2668 files changed, 123712 insertions, 14153 deletions

diff --git a/Documentation/ABI/testing/sysfs-class-dual-role-usb b/Documentation/ABI/testing/sysfs-class-dual-role-usb
new file mode 100644
index 00000000000..a900fd75430
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-dual-role-usb
@@ -0,0 +1,71 @@
+What:		/sys/class/dual_role_usb/.../
+Date:		June 2015
+Contact:	Badhri Jagan Sridharan<badhri@google.com>
+Description:
+		Provide a generic interface to monitor and change
+		the state of dual role usb ports. The name here
+		refers to the name mentioned in the
+		dual_role_phy_desc that is passed while registering
+		the dual_role_phy_intstance through
+		devm_dual_role_instance_register.
+
+What:           /sys/class/dual_role_usb/.../supported_modes
+Date:           June 2015
+Contact:        Badhri Jagan Sridharan<badhri@google.com>
+Description:
+		This is a static node, once initialized this
+		is not expected to change during runtime. "dfp"
+		refers to "downstream facing port" i.e. port can
+		only act as host. "ufp" refers to "upstream
+		facing port" i.e. port can only act as device.
+		"dfp ufp" refers to "dual role port" i.e. the port
+		can either be a host port or a device port.
+
+What:		/sys/class/dual_role_usb/.../mode
+Date:		June 2015
+Contact:	Badhri Jagan Sridharan<badhri@google.com>
+Description:
+		The mode node refers to the current mode in which the
+		port is operating. "dfp" for host ports. "ufp" for device
+		ports and "none" when cable is not connected.
+
+		On devices where the USB mode is software-controllable,
+		userspace can change the mode by writing "dfp" or "ufp".
+		On devices where the USB mode is fixed in hardware,
+		this attribute is read-only.
+
+What:		/sys/class/dual_role_usb/.../power_role
+Date:		June 2015
+Contact:	Badhri Jagan Sridharan<badhri@google.com>
+Description:
+		The power_role node mentions whether the port
+		is "sink"ing or "source"ing power. "none" if
+		they are not connected.
+
+		On devices implementing USB Power Delivery,
+		userspace can control the power role by writing "sink" or
+		"source". On devices without USB-PD, this attribute is
+		read-only.
+
+What:		/sys/class/dual_role_usb/.../data_role
+Date:		June 2015
+Contact:	Badhri Jagan Sridharan<badhri@google.com>
+Description:
+		The data_role node mentions whether the port
+		is acting as "host" or "device" for USB data connection.
+		"none" if there is no active data link.
+
+		On devices implementing USB Power Delivery, userspace
+		can control the data role by writing "host" or "device".
+		On devices without USB-PD, this attribute is read-only
+
+What:		/sys/class/dual_role_usb/.../powers_vconn
+Date:		June 2015
+Contact:	Badhri Jagan Sridharan<badhri@google.com>
+Description:
+		The powers_vconn node mentions whether the port
+		is supplying power for VCONN pin.
+
+		On devices with software control of VCONN,
+		userspace can disable the power supply to VCONN by writing "n",
+		or enable the power supply by writing "y".
diff --git a/Documentation/ABI/testing/sysfs-kernel-wakeup_reasons b/Documentation/ABI/testing/sysfs-kernel-wakeup_reasons
new file mode 100644
index 00000000000..acb19b91c19
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-wakeup_reasons
@@ -0,0 +1,16 @@
+What:		/sys/kernel/wakeup_reasons/last_resume_reason
+Date:		February 2014
+Contact:	Ruchi Kandoi <kandoiruchi@google.com>
+Description:
+		The /sys/kernel/wakeup_reasons/last_resume_reason is
+		used to report wakeup reasons after system exited suspend.
+
+What:		/sys/kernel/wakeup_reasons/last_suspend_time
+Date:		March 2015
+Contact:	jinqian <jinqian@google.com>
+Description:
+		The /sys/kernel/wakeup_reasons/last_suspend_time is
+		used to report time spent in last suspend cycle. It contains
+		two numbers (in seconds) separated by space. First number is
+		the time spent in suspend and resume processes. Second number
+		is the time spent in sleep state.
\ No newline at end of file
diff --git a/Documentation/android.txt b/Documentation/android.txt
new file mode 100644
index 00000000000..0f40a78b045
--- /dev/null
+++ b/Documentation/android.txt
@@ -0,0 +1,121 @@
+				=============
+				A N D R O I D
+				=============
+
+Copyright (C) 2009 Google, Inc.
+Written by Mike Chan <mike@android.com>
+
+CONTENTS:
+---------
+
+1. Android
+  1.1 Required enabled config options
+  1.2 Required disabled config options
+  1.3 Recommended enabled config options
+2. Contact
+
+
+1. Android
+==========
+
+Android (www.android.com) is an open source operating system for mobile devices.
+This document describes configurations needed to run the Android framework on
+top of the Linux kernel.
+
+To see a working defconfig look at msm_defconfig or goldfish_defconfig
+which can be found at http://android.git.kernel.org in kernel/common.git
+and kernel/msm.git
+
+
+1.1 Required enabled config options
+-----------------------------------
+After building a standard defconfig, ensure that these options are enabled in
+your .config or defconfig if they are not already. Based off the msm_defconfig.
+You should keep the rest of the default options enabled in the defconfig
+unless you know what you are doing.
+
+ANDROID_PARANOID_NETWORK
+ASHMEM
+CONFIG_FB_MODE_HELPERS
+CONFIG_FONT_8x16
+CONFIG_FONT_8x8
+CONFIG_YAFFS_SHORT_NAMES_IN_RAM
+DAB
+EARLYSUSPEND
+FB
+FB_CFB_COPYAREA
+FB_CFB_FILLRECT
+FB_CFB_IMAGEBLIT
+FB_DEFERRED_IO
+FB_TILEBLITTING
+HIGH_RES_TIMERS
+INOTIFY
+INOTIFY_USER
+INPUT_EVDEV
+INPUT_GPIO
+INPUT_MISC
+LEDS_CLASS
+LEDS_GPIO
+LOCK_KERNEL
+LkOGGER
+LOW_MEMORY_KILLER
+MISC_DEVICES
+NEW_LEDS
+NO_HZ
+POWER_SUPPLY
+PREEMPT
+RAMFS
+RTC_CLASS
+RTC_LIB
+SWITCH
+SWITCH_GPIO
+TMPFS
+UID_STAT
+UID16
+USB_FUNCTION
+USB_FUNCTION_ADB
+USER_WAKELOCK
+VIDEO_OUTPUT_CONTROL
+WAKELOCK
+YAFFS_AUTO_YAFFS2
+YAFFS_FS
+YAFFS_YAFFS1
+YAFFS_YAFFS2
+
+
+1.2 Required disabled config options
+------------------------------------
+CONFIG_YAFFS_DISABLE_LAZY_LOAD
+DNOTIFY
+
+
+1.3 Recommended enabled config options
+------------------------------
+ANDROID_PMEM
+PSTORE_CONSOLE
+PSTORE_RAM
+SCHEDSTATS
+DEBUG_PREEMPT
+DEBUG_MUTEXES
+DEBUG_SPINLOCK_SLEEP
+DEBUG_INFO
+FRAME_POINTER
+CPU_FREQ
+CPU_FREQ_TABLE
+CPU_FREQ_DEFAULT_GOV_ONDEMAND
+CPU_FREQ_GOV_ONDEMAND
+CRC_CCITT
+EMBEDDED
+INPUT_TOUCHSCREEN
+I2C
+I2C_BOARDINFO
+LOG_BUF_SHIFT=17
+SERIAL_CORE
+SERIAL_CORE_CONSOLE
+
+
+2. Contact
+==========
+website: http://android.git.kernel.org
+
+mailing-lists: android-kernel@googlegroups.com
diff --git a/Documentation/arm/small_task_packing.txt b/Documentation/arm/small_task_packing.txt
new file mode 100644
index 00000000000..43f0a8b8023
--- /dev/null
+++ b/Documentation/arm/small_task_packing.txt
@@ -0,0 +1,136 @@
+Small Task Packing in the big.LITTLE MP Reference Patch Set
+
+What is small task packing?
+----
+Simply that the scheduler will fit as many small tasks on a single CPU
+as possible before using other CPUs. A small task is defined as one
+whose tracked load is less than 90% of a NICE_0 task. This is a change
+from the usual behavior since the scheduler will normally use an idle
+CPU for a waking task unless that task is considered cache hot.
+
+
+How is it implemented?
+----
+Since all small tasks must wake up relatively frequently, the main
+requirement for packing small tasks is to select a partly-busy CPU when
+waking rather than looking for an idle CPU. We use the tracked load of
+the CPU runqueue to determine how heavily loaded each CPU is and the
+tracked load of the task to determine if it will fit on the CPU. We
+always start with the lowest-numbered CPU in a sched domain and stop
+looking when we find a CPU with enough space for the task.
+
+Some further tweaks are necessary to suppress load balancing when the
+CPU is not fully loaded, otherwise the scheduler attempts to spread
+tasks evenly across the domain.
+
+
+How does it interact with the HMP patches?
+----
+Firstly, we only enable packing on the little domain. The intent is that
+the big domain is intended to spread tasks amongst the available CPUs
+one-task-per-CPU. The little domain however is attempting to use as
+little power as possible while servicing its tasks.
+
+Secondly, since we offload big tasks onto little CPUs in order to try
+to devote one CPU to each task, we have a threshold above which we do
+not try to pack a task and instead will select an idle CPU if possible.
+This maintains maximum forward progress for busy tasks temporarily
+demoted from big CPUs.
+
+
+Can the behaviour be tuned?
+----
+Yes, the load level of a 'full' CPU can be easily modified in the source
+and is exposed through sysfs as /sys/kernel/hmp/packing_limit to be
+changed at runtime. The presence of the packing behaviour is controlled
+by CONFIG_SCHED_HMP_LITTLE_PACKING and can be disabled at run-time
+using /sys/kernel/hmp/packing_enable.
+The definition of a small task is hard coded as 90% of NICE_0_LOAD
+and cannot be modified at run time.
+
+
+Why do I need to tune it?
+----
+The optimal configuration is likely to be different depending upon the
+design and manufacturing of your SoC.
+
+In the main, there are two system effects from enabling small task
+packing.
+
+1. CPU operating point may increase
+2. wakeup latency of tasks may be increased
+
+There are also likely to be secondary effects from loading one CPU
+rather than spreading tasks.
+
+Note that all of these system effects are dependent upon the workload
+under consideration.
+
+
+CPU Operating Point
+----
+The primary impact of loading one CPU with a number of light tasks is to
+increase the compute requirement of that CPU since it is no longer idle
+as often. Increased compute requirement causes an increase in the
+frequency of the CPU through CPUfreq.
+
+Consider this example:
+We have a system with 3 CPUs which can operate at any frequency between
+350MHz and 1GHz. The system has 6 tasks which would each produce 10%
+load at 1GHz. The scheduler has frequency-invariant load scaling
+enabled. Our DVFS governor aims for 80% utilization at the chosen
+frequency.
+
+Without task packing, these tasks will be spread out amongst all CPUs
+such that each has 2. This will produce roughly 20% system load, and
+the frequency of the package will remain at 350MHz.
+
+With task packing set to the default packing_limit, all of these tasks
+will sit on one CPU and require a package frequency of ~750MHz to reach
+80% utilization. (0.75 = 0.6 * 0.8).
+
+When a package operates on a single frequency domain, all CPUs in that
+package share frequency and voltage.
+
+Depending upon the SoC implementation there can be a significant amount
+of energy lost to leakage from idle CPUs. The decision about how
+loaded a CPU must be to be considered 'full' is therefore controllable
+through sysfs (sys/kernel/hmp/packing_limit) and directly in the code.
+
+Continuing the example, lets set packing_limit to 450 which means we
+will pack tasks until the total load of all running tasks >= 450. In
+practise, this is very similar to a 55% idle 1Ghz CPU.
+
+Now we are only able to place 4 tasks on CPU0, and two will overflow
+onto CPU1. CPU0 will have a load of 40% and CPU1 will have a load of
+20%. In order to still hit 80% utilization, CPU0 now only needs to
+operate at (0.4*0.8=0.32) 320MHz, which means that the lowest operating
+point will be selected, the same as in the non-packing case, except that
+now CPU2 is no longer needed and can be power-gated.
+
+In order to use less energy, the saving from power-gating CPU2 must be
+more than the energy spent running CPU0 for the extra cycles. This
+depends upon the SoC implementation.
+
+This is obviously a contrived example requiring all the tasks to
+be runnable at the same time, but it illustrates the point.
+
+
+Wakeup Latency
+----
+This is an unavoidable consequence of trying to pack tasks together
+rather than giving them a CPU each. If you cannot find an acceptable
+level of wakeup latency, you should turn packing off.
+
+Cyclictest is a good test application for determining the added latency
+when configuring packing.
+
+
+Why is it turned off for the VersatileExpress V2P_CA15A7 CoreTile?
+----
+Simply, this core tile only has power gating for the whole A7 package.
+When small task packing is enabled, all our low-energy use cases
+normally fit onto one A7 CPU. We therefore end up with 2 mostly-idle
+CPUs and one mostly-busy CPU. This decreases the amount of time
+available where the whole package is idle and can be turned off.
+
diff --git a/Documentation/arm64/legacy_instructions.txt b/Documentation/arm64/legacy_instructions.txt
new file mode 100644
index 00000000000..01bf3d9fac8
--- /dev/null
+++ b/Documentation/arm64/legacy_instructions.txt
@@ -0,0 +1,57 @@
+The arm64 port of the Linux kernel provides infrastructure to support
+emulation of instructions which have been deprecated, or obsoleted in
+the architecture. The infrastructure code uses undefined instruction
+hooks to support emulation. Where available it also allows turning on
+the instruction execution in hardware.
+
+The emulation mode can be controlled by writing to sysctl nodes
+(/proc/sys/abi). The following explains the different execution
+behaviours and the corresponding values of the sysctl nodes -
+
+* Undef
+  Value: 0
+  Generates undefined instruction abort. Default for instructions that
+  have been obsoleted in the architecture, e.g., SWP
+
+* Emulate
+  Value: 1
+  Uses software emulation. To aid migration of software, in this mode
+  usage of emulated instruction is traced as well as rate limited
+  warnings are issued. This is the default for deprecated
+  instructions, .e.g., CP15 barriers
+
+* Hardware Execution
+  Value: 2
+  Although marked as deprecated, some implementations may support the
+  enabling/disabling of hardware support for the execution of these
+  instructions. Using hardware execution generally provides better
+  performance, but at the loss of ability to gather runtime statistics
+  about the use of the deprecated instructions.
+
+The default mode depends on the status of the instruction in the
+architecture. Deprecated instructions should default to emulation
+while obsolete instructions must be undefined by default.
+
+Note: Instruction emulation may not be possible in all cases. See
+individual instruction notes for further information.
+
+Supported legacy instructions
+-----------------------------
+* SWP{B}
+Node: /proc/sys/abi/swp
+Status: Obsolete
+Default: Undef (0)
+
+* CP15 Barriers
+Node: /proc/sys/abi/cp15_barrier
+Status: Deprecated
+Default: Emulate (1)
+
+* SETEND
+Node: /proc/sys/abi/setend
+Status: Deprecated
+Default: Emulate (1)*
+Note: All the cpus on the system must have mixed endian support at EL0
+for this feature to be enabled. If a new CPU - which doesn't support mixed
+endian - is hotplugged in after this feature has been enabled, there could
+be unexpected results in the application.
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 10c949b293e..925b8201eba 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -578,6 +578,15 @@ is completely unused; @cgrp->parent is still valid. (Note - can also
 be called for a newly-created cgroup if an error occurs after this
 subsystem's create() method has been called for the new cgroup).
 
+int allow_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
+(cgroup_mutex held by caller)
+
+Called prior to moving a task into a cgroup; if the subsystem
+returns an error, this will abort the attach operation.  Used
+to extend the permission checks - if all subsystems in a cgroup
+return 0, the attach will be allowed to proceed, even if the
+default permission check (root or same user) fails.
+
 int can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
 (cgroup_mutex held by caller)
 
diff --git a/Documentation/cpu-freq/governors.txt b/Documentation/cpu-freq/governors.txt
index 77ec21574fb..2ed766ec75f 100644
--- a/Documentation/cpu-freq/governors.txt
+++ b/Documentation/cpu-freq/governors.txt
@@ -28,6 +28,7 @@ Contents:
 2.3  Userspace
 2.4  Ondemand
 2.5  Conservative
+2.6  Interactive
 
 3.   The Governor Interface in the CPUfreq Core
 
@@ -218,6 +219,90 @@ a decision on when to decrease the frequency while running in any
 speed. Load for frequency increase is still evaluated every
 sampling rate.
 
+2.6 Interactive
+---------------
+
+The CPUfreq governor "interactive" is designed for latency-sensitive,
+interactive workloads. This governor sets the CPU speed depending on
+usage, similar to "ondemand" and "conservative" governors, but with a
+different set of configurable behaviors.
+
+The tuneable values for this governor are:
+
+target_loads: CPU load values used to adjust speed to influence the
+current CPU load toward that value.  In general, the lower the target
+load, the more often the governor will raise CPU speeds to bring load
+below the target.  The format is a single target load, optionally
+followed by pairs of CPU speeds and CPU loads to target at or above
+those speeds.  Colons can be used between the speeds and associated
+target loads for readability.  For example:
+
+   85 1000000:90 1700000:99
+
+targets CPU load 85% below speed 1GHz, 90% at or above 1GHz, until
+1.7GHz and above, at which load 99% is targeted.  If speeds are
+specified these must appear in ascending order.  Higher target load
+values are typically specified for higher speeds, that is, target load
+values also usually appear in an ascending order. The default is
+target load 90% for all speeds.
+
+min_sample_time: The minimum amount of time to spend at the current
+frequency before ramping down. Default is 80000 uS.
+
+hispeed_freq: An intermediate "hi speed" at which to initially ramp
+when CPU load hits the value specified in go_hispeed_load.  If load
+stays high for the amount of time specified in above_hispeed_delay,
+then speed may be bumped higher.  Default is the maximum speed
+allowed by the policy at governor initialization time.
+
+go_hispeed_load: The CPU load at which to ramp to hispeed_freq.
+Default is 99%.
+
+above_hispeed_delay: When speed is at or above hispeed_freq, wait for
+this long before raising speed in response to continued high load.
+The format is a single delay value, optionally followed by pairs of
+CPU speeds and the delay to use at or above those speeds.  Colons can
+be used between the speeds and associated delays for readability.  For
+example:
+
+   80000 1300000:200000 1500000:40000
+
+uses delay 80000 uS until CPU speed 1.3 GHz, at which speed delay
+200000 uS is used until speed 1.5 GHz, at which speed (and above)
+delay 40000 uS is used.  If speeds are specified these must appear in
+ascending order.  Default is 20000 uS.
+
+timer_rate: Sample rate for reevaluating CPU load when the CPU is not
+idle.  A deferrable timer is used, such that the CPU will not be woken
+from idle to service this timer until something else needs to run.
+(The maximum time to allow deferring this timer when not running at
+minimum speed is configurable via timer_slack.)  Default is 20000 uS.
+
+timer_slack: Maximum additional time to defer handling the governor
+sampling timer beyond timer_rate when running at speeds above the
+minimum.  For platforms that consume additional power at idle when
+CPUs are running at speeds greater than minimum, this places an upper
+bound on how long the timer will be deferred prior to re-evaluating
+load and dropping speed.  For example, if timer_rate is 20000uS and
+timer_slack is 10000uS then timers will be deferred for up to 30msec
+when not at lowest speed.  A value of -1 means defer timers
+indefinitely at all speeds.  Default is 80000 uS.
+
+boost: If non-zero, immediately boost speed of all CPUs to at least
+hispeed_freq until zero is written to this attribute.  If zero, allow
+CPU speeds to drop below hispeed_freq according to load as usual.
+Default is zero.
+
+boostpulse: On each write, immediately boost speed of all CPUs to
+hispeed_freq for at least the period of time specified by
+boostpulse_duration, after which speeds are allowed to drop below
+hispeed_freq according to load as usual.
+
+boostpulse_duration: Length of time to hold CPU speed at hispeed_freq
+on a write to boostpulse, before allowing speed to drop according to
+load as usual.  Default is 80000 uS.
+
+
 3. The Governor Interface in the CPUfreq Core
 =============================================
 
diff --git a/Documentation/device-mapper/dm-crypt.txt b/Documentation/device-mapper/dm-crypt.txt
index c81839b52c4..692171fe9da 100644
--- a/Documentation/device-mapper/dm-crypt.txt
+++ b/Documentation/device-mapper/dm-crypt.txt
@@ -5,7 +5,7 @@ Device-Mapper's "crypt" target provides transparent encryption of block devices
 using the kernel crypto API.
 
 For a more detailed description of supported parameters see:
-http://code.google.com/p/cryptsetup/wiki/DMCrypt
+https://gitlab.com/cryptsetup/cryptsetup/wikis/DMCrypt
 
 Parameters: <cipher> <key> <iv_offset> <device path> \
 	      <offset> [<#opt_params> <opt_params>]
@@ -51,7 +51,7 @@ Parameters: <cipher> <key> <iv_offset> <device path> \
     Otherwise #opt_params is the number of following arguments.
 
     Example of optional parameters section:
-        1 allow_discards
+        3 allow_discards same_cpu_crypt submit_from_crypt_cpus
 
 allow_discards
     Block discard requests (a.k.a. TRIM) are passed through the crypt device.
@@ -63,11 +63,24 @@ allow_discards
     used space etc.) if the discarded blocks can be located easily on the
     device later.
 
+same_cpu_crypt
+    Perform encryption using the same cpu that IO was submitted on.
+    The default is to use an unbound workqueue so that encryption work
+    is automatically balanced between available CPUs.
+
+submit_from_crypt_cpus
+    Disable offloading writes to a separate thread after encryption.
+    There are some situations where offloading write bios from the
+    encryption threads to a single thread degrades performance
+    significantly.  The default is to offload write bios to the same
+    thread because it benefits CFQ to have writes submitted using the
+    same context.
+
 Example scripts
 ===============
 LUKS (Linux Unified Key Setup) is now the preferred way to set up disk
 encryption with dm-crypt using the 'cryptsetup' utility, see
-http://code.google.com/p/cryptsetup/
+https://gitlab.com/cryptsetup/cryptsetup
 
 [[
 #!/bin/sh
diff --git a/Documentation/device-mapper/verity.txt b/Documentation/device-mapper/verity.txt
index 9884681535e..0075f70cd3f 100644
--- a/Documentation/device-mapper/verity.txt
+++ b/Documentation/device-mapper/verity.txt
@@ -125,7 +125,7 @@ block boundary) are the hash blocks which are stored a depth at a time
 
 The full specification of kernel parameters and on-disk metadata format
 is available at the cryptsetup project's wiki page
-  http://code.google.com/p/cryptsetup/wiki/DMVerity
+  https://gitlab.com/cryptsetup/cryptsetup/wikis/DMVerity
 
 Status
 ======
@@ -142,7 +142,7 @@ Set up a device:
 
 A command line tool veritysetup is available to compute or verify
 the hash tree or activate the kernel device. This is available from
-the cryptsetup upstream repository http://code.google.com/p/cryptsetup/
+the cryptsetup upstream repository https://gitlab.com/cryptsetup/cryptsetup/
 (as a libcryptsetup extension).
 
 Create hash on the device:
diff --git a/Documentation/devicetree/bindings/arm/arch_timer.txt b/Documentation/devicetree/bindings/arm/arch_timer.txt
index 37b2cafa4e5..271483595a1 100644
--- a/Documentation/devicetree/bindings/arm/arch_timer.txt
+++ b/Documentation/devicetree/bindings/arm/arch_timer.txt
@@ -42,6 +42,9 @@ Example:
 
 - reg : The control frame base address.
 
+- arm,cnttidr : The value of the CNTTIDR register if not accessible from
+  the level the kernel is running at. To be used only in extreme cases.
+
 Note that #address-cells, #size-cells, and ranges shall be present to ensure
 the CPU can address a frame's registers.
 
diff --git a/Documentation/devicetree/bindings/arm/arm,scpi.txt b/Documentation/devicetree/bindings/arm/arm,scpi.txt
new file mode 100644
index 00000000000..e21cce64656
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/arm,scpi.txt
@@ -0,0 +1,151 @@
+System Control and Power Interface (SCPI) Message Protocol
+----------------------------------------------------------
+
+Firmware implementing the SCPI described in ARM document number ARM DUI 0922B
+("ARM Compute Subsystem SCP: Message Interface Protocols")[0] can be used
+by Linux to initiate various system control and power operations.
+
+Required properties:
+
+- compatible : should be "arm,scpi"
+- mboxes: List of phandle and mailbox channel specifiers
+	  All the channels reserved by remote SCP firmware for use by
+	  SCPI message protocol should be specified in any order
+- shmem : List of phandle pointing to the shared memory(SHM) area between the
+	  processors using these mailboxes for IPC, one for each mailbox
+	  SHM can be any memory reserved for the purpose of this communication
+	  between the processors.
+
+See Documentation/devicetree/bindings/mailbox/mailbox.txt
+for more details about the generic mailbox controller and
+client driver bindings.
+
+Clock bindings for the clocks based on SCPI Message Protocol
+------------------------------------------------------------
+
+This binding uses the common clock binding[1].
+
+Container Node
+==============
+Required properties:
+- compatible : should be "arm,scpi-clocks"
+	       All the clocks provided by SCP firmware via SCPI message
+	       protocol much be listed as sub-nodes under this node.
+
+Sub-nodes
+=========
+Required properties:
+- compatible : shall include one of the following
+	"arm,scpi-dvfs-clocks" - all the clocks that are variable and index based.
+		These clocks don't provide an entire range of values between the
+		limits but only discrete points within the range. The firmware
+		provides the mapping for each such operating frequency and the
+		index associated with it. The firmware also manages the
+		voltage scaling appropriately with the clock scaling.
+	"arm,scpi-variable-clocks" - all the clocks that are variable and provide full
+		range within the specified range. The firmware provides the
+		range of values within a specified range.
+
+Other required properties for all clocks(all from common clock binding):
+- #clock-cells : should be set to 1 as each of the SCPI clocks have multiple
+	outputs.
+- clock-output-names : shall be the corresponding names of the outputs.
+- clock-indices: The identifying number for the clocks(i.e.clock_id) in the
+	node. It can be non linear and hence provide the mapping of identifiers
+	into the clock-output-names array.
+
+SRAM and Shared Memory for SCPI
+-------------------------------
+
+A small area of SRAM is reserved for SCPI communication between application
+processors and SCP.
+
+Required properties:
+- compatible : should be "arm,juno-sram-ns" for Non-secure SRAM on Juno
+
+The rest of the properties should follow the generic mmio-sram description
+found in ../../misc/sysram.txt
+
+Each sub-node represents the reserved area for SCPI.
+
+Required sub-node properties:
+- reg : The base offset and size of the reserved area with the SRAM
+- compatible : should be "arm,juno-scp-shmem" for Non-secure SRAM based
+	       shared memory on Juno platforms
+
+[0] http://community.arm.com/servlet/JiveServlet/download/8401-45-18326/DUI0922B_scp_message_interface.pdf
+[1] Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+Example:
+
+sram: sram@50000000 {
+	compatible = "arm,juno-sram-ns", "mmio-sram";
+	reg = <0x0 0x50000000 0x0 0x10000>;
+
+	#address-cells = <1>;
+	#size-cells = <1>;
+	ranges = <0 0x0 0x50000000 0x10000>;
+
+	cpu_scp_lpri: scp-shmem@0 {
+		compatible = "arm,juno-scp-shmem";
+		reg = <0x0 0x200>;
+	};
+
+	cpu_scp_hpri: scp-shmem@200 {
+		compatible = "arm,juno-scp-shmem";
+		reg = <0x200 0x200>;
+	};
+};
+
+mailbox: mailbox0@40000000 {
+	....
+	#mbox-cells = <1>;
+};
+
+scpi_protocol: scpi@2e000000 {
+	compatible = "arm,scpi";
+	mboxes = <&mailbox 0 &mailbox 1>;
+	shmem = <&cpu_scp_lpri &cpu_scp_hpri>;
+
+	clocks {
+		compatible = "arm,scpi-clocks";
+
+		scpi_dvfs: scpi_clocks@0 {
+			compatible = "arm,scpi-dvfs-clocks";
+			#clock-cells = <1>;
+			clock-indices = <0>, <1>, <2>;
+			clock-output-names = "atlclk", "aplclk","gpuclk";
+		};
+		scpi_clk: scpi_clocks@3 {
+			compatible = "arm,scpi-variable-clocks";
+			#clock-cells = <1>;
+			clock-indices = <3>, <4>;
+			clock-output-names = "pxlclk0", "pxlclk1";
+		};
+	};
+};
+
+cpu@0 {
+	...
+	reg = <0 0>;
+	clocks = <&scpi_dvfs 0>;
+};
+
+hdlcd@7ff60000 {
+	...
+	reg = <0 0x7ff60000 0 0x1000>;
+	clocks = <&scpi_clk 4>;
+};
+
+In the above example, the #clock-cells is set to 1 as required.
+scpi_dvfs has 3 output clocks namely: vbig, vlittle and vgpu with 0, 1
+and 2 as clock-indices. scpi_clk has 2 output clocks namely: pxlclk0 and
+pxlclk1 with 3 and 4 as clock-indices.
+
+The first consumer in the example is cpu@0 and it has '0' as the clock
+specifier which points to the first entry in the output clocks of
+scpi_dvfs i.e. "atlclk".
+
+Similarly the second example is hdlcd@7ff60000 and it has pxlclk1 as input
+clock. '4' in the clock specifier here points to the second entry
+in the output clocks of scpi_clocks  i.e. "pxlclk1"
diff --git a/Documentation/devicetree/bindings/arm/arm-boards b/Documentation/devicetree/bindings/arm/arm-boards
index c554ed3d44f..074d1703d18 100644
--- a/Documentation/devicetree/bindings/arm/arm-boards
+++ b/Documentation/devicetree/bindings/arm/arm-boards
@@ -92,3 +92,69 @@ Required nodes:
 - core-module: the root node to the Versatile platforms must have
   a core-module with regs and the compatible strings
   "arm,core-module-versatile", "syscon"
+
+ARM Versatile Express Boards
+-----------------------------
+For details on the device tree bindings for ARM Versatile Express boards
+please consult the vexpress.txt file in the same directory as this file.
+
+ARM Juno Boards
+----------------
+The Juno boards are targeting development for AArch64 systems. The first
+iteration, Juno r0, is a vehicle for evaluating big.LITTLE on AArch64,
+with the second iteration, Juno r1, mainly aimed at development of PCIe
+based systems. Juno r1 also has support for AXI masters placed on the TLX
+connectors to join the coherency domain.
+
+Juno boards are described in a similar way to ARM Versatile Express boards,
+with the motherboard part of the hardware being described in a separate file
+to highlight the fact that is part of the support infrastructure for the SoC.
+Juno device tree bindings also share the Versatile Express bindings as
+described under the RS1 memory mapping.
+
+Required properties (in root node):
+	compatible = "arm,juno";	/* For Juno r0 board */
+	compatible = "arm,juno-r1";	/* For Juno r1 board */
+
+Required nodes:
+The description for the board must include:
+   - a "psci" node describing the boot method used for the secondary CPUs.
+     A detailed description of the bindings used for "psci" nodes is present
+     in the psci.txt file.
+   - a "cpus" node describing the available cores and their associated
+     "enable-method"s. For more details see cpus.txt file.
+
+Example:
+
+/dts-v1/;
+/ {
+	model = "ARM Juno development board (r0)";
+	compatible = "arm,juno", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		A57_0: cpu@0 {
+			compatible = "arm,cortex-a57","arm,armv8";
+			reg = <0x0 0x0>;
+			device_type = "cpu";
+			enable-method = "psci";
+		};
+
+		.....
+
+		A53_0: cpu@100 {
+			compatible = "arm,cortex-a53","arm,armv8";
+			reg = <0x0 0x100>;
+			device_type = "cpu";
+			enable-method = "psci";
+		};
+
+		.....
+	};
+
+};
diff --git a/Documentation/devicetree/bindings/arm/coresight.txt b/Documentation/devicetree/bindings/arm/coresight.txt
new file mode 100644
index 00000000000..88602b75418
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/coresight.txt
@@ -0,0 +1,199 @@
+* CoreSight Components:
+
+CoreSight components are compliant with the ARM CoreSight architecture
+specification and can be connected in various topologies to suit a particular
+SoCs tracing needs. These trace components can generally be classified as
+sinks, links and sources. Trace data produced by one or more sources flows
+through the intermediate links connecting the source to the currently selected
+sink. Each CoreSight component device should use these properties to describe
+its hardware characteristcs.
+
+* Required properties for all components *except* non-configurable replicators:
+
+	* compatible: These have to be supplemented with "arm,primecell" as
+	  drivers are using the AMBA bus interface.  Possible values include:
+		- "arm,coresight-etb10", "arm,primecell";
+		- "arm,coresight-tpiu", "arm,primecell";
+		- "arm,coresight-tmc", "arm,primecell";
+		- "arm,coresight-funnel", "arm,primecell";
+		- "arm,coresight-etm3x", "arm,primecell";
+
+	* reg: physical base address and length of the register
+	  set(s) of the component.
+
+	* clocks: the clock associated to this component.
+
+	* clock-names: the name of the clock as referenced by the code.
+	  Since we are using the AMBA framework, the name should be
+	  "apb_pclk".
+
+	* port or ports: The representation of the component's port
+	  layout using the generic DT graph presentation found in
+	  "bindings/graph.txt".
+
+* Required properties for devices that don't show up on the AMBA bus, such as
+  non-configurable replicators:
+
+	* compatible: Currently supported value is (note the absence of the
+	  AMBA markee):
+		- "arm,coresight-replicator"
+
+	* port or ports: same as above.
+
+* Optional properties for ETM/PTMs:
+
+	* arm,cp14: must be present if the system accesses ETM/PTM management
+	  registers via co-processor 14.
+
+	* cpu: the cpu phandle this ETM/PTM is affined to. When omitted the
+	  source is considered to belong to CPU0.
+
+* Optional property for TMC:
+
+	* arm,buffer-size: size of contiguous buffer space for TMC ETR
+	 (embedded trace router)
+
+
+Example:
+
+1. Sinks
+	etb@20010000 {
+		compatible = "arm,coresight-etb10", "arm,primecell";
+		reg = <0 0x20010000 0 0x1000>;
+
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			etb_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator_out_port0>;
+			};
+		};
+	};
+
+	tpiu@20030000 {
+		compatible = "arm,coresight-tpiu", "arm,primecell";
+		reg = <0 0x20030000 0 0x1000>;
+
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			tpiu_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator_out_port1>;
+			};
+		};
+	};
+
+2. Links
+	replicator {
+		/* non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator_out_port0: endpoint {
+					remote-endpoint = <&etb_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator_out_port1: endpoint {
+					remote-endpoint = <&tpiu_in_port>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&funnel_out_port0>;
+				};
+			};
+		};
+	};
+
+	funnel@20040000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0x20040000 0 0x1000>;
+
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel_out_port0: endpoint {
+					remote-endpoint =
+							<&replicator_in_port0>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm0_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm1_out_port>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&etm0_out_port>;
+				};
+			};
+
+		};
+	};
+
+3. Sources
+	ptm@2201c000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0x2201c000 0 0x1000>;
+
+		cpu = <&cpu0>;
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			ptm0_out_port: endpoint {
+				remote-endpoint = <&funnel_in_port0>;
+			};
+		};
+	};
+
+	ptm@2201d000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0x2201d000 0 0x1000>;
+
+		cpu = <&cpu1>;
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			ptm1_out_port: endpoint {
+				remote-endpoint = <&funnel_in_port1>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/dma/fsl-mxs-dma.txt b/Documentation/devicetree/bindings/dma/fsl-mxs-dma.txt
index a4873e5e3e3..e30e184f50c 100644
--- a/Documentation/devicetree/bindings/dma/fsl-mxs-dma.txt
+++ b/Documentation/devicetree/bindings/dma/fsl-mxs-dma.txt
@@ -38,7 +38,7 @@ dma_apbx: dma-apbx@80024000 {
 		      80 81 68 69
 		      70 71 72 73
 		      74 75 76 77>;
-	interrupt-names = "auart4-rx", "aurat4-tx", "spdif-tx", "empty",
+	interrupt-names = "auart4-rx", "auart4-tx", "spdif-tx", "empty",
 			  "saif0", "saif1", "i2c0", "i2c1",
 			  "auart0-rx", "auart0-tx", "auart1-rx", "auart1-tx",
 			  "auart2-rx", "auart2-tx", "auart3-rx", "auart3-tx";
diff --git a/Documentation/devicetree/bindings/i2c/i2c-designware.txt b/Documentation/devicetree/bindings/i2c/i2c-designware.txt
index 5199b0c8cf7..fee26dc3e85 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-designware.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-designware.txt
@@ -14,10 +14,10 @@ Optional properties :
  - i2c-sda-hold-time-ns : should contain the SDA hold time in nanoseconds.
    This option is only supported in hardware blocks version 1.11a or newer.
 
- - i2c-scl-falling-time : should contain the SCL falling time in nanoseconds.
+ - i2c-scl-falling-time-ns : should contain the SCL falling time in nanoseconds.
    This value which is by default 300ns is used to compute the tLOW period.
 
- - i2c-sda-falling-time : should contain the SDA falling time in nanoseconds.
+ - i2c-sda-falling-time-ns : should contain the SDA falling time in nanoseconds.
    This value which is by default 300ns is used to compute the tHIGH period.
 
 Example :
diff --git a/Documentation/devicetree/bindings/mailbox/arm-mhu.txt b/Documentation/devicetree/bindings/mailbox/arm-mhu.txt
new file mode 100644
index 00000000000..4971f03f0b3
--- /dev/null
+++ b/Documentation/devicetree/bindings/mailbox/arm-mhu.txt
@@ -0,0 +1,43 @@
+ARM MHU Mailbox Driver
+======================
+
+The ARM's Message-Handling-Unit (MHU) is a mailbox controller that has
+3 independent channels/links to communicate with remote processor(s).
+ MHU links are hardwired on a platform. A link raises interrupt for any
+received data. However, there is no specified way of knowing if the sent
+data has been read by the remote. This driver assumes the sender polls
+STAT register and the remote clears it after having read the data.
+The last channel is specified to be a 'Secure' resource, hence can't be
+used by Linux running NS.
+
+Mailbox Device Node:
+====================
+
+Required properties:
+--------------------
+- compatible:		Shall be "arm,mhu" & "arm,primecell"
+- reg:			Contains the mailbox register address range (base
+			address and length)
+- #mbox-cells		Shall be 1 - the index of the channel needed.
+- interrupts:		Contains the interrupt information corresponding to
+			each of the 3 links of MHU.
+
+Example:
+--------
+
+	mhu: mailbox@2b1f0000 {
+		#mbox-cells = <1>;
+		compatible = "arm,mhu", "arm,primecell";
+		reg = <0 0x2b1f0000 0x1000>;
+		interrupts = <0 36 4>, /* LP-NonSecure */
+			     <0 35 4>, /* HP-NonSecure */
+			     <0 37 4>; /* Secure */
+		clocks = <&clock 0 2 1>;
+		clock-names = "apb_pclk";
+	};
+
+	mhu_client: scb@2e000000 {
+		compatible = "fujitsu,mb86s70-scb-1.0";
+		reg = <0 0x2e000000 0x4000>;
+		mboxes = <&mhu 1>; /* HP-NonSecure */
+	};
diff --git a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
index 750d577e808..f5a8ca29aff 100644
--- a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
+++ b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
@@ -1,7 +1,7 @@
 * Marvell Armada 370 / Armada XP Ethernet Controller (NETA)
 
 Required properties:
-- compatible: should be "marvell,armada-370-neta".
+- compatible: "marvell,armada-370-neta" or "marvell,armada-xp-neta".
 - reg: address and length of the register set for the device.
 - interrupts: interrupt for the device
 - phy: See ethernet.txt file in the same directory.
diff --git a/Documentation/devicetree/bindings/pinctrl/marvell,armada-370-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/marvell,armada-370-pinctrl.txt
index adda2a8d1d5..e357b020861 100644
--- a/Documentation/devicetree/bindings/pinctrl/marvell,armada-370-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/marvell,armada-370-pinctrl.txt
@@ -92,5 +92,5 @@ mpp61         61       gpo, dev(wen1), uart1(txd), audio(rclk)
 mpp62         62       gpio, dev(a2), uart1(cts), tdm(drx), pcie(clkreq0),
                        audio(mclk), uart0(cts)
 mpp63         63       gpo, spi0(sck), tclk
-mpp64         64       gpio, spi0(miso), spi0-1(cs1)
-mpp65         65       gpio, spi0(mosi), spi0-1(cs2)
+mpp64         64       gpio, spi0(miso), spi0(cs1)
+mpp65         65       gpio, spi0(mosi), spi0(cs2)
diff --git a/Documentation/devicetree/bindings/pinctrl/marvell,armada-375-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/marvell,armada-375-pinctrl.txt
index 7de0cda4a37..bedbe42c8c0 100644
--- a/Documentation/devicetree/bindings/pinctrl/marvell,armada-375-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/marvell,armada-375-pinctrl.txt
@@ -22,8 +22,8 @@ mpp5          5        gpio, dev(ad7), spi0(cs2), spi1(cs2)
 mpp6          6        gpio, dev(ad0), led(p1), audio(rclk)
 mpp7          7        gpio, dev(ad1), ptp(clk), led(p2), audio(extclk)
 mpp8          8        gpio, dev (bootcs), spi0(cs0), spi1(cs0)
-mpp9          9        gpio, nf(wen), spi0(sck), spi1(sck)
-mpp10        10        gpio, nf(ren), dram(vttctrl), led(c1)
+mpp9          9        gpio, spi0(sck), spi1(sck), nand(we)
+mpp10        10        gpio, dram(vttctrl), led(c1), nand(re)
 mpp11        11        gpio, dev(a0), led(c2), audio(sdo)
 mpp12        12        gpio, dev(a1), audio(bclk)
 mpp13        13        gpio, dev(readyn), pcie0(rstoutn), pcie1(rstoutn)
diff --git a/Documentation/devicetree/bindings/pinctrl/marvell,armada-38x-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/marvell,armada-38x-pinctrl.txt
index b17c96849fc..4ac138aaaf8 100644
--- a/Documentation/devicetree/bindings/pinctrl/marvell,armada-38x-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/marvell,armada-38x-pinctrl.txt
@@ -27,15 +27,15 @@ mpp8          8        gpio, ge0(txd1), dev(ad10)
 mpp9          9        gpio, ge0(txd2), dev(ad11)
 mpp10         10       gpio, ge0(txd3), dev(ad12)
 mpp11         11       gpio, ge0(txctl), dev(ad13)
-mpp12         12       gpio, ge0(rxd0), pcie0(rstout), pcie1(rstout) [1], spi0(cs1), dev(ad14)
-mpp13         13       gpio, ge0(rxd1), pcie0(clkreq), pcie1(clkreq) [1], spi0(cs2), dev(ad15)
-mpp14         14       gpio, ge0(rxd2), ptp(clk), m(vtt_ctrl), spi0(cs3), dev(wen1)
-mpp15         15       gpio, ge0(rxd3), ge(mdc slave), pcie0(rstout), spi0(mosi), pcie1(rstout) [1]
-mpp16         16       gpio, ge0(rxctl), ge(mdio slave), m(decc_err), spi0(miso), pcie0(clkreq)
+mpp12         12       gpio, ge0(rxd0), pcie0(rstout), spi0(cs1), dev(ad14), pcie3(clkreq)
+mpp13         13       gpio, ge0(rxd1), pcie0(clkreq), pcie1(clkreq) [1], spi0(cs2), dev(ad15), pcie2(clkreq)
+mpp14         14       gpio, ge0(rxd2), ptp(clk), m(vtt_ctrl), spi0(cs3), dev(wen1), pcie3(clkreq)
+mpp15         15       gpio, ge0(rxd3), ge(mdc slave), pcie0(rstout), spi0(mosi)
+mpp16         16       gpio, ge0(rxctl), ge(mdio slave), m(decc_err), spi0(miso), pcie0(clkreq), pcie1(clkreq) [1]
 mpp17         17       gpio, ge0(rxclk), ptp(clk), ua1(rxd), spi0(sck), sata1(prsnt)
-mpp18         18       gpio, ge0(rxerr), ptp(trig_gen), ua1(txd), spi0(cs0), pcie1(rstout) [1]
-mpp19         19       gpio, ge0(col), ptp(event_req), pcie0(clkreq), sata1(prsnt), ua0(cts)
-mpp20         20       gpio, ge0(txclk), ptp(clk), pcie1(rstout) [1], sata0(prsnt), ua0(rts)
+mpp18         18       gpio, ge0(rxerr), ptp(trig_gen), ua1(txd), spi0(cs0)
+mpp19         19       gpio, ge0(col), ptp(event_req), ge0(txerr), sata1(prsnt), ua0(cts)
+mpp20         20       gpio, ge0(txclk), ptp(clk), sata0(prsnt), ua0(rts)
 mpp21         21       gpio, spi0(cs1), ge1(rxd0), sata0(prsnt), sd0(cmd), dev(bootcs)
 mpp22         22       gpio, spi0(mosi), dev(ad0)
 mpp23         23       gpio, spi0(sck), dev(ad2)
@@ -58,23 +58,23 @@ mpp39         39       gpio, i2c1(sck), ge1(rxd2), ua0(cts), sd0(d1), dev(a2)
 mpp40         40       gpio, i2c1(sda), ge1(rxd3), ua0(rts), sd0(d2), dev(ad6)
 mpp41         41       gpio, ua1(rxd), ge1(rxctl), ua0(cts), spi1(cs3), dev(burst/last)
 mpp42         42       gpio, ua1(txd), ua0(rts), dev(ad7)
-mpp43         43       gpio, pcie0(clkreq), m(vtt_ctrl), m(decc_err), pcie0(rstout), dev(clkout)
-mpp44         44       gpio, sata0(prsnt), sata1(prsnt), sata2(prsnt) [2], sata3(prsnt) [3], pcie0(rstout)
-mpp45         45       gpio, ref(clk_out0), pcie0(rstout), pcie1(rstout) [1], pcie2(rstout), pcie3(rstout)
-mpp46         46       gpio, ref(clk_out1), pcie0(rstout), pcie1(rstout) [1], pcie2(rstout), pcie3(rstout)
-mpp47         47       gpio, sata0(prsnt), sata1(prsnt), sata2(prsnt) [2], spi1(cs2), sata3(prsnt) [2]
-mpp48         48       gpio, sata0(prsnt), m(vtt_ctrl), tdm2c(pclk), audio(mclk), sd0(d4)
-mpp49         49       gpio, sata2(prsnt) [2], sata3(prsnt) [2], tdm2c(fsync), audio(lrclk), sd0(d5)
-mpp50         50       gpio, pcie0(rstout), pcie1(rstout) [1], tdm2c(drx), audio(extclk), sd0(cmd)
+mpp43         43       gpio, pcie0(clkreq), m(vtt_ctrl), m(decc_err), spi1(cs2), dev(clkout)
+mpp44         44       gpio, sata0(prsnt), sata1(prsnt), sata2(prsnt) [2], sata3(prsnt) [3]
+mpp45         45       gpio, ref(clk_out0), pcie0(rstout)
+mpp46         46       gpio, ref(clk_out1), pcie0(rstout)
+mpp47         47       gpio, sata0(prsnt), sata1(prsnt), sata2(prsnt) [2], sata3(prsnt) [2]
+mpp48         48       gpio, sata0(prsnt), m(vtt_ctrl), tdm2c(pclk), audio(mclk), sd0(d4), pcie0(clkreq)
+mpp49         49       gpio, sata2(prsnt) [2], sata3(prsnt) [2], tdm2c(fsync), audio(lrclk), sd0(d5), pcie1(clkreq)
+mpp50         50       gpio, pcie0(rstout), tdm2c(drx), audio(extclk), sd0(cmd)
 mpp51         51       gpio, tdm2c(dtx), audio(sdo), m(decc_err)
-mpp52         52       gpio, pcie0(rstout), pcie1(rstout) [1], tdm2c(intn), audio(sdi), sd0(d6)
+mpp52         52       gpio, pcie0(rstout), tdm2c(intn), audio(sdi), sd0(d6)
 mpp53         53       gpio, sata1(prsnt), sata0(prsnt), tdm2c(rstn), audio(bclk), sd0(d7)
-mpp54         54       gpio, sata0(prsnt), sata1(prsnt), pcie0(rstout), pcie1(rstout) [1], sd0(d3)
+mpp54         54       gpio, sata0(prsnt), sata1(prsnt), pcie0(rstout), ge0(txerr), sd0(d3)
 mpp55         55       gpio, ua1(cts), ge(mdio), pcie1(clkreq) [1], spi1(cs1), sd0(d0)
 mpp56         56       gpio, ua1(rts), ge(mdc), m(decc_err), spi1(mosi)
 mpp57         57       gpio, spi1(sck), sd0(clk)
 mpp58         58       gpio, pcie1(clkreq) [1], i2c1(sck), pcie2(clkreq), spi1(miso), sd0(d1)
-mpp59         59       gpio, pcie0(rstout), i2c1(sda), pcie1(rstout) [1], spi1(cs0), sd0(d2)
+mpp59         59       gpio, pcie0(rstout), i2c1(sda), spi1(cs0), sd0(d2)
 
 [1]: only available on 88F6820 and 88F6828
 [2]: only available on 88F6828
diff --git a/Documentation/devicetree/bindings/pinctrl/marvell,armada-xp-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/marvell,armada-xp-pinctrl.txt
index 373dbccd7ab..96e7744cab8 100644
--- a/Documentation/devicetree/bindings/pinctrl/marvell,armada-xp-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/marvell,armada-xp-pinctrl.txt
@@ -42,15 +42,15 @@ mpp20         20       gpio, ge0(rxd4), ge1(rxd2), lcd(d20), ptp(clk)
 mpp21         21       gpio, ge0(rxd5), ge1(rxd3), lcd(d21), mem(bat)
 mpp22         22       gpio, ge0(rxd6), ge1(rxctl), lcd(d22), sata0(prsnt)
 mpp23         23       gpio, ge0(rxd7), ge1(rxclk), lcd(d23), sata1(prsnt)
-mpp24         24       gpio, lcd(hsync), sata1(prsnt), nf(bootcs-re), tdm(rst)
-mpp25         25       gpio, lcd(vsync), sata0(prsnt), nf(bootcs-we), tdm(pclk)
-mpp26         26       gpio, lcd(clk), tdm(fsync), vdd(cpu1-pd)
+mpp24         24       gpio, lcd(hsync), sata1(prsnt), tdm(rst)
+mpp25         25       gpio, lcd(vsync), sata0(prsnt), tdm(pclk)
+mpp26         26       gpio, lcd(clk), tdm(fsync)
 mpp27         27       gpio, lcd(e), tdm(dtx), ptp(trig)
 mpp28         28       gpio, lcd(pwm), tdm(drx), ptp(evreq)
-mpp29         29       gpio, lcd(ref-clk), tdm(int0), ptp(clk), vdd(cpu0-pd)
+mpp29         29       gpio, lcd(ref-clk), tdm(int0), ptp(clk)
 mpp30         30       gpio, tdm(int1), sd0(clk)
-mpp31         31       gpio, tdm(int2), sd0(cmd), vdd(cpu0-pd)
-mpp32         32       gpio, tdm(int3), sd0(d0), vdd(cpu1-pd)
+mpp31         31       gpio, tdm(int2), sd0(cmd)
+mpp32         32       gpio, tdm(int3), sd0(d0)
 mpp33         33       gpio, tdm(int4), sd0(d1), mem(bat)
 mpp34         34       gpio, tdm(int5), sd0(d2), sata0(prsnt)
 mpp35         35       gpio, tdm(int6), sd0(d3), sata1(prsnt)
@@ -58,21 +58,18 @@ mpp36         36       gpio, spi(mosi)
 mpp37         37       gpio, spi(miso)
 mpp38         38       gpio, spi(sck)
 mpp39         39       gpio, spi(cs0)
-mpp40         40       gpio, spi(cs1), uart2(cts), lcd(vga-hsync), vdd(cpu1-pd),
-                       pcie(clkreq0)
+mpp40         40       gpio, spi(cs1), uart2(cts), lcd(vga-hsync), pcie(clkreq0)
 mpp41         41       gpio, spi(cs2), uart2(rts), lcd(vga-vsync), sata1(prsnt),
                        pcie(clkreq1)
-mpp42         42       gpio, uart2(rxd), uart0(cts), tdm(int7), tdm-1(timer),
-                       vdd(cpu0-pd)
-mpp43         43       gpio, uart2(txd), uart0(rts), spi(cs3), pcie(rstout),
-                       vdd(cpu2-3-pd){1}
+mpp42         42       gpio, uart2(rxd), uart0(cts), tdm(int7), tdm-1(timer)
+mpp43         43       gpio, uart2(txd), uart0(rts), spi(cs3), pcie(rstout)
 mpp44         44       gpio, uart2(cts), uart3(rxd), spi(cs4), pcie(clkreq2),
                        mem(bat)
 mpp45         45       gpio, uart2(rts), uart3(txd), spi(cs5), sata1(prsnt)
 mpp46         46       gpio, uart3(rts), uart1(rts), spi(cs6), sata0(prsnt)
 mpp47         47       gpio, uart3(cts), uart1(cts), spi(cs7), pcie(clkreq3),
                        ref(clkout)
-mpp48         48       gpio, tclk, dev(burst/last)
+mpp48         48       gpio, dev(clkout), dev(burst/last)
 
 * Marvell Armada XP (mv78260 and mv78460 only)
 
@@ -84,9 +81,9 @@ mpp51         51       gpio, dev(ad16)
 mpp52         52       gpio, dev(ad17)
 mpp53         53       gpio, dev(ad18)
 mpp54         54       gpio, dev(ad19)
-mpp55         55       gpio, dev(ad20), vdd(cpu0-pd)
-mpp56         56       gpio, dev(ad21), vdd(cpu1-pd)
-mpp57         57       gpio, dev(ad22), vdd(cpu2-3-pd){1}
+mpp55         55       gpio, dev(ad20)
+mpp56         56       gpio, dev(ad21)
+mpp57         57       gpio, dev(ad22)
 mpp58         58       gpio, dev(ad23)
 mpp59         59       gpio, dev(ad24)
 mpp60         60       gpio, dev(ad25)
@@ -96,6 +93,3 @@ mpp63         63       gpio, dev(ad28)
 mpp64         64       gpio, dev(ad29)
 mpp65         65       gpio, dev(ad30)
 mpp66         66       gpio, dev(ad31)
-
-Notes:
-* {1} vdd(cpu2-3-pd) only available on mv78460.
diff --git a/Documentation/devicetree/bindings/spi/spi_pl022.txt b/Documentation/devicetree/bindings/spi/spi_pl022.txt
index 22ed6797216..4d1673ca8cf 100644
--- a/Documentation/devicetree/bindings/spi/spi_pl022.txt
+++ b/Documentation/devicetree/bindings/spi/spi_pl022.txt
@@ -4,9 +4,9 @@ Required properties:
 - compatible : "arm,pl022", "arm,primecell"
 - reg : Offset and length of the register set for the device
 - interrupts : Should contain SPI controller interrupt
+- num-cs : total number of chipselects
 
 Optional properties:
-- num-cs : total number of chipselects
 - cs-gpios : should specify GPIOs used for chipselects.
   The gpios will be referred to as reg = <index> in the SPI child nodes.
   If unspecified, a single SPI device without a chip select can be used.
diff --git a/Documentation/devicetree/bindings/thermal/thermal.txt b/Documentation/devicetree/bindings/thermal/thermal.txt
index f5db6b72a36..99d6608c9d5 100644
--- a/Documentation/devicetree/bindings/thermal/thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/thermal.txt
@@ -167,6 +167,13 @@ Optional property:
 			by means of sensor ID. Additional coefficients are
 			interpreted as constant offset.
 
+- sustainable-power:	An estimate of the sustainable power (in mW) that the
+  Type: unsigned	thermal zone can dissipate at the desired
+  Size: one cell	control temperature.  For reference, the
+			sustainable power of a 4'' phone is typically
+			2000mW, while on a 10'' tablet is around
+			4500mW.
+
 Note: The delay properties are bound to the maximum dT/dt (temperature
 derivative over time) in two situations for a thermal zone:
 (i)  - when passive cooling is activated (polling-delay-passive); and
@@ -546,6 +553,8 @@ thermal-zones {
 		 */
 		coefficients =		<1200	-345	890>;
 
+		sustainable-power = <2500>;
+
 		trips {
 			/* Trips are based on resulting linear equation */
 			cpu-trip: cpu-trip {
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index eb8a10e22f7..e2def60b346 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -369,6 +369,8 @@ is not associated with a file:
  [stack:1001]             = the stack of the thread with tid 1001
  [vdso]                   = the "virtual dynamic shared object",
                             the kernel system call handler
+ [anon:<name>]            = an anonymous mapping that has been
+                            named by userspace
 
  or if empty, the mapping is anonymous.
 
@@ -419,6 +421,7 @@ KernelPageSize:        4 kB
 MMUPageSize:           4 kB
 Locked:              374 kB
 VmFlags: rd ex mr mw me de
+Name:           name from userspace
 
 the first of these lines shows the same information as is displayed for the
 mapping in /proc/PID/maps.  The remaining lines show the size of the mapping
@@ -470,6 +473,9 @@ Note that there is no guarantee that every flag and associated mnemonic will
 be present in all further kernel releases. Things get changed, the flags may
 be vanished or the reverse -- new added.
 
+The "Name" field will only be present on a mapping that has been named by
+userspace, and will show the name passed in by userspace.
+
 This file is only present if the CONFIG_MMU kernel configuration option is
 enabled.
 
@@ -488,6 +494,10 @@ To clear the bits for the file mapped pages associated with the process
 To clear the soft-dirty bit
     > echo 4 > /proc/PID/clear_refs
 
+To reset the peak resident set size ("high water mark") to the process's
+current value:
+    > echo 5 > /proc/PID/clear_refs
+
 Any other value written to /proc/PID/clear_refs will have no effect.
 
 The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 479f33204a3..80f1e7def67 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1270,6 +1270,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	i8042.notimeout	[HW] Ignore timeout condition signalled by controller
 	i8042.reset	[HW] Reset the controller during init and cleanup
 	i8042.unlock	[HW] Unlock (ignore) the keylock
+	i8042.kbdreset  [HW] Reset device connected to KBD port
 
 	i810=		[HW,DRM]
 
@@ -1489,6 +1490,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	ip=		[IP_PNP]
 			See Documentation/filesystems/nfs/nfsroot.txt.
 
+	irqaffinity=	[SMP] Set the default irq affinity mask
+			Format:
+			<cpu number>,...,<cpu number>
+			or
+			<cpu number>-<cpu number>
+			(must be a positive range in ascending order)
+			or a mixture
+			<cpu number>,...,<cpu number>-<cpu number>
+
 	irqfixup	[HW]
 			When an interrupt is not handled search all handlers
 			for it. Intended to get systems with badly broken
@@ -3643,6 +3653,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 					READ_CAPACITY_16 command);
 				f = NO_REPORT_OPCODES (don't use report opcodes
 					command, uas only);
+				g = MAX_SECTORS_240 (don't transfer more than
+					240 sectors at a time, uas only);
 				h = CAPACITY_HEURISTICS (decrease the
 					reported device capacity by one
 					sector if the number is odd);
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index a476b08a43e..64a0fc5985d 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -60,7 +60,9 @@ fwmark_reflect - BOOLEAN
 	Controls the fwmark of kernel-generated IPv4 reply packets that are not
 	associated with a socket for example, TCP RSTs or ICMP echo replies).
 	If unset, these packets have a fwmark of zero. If set, they have the
-	fwmark of the packet they are replying to.
+	fwmark of the packet they are replying to. Similarly affects the fwmark
+	used by internal routing lookups triggered by incoming packets, such as
+	the ones used for Path MTU Discovery.
 	Default: 0
 
 route/max_size - INTEGER
@@ -516,6 +518,16 @@ tcp_fastopen - INTEGER
 
 	See include/net/tcp.h and the code for more details.
 
+tcp_fwmark_accept - BOOLEAN
+	If set, incoming connections to listening sockets that do not have a
+	socket mark will set the mark of the accepting socket to the fwmark of
+	the incoming SYN packet. This will cause all packets on that connection
+	(starting from the first SYNACK) to be sent with that fwmark. The
+	listening socket's mark is unchanged. Listening sockets that already
+	have a fwmark set via setsockopt(SOL_SOCKET, SO_MARK, ...) are
+	unaffected.
+	Default: 0
+
 tcp_syn_retries - INTEGER
 	Number of times initial SYNs for an active TCP connection attempt
 	will be retransmitted. Should not be higher than 255. Default value
@@ -1212,7 +1224,9 @@ fwmark_reflect - BOOLEAN
 	Controls the fwmark of kernel-generated IPv6 reply packets that are not
 	associated with a socket for example, TCP RSTs or ICMPv6 echo replies).
 	If unset, these packets have a fwmark of zero. If set, they have the
-	fwmark of the packet they are replying to.
+	fwmark of the packet they are replying to. Similarly affects the fwmark
+	used by internal routing lookups triggered by incoming packets, such as
+	the ones used for Path MTU Discovery.
 	Default: 0
 
 conf/interface/*:
@@ -1466,6 +1480,19 @@ suppress_frag_ndisc - INTEGER
 	1 - (default) discard fragmented neighbor discovery packets
 	0 - allow fragmented neighbor discovery packets
 
+optimistic_dad - BOOLEAN
+	Whether to perform Optimistic Duplicate Address Detection (RFC 4429).
+		0: disabled (default)
+		1: enabled
+
+use_optimistic - BOOLEAN
+	If enabled, do not classify optimistic addresses as deprecated during
+	source address selection.  Preferred addresses will still be chosen
+	before optimistic addresses, subject to other ranking in the source
+	address selection algorithm.
+		0: disabled (default)
+		1: enabled
+
 icmp/*:
 ratelimit - INTEGER
 	Limit the maximal rates for sending ICMPv6 packets.
diff --git a/Documentation/networking/rds.txt b/Documentation/networking/rds.txt
index c67077cbeb8..e1a3d59bbe0 100644
--- a/Documentation/networking/rds.txt
+++ b/Documentation/networking/rds.txt
@@ -62,11 +62,10 @@ Socket Interface
 ================
 
   AF_RDS, PF_RDS, SOL_RDS
-        These constants haven't been assigned yet, because RDS isn't in
-        mainline yet. Currently, the kernel module assigns some constant
-        and publishes it to user space through two sysctl files
-                /proc/sys/net/rds/pf_rds
-                /proc/sys/net/rds/sol_rds
+	AF_RDS and PF_RDS are the domain type to be used with socket(2)
+	to create RDS sockets. SOL_RDS is the socket-level to be used
+	with setsockopt(2) and getsockopt(2) for RDS specific socket
+	options.
 
   fd = socket(PF_RDS, SOCK_SEQPACKET, 0);
         This creates a new, unbound RDS socket.
diff --git a/Documentation/pinctrl.txt b/Documentation/pinctrl.txt
index b8f2147b96d..0df872a4105 100644
--- a/Documentation/pinctrl.txt
+++ b/Documentation/pinctrl.txt
@@ -72,7 +72,6 @@ static struct pinctrl_desc foo_desc = {
 	.name = "foo",
 	.pins = foo_pins,
 	.npins = ARRAY_SIZE(foo_pins),
-	.maxpin = 63,
 	.owner = THIS_MODULE,
 };
 
@@ -164,8 +163,8 @@ static const char *foo_get_group_name(struct pinctrl_dev *pctldev,
 }
 
 static int foo_get_group_pins(struct pinctrl_dev *pctldev, unsigned selector,
-			       unsigned ** const pins,
-			       unsigned * const num_pins)
+			       const unsigned **pins,
+			       unsigned *num_pins)
 {
 	*pins = (unsigned *) foo_groups[selector].pins;
 	*num_pins = foo_groups[selector].num_pins;
@@ -570,9 +569,8 @@ is possible to perform the requested mux setting, poke the hardware so that
 this happens.
 
 Pinmux drivers are required to supply a few callback functions, some are
-optional. Usually the enable() and disable() functions are implemented,
-writing values into some certain registers to activate a certain mux setting
-for a certain pin.
+optional. Usually the set_mux() function is implemented, writing values into
+some certain registers to activate a certain mux setting for a certain pin.
 
 A simple driver for the above example will work by setting bits 0, 1, 2, 3 or 4
 into some register named MUX to select a certain function with a certain
@@ -1266,7 +1264,7 @@ The semantics of the pinctrl APIs are:
 
 Usually the pin control core handled the get/put pair and call out to the
 device drivers bookkeeping operations, like checking available functions and
-the associated pins, whereas the enable/disable pass on to the pin controller
+the associated pins, whereas select_state pass on to the pin controller
 driver which takes care of activating and/or deactivating the mux setting by
 quickly poking some registers.
 
@@ -1363,8 +1361,9 @@ function, but with different named in the mapping as described under
 "Advanced mapping" above. So that for an SPI device, we have two states named
 "pos-A" and "pos-B".
 
-This snippet first muxes the function in the pins defined by group A, enables
-it, disables and releases it, and muxes it in on the pins defined by group B:
+This snippet first initializes a state object for both groups (in foo_probe()),
+then muxes the function in the pins defined by group A, and finally muxes it in
+on the pins defined by group B:
 
 #include <linux/pinctrl/consumer.h>
 
diff --git a/Documentation/ramoops.txt b/Documentation/ramoops.txt
index 69b3cac4749..5d8675615e5 100644
--- a/Documentation/ramoops.txt
+++ b/Documentation/ramoops.txt
@@ -14,11 +14,19 @@ 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:
+Ramoops uses a predefined memory area to store the dump. The start and size
+and type of the memory area are set using three variables:
   * "mem_address" for the start
   * "mem_size" for the size. The memory size will be rounded down to a
   power of two.
+  * "mem_type" to specifiy if the memory type (default is pgprot_writecombine).
+
+Typically the default value of mem_type=0 should be used as that sets the pstore
+mapping to pgprot_writecombine. Setting mem_type=1 attempts to use
+pgprot_noncached, which only works on some platforms. This is because pstore
+depends on atomic operations. At least on ARM, pgprot_noncached causes the
+memory to be mapped strongly ordered, and atomic operations on strongly ordered
+memory are implementation defined, and won't work on many ARMs such as omaps.
 
 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
@@ -55,6 +63,7 @@ Setting the ramoops parameters can be done in 2 different manners:
 static struct ramoops_platform_data ramoops_data = {
         .mem_size               = <...>,
         .mem_address            = <...>,
+        .mem_type               = <...>,
         .record_size            = <...>,
         .dump_oops              = <...>,
         .ecc                    = <...>,
diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt
index aee73e78c7d..3049a612291 100644
--- a/Documentation/stable_kernel_rules.txt
+++ b/Documentation/stable_kernel_rules.txt
@@ -32,18 +32,51 @@ Procedure for submitting patches to the -stable tree:
  - If the patch covers files in net/ or drivers/net please follow netdev stable
    submission guidelines as described in
    Documentation/networking/netdev-FAQ.txt
- - Send the patch, after verifying that it follows the above rules, to
-   stable@vger.kernel.org.  You must note the upstream commit ID in the
-   changelog of your submission, as well as the kernel version you wish
-   it to be applied to.
- - To have the patch automatically included in the stable tree, add the tag
+ - Security patches should not be handled (solely) by the -stable review
+   process but should follow the procedures in Documentation/SecurityBugs.
+
+For all other submissions, choose one of the following procedures:
+
+   --- Option 1 ---
+
+   To have the patch automatically included in the stable tree, add the tag
      Cc: stable@vger.kernel.org
    in the sign-off area. Once the patch is merged it will be applied to
    the stable tree without anything else needing to be done by the author
    or subsystem maintainer.
- - If the patch requires other patches as prerequisites which can be
-   cherry-picked, then this can be specified in the following format in
-   the sign-off area:
+
+   --- Option 2 ---
+
+   After the patch has been merged to Linus' tree, send an email to
+   stable@vger.kernel.org containing the subject of the patch, the commit ID,
+   why you think it should be applied, and what kernel version you wish it to
+   be applied to.
+
+   --- Option 3 ---
+
+   Send the patch, after verifying that it follows the above rules, to
+   stable@vger.kernel.org.  You must note the upstream commit ID in the
+   changelog of your submission, as well as the kernel version you wish
+   it to be applied to.
+
+Option 1 is *strongly* preferred, is the easiest and most common.  Options 2 and
+3 are more useful if the patch isn't deemed worthy at the time it is applied to
+a public git tree (for instance, because it deserves more regression testing
+first).  Option 3 is especially useful if the patch needs some special handling
+to apply to an older kernel (e.g., if API's have changed in the meantime).
+
+Note that for Option 3, if the patch deviates from the original upstream patch
+(for example because it had to be backported) this must be very clearly
+documented and justified in the patch description.
+
+The upstream commit ID must be specified with a separate line above the commit
+text, like this:
+
+    commit <sha1> upstream.
+
+Additionally, some patches submitted via Option 1 may have additional patch
+prerequisites which can be cherry-picked. This can be specified in the following
+format in the sign-off area:
 
      Cc: <stable@vger.kernel.org> # 3.3.x: a1f84a3: sched: Check for idle
      Cc: <stable@vger.kernel.org> # 3.3.x: 1b9508f: sched: Rate-limit newidle
@@ -57,13 +90,23 @@ Procedure for submitting patches to the -stable tree:
      git cherry-pick fd21073
      git cherry-pick <this commit>
 
+Also, some patches may have kernel version prerequisites.  This can be
+specified in the following format in the sign-off area:
+
+     Cc:  <stable@vger.kernel.org> # 3.3.x-
+
+   The tag has the meaning of:
+     git cherry-pick <this commit>
+
+   For each "-stable" tree starting with the specified version.
+
+Following the submission:
+
  - The sender will receive an ACK when the patch has been accepted into the
    queue, or a NAK if the patch is rejected.  This response might take a few
    days, according to the developer's schedules.
  - If accepted, the patch will be added to the -stable queue, for review by
    other developers and by the relevant subsystem maintainer.
- - Security patches should not be sent to this alias, but instead to the
-   documented security@kernel.org address.
 
 
 Review cycle:
diff --git a/Documentation/sync.txt b/Documentation/sync.txt
new file mode 100644
index 00000000000..a2d05e7fa19
--- /dev/null
+++ b/Documentation/sync.txt
@@ -0,0 +1,75 @@
+Motivation:
+
+In complicated DMA pipelines such as graphics (multimedia, camera, gpu, display)
+a consumer of a buffer needs to know when the producer has finished producing
+it.  Likewise the producer needs to know when the consumer is finished with the
+buffer so it can reuse it.  A particular buffer may be consumed by multiple
+consumers which will retain the buffer for different amounts of time.  In
+addition, a consumer may consume multiple buffers atomically.
+The sync framework adds an API which allows synchronization between the
+producers and consumers in a generic way while also allowing platforms which
+have shared hardware synchronization primitives to exploit them.
+
+Goals:
+	* provide a generic API for expressing synchronization dependencies
+	* allow drivers to exploit hardware synchronization between hardware
+	  blocks
+	* provide a userspace API that allows a compositor to manage
+	  dependencies.
+	* provide rich telemetry data to allow debugging slowdowns and stalls of
+	   the graphics pipeline.
+
+Objects:
+	* sync_timeline
+	* sync_pt
+	* sync_fence
+
+sync_timeline:
+
+A sync_timeline is an abstract monotonically increasing counter. In general,
+each driver/hardware block context will have one of these.  They can be backed
+by the appropriate hardware or rely on the generic sw_sync implementation.
+Timelines are only ever created through their specific implementations
+(i.e. sw_sync.)
+
+sync_pt:
+
+A sync_pt is an abstract value which marks a point on a sync_timeline. Sync_pts
+have a single timeline parent.  They have 3 states: active, signaled, and error.
+They start in active state and transition, once, to either signaled (when the
+timeline counter advances beyond the sync_pt’s value) or error state.
+
+sync_fence:
+
+Sync_fences are the primary primitives used by drivers to coordinate
+synchronization of their buffers.  They are a collection of sync_pts which may
+or may not have the same timeline parent.  A sync_pt can only exist in one fence
+and the fence's list of sync_pts is immutable once created.  Fences can be
+waited on synchronously or asynchronously.  Two fences can also be merged to
+create a third fence containing a copy of the two fences’ sync_pts.  Fences are
+backed by file descriptors to allow userspace to coordinate the display pipeline
+dependencies.
+
+Use:
+
+A driver implementing sync support should have a work submission function which:
+     * takes a fence argument specifying when to begin work
+     * asynchronously queues that work to kick off when the fence is signaled
+     * returns a fence to indicate when its work will be done.
+     * signals the returned fence once the work is completed.
+
+Consider an imaginary display driver that has the following API:
+/*
+ * assumes buf is ready to be displayed.
+ * blocks until the buffer is on screen.
+ */
+    void display_buffer(struct dma_buf *buf);
+
+The new API will become:
+/*
+ * will display buf when fence is signaled.
+ * returns immediately with a fence that will signal when buf
+ * is no longer displayed.
+ */
+struct sync_fence* display_buffer(struct dma_buf *buf,
+                                 struct sync_fence *fence);
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 4415aa91568..9aecaa51f73 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -29,6 +29,7 @@ Currently, these files are in /proc/sys/vm:
 - dirty_writeback_centisecs
 - drop_caches
 - extfrag_threshold
+- extra_free_kbytes
 - hugepages_treat_as_movable
 - hugetlb_shm_group
 - laptop_mode
@@ -225,6 +226,21 @@ fragmentation index is <= extfrag_threshold. The default value is 500.
 
 ==============================================================
 
+extra_free_kbytes
+
+This parameter tells the VM to keep extra free memory between the threshold
+where background reclaim (kswapd) kicks in, and the threshold where direct
+reclaim (by allocating processes) kicks in.
+
+This is useful for workloads that require low latency memory allocations
+and have a bounded burstiness in memory allocations, for example a
+realtime application that receives and transmits network traffic
+(causing in-kernel memory allocations) with a maximum total message burst
+size of 200MB may need 200MB of extra free memory to avoid direct reclaim
+related latencies.
+
+==============================================================
+
 hugepages_treat_as_movable
 
 This parameter controls whether we can allocate hugepages from ZONE_MOVABLE
diff --git a/Documentation/thermal/cpu-cooling-api.txt b/Documentation/thermal/cpu-cooling-api.txt
index fca24c931ec..71653584cd0 100644
--- a/Documentation/thermal/cpu-cooling-api.txt
+++ b/Documentation/thermal/cpu-cooling-api.txt
@@ -3,7 +3,7 @@ CPU cooling APIs How To
 
 Written by Amit Daniel Kachhap <amit.kachhap@linaro.org>
 
-Updated: 12 May 2012
+Updated: 6 Jan 2015
 
 Copyright (c)  2012 Samsung Electronics Co., Ltd(http://www.samsung.com)
 
@@ -25,8 +25,173 @@ the user. The registration APIs returns the cooling device pointer.
 
    clip_cpus: cpumask of cpus where the frequency constraints will happen.
 
-1.1.2 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
+1.1.2 struct thermal_cooling_device *of_cpufreq_cooling_register(
+	struct device_node *np, const struct cpumask *clip_cpus)
+
+    This interface function registers the cpufreq cooling device with
+    the name "thermal-cpufreq-%x" linking it with a device tree node, in
+    order to bind it via the thermal DT code. This api can support multiple
+    instances of cpufreq cooling devices.
+
+    np: pointer to the cooling device device tree node
+    clip_cpus: cpumask of cpus where the frequency constraints will happen.
+
+1.1.3 struct thermal_cooling_device *cpufreq_power_cooling_register(
+    const struct cpumask *clip_cpus, u32 capacitance,
+    get_static_t plat_static_func)
+
+Similar to cpufreq_cooling_register, this function registers a cpufreq
+cooling device.  Using this function, the cooling device will
+implement the power extensions by using a simple cpu power model.  The
+cpus must have registered their OPPs using the OPP library.
+
+The additional parameters are needed for the power model (See 2. Power
+models).  "capacitance" is the dynamic power coefficient (See 2.1
+Dynamic power).  "plat_static_func" is a function to calculate the
+static power consumed by these cpus (See 2.2 Static power).
+
+1.1.4 struct thermal_cooling_device *of_cpufreq_power_cooling_register(
+    struct device_node *np, const struct cpumask *clip_cpus, u32 capacitance,
+    get_static_t plat_static_func)
+
+Similar to cpufreq_power_cooling_register, this function register a
+cpufreq cooling device with power extensions using the device tree
+information supplied by the np parameter.
+
+1.1.5 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 
     This interface function unregisters the "thermal-cpufreq-%x" cooling device.
 
     cdev: Cooling device pointer which has to be unregistered.
+
+2. Power models
+
+The power API registration functions provide a simple power model for
+CPUs.  The current power is calculated as dynamic + (optionally)
+static power.  This power model requires that the operating-points of
+the CPUs are registered using the kernel's opp library and the
+`cpufreq_frequency_table` is assigned to the `struct device` of the
+cpu.  If you are using CONFIG_CPUFREQ_DT then the
+`cpufreq_frequency_table` should already be assigned to the cpu
+device.
+
+The `plat_static_func` parameter of `cpufreq_power_cooling_register()`
+and `of_cpufreq_power_cooling_register()` is optional.  If you don't
+provide it, only dynamic power will be considered.
+
+2.1 Dynamic power
+
+The dynamic power consumption of a processor depends on many factors.
+For a given processor implementation the primary factors are:
+
+- The time the processor spends running, consuming dynamic power, as
+  compared to the time in idle states where dynamic consumption is
+  negligible.  Herein we refer to this as 'utilisation'.
+- The voltage and frequency levels as a result of DVFS.  The DVFS
+  level is a dominant factor governing power consumption.
+- In running time the 'execution' behaviour (instruction types, memory
+  access patterns and so forth) causes, in most cases, a second order
+  variation.  In pathological cases this variation can be significant,
+  but typically it is of a much lesser impact than the factors above.
+
+A high level dynamic power consumption model may then be represented as:
+
+Pdyn = f(run) * Voltage^2 * Frequency * Utilisation
+
+f(run) here represents the described execution behaviour and its
+result has a units of Watts/Hz/Volt^2 (this often expressed in
+mW/MHz/uVolt^2)
+
+The detailed behaviour for f(run) could be modelled on-line.  However,
+in practice, such an on-line model has dependencies on a number of
+implementation specific processor support and characterisation
+factors.  Therefore, in initial implementation that contribution is
+represented as a constant coefficient.  This is a simplification
+consistent with the relative contribution to overall power variation.
+
+In this simplified representation our model becomes:
+
+Pdyn = Capacitance * Voltage^2 * Frequency * Utilisation
+
+Where `capacitance` is a constant that represents an indicative
+running time dynamic power coefficient in fundamental units of
+mW/MHz/uVolt^2.  Typical values for mobile CPUs might lie in range
+from 100 to 500.  For reference, the approximate values for the SoC in
+ARM's Juno Development Platform are 530 for the Cortex-A57 cluster and
+140 for the Cortex-A53 cluster.
+
+
+2.2 Static power
+
+Static leakage power consumption depends on a number of factors.  For a
+given circuit implementation the primary factors are:
+
+- Time the circuit spends in each 'power state'
+- Temperature
+- Operating voltage
+- Process grade
+
+The time the circuit spends in each 'power state' for a given
+evaluation period at first order means OFF or ON.  However,
+'retention' states can also be supported that reduce power during
+inactive periods without loss of context.
+
+Note: The visibility of state entries to the OS can vary, according to
+platform specifics, and this can then impact the accuracy of a model
+based on OS state information alone.  It might be possible in some
+cases to extract more accurate information from system resources.
+
+The temperature, operating voltage and process 'grade' (slow to fast)
+of the circuit are all significant factors in static leakage power
+consumption.  All of these have complex relationships to static power.
+
+Circuit implementation specific factors include the chosen silicon
+process as well as the type, number and size of transistors in both
+the logic gates and any RAM elements included.
+
+The static power consumption modelling must take into account the
+power managed regions that are implemented.  Taking the example of an
+ARM processor cluster, the modelling would take into account whether
+each CPU can be powered OFF separately or if only a single power
+region is implemented for the complete cluster.
+
+In one view, there are others, a static power consumption model can
+then start from a set of reference values for each power managed
+region (e.g. CPU, Cluster/L2) in each state (e.g. ON, OFF) at an
+arbitrary process grade, voltage and temperature point.  These values
+are then scaled for all of the following: the time in each state, the
+process grade, the current temperature and the operating voltage.
+However, since both implementation specific and complex relationships
+dominate the estimate, the appropriate interface to the model from the
+cpu cooling device is to provide a function callback that calculates
+the static power in this platform.  When registering the cpu cooling
+device pass a function pointer that follows the `get_static_t`
+prototype:
+
+    int plat_get_static(cpumask_t *cpumask, int interval,
+                        unsigned long voltage, u32 &power);
+
+`cpumask` is the cpumask of the cpus involved in the calculation.
+`voltage` is the voltage at which they are operating.  The function
+should calculate the average static power for the last `interval`
+milliseconds.  It returns 0 on success, -E* on error.  If it
+succeeds, it should store the static power in `power`.  Reading the
+temperature of the cpus described by `cpumask` is left for
+plat_get_static() to do as the platform knows best which thermal
+sensor is closest to the cpu.
+
+If `plat_static_func` is NULL, static power is considered to be
+negligible for this platform and only dynamic power is considered.
+
+The platform specific callback can then use any combination of tables
+and/or equations to permute the estimated value.  Process grade
+information is not passed to the model since access to such data, from
+on-chip measurement capability or manufacture time data, is platform
+specific.
+
+Note: the significance of static power for CPUs in comparison to
+dynamic power is highly dependent on implementation.  Given the
+potential complexity in implementation, the importance and accuracy of
+its inclusion when using cpu cooling devices should be assessed on a
+case by case basis.
+
diff --git a/Documentation/thermal/power_allocator.txt b/Documentation/thermal/power_allocator.txt
new file mode 100644
index 00000000000..c3797b52999
--- /dev/null
+++ b/Documentation/thermal/power_allocator.txt
@@ -0,0 +1,247 @@
+Power allocator governor tunables
+=================================
+
+Trip points
+-----------
+
+The governor requires the following two passive trip points:
+
+1.  "switch on" trip point: temperature above which the governor
+    control loop starts operating.  This is the first passive trip
+    point of the thermal zone.
+
+2.  "desired temperature" trip point: it should be higher than the
+    "switch on" trip point.  This the target temperature the governor
+    is controlling for.  This is the last passive trip point of the
+    thermal zone.
+
+PID Controller
+--------------
+
+The power allocator governor implements a
+Proportional-Integral-Derivative controller (PID controller) with
+temperature as the control input and power as the controlled output:
+
+    P_max = k_p * e + k_i * err_integral + k_d * diff_err + sustainable_power
+
+where
+    e = desired_temperature - current_temperature
+    err_integral is the sum of previous errors
+    diff_err = e - previous_error
+
+It is similar to the one depicted below:
+
+                                      k_d
+                                       |
+current_temp                           |
+     |                                 v
+     |                +----------+   +---+
+     |         +----->| diff_err |-->| X |------+
+     |         |      +----------+   +---+      |
+     |         |                                |      tdp        actor
+     |         |                      k_i       |       |  get_requested_power()
+     |         |                       |        |       |        |     |
+     |         |                       |        |       |        |     | ...
+     v         |                       v        v       v        v     v
+   +---+       |      +-------+      +---+    +---+   +---+   +----------+
+   | S |-------+----->| sum e |----->| X |--->| S |-->| S |-->|power     |
+   +---+       |      +-------+      +---+    +---+   +---+   |allocation|
+     ^         |                                ^             +----------+
+     |         |                                |                |     |
+     |         |        +---+                   |                |     |
+     |         +------->| X |-------------------+                v     v
+     |                  +---+                               granted performance
+desired_temperature       ^
+                          |
+                          |
+                      k_po/k_pu
+
+Sustainable power
+-----------------
+
+An estimate of the sustainable dissipatable power (in mW) should be
+provided while registering the thermal zone.  This estimates the
+sustained power that can be dissipated at the desired control
+temperature.  This is the maximum sustained power for allocation at
+the desired maximum temperature.  The actual sustained power can vary
+for a number of reasons.  The closed loop controller will take care of
+variations such as environmental conditions, and some factors related
+to the speed-grade of the silicon.  `sustainable_power` is therefore
+simply an estimate, and may be tuned to affect the aggressiveness of
+the thermal ramp. For reference, the sustainable power of a 4" phone
+is typically 2000mW, while on a 10" tablet is around 4500mW (may vary
+depending on screen size).
+
+If you are using device tree, do add it as a property of the
+thermal-zone.  For example:
+
+	thermal-zones {
+		soc_thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <100>;
+			sustainable-power = <2500>;
+			...
+
+Instead, if the thermal zone is registered from the platform code, pass a
+`thermal_zone_params` that has a `sustainable_power`.  If no
+`thermal_zone_params` were being passed, then something like below
+will suffice:
+
+	static const struct thermal_zone_params tz_params = {
+		.sustainable_power = 3500,
+	};
+
+and then pass `tz_params` as the 5th parameter to
+`thermal_zone_device_register()`
+
+k_po and k_pu
+-------------
+
+The implementation of the PID controller in the power allocator
+thermal governor allows the configuration of two proportional term
+constants: `k_po` and `k_pu`.  `k_po` is the proportional term
+constant during temperature overshoot periods (current temperature is
+above "desired temperature" trip point).  Conversely, `k_pu` is the
+proportional term constant during temperature undershoot periods
+(current temperature below "desired temperature" trip point).
+
+These controls are intended as the primary mechanism for configuring
+the permitted thermal "ramp" of the system.  For instance, a lower
+`k_pu` value will provide a slower ramp, at the cost of capping
+available capacity at a low temperature.  On the other hand, a high
+value of `k_pu` will result in the governor granting very high power
+whilst temperature is low, and may lead to temperature overshooting.
+
+The default value for `k_pu` is:
+
+    2 * sustainable_power / (desired_temperature - switch_on_temp)
+
+This means that at `switch_on_temp` the output of the controller's
+proportional term will be 2 * `sustainable_power`.  The default value
+for `k_po` is:
+
+    sustainable_power / (desired_temperature - switch_on_temp)
+
+Focusing on the proportional and feed forward values of the PID
+controller equation we have:
+
+    P_max = k_p * e + sustainable_power
+
+The proportional term is proportional to the difference between the
+desired temperature and the current one.  When the current temperature
+is the desired one, then the proportional component is zero and
+`P_max` = `sustainable_power`.  That is, the system should operate in
+thermal equilibrium under constant load.  `sustainable_power` is only
+an estimate, which is the reason for closed-loop control such as this.
+
+Expanding `k_pu` we get:
+    P_max = 2 * sustainable_power * (T_set - T) / (T_set - T_on) +
+        sustainable_power
+
+where
+    T_set is the desired temperature
+    T is the current temperature
+    T_on is the switch on temperature
+
+When the current temperature is the switch_on temperature, the above
+formula becomes:
+
+    P_max = 2 * sustainable_power * (T_set - T_on) / (T_set - T_on) +
+        sustainable_power = 2 * sustainable_power + sustainable_power =
+        3 * sustainable_power
+
+Therefore, the proportional term alone linearly decreases power from
+3 * `sustainable_power` to `sustainable_power` as the temperature
+rises from the switch on temperature to the desired temperature.
+
+k_i and integral_cutoff
+-----------------------
+
+`k_i` configures the PID loop's integral term constant.  This term
+allows the PID controller to compensate for long term drift and for
+the quantized nature of the output control: cooling devices can't set
+the exact power that the governor requests.  When the temperature
+error is below `integral_cutoff`, errors are accumulated in the
+integral term.  This term is then multiplied by `k_i` and the result
+added to the output of the controller.  Typically `k_i` is set low (1
+or 2) and `integral_cutoff` is 0.
+
+k_d
+---
+
+`k_d` configures the PID loop's derivative term constant.  It's
+recommended to leave it as the default: 0.
+
+Cooling device power API
+========================
+
+Cooling devices controlled by this governor must supply the additional
+"power" API in their `cooling_device_ops`.  It consists on three ops:
+
+1. int get_requested_power(struct thermal_cooling_device *cdev,
+	struct thermal_zone_device *tz, u32 *power);
+@cdev: The `struct thermal_cooling_device` pointer
+@tz: thermal zone in which we are currently operating
+@power: pointer in which to store the calculated power
+
+`get_requested_power()` calculates the power requested by the device
+in milliwatts and stores it in @power .  It should return 0 on
+success, -E* on failure.  This is currently used by the power
+allocator governor to calculate how much power to give to each cooling
+device.
+
+2. int state2power(struct thermal_cooling_device *cdev, struct
+        thermal_zone_device *tz, unsigned long state, u32 *power);
+@cdev: The `struct thermal_cooling_device` pointer
+@tz: thermal zone in which we are currently operating
+@state: A cooling device state
+@power: pointer in which to store the equivalent power
+
+Convert cooling device state @state into power consumption in
+milliwatts and store it in @power.  It should return 0 on success, -E*
+on failure.  This is currently used by thermal core to calculate the
+maximum power that an actor can consume.
+
+3. int power2state(struct thermal_cooling_device *cdev, u32 power,
+	unsigned long *state);
+@cdev: The `struct thermal_cooling_device` pointer
+@power: power in milliwatts
+@state: pointer in which to store the resulting state
+
+Calculate a cooling device state that would make the device consume at
+most @power mW and store it in @state.  It should return 0 on success,
+-E* on failure.  This is currently used by the thermal core to convert
+a given power set by the power allocator governor to a state that the
+cooling device can set.  It is a function because this conversion may
+depend on external factors that may change so this function should the
+best conversion given "current circumstances".
+
+Cooling device weights
+----------------------
+
+Weights are a mechanism to bias the allocation among cooling
+devices.  They express the relative power efficiency of different
+cooling devices.  Higher weight can be used to express higher power
+efficiency.  Weighting is relative such that if each cooling device
+has a weight of one they are considered equal.  This is particularly
+useful in heterogeneous systems where two cooling devices may perform
+the same kind of compute, but with different efficiency.  For example,
+a system with two different types of processors.
+
+If the thermal zone is registered using
+`thermal_zone_device_register()` (i.e., platform code), then weights
+are passed as part of the thermal zone's `thermal_bind_parameters`.
+If the platform is registered using device tree, then they are passed
+as the `contribution` property of each map in the `cooling-maps` node.
+
+Limitations of the power allocator governor
+===========================================
+
+The power allocator governor's PID controller works best if there is a
+periodic tick.  If you have a driver that calls
+`thermal_zone_device_update()` (or anything that ends up calling the
+governor's `throttle()` function) repetitively, the governor response
+won't be very good.  Note that this is not particular to this
+governor, step-wise will also misbehave if you call its throttle()
+faster than the normal thermal framework tick (due to interrupts for
+example) as it will overreact.
diff --git a/Documentation/thermal/sysfs-api.txt b/Documentation/thermal/sysfs-api.txt
index 87519cb379e..c1f6864a8c5 100644
--- a/Documentation/thermal/sysfs-api.txt
+++ b/Documentation/thermal/sysfs-api.txt
@@ -95,7 +95,7 @@ temperature) and throttle appropriate devices.
 1.3 interface for binding a thermal zone device with a thermal cooling device
 1.3.1 int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz,
 	int trip, struct thermal_cooling_device *cdev,
-	unsigned long upper, unsigned long lower);
+	unsigned long upper, unsigned long lower, unsigned int weight);
 
     This interface function bind a thermal cooling device to the certain trip
     point of a thermal zone device.
@@ -110,6 +110,8 @@ temperature) and throttle appropriate devices.
     lower:the Minimum cooling state can be used for this trip point.
           THERMAL_NO_LIMIT means no lower limit,
 	  and the cooling device can be in cooling state 0.
+    weight: the influence of this cooling device in this thermal
+            zone.  See 1.4.1 below for more information.
 
 1.3.2 int thermal_zone_unbind_cooling_device(struct thermal_zone_device *tz,
 		int trip, struct thermal_cooling_device *cdev);
@@ -127,9 +129,15 @@ temperature) and throttle appropriate devices.
     This structure defines the following parameters that are used to bind
     a zone with a cooling device for a particular trip point.
     .cdev: The cooling device pointer
-    .weight: The 'influence' of a particular cooling device on this zone.
-             This is on a percentage scale. The sum of all these weights
-             (for a particular zone) cannot exceed 100.
+    .weight: The 'influence' of a particular cooling device on this
+             zone. This is relative to the rest of the cooling
+             devices. For example, if all cooling devices have a
+             weight of 1, then they all contribute the same. You can
+             use percentages if you want, but it's not mandatory. A
+             weight of 0 means that this cooling device doesn't
+             contribute to the cooling of this zone unless all cooling
+             devices have a weight of 0. If all weights are 0, then
+             they all contribute the same.
     .trip_mask:This is a bit mask that gives the binding relation between
                this thermal zone and cdev, for a particular trip point.
                If nth bit is set, then the cdev and thermal zone are bound
@@ -176,6 +184,14 @@ Thermal zone device sys I/F, created once it's registered:
     |---trip_point_[0-*]_type:	Trip point type
     |---trip_point_[0-*]_hyst:	Hysteresis value for this trip point
     |---emul_temp:		Emulated temperature set node
+    |---sustainable_power:      Sustainable dissipatable power
+    |---k_po:                   Proportional term during temperature overshoot
+    |---k_pu:                   Proportional term during temperature undershoot
+    |---k_i:                    PID's integral term in the power allocator gov
+    |---k_d:                    PID's derivative term in the power allocator
+    |---integral_cutoff:        Offset above which errors are accumulated
+    |---slope:                  Slope constant applied as linear extrapolation
+    |---offset:                 Offset constant applied as linear extrapolation
 
 Thermal cooling device sys I/F, created once it's registered:
 /sys/class/thermal/cooling_device[0-*]:
@@ -192,6 +208,8 @@ thermal_zone_bind_cooling_device/thermal_zone_unbind_cooling_device.
 /sys/class/thermal/thermal_zone[0-*]:
     |---cdev[0-*]:		[0-*]th cooling device in current thermal zone
     |---cdev[0-*]_trip_point:	Trip point that cdev[0-*] is associated with
+    |---cdev[0-*]_weight:       Influence of the cooling device in
+                                this thermal zone
 
 Besides the thermal zone device sysfs I/F and cooling device sysfs I/F,
 the generic thermal driver also creates a hwmon sysfs I/F for each _type_
@@ -265,6 +283,14 @@ cdev[0-*]_trip_point
 	point.
 	RO, Optional
 
+cdev[0-*]_weight
+        The influence of cdev[0-*] in this thermal zone. This value
+        is relative to the rest of cooling devices in the thermal
+        zone. For example, if a cooling device has a weight double
+        than that of other, it's twice as effective in cooling the
+        thermal zone.
+        RW, Optional
+
 passive
 	Attribute is only present for zones in which the passive cooling
 	policy is not supported by native thermal driver. Default is zero
@@ -289,6 +315,66 @@ emul_temp
 	  because userland can easily disable the thermal policy by simply
 	  flooding this sysfs node with low temperature values.
 
+sustainable_power
+	An estimate of the sustained power that can be dissipated by
+	the thermal zone. Used by the power allocator governor. For
+	more information see Documentation/thermal/power_allocator.txt
+	Unit: milliwatts
+	RW, Optional
+
+k_po
+	The proportional term of the power allocator governor's PID
+	controller during temperature overshoot. Temperature overshoot
+	is when the current temperature is above the "desired
+	temperature" trip point. For more information see
+	Documentation/thermal/power_allocator.txt
+	RW, Optional
+
+k_pu
+	The proportional term of the power allocator governor's PID
+	controller during temperature undershoot. Temperature undershoot
+	is when the current temperature is below the "desired
+	temperature" trip point. For more information see
+	Documentation/thermal/power_allocator.txt
+	RW, Optional
+
+k_i
+	The integral term of the power allocator governor's PID
+	controller. This term allows the PID controller to compensate
+	for long term drift. For more information see
+	Documentation/thermal/power_allocator.txt
+	RW, Optional
+
+k_d
+	The derivative term of the power allocator governor's PID
+	controller. For more information see
+	Documentation/thermal/power_allocator.txt
+	RW, Optional
+
+integral_cutoff
+	Temperature offset from the desired temperature trip point
+	above which the integral term of the power allocator
+	governor's PID controller starts accumulating errors. For
+	example, if integral_cutoff is 0, then the integral term only
+	accumulates error when temperature is above the desired
+	temperature trip point. For more information see
+	Documentation/thermal/power_allocator.txt
+	RW, Optional
+
+slope
+	The slope constant used in a linear extrapolation model
+	to determine a hotspot temperature based off the sensor's
+	raw readings. It is up to the device driver to determine
+	the usage of these values.
+	RW, Optional
+
+offset
+	The offset constant used in a linear extrapolation model
+	to determine a hotspot temperature based off the sensor's
+	raw readings. It is up to the device driver to determine
+	the usage of these values.
+	RW, Optional
+
 *****************************
 * Cooling device attributes *
 *****************************
@@ -318,7 +404,8 @@ passive, active. If an ACPI thermal zone supports critical, passive,
 active[0] and active[1] at the same time, it may register itself as a
 thermal_zone_device (thermal_zone1) with 4 trip points in all.
 It has one processor and one fan, which are both registered as
-thermal_cooling_device.
+thermal_cooling_device. Both are considered to have the same
+effectiveness in cooling the thermal zone.
 
 If the processor is listed in _PSL method, and the fan is listed in _AL0
 method, the sys I/F structure will be built like this:
@@ -340,8 +427,10 @@ method, the sys I/F structure will be built like this:
     |---trip_point_3_type:	active1
     |---cdev0:			--->/sys/class/thermal/cooling_device0
     |---cdev0_trip_point:	1	/* cdev0 can be used for passive */
+    |---cdev0_weight:           1024
     |---cdev1:			--->/sys/class/thermal/cooling_device3
     |---cdev1_trip_point:	2	/* cdev1 can be used for active[0]*/
+    |---cdev1_weight:           1024
 
 |cooling_device0:
     |---type:			Processor
diff --git a/Documentation/trace/coresight.txt b/Documentation/trace/coresight.txt
new file mode 100644
index 00000000000..77d14d51a67
--- /dev/null
+++ b/Documentation/trace/coresight.txt
@@ -0,0 +1,299 @@
+		Coresight - HW Assisted Tracing on ARM
+		======================================
+
+   Author:   Mathieu Poirier <mathieu.poirier@linaro.org>
+   Date:     September 11th, 2014
+
+Introduction
+------------
+
+Coresight is an umbrella of technologies allowing for the debugging of ARM
+based SoC.  It includes solutions for JTAG and HW assisted tracing.  This
+document is concerned with the latter.
+
+HW assisted tracing is becoming increasingly useful when dealing with systems
+that have many SoCs and other components like GPU and DMA engines.  ARM has
+developed a HW assisted tracing solution by means of different components, each
+being added to a design at synthesis time to cater to specific tracing needs.
+Compoments are generally categorised as source, link and sinks and are
+(usually) discovered using the AMBA bus.
+
+"Sources" generate a compressed stream representing the processor instruction
+path based on tracing scenarios as configured by users.  From there the stream
+flows through the coresight system (via ATB bus) using links that are connecting
+the emanating source to a sink(s).  Sinks serve as endpoints to the coresight
+implementation, either storing the compressed stream in a memory buffer or
+creating an interface to the outside world where data can be transferred to a
+host without fear of filling up the onboard coresight memory buffer.
+
+At typical coresight system would look like this:
+
+  *****************************************************************
+ **************************** AMBA AXI  ****************************===||
+  *****************************************************************    ||
+        ^                    ^                            |            ||
+        |                    |                            *            **
+     0000000    :::::     0000000    :::::    :::::    @@@@@@@    ||||||||||||
+     0 CPU 0<-->: C :     0 CPU 0<-->: C :    : C :    @ STM @    || System ||
+  |->0000000    : T :  |->0000000    : T :    : T :<--->@@@@@     || Memory ||
+  |  #######<-->: I :  |  #######<-->: I :    : I :      @@@<-|   ||||||||||||
+  |  # ETM #    :::::  |  # PTM #    :::::    :::::       @   |
+  |   #####      ^ ^   |   #####      ^ !      ^ !        .   |   |||||||||
+  | |->###       | !   | |->###       | !      | !        .   |   || DAP ||
+  | |   #        | !   | |   #        | !      | !        .   |   |||||||||
+  | |   .        | !   | |   .        | !      | !        .   |      |  |
+  | |   .        | !   | |   .        | !      | !        .   |      |  *
+  | |   .        | !   | |   .        | !      | !        .   |      | SWD/
+  | |   .        | !   | |   .        | !      | !        .   |      | JTAG
+  *****************************************************************<-|
+ *************************** AMBA Debug APB ************************
+  *****************************************************************
+   |    .          !         .          !        !        .    |
+   |    .          *         .          *        *        .    |
+  *****************************************************************
+ ******************** Cross Trigger Matrix (CTM) *******************
+  *****************************************************************
+   |    .     ^              .                            .    |
+   |    *     !              *                            *    |
+  *****************************************************************
+ ****************** AMBA Advanced Trace Bus (ATB) ******************
+  *****************************************************************
+   |          !                        ===============         |
+   |          *                         ===== F =====<---------|
+   |   :::::::::                         ==== U ====
+   |-->:: CTI ::<!!                       === N ===
+   |   :::::::::  !                        == N ==
+   |    ^         *                        == E ==
+   |    !  &&&&&&&&&       IIIIIII         == L ==
+   |------>&& ETB &&<......II     I        =======
+   |    !  &&&&&&&&&       II     I           .
+   |    !                    I     I          .
+   |    !                    I REP I<..........
+   |    !                    I     I
+   |    !!>&&&&&&&&&       II     I           *Source: ARM ltd.
+   |------>& TPIU  &<......II    I            DAP = Debug Access Port
+           &&&&&&&&&       IIIIIII            ETM = Embedded Trace Macrocell
+               ;                              PTM = Program Trace Macrocell
+               ;                              CTI = Cross Trigger Interface
+               *                              ETB = Embedded Trace Buffer
+          To trace port                       TPIU= Trace Port Interface Unit
+                                              SWD = Serial Wire Debug
+
+While on target configuration of the components is done via the APB bus,
+all trace data are carried out-of-band on the ATB bus.  The CTM provides
+a way to aggregate and distribute signals between CoreSight components.
+
+The coresight framework provides a central point to represent, configure and
+manage coresight devices on a platform.  This first implementation centers on
+the basic tracing functionality, enabling components such ETM/PTM, funnel,
+replicator, TMC, TPIU and ETB.  Future work will enable more
+intricate IP blocks such as STM and CTI.
+
+
+Acronyms and Classification
+---------------------------
+
+Acronyms:
+
+PTM:     Program Trace Macrocell
+ETM:     Embedded Trace Macrocell
+STM:     System trace Macrocell
+ETB:     Embedded Trace Buffer
+ITM:     Instrumentation Trace Macrocell
+TPIU:    Trace Port Interface Unit
+TMC-ETR: Trace Memory Controller, configured as Embedded Trace Router
+TMC-ETF: Trace Memory Controller, configured as Embedded Trace FIFO
+CTI:     Cross Trigger Interface
+
+Classification:
+
+Source:
+   ETMv3.x ETMv4, PTMv1.0, PTMv1.1, STM, STM500, ITM
+Link:
+   Funnel, replicator (intelligent or not), TMC-ETR
+Sinks:
+   ETBv1.0, ETB1.1, TPIU, TMC-ETF
+Misc:
+   CTI
+
+
+Device Tree Bindings
+----------------------
+
+See Documentation/devicetree/bindings/arm/coresight.txt for details.
+
+As of this writing drivers for ITM, STMs and CTIs are not provided but are
+expected to be added as the solution matures.
+
+
+Framework and implementation
+----------------------------
+
+The coresight framework provides a central point to represent, configure and
+manage coresight devices on a platform.  Any coresight compliant device can
+register with the framework for as long as they use the right APIs:
+
+struct coresight_device *coresight_register(struct coresight_desc *desc);
+void coresight_unregister(struct coresight_device *csdev);
+
+The registering function is taking a "struct coresight_device *csdev" and
+register the device with the core framework.  The unregister function takes
+a reference to a "strut coresight_device", obtained at registration time.
+
+If everything goes well during the registration process the new devices will
+show up under /sys/bus/coresight/devices, as showns here for a TC2 platform:
+
+root:~# ls /sys/bus/coresight/devices/
+replicator  20030000.tpiu    2201c000.ptm  2203c000.etm  2203e000.etm
+20010000.etb         20040000.funnel  2201d000.ptm  2203d000.etm
+root:~#
+
+The functions take a "struct coresight_device", which looks like this:
+
+struct coresight_desc {
+        enum coresight_dev_type type;
+        struct coresight_dev_subtype subtype;
+        const struct coresight_ops *ops;
+        struct coresight_platform_data *pdata;
+        struct device *dev;
+        const struct attribute_group **groups;
+};
+
+
+The "coresight_dev_type" identifies what the device is, i.e, source link or
+sink while the "coresight_dev_subtype" will characterise that type further.
+
+The "struct coresight_ops" is mandatory and will tell the framework how to
+perform base operations related to the components, each component having
+a different set of requirement.  For that "struct coresight_ops_sink",
+"struct coresight_ops_link" and "struct coresight_ops_source" have been
+provided.
+
+The next field, "struct coresight_platform_data *pdata" is acquired by calling
+"of_get_coresight_platform_data()", as part of the driver's _probe routine and
+"struct device *dev" gets the device reference embedded in the "amba_device":
+
+static int etm_probe(struct amba_device *adev, const struct amba_id *id)
+{
+ ...
+ ...
+ drvdata->dev = &adev->dev;
+ ...
+}
+
+Specific class of device (source, link, or sink) have generic operations
+that can be performed on them (see "struct coresight_ops").  The
+"**groups" is a list of sysfs entries pertaining to operations
+specific to that component only.  "Implementation defined" customisations are
+expected to be accessed and controlled using those entries.
+
+Last but not least, "struct module *owner" is expected to be set to reflect
+the information carried in "THIS_MODULE".
+
+How to use
+----------
+
+Before trace collection can start, a coresight sink needs to be identify.
+There is no limit on the amount of sinks (nor sources) that can be enabled at
+any given moment.  As a generic operation, all device pertaining to the sink
+class will have an "active" entry in sysfs:
+
+root:/sys/bus/coresight/devices# ls
+replicator  20030000.tpiu    2201c000.ptm  2203c000.etm  2203e000.etm
+20010000.etb         20040000.funnel  2201d000.ptm  2203d000.etm
+root:/sys/bus/coresight/devices# ls 20010000.etb
+enable_sink  status  trigger_cntr
+root:/sys/bus/coresight/devices# echo 1 > 20010000.etb/enable_sink
+root:/sys/bus/coresight/devices# cat 20010000.etb/enable_sink
+1
+root:/sys/bus/coresight/devices#
+
+At boot time the current etm3x driver will configure the first address
+comparator with "_stext" and "_etext", essentially tracing any instruction
+that falls within that range.  As such "enabling" a source will immediately
+trigger a trace capture:
+
+root:/sys/bus/coresight/devices# echo 1 > 2201c000.ptm/enable_source
+root:/sys/bus/coresight/devices# cat 2201c000.ptm/enable_source
+1
+root:/sys/bus/coresight/devices# cat 20010000.etb/status
+Depth:          0x2000
+Status:         0x1
+RAM read ptr:   0x0
+RAM wrt ptr:    0x19d3   <----- The write pointer is moving
+Trigger cnt:    0x0
+Control:        0x1
+Flush status:   0x0
+Flush ctrl:     0x2001
+root:/sys/bus/coresight/devices#
+
+Trace collection is stopped the same way:
+
+root:/sys/bus/coresight/devices# echo 0 > 2201c000.ptm/enable_source
+root:/sys/bus/coresight/devices#
+
+The content of the ETB buffer can be harvested directly from /dev:
+
+root:/sys/bus/coresight/devices# dd if=/dev/20010000.etb \
+of=~/cstrace.bin
+
+64+0 records in
+64+0 records out
+32768 bytes (33 kB) copied, 0.00125258 s, 26.2 MB/s
+root:/sys/bus/coresight/devices#
+
+The file cstrace.bin can be decompressed using "ptm2human", DS-5 or Trace32.
+
+Following is a DS-5 output of an experimental loop that increments a variable up
+to a certain value.  The example is simple and yet provides a glimpse of the
+wealth of possibilities that coresight provides.
+
+Info                                    Tracing enabled
+Instruction     106378866       0x8026B53C      E52DE004        false   PUSH     {lr}
+Instruction     0       0x8026B540      E24DD00C        false   SUB      sp,sp,#0xc
+Instruction     0       0x8026B544      E3A03000        false   MOV      r3,#0
+Instruction     0       0x8026B548      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Timestamp                                       Timestamp: 17106715833
+Instruction     319     0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Instruction     9       0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Instruction     7       0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Instruction     7       0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Instruction     10      0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Instruction     6       0x8026B560      EE1D3F30        false   MRC      p15,#0x0,r3,c13,c0,#1
+Instruction     0       0x8026B564      E1A0100D        false   MOV      r1,sp
+Instruction     0       0x8026B568      E3C12D7F        false   BIC      r2,r1,#0x1fc0
+Instruction     0       0x8026B56C      E3C2203F        false   BIC      r2,r2,#0x3f
+Instruction     0       0x8026B570      E59D1004        false   LDR      r1,[sp,#4]
+Instruction     0       0x8026B574      E59F0010        false   LDR      r0,[pc,#16] ; [0x8026B58C] = 0x80550368
+Instruction     0       0x8026B578      E592200C        false   LDR      r2,[r2,#0xc]
+Instruction     0       0x8026B57C      E59221D0        false   LDR      r2,[r2,#0x1d0]
+Instruction     0       0x8026B580      EB07A4CF        true    BL       {pc}+0x1e9344 ; 0x804548c4
+Info                                    Tracing enabled
+Instruction     13570831        0x8026B584      E28DD00C        false   ADD      sp,sp,#0xc
+Instruction     0       0x8026B588      E8BD8000        true    LDM      sp!,{pc}
+Timestamp                                       Timestamp: 17107041535
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index 4da42616939..0344f76da57 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -2043,6 +2043,35 @@ will produce:
  1)   1.449 us    |             }
 
 
+You can disable the hierarchical function call formatting and instead print a
+flat list of function entry and return events.  This uses the format described
+in the Output Formatting section and respects all the trace options that
+control that formatting.  Hierarchical formatting is the default.
+
+	hierachical: echo nofuncgraph-flat > trace_options
+	flat: echo funcgraph-flat > trace_options
+
+  ie:
+
+  # tracer: function_graph
+  #
+  # entries-in-buffer/entries-written: 68355/68355   #P:2
+  #
+  #                              _-----=> irqs-off
+  #                             / _----=> need-resched
+  #                            | / _---=> hardirq/softirq
+  #                            || / _--=> preempt-depth
+  #                            ||| /     delay
+  #           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
+  #              | |       |   ||||       |         |
+                sh-1806  [001] d...   198.843443: graph_ent: func=_raw_spin_lock
+                sh-1806  [001] d...   198.843445: graph_ent: func=__raw_spin_lock
+                sh-1806  [001] d..1   198.843447: graph_ret: func=__raw_spin_lock
+                sh-1806  [001] d..1   198.843449: graph_ret: func=_raw_spin_lock
+                sh-1806  [001] d..1   198.843451: graph_ent: func=_raw_spin_unlock_irqrestore
+                sh-1806  [001] d...   198.843453: graph_ret: func=_raw_spin_unlock_irqrestore
+
+
 You might find other useful features for this tracer in the
 following "dynamic ftrace" section such as tracing only specific
 functions or tasks.
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 7610eaa4d49..702bb2557db 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2455,7 +2455,8 @@ should be created before this ioctl is invoked.
 
 Possible features:
 	- KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state.
-	  Depends on KVM_CAP_ARM_PSCI.
+	  Depends on KVM_CAP_ARM_PSCI.  If not set, the CPU will be powered on
+	  and execute guest code when KVM_RUN is called.
 	- KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode.
 	  Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
 	- KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 for the CPU.
@@ -2951,6 +2952,15 @@ HVC instruction based PSCI call from the vcpu. The 'type' field describes
 the system-level event type. The 'flags' field describes architecture
 specific flags for the system-level event.
 
+Valid values for 'type' are:
+  KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the
+   VM. Userspace is not obliged to honour this, and if it does honour
+   this does not need to destroy the VM synchronously (ie it may call
+   KVM_RUN again before shutdown finally occurs).
+  KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM.
+   As with SHUTDOWN, userspace can choose to ignore the request, or
+   to schedule the reset to occur in the future and may call KVM_RUN again.
+
 		/* Fix the size of the union. */
 		char padding[256];
 	};
diff --git a/Documentation/virtual/kvm/devices/s390_flic.txt b/Documentation/virtual/kvm/devices/s390_flic.txt
index 4ceef53164b..d1ad9d5cae4 100644
--- a/Documentation/virtual/kvm/devices/s390_flic.txt
+++ b/Documentation/virtual/kvm/devices/s390_flic.txt
@@ -27,6 +27,9 @@ Groups:
     Copies all floating interrupts into a buffer provided by userspace.
     When the buffer is too small it returns -ENOMEM, which is the indication
     for userspace to try again with a bigger buffer.
+    -ENOBUFS is returned when the allocation of a kernelspace buffer has
+    failed.
+    -EFAULT is returned when copying data to userspace failed.
     All interrupts remain pending, i.e. are not deleted from the list of
     currently pending interrupts.
     attr->addr contains the userspace address of the buffer into which all
diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index 53838d9c629..c59bd9bc41e 100644
--- a/Documentation/virtual/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
@@ -169,6 +169,10 @@ Shadow pages contain the following information:
     Contains the value of cr4.smep && !cr0.wp for which the page is valid
     (pages for which this is true are different from other pages; see the
     treatment of cr0.wp=0 below).
+  role.smap_andnot_wp:
+    Contains the value of cr4.smap && !cr0.wp for which the page is valid
+    (pages for which this is true are different from other pages; see the
+    treatment of cr0.wp=0 below).
   gfn:
     Either the guest page table containing the translations shadowed by this
     page, or the base page frame for linear translations.  See role.direct.
@@ -344,10 +348,16 @@ on fault type:
 
 (user write faults generate a #PF)
 
-In the first case there is an additional complication if CR4.SMEP is
-enabled: since we've turned the page into a kernel page, the kernel may now
-execute it.  We handle this by also setting spte.nx.  If we get a user
-fetch or read fault, we'll change spte.u=1 and spte.nx=gpte.nx back.
+In the first case there are two additional complications:
+- if CR4.SMEP is enabled: since we've turned the page into a kernel page,
+  the kernel may now execute it.  We handle this by also setting spte.nx.
+  If we get a user fetch or read fault, we'll change spte.u=1 and
+  spte.nx=gpte.nx back.
+- if CR4.SMAP is disabled: since the page has been changed to a kernel
+  page, it can not be reused when CR4.SMAP is enabled. We set
+  CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note,
+  here we do not care the case that CR4.SMAP is enabled since KVM will
+  directly inject #PF to guest due to failed permission check.
 
 To prevent an spte that was converted into a kernel page with cr0.wp=0
 from being written by the kernel after cr0.wp has changed to 1, we make
diff --git a/MAINTAINERS b/MAINTAINERS
index c721042e7e4..94778f0c8e0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -918,6 +918,14 @@ M:	Hubert Feurstein <hubert.feurstein@contec.at>
 S:	Maintained
 F:	arch/arm/mach-ep93xx/micro9.c
 
+ARM/CORESIGHT FRAMEWORK AND DRIVERS
+M:	Mathieu Poirier <mathieu.poirier@linaro.org>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	drivers/hwtracing/coresight/*
+F:	Documentation/trace/coresight.txt
+F:	Documentation/devicetree/bindings/arm/coresight.txt
+
 ARM/CORGI MACHINE SUPPORT
 M:	Richard Purdie <rpurdie@rpsys.net>
 S:	Maintained
@@ -1562,6 +1570,7 @@ M:	Will Deacon <will.deacon@arm.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	drivers/iommu/arm-smmu.c
+F:	drivers/iommu/io-pgtable-arm.c
 
 ARM64 PORT (AARCH64 ARCHITECTURE)
 M:	Catalin Marinas <catalin.marinas@arm.com>
@@ -8185,6 +8194,16 @@ W:	http://www.sunplus.com
 S:	Supported
 F:	arch/score/
 
+SYSTEM CONTROL & POWER INTERFACE (SCPI) Message Protocol drivers
+M:	Sudeep Holla <sudeep.holla@arm.com>
+L:	linux-arm-kernel@lists.infradead.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/arm/arm,scpi.txt
+F:	drivers/clk/clk-scpi.c
+F:	drivers/cpufreq/scpi-cpufreq.c
+F:	drivers/firmware/arm_scpi.c
+F:	include/linux/scpi_protocol.h
+
 SCSI CDROM DRIVER
 M:	Jens Axboe <axboe@kernel.dk>
 L:	linux-scsi@vger.kernel.org
@@ -9297,6 +9316,7 @@ Q:	https://patchwork.kernel.org/project/linux-pm/list/
 S:	Supported
 F:	drivers/thermal/
 F:	include/linux/thermal.h
+F:	include/uapi/linux/thermal.h
 F:	include/linux/cpu_cooling.h
 F:	Documentation/devicetree/bindings/thermal/
 
diff --git a/Makefile b/Makefile
index fd80c6e9bc2..56992aa8725 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
 VERSION = 3
 PATCHLEVEL = 18
-SUBLEVEL = 0
+SUBLEVEL = 20
 EXTRAVERSION =
-NAME = Diseased Newt
+NAME = Shuffling Zombie Juror
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
diff --git a/android/configs/README b/android/configs/README
new file mode 100644
index 00000000000..8798731f890
--- /dev/null
+++ b/android/configs/README
@@ -0,0 +1,15 @@
+The files in this directory are meant to be used as a base for an Android
+kernel config. All devices should have the options in android-base.cfg enabled.
+While not mandatory, the options in android-recommended.cfg enable advanced
+Android features.
+
+Assuming you already have a minimalist defconfig for your device, a possible
+way to enable these options would be:
+
+     ARCH=<arch> scripts/kconfig/merge_config.sh <path_to>/<device>_defconfig android/configs/android-base.cfg android/configs/android-recommended.cfg
+
+This will generate a .config that can then be used to save a new defconfig or
+compile a new kernel with Android features enabled.
+
+Because there is no tool to consistently generate these config fragments,
+lets keep them alphabetically sorted instead of random.
diff --git a/android/configs/android-base.cfg b/android/configs/android-base.cfg
new file mode 100644
index 00000000000..154bf1647b5
--- /dev/null
+++ b/android/configs/android-base.cfg
@@ -0,0 +1,160 @@
+#  KEEP ALPHABETICALLY SORTED
+# CONFIG_DEVKMEM is not set
+# CONFIG_DEVMEM is not set
+# CONFIG_INET_LRO is not set
+# CONFIG_MODULES is not set
+# CONFIG_OABI_COMPAT is not set
+CONFIG_ANDROID=y
+CONFIG_ANDROID_BINDER_IPC=y
+CONFIG_ANDROID_LOW_MEMORY_KILLER=y
+CONFIG_ARMV8_DEPRECATED=y
+CONFIG_ASHMEM=y
+CONFIG_AUDIT=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_DEBUG=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CP15_BARRIER_EMULATION=y
+CONFIG_DM_CRYPT=y
+CONFIG_DM_VERITY=y
+CONFIG_EMBEDDED=y
+CONFIG_FB=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
+CONFIG_INET6_IPCOMP=y
+CONFIG_INET=y
+CONFIG_INET_ESP=y
+CONFIG_INET_XFRM_MODE_TUNNEL=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_MANGLE=y
+CONFIG_IP6_NF_RAW=y
+CONFIG_IP6_NF_TARGET_REJECT=y
+CONFIG_IP6_NF_TARGET_REJECT_SKERR=y
+CONFIG_IPV6=y
+CONFIG_IPV6_MIP6=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_IPV6_OPTIMISTIC_DAD=y
+CONFIG_IPV6_PRIVACY=y
+CONFIG_IPV6_ROUTER_PREF=y
+CONFIG_IPV6_ROUTE_INFO=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_NF_ARPFILTER=y
+CONFIG_IP_NF_ARPTABLES=y
+CONFIG_IP_NF_ARP_MANGLE=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_MANGLE=y
+CONFIG_IP_NF_MATCH_AH=y
+CONFIG_IP_NF_MATCH_ECN=y
+CONFIG_IP_NF_MATCH_TTL=y
+CONFIG_IP_NF_RAW=y
+CONFIG_IP_NF_SECURITY=y
+CONFIG_IP_NF_TARGET_MASQUERADE=y
+CONFIG_IP_NF_TARGET_NETMAP=y
+CONFIG_IP_NF_TARGET_REDIRECT=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_IP_NF_TARGET_REJECT_SKERR=y
+CONFIG_NET=y
+CONFIG_NETDEVICES=y
+CONFIG_NETFILTER=y
+CONFIG_NETFILTER_TPROXY=y
+CONFIG_NETFILTER_XT_MATCH_COMMENT=y
+CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_CONNMARK=y
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
+CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_HELPER=y
+CONFIG_NETFILTER_XT_MATCH_IPRANGE=y
+CONFIG_NETFILTER_XT_MATCH_LENGTH=y
+CONFIG_NETFILTER_XT_MATCH_LIMIT=y
+CONFIG_NETFILTER_XT_MATCH_MAC=y
+CONFIG_NETFILTER_XT_MATCH_MARK=y
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
+CONFIG_NETFILTER_XT_MATCH_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_QTAGUID=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA2=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA=y
+CONFIG_NETFILTER_XT_MATCH_SOCKET=y
+CONFIG_NETFILTER_XT_MATCH_STATE=y
+CONFIG_NETFILTER_XT_MATCH_STATISTIC=y
+CONFIG_NETFILTER_XT_MATCH_STRING=y
+CONFIG_NETFILTER_XT_MATCH_TIME=y
+CONFIG_NETFILTER_XT_MATCH_U32=y
+CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y
+CONFIG_NETFILTER_XT_TARGET_CONNMARK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y
+CONFIG_NETFILTER_XT_TARGET_MARK=y
+CONFIG_NETFILTER_XT_TARGET_NFLOG=y
+CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
+CONFIG_NETFILTER_XT_TARGET_TPROXY=y
+CONFIG_NETFILTER_XT_TARGET_TRACE=y
+CONFIG_NET_CLS_ACT=y
+CONFIG_NET_CLS_U32=y
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_U32=y
+CONFIG_NET_KEY=y
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_HTB=y
+CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_AMANDA=y
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NF_CONNTRACK_FTP=y
+CONFIG_NF_CONNTRACK_H323=y
+CONFIG_NF_CONNTRACK_IPV4=y
+CONFIG_NF_CONNTRACK_IPV6=y
+CONFIG_NF_CONNTRACK_IRC=y
+CONFIG_NF_CONNTRACK_NETBIOS_NS=y
+CONFIG_NF_CONNTRACK_PPTP=y
+CONFIG_NF_CONNTRACK_SANE=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_TFTP=y
+CONFIG_NF_CT_NETLINK=y
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
+CONFIG_NF_NAT=y
+CONFIG_NO_HZ=y
+CONFIG_PACKET=y
+CONFIG_PM_AUTOSLEEP=y
+CONFIG_PM_WAKELOCKS=y
+CONFIG_PPP=y
+CONFIG_PPPOLAC=y
+CONFIG_PPPOPNS=y
+CONFIG_PPP_BSDCOMP=y
+CONFIG_PPP_DEFLATE=y
+CONFIG_PPP_MPPE=y
+CONFIG_PREEMPT=y
+CONFIG_RESOURCE_COUNTERS=y
+CONFIG_RTC_CLASS=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SETEND_EMULATION=y
+CONFIG_STAGING=y
+CONFIG_SWITCH=y
+CONFIG_SWP_EMULATION=y
+CONFIG_SYNC=y
+CONFIG_SYSVIPC=y
+CONFIG_TUN=y
+CONFIG_UNIX=y
+CONFIG_USB_GADGET=y
+CONFIG_USB_CONFIGFS=y
+CONFIG_USB_CONFIGFS_F_FS=y
+CONFIG_USB_CONFIGFS_F_MTP=y
+CONFIG_USB_CONFIGFS_F_PTP=y
+CONFIG_USB_CONFIGFS_F_ACC=y
+CONFIG_USB_CONFIGFS_F_AUDIO_SRC=y
+CONFIG_USB_CONFIGFS_UEVENT=y
+CONFIG_USB_OTG_WAKELOCK=y
+CONFIG_XFRM_USER=y
diff --git a/android/configs/android-recommended.cfg b/android/configs/android-recommended.cfg
new file mode 100644
index 00000000000..960b9de2860
--- /dev/null
+++ b/android/configs/android-recommended.cfg
@@ -0,0 +1,121 @@
+#  KEEP ALPHABETICALLY SORTED
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_NF_CONNTRACK_SIP is not set
+# CONFIG_PM_WAKELOCKS_GC is not set
+# CONFIG_VT is not set
+CONFIG_ANDROID_TIMED_GPIO=y
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=8192
+CONFIG_COMPACTION=y
+CONFIG_DM_UEVENT=y
+CONFIG_DRAGONRISE_FF=y
+CONFIG_ENABLE_DEFAULT_TRACERS=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_FUSE_FS=y
+CONFIG_GREENASIA_FF=y
+CONFIG_HIDRAW=y
+CONFIG_HID_A4TECH=y
+CONFIG_HID_ACRUX=y
+CONFIG_HID_ACRUX_FF=y
+CONFIG_HID_APPLE=y
+CONFIG_HID_BELKIN=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_DRAGONRISE=y
+CONFIG_HID_ELECOM=y
+CONFIG_HID_EMS_FF=y
+CONFIG_HID_EZKEY=y
+CONFIG_HID_GREENASIA=y
+CONFIG_HID_GYRATION=y
+CONFIG_HID_HOLTEK=y
+CONFIG_HID_KENSINGTON=y
+CONFIG_HID_KEYTOUCH=y
+CONFIG_HID_KYE=y
+CONFIG_HID_LCPOWER=y
+CONFIG_HID_LOGITECH=y
+CONFIG_HID_LOGITECH_DJ=y
+CONFIG_HID_MAGICMOUSE=y
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
+CONFIG_HID_MULTITOUCH=y
+CONFIG_HID_NTRIG=y
+CONFIG_HID_ORTEK=y
+CONFIG_HID_PANTHERLORD=y
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_PICOLCD=y
+CONFIG_HID_PRIMAX=y
+CONFIG_HID_PRODIKEYS=y
+CONFIG_HID_ROCCAT=y
+CONFIG_HID_SAITEK=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SMARTJOYPLUS=y
+CONFIG_HID_SONY=y
+CONFIG_HID_SPEEDLINK=y
+CONFIG_HID_SUNPLUS=y
+CONFIG_HID_THRUSTMASTER=y
+CONFIG_HID_TIVO=y
+CONFIG_HID_TOPSEED=y
+CONFIG_HID_TWINHAN=y
+CONFIG_HID_UCLOGIC=y
+CONFIG_HID_WACOM=y
+CONFIG_HID_WALTOP=y
+CONFIG_HID_WIIMOTE=y
+CONFIG_HID_ZEROPLUS=y
+CONFIG_HID_ZYDACRON=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_INPUT_GPIO=y
+CONFIG_INPUT_JOYSTICK=y
+CONFIG_INPUT_KEYCHORD=y
+CONFIG_INPUT_KEYRESET=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_TABLET=y
+CONFIG_INPUT_UINPUT=y
+CONFIG_ION=y
+CONFIG_JOYSTICK_XPAD=y
+CONFIG_JOYSTICK_XPAD_FF=y
+CONFIG_JOYSTICK_XPAD_LEDS=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_KSM=y
+CONFIG_LOGIG940_FF=y
+CONFIG_LOGIRUMBLEPAD2_FF=y
+CONFIG_LOGITECH_FF=y
+CONFIG_MD=y
+CONFIG_MEDIA_SUPPORT=y
+CONFIG_MSDOS_FS=y
+CONFIG_PANIC_TIMEOUT=5
+CONFIG_PANTHERLORD_FF=y
+CONFIG_PERF_EVENTS=y
+CONFIG_PM_DEBUG=y
+CONFIG_PM_RUNTIME=y
+CONFIG_PM_WAKELOCKS_LIMIT=0
+CONFIG_POWER_SUPPLY=y
+CONFIG_PSTORE=y
+CONFIG_PSTORE_CONSOLE=y
+CONFIG_PSTORE_RAM=y
+CONFIG_SCHEDSTATS=y
+CONFIG_SMARTJOYPLUS_FF=y
+CONFIG_SND=y
+CONFIG_SOUND=y
+CONFIG_SUSPEND_TIME=y
+CONFIG_TABLET_USB_ACECAD=y
+CONFIG_TABLET_USB_AIPTEK=y
+CONFIG_TABLET_USB_GTCO=y
+CONFIG_TABLET_USB_HANWANG=y
+CONFIG_TABLET_USB_KBTAB=y
+CONFIG_TABLET_USB_WACOM=y
+CONFIG_TIMER_STATS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_UHID=y
+CONFIG_UID_STAT=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_HIDDEV=y
+CONFIG_USB_USBNET=y
+CONFIG_VFAT_FS=y
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 98838a05ba6..9d0ac091a52 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -156,6 +156,8 @@ retry:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
index cfaedd9c61c..1c169dc74ad 100644
--- a/arch/arc/boot/dts/nsimosci.dts
+++ b/arch/arc/boot/dts/nsimosci.dts
@@ -20,7 +20,7 @@
 		/* this is for console on PGU */
 		/* bootargs = "console=tty0 consoleblank=0"; */
 		/* this is for console on serial */
-		bootargs = "earlycon=uart8250,mmio32,0xc0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug";
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug";
 	};
 
 	aliases {
@@ -41,9 +41,9 @@
 			#interrupt-cells = <1>;
 		};
 
-		uart0: serial@c0000000 {
+		uart0: serial@f0000000 {
 			compatible = "ns8250";
-			reg = <0xc0000000 0x2000>;
+			reg = <0xf0000000 0x2000>;
 			interrupts = <11>;
 			clock-frequency = <3686400>;
 			baud = <115200>;
@@ -52,21 +52,21 @@
 			no-loopback-test = <1>;
 		};
 
-		pgu0: pgu@c9000000 {
+		pgu0: pgu@f9000000 {
 			compatible = "snps,arcpgufb";
-			reg = <0xc9000000 0x400>;
+			reg = <0xf9000000 0x400>;
 		};
 
-		ps2: ps2@c9001000 {
+		ps2: ps2@f9001000 {
 			compatible = "snps,arc_ps2";
-			reg = <0xc9000400 0x14>;
+			reg = <0xf9000400 0x14>;
 			interrupts = <13>;
 			interrupt-names = "arc_ps2_irq";
 		};
 
-		eth0: ethernet@c0003000 {
+		eth0: ethernet@f0003000 {
 			compatible = "snps,oscilan";
-			reg = <0xc0003000 0x44>;
+			reg = <0xf0003000 0x44>;
 			interrupts = <7>, <8>;
 			interrupt-names = "rx", "tx";
 		};
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 067551b6920..20b7dc17979 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -43,6 +43,12 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
 	unsigned int temp;						\
 									\
+	/*								\
+	 * Explicit full memory barrier needed before/after as		\
+	 * LLOCK/SCOND thmeselves don't provide any such semantics	\
+	 */								\
+	smp_mb();							\
+									\
 	__asm__ __volatile__(						\
 	"1:	llock   %0, [%1]	\n"				\
 	"	" #asm_op " %0, %0, %2	\n"				\
@@ -52,6 +58,8 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	: "r"(&v->counter), "ir"(i)					\
 	: "cc");							\
 									\
+	smp_mb();							\
+									\
 	return temp;							\
 }
 
@@ -99,12 +107,15 @@ static inline void atomic_##op(int i, atomic_t *v)			\
 	atomic_ops_unlock(flags);					\
 }
 
-#define ATOMIC_OP_RETURN(op, c_op)					\
+#define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
 static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
 	unsigned long flags;						\
 	unsigned long temp;						\
 									\
+	/*								\
+	 * spin lock/unlock provides the needed smp_mb() before/after	\
+	 */								\
 	atomic_ops_lock(flags);						\
 	temp = v->counter;						\
 	temp c_op i;							\
@@ -142,9 +153,19 @@ ATOMIC_OP(and, &=, and)
 #define __atomic_add_unless(v, a, u)					\
 ({									\
 	int c, old;							\
+									\
+	/*								\
+	 * Explicit full memory barrier needed before/after as		\
+	 * LLOCK/SCOND thmeselves don't provide any such semantics	\
+	 */								\
+	smp_mb();							\
+									\
 	c = atomic_read(v);						\
 	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c)\
 		c = old;						\
+									\
+	smp_mb();							\
+									\
 	c;								\
 })
 
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
index 1a5bf07eefe..89fbbb0db51 100644
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -103,6 +103,12 @@ static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *m)
 	if (__builtin_constant_p(nr))
 		nr &= 0x1f;
 
+	/*
+	 * Explicit full memory barrier needed before/after as
+	 * LLOCK/SCOND themselves don't provide any such semantics
+	 */
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	llock   %0, [%2]	\n"
 	"	bset    %1, %0, %3	\n"
@@ -112,6 +118,8 @@ static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *m)
 	: "r"(m), "ir"(nr)
 	: "cc");
 
+	smp_mb();
+
 	return (old & (1 << nr)) != 0;
 }
 
@@ -125,6 +133,8 @@ test_and_clear_bit(unsigned long nr, volatile unsigned long *m)
 	if (__builtin_constant_p(nr))
 		nr &= 0x1f;
 
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	llock   %0, [%2]	\n"
 	"	bclr    %1, %0, %3	\n"
@@ -134,6 +144,8 @@ test_and_clear_bit(unsigned long nr, volatile unsigned long *m)
 	: "r"(m), "ir"(nr)
 	: "cc");
 
+	smp_mb();
+
 	return (old & (1 << nr)) != 0;
 }
 
@@ -147,6 +159,8 @@ test_and_change_bit(unsigned long nr, volatile unsigned long *m)
 	if (__builtin_constant_p(nr))
 		nr &= 0x1f;
 
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	llock   %0, [%2]	\n"
 	"	bxor    %1, %0, %3	\n"
@@ -156,6 +170,8 @@ test_and_change_bit(unsigned long nr, volatile unsigned long *m)
 	: "r"(m), "ir"(nr)
 	: "cc");
 
+	smp_mb();
+
 	return (old & (1 << nr)) != 0;
 }
 
@@ -235,6 +251,9 @@ static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *m)
 	if (__builtin_constant_p(nr))
 		nr &= 0x1f;
 
+	/*
+	 * spin lock/unlock provide the needed smp_mb() before/after
+	 */
 	bitops_lock(flags);
 
 	old = *m;
diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h
index 03cd6894855..44fd531f4d7 100644
--- a/arch/arc/include/asm/cmpxchg.h
+++ b/arch/arc/include/asm/cmpxchg.h
@@ -10,6 +10,8 @@
 #define __ASM_ARC_CMPXCHG_H
 
 #include <linux/types.h>
+
+#include <asm/barrier.h>
 #include <asm/smp.h>
 
 #ifdef CONFIG_ARC_HAS_LLSC
@@ -19,16 +21,25 @@ __cmpxchg(volatile void *ptr, unsigned long expected, unsigned long new)
 {
 	unsigned long prev;
 
+	/*
+	 * Explicit full memory barrier needed before/after as
+	 * LLOCK/SCOND thmeselves don't provide any such semantics
+	 */
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	llock   %0, [%1]	\n"
 	"	brne    %0, %2, 2f	\n"
 	"	scond   %3, [%1]	\n"
 	"	bnz     1b		\n"
 	"2:				\n"
-	: "=&r"(prev)
-	: "r"(ptr), "ir"(expected),
-	  "r"(new) /* can't be "ir". scond can't take limm for "b" */
-	: "cc");
+	: "=&r"(prev)	/* Early clobber, to prevent reg reuse */
+	: "r"(ptr),	/* Not "m": llock only supports reg direct addr mode */
+	  "ir"(expected),
+	  "r"(new)	/* can't be "ir". scond can't take LIMM for "b" */
+	: "cc", "memory"); /* so that gcc knows memory is being written here */
+
+	smp_mb();
 
 	return prev;
 }
@@ -42,6 +53,9 @@ __cmpxchg(volatile void *ptr, unsigned long expected, unsigned long new)
 	int prev;
 	volatile unsigned long *p = ptr;
 
+	/*
+	 * spin lock/unlock provide the needed smp_mb() before/after
+	 */
 	atomic_ops_lock(flags);
 	prev = *p;
 	if (prev == expected)
@@ -77,12 +91,16 @@ static inline unsigned long __xchg(unsigned long val, volatile void *ptr,
 
 	switch (size) {
 	case 4:
+		smp_mb();
+
 		__asm__ __volatile__(
 		"	ex  %0, [%1]	\n"
 		: "+r"(val)
 		: "r"(ptr)
 		: "memory");
 
+		smp_mb();
+
 		return val;
 	}
 	return __xchg_bad_pointer();
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 6b0b7f7ef78..7670f33b9ce 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -259,7 +259,8 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep)
 #define pmd_clear(xp)			do { pmd_val(*(xp)) = 0; } while (0)
 
 #define pte_page(x) (mem_map + \
-		(unsigned long)(((pte_val(x) - PAGE_OFFSET) >> PAGE_SHIFT)))
+		(unsigned long)(((pte_val(x) - CONFIG_LINUX_LINK_BASE) >> \
+				PAGE_SHIFT)))
 
 #define mk_pte(page, pgprot)						\
 ({									\
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index 210fe97464c..c750af16197 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -75,18 +75,19 @@ unsigned long thread_saved_pc(struct task_struct *t);
 #define release_segments(mm)        do { } while (0)
 
 #define KSTK_EIP(tsk)   (task_pt_regs(tsk)->ret)
+#define KSTK_ESP(tsk)   (task_pt_regs(tsk)->sp)
 
 /*
  * Where abouts of Task's sp, fp, blink when it was last seen in kernel mode.
  * Look in process.c for details of kernel stack layout
  */
-#define KSTK_ESP(tsk)   (tsk->thread.ksp)
+#define TSK_K_ESP(tsk)		(tsk->thread.ksp)
 
-#define KSTK_REG(tsk, off)	(*((unsigned int *)(KSTK_ESP(tsk) + \
+#define TSK_K_REG(tsk, off)	(*((unsigned int *)(TSK_K_ESP(tsk) + \
 					sizeof(struct callee_regs) + off)))
 
-#define KSTK_BLINK(tsk) KSTK_REG(tsk, 4)
-#define KSTK_FP(tsk)    KSTK_REG(tsk, 0)
+#define TSK_K_BLINK(tsk)	TSK_K_REG(tsk, 4)
+#define TSK_K_FP(tsk)		TSK_K_REG(tsk, 0)
 
 extern void start_thread(struct pt_regs * regs, unsigned long pc,
 			 unsigned long usp);
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index b6a8c2dfbe6..e1651df6a93 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -22,24 +22,46 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
 
+	/*
+	 * This smp_mb() is technically superfluous, we only need the one
+	 * after the lock for providing the ACQUIRE semantics.
+	 * However doing the "right" thing was regressing hackbench
+	 * so keeping this, pending further investigation
+	 */
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
 	"	breq  %0, %2, 1b	\n"
 	: "+&r" (tmp)
 	: "r"(&(lock->slock)), "ir"(__ARCH_SPIN_LOCK_LOCKED__)
 	: "memory");
+
+	/*
+	 * ACQUIRE barrier to ensure load/store after taking the lock
+	 * don't "bleed-up" out of the critical section (leak-in is allowed)
+	 * http://www.spinics.net/lists/kernel/msg2010409.html
+	 *
+	 * ARCv2 only has load-load, store-store and all-all barrier
+	 * thus need the full all-all barrier
+	 */
+	smp_mb();
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
 
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
 	: "+r" (tmp)
 	: "r"(&(lock->slock))
 	: "memory");
 
+	smp_mb();
+
 	return (tmp == __ARCH_SPIN_LOCK_UNLOCKED__);
 }
 
@@ -47,12 +69,22 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__;
 
+	/*
+	 * RELEASE barrier: given the instructions avail on ARCv2, full barrier
+	 * is the only option
+	 */
+	smp_mb();
+
 	__asm__ __volatile__(
 	"	ex  %0, [%1]		\n"
 	: "+r" (tmp)
 	: "r"(&(lock->slock))
 	: "memory");
 
+	/*
+	 * superfluous, but keeping for now - see pairing version in
+	 * arch_spin_lock above
+	 */
 	smp_mb();
 }
 
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index cb3142a2d40..a86d567f6c7 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -67,7 +67,7 @@ stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs,
 	       sigset_t *set)
 {
 	int err;
-	err = __copy_to_user(&(sf->uc.uc_mcontext.regs), regs,
+	err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), regs,
 			     sizeof(sf->uc.uc_mcontext.regs.scratch));
 	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t));
 
@@ -83,7 +83,7 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
 	if (!err)
 		set_current_blocked(&set);
 
-	err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs),
+	err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs.scratch),
 				sizeof(sf->uc.uc_mcontext.regs.scratch));
 
 	return err;
@@ -131,6 +131,15 @@ SYSCALL_DEFINE0(rt_sigreturn)
 	/* Don't restart from sigreturn */
 	syscall_wont_restart(regs);
 
+	/*
+	 * Ensure that sigreturn always returns to user mode (in case the
+	 * regs saved on user stack got fudged between save and sigreturn)
+	 * Otherwise it is easy to panic the kernel with a custom
+	 * signal handler and/or restorer which clobberes the status32/ret
+	 * to return to a bogus location in kernel mode.
+	 */
+	regs->status32 |= STATUS_U_MASK;
+
 	return regs->r0;
 
 badframe:
@@ -229,8 +238,11 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs)
 
 	/*
 	 * handler returns using sigreturn stub provided already by userpsace
+	 * If not, nuke the process right away
 	 */
-	BUG_ON(!(ksig->ka.sa.sa_flags & SA_RESTORER));
+	if(!(ksig->ka.sa.sa_flags & SA_RESTORER))
+		return 1;
+
 	regs->blink = (unsigned long)ksig->ka.sa.sa_restorer;
 
 	/* User Stack for signal handler will be above the frame just carved */
@@ -296,12 +308,12 @@ static void
 handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
 	sigset_t *oldset = sigmask_to_save();
-	int ret;
+	int failed;
 
 	/* Set up the stack frame */
-	ret = setup_rt_frame(ksig, oldset, regs);
+	failed = setup_rt_frame(ksig, oldset, regs);
 
-	signal_setup_done(ret, ksig, 0);
+	signal_setup_done(failed, ksig, 0);
 }
 
 void do_signal(struct pt_regs *regs)
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
index 9ce47cfe230..fb98769b6a9 100644
--- a/arch/arc/kernel/stacktrace.c
+++ b/arch/arc/kernel/stacktrace.c
@@ -64,9 +64,9 @@ static void seed_unwind_frame_info(struct task_struct *tsk,
 
 		frame_info->task = tsk;
 
-		frame_info->regs.r27 = KSTK_FP(tsk);
-		frame_info->regs.r28 = KSTK_ESP(tsk);
-		frame_info->regs.r31 = KSTK_BLINK(tsk);
+		frame_info->regs.r27 = TSK_K_FP(tsk);
+		frame_info->regs.r28 = TSK_K_ESP(tsk);
+		frame_info->regs.r31 = TSK_K_BLINK(tsk);
 		frame_info->regs.r63 = (unsigned int)__switch_to;
 
 		/* In the prologue of __switch_to, first FP is saved on stack
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 6f7e3a68803..563cb27e37f 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -161,6 +161,8 @@ good_area:
 
 	if (fault & VM_FAULT_OOM)
 		goto out_of_memory;
+	else if (fault & VM_FAULT_SIGSEGV)
+		goto bad_area;
 	else if (fault & VM_FAULT_SIGBUS)
 		goto do_sigbus;
 
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 89c4b5ccc68..9233d3a7a9f 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1385,6 +1385,104 @@ config SCHED_SMT
 	  MultiThreading at a cost of slightly increased overhead in some
 	  places. If unsure say N here.
 
