/include/plat/watchdog-reset.h index 54b762acb5a0..40dbb2b0ae22 100644 --- a/arch/arm/plat-samsung/include/plat/watchdog-reset.h +++ b/arch/arm/plat-samsung/include/plat/watchdog-reset.h @@ -10,6 +10,7 @@ * published by the Free Software Foundation. */ +#include <plat/clock.h> #include <plat/regs-watchdog.h> #include <mach/map.h> @@ -19,17 +20,12 @@ static inline void arch_wdt_reset(void) { - struct clk *wdtclk; - printk("arch_reset: attempting watchdog reset\n"); __raw_writel(0, S3C2410_WTCON); /* disable watchdog, to be safe */ - wdtclk = clk_get(NULL, "watchdog"); - if (!IS_ERR(wdtclk)) { - clk_enable(wdtclk); - } else - printk(KERN_WARNING "%s: warning: cannot get watchdog clock\n", __func__); + if (s3c2410_wdtclk) + clk_enable(s3c2410_wdtclk); /* put initial values into count and data */ __raw_writel(0x80, S3C2410_WTCNT); diff --git a/arch/arm/plat-samsung/irq-vic-timer.c b/arch/arm/plat-samsung/irq-vic-timer.c index f714d060370d..51583cd30164 100644 --- a/arch/arm/plat-samsung/irq-vic-timer.c +++ b/arch/arm/plat-samsung/irq-vic-timer.c @@ -22,9 +22,14 @@ #include <plat/irq-vic-timer.h> #include <plat/regs-timer.h> +#include <asm/mach/irq.h> + static void s3c_irq_demux_vic_timer(unsigned int irq, struct irq_desc *desc) { + struct irq_chip *chip = irq_get_chip(irq); + chained_irq_enter(chip, desc); generic_handle_irq((int)desc->irq_data.handler_data); + chained_irq_exit(chip, desc); } /* We assume the IRQ_TIMER0..IRQ_TIMER4 range is continuous. */ diff --git a/arch/arm/tools/mach-types b/arch/arm/tools/mach-types index fff68d0d521b..62cc8f981171 100644 --- a/arch/arm/tools/mach-types +++ b/arch/arm/tools/mach-types @@ -351,7 +351,7 @@ centro MACH_CENTRO CENTRO 1944 nokia_rx51 MACH_NOKIA_RX51 NOKIA_RX51 1955 omap_zoom2 MACH_OMAP_ZOOM2 OMAP_ZOOM2 1967 cpuat9260 MACH_CPUAT9260 CPUAT9260 1973 -eukrea_cpuimx27 MACH_CPUIMX27 CPUIMX27 1975 +eukrea_cpuimx27 MACH_EUKREA_CPUIMX27 EUKREA_CPUIMX27 1975 acs5k MACH_ACS5K ACS5K 1982 snapper_9260 MACH_SNAPPER_9260 SNAPPER_9260 1987 dsm320 MACH_DSM320 DSM320 1988 @@ -476,8 +476,8 @@ cns3420vb MACH_CNS3420VB CNS3420VB 2776 omap4_panda MACH_OMAP4_PANDA OMAP4_PANDA 2791 ti8168evm MACH_TI8168EVM TI8168EVM 2800 teton_bga MACH_TETON_BGA TETON_BGA 2816 -eukrea_cpuimx25sd MACH_EUKREA_CPUIMX25 EUKREA_CPUIMX25 2820 -eukrea_cpuimx35sd MACH_EUKREA_CPUIMX35 EUKREA_CPUIMX35 2821 +eukrea_cpuimx25sd MACH_EUKREA_CPUIMX25SD EUKREA_CPUIMX25SD 2820 +eukrea_cpuimx35sd MACH_EUKREA_CPUIMX35SD EUKREA_CPUIMX35SD 2821 eukrea_cpuimx51sd MACH_EUKREA_CPUIMX51SD EUKREA_CPUIMX51SD 2822 eukrea_cpuimx51 MACH_EUKREA_CPUIMX51 EUKREA_CPUIMX51 2823 smdkc210 MACH_SMDKC210 SMDKC210 2838 diff --git a/arch/avr32/kernel/syscall_table.S b/arch/avr32/kernel/syscall_table.S index c7fd394d28a4..6eba53530d1c 100644 --- a/arch/avr32/kernel/syscall_table.S +++ b/arch/avr32/kernel/syscall_table.S @@ -158,7 +158,7 @@ sys_call_table: .long sys_sched_rr_get_interval .long sys_nanosleep .long sys_poll - .long sys_nfsservctl /* 145 */ + .long sys_ni_syscall /* 145 was nfsservctl */ .long sys_setresgid .long sys_getresgid .long sys_prctl diff --git a/arch/blackfin/mach-common/entry.S b/arch/blackfin/mach-common/entry.S index 225d311c9701..e4137297b790 100644 --- a/arch/blackfin/mach-common/entry.S +++ b/arch/blackfin/mach-common/entry.S @@ -1543,7 +1543,7 @@ ENTRY(_sys_call_table) .long _sys_ni_syscall /* for vm86 */ .long _sys_ni_syscall /* old "query_module" */ .long _sys_ni_syscall /* sys_poll */ - .long _sys_nfsservctl + .long _sys_ni_syscall /* old nfsservctl */ .long _sys_setresgid /* setresgid16 */ /* 170 */ .long _sys_getresgid /* getresgid16 */ .long _sys_prctl diff --git a/arch/cris/arch-v10/kernel/entry.S b/arch/cris/arch-v10/kernel/entry.S index 1161883eb582..592fbe9dfb62 100644 --- a/arch/cris/arch-v10/kernel/entry.S +++ b/arch/cris/arch-v10/kernel/entry.S @@ -771,7 +771,7 @@ sys_call_table: .long sys_ni_syscall /* sys_vm86 */ .long sys_ni_syscall /* Old sys_query_module */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* old nfsservctl */ .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl diff --git a/arch/cris/arch-v32/kernel/entry.S b/arch/cris/arch-v32/kernel/entry.S index 84fed7e91ada..c3ea4694fbaf 100644 --- a/arch/cris/arch-v32/kernel/entry.S +++ b/arch/cris/arch-v32/kernel/entry.S @@ -714,7 +714,7 @@ sys_call_table: .long sys_ni_syscall /* sys_vm86 */ .long sys_ni_syscall /* Old sys_query_module */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* Old nfsservctl */ .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl diff --git a/arch/cris/include/asm/serial.h b/arch/cris/include/asm/serial.h new file mode 100644 index 000000000000..af7535a955fb --- /dev/null +++ b/arch/cris/include/asm/serial.h @@ -0,0 +1,9 @@ +#ifndef _ASM_SERIAL_H +#define _ASM_SERIAL_H + +/* + * This assumes you have a 1.8432 MHz clock for your UART. + */ +#define BASE_BAUD (1843200 / 16) + +#endif /* _ASM_SERIAL_H */ diff --git a/arch/frv/kernel/entry.S b/arch/frv/kernel/entry.S index 017d6d7b784f..5ba23f715ea5 100644 --- a/arch/frv/kernel/entry.S +++ b/arch/frv/kernel/entry.S @@ -1358,7 +1358,7 @@ sys_call_table: .long sys_ni_syscall /* for vm86 */ .long sys_ni_syscall /* Old sys_query_module */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* Old nfsservctl */ .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl diff --git a/arch/h8300/kernel/syscalls.S b/arch/h8300/kernel/syscalls.S index f4b2e67bcc34..4be2ea2fbe26 100644 --- a/arch/h8300/kernel/syscalls.S +++ b/arch/h8300/kernel/syscalls.S @@ -183,7 +183,7 @@ SYMBOL_NAME_LABEL(sys_call_table) .long SYMBOL_NAME(sys_ni_syscall) /* for vm86 */ .long SYMBOL_NAME(sys_ni_syscall) /* sys_query_module */ .long SYMBOL_NAME(sys_poll) - .long SYMBOL_NAME(sys_nfsservctl) + .long SYMBOL_NAME(sys_ni_syscall) /* old nfsservctl */ .long SYMBOL_NAME(sys_setresgid16) /* 170 */ .long SYMBOL_NAME(sys_getresgid16) .long SYMBOL_NAME(sys_prctl) diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 124854714958..3ff7785b3beb 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -162,7 +162,6 @@ config IA64_GENERIC select ACPI_NUMA select SWIOTLB select PCI_MSI - select DMAR help This selects the system type of your hardware. A "generic" kernel will run on any supported IA-64 system. However, if you configure diff --git a/arch/ia64/configs/generic_defconfig b/arch/ia64/configs/generic_defconfig index 1d7bca0a396d..0e5cd1405e0e 100644 --- a/arch/ia64/configs/generic_defconfig +++ b/arch/ia64/configs/generic_defconfig @@ -234,3 +234,4 @@ CONFIG_CRYPTO_MD5=y # CONFIG_CRYPTO_ANSI_CPRNG is not set CONFIG_CRC_T10DIF=y CONFIG_MISC_DEVICES=y +CONFIG_DMAR=y diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index 97dd2abdeb1a..198c753d1006 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -1614,7 +1614,7 @@ sys_call_table: data8 sys_sched_get_priority_min data8 sys_sched_rr_get_interval data8 sys_nanosleep - data8 sys_nfsservctl + data8 sys_ni_syscall // old nfsservctl data8 sys_prctl // 1170 data8 sys_getpagesize data8 sys_mmap2 diff --git a/arch/m32r/kernel/syscall_table.S b/arch/m32r/kernel/syscall_table.S index 528f2e6ad064..f365c19795ef 100644 --- a/arch/m32r/kernel/syscall_table.S +++ b/arch/m32r/kernel/syscall_table.S @@ -168,7 +168,7 @@ ENTRY(sys_call_table) .long sys_tas /* vm86 syscall holder */ .long sys_ni_syscall /* query_module syscall holder */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* was nfsservctl */ .long sys_setresgid /* 170 */ .long sys_getresgid .long sys_prctl diff --git a/arch/m68k/include/asm/page_mm.h b/arch/m68k/include/asm/page_mm.h index 31d5570d6567..89f201434b5a 100644 --- a/arch/m68k/include/asm/page_mm.h +++ b/arch/m68k/include/asm/page_mm.h @@ -162,7 +162,7 @@ static inline __attribute_const__ int __virt_to_node_shift(void) pgdat->node_mem_map + (__pfn - pgdat->node_start_pfn); \ }) #define page_to_pfn(_page) ({ \ - struct page *__p = (_page); \ + const struct page *__p = (_page); \ struct pglist_data *pgdat; \ pgdat = &pg_data_map[page_to_nid(__p)]; \ ((__p) - pgdat->node_mem_map) + pgdat->node_start_pfn; \ diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S index 00d1452f9571..c468f2edaa85 100644 --- a/arch/m68k/kernel/syscalltable.S +++ b/arch/m68k/kernel/syscalltable.S @@ -189,7 +189,7 @@ ENTRY(sys_call_table) .long sys_getpagesize .long sys_ni_syscall /* old "query_module" */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* old nfsservctl */ .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl diff --git a/arch/microblaze/kernel/syscall_table.S b/arch/microblaze/kernel/syscall_table.S index d915a122c865..8789daa2a346 100644 --- a/arch/microblaze/kernel/syscall_table.S +++ b/arch/microblaze/kernel/syscall_table.S @@ -173,7 +173,7 @@ ENTRY(sys_call_table) .long sys_ni_syscall /* sys_vm86 */ .long sys_ni_syscall /* Old sys_query_module */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* old nfsservctl */ .long sys_setresgid /* 170 */ .long sys_getresgid .long sys_prctl diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index e521420a45a5..865bc7a6f5a1 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -424,7 +424,7 @@ einval: li v0, -ENOSYS sys sys_getresuid 3 sys sys_ni_syscall 0 /* was sys_query_module */ sys sys_poll 3 - sys sys_nfsservctl 3 + sys sys_ni_syscall 0 /* was nfsservctl */ sys sys_setresgid 3 /* 4190 */ sys sys_getresgid 3 sys sys_prctl 5 diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index 85874d6a8a70..fb7334bea731 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -299,7 +299,7 @@ sys_call_table: PTR sys_ni_syscall /* 5170, was get_kernel_syms */ PTR sys_ni_syscall /* was query_module */ PTR sys_quotactl - PTR sys_nfsservctl + PTR sys_ni_syscall /* was nfsservctl */ PTR sys_ni_syscall /* res. for getpmsg */ PTR sys_ni_syscall /* 5175 for putpmsg */ PTR sys_ni_syscall /* res. for afs_syscall */ diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index b85842fc87ae..f9296e894e46 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -294,7 +294,7 @@ EXPORT(sysn32_call_table) PTR sys_ni_syscall /* 6170, was get_kernel_syms */ PTR sys_ni_syscall /* was query_module */ PTR sys_quotactl - PTR compat_sys_nfsservctl + PTR sys_ni_syscall /* was nfsservctl */ PTR sys_ni_syscall /* res. for getpmsg */ PTR sys_ni_syscall /* 6175 for putpmsg */ PTR sys_ni_syscall /* res. for afs_syscall */ diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 46c4763edf21..4d7c9827706f 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -392,7 +392,7 @@ sys_call_table: PTR sys_getresuid PTR sys_ni_syscall /* was query_module */ PTR sys_poll - PTR compat_sys_nfsservctl + PTR sys_ni_syscall /* was nfsservctl */ PTR sys_setresgid /* 4190 */ PTR sys_getresgid PTR sys_prctl diff --git a/arch/mn10300/kernel/entry.S b/arch/mn10300/kernel/entry.S index ae435e1d5669..3e3620d9fc45 100644 --- a/arch/mn10300/kernel/entry.S +++ b/arch/mn10300/kernel/entry.S @@ -589,7 +589,7 @@ ENTRY(sys_call_table) .long sys_ni_syscall /* vm86 */ .long sys_ni_syscall /* Old sys_query_module */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* was nfsservctl */ .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl diff --git a/arch/openrisc/include/asm/dma-mapping.h b/arch/openrisc/include/asm/dma-mapping.h index 052f877b52a5..60b472233900 100644 --- a/arch/openrisc/include/asm/dma-mapping.h +++ b/arch/openrisc/include/asm/dma-mapping.h @@ -31,7 +31,6 @@ #define DMA_ERROR_CODE (~(dma_addr_t)0x0) -int dma_mapping_error(struct device *dev, dma_addr_t dma_addr); #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h) @@ -47,6 +46,12 @@ dma_addr_t or1k_map_page(struct device *dev, struct page *page, void or1k_unmap_page(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs); +int or1k_map_sg(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, + struct dma_attrs *attrs); +void or1k_unmap_sg(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, + struct dma_attrs *attrs); void or1k_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir); @@ -98,6 +103,51 @@ static inline void dma_unmap_single(struct device *dev, dma_addr_t addr, debug_dma_unmap_page(dev, addr, size, dir, true); } +static inline int dma_map_sg(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir) +{ + int i, ents; + struct scatterlist *s; + + for_each_sg(sg, s, nents, i) + kmemcheck_mark_initialized(sg_virt(s), s->length); + BUG_ON(!valid_dma_direction(dir)); + ents = or1k_map_sg(dev, sg, nents, dir, NULL); + debug_dma_map_sg(dev, sg, nents, ents, dir); + + return ents; +} + +static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir) +{ + BUG_ON(!valid_dma_direction(dir)); + debug_dma_unmap_sg(dev, sg, nents, dir); + or1k_unmap_sg(dev, sg, nents, dir, NULL); +} + +static inline dma_addr_t dma_map_page(struct device *dev, struct page *page, + size_t offset, size_t size, + enum dma_data_direction dir) +{ + dma_addr_t addr; + + kmemcheck_mark_initialized(page_address(page) + offset, size); + BUG_ON(!valid_dma_direction(dir)); + addr = or1k_map_page(dev, page, offset, size, dir, NULL); + debug_dma_map_page(dev, page, offset, size, dir, addr, false); + + return addr; +} + +static inline void dma_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ + BUG_ON(!valid_dma_direction(dir)); + or1k_unmap_page(dev, addr, size, dir, NULL); + debug_dma_unmap_page(dev, addr, size, dir, true); +} + static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) @@ -119,7 +169,12 @@ static inline void dma_sync_single_for_device(struct device *dev, static inline int dma_supported(struct device *dev, u64 dma_mask) { /* Support 32 bit DMA mask exclusively */ - return dma_mask == 0xffffffffULL; + return dma_mask == DMA_BIT_MASK(32); +} + +static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + return 0; } static inline int dma_set_mask(struct