+config SCHED_HMP
+	bool "(EXPERIMENTAL) Heterogenous multiprocessor scheduling"
+	depends on SCHED_MC && FAIR_GROUP_SCHED && !SCHED_AUTOGROUP
+	help
+	  Experimental scheduler optimizations for heterogeneous platforms.
+	  Attempts to introspectively select task affinity to optimize power
+	  and performance. Basic support for multiple (>2) cpu types is in place,
+	  but it has only been tested with two types of cpus.
+	  There is currently no support for migration of task groups, hence
+	  !SCHED_AUTOGROUP. Furthermore, normal load-balancing must be disabled
+	  between cpus of different type (DISABLE_CPU_SCHED_DOMAIN_BALANCE).
+	  When turned on, this option adds sys/kernel/hmp directory which
+	  contains the following files:
+	  up_threshold - the load average threshold used for up migration
+	                 (0 - 1023)
+	  down_threshold - the load average threshold used for down migration
+	                 (0 - 1023)
+	  hmp_domains - a list of cpumasks for the present HMP domains,
+	                starting with the 'biggest' and ending with the
+	                'smallest'.
+	  Note that both the threshold files can be written at runtime to
+	  control scheduler behaviour.
+
+config SCHED_HMP_PRIO_FILTER
+	bool "(EXPERIMENTAL) Filter HMP migrations by task priority"
+	depends on SCHED_HMP
+	help
+	  Enables task priority based HMP migration filter. Any task with
+	  a NICE value above the threshold will always be on low-power cpus
+	  with less compute capacity.
+
+config SCHED_HMP_PRIO_FILTER_VAL
+	int "NICE priority threshold"
+	default 5
+	depends on SCHED_HMP_PRIO_FILTER
+
+config HMP_FAST_CPU_MASK
+	string "HMP scheduler fast CPU mask"
+	depends on SCHED_HMP
+	help
+          Leave empty to use device tree information.
+	  Specify the cpuids of the fast CPUs in the system as a list string,
+	  e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_SLOW_CPU_MASK
+	string "HMP scheduler slow CPU mask"
+	depends on SCHED_HMP
+	help
+	  Leave empty to use device tree information.
+	  Specify the cpuids of the slow CPUs in the system as a list string,
+	  e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_VARIABLE_SCALE
+	bool "Allows changing the load tracking scale through sysfs"
+	depends on SCHED_HMP
+	help
+	  When turned on, this option exports the load average period value
+	  for the load tracking patches through sysfs.
+	  The values can be modified to change the rate of load accumulation
+	  used for HMP migration. 'load_avg_period_ms' is the time in ms to
+	  reach a load average of 0.5 for an idle task of 0 load average
+	  ratio which becomes 100% busy.
+	  For example, with load_avg_period_ms = 128 and up_threshold = 512,
+	  a running task with a load of 0 will be migrated to a bigger CPU after
+	  128ms, because after 128ms its load_avg_ratio is 0.5 and the real
+	  up_threshold is 0.5.
+	  This patch has the same behavior as changing the Y of the load
+	  average computation to
+	        (1002/1024)^(LOAD_AVG_PERIOD/load_avg_period_ms)
+	  but removes intermediate overflows in computation.
+
+config HMP_FREQUENCY_INVARIANT_SCALE
+	bool "(EXPERIMENTAL) Frequency-Invariant Tracked Load for HMP"
+	depends on SCHED_HMP && CPU_FREQ
+	help
+	  Scales the current load contribution in line with the frequency
+	  of the CPU that the task was executed on.
+	  In this version, we use a simple linear scale derived from the
+	  maximum frequency reported by CPUFreq.
+	  Restricting tracked load to be scaled by the CPU's frequency
+	  represents the consumption of possible compute capacity
+	  (rather than consumption of actual instantaneous capacity as
+	  normal) and allows the HMP migration's simple threshold
+	  migration strategy to interact more predictably with CPUFreq's
+	  asynchronous compute capacity changes.
+
+config SCHED_HMP_LITTLE_PACKING
+	bool "Small task packing for HMP"
+	depends on SCHED_HMP
+	default n
+	help
+	  Allows the HMP Scheduler to pack small tasks into CPUs in the
+	  smallest HMP domain.
+	  Controlled by two sysfs files in sys/kernel/hmp.
+	  packing_enable: 1 to enable, 0 to disable packing. Default 1.
+	  packing_limit: runqueue load ratio where a RQ is considered
+	    to be full. Default is NICE_0_LOAD * 9/8.
+
 config HAVE_ARM_SCU
 	bool
 	help
@@ -1790,6 +1888,15 @@ config XEN
 	help
 	  Say Y if you want to run Linux in a Virtual Machine on Xen on ARM.
 
+config ARM_FLUSH_CONSOLE_ON_RESTART
+	bool "Force flush the console on restart"
+	help
+	  If the console is locked while the system is rebooted, the messages
+	  in the temporary logbuffer would not have propogated to all the
+	  console drivers. This option forces the console lock to be
+	  released if it failed to be acquired, which will cause all the
+	  pending messages to be flushed.
+
 endmenu
 
 menu "Boot options"
@@ -1820,6 +1927,21 @@ config DEPRECATED_PARAM_STRUCT
 	  This was deprecated in 2001 and announced to live on for 5 years.
 	  Some old boot loaders still use this way.
 
+config BUILD_ARM_APPENDED_DTB_IMAGE
+	bool "Build a concatenated zImage/dtb by default"
+	depends on OF
+	help
+	  Enabling this option will cause a concatenated zImage and list of
+	  DTBs to be built by default (instead of a standalone zImage.)
+	  The image will built in arch/arm/boot/zImage-dtb
+
+config BUILD_ARM_APPENDED_DTB_IMAGE_NAMES
+	string "Default dtb names"
+	depends on BUILD_ARM_APPENDED_DTB_IMAGE
+	help
+	  Space separated list of names of dtbs to append when
+	  building a concatenated zImage-dtb.
+
 # Compressed boot loader in ROM.  Yes, we really want to ask about
 # TEXT and BSS so we preserve their values in the config files.
 config ZBOOT_ROM_TEXT
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index d8f6a2ec3d4..02a0527fd10 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -1297,9 +1297,17 @@ config EARLY_PRINTK
 	  kernel low-level debugging functions. Add earlyprintk to your
 	  kernel parameters to enable this console.
 
+config EARLY_PRINTK_DIRECT
+	bool "Early printk direct"
+	depends on DEBUG_LL
+	help
+	  Say Y here if you want to have an early console using the
+	  kernel low-level debugging functions and EARLY_PRINTK is
+	  not early enough.
+
 config OC_ETM
 	bool "On-chip ETM and ETB"
-	depends on ARM_AMBA
+	depends on ARM_AMBA && !CORESIGHT
 	help
 	  Enables the on-chip embedded trace macrocell and embedded trace
 	  buffer driver that will allow you to collect traces of the
@@ -1331,4 +1339,6 @@ config DEBUG_SET_MODULE_RONX
 	  against certain classes of kernel exploits.
 	  If in doubt, say "N".
 
+source "drivers/hwtracing/coresight/Kconfig"
+
 endmenu
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 034a94904d6..7de6eb721ae 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -278,6 +278,8 @@ libs-y				:= arch/arm/lib/ $(libs-y)
 # Default target when executing plain make
 ifeq ($(CONFIG_XIP_KERNEL),y)
 KBUILD_IMAGE := xipImage
+else ifeq ($(CONFIG_BUILD_ARM_APPENDED_DTB_IMAGE),y)
+KBUILD_IMAGE := zImage-dtb
 else
 KBUILD_IMAGE := zImage
 endif
@@ -312,8 +314,15 @@ $(INSTALL_TARGETS):
 	$(Q)$(MAKE) $(build)=$(boot)/dts MACHINE=$(MACHINE) $(boot)/dts/$@
 
 PHONY += dtbs dtbs_install
-dtbs dtbs_install: prepare scripts
-	$(Q)$(MAKE) $(build)=$(boot)/dts MACHINE=$(MACHINE) $@
+
+dtbs: prepare scripts
+	$(Q)$(MAKE) $(build)=$(boot)/dts MACHINE=$(MACHINE)
+
+dtbs_install:
+	$(Q)$(MAKE) $(dtbinst)=$(boot)/dts MACHINE=$(MACHINE)
+
+zImage-dtb: vmlinux scripts dtbs
+	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 
 # We use MRPROPER_FILES and CLEAN_FILES now
 archclean:
diff --git a/arch/arm/boot/.gitignore b/arch/arm/boot/.gitignore
index 3c79f85975a..ad7a0253ea9 100644
--- a/arch/arm/boot/.gitignore
+++ b/arch/arm/boot/.gitignore
@@ -4,3 +4,4 @@ xipImage
 bootpImage
 uImage
 *.dtb
+zImage-dtb
\ No newline at end of file
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index ec2f8065f95..d09b00ad5fb 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -14,6 +14,7 @@
 ifneq ($(MACHINE),)
 include $(srctree)/$(MACHINE)/Makefile.boot
 endif
+include $(srctree)/arch/arm/boot/dts/Makefile
 
 # Note: the following conditions must always be true:
 #   ZRELADDR == virt_to_phys(PAGE_OFFSET + TEXT_OFFSET)
@@ -27,6 +28,14 @@ export ZRELADDR INITRD_PHYS PARAMS_PHYS
 
 targets := Image zImage xipImage bootpImage uImage
 
+DTB_NAMES := $(subst $\",,$(CONFIG_BUILD_ARM_APPENDED_DTB_IMAGE_NAMES))
+ifneq ($(DTB_NAMES),)
+DTB_LIST := $(addsuffix .dtb,$(DTB_NAMES))
+else
+DTB_LIST := $(dtb-y)
+endif
+DTB_OBJS := $(addprefix $(obj)/dts/,$(DTB_LIST))
+
 ifeq ($(CONFIG_XIP_KERNEL),y)
 
 $(obj)/xipImage: vmlinux FORCE
@@ -55,6 +64,10 @@ $(obj)/zImage:	$(obj)/compressed/vmlinux FORCE
 	$(call if_changed,objcopy)
 	@$(kecho) '  Kernel: $@ is ready'
 
+$(obj)/zImage-dtb:	$(obj)/zImage $(DTB_OBJS) FORCE
+	$(call if_changed,cat)
+	@echo '  Kernel: $@ is ready'
+
 endif
 
 ifneq ($(LOADADDR),)
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 68be9017593..3f25fac7a84 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -730,6 +730,8 @@ __armv7_mmu_cache_on:
 		bic     r6, r6, #1 << 31        @ 32-bit translation system
 		bic     r6, r6, #3 << 0         @ use only ttbr0
 		mcrne	p15, 0, r3, c2, c0, 0	@ load page table pointer
+		mcrne	p15, 0, r0, c8, c7, 0	@ flush I,D TLBs
+		mcr	p15, 0, r0, c7, c5, 4	@ ISB
 		mcrne	p15, 0, r1, c3, c0, 0	@ load domain access control
 		mcrne   p15, 0, r6, c2, c0, 2   @ load ttb control
 #endif
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 38c89cafa1a..7fdb71cbca5 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -517,15 +517,14 @@ dtb-$(CONFIG_MACH_DOVE) += dove-cm-a510.dtb \
 	dove-dove-db.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt6589-aquaris5.dtb
 
-targets += dtbs dtbs_install
-targets += $(dtb-y)
+DTB_NAMES := $(subst $\",,$(CONFIG_BUILD_ARM_APPENDED_DTB_IMAGE_NAMES))
+ifneq ($(DTB_NAMES),)
+DTB_LIST := $(addsuffix .dtb,$(DTB_NAMES))
+else
+DTB_LIST := $(dtb-y)
 endif
 
-# *.dtb used to be generated in the directory above. Clean out the
-# old build results so people don't accidentally use them.
-dtbs: $(addprefix $(obj)/, $(dtb-y))
-	$(Q)rm -f $(obj)/../*.dtb
-
-clean-files := *.dtb
+endif
 
-dtbs_install: $(addsuffix _dtbinst_, $(dtb-y))
+always		:= $(DTB_LIST)
+clean-files	:= *.dtb
diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi
index 6cc25ed912e..2c6248d9a9e 100644
--- a/arch/arm/boot/dts/am335x-bone-common.dtsi
+++ b/arch/arm/boot/dts/am335x-bone-common.dtsi
@@ -195,6 +195,7 @@
 
 &usb0 {
 	status = "okay";
+	dr_mode = "peripheral";
 };
 
 &usb1 {
diff --git a/arch/arm/boot/dts/am33xx-clocks.dtsi b/arch/arm/boot/dts/am33xx-clocks.dtsi
index 712edce7d6f..071b56aa0c7 100644
--- a/arch/arm/boot/dts/am33xx-clocks.dtsi
+++ b/arch/arm/boot/dts/am33xx-clocks.dtsi
@@ -99,7 +99,7 @@
 	ehrpwm0_tbclk: ehrpwm0_tbclk@44e10664 {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <0>;
 		reg = <0x0664>;
 	};
@@ -107,7 +107,7 @@
 	ehrpwm1_tbclk: ehrpwm1_tbclk@44e10664 {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <1>;
 		reg = <0x0664>;
 	};
@@ -115,7 +115,7 @@
 	ehrpwm2_tbclk: ehrpwm2_tbclk@44e10664 {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <2>;
 		reg = <0x0664>;
 	};
diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts
index 87aa4f3b8b3..53bbfc90b26 100644
--- a/arch/arm/boot/dts/am437x-sk-evm.dts
+++ b/arch/arm/boot/dts/am437x-sk-evm.dts
@@ -100,7 +100,7 @@
 	};
 
 	lcd0: display {
-		compatible = "osddisplays,osd057T0559-34ts", "panel-dpi";
+		compatible = "newhaven,nhd-4.3-480272ef-atxl", "panel-dpi";
 		label = "lcd";
 
 		pinctrl-names = "default";
@@ -112,11 +112,11 @@
 			clock-frequency = <9000000>;
 			hactive = <480>;
 			vactive = <272>;
-			hfront-porch = <8>;
-			hback-porch = <43>;
-			hsync-len = <4>;
-			vback-porch = <12>;
-			vfront-porch = <4>;
+			hfront-porch = <2>;
+			hback-porch = <2>;
+			hsync-len = <41>;
+			vfront-porch = <2>;
+			vback-porch = <2>;
 			vsync-len = <10>;
 			hsync-active = <0>;
 			vsync-active = <0>;
@@ -320,8 +320,7 @@
 
 	lcd_pins: lcd_pins {
 		pinctrl-single,pins = <
-			/* GPIO 5_8 to select LCD / HDMI */
-			0x238 (PIN_OUTPUT_PULLUP | MUX_MODE7)
+			0x1c (PIN_OUTPUT_PULLDOWN | MUX_MODE7) /* gpcm_ad7.gpio1_7 */
 		>;
 	};
 };
diff --git a/arch/arm/boot/dts/am43xx-clocks.dtsi b/arch/arm/boot/dts/am43xx-clocks.dtsi
index c7dc9dab93a..cfb49686ab6 100644
--- a/arch/arm/boot/dts/am43xx-clocks.dtsi
+++ b/arch/arm/boot/dts/am43xx-clocks.dtsi
@@ -107,7 +107,7 @@
 	ehrpwm0_tbclk: ehrpwm0_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <0>;
 		reg = <0x0664>;
 	};
@@ -115,7 +115,7 @@
 	ehrpwm1_tbclk: ehrpwm1_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <1>;
 		reg = <0x0664>;
 	};
@@ -123,7 +123,7 @@
 	ehrpwm2_tbclk: ehrpwm2_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <2>;
 		reg = <0x0664>;
 	};
@@ -131,7 +131,7 @@
 	ehrpwm3_tbclk: ehrpwm3_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <4>;
 		reg = <0x0664>;
 	};
@@ -139,7 +139,7 @@
 	ehrpwm4_tbclk: ehrpwm4_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <5>;
 		reg = <0x0664>;
 	};
@@ -147,7 +147,7 @@
 	ehrpwm5_tbclk: ehrpwm5_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <6>;
 		reg = <0x0664>;
 	};
diff --git a/arch/arm/boot/dts/armada-370-db.dts b/arch/arm/boot/dts/armada-370-db.dts
index a495e5821ab..d5051358fb1 100644
--- a/arch/arm/boot/dts/armada-370-db.dts
+++ b/arch/arm/boot/dts/armada-370-db.dts
@@ -102,30 +102,6 @@
 				broken-cd;
 			};
 
-			pinctrl {
-				/*
-				 * These pins might be muxed as I2S by
-				 * the bootloader, but it conflicts
-				 * with the real I2S pins that are
-				 * muxed using i2s_pins. We must mux
-				 * those pins to a function other than
-				 * I2S.
-				 */
-				pinctrl-0 = <&hog_pins1 &hog_pins2>;
-				pinctrl-names = "default";
-
-				hog_pins1: hog-pins1 {
-					marvell,pins = "mpp6",  "mpp8", "mpp10",
-						       "mpp12", "mpp13";
-					marvell,function = "gpio";
-				};
-
-				hog_pins2: hog-pins2 {
-					marvell,pins = "mpp5", "mpp7", "mpp9";
-					marvell,function = "gpo";
-				};
-			};
-
 			usb@50000 {
 				status = "okay";
 			};
diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi
index 83286ec9702..84366cddaa8 100644
--- a/arch/arm/boot/dts/armada-370-xp.dtsi
+++ b/arch/arm/boot/dts/armada-370-xp.dtsi
@@ -225,7 +225,6 @@
 			};
 
 			eth0: ethernet@70000 {
-				compatible = "marvell,armada-370-neta";
 				reg = <0x70000 0x4000>;
 				interrupts = <8>;
 				clocks = <&gateclk 4>;
@@ -241,7 +240,6 @@
 			};
 
 			eth1: ethernet@74000 {
-				compatible = "marvell,armada-370-neta";
 				reg = <0x74000 0x4000>;
 				interrupts = <10>;
 				clocks = <&gateclk 3>;
diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi
index 6b3c23b1e13..b6e02689c61 100644
--- a/arch/arm/boot/dts/armada-370.dtsi
+++ b/arch/arm/boot/dts/armada-370.dtsi
@@ -106,11 +106,6 @@
 				reg = <0x11100 0x20>;
 			};
 
-			system-controller@18200 {
-				compatible = "marvell,armada-370-xp-system-controller";
-				reg = <0x18200 0x100>;
-			};
-
 			pinctrl {
 				compatible = "marvell,mv88f6710-pinctrl";
 				reg = <0x18000 0x38>;
@@ -205,6 +200,11 @@
 				interrupts = <91>;
 			};
 
+			system-controller@18200 {
+				compatible = "marvell,armada-370-xp-system-controller";
+				reg = <0x18200 0x100>;
+			};
+
 			gateclk: clock-gating-control@18220 {
 				compatible = "marvell,armada-370-gating-clock";
 				reg = <0x18220 0x4>;
@@ -302,6 +302,14 @@
 					dmacap,memset;
 				};
 			};
+
+			ethernet@70000 {
+				compatible = "marvell,armada-370-neta";
+			};
+
+			ethernet@74000 {
+				compatible = "marvell,armada-370-neta";
+			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
index 480e237a870..677160effbb 100644
--- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
@@ -296,7 +296,7 @@
 			};
 
 			eth3: ethernet@34000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x34000 0x4000>;
 				interrupts = <14>;
 				clocks = <&gateclk 1>;
diff --git a/arch/arm/boot/dts/armada-xp-mv78460.dtsi b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
index 2c7b1fef470..e143776b78e 100644
--- a/arch/arm/boot/dts/armada-xp-mv78460.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
@@ -334,7 +334,7 @@
 			};
 
 			eth3: ethernet@34000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x34000 0x4000>;
 				interrupts = <14>;
 				clocks = <&gateclk 1>;
diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
index 4e5a59ee150..db06fa397f7 100644
--- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
+++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
@@ -71,6 +71,10 @@
 		};
 
 		internal-regs {
+			rtc@10300 {
+				/* No crystal connected to the internal RTC */
+				status = "disabled";
+			};
 			serial@12000 {
 				status = "okay";
 			};
diff --git a/arch/arm/boot/dts/armada-xp.dtsi b/arch/arm/boot/dts/armada-xp.dtsi
index bff9f6c18db..66d25b78806 100644
--- a/arch/arm/boot/dts/armada-xp.dtsi
+++ b/arch/arm/boot/dts/armada-xp.dtsi
@@ -125,7 +125,7 @@
 			};
 
 			eth2: ethernet@30000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x30000 0x4000>;
 				interrupts = <12>;
 				clocks = <&gateclk 2>;
@@ -168,6 +168,14 @@
 				};
 			};
 
+			ethernet@70000 {
+				compatible = "marvell,armada-xp-neta";
+			};
+
+			ethernet@74000 {
+				compatible = "marvell,armada-xp-neta";
+			};
+
 			xor@f0900 {
 				compatible = "marvell,orion-xor";
 				reg = <0xF0900 0x100
diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts
index b5b84006469..d7f6ae4e5b9 100644
--- a/arch/arm/boot/dts/at91-sama5d4ek.dts
+++ b/arch/arm/boot/dts/at91-sama5d4ek.dts
@@ -108,8 +108,8 @@
 			mmc0: mmc@f8000000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_mmc0_clk_cmd_dat0 &pinctrl_mmc0_dat1_3 &pinctrl_mmc0_cd>;
-				slot@1 {
-					reg = <1>;
+				slot@0 {
+					reg = <0>;
 					bus-width = <4>;
 					cd-gpios = <&pioE 5 0>;
 				};
diff --git a/arch/arm/boot/dts/bcm63138.dtsi b/arch/arm/boot/dts/bcm63138.dtsi
index f3bb2dd6269..c97844cac4e 100644
--- a/arch/arm/boot/dts/bcm63138.dtsi
+++ b/arch/arm/boot/dts/bcm63138.dtsi
@@ -66,8 +66,9 @@
 			reg = <0x1d000 0x1000>;
 			cache-unified;
 			cache-level = <2>;
-			cache-sets = <16>;
-			cache-size = <0x80000>;
+			cache-size = <524288>;
+			cache-sets = <1024>;
+			cache-line-size = <32>;
 			interrupts = <GIC_PPI 0 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
diff --git a/arch/arm/boot/dts/berlin2q-marvell-dmp.dts b/arch/arm/boot/dts/berlin2q-marvell-dmp.dts
index ea1f99b8eed..45ac1d04cf4 100644
--- a/arch/arm/boot/dts/berlin2q-marvell-dmp.dts
+++ b/arch/arm/boot/dts/berlin2q-marvell-dmp.dts
@@ -30,6 +30,8 @@
 };
 
 &sdhci2 {
+	broken-cd;
+	bus-width = <8>;
 	non-removable;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/berlin2q.dtsi b/arch/arm/boot/dts/berlin2q.dtsi
index 891d56b0392..b805e19ed39 100644
--- a/arch/arm/boot/dts/berlin2q.dtsi
+++ b/arch/arm/boot/dts/berlin2q.dtsi
@@ -83,7 +83,8 @@
 			compatible = "mrvl,pxav3-mmc";
 			reg = <0xab1000 0x200>;
 			interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&chip CLKID_SDIO1XIN>;
+			clocks = <&chip CLKID_NFC_ECC>, <&chip CLKID_NFC>;
+			clock-names = "io", "core";
 			status = "disabled";
 		};
 
@@ -314,36 +315,6 @@
 				interrupt-parent = <&gic>;
 				interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>;
 			};
-
-			gpio4: gpio@5000 {
-				compatible = "snps,dw-apb-gpio";
-				reg = <0x5000 0x400>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				porte: gpio-port@4 {
-					compatible = "snps,dw-apb-gpio-port";
-					gpio-controller;
-					#gpio-cells = <2>;
-					snps,nr-gpios = <32>;
-					reg = <0>;
-				};
-			};
-
-			gpio5: gpio@c000 {
-				compatible = "snps,dw-apb-gpio";
-				reg = <0xc000 0x400>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				portf: gpio-port@5 {
-					compatible = "snps,dw-apb-gpio-port";
-					gpio-controller;
-					#gpio-cells = <2>;
-					snps,nr-gpios = <32>;
-					reg = <0>;
-				};
-			};
 		};
 
 		chip: chip-control@ea0000 {
@@ -372,6 +343,21 @@
 			ranges = <0 0xfc0000 0x10000>;
 			interrupt-parent = <&sic>;
 
+			sm_gpio1: gpio@5000 {
+				compatible = "snps,dw-apb-gpio";
+				reg = <0x5000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				portf: gpio-port@5 {
+					compatible = "snps,dw-apb-gpio-port";
+					gpio-controller;
+					#gpio-cells = <2>;
+					snps,nr-gpios = <32>;
+					reg = <0>;
+				};
+			};
+
 			i2c2: i2c@7000 {
 				compatible = "snps,designware-i2c";
 				#address-cells = <1>;
@@ -422,6 +408,21 @@
 				status = "disabled";
 			};
 
+			sm_gpio0: gpio@c000 {
+				compatible = "snps,dw-apb-gpio";
+				reg = <0xc000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				porte: gpio-port@4 {
+					compatible = "snps,dw-apb-gpio-port";
+					gpio-controller;
+					#gpio-cells = <2>;
+					snps,nr-gpios = <32>;
+					reg = <0>;
+				};
+			};
+
 			sysctrl: pin-controller@d000 {
 				compatible = "marvell,berlin2q-system-ctrl";
 				reg = <0xd000 0x100>;
diff --git a/arch/arm/boot/dts/dove.dtsi b/arch/arm/boot/dts/dove.dtsi
index a5441d5482a..3cc8b832034 100644
--- a/arch/arm/boot/dts/dove.dtsi
+++ b/arch/arm/boot/dts/dove.dtsi
@@ -154,7 +154,7 @@
 
 			uart2: serial@12200 {
 				compatible = "ns16550a";
-				reg = <0x12000 0x100>;
+				reg = <0x12200 0x100>;
 				reg-shift = <2>;
 				interrupts = <9>;
 				clocks = <&core_clk 0>;
@@ -163,7 +163,7 @@
 
 			uart3: serial@12300 {
 				compatible = "ns16550a";
-				reg = <0x12100 0x100>;
+				reg = <0x12300 0x100>;
 				reg-shift = <2>;
 				interrupts = <10>;
 				clocks = <&core_clk 0>;
diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts
index c6ce6258434..1bd6c79f445 100644
--- a/arch/arm/boot/dts/dra7-evm.dts
+++ b/arch/arm/boot/dts/dra7-evm.dts
@@ -399,23 +399,23 @@
 		};
 		partition@5 {
 			label = "QSPI.u-boot-spl-os";
-			reg = <0x00140000 0x00010000>;
+			reg = <0x00140000 0x00080000>;
 		};
 		partition@6 {
 			label = "QSPI.u-boot-env";
-			reg = <0x00150000 0x00010000>;
+			reg = <0x001c0000 0x00010000>;
 		};
 		partition@7 {
 			label = "QSPI.u-boot-env.backup1";
-			reg = <0x00160000 0x0010000>;
+			reg = <0x001d0000 0x0010000>;
 		};
 		partition@8 {
 			label = "QSPI.kernel";
-			reg = <0x00170000 0x0800000>;
+			reg = <0x001e0000 0x0800000>;
 		};
 		partition@9 {
 			label = "QSPI.file-system";
-			reg = <0x00970000 0x01690000>;
+			reg = <0x009e0000 0x01620000>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 9cc98436a98..666e796847d 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -653,7 +653,7 @@
 		};
 
 		wdt2: wdt@4ae14000 {
-			compatible = "ti,omap4-wdt";
+			compatible = "ti,omap3-wdt";
 			reg = <0x4ae14000 0x80>;
 			interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "wd_timer2";
diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi
index 2c05b3f017f..64c0f75b544 100644
--- a/arch/arm/boot/dts/dra7xx-clocks.dtsi
+++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi
@@ -243,10 +243,18 @@
 		ti,invert-autoidle-bit;
 	};
 
+	dpll_core_byp_mux: dpll_core_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		ti,bit-shift = <23>;
+		reg = <0x012c>;
+	};
+
 	dpll_core_ck: dpll_core_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-core-clock";
-		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		clocks = <&sys_clkin1>, <&dpll_core_byp_mux>;
 		reg = <0x0120>, <0x0124>, <0x012c>, <0x0128>;
 	};
 
@@ -309,10 +317,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_dsp_byp_mux: dpll_dsp_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&dsp_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x0240>;
+	};
+
 	dpll_dsp_ck: dpll_dsp_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&dsp_dpll_hs_clk_div>;
+		clocks = <&sys_clkin1>, <&dpll_dsp_byp_mux>;
 		reg = <0x0234>, <0x0238>, <0x0240>, <0x023c>;
 	};
 
@@ -335,10 +351,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_iva_byp_mux: dpll_iva_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&iva_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x01ac>;
+	};
+
 	dpll_iva_ck: dpll_iva_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&iva_dpll_hs_clk_div>;
+		clocks = <&sys_clkin1>, <&dpll_iva_byp_mux>;
 		reg = <0x01a0>, <0x01a4>, <0x01ac>, <0x01a8>;
 	};
 
@@ -361,10 +385,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_gpu_byp_mux: dpll_gpu_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		ti,bit-shift = <23>;
+		reg = <0x02e4>;
+	};
+
 	dpll_gpu_ck: dpll_gpu_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		clocks = <&sys_clkin1>, <&dpll_gpu_byp_mux>;
 		reg = <0x02d8>, <0x02dc>, <0x02e4>, <0x02e0>;
 	};
 
@@ -398,10 +430,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_ddr_byp_mux: dpll_ddr_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		ti,bit-shift = <23>;
+		reg = <0x021c>;
+	};
+
 	dpll_ddr_ck: dpll_ddr_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		clocks = <&sys_clkin1>, <&dpll_ddr_byp_mux>;
 		reg = <0x0210>, <0x0214>, <0x021c>, <0x0218>;
 	};
 
@@ -416,10 +456,18 @@
 		ti,invert-autoidle-bit;
 	};
 
+	dpll_gmac_byp_mux: dpll_gmac_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		ti,bit-shift = <23>;
+		reg = <0x02b4>;
+	};
+
 	dpll_gmac_ck: dpll_gmac_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		clocks = <&sys_clkin1>, <&dpll_gmac_byp_mux>;
 		reg = <0x02a8>, <0x02ac>, <0x02b4>, <0x02b0>;
 	};
 
@@ -482,10 +530,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_eve_byp_mux: dpll_eve_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&eve_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x0290>;
+	};
+
 	dpll_eve_ck: dpll_eve_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&eve_dpll_hs_clk_div>;
+		clocks = <&sys_clkin1>, <&dpll_eve_byp_mux>;
 		reg = <0x0284>, <0x0288>, <0x0290>, <0x028c>;
 	};
 
@@ -1249,10 +1305,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_per_byp_mux: dpll_per_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&per_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x014c>;
+	};
+
 	dpll_per_ck: dpll_per_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&per_dpll_hs_clk_div>;
+		clocks = <&sys_clkin1>, <&dpll_per_byp_mux>;
 		reg = <0x0140>, <0x0144>, <0x014c>, <0x0148>;
 	};
 
@@ -1275,10 +1339,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_usb_byp_mux: dpll_usb_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&usb_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x018c>;
+	};
+
 	dpll_usb_ck: dpll_usb_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-j-type-clock";
-		clocks = <&sys_clkin1>, <&usb_dpll_hs_clk_div>;
+		clocks = <&sys_clkin1>, <&dpll_usb_byp_mux>;
 		reg = <0x0180>, <0x0184>, <0x018c>, <0x0188>;
 	};
 
diff --git a/arch/arm/boot/dts/exynos4.dtsi b/arch/arm/boot/dts/exynos4.dtsi
index e0278ecbc81..98960b7bc51 100644
--- a/arch/arm/boot/dts/exynos4.dtsi
+++ b/arch/arm/boot/dts/exynos4.dtsi
@@ -368,7 +368,7 @@
 	};
 
 	i2s1: i2s@13960000 {
-		compatible = "samsung,s5pv210-i2s";
+		compatible = "samsung,s3c6410-i2s";
 		reg = <0x13960000 0x100>;
 		clocks = <&clock CLK_I2S1>;
 		clock-names = "iis";
@@ -378,7 +378,7 @@
 	};
 
 	i2s2: i2s@13970000 {
-		compatible = "samsung,s5pv210-i2s";
+		compatible = "samsung,s3c6410-i2s";
 		reg = <0x13970000 0x100>;
 		clocks = <&clock CLK_I2S2>;
 		clock-names = "iis";
diff --git a/arch/arm/boot/dts/hip04.dtsi b/arch/arm/boot/dts/hip04.dtsi
index 93b6c909e99..44044f27511 100644
--- a/arch/arm/boot/dts/hip04.dtsi
+++ b/arch/arm/boot/dts/hip04.dtsi
@@ -190,6 +190,12 @@
 		clock-frequency = <168000000>;
 	};
 
+	clk_375m: clk_375m {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <375000000>;
+	};
+
 	soc {
 		/* It's a 32-bit SoC. */
 		#address-cells = <1>;
@@ -264,4 +270,714 @@
 		};
 
 	};
+
+	etb@0,e3c42000 {
+		compatible = "arm,coresight-etb10", "arm,primecell";
+		reg = <0 0xe3c42000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		port {
+			etb0_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator0_out_port0>;
+			};
+		};
+	};
+
+	etb@0,e3c82000 {
+		compatible = "arm,coresight-etb10", "arm,primecell";
+		reg = <0 0xe3c82000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		port {
+			etb1_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator1_out_port0>;
+			};
+		};
+	};
+
+	etb@0,e3cc2000 {
+		compatible = "arm,coresight-etb10", "arm,primecell";
+		reg = <0 0xe3cc2000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		port {
+			etb2_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator2_out_port0>;
+			};
+		};
+	};
+
+	etb@0,e3d02000 {
+		compatible = "arm,coresight-etb10", "arm,primecell";
+		reg = <0 0xe3d02000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		port {
+			etb3_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator3_out_port0>;
+			};
+		};
+	};
+
+	tpiu@0,e3c05000 {
+		compatible = "arm,coresight-tpiu", "arm,primecell";
+		reg = <0 0xe3c05000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		port {
+			tpiu_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&funnel4_out_port0>;
+			};
+		};
+	};
+
+	replicator0 {
+		/* non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator0_out_port0: endpoint {
+					remote-endpoint = <&etb0_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator0_out_port1: endpoint {
+					remote-endpoint = <&funnel4_in_port0>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator0_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&funnel0_out_port0>;
+				};
+			};
+		};
+	};
+
+	replicator1 {
+		/* non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator1_out_port0: endpoint {
+					remote-endpoint = <&etb1_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator1_out_port1: endpoint {
+					remote-endpoint = <&funnel4_in_port1>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator1_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&funnel1_out_port0>;
+				};
+			};
+		};
+	};
+
+	replicator2 {
+		/* non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator2_out_port0: endpoint {
+					remote-endpoint = <&etb2_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+					replicator2_out_port1: endpoint {
+					remote-endpoint = <&funnel4_in_port2>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator2_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&funnel2_out_port0>;
+				};
+			};
+		};
+	};
+
+	replicator3 {
+		/* non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator3_out_port0: endpoint {
+					remote-endpoint = <&etb3_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator3_out_port1: endpoint {
+					remote-endpoint = <&funnel4_in_port3>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator3_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&funnel3_out_port0>;
+				};
+			};
+		};
+	};
+
+	funnel@0,e3c41000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0xe3c41000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel0_out_port0: endpoint {
+					remote-endpoint =
+						<&replicator0_in_port0>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel0_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm0_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel0_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm1_out_port>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel0_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm2_out_port>;
+				};
+			};
+
+			port@4 {
+				reg = <3>;
+				funnel0_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm3_out_port>;
+				};
+			};
+		};
+	};
+
+	funnel@0,e3c81000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0xe3c81000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel1_out_port0: endpoint {
+					remote-endpoint =
+						<&replicator1_in_port0>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel1_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm4_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel1_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm5_out_port>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel1_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm6_out_port>;
+				};
+			};
+
+			port@4 {
+				reg = <3>;
+				funnel1_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm7_out_port>;
+				};
+			};
+		};
+	};
+
+	funnel@0,e3cc1000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0xe3cc1000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel2_out_port0: endpoint {
+					remote-endpoint =
+						<&replicator2_in_port0>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel2_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm8_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel2_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm9_out_port>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel2_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm10_out_port>;
+				};
+			};
+
+			port@4 {
+				reg = <3>;
+				funnel2_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm11_out_port>;
+				};
+			};
+		};
+	};
+
+	funnel@0,e3d01000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0xe3d01000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel3_out_port0: endpoint {
+					remote-endpoint =
+						<&replicator3_in_port0>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel3_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm12_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel3_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm13_out_port>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel3_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm14_out_port>;
+				};
+			};
+
+			port@4 {
+				reg = <3>;
+				funnel3_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm15_out_port>;
+				};
+			};
+		};
+	};
+
+	funnel@0,e3c04000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0xe3c04000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel4_out_port0: endpoint {
+					remote-endpoint = <&tpiu_in_port>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel4_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint =
+						<&replicator0_out_port1>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel4_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint =
+						<&replicator1_out_port1>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel4_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint =
+						<&replicator2_out_port1>;
+				};
+			};
+
+			port@4 {
+				reg = <3>;
+				funnel4_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint =
+						<&replicator3_out_port1>;
+				};
+			};
+		};
+	};
+
+	ptm@0,e3c7c000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3c7c000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU0>;
+		port {
+			ptm0_out_port: endpoint {
+				remote-endpoint = <&funnel0_in_port0>;
+			};
+		};
+	};
+
+	ptm@0,e3c7d000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3c7d000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU1>;
+		port {
+			ptm1_out_port: endpoint {
+				remote-endpoint = <&funnel0_in_port1>;
+			};
+		};
+	};
+
+	ptm@0,e3c7e000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3c7e000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU2>;
+		port {
+			ptm2_out_port: endpoint {
+				remote-endpoint = <&funnel0_in_port2>;
+			};
+		};
+	};
+
+	ptm@0,e3c7f000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3c7f000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU3>;
+		port {
+			ptm3_out_port: endpoint {
+				remote-endpoint = <&funnel0_in_port3>;
+			};
+		};
+	};
+
+	ptm@0,e3cbc000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cbc000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU4>;
+		port {
+			ptm4_out_port: endpoint {
+				remote-endpoint = <&funnel1_in_port0>;
+			};
+		};
+	};
+
+	ptm@0,e3cbd000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cbd000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU5>;
+		port {
+			ptm5_out_port: endpoint {
+				remote-endpoint = <&funnel1_in_port1>;
+			};
+		};
+	};
+
+	ptm@0,e3cbe000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cbe000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU6>;
+		port {
+			ptm6_out_port: endpoint {
+				remote-endpoint = <&funnel1_in_port2>;
+			};
+		};
+	};
+
+	ptm@0,e3cbf000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cbf000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU7>;
+		port {
+			ptm7_out_port: endpoint {
+				remote-endpoint = <&funnel1_in_port3>;
+			};
+		};
+	};
+
+	ptm@0,e3cfc000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cfc000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU8>;
+		port {
+			ptm8_out_port: endpoint {
+				remote-endpoint = <&funnel2_in_port0>;
+			};
+		};
+	};
+
+	ptm@0,e3cfd000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cfd000 0 0x1000>;
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU9>;
+		port {
+			ptm9_out_port: endpoint {
+				remote-endpoint = <&funnel2_in_port1>;
+			};
+		};
+	};
+
+	ptm@0,e3cfe000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cfe000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU10>;
+		port {
+			ptm10_out_port: endpoint {
+				remote-endpoint = <&funnel2_in_port2>;
+			};
+		};
+	};
+
+	ptm@0,e3cff000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cff000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU11>;
+		port {
+			ptm11_out_port: endpoint {
+				remote-endpoint = <&funnel2_in_port3>;
+			};
+		};
+	};
+
+	ptm@0,e3d3c000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3d3c000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU12>;
+		port {
+			ptm12_out_port: endpoint {
+				remote-endpoint = <&funnel3_in_port0>;
+			};
+		};
+	};
+
+	ptm@0,e3d3d000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3d3d000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU13>;
+		port {
+			ptm13_out_port: endpoint {
+				remote-endpoint = <&funnel3_in_port1>;
+			};
+		};
+	};
+
+	ptm@0,e3d3e000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3d3e000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU14>;
+		port {
+			ptm14_out_port: endpoint {
+				remote-endpoint = <&funnel3_in_port2>;
+			};
+		};
+	};
+
+	ptm@0,e3d3f000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3d3f000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU15>;
+		port {
+			ptm15_out_port: endpoint {
+				remote-endpoint = <&funnel3_in_port3>;
+			};
+		};
+	};
 };
diff --git a/arch/arm/boot/dts/imx23-olinuxino.dts b/arch/arm/boot/dts/imx23-olinuxino.dts
index 7e6eef2488e..82045398bf1 100644
--- a/arch/arm/boot/dts/imx23-olinuxino.dts
+++ b/arch/arm/boot/dts/imx23-olinuxino.dts
@@ -12,6 +12,7 @@
  */
 
 /dts-v1/;
+#include <dt-bindings/gpio/gpio.h>
 #include "imx23.dtsi"
 
 / {
@@ -93,6 +94,7 @@
 
 	ahb@80080000 {
 		usb0: usb@80080000 {
+			dr_mode = "host";
 			vbus-supply = <&reg_usb0_vbus>;
 			status = "okay";
 		};
@@ -122,7 +124,7 @@
 
 		user {
 			label = "green";
-			gpios = <&gpio2 1 1>;
+			gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi
index 58d3c3cf292..677f81d9dcd 100644
--- a/arch/arm/boot/dts/imx25.dtsi
+++ b/arch/arm/boot/dts/imx25.dtsi
@@ -162,7 +162,7 @@
 				#size-cells = <0>;
 				compatible = "fsl,imx25-cspi", "fsl,imx35-cspi";
 				reg = <0x43fa4000 0x4000>;
-				clocks = <&clks 62>, <&clks 62>;
+				clocks = <&clks 78>, <&clks 78>;
 				clock-names = "ipg", "per";
 				interrupts = <14>;
 				status = "disabled";
@@ -369,7 +369,7 @@
 				compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
 				#pwm-cells = <2>;
 				reg = <0x53fa0000 0x4000>;
-				clocks = <&clks 106>, <&clks 36>;
+				clocks = <&clks 106>, <&clks 52>;
 				clock-names = "ipg", "per";
 				interrupts = <36>;
 			};
@@ -388,7 +388,7 @@
 				compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
 				#pwm-cells = <2>;
 				reg = <0x53fa8000 0x4000>;
-				clocks = <&clks 107>, <&clks 36>;
+				clocks = <&clks 107>, <&clks 52>;
 				clock-names = "ipg", "per";
 				interrupts = <41>;
 			};
@@ -428,8 +428,9 @@
 
 			pwm4: pwm@53fc8000 {
 				compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
+				#pwm-cells = <2>;
 				reg = <0x53fc8000 0x4000>;
-				clocks = <&clks 108>, <&clks 36>;
+				clocks = <&clks 108>, <&clks 52>;
 				clock-names = "ipg", "per";
 				interrupts = <42>;
 			};
@@ -476,7 +477,7 @@
 				compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
 				#pwm-cells = <2>;
 				reg = <0x53fe0000 0x4000>;
-				clocks = <&clks 105>, <&clks 36>;
+				clocks = <&clks 105>, <&clks 52>;
 				clock-names = "ipg", "per";
 				interrupts = <26>;
 			};
diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi
index 107d713e1cb..12ac5f7e0a2 100644
--- a/arch/arm/boot/dts/imx27.dtsi
+++ b/arch/arm/boot/dts/imx27.dtsi
@@ -531,7 +531,7 @@
 
 			fec: ethernet@1002b000 {
 				compatible = "fsl,imx27-fec";
-				reg = <0x1002b000 0x4000>;
+				reg = <0x1002b000 0x1000>;
 				interrupts = <50>;
 				clocks = <&clks IMX27_CLK_FEC_IPG_GATE>,
 					 <&clks IMX27_CLK_FEC_AHB_GATE>;
diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi
index 47f68ac868d..5ed245a3f9a 100644
--- a/arch/arm/boot/dts/imx28.dtsi
+++ b/arch/arm/boot/dts/imx28.dtsi
@@ -900,7 +900,7 @@
 					      80 81 68 69
 					      70 71 72 73
 					      74 75 76 77>;
-				interrupt-names = "auart4-rx", "aurat4-tx", "spdif-tx", "empty",
+				interrupt-names = "auart4-rx", "auart4-tx", "spdif-tx", "empty",
 						  "saif0", "saif1", "i2c0", "i2c1",
 						  "auart0-rx", "auart0-tx", "auart1-rx", "auart1-tx",
 						  "auart2-rx", "auart2-tx", "auart3-rx", "auart3-tx";
diff --git a/arch/arm/boot/dts/imx51-babbage.dts b/arch/arm/boot/dts/imx51-babbage.dts
index 56569cecaa7..649befeb2cf 100644
--- a/arch/arm/boot/dts/imx51-babbage.dts
+++ b/arch/arm/boot/dts/imx51-babbage.dts
@@ -127,24 +127,12 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		reg_usbh1_vbus: regulator@0 {
-			compatible = "regulator-fixed";
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_usbh1reg>;
-			reg = <0>;
-			regulator-name = "usbh1_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-			gpio = <&gpio2 5 GPIO_ACTIVE_HIGH>;
-			enable-active-high;
-		};
-
-		reg_usbotg_vbus: regulator@1 {
+		reg_hub_reset: regulator@0 {
 			compatible = "regulator-fixed";
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_usbotgreg>;
-			reg = <1>;
-			regulator-name = "usbotg_vbus";
+			reg = <0>;
+			regulator-name = "hub_reset";
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
 			gpio = <&gpio1 7 GPIO_ACTIVE_HIGH>;
@@ -176,6 +164,7 @@
 			reg = <0>;
 			clocks = <&clks IMX5_CLK_DUMMY>;
 			clock-names = "main_clk";
+			reset-gpios = <&gpio2 5 GPIO_ACTIVE_LOW>;
 		};
 	};
 };
@@ -419,7 +408,7 @@
 &usbh1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usbh1>;
-	vbus-supply = <&reg_usbh1_vbus>;
+	vbus-supply = <&reg_hub_reset>;
 	fsl,usbphy = <&usbh1phy>;
 	phy_type = "ulpi";
 	status = "okay";
@@ -429,7 +418,6 @@
 	dr_mode = "otg";
 	disable-over-current;
 	phy_type = "utmi_wide";
-	vbus-supply = <&reg_usbotg_vbus>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
index 0e50bb0a6b9..41356975242 100644
--- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
@@ -31,6 +31,7 @@
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
 			gpio = <&gpio4 15 0>;
+			enable-active-high;
 		};
 
 		reg_usb_h1_vbus: regulator@1 {
@@ -40,6 +41,7 @@
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
 			gpio = <&gpio1 0 0>;
+			enable-active-high;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
index baf2f00d519..b57e554dba4 100644
--- a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
@@ -35,6 +35,7 @@
 			regulator-max-microvolt = <5000000>;
 			gpio = <&gpio3 22 0>;
 			enable-active-high;
+			vin-supply = <&swbst_reg>;
 		};
 
 		reg_usb_h1_vbus: regulator@1 {
@@ -45,6 +46,7 @@
 			regulator-max-microvolt = <5000000>;
 			gpio = <&gpio1 29 0>;
 			enable-active-high;
+			vin-supply = <&swbst_reg>;
 		};
 
 		reg_audio: regulator@2 {
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index bc82a12d4c2..ae630a928ac 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -445,6 +445,8 @@
 		DRVDD-supply = <&vmmc2>;
 		IOVDD-supply = <&vio>;
 		DVDD-supply = <&vio>;
+
+		ai3x-micbias-vg = <1>;
 	};
 
 	tlv320aic3x_aux: tlv320aic3x@19 {
@@ -456,6 +458,8 @@
 		DRVDD-supply = <&vmmc2>;
 		IOVDD-supply = <&vio>;
 		DVDD-supply = <&vio>;
+
+		ai3x-micbias-vg = <2>;
 	};
 
 	tsl2563: tsl2563@29 {
diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi
index e06c11fa869..516d62ac25a 100644
--- a/arch/arm/boot/dts/r8a7791.dtsi
+++ b/arch/arm/boot/dts/r8a7791.dtsi
@@ -695,19 +695,19 @@
 		};
 
 		/* Variable factor clocks */
-		sd1_clk: sd2_clk@e6150078 {
+		sd2_clk: sd2_clk@e6150078 {
 			compatible = "renesas,r8a7791-div6-clock", "renesas,cpg-div6-clock";
 			reg = <0 0xe6150078 0 4>;
 			clocks = <&pll1_div2_clk>;
 			#clock-cells = <0>;
-			clock-output-names = "sd1";
+			clock-output-names = "sd2";
 		};
-		sd2_clk: sd3_clk@e615026c {
+		sd3_clk: sd3_clk@e615026c {
 			compatible = "renesas,r8a7791-div6-clock", "renesas,cpg-div6-clock";
 			reg = <0 0xe615026c 0 4>;
 			clocks = <&pll1_div2_clk>;
 			#clock-cells = <0>;
-			clock-output-names = "sd2";
+			clock-output-names = "sd3";
 		};
 		mmc0_clk: mmc0_clk@e6150240 {
 			compatible = "renesas,r8a7791-div6-clock", "renesas,cpg-div6-clock";
@@ -922,17 +922,20 @@
 		mstp3_clks: mstp3_clks@e615013c {
 			compatible = "renesas,r8a7791-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0 0xe615013c 0 4>, <0 0xe6150048 0 4>;
-			clocks = <&cp_clk>, <&sd2_clk>, <&sd1_clk>, <&cpg_clocks R8A7791_CLK_SD0>,
-				 <&mmc0_clk>, <&hp_clk>, <&mp_clk>, <&hp_clk>, <&mp_clk>, <&rclk_clk>;
+			clocks = <&cp_clk>, <&sd3_clk>, <&sd2_clk>, <&cpg_clocks R8A7791_CLK_SD0>,
+				 <&mmc0_clk>, <&hp_clk>, <&mp_clk>, <&hp_clk>, <&mp_clk>, <&rclk_clk>,
+				 <&hp_clk>, <&hp_clk>;
 			#clock-cells = <1>;
 			renesas,clock-indices = <
 				R8A7791_CLK_TPU0 R8A7791_CLK_SDHI2 R8A7791_CLK_SDHI1 R8A7791_CLK_SDHI0
 				R8A7791_CLK_MMCIF0 R8A7791_CLK_IIC0 R8A7791_CLK_PCIEC R8A7791_CLK_IIC1
 				R8A7791_CLK_SSUSB R8A7791_CLK_CMT1
+				R8A7791_CLK_USBDMAC0 R8A7791_CLK_USBDMAC1
 			>;
 			clock-output-names =
 				"tpu0", "sdhi2", "sdhi1", "sdhi0",
-				"mmcif0", "i2c7", "pciec", "i2c8", "ssusb", "cmt1";
+				"mmcif0", "i2c7", "pciec", "i2c8", "ssusb", "cmt1",
+				"usbdmac0", "usbdmac1";
 		};
 		mstp5_clks: mstp5_clks@e6150144 {
 			compatible = "renesas,r8a7791-mstp-clocks", "renesas,cpg-mstp-clocks";
diff --git a/arch/arm/boot/dts/s3c6410-mini6410.dts b/arch/arm/boot/dts/s3c6410-mini6410.dts
index 57e00f9bce9..a25debb5040 100644
--- a/arch/arm/boot/dts/s3c6410-mini6410.dts
+++ b/arch/arm/boot/dts/s3c6410-mini6410.dts
@@ -198,10 +198,6 @@
 	status = "okay";
 };
 
-&pwm {
-	status = "okay";
-};
-
 &pinctrl0 {
 	gpio_leds: gpio-leds {
 		samsung,pins = "gpk-4", "gpk-5", "gpk-6", "gpk-7";
diff --git a/arch/arm/boot/dts/s3c64xx.dtsi b/arch/arm/boot/dts/s3c64xx.dtsi
index ff5bdaac987..0ccb414cd26 100644
--- a/arch/arm/boot/dts/s3c64xx.dtsi
+++ b/arch/arm/boot/dts/s3c64xx.dtsi
@@ -172,7 +172,6 @@
 			clocks = <&clocks PCLK_PWM>;
 			samsung,pwm-outputs = <0>, <1>;
 			#pwm-cells = <3>;
-			status = "disabled";
 		};
 
 		pinctrl0: pinctrl@7f008000 {
diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi
index 9d2323020d3..563640f59a4 100644
--- a/arch/arm/boot/dts/ste-dbx5x0.dtsi
+++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi
@@ -995,23 +995,6 @@
 			status = "disabled";
 		};
 
-		vmmci: regulator-gpio {
-			compatible = "regulator-gpio";
-
-			regulator-min-microvolt = <1800000>;
-			regulator-max-microvolt = <2900000>;
-			regulator-name = "mmci-reg";
-			regulator-type = "voltage";
-
-			startup-delay-us = <100>;
-			enable-active-high;
-
-			states = <1800000 0x1
-				  2900000 0x0>;
-
-			status = "disabled";
-		};
-
 		mcde@a0350000 {
 			compatible = "stericsson,mcde";
 			reg = <0xa0350000 0x1000>, /* MCDE */
diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi
index bf8f0eddc2c..744c1e3a744 100644
--- a/arch/arm/boot/dts/ste-href.dtsi
+++ b/arch/arm/boot/dts/ste-href.dtsi
@@ -111,6 +111,21 @@
 			pinctrl-1 = <&i2c3_sleep_mode>;
 		};
 
+		vmmci: regulator-gpio {
+			compatible = "regulator-gpio";
+
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2900000>;
+			regulator-name = "mmci-reg";
+			regulator-type = "voltage";
+
+			startup-delay-us = <100>;
+			enable-active-high;
+
+			states = <1800000 0x1
+				  2900000 0x0>;
+		};
+
 		// External Micro SD slot
 		sdi0_per1@80126000 {
 			arm,primecell-periphid = <0x10480180>;
diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts
index 3e97a669f15..17c4422def0 100644
--- a/arch/arm/boot/dts/ste-snowball.dts
+++ b/arch/arm/boot/dts/ste-snowball.dts
@@ -146,8 +146,21 @@
 		};
 
 		vmmci: regulator-gpio {
+			compatible = "regulator-gpio";
+
 			gpios = <&gpio7 4 0x4>;
 			enable-gpio = <&gpio6 25 0x4>;
+
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2900000>;
+			regulator-name = "mmci-reg";
+			regulator-type = "voltage";
+
+			startup-delay-us = <100>;
+			enable-active-high;
+
+			states = <1800000 0x1
+				  2900000 0x0>;
 		};
 
 		// External Micro SD slot
diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi
index 8acf5d85c99..f76fe94267d 100644
--- a/arch/arm/boot/dts/tegra20.dtsi
+++ b/arch/arm/boot/dts/tegra20.dtsi
@@ -68,9 +68,9 @@
 			reset-names = "2d";
 		};
 
-		gr3d@54140000 {
+		gr3d@54180000 {
 			compatible = "nvidia,tegra20-gr3d";
-			reg = <0x54140000 0x00040000>;
+			reg = <0x54180000 0x00040000>;
 			clocks = <&tegra_car TEGRA20_CLK_GR3D>;
 			resets = <&tegra_car 24>;
 			reset-names = "3d";
@@ -130,9 +130,9 @@
 			status = "disabled";
 		};
 
-		dsi@542c0000 {
+		dsi@54300000 {
 			compatible = "nvidia,tegra20-dsi";
-			reg = <0x542c0000 0x00040000>;
+			reg = <0x54300000 0x00040000>;
 			clocks = <&tegra_car TEGRA20_CLK_DSI>;
 			resets = <&tegra_car 48>;
 			reset-names = "dsi";
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
index 322fd1519b0..7a2aeacd62c 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
@@ -358,6 +358,204 @@
 		};
 	};
 
+	etb@0,20010000 {
+		compatible = "arm,coresight-etb10", "arm,primecell";
+		reg = <0 0x20010000 0 0x1000>;
+
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			etb_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator_out_port0>;
+			};
+		};
+	};
+
+	tpiu@0,20030000 {
+		compatible = "arm,coresight-tpiu", "arm,primecell";
+		reg = <0 0x20030000 0 0x1000>;
+
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			tpiu_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator_out_port1>;
+			};
+		};
+	};
+
+	replicator {
+		/* non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator_out_port0: endpoint {
+					remote-endpoint = <&etb_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator_out_port1: endpoint {
+					remote-endpoint = <&tpiu_in_port>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&funnel_out_port0>;
+				};
+			};
+		};
+	};
+
+	funnel@0,20040000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0x20040000 0 0x1000>;
+
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel_out_port0: endpoint {
+					remote-endpoint =
+						<&replicator_in_port0>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm0_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm1_out_port>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&etm0_out_port>;
+				};
+			};
+
+			/* Input port #3 is for ITM, not supported here */
+
+			port@4 {
+				reg = <4>;
+				funnel_in_port4: endpoint {
+					slave-mode;
+					remote-endpoint = <&etm1_out_port>;
+				};
+			};
+
+			port@5 {
+				reg = <5>;
+				funnel_in_port5: endpoint {
+					slave-mode;
+					remote-endpoint = <&etm2_out_port>;
+				};
+			};
+		};
+	};
+
+	ptm@0,2201c000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0x2201c000 0 0x1000>;
+
+		cpu = <&cpu0>;
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			ptm0_out_port: endpoint {
+				remote-endpoint = <&funnel_in_port0>;
+			};
+		};
+	};
+
+	ptm@0,2201d000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0x2201d000 0 0x1000>;
+
+		cpu = <&cpu1>;
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			ptm1_out_port: endpoint {
+				remote-endpoint = <&funnel_in_port1>;
+			};
+		};
+	};
+
+	etm@0,2203c000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0x2203c000 0 0x1000>;
+
+		cpu = <&cpu2>;
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			etm0_out_port: endpoint {
+				remote-endpoint = <&funnel_in_port2>;
+			};
+		};
+	};
+
+	etm@0,2203d000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0x2203d000 0 0x1000>;
+
+		cpu = <&cpu3>;
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			etm1_out_port: endpoint {
+				remote-endpoint = <&funnel_in_port4>;
+			};
+		};
+	};
+
+	etm@0,2203e000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0x2203e000 0 0x1000>;
+
+		cpu = <&cpu4>;
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			etm2_out_port: endpoint {
+				remote-endpoint = <&funnel_in_port5>;
+			};
+		};
+	};
+
 	smb {
 		compatible = "simple-bus";
 
diff --git a/arch/arm/common/Kconfig b/arch/arm/common/Kconfig
index c3a4e9ceba3..f4a38a76db6 100644
--- a/arch/arm/common/Kconfig
+++ b/arch/arm/common/Kconfig
@@ -20,3 +20,7 @@ config SHARP_SCOOP
 
 config TI_PRIV_EDMA
 	bool
+
+config FIQ_GLUE
+	bool
+	select FIQ
diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile
index 70b1eff477b..5748afda068 100644
--- a/arch/arm/common/Makefile
+++ b/arch/arm/common/Makefile
@@ -4,6 +4,7 @@
 
 obj-y				+= firmware.o
 
+obj-$(CONFIG_FIQ_GLUE)		+= fiq_glue.o fiq_glue_setup.o
 obj-$(CONFIG_ICST)		+= icst.o
 obj-$(CONFIG_SA1111)		+= sa1111.o
 obj-$(CONFIG_DMABOUNCE)		+= dmabounce.o
diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c
index 6eaddc47c43..32d8281e642 100644
--- a/arch/arm/common/bL_switcher.c
+++ b/arch/arm/common/bL_switcher.c
@@ -784,7 +784,11 @@ static int bL_switcher_hotplug_callback(struct notifier_block *nfb,
 	return NOTIFY_DONE;
 }
 
+#ifdef CONFIG_SCHED_HMP
+static bool no_bL_switcher = true;
+#else
 static bool no_bL_switcher;
+#endif
 core_param(no_bL_switcher, no_bL_switcher, bool, 0644);
 
 static int __init bL_switcher_init(void)
diff --git a/arch/arm/common/fiq_glue.S b/arch/arm/common/fiq_glue.S
new file mode 100644
index 00000000000..24b42cec481
--- /dev/null
+++ b/arch/arm/common/fiq_glue.S
@@ -0,0 +1,118 @@
+/*
+ * Copyright (C) 2008 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+		.text
+
+		.global fiq_glue_end
+
+		/* fiq stack: r0-r15,cpsr,spsr of interrupted mode */
+
+ENTRY(fiq_glue)
+		/* store pc, cpsr from previous mode, reserve space for spsr */
+		mrs	r12, spsr
+		sub	lr, lr, #4
+		subs	r10, #1
+		bne	nested_fiq
+
+		str	r12, [sp, #-8]!
+		str	lr, [sp, #-4]!
+
+		/* store r8-r14 from previous mode */
+		sub	sp, sp, #(7 * 4)
+		stmia	sp, {r8-r14}^
+		nop
+
+		/* store r0-r7 from previous mode */
+		stmfd	sp!, {r0-r7}
+
+		/* setup func(data,regs) arguments */
+		mov	r0, r9
+		mov	r1, sp
+		mov	r3, r8
+
+		mov	r7, sp
+
+		/* Get sp and lr from non-user modes */
+		and	r4, r12, #MODE_MASK
+		cmp	r4, #USR_MODE
+		beq	fiq_from_usr_mode
+
+		mov	r7, sp
+		orr	r4, r4, #(PSR_I_BIT | PSR_F_BIT)
+		msr	cpsr_c, r4
+		str	sp, [r7, #(4 * 13)]
+		str	lr, [r7, #(4 * 14)]
+		mrs	r5, spsr
+		str	r5, [r7, #(4 * 17)]
+
+		cmp	r4, #(SVC_MODE | PSR_I_BIT | PSR_F_BIT)
+		/* use fiq stack if we reenter this mode */
+		subne	sp, r7, #(4 * 3)
+
+fiq_from_usr_mode:
+		msr	cpsr_c, #(SVC_MODE | PSR_I_BIT | PSR_F_BIT)
+		mov	r2, sp
+		sub	sp, r7, #12
+		stmfd	sp!, {r2, ip, lr}
+		/* call func(data,regs) */
+		blx	r3
+		ldmfd	sp, {r2, ip, lr}
+		mov	sp, r2
+
+		/* restore/discard saved state */
+		cmp	r4, #USR_MODE
+		beq	fiq_from_usr_mode_exit
+
+		msr	cpsr_c, r4
+		ldr	sp, [r7, #(4 * 13)]
+		ldr	lr, [r7, #(4 * 14)]
+		msr	spsr_cxsf, r5
+
+fiq_from_usr_mode_exit:
+		msr	cpsr_c, #(FIQ_MODE | PSR_I_BIT | PSR_F_BIT)
+
+		ldmfd	sp!, {r0-r7}
+		ldr	lr, [sp, #(4 * 7)]
+		ldr	r12, [sp, #(4 * 8)]
+		add	sp, sp, #(10 * 4)
+exit_fiq:
+		msr	spsr_cxsf, r12
+		add	r10, #1
+		cmp	r11, #0
+		moveqs	pc, lr
+		bx	r11 /* jump to custom fiq return function */
+
+nested_fiq:
+		orr	r12, r12, #(PSR_F_BIT)
+		b	exit_fiq
+
+fiq_glue_end:
+
+ENTRY(fiq_glue_setup) /* func, data, sp, smc call number */
+		stmfd		sp!, {r4}
+		mrs		r4, cpsr
+		msr		cpsr_c, #(FIQ_MODE | PSR_I_BIT | PSR_F_BIT)
+		movs		r8, r0
+		mov		r9, r1
+		mov		sp, r2
+		mov		r11, r3
+		moveq		r10, #0
+		movne		r10, #1
+		msr		cpsr_c, r4
+		ldmfd		sp!, {r4}
+		bx		lr
+
diff --git a/arch/arm/common/fiq_glue_setup.c b/arch/arm/common/fiq_glue_setup.c
new file mode 100644
index 00000000000..8cb1b611c6d
--- /dev/null
+++ b/arch/arm/common/fiq_glue_setup.c
@@ -0,0 +1,147 @@
+/*
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+#include <asm/fiq.h>
+#include <asm/fiq_glue.h>
+
+extern unsigned char fiq_glue, fiq_glue_end;
+extern void fiq_glue_setup(void *func, void *data, void *sp,
+			   fiq_return_handler_t fiq_return_handler);
+
+static struct fiq_handler fiq_debbuger_fiq_handler = {
+	.name = "fiq_glue",
+};
+DEFINE_PER_CPU(void *, fiq_stack);
+static struct fiq_glue_handler *current_handler;
+static fiq_return_handler_t fiq_return_handler;
+static DEFINE_MUTEX(fiq_glue_lock);
+
+static void fiq_glue_setup_helper(void *info)
+{
+	struct fiq_glue_handler *handler = info;
+	fiq_glue_setup(handler->fiq, handler,
+		__get_cpu_var(fiq_stack) + THREAD_START_SP,
+		fiq_return_handler);
+}
+
+int fiq_glue_register_handler(struct fiq_glue_handler *handler)
+{
+	int ret;
+	int cpu;
+
+	if (!handler || !handler->fiq)
+		return -EINVAL;
+
+	mutex_lock(&fiq_glue_lock);
+	if (fiq_stack) {
+		ret = -EBUSY;
+		goto err_busy;
+	}
+
+	for_each_possible_cpu(cpu) {
+		void *stack;
+		stack = (void *)__get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER);
+		if (WARN_ON(!stack)) {
+			ret = -ENOMEM;
+			goto err_alloc_fiq_stack;
+		}
+		per_cpu(fiq_stack, cpu) = stack;
+	}
+
+	ret = claim_fiq(&fiq_debbuger_fiq_handler);
+	if (WARN_ON(ret))
+		goto err_claim_fiq;
+
+	current_handler = handler;
+	on_each_cpu(fiq_glue_setup_helper, handler, true);
+	set_fiq_handler(&fiq_glue, &fiq_glue_end - &fiq_glue);
+
+	mutex_unlock(&fiq_glue_lock);
+	return 0;
+
+err_claim_fiq:
+err_alloc_fiq_stack:
+	for_each_possible_cpu(cpu) {
+		__free_pages(per_cpu(fiq_stack, cpu), THREAD_SIZE_ORDER);
+		per_cpu(fiq_stack, cpu) = NULL;
+	}
+err_busy:
+	mutex_unlock(&fiq_glue_lock);
+	return ret;
+}
+
+static void fiq_glue_update_return_handler(void (*fiq_return)(void))
+{
+	fiq_return_handler = fiq_return;
+	if (current_handler)
+		on_each_cpu(fiq_glue_setup_helper, current_handler, true);
+}
+
+int fiq_glue_set_return_handler(void (*fiq_return)(void))
+{
+	int ret;
+
+	mutex_lock(&fiq_glue_lock);
+	if (fiq_return_handler) {
+		ret = -EBUSY;
+		goto err_busy;
+	}
+	fiq_glue_update_return_handler(fiq_return);
+	ret = 0;
+err_busy:
+	mutex_unlock(&fiq_glue_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL(fiq_glue_set_return_handler);
+
+int fiq_glue_clear_return_handler(void (*fiq_return)(void))
+{
+	int ret;
+
+	mutex_lock(&fiq_glue_lock);
+	if (WARN_ON(fiq_return_handler != fiq_return)) {
+		ret = -EINVAL;
+		goto err_inval;
+	}
+	fiq_glue_update_return_handler(NULL);
+	ret = 0;
+err_inval:
+	mutex_unlock(&fiq_glue_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL(fiq_glue_clear_return_handler);
+
+/**
+ * fiq_glue_resume - Restore fiqs after suspend or low power idle states
+ *
+ * This must be called before calling local_fiq_enable after returning from a
+ * power state where the fiq mode registers were lost. If a driver provided
+ * a resume hook when it registered the handler it will be called.
+ */
+
+void fiq_glue_resume(void)
+{
+	if (!current_handler)
+		return;
+	fiq_glue_setup(current_handler->fiq, current_handler,
+		__get_cpu_var(fiq_stack) + THREAD_START_SP,
+		fiq_return_handler);
+	if (current_handler->resume)
+		current_handler->resume(current_handler);
+}
+
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 9d7a32f93fc..37560f19d34 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -320,6 +320,7 @@ CONFIG_USB=y
 CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_XHCI_MVEBU=y
 CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_EXYNOS=y
 CONFIG_USB_EHCI_TEGRA=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_USB_ISP1760_HCD=y
@@ -445,4 +446,4 @@ CONFIG_DEBUG_FS=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_LOCKUP_DETECTOR=y
 CONFIG_CRYPTO_DEV_TEGRA_AES=y
-CONFIG_GENERIC_CPUFREQ_CPU0=y
+CONFIG_CPUFREQ_DT=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index b3f86670d2e..a0e51bb68b2 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -68,7 +68,7 @@ CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
-CONFIG_GENERIC_CPUFREQ_CPU0=y
+CONFIG_CPUFREQ_DT=y
 # CONFIG_ARM_OMAP2PLUS_CPUFREQ is not set
 CONFIG_CPU_IDLE=y
 CONFIG_BINFMT_MISC=y
diff --git a/arch/arm/configs/shmobile_defconfig b/arch/arm/configs/shmobile_defconfig
index d7346ad5104..bfe79d5b821 100644
--- a/arch/arm/configs/shmobile_defconfig
+++ b/arch/arm/configs/shmobile_defconfig
@@ -176,5 +176,5 @@ CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
 CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
 CONFIG_CPU_THERMAL=y
-CONFIG_GENERIC_CPUFREQ_CPU0=y
+CONFIG_CPUFREQ_DT=y
 CONFIG_REGULATOR_DA9210=y
diff --git a/arch/arm/crypto/aes_glue.c b/arch/arm/crypto/aes_glue.c
index 3003fa1f6fb..0409b8f8978 100644
--- a/arch/arm/crypto/aes_glue.c
+++ b/arch/arm/crypto/aes_glue.c
@@ -93,6 +93,6 @@ module_exit(aes_fini);
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm (ASM)");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("aes");
-MODULE_ALIAS("aes-asm");
+MODULE_ALIAS_CRYPTO("aes");
+MODULE_ALIAS_CRYPTO("aes-asm");
 MODULE_AUTHOR("David McCullough <ucdevel@gmail.com>");
diff --git a/arch/arm/crypto/aesbs-core.S_shipped b/arch/arm/crypto/aesbs-core.S_shipped
index 71e5fc7cfb1..1d1800f71c5 100644
--- a/arch/arm/crypto/aesbs-core.S_shipped
+++ b/arch/arm/crypto/aesbs-core.S_shipped
@@ -58,14 +58,18 @@
 # define VFP_ABI_FRAME	0
 # define BSAES_ASM_EXTENDED_KEY
 # define XTS_CHAIN_TWEAK
-# define __ARM_ARCH__	7
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
 #endif
 
 #ifdef __thumb__
 # define adrl adr
 #endif
 
-#if __ARM_ARCH__>=7
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
 .text
 .syntax	unified 	@ ARMv7-capable assembler is expected to handle this
 #ifdef __thumb2__
@@ -74,8 +78,6 @@
 .code   32
 #endif
 
-.fpu	neon
-
 .type	_bsaes_decrypt8,%function
 .align	4
 _bsaes_decrypt8:
@@ -2095,9 +2097,11 @@ bsaes_xts_decrypt:
 	vld1.8	{q8}, [r0]			@ initial tweak
 	adr	r2, .Lxts_magic
 
+#ifndef	XTS_CHAIN_TWEAK
 	tst	r9, #0xf			@ if not multiple of 16
 	it	ne				@ Thumb2 thing, sanity check in ARM
 	subne	r9, #0x10			@ subtract another 16 bytes
+#endif
 	subs	r9, #0x80
 
 	blo	.Lxts_dec_short
diff --git a/arch/arm/crypto/bsaes-armv7.pl b/arch/arm/crypto/bsaes-armv7.pl
index be068db960e..a4d3856e7d2 100644
--- a/arch/arm/crypto/bsaes-armv7.pl
+++ b/arch/arm/crypto/bsaes-armv7.pl
@@ -701,14 +701,18 @@ $code.=<<___;
 # define VFP_ABI_FRAME	0
 # define BSAES_ASM_EXTENDED_KEY
 # define XTS_CHAIN_TWEAK
-# define __ARM_ARCH__	7
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
 #endif
 
 #ifdef __thumb__
 # define adrl adr
 #endif
 
-#if __ARM_ARCH__>=7
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
 .text
 .syntax	unified 	@ ARMv7-capable assembler is expected to handle this
 #ifdef __thumb2__
@@ -717,8 +721,6 @@ $code.=<<___;
 .code   32
 #endif
 
-.fpu	neon
-
 .type	_bsaes_decrypt8,%function
 .align	4
 _bsaes_decrypt8:
@@ -2076,9 +2078,11 @@ bsaes_xts_decrypt:
 	vld1.8	{@XMM[8]}, [r0]			@ initial tweak
 	adr	$magic, .Lxts_magic
 
+#ifndef	XTS_CHAIN_TWEAK
 	tst	$len, #0xf			@ if not multiple of 16
 	it	ne				@ Thumb2 thing, sanity check in ARM
 	subne	$len, #0x10			@ subtract another 16 bytes
+#endif
 	subs	$len, #0x80
 
 	blo	.Lxts_dec_short
diff --git a/arch/arm/crypto/sha1_glue.c b/arch/arm/crypto/sha1_glue.c
index 84f2a756588..e31b0440c61 100644
--- a/arch/arm/crypto/sha1_glue.c
+++ b/arch/arm/crypto/sha1_glue.c
@@ -171,5 +171,5 @@ module_exit(sha1_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm (ARM)");
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
 MODULE_AUTHOR("David McCullough <ucdevel@gmail.com>");
diff --git a/arch/arm/crypto/sha1_neon_glue.c b/arch/arm/crypto/sha1_neon_glue.c
index 6f1b411b1d5..0b0083757d4 100644
--- a/arch/arm/crypto/sha1_neon_glue.c
+++ b/arch/arm/crypto/sha1_neon_glue.c
@@ -194,4 +194,4 @@ module_exit(sha1_neon_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, NEON accelerated");
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
diff --git a/arch/arm/crypto/sha512_neon_glue.c b/arch/arm/crypto/sha512_neon_glue.c
index 0d2758ff5e1..f3452c66059 100644
--- a/arch/arm/crypto/sha512_neon_glue.c
+++ b/arch/arm/crypto/sha512_neon_glue.c
@@ -301,5 +301,5 @@ module_exit(sha512_neon_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, NEON accelerated");
 
-MODULE_ALIAS("sha512");
-MODULE_ALIAS("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
+MODULE_ALIAS_CRYPTO("sha384");
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index 92793ba69c4..d4ebf5679f1 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -78,6 +78,15 @@ static inline u32 arch_timer_get_cntfrq(void)
 	return val;
 }
 
+static inline u64 arch_counter_get_cntpct(void)
+{
+	u64 cval;
+
+	isb();
+	asm volatile("mrrc p15, 0, %Q0, %R0, c14" : "=r" (cval));
+	return cval;
+}
+
 static inline u64 arch_counter_get_cntvct(void)
 {
 	u64 cval;
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index afb9cafd378..674d03f4ba1 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -115,7 +115,7 @@ int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs);
    the loader.  We need to make sure that it is out of the way of the program
    that it will "exec", and that there is sufficient room for the brk.  */
 
-#define ELF_ET_DYN_BASE	(2 * TASK_SIZE / 3)
+#define ELF_ET_DYN_BASE	(TASK_SIZE / 3 * 2)
 
 /* When the program starts, a1 contains a pointer to a function to be 
    registered with atexit, as per the SVR4 ABI.  A value of 0 means we 
diff --git a/arch/arm/include/asm/fiq_glue.h b/arch/arm/include/asm/fiq_glue.h
new file mode 100644
index 00000000000..a9e244f9f19
--- /dev/null
+++ b/arch/arm/include/asm/fiq_glue.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __ASM_FIQ_GLUE_H
+#define __ASM_FIQ_GLUE_H
+
+struct fiq_glue_handler {
+	void (*fiq)(struct fiq_glue_handler *h, void *regs, void *svc_sp);
+	void (*resume)(struct fiq_glue_handler *h);
+};
+typedef void (*fiq_return_handler_t)(void);
+
+int fiq_glue_register_handler(struct fiq_glue_handler *handler);
+int fiq_glue_set_return_handler(fiq_return_handler_t fiq_return);
+int fiq_glue_clear_return_handler(fiq_return_handler_t fiq_return);
+
+#ifdef CONFIG_FIQ_GLUE
+void fiq_glue_resume(void);
+#else
+static inline void fiq_glue_resume(void) {}
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
index fe3ea776dc3..5df33e30ae1 100644
--- a/arch/arm/include/asm/hardirq.h
+++ b/arch/arm/include/asm/hardirq.h
@@ -5,7 +5,7 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
-#define NR_IPI	8
+#define NR_IPI	9
 
 typedef struct {
 	unsigned int __softirq_pending;
diff --git a/arch/arm/include/asm/hardware/coresight.h b/arch/arm/include/asm/hardware/coresight.h
index ad774f37c47..b3507650b41 100644
--- a/arch/arm/include/asm/hardware/coresight.h
+++ b/arch/arm/include/asm/hardware/coresight.h
@@ -17,15 +17,23 @@
 #define TRACER_ACCESSED_BIT	0
 #define TRACER_RUNNING_BIT	1
 #define TRACER_CYCLE_ACC_BIT	2
+#define TRACER_TRACE_DATA_BIT	3
+#define TRACER_TIMESTAMP_BIT	4
+#define TRACER_BRANCHOUTPUT_BIT	5
+#define TRACER_RETURN_STACK_BIT	6
 #define TRACER_ACCESSED		BIT(TRACER_ACCESSED_BIT)
 #define TRACER_RUNNING		BIT(TRACER_RUNNING_BIT)
 #define TRACER_CYCLE_ACC	BIT(TRACER_CYCLE_ACC_BIT)
+#define TRACER_TRACE_DATA	BIT(TRACER_TRACE_DATA_BIT)
+#define TRACER_TIMESTAMP	BIT(TRACER_TIMESTAMP_BIT)
+#define TRACER_BRANCHOUTPUT	BIT(TRACER_BRANCHOUTPUT_BIT)
+#define TRACER_RETURN_STACK	BIT(TRACER_RETURN_STACK_BIT)
 
 #define TRACER_TIMEOUT 10000
 
-#define etm_writel(t, v, x) \
-	(writel_relaxed((v), (t)->etm_regs + (x)))
-#define etm_readl(t, x) (readl_relaxed((t)->etm_regs + (x)))
+#define etm_writel(t, id, v, x) \
+	(writel_relaxed((v), (t)->etm_regs[(id)] + (x)))
+#define etm_readl(t, id, x) (readl_relaxed((t)->etm_regs[(id)] + (x)))
 
 /* CoreSight Management Registers */
 #define CSMR_LOCKACCESS 0xfb0
@@ -43,7 +51,7 @@
 #define ETMCTRL_POWERDOWN	1
 #define ETMCTRL_PROGRAM		(1 << 10)
 #define ETMCTRL_PORTSEL		(1 << 11)
-#define ETMCTRL_DO_CONTEXTID	(3 << 14)
+#define ETMCTRL_CONTEXTIDSIZE(x) (((x) & 3) << 14)
 #define ETMCTRL_PORTMASK1	(7 << 4)
 #define ETMCTRL_PORTMASK2	(1 << 21)
 #define ETMCTRL_PORTMASK	(ETMCTRL_PORTMASK1 | ETMCTRL_PORTMASK2)
@@ -55,9 +63,12 @@
 #define ETMCTRL_DATA_DO_BOTH	(ETMCTRL_DATA_DO_DATA | ETMCTRL_DATA_DO_ADDR)
 #define ETMCTRL_BRANCH_OUTPUT	(1 << 8)
 #define ETMCTRL_CYCLEACCURATE	(1 << 12)
+#define ETMCTRL_TIMESTAMP_EN	(1 << 28)
+#define ETMCTRL_RETURN_STACK_EN	(1 << 29)
 
 /* ETM configuration code register */
 #define ETMR_CONFCODE		(0x04)
+#define ETMCCR_ETMIDR_PRESENT	BIT(31)
 
 /* ETM trace start/stop resource control register */
 #define ETMR_TRACESSCTRL	(0x18)
@@ -113,10 +124,25 @@
 #define ETMR_TRACEENCTRL	0x24
 #define ETMTE_INCLEXCL		BIT(24)
 #define ETMR_TRACEENEVT		0x20
-#define ETMCTRL_OPTS		(ETMCTRL_DO_CPRT | \
-				ETMCTRL_DATA_DO_ADDR | \
-				ETMCTRL_BRANCH_OUTPUT | \
-				ETMCTRL_DO_CONTEXTID)
+
+#define ETMR_VIEWDATAEVT	0x30
+#define ETMR_VIEWDATACTRL1	0x34
+#define ETMR_VIEWDATACTRL2	0x38
+#define ETMR_VIEWDATACTRL3	0x3c
+#define ETMVDC3_EXCLONLY	BIT(16)
+
+#define ETMCTRL_OPTS		(ETMCTRL_DO_CPRT)
+
+#define ETMR_ID			0x1e4
+#define ETMIDR_VERSION(x)	(((x) >> 4) & 0xff)
+#define ETMIDR_VERSION_3_1	0x21
+#define ETMIDR_VERSION_PFT_1_0	0x30
+
+#define ETMR_CCE		0x1e8
+#define ETMCCER_RETURN_STACK_IMPLEMENTED	BIT(23)
+#define ETMCCER_TIMESTAMPING_IMPLEMENTED	BIT(22)
+
+#define ETMR_TRACEIDR		0x200
 
 /* ETM management registers, "ETM Architecture", 3.5.24 */
 #define ETMMR_OSLAR	0x300
@@ -140,14 +166,16 @@
 #define ETBFF_TRIGIN		BIT(8)
 #define ETBFF_TRIGEVT		BIT(9)
 #define ETBFF_TRIGFL		BIT(10)
+#define ETBFF_STOPFL		BIT(12)
 
 #define etb_writel(t, v, x) \
 	(writel_relaxed((v), (t)->etb_regs + (x)))
 #define etb_readl(t, x) (readl_relaxed((t)->etb_regs + (x)))
 
-#define etm_lock(t) do { etm_writel((t), 0, CSMR_LOCKACCESS); } while (0)
-#define etm_unlock(t) \
-	do { etm_writel((t), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0)
+#define etm_lock(t, id) \
+	do { etm_writel((t), (id), 0, CSMR_LOCKACCESS); } while (0)
+#define etm_unlock(t, id) \
+	do { etm_writel((t), (id), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0)
 
 #define etb_lock(t) do { etb_writel((t), 0, CSMR_LOCKACCESS); } while (0)
 #define etb_unlock(t) \
diff --git a/arch/arm/include/asm/hardware/cp14.h b/arch/arm/include/asm/hardware/cp14.h
new file mode 100644
index 00000000000..61576dc58ed
--- /dev/null
+++ b/arch/arm/include/asm/hardware/cp14.h
@@ -0,0 +1,542 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __ASM_HARDWARE_CP14_H
+#define __ASM_HARDWARE_CP14_H
+
+#include <linux/types.h>
+
+/* Accessors for CP14 registers */
+#define dbg_read(reg)			RCP14_##reg()
+#define dbg_write(val, reg)		WCP14_##reg(val)
+#define etm_read(reg)			RCP14_##reg()
+#define etm_write(val, reg)		WCP14_##reg(val)
+
+/* MRC14 and MCR14 */
+#define MRC14(op1, crn, crm, op2)					\
+({									\
+u32 val;								\
+asm volatile("mrc p14, "#op1", %0, "#crn", "#crm", "#op2 : "=r" (val));	\
+val;									\
+})
+
+#define MCR14(val, op1, crn, crm, op2)					\
+({									\
+asm volatile("mcr p14, "#op1", %0, "#crn", "#crm", "#op2 : : "r" (val));\
+})
+
+/*
+ * Debug Registers
+ *
+ * Available only in DBGv7
+ * DBGECR, DBGDSCCR, DBGDSMCR, DBGDRCR
+ *
+ * Available only in DBGv7.1
+ * DBGBXVRm, DBGOSDLR, DBGDEVID2, DBGDEVID1
+ *
+ * Read only
+ * DBGDIDR, DBGDSCRint, DBGDTRRXint, DBGDRAR, DBGOSLSR, DBGOSSRR, DBGPRSR,
+ * DBGPRSR, DBGDSAR, DBGAUTHSTATUS, DBGDEVID2, DBGDEVID1, DBGDEVID
+ *
+ * Write only
+ * DBGDTRTXint, DBGOSLAR
+ */
+#define RCP14_DBGDIDR()			MRC14(0, c0, c0, 0)
+#define RCP14_DBGDSCRint()		MRC14(0, c0, c1, 0)
+#define RCP14_DBGDTRRXint()		MRC14(0, c0, c5, 0)
+#define RCP14_DBGWFAR()			MRC14(0, c0, c6, 0)
+#define RCP14_DBGVCR()			MRC14(0, c0, c7, 0)
+#define RCP14_DBGECR()			MRC14(0, c0, c9, 0)
+#define RCP14_DBGDSCCR()		MRC14(0, c0, c10, 0)
+#define RCP14_DBGDSMCR()		MRC14(0, c0, c11, 0)
+#define RCP14_DBGDTRRXext()		MRC14(0, c0, c0, 2)
+#define RCP14_DBGDSCRext()		MRC14(0, c0, c2, 2)
+#define RCP14_DBGDTRTXext()		MRC14(0, c0, c3, 2)
+#define RCP14_DBGDRCR()			MRC14(0, c0, c4, 2)
+#define RCP14_DBGBVR0()			MRC14(0, c0, c0, 4)
+#define RCP14_DBGBVR1()			MRC14(0, c0, c1, 4)
+#define RCP14_DBGBVR2()			MRC14(0, c0, c2, 4)
+#define RCP14_DBGBVR3()			MRC14(0, c0, c3, 4)
+#define RCP14_DBGBVR4()			MRC14(0, c0, c4, 4)
+#define RCP14_DBGBVR5()			MRC14(0, c0, c5, 4)
+#define RCP14_DBGBVR6()			MRC14(0, c0, c6, 4)
+#define RCP14_DBGBVR7()			MRC14(0, c0, c7, 4)
+#define RCP14_DBGBVR8()			MRC14(0, c0, c8, 4)
+#define RCP14_DBGBVR9()			MRC14(0, c0, c9, 4)
+#define RCP14_DBGBVR10()		MRC14(0, c0, c10, 4)
+#define RCP14_DBGBVR11()		MRC14(0, c0, c11, 4)
+#define RCP14_DBGBVR12()		MRC14(0, c0, c12, 4)
+#define RCP14_DBGBVR13()		MRC14(0, c0, c13, 4)
+#define RCP14_DBGBVR14()		MRC14(0, c0, c14, 4)
+#define RCP14_DBGBVR15()		MRC14(0, c0, c15, 4)
+#define RCP14_DBGBCR0()			MRC14(0, c0, c0, 5)
+#define RCP14_DBGBCR1()			MRC14(0, c0, c1, 5)
+#define RCP14_DBGBCR2()			MRC14(0, c0, c2, 5)
+#define RCP14_DBGBCR3()			MRC14(0, c0, c3, 5)
+#define RCP14_DBGBCR4()			MRC14(0, c0, c4, 5)
+#define RCP14_DBGBCR5()			MRC14(0, c0, c5, 5)
+#define RCP14_DBGBCR6()			MRC14(0, c0, c6, 5)
+#define RCP14_DBGBCR7()			MRC14(0, c0, c7, 5)
+#define RCP14_DBGBCR8()			MRC14(0, c0, c8, 5)
+#define RCP14_DBGBCR9()			MRC14(0, c0, c9, 5)
+#define RCP14_DBGBCR10()		MRC14(0, c0, c10, 5)
+#define RCP14_DBGBCR11()		MRC14(0, c0, c11, 5)
+#define RCP14_DBGBCR12()		MRC14(0, c0, c12, 5)
+#define RCP14_DBGBCR13()		MRC14(0, c0, c13, 5)
+#define RCP14_DBGBCR14()		MRC14(0, c0, c14, 5)
+#define RCP14_DBGBCR15()		MRC14(0, c0, c15, 5)
+#define RCP14_DBGWVR0()			MRC14(0, c0, c0, 6)
+#define RCP14_DBGWVR1()			MRC14(0, c0, c1, 6)
+#define RCP14_DBGWVR2()			MRC14(0, c0, c2, 6)
+#define RCP14_DBGWVR3()			MRC14(0, c0, c3, 6)
+#define RCP14_DBGWVR4()			MRC14(0, c0, c4, 6)
+#define RCP14_DBGWVR5()			MRC14(0, c0, c5, 6)
+#define RCP14_DBGWVR6()			MRC14(0, c0, c6, 6)
+#define RCP14_DBGWVR7()			MRC14(0, c0, c7, 6)
+#define RCP14_DBGWVR8()			MRC14(0, c0, c8, 6)
+#define RCP14_DBGWVR9()			MRC14(0, c0, c9, 6)
+#define RCP14_DBGWVR10()		MRC14(0, c0, c10, 6)
+#define RCP14_DBGWVR11()		MRC14(0, c0, c11, 6)
+#define RCP14_DBGWVR12()		MRC14(0, c0, c12, 6)
+#define RCP14_DBGWVR13()		MRC14(0, c0, c13, 6)
+#define RCP14_DBGWVR14()		MRC14(0, c0, c14, 6)
+#define RCP14_DBGWVR15()		MRC14(0, c0, c15, 6)
+#define RCP14_DBGWCR0()			MRC14(0, c0, c0, 7)
+#define RCP14_DBGWCR1()			MRC14(0, c0, c1, 7)
+#define RCP14_DBGWCR2()			MRC14(0, c0, c2, 7)
+#define RCP14_DBGWCR3()			MRC14(0, c0, c3, 7)
+#define RCP14_DBGWCR4()			MRC14(0, c0, c4, 7)
+#define RCP14_DBGWCR5()			MRC14(0, c0, c5, 7)
+#define RCP14_DBGWCR6()			MRC14(0, c0, c6, 7)
+#define RCP14_DBGWCR7()			MRC14(0, c0, c7, 7)
+#define RCP14_DBGWCR8()			MRC14(0, c0, c8, 7)
+#define RCP14_DBGWCR9()			MRC14(0, c0, c9, 7)
+#define RCP14_DBGWCR10()		MRC14(0, c0, c10, 7)
+#define RCP14_DBGWCR11()		MRC14(0, c0, c11, 7)
+#define RCP14_DBGWCR12()		MRC14(0, c0, c12, 7)
+#define RCP14_DBGWCR13()		MRC14(0, c0, c13, 7)
+#define RCP14_DBGWCR14()		MRC14(0, c0, c14, 7)
+#define RCP14_DBGWCR15()		MRC14(0, c0, c15, 7)
+#define RCP14_DBGDRAR()			MRC14(0, c1, c0, 0)
+#define RCP14_DBGBXVR0()		MRC14(0, c1, c0, 1)
+#define RCP14_DBGBXVR1()		MRC14(0, c1, c1, 1)
+#define RCP14_DBGBXVR2()		MRC14(0, c1, c2, 1)
+#define RCP14_DBGBXVR3()		MRC14(0, c1, c3, 1)
+#define RCP14_DBGBXVR4()		MRC14(0, c1, c4, 1)
+#define RCP14_DBGBXVR5()		MRC14(0, c1, c5, 1)
+#define RCP14_DBGBXVR6()		MRC14(0, c1, c6, 1)
+#define RCP14_DBGBXVR7()		MRC14(0, c1, c7, 1)
+#define RCP14_DBGBXVR8()		MRC14(0, c1, c8, 1)
+#define RCP14_DBGBXVR9()		MRC14(0, c1, c9, 1)
+#define RCP14_DBGBXVR10()		MRC14(0, c1, c10, 1)
+#define RCP14_DBGBXVR11()		MRC14(0, c1, c11, 1)
+#define RCP14_DBGBXVR12()		MRC14(0, c1, c12, 1)
+#define RCP14_DBGBXVR13()		MRC14(0, c1, c13, 1)
+#define RCP14_DBGBXVR14()		MRC14(0, c1, c14, 1)
+#define RCP14_DBGBXVR15()		MRC14(0, c1, c15, 1)
+#define RCP14_DBGOSLSR()		MRC14(0, c1, c1, 4)
+#define RCP14_DBGOSSRR()		MRC14(0, c1, c2, 4)
+#define RCP14_DBGOSDLR()		MRC14(0, c1, c3, 4)
+#define RCP14_DBGPRCR()			MRC14(0, c1, c4, 4)
+#define RCP14_DBGPRSR()			MRC14(0, c1, c5, 4)
+#define RCP14_DBGDSAR()			MRC14(0, c2, c0, 0)
+#define RCP14_DBGITCTRL()		MRC14(0, c7, c0, 4)
+#define RCP14_DBGCLAIMSET()		MRC14(0, c7, c8, 6)
+#define RCP14_DBGCLAIMCLR()		MRC14(0, c7, c9, 6)
+#define RCP14_DBGAUTHSTATUS()		MRC14(0, c7, c14, 6)
+#define RCP14_DBGDEVID2()		MRC14(0, c7, c0, 7)
+#define RCP14_DBGDEVID1()		MRC14(0, c7, c1, 7)
+#define RCP14_DBGDEVID()		MRC14(0, c7, c2, 7)
+
+#define WCP14_DBGDTRTXint(val)		MCR14(val, 0, c0, c5, 0)
+#define WCP14_DBGWFAR(val)		MCR14(val, 0, c0, c6, 0)
+#define WCP14_DBGVCR(val)		MCR14(val, 0, c0, c7, 0)
+#define WCP14_DBGECR(val)		MCR14(val, 0, c0, c9, 0)
+#define WCP14_DBGDSCCR(val)		MCR14(val, 0, c0, c10, 0)
+#define WCP14_DBGDSMCR(val)		MCR14(val, 0, c0, c11, 0)
+#define WCP14_DBGDTRRXext(val)		MCR14(val, 0, c0, c0, 2)
+#define WCP14_DBGDSCRext(val)		MCR14(val, 0, c0, c2, 2)
+#define WCP14_DBGDTRTXext(val)		MCR14(val, 0, c0, c3, 2)
+#define WCP14_DBGDRCR(val)		MCR14(val, 0, c0, c4, 2)
+#define WCP14_DBGBVR0(val)		MCR14(val, 0, c0, c0, 4)
+#define WCP14_DBGBVR1(val)		MCR14(val, 0, c0, c1, 4)
+#define WCP14_DBGBVR2(val)		MCR14(val, 0, c0, c2, 4)
+#define WCP14_DBGBVR3(val)		MCR14(val, 0, c0, c3, 4)
+#define WCP14_DBGBVR4(val)		MCR14(val, 0, c0, c4, 4)
+#define WCP14_DBGBVR5(val)		MCR14(val, 0, c0, c5, 4)
+#define WCP14_DBGBVR6(val)		MCR14(val, 0, c0, c6, 4)
+#define WCP14_DBGBVR7(val)		MCR14(val, 0, c0, c7, 4)
+#define WCP14_DBGBVR8(val)		MCR14(val, 0, c0, c8, 4)
+#define WCP14_DBGBVR9(val)		MCR14(val, 0, c0, c9, 4)
+#define WCP14_DBGBVR10(val)		MCR14(val, 0, c0, c10, 4)
+#define WCP14_DBGBVR11(val)		MCR14(val, 0, c0, c11, 4)
+#define WCP14_DBGBVR12(val)		MCR14(val, 0, c0, c12, 4)
+#define WCP14_DBGBVR13(val)		MCR14(val, 0, c0, c13, 4)
+#define WCP14_DBGBVR14(val)		MCR14(val, 0, c0, c14, 4)
+#define WCP14_DBGBVR15(val)		MCR14(val, 0, c0, c15, 4)
+#define WCP14_DBGBCR0(val)		MCR14(val, 0, c0, c0, 5)
+#define WCP14_DBGBCR1(val)		MCR14(val, 0, c0, c1, 5)
+#define WCP14_DBGBCR2(val)		MCR14(val, 0, c0, c2, 5)
+#define WCP14_DBGBCR3(val)		MCR14(val, 0, c0, c3, 5)
+#define WCP14_DBGBCR4(val)		MCR14(val, 0, c0, c4, 5)
+#define WCP14_DBGBCR5(val)		MCR14(val, 0, c0, c5, 5)
+#define WCP14_DBGBCR6(val)		MCR14(val, 0, c0, c6, 5)
+#define WCP14_DBGBCR7(val)		MCR14(val, 0, c0, c7, 5)
+#define WCP14_DBGBCR8(val)		MCR14(val, 0, c0, c8, 5)
+#define WCP14_DBGBCR9(val)		MCR14(val, 0, c0, c9, 5)
+#define WCP14_DBGBCR10(val)		MCR14(val, 0, c0, c10, 5)
+#define WCP14_DBGBCR11(val)		MCR14(val, 0, c0, c11, 5)
+#define WCP14_DBGBCR12(val)		MCR14(val, 0, c0, c12, 5)
+#define WCP14_DBGBCR13(val)		MCR14(val, 0, c0, c13, 5)
+#define WCP14_DBGBCR14(val)		MCR14(val, 0, c0, c14, 5)
+#define WCP14_DBGBCR15(val)		MCR14(val, 0, c0, c15, 5)
+#define WCP14_DBGWVR0(val)		MCR14(val, 0, c0, c0, 6)
+#define WCP14_DBGWVR1(val)		MCR14(val, 0, c0, c1, 6)
+#define WCP14_DBGWVR2(val)		MCR14(val, 0, c0, c2, 6)
+#define WCP14_DBGWVR3(val)		MCR14(val, 0, c0, c3, 6)
+#define WCP14_DBGWVR4(val)		MCR14(val, 0, c0, c4, 6)
+#define WCP14_DBGWVR5(val)		MCR14(val, 0, c0, c5, 6)
+#define WCP14_DBGWVR6(val)		MCR14(val, 0, c0, c6, 6)
+#define WCP14_DBGWVR7(val)		MCR14(val, 0, c0, c7, 6)
+#define WCP14_DBGWVR8(val)		MCR14(val, 0, c0, c8, 6)
+#define WCP14_DBGWVR9(val)		MCR14(val, 0, c0, c9, 6)
+#define WCP14_DBGWVR10(val)		MCR14(val, 0, c0, c10, 6)
+#define WCP14_DBGWVR11(val)		MCR14(val, 0, c0, c11, 6)
+#define WCP14_DBGWVR12(val)		MCR14(val, 0, c0, c12, 6)
+#define WCP14_DBGWVR13(val)		MCR14(val, 0, c0, c13, 6)
+#define WCP14_DBGWVR14(val)		MCR14(val, 0, c0, c14, 6)
+#define WCP14_DBGWVR15(val)		MCR14(val, 0, c0, c15, 6)
+#define WCP14_DBGWCR0(val)		MCR14(val, 0, c0, c0, 7)
+#define WCP14_DBGWCR1(val)		MCR14(val, 0, c0, c1, 7)
+#define WCP14_DBGWCR2(val)		MCR14(val, 0, c0, c2, 7)
+#define WCP14_DBGWCR3(val)		MCR14(val, 0, c0, c3, 7)
+#define WCP14_DBGWCR4(val)		MCR14(val, 0, c0, c4, 7)
+#define WCP14_DBGWCR5(val)		MCR14(val, 0, c0, c5, 7)
+#define WCP14_DBGWCR6(val)		MCR14(val, 0, c0, c6, 7)
+#define WCP14_DBGWCR7(val)		MCR14(val, 0, c0, c7, 7)
+#define WCP14_DBGWCR8(val)		MCR14(val, 0, c0, c8, 7)
+#define WCP14_DBGWCR9(val)		MCR14(val, 0, c0, c9, 7)
+#define WCP14_DBGWCR10(val)		MCR14(val, 0, c0, c10, 7)
+#define WCP14_DBGWCR11(val)		MCR14(val, 0, c0, c11, 7)
+#define WCP14_DBGWCR12(val)		MCR14(val, 0, c0, c12, 7)
+#define WCP14_DBGWCR13(val)		MCR14(val, 0, c0, c13, 7)
+#define WCP14_DBGWCR14(val)		MCR14(val, 0, c0, c14, 7)
+#define WCP14_DBGWCR15(val)		MCR14(val, 0, c0, c15, 7)
+#define WCP14_DBGBXVR0(val)		MCR14(val, 0, c1, c0, 1)
+#define WCP14_DBGBXVR1(val)		MCR14(val, 0, c1, c1, 1)
+#define WCP14_DBGBXVR2(val)		MCR14(val, 0, c1, c2, 1)
+#define WCP14_DBGBXVR3(val)		MCR14(val, 0, c1, c3, 1)
+#define WCP14_DBGBXVR4(val)		MCR14(val, 0, c1, c4, 1)
+#define WCP14_DBGBXVR5(val)		MCR14(val, 0, c1, c5, 1)
+#define WCP14_DBGBXVR6(val)		MCR14(val, 0, c1, c6, 1)
+#define WCP14_DBGBXVR7(val)		MCR14(val, 0, c1, c7, 1)
+#define WCP14_DBGBXVR8(val)		MCR14(val, 0, c1, c8, 1)
+#define WCP14_DBGBXVR9(val)		MCR14(val, 0, c1, c9, 1)
+#define WCP14_DBGBXVR10(val)		MCR14(val, 0, c1, c10, 1)
+#define WCP14_DBGBXVR11(val)		MCR14(val, 0, c1, c11, 1)
+#define WCP14_DBGBXVR12(val)		MCR14(val, 0, c1, c12, 1)
+#define WCP14_DBGBXVR13(val)		MCR14(val, 0, c1, c13, 1)
+#define WCP14_DBGBXVR14(val)		MCR14(val, 0, c1, c14, 1)
+#define WCP14_DBGBXVR15(val)		MCR14(val, 0, c1, c15, 1)
+#define WCP14_DBGOSLAR(val)		MCR14(val, 0, c1, c0, 4)
+#define WCP14_DBGOSSRR(val)		MCR14(val, 0, c1, c2, 4)
+#define WCP14_DBGOSDLR(val)		MCR14(val, 0, c1, c3, 4)
+#define WCP14_DBGPRCR(val)		MCR14(val, 0, c1, c4, 4)
+#define WCP14_DBGITCTRL(val)		MCR14(val, 0, c7, c0, 4)
+#define WCP14_DBGCLAIMSET(val)		MCR14(val, 0, c7, c8, 6)
+#define WCP14_DBGCLAIMCLR(val)		MCR14(val, 0, c7, c9, 6)
+
+/*
+ * ETM Registers
+ *
+ * Available only in ETMv3.3, 3.4, 3.5
+ * ETMASICCR, ETMTECR2, ETMFFRR, ETMVDEVR, ETMVDCR1, ETMVDCR2, ETMVDCR3,
+ * ETMDCVRn, ETMDCMRn
+ *
+ * Available only in ETMv3.5 as read only
+ * ETMIDR2
+ *
+ * Available only in ETMv3.5, PFTv1.0, 1.1
+ * ETMTSEVR, ETMVMIDCVR, ETMPDCR
+ *
+ * Read only
+ * ETMCCR, ETMSCR, ETMIDR, ETMCCER, ETMOSLSR
+ * ETMLSR, ETMAUTHSTATUS, ETMDEVID, ETMDEVTYPE, ETMPIDR4, ETMPIDR5, ETMPIDR6,
+ * ETMPIDR7, ETMPIDR0, ETMPIDR1, ETMPIDR2, ETMPIDR2, ETMPIDR3, ETMCIDR0,
+ * ETMCIDR1, ETMCIDR2, ETMCIDR3
+ *
+ * Write only
+ * ETMOSLAR, ETMLAR
+ * Note: ETMCCER[11] controls WO nature of certain regs. Refer ETM arch spec.
+ */
+#define RCP14_ETMCR()			MRC14(1, c0, c0, 0)
+#define RCP14_ETMCCR()			MRC14(1, c0, c1, 0)
+#define RCP14_ETMTRIGGER()		MRC14(1, c0, c2, 0)
+#define RCP14_ETMASICCR()		MRC14(1, c0, c3, 0)
+#define RCP14_ETMSR()			MRC14(1, c0, c4, 0)
+#define RCP14_ETMSCR()			MRC14(1, c0, c5, 0)
+#define RCP14_ETMTSSCR()		MRC14(1, c0, c6, 0)
+#define RCP14_ETMTECR2()		MRC14(1, c0, c7, 0)
+#define RCP14_ETMTEEVR()		MRC14(1, c0, c8, 0)
+#define RCP14_ETMTECR1()		MRC14(1, c0, c9, 0)
+#define RCP14_ETMFFRR()			MRC14(1, c0, c10, 0)
+#define RCP14_ETMFFLR()			MRC14(1, c0, c11, 0)
+#define RCP14_ETMVDEVR()		MRC14(1, c0, c12, 0)
+#define RCP14_ETMVDCR1()		MRC14(1, c0, c13, 0)
+#define RCP14_ETMVDCR2()		MRC14(1, c0, c14, 0)
+#define RCP14_ETMVDCR3()		MRC14(1, c0, c15, 0)
+#define RCP14_ETMACVR0()		MRC14(1, c0, c0, 1)
+#define RCP14_ETMACVR1()		MRC14(1, c0, c1, 1)
+#define RCP14_ETMACVR2()		MRC14(1, c0, c2, 1)
+#define RCP14_ETMACVR3()		MRC14(1, c0, c3, 1)
+#define RCP14_ETMACVR4()		MRC14(1, c0, c4, 1)
+#define RCP14_ETMACVR5()		MRC14(1, c0, c5, 1)
+#define RCP14_ETMACVR6()		MRC14(1, c0, c6, 1)
+#define RCP14_ETMACVR7()		MRC14(1, c0, c7, 1)
+#define RCP14_ETMACVR8()		MRC14(1, c0, c8, 1)
+#define RCP14_ETMACVR9()		MRC14(1, c0, c9, 1)
+#define RCP14_ETMACVR10()		MRC14(1, c0, c10, 1)
+#define RCP14_ETMACVR11()		MRC14(1, c0, c11, 1)
+#define RCP14_ETMACVR12()		MRC14(1, c0, c12, 1)
+#define RCP14_ETMACVR13()		MRC14(1, c0, c13, 1)
+#define RCP14_ETMACVR14()		MRC14(1, c0, c14, 1)
+#define RCP14_ETMACVR15()		MRC14(1, c0, c15, 1)
+#define RCP14_ETMACTR0()		MRC14(1, c0, c0, 2)
+#define RCP14_ETMACTR1()		MRC14(1, c0, c1, 2)
+#define RCP14_ETMACTR2()		MRC14(1, c0, c2, 2)
+#define RCP14_ETMACTR3()		MRC14(1, c0, c3, 2)
+#define RCP14_ETMACTR4()		MRC14(1, c0, c4, 2)
+#define RCP14_ETMACTR5()		MRC14(1, c0, c5, 2)
+#define RCP14_ETMACTR6()		MRC14(1, c0, c6, 2)
+#define RCP14_ETMACTR7()		MRC14(1, c0, c7, 2)
+#define RCP14_ETMACTR8()		MRC14(1, c0, c8, 2)
+#define RCP14_ETMACTR9()		MRC14(1, c0, c9, 2)
+#define RCP14_ETMACTR10()		MRC14(1, c0, c10, 2)
+#define RCP14_ETMACTR11()		MRC14(1, c0, c11, 2)
+#define RCP14_ETMACTR12()		MRC14(1, c0, c12, 2)
+#define RCP14_ETMACTR13()		MRC14(1, c0, c13, 2)
+#define RCP14_ETMACTR14()		MRC14(1, c0, c14, 2)
+#define RCP14_ETMACTR15()		MRC14(1, c0, c15, 2)
+#define RCP14_ETMDCVR0()		MRC14(1, c0, c0, 3)
+#define RCP14_ETMDCVR2()		MRC14(1, c0, c2, 3)
+#define RCP14_ETMDCVR4()		MRC14(1, c0, c4, 3)
+#define RCP14_ETMDCVR6()		MRC14(1, c0, c6, 3)
+#define RCP14_ETMDCVR8()		MRC14(1, c0, c8, 3)
+#define RCP14_ETMDCVR10()		MRC14(1, c0, c10, 3)
+#define RCP14_ETMDCVR12()		MRC14(1, c0, c12, 3)
+#define RCP14_ETMDCVR14()		MRC14(1, c0, c14, 3)
+#define RCP14_ETMDCMR0()		MRC14(1, c0, c0, 4)
+#define RCP14_ETMDCMR2()		MRC14(1, c0, c2, 4)
+#define RCP14_ETMDCMR4()		MRC14(1, c0, c4, 4)
+#define RCP14_ETMDCMR6()		MRC14(1, c0, c6, 4)
+#define RCP14_ETMDCMR8()		MRC14(1, c0, c8, 4)
+#define RCP14_ETMDCMR10()		MRC14(1, c0, c10, 4)
+#define RCP14_ETMDCMR12()		MRC14(1, c0, c12, 4)
+#define RCP14_ETMDCMR14()		MRC14(1, c0, c14, 4)
+#define RCP14_ETMCNTRLDVR0()		MRC14(1, c0, c0, 5)
+#define RCP14_ETMCNTRLDVR1()		MRC14(1, c0, c1, 5)
+#define RCP14_ETMCNTRLDVR2()		MRC14(1, c0, c2, 5)
+#define RCP14_ETMCNTRLDVR3()		MRC14(1, c0, c3, 5)
+#define RCP14_ETMCNTENR0()		MRC14(1, c0, c4, 5)
+#define RCP14_ETMCNTENR1()		MRC14(1, c0, c5, 5)
+#define RCP14_ETMCNTENR2()		MRC14(1, c0, c6, 5)
+#define RCP14_ETMCNTENR3()		MRC14(1, c0, c7, 5)
+#define RCP14_ETMCNTRLDEVR0()		MRC14(1, c0, c8, 5)
+#define RCP14_ETMCNTRLDEVR1()		MRC14(1, c0, c9, 5)
+#define RCP14_ETMCNTRLDEVR2()		MRC14(1, c0, c10, 5)
+#define RCP14_ETMCNTRLDEVR3()		MRC14(1, c0, c11, 5)
+#define RCP14_ETMCNTVR0()		MRC14(1, c0, c12, 5)
+#define RCP14_ETMCNTVR1()		MRC14(1, c0, c13, 5)
+#define RCP14_ETMCNTVR2()		MRC14(1, c0, c14, 5)
+#define RCP14_ETMCNTVR3()		MRC14(1, c0, c15, 5)
+#define RCP14_ETMSQ12EVR()		MRC14(1, c0, c0, 6)
+#define RCP14_ETMSQ21EVR()		MRC14(1, c0, c1, 6)
+#define RCP14_ETMSQ23EVR()		MRC14(1, c0, c2, 6)
+#define RCP14_ETMSQ31EVR()		MRC14(1, c0, c3, 6)
+#define RCP14_ETMSQ32EVR()		MRC14(1, c0, c4, 6)
+#define RCP14_ETMSQ13EVR()		MRC14(1, c0, c5, 6)
+#define RCP14_ETMSQR()			MRC14(1, c0, c7, 6)
+#define RCP14_ETMEXTOUTEVR0()		MRC14(1, c0, c8, 6)
+#define RCP14_ETMEXTOUTEVR1()		MRC14(1, c0, c9, 6)
+#define RCP14_ETMEXTOUTEVR2()		MRC14(1, c0, c10, 6)
+#define RCP14_ETMEXTOUTEVR3()		MRC14(1, c0, c11, 6)
+#define RCP14_ETMCIDCVR0()		MRC14(1, c0, c12, 6)
+#define RCP14_ETMCIDCVR1()		MRC14(1, c0, c13, 6)
+#define RCP14_ETMCIDCVR2()		MRC14(1, c0, c14, 6)
+#define RCP14_ETMCIDCMR()		MRC14(1, c0, c15, 6)
+#define RCP14_ETMIMPSPEC0()		MRC14(1, c0, c0, 7)
+#define RCP14_ETMIMPSPEC1()		MRC14(1, c0, c1, 7)
+#define RCP14_ETMIMPSPEC2()		MRC14(1, c0, c2, 7)
+#define RCP14_ETMIMPSPEC3()		MRC14(1, c0, c3, 7)
+#define RCP14_ETMIMPSPEC4()		MRC14(1, c0, c4, 7)
+#define RCP14_ETMIMPSPEC5()		MRC14(1, c0, c5, 7)
+#define RCP14_ETMIMPSPEC6()		MRC14(1, c0, c6, 7)
+#define RCP14_ETMIMPSPEC7()		MRC14(1, c0, c7, 7)
+#define RCP14_ETMSYNCFR()		MRC14(1, c0, c8, 7)
+#define RCP14_ETMIDR()			MRC14(1, c0, c9, 7)
+#define RCP14_ETMCCER()			MRC14(1, c0, c10, 7)
+#define RCP14_ETMEXTINSELR()		MRC14(1, c0, c11, 7)
+#define RCP14_ETMTESSEICR()		MRC14(1, c0, c12, 7)
+#define RCP14_ETMEIBCR()		MRC14(1, c0, c13, 7)
+#define RCP14_ETMTSEVR()		MRC14(1, c0, c14, 7)
+#define RCP14_ETMAUXCR()		MRC14(1, c0, c15, 7)
+#define RCP14_ETMTRACEIDR()		MRC14(1, c1, c0, 0)
+#define RCP14_ETMIDR2()			MRC14(1, c1, c2, 0)
+#define RCP14_ETMVMIDCVR()		MRC14(1, c1, c0, 1)
+#define RCP14_ETMOSLSR()		MRC14(1, c1, c1, 4)
+/* Not available in PFTv1.1 */
+#define RCP14_ETMOSSRR()		MRC14(1, c1, c2, 4)
+#define RCP14_ETMPDCR()			MRC14(1, c1, c4, 4)
+#define RCP14_ETMPDSR()			MRC14(1, c1, c5, 4)
+#define RCP14_ETMITCTRL()		MRC14(1, c7, c0, 4)
+#define RCP14_ETMCLAIMSET()		MRC14(1, c7, c8, 6)
+#define RCP14_ETMCLAIMCLR()		MRC14(1, c7, c9, 6)
+#define RCP14_ETMLSR()			MRC14(1, c7, c13, 6)
+#define RCP14_ETMAUTHSTATUS()		MRC14(1, c7, c14, 6)
+#define RCP14_ETMDEVID()		MRC14(1, c7, c2, 7)
+#define RCP14_ETMDEVTYPE()		MRC14(1, c7, c3, 7)
+#define RCP14_ETMPIDR4()		MRC14(1, c7, c4, 7)
+#define RCP14_ETMPIDR5()		MRC14(1, c7, c5, 7)
+#define RCP14_ETMPIDR6()		MRC14(1, c7, c6, 7)
+#define RCP14_ETMPIDR7()		MRC14(1, c7, c7, 7)
+#define RCP14_ETMPIDR0()		MRC14(1, c7, c8, 7)
+#define RCP14_ETMPIDR1()		MRC14(1, c7, c9, 7)
+#define RCP14_ETMPIDR2()		MRC14(1, c7, c10, 7)
+#define RCP14_ETMPIDR3()		MRC14(1, c7, c11, 7)
+#define RCP14_ETMCIDR0()		MRC14(1, c7, c12, 7)
+#define RCP14_ETMCIDR1()		MRC14(1, c7, c13, 7)
+#define RCP14_ETMCIDR2()		MRC14(1, c7, c14, 7)
+#define RCP14_ETMCIDR3()		MRC14(1, c7, c15, 7)
+
+#define WCP14_ETMCR(val)		MCR14(val, 1, c0, c0, 0)
+#define WCP14_ETMTRIGGER(val)		MCR14(val, 1, c0, c2, 0)
+#define WCP14_ETMASICCR(val)		MCR14(val, 1, c0, c3, 0)
+#define WCP14_ETMSR(val)		MCR14(val, 1, c0, c4, 0)
+#define WCP14_ETMTSSCR(val)		MCR14(val, 1, c0, c6, 0)
+#define WCP14_ETMTECR2(val)		MCR14(val, 1, c0, c7, 0)
+#define WCP14_ETMTEEVR(val)		MCR14(val, 1, c0, c8, 0)
+#define WCP14_ETMTECR1(val)		MCR14(val, 1, c0, c9, 0)
+#define WCP14_ETMFFRR(val)		MCR14(val, 1, c0, c10, 0)
+#define WCP14_ETMFFLR(val)		MCR14(val, 1, c0, c11, 0)
+#define WCP14_ETMVDEVR(val)		MCR14(val, 1, c0, c12, 0)
+#define WCP14_ETMVDCR1(val)		MCR14(val, 1, c0, c13, 0)
+#define WCP14_ETMVDCR2(val)		MCR14(val, 1, c0, c14, 0)
+#define WCP14_ETMVDCR3(val)		MCR14(val, 1, c0, c15, 0)
+#define WCP14_ETMACVR0(val)		MCR14(val, 1, c0, c0, 1)
+#define WCP14_ETMACVR1(val)		MCR14(val, 1, c0, c1, 1)
+#define WCP14_ETMACVR2(val)		MCR14(val, 1, c0, c2, 1)
+#define WCP14_ETMACVR3(val)		MCR14(val, 1, c0, c3, 1)
+#define WCP14_ETMACVR4(val)		MCR14(val, 1, c0, c4, 1)
+#define WCP14_ETMACVR5(val)		MCR14(val, 1, c0, c5, 1)
+#define WCP14_ETMACVR6(val)		MCR14(val, 1, c0, c6, 1)
+#define WCP14_ETMACVR7(val)		MCR14(val, 1, c0, c7, 1)
+#define WCP14_ETMACVR8(val)		MCR14(val, 1, c0, c8, 1)
+#define WCP14_ETMACVR9(val)		MCR14(val, 1, c0, c9, 1)
+#define WCP14_ETMACVR10(val)		MCR14(val, 1, c0, c10, 1)
+#define WCP14_ETMACVR11(val)		MCR14(val, 1, c0, c11, 1)
+#define WCP14_ETMACVR12(val)		MCR14(val, 1, c0, c12, 1)
+#define WCP14_ETMACVR13(val)		MCR14(val, 1, c0, c13, 1)
+#define WCP14_ETMACVR14(val)		MCR14(val, 1, c0, c14, 1)
+#define WCP14_ETMACVR15(val)		MCR14(val, 1, c0, c15, 1)
+#define WCP14_ETMACTR0(val)		MCR14(val, 1, c0, c0, 2)
+#define WCP14_ETMACTR1(val)		MCR14(val, 1, c0, c1, 2)
+#define WCP14_ETMACTR2(val)		MCR14(val, 1, c0, c2, 2)
+#define WCP14_ETMACTR3(val)		MCR14(val, 1, c0, c3, 2)
+#define WCP14_ETMACTR4(val)		MCR14(val, 1, c0, c4, 2)
+#define WCP14_ETMACTR5(val)		MCR14(val, 1, c0, c5, 2)
+#define WCP14_ETMACTR6(val)		MCR14(val, 1, c0, c6, 2)
+#define WCP14_ETMACTR7(val)		MCR14(val, 1, c0, c7, 2)
+#define WCP14_ETMACTR8(val)		MCR14(val, 1, c0, c8, 2)
+#define WCP14_ETMACTR9(val)		MCR14(val, 1, c0, c9, 2)
+#define WCP14_ETMACTR10(val)		MCR14(val, 1, c0, c10, 2)
+#define WCP14_ETMACTR11(val)		MCR14(val, 1, c0, c11, 2)
+#define WCP14_ETMACTR12(val)		MCR14(val, 1, c0, c12, 2)
+#define WCP14_ETMACTR13(val)		MCR14(val, 1, c0, c13, 2)
+#define WCP14_ETMACTR14(val)		MCR14(val, 1, c0, c14, 2)
+#define WCP14_ETMACTR15(val)		MCR14(val, 1, c0, c15, 2)
+#define WCP14_ETMDCVR0(val)		MCR14(val, 1, c0, c0, 3)
+#define WCP14_ETMDCVR2(val)		MCR14(val, 1, c0, c2, 3)
+#define WCP14_ETMDCVR4(val)		MCR14(val, 1, c0, c4, 3)
+#define WCP14_ETMDCVR6(val)		MCR14(val, 1, c0, c6, 3)
+#define WCP14_ETMDCVR8(val)		MCR14(val, 1, c0, c8, 3)
+#define WCP14_ETMDCVR10(val)		MCR14(val, 1, c0, c10, 3)
+#define WCP14_ETMDCVR12(val)		MCR14(val, 1, c0, c12, 3)
+#define WCP14_ETMDCVR14(val)		MCR14(val, 1, c0, c14, 3)
+#define WCP14_ETMDCMR0(val)		MCR14(val, 1, c0, c0, 4)
+#define WCP14_ETMDCMR2(val)		MCR14(val, 1, c0, c2, 4)
+#define WCP14_ETMDCMR4(val)		MCR14(val, 1, c0, c4, 4)
+#define WCP14_ETMDCMR6(val)		MCR14(val, 1, c0, c6, 4)
+#define WCP14_ETMDCMR8(val)		MCR14(val, 1, c0, c8, 4)
+#define WCP14_ETMDCMR10(val)		MCR14(val, 1, c0, c10, 4)
+#define WCP14_ETMDCMR12(val)		MCR14(val, 1, c0, c12, 4)
+#define WCP14_ETMDCMR14(val)		MCR14(val, 1, c0, c14, 4)
+#define WCP14_ETMCNTRLDVR0(val)		MCR14(val, 1, c0, c0, 5)
+#define WCP14_ETMCNTRLDVR1(val)		MCR14(val, 1, c0, c1, 5)
+#define WCP14_ETMCNTRLDVR2(val)		MCR14(val, 1, c0, c2, 5)
+#define WCP14_ETMCNTRLDVR3(val)		MCR14(val, 1, c0, c3, 5)
+#define WCP14_ETMCNTENR0(val)		MCR14(val, 1, c0, c4, 5)
+#define WCP14_ETMCNTENR1(val)		MCR14(val, 1, c0, c5, 5)
+#define WCP14_ETMCNTENR2(val)		MCR14(val, 1, c0, c6, 5)
+#define WCP14_ETMCNTENR3(val)		MCR14(val, 1, c0, c7, 5)
+#define WCP14_ETMCNTRLDEVR0(val)	MCR14(val, 1, c0, c8, 5)
+#define WCP14_ETMCNTRLDEVR1(val)	MCR14(val, 1, c0, c9, 5)
+#define WCP14_ETMCNTRLDEVR2(val)	MCR14(val, 1, c0, c10, 5)
+#define WCP14_ETMCNTRLDEVR3(val)	MCR14(val, 1, c0, c11, 5)
+#define WCP14_ETMCNTVR0(val)		MCR14(val, 1, c0, c12, 5)
+#define WCP14_ETMCNTVR1(val)		MCR14(val, 1, c0, c13, 5)
+#define WCP14_ETMCNTVR2(val)		MCR14(val, 1, c0, c14, 5)
+#define WCP14_ETMCNTVR3(val)		MCR14(val, 1, c0, c15, 5)
+#define WCP14_ETMSQ12EVR(val)		MCR14(val, 1, c0, c0, 6)
+#define WCP14_ETMSQ21EVR(val)		MCR14(val, 1, c0, c1, 6)
+#define WCP14_ETMSQ23EVR(val)		MCR14(val, 1, c0, c2, 6)
+#define WCP14_ETMSQ31EVR(val)		MCR14(val, 1, c0, c3, 6)
+#define WCP14_ETMSQ32EVR(val)		MCR14(val, 1, c0, c4, 6)
+#define WCP14_ETMSQ13EVR(val)		MCR14(val, 1, c0, c5, 6)
+#define WCP14_ETMSQR(val)		MCR14(val, 1, c0, c7, 6)
+#define WCP14_ETMEXTOUTEVR0(val)	MCR14(val, 1, c0, c8, 6)
+#define WCP14_ETMEXTOUTEVR1(val)	MCR14(val, 1, c0, c9, 6)
+#define WCP14_ETMEXTOUTEVR2(val)	MCR14(val, 1, c0, c10, 6)
+#define WCP14_ETMEXTOUTEVR3(val)	MCR14(val, 1, c0, c11, 6)
+#define WCP14_ETMCIDCVR0(val)		MCR14(val, 1, c0, c12, 6)
+#define WCP14_ETMCIDCVR1(val)		MCR14(val, 1, c0, c13, 6)
+#define WCP14_ETMCIDCVR2(val)		MCR14(val, 1, c0, c14, 6)
+#define WCP14_ETMCIDCMR(val)		MCR14(val, 1, c0, c15, 6)
+#define WCP14_ETMIMPSPEC0(val)		MCR14(val, 1, c0, c0, 7)
+#define WCP14_ETMIMPSPEC1(val)		MCR14(val, 1, c0, c1, 7)
+#define WCP14_ETMIMPSPEC2(val)		MCR14(val, 1, c0, c2, 7)
+#define WCP14_ETMIMPSPEC3(val)		MCR14(val, 1, c0, c3, 7)
+#define WCP14_ETMIMPSPEC4(val)		MCR14(val, 1, c0, c4, 7)
+#define WCP14_ETMIMPSPEC5(val)		MCR14(val, 1, c0, c5, 7)
+#define WCP14_ETMIMPSPEC6(val)		MCR14(val, 1, c0, c6, 7)
+#define WCP14_ETMIMPSPEC7(val)		MCR14(val, 1, c0, c7, 7)
+/* Can be read only in ETMv3.4, ETMv3.5 */
+#define WCP14_ETMSYNCFR(val)		MCR14(val, 1, c0, c8, 7)
+#define WCP14_ETMEXTINSELR(val)		MCR14(val, 1, c0, c11, 7)
+#define WCP14_ETMTESSEICR(val)		MCR14(val, 1, c0, c12, 7)
+#define WCP14_ETMEIBCR(val)		MCR14(val, 1, c0, c13, 7)
+#define WCP14_ETMTSEVR(val)		MCR14(val, 1, c0, c14, 7)
+#define WCP14_ETMAUXCR(val)		MCR14(val, 1, c0, c15, 7)
+#define WCP14_ETMTRACEIDR(val)		MCR14(val, 1, c1, c0, 0)
+#define WCP14_ETMIDR2(val)		MCR14(val, 1, c1, c2, 0)
+#define WCP14_ETMVMIDCVR(val)		MCR14(val, 1, c1, c0, 1)
+#define WCP14_ETMOSLAR(val)		MCR14(val, 1, c1, c0, 4)
+/* Not available in PFTv1.1 */
+#define WCP14_ETMOSSRR(val)		MCR14(val, 1, c1, c2, 4)
+#define WCP14_ETMPDCR(val)		MCR14(val, 1, c1, c4, 4)
+#define WCP14_ETMPDSR(val)		MCR14(val, 1, c1, c5, 4)
+#define WCP14_ETMITCTRL(val)		MCR14(val, 1, c7, c0, 4)
+#define WCP14_ETMCLAIMSET(val)		MCR14(val, 1, c7, c8, 6)
+#define WCP14_ETMCLAIMCLR(val)		MCR14(val, 1, c7, c9, 6)
+/* Writes to this from CP14 interface are ignored */
+#define WCP14_ETMLAR(val)		MCR14(val, 1, c7, c12, 6)
+
+#endif
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index 53c15dec7af..809203a4b71 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -35,6 +35,9 @@ extern void (*handle_arch_irq)(struct pt_regs *);
 extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
 #endif
 
+void arch_trigger_all_cpu_backtrace(void);
+#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
+
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index b9db269c6e6..66ce17655bb 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -33,6 +33,11 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu);
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
 void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
 
+static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.hcr = HCR_GUEST_MASK;
+}
+
 static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu)
 {
 	return 1;
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index acb0d571271..16d9d788d0b 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -44,6 +44,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/highmem.h>
 #include <asm/cacheflush.h>
 #include <asm/pgalloc.h>
 
@@ -52,6 +53,7 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
 void free_boot_hyp_pgd(void);
 void free_hyp_pgds(void);
 
+void stage2_unmap_vm(struct kvm *kvm);
 int kvm_alloc_stage2_pgd(struct kvm *kvm);
 void kvm_free_stage2_pgd(struct kvm *kvm);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
@@ -126,29 +128,28 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
 	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
 })
 
+#define kvm_pgd_index(addr)			pgd_index(addr)
+
 static inline bool kvm_page_empty(void *ptr)
 {
 	struct page *ptr_page = virt_to_page(ptr);
 	return page_count(ptr_page) == 1;
 }
 
-
 #define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep)
 #define kvm_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp)
 #define kvm_pud_table_empty(kvm, pudp) (0)
 
 #define KVM_PREALLOC_LEVEL	0
 
-static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd)
+static inline void *kvm_get_hwpgd(struct kvm *kvm)
 {
-	return 0;
+	return kvm->arch.pgd;
 }
 
-static inline void kvm_free_hwpgd(struct kvm *kvm) { }
-
-static inline void *kvm_get_hwpgd(struct kvm *kvm)
+static inline unsigned int kvm_get_hwpgd_size(void)
 {
-	return kvm->arch.pgd;
+	return PTRS_PER_S2_PGD * sizeof(pgd_t);
 }
 
 struct kvm;
@@ -160,12 +161,10 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 	return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101;
 }
 
-static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
-					     unsigned long size)
+static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
+					       unsigned long size,
+					       bool ipa_uncached)
 {
-	if (!vcpu_has_cache_enabled(vcpu))
-		kvm_flush_dcache_to_poc((void *)hva, size);
-	
 	/*
 	 * If we are going to insert an instruction page and the icache is
 	 * either VIPT or PIPT, there is a potential problem where the host
@@ -177,15 +176,73 @@ static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
 	 *
 	 * VIVT caches are tagged using both the ASID and the VMID and doesn't
 	 * need any kind of flushing (DDI 0406C.b - Page B3-1392).
+	 *
+	 * We need to do this through a kernel mapping (using the
+	 * user-space mapping has proved to be the wrong
+	 * solution). For that, we need to kmap one page at a time,
+	 * and iterate over the range.
 	 */
-	if (icache_is_pipt()) {
-		__cpuc_coherent_user_range(hva, hva + size);
-	} else if (!icache_is_vivt_asid_tagged()) {
+
+	bool need_flush = !vcpu_has_cache_enabled(vcpu) || ipa_uncached;
+
+	VM_BUG_ON(size & ~PAGE_MASK);
+
+	if (!need_flush && !icache_is_pipt())
+		goto vipt_cache;
+
+	while (size) {
+		void *va = kmap_atomic_pfn(pfn);
+
+		if (need_flush)
+			kvm_flush_dcache_to_poc(va, PAGE_SIZE);
+
+		if (icache_is_pipt())
+			__cpuc_coherent_user_range((unsigned long)va,
+						   (unsigned long)va + PAGE_SIZE);
+
+		size -= PAGE_SIZE;
+		pfn++;
+
+		kunmap_atomic(va);
+	}
+
+vipt_cache:
+	if (!icache_is_pipt() && !icache_is_vivt_asid_tagged()) {
 		/* any kind of VIPT cache */
 		__flush_icache_all();
 	}
 }
 
+static inline void __kvm_flush_dcache_pte(pte_t pte)
+{
+	void *va = kmap_atomic(pte_page(pte));
+
+	kvm_flush_dcache_to_poc(va, PAGE_SIZE);
+
+	kunmap_atomic(va);
+}
+
+static inline void __kvm_flush_dcache_pmd(pmd_t pmd)
+{
+	unsigned long size = PMD_SIZE;
+	pfn_t pfn = pmd_pfn(pmd);
+
+	while (size) {
+		void *va = kmap_atomic_pfn(pfn);
+
+		kvm_flush_dcache_to_poc(va, PAGE_SIZE);
+
+		pfn++;
+		size -= PAGE_SIZE;
+
+		kunmap_atomic(va);
+	}
+}
+
+static inline void __kvm_flush_dcache_pud(pud_t pud)
+{
+}
+
 #define kvm_virt_to_phys(x)		virt_to_idmap((unsigned long)(x))
 
 void stage2_flush_vm(struct kvm *kvm);
diff --git a/arch/arm/include/asm/mach/mmc.h b/arch/arm/include/asm/mach/mmc.h
new file mode 100644
index 00000000000..bca864ac945
--- /dev/null
+++ b/arch/arm/include/asm/mach/mmc.h
@@ -0,0 +1,28 @@
+/*
+ *  arch/arm/include/asm/mach/mmc.h
+ */
+#ifndef ASMARM_MACH_MMC_H
+#define ASMARM_MACH_MMC_H
+
+#include <linux/mmc/host.h>
+#include <linux/mmc/card.h>
+#include <linux/mmc/sdio_func.h>
+
+struct embedded_sdio_data {
+        struct sdio_cis cis;
+        struct sdio_cccr cccr;
+        struct sdio_embedded_func *funcs;
+        int num_funcs;
+};
+
+struct mmc_platform_data {
+	unsigned int ocr_mask;			/* available voltages */
+	int built_in;				/* built-in device flag */
+	int card_present;			/* card detect state */
+	u32 (*translate_vdd)(struct device *, unsigned int);
+	unsigned int (*status)(struct device *);
+	struct embedded_sdio_data *embedded_sdio;
+	int (*register_status_notify)(void (*callback)(int card_present, void *dev_id), void *dev_id);
+};
+
+#endif
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 18f5a554134..7f31b4fd418 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -81,6 +81,8 @@ extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask);
 
 extern int register_ipi_completion(struct completion *completion, int cpu);
 
+extern void smp_send_all_cpu_backtrace(void);
+
 struct smp_operations {
 #ifdef CONFIG_SMP
 	/*
diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h
index 135c24a5ba2..68c739b3fdf 100644
--- a/arch/arm/include/asm/xen/page.h
+++ b/arch/arm/include/asm/xen/page.h
@@ -107,4 +107,8 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 #define xen_remap(cookie, size) ioremap_cache((cookie), (size))
 #define xen_unmap(cookie) iounmap((cookie))
 
+bool xen_arch_need_swiotlb(struct device *dev,
+			   unsigned long pfn,
+			   unsigned long mfn);
+
 #endif /* _ASM_ARM_XEN_PAGE_H */
diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index 09ee408c1a6..b404cf88602 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -193,8 +193,14 @@ struct kvm_arch_memory_slot {
 #define KVM_ARM_IRQ_CPU_IRQ		0
 #define KVM_ARM_IRQ_CPU_FIQ		1
 
-/* Highest supported SPI, from VGIC_NR_IRQS */
+/*
+ * This used to hold the highest supported SPI, but it is now obsolete
+ * and only here to provide source code level compatibility with older
+ * userland. The highest SPI number can be set via KVM_DEV_ARM_VGIC_GRP_NR_IRQS.
+ */
+#ifndef __KERNEL__
 #define KVM_ARM_IRQ_GIC_MAX		127
+#endif
 
 /* PSCI interface */
 #define KVM_PSCI_FN_BASE		0x95c1ba5e
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 38ddd9f83d0..2ecc7d15bc0 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -84,6 +84,7 @@ obj-$(CONFIG_CPU_PJ4B)		+= pj4-cp0.o
 obj-$(CONFIG_IWMMXT)		+= iwmmxt.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_regs.o
 obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o perf_event_cpu.o
+CFLAGS_pj4-cp0.o		:= -marm
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
 obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
 
@@ -97,7 +98,7 @@ obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 
 obj-$(CONFIG_ARM_VIRT_EXT)	+= hyp-stub.o
 ifeq ($(CONFIG_ARM_PSCI),y)
-obj-y				+= psci.o
+obj-y				+= psci.o psci-call.o
 obj-$(CONFIG_SMP)		+= psci_smp.o
 endif
 
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 2d2d6087b9b..713e807621d 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -10,7 +10,6 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
-#include <linux/compiler.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
@@ -40,19 +39,10 @@
  * GCC 3.2.x: miscompiles NEW_AUX_ENT in fs/binfmt_elf.c
  *            (http://gcc.gnu.org/PR8896) and incorrect structure
  *	      initialisation in fs/jffs2/erase.c
- * GCC 4.8.0-4.8.2: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58854
- *	      miscompiles find_get_entry(), and can result in EXT3 and EXT4
- *	      filesystem corruption (possibly other FS too).
  */
-#ifdef __GNUC__
 #if (__GNUC__ == 3 && __GNUC_MINOR__ < 3)
 #error Your compiler is too buggy; it is known to miscompile kernels.
-#error    Known good compilers: 3.3, 4.x
-#endif
-#if GCC_VERSION >= 40800 && GCC_VERSION < 40803
-#error Your compiler is too buggy; it is known to miscompile kernels
-#error and result in filesystem corruption and oopses.
-#endif
+#error    Known good compilers: 3.3
 #endif
 
 int main(void)
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 6bb09d4abde..eb6f1927b2c 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -33,7 +33,9 @@ ret_fast_syscall:
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
 	disable_irq				@ disable interrupts
-	ldr	r1, [tsk, #TI_FLAGS]
+	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
+	tst	r1, #_TIF_SYSCALL_WORK
+	bne	__sys_trace_return
 	tst	r1, #_TIF_WORK_MASK
 	bne	fast_work_pending
 	asm_trace_hardirqs_on
diff --git a/arch/arm/kernel/etm.c b/arch/arm/kernel/etm.c
index 131a6ab5f35..a634e0ef6d1 100644
--- a/arch/arm/kernel/etm.c
+++ b/arch/arm/kernel/etm.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/io.h>
+#include <linux/slab.h>
 #include <linux/sysrq.h>
 #include <linux/device.h>
 #include <linux/clk.h>
@@ -37,26 +38,37 @@ MODULE_AUTHOR("Alexander Shishkin");
 struct tracectx {
 	unsigned int	etb_bufsz;
 	void __iomem	*etb_regs;
-	void __iomem	*etm_regs;
+	void __iomem	**etm_regs;
+	int		etm_regs_count;
 	unsigned long	flags;
 	int		ncmppairs;
 	int		etm_portsz;
+	int		etm_contextid_size;
+	u32		etb_fc;
+	unsigned long	range_start;
+	unsigned long	range_end;
+	unsigned long	data_range_start;
+	unsigned long	data_range_end;
+	bool		dump_initial_etb;
 	struct device	*dev;
 	struct clk	*emu_clk;
 	struct mutex	mutex;
 };
 
-static struct tracectx tracer;
+static struct tracectx tracer = {
+	.range_start = (unsigned long)_stext,
+	.range_end = (unsigned long)_etext,
+};
 
 static inline bool trace_isrunning(struct tracectx *t)
 {
 	return !!(t->flags & TRACER_RUNNING);
 }
 
-static int etm_setup_address_range(struct tracectx *t, int n,
+static int etm_setup_address_range(struct tracectx *t, int id, int n,
 		unsigned long start, unsigned long end, int exclude, int data)
 {
-	u32 flags = ETMAAT_ARM | ETMAAT_IGNCONTEXTID | ETMAAT_NSONLY | \
+	u32 flags = ETMAAT_ARM | ETMAAT_IGNCONTEXTID | ETMAAT_IGNSECURITY |
 		    ETMAAT_NOVALCMP;
 
 	if (n < 1 || n > t->ncmppairs)
@@ -72,95 +84,185 @@ static int etm_setup_address_range(struct tracectx *t, int n,
 		flags |= ETMAAT_IEXEC;
 
 	/* first comparator for the range */
-	etm_writel(t, flags, ETMR_COMP_ACC_TYPE(n * 2));
-	etm_writel(t, start, ETMR_COMP_VAL(n * 2));
+	etm_writel(t, id, flags, ETMR_COMP_ACC_TYPE(n * 2));
+	etm_writel(t, id, start, ETMR_COMP_VAL(n * 2));
 
 	/* second comparator is right next to it */
-	etm_writel(t, flags, ETMR_COMP_ACC_TYPE(n * 2 + 1));
-	etm_writel(t, end, ETMR_COMP_VAL(n * 2 + 1));
-
-	flags = exclude ? ETMTE_INCLEXCL : 0;
-	etm_writel(t, flags | (1 << n), ETMR_TRACEENCTRL);
+	etm_writel(t, id, flags, ETMR_COMP_ACC_TYPE(n * 2 + 1));
+	etm_writel(t, id, end, ETMR_COMP_VAL(n * 2 + 1));
+
+	if (data) {
+		flags = exclude ? ETMVDC3_EXCLONLY : 0;
+		if (exclude)
+			n += 8;
+		etm_writel(t, id, flags | BIT(n), ETMR_VIEWDATACTRL3);
+	} else {
+		flags = exclude ? ETMTE_INCLEXCL : 0;
+		etm_writel(t, id, flags | (1 << n), ETMR_TRACEENCTRL);
+	}
 
 	return 0;
 }
 
-static int trace_start(struct tracectx *t)
+static int trace_start_etm(struct tracectx *t, int id)
 {
 	u32 v;
 	unsigned long timeout = TRACER_TIMEOUT;
 
-	etb_unlock(t);
-
-	etb_writel(t, 0, ETBR_FORMATTERCTRL);
-	etb_writel(t, 1, ETBR_CTRL);
-
-	etb_lock(t);
-
-	/* configure etm */
 	v = ETMCTRL_OPTS | ETMCTRL_PROGRAM | ETMCTRL_PORTSIZE(t->etm_portsz);
+	v |= ETMCTRL_CONTEXTIDSIZE(t->etm_contextid_size);
 
 	if (t->flags & TRACER_CYCLE_ACC)
 		v |= ETMCTRL_CYCLEACCURATE;
 
-	etm_unlock(t);
+	if (t->flags & TRACER_BRANCHOUTPUT)
+		v |= ETMCTRL_BRANCH_OUTPUT;
+
+	if (t->flags & TRACER_TRACE_DATA)
+		v |= ETMCTRL_DATA_DO_ADDR;
+
+	if (t->flags & TRACER_TIMESTAMP)
+		v |= ETMCTRL_TIMESTAMP_EN;
+
+	if (t->flags & TRACER_RETURN_STACK)
+		v |= ETMCTRL_RETURN_STACK_EN;
 
-	etm_writel(t, v, ETMR_CTRL);
+	etm_unlock(t, id);
 
-	while (!(etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout)
+	etm_writel(t, id, v, ETMR_CTRL);
+
+	while (!(etm_readl(t, id, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout)
 		;
 	if (!timeout) {
 		dev_dbg(t->dev, "Waiting for progbit to assert timed out\n");
-		etm_lock(t);
+		etm_lock(t, id);
 		return -EFAULT;
 	}
 
-	etm_setup_address_range(t, 1, (unsigned long)_stext,
-			(unsigned long)_etext, 0, 0);
-	etm_writel(t, 0, ETMR_TRACEENCTRL2);
-	etm_writel(t, 0, ETMR_TRACESSCTRL);
-	etm_writel(t, 0x6f, ETMR_TRACEENEVT);
+	if (t->range_start || t->range_end)
+		etm_setup_address_range(t, id, 1,
+					t->range_start, t->range_end, 0, 0);
+	else
+		etm_writel(t, id, ETMTE_INCLEXCL, ETMR_TRACEENCTRL);
+
+	etm_writel(t, id, 0, ETMR_TRACEENCTRL2);
+	etm_writel(t, id, 0, ETMR_TRACESSCTRL);
+	etm_writel(t, id, 0x6f, ETMR_TRACEENEVT);
+
+	etm_writel(t, id, 0, ETMR_VIEWDATACTRL1);
+	etm_writel(t, id, 0, ETMR_VIEWDATACTRL2);
+
+	if (t->data_range_start || t->data_range_end)
+		etm_setup_address_range(t, id, 2, t->data_range_start,
+					t->data_range_end, 0, 1);
+	else
+		etm_writel(t, id, ETMVDC3_EXCLONLY, ETMR_VIEWDATACTRL3);
+
+	etm_writel(t, id, 0x6f, ETMR_VIEWDATAEVT);
 
 	v &= ~ETMCTRL_PROGRAM;
 	v |= ETMCTRL_PORTSEL;
 
-	etm_writel(t, v, ETMR_CTRL);
+	etm_writel(t, id, v, ETMR_CTRL);
 
 	timeout = TRACER_TIMEOUT;
-	while (etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM && --timeout)
+	while (etm_readl(t, id, ETMR_CTRL) & ETMCTRL_PROGRAM && --timeout)
 		;
 	if (!timeout) {
 		dev_dbg(t->dev, "Waiting for progbit to deassert timed out\n");
-		etm_lock(t);
+		etm_lock(t, id);
 		return -EFAULT;
 	}
 
-	etm_lock(t);
+	etm_lock(t, id);
+	return 0;
+}
+
+static int trace_start(struct tracectx *t)
+{
+	int ret;
+	int id;
+	u32 etb_fc = t->etb_fc;
+
+	etb_unlock(t);
+
+	t->dump_initial_etb = false;
+	etb_writel(t, 0, ETBR_WRITEADDR);
+	etb_writel(t, etb_fc, ETBR_FORMATTERCTRL);
+	etb_writel(t, 1, ETBR_CTRL);
+
+	etb_lock(t);
+
+	/* configure etm(s) */
+	for (id = 0; id < t->etm_regs_count; id++) {
+		ret = trace_start_etm(t, id);
+		if (ret)
+			return ret;
+	}
 
 	t->flags |= TRACER_RUNNING;
 
 	return 0;
 }
 
-static int trace_stop(struct tracectx *t)
+static int trace_stop_etm(struct tracectx *t, int id)
 {
 	unsigned long timeout = TRACER_TIMEOUT;
 
-	etm_unlock(t);
+	etm_unlock(t, id);
 
-	etm_writel(t, 0x440, ETMR_CTRL);
-	while (!(etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout)
+	etm_writel(t, id, 0x440, ETMR_CTRL);
+	while (!(etm_readl(t, id, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout)
 		;
 	if (!timeout) {
-		dev_dbg(t->dev, "Waiting for progbit to assert timed out\n");
-		etm_lock(t);
+		dev_err(t->dev,
+			"etm%d: Waiting for progbit to assert timed out\n",
+			id);
+		etm_lock(t, id);
 		return -EFAULT;
 	}
 
-	etm_lock(t);
+	etm_lock(t, id);
+	return 0;
+}
+
+static int trace_power_down_etm(struct tracectx *t, int id)
+{
+	unsigned long timeout = TRACER_TIMEOUT;
+	etm_unlock(t, id);
+	while (!(etm_readl(t, id, ETMR_STATUS) & ETMST_PROGBIT) && --timeout)
+		;
+	if (!timeout) {
+		dev_err(t->dev, "etm%d: Waiting for status progbit to assert timed out\n",
+			id);
+		etm_lock(t, id);
+		return -EFAULT;
+	}
+
+	etm_writel(t, id, 0x441, ETMR_CTRL);
+
+	etm_lock(t, id);
+	return 0;
+}
+
+static int trace_stop(struct tracectx *t)
+{
+	int id;
+	unsigned long timeout = TRACER_TIMEOUT;
+	u32 etb_fc = t->etb_fc;
+
+	for (id = 0; id < t->etm_regs_count; id++)
+		trace_stop_etm(t, id);
+
+	for (id = 0; id < t->etm_regs_count; id++)
+		trace_power_down_etm(t, id);
 
 	etb_unlock(t);
-	etb_writel(t, ETBFF_MANUAL_FLUSH, ETBR_FORMATTERCTRL);
+	if (etb_fc) {
+		etb_fc |= ETBFF_STOPFL;
+		etb_writel(t, t->etb_fc, ETBR_FORMATTERCTRL);
+	}
+	etb_writel(t, etb_fc | ETBFF_MANUAL_FLUSH, ETBR_FORMATTERCTRL);
 
 	timeout = TRACER_TIMEOUT;
 	while (etb_readl(t, ETBR_FORMATTERCTRL) &
@@ -185,24 +287,15 @@ static int trace_stop(struct tracectx *t)
 static int etb_getdatalen(struct tracectx *t)
 {
 	u32 v;
-	int rp, wp;
+	int wp;
 
 	v = etb_readl(t, ETBR_STATUS);
 
 	if (v & 1)
 		return t->etb_bufsz;
 
-	rp = etb_readl(t, ETBR_READADDR);
 	wp = etb_readl(t, ETBR_WRITEADDR);
-
-	if (rp > wp) {
-		etb_writel(t, 0, ETBR_READADDR);
-		etb_writel(t, 0, ETBR_WRITEADDR);
-
-		return 0;
-	}
-
-	return wp - rp;
+	return wp;
 }
 
 /* sysrq+v will always stop the running trace and leave it at that */
@@ -235,21 +328,18 @@ static void etm_dump(void)
 		printk("%08x", cpu_to_be32(etb_readl(t, ETBR_READMEM)));
 	printk(KERN_INFO "\n--- ETB buffer end ---\n");
 
-	/* deassert the overflow bit */
-	etb_writel(t, 1, ETBR_CTRL);
-	etb_writel(t, 0, ETBR_CTRL);
-
-	etb_writel(t, 0, ETBR_TRIGGERCOUNT);
-	etb_writel(t, 0, ETBR_READADDR);
-	etb_writel(t, 0, ETBR_WRITEADDR);
-
 	etb_lock(t);
 }
 
 static void sysrq_etm_dump(int key)
 {
+	if (!mutex_trylock(&tracer.mutex)) {
+		printk(KERN_INFO "Tracing hardware busy\n");
+		return;
+	}
 	dev_dbg(tracer.dev, "Dumping ETB buffer\n");
 	etm_dump();
+	mutex_unlock(&tracer.mutex);
 }
 
 static struct sysrq_key_op sysrq_etm_op = {
@@ -276,6 +366,10 @@ static ssize_t etb_read(struct file *file, char __user *data,
 	struct tracectx *t = file->private_data;
 	u32 first = 0;
 	u32 *buf;
+	int wpos;
+	int skip;
+	long wlength;
+	loff_t pos = *ppos;
 
 	mutex_lock(&t->mutex);
 
@@ -287,31 +381,39 @@ static ssize_t etb_read(struct file *file, char __user *data,
 	etb_unlock(t);
 
 	total = etb_getdatalen(t);
+	if (total == 0 && t->dump_initial_etb)
+		total = t->etb_bufsz;
 	if (total == t->etb_bufsz)
 		first = etb_readl(t, ETBR_WRITEADDR);
 
+	if (pos > total * 4) {
+		skip = 0;
+		wpos = total;
+	} else {
+		skip = (int)pos % 4;
+		wpos = (int)pos / 4;
+	}
+	total -= wpos;
+	first = (first + wpos) % t->etb_bufsz;
+
 	etb_writel(t, first, ETBR_READADDR);
 
-	length = min(total * 4, (int)len);
-	buf = vmalloc(length);
+	wlength = min(total, DIV_ROUND_UP(skip + (int)len, 4));
+	length = min(total * 4 - skip, (int)len);
+	buf = vmalloc(wlength * 4);
 
-	dev_dbg(t->dev, "ETB buffer length: %d\n", total);
+	dev_dbg(t->dev, "ETB read %ld bytes to %lld from %ld words at %d\n",
+		length, pos, wlength, first);
+	dev_dbg(t->dev, "ETB buffer length: %d\n", total + wpos);
 	dev_dbg(t->dev, "ETB status reg: %x\n", etb_readl(t, ETBR_STATUS));
-	for (i = 0; i < length / 4; i++)
+	for (i = 0; i < wlength; i++)
 		buf[i] = etb_readl(t, ETBR_READMEM);
 
-	/* the only way to deassert overflow bit in ETB status is this */
-	etb_writel(t, 1, ETBR_CTRL);
-	etb_writel(t, 0, ETBR_CTRL);
-
-	etb_writel(t, 0, ETBR_WRITEADDR);
-	etb_writel(t, 0, ETBR_READADDR);
-	etb_writel(t, 0, ETBR_TRIGGERCOUNT);
-
 	etb_lock(t);
 
-	length -= copy_to_user(data, buf, length);
+	length -= copy_to_user(data, (u8 *)buf + skip, length);
 	vfree(buf);
+	*ppos = pos + length;
 
 out:
 	mutex_unlock(&t->mutex);
@@ -348,28 +450,17 @@ static int etb_probe(struct amba_device *dev, const struct amba_id *id)
 	if (ret)
 		goto out;
 
+	mutex_lock(&t->mutex);
 	t->etb_regs = ioremap_nocache(dev->res.start, resource_size(&dev->res));
 	if (!t->etb_regs) {
 		ret = -ENOMEM;
 		goto out_release;
 	}
 
+	t->dev = &dev->dev;
+	t->dump_initial_etb = true;
 	amba_set_drvdata(dev, t);
 
-	etb_miscdev.parent = &dev->dev;
-
-	ret = misc_register(&etb_miscdev);
-	if (ret)
-		goto out_unmap;
-
-	t->emu_clk = clk_get(&dev->dev, "emu_src_ck");
-	if (IS_ERR(t->emu_clk)) {
-		dev_dbg(&dev->dev, "Failed to obtain emu_src_ck.\n");
-		return -EFAULT;
-	}
-
-	clk_enable(t->emu_clk);
-
 	etb_unlock(t);
 	t->etb_bufsz = etb_readl(t, ETBR_DEPTH);
 	dev_dbg(&dev->dev, "Size: %x\n", t->etb_bufsz);
@@ -378,6 +469,20 @@ static int etb_probe(struct amba_device *dev, const struct amba_id *id)
 	etb_writel(t, 0, ETBR_CTRL);
 	etb_writel(t, 0x1000, ETBR_FORMATTERCTRL);
 	etb_lock(t);
+	mutex_unlock(&t->mutex);
+
+	etb_miscdev.parent = &dev->dev;
+
+	ret = misc_register(&etb_miscdev);
+	if (ret)
+		goto out_unmap;
+
+	/* Get optional clock. Currently used to select clock source on omap3 */
+	t->emu_clk = clk_get(&dev->dev, "emu_src_ck");
+	if (IS_ERR(t->emu_clk))
+		dev_dbg(&dev->dev, "Failed to obtain emu_src_ck.\n");
+	else
+		clk_enable(t->emu_clk);
 
 	dev_dbg(&dev->dev, "ETB AMBA driver initialized.\n");
 
@@ -385,9 +490,12 @@ out:
 	return ret;
 
 out_unmap:
+	mutex_lock(&t->mutex);
 	iounmap(t->etb_regs);
+	t->etb_regs = NULL;
 
 out_release:
+	mutex_unlock(&t->mutex);
 	amba_release_regions(dev);
 
 	return ret;
@@ -400,8 +508,10 @@ static int etb_remove(struct amba_device *dev)
 	iounmap(t->etb_regs);
 	t->etb_regs = NULL;
 
-	clk_disable(t->emu_clk);
-	clk_put(t->emu_clk);
+	if (!IS_ERR(t->emu_clk)) {
+		clk_disable(t->emu_clk);
+		clk_put(t->emu_clk);
+	}
 
 	amba_release_regions(dev);
 
@@ -445,7 +555,10 @@ static ssize_t trace_running_store(struct kobject *kobj,
 		return -EINVAL;
 
 	mutex_lock(&tracer.mutex);
-	ret = value ? trace_start(&tracer) : trace_stop(&tracer);
+	if (!tracer.etb_regs)
+		ret = -ENODEV;
+	else
+		ret = value ? trace_start(&tracer) : trace_stop(&tracer);
 	mutex_unlock(&tracer.mutex);
 
 	return ret ? : n;
@@ -460,36 +573,50 @@ static ssize_t trace_info_show(struct kobject *kobj,
 {
 	u32 etb_wa, etb_ra, etb_st, etb_fc, etm_ctrl, etm_st;
 	int datalen;
+	int id;
+	int ret;
 
-	etb_unlock(&tracer);
-	datalen = etb_getdatalen(&tracer);
-	etb_wa = etb_readl(&tracer, ETBR_WRITEADDR);
-	etb_ra = etb_readl(&tracer, ETBR_READADDR);
-	etb_st = etb_readl(&tracer, ETBR_STATUS);
-	etb_fc = etb_readl(&tracer, ETBR_FORMATTERCTRL);
-	etb_lock(&tracer);
-
-	etm_unlock(&tracer);
-	etm_ctrl = etm_readl(&tracer, ETMR_CTRL);
-	etm_st = etm_readl(&tracer, ETMR_STATUS);
-	etm_lock(&tracer);
+	mutex_lock(&tracer.mutex);
+	if (tracer.etb_regs) {
+		etb_unlock(&tracer);
+		datalen = etb_getdatalen(&tracer);
+		etb_wa = etb_readl(&tracer, ETBR_WRITEADDR);
+		etb_ra = etb_readl(&tracer, ETBR_READADDR);
+		etb_st = etb_readl(&tracer, ETBR_STATUS);
+		etb_fc = etb_readl(&tracer, ETBR_FORMATTERCTRL);
+		etb_lock(&tracer);
+	} else {
+		etb_wa = etb_ra = etb_st = etb_fc = ~0;
+		datalen = -1;
+	}
 
-	return sprintf(buf, "Trace buffer len: %d\nComparator pairs: %d\n"
+	ret = sprintf(buf, "Trace buffer len: %d\nComparator pairs: %d\n"
 			"ETBR_WRITEADDR:\t%08x\n"
 			"ETBR_READADDR:\t%08x\n"
 			"ETBR_STATUS:\t%08x\n"
-			"ETBR_FORMATTERCTRL:\t%08x\n"
-			"ETMR_CTRL:\t%08x\n"
-			"ETMR_STATUS:\t%08x\n",
+			"ETBR_FORMATTERCTRL:\t%08x\n",
 			datalen,
 			tracer.ncmppairs,
 			etb_wa,
 			etb_ra,
 			etb_st,
-			etb_fc,
+			etb_fc
+			);
+
+	for (id = 0; id < tracer.etm_regs_count; id++) {
+		etm_unlock(&tracer, id);
+		etm_ctrl = etm_readl(&tracer, id, ETMR_CTRL);
+		etm_st = etm_readl(&tracer, id, ETMR_STATUS);
+		etm_lock(&tracer, id);
+		ret += sprintf(buf + ret, "ETMR_CTRL:\t%08x\n"
+			"ETMR_STATUS:\t%08x\n",
 			etm_ctrl,
 			etm_st
 			);
+	}
+	mutex_unlock(&tracer.mutex);
+
+	return ret;
 }
 
 static struct kobj_attribute trace_info_attr =
@@ -528,42 +655,260 @@ static ssize_t trace_mode_store(struct kobject *kobj,
 static struct kobj_attribute trace_mode_attr =
 	__ATTR(trace_mode, 0644, trace_mode_show, trace_mode_store);
 
+static ssize_t trace_contextid_size_show(struct kobject *kobj,
+					 struct kobj_attribute *attr,
+					 char *buf)
+{
+	/* 0: No context id tracing, 1: One byte, 2: Two bytes, 3: Four bytes */
+	return sprintf(buf, "%d\n", (1 << tracer.etm_contextid_size) >> 1);
+}
+
+static ssize_t trace_contextid_size_store(struct kobject *kobj,
+					  struct kobj_attribute *attr,
+					  const char *buf, size_t n)
+{
+	unsigned int contextid_size;
+
+	if (sscanf(buf, "%u", &contextid_size) != 1)
+		return -EINVAL;
+
+	if (contextid_size == 3 || contextid_size > 4)
+		return -EINVAL;
+
+	mutex_lock(&tracer.mutex);
+	tracer.etm_contextid_size = fls(contextid_size);
+	mutex_unlock(&tracer.mutex);
+
+	return n;
+}
+
+static struct kobj_attribute trace_contextid_size_attr =
+	__ATTR(trace_contextid_size, 0644,
+		trace_contextid_size_show, trace_contextid_size_store);
+
+static ssize_t trace_branch_output_show(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					char *buf)
+{
+	return sprintf(buf, "%d\n", !!(tracer.flags & TRACER_BRANCHOUTPUT));
+}
+
+static ssize_t trace_branch_output_store(struct kobject *kobj,
+					 struct kobj_attribute *attr,
+					 const char *buf, size_t n)
+{
+	unsigned int branch_output;
+
+	if (sscanf(buf, "%u", &branch_output) != 1)
+		return -EINVAL;
+
+	mutex_lock(&tracer.mutex);
+	if (branch_output) {
+		tracer.flags |= TRACER_BRANCHOUTPUT;
+		/* Branch broadcasting is incompatible with the return stack */
+		tracer.flags &= ~TRACER_RETURN_STACK;
+	} else {
+		tracer.flags &= ~TRACER_BRANCHOUTPUT;
+	}
+	mutex_unlock(&tracer.mutex);
+
+	return n;
+}
+
+static struct kobj_attribute trace_branch_output_attr =
+	__ATTR(trace_branch_output, 0644,
+		trace_branch_output_show, trace_branch_output_store);
+
+static ssize_t trace_return_stack_show(struct kobject *kobj,
+				  struct kobj_attribute *attr,
+				  char *buf)
+{
+	return sprintf(buf, "%d\n", !!(tracer.flags & TRACER_RETURN_STACK));
+}
+
+static ssize_t trace_return_stack_store(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   const char *buf, size_t n)
+{
+	unsigned int return_stack;
+
+	if (sscanf(buf, "%u", &return_stack) != 1)
+		return -EINVAL;
+
+	mutex_lock(&tracer.mutex);
+	if (return_stack) {
+		tracer.flags |= TRACER_RETURN_STACK;
+		/* Return stack is incompatible with branch broadcasting */
+		tracer.flags &= ~TRACER_BRANCHOUTPUT;
+	} else {
+		tracer.flags &= ~TRACER_RETURN_STACK;
+	}
+	mutex_unlock(&tracer.mutex);
+
+	return n;
+}
+
+static struct kobj_attribute trace_return_stack_attr =
+	__ATTR(trace_return_stack, 0644,
+		trace_return_stack_show, trace_return_stack_store);
+
+static ssize_t trace_timestamp_show(struct kobject *kobj,
+				  struct kobj_attribute *attr,
+				  char *buf)
+{
+	return sprintf(buf, "%d\n", !!(tracer.flags & TRACER_TIMESTAMP));
+}
+
+static ssize_t trace_timestamp_store(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   const char *buf, size_t n)
+{
+	unsigned int timestamp;
+
+	if (sscanf(buf, "%u", &timestamp) != 1)
+		return -EINVAL;
+
+	mutex_lock(&tracer.mutex);
+	if (timestamp)
+		tracer.flags |= TRACER_TIMESTAMP;
+	else
+		tracer.flags &= ~TRACER_TIMESTAMP;
+	mutex_unlock(&tracer.mutex);
+
+	return n;
+}
+
+static struct kobj_attribute trace_timestamp_attr =
+	__ATTR(trace_timestamp, 0644,
+		trace_timestamp_show, trace_timestamp_store);
+
+static ssize_t trace_range_show(struct kobject *kobj,
+				  struct kobj_attribute *attr,
+				  char *buf)
+{
+	return sprintf(buf, "%08lx %08lx\n",
+			tracer.range_start, tracer.range_end);
+}
+
+static ssize_t trace_range_store(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   const char *buf, size_t n)
+{
+	unsigned long range_start, range_end;
+
+	if (sscanf(buf, "%lx %lx", &range_start, &range_end) != 2)
+		return -EINVAL;
+
+	mutex_lock(&tracer.mutex);
+	tracer.range_start = range_start;
+	tracer.range_end = range_end;
+	mutex_unlock(&tracer.mutex);
+
+	return n;
+}
+
+
+static struct kobj_attribute trace_range_attr =
+	__ATTR(trace_range, 0644, trace_range_show, trace_range_store);
+
+static ssize_t trace_data_range_show(struct kobject *kobj,
+				  struct kobj_attribute *attr,
+				  char *buf)
+{
+	unsigned long range_start;
+	u64 range_end;
+	mutex_lock(&tracer.mutex);
+	range_start = tracer.data_range_start;
+	range_end = tracer.data_range_end;
+	if (!range_end && (tracer.flags & TRACER_TRACE_DATA))
+		range_end = 0x100000000ULL;
+	mutex_unlock(&tracer.mutex);
+	return sprintf(buf, "%08lx %08llx\n", range_start, range_end);
+}
+
+static ssize_t trace_data_range_store(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   const char *buf, size_t n)
+{
+	unsigned long range_start;
+	u64 range_end;
+
+	if (sscanf(buf, "%lx %llx", &range_start, &range_end) != 2)
+		return -EINVAL;
+
+	mutex_lock(&tracer.mutex);
+	tracer.data_range_start = range_start;
+	tracer.data_range_end = (unsigned long)range_end;
+	if (range_end)
+		tracer.flags |= TRACER_TRACE_DATA;
+	else
+		tracer.flags &= ~TRACER_TRACE_DATA;
+	mutex_unlock(&tracer.mutex);
+
+	return n;
+}
+
+
+static struct kobj_attribute trace_data_range_attr =
+	__ATTR(trace_data_range, 0644,
+		trace_data_range_show, trace_data_range_store);
+
 static int etm_probe(struct amba_device *dev, const struct amba_id *id)
 {
 	struct tracectx *t = &tracer;
 	int ret = 0;
+	void __iomem **new_regs;
+	int new_count;
+	u32 etmccr;
+	u32 etmidr;
+	u32 etmccer = 0;
+	u8 etm_version = 0;
+
+	mutex_lock(&t->mutex);
+	new_count = t->etm_regs_count + 1;
+	new_regs = krealloc(t->etm_regs,
+				sizeof(t->etm_regs[0]) * new_count, GFP_KERNEL);
 
-	if (t->etm_regs) {
-		dev_dbg(&dev->dev, "ETM already initialized\n");
-		ret = -EBUSY;
+	if (!new_regs) {
+		dev_dbg(&dev->dev, "Failed to allocate ETM register array\n");
+		ret = -ENOMEM;
 		goto out;
 	}
+	t->etm_regs = new_regs;
 
 	ret = amba_request_regions(dev, NULL);
 	if (ret)
 		goto out;
 
-	t->etm_regs = ioremap_nocache(dev->res.start, resource_size(&dev->res));
-	if (!t->etm_regs) {
+	t->etm_regs[t->etm_regs_count] =
+		ioremap_nocache(dev->res.start, resource_size(&dev->res));
+	if (!t->etm_regs[t->etm_regs_count]) {
 		ret = -ENOMEM;
 		goto out_release;
 	}
 
-	amba_set_drvdata(dev, t);
+	amba_set_drvdata(dev, t->etm_regs[t->etm_regs_count]);
 
-	mutex_init(&t->mutex);
-	t->dev = &dev->dev;
-	t->flags = TRACER_CYCLE_ACC;
+	t->flags = TRACER_CYCLE_ACC | TRACER_TRACE_DATA | TRACER_BRANCHOUTPUT;
 	t->etm_portsz = 1;
+	t->etm_contextid_size = 3;
 
-	etm_unlock(t);
-	(void)etm_readl(t, ETMMR_PDSR);
+	etm_unlock(t, t->etm_regs_count);
+	(void)etm_readl(t, t->etm_regs_count, ETMMR_PDSR);
 	/* dummy first read */
-	(void)etm_readl(&tracer, ETMMR_OSSRR);
-
-	t->ncmppairs = etm_readl(t, ETMR_CONFCODE) & 0xf;
-	etm_writel(t, 0x440, ETMR_CTRL);
-	etm_lock(t);
+	(void)etm_readl(&tracer, t->etm_regs_count, ETMMR_OSSRR);
+
+	etmccr = etm_readl(t, t->etm_regs_count, ETMR_CONFCODE);
+	t->ncmppairs = etmccr & 0xf;
+	if (etmccr & ETMCCR_ETMIDR_PRESENT) {
+		etmidr = etm_readl(t, t->etm_regs_count, ETMR_ID);
+		etm_version = ETMIDR_VERSION(etmidr);
+		if (etm_version >= ETMIDR_VERSION_3_1)
+			etmccer = etm_readl(t, t->etm_regs_count, ETMR_CCE);
+	}
+	etm_writel(t, t->etm_regs_count, 0x441, ETMR_CTRL);
+	etm_writel(t, t->etm_regs_count, new_count, ETMR_TRACEIDR);
+	etm_lock(t, t->etm_regs_count);
 
 	ret = sysfs_create_file(&dev->dev.kobj,
 			&trace_running_attr.attr);
@@ -579,32 +924,97 @@ static int etm_probe(struct amba_device *dev, const struct amba_id *id)
 	if (ret)
 		dev_dbg(&dev->dev, "Failed to create trace_mode in sysfs\n");
 
-	dev_dbg(t->dev, "ETM AMBA driver initialized.\n");
+	ret = sysfs_create_file(&dev->dev.kobj,
+				&trace_contextid_size_attr.attr);
+	if (ret)
+		dev_dbg(&dev->dev,
+			"Failed to create trace_contextid_size in sysfs\n");
+
+	ret = sysfs_create_file(&dev->dev.kobj,
+				&trace_branch_output_attr.attr);
+	if (ret)
+		dev_dbg(&dev->dev,
+			"Failed to create trace_branch_output in sysfs\n");
+
+	if (etmccer & ETMCCER_RETURN_STACK_IMPLEMENTED) {
+		ret = sysfs_create_file(&dev->dev.kobj,
+					&trace_return_stack_attr.attr);
+		if (ret)
+			dev_dbg(&dev->dev,
+			      "Failed to create trace_return_stack in sysfs\n");
+	}
+
+	if (etmccer & ETMCCER_TIMESTAMPING_IMPLEMENTED) {
+		ret = sysfs_create_file(&dev->dev.kobj,
+					&trace_timestamp_attr.attr);
+		if (ret)
+			dev_dbg(&dev->dev,
+				"Failed to create trace_timestamp in sysfs\n");
+	}
+
+	ret = sysfs_create_file(&dev->dev.kobj, &trace_range_attr.attr);
+	if (ret)
+		dev_dbg(&dev->dev, "Failed to create trace_range in sysfs\n");
+
+	if (etm_version < ETMIDR_VERSION_PFT_1_0) {
+		ret = sysfs_create_file(&dev->dev.kobj,
+					&trace_data_range_attr.attr);
+		if (ret)
+			dev_dbg(&dev->dev,
+				"Failed to create trace_data_range in sysfs\n");
+	} else {
+		tracer.flags &= ~TRACER_TRACE_DATA;
+	}
+
+	dev_dbg(&dev->dev, "ETM AMBA driver initialized.\n");
+
+	/* Enable formatter if there are multiple trace sources */
+	if (new_count > 1)
+		t->etb_fc = ETBFF_ENFCONT | ETBFF_ENFTC;
+
+	t->etm_regs_count = new_count;
 
 out:
+	mutex_unlock(&t->mutex);
 	return ret;
 
 out_unmap:
-	iounmap(t->etm_regs);
+	iounmap(t->etm_regs[t->etm_regs_count]);
 
 out_release:
 	amba_release_regions(dev);
 
+	mutex_unlock(&t->mutex);
 	return ret;
 }
 
 static int etm_remove(struct amba_device *dev)
 {
-	struct tracectx *t = amba_get_drvdata(dev);
-
-	iounmap(t->etm_regs);
-	t->etm_regs = NULL;
-
-	amba_release_regions(dev);
+	int i;
+	struct tracectx *t = &tracer;
+	void __iomem	*etm_regs = amba_get_drvdata(dev);
 
 	sysfs_remove_file(&dev->dev.kobj, &trace_running_attr.attr);
 	sysfs_remove_file(&dev->dev.kobj, &trace_info_attr.attr);
 	sysfs_remove_file(&dev->dev.kobj, &trace_mode_attr.attr);
+	sysfs_remove_file(&dev->dev.kobj, &trace_range_attr.attr);
+	sysfs_remove_file(&dev->dev.kobj, &trace_data_range_attr.attr);
+
+	mutex_lock(&t->mutex);
+	for (i = 0; i < t->etm_regs_count; i++)
+		if (t->etm_regs[i] == etm_regs)
+			break;
+	for (; i < t->etm_regs_count - 1; i++)
+		t->etm_regs[i] = t->etm_regs[i + 1];
+	t->etm_regs_count--;
+	if (!t->etm_regs_count) {
+		kfree(t->etm_regs);
+		t->etm_regs = NULL;
+	}
+	mutex_unlock(&t->mutex);
+
+	iounmap(etm_regs);
+	amba_release_regions(dev);
 
 	return 0;
 }
@@ -614,6 +1024,10 @@ static struct amba_id etm_ids[] = {
 		.id	= 0x0003b921,
 		.mask	= 0x0007ffff,
 	},
+	{
+		.id	= 0x0003b950,
+		.mask	= 0x0007ffff,
+	},
 	{ 0, 0 },
 };
 
@@ -631,6 +1045,8 @@ static int __init etm_init(void)
 {
 	int retval;
 
+	mutex_init(&tracer.mutex);
+
 	retval = amba_driver_register(&etb_driver);
 	if (retval) {
 		printk(KERN_ERR "Failed to register etb\n");
diff --git a/arch/arm/kernel/hibernate.c b/arch/arm/kernel/hibernate.c
index c4cc50e58c1..cfb354ff2a6 100644
--- a/arch/arm/kernel/hibernate.c
+++ b/arch/arm/kernel/hibernate.c
@@ -22,6 +22,7 @@
 #include <asm/suspend.h>
 #include <asm/memory.h>
 #include <asm/sections.h>
+#include "reboot.h"
 
 int pfn_is_nosave(unsigned long pfn)
 {
@@ -61,7 +62,7 @@ static int notrace arch_save_image(unsigned long unused)
 
 	ret = swsusp_save();
 	if (ret == 0)
-		soft_restart(virt_to_phys(cpu_resume));
+		_soft_restart(virt_to_phys(cpu_resume), false);
 	return ret;
 }
 
@@ -86,7 +87,7 @@ static void notrace arch_restore_image(void *unused)
 	for (pbe = restore_pblist; pbe; pbe = pbe->next)
 		copy_page(pbe->orig_address, pbe->address);
 
-	soft_restart(virt_to_phys(cpu_resume));
+	_soft_restart(virt_to_phys(cpu_resume), false);
 }
 
 static u64 resume_stack[PAGE_SIZE/2/sizeof(u64)] __nosavedata;
diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S
index ad58e565fe9..49fadbda8c6 100644
--- a/arch/arm/kernel/iwmmxt.S
+++ b/arch/arm/kernel/iwmmxt.S
@@ -58,6 +58,7 @@
 #define MMX_SIZE		(0x98)
 
 	.text
+	.arm
 
 /*
  * Lazy switching of Concan coprocessor context
@@ -182,6 +183,8 @@ concan_load:
 	tmcr	wCon, r2
 	ret	lr
 
+ENDPROC(iwmmxt_task_enable)
+
 /*
  * Back up Concan regs to save area and disable access to them
  * (mainly for gdb or sleep mode usage)
@@ -232,6 +235,8 @@ ENTRY(iwmmxt_task_disable)
 1:	msr	cpsr_c, ip			@ restore interrupt mode
 	ldmfd	sp!, {r4, pc}
 
+ENDPROC(iwmmxt_task_disable)
+
 /*
  * Copy Concan state to given memory address
  *
@@ -268,6 +273,8 @@ ENTRY(iwmmxt_task_copy)
 	msr	cpsr_c, ip			@ restore interrupt mode
 	ret	r3
 
+ENDPROC(iwmmxt_task_copy)
+
 /*
  * Restore Concan state from given memory address
  *
@@ -304,6 +311,8 @@ ENTRY(iwmmxt_task_restore)
 	msr	cpsr_c, ip			@ restore interrupt mode
 	ret	r3
 
+ENDPROC(iwmmxt_task_restore)
+
 /*
  * Concan handling on task switch
  *
@@ -335,6 +344,8 @@ ENTRY(iwmmxt_task_switch)
 	mrc	p15, 0, r1, c2, c0, 0
 	sub	pc, lr, r1, lsr #32		@ cpwait and return
 
+ENDPROC(iwmmxt_task_switch)
+
 /*
  * Remove Concan ownership of given task
  *
@@ -353,6 +364,8 @@ ENTRY(iwmmxt_task_release)
 	msr	cpsr_c, r2			@ restore interrupts
 	ret	lr
 
+ENDPROC(iwmmxt_task_release)
+
 	.data
 concan_owner:
 	.word	0
diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c
index a74b53c1b7d..241255835ab 100644
--- a/arch/arm/kernel/kgdb.c
+++ b/arch/arm/kernel/kgdb.c
@@ -144,6 +144,8 @@ int kgdb_arch_handle_exception(int exception_vector, int signo,
 
 static int kgdb_brk_fn(struct pt_regs *regs, unsigned int instr)
 {
+	if (user_mode(regs))
+		return -1;
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
 
 	return 0;
@@ -151,6 +153,8 @@ static int kgdb_brk_fn(struct pt_regs *regs, unsigned int instr)
 
 static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int instr)
 {
+	if (user_mode(regs))
+		return -1;
 	compiled_break = 1;
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
 
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index fe972a2f3df..617ec4ab4d8 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -32,6 +32,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/leds.h>
 #include <linux/reboot.h>
+#include <linux/console.h>
 
 #include <asm/cacheflush.h>
 #include <asm/idmap.h>
@@ -41,6 +42,7 @@
 #include <asm/system_misc.h>
 #include <asm/mach/time.h>
 #include <asm/tls.h>
+#include "reboot.h"
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 #include <linux/stackprotector.h>
@@ -59,9 +61,46 @@ static const char *isa_modes[] __maybe_unused = {
   "ARM" , "Thumb" , "Jazelle", "ThumbEE"
 };
 
+#ifdef CONFIG_SMP
+void arch_trigger_all_cpu_backtrace(void)
+{
+	smp_send_all_cpu_backtrace();
+}
+#else
+void arch_trigger_all_cpu_backtrace(void)
+{
+	dump_stack();
+}
+#endif
+
 extern void call_with_stack(void (*fn)(void *), void *arg, void *sp);
 typedef void (*phys_reset_t)(unsigned long);
 
+#ifdef CONFIG_ARM_FLUSH_CONSOLE_ON_RESTART
+void arm_machine_flush_console(void)
+{
+	printk("\n");
+	pr_emerg("Restarting %s\n", linux_banner);
+	if (console_trylock()) {
+		console_unlock();
+		return;
+	}
+
+	mdelay(50);
+
+	local_irq_disable();
+	if (!console_trylock())
+		pr_emerg("arm_restart: Console was locked! Busting\n");
+	else
+		pr_emerg("arm_restart: Console was locked!\n");
+	console_unlock();
+}
+#else
+void arm_machine_flush_console(void)
+{
+}
+#endif
+
 /*
  * A temporary stack to use for CPU reset. This is static so that we
  * don't clobber it with the identity mapping. When running with this
@@ -95,7 +134,7 @@ static void __soft_restart(void *addr)
 	BUG();
 }
 
-void soft_restart(unsigned long addr)
+void _soft_restart(unsigned long addr, bool disable_l2)
 {
 	u64 *stack = soft_restart_stack + ARRAY_SIZE(soft_restart_stack);
 
@@ -104,7 +143,7 @@ void soft_restart(unsigned long addr)
 	local_fiq_disable();
 
 	/* Disable the L2 if we're the last man standing. */
-	if (num_online_cpus() == 1)
+	if (disable_l2)
 		outer_disable();
 
 	/* Change to the new stack and continue with the reset. */
@@ -114,6 +153,11 @@ void soft_restart(unsigned long addr)
 	BUG();
 }
 
+void soft_restart(unsigned long addr)
+{
+	_soft_restart(addr, num_online_cpus() == 1);
+}
+
 /*
  * Function pointers to optional machine specific functions
  */
@@ -148,6 +192,7 @@ void arch_cpu_idle_prepare(void)
 
 void arch_cpu_idle_enter(void)
 {
+	idle_notifier_call_chain(IDLE_START);
 	ledtrig_cpu(CPU_LED_IDLE_START);
 #ifdef CONFIG_PL310_ERRATA_769419
 	wmb();
@@ -157,6 +202,7 @@ void arch_cpu_idle_enter(void)
 void arch_cpu_idle_exit(void)
 {
 	ledtrig_cpu(CPU_LED_IDLE_END);
+	idle_notifier_call_chain(IDLE_END);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -177,6 +223,16 @@ void arch_cpu_idle_dead(void)
  */
 void machine_shutdown(void)
 {
+#ifdef CONFIG_SMP
+	/*
+	 * Disable preemption so we're guaranteed to
+	 * run to power off or reboot and prevent
+	 * the possibility of switching to another
+	 * thread that might wind up blocking on
+	 * one of the stopped CPUs.
+	 */
+	preempt_disable();
+#endif
 	disable_nonboot_cpus();
 }
 
@@ -225,6 +281,11 @@ void machine_restart(char *cmd)
 	local_irq_disable();
 	smp_send_stop();
 
+
+	/* Flush the console to make sure all the relevant messages make it
+	 * out to the console drivers */
+	arm_machine_flush_console();
+
 	if (arm_pm_restart)
 		arm_pm_restart(reboot_mode, cmd);
 	else
@@ -239,6 +300,77 @@ void machine_restart(char *cmd)
 	while (1);
 }
 
+/*
+ * dump a block of kernel memory from around the given address
+ */
+static void show_data(unsigned long addr, int nbytes, const char *name)
+{
+	int	i, j;
+	int	nlines;
+	u32	*p;
+
+	/*
+	 * don't attempt to dump non-kernel addresses or
+	 * values that are probably just small negative numbers
+	 */
+	if (addr < PAGE_OFFSET || addr > -256UL)
+		return;
+
+	printk("\n%s: %#lx:\n", name, addr);
+
+	/*
+	 * round address down to a 32 bit boundary
+	 * and always dump a multiple of 32 bytes
+	 */
+	p = (u32 *)(addr & ~(sizeof(u32) - 1));
+	nbytes += (addr & (sizeof(u32) - 1));
+	nlines = (nbytes + 31) / 32;
+
+
+	for (i = 0; i < nlines; i++) {
+		/*
+		 * just display low 16 bits of address to keep
+		 * each line of the dump < 80 characters
+		 */
+		printk("%04lx ", (unsigned long)p & 0xffff);
+		for (j = 0; j < 8; j++) {
+			u32	data;
+			if (probe_kernel_address(p, data)) {
+				printk(" ********");
+			} else {
+				printk(" %08x", data);
+			}
+			++p;
+		}
+		printk("\n");
+	}
+}
+
+static void show_extra_register_data(struct pt_regs *regs, int nbytes)
+{
+	mm_segment_t fs;
+
+	fs = get_fs();
+	set_fs(KERNEL_DS);
+	show_data(regs->ARM_pc - nbytes, nbytes * 2, "PC");
+	show_data(regs->ARM_lr - nbytes, nbytes * 2, "LR");
+	show_data(regs->ARM_sp - nbytes, nbytes * 2, "SP");
+	show_data(regs->ARM_ip - nbytes, nbytes * 2, "IP");
+	show_data(regs->ARM_fp - nbytes, nbytes * 2, "FP");
+	show_data(regs->ARM_r0 - nbytes, nbytes * 2, "R0");
+	show_data(regs->ARM_r1 - nbytes, nbytes * 2, "R1");
+	show_data(regs->ARM_r2 - nbytes, nbytes * 2, "R2");
+	show_data(regs->ARM_r3 - nbytes, nbytes * 2, "R3");
+	show_data(regs->ARM_r4 - nbytes, nbytes * 2, "R4");
+	show_data(regs->ARM_r5 - nbytes, nbytes * 2, "R5");
+	show_data(regs->ARM_r6 - nbytes, nbytes * 2, "R6");
+	show_data(regs->ARM_r7 - nbytes, nbytes * 2, "R7");
+	show_data(regs->ARM_r8 - nbytes, nbytes * 2, "R8");
+	show_data(regs->ARM_r9 - nbytes, nbytes * 2, "R9");
+	show_data(regs->ARM_r10 - nbytes, nbytes * 2, "R10");
+	set_fs(fs);
+}
+
 void __show_regs(struct pt_regs *regs)
 {
 	unsigned long flags;
@@ -300,6 +432,8 @@ void __show_regs(struct pt_regs *regs)
 		printk("Control: %08x%s\n", ctrl, buf);
 	}
 #endif
+
+	show_extra_register_data(regs, 128);
 }
 
 void show_regs(struct pt_regs * regs)
diff --git a/arch/arm/kernel/psci-call.S b/arch/arm/kernel/psci-call.S
new file mode 100644
index 00000000000..a78e9e1e206
--- /dev/null
+++ b/arch/arm/kernel/psci-call.S
@@ -0,0 +1,31 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2015 ARM Limited
+ *
+ * Author: Mark Rutland <mark.rutland@arm.com>
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/opcodes-sec.h>
+#include <asm/opcodes-virt.h>
+
+/* int __invoke_psci_fn_hvc(u32 function_id, u32 arg0, u32 arg1, u32 arg2) */
+ENTRY(__invoke_psci_fn_hvc)
+	__HVC(0)
+	bx	lr
+ENDPROC(__invoke_psci_fn_hvc)
+
+/* int __invoke_psci_fn_smc(u32 function_id, u32 arg0, u32 arg1, u32 arg2) */
+ENTRY(__invoke_psci_fn_smc)
+	__SMC(0)
+	bx	lr
+ENDPROC(__invoke_psci_fn_smc)
diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c
index f73891b6b73..f90fdf4ce7c 100644
--- a/arch/arm/kernel/psci.c
+++ b/arch/arm/kernel/psci.c
@@ -23,8 +23,6 @@
 
 #include <asm/compiler.h>
 #include <asm/errno.h>
-#include <asm/opcodes-sec.h>
-#include <asm/opcodes-virt.h>
 #include <asm/psci.h>
 #include <asm/system_misc.h>
 
@@ -33,6 +31,9 @@ struct psci_operations psci_ops;
 static int (*invoke_psci_fn)(u32, u32, u32, u32);
 typedef int (*psci_initcall_t)(const struct device_node *);
 
+asmlinkage int __invoke_psci_fn_hvc(u32, u32, u32, u32);
+asmlinkage int __invoke_psci_fn_smc(u32, u32, u32, u32);
+
 enum psci_function {
 	PSCI_FN_CPU_SUSPEND,
 	PSCI_FN_CPU_ON,
@@ -71,40 +72,6 @@ static u32 psci_power_state_pack(struct psci_power_state state)
 		 & PSCI_0_2_POWER_STATE_AFFL_MASK);
 }
 
-/*
- * The following two functions are invoked via the invoke_psci_fn pointer
- * and will not be inlined, allowing us to piggyback on the AAPCS.
- */
-static noinline int __invoke_psci_fn_hvc(u32 function_id, u32 arg0, u32 arg1,
-					 u32 arg2)
-{
-	asm volatile(
-			__asmeq("%0", "r0")
-			__asmeq("%1", "r1")
-			__asmeq("%2", "r2")
-			__asmeq("%3", "r3")
-			__HVC(0)
-		: "+r" (function_id)
-		: "r" (arg0), "r" (arg1), "r" (arg2));
-
-	return function_id;
-}
-
-static noinline int __invoke_psci_fn_smc(u32 function_id, u32 arg0, u32 arg1,
-					 u32 arg2)
-{
-	asm volatile(
-			__asmeq("%0", "r0")
-			__asmeq("%1", "r1")
-			__asmeq("%2", "r2")
-			__asmeq("%3", "r3")
-			__SMC(0)
-		: "+r" (function_id)
-		: "r" (arg0), "r" (arg1), "r" (arg2));
-
-	return function_id;
-}
-
 static int psci_get_version(void)
 {
 	int err;
diff --git a/arch/arm/kernel/reboot.h b/arch/arm/kernel/reboot.h
new file mode 100644
index 00000000000..c87f05816d6
--- /dev/null
+++ b/arch/arm/kernel/reboot.h
@@ -0,0 +1,6 @@
+#ifndef REBOOT_H
+#define REBOOT_H
+
+extern void _soft_restart(unsigned long addr, bool disable_l2);
+
+#endif
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index c03106378b4..306e1ac2c8e 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -1043,6 +1043,15 @@ static int c_show(struct seq_file *m, void *v)
 		seq_printf(m, "model name\t: %s rev %d (%s)\n",
 			   cpu_name, cpuid & 15, elf_platform);
 
+#if defined(CONFIG_SMP)
+		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
+			   per_cpu(cpu_data, i).loops_per_jiffy / (500000UL/HZ),
+			   (per_cpu(cpu_data, i).loops_per_jiffy / (5000UL/HZ)) % 100);
+#else
+		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
+			   loops_per_jiffy / (500000/HZ),
+			   (loops_per_jiffy / (5000/HZ)) % 100);
+#endif
 		/* dump out the processor features */
 		seq_puts(m, "Features\t: ");
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 13396d3d600..9ce02e6e396 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -72,6 +72,7 @@ enum ipi_msg_type {
 	IPI_CPU_STOP,
 	IPI_IRQ_WORK,
 	IPI_COMPLETION,
+	IPI_CPU_BACKTRACE,
 };
 
 static DECLARE_COMPLETION(cpu_running);
@@ -387,8 +388,17 @@ asmlinkage void secondary_start_kernel(void)
 
 void __init smp_cpus_done(unsigned int max_cpus)
 {
-	printk(KERN_INFO "SMP: Total of %d processors activated.\n",
-	       num_online_cpus());
+	int cpu;
+	unsigned long bogosum = 0;
+
+	for_each_online_cpu(cpu)
+		bogosum += per_cpu(cpu_data, cpu).loops_per_jiffy;
+
+	printk(KERN_INFO "SMP: Total of %d processors activated "
+	       "(%lu.%02lu BogoMIPS).\n",
+	       num_online_cpus(),
+	       bogosum / (500000/HZ),
+	       (bogosum / (5000/HZ)) % 100);
 
 	hyp_mode_check();
 }
@@ -447,6 +457,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = {
 	S(IPI_CPU_STOP, "CPU stop interrupts"),
 	S(IPI_IRQ_WORK, "IRQ work interrupts"),
 	S(IPI_COMPLETION, "completion interrupts"),
+	S(IPI_CPU_BACKTRACE, "CPU backtrace"),
 };
 
 static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
@@ -548,6 +559,58 @@ static void ipi_complete(unsigned int cpu)
 	complete(per_cpu(cpu_completion, cpu));
 }
 
+static cpumask_t backtrace_mask;
+static DEFINE_RAW_SPINLOCK(backtrace_lock);
+
+/* "in progress" flag of arch_trigger_all_cpu_backtrace */
+static unsigned long backtrace_flag;
+
+void smp_send_all_cpu_backtrace(void)
+{
+	unsigned int this_cpu = smp_processor_id();
+	int i;
+
+	if (test_and_set_bit(0, &backtrace_flag))
+		/*
+		 * If there is already a trigger_all_cpu_backtrace() in progress
+		 * (backtrace_flag == 1), don't output double cpu dump infos.
+		 */
+		return;
+
+	cpumask_copy(&backtrace_mask, cpu_online_mask);
+	cpu_clear(this_cpu, backtrace_mask);
+
+	pr_info("Backtrace for cpu %d (current):\n", this_cpu);
+	dump_stack();
+
+	pr_info("\nsending IPI to all other CPUs:\n");
+	smp_cross_call(&backtrace_mask, IPI_CPU_BACKTRACE);
+
+	/* Wait for up to 10 seconds for all other CPUs to do the backtrace */
+	for (i = 0; i < 10 * 1000; i++) {
+		if (cpumask_empty(&backtrace_mask))
+			break;
+		mdelay(1);
+	}
+
+	clear_bit(0, &backtrace_flag);
+	smp_mb__after_atomic();
+}
+
+/*
+ * ipi_cpu_backtrace - handle IPI from smp_send_all_cpu_backtrace()
+ */
+static void ipi_cpu_backtrace(unsigned int cpu, struct pt_regs *regs)
+{
+	if (cpu_isset(cpu, backtrace_mask)) {
+		raw_spin_lock(&backtrace_lock);
+		pr_warning("IPI backtrace for cpu %d\n", cpu);
+		show_regs(regs);
+		raw_spin_unlock(&backtrace_lock);
+		cpu_clear(cpu, backtrace_mask);
+	}
+}
+
 /*
  * Main handler for inter-processor interrupts
  */
@@ -614,6 +677,10 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 		irq_exit();
 		break;
 
+	case IPI_CPU_BACKTRACE:
+		ipi_cpu_backtrace(cpu, regs);
+		break;
+
 	default:
 		printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
 		       cpu, ipinr);
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 89cfdd6e50c..efc2cb392e9 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 
 #include <asm/cputype.h>
+#include <asm/smp_plat.h>
 #include <asm/topology.h>
 
 /*
@@ -289,6 +290,111 @@ static struct sched_domain_topology_level arm_topology[] = {
 	{ NULL, },
 };
 
+#ifdef CONFIG_SCHED_HMP
+
+static const char * const little_cores[] = {
+	"arm,cortex-a7",
+	NULL,
+};
+
+static bool is_little_cpu(struct device_node *cn)
+{
+	const char * const *lc;
+	for (lc = little_cores; *lc; lc++)
+		if (of_device_is_compatible(cn, *lc))
+			return true;
+	return false;
+}
+
+void __init arch_get_fast_and_slow_cpus(struct cpumask *fast,
+					struct cpumask *slow)
+{
+	struct device_node *cn = NULL;
+	int cpu;
+
+	cpumask_clear(fast);
+	cpumask_clear(slow);
+
+	/*
+	 * Use the config options if they are given. This helps testing
+	 * HMP scheduling on systems without a big.LITTLE architecture.
+	 */
+	if (strlen(CONFIG_HMP_FAST_CPU_MASK) && strlen(CONFIG_HMP_SLOW_CPU_MASK)) {
+		if (cpulist_parse(CONFIG_HMP_FAST_CPU_MASK, fast))
+			WARN(1, "Failed to parse HMP fast cpu mask!\n");
+		if (cpulist_parse(CONFIG_HMP_SLOW_CPU_MASK, slow))
+			WARN(1, "Failed to parse HMP slow cpu mask!\n");
+		return;
+	}
+
+	/*
+	 * Else, parse device tree for little cores.
+	 */
+	while ((cn = of_find_node_by_type(cn, "cpu"))) {
+
+		const u32 *mpidr;
+		int len;
+
+		mpidr = of_get_property(cn, "reg", &len);
+		if (!mpidr || len != 4) {
+			pr_err("* %s missing reg property\n", cn->full_name);
+			continue;
+		}
+
+		cpu = get_logical_index(be32_to_cpup(mpidr));
+		if (cpu == -EINVAL) {
+			pr_err("couldn't get logical index for mpidr %x\n",
+							be32_to_cpup(mpidr));
+			break;
+		}
+
+		if (is_little_cpu(cn))
+			cpumask_set_cpu(cpu, slow);
+		else
+			cpumask_set_cpu(cpu, fast);
+	}
+
+	if (!cpumask_empty(fast) && !cpumask_empty(slow))
+		return;
+
+	/*
+	 * We didn't find both big and little cores so let's call all cores
+	 * fast as this will keep the system running, with all cores being
+	 * treated equal.
+	 */
+	cpumask_setall(fast);
+	cpumask_clear(slow);
+}
+
+struct cpumask hmp_slow_cpu_mask;
+
+void __init arch_get_hmp_domains(struct list_head *hmp_domains_list)
+{
+	struct cpumask hmp_fast_cpu_mask;
+	struct hmp_domain *domain;
+
+	arch_get_fast_and_slow_cpus(&hmp_fast_cpu_mask, &hmp_slow_cpu_mask);
+
+	/*
+	 * Initialize hmp_domains
+	 * Must be ordered with respect to compute capacity.
+	 * Fastest domain at head of list.
+	 */
+	if(!cpumask_empty(&hmp_slow_cpu_mask)) {
+		domain = (struct hmp_domain *)
+			kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+		cpumask_copy(&domain->possible_cpus, &hmp_slow_cpu_mask);
+		cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+		list_add(&domain->hmp_domains, hmp_domains_list);
+	}
+	domain = (struct hmp_domain *)
+		kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+	cpumask_copy(&domain->possible_cpus, &hmp_fast_cpu_mask);
+	cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+	list_add(&domain->hmp_domains, hmp_domains_list);
+}
+#endif /* CONFIG_SCHED_HMP */
+
 /*
  * init_cpu_topology is called at boot when only one cpu is running
  * which prevent simultaneous write access to cpu_topology array
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 9e193c8a959..ed5834e8e2a 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -213,6 +213,11 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	int err;
 	struct kvm_vcpu *vcpu;
 
+	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) {
+		err = -EBUSY;
+		goto out;
+	}
+
 	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
 	if (!vcpu) {
 		err = -ENOMEM;
@@ -419,6 +424,7 @@ static void update_vttbr(struct kvm *kvm)
 
 static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 {
+	struct kvm *kvm = vcpu->kvm;
 	int ret;
 
 	if (likely(vcpu->arch.has_run_once))
@@ -427,15 +433,23 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.has_run_once = true;
 
 	/*
-	 * Initialize the VGIC before running a vcpu the first time on
-	 * this VM.
+	 * Map the VGIC hardware resources before running a vcpu the first
+	 * time on this VM.
 	 */
-	if (unlikely(!vgic_initialized(vcpu->kvm))) {
-		ret = kvm_vgic_init(vcpu->kvm);
+	if (unlikely(!vgic_initialized(kvm))) {
+		ret = kvm_vgic_map_resources(kvm);
 		if (ret)
 			return ret;
 	}
 
+	/*
+	 * Enable the arch timers only if we have an in-kernel VGIC
+	 * and it has been properly initialized, since we cannot handle
+	 * interrupts from the virtual timer with a userspace gic.
+	 */
+	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm))
+		kvm_timer_enable(kvm);
+
 	return 0;
 }
 
@@ -639,8 +653,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 		if (!irqchip_in_kernel(kvm))
 			return -ENXIO;
 
-		if (irq_num < VGIC_NR_PRIVATE_IRQS ||
-		    irq_num > KVM_ARM_IRQ_GIC_MAX)
+		if (irq_num < VGIC_NR_PRIVATE_IRQS)
 			return -EINVAL;
 
 		return kvm_vgic_inject_irq(kvm, 0, irq_num, level);
@@ -659,10 +672,21 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 		return ret;
 
 	/*
+	 * Ensure a rebooted VM will fault in RAM pages and detect if the
+	 * guest MMU is turned off and flush the caches as needed.
+	 */
+	if (vcpu->arch.has_run_once)
+		stage2_unmap_vm(vcpu->kvm);
+
+	vcpu_reset_hcr(vcpu);
+
+	/*
 	 * Handle the "start in power-off" case by marking the VCPU as paused.
 	 */
-	if (__test_and_clear_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
+	if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
 		vcpu->arch.pause = true;
+	else
+		vcpu->arch.pause = false;
 
 	return 0;
 }
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index cc0b78769bd..8c97208b9b9 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -38,7 +38,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.hcr = HCR_GUEST_MASK;
 	return 0;
 }
 
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index 01dcb0e752d..d66d608f7ce 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -159,13 +159,9 @@ __kvm_vcpu_return:
 	@ Don't trap coprocessor accesses for host kernel
 	set_hstr vmexit
 	set_hdcr vmexit
-	set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11))
+	set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)), after_vfp_restore
 
 #ifdef CONFIG_VFPv3
-	@ Save floating point registers we if let guest use them.
-	tst	r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
-	bne	after_vfp_restore
-
 	@ Switch VFP/NEON hardware state to the host's
 	add	r7, vcpu, #VCPU_VFP_GUEST
 	store_vfp_state r7
@@ -177,6 +173,8 @@ after_vfp_restore:
 	@ Restore FPEXC_EN which we clobbered on entry
 	pop	{r2}
 	VFPFMXR FPEXC, r2
+#else
+after_vfp_restore:
 #endif
 
 	@ Reset Hyp-role
@@ -472,7 +470,7 @@ switch_to_guest_vfp:
 	push	{r3-r7}
 
 	@ NEON/VFP used.  Turn on VFP access.
-	set_hcptr vmexit, (HCPTR_TCP(10) | HCPTR_TCP(11))
+	set_hcptr vmtrap, (HCPTR_TCP(10) | HCPTR_TCP(11))
 
 	@ Switch VFP/NEON hardware state to the guest's
 	add	r7, r0, #VCPU_VFP_HOST
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 14d48838848..f6f14812d10 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -599,8 +599,13 @@ ARM_BE8(rev	r6, r6  )
 .endm
 
 /* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return
- * (hardware reset value is 0). Keep previous value in r2. */
-.macro set_hcptr operation, mask
+ * (hardware reset value is 0). Keep previous value in r2.
+ * An ISB is emited on vmexit/vmtrap, but executed on vmexit only if
+ * VFP wasn't already enabled (always executed on vmtrap).
+ * If a label is specified with vmexit, it is branched to if VFP wasn't
+ * enabled.
+ */
+.macro set_hcptr operation, mask, label = none
 	mrc	p15, 4, r2, c1, c1, 2
 	ldr	r3, =\mask
 	.if \operation == vmentry
@@ -609,6 +614,17 @@ ARM_BE8(rev	r6, r6  )
 	bic	r3, r2, r3		@ Don't trap defined coproc-accesses
 	.endif
 	mcr	p15, 4, r3, c1, c1, 2
+	.if \operation != vmentry
+	.if \operation == vmexit
+	tst	r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
+	beq	1f
+	.endif
+	isb
+	.if \label != none
+	b	\label
+	.endif
+1:
+	.endif
 .endm
 
 /* Configures the HDCR (Hyp Debug Configuration Register) on entry/return
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 8664ff17cbb..cba52cf6ed3 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -58,6 +58,26 @@ static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
 }
 
+/*
+ * D-Cache management functions. They take the page table entries by
+ * value, as they are flushing the cache using the kernel mapping (or
+ * kmap on 32bit).
+ */
+static void kvm_flush_dcache_pte(pte_t pte)
+{
+	__kvm_flush_dcache_pte(pte);
+}
+
+static void kvm_flush_dcache_pmd(pmd_t pmd)
+{
+	__kvm_flush_dcache_pmd(pmd);
+}
+
+static void kvm_flush_dcache_pud(pud_t pud)
+{
+	__kvm_flush_dcache_pud(pud);
+}
+
 static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
 				  int min, int max)
 {
@@ -119,6 +139,26 @@ static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
 	put_page(virt_to_page(pmd));
 }
 
+/*
+ * Unmapping vs dcache management:
+ *
+ * If a guest maps certain memory pages as uncached, all writes will
+ * bypass the data cache and go directly to RAM.  However, the CPUs
+ * can still speculate reads (not writes) and fill cache lines with
+ * data.
+ *
+ * Those cache lines will be *clean* cache lines though, so a
+ * clean+invalidate operation is equivalent to an invalidate
+ * operation, because no cache lines are marked dirty.
+ *
+ * Those clean cache lines could be filled prior to an uncached write
+ * by the guest, and the cache coherent IO subsystem would therefore
+ * end up writing old data to disk.
+ *
+ * This is why right after unmapping a page/section and invalidating
+ * the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure
+ * the IO subsystem will never hit in the cache.
+ */
 static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
 		       phys_addr_t addr, phys_addr_t end)
 {
@@ -128,9 +168,16 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
 	start_pte = pte = pte_offset_kernel(pmd, addr);
 	do {
 		if (!pte_none(*pte)) {
+			pte_t old_pte = *pte;
+
 			kvm_set_pte(pte, __pte(0));
-			put_page(virt_to_page(pte));
 			kvm_tlb_flush_vmid_ipa(kvm, addr);
+
+			/* No need to invalidate the cache for device mappings */
+			if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
+				kvm_flush_dcache_pte(old_pte);
+
+			put_page(virt_to_page(pte));
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 
@@ -149,8 +196,13 @@ static void unmap_pmds(struct kvm *kvm, pud_t *pud,
 		next = kvm_pmd_addr_end(addr, end);
 		if (!pmd_none(*pmd)) {
 			if (kvm_pmd_huge(*pmd)) {
+				pmd_t old_pmd = *pmd;
+
 				pmd_clear(pmd);
 				kvm_tlb_flush_vmid_ipa(kvm, addr);
+
+				kvm_flush_dcache_pmd(old_pmd);
+
 				put_page(virt_to_page(pmd));
 			} else {
 				unmap_ptes(kvm, pmd, addr, next);
@@ -173,8 +225,13 @@ static void unmap_puds(struct kvm *kvm, pgd_t *pgd,
 		next = kvm_pud_addr_end(addr, end);
 		if (!pud_none(*pud)) {
 			if (pud_huge(*pud)) {
+				pud_t old_pud = *pud;
+
 				pud_clear(pud);
 				kvm_tlb_flush_vmid_ipa(kvm, addr);
+
+				kvm_flush_dcache_pud(old_pud);
+
 				put_page(virt_to_page(pud));
 			} else {
 				unmap_pmds(kvm, pud, addr, next);
@@ -194,7 +251,7 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
 	phys_addr_t addr = start, end = start + size;
 	phys_addr_t next;
 
-	pgd = pgdp + pgd_index(addr);
+	pgd = pgdp + kvm_pgd_index(addr);
 	do {
 		next = kvm_pgd_addr_end(addr, end);
 		if (!pgd_none(*pgd))
@@ -209,10 +266,9 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
 
 	pte = pte_offset_kernel(pmd, addr);
 	do {
-		if (!pte_none(*pte)) {
-			hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
-			kvm_flush_dcache_to_poc((void*)hva, PAGE_SIZE);
-		}
+		if (!pte_none(*pte) &&
+		    (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
+			kvm_flush_dcache_pte(*pte);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
@@ -226,12 +282,10 @@ static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
 	do {
 		next = kvm_pmd_addr_end(addr, end);
 		if (!pmd_none(*pmd)) {
-			if (kvm_pmd_huge(*pmd)) {
-				hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
-				kvm_flush_dcache_to_poc((void*)hva, PMD_SIZE);
-			} else {
+			if (kvm_pmd_huge(*pmd))
+				kvm_flush_dcache_pmd(*pmd);
+			else
 				stage2_flush_ptes(kvm, pmd, addr, next);
-			}
 		}
 	} while (pmd++, addr = next, addr != end);
 }
@@ -246,12 +300,10 @@ static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd,
 	do {
 		next = kvm_pud_addr_end(addr, end);
 		if (!pud_none(*pud)) {
-			if (pud_huge(*pud)) {
-				hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
-				kvm_flush_dcache_to_poc((void*)hva, PUD_SIZE);
-			} else {
+			if (pud_huge(*pud))
+				kvm_flush_dcache_pud(*pud);
+			else
 				stage2_flush_pmds(kvm, pud, addr, next);
-			}
 		}
 	} while (pud++, addr = next, addr != end);
 }
@@ -264,7 +316,7 @@ static void stage2_flush_memslot(struct kvm *kvm,
 	phys_addr_t next;
 	pgd_t *pgd;
 
-	pgd = kvm->arch.pgd + pgd_index(addr);
+	pgd = kvm->arch.pgd + kvm_pgd_index(addr);
 	do {
 		next = kvm_pgd_addr_end(addr, end);
 		stage2_flush_puds(kvm, pgd, addr, next);
@@ -541,6 +593,20 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
 				     __phys_to_pfn(phys_addr), PAGE_HYP_DEVICE);
 }
 
+/* Free the HW pgd, one page at a time */
+static void kvm_free_hwpgd(void *hwpgd)
+{
+	free_pages_exact(hwpgd, kvm_get_hwpgd_size());
+}
+
+/* Allocate the HW PGD, making sure that each page gets its own refcount */
+static void *kvm_alloc_hwpgd(void)
+{
+	unsigned int size = kvm_get_hwpgd_size();
+
+	return alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
+}
+
 /**
  * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation.
  * @kvm:	The KVM struct pointer for the VM.
@@ -554,15 +620,31 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
  */
 int kvm_alloc_stage2_pgd(struct kvm *kvm)
 {
-	int ret;
 	pgd_t *pgd;
+	void *hwpgd;
 
 	if (kvm->arch.pgd != NULL) {
 		kvm_err("kvm_arch already initialized?\n");
 		return -EINVAL;
 	}
 
+	hwpgd = kvm_alloc_hwpgd();
+	if (!hwpgd)
+		return -ENOMEM;
+
+	/* When the kernel uses more levels of page tables than the
+	 * guest, we allocate a fake PGD and pre-populate it to point
+	 * to the next-level page table, which will be the real
+	 * initial page table pointed to by the VTTBR.
+	 *
+	 * When KVM_PREALLOC_LEVEL==2, we allocate a single page for
+	 * the PMD and the kernel will use folded pud.
+	 * When KVM_PREALLOC_LEVEL==1, we allocate 2 consecutive PUD
+	 * pages.
+	 */
 	if (KVM_PREALLOC_LEVEL > 0) {
+		int i;
+
 		/*
 		 * Allocate fake pgd for the page table manipulation macros to
 		 * work.  This is not used by the hardware and we have no
@@ -570,30 +652,32 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
 		 */
 		pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t),
 				       GFP_KERNEL | __GFP_ZERO);
+
+		if (!pgd) {
+			kvm_free_hwpgd(hwpgd);
+			return -ENOMEM;
+		}
+
+		/* Plug the HW PGD into the fake one. */
+		for (i = 0; i < PTRS_PER_S2_PGD; i++) {
+			if (KVM_PREALLOC_LEVEL == 1)
+				pgd_populate(NULL, pgd + i,
+					     (pud_t *)hwpgd + i * PTRS_PER_PUD);
+			else if (KVM_PREALLOC_LEVEL == 2)
+				pud_populate(NULL, pud_offset(pgd, 0) + i,
+					     (pmd_t *)hwpgd + i * PTRS_PER_PMD);
+		}
 	} else {
 		/*
 		 * Allocate actual first-level Stage-2 page table used by the
 		 * hardware for Stage-2 page table walks.
 		 */
-		pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, S2_PGD_ORDER);
+		pgd = (pgd_t *)hwpgd;
 	}
 
-	if (!pgd)
-		return -ENOMEM;
-
-	ret = kvm_prealloc_hwpgd(kvm, pgd);
-	if (ret)
-		goto out_err;
-
 	kvm_clean_pgd(pgd);
 	kvm->arch.pgd = pgd;
 	return 0;
-out_err:
-	if (KVM_PREALLOC_LEVEL > 0)
-		kfree(pgd);
-	else
-		free_pages((unsigned long)pgd, S2_PGD_ORDER);
-	return ret;
 }
 
 /**
@@ -612,6 +696,71 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 	unmap_range(kvm, kvm->arch.pgd, start, size);
 }
 
+static void stage2_unmap_memslot(struct kvm *kvm,
+				 struct kvm_memory_slot *memslot)
+{
+	hva_t hva = memslot->userspace_addr;
+	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
+	phys_addr_t size = PAGE_SIZE * memslot->npages;
+	hva_t reg_end = hva + size;
+
+	/*
+	 * A memory region could potentially cover multiple VMAs, and any holes
+	 * between them, so iterate over all of them to find out if we should
+	 * unmap any of them.
+	 *
+	 *     +--------------------------------------------+
+	 * +---------------+----------------+   +----------------+
+	 * |   : VMA 1     |      VMA 2     |   |    VMA 3  :    |
+	 * +---------------+----------------+   +----------------+
+	 *     |               memory region                |
+	 *     +--------------------------------------------+
+	 */
+	do {
+		struct vm_area_struct *vma = find_vma(current->mm, hva);
+		hva_t vm_start, vm_end;
+
+		if (!vma || vma->vm_start >= reg_end)
+			break;
+
+		/*
+		 * Take the intersection of this VMA with the memory region
+		 */
+		vm_start = max(hva, vma->vm_start);
+		vm_end = min(reg_end, vma->vm_end);
+
+		if (!(vma->vm_flags & VM_PFNMAP)) {
+			gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
+			unmap_stage2_range(kvm, gpa, vm_end - vm_start);
+		}
+		hva = vm_end;
+	} while (hva < reg_end);
+}
+
+/**
+ * stage2_unmap_vm - Unmap Stage-2 RAM mappings
+ * @kvm: The struct kvm pointer
+ *
+ * Go through the memregions and unmap any reguler RAM
+ * backing memory already mapped to the VM.
+ */
+void stage2_unmap_vm(struct kvm *kvm)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	int idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	spin_lock(&kvm->mmu_lock);
+
+	slots = kvm_memslots(kvm);
+	kvm_for_each_memslot(memslot, slots)
+		stage2_unmap_memslot(kvm, memslot);
+
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, idx);
+}
+
 /**
  * kvm_free_stage2_pgd - free all stage-2 tables
  * @kvm:	The KVM struct pointer for the VM.
@@ -629,11 +778,10 @@ void kvm_free_stage2_pgd(struct kvm *kvm)
 		return;
 
 	unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
-	kvm_free_hwpgd(kvm);
+	kvm_free_hwpgd(kvm_get_hwpgd(kvm));
 	if (KVM_PREALLOC_LEVEL > 0)
 		kfree(kvm->arch.pgd);
-	else
-		free_pages((unsigned long)kvm->arch.pgd, S2_PGD_ORDER);
+
 	kvm->arch.pgd = NULL;
 }
 
@@ -643,7 +791,7 @@ static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	pgd_t *pgd;
 	pud_t *pud;
 
-	pgd = kvm->arch.pgd + pgd_index(addr);
+	pgd = kvm->arch.pgd + kvm_pgd_index(addr);
 	if (WARN_ON(pgd_none(*pgd))) {
 		if (!cache)
 			return NULL;
@@ -840,6 +988,12 @@ static bool kvm_is_device_pfn(unsigned long pfn)
 	return !pfn_valid(pfn);
 }
 
+static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
+				      unsigned long size, bool uncached)
+{
+	__coherent_cache_guest_page(vcpu, pfn, size, uncached);
+}
+
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			  struct kvm_memory_slot *memslot, unsigned long hva,
 			  unsigned long fault_status)
@@ -853,6 +1007,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	struct vm_area_struct *vma;
 	pfn_t pfn;
 	pgprot_t mem_type = PAGE_S2;
+	bool fault_ipa_uncached;
 
 	write_fault = kvm_is_write_fault(vcpu);
 	if (fault_status == FSC_PERM && !write_fault) {
@@ -919,6 +1074,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (!hugetlb && !force_pte)
 		hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa);
 
+	fault_ipa_uncached = memslot->flags & KVM_MEMSLOT_INCOHERENT;
+
 	if (hugetlb) {
 		pmd_t new_pmd = pfn_pmd(pfn, mem_type);
 		new_pmd = pmd_mkhuge(new_pmd);
@@ -926,7 +1083,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			kvm_set_s2pmd_writable(&new_pmd);
 			kvm_set_pfn_dirty(pfn);
 		}
-		coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE);
+		coherent_cache_guest_page(vcpu, pfn, PMD_SIZE, fault_ipa_uncached);
 		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
 	} else {
 		pte_t new_pte = pfn_pte(pfn, mem_type);
@@ -934,7 +1091,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			kvm_set_s2pte_writable(&new_pte);
 			kvm_set_pfn_dirty(pfn);
 		}
-		coherent_cache_guest_page(vcpu, hva, PAGE_SIZE);
+		coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE, fault_ipa_uncached);
 		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte,
 			pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE));
 	}
@@ -1294,11 +1451,12 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		hva = vm_end;
 	} while (hva < reg_end);
 
-	if (ret) {
-		spin_lock(&kvm->mmu_lock);
+	spin_lock(&kvm->mmu_lock);
+	if (ret)
 		unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size);
-		spin_unlock(&kvm->mmu_lock);
-	}
+	else
+		stage2_flush_memslot(kvm, memslot);
+	spin_unlock(&kvm->mmu_lock);
 	return ret;
 }
 
@@ -1310,6 +1468,15 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 			    unsigned long npages)
 {
+	/*
+	 * Readonly memslots are not incoherent with the caches by definition,
+	 * but in practice, they are used mostly to emulate ROMs or NOR flashes
+	 * that the guest may consider devices and hence map as uncached.
+	 * To prevent incoherency issues in these cases, tag all readonly
+	 * regions as incoherent.
+	 */
+	if (slot->flags & KVM_MEM_READONLY)
+		slot->flags |= KVM_MEMSLOT_INCOHERENT;
 	return 0;
 }
 
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 09cf37737ee..4d0d89e342f 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -15,6 +15,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/preempt.h>
 #include <linux/kvm_host.h>
 #include <linux/wait.h>
 
@@ -166,6 +167,23 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
 
 static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type)
 {
+	int i;
+	struct kvm_vcpu *tmp;
+
+	/*
+	 * The KVM ABI specifies that a system event exit may call KVM_RUN
+	 * again and may perform shutdown/reboot at a later time that when the
+	 * actual request is made.  Since we are implementing PSCI and a
+	 * caller of PSCI reboot and shutdown expects that the system shuts
+	 * down or reboots immediately, let's make sure that VCPUs are not run
+	 * after this call is handled and before the VCPUs have been
+	 * re-initialized.
+	 */
+	kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
+		tmp->arch.pause = true;
+		kvm_vcpu_kick(tmp);
+	}
+
 	memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event));
 	vcpu->run->system_event.type = type;
 	vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
@@ -219,10 +237,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 	case PSCI_0_2_FN64_AFFINITY_INFO:
 		val = kvm_psci_vcpu_affinity_info(vcpu);
 		break;
-	case PSCI_0_2_FN_MIGRATE:
-	case PSCI_0_2_FN64_MIGRATE:
-		val = PSCI_RET_NOT_SUPPORTED;
-		break;
 	case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
 		/*
 		 * Trusted OS is MP hence does not require migration
@@ -231,10 +245,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		 */
 		val = PSCI_0_2_TOS_MP;
 		break;
-	case PSCI_0_2_FN_MIGRATE_INFO_UP_CPU:
-	case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU:
-		val = PSCI_RET_NOT_SUPPORTED;
-		break;
 	case PSCI_0_2_FN_SYSTEM_OFF:
 		kvm_psci_system_off(vcpu);
 		/*
@@ -260,7 +270,8 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		ret = 0;
 		break;
 	default:
-		return -EINVAL;
+		val = PSCI_RET_NOT_SUPPORTED;
+		break;
 	}
 
 	*vcpu_reg(vcpu, 0) = val;
@@ -280,12 +291,9 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 	case KVM_PSCI_FN_CPU_ON:
 		val = kvm_psci_vcpu_on(vcpu);
 		break;
-	case KVM_PSCI_FN_CPU_SUSPEND:
-	case KVM_PSCI_FN_MIGRATE:
+	default:
 		val = PSCI_RET_NOT_SUPPORTED;
 		break;
-	default:
-		return -EINVAL;
 	}
 
 	*vcpu_reg(vcpu, 0) = val;
diff --git a/arch/arm/mach-at91/pm.h b/arch/arm/mach-at91/pm.h
index c5101dcb4fb..1d4df3b70eb 100644
--- a/arch/arm/mach-at91/pm.h
+++ b/arch/arm/mach-at91/pm.h
@@ -45,7 +45,7 @@ static inline void at91rm9200_standby(void)
 		"    mcr    p15, 0, %0, c7, c0, 4\n\t"
 		"    str    %5, [%1, %2]"
 		:
-		: "r" (0), "r" (AT91_BASE_SYS), "r" (AT91RM9200_SDRAMC_LPR),
+		: "r" (0), "r" (at91_ramc_base[0]), "r" (AT91RM9200_SDRAMC_LPR),
 		  "r" (1), "r" (AT91RM9200_SDRAMC_SRR),
 		  "r" (lpr));
 }
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 4e79da7c5e3..5474a76803f 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -144,8 +144,8 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 		post_div_table[1].div = 1;
 		post_div_table[2].div = 1;
 		video_div_table[1].div = 1;
-		video_div_table[2].div = 1;
-	};
+		video_div_table[3].div = 1;
+	}
 
 	clk[IMX6QDL_PLL1_BYPASS_SRC] = imx_clk_mux("pll1_bypass_src", base + 0x00, 14, 2, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
 	clk[IMX6QDL_PLL2_BYPASS_SRC] = imx_clk_mux("pll2_bypass_src", base + 0x30, 14, 2, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
@@ -439,7 +439,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[IMX6QDL_CLK_GPMI_IO]      = imx_clk_gate2("gpmi_io",       "enfc",              base + 0x78, 28);
 	clk[IMX6QDL_CLK_GPMI_APB]     = imx_clk_gate2("gpmi_apb",      "usdhc3",            base + 0x78, 30);
 	clk[IMX6QDL_CLK_ROM]          = imx_clk_gate2("rom",           "ahb",               base + 0x7c, 0);
-	clk[IMX6QDL_CLK_SATA]         = imx_clk_gate2("sata",          "ipg",               base + 0x7c, 4);
+	clk[IMX6QDL_CLK_SATA]         = imx_clk_gate2("sata",          "ahb",               base + 0x7c, 4);
 	clk[IMX6QDL_CLK_SDMA]         = imx_clk_gate2("sdma",          "ahb",               base + 0x7c, 6);
 	clk[IMX6QDL_CLK_SPBA]         = imx_clk_gate2("spba",          "ipg",               base + 0x7c, 12);
 	clk[IMX6QDL_CLK_SPDIF]        = imx_clk_gate2("spdif",         "spdif_podf",        base + 0x7c, 14);
diff --git a/arch/arm/mach-imx/clk-imx6sx.c b/arch/arm/mach-imx/clk-imx6sx.c
index 17354a11356..5a3e5a159e7 100644
--- a/arch/arm/mach-imx/clk-imx6sx.c
+++ b/arch/arm/mach-imx/clk-imx6sx.c
@@ -558,6 +558,9 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clk_set_parent(clks[IMX6SX_CLK_GPU_CORE_SEL], clks[IMX6SX_CLK_PLL3_PFD0]);
 	clk_set_parent(clks[IMX6SX_CLK_GPU_AXI_SEL], clks[IMX6SX_CLK_PLL3_PFD0]);
 
+	clk_set_parent(clks[IMX6SX_CLK_QSPI1_SEL], clks[IMX6SX_CLK_PLL2_BUS]);
+	clk_set_parent(clks[IMX6SX_CLK_QSPI2_SEL], clks[IMX6SX_CLK_PLL2_BUS]);
+
 	/* Set initial power mode */
 	imx6q_set_lpm(WAIT_CLOCKED);
 }
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index 044b51185fc..01efe130912 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -342,6 +342,13 @@ static void __init armada_375_380_coherency_init(struct device_node *np)
 	arch_ioremap_caller = armada_pcie_wa_ioremap_caller;
 
 	/*
+	 * We should switch the PL310 to I/O coherency mode only if
+	 * I/O coherency is actually enabled.
+	 */
+	if (!coherency_available())
+		return;
+
+	/*
 	 * Add the PL310 property "arm,io-coherent". This makes sure the
 	 * outer sync operation is not used, which allows to
 	 * workaround the system erratum that causes deadlocks when
@@ -361,30 +368,51 @@ static int coherency_type(void)
 {
 	struct device_node *np;
 	const struct of_device_id *match;
+	int type;
 
-	np = of_find_matching_node_and_match(NULL, of_coherency_table, &match);
-	if (np) {
-		int type = (int) match->data;
+	/*
+	 * The coherency fabric is needed:
+	 * - For coherency between processors on Armada XP, so only
+	 *   when SMP is enabled.
+	 * - For coherency between the processor and I/O devices, but
+	 *   this coherency requires many pre-requisites (write
+	 *   allocate cache policy, shareable pages, SMP bit set) that
+	 *   are only meant in SMP situations.
+	 *
+	 * Note that this means that on Armada 370, there is currently
+	 * no way to use hardware I/O coherency, because even when
+	 * CONFIG_SMP is enabled, is_smp() returns false due to the
+	 * Armada 370 being a single-core processor. To lift this
+	 * limitation, we would have to find a way to make the cache
+	 * policy set to write-allocate (on all Armada SoCs), and to
+	 * set the shareable attribute in page tables (on all Armada
+	 * SoCs except the Armada 370). Unfortunately, such decisions
+	 * are taken very early in the kernel boot process, at a point
+	 * where we don't know yet on which SoC we are running.
+
+	 */
+	if (!is_smp())
+		return COHERENCY_FABRIC_TYPE_NONE;
 
-		/* Armada 370/XP coherency works in both UP and SMP */
-		if (type == COHERENCY_FABRIC_TYPE_ARMADA_370_XP)
-			return type;
+	np = of_find_matching_node_and_match(NULL, of_coherency_table, &match);
+	if (!np)
+		return COHERENCY_FABRIC_TYPE_NONE;
 
-		/* Armada 375 coherency works only on SMP */
-		else if (type == COHERENCY_FABRIC_TYPE_ARMADA_375 && is_smp())
-			return type;
+	type = (int) match->data;
 
-		/* Armada 380 coherency works only on SMP */
-		else if (type == COHERENCY_FABRIC_TYPE_ARMADA_380 && is_smp())
-			return type;
-	}
+	of_node_put(np);
 
-	return COHERENCY_FABRIC_TYPE_NONE;
+	return type;
 }
 
+/*
+ * As a precaution, we currently completely disable hardware I/O
+ * coherency, until enough testing is done with automatic I/O
+ * synchronization barriers to validate that it is a proper solution.
+ */
 int coherency_available(void)
 {
-	return coherency_type() != COHERENCY_FABRIC_TYPE_NONE;
+	return false;
 }
 
 int __init coherency_init(void)
@@ -420,8 +448,9 @@ static int __init coherency_late_init(void)
 			armada_375_coherency_init_wa();
 	}
 
-	bus_register_notifier(&platform_bus_type,
-			      &mvebu_hwcc_nb);
+	if (coherency_available())
+		bus_register_notifier(&platform_bus_type,
+				      &mvebu_hwcc_nb);
 
 	return 0;
 }
diff --git a/arch/arm/mach-mvebu/coherency_ll.S b/arch/arm/mach-mvebu/coherency_ll.S
index f5d881b5d0f..8b2fbc8b6bc 100644
--- a/arch/arm/mach-mvebu/coherency_ll.S
+++ b/arch/arm/mach-mvebu/coherency_ll.S
@@ -24,7 +24,10 @@
 #include <asm/cp15.h>
 
 	.text
-/* Returns the coherency base address in r1 (r0 is untouched) */
+/*
+ * Returns the coherency base address in r1 (r0 is untouched), or 0 if
+ * the coherency fabric is not enabled.
+ */
 ENTRY(ll_get_coherency_base)
 	mrc	p15, 0, r1, c1, c0, 0
 	tst	r1, #CR_M @ Check MMU bit enabled
@@ -32,8 +35,13 @@ ENTRY(ll_get_coherency_base)
 
 	/*
 	 * MMU is disabled, use the physical address of the coherency
-	 * base address.
+	 * base address. However, if the coherency fabric isn't mapped
+	 * (i.e its virtual address is zero), it means coherency is
+	 * not enabled, so we return 0.
 	 */
+	ldr	r1, =coherency_base
+	cmp	r1, #0
+	beq	2f
 	adr	r1, 3f
 	ldr	r3, [r1]
 	ldr	r1, [r1, r3]
@@ -85,6 +93,9 @@ ENTRY(ll_add_cpu_to_smp_group)
 	 */
 	mov 	r0, lr
 	bl	ll_get_coherency_base
+	/* Bail out if the coherency is not enabled */
+	cmp	r1, #0
+	reteq	r0
 	bl	ll_get_coherency_cpumask
 	mov 	lr, r0
 	add	r0, r1, #ARMADA_XP_CFB_CFG_REG_OFFSET
@@ -107,6 +118,9 @@ ENTRY(ll_enable_coherency)
 	 */
 	mov r0, lr
 	bl	ll_get_coherency_base
+	/* Bail out if the coherency is not enabled */
+	cmp	r1, #0
+	reteq	r0
 	bl	ll_get_coherency_cpumask
 	mov lr, r0
 	add	r0, r1, #ARMADA_XP_CFB_CTL_REG_OFFSET
@@ -131,6 +145,9 @@ ENTRY(ll_disable_coherency)
 	 */
 	mov 	r0, lr
 	bl	ll_get_coherency_base
+	/* Bail out if the coherency is not enabled */
+	cmp	r1, #0
+	reteq	r0
 	bl	ll_get_coherency_cpumask
 	mov 	lr, r0
 	add	r0, r1, #ARMADA_XP_CFB_CTL_REG_OFFSET
diff --git a/arch/arm/mach-mvebu/pmsu.c b/arch/arm/mach-mvebu/pmsu.c
index bbd8664d1ba..6f8a85c5965 100644
--- a/arch/arm/mach-mvebu/pmsu.c
+++ b/arch/arm/mach-mvebu/pmsu.c
@@ -415,6 +415,9 @@ static __init int armada_38x_cpuidle_init(void)
 	void __iomem *mpsoc_base;
 	u32 reg;
 
+	pr_warn("CPU idle is currently broken on Armada 38x: disabling");
+	return 0;
+
 	np = of_find_compatible_node(NULL, NULL,
 				     "marvell,armada-380-coherency-fabric");
 	if (!np)
@@ -476,6 +479,16 @@ static int __init mvebu_v7_cpu_pm_init(void)
 		return 0;
 	of_node_put(np);
 
+	/*
+	 * Currently the CPU idle support for Armada 38x is broken, as
+	 * the CPU hotplug uses some of the CPU idle functions it is
+	 * broken too, so let's disable it
+	 */
+	if (of_machine_is_compatible("marvell,armada380")) {
+		cpu_hotplug_disable();
+		pr_warn("CPU hotplug support is currently broken on Armada 38x: disabling");
+	}
+
 	if (of_machine_is_compatible("marvell,armadaxp"))
 		ret = armada_xp_cpuidle_init();
 	else if (of_machine_is_compatible("marvell,armada370"))
@@ -489,7 +502,8 @@ static int __init mvebu_v7_cpu_pm_init(void)
 		return ret;
 
 	mvebu_v7_pmsu_enable_l2_powerdown_onidle();
-	platform_device_register(&mvebu_v7_cpuidle_device);
+	if (mvebu_v7_cpuidle_device.name)
+		platform_device_register(&mvebu_v7_cpuidle_device);
 	cpu_pm_register_notifier(&mvebu_v7_cpu_pm_notifier);
 
 	return 0;
diff --git a/arch/arm/mach-mvebu/system-controller.c b/arch/arm/mach-mvebu/system-controller.c
index a068cb5c2ce..c6c132acd7a 100644
--- a/arch/arm/mach-mvebu/system-controller.c
+++ b/arch/arm/mach-mvebu/system-controller.c
@@ -126,7 +126,7 @@ int mvebu_system_controller_get_soc_id(u32 *dev, u32 *rev)
 		return -ENODEV;
 }
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(CONFIG_MACH_MVEBU_V7)
 void mvebu_armada375_smp_wa_init(void)
 {
 	u32 dev, rev;
diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index 377eea849e7..db57741c9c8 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -249,6 +249,7 @@ extern void omap4_cpu_die(unsigned int cpu);
 extern struct smp_operations omap4_smp_ops;
 
 extern void omap5_secondary_startup(void);
+extern void omap5_secondary_hyp_startup(void);
 #endif
 
 #if defined(CONFIG_SMP) && defined(CONFIG_PM)
diff --git a/arch/arm/mach-omap2/omap-headsmp.S b/arch/arm/mach-omap2/omap-headsmp.S
index 4993d4bfe9b..6d1dffca6c7 100644
--- a/arch/arm/mach-omap2/omap-headsmp.S
+++ b/arch/arm/mach-omap2/omap-headsmp.S
@@ -22,6 +22,7 @@
 
 /* Physical address needed since MMU not enabled yet on secondary core */
 #define AUX_CORE_BOOT0_PA			0x48281800
+#define API_HYP_ENTRY				0x102
 
 /*
  * OMAP5 specific entry point for secondary CPU to jump from ROM
@@ -41,6 +42,26 @@ wait:	ldr	r2, =AUX_CORE_BOOT0_PA	@ read from AuxCoreBoot0
 	b	secondary_startup
 ENDPROC(omap5_secondary_startup)
 /*
+ * Same as omap5_secondary_startup except we call into the ROM to
+ * enable HYP mode first.  This is called instead of
+ * omap5_secondary_startup if the primary CPU was put into HYP mode by
+ * the boot loader.
+ */
+ENTRY(omap5_secondary_hyp_startup)
+wait_2:	ldr	r2, =AUX_CORE_BOOT0_PA	@ read from AuxCoreBoot0
+	ldr	r0, [r2]
+	mov	r0, r0, lsr #5
+	mrc	p15, 0, r4, c0, c0, 5
+	and	r4, r4, #0x0f
+	cmp	r0, r4
+	bne	wait_2
+	ldr	r12, =API_HYP_ENTRY
+	adr	r0, hyp_boot
+	smc	#0
+hyp_boot:
+	b	secondary_startup
+ENDPROC(omap5_secondary_hyp_startup)
+/*
  * OMAP4 specific entry point for secondary CPU to jump from ROM
  * code.  This routine also provides a holding flag into which
  * secondary core is held until we're ready for it to initialise.
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 256e84ef0f6..5305ec7341e 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -22,6 +22,7 @@
 #include <linux/irqchip/arm-gic.h>
 
 #include <asm/smp_scu.h>
+#include <asm/virt.h>
 
 #include "omap-secure.h"
 #include "omap-wakeupgen.h"
@@ -227,8 +228,16 @@ static void __init omap4_smp_prepare_cpus(unsigned int max_cpus)
 	if (omap_secure_apis_support())
 		omap_auxcoreboot_addr(virt_to_phys(startup_addr));
 	else
-		writel_relaxed(virt_to_phys(omap5_secondary_startup),
-			       base + OMAP_AUX_CORE_BOOT_1);
+		/*
+		 * If the boot CPU is in HYP mode then start secondary
+		 * CPU in HYP mode as well.
+		 */
+		if ((__boot_cpu_mode & MODE_MASK) == HYP_MODE)
+			writel_relaxed(virt_to_phys(omap5_secondary_hyp_startup),
+				       base + OMAP_AUX_CORE_BOOT_1);
+		else
+			writel_relaxed(virt_to_phys(omap5_secondary_startup),
+				       base + OMAP_AUX_CORE_BOOT_1);
 
 }
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 5684f112654..4e9d2a97c2c 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -2017,7 +2017,7 @@ static struct omap_hwmod dra7xx_uart3_hwmod = {
 	.class		= &dra7xx_uart_hwmod_class,
 	.clkdm_name	= "l4per_clkdm",
 	.main_clk	= "uart3_gfclk_mux",
-	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.flags		= HWMOD_SWSUP_SIDLE_ACT | DEBUG_OMAP4UART3_FLAGS,
 	.prcm = {
 		.omap4 = {
 			.clkctrl_offs = DRA7XX_CM_L4PER_UART3_CLKCTRL_OFFSET,
diff --git a/arch/arm/mach-omap2/pm44xx.c b/arch/arm/mach-omap2/pm44xx.c
index 503097c72b8..e7f823b960c 100644
--- a/arch/arm/mach-omap2/pm44xx.c
+++ b/arch/arm/mach-omap2/pm44xx.c
@@ -160,26 +160,6 @@ static inline int omap4_init_static_deps(void)
 	struct clockdomain *ducati_clkdm, *l3_2_clkdm;
 	int ret = 0;
 
-	if (omap_rev() == OMAP4430_REV_ES1_0) {
-		WARN(1, "Power Management not supported on OMAP4430 ES1.0\n");
-		return -ENODEV;
-	}
-
-	pr_err("Power Management for TI OMAP4.\n");
-	/*
-	 * OMAP4 chip PM currently works only with certain (newer)
-	 * versions of bootloaders. This is due to missing code in the
-	 * kernel to properly reset and initialize some devices.
-	 * http://www.spinics.net/lists/arm-kernel/msg218641.html
-	 */
-	pr_warn("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n");
-
-	ret = pwrdm_for_each(pwrdms_setup, NULL);
-	if (ret) {
-		pr_err("Failed to setup powerdomains\n");
-		return ret;
-	}
-
 	/*
 	 * The dynamic dependency between MPUSS -> MEMIF and
 	 * MPUSS -> L4_PER/L3_* and DUCATI -> L3_* doesn't work as
@@ -272,6 +252,15 @@ int __init omap4_pm_init(void)
 
 	pr_info("Power Management for TI OMAP4+ devices.\n");
 
+	/*
+	 * OMAP4 chip PM currently works only with certain (newer)
+	 * versions of bootloaders. This is due to missing code in the
+	 * kernel to properly reset and initialize some devices.
+	 * http://www.spinics.net/lists/arm-kernel/msg218641.html
+	 */
+	if (cpu_is_omap44xx())
+		pr_warn("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n");
+
 	ret = pwrdm_for_each(pwrdms_setup, NULL);
 	if (ret) {
 		pr_err("Failed to setup powerdomains.\n");
diff --git a/arch/arm/mach-omap2/prm-regbits-34xx.h b/arch/arm/mach-omap2/prm-regbits-34xx.h
index cbefbd7cfdb..661d753df58 100644
--- a/arch/arm/mach-omap2/prm-regbits-34xx.h
+++ b/arch/arm/mach-omap2/prm-regbits-34xx.h
@@ -112,6 +112,7 @@
 #define OMAP3430_VC_CMD_ONLP_SHIFT			16
 #define OMAP3430_VC_CMD_RET_SHIFT			8
 #define OMAP3430_VC_CMD_OFF_SHIFT			0
+#define OMAP3430_SREN_MASK				(1 << 4)
 #define OMAP3430_HSEN_MASK				(1 << 3)
 #define OMAP3430_MCODE_MASK				(0x7 << 0)
 #define OMAP3430_VALID_MASK				(1 << 24)
diff --git a/arch/arm/mach-omap2/prm-regbits-44xx.h b/arch/arm/mach-omap2/prm-regbits-44xx.h
index b1c7a33e00e..e794828dee5 100644
--- a/arch/arm/mach-omap2/prm-regbits-44xx.h
+++ b/arch/arm/mach-omap2/prm-regbits-44xx.h
@@ -35,6 +35,7 @@
 #define OMAP4430_GLOBAL_WARM_SW_RST_SHIFT				1
 #define OMAP4430_GLOBAL_WUEN_MASK					(1 << 16)
 #define OMAP4430_HSMCODE_MASK						(0x7 << 0)
+#define OMAP4430_SRMODEEN_MASK						(1 << 4)
 #define OMAP4430_HSMODEEN_MASK						(1 << 3)
 #define OMAP4430_HSSCLL_SHIFT						24
 #define OMAP4430_ICEPICK_RST_SHIFT					9
diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S
index d1dedc8195e..eafd120b53f 100644
--- a/arch/arm/mach-omap2/sleep34xx.S
+++ b/arch/arm/mach-omap2/sleep34xx.S
@@ -203,23 +203,8 @@ save_context_wfi:
 	 */
 	ldr	r1, kernel_flush
 	blx	r1
-	/*
-	 * The kernel doesn't interwork: v7_flush_dcache_all in particluar will
-	 * always return in Thumb state when CONFIG_THUMB2_KERNEL is enabled.
-	 * This sequence switches back to ARM.  Note that .align may insert a
-	 * nop: bx pc needs to be word-aligned in order to work.
-	 */
- THUMB(	.thumb		)
- THUMB(	.align		)
- THUMB(	bx	pc	)
- THUMB(	nop		)
-	.arm
-
 	b	omap3_do_wfi
-
-/*
- * Local variables
- */
+ENDPROC(omap34xx_cpu_suspend)
 omap3_do_wfi_sram_addr:
 	.word omap3_do_wfi_sram
 kernel_flush:
@@ -364,10 +349,7 @@ exit_nonoff_modes:
  * ===================================
  */
 	ldmfd	sp!, {r4 - r11, pc}	@ restore regs and return
-
-/*
- * Local variables
- */
+ENDPROC(omap3_do_wfi)
 sdrc_power:
 	.word	SDRC_POWER_V
 cm_idlest1_core:
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index 4f61148ec16..fb0cb2b817a 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -513,11 +513,11 @@ static void __init realtime_counter_init(void)
 	rate = clk_get_rate(sys_clk);
 	/* Numerator/denumerator values refer TRM Realtime Counter section */
 	switch (rate) {
-	case 1200000:
+	case 12000000:
 		num = 64;
 		den = 125;
 		break;
-	case 1300000:
+	case 13000000:
 		num = 768;
 		den = 1625;
 		break;
@@ -529,11 +529,11 @@ static void __init realtime_counter_init(void)
 		num = 192;
 		den = 625;
 		break;
-	case 2600000:
+	case 26000000:
 		num = 384;
 		den = 1625;
 		break;
-	case 2700000:
+	case 27000000:
 		num = 256;
 		den = 1125;
 		break;
diff --git a/arch/arm/mach-omap2/vc.c b/arch/arm/mach-omap2/vc.c
index be9ef834fa8..076fd20d7e5 100644
--- a/arch/arm/mach-omap2/vc.c
+++ b/arch/arm/mach-omap2/vc.c
@@ -316,7 +316,8 @@ static void __init omap3_vc_init_pmic_signaling(struct voltagedomain *voltdm)
 	 * idle. And we can also scale voltages to zero for off-idle.
 	 * Note that no actual voltage scaling during off-idle will
 	 * happen unless the board specific twl4030 PMIC scripts are
-	 * loaded.
+	 * loaded. See also omap_vc_i2c_init for comments regarding
+	 * erratum i531.
 	 */
 	val = voltdm->read(OMAP3_PRM_VOLTCTRL_OFFSET);
 	if (!(val & OMAP3430_PRM_VOLTCTRL_SEL_OFF)) {
@@ -704,9 +705,16 @@ static void __init omap_vc_i2c_init(struct voltagedomain *voltdm)
 		return;
 	}
 
+	/*
+	 * Note that for omap3 OMAP3430_SREN_MASK clears SREN to work around
+	 * erratum i531 "Extra Power Consumed When Repeated Start Operation
+	 * Mode Is Enabled on I2C Interface Dedicated for Smart Reflex (I2C4)".
+	 * Otherwise I2C4 eventually leads into about 23mW extra power being
+	 * consumed even during off idle using VMODE.
+	 */
 	i2c_high_speed = voltdm->pmic->i2c_high_speed;
 	if (i2c_high_speed)
-		voltdm->rmw(vc->common->i2c_cfg_hsen_mask,
+		voltdm->rmw(vc->common->i2c_cfg_clear_mask,
 			    vc->common->i2c_cfg_hsen_mask,
 			    vc->common->i2c_cfg_reg);
 
diff --git a/arch/arm/mach-omap2/vc.h b/arch/arm/mach-omap2/vc.h
index cdbdd78e755..89b83b7ff3e 100644
--- a/arch/arm/mach-omap2/vc.h
+++ b/arch/arm/mach-omap2/vc.h
@@ -34,6 +34,7 @@ struct voltagedomain;
  * @cmd_ret_shift: RET field shift in PRM_VC_CMD_VAL_* register
  * @cmd_off_shift: OFF field shift in PRM_VC_CMD_VAL_* register
  * @i2c_cfg_reg: I2C configuration register offset
+ * @i2c_cfg_clear_mask: high-speed mode bit clear mask in I2C config register
  * @i2c_cfg_hsen_mask: high-speed mode bit field mask in I2C config register
  * @i2c_mcode_mask: MCODE field mask for I2C config register
  *
@@ -52,6 +53,7 @@ struct omap_vc_common {
 	u8 cmd_ret_shift;
 	u8 cmd_off_shift;
 	u8 i2c_cfg_reg;
+	u8 i2c_cfg_clear_mask;
 	u8 i2c_cfg_hsen_mask;
 	u8 i2c_mcode_mask;
 };
diff --git a/arch/arm/mach-omap2/vc3xxx_data.c b/arch/arm/mach-omap2/vc3xxx_data.c
index 75bc4aa22b3..71d74c9172c 100644
--- a/arch/arm/mach-omap2/vc3xxx_data.c
+++ b/arch/arm/mach-omap2/vc3xxx_data.c
@@ -40,6 +40,7 @@ static struct omap_vc_common omap3_vc_common = {
 	.cmd_onlp_shift	 = OMAP3430_VC_CMD_ONLP_SHIFT,
 	.cmd_ret_shift	 = OMAP3430_VC_CMD_RET_SHIFT,
 	.cmd_off_shift	 = OMAP3430_VC_CMD_OFF_SHIFT,
+	.i2c_cfg_clear_mask = OMAP3430_SREN_MASK | OMAP3430_HSEN_MASK,
 	.i2c_cfg_hsen_mask = OMAP3430_HSEN_MASK,
 	.i2c_cfg_reg	 = OMAP3_PRM_VC_I2C_CFG_OFFSET,
 	.i2c_mcode_mask	 = OMAP3430_MCODE_MASK,
diff --git a/arch/arm/mach-omap2/vc44xx_data.c b/arch/arm/mach-omap2/vc44xx_data.c
index 085e5d6a04f..2abd5fa8a69 100644
--- a/arch/arm/mach-omap2/vc44xx_data.c
+++ b/arch/arm/mach-omap2/vc44xx_data.c
@@ -42,6 +42,7 @@ static const struct omap_vc_common omap4_vc_common = {
 	.cmd_ret_shift = OMAP4430_RET_SHIFT,
 	.cmd_off_shift = OMAP4430_OFF_SHIFT,
 	.i2c_cfg_reg = OMAP4_PRM_VC_CFG_I2C_MODE_OFFSET,
+	.i2c_cfg_clear_mask = OMAP4430_SRMODEEN_MASK | OMAP4430_HSMODEEN_MASK,
 	.i2c_cfg_hsen_mask = OMAP4430_HSMODEEN_MASK,
 	.i2c_mcode_mask	 = OMAP4430_HSMCODE_MASK,
 };
diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c
index 06022b23573..89f790dda93 100644
--- a/arch/arm/mach-pxa/corgi.c
+++ b/arch/arm/mach-pxa/corgi.c
@@ -26,6 +26,7 @@
 #include <linux/i2c.h>
 #include <linux/i2c/pxa-i2c.h>
 #include <linux/io.h>
+#include <linux/regulator/machine.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/ads7846.h>
 #include <linux/spi/corgi_lcd.h>
@@ -752,6 +753,8 @@ static void __init corgi_init(void)
 		sharpsl_nand_partitions[1].size = 53 * 1024 * 1024;
 
 	platform_add_devices(devices, ARRAY_SIZE(devices));
+
+	regulator_has_full_constraints();
 }
 
 static void __init fixup_corgi(struct tag *tags, char **cmdline)
diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c
index c66ad4edc5e..5fb41ad6e3b 100644
--- a/arch/arm/mach-pxa/hx4700.c
+++ b/arch/arm/mach-pxa/hx4700.c
@@ -893,6 +893,8 @@ static void __init hx4700_init(void)
 	mdelay(10);
 	gpio_set_value(GPIO71_HX4700_ASIC3_nRESET, 1);
 	mdelay(10);
+
+	regulator_has_full_constraints();
 }
 
 MACHINE_START(H4700, "HP iPAQ HX4700")
diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c
index 13199162911..e81d216b05e 100644
--- a/arch/arm/mach-pxa/poodle.c
+++ b/arch/arm/mach-pxa/poodle.c
@@ -25,6 +25,7 @@
 #include <linux/gpio.h>
 #include <linux/i2c.h>
 #include <linux/i2c/pxa-i2c.h>
+#include <linux/regulator/machine.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/ads7846.h>
 #include <linux/spi/pxa2xx_spi.h>
@@ -455,6 +456,7 @@ static void __init poodle_init(void)
 	pxa_set_i2c_info(NULL);
 	i2c_register_board_info(0, ARRAY_AND_SIZE(poodle_i2c_devices));
 	poodle_init_spi();
+	regulator_has_full_constraints();
 }
 
 static void __init fixup_poodle(struct tag *tags, char **cmdline)
diff --git a/arch/arm/mach-s3c64xx/crag6410.h b/arch/arm/mach-s3c64xx/crag6410.h
index 7bc66682687..dcbe17f5e5f 100644
--- a/arch/arm/mach-s3c64xx/crag6410.h
+++ b/arch/arm/mach-s3c64xx/crag6410.h
@@ -14,6 +14,7 @@
 #include <mach/gpio-samsung.h>
 
 #define GLENFARCLAS_PMIC_IRQ_BASE	IRQ_BOARD_START
+#define BANFF_PMIC_IRQ_BASE		(IRQ_BOARD_START + 64)
 
 #define PCA935X_GPIO_BASE		GPIO_BOARD_START
 #define CODEC_GPIO_BASE			(GPIO_BOARD_START + 8)
diff --git a/arch/arm/mach-s3c64xx/mach-crag6410.c b/arch/arm/mach-s3c64xx/mach-crag6410.c
index 10b913baab2..65c426bc45f 100644
--- a/arch/arm/mach-s3c64xx/mach-crag6410.c
+++ b/arch/arm/mach-s3c64xx/mach-crag6410.c
@@ -554,6 +554,7 @@ static struct wm831x_touch_pdata touch_pdata = {
 
 static struct wm831x_pdata crag_pmic_pdata = {
 	.wm831x_num = 1,
+	.irq_base = BANFF_PMIC_IRQ_BASE,
 	.gpio_base = BANFF_PMIC_GPIO_BASE,
 	.soft_shutdown = true,
 
diff --git a/arch/arm/mach-sa1100/pm.c b/arch/arm/mach-sa1100/pm.c
index 6645d1e31f1..34853d5dfda 100644
--- a/arch/arm/mach-sa1100/pm.c
+++ b/arch/arm/mach-sa1100/pm.c
@@ -81,6 +81,7 @@ static int sa11x0_pm_enter(suspend_state_t state)
 	/*
 	 * Ensure not to come back here if it wasn't intended
 	 */
+	RCSR = RCSR_SMR;
 	PSPR = 0;
 
 	/*
diff --git a/arch/arm/mach-shmobile/pm-r8a7790.c b/arch/arm/mach-shmobile/pm-r8a7790.c
index 80e8d95e54d..23b61f170c2 100644
--- a/arch/arm/mach-shmobile/pm-r8a7790.c
+++ b/arch/arm/mach-shmobile/pm-r8a7790.c
@@ -38,7 +38,7 @@ static void __init r8a7790_sysc_init(void)
 	void __iomem *base = rcar_sysc_init(0xe6180000);
 
 	/* enable all interrupt sources, but do not use interrupt handler */
-	iowrite32(0x0131000e, base + SYSCIER);
+	iowrite32(0x013111ef, base + SYSCIER);
 	iowrite32(0, base + SYSCIMR);
 }
 
diff --git a/arch/arm/mach-shmobile/pm-r8a7791.c b/arch/arm/mach-shmobile/pm-r8a7791.c
index 25f107bb365..f7cfb3b7257 100644
--- a/arch/arm/mach-shmobile/pm-r8a7791.c
+++ b/arch/arm/mach-shmobile/pm-r8a7791.c
@@ -33,7 +33,7 @@ static void __init r8a7791_sysc_init(void)
 	void __iomem *base = rcar_sysc_init(0xe6180000);
 
 	/* enable all interrupt sources, but do not use interrupt handler */
-	iowrite32(0x0131000e, base + SYSCIER);
+	iowrite32(0x00111003, base + SYSCIER);
 	iowrite32(0, base + SYSCIMR);
 }
 
diff --git a/arch/arm/mach-shmobile/setup-sh73a0.c b/arch/arm/mach-shmobile/setup-sh73a0.c
index 328657d011d..1ba4f635784 100644
--- a/arch/arm/mach-shmobile/setup-sh73a0.c
+++ b/arch/arm/mach-shmobile/setup-sh73a0.c
@@ -598,6 +598,7 @@ static struct platform_device ipmmu_device = {
 
 static struct renesas_intc_irqpin_config irqpin0_platform_data = {
 	.irq_base = irq_pin(0), /* IRQ0 -> IRQ7 */
+	.control_parent = true,
 };
 
 static struct resource irqpin0_resources[] = {
@@ -659,6 +660,7 @@ static struct platform_device irqpin1_device = {
 
 static struct renesas_intc_irqpin_config irqpin2_platform_data = {
 	.irq_base = irq_pin(16), /* IRQ16 -> IRQ23 */
+	.control_parent = true,
 };
 
 static struct resource irqpin2_resources[] = {
@@ -689,6 +691,7 @@ static struct platform_device irqpin2_device = {
 
 static struct renesas_intc_irqpin_config irqpin3_platform_data = {
 	.irq_base = irq_pin(24), /* IRQ24 -> IRQ31 */
+	.control_parent = true,
 };
 
 static struct resource irqpin3_resources[] = {
diff --git a/arch/arm/mach-sunxi/Kconfig b/arch/arm/mach-sunxi/Kconfig
index 1aaa1e15ef7..d5fd511c147 100644
--- a/arch/arm/mach-sunxi/Kconfig
+++ b/arch/arm/mach-sunxi/Kconfig
@@ -1,10 +1,12 @@
 menuconfig ARCH_SUNXI
 	bool "Allwinner SoCs" if ARCH_MULTI_V7
 	select ARCH_REQUIRE_GPIOLIB
+	select ARCH_HAS_RESET_CONTROLLER
 	select CLKSRC_MMIO
 	select GENERIC_IRQ_CHIP
 	select PINCTRL
 	select SUN4I_TIMER
+	select RESET_CONTROLLER
 
 if ARCH_SUNXI
 
@@ -20,10 +22,8 @@ config MACH_SUN5I
 config MACH_SUN6I
 	bool "Allwinner A31 (sun6i) SoCs support"
 	default ARCH_SUNXI
-	select ARCH_HAS_RESET_CONTROLLER
 	select ARM_GIC
 	select MFD_SUN6I_PRCM
-	select RESET_CONTROLLER
 	select SUN5I_HSTIMER
 
 config MACH_SUN7I
@@ -37,9 +37,7 @@ config MACH_SUN7I
 config MACH_SUN8I
 	bool "Allwinner A23 (sun8i) SoCs support"
 	default ARCH_SUNXI
-	select ARCH_HAS_RESET_CONTROLLER
 	select ARM_GIC
 	select MFD_SUN6I_PRCM
-	select RESET_CONTROLLER
 
 endif
diff --git a/arch/arm/mach-tegra/cpuidle-tegra20.c b/arch/arm/mach-tegra/cpuidle-tegra20.c
index b30bf5cba65..f209e9c507e 100644
--- a/arch/arm/mach-tegra/cpuidle-tegra20.c
+++ b/arch/arm/mach-tegra/cpuidle-tegra20.c
@@ -35,6 +35,7 @@
 #include "iomap.h"
 #include "irq.h"
 #include "pm.h"
+#include "reset.h"
 #include "sleep.h"
 
 #ifdef CONFIG_PM_SLEEP
@@ -72,15 +73,13 @@ static struct cpuidle_driver tegra_idle_driver = {
 
 #ifdef CONFIG_PM_SLEEP
 #ifdef CONFIG_SMP
-static void __iomem *pmc = IO_ADDRESS(TEGRA_PMC_BASE);
-
 static int tegra20_reset_sleeping_cpu_1(void)
 {
 	int ret = 0;
 
 	tegra_pen_lock();
 
-	if (readl(pmc + PMC_SCRATCH41) == CPU_RESETTABLE)
+	if (readb(tegra20_cpu1_resettable_status) == CPU_RESETTABLE)
 		tegra20_cpu_shutdown(1);
 	else
 		ret = -EINVAL;
diff --git a/arch/arm/mach-tegra/reset-handler.S b/arch/arm/mach-tegra/reset-handler.S
index 7b2baab0f0b..e3070fdab80 100644
--- a/arch/arm/mach-tegra/reset-handler.S
+++ b/arch/arm/mach-tegra/reset-handler.S
@@ -51,6 +51,7 @@ ENTRY(tegra_resume)
  THUMB(	it	ne )
 	bne	cpu_resume			@ no
 
+	tegra_get_soc_id TEGRA_APB_MISC_BASE, r6
 	/* Are we on Tegra20? */
 	cmp	r6, #TEGRA20
 	beq	1f				@ Yes
@@ -168,10 +169,10 @@ after_errata:
 	cmp	r6, #TEGRA20
 	bne	1f
 	/* If not CPU0, don't let CPU0 reset CPU1 now that CPU1 is coming up. */
-	mov32	r5, TEGRA_PMC_BASE
-	mov	r0, #0
+	mov32	r5, TEGRA_IRAM_BASE + TEGRA_IRAM_RESET_HANDLER_OFFSET
+	mov	r0, #CPU_NOT_RESETTABLE
 	cmp	r10, #0
-	strne	r0, [r5, #PMC_SCRATCH41]
+	strneb	r0, [r5, #__tegra20_cpu1_resettable_status_offset]
 1:
 #endif
 
@@ -280,6 +281,10 @@ __tegra_cpu_reset_handler_data:
 	.rept	TEGRA_RESET_DATA_SIZE
 	.long	0
 	.endr
+	.globl	__tegra20_cpu1_resettable_status_offset
+	.equ	__tegra20_cpu1_resettable_status_offset, \
+					. - __tegra_cpu_reset_handler_start
+	.byte	0
 	.align L1_CACHE_SHIFT
 
 ENTRY(__tegra_cpu_reset_handler_end)
diff --git a/arch/arm/mach-tegra/reset.h b/arch/arm/mach-tegra/reset.h
index 76a93434c6e..29c3dec0126 100644
--- a/arch/arm/mach-tegra/reset.h
+++ b/arch/arm/mach-tegra/reset.h
@@ -35,6 +35,7 @@ extern unsigned long __tegra_cpu_reset_handler_data[TEGRA_RESET_DATA_SIZE];
 
 void __tegra_cpu_reset_handler_start(void);
 void __tegra_cpu_reset_handler(void);
+void __tegra20_cpu1_resettable_status_offset(void);
 void __tegra_cpu_reset_handler_end(void);
 void tegra_secondary_startup(void);
 
@@ -47,6 +48,9 @@ void tegra_secondary_startup(void);
 	(IO_ADDRESS(TEGRA_IRAM_BASE + TEGRA_IRAM_RESET_HANDLER_OFFSET + \
 	((u32)&__tegra_cpu_reset_handler_data[TEGRA_RESET_MASK_LP2] - \
 	 (u32)__tegra_cpu_reset_handler_start)))
+#define tegra20_cpu1_resettable_status \
+	(IO_ADDRESS(TEGRA_IRAM_BASE + TEGRA_IRAM_RESET_HANDLER_OFFSET + \
+	 (u32)__tegra20_cpu1_resettable_status_offset))
 #endif
 
 #define tegra_cpu_reset_handler_offset \
diff --git a/arch/arm/mach-tegra/sleep-tegra20.S b/arch/arm/mach-tegra/sleep-tegra20.S
index be4bc5f853f..e6b684e1432 100644
--- a/arch/arm/mach-tegra/sleep-tegra20.S
+++ b/arch/arm/mach-tegra/sleep-tegra20.S
@@ -97,9 +97,10 @@ ENDPROC(tegra20_hotplug_shutdown)
 ENTRY(tegra20_cpu_shutdown)
 	cmp	r0, #0
 	reteq	lr			@ must not be called for CPU 0
-	mov32	r1, TEGRA_PMC_VIRT + PMC_SCRATCH41
+	mov32	r1, TEGRA_IRAM_RESET_BASE_VIRT
+	ldr	r2, =__tegra20_cpu1_resettable_status_offset
 	mov	r12, #CPU_RESETTABLE
-	str	r12, [r1]
+	strb	r12, [r1, r2]
 
 	cpu_to_halt_reg r1, r0
 	ldr	r3, =TEGRA_FLOW_CTRL_VIRT
@@ -182,38 +183,41 @@ ENDPROC(tegra_pen_unlock)
 /*
  * tegra20_cpu_clear_resettable(void)
  *
- * Called to clear the "resettable soon" flag in PMC_SCRATCH41 when
+ * Called to clear the "resettable soon" flag in IRAM variable when
  * it is expected that the secondary CPU will be idle soon.
  */
 ENTRY(tegra20_cpu_clear_resettable)
-	mov32	r1, TEGRA_PMC_VIRT + PMC_SCRATCH41
+	mov32	r1, TEGRA_IRAM_RESET_BASE_VIRT
+	ldr	r2, =__tegra20_cpu1_resettable_status_offset
 	mov	r12, #CPU_NOT_RESETTABLE
-	str	r12, [r1]
+	strb	r12, [r1, r2]
 	ret	lr
 ENDPROC(tegra20_cpu_clear_resettable)
 
 /*
  * tegra20_cpu_set_resettable_soon(void)
  *
- * Called to set the "resettable soon" flag in PMC_SCRATCH41 when
+ * Called to set the "resettable soon" flag in IRAM variable when
  * it is expected that the secondary CPU will be idle soon.
  */
 ENTRY(tegra20_cpu_set_resettable_soon)
-	mov32	r1, TEGRA_PMC_VIRT + PMC_SCRATCH41
+	mov32	r1, TEGRA_IRAM_RESET_BASE_VIRT
+	ldr	r2, =__tegra20_cpu1_resettable_status_offset
 	mov	r12, #CPU_RESETTABLE_SOON
-	str	r12, [r1]
+	strb	r12, [r1, r2]
 	ret	lr
 ENDPROC(tegra20_cpu_set_resettable_soon)
 
 /*
  * tegra20_cpu_is_resettable_soon(void)
  *
- * Returns true if the "resettable soon" flag in PMC_SCRATCH41 has been
+ * Returns true if the "resettable soon" flag in IRAM variable has been
  * set because it is expected that the secondary CPU will be idle soon.
  */
 ENTRY(tegra20_cpu_is_resettable_soon)
-	mov32	r1, TEGRA_PMC_VIRT + PMC_SCRATCH41
-	ldr	r12, [r1]
+	mov32	r1, TEGRA_IRAM_RESET_BASE_VIRT
+	ldr	r2, =__tegra20_cpu1_resettable_status_offset
+	ldrb	r12, [r1, r2]
 	cmp	r12, #CPU_RESETTABLE_SOON
 	moveq	r0, #1
 	movne	r0, #0
@@ -256,9 +260,10 @@ ENTRY(tegra20_sleep_cpu_secondary_finish)
 	mov	r0, #TEGRA_FLUSH_CACHE_LOUIS
 	bl	tegra_disable_clean_inv_dcache
 
-	mov32	r0, TEGRA_PMC_VIRT + PMC_SCRATCH41
+	mov32	r0, TEGRA_IRAM_RESET_BASE_VIRT
+	ldr	r4, =__tegra20_cpu1_resettable_status_offset
 	mov	r3, #CPU_RESETTABLE
-	str	r3, [r0]
+	strb	r3, [r0, r4]
 
 	bl	tegra_cpu_do_idle
 
@@ -274,10 +279,10 @@ ENTRY(tegra20_sleep_cpu_secondary_finish)
 
 	bl	tegra_pen_lock
 
-	mov32	r3, TEGRA_PMC_VIRT
-	add	r0, r3, #PMC_SCRATCH41
+	mov32	r0, TEGRA_IRAM_RESET_BASE_VIRT
+	ldr	r4, =__tegra20_cpu1_resettable_status_offset
 	mov	r3, #CPU_NOT_RESETTABLE
-	str	r3, [r0]
+	strb	r3, [r0, r4]
 
 	bl	tegra_pen_unlock
 
diff --git a/arch/arm/mach-tegra/sleep.h b/arch/arm/mach-tegra/sleep.h
index 92d46ec1361..0d59360d891 100644
--- a/arch/arm/mach-tegra/sleep.h
+++ b/arch/arm/mach-tegra/sleep.h
@@ -18,6 +18,7 @@
 #define __MACH_TEGRA_SLEEP_H
 
 #include "iomap.h"
+#include "irammap.h"
 
 #define TEGRA_ARM_PERIF_VIRT (TEGRA_ARM_PERIF_BASE - IO_CPU_PHYS \
 					+ IO_CPU_VIRT)
@@ -29,6 +30,9 @@
 					+ IO_APB_VIRT)
 #define TEGRA_PMC_VIRT	(TEGRA_PMC_BASE - IO_APB_PHYS + IO_APB_VIRT)
 
+#define TEGRA_IRAM_RESET_BASE_VIRT (IO_IRAM_VIRT + \
+				TEGRA_IRAM_RESET_HANDLER_OFFSET)
+
 /* PMC_SCRATCH37-39 and 41 are used for tegra_pen_lock and idle */
 #define PMC_SCRATCH37	0x130
 #define PMC_SCRATCH38	0x134
diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
index b2cfba16c4e..18865136156 100644
--- a/arch/arm/mach-vexpress/Kconfig
+++ b/arch/arm/mach-vexpress/Kconfig
@@ -75,6 +75,7 @@ config ARCH_VEXPRESS_TC2_PM
 	depends on MCPM
 	select ARM_CCI
 	select ARCH_VEXPRESS_SPC
+	select ARM_CPU_SUSPEND
 	help
 	  Support for CPU and cluster power management on Versatile Express
 	  with a TC2 (A15x2 A7x3) big.LITTLE core tile.
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index 24659952c27..11da0f50a1f 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -270,6 +270,11 @@ v6_dma_clean_range:
  *	- end     - virtual end address of region
  */
 ENTRY(v6_dma_flush_range)
+#ifdef CONFIG_CACHE_FLUSH_RANGE_LIMIT
+	sub	r2, r1, r0
+	cmp	r2, #CONFIG_CACHE_FLUSH_RANGE_LIMIT
+	bhi	v6_dma_flush_dcache_all
+#endif
 #ifdef CONFIG_DMA_CACHE_RWFO
 	ldrb	r2, [r0]		@ read for ownership
 	strb	r2, [r0]		@ write for ownership
@@ -292,6 +297,18 @@ ENTRY(v6_dma_flush_range)
 	mcr	p15, 0, r0, c7, c10, 4		@ drain write buffer
 	ret	lr
 
+#ifdef CONFIG_CACHE_FLUSH_RANGE_LIMIT
+v6_dma_flush_dcache_all:
+	mov	r0, #0
+#ifdef HARVARD_CACHE
+	mcr	p15, 0, r0, c7, c14, 0		@ D cache clean+invalidate
+#else
+	mcr	p15, 0, r0, c7, c15, 0		@ Cache clean+invalidate
+#endif
+	mcr	p15, 0, r0, c7, c10, 4		@ drain write buffer
+	mov	pc, lr
+#endif
+
 /*
  *	dma_map_area(start, size, dir)
  *	- start	- kernel virtual start address
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 6eb97b3a748..4370933f16c 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -144,21 +144,17 @@ static void flush_context(unsigned int cpu)
 	/* Update the list of reserved ASIDs and the ASID bitmap. */
 	bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
 	for_each_possible_cpu(i) {
-		if (i == cpu) {
-			asid = 0;
-		} else {
-			asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
-			/*
-			 * If this CPU has already been through a
-			 * rollover, but hasn't run another task in
-			 * the meantime, we must preserve its reserved
-			 * ASID, as this is the only trace we have of
-			 * the process it is still running.
-			 */
-			if (asid == 0)
-				asid = per_cpu(reserved_asids, i);
-			__set_bit(asid & ~ASID_MASK, asid_map);
-		}
+		asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
+		/*
+		 * If this CPU has already been through a
+		 * rollover, but hasn't run another task in
+		 * the meantime, we must preserve its reserved
+		 * ASID, as this is the only trace we have of
+		 * the process it is still running.
+		 */
+		if (asid == 0)
+			asid = per_cpu(reserved_asids, i);
+		__set_bit(asid & ~ASID_MASK, asid_map);
 		per_cpu(reserved_asids, i) = asid;
 	}
 
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index eb8830a4c5e..b784579545e 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -274,10 +274,10 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 		local_irq_enable();
 
 	/*
-	 * If we're in an interrupt or have no user
+	 * If we're in an interrupt, or have no irqs, or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (in_atomic() || irqs_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))
diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c
index 66781bf3407..c7241241509 100644
--- a/arch/arm/mm/hugetlbpage.c
+++ b/arch/arm/mm/hugetlbpage.c
@@ -36,12 +36,6 @@
  * of type casting from pmd_t * to pte_t *.
  */
 
-struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
-			      int write)
-{
-	return ERR_PTR(-EINVAL);
-}
-
 int pud_huge(pud_t pud)
 {
 	return 0;
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 9f98cec7fe1..fb9d305c874 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1118,22 +1118,22 @@ void __init sanity_check_meminfo(void)
 			}
 
 			/*
-			 * Find the first non-section-aligned page, and point
+			 * Find the first non-pmd-aligned page, and point
 			 * memblock_limit at it. This relies on rounding the
-			 * limit down to be section-aligned, which happens at
-			 * the end of this function.
+			 * limit down to be pmd-aligned, which happens at the
+			 * end of this function.
 			 *
 			 * With this algorithm, the start or end of almost any
-			 * bank can be non-section-aligned. The only exception
-			 * is that the start of the bank 0 must be section-
+			 * bank can be non-pmd-aligned. The only exception is
+			 * that the start of the bank 0 must be section-
 			 * aligned, since otherwise memory would need to be
 			 * allocated when mapping the start of bank 0, which
 			 * occurs before any free memory is mapped.
 			 */
 			if (!memblock_limit) {
-				if (!IS_ALIGNED(block_start, SECTION_SIZE))
+				if (!IS_ALIGNED(block_start, PMD_SIZE))
 					memblock_limit = block_start;
-				else if (!IS_ALIGNED(block_end, SECTION_SIZE))
+				else if (!IS_ALIGNED(block_end, PMD_SIZE))
 					memblock_limit = arm_lowmem_limit;
 			}
 
@@ -1143,12 +1143,12 @@ void __init sanity_check_meminfo(void)
 	high_memory = __va(arm_lowmem_limit - 1) + 1;
 
 	/*
-	 * Round the memblock limit down to a section size.  This
+	 * Round the memblock limit down to a pmd size.  This
 	 * helps to ensure that we will allocate memory from the
-	 * last full section, which should be mapped.
+	 * last full pmd, which should be mapped.
 	 */
 	if (memblock_limit)
-		memblock_limit = round_down(memblock_limit, SECTION_SIZE);
+		memblock_limit = round_down(memblock_limit, PMD_SIZE);
 	if (!memblock_limit)
 		memblock_limit = arm_lowmem_limit;
 
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index e1268f90502..f412b53ed26 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -449,10 +449,21 @@ static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx)
 		return;
 	}
 #endif
-	if (rm != ARM_R0)
-		emit(ARM_MOV_R(ARM_R0, rm), ctx);
+
+	/*
+	 * For BPF_ALU | BPF_DIV | BPF_K instructions, rm is ARM_R4
+	 * (r_A) and rn is ARM_R0 (r_scratch) so load rn first into
+	 * ARM_R1 to avoid accidentally overwriting ARM_R0 with rm
+	 * before using it as a source for ARM_R1.
+	 *
+	 * For BPF_ALU | BPF_DIV | BPF_X rm is ARM_R4 (r_A) and rn is
+	 * ARM_R5 (r_X) so there is no particular register overlap
+	 * issues.
+	 */
 	if (rn != ARM_R1)
 		emit(ARM_MOV_R(ARM_R1, rn), ctx);
+	if (rm != ARM_R0)
+		emit(ARM_MOV_R(ARM_R0, rm), ctx);
 
 	ctx->seen |= SEEN_CALL;
 	emit_mov_i(ARM_R3, (u32)jit_udiv, ctx);
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index b0e77de9914..f8a576b1d9b 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -16,6 +16,13 @@
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
+bool xen_arch_need_swiotlb(struct device *dev,
+			   unsigned long pfn,
+			   unsigned long mfn)
+{
+	return (pfn != mfn);
+}
+
 int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 				 unsigned int address_bits,
 				 dma_addr_t *dma_handle)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 9532f8d5857..f462701f929 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -37,6 +37,7 @@ config ARM64
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_BPF_JIT
 	select HAVE_C_RECORDMCOUNT
@@ -88,6 +89,10 @@ config MMU
 config NO_IOPORT_MAP
 	def_bool y if !PCI
 
+config ILLEGAL_POINTER_VALUE
+	hex
+	default 0xdead000000000000
+
 config STACKTRACE_SUPPORT
 	def_bool y
 
@@ -193,6 +198,135 @@ endmenu
 
 menu "Kernel Features"
 
+menu "ARM errata workarounds via the alternatives framework"
+
+config ARM64_ERRATUM_826319
+	bool "Cortex-A53: 826319: System might deadlock if a write cannot complete until read data is accepted"
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 826319 on Cortex-A53 parts up to r0p2 with an AMBA 4 ACE or
+	  AXI master interface and an L2 cache.
+
+	  If a Cortex-A53 uses an AMBA AXI4 ACE interface to other processors
+	  and is unable to accept a certain write via this interface, it will
+	  not progress on read data presented on the read data channel and the
+	  system can deadlock.
+
+	  The workaround promotes data cache clean instructions to
+	  data cache clean-and-invalidate.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_827319
+	bool "Cortex-A53: 827319: Data cache clean instructions might cause overlapping transactions to the interconnect"
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 827319 on Cortex-A53 parts up to r0p2 with an AMBA 5 CHI
+	  master interface and an L2 cache.
+
+	  Under certain conditions this erratum can cause a clean line eviction
+	  to occur at the same time as another transaction to the same address
+	  on the AMBA 5 CHI interface, which can cause data corruption if the
+	  interconnect reorders the two transactions.
+
+	  The workaround promotes data cache clean instructions to
+	  data cache clean-and-invalidate.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_824069
+	bool "Cortex-A53: 824069: Cache line might not be marked as clean after a CleanShared snoop"
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 824069 on Cortex-A53 parts up to r0p2 when it is connected
+	  to a coherent interconnect.
+
+	  If a Cortex-A53 processor is executing a store or prefetch for
+	  write instruction at the same time as a processor in another
+	  cluster is executing a cache maintenance operation to the same
+	  address, then this erratum might cause a clean cache line to be
+	  incorrectly marked as dirty.
+
+	  The workaround promotes data cache clean instructions to
+	  data cache clean-and-invalidate.
+	  Please note that this option does not necessarily enable the
+	  workaround, as it depends on the alternative framework, which will
+	  only patch the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_819472
+	bool "Cortex-A53: 819472: Store exclusive instructions might cause data corruption"
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 819472 on Cortex-A53 parts up to r0p1 with an L2 cache
+	  present when it is connected to a coherent interconnect.
+
+	  If the processor is executing a load and store exclusive sequence at
+	  the same time as a processor in another cluster is executing a cache
+	  maintenance operation to the same address, then this erratum might
+	  cause data corruption.
+
+	  The workaround promotes data cache clean instructions to
+	  data cache clean-and-invalidate.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_832075
+	bool "Cortex-A57: 832075: possible deadlock on mixing exclusive memory accesses with device loads"
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 832075 on Cortex-A57 parts up to r1p2.
+
+	  Affected Cortex-A57 parts might deadlock when exclusive load/store
+	  instructions to Write-Back memory are mixed with Device loads.
+
+	  The workaround is to promote device loads to use Load-Acquire
+	  semantics.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_845719
+	bool "Cortex-A53: 845719: a load might read incorrect data"
+	depends on COMPAT
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 845719 on Cortex-A53 parts up to r0p4.
+
+	  When running a compat (AArch32) userspace on an affected Cortex-A53
+	  part, a load at EL0 from a virtual address that matches the bottom 32
+	  bits of the virtual address used by a recent load at (AArch64) EL1
+	  might return incorrect data.
+
+	  The workaround is to write the contextidr_el1 register on exception
+	  return to a 32-bit task.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
+endmenu
+
+
 choice
 	prompt "Page size"
 	default ARM64_4K_PAGES
@@ -233,7 +367,6 @@ config ARM64_VA_BITS_42
 
 config ARM64_VA_BITS_48
 	bool "48-bit"
-	depends on !ARM_SMMU
 
 endchoice
 
@@ -284,6 +417,97 @@ config SCHED_SMT
 	  MultiThreading at a cost of slightly increased overhead in some
 	  places. If unsure say N here.
 
+config SCHED_HMP
+	bool "(EXPERIMENTAL) Heterogenous multiprocessor scheduling"
+	depends on SCHED_MC && FAIR_GROUP_SCHED && !SCHED_AUTOGROUP
+	help
+	  Experimental scheduler optimizations for heterogeneous platforms.
+	  Attempts to introspectively select task affinity to optimize power
+	  and performance. Basic support for multiple (>2) cpu types is in place,
+	  but it has only been tested with two types of cpus.
+	  There is currently no support for migration of task groups, hence
+	  !SCHED_AUTOGROUP. Furthermore, normal load-balancing must be disabled
+	  between cpus of different type (DISABLE_CPU_SCHED_DOMAIN_BALANCE).
+
+config SCHED_HMP_PRIO_FILTER
+	bool "(EXPERIMENTAL) Filter HMP migrations by task priority"
+	depends on SCHED_HMP
+	help
+	  Enables task priority based HMP migration filter. Any task with
+	  a NICE value above the threshold will always be on low-power cpus
+	  with less compute capacity.
+
+config SCHED_HMP_PRIO_FILTER_VAL
+	int "NICE priority threshold"
+	default 5
+	depends on SCHED_HMP_PRIO_FILTER
+
+config HMP_FAST_CPU_MASK
+	string "HMP scheduler fast CPU mask"
+	depends on SCHED_HMP
+	help
+          Leave empty to use device tree information.
+	  Specify the cpuids of the fast CPUs in the system as a list string,
+	  e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_SLOW_CPU_MASK
+	string "HMP scheduler slow CPU mask"
+	depends on SCHED_HMP
+	help
+	  Leave empty to use device tree information.
+	  Specify the cpuids of the slow CPUs in the system as a list string,
+	  e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_VARIABLE_SCALE
+	bool "Allows changing the load tracking scale through sysfs"
+	depends on SCHED_HMP
+	help
+	  When turned on, this option exports the thresholds and load average
+	  period value for the load tracking patches through sysfs.
+	  The values can be modified to change the rate of load accumulation
+	  and the thresholds used for HMP migration.
+	  The load_avg_period_ms is the time in ms to reach a load average of
+	  0.5 for an idle task of 0 load average ratio that start a busy loop.
+	  The up_threshold and down_threshold is the value to go to a faster
+	  CPU or to go back to a slower cpu.
+	  The {up,down}_threshold are devided by 1024 before being compared
+	  to the load average.
+	  For examples, with load_avg_period_ms = 128 and up_threshold = 512,
+	  a running task with a load of 0 will be migrated to a bigger CPU after
+	  128ms, because after 128ms its load_avg_ratio is 0.5 and the real
+	  up_threshold is 0.5.
+	  This patch has the same behavior as changing the Y of the load
+	  average computation to
+	        (1002/1024)^(LOAD_AVG_PERIOD/load_avg_period_ms)
+	  but it remove intermadiate overflows in computation.
+
+config HMP_FREQUENCY_INVARIANT_SCALE
+	bool "(EXPERIMENTAL) Frequency-Invariant Tracked Load for HMP"
+	depends on HMP_VARIABLE_SCALE && CPU_FREQ
+	help
+	  Scales the current load contribution in line with the frequency
+	  of the CPU that the task was executed on.
+	  In this version, we use a simple linear scale derived from the
+	  maximum frequency reported by CPUFreq.
+	  Restricting tracked load to be scaled by the CPU's frequency
+	  represents the consumption of possible compute capacity
+	  (rather than consumption of actual instantaneous capacity as
+	  normal) and allows the HMP migration's simple threshold
+	  migration strategy to interact more predictably with CPUFreq's
+	  asynchronous compute capacity changes.
+
+config SCHED_HMP_LITTLE_PACKING
+	bool "Small task packing for HMP"
+	depends on SCHED_HMP
+	default n
+	help
+	  Allows the HMP Scheduler to pack small tasks into CPUs in the
+	  smallest HMP domain.
+	  Controlled by two sysfs files in sys/kernel/hmp.
+	  packing_enable: 1 to enable, 0 to disable packing. Default 1.
+	  packing_limit: runqueue load ratio where a RQ is considered
+	    to be full. Default is NICE_0_LOAD * 9/8.
+
 config NR_CPUS
 	int "Maximum number of CPUs (2-64)"
 	range 2 64
@@ -345,6 +569,19 @@ config ARCH_HAS_CACHE_LINE_SIZE
 
 source "mm/Kconfig"
 
+config SECCOMP
+	bool "Enable seccomp to safely compute untrusted bytecode"
+	---help---
+	  This kernel feature is useful for number crunching applications
+	  that may need to compute untrusted bytecode during their
+	  execution. By using pipes or other transports made available to
+	  the process as file descriptors supporting the read/write
+	  syscalls, it's possible to isolate those applications in
+	  their own address space using seccomp. Once seccomp is
+	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
+	  and the task is only allowed to execute a few safe syscalls
+	  defined by each seccomp mode.
+
 config XEN_DOM0
 	def_bool y
 	depends on XEN
@@ -361,6 +598,74 @@ config FORCE_MAX_ZONEORDER
 	default "14" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)
 	default "11"
 
+menuconfig ARMV8_DEPRECATED
+	bool "Emulate deprecated/obsolete ARMv8 instructions"
+	depends on COMPAT
+	help
+	  Legacy software support may require certain instructions
+	  that have been deprecated or obsoleted in the architecture.
+
+	  Enable this config to enable selective emulation of these
+	  features.
+
+	  If unsure, say Y
+
+if ARMV8_DEPRECATED
+
+config SWP_EMULATION
+	bool "Emulate SWP/SWPB instructions"
+	help
+	  ARMv8 obsoletes the use of A32 SWP/SWPB instructions such that
+	  they are always undefined. Say Y here to enable software
+	  emulation of these instructions for userspace using LDXR/STXR.
+
+	  In some older versions of glibc [<=2.8] SWP is used during futex
+	  trylock() operations with the assumption that the code will not
+	  be preempted. This invalid assumption may be more likely to fail
+	  with SWP emulation enabled, leading to deadlock of the user
+	  application.
+
+	  NOTE: when accessing uncached shared regions, LDXR/STXR rely
+	  on an external transaction monitoring block called a global
+	  monitor to maintain update atomicity. If your system does not
+	  implement a global monitor, this option can cause programs that
+	  perform SWP operations to uncached memory to deadlock.
+
+	  If unsure, say Y
+
+config CP15_BARRIER_EMULATION
+	bool "Emulate CP15 Barrier instructions"
+	help
+	  The CP15 barrier instructions - CP15ISB, CP15DSB, and
+	  CP15DMB - are deprecated in ARMv8 (and ARMv7). It is
+	  strongly recommended to use the ISB, DSB, and DMB
+	  instructions instead.
+
+	  Say Y here to enable software emulation of these
+	  instructions for AArch32 userspace code. When this option is
+	  enabled, CP15 barrier usage is traced which can help
+	  identify software that needs updating.
+
+	  If unsure, say Y
+
+config SETEND_EMULATION
+	bool "Emulate SETEND instruction"
+	help
+	  The SETEND instruction alters the data-endianness of the
+	  AArch32 EL0, and is deprecated in ARMv8.
+
+	  Say Y here to enable software emulation of the instruction
+	  for AArch32 userspace code.
+
+	  Note: All the cpus on the system must have mixed endian support at EL0
+	  for this feature to be enabled. If a new CPU - which doesn't support mixed
+	  endian - is hotplugged in after this feature has been enabled, there could
+	  be unexpected results in the applications.
+
+	  If unsure, say Y
+
+endif
+
 endmenu
 
 menu "Boot options"
@@ -373,6 +678,23 @@ config CMDLINE
 	  entering them here. As a minimum, you should specify the the
 	  root device (e.g. root=/dev/nfs).
 