device *dev, u64 dma_mask) diff --git a/arch/openrisc/include/asm/sigcontext.h b/arch/openrisc/include/asm/sigcontext.h index 54a5c50132e3..b79c2b19afbe 100644 --- a/arch/openrisc/include/asm/sigcontext.h +++ b/arch/openrisc/include/asm/sigcontext.h @@ -23,16 +23,11 @@ /* This struct is saved by setup_frame in signal.c, to keep the current context while a signal handler is executed. It's restored by sys_sigreturn. - - To keep things simple, we use pt_regs here even though normally you just - specify the list of regs to save. Then we can use copy_from_user on the - entire regs instead of a bunch of get_user's as well... */ struct sigcontext { - struct pt_regs regs; /* needs to be first */ + struct user_regs_struct regs; /* needs to be first */ unsigned long oldmask; - unsigned long usp; /* usp before stacking this gunk on it */ }; #endif /* __ASM_OPENRISC_SIGCONTEXT_H */ diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c index 968d3ee477e3..f1c8ee2895d0 100644 --- a/arch/openrisc/kernel/dma.c +++ b/arch/openrisc/kernel/dma.c @@ -154,6 +154,33 @@ void or1k_unmap_page(struct device *dev, dma_addr_t dma_handle, /* Nothing special to do here... */ } +int or1k_map_sg(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + struct scatterlist *s; + int i; + + for_each_sg(sg, s, nents, i) { + s->dma_address = or1k_map_page(dev, sg_page(s), s->offset, + s->length, dir, NULL); + } + + return nents; +} + +void or1k_unmap_sg(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + struct scatterlist *s; + int i; + + for_each_sg(sg, s, nents, i) { + or1k_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, NULL); + } +} + void or1k_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir) @@ -187,5 +214,4 @@ static int __init dma_init(void) return 0; } - fs_initcall(dma_init); diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c index 5f759c76834e..95207ab0c99e 100644 --- a/arch/openrisc/kernel/signal.c +++ b/arch/openrisc/kernel/signal.c @@ -52,31 +52,25 @@ struct rt_sigframe { static int restore_sigcontext(struct pt_regs *regs, struct sigcontext *sc) { unsigned int err = 0; - unsigned long old_usp; /* Alwys make any pending restarted system call return -EINTR */ current_thread_info()->restart_block.fn = do_no_restart_syscall; - /* restore the regs from &sc->regs (same as sc, since regs is first) + /* + * Restore the regs from &sc->regs. * (sc is already checked for VERIFY_READ since the sigframe was * checked in sys_sigreturn previously) */ - - if (__copy_from_user(regs, sc, sizeof(struct pt_regs))) + if (__copy_from_user(regs, sc->regs.gpr, 32 * sizeof(unsigned long))) + goto badframe; + if (__copy_from_user(®s->pc, &sc->regs.pc, sizeof(unsigned long))) + goto badframe; + if (__copy_from_user(®s->sr, &sc->regs.sr, sizeof(unsigned long))) goto badframe; /* make sure the SM-bit is cleared so user-mode cannot fool us */ regs->sr &= ~SPR_SR_SM; - /* restore the old USP as it was before we stacked the sc etc. - * (we cannot just pop the sigcontext since we aligned the sp and - * stuff after pushing it) - */ - - err |= __get_user(old_usp, &sc->usp); - - regs->sp = old_usp; - /* TODO: the other ports use regs->orig_XX to disable syscall checks * after this completes, but we don't use that mechanism. maybe we can * use it now ? @@ -137,18 +131,17 @@ static int setup_sigcontext(struct sigcontext *sc, struct pt_regs *regs, unsigned long mask) { int err = 0; - unsigned long usp = regs->sp; - /* copy the regs. they are first in sc so we can use sc directly */ + /* copy the regs */ - err |= __copy_to_user(sc, regs, sizeof(struct pt_regs)); + err |= __copy_to_user(sc->regs.gpr, regs, 32 * sizeof(unsigned long)); + err |= __copy_to_user(&sc->regs.pc, ®s->pc, sizeof(unsigned long)); + err |= __copy_to_user(&sc->regs.sr, ®s->sr, sizeof(unsigned long)); /* then some other stuff */ err |= __put_user(mask, &sc->oldmask); - err |= __put_user(usp, &sc->usp); - return err; } diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index e66366fd2abc..3735abd7f8f6 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -259,7 +259,7 @@ ENTRY_SAME(ni_syscall) /* query_module */ ENTRY_SAME(poll) /* structs contain pointers and an in_addr... */ - ENTRY_COMP(nfsservctl) + ENTRY_SAME(ni_syscall) /* was nfsservctl */ ENTRY_SAME(setresgid) /* 170 */ ENTRY_SAME(getresgid) ENTRY_SAME(prctl) diff --git a/arch/powerpc/boot/dts/p1023rds.dts b/arch/powerpc/boot/dts/p1023rds.dts index bfa96aa8f2ca..d9b776740a67 100644 --- a/arch/powerpc/boot/dts/p1023rds.dts +++ b/arch/powerpc/boot/dts/p1023rds.dts @@ -387,7 +387,7 @@ #size-cells = <1>; compatible = "cfi-flash"; reg = <0x0 0x0 0x02000000>; - bank-width = <1>; + bank-width = <2>; device-width = <1>; partition@0 { label = "ramdisk"; diff --git a/arch/powerpc/configs/85xx/p1023rds_defconfig b/arch/powerpc/configs/85xx/p1023rds_defconfig index 980ff8f61fd4..3ff5a81c709f 100644 --- a/arch/powerpc/configs/85xx/p1023rds_defconfig +++ b/arch/powerpc/configs/85xx/p1023rds_defconfig @@ -171,3 +171,4 @@ CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_SHA512=y CONFIG_CRYPTO_AES=y # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DEV_FSL_CAAM=y diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig index 10562a5c65b9..4311d02a3bfd 100644 --- a/arch/powerpc/configs/corenet32_smp_defconfig +++ b/arch/powerpc/configs/corenet32_smp_defconfig @@ -185,3 +185,4 @@ CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_SHA512=y CONFIG_CRYPTO_AES=y # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DEV_FSL_CAAM=y diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig index d32283555b53..c92c204a204b 100644 --- a/arch/powerpc/configs/corenet64_smp_defconfig +++ b/arch/powerpc/configs/corenet64_smp_defconfig @@ -100,5 +100,8 @@ CONFIG_DEBUG_INFO=y CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_VIRQ_DEBUG=y CONFIG_CRYPTO_PCBC=m +CONFIG_CRYPTO_SHA256=y +CONFIG_CRYPTO_SHA512=y +CONFIG_CRYPTO_AES=y # CONFIG_CRYPTO_ANSI_CPRNG is not set -CONFIG_CRYPTO_DEV_TALITOS=y +CONFIG_CRYPTO_DEV_FSL_CAAM=y diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig index fcd85d2c72dc..a3467bfb7671 100644 --- a/arch/powerpc/configs/mpc85xx_defconfig +++ b/arch/powerpc/configs/mpc85xx_defconfig @@ -139,6 +139,7 @@ CONFIG_SND=y CONFIG_SND_INTEL8X0=y # CONFIG_SND_PPC is not set # CONFIG_SND_USB is not set +CONFIG_SND_SOC=y CONFIG_HID_A4TECH=y CONFIG_HID_APPLE=y CONFIG_HID_BELKIN=y diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig index 908c941fc24c..9693f6ed3da0 100644 --- a/arch/powerpc/configs/mpc85xx_smp_defconfig +++ b/arch/powerpc/configs/mpc85xx_smp_defconfig @@ -140,6 +140,7 @@ CONFIG_SND=y CONFIG_SND_INTEL8X0=y # CONFIG_SND_PPC is not set # CONFIG_SND_USB is not set +CONFIG_SND_SOC=y CONFIG_HID_A4TECH=y CONFIG_HID_APPLE=y CONFIG_HID_BELKIN=y diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index f6736b7da463..fa0d27a400de 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -171,7 +171,7 @@ SYSCALL_SPU(setresuid) SYSCALL_SPU(getresuid) SYSCALL(ni_syscall) SYSCALL_SPU(poll) -COMPAT_SYS(nfsservctl) +SYSCALL(ni_syscall) SYSCALL_SPU(setresgid) SYSCALL_SPU(getresgid) COMPAT_SYS_SPU(prctl) diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 2de8551df40f..c65f75aa7ff7 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -54,6 +54,7 @@ #define ODSR_CLEAR 0x1c00 #define LTLEECSR_ENABLE_ALL 0xFFC000FC #define ESCSR_CLEAR 0x07120204 +#define IECSR_CLEAR 0x80000000 #define RIO_PORT1_EDCSR 0x0640 #define RIO_PORT2_EDCSR 0x0680 @@ -1089,11 +1090,11 @@ static void port_error_handler(struct rio_mport *port, int offset) if (offset == 0) { out_be32((u32 *)(rio_regs_win + RIO_PORT1_EDCSR), 0); - out_be32((u32 *)(rio_regs_win + RIO_PORT1_IECSR), 0); + out_be32((u32 *)(rio_regs_win + RIO_PORT1_IECSR), IECSR_CLEAR); out_be32((u32 *)(rio_regs_win + RIO_ESCSR), ESCSR_CLEAR); } else { out_be32((u32 *)(rio_regs_win + RIO_PORT2_EDCSR), 0); - out_be32((u32 *)(rio_regs_win + RIO_PORT2_IECSR), 0); + out_be32((u32 *)(rio_regs_win + RIO_PORT2_IECSR), IECSR_CLEAR); out_be32((u32 *)(rio_regs_win + RIO_PORT2_ESCSR), ESCSR_CLEAR); } } diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index 08ab9aa6a0d5..7526db6bf501 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -665,12 +665,6 @@ ENTRY(sys32_poll_wrapper) lgfr %r4,%r4 # long jg sys_poll # branch to system call -ENTRY(compat_sys_nfsservctl_wrapper) - lgfr %r2,%r2 # int - llgtr %r3,%r3 # struct compat_nfsctl_arg* - llgtr %r4,%r4 # union compat_nfsctl_res* - jg compat_sys_nfsservctl # branch to system call - ENTRY(sys32_setresgid16_wrapper) llgfr %r2,%r2 # __kernel_old_gid_emu31_t llgfr %r3,%r3 # __kernel_old_gid_emu31_t diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 068f8465c4ee..f297456dba7a 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -396,17 +396,19 @@ static __init void detect_machine_facilities(void) static __init void rescue_initrd(void) { #ifdef CONFIG_BLK_DEV_INITRD + unsigned long min_initrd_addr = (unsigned long) _end + (4UL << 20); /* - * Move the initrd right behind the bss section in case it starts - * within the bss section. So we don't overwrite it when the bss - * section gets cleared. + * Just like in case of IPL from VM reader we make sure there is a + * gap of 4MB between end of kernel and start of initrd. + * That way we can also be sure that saving an NSS will succeed, + * which however only requires different segments. */ if (!INITRD_START || !INITRD_SIZE) return; - if (INITRD_START >= (unsigned long) __bss_stop) + if (INITRD_START >= min_initrd_addr) return; - memmove(__bss_stop, (void *) INITRD_START, INITRD_SIZE); - INITRD_START = (unsigned long) __bss_stop; + memmove((void *) min_initrd_addr, (void *) INITRD_START, INITRD_SIZE); + INITRD_START = min_initrd_addr; #endif } diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 04361d5a4279..48c710206366 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1220,7 +1220,7 @@ static int __init reipl_fcp_init(void) /* sysfs: create fcp kset for mixing attr group and bin attrs */ reipl_fcp_kset = kset_create_and_add(IPL_FCP_STR, NULL, &reipl_kset->kobj); - if (!reipl_kset) { + if (!reipl_fcp_kset) { free_page((unsigned long) reipl_block_fcp); return -ENOMEM; } @@ -1618,7 +1618,8 @@ static struct shutdown_action vmcmd_action = {SHUTDOWN_ACTION_VMCMD_STR, static void stop_run(struct shutdown_trigger *trigger) { - if (strcmp(trigger->name, ON_PANIC_STR) == 0) + if (strcmp(trigger->name, ON_PANIC_STR) == 0 || + strcmp(trigger->name, ON_RESTART_STR) == 0) disabled_wait((unsigned long) __builtin_return_address(0)); while (sigp(smp_processor_id(), sigp_stop) == sigp_busy) cpu_relax(); @@ -1717,7 +1718,7 @@ static void do_panic(void) /* on restart */ static struct shutdown_trigger on_restart_trigger = {ON_RESTART_STR, - &reipl_action}; + &stop_action}; static ssize_t on_restart_show(struct kobject *kobj, struct kobj_attribute *attr, char *page) diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 6ee39ef8fe4a..73eb08c874fb 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -177,7 +177,7 @@ SYSCALL(sys_getresuid16,sys_ni_syscall,sys32_getresuid16_wrapper) /* 165 old get NI_SYSCALL /* for vm86 */ NI_SYSCALL /* old sys_query_module */ SYSCALL(sys_poll,sys_poll,sys32_poll_wrapper) -SYSCALL(sys_nfsservctl,sys_nfsservctl,compat_sys_nfsservctl_wrapper) +NI_SYSCALL /* old nfsservctl */ SYSCALL(sys_setresgid16,sys_ni_syscall,sys32_setresgid16_wrapper) /* 170 old setresgid16 syscall */ SYSCALL(sys_getresgid16,sys_ni_syscall,sys32_getresgid16_wrapper) /* old getresgid16 syscall */ SYSCALL(sys_prctl,sys_prctl,sys32_prctl_wrapper) diff --git a/arch/sh/include/asm/ptrace.h b/arch/sh/include/asm/ptrace.h index b97baf81a87b..2d3679b2447f 100644 --- a/arch/sh/include/asm/ptrace.h +++ b/arch/sh/include/asm/ptrace.h @@ -123,7 +123,7 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, struct perf_event; struct perf_sample_data; -extern void ptrace_triggered(struct perf_event *bp, int nmi, +extern void ptrace_triggered(struct perf_event *bp, struct perf_sample_data *data, struct pt_regs *regs); #define task_pt_regs(task) \ diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7757.c b/arch/sh/kernel/cpu/sh4a/setup-sh7757.c index e915deafac89..05559295d2ca 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7757.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7757.c @@ -15,6 +15,7 @@ #include <linux/serial_sci.h> #include <linux/io.h> #include <linux/mm.h> +#include <linux/dma-mapping.h> #include <linux/sh_timer.h> #include <linux/sh_dma.h> diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index 32114e0941ae..db4ecd731a00 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -22,7 +22,7 @@ #include <linux/atomic.h> #include <asm/smp.h> -static void (*pm_idle)(void); +void (*pm_idle)(void); static int hlt_counter; diff --git a/arch/sh/kernel/syscalls_32.S b/arch/sh/kernel/syscalls_32.S index 39b051de4c7c..293e39c59c00 100644 --- a/arch/sh/kernel/syscalls_32.S +++ b/arch/sh/kernel/syscalls_32.S @@ -185,7 +185,7 @@ ENTRY(sys_call_table) .long sys_ni_syscall /* vm86 */ .long sys_ni_syscall /* old "query_module" */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* was nfsservctl */ .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl diff --git a/arch/sh/kernel/syscalls_64.S b/arch/sh/kernel/syscalls_64.S index 089c4d825d08..ceb34b94afa9 100644 --- a/arch/sh/kernel/syscalls_64.S +++ b/arch/sh/kernel/syscalls_64.S @@ -189,7 +189,7 @@ sys_call_table: .long sys_ni_syscall /* vm86 */ .long sys_ni_syscall /* old "query_module" */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* was nfsservctl */ .