+choice
+	prompt "Kernel command line type" if CMDLINE != ""
+	default CMDLINE_FROM_BOOTLOADER
+
+config CMDLINE_FROM_BOOTLOADER
+	bool "Use bootloader kernel arguments if available"
+	help
+	  Uses the command-line options passed by the boot loader. If
+	  the boot loader doesn't provide any, the default kernel command
+	  string provided in CMDLINE will be used.
+
+config CMDLINE_EXTEND
+	bool "Extend bootloader kernel arguments"
+	help
+	  The command-line arguments provided by the boot loader will be
+	  appended to the default kernel command string.
+
 config CMDLINE_FORCE
 	bool "Always use the default kernel command string"
 	help
@@ -380,6 +702,7 @@ config CMDLINE_FORCE
 	  loader passes other arguments to the kernel.
 	  This is useful if you cannot or don't want to change the
 	  command-line options your boot loader passes to the kernel.
+endchoice
 
 config EFI_STUB
 	bool
@@ -401,6 +724,21 @@ config EFI
 	  allow the kernel to be booted as an EFI application. This
 	  is only useful on systems that have UEFI firmware.
 
+config BUILD_ARM64_APPENDED_DTB_IMAGE
+	bool "Build a concatenated Image.gz/dtb by default"
+	depends on OF
+	help
+	  Enabling this option will cause a concatenated Image.gz and list of
+	  DTBs to be built by default (instead of a standalone Image.gz.)
+	  The image will built in arch/arm64/boot/Image.gz-dtb
+
+config BUILD_ARM64_APPENDED_DTB_IMAGE_NAMES
+	string "Default dtb names"
+	depends on BUILD_ARM64_APPENDED_DTB_IMAGE
+	help
+	  Space separated list of names of dtbs to append when
+	  building a concatenated Image.gz-dtb.
+
 endmenu
 
 menu "Userspace binary formats"
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index 0a12933e50e..8dd3a551c17 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -54,4 +54,6 @@ config DEBUG_SET_MODULE_RONX
           against certain classes of kernel exploits.
           If in doubt, say "N".
 
+source "drivers/hwtracing/coresight/Kconfig"
+
 endmenu
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 20901ffed18..18daa9f14c2 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -20,6 +20,7 @@ LIBGCC 		:= $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
 KBUILD_DEFCONFIG := defconfig
 
 KBUILD_CFLAGS	+= -mgeneral-regs-only
+KBUILD_CFLAGS	+= -fno-pic
 ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
 KBUILD_CPPFLAGS	+= -mbig-endian
 AS		+= -EB
@@ -54,7 +55,12 @@ libs-y		+= $(LIBGCC)
 libs-$(CONFIG_EFI_STUB) += drivers/firmware/efi/libstub/
 
 # Default target when executing plain make
+ifeq ($(CONFIG_BUILD_ARM64_APPENDED_DTB_IMAGE),y)
+KBUILD_IMAGE	:= Image.gz-dtb
+else
 KBUILD_IMAGE	:= Image.gz
+endif
+
 KBUILD_DTBS	:= dtbs
 
 all:	$(KBUILD_IMAGE) $(KBUILD_DTBS)
@@ -70,8 +76,16 @@ zinstall install: vmlinux
 %.dtb: scripts
 	$(Q)$(MAKE) $(build)=$(boot)/dts $(boot)/dts/$@
 
-dtbs: scripts
-	$(Q)$(MAKE) $(build)=$(boot)/dts dtbs
+PHONY += dtbs dtbs_install
+
+dtbs: prepare scripts
+	$(Q)$(MAKE) $(build)=$(boot)/dts
+
+dtbs_install:
+	$(Q)$(MAKE) $(dtbinst)=$(boot)/dts
+
+Image.gz-dtb: vmlinux scripts dtbs
+	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
 PHONY += vdso_install
 vdso_install:
@@ -85,6 +99,7 @@ define archhelp
   echo  '* Image.gz      - Compressed kernel image (arch/$(ARCH)/boot/Image.gz)'
   echo  '  Image         - Uncompressed kernel image (arch/$(ARCH)/boot/Image)'
   echo  '* dtbs          - Build device tree blobs for enabled boards'
+  echo  '  dtbs_install  - Install dtbs to $(INSTALL_DTBS_PATH)'
   echo  '  install       - Install uncompressed kernel'
   echo  '  zinstall      - Install compressed kernel'
   echo  '                  Install using (your) ~/bin/installkernel or'
diff --git a/arch/arm64/boot/.gitignore b/arch/arm64/boot/.gitignore
index 8dab0bb6ae6..eb3551131b1 100644
--- a/arch/arm64/boot/.gitignore
+++ b/arch/arm64/boot/.gitignore
@@ -1,2 +1,3 @@
 Image
 Image.gz
+Image.gz-dtb
diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile
index 5a0e3ab854a..71f513face1 100644
--- a/arch/arm64/boot/Makefile
+++ b/arch/arm64/boot/Makefile
@@ -14,14 +14,27 @@
 # Based on the ia64 boot/Makefile.
 #
 
+include $(srctree)/arch/arm64/boot/dts/Makefile
+
 targets := Image Image.gz
 
+DTB_NAMES := $(subst $\",,$(CONFIG_BUILD_ARM64_APPENDED_DTB_IMAGE_NAMES))
+ifneq ($(DTB_NAMES),)
+DTB_LIST := $(addsuffix .dtb,$(DTB_NAMES))
+DTB_OBJS := $(addprefix $(obj)/dts/,$(DTB_LIST))
+else
+DTB_OBJS := $(shell find $(obj)/dts/ -name \*.dtb)
+endif
+
 $(obj)/Image: vmlinux FORCE
 	$(call if_changed,objcopy)
 
 $(obj)/Image.gz: $(obj)/Image FORCE
 	$(call if_changed,gzip)
 
+$(obj)/Image.gz-dtb: $(obj)/Image.gz $(DTB_OBJS) FORCE
+	$(call if_changed,cat)
+
 install: $(obj)/Image
 	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
 	$(obj)/Image System.map "$(INSTALL_PATH)"
diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile
index f8001a62029..68d25679520 100644
--- a/arch/arm64/boot/dts/Makefile
+++ b/arch/arm64/boot/dts/Makefile
@@ -1,10 +1,6 @@
-dtb-$(CONFIG_ARCH_THUNDER) += thunder-88xx.dtb
-dtb-$(CONFIG_ARCH_VEXPRESS) += rtsm_ve-aemv8a.dtb foundation-v8.dtb
-dtb-$(CONFIG_ARCH_XGENE) += apm-mustang.dtb
+dts-dirs += apm
+dts-dirs += arm
+dts-dirs += cavium
 
-targets += dtbs
-targets += $(dtb-y)
-
-dtbs: $(addprefix $(obj)/, $(dtb-y))
-
-clean-files := *.dtb
+always		:= $(dtb-y)
+subdir-y	:= $(dts-dirs)
diff --git a/arch/arm64/boot/dts/apm/Makefile b/arch/arm64/boot/dts/apm/Makefile
new file mode 100644
index 00000000000..a2afabbc171
--- /dev/null
+++ b/arch/arm64/boot/dts/apm/Makefile
@@ -0,0 +1,5 @@
+dtb-$(CONFIG_ARCH_XGENE) += apm-mustang.dtb
+
+always		:= $(dtb-y)
+subdir-y	:= $(dts-dirs)
+clean-files	:= *.dtb
diff --git a/arch/arm64/boot/dts/apm-mustang.dts b/arch/arm64/boot/dts/apm/apm-mustang.dts
index 2e25de0800b..2e25de0800b 100644
--- a/arch/arm64/boot/dts/apm-mustang.dts
+++ b/arch/arm64/boot/dts/apm/apm-mustang.dts
diff --git a/arch/arm64/boot/dts/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi
index f1ad9c2ab2e..f1ad9c2ab2e 100644
--- a/arch/arm64/boot/dts/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi
diff --git a/arch/arm64/boot/dts/arm/Makefile b/arch/arm64/boot/dts/arm/Makefile
new file mode 100644
index 00000000000..22731a4eeda
--- /dev/null
+++ b/arch/arm64/boot/dts/arm/Makefile
@@ -0,0 +1,7 @@
+dtb-$(CONFIG_ARCH_VEXPRESS) += fvp-base-gicv2-psci.dtb
+dtb-$(CONFIG_ARCH_VEXPRESS) += fvp-foundation-gicv2-psci.dtb
+dtb-$(CONFIG_ARCH_VEXPRESS) += juno.dtb juno-r1.dtb
+
+always		:= $(dtb-y)
+subdir-y	:= $(dts-dirs)
+clean-files	:= *.dtb
diff --git a/arch/arm64/boot/dts/arm/fvp-base-gicv2-psci.dts b/arch/arm64/boot/dts/arm/fvp-base-gicv2-psci.dts
new file mode 100644
index 00000000000..8eb4057e1a4
--- /dev/null
+++ b/arch/arm64/boot/dts/arm/fvp-base-gicv2-psci.dts
@@ -0,0 +1,298 @@
+/*
+ * Copyright (c) 2013-2014, ARM Limited and Contributors. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * Redistributions of source code must retain the above copyright notice, this
+ * list of conditions and the following disclaimer.
+ *
+ * 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.
+ *
+ * Neither the name of ARM 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 THE COPYRIGHT HOLDER 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.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/memreserve/ 0x80000000 0x00010000;
+
+/ {
+};
+
+/ {
+	model = "FVP Base";
+	compatible = "arm,fvp-base", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	psci {
+		compatible = "arm,psci-1.0", "arm,psci-0.2", "arm,psci";
+		method = "smc";
+		cpu_suspend = <0xc4000001>;
+		cpu_off = <0x84000002>;
+		cpu_on = <0xc4000003>;
+		sys_poweroff = <0x84000008>;
+		sys_reset = <0x84000009>;
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&CPU0>;
+				};
+				core1 {
+					cpu = <&CPU1>;
+				};
+				core2 {
+					cpu = <&CPU2>;
+				};
+				core3 {
+					cpu = <&CPU3>;
+				};
+			};
+
+			cluster1 {
+				core0 {
+					cpu = <&CPU4>;
+				};
+				core1 {
+					cpu = <&CPU5>;
+				};
+				core2 {
+					cpu = <&CPU6>;
+				};
+				core3 {
+					cpu = <&CPU7>;
+				};
+			};
+		};
+
+		idle-states {
+			entry-method = "arm,psci";
+
+			CPU_SLEEP_0: cpu-sleep-0 {
+				compatible = "arm,idle-state";
+				local-timer-stop;
+				arm,psci-suspend-param = <0x0010000>;
+				entry-latency-us = <40>;
+				exit-latency-us = <100>;
+				min-residency-us = <150>;
+			};
+
+			CLUSTER_SLEEP_0: cluster-sleep-0 {
+				compatible = "arm,idle-state";
+				local-timer-stop;
+				arm,psci-suspend-param = <0x1010000>;
+				entry-latency-us = <500>;
+				exit-latency-us = <1000>;
+				min-residency-us = <2500>;
+			};
+		};
+
+		CPU0:cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,armv8";
+			reg = <0x0 0x0>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		};
+
+		CPU1:cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,armv8";
+			reg = <0x0 0x1>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		};
+
+		CPU2:cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,armv8";
+			reg = <0x0 0x2>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		};
+
+		CPU3:cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,armv8";
+			reg = <0x0 0x3>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		};
+
+		CPU4:cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,armv8";
+			reg = <0x0 0x100>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		};
+
+		CPU5:cpu@101 {
+			device_type = "cpu";
+			compatible = "arm,armv8";
+			reg = <0x0 0x101>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		};
+
+		CPU6:cpu@102 {
+			device_type = "cpu";
+			compatible = "arm,armv8";
+			reg = <0x0 0x102>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		};
+
+		CPU7:cpu@103 {
+			device_type = "cpu";
+			compatible = "arm,armv8";
+			reg = <0x0 0x103>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x00000000 0x80000000 0 0x7F000000>,
+		      <0x00000008 0x80000000 0 0x80000000>;
+	};
+
+	gic: interrupt-controller@2f000000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0x0 0x2f000000 0 0x10000>,
+		      <0x0 0x2c000000 0 0x2000>,
+		      <0x0 0x2c010000 0 0x2000>,
+		      <0x0 0x2c02F000 0 0x2000>;
+		interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_HIGH)>;
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>;
+		clock-frequency = <100000000>;
+	};
+
+	timer@2a810000 {
+			compatible = "arm,armv7-timer-mem";
+			reg = <0x0 0x2a810000 0x0 0x10000>;
+			clock-frequency = <100000000>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+			frame@2a830000 {
+				frame-number = <1>;
+				interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
+				reg = <0x0 0x2a830000 0x0 0x10000>;
+			};
+	};
+
+	pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <GIC_SPI 60 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 61 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
diff --git a/arch/arm64/boot/dts/arm/fvp-foundation-gicv2-psci.dts b/arch/arm64/boot/dts/arm/fvp-foundation-gicv2-psci.dts
new file mode 100644
index 00000000000..6e1ce79a87c
--- /dev/null
+++ b/arch/arm64/boot/dts/arm/fvp-foundation-gicv2-psci.dts
@@ -0,0 +1,51 @@
+/* Foundation model is Base model with bits removed */
+
+#include "fvp-base-gicv2-psci.dts"
+
+&CPU4 {
+	status = "disabled";
+};
+
+&CPU5 {
+	status = "disabled";
+};
+
+&CPU6 {
+	status = "disabled";
+};
+
+&CPU7 {
+	status = "disabled";
+};
+
+&flash {
+	status = "disabled";
+};
+
+&v2m_video_ram {
+	status = "disabled";
+};
+
+&aaci {
+	status = "disabled";
+};
+
+&mmci {
+	status = "disabled";
+};
+
+&kmi0 {
+	status = "disabled";
+};
+
+&kmi1 {
+	status = "disabled";
+};
+
+&clcd {
+	status = "disabled";
+};
+
+&v2m_oscclk1 {
+	status = "disabled";
+};
diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi
new file mode 100644
index 00000000000..69e7d96d907
--- /dev/null
+++ b/arch/arm64/boot/dts/arm/juno-base.dtsi
@@ -0,0 +1,218 @@
+	/*
+	 *  Devices shared by all Juno boards
+	 */
+
+	memtimer: timer@2a810000 {
+		compatible = "arm,armv7-timer-mem";
+		reg = <0x0 0x2a810000 0x0 0x10000>;
+		arm,cnttidr = <0x1>;
+		clock-frequency = <50000000>;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+		frame@2a830000 {
+			frame-number = <1>;
+			interrupts = <0 60 4>;
+			reg = <0x0 0x2a830000 0x0 0x10000>;
+		};
+	};
+
+	mailbox: mhu@2b1f0000 {
+		compatible = "arm,mhu", "arm,primecell";
+		reg = <0x0 0x2b1f0000 0x0 0x1000>;
+		interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "mhu_lpri_rx",
+				  "mhu_hpri_rx";
+		#mbox-cells = <1>;
+		clocks = <&soc_refclk100mhz>;
+		clock-names = "apb_pclk";
+	};
+
+	gic: interrupt-controller@2c010000 {
+		compatible = "arm,gic-400", "arm,cortex-a15-gic";
+		reg = <0x0 0x2c010000 0 0x1000>,
+		      <0x0 0x2c02f000 0 0x2000>,
+		      <0x0 0x2c04f000 0 0x2000>,
+		      <0x0 0x2c06f000 0 0x2000>;
+		#address-cells = <2>;
+		#interrupt-cells = <3>;
+		#size-cells = <2>;
+		interrupt-controller;
+		interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(6) | IRQ_TYPE_LEVEL_HIGH)>;
+		ranges = <0 0 0 0x2c1c0000 0 0x40000>;
+		v2m_0: v2m@0 {
+			compatible = "arm,gic-v2m-frame";
+			msi-controller;
+			reg = <0 0 0 0x1000>;
+		};
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(6) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(6) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(6) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(6) | IRQ_TYPE_LEVEL_LOW)>;
+	};
+
+	sram: sram@2e000000 {
+		compatible = "arm,juno-sram-ns", "mmio-sram";
+		reg = <0x0 0x2e000000 0x0 0x8000>;
+
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x0 0x2e000000 0x8000>;
+
+		cpu_scp_lpri: scp-shmem@0 {
+			compatible = "arm,juno-scp-shmem";
+			reg = <0x0 0x200>;
+		};
+
+		cpu_scp_hpri: scp-shmem@200 {
+			compatible = "arm,juno-scp-shmem";
+			reg = <0x200 0x200>;
+		};
+	};
+
+	scpi {
+		compatible = "arm,scpi";
+		mboxes = <&mailbox 1>;
+		shmem = <&cpu_scp_hpri>;
+
+		clocks {
+			compatible = "arm,scpi-clocks";
+
+			scpi_dvfs: scpi_clocks@0 {
+				compatible = "arm,scpi-dvfs-clocks";
+				#clock-cells = <1>;
+				clock-indices = <0>, <1>, <2>;
+				clock-output-names = "atlclk", "aplclk","gpuclk";
+			};
+			scpi_clk: scpi_clocks@3 {
+				compatible = "arm,scpi-variable-clocks";
+				#clock-cells = <1>;
+				clock-indices = <3>, <4>, <5>;
+				clock-output-names = "pxlclk0", "pxlclk1", "i2s_clock";
+			};
+		};
+	};
+
+	/include/ "juno-clocks.dtsi"
+
+	dma@7ff00000 {
+		compatible = "arm,pl330", "arm,primecell";
+		reg = <0x0 0x7ff00000 0 0x1000>;
+		#dma-cells = <1>;
+		#dma-channels = <8>;
+		#dma-requests = <32>;
+		interrupts = <GIC_SPI 88 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 90 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&soc_faxiclk>;
+		clock-names = "apb_pclk";
+	};
+
+	soc_uart0: uart@7ff80000 {
+		compatible = "arm,pl011", "arm,primecell";
+		reg = <0x0 0x7ff80000 0x0 0x1000>;
+		interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&soc_uartclk>, <&soc_refclk100mhz>;
+		clock-names = "uartclk", "apb_pclk";
+	};
+
+	i2c@7ffa0000 {
+		compatible = "snps,designware-i2c";
+		reg = <0x0 0x7ffa0000 0x0 0x1000>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		interrupts = <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>;
+		clock-frequency = <400000>;
+		i2c-sda-hold-time-ns = <500>;
+		clocks = <&soc_smc50mhz>;
+
+		dvi0: dvi-transmitter@70 {
+			compatible = "nxp,tda998x";
+			reg = <0x70>;
+		};
+
+		dvi1: dvi-transmitter@71 {
+			compatible = "nxp,tda998x";
+			reg = <0x71>;
+		};
+	};
+
+	ohci@7ffb0000 {
+		compatible = "generic-ohci";
+		reg = <0x0 0x7ffb0000 0x0 0x10000>;
+		interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&soc_usb48mhz>;
+	};
+
+	ehci@7ffc0000 {
+		compatible = "generic-ehci";
+		reg = <0x0 0x7ffc0000 0x0 0x10000>;
+		interrupts = <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&soc_usb48mhz>;
+	};
+
+	memory-controller@7ffd0000 {
+		compatible = "arm,pl354", "arm,primecell";
+		reg = <0 0x7ffd0000 0 0x1000>;
+		interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		/* last 16MB of the first memory area is reserved for secure world use by firmware */
+		reg = <0x00000000 0x80000000 0x0 0x7f000000>,
+		      <0x00000008 0x80000000 0x1 0x80000000>;
+	};
+
+	gpu: gpu@0x2d000000 {
+		compatible = "arm,malit6xx", "arm,mali";
+		#cooling-cells = <2>; /* min followed by max */
+		reg = <0x0 0x2d000000 0x0 0x4000>;
+		interrupts = <0 33 4>, <0 34 4>, <0 32 4>;
+		interrupt-names = "JOB", "MMU", "GPU";
+		clocks = <&scpi_dvfs 2>;
+		clock-names = "clk_mali";
+	};
+
+	smb {
+		compatible = "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 15>;
+		interrupt-map = <0 0  0 &gic 0 0 0  68 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  1 &gic 0 0 0  69 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  2 &gic 0 0 0  70 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  3 &gic 0 0 0 160 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  4 &gic 0 0 0 161 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  5 &gic 0 0 0 162 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  6 &gic 0 0 0 163 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  7 &gic 0 0 0 164 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  8 &gic 0 0 0 165 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  9 &gic 0 0 0 166 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 10 &gic 0 0 0 167 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 11 &gic 0 0 0 168 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 12 &gic 0 0 0 169 IRQ_TYPE_LEVEL_HIGH>;
+
+		/include/ "juno-motherboard.dtsi"
+	};
diff --git a/arch/arm64/boot/dts/arm/juno-clocks.dtsi b/arch/arm64/boot/dts/arm/juno-clocks.dtsi
new file mode 100644
index 00000000000..25352ed943e
--- /dev/null
+++ b/arch/arm64/boot/dts/arm/juno-clocks.dtsi
@@ -0,0 +1,44 @@
+/*
+ * ARM Juno Platform clocks
+ *
+ * Copyright (c) 2013-2014 ARM Ltd
+ *
+ * This file is licensed under a dual GPLv2 or BSD license.
+ *
+ */
+
+	/* SoC fixed clocks */
+	soc_uartclk: refclk7273800hz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <7273800>;
+		clock-output-names = "juno:uartclk";
+	};
+
+	soc_usb48mhz: clk48mhz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <48000000>;
+		clock-output-names = "clk48mhz";
+	};
+
+	soc_smc50mhz: clk50mhz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <50000000>;
+		clock-output-names = "smc_clk";
+	};
+
+	soc_refclk100mhz: refclk100mhz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <100000000>;
+		clock-output-names = "apb_pclk";
+	};
+
+	soc_faxiclk: refclk400mhz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <400000000>;
+		clock-output-names = "faxi_clk";
+	};
diff --git a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
new file mode 100644
index 00000000000..c138b95a835
--- /dev/null
+++ b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
@@ -0,0 +1,129 @@
+/*
+ * ARM Juno Platform motherboard peripherals
+ *
+ * Copyright (c) 2013-2014 ARM Ltd
+ *
+ * This file is licensed under a dual GPLv2 or BSD license.
+ *
+ */
+
+		mb_clk24mhz: clk24mhz {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <24000000>;
+			clock-output-names = "juno_mb:clk24mhz";
+		};
+
+		mb_clk25mhz: clk25mhz {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <25000000>;
+			clock-output-names = "juno_mb:clk25mhz";
+		};
+
+		motherboard {
+			compatible = "arm,vexpress,v2p-p1", "simple-bus";
+			#address-cells = <2>;  /* SMB chipselect number and offset */
+			#size-cells = <1>;
+			#interrupt-cells = <1>;
+			ranges;
+			model = "V2M-Juno";
+			arm,hbi = <0x252>;
+			arm,vexpress,site = <0>;
+			arm,v2m-memory-map = "rs1";
+
+			mb_fixed_3v3: fixedregulator@0 {
+				compatible = "regulator-fixed";
+				regulator-name = "MCC_SB_3V3";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			ethernet@2,00000000 {
+				compatible = "smsc,lan9118", "smsc,lan9115";
+				reg = <2 0x00000000 0x10000>;
+				interrupts = <3>;
+				phy-mode = "mii";
+				reg-io-width = <4>;
+				smsc,irq-active-high;
+				smsc,irq-push-pull;
+				clocks = <&mb_clk25mhz>;
+				vdd33a-supply = <&mb_fixed_3v3>;
+				vddvario-supply = <&mb_fixed_3v3>;
+			};
+
+			usb@5,00000000 {
+				compatible = "nxp,usb-isp1763";
+				reg = <5 0x00000000 0x20000>;
+				bus-width = <16>;
+				interrupts = <4>;
+			};
+
+			iofpga@3,00000000 {
+				compatible = "arm,amba-bus", "simple-bus";
+				#address-cells = <1>;
+				#size-cells = <1>;
+				ranges = <0 3 0 0x200000>;
+
+				mmci@050000 {
+					compatible = "arm,pl180", "arm,primecell";
+					reg = <0x050000 0x1000>;
+					interrupts = <5>;
+					/* cd-gpios = <&v2m_mmc_gpios 0 0>;
+					wp-gpios = <&v2m_mmc_gpios 1 0>; */
+					max-frequency = <12000000>;
+					vmmc-supply = <&mb_fixed_3v3>;
+					clocks = <&mb_clk24mhz>, <&soc_smc50mhz>;
+					clock-names = "mclk", "apb_pclk";
+				};
+
+				kmi@060000 {
+					compatible = "arm,pl050", "arm,primecell";
+					reg = <0x060000 0x1000>;
+					interrupts = <8>;
+					clocks = <&mb_clk24mhz>, <&soc_smc50mhz>;
+					clock-names = "KMIREFCLK", "apb_pclk";
+				};
+
+				kmi@070000 {
+					compatible = "arm,pl050", "arm,primecell";
+					reg = <0x070000 0x1000>;
+					interrupts = <8>;
+					clocks = <&mb_clk24mhz>, <&soc_smc50mhz>;
+					clock-names = "KMIREFCLK", "apb_pclk";
+				};
+
+				wdt@0f0000 {
+					compatible = "arm,sp805", "arm,primecell";
+					reg = <0x0f0000 0x10000>;
+					interrupts = <7>;
+					clocks = <&mb_clk24mhz>, <&soc_smc50mhz>;
+					clock-names = "wdogclk", "apb_pclk";
+				};
+
+				v2m_timer01: timer@110000 {
+					compatible = "arm,sp804", "arm,primecell";
+					reg = <0x110000 0x10000>;
+					interrupts = <9>;
+					clocks = <&mb_clk24mhz>, <&soc_smc50mhz>;
+					clock-names = "timclken1", "apb_pclk";
+				};
+
+				v2m_timer23: timer@120000 {
+					compatible = "arm,sp804", "arm,primecell";
+					reg = <0x120000 0x10000>;
+					interrupts = <9>;
+					clocks = <&mb_clk24mhz>, <&soc_smc50mhz>;
+					clock-names = "timclken1", "apb_pclk";
+				};
+
+				rtc@170000 {
+					compatible = "arm,pl031", "arm,primecell";
+					reg = <0x170000 0x10000>;
+					interrupts = <0>;
+					clocks = <&soc_smc50mhz>;
+					clock-names = "apb_pclk";
+				};
+			};
+		};
diff --git a/arch/arm64/boot/dts/arm/juno-r1.dts b/arch/arm64/boot/dts/arm/juno-r1.dts
new file mode 100644
index 00000000000..2273cccdeaa
--- /dev/null
+++ b/arch/arm64/boot/dts/arm/juno-r1.dts
@@ -0,0 +1,176 @@
+/*
+ * ARM Ltd. Juno Platform
+ *
+ * Copyright (c) 2015 ARM Ltd.
+ *
+ * This file is licensed under a dual GPLv2 or BSD license.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	model = "ARM Juno development board (r1)";
+	compatible = "arm,juno-r1", "arm,juno", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	aliases {
+		serial0 = &soc_uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	psci {
+		compatible = "arm,psci-0.2";
+		method = "smc";
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&A57_0>;
+				};
+				core1 {
+					cpu = <&A57_1>;
+				};
+			};
+
+			cluster1 {
+				core0 {
+					cpu = <&A53_0>;
+				};
+				core1 {
+					cpu = <&A53_1>;
+				};
+				core2 {
+					cpu = <&A53_2>;
+				};
+				core3 {
+					cpu = <&A53_3>;
+				};
+			};
+		};
+
+		idle-states {
+			entry-method = "arm,psci";
+
+			CPU_SLEEP_0: cpu-sleep-0 {
+				compatible = "arm,idle-state";
+				arm,psci-suspend-param = <0x0010000>;
+				local-timer-stop;
+				entry-latency-us = <100>;
+				exit-latency-us = <250>;
+				min-residency-us = <2000>;
+			};
+
+			CLUSTER_SLEEP_0: cluster-sleep-0 {
+				compatible = "arm,idle-state";
+				arm,psci-suspend-param = <0x1010000>;
+				local-timer-stop;
+				entry-latency-us = <800>;
+				exit-latency-us = <700>;
+				min-residency-us = <2500>;
+			};
+		};
+
+		A57_0: cpu@0 {
+			compatible = "arm,cortex-a57","arm,armv8";
+			reg = <0x0 0x0>;
+			device_type = "cpu";
+			enable-method = "psci";
+			next-level-cache = <&A57_L2>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+			clocks = <&scpi_dvfs 0>;
+		};
+
+		A57_1: cpu@1 {
+			compatible = "arm,cortex-a57","arm,armv8";
+			reg = <0x0 0x1>;
+			device_type = "cpu";
+			enable-method = "psci";
+			next-level-cache = <&A57_L2>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+			clocks = <&scpi_dvfs 0>;
+		};
+
+		A53_0: cpu@100 {
+			compatible = "arm,cortex-a53","arm,armv8";
+			reg = <0x0 0x100>;
+			device_type = "cpu";
+			enable-method = "psci";
+			next-level-cache = <&A53_L2>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+			clocks = <&scpi_dvfs 1>;
+		};
+
+		A53_1: cpu@101 {
+			compatible = "arm,cortex-a53","arm,armv8";
+			reg = <0x0 0x101>;
+			device_type = "cpu";
+			enable-method = "psci";
+			next-level-cache = <&A53_L2>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+			clocks = <&scpi_dvfs 1>;
+		};
+
+		A53_2: cpu@102 {
+			compatible = "arm,cortex-a53","arm,armv8";
+			reg = <0x0 0x102>;
+			device_type = "cpu";
+			enable-method = "psci";
+			next-level-cache = <&A53_L2>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+			clocks = <&scpi_dvfs 1>;
+		};
+
+		A53_3: cpu@103 {
+			compatible = "arm,cortex-a53","arm,armv8";
+			reg = <0x0 0x103>;
+			device_type = "cpu";
+			enable-method = "psci";
+			next-level-cache = <&A53_L2>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+			clocks = <&scpi_dvfs 1>;
+		};
+
+		A57_L2: l2-cache0 {
+			compatible = "cache";
+		};
+
+		A53_L2: l2-cache1 {
+			compatible = "cache";
+		};
+	};
+
+	pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <GIC_SPI 02 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 06 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&A57_0>,
+				     <&A57_1>,
+				     <&A53_0>,
+				     <&A53_1>,
+				     <&A53_2>,
+				     <&A53_3>;
+	};
+
+	#include "juno-base.dtsi"
+
+};
+
+&memtimer {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/arm/juno.dts b/arch/arm64/boot/dts/arm/juno.dts
new file mode 100644
index 00000000000..890a4977e0d
--- /dev/null
+++ b/arch/arm64/boot/dts/arm/juno.dts
@@ -0,0 +1,221 @@
+/*
+ * ARM Ltd. Juno Platform
+ *
+ * Copyright (c) 2013-2014 ARM Ltd.
+ *
+ * This file is licensed under a dual GPLv2 or BSD license.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/thermal/thermal.h>
+
+/ {
+	model = "ARM Juno development board (r0)";
+	compatible = "arm,juno", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	aliases {
+		serial0 = &soc_uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	psci {
+		compatible = "arm,psci-0.2";
+		method = "smc";
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu-map {
+			cluster0: cluster0 {
+				#cooling-cells = <2>; /* min followed by max */
+				core0 {
+					cpu = <&A57_0>;
+				};
+				core1 {
+					cpu = <&A57_1>;
+				};
+			};
+
+			cluster1: cluster1 {
+				#cooling-cells = <2>; /* min followed by max */
+				core0 {
+					cpu = <&A53_0>;
+				};
+				core1 {
+					cpu = <&A53_1>;
+				};
+				core2 {
+					cpu = <&A53_2>;
+				};
+				core3 {
+					cpu = <&A53_3>;
+				};
+			};
+		};
+
+		idle-states {
+			entry-method = "arm,psci";
+
+			CPU_SLEEP_0: cpu-sleep-0 {
+				compatible = "arm,idle-state";
+				arm,psci-suspend-param = <0x0010000>;
+				local-timer-stop;
+				entry-latency-us = <100>;
+				exit-latency-us = <250>;
+				min-residency-us = <2000>;
+			};
+
+			CLUSTER_SLEEP_0: cluster-sleep-0 {
+				compatible = "arm,idle-state";
+				arm,psci-suspend-param = <0x1010000>;
+				local-timer-stop;
+				entry-latency-us = <800>;
+				exit-latency-us = <700>;
+				min-residency-us = <2500>;
+			};
+		};
+
+		A57_0: cpu@0 {
+			compatible = "arm,cortex-a57","arm,armv8";
+			reg = <0x0 0x0>;
+			device_type = "cpu";
+			enable-method = "psci";
+			next-level-cache = <&A57_L2>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+			clocks = <&scpi_dvfs 0>;
+		};
+
+		A57_1: cpu@1 {
+			compatible = "arm,cortex-a57","arm,armv8";
+			reg = <0x0 0x1>;
+			device_type = "cpu";
+			enable-method = "psci";
+			next-level-cache = <&A57_L2>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+			clocks = <&scpi_dvfs 0>;
+		};
+
+		A53_0: cpu@100 {
+			compatible = "arm,cortex-a53","arm,armv8";
+			reg = <0x0 0x100>;
+			device_type = "cpu";
+			enable-method = "psci";
+			next-level-cache = <&A53_L2>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+			clocks = <&scpi_dvfs 1>;
+		};
+
+		A53_1: cpu@101 {
+			compatible = "arm,cortex-a53","arm,armv8";
+			reg = <0x0 0x101>;
+			device_type = "cpu";
+			enable-method = "psci";
+			next-level-cache = <&A53_L2>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+			clocks = <&scpi_dvfs 1>;
+		};
+
+		A53_2: cpu@102 {
+			compatible = "arm,cortex-a53","arm,armv8";
+			reg = <0x0 0x102>;
+			device_type = "cpu";
+			enable-method = "psci";
+			next-level-cache = <&A53_L2>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+			clocks = <&scpi_dvfs 1>;
+		};
+
+		A53_3: cpu@103 {
+			compatible = "arm,cortex-a53","arm,armv8";
+			reg = <0x0 0x103>;
+			device_type = "cpu";
+			enable-method = "psci";
+			next-level-cache = <&A53_L2>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+			clocks = <&scpi_dvfs 1>;
+		};
+
+		A57_L2: l2-cache0 {
+			compatible = "cache";
+		};
+
+		A53_L2: l2-cache1 {
+			compatible = "cache";
+		};
+	};
+
+	pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <GIC_SPI 02 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 06 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&A57_0>,
+				     <&A57_1>,
+				     <&A53_0>,
+				     <&A53_1>,
+				     <&A53_2>,
+				     <&A53_3>;
+	};
+
+	scpi_sensor0: scpi-sensor@0 {
+		compatible = "arm,scpi-thermal";
+		#thermal-sensor-cells = <1>;
+	};
+
+	thermal-zones {
+		soc_thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <100>;
+			sustainable-power = <2500>;
+
+			thermal-sensors = <&scpi_sensor0 3>;
+
+			trips {
+				threshold: trip-point@0 {
+					temperature = <55000>;
+					hysteresis = <1000>;
+					type = "passive";
+				};
+				target: trip-point@1 {
+					temperature = <65000>;
+					hysteresis = <1000>;
+					type = "passive";
+				};
+			};
+
+			cooling-maps {
+			        map0 {
+				     trip = <&target>;
+				     contribution = <1024>;
+				     cooling-device = <&cluster0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+				map1 {
+				     trip = <&target>;
+				     contribution = <2048>;
+				     cooling-device = <&cluster1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+				map2 {
+				     trip = <&target>;
+				     contribution = <1024>;
+				     cooling-device = <&gpu 0 4>;
+				};
+
+			};
+		};
+	};
+
+	#include "juno-base.dtsi"
+};
diff --git a/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi b/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi
index c46cbb29f3c..5f1910454e9 100644
--- a/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi
+++ b/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi
@@ -15,7 +15,7 @@
 		#interrupt-cells = <1>;
 		ranges;
 
-		flash@0,00000000 {
+		flash: flash@0,00000000 {
 			compatible = "arm,vexpress-flash", "cfi-flash";
 			reg = <0 0x00000000 0x04000000>,
 			      <4 0x00000000 0x04000000>;
@@ -76,7 +76,7 @@
 				clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3";
 			};
 
-			aaci@040000 {
+			aaci: aaci@040000 {
 				compatible = "arm,pl041", "arm,primecell";
 				reg = <0x040000 0x1000>;
 				interrupts = <11>;
@@ -84,7 +84,7 @@
 				clock-names = "apb_pclk";
 			};
 
-			mmci@050000 {
+			mmci: mmci@050000 {
 				compatible = "arm,pl180", "arm,primecell";
 				reg = <0x050000 0x1000>;
 				interrupts = <9 10>;
@@ -96,7 +96,7 @@
 				clock-names = "mclk", "apb_pclk";
 			};
 
-			kmi@060000 {
+			kmi0: kmi@060000 {
 				compatible = "arm,pl050", "arm,primecell";
 				reg = <0x060000 0x1000>;
 				interrupts = <12>;
@@ -104,7 +104,7 @@
 				clock-names = "KMIREFCLK", "apb_pclk";
 			};
 
-			kmi@070000 {
+			kmi1: kmi@070000 {
 				compatible = "arm,pl050", "arm,primecell";
 				reg = <0x070000 0x1000>;
 				interrupts = <13>;
@@ -176,7 +176,7 @@
 				clock-names = "apb_pclk";
 			};
 
-			clcd@1f0000 {
+			clcd: clcd@1f0000 {
 				compatible = "arm,pl111", "arm,primecell";
 				reg = <0x1f0000 0x1000>;
 				interrupt-names = "combined";
diff --git a/arch/arm64/boot/dts/cavium/Makefile b/arch/arm64/boot/dts/cavium/Makefile
new file mode 100644
index 00000000000..e34f89ddabb
--- /dev/null
+++ b/arch/arm64/boot/dts/cavium/Makefile
@@ -0,0 +1,5 @@
+dtb-$(CONFIG_ARCH_THUNDER) += thunder-88xx.dtb
+
+always		:= $(dtb-y)
+subdir-y	:= $(dts-dirs)
+clean-files	:= *.dtb
diff --git a/arch/arm64/boot/dts/thunder-88xx.dts b/arch/arm64/boot/dts/cavium/thunder-88xx.dts
index 800ba65991f..800ba65991f 100644
--- a/arch/arm64/boot/dts/thunder-88xx.dts
+++ b/arch/arm64/boot/dts/cavium/thunder-88xx.dts
diff --git a/arch/arm64/boot/dts/thunder-88xx.dtsi b/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
index d8c0bdc5188..d8c0bdc5188 100644
--- a/arch/arm64/boot/dts/thunder-88xx.dtsi
+++ b/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
diff --git a/arch/arm64/boot/dts/foundation-v8.dts b/arch/arm64/boot/dts/foundation-v8.dts
deleted file mode 100644
index 4a060906809..00000000000
--- a/arch/arm64/boot/dts/foundation-v8.dts
+++ /dev/null
@@ -1,232 +0,0 @@
-/*
- * ARM Ltd.
- *
- * ARMv8 Foundation model DTS
- */
-
-/dts-v1/;
-
-/memreserve/ 0x80000000 0x00010000;
-
-/ {
-	model = "Foundation-v8A";
-	compatible = "arm,foundation-aarch64", "arm,vexpress";
-	interrupt-parent = <&gic>;
-	#address-cells = <2>;
-	#size-cells = <2>;
-
-	chosen { };
-
-	aliases {
-		serial0 = &v2m_serial0;
-		serial1 = &v2m_serial1;
-		serial2 = &v2m_serial2;
-		serial3 = &v2m_serial3;
-	};
-
-	cpus {
-		#address-cells = <2>;
-		#size-cells = <0>;
-
-		cpu@0 {
-			device_type = "cpu";
-			compatible = "arm,armv8";
-			reg = <0x0 0x0>;
-			enable-method = "spin-table";
-			cpu-release-addr = <0x0 0x8000fff8>;
-		};
-		cpu@1 {
-			device_type = "cpu";
-			compatible = "arm,armv8";
-			reg = <0x0 0x1>;
-			enable-method = "spin-table";
-			cpu-release-addr = <0x0 0x8000fff8>;
-		};
-		cpu@2 {
-			device_type = "cpu";
-			compatible = "arm,armv8";
-			reg = <0x0 0x2>;
-			enable-method = "spin-table";
-			cpu-release-addr = <0x0 0x8000fff8>;
-		};
-		cpu@3 {
-			device_type = "cpu";
-			compatible = "arm,armv8";
-			reg = <0x0 0x3>;
-			enable-method = "spin-table";
-			cpu-release-addr = <0x0 0x8000fff8>;
-		};
-	};
-
-	memory@80000000 {
-		device_type = "memory";
-		reg = <0x00000000 0x80000000 0 0x80000000>,
-		      <0x00000008 0x80000000 0 0x80000000>;
-	};
-
-	gic: interrupt-controller@2c001000 {
-		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
-		#interrupt-cells = <3>;
-		#address-cells = <0>;
-		interrupt-controller;
-		reg = <0x0 0x2c001000 0 0x1000>,
-		      <0x0 0x2c002000 0 0x1000>,
-		      <0x0 0x2c004000 0 0x2000>,
-		      <0x0 0x2c006000 0 0x2000>;
-		interrupts = <1 9 0xf04>;
-	};
-
-	timer {
-		compatible = "arm,armv8-timer";
-		interrupts = <1 13 0xff01>,
-			     <1 14 0xff01>,
-			     <1 11 0xff01>,
-			     <1 10 0xff01>;
-		clock-frequency = <100000000>;
-	};
-
-	pmu {
-		compatible = "arm,armv8-pmuv3";
-		interrupts = <0 60 4>,
-			     <0 61 4>,
-			     <0 62 4>,
-			     <0 63 4>;
-	};
-
-	smb {
-		compatible = "arm,vexpress,v2m-p1", "simple-bus";
-		arm,v2m-memory-map = "rs1";
-		#address-cells = <2>; /* SMB chipselect number and offset */
-		#size-cells = <1>;
-
-		ranges = <0 0 0 0x08000000 0x04000000>,
-			 <1 0 0 0x14000000 0x04000000>,
-			 <2 0 0 0x18000000 0x04000000>,
-			 <3 0 0 0x1c000000 0x04000000>,
-			 <4 0 0 0x0c000000 0x04000000>,
-			 <5 0 0 0x10000000 0x04000000>;
-
-		#interrupt-cells = <1>;
-		interrupt-map-mask = <0 0 63>;
-		interrupt-map = <0 0  0 &gic 0  0 4>,
-				<0 0  1 &gic 0  1 4>,
-				<0 0  2 &gic 0  2 4>,
-				<0 0  3 &gic 0  3 4>,
-				<0 0  4 &gic 0  4 4>,
-				<0 0  5 &gic 0  5 4>,
-				<0 0  6 &gic 0  6 4>,
-				<0 0  7 &gic 0  7 4>,
-				<0 0  8 &gic 0  8 4>,
-				<0 0  9 &gic 0  9 4>,
-				<0 0 10 &gic 0 10 4>,
-				<0 0 11 &gic 0 11 4>,
-				<0 0 12 &gic 0 12 4>,
-				<0 0 13 &gic 0 13 4>,
-				<0 0 14 &gic 0 14 4>,
-				<0 0 15 &gic 0 15 4>,
-				<0 0 16 &gic 0 16 4>,
-				<0 0 17 &gic 0 17 4>,
-				<0 0 18 &gic 0 18 4>,
-				<0 0 19 &gic 0 19 4>,
-				<0 0 20 &gic 0 20 4>,
-				<0 0 21 &gic 0 21 4>,
-				<0 0 22 &gic 0 22 4>,
-				<0 0 23 &gic 0 23 4>,
-				<0 0 24 &gic 0 24 4>,
-				<0 0 25 &gic 0 25 4>,
-				<0 0 26 &gic 0 26 4>,
-				<0 0 27 &gic 0 27 4>,
-				<0 0 28 &gic 0 28 4>,
-				<0 0 29 &gic 0 29 4>,
-				<0 0 30 &gic 0 30 4>,
-				<0 0 31 &gic 0 31 4>,
-				<0 0 32 &gic 0 32 4>,
-				<0 0 33 &gic 0 33 4>,
-				<0 0 34 &gic 0 34 4>,
-				<0 0 35 &gic 0 35 4>,
-				<0 0 36 &gic 0 36 4>,
-				<0 0 37 &gic 0 37 4>,
-				<0 0 38 &gic 0 38 4>,
-				<0 0 39 &gic 0 39 4>,
-				<0 0 40 &gic 0 40 4>,
-				<0 0 41 &gic 0 41 4>,
-				<0 0 42 &gic 0 42 4>;
-
-		ethernet@2,02000000 {
-			compatible = "smsc,lan91c111";
-			reg = <2 0x02000000 0x10000>;
-			interrupts = <15>;
-		};
-
-		v2m_clk24mhz: clk24mhz {
-			compatible = "fixed-clock";
-			#clock-cells = <0>;
-			clock-frequency = <24000000>;
-			clock-output-names = "v2m:clk24mhz";
-		};
-
-		v2m_refclk1mhz: refclk1mhz {
-			compatible = "fixed-clock";
-			#clock-cells = <0>;
-			clock-frequency = <1000000>;
-			clock-output-names = "v2m:refclk1mhz";
-		};
-
-		v2m_refclk32khz: refclk32khz {
-			compatible = "fixed-clock";
-			#clock-cells = <0>;
-			clock-frequency = <32768>;
-			clock-output-names = "v2m:refclk32khz";
-		};
-
-		iofpga@3,00000000 {
-			compatible = "arm,amba-bus", "simple-bus";
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges = <0 3 0 0x200000>;
-
-			v2m_sysreg: sysreg@010000 {
-				compatible = "arm,vexpress-sysreg";
-				reg = <0x010000 0x1000>;
-			};
-
-			v2m_serial0: uart@090000 {
-				compatible = "arm,pl011", "arm,primecell";
-				reg = <0x090000 0x1000>;
-				interrupts = <5>;
-				clocks = <&v2m_clk24mhz>, <&v2m_clk24mhz>;
-				clock-names = "uartclk", "apb_pclk";
-			};
-
-			v2m_serial1: uart@0a0000 {
-				compatible = "arm,pl011", "arm,primecell";
-				reg = <0x0a0000 0x1000>;
-				interrupts = <6>;
-				clocks = <&v2m_clk24mhz>, <&v2m_clk24mhz>;
-				clock-names = "uartclk", "apb_pclk";
-			};
-
-			v2m_serial2: uart@0b0000 {
-				compatible = "arm,pl011", "arm,primecell";
-				reg = <0x0b0000 0x1000>;
-				interrupts = <7>;
-				clocks = <&v2m_clk24mhz>, <&v2m_clk24mhz>;
-				clock-names = "uartclk", "apb_pclk";
-			};
-
-			v2m_serial3: uart@0c0000 {
-				compatible = "arm,pl011", "arm,primecell";
-				reg = <0x0c0000 0x1000>;
-				interrupts = <8>;
-				clocks = <&v2m_clk24mhz>, <&v2m_clk24mhz>;
-				clock-names = "uartclk", "apb_pclk";
-			};
-
-			virtio_block@0130000 {
-				compatible = "virtio,mmio";
-				reg = <0x130000 0x200>;
-				interrupts = <42>;
-			};
-		};
-	};
-};
diff --git a/arch/arm64/boot/dts/include/dt-bindings b/arch/arm64/boot/dts/include/dt-bindings
new file mode 120000
index 00000000000..08c00e4972f
--- /dev/null
+++ b/arch/arm64/boot/dts/include/dt-bindings
@@ -0,0 +1 @@
+../../../../../include/dt-bindings
\ No newline at end of file
diff --git a/arch/arm64/boot/dts/rtsm_ve-aemv8a.dts b/arch/arm64/boot/dts/rtsm_ve-aemv8a.dts
deleted file mode 100644
index 572005ea221..00000000000
--- a/arch/arm64/boot/dts/rtsm_ve-aemv8a.dts
+++ /dev/null
@@ -1,159 +0,0 @@
-/*
- * ARM Ltd. Fast Models
- *
- * Architecture Envelope Model (AEM) ARMv8-A
- * ARMAEMv8AMPCT
- *
- * RTSM_VE_AEMv8A.lisa
- */
-
-/dts-v1/;
-
-/memreserve/ 0x80000000 0x00010000;
-
-/ {
-	model = "RTSM_VE_AEMv8A";
-	compatible = "arm,rtsm_ve,aemv8a", "arm,vexpress";
-	interrupt-parent = <&gic>;
-	#address-cells = <2>;
-	#size-cells = <2>;
-
-	chosen { };
-
-	aliases {
-		serial0 = &v2m_serial0;
-		serial1 = &v2m_serial1;
-		serial2 = &v2m_serial2;
-		serial3 = &v2m_serial3;
-	};
-
-	cpus {
-		#address-cells = <2>;
-		#size-cells = <0>;
-
-		cpu@0 {
-			device_type = "cpu";
-			compatible = "arm,armv8";
-			reg = <0x0 0x0>;
-			enable-method = "spin-table";
-			cpu-release-addr = <0x0 0x8000fff8>;
-		};
-		cpu@1 {
-			device_type = "cpu";
-			compatible = "arm,armv8";
-			reg = <0x0 0x1>;
-			enable-method = "spin-table";
-			cpu-release-addr = <0x0 0x8000fff8>;
-		};
-		cpu@2 {
-			device_type = "cpu";
-			compatible = "arm,armv8";
-			reg = <0x0 0x2>;
-			enable-method = "spin-table";
-			cpu-release-addr = <0x0 0x8000fff8>;
-		};
-		cpu@3 {
-			device_type = "cpu";
-			compatible = "arm,armv8";
-			reg = <0x0 0x3>;
-			enable-method = "spin-table";
-			cpu-release-addr = <0x0 0x8000fff8>;
-		};
-	};
-
-	memory@80000000 {
-		device_type = "memory";
-		reg = <0x00000000 0x80000000 0 0x80000000>,
-		      <0x00000008 0x80000000 0 0x80000000>;
-	};
-
-	gic: interrupt-controller@2c001000 {
-		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
-		#interrupt-cells = <3>;
-		#address-cells = <0>;
-		interrupt-controller;
-		reg = <0x0 0x2c001000 0 0x1000>,
-		      <0x0 0x2c002000 0 0x1000>,
-		      <0x0 0x2c004000 0 0x2000>,
-		      <0x0 0x2c006000 0 0x2000>;
-		interrupts = <1 9 0xf04>;
-	};
-
-	timer {
-		compatible = "arm,armv8-timer";
-		interrupts = <1 13 0xff01>,
-			     <1 14 0xff01>,
-			     <1 11 0xff01>,
-			     <1 10 0xff01>;
-		clock-frequency = <100000000>;
-	};
-
-	pmu {
-		compatible = "arm,armv8-pmuv3";
-		interrupts = <0 60 4>,
-			     <0 61 4>,
-			     <0 62 4>,
-			     <0 63 4>;
-	};
-
-	smb {
-		compatible = "simple-bus";
-
-		#address-cells = <2>;
-		#size-cells = <1>;
-		ranges = <0 0 0 0x08000000 0x04000000>,
-			 <1 0 0 0x14000000 0x04000000>,
-			 <2 0 0 0x18000000 0x04000000>,
-			 <3 0 0 0x1c000000 0x04000000>,
-			 <4 0 0 0x0c000000 0x04000000>,
-			 <5 0 0 0x10000000 0x04000000>;
-
-		#interrupt-cells = <1>;
-		interrupt-map-mask = <0 0 63>;
-		interrupt-map = <0 0  0 &gic 0  0 4>,
-				<0 0  1 &gic 0  1 4>,
-				<0 0  2 &gic 0  2 4>,
-				<0 0  3 &gic 0  3 4>,
-				<0 0  4 &gic 0  4 4>,
-				<0 0  5 &gic 0  5 4>,
-				<0 0  6 &gic 0  6 4>,
-				<0 0  7 &gic 0  7 4>,
-				<0 0  8 &gic 0  8 4>,
-				<0 0  9 &gic 0  9 4>,
-				<0 0 10 &gic 0 10 4>,
-				<0 0 11 &gic 0 11 4>,
-				<0 0 12 &gic 0 12 4>,
-				<0 0 13 &gic 0 13 4>,
-				<0 0 14 &gic 0 14 4>,
-				<0 0 15 &gic 0 15 4>,
-				<0 0 16 &gic 0 16 4>,
-				<0 0 17 &gic 0 17 4>,
-				<0 0 18 &gic 0 18 4>,
-				<0 0 19 &gic 0 19 4>,
-				<0 0 20 &gic 0 20 4>,
-				<0 0 21 &gic 0 21 4>,
-				<0 0 22 &gic 0 22 4>,
-				<0 0 23 &gic 0 23 4>,
-				<0 0 24 &gic 0 24 4>,
-				<0 0 25 &gic 0 25 4>,
-				<0 0 26 &gic 0 26 4>,
-				<0 0 27 &gic 0 27 4>,
-				<0 0 28 &gic 0 28 4>,
-				<0 0 29 &gic 0 29 4>,
-				<0 0 30 &gic 0 30 4>,
-				<0 0 31 &gic 0 31 4>,
-				<0 0 32 &gic 0 32 4>,
-				<0 0 33 &gic 0 33 4>,
-				<0 0 34 &gic 0 34 4>,
-				<0 0 35 &gic 0 35 4>,
-				<0 0 36 &gic 0 36 4>,
-				<0 0 37 &gic 0 37 4>,
-				<0 0 38 &gic 0 38 4>,
-				<0 0 39 &gic 0 39 4>,
-				<0 0 40 &gic 0 40 4>,
-				<0 0 41 &gic 0 41 4>,
-				<0 0 42 &gic 0 42 4>;
-
-		/include/ "rtsm_ve-motherboard.dtsi"
-	};
-};
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index 9e6cdde9b43..0156a268e16 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -294,4 +294,4 @@ module_exit(aes_mod_exit);
 MODULE_DESCRIPTION("Synchronous AES in CCM mode using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("ccm(aes)");
+MODULE_ALIAS_CRYPTO("ccm(aes)");
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 79cd911ef88..5f63a791b2f 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -38,10 +38,10 @@ MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions");
 #define aes_xts_encrypt		neon_aes_xts_encrypt
 #define aes_xts_decrypt		neon_aes_xts_decrypt
 MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 NEON");
-MODULE_ALIAS("ecb(aes)");
-MODULE_ALIAS("cbc(aes)");
-MODULE_ALIAS("ctr(aes)");
-MODULE_ALIAS("xts(aes)");
+MODULE_ALIAS_CRYPTO("ecb(aes)");
+MODULE_ALIAS_CRYPTO("cbc(aes)");
+MODULE_ALIAS_CRYPTO("ctr(aes)");
+MODULE_ALIAS_CRYPTO("xts(aes)");
 #endif
 
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
diff --git a/arch/arm64/include/asm/alternative-asm.h b/arch/arm64/include/asm/alternative-asm.h
new file mode 100644
index 00000000000..919a67855b6
--- /dev/null
+++ b/arch/arm64/include/asm/alternative-asm.h
@@ -0,0 +1,29 @@
+#ifndef __ASM_ALTERNATIVE_ASM_H
+#define __ASM_ALTERNATIVE_ASM_H
+
+#ifdef __ASSEMBLY__
+
+.macro altinstruction_entry orig_offset alt_offset feature orig_len alt_len
+	.word \orig_offset - .
+	.word \alt_offset - .
+	.hword \feature
+	.byte \orig_len
+	.byte \alt_len
+.endm
+
+.macro alternative_insn insn1 insn2 cap
+661:	\insn1
+662:	.pushsection .altinstructions, "a"
+	altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f
+	.popsection
+	.pushsection .altinstr_replacement, "ax"
+663:	\insn2
+664:	.popsection
+	.if ((664b-663b) != (662b-661b))
+		.error "Alternatives instruction length mismatch"
+	.endif
+.endm
+
+#endif  /*  __ASSEMBLY__  */
+
+#endif /* __ASM_ALTERNATIVE_ASM_H */
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
new file mode 100644
index 00000000000..f6d206e7f9e
--- /dev/null
+++ b/arch/arm64/include/asm/alternative.h
@@ -0,0 +1,43 @@
+#ifndef __ASM_ALTERNATIVE_H
+#define __ASM_ALTERNATIVE_H
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/stringify.h>
+
+struct alt_instr {
+	s32 orig_offset;	/* offset to original instruction */
+	s32 alt_offset;		/* offset to replacement instruction */
+	u16 cpufeature;		/* cpufeature bit set for replacement */
+	u8  orig_len;		/* size of original instruction(s) */
+	u8  alt_len;		/* size of new instruction(s), <= orig_len */
+};
+
+void apply_alternatives(void);
+void free_alternatives_memory(void);
+
+#define ALTINSTR_ENTRY(feature)						      \
+	" .word 661b - .\n"				/* label           */ \
+	" .word 663f - .\n"				/* new instruction */ \
+	" .hword " __stringify(feature) "\n"		/* feature bit     */ \
+	" .byte 662b-661b\n"				/* source len      */ \
+	" .byte 664f-663f\n"				/* replacement len */
+
+/* alternative assembly primitive: */
+#define ALTERNATIVE(oldinstr, newinstr, feature)			\
+	"661:\n\t"							\
+	oldinstr "\n"							\
+	"662:\n"							\
+	".pushsection .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY(feature)						\
+	".popsection\n"							\
+	".pushsection .altinstr_replacement, \"a\"\n"			\
+	"663:\n\t"							\
+	newinstr "\n"							\
+	"664:\n\t"							\
+	".popsection\n\t"						\
+	".if ((664b-663b) != (662b-661b))\n\t"				\
+	"	.error \"Alternatives instruction length mismatch\"\n\t"\
+	".endif\n"
+
+#endif /* __ASM_ALTERNATIVE_H */
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index f19097134b0..b1fa4e61471 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -104,6 +104,15 @@ static inline void arch_timer_set_cntkctl(u32 cntkctl)
 	asm volatile("msr	cntkctl_el1, %0" : : "r" (cntkctl));
 }
 
+static inline u64 arch_counter_get_cntpct(void)
+{
+	/*
+	 * AArch64 kernel and user space mandate the use of CNTVCT.
+	 */
+	BUG();
+	return 0;
+}
+
 static inline u64 arch_counter_get_cntvct(void)
 {
 	u64 cval;
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index 56de5aadede..3fb053fa6e9 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -205,6 +205,13 @@ typedef struct compat_siginfo {
 			compat_long_t _band;	/* POLL_IN, POLL_OUT, POLL_MSG */
 			int _fd;
 		} _sigpoll;
+
+		/* SIGSYS */
+		struct {
+			compat_uptr_t _call_addr; /* calling user insn */
+			int _syscall;	/* triggering system call number */
+			compat_uint_t _arch;	/* AUDIT_ARCH_* of syscall */
+		} _sigsys;
 	} _sifields;
 } compat_siginfo_t;
 
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index cd4ac051648..3ae74b56947 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -21,9 +21,42 @@
 #define MAX_CPU_FEATURES	(8 * sizeof(elf_hwcap))
 #define cpu_feature(x)		ilog2(HWCAP_ ## x)
 
+#define ARM64_WORKAROUND_CLEAN_CACHE		0
+#define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE	1
+#define ARM64_WORKAROUND_845719			2
+
+#define NCAPS					3
+
+#ifndef __ASSEMBLY__
+
+extern DECLARE_BITMAP(cpu_hwcaps, NCAPS);
+
 static inline bool cpu_have_feature(unsigned int num)
 {
 	return elf_hwcap & (1UL << num);
 }
 
+static inline bool cpus_have_cap(unsigned int num)
+{
+	if (num >= NCAPS)
+		return false;
+	return test_bit(num, cpu_hwcaps);
+}
+
+static inline void cpus_set_cap(unsigned int num)
+{
+	if (num >= NCAPS)
+		pr_warn("Attempt to set an illegal CPU capability (%d >= %d)\n",
+			num, NCAPS);
+	else
+		__set_bit(num, cpu_hwcaps);
+}
+
+void check_local_cpu_errata(void);
+
+bool cpu_supports_mixed_endian_el0(void);
+bool system_supports_mixed_endian_el0(void);
+
+#endif /* __ASSEMBLY__ */
+
 #endif
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 379d0b87432..a84ec605bed 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -57,6 +57,11 @@
 #define MIDR_IMPLEMENTOR(midr)	\
 	(((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT)
 
+#define MIDR_CPU_PART(imp, partnum) \
+	(((imp)			<< MIDR_IMPLEMENTOR_SHIFT) | \
+	(0xf			<< MIDR_ARCHITECTURE_SHIFT) | \
+	((partnum)		<< MIDR_PARTNUM_SHIFT))
+
 #define ARM_CPU_IMP_ARM		0x41
 #define ARM_CPU_IMP_APM		0x50
 
@@ -67,6 +72,18 @@
 
 #define APM_CPU_PART_POTENZA	0x000
 
+#define ID_AA64MMFR0_BIGENDEL0_SHIFT	16
+#define ID_AA64MMFR0_BIGENDEL0_MASK	(0xf << ID_AA64MMFR0_BIGENDEL0_SHIFT)
+#define ID_AA64MMFR0_BIGENDEL0(mmfr0)	\
+	(((mmfr0) & ID_AA64MMFR0_BIGENDEL0_MASK) >> ID_AA64MMFR0_BIGENDEL0_SHIFT)
+#define ID_AA64MMFR0_BIGEND_SHIFT	8
+#define ID_AA64MMFR0_BIGEND_MASK	(0xf << ID_AA64MMFR0_BIGEND_SHIFT)
+#define ID_AA64MMFR0_BIGEND(mmfr0)	\
+	(((mmfr0) & ID_AA64MMFR0_BIGEND_MASK) >> ID_AA64MMFR0_BIGEND_SHIFT)
+
+#define SCTLR_EL1_CP15BEN	(0x1 << 5)
+#define SCTLR_EL1_SED		(0x1 << 8)
+
 #ifndef __ASSEMBLY__
 
 /*
@@ -99,6 +116,11 @@ static inline u32 __attribute_const__ read_cpuid_cachetype(void)
 	return read_cpuid(CTR_EL0);
 }
 
+static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0)
+{
+	return (ID_AA64MMFR0_BIGEND(mmfr0) == 0x1) ||
+		(ID_AA64MMFR0_BIGENDEL0(mmfr0) == 0x1);
+}
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 024c46183c3..0ad735166d9 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -30,6 +30,7 @@
 #define COMPAT_HWCAP_IDIVA	(1 << 17)
 #define COMPAT_HWCAP_IDIVT	(1 << 18)
 #define COMPAT_HWCAP_IDIV	(COMPAT_HWCAP_IDIVA|COMPAT_HWCAP_IDIVT)
+#define COMPAT_HWCAP_LPAE	(1 << 20)
 #define COMPAT_HWCAP_EVTSTRM	(1 << 21)
 
 #define COMPAT_HWCAP2_AES	(1 << 0)
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 56a9e63b6c3..e2ff32a93b5 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -354,6 +354,16 @@ bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn);
 int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
 int aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt);
 int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
+
+bool aarch32_insn_is_wide(u32 insn);
+
+#define A32_RN_OFFSET	16
+#define A32_RT_OFFSET	12
+#define A32_RT2_OFFSET	 0
+
+u32 aarch32_insn_extract_reg_num(u32 insn, int offset);
+u32 aarch32_insn_mcr_extract_opc2(u32 insn);
+u32 aarch32_insn_mcr_extract_crm(u32 insn);
 #endif /* __ASSEMBLY__ */
 
 #endif	/* __ASM_INSN_H */
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 79f1d519221..75825b63464 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -28,6 +28,8 @@
 #include <asm/barrier.h>
 #include <asm/pgtable.h>
 #include <asm/early_ioremap.h>
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
 
 #include <xen/xen.h>
 
@@ -57,28 +59,41 @@ static inline void __raw_writeq(u64 val, volatile void __iomem *addr)
 static inline u8 __raw_readb(const volatile void __iomem *addr)
 {
 	u8 val;
-	asm volatile("ldrb %w0, [%1]" : "=r" (val) : "r" (addr));
+	asm volatile(ALTERNATIVE("ldrb %w0, [%1]",
+				 "ldarb %w0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
+		     : "=r" (val) : "r" (addr));
 	return val;
 }
 
 static inline u16 __raw_readw(const volatile void __iomem *addr)
 {
 	u16 val;
-	asm volatile("ldrh %w0, [%1]" : "=r" (val) : "r" (addr));
+
+	asm volatile(ALTERNATIVE("ldrh %w0, [%1]",
+				 "ldarh %w0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
+		     : "=r" (val) : "r" (addr));
 	return val;
 }
 
 static inline u32 __raw_readl(const volatile void __iomem *addr)
 {
 	u32 val;
-	asm volatile("ldr %w0, [%1]" : "=r" (val) : "r" (addr));
+	asm volatile(ALTERNATIVE("ldr %w0, [%1]",
+				 "ldar %w0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
+		     : "=r" (val) : "r" (addr));
 	return val;
 }
 
 static inline u64 __raw_readq(const volatile void __iomem *addr)
 {
 	u64 val;
-	asm volatile("ldr %0, [%1]" : "=r" (val) : "r" (addr));
+	asm volatile(ALTERNATIVE("ldr %0, [%1]",
+				 "ldar %0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
+		     : "=r" (val) : "r" (addr));
 	return val;
 }
 
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 7fd3e27e3cc..8afb863f5a9 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -18,6 +18,7 @@
 #ifndef __ARM64_KVM_ARM_H__
 #define __ARM64_KVM_ARM_H__
 
+#include <asm/memory.h>
 #include <asm/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
@@ -160,9 +161,9 @@
 #endif
 
 #define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((1LLU << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
-#define VTTBR_VMID_SHIFT  (48LLU)
-#define VTTBR_VMID_MASK	  (0xffLLU << VTTBR_VMID_SHIFT)
+#define VTTBR_BADDR_MASK  (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_VMID_SHIFT  (UL(48))
+#define VTTBR_VMID_MASK	  (UL(0xFF) << VTTBR_VMID_SHIFT)
 
 /* Hyp System Trap Register */
 #define HSTR_EL2_TTEE	(1 << 16)
@@ -185,13 +186,13 @@
 
 /* Exception Syndrome Register (ESR) bits */
 #define ESR_EL2_EC_SHIFT	(26)
-#define ESR_EL2_EC		(0x3fU << ESR_EL2_EC_SHIFT)
-#define ESR_EL2_IL		(1U << 25)
+#define ESR_EL2_EC		(UL(0x3f) << ESR_EL2_EC_SHIFT)
+#define ESR_EL2_IL		(UL(1) << 25)
 #define ESR_EL2_ISS		(ESR_EL2_IL - 1)
 #define ESR_EL2_ISV_SHIFT	(24)
-#define ESR_EL2_ISV		(1U << ESR_EL2_ISV_SHIFT)
+#define ESR_EL2_ISV		(UL(1) << ESR_EL2_ISV_SHIFT)
 #define ESR_EL2_SAS_SHIFT	(22)
-#define ESR_EL2_SAS		(3U << ESR_EL2_SAS_SHIFT)
+#define ESR_EL2_SAS		(UL(3) << ESR_EL2_SAS_SHIFT)
 #define ESR_EL2_SSE		(1 << 21)
 #define ESR_EL2_SRT_SHIFT	(16)
 #define ESR_EL2_SRT_MASK	(0x1f << ESR_EL2_SRT_SHIFT)
@@ -205,16 +206,16 @@
 #define ESR_EL2_FSC_TYPE	(0x3c)
 
 #define ESR_EL2_CV_SHIFT	(24)
-#define ESR_EL2_CV		(1U << ESR_EL2_CV_SHIFT)
+#define ESR_EL2_CV		(UL(1) << ESR_EL2_CV_SHIFT)
 #define ESR_EL2_COND_SHIFT	(20)
-#define ESR_EL2_COND		(0xfU << ESR_EL2_COND_SHIFT)
+#define ESR_EL2_COND		(UL(0xf) << ESR_EL2_COND_SHIFT)
 
 
 #define FSC_FAULT	(0x04)
 #define FSC_PERM	(0x0c)
 
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
-#define HPFAR_MASK	(~0xFUL)
+#define HPFAR_MASK	(~UL(0xf))
 
 #define ESR_EL2_EC_UNKNOWN	(0x00)
 #define ESR_EL2_EC_WFI		(0x01)
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 5674a55b551..865a7e28ea2 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -38,6 +38,13 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu);
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
 void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
 
+static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
+	if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
+		vcpu->arch.hcr_el2 &= ~HCR_RW;
+}
+
 static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
 {
 	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 2012c4ba8d6..dbd32127dbb 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -200,6 +200,7 @@ struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
 struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
 
 u64 kvm_call_hyp(void *hypfn, ...);
+void force_vm_exit(const cpumask_t *mask);
 
 int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		int exception_index);
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 0caf7a59f6a..a205e957d5c 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -83,6 +83,7 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
 void free_boot_hyp_pgd(void);
 void free_hyp_pgds(void);
 
+void stage2_unmap_vm(struct kvm *kvm);
 int kvm_alloc_stage2_pgd(struct kvm *kvm);
 void kvm_free_stage2_pgd(struct kvm *kvm);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
@@ -136,6 +137,8 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
 #define PTRS_PER_S2_PGD		(1 << PTRS_PER_S2_PGD_SHIFT)
 #define S2_PGD_ORDER		get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
 
+#define kvm_pgd_index(addr)	(((addr) >> PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1))
+
 /*
  * If we are concatenating first level stage-2 page tables, we would have less
  * than or equal to 16 pointers in the fake PGD, because that's what the
@@ -149,43 +152,6 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
 #define KVM_PREALLOC_LEVEL	(0)
 #endif
 
-/**
- * kvm_prealloc_hwpgd - allocate inital table for VTTBR
- * @kvm:	The KVM struct pointer for the VM.
- * @pgd:	The kernel pseudo pgd
- *
- * When the kernel uses more levels of page tables than the guest, we allocate
- * a fake PGD and pre-populate it to point to the next-level page table, which
- * will be the real initial page table pointed to by the VTTBR.
- *
- * When KVM_PREALLOC_LEVEL==2, we allocate a single page for the PMD and
- * the kernel will use folded pud.  When KVM_PREALLOC_LEVEL==1, we
- * allocate 2 consecutive PUD pages.
- */
-static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd)
-{
-	unsigned int i;
-	unsigned long hwpgd;
-
-	if (KVM_PREALLOC_LEVEL == 0)
-		return 0;
-
-	hwpgd = __get_free_pages(GFP_KERNEL | __GFP_ZERO, PTRS_PER_S2_PGD_SHIFT);
-	if (!hwpgd)
-		return -ENOMEM;
-
-	for (i = 0; i < PTRS_PER_S2_PGD; i++) {
-		if (KVM_PREALLOC_LEVEL == 1)
-			pgd_populate(NULL, pgd + i,
-				     (pud_t *)hwpgd + i * PTRS_PER_PUD);
-		else if (KVM_PREALLOC_LEVEL == 2)
-			pud_populate(NULL, pud_offset(pgd, 0) + i,
-				     (pmd_t *)hwpgd + i * PTRS_PER_PMD);
-	}
-
-	return 0;
-}
-
 static inline void *kvm_get_hwpgd(struct kvm *kvm)
 {
 	pgd_t *pgd = kvm->arch.pgd;
@@ -202,12 +168,11 @@ static inline void *kvm_get_hwpgd(struct kvm *kvm)
 	return pmd_offset(pud, 0);
 }
 
-static inline void kvm_free_hwpgd(struct kvm *kvm)
+static inline unsigned int kvm_get_hwpgd_size(void)
 {
-	if (KVM_PREALLOC_LEVEL > 0) {
-		unsigned long hwpgd = (unsigned long)kvm_get_hwpgd(kvm);
-		free_pages(hwpgd, PTRS_PER_S2_PGD_SHIFT);
-	}
+	if (KVM_PREALLOC_LEVEL > 0)
+		return PTRS_PER_S2_PGD * PAGE_SIZE;
+	return PTRS_PER_S2_PGD * sizeof(pgd_t);
 }
 
 static inline bool kvm_page_empty(void *ptr)
@@ -242,20 +207,42 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 	return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
 }
 
-static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
-					     unsigned long size)
+static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
+					       unsigned long size,
+					       bool ipa_uncached)
 {
-	if (!vcpu_has_cache_enabled(vcpu))
-		kvm_flush_dcache_to_poc((void *)hva, size);
+	void *va = page_address(pfn_to_page(pfn));
+
+	if (!vcpu_has_cache_enabled(vcpu) || ipa_uncached)
+		kvm_flush_dcache_to_poc(va, size);
 
 	if (!icache_is_aliasing()) {		/* PIPT */
-		flush_icache_range(hva, hva + size);
+		flush_icache_range((unsigned long)va,
+				   (unsigned long)va + size);
 	} else if (!icache_is_aivivt()) {	/* non ASID-tagged VIVT */
 		/* any kind of VIPT cache */
 		__flush_icache_all();
 	}
 }
 
+static inline void __kvm_flush_dcache_pte(pte_t pte)
+{
+	struct page *page = pte_page(pte);
+	kvm_flush_dcache_to_poc(page_address(page), PAGE_SIZE);
+}
+
+static inline void __kvm_flush_dcache_pmd(pmd_t pmd)
+{
+	struct page *page = pmd_page(pmd);
+	kvm_flush_dcache_to_poc(page_address(page), PMD_SIZE);
+}
+
+static inline void __kvm_flush_dcache_pud(pud_t pud)
+{
+	struct page *page = pud_page(pud);
+	kvm_flush_dcache_to_poc(page_address(page), PUD_SIZE);
+}
+
 #define kvm_virt_to_phys(x)		__virt_to_phys((unsigned long)(x))
 
 void stage2_flush_vm(struct kvm *kvm);
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index a9eee33dfa6..101a42bde72 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -151,6 +151,15 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 {
 	unsigned int cpu = smp_processor_id();
 
+	/*
+	 * init_mm.pgd does not contain any user mappings and it is always
+	 * active for kernel addresses in TTBR1. Just set the reserved TTBR0.
+	 */
+	if (next == &init_mm) {
+		cpu_set_reserved_ttbr0();
+		return;
+	}
+
 	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next)
 		check_and_switch_context(next, tsk);
 }
diff --git a/arch/arm64/include/asm/opcodes.h b/arch/arm64/include/asm/opcodes.h
new file mode 100644
index 00000000000..4e603ea36ad
--- /dev/null
+++ b/arch/arm64/include/asm/opcodes.h
@@ -0,0 +1 @@
+#include <../../arm/include/asm/opcodes.h>
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 41ed9e13795..d6dd9fdbc3b 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -58,6 +58,13 @@
 #define COMPAT_PSR_Z_BIT	0x40000000
 #define COMPAT_PSR_N_BIT	0x80000000
 #define COMPAT_PSR_IT_MASK	0x0600fc00	/* If-Then execution state mask */
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define COMPAT_PSR_ENDSTATE	COMPAT_PSR_E_BIT
+#else
+#define COMPAT_PSR_ENDSTATE	0
+#endif
+
 /*
  * These are 'magic' values for PTRACE_PEEKUSR that return info about where a
  * process is located in memory.
diff --git a/arch/arm64/include/asm/seccomp.h b/arch/arm64/include/asm/seccomp.h
new file mode 100644
index 00000000000..c76fac97962
--- /dev/null
+++ b/arch/arm64/include/asm/seccomp.h
@@ -0,0 +1,25 @@
+/*
+ * arch/arm64/include/asm/seccomp.h
+ *
+ * Copyright (C) 2014 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef _ASM_SECCOMP_H
+#define _ASM_SECCOMP_H
+
+#include <asm/unistd.h>
+
+#ifdef CONFIG_COMPAT
+#define __NR_seccomp_read_32		__NR_compat_read
+#define __NR_seccomp_write_32		__NR_compat_write
+#define __NR_seccomp_exit_32		__NR_compat_exit
+#define __NR_seccomp_sigreturn_32	__NR_compat_rt_sigreturn
+#endif /* CONFIG_COMPAT */
+
+#include <asm-generic/seccomp.h>
+
+#endif /* _ASM_SECCOMP_H */
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index a82c0c5c8b5..53d9c354219 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -19,10 +19,6 @@
 #ifndef __ASM_TLB_H
 #define __ASM_TLB_H
 
-#define  __tlb_remove_pmd_tlb_entry __tlb_remove_pmd_tlb_entry
-
-#include <asm-generic/tlb.h>
-
 #include <linux/pagemap.h>
 #include <linux/swap.h>
 
@@ -37,71 +33,23 @@ static inline void __tlb_remove_table(void *_table)
 #define tlb_remove_entry(tlb, entry)	tlb_remove_page(tlb, entry)
 #endif /* CONFIG_HAVE_RCU_TABLE_FREE */
 
-/*
- * There's three ways the TLB shootdown code is used:
- *  1. Unmapping a range of vmas.  See zap_page_range(), unmap_region().
- *     tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called.
- *  2. Unmapping all vmas.  See exit_mmap().
- *     tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called.
- *     Page tables will be freed.
- *  3. Unmapping argument pages.  See shift_arg_pages().
- *     tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called.
- */
+#include <asm-generic/tlb.h>
+
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
 	if (tlb->fullmm) {
 		flush_tlb_mm(tlb->mm);
-	} else if (tlb->end > 0) {
+	} else {
 		struct vm_area_struct vma = { .vm_mm = tlb->mm, };
 		flush_tlb_range(&vma, tlb->start, tlb->end);
-		tlb->start = TASK_SIZE;
-		tlb->end = 0;
-	}
-}
-
-static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
-{
-	if (!tlb->fullmm) {
-		tlb->start = min(tlb->start, addr);
-		tlb->end = max(tlb->end, addr + PAGE_SIZE);
-	}
-}
-
-/*
- * Memorize the range for the TLB flush.
- */
-static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
-					  unsigned long addr)
-{
-	tlb_add_flush(tlb, addr);
-}
-
-/*
- * In the case of tlb vma handling, we can optimise these away in the
- * case where we're doing a full MM flush.  When we're doing a munmap,
- * the vmas are adjusted to only cover the region to be torn down.
- */
-static inline void tlb_start_vma(struct mmu_gather *tlb,
-				 struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm) {
-		tlb->start = TASK_SIZE;
-		tlb->end = 0;
 	}
 }
 
-static inline void tlb_end_vma(struct mmu_gather *tlb,
-			       struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm)
-		tlb_flush(tlb);
-}
-
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 				  unsigned long addr)
 {
+	__flush_tlb_pgtable(tlb->mm, addr);
 	pgtable_page_dtor(pte);
-	tlb_add_flush(tlb, addr);
 	tlb_remove_entry(tlb, pte);
 }
 
@@ -109,7 +57,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 				  unsigned long addr)
 {
-	tlb_add_flush(tlb, addr);
+	__flush_tlb_pgtable(tlb->mm, addr);
 	tlb_remove_entry(tlb, virt_to_page(pmdp));
 }
 #endif
@@ -118,15 +66,9 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
 				  unsigned long addr)
 {
-	tlb_add_flush(tlb, addr);
+	__flush_tlb_pgtable(tlb->mm, addr);
 	tlb_remove_entry(tlb, virt_to_page(pudp));
 }
 #endif
 
-static inline void __tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp,
-						unsigned long address)
-{
-	tlb_add_flush(tlb, address);
-}
-
 #endif
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 73f0ce570fb..8b8d8cb46e0 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -149,6 +149,19 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
 }
 
 /*
+ * Used to invalidate the TLB (walk caches) corresponding to intermediate page
+ * table levels (pgd/pud/pmd).
+ */
+static inline void __flush_tlb_pgtable(struct mm_struct *mm,
+				       unsigned long uaddr)
+{
+	unsigned long addr = uaddr >> 12 | ((unsigned long)ASID(mm) << 48);
+
+	dsb(ishst);
+	asm("tlbi	vae1is, %0" : : "r" (addr));
+	dsb(ish);
+}
+/*
  * On AArch64, the cache coherency is handled via the set_pte_at() function.
  */
 static inline void update_mmu_cache(struct vm_area_struct *vma,
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 10ca8ff93cc..232e4ba5d31 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -18,6 +18,22 @@
 #ifndef __ASM_TRAP_H
 #define __ASM_TRAP_H
 
+#include <linux/list.h>
+
+struct pt_regs;
+
+struct undef_hook {
+	struct list_head node;
+	u32 instr_mask;
+	u32 instr_val;
+	u64 pstate_mask;
+	u64 pstate_val;
+	int (*fn)(struct pt_regs *regs, u32 instr);
+};
+
+void register_undef_hook(struct undef_hook *hook);
+void unregister_undef_hook(struct undef_hook *hook);
+
 static inline int in_exception_text(unsigned long ptr)
 {
 	extern char __exception_text_start[];
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 6d2bf419431..49c9aefd24a 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -31,6 +31,9 @@
  * Compat syscall numbers used by the AArch64 kernel.
  */
 #define __NR_compat_restart_syscall	0
+#define __NR_compat_exit		1
+#define __NR_compat_read		3
+#define __NR_compat_write		4
 #define __NR_compat_sigreturn		119
 #define __NR_compat_rt_sigreturn	173
 
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 9dfdac4a74a..8893cebcea5 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -787,7 +787,8 @@ __SYSCALL(__NR_sched_setattr, sys_sched_setattr)
 __SYSCALL(__NR_sched_getattr, sys_sched_getattr)
 #define __NR_renameat2 382
 __SYSCALL(__NR_renameat2, sys_renameat2)
-			/* 383 for seccomp */
+#define __NR_seccomp 383
+__SYSCALL(__NR_seccomp, sys_seccomp)
 #define __NR_getrandom 384
 __SYSCALL(__NR_getrandom, sys_getrandom)
 #define __NR_memfd_create 385
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 8e38878c87c..d9e9822efce 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -179,8 +179,14 @@ struct kvm_arch_memory_slot {
 #define KVM_ARM_IRQ_CPU_IRQ		0
 #define KVM_ARM_IRQ_CPU_FIQ		1
 
-/* Highest supported SPI, from VGIC_NR_IRQS */
+/*
+ * This used to hold the highest supported SPI, but it is now obsolete
+ * and only here to provide source code level compatibility with older
+ * userland. The highest SPI number can be set via KVM_DEV_ARM_VGIC_GRP_NR_IRQS.
+ */
+#ifndef __KERNEL__
 #define KVM_ARM_IRQ_GIC_MAX		127
+#endif
 
 /* PSCI interface */
 #define KVM_PSCI_FN_BASE		0x95c1ba5e
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 5bd029b4364..0a44aa522fd 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -5,6 +5,7 @@
 CPPFLAGS_vmlinux.lds	:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 AFLAGS_head.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 CFLAGS_efi-stub.o 	:= -DTEXT_OFFSET=$(TEXT_OFFSET)
+CFLAGS_armv8_deprecated.o := -I$(src)
 
 CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_insn.o = -pg
@@ -14,11 +15,12 @@ CFLAGS_REMOVE_return_address.o = -pg
 arm64-obj-y		:= cputable.o debug-monitors.o entry.o irq.o fpsimd.o	\
 			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\
 			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
-			   hyp-stub.o psci.o cpu_ops.o insn.o return_address.o	\
-			   cpuinfo.o
+			   hyp-stub.o psci.o psci-call.o cpu_ops.o insn.o 	\
+			   return_address.o cpuinfo.o cpu_errata.o alternative.o
 
 arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
-					   sys_compat.o
+					   sys_compat.o				\
+					   ../../arm/kernel/opcodes.o
 arm64-obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace.o entry-ftrace.o
 arm64-obj-$(CONFIG_MODULES)		+= arm64ksyms.o module.o
 arm64-obj-$(CONFIG_SMP)			+= smp.o smp_spin_table.o topology.o
@@ -31,6 +33,7 @@ arm64-obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
 arm64-obj-$(CONFIG_KGDB)		+= kgdb.o
 arm64-obj-$(CONFIG_EFI)			+= efi.o efi-stub.o efi-entry.o
 arm64-obj-$(CONFIG_PCI)			+= pci.o
+arm64-obj-$(CONFIG_ARMV8_DEPRECATED)	+= armv8_deprecated.o
 
 obj-y					+= $(arm64-obj-y) vdso/
 obj-m					+= $(arm64-obj-m)
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
new file mode 100644
index 00000000000..1a3badab800
--- /dev/null
+++ b/arch/arm64/kernel/alternative.c
@@ -0,0 +1,64 @@
+/*
+ * alternative runtime patching
+ * inspired by the x86 version
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt) "alternatives: " fmt
+
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <asm/cacheflush.h>
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
+#include <linux/stop_machine.h>
+
+extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
+
+static int __apply_alternatives(void *dummy)
+{
+	struct alt_instr *alt;
+	u8 *origptr, *replptr;
+
+	for (alt = __alt_instructions; alt < __alt_instructions_end; alt++) {
+		if (!cpus_have_cap(alt->cpufeature))
+			continue;
+
+		BUG_ON(alt->alt_len > alt->orig_len);
+
+		pr_info_once("patching kernel code\n");
+
+		origptr = (u8 *)&alt->orig_offset + alt->orig_offset;
+		replptr = (u8 *)&alt->alt_offset + alt->alt_offset;
+		memcpy(origptr, replptr, alt->alt_len);
+		flush_icache_range((uintptr_t)origptr,
+				   (uintptr_t)(origptr + alt->alt_len));
+	}
+
+	return 0;
+}
+
+void apply_alternatives(void)
+{
+	/* better not try code patching on a live SMP system */
+	stop_machine(__apply_alternatives, NULL, NULL);
+}
+
+void free_alternatives_memory(void)
+{
+	free_reserved_area(__alt_instructions, __alt_instructions_end,
+			   0, "alternatives");
+}
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
new file mode 100644
index 00000000000..7922c2e710c
--- /dev/null
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -0,0 +1,662 @@
+/*
+ *  Copyright (C) 2014 ARM Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/cpu.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/perf_event.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/sysctl.h>
+
+#include <asm/insn.h>
+#include <asm/opcodes.h>
+#include <asm/system_misc.h>
+#include <asm/traps.h>
+#include <asm/uaccess.h>
+#include <asm/cpufeature.h>
+
+#define CREATE_TRACE_POINTS
+#include "trace-events-emulation.h"
+
+/*
+ * The runtime support for deprecated instruction support can be in one of
+ * following three states -
+ *
+ * 0 = undef
+ * 1 = emulate (software emulation)
+ * 2 = hw (supported in hardware)
+ */
+enum insn_emulation_mode {
+	INSN_UNDEF,
+	INSN_EMULATE,
+	INSN_HW,
+};
+
+enum legacy_insn_status {
+	INSN_DEPRECATED,
+	INSN_OBSOLETE,
+};
+
+struct insn_emulation_ops {
+	const char		*name;
+	enum legacy_insn_status	status;
+	struct undef_hook	*hooks;
+	int			(*set_hw_mode)(bool enable);
+};
+
+struct insn_emulation {
+	struct list_head node;
+	struct insn_emulation_ops *ops;
+	int current_mode;
+	int min;
+	int max;
+};
+
+static LIST_HEAD(insn_emulation);
+static int nr_insn_emulated;
+static DEFINE_RAW_SPINLOCK(insn_emulation_lock);
+
+static void register_emulation_hooks(struct insn_emulation_ops *ops)
+{
+	struct undef_hook *hook;
+
+	BUG_ON(!ops->hooks);
+
+	for (hook = ops->hooks; hook->instr_mask; hook++)
+		register_undef_hook(hook);
+
+	pr_notice("Registered %s emulation handler\n", ops->name);
+}
+
+static void remove_emulation_hooks(struct insn_emulation_ops *ops)
+{
+	struct undef_hook *hook;
+
+	BUG_ON(!ops->hooks);
+
+	for (hook = ops->hooks; hook->instr_mask; hook++)
+		unregister_undef_hook(hook);
+
+	pr_notice("Removed %s emulation handler\n", ops->name);
+}
+
+static void enable_insn_hw_mode(void *data)
+{
+	struct insn_emulation *insn = (struct insn_emulation *)data;
+	if (insn->ops->set_hw_mode)
+		insn->ops->set_hw_mode(true);
+}
+
+static void disable_insn_hw_mode(void *data)
+{
+	struct insn_emulation *insn = (struct insn_emulation *)data;
+	if (insn->ops->set_hw_mode)
+		insn->ops->set_hw_mode(false);
+}
+
+/* Run set_hw_mode(mode) on all active CPUs */
+static int run_all_cpu_set_hw_mode(struct insn_emulation *insn, bool enable)
+{
+	if (!insn->ops->set_hw_mode)
+		return -EINVAL;
+	if (enable)
+		on_each_cpu(enable_insn_hw_mode, (void *)insn, true);
+	else
+		on_each_cpu(disable_insn_hw_mode, (void *)insn, true);
+	return 0;
+}
+
+/*
+ * Run set_hw_mode for all insns on a starting CPU.
+ * Returns:
+ *  0 		- If all the hooks ran successfully.
+ * -EINVAL	- At least one hook is not supported by the CPU.
+ */
+static int run_all_insn_set_hw_mode(unsigned long cpu)
+{
+	int rc = 0;
+	unsigned long flags;
+	struct insn_emulation *insn;
+
+	raw_spin_lock_irqsave(&insn_emulation_lock, flags);
+	list_for_each_entry(insn, &insn_emulation, node) {
+		bool enable = (insn->current_mode == INSN_HW);
+		if (insn->ops->set_hw_mode && insn->ops->set_hw_mode(enable)) {
+			pr_warn("CPU[%ld] cannot support the emulation of %s",
+				cpu, insn->ops->name);
+			rc = -EINVAL;
+		}
+	}
+	raw_spin_unlock_irqrestore(&insn_emulation_lock, flags);
+	return rc;
+}
+
+static int update_insn_emulation_mode(struct insn_emulation *insn,
+				       enum insn_emulation_mode prev)
+{
+	int ret = 0;
+
+	switch (prev) {
+	case INSN_UNDEF: /* Nothing to be done */
+		break;
+	case INSN_EMULATE:
+		remove_emulation_hooks(insn->ops);
+		break;
+	case INSN_HW:
+		if (!run_all_cpu_set_hw_mode(insn, false))
+			pr_notice("Disabled %s support\n", insn->ops->name);
+		break;
+	}
+
+	switch (insn->current_mode) {
+	case INSN_UNDEF:
+		break;
+	case INSN_EMULATE:
+		register_emulation_hooks(insn->ops);
+		break;
+	case INSN_HW:
+		ret = run_all_cpu_set_hw_mode(insn, true);
+		if (!ret)
+			pr_notice("Enabled %s support\n", insn->ops->name);
+		break;
+	}
+
+	return ret;
+}
+
+static void register_insn_emulation(struct insn_emulation_ops *ops)
+{
+	unsigned long flags;
+	struct insn_emulation *insn;
+
+	insn = kzalloc(sizeof(*insn), GFP_KERNEL);
+	insn->ops = ops;
+	insn->min = INSN_UNDEF;
+
+	switch (ops->status) {
+	case INSN_DEPRECATED:
+		insn->current_mode = INSN_EMULATE;
+		/* Disable the HW mode if it was turned on at early boot time */
+		run_all_cpu_set_hw_mode(insn, false);
+		insn->max = INSN_HW;
+		break;
+	case INSN_OBSOLETE:
+		insn->current_mode = INSN_UNDEF;
+		insn->max = INSN_EMULATE;
+		break;
+	}
+
+	raw_spin_lock_irqsave(&insn_emulation_lock, flags);
+	list_add(&insn->node, &insn_emulation);
+	nr_insn_emulated++;
+	raw_spin_unlock_irqrestore(&insn_emulation_lock, flags);
+
+	/* Register any handlers if required */
+	update_insn_emulation_mode(insn, INSN_UNDEF);
+}
+
+static int emulation_proc_handler(struct ctl_table *table, int write,
+				  void __user *buffer, size_t *lenp,
+				  loff_t *ppos)
+{
+	int ret = 0;
+	struct insn_emulation *insn = (struct insn_emulation *) table->data;
+	enum insn_emulation_mode prev_mode = insn->current_mode;
+
+	table->data = &insn->current_mode;
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+	if (ret || !write || prev_mode == insn->current_mode)
+		goto ret;
+
+	ret = update_insn_emulation_mode(insn, prev_mode);
+	if (ret) {
+		/* Mode change failed, revert to previous mode. */
+		insn->current_mode = prev_mode;
+		update_insn_emulation_mode(insn, INSN_UNDEF);
+	}
+ret:
+	table->data = insn;
+	return ret;
+}
+
+static struct ctl_table ctl_abi[] = {
+	{
+		.procname = "abi",
+		.mode = 0555,
+	},
+	{ }
+};
+
+static void register_insn_emulation_sysctl(struct ctl_table *table)
+{
+	unsigned long flags;
+	int i = 0;
+	struct insn_emulation *insn;
+	struct ctl_table *insns_sysctl, *sysctl;
+
+	insns_sysctl = kzalloc(sizeof(*sysctl) * (nr_insn_emulated + 1),
+			      GFP_KERNEL);
+
+	raw_spin_lock_irqsave(&insn_emulation_lock, flags);
+	list_for_each_entry(insn, &insn_emulation, node) {
+		sysctl = &insns_sysctl[i];
+
+		sysctl->mode = 0644;
+		sysctl->maxlen = sizeof(int);
+
+		sysctl->procname = insn->ops->name;
+		sysctl->data = insn;
+		sysctl->extra1 = &insn->min;
+		sysctl->extra2 = &insn->max;
+		sysctl->proc_handler = emulation_proc_handler;
+		i++;
+	}
+	raw_spin_unlock_irqrestore(&insn_emulation_lock, flags);
+
+	table->child = insns_sysctl;
+	register_sysctl_table(table);
+}
+
+/*
+ *  Implement emulation of the SWP/SWPB instructions using load-exclusive and
+ *  store-exclusive.
+ *
+ *  Syntax of SWP{B} instruction: SWP{B}<c> <Rt>, <Rt2>, [<Rn>]
+ *  Where: Rt  = destination
+ *	   Rt2 = source
+ *	   Rn  = address
+ */
+
+/*
+ * Error-checking SWP macros implemented using ldxr{b}/stxr{b}
+ */
+#define __user_swpX_asm(data, addr, res, temp, B)		\
+	__asm__ __volatile__(					\
+	"	mov		%w2, %w1\n"			\
+	"0:	ldxr"B"		%w1, [%3]\n"			\
+	"1:	stxr"B"		%w0, %w2, [%3]\n"		\
+	"	cbz		%w0, 2f\n"			\
+	"	mov		%w0, %w4\n"			\
+	"2:\n"							\
+	"	.pushsection	 .fixup,\"ax\"\n"		\
+	"	.align		2\n"				\
+	"3:	mov		%w0, %w5\n"			\
+	"	b		2b\n"				\
+	"	.popsection"					\
+	"	.pushsection	 __ex_table,\"a\"\n"		\
+	"	.align		3\n"				\
+	"	.quad		0b, 3b\n"			\
+	"	.quad		1b, 3b\n"			\
+	"	.popsection"					\
+	: "=&r" (res), "+r" (data), "=&r" (temp)		\
+	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT)		\
+	: "memory")
+
+#define __user_swp_asm(data, addr, res, temp) \
+	__user_swpX_asm(data, addr, res, temp, "")
+#define __user_swpb_asm(data, addr, res, temp) \
+	__user_swpX_asm(data, addr, res, temp, "b")
+
+/*
+ * Bit 22 of the instruction encoding distinguishes between
+ * the SWP and SWPB variants (bit set means SWPB).
+ */
+#define TYPE_SWPB (1 << 22)
+
+/*
+ * Set up process info to signal segmentation fault - called on access error.
+ */
+static void set_segfault(struct pt_regs *regs, unsigned long addr)
+{
+	siginfo_t info;
+
+	down_read(&current->mm->mmap_sem);
+	if (find_vma(current->mm, addr) == NULL)
+		info.si_code = SEGV_MAPERR;
+	else
+		info.si_code = SEGV_ACCERR;
+	up_read(&current->mm->mmap_sem);
+
+	info.si_signo = SIGSEGV;
+	info.si_errno = 0;
+	info.si_addr  = (void *) instruction_pointer(regs);
+
+	pr_debug("SWP{B} emulation: access caused memory abort!\n");
+	arm64_notify_die("Illegal memory access", regs, &info, 0);
+}
+
+static int emulate_swpX(unsigned int address, unsigned int *data,
+			unsigned int type)
+{
+	unsigned int res = 0;
+
+	if ((type != TYPE_SWPB) && (address & 0x3)) {
+		/* SWP to unaligned address not permitted */
+		pr_debug("SWP instruction on unaligned pointer!\n");
+		return -EFAULT;
+	}
+
+	while (1) {
+		unsigned long temp;
+
+		if (type == TYPE_SWPB)
+			__user_swpb_asm(*data, address, res, temp);
+		else
+			__user_swp_asm(*data, address, res, temp);
+
+		if (likely(res != -EAGAIN) || signal_pending(current))
+			break;
+
+		cond_resched();
+	}
+
+	return res;
+}
+
+/*
+ * swp_handler logs the id of calling process, dissects the instruction, sanity
+ * checks the memory location, calls emulate_swpX for the actual operation and
+ * deals with fixup/error handling before returning
+ */
+static int swp_handler(struct pt_regs *regs, u32 instr)
+{
+	u32 destreg, data, type, address = 0;
+	int rn, rt2, res = 0;
+
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->pc);
+
+	type = instr & TYPE_SWPB;
+
+	switch (arm_check_condition(instr, regs->pstate)) {
+	case ARM_OPCODE_CONDTEST_PASS:
+		break;
+	case ARM_OPCODE_CONDTEST_FAIL:
+		/* Condition failed - return to next instruction */
+		goto ret;
+	case ARM_OPCODE_CONDTEST_UNCOND:
+		/* If unconditional encoding - not a SWP, undef */
+		return -EFAULT;
+	default:
+		return -EINVAL;
+	}
+
+	rn = aarch32_insn_extract_reg_num(instr, A32_RN_OFFSET);
+	rt2 = aarch32_insn_extract_reg_num(instr, A32_RT2_OFFSET);
+
+	address = (u32)regs->user_regs.regs[rn];
+	data	= (u32)regs->user_regs.regs[rt2];
+	destreg = aarch32_insn_extract_reg_num(instr, A32_RT_OFFSET);
+
+	pr_debug("addr in r%d->0x%08x, dest is r%d, source in r%d->0x%08x)\n",
+		rn, address, destreg,
+		aarch32_insn_extract_reg_num(instr, A32_RT2_OFFSET), data);
+
+	/* Check access in reasonable access range for both SWP and SWPB */
+	if (!access_ok(VERIFY_WRITE, (address & ~3), 4)) {
+		pr_debug("SWP{B} emulation: access to 0x%08x not allowed!\n",
+			address);
+		goto fault;
+	}
+
+	res = emulate_swpX(address, &data, type);
+	if (res == -EFAULT)
+		goto fault;
+	else if (res == 0)
+		regs->user_regs.regs[destreg] = data;
+
+ret:
+	if (type == TYPE_SWPB)
+		trace_instruction_emulation("swpb", regs->pc);
+	else
+		trace_instruction_emulation("swp", regs->pc);
+
+	pr_warn_ratelimited("\"%s\" (%ld) uses obsolete SWP{B} instruction at 0x%llx\n",
+			current->comm, (unsigned long)current->pid, regs->pc);
+
+	regs->pc += 4;
+	return 0;
+
+fault:
+	set_segfault(regs, address);
+
+	return 0;
+}
+
+/*
+ * Only emulate SWP/SWPB executed in ARM state/User mode.
+ * The kernel must be SWP free and SWP{B} does not exist in Thumb.
+ */
+static struct undef_hook swp_hooks[] = {
+	{
+		.instr_mask	= 0x0fb00ff0,
+		.instr_val	= 0x01000090,
+		.pstate_mask	= COMPAT_PSR_MODE_MASK,
+		.pstate_val	= COMPAT_PSR_MODE_USR,
+		.fn		= swp_handler
+	},
+	{ }
+};
+
+static struct insn_emulation_ops swp_ops = {
+	.name = "swp",
+	.status = INSN_OBSOLETE,
+	.hooks = swp_hooks,
+	.set_hw_mode = NULL,
+};
+
+static int cp15barrier_handler(struct pt_regs *regs, u32 instr)
+{
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->pc);
+
+	switch (arm_check_condition(instr, regs->pstate)) {
+	case ARM_OPCODE_CONDTEST_PASS:
+		break;
+	case ARM_OPCODE_CONDTEST_FAIL:
+		/* Condition failed - return to next instruction */
+		goto ret;
+	case ARM_OPCODE_CONDTEST_UNCOND:
+		/* If unconditional encoding - not a barrier instruction */
+		return -EFAULT;
+	default:
+		return -EINVAL;
+	}
+
+	switch (aarch32_insn_mcr_extract_crm(instr)) {
+	case 10:
+		/*
+		 * dmb - mcr p15, 0, Rt, c7, c10, 5
+		 * dsb - mcr p15, 0, Rt, c7, c10, 4
+		 */
+		if (aarch32_insn_mcr_extract_opc2(instr) == 5) {
+			dmb(sy);
+			trace_instruction_emulation(
+				"mcr p15, 0, Rt, c7, c10, 5 ; dmb", regs->pc);
+		} else {
+			dsb(sy);
+			trace_instruction_emulation(
+				"mcr p15, 0, Rt, c7, c10, 4 ; dsb", regs->pc);
+		}
+		break;
+	case 5:
+		/*
+		 * isb - mcr p15, 0, Rt, c7, c5, 4
+		 *
+		 * Taking an exception or returning from one acts as an
+		 * instruction barrier. So no explicit barrier needed here.
+		 */
+		trace_instruction_emulation(
+			"mcr p15, 0, Rt, c7, c5, 4 ; isb", regs->pc);
+		break;
+	}
+
+ret:
+	pr_warn_ratelimited("\"%s\" (%ld) uses deprecated CP15 Barrier instruction at 0x%llx\n",
+			current->comm, (unsigned long)current->pid, regs->pc);
+
+	regs->pc += 4;
+	return 0;
+}
+
+static inline void config_sctlr_el1(u32 clear, u32 set)
+{
+	u32 val;
+
+	asm volatile("mrs %0, sctlr_el1" : "=r" (val));
+	val &= ~clear;
+	val |= set;
+	asm volatile("msr sctlr_el1, %0" : : "r" (val));
+}
+
+static int cp15_barrier_set_hw_mode(bool enable)
+{
+	if (enable)
+		config_sctlr_el1(0, SCTLR_EL1_CP15BEN);
+	else
+		config_sctlr_el1(SCTLR_EL1_CP15BEN, 0);
+	return 0;
+}
+
+static struct undef_hook cp15_barrier_hooks[] = {
+	{
+		.instr_mask	= 0x0fff0fdf,
+		.instr_val	= 0x0e070f9a,
+		.pstate_mask	= COMPAT_PSR_MODE_MASK,
+		.pstate_val	= COMPAT_PSR_MODE_USR,
+		.fn		= cp15barrier_handler,
+	},
+	{
+		.instr_mask	= 0x0fff0fff,
+		.instr_val	= 0x0e070f95,
+		.pstate_mask	= COMPAT_PSR_MODE_MASK,
+		.pstate_val	= COMPAT_PSR_MODE_USR,
+		.fn		= cp15barrier_handler,
+	},
+	{ }
+};
+
+static struct insn_emulation_ops cp15_barrier_ops = {
+	.name = "cp15_barrier",
+	.status = INSN_DEPRECATED,
+	.hooks = cp15_barrier_hooks,
+	.set_hw_mode = cp15_barrier_set_hw_mode,
+};
+
+static int setend_set_hw_mode(bool enable)
+{
+	if (!cpu_supports_mixed_endian_el0())
+		return -EINVAL;
+
+	if (enable)
+		config_sctlr_el1(SCTLR_EL1_SED, 0);
+	else
+		config_sctlr_el1(0, SCTLR_EL1_SED);
+	return 0;
+}
+
+static int compat_setend_handler(struct pt_regs *regs, u32 big_endian)
+{
+	char *insn;
+
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->pc);
+
+	if (big_endian) {
+		insn = "setend be";
+		regs->pstate |= COMPAT_PSR_E_BIT;
+	} else {
+		insn = "setend le";
+		regs->pstate &= ~COMPAT_PSR_E_BIT;
+	}
+
+	trace_instruction_emulation(insn, regs->pc);
+	pr_warn_ratelimited("\"%s\" (%ld) uses deprecated setend instruction at 0x%llx\n",
+			current->comm, (unsigned long)current->pid, regs->pc);
+
+	return 0;
+}
+
+static int a32_setend_handler(struct pt_regs *regs, u32 instr)
+{
+	int rc = compat_setend_handler(regs, (instr >> 9) & 1);
+	regs->pc += 4;
+	return rc;
+}
+
+static int t16_setend_handler(struct pt_regs *regs, u32 instr)
+{
+	int rc = compat_setend_handler(regs, (instr >> 3) & 1);
+	regs->pc += 2;
+	return rc;
+}
+
+static struct undef_hook setend_hooks[] = {
+	{
+		.instr_mask	= 0xfffffdff,
+		.instr_val	= 0xf1010000,
+		.pstate_mask	= COMPAT_PSR_MODE_MASK,
+		.pstate_val	= COMPAT_PSR_MODE_USR,
+		.fn		= a32_setend_handler,
+	},
+	{
+		/* Thumb mode */
+		.instr_mask	= 0x0000fff7,
+		.instr_val	= 0x0000b650,
+		.pstate_mask	= (COMPAT_PSR_T_BIT | COMPAT_PSR_MODE_MASK),
+		.pstate_val	= (COMPAT_PSR_T_BIT | COMPAT_PSR_MODE_USR),
+		.fn		= t16_setend_handler,
+	},
+	{}
+};
+
+static struct insn_emulation_ops setend_ops = {
+	.name = "setend",
+	.status = INSN_DEPRECATED,
+	.hooks = setend_hooks,
+	.set_hw_mode = setend_set_hw_mode,
+};
+
+static int insn_cpu_hotplug_notify(struct notifier_block *b,
+			      unsigned long action, void *hcpu)
+{
+	int rc = 0;
+	if ((action & ~CPU_TASKS_FROZEN) == CPU_STARTING)
+		rc = run_all_insn_set_hw_mode((unsigned long)hcpu);
+
+	return notifier_from_errno(rc);
+}
+
+static struct notifier_block insn_cpu_hotplug_notifier = {
+	.notifier_call = insn_cpu_hotplug_notify,
+};
+
+/*
+ * Invoked as late_initcall, since not needed before init spawned.
+ */
+static int __init armv8_deprecated_init(void)
+{
+	if (IS_ENABLED(CONFIG_SWP_EMULATION))
+		register_insn_emulation(&swp_ops);
+
+	if (IS_ENABLED(CONFIG_CP15_BARRIER_EMULATION))
+		register_insn_emulation(&cp15_barrier_ops);
+
+	if (IS_ENABLED(CONFIG_SETEND_EMULATION)) {
+		if(system_supports_mixed_endian_el0())
+			register_insn_emulation(&setend_ops);
+		else
+			pr_info("setend instruction emulation is not supported on the system");
+	}
+
+	register_cpu_notifier(&insn_cpu_hotplug_notifier);
+	register_insn_emulation_sysctl(ctl_abi);
+
+	return 0;
+}
+
+late_initcall(armv8_deprecated_init);
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
new file mode 100644
index 00000000000..bbc710aafb3
--- /dev/null
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -0,0 +1,120 @@
+/*
+ * Contains CPU specific errata definitions
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt) "alternative: " fmt
+
+#include <linux/types.h>
+#include <asm/cpu.h>
+#include <asm/cputype.h>
+#include <asm/cpufeature.h>
+
+#define MIDR_CORTEX_A53 MIDR_CPU_PART(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
+#define MIDR_CORTEX_A57 MIDR_CPU_PART(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
+
+/*
+ * Add a struct or another datatype to the union below if you need
+ * different means to detect an affected CPU.
+ */
+struct arm64_cpu_capabilities {
+	const char *desc;
+	u16 capability;
+	bool (*is_affected)(struct arm64_cpu_capabilities *);
+	union {
+		struct {
+			u32 midr_model;
+			u32 midr_range_min, midr_range_max;
+		};
+	};
+};
+
+#define CPU_MODEL_MASK (MIDR_IMPLEMENTOR_MASK | MIDR_PARTNUM_MASK | \
+			MIDR_ARCHITECTURE_MASK)
+
+static bool __maybe_unused
+is_affected_midr_range(struct arm64_cpu_capabilities *entry)
+{
+	u32 midr = read_cpuid_id();
+
+	if ((midr & CPU_MODEL_MASK) != entry->midr_model)
+		return false;
+
+	midr &= MIDR_REVISION_MASK | MIDR_VARIANT_MASK;
+
+	return (midr >= entry->midr_range_min && midr <= entry->midr_range_max);
+}
+
+#define MIDR_RANGE(model, min, max) \
+	.is_affected = is_affected_midr_range, \
+	.midr_model = model, \
+	.midr_range_min = min, \
+	.midr_range_max = max
+
+struct arm64_cpu_capabilities arm64_errata[] = {
+#if	defined(CONFIG_ARM64_ERRATUM_826319) || \
+	defined(CONFIG_ARM64_ERRATUM_827319) || \
+	defined(CONFIG_ARM64_ERRATUM_824069)
+	{
+	/* Cortex-A53 r0p[012] */
+		.desc = "ARM errata 826319, 827319, 824069",
+		.capability = ARM64_WORKAROUND_CLEAN_CACHE,
+		MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x02),
+	},
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_819472
+	{
+	/* Cortex-A53 r0p[01] */
+		.desc = "ARM errata 819472",
+		.capability = ARM64_WORKAROUND_CLEAN_CACHE,
+		MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x01),
+	},
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_832075
+	{
+	/* Cortex-A57 r0p0 - r1p2 */
+		.desc = "ARM erratum 832075",
+		.capability = ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE,
+		MIDR_RANGE(MIDR_CORTEX_A57, 0x00,
+			   (1 << MIDR_VARIANT_SHIFT) | 2),
+	},
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_845719
+	{
+	/* Cortex-A53 r0p[01234] */
+		.desc = "ARM erratum 845719",
+		.capability = ARM64_WORKAROUND_845719,
+		MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x04),
+	},
+#endif
+	{
+	}
+};
+
+void check_local_cpu_errata(void)
+{
+	struct arm64_cpu_capabilities *cpus = arm64_errata;
+	int i;
+
+	for (i = 0; cpus[i].desc; i++) {
+		if (!cpus[i].is_affected(&cpus[i]))
+			continue;
+
+		if (!cpus_have_cap(cpus[i].capability))
+			pr_info("enabling workaround for %s\n", cpus[i].desc);
+		cpus_set_cap(cpus[i].capability);
+	}
+}
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 504fdaa8367..e86b9b42703 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -18,6 +18,7 @@
 #include <asm/cachetype.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
+#include <asm/cpufeature.h>
 
 #include <linux/bitops.h>
 #include <linux/bug.h>
@@ -34,6 +35,27 @@
  */
 DEFINE_PER_CPU(struct cpuinfo_arm64, cpu_data);
 static struct cpuinfo_arm64 boot_cpu_data;
+static bool mixed_endian_el0 = true;
+
+bool cpu_supports_mixed_endian_el0(void)
+{
+	return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1));
+}
+
+bool system_supports_mixed_endian_el0(void)
+{
+	return mixed_endian_el0;
+}
+
+static void update_mixed_endian_el0_support(struct cpuinfo_arm64 *info)
+{
+	mixed_endian_el0 &= id_aa64mmfr0_mixed_endian_el0(info->reg_id_aa64mmfr0);
+}
+
+static void update_cpu_features(struct cpuinfo_arm64 *info)
+{
+	update_mixed_endian_el0_support(info);
+}
 
 static char *icache_policy_str[] = {
 	[ICACHE_POLICY_RESERVED] = "RESERVED/UNKNOWN",
@@ -186,6 +208,9 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	info->reg_id_pfr1 = read_cpuid(ID_PFR1_EL1);
 
 	cpuinfo_detect_icache_policy(info);
+
+	check_local_cpu_errata();
+	update_cpu_features(info);
 }
 
 void cpuinfo_store_cpu(void)
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 95c49ebc660..1d85a7c5a85 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -327,6 +327,7 @@ void __init efi_idmap_init(void)
 
 	/* boot time idmap_pg_dir is incomplete, so fill in missing parts */
 	efi_setup_idmap();
+	early_memunmap(memmap.map, memmap.map_end - memmap.map);
 }
 
 static int __init remap_region(efi_memory_desc_t *md, void **new)
@@ -381,7 +382,6 @@ static int __init arm64_enter_virtual_mode(void)
 	}
 
 	mapsize = memmap.map_end - memmap.map;
-	early_memunmap(memmap.map, mapsize);
 
 	if (efi_runtime_disabled()) {
 		pr_info("EFI runtime services will be disabled.\n");
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 726b910fe6e..c19999ce2fb 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -21,8 +21,10 @@
 #include <linux/init.h>
 #include <linux/linkage.h>
 
+#include <asm/alternative-asm.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
+#include <asm/cpufeature.h>
 #include <asm/errno.h>
 #include <asm/esr.h>
 #include <asm/thread_info.h>
@@ -118,6 +120,24 @@
 	.if	\el == 0
 	ct_user_enter
 	ldr	x23, [sp, #S_SP]		// load return stack pointer
+
+#ifdef CONFIG_ARM64_ERRATUM_845719
+	alternative_insn						\
+	"nop",								\
+	"tbz x22, #4, 1f",						\
+	ARM64_WORKAROUND_845719
+#ifdef CONFIG_PID_IN_CONTEXTIDR
+	alternative_insn						\
+	"nop; nop",							\
+	"mrs x29, contextidr_el1; msr contextidr_el1, x29; 1:",		\
+	ARM64_WORKAROUND_845719
+#else
+	alternative_insn						\
+	"nop",								\
+	"msr contextidr_el1, xzr; 1:",					\
+	ARM64_WORKAROUND_845719
+#endif
+#endif
 	.endif
 	.if	\ret
 	ldr	x1, [sp, #S_X1]			// preserve x0 (syscall return)
@@ -455,8 +475,8 @@ el0_da:
 	bic	x0, x26, #(0xff << 56)
 	mov	x1, x25
 	mov	x2, sp
-	adr	lr, ret_to_user
-	b	do_mem_abort
+	bl	do_mem_abort
+	b	ret_to_user
 el0_ia:
 	/*
 	 * Instruction abort handling
@@ -468,8 +488,8 @@ el0_ia:
 	mov	x0, x26
 	orr	x1, x25, #1 << 24		// use reserved ISS bit for instruction aborts
 	mov	x2, sp
-	adr	lr, ret_to_user
-	b	do_mem_abort
+	bl	do_mem_abort
+	b	ret_to_user
 el0_fpsimd_acc:
 	/*
 	 * Floating Point or Advanced SIMD access
@@ -478,8 +498,8 @@ el0_fpsimd_acc:
 	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
-	adr	lr, ret_to_user
-	b	do_fpsimd_acc
+	bl	do_fpsimd_acc
+	b	ret_to_user
 el0_fpsimd_exc:
 	/*
 	 * Floating Point or Advanced SIMD exception
@@ -488,8 +508,8 @@ el0_fpsimd_exc:
 	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
-	adr	lr, ret_to_user
-	b	do_fpsimd_exc
+	bl	do_fpsimd_exc
+	b	ret_to_user
 el0_sp_pc:
 	/*
 	 * Stack or PC alignment exception handling
@@ -497,11 +517,12 @@ el0_sp_pc:
 	mrs	x26, far_el1
 	// enable interrupts before calling the main handler
 	enable_dbg_and_irq
+	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
 	mov	x2, sp
-	adr	lr, ret_to_user
-	b	do_sp_pc_abort
+	bl	do_sp_pc_abort
+	b	ret_to_user
 el0_undef:
 	/*
 	 * Undefined instruction
@@ -510,8 +531,8 @@ el0_undef:
 	enable_dbg_and_irq
 	ct_user_exit
 	mov	x0, sp
-	adr	lr, ret_to_user
-	b	do_undefinstr
+	bl	do_undefinstr
+	b	ret_to_user
 el0_dbg:
 	/*
 	 * Debug exception handling
@@ -530,8 +551,8 @@ el0_inv:
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
 	mrs	x2, esr_el1
-	adr	lr, ret_to_user
-	b	bad_mode
+	bl	bad_mode
+	b	ret_to_user
 ENDPROC(el0_sync)
 
 	.align	6
@@ -653,14 +674,15 @@ el0_svc_naked:					// compat entry point
 	ldr	x16, [tsk, #TI_FLAGS]		// check for syscall hooks
 	tst	x16, #_TIF_SYSCALL_WORK
 	b.ne	__sys_trace
-	adr	lr, ret_fast_syscall		// return address
 	cmp     scno, sc_nr                     // check upper syscall limit
 	b.hs	ni_sys
 	ldr	x16, [stbl, scno, lsl #3]	// address in the syscall table
-	br	x16				// call sys_* routine
+	blr	x16				// call sys_* routine
+	b	ret_fast_syscall
 ni_sys:
 	mov	x0, sp
-	b	do_ni_syscall
+	bl	do_ni_syscall
+	b	ret_fast_syscall
 ENDPROC(el0_svc)
 
 	/*
@@ -668,26 +690,38 @@ ENDPROC(el0_svc)
 	 * switches, and waiting for our parent to respond.
 	 */
 __sys_trace:
-	mov	x0, sp
+	mov	w0, #-1				// set default errno for
+	cmp     scno, x0			// user-issued syscall(-1)
+	b.ne	1f
+	mov	x0, #-ENOSYS
+	str	x0, [sp, #S_X0]
+1:	mov	x0, sp
 	bl	syscall_trace_enter
-	adr	lr, __sys_trace_return		// return address
+	cmp	w0, #-1				// skip the syscall?
+	b.eq	__sys_trace_return_skipped
 	uxtw	scno, w0			// syscall number (possibly new)
 	mov	x1, sp				// pointer to regs
 	cmp	scno, sc_nr			// check upper syscall limit
-	b.hs	ni_sys
+	b.hs	__ni_sys_trace
 	ldp	x0, x1, [sp]			// restore the syscall args
 	ldp	x2, x3, [sp, #S_X2]
 	ldp	x4, x5, [sp, #S_X4]
 	ldp	x6, x7, [sp, #S_X6]
 	ldr	x16, [stbl, scno, lsl #3]	// address in the syscall table
-	br	x16				// call sys_* routine
+	blr	x16				// call sys_* routine
 
 __sys_trace_return:
-	str	x0, [sp]			// save returned x0
+	str	x0, [sp, #S_X0]			// save returned x0
+__sys_trace_return_skipped:
 	mov	x0, sp
 	bl	syscall_trace_exit
 	b	ret_to_user
 
+__ni_sys_trace:
+	mov	x0, sp
+	bl	do_ni_syscall
+	b	__sys_trace_return
+
 /*
  * Special system call wrappers.
  */
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 8cd27fedc8b..7e9327a0986 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -960,3 +960,29 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
 
 	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift);
 }
+
+bool aarch32_insn_is_wide(u32 insn)
+{
+	return insn >= 0xe800;
+}
+
+/*
+ * Macros/defines for extracting register numbers from instruction.
+ */
+u32 aarch32_insn_extract_reg_num(u32 insn, int offset)
+{
+	return (insn & (0xf << offset)) >> offset;
+}
+
+#define OPC2_MASK	0x7
+#define OPC2_OFFSET	5
+u32 aarch32_insn_mcr_extract_opc2(u32 insn)
+{
+	return (insn & (OPC2_MASK << OPC2_OFFSET)) >> OPC2_OFFSET;
+}
+
+#define CRM_MASK	0xf
+u32 aarch32_insn_mcr_extract_crm(u32 insn)
+{
+	return insn & CRM_MASK;
+}
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index fde9923af85..07c4c53d750 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -163,6 +163,70 @@ void machine_restart(char *cmd)
 	while (1);
 }
 
+/*
+ * dump a block of kernel memory from around the given address
+ */
+static void show_data(unsigned long addr, int nbytes, const char *name)
+{
+	int	i, j;
+	int	nlines;
+	u32	*p;
+
+	/*
+	 * don't attempt to dump non-kernel addresses or
+	 * values that are probably just small negative numbers
+	 */
+	if (addr < PAGE_OFFSET || addr > -256UL)
+		return;
+
+	printk("\n%s: %#lx:\n", name, addr);
+
+	/*
+	 * round address down to a 32 bit boundary
+	 * and always dump a multiple of 32 bytes
+	 */
+	p = (u32 *)(addr & ~(sizeof(u32) - 1));
+	nbytes += (addr & (sizeof(u32) - 1));
+	nlines = (nbytes + 31) / 32;
+
+
+	for (i = 0; i < nlines; i++) {
+		/*
+		 * just display low 16 bits of address to keep
+		 * each line of the dump < 80 characters
+		 */
+		printk("%04lx ", (unsigned long)p & 0xffff);
+		for (j = 0; j < 8; j++) {
+			u32	data;
+			if (probe_kernel_address(p, data)) {
+				printk(" ********");
+			} else {
+				printk(" %08x", data);
+			}
+			++p;
+		}
+		printk("\n");
+	}
+}
+
+static void show_extra_register_data(struct pt_regs *regs, int nbytes)
+{
+	mm_segment_t fs;
+	unsigned int i;
+
+	fs = get_fs();
+	set_fs(KERNEL_DS);
+	show_data(regs->pc - nbytes, nbytes * 2, "PC");
+	show_data(regs->regs[30] - nbytes, nbytes * 2, "LR");
+	show_data(regs->sp - nbytes, nbytes * 2, "SP");
+	for (i = 0; i < 30; i++) {
+		char name[4];
+		snprintf(name, sizeof(name), "X%u", i);
+		show_data(regs->regs[i] - nbytes, nbytes * 2, name);
+	}
+	set_fs(fs);
+}
+
 void __show_regs(struct pt_regs *regs)
 {
 	int i, top_reg;
@@ -189,6 +253,8 @@ void __show_regs(struct pt_regs *regs)
 		if (i % 2 == 0)
 			printk("\n");
 	}
+	if (!user_mode(regs))
+		show_extra_register_data(regs, 128);
 	printk("\n");
 }
 
diff --git a/arch/arm64/kernel/psci-call.S b/arch/arm64/kernel/psci-call.S
new file mode 100644
index 00000000000..cf83e61cd3b
--- /dev/null
+++ b/arch/arm64/kernel/psci-call.S
@@ -0,0 +1,28 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2015 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#include <linux/linkage.h>
+
+/* int __invoke_psci_fn_hvc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */
+ENTRY(__invoke_psci_fn_hvc)
+	hvc	#0
+	ret
+ENDPROC(__invoke_psci_fn_hvc)
+
+/* int __invoke_psci_fn_smc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */
+ENTRY(__invoke_psci_fn_smc)
+	smc	#0
+	ret
+ENDPROC(__invoke_psci_fn_smc)
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 663da771580..81c081eaca4 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -57,6 +57,9 @@ static struct psci_operations psci_ops;
 static int (*invoke_psci_fn)(u64, u64, u64, u64);
 typedef int (*psci_initcall_t)(const struct device_node *);
 
+asmlinkage int __invoke_psci_fn_hvc(u64, u64, u64, u64);
+asmlinkage int __invoke_psci_fn_smc(u64, u64, u64, u64);
+
 enum psci_function {
 	PSCI_FN_CPU_SUSPEND,
 	PSCI_FN_CPU_ON,
@@ -109,40 +112,6 @@ static void psci_power_state_unpack(u32 power_state,
 			PSCI_0_2_POWER_STATE_AFFL_SHIFT;
 }
 
-/*
- * The following two functions are invoked via the invoke_psci_fn pointer
- * and will not be inlined, allowing us to piggyback on the AAPCS.
- */
-static noinline int __invoke_psci_fn_hvc(u64 function_id, u64 arg0, u64 arg1,
-					 u64 arg2)
-{
-	asm volatile(
-			__asmeq("%0", "x0")
-			__asmeq("%1", "x1")
-			__asmeq("%2", "x2")
-			__asmeq("%3", "x3")
-			"hvc	#0\n"
-		: "+r" (function_id)
-		: "r" (arg0), "r" (arg1), "r" (arg2));
-
-	return function_id;
-}
-
-static noinline int __invoke_psci_fn_smc(u64 function_id, u64 arg0, u64 arg1,
-					 u64 arg2)
-{
-	asm volatile(
-			__asmeq("%0", "x0")
-			__asmeq("%1", "x1")
-			__asmeq("%2", "x2")
-			__asmeq("%3", "x3")
-			"smc	#0\n"
-		: "+r" (function_id)
-		: "r" (arg0), "r" (arg1), "r" (arg2));
-
-	return function_id;
-}
-
 static int psci_get_version(void)
 {
 	int err;
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 8a4ae8e7321..d882b833dbd 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -27,6 +27,7 @@
 #include <linux/smp.h>
 #include <linux/ptrace.h>
 #include <linux/user.h>
+#include <linux/seccomp.h>
 #include <linux/security.h>
 #include <linux/init.h>
 #include <linux/signal.h>
@@ -551,6 +552,32 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset,
 	return ret;
 }
 
+static int system_call_get(struct task_struct *target,
+			   const struct user_regset *regset,
+			   unsigned int pos, unsigned int count,
+			   void *kbuf, void __user *ubuf)
+{
+	int syscallno = task_pt_regs(target)->syscallno;
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   &syscallno, 0, -1);
+}
+
+static int system_call_set(struct task_struct *target,
+			   const struct user_regset *regset,
+			   unsigned int pos, unsigned int count,
+			   const void *kbuf, const void __user *ubuf)
+{
+	int syscallno, ret;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &syscallno, 0, -1);
+	if (ret)
+		return ret;
+
+	task_pt_regs(target)->syscallno = syscallno;
+	return ret;
+}
+
 enum aarch64_regset {
 	REGSET_GPR,
 	REGSET_FPR,
@@ -559,6 +586,7 @@ enum aarch64_regset {
 	REGSET_HW_BREAK,
 	REGSET_HW_WATCH,
 #endif
+	REGSET_SYSTEM_CALL,
 };
 
 static const struct user_regset aarch64_regsets[] = {
@@ -608,6 +636,14 @@ static const struct user_regset aarch64_regsets[] = {
 		.set = hw_break_set,
 	},
 #endif
+	[REGSET_SYSTEM_CALL] = {
+		.core_note_type = NT_ARM_SYSTEM_CALL,
+		.n = 1,
+		.size = sizeof(int),
+		.align = sizeof(int),
+		.get = system_call_get,
+		.set = system_call_set,
+	},
 };
 
 static const struct user_regset_view user_aarch64_view = {
@@ -1114,6 +1150,10 @@ static void tracehook_report_syscall(struct pt_regs *regs,
 
 asmlinkage int syscall_trace_enter(struct pt_regs *regs)
 {
+	/* Do the secure computing check first; failures should be fast. */
+	if (secure_computing() == -1)
+		return -1;
+
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
 
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 2437196cc5d..ae8be923f2c 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -43,12 +43,14 @@
 #include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 #include <linux/efi.h>
+#include <linux/personality.h>
 
 #include <asm/fixmap.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/elf.h>
 #include <asm/cputable.h>
+#include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
@@ -72,13 +74,15 @@ EXPORT_SYMBOL_GPL(elf_hwcap);
 				 COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\
 				 COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\
 				 COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
-				 COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV)
+				 COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV|\
+				 COMPAT_HWCAP_LPAE)
 unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT;
 unsigned int compat_elf_hwcap2 __read_mostly;
 #endif
 
+DECLARE_BITMAP(cpu_hwcaps, NCAPS);
+
 static const char *cpu_name;
-static const char *machine_name;
 phys_addr_t __fdt_pointer __initdata;
 
 /*
@@ -311,7 +315,7 @@ static void __init setup_machine_fdt(phys_addr_t dt_phys)
 			cpu_relax();
 	}
 
-	machine_name = of_flat_dt_get_machine_name();
+	dump_stack_set_arch_desc("%s (DT)", of_flat_dt_get_machine_name());
 }
 
 /*
@@ -393,6 +397,7 @@ void __init setup_arch(char **cmdline_p)
 	request_standard_resources();
 
 	efi_idmap_init();
+	early_ioremap_reset();
 
 	unflatten_device_tree();
 
@@ -447,14 +452,50 @@ static const char *hwcap_str[] = {
 	NULL
 };
 
+#ifdef CONFIG_COMPAT
+static const char *compat_hwcap_str[] = {
+	"swp",
+	"half",
+	"thumb",
+	"26bit",
+	"fastmult",
+	"fpa",
+	"vfp",
+	"edsp",
+	"java",
+	"iwmmxt",
+	"crunch",
+	"thumbee",
+	"neon",
+	"vfpv3",
+	"vfpv3d16",
+	"tls",
+	"vfpv4",
+	"idiva",
+	"idivt",
+	"vfpd32",
+	"lpae",
+	"evtstrm"
+};
+
+static const char *compat_hwcap2_str[] = {
+	"aes",
+	"pmull",
+	"sha1",
+	"sha2",
+	"crc32",
+	NULL
+};
+#endif /* CONFIG_COMPAT */
+
 static int c_show(struct seq_file *m, void *v)
 {
-	int i;
-
-	seq_printf(m, "Processor\t: %s rev %d (%s)\n",
-		   cpu_name, read_cpuid_id() & 15, ELF_PLATFORM);
+	int i, j;
 
 	for_each_online_cpu(i) {
+		struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
+		u32 midr = cpuinfo->reg_midr;
+
 		/*
 		 * glibc reads /proc/cpuinfo to determine the number of
 		 * online processors, looking for lines beginning with
@@ -463,24 +504,38 @@ static int c_show(struct seq_file *m, void *v)
 #ifdef CONFIG_SMP
 		seq_printf(m, "processor\t: %d\n", i);
 #endif
-	}
-
-	/* dump out the processor features */
-	seq_puts(m, "Features\t: ");
-
-	for (i = 0; hwcap_str[i]; i++)
-		if (elf_hwcap & (1 << i))
-			seq_printf(m, "%s ", hwcap_str[i]);
-
-	seq_printf(m, "\nCPU implementer\t: 0x%02x\n", read_cpuid_id() >> 24);
-	seq_printf(m, "CPU architecture: AArch64\n");
-	seq_printf(m, "CPU variant\t: 0x%x\n", (read_cpuid_id() >> 20) & 15);
-	seq_printf(m, "CPU part\t: 0x%03x\n", (read_cpuid_id() >> 4) & 0xfff);
-	seq_printf(m, "CPU revision\t: %d\n", read_cpuid_id() & 15);
 
-	seq_puts(m, "\n");
-
-	seq_printf(m, "Hardware\t: %s\n", machine_name);
+		/*
+		 * Dump out the common processor features in a single line.
+		 * Userspace should read the hwcaps with getauxval(AT_HWCAP)
+		 * rather than attempting to parse this, but there's a body of
+		 * software which does already (at least for 32-bit).
+		 */
+		seq_puts(m, "Features\t:");
+		if (personality(current->personality) == PER_LINUX32) {
+#ifdef CONFIG_COMPAT
+			for (j = 0; compat_hwcap_str[j]; j++)
+				if (compat_elf_hwcap & (1 << j))
+					seq_printf(m, " %s", compat_hwcap_str[j]);
+
+			for (j = 0; compat_hwcap2_str[j]; j++)
+				if (compat_elf_hwcap2 & (1 << j))
+					seq_printf(m, " %s", compat_hwcap2_str[j]);
+#endif /* CONFIG_COMPAT */
+		} else {
+			for (j = 0; hwcap_str[j]; j++)
+				if (elf_hwcap & (1 << j))
+					seq_printf(m, " %s", hwcap_str[j]);
+		}
+		seq_puts(m, "\n");
+
+		seq_printf(m, "CPU implementer\t: 0x%02x\n",
+			   MIDR_IMPLEMENTOR(midr));
+		seq_printf(m, "CPU architecture: 8\n");
+		seq_printf(m, "CPU variant\t: 0x%x\n", MIDR_VARIANT(midr));
+		seq_printf(m, "CPU part\t: 0x%03x\n", MIDR_PARTNUM(midr));
+		seq_printf(m, "CPU revision\t: %d\n\n", MIDR_REVISION(midr));
+	}
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 1b9ad02837c..6acffecabea 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -154,8 +154,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 	case __SI_TIMER:
 		 err |= __put_user(from->si_tid, &to->si_tid);
 		 err |= __put_user(from->si_overrun, &to->si_overrun);
-		 err |= __put_user((compat_uptr_t)(unsigned long)from->si_ptr,
-				   &to->si_ptr);
+		 err |= __put_user(from->si_int, &to->si_int);
 		break;
 	case __SI_POLL:
 		err |= __put_user(from->si_band, &to->si_band);
@@ -184,7 +183,13 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 	case __SI_MESGQ: /* But this is */
 		err |= __put_user(from->si_pid, &to->si_pid);
 		err |= __put_user(from->si_uid, &to->si_uid);
-		err |= __put_user((compat_uptr_t)(unsigned long)from->si_ptr, &to->si_ptr);
+		err |= __put_user(from->si_int, &to->si_int);
+		break;
+	case __SI_SYS:
+		err |= __put_user((compat_uptr_t)(unsigned long)
+				from->si_call_addr, &to->si_call_addr);
+		err |= __put_user(from->si_syscall, &to->si_syscall);
+		err |= __put_user(from->si_arch, &to->si_arch);
 		break;
 	default: /* this is just in case for now ... */
 		err |= __put_user(from->si_pid, &to->si_pid);
@@ -434,7 +439,7 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 {
 	compat_ulong_t handler = ptr_to_compat(ka->sa.sa_handler);
 	compat_ulong_t retcode;
-	compat_ulong_t spsr = regs->pstate & ~PSR_f;
+	compat_ulong_t spsr = regs->pstate & ~(PSR_f | COMPAT_PSR_E_BIT);
 	int thumb;
 
 	/* Check if the handler is written for ARM or Thumb */
@@ -448,6 +453,9 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 	/* The IT state must be cleared for both ARM and Thumb-2 */
 	spsr &= ~COMPAT_PSR_IT_MASK;
 
+	/* Restore the original endianness */
+	spsr |= COMPAT_PSR_ENDSTATE;
+
 	if (ka->sa.sa_flags & SA_RESTORER) {
 		retcode = ptr_to_compat(ka->sa.sa_restorer);
 	} else {
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index a564b440416..ede186cdd45 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -147,14 +147,12 @@ cpu_resume_after_mmu:
 	ret
 ENDPROC(cpu_resume_after_mmu)
 
-	.data
 ENTRY(cpu_resume)
 	bl	el2_setup		// if in EL2 drop to EL1 cleanly
 #ifdef CONFIG_SMP
 	mrs	x1, mpidr_el1
-	adr	x4, mpidr_hash_ptr
-	ldr	x5, [x4]
-	add	x8, x4, x5		// x8 = struct mpidr_hash phys address
+	adrp	x8, mpidr_hash
+	add x8, x8, #:lo12:mpidr_hash // x8 = struct mpidr_hash phys address
         /* retrieve mpidr_hash members to compute the hash */
 	ldr	x2, [x8, #MPIDR_HASH_MASK]
 	ldp	w3, w4, [x8, #MPIDR_HASH_SHIFTS]
@@ -164,14 +162,15 @@ ENTRY(cpu_resume)
 #else
 	mov	x7, xzr
 #endif
-	adr	x0, sleep_save_sp
+	adrp	x0, sleep_save_sp
+	add	x0, x0, #:lo12:sleep_save_sp
 	ldr	x0, [x0, #SLEEP_SAVE_SP_PHYS]
 	ldr	x0, [x0, x7, lsl #3]
 	/* load sp from context */
 	ldr	x2, [x0, #CPU_CTX_SP]
-	adr	x1, sleep_idmap_phys
+	adrp	x1, sleep_idmap_phys
 	/* load physical address of identity map page table in x1 */
-	ldr	x1, [x1]
+	ldr	x1, [x1, #:lo12:sleep_idmap_phys]
 	mov	sp, x2
 	/*
 	 * cpu_do_resume expects x0 to contain context physical address
@@ -180,26 +179,3 @@ ENTRY(cpu_resume)
 	bl	cpu_do_resume		// PC relative jump, MMU off
 	b	cpu_resume_mmu		// Resume MMU, never returns
 ENDPROC(cpu_resume)
-
-	.align 3
-mpidr_hash_ptr:
-	/*
-	 * offset of mpidr_hash symbol from current location
-	 * used to obtain run-time mpidr_hash address with MMU off
-         */
-	.quad	mpidr_hash - .
-/*
- * physical address of identity mapped page tables
- */
-	.type	sleep_idmap_phys, #object
-ENTRY(sleep_idmap_phys)
-	.quad	0
-/*
- * struct sleep_save_sp {
- *	phys_addr_t *save_ptr_stash;
- *	phys_addr_t save_ptr_stash_phys;
- * };
- */
-	.type	sleep_save_sp, #object
-ENTRY(sleep_save_sp)
-	.space	SLEEP_SAVE_SP_SZ	// struct sleep_save_sp
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index b06d1d90ee8..0ef87896e4a 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -37,6 +37,7 @@
 #include <linux/of.h>
 #include <linux/irq_work.h>
 
+#include <asm/alternative.h>
 #include <asm/atomic.h>
 #include <asm/cacheflush.h>
 #include <asm/cpu.h>
@@ -309,6 +310,7 @@ void cpu_die(void)
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	pr_info("SMP: Total of %d processors activated.\n", num_online_cpus());
+	apply_alternatives();
 }
 
 void __init smp_prepare_boot_cpu(void)
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 13ad4dbb161..2d6b6065fe7 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -5,6 +5,7 @@
 #include <asm/debug-monitors.h>
 #include <asm/pgtable.h>
 #include <asm/memory.h>
+#include <asm/mmu_context.h>
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>
 #include <asm/tlbflush.h>
@@ -98,7 +99,18 @@ int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	 */
 	ret = __cpu_suspend_enter(arg, fn);
 	if (ret == 0) {
-		cpu_switch_mm(mm->pgd, mm);
+		/*
+		 * We are resuming from reset with TTBR0_EL1 set to the
+		 * idmap to enable the MMU; restore the active_mm mappings in
+		 * TTBR0_EL1 unless the active_mm == &init_mm, in which case
+		 * the thread entered __cpu_suspend with TTBR0_EL1 set to
+		 * reserved TTBR0 page tables and should be restored as such.
+		 */
+		if (mm == &init_mm)
+			cpu_set_reserved_ttbr0();
+		else
+			cpu_switch_mm(mm->pgd, mm);
+
 		flush_tlb_all();
 
 		/*
@@ -126,8 +138,8 @@ int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	return ret;
 }
 
-extern struct sleep_save_sp sleep_save_sp;
-extern phys_addr_t sleep_idmap_phys;
+struct sleep_save_sp sleep_save_sp;
+phys_addr_t sleep_idmap_phys;
 
 static int __init cpu_suspend_init(void)
 {
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index b6ee26b0939..4a59e6922e8 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -18,9 +18,11 @@
 #include <linux/node.h>
 #include <linux/nodemask.h>
 #include <linux/of.h>
+#include <linux/slab.h>
 #include <linux/sched.h>
 
 #include <asm/cputype.h>
+#include <asm/smp_plat.h>
 #include <asm/topology.h>
 
 static int __init get_cpu_for_node(struct device_node *node)
@@ -271,6 +273,126 @@ topology_populated:
 	update_siblings_masks(cpuid);
 }
 
+#ifdef CONFIG_SCHED_HMP
+
+/*
+ * Retrieve logical cpu index corresponding to a given MPIDR[23:0]
+ *  - mpidr: MPIDR[23:0] to be used for the look-up
+ *
+ * Returns the cpu logical index or -EINVAL on look-up error
+ */
+static inline int get_logical_index(u32 mpidr)
+{
+	int cpu;
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+		if (cpu_logical_map(cpu) == mpidr)
+			return cpu;
+	return -EINVAL;
+}
+
+static const char * const little_cores[] = {
+	"arm,cortex-a53",
+	NULL,
+};
+
+static bool is_little_cpu(struct device_node *cn)
+{
+	const char * const *lc;
+	for (lc = little_cores; *lc; lc++)
+		if (of_device_is_compatible(cn, *lc))
+			return true;
+	return false;
+}
+
+void __init arch_get_fast_and_slow_cpus(struct cpumask *fast,
+					struct cpumask *slow)
+{
+	struct device_node *cn = NULL;
+	int cpu;
+
+	cpumask_clear(fast);
+	cpumask_clear(slow);
+
+	/*
+	 * Use the config options if they are given. This helps testing
+	 * HMP scheduling on systems without a big.LITTLE architecture.
+	 */
+	if (strlen(CONFIG_HMP_FAST_CPU_MASK) && strlen(CONFIG_HMP_SLOW_CPU_MASK)) {
+		if (cpulist_parse(CONFIG_HMP_FAST_CPU_MASK, fast))
+			WARN(1, "Failed to parse HMP fast cpu mask!\n");
+		if (cpulist_parse(CONFIG_HMP_SLOW_CPU_MASK, slow))
+			WARN(1, "Failed to parse HMP slow cpu mask!\n");
+		return;
+	}
+
+	/*
+	 * Else, parse device tree for little cores.
+	 */
+	while ((cn = of_find_node_by_type(cn, "cpu"))) {
+
+		const u32 *mpidr;
+		int len;
+
+		mpidr = of_get_property(cn, "reg", &len);
+		if (!mpidr || len != 8) {
+			pr_err("%s missing reg property\n", cn->full_name);
+			continue;
+		}
+
+		cpu = get_logical_index(be32_to_cpup(mpidr+1));
+		if (cpu == -EINVAL) {
+			pr_err("couldn't get logical index for mpidr %x\n",
+							be32_to_cpup(mpidr+1));
+			break;
+		}
+
+		if (is_little_cpu(cn))
+			cpumask_set_cpu(cpu, slow);
+		else
+			cpumask_set_cpu(cpu, fast);
+	}
+
+	if (!cpumask_empty(fast) && !cpumask_empty(slow))
+		return;
+
+	/*
+	 * We didn't find both big and little cores so let's call all cores
+	 * fast as this will keep the system running, with all cores being
+	 * treated equal.
+	 */
+	cpumask_setall(fast);
+	cpumask_clear(slow);
+}
+
+struct cpumask hmp_slow_cpu_mask;
+
+void __init arch_get_hmp_domains(struct list_head *hmp_domains_list)
+{
+	struct cpumask hmp_fast_cpu_mask;
+	struct hmp_domain *domain;
+
+	arch_get_fast_and_slow_cpus(&hmp_fast_cpu_mask, &hmp_slow_cpu_mask);
+
+	/*
+	 * Initialize hmp_domains
+	 * Must be ordered with respect to compute capacity.
+	 * Fastest domain at head of list.
+	 */
+	if(!cpumask_empty(&hmp_slow_cpu_mask)) {
+		domain = (struct hmp_domain *)
+			kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+		cpumask_copy(&domain->possible_cpus, &hmp_slow_cpu_mask);
+		cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+		list_add(&domain->hmp_domains, hmp_domains_list);
+	}
+	domain = (struct hmp_domain *)
+		kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+	cpumask_copy(&domain->possible_cpus, &hmp_fast_cpu_mask);
+	cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+	list_add(&domain->hmp_domains, hmp_domains_list);
+}
+#endif /* CONFIG_SCHED_HMP */
+
 static void __init reset_cpu_topology(void)
 {
 	unsigned int cpu;
diff --git a/arch/arm64/kernel/trace-events-emulation.h b/arch/arm64/kernel/trace-events-emulation.h
new file mode 100644
index 00000000000..ae1dd598ea6
--- /dev/null
+++ b/arch/arm64/kernel/trace-events-emulation.h
@@ -0,0 +1,35 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM emulation
+
+#if !defined(_TRACE_EMULATION_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_EMULATION_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(instruction_emulation,
+
+	TP_PROTO(const char *instr, u64 addr),
+	TP_ARGS(instr, addr),
+
+	TP_STRUCT__entry(
+		__string(instr, instr)
+		__field(u64, addr)
+	),
+
+	TP_fast_assign(
+		__assign_str(instr, instr);
+		__entry->addr = addr;
+	),
+
+	TP_printk("instr=\"%s\" addr=0x%llx", __get_str(instr), __entry->addr)
+);
+
+#endif /* _TRACE_EMULATION_H */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH .
+
+#define TRACE_INCLUDE_FILE trace-events-emulation
+#include <trace/define_trace.h>
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index de1b085e796..0a801e3743d 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -259,6 +259,69 @@ void arm64_notify_die(const char *str, struct pt_regs *regs,
 	}
 }
 