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c index d9006f8ffc14..7bbef95c9d1b 100644 --- a/arch/sh/kernel/traps_32.c +++ b/arch/sh/kernel/traps_32.c @@ -316,6 +316,35 @@ static int handle_unaligned_ins(insn_size_t instruction, struct pt_regs *regs, break; } break; + + case 9: /* mov.w @(disp,PC),Rn */ + srcu = (unsigned char __user *)regs->pc; + srcu += 4; + srcu += (instruction & 0x00FF) << 1; + dst = (unsigned char *)rn; + *(unsigned long *)dst = 0; + +#if !defined(__LITTLE_ENDIAN__) + dst += 2; +#endif + + if (ma->from(dst, srcu, 2)) + goto fetch_fault; + sign_extend(2, dst); + ret = 0; + break; + + case 0xd: /* mov.l @(disp,PC),Rn */ + srcu = (unsigned char __user *)(regs->pc & ~0x3); + srcu += 4; + srcu += (instruction & 0x00FF) << 2; + dst = (unsigned char *)rn; + *(unsigned long *)dst = 0; + + if (ma->from(dst, srcu, 4)) + goto fetch_fault; + ret = 0; + break; } return ret; @@ -466,6 +495,7 @@ int handle_unaligned_access(insn_size_t instruction, struct pt_regs *regs, case 0x0500: /* mov.w @(disp,Rm),R0 */ goto simple; case 0x0B00: /* bf lab - no delayslot*/ + ret = 0; break; case 0x0F00: /* bf/s lab */ ret = handle_delayslot(regs, instruction, ma); @@ -479,6 +509,7 @@ int handle_unaligned_access(insn_size_t instruction, struct pt_regs *regs, } break; case 0x0900: /* bt lab - no delayslot */ + ret = 0; break; case 0x0D00: /* bt/s lab */ ret = handle_delayslot(regs, instruction, ma); @@ -494,6 +525,9 @@ int handle_unaligned_access(insn_size_t instruction, struct pt_regs *regs, } break; + case 0x9000: /* mov.w @(disp,Rm),Rn */ + goto simple; + case 0xA000: /* bra label */ ret = handle_delayslot(regs, instruction, ma); if (ret==0) @@ -507,6 +541,9 @@ int handle_unaligned_access(insn_size_t instruction, struct pt_regs *regs, regs->pc += SH_PC_12BIT_OFFSET(instruction); } break; + + case 0xD000: /* mov.l @(disp,Rm),Rn */ + goto simple; } return ret; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 42c67beadcae..1a6f20d4e7e6 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -55,6 +55,7 @@ config SPARC64 select PERF_USE_VMALLOC select IRQ_PREFLOW_FASTEOI select ARCH_HAVE_NMI_SAFE_CMPXCHG + select HAVE_C_RECORDMCOUNT config ARCH_DEFCONFIG string diff --git a/arch/sparc/include/asm/sigcontext.h b/arch/sparc/include/asm/sigcontext.h index a1607d180354..69914d748130 100644 --- a/arch/sparc/include/asm/sigcontext.h +++ b/arch/sparc/include/asm/sigcontext.h @@ -45,6 +45,19 @@ typedef struct { int si_mask; } __siginfo32_t; +#define __SIGC_MAXWIN 7 + +typedef struct { + unsigned long locals[8]; + unsigned long ins[8]; +} __siginfo_reg_window; + +typedef struct { + int wsaved; + __siginfo_reg_window reg_window[__SIGC_MAXWIN]; + unsigned long rwbuf_stkptrs[__SIGC_MAXWIN]; +} __siginfo_rwin_t; + #ifdef CONFIG_SPARC64 typedef struct { unsigned int si_float_regs [64]; @@ -73,6 +86,7 @@ struct sigcontext { unsigned long ss_size; } sigc_stack; unsigned long sigc_mask; + __siginfo_rwin_t * sigc_rwin_save; }; #else diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h index 5f5b8bf3f50d..bcc98fc35281 100644 --- a/arch/sparc/include/asm/spinlock_32.h +++ b/arch/sparc/include/asm/spinlock_32.h @@ -131,6 +131,15 @@ static inline void arch_write_lock(arch_rwlock_t *rw) *(volatile __u32 *)&lp->lock = ~0U; } +static void inline arch_write_unlock(arch_rwlock_t *lock) +{ + __asm__ __volatile__( +" st %%g0, [%0]" + : /* no outputs */ + : "r" (lock) + : "memory"); +} + static inline int arch_write_trylock(arch_rwlock_t *rw) { unsigned int val; @@ -175,8 +184,6 @@ static inline int __arch_read_trylock(arch_rwlock_t *rw) res; \ }) -#define arch_write_unlock(rw) do { (rw)->lock = 0; } while(0) - #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) #define arch_read_lock_flags(rw, flags) arch_read_lock(rw) #define arch_write_lock_flags(rw, flags) arch_write_lock(rw) diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h index 073936a8b275..968917694978 100644 --- a/arch/sparc/include/asm/spinlock_64.h +++ b/arch/sparc/include/asm/spinlock_64.h @@ -210,14 +210,8 @@ static int inline arch_write_trylock(arch_rwlock_t *lock) return result; } -#define arch_read_lock(p) arch_read_lock(p) #define arch_read_lock_flags(p, f) arch_read_lock(p) -#define arch_read_trylock(p) arch_read_trylock(p) -#define arch_read_unlock(p) arch_read_unlock(p) -#define arch_write_lock(p) arch_write_lock(p) #define arch_write_lock_flags(p, f) arch_write_lock(p) -#define arch_write_unlock(p) arch_write_unlock(p) -#define arch_write_trylock(p) arch_write_trylock(p) #define arch_read_can_lock(rw) (!((rw)->lock & 0x80000000UL)) #define arch_write_can_lock(rw) (!(rw)->lock) diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile index b90b4a1d070a..cb85458f89d2 100644 --- a/arch/sparc/kernel/Makefile +++ b/arch/sparc/kernel/Makefile @@ -32,6 +32,7 @@ obj-$(CONFIG_SPARC32) += sun4m_irq.o sun4c_irq.o sun4d_irq.o obj-y += process_$(BITS).o obj-y += signal_$(BITS).o +obj-y += sigutil_$(BITS).o obj-$(CONFIG_SPARC32) += ioport.o obj-y += setup_$(BITS).o obj-y += idprom.o diff --git a/arch/sparc/kernel/irq.h b/arch/sparc/kernel/irq.h index 100b9c204e78..42851122bbd9 100644 --- a/arch/sparc/kernel/irq.h +++ b/arch/sparc/kernel/irq.h @@ -88,7 +88,7 @@ BTFIXUPDEF_CALL(void, set_irq_udt, int) #define set_irq_udt(cpu) BTFIXUP_CALL(set_irq_udt)(cpu) /* All SUN4D IPIs are sent on this IRQ, may be shared with hard IRQs */ -#define SUN4D_IPI_IRQ 14 +#define SUN4D_IPI_IRQ 13 extern void sun4d_ipi_interrupt(void); diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c index a19f04195478..1aaf8c180be5 100644 --- a/arch/sparc/kernel/pcic.c +++ b/arch/sparc/kernel/pcic.c @@ -352,8 +352,8 @@ int __init pcic_probe(void) strcpy(pbm->prom_name, namebuf); { - extern volatile int t_nmi[1]; - extern int pcic_nmi_trap_patch[1]; + extern volatile int t_nmi[4]; + extern int pcic_nmi_trap_patch[4]; t_nmi[0] = pcic_nmi_trap_patch[0]; t_nmi[1] = pcic_nmi_trap_patch[1]; diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 3e9daea1653d..3c5bb784214f 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -440,8 +440,14 @@ static void __init init_sparc64_elf_hwcap(void) cap |= AV_SPARC_VIS; if (tlb_type == cheetah || tlb_type == cheetah_plus) cap |= AV_SPARC_VIS | AV_SPARC_VIS2; - if (tlb_type == cheetah_plus) - cap |= AV_SPARC_POPC; + if (tlb_type == cheetah_plus) { + unsigned long impl, ver; + + __asm__ __volatile__("rdpr %%ver, %0" : "=r" (ver)); + impl = ((ver >> 32) & 0xffff); + if (impl == PANTHER_IMPL) + cap |= AV_SPARC_POPC; + } if (tlb_type == hypervisor) { if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1) cap |= AV_SPARC_ASI_BLK_INIT; diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index 75fad425e249..1ba95aff5d59 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -29,6 +29,8 @@ #include <asm/visasm.h> #include <asm/compat_signal.h> +#include "sigutil.h" + #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) /* This magic should be in g_upper[0] for all upper parts @@ -44,14 +46,14 @@ typedef struct { struct signal_frame32 { struct sparc_stackf32 ss; __siginfo32_t info; - /* __siginfo_fpu32_t * */ u32 fpu_save; + /* __siginfo_fpu_t * */ u32 fpu_save; unsigned int insns[2]; unsigned int extramask[_COMPAT_NSIG_WORDS - 1]; unsigned int extra_size; /* Should be sizeof(siginfo_extra_v8plus_t) */ /* Only valid if (info.si_regs.psr & (PSR_VERS|PSR_IMPL)) == PSR_V8PLUS */ siginfo_extra_v8plus_t v8plus; - __siginfo_fpu_t fpu_state; -}; + /* __siginfo_rwin_t * */u32 rwin_save; +} __attribute__((aligned(8))); typedef struct compat_siginfo{ int si_signo; @@ -110,18 +112,14 @@ struct rt_signal_frame32 { compat_siginfo_t info; struct pt_regs32 regs; compat_sigset_t mask; - /* __siginfo_fpu32_t * */ u32 fpu_save; + /* __siginfo_fpu_t * */ u32 fpu_save; unsigned int insns[2]; stack_t32 stack; unsigned int extra_size; /* Should be sizeof(siginfo_extra_v8plus_t) */ /* Only valid if (regs.psr & (PSR_VERS|PSR_IMPL)) == PSR_V8PLUS */ siginfo_extra_v8plus_t v8plus; - __siginfo_fpu_t fpu_state; -}; - -/* Align macros */ -#define SF_ALIGNEDSZ (((sizeof(struct signal_frame32) + 15) & (~15))) -#define RT_ALIGNEDSZ (((sizeof(struct rt_signal_frame32) + 15) & (~15))) + /* __siginfo_rwin_t * */u32 rwin_save; +} __attribute__((aligned(8))); int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) { @@ -192,30 +190,13 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) return 0; } -static int restore_fpu_state32(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) -{ - unsigned long *fpregs = current_thread_info()->fpregs; - unsigned long fprs; - int err; - - err = __get_user(fprs, &fpu->si_fprs); - fprs_write(0); - regs->tstate &= ~TSTATE_PEF; - if (fprs & FPRS_DL) - err |= copy_from_user(fpregs, &fpu->si_float_regs[0], (sizeof(unsigned int) * 32)); - if (fprs & FPRS_DU) - err |= copy_from_user(fpregs+16, &fpu->si_float_regs[32], (sizeof(unsigned int) * 32)); - err |= __get_user(current_thread_info()->xfsr[0], &fpu->si_fsr); - err |= __get_user(current_thread_info()->gsr[0], &fpu->si_gsr); - current_thread_info()->fpsaved[0] |= fprs; - return err; -} - void do_sigreturn32(struct pt_regs *regs) { struct signal_frame32 __user *sf; + compat_uptr_t fpu_save; + compat_uptr_t rwin_save; unsigned int psr; - unsigned pc, npc, fpu_save; + unsigned pc, npc; sigset_t set; unsigned seta[_COMPAT_NSIG_WORDS]; int err, i; @@ -273,8 +254,13 @@ void do_sigreturn32(struct pt_regs *regs) pt_regs_clear_syscall(regs); err |= __get_user(fpu_save, &sf->fpu_save); - if (fpu_save) - err |= restore_fpu_state32(regs, &sf->fpu_state); + if (!err && fpu_save) + err |= restore_fpu_state(regs, compat_ptr(fpu_save)); + err |= __get_user(rwin_save, &sf->rwin_save); + if (!err && rwin_save) { + if (restore_rwin_state(compat_ptr(rwin_save))) + goto segv; + } err |= __get_user(seta[0], &sf->info.si_mask); err |= copy_from_user(seta+1, &sf->extramask, (_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int)); @@ -300,7 +286,9 @@ segv: asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) { struct rt_signal_frame32 __user *sf; - unsigned int psr, pc, npc, fpu_save, u_ss_sp; + unsigned int psr, pc, npc, u_ss_sp; + compat_uptr_t fpu_save; + compat_uptr_t rwin_save; mm_segment_t old_fs; sigset_t set; compat_sigset_t seta; @@ -359,8 +347,8 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) pt_regs_clear_syscall(regs); err |= __get_user(fpu_save, &sf->fpu_save); - if (fpu_save) - err |= restore_fpu_state32(regs, &sf->fpu_state); + if (!err && fpu_save) + err |= restore_fpu_state(regs, compat_ptr(fpu_save)); err |= copy_from_user(&seta, &sf->mask, sizeof(compat_sigset_t)); err |= __get_user(u_ss_sp, &sf->stack.ss_sp); st.ss_sp = compat_ptr(u_ss_sp); @@ -376,6 +364,12 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) do_sigaltstack((stack_t __user *) &st, NULL, (unsigned long)sf); set_fs(old_fs); + err |= __get_user(rwin_save, &sf->rwin_save); + if (!err && rwin_save) { + if (restore_rwin_state(compat_ptr(rwin_save))) + goto segv; + } + switch (_NSIG_WORDS) { case 4: set.sig[3] = seta.sig[6] + (((long)seta.sig[7]) << 32); case 3: set.sig[2] = seta.sig[4] + (((long)seta.sig[5]) << 32); @@ -433,26 +427,6 @@ static void __user *get_sigframe(struct sigaction *sa, struct pt_regs *regs, uns return (void __user *) sp; } -static int save_fpu_state32(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) -{ - unsigned long *fpregs = current_thread_info()->fpregs; - unsigned long fprs; - int err = 0; - - fprs = current_thread_info()->fpsaved[0]; - if (fprs & FPRS_DL) - err |= copy_to_user(&fpu->si_float_regs[0], fpregs, - (sizeof(unsigned int) * 32)); - if (fprs & FPRS_DU) - err |= copy_to_user(&fpu->si_float_regs[32], fpregs+16, - (sizeof(unsigned int) * 32)); - err |= __put_user(current_thread_info()->xfsr[0], &fpu->si_fsr); - err |= __put_user(current_thread_info()->gsr[0], &fpu->si_gsr); - err |= __put_user(fprs, &fpu->si_fprs); - - return err; -} - /* The I-cache flush instruction only works in the primary ASI, which * right now is the nucleus, aka. kernel space. * @@ -515,18 +489,23 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, int signo, sigset_t *oldset) { struct signal_frame32 __user *sf; + int i, err, wsaved; + void __user *tail; int sigframe_size; u32 psr; - int i, err; unsigned int seta[_COMPAT_NSIG_WORDS]; /* 1. Make sure everything is clean */ synchronize_user_stack(); save_and_clear_fpu(); - sigframe_size = SF_ALIGNEDSZ; - if (!(current_thread_info()->fpsaved[0] & FPRS_FEF)) - sigframe_size -= sizeof(__siginfo_fpu_t); + wsaved = get_thread_wsaved(); + + sigframe_size = sizeof(*sf); + if (current_thread_info()->fpsaved[0] & FPRS_FEF) + sigframe_size += sizeof(__siginfo_fpu_t); + if (wsaved) + sigframe_size += sizeof(__siginfo_rwin_t); sf = (struct signal_frame32 __user *) get_sigframe(&ka->sa, regs, sigframe_size); @@ -534,8 +513,7 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, if (invalid_frame_pointer(sf, sigframe_size)) goto sigill; - if (get_thread_wsaved() != 0) - goto sigill; + tail = (sf + 1); /* 2. Save the current process state */ if (test_thread_flag(TIF_32BIT)) { @@ -560,11 +538,22 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, &sf->v8plus.asi); if (psr & PSR_EF) { - err |= save_fpu_state32(regs, &sf->fpu_state); - err |= __put_user((u64)&sf->fpu_state, &sf->fpu_save); + __siginfo_fpu_t __user *fp = tail; + tail += sizeof(*fp); + err |= save_fpu_state(regs, fp); + err |= __put_user((u64)fp, &sf->fpu_save); } else { err |= __put_user(0, &sf->fpu_save); } + if (wsaved) { + __siginfo_rwin_t __user *rwp = tail; + tail += sizeof(*rwp); + err |= save_rwin_state(wsaved, rwp); + err |= __put_user((u64)rwp, &sf->rwin_save); + set_thread_wsaved(0); + } else { + err |= __put_user(0, &sf->rwin_save); + } switch (_NSIG_WORDS) { case 4: seta[7] = (oldset->sig[3] >> 32); @@ -580,10 +569,21 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, err |= __copy_to_user(sf->extramask, seta + 1, (_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int)); - err |= copy_in_user((u32 __user *)sf, - (u32 __user *)(regs->u_regs[UREG_FP]), - sizeof(struct reg_window32)); - + if (!wsaved) { + err |= copy_in_user((u32 __user *)sf, + (u32 __user *)(regs->u_regs[UREG_FP]), + sizeof(struct reg_window32)); + } else { + struct reg_window *rp; + + rp = ¤t_thread_info()->reg_window[wsaved - 1]; + for (i = 0; i < 8; i++) + err |= __put_user(rp->locals[i], &sf->ss.locals[i]); + for (i = 0; i < 6; i++) + err |= __put_user(rp->ins[i], &sf->ss.ins[i]); + err |= __put_user(rp->ins[6], &sf->ss.fp); + err |= __put_user(rp->ins[7], &sf->ss.callers_pc); + } if (err) goto sigsegv; @@ -613,7 +613,6 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, err |= __put_user(0x91d02010, &sf->insns[1]); /*t 0x10*/ if (err) goto sigsegv; - flush_signal_insns(address); } return 0; @@ -632,18 +631,23 @@ static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs, siginfo_t *info) { struct rt_signal_frame32 __user *sf; + int i, err, wsaved; + void __user *tail; int sigframe_size; u32 psr; - int i, err; compat_sigset_t seta; /* 1. Make sure everything is clean */ synchronize_user_stack(); save_and_clear_fpu(); - sigframe_size = RT_ALIGNEDSZ; - if (!(current_thread_info()->fpsaved[0] & FPRS_FEF)) - sigframe_size -= sizeof(__siginfo_fpu_t); + wsaved = get_thread_wsaved(); + + sigframe_size = sizeof(*sf); + if (current_thread_info()->fpsaved[0] & FPRS_FEF) + sigframe_size += sizeof(__siginfo_fpu_t); + if (wsaved) + sigframe_size += sizeof(__siginfo_rwin_t); sf = (struct rt_signal_frame32 __user *) get_sigframe(&ka->sa, regs, sigframe_size); @@ -651,8 +655,7 @@ static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs, if (invalid_frame_pointer(sf, sigframe_size)) goto sigill; - if (get_thread_wsaved() != 0) - goto sigill; + tail = (sf + 1); /* 2. Save the current process state */ if (test_thread_flag(TIF_32BIT)) { @@ -677,11 +680,22 @@ static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs, &sf->v8plus.asi); if (psr & PSR_EF) { - err |= save_fpu_state32(regs, &sf->fpu_state); - err |= __put_user((u64)&sf->fpu_state, &sf->fpu_save); + __siginfo_fpu_t __user *fp = tail; + tail += sizeof(*fp); + err |= save_fpu_state(regs, fp); + err |= __put_user((u64)fp, &sf->fpu_save); } else { err |= __put_user(0, &sf->fpu_save); } + if (wsaved) { + __siginfo_rwin_t __user *rwp = tail; + tail += sizeof(*rwp); + err |= save_rwin_state(wsaved, rwp); + err |= __put_user((u64)rwp, &sf->rwin_save); + set_thread_wsaved(0); + } else { + err |= __put_user(0, &sf->rwin_save); + } /* Update the siginfo structure. */ err |= copy_siginfo_to_user32(&sf->info, info); @@ -703,9 +717,21 @@ static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs, } err |= __copy_to_user(&sf->mask, &seta, sizeof(compat_sigset_t)); - err |= copy_in_user((u32 __user *)sf, - (u32 __user *)(regs->u_regs[UREG_FP]), - sizeof(struct reg_window32)); + if (!wsaved) { + err |= copy_in_user((u32 __user *)sf, + (u32 __user *)(regs->u_regs[UREG_FP]), + sizeof(struct reg_window32)); + } else { + struct reg_window *rp; + + rp = ¤t_thread_info()->reg_window[wsaved - 1]; + for (i = 0; i < 8; i++) + err |= __put_user(rp->locals[i], &sf->ss.locals[i]); + for (i = 0; i < 6; i++) + err |= __put_user(rp->ins[i], &sf->ss.ins[i]); + err |= __put_user(rp->ins[6], &sf->ss.fp); + err |= __put_user(rp->ins[7], &sf->ss.callers_pc); + } if (err) goto sigsegv; diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index 5e5c5fd03783..04ede8f04add 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -26,6 +26,8 @@ #include <asm/pgtable.h> #include <asm/cacheflush.h> /* flush_sig_insns */ +#include "sigutil.h" + #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) extern void fpsave(unsigned long *fpregs, unsigned long *fsr, @@ -39,8 +41,8 @@ struct signal_frame { unsigned long insns[2] __attribute__ ((aligned (8))); unsigned int extramask[_NSIG_WORDS - 1]; unsigned int extra_size; /* Should be 0 */ - __siginfo_fpu_t fpu_state; -}; + __siginfo_rwin_t __user *rwin_save; +} __attribute__((aligned(8))); struct rt_signal_frame { struct sparc_stackf ss; @@ -51,8 +53,8 @@ struct rt_signal_frame { unsigned int insns[2]; stack_t stack; unsigned int extra_size; /* Should be 0 */ - __siginfo_fpu_t fpu_state; -}; + __siginfo_rwin_t __user *rwin_save; +} __attribute__((aligned(8))); /* Align macros */ #define SF_ALIGNEDSZ (((sizeof(struct signal_frame) + 7) & (~7))) @@ -79,43 +81,13 @@ asmlinkage int sys_sigsuspend(old_sigset_t set) return _sigpause_common(set); } -static inline int -restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) -{ - int err; -#ifdef CONFIG_SMP - if (test_tsk_thread_flag(current, TIF_USEDFPU)) - regs->psr &= ~PSR_EF; -#else - if (current == last_task_used_math) { - last_task_used_math = NULL; - regs->psr &= ~PSR_EF; - } -#endif - set_used_math(); - clear_tsk_thread_flag(current, TIF_USEDFPU); - - if (!access_ok(VERIFY_READ, fpu, sizeof(*fpu))) - return -EFAULT; - - err = __copy_from_user(¤t->thread.float_regs[0], &fpu->si_float_regs[0], - (sizeof(unsigned long) * 32)); - err |= __get_user(current->thread.fsr, &fpu->si_fsr); - err |= __get_user(current->thread.fpqdepth, &fpu->si_fpqdepth); - if (current->thread.fpqdepth != 0) - err |= __copy_from_user(¤t->thread.fpqueue[0], - &fpu->si_fpqueue[0], - ((sizeof(unsigned long) + - (sizeof(unsigned long *)))*16)); - return err; -} - asmlinkage void do_sigreturn(struct pt_regs *regs) { struct signal_frame __user *sf; unsigned long up_psr, pc, npc; sigset_t set; __siginfo_fpu_t __user *fpu_save; + __siginfo_rwin_t __user *rwin_save; int err; /* Always make any pending restarted system calls return -EINTR */ @@ -150,9 +122,11 @@ asmlinkage void do_sigreturn(struct pt_regs *regs) pt_regs_clear_syscall(regs); err |= __get_user(fpu_save, &sf->fpu_save); - if (fpu_save) err |= restore_fpu_state(regs, fpu_save); + err |= __get_user(rwin_save, &sf->rwin_save); + if (rwin_save) + err |= restore_rwin_state(rwin_save); /* This is pretty much atomic, no amount locking would prevent * the races which exist anyways. @@ -180,6 +154,7 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs) struct rt_signal_frame __user *sf; unsigned int psr, pc, npc; __siginfo_fpu_t __user *fpu_save; + __siginfo_rwin_t __user *rwin_save; mm_segment_t old_fs; sigset_t set; stack_t st; @@ -207,8 +182,7 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs) pt_regs_clear_syscall(regs); err |= __get_user(fpu_save, &sf->fpu_save); - - if (fpu_save) + if (!err && fpu_save) err |= restore_fpu_state(regs, fpu_save); err |= __copy_from_user(&set, &sf->mask, sizeof(sigset_t)); @@ -228,6 +202,12 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs) do_sigaltstack((const stack_t __user *) &st, NULL, (unsigned long)sf); set_fs(old_fs); + err |= __get_user(rwin_save, &sf->rwin_save); + if (!err && rwin_save) { + if (restore_rwin_state(rwin_save)) + goto segv; + } + sigdelsetmask(&set, ~_BLOCKABLE); spin_lock_irq(¤t->sighand->siglock); current->blocked = set; @@ -280,53 +260,23 @@ static inline void __user *get_sigframe(struct sigaction *sa, struct pt_regs *re return (void __user *) sp; } -static inline int -save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) -{ - int err = 0; -#ifdef CONFIG_SMP - if (test_tsk_thread_flag(current, TIF_USEDFPU)) { - put_psr(get_psr() | PSR_EF); - fpsave(¤t->thread.float_regs[0], ¤t->thread.fsr, - ¤t->thread.fpqueue[0], ¤t->thread.fpqdepth); - regs->psr &= ~(PSR_EF); - clear_tsk_thread_flag(current, TIF_USEDFPU); - } -#else - if (current == last_task_used_math) { - put_psr(get_psr() | PSR_EF); - fpsave(¤t->thread.float_regs[0], ¤t->thread.fsr, - ¤t->thread.fpqueue[0], ¤t->thread.fpqdepth); - last_task_used_math = NULL; - regs->psr &= ~(PSR_EF); - } -#endif - err |= __copy_to_user(&fpu->si_float_regs[0], - ¤t->thread.float_regs[0], - (sizeof(unsigned long) * 32)); - err |= __put_user(current->thread.fsr, &fpu->si_fsr); - err |= __put_user(current->thread.fpqdepth, &fpu->si_fpqdepth); - if (current->thread.fpqdepth != 0) - err |= __copy_to_user(&fpu->si_fpqueue[0], - ¤t->thread.fpqueue[0], - ((sizeof(unsigned long) + - (sizeof(unsigned long *)))*16)); - clear_used_math(); - return err; -} - static int setup_frame(struct k_sigaction *ka, struct pt_regs *regs, int signo, sigset_t *oldset) { struct signal_frame __user *sf; - int sigframe_size, err; + int sigframe_size, err, wsaved; + void __user *tail; /* 1. Make sure everything is clean */ synchronize_user_stack(); - sigframe_size = SF_ALIGNEDSZ; - if (!used_math()) - sigframe_size -= sizeof(__siginfo_fpu_t); + wsaved = current_thread_info()->w_saved; + + sigframe_size = sizeof(*sf); + if (used_math()) + sigframe_size += sizeof(__siginfo_fpu_t); + if (wsaved) + sigframe_size += sizeof(__siginfo_rwin_t); sf = (struct signal_frame __user *) get_sigframe(&ka->sa, regs, sigframe_size); @@ -334,8 +284,7 @@ static int setup_frame(struct k_sigaction *ka, struct pt_regs *regs, if (invalid_frame_pointer(sf, sigframe_size)) goto sigill_and_return; - if (current_thread_info()->w_saved != 0) - goto sigill_and_return; + tail = sf + 1; /* 2. Save the current process state */ err = __copy_to_user(&sf->info.si_regs, regs, sizeof(struct pt_regs)); @@ -343,17 +292,34 @@ static int setup_frame(struct k_sigaction *ka, struct pt_regs *regs, err |= __put_user(0, &sf->extra_size); if (used_math()) { - err |= save_fpu_state(regs, &sf->fpu_state); - err |= __put_user(&sf->fpu_state, &sf->fpu_save); + __siginfo_fpu_t __user *fp = tail; + tail += sizeof(*fp); + err |= save_fpu_state(regs, fp); + err |= __put_user(fp, &sf->fpu_save); } else { err |= __put_user(0, &sf->fpu_save); } + if (wsaved) { + __siginfo_rwin_t __user *rwp = tail; + tail += sizeof(*rwp); + err |= save_rwin_state(wsaved, rwp); + err |= __put_user(rwp, &sf->rwin_save); + } else { + err |= __put_user(0, &sf->rwin_save); + } err |= __put_user(oldset->sig[0], &sf->info.si_mask); err |= __copy_to_user(sf->extramask, &oldset->sig[1], (_NSIG_WORDS - 1) * sizeof(unsigned int)); - err |= __copy_to_user(sf, (char *) regs->u_regs[UREG_FP], - sizeof(struct reg_window32)); + if (!wsaved) { + err |= __copy_to_user(sf, (char *) regs->u_regs[UREG_FP], + sizeof(struct reg_window32)); + } else { + struct reg_window32 *rp; + + rp = ¤t_thread_info()->reg_window[wsaved - 1]; + err |= __copy_to_user(sf, rp, sizeof(struct reg_window32)); + } if (err) goto sigsegv; @@ -399,21 +365,24 @@ static int setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, int signo, sigset_t *oldset, siginfo_t *info) { struct rt_signal_frame __user *sf; - int sigframe_size; + int sigframe_size, wsaved; + void __user *tail; unsigned int psr; int err; synchronize_user_stack(); - sigframe_size = RT_ALIGNEDSZ; - if (!used_math()) - sigframe_size -= sizeof(__siginfo_fpu_t); + wsaved = current_thread_info()->w_saved; + sigframe_size = sizeof(*sf); + if (used_math()) + sigframe_size += sizeof(__siginfo_fpu_t); + if (wsaved) + sigframe_size += sizeof(__siginfo_rwin_t); sf = (struct rt_signal_frame __user *) get_sigframe(&ka->sa, regs, sigframe_size); if (invalid_frame_pointer(sf, sigframe_size)) goto sigill; - if (current_thread_info()->w_saved != 0) - goto sigill; + tail = sf + 1; err = __put_user(regs->pc, &sf->regs.pc); err |= __put_user(regs->npc, &sf->regs.npc); err |= __put_user(regs->y, &sf->regs.y); @@ -425,11 +394,21 @@ static int setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, err |= __put_user(0, &sf->extra_size); if (psr & PSR_EF) { - err |= save_fpu_state(regs, &sf->fpu_state); - err |= __put_user(&sf->fpu_state, &sf->fpu_save); + __siginfo_fpu_t *fp = tail; + tail += sizeof(*fp); + err |= save_fpu_state(regs, fp); + err |= __put_user(fp, &sf->fpu_save); } else { err |= __put_user(0, &sf->fpu_save); } + if (wsaved) { + __siginfo_rwin_t *rwp = tail; + tail += sizeof(*rwp); + err |= save_rwin_state(wsaved, rwp); + err |= __put_user(rwp, &sf->rwin_save); + } else { + err |= __put_user(0, &sf->rwin_save); + } err |= __copy_to_user(&sf->mask, &oldset->sig[0], sizeof(sigset_t)); /* Setup sigaltstack */ @@ -437,8 +416,15 @@ static int setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, err |= __put_user(sas_ss_flags(regs->u_regs[UREG_FP]), &sf->stack.ss_flags); err |= __put_user(current->sas_ss_size, &sf->stack.ss_size); - err |= __copy_to_user(sf, (char *) regs->u_regs[UREG_FP], - sizeof(struct reg_window32)); + if (!wsaved) { + err |= __copy_to_user(sf, (char *) regs->u_regs[UREG_FP], + sizeof(struct reg_window32)); + } else { + struct reg_window32 *rp; + + rp = ¤t_thread_info()->reg_window[wsaved - 1]; + err |= __copy_to_user(sf, rp, sizeof(struct reg_window32)); + } err |= copy_siginfo_to_user(&sf->info, info); diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index 006fe4515886..47509df3b893 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -34,6 +34,7 @@ #include "entry.h" #include "systbls.h" +#include "sigutil.h" #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) @@ -236,7 +237,7 @@ struct rt_signal_frame { __siginfo_fpu_t __user *fpu_save; stack_t stack; sigset_t mask; - __siginfo_fpu_t fpu_state; + __siginfo_rwin_t *rwin_save; }; static long _sigpause_common(old_sigset_t set) @@ -266,33 +267,12 @@ asmlinkage long sys_sigsuspend(old_sigset_t set) return _sigpause_common(set); } -static inline int -restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) -{ - unsigned long *fpregs = current_thread_info()->fpregs; - unsigned long fprs; - int err; - - err = __get_user(fprs, &fpu->si_fprs); - fprs_write(0); - regs->tstate &= ~TSTATE_PEF; - if (fprs & FPRS_DL) - err |= copy_from_user(fpregs, &fpu->si_float_regs[0], - (sizeof(unsigned int) * 32)); - if (fprs & FPRS_DU) - err |= copy_from_user(fpregs+16, &fpu->si_float_regs[32], - (sizeof(unsigned int) * 