+static LIST_HEAD(undef_hook);
+static DEFINE_RAW_SPINLOCK(undef_lock);
+
+void register_undef_hook(struct undef_hook *hook)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&undef_lock, flags);
+	list_add(&hook->node, &undef_hook);
+	raw_spin_unlock_irqrestore(&undef_lock, flags);
+}
+
+void unregister_undef_hook(struct undef_hook *hook)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&undef_lock, flags);
+	list_del(&hook->node);
+	raw_spin_unlock_irqrestore(&undef_lock, flags);
+}
+
+static int call_undef_hook(struct pt_regs *regs)
+{
+	struct undef_hook *hook;
+	unsigned long flags;
+	u32 instr;
+	int (*fn)(struct pt_regs *regs, u32 instr) = NULL;
+	void __user *pc = (void __user *)instruction_pointer(regs);
+
+	if (!user_mode(regs))
+		return 1;
+
+	if (compat_thumb_mode(regs)) {
+		/* 16-bit Thumb instruction */
+		if (get_user(instr, (u16 __user *)pc))
+			goto exit;
+		instr = le16_to_cpu(instr);
+		if (aarch32_insn_is_wide(instr)) {
+			u32 instr2;
+
+			if (get_user(instr2, (u16 __user *)(pc + 2)))
+				goto exit;
+			instr2 = le16_to_cpu(instr2);
+			instr = (instr << 16) | instr2;
+		}
+	} else {
+		/* 32-bit ARM instruction */
+		if (get_user(instr, (u32 __user *)pc))
+			goto exit;
+		instr = le32_to_cpu(instr);
+	}
+
+	raw_spin_lock_irqsave(&undef_lock, flags);
+	list_for_each_entry(hook, &undef_hook, node)
+		if ((instr & hook->instr_mask) == hook->instr_val &&
+			(regs->pstate & hook->pstate_mask) == hook->pstate_val)
+			fn = hook->fn;
+
+	raw_spin_unlock_irqrestore(&undef_lock, flags);
+exit:
+	return fn ? fn(regs, instr) : 1;
+}
+
 asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 {
 	siginfo_t info;
@@ -268,6 +331,9 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 	if (!aarch32_break_handler(regs))
 		return;
 
+	if (call_undef_hook(regs) == 0)
+		return;
+
 	if (show_unhandled_signals && unhandled_signal(current, SIGILL) &&
 	    printk_ratelimit()) {
 		pr_info("%s[%d]: undefined instruction: pc=%p\n",
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index ff3bddea482..f6fe17d88da 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -15,6 +15,10 @@ ccflags-y := -shared -fno-common -fno-builtin
 ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \
 		$(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
 
+# Workaround for bare-metal (ELF) toolchains that neglect to pass -shared
+# down to collect2, resulting in silent corruption of the vDSO image.
+ccflags-y += -Wl,-shared
+
 obj-y += vdso.o
 extra-y += vdso.lds vdso-offsets.h
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index edf8715ba39..2f600294e8c 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -100,6 +100,17 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
 
+	. = ALIGN(4);
+	.altinstructions : {
+		__alt_instructions = .;
+		*(.altinstructions)
+		__alt_instructions_end = .;
+	}
+	.altinstr_replacement : {
+		*(.altinstr_replacement)
+	}
+
+	. = ALIGN(PAGE_SIZE);
 	_data = .;
 	_sdata = .;
 	RW_DATA_SECTION(64, PAGE_SIZE, THREAD_SIZE)
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 76794692c20..84d5959ff87 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -38,7 +38,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
 	return 0;
 }
 
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index b72aa9f9215..a767f6a4ce5 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -1014,6 +1014,7 @@ ENTRY(__kvm_tlb_flush_vmid_ipa)
 	 * Instead, we invalidate Stage-2 for this IPA, and the
 	 * whole of Stage-1. Weep...
 	 */
+	lsr	x1, x1, #12
 	tlbi	ipas2e1is, x1
 	/*
 	 * We have to ensure completion of the invalidation at Stage-2,
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 70a7816535c..0b432657898 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -90,7 +90,6 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 			if (!cpu_has_32bit_el1())
 				return -EINVAL;
 			cpu_reset = &default_regs_reset32;
-			vcpu->arch.hcr_el2 &= ~HCR_RW;
 		} else {
 			cpu_reset = &default_regs_reset;
 		}
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 23663837acf..8eaf18577d7 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -20,6 +20,8 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <asm/assembler.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
 
 #include "proc-macros.S"
 
@@ -210,7 +212,7 @@ __dma_clean_range:
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
 	bic	x0, x0, x3
-1:	dc	cvac, x0			// clean D / U line
+1:	alternative_insn "dc cvac, x0", "dc civac, x0", ARM64_WORKAROUND_CLEAN_CACHE
 	add	x0, x0, x2
 	cmp	x0, x1
 	b.lo	1b
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index baa758d3702..76c1e6cd36f 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -92,6 +92,14 @@ static void reset_context(void *info)
 	unsigned int cpu = smp_processor_id();
 	struct mm_struct *mm = current->active_mm;
 
+	/*
+	 * current->active_mm could be init_mm for the idle thread immediately
+	 * after secondary CPU boot or hotplug. TTBR0_EL1 is already set to
+	 * the reserved value, so no need to reset any context.
+	 */
+	if (mm == &init_mm)
+		return;
+
 	smp_rmb();
 	asid = cpu_last_asid + cpu;
 
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index d9209420391..6efbb52cb92 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -51,7 +51,7 @@ static int __init early_coherent_pool(char *p)
 }
 early_param("coherent_pool", early_coherent_pool);
 
-static void *__alloc_from_pool(size_t size, struct page **ret_page)
+static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags)
 {
 	unsigned long val;
 	void *ptr = NULL;
@@ -67,6 +67,7 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page)
 
 		*ret_page = phys_to_page(phys);
 		ptr = (void *)val;
+		memset(ptr, 0, size);
 	}
 
 	return ptr;
@@ -101,6 +102,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size,
 		flags |= GFP_DMA;
 	if (IS_ENABLED(CONFIG_DMA_CMA) && (flags & __GFP_WAIT)) {
 		struct page *page;
+		void *addr;
 
 		size = PAGE_ALIGN(size);
 		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
@@ -109,7 +111,9 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size,
 			return NULL;
 
 		*dma_handle = phys_to_dma(dev, page_to_phys(page));
-		return page_address(page);
+		addr = page_address(page);
+		memset(addr, 0, size);
+		return addr;
 	} else {
 		return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
 	}
@@ -145,7 +149,7 @@ static void *__dma_alloc_noncoherent(struct device *dev, size_t size,
 
 	if (!(flags & __GFP_WAIT)) {
 		struct page *page = NULL;
-		void *addr = __alloc_from_pool(size, &page);
+		void *addr = __alloc_from_pool(size, &page, flags);
 
 		if (addr)
 			*dma_handle = phys_to_dma(dev, page_to_phys(page));
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 023747bf4dd..0eeb4f0930a 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -38,21 +38,15 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 }
 #endif
 
-struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
-			      int write)
-{
-	return ERR_PTR(-EINVAL);
-}
-
 int pmd_huge(pmd_t pmd)
 {
-	return !(pmd_val(pmd) & PMD_TABLE_BIT);
+	return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
 }
 
 int pud_huge(pud_t pud)
 {
 #ifndef __PAGETABLE_PMD_FOLDED
-	return !(pud_val(pud) & PUD_TABLE_BIT);
+	return pud_val(pud) && !(pud_val(pud) & PUD_TABLE_BIT);
 #else
 	return 0;
 #endif
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 494297c698c..b45b31397d0 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -39,6 +39,7 @@
 #include <asm/setup.h>
 #include <asm/sizes.h>
 #include <asm/tlb.h>
+#include <asm/alternative.h>
 
 #include "mm.h"
 
@@ -113,9 +114,11 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 }
 
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
+#define PFN_MASK ((1UL << (64 - PAGE_SHIFT)) - 1)
+
 int pfn_valid(unsigned long pfn)
 {
-	return memblock_is_memory(pfn << PAGE_SHIFT);
+	return (pfn & PFN_MASK) == pfn && memblock_is_memory(pfn << PAGE_SHIFT);
 }
 EXPORT_SYMBOL(pfn_valid);
 #endif
@@ -237,7 +240,7 @@ static void __init free_unused_memmap(void)
 		 * memmap entries are valid from the bank end aligned to
 		 * MAX_ORDER_NR_PAGES.
 		 */
-		prev_end = ALIGN(start + __phys_to_pfn(reg->size),
+		prev_end = ALIGN(__phys_to_pfn(reg->base + reg->size),
 				 MAX_ORDER_NR_PAGES);
 	}
 
@@ -325,6 +328,7 @@ void __init mem_init(void)
 void free_initmem(void)
 {
 	free_initmem_default(0);
+	free_alternatives_memory();
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -333,14 +337,8 @@ static int keep_initrd;
 
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	if (!keep_initrd) {
-		if (start == initrd_start)
-			start = round_down(start, PAGE_SIZE);
-		if (end == initrd_end)
-			end = round_up(end, PAGE_SIZE);
-
+	if (!keep_initrd)
 		free_reserved_area((void *)start, (void *)end, 0, "initrd");
-	}
 }
 
 static int __init keepinitrd_setup(char *__unused)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 41f1e3e2ea2..dc6a4842683 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -60,7 +60,7 @@ struct jit_ctx {
 	const struct bpf_prog *prog;
 	int idx;
 	int tmp_used;
-	int body_offset;
+	int epilogue_offset;
 	int *offset;
 	u32 *image;
 };
@@ -130,8 +130,8 @@ static void jit_fill_hole(void *area, unsigned int size)
 
 static inline int epilogue_offset(const struct jit_ctx *ctx)
 {
-	int to = ctx->offset[ctx->prog->len - 1];
-	int from = ctx->idx - ctx->body_offset;
+	int to = ctx->epilogue_offset;
+	int from = ctx->idx;
 
 	return to - from;
 }
@@ -463,6 +463,8 @@ emit_cond_jmp:
 	}
 	/* function return */
 	case BPF_JMP | BPF_EXIT:
+		/* Optimization: when last instruction is EXIT,
+		   simply fallthrough to epilogue. */
 		if (i == ctx->prog->len - 1)
 			break;
 		jmp_offset = epilogue_offset(ctx);
@@ -485,7 +487,7 @@ emit_cond_jmp:
 			return -EINVAL;
 		}
 
-		imm64 = (u64)insn1.imm << 32 | imm;
+		imm64 = (u64)insn1.imm << 32 | (u32)imm;
 		emit_a64_mov_i64(dst, imm64, ctx);
 
 		return 1;
@@ -685,11 +687,13 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
 
 	/* 1. Initial fake pass to compute ctx->idx. */
 
-	/* Fake pass to fill in ctx->offset. */
+	/* Fake pass to fill in ctx->offset and ctx->tmp_used. */
 	if (build_body(&ctx))
 		goto out;
 
 	build_prologue(&ctx);
+
+	ctx.epilogue_offset = ctx.idx;
 	build_epilogue(&ctx);
 
 	/* Now we know the actual image size. */
@@ -706,7 +710,6 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
 
 	build_prologue(&ctx);
 
-	ctx.body_offset = ctx.idx;
 	if (build_body(&ctx)) {
 		bpf_jit_binary_free(header);
 		goto out;
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index 0eca9332719..d223a8b57c1 100644
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -142,6 +142,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/c6x/kernel/time.c b/arch/c6x/kernel/time.c
index 356ee84cad9..04845aaf598 100644
--- a/arch/c6x/kernel/time.c
+++ b/arch/c6x/kernel/time.c
@@ -49,7 +49,7 @@ u64 sched_clock(void)
 	return (tsc * sched_clock_multiplier) >> SCHED_CLOCK_SHIFT;
 }
 
-void time_init(void)
+void __init time_init(void)
 {
 	u64 tmp = (u64)NSEC_PER_SEC << SCHED_CLOCK_SHIFT;
 
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index 1790f22e71a..2686a7aa8ec 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -176,6 +176,8 @@ retry:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index 9a66372fc7c..ec4917ddf67 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -168,6 +168,8 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 7225dad8709..ba5ba7accd0 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -172,6 +172,8 @@ retry:
 		 */
 		if (fault & VM_FAULT_OOM) {
 			goto out_of_memory;
+		} else if (fault & VM_FAULT_SIGSEGV) {
+			goto bad_area;
 		} else if (fault & VM_FAULT_SIGBUS) {
 			signal = SIGBUS;
 			goto bad_area;
diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c
index 76069c18ee4..52b7604b521 100644
--- a/arch/ia64/mm/hugetlbpage.c
+++ b/arch/ia64/mm/hugetlbpage.c
@@ -114,12 +114,6 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
-struct page *
-follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write)
-{
-	return NULL;
-}
-
 void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 			unsigned long addr, unsigned long end,
 			unsigned long floor, unsigned long ceiling)
diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index e9c6a8014bd..e3d4d489010 100644
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -200,6 +200,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index 2bd7487440c..b2f04aee46e 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -145,6 +145,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto map_err;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto bus_err;
 		BUG();
diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h
index 881071c0794..13272fd5a5b 100644
--- a/arch/metag/include/asm/processor.h
+++ b/arch/metag/include/asm/processor.h
@@ -149,8 +149,8 @@ extern void exit_thread(void);
 
 unsigned long get_wchan(struct task_struct *p);
 
-#define	KSTK_EIP(tsk)	((tsk)->thread.kernel_context->CurrPC)
-#define	KSTK_ESP(tsk)	((tsk)->thread.kernel_context->AX[0].U0)
+#define	KSTK_EIP(tsk)	(task_pt_regs(tsk)->ctx.CurrPC)
+#define	KSTK_ESP(tsk)	(task_pt_regs(tsk)->ctx.AX[0].U0)
 
 #define user_stack_pointer(regs)        ((regs)->ctx.AX[0].U0)
 
diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c
index 332680e5ebf..2de5dc695a8 100644
--- a/arch/metag/mm/fault.c
+++ b/arch/metag/mm/fault.c
@@ -141,6 +141,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/metag/mm/hugetlbpage.c b/arch/metag/mm/hugetlbpage.c
index 3c32075d294..7ca80ac42ed 100644
--- a/arch/metag/mm/hugetlbpage.c
+++ b/arch/metag/mm/hugetlbpage.c
@@ -94,12 +94,6 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 	return 0;
 }
 
-struct page *follow_huge_addr(struct mm_struct *mm,
-			      unsigned long address, int write)
-{
-	return ERR_PTR(-EINVAL);
-}
-
 int pmd_huge(pmd_t pmd)
 {
 	return pmd_page_shift(pmd) > PAGE_SHIFT;
diff --git a/arch/microblaze/include/asm/tlb.h b/arch/microblaze/include/asm/tlb.h
index 8aa97817cc8..99b6ded5484 100644
--- a/arch/microblaze/include/asm/tlb.h
+++ b/arch/microblaze/include/asm/tlb.h
@@ -14,7 +14,6 @@
 #define tlb_flush(tlb)	flush_tlb_mm((tlb)->mm)
 
 #include <linux/pagemap.h>
-#include <asm-generic/tlb.h>
 
 #ifdef CONFIG_MMU
 #define tlb_start_vma(tlb, vma)		do { } while (0)
@@ -22,4 +21,6 @@
 #define __tlb_remove_tlb_entry(tlb, pte, address) do { } while (0)
 #endif
 
+#include <asm-generic/tlb.h>
+
 #endif /* _ASM_MICROBLAZE_TLB_H */
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index fa4cf52aa7a..d46a5ebb757 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -224,6 +224,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 9536ef912f5..155bb7f5ad2 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2048,7 +2048,7 @@ config MIPS_CMP
 
 config MIPS_CPS
 	bool "MIPS Coherent Processing System support"
-	depends on SYS_SUPPORTS_MIPS_CPS
+	depends on SYS_SUPPORTS_MIPS_CPS && !64BIT
 	select MIPS_CM
 	select MIPS_CPC
 	select MIPS_CPS_PM if HOTPLUG_CPU
diff --git a/arch/mips/alchemy/common/clock.c b/arch/mips/alchemy/common/clock.c
index d7557cde271..3fff11ec7dc 100644
--- a/arch/mips/alchemy/common/clock.c
+++ b/arch/mips/alchemy/common/clock.c
@@ -128,6 +128,8 @@ static unsigned long alchemy_clk_cpu_recalc(struct clk_hw *hw,
 		t = 396000000;
 	else {
 		t = alchemy_rdsys(AU1000_SYS_CPUPLL) & 0x7f;
+		if (alchemy_get_cputype() < ALCHEMY_CPU_AU1300)
+			t &= 0x3f;
 		t *= parent_rate;
 	}
 
diff --git a/arch/mips/bcm47xx/board.c b/arch/mips/bcm47xx/board.c
index b3ae068ca4f..3fd369d7444 100644
--- a/arch/mips/bcm47xx/board.c
+++ b/arch/mips/bcm47xx/board.c
@@ -247,8 +247,8 @@ static __init const struct bcm47xx_board_type *bcm47xx_board_get_nvram(void)
 	}
 
 	if (bcm47xx_nvram_getenv("hardware_version", buf1, sizeof(buf1)) >= 0 &&
-	    bcm47xx_nvram_getenv("boardtype", buf2, sizeof(buf2)) >= 0) {
-		for (e2 = bcm47xx_board_list_boot_hw; e2->value1; e2++) {
+	    bcm47xx_nvram_getenv("boardnum", buf2, sizeof(buf2)) >= 0) {
+		for (e2 = bcm47xx_board_list_hw_version_num; e2->value1; e2++) {
 			if (!strstarts(buf1, e2->value1) &&
 			    !strcmp(buf2, e2->value2))
 				return &e2->board;
diff --git a/arch/mips/bcm63xx/prom.c b/arch/mips/bcm63xx/prom.c
index e1f27d653f6..7019e296700 100644
--- a/arch/mips/bcm63xx/prom.c
+++ b/arch/mips/bcm63xx/prom.c
@@ -17,7 +17,6 @@
 #include <bcm63xx_cpu.h>
 #include <bcm63xx_io.h>
 #include <bcm63xx_regs.h>
-#include <bcm63xx_gpio.h>
 
 void __init prom_init(void)
 {
@@ -53,9 +52,6 @@ void __init prom_init(void)
 	reg &= ~mask;
 	bcm_perf_writel(reg, PERF_CKCTL_REG);
 
-	/* register gpiochip */
-	bcm63xx_gpio_init();
-
 	/* do low level board init */
 	board_prom_init();
 
diff --git a/arch/mips/bcm63xx/setup.c b/arch/mips/bcm63xx/setup.c
index 6660c7ddf87..240fb4ffa55 100644
--- a/arch/mips/bcm63xx/setup.c
+++ b/arch/mips/bcm63xx/setup.c
@@ -20,6 +20,7 @@
 #include <bcm63xx_cpu.h>
 #include <bcm63xx_regs.h>
 #include <bcm63xx_io.h>
+#include <bcm63xx_gpio.h>
 
 void bcm63xx_machine_halt(void)
 {
@@ -160,6 +161,9 @@ void __init plat_mem_setup(void)
 
 int __init bcm63xx_register_devices(void)
 {
+	/* register gpiochip */
+	bcm63xx_gpio_init();
+
 	return board_register_devices();
 }
 
diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index 02f24447520..c76a289b95b 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -306,7 +306,7 @@ void __init plat_swiotlb_setup(void)
 		swiotlbsize = 64 * (1<<20);
 	}
 #endif
-#ifdef CONFIG_USB_OCTEON_OHCI
+#ifdef CONFIG_USB_OHCI_HCD_PLATFORM
 	/* OCTEON II ohci is only 32-bit. */
 	if (OCTEON_IS_MODEL(OCTEON_CN6XXX) && max_addr >= 0x100000000ul)
 		swiotlbsize = 64 * (1<<20);
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index ecd903dd1c4..8b1eeffa12e 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -240,9 +240,7 @@ static int octeon_cpu_disable(void)
 
 	set_cpu_online(cpu, false);
 	cpu_clear(cpu, cpu_callin_map);
-	local_irq_disable();
 	octeon_fixup_irqs();
-	local_irq_enable();
 
 	flush_cache_all();
 	local_flush_tlb_all();
diff --git a/arch/mips/include/asm/asm-eva.h b/arch/mips/include/asm/asm-eva.h
index e41c56e375b..1e38f0e1ea3 100644
--- a/arch/mips/include/asm/asm-eva.h
+++ b/arch/mips/include/asm/asm-eva.h
@@ -11,6 +11,36 @@
 #define __ASM_ASM_EVA_H
 
 #ifndef __ASSEMBLY__
+
+/* Kernel variants */
+
+#define kernel_cache(op, base)		"cache " op ", " base "\n"
+#define kernel_ll(reg, addr)		"ll " reg ", " addr "\n"
+#define kernel_sc(reg, addr)		"sc " reg ", " addr "\n"
+#define kernel_lw(reg, addr)		"lw " reg ", " addr "\n"
+#define kernel_lwl(reg, addr)		"lwl " reg ", " addr "\n"
+#define kernel_lwr(reg, addr)		"lwr " reg ", " addr "\n"
+#define kernel_lh(reg, addr)		"lh " reg ", " addr "\n"
+#define kernel_lb(reg, addr)		"lb " reg ", " addr "\n"
+#define kernel_lbu(reg, addr)		"lbu " reg ", " addr "\n"
+#define kernel_sw(reg, addr)		"sw " reg ", " addr "\n"
+#define kernel_swl(reg, addr)		"swl " reg ", " addr "\n"
+#define kernel_swr(reg, addr)		"swr " reg ", " addr "\n"
+#define kernel_sh(reg, addr)		"sh " reg ", " addr "\n"
+#define kernel_sb(reg, addr)		"sb " reg ", " addr "\n"
+
+#ifdef CONFIG_32BIT
+/*
+ * No 'sd' or 'ld' instructions in 32-bit but the code will
+ * do the correct thing
+ */
+#define kernel_sd(reg, addr)		user_sw(reg, addr)
+#define kernel_ld(reg, addr)		user_lw(reg, addr)
+#else
+#define kernel_sd(reg, addr)		"sd " reg", " addr "\n"
+#define kernel_ld(reg, addr)		"ld " reg", " addr "\n"
+#endif /* CONFIG_32BIT */
+
 #ifdef CONFIG_EVA
 
 #define __BUILD_EVA_INSN(insn, reg, addr)				\
@@ -41,37 +71,60 @@
 
 #else
 
-#define user_cache(op, base)		"cache " op ", " base "\n"
-#define user_ll(reg, addr)		"ll " reg ", " addr "\n"
-#define user_sc(reg, addr)		"sc " reg ", " addr "\n"
-#define user_lw(reg, addr)		"lw " reg ", " addr "\n"
-#define user_lwl(reg, addr)		"lwl " reg ", " addr "\n"
-#define user_lwr(reg, addr)		"lwr " reg ", " addr "\n"
-#define user_lh(reg, addr)		"lh " reg ", " addr "\n"
-#define user_lb(reg, addr)		"lb " reg ", " addr "\n"
-#define user_lbu(reg, addr)		"lbu " reg ", " addr "\n"
-#define user_sw(reg, addr)		"sw " reg ", " addr "\n"
-#define user_swl(reg, addr)		"swl " reg ", " addr "\n"
-#define user_swr(reg, addr)		"swr " reg ", " addr "\n"
-#define user_sh(reg, addr)		"sh " reg ", " addr "\n"
-#define user_sb(reg, addr)		"sb " reg ", " addr "\n"
+#define user_cache(op, base)		kernel_cache(op, base)
+#define user_ll(reg, addr)		kernel_ll(reg, addr)
+#define user_sc(reg, addr)		kernel_sc(reg, addr)
+#define user_lw(reg, addr)		kernel_lw(reg, addr)
+#define user_lwl(reg, addr)		kernel_lwl(reg, addr)
+#define user_lwr(reg, addr)		kernel_lwr(reg, addr)
+#define user_lh(reg, addr)		kernel_lh(reg, addr)
+#define user_lb(reg, addr)		kernel_lb(reg, addr)
+#define user_lbu(reg, addr)		kernel_lbu(reg, addr)
+#define user_sw(reg, addr)		kernel_sw(reg, addr)
+#define user_swl(reg, addr)		kernel_swl(reg, addr)
+#define user_swr(reg, addr)		kernel_swr(reg, addr)
+#define user_sh(reg, addr)		kernel_sh(reg, addr)
+#define user_sb(reg, addr)		kernel_sb(reg, addr)
 
 #ifdef CONFIG_32BIT
-/*
- * No 'sd' or 'ld' instructions in 32-bit but the code will
- * do the correct thing
- */
-#define user_sd(reg, addr)		user_sw(reg, addr)
-#define user_ld(reg, addr)		user_lw(reg, addr)
+#define user_sd(reg, addr)		kernel_sw(reg, addr)
+#define user_ld(reg, addr)		kernel_lw(reg, addr)
 #else
-#define user_sd(reg, addr)		"sd " reg", " addr "\n"
-#define user_ld(reg, addr)		"ld " reg", " addr "\n"
+#define user_sd(reg, addr)		kernel_sd(reg, addr)
+#define user_ld(reg, addr)		kernel_ld(reg, addr)
 #endif /* CONFIG_32BIT */
 
 #endif /* CONFIG_EVA */
 
 #else /* __ASSEMBLY__ */
 
+#define kernel_cache(op, base)		cache op, base
+#define kernel_ll(reg, addr)		ll reg, addr
+#define kernel_sc(reg, addr)		sc reg, addr
+#define kernel_lw(reg, addr)		lw reg, addr
+#define kernel_lwl(reg, addr)		lwl reg, addr
+#define kernel_lwr(reg, addr)		lwr reg, addr
+#define kernel_lh(reg, addr)		lh reg, addr
+#define kernel_lb(reg, addr)		lb reg, addr
+#define kernel_lbu(reg, addr)		lbu reg, addr
+#define kernel_sw(reg, addr)		sw reg, addr
+#define kernel_swl(reg, addr)		swl reg, addr
+#define kernel_swr(reg, addr)		swr reg, addr
+#define kernel_sh(reg, addr)		sh reg, addr
+#define kernel_sb(reg, addr)		sb reg, addr
+
+#ifdef CONFIG_32BIT
+/*
+ * No 'sd' or 'ld' instructions in 32-bit but the code will
+ * do the correct thing
+ */
+#define kernel_sd(reg, addr)		user_sw(reg, addr)
+#define kernel_ld(reg, addr)		user_lw(reg, addr)
+#else
+#define kernel_sd(reg, addr)		sd reg, addr
+#define kernel_ld(reg, addr)		ld reg, addr
+#endif /* CONFIG_32BIT */
+
 #ifdef CONFIG_EVA
 
 #define __BUILD_EVA_INSN(insn, reg, addr)			\
@@ -101,31 +154,27 @@
 #define user_sd(reg, addr)		user_sw(reg, addr)
 #else
 
-#define user_cache(op, base)		cache op, base
-#define user_ll(reg, addr)		ll reg, addr
-#define user_sc(reg, addr)		sc reg, addr
-#define user_lw(reg, addr)		lw reg, addr
-#define user_lwl(reg, addr)		lwl reg, addr
-#define user_lwr(reg, addr)		lwr reg, addr
-#define user_lh(reg, addr)		lh reg, addr
-#define user_lb(reg, addr)		lb reg, addr
-#define user_lbu(reg, addr)		lbu reg, addr
-#define user_sw(reg, addr)		sw reg, addr
-#define user_swl(reg, addr)		swl reg, addr
-#define user_swr(reg, addr)		swr reg, addr
-#define user_sh(reg, addr)		sh reg, addr
-#define user_sb(reg, addr)		sb reg, addr
+#define user_cache(op, base)		kernel_cache(op, base)
+#define user_ll(reg, addr)		kernel_ll(reg, addr)
+#define user_sc(reg, addr)		kernel_sc(reg, addr)
+#define user_lw(reg, addr)		kernel_lw(reg, addr)
+#define user_lwl(reg, addr)		kernel_lwl(reg, addr)
+#define user_lwr(reg, addr)		kernel_lwr(reg, addr)
+#define user_lh(reg, addr)		kernel_lh(reg, addr)
+#define user_lb(reg, addr)		kernel_lb(reg, addr)
+#define user_lbu(reg, addr)		kernel_lbu(reg, addr)
+#define user_sw(reg, addr)		kernel_sw(reg, addr)
+#define user_swl(reg, addr)		kernel_swl(reg, addr)
+#define user_swr(reg, addr)		kernel_swr(reg, addr)
+#define user_sh(reg, addr)		kernel_sh(reg, addr)
+#define user_sb(reg, addr)		kernel_sb(reg, addr)
 
 #ifdef CONFIG_32BIT
-/*
- * No 'sd' or 'ld' instructions in 32-bit but the code will
- * do the correct thing
- */
-#define user_sd(reg, addr)		user_sw(reg, addr)
-#define user_ld(reg, addr)		user_lw(reg, addr)
+#define user_sd(reg, addr)		kernel_sw(reg, addr)
+#define user_ld(reg, addr)		kernel_lw(reg, addr)
 #else
-#define user_sd(reg, addr)		sd reg, addr
-#define user_ld(reg, addr)		ld reg, addr
+#define user_sd(reg, addr)		kernel_sd(reg, addr)
+#define user_ld(reg, addr)		kernel_sd(reg, addr)
 #endif /* CONFIG_32BIT */
 
 #endif /* CONFIG_EVA */
diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index 6caf8766b80..71fef0af9c9 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -304,7 +304,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	add	$1, \base, \off
+	addu	$1, \base, \off
 	.word	LDD_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@@ -313,7 +313,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	add	$1, \base, \off
+	addu	$1, \base, \off
 	.word	STD_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
diff --git a/arch/mips/include/asm/cpu-info.h b/arch/mips/include/asm/cpu-info.h
index a6c9ccb33c5..c3f4f2d2e10 100644
--- a/arch/mips/include/asm/cpu-info.h
+++ b/arch/mips/include/asm/cpu-info.h
@@ -84,6 +84,11 @@ struct cpuinfo_mips {
 	 * (shifted by _CACHE_SHIFT)
 	 */
 	unsigned int		writecombine;
+	/*
+	 * Simple counter to prevent enabling HTW in nested
+	 * htw_start/htw_stop calls
+	 */
+	unsigned int		htw_seq;
 } __attribute__((aligned(SMP_CACHE_BYTES)));
 
 extern struct cpuinfo_mips cpu_data[];
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index dd562414cd5..99f71e87ce3 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -150,6 +150,7 @@ static inline void lose_fpu(int save)
 		}
 		disable_msa();
 		clear_thread_flag(TIF_USEDMSA);
+		__disable_fpu();
 	} else if (is_fpu_owner()) {
 		if (save)
 			_save_fp(current);
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index f2c249796ea..4e3205a3bee 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -321,6 +321,7 @@ enum mips_mmu_types {
 #define T_TRAP			13	/* Trap instruction */
 #define T_VCEI			14	/* Virtual coherency exception */
 #define T_FPE			15	/* Floating point exception */
+#define T_MSADIS		21	/* MSA disabled exception */
 #define T_WATCH			23	/* Watch address reference */
 #define T_VCED			31	/* Virtual coherency data */
 
@@ -577,6 +578,7 @@ struct kvm_mips_callbacks {
 	int (*handle_syscall)(struct kvm_vcpu *vcpu);
 	int (*handle_res_inst)(struct kvm_vcpu *vcpu);
 	int (*handle_break)(struct kvm_vcpu *vcpu);
+	int (*handle_msa_disabled)(struct kvm_vcpu *vcpu);
 	int (*vm_init)(struct kvm *kvm);
 	int (*vcpu_init)(struct kvm_vcpu *vcpu);
 	int (*vcpu_setup)(struct kvm_vcpu *vcpu);
diff --git a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h
index fa1f3cfbae8..d68e685cde6 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h
@@ -50,7 +50,6 @@
 #define cpu_has_mips32r2	0
 #define cpu_has_mips64r1	0
 #define cpu_has_mips64r2	1
-#define cpu_has_mips_r2_exec_hazard 0
 #define cpu_has_dsp		0
 #define cpu_has_dsp2		0
 #define cpu_has_mipsmt		0
diff --git a/arch/mips/include/asm/mach-generic/spaces.h b/arch/mips/include/asm/mach-generic/spaces.h
index 9488fa5f886..afc96ecb900 100644
--- a/arch/mips/include/asm/mach-generic/spaces.h
+++ b/arch/mips/include/asm/mach-generic/spaces.h
@@ -94,7 +94,11 @@
 #endif
 
 #ifndef FIXADDR_TOP
+#ifdef CONFIG_KVM_GUEST
+#define FIXADDR_TOP		((unsigned long)(long)(int)0x7ffe0000)
+#else
 #define FIXADDR_TOP		((unsigned long)(long)(int)0xfffe0000)
 #endif
+#endif
 
 #endif /* __ASM_MACH_GENERIC_SPACES_H */
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 22a135ac91d..f38ca68285e 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -1343,12 +1343,27 @@ do {									\
 	__res;								\
 })
 
+#define _write_32bit_cp1_register(dest, val, gas_hardfloat)		\
+do {									\
+	__asm__ __volatile__(						\
+	"	.set	push					\n"	\
+	"	.set	reorder					\n"	\
+	"	"STR(gas_hardfloat)"				\n"	\
+	"	ctc1	%0,"STR(dest)"				\n"	\
+	"	.set	pop					\n"	\
+	: : "r" (val));							\
+} while (0)
+
 #ifdef GAS_HAS_SET_HARDFLOAT
 #define read_32bit_cp1_register(source)					\
 	_read_32bit_cp1_register(source, .set hardfloat)
+#define write_32bit_cp1_register(dest, val)				\
+	_write_32bit_cp1_register(dest, val, .set hardfloat)
 #else
 #define read_32bit_cp1_register(source)					\
 	_read_32bit_cp1_register(source, )
+#define write_32bit_cp1_register(dest, val)				\
+	_write_32bit_cp1_register(dest, val, )
 #endif
 
 #ifdef HAVE_AS_DSP
diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h
index 2f82568a3ee..bc01579a907 100644
--- a/arch/mips/include/asm/mmu_context.h
+++ b/arch/mips/include/asm/mmu_context.h
@@ -25,7 +25,6 @@ do {									\
 	if (cpu_has_htw) {						\
 		write_c0_pwbase(pgd);					\
 		back_to_back_c0_hazard();				\
-		htw_reset();						\
 	}								\
 } while (0)
 
@@ -142,6 +141,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	unsigned long flags;
 	local_irq_save(flags);
 
+	htw_stop();
 	/* Check if our ASID is of an older version and thus invalid */
 	if ((cpu_context(cpu, next) ^ asid_cache(cpu)) & ASID_VERSION_MASK)
 		get_new_mmu_context(next, cpu);
@@ -154,6 +154,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	 */
 	cpumask_clear_cpu(cpu, mm_cpumask(prev));
 	cpumask_set_cpu(cpu, mm_cpumask(next));
+	htw_start();
 
 	local_irq_restore(flags);
 }
@@ -180,6 +181,7 @@ activate_mm(struct mm_struct *prev, struct mm_struct *next)
 
 	local_irq_save(flags);
 
+	htw_stop();
 	/* Unconditionally get a new ASID.  */
 	get_new_mmu_context(next, cpu);
 
@@ -189,6 +191,7 @@ activate_mm(struct mm_struct *prev, struct mm_struct *next)
 	/* mark mmu ownership change */
 	cpumask_clear_cpu(cpu, mm_cpumask(prev));
 	cpumask_set_cpu(cpu, mm_cpumask(next));
+	htw_start();
 
 	local_irq_restore(flags);
 }
@@ -203,6 +206,7 @@ drop_mmu_context(struct mm_struct *mm, unsigned cpu)
 	unsigned long flags;
 
 	local_irq_save(flags);
+	htw_stop();
 
 	if (cpumask_test_cpu(cpu, mm_cpumask(mm)))  {
 		get_new_mmu_context(mm, cpu);
@@ -211,6 +215,7 @@ drop_mmu_context(struct mm_struct *mm, unsigned cpu)
 		/* will get a new context next time */
 		cpu_context(cpu, mm) = 0;
 	}
+	htw_start();
 	local_irq_restore(flags);
 }
 
diff --git a/arch/mips/include/asm/octeon/pci-octeon.h b/arch/mips/include/asm/octeon/pci-octeon.h
index 64ba56a0284..1884609741a 100644
--- a/arch/mips/include/asm/octeon/pci-octeon.h
+++ b/arch/mips/include/asm/octeon/pci-octeon.h
@@ -11,9 +11,6 @@
 
 #include <linux/pci.h>
 
-/* Some PCI cards require delays when accessing config space. */
-#define PCI_CONFIG_SPACE_DELAY 10000
-
 /*
  * The physical memory base mapped by BAR1.  256MB at the end of the
  * first 4GB.
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index d6d1928539b..bc3fc4fdc9a 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -99,29 +99,35 @@ extern void paging_init(void);
 
 #define htw_stop()							\
 do {									\
-	if (cpu_has_htw)						\
-		write_c0_pwctl(read_c0_pwctl() &			\
-			       ~(1 << MIPS_PWCTL_PWEN_SHIFT));		\
+	unsigned long flags;						\
+									\
+	if (cpu_has_htw) {						\
+		local_irq_save(flags);					\
+		if(!raw_current_cpu_data.htw_seq++) {			\
+			write_c0_pwctl(read_c0_pwctl() &		\
+				       ~(1 << MIPS_PWCTL_PWEN_SHIFT));	\
+			back_to_back_c0_hazard();			\
+		}							\
+		local_irq_restore(flags);				\
+	}								\
 } while(0)
 
 #define htw_start()							\
 do {									\
-	if (cpu_has_htw)						\
-		write_c0_pwctl(read_c0_pwctl() |			\
-			       (1 << MIPS_PWCTL_PWEN_SHIFT));		\
-} while(0)
-
-
-#define htw_reset()							\
-do {									\
+	unsigned long flags;						\
+									\
 	if (cpu_has_htw) {						\
-		htw_stop();						\
-		back_to_back_c0_hazard();				\
-		htw_start();						\
-		back_to_back_c0_hazard();				\
+		local_irq_save(flags);					\
+		if (!--raw_current_cpu_data.htw_seq) {			\
+			write_c0_pwctl(read_c0_pwctl() |		\
+				       (1 << MIPS_PWCTL_PWEN_SHIFT));	\
+			back_to_back_c0_hazard();			\
+		}							\
+		local_irq_restore(flags);				\
 	}								\
 } while(0)
 
+
 extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 	pte_t pteval);
 
@@ -153,12 +159,13 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt
 {
 	pte_t null = __pte(0);
 
+	htw_stop();
 	/* Preserve global status for the pair */
 	if (ptep_buddy(ptep)->pte_low & _PAGE_GLOBAL)
 		null.pte_low = null.pte_high = _PAGE_GLOBAL;
 
 	set_pte_at(mm, addr, ptep, null);
-	htw_reset();
+	htw_start();
 }
 #else
 
@@ -188,6 +195,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
+	htw_stop();
 #if !defined(CONFIG_CPU_R3000) && !defined(CONFIG_CPU_TX39XX)
 	/* Preserve global status for the pair */
 	if (pte_val(*ptep_buddy(ptep)) & _PAGE_GLOBAL)
@@ -195,7 +203,7 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt
 	else
 #endif
 		set_pte_at(mm, addr, ptep, __pte(0));
-	htw_reset();
+	htw_start();
 }
 #endif
 
diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S
index 0384b05ab5a..55b759a0019 100644
--- a/arch/mips/kernel/cps-vec.S
+++ b/arch/mips/kernel/cps-vec.S
@@ -99,11 +99,11 @@ not_nmi:
 	xori	t2, t1, 0x7
 	beqz	t2, 1f
 	 li	t3, 32
-	addi	t1, t1, 1
+	addiu	t1, t1, 1
 	sllv	t1, t3, t1
 1:	/* At this point t1 == I-cache sets per way */
 	_EXT	t2, v0, MIPS_CONF1_IA_SHF, MIPS_CONF1_IA_SZ
-	addi	t2, t2, 1
+	addiu	t2, t2, 1
 	mul	t1, t1, t0
 	mul	t1, t1, t2
 
@@ -126,11 +126,11 @@ icache_done:
 	xori	t2, t1, 0x7
 	beqz	t2, 1f
 	 li	t3, 32
-	addi	t1, t1, 1
+	addiu	t1, t1, 1
 	sllv	t1, t3, t1
 1:	/* At this point t1 == D-cache sets per way */
 	_EXT	t2, v0, MIPS_CONF1_DA_SHF, MIPS_CONF1_DA_SZ
-	addi	t2, t2, 1
+	addiu	t2, t2, 1
 	mul	t1, t1, t0
 	mul	t1, t1, t2
 
@@ -250,7 +250,7 @@ LEAF(mips_cps_core_init)
 	mfc0	t0, CP0_MVPCONF0
 	srl	t0, t0, MVPCONF0_PVPE_SHIFT
 	andi	t0, t0, (MVPCONF0_PVPE >> MVPCONF0_PVPE_SHIFT)
-	addi	t7, t0, 1
+	addiu	t7, t0, 1
 
 	/* If there's only 1, we're done */
 	beqz	t0, 2f
@@ -280,7 +280,7 @@ LEAF(mips_cps_core_init)
 	mttc0	t0, CP0_TCHALT
 
 	/* Next VPE */
-	addi	t5, t5, 1
+	addiu	t5, t5, 1
 	slt	t0, t5, t7
 	bnez	t0, 1b
 	 nop
@@ -317,7 +317,7 @@ LEAF(mips_cps_boot_vpes)
 	mfc0	t1, CP0_MVPCONF0
 	srl	t1, t1, MVPCONF0_PVPE_SHIFT
 	andi	t1, t1, MVPCONF0_PVPE >> MVPCONF0_PVPE_SHIFT
-	addi	t1, t1, 1
+	addiu	t1, t1, 1
 
 	/* Calculate a mask for the VPE ID from EBase.CPUNum */
 	clz	t1, t1
@@ -424,7 +424,7 @@ LEAF(mips_cps_boot_vpes)
 
 	/* Next VPE */
 2:	srl	t6, t6, 1
-	addi	t5, t5, 1
+	addiu	t5, t5, 1
 	bnez	t6, 1b
 	 nop
 
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index dc49cf30c2d..5d6e59f2075 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -367,8 +367,10 @@ static inline unsigned int decode_config3(struct cpuinfo_mips *c)
 	if (config3 & MIPS_CONF3_MSA)
 		c->ases |= MIPS_ASE_MSA;
 	/* Only tested on 32-bit cores */
-	if ((config3 & MIPS_CONF3_PW) && config_enabled(CONFIG_32BIT))
+	if ((config3 & MIPS_CONF3_PW) && config_enabled(CONFIG_32BIT)) {
+		c->htw_seq = 0;
 		c->options |= MIPS_CPU_HTW;
+	}
 
 	return config3 & MIPS_CONF_M;
 }
diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S
index 4353d323f01..39d682937d5 100644
--- a/arch/mips/kernel/entry.S
+++ b/arch/mips/kernel/entry.S
@@ -10,6 +10,7 @@
 
 #include <asm/asm.h>
 #include <asm/asmmacro.h>
+#include <asm/compiler.h>
 #include <asm/regdef.h>
 #include <asm/mipsregs.h>
 #include <asm/stackframe.h>
@@ -166,7 +167,7 @@ syscall_exit_work:
  * For C code use the inline version named instruction_hazard().
  */
 LEAF(mips_ihb)
-	.set	mips32r2
+	.set	MIPS_ISA_LEVEL_RAW
 	jr.hb	ra
 	nop
 	END(mips_ihb)
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index d2bfbc2e899..be15e52a47a 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -109,7 +109,7 @@ void __init init_IRQ(void)
 #endif
 }
 
-#ifdef DEBUG_STACKOVERFLOW
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
 static inline void check_stack_overflow(void)
 {
 	unsigned long sp;
diff --git a/arch/mips/kernel/irq_cpu.c b/arch/mips/kernel/irq_cpu.c
index e498f2b3646..f5598e25e90 100644
--- a/arch/mips/kernel/irq_cpu.c
+++ b/arch/mips/kernel/irq_cpu.c
@@ -56,6 +56,8 @@ static struct irq_chip mips_cpu_irq_controller = {
 	.irq_mask_ack	= mask_mips_irq,
 	.irq_unmask	= unmask_mips_irq,
 	.irq_eoi	= unmask_mips_irq,
+	.irq_disable	= mask_mips_irq,
+	.irq_enable	= unmask_mips_irq,
 };
 
 /*
@@ -92,6 +94,8 @@ static struct irq_chip mips_mt_cpu_irq_controller = {
 	.irq_mask_ack	= mips_mt_cpu_irq_ack,
 	.irq_unmask	= unmask_mips_irq,
 	.irq_eoi	= unmask_mips_irq,
+	.irq_disable	= mask_mips_irq,
+	.irq_enable	= unmask_mips_irq,
 };
 
 void __init mips_cpu_irq_init(void)
diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c
index 2607c3a4ff7..1b2452e2be6 100644
--- a/arch/mips/kernel/mips_ksyms.c
+++ b/arch/mips/kernel/mips_ksyms.c
@@ -14,6 +14,8 @@
 #include <linux/mm.h>
 #include <asm/uaccess.h>
 #include <asm/ftrace.h>
+#include <asm/fpu.h>
+#include <asm/msa.h>
 
 extern void *__bzero(void *__s, size_t __count);
 extern long __strncpy_from_kernel_nocheck_asm(char *__to,
@@ -34,6 +36,14 @@ extern long __strnlen_user_nocheck_asm(const char *s);
 extern long __strnlen_user_asm(const char *s);
 
 /*
+ * Core architecture code
+ */
+EXPORT_SYMBOL_GPL(_save_fp);
+#ifdef CONFIG_CPU_HAS_MSA
+EXPORT_SYMBOL_GPL(_save_msa);
+#endif
+
+/*
  * String functions
  */
 EXPORT_SYMBOL(memset);
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index e6e16a1d4ad..0854f17829f 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -88,6 +88,12 @@ static void __init cps_smp_setup(void)
 
 	/* Make core 0 coherent with everything */
 	write_gcr_cl_coherence(0xff);
+
+#ifdef CONFIG_MIPS_MT_FPAFF
+	/* If we have an FPU, enroll ourselves in the FPU-full mask */
+	if (cpu_has_fpu)
+		cpu_set(0, mt_fpu_cpumask);
+#endif /* CONFIG_MIPS_MT_FPAFF */
 }
 
 static void __init cps_prepare_cpus(unsigned int max_cpus)
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index c94c4e92e17..1c0d8c50b7e 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -123,10 +123,10 @@ asmlinkage void start_secondary(void)
 	unsigned int cpu;
 
 	cpu_probe();
-	cpu_report();
 	per_cpu_trap_init(false);
 	mips_clockevent_init();
 	mp_ops->init_secondary();
+	cpu_report();
 
 	/*
 	 * XXX parity protection should be folded in here when it's converted
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 22b19c27504..d255a2a1837 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1184,7 +1184,8 @@ static int enable_restore_fp_context(int msa)
 
 		/* Restore the scalar FP control & status register */
 		if (!was_fpu_owner)
-			asm volatile("ctc1 %0, $31" : : "r"(current->thread.fpu.fcr31));
+			write_32bit_cp1_register(CP1_STATUS,
+						 current->thread.fpu.fcr31);
 	}
 
 out:
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index fb3e8dfd1ff..838d3a6a5b7 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -2176,6 +2176,7 @@ enum emulation_result kvm_mips_check_privilege(unsigned long cause,
 		case T_SYSCALL:
 		case T_BREAK:
 		case T_RES_INST:
+		case T_MSADIS:
 			break;
 
 		case T_COP_UNUSABLE:
diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S
index d7279c03c51..4a68b176d6e 100644
--- a/arch/mips/kvm/locore.S
+++ b/arch/mips/kvm/locore.S
@@ -434,7 +434,7 @@ __kvm_mips_return_to_guest:
 	/* Setup status register for running guest in UM */
 	.set	at
 	or	v1, v1, (ST0_EXL | KSU_USER | ST0_IE)
-	and	v1, v1, ~ST0_CU0
+	and	v1, v1, ~(ST0_CU0 | ST0_MX)
 	.set	noat
 	mtc0	v1, CP0_STATUS
 	ehb
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index e3b21e51ff7..a53eaf50c22 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -15,9 +15,11 @@
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
 #include <linux/bootmem.h>
+#include <asm/fpu.h>
 #include <asm/page.h>
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
+#include <asm/pgtable.h>
 
 #include <linux/kvm_host.h>
 
@@ -378,6 +380,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		vcpu->mmio_needed = 0;
 	}
 
+	lose_fpu(1);
+
 	local_irq_disable();
 	/* Check if we have any exceptions/interrupts pending */
 	kvm_mips_deliver_interrupts(vcpu,
@@ -385,8 +389,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 	kvm_guest_enter();
 
+	/* Disable hardware page table walking while in guest */
+	htw_stop();
+
 	r = __kvm_mips_vcpu_run(run, vcpu);
 
+	/* Re-enable HTW before enabling interrupts */
+	htw_start();
+
 	kvm_guest_exit();
 	local_irq_enable();
 
@@ -774,7 +784,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 
 	/* If nothing is dirty, don't bother messing with page tables. */
 	if (is_dirty) {
-		memslot = &kvm->memslots->memslots[log->slot];
+		memslot = id_to_memslot(kvm->memslots, log->slot);
 
 		ga = memslot->base_gfn << PAGE_SHIFT;
 		ga_end = ga + (memslot->npages << PAGE_SHIFT);
@@ -980,9 +990,6 @@ static void kvm_mips_set_c0_status(void)
 {
 	uint32_t status = read_c0_status();
 
-	if (cpu_has_fpu)
-		status |= (ST0_CU1);
-
 	if (cpu_has_dsp)
 		status |= (ST0_MX);
 
@@ -1002,6 +1009,9 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	enum emulation_result er = EMULATE_DONE;
 	int ret = RESUME_GUEST;
 
+	/* re-enable HTW before enabling interrupts */
+	htw_start();
+
 	/* Set a default exit reason */
 	run->exit_reason = KVM_EXIT_UNKNOWN;
 	run->ready_for_interrupt_injection = 1;
@@ -1109,6 +1119,10 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		ret = kvm_mips_callbacks->handle_break(vcpu);
 		break;
 
+	case T_MSADIS:
+		ret = kvm_mips_callbacks->handle_msa_disabled(vcpu);
+		break;
+
 	default:
 		kvm_err("Exception Code: %d, not yet handled, @ PC: %p, inst: 0x%08x  BadVaddr: %#lx Status: %#lx\n",
 			exccode, opc, kvm_get_inst(opc, vcpu), badvaddr,
@@ -1136,6 +1150,9 @@ skip_emul:
 		}
 	}
 
+	/* Disable HTW before returning to guest or host */
+	htw_stop();
+
 	return ret;
 }
 
diff --git a/arch/mips/kvm/trace.h b/arch/mips/kvm/trace.h
index c1388d40663..bd6437f67dc 100644
--- a/arch/mips/kvm/trace.h
+++ b/arch/mips/kvm/trace.h
@@ -24,18 +24,18 @@ TRACE_EVENT(kvm_exit,
 	    TP_PROTO(struct kvm_vcpu *vcpu, unsigned int reason),
 	    TP_ARGS(vcpu, reason),
 	    TP_STRUCT__entry(
-			__field(struct kvm_vcpu *, vcpu)
+			__field(unsigned long, pc)
 			__field(unsigned int, reason)
 	    ),
 
 	    TP_fast_assign(
-			__entry->vcpu = vcpu;
+			__entry->pc = vcpu->arch.pc;
 			__entry->reason = reason;
 	    ),
 
 	    TP_printk("[%s]PC: 0x%08lx",
 		      kvm_mips_exit_types_str[__entry->reason],
-		      __entry->vcpu->arch.pc)
+		      __entry->pc)
 );
 
 #endif /* _TRACE_KVM_H */
diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c
index fd7257b70e6..4372cc86650 100644
--- a/arch/mips/kvm/trap_emul.c
+++ b/arch/mips/kvm/trap_emul.c
@@ -330,6 +330,33 @@ static int kvm_trap_emul_handle_break(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
+static int kvm_trap_emul_handle_msa_disabled(struct kvm_vcpu *vcpu)
+{
+	struct kvm_run *run = vcpu->run;
+	uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc;
+	unsigned long cause = vcpu->arch.host_cp0_cause;
+	enum emulation_result er = EMULATE_DONE;
+	int ret = RESUME_GUEST;
+
+	/* No MSA supported in guest, guest reserved instruction exception */
+	er = kvm_mips_emulate_ri_exc(cause, opc, run, vcpu);
+
+	switch (er) {
+	case EMULATE_DONE:
+		ret = RESUME_GUEST;
+		break;
+
+	case EMULATE_FAIL:
+		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		ret = RESUME_HOST;
+		break;
+
+	default:
+		BUG();
+	}
+	return ret;
+}
+
 static int kvm_trap_emul_vm_init(struct kvm *kvm)
 {
 	return 0;
@@ -470,6 +497,7 @@ static struct kvm_mips_callbacks kvm_trap_emul_callbacks = {
 	.handle_syscall = kvm_trap_emul_handle_syscall,
 	.handle_res_inst = kvm_trap_emul_handle_res_inst,
 	.handle_break = kvm_trap_emul_handle_break,
+	.handle_msa_disabled = kvm_trap_emul_handle_msa_disabled,
 
 	.vm_init = kvm_trap_emul_vm_init,
 	.vcpu_init = kvm_trap_emul_vcpu_init,
diff --git a/arch/mips/loongson/loongson-3/irq.c b/arch/mips/loongson/loongson-3/irq.c
index ca1c62af518..8f5209aff01 100644
--- a/arch/mips/loongson/loongson-3/irq.c
+++ b/arch/mips/loongson/loongson-3/irq.c
@@ -44,6 +44,7 @@ void mach_irq_dispatch(unsigned int pending)
 
 static struct irqaction cascade_irqaction = {
 	.handler = no_action,
+	.flags = IRQF_NO_SUSPEND,
 	.name = "cascade",
 };
 
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index becc42bb184..70ab5d66433 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -158,6 +158,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c
index 4ec8ee10d37..06e0f421b41 100644
--- a/arch/mips/mm/hugetlbpage.c
+++ b/arch/mips/mm/hugetlbpage.c
@@ -68,12 +68,6 @@ int is_aligned_hugepage_range(unsigned long addr, unsigned long len)
 	return 0;
 }
 
-struct page *
-follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
-{
-	return ERR_PTR(-EINVAL);
-}
-
 int pmd_huge(pmd_t pmd)
 {
 	return (pmd_val(pmd) & _PAGE_HUGE) != 0;
@@ -83,15 +77,3 @@ int pud_huge(pud_t pud)
 {
 	return (pud_val(pud) & _PAGE_HUGE) != 0;
 }
-
-struct page *
-follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-		pmd_t *pmd, int write)
-{
-	struct page *page;
-
-	page = pte_page(*(pte_t *)pmd);
-	if (page)
-		page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT);
-	return page;
-}
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index c3917e251f5..11688e50e3e 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -489,6 +489,8 @@ static void r4k_tlb_configure(void)
 #ifdef CONFIG_64BIT
 		pg |= PG_ELPA;
 #endif
+		if (cpu_has_rixiex)
+			pg |= PG_IEC;
 		write_c0_pagegrain(pg);
 	}
 
diff --git a/arch/mips/mti-malta/malta-memory.c b/arch/mips/mti-malta/malta-memory.c
index 8fddd2cdbff..efe366d618b 100644
--- a/arch/mips/mti-malta/malta-memory.c
+++ b/arch/mips/mti-malta/malta-memory.c
@@ -53,6 +53,12 @@ fw_memblock_t * __init fw_getmdesc(int eva)
 		pr_warn("memsize not set in YAMON, set to default (32Mb)\n");
 		physical_memsize = 0x02000000;
 	} else {
+		if (memsize > (256 << 20)) { /* memsize should be capped to 256M */
+			pr_warn("Unsupported memsize value (0x%lx) detected! "
+				"Using 0x10000000 (256M) instead\n",
+				memsize);
+			memsize = 256 << 20;
+		}
 		/* If ememsize is set, then set physical_memsize to that */
 		physical_memsize = ememsize ? : memsize;
 	}
diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index 9b55143d19d..9fd6834a217 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -426,7 +426,7 @@ static inline void emit_mod(unsigned int dst, unsigned int src,
 		u32 *p = &ctx->target[ctx->idx];
 		uasm_i_divu(&p, dst, src);
 		p = &ctx->target[ctx->idx + 1];
-		uasm_i_mflo(&p, dst);
+		uasm_i_mfhi(&p, dst);
 	}
 	ctx->idx += 2; /* 2 insts */
 }
@@ -971,7 +971,7 @@ load_ind:
 			break;
 		case BPF_ALU | BPF_MOD | BPF_K:
 			/* A %= k */
-			if (k == 1 || optimize_div(&k)) {
+			if (k == 1) {
 				ctx->flags |= SEEN_A;
 				emit_jit_reg_move(r_A, r_zero, ctx);
 			} else {
diff --git a/arch/mips/netlogic/xlp/ahci-init-xlp2.c b/arch/mips/netlogic/xlp/ahci-init-xlp2.c
index c83dbf3689e..7b066a44e67 100644
--- a/arch/mips/netlogic/xlp/ahci-init-xlp2.c
+++ b/arch/mips/netlogic/xlp/ahci-init-xlp2.c
@@ -203,6 +203,7 @@ static u8 read_phy_reg(u64 regbase, u32 addr, u32 physel)
 static void config_sata_phy(u64 regbase)
 {
 	u32 port, i, reg;
+	u8 val;
 
 	for (port = 0; port < 2; port++) {
 		for (i = 0, reg = RXCDRCALFOSC0; reg <= CALDUTY; reg++, i++)
@@ -210,6 +211,18 @@ static void config_sata_phy(u64 regbase)
 
 		for (i = 0, reg = RXDPIF; reg <= PPMDRIFTMAX_HI; reg++, i++)
 			write_phy_reg(regbase, reg, port, sata_phy_config2[i]);
+
+		/* Fix for PHY link up failures at lower temperatures */
+		write_phy_reg(regbase, 0x800F, port, 0x1f);
+
+		val = read_phy_reg(regbase, 0x0029, port);
+		write_phy_reg(regbase, 0x0029, port, val | (0x7 << 1));
+
+		val = read_phy_reg(regbase, 0x0056, port);
+		write_phy_reg(regbase, 0x0056, port, val & ~(1 << 3));
+
+		val = read_phy_reg(regbase, 0x0018, port);
+		write_phy_reg(regbase, 0x0018, port, val & ~(0x7 << 0));
 	}
 }
 
diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
index 59cccd95688..14d3351227e 100644
--- a/arch/mips/pci/pci-octeon.c
+++ b/arch/mips/pci/pci-octeon.c
@@ -214,6 +214,8 @@ const char *octeon_get_pci_interrupts(void)
 		return "AAABAAAAAAAAAAAAAAAAAAAAAAAAAAAA";
 	case CVMX_BOARD_TYPE_BBGW_REF:
 		return "AABCD";
+	case CVMX_BOARD_TYPE_CUST_DSR1000N:
+		return "CCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC";
 	case CVMX_BOARD_TYPE_THUNDER:
 	case CVMX_BOARD_TYPE_EBH3000:
 	default:
@@ -271,9 +273,6 @@ static int octeon_read_config(struct pci_bus *bus, unsigned int devfn,
 	pci_addr.s.func = devfn & 0x7;
 	pci_addr.s.reg = reg;
 
-#if PCI_CONFIG_SPACE_DELAY
-	udelay(PCI_CONFIG_SPACE_DELAY);
-#endif
 	switch (size) {
 	case 4:
 		*val = le32_to_cpu(cvmx_read64_uint32(pci_addr.u64));
@@ -308,9 +307,6 @@ static int octeon_write_config(struct pci_bus *bus, unsigned int devfn,
 	pci_addr.s.func = devfn & 0x7;
 	pci_addr.s.reg = reg;
 
-#if PCI_CONFIG_SPACE_DELAY
-	udelay(PCI_CONFIG_SPACE_DELAY);
-#endif
 	switch (size) {
 	case 4:
 		cvmx_write64_uint32(pci_addr.u64, cpu_to_le32(val));
diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c
index 5e36c33e554..38335af0a7f 100644
--- a/arch/mips/pci/pcie-octeon.c
+++ b/arch/mips/pci/pcie-octeon.c
@@ -1762,14 +1762,6 @@ static int octeon_pcie_write_config(unsigned int pcie_port, struct pci_bus *bus,
 	default:
 		return PCIBIOS_FUNC_NOT_SUPPORTED;
 	}
-#if PCI_CONFIG_SPACE_DELAY
-	/*
-	 * Delay on writes so that devices have time to come up. Some
-	 * bridges need this to allow time for the secondary busses to
-	 * work
-	 */
-	udelay(PCI_CONFIG_SPACE_DELAY);
-#endif
 	return PCIBIOS_SUCCESSFUL;
 }
 
diff --git a/arch/mips/power/hibernate.S b/arch/mips/power/hibernate.S
index 32a7c828f07..e7567c8a9e7 100644
--- a/arch/mips/power/hibernate.S
+++ b/arch/mips/power/hibernate.S
@@ -30,6 +30,8 @@ LEAF(swsusp_arch_suspend)
 END(swsusp_arch_suspend)
 
 LEAF(swsusp_arch_resume)
+	/* Avoid TLB mismatch during and after kernel resume */
+	jal local_flush_tlb_all
 	PTR_L t0, restore_pblist
 0:
 	PTR_L t1, PBE_ADDRESS(t0)   /* source */
@@ -43,7 +45,6 @@ LEAF(swsusp_arch_resume)
 	bne t1, t3, 1b
 	PTR_L t0, PBE_NEXT(t0)
 	bnez t0, 0b
-	jal local_flush_tlb_all /* Avoid TLB mismatch after kernel resume */
 	PTR_LA t0, saved_regs
 	PTR_L ra, PT_R31(t0)
 	PTR_L sp, PT_R29(t0)
diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig
index 77e8a9620e1..d50914d5191 100644
--- a/arch/mips/ralink/Kconfig
+++ b/arch/mips/ralink/Kconfig
@@ -7,6 +7,11 @@ config CLKEVT_RT3352
 	select CLKSRC_OF
 	select CLKSRC_MMIO
 
+config RALINK_ILL_ACC
+	bool
+	depends on SOC_RT305X
+	default y
+
 choice
 	prompt "Ralink SoC selection"
 	default SOC_RT305X
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index 3516cbdf1ee..0c2cc5d39c8 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -262,6 +262,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index 0703acf7d32..230ac20ae79 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -171,6 +171,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h
index 3391d061ecc..78c9fd32c55 100644
--- a/arch/parisc/include/asm/elf.h
+++ b/arch/parisc/include/asm/elf.h
@@ -348,6 +348,10 @@ struct pt_regs;	/* forward declaration... */
 
 #define ELF_HWCAP	0
 
+#define STACK_RND_MASK	(is_32bit_task() ? \
+				0x7ff >> (PAGE_SHIFT - 12) : \
+				0x3ffff >> (PAGE_SHIFT - 12))
+
 struct mm_struct;
 extern unsigned long arch_randomize_brk(struct mm_struct *);
 #define arch_randomize_brk arch_randomize_brk
diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h
index d2d11b7055b..8121aa6db2f 100644
--- a/arch/parisc/include/asm/ldcw.h
+++ b/arch/parisc/include/asm/ldcw.h
@@ -33,11 +33,18 @@
 
 #endif /*!CONFIG_PA20*/
 
-/* LDCW, the only atomic read-write operation PA-RISC has. *sigh*.  */
+/* LDCW, the only atomic read-write operation PA-RISC has. *sigh*.
+   We don't explicitly expose that "*a" may be written as reload
+   fails to find a register in class R1_REGS when "a" needs to be
+   reloaded when generating 64-bit PIC code.  Instead, we clobber
+   memory to indicate to the compiler that the assembly code reads
+   or writes to items other than those listed in the input and output
+   operands.  This may pessimize the code somewhat but __ldcw is
+   usually used within code blocks surrounded by memory barriors.  */
 #define __ldcw(a) ({						\
 	unsigned __ret;						\
-	__asm__ __volatile__(__LDCW " 0(%2),%0"			\
-		: "=r" (__ret), "+m" (*(a)) : "r" (a));		\
+	__asm__ __volatile__(__LDCW " 0(%1),%0"			\
+		: "=r" (__ret) : "r" (a) : "memory");		\
 	__ret;							\
 })
 
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index e1ffea2f9a0..5aba01ac457 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -77,6 +77,9 @@ static unsigned long mmap_upper_limit(void)
 	if (stack_base > STACK_SIZE_MAX)
 		stack_base = STACK_SIZE_MAX;
 
+	/* Add space for stack randomization. */
+	stack_base += (STACK_RND_MASK << PAGE_SHIFT);
+
 	return PAGE_ALIGN(STACK_TOP - stack_base);
 }
 
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 3ca9c1131cf..e5120e65324 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -256,6 +256,8 @@ good_area:
 		 */
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto bad_area;
 		BUG();
diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi
index 1382fec9e8c..7fcb1ac0f23 100644
--- a/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi
@@ -50,6 +50,7 @@ ethernet@b0000 {
 	fsl,num_tx_queues = <0x8>;
 	fsl,magic-packet;
 	local-mac-address = [ 00 00 00 00 00 00 ];
+	ranges;
 
 	queue-group@b0000 {
 		#address-cells = <1>;
diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi
index 221cd2ea5b3..9f25427c152 100644
--- a/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi
@@ -50,6 +50,7 @@ ethernet@b1000 {
 	fsl,num_tx_queues = <0x8>;
 	fsl,magic-packet;
 	local-mac-address = [ 00 00 00 00 00 00 ];
+	ranges;
 
 	queue-group@b1000 {
 		#address-cells = <1>;
diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi
index 61456c31760..cd7c318ab13 100644
--- a/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi
+++ b/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi
@@ -49,6 +49,7 @@ ethernet@b2000 {
 	fsl,num_tx_queues = <0x8>;
 	fsl,magic-packet;
 	local-mac-address = [ 00 00 00 00 00 00 ];
+	ranges;
 
 	queue-group@b2000 {
 		#address-cells = <1>;
diff --git a/arch/powerpc/crypto/sha1.c b/arch/powerpc/crypto/sha1.c
index f9e8b9491ef..b51da913274 100644
--- a/arch/powerpc/crypto/sha1.c
+++ b/arch/powerpc/crypto/sha1.c
@@ -154,4 +154,5 @@ module_exit(sha1_powerpc_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm");
 
-MODULE_ALIAS("sha1-powerpc");
+MODULE_ALIAS_CRYPTO("sha1");
+MODULE_ALIAS_CRYPTO("sha1-powerpc");
diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index 2bf8e9307be..4c8ad592ae3 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -55,7 +55,7 @@ static inline cpumask_t cpu_thread_mask_to_cores(const struct cpumask *threads)
 
 static inline int cpu_nr_cores(void)
 {
-	return NR_CPUS >> threads_shift;
+	return nr_cpu_ids >> threads_shift;
 }
 
 static inline cpumask_t cpu_online_cores_map(void)
diff --git a/arch/powerpc/include/asm/irq_work.h b/arch/powerpc/include/asm/irq_work.h
new file mode 100644
index 00000000000..744fd54de37
--- /dev/null
+++ b/arch/powerpc/include/asm/irq_work.h
@@ -0,0 +1,9 @@
+#ifndef _ASM_POWERPC_IRQ_WORK_H
+#define _ASM_POWERPC_IRQ_WORK_H
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return true;
+}
+
+#endif /* _ASM_POWERPC_IRQ_WORK_H */
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index e9a9f60e596..fc3ee06eab8 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -3,7 +3,6 @@
 #ifdef __KERNEL__
 
 #include <linux/mm.h>
-#include <asm-generic/tlb.h>
 
 #ifdef CONFIG_PPC_BOOK3E
 extern void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address);
@@ -14,6 +13,8 @@ static inline void tlb_flush_pgtable(struct mmu_gather *tlb,
 }
 #endif /* !CONFIG_PPC_BOOK3E */
 
+extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
+
 #ifdef CONFIG_PPC64
 #include <asm/pgalloc-64.h>
 #else
diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h
index f09a22fa1bd..bfa8f8ac51f 100644
--- a/arch/powerpc/include/asm/pnv-pci.h
+++ b/arch/powerpc/include/asm/pnv-pci.h
@@ -19,7 +19,7 @@ int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
 int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num);
 void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num);
 int pnv_cxl_get_irq_count(struct pci_dev *dev);
-struct device_node *pnv_pci_to_phb_node(struct pci_dev *dev);
+struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev);
 
 #ifdef CONFIG_CXL_BASE
 int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs,
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index c998279bd85..a68ee15964b 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -118,8 +118,10 @@
 #define __MSR		(MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_ISF |MSR_HV)
 #ifdef __BIG_ENDIAN__
 #define MSR_		__MSR
+#define MSR_IDLE	(MSR_ME | MSR_SF | MSR_HV)
 #else
 #define MSR_		(__MSR | MSR_LE)
+#define MSR_IDLE	(MSR_ME | MSR_SF | MSR_HV | MSR_LE)
 #endif
 #define MSR_KERNEL	(MSR_ | MSR_64BIT)
 #define MSR_USER32	(MSR_ | MSR_PR | MSR_EE)
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index 6240698fee9..ff21b7a2f0c 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/arch/powerpc/include/asm/syscall.h
@@ -90,6 +90,10 @@ static inline void syscall_set_arguments(struct task_struct *task,
 
 static inline int syscall_get_arch(void)
 {
-	return is_32bit_task() ? AUDIT_ARCH_PPC : AUDIT_ARCH_PPC64;
+	int arch = is_32bit_task() ? AUDIT_ARCH_PPC : AUDIT_ARCH_PPC64;
+#ifdef __LITTLE_ENDIAN__
+	arch |= __AUDIT_ARCH_LE;
+#endif
+	return arch;
 }
 #endif	/* _ASM_SYSCALL_H */
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index e2b428b0f7b..20733fa518a 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -27,6 +27,7 @@
 
 #define tlb_start_vma(tlb, vma)	do { } while (0)
 #define tlb_end_vma(tlb, vma)	do { } while (0)
+#define __tlb_remove_tlb_entry	__tlb_remove_tlb_entry
 
 extern void tlb_flush(struct mmu_gather *tlb);
 
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index 40198d50b4c..8005b79ecbc 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -61,12 +61,22 @@ struct cache_type_info {
 };
 
 /* These are used to index the cache_type_info array. */
-#define CACHE_TYPE_UNIFIED     0
-#define CACHE_TYPE_INSTRUCTION 1
-#define CACHE_TYPE_DATA        2
+#define CACHE_TYPE_UNIFIED     0 /* cache-size, cache-block-size, etc. */
+#define CACHE_TYPE_UNIFIED_D   1 /* d-cache-size, d-cache-block-size, etc */
+#define CACHE_TYPE_INSTRUCTION 2
+#define CACHE_TYPE_DATA        3
 
 static const struct cache_type_info cache_type_info[] = {
 	{
+		/* Embedded systems that use cache-size, cache-block-size,
+		 * etc. for the Unified (typically L2) cache. */
+		.name            = "Unified",
+		.size_prop       = "cache-size",
+		.line_size_props = { "cache-line-size",
+				     "cache-block-size", },
+		.nr_sets_prop    = "cache-sets",
+	},
+	{
 		/* PowerPC Processor binding says the [di]-cache-*
 		 * must be equal on unified caches, so just use
 		 * d-cache properties. */
@@ -293,7 +303,8 @@ static struct cache *cache_find_first_sibling(struct cache *cache)
 {
 	struct cache *iter;
 
-	if (cache->type == CACHE_TYPE_UNIFIED)
+	if (cache->type == CACHE_TYPE_UNIFIED ||
+	    cache->type == CACHE_TYPE_UNIFIED_D)
 		return cache;
 
 	list_for_each_entry(iter, &cache_list, list)
@@ -324,16 +335,29 @@ static bool cache_node_is_unified(const struct device_node *np)
 	return of_get_property(np, "cache-unified", NULL);
 }
 
-static struct cache *cache_do_one_devnode_unified(struct device_node *node,
-						  int level)
+/*
+ * Unified caches can have two different sets of tags.  Most embedded
+ * use cache-size, etc. for the unified cache size, but open firmware systems
+ * use d-cache-size, etc.   Check on initialization for which type we have, and
+ * return the appropriate structure type.  Assume it's embedded if it isn't
+ * open firmware.  If it's yet a 3rd type, then there will be missing entries
+ * in /sys/devices/system/cpu/cpu0/cache/index2/, and this code will need
+ * to be extended further.
+ */
+static int cache_is_unified_d(const struct device_node *np)
 {
-	struct cache *cache;
+	return of_get_property(np,
+		cache_type_info[CACHE_TYPE_UNIFIED_D].size_prop, NULL) ?
+		CACHE_TYPE_UNIFIED_D : CACHE_TYPE_UNIFIED;
+}
 
+/*
+ */
+static struct cache *cache_do_one_devnode_unified(struct device_node *node, int level)
+{
 	pr_debug("creating L%d ucache for %s\n", level, node->full_name);
 
-	cache = new_cache(CACHE_TYPE_UNIFIED, level, node);
-
-	return cache;
+	return new_cache(cache_is_unified_d(node), level, node);
 }
 
 static struct cache *cache_do_one_devnode_split(struct device_node *node,
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 72e783ea068..5e019842519 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1399,7 +1399,7 @@ machine_check_handle_early:
 	bne	9f			/* continue in V mode if we are. */
 
 5:
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 	/*
 	 * We are coming from kernel context. Check if we are coming from
 	 * guest. if yes, then we can continue. We will fall through
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index c0754bbf811..283c603716a 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -101,7 +101,23 @@ _GLOBAL(power7_powersave_common)
 	std	r9,_MSR(r1)
 	std	r1,PACAR1(r13)
 
-_GLOBAL(power7_enter_nap_mode)
+	/*
+	 * Go to real mode to do the nap, as required by the architecture.
+	 * Also, we need to be in real mode before setting hwthread_state,
+	 * because as soon as we do that, another thread can switch
+	 * the MMU context to the guest.
+	 */
+	LOAD_REG_IMMEDIATE(r5, MSR_IDLE)
+	li	r6, MSR_RI
+	andc	r6, r9, r6
+	LOAD_REG_ADDR(r7, power7_enter_nap_mode)
+	mtmsrd	r6, 1		/* clear RI before setting SRR0/1 */
+	mtspr	SPRN_SRR0, r7
+	mtspr	SPRN_SRR1, r5
+	rfid
+
+	.globl	power7_enter_nap_mode
+power7_enter_nap_mode:
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	/* Tell KVM we're napping */
 	li	r4,KVM_HWTHREAD_IN_NAP
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index aa9aff3d6ad..b6f123ab90e 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -79,7 +79,7 @@ static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits)
 	}
 	if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) {
 		if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
-			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE);
+			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET);
 		/* reset error bits */
 		dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB;
 	}
@@ -110,7 +110,7 @@ static long mce_handle_common_ierror(uint64_t srr1)
 		break;
 	case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
 		if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
-			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE);
+			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET);
 			handled = 1;
 		}
 		break;
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index 6e7c4923b5e..411116c38da 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -69,8 +69,12 @@ static void udbg_uart_putc(char c)
 
 static int udbg_uart_getc_poll(void)
 {
-	if (!udbg_uart_in || !(udbg_uart_in(UART_LSR) & LSR_DR))
+	if (!udbg_uart_in)
+		return -1;
+
+	if (!(udbg_uart_in(UART_LSR) & LSR_DR))
 		return udbg_uart_in(UART_RBR);
+
 	return -1;
 }
 
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index f096e72262f..1db685104ff 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -213,6 +213,7 @@ SECTIONS
 		*(.opd)
 	}
 
+	. = ALIGN(256);
 	.got : AT(ADDR(.got) - LOAD_OFFSET) {
 		__toc_start = .;
 #ifndef CONFIG_RELOCATABLE
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index 5a236f082c7..1b5305d4bda 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -76,7 +76,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 		if (*flt & VM_FAULT_OOM) {
 			ret = -ENOMEM;
 			goto out_unlock;
-		} else if (*flt & VM_FAULT_SIGBUS) {
+		} else if (*flt & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) {
 			ret = -EFAULT;
 			goto out_unlock;
 		}
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 08d659a9fcd..f06b56baf0b 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -444,6 +444,8 @@ good_area:
 	 */
 	fault = handle_mm_fault(mm, vma, address, flags);
 	if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
+		if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		rc = mm_fault_error(regs, address, fault);
 		if (rc >= MM_FAULT_RETURN)
 			goto bail;
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 7e70ae968e5..17e83a043bb 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -517,8 +517,6 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif
 	for (i = 0; i < num_hugepd; i++, hpdp++)
 		hpdp->pd = 0;
 
-	tlb->need_flush = 1;
-
 #ifdef CONFIG_PPC_FSL_BOOK3E
 	hugepd_free(tlb, hugepte);
 #else
@@ -706,6 +704,14 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 	return NULL;
 }
 
+struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+		pud_t *pud, int write)
+{
+	BUG();
+	return NULL;
+}
+
 static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
 				      unsigned long sz)
 {
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 2396dda282c..ead55351b25 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -243,7 +243,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
 	sp = regs->gpr[1];
 	perf_callchain_store(entry, next_ip);
 
-	for (;;) {
+	while (entry->nr < PERF_MAX_STACK_DEPTH) {
 		fp = (unsigned long __user *) sp;
 		if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp))
 			return;
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index a6995d4e93d..ffa07eb5fff 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -131,7 +131,16 @@ static void pmao_restore_workaround(bool ebb) { }
 
 static bool regs_use_siar(struct pt_regs *regs)
 {
-	return !!regs->result;
+	/*
+	 * When we take a performance monitor exception the regs are setup
+	 * using perf_read_regs() which overloads some fields, in particular
+	 * regs->result to tell us whether to use SIAR.
+	 *
+	 * However if the regs are from another exception, eg. a syscall, then
+	 * they have not been setup using perf_read_regs() and so regs->result
+	 * is something random.
+	 */
+	return ((TRAP(regs) == 0xf00) && regs->result);
 }
 
 /*
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index dba34088da2..d073e0679a0 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -217,11 +217,14 @@ static bool is_physical_domain(int domain)
 		domain == HV_24X7_PERF_DOMAIN_PHYSICAL_CORE;
 }
 
+DEFINE_PER_CPU(char, hv_24x7_reqb[4096]) __aligned(4096);
+DEFINE_PER_CPU(char, hv_24x7_resb[4096]) __aligned(4096);
+
 static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix,
 					 u16 lpar, u64 *res,
 					 bool success_expected)
 {
-	unsigned long ret = -ENOMEM;
+	unsigned long ret;
 
 	/*
 	 * request_buffer and result_buffer are not required to be 4k aligned,
@@ -243,13 +246,11 @@ static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix,
 	BUILD_BUG_ON(sizeof(*request_buffer) > 4096);
 	BUILD_BUG_ON(sizeof(*result_buffer) > 4096);
 
-	request_buffer = kmem_cache_zalloc(hv_page_cache, GFP_USER);
-	if (!request_buffer)
-		goto out;
+	request_buffer = (void *)get_cpu_var(hv_24x7_reqb);
+	result_buffer = (void *)get_cpu_var(hv_24x7_resb);
 
-	result_buffer = kmem_cache_zalloc(hv_page_cache, GFP_USER);
-	if (!result_buffer)
-		goto out_free_request_buffer;
+	memset(request_buffer, 0, 4096);
+	memset(result_buffer, 0, 4096);
 
 	*request_buffer = (struct reqb) {
 		.buf = {
@@ -278,15 +279,11 @@ static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix,
 				domain, offset, ix, lpar, ret, ret,
 				result_buffer->buf.detailed_rc,
 				result_buffer->buf.failing_request_ix);
-		goto out_free_result_buffer;
+		goto out;
 	}
 
 	*res = be64_to_cpu(result_buffer->result);
 
-out_free_result_buffer:
-	kfree(result_buffer);
-out_free_request_buffer:
-	kfree(request_buffer);
 out:
 	return ret;
 }
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index 8a106b4172e..28e558d3316 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -163,7 +163,7 @@ static unsigned int iic_get_irq(void)
 
 void iic_setup_cpu(void)
 {
-	out_be64(&__get_cpu_var(cpu_iic).regs->prio, 0xff);
+	out_be64(&this_cpu_ptr(&cpu_iic)->regs->prio, 0xff);
 }
 
 u8 iic_get_target_id(int cpu)
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 2b90ff8a93b..59ef76c5f4f 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -197,7 +197,7 @@ static int tce_build_cell(struct iommu_table *tbl, long index, long npages,
 
 	io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset);
 
-	for (i = 0; i < npages; i++, uaddr += tbl->it_page_shift)
+	for (i = 0; i < npages; i++, uaddr += (1 << tbl->it_page_shift))
 		io_pte[i] = base_pte | (__pa(uaddr) & CBE_IOPTE_RPN_Mask);
 
 	mb();
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 87ba7cf99cd..65d633f20d3 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -164,7 +164,7 @@ static void spufs_prune_dir(struct dentry *dir)
 	struct dentry *dentry, *tmp;
 
 	mutex_lock(&dir->d_inode->i_mutex);
-	list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_u.d_child) {
+	list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) {
 		spin_lock(&dentry->d_lock);
 		if (!(d_unhashed(dentry)) && dentry->d_inode) {
 			dget_dlock(dentry);
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index feb549aa3ee..b67ea67eb71 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -40,7 +40,6 @@ BEGIN_FTR_SECTION;						\
 	b	1f;						\
 END_FTR_SECTION(0, 1);						\
 	ld	r12,opal_tracepoint_refcount@toc(r2);		\
-	std	r12,32(r1);					\
 	cmpdi	r12,0;						\
 	bne-	LABEL;						\
 1:
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 3ba435ec3dc..86a7256d84e 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1355,13 +1355,13 @@ static void set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq)
 
 #ifdef CONFIG_CXL_BASE
 
-struct device_node *pnv_pci_to_phb_node(struct pci_dev *dev)
+struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev)
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
 
-	return hose->dn;
+	return of_node_get(hose->dn);
 }
-EXPORT_SYMBOL(pnv_pci_to_phb_node);
+EXPORT_SYMBOL(pnv_pci_get_phb_node);
 
 int pnv_phb_to_cxl(struct pci_dev *dev)
 {
@@ -1645,7 +1645,8 @@ static void pnv_ioda_setup_pe_seg(struct pci_controller *hose,
 				region.start += phb->ioda.io_segsize;
 				index++;
 			}
-		} else if (res->flags & IORESOURCE_MEM) {
+		} else if ((res->flags & IORESOURCE_MEM) &&
+			   !pnv_pci_is_mem_pref_64(res->flags)) {
 			region.start = res->start -
 				       hose->mem_offset[0] -
 				       phb->ioda.m32_pci_base;
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index e7cb6d4a871..f8c9ff7886e 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -25,10 +25,10 @@
 static struct kobject *mobility_kobj;
 
 struct update_props_workarea {
-	u32 phandle;
-	u32 state;
-	u64 reserved;
-	u32 nprops;
+	__be32 phandle;
+	__be32 state;
+	__be64 reserved;
+	__be32 nprops;
 } __packed;
 
 #define NODE_ACTION_MASK	0xff000000
@@ -54,11 +54,11 @@ static int mobility_rtas_call(int token, char *buf, s32 scope)
 	return rc;
 }
 
-static int delete_dt_node(u32 phandle)
+static int delete_dt_node(__be32 phandle)
 {
 	struct device_node *dn;
 
-	dn = of_find_node_by_phandle(phandle);
+	dn = of_find_node_by_phandle(be32_to_cpu(phandle));
 	if (!dn)
 		return -ENOENT;
 
@@ -127,7 +127,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop,
 	return 0;
 }
 
-static int update_dt_node(u32 phandle, s32 scope)
+static int update_dt_node(__be32 phandle, s32 scope)
 {
 	struct update_props_workarea *upwa;
 	struct device_node *dn;
@@ -136,6 +136,7 @@ static int update_dt_node(u32 phandle, s32 scope)
 	char *prop_data;
 	char *rtas_buf;
 	int update_properties_token;
+	u32 nprops;
 	u32 vd;
 
 	update_properties_token = rtas_token("ibm,update-properties");
@@ -146,7 +147,7 @@ static int update_dt_node(u32 phandle, s32 scope)
 	if (!rtas_buf)
 		return -ENOMEM;
 
-	dn = of_find_node_by_phandle(phandle);
+	dn = of_find_node_by_phandle(be32_to_cpu(phandle));
 	if (!dn) {
 		kfree(rtas_buf);
 		return -ENOENT;
@@ -162,6 +163,7 @@ static int update_dt_node(u32 phandle, s32 scope)
 			break;
 
 		prop_data = rtas_buf + sizeof(*upwa);
+		nprops = be32_to_cpu(upwa->nprops);
 
 		/* On the first call to ibm,update-properties for a node the
 		 * the first property value descriptor contains an empty
@@ -170,17 +172,17 @@ static int update_dt_node(u32 phandle, s32 scope)
 		 */
 		if (*prop_data == 0) {
 			prop_data++;
-			vd = *(u32 *)prop_data;
+			vd = be32_to_cpu(*(__be32 *)prop_data);
 			prop_data += vd + sizeof(vd);
-			upwa->nprops--;
+			nprops--;
 		}
 
-		for (i = 0; i < upwa->nprops; i++) {
+		for (i = 0; i < nprops; i++) {
 			char *prop_name;
 
 			prop_name = prop_data;
 			prop_data += strlen(prop_name) + 1;
-			vd = *(u32 *)prop_data;
+			vd = be32_to_cpu(*(__be32 *)prop_data);
 			prop_data += sizeof(vd);
 
 			switch (vd) {
@@ -212,13 +214,13 @@ static int update_dt_node(u32 phandle, s32 scope)
 	return 0;
 }
 
-static int add_dt_node(u32 parent_phandle, u32 drc_index)
+static int add_dt_node(__be32 parent_phandle, __be32 drc_index)
 {
 	struct device_node *dn;
 	struct device_node *parent_dn;
 	int rc;
 
-	parent_dn = of_find_node_by_phandle(parent_phandle);
+	parent_dn = of_find_node_by_phandle(be32_to_cpu(parent_phandle));
 	if (!parent_dn)
 		return -ENOENT;
 
@@ -237,7 +239,7 @@ static int add_dt_node(u32 parent_phandle, u32 drc_index)
 int pseries_devicetree_update(s32 scope)
 {
 	char *rtas_buf;
-	u32 *data;
+	__be32 *data;
 	int update_nodes_token;
 	int rc;
 
@@ -254,17 +256,17 @@ int pseries_devicetree_update(s32 scope)
 		if (rc && rc != 1)
 			break;
 
-		data = (u32 *)rtas_buf + 4;
-		while (*data & NODE_ACTION_MASK) {
+		data = (__be32 *)rtas_buf + 4;
+		while (be32_to_cpu(*data) & NODE_ACTION_MASK) {
 			int i;
-			u32 action = *data & NODE_ACTION_MASK;
-			int node_count = *data & NODE_COUNT_MASK;
+			u32 action = be32_to_cpu(*data) & NODE_ACTION_MASK;
+			u32 node_count = be32_to_cpu(*data) & NODE_COUNT_MASK;
 
 			data++;
 
 			for (i = 0; i < node_count; i++) {
-				u32 phandle = *data++;
-				u32 drc_index;
+				__be32 phandle = *data++;
+				__be32 drc_index;
 
 				switch (action) {
 				case DELETE_DT_NODE:
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index ad56edc3991..e8bb33b2d3c 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -156,7 +156,7 @@ axon_ram_direct_access(struct block_device *device, sector_t sector,
 	}
 
 	*kaddr = (void *)(bank->ph_addr + offset);
-	*pfn = virt_to_phys(kaddr) >> PAGE_SHIFT;
+	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
 
 	return 0;
 }
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index c8efbb37d6e..e23f559faa4 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -293,6 +293,7 @@ static inline void disable_surveillance(void)
 	args.token = rtas_token("set-indicator");
 	if (args.token == RTAS_UNKNOWN_SERVICE)
 		return;
+	args.token = cpu_to_be32(args.token);
 	args.nargs = cpu_to_be32(3);
 	args.nret = cpu_to_be32(1);
 	args.rets = &args.args[3];
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index 23223cd63e5..1f272b24fc0 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -979,7 +979,7 @@ static void __exit aes_s390_fini(void)
 module_init(aes_s390_init);
 module_exit(aes_s390_fini);
 
-MODULE_ALIAS("aes-all");
+MODULE_ALIAS_CRYPTO("aes-all");
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm");
 MODULE_LICENSE("GPL");
diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c
index 7acb77f7ef1..9e05cc453a4 100644
--- a/arch/s390/crypto/des_s390.c
+++ b/arch/s390/crypto/des_s390.c
@@ -619,8 +619,8 @@ static void __exit des_s390_exit(void)
 module_init(des_s390_init);
 module_exit(des_s390_exit);
 
-MODULE_ALIAS("des");
-MODULE_ALIAS("des3_ede");
+MODULE_ALIAS_CRYPTO("des");
+MODULE_ALIAS_CRYPTO("des3_ede");
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms");
diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c
index d43485d142e..b258110da95 100644
--- a/arch/s390/crypto/ghash_s390.c
+++ b/arch/s390/crypto/ghash_s390.c
@@ -16,11 +16,12 @@
 #define GHASH_DIGEST_SIZE	16
 
 struct ghash_ctx {
-	u8 icv[16];
-	u8 key[16];
+	u8 key[GHASH_BLOCK_SIZE];
 };
 
 struct ghash_desc_ctx {
+	u8 icv[GHASH_BLOCK_SIZE];
+	u8 key[GHASH_BLOCK_SIZE];
 	u8 buffer[GHASH_BLOCK_SIZE];
 	u32 bytes;
 };
@@ -28,8 +29,10 @@ struct ghash_desc_ctx {
 static int ghash_init(struct shash_desc *desc)
 {
 	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+	struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
 
 	memset(dctx, 0, sizeof(*dctx));
+	memcpy(dctx->key, ctx->key, GHASH_BLOCK_SIZE);
 
 	return 0;
 }
@@ -45,7 +48,6 @@ static int ghash_setkey(struct crypto_shash *tfm,
 	}
 
 	memcpy(ctx->key, key, GHASH_BLOCK_SIZE);
-	memset(ctx->icv, 0, GHASH_BLOCK_SIZE);
 
 	return 0;
 }
@@ -54,7 +56,6 @@ static int ghash_update(struct shash_desc *desc,
 			 const u8 *src, unsigned int srclen)
 {
 	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-	struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
 	unsigned int n;
 	u8 *buf = dctx->buffer;
 	int ret;
@@ -70,7 +71,7 @@ static int ghash_update(struct shash_desc *desc,
 		src += n;
 
 		if (!dctx->bytes) {
-			ret = crypt_s390_kimd(KIMD_GHASH, ctx, buf,
+			ret = crypt_s390_kimd(KIMD_GHASH, dctx, buf,
 					      GHASH_BLOCK_SIZE);
 			if (ret != GHASH_BLOCK_SIZE)
 				return -EIO;
@@ -79,7 +80,7 @@ static int ghash_update(struct shash_desc *desc,
 
 	n = srclen & ~(GHASH_BLOCK_SIZE - 1);
 	if (n) {
-		ret = crypt_s390_kimd(KIMD_GHASH, ctx, src, n);
+		ret = crypt_s390_kimd(KIMD_GHASH, dctx, src, n);
 		if (ret != n)
 			return -EIO;
 		src += n;
@@ -94,7 +95,7 @@ static int ghash_update(struct shash_desc *desc,
 	return 0;
 }
 
-static int ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx)
+static int ghash_flush(struct ghash_desc_ctx *dctx)
 {
 	u8 *buf = dctx->buffer;
 	int ret;
@@ -104,24 +105,24 @@ static int ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx)
 
 		memset(pos, 0, dctx->bytes);
 
-		ret = crypt_s390_kimd(KIMD_GHASH, ctx, buf, GHASH_BLOCK_SIZE);
+		ret = crypt_s390_kimd(KIMD_GHASH, dctx, buf, GHASH_BLOCK_SIZE);
 		if (ret != GHASH_BLOCK_SIZE)
 			return -EIO;
+
+		dctx->bytes = 0;
 	}
 
-	dctx->bytes = 0;
 	return 0;
 }
 
 static int ghash_final(struct shash_desc *desc, u8 *dst)
 {
 	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-	struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
 	int ret;
 
-	ret = ghash_flush(ctx, dctx);
+	ret = ghash_flush(dctx);
 	if (!ret)
-		memcpy(dst, ctx->icv, GHASH_BLOCK_SIZE);
+		memcpy(dst, dctx->icv, GHASH_BLOCK_SIZE);
 	return ret;
 }
 
@@ -160,7 +161,7 @@ static void __exit ghash_mod_exit(void)
 module_init(ghash_mod_init);
 module_exit(ghash_mod_exit);
 
-MODULE_ALIAS("ghash");
+MODULE_ALIAS_CRYPTO("ghash");
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("GHASH Message Digest Algorithm, s390 implementation");
diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c
index a1b3a9dc9d8..5b2bee32369 100644
--- a/arch/s390/crypto/sha1_s390.c
+++ b/arch/s390/crypto/sha1_s390.c
@@ -103,6 +103,6 @@ static void __exit sha1_s390_fini(void)
 module_init(sha1_s390_init);
 module_exit(sha1_s390_fini);
 
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm");
diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c
index 9b853809a49..b74ff158108 100644
--- a/arch/s390/crypto/sha256_s390.c
+++ b/arch/s390/crypto/sha256_s390.c
@@ -143,7 +143,7 @@ static void __exit sha256_s390_fini(void)
 module_init(sha256_s390_init);
 module_exit(sha256_s390_fini);
 
-MODULE_ALIAS("sha256");
-MODULE_ALIAS("sha224");
+MODULE_ALIAS_CRYPTO("sha256");
+MODULE_ALIAS_CRYPTO("sha224");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA256 and SHA224 Secure Hash Algorithm");
diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c
index 32a81383b69..0c36989ba18 100644
--- a/arch/s390/crypto/sha512_s390.c
+++ b/arch/s390/crypto/sha512_s390.c
@@ -86,7 +86,7 @@ static struct shash_alg sha512_alg = {
 	}
 };
 
-MODULE_ALIAS("sha512");
+MODULE_ALIAS_CRYPTO("sha512");
 
 static int sha384_init(struct shash_desc *desc)
 {
@@ -126,7 +126,7 @@ static struct shash_alg sha384_alg = {
 	}
 };
 
-MODULE_ALIAS("sha384");
+MODULE_ALIAS_CRYPTO("sha384");
 
 static int __init init(void)
 {
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 57c882761de..b0373b44b32 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -582,7 +582,7 @@ static inline int pmd_large(pmd_t pmd)
 	return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0;
 }
 
-static inline int pmd_pfn(pmd_t pmd)
+static inline unsigned long pmd_pfn(pmd_t pmd)
 {
 	unsigned long origin_mask;
 
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index ca38139423a..437e6115927 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -249,7 +249,7 @@ COMPAT_SYSCALL_DEFINE2(s390_setgroups16, int, gidsetsize, u16 __user *, grouplis
 	struct group_info *group_info;
 	int retval;
 
-	if (!capable(CAP_SETGID))
+	if (!may_setgroups())
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 9f73c805902..49b74454d7e 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -415,7 +415,7 @@ static void *nt_s390_vx_low(void *ptr, __vector128 *vx_regs)
 	ptr += len;
 	/* Copy lower halves of SIMD registers 0-15 */
 	for (i = 0; i < 16; i++) {
-		memcpy(ptr, &vx_regs[i], 8);
+		memcpy(ptr, &vx_regs[i].u[2], 8);
 		ptr += 8;
 	}
 	return ptr;
diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c
index 1c4c5accd22..d3236c9e226 100644
--- a/arch/s390/kernel/suspend.c
+++ b/arch/s390/kernel/suspend.c
@@ -138,6 +138,8 @@ int pfn_is_nosave(unsigned long pfn)
 {
 	unsigned long nosave_begin_pfn = PFN_DOWN(__pa(&__nosave_begin));
 	unsigned long nosave_end_pfn = PFN_DOWN(__pa(&__nosave_end));
+	unsigned long eshared_pfn = PFN_DOWN(__pa(&_eshared)) - 1;
+	unsigned long stext_pfn = PFN_DOWN(__pa(&_stext));
 
 	/* Always save lowcore pages (LC protection might be enabled). */
 	if (pfn <= LC_PAGES)
@@ -145,6 +147,8 @@ int pfn_is_nosave(unsigned long pfn)
 	if (pfn >= nosave_begin_pfn && pfn < nosave_end_pfn)
 		return 1;
 	/* Skip memory holes and read-only pages (NSS, DCSS, ...). */
+	if (pfn >= stext_pfn && pfn <= eshared_pfn)
+		return ipl_info.type == IPL_TYPE_NSS ? 1 : 0;
 	if (tprot(PFN_PHYS(pfn)))
 		return 1;
 	return 0;
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 0f961a1c64b..6dc0ad9c705 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -229,10 +229,12 @@ static void ipte_lock_simple(struct kvm_vcpu *vcpu)
 		goto out;
 	ic = &vcpu->kvm->arch.sca->ipte_control;
 	do {
-		old = ACCESS_ONCE(*ic);
+		old = *ic;
+		barrier();
 		while (old.k) {
 			cond_resched();
-			old = ACCESS_ONCE(*ic);
+			old = *ic;
+			barrier();
 		}
 		new = old;
 		new.k = 1;
@@ -251,7 +253,9 @@ static void ipte_unlock_simple(struct kvm_vcpu *vcpu)
 		goto out;
 	ic = &vcpu->kvm->arch.sca->ipte_control;
 	do {
-		new = old = ACCESS_ONCE(*ic);
+		old = *ic;
+		barrier();
+		new = old;
 		new.k = 0;
 	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
 	wake_up(&vcpu->kvm->arch.ipte_wq);
@@ -265,10 +269,12 @@ static void ipte_lock_siif(struct kvm_vcpu *vcpu)
 
 	ic = &vcpu->kvm->arch.sca->ipte_control;
 	do {
-		old = ACCESS_ONCE(*ic);
+		old = *ic;
+		barrier();
 		while (old.kg) {
 			cond_resched();
-			old = ACCESS_ONCE(*ic);
+			old = *ic;
+			barrier();
 		}
 		new = old;
 		new.k = 1;
@@ -282,7 +288,9 @@ static void ipte_unlock_siif(struct kvm_vcpu *vcpu)
 
 	ic = &vcpu->kvm->arch.sca->ipte_control;
 	do {
-		new = old = ACCESS_ONCE(*ic);
+		old = *ic;
+		barrier();
+		new = old;
 		new.kh--;
 		if (!new.kh)
 			new.k = 0;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index a39838457f0..cd6344d334c 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -16,6 +16,7 @@
 #include <linux/mmu_context.h>
 #include <linux/signal.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <asm/asm-offsets.h>
 #include <asm/uaccess.h>
 #include "kvm-s390.h"
@@ -270,7 +271,7 @@ static int __must_check __deliver_prog_irq(struct kvm_vcpu *vcpu,
 		break;
 	case PGM_MONITOR:
 		rc = put_guest_lc(vcpu, pgm_info->mon_class_nr,
-				  (u64 *)__LC_MON_CLASS_NR);
+				  (u16 *)__LC_MON_CLASS_NR);
 		rc |= put_guest_lc(vcpu, pgm_info->mon_code,
 				   (u64 *)__LC_MON_CODE);
 		break;
@@ -613,7 +614,7 @@ no_timer:
 	__unset_cpu_idle(vcpu);
 	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 
-	hrtimer_try_to_cancel(&vcpu->arch.ckc_timer);
+	hrtimer_cancel(&vcpu->arch.ckc_timer);
 	return 0;
 }
 
@@ -633,10 +634,20 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
 enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
 {
 	struct kvm_vcpu *vcpu;
+	u64 now, sltime;
 
 	vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
-	kvm_s390_vcpu_wakeup(vcpu);
+	now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
+	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
 
+	/*
+	 * If the monotonic clock runs faster than the tod clock we might be
+	 * woken up too early and have to go back to sleep to avoid deadlocks.
+	 */
+	if (vcpu->arch.sie_block->ckc > now &&
+	    hrtimer_forward_now(timer, ns_to_ktime(sltime)))
+		return HRTIMER_RESTART;
+	kvm_s390_vcpu_wakeup(vcpu);
 	return HRTIMER_NORESTART;
 }
 
@@ -774,7 +785,6 @@ struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
 
 	if ((!schid && !cr6) || (schid && cr6))
 		return NULL;
-	mutex_lock(&kvm->lock);
 	fi = &kvm->arch.float_int;
 	spin_lock(&fi->lock);
 	inti = NULL;
@@ -802,7 +812,6 @@ struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
 	if (list_empty(&fi->list))
 		atomic_set(&fi->active, 0);
 	spin_unlock(&fi->lock);
-	mutex_unlock(&kvm->lock);
 	return inti;
 }
 
@@ -815,7 +824,6 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 	int sigcpu;
 	int rc = 0;
 
-	mutex_lock(&kvm->lock);
 	fi = &kvm->arch.float_int;
 	spin_lock(&fi->lock);
 	if (fi->irq_count >= KVM_S390_MAX_FLOAT_IRQS) {
@@ -840,6 +848,8 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 		list_add_tail(&inti->list, &iter->list);
 	}
 	atomic_set(&fi->active, 1);
+	if (atomic_read(&kvm->online_vcpus) == 0)
+		goto unlock_fi;
 	sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
 	if (sigcpu == KVM_MAX_VCPUS) {
 		do {
@@ -856,7 +866,6 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 	kvm_s390_vcpu_wakeup(kvm_get_vcpu(kvm, sigcpu));
 unlock_fi:
 	spin_unlock(&fi->lock);
-	mutex_unlock(&kvm->lock);
 	return rc;
 }
 
@@ -864,6 +873,7 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 		       struct kvm_s390_interrupt *s390int)
 {
 	struct kvm_s390_interrupt_info *inti;
+	int rc;
 
 	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
 	if (!inti)
@@ -911,13 +921,16 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 	trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64,
 				 2);
 
-	return __inject_vm(kvm, inti);
+	rc = __inject_vm(kvm, inti);
+	if (rc)
+		kfree(inti);
+	return rc;
 }
 
-void kvm_s390_reinject_io_int(struct kvm *kvm,
+int kvm_s390_reinject_io_int(struct kvm *kvm,
 			      struct kvm_s390_interrupt_info *inti)
 {
-	__inject_vm(kvm, inti);
+	return __inject_vm(kvm, inti);
 }
 
 int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
@@ -1013,7 +1026,6 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm)
 	struct kvm_s390_float_interrupt *fi;
 	struct kvm_s390_interrupt_info	*n, *inti = NULL;
 
-	mutex_lock(&kvm->lock);
 	fi = &kvm->arch.float_int;
 	spin_lock(&fi->lock);
 	list_for_each_entry_safe(inti, n, &fi->list, list) {
@@ -1023,66 +1035,68 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm)
 	fi->irq_count = 0;
 	atomic_set(&fi->active, 0);
 	spin_unlock(&fi->lock);
-	mutex_unlock(&kvm->lock);
 }
 
-static inline int copy_irq_to_user(struct kvm_s390_interrupt_info *inti,
-				   u8 *addr)
+static void inti_to_irq(struct kvm_s390_interrupt_info *inti,
+		       struct kvm_s390_irq *irq)
 {
-	struct kvm_s390_irq __user *uptr = (struct kvm_s390_irq __user *) addr;
-	struct kvm_s390_irq irq = {0};
-
-	irq.type = inti->type;
+	irq->type = inti->type;
 	switch (inti->type) {
 	case KVM_S390_INT_PFAULT_INIT:
 	case KVM_S390_INT_PFAULT_DONE:
 	case KVM_S390_INT_VIRTIO:
 	case KVM_S390_INT_SERVICE:
-		irq.u.ext = inti->ext;
+		irq->u.ext = inti->ext;
 		break;
 	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
-		irq.u.io = inti->io;
+		irq->u.io = inti->io;
 		break;
 	case KVM_S390_MCHK:
-		irq.u.mchk = inti->mchk;
+		irq->u.mchk = inti->mchk;
 		break;
-	default:
-		return -EINVAL;
 	}
-
-	if (copy_to_user(uptr, &irq, sizeof(irq)))
-		return -EFAULT;
-
-	return 0;
 }
 
-static int get_all_floating_irqs(struct kvm *kvm, __u8 *buf, __u64 len)
+static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len)
 {
 	struct kvm_s390_interrupt_info *inti;
 	struct kvm_s390_float_interrupt *fi;
+	struct kvm_s390_irq *buf;
+	int max_irqs;
 	int ret = 0;
 	int n = 0;
 
-	mutex_lock(&kvm->lock);
+	if (len > KVM_S390_FLIC_MAX_BUFFER || len == 0)
+		return -EINVAL;
+
+	/*
+	 * We are already using -ENOMEM to signal
+	 * userspace it may retry with a bigger buffer,
+	 * so we need to use something else for this case
+	 */
+	buf = vzalloc(len);
+	if (!buf)
+		return -ENOBUFS;
+
+	max_irqs = len / sizeof(struct kvm_s390_irq);
+
 	fi = &kvm->arch.float_int;
 	spin_lock(&fi->lock);
-
 	list_for_each_entry(inti, &fi->list, list) {
-		if (len < sizeof(struct kvm_s390_irq)) {
+		if (n == max_irqs) {
 			/* signal userspace to try again */
 			ret = -ENOMEM;
 			break;
 		}
-		ret = copy_irq_to_user(inti, buf);
-		if (ret)
-			break;
-		buf += sizeof(struct kvm_s390_irq);
-		len -= sizeof(struct kvm_s390_irq);
+		inti_to_irq(inti, &buf[n]);
 		n++;
 	}
-
 	spin_unlock(&fi->lock);
-	mutex_unlock(&kvm->lock);
+	if (!ret && n > 0) {
+		if (copy_to_user(usrbuf, buf, sizeof(struct kvm_s390_irq) * n))
+			ret = -EFAULT;
+	}
+	vfree(buf);
 
 	return ret < 0 ? ret : n;
 }
@@ -1093,7 +1107,7 @@ static int flic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 
 	switch (attr->group) {
 	case KVM_DEV_FLIC_GET_ALL_IRQS:
-		r = get_all_floating_irqs(dev->kvm, (u8 *) attr->addr,
+		r = get_all_floating_irqs(dev->kvm, (u8 __user *) attr->addr,
 					  attr->attr);
 		break;
 	default:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 55aade49b6d..49e4d64ff74 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -152,7 +152,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_S390_CSS_SUPPORT:
-	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_ENABLE_CAP_VM:
@@ -662,7 +661,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 		if (rc)
 			return rc;
 	}
-	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
+	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
 	get_cpu_id(&vcpu->arch.cpu_id);
 	vcpu->arch.cpu_id.version = 0xff;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 244d0230318..4c173474ecf 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -148,8 +148,8 @@ int __must_check kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 int __must_check kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
 struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
 						    u64 cr6, u64 schid);
-void kvm_s390_reinject_io_int(struct kvm *kvm,
-			      struct kvm_s390_interrupt_info *inti);
+int kvm_s390_reinject_io_int(struct kvm *kvm,
+			     struct kvm_s390_interrupt_info *inti);
 int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked);
 
 /* implemented in priv.c */
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 72bb2dd8b9c..a30102c4d70 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -228,18 +228,19 @@ static int handle_tpi(struct kvm_vcpu *vcpu)
 	struct kvm_s390_interrupt_info *inti;
 	unsigned long len;
 	u32 tpi_data[3];
-	int cc, rc;
+	int rc;
 	u64 addr;
 
-	rc = 0;
 	addr = kvm_s390_get_base_disp_s(vcpu);
 	if (addr & 3)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
-	cc = 0;
+
 	inti = kvm_s390_get_io_int(vcpu->kvm, vcpu->arch.sie_block->gcr[6], 0);
-	if (!inti)
-		goto no_interrupt;
-	cc = 1;
+	if (!inti) {
+		kvm_s390_set_psw_cc(vcpu, 0);
+		return 0;
+	}
+
 	tpi_data[0] = inti->io.subchannel_id << 16 | inti->io.subchannel_nr;
 	tpi_data[1] = inti->io.io_int_parm;
 	tpi_data[2] = inti->io.io_int_word;
@@ -250,30 +251,38 @@ static int handle_tpi(struct kvm_vcpu *vcpu)
 		 */
 		len = sizeof(tpi_data) - 4;
 		rc = write_guest(vcpu, addr, &tpi_data, len);
-		if (rc)
-			return kvm_s390_inject_prog_cond(vcpu, rc);
+		if (rc) {
+			rc = kvm_s390_inject_prog_cond(vcpu, rc);
+			goto reinject_interrupt;
+		}
 	} else {
 		/*
 		 * Store the three-word I/O interruption code into
 		 * the appropriate lowcore area.
 		 */
 		len = sizeof(tpi_data);
-		if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len))
+		if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len)) {
+			/* failed writes to the low core are not recoverable */
 			rc = -EFAULT;
+			goto reinject_interrupt;
+		}
 	}
+
+	/* irq was successfully handed to the guest */
+	kfree(inti);
+	kvm_s390_set_psw_cc(vcpu, 1);
+	return 0;
+reinject_interrupt:
 	/*
 	 * If we encounter a problem storing the interruption code, the
 	 * instruction is suppressed from the guest's view: reinject the
 	 * interrupt.
 	 */
-	if (!rc)
+	if (kvm_s390_reinject_io_int(vcpu->kvm, inti)) {
 		kfree(inti);
-	else
-		kvm_s390_reinject_io_int(vcpu->kvm, inti);
-no_interrupt:
-	/* Set condition code and we're done. */
-	if (!rc)
-		kvm_s390_set_psw_cc(vcpu, cc);
+		rc = -EFAULT;
+	}
+	/* don't set the cc, a pgm irq was injected or we drop to user space */
 	return rc ? -EFAULT : 0;
 }
 
@@ -461,6 +470,7 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem)
 	for (n = mem->count - 1; n > 0 ; n--)
 		memcpy(&mem->vm[n], &mem->vm[n - 1], sizeof(mem->vm[0]));
 
+	memset(&mem->vm[0], 0, sizeof(mem->vm[0]));
 	mem->vm[0].cpus_total = cpus;
 	mem->vm[0].cpus_configured = cpus;
 	mem->vm[0].cpus_standby = 0;
@@ -791,7 +801,7 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu)
 			break;
 		reg = (reg + 1) % 16;
 	} while (1);
-
+	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 	return 0;
 }
 
@@ -863,7 +873,7 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
 			break;
 		reg = (reg + 1) % 16;
 	} while (1);
-
+	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 	return 0;
 }
 
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index a2b81d6ce8a..fbe8f2cf924 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -374,6 +374,12 @@ static noinline void do_fault_error(struct pt_regs *regs, int fault)
 				do_no_context(regs);
 			else
 				pagefault_out_of_memory();
+		} else if (fault & VM_FAULT_SIGSEGV) {
+			/* Kernel mode? Handle exceptions or die */
+			if (!user_mode(regs))
+				do_no_context(regs);
+			else
+				do_sigsegv(regs, SEGV_MAPERR);
 		} else if (fault & VM_FAULT_SIGBUS) {
 			/* Kernel mode? Handle exceptions or die */
 			if (!user_mode(regs))
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 3c80d2e38f0..210ffede015 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -192,12 +192,6 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 	return 0;
 }
 
-struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
-			      int write)
-{
-	return ERR_PTR(-EINVAL);
-}
-
 int pmd_huge(pmd_t pmd)
 {
 	if (!MACHINE_HAS_HPAGE)
@@ -210,17 +204,3 @@ int pud_huge(pud_t pud)
 {
 	return 0;
 }
-
-struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-			     pmd_t *pmdp, int write)
-{
-	struct page *page;
-
-	if (!MACHINE_HAS_HPAGE)
-		return NULL;
-
-	page = pmd_page(*pmdp);
-	if (page)
-		page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT);
-	return page;
-}
diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c
index 52238983527..6860beb2a28 100644
--- a/arch/score/mm/fault.c
+++ b/arch/score/mm/fault.c
@@ -114,6 +114,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 541dc610150..a58fec9b55e 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -353,6 +353,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 	} else {
 		if (fault & VM_FAULT_SIGBUS)
 			do_sigbus(regs, error_code, address);
+		else if (fault & VM_FAULT_SIGSEGV)
+			bad_area(regs, error_code, address);
 		else
 			BUG();
 	}
diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c
index d7762349ea4..534bc978af8 100644
--- a/arch/sh/mm/hugetlbpage.c
+++ b/arch/sh/mm/hugetlbpage.c
@@ -67,12 +67,6 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 	return 0;
 }
 
-struct page *follow_huge_addr(struct mm_struct *mm,
-			      unsigned long address, int write)
-{
-	return ERR_PTR(-EINVAL);
-}
-
 int pmd_huge(pmd_t pmd)
 {
 	return 0;
@@ -82,9 +76,3 @@ int pud_huge(pud_t pud)
 {
 	return 0;
 }
-
-struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-			     pmd_t *pmd, int write)
-{
-	return NULL;
-}
diff --git a/arch/sparc/crypto/aes_glue.c b/arch/sparc/crypto/aes_glue.c
index df922f52d76..705408766ab 100644
--- a/arch/sparc/crypto/aes_glue.c
+++ b/arch/sparc/crypto/aes_glue.c
@@ -499,6 +499,6 @@ module_exit(aes_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("AES Secure Hash Algorithm, sparc64 aes opcode accelerated");
 
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
 
 #include "crop_devid.c"
diff --git a/arch/sparc/crypto/camellia_glue.c b/arch/sparc/crypto/camellia_glue.c
index 888f6260b4e..641f55cb61c 100644
--- a/arch/sparc/crypto/camellia_glue.c
+++ b/arch/sparc/crypto/camellia_glue.c
@@ -322,6 +322,6 @@ module_exit(camellia_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Camellia Cipher Algorithm, sparc64 camellia opcode accelerated");
 
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
 
 #include "crop_devid.c"
diff --git a/arch/sparc/crypto/crc32c_glue.c b/arch/sparc/crypto/crc32c_glue.c
index 5162fad912c..d1064e46efe 100644
--- a/arch/sparc/crypto/crc32c_glue.c
+++ b/arch/sparc/crypto/crc32c_glue.c
@@ -176,6 +176,6 @@ module_exit(crc32c_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("CRC32c (Castagnoli), sparc64 crc32c opcode accelerated");
 
-MODULE_ALIAS("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c");
 
 #include "crop_devid.c"
diff --git a/arch/sparc/crypto/des_glue.c b/arch/sparc/crypto/des_glue.c
index 3065bc61f9d..d1150097299 100644
--- a/arch/sparc/crypto/des_glue.c
+++ b/arch/sparc/crypto/des_glue.c
@@ -532,6 +532,6 @@ module_exit(des_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms, sparc64 des opcode accelerated");
 
-MODULE_ALIAS("des");
+MODULE_ALIAS_CRYPTO("des");
 
 #include "crop_devid.c"
diff --git a/arch/sparc/crypto/md5_glue.c b/arch/sparc/crypto/md5_glue.c
index 09a9ea1dfb6..64c7ff5f72a 100644
--- a/arch/sparc/crypto/md5_glue.c
+++ b/arch/sparc/crypto/md5_glue.c
@@ -185,6 +185,6 @@ module_exit(md5_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MD5 Secure Hash Algorithm, sparc64 md5 opcode accelerated");
 
-MODULE_ALIAS("md5");
+MODULE_ALIAS_CRYPTO("md5");
 
 #include "crop_devid.c"
diff --git a/arch/sparc/crypto/sha1_glue.c b/arch/sparc/crypto/sha1_glue.c
index 6cd5f29e1e0..1b3e47accc7 100644
--- a/arch/sparc/crypto/sha1_glue.c
+++ b/arch/sparc/crypto/sha1_glue.c
@@ -180,6 +180,6 @@ module_exit(sha1_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, sparc64 sha1 opcode accelerated");
 
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
 
 #include "crop_devid.c"
diff --git a/arch/sparc/crypto/sha256_glue.c b/arch/sparc/crypto/sha256_glue.c
index 04f555ab268..41f27cca2a2 100644
--- a/arch/sparc/crypto/sha256_glue.c
+++ b/arch/sparc/crypto/sha256_glue.c
@@ -237,7 +237,7 @@ module_exit(sha256_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm, sparc64 sha256 opcode accelerated");
 
-MODULE_ALIAS("sha224");
-MODULE_ALIAS("sha256");
+MODULE_ALIAS_CRYPTO("sha224");
+MODULE_ALIAS_CRYPTO("sha256");
 
 #include "crop_devid.c"
diff --git a/arch/sparc/crypto/sha512_glue.c b/arch/sparc/crypto/sha512_glue.c
index f04d1994d19..9fff88541b8 100644
--- a/arch/sparc/crypto/sha512_glue.c
+++ b/arch/sparc/crypto/sha512_glue.c
@@ -222,7 +222,7 @@ module_exit(sha512_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA-384 and SHA-512 Secure Hash Algorithm, sparc64 sha512 opcode accelerated");
 
-MODULE_ALIAS("sha384");
-MODULE_ALIAS("sha512");
+MODULE_ALIAS_CRYPTO("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
 
 #include "crop_devid.c"
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index 4310332872d..71762565513 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -2307,7 +2307,7 @@ void *ldc_alloc_exp_dring(struct ldc_channel *lp, unsigned int len,
 	if (len & (8UL - 1))
 		return ERR_PTR(-EINVAL);
 
-	buf = kzalloc(len, GFP_KERNEL);
+	buf = kzalloc(len, GFP_ATOMIC);
 	if (!buf)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 46a5e450875..af53c25da2e 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -960,6 +960,8 @@ out:
 	cpuc->pcr[0] |= cpuc->event[0]->hw.config_base;
 }
 
+static void sparc_pmu_start(struct perf_event *event, int flags);
+
 /* On this PMU each PIC has it's own PCR control register.  */
 static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc)
 {
@@ -972,20 +974,13 @@ static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc)
 		struct perf_event *cp = cpuc->event[i];
 		struct hw_perf_event *hwc = &cp->hw;
 		int idx = hwc->idx;
-		u64 enc;
 
 		if (cpuc->current_idx[i] != PIC_NO_INDEX)
 			continue;
 
-		sparc_perf_event_set_period(cp, hwc, idx);
 		cpuc->current_idx[i] = idx;
 
-		enc = perf_event_get_enc(cpuc->events[i]);
-		cpuc->pcr[idx] &= ~mask_for_index(idx);
-		if (hwc->state & PERF_HES_STOPPED)
-			cpuc->pcr[idx] |= nop_for_index(idx);
-		else
-			cpuc->pcr[idx] |= event_encoding(enc, idx);
+		sparc_pmu_start(cp, PERF_EF_RELOAD);
 	}
 out:
 	for (i = 0; i < cpuc->n_events; i++) {
@@ -1101,7 +1096,6 @@ static void sparc_pmu_del(struct perf_event *event, int _flags)
 	int i;
 
 	local_irq_save(flags);
-	perf_pmu_disable(event->pmu);
 
 	for (i = 0; i < cpuc->n_events; i++) {
 		if (event == cpuc->event[i]) {
@@ -1127,7 +1121,6 @@ static void sparc_pmu_del(struct perf_event *event, int _flags)
 		}
 	}
 
-	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
@@ -1361,7 +1354,6 @@ static int sparc_pmu_add(struct perf_event *event, int ef_flags)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	perf_pmu_disable(event->pmu);
 
 	n0 = cpuc->n_events;
 	if (n0 >= sparc_pmu->max_hw_events)
@@ -1394,7 +1386,6 @@ nocheck:
 
 	ret = 0;
 out:
-	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 	return ret;
 }
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 0be7bf978cb..46a59643bb1 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -287,6 +287,8 @@ void arch_trigger_all_cpu_backtrace(bool include_self)
 			printk("             TPC[%lx] O7[%lx] I7[%lx] RPC[%lx]\n",
 			       gp->tpc, gp->o7, gp->i7, gp->rpc);
 		}
+
+		touch_nmi_watchdog();
 	}
 
 	memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
@@ -362,6 +364,8 @@ static void pmu_snapshot_all_cpus(void)
 		       (cpu == this_cpu ? '*' : ' '), cpu,
 		       pp->pcr[0], pp->pcr[1], pp->pcr[2], pp->pcr[3],
 		       pp->pic[0], pp->pic[1], pp->pic[2], pp->pic[3]);
+
+		touch_nmi_watchdog();
 	}
 
 	memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index c85403d0496..30e7ddb27a3 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -333,7 +333,7 @@ SYSCALL_DEFINE6(sparc_ipc, unsigned int, call, int, first, unsigned long, second
 	long err;
 
 	/* No need for backward compatibility. We can start fresh... */
-	if (call <= SEMCTL) {
+	if (call <= SEMTIMEDOP) {
 		switch (call) {
 		case SEMOP:
 			err = sys_semtimedop(first, ptr,
diff --git a/arch/sparc/lib/memmove.S b/arch/sparc/lib/memmove.S
index b7f6334e159..857ad4f8905 100644
--- a/arch/sparc/lib/memmove.S
+++ b/arch/sparc/lib/memmove.S
@@ -8,9 +8,11 @@
 
 	.text
 ENTRY(memmove) /* o0=dst o1=src o2=len */
-	mov		%o0, %g1
+	brz,pn		%o2, 99f
+	 mov		%o0, %g1
+
 	cmp		%o0, %o1
-	bleu,pt		%xcc, memcpy
+	bleu,pt		%xcc, 2f
 	 add		%o1, %o2, %g7
 	cmp		%g7, %o0
 	bleu,pt		%xcc, memcpy
@@ -24,7 +26,34 @@ ENTRY(memmove) /* o0=dst o1=src o2=len */
 	stb		%g7, [%o0]
 	bne,pt		%icc, 1b
 	 sub		%o0, 1, %o0
-
+99:
 	retl
 	 mov		%g1, %o0
+
+	/* We can't just call memcpy for these memmove cases.  On some
+	 * chips the memcpy uses cache initializing stores and when dst
+	 * and src are close enough, those can clobber the source data
+	 * before we've loaded it in.
+	 */
+2:	or		%o0, %o1, %g7
+	or		%o2, %g7, %g7
+	andcc		%g7, 0x7, %g0
+	bne,pn		%xcc, 4f
+	 nop
+
+3:	ldx		[%o1], %g7
+	add		%o1, 8, %o1
+	subcc		%o2, 8, %o2
+	add		%o0, 8, %o0
+	bne,pt		%icc, 3b
+	 stx		%g7, [%o0 - 0x8]
+	ba,a,pt		%xcc, 99b
+
+4:	ldub		[%o1], %g7
+	add		%o1, 1, %o1
+	subcc		%o2, 1, %o2
+	add		%o0, 1, %o0
+	bne,pt		%icc, 4b
+	 stb		%g7, [%o0 - 0x1]
+	ba,a,pt		%xcc, 99b
 ENDPROC(memmove)
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 908e8c17c90..70d817154fe 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -249,6 +249,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 18fcd716709..47982324942 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -446,6 +446,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index d329537739c..4242eab12e1 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -215,12 +215,6 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 	return entry;
 }
 
-struct page *follow_huge_addr(struct mm_struct *mm,
-			      unsigned long address, int write)
-{
-	return ERR_PTR(-EINVAL);
-}
-
 int pmd_huge(pmd_t pmd)
 {
 	return 0;
@@ -230,9 +224,3 @@ int pud_huge(pud_t pud)
 {
 	return 0;
 }
-
-struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-			     pmd_t *pmd, int write)
-{
-	return NULL;
-}
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index be65f035d18..5cbc96d801f 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -460,10 +460,12 @@ static void __init sparc_context_init(int numctx)
 void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm,
 	       struct task_struct *tsk)
 {
+	unsigned long flags;
+
 	if (mm->context == NO_CONTEXT) {
-		spin_lock(&srmmu_context_spinlock);
+		spin_lock_irqsave(&srmmu_context_spinlock, flags);
 		alloc_context(old_mm, mm);
-		spin_unlock(&srmmu_context_spinlock);
+		spin_unlock_irqrestore(&srmmu_context_spinlock, flags);
 		srmmu_ctxd_set(&srmmu_context_table[mm->context], mm->pgd);
 	}
 
@@ -986,14 +988,15 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 
 void destroy_context(struct mm_struct *mm)
 {
+	unsigned long flags;
 
 	if (mm->context != NO_CONTEXT) {
 		flush_cache_mm(mm);
 		srmmu_ctxd_set(&srmmu_context_table[mm->context], srmmu_swapper_pg_dir);
 		flush_tlb_mm(mm);
-		spin_lock(&srmmu_context_spinlock);
+		spin_lock_irqsave(&srmmu_context_spinlock, flags);
 		free_context(mm->context);
-		spin_unlock(&srmmu_context_spinlock);
+		spin_unlock_irqrestore(&srmmu_context_spinlock, flags);
 		mm->context = NO_CONTEXT;
 	}
 }
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index 6c0571216a9..c6d2a76d91a 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -444,6 +444,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c
index e514899e110..8a00c7b7b86 100644
--- a/arch/tile/mm/hugetlbpage.c
+++ b/arch/tile/mm/hugetlbpage.c
@@ -150,12 +150,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	return NULL;
 }
 
-struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
-			      int write)
-{
-	return ERR_PTR(-EINVAL);
-}
-
 int pmd_huge(pmd_t pmd)
 {
 	return !!(pmd_val(pmd) & _PAGE_HUGE_PAGE);
@@ -166,28 +160,6 @@ int pud_huge(pud_t pud)
 	return !!(pud_val(pud) & _PAGE_HUGE_PAGE);
 }
 
-struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-			     pmd_t *pmd, int write)
-{
-	struct page *page;
-
-	page = pte_page(*(pte_t *)pmd);
-	if (page)
-		page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
-	return page;
-}
-
-struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
-			     pud_t *pud, int write)
-{
-	struct page *page;
-
-	page = pte_page(*(pte_t *)pud);
-	if (page)
-		page += ((address & ~PUD_MASK) >> PAGE_SHIFT);
-	return page;
-}
-
 int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 {
 	return 0;
diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common
index 87bc86821bc..d195a87ca54 100644
--- a/arch/um/Kconfig.common
+++ b/arch/um/Kconfig.common
@@ -3,6 +3,7 @@ config UML
 	default y
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_UID16
+	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES
 	select GENERIC_IO
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 5678c3571e7..209617302df 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -80,6 +80,8 @@ good_area:
 		if (unlikely(fault & VM_FAULT_ERROR)) {
 			if (fault & VM_FAULT_OOM) {
 				goto out_of_memory;
+			} else if (fault & VM_FAULT_SIGSEGV) {
+				goto out;
 			} else if (fault & VM_FAULT_SIGBUS) {
 				err = -EACCES;
 				goto out;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 41a503c1586..c9148e26851 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -173,7 +173,7 @@ config SBUS
 
 config NEED_DMA_MAP_STATE
 	def_bool y
-	depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG
+	depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG || SWIOTLB
 
 config NEED_SG_DMA_LENGTH
 	def_bool y
@@ -856,7 +856,7 @@ source "kernel/Kconfig.preempt"
 
 config X86_UP_APIC
 	bool "Local APIC support on uniprocessors"
-	depends on X86_32 && !SMP && !X86_32_NON_STANDARD && !PCI_MSI
+	depends on X86_32 && !SMP && !X86_32_NON_STANDARD
 	---help---
 	  A local APIC (Advanced Programmable Interrupt Controller) is an
 	  integrated interrupt controller in the CPU. If you have a single-CPU
@@ -867,6 +867,10 @@ config X86_UP_APIC
 	  performance counters), and the NMI watchdog which detects hard
 	  lockups.
 
+config X86_UP_APIC_MSI
+	def_bool y
+	select X86_UP_APIC if X86_32 && !SMP && !X86_32_NON_STANDARD && PCI_MSI
+
 config X86_UP_IOAPIC
 	bool "IO-APIC support on uniprocessors"
 	depends on X86_UP_APIC
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 5b016e2498f..3db07f30636 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -51,6 +51,7 @@ targets += cpustr.h
 $(obj)/cpustr.h: $(obj)/mkcpustr FORCE
 	$(call if_changed,cpustr)
 endif
+clean-files += cpustr.h
 
 # ---------------------------------------------------------------------------
 
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 45abc363dd3..30c0acf4ea6 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -36,6 +36,7 @@ vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/aslr.o
 $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
 
 vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o
+vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
 
 $(obj)/vmlinux: $(vmlinux-objs-y) FORCE
 	$(call if_changed,ld)
@@ -77,7 +78,7 @@ suffix-$(CONFIG_KERNEL_LZO) 	:= lzo
 suffix-$(CONFIG_KERNEL_LZ4) 	:= lz4
 
 RUN_SIZE = $(shell $(OBJDUMP) -h vmlinux | \
-	     perl $(srctree)/arch/x86/tools/calc_run_size.pl)
+	     $(CONFIG_SHELL) $(srctree)/arch/x86/tools/calc_run_size.sh)
 quiet_cmd_mkpiggy = MKPIGGY $@
       cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false )
 
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 1acf605a646..3790a66d689 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -1110,6 +1110,8 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	if (!cmdline_ptr)
 		goto fail;
 	hdr->cmd_line_ptr = (unsigned long)cmdline_ptr;
+	/* Fill in upper bits of command line address, NOP on 32 bit  */
+	boot_params->ext_cmd_line_ptr = (u64)(unsigned long)cmdline_ptr >> 32;
 
 	hdr->ramdisk_image = 0;
 	hdr->ramdisk_size = 0;
diff --git a/arch/x86/boot/compressed/efi_stub_64.S b/arch/x86/boot/compressed/efi_stub_64.S
index 7ff3632806b..99494dff211 100644
--- a/arch/x86/boot/compressed/efi_stub_64.S
+++ b/arch/x86/boot/compressed/efi_stub_64.S
@@ -3,28 +3,3 @@
 #include <asm/processor-flags.h>
 
 #include "../../platform/efi/efi_stub_64.S"
-
-#ifdef CONFIG_EFI_MIXED
-	.code64
-	.text
-ENTRY(efi64_thunk)
-	push	%rbp
-	push	%rbx
-
-	subq	$16, %rsp
-	leaq	efi_exit32(%rip), %rax
-	movl	%eax, 8(%rsp)
-	leaq	efi_gdt64(%rip), %rax
-	movl	%eax, 4(%rsp)
-	movl	%eax, 2(%rax)		/* Fixup the gdt base address */
-	leaq	efi32_boot_gdt(%rip), %rax
-	movl	%eax, (%rsp)
-
-	call	__efi64_thunk
-
-	addq	$16, %rsp
-	pop	%rbx
-	pop	%rbp
-	ret
-ENDPROC(efi64_thunk)
-#endif /* CONFIG_EFI_MIXED */
diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S
new file mode 100644
index 00000000000..630384a4c14
--- /dev/null
+++ b/arch/x86/boot/compressed/efi_thunk_64.S
@@ -0,0 +1,196 @@
+/*
+ * Copyright (C) 2014, 2015 Intel Corporation; author Matt Fleming
+ *
+ * Early support for invoking 32-bit EFI services from a 64-bit kernel.
+ *
+ * Because this thunking occurs before ExitBootServices() we have to
+ * restore the firmware's 32-bit GDT before we make EFI serivce calls,
+ * since the firmware's 32-bit IDT is still currently installed and it
+ * needs to be able to service interrupts.
+ *
+ * On the plus side, we don't have to worry about mangling 64-bit
+ * addresses into 32-bits because we're executing with an identify
+ * mapped pagetable and haven't transitioned to 64-bit virtual addresses
+ * yet.
+ */
+
+#include <linux/linkage.h>
+#include <asm/msr.h>
+#include <asm/page_types.h>
+#include <asm/processor-flags.h>
+#include <asm/segment.h>
+
+	.code64
+	.text
+ENTRY(efi64_thunk)
+	push	%rbp
+	push	%rbx
+
+	subq	$8, %rsp
+	leaq	efi_exit32(%rip), %rax
+	movl	%eax, 4(%rsp)
+	leaq	efi_gdt64(%rip), %rax
+	movl	%eax, (%rsp)
+	movl	%eax, 2(%rax)		/* Fixup the gdt base address */
+
+	movl	%ds, %eax
+	push	%rax
+	movl	%es, %eax
+	push	%rax
+	movl	%ss, %eax
+	push	%rax
+
+	/*
+	 * Convert x86-64 ABI params to i386 ABI
+	 */
+	subq	$32, %rsp
+	movl	%esi, 0x0(%rsp)
+	movl	%edx, 0x4(%rsp)
+	movl	%ecx, 0x8(%rsp)
+	movq	%r8, %rsi
+	movl	%esi, 0xc(%rsp)
+	movq	%r9, %rsi
+	movl	%esi,  0x10(%rsp)
+
+	sgdt	save_gdt(%rip)
+
+	leaq	1f(%rip), %rbx
+	movq	%rbx, func_rt_ptr(%rip)
+
+	/*
+	 * Switch to gdt with 32-bit segments. This is the firmware GDT
+	 * that was installed when the kernel started executing. This
+	 * pointer was saved at the EFI stub entry point in head_64.S.
+	 */
+	leaq	efi32_boot_gdt(%rip), %rax
+	lgdt	(%rax)
+
+	pushq	$__KERNEL_CS
+	leaq	efi_enter32(%rip), %rax
+	pushq	%rax
+	lretq
+
+1:	addq	$32, %rsp
+
+	lgdt	save_gdt(%rip)
+
+	pop	%rbx
+	movl	%ebx, %ss
+	pop	%rbx
+	movl	%ebx, %es
+	pop	%rbx
+	movl	%ebx, %ds
+
+	/*
+	 * Convert 32-bit status code into 64-bit.
+	 */
+	test	%rax, %rax
+	jz	1f
+	movl	%eax, %ecx
+	andl	$0x0fffffff, %ecx
+	andl	$0xf0000000, %eax
+	shl	$32, %rax
+	or	%rcx, %rax
+1:
+	addq	$8, %rsp
+	pop	%rbx
+	pop	%rbp
+	ret
+ENDPROC(efi64_thunk)
+
+ENTRY(efi_exit32)
+	movq	func_rt_ptr(%rip), %rax
+	push	%rax
+	mov	%rdi, %rax
+	ret
+ENDPROC(efi_exit32)
+
+	.code32
+/*
+ * EFI service pointer must be in %edi.
+ *
+ * The stack should represent the 32-bit calling convention.
+ */
+ENTRY(efi_enter32)
+	movl	$__KERNEL_DS, %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	movl	%eax, %ss
+
+	/* Reload pgtables */
+	movl	%cr3, %eax
+	movl	%eax, %cr3
+
+	/* Disable paging */
+	movl	%cr0, %eax
+	btrl	$X86_CR0_PG_BIT, %eax
+	movl	%eax, %cr0
+
+	/* Disable long mode via EFER */
+	movl	$MSR_EFER, %ecx
+	rdmsr
+	btrl	$_EFER_LME, %eax
+	wrmsr
+
+	call	*%edi
+
+	/* We must preserve return value */
+	movl	%eax, %edi
+
+	/*
+	 * Some firmware will return with interrupts enabled. Be sure to
+	 * disable them before we switch GDTs.
+	 */
+	cli
+
+	movl	56(%esp), %eax
+	movl	%eax, 2(%eax)
+	lgdtl	(%eax)
+
+	movl	%cr4, %eax
+	btsl	$(X86_CR4_PAE_BIT), %eax
+	movl	%eax, %cr4
+
+	movl	%cr3, %eax
+	movl	%eax, %cr3
+
+	movl	$MSR_EFER, %ecx
+	rdmsr
+	btsl	$_EFER_LME, %eax
+	wrmsr
+
+	xorl	%eax, %eax
+	lldt	%ax
+
+	movl	60(%esp), %eax
+	pushl	$__KERNEL_CS
+	pushl	%eax
+
+	/* Enable paging */
+	movl	%cr0, %eax
+	btsl	$X86_CR0_PG_BIT, %eax
+	movl	%eax, %cr0
+	lret
+ENDPROC(efi_enter32)
+
+	.data
+	.balign	8
+	.global	efi32_boot_gdt
+efi32_boot_gdt:	.word	0
+		.quad	0
+
+save_gdt:	.word	0
+		.quad	0
+func_rt_ptr:	.quad	0
+
+	.global efi_gdt64
+efi_gdt64:
+	.word	efi_gdt64_end - efi_gdt64
+	.long	0			/* Filled out by user */
+	.word	0
+	.quad	0x0000000000000000	/* NULL descriptor */
+	.quad	0x00af9a000000ffff	/* __KERNEL_CS */
+	.quad	0x00cf92000000ffff	/* __KERNEL_DS */
+	.quad	0x0080890000000000	/* TS descriptor */
+	.quad   0x0000000000000000	/* TS continued */
+efi_gdt64_end:
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 30dd59a9f0b..0c33a7c67ea 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -361,6 +361,8 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 				  unsigned long output_len,
 				  unsigned long run_size)
 {
+	unsigned char *output_orig = output;
+
 	real_mode = rmode;
 
 	sanitize_boot_params(real_mode);
@@ -409,7 +411,12 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 	debug_putstr("\nDecompressing Linux... ");
 	decompress(input_data, input_len, NULL, NULL, output, NULL, error);
 	parse_elf(output);
-	handle_relocations(output, output_len);
+	/*
+	 * 32-bit always performs relocations. 64-bit relocations are only
+	 * needed if kASLR has chosen a different load address.
+	 */
+	if (!IS_ENABLED(CONFIG_X86_64) || output != output_orig)
+		handle_relocations(output, output_len);
 	debug_putstr("done.\nBooting the kernel.\n");
 	return output;
 }
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index fd0f848938c..5a4a089e8b1 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -26,7 +26,6 @@ obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
 
 obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o
 obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
-obj-$(CONFIG_CRYPTO_SHA1_MB) += sha-mb/
 obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o
 obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
 obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
@@ -46,6 +45,7 @@ endif
 ifeq ($(avx2_supported),yes)
 	obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o
 	obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o
+	obj-$(CONFIG_CRYPTO_SHA1_MB) += sha-mb/
 endif
 
 aes-i586-y := aes-i586-asm_32.o aes_glue.o
diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
index 2df2a0298f5..a916c4a6116 100644
--- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
+++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
@@ -208,7 +208,7 @@ ddq_add_8:
 
 	.if (klen == KEY_128)
 		.if (load_keys)
-			vmovdqa	3*16(p_keys), xkeyA
+			vmovdqa	3*16(p_keys), xkey4
 		.endif
 	.else
 		vmovdqa	3*16(p_keys), xkeyA
@@ -224,7 +224,7 @@ ddq_add_8:
 	add	$(16*by), p_in
 
 	.if (klen == KEY_128)
-		vmovdqa	4*16(p_keys), xkey4
+		vmovdqa	4*16(p_keys), xkeyB
 	.else
 		.if (load_keys)
 			vmovdqa	4*16(p_keys), xkey4
@@ -234,7 +234,12 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkeyA, var_xdata, var_xdata		/* key 3 */
+		/* key 3 */
+		.if (klen == KEY_128)
+			vaesenc	xkey4, var_xdata, var_xdata
+		.else
+			vaesenc	xkeyA, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
@@ -243,13 +248,18 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkey4, var_xdata, var_xdata		/* key 4 */
+		/* key 4 */
+		.if (klen == KEY_128)
+			vaesenc	xkeyB, var_xdata, var_xdata
+		.else
+			vaesenc	xkey4, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
 	.if (klen == KEY_128)
 		.if (load_keys)
-			vmovdqa	6*16(p_keys), xkeyB
+			vmovdqa	6*16(p_keys), xkey8
 		.endif
 	.else
 		vmovdqa	6*16(p_keys), xkeyB
@@ -267,12 +277,17 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkeyB, var_xdata, var_xdata		/* key 6 */
+		/* key 6 */
+		.if (klen == KEY_128)
+			vaesenc	xkey8, var_xdata, var_xdata
+		.else
+			vaesenc	xkeyB, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
 	.if (klen == KEY_128)
-		vmovdqa	8*16(p_keys), xkey8
+		vmovdqa	8*16(p_keys), xkeyB
 	.else
 		.if (load_keys)
 			vmovdqa	8*16(p_keys), xkey8
@@ -288,7 +303,7 @@ ddq_add_8:
 
 	.if (klen == KEY_128)
 		.if (load_keys)
-			vmovdqa	9*16(p_keys), xkeyA
+			vmovdqa	9*16(p_keys), xkey12
 		.endif
 	.else
 		vmovdqa	9*16(p_keys), xkeyA
@@ -297,7 +312,12 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkey8, var_xdata, var_xdata		/* key 8 */
+		/* key 8 */
+		.if (klen == KEY_128)
+			vaesenc	xkeyB, var_xdata, var_xdata
+		.else
+			vaesenc	xkey8, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
@@ -306,7 +326,12 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkeyA, var_xdata, var_xdata		/* key 9 */
+		/* key 9 */
+		.if (klen == KEY_128)
+			vaesenc	xkey12, var_xdata, var_xdata
+		.else
+			vaesenc	xkeyA, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
@@ -412,7 +437,6 @@ ddq_add_8:
 /* main body of aes ctr load */
 
 .macro do_aes_ctrmain key_len
-
 	cmp	$16, num_bytes
 	jb	.Ldo_return2\key_len
 
diff --git a/arch/x86/crypto/aes_glue.c b/arch/x86/crypto/aes_glue.c
index aafe8ce0d65..e26984f7ab8 100644
--- a/arch/x86/crypto/aes_glue.c
+++ b/arch/x86/crypto/aes_glue.c
@@ -66,5 +66,5 @@ module_exit(aes_fini);
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, asm optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("aes");
-MODULE_ALIAS("aes-asm");
+MODULE_ALIAS_CRYPTO("aes");
+MODULE_ALIAS_CRYPTO("aes-asm");
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 888950f29fd..5a93783a8a0 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -1137,7 +1137,7 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
 		src = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC);
 		if (!src)
 			return -ENOMEM;
-		assoc = (src + req->cryptlen + auth_tag_len);
+		assoc = (src + req->cryptlen);
 		scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0);
 		scatterwalk_map_and_copy(assoc, req->assoc, 0,
 			req->assoclen, 0);
@@ -1162,7 +1162,7 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
 		scatterwalk_done(&src_sg_walk, 0, 0);
 		scatterwalk_done(&assoc_sg_walk, 0, 0);
 	} else {
-		scatterwalk_map_and_copy(dst, req->dst, 0, req->cryptlen, 1);
+		scatterwalk_map_and_copy(dst, req->dst, 0, tempCipherLen, 1);
 		kfree(src);
 	}
 	return retval;
@@ -1550,4 +1550,4 @@ module_exit(aesni_exit);
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, Intel AES-NI instructions optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c
index 8af519ed73d..17c05531dfd 100644
--- a/arch/x86/crypto/blowfish_glue.c
+++ b/arch/x86/crypto/blowfish_glue.c
@@ -478,5 +478,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Blowfish Cipher Algorithm, asm optimized");
-MODULE_ALIAS("blowfish");
-MODULE_ALIAS("blowfish-asm");
+MODULE_ALIAS_CRYPTO("blowfish");
+MODULE_ALIAS_CRYPTO("blowfish-asm");
diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c
index 4209a76fcda..9a07fafe383 100644
--- a/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -582,5 +582,5 @@ module_exit(camellia_aesni_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX2 optimized");
-MODULE_ALIAS("camellia");
-MODULE_ALIAS("camellia-asm");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-asm");
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index 87a041a10f4..ed38d959add 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -574,5 +574,5 @@ module_exit(camellia_aesni_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX optimized");
-MODULE_ALIAS("camellia");
-MODULE_ALIAS("camellia-asm");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-asm");
diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c
index c171dcbf192..5c8b6266a39 100644
--- a/arch/x86/crypto/camellia_glue.c
+++ b/arch/x86/crypto/camellia_glue.c
@@ -1725,5 +1725,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Camellia Cipher Algorithm, asm optimized");
-MODULE_ALIAS("camellia");
-MODULE_ALIAS("camellia-asm");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-asm");
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index e57e20ab5e0..60ada677a92 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -491,4 +491,4 @@ module_exit(cast5_exit);
 
 MODULE_DESCRIPTION("Cast5 Cipher Algorithm, AVX optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("cast5");
+MODULE_ALIAS_CRYPTO("cast5");
diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c
index 09f3677393e..0160f68a57f 100644
--- a/arch/x86/crypto/cast6_avx_glue.c
+++ b/arch/x86/crypto/cast6_avx_glue.c
@@ -611,4 +611,4 @@ module_exit(cast6_exit);
 
 MODULE_DESCRIPTION("Cast6 Cipher Algorithm, AVX optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("cast6");
+MODULE_ALIAS_CRYPTO("cast6");
diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c
index 9d014a74ef9..1937fc1d876 100644
--- a/arch/x86/crypto/crc32-pclmul_glue.c
+++ b/arch/x86/crypto/crc32-pclmul_glue.c
@@ -197,5 +197,5 @@ module_exit(crc32_pclmul_mod_fini);
 MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>");
 MODULE_LICENSE("GPL");
 
-MODULE_ALIAS("crc32");
-MODULE_ALIAS("crc32-pclmul");
+MODULE_ALIAS_CRYPTO("crc32");
+MODULE_ALIAS_CRYPTO("crc32-pclmul");
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index 6812ad98355..28640c3d6af 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -280,5 +280,5 @@ MODULE_AUTHOR("Austin Zhang <austin.zhang@intel.com>, Kent Liu <kent.liu@intel.c
 MODULE_DESCRIPTION("CRC32c (Castagnoli) optimization using Intel Hardware.");
 MODULE_LICENSE("GPL");
 
-MODULE_ALIAS("crc32c");
-MODULE_ALIAS("crc32c-intel");
+MODULE_ALIAS_CRYPTO("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c-intel");
diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c
index 7845d7fd54c..b6c67bf30fd 100644
--- a/arch/x86/crypto/crct10dif-pclmul_glue.c
+++ b/arch/x86/crypto/crct10dif-pclmul_glue.c
@@ -147,5 +147,5 @@ MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>");
 MODULE_DESCRIPTION("T10 DIF CRC calculation accelerated with PCLMULQDQ.");
 MODULE_LICENSE("GPL");
 
-MODULE_ALIAS("crct10dif");
-MODULE_ALIAS("crct10dif-pclmul");
+MODULE_ALIAS_CRYPTO("crct10dif");
+MODULE_ALIAS_CRYPTO("crct10dif-pclmul");
diff --git a/arch/x86/crypto/des3_ede_glue.c b/arch/x86/crypto/des3_ede_glue.c
index 0e9c0668fe4..38a14f818ef 100644
--- a/arch/x86/crypto/des3_ede_glue.c
+++ b/arch/x86/crypto/des3_ede_glue.c
@@ -502,8 +502,8 @@ module_exit(des3_ede_x86_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Triple DES EDE Cipher Algorithm, asm optimized");
-MODULE_ALIAS("des3_ede");
-MODULE_ALIAS("des3_ede-asm");
-MODULE_ALIAS("des");
-MODULE_ALIAS("des-asm");
+MODULE_ALIAS_CRYPTO("des3_ede");
+MODULE_ALIAS_CRYPTO("des3_ede-asm");
+MODULE_ALIAS_CRYPTO("des");
+MODULE_ALIAS_CRYPTO("des-asm");
 MODULE_AUTHOR("Jussi Kivilinna <jussi.kivilinna@iki.fi>");
diff --git a/arch/x86/crypto/fpu.c b/arch/x86/crypto/fpu.c
index 98d7a188f46..f368ba26173 100644
--- a/arch/x86/crypto/fpu.c
+++ b/arch/x86/crypto/fpu.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/crypto.h>
 #include <asm/i387.h>
 
 struct crypto_fpu_ctx {
@@ -159,3 +160,5 @@ void __exit crypto_fpu_exit(void)
 {
 	crypto_unregister_template(&crypto_fpu_tmpl);
 }
+
+MODULE_ALIAS_CRYPTO("fpu");
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 88bb7ba8b17..8253d85aa16 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -341,4 +341,4 @@ module_exit(ghash_pclmulqdqni_mod_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("GHASH Message Digest Algorithm, "
 		   "acclerated by PCLMULQDQ-NI");
-MODULE_ALIAS("ghash");
+MODULE_ALIAS_CRYPTO("ghash");
diff --git a/arch/x86/crypto/salsa20_glue.c b/arch/x86/crypto/salsa20_glue.c
index 5e8e67739bb..399a29d067d 100644
--- a/arch/x86/crypto/salsa20_glue.c
+++ b/arch/x86/crypto/salsa20_glue.c
@@ -119,5 +119,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION ("Salsa20 stream cipher algorithm (optimized assembly version)");
-MODULE_ALIAS("salsa20");
-MODULE_ALIAS("salsa20-asm");
+MODULE_ALIAS_CRYPTO("salsa20");
+MODULE_ALIAS_CRYPTO("salsa20-asm");
diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c
index 2fae489b152..437e47a4d30 100644
--- a/arch/x86/crypto/serpent_avx2_glue.c
+++ b/arch/x86/crypto/serpent_avx2_glue.c
@@ -558,5 +558,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX2 optimized");
-MODULE_ALIAS("serpent");
-MODULE_ALIAS("serpent-asm");
+MODULE_ALIAS_CRYPTO("serpent");
+MODULE_ALIAS_CRYPTO("serpent-asm");
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
index ff487087097..7e217398b4e 100644
--- a/arch/x86/crypto/serpent_avx_glue.c
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -617,4 +617,4 @@ module_exit(serpent_exit);
 
 MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("serpent");
+MODULE_ALIAS_CRYPTO("serpent");
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index 8c95f863730..bf025adaea0 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -618,4 +618,4 @@ module_exit(serpent_sse2_exit);
 
 MODULE_DESCRIPTION("Serpent Cipher Algorithm, SSE2 optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("serpent");
+MODULE_ALIAS_CRYPTO("serpent");
diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c
index 99eefd81295..d42c9b7fadc 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb.c
+++ b/arch/x86/crypto/sha-mb/sha1_mb.c
@@ -932,4 +932,4 @@ module_exit(sha1_mb_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, multi buffer accelerated");
 
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 74d16ef707c..6c20fe04a73 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -278,4 +278,4 @@ module_exit(sha1_ssse3_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, Supplemental SSE3 accelerated");
 
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index f248546da1c..4dc100d8290 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -318,5 +318,5 @@ module_exit(sha256_ssse3_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, Supplemental SSE3 accelerated");
 
-MODULE_ALIAS("sha256");
-MODULE_ALIAS("sha224");
+MODULE_ALIAS_CRYPTO("sha256");
+MODULE_ALIAS_CRYPTO("sha224");
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index 8626b03e83b..26a5898a6f2 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -326,5 +326,5 @@ module_exit(sha512_ssse3_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, Supplemental SSE3 accelerated");
 
-MODULE_ALIAS("sha512");
-MODULE_ALIAS("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
+MODULE_ALIAS_CRYPTO("sha384");
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
index 4e3c665be12..1ac531ea9bc 100644
--- a/arch/x86/crypto/twofish_avx_glue.c
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -579,4 +579,4 @@ module_exit(twofish_exit);
 
 MODULE_DESCRIPTION("Twofish Cipher Algorithm, AVX optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("twofish");
+MODULE_ALIAS_CRYPTO("twofish");
diff --git a/arch/x86/crypto/twofish_glue.c b/arch/x86/crypto/twofish_glue.c
index 0a520230350..77e06c2da83 100644
--- a/arch/x86/crypto/twofish_glue.c
+++ b/arch/x86/crypto/twofish_glue.c
@@ -96,5 +96,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION ("Twofish Cipher Algorithm, asm optimized");
-MODULE_ALIAS("twofish");
-MODULE_ALIAS("twofish-asm");
+MODULE_ALIAS_CRYPTO("twofish");
+MODULE_ALIAS_CRYPTO("twofish-asm");
diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c
index 13e63b3e1df..56d8a08ee47 100644
--- a/arch/x86/crypto/twofish_glue_3way.c
+++ b/arch/x86/crypto/twofish_glue_3way.c
@@ -495,5 +495,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Twofish Cipher Algorithm, 3-way parallel asm optimized");
-MODULE_ALIAS("twofish");
-MODULE_ALIAS("twofish-asm");
+MODULE_ALIAS_CRYPTO("twofish");
+MODULE_ALIAS_CRYPTO("twofish-asm");
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 50d033a8947..a94b82e8f15 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -251,7 +251,8 @@ static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
 		gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i];
 }
 
-#define _LDT_empty(info)				\
+/* This intentionally ignores lm, since 32-bit apps don't have that field. */
+#define LDT_empty(info)					\
 	((info)->base_addr		== 0	&&	\
 	 (info)->limit			== 0	&&	\
 	 (info)->contents		== 0	&&	\
@@ -261,11 +262,18 @@ static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
 	 (info)->seg_not_present	== 1	&&	\
 	 (info)->useable		== 0)
 
-#ifdef CONFIG_X86_64
-#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0))
-#else
-#define LDT_empty(info) (_LDT_empty(info))
-#endif
+/* Lots of programs expect an all-zero user_desc to mean "no segment at all". */
+static inline bool LDT_zero(const struct user_desc *info)
+{
+	return (info->base_addr		== 0 &&
+		info->limit		== 0 &&
+		info->contents		== 0 &&
+		info->read_exec_only	== 0 &&
+		info->seg_32bit		== 0 &&
+		info->limit_in_pages	== 0 &&
+		info->seg_not_present	== 0 &&
+		info->useable		== 0);
+}
 
 static inline void clear_LDT(void)
 {
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index e97622f5772..f895358db0a 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -368,7 +368,7 @@ static inline void drop_fpu(struct task_struct *tsk)
 	preempt_disable();
 	tsk->thread.fpu_counter = 0;
 	__drop_fpu(tsk);
-	clear_used_math();
+	clear_stopped_child_used_math(tsk);
 	preempt_enable();
 }
 
diff --git a/arch/x86/include/asm/idle.h b/arch/x86/include/asm/idle.h
index c5d1785373e..02bab09707f 100644
--- a/arch/x86/include/asm/idle.h
+++ b/arch/x86/include/asm/idle.h
@@ -1,13 +1,6 @@
 #ifndef _ASM_X86_IDLE_H
 #define _ASM_X86_IDLE_H
 
-#define IDLE_START 1
-#define IDLE_END 2
-
-struct notifier_block;
-void idle_notifier_register(struct notifier_block *n);
-void idle_notifier_unregister(struct notifier_block *n);
-
 #ifdef CONFIG_X86_64
 void enter_idle(void);
 void exit_idle(void);
diff --git a/arch/x86/include/asm/iommu_table.h b/arch/x86/include/asm/iommu_table.h
index f42a04735a0..e37d6b3ad98 100644
--- a/arch/x86/include/asm/iommu_table.h
+++ b/arch/x86/include/asm/iommu_table.h
@@ -79,11 +79,12 @@ struct iommu_table_entry {
  *  d). Similar to the 'init', except that this gets called from pci_iommu_init
  *      where we do have a memory allocator.
  *
- * The standard vs the _FINISH differs in that the _FINISH variant will
- * continue detecting other IOMMUs in the call list after the
- * the detection routine returns a positive number. The _FINISH will
- * stop the execution chain. Both will still call the 'init' and
- * 'late_init' functions if they are set.
+ * The standard IOMMU_INIT differs from the IOMMU_INIT_FINISH variant
+ * in that the former will continue detecting other IOMMUs in the call
+ * list after the detection routine returns a positive number, while the
+ * latter will stop the execution chain upon first successful detection.
+ * Both variants will still call the 'init' and 'late_init' functions if
+ * they are set.
  */
 #define IOMMU_INIT_FINISH(_detect, _depend, _init, _late_init)		\
 	__IOMMU_INIT(_detect, _depend, _init, _late_init, 1)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6ed0c30d6a0..306d152336c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -201,6 +201,7 @@ union kvm_mmu_page_role {
 		unsigned nxe:1;
 		unsigned cr0_wp:1;
 		unsigned smep_andnot_wp:1;
+		unsigned smap_andnot_wp:1;
 	};
 };
 
@@ -392,6 +393,7 @@ struct kvm_vcpu_arch {
 	struct kvm_mmu_memory_cache mmu_page_header_cache;
 
 	struct fpu guest_fpu;
+	bool eager_fpu;
 	u64 xcr0;
 	u64 guest_supported_xcr0;
 	u32 guest_xstate_size;
@@ -569,7 +571,7 @@ struct kvm_arch {
 	struct kvm_pic *vpic;
 	struct kvm_ioapic *vioapic;
 	struct kvm_pit *vpit;
-	int vapics_in_nmi_mode;
+	atomic_t vapics_in_nmi_mode;
 	struct mutex apic_map_lock;
 	struct kvm_apic_map *apic_map;
 
@@ -707,6 +709,7 @@ struct kvm_x86_ops {
 	void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
 	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
 	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
+	void (*fpu_activate)(struct kvm_vcpu *vcpu);
 	void (*fpu_deactivate)(struct kvm_vcpu *vcpu);
 
 	void (*tlb_flush)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 958b90f761e..40b35a55ce8 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -34,6 +34,10 @@
 #define MCI_STATUS_S	 (1ULL<<56)  /* Signaled machine check */
 #define MCI_STATUS_AR	 (1ULL<<55)  /* Action required */
 
+/* AMD-specific bits */
+#define MCI_STATUS_DEFERRED	(1ULL<<44)  /* declare an uncorrected error */
+#define MCI_STATUS_POISON	(1ULL<<43)  /* access poisonous data */
+
 /*
  * Note that the full MCACOD field of IA32_MCi_STATUS MSR is
  * bits 15:0.  But bit 12 is the 'F' bit, defined for corrected
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 64dc362506b..201b520521e 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -78,6 +78,7 @@ static inline void __exit exit_amd_microcode(void) {}
 extern void __init load_ucode_bsp(void);
 extern void load_ucode_ap(void);
 extern int __init save_microcode_in_initrd(void);
+void reload_early_microcode(void);
 #else
 static inline void __init load_ucode_bsp(void) {}
 static inline void load_ucode_ap(void) {}
@@ -85,6 +86,7 @@ static inline int __init save_microcode_in_initrd(void)
 {
 	return 0;
 }
+static inline void reload_early_microcode(void) {}
 #endif
 
 #endif /* _ASM_X86_MICROCODE_H */
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index b7b10b82d3e..af935397e05 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -59,7 +59,7 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table,
 
 extern int __apply_microcode_amd(struct microcode_amd *mc_amd);
 extern int apply_microcode_amd(int cpu);
-extern enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
+extern enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size);
 
 #define PATCH_MAX_SIZE PAGE_SIZE
 extern u8 amd_ucode_patch[PATCH_MAX_SIZE];
@@ -68,10 +68,12 @@ extern u8 amd_ucode_patch[PATCH_MAX_SIZE];
 extern void __init load_ucode_amd_bsp(void);
 extern void load_ucode_amd_ap(void);
 extern int __init save_microcode_in_initrd_amd(void);
+void reload_ucode_amd(void);
 #else
 static inline void __init load_ucode_amd_bsp(void) {}
 static inline void load_ucode_amd_ap(void) {}
 static inline int __init save_microcode_in_initrd_amd(void) { return -EINVAL; }
+void reload_ucode_amd(void) {}
 #endif
 
 #endif /* _ASM_X86_MICROCODE_AMD_H */
diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h
index bbe296e0bce..dd4c20043ce 100644
--- a/arch/x86/include/asm/microcode_intel.h
+++ b/arch/x86/include/asm/microcode_intel.h
@@ -68,11 +68,13 @@ extern void __init load_ucode_intel_bsp(void);
 extern void load_ucode_intel_ap(void);
 extern void show_ucode_info_early(void);
 extern int __init save_microcode_in_initrd_intel(void);
+void reload_ucode_intel(void);
 #else
 static inline __init void load_ucode_intel_bsp(void) {}
 static inline void load_ucode_intel_ap(void) {}
 static inline void show_ucode_info_early(void) {}
 static inline int __init save_microcode_in_initrd_intel(void) { return -EINVAL; }
+static inline void reload_ucode_intel(void) {}
 #endif
 
 #if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU)
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index a1410db38a1..653dfa7662e 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -30,6 +30,14 @@ static inline void __mwait(unsigned long eax, unsigned long ecx)
 		     :: "a" (eax), "c" (ecx));
 }
 
+static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
+{
+	trace_hardirqs_on();
+	/* "mwait %eax, %ecx;" */
+	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
+		     :: "a" (eax), "c" (ecx));
+}
+
 /*
  * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
  * which can obviate IPI to trigger checking of need_resched.
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index cd6e1610e29..a9d76e02301 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -80,16 +80,16 @@ static inline void write_cr3(unsigned long x)
 	PVOP_VCALL1(pv_mmu_ops.write_cr3, x);
 }
 
-static inline unsigned long read_cr4(void)
+static inline unsigned long __read_cr4(void)
 {
 	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4);
 }
-static inline unsigned long read_cr4_safe(void)
+static inline unsigned long __read_cr4_safe(void)
 {
 	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4_safe);
 }
 
-static inline void write_cr4(unsigned long x)
+static inline void __write_cr4(unsigned long x)
 {
 	PVOP_VCALL1(pv_cpu_ops.write_cr4, x);
 }
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index eb71ec79473..ddd8d13a010 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -578,39 +578,6 @@ static inline void load_sp0(struct tss_struct *tss,
 #define set_iopl_mask native_set_iopl_mask
 #endif /* CONFIG_PARAVIRT */
 
-/*
- * Save the cr4 feature set we're using (ie
- * Pentium 4MB enable and PPro Global page
- * enable), so that any CPU's that boot up
- * after us can get the correct flags.
- */
-extern unsigned long mmu_cr4_features;
-extern u32 *trampoline_cr4_features;
-
-static inline void set_in_cr4(unsigned long mask)
-{
-	unsigned long cr4;
-
-	mmu_cr4_features |= mask;
-	if (trampoline_cr4_features)
-		*trampoline_cr4_features = mmu_cr4_features;
-	cr4 = read_cr4();
-	cr4 |= mask;
-	write_cr4(cr4);
-}
-
-static inline void clear_in_cr4(unsigned long mask)
-{
-	unsigned long cr4;
-
-	mmu_cr4_features &= ~mask;
-	if (trampoline_cr4_features)
-		*trampoline_cr4_features = mmu_cr4_features;
-	cr4 = read_cr4();
-	cr4 &= ~mask;
-	write_cr4(cr4);
-}
-
 typedef struct {
 	unsigned long		seg;
 } mm_segment_t;
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 6f1c3a8a33a..bcc9a2f46c6 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -212,10 +212,21 @@
 #define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8)
 
 #ifdef __KERNEL__
+
+/*
+ * early_idt_handler_array is an array of entry points referenced in the
+ * early IDT.  For simplicity, it's a real array with one entry point
+ * every nine bytes.  That leaves room for an optional 'push $0' if the
+ * vector has no error code (two bytes), a 'push $vector_number' (two
+ * bytes), and a jump to the common entry code (up to five bytes).
+ */
+#define EARLY_IDT_HANDLER_SIZE 9
+
 #ifndef __ASSEMBLY__
-extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][2+2+5];
+
+extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE];
 #ifdef CONFIG_TRACING
-#define trace_early_idt_handlers early_idt_handlers
+# define trace_early_idt_handler_array early_idt_handler_array
 #endif
 
 /*
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index e820c080a4e..6a4b00fafb0 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -137,17 +137,17 @@ static inline void write_cr3(unsigned long x)
 	native_write_cr3(x);
 }
 
-static inline unsigned long read_cr4(void)
+static inline unsigned long __read_cr4(void)
 {
 	return native_read_cr4();
 }
 
-static inline unsigned long read_cr4_safe(void)
+static inline unsigned long __read_cr4_safe(void)
 {
 	return native_read_cr4_safe();
 }
 
-static inline void write_cr4(unsigned long x)
+static inline void __write_cr4(unsigned long x)
 {
 	native_write_cr4(x);
 }
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 04905bfc508..cd791948b28 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -15,6 +15,75 @@
 #define __flush_tlb_single(addr) __native_flush_tlb_single(addr)
 #endif
 
+struct tlb_state {
+#ifdef CONFIG_SMP
+	struct mm_struct *active_mm;
+	int state;
+#endif
+
+	/*
+	 * Access to this CR4 shadow and to H/W CR4 is protected by
+	 * disabling interrupts when modifying either one.
+	 */
+	unsigned long cr4;
+};
+DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
+
+/* Initialize cr4 shadow for this CPU. */
+static inline void cr4_init_shadow(void)
+{
+	this_cpu_write(cpu_tlbstate.cr4, __read_cr4());
+}
+
+/* Set in this cpu's CR4. */
+static inline void cr4_set_bits(unsigned long mask)
+{
+	unsigned long cr4;
+
+	cr4 = this_cpu_read(cpu_tlbstate.cr4);
+	if ((cr4 | mask) != cr4) {
+		cr4 |= mask;
+		this_cpu_write(cpu_tlbstate.cr4, cr4);
+		__write_cr4(cr4);
+	}
+}
+
+/* Clear in this cpu's CR4. */
+static inline void cr4_clear_bits(unsigned long mask)
+{
+	unsigned long cr4;
+
+	cr4 = this_cpu_read(cpu_tlbstate.cr4);
+	if ((cr4 & ~mask) != cr4) {
+		cr4 &= ~mask;
+		this_cpu_write(cpu_tlbstate.cr4, cr4);
+		__write_cr4(cr4);
+	}
+}
+
+/* Read the CR4 shadow. */
+static inline unsigned long cr4_read_shadow(void)
+{
+	return this_cpu_read(cpu_tlbstate.cr4);
+}
+
+/*
+ * Save some of cr4 feature set we're using (e.g.  Pentium 4MB
+ * enable and PPro Global page enable), so that any CPU's that boot
+ * up after us can get the correct flags.  This should only be used
+ * during boot on the boot cpu.
+ */
+extern unsigned long mmu_cr4_features;
+extern u32 *trampoline_cr4_features;
+
+static inline void cr4_set_bits_and_update_boot(unsigned long mask)
+{
+	mmu_cr4_features |= mask;
+	if (trampoline_cr4_features)
+		*trampoline_cr4_features = mmu_cr4_features;
+	cr4_set_bits(mask);
+}
+
 static inline void __native_flush_tlb(void)
 {
 	native_write_cr3(native_read_cr3());
@@ -24,7 +93,7 @@ static inline void __native_flush_tlb_global_irq_disabled(void)
 {
 	unsigned long cr4;
 
-	cr4 = native_read_cr4();
+	cr4 = this_cpu_read(cpu_tlbstate.cr4);
 	/* clear PGE */
 	native_write_cr4(cr4 & ~X86_CR4_PGE);
 	/* write old PGE again and flush TLBs */
@@ -184,12 +253,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 #define TLBSTATE_OK	1
 #define TLBSTATE_LAZY	2
 
-struct tlb_state {
-	struct mm_struct *active_mm;
-	int state;
-};
-DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
-
 static inline void reset_lazy_tlbstate(void)
 {
 	this_cpu_write(cpu_tlbstate.state, 0);
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 5da71c27cc5..cce9ee68e33 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -19,6 +19,7 @@
 
 #include <asm/vmx.h>
 #include <asm/svm.h>
+#include <asm/tlbflush.h>
 
 /*
  * VMX functions:
@@ -40,12 +41,12 @@ static inline int cpu_has_vmx(void)
 static inline void cpu_vmxoff(void)
 {
 	asm volatile (ASM_VMX_VMXOFF : : : "cc");
-	write_cr4(read_cr4() & ~X86_CR4_VMXE);
+	cr4_clear_bits(X86_CR4_VMXE);
 }
 
 static inline int cpu_vmx_enabled(void)
 {
-	return read_cr4() & X86_CR4_VMXE;
+	return __read_cr4() & X86_CR4_VMXE;
 }
 
 /** Disable VMX if it is enabled on the current CPU
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index 2a46ca720af..2874be9aef0 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -34,7 +34,7 @@ static inline unsigned int __getcpu(void)
 		native_read_tscp(&p);
 	} else {
 		/* Load per CPU data from GDT */
-		asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+		asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
 	}
 
 	return p;
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index c949923a566..f58ef6c0613 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -236,4 +236,11 @@ void make_lowmem_page_readwrite(void *vaddr);
 #define xen_remap(cookie, size) ioremap((cookie), (size));
 #define xen_unmap(cookie) iounmap((cookie))
 
+static inline bool xen_arch_need_swiotlb(struct device *dev,
+					 unsigned long pfn,
+					 unsigned long mfn)
+{
+	return false;
+}
+
 #endif /* _ASM_X86_XEN_PAGE_H */
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 7e7a79ada65..d82b80405e4 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -81,18 +81,15 @@ static inline int xsave_state_booting(struct xsave_struct *fx, u64 mask)
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		asm volatile("1:"XSAVES"\n\t"
 			"2:\n\t"
-			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			     xstate_fault
+			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 			:   "memory");
 	else
 		asm volatile("1:"XSAVE"\n\t"
 			"2:\n\t"
-			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			     xstate_fault
+			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 			:   "memory");
-
-	asm volatile(xstate_fault
-		     : "0" (0)
-		     : "memory");
-
 	return err;
 }
 
@@ -111,18 +108,15 @@ static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask)
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		asm volatile("1:"XRSTORS"\n\t"
 			"2:\n\t"
-			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			     xstate_fault
+			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 			:   "memory");
 	else
 		asm volatile("1:"XRSTOR"\n\t"
 			"2:\n\t"
-			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			     xstate_fault
+			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 			:   "memory");
-
-	asm volatile(xstate_fault
-		     : "0" (0)
-		     : "memory");
-
 	return err;
 }
 
@@ -148,9 +142,9 @@ static inline int xsave_state(struct xsave_struct *fx, u64 mask)
 	 */
 	alternative_input_2(
 		"1:"XSAVE,
-		"1:"XSAVEOPT,
+		XSAVEOPT,
 		X86_FEATURE_XSAVEOPT,
-		"1:"XSAVES,
+		XSAVES,
 		X86_FEATURE_XSAVES,
 		[fx] "D" (fx), "a" (lmask), "d" (hmask) :
 		"memory");
@@ -177,7 +171,7 @@ static inline int xrstor_state(struct xsave_struct *fx, u64 mask)
 	 */
 	alternative_input(
 		"1: " XRSTOR,
-		"1: " XRSTORS,
+		XRSTORS,
 		X86_FEATURE_XSAVES,
 		"D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 		: "memory");
diff --git a/arch/x86/include/uapi/asm/ldt.h b/arch/x86/include/uapi/asm/ldt.h
index 46727eb37bf..6e1aaf73852 100644
--- a/arch/x86/include/uapi/asm/ldt.h
+++ b/arch/x86/include/uapi/asm/ldt.h
@@ -28,6 +28,13 @@ struct user_desc {
 	unsigned int  seg_not_present:1;
 	unsigned int  useable:1;
 #ifdef __x86_64__
+	/*
+	 * Because this bit is not present in 32-bit user code, user
+	 * programs can pass uninitialized values here.  Therefore, in
+	 * any context in which a user_desc comes from a 32-bit program,
+	 * the kernel must act as though lm == 0, regardless of the
+	 * actual value.
+	 */
 	unsigned int  lm:1;
 #endif
 };
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index a142e77693e..a3eadfdc3e0 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -604,18 +604,24 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger)
 
 int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp)
 {
-	int irq;
+	int rc, irq, trigger, polarity;
 
 	if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
 		*irqp = gsi;
-	} else {
-		irq = mp_map_gsi_to_irq(gsi,
-					IOAPIC_MAP_ALLOC | IOAPIC_MAP_CHECK);
-		if (irq < 0)
-			return -1;
-		*irqp = irq;
+		return 0;
 	}
-	return 0;
+
+	rc = acpi_get_override_irq(gsi, &trigger, &polarity);
+	if (rc == 0) {
+		trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
+		polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
+		irq = acpi_register_gsi(NULL, gsi, trigger, polarity);
+		if (irq >= 0) {
+			*irqp = irq;
+			return 0;
+		}
+	}
+	return -1;
 }
 EXPORT_SYMBOL_GPL(acpi_gsi_to_irq);
 
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 31368207837..d1daead5fcd 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -78,7 +78,7 @@ int x86_acpi_suspend_lowlevel(void)
 
 	header->pmode_cr0 = read_cr0();
 	if (__this_cpu_read(cpu_info.cpuid_level) >= 0) {
-		header->pmode_cr4 = read_cr4();
+		header->pmode_cr4 = __read_cr4();
 		header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_CR4);
 	}
 	if (!rdmsr_safe(MSR_IA32_MISC_ENABLE,
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 4128b5fcb55..2aaee79fb12 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -40,7 +40,7 @@ static unsigned int get_apic_id(unsigned long x)
 	unsigned int id;
 
 	rdmsrl(MSR_FAM10H_NODE_ID, value);
-	id = ((x >> 24) & 0xffU) | ((value << 2) & 0x3f00U);
+	id = ((x >> 24) & 0xffU) | ((value << 2) & 0xff00U);
 
 	return id;
 }
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index e27b49d7c92..80091ae54c2 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -66,3 +66,4 @@ targets += capflags.c
 $(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE
 	$(call if_changed,mkcapflags)
 endif
+clean-files += capflags.c
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index cfa9b5b2c27..7bc49c3b968 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -19,6 +19,7 @@
 #include <asm/archrandom.h>
 #include <asm/hypervisor.h>
 #include <asm/processor.h>
+#include <asm/tlbflush.h>
 #include <asm/debugreg.h>
 #include <asm/sections.h>
 #include <asm/vsyscall.h>
@@ -278,7 +279,7 @@ __setup("nosmep", setup_disable_smep);
 static __always_inline void setup_smep(struct cpuinfo_x86 *c)
 {
 	if (cpu_has(c, X86_FEATURE_SMEP))
-		set_in_cr4(X86_CR4_SMEP);
+		cr4_set_bits(X86_CR4_SMEP);
 }
 
 static __init int setup_disable_smap(char *arg)
@@ -298,9 +299,9 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c)
 
 	if (cpu_has(c, X86_FEATURE_SMAP)) {
 #ifdef CONFIG_X86_SMAP
-		set_in_cr4(X86_CR4_SMAP);
+		cr4_set_bits(X86_CR4_SMAP);
 #else
-		clear_in_cr4(X86_CR4_SMAP);
+		cr4_clear_bits(X86_CR4_SMAP);
 #endif
 	}
 }
@@ -1304,6 +1305,12 @@ void cpu_init(void)
 	wait_for_master_cpu(cpu);
 
 	/*
+	 * Initialize the CR4 shadow before doing anything that could
+	 * try to read it.
+	 */
+	cr4_init_shadow();
+
+	/*
 	 * Load microcode on this cpu if a valid microcode is available.
 	 * This is early microcode loading procedure.
 	 */
@@ -1322,7 +1329,7 @@ void cpu_init(void)
 
 	pr_debug("Initializing CPU#%d\n", cpu);
 
-	clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
+	cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
 
 	/*
 	 * Initialize the per-CPU GDT with the boot GDT,
@@ -1403,7 +1410,7 @@ void cpu_init(void)
 	printk(KERN_INFO "Initializing CPU#%d\n", cpu);
 
 	if (cpu_feature_enabled(X86_FEATURE_VME) || cpu_has_tsc || cpu_has_de)
-		clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
+		cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
 
 	load_current_idt();
 	switch_to_new_gdt(cpu);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index 09edd0b65fe..10b46906767 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -3,6 +3,8 @@
 
 enum severity_level {
 	MCE_NO_SEVERITY,
+	MCE_DEFERRED_SEVERITY,
+	MCE_UCNA_SEVERITY = MCE_DEFERRED_SEVERITY,
 	MCE_KEEP_SEVERITY,
 	MCE_SOME_SEVERITY,
 	MCE_AO_SEVERITY,
@@ -21,7 +23,7 @@ struct mce_bank {
 	char			attrname[ATTR_LEN];	/* attribute name */
 };
 
-int mce_severity(struct mce *a, int tolerant, char **msg);
+int mce_severity(struct mce *a, int tolerant, char **msg, bool is_excp);
 struct dentry *mce_get_debugfs_dir(void);
 
 extern struct mce_bank *mce_banks;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index c370e1c4468..8bb433043a7 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -31,6 +31,7 @@
 
 enum context { IN_KERNEL = 1, IN_USER = 2 };
 enum ser { SER_REQUIRED = 1, NO_SER = 2 };
+enum exception { EXCP_CONTEXT = 1, NO_EXCP = 2 };
 
 static struct severity {
 	u64 mask;
@@ -40,6 +41,7 @@ static struct severity {
 	unsigned char mcgres;
 	unsigned char ser;
 	unsigned char context;
+	unsigned char excp;
 	unsigned char covered;
 	char *msg;
 } severities[] = {
@@ -48,6 +50,8 @@ static struct severity {
 #define  USER		.context = IN_USER
 #define  SER		.ser = SER_REQUIRED
 #define  NOSER		.ser = NO_SER
+#define  EXCP		.excp = EXCP_CONTEXT
+#define  NOEXCP		.excp = NO_EXCP
 #define  BITCLR(x)	.mask = x, .result = 0
 #define  BITSET(x)	.mask = x, .result = x
 #define  MCGMASK(x, y)	.mcgmask = x, .mcgres = y
@@ -62,7 +66,7 @@ static struct severity {
 		),
 	MCESEV(
 		NO, "Not enabled",
-		BITCLR(MCI_STATUS_EN)
+		EXCP, BITCLR(MCI_STATUS_EN)
 		),
 	MCESEV(
 		PANIC, "Processor context corrupt",
@@ -71,16 +75,20 @@ static struct severity {
 	/* When MCIP is not set something is very confused */
 	MCESEV(
 		PANIC, "MCIP not set in MCA handler",
-		MCGMASK(MCG_STATUS_MCIP, 0)
+		EXCP, MCGMASK(MCG_STATUS_MCIP, 0)
 		),
 	/* Neither return not error IP -- no chance to recover -> PANIC */
 	MCESEV(
 		PANIC, "Neither restart nor error IP",
-		MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, 0)
+		EXCP, MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, 0)
 		),
 	MCESEV(
 		PANIC, "In kernel and no restart IP",
-		KERNEL, MCGMASK(MCG_STATUS_RIPV, 0)
+		EXCP, KERNEL, MCGMASK(MCG_STATUS_RIPV, 0)
+		),
+	MCESEV(
+		DEFERRED, "Deferred error",
+		NOSER, MASK(MCI_STATUS_UC|MCI_STATUS_DEFERRED|MCI_STATUS_POISON, MCI_STATUS_DEFERRED)
 		),
 	MCESEV(
 		KEEP, "Corrected error",
@@ -89,7 +97,7 @@ static struct severity {
 
 	/* ignore OVER for UCNA */
 	MCESEV(
-		KEEP, "Uncorrected no action required",
+		UCNA, "Uncorrected no action required",
 		SER, MASK(MCI_UC_SAR, MCI_STATUS_UC)
 		),
 	MCESEV(
@@ -178,8 +186,9 @@ static int error_context(struct mce *m)
 	return ((m->cs & 3) == 3) ? IN_USER : IN_KERNEL;
 }
 
-int mce_severity(struct mce *m, int tolerant, char **msg)
+int mce_severity(struct mce *m, int tolerant, char **msg, bool is_excp)
 {
+	enum exception excp = (is_excp ? EXCP_CONTEXT : NO_EXCP);
 	enum context ctx = error_context(m);
 	struct severity *s;
 
@@ -194,6 +203,8 @@ int mce_severity(struct mce *m, int tolerant, char **msg)
 			continue;
 		if (s->context && ctx != s->context)
 			continue;
+		if (s->excp && excp != s->excp)
+			continue;
 		if (msg)
 			*msg = s->msg;
 		s->covered = 1;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 61a9668cebf..bf44e45a2a7 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -43,6 +43,7 @@
 #include <linux/export.h>
 
 #include <asm/processor.h>
+#include <asm/tlbflush.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 
@@ -660,6 +661,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 			  struct pt_regs *regs)
 {
 	int i, ret = 0;
+	char *tmp;
 
 	for (i = 0; i < mca_cfg.banks; i++) {
 		m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
@@ -668,8 +670,11 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 			if (quirk_no_way_out)
 				quirk_no_way_out(i, m, regs);
 		}
-		if (mce_severity(m, mca_cfg.tolerant, msg) >= MCE_PANIC_SEVERITY)
+
+		if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
+			*msg = tmp;
 			ret = 1;
+		}
 	}
 	return ret;
 }
@@ -754,7 +759,7 @@ static void mce_reign(void)
 	for_each_possible_cpu(cpu) {
 		int severity = mce_severity(&per_cpu(mces_seen, cpu),
 					    mca_cfg.tolerant,
-					    &nmsg);
+					    &nmsg, true);
 		if (severity > global_worst) {
 			msg = nmsg;
 			global_worst = severity;
@@ -1095,13 +1100,14 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		 */
 		add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
 
-		severity = mce_severity(&m, cfg->tolerant, NULL);
+		severity = mce_severity(&m, cfg->tolerant, NULL, true);
 
 		/*
-		 * When machine check was for corrected handler don't touch,
-		 * unless we're panicing.
+		 * When machine check was for corrected/deferred handler don't
+		 * touch, unless we're panicing.
 		 */
-		if (severity == MCE_KEEP_SEVERITY && !no_way_out)
+		if ((severity == MCE_KEEP_SEVERITY ||
+		     severity == MCE_UCNA_SEVERITY) && !no_way_out)
 			continue;
 		__set_bit(i, toclear);
 		if (severity == MCE_NO_SEVERITY) {
@@ -1455,7 +1461,7 @@ static void __mcheck_cpu_init_generic(void)
 	bitmap_fill(all_banks, MAX_NR_BANKS);
 	machine_check_poll(MCP_UC | m_fl, &all_banks);
 
-	set_in_cr4(X86_CR4_MCE);
+	cr4_set_bits(X86_CR4_MCE);
 
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 	if (cap & MCG_CTL_P)
diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c
index a3042989398..30692ac88d1 100644
--- a/arch/x86/kernel/cpu/mcheck/p5.c
+++ b/arch/x86/kernel/cpu/mcheck/p5.c
@@ -8,6 +8,7 @@
 #include <linux/smp.h>
 
 #include <asm/processor.h>
+#include <asm/tlbflush.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 
@@ -59,7 +60,7 @@ void intel_p5_mcheck_init(struct cpuinfo_x86 *c)
 	       "Intel old style machine check architecture supported.\n");
 
 	/* Enable MCE: */
-	set_in_cr4(X86_CR4_MCE);
+	cr4_set_bits(X86_CR4_MCE);
 	printk(KERN_INFO
 	       "Intel old style machine check reporting enabled on CPU#%d.\n",
 	       smp_processor_id());
diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c
index 7dc5564d0cd..590cc753ba8 100644
--- a/arch/x86/kernel/cpu/mcheck/winchip.c
+++ b/arch/x86/kernel/cpu/mcheck/winchip.c
@@ -7,6 +7,7 @@
 #include <linux/types.h>
 
 #include <asm/processor.h>
+#include <asm/tlbflush.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 
@@ -31,7 +32,7 @@ void winchip_mcheck_init(struct cpuinfo_x86 *c)
 	lo &= ~(1<<4);	/* Enable MCE */
 	wrmsr(MSR_IDT_FCR1, lo, hi);
 
-	set_in_cr4(X86_CR4_MCE);
+	cr4_set_bits(X86_CR4_MCE);
 
 	printk(KERN_INFO
 	       "Winchip machine check reporting enabled on CPU#0.\n");
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 8fffd845e22..bfbbe6195e2 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -376,7 +376,7 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
 	return UCODE_OK;
 }
 
-enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
+enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size)
 {
 	enum ucode_state ret;
 
@@ -390,8 +390,8 @@ enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
 
 #if defined(CONFIG_MICROCODE_AMD_EARLY) && defined(CONFIG_X86_32)
 	/* save BSP's matching patch for early load */
-	if (cpu_data(smp_processor_id()).cpu_index == boot_cpu_data.cpu_index) {
-		struct ucode_patch *p = find_patch(smp_processor_id());
+	if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) {
+		struct ucode_patch *p = find_patch(cpu);
 		if (p) {
 			memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
 			memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data),
@@ -444,7 +444,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 		goto fw_release;
 	}
 
-	ret = load_microcode_amd(c->x86, fw->data, fw->size);
+	ret = load_microcode_amd(cpu, c->x86, fw->data, fw->size);
 
  fw_release:
 	release_firmware(fw);
diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c
index 06674473b0e..737737edbd1 100644
--- a/arch/x86/kernel/cpu/microcode/amd_early.c
+++ b/arch/x86/kernel/cpu/microcode/amd_early.c
@@ -389,7 +389,7 @@ int __init save_microcode_in_initrd_amd(void)
 	eax   = cpuid_eax(0x00000001);
 	eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
 
-	ret = load_microcode_amd(eax, container, container_size);
+	ret = load_microcode_amd(smp_processor_id(), eax, container, container_size);
 	if (ret != UCODE_OK)
 		retval = -EINVAL;
 
@@ -402,3 +402,21 @@ int __init save_microcode_in_initrd_amd(void)
 
 	return retval;
 }
+
+void reload_ucode_amd(void)
+{
+	struct microcode_amd *mc;
+	u32 rev, eax;
+
+	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax);
+
+	mc = (struct microcode_amd *)amd_ucode_patch;
+
+	if (mc && rev < mc->hdr.patch_id) {
+		if (!__apply_microcode_amd(mc)) {
+			ucode_new_rev = mc->hdr.patch_id;
+			pr_info("microcode: reload patch_level=0x%08x\n",
+				ucode_new_rev);
+		}
+	}
+}
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 08fe6e8a726..36a83617eb2 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -465,16 +465,8 @@ static void mc_bp_resume(void)
 
 	if (uci->valid && uci->mc)
 		microcode_ops->apply_microcode(cpu);
-#ifdef CONFIG_X86_64
 	else if (!uci->mc)
-		/*
-		 * We might resume and not have applied late microcode but still
-		 * have a newer patch stashed from the early loader. We don't
-		 * have it in uci->mc so we have to load it the same way we're
-		 * applying patches early on the APs.
-		 */
-		load_ucode_ap();
-#endif
+		reload_early_microcode();
 }
 
 static struct syscore_ops mc_syscore_ops = {
@@ -559,8 +551,8 @@ static int __init microcode_init(void)
 	struct cpuinfo_x86 *c = &cpu_data(0);
 	int error;
 
-	if (dis_ucode_ldr)
-		return 0;
+	if (paravirt_enabled() || dis_ucode_ldr)
+		return -EINVAL;
 
 	if (c->x86_vendor == X86_VENDOR_INTEL)
 		microcode_ops = init_intel_microcode();
diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c
index 2c017f242a7..d45df4bd16a 100644
--- a/arch/x86/kernel/cpu/microcode/core_early.c
+++ b/arch/x86/kernel/cpu/microcode/core_early.c
@@ -176,3 +176,24 @@ int __init save_microcode_in_initrd(void)
 
 	return 0;
 }
+
+void reload_early_microcode(void)
+{
+	int vendor, x86;
+
+	vendor = x86_vendor();
+	x86 = x86_family();
+
+	switch (vendor) {
+	case X86_VENDOR_INTEL:
+		if (x86 >= 6)
+			reload_ucode_intel();
+		break;
+	case X86_VENDOR_AMD:
+		if (x86 >= 0x10)
+			reload_ucode_amd();
+		break;
+	default:
+		break;
+	}
+}
diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c
index b88343f7a3b..5e109a31f62 100644
--- a/arch/x86/kernel/cpu/microcode/intel_early.c
+++ b/arch/x86/kernel/cpu/microcode/intel_early.c
@@ -321,7 +321,7 @@ get_matching_model_microcode(int cpu, unsigned long start,
 	unsigned int mc_saved_count = mc_saved_data->mc_saved_count;
 	int i;
 
-	while (leftover) {
+	while (leftover && mc_saved_count < ARRAY_SIZE(mc_saved_tmp)) {
 		mc_header = (struct microcode_header_intel *)ucode_ptr;
 
 		mc_size = get_totalsize(mc_header);
@@ -650,8 +650,7 @@ static inline void print_ucode(struct ucode_cpu_info *uci)
 }
 #endif
 
-static int apply_microcode_early(struct mc_saved_data *mc_saved_data,
-				 struct ucode_cpu_info *uci)
+static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
 {
 	struct microcode_intel *mc_intel;
 	unsigned int val[2];
@@ -680,7 +679,10 @@ static int apply_microcode_early(struct mc_saved_data *mc_saved_data,
 #endif
 	uci->cpu_sig.rev = val[1];
 
-	print_ucode(uci);
+	if (early)
+		print_ucode(uci);
+	else
+		print_ucode_info(uci, mc_intel->hdr.date);
 
 	return 0;
 }
@@ -715,12 +717,17 @@ _load_ucode_intel_bsp(struct mc_saved_data *mc_saved_data,
 		      unsigned long initrd_end_early,
 		      struct ucode_cpu_info *uci)
 {
+	enum ucode_state ret;
+
 	collect_cpu_info_early(uci);
 	scan_microcode(initrd_start_early, initrd_end_early, mc_saved_data,
 		       mc_saved_in_initrd, uci);
-	load_microcode(mc_saved_data, mc_saved_in_initrd,
-		       initrd_start_early, uci);
-	apply_microcode_early(mc_saved_data, uci);
+
+	ret = load_microcode(mc_saved_data, mc_saved_in_initrd,
+			     initrd_start_early, uci);
+
+	if (ret == UCODE_OK)
+		apply_microcode_early(uci, true);
 }
 
 void __init
@@ -749,7 +756,8 @@ load_ucode_intel_bsp(void)
 	initrd_end_early = initrd_start_early + ramdisk_size;
 
 	_load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd,
-			      initrd_start_early, initrd_end_early, &uci);
+			      initrd_start_early, initrd_end_early,
+			      &uci);
 #endif
 }
 
@@ -783,5 +791,23 @@ void load_ucode_intel_ap(void)
 	collect_cpu_info_early(&uci);
 	load_microcode(mc_saved_data_p, mc_saved_in_initrd_p,
 		       initrd_start_addr, &uci);
-	apply_microcode_early(mc_saved_data_p, &uci);
+	apply_microcode_early(&uci, true);
+}
+
+void reload_ucode_intel(void)
+{
+	struct ucode_cpu_info uci;
+	enum ucode_state ret;
+
+	if (!mc_saved_data.mc_saved_count)
+		return;
+
+	collect_cpu_info_early(&uci);
+
+	ret = generic_load_microcode_early(mc_saved_data.mc_saved,
+					   mc_saved_data.mc_saved_count, &uci);
+	if (ret != UCODE_OK)
+		return;
+
+	apply_microcode_early(&uci, false);
 }
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index a450373e8e9..939155ffdec 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -107,6 +107,7 @@ static struct clocksource hyperv_cs = {
 	.rating		= 400, /* use this when running on Hyperv*/
 	.read		= read_hv_clock,
 	.mask		= CLOCKSOURCE_MASK(64),
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 static void __init ms_hyperv_init_platform(void)
diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c
index 9e451b0876b..f8c81ba0b46 100644
--- a/arch/x86/kernel/cpu/mtrr/cyrix.c
+++ b/arch/x86/kernel/cpu/mtrr/cyrix.c
@@ -138,8 +138,8 @@ static void prepare_set(void)
 
 	/*  Save value of CR4 and clear Page Global Enable (bit 7)  */
 	if (cpu_has_pge) {
-		cr4 = read_cr4();
-		write_cr4(cr4 & ~X86_CR4_PGE);
+		cr4 = __read_cr4();
+		__write_cr4(cr4 & ~X86_CR4_PGE);
 	}
 
 	/*
@@ -171,7 +171,7 @@ static void post_set(void)
 
 	/* Restore value of CR4 */
 	if (cpu_has_pge)
-		write_cr4(cr4);
+		__write_cr4(cr4);
 }
 
 static void cyrix_set_arr(unsigned int reg, unsigned long base,
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 0e25a1bc5ab..7d74f7b3c6b 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -678,8 +678,8 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 
 	/* Save value of CR4 and clear Page Global Enable (bit 7) */
 	if (cpu_has_pge) {
-		cr4 = read_cr4();
-		write_cr4(cr4 & ~X86_CR4_PGE);
+		cr4 = __read_cr4();
+		__write_cr4(cr4 & ~X86_CR4_PGE);
 	}
 
 	/* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */
@@ -708,7 +708,7 @@ static void post_set(void) __releases(set_atomicity_lock)
 
 	/* Restore value of CR4 */
 	if (cpu_has_pge)
-		write_cr4(cr4);
+		__write_cr4(cr4);
 	raw_spin_unlock(&set_atomicity_lock);
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 143e5f5dc85..6b5acd5f4a3 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -31,6 +31,7 @@
 #include <asm/nmi.h>
 #include <asm/smp.h>
 #include <asm/alternative.h>
+#include <asm/tlbflush.h>
 #include <asm/timer.h>
 #include <asm/desc.h>
 #include <asm/ldt.h>
@@ -1328,7 +1329,7 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 
 	case CPU_STARTING:
 		if (x86_pmu.attr_rdpmc)
-			set_in_cr4(X86_CR4_PCE);
+			cr4_set_bits(X86_CR4_PCE);
 		if (x86_pmu.cpu_starting)
 			x86_pmu.cpu_starting(cpu);
 		break;
@@ -1834,9 +1835,9 @@ static void change_rdpmc(void *info)
 	bool enable = !!(unsigned long)info;
 
 	if (enable)
-		set_in_cr4(X86_CR4_PCE);
+		cr4_set_bits(X86_CR4_PCE);
 	else
-		clear_in_cr4(X86_CR4_PCE);
+		cr4_clear_bits(X86_CR4_PCE);
 }
 
 static ssize_t set_attr_rdpmc(struct device *cdev,
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 944bf019b74..df11583a904 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2431,6 +2431,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 55: /* 22nm Atom "Silvermont"                */
+	case 76: /* 14nm Atom "Airmont"                   */
 	case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
@@ -2603,13 +2604,13 @@ __init int intel_pmu_init(void)
 		 * counter, so do not extend mask to generic counters
 		 */
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
-			if (c->cmask != FIXED_EVENT_FLAGS
-			    || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) {
-				continue;
+			if (c->cmask == FIXED_EVENT_FLAGS
+			    && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) {
+				c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
 			}
-
-			c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
-			c->weight += x86_pmu.num_counters;
+			c->idxmsk64 &=
+				~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
+			c->weight = hweight64(c->idxmsk64);
 		}
 	}
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index d64f275fe27..611d821eac1 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -135,7 +135,7 @@ static inline u64 rapl_scale(u64 v)
 	 * or use ldexp(count, -32).
 	 * Watts = Joules/Time delta
 	 */
-	return v << (32 - __this_cpu_read(rapl_pmu->hw_unit));
+	return v << (32 - __this_cpu_read(rapl_pmu)->hw_unit);
 }
 
 static u64 rapl_event_update(struct perf_event *event)
@@ -664,6 +664,7 @@ static int __init rapl_pmu_init(void)
 		break;
 	case 60: /* Haswell */
 	case 69: /* Haswell-Celeron */
+	case 61: /* Broadwell */
 		rapl_cntr_mask = RAPL_IDX_HSW;
 		rapl_pmu_events_group.attrs = rapl_events_hsw_attr;
 		break;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 9762dbd9f3f..e98f68cfea0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -276,6 +276,17 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
 	return box;
 }
 
+/*
+ * Using uncore_pmu_event_init pmu event_init callback
+ * as a detection point for uncore events.
+ */
+static int uncore_pmu_event_init(struct perf_event *event);
+
+static bool is_uncore_event(struct perf_event *event)
+{
+	return event->pmu->event_init == uncore_pmu_event_init;
+}
+
 static int
 uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp)
 {
@@ -290,13 +301,18 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, b
 		return -EINVAL;
 
 	n = box->n_events;
-	box->event_list[n] = leader;
-	n++;
+
+	if (is_uncore_event(leader)) {
+		box->event_list[n] = leader;
+		n++;
+	}
+
 	if (!dogrp)
 		return n;
 
 	list_for_each_entry(event, &leader->sibling_list, group_entry) {
-		if (event->state <= PERF_EVENT_STATE_OFF)
+		if (!is_uncore_event(event) ||
+		    event->state <= PERF_EVENT_STATE_OFF)
 			continue;
 
 		if (n >= max_count)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 18eb78bbdd1..863d9b02563 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -17,7 +17,7 @@
 #define UNCORE_PCI_DEV_TYPE(data)	((data >> 8) & 0xff)
 #define UNCORE_PCI_DEV_IDX(data)	(data & 0xff)
 #define UNCORE_EXTRA_PCI_DEV		0xff
-#define UNCORE_EXTRA_PCI_DEV_MAX	2
+#define UNCORE_EXTRA_PCI_DEV_MAX	3
 
 /* support up to 8 sockets */
 #define UNCORE_SOCKET_MAX		8
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index f9ed429d6e4..ab474faa262 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -887,6 +887,7 @@ void snbep_uncore_cpu_init(void)
 enum {
 	SNBEP_PCI_QPI_PORT0_FILTER,
 	SNBEP_PCI_QPI_PORT1_FILTER,
+	HSWEP_PCI_PCU_3,
 };
 
 static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
@@ -2022,6 +2023,17 @@ void hswep_uncore_cpu_init(void)
 {
 	if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+
+	/* Detect 6-8 core systems with only two SBOXes */
+	if (uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3]) {
+		u32 capid4;
+
+		pci_read_config_dword(uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3],
+				      0x94, &capid4);
+		if (((capid4 >> 6) & 0x3) == 0)
+			hswep_uncore_sbox.num_boxes = 2;
+	}
+
 	uncore_msr_uncores = hswep_msr_uncores;
 }
 
@@ -2279,6 +2291,11 @@ static DEFINE_PCI_DEVICE_TABLE(hswep_uncore_pci_ids) = {
 		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
 						   SNBEP_PCI_QPI_PORT1_FILTER),
 	},
+	{ /* PCU.3 (for Capability registers) */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fc0),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   HSWEP_PCI_PCU_3),
+	},
 	{ /* end: all zeroes */ }
 };
 
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 344b63f18d1..3dddb89ba32 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -982,6 +982,9 @@ ENTRY(xen_hypervisor_callback)
 ENTRY(xen_do_upcall)
 1:	mov %esp, %eax
 	call xen_evtchn_do_upcall
+#ifndef CONFIG_PREEMPT
+	call xen_maybe_preempt_hcall
+#endif
 	jmp  ret_from_intr
 	CFI_ENDPROC
 ENDPROC(xen_hypervisor_callback)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index c0226ab5410..e36d9815ef5 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -334,11 +334,14 @@ ENTRY(ret_from_fork)
 	testl $3, CS-ARGOFFSET(%rsp)		# from kernel_thread?
 	jz   1f
 
-	testl $_TIF_IA32, TI_flags(%rcx)	# 32-bit compat task needs IRET
-	jnz  int_ret_from_sys_call
-
-	RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET
-	jmp ret_from_sys_call			# go to the SYSRET fastpath
+	/*
+	 * By the time we get here, we have no idea whether our pt_regs,
+	 * ti flags, and ti status came from the 64-bit SYSCALL fast path,
+	 * the slow path, or one of the ia32entry paths.
+	 * Use int_ret_from_sys_call to return, since it can safely handle
+	 * all of the above.
+	 */
+	jmp  int_ret_from_sys_call
 
 1:
 	subq $REST_SKIP, %rsp	# leave space for volatiles
@@ -1170,6 +1173,9 @@ ENTRY(xen_do_hypervisor_callback)   # do_hypervisor_callback(struct *pt_regs)
 	popq %rsp
 	CFI_DEF_CFA_REGISTER rsp
 	decl PER_CPU_VAR(irq_count)
+#ifndef CONFIG_PREEMPT
+	call xen_maybe_preempt_hcall
+#endif
 	jmp  error_exit
 	CFI_ENDPROC
 END(xen_do_hypervisor_callback)
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index d6c1b983699..2911ef3a9f1 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -31,6 +31,7 @@ static void __init i386_default_early_setup(void)
 
 asmlinkage __visible void __init i386_start_kernel(void)
 {
+	cr4_init_shadow();
 	sanitize_boot_params(&boot_params);
 
 	/* Call the subarch specific early setup function */
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index eda1a865641..957fdb5eb2e 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -155,6 +155,8 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 				(__START_KERNEL & PGDIR_MASK)));
 	BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END);
 
+	cr4_init_shadow();
+
 	/* Kill off the identity-map trampoline */
 	reset_early_page_tables();
 
@@ -162,7 +164,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 	clear_bss();
 
 	for (i = 0; i < NUM_EXCEPTION_VECTORS; i++)
-		set_intr_gate(i, early_idt_handlers[i]);
+		set_intr_gate(i, early_idt_handler_array[i]);
 	load_idt((const struct desc_ptr *)&idt_descr);
 
 	copy_bootdata(__va(real_mode_data));
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index f36bd42d6f0..e7be5290fe1 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -61,9 +61,16 @@
 #define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
 #endif
 
-/* Number of possible pages in the lowmem region */
-LOWMEM_PAGES = (((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT)
-	
+/*
+ * Number of possible pages in the lowmem region.
+ *
+ * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a
+ * gas warning about overflowing shift count when gas has been compiled
+ * with only a host target support using a 32-bit type for internal
+ * representation.
+ */
+LOWMEM_PAGES = (((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT)
+
 /* Enough space to fit pagetables for the low memory linear map */
 MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT
 
@@ -477,21 +484,22 @@ is486:
 __INIT
 setup_once:
 	/*
-	 * Set up a idt with 256 entries pointing to ignore_int,
-	 * interrupt gates. It doesn't actually load idt - that needs
-	 * to be done on each CPU. Interrupts are enabled elsewhere,
-	 * when we can be relatively sure everything is ok.
+	 * Set up a idt with 256 interrupt gates that push zero if there
+	 * is no error code and then jump to early_idt_handler_common.
+	 * It doesn't actually load the idt - that needs to be done on
+	 * each CPU. Interrupts are enabled elsewhere, when we can be
+	 * relatively sure everything is ok.
 	 */
 
 	movl $idt_table,%edi
-	movl $early_idt_handlers,%eax
+	movl $early_idt_handler_array,%eax
 	movl $NUM_EXCEPTION_VECTORS,%ecx
 1:
 	movl %eax,(%edi)
 	movl %eax,4(%edi)
 	/* interrupt gate, dpl=0, present */
 	movl $(0x8E000000 + __KERNEL_CS),2(%edi)
-	addl $9,%eax
+	addl $EARLY_IDT_HANDLER_SIZE,%eax
 	addl $8,%edi
 	loop 1b
 
@@ -523,26 +531,28 @@ setup_once:
 	andl $0,setup_once_ref	/* Once is enough, thanks */
 	ret
 
-ENTRY(early_idt_handlers)
+ENTRY(early_idt_handler_array)
 	# 36(%esp) %eflags
 	# 32(%esp) %cs
 	# 28(%esp) %eip
 	# 24(%rsp) error code
 	i = 0
 	.rept NUM_EXCEPTION_VECTORS
-	.if (EXCEPTION_ERRCODE_MASK >> i) & 1
-	ASM_NOP2
-	.else
+	.ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1
 	pushl $0		# Dummy error code, to make stack frame uniform
 	.endif
 	pushl $i		# 20(%esp) Vector number
-	jmp early_idt_handler
+	jmp early_idt_handler_common
 	i = i + 1
+	.fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
 	.endr
-ENDPROC(early_idt_handlers)
+ENDPROC(early_idt_handler_array)
 	
-	/* This is global to keep gas from relaxing the jumps */
-ENTRY(early_idt_handler)
+early_idt_handler_common:
+	/*
+	 * The stack is the hardware frame, an error code or zero, and the
+	 * vector number.
+	 */
 	cld
 
 	cmpl $2,(%esp)		# X86_TRAP_NMI
@@ -602,7 +612,7 @@ ex_entry:
 is_nmi:
 	addl $8,%esp		/* drop vector number and error code */
 	iret
-ENDPROC(early_idt_handler)
+ENDPROC(early_idt_handler_common)
 
 /* This is the default interrupt "handler" :-) */
 	ALIGN
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index a468c0a65c4..a2dc0add72e 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -321,26 +321,28 @@ bad_address:
 	jmp bad_address
 
 	__INIT
-	.globl early_idt_handlers
-early_idt_handlers:
+ENTRY(early_idt_handler_array)
 	# 104(%rsp) %rflags
 	#  96(%rsp) %cs
 	#  88(%rsp) %rip
 	#  80(%rsp) error code
 	i = 0
 	.rept NUM_EXCEPTION_VECTORS
-	.if (EXCEPTION_ERRCODE_MASK >> i) & 1
-	ASM_NOP2
-	.else
+	.ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1
 	pushq $0		# Dummy error code, to make stack frame uniform
 	.endif
 	pushq $i		# 72(%rsp) Vector number
-	jmp early_idt_handler
+	jmp early_idt_handler_common
 	i = i + 1
+	.fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
 	.endr
+ENDPROC(early_idt_handler_array)
 
-/* This is global to keep gas from relaxing the jumps */
-ENTRY(early_idt_handler)
+early_idt_handler_common:
+	/*
+	 * The stack is the hardware frame, an error code or zero, and the
+	 * vector number.
+	 */
 	cld
 
 	cmpl $2,(%rsp)		# X86_TRAP_NMI
@@ -412,7 +414,7 @@ ENTRY(early_idt_handler)
 is_nmi:
 	addq $16,%rsp		# drop vector number and error code
 	INTERRUPT_RETURN
-ENDPROC(early_idt_handler)
+ENDPROC(early_idt_handler_common)
 
 	__INITDATA
 
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index a9a4229f616..8d6e954db2a 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -13,6 +13,7 @@
 #include <asm/sigcontext.h>
 #include <asm/processor.h>
 #include <asm/math_emu.h>
+#include <asm/tlbflush.h>
 #include <asm/uaccess.h>
 #include <asm/ptrace.h>
 #include <asm/i387.h>
@@ -155,6 +156,21 @@ static void init_thread_xstate(void)
 		xstate_size = sizeof(struct i387_fxsave_struct);
 	else
 		xstate_size = sizeof(struct i387_fsave_struct);
+
+	/*
+	 * Quirk: we don't yet handle the XSAVES* instructions
+	 * correctly, as we don't correctly convert between
+	 * standard and compacted format when interfacing
+	 * with user-space - so disable it for now.
+	 *
+	 * The difference is small: with recent CPUs the
+	 * compacted format is only marginally smaller than
+	 * the standard FPU state format.
+	 *
+	 * ( This is easy to backport while we are fixing
+	 *   XSAVES* support. )
+	 */
+	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
 }
 
 /*
@@ -180,7 +196,7 @@ void fpu_init(void)
 	if (cpu_has_xmm)
 		cr4_mask |= X86_CR4_OSXMMEXCPT;
 	if (cr4_mask)
-		set_in_cr4(cr4_mask);
+		cr4_set_bits(cr4_mask);
 
 	cr0 = read_cr0();
 	cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 922d2858102..37907756fc4 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -127,7 +127,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	seq_printf(p, "  Machine check polls\n");
 #endif
 #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
-	seq_printf(p, "%*s: ", prec, "THR");
+	seq_printf(p, "%*s: ", prec, "HYP");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count);
 	seq_printf(p, "  Hypervisor callback interrupts\n");
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 67e6d19ef1b..f2e281cf8c1 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -330,13 +330,16 @@ int __copy_instruction(u8 *dest, u8 *src)
 {
 	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
+	int length;
 
 	kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src));
 	insn_get_length(&insn);
+	length = insn.length;
+
 	/* Another subsystem puts a breakpoint, failed to recover */
 	if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
 		return 0;
-	memcpy(dest, insn.kaddr, insn.length);
+	memcpy(dest, insn.kaddr, length);
 
 #ifdef CONFIG_X86_64
 	if (insn_rip_relative(&insn)) {
@@ -366,7 +369,7 @@ int __copy_instruction(u8 *dest, u8 *src)
 		*(s32 *) disp = (s32) newdisp;
 	}
 #endif
-	return insn.length;
+	return length;
 }
 
 static int arch_copy_kprobe(struct kprobe *p)
@@ -1018,6 +1021,15 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	regs->flags &= ~X86_EFLAGS_IF;
 	trace_hardirqs_off();
 	regs->ip = (unsigned long)(jp->entry);
+
+	/*
+	 * jprobes use jprobe_return() which skips the normal return
+	 * path of the function, and this messes up the accounting of the
+	 * function graph tracer to get messed up.
+	 *
+	 * Pause function graph tracing while performing the jprobe function.
+	 */
+	pause_graph_tracing();
 	return 1;
 }
 NOKPROBE_SYMBOL(setjmp_pre_handler);
@@ -1046,24 +1058,25 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 	u8 *addr = (u8 *) (regs->ip - 1);
 	struct jprobe *jp = container_of(p, struct jprobe, kp);
+	void *saved_sp = kcb->jprobe_saved_sp;
 
 	if ((addr > (u8 *) jprobe_return) &&
 	    (addr < (u8 *) jprobe_return_end)) {
-		if (stack_addr(regs) != kcb->jprobe_saved_sp) {
+		if (stack_addr(regs) != saved_sp) {
 			struct pt_regs *saved_regs = &kcb->jprobe_saved_regs;
 			printk(KERN_ERR
 			       "current sp %p does not match saved sp %p\n",
-			       stack_addr(regs), kcb->jprobe_saved_sp);
+			       stack_addr(regs), saved_sp);
 			printk(KERN_ERR "Saved registers for jprobe %p\n", jp);
 			show_regs(saved_regs);
 			printk(KERN_ERR "Current registers\n");
 			show_regs(regs);
 			BUG();
 		}
+		/* It's OK to start function graph tracing again */
+		unpause_graph_tracing();
 		*regs = kcb->jprobe_saved_regs;
-		memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp),
-		       kcb->jprobes_stack,
-		       MIN_STACK_SIZE(kcb->jprobe_saved_sp));
+		memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp));
 		preempt_enable_no_resched();
 		return 1;
 	}
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index f6945bef2cd..94f64348430 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -283,7 +283,14 @@ NOKPROBE_SYMBOL(do_async_page_fault);
 static void __init paravirt_ops_setup(void)
 {
 	pv_info.name = "KVM";
-	pv_info.paravirt_enabled = 1;
+
+	/*
+	 * KVM isn't paravirt in the sense of paravirt_enabled.  A KVM
+	 * guest kernel works like a bare metal kernel with additional
+	 * features, and paravirt_enabled is about features that are
+	 * missing.
+	 */
+	pv_info.paravirt_enabled = 0;
 
 	if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
 		pv_cpu_ops.io_delay = kvm_io_delay;
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index d9156ceecdf..a2de9bc7ac0 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -263,7 +263,6 @@ void __init kvmclock_init(void)
 #endif
 	kvm_get_preset_lpj();
 	clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
-	pv_info.paravirt_enabled = 1;
 	pv_info.name = "KVM";
 
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
diff --git a/arch/x86/kernel/pmc_atom.c b/arch/x86/kernel/pmc_atom.c
index 0ee5025e0fa..8bb9a611ca2 100644
--- a/arch/x86/kernel/pmc_atom.c
+++ b/arch/x86/kernel/pmc_atom.c
@@ -217,6 +217,8 @@ static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev)
 	if (!dir)
 		return -ENOMEM;
 
+	pmc->dbgfs_dir = dir;
+
 	f = debugfs_create_file("dev_state", S_IFREG | S_IRUGO,
 				dir, pmc, &pmc_dev_state_ops);
 	if (!f) {
@@ -229,7 +231,7 @@ static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev)
 		dev_err(&pdev->dev, "sleep_state register failed\n");
 		goto err;
 	}
-	pmc->dbgfs_dir = dir;
+
 	return 0;
 err:
 	pmc_dbgfs_unregister(pmc);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index e127ddaa2d5..0885df57ce7 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -24,10 +24,12 @@
 #include <asm/syscalls.h>
 #include <asm/idle.h>
 #include <asm/uaccess.h>
+#include <asm/mwait.h>
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
 #include <asm/debugreg.h>
 #include <asm/nmi.h>
+#include <asm/tlbflush.h>
 
 /*
  * per-CPU TSS segments. Threads are completely 'soft' on Linux,
@@ -40,19 +42,6 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS;
 
 #ifdef CONFIG_X86_64
 static DEFINE_PER_CPU(unsigned char, is_idle);
-static ATOMIC_NOTIFIER_HEAD(idle_notifier);
-
-void idle_notifier_register(struct notifier_block *n)
-{
-	atomic_notifier_chain_register(&idle_notifier, n);
-}
-EXPORT_SYMBOL_GPL(idle_notifier_register);
-
-void idle_notifier_unregister(struct notifier_block *n)
-{
-	atomic_notifier_chain_unregister(&idle_notifier, n);
-}
-EXPORT_SYMBOL_GPL(idle_notifier_unregister);
 #endif
 
 struct kmem_cache *task_xstate_cachep;
@@ -141,7 +130,7 @@ void flush_thread(void)
 
 static void hard_disable_TSC(void)
 {
-	write_cr4(read_cr4() | X86_CR4_TSD);
+	cr4_set_bits(X86_CR4_TSD);
 }
 
 void disable_TSC(void)
@@ -158,7 +147,7 @@ void disable_TSC(void)
 
 static void hard_enable_TSC(void)
 {
-	write_cr4(read_cr4() & ~X86_CR4_TSD);
+	cr4_clear_bits(X86_CR4_TSD);
 }
 
 static void enable_TSC(void)
@@ -260,14 +249,14 @@ static inline void play_dead(void)
 void enter_idle(void)
 {
 	this_cpu_write(is_idle, 1);
-	atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
+	idle_notifier_call_chain(IDLE_START);
 }
 
 static void __exit_idle(void)
 {
 	if (x86_test_and_clear_bit_percpu(0, is_idle) == 0)
 		return;
-	atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
+	idle_notifier_call_chain(IDLE_END);
 }
 
 /* Called from interrupts to signify idle end */
@@ -398,6 +387,53 @@ static void amd_e400_idle(void)
 		default_idle();
 }
 
+/*
+ * Intel Core2 and older machines prefer MWAIT over HALT for C1.
+ * We can't rely on cpuidle installing MWAIT, because it will not load
+ * on systems that support only C1 -- so the boot default must be MWAIT.
+ *
+ * Some AMD machines are the opposite, they depend on using HALT.
+ *
+ * So for default C1, which is used during boot until cpuidle loads,
+ * use MWAIT-C1 on Intel HW that has it, else use HALT.
+ */
+static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
+{
+	if (c->x86_vendor != X86_VENDOR_INTEL)
+		return 0;
+
+	if (!cpu_has(c, X86_FEATURE_MWAIT))
+		return 0;
+
+	return 1;
+}
+
+/*
+ * MONITOR/MWAIT with no hints, used for default default C1 state.
+ * This invokes MWAIT with interrutps enabled and no flags,
+ * which is backwards compatible with the original MWAIT implementation.
+ */
+
+static void mwait_idle(void)
+{
+	if (!current_set_polling_and_test()) {
+		if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) {
+			smp_mb(); /* quirk */
+			clflush((void *)&current_thread_info()->flags);
+			smp_mb(); /* quirk */
+		}
+
+		__monitor((void *)&current_thread_info()->flags, 0, 0);
+		if (!need_resched())
+			__sti_mwait(0, 0);
+		else
+			local_irq_enable();
+	} else {
+		local_irq_enable();
+	}
+	__current_clr_polling();
+}
+
 void select_idle_routine(const struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
@@ -411,6 +447,9 @@ void select_idle_routine(const struct cpuinfo_x86 *c)
 		/* E400: APIC timer interrupt does not wake up CPU from C1e */
 		pr_info("using AMD E400 aware idle routine\n");
 		x86_idle = amd_e400_idle;
+	} else if (prefer_mwait_c1_over_halt(c)) {
+		pr_info("using mwait in idle threads\n");
+		x86_idle = mwait_idle;
 	} else
 		x86_idle = default_idle;
 }
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 8f3ebfe710d..603c4f99cb5 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -101,7 +101,7 @@ void __show_regs(struct pt_regs *regs, int all)
 	cr0 = read_cr0();
 	cr2 = read_cr2();
 	cr3 = read_cr3();
-	cr4 = read_cr4_safe();
+	cr4 = __read_cr4_safe();
 	printk(KERN_DEFAULT "CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n",
 			cr0, cr2, cr3, cr4);
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 3ed4a68d401..67fcc43577d 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -93,7 +93,7 @@ void __show_regs(struct pt_regs *regs, int all)
 	cr0 = read_cr0();
 	cr2 = read_cr2();
 	cr3 = read_cr3();
-	cr4 = read_cr4();
+	cr4 = __read_cr4();
 
 	printk(KERN_DEFAULT "FS:  %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
 	       fs, fsindex, gs, gsindex, shadowgs);
@@ -283,24 +283,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	fpu = switch_fpu_prepare(prev_p, next_p, cpu);
 
-	/*
-	 * Reload esp0, LDT and the page table pointer:
-	 */
+	/* Reload esp0 and ss1. */
 	load_sp0(tss, next);
 
-	/*
-	 * Switch DS and ES.
-	 * This won't pick up thread selector changes, but I guess that is ok.
-	 */
-	savesegment(es, prev->es);
-	if (unlikely(next->es | prev->es))
-		loadsegment(es, next->es);
-
-	savesegment(ds, prev->ds);
-	if (unlikely(next->ds | prev->ds))
-		loadsegment(ds, next->ds);
-
-
 	/* We must save %fs and %gs before load_TLS() because
 	 * %fs and %gs may be cleared by load_TLS().
 	 *
@@ -309,41 +294,101 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	savesegment(fs, fsindex);
 	savesegment(gs, gsindex);
 
+	/*
+	 * Load TLS before restoring any segments so that segment loads
+	 * reference the correct GDT entries.
+	 */
 	load_TLS(next, cpu);
 
 	/*
-	 * Leave lazy mode, flushing any hypercalls made here.
-	 * This must be done before restoring TLS segments so
-	 * the GDT and LDT are properly updated, and must be
-	 * done before math_state_restore, so the TS bit is up
-	 * to date.
+	 * Leave lazy mode, flushing any hypercalls made here.  This
+	 * must be done after loading TLS entries in the GDT but before
+	 * loading segments that might reference them, and and it must
+	 * be done before math_state_restore, so the TS bit is up to
+	 * date.
 	 */
 	arch_end_context_switch(next_p);
 
+	/* Switch DS and ES.
+	 *
+	 * Reading them only returns the selectors, but writing them (if
+	 * nonzero) loads the full descriptor from the GDT or LDT.  The
+	 * LDT for next is loaded in switch_mm, and the GDT is loaded
+	 * above.
+	 *
+	 * We therefore need to write new values to the segment
+	 * registers on every context switch unless both the new and old
+	 * values are zero.
+	 *
+	 * Note that we don't need to do anything for CS and SS, as
+	 * those are saved and restored as part of pt_regs.
+	 */
+	savesegment(es, prev->es);
+	if (unlikely(next->es | prev->es))
+		loadsegment(es, next->es);
+
+	savesegment(ds, prev->ds);
+	if (unlikely(next->ds | prev->ds))
+		loadsegment(ds, next->ds);
+
 	/*
 	 * Switch FS and GS.
 	 *
-	 * Segment register != 0 always requires a reload.  Also
-	 * reload when it has changed.  When prev process used 64bit
-	 * base always reload to avoid an information leak.
+	 * These are even more complicated than FS and GS: they have
+	 * 64-bit bases are that controlled by arch_prctl.  Those bases
+	 * only differ from the values in the GDT or LDT if the selector
+	 * is 0.
+	 *
+	 * Loading the segment register resets the hidden base part of
+	 * the register to 0 or the value from the GDT / LDT.  If the
+	 * next base address zero, writing 0 to the segment register is
+	 * much faster than using wrmsr to explicitly zero the base.
+	 *
+	 * The thread_struct.fs and thread_struct.gs values are 0
+	 * if the fs and gs bases respectively are not overridden
+	 * from the values implied by fsindex and gsindex.  They
+	 * are nonzero, and store the nonzero base addresses, if
+	 * the bases are overridden.
+	 *
+	 * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should
+	 * be impossible.
+	 *
+	 * Therefore we need to reload the segment registers if either
+	 * the old or new selector is nonzero, and we need to override
+	 * the base address if next thread expects it to be overridden.
+	 *
+	 * This code is unnecessarily slow in the case where the old and
+	 * new indexes are zero and the new base is nonzero -- it will
+	 * unnecessarily write 0 to the selector before writing the new
+	 * base address.
+	 *
+	 * Note: This all depends on arch_prctl being the only way that
+	 * user code can override the segment base.  Once wrfsbase and
+	 * wrgsbase are enabled, most of this code will need to change.
 	 */
 	if (unlikely(fsindex | next->fsindex | prev->fs)) {
 		loadsegment(fs, next->fsindex);
+
 		/*
-		 * Check if the user used a selector != 0; if yes
-		 *  clear 64bit base, since overloaded base is always
-		 *  mapped to the Null selector
+		 * If user code wrote a nonzero value to FS, then it also
+		 * cleared the overridden base address.
+		 *
+		 * XXX: if user code wrote 0 to FS and cleared the base
+		 * address itself, we won't notice and we'll incorrectly
+		 * restore the prior base address next time we reschdule
+		 * the process.
 		 */
 		if (fsindex)
 			prev->fs = 0;
 	}
-	/* when next process has a 64bit base use it */
 	if (next->fs)
 		wrmsrl(MSR_FS_BASE, next->fs);
 	prev->fsindex = fsindex;
 
 	if (unlikely(gsindex | next->gsindex | prev->gs)) {
 		load_gs_index(next->gsindex);
+
+		/* This works (and fails) the same way as fsindex above. */
 		if (gsindex)
 			prev->gs = 0;
 	}
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 17962e667a9..587be13be0b 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -182,6 +182,16 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 		},
 	},
 
+	/* ASRock */
+	{	/* Handle problems with rebooting on ASRock Q1900DC-ITX */
+		.callback = set_pci_reboot,
+		.ident = "ASRock Q1900DC-ITX",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASRock"),
+			DMI_MATCH(DMI_BOARD_NAME, "Q1900DC-ITX"),
+		},
+	},
+
 	/* ASUS */
 	{	/* Handle problems with rebooting on ASUS P4S800 */
 		.callback = set_bios_reboot,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ab08aa2276f..87b6496a32f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1176,7 +1176,7 @@ void __init setup_arch(char **cmdline_p)
 
 	if (boot_cpu_data.cpuid_level >= 0) {
 		/* A CPU has %cr4 if and only if it has CPUID */
-		mmu_cr4_features = read_cr4();
+		mmu_cr4_features = __read_cr4();
 		if (trampoline_cr4_features)
 			*trampoline_cr4_features = mmu_cr4_features;
 	}
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index f7fec09e3e3..7fc5e843f24 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -27,6 +27,58 @@ static int get_free_idx(void)
 	return -ESRCH;
 }
 
+static bool tls_desc_okay(const struct user_desc *info)
+{
+	/*
+	 * For historical reasons (i.e. no one ever documented how any
+	 * of the segmentation APIs work), user programs can and do
+	 * assume that a struct user_desc that's all zeros except for
+	 * entry_number means "no segment at all".  This never actually
+	 * worked.  In fact, up to Linux 3.19, a struct user_desc like
+	 * this would create a 16-bit read-write segment with base and
+	 * limit both equal to zero.
+	 *
+	 * That was close enough to "no segment at all" until we
+	 * hardened this function to disallow 16-bit TLS segments.  Fix
+	 * it up by interpreting these zeroed segments the way that they
+	 * were almost certainly intended to be interpreted.
+	 *
+	 * The correct way to ask for "no segment at all" is to specify
+	 * a user_desc that satisfies LDT_empty.  To keep everything
+	 * working, we accept both.
+	 *
+	 * Note that there's a similar kludge in modify_ldt -- look at
+	 * the distinction between modes 1 and 0x11.
+	 */
+	if (LDT_empty(info) || LDT_zero(info))
+		return true;
+
+	/*
+	 * espfix is required for 16-bit data segments, but espfix
+	 * only works for LDT segments.
+	 */
+	if (!info->seg_32bit)
+		return false;
+
+	/* Only allow data segments in the TLS array. */
+	if (info->contents > 1)
+		return false;
+
+	/*
+	 * Non-present segments with DPL 3 present an interesting attack
+	 * surface.  The kernel should handle such segments correctly,
+	 * but TLS is very difficult to protect in a sandbox, so prevent
+	 * such segments from being created.
+	 *
+	 * If userspace needs to remove a TLS entry, it can still delete
+	 * it outright.
+	 */
+	if (info->seg_not_present)
+		return false;
+
+	return true;
+}
+
 static void set_tls_desc(struct task_struct *p, int idx,
 			 const struct user_desc *info, int n)
 {
@@ -40,7 +92,7 @@ static void set_tls_desc(struct task_struct *p, int idx,
 	cpu = get_cpu();
 
 	while (n-- > 0) {
-		if (LDT_empty(info))
+		if (LDT_empty(info) || LDT_zero(info))
 			desc->a = desc->b = 0;
 		else
 			fill_ldt(desc, info);
@@ -66,6 +118,9 @@ int do_set_thread_area(struct task_struct *p, int idx,
 	if (copy_from_user(&info, u_info, sizeof(info)))
 		return -EFAULT;
 
+	if (!tls_desc_okay(&info))
+		return -EINVAL;
+
 	if (idx == -1)
 		idx = info.entry_number;
 
@@ -192,6 +247,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset,
 {
 	struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES];
 	const struct user_desc *info;
+	int i;
 
 	if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
 	    (pos % sizeof(struct user_desc)) != 0 ||
@@ -205,6 +261,10 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset,
 	else
 		info = infobuf;
 
+	for (i = 0; i < count / sizeof(struct user_desc); i++)
+		if (!tls_desc_okay(info + i))
+			return -EINVAL;
+
 	set_tls_desc(target,
 		     GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)),
 		     info, count / sizeof(struct user_desc));
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index de801f22128..07ab8e9733c 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -387,7 +387,7 @@ NOKPROBE_SYMBOL(do_int3);
  * for scheduling or signal handling. The actual stack switch is done in
  * entry.S
  */
-asmlinkage __visible struct pt_regs *sync_regs(struct pt_regs *eregs)
+asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs)
 {
 	struct pt_regs *regs = eregs;
 	/* Did already sync */
@@ -413,7 +413,7 @@ struct bad_iret_stack {
 	struct pt_regs regs;
 };
 
-asmlinkage __visible
+asmlinkage __visible notrace
 struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
 {
 	/*
@@ -436,6 +436,7 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
 	BUG_ON(!user_mode_vm(&new_stack->regs));
 	return new_stack;
 }
+NOKPROBE_SYMBOL(fixup_bad_iret);
 #endif
 
 /*
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index b7e50bba3bb..505449700e0 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -617,7 +617,7 @@ static unsigned long quick_pit_calibrate(void)
 			goto success;
 		}
 	}
-	pr_err("Fast TSC calibration failed\n");
+	pr_info("Fast TSC calibration failed\n");
 	return 0;
 
 success:
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 4c540c4719d..cdc6cf90307 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -12,6 +12,7 @@
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
 #include <asm/sigframe.h>
+#include <asm/tlbflush.h>
 #include <asm/xcr.h>
 
 /*
@@ -378,7 +379,7 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 		 * thread's fpu state, reconstruct fxstate from the fsave
 		 * header. Sanitize the copied state etc.
 		 */
-		struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+		struct fpu *fpu = &tsk->thread.fpu;
 		struct user_i387_ia32_struct env;
 		int err = 0;
 
@@ -392,14 +393,15 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 		 */
 		drop_fpu(tsk);
 
-		if (__copy_from_user(xsave, buf_fx, state_size) ||
+		if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) ||
 		    __copy_from_user(&env, buf, sizeof(env))) {
+			fpu_finit(fpu);
 			err = -1;
 		} else {
 			sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
-			set_used_math();
 		}
 
+		set_used_math();
 		if (use_eager_fpu()) {
 			preempt_disable();
 			math_state_restore();
@@ -453,7 +455,7 @@ static void prepare_fx_sw_frame(void)
  */
 static inline void xstate_enable(void)
 {
-	set_in_cr4(X86_CR4_OSXSAVE);
+	cr4_set_bits(X86_CR4_OSXSAVE);
 	xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
 }
 
@@ -738,3 +740,4 @@ void *get_xsave_addr(struct xsave_struct *xsave, int xstate)
 
 	return (void *)xsave + xstate_comp_offsets[feature];
 }
+EXPORT_SYMBOL_GPL(get_xsave_addr);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 976e3a57f9e..81c6d541d98 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -16,6 +16,8 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
+#include <asm/i387.h> /* For use_eager_fpu.  Ugh! */
+#include <asm/fpu-internal.h> /* For use_eager_fpu.  Ugh! */
 #include <asm/user.h>
 #include <asm/xsave.h>
 #include "cpuid.h"
@@ -88,6 +90,8 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 			xstate_required_size(vcpu->arch.xcr0);
 	}
 
+	vcpu->arch.eager_fpu = guest_cpuid_has_mpx(vcpu);
+
 	/*
 	 * The existing code assumes virtual address is 48-bit in the canonical
 	 * address checks; exit if it is ever changed.
@@ -319,6 +323,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) |
 		F(ADX) | F(SMAP);
 
+	/* cpuid 0xD.1.eax */
+	const u32 kvm_supported_word10_x86_features =
+		F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1);
+
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
 
@@ -455,13 +463,18 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		entry->eax &= supported;
 		entry->edx &= supported >> 32;
 		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+		if (!supported)
+			break;
+
 		for (idx = 1, i = 1; idx < 64; ++idx) {
 			u64 mask = ((u64)1 << idx);
 			if (*nent >= maxnent)
 				goto out;
 
 			do_cpuid_1_ent(&entry[i], function, idx);
-			if (entry[i].eax == 0 || !(supported & mask))
+			if (idx == 1)
+				entry[i].eax &= kvm_supported_word10_x86_features;
+			else if (entry[i].eax == 0 || !(supported & mask))
 				continue;
 			entry[i].flags |=
 			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 4452eedfaed..9bec2b8cdce 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -111,4 +111,12 @@ static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu)
 	best = kvm_find_cpuid_entry(vcpu, 7, 0);
 	return best && (best->ebx & bit(X86_FEATURE_RTM));
 }
+
+static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->ebx & bit(X86_FEATURE_MPX));
+}
 #endif
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 9f8a2faf504..974e4d98ed2 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2128,7 +2128,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 	/* Outer-privilege level return is not implemented */
 	if (ctxt->mode >= X86EMUL_MODE_PROT16 && (cs & 3) > cpl)
 		return X86EMUL_UNHANDLEABLE;
-	rc = __load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS, 0, false,
+	rc = __load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS, cpl, false,
 				       &new_desc);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
@@ -2345,7 +2345,7 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
 	 * Not recognized on AMD in compat mode (but is recognized in legacy
 	 * mode).
 	 */
-	if ((ctxt->mode == X86EMUL_MODE_PROT32) && (efer & EFER_LMA)
+	if ((ctxt->mode != X86EMUL_MODE_PROT64) && (efer & EFER_LMA)
 	    && !vendor_intel(ctxt))
 		return emulate_ud(ctxt);
 
@@ -2358,25 +2358,13 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
 	setup_syscalls_segments(ctxt, &cs, &ss);
 
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data);
-	switch (ctxt->mode) {
-	case X86EMUL_MODE_PROT32:
-		if ((msr_data & 0xfffc) == 0x0)
-			return emulate_gp(ctxt, 0);
-		break;
-	case X86EMUL_MODE_PROT64:
-		if (msr_data == 0x0)
-			return emulate_gp(ctxt, 0);
-		break;
-	default:
-		break;
-	}
+	if ((msr_data & 0xfffc) == 0x0)
+		return emulate_gp(ctxt, 0);
 
 	ctxt->eflags &= ~(EFLG_VM | EFLG_IF);
-	cs_sel = (u16)msr_data;
-	cs_sel &= ~SELECTOR_RPL_MASK;
+	cs_sel = (u16)msr_data & ~SELECTOR_RPL_MASK;
 	ss_sel = cs_sel + 8;
-	ss_sel &= ~SELECTOR_RPL_MASK;
-	if (ctxt->mode == X86EMUL_MODE_PROT64 || (efer & EFER_LMA)) {
+	if (efer & EFER_LMA) {
 		cs.d = 0;
 		cs.l = 1;
 	}
@@ -2385,10 +2373,11 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
 	ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
 
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_EIP, &msr_data);
-	ctxt->_eip = msr_data;
+	ctxt->_eip = (efer & EFER_LMA) ? msr_data : (u32)msr_data;
 
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_ESP, &msr_data);
-	*reg_write(ctxt, VCPU_REGS_RSP) = msr_data;
+	*reg_write(ctxt, VCPU_REGS_RSP) = (efer & EFER_LMA) ? msr_data :
+							      (u32)msr_data;
 
 	return X86EMUL_CONTINUE;
 }
@@ -3788,8 +3777,8 @@ static const struct opcode group5[] = {
 };
 
 static const struct opcode group6[] = {
-	DI(Prot,	sldt),
-	DI(Prot,	str),
+	DI(Prot | DstMem,	sldt),
+	DI(Prot | DstMem,	str),
 	II(Prot | Priv | SrcMem16, em_lldt, lldt),
 	II(Prot | Priv | SrcMem16, em_ltr, ltr),
 	N, N, N, N,
@@ -4840,7 +4829,8 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 		if (rc != X86EMUL_CONTINUE)
 			goto done;
 	}
-	ctxt->dst.orig_val = ctxt->dst.val;
+	/* Copy full 64-bit value for CMPXCHG8B.  */
+	ctxt->dst.orig_val64 = ctxt->dst.val64;
 
 special_insn:
 
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 298781d4cfb..1406ffde3e3 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -305,7 +305,7 @@ static void pit_do_work(struct kthread_work *work)
 		 * LVT0 to NMI delivery. Other PIC interrupts are just sent to
 		 * VCPU0, and only if its LVT0 is in EXTINT mode.
 		 */
-		if (kvm->arch.vapics_in_nmi_mode > 0)
+		if (atomic_read(&kvm->arch.vapics_in_nmi_mode) > 0)
 			kvm_for_each_vcpu(i, vcpu, kvm)
 				kvm_apic_nmi_wd_deliver(vcpu);
 	}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index b8345dd41b2..de8e5004012 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1112,10 +1112,10 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
 		if (!nmi_wd_enabled) {
 			apic_debug("Receive NMI setting on APIC_LVT0 "
 				   "for cpu %d\n", apic->vcpu->vcpu_id);
-			apic->vcpu->kvm->arch.vapics_in_nmi_mode++;
+			atomic_inc(&apic->vcpu->kvm->arch.vapics_in_nmi_mode);
 		}
 	} else if (nmi_wd_enabled)
-		apic->vcpu->kvm->arch.vapics_in_nmi_mode--;
+		atomic_dec(&apic->vcpu->kvm->arch.vapics_in_nmi_mode);
 }
 
 static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
@@ -1687,6 +1687,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
 
 	apic_update_ppr(apic);
 	hrtimer_cancel(&apic->lapic_timer.timer);
+	apic_manage_nmi_watchdog(apic, kvm_apic_get_reg(apic, APIC_LVT0));
 	update_divide_count(apic);
 	start_apic_timer(apic);
 	apic->irr_pending = true;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 978f402006e..f696dedb0fa 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3625,8 +3625,8 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
 	}
 }
 
-void update_permission_bitmask(struct kvm_vcpu *vcpu,
-		struct kvm_mmu *mmu, bool ept)
+static void update_permission_bitmask(struct kvm_vcpu *vcpu,
+				      struct kvm_mmu *mmu, bool ept)
 {
 	unsigned bit, byte, pfec;
 	u8 map;
@@ -3807,6 +3807,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 {
 	bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+	bool smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
 	ASSERT(vcpu);
 	ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
 
@@ -3824,6 +3825,8 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 	vcpu->arch.mmu.base_role.cr0_wp  = is_write_protection(vcpu);
 	vcpu->arch.mmu.base_role.smep_andnot_wp
 		= smep && !is_write_protection(vcpu);
+	context->base_role.smap_andnot_wp
+		= smap && !is_write_protection(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
 
@@ -4095,12 +4098,18 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 		       const u8 *new, int bytes)
 {
 	gfn_t gfn = gpa >> PAGE_SHIFT;
-	union kvm_mmu_page_role mask = { .word = 0 };
 	struct kvm_mmu_page *sp;
 	LIST_HEAD(invalid_list);
 	u64 entry, gentry, *spte;
 	int npte;
 	bool remote_flush, local_flush, zap_page;
+	union kvm_mmu_page_role mask = { };
+
+	mask.cr0_wp = 1;
+	mask.cr4_pae = 1;
+	mask.nxe = 1;
+	mask.smep_andnot_wp = 1;
+	mask.smap_andnot_wp = 1;
 
 	/*
 	 * If we don't have indirect shadow pages, it means no page is
@@ -4126,7 +4135,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	++vcpu->kvm->stat.mmu_pte_write;
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
 
-	mask.cr0_wp = mask.cr4_pae = mask.nxe = 1;
 	for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
 		if (detect_write_misaligned(sp, gpa, bytes) ||
 		      detect_write_flooding(sp)) {
@@ -4449,7 +4457,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm)
 	 * zap all shadow pages.
 	 */
 	if (unlikely(kvm_current_mmio_generation(kvm) == 0)) {
-		printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n");
+		printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n");
 		kvm_mmu_invalidate_zap_all_pages(kvm);
 	}
 }
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index bde8ee72575..a6b87644330 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -84,8 +84,6 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct);
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
 		bool execonly);
-void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
-		bool ept);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {
@@ -179,6 +177,8 @@ static inline bool permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	int index = (pfec >> 1) +
 		    (smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1));
 
+	WARN_ON(pfec & PFERR_RSVD_MASK);
+
 	return (mmu->permissions[index] >> pte_access) & 1;
 }
 
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index fd49c867b25..6e6d115fe9b 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -718,6 +718,13 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 					      mmu_is_nested(vcpu));
 		if (likely(r != RET_MMIO_PF_INVALID))
 			return r;
+
+		/*
+		 * page fault with PFEC.RSVD  = 1 is caused by shadow
+		 * page fault, should not be used to walk guest page
+		 * table.
+		 */
+		error_code &= ~PFERR_RSVD_MASK;
 	};
 
 	r = mmu_topup_memory_caches(vcpu);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 7527cefc5a4..b83bff87408 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -511,8 +511,10 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (svm->vmcb->control.next_rip != 0)
+	if (svm->vmcb->control.next_rip != 0) {
+		WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS));
 		svm->next_rip = svm->vmcb->control.next_rip;
+	}
 
 	if (!svm->next_rip) {
 		if (emulate_instruction(vcpu, EMULTYPE_SKIP) !=
@@ -1581,7 +1583,7 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 static int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
-	unsigned long host_cr4_mce = read_cr4() & X86_CR4_MCE;
+	unsigned long host_cr4_mce = cr4_read_shadow() & X86_CR4_MCE;
 	unsigned long old_cr4 = to_svm(vcpu)->vmcb->save.cr4;
 
 	if (cr4 & X86_CR4_VMXE)
@@ -4306,7 +4308,9 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu,
 		break;
 	}
 
-	vmcb->control.next_rip  = info->next_rip;
+	/* TODO: Advertise NRIPS to guest hypervisor unconditionally */
+	if (static_cpu_has(X86_FEATURE_NRIPS))
+		vmcb->control.next_rip  = info->next_rip;
 	vmcb->control.exit_code = icpt_info.exit_code;
 	vmexit = nested_svm_exit_handled(svm);
 
@@ -4370,6 +4374,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.cache_reg = svm_cache_reg,
 	.get_rflags = svm_get_rflags,
 	.set_rflags = svm_set_rflags,
+	.fpu_activate = svm_fpu_activate,
 	.fpu_deactivate = svm_fpu_deactivate,
 
 	.tlb_flush = svm_flush_tlb,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3e556c68351..0d7f1dcfcda 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2377,7 +2377,6 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 	nested_vmx_secondary_ctls_low = 0;
 	nested_vmx_secondary_ctls_high &=
 		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
-		SECONDARY_EXEC_UNRESTRICTED_GUEST |
 		SECONDARY_EXEC_WBINVD_EXITING;
 
 	if (enable_ept) {
@@ -2396,6 +2395,10 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 	} else
 		nested_vmx_ept_caps = 0;
 
+	if (enable_unrestricted_guest)
+		nested_vmx_secondary_ctls_high |=
+			SECONDARY_EXEC_UNRESTRICTED_GUEST;
+
 	/* miscellaneous data */
 	rdmsr(MSR_IA32_VMX_MISC, nested_vmx_misc_low, nested_vmx_misc_high);
 	nested_vmx_misc_low &= VMX_MISC_SAVE_EFER_LMA;
@@ -2741,7 +2744,7 @@ static int hardware_enable(void)
 	u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
 	u64 old, test_bits;
 
-	if (read_cr4() & X86_CR4_VMXE)
+	if (cr4_read_shadow() & X86_CR4_VMXE)
 		return -EBUSY;
 
 	INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
@@ -2768,7 +2771,7 @@ static int hardware_enable(void)
 		/* enable and lock */
 		wrmsrl(MSR_IA32_FEATURE_CONTROL, old | test_bits);
 	}
-	write_cr4(read_cr4() | X86_CR4_VMXE); /* FIXME: not cpu hotplug safe */
+	cr4_set_bits(X86_CR4_VMXE);
 
 	if (vmm_exclusive) {
 		kvm_cpu_vmxon(phys_addr);
@@ -2805,7 +2808,7 @@ static void hardware_disable(void)
 		vmclear_local_loaded_vmcss();
 		kvm_cpu_vmxoff();
 	}
-	write_cr4(read_cr4() & ~X86_CR4_VMXE);
+	cr4_clear_bits(X86_CR4_VMXE);
 }
 
 static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt,
@@ -3550,8 +3553,16 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 
 static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
-	unsigned long hw_cr4 = cr4 | (to_vmx(vcpu)->rmode.vm86_active ?
-		    KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON);
+	/*
+	 * Pass through host's Machine Check Enable value to hw_cr4, which
+	 * is in force while we are in guest mode.  Do not let guests control
+	 * this bit, even if host CR4.MCE == 0.
+	 */
+	unsigned long hw_cr4 =
+		(cr4_read_shadow() & X86_CR4_MCE) |
+		(cr4 & ~X86_CR4_MCE) |
+		(to_vmx(vcpu)->rmode.vm86_active ?
+		 KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON);
 
 	if (cr4 & X86_CR4_VMXE) {
 		/*
@@ -4277,7 +4288,7 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 	vmcs_writel(HOST_CR3, read_cr3());  /* 22.2.3  FIXME: shadow tables */
 
 	/* Save the most likely value for this task's CR4 in the VMCS. */
-	cr4 = read_cr4();
+	cr4 = cr4_read_shadow();
 	vmcs_writel(HOST_CR4, cr4);			/* 22.2.3, 22.2.5 */
 	vmx->host_state.vmcs_host_cr4 = cr4;
 
@@ -7560,7 +7571,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
 
-	cr4 = read_cr4();
+	cr4 = cr4_read_shadow();
 	if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) {
 		vmcs_writel(HOST_CR4, cr4);
 		vmx->host_state.vmcs_host_cr4 = cr4;
@@ -9117,6 +9128,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.cache_reg = vmx_cache_reg,
 	.get_rflags = vmx_get_rflags,
 	.set_rflags = vmx_set_rflags,
+	.fpu_activate = vmx_fpu_activate,
 	.fpu_deactivate = vmx_fpu_deactivate,
 
 	.tlb_flush = vmx_flush_tlb,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0033df32a74..0bb431c3f74 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -678,8 +678,9 @@ EXPORT_SYMBOL_GPL(kvm_set_xcr);
 int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	unsigned long old_cr4 = kvm_read_cr4(vcpu);
-	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE |
-				   X86_CR4_PAE | X86_CR4_SMEP;
+	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
+				   X86_CR4_SMEP | X86_CR4_SMAP;
+
 	if (cr4 & CR4_RESERVED_BITS)
 		return 1;
 
@@ -720,9 +721,6 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
 		kvm_mmu_reset_context(vcpu);
 
-	if ((cr4 ^ old_cr4) & X86_CR4_SMAP)
-		update_permission_bitmask(vcpu, vcpu->arch.walk_mmu, false);
-
 	if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE)
 		kvm_update_cpuid(vcpu);
 
@@ -1237,21 +1235,22 @@ void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_X86_64
 	bool vcpus_matched;
-	bool do_request = false;
 	struct kvm_arch *ka = &vcpu->kvm->arch;
 	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 
 	vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 ==
 			 atomic_read(&vcpu->kvm->online_vcpus));
 
-	if (vcpus_matched && gtod->clock.vclock_mode == VCLOCK_TSC)
-		if (!ka->use_master_clock)
-			do_request = 1;
-
-	if (!vcpus_matched && ka->use_master_clock)
-			do_request = 1;
-
-	if (do_request)
+	/*
+	 * Once the masterclock is enabled, always perform request in
+	 * order to update it.
+	 *
+	 * In order to enable masterclock, the host clocksource must be TSC
+	 * and the vcpus need to have matched TSCs.  When that happens,
+	 * perform request to enable masterclock.
+	 */
+	if (ka->use_master_clock ||
+	    (gtod->clock.vclock_mode == VCLOCK_TSC && vcpus_matched))
 		kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 
 	trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc,
@@ -2712,7 +2711,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_USER_NMI:
 	case KVM_CAP_REINJECT_CONTROL:
 	case KVM_CAP_IRQ_INJECT_STATUS:
-	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_IOEVENTFD_NO_LENGTH:
 	case KVM_CAP_PIT2:
@@ -3128,15 +3126,89 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+#define XSTATE_COMPACTION_ENABLED (1ULL << 63)
+
+static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
+{
+	struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
+	u64 xstate_bv = xsave->xsave_hdr.xstate_bv;
+	u64 valid;
+
+	/*
+	 * Copy legacy XSAVE area, to avoid complications with CPUID
+	 * leaves 0 and 1 in the loop below.
+	 */
+	memcpy(dest, xsave, XSAVE_HDR_OFFSET);
+
+	/* Set XSTATE_BV */
+	*(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv;
+
+	/*
+	 * Copy each region from the possibly compacted offset to the
+	 * non-compacted offset.
+	 */
+	valid = xstate_bv & ~XSTATE_FPSSE;
+	while (valid) {
+		u64 feature = valid & -valid;
+		int index = fls64(feature) - 1;
+		void *src = get_xsave_addr(xsave, feature);
+
+		if (src) {
+			u32 size, offset, ecx, edx;
+			cpuid_count(XSTATE_CPUID, index,
+				    &size, &offset, &ecx, &edx);
+			memcpy(dest + offset, src, size);
+		}
+
+		valid -= feature;
+	}
+}
+
+static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
+{
+	struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
+	u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET);
+	u64 valid;
+
+	/*
+	 * Copy legacy XSAVE area, to avoid complications with CPUID
+	 * leaves 0 and 1 in the loop below.
+	 */
+	memcpy(xsave, src, XSAVE_HDR_OFFSET);
+
+	/* Set XSTATE_BV and possibly XCOMP_BV.  */
+	xsave->xsave_hdr.xstate_bv = xstate_bv;
+	if (cpu_has_xsaves)
+		xsave->xsave_hdr.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
+
+	/*
+	 * Copy each region from the non-compacted offset to the
+	 * possibly compacted offset.
+	 */
+	valid = xstate_bv & ~XSTATE_FPSSE;
+	while (valid) {
+		u64 feature = valid & -valid;
+		int index = fls64(feature) - 1;
+		void *dest = get_xsave_addr(xsave, feature);
+
+		if (dest) {
+			u32 size, offset, ecx, edx;
+			cpuid_count(XSTATE_CPUID, index,
+				    &size, &offset, &ecx, &edx);
+			memcpy(dest, src + offset, size);
+		} else
+			WARN_ON_ONCE(1);
+
+		valid -= feature;
+	}
+}
+
 static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 					 struct kvm_xsave *guest_xsave)
 {
 	if (cpu_has_xsave) {
-		memcpy(guest_xsave->region,
-			&vcpu->arch.guest_fpu.state->xsave,
-			vcpu->arch.guest_xstate_size);
-		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] &=
-			vcpu->arch.guest_supported_xcr0 | XSTATE_FPSSE;
+		memset(guest_xsave, 0, sizeof(struct kvm_xsave));
+		fill_xsave((u8 *) guest_xsave->region, vcpu);
 	} else {
 		memcpy(guest_xsave->region,
 			&vcpu->arch.guest_fpu.state->fxsave,
@@ -3160,8 +3232,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 		 */
 		if (xstate_bv & ~kvm_supported_xcr0())
 			return -EINVAL;
-		memcpy(&vcpu->arch.guest_fpu.state->xsave,
-			guest_xsave->region, vcpu->arch.guest_xstate_size);
+		load_xsave(vcpu, (u8 *)guest_xsave->region);
 	} else {
 		if (xstate_bv & ~XSTATE_FPSSE)
 			return -EINVAL;
@@ -5706,7 +5777,6 @@ int kvm_arch_init(void *opaque)
 	kvm_set_mmio_spte_mask();
 
 	kvm_x86_ops = ops;
-	kvm_init_msr_list();
 
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
 			PT_DIRTY_MASK, PT64_NX_MASK, 0);
@@ -6067,6 +6137,8 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 		return;
 
 	page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+	if (is_error_page(page))
+		return;
 	kvm_x86_ops->set_apic_access_page_addr(vcpu, page_to_phys(page));
 
 	/*
@@ -6873,6 +6945,9 @@ int fx_init(struct kvm_vcpu *vcpu)
 		return err;
 
 	fpu_finit(&vcpu->arch.guest_fpu);
+	if (cpu_has_xsaves)
+		vcpu->arch.guest_fpu.state->xsave.xsave_hdr.xcomp_bv =
+			host_xcr0 | XSTATE_COMPACTION_ENABLED;
 
 	/*
 	 * Ensure guest xcr0 is valid for loading
@@ -6918,7 +6993,9 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 	fpu_save_init(&vcpu->arch.guest_fpu);
 	__kernel_fpu_end();
 	++vcpu->stat.fpu_reload;
-	kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
+	if (!vcpu->arch.eager_fpu)
+		kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
+
 	trace_kvm_fpu(0);
 }
 
@@ -6934,11 +7011,21 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 						unsigned int id)
 {
+	struct kvm_vcpu *vcpu;
+
 	if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
 		printk_once(KERN_WARNING
 		"kvm: SMP vm created on host with unstable TSC; "
 		"guest TSC will not be reliable\n");
-	return kvm_x86_ops->vcpu_create(kvm, id);
+
+	vcpu = kvm_x86_ops->vcpu_create(kvm, id);
+
+	/*
+	 * Activate fpu unconditionally in case the guest needs eager FPU.  It will be
+	 * deactivated soon if it doesn't.
+	 */
+	kvm_x86_ops->fpu_activate(vcpu);
+	return vcpu;
 }
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
@@ -7134,7 +7221,14 @@ void kvm_arch_hardware_disable(void)
 
 int kvm_arch_hardware_setup(void)
 {
-	return kvm_x86_ops->hardware_setup();
+	int r;
+
+	r = kvm_x86_ops->hardware_setup();
+	if (r != 0)
+		return r;
+
+	kvm_init_msr_list();
+	return 0;
 }
 
 void kvm_arch_hardware_unsetup(void)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index d973e61e450..6fa245ae52c 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -600,7 +600,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code,
 			printk(nx_warning, from_kuid(&init_user_ns, current_uid()));
 		if (pte && pte_present(*pte) && pte_exec(*pte) &&
 				(pgd_flags(*pgd) & _PAGE_USER) &&
-				(read_cr4() & X86_CR4_SMEP))
+				(__read_cr4() & X86_CR4_SMEP))
 			printk(smep_warning, from_kuid(&init_user_ns, current_uid()));
 	}
 
@@ -844,11 +844,8 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 	  unsigned int fault)
 {
 	struct task_struct *tsk = current;
-	struct mm_struct *mm = tsk->mm;
 	int code = BUS_ADRERR;
 
-	up_read(&mm->mmap_sem);
-
 	/* Kernel mode? Handle exceptions or die: */
 	if (!(error_code & PF_USER)) {
 		no_context(regs, error_code, address, SIGBUS, BUS_ADRERR);
@@ -879,7 +876,6 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 	       unsigned long address, unsigned int fault)
 {
 	if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
-		up_read(&current->mm->mmap_sem);
 		no_context(regs, error_code, address, 0, 0);
 		return;
 	}
@@ -887,14 +883,11 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 	if (fault & VM_FAULT_OOM) {
 		/* Kernel mode? Handle exceptions or die: */
 		if (!(error_code & PF_USER)) {
-			up_read(&current->mm->mmap_sem);
 			no_context(regs, error_code, address,
 				   SIGSEGV, SEGV_MAPERR);
 			return;
 		}
 
-		up_read(&current->mm->mmap_sem);
-
 		/*
 		 * We ran out of memory, call the OOM killer, and return the
 		 * userspace (which will retry the fault, or kill us if we got
@@ -905,6 +898,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
 			     VM_FAULT_HWPOISON_LARGE))
 			do_sigbus(regs, error_code, address, fault);
+		else if (fault & VM_FAULT_SIGSEGV)
+			bad_area_nosemaphore(regs, error_code, address);
 		else
 			BUG();
 	}
@@ -1247,6 +1242,7 @@ good_area:
 		return;
 
 	if (unlikely(fault & VM_FAULT_ERROR)) {
+		up_read(&mm->mmap_sem);
 		mm_fault_error(regs, error_code, address, fault);
 		return;
 	}
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 207d9aef662..448ee8912d9 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -172,7 +172,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		 */
 		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
-		if (unlikely(pmd_large(pmd))) {
+		if (unlikely(pmd_large(pmd) || !pmd_present(pmd))) {
 			/*
 			 * NUMA hinting faults need to be handled in the GUP
 			 * slowpath for accounting purposes and so that they
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 8b977ebf938..9161f764121 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -52,23 +52,17 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
-struct page *
-follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-		pmd_t *pmd, int write)
-{
-	return NULL;
-}
 #else
 
-struct page *
-follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
-{
-	return ERR_PTR(-EINVAL);
-}
-
+/*
+ * pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal
+ * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry.
+ * Otherwise, returns 0.
+ */
 int pmd_huge(pmd_t pmd)
 {
-	return !!(pmd_val(pmd) & _PAGE_PSE);
+	return !pmd_none(pmd) &&
+		(pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT;
 }
 
 int pud_huge(pud_t pud)
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 66dba36f234..0a59a63bcda 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -144,11 +144,11 @@ static void __init probe_page_size_mask(void)
 
 	/* Enable PSE if available */
 	if (cpu_has_pse)
-		set_in_cr4(X86_CR4_PSE);
+		cr4_set_bits_and_update_boot(X86_CR4_PSE);
 
 	/* Enable PGE if available */
 	if (cpu_has_pge) {
-		set_in_cr4(X86_CR4_PGE);
+		cr4_set_bits_and_update_boot(X86_CR4_PGE);
 		__supported_pte_mask |= _PAGE_GLOBAL;
 	}
 }
@@ -687,3 +687,11 @@ void __init zone_sizes_init(void)
 	free_area_init_nodes(max_zone_pfns);
 }
 
+DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
+#ifdef CONFIG_SMP
+	.active_mm = &init_mm,
+	.state = 0,
+#endif
+	.cr4 = ~0UL,	/* fail hard if we screw up cr4 shadow initialization */
+};
+EXPORT_SYMBOL_GPL(cpu_tlbstate);
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 919b91205cd..df4552bd239 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -35,12 +35,12 @@ struct va_alignment __read_mostly va_align = {
 	.flags = -1,
 };
 
-static unsigned int stack_maxrandom_size(void)
+static unsigned long stack_maxrandom_size(void)
 {
-	unsigned int max = 0;
+	unsigned long max = 0;
 	if ((current->flags & PF_RANDOMIZE) &&
 		!(current->personality & ADDR_NO_RANDOMIZE)) {
-		max = ((-1U) & STACK_RND_MASK) << PAGE_SHIFT;
+		max = ((-1UL) & STACK_RND_MASK) << PAGE_SHIFT;
 	}
 
 	return max;
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index ee61c36d64f..3250f2371ae 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -14,9 +14,6 @@
 #include <asm/uv/uv.h>
 #include <linux/debugfs.h>
 
-DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate)
-			= { &init_mm, 0, };
-
 /*
  *	Smarter SMP flushing macros.
  *		c/o Linus Torvalds.
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 3f627345d51..82003a36ad9 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -558,6 +558,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 				if (is_ereg(dst_reg))
 					EMIT1(0x41);
 				EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8);
+
+				/* emit 'movzwl eax, ax' */
+				if (is_ereg(dst_reg))
+					EMIT3(0x45, 0x0F, 0xB7);
+				else
+					EMIT2(0x0F, 0xB7);
+				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
 				break;
 			case 32:
 				/* emit 'bswap eax' to swap lower 4 bytes */
@@ -576,6 +583,27 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			break;
 
 		case BPF_ALU | BPF_END | BPF_FROM_LE:
+			switch (imm32) {
+			case 16:
+				/* emit 'movzwl eax, ax' to zero extend 16-bit
+				 * into 64 bit
+				 */
+				if (is_ereg(dst_reg))
+					EMIT3(0x45, 0x0F, 0xB7);
+				else
+					EMIT2(0x0F, 0xB7);
+				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
+				break;
+			case 32:
+				/* emit 'mov eax, eax' to clear upper 32-bits */
+				if (is_ereg(dst_reg))
+					EMIT1(0x45);
+				EMIT2(0x89, add_2reg(0xC0, dst_reg, dst_reg));
+				break;
+			case 64:
+				/* nop */
+				break;
+			}
 			break;
 
 			/* ST: *(u8*)(dst_reg + off) = imm */
@@ -936,7 +964,12 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
 	}
 	ctx.cleanup_addr = proglen;
 
-	for (pass = 0; pass < 10; pass++) {
+	/* JITed image shrinks with every pass and the loop iterates
+	 * until the image stops shrinking. Very large bpf programs
+	 * may converge on the last pass. In such case do one more
+	 * pass to emit the final image
+	 */
+	for (pass = 0; pass < 10 || image; pass++) {
 		proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
 		if (proglen <= 0) {
 			image = NULL;
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index cfd1b132b8e..a3e94b4108b 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -84,6 +84,17 @@ static const struct dmi_system_id pci_crs_quirks[] __initconst = {
 			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
 		},
 	},
+	/* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/931368 */
+	/* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/1033299 */
+	{
+		.callback = set_use_crs,
+		.ident = "Foxconn K8M890-8237A",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Foxconn"),
+			DMI_MATCH(DMI_BOARD_NAME, "K8M890-8237A"),
+			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
+		},
+	},
 
 	/* Now for the blacklist.. */
 
@@ -124,8 +135,10 @@ void __init pci_acpi_crs_quirks(void)
 {
 	int year;
 
-	if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008)
-		pci_use_crs = false;
+	if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008) {
+		if (iomem_resource.end <= 0xffffffff)
+			pci_use_crs = false;
+	}
 
 	dmi_check_system(pci_crs_quirks);
 
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 7b20bccf364..2fb384724eb 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -448,6 +448,22 @@ static const struct dmi_system_id pciprobe_dmi_table[] __initconst = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "ftServer"),
 		},
 	},
+        {
+                .callback = set_scan_all,
+                .ident = "Stratus/NEC ftServer",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R32"),
+                },
+        },
+        {
+                .callback = set_scan_all,
+                .ident = "Stratus/NEC ftServer",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R31"),
+                },
+        },
 	{}
 };
 
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 37c1435889c..d0583eb61a5 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -216,7 +216,7 @@ static void pcibios_allocate_bridge_resources(struct pci_dev *dev)
 			continue;
 		if (r->parent)	/* Already allocated */
 			continue;
-		if (!r->start || pci_claim_resource(dev, idx) < 0) {
+		if (!r->start || pci_claim_bridge_resource(dev, idx) < 0) {
 			/*
 			 * Something is wrong with the region.
 			 * Invalidate the resource to prevent
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 093f5f4272d..6b3cf7c4e5c 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -452,52 +452,6 @@ int __init pci_xen_hvm_init(void)
 }
 
 #ifdef CONFIG_XEN_DOM0
-static __init void xen_setup_acpi_sci(void)
-{
-	int rc;
-	int trigger, polarity;
-	int gsi = acpi_sci_override_gsi;
-	int irq = -1;
-	int gsi_override = -1;
-
-	if (!gsi)
-		return;
-
-	rc = acpi_get_override_irq(gsi, &trigger, &polarity);
-	if (rc) {
-		printk(KERN_WARNING "xen: acpi_get_override_irq failed for acpi"
-				" sci, rc=%d\n", rc);
-		return;
-	}
-	trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
-	polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
-
-	printk(KERN_INFO "xen: sci override: global_irq=%d trigger=%d "
-			"polarity=%d\n", gsi, trigger, polarity);
-
-	/* Before we bind the GSI to a Linux IRQ, check whether
-	 * we need to override it with bus_irq (IRQ) value. Usually for
-	 * IRQs below IRQ_LEGACY_IRQ this holds IRQ == GSI, as so:
-	 *  ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 9 low level)
-	 * but there are oddballs where the IRQ != GSI:
-	 *  ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 20 low level)
-	 * which ends up being: gsi_to_irq[9] == 20
-	 * (which is what acpi_gsi_to_irq ends up calling when starting the
-	 * the ACPI interpreter and keels over since IRQ 9 has not been
-	 * setup as we had setup IRQ 20 for it).
-	 */
-	if (acpi_gsi_to_irq(gsi, &irq) == 0) {
-		/* Use the provided value if it's valid. */
-		if (irq >= 0)
-			gsi_override = irq;
-	}
-
-	gsi = xen_register_gsi(gsi, gsi_override, trigger, polarity);
-	printk(KERN_INFO "xen: acpi sci %d\n", gsi);
-
-	return;
-}
-
 int __init pci_xen_initial_domain(void)
 {
 	int irq;
@@ -509,7 +463,6 @@ int __init pci_xen_initial_domain(void)
 	x86_msi.msi_mask_irq = xen_nop_msi_mask_irq;
 	x86_msi.msix_mask_irq = xen_nop_msix_mask_irq;
 #endif
-	xen_setup_acpi_sci();
 	__acpi_register_gsi = acpi_register_gsi_xen;
 	/* Pre-allocate legacy irqs */
 	for (irq = 0; irq < nr_legacy_irqs(); irq++) {
diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S
index 5fcda727255..86d0f9e08dd 100644
--- a/arch/x86/platform/efi/efi_stub_64.S
+++ b/arch/x86/platform/efi/efi_stub_64.S
@@ -91,167 +91,6 @@ ENTRY(efi_call)
 	ret
 ENDPROC(efi_call)
 
-#ifdef CONFIG_EFI_MIXED
-
-/*
- * We run this function from the 1:1 mapping.
- *
- * This function must be invoked with a 1:1 mapped stack.
- */
-ENTRY(__efi64_thunk)
-	movl	%ds, %eax
-	push	%rax
-	movl	%es, %eax
-	push	%rax
-	movl	%ss, %eax
-	push	%rax
-
-	subq	$32, %rsp
-	movl	%esi, 0x0(%rsp)
-	movl	%edx, 0x4(%rsp)
-	movl	%ecx, 0x8(%rsp)
-	movq	%r8, %rsi
-	movl	%esi, 0xc(%rsp)
-	movq	%r9, %rsi
-	movl	%esi,  0x10(%rsp)
-
-	sgdt	save_gdt(%rip)
-
-	leaq	1f(%rip), %rbx
-	movq	%rbx, func_rt_ptr(%rip)
-
-	/* Switch to gdt with 32-bit segments */
-	movl	64(%rsp), %eax
-	lgdt	(%rax)
-
-	leaq	efi_enter32(%rip), %rax
-	pushq	$__KERNEL_CS
-	pushq	%rax
-	lretq
-
-1:	addq	$32, %rsp
-
-	lgdt	save_gdt(%rip)
-
-	pop	%rbx
-	movl	%ebx, %ss
-	pop	%rbx
-	movl	%ebx, %es
-	pop	%rbx
-	movl	%ebx, %ds
-
-	/*
-	 * Convert 32-bit status code into 64-bit.
-	 */
-	test	%rax, %rax
-	jz	1f
-	movl	%eax, %ecx
-	andl	$0x0fffffff, %ecx
-	andl	$0xf0000000, %eax
-	shl	$32, %rax
-	or	%rcx, %rax
-1:
-	ret
-ENDPROC(__efi64_thunk)
-
-ENTRY(efi_exit32)
-	movq	func_rt_ptr(%rip), %rax
-	push	%rax
-	mov	%rdi, %rax
-	ret
-ENDPROC(efi_exit32)
-
-	.code32
-/*
- * EFI service pointer must be in %edi.
- *
- * The stack should represent the 32-bit calling convention.
- */
-ENTRY(efi_enter32)
-	movl	$__KERNEL_DS, %eax
-	movl	%eax, %ds
-	movl	%eax, %es
-	movl	%eax, %ss
-
-	/* Reload pgtables */
-	movl	%cr3, %eax
-	movl	%eax, %cr3
-
-	/* Disable paging */
-	movl	%cr0, %eax
-	btrl	$X86_CR0_PG_BIT, %eax
-	movl	%eax, %cr0
-
-	/* Disable long mode via EFER */
-	movl	$MSR_EFER, %ecx
-	rdmsr
-	btrl	$_EFER_LME, %eax
-	wrmsr
-
-	call	*%edi
-
-	/* We must preserve return value */
-	movl	%eax, %edi
-
-	/*
-	 * Some firmware will return with interrupts enabled. Be sure to
-	 * disable them before we switch GDTs.
-	 */
-	cli
-
-	movl	68(%esp), %eax
-	movl	%eax, 2(%eax)
-	lgdtl	(%eax)
-
-	movl	%cr4, %eax
-	btsl	$(X86_CR4_PAE_BIT), %eax
-	movl	%eax, %cr4
-
-	movl	%cr3, %eax
-	movl	%eax, %cr3
-
-	movl	$MSR_EFER, %ecx
-	rdmsr
-	btsl	$_EFER_LME, %eax
-	wrmsr
-
-	xorl	%eax, %eax
-	lldt	%ax
-
-	movl	72(%esp), %eax
-	pushl	$__KERNEL_CS
-	pushl	%eax
-
-	/* Enable paging */
-	movl	%cr0, %eax
-	btsl	$X86_CR0_PG_BIT, %eax
-	movl	%eax, %cr0
-	lret
-ENDPROC(efi_enter32)
-
-	.data
-	.balign	8
-	.global	efi32_boot_gdt
-efi32_boot_gdt:	.word	0
-		.quad	0
-
-save_gdt:	.word	0
-		.quad	0
-func_rt_ptr:	.quad	0
-
-	.global efi_gdt64
-efi_gdt64:
-	.word	efi_gdt64_end - efi_gdt64
-	.long	0			/* Filled out by user */
-	.word	0
-	.quad	0x0000000000000000	/* NULL descriptor */
-	.quad	0x00af9a000000ffff	/* __KERNEL_CS */
-	.quad	0x00cf92000000ffff	/* __KERNEL_DS */
-	.quad	0x0080890000000000	/* TS descriptor */
-	.quad   0x0000000000000000	/* TS continued */
-efi_gdt64_end:
-#endif /* CONFIG_EFI_MIXED */
-
 	.data
 ENTRY(efi_scratch)
 	.fill 3,8,0
diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S
index 8806fa73e6e..ff85d28c50f 100644
--- a/arch/x86/platform/efi/efi_thunk_64.S
+++ b/arch/x86/platform/efi/efi_thunk_64.S
@@ -1,9 +1,26 @@
 /*
  * Copyright (C) 2014 Intel Corporation; author Matt Fleming
+ *
+ * Support for invoking 32-bit EFI runtime services from a 64-bit
+ * kernel.
+ *
+ * The below thunking functions are only used after ExitBootServices()
+ * has been called. This simplifies things considerably as compared with
+ * the early EFI thunking because we can leave all the kernel state
+ * intact (GDT, IDT, etc) and simply invoke the the 32-bit EFI runtime
+ * services from __KERNEL32_CS. This means we can continue to service
+ * interrupts across an EFI mixed mode call.
+ *
+ * We do however, need to handle the fact that we're running in a full
+ * 64-bit virtual address space. Things like the stack and instruction
+ * addresses need to be accessible by the 32-bit firmware, so we rely on
+ * using the identity mappings in the EFI page table to access the stack
+ * and kernel text (see efi_setup_page_tables()).
  */
 
 #include <linux/linkage.h>
 #include <asm/page_types.h>
+#include <asm/segment.h>
 
 	.text
 	.code64
@@ -33,14 +50,6 @@ ENTRY(efi64_thunk)
 	leaq	efi_exit32(%rip), %rbx
 	subq	%rax, %rbx
 	movl	%ebx, 8(%rsp)
-	leaq	efi_gdt64(%rip), %rbx
-	subq	%rax, %rbx
-	movl	%ebx, 2(%ebx)
-	movl	%ebx, 4(%rsp)
-	leaq	efi_gdt32(%rip), %rbx
-	subq	%rax, %rbx
-	movl	%ebx, 2(%ebx)
-	movl	%ebx, (%rsp)
 
 	leaq	__efi64_thunk(%rip), %rbx
 	subq	%rax, %rbx
@@ -52,14 +61,92 @@ ENTRY(efi64_thunk)
 	retq
 ENDPROC(efi64_thunk)
 
-	.data
-efi_gdt32:
-	.word 	efi_gdt32_end - efi_gdt32
-	.long	0			/* Filled out above */
-	.word	0
-	.quad	0x0000000000000000	/* NULL descriptor */
-	.quad	0x00cf9a000000ffff	/* __KERNEL_CS */
-	.quad	0x00cf93000000ffff	/* __KERNEL_DS */
-efi_gdt32_end:
+/*
+ * We run this function from the 1:1 mapping.
+ *
+ * This function must be invoked with a 1:1 mapped stack.
+ */
+ENTRY(__efi64_thunk)
+	movl	%ds, %eax
+	push	%rax
+	movl	%es, %eax
+	push	%rax
+	movl	%ss, %eax
+	push	%rax
+
+	subq	$32, %rsp
+	movl	%esi, 0x0(%rsp)
+	movl	%edx, 0x4(%rsp)
+	movl	%ecx, 0x8(%rsp)
+	movq	%r8, %rsi
+	movl	%esi, 0xc(%rsp)
+	movq	%r9, %rsi
+	movl	%esi,  0x10(%rsp)
+
+	leaq	1f(%rip), %rbx
+	movq	%rbx, func_rt_ptr(%rip)
+
+	/* Switch to 32-bit descriptor */
+	pushq	$__KERNEL32_CS
+	leaq	efi_enter32(%rip), %rax
+	pushq	%rax
+	lretq
+
+1:	addq	$32, %rsp
+
+	pop	%rbx
+	movl	%ebx, %ss
+	pop	%rbx
+	movl	%ebx, %es
+	pop	%rbx
+	movl	%ebx, %ds
 
+	/*
+	 * Convert 32-bit status code into 64-bit.
+	 */
+	test	%rax, %rax
+	jz	1f
+	movl	%eax, %ecx
+	andl	$0x0fffffff, %ecx
+	andl	$0xf0000000, %eax
+	shl	$32, %rax
+	or	%rcx, %rax
+1:
+	ret
+ENDPROC(__efi64_thunk)
+
+ENTRY(efi_exit32)
+	movq	func_rt_ptr(%rip), %rax
+	push	%rax
+	mov	%rdi, %rax
+	ret
+ENDPROC(efi_exit32)
+
+	.code32
+/*
+ * EFI service pointer must be in %edi.
+ *
+ * The stack should represent the 32-bit calling convention.
+ */
+ENTRY(efi_enter32)
+	movl	$__KERNEL_DS, %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	movl	%eax, %ss
+
+	call	*%edi
+
+	/* We must preserve return value */
+	movl	%eax, %edi
+
+	movl	72(%esp), %eax
+	pushl	$__KERNEL_CS
+	pushl	%eax
+
+	lret
+ENDPROC(efi_enter32)
+
+	.data
+	.balign	8
+func_rt_ptr:		.quad 0
 efi_saved_sp:		.quad 0
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 6ec7910f59b..3e32ed5648a 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -105,11 +105,8 @@ static void __save_processor_state(struct saved_context *ctxt)
 	ctxt->cr0 = read_cr0();
 	ctxt->cr2 = read_cr2();
 	ctxt->cr3 = read_cr3();
-#ifdef CONFIG_X86_32
-	ctxt->cr4 = read_cr4_safe();
-#else
-/* CONFIG_X86_64 */
-	ctxt->cr4 = read_cr4();
+	ctxt->cr4 = __read_cr4_safe();
+#ifdef CONFIG_X86_64
 	ctxt->cr8 = read_cr8();
 #endif
 	ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE,
@@ -175,12 +172,12 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	/* cr4 was introduced in the Pentium CPU */
 #ifdef CONFIG_X86_32
 	if (ctxt->cr4)
-		write_cr4(ctxt->cr4);
+		__write_cr4(ctxt->cr4);
 #else
 /* CONFIG X86_64 */
 	wrmsrl(MSR_EFER, ctxt->efer);
 	write_cr8(ctxt->cr8);
-	write_cr4(ctxt->cr4);
+	__write_cr4(ctxt->cr4);
 #endif
 	write_cr3(ctxt->cr3);
 	write_cr2(ctxt->cr2);
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index bad628a620c..0b7a63d9844 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -81,7 +81,7 @@ void __init setup_real_mode(void)
 
 	trampoline_header->start = (u64) secondary_startup_64;
 	trampoline_cr4_features = &trampoline_header->cr4;
-	*trampoline_cr4_features = read_cr4();
+	*trampoline_cr4_features = __read_cr4();
 
 	trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd);
 	trampoline_pgd[0] = init_level4_pgt[pgd_index(__PAGE_OFFSET)].pgd;
diff --git a/arch/x86/tools/calc_run_size.pl b/arch/x86/tools/calc_run_size.pl
deleted file mode 100644
index 23210baade2..00000000000
--- a/arch/x86/tools/calc_run_size.pl
+++ /dev/null
@@ -1,39 +0,0 @@
-#!/usr/bin/perl
-#
-# Calculate the amount of space needed to run the kernel, including room for
-# the .bss and .brk sections.
-#
-# Usage:
-# objdump -h a.out | perl calc_run_size.pl
-use strict;
-
-my $mem_size = 0;
-my $file_offset = 0;
-
-my $sections=" *[0-9]+ \.(?:bss|brk) +";
-while (<>) {
-	if (/^$sections([0-9a-f]+) +(?:[0-9a-f]+ +){2}([0-9a-f]+)/) {
-		my $size = hex($1);
-		my $offset = hex($2);
-		$mem_size += $size;
-		if ($file_offset == 0) {
-			$file_offset = $offset;
-		} elsif ($file_offset != $offset) {
-			# BFD linker shows the same file offset in ELF.
-			# Gold linker shows them as consecutive.
-			next if ($file_offset + $mem_size == $offset + $size);
-
-			printf STDERR "file_offset: 0x%lx\n", $file_offset;
-			printf STDERR "mem_size: 0x%lx\n", $mem_size;
-			printf STDERR "offset: 0x%lx\n", $offset;
-			printf STDERR "size: 0x%lx\n", $size;
-
-			die ".bss and .brk are non-contiguous\n";
-		}
-	}
-}
-
-if ($file_offset == 0) {
-	die "Never found .bss or .brk file offset\n";
-}
-printf("%d\n", $mem_size + $file_offset);
diff --git a/arch/x86/tools/calc_run_size.sh b/arch/x86/tools/calc_run_size.sh
new file mode 100644
index 00000000000..1a4c17bb391
--- /dev/null
+++ b/arch/x86/tools/calc_run_size.sh
@@ -0,0 +1,42 @@
+#!/bin/sh
+#
+# Calculate the amount of space needed to run the kernel, including room for
+# the .bss and .brk sections.
+#
+# Usage:
+# objdump -h a.out | sh calc_run_size.sh
+
+NUM='\([0-9a-fA-F]*[ \t]*\)'
+OUT=$(sed -n 's/^[ \t0-9]*.b[sr][sk][ \t]*'"$NUM$NUM$NUM$NUM"'.*/\1\4/p')
+if [ -z "$OUT" ] ; then
+	echo "Never found .bss or .brk file offset" >&2
+	exit 1
+fi
+
+OUT=$(echo ${OUT# })
+sizeA=$(printf "%d" 0x${OUT%% *})
+OUT=${OUT#* }
+offsetA=$(printf "%d" 0x${OUT%% *})
+OUT=${OUT#* }
+sizeB=$(printf "%d" 0x${OUT%% *})
+OUT=${OUT#* }
+offsetB=$(printf "%d" 0x${OUT%% *})
+
+run_size=$(( $offsetA + $sizeA + $sizeB ))
+
+# BFD linker shows the same file offset in ELF.
+if [ "$offsetA" -ne "$offsetB" ] ; then
+	# Gold linker shows them as consecutive.
+	endB=$(( $offsetB + $sizeB ))
+	if [ "$endB" != "$run_size" ] ; then
+		printf "sizeA: 0x%x\n" $sizeA >&2
+		printf "offsetA: 0x%x\n" $offsetA >&2
+		printf "sizeB: 0x%x\n" $sizeB >&2
+		printf "offsetB: 0x%x\n" $offsetB >&2
+		echo ".bss and .brk are non-contiguous" >&2
+		exit 1
+	fi
+fi
+
+printf "%d\n" $run_size
+exit 0
diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c
index 531d4269e2e..bd16d6c370e 100644
--- a/arch/x86/um/sys_call_table_32.c
+++ b/arch/x86/um/sys_call_table_32.c
@@ -34,7 +34,7 @@ typedef asmlinkage void (*sys_call_ptr_t)(void);
 
 extern asmlinkage void sys_ni_syscall(void);
 
-const sys_call_ptr_t sys_call_table[] __cacheline_aligned = {
+const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
 	/*
 	 * Smells like a compiler bug -- it doesn't work
 	 * when the & below is removed.
diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c
index f2f0723070c..95783087f0d 100644
--- a/arch/x86/um/sys_call_table_64.c
+++ b/arch/x86/um/sys_call_table_64.c
@@ -46,7 +46,7 @@ typedef void (*sys_call_ptr_t)(void);
 
 extern void sys_ni_syscall(void);
 
-const sys_call_ptr_t sys_call_table[] __cacheline_aligned = {
+const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
 	/*
 	 * Smells like a compiler bug -- it doesn't work
 	 * when the & below is removed.
diff --git a/arch/x86/vdso/vdso32/sigreturn.S b/arch/x86/vdso/vdso32/sigreturn.S
index 31776d0efc8..d7ec4e251c0 100644
--- a/arch/x86/vdso/vdso32/sigreturn.S
+++ b/arch/x86/vdso/vdso32/sigreturn.S
@@ -17,6 +17,7 @@
 	.text
 	.globl __kernel_sigreturn
 	.type __kernel_sigreturn,@function
+	nop /* this guy is needed for .LSTARTFDEDLSI1 below (watch for HACK) */
 	ALIGN
 __kernel_sigreturn:
 .LSTART_sigreturn:
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 970463b566c..208c2206df4 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -54,12 +54,17 @@ subsys_initcall(init_vdso);
 
 struct linux_binprm;
 
-/* Put the vdso above the (randomized) stack with another randomized offset.
-   This way there is no hole in the middle of address space.
-   To save memory make sure it is still in the same PTE as the stack top.
-   This doesn't give that many random bits.
-
-   Only used for the 64-bit and x32 vdsos. */
+/*
+ * Put the vdso above the (randomized) stack with another randomized
+ * offset.  This way there is no hole in the middle of address space.
+ * To save memory make sure it is still in the same PTE as the stack
+ * top.  This doesn't give that many random bits.
+ *
+ * Note that this algorithm is imperfect: the distribution of the vdso
+ * start address within a PMD is biased toward the end.
+ *
+ * Only used for the 64-bit and x32 vdsos.
+ */
 static unsigned long vdso_addr(unsigned long start, unsigned len)
 {
 #ifdef CONFIG_X86_32
@@ -67,22 +72,30 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
 #else
 	unsigned long addr, end;
 	unsigned offset;
-	end = (start + PMD_SIZE - 1) & PMD_MASK;
+
+	/*
+	 * Round up the start address.  It can start out unaligned as a result
+	 * of stack start randomization.
+	 */
+	start = PAGE_ALIGN(start);
+
+	/* Round the lowest possible end address up to a PMD boundary. */
+	end = (start + len + PMD_SIZE - 1) & PMD_MASK;
 	if (end >= TASK_SIZE_MAX)
 		end = TASK_SIZE_MAX;
 	end -= len;
-	/* This loses some more bits than a modulo, but is cheaper */
-	offset = get_random_int() & (PTRS_PER_PTE - 1);
-	addr = start + (offset << PAGE_SHIFT);
-	if (addr >= end)
-		addr = end;
+
+	if (end > start) {
+		offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
+		addr = start + (offset << PAGE_SHIFT);
+	} else {
+		addr = start;
+	}
 
 	/*
-	 * page-align it here so that get_unmapped_area doesn't
-	 * align it wrongfully again to the next page. addr can come in 4K
-	 * unaligned here as a result of stack start randomization.
+	 * Forcibly align the final address in case we have a hardware
+	 * issue that requires alignment for performance reasons.
 	 */
-	addr = PAGE_ALIGN(addr);
 	addr = align_vdso_addr(addr);
 
 	return addr;
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index fac5e4f9607..7d67146c3f8 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1483,10 +1483,10 @@ static void xen_pvh_set_cr_flags(int cpu)
 	 * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu_init.
 	*/
 	if (cpu_has_pse)
-		set_in_cr4(X86_CR4_PSE);
+		cr4_set_bits_and_update_boot(X86_CR4_PSE);
 
 	if (cpu_has_pge)
-		set_in_cr4(X86_CR4_PGE);
+		cr4_set_bits_and_update_boot(X86_CR4_PGE);
 }
 
 /*
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 81f57e8c8f1..e28ef29b0b1 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -406,6 +406,66 @@ source "drivers/pcmcia/Kconfig"
 
 source "drivers/pci/hotplug/Kconfig"
 
+config XTFPGA_LCD
+	bool "Enable XTFPGA LCD driver"
+	depends on XTENSA_PLATFORM_XTFPGA
+	default n
+	help
+	  There's a 2x16 LCD on most of XTFPGA boards, kernel may output
+	  progress messages there during bootup/shutdown. It may be useful
+	  during board bringup.
+
+	  If unsure, say N.
+
+config XTFPGA_LCD_BASE_ADDR
+	hex "XTFPGA LCD base address"
+	depends on XTFPGA_LCD
+	default "0x0d0c0000"
+	help
+	  Base address of the LCD controller inside KIO region.
+	  Different boards from XTFPGA family have LCD controller at different
+	  addresses. Please consult prototyping user guide for your board for
+	  the correct address. Wrong address here may lead to hardware lockup.
+
+config XTFPGA_LCD_8BIT_ACCESS
+	bool "Use 8-bit access to XTFPGA LCD"
+	depends on XTFPGA_LCD
+	default n
+	help
+	  LCD may be connected with 4- or 8-bit interface, 8-bit access may
+	  only be used with 8-bit interface. Please consult prototyping user
+	  guide for your board for the correct interface width.
+
+config XTFPGA_LCD
+	bool "Enable XTFPGA LCD driver"
+	depends on XTENSA_PLATFORM_XTFPGA
+	default n
+	help
+	  There's a 2x16 LCD on most of XTFPGA boards, kernel may output
+	  progress messages there during bootup/shutdown. It may be useful
+	  during board bringup.
+
+	  If unsure, say N.
+
+config XTFPGA_LCD_BASE_ADDR
+	hex "XTFPGA LCD base address"
+	depends on XTFPGA_LCD
+	default "0x0d0c0000"
+	help
+	  Base address of the LCD controller inside KIO region.
+	  Different boards from XTFPGA family have LCD controller at different
+	  addresses. Please consult prototyping user guide for your board for
+	  the correct address. Wrong address here may lead to hardware lockup.
+
+config XTFPGA_LCD_8BIT_ACCESS
+	bool "Use 8-bit access to XTFPGA LCD"
+	depends on XTFPGA_LCD
+	default n
+	help
+	  LCD may be connected with 4- or 8-bit interface, 8-bit access may
+	  only be used with 8-bit interface. Please consult prototyping user
+	  guide for your board for the correct interface width.
+
 endmenu
 
 menu "Executable file formats"
diff --git a/arch/xtensa/include/asm/highmem.h b/arch/xtensa/include/asm/highmem.h
index 2c7901edffa..01cef6b4082 100644
--- a/arch/xtensa/include/asm/highmem.h
+++ b/arch/xtensa/include/asm/highmem.h
@@ -25,7 +25,7 @@
 #define PKMAP_NR(virt)		(((virt) - PKMAP_BASE) >> PAGE_SHIFT)
 #define PKMAP_ADDR(nr)		(PKMAP_BASE + ((nr) << PAGE_SHIFT))
 
-#define kmap_prot		PAGE_KERNEL
+#define kmap_prot		PAGE_KERNEL_EXEC
 
 #if DCACHE_WAY_SIZE > PAGE_SIZE
 #define get_pkmap_color get_pkmap_color
diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h
index db5bb72e2f4..62d84657c60 100644
--- a/arch/xtensa/include/uapi/asm/unistd.h
+++ b/arch/xtensa/include/uapi/asm/unistd.h
@@ -715,7 +715,7 @@ __SYSCALL(323, sys_process_vm_writev, 6)
 __SYSCALL(324, sys_name_to_handle_at, 5)
 #define __NR_open_by_handle_at			325
 __SYSCALL(325, sys_open_by_handle_at, 3)
-#define __NR_sync_file_range			326
+#define __NR_sync_file_range2			326
 __SYSCALL(326, sys_sync_file_range2, 6)
 #define __NR_perf_event_open			327
 __SYSCALL(327, sys_perf_event_open, 5)
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index b57c4f91f48..9e3571a6535 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -117,6 +117,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c
index d05f8feeb8d..17b1ef3232e 100644
--- a/arch/xtensa/platforms/iss/network.c
+++ b/arch/xtensa/platforms/iss/network.c
@@ -349,8 +349,8 @@ static void iss_net_timer(unsigned long priv)
 {
 	struct iss_net_private *lp = (struct iss_net_private *)priv;
 
-	spin_lock(&lp->lock);
 	iss_net_poll();
+	spin_lock(&lp->lock);
 	mod_timer(&lp->timer, jiffies + lp->timer_val);
 	spin_unlock(&lp->lock);
 }
@@ -361,7 +361,7 @@ static int iss_net_open(struct net_device *dev)
 	struct iss_net_private *lp = netdev_priv(dev);
 	int err;
 
-	spin_lock(&lp->lock);
+	spin_lock_bh(&lp->lock);
 
 	err = lp->tp.open(lp);
 	if (err < 0)
@@ -376,9 +376,11 @@ static int iss_net_open(struct net_device *dev)
 	while ((err = iss_net_rx(dev)) > 0)
 		;
 
-	spin_lock(&opened_lock);
+	spin_unlock_bh(&lp->lock);
+	spin_lock_bh(&opened_lock);
 	list_add(&lp->opened_list, &opened);
-	spin_unlock(&opened_lock);
+	spin_unlock_bh(&opened_lock);
+	spin_lock_bh(&lp->lock);
 
 	init_timer(&lp->timer);
 	lp->timer_val = ISS_NET_TIMER_VALUE;
@@ -387,7 +389,7 @@ static int iss_net_open(struct net_device *dev)
 	mod_timer(&lp->timer, jiffies + lp->timer_val);
 
 out:
-	spin_unlock(&lp->lock);
+	spin_unlock_bh(&lp->lock);
 	return err;
 }
 
@@ -395,7 +397,7 @@ static int iss_net_close(struct net_device *dev)
 {
 	struct iss_net_private *lp = netdev_priv(dev);
 	netif_stop_queue(dev);
-	spin_lock(&lp->lock);
+	spin_lock_bh(&lp->lock);
 
 	spin_lock(&opened_lock);
 	list_del(&opened);
@@ -405,18 +407,17 @@ static int iss_net_close(struct net_device *dev)
 
 	lp->tp.close(lp);
 
-	spin_unlock(&lp->lock);
+	spin_unlock_bh(&lp->lock);
 	return 0;
 }
 
 static int iss_net_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct iss_net_private *lp = netdev_priv(dev);
-	unsigned long flags;
 	int len;
 
 	netif_stop_queue(dev);
-	spin_lock_irqsave(&lp->lock, flags);
+	spin_lock_bh(&lp->lock);
 
 	len = lp->tp.write(lp, &skb);
 
@@ -438,7 +439,7 @@ static int iss_net_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		pr_err("%s: %s failed(%d)\n", dev->name, __func__, len);
 	}
 
-	spin_unlock_irqrestore(&lp->lock, flags);
+	spin_unlock_bh(&lp->lock);
 
 	dev_kfree_skb(skb);
 	return NETDEV_TX_OK;
@@ -466,9 +467,9 @@ static int iss_net_set_mac(struct net_device *dev, void *addr)
 
 	if (!is_valid_ether_addr(hwaddr->sa_data))
 		return -EADDRNOTAVAIL;
-	spin_lock(&lp->lock);
+	spin_lock_bh(&lp->lock);
 	memcpy(dev->dev_addr, hwaddr->sa_data, ETH_ALEN);
-	spin_unlock(&lp->lock);
+	spin_unlock_bh(&lp->lock);
 	return 0;
 }
 
@@ -520,11 +521,11 @@ static int iss_net_configure(int index, char *init)
 	*lp = (struct iss_net_private) {
 		.device_list		= LIST_HEAD_INIT(lp->device_list),
 		.opened_list		= LIST_HEAD_INIT(lp->opened_list),
-		.lock			= __SPIN_LOCK_UNLOCKED(lp.lock),
 		.dev			= dev,
 		.index			= index,
-		};
+	};
 
+	spin_lock_init(&lp->lock);
 	/*
 	 * If this name ends up conflicting with an existing registered
 	 * netdevice, that is OK, register_netdev{,ice}() will notice this
diff --git a/arch/xtensa/platforms/xtfpga/Makefile b/arch/xtensa/platforms/xtfpga/Makefile
index b9ae206340c..7839d38b233 100644
--- a/arch/xtensa/platforms/xtfpga/Makefile
+++ b/arch/xtensa/platforms/xtfpga/Makefile
@@ -6,4 +6,5 @@
 #
 # Note 2! The CFLAGS definitions are in the main makefile...
 