32)); - err |= __get_user(current_thread_info()->xfsr[0], &fpu->si_fsr); - err |= __get_user(current_thread_info()->gsr[0], &fpu->si_gsr); - current_thread_info()->fpsaved[0] |= fprs; - return err; -} - void do_rt_sigreturn(struct pt_regs *regs) { struct rt_signal_frame __user *sf; unsigned long tpc, tnpc, tstate; __siginfo_fpu_t __user *fpu_save; + __siginfo_rwin_t __user *rwin_save; sigset_t set; int err; @@ -325,8 +305,8 @@ void do_rt_sigreturn(struct pt_regs *regs) regs->tstate |= (tstate & (TSTATE_ASI | TSTATE_ICC | TSTATE_XCC)); err |= __get_user(fpu_save, &sf->fpu_save); - if (fpu_save) - err |= restore_fpu_state(regs, &sf->fpu_state); + if (!err && fpu_save) + err |= restore_fpu_state(regs, fpu_save); err |= __copy_from_user(&set, &sf->mask, sizeof(sigset_t)); err |= do_sigaltstack(&sf->stack, NULL, (unsigned long)sf); @@ -334,6 +314,12 @@ void do_rt_sigreturn(struct pt_regs *regs) if (err) goto segv; + err |= __get_user(rwin_save, &sf->rwin_save); + if (!err && rwin_save) { + if (restore_rwin_state(rwin_save)) + goto segv; + } + regs->tpc = tpc; regs->tnpc = tnpc; @@ -351,34 +337,13 @@ segv: } /* Checks if the fp is valid */ -static int invalid_frame_pointer(void __user *fp, int fplen) +static int invalid_frame_pointer(void __user *fp) { if (((unsigned long) fp) & 15) return 1; return 0; } -static inline int -save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) -{ - unsigned long *fpregs = current_thread_info()->fpregs; - unsigned long fprs; - int err = 0; - - fprs = current_thread_info()->fpsaved[0]; - if (fprs & FPRS_DL) - err |= copy_to_user(&fpu->si_float_regs[0], fpregs, - (sizeof(unsigned int) * 32)); - if (fprs & FPRS_DU) - err |= copy_to_user(&fpu->si_float_regs[32], fpregs+16, - (sizeof(unsigned int) * 32)); - err |= __put_user(current_thread_info()->xfsr[0], &fpu->si_fsr); - err |= __put_user(current_thread_info()->gsr[0], &fpu->si_gsr); - err |= __put_user(fprs, &fpu->si_fprs); - - return err; -} - static inline void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, unsigned long framesize) { unsigned long sp = regs->u_regs[UREG_FP] + STACK_BIAS; @@ -414,34 +379,48 @@ setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, int signo, sigset_t *oldset, siginfo_t *info) { struct rt_signal_frame __user *sf; - int sigframe_size, err; + int wsaved, err, sf_size; + void __user *tail; /* 1. Make sure everything is clean */ synchronize_user_stack(); save_and_clear_fpu(); - sigframe_size = sizeof(struct rt_signal_frame); - if (!(current_thread_info()->fpsaved[0] & FPRS_FEF)) - sigframe_size -= sizeof(__siginfo_fpu_t); + wsaved = get_thread_wsaved(); + sf_size = sizeof(struct rt_signal_frame); + if (current_thread_info()->fpsaved[0] & FPRS_FEF) + sf_size += sizeof(__siginfo_fpu_t); + if (wsaved) + sf_size += sizeof(__siginfo_rwin_t); sf = (struct rt_signal_frame __user *) - get_sigframe(ka, regs, sigframe_size); - - if (invalid_frame_pointer (sf, sigframe_size)) - goto sigill; + get_sigframe(ka, regs, sf_size); - if (get_thread_wsaved() != 0) + if (invalid_frame_pointer (sf)) goto sigill; + tail = (sf + 1); + /* 2. Save the current process state */ err = copy_to_user(&sf->regs, regs, sizeof (*regs)); if (current_thread_info()->fpsaved[0] & FPRS_FEF) { - err |= save_fpu_state(regs, &sf->fpu_state); - err |= __put_user((u64)&sf->fpu_state, &sf->fpu_save); + __siginfo_fpu_t __user *fpu_save = tail; + tail += sizeof(__siginfo_fpu_t); + err |= save_fpu_state(regs, fpu_save); + err |= __put_user((u64)fpu_save, &sf->fpu_save); } else { err |= __put_user(0, &sf->fpu_save); } + if (wsaved) { + __siginfo_rwin_t __user *rwin_save = tail; + tail += sizeof(__siginfo_rwin_t); + err |= save_rwin_state(wsaved, rwin_save); + err |= __put_user((u64)rwin_save, &sf->rwin_save); + set_thread_wsaved(0); + } else { + err |= __put_user(0, &sf->rwin_save); + } /* Setup sigaltstack */ err |= __put_user(current->sas_ss_sp, &sf->stack.ss_sp); @@ -450,10 +429,17 @@ setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, err |= copy_to_user(&sf->mask, oldset, sizeof(sigset_t)); - err |= copy_in_user((u64 __user *)sf, - (u64 __user *)(regs->u_regs[UREG_FP]+STACK_BIAS), - sizeof(struct reg_window)); + if (!wsaved) { + err |= copy_in_user((u64 __user *)sf, + (u64 __user *)(regs->u_regs[UREG_FP] + + STACK_BIAS), + sizeof(struct reg_window)); + } else { + struct reg_window *rp; + rp = ¤t_thread_info()->reg_window[wsaved - 1]; + err |= copy_to_user(sf, rp, sizeof(struct reg_window)); + } if (info) err |= copy_siginfo_to_user(&sf->info, info); else { diff --git a/arch/sparc/kernel/sigutil.h b/arch/sparc/kernel/sigutil.h new file mode 100644 index 000000000000..d223aa432bb6 --- /dev/null +++ b/arch/sparc/kernel/sigutil.h @@ -0,0 +1,9 @@ +#ifndef _SIGUTIL_H +#define _SIGUTIL_H + +int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu); +int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu); +int save_rwin_state(int wsaved, __siginfo_rwin_t __user *rwin); +int restore_rwin_state(__siginfo_rwin_t __user *rp); + +#endif /* _SIGUTIL_H */ diff --git a/arch/sparc/kernel/sigutil_32.c b/arch/sparc/kernel/sigutil_32.c new file mode 100644 index 000000000000..35c7897b009a --- /dev/null +++ b/arch/sparc/kernel/sigutil_32.c @@ -0,0 +1,120 @@ +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/thread_info.h> +#include <linux/uaccess.h> +#include <linux/sched.h> + +#include <asm/sigcontext.h> +#include <asm/fpumacro.h> +#include <asm/ptrace.h> + +#include "sigutil.h" + +int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) +{ + int err = 0; +#ifdef CONFIG_SMP + if (test_tsk_thread_flag(current, TIF_USEDFPU)) { + put_psr(get_psr() | PSR_EF); + fpsave(¤t->thread.float_regs[0], ¤t->thread.fsr, + ¤t->thread.fpqueue[0], ¤t->thread.fpqdepth); + regs->psr &= ~(PSR_EF); + clear_tsk_thread_flag(current, TIF_USEDFPU); + } +#else + if (current == last_task_used_math) { + put_psr(get_psr() | PSR_EF); + fpsave(¤t->thread.float_regs[0], ¤t->thread.fsr, + ¤t->thread.fpqueue[0], ¤t->thread.fpqdepth); + last_task_used_math = NULL; + regs->psr &= ~(PSR_EF); + } +#endif + err |= __copy_to_user(&fpu->si_float_regs[0], + ¤t->thread.float_regs[0], + (sizeof(unsigned long) * 32)); + err |= __put_user(current->thread.fsr, &fpu->si_fsr); + err |= __put_user(current->thread.fpqdepth, &fpu->si_fpqdepth); + if (current->thread.fpqdepth != 0) + err |= __copy_to_user(&fpu->si_fpqueue[0], + ¤t->thread.fpqueue[0], + ((sizeof(unsigned long) + + (sizeof(unsigned long *)))*16)); + clear_used_math(); + return err; +} + +int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) +{ + int err; +#ifdef CONFIG_SMP + if (test_tsk_thread_flag(current, TIF_USEDFPU)) + regs->psr &= ~PSR_EF; +#else + if (current == last_task_used_math) { + last_task_used_math = NULL; + regs->psr &= ~PSR_EF; + } +#endif + set_used_math(); + clear_tsk_thread_flag(current, TIF_USEDFPU); + + if (!access_ok(VERIFY_READ, fpu, sizeof(*fpu))) + return -EFAULT; + + err = __copy_from_user(¤t->thread.float_regs[0], &fpu->si_float_regs[0], + (sizeof(unsigned long) * 32)); + err |= __get_user(current->thread.fsr, &fpu->si_fsr); + err |= __get_user(current->thread.fpqdepth, &fpu->si_fpqdepth); + if (current->thread.fpqdepth != 0) + err |= __copy_from_user(¤t->thread.fpqueue[0], + &fpu->si_fpqueue[0], + ((sizeof(unsigned long) + + (sizeof(unsigned long *)))*16)); + return err; +} + +int save_rwin_state(int wsaved, __siginfo_rwin_t __user *rwin) +{ + int i, err = __put_user(wsaved, &rwin->wsaved); + + for (i = 0; i < wsaved; i++) { + struct reg_window32 *rp; + unsigned long fp; + + rp = ¤t_thread_info()->reg_window[i]; + fp = current_thread_info()->rwbuf_stkptrs[i]; + err |= copy_to_user(&rwin->reg_window[i], rp, + sizeof(struct reg_window32)); + err |= __put_user(fp, &rwin->rwbuf_stkptrs[i]); + } + return err; +} + +int restore_rwin_state(__siginfo_rwin_t __user *rp) +{ + struct thread_info *t = current_thread_info(); + int i, wsaved, err; + + __get_user(wsaved, &rp->wsaved); + if (wsaved > NSWINS) + return -EFAULT; + + err = 0; + for (i = 0; i < wsaved; i++) { + err |= copy_from_user(&t->reg_window[i], + &rp->reg_window[i], + sizeof(struct reg_window32)); + err |= __get_user(t->rwbuf_stkptrs[i], + &rp->rwbuf_stkptrs[i]); + } + if (err) + return err; + + t->w_saved = wsaved; + synchronize_user_stack(); + if (t->w_saved) + return -EFAULT; + return 0; + +} diff --git a/arch/sparc/kernel/sigutil_64.c b/arch/sparc/kernel/sigutil_64.c new file mode 100644 index 000000000000..e7dc508c38eb --- /dev/null +++ b/arch/sparc/kernel/sigutil_64.c @@ -0,0 +1,93 @@ +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/thread_info.h> +#include <linux/uaccess.h> + +#include <asm/sigcontext.h> +#include <asm/fpumacro.h> +#include <asm/ptrace.h> + +#include "sigutil.h" + +int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) +{ + unsigned long *fpregs = current_thread_info()->fpregs; + unsigned long fprs; + int err = 0; + + fprs = current_thread_info()->fpsaved[0]; + if (fprs & FPRS_DL) + err |= copy_to_user(&fpu->si_float_regs[0], fpregs, + (sizeof(unsigned int) * 32)); + if (fprs & FPRS_DU) + err |= copy_to_user(&fpu->si_float_regs[32], fpregs+16, + (sizeof(unsigned int) * 32)); + err |= __put_user(current_thread_info()->xfsr[0], &fpu->si_fsr); + err |= __put_user(current_thread_info()->gsr[0], &fpu->si_gsr); + err |= __put_user(fprs, &fpu->si_fprs); + + return err; +} + +int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) +{ + unsigned long *fpregs = current_thread_info()->fpregs; + unsigned long fprs; + int err; + + err = __get_user(fprs, &fpu->si_fprs); + fprs_write(0); + regs->tstate &= ~TSTATE_PEF; + if (fprs & FPRS_DL) + err |= copy_from_user(fpregs, &fpu->si_float_regs[0], + (sizeof(unsigned int) * 32)); + if (fprs & FPRS_DU) + err |= copy_from_user(fpregs+16, &fpu->si_float_regs[32], + (sizeof(unsigned int) * 32)); + err |= __get_user(current_thread_info()->xfsr[0], &fpu->si_fsr); + err |= __get_user(current_thread_info()->gsr[0], &fpu->si_gsr); + current_thread_info()->fpsaved[0] |= fprs; + return err; +} + +int save_rwin_state(int wsaved, __siginfo_rwin_t __user *rwin) +{ + int i, err = __put_user(wsaved, &rwin->wsaved); + + for (i = 0; i < wsaved; i++) { + struct reg_window *rp = ¤t_thread_info()->reg_window[i]; + unsigned long fp = current_thread_info()->rwbuf_stkptrs[i]; + + err |= copy_to_user(&rwin->reg_window[i], rp, + sizeof(struct reg_window)); + err |= __put_user(fp, &rwin->rwbuf_stkptrs[i]); + } + return err; +} + +int restore_rwin_state(__siginfo_rwin_t __user *rp) +{ + struct thread_info *t = current_thread_info(); + int i, wsaved, err; + + __get_user(wsaved, &rp->wsaved); + if (wsaved > NSWINS) + return -EFAULT; + + err = 0; + for (i = 0; i < wsaved; i++) { + err |= copy_from_user(&t->reg_window[i], + &rp->reg_window[i], + sizeof(struct reg_window)); + err |= __get_user(t->rwbuf_stkptrs[i], + &rp->rwbuf_stkptrs[i]); + } + if (err) + return err; + + set_thread_wsaved(wsaved); + synchronize_user_stack(); + if (get_thread_wsaved()) + return -EFAULT; + return 0; +} diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S index 44e5faf1ad5f..d97f3eb72e06 100644 --- a/arch/sparc/kernel/sys32.S +++ b/arch/sparc/kernel/sys32.S @@ -81,7 +81,6 @@ SIGN2(sys32_fadvise64, compat_sys_fadvise64, %o0, %o4) SIGN2(sys32_fadvise64_64, compat_sys_fadvise64_64, %o0, %o5) SIGN2(sys32_bdflush, sys_bdflush, %o0, %o1) SIGN1(sys32_mlockall, sys_mlockall, %o0) -SIGN1(sys32_nfsservctl, compat_sys_nfsservctl, %o0) SIGN1(sys32_clock_nanosleep, compat_sys_clock_nanosleep, %o1) SIGN1(sys32_timer_settime, compat_sys_timer_settime, %o1) SIGN1(sys32_io_submit, compat_sys_io_submit, %o1) diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S index 6e492d59f6b1..09d8ec454450 100644 --- a/arch/sparc/kernel/systbls_32.S +++ b/arch/sparc/kernel/systbls_32.S @@ -67,7 +67,7 @@ sys_call_table: /*235*/ .long sys_fstatfs64, sys_llseek, sys_mlock, sys_munlock, sys_mlockall /*240*/ .long sys_munlockall, sys_sched_setparam, sys_sched_getparam, sys_sched_setscheduler, sys_sched_getscheduler /*245*/ .long sys_sched_yield, sys_sched_get_priority_max, sys_sched_get_priority_min, sys_sched_rr_get_interval, sys_nanosleep -/*250*/ .long sys_mremap, sys_sysctl, sys_getsid, sys_fdatasync, sys_nfsservctl +/*250*/ .long sys_mremap, sys_sysctl, sys_getsid, sys_fdatasync, sys_ni_syscall /*255*/ .long sys_sync_file_range, sys_clock_settime, sys_clock_gettime, sys_clock_getres, sys_clock_nanosleep /*260*/ .long sys_sched_getaffinity, sys_sched_setaffinity, sys_timer_settime, sys_timer_gettime, sys_timer_getoverrun /*265*/ .long sys_timer_delete, sys_timer_create, sys_nis_syscall, sys_io_setup, sys_io_destroy diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index f566518483b5..edbec45d4688 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -68,7 +68,7 @@ sys_call_table32: .word compat_sys_fstatfs64, sys_llseek, sys_mlock, sys_munlock, sys32_mlockall /*240*/ .word sys_munlockall, sys32_sched_setparam, sys32_sched_getparam, sys32_sched_setscheduler, sys32_sched_getscheduler .word sys_sched_yield, sys32_sched_get_priority_max, sys32_sched_get_priority_min, sys32_sched_rr_get_interval, compat_sys_nanosleep -/*250*/ .word sys_mremap, compat_sys_sysctl, sys32_getsid, sys_fdatasync, sys32_nfsservctl +/*250*/ .word sys_mremap, compat_sys_sysctl, sys32_getsid, sys_fdatasync, sys_nis_syscall .word sys32_sync_file_range, compat_sys_clock_settime, compat_sys_clock_gettime, compat_sys_clock_getres, sys32_clock_nanosleep /*260*/ .word compat_sys_sched_getaffinity, compat_sys_sched_setaffinity, sys32_timer_settime, compat_sys_timer_gettime, sys_timer_getoverrun .word sys_timer_delete, compat_sys_timer_create, sys_ni_syscall, compat_sys_io_setup, sys_io_destroy @@ -145,7 +145,7 @@ sys_call_table: .word