-obj-y			= setup.o lcd.o
+obj-y			+= setup.o
+obj-$(CONFIG_XTFPGA_LCD) += lcd.o
diff --git a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h
index aeb316b7ff8..e8cc86fbba0 100644
--- a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h
+++ b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h
@@ -40,9 +40,6 @@
 
 /* UART */
 #define DUART16552_PADDR	(XCHAL_KIO_PADDR + 0x0D050020)
-/* LCD instruction and data addresses. */
-#define LCD_INSTR_ADDR		((char *)IOADDR(0x0D040000))
-#define LCD_DATA_ADDR		((char *)IOADDR(0x0D040004))
 
 /* Misc. */
 #define XTFPGA_FPGAREGS_VADDR	IOADDR(0x0D020000)
diff --git a/arch/xtensa/platforms/xtfpga/include/platform/lcd.h b/arch/xtensa/platforms/xtfpga/include/platform/lcd.h
index 0e435645af5..4c8541ed113 100644
--- a/arch/xtensa/platforms/xtfpga/include/platform/lcd.h
+++ b/arch/xtensa/platforms/xtfpga/include/platform/lcd.h
@@ -11,10 +11,25 @@
 #ifndef __XTENSA_XTAVNET_LCD_H
 #define __XTENSA_XTAVNET_LCD_H
 
+#ifdef CONFIG_XTFPGA_LCD
 /* Display string STR at position POS on the LCD. */
 void lcd_disp_at_pos(char *str, unsigned char pos);
 
 /* Shift the contents of the LCD display left or right. */
 void lcd_shiftleft(void);
 void lcd_shiftright(void);
+#else
+static inline void lcd_disp_at_pos(char *str, unsigned char pos)
+{
+}
+
+static inline void lcd_shiftleft(void)
+{
+}
+
+static inline void lcd_shiftright(void)
+{
+}
+#endif
+
 #endif
diff --git a/arch/xtensa/platforms/xtfpga/lcd.c b/arch/xtensa/platforms/xtfpga/lcd.c
index 2872301598d..4dc0c1b43f4 100644
--- a/arch/xtensa/platforms/xtfpga/lcd.c
+++ b/arch/xtensa/platforms/xtfpga/lcd.c
@@ -1,50 +1,63 @@
 /*
- * Driver for the LCD display on the Tensilica LX60 Board.
+ * Driver for the LCD display on the Tensilica XTFPGA board family.
+ * http://www.mytechcorp.com/cfdata/productFile/File1/MOC-16216B-B-A0A04.pdf
  *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
  * Copyright (C) 2001, 2006 Tensilica Inc.
+ * Copyright (C) 2015 Cadence Design Systems Inc.
  */
 
-/*
- *
- * FIXME: this code is from the examples from the LX60 user guide.
- *
- * The lcd_pause function does busy waiting, which is probably not
- * great. Maybe the code could be changed to use kernel timers, or
- * change the hardware to not need to wait.
- */
-
+#include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/io.h>
 
 #include <platform/hardware.h>
 #include <platform/lcd.h>
-#include <linux/delay.h>
 
-#define LCD_PAUSE_ITERATIONS	4000
+/* LCD instruction and data addresses. */
+#define LCD_INSTR_ADDR		((char *)IOADDR(CONFIG_XTFPGA_LCD_BASE_ADDR))
+#define LCD_DATA_ADDR		(LCD_INSTR_ADDR + 4)
+
 #define LCD_CLEAR		0x1
 #define LCD_DISPLAY_ON		0xc
 
 /* 8bit and 2 lines display */
 #define LCD_DISPLAY_MODE8BIT	0x38
+#define LCD_DISPLAY_MODE4BIT	0x28
 #define LCD_DISPLAY_POS		0x80
 #define LCD_SHIFT_LEFT		0x18
 #define LCD_SHIFT_RIGHT		0x1c
 
+static void lcd_put_byte(u8 *addr, u8 data)
+{
+#ifdef CONFIG_XTFPGA_LCD_8BIT_ACCESS
+	ACCESS_ONCE(*addr) = data;
+#else
+	ACCESS_ONCE(*addr) = data & 0xf0;
+	ACCESS_ONCE(*addr) = (data << 4) & 0xf0;
+#endif
+}
+
 static int __init lcd_init(void)
 {
-	*LCD_INSTR_ADDR = LCD_DISPLAY_MODE8BIT;
+	ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT;
 	mdelay(5);
-	*LCD_INSTR_ADDR = LCD_DISPLAY_MODE8BIT;
+	ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT;
 	udelay(200);
-	*LCD_INSTR_ADDR = LCD_DISPLAY_MODE8BIT;
+	ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT;
+	udelay(50);
+#ifndef CONFIG_XTFPGA_LCD_8BIT_ACCESS
+	ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE4BIT;
+	udelay(50);
+	lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_MODE4BIT);
 	udelay(50);
-	*LCD_INSTR_ADDR = LCD_DISPLAY_ON;
+#endif
+	lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_ON);
 	udelay(50);
-	*LCD_INSTR_ADDR = LCD_CLEAR;
+	lcd_put_byte(LCD_INSTR_ADDR, LCD_CLEAR);
 	mdelay(10);
 	lcd_disp_at_pos("XTENSA LINUX", 0);
 	return 0;
@@ -52,10 +65,10 @@ static int __init lcd_init(void)
 
 void lcd_disp_at_pos(char *str, unsigned char pos)
 {
-	*LCD_INSTR_ADDR = LCD_DISPLAY_POS | pos;
+	lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_POS | pos);
 	udelay(100);
 	while (*str != 0) {
-		*LCD_DATA_ADDR = *str;
+		lcd_put_byte(LCD_DATA_ADDR, *str);
 		udelay(200);
 		str++;
 	}
@@ -63,13 +76,13 @@ void lcd_disp_at_pos(char *str, unsigned char pos)
 
 void lcd_shiftleft(void)
 {
-	*LCD_INSTR_ADDR = LCD_SHIFT_LEFT;
+	lcd_put_byte(LCD_INSTR_ADDR, LCD_SHIFT_LEFT);
 	udelay(50);
 }
 
 void lcd_shiftright(void)
 {
-	*LCD_INSTR_ADDR = LCD_SHIFT_RIGHT;
+	lcd_put_byte(LCD_INSTR_ADDR, LCD_SHIFT_RIGHT);
 	udelay(50);
 }
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 0421b53e643..93f9152fc27 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -525,6 +525,9 @@ void blk_cleanup_queue(struct request_queue *q)
 	del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
 	blk_sync_queue(q);
 
+	if (q->mq_ops)
+		blk_mq_free_queue(q);
+
 	spin_lock_irq(lock);
 	if (q->queue_lock != &q->__queue_lock)
 		q->queue_lock = &q->__queue_lock;
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 89b97b5e088..2be75ff7f17 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -609,7 +609,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS)) {
 		struct bio_vec *bprev;
 
-		bprev = &rq->biotail->bi_io_vec[bio->bi_vcnt - 1];
+		bprev = &rq->biotail->bi_io_vec[rq->biotail->bi_vcnt - 1];
 		if (bvec_gap_to_prev(bprev, bio->bi_io_vec[0].bv_offset))
 			return false;
 	}
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index 1065d7c65fa..72e5ed691e3 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -90,7 +90,7 @@ unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set)
 	unsigned int *map;
 
 	/* If cpus are offline, map them to first hctx */
-	map = kzalloc_node(sizeof(*map) * num_possible_cpus(), GFP_KERNEL,
+	map = kzalloc_node(sizeof(*map) * nr_cpu_ids, GFP_KERNEL,
 				set->numa_node);
 	if (!map)
 		return NULL;
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 371d8800b48..1630a20d5dc 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -390,16 +390,15 @@ static void blk_mq_sysfs_init(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
-	int i, j;
+	int i;
 
 	kobject_init(&q->mq_kobj, &blk_mq_ktype);
 
-	queue_for_each_hw_ctx(q, hctx, i) {
+	queue_for_each_hw_ctx(q, hctx, i)
 		kobject_init(&hctx->kobj, &blk_mq_hw_ktype);
 
-		hctx_for_each_ctx(hctx, ctx, j)
-			kobject_init(&ctx->kobj, &blk_mq_ctx_ktype);
-	}
+	queue_for_each_ctx(q, ctx, i)
+		kobject_init(&ctx->kobj, &blk_mq_ctx_ktype);
 }
 
 /* see blk_register_queue() */
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 8317175a300..702ae29b8d9 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -137,6 +137,7 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 static int __bt_get_word(struct blk_align_bitmap *bm, unsigned int last_tag)
 {
 	int tag, org_last_tag, end;
+	bool wrap = last_tag != 0;
 
 	org_last_tag = last_tag;
 	end = bm->depth;
@@ -148,15 +149,16 @@ restart:
 			 * We started with an offset, start from 0 to
 			 * exhaust the map.
 			 */
-			if (org_last_tag && last_tag) {
-				end = last_tag;
+			if (wrap) {
+				wrap = false;
+				end = org_last_tag;
 				last_tag = 0;
 				goto restart;
 			}
 			return -1;
 		}
 		last_tag = tag + 1;
-	} while (test_and_set_bit_lock(tag, &bm->word));
+	} while (test_and_set_bit(tag, &bm->word));
 
 	return tag;
 }
@@ -340,11 +342,10 @@ static void bt_clear_tag(struct blk_mq_bitmap_tags *bt, unsigned int tag)
 	struct bt_wait_state *bs;
 	int wait_cnt;
 
-	/*
-	 * The unlock memory barrier need to order access to req in free
-	 * path and clearing tag bit
-	 */
-	clear_bit_unlock(TAG_TO_BIT(bt, tag), &bt->map[index].word);
+	clear_bit(TAG_TO_BIT(bt, tag), &bt->map[index].word);
+
+	/* Ensure that the wait list checks occur after clear_bit(). */
+	smp_mb();
 
 	bs = bt_wake_ptr(bt);
 	if (!bs)
@@ -499,6 +500,7 @@ static int bt_alloc(struct blk_mq_bitmap_tags *bt, unsigned int depth,
 	bt->bs = kzalloc(BT_WAIT_QUEUES * sizeof(*bt->bs), GFP_KERNEL);
 	if (!bt->bs) {
 		kfree(bt->map);
+		bt->map = NULL;
 		return -ENOMEM;
 	}
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1d016fc9a8b..691959ecb80 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1473,22 +1473,6 @@ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu)
 	return NOTIFY_OK;
 }
 
-static int blk_mq_hctx_cpu_online(struct blk_mq_hw_ctx *hctx, int cpu)
-{
-	struct request_queue *q = hctx->queue;
-	struct blk_mq_tag_set *set = q->tag_set;
-
-	if (set->tags[hctx->queue_num])
-		return NOTIFY_OK;
-
-	set->tags[hctx->queue_num] = blk_mq_init_rq_map(set, hctx->queue_num);
-	if (!set->tags[hctx->queue_num])
-		return NOTIFY_STOP;
-
-	hctx->tags = set->tags[hctx->queue_num];
-	return NOTIFY_OK;
-}
-
 static int blk_mq_hctx_notify(void *data, unsigned long action,
 			      unsigned int cpu)
 {
@@ -1496,8 +1480,11 @@ static int blk_mq_hctx_notify(void *data, unsigned long action,
 
 	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN)
 		return blk_mq_hctx_cpu_offline(hctx, cpu);
-	else if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
-		return blk_mq_hctx_cpu_online(hctx, cpu);
+
+	/*
+	 * In case of CPU online, tags may be reallocated
+	 * in blk_mq_map_swqueue() after mapping is updated.
+	 */
 
 	return NOTIFY_OK;
 }
@@ -1682,6 +1669,7 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	unsigned int i;
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
+	struct blk_mq_tag_set *set = q->tag_set;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		cpumask_clear(hctx->cpumask);
@@ -1708,16 +1696,20 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 		 * disable it and free the request entries.
 		 */
 		if (!hctx->nr_ctx) {
-			struct blk_mq_tag_set *set = q->tag_set;
-
 			if (set->tags[i]) {
 				blk_mq_free_rq_map(set, set->tags[i], i);
 				set->tags[i] = NULL;
-				hctx->tags = NULL;
 			}
+			hctx->tags = NULL;
 			continue;
 		}
 
+		/* unmapped hw queue can be remapped after CPU topo changed */
+		if (!set->tags[i])
+			set->tags[i] = blk_mq_init_rq_map(set, i);
+		hctx->tags = set->tags[i];
+		WARN_ON(!hctx->tags);
+
 		/*
 		 * Initialize batch roundrobin counts
 		 */
@@ -1831,7 +1823,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 	 */
 	if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release,
 			    PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
-		goto err_map;
+		goto err_mq_usage;
 
 	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
 	blk_queue_rq_timeout(q, 30000);
@@ -1874,7 +1866,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
 
 	if (blk_mq_init_hw_queues(q, set))
-		goto err_hw;
+		goto err_mq_usage;
 
 	mutex_lock(&all_q_mutex);
 	list_add_tail(&q->all_q_node, &all_q_list);
@@ -1886,7 +1878,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 
 	return q;
 
-err_hw:
+err_mq_usage:
 	blk_cleanup_queue(q);
 err_hctxs:
 	kfree(map);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 1fac4340891..935ea2aa073 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -492,17 +492,15 @@ static void blk_free_queue_rcu(struct rcu_head *rcu_head)
  *     Currently, its primary task it to free all the &struct request
  *     structures that were allocated to the queue and the queue itself.
  *
- * Caveat:
- *     Hopefully the low level driver will have finished any
- *     outstanding requests first...
+ * Note:
+ *     The low level driver must have finished any outstanding requests first
+ *     via blk_cleanup_queue().
  **/
 static void blk_release_queue(struct kobject *kobj)
 {
 	struct request_queue *q =
 		container_of(kobj, struct request_queue, kobj);
 
-	blk_sync_queue(q);
-
 	blkcg_exit_queue(q);
 
 	if (q->elevator) {
@@ -517,9 +515,7 @@ static void blk_release_queue(struct kobject *kobj)
 	if (q->queue_tags)
 		__blk_queue_free_tags(q);
 
-	if (q->mq_ops)
-		blk_mq_free_queue(q);
-	else
+	if (!q->mq_ops)
 		blk_free_flush_queue(q->fq);
 
 	blk_trace_shutdown(q);
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 9273d0969eb..5b9c6d5c363 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1292,6 +1292,9 @@ static u64 tg_prfill_cpu_rwstat(struct seq_file *sf,
 	struct blkg_rwstat rwstat = { }, tmp;
 	int i, cpu;
 
+	if (tg->stats_cpu == NULL)
+		return 0;
+
 	for_each_possible_cpu(cpu) {
 		struct tg_stats_cpu *sc = per_cpu_ptr(tg->stats_cpu, cpu);
 
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 6f2751d305d..5da8e6e9ab4 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -3590,6 +3590,11 @@ retry:
 
 	blkcg = bio_blkcg(bio);
 	cfqg = cfq_lookup_create_cfqg(cfqd, blkcg);
+	if (!cfqg) {
+		cfqq = &cfqd->oom_cfqq;
+		goto out;
+	}
+
 	cfqq = cic_to_cfqq(cic, is_sync);
 
 	/*
@@ -3626,7 +3631,7 @@ retry:
 		} else
 			cfqq = &cfqd->oom_cfqq;
 	}
-
+out:
 	if (new_cfqq)
 		kmem_cache_free(cfq_pool, new_cfqq);
 
@@ -3656,12 +3661,17 @@ static struct cfq_queue *
 cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic,
 	      struct bio *bio, gfp_t gfp_mask)
 {
-	const int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio);
-	const int ioprio = IOPRIO_PRIO_DATA(cic->ioprio);
+	int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio);
+	int ioprio = IOPRIO_PRIO_DATA(cic->ioprio);
 	struct cfq_queue **async_cfqq = NULL;
 	struct cfq_queue *cfqq = NULL;
 
 	if (!is_sync) {
+		if (!ioprio_valid(cic->ioprio)) {
+			struct task_struct *tsk = current;
+			ioprio = task_nice_ioprio(tsk);
+			ioprio_class = task_nice_ioclass(tsk);
+		}
 		async_cfqq = cfq_async_queue_prio(cfqd, ioprio_class, ioprio);
 		cfqq = *async_cfqq;
 	}
diff --git a/block/genhd.c b/block/genhd.c
index bd3060684ab..c675ad1ad69 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -422,9 +422,9 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
 	/* allocate ext devt */
 	idr_preload(GFP_KERNEL);
 
-	spin_lock(&ext_devt_lock);
+	spin_lock_bh(&ext_devt_lock);
 	idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_NOWAIT);
-	spin_unlock(&ext_devt_lock);
+	spin_unlock_bh(&ext_devt_lock);
 
 	idr_preload_end();
 	if (idx < 0)
@@ -449,9 +449,9 @@ void blk_free_devt(dev_t devt)
 		return;
 
 	if (MAJOR(devt) == BLOCK_EXT_MAJOR) {
-		spin_lock(&ext_devt_lock);
+		spin_lock_bh(&ext_devt_lock);
 		idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
-		spin_unlock(&ext_devt_lock);
+		spin_unlock_bh(&ext_devt_lock);
 	}
 }
 
@@ -691,13 +691,13 @@ struct gendisk *get_gendisk(dev_t devt, int *partno)
 	} else {
 		struct hd_struct *part;
 
-		spin_lock(&ext_devt_lock);
+		spin_lock_bh(&ext_devt_lock);
 		part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
 		if (part && get_disk(part_to_disk(part))) {
 			*partno = part->partno;
 			disk = part_to_disk(part);
 		}
-		spin_unlock(&ext_devt_lock);
+		spin_unlock_bh(&ext_devt_lock);
 	}
 
 	return disk;
@@ -1070,9 +1070,16 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno)
 	struct disk_part_tbl *old_ptbl = disk->part_tbl;
 	struct disk_part_tbl *new_ptbl;
 	int len = old_ptbl ? old_ptbl->len : 0;
-	int target = partno + 1;
+	int i, target;
 	size_t size;
-	int i;
+
+	/*
+	 * check for int overflow, since we can get here from blkpg_ioctl()
+	 * with a user passed 'partno'.
+	 */
+	target = partno + 1;
+	if (target < 0)
+		return -EINVAL;
 
 	/* disk_max_parts() is zero during initialization, ignore if so */
 	if (disk_max_parts(disk) && target > disk_max_parts(disk))
@@ -1109,6 +1116,22 @@ static void disk_release(struct device *dev)
 		blk_put_queue(disk->queue);
 	kfree(disk);
 }
+
+static int disk_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	struct disk_part_iter piter;
+	struct hd_struct *part;
+	int cnt = 0;
+
+	disk_part_iter_init(&piter, disk, 0);
+	while((part = disk_part_iter_next(&piter)))
+		cnt++;
+	disk_part_iter_exit(&piter);
+	add_uevent_var(env, "NPARTS=%u", cnt);
+	return 0;
+}
+
 struct class block_class = {
 	.name		= "block",
 };
@@ -1128,6 +1151,7 @@ static struct device_type disk_type = {
 	.groups		= disk_attr_groups,
 	.release	= disk_release,
 	.devnode	= block_devnode,
+	.uevent		= disk_uevent,
 };
 
 #ifdef CONFIG_PROC_FS
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 0d9e5f97f0a..47284e71265 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -217,10 +217,21 @@ static void part_release(struct device *dev)
 	kfree(p);
 }
 
+static int part_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	struct hd_struct *part = dev_to_part(dev);
+
+	add_uevent_var(env, "PARTN=%u", part->partno);
+	if (part->info && part->info->volname[0])
+		add_uevent_var(env, "PARTNAME=%s", part->info->volname);
+	return 0;
+}
+
 struct device_type part_type = {
 	.name		= "partition",
 	.groups		= part_attr_groups,
 	.release	= part_release,
+	.uevent		= part_uevent,
 };
 
 static void delete_partition_rcu_cb(struct rcu_head *head)
diff --git a/crypto/842.c b/crypto/842.c
index 65c7a89cfa0..b48f4f108c4 100644
--- a/crypto/842.c
+++ b/crypto/842.c
@@ -180,3 +180,4 @@ module_exit(nx842_mod_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("842 Compression Algorithm");
+MODULE_ALIAS_CRYPTO("842");
diff --git a/crypto/aes_generic.c b/crypto/aes_generic.c
index fd0d6b45497..3dd101144a5 100644
--- a/crypto/aes_generic.c
+++ b/crypto/aes_generic.c
@@ -1474,4 +1474,5 @@ module_exit(aes_fini);
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
+MODULE_ALIAS_CRYPTO("aes-generic");
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 6a3ad801158..1de4beeb25f 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -449,6 +449,9 @@ void af_alg_complete(struct crypto_async_request *req, int err)
 {
 	struct af_alg_completion *completion = req->data;
 
+	if (err == -EINPROGRESS)
+		return;
+
 	completion->err = err;
 	complete(&completion->completion);
 }
diff --git a/crypto/algapi.c b/crypto/algapi.c
index e8d3a7dca8c..71a8143e23b 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -509,8 +509,8 @@ static struct crypto_template *__crypto_lookup_template(const char *name)
 
 struct crypto_template *crypto_lookup_template(const char *name)
 {
-	return try_then_request_module(__crypto_lookup_template(name), "%s",
-				       name);
+	return try_then_request_module(__crypto_lookup_template(name),
+				       "crypto-%s", name);
 }
 EXPORT_SYMBOL_GPL(crypto_lookup_template);
 
diff --git a/crypto/ansi_cprng.c b/crypto/ansi_cprng.c
index 666f1962a16..6f5bebc9bf0 100644
--- a/crypto/ansi_cprng.c
+++ b/crypto/ansi_cprng.c
@@ -476,4 +476,5 @@ module_param(dbg, int, 0);
 MODULE_PARM_DESC(dbg, "Boolean to enable debugging (0/1 == off/on)");
 module_init(prng_mod_init);
 module_exit(prng_mod_fini);
-MODULE_ALIAS("stdrng");
+MODULE_ALIAS_CRYPTO("stdrng");
+MODULE_ALIAS_CRYPTO("ansi_cprng");
diff --git a/crypto/anubis.c b/crypto/anubis.c
index 008c8a4fb67..4bb187c2a90 100644
--- a/crypto/anubis.c
+++ b/crypto/anubis.c
@@ -704,3 +704,4 @@ module_exit(anubis_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Anubis Cryptographic Algorithm");
+MODULE_ALIAS_CRYPTO("anubis");
diff --git a/crypto/api.c b/crypto/api.c
index a2b39c5f364..2a81e98a002 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -216,11 +216,11 @@ struct crypto_alg *crypto_larval_lookup(const char *name, u32 type, u32 mask)
 
 	alg = crypto_alg_lookup(name, type, mask);
 	if (!alg) {
-		request_module("%s", name);
+		request_module("crypto-%s", name);
 
 		if (!((type ^ CRYPTO_ALG_NEED_FALLBACK) & mask &
 		      CRYPTO_ALG_NEED_FALLBACK))
-			request_module("%s-all", name);
+			request_module("crypto-%s-all", name);
 
 		alg = crypto_alg_lookup(name, type, mask);
 	}
diff --git a/crypto/arc4.c b/crypto/arc4.c
index 5a772c3657d..f1a81925558 100644
--- a/crypto/arc4.c
+++ b/crypto/arc4.c
@@ -166,3 +166,4 @@ module_exit(arc4_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("ARC4 Cipher Algorithm");
 MODULE_AUTHOR("Jon Oberheide <jon@oberheide.org>");
+MODULE_ALIAS_CRYPTO("arc4");
diff --git a/crypto/asymmetric_keys/asymmetric_keys.h b/crypto/asymmetric_keys/asymmetric_keys.h
index f97330886d5..3f5b537ab33 100644
--- a/crypto/asymmetric_keys/asymmetric_keys.h
+++ b/crypto/asymmetric_keys/asymmetric_keys.h
@@ -11,6 +11,9 @@
 
 extern struct asymmetric_key_id *asymmetric_key_hex_to_key_id(const char *id);
 
+extern int __asymmetric_key_hex_to_key_id(const char *id,
+					  struct asymmetric_key_id *match_id,
+					  size_t hexlen);
 static inline
 const struct asymmetric_key_ids *asymmetric_key_ids(const struct key *key)
 {
diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c
index bcbbbd794e1..b0e4ed23d66 100644
--- a/crypto/asymmetric_keys/asymmetric_type.c
+++ b/crypto/asymmetric_keys/asymmetric_type.c
@@ -104,6 +104,15 @@ static bool asymmetric_match_key_ids(
 	return false;
 }
 
+/* helper function can be called directly with pre-allocated memory */
+inline int __asymmetric_key_hex_to_key_id(const char *id,
+				   struct asymmetric_key_id *match_id,
+				   size_t hexlen)
+{
+	match_id->len = hexlen;
+	return hex2bin(match_id->data, id, hexlen);
+}
+
 /**
  * asymmetric_key_hex_to_key_id - Convert a hex string into a key ID.
  * @id: The ID as a hex string.
@@ -111,21 +120,20 @@ static bool asymmetric_match_key_ids(
 struct asymmetric_key_id *asymmetric_key_hex_to_key_id(const char *id)
 {
 	struct asymmetric_key_id *match_id;
-	size_t hexlen;
+	size_t asciihexlen;
 	int ret;
 
 	if (!*id)
 		return ERR_PTR(-EINVAL);
-	hexlen = strlen(id);
-	if (hexlen & 1)
+	asciihexlen = strlen(id);
+	if (asciihexlen & 1)
 		return ERR_PTR(-EINVAL);
 
-	match_id = kmalloc(sizeof(struct asymmetric_key_id) + hexlen / 2,
+	match_id = kmalloc(sizeof(struct asymmetric_key_id) + asciihexlen / 2,
 			   GFP_KERNEL);
 	if (!match_id)
 		return ERR_PTR(-ENOMEM);
-	match_id->len = hexlen / 2;
-	ret = hex2bin(match_id->data, id, hexlen / 2);
+	ret = __asymmetric_key_hex_to_key_id(id, match_id, asciihexlen / 2);
 	if (ret < 0) {
 		kfree(match_id);
 		return ERR_PTR(-EINVAL);
diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c
index a6c42031628..24f17e6c590 100644
--- a/crypto/asymmetric_keys/x509_public_key.c
+++ b/crypto/asymmetric_keys/x509_public_key.c
@@ -28,17 +28,30 @@ static bool use_builtin_keys;
 static struct asymmetric_key_id *ca_keyid;
 
 #ifndef MODULE
+static struct {
+	struct asymmetric_key_id id;
+	unsigned char data[10];
+} cakey;
+
 static int __init ca_keys_setup(char *str)
 {
 	if (!str)		/* default system keyring */
 		return 1;
 
 	if (strncmp(str, "id:", 3) == 0) {
-		struct asymmetric_key_id *p;
-		p = asymmetric_key_hex_to_key_id(str + 3);
-		if (p == ERR_PTR(-EINVAL))
-			pr_err("Unparsable hex string in ca_keys\n");
-		else if (!IS_ERR(p))
+		struct asymmetric_key_id *p = &cakey.id;
+		size_t hexlen = (strlen(str) - 3) / 2;
+		int ret;
+
+		if (hexlen == 0 || hexlen > sizeof(cakey.data)) {
+			pr_err("Missing or invalid ca_keys id\n");
+			return 1;
+		}
+
+		ret = __asymmetric_key_hex_to_key_id(str + 3, p, hexlen);
+		if (ret < 0)
+			pr_err("Unparsable ca_keys id hex string\n");
+		else
 			ca_keyid = p;	/* owner key 'id:xxxxxx' */
 	} else if (strcmp(str, "builtin") == 0) {
 		use_builtin_keys = true;
diff --git a/crypto/authenc.c b/crypto/authenc.c
index e1223559d5d..78fb16cab13 100644
--- a/crypto/authenc.c
+++ b/crypto/authenc.c
@@ -721,3 +721,4 @@ module_exit(crypto_authenc_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Simple AEAD wrapper for IPsec");
+MODULE_ALIAS_CRYPTO("authenc");
diff --git a/crypto/authencesn.c b/crypto/authencesn.c
index 4be0dd4373a..024bff2344f 100644
--- a/crypto/authencesn.c
+++ b/crypto/authencesn.c
@@ -814,3 +814,4 @@ module_exit(crypto_authenc_esn_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>");
 MODULE_DESCRIPTION("AEAD wrapper for IPsec with extended sequence numbers");
+MODULE_ALIAS_CRYPTO("authencesn");
diff --git a/crypto/blowfish_generic.c b/crypto/blowfish_generic.c
index 8baf5447d35..87b392a77a9 100644
--- a/crypto/blowfish_generic.c
+++ b/crypto/blowfish_generic.c
@@ -138,4 +138,5 @@ module_exit(blowfish_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Blowfish Cipher Algorithm");
-MODULE_ALIAS("blowfish");
+MODULE_ALIAS_CRYPTO("blowfish");
+MODULE_ALIAS_CRYPTO("blowfish-generic");
diff --git a/crypto/camellia_generic.c b/crypto/camellia_generic.c
index 26bcd7a2d6b..a02286bf319 100644
--- a/crypto/camellia_generic.c
+++ b/crypto/camellia_generic.c
@@ -1098,4 +1098,5 @@ module_exit(camellia_fini);
 
 MODULE_DESCRIPTION("Camellia Cipher Algorithm");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("camellia");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-generic");
diff --git a/crypto/cast5_generic.c b/crypto/cast5_generic.c
index 5558f630a0e..df5c7262938 100644
--- a/crypto/cast5_generic.c
+++ b/crypto/cast5_generic.c
@@ -549,4 +549,5 @@ module_exit(cast5_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Cast5 Cipher Algorithm");
-MODULE_ALIAS("cast5");
+MODULE_ALIAS_CRYPTO("cast5");
+MODULE_ALIAS_CRYPTO("cast5-generic");
diff --git a/crypto/cast6_generic.c b/crypto/cast6_generic.c
index de732528a43..058c8d755d0 100644
--- a/crypto/cast6_generic.c
+++ b/crypto/cast6_generic.c
@@ -291,4 +291,5 @@ module_exit(cast6_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Cast6 Cipher Algorithm");
-MODULE_ALIAS("cast6");
+MODULE_ALIAS_CRYPTO("cast6");
+MODULE_ALIAS_CRYPTO("cast6-generic");
diff --git a/crypto/cbc.c b/crypto/cbc.c
index 61ac42e1e32..780ee27b2d4 100644
--- a/crypto/cbc.c
+++ b/crypto/cbc.c
@@ -289,3 +289,4 @@ module_exit(crypto_cbc_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("CBC block cipher algorithm");
+MODULE_ALIAS_CRYPTO("cbc");
diff --git a/crypto/ccm.c b/crypto/ccm.c
index 1df84217f7c..003bbbd21a2 100644
--- a/crypto/ccm.c
+++ b/crypto/ccm.c
@@ -879,5 +879,6 @@ module_exit(crypto_ccm_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Counter with CBC MAC");
-MODULE_ALIAS("ccm_base");
-MODULE_ALIAS("rfc4309");
+MODULE_ALIAS_CRYPTO("ccm_base");
+MODULE_ALIAS_CRYPTO("rfc4309");
+MODULE_ALIAS_CRYPTO("ccm");
diff --git a/crypto/chainiv.c b/crypto/chainiv.c
index 9c294c8f9a0..63c17d5992f 100644
--- a/crypto/chainiv.c
+++ b/crypto/chainiv.c
@@ -359,3 +359,4 @@ module_exit(chainiv_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Chain IV Generator");
+MODULE_ALIAS_CRYPTO("chainiv");
diff --git a/crypto/cmac.c b/crypto/cmac.c
index 50880cf17fa..7a8bfbd548f 100644
--- a/crypto/cmac.c
+++ b/crypto/cmac.c
@@ -313,3 +313,4 @@ module_exit(crypto_cmac_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("CMAC keyed hash algorithm");
+MODULE_ALIAS_CRYPTO("cmac");
diff --git a/crypto/crc32.c b/crypto/crc32.c
index 9d1c4156989..187ded28cb0 100644
--- a/crypto/crc32.c
+++ b/crypto/crc32.c
@@ -156,3 +156,4 @@ module_exit(crc32_mod_fini);
 MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>");
 MODULE_DESCRIPTION("CRC32 calculations wrapper for lib/crc32");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("crc32");
diff --git a/crypto/crc32c_generic.c b/crypto/crc32c_generic.c
index d9c7beba8e5..06f1b60f02b 100644
--- a/crypto/crc32c_generic.c
+++ b/crypto/crc32c_generic.c
@@ -170,5 +170,6 @@ module_exit(crc32c_mod_fini);
 MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>");
 MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations wrapper for lib/crc32c");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c-generic");
 MODULE_SOFTDEP("pre: crc32c");
diff --git a/crypto/crct10dif_generic.c b/crypto/crct10dif_generic.c
index 877e7114ec5..c1229614c7e 100644
--- a/crypto/crct10dif_generic.c
+++ b/crypto/crct10dif_generic.c
@@ -124,4 +124,5 @@ module_exit(crct10dif_mod_fini);
 MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>");
 MODULE_DESCRIPTION("T10 DIF CRC calculation.");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("crct10dif");
+MODULE_ALIAS_CRYPTO("crct10dif");
+MODULE_ALIAS_CRYPTO("crct10dif-generic");
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index e592c90abeb..650afac10fd 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -955,3 +955,4 @@ module_exit(cryptd_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Software async crypto daemon");
+MODULE_ALIAS_CRYPTO("cryptd");
diff --git a/crypto/crypto_null.c b/crypto/crypto_null.c
index 1dc54bb95a8..a20319132e3 100644
--- a/crypto/crypto_null.c
+++ b/crypto/crypto_null.c
@@ -145,9 +145,9 @@ static struct crypto_alg null_algs[3] = { {
 	.coa_decompress		=	null_compress } }
 } };
 
-MODULE_ALIAS("compress_null");
-MODULE_ALIAS("digest_null");
-MODULE_ALIAS("cipher_null");
+MODULE_ALIAS_CRYPTO("compress_null");
+MODULE_ALIAS_CRYPTO("digest_null");
+MODULE_ALIAS_CRYPTO("cipher_null");
 
 static int __init crypto_null_mod_init(void)
 {
diff --git a/crypto/ctr.c b/crypto/ctr.c
index f2b94f27bb2..2386f731395 100644
--- a/crypto/ctr.c
+++ b/crypto/ctr.c
@@ -466,4 +466,5 @@ module_exit(crypto_ctr_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("CTR Counter block mode");
-MODULE_ALIAS("rfc3686");
+MODULE_ALIAS_CRYPTO("rfc3686");
+MODULE_ALIAS_CRYPTO("ctr");
diff --git a/crypto/cts.c b/crypto/cts.c
index 133f0874c95..bd9405820e8 100644
--- a/crypto/cts.c
+++ b/crypto/cts.c
@@ -351,3 +351,4 @@ module_exit(crypto_cts_module_exit);
 
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_DESCRIPTION("CTS-CBC CipherText Stealing for CBC");
+MODULE_ALIAS_CRYPTO("cts");
diff --git a/crypto/deflate.c b/crypto/deflate.c
index b57d70eb156..95d8d37c502 100644
--- a/crypto/deflate.c
+++ b/crypto/deflate.c
@@ -222,4 +222,4 @@ module_exit(deflate_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Deflate Compression Algorithm for IPCOMP");
 MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");
-
+MODULE_ALIAS_CRYPTO("deflate");
diff --git a/crypto/des_generic.c b/crypto/des_generic.c
index 298d464ab7d..a71720544d1 100644
--- a/crypto/des_generic.c
+++ b/crypto/des_generic.c
@@ -983,8 +983,6 @@ static struct crypto_alg des_algs[2] = { {
 	.cia_decrypt		=	des3_ede_decrypt } }
 } };
 
-MODULE_ALIAS("des3_ede");
-
 static int __init des_generic_mod_init(void)
 {
 	return crypto_register_algs(des_algs, ARRAY_SIZE(des_algs));
@@ -1001,4 +999,7 @@ module_exit(des_generic_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms");
 MODULE_AUTHOR("Dag Arne Osvik <da@osvik.no>");
-MODULE_ALIAS("des");
+MODULE_ALIAS_CRYPTO("des");
+MODULE_ALIAS_CRYPTO("des-generic");
+MODULE_ALIAS_CRYPTO("des3_ede");
+MODULE_ALIAS_CRYPTO("des3_ede-generic");
diff --git a/crypto/ecb.c b/crypto/ecb.c
index 935cfef4aa8..12011aff097 100644
--- a/crypto/ecb.c
+++ b/crypto/ecb.c
@@ -185,3 +185,4 @@ module_exit(crypto_ecb_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("ECB block cipher algorithm");
+MODULE_ALIAS_CRYPTO("ecb");
diff --git a/crypto/eseqiv.c b/crypto/eseqiv.c
index bf7ab4a8949..f116fae766f 100644
--- a/crypto/eseqiv.c
+++ b/crypto/eseqiv.c
@@ -267,3 +267,4 @@ module_exit(eseqiv_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Encrypted Sequence Number IV Generator");
+MODULE_ALIAS_CRYPTO("eseqiv");
diff --git a/crypto/fcrypt.c b/crypto/fcrypt.c
index 021d7fec6bc..77286ea2886 100644
--- a/crypto/fcrypt.c
+++ b/crypto/fcrypt.c
@@ -420,3 +420,4 @@ module_exit(fcrypt_mod_fini);
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_DESCRIPTION("FCrypt Cipher Algorithm");
 MODULE_AUTHOR("David Howells <dhowells@redhat.com>");
+MODULE_ALIAS_CRYPTO("fcrypt");
diff --git a/crypto/gcm.c b/crypto/gcm.c
index 276cdac567b..2e403f6138c 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -1441,6 +1441,7 @@ module_exit(crypto_gcm_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Galois/Counter Mode");
 MODULE_AUTHOR("Mikko Herranen <mh1@iki.fi>");
-MODULE_ALIAS("gcm_base");
-MODULE_ALIAS("rfc4106");
-MODULE_ALIAS("rfc4543");
+MODULE_ALIAS_CRYPTO("gcm_base");
+MODULE_ALIAS_CRYPTO("rfc4106");
+MODULE_ALIAS_CRYPTO("rfc4543");
+MODULE_ALIAS_CRYPTO("gcm");
diff --git a/crypto/ghash-generic.c b/crypto/ghash-generic.c
index 9d3f0c69a86..bac70995e06 100644
--- a/crypto/ghash-generic.c
+++ b/crypto/ghash-generic.c
@@ -172,4 +172,5 @@ module_exit(ghash_mod_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("GHASH Message Digest Algorithm");
-MODULE_ALIAS("ghash");
+MODULE_ALIAS_CRYPTO("ghash");
+MODULE_ALIAS_CRYPTO("ghash-generic");
diff --git a/crypto/hmac.c b/crypto/hmac.c
index e392219ddc6..72e38c098bb 100644
--- a/crypto/hmac.c
+++ b/crypto/hmac.c
@@ -268,3 +268,4 @@ module_exit(hmac_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("HMAC hash algorithm");
+MODULE_ALIAS_CRYPTO("hmac");
diff --git a/crypto/khazad.c b/crypto/khazad.c
index 60e7cd66fac..873eb5ded6d 100644
--- a/crypto/khazad.c
+++ b/crypto/khazad.c
@@ -880,3 +880,4 @@ module_exit(khazad_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Khazad Cryptographic Algorithm");
+MODULE_ALIAS_CRYPTO("khazad");
diff --git a/crypto/krng.c b/crypto/krng.c
index a2d2b72fc13..0224841b657 100644
--- a/crypto/krng.c
+++ b/crypto/krng.c
@@ -62,4 +62,5 @@ module_exit(krng_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Kernel Random Number Generator");
-MODULE_ALIAS("stdrng");
+MODULE_ALIAS_CRYPTO("stdrng");
+MODULE_ALIAS_CRYPTO("krng");
diff --git a/crypto/lrw.c b/crypto/lrw.c
index ba42acc4deb..6f9908a7ebc 100644
--- a/crypto/lrw.c
+++ b/crypto/lrw.c
@@ -400,3 +400,4 @@ module_exit(crypto_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("LRW block cipher mode");
+MODULE_ALIAS_CRYPTO("lrw");
diff --git a/crypto/lz4.c b/crypto/lz4.c
index 34d072b72a7..aefbceaf310 100644
--- a/crypto/lz4.c
+++ b/crypto/lz4.c
@@ -104,3 +104,4 @@ module_exit(lz4_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("LZ4 Compression Algorithm");
+MODULE_ALIAS_CRYPTO("lz4");
diff --git a/crypto/lz4hc.c b/crypto/lz4hc.c
index 9218b3fed5e..a1d3b5bd3d8 100644
--- a/crypto/lz4hc.c
+++ b/crypto/lz4hc.c
@@ -104,3 +104,4 @@ module_exit(lz4hc_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("LZ4HC Compression Algorithm");
+MODULE_ALIAS_CRYPTO("lz4hc");
diff --git a/crypto/lzo.c b/crypto/lzo.c
index a8ff2f778dc..4b3e92525da 100644
--- a/crypto/lzo.c
+++ b/crypto/lzo.c
@@ -107,3 +107,4 @@ module_exit(lzo_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("LZO Compression Algorithm");
+MODULE_ALIAS_CRYPTO("lzo");
diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c
index b39fbd53010..a8e870444ea 100644
--- a/crypto/mcryptd.c
+++ b/crypto/mcryptd.c
@@ -703,3 +703,4 @@ module_exit(mcryptd_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Software async multibuffer crypto daemon");
+MODULE_ALIAS_CRYPTO("mcryptd");
diff --git a/crypto/md4.c b/crypto/md4.c
index 0477a6a01d5..3515af425cc 100644
--- a/crypto/md4.c
+++ b/crypto/md4.c
@@ -255,4 +255,4 @@ module_exit(md4_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MD4 Message Digest Algorithm");
-
+MODULE_ALIAS_CRYPTO("md4");
diff --git a/crypto/md5.c b/crypto/md5.c
index 7febeaab923..36f5e5b103f 100644
--- a/crypto/md5.c
+++ b/crypto/md5.c
@@ -168,3 +168,4 @@ module_exit(md5_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MD5 Message Digest Algorithm");
+MODULE_ALIAS_CRYPTO("md5");
diff --git a/crypto/michael_mic.c b/crypto/michael_mic.c
index 079b761bc70..46195e0d0f4 100644
--- a/crypto/michael_mic.c
+++ b/crypto/michael_mic.c
@@ -184,3 +184,4 @@ module_exit(michael_mic_exit);
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Michael MIC");
 MODULE_AUTHOR("Jouni Malinen <j@w1.fi>");
+MODULE_ALIAS_CRYPTO("michael_mic");
diff --git a/crypto/pcbc.c b/crypto/pcbc.c
index d1b8bdfb585..f654965f093 100644
--- a/crypto/pcbc.c
+++ b/crypto/pcbc.c
@@ -295,3 +295,4 @@ module_exit(crypto_pcbc_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("PCBC block cipher algorithm");
+MODULE_ALIAS_CRYPTO("pcbc");
diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c
index 309d345ead9..c305d411273 100644
--- a/crypto/pcrypt.c
+++ b/crypto/pcrypt.c
@@ -565,3 +565,4 @@ module_exit(pcrypt_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>");
 MODULE_DESCRIPTION("Parallel crypto wrapper");
+MODULE_ALIAS_CRYPTO("pcrypt");
diff --git a/crypto/rmd128.c b/crypto/rmd128.c
index 8a0f68b7f25..049486ede93 100644
--- a/crypto/rmd128.c
+++ b/crypto/rmd128.c
@@ -327,3 +327,4 @@ module_exit(rmd128_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
 MODULE_DESCRIPTION("RIPEMD-128 Message Digest");
+MODULE_ALIAS_CRYPTO("rmd128");
diff --git a/crypto/rmd160.c b/crypto/rmd160.c
index 525d7bb752c..de585e51d45 100644
--- a/crypto/rmd160.c
+++ b/crypto/rmd160.c
@@ -371,3 +371,4 @@ module_exit(rmd160_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
 MODULE_DESCRIPTION("RIPEMD-160 Message Digest");
+MODULE_ALIAS_CRYPTO("rmd160");
diff --git a/crypto/rmd256.c b/crypto/rmd256.c
index 69293d9b56e..4ec02a754e0 100644
--- a/crypto/rmd256.c
+++ b/crypto/rmd256.c
@@ -346,3 +346,4 @@ module_exit(rmd256_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
 MODULE_DESCRIPTION("RIPEMD-256 Message Digest");
+MODULE_ALIAS_CRYPTO("rmd256");
diff --git a/crypto/rmd320.c b/crypto/rmd320.c
index 09f97dfdfbb..770f2cb369f 100644
--- a/crypto/rmd320.c
+++ b/crypto/rmd320.c
@@ -395,3 +395,4 @@ module_exit(rmd320_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
 MODULE_DESCRIPTION("RIPEMD-320 Message Digest");
+MODULE_ALIAS_CRYPTO("rmd320");
diff --git a/crypto/salsa20_generic.c b/crypto/salsa20_generic.c
index 9a4770c0228..f550b5d9463 100644
--- a/crypto/salsa20_generic.c
+++ b/crypto/salsa20_generic.c
@@ -248,4 +248,5 @@ module_exit(salsa20_generic_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION ("Salsa20 stream cipher algorithm");
-MODULE_ALIAS("salsa20");
+MODULE_ALIAS_CRYPTO("salsa20");
+MODULE_ALIAS_CRYPTO("salsa20-generic");
diff --git a/crypto/seed.c b/crypto/seed.c
index 9c904d6d215..c6ba8438be4 100644
--- a/crypto/seed.c
+++ b/crypto/seed.c
@@ -476,3 +476,4 @@ module_exit(seed_fini);
 MODULE_DESCRIPTION("SEED Cipher Algorithm");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Hye-Shik Chang <perky@FreeBSD.org>, Kim Hyun <hkim@kisa.or.kr>");
+MODULE_ALIAS_CRYPTO("seed");
diff --git a/crypto/seqiv.c b/crypto/seqiv.c
index ee190fcedcd..9daa854cc48 100644
--- a/crypto/seqiv.c
+++ b/crypto/seqiv.c
@@ -362,3 +362,4 @@ module_exit(seqiv_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Sequence Number IV Generator");
+MODULE_ALIAS_CRYPTO("seqiv");
diff --git a/crypto/serpent_generic.c b/crypto/serpent_generic.c
index 7ddbd7e8885..94970a79497 100644
--- a/crypto/serpent_generic.c
+++ b/crypto/serpent_generic.c
@@ -665,5 +665,6 @@ module_exit(serpent_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Serpent and tnepres (kerneli compatible serpent reversed) Cipher Algorithm");
 MODULE_AUTHOR("Dag Arne Osvik <osvik@ii.uib.no>");
-MODULE_ALIAS("tnepres");
-MODULE_ALIAS("serpent");
+MODULE_ALIAS_CRYPTO("tnepres");
+MODULE_ALIAS_CRYPTO("serpent");
+MODULE_ALIAS_CRYPTO("serpent-generic");
diff --git a/crypto/sha1_generic.c b/crypto/sha1_generic.c
index 7bb04743278..a3e50c37eb6 100644
--- a/crypto/sha1_generic.c
+++ b/crypto/sha1_generic.c
@@ -153,4 +153,5 @@ module_exit(sha1_generic_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm");
 
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
+MODULE_ALIAS_CRYPTO("sha1-generic");
diff --git a/crypto/sha256_generic.c b/crypto/sha256_generic.c
index 65e7b76b057..b001ff5c2ef 100644
--- a/crypto/sha256_generic.c
+++ b/crypto/sha256_generic.c
@@ -384,5 +384,7 @@ module_exit(sha256_generic_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm");
 
-MODULE_ALIAS("sha224");
-MODULE_ALIAS("sha256");
+MODULE_ALIAS_CRYPTO("sha224");
+MODULE_ALIAS_CRYPTO("sha224-generic");
+MODULE_ALIAS_CRYPTO("sha256");
+MODULE_ALIAS_CRYPTO("sha256-generic");
diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c
index 95db67197cd..1c3c3767e07 100644
--- a/crypto/sha512_generic.c
+++ b/crypto/sha512_generic.c
@@ -288,5 +288,7 @@ module_exit(sha512_generic_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA-512 and SHA-384 Secure Hash Algorithms");
 
-MODULE_ALIAS("sha384");
-MODULE_ALIAS("sha512");
+MODULE_ALIAS_CRYPTO("sha384");
+MODULE_ALIAS_CRYPTO("sha384-generic");
+MODULE_ALIAS_CRYPTO("sha512");
+MODULE_ALIAS_CRYPTO("sha512-generic");
diff --git a/crypto/tea.c b/crypto/tea.c
index 0a572323ee4..b70b441c7d1 100644
--- a/crypto/tea.c
+++ b/crypto/tea.c
@@ -270,8 +270,9 @@ static void __exit tea_mod_fini(void)
 	crypto_unregister_algs(tea_algs, ARRAY_SIZE(tea_algs));
 }
 
-MODULE_ALIAS("xtea");
-MODULE_ALIAS("xeta");
+MODULE_ALIAS_CRYPTO("tea");
+MODULE_ALIAS_CRYPTO("xtea");
+MODULE_ALIAS_CRYPTO("xeta");
 
 module_init(tea_mod_init);
 module_exit(tea_mod_fini);
diff --git a/crypto/tgr192.c b/crypto/tgr192.c
index 3c7af0d1ff7..321bc6ff2a9 100644
--- a/crypto/tgr192.c
+++ b/crypto/tgr192.c
@@ -676,8 +676,9 @@ static void __exit tgr192_mod_fini(void)
 	crypto_unregister_shashes(tgr_algs, ARRAY_SIZE(tgr_algs));
 }
 
-MODULE_ALIAS("tgr160");
-MODULE_ALIAS("tgr128");
+MODULE_ALIAS_CRYPTO("tgr192");
+MODULE_ALIAS_CRYPTO("tgr160");
+MODULE_ALIAS_CRYPTO("tgr128");
 
 module_init(tgr192_mod_init);
 module_exit(tgr192_mod_fini);
diff --git a/crypto/twofish_generic.c b/crypto/twofish_generic.c
index 2d5000552d0..ebf7a3efb57 100644
--- a/crypto/twofish_generic.c
+++ b/crypto/twofish_generic.c
@@ -211,4 +211,5 @@ module_exit(twofish_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION ("Twofish Cipher Algorithm");
-MODULE_ALIAS("twofish");
+MODULE_ALIAS_CRYPTO("twofish");
+MODULE_ALIAS_CRYPTO("twofish-generic");
diff --git a/crypto/vmac.c b/crypto/vmac.c
index d84c24bd7ff..df76a816cfb 100644
--- a/crypto/vmac.c
+++ b/crypto/vmac.c
@@ -713,3 +713,4 @@ module_exit(vmac_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("VMAC hash algorithm");
+MODULE_ALIAS_CRYPTO("vmac");
diff --git a/crypto/wp512.c b/crypto/wp512.c
index ec64e7762fb..7ee5a043a98 100644
--- a/crypto/wp512.c
+++ b/crypto/wp512.c
@@ -1167,8 +1167,9 @@ static void __exit wp512_mod_fini(void)
 	crypto_unregister_shashes(wp_algs, ARRAY_SIZE(wp_algs));
 }
 
-MODULE_ALIAS("wp384");
-MODULE_ALIAS("wp256");
+MODULE_ALIAS_CRYPTO("wp512");
+MODULE_ALIAS_CRYPTO("wp384");
+MODULE_ALIAS_CRYPTO("wp256");
 
 module_init(wp512_mod_init);
 module_exit(wp512_mod_fini);
diff --git a/crypto/xcbc.c b/crypto/xcbc.c
index a5fbdf3738c..df90b332554 100644
--- a/crypto/xcbc.c
+++ b/crypto/xcbc.c
@@ -286,3 +286,4 @@ module_exit(crypto_xcbc_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("XCBC keyed hash algorithm");
+MODULE_ALIAS_CRYPTO("xcbc");
diff --git a/crypto/xts.c b/crypto/xts.c
index ca1608f44cb..f6fd43f100c 100644
--- a/crypto/xts.c
+++ b/crypto/xts.c
@@ -362,3 +362,4 @@ module_exit(crypto_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("XTS block cipher mode");
+MODULE_ALIAS_CRYPTO("xts");
diff --git a/crypto/zlib.c b/crypto/zlib.c
index c9ee681d57f..0eefa9d237a 100644
--- a/crypto/zlib.c
+++ b/crypto/zlib.c
@@ -378,3 +378,4 @@ module_exit(zlib_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Zlib Compression Algorithm");
 MODULE_AUTHOR("Sony Corporation");
+MODULE_ALIAS_CRYPTO("zlib");
diff --git a/drivers/Kconfig b/drivers/Kconfig
index 1a693d3f9d5..87a2552cafe 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -100,6 +100,8 @@ source "drivers/memstick/Kconfig"
 
 source "drivers/leds/Kconfig"
 
+source "drivers/switch/Kconfig"
+
 source "drivers/accessibility/Kconfig"
 
 source "drivers/infiniband/Kconfig"
@@ -182,4 +184,6 @@ source "drivers/ras/Kconfig"
 
 source "drivers/thunderbolt/Kconfig"
 
+source "drivers/gator/Kconfig"
+
 endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index ebee55537a0..4f0e5e2acfb 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -117,6 +117,7 @@ obj-$(CONFIG_CPU_IDLE)		+= cpuidle/
 obj-y				+= mmc/
 obj-$(CONFIG_MEMSTICK)		+= memstick/
 obj-y				+= leds/
+obj-$(CONFIG_SWITCH)		+= switch/
 obj-$(CONFIG_INFINIBAND)	+= infiniband/
 obj-$(CONFIG_SGI_SN)		+= sn/
 obj-y				+= firmware/
@@ -161,3 +162,6 @@ obj-$(CONFIG_POWERCAP)		+= powercap/
 obj-$(CONFIG_MCB)		+= mcb/
 obj-$(CONFIG_RAS)		+= ras/
 obj-$(CONFIG_THUNDERBOLT)	+= thunderbolt/
+obj-$(CONFIG_CORESIGHT)		+= hwtracing/coresight/
+
+obj-$(CONFIG_GATOR)		+= gator/
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index c3b2fcb729f..6d11522f0e4 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -47,6 +47,7 @@ acpi-y				+= int340x_thermal.o
 acpi-y				+= power.o
 acpi-y				+= event.o
 acpi-y				+= sysfs.o
+acpi-y				+= property.o
 acpi-$(CONFIG_X86)		+= acpi_cmos_rtc.o
 acpi-$(CONFIG_DEBUG_FS)		+= debugfs.o
 acpi-$(CONFIG_ACPI_NUMA)	+= numa.o
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 93d160661f4..fdb5701bed7 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -65,6 +65,7 @@ struct lpss_private_data;
 
 struct lpss_device_desc {
 	unsigned int flags;
+	const char *clk_con_id;
 	unsigned int prv_offset;
 	size_t prv_size_override;
 	void (*setup)(struct lpss_private_data *pdata);
@@ -105,7 +106,7 @@ static void lpss_uart_setup(struct lpss_private_data *pdata)
 	}
 }
 
-static void byt_i2c_setup(struct lpss_private_data *pdata)
+static void lpss_deassert_reset(struct lpss_private_data *pdata)
 {
 	unsigned int offset;
 	u32 val;
@@ -114,9 +115,18 @@ static void byt_i2c_setup(struct lpss_private_data *pdata)
 	val = readl(pdata->mmio_base + offset);
 	val |= LPSS_RESETS_RESET_APB | LPSS_RESETS_RESET_FUNC;
 	writel(val, pdata->mmio_base + offset);
+}
+
+#define LPSS_I2C_ENABLE			0x6c
+
+static void byt_i2c_setup(struct lpss_private_data *pdata)
+{
+	lpss_deassert_reset(pdata);
 
 	if (readl(pdata->mmio_base + pdata->dev_desc->prv_offset))
 		pdata->fixed_clk_rate = 133000000;
+
+	writel(0, pdata->mmio_base + LPSS_I2C_ENABLE);
 }
 
 static struct lpss_device_desc lpt_dev_desc = {
@@ -131,6 +141,7 @@ static struct lpss_device_desc lpt_i2c_dev_desc = {
 
 static struct lpss_device_desc lpt_uart_dev_desc = {
 	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_LTR,
+	.clk_con_id = "baudclk",
 	.prv_offset = 0x800,
 	.setup = lpss_uart_setup,
 };
@@ -147,6 +158,7 @@ static struct lpss_device_desc byt_pwm_dev_desc = {
 
 static struct lpss_device_desc byt_uart_dev_desc = {
 	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
+	.clk_con_id = "baudclk",
 	.prv_offset = 0x800,
 	.setup = lpss_uart_setup,
 };
@@ -166,6 +178,12 @@ static struct lpss_device_desc byt_i2c_dev_desc = {
 	.setup = byt_i2c_setup,
 };
 
+static struct lpss_device_desc bsw_spi_dev_desc = {
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
+	.prv_offset = 0x400,
+	.setup = lpss_deassert_reset,
+};
+
 #else
 
 #define LPSS_ADDR(desc) (0UL)
@@ -198,7 +216,7 @@ static const struct acpi_device_id acpi_lpss_device_ids[] = {
 	/* Braswell LPSS devices */
 	{ "80862288", LPSS_ADDR(byt_pwm_dev_desc) },
 	{ "8086228A", LPSS_ADDR(byt_uart_dev_desc) },
-	{ "8086228E", LPSS_ADDR(byt_spi_dev_desc) },
+	{ "8086228E", LPSS_ADDR(bsw_spi_dev_desc) },
 	{ "808622C1", LPSS_ADDR(byt_i2c_dev_desc) },
 
 	{ "INT3430", LPSS_ADDR(lpt_dev_desc) },
@@ -298,7 +316,7 @@ out:
 		return PTR_ERR(clk);
 
 	pdata->clk = clk;
-	clk_register_clkdev(clk, NULL, devname);
+	clk_register_clkdev(clk, dev_desc->clk_con_id, devname);
 	return 0;
 }
 
diff --git a/drivers/acpi/acpi_pnp.c b/drivers/acpi/acpi_pnp.c
index b193f842599..ff6d8adc9cd 100644
--- a/drivers/acpi/acpi_pnp.c
+++ b/drivers/acpi/acpi_pnp.c
@@ -304,6 +304,8 @@ static const struct acpi_device_id acpi_pnp_device_ids[] = {
 	{"PNPb006"},
 	/* cs423x-pnpbios */
 	{"CSC0100"},
+	{"CSC0103"},
+	{"CSC0110"},
 	{"CSC0000"},
 	{"GIM0100"},		/* Guillemot Turtlebeach something appears to be cs4232 compatible */
 	/* es18xx-pnpbios */
diff --git a/drivers/acpi/acpica/acmacros.h b/drivers/acpi/acpica/acmacros.h
index 4bceb11c738..624cbb3b568 100644
--- a/drivers/acpi/acpica/acmacros.h
+++ b/drivers/acpi/acpica/acmacros.h
@@ -63,23 +63,12 @@
 #define ACPI_SET64(ptr, val)            (*ACPI_CAST64 (ptr) = (u64) (val))
 
 /*
- * printf() format helpers. These macros are workarounds for the difficulties
+ * printf() format helper. This macros is a workaround for the difficulties
  * with emitting 64-bit integers and 64-bit pointers with the same code
  * for both 32-bit and 64-bit hosts.
  */
 #define ACPI_FORMAT_UINT64(i)           ACPI_HIDWORD(i), ACPI_LODWORD(i)
 
-#if ACPI_MACHINE_WIDTH == 64
-#define ACPI_FORMAT_NATIVE_UINT(i)      ACPI_FORMAT_UINT64(i)
-#define ACPI_FORMAT_TO_UINT(i)          ACPI_FORMAT_UINT64(i)
-#define ACPI_PRINTF_UINT                 "0x%8.8X%8.8X"
-
-#else
-#define ACPI_FORMAT_NATIVE_UINT(i)      0, (u32) (i)
-#define ACPI_FORMAT_TO_UINT(i)          (u32) (i)
-#define ACPI_PRINTF_UINT                 "0x%8.8X"
-#endif
-
 /*
  * Macros for moving data around to/from buffers that are possibly unaligned.
  * If the hardware supports the transfer of unaligned data, just do the store.
diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c
index 6c0759c0db4..5e7c7c301c5 100644
--- a/drivers/acpi/acpica/dsopcode.c
+++ b/drivers/acpi/acpica/dsopcode.c
@@ -446,7 +446,7 @@ acpi_ds_eval_region_operands(struct acpi_walk_state *walk_state,
 
 	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "RgnObj %p Addr %8.8X%8.8X Len %X\n",
 			  obj_desc,
-			  ACPI_FORMAT_NATIVE_UINT(obj_desc->region.address),
+			  ACPI_FORMAT_UINT64(obj_desc->region.address),
 			  obj_desc->region.length));
 
 	/* Now the address and length are valid for this opregion */
@@ -539,13 +539,12 @@ acpi_ds_eval_table_region_operands(struct acpi_walk_state *walk_state,
 		return_ACPI_STATUS(AE_NOT_EXIST);
 	}
 
-	obj_desc->region.address =
-	    (acpi_physical_address) ACPI_TO_INTEGER(table);
+	obj_desc->region.address = ACPI_PTR_TO_PHYSADDR(table);
 	obj_desc->region.length = table->length;
 
 	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "RgnObj %p Addr %8.8X%8.8X Len %X\n",
 			  obj_desc,
-			  ACPI_FORMAT_NATIVE_UINT(obj_desc->region.address),
+			  ACPI_FORMAT_UINT64(obj_desc->region.address),
 			  obj_desc->region.length));
 
 	/* Now the address and length are valid for this opregion */
diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c
index 8eb8575e8c1..9ce53980201 100644
--- a/drivers/acpi/acpica/evregion.c
+++ b/drivers/acpi/acpica/evregion.c
@@ -272,7 +272,7 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj,
 	ACPI_DEBUG_PRINT((ACPI_DB_OPREGION,
 			  "Handler %p (@%p) Address %8.8X%8.8X [%s]\n",
 			  &region_obj->region.handler->address_space, handler,
-			  ACPI_FORMAT_NATIVE_UINT(address),
+			  ACPI_FORMAT_UINT64(address),
 			  acpi_ut_get_region_name(region_obj->region.
 						  space_id)));
 
diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c
index 0f23c3f2678..16b4909a8b9 100644
--- a/drivers/acpi/acpica/exdump.c
+++ b/drivers/acpi/acpica/exdump.c
@@ -767,8 +767,8 @@ void acpi_ex_dump_operand(union acpi_operand_object *obj_desc, u32 depth)
 			acpi_os_printf("\n");
 		} else {
 			acpi_os_printf(" base %8.8X%8.8X Length %X\n",
-				       ACPI_FORMAT_NATIVE_UINT(obj_desc->region.
-							       address),
+				       ACPI_FORMAT_UINT64(obj_desc->region.
+							  address),
 				       obj_desc->region.length);
 		}
 		break;
diff --git a/drivers/acpi/acpica/exfldio.c b/drivers/acpi/acpica/exfldio.c
index 1d1b27a96c5..58ea85e42bf 100644
--- a/drivers/acpi/acpica/exfldio.c
+++ b/drivers/acpi/acpica/exfldio.c
@@ -263,17 +263,15 @@ acpi_ex_access_region(union acpi_operand_object *obj_desc,
 	}
 
 	ACPI_DEBUG_PRINT_RAW((ACPI_DB_BFIELD,
-			      " Region [%s:%X], Width %X, ByteBase %X, Offset %X at %p\n",
+			      " Region [%s:%X], Width %X, ByteBase %X, Offset %X at %8.8X%8.8X\n",
 			      acpi_ut_get_region_name(rgn_desc->region.
 						      space_id),
 			      rgn_desc->region.space_id,
 			      obj_desc->common_field.access_byte_width,
 			      obj_desc->common_field.base_byte_offset,
-			      field_datum_byte_offset, ACPI_CAST_PTR(void,
-								     (rgn_desc->
-								      region.
-								      address +
-								      region_offset))));
+			      field_datum_byte_offset,
+			      ACPI_FORMAT_UINT64(rgn_desc->region.address +
+						 region_offset)));
 
 	/* Invoke the appropriate address_space/op_region handler */
 
diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c
index cd5288a257a..be51d3ed4d0 100644
--- a/drivers/acpi/acpica/exregion.c
+++ b/drivers/acpi/acpica/exregion.c
@@ -181,7 +181,7 @@ acpi_ex_system_memory_space_handler(u32 function,
 		if (!mem_info->mapped_logical_address) {
 			ACPI_ERROR((AE_INFO,
 				    "Could not map memory at 0x%8.8X%8.8X, size %u",
-				    ACPI_FORMAT_NATIVE_UINT(address),
+				    ACPI_FORMAT_UINT64(address),
 				    (u32) map_length));
 			mem_info->mapped_length = 0;
 			return_ACPI_STATUS(AE_NO_MEMORY);
@@ -202,8 +202,7 @@ acpi_ex_system_memory_space_handler(u32 function,
 
 	ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 			  "System-Memory (width %u) R/W %u Address=%8.8X%8.8X\n",
-			  bit_width, function,
-			  ACPI_FORMAT_NATIVE_UINT(address)));
+			  bit_width, function, ACPI_FORMAT_UINT64(address)));
 
 	/*
 	 * Perform the memory read or write
@@ -318,8 +317,7 @@ acpi_ex_system_io_space_handler(u32 function,
 
 	ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 			  "System-IO (width %u) R/W %u Address=%8.8X%8.8X\n",
-			  bit_width, function,
-			  ACPI_FORMAT_NATIVE_UINT(address)));
+			  bit_width, function, ACPI_FORMAT_UINT64(address)));
 
 	/* Decode the function parameter */
 
diff --git a/drivers/acpi/acpica/hwvalid.c b/drivers/acpi/acpica/hwvalid.c
index 6b919127cd9..dabf754ea4a 100644
--- a/drivers/acpi/acpica/hwvalid.c
+++ b/drivers/acpi/acpica/hwvalid.c
@@ -142,17 +142,17 @@ acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width)
 	byte_width = ACPI_DIV_8(bit_width);
 	last_address = address + byte_width - 1;
 
-	ACPI_DEBUG_PRINT((ACPI_DB_IO, "Address %p LastAddress %p Length %X",
-			  ACPI_CAST_PTR(void, address), ACPI_CAST_PTR(void,
-								      last_address),
-			  byte_width));
+	ACPI_DEBUG_PRINT((ACPI_DB_IO,
+			  "Address %8.8X%8.8X LastAddress %8.8X%8.8X Length %X",
+			  ACPI_FORMAT_UINT64(address),
+			  ACPI_FORMAT_UINT64(last_address), byte_width));
 
 	/* Maximum 16-bit address in I/O space */
 
 	if (last_address > ACPI_UINT16_MAX) {
 		ACPI_ERROR((AE_INFO,
-			    "Illegal I/O port address/length above 64K: %p/0x%X",
-			    ACPI_CAST_PTR(void, address), byte_width));
+			    "Illegal I/O port address/length above 64K: %8.8X%8.8X/0x%X",
+			    ACPI_FORMAT_UINT64(address), byte_width));
 		return_ACPI_STATUS(AE_LIMIT);
 	}
 
@@ -181,8 +181,8 @@ acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width)
 
 			if (acpi_gbl_osi_data >= port_info->osi_dependency) {
 				ACPI_DEBUG_PRINT((ACPI_DB_IO,
-						  "Denied AML access to port 0x%p/%X (%s 0x%.4X-0x%.4X)",
-						  ACPI_CAST_PTR(void, address),
+						  "Denied AML access to port 0x%8.8X%8.8X/%X (%s 0x%.4X-0x%.4X)",
+						  ACPI_FORMAT_UINT64(address),
 						  byte_width, port_info->name,
 						  port_info->start,
 						  port_info->end));
diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c
index 3d88ef4a3e0..809ed52de9c 100644
--- a/drivers/acpi/acpica/nsdump.c
+++ b/drivers/acpi/acpica/nsdump.c
@@ -271,12 +271,11 @@ acpi_ns_dump_one_object(acpi_handle obj_handle,
 		switch (type) {
 		case ACPI_TYPE_PROCESSOR:
 
-			acpi_os_printf("ID %02X Len %02X Addr %p\n",
+			acpi_os_printf("ID %02X Len %02X Addr %8.8X%8.8X\n",
 				       obj_desc->processor.proc_id,
 				       obj_desc->processor.length,
-				       ACPI_CAST_PTR(void,
-						     obj_desc->processor.
-						     address));
+				       ACPI_FORMAT_UINT64(obj_desc->processor.
+							  address));
 			break;
 
 		case ACPI_TYPE_DEVICE:
@@ -347,8 +346,9 @@ acpi_ns_dump_one_object(acpi_handle obj_handle,
 							       space_id));
 			if (obj_desc->region.flags & AOPOBJ_DATA_VALID) {
 				acpi_os_printf(" Addr %8.8X%8.8X Len %.4X\n",
-					       ACPI_FORMAT_NATIVE_UINT
-					       (obj_desc->region.address),
+					       ACPI_FORMAT_UINT64(obj_desc->
+								  region.
+								  address),
 					       obj_desc->region.length);
 			} else {
 				acpi_os_printf
diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c
index f499c10ceb4..a078053ff47 100644
--- a/drivers/acpi/acpica/tbdata.c
+++ b/drivers/acpi/acpica/tbdata.c
@@ -113,9 +113,9 @@ acpi_tb_acquire_table(struct acpi_table_desc *table_desc,
 	case ACPI_TABLE_ORIGIN_INTERNAL_VIRTUAL:
 	case ACPI_TABLE_ORIGIN_EXTERNAL_VIRTUAL:
 
-		table =
-		    ACPI_CAST_PTR(struct acpi_table_header,
-				  table_desc->address);
+		table = ACPI_CAST_PTR(struct acpi_table_header,
+				      ACPI_PHYSADDR_TO_PTR(table_desc->
+							   address));
 		break;
 
 	default:
@@ -214,7 +214,8 @@ acpi_tb_acquire_temp_table(struct acpi_table_desc *table_desc,
 	case ACPI_TABLE_ORIGIN_INTERNAL_VIRTUAL:
 	case ACPI_TABLE_ORIGIN_EXTERNAL_VIRTUAL:
 
-		table_header = ACPI_CAST_PTR(struct acpi_table_header, address);
+		table_header = ACPI_CAST_PTR(struct acpi_table_header,
+					     ACPI_PHYSADDR_TO_PTR(address));
 		if (!table_header) {
 			return (AE_NO_MEMORY);
 		}
@@ -398,14 +399,14 @@ acpi_tb_verify_temp_table(struct acpi_table_desc * table_desc, char *signature)
 					    table_desc->length);
 		if (ACPI_FAILURE(status)) {
 			ACPI_EXCEPTION((AE_INFO, AE_NO_MEMORY,
-					"%4.4s " ACPI_PRINTF_UINT
+					"%4.4s 0x%8.8X%8.8X"
 					" Attempted table install failed",
 					acpi_ut_valid_acpi_name(table_desc->
 								signature.
 								ascii) ?
 					table_desc->signature.ascii : "????",
-					ACPI_FORMAT_TO_UINT(table_desc->
-							    address)));
+					ACPI_FORMAT_UINT64(table_desc->
+							   address)));
 			goto invalidate_and_exit;
 		}
 	}
diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c
index 755b90c40dd..8e1a43ae2f9 100644
--- a/drivers/acpi/acpica/tbinstal.c
+++ b/drivers/acpi/acpica/tbinstal.c
@@ -187,8 +187,9 @@ acpi_tb_install_fixed_table(acpi_physical_address address,
 	status = acpi_tb_acquire_temp_table(&new_table_desc, address,
 					    ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL);
 	if (ACPI_FAILURE(status)) {
-		ACPI_ERROR((AE_INFO, "Could not acquire table length at %p",
-			    ACPI_CAST_PTR(void, address)));
+		ACPI_ERROR((AE_INFO,
+			    "Could not acquire table length at %8.8X%8.8X",
+			    ACPI_FORMAT_UINT64(address)));
 		return_ACPI_STATUS(status);
 	}
 
@@ -246,8 +247,9 @@ acpi_tb_install_standard_table(acpi_physical_address address,
 
 	status = acpi_tb_acquire_temp_table(&new_table_desc, address, flags);
 	if (ACPI_FAILURE(status)) {
-		ACPI_ERROR((AE_INFO, "Could not acquire table length at %p",
-			    ACPI_CAST_PTR(void, address)));
+		ACPI_ERROR((AE_INFO,
+			    "Could not acquire table length at %8.8X%8.8X",
+			    ACPI_FORMAT_UINT64(address)));
 		return_ACPI_STATUS(status);
 	}
 
@@ -258,9 +260,10 @@ acpi_tb_install_standard_table(acpi_physical_address address,
 	if (!reload &&
 	    acpi_gbl_disable_ssdt_table_install &&
 	    ACPI_COMPARE_NAME(&new_table_desc.signature, ACPI_SIG_SSDT)) {
-		ACPI_INFO((AE_INFO, "Ignoring installation of %4.4s at %p",
-			   new_table_desc.signature.ascii, ACPI_CAST_PTR(void,
-									 address)));
+		ACPI_INFO((AE_INFO,
+			   "Ignoring installation of %4.4s at %8.8X%8.8X",
+			   new_table_desc.signature.ascii,
+			   ACPI_FORMAT_UINT64(address)));
 		goto release_and_exit;
 	}
 
@@ -346,7 +349,6 @@ acpi_tb_install_standard_table(acpi_physical_address address,
 				 */
 				acpi_tb_uninstall_table(&new_table_desc);
 				*table_index = i;
-				(void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
 				return_ACPI_STATUS(AE_OK);
 			}
 		}
@@ -429,11 +431,11 @@ finish_override:
 		return;
 	}
 
-	ACPI_INFO((AE_INFO, "%4.4s " ACPI_PRINTF_UINT
-		   " %s table override, new table: " ACPI_PRINTF_UINT,
+	ACPI_INFO((AE_INFO, "%4.4s 0x%8.8X%8.8X"
+		   " %s table override, new table: 0x%8.8X%8.8X",
 		   old_table_desc->signature.ascii,
-		   ACPI_FORMAT_TO_UINT(old_table_desc->address),
-		   override_type, ACPI_FORMAT_TO_UINT(new_table_desc.address)));
+		   ACPI_FORMAT_UINT64(old_table_desc->address),
+		   override_type, ACPI_FORMAT_UINT64(new_table_desc.address)));
 
 	/* We can now uninstall the original table */
 
@@ -517,7 +519,7 @@ void acpi_tb_uninstall_table(struct acpi_table_desc *table_desc)
 
 	if ((table_desc->flags & ACPI_TABLE_ORIGIN_MASK) ==
 	    ACPI_TABLE_ORIGIN_INTERNAL_VIRTUAL) {
-		ACPI_FREE(ACPI_CAST_PTR(void, table_desc->address));
+		ACPI_FREE(ACPI_PHYSADDR_TO_PTR(table_desc->address));
 	}
 
 	table_desc->address = ACPI_PTR_TO_PHYSADDR(NULL);
diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c
index df3bb20ea32..a23bdaec604 100644
--- a/drivers/acpi/acpica/tbprint.c
+++ b/drivers/acpi/acpica/tbprint.c
@@ -127,18 +127,12 @@ acpi_tb_print_table_header(acpi_physical_address address,
 {
 	struct acpi_table_header local_header;
 
-	/*
-	 * The reason that we use ACPI_PRINTF_UINT and ACPI_FORMAT_TO_UINT is to
-	 * support both 32-bit and 64-bit hosts/addresses in a consistent manner.
-	 * The %p specifier does not emit uniform output on all hosts. On some,
-	 * leading zeros are not supported.
-	 */
 	if (ACPI_COMPARE_NAME(header->signature, ACPI_SIG_FACS)) {
 
 		/* FACS only has signature and length fields */
 
-		ACPI_INFO((AE_INFO, "%-4.4s " ACPI_PRINTF_UINT " %06X",
-			   header->signature, ACPI_FORMAT_TO_UINT(address),
+		ACPI_INFO((AE_INFO, "%-4.4s 0x%8.8X%8.8X %06X",
+			   header->signature, ACPI_FORMAT_UINT64(address),
 			   header->length));
 	} else if (ACPI_VALIDATE_RSDP_SIG(header->signature)) {
 
@@ -149,9 +143,8 @@ acpi_tb_print_table_header(acpi_physical_address address,
 					  header)->oem_id, ACPI_OEM_ID_SIZE);
 		acpi_tb_fix_string(local_header.oem_id, ACPI_OEM_ID_SIZE);
 
-		ACPI_INFO((AE_INFO,
-			   "RSDP " ACPI_PRINTF_UINT " %06X (v%.2d %-6.6s)",
-			   ACPI_FORMAT_TO_UINT(address),
+		ACPI_INFO((AE_INFO, "RSDP 0x%8.8X%8.8X %06X (v%.2d %-6.6s)",
+			   ACPI_FORMAT_UINT64(address),
 			   (ACPI_CAST_PTR(struct acpi_table_rsdp, header)->
 			    revision >
 			    0) ? ACPI_CAST_PTR(struct acpi_table_rsdp,
@@ -165,9 +158,9 @@ acpi_tb_print_table_header(acpi_physical_address address,
 		acpi_tb_cleanup_table_header(&local_header, header);
 
 		ACPI_INFO((AE_INFO,
-			   "%-4.4s " ACPI_PRINTF_UINT
+			   "%-4.4s 0x%8.8X%8.8X"
 			   " %06X (v%.2d %-6.6s %-8.8s %08X %-4.4s %08X)",
-			   local_header.signature, ACPI_FORMAT_TO_UINT(address),
+			   local_header.signature, ACPI_FORMAT_UINT64(address),
 			   local_header.length, local_header.revision,
 			   local_header.oem_id, local_header.oem_table_id,
 			   local_header.oem_revision,
diff --git a/drivers/acpi/acpica/tbxfroot.c b/drivers/acpi/acpica/tbxfroot.c
index 43a54af2b54..89772b3fe55 100644
--- a/drivers/acpi/acpica/tbxfroot.c
+++ b/drivers/acpi/acpica/tbxfroot.c
@@ -142,7 +142,7 @@ acpi_status acpi_tb_validate_rsdp(struct acpi_table_rsdp * rsdp)
  *
  ******************************************************************************/
 
-acpi_status __init acpi_find_root_pointer(acpi_size *table_address)
+acpi_status __init acpi_find_root_pointer(acpi_physical_address * table_address)
 {
 	u8 *table_ptr;
 	u8 *mem_rover;
@@ -200,7 +200,8 @@ acpi_status __init acpi_find_root_pointer(acpi_size *table_address)
 			physical_address +=
 			    (u32) ACPI_PTR_DIFF(mem_rover, table_ptr);
 
-			*table_address = physical_address;
+			*table_address =
+			    (acpi_physical_address) physical_address;
 			return_ACPI_STATUS(AE_OK);
 		}
 	}
@@ -233,7 +234,7 @@ acpi_status __init acpi_find_root_pointer(acpi_size *table_address)
 		    (ACPI_HI_RSDP_WINDOW_BASE +
 		     ACPI_PTR_DIFF(mem_rover, table_ptr));
 
-		*table_address = physical_address;
+		*table_address = (acpi_physical_address) physical_address;
 		return_ACPI_STATUS(AE_OK);
 	}
 
diff --git a/drivers/acpi/acpica/utaddress.c b/drivers/acpi/acpica/utaddress.c
index a1acec9d2ef..65985036c5c 100644
--- a/drivers/acpi/acpica/utaddress.c
+++ b/drivers/acpi/acpica/utaddress.c
@@ -107,10 +107,10 @@ acpi_ut_add_address_range(acpi_adr_space_type space_id,
 	acpi_gbl_address_range_list[space_id] = range_info;
 
 	ACPI_DEBUG_PRINT((ACPI_DB_NAMES,
-			  "\nAdded [%4.4s] address range: 0x%p-0x%p\n",
+			  "\nAdded [%4.4s] address range: 0x%8.8X%8.8X-0x%8.8X%8.8X\n",
 			  acpi_ut_get_node_name(range_info->region_node),
-			  ACPI_CAST_PTR(void, address),
-			  ACPI_CAST_PTR(void, range_info->end_address)));
+			  ACPI_FORMAT_UINT64(address),
+			  ACPI_FORMAT_UINT64(range_info->end_address)));
 
 	(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
 	return_ACPI_STATUS(AE_OK);
@@ -160,15 +160,13 @@ acpi_ut_remove_address_range(acpi_adr_space_type space_id,
 			}
 
 			ACPI_DEBUG_PRINT((ACPI_DB_NAMES,
-					  "\nRemoved [%4.4s] address range: 0x%p-0x%p\n",
+					  "\nRemoved [%4.4s] address range: 0x%8.8X%8.8X-0x%8.8X%8.8X\n",
 					  acpi_ut_get_node_name(range_info->
 								region_node),
-					  ACPI_CAST_PTR(void,
-							range_info->
-							start_address),
-					  ACPI_CAST_PTR(void,
-							range_info->
-							end_address)));
+					  ACPI_FORMAT_UINT64(range_info->
+							     start_address),
+					  ACPI_FORMAT_UINT64(range_info->
+							     end_address)));
 
 			ACPI_FREE(range_info);
 			return_VOID;
@@ -245,16 +243,14 @@ acpi_ut_check_address_range(acpi_adr_space_type space_id,
 								  region_node);
 
 				ACPI_WARNING((AE_INFO,
-					      "%s range 0x%p-0x%p conflicts with OpRegion 0x%p-0x%p (%s)",
+					      "%s range 0x%8.8X%8.8X-0x%8.8X%8.8X conflicts with OpRegion 0x%8.8X%8.8X-0x%8.8X%8.8X (%s)",
 					      acpi_ut_get_region_name(space_id),
-					      ACPI_CAST_PTR(void, address),
-					      ACPI_CAST_PTR(void, end_address),
-					      ACPI_CAST_PTR(void,
-							    range_info->
-							    start_address),
-					      ACPI_CAST_PTR(void,
-							    range_info->
-							    end_address),
+					      ACPI_FORMAT_UINT64(address),
+					      ACPI_FORMAT_UINT64(end_address),
+					      ACPI_FORMAT_UINT64(range_info->
+								 start_address),
+					      ACPI_FORMAT_UINT64(range_info->
+								 end_address),
 					      pathname));
 				ACPI_FREE(pathname);
 			}
diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c
index 13380d81846..64f8f307243 100644
--- a/drivers/acpi/acpica/utxfinit.c
+++ b/drivers/acpi/acpica/utxfinit.c
@@ -175,10 +175,12 @@ acpi_status __init acpi_enable_subsystem(u32 flags)
 	 * Obtain a permanent mapping for the FACS. This is required for the
 	 * Global Lock and the Firmware Waking Vector
 	 */
-	status = acpi_tb_initialize_facs();
-	if (ACPI_FAILURE(status)) {
-		ACPI_WARNING((AE_INFO, "Could not map the FACS table"));
-		return_ACPI_STATUS(status);
+	if (!(flags & ACPI_NO_FACS_INIT)) {
+		status = acpi_tb_initialize_facs();
+		if (ACPI_FAILURE(status)) {
+			ACPI_WARNING((AE_INFO, "Could not map the FACS table"));
+			return_ACPI_STATUS(status);
+		}
 	}
 #endif				/* !ACPI_REDUCED_HARDWARE */
 
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 7db19316076..813397a2559 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -257,7 +257,7 @@ int acpi_bus_init_power(struct acpi_device *device)
 
 	device->power.state = ACPI_STATE_UNKNOWN;
 	if (!acpi_device_is_present(device))
-		return 0;
+		return -ENXIO;
 
 	result = acpi_device_get_power(device, &state);
 	if (result)
@@ -680,13 +680,21 @@ static int acpi_device_wakeup(struct acpi_device *adev, u32 target_state,
 		if (error)
 			return error;
 
+		if (adev->wakeup.flags.enabled)
+			return 0;
+
 		res = acpi_enable_gpe(wakeup->gpe_device, wakeup->gpe_number);
-		if (ACPI_FAILURE(res)) {
+		if (ACPI_SUCCESS(res)) {
+			adev->wakeup.flags.enabled = 1;
+		} else {
 			acpi_disable_wakeup_device_power(adev);
 			return -EIO;
 		}
 	} else {
-		acpi_disable_gpe(wakeup->gpe_device, wakeup->gpe_number);
+		if (adev->wakeup.flags.enabled) {
+			acpi_disable_gpe(wakeup->gpe_device, wakeup->gpe_number);
+			adev->wakeup.flags.enabled = 0;
+		}
 		acpi_disable_wakeup_device_power(adev);
 	}
 	return 0;
@@ -949,6 +957,7 @@ EXPORT_SYMBOL_GPL(acpi_subsys_prepare);
  */
 void acpi_subsys_complete(struct device *dev)
 {
+	pm_generic_complete(dev);
 	/*
 	 * If the device had been runtime-suspended before the system went into
 	 * the sleep state it is going out of and it has never been resumed till
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 447f6d679b2..163e82f536f 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -173,4 +173,10 @@ static inline void suspend_nvs_restore(void) {}
 bool acpi_osi_is_win8(void);
 #endif
 
+/*--------------------------------------------------------------------------
+				Device properties
+  -------------------------------------------------------------------------- */
+void acpi_init_properties(struct acpi_device *adev);
+void acpi_free_properties(struct acpi_device *adev);
+
 #endif /* _ACPI_INTERNAL_H_ */
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 9964f70be98..83835981822 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -182,7 +182,7 @@ static void __init acpi_request_region (struct acpi_generic_address *gas,
 		request_mem_region(addr, length, desc);
 }
 
-static int __init acpi_reserve_resources(void)
+static void __init acpi_reserve_resources(void)
 {
 	acpi_request_region(&acpi_gbl_FADT.xpm1a_event_block, acpi_gbl_FADT.pm1_event_length,
 		"ACPI PM1a_EVT_BLK");
@@ -211,10 +211,7 @@ static int __init acpi_reserve_resources(void)
 	if (!(acpi_gbl_FADT.gpe1_block_length & 0x1))
 		acpi_request_region(&acpi_gbl_FADT.xgpe1_block,
 			       acpi_gbl_FADT.gpe1_block_length, "ACPI GPE1_BLK");
-
-	return 0;
 }
-device_initcall(acpi_reserve_resources);
 
 void acpi_os_printf(const char *fmt, ...)
 {
@@ -1839,6 +1836,7 @@ acpi_status __init acpi_os_initialize(void)
 
 acpi_status __init acpi_os_initialize1(void)
 {
+	acpi_reserve_resources();
 	kacpid_wq = alloc_workqueue("kacpid", 0, 1);
 	kacpi_notify_wq = alloc_workqueue("kacpi_notify", 0, 1);
 	kacpi_hotplug_wq = alloc_ordered_workqueue("kacpi_hotplug", 0);
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 17f9ec50197..fd8496a92b4 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -962,7 +962,7 @@ static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr)
 		return -EINVAL;
 
 	drv->safe_state_index = -1;
-	for (i = 0; i < CPUIDLE_STATE_MAX; i++) {
+	for (i = CPUIDLE_DRIVER_STATE_START; i < CPUIDLE_STATE_MAX; i++) {
 		drv->states[i].name[0] = '\0';
 		drv->states[i].desc[0] = '\0';
 	}
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
new file mode 100644
index 00000000000..2541b1fd1fa
--- /dev/null
+++ b/drivers/acpi/property.c
@@ -0,0 +1,542 @@
+/*
+ * ACPI device specific properties support.
+ *
+ * Copyright (C) 2014, Intel Corporation
+ * All rights reserved.
+ *
+ * Authors: Mika Westerberg <mika.westerberg@linux.intel.com>
+ *          Darren Hart <dvhart@linux.intel.com>
+ *          Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/export.h>
+
+#include "internal.h"
+
+/* ACPI _DSD device properties UUID: daffd814-6eba-4d8c-8a91-bc9bbf4aa301 */
+static const u8 prp_uuid[16] = {
+	0x14, 0xd8, 0xff, 0xda, 0xba, 0x6e, 0x8c, 0x4d,
+	0x8a, 0x91, 0xbc, 0x9b, 0xbf, 0x4a, 0xa3, 0x01
+};
+
+static bool acpi_property_value_ok(const union acpi_object *value)
+{
+	int j;
+
+	/*
+	 * The value must be an integer, a string, a reference, or a package
+	 * whose every element must be an integer, a string, or a reference.
+	 */
+	switch (value->type) {
+	case ACPI_TYPE_INTEGER:
+	case ACPI_TYPE_STRING:
+	case ACPI_TYPE_LOCAL_REFERENCE:
+		return true;
+
+	case ACPI_TYPE_PACKAGE:
+		for (j = 0; j < value->package.count; j++)
+			switch (value->package.elements[j].type) {
+			case ACPI_TYPE_INTEGER:
+			case ACPI_TYPE_STRING:
+			case ACPI_TYPE_LOCAL_REFERENCE:
+				continue;
+
+			default:
+				return false;
+			}
+
+		return true;
+	}
+	return false;
+}
+
+static bool acpi_properties_format_valid(const union acpi_object *properties)
+{
+	int i;
+
+	for (i = 0; i < properties->package.count; i++) {
+		const union acpi_object *property;
+
+		property = &properties->package.elements[i];
+		/*
+		 * Only two elements allowed, the first one must be a string and
+		 * the second one has to satisfy certain conditions.
+		 */
+		if (property->package.count != 2
+		    || property->package.elements[0].type != ACPI_TYPE_STRING
+		    || !acpi_property_value_ok(&property->package.elements[1]))
+			return false;
+	}
+	return true;
+}
+
+void acpi_init_properties(struct acpi_device *adev)
+{
+	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER };
+	const union acpi_object *desc;
+	acpi_status status;
+	int i;
+
+	status = acpi_evaluate_object_typed(adev->handle, "_DSD", NULL, &buf,
+					    ACPI_TYPE_PACKAGE);
+	if (ACPI_FAILURE(status))
+		return;
+
+	desc = buf.pointer;
+	if (desc->package.count % 2)
+		goto fail;
+
+	/* Look for the device properties UUID. */
+	for (i = 0; i < desc->package.count; i += 2) {
+		const union acpi_object *uuid, *properties;
+
+		uuid = &desc->package.elements[i];
+		properties = &desc->package.elements[i + 1];
+
+		/*
+		 * The first element must be a UUID and the second one must be
+		 * a package.
+		 */
+		if (uuid->type != ACPI_TYPE_BUFFER || uuid->buffer.length != 16
+		    || properties->type != ACPI_TYPE_PACKAGE)
+			break;
+
+		if (memcmp(uuid->buffer.pointer, prp_uuid, sizeof(prp_uuid)))
+			continue;
+
+		/*
+		 * We found the matching UUID. Now validate the format of the
+		 * package immediately following it.
+		 */
+		if (!acpi_properties_format_valid(properties))
+			break;
+
+		adev->data.pointer = buf.pointer;
+		adev->data.properties = properties;
+		return;
+	}
+
+ fail:
+	dev_warn(&adev->dev, "Returned _DSD data is not valid, skipping\n");
+	ACPI_FREE(buf.pointer);
+}
+
+void acpi_free_properties(struct acpi_device *adev)
+{
+	ACPI_FREE((void *)adev->data.pointer);
+	adev->data.pointer = NULL;
+	adev->data.properties = NULL;
+}
+
+/**
+ * acpi_dev_get_property - return an ACPI property with given name
+ * @adev: ACPI device to get property
+ * @name: Name of the property
+ * @type: Expected property type
+ * @obj: Location to store the property value (if not %NULL)
+ *
+ * Look up a property with @name and store a pointer to the resulting ACPI
+ * object at the location pointed to by @obj if found.
+ *
+ * Callers must not attempt to free the returned objects.  These objects will be
+ * freed by the ACPI core automatically during the removal of @adev.
+ *
+ * Return: %0 if property with @name has been found (success),
+ *         %-EINVAL if the arguments are invalid,
+ *         %-ENODATA if the property doesn't exist,
+ *         %-EPROTO if the property value type doesn't match @type.
+ */
+int acpi_dev_get_property(struct acpi_device *adev, const char *name,
+			  acpi_object_type type, const union acpi_object **obj)
+{
+	const union acpi_object *properties;
+	int i;
+
+	if (!adev || !name)
+		return -EINVAL;
+
+	if (!adev->data.pointer || !adev->data.properties)
+		return -ENODATA;
+
+	properties = adev->data.properties;
+	for (i = 0; i < properties->package.count; i++) {
+		const union acpi_object *propname, *propvalue;
+		const union acpi_object *property;
+
+		property = &properties->package.elements[i];
+
+		propname = &property->package.elements[0];
+		propvalue = &property->package.elements[1];
+
+		if (!strcmp(name, propname->string.pointer)) {
+			if (type != ACPI_TYPE_ANY && propvalue->type != type)
+				return -EPROTO;
+			else if (obj)
+				*obj = propvalue;
+
+			return 0;
+		}
+	}
+	return -ENODATA;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_get_property);
+
+/**
+ * acpi_dev_get_property_array - return an ACPI array property with given name
+ * @adev: ACPI device to get property
+ * @name: Name of the property
+ * @type: Expected type of array elements
+ * @obj: Location to store a pointer to the property value (if not NULL)
+ *
+ * Look up an array property with @name and store a pointer to the resulting
+ * ACPI object at the location pointed to by @obj if found.
+ *
+ * Callers must not attempt to free the returned objects.  Those objects will be
+ * freed by the ACPI core automatically during the removal of @adev.
+ *
+ * Return: %0 if array property (package) with @name has been found (success),
+ *         %-EINVAL if the arguments are invalid,
+ *         %-ENODATA if the property doesn't exist,
+ *         %-EPROTO if the property is not a package or the type of its elements
+ *           doesn't match @type.
+ */
+int acpi_dev_get_property_array(struct acpi_device *adev, const char *name,
+				acpi_object_type type,
+				const union acpi_object **obj)
+{
+	const union acpi_object *prop;
+	int ret, i;
+
+	ret = acpi_dev_get_property(adev, name, ACPI_TYPE_PACKAGE, &prop);
+	if (ret)
+		return ret;
+
+	if (type != ACPI_TYPE_ANY) {
+		/* Check that all elements are of correct type. */
+		for (i = 0; i < prop->package.count; i++)
+			if (prop->package.elements[i].type != type)
+				return -EPROTO;
+	}
+	if (obj)
+		*obj = prop;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_get_property_array);
+
+/**
+ * acpi_dev_get_property_reference - returns handle to the referenced object
+ * @adev: ACPI device to get property
+ * @name: Name of the property
+ * @size_prop: Name of the "size" property in referenced object
+ * @index: Index of the reference to return
+ * @args: Location to store the returned reference with optional arguments
+ *
+ * Find property with @name, verifify that it is a package containing at least
+ * one object reference and if so, store the ACPI device object pointer to the
+ * target object in @args->adev.
+ *
+ * If the reference includes arguments (@size_prop is not %NULL) follow the
+ * reference and check whether or not there is an integer property @size_prop
+ * under the target object and if so, whether or not its value matches the
+ * number of arguments that follow the reference.  If there's more than one
+ * reference in the property value package, @index is used to select the one to
+ * return.
+ *
+ * Return: %0 on success, negative error code on failure.
+ */
+int acpi_dev_get_property_reference(struct acpi_device *adev, const char *name,
+				    const char *size_prop, size_t index,
+				    struct acpi_reference_args *args)
+{
+	const union acpi_object *element, *end;
+	const union acpi_object *obj;
+	struct acpi_device *device;
+	int ret, idx = 0;
+
+	ret = acpi_dev_get_property(adev, name, ACPI_TYPE_ANY, &obj);
+	if (ret)
+		return ret;
+
+	/*
+	 * The simplest case is when the value is a single reference.  Just
+	 * return that reference then.
+	 */
+	if (obj->type == ACPI_TYPE_LOCAL_REFERENCE) {
+		if (size_prop || index)
+			return -EINVAL;
+
+		ret = acpi_bus_get_device(obj->reference.handle, &device);
+		if (ret)
+			return ret;
+
+		args->adev = device;
+		args->nargs = 0;
+		return 0;
+	}
+
+	/*
+	 * If it is not a single reference, then it is a package of
+	 * references followed by number of ints as follows:
+	 *
+	 *  Package () { REF, INT, REF, INT, INT }
+	 *
+	 * The index argument is then used to determine which reference
+	 * the caller wants (along with the arguments).
+	 */
+	if (obj->type != ACPI_TYPE_PACKAGE || index >= obj->package.count)
+		return -EPROTO;
+
+	element = obj->package.elements;
+	end = element + obj->package.count;
+
+	while (element < end) {
+		u32 nargs, i;
+
+		if (element->type != ACPI_TYPE_LOCAL_REFERENCE)
+			return -EPROTO;
+
+		ret = acpi_bus_get_device(element->reference.handle, &device);
+		if (ret)
+			return -ENODEV;
+
+		element++;
+		nargs = 0;
+
+		if (size_prop) {
+			const union acpi_object *prop;
+
+			/*
+			 * Find out how many arguments the refenced object
+			 * expects by reading its size_prop property.
+			 */
+			ret = acpi_dev_get_property(device, size_prop,
+						    ACPI_TYPE_INTEGER, &prop);
+			if (ret)
+				return ret;
+
+			nargs = prop->integer.value;
+			if (nargs > MAX_ACPI_REFERENCE_ARGS
+			    || element + nargs > end)
+				return -EPROTO;
+
+			/*
+			 * Skip to the start of the arguments and verify
+			 * that they all are in fact integers.
+			 */
+			for (i = 0; i < nargs; i++)
+				if (element[i].type != ACPI_TYPE_INTEGER)
+					return -EPROTO;
+		} else {
+			/* assume following integer elements are all args */
+			for (i = 0; element + i < end; i++) {
+				int type = element[i].type;
+
+				if (type == ACPI_TYPE_INTEGER)
+					nargs++;
+				else if (type == ACPI_TYPE_LOCAL_REFERENCE)
+					break;
+				else
+					return -EPROTO;
+			}
+		}
+
+		if (idx++ == index) {
+			args->adev = device;
+			args->nargs = nargs;
+			for (i = 0; i < nargs; i++)
+				args->args[i] = element[i].integer.value;
+
+			return 0;
+		}
+
+		element += nargs;
+	}
+
+	return -EPROTO;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_get_property_reference);
+
+int acpi_dev_prop_get(struct acpi_device *adev, const char *propname,
+		      void **valptr)
+{
+	return acpi_dev_get_property(adev, propname, ACPI_TYPE_ANY,
+				     (const union acpi_object **)valptr);
+}
+
+int acpi_dev_prop_read_single(struct acpi_device *adev, const char *propname,
+			      enum dev_prop_type proptype, void *val)
+{
+	const union acpi_object *obj;
+	int ret;
+
+	if (!val)
+		return -EINVAL;
+
+	if (proptype >= DEV_PROP_U8 && proptype <= DEV_PROP_U64) {
+		ret = acpi_dev_get_property(adev, propname, ACPI_TYPE_INTEGER, &obj);
+		if (ret)
+			return ret;
+
+		switch (proptype) {
+		case DEV_PROP_U8:
+			if (obj->integer.value > U8_MAX)
+				return -EOVERFLOW;
+			*(u8 *)val = obj->integer.value;
+			break;
+		case DEV_PROP_U16:
+			if (obj->integer.value > U16_MAX)
+				return -EOVERFLOW;
+			*(u16 *)val = obj->integer.value;
+			break;
+		case DEV_PROP_U32:
+			if (obj->integer.value > U32_MAX)
+				return -EOVERFLOW;
+			*(u32 *)val = obj->integer.value;
+			break;
+		default:
+			*(u64 *)val = obj->integer.value;
+			break;
+		}
+	} else if (proptype == DEV_PROP_STRING) {
+		ret = acpi_dev_get_property(adev, propname, ACPI_TYPE_STRING, &obj);
+		if (ret)
+			return ret;
+
+		*(char **)val = obj->string.pointer;
+	} else {
+		ret = -EINVAL;
+	}
+	return ret;
+}
+
+static int acpi_copy_property_array_u8(const union acpi_object *items, u8 *val,
+				       size_t nval)
+{
+	int i;
+
+	for (i = 0; i < nval; i++) {
+		if (items[i].type != ACPI_TYPE_INTEGER)
+			return -EPROTO;
+		if (items[i].integer.value > U8_MAX)
+			return -EOVERFLOW;
+
+		val[i] = items[i].integer.value;
+	}
+	return 0;
+}
+
+static int acpi_copy_property_array_u16(const union acpi_object *items,
+					u16 *val, size_t nval)
+{
+	int i;
+
+	for (i = 0; i < nval; i++) {
+		if (items[i].type != ACPI_TYPE_INTEGER)
+			return -EPROTO;
+		if (items[i].integer.value > U16_MAX)
+			return -EOVERFLOW;
+
+		val[i] = items[i].integer.value;
+	}
+	return 0;
+}
+
+static int acpi_copy_property_array_u32(const union acpi_object *items,
+					u32 *val, size_t nval)
+{
+	int i;
+
+	for (i = 0; i < nval; i++) {
+		if (items[i].type != ACPI_TYPE_INTEGER)
+			return -EPROTO;
+		if (items[i].integer.value > U32_MAX)
+			return -EOVERFLOW;
+
+		val[i] = items[i].integer.value;
+	}
+	return 0;
+}
+
+static int acpi_copy_property_array_u64(const union acpi_object *items,
+					u64 *val, size_t nval)
+{
+	int i;
+
+	for (i = 0; i < nval; i++) {
+		if (items[i].type != ACPI_TYPE_INTEGER)
+			return -EPROTO;
+
+		val[i] = items[i].integer.value;
+	}
+	return 0;
+}
+
+static int acpi_copy_property_array_string(const union acpi_object *items,
+					   char **val, size_t nval)
+{
+	int i;
+
+	for (i = 0; i < nval; i++) {
+		if (items[i].type != ACPI_TYPE_STRING)
+			return -EPROTO;
+
+		val[i] = items[i].string.pointer;
+	}
+	return 0;
+}
+
+int acpi_dev_prop_read(struct acpi_device *adev, const char *propname,
+		       enum dev_prop_type proptype, void *val, size_t nval)
+{
+	const union acpi_object *obj;
+	const union acpi_object *items;
+	int ret;
+
+	if (val && nval == 1) {
+		ret = acpi_dev_prop_read_single(adev, propname, proptype, val);
+		if (!ret)
+			return ret;
+	}
+
+	ret = acpi_dev_get_property_array(adev, propname, ACPI_TYPE_ANY, &obj);
+	if (ret)
+		return ret;
+
+	if (!val)
+		return obj->package.count;
+	else if (nval <= 0)
+		return -EINVAL;
+
+	if (nval > obj->package.count)
+		return -EOVERFLOW;
+
+	items = obj->package.elements;
+	switch (proptype) {
+	case DEV_PROP_U8:
+		ret = acpi_copy_property_array_u8(items, (u8 *)val, nval);
+		break;
+	case DEV_PROP_U16:
+		ret = acpi_copy_property_array_u16(items, (u16 *)val, nval);
+		break;
+	case DEV_PROP_U32:
+		ret = acpi_copy_property_array_u32(items, (u32 *)val, nval);
+		break;
+	case DEV_PROP_U64:
+		ret = acpi_copy_property_array_u64(items, (u64 *)val, nval);
+		break;
+	case DEV_PROP_STRING:
+		ret = acpi_copy_property_array_string(items, (char **)val, nval);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	return ret;
+}
diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c
index a7a3edd28be..f23179e8412 100644
--- a/drivers/acpi/sbs.c
+++ b/drivers/acpi/sbs.c
@@ -670,7 +670,7 @@ static int acpi_sbs_add(struct acpi_device *device)
 	if (!sbs_manager_broken) {
 		result = acpi_manager_get_info(sbs);
 		if (!result) {
-			sbs->manager_present = 0;
+			sbs->manager_present = 1;
 			for (id = 0; id < MAX_SBS_BAT; ++id)
 				if ((sbs->batteries_supported & (1 << id)))
 					acpi_battery_add(sbs, id);
diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c
index 26e5b506052..bf034f8b7c1 100644
--- a/drivers/acpi/sbshc.c
+++ b/drivers/acpi/sbshc.c
@@ -14,6 +14,7 @@
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
+#include <linux/dmi.h>
 #include "sbshc.h"
 
 #define PREFIX "ACPI: "
@@ -87,6 +88,8 @@ enum acpi_smb_offset {
 	ACPI_SMB_ALARM_DATA = 0x26,	/* 2 bytes alarm data */
 };
 
+static bool macbook;
+
 static inline int smb_hc_read(struct acpi_smb_hc *hc, u8 address, u8 *data)
 {
 	return ec_read(hc->offset + address, data);
@@ -132,6 +135,8 @@ static int acpi_smbus_transaction(struct acpi_smb_hc *hc, u8 protocol,
 	}
 
 	mutex_lock(&hc->lock);
+	if (macbook)
+		udelay(5);
 	if (smb_hc_read(hc, ACPI_SMB_PROTOCOL, &temp))
 		goto end;
 	if (temp) {
@@ -257,12 +262,29 @@ extern int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit,
 			      acpi_handle handle, acpi_ec_query_func func,
 			      void *data);
 
+static int macbook_dmi_match(const struct dmi_system_id *d)
+{
+	pr_debug("Detected MacBook, enabling workaround\n");
+	macbook = true;
+	return 0;
+}
+
+static struct dmi_system_id acpi_smbus_dmi_table[] = {
+	{ macbook_dmi_match, "Apple MacBook", {
+	  DMI_MATCH(DMI_BOARD_VENDOR, "Apple"),
+	  DMI_MATCH(DMI_PRODUCT_NAME, "MacBook") },
+	},
+	{ },
+};
+
 static int acpi_smbus_hc_add(struct acpi_device *device)
 {
 	int status;
 	unsigned long long val;
 	struct acpi_smb_hc *hc;
 
+	dmi_check_system(acpi_smbus_dmi_table);
+
 	if (!device)
 		return -EINVAL;
 
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 0476e90b209..01aa1c7f4e9 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -251,7 +251,11 @@ bool acpi_scan_is_offline(struct acpi_device *adev, bool uevent)
 	struct acpi_device_physical_node *pn;
 	bool offline = true;
 
-	mutex_lock(&adev->physical_node_lock);
+	/*
+	 * acpi_container_offline() calls this for all of the container's
+	 * children under the container's physical_node_lock lock.
+	 */
+	mutex_lock_nested(&adev->physical_node_lock, SINGLE_DEPTH_NESTING);
 
 	list_for_each_entry(pn, &adev->physical_node_list, node)
 		if (device_supports_offline(pn->dev) && !pn->dev->offline) {
@@ -909,7 +913,7 @@ static void acpi_free_power_resources_lists(struct acpi_device *device)
 	if (device->wakeup.flags.valid)
 		acpi_power_resources_list_free(&device->wakeup.resources);
 
-	if (!device->flags.power_manageable)
+	if (!device->power.flags.power_resources)
 		return;
 
 	for (i = ACPI_STATE_D0; i <= ACPI_STATE_D3_HOT; i++) {
@@ -922,6 +926,7 @@ static void acpi_device_release(struct device *dev)
 {
 	struct acpi_device *acpi_dev = to_acpi_device(dev);
 
+	acpi_free_properties(acpi_dev);
 	acpi_free_pnp_ids(&acpi_dev->pnp);
 	acpi_free_power_resources_lists(acpi_dev);
 	kfree(acpi_dev);
@@ -1631,10 +1636,8 @@ static void acpi_bus_get_power_flags(struct acpi_device *device)
 			device->power.flags.power_resources)
 		device->power.states[ACPI_STATE_D3_COLD].flags.os_accessible = 1;
 
-	if (acpi_bus_init_power(device)) {
-		acpi_free_power_resources_lists(device);
+	if (acpi_bus_init_power(device))
 		device->flags.power_manageable = 0;
-	}
 }
 
 static void acpi_bus_get_flags(struct acpi_device *device)
@@ -1926,6 +1929,7 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle,
 	acpi_set_device_status(device, sta);
 	acpi_device_get_busid(device);
 	acpi_set_pnp_ids(handle, &device->pnp, type);
+	acpi_init_properties(device);
 	acpi_bus_get_flags(device);
 	device->flags.match_driver = false;
 	device->flags.initialized = true;
@@ -2202,13 +2206,18 @@ static void acpi_bus_attach(struct acpi_device *device)
 	/* Skip devices that are not present. */
 	if (!acpi_device_is_present(device)) {
 		device->flags.visited = false;
+		device->flags.power_manageable = 0;
 		return;
 	}
 	if (device->handler)
 		goto ok;
 
 	if (!device->flags.initialized) {
-		acpi_bus_update_power(device, NULL);
+		device->flags.power_manageable =
+			device->power.states[ACPI_STATE_D0].flags.valid;
+		if (acpi_bus_init_power(device))
+			device->flags.power_manageable = 0;
+
 		device->flags.initialized = true;
 	}
 	device->flags.visited = false;
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index d24fa1964eb..6d4e44ea74a 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -800,7 +800,8 @@ static int acpi_thermal_cooling_device_cb(struct thermal_zone_device *thermal,
 				result =
 					thermal_zone_bind_cooling_device
 					(thermal, trip, cdev,
-					 THERMAL_NO_LIMIT, THERMAL_NO_LIMIT);
+					 THERMAL_NO_LIMIT, THERMAL_NO_LIMIT,
+					 THERMAL_WEIGHT_DEFAULT);
 			else
 				result =
 					thermal_zone_unbind_cooling_device
@@ -824,7 +825,8 @@ static int acpi_thermal_cooling_device_cb(struct thermal_zone_device *thermal,
 			if (bind)
 				result = thermal_zone_bind_cooling_device
 					(thermal, trip, cdev,
-					 THERMAL_NO_LIMIT, THERMAL_NO_LIMIT);
+					 THERMAL_NO_LIMIT, THERMAL_NO_LIMIT,
+					 THERMAL_WEIGHT_DEFAULT);
 			else
 				result = thermal_zone_unbind_cooling_device
 					(thermal, trip, cdev);
@@ -841,7 +843,8 @@ static int acpi_thermal_cooling_device_cb(struct thermal_zone_device *thermal,
 				result = thermal_zone_bind_cooling_device
 						(thermal, THERMAL_TRIPS_NONE,
 						 cdev, THERMAL_NO_LIMIT,
-						 THERMAL_NO_LIMIT);
+						 THERMAL_NO_LIMIT,
+						 THERMAL_WEIGHT_DEFAULT);
 			else
 				result = thermal_zone_unbind_cooling_device
 						(thermal, THERMAL_TRIPS_NONE,
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index 9d75ead2a1f..ff7bc22b613 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -155,6 +155,7 @@ struct acpi_video_bus {
 	u8 dos_setting;
 	struct acpi_video_enumerated_device *attached_array;
 	u8 attached_count;
+	u8 child_count;
 	struct acpi_video_bus_cap cap;
 	struct acpi_video_bus_flags flags;
 	struct list_head video_device_list;
@@ -504,6 +505,23 @@ static struct dmi_system_id video_dmi_table[] __initdata = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "HP ENVY 15 Notebook PC"),
 		},
 	},
+
+	{
+	 .callback = video_disable_native_backlight,
+	 .ident = "SAMSUNG 870Z5E/880Z5E/680Z5E",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "870Z5E/880Z5E/680Z5E"),
+		},
+	},
+	{
+	 .callback = video_disable_native_backlight,
+	 .ident = "SAMSUNG 370R4E/370R4V/370R5E/3570RE/370R5V",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "370R4E/370R4V/370R5E/3570RE/370R5V"),
+		},
+	},
 	{}
 };
 
@@ -1159,8 +1177,12 @@ static bool acpi_video_device_in_dod(struct acpi_video_device *device)
 	struct acpi_video_bus *video = device->video;
 	int i;
 
-	/* If we have a broken _DOD, no need to test */
-	if (!video->attached_count)
+	/*
+	 * If we have a broken _DOD or we have more than 8 output devices
+	 * under the graphics controller node that we can't proper deal with
+	 * in the operation region code currently, no need to test.
+	 */
+	if (!video->attached_count || video->child_count > 8)
 		return true;
 
 	for (i = 0; i < video->attached_count; i++) {
@@ -1413,6 +1435,7 @@ acpi_video_bus_get_devices(struct acpi_video_bus *video,
 			dev_err(&dev->dev, "Can't attach device\n");
 			break;
 		}
+		video->child_count++;
 	}
 	return status;
 }
@@ -2101,6 +2124,17 @@ EXPORT_SYMBOL(acpi_video_unregister_backlight);
 
 static int __init acpi_video_init(void)
 {
+	/*
+	 * Let the module load even if ACPI is disabled (e.g. due to
+	 * a broken BIOS) so that i915.ko can still be loaded on such
+	 * old systems without an AcpiOpRegion.
+	 *
+	 * acpi_video_register() will report -ENODEV later as well due
+	 * to acpi_disabled when i915.ko tries to register itself afterwards.
+	 */
+	if (acpi_disabled)
+		return 0;
+
 	dmi_check_system(video_dmi_table);
 
 	if (intel_opregion_present())
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index 47bbdc1b5be..a4ac490dd78 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -336,7 +336,7 @@ int amba_device_add(struct amba_device *dev, struct resource *parent)
 
 		amba_put_disable_pclk(dev);
 
-		if (cid == AMBA_CID)
+		if (cid == AMBA_CID || cid == CORESIGHT_CID)
 			dev->periphid = pid;
 
 		if (!dev->periphid)
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 49f1e689058..73187771836 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -66,6 +66,7 @@ enum board_ids {
 	board_ahci_yes_fbs,
 
 	/* board IDs for specific chipsets in alphabetical order */
+	board_ahci_avn,
 	board_ahci_mcp65,
 	board_ahci_mcp77,
 	board_ahci_mcp89,
@@ -84,6 +85,8 @@ enum board_ids {
 static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
 static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class,
 				 unsigned long deadline);
+static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class,
+			      unsigned long deadline);
 static void ahci_mcp89_apple_enable(struct pci_dev *pdev);
 static bool is_mcp89_apple(struct pci_dev *pdev);
 static int ahci_p5wdh_hardreset(struct ata_link *link, unsigned int *class,
@@ -107,6 +110,11 @@ static struct ata_port_operations ahci_p5wdh_ops = {
 	.hardreset		= ahci_p5wdh_hardreset,
 };
 
+static struct ata_port_operations ahci_avn_ops = {
+	.inherits		= &ahci_ops,
+	.hardreset		= ahci_avn_hardreset,
+};
+
 static const struct ata_port_info ahci_port_info[] = {
 	/* by features */
 	[board_ahci] = {
@@ -151,6 +159,12 @@ static const struct ata_port_info ahci_port_info[] = {
 		.port_ops	= &ahci_ops,
 	},
 	/* by chipsets */
+	[board_ahci_avn] = {
+		.flags		= AHCI_FLAG_COMMON,
+		.pio_mask	= ATA_PIO4,
+		.udma_mask	= ATA_UDMA6,
+		.port_ops	= &ahci_avn_ops,
+	},
 	[board_ahci_mcp65] = {
 		AHCI_HFLAGS	(AHCI_HFLAG_NO_FPDMA_AA | AHCI_HFLAG_NO_PMP |
 				 AHCI_HFLAG_YES_NCQ),
@@ -290,14 +304,14 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x1f27), board_ahci }, /* Avoton RAID */
 	{ PCI_VDEVICE(INTEL, 0x1f2e), board_ahci }, /* Avoton RAID */
 	{ PCI_VDEVICE(INTEL, 0x1f2f), board_ahci }, /* Avoton RAID */
-	{ PCI_VDEVICE(INTEL, 0x1f32), board_ahci }, /* Avoton AHCI */
-	{ PCI_VDEVICE(INTEL, 0x1f33), board_ahci }, /* Avoton AHCI */
-	{ PCI_VDEVICE(INTEL, 0x1f34), board_ahci }, /* Avoton RAID */
-	{ PCI_VDEVICE(INTEL, 0x1f35), board_ahci }, /* Avoton RAID */
-	{ PCI_VDEVICE(INTEL, 0x1f36), board_ahci }, /* Avoton RAID */
-	{ PCI_VDEVICE(INTEL, 0x1f37), board_ahci }, /* Avoton RAID */
-	{ PCI_VDEVICE(INTEL, 0x1f3e), board_ahci }, /* Avoton RAID */
-	{ PCI_VDEVICE(INTEL, 0x1f3f), board_ahci }, /* Avoton RAID */
+	{ PCI_VDEVICE(INTEL, 0x1f32), board_ahci_avn }, /* Avoton AHCI */
+	{ PCI_VDEVICE(INTEL, 0x1f33), board_ahci_avn }, /* Avoton AHCI */
+	{ PCI_VDEVICE(INTEL, 0x1f34), board_ahci_avn }, /* Avoton RAID */
+	{ PCI_VDEVICE(INTEL, 0x1f35), board_ahci_avn }, /* Avoton RAID */
+	{ PCI_VDEVICE(INTEL, 0x1f36), board_ahci_avn }, /* Avoton RAID */
+	{ PCI_VDEVICE(INTEL, 0x1f37), board_ahci_avn }, /* Avoton RAID */
+	{ PCI_VDEVICE(INTEL, 0x1f3e), board_ahci_avn }, /* Avoton RAID */
+	{ PCI_VDEVICE(INTEL, 0x1f3f), board_ahci_avn }, /* Avoton RAID */
 	{ PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Wellsburg RAID */
 	{ PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* Wellsburg RAID */
 	{ PCI_VDEVICE(INTEL, 0x8d02), board_ahci }, /* Wellsburg AHCI */
@@ -671,6 +685,79 @@ static int ahci_p5wdh_hardreset(struct ata_link *link, unsigned int *class,
 	return rc;
 }
 
+/*
+ * ahci_avn_hardreset - attempt more aggressive recovery of Avoton ports.
+ *
+ * It has been observed with some SSDs that the timing of events in the
+ * link synchronization phase can leave the port in a state that can not
+ * be recovered by a SATA-hard-reset alone.  The failing signature is
+ * SStatus.DET stuck at 1 ("Device presence detected but Phy
+ * communication not established").  It was found that unloading and
+ * reloading the driver when this problem occurs allows the drive
+ * connection to be recovered (DET advanced to 0x3).  The critical
+ * component of reloading the driver is that the port state machines are
+ * reset by bouncing "port enable" in the AHCI PCS configuration
+ * register.  So, reproduce that effect by bouncing a port whenever we
+ * see DET==1 after a reset.
+ */
+static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class,
+			      unsigned long deadline)
+{
+	const unsigned long *timing = sata_ehc_deb_timing(&link->eh_context);
+	struct ata_port *ap = link->ap;
+	struct ahci_port_priv *pp = ap->private_data;
+	struct ahci_host_priv *hpriv = ap->host->private_data;
+	u8 *d2h_fis = pp->rx_fis + RX_FIS_D2H_REG;
+	unsigned long tmo = deadline - jiffies;
+	struct ata_taskfile tf;
+	bool online;
+	int rc, i;
+
+	DPRINTK("ENTER\n");
+
+	ahci_stop_engine(ap);
+
+	for (i = 0; i < 2; i++) {
+		u16 val;
+		u32 sstatus;
+		int port = ap->port_no;
+		struct ata_host *host = ap->host;
+		struct pci_dev *pdev = to_pci_dev(host->dev);
+
+		/* clear D2H reception area to properly wait for D2H FIS */
+		ata_tf_init(link->device, &tf);
+		tf.command = ATA_BUSY;
+		ata_tf_to_fis(&tf, 0, 0, d2h_fis);
+
+		rc = sata_link_hardreset(link, timing, deadline, &online,
+				ahci_check_ready);
+
+		if (sata_scr_read(link, SCR_STATUS, &sstatus) != 0 ||
+				(sstatus & 0xf) != 1)
+			break;
+
+		ata_link_printk(link, KERN_INFO, "avn bounce port%d\n",
+				port);
+
+		pci_read_config_word(pdev, 0x92, &val);
+		val &= ~(1 << port);
+		pci_write_config_word(pdev, 0x92, val);
+		ata_msleep(ap, 1000);
+		val |= 1 << port;
+		pci_write_config_word(pdev, 0x92, val);
+		deadline += tmo;
+	}
+
+	hpriv->start_engine(ap);
+
+	if (online)
+		*class = ahci_dev_classify(ap);
+
+	DPRINTK("EXIT, rc=%d, class=%u\n", rc, *class);
+	return rc;
+}
+
+
 #ifdef CONFIG_PM
 static int ahci_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg)
 {
diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c
index 68672d2692e..e3267b78b20 100644
--- a/drivers/ata/ahci_mvebu.c
+++ b/drivers/ata/ahci_mvebu.c
@@ -43,7 +43,7 @@ static void ahci_mvebu_mbus_config(struct ahci_host_priv *hpriv,
 		writel((cs->mbus_attr << 8) |
 		       (dram->mbus_dram_target_id << 4) | 1,
 		       hpriv->mmio + AHCI_WINDOW_CTRL(i));
-		writel(cs->base, hpriv->mmio + AHCI_WINDOW_BASE(i));
+		writel(cs->base >> 16, hpriv->mmio + AHCI_WINDOW_BASE(i));
 		writel(((cs->size - 1) & 0xffff0000),
 		       hpriv->mmio + AHCI_WINDOW_SIZE(i));
 	}
diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c
index 0f8538f238b..0ffd3c930be 100644
--- a/drivers/ata/ahci_xgene.c
+++ b/drivers/ata/ahci_xgene.c
@@ -188,7 +188,7 @@ static unsigned int xgene_ahci_read_id(struct ata_device *dev,
 	 *
 	 * Clear reserved bit 8 (DEVSLP bit) as we don't support DEVSLP
 	 */
-	id[ATA_ID_FEATURE_SUPP] &= ~(1 << 8);
+	id[ATA_ID_FEATURE_SUPP] &= cpu_to_le16(~(1 << 8));
 
 	return 0;
 }
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 97683e45ab0..de88999521b 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -1707,8 +1707,7 @@ static void ahci_handle_port_interrupt(struct ata_port *ap,
 	if (unlikely(resetting))
 		status &= ~PORT_IRQ_BAD_PMP;
 
-	/* if LPM is enabled, PHYRDY doesn't mean anything */
-	if (ap->link.lpm_policy > ATA_LPM_MAX_POWER) {
+	if (sata_lpm_ignore_phy_events(&ap->link)) {
 		status &= ~PORT_IRQ_PHYRDY;
 		ahci_scr_write(&ap->link, SCR_ERROR, SERR_PHYRDY_CHG);
 	}
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index c5ba15af87d..98dc0dc605b 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4174,9 +4174,10 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "ST3320[68]13AS",	"SD1[5-9]",	ATA_HORKAGE_NONCQ |
 						ATA_HORKAGE_FIRMWARE_WARN },
 
-	/* Seagate Momentus SpinPoint M8 seem to have FPMDA_AA issues */
+	/* drives which fail FPDMA_AA activation (some may freeze afterwards) */
 	{ "ST1000LM024 HN-M101MBB", "2AR10001",	ATA_HORKAGE_BROKEN_FPDMA_AA },
 	{ "ST1000LM024 HN-M101MBB", "2BA30001",	ATA_HORKAGE_BROKEN_FPDMA_AA },
+	{ "VB0250EAVER",	"HPG7",		ATA_HORKAGE_BROKEN_FPDMA_AA },
 
 	/* Blacklist entries taken from Silicon Image 3124/3132
 	   Windows driver .inf file - also several Linux problem reports */
@@ -4230,6 +4231,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "Micron_M550*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
 	{ "Crucial_CT*M550SSD*",	NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
 
+	/* devices that don't properly handle TRIM commands */
+	{ "SuperSSpeed S238*",		NULL,	ATA_HORKAGE_NOTRIM, },
+
 	/*
 	 * Some WD SATA-I drives spin up and down erratically when the link
 	 * is put into the slumber mode.  We don't have full list of the
@@ -4467,7 +4471,8 @@ static unsigned int ata_dev_set_xfermode(struct ata_device *dev)
 	else /* In the ancient relic department - skip all of this */
 		return 0;
 
-	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0);
+	/* On some disks, this command causes spin-up, so we need longer timeout */
+	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 15000);
 
 	DPRINTK("EXIT, err_mask=%x\n", err_mask);
 	return err_mask;
@@ -4740,7 +4745,10 @@ static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap)
 		return NULL;
 
 	for (i = 0, tag = ap->last_tag + 1; i < max_queue; i++, tag++) {
-		tag = tag < max_queue ? tag : 0;
+		if (ap->flags & ATA_FLAG_LOWTAG)
+			tag = i;
+		else
+			tag = tag < max_queue ? tag : 0;
 
 		/* the last tag is reserved for internal command. */
 		if (tag == ATA_TAG_INTERNAL)
@@ -6744,6 +6752,38 @@ u32 ata_wait_register(struct ata_port *ap, void __iomem *reg, u32 mask, u32 val,
 	return tmp;
 }
 
+/**
+ *	sata_lpm_ignore_phy_events - test if PHY event should be ignored
+ *	@link: Link receiving the event
+ *
+ *	Test whether the received PHY event has to be ignored or not.
+ *
+ *	LOCKING:
+ *	None:
+ *
+ *	RETURNS:
+ *	True if the event has to be ignored.
+ */
+bool sata_lpm_ignore_phy_events(struct ata_link *link)
+{
+	unsigned long lpm_timeout = link->last_lpm_change +
+				    msecs_to_jiffies(ATA_TMOUT_SPURIOUS_PHY);
+
+	/* if LPM is enabled, PHYRDY doesn't mean anything */
+	if (link->lpm_policy > ATA_LPM_MAX_POWER)
+		return true;
+
+	/* ignore the first PHY event after the LPM policy changed
+	 * as it is might be spurious
+	 */
+	if ((link->flags & ATA_LFLAG_CHANGED) &&
+	    time_before(jiffies, lpm_timeout))
+		return true;
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(sata_lpm_ignore_phy_events);
+
 /*
  * Dummy port_ops
  */
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index dad83df555c..4ec95b76f6a 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -3490,6 +3490,9 @@ static int ata_eh_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 		}
 	}
 
+	link->last_lpm_change = jiffies;
+	link->flags |= ATA_LFLAG_CHANGED;
+
 	return 0;
 
 fail:
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 0586f66d70f..d6ff64248c2 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -2514,7 +2514,8 @@ static unsigned int ata_scsiop_read_cap(struct ata_scsi_args *args, u8 *rbuf)
 		rbuf[14] = (lowest_aligned >> 8) & 0x3f;
 		rbuf[15] = lowest_aligned;
 
-		if (ata_id_has_trim(args->id)) {
+		if (ata_id_has_trim(args->id) &&
+		    !(dev->horkage & ATA_HORKAGE_NOTRIM)) {
 			rbuf[14] |= 0x80; /* TPE */
 
 			if (ata_id_has_zero_after_trim(args->id))
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index db90aa35cb7..2e86e3b8526 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -1333,7 +1333,19 @@ void ata_sff_flush_pio_task(struct ata_port *ap)
 	DPRINTK("ENTER\n");
 
 	cancel_delayed_work_sync(&ap->sff_pio_task);
+
+	/*
+	 * We wanna reset the HSM state to IDLE.  If we do so without
+	 * grabbing the port lock, critical sections protected by it which
+	 * expect the HSM state to stay stable may get surprised.  For
+	 * example, we may set IDLE in between the time
+	 * __ata_sff_port_intr() checks for HSM_ST_IDLE and before it calls
+	 * ata_sff_hsm_move() causing ata_sff_hsm_move() to BUG().
+	 */
+	spin_lock_irq(ap->lock);
 	ap->hsm_task_state = HSM_ST_IDLE;
+	spin_unlock_irq(ap->lock);
+
 	ap->sff_pio_task_link = NULL;
 
 	if (ata_msg_ctl(ap))
diff --git a/drivers/ata/pata_octeon_cf.c b/drivers/ata/pata_octeon_cf.c
index 2a97d3a531e..afc252f523f 100644
--- a/drivers/ata/pata_octeon_cf.c
+++ b/drivers/ata/pata_octeon_cf.c
@@ -1053,7 +1053,7 @@ static struct of_device_id octeon_cf_match[] = {
 	},
 	{},
 };
-MODULE_DEVICE_TABLE(of, octeon_i2c_match);
+MODULE_DEVICE_TABLE(of, octeon_cf_match);
 
 static struct platform_driver octeon_cf_driver = {
 	.probe		= octeon_cf_probe,
diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c
index 0bb2cabd219..4ebaa1e7b2d 100644
--- a/drivers/ata/sata_dwc_460ex.c
+++ b/drivers/ata/sata_dwc_460ex.c
@@ -797,7 +797,7 @@ static int dma_dwc_init(struct sata_dwc_device *hsdev, int irq)
 	if (err) {
 		dev_err(host_pvt.dwc_dev, "%s: dma_request_interrupts returns"
 			" %d\n", __func__, err);
-		goto error_out;
+		return err;
 	}
 
 	/* Enabe DMA */
@@ -808,11 +808,6 @@ static int dma_dwc_init(struct sata_dwc_device *hsdev, int irq)
 		sata_dma_regs);
 
 	return 0;
-
-error_out:
-	dma_dwc_exit(hsdev);
-
-	return err;
 }
 
 static int sata_dwc_scr_read(struct ata_link *link, unsigned int scr, u32 *val)
@@ -1662,7 +1657,7 @@ static int sata_dwc_probe(struct platform_device *ofdev)
 	char *ver = (char *)&versionr;
 	u8 *base = NULL;
 	int err = 0;
-	int irq, rc;
+	int irq;
 	struct ata_host *host;
 	struct ata_port_info pi = sata_dwc_port_info[0];
 	const struct ata_port_info *ppi[] = { &pi, NULL };
@@ -1725,7 +1720,7 @@ static int sata_dwc_probe(struct platform_device *ofdev)
 	if (irq == NO_IRQ) {
 		dev_err(&ofdev->dev, "no SATA DMA irq\n");
 		err = -ENODEV;
-		goto error_out;
+		goto error_iomap;
 	}
 
 	/* Get physical SATA DMA register base address */
@@ -1734,14 +1729,16 @@ static int sata_dwc_probe(struct platform_device *ofdev)
 		dev_err(&ofdev->dev, "ioremap failed for AHBDMA register"
 			" address\n");
 		err = -ENODEV;
-		goto error_out;
+		goto error_iomap;
 	}
 
 	/* Save dev for later use in dev_xxx() routines */
 	host_pvt.dwc_dev = &ofdev->dev;
 
 	/* Initialize AHB DMAC */
-	dma_dwc_init(hsdev, irq);
+	err = dma_dwc_init(hsdev, irq);
+	if (err)
+		goto error_dma_iomap;
 
 	/* Enable SATA Interrupts */
 	sata_dwc_enable_interrupts(hsdev);
@@ -1759,9 +1756,8 @@ static int sata_dwc_probe(struct platform_device *ofdev)
 	 * device discovery process, invoking our port_start() handler &
 	 * error_handler() to execute a dummy Softreset EH session
 	 */
-	rc = ata_host_activate(host, irq, sata_dwc_isr, 0, &sata_dwc_sht);
-
-	if (rc != 0)
+	err = ata_host_activate(host, irq, sata_dwc_isr, 0, &sata_dwc_sht);
+	if (err)
 		dev_err(&ofdev->dev, "failed to activate host");
 
 	dev_set_drvdata(&ofdev->dev, host);
@@ -1770,7 +1766,8 @@ static int sata_dwc_probe(struct platform_device *ofdev)
 error_out:
 	/* Free SATA DMA resources */
 	dma_dwc_exit(hsdev);
-
+error_dma_iomap:
+	iounmap((void __iomem *)host_pvt.sata_dma_regs);
 error_iomap:
 	iounmap(base);
 error_kmalloc:
@@ -1791,6 +1788,7 @@ static int sata_dwc_remove(struct platform_device *ofdev)
 	/* Free SATA DMA resources */
 	dma_dwc_exit(hsdev);
 
+	iounmap((void __iomem *)host_pvt.sata_dma_regs);
 	iounmap(hsdev->reg_base);
 	kfree(hsdev);
 	kfree(host);
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index d81b20ddb52..ea655949023 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -246,7 +246,7 @@ enum {
 	/* host flags */
 	SIL24_COMMON_FLAGS	= ATA_FLAG_SATA | ATA_FLAG_PIO_DMA |
 				  ATA_FLAG_NCQ | ATA_FLAG_ACPI_SATA |
-				  ATA_FLAG_AN | ATA_FLAG_PMP,
+				  ATA_FLAG_AN | ATA_FLAG_PMP | ATA_FLAG_LOWTAG,
 	SIL24_FLAG_PCIX_IRQ_WOC	= (1 << 24), /* IRQ loss errata on PCI-X */
 
 	IRQ_STAT_4PORTS		= 0xf,
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index df04227d00c..c7d273ba567 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -220,8 +220,13 @@ config GENERIC_CPU_DEVICES
 	bool
 	default n
 