sys_fstatfs64, sys_llseek, sys_mlock, sys_munlock, sys_mlockall /*240*/ .word sys_munlockall, sys_sched_setparam, sys_sched_getparam, sys_sched_setscheduler, sys_sched_getscheduler .word sys_sched_yield, sys_sched_get_priority_max, sys_sched_get_priority_min, sys_sched_rr_get_interval, sys_nanosleep -/*250*/ .word sys_64_mremap, sys_sysctl, sys_getsid, sys_fdatasync, sys_nfsservctl +/*250*/ .word sys_64_mremap, sys_sysctl, sys_getsid, sys_fdatasync, sys_nis_syscall .word sys_sync_file_range, sys_clock_settime, sys_clock_gettime, sys_clock_getres, sys_clock_nanosleep /*260*/ .word sys_sched_getaffinity, sys_sched_setaffinity, sys_timer_settime, sys_timer_gettime, sys_timer_getoverrun .word sys_timer_delete, sys_timer_create, sys_ni_syscall, sys_io_setup, sys_io_destroy diff --git a/arch/um/Kconfig.x86 b/arch/um/Kconfig.x86 index d31ecf346b4e..21bebe63df66 100644 --- a/arch/um/Kconfig.x86 +++ b/arch/um/Kconfig.x86 @@ -10,6 +10,10 @@ config CMPXCHG_LOCAL bool default n +config CMPXCHG_DOUBLE + bool + default n + source "arch/x86/Kconfig.cpu" endmenu diff --git a/arch/um/Makefile b/arch/um/Makefile index fab8121d2b32..c0f712cc7c5f 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -41,7 +41,7 @@ KBUILD_CPPFLAGS += -I$(srctree)/$(ARCH_DIR)/sys-$(SUBARCH) KBUILD_CFLAGS += $(CFLAGS) $(CFLAGS-y) -D__arch_um__ -DSUBARCH=\"$(SUBARCH)\" \ $(ARCH_INCLUDE) $(MODE_INCLUDE) -Dvmap=kernel_vmap \ -Din6addr_loopback=kernel_in6addr_loopback \ - -Din6addr_any=kernel_in6addr_any + -Din6addr_any=kernel_in6addr_any -Dstrrchr=kernel_strrchr KBUILD_AFLAGS += $(ARCH_INCLUDE) diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index d51c404239a8..364c8a15c4c3 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -399,8 +399,8 @@ int line_setup_irq(int fd, int input, int output, struct line *line, void *data) * is done under a spinlock. Checking whether the device is in use is * line->tty->count > 1, also under the spinlock. * - * tty->count serves to decide whether the device should be enabled or - * disabled on the host. If it's equal to 1, then we are doing the + * line->count serves to decide whether the device should be enabled or + * disabled on the host. If it's equal to 0, then we are doing the * first open or last close. Otherwise, open and close just return. */ @@ -414,16 +414,16 @@ int line_open(struct line *lines, struct tty_struct *tty) goto out_unlock; err = 0; - if (tty->count > 1) + if (line->count++) goto out_unlock; - spin_unlock(&line->count_lock); - + BUG_ON(tty->driver_data); tty->driver_data = line; line->tty = tty; + spin_unlock(&line->count_lock); err = enable_chan(line); - if (err) + if (err) /* line_close() will be called by our caller */ return err; INIT_DELAYED_WORK(&line->task, line_timer_cb); @@ -436,7 +436,7 @@ int line_open(struct line *lines, struct tty_struct *tty) chan_window_size(&line->chan_list, &tty->winsize.ws_row, &tty->winsize.ws_col); - return err; + return 0; out_unlock: spin_unlock(&line->count_lock); @@ -460,17 +460,16 @@ void line_close(struct tty_struct *tty, struct file * filp) flush_buffer(line); spin_lock(&line->count_lock); - if (!line->valid) - goto out_unlock; + BUG_ON(!line->valid); - if (tty->count > 1) + if (--line->count) goto out_unlock; - spin_unlock(&line->count_lock); - line->tty = NULL; tty->driver_data = NULL; + spin_unlock(&line->count_lock); + if (line->sigio) { unregister_winch(tty); line->sigio = 0; @@ -498,7 +497,7 @@ static int setup_one_line(struct line *lines, int n, char *init, int init_prio, spin_lock(&line->count_lock); - if (line->tty != NULL) { + if (line->count) { *error_out = "Device is already open"; goto out; } @@ -722,41 +721,53 @@ struct winch { int pid; struct tty_struct *tty; unsigned long stack; + struct work_struct work; }; -static void free_winch(struct winch *winch, int free_irq_ok) +static void __free_winch(struct work_struct *work) { - if (free_irq_ok) - free_irq(WINCH_IRQ, winch); - - list_del(&winch->list); + struct winch *winch = container_of(work, struct winch, work); + free_irq(WINCH_IRQ, winch); if (winch->pid != -1) os_kill_process(winch->pid, 1); - if (winch->fd != -1) - os_close_file(winch->fd); if (winch->stack != 0) free_stack(winch->stack, 0); kfree(winch); } +static void free_winch(struct winch *winch) +{ + int fd = winch->fd; + winch->fd = -1; + if (fd != -1) + os_close_file(fd); + list_del(&winch->list); + __free_winch(&winch->work); +} + static irqreturn_t winch_interrupt(int irq, void *data) { struct winch *winch = data; struct tty_struct *tty; struct line *line; + int fd = winch->fd; int err; char c; - if (winch->fd != -1) { - err = generic_read(winch->fd, &c, NULL); + if (fd != -1) { + err = generic_read(fd, &c, NULL); if (err < 0) { if (err != -EAGAIN) { + winch->fd = -1; + list_del(&winch->list); + os_close_file(fd); printk(KERN_ERR "winch_interrupt : " "read failed, errno = %d\n", -err); printk(KERN_ERR "fd %d is losing SIGWINCH " "support\n", winch->tty_fd); - free_winch(winch, 0); + INIT_WORK(&winch->work, __free_winch); + schedule_work(&winch->work); return IRQ_HANDLED; } goto out; @@ -828,7 +839,7 @@ static void unregister_winch(struct tty_struct *tty) list_for_each_safe(ele, next, &winch_handlers) { winch = list_entry(ele, struct winch, list); if (winch->tty == tty) { - free_winch(winch, 1); + free_winch(winch); break; } } @@ -844,7 +855,7 @@ static void winch_cleanup(void) list_for_each_safe(ele, next, &winch_handlers) { winch = list_entry(ele, struct winch, list); - free_winch(winch, 1); + free_winch(winch); } spin_unlock(&winch_handler_lock); diff --git a/arch/um/drivers/xterm.c b/arch/um/drivers/xterm.c index 8ac7146c237f..2e1de5728604 100644 --- a/arch/um/drivers/xterm.c +++ b/arch/um/drivers/xterm.c @@ -123,6 +123,7 @@ static int xterm_open(int input, int output, int primary, void *d, err = -errno; printk(UM_KERN_ERR "xterm_open : unlink failed, errno = %d\n", errno); + close(fd); return err; } close(fd); diff --git a/arch/um/include/asm/ptrace-generic.h b/arch/um/include/asm/ptrace-generic.h index ae084ad1a3a0..1a7d2757fe05 100644 --- a/arch/um/include/asm/ptrace-generic.h +++ b/arch/um/include/asm/ptrace-generic.h @@ -42,10 +42,6 @@ extern long subarch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data); extern unsigned long getreg(struct task_struct *child, int regno); extern int putreg(struct task_struct *child, int regno, unsigned long value); -extern int get_fpregs(struct user_i387_struct __user *buf, - struct task_struct *child); -extern int set_fpregs(struct user_i387_struct __user *buf, - struct task_struct *child); extern int arch_copy_tls(struct task_struct *new); extern void clear_flushed_tls(struct task_struct *task); diff --git a/arch/um/include/shared/line.h b/arch/um/include/shared/line.h index 72f4f25af247..63df3ca02ac2 100644 --- a/arch/um/include/shared/line.h +++ b/arch/um/include/shared/line.h @@ -33,6 +33,7 @@ struct line_driver { struct line { struct tty_struct *tty; spinlock_t count_lock; + unsigned long count; int valid; char *init_str; diff --git a/arch/um/include/shared/registers.h b/arch/um/include/shared/registers.h index b0b4589e0ebc..f1e0aa56c52a 100644 --- a/arch/um/include/shared/registers.h +++ b/arch/um/include/shared/registers.h @@ -16,7 +16,7 @@ extern int restore_fpx_registers(int pid, unsigned long *fp_regs); extern int save_registers(int pid, struct uml_pt_regs *regs); extern int restore_registers(int pid, struct uml_pt_regs *regs); extern int init_registers(int pid); -extern void get_safe_registers(unsigned long *regs); +extern void get_safe_registers(unsigned long *regs, unsigned long *fp_regs); extern unsigned long get_thread_reg(int reg, jmp_buf *buf); extern int get_fp_registers(int pid, unsigned long *regs); extern int put_fp_registers(int pid, unsigned long *regs); diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index fab4371184f6..21c1ae7c3d75 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -202,7 +202,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, arch_copy_thread(¤t->thread.arch, &p->thread.arch); } else { - get_safe_registers(p->thread.regs.regs.gp); + get_safe_registers(p->thread.regs.regs.gp, p->thread.regs.regs.fp); p->thread.request.u.thread = current->thread.request.u.thread; handler = new_thread_handler; } diff --git a/arch/um/kernel/ptrace.c b/arch/um/kernel/ptrace.c index 701b672c1122..c9da32b0c707 100644 --- a/arch/um/kernel/ptrace.c +++ b/arch/um/kernel/ptrace.c @@ -50,23 +50,11 @@ long arch_ptrace(struct task_struct *child, long request, void __user *vp = p; switch (request) { - /* read word at location addr. */ - case PTRACE_PEEKTEXT: - case PTRACE_PEEKDATA: - ret = generic_ptrace_peekdata(child, addr, data); - break; - /* read the word at location addr in the USER area. */ case PTRACE_PEEKUSR: ret = peek_user(child, addr, data); break; - /* write the word at location addr. */ - case PTRACE_POKETEXT: - case PTRACE_POKEDATA: - ret = generic_ptrace_pokedata(child, addr, data); - break; - /* write the word at location addr in the USER area */ case PTRACE_POKEUSR: ret = poke_user(child, addr, data); @@ -107,16 +95,6 @@ long arch_ptrace(struct task_struct *child, long request, break; } #endif -#ifdef PTRACE_GETFPREGS - case PTRACE_GETFPREGS: /* Get the child FPU state. */ - ret = get_fpregs(vp, child); - break; -#endif -#ifdef PTRACE_SETFPREGS - case PTRACE_SETFPREGS: /* Set the child FPU state. */ - ret = set_fpregs(vp, child); - break; -#endif case PTRACE_GET_THREAD_AREA: ret = ptrace_get_thread_area(child, addr, vp); break; @@ -154,12 +132,6 @@ long arch_ptrace(struct task_struct *child, long request, break; } #endif -#ifdef PTRACE_ARCH_PRCTL - case PTRACE_ARCH_PRCTL: - /* XXX Calls ptrace on the host - needs some SMP thinking */ - ret = arch_prctl(child, data, (void __user *) addr); - break; -#endif default: ret = ptrace_request(child, request, addr, data); if (ret == -EIO) diff --git a/arch/um/os-Linux/registers.c b/arch/um/os-Linux/registers.c index 830fe6a1518a..b866b9e3bef9 100644 --- a/arch/um/os-Linux/registers.c +++ b/arch/um/os-Linux/registers.c @@ -8,6 +8,8 @@ #include <string.h> #include <sys/ptrace.h> #include "sysdep/ptrace.h" +#include "sysdep/ptrace_user.h" +#include "registers.h" int save_registers(int pid, struct uml_pt_regs *regs) { @@ -32,6 +34,7 @@ int restore_registers(int pid, struct uml_pt_regs *regs) /* This is set once at boot time and not changed thereafter */ static unsigned long exec_regs[MAX_REG_NR]; +static unsigned long exec_fp_regs[FP_SIZE]; int init_registers(int pid) { @@ -42,10 +45,14 @@ int init_registers(int pid) return -errno; arch_init_registers(pid); + get_fp_registers(pid, exec_fp_regs); return 0; } -void get_safe_registers(unsigned long *regs) +void get_safe_registers(unsigned long *regs, unsigned long *fp_regs) { memcpy(regs, exec_regs, sizeof(exec_regs)); + + if (fp_regs) + memcpy(fp_regs, exec_fp_regs, sizeof(exec_fp_regs)); } diff --git a/arch/um/os-Linux/skas/mem.c b/arch/um/os-Linux/skas/mem.c index d261f170d120..e771398be5f3 100644 --- a/arch/um/os-Linux/skas/mem.c +++ b/arch/um/os-Linux/skas/mem.c @@ -39,7 +39,7 @@ static unsigned long syscall_regs[MAX_REG_NR]; static int __init init_syscall_regs(void) { - get_safe_registers(syscall_regs); + get_safe_registers(syscall_regs, NULL); syscall_regs[REGS_IP_INDEX] = STUB_CODE + ((unsigned long) &batch_syscall_stub - (unsigned long) &__syscall_stub_start); diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index d6e0a2234b86..dee0e8cf8ad0 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -373,6 +373,9 @@ void userspace(struct uml_pt_regs *regs) if (ptrace(PTRACE_SETREGS, pid, 0, regs->gp)) fatal_sigsegv(); + if (put_fp_registers(pid, regs->fp)) + fatal_sigsegv(); + /* Now we set local_using_sysemu to be used for one loop */ local_using_sysemu = get_using_sysemu(); @@ -399,6 +402,12 @@ void userspace(struct uml_pt_regs *regs) fatal_sigsegv(); } + if (get_fp_registers(pid, regs->fp)) { + printk(UM_KERN_ERR "userspace - get_fp_registers failed, " + "errno = %d\n", errno); + fatal_sigsegv(); + } + UPT_SYSCALL_NR(regs) = -1; /* Assume: It's not a syscall */ if (WIFSTOPPED(status)) { @@ -457,10 +466,11 @@ void userspace(struct uml_pt_regs *regs) } static unsigned long thread_regs[MAX_REG_NR]; +static unsigned long thread_fp_regs[FP_SIZE]; static int __init init_thread_regs(void) { - get_safe_registers(thread_regs); + get_safe_registers(thread_regs, thread_fp_regs); /* Set parent's instruction pointer to start of clone-stub */ thread_regs[REGS_IP_INDEX] = STUB_CODE + (unsigned long) stub_clone_handler - @@ -503,6 +513,13 @@ int copy_context_skas0(unsigned long new_stack, int pid) return err; } + err = put_fp_registers(pid, thread_fp_regs); + if (err < 0) { + printk(UM_KERN_ERR "copy_context_skas0 : put_fp_registers " + "failed, pid = %d, err = %d\n", pid, err); + return err; + } + /* set a well known return code for detection of child write failure */ child_data->err = 12345678; diff --git a/arch/um/sys-i386/asm/ptrace.h b/arch/um/sys-i386/asm/ptrace.h index 0273e4d09af7..5d2a59112537 100644 --- a/arch/um/sys-i386/asm/ptrace.h +++ b/arch/um/sys-i386/asm/ptrace.h @@ -42,11 +42,6 @@ */ struct user_desc; -extern int get_fpxregs(struct user_fxsr_struct __user *buf, - struct task_struct *child); -extern int set_fpxregs(struct user_fxsr_struct __user *buf, - struct task_struct *tsk); - extern int ptrace_get_thread_area(struct task_struct *child, int idx, struct user_desc __user *user_desc); diff --git a/arch/um/sys-i386/ptrace.c b/arch/um/sys-i386/ptrace.c index d23b2d3ea384..3375c2717851 100644 --- a/arch/um/sys-i386/ptrace.c +++ b/arch/um/sys-i386/ptrace.c @@ -145,7 +145,7 @@ int peek_user(struct task_struct *child, long addr, long data) return put_user(tmp, (unsigned long __user *) data); } -int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) +static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { int err, n, cpu = ((struct thread_info *) child->stack)->cpu; struct user_i387_struct fpregs; @@ -161,7 +161,7 @@ int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) return n; } -int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) +static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { int n, cpu = ((struct thread_info *) child->stack)->cpu; struct user_i387_struct fpregs; @@ -174,7 +174,7 @@ int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) (unsigned long *) &fpregs); } -int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) +static int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) { int err, n, cpu = ((struct thread_info *) child->stack)->cpu; struct user_fxsr_struct fpregs; @@ -190,7 +190,7 @@ int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) return n; } -int set_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) +static int set_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) { int n, cpu = ((struct thread_info *) child->stack)->cpu; struct user_fxsr_struct fpregs; @@ -206,5 +206,23 @@ int set_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) long subarch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data) { - return -EIO; + int ret = -EIO; + void __user *datap = (void __user *) data; + switch (request) { + case PTRACE_GETFPREGS: /* Get the child FPU state. */ + ret = get_fpregs(datap, child); + break; + case PTRACE_SETFPREGS: /* Set the child FPU state. */ + ret = set_fpregs(datap, child); + break; + case PTRACE_GETFPXREGS: /* Get the child FPU state. */ + ret = get_fpxregs(datap, child); + break; + case PTRACE_SETFPXREGS: /* Set the child FPU state. */ + ret = set_fpxregs(datap, child); + break; + default: + ret = -EIO; + } + return ret; } diff --git a/arch/um/sys-i386/shared/sysdep/ptrace.h b/arch/um/sys-i386/shared/sysdep/ptrace.h index d50e62e07070..c398a5076111 100644 --- a/arch/um/sys-i386/shared/sysdep/ptrace.h +++ b/arch/um/sys-i386/shared/sysdep/ptrace.h @@ -53,6 +53,7 @@ extern int sysemu_supported; struct uml_pt_regs { unsigned long gp[MAX_REG_NR]; + unsigned long fp[HOST_FPX_SIZE]; struct faultinfo faultinfo; long syscall; int is_user; diff --git a/arch/um/sys-x86_64/ptrace.c b/arch/um/sys-x86_64/ptrace.c index f43613643cdb..4005506834fd 100644 --- a/arch/um/sys-x86_64/ptrace.c +++ b/arch/um/sys-x86_64/ptrace.c @@ -145,7 +145,7 @@ int is_syscall(unsigned long addr) return instr == 0x050f; } -int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) +static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { int err, n, cpu = ((struct thread_info *) child->stack)->cpu; long fpregs[HOST_FP_SIZE]; @@ -162,7 +162,7 @@ int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) return n; } -int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) +static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { int n, cpu = ((struct thread_info *) child->stack)->cpu; long fpregs[HOST_FP_SIZE]; @@ -182,12 +182,16 @@ long subarch_ptrace(struct task_struct *child, long request, void __user *datap = (void __user *) data; switch (request) { - case PTRACE_GETFPXREGS: /* Get the child FPU state. */ + case PTRACE_GETFPREGS: /* Get the child FPU state. */ ret = get_fpregs(datap, child); break; - case PTRACE_SETFPXREGS: /* Set the child FPU state. */ + case PTRACE_SETFPREGS: /* Set the child FPU state. */ ret = set_fpregs(datap, child); break; + case PTRACE_ARCH_PRCTL: + /* XXX Calls ptrace on the host - needs some SMP thinking */ + ret = arch_prctl(child, data, (void __user *) addr); + break; } return ret; diff --git a/arch/um/sys-x86_64/shared/sysdep/ptrace.h b/arch/um/sys-x86_64/shared/sysdep/ptrace.h index fdba5457947a..8ee8f8e12af1 100644 --- a/arch/um/sys-x86_64/shared/sysdep/ptrace.h +++ b/arch/um/sys-x86_64/shared/sysdep/ptrace.h @@ -85,6 +85,7 @@ struct uml_pt_regs { unsigned long gp[MAX_REG_NR]; + unsigned long fp[HOST_FP_SIZE]; struct faultinfo faultinfo; long syscall; int is_user; diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index a0e866d233ee..54edb207ff3a 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -672,7 +672,7 @@ ia32_sys_call_table: .quad sys32_vm86_warning /* vm86 */ .quad quiet_ni_syscall /* query_module */ .quad sys_poll - .quad compat_sys_nfsservctl + .quad quiet_ni_syscall /* old nfsservctl */ .quad sys_setresgid16 /* 170 */ .quad sys_getresgid16 .quad sys_prctl diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h index 4554cc6fb96a..091508b533b4 100644 --- a/arch/x86/include/asm/alternative-asm.h +++ b/arch/x86/include/asm/alternative-asm.h @@ -16,7 +16,6 @@ #endif .macro altinstruction_entry orig alt feature orig_len alt_len - .align 8 .long \orig - . .long \alt - . .word \feature diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 23fb6d79f209..37ad100a2210 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -48,9 +48,6 @@ struct alt_instr { u16 cpuid; /* cpuid bit set for replacement */ u8 instrlen; /* length of original instruction */ u8 replacementlen; /* length of new instruction, <= instrlen */ -#ifdef CONFIG_X86_64 - u32 pad2; -#endif }; extern void alternative_instructions(void); @@ -83,7 +80,6 @@ static inline int alternatives_text_reserved(void *start, void *end) \ "661:\n\t" oldinstr "\n662:\n" \ ".section .altinstructions,\"a\"\n" \ - _ASM_ALIGN "\n" \ " .long 661b - .\n" /* label */ \ " .long 663f - .\n" /* new instruction */ \ " .word " __stringify(feature) "\n" /* feature bit */ \ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 4258aac99a6e..88b23a43f340 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -332,7 +332,6 @@ static __always_inline __pure bool __static_cpu_has(u16 bit) asm goto("1: jmp %l[t_no]\n" "2:\n" ".section .altinstructions,\"a\"\n" - _ASM_ALIGN "\n" " .long 1b - .\n" " .long 0\n" /* no replacement */ " .word %P0\n" /* feature bit */ @@ -350,7 +349,6 @@ static __always_inline __pure bool __static_cpu_has(u16 bit) asm volatile("1: movb $0,%0\n" "2:\n" ".section .altinstructions,\"a\"\n" - _ASM_ALIGN "\n" " .long 1b - .\n" " .long 3f - .\n" " .word %P1\n" /* feature bit */ diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index a518c0a45044..c59cc97fe6c1 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -44,7 +44,7 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) : "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) ); #elif defined(__x86_64__) __asm__ ( - "mul %[mul_frac] ; shrd $32, %[hi], %[lo]" + "mulq %[mul_frac] ; shrd $32, %[hi], %[lo]" : [lo]"=a"(product), [hi]"=d"(tmp) : "0"(delta), diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index d92641cc7acc..201040573444 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -414,7 +414,7 @@ __SYSCALL(__NR_query_module, sys_ni_syscall) __SYSCALL(__NR_quotactl, sys_quotactl) #define __NR_nfsservctl 180 -__SYSCALL(__NR_nfsservctl, sys_nfsservctl) +__SYSCALL(__NR_nfsservctl, sys_ni_syscall) /* reserved for LiS/STREAMS */ #define __NR_getpmsg 181 diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 64a619d47d34..7ff4669580cf 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -39,7 +39,7 @@ typedef struct xpaddr { ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE)) extern unsigned long *machine_to_phys_mapping; -extern unsigned int machine_to_phys_order; +extern unsigned long machine_to_phys_nr; extern unsigned long get_phys_to_machine(unsigned long pfn); extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn); @@ -87,7 +87,7 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn) if (xen_feature(XENFEAT_auto_translated_physmap)) return mfn; - if (unlikely((mfn >> machine_to_phys_order) != 0)) { + if (unlikely(mfn >= machine_to_phys_nr)) { pfn = ~0; goto try_override; } diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index adc66c3a1fef..34b18594e724 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -207,7 +207,6 @@ static int __cpuinit uv_wakeup_secondary(int phys_apicid, unsigned long start_ri ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | APIC_DM_INIT; uv_write_global_mmr64(pnode, UVH_IPI_INT, val); - mdelay(10); val = (1UL << UVH_IPI_INT_SEND_SHFT) | (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) | diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 08119a37e53c..6b96110bb0c3 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -149,7 +149,6 @@ struct set_mtrr_data { */ static int mtrr_rendezvous_handler(void *info) { -#ifdef CONFIG_SMP struct set_mtrr_data *data = info; /* @@ -171,7 +170,6 @@ static int mtrr_rendezvous_handler(void *info) } else if (mtrr_aps_delayed_init || !cpu_online(smp_processor_id())) { mtrr_if->set_all(); } -#endif return 0; } diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 4ee3abf20ed6..cfa62ec090ec 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1900,6 +1900,9 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) perf_callchain_store(entry, regs->ip); + if (!current->mm) + return; + if (perf_callchain_user32(regs, entry)) return; diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 5c1a91974918..f3f6f5344001 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -54,6 +54,7 @@ #include <asm/ftrace.h> #include <asm/irq_vectors.h> #include <asm/cpufeature.h> +#include <asm/alternative-asm.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ #include <linux/elf-em.h> @@ -873,12 +874,7 @@ ENTRY(simd_coprocessor_error) 661: pushl_cfi $do_general_protection 662: .section .altinstructions,"a" - .balign 4 - .long 661b - .long 663f - .word X86_FEATURE_XMM - .byte 662b-661b - .byte 664f-663f + altinstruction_entry 661b, 663f, X86_FEATURE_XMM, 662b-661b, 664f-663f .previous .section .altinstr_replacement,"ax" 663: pushl $do_simd_coprocessor_error diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index fbb0a045a1a2..bc19be332bc9 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -168,7 +168,7 @@ ENTRY(sys_call_table) .long ptregs_vm86 .long sys_ni_syscall /* Old sys_query_module */ .long sys_poll - .long sys_nfsservctl + .long sys_ni_syscall /* Old nfsservctl */ .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 988724b236b6..ff5790d8e990 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -22,6 +22,8 @@ config KVM depends on HAVE_KVM # for device assignment: depends on PCI + # for TASKSTATS/TASK_DELAY_ACCT: + depends on NET select PREEMPT_NOTIFIERS select MMU_NOTIFIER select ANON_INODES @@ -31,6 +33,7 @@ config KVM select KVM_ASYNC_PF select USER_RETURN_NOTIFIER select KVM_MMIO + select TASKSTATS select TASK_DELAY_ACCT ---help--- Support hosting fully virtualized guest machines using hardware diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 247aae3dc008..0d17c8c50acd 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -17,6 +17,7 @@ #include <asm/traps.h> /* dotraplinkage, ... */ #include <asm/pgalloc.h> /* pgd_*(), ... */ #include <asm/kmemcheck.h> /* kmemcheck_*(), ... */ +#include <asm/vsyscall.h> /* * Page fault error code bits: diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index ae3cb23cd89b..039d91315bc5 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -360,6 +360,20 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root) } } + /* After the PCI-E bus has been walked and all devices discovered, + * configure any settings of the fabric that might be necessary. + */ + if (bus) { + struct pci_bus *child; + list_for_each_entry(child, &bus->children, node) { + struct pci_dev *self = child->self; + if (!self) + continue; + + pcie_bus_configure_settings(child, self->pcie_mpss); + } + } + if (!bus) kfree(sd); diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c index 7000e74b3087..58425adc22c6 100644 --- a/arch/x86/platform/mrst/mrst.c +++ b/arch/x86/platform/mrst/mrst.c @@ -689,7 +689,9 @@ static int __init sfi_parse_devs(struct sfi_table_header *table) irq_attr.trigger = 1; irq_attr.polarity = 1; io_apic_set_pci_routing(NULL, pentry->irq, &irq_attr); - } + } else + pentry->irq = 0; /* No irq */ + switch (pentry->type) { case SFI_DEV_TYPE_IPC: /* ID as IRQ is a hack that will go away */ diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c index 8b9940e78e2f..7cce722667b8 100644 --- a/arch/x86/platform/olpc/olpc.c +++ b/arch/x86/platform/olpc/olpc.c @@ -161,13 +161,13 @@ restart: if (inbuf && inlen) { /* write data to EC */ for (i = 0; i < inlen; i++) { + pr_devel("olpc-ec: sending cmd arg 0x%x\n", inbuf[i]); + outb(inbuf[i], 0x68); if (wait_on_ibf(0x6c, 0)) { printk(KERN_ERR "olpc-ec: timeout waiting for" " EC accept data!\n"); goto err; } - pr_devel("olpc-ec: sending cmd arg 0x%x\n", inbuf[i]); - outb(inbuf[i], 0x68); } } if (outbuf && outlen) { diff --git a/arch/x86/vdso/vdso32/sysenter.S b/arch/x86/vdso/vdso32/sysenter.S index e2800affa754..e354bceee0e0 100644 --- a/arch/x86/vdso/vdso32/sysenter.S +++ b/arch/x86/vdso/vdso32/sysenter.S @@ -43,7 +43,7 @@ __kernel_vsyscall: .space 7,0x90 /* 14: System call restart point is here! (SYSENTER_RETURN-2) */ - jmp .Lenter_kernel + int $0x80 /* 16: System call normal return point is here! */ VDSO32_SYSENTER_RETURN: /* Symbol used by sysenter.c via vdso32-syms.h */ pop %ebp diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 3326204e251f..add2c2d729ce 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -15,7 +15,7 @@ obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \ grant-table.o suspend.o platform-pci-unplug.o \ p2m.o -obj-$(CONFIG_FTRACE) += trace.o +obj-$(CONFIG_EVENT_TRACING) += trace.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index e2345af01af0..2d69617950f7 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -77,8 +77,8 @@ EXPORT_SYMBOL_GPL(xen_domain_type); unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START; EXPORT_SYMBOL(machine_to_phys_mapping); -unsigned int machine_to_phys_order; -EXPORT_SYMBOL(machine_to_phys_order); +unsigned long machine_to_phys_nr; +EXPORT_SYMBOL(machine_to_phys_nr); struct start_info *xen_start_info; EXPORT_SYMBOL_GPL(xen_start_info); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 8cce339db5e7..3dd53f997b11 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1713,15 +1713,17 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) void __init xen_setup_machphys_mapping(void) { struct xen_machphys_mapping mapping; - unsigned long machine_to_phys_nr_ents; if (HYPERVISOR_memory_op(XENMEM_machphys_mapping, &mapping) == 0) { machine_to_phys_mapping = (unsigned long *)mapping.v_start; - machine_to_phys_nr_ents = mapping.max_mfn + 1; + machine_to_phys_nr = mapping.max_mfn + 1; } else { - machine_to_phys_nr_ents = MACH2PHYS_NR_ENTRIES; + machine_to_phys_nr = MACH2PHYS_NR_ENTRIES; } - machine_to_phys_order = fls(machine_to_phys_nr_ents - 1); +#ifdef CONFIG_X86_32 + WARN_ON((machine_to_phys_mapping + (machine_to_phys_nr - 1)) + < machine_to_phys_mapping); +#endif } #ifdef CONFIG_X86_64 diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index df118a825f39..46d6d21dbdbe 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -184,6 +184,19 @@ static unsigned long __init xen_set_identity(const struct e820entry *list, PFN_UP(start_pci), PFN_DOWN(last)); return identity; } + +static unsigned long __init xen_get_max_pages(void) +{ + unsigned long max_pages = MAX_DOMAIN_PAGES; + domid_t domid = DOMID_SELF; + int ret; + + ret = HYPERVISOR_memory_op(XENMEM_maximum_reservation, &domid); + if (ret > 0) + max_pages = ret; + return min(max_pages, MAX_DOMAIN_PAGES); +} + /** * machine_specific_memory_setup - Hook for machine specific memory setup. **/ @@ -292,6 +305,14 @@ char * __init xen_memory_setup(void) sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + extra_limit = xen_get_max_pages(); + if (max_pfn + extra_pages > extra_limit) { + if (extra_limit > max_pfn) + extra_pages = extra_limit - max_pfn; + else + extra_pages = 0; + } + extra_pages += xen_return_unused_memory(xen_start_info->nr_pages, &e820); /* diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index b4533a86d7e4..041d4fe9dfe4 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -32,6 +32,7 @@ #include <xen/page.h> #include <xen/events.h> +#include <xen/hvc-console.h> #include "xen-ops.h" #include "mmu.h" @@ -207,6 +208,15 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus) unsigned cpu; unsigned int i; + if (skip_ioapic_setup) { + char *m = (max_cpus == 0) ? + "The nosmp parameter is incompatible with Xen; " \ + "use Xen dom0_max_vcpus=1 parameter" : + "The noapic parameter is incompatible with Xen"; + + xen_raw_printk(m); + panic(m); + } xen_init_lock_cpu(0); smp_store_cpu_info(0); @@ -521,10 +531,7 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) native_smp_prepare_cpus(max_cpus); WARN_ON(xen_smp_intr_init(0)); - if (!xen_have_vector_callback) - return; xen_init_lock_cpu(0); - xen_init_spinlocks(); } static int __cpuinit xen_hvm_cpu_up(unsigned int cpu) @@ -546,6 +553,8 @@ static void xen_hvm_cpu_die(unsigned int cpu) void __init xen_hvm_smp_init(void) { + if (!xen_have_vector_callback) + return; smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; smp_ops.smp_send_reschedule = xen_smp_send_reschedule; smp_ops.cpu_up = xen_hvm_cpu_up; diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 5158c505bef9..163b4679556e 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -168,9 +168,10 @@ cycle_t xen_clocksource_read(void) struct pvclock_vcpu_time_info *src; cycle_t ret; - src = &get_cpu_var(xen_vcpu)->time; + preempt_disable_notrace(); + src = &__get_cpu_var(xen_vcpu)->time; ret = pvclock_clocksource_read(src); - put_cpu_var(xen_vcpu); + preempt_enable_notrace(); return ret; } diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S index 22a2093b5862..b040b0e518ca 100644 --- a/arch/x86/xen/xen-asm_32.S +++ b/arch/x86/xen/xen-asm_32.S @@ -113,11 +113,13 @@ xen_iret_start_crit: /* * If there's something pending, mask events again so we can - * jump back into xen_hypervisor_callback + * jump back into xen_hypervisor_callback. Otherwise do not + * touch XEN_vcpu_info_mask. */ - sete XEN_vcpu_info_mask(%eax) + jne 1f + movb $1, XEN_vcpu_info_mask(%eax) - popl %eax +1: popl %eax /* * From this point on the registers are restored and the stack diff --git a/arch/xtensa/include/asm/unistd.h b/arch/xtensa/include/asm/unistd.h index a6f934f37f1a..798ee6d285a1 100644 --- a/arch/xtensa/include/asm/unistd.h +++ b/arch/xtensa/include/asm/unistd.h @@ -455,7 +455,7 @@ __SYSCALL(203, sys_reboot, 3) #define __NR_quotactl 204 __SYSCALL(204, sys_quotactl, 4) #define __NR_nfsservctl 205 -__SYSCALL(205, sys_nfsservctl, 3) +__SYSCALL(205, sys_ni_syscall, 0) #define __NR__sysctl 206 __SYSCALL(206, sys_sysctl, 1) #define __NR_bdflush 207 diff --git a/block/Kconfig b/block/Kconfig index 60be1e0455da..e97934eececa 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -65,6 +65,16 @@ config BLK_DEV_BSG If unsure, say Y. +config BLK_DEV_BSGLIB + bool "Block layer SG support v4 helper lib" + default n + select BLK_DEV_BSG + help + Subsystems will normally enable this if needed. Users will not + normally need to manually enable this. + + If unsure, say N. + config BLK_DEV_INTEGRITY bool "Block layer data integrity support" ---help--- diff --git a/block/Makefile b/block/Makefile index 0fec4b3fab51..514c6e4f427a 100644 --- a/block/Makefile +++ b/block/Makefile @@ -8,6 +8,7 @@ obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \ blk-iopoll.o blk-lib.o ioctl.o genhd.o scsi_ioctl.o obj-$(CONFIG_BLK_DEV_BSG) += bsg.o +obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o obj-$(CONFIG_BLK_DEV_THROTTLING) += blk-throttle.o obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index bcaf16ee6ad1..b596e54ddd71 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -785,10 +785,10 @@ static int blkio_policy_parse_and_set(char *buf, { char *s[4], *p, *major_s = NULL, *minor_s = NULL; int ret; - unsigned long major, minor, temp; + unsigned long major, minor; int i = 0; dev_t dev; - u64 bps, iops; + u64 temp; memset(s, 0, sizeof(s)); @@ -826,20 +826,23 @@ static int blkio_policy_parse_and_set(char *buf, dev = MKDEV(major, minor); - ret = blkio_check_dev_num(dev); + ret = strict_strtoull(s[1], 10, &temp); if (ret) - return ret; + return -EINVAL; - newpn->dev = dev; + /* For rule removal, do not check for device presence. */ + if (temp) { + ret = blkio_check_dev_num(dev); + if (ret) + return ret; + } - if (s[1] == NULL) - return -EINVAL; + newpn->dev = dev; switch (plid) { case BLKIO_POLICY_PROP: - ret = strict_strtoul(s[1], 10, &temp); - if (ret || (temp < BLKIO_WEIGHT_MIN && temp > 0) || - temp > BLKIO_WEIGHT_MAX) + if ((temp < BLKIO_WEIGHT_MIN && temp > 0) || + temp > BLKIO_WEIGHT_MAX) return -EINVAL; newpn->plid = plid; @@ -850,26 +853,18 @@ static int blkio_policy_parse_and_set(char *buf, switch(fileid) { case BLKIO_THROTL_read_bps_device: case BLKIO_THROTL_write_bps_device: - ret = strict_strtoull(s[1], 10, &bps); - if (ret) - return -EINVAL; - newpn->plid = plid; newpn->fileid = fileid; - newpn->val.bps = bps; + newpn->val.bps = temp; break; case BLKIO_THROTL_read_iops_device: case BLKIO_THROTL_write_iops_device: - ret = strict_strtoull(s[1], 10, &iops); - if (ret) - return -EINVAL; - - if (iops > THROTL_IOPS_MAX) + if (temp > THROTL_IOPS_MAX) return -EINVAL; newpn->plid = plid; newpn->fileid = fileid; - newpn->val.iops = (unsigned int)iops; + newpn->val.iops = (unsigned int)temp; break; } break; diff --git a/block/blk-core.c b/block/blk-core.c index b627558c461f..b2ed78afd9f0 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1167,7 +1167,7 @@ static bool bio_attempt_front_merge(struct request_queue *q, * true if merge was successful, otherwise false. */ static bool attempt_plug_merge(struct task_struct *tsk, struct request_queue *q, - struct bio *bio) + struct bio *bio, unsigned int *request_count) { struct blk_plug *plug; struct request *rq; @@ -1176,10 +1176,13 @@ static bool attempt_plug_merge(struct task_struct *tsk, struct request_queue *q, plug = tsk->plug; if (!plug) goto out; + *request_count = 0; list_for_each_entry_reverse(rq, &plug->list, queuelist) { int el_ret; + (*request_count)++; + if (rq->q != q) continue; @@ -1219,6 +1222,7 @@ static int __make_request(struct request_queue *q, struct bio *bio) struct blk_plug *plug; int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT; struct request *req; + unsigned int request_count = 0; /* * low level driver can indicate that it wants pages above a @@ -1237,7 +1241,7 @@ static int __make_request(struct request_queue *q, struct bio *bio) * Check if we can merge with the plugged list before grabbing * any locks. */ - if (attempt_plug_merge(current, q, bio)) + if (attempt_plug_merge(current, q, bio, &request_count)) goto out; spin_lock_irq(q->queue_lock); @@ -1302,11 +1306,10 @@ get_rq: if (__rq->q != q) plug->should_sort = 1; } + if (request_count >= BLK_MAX_REQUEST_COUNT) + blk_flush_plug_list(plug, false); list_add_tail(&req->queuelist, &plug->list); - plug->count++; drive_stat_acct(req, 1); - if (plug->count >= BLK_MAX_REQUEST_COUNT) - blk_flush_plug_list(plug, false); } else { spin_lock_irq(q->queue_lock); add_acct_request(q, req, where); @@ -1702,6 +1705,7 @@ EXPORT_SYMBOL_GPL(blk_rq_check_limits); int blk_insert_cloned_request(struct request_queue *q, struct request *rq) { unsigned long flags; + int where = ELEVATOR_INSERT_BACK; if (blk_rq_check_limits(q, rq)) return -EIO; @@ -1718,7 +1722,10 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq) */ BUG_ON(blk_queued_rq(rq)); - add_acct_request(q, rq, ELEVATOR_INSERT_BACK); + if (rq->cmd_flags & (REQ_FLUSH|REQ_FUA)) + where = ELEVATOR_INSERT_FLUSH; + + add_acct_request(q, rq, where); spin_unlock_irqrestore(q->queue_lock, flags); return 0; @@ -2275,7 +2282,7 @@ static bool blk_end_bidi_request(struct request *rq, int error, * %false - we are done with this request * %true - still buffers pending for this request **/ -static bool __blk_end_bidi_request(struct request *rq, int error, +bool __blk_end_bidi_request(struct request *rq, int error, unsigned int nr_bytes, unsigned int bidi_bytes) { if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes)) @@ -2630,7 +2637,6 @@ void blk_start_plug(struct blk_plug *plug) INIT_LIST_HEAD(&plug->list); INIT_LIST_HEAD(&plug->cb_list); plug->should_sort = 0; - plug->count = 0; /* * If this is a nested plug, don't actually assign it. It will be @@ -2714,7 +2720,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) return; list_splice_init(&plug->list, &list); - plug->count = 0; if (plug->should_sort) { list_sort(NULL, &list, plug_rq_cmp); diff --git a/block/blk-flush.c b/block/blk-flush.c index bb21e4c36f70..491eb30a242d 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -95,11 +95,12 @@ static unsigned int blk_flush_policy(unsigned int fflags, struct request *rq) { unsigned int policy = 0; + if (blk_rq_sectors(rq)) + policy |= REQ_FSEQ_DATA; + if (fflags & REQ_FLUSH) { if (rq->cmd_flags & REQ_FLUSH) policy |= REQ_FSEQ_PREFLUSH; - if (blk_rq_sectors(rq)) - policy |= REQ_FSEQ_DATA; if (!(fflags & REQ_FUA) && (rq->cmd_flags & REQ_FUA)) policy |= REQ_FSEQ_POSTFLUSH; } @@ -122,7 +123,7 @@ static void blk_flush_restore_request(struct request *rq) /* make @rq a normal request */ rq->cmd_flags &= ~REQ_FLUSH_SEQ; - rq->end_io = NULL; + rq->end_io = rq->flush.saved_end_io; } /** @@ -300,9 +301,6 @@ void blk_insert_flush(struct request *rq) unsigned int fflags = q->flush_flags; /* may change, cache */ unsigned int policy = blk_flush_policy(fflags, rq); - BUG_ON(rq->end_io); - BUG_ON(!rq->bio || rq->bio != rq->biotail); - /* * @policy now records what operations need to be done. Adjust * REQ_FLUSH and FUA for the driver. @@ -312,6 +310,19 @@ void blk_insert_flush(struct request *rq) rq->cmd_flags &= ~REQ_FUA; /* + * An empty flush handed down from a stacking driver may + * translate into nothing if the underlying device does not + * advertise a write-back cache. In this case, simply + * complete the request. + */ + if (!policy) { + __blk_end_bidi_request(rq, 0, 0, 0); + return; + } + + BUG_ON(!rq->bio || rq->bio != rq->biotail); + + /* * If there's data but flush is not necessary, the request can be * processed directly without going through flush machinery. Queue * for normal execution. @@ -319,6 +330,7 @@ void blk_insert_flush(struct request *rq) if ((policy & REQ_FSEQ_DATA) && !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) { list_add_tail(&rq->queuelist, &q->queue_head); + blk_run_queue_async(q); return; } @@ -329,6 +341,7 @@ void blk_insert_flush(struct request *rq) memset(&rq->flush, 0, sizeof(rq->flush)); INIT_LIST_HEAD(&rq->flush.list); rq->cmd_flags |= REQ_FLUSH_SEQ; + rq->flush.saved_end_io = rq->end_io; /* Usually NULL */ rq->end_io = flush_data_end_io; blk_flush_complete_seq(rq, REQ_FSEQ_ACTIONS & ~policy, 0); diff --git a/block/blk-softirq.c b/block/blk-softirq.c index 475fab809a80..1366a89d8e66 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -115,7 +115,7 @@ void __blk_complete_request(struct request *req) /* * Select completion CPU */ - if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && req->cpu != -1) { + if (req->cpu != -1) { ccpu = req->cpu; if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) { ccpu = blk_cpu_to_group(ccpu); @@ -124,6 +124,14 @@ void __blk_complete_request(struct request *req) } else ccpu = cpu; + /* + * If current CPU and requested CPU are in the same group, running + * softirq in current CPU. One might concern this is just like + * QUEUE_FLAG_SAME_FORCE, but actually not. blk_complete_request() is + * running in interrupt handler, and currently I/O controller doesn't |