+config HAVE_CPU_AUTOPROBE
+	def_bool ARCH_HAS_CPU_AUTOPROBE
+
 config GENERIC_CPU_AUTOPROBE
 	bool
+	depends on !ARCH_HAS_CPU_AUTOPROBE
+	select HAVE_CPU_AUTOPROBE
 
 config SOC_BUS
 	bool
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 6922cd6850a..53c3fe1aeb2 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -4,7 +4,7 @@ obj-y			:= component.o core.o bus.o dd.o syscore.o \
 			   driver.o class.o platform.o \
 			   cpu.o firmware.o init.o map.o devres.o \
 			   attribute_container.o transport_class.o \
-			   topology.o container.o
+			   topology.o container.o property.o
 obj-$(CONFIG_DEVTMPFS)	+= devtmpfs.o
 obj-$(CONFIG_DMA_CMA) += dma-contiguous.o
 obj-y			+= power/
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 83e910a5756..79bc203f51e 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -254,13 +254,15 @@ static ssize_t store_drivers_probe(struct bus_type *bus,
 				   const char *buf, size_t count)
 {
 	struct device *dev;
+	int err = -EINVAL;
 
 	dev = bus_find_device_by_name(bus, NULL, buf);
 	if (!dev)
 		return -ENODEV;
-	if (bus_rescan_devices_helper(dev, NULL) != 0)
-		return -EINVAL;
-	return count;
+	if (bus_rescan_devices_helper(dev, NULL) == 0)
+		err = count;
+	put_device(dev);
+	return err;
 }
 
 static struct device *next_device(struct klist_iter *i)
@@ -513,11 +515,11 @@ int bus_add_device(struct device *dev)
 			goto out_put;
 		error = device_add_groups(dev, bus->dev_groups);
 		if (error)
-			goto out_groups;
+			goto out_id;
 		error = sysfs_create_link(&bus->p->devices_kset->kobj,
 						&dev->kobj, dev_name(dev));
 		if (error)
-			goto out_id;
+			goto out_groups;
 		error = sysfs_create_link(&dev->kobj,
 				&dev->bus->p->subsys.kobj, "subsystem");
 		if (error)
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 006b1bc5297..8a38bf8c792 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -287,6 +287,7 @@ static void cpu_device_release(struct device *dev)
 	 */
 }
 
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
 #ifdef CONFIG_GENERIC_CPU_AUTOPROBE
 static ssize_t print_cpu_modalias(struct device *dev,
 				  struct device_attribute *attr,
@@ -309,6 +310,9 @@ static ssize_t print_cpu_modalias(struct device *dev,
 	buf[n++] = '\n';
 	return n;
 }
+#else
+#define print_cpu_modalias	arch_print_cpu_modalias
+#endif
 
 static int cpu_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
@@ -342,7 +346,7 @@ int register_cpu(struct cpu *cpu, int num)
 	cpu->dev.offline_disabled = !cpu->hotpluggable;
 	cpu->dev.offline = !cpu_online(num);
 	cpu->dev.of_node = of_get_cpu_node(num, NULL);
-#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
 	cpu->dev.bus->uevent = cpu_uevent;
 #endif
 	cpu->dev.groups = common_cpu_attr_groups;
@@ -366,7 +370,7 @@ struct device *get_cpu_device(unsigned cpu)
 }
 EXPORT_SYMBOL_GPL(get_cpu_device);
 
-#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
 static DEVICE_ATTR(modalias, 0444, print_cpu_modalias, NULL);
 #endif
 
@@ -380,7 +384,7 @@ static struct attribute *cpu_root_attrs[] = {
 	&cpu_attrs[2].attr.attr,
 	&dev_attr_kernel_max.attr,
 	&dev_attr_offline.attr,
-#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
 	&dev_attr_modalias.attr,
 #endif
 	NULL
diff --git a/drivers/base/dma-mapping.c b/drivers/base/dma-mapping.c
index 9e8bbdd470c..e5127e50af5 100644
--- a/drivers/base/dma-mapping.c
+++ b/drivers/base/dma-mapping.c
@@ -228,9 +228,19 @@ EXPORT_SYMBOL(dmam_release_declared_memory);
 int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
 		 void *cpu_addr, dma_addr_t handle, size_t size)
 {
-	struct page *page = virt_to_page(cpu_addr);
+	struct page *page;
 	int ret;
 
+	if (virt_addr_valid(cpu_addr))
+		page = virt_to_page(cpu_addr);
+	else {
+#ifdef dma_to_phys
+		page = pfn_to_page(dma_to_phys(dev, handle) >> PAGE_SHIFT);
+#else
+		BUG();
+#endif
+	}
+
 	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
 	if (unlikely(ret))
 		return ret;
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 3d785ebb48d..50e8bd00e43 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -545,10 +545,8 @@ static void fw_dev_release(struct device *dev)
 	kfree(fw_priv);
 }
 
-static int firmware_uevent(struct device *dev, struct kobj_uevent_env *env)
+static int do_firmware_uevent(struct firmware_priv *fw_priv, struct kobj_uevent_env *env)
 {
-	struct firmware_priv *fw_priv = to_firmware_priv(dev);
-
 	if (add_uevent_var(env, "FIRMWARE=%s", fw_priv->buf->fw_id))
 		return -ENOMEM;
 	if (add_uevent_var(env, "TIMEOUT=%i", loading_timeout))
@@ -559,6 +557,18 @@ static int firmware_uevent(struct device *dev, struct kobj_uevent_env *env)
 	return 0;
 }
 
+static int firmware_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	struct firmware_priv *fw_priv = to_firmware_priv(dev);
+	int err = 0;
+
+	mutex_lock(&fw_lock);
+	if (fw_priv->buf)
+		err = do_firmware_uevent(fw_priv, env);
+	mutex_unlock(&fw_lock);
+	return err;
+}
+
 static struct class firmware_class = {
 	.name		= "firmware",
 	.class_attrs	= firmware_class_attrs,
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index b2afc29403f..360272cd454 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -101,6 +101,15 @@ int platform_get_irq(struct platform_device *dev, unsigned int num)
 	}
 
 	r = platform_get_resource(dev, IORESOURCE_IRQ, num);
+	/*
+	 * The resources may pass trigger flags to the irqs that need
+	 * to be set up. It so happens that the trigger flags for
+	 * IORESOURCE_BITS correspond 1-to-1 to the IRQF_TRIGGER*
+	 * settings.
+	 */
+	if (r && r->flags & IORESOURCE_BITS)
+		irqd_set_trigger_type(irq_get_irq_data(r->start),
+				      r->flags & IORESOURCE_BITS);
 
 	return r ? r->start : -ENXIO;
 #endif
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 9717d5f2013..dcf394f21df 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -32,6 +32,7 @@
 #include <linux/cpufreq.h>
 #include <linux/cpuidle.h>
 #include <linux/timer.h>
+#include <linux/wakeup_reason.h>
 
 #include "../base.h"
 #include "power.h"
@@ -58,6 +59,12 @@ struct suspend_stats suspend_stats;
 static DEFINE_MUTEX(dpm_list_mtx);
 static pm_message_t pm_transition;
 
+static void dpm_drv_timeout(unsigned long data);
+struct dpm_drv_wd_data {
+	struct device *dev;
+	struct task_struct *tsk;
+};
+
 static int async_error;
 
 static char *pm_verb(int event)
@@ -828,6 +835,30 @@ static void async_resume(void *data, async_cookie_t cookie)
 }
 
 /**
+ *	dpm_drv_timeout - Driver suspend / resume watchdog handler
+ *	@data: struct device which timed out
+ *
+ * 	Called when a driver has timed out suspending or resuming.
+ * 	There's not much we can do here to recover so
+ * 	BUG() out for a crash-dump
+ *
+ */
+static void dpm_drv_timeout(unsigned long data)
+{
+	struct dpm_drv_wd_data *wd_data = (void *)data;
+	struct device *dev = wd_data->dev;
+	struct task_struct *tsk = wd_data->tsk;
+
+	printk(KERN_EMERG "**** DPM device timeout: %s (%s)\n", dev_name(dev),
+	       (dev->driver ? dev->driver->name : "no driver"));
+
+	printk(KERN_EMERG "dpm suspend stack:\n");
+	show_stack(tsk, NULL);
+
+	BUG();
+}
+
+/**
  * dpm_resume - Execute "resume" callbacks for non-sysdev devices.
  * @state: PM transition of the system being carried out.
  *
@@ -1336,6 +1367,9 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 	pm_callback_t callback = NULL;
 	char *info = NULL;
 	int error = 0;
+	struct timer_list timer;
+	struct dpm_drv_wd_data data;
+	char suspend_abort[MAX_SUSPEND_ABORT_LEN];
 	DECLARE_DPM_WATCHDOG_ON_STACK(wd);
 
 	dpm_wait_for_children(dev, async);
@@ -1353,12 +1387,23 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 		pm_wakeup_event(dev, 0);
 
 	if (pm_wakeup_pending()) {
+		pm_get_active_wakeup_sources(suspend_abort,
+			MAX_SUSPEND_ABORT_LEN);
+		log_suspend_abort_reason(suspend_abort);
 		async_error = -EBUSY;
 		goto Complete;
 	}
 
 	if (dev->power.syscore)
 		goto Complete;
+	
+	data.dev = dev;
+	data.tsk = get_current();
+	init_timer_on_stack(&timer);
+	timer.expires = jiffies + HZ * 12;
+	timer.function = dpm_drv_timeout;
+	timer.data = (unsigned long)&data;
+	add_timer(&timer);
 
 	if (dev->power.direct_complete) {
 		if (pm_runtime_status_suspended(dev)) {
@@ -1439,6 +1484,9 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 	device_unlock(dev);
 	dpm_watchdog_clear(&wd);
 
+	del_timer_sync(&timer);
+	destroy_timer_on_stack(&timer);
+
  Complete:
 	complete_all(&dev->power.completion);
 	if (error)
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
index 89ced955faf..84b16d47cf5 100644
--- a/drivers/base/power/opp.c
+++ b/drivers/base/power/opp.c
@@ -164,6 +164,41 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_voltage);
 
 /**
+ * dev_pm_opp_get_voltage_always() - Gets the voltage corresponding to an opp
+ * @opp:	opp for which voltage has to be returned for
+ *
+ * This function is similar to dev_pm_opp_get_voltage() except that it
+ * works for disabled opps as well.  In most cases, you want to
+ * operate only on available opps so you should use
+ * dev_pm_opp_get_voltage() instead.
+ *
+ * Return: voltage in micro volt corresponding to the opp, else
+ * return 0
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. This means that opp which could have been fetched by
+ * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
+ * under RCU lock. The pointer returned by the opp_find_freq family must be
+ * used in the same section as the usage of this function with the pointer
+ * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
+ * pointer.
+ */
+unsigned long dev_pm_opp_get_voltage_always(struct dev_pm_opp *opp)
+{
+	struct dev_pm_opp *tmp_opp;
+	unsigned long v = 0;
+
+	tmp_opp = rcu_dereference(opp);
+	if (unlikely(IS_ERR_OR_NULL(tmp_opp)))
+		pr_err("%s: Invalid parameters\n", __func__);
+	else
+		v = tmp_opp->u_volt;
+
+	return v;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_voltage_always);
+
+/**
  * dev_pm_opp_get_freq() - Gets the frequency corresponding to an available opp
  * @opp:	opp for which frequency has to be returned for
  *
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index c2744b30d5d..f1cf53abd32 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -14,6 +14,7 @@
 #include <linux/suspend.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
+#include <linux/types.h>
 #include <trace/events/power.h>
 
 #include "power.h"
@@ -668,6 +669,37 @@ void pm_wakeup_event(struct device *dev, unsigned int msec)
 }
 EXPORT_SYMBOL_GPL(pm_wakeup_event);
 
+void pm_get_active_wakeup_sources(char *pending_wakeup_source, size_t max)
+{
+	struct wakeup_source *ws, *last_active_ws = NULL;
+	int len = 0;
+	bool active = false;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+		if (ws->active) {
+			if (!active)
+				len += scnprintf(pending_wakeup_source, max,
+						"Pending Wakeup Sources: ");
+			len += scnprintf(pending_wakeup_source + len, max - len,
+				"%s ", ws->name);
+			active = true;
+		} else if (!active &&
+			   (!last_active_ws ||
+			    ktime_to_ns(ws->last_time) >
+			    ktime_to_ns(last_active_ws->last_time))) {
+			last_active_ws = ws;
+		}
+	}
+	if (!active && last_active_ws) {
+		scnprintf(pending_wakeup_source, max,
+				"Last active Wakeup Source: %s",
+				last_active_ws->name);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(pm_get_active_wakeup_sources);
+
 void pm_print_active_wakeup_sources(void)
 {
 	struct wakeup_source *ws;
diff --git a/drivers/base/property.c b/drivers/base/property.c
new file mode 100644
index 00000000000..6a94ef6e83c
--- /dev/null
+++ b/drivers/base/property.c
@@ -0,0 +1,185 @@
+/*
+ * property.c - Unified device property interface.
+ *
+ * Copyright (C) 2014, Intel Corporation
+ * Authors: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *          Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/property.h>
+#include <linux/export.h>
+#include <linux/acpi.h>
+#include <linux/of.h>
+
+/**
+ * device_property_present - check if a property of a device is present
+ * @dev: Device whose property is being checked
+ * @propname: Name of the property
+ *
+ * Check if property @propname is present in the device firmware description.
+ */
+bool device_property_present(struct device *dev, const char *propname)
+{
+	if (IS_ENABLED(CONFIG_OF) && dev->of_node)
+		return of_property_read_bool(dev->of_node, propname);
+
+	return !acpi_dev_prop_get(ACPI_COMPANION(dev), propname, NULL);
+}
+EXPORT_SYMBOL_GPL(device_property_present);
+
+#define OF_DEV_PROP_READ_ARRAY(node, propname, type, val, nval) \
+	(val) ? of_property_read_##type##_array((node), (propname), (val), (nval)) \
+	      : of_property_count_elems_of_size((node), (propname), sizeof(type))
+
+#define DEV_PROP_READ_ARRAY(_dev_, _propname_, _type_, _proptype_, _val_, _nval_) \
+	IS_ENABLED(CONFIG_OF) && _dev_->of_node ? \
+		(OF_DEV_PROP_READ_ARRAY(_dev_->of_node, _propname_, _type_, \
+					_val_, _nval_)) : \
+		acpi_dev_prop_read(ACPI_COMPANION(_dev_), _propname_, \
+				   _proptype_, _val_, _nval_)
+
+/**
+ * device_property_read_u8_array - return a u8 array property of a device
+ * @dev: Device to get the property of
+ * @propname: Name of the property
+ * @val: The values are stored here
+ * @nval: Size of the @val array
+ *
+ * Function reads an array of u8 properties with @propname from the device
+ * firmware description and stores them to @val if found.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO if the property is not an array of numbers,
+ *	   %-EOVERFLOW if the size of the property is not as expected.
+ */
+int device_property_read_u8_array(struct device *dev, const char *propname,
+				  u8 *val, size_t nval)
+{
+	return DEV_PROP_READ_ARRAY(dev, propname, u8, DEV_PROP_U8, val, nval);
+}
+EXPORT_SYMBOL_GPL(device_property_read_u8_array);
+
+/**
+ * device_property_read_u16_array - return a u16 array property of a device
+ * @dev: Device to get the property of
+ * @propname: Name of the property
+ * @val: The values are stored here
+ * @nval: Size of the @val array
+ *
+ * Function reads an array of u16 properties with @propname from the device
+ * firmware description and stores them to @val if found.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO if the property is not an array of numbers,
+ *	   %-EOVERFLOW if the size of the property is not as expected.
+ */
+int device_property_read_u16_array(struct device *dev, const char *propname,
+				   u16 *val, size_t nval)
+{
+	return DEV_PROP_READ_ARRAY(dev, propname, u16, DEV_PROP_U16, val, nval);
+}
+EXPORT_SYMBOL_GPL(device_property_read_u16_array);
+
+/**
+ * device_property_read_u32_array - return a u32 array property of a device
+ * @dev: Device to get the property of
+ * @propname: Name of the property
+ * @val: The values are stored here
+ * @nval: Size of the @val array
+ *
+ * Function reads an array of u32 properties with @propname from the device
+ * firmware description and stores them to @val if found.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO if the property is not an array of numbers,
+ *	   %-EOVERFLOW if the size of the property is not as expected.
+ */
+int device_property_read_u32_array(struct device *dev, const char *propname,
+				   u32 *val, size_t nval)
+{
+	return DEV_PROP_READ_ARRAY(dev, propname, u32, DEV_PROP_U32, val, nval);
+}
+EXPORT_SYMBOL_GPL(device_property_read_u32_array);
+
+/**
+ * device_property_read_u64_array - return a u64 array property of a device
+ * @dev: Device to get the property of
+ * @propname: Name of the property
+ * @val: The values are stored here
+ * @nval: Size of the @val array
+ *
+ * Function reads an array of u64 properties with @propname from the device
+ * firmware description and stores them to @val if found.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO if the property is not an array of numbers,
+ *	   %-EOVERFLOW if the size of the property is not as expected.
+ */
+int device_property_read_u64_array(struct device *dev, const char *propname,
+				   u64 *val, size_t nval)
+{
+	return DEV_PROP_READ_ARRAY(dev, propname, u64, DEV_PROP_U64, val, nval);
+}
+EXPORT_SYMBOL_GPL(device_property_read_u64_array);
+
+/**
+ * device_property_read_string_array - return a string array property of device
+ * @dev: Device to get the property of
+ * @propname: Name of the property
+ * @val: The values are stored here
+ * @nval: Size of the @val array
+ *
+ * Function reads an array of string properties with @propname from the device
+ * firmware description and stores them to @val if found.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO or %-EILSEQ if the property is not an array of strings,
+ *	   %-EOVERFLOW if the size of the property is not as expected.
+ */
+int device_property_read_string_array(struct device *dev, const char *propname,
+				      const char **val, size_t nval)
+{
+	return IS_ENABLED(CONFIG_OF) && dev->of_node ?
+		of_property_read_string_array(dev->of_node, propname, val, nval) :
+		acpi_dev_prop_read(ACPI_COMPANION(dev), propname,
+				   DEV_PROP_STRING, val, nval);
+}
+EXPORT_SYMBOL_GPL(device_property_read_string_array);
+
+/**
+ * device_property_read_string - return a string property of a device
+ * @dev: Device to get the property of
+ * @propname: Name of the property
+ * @val: The value is stored here
+ *
+ * Function reads property @propname from the device firmware description and
+ * stores the value into @val if found. The value is checked to be a string.
+ *
+ * Return: %0 if the property was found (success),
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO or %-EILSEQ if the property type is not a string.
+ */
+int device_property_read_string(struct device *dev, const char *propname,
+				const char **val)
+{
+	return IS_ENABLED(CONFIG_OF) && dev->of_node ?
+		of_property_read_string(dev->of_node, propname, val) :
+		acpi_dev_prop_read(ACPI_COMPANION(dev), propname,
+				   DEV_PROP_STRING, val, 1);
+}
+EXPORT_SYMBOL_GPL(device_property_read_string);
diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index 0da5865df5b..8e1f5f67e25 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -237,4 +237,12 @@ extern struct regcache_ops regcache_rbtree_ops;
 extern struct regcache_ops regcache_lzo_ops;
 extern struct regcache_ops regcache_flat_ops;
 
+static inline const char *regmap_name(const struct regmap *map)
+{
+	if (map->dev)
+		return dev_name(map->dev);
+
+	return map->name;
+}
+
 #endif
diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c
index f3e8fe0cc65..9d09c5bb587 100644
--- a/drivers/base/regmap/regcache-rbtree.c
+++ b/drivers/base/regmap/regcache-rbtree.c
@@ -307,7 +307,7 @@ static int regcache_rbtree_insert_to_block(struct regmap *map,
 	if (pos == 0) {
 		memmove(blk + offset * map->cache_word_size,
 			blk, rbnode->blklen * map->cache_word_size);
-		bitmap_shift_right(present, present, offset, blklen);
+		bitmap_shift_left(present, present, offset, blklen);
 	}
 
 	/* update the rbnode block, its size and the base register */
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index f1280dc356d..e5c1eda6a4c 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -213,7 +213,7 @@ int regcache_read(struct regmap *map,
 		ret = map->cache_ops->read(map, reg, value);
 
 		if (ret == 0)
-			trace_regmap_reg_read_cache(map->dev, reg, *value);
+			trace_regmap_reg_read_cache(map, reg, *value);
 
 		return ret;
 	}
@@ -306,7 +306,7 @@ int regcache_sync(struct regmap *map)
 	dev_dbg(map->dev, "Syncing %s cache\n",
 		map->cache_ops->name);
 	name = map->cache_ops->name;
-	trace_regcache_sync(map->dev, name, "start");
+	trace_regcache_sync(map, name, "start");
 
 	if (!map->cache_dirty)
 		goto out;
@@ -341,7 +341,7 @@ out:
 
 	regmap_async_complete(map);
 
-	trace_regcache_sync(map->dev, name, "stop");
+	trace_regcache_sync(map, name, "stop");
 
 	return ret;
 }
@@ -376,7 +376,7 @@ int regcache_sync_region(struct regmap *map, unsigned int min,
 	name = map->cache_ops->name;
 	dev_dbg(map->dev, "Syncing %s cache from %d-%d\n", name, min, max);
 
-	trace_regcache_sync(map->dev, name, "start region");
+	trace_regcache_sync(map, name, "start region");
 
 	if (!map->cache_dirty)
 		goto out;
@@ -396,7 +396,7 @@ out:
 
 	regmap_async_complete(map);
 
-	trace_regcache_sync(map->dev, name, "stop region");
+	trace_regcache_sync(map, name, "stop region");
 
 	return ret;
 }
@@ -423,7 +423,7 @@ int regcache_drop_region(struct regmap *map, unsigned int min,
 
 	map->lock(map->lock_arg);
 
-	trace_regcache_drop_region(map->dev, min, max);
+	trace_regcache_drop_region(map, min, max);
 
 	ret = map->cache_ops->drop(map, min, max);
 
@@ -450,7 +450,7 @@ void regcache_cache_only(struct regmap *map, bool enable)
 	map->lock(map->lock_arg);
 	WARN_ON(map->cache_bypass && enable);
 	map->cache_only = enable;
-	trace_regmap_cache_only(map->dev, enable);
+	trace_regmap_cache_only(map, enable);
 	map->unlock(map->lock_arg);
 }
 EXPORT_SYMBOL_GPL(regcache_cache_only);
@@ -488,7 +488,7 @@ void regcache_cache_bypass(struct regmap *map, bool enable)
 	map->lock(map->lock_arg);
 	WARN_ON(map->cache_only && enable);
 	map->cache_bypass = enable;
-	trace_regmap_cache_bypass(map->dev, enable);
+	trace_regmap_cache_bypass(map, enable);
 	map->unlock(map->lock_arg);
 }
 EXPORT_SYMBOL_GPL(regcache_cache_bypass);
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index d2f8a818d20..b389c1dbcdf 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -944,11 +944,10 @@ EXPORT_SYMBOL_GPL(devm_regmap_init);
 static void regmap_field_init(struct regmap_field *rm_field,
 	struct regmap *regmap, struct reg_field reg_field)
 {
-	int field_bits = reg_field.msb - reg_field.lsb + 1;
 	rm_field->regmap = regmap;
 	rm_field->reg = reg_field.reg;
 	rm_field->shift = reg_field.lsb;
-	rm_field->mask = ((BIT(field_bits) - 1) << reg_field.lsb);
+	rm_field->mask = GENMASK(reg_field.msb, reg_field.lsb);
 	rm_field->id_size = reg_field.id_size;
 	rm_field->id_offset = reg_field.id_offset;
 }
@@ -1280,7 +1279,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg,
 	if (map->async && map->bus->async_write) {
 		struct regmap_async *async;
 
-		trace_regmap_async_write_start(map->dev, reg, val_len);
+		trace_regmap_async_write_start(map, reg, val_len);
 
 		spin_lock_irqsave(&map->async_lock, flags);
 		async = list_first_entry_or_null(&map->async_free,
@@ -1338,8 +1337,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg,
 		return ret;
 	}
 
-	trace_regmap_hw_write_start(map->dev, reg,
-				    val_len / map->format.val_bytes);
+	trace_regmap_hw_write_start(map, reg, val_len / map->format.val_bytes);
 
 	/* If we're doing a single register write we can probably just
 	 * send the work_buf directly, otherwise try to do a gather
@@ -1371,8 +1369,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg,
 		kfree(buf);
 	}
 
-	trace_regmap_hw_write_done(map->dev, reg,
-				   val_len / map->format.val_bytes);
+	trace_regmap_hw_write_done(map, reg, val_len / map->format.val_bytes);
 
 	return ret;
 }
@@ -1406,12 +1403,12 @@ static int _regmap_bus_formatted_write(void *context, unsigned int reg,
 
 	map->format.format_write(map, reg, val);
 
-	trace_regmap_hw_write_start(map->dev, reg, 1);
+	trace_regmap_hw_write_start(map, reg, 1);
 
 	ret = map->bus->write(map->bus_context, map->work_buf,
 			      map->format.buf_size);
 
-	trace_regmap_hw_write_done(map->dev, reg, 1);
+	trace_regmap_hw_write_done(map, reg, 1);
 
 	return ret;
 }
@@ -1469,7 +1466,7 @@ int _regmap_write(struct regmap *map, unsigned int reg,
 		dev_info(map->dev, "%x <= %x\n", reg, val);
 #endif
 
-	trace_regmap_reg_write(map->dev, reg, val);
+	trace_regmap_reg_write(map, reg, val);
 
 	return map->reg_write(context, reg, val);
 }
@@ -1772,7 +1769,7 @@ static int _regmap_raw_multi_reg_write(struct regmap *map,
 	for (i = 0; i < num_regs; i++) {
 		int reg = regs[i].reg;
 		int val = regs[i].def;
-		trace_regmap_hw_write_start(map->dev, reg, 1);
+		trace_regmap_hw_write_start(map, reg, 1);
 		map->format.format_reg(u8, reg, map->reg_shift);
 		u8 += reg_bytes + pad_bytes;
 		map->format.format_val(u8, val, 0);
@@ -1787,7 +1784,7 @@ static int _regmap_raw_multi_reg_write(struct regmap *map,
 
 	for (i = 0; i < num_regs; i++) {
 		int reg = regs[i].reg;
-		trace_regmap_hw_write_done(map->dev, reg, 1);
+		trace_regmap_hw_write_done(map, reg, 1);
 	}
 	return ret;
 }
@@ -2058,15 +2055,13 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
 	 */
 	u8[0] |= map->read_flag_mask;
 
-	trace_regmap_hw_read_start(map->dev, reg,
-				   val_len / map->format.val_bytes);
+	trace_regmap_hw_read_start(map, reg, val_len / map->format.val_bytes);
 
 	ret = map->bus->read(map->bus_context, map->work_buf,
 			     map->format.reg_bytes + map->format.pad_bytes,
 			     val, val_len);
 
-	trace_regmap_hw_read_done(map->dev, reg,
-				  val_len / map->format.val_bytes);
+	trace_regmap_hw_read_done(map, reg, val_len / map->format.val_bytes);
 
 	return ret;
 }
@@ -2122,7 +2117,7 @@ static int _regmap_read(struct regmap *map, unsigned int reg,
 			dev_info(map->dev, "%x => %x\n", reg, *val);
 #endif
 
-		trace_regmap_reg_read(map->dev, reg, *val);
+		trace_regmap_reg_read(map, reg, *val);
 
 		if (!map->cache_bypass)
 			regcache_write(map, reg, *val);
@@ -2321,7 +2316,7 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val,
 					  &ival);
 			if (ret != 0)
 				return ret;
-			memcpy(val + (i * val_bytes), &ival, val_bytes);
+			map->format.format_val(val + (i * val_bytes), ival, 0);
 		}
 	}
 
@@ -2479,7 +2474,7 @@ void regmap_async_complete_cb(struct regmap_async *async, int ret)
 	struct regmap *map = async->map;
 	bool wake;
 
-	trace_regmap_async_io_complete(map->dev);
+	trace_regmap_async_io_complete(map);
 
 	spin_lock(&map->async_lock);
 	list_move(&async->list, &map->async_free);
@@ -2524,7 +2519,7 @@ int regmap_async_complete(struct regmap *map)
 	if (!map->bus || !map->bus->async_write)
 		return 0;
 
-	trace_regmap_async_complete_start(map->dev);
+	trace_regmap_async_complete_start(map);
 
 	wait_event(map->async_waitq, regmap_async_is_done(map));
 
@@ -2533,7 +2528,7 @@ int regmap_async_complete(struct regmap *map)
 	map->async_ret = 0;
 	spin_unlock_irqrestore(&map->async_lock, flags);
 
-	trace_regmap_async_complete_done(map->dev);
+	trace_regmap_async_complete_done(map);
 
 	return ret;
 }
diff --git a/drivers/base/syscore.c b/drivers/base/syscore.c
index 8d98a329f6e..96c34a95cc6 100644
--- a/drivers/base/syscore.c
+++ b/drivers/base/syscore.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/suspend.h>
 #include <trace/events/power.h>
+#include <linux/wakeup_reason.h>
 
 static LIST_HEAD(syscore_ops_list);
 static DEFINE_MUTEX(syscore_ops_lock);
@@ -75,6 +76,8 @@ int syscore_suspend(void)
 	return 0;
 
  err_out:
+	log_suspend_abort_reason("System core suspend callback %pF failed",
+		ops->suspend);
 	pr_err("PM: System core suspend callback %pF failed.\n", ops->suspend);
 
 	list_for_each_entry_continue(ops, &syscore_ops_list, node)
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 5a01c53ddde..3b797cd5a40 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1545,6 +1545,7 @@ int drbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct
 		struct request_queue * const b =
 			device->ldev->backing_bdev->bd_disk->queue;
 		if (b->merge_bvec_fn) {
+			bvm->bi_bdev = device->ldev->backing_bdev;
 			backing_limit = b->merge_bvec_fn(b, bvm, bvec);
 			limit = min(limit, backing_limit);
 		}
@@ -1628,7 +1629,7 @@ void request_timer_fn(unsigned long data)
 		 time_after(now, req_peer->pre_send_jif + ent) &&
 		!time_in_range(now, connection->last_reconnect_jif, connection->last_reconnect_jif + ent)) {
 		drbd_warn(device, "Remote failed to finish a request within ko-count * timeout\n");
-		_drbd_set_state(_NS(device, conn, C_TIMEOUT), CS_VERBOSE | CS_HARD, NULL);
+		_conn_request_state(connection, NS(conn, C_TIMEOUT), CS_VERBOSE | CS_HARD);
 	}
 	if (dt && oldest_submit_jif != now &&
 		 time_after(now, oldest_submit_jif + dt) &&
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 4bc2a5cb993..a98c41f72c6 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -803,10 +803,6 @@ static int __init nbd_init(void)
 		return -EINVAL;
 	}
 
-	nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL);
-	if (!nbd_dev)
-		return -ENOMEM;
-
 	part_shift = 0;
 	if (max_part > 0) {
 		part_shift = fls(max_part);
@@ -828,6 +824,10 @@ static int __init nbd_init(void)
 	if (nbds_max > 1UL << (MINORBITS - part_shift))
 		return -EINVAL;
 
+	nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL);
+	if (!nbd_dev)
+		return -ENOMEM;
+
 	for (i = 0; i < nbds_max; i++) {
 		struct gendisk *disk = alloc_disk(1 << part_shift);
 		if (!disk)
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 27b71a0b72d..501a8ca662f 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -1998,11 +1998,11 @@ static struct rbd_obj_request *rbd_obj_request_create(const char *object_name,
 	rbd_assert(obj_request_type_valid(type));
 
 	size = strlen(object_name) + 1;
-	name = kmalloc(size, GFP_KERNEL);
+	name = kmalloc(size, GFP_NOIO);
 	if (!name)
 		return NULL;
 
-	obj_request = kmem_cache_zalloc(rbd_obj_request_cache, GFP_KERNEL);
+	obj_request = kmem_cache_zalloc(rbd_obj_request_cache, GFP_NOIO);
 	if (!obj_request) {
 		kfree(name);
 		return NULL;
@@ -2098,32 +2098,26 @@ static void rbd_dev_parent_put(struct rbd_device *rbd_dev)
  * If an image has a non-zero parent overlap, get a reference to its
  * parent.
  *
- * We must get the reference before checking for the overlap to
- * coordinate properly with zeroing the parent overlap in
- * rbd_dev_v2_parent_info() when an image gets flattened.  We
- * drop it again if there is no overlap.
- *
  * Returns true if the rbd device has a parent with a non-zero
  * overlap and a reference for it was successfully taken, or
  * false otherwise.
  */
 static bool rbd_dev_parent_get(struct rbd_device *rbd_dev)
 {
-	int counter;
+	int counter = 0;
 
 	if (!rbd_dev->parent_spec)
 		return false;
 
-	counter = atomic_inc_return_safe(&rbd_dev->parent_ref);
-	if (counter > 0 && rbd_dev->parent_overlap)
-		return true;
-
-	/* Image was flattened, but parent is not yet torn down */
+	down_read(&rbd_dev->header_rwsem);
+	if (rbd_dev->parent_overlap)
+		counter = atomic_inc_return_safe(&rbd_dev->parent_ref);
+	up_read(&rbd_dev->header_rwsem);
 
 	if (counter < 0)
 		rbd_warn(rbd_dev, "parent reference overflow");
 
-	return false;
+	return counter > 0;
 }
 
 /*
@@ -2267,6 +2261,11 @@ static bool rbd_img_obj_end_request(struct rbd_obj_request *obj_request)
 			result, xferred);
 		if (!img_request->result)
 			img_request->result = result;
+		/*
+		 * Need to end I/O on the entire obj_request worth of
+		 * bytes in case of error.
+		 */
+		xferred = obj_request->length;
 	}
 
 	/* Image object requests don't own their page array */
@@ -4236,7 +4235,6 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
 		 */
 		if (rbd_dev->parent_overlap) {
 			rbd_dev->parent_overlap = 0;
-			smp_mb();
 			rbd_dev_parent_put(rbd_dev);
 			pr_info("%s: clone image has been flattened\n",
 				rbd_dev->disk->disk_name);
@@ -4282,7 +4280,6 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
 	 * treat it specially.
 	 */
 	rbd_dev->parent_overlap = overlap;
-	smp_mb();
 	if (!overlap) {
 
 		/* A null parent_spec indicates it's the initial probe */
@@ -5111,10 +5108,7 @@ static void rbd_dev_unprobe(struct rbd_device *rbd_dev)
 {
 	struct rbd_image_header	*header;
 
-	/* Drop parent reference unless it's already been done (or none) */
-
-	if (rbd_dev->parent_overlap)
-		rbd_dev_parent_put(rbd_dev);
+	rbd_dev_parent_put(rbd_dev);
 
 	/* Free dynamic fields from the header, then zero it out */
 
diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c
index d85ced27ebd..8dc319dd315 100644
--- a/drivers/bluetooth/ath3k.c
+++ b/drivers/bluetooth/ath3k.c
@@ -65,6 +65,7 @@ static const struct usb_device_id ath3k_table[] = {
 	/* Atheros AR3011 with sflash firmware*/
 	{ USB_DEVICE(0x0489, 0xE027) },
 	{ USB_DEVICE(0x0489, 0xE03D) },
+	{ USB_DEVICE(0x04F2, 0xAFF1) },
 	{ USB_DEVICE(0x0930, 0x0215) },
 	{ USB_DEVICE(0x0CF3, 0x3002) },
 	{ USB_DEVICE(0x0CF3, 0xE019) },
@@ -79,6 +80,8 @@ static const struct usb_device_id ath3k_table[] = {
 	{ USB_DEVICE(0x0489, 0xe057) },
 	{ USB_DEVICE(0x0489, 0xe056) },
 	{ USB_DEVICE(0x0489, 0xe05f) },
+	{ USB_DEVICE(0x0489, 0xe076) },
+	{ USB_DEVICE(0x0489, 0xe078) },
 	{ USB_DEVICE(0x04c5, 0x1330) },
 	{ USB_DEVICE(0x04CA, 0x3004) },
 	{ USB_DEVICE(0x04CA, 0x3005) },
@@ -86,6 +89,9 @@ static const struct usb_device_id ath3k_table[] = {
 	{ USB_DEVICE(0x04CA, 0x3007) },
 	{ USB_DEVICE(0x04CA, 0x3008) },
 	{ USB_DEVICE(0x04CA, 0x300b) },
+	{ USB_DEVICE(0x04CA, 0x300d) },
+	{ USB_DEVICE(0x04CA, 0x300f) },
+	{ USB_DEVICE(0x04CA, 0x3010) },
 	{ USB_DEVICE(0x0930, 0x0219) },
 	{ USB_DEVICE(0x0930, 0x0220) },
 	{ USB_DEVICE(0x0930, 0x0227) },
@@ -105,7 +111,10 @@ static const struct usb_device_id ath3k_table[] = {
 	{ USB_DEVICE(0x13d3, 0x3375) },
 	{ USB_DEVICE(0x13d3, 0x3393) },
 	{ USB_DEVICE(0x13d3, 0x3402) },
+	{ USB_DEVICE(0x13d3, 0x3408) },
+	{ USB_DEVICE(0x13d3, 0x3423) },
 	{ USB_DEVICE(0x13d3, 0x3432) },
+	{ USB_DEVICE(0x13d3, 0x3474) },
 
 	/* Atheros AR5BBU12 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xE02C) },
@@ -130,6 +139,8 @@ static const struct usb_device_id ath3k_blist_tbl[] = {
 	{ USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe05f), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe076), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe078), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 },
@@ -137,6 +148,9 @@ static const struct usb_device_id ath3k_blist_tbl[] = {
 	{ USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x300b), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x300d), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0227), .driver_info = BTUSB_ATH3012 },
@@ -156,7 +170,10 @@ static const struct usb_device_id ath3k_blist_tbl[] = {
 	{ USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3408), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3423), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3432), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3474), .driver_info = BTUSB_ATH3012 },
 
 	/* Atheros AR5BBU22 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xE036), .driver_info = BTUSB_ATH3012 },
@@ -168,6 +185,8 @@ static const struct usb_device_id ath3k_blist_tbl[] = {
 #define USB_REQ_DFU_DNLOAD	1
 #define BULK_SIZE		4096
 #define FW_HDR_SIZE		20
+#define TIMEGAP_USEC_MIN	50
+#define TIMEGAP_USEC_MAX	100
 
 static int ath3k_load_firmware(struct usb_device *udev,
 				const struct firmware *firmware)
@@ -199,6 +218,9 @@ static int ath3k_load_firmware(struct usb_device *udev,
 	pipe = usb_sndbulkpipe(udev, 0x02);
 
 	while (count) {
+		/* workaround the compatibility issue with xHCI controller*/
+		usleep_range(TIMEGAP_USEC_MIN, TIMEGAP_USEC_MAX);
+
 		size = min_t(uint, count, BULK_SIZE);
 		memcpy(send_buf, firmware->data + sent, size);
 
@@ -296,6 +318,9 @@ static int ath3k_load_fwfile(struct usb_device *udev,
 	pipe = usb_sndbulkpipe(udev, 0x02);
 
 	while (count) {
+		/* workaround the compatibility issue with xHCI controller*/
+		usleep_range(TIMEGAP_USEC_MIN, TIMEGAP_USEC_MAX);
+
 		size = min_t(uint, count, BULK_SIZE);
 		memcpy(send_buf, firmware->data + sent, size);
 
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index edfc17bfcd4..c675e2bd9fd 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -107,14 +107,25 @@ static const struct usb_device_id btusb_table[] = {
 	{ USB_DEVICE(0x0b05, 0x17cb) },
 	{ USB_DEVICE(0x413c, 0x8197) },
 
+	/* Broadcom BCM20702B0 (Dynex/Insignia) */
+	{ USB_DEVICE(0x19ff, 0x0239), .driver_info = BTUSB_BCM_PATCHRAM },
+
 	/* Foxconn - Hon Hai */
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x0489, 0xff, 0x01, 0x01) },
 
+	/* Lite-On Technology - Broadcom based */
+	{ USB_VENDOR_AND_INTERFACE_INFO(0x04ca, 0xff, 0x01, 0x01),
+	  .driver_info = BTUSB_BCM_PATCHRAM },
+
 	/* Broadcom devices with vendor specific id */
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x0a5c, 0xff, 0x01, 0x01),
 	  .driver_info = BTUSB_BCM_PATCHRAM },
 
 	/* ASUSTek Computer - Broadcom based */
+	{ USB_VENDOR_AND_INTERFACE_INFO(0x0b05, 0xff, 0x01, 0x01),
+	  .driver_info = BTUSB_BCM_PATCHRAM },
+
+	/* ASUSTek Computer - Broadcom based */
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x0b05, 0xff, 0x01, 0x01) },
 
 	/* Belkin F8065bf - Broadcom based */
@@ -142,6 +153,7 @@ static const struct usb_device_id blacklist_table[] = {
 	/* Atheros 3011 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xe027), .driver_info = BTUSB_IGNORE },
 	{ USB_DEVICE(0x0489, 0xe03d), .driver_info = BTUSB_IGNORE },
+	{ USB_DEVICE(0x04f2, 0xaff1), .driver_info = BTUSB_IGNORE },
 	{ USB_DEVICE(0x0930, 0x0215), .driver_info = BTUSB_IGNORE },
 	{ USB_DEVICE(0x0cf3, 0x3002), .driver_info = BTUSB_IGNORE },
 	{ USB_DEVICE(0x0cf3, 0xe019), .driver_info = BTUSB_IGNORE },
@@ -156,6 +168,8 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe05f), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe076), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe078), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 },
@@ -163,6 +177,9 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x300b), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x300d), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0227), .driver_info = BTUSB_ATH3012 },
@@ -182,7 +199,10 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3408), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3423), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3432), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3474), .driver_info = BTUSB_ATH3012 },
 
 	/* Atheros AR5BBU12 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xe02c), .driver_info = BTUSB_IGNORE },
@@ -1573,6 +1593,8 @@ static int btusb_setup_intel(struct hci_dev *hdev)
 	}
 	fw_ptr = fw->data;
 
+	kfree_skb(skb);
+
 	/* This Intel specific command enables the manufacturer mode of the
 	 * controller.
 	 *
diff --git a/drivers/bus/arm-ccn.c b/drivers/bus/arm-ccn.c
index aaa0f2a8711..60397ec77ff 100644
--- a/drivers/bus/arm-ccn.c
+++ b/drivers/bus/arm-ccn.c
@@ -212,7 +212,7 @@ static int arm_ccn_node_to_xp_port(int node)
 
 static void arm_ccn_pmu_config_set(u64 *config, u32 node_xp, u32 type, u32 port)
 {
-	*config &= ~((0xff << 0) | (0xff << 8) | (0xff << 24));
+	*config &= ~((0xff << 0) | (0xff << 8) | (0x3 << 24));
 	*config |= (node_xp << 0) | (type << 8) | (port << 24);
 }
 
diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c
index 26c3779d871..d29f5ffdb0f 100644
--- a/drivers/bus/mvebu-mbus.c
+++ b/drivers/bus/mvebu-mbus.c
@@ -182,12 +182,25 @@ static void mvebu_mbus_disable_window(struct mvebu_mbus_state *mbus,
 }
 
 /* Checks whether the given window number is available */
+
+/* On Armada XP, 375 and 38x the MBus window 13 has the remap
+ * capability, like windows 0 to 7. However, the mvebu-mbus driver
+ * isn't currently taking into account this special case, which means
+ * that when window 13 is actually used, the remap registers are left
+ * to 0, making the device using this MBus window unavailable. The
+ * quick fix for stable is to not use window 13. A follow up patch
+ * will correctly handle this window.
+*/
 static int mvebu_mbus_window_is_free(struct mvebu_mbus_state *mbus,
 				     const int win)
 {
 	void __iomem *addr = mbus->mbuswins_base +
 		mbus->soc->win_cfg_offset(win);
 	u32 ctrl = readl(addr + WIN_CTRL_OFF);
+
+	if (win == 13)
+		return false;
+
 	return !(ctrl & WIN_CTRL_ENABLE);
 }
 
diff --git a/drivers/bus/omap_l3_noc.c b/drivers/bus/omap_l3_noc.c
index 531ae591783..17d86595951 100644
--- a/drivers/bus/omap_l3_noc.c
+++ b/drivers/bus/omap_l3_noc.c
@@ -222,10 +222,14 @@ static irqreturn_t l3_interrupt_handler(int irq, void *_l3)
 			}
 
 			/* Error found so break the for loop */
-			break;
+			return IRQ_HANDLED;
 		}
 	}
-	return IRQ_HANDLED;
+
+	dev_err(l3->dev, "L3 %s IRQ not handled!!\n",
+		inttype ? "debug" : "application");
+
+	return IRQ_NONE;
 }
 
 static const struct of_device_id l3_noc_match[] = {
@@ -296,11 +300,66 @@ static int omap_l3_probe(struct platform_device *pdev)
 	return ret;
 }
 
+#ifdef	CONFIG_PM
+
+/**
+ * l3_resume_noirq() - resume function for l3_noc
+ * @dev:	pointer to l3_noc device structure
+ *
+ * We only have the resume handler only since we
+ * have already maintained the delta register
+ * configuration as part of configuring the system
+ */
+static int l3_resume_noirq(struct device *dev)
+{
+	struct omap_l3 *l3 = dev_get_drvdata(dev);
+	int i;
+	struct l3_flagmux_data *flag_mux;
+	void __iomem *base, *mask_regx = NULL;
+	u32 mask_val;
+
+	for (i = 0; i < l3->num_modules; i++) {
+		base = l3->l3_base[i];
+		flag_mux = l3->l3_flagmux[i];
+		if (!flag_mux->mask_app_bits && !flag_mux->mask_dbg_bits)
+			continue;
+
+		mask_regx = base + flag_mux->offset + L3_FLAGMUX_MASK0 +
+			   (L3_APPLICATION_ERROR << 3);
+		mask_val = readl_relaxed(mask_regx);
+		mask_val &= ~(flag_mux->mask_app_bits);
+
+		writel_relaxed(mask_val, mask_regx);
+		mask_regx = base + flag_mux->offset + L3_FLAGMUX_MASK0 +
+			   (L3_DEBUG_ERROR << 3);
+		mask_val = readl_relaxed(mask_regx);
+		mask_val &= ~(flag_mux->mask_dbg_bits);
+
+		writel_relaxed(mask_val, mask_regx);
+	}
+
+	/* Dummy read to force OCP barrier */
+	if (mask_regx)
+		(void)readl(mask_regx);
+
+	return 0;
+}
+
+static const struct dev_pm_ops l3_dev_pm_ops = {
+	.resume_noirq		= l3_resume_noirq,
+};
+
+#define L3_DEV_PM_OPS (&l3_dev_pm_ops)
+#else
+#define L3_DEV_PM_OPS NULL
+#endif
+
 static struct platform_driver omap_l3_driver = {
 	.probe		= omap_l3_probe,
 	.driver		= {
 		.name		= "omap_l3_noc",
 		.owner		= THIS_MODULE,
+		.pm		= L3_DEV_PM_OPS,
 		.of_match_table = of_match_ptr(l3_noc_match),
 	},
 };
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index efefd12a0f7..b96a3a5bcba 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -6,6 +6,19 @@ menu "Character devices"
 
 source "drivers/tty/Kconfig"
 
+config DEVMEM
+	bool "Memory device driver"
+	default y
+	help
+	  The memory driver provides two character devices, mem and kmem, which
+	  provide access to the system's memory. The mem device is a view of
+	  physical memory, and each byte in the device corresponds to the
+	  matching physical address. The kmem device is the same as mem, but
+	  the addresses correspond to the kernel's virtual address space rather
+	  than physical memory. These devices are standard parts of a Linux
+	  system and most users should say Y here. You might say N if very
+	  security conscience or memory is tight.
+
 config DEVKMEM
 	bool "/dev/kmem virtual device support"
 	default y
@@ -579,6 +592,10 @@ config DEVPORT
 	depends on ISA || PCI
 	default y
 
+config DCC_TTY
+	tristate "DCC tty driver"
+	depends on ARM
+
 source "drivers/s390/char/Kconfig"
 
 config MSM_SMD_PKT
diff --git a/drivers/char/Makefile b/drivers/char/Makefile
index d06cde26031..e38fb5b6148 100644
--- a/drivers/char/Makefile
+++ b/drivers/char/Makefile
@@ -55,6 +55,7 @@ obj-$(CONFIG_PCMCIA)		+= pcmcia/
 obj-$(CONFIG_HANGCHECK_TIMER)	+= hangcheck-timer.o
 obj-$(CONFIG_TCG_TPM)		+= tpm/
 
+obj-$(CONFIG_DCC_TTY)		+= dcc_tty.o
 obj-$(CONFIG_PS3_FLASH)		+= ps3flash.o
 
 obj-$(CONFIG_JS_RTC)		+= js-rtc.o
diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
index 9a024f899dd..9a99d0a3ff0 100644
--- a/drivers/char/agp/intel-gtt.c
+++ b/drivers/char/agp/intel-gtt.c
@@ -585,7 +585,7 @@ static inline int needs_ilk_vtd_wa(void)
 	/* Query intel_iommu to see if we need the workaround. Presumably that
 	 * was loaded first.
 	 */
-	if ((gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_M_HB ||
+	if ((gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_D_IG ||
 	     gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_M_IG) &&
 	     intel_iommu_gfx_mapped)
 		return 1;
diff --git a/drivers/char/dcc_tty.c b/drivers/char/dcc_tty.c
new file mode 100644
index 00000000000..0a62d410286
--- /dev/null
+++ b/drivers/char/dcc_tty.c
@@ -0,0 +1,326 @@
+/* drivers/char/dcc_tty.c
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/delay.h>
+#include <linux/console.h>
+#include <linux/hrtimer.h>
+#include <linux/tty.h>
+#include <linux/tty_driver.h>
+#include <linux/tty_flip.h>
+
+MODULE_DESCRIPTION("DCC TTY Driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1.0");
+
+DEFINE_SPINLOCK(g_dcc_tty_lock);
+static struct hrtimer g_dcc_timer;
+static char g_dcc_buffer[16];
+static int g_dcc_buffer_head;
+static int g_dcc_buffer_count;
+static unsigned g_dcc_write_delay_usecs = 1;
+static struct tty_driver *g_dcc_tty_driver;
+static struct tty_struct *g_dcc_tty;
+static int g_dcc_tty_open_count;
+
+static void dcc_poll_locked(void)
+{
+	char ch;
+	int rch;
+	int written;
+
+	while (g_dcc_buffer_count) {
+		ch = g_dcc_buffer[g_dcc_buffer_head];
+		asm(
+			"mrc 14, 0, r15, c0, c1, 0\n"
+			"mcrcc 14, 0, %1, c0, c5, 0\n"
+			"movcc %0, #1\n"
+			"movcs %0, #0\n"
+			: "=r" (written)
+			: "r" (ch)
+		);
+		if (written) {
+			if (ch == '\n')
+				g_dcc_buffer[g_dcc_buffer_head] = '\r';
+			else {
+				g_dcc_buffer_head = (g_dcc_buffer_head + 1) % ARRAY_SIZE(g_dcc_buffer);
+				g_dcc_buffer_count--;
+				if (g_dcc_tty)
+					tty_wakeup(g_dcc_tty);
+			}
+			g_dcc_write_delay_usecs = 1;
+		} else {
+			if (g_dcc_write_delay_usecs > 0x100)
+				break;
+			g_dcc_write_delay_usecs <<= 1;
+			udelay(g_dcc_write_delay_usecs);
+		}
+	}
+
+	if (g_dcc_tty && !test_bit(TTY_THROTTLED, &g_dcc_tty->flags)) {
+		asm(
+			"mrc 14, 0, %0, c0, c1, 0\n"
+			"tst %0, #(1 << 30)\n"
+			"moveq %0, #-1\n"
+			"mrcne 14, 0, %0, c0, c5, 0\n"
+			: "=r" (rch)
+		);
+		if (rch >= 0) {
+			ch = rch;
+			tty_insert_flip_string(g_dcc_tty->port, &ch, 1);
+			tty_flip_buffer_push(g_dcc_tty->port);
+		}
+	}
+
+
+	if (g_dcc_buffer_count)
+		hrtimer_start(&g_dcc_timer, ktime_set(0, g_dcc_write_delay_usecs * NSEC_PER_USEC), HRTIMER_MODE_REL);
+	else
+		hrtimer_start(&g_dcc_timer, ktime_set(0, 20 * NSEC_PER_MSEC), HRTIMER_MODE_REL);
+}
+
+static int dcc_tty_open(struct tty_struct * tty, struct file * filp)
+{
+	int ret;
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&g_dcc_tty_lock, irq_flags);
+	if (g_dcc_tty == NULL || g_dcc_tty == tty) {
+		g_dcc_tty = tty;
+		g_dcc_tty_open_count++;
+		ret = 0;
+	} else
+		ret = -EBUSY;
+	spin_unlock_irqrestore(&g_dcc_tty_lock, irq_flags);
+
+	printk("dcc_tty_open, tty %p, f_flags %x, returned %d\n", tty, filp->f_flags, ret);
+
+	return ret;
+}
+
+static void dcc_tty_close(struct tty_struct * tty, struct file * filp)
+{
+	printk("dcc_tty_close, tty %p, f_flags %x\n", tty, filp->f_flags);
+	if (g_dcc_tty == tty) {
+		if (--g_dcc_tty_open_count == 0)
+			g_dcc_tty = NULL;
+	}
+}
+
+static int dcc_write(const unsigned char *buf_start, int count)
+{
+	const unsigned char *buf = buf_start;
+	unsigned long irq_flags;
+	int copy_len;
+	int space_left;
+	int tail;
+
+	if (count < 1)
+		return 0;
+
+	spin_lock_irqsave(&g_dcc_tty_lock, irq_flags);
+	do {
+		tail = (g_dcc_buffer_head + g_dcc_buffer_count) % ARRAY_SIZE(g_dcc_buffer);
+		copy_len = ARRAY_SIZE(g_dcc_buffer) - tail;
+		space_left = ARRAY_SIZE(g_dcc_buffer) - g_dcc_buffer_count;
+		if (copy_len > space_left)
+			copy_len = space_left;
+		if (copy_len > count)
+			copy_len = count;
+		memcpy(&g_dcc_buffer[tail], buf, copy_len);
+		g_dcc_buffer_count += copy_len;
+		buf += copy_len;
+		count -= copy_len;
+		if (copy_len < count && copy_len < space_left) {
+			space_left -= copy_len;
+			copy_len = count;
+			if (copy_len > space_left) {
+				copy_len = space_left;
+			}
+			memcpy(g_dcc_buffer, buf, copy_len);
+			buf += copy_len;
+			count -= copy_len;
+			g_dcc_buffer_count += copy_len;
+		}
+		dcc_poll_locked();
+		space_left = ARRAY_SIZE(g_dcc_buffer) - g_dcc_buffer_count;
+	} while(count && space_left);
+	spin_unlock_irqrestore(&g_dcc_tty_lock, irq_flags);
+	return buf - buf_start;
+}
+
+static int dcc_tty_write(struct tty_struct * tty, const unsigned char *buf, int count)
+{
+	int ret;
+	/* printk("dcc_tty_write %p, %d\n", buf, count); */
+	ret = dcc_write(buf, count);
+	if (ret != count)
+		printk("dcc_tty_write %p, %d, returned %d\n", buf, count, ret);
+	return ret;
+}
+
+static int dcc_tty_write_room(struct tty_struct *tty)
+{
+	int space_left;
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&g_dcc_tty_lock, irq_flags);
+	space_left = ARRAY_SIZE(g_dcc_buffer) - g_dcc_buffer_count;
+	spin_unlock_irqrestore(&g_dcc_tty_lock, irq_flags);
+	return space_left;
+}
+
+static int dcc_tty_chars_in_buffer(struct tty_struct *tty)
+{
+	int ret;
+	asm(
+		"mrc 14, 0, %0, c0, c1, 0\n"
+		"mov %0, %0, LSR #30\n"
+		"and %0, %0, #1\n"
+		: "=r" (ret)
+	);
+	return ret;
+}
+
+static void dcc_tty_unthrottle(struct tty_struct * tty)
+{
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&g_dcc_tty_lock, irq_flags);
+	dcc_poll_locked();
+	spin_unlock_irqrestore(&g_dcc_tty_lock, irq_flags);
+}
+
+static enum hrtimer_restart dcc_tty_timer_func(struct hrtimer *timer)
+{
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&g_dcc_tty_lock, irq_flags);
+	dcc_poll_locked();
+	spin_unlock_irqrestore(&g_dcc_tty_lock, irq_flags);
+	return HRTIMER_NORESTART;
+}
+
+void dcc_console_write(struct console *co, const char *b, unsigned count)
+{
+#if 1
+	dcc_write(b, count);
+#else
+	/* blocking printk */
+	while (count > 0) {
+		int written;
+		written = dcc_write(b, count);
+		if (written) {
+			b += written;
+			count -= written;
+		}
+	}
+#endif
+}
+
+static struct tty_driver *dcc_console_device(struct console *c, int *index)
+{
+	*index = 0;
+	return g_dcc_tty_driver;
+}
+
+static int __init dcc_console_setup(struct console *co, char *options)
+{
+	if (co->index != 0)
+		return -ENODEV;
+	return 0;
+}
+
+
+static struct console dcc_console =
+{
+	.name		= "ttyDCC",
+	.write		= dcc_console_write,
+	.device		= dcc_console_device,
+	.setup		= dcc_console_setup,
+	.flags		= CON_PRINTBUFFER,
+	.index		= -1,
+};
+
+static struct tty_operations dcc_tty_ops = {
+	.open = dcc_tty_open,
+	.close = dcc_tty_close,
+	.write = dcc_tty_write,
+	.write_room = dcc_tty_write_room,
+	.chars_in_buffer = dcc_tty_chars_in_buffer,
+	.unthrottle = dcc_tty_unthrottle,
+};
+
+static int __init dcc_tty_init(void)
+{
+	int ret;
+
+	hrtimer_init(&g_dcc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	g_dcc_timer.function = dcc_tty_timer_func;
+
+	g_dcc_tty_driver = alloc_tty_driver(1);
+	if (!g_dcc_tty_driver) {
+		printk(KERN_ERR "dcc_tty_probe: alloc_tty_driver failed\n");
+		ret = -ENOMEM;
+		goto err_alloc_tty_driver_failed;
+	}
+	g_dcc_tty_driver->owner = THIS_MODULE;
+	g_dcc_tty_driver->driver_name = "dcc";
+	g_dcc_tty_driver->name = "ttyDCC";
+	g_dcc_tty_driver->major = 0; // auto assign
+	g_dcc_tty_driver->minor_start = 0;
+	g_dcc_tty_driver->type = TTY_DRIVER_TYPE_SERIAL;
+	g_dcc_tty_driver->subtype = SERIAL_TYPE_NORMAL;
+	g_dcc_tty_driver->init_termios = tty_std_termios;
+	g_dcc_tty_driver->flags = TTY_DRIVER_RESET_TERMIOS | TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV;
+	tty_set_operations(g_dcc_tty_driver, &dcc_tty_ops);
+	ret = tty_register_driver(g_dcc_tty_driver);
+	if (ret) {
+		printk(KERN_ERR "dcc_tty_probe: tty_register_driver failed, %d\n", ret);
+		goto err_tty_register_driver_failed;
+	}
+	tty_register_device(g_dcc_tty_driver, 0, NULL);
+
+	register_console(&dcc_console);
+	hrtimer_start(&g_dcc_timer, ktime_set(0, 0), HRTIMER_MODE_REL);
+
+	return 0;
+
+err_tty_register_driver_failed:
+	put_tty_driver(g_dcc_tty_driver);
+	g_dcc_tty_driver = NULL;
+err_alloc_tty_driver_failed:
+	return ret;
+}
+
+static void  __exit dcc_tty_exit(void)
+{
+	int ret;
+
+	tty_unregister_device(g_dcc_tty_driver, 0);
+	ret = tty_unregister_driver(g_dcc_tty_driver);
+	if (ret < 0) {
+		printk(KERN_ERR "dcc_tty_remove: tty_unregister_driver failed, %d\n", ret);
+	} else {
+		put_tty_driver(g_dcc_tty_driver);
+	}
+	g_dcc_tty_driver = NULL;
+}
+
+module_init(dcc_tty_init);
+module_exit(dcc_tty_exit);
+
+
diff --git a/drivers/char/i8k.c b/drivers/char/i8k.c
index 34174d01462..471f985e38d 100644
--- a/drivers/char/i8k.c
+++ b/drivers/char/i8k.c
@@ -711,6 +711,14 @@ static struct dmi_system_id i8k_dmi_table[] __initdata = {
 		.driver_data = (void *)&i8k_config_data[DELL_LATITUDE_D520],
 	},
 	{
+		.ident = "Dell Latitude E6440",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6440"),
+		},
+		.driver_data = (void *)&i8k_config_data[DELL_LATITUDE_E6540],
+	},
+	{
 		.ident = "Dell Latitude E6540",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 524b707894e..37e17cac4bf 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -58,6 +58,7 @@ static inline int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
 }
 #endif
 
+#if defined(CONFIG_DEVMEM) || defined(CONFIG_DEVKMEM)
 #ifdef CONFIG_STRICT_DEVMEM
 static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 {
@@ -83,7 +84,9 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 	return 1;
 }
 #endif
+#endif
 
+#ifdef CONFIG_DEVMEM
 void __weak unxlate_dev_mem_ptr(unsigned long phys, void *addr)
 {
 }
@@ -216,6 +219,9 @@ static ssize_t write_mem(struct file *file, const char __user *buf,
 	*ppos += written;
 	return written;
 }
+#endif	/* CONFIG_DEVMEM */
+
+#if defined(CONFIG_DEVMEM) || defined(CONFIG_DEVKMEM)
 
 int __weak phys_mem_access_prot_allowed(struct file *file,
 	unsigned long pfn, unsigned long size, pgprot_t *vma_prot)
@@ -337,6 +343,7 @@ static int mmap_mem(struct file *file, struct vm_area_struct *vma)
 	}
 	return 0;
 }
+#endif	/* CONFIG_DEVMEM */
 
 #ifdef CONFIG_DEVKMEM
 static int mmap_kmem(struct file *file, struct vm_area_struct *vma)
@@ -667,6 +674,8 @@ static loff_t null_lseek(struct file *file, loff_t offset, int orig)
 	return file->f_pos = 0;
 }
 
+#if defined(CONFIG_DEVMEM) || defined(CONFIG_DEVKMEM) || defined(CONFIG_DEVPORT)
+
 /*
  * The memory devices use the full 32/64 bits of the offset, and so we cannot
  * check against negative addresses: they are ok. The return value is weird,
@@ -700,10 +709,14 @@ static loff_t memory_lseek(struct file *file, loff_t offset, int orig)
 	return ret;
 }
 
+#endif
+
+#if defined(CONFIG_DEVMEM) || defined(CONFIG_DEVKMEM) || defined(CONFIG_DEVPORT)
 static int open_port(struct inode *inode, struct file *filp)
 {
 	return capable(CAP_SYS_RAWIO) ? 0 : -EPERM;
 }
+#endif
 
 #define zero_lseek	null_lseek
 #define full_lseek      null_lseek
@@ -712,6 +725,7 @@ static int open_port(struct inode *inode, struct file *filp)
 #define open_mem	open_port
 #define open_kmem	open_mem
 
+#ifdef CONFIG_DEVMEM
 static const struct file_operations mem_fops = {
 	.llseek		= memory_lseek,
 	.read		= read_mem,
@@ -720,6 +734,7 @@ static const struct file_operations mem_fops = {
 	.open		= open_mem,
 	.get_unmapped_area = get_unmapped_area_mem,
 };
+#endif
 
 #ifdef CONFIG_DEVKMEM
 static const struct file_operations kmem_fops = {
@@ -782,7 +797,9 @@ static const struct memdev {
 	const struct file_operations *fops;
 	struct backing_dev_info *dev_info;
 } devlist[] = {
+#ifdef CONFIG_DEVMEM
 	 [1] = { "mem", 0, &mem_fops, &directly_mappable_cdev_bdi },
+#endif
 #ifdef CONFIG_DEVKMEM
 	 [2] = { "kmem", 0, &kmem_fops, &directly_mappable_cdev_bdi },
 #endif
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 04645c09fe5..9cd6968e2f9 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -569,19 +569,19 @@ static void fast_mix(struct fast_pool *f)
 	__u32 c = f->pool[2],	d = f->pool[3];
 
 	a += b;			c += d;
-	b = rol32(a, 6);	d = rol32(c, 27);
+	b = rol32(b, 6);	d = rol32(d, 27);
 	d ^= a;			b ^= c;
 
 	a += b;			c += d;
-	b = rol32(a, 16);	d = rol32(c, 14);
+	b = rol32(b, 16);	d = rol32(d, 14);
 	d ^= a;			b ^= c;
 
 	a += b;			c += d;
-	b = rol32(a, 6);	d = rol32(c, 27);
+	b = rol32(b, 6);	d = rol32(d, 27);
 	d ^= a;			b ^= c;
 
 	a += b;			c += d;
-	b = rol32(a, 16);	d = rol32(c, 14);
+	b = rol32(b, 16);	d = rol32(d, 14);
 	d ^= a;			b ^= c;
 
 	f->pool[0] = a;  f->pool[1] = b;
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index 6af17002a11..cfb9089887b 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -1122,7 +1122,7 @@ struct tpm_chip *tpm_register_hardware(struct device *dev,
 
 	/* Make chip available */
 	spin_lock(&driver_lock);
-	list_add_rcu(&chip->list, &tpm_chip_list);
+	list_add_tail_rcu(&chip->list, &tpm_chip_list);
 	spin_unlock(&driver_lock);
 
 	return chip;
diff --git a/drivers/char/tpm/tpm_i2c_atmel.c b/drivers/char/tpm/tpm_i2c_atmel.c
index 77272925dee..503a85ae176 100644
--- a/drivers/char/tpm/tpm_i2c_atmel.c
+++ b/drivers/char/tpm/tpm_i2c_atmel.c
@@ -168,6 +168,10 @@ static int i2c_atmel_probe(struct i2c_client *client,
 
 	chip->vendor.priv = devm_kzalloc(dev, sizeof(struct priv_data),
 					 GFP_KERNEL);
+	if (!chip->vendor.priv) {
+		rc = -ENOMEM;
+		goto out_err;
+	}
 
 	/* Default timeouts */
 	chip->vendor.timeout_a = msecs_to_jiffies(TPM_I2C_SHORT_TIMEOUT);
diff --git a/drivers/char/tpm/tpm_i2c_nuvoton.c b/drivers/char/tpm/tpm_i2c_nuvoton.c
index 7b158efd49f..23c7b137a7f 100644
--- a/drivers/char/tpm/tpm_i2c_nuvoton.c
+++ b/drivers/char/tpm/tpm_i2c_nuvoton.c
@@ -538,6 +538,11 @@ static int i2c_nuvoton_probe(struct i2c_client *client,
 
 	chip->vendor.priv = devm_kzalloc(dev, sizeof(struct priv_data),
 					 GFP_KERNEL);
+	if (!chip->vendor.priv) {
+		rc = -ENOMEM;
+		goto out_err;
+	}
+
 	init_waitqueue_head(&chip->vendor.read_queue);
 	init_waitqueue_head(&chip->vendor.int_queue);
 
diff --git a/drivers/char/tpm/tpm_i2c_stm_st33.c b/drivers/char/tpm/tpm_i2c_stm_st33.c
index 4669e371342..3f187a529e9 100644
--- a/drivers/char/tpm/tpm_i2c_stm_st33.c
+++ b/drivers/char/tpm/tpm_i2c_stm_st33.c
@@ -397,7 +397,7 @@ static int wait_for_stat(struct tpm_chip *chip, u8 mask, unsigned long timeout,
  */
 static int recv_data(struct tpm_chip *chip, u8 *buf, size_t count)
 {
-	int size = 0, burstcnt, len;
+	int size = 0, burstcnt, len, ret;
 	struct i2c_client *client;
 
 	client = (struct i2c_client *)TPM_VPRIV(chip);
@@ -406,13 +406,15 @@ static int recv_data(struct tpm_chip *chip, u8 *buf, size_t count)
 	       wait_for_stat(chip,
 			     TPM_STS_DATA_AVAIL | TPM_STS_VALID,
 			     chip->vendor.timeout_c,
-			     &chip->vendor.read_queue)
-	       == 0) {
+			     &chip->vendor.read_queue) == 0) {
 		burstcnt = get_burstcount(chip);
 		if (burstcnt < 0)
 			return burstcnt;
 		len = min_t(int, burstcnt, count - size);
-		I2C_READ_DATA(client, TPM_DATA_FIFO, buf + size, len);
+		ret = I2C_READ_DATA(client, TPM_DATA_FIFO, buf + size, len);
+		if (ret < 0)
+			return ret;
+
 		size += len;
 	}
 	return size;
@@ -487,7 +489,7 @@ static int tpm_stm_i2c_send(struct tpm_chip *chip, unsigned char *buf,
 		if (burstcnt < 0)
 			return burstcnt;
 		size = min_t(int, len - i - 1, burstcnt);
-		ret = I2C_WRITE_DATA(client, TPM_DATA_FIFO, buf, size);
+		ret = I2C_WRITE_DATA(client, TPM_DATA_FIFO, buf + i, size);
 		if (ret < 0)
 			goto out_err;
 
diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c
index af74c57e509..643bba7d6f8 100644
--- a/drivers/char/tpm/tpm_ibmvtpm.c
+++ b/drivers/char/tpm/tpm_ibmvtpm.c
@@ -124,7 +124,7 @@ static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count)
 {
 	struct ibmvtpm_dev *ibmvtpm;
 	struct ibmvtpm_crq crq;
-	u64 *word = (u64 *) &crq;
+	__be64 *word = (__be64 *)&crq;
 	int rc;
 
 	ibmvtpm = (struct ibmvtpm_dev *)TPM_VPRIV(chip);
@@ -145,10 +145,11 @@ static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count)
 	memcpy((void *)ibmvtpm->rtce_buf, (void *)buf, count);
 	crq.valid = (u8)IBMVTPM_VALID_CMD;
 	crq.msg = (u8)VTPM_TPM_COMMAND;
-	crq.len = (u16)count;
-	crq.data = ibmvtpm->rtce_dma_handle;
+	crq.len = cpu_to_be16(count);
+	crq.data = cpu_to_be32(ibmvtpm->rtce_dma_handle);
 
-	rc = ibmvtpm_send_crq(ibmvtpm->vdev, word[0], word[1]);
+	rc = ibmvtpm_send_crq(ibmvtpm->vdev, be64_to_cpu(word[0]),
+			      be64_to_cpu(word[1]));
 	if (rc != H_SUCCESS) {
 		dev_err(ibmvtpm->dev, "tpm_ibmvtpm_send failed rc=%d\n", rc);
 		rc = 0;
@@ -186,7 +187,8 @@ static int ibmvtpm_crq_get_rtce_size(struct ibmvtpm_dev *ibmvtpm)
 	crq.valid = (u8)IBMVTPM_VALID_CMD;
 	crq.msg = (u8)VTPM_GET_RTCE_BUFFER_SIZE;
 
-	rc = ibmvtpm_send_crq(ibmvtpm->vdev, buf[0], buf[1]);
+	rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
+			      cpu_to_be64(buf[1]));
 	if (rc != H_SUCCESS)
 		dev_err(ibmvtpm->dev,
 			"ibmvtpm_crq_get_rtce_size failed rc=%d\n", rc);
@@ -212,7 +214,8 @@ static int ibmvtpm_crq_get_version(struct ibmvtpm_dev *ibmvtpm)
 	crq.valid = (u8)IBMVTPM_VALID_CMD;
 	crq.msg = (u8)VTPM_GET_VERSION;
 
-	rc = ibmvtpm_send_crq(ibmvtpm->vdev, buf[0], buf[1]);
+	rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
+			      cpu_to_be64(buf[1]));
 	if (rc != H_SUCCESS)
 		dev_err(ibmvtpm->dev,
 			"ibmvtpm_crq_get_version failed rc=%d\n", rc);
@@ -307,6 +310,14 @@ static int tpm_ibmvtpm_remove(struct vio_dev *vdev)
 static unsigned long tpm_ibmvtpm_get_desired_dma(struct vio_dev *vdev)
 {
 	struct ibmvtpm_dev *ibmvtpm = ibmvtpm_get_data(&vdev->dev);
+
+	/* ibmvtpm initializes at probe time, so the data we are
+	* asking for may not be set yet. Estimate that 4K required
+	* for TCE-mapped buffer in addition to CRQ.
+	*/
+	if (!ibmvtpm)
+		return CRQ_RES_BUF_SIZE + PAGE_SIZE;
+
 	return CRQ_RES_BUF_SIZE + ibmvtpm->rtce_size;
 }
 
@@ -327,7 +338,8 @@ static int tpm_ibmvtpm_suspend(struct device *dev)
 	crq.valid = (u8)IBMVTPM_VALID_CMD;
 	crq.msg = (u8)VTPM_PREPARE_TO_SUSPEND;
 
-	rc = ibmvtpm_send_crq(ibmvtpm->vdev, buf[0], buf[1]);
+	rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
+			      cpu_to_be64(buf[1]));
 	if (rc != H_SUCCESS)
 		dev_err(ibmvtpm->dev,
 			"tpm_ibmvtpm_suspend failed rc=%d\n", rc);
@@ -472,11 +484,11 @@ static void ibmvtpm_crq_process(struct ibmvtpm_crq *crq,
 	case IBMVTPM_VALID_CMD:
 		switch (crq->msg) {
 		case VTPM_GET_RTCE_BUFFER_SIZE_RES:
-			if (crq->len <= 0) {
+			if (be16_to_cpu(crq->len) <= 0) {
 				dev_err(ibmvtpm->dev, "Invalid rtce size\n");
 				return;
 			}
-			ibmvtpm->rtce_size = crq->len;
+			ibmvtpm->rtce_size = be16_to_cpu(crq->len);
 			ibmvtpm->rtce_buf = kmalloc(ibmvtpm->rtce_size,
 						    GFP_KERNEL);
 			if (!ibmvtpm->rtce_buf) {
@@ -497,11 +509,11 @@ static void ibmvtpm_crq_process(struct ibmvtpm_crq *crq,
 
 			return;
 		case VTPM_GET_VERSION_RES:
-			ibmvtpm->vtpm_version = crq->data;
+			ibmvtpm->vtpm_version = be32_to_cpu(crq->data);
 			return;
 		case VTPM_TPM_COMMAND_RES:
 			/* len of the data in rtce buffer */
-			ibmvtpm->res_len = crq->len;
+			ibmvtpm->res_len = be16_to_cpu(crq->len);
 			wake_up_interruptible(&ibmvtpm->wq);
 			return;
 		default:
@@ -567,6 +579,9 @@ static int tpm_ibmvtpm_probe(struct vio_dev *vio_dev,
 		goto cleanup;
 	}
 
+	ibmvtpm->dev = dev;
+	ibmvtpm->vdev = vio_dev;
+
 	crq_q = &ibmvtpm->crq_queue;
 	crq_q->crq_addr = (struct ibmvtpm_crq *)get_zeroed_page(GFP_KERNEL);
 	if (!crq_q->crq_addr) {
@@ -611,8 +626,6 @@ static int tpm_ibmvtpm_probe(struct vio_dev *vio_dev,
 
 	crq_q->index = 0;
 
-	ibmvtpm->dev = dev;
-	ibmvtpm->vdev = vio_dev;
 	TPM_VPRIV(chip) = (void *)ibmvtpm;
 
 	spin_lock_init(&ibmvtpm->rtce_lock);
diff --git a/drivers/char/tpm/tpm_ibmvtpm.h b/drivers/char/tpm/tpm_ibmvtpm.h
index bd82a791f99..b2c231b1bee 100644
--- a/drivers/char/tpm/tpm_ibmvtpm.h
+++ b/drivers/char/tpm/tpm_ibmvtpm.h
@@ -22,9 +22,9 @@
 struct ibmvtpm_crq {
 	u8 valid;
 	u8 msg;
-	u16 len;
-	u32 data;
-	u64 reserved;
+	__be16 len;
+	__be32 data;
+	__be64 reserved;
 } __attribute__((packed, aligned(8)));
 
 struct ibmvtpm_crq_queue {
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index 2c46734b266..51350cd0847 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -75,6 +75,10 @@ enum tis_defaults {
 #define	TPM_DID_VID(l)			(0x0F00 | ((l) << 12))
 #define	TPM_RID(l)			(0x0F04 | ((l) << 12))
 
+struct priv_data {
+	bool irq_tested;
+};
+
 static LIST_HEAD(tis_chips);
 static DEFINE_MUTEX(tis_lock);
 
@@ -338,12 +342,27 @@ out_err:
 	return rc;
 }
 
+static void disable_interrupts(struct tpm_chip *chip)
+{
+	u32 intmask;
+
+	intmask =
+	    ioread32(chip->vendor.iobase +
+		     TPM_INT_ENABLE(chip->vendor.locality));
+	intmask &= ~TPM_GLOBAL_INT_ENABLE;
+	iowrite32(intmask,
+		  chip->vendor.iobase +
+		  TPM_INT_ENABLE(chip->vendor.locality));
+	free_irq(chip->vendor.irq, chip);
+	chip->vendor.irq = 0;
+}
+
 /*
  * If interrupts are used (signaled by an irq set in the vendor structure)
  * tpm.c can skip polling for the data to be available as the interrupt is
  * waited for here
  */
-static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len)
+static int tpm_tis_send_main(struct tpm_chip *chip, u8 *buf, size_t len)
 {
 	int rc;
 	u32 ordinal;
@@ -373,6 +392,30 @@ out_err:
 	return rc;
 }
 
+static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len)
+{
+	int rc, irq;
+	struct priv_data *priv = chip->vendor.priv;
+
+	if (!chip->vendor.irq || priv->irq_tested)
+		return tpm_tis_send_main(chip, buf, len);
+
+	/* Verify receipt of the expected IRQ */
+	irq = chip->vendor.irq;
+	chip->vendor.irq = 0;
+	rc = tpm_tis_send_main(chip, buf, len);
+	chip->vendor.irq = irq;
+	if (!priv->irq_tested)
+		msleep(1);
+	if (!priv->irq_tested) {
+		disable_interrupts(chip);
+		dev_err(chip->dev,
+			FW_BUG "TPM interrupt not working, polling instead\n");
+	}
+	priv->irq_tested = true;
+	return rc;
+}
+
 struct tis_vendor_timeout_override {
 	u32 did_vid;
 	unsigned long timeout_us[4];
@@ -505,6 +548,7 @@ static irqreturn_t tis_int_handler(int dummy, void *dev_id)
 	if (interrupt == 0)
 		return IRQ_NONE;
 
+	((struct priv_data *)chip->vendor.priv)->irq_tested = true;
 	if (interrupt & TPM_INTF_DATA_AVAIL_INT)
 		wake_up_interruptible(&chip->vendor.read_queue);
 	if (interrupt & TPM_INTF_LOCALITY_CHANGE_INT)
@@ -534,9 +578,14 @@ static int tpm_tis_init(struct device *dev, resource_size_t start,
 	u32 vendor, intfcaps, intmask;
 	int rc, i, irq_s, irq_e, probe;
 	struct tpm_chip *chip;
+	struct priv_data *priv;
 
+	priv = devm_kzalloc(dev, sizeof(struct priv_data), GFP_KERNEL);
+	if (priv == NULL)
+		return -ENOMEM;
 	if (!(chip = tpm_register_hardware(dev, &tpm_tis)))
 		return -ENODEV;
+	chip->vendor.priv = priv;
 
 	chip->vendor.iobase = ioremap(start, len);
 	if (!chip->vendor.iobase) {
@@ -605,19 +654,6 @@ static int tpm_tis_init(struct device *dev, resource_size_t start,
 	if (intfcaps & TPM_INTF_DATA_AVAIL_INT)
 		dev_dbg(dev, "\tData Avail Int Support\n");
 
-	/* get the timeouts before testing for irqs */
-	if (tpm_get_timeouts(chip)) {
-		dev_err(dev, "Could not get TPM timeouts and durations\n");
-		rc = -ENODEV;
-		goto out_err;
-	}
-
-	if (tpm_do_selftest(chip)) {
-		dev_err(dev, "TPM self test failed\n");
-		rc = -ENODEV;
-		goto out_err;
-	}
-
 	/* INTERRUPT Setup */
 	init_waitqueue_head(&chip->vendor.read_queue);
 	init_waitqueue_head(&chip->vendor.int_queue);
@@ -719,6 +755,18 @@ static int tpm_tis_init(struct device *dev, resource_size_t start,
 		}
 	}
 
+	if (tpm_get_timeouts(chip)) {
+		dev_err(dev, "Could not get TPM timeouts and durations\n");
+		rc = -ENODEV;
+		goto out_err;
+	}
+
+	if (tpm_do_selftest(chip)) {
+		dev_err(dev, "TPM self test failed\n");
+		rc = -ENODEV;
+		goto out_err;
+	}
+
 	INIT_LIST_HEAD(&chip->vendor.list);
 	mutex_lock(&tis_lock);
 	list_add(&chip->vendor.list, &tis_chips);
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index cf7a561fad7..6e09c1dac2b 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -142,6 +142,7 @@ struct ports_device {
 	 * notification
 	 */
 	struct work_struct control_work;
+	struct work_struct config_work;
 
 	struct list_head ports;
 
@@ -1832,10 +1833,21 @@ static void config_intr(struct virtio_device *vdev)
 
 	portdev = vdev->priv;
 
+	if (!use_multiport(portdev))
+		schedule_work(&portdev->config_work);
+}
+
+static void config_work_handler(struct work_struct *work)
+{
+	struct ports_device *portdev;
+
+	portdev = container_of(work, struct ports_device, control_work);
 	if (!use_multiport(portdev)) {
+		struct virtio_device *vdev;
 		struct port *port;
 		u16 rows, cols;
 
+		vdev = portdev->vdev;
 		virtio_cread(vdev, struct virtio_console_config, cols, &cols);
 		virtio_cread(vdev, struct virtio_console_config, rows, &rows);
 
@@ -2026,12 +2038,14 @@ static int virtcons_probe(struct virtio_device *vdev)
 
 	virtio_device_ready(portdev->vdev);
 
+	INIT_WORK(&portdev->config_work, &config_work_handler);
+	INIT_WORK(&portdev->control_work, &control_work_handler);
+
 	if (multiport) {
 		unsigned int nr_added_bufs;
 
 		spin_lock_init(&portdev->c_ivq_lock);
 		spin_lock_init(&portdev->c_ovq_lock);
-		INIT_WORK(&portdev->control_work, &control_work_handler);
 
 		nr_added_bufs = fill_queue(portdev->c_ivq,
 					   &portdev->c_ivq_lock);
@@ -2099,6 +2113,8 @@ static void virtcons_remove(struct virtio_device *vdev)
 	/* Finish up work that's lined up */
 	if (use_multiport(portdev))
 		cancel_work_sync(&portdev->control_work);
+	else
+		cancel_work_sync(&portdev->config_work);
 
 	list_for_each_entry_safe(port, port2, &portdev->ports, list)
 		unplug_port(port);
@@ -2150,6 +2166,7 @@ static int virtcons_freeze(struct virtio_device *vdev)
 
 	virtqueue_disable_cb(portdev->c_ivq);
 	cancel_work_sync(&portdev->control_work);
+	cancel_work_sync(&portdev->config_work);
 	/*
 	 * Once more: if control_work_handler() was running, it would
 	 * enable the cb as the last step.
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 455fd17d938..32bca44058d 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -58,6 +58,16 @@ config COMMON_CLK_RK808
 	  clocked at 32KHz each. Clkout1 is always on, Clkout2 can off
 	  by control register.
 
+config COMMON_CLK_SCPI
+	tristate "Clock driver controlled via SCPI interface"
+	depends on ARM_SCPI_PROTOCOL || COMPILE_TEST
+	  ---help---
+	  This driver provides support for clocks that are controlled
+	  by firmware that implements the SCPI interface.
+
+	  This driver uses SCPI Message Protocol to interact with the
+	  firmware providing all the clock controls.
+
 config COMMON_CLK_SI5351
 	tristate "Clock driver for SiLabs 5351A/B/C"
 	depends on I2C
@@ -134,6 +144,24 @@ config COMMON_CLK_PXA
 	---help---
 	  Sypport for the Marvell PXA SoC.
 
+config COMMON_CLK_FREQ_STATS_ACCOUNTING
+	bool "Enable clock frequency stats accounting"
+	depends on COMMON_CLK
+	depends on DEBUG_FS
+	---help---
+	 Allows accounting of the time spent by various clocks in each
+	 of its operating frequency. The stats get reported as a part
+	 of clk_summary. Would be be useful in finding out which
+	 components are running at what power states to debug
+	 battery consumption issues.
+
+config COMMON_CLK_BEGIN_ACCOUNTING_FROM_BOOT
+	bool "Start clock frequency stats accounting from boot"
+	depends on COMMON_CLK_FREQ_STATS_ACCOUNTING
+	---help---
+	 Enabling this option starts the frequency accounting right from
+	 the boot.
+
 source "drivers/clk/qcom/Kconfig"
 
 endmenu
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index d5fba5bc6e1..589b7732e5b 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -33,6 +33,7 @@ obj-$(CONFIG_COMMON_CLK_PALMAS)		+= clk-palmas.o
 obj-$(CONFIG_CLK_PPC_CORENET)		+= clk-ppc-corenet.o
 obj-$(CONFIG_COMMON_CLK_RK808)		+= clk-rk808.o
 obj-$(CONFIG_COMMON_CLK_S2MPS11)	+= clk-s2mps11.o
+obj-$(CONFIG_COMMON_CLK_SCPI)           += clk-scpi.o
 obj-$(CONFIG_COMMON_CLK_SI5351)		+= clk-si5351.o
 obj-$(CONFIG_COMMON_CLK_SI570)		+= clk-si570.o
 obj-$(CONFIG_CLK_TWL6040)		+= clk-twl6040.o
diff --git a/drivers/clk/at91/clk-pll.c b/drivers/clk/at91/clk-pll.c
index 6ec79dbc084..cbbe40377ad 100644
--- a/drivers/clk/at91/clk-pll.c
+++ b/drivers/clk/at91/clk-pll.c
@@ -173,8 +173,7 @@ static long clk_pll_get_best_div_mul(struct clk_pll *pll, unsigned long rate,
 	int i = 0;
 
 	/* Check if parent_rate is a valid input rate */
-	if (parent_rate < characteristics->input.min ||
-	    parent_rate > characteristics->input.max)
+	if (parent_rate < characteristics->input.min)
 		return -ERANGE;
 
 	/*
@@ -187,6 +186,15 @@ static long clk_pll_get_best_div_mul(struct clk_pll *pll, unsigned long rate,
 	if (!mindiv)
 		mindiv = 1;
 
+	if (parent_rate > characteristics->input.max) {
+		tmpdiv = DIV_ROUND_UP(parent_rate, characteristics->input.max);
+		if (tmpdiv > PLL_DIV_MAX)
+			return -ERANGE;
+
+		if (tmpdiv > mindiv)
+			mindiv = tmpdiv;
+	}
+
 	/*
 	 * Calculate the maximum divider which is limited by PLL register
 	 * layout (limited by the MUL or DIV field size).
diff --git a/drivers/clk/at91/clk-slow.c b/drivers/clk/at91/clk-slow.c
index 32f7c1b3620..2f13bd5246b 100644
--- a/drivers/clk/at91/clk-slow.c
+++ b/drivers/clk/at91/clk-slow.c
@@ -70,6 +70,7 @@ struct clk_sam9x5_slow {
 
 #define to_clk_sam9x5_slow(hw) container_of(hw, struct clk_sam9x5_slow, hw)
 
+static struct clk *slow_clk;
 
 static int clk_slow_osc_prepare(struct clk_hw *hw)
 {
@@ -357,6 +358,8 @@ at91_clk_register_sam9x5_slow(void __iomem *sckcr,
 	clk = clk_register(NULL, &slowck->hw);
 	if (IS_ERR(clk))
 		kfree(slowck);
+	else
+		slow_clk = clk;
 
 	return clk;
 }
@@ -433,6 +436,8 @@ at91_clk_register_sam9260_slow(struct at91_pmc *pmc,
 	clk = clk_register(NULL, &slowck->hw);
 	if (IS_ERR(clk))
 		kfree(slowck);
+	else
+		slow_clk = clk;
 
 	return clk;
 }
@@ -465,3 +470,25 @@ void __init of_at91sam9260_clk_slow_setup(struct device_node *np,
 
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
+
+/*
+ * FIXME: All slow clk users are not properly claiming it (get + prepare +
+ * enable) before using it.
+ * If all users properly claiming this clock decide that they don't need it
+ * anymore (or are removed), it is disabled while faulty users are still
+ * requiring it, and the system hangs.
+ * Prevent this clock from being disabled until all users are properly
+ * requesting it.
+ * Once this is done we should remove this function and the slow_clk variable.
+ */
+static int __init of_at91_clk_slow_retain(void)
+{
+	if (!slow_clk)
+		return 0;
+
+	__clk_get(slow_clk);
+	clk_prepare_enable(slow_clk);
+
+	return 0;
+}
+arch_initcall(of_at91_clk_slow_retain);
diff --git a/drivers/clk/at91/clk-usb.c b/drivers/clk/at91/clk-usb.c
index a23ac0c724f..0283a5713d6 100644
--- a/drivers/clk/at91/clk-usb.c
+++ b/drivers/clk/at91/clk-usb.c
@@ -56,22 +56,53 @@ static unsigned long at91sam9x5_clk_usb_recalc_rate(struct clk_hw *hw,
 	return DIV_ROUND_CLOSEST(parent_rate, (usbdiv + 1));
 }
 
-static long at91sam9x5_clk_usb_round_rate(struct clk_hw *hw, unsigned long rate,
-					  unsigned long *parent_rate)
+static long at91sam9x5_clk_usb_determine_rate(struct clk_hw *hw,
+					      unsigned long rate,
+					      unsigned long *best_parent_rate,
+					      struct clk_hw **best_parent_hw)
 {
-	unsigned long div;
+	struct clk *parent = NULL;
+	long best_rate = -EINVAL;
+	unsigned long tmp_rate;
+	int best_diff = -1;
+	int tmp_diff;
+	int i;
 
-	if (!rate)
-		return -EINVAL;
+	for (i = 0; i < __clk_get_num_parents(hw->clk); i++) {
+		int div;
 
-	if (rate >= *parent_rate)
-		return *parent_rate;
+		parent = clk_get_parent_by_index(hw->clk, i);
+		if (!parent)
+			continue;
+
+		for (div = 1; div < SAM9X5_USB_MAX_DIV + 2; div++) {
+			unsigned long tmp_parent_rate;
+
+			tmp_parent_rate = rate * div;
+			tmp_parent_rate = __clk_round_rate(parent,
+							   tmp_parent_rate);
+			tmp_rate = DIV_ROUND_CLOSEST(tmp_parent_rate, div);
+			if (tmp_rate < rate)
+				tmp_diff = rate - tmp_rate;
+			else
+				tmp_diff = tmp_rate - rate;
+
+			if (best_diff < 0 || best_diff > tmp_diff) {
+				best_rate = tmp_rate;
+				best_diff = tmp_diff;
+				*best_parent_rate = tmp_parent_rate;
+				*best_parent_hw = __clk_get_hw(parent);
+			}
+
+			if (!best_diff || tmp_rate < rate)
+				break;
+		}
 
-	div = DIV_ROUND_CLOSEST(*parent_rate, rate);
-	if (div > SAM9X5_USB_MAX_DIV + 1)
-		div = SAM9X5_USB_MAX_DIV + 1;
+		if (!best_diff)
+			break;
+	}
 
-	return DIV_ROUND_CLOSEST(*parent_rate, div);
+	return best_rate;
 }
 
 static int at91sam9x5_clk_usb_set_parent(struct clk_hw *hw, u8 index)
@@ -121,7 +152,7 @@ static int at91sam9x5_clk_usb_set_rate(struct clk_hw *hw, unsigned long rate,
 
 static const struct clk_ops at91sam9x5_usb_ops = {
 	.recalc_rate = at91sam9x5_clk_usb_recalc_rate,
-	.round_rate = at91sam9x5_clk_usb_round_rate,
+	.determine_rate = at91sam9x5_clk_usb_determine_rate,
 	.get_parent = at91sam9x5_clk_usb_get_parent,
 	.set_parent = at91sam9x5_clk_usb_set_parent,
 	.set_rate = at91sam9x5_clk_usb_set_rate,
@@ -159,7 +190,7 @@ static const struct clk_ops at91sam9n12_usb_ops = {
 	.disable = at91sam9n12_clk_usb_disable,
 	.is_enabled = at91sam9n12_clk_usb_is_enabled,
 	.recalc_rate = at91sam9x5_clk_usb_recalc_rate,
-	.round_rate = at91sam9x5_clk_usb_round_rate,
+	.determine_rate = at91sam9x5_clk_usb_determine_rate,
 	.set_rate = at91sam9x5_clk_usb_set_rate,
 };
 
@@ -179,7 +210,8 @@ at91sam9x5_clk_register_usb(struct at91_pmc *pmc, const char *name,
 	init.ops = &at91sam9x5_usb_ops;
 	init.parent_names = parent_names;
 	init.num_parents = num_parents;
-	init.flags = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE;
+	init.flags = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE |
+		     CLK_SET_RATE_PARENT;
 
 	usb->hw.init = &init;
 	usb->pmc = pmc;
@@ -207,7 +239,7 @@ at91sam9n12_clk_register_usb(struct at91_pmc *pmc, const char *name,
 	init.ops = &at91sam9n12_usb_ops;
 	init.parent_names = &parent_name;
 	init.num_parents = 1;
-	init.flags = CLK_SET_RATE_GATE;
+	init.flags = CLK_SET_RATE_GATE | CLK_SET_RATE_PARENT;
 
 	usb->hw.init = &init;
 	usb->pmc = pmc;
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index 52d2041fa3f..af2c9919554 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -120,7 +120,7 @@ extern void __init of_at91sam9x5_clk_smd_setup(struct device_node *np,
 					       struct at91_pmc *pmc);
 #endif
 
-#if defined(CONFIG_HAVE_AT91_SMD)
+#if defined(CONFIG_HAVE_AT91_H32MX)
 extern void __init of_sama5d4_clk_h32mx_setup(struct device_node *np,
 					      struct at91_pmc *pmc);
 #endif
diff --git a/drivers/clk/berlin/bg2q.c b/drivers/clk/berlin/bg2q.c
index 21784e4eb3f..440ef81ab15 100644
--- a/drivers/clk/berlin/bg2q.c
+++ b/drivers/clk/berlin/bg2q.c
@@ -285,7 +285,6 @@ static const struct berlin2_gate_data bg2q_gates[] __initconst = {
 	{ "pbridge",	"perif",	15, CLK_IGNORE_UNUSED },
 	{ "sdio",	"perif",	16, CLK_IGNORE_UNUSED },
 	{ "nfc",	"perif",	18 },
-	{ "smemc",	"perif",	19 },
 	{ "pcie",	"perif",	22 },
 };
 
diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index c0a842b335c..a52154caf52 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -129,12 +129,6 @@ static unsigned long clk_divider_recalc_rate(struct clk_hw *hw,
 	return DIV_ROUND_UP(parent_rate, div);
 }
 
-/*
- * The reverse of DIV_ROUND_UP: The maximum number which
- * divided by m is r
- */
-#define MULT_ROUND_UP(r, m) ((r) * (m) + (m) - 1)
-
 static bool _is_valid_table_div(const struct clk_div_table *table,
 							 unsigned int div)
 {
@@ -208,6 +202,7 @@ static int _div_round_closest(struct clk_divider *divider,
 		unsigned long parent_rate, unsigned long rate)
 {
 	int up, down, div;
+	unsigned long up_rate, down_rate;
 
 	up = down = div = DIV_ROUND_CLOSEST(parent_rate, rate);
 
@@ -219,7 +214,10 @@ static int _div_round_closest(struct clk_divider *divider,
 		down = _round_down_table(divider->table, div);
 	}
 
-	return (up - div) <= (div - down) ? up : down;
+	up_rate = DIV_ROUND_UP(parent_rate, up);
+	down_rate = DIV_ROUND_UP(parent_rate, down);
+
+	return (rate - up_rate) <= (down_rate - rate) ? up : down;
 }
 
 static int _div_round(struct clk_divider *divider, unsigned long parent_rate,
@@ -300,7 +298,7 @@ static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
 			return i;
 		}
 		parent_rate = __clk_round_rate(__clk_get_parent(hw->clk),
-				MULT_ROUND_UP(rate, i));
+					       rate * i);
 		now = DIV_ROUND_UP(parent_rate, i);
 		if (_is_best_div(divider, rate, now, best)) {
 			bestdiv = i;
diff --git a/drivers/clk/clk-gate.c b/drivers/clk/clk-gate.c
index 51fd87fb7ba..da00eeb95da 100644
--- a/drivers/clk/clk-gate.c
+++ b/drivers/clk/clk-gate.c
@@ -128,7 +128,7 @@ struct clk *clk_register_gate(struct device *dev, const char *name,
 	struct clk_init_data init;
 
 	if (clk_gate_flags & CLK_GATE_HIWORD_MASK) {
-		if (bit_idx > 16) {
+		if (bit_idx > 15) {
 			pr_err("gate bit exceeds LOWORD field\n");
 			return ERR_PTR(-EINVAL);
 		}
diff --git a/drivers/clk/clk-ppc-corenet.c b/drivers/clk/clk-ppc-corenet.c
index 8e58edfeeb3..8b284be4efa 100644
--- a/drivers/clk/clk-ppc-corenet.c
+++ b/drivers/clk/clk-ppc-corenet.c
@@ -291,7 +291,7 @@ static const struct of_device_id ppc_clk_ids[] __initconst = {
 	{}
 };
 
-static struct platform_driver ppc_corenet_clk_driver __initdata = {
+static struct platform_driver ppc_corenet_clk_driver = {
 	.driver = {
 		.name = "ppc_corenet_clock",
 		.owner = THIS_MODULE,
diff --git a/drivers/clk/clk-scpi.c b/drivers/clk/clk-scpi.c
new file mode 100644
index 00000000000..164e848dac1
--- /dev/null
+++ b/drivers/clk/clk-scpi.c
@@ -0,0 +1,323 @@
+/*
+ * System Control and Power Interface (SCPI) Protocol based clock driver
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/of.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/scpi_protocol.h>
+
+struct scpi_clk {
+	u32 id;
+	struct clk_hw hw;
+	struct scpi_dvfs_info *info;
+	struct scpi_ops *scpi_ops;
+	unsigned long rate_min;
+	unsigned long rate_max;
+};
+
+#define to_scpi_clk(clk) container_of(clk, struct scpi_clk, hw)
+
+static struct platform_device *cpufreq_dev;
+
+static unsigned long scpi_clk_recalc_rate(struct clk_hw *hw,
+					  unsigned long parent_rate)
+{
+	struct scpi_clk *clk = to_scpi_clk(hw);
+
+	return clk->scpi_ops->clk_get_val(clk->id);
+}
+
+static long scpi_clk_round_rate(struct clk_hw *hw, unsigned long rate,
+				unsigned long *parent_rate)
+{
+	struct scpi_clk *clk = to_scpi_clk(hw);
+
+	if (clk->rate_min && rate < clk->rate_min)
+		rate = clk->rate_min;
+	if (clk->rate_max && rate > clk->rate_max)
+		rate = clk->rate_max;
+
+	return rate;
+}
+
+static int scpi_clk_set_rate(struct clk_hw *hw, unsigned long rate,
+			     unsigned long parent_rate)
+{
+	struct scpi_clk *clk = to_scpi_clk(hw);
+
+	return clk->scpi_ops->clk_set_val(clk->id, rate);
+}
+
+static const struct clk_ops scpi_clk_ops = {
+	.recalc_rate = scpi_clk_recalc_rate,
+	.round_rate = scpi_clk_round_rate,
+	.set_rate = scpi_clk_set_rate,
+};
+
+/* find closest match to given frequency in OPP table */
+static int __scpi_dvfs_round_rate(struct scpi_clk *clk, unsigned long rate)
+{
+	int idx;
+	u32 fmin = 0, fmax = ~0, ftmp;
+	const struct scpi_opp *opp = clk->info->opps;
+
+	for (idx = 0; idx < clk->info->count; idx++, opp++) {
+		ftmp = opp->freq;
+		if (ftmp >= (u32)rate) {
+			if (ftmp <= fmax)
+				fmax = ftmp;
+			break;
+		} else if (ftmp >= fmin) {
+			fmin = ftmp;
+		}
+	}
+	return fmax != ~0 ? fmax : fmin;
+}
+
+static unsigned long scpi_dvfs_recalc_rate(struct clk_hw *hw,
+					   unsigned long parent_rate)
+{
+	struct scpi_clk *clk = to_scpi_clk(hw);
+	int idx = clk->scpi_ops->dvfs_get_idx(clk->id);
+	const struct scpi_opp *opp;
+
+	if (idx < 0)
+		return 0;
+
+	opp = clk->info->opps + idx;
+	return opp->freq;
+}
+
+static long scpi_dvfs_round_rate(struct clk_hw *hw, unsigned long rate,
+				 unsigned long *parent_rate)
+{
+	struct scpi_clk *clk = to_scpi_clk(hw);
+
+	return __scpi_dvfs_round_rate(clk, rate);
+}
+
+static int __scpi_find_dvfs_index(struct scpi_clk *clk, unsigned long rate)
+{
+	int idx, max_opp = clk->info->count;
+	const struct scpi_opp *opp = clk->info->opps;
+
+	for (idx = 0; idx < max_opp; idx++, opp++)
+		if (opp->freq == rate)
+			return idx;
+	return -EINVAL;
+}
+
+static int scpi_dvfs_set_rate(struct clk_hw *hw, unsigned long rate,
+			      unsigned long parent_rate)
+{
+	struct scpi_clk *clk = to_scpi_clk(hw);
+	int ret = __scpi_find_dvfs_index(clk, rate);
+
+	if (ret < 0)
+		return ret;
+	return clk->scpi_ops->dvfs_set_idx(clk->id, (u8)ret);
+}
+
+static const struct clk_ops scpi_dvfs_ops = {
+	.recalc_rate = scpi_dvfs_recalc_rate,
+	.round_rate = scpi_dvfs_round_rate,
+	.set_rate = scpi_dvfs_set_rate,
+};
+
+static const struct of_device_id scpi_clk_match[] = {
+	{ .compatible = "arm,scpi-dvfs-clocks", .data = &scpi_dvfs_ops, },
+	{ .compatible = "arm,scpi-variable-clocks", .data = &scpi_clk_ops, },
+	{}
+};
+
+static struct clk *
+scpi_clk_ops_init(struct device *dev, const struct of_device_id *match,
+		  struct scpi_clk *sclk, const char *name)
+{
+	struct clk_init_data init;
+
+	init.name = name;
+	init.flags = CLK_IS_ROOT;
+	init.num_parents = 0;
+	init.ops = match->data;
+	sclk->hw.init = &init;
+	sclk->scpi_ops = get_scpi_ops();
+
+	if (init.ops == &scpi_dvfs_ops) {
+		sclk->info = sclk->scpi_ops->dvfs_get_info(sclk->id);
+		if (IS_ERR(sclk->info))
+			return NULL;
+	} else if (init.ops == &scpi_clk_ops) {
+		if (sclk->scpi_ops->clk_get_range(sclk->id, &sclk->rate_min,
+				      &sclk->rate_max) || !sclk->rate_max)
+			return NULL;
+	} else {
+		return NULL;
+	}
+
+	return devm_clk_register(dev, &sclk->hw);
+}
+
+struct scpi_clk_data {
+	struct scpi_clk **clk;
+	unsigned int clk_num;
+};
+
+static struct clk *
+scpi_of_clk_src_get(struct of_phandle_args *clkspec, void *data)
+{
+	struct scpi_clk *sclk;
+	struct scpi_clk_data *clk_data = data;
+	unsigned int idx = clkspec->args[0], count;
+
+	for (count = 0; count < clk_data->clk_num; count++) {
+		sclk = clk_data->clk[count];
+		if (idx == sclk->id)
+			return sclk->hw.clk;
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static int scpi_clk_add(struct device *dev, struct device_node *np,
+			const struct of_device_id *match)
+{
+	struct clk **clks;
+	int idx, count;
+	struct scpi_clk_data *clk_data;
+
+	count = of_property_count_strings(np, "clock-output-names");
+	if (count < 0) {
+		dev_err(dev, "%s: invalid clock output count\n", np->name);
+		return -EINVAL;
+	}
+
+	clk_data = devm_kmalloc(dev, sizeof(*clk_data), GFP_KERNEL);
+	if (!clk_data)
+		return -ENOMEM;
+
+	clk_data->clk_num = count;
+	clk_data->clk = devm_kcalloc(dev, count, sizeof(*clk_data->clk),
+				     GFP_KERNEL);
+	if (!clk_data->clk)
+		return -ENOMEM;
+
+	clks = devm_kcalloc(dev, count, sizeof(*clks), GFP_KERNEL);
+	if (!clks)
+		return -ENOMEM;
+
+	for (idx = 0; idx < count; idx++) {
+		struct scpi_clk *sclk;
+		const char *name;
+		u32 val;
+
+		sclk = devm_kzalloc(dev, sizeof(*sclk), GFP_KERNEL);
+		if (!sclk)
+			return -ENOMEM;
+
+		if (of_property_read_string_index(np, "clock-output-names",
+						  idx, &name)) {
+			dev_err(dev, "invalid clock name @ %s\n", np->name);
+			return -EINVAL;
+		}
+
+		if (of_property_read_u32_index(np, "clock-indices",
+					       idx, &val)) {
+			dev_err(dev, "invalid clock index @ %s\n", np->name);
+			return -EINVAL;
+		}
+
+		sclk->id = val;
+
+		clks[idx] = scpi_clk_ops_init(dev, match, sclk, name);
+		if (IS_ERR_OR_NULL(clks[idx]))
+			dev_err(dev, "failed to register clock '%s'\n", name);
+		else
+			dev_dbg(dev, "Registered clock '%s'\n", name);
+		clk_data->clk[idx] = sclk;
+	}
+
+	return of_clk_add_provider(np, scpi_of_clk_src_get, clk_data);
+}
+
+static int scpi_clocks_remove(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *child, *np = dev->of_node;
+
+	if (cpufreq_dev) {
+		platform_device_unregister(cpufreq_dev);
+		cpufreq_dev = NULL;
+	}
+
+	for_each_available_child_of_node(np, child)
+		of_clk_del_provider(np);
+	return 0;
+}
+
+static int scpi_clocks_probe(struct platform_device *pdev)
+{
+	int ret;
+	struct device *dev = &pdev->dev;
+	struct device_node *child, *np = dev->of_node;
+	const struct of_device_id *match;
+
+	if (!get_scpi_ops())
+		return -ENXIO;
+
+	for_each_available_child_of_node(np, child) {
+		match = of_match_node(scpi_clk_match, child);
+		if (!match)
+			continue;
+		ret = scpi_clk_add(dev, child, match);
+		if (ret) {
+			scpi_clocks_remove(pdev);
+			return ret;
+		}
+	}
+	/* Add the virtual cpufreq device */
+	cpufreq_dev = platform_device_register_simple("scpi-cpufreq",
+						      -1, NULL, 0);
+	if (!cpufreq_dev)
+		pr_warn("unable to register cpufreq device");
+
+	return 0;
+}
+
+static const struct of_device_id scpi_clocks_ids[] = {
+	{ .compatible = "arm,scpi-clocks", },
+	{}
+};
+
+static struct platform_driver scpi_clocks_driver = {
+	.driver	= {
+		.name = "scpi_clocks",
+		.of_match_table = scpi_clocks_ids,
+	},
+	.probe = scpi_clocks_probe,
+	.remove = scpi_clocks_remove,
+};
+module_platform_driver(scpi_clocks_driver);
+
+MODULE_AUTHOR("Sudeep Holla <sudeep.holla@arm.com>");
+MODULE_DESCRIPTION("ARM SCPI clock driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 4896ae9e23d..d2f0a565f75 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -114,6 +114,134 @@ static struct hlist_head *orphan_list[] = {
 	NULL,
 };
 
+#ifdef CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING
+
+#ifdef CONFIG_COMMON_CLK_BEGIN_ACCOUNTING_FROM_BOOT
+static bool freq_stats_on = true;
+#else
+static bool freq_stats_on;
+#endif /*CONFIG_COMMON_CLK_BEGIN_ACCOUNTING_FROM_BOOT*/
+
+static void free_tree(struct rb_node *node)
+{
+	struct freq_stats *this;
+
+	if (!node)
+		return;
+
+	free_tree(node->rb_left);
+	free_tree(node->rb_right);
+
+	this = rb_entry(node, struct freq_stats, node);
+	kfree(this);
+}
+
+static struct freq_stats *freq_stats_insert(struct rb_root *freq_stats_table,
+		unsigned long rate)
+{
+	struct rb_node **new = &(freq_stats_table->rb_node), *parent = NULL;
+	struct freq_stats *this;
+
+	/* Figure out where to put new node */
+	while (*new) {
+		this = rb_entry(*new, struct freq_stats, node);
+		parent = *new;
+
+		if (rate < this->rate)
+			new = &((*new)->rb_left);
+		else if (rate > this->rate)
+			new = &((*new)->rb_right);
+		else
+			return this;
+	}
+
+	this = kzalloc(sizeof(*this), GFP_ATOMIC);
+	this->rate = rate;
+
+	/* Add new node and rebalance tree. */
+	rb_link_node(&this->node, parent, new);
+	rb_insert_color(&this->node, freq_stats_table);
+
+	return this;
+}
+
+static void generic_print_freq_stats_table(struct seq_file *m,
+				struct clk *clk,
+				bool indent, int level)
+{
+	struct rb_node *pos;
+	struct freq_stats *cur;
+
+	if (indent)
+		seq_printf(m, "%*s*%s%20s", level * 3 + 1, "",
+			!clk->current_freq_stats ? "[" : "",
+			"default_freq");
+	else
+		seq_printf(m, "%2s%20s", !clk->current_freq_stats ? "[" : "",
+			"default_freq");
+
+	if (!clk->current_freq_stats && !ktime_equal(clk->start_time,
+					ktime_set(0, 0)))
+		seq_printf(m, "%40llu",
+			ktime_to_ms(ktime_add(clk->default_freq_time,
+			ktime_sub(ktime_get(), clk->start_time))));
+	else
+		seq_printf(m, "%40llu", ktime_to_ms(clk->default_freq_time));
+
+	if (!clk->current_freq_stats)
+		seq_puts(m, "]");
+
+	seq_puts(m, "\n");
+
+	for (pos = rb_first(&clk->freq_stats_table); pos; pos = rb_next(pos)) {
+		cur = rb_entry(pos, typeof(*cur), node);
+
+		if (indent)
+			seq_printf(m, "%*s*%s%20lu", level * 3 + 1, "",
+				cur->rate == clk->rate ? "[" : "", cur->rate);
+		else
+			seq_printf(m, "%2s%20lu", cur->rate == clk->rate ?
+				"[" : "", cur->rate);
+
+		if (cur->rate == clk->rate && !ktime_equal(clk->start_time,
+					ktime_set(0, 0)))
+			seq_printf(m, "%40llu",
+			ktime_to_ms(ktime_add(cur->time_spent,
+			ktime_sub(ktime_get(), clk->start_time))));
+		else
+			seq_printf(m, "%40llu", ktime_to_ms(cur->time_spent));
+
+		if (cur->rate == clk->rate)
+			seq_puts(m, "]");
+		seq_puts(m, "\n");
+	}
+}
+
+static int clock_print_freq_stats_table(struct seq_file *m, void *unused)
+{
+	struct clk *clk = m->private;
+
+	if (!(clk->flags & CLK_GET_RATE_NOCACHE))
+		generic_print_freq_stats_table(m, clk, false, 0);
+
+	return 0;
+}
+
+static int freq_stats_table_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, clock_print_freq_stats_table,
+		inode->i_private);
+}
+
+static const struct file_operations freq_stats_table_fops = {
+	.open           = freq_stats_table_open,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release        = seq_release,
+};
+#endif /*CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING*/
+
+
 static void clk_summary_show_one(struct seq_file *s, struct clk *c, int level)
 {
 	if (!c)
@@ -124,6 +252,12 @@ static void clk_summary_show_one(struct seq_file *s, struct clk *c, int level)
 		   30 - level * 3, c->name,
 		   c->enable_count, c->prepare_count, clk_get_rate(c),
 		   clk_get_accuracy(c), clk_get_phase(c));
+
+#ifdef CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING
+	if (!(c->flags & CLK_GET_RATE_NOCACHE))
+		generic_print_freq_stats_table(s, c, true, level);
+#endif /*CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING*/
+
 }
 
 static void clk_summary_show_subtree(struct seq_file *s, struct clk *c,
@@ -240,7 +374,78 @@ static const struct file_operations clk_dump_fops = {
 	.release	= single_release,
 };
 
-/* caller must hold prepare_lock */
+#ifdef CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING
+static int freq_stats_get(void *unused, u64 *val)
+{
+	*val = freq_stats_on;
+	return 0;
+}
+
+static void clk_traverse_subtree(struct clk *clk, int freq_stats_on)
+{
+	struct clk *child;
+	struct rb_node *node;
+
+	if (!clk)
+		return;
+
+	if (freq_stats_on) {
+		for (node = rb_first(&clk->freq_stats_table);
+			node; node = rb_next(node))
+			rb_entry(node, struct freq_stats, node)->time_spent =
+							ktime_set(0, 0);
+
+		clk->current_freq_stats = freq_stats_insert(
+						&clk->freq_stats_table,
+						clk_get_rate(clk));
+
+		if (clk->enable_count > 0)
+			clk->start_time = ktime_get();
+	} else {
+		if (clk->enable_count > 0) {
+			if (!clk->current_freq_stats)
+				clk->default_freq_time =
+				ktime_add(clk->default_freq_time,
+				ktime_sub(ktime_get(), clk->start_time));
+			else
+				clk->current_freq_stats->time_spent =
+				ktime_add(clk->current_freq_stats->time_spent,
+				ktime_sub(ktime_get(), clk->start_time));
+
+			clk->start_time = ktime_set(0, 0);
+		}
+	}
+	hlist_for_each_entry(child, &clk->children, child_node)
+		clk_traverse_subtree(child, freq_stats_on);
+}
+
+static int freq_stats_set(void *data, u64 val)
+{
+	struct clk *c;
+	unsigned long flags;
+	struct hlist_head **lists = (struct hlist_head **)data;
+
+	clk_prepare_lock();
+	flags = clk_enable_lock();
+
+	if (val == 0)
+		freq_stats_on = 0;
+	else
+		freq_stats_on = 1;
+
+	for (; *lists; lists++)
+		hlist_for_each_entry(c, *lists, child_node)
+			clk_traverse_subtree(c, freq_stats_on);
+
+	clk_enable_unlock(flags);
+	clk_prepare_unlock();
+
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(freq_stats_fops, freq_stats_get,
+			freq_stats_set, "%llu\n");
+#endif /*CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING*/
+
 static int clk_debug_create_one(struct clk *clk, struct dentry *pdentry)
 {
 	struct dentry *d;
@@ -292,6 +497,14 @@ static int clk_debug_create_one(struct clk *clk, struct dentry *pdentry)
 	if (!d)
 		goto err_out;
 
+#ifdef CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING
+	d = debugfs_create_file("frequency_stats_table", S_IRUGO, clk->dentry,
+			clk, &freq_stats_table_fops);
+
+	if (!d)
+		goto err_out;
+#endif /*CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING*/
+
 	if (clk->ops->debug_init) {
 		ret = clk->ops->debug_init(clk->hw, clk->dentry);
 		if (ret)
@@ -344,13 +557,9 @@ unlock:
 static void clk_debug_unregister(struct clk *clk)
 {
 	mutex_lock(&clk_debug_lock);
-	if (!clk->dentry)
-		goto out;
-
 	hlist_del_init(&clk->debug_node);
 	debugfs_remove_recursive(clk->dentry);
 	clk->dentry = NULL;
-out:
 	mutex_unlock(&clk_debug_lock);
 }
 
@@ -408,6 +617,13 @@ static int __init clk_debug_init(void)
 	if (!d)
 		return -ENOMEM;
 
+#ifdef CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING
+	d = debugfs_create_file("freq_stats_on", S_IRUGO|S_IWUSR,
+				rootdir, &all_lists, &freq_stats_fops);
+	if (!d)
+		return -ENOMEM;
+#endif /*CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING*/
+
 	mutex_lock(&clk_debug_lock);
 	hlist_for_each_entry(clk, &clk_debug_list, debug_node)
 		clk_debug_create_one(clk, rootdir);
@@ -857,6 +1073,22 @@ static void __clk_disable(struct clk *clk)
 	if (clk->ops->disable)
 		clk->ops->disable(clk->hw);
 
+#ifdef CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING
+
+	if (freq_stats_on) {
+		if (!clk->current_freq_stats)
+			clk->default_freq_time =
+			ktime_add(clk->default_freq_time,
+			ktime_sub(ktime_get(), clk->start_time));
+		else
+			clk->current_freq_stats->time_spent =
+			ktime_add(clk->current_freq_stats->time_spent,
+			ktime_sub(ktime_get(), clk->start_time));
+
+		clk->start_time = ktime_set(0, 0);
+	}
+#endif /*CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING*/
+
 	__clk_disable(clk->parent);
 }
 
@@ -908,6 +1140,11 @@ static int __clk_enable(struct clk *clk)
 				return ret;
 			}
 		}
+
+#ifdef CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING
+	if (freq_stats_on)
+		clk->start_time = ktime_get();
+#endif /*CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING*/
 	}
 
 	clk->enable_count++;
@@ -1488,6 +1725,32 @@ static void clk_change_rate(struct clk *clk)
 
 	clk->rate = clk_recalc(clk, best_parent_rate);
 
+#ifdef CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING
+	if (freq_stats_on) {
+		if (!ktime_equal(clk->start_time, ktime_set(0, 0))) {
+			if (!clk->current_freq_stats)
+				clk->default_freq_time =
+					ktime_add(clk->default_freq_time,
+					ktime_sub(ktime_get(),
+					clk->start_time));
+			else
+				clk->current_freq_stats->time_spent =
+					ktime_add(
+					clk->current_freq_stats->time_spent,
+					ktime_sub(ktime_get(),
+					clk->start_time));
+		}
+
+		clk->current_freq_stats = freq_stats_insert(
+						&clk->freq_stats_table,
+						clk->rate);
+
+		if (clk->enable_count > 0)
+			clk->start_time = ktime_get();
+	}
+#endif /*CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING*/
+
+
 	if (clk->notifier_count && old_rate != clk->rate)
 		__clk_notify(clk, POST_RATE_CHANGE, old_rate, clk->rate);
 
@@ -1944,7 +2207,6 @@ int __clk_init(struct device *dev, struct clk *clk)
 	else
 		clk->rate = 0;
 
-	clk_debug_register(clk);
 	/*
 	 * walk the list of orphan clocks and reparent any that are children of
 	 * this clock
@@ -1979,6 +2241,9 @@ int __clk_init(struct device *dev, struct clk *clk)
 out:
 	clk_prepare_unlock();
 
+	if (!ret)
+		clk_debug_register(clk);
+
 	return ret;
 }
 
@@ -2115,6 +2380,11 @@ static void __clk_release(struct kref *ref)
 
 	kfree(clk->parent_names);
 	kfree(clk->name);
+
+#ifdef CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING
+	free_tree(clk->freq_stats_table.rb_node);
+#endif/*CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING*/
+
 	kfree(clk);
 }
 
@@ -2273,14 +2543,17 @@ int __clk_get(struct clk *clk)
 
 void __clk_put(struct clk *clk)
 {
+	struct module *owner;
+
 	if (!clk || WARN_ON_ONCE(IS_ERR(clk)))
 		return;
 
 	clk_prepare_lock();
+	owner = clk->owner;
 	kref_put(&clk->ref, __clk_release);
 	clk_prepare_unlock();
 
-	module_put(clk->owner);
+	module_put(owner);
 }
 
 /***        clk rate change notifiers        ***/
diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c
index cfa9eb4fe9c..f76b6853b61 100644
--- a/drivers/clk/qcom/clk-rcg2.c
+++ b/drivers/clk/qcom/clk-rcg2.c
@@ -240,7 +240,7 @@ static int clk_rcg2_configure(struct clk_rcg2 *rcg, const struct freq_tbl *f)
 	mask |= CFG_SRC_SEL_MASK | CFG_MODE_MASK;
 	cfg = f->pre_div << CFG_SRC_DIV_SHIFT;
 	cfg |= rcg->parent_map[f->src] << CFG_SRC_SEL_SHIFT;
-	if (rcg->mnd_width && f->n)
+	if (rcg->mnd_width && f->n && (f->m != f->n))
 		cfg |= CFG_MODE_DUAL_EDGE;
 	ret = regmap_update_bits(rcg->clkr.regmap,
 			rcg->cmd_rcgr + CFG_REG, mask, cfg);
diff --git a/drivers/clk/qcom/gcc-ipq806x.c b/drivers/clk/qcom/gcc-ipq806x.c
index 5cd62a709ac..8c37d9c374e 100644
--- a/drivers/clk/qcom/gcc-ipq806x.c
+++ b/drivers/clk/qcom/gcc-ipq806x.c
@@ -514,8 +514,8 @@ static struct freq_tbl clk_tbl_gsbi_qup[] = {
 	{ 10800000, P_PXO,  1, 2,  5 },
 	{ 15060000, P_PLL8, 1, 2, 51 },
 	{ 24000000, P_PLL8, 4, 1,  4 },
+	{ 25000000, P_PXO,  1, 0,  0 },
 	{ 25600000, P_PLL8, 1, 1, 15 },
-	{ 27000000, P_PXO,  1, 0,  0 },
 	{ 48000000, P_PLL8, 4, 1,  2 },
 	{ 51200000, P_PLL8, 1, 2, 15 },
 	{ }
diff --git a/drivers/clk/rockchip/clk-rk3188.c b/drivers/clk/rockchip/clk-rk3188.c
index beed49c7912..8088b384ce6 100644
--- a/drivers/clk/rockchip/clk-rk3188.c
+++ b/drivers/clk/rockchip/clk-rk3188.c
@@ -210,6 +210,17 @@ PNAME(mux_sclk_hsadc_p)		= { "hsadc_src", "hsadc_frac", "ext_hsadc" };
 PNAME(mux_mac_p)		= { "gpll", "dpll" };
 PNAME(mux_sclk_macref_p)	= { "mac_src", "ext_rmii" };
 
+static struct rockchip_pll_clock rk3066_pll_clks[] __initdata = {
+	[apll] = PLL(pll_rk3066, PLL_APLL, "apll", mux_pll_p, 0, RK2928_PLL_CON(0),
+		     RK2928_MODE_CON, 0, 5, rk3188_pll_rates),
+	[dpll] = PLL(pll_rk3066, PLL_DPLL, "dpll", mux_pll_p, 0, RK2928_PLL_CON(4),
+		     RK2928_MODE_CON, 4, 4, NULL),
+	[cpll] = PLL(pll_rk3066, PLL_CPLL, "cpll", mux_pll_p, 0, RK2928_PLL_CON(8),
+		     RK2928_MODE_CON, 8, 6, rk3188_pll_rates),
+	[gpll] = PLL(pll_rk3066, PLL_GPLL, "gpll", mux_pll_p, 0, RK2928_PLL_CON(12),
+		     RK2928_MODE_CON, 12, 7, rk3188_pll_rates),
+};
+
 static struct rockchip_pll_clock rk3188_pll_clks[] __initdata = {
 	[apll] = PLL(pll_rk3066, PLL_APLL, "apll", mux_pll_p, 0, RK2928_PLL_CON(0),
 		     RK2928_MODE_CON, 0, 6, rk3188_pll_rates),
@@ -742,8 +753,8 @@ static void __init rk3188_common_clk_init(struct device_node *np)
 static void __init rk3066a_clk_init(struct device_node *np)
 {
 	rk3188_common_clk_init(np);
-	rockchip_clk_register_plls(rk3188_pll_clks,
-				   ARRAY_SIZE(rk3188_pll_clks),
+	rockchip_clk_register_plls(rk3066_pll_clks,
+				   ARRAY_SIZE(rk3066_pll_clks),
 				   RK3066_GRF_SOC_STATUS);
 	rockchip_clk_register_branches(rk3066a_clk_branches,
 				  ARRAY_SIZE(rk3066a_clk_branches));
diff --git a/drivers/clk/rockchip/clk-rk3288.c b/drivers/clk/rockchip/clk-rk3288.c
index 23278291da4..6dbc64759a5 100644
--- a/drivers/clk/rockchip/clk-rk3288.c
+++ b/drivers/clk/rockchip/clk-rk3288.c
@@ -142,20 +142,20 @@ struct rockchip_pll_rate_table rk3288_pll_rates[] = {
 	}
 
 static struct rockchip_cpuclk_rate_table rk3288_cpuclk_rates[] __initdata = {
-	RK3288_CPUCLK_RATE(1800000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE(1704000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE(1608000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE(1512000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE(1416000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE(1200000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE(1008000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE( 816000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE( 696000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE( 600000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE( 408000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE( 312000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE( 216000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE( 126000000, 2, 4, 2, 4, 4),
+	RK3288_CPUCLK_RATE(1800000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE(1704000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE(1608000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE(1512000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE(1416000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE(1200000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE(1008000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE( 816000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE( 696000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE( 600000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE( 408000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE( 312000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE( 216000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE( 126000000, 1, 3, 1, 3, 3),
 };
 
 static const struct rockchip_cpuclk_reg_data rk3288_cpuclk_data = {
diff --git a/drivers/clk/samsung/clk-exynos-audss.c b/drivers/clk/samsung/clk-exynos-audss.c
index 13eae14c2cc..b50469faf70 100644
--- a/drivers/clk/samsung/clk-exynos-audss.c
+++ b/drivers/clk/samsung/clk-exynos-audss.c
@@ -210,6 +210,10 @@ static int exynos_audss_clk_remove(struct platform_device *pdev)
 {
 	int i;
 
+#ifdef CONFIG_PM_SLEEP
+	unregister_syscore_ops(&exynos_audss_clk_syscore_ops);
+#endif
+
 	of_clk_del_provider(pdev->dev.of_node);
 
 	for (i = 0; i < clk_data.clk_num; i++) {
diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index 940f02837b8..6197317ea2d 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -1354,7 +1354,7 @@ static struct samsung_pll_clock exynos4x12_plls[nr_plls] __initdata = {
 			VPLL_LOCK, VPLL_CON0, NULL),
 };
 
-static void __init exynos4_core_down_clock(enum exynos4_soc soc)
+static void __init exynos4x12_core_down_clock(void)
 {
 	unsigned int tmp;
 
@@ -1373,11 +1373,9 @@ static void __init exynos4_core_down_clock(enum exynos4_soc soc)
 	__raw_writel(tmp, reg_base + PWR_CTRL1);
 
 	/*
-	 * Disable the clock up feature on Exynos4x12, in case it was
-	 * enabled by bootloader.
+	 * Disable the clock up feature in case it was enabled by bootloader.
 	 */
-	if (exynos4_soc == EXYNOS4X12)
-		__raw_writel(0x0, reg_base + E4X12_PWR_CTRL2);
+	__raw_writel(0x0, reg_base + E4X12_PWR_CTRL2);
 }
 
 /* register exynos4 clocks */
@@ -1474,7 +1472,8 @@ static void __init exynos4_clk_init(struct device_node *np,
 	samsung_clk_register_alias(ctx, exynos4_aliases,
 			ARRAY_SIZE(exynos4_aliases));
 
-	exynos4_core_down_clock(soc);
+	if (soc == EXYNOS4X12)
+		exynos4x12_core_down_clock();
 	exynos4_clk_sleep_init();
 
 	samsung_clk_of_add_provider(np, ctx);
diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c
index d5dc951264c..b18e22fb25a 100644
--- a/drivers/clk/sunxi/clk-sunxi.c
+++ b/drivers/clk/sunxi/clk-sunxi.c
@@ -419,6 +419,7 @@ static struct clk_factors_config sun6i_a31_pll1_config = {
 	.kwidth = 2,
 	.mshift = 0,
 	.mwidth = 2,
+	.n_start = 1,
 };
 
 static struct clk_factors_config sun8i_a23_pll1_config = {
diff --git a/drivers/clk/tegra/clk.c b/drivers/clk/tegra/clk.c
index 97dc8595c3c..c51f7c84c16 100644
--- a/drivers/clk/tegra/clk.c
+++ b/drivers/clk/tegra/clk.c
@@ -272,7 +272,7 @@ void __init tegra_add_of_provider(struct device_node *np)
 	of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
 
 	rst_ctlr.of_node = np;
-	rst_ctlr.nr_resets = clk_num * 32;
+	rst_ctlr.nr_resets = periph_banks * 32;
 	reset_controller_register(&rst_ctlr);
 }
 
diff --git a/drivers/clk/zynq/clkc.c b/drivers/clk/zynq/clkc.c
index 9037bebd69f..f870aad5771 100644
--- a/drivers/clk/zynq/clkc.c
+++ b/drivers/clk/zynq/clkc.c
@@ -303,6 +303,7 @@ static void __init zynq_clk_setup(struct device_node *np)
 	clks[cpu_2x] = clk_register_gate(NULL, clk_output_name[cpu_2x],
 			"cpu_2x_div", CLK_IGNORE_UNUSED, SLCR_ARM_CLK_CTRL,
 			26, 0, &armclk_lock);
+	clk_prepare_enable(clks[cpu_2x]);
 
 	clk = clk_register_fixed_factor(NULL, "cpu_1x_div", "cpu_div", 0, 1,
 			4 + 2 * tmp);
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 43005d4d334..b593b98d700 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -462,7 +462,10 @@ static void __init arch_counter_register(unsigned type)
 
 	/* Register the CP15 based counter if we have one */
 	if (type & ARCH_CP15_TIMER) {
-		arch_timer_read_counter = arch_counter_get_cntvct;
+		if (IS_ENABLED(CONFIG_ARM64) || arch_timer_use_virtual)
+			arch_timer_read_counter = arch_counter_get_cntvct;
+		else
+			arch_timer_read_counter = arch_counter_get_cntpct;
 	} else {
 		arch_timer_read_counter = arch_counter_get_cntvct_mem;
 
@@ -735,14 +738,16 @@ static void __init arch_timer_mem_init(struct device_node *np)
 	u32 cnttidr;
 
 	arch_timers_present |= ARCH_MEM_TIMER;
-	cntctlbase = of_iomap(np, 0);
-	if (!cntctlbase) {
-		pr_err("arch_timer: Can't find CNTCTLBase\n");
-		return;
-	}
+	if (of_property_read_u32(np, "arm,cnttidr", &cnttidr)) {
+		cntctlbase = of_iomap(np, 0);
+		if (!cntctlbase) {
+			pr_err("arch_timer: Can't find CNTCTLBase\n");
+			return;
+		}
 
-	cnttidr = readl_relaxed(cntctlbase + CNTTIDR);
-	iounmap(cntctlbase);
+		cnttidr = readl_relaxed(cntctlbase + CNTTIDR);
+		iounmap(cntctlbase);
+	}
 
 	/*
 	 * Try to find a virtual capable frame. Otherwise fall back to a
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index 9403061a2ac..c844616028d 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -97,8 +97,8 @@ static void exynos4_mct_write(unsigned int value, unsigned long offset)
 	writel_relaxed(value, reg_base + offset);
 
 	if (likely(offset >= EXYNOS4_MCT_L_BASE(0))) {
-		stat_addr = (offset & ~EXYNOS4_MCT_L_MASK) + MCT_L_WSTAT_OFFSET;
-		switch (offset & EXYNOS4_MCT_L_MASK) {
+		stat_addr = (offset & EXYNOS4_MCT_L_MASK) + MCT_L_WSTAT_OFFSET;
+		switch (offset & ~EXYNOS4_MCT_L_MASK) {
 		case MCT_L_TCON_OFFSET:
 			mask = 1 << 3;		/* L_TCON write status */
 			break;
@@ -466,15 +466,12 @@ static int exynos4_local_timer_setup(struct clock_event_device *evt)
 	exynos4_mct_write(TICK_BASE_CNT, mevt->base + MCT_L_TCNTB_OFFSET);
 
 	if (mct_int_type == MCT_INT_SPI) {
-		evt->irq = mct_irqs[MCT_L0_IRQ + cpu];
-		if (request_irq(evt->irq, exynos4_mct_tick_isr,
-				IRQF_TIMER | IRQF_NOBALANCING,
-				evt->name, mevt)) {
-			pr_err("exynos-mct: cannot register IRQ %d\n",
-				evt->irq);
+
+		if (evt->irq == -1)
 			return -EIO;
-		}
-		irq_force_affinity(mct_irqs[MCT_L0_IRQ + cpu], cpumask_of(cpu));
+
+		irq_force_affinity(evt->irq, cpumask_of(cpu));
+		enable_irq(evt->irq);
 	} else {
 		enable_percpu_irq(mct_irqs[MCT_L0_IRQ], 0);
 	}
@@ -487,10 +484,12 @@ static int exynos4_local_timer_setup(struct clock_event_device *evt)
 static void exynos4_local_timer_stop(struct clock_event_device *evt)
 {
 	evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt);
-	if (mct_int_type == MCT_INT_SPI)
-		free_irq(evt->irq, this_cpu_ptr(&percpu_mct_tick));
-	else
+	if (mct_int_type == MCT_INT_SPI) {
+		if (evt->irq != -1)
+			disable_irq_nosync(evt->irq);
+	} else {
 		disable_percpu_irq(mct_irqs[MCT_L0_IRQ]);
+	}
 }
 
 static int exynos4_mct_cpu_notify(struct notifier_block *self,
@@ -522,7 +521,7 @@ static struct notifier_block exynos4_mct_cpu_nb = {
 
 static void __init exynos4_timer_resources(struct device_node *np, void __iomem *base)
 {
-	int err;
+	int err, cpu;
 	struct mct_clock_event_device *mevt = this_cpu_ptr(&percpu_mct_tick);
 	struct clk *mct_clk, *tick_clk;
 
@@ -549,7 +548,25 @@ static void __init exynos4_timer_resources(struct device_node *np, void __iomem
 		WARN(err, "MCT: can't request IRQ %d (%d)\n",
 		     mct_irqs[MCT_L0_IRQ], err);
 	} else {
-		irq_set_affinity(mct_irqs[MCT_L0_IRQ], cpumask_of(0));
+		for_each_possible_cpu(cpu) {
+			int mct_irq = mct_irqs[MCT_L0_IRQ + cpu];
+			struct mct_clock_event_device *pcpu_mevt =
+				per_cpu_ptr(&percpu_mct_tick, cpu);
+
+			pcpu_mevt->evt.irq = -1;
+
+			irq_set_status_flags(mct_irq, IRQ_NOAUTOEN);
+			if (request_irq(mct_irq,
+					exynos4_mct_tick_isr,
+					IRQF_TIMER | IRQF_NOBALANCING,
+					pcpu_mevt->name, pcpu_mevt)) {
+				pr_err("exynos-mct: cannot register IRQ (cpu%d)\n",
+									cpu);
+
+				continue;
+			}
+			pcpu_mevt->evt.irq = mct_irq;
+		}
 	}
 
 	err = register_cpu_notifier(&exynos4_mct_cpu_nb);
diff --git a/drivers/clocksource/mtk_timer.c b/drivers/clocksource/mtk_timer.c
index 32a3d25795d..68ab42356d0 100644
--- a/drivers/clocksource/mtk_timer.c
+++ b/drivers/clocksource/mtk_timer.c
@@ -224,6 +224,8 @@ static void __init mtk_timer_init(struct device_node *node)
 	}
 	rate = clk_get_rate(clk);
 
+	mtk_timer_global_reset(evt);
+
 	if (request_irq(evt->dev.irq, mtk_timer_interrupt,
 			IRQF_TIMER | IRQF_IRQPOLL, "mtk_timer", evt)) {
 		pr_warn("failed to setup irq %d\n", evt->dev.irq);
@@ -232,8 +234,6 @@ static void __init mtk_timer_init(struct device_node *node)
 
 	evt->ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
 
-	mtk_timer_global_reset(evt);
-
 	/* Configure clock source */
 	mtk_timer_setup(evt, GPT_CLK_SRC, TIMER_CTRL_OP_FREERUN);
 	clocksource_mmio_init(evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC),
@@ -241,10 +241,11 @@ static void __init mtk_timer_init(struct device_node *node)
 
 	/* Configure clock event */
 	mtk_timer_setup(evt, GPT_CLK_EVT, TIMER_CTRL_OP_REPEAT);
-	mtk_timer_enable_irq(evt, GPT_CLK_EVT);
-
 	clockevents_config_and_register(&evt->dev, rate, 0x3,
 					0xffffffff);
+
+	mtk_timer_enable_irq(evt, GPT_CLK_EVT);
+
 	return;
 
 err_clk_disable:
diff --git a/drivers/clocksource/time-efm32.c b/drivers/clocksource/time-efm32.c
index bba62f9deef..ec57ba2bbd8 100644
--- a/drivers/clocksource/time-efm32.c
+++ b/drivers/clocksource/time-efm32.c
@@ -225,12 +225,12 @@ static int __init efm32_clockevent_init(struct device_node *np)
 	clock_event_ddata.base = base;
 	clock_event_ddata.periodic_top = DIV_ROUND_CLOSEST(rate, 1024 * HZ);
 
-	setup_irq(irq, &efm32_clock_event_irq);
-
 	clockevents_config_and_register(&clock_event_ddata.evtdev,
 					DIV_ROUND_CLOSEST(rate, 1024),
 					0xf, 0xffff);
 
+	setup_irq(irq, &efm32_clock_event_irq);
+
 	return 0;
 
 err_get_irq:
diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c
index 02268448dc8..5dcbf90b801 100644
--- a/drivers/clocksource/timer-sun5i.c
+++ b/drivers/clocksource/timer-sun5i.c
@@ -178,10 +178,6 @@ static void __init sun5i_timer_init(struct device_node *node)
 
 	ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
 
-	ret = setup_irq(irq, &sun5i_timer_irq);
-	if (ret)
-		pr_warn("failed to setup irq %d\n", irq);
-
 	/* Enable timer0 interrupt */
 	val = readl(timer_base + TIMER_IRQ_EN_REG);
 	writel(val | TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_EN_REG);
@@ -191,6 +187,10 @@ static void __init sun5i_timer_init(struct device_node *node)
 
 	clockevents_config_and_register(&sun5i_clockevent, rate,
 					TIMER_SYNC_TICKS, 0xffffffff);
+
+	ret = setup_irq(irq, &sun5i_timer_irq);
+	if (ret)
+		pr_warn("failed to setup irq %d\n", irq);
 }
 CLOCKSOURCE_OF_DECLARE(sun5i_a13, "allwinner,sun5i-a13-hstimer",
 		       sun5i_timer_init);
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 3489f8f5fad..548311fd04c 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -102,6 +102,16 @@ config CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
 	  Be aware that not all cpufreq drivers support the conservative
 	  governor. If unsure have a look at the help section of the
 	  driver. Fallback governor will be the performance governor.
+
+config CPU_FREQ_DEFAULT_GOV_INTERACTIVE
+	bool "interactive"
+	select CPU_FREQ_GOV_INTERACTIVE
+	help
+	  Use the CPUFreq governor 'interactive' as default. This allows
+	  you to get a full dynamic cpu frequency capable system by simply
+	  loading your cpufreq low-level hardware driver, using the
+	  'interactive' governor for latency-sensitive workloads.
+
 endchoice
 
 config CPU_FREQ_GOV_PERFORMANCE
@@ -159,6 +169,23 @@ config CPU_FREQ_GOV_ONDEMAND
 
 	  If in doubt, say N.
 
+config CPU_FREQ_GOV_INTERACTIVE
+	tristate "'interactive' cpufreq policy governor"
+	help
+	  'interactive' - This driver adds a dynamic cpufreq policy governor
+	  designed for latency-sensitive workloads.
+
+	  This governor attempts to reduce the latency of clock
+	  increases so that the system is more responsive to
+	  interactive workloads.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called cpufreq_interactive.
+
+	  For details, take a look at linux/Documentation/cpu-freq.
+
+	  If in doubt, say N.
+
 config CPU_FREQ_GOV_CONSERVATIVE
 	tristate "'conservative' cpufreq governor"
 	depends on CPU_FREQ
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 83a75dc8476..aa6a665d846 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -5,7 +5,7 @@
 # big LITTLE core layer and glue drivers
 config ARM_BIG_LITTLE_CPUFREQ
 	tristate "Generic ARM big LITTLE CPUfreq driver"
-	depends on ARM && BIG_LITTLE && ARM_CPU_TOPOLOGY && HAVE_CLK
+	depends on (ARM_CPU_TOPOLOGY || ARM64) && HAVE_CLK
 	select PM_OPP
 	help
 	  This enables the Generic CPUfreq driver for ARM big.LITTLE platforms.
@@ -24,6 +24,15 @@ config ARM_VEXPRESS_SPC_CPUFREQ
           This add the CPUfreq driver support for Versatile Express
 	  big.LITTLE platforms using SPC for power management.
 
+config ARM_SCPI_CPUFREQ
+        tristate "SCPI based CPUfreq driver"
+	depends on ARM_BIG_LITTLE_CPUFREQ && ARM_SCPI_PROTOCOL
+        help
+	  This adds the CPUfreq driver support for ARM big.LITTLE platforms
+	  using SCPI protocol for CPU power management.
+
+	  This driver uses SCPI Message Protocol driver to interact with the
+	  firmware providing the CPU DVFS functionality.
 
 config ARM_EXYNOS_CPUFREQ
 	bool
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 40c53dc1937..bb77713d736 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_CPU_FREQ_GOV_POWERSAVE)	+= cpufreq_powersave.o
 obj-$(CONFIG_CPU_FREQ_GOV_USERSPACE)	+= cpufreq_userspace.o
 obj-$(CONFIG_CPU_FREQ_GOV_ONDEMAND)	+= cpufreq_ondemand.o
 obj-$(CONFIG_CPU_FREQ_GOV_CONSERVATIVE)	+= cpufreq_conservative.o
+obj-$(CONFIG_CPU_FREQ_GOV_INTERACTIVE)	+= cpufreq_interactive.o
 obj-$(CONFIG_CPU_FREQ_GOV_COMMON)		+= cpufreq_governor.o
 
 obj-$(CONFIG_CPUFREQ_DT)		+= cpufreq-dt.o
@@ -77,6 +78,7 @@ obj-$(CONFIG_ARM_SA1110_CPUFREQ)	+= sa1110-cpufreq.o
 obj-$(CONFIG_ARM_SPEAR_CPUFREQ)		+= spear-cpufreq.o
 obj-$(CONFIG_ARM_TEGRA_CPUFREQ)		+= tegra-cpufreq.o
 obj-$(CONFIG_ARM_VEXPRESS_SPC_CPUFREQ)	+= vexpress-spc-cpufreq.o
+obj-$(CONFIG_ARM_SCPI_CPUFREQ)		+= scpi-cpufreq.o
 
 ##################################################################################
 # PowerPC platform drivers
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index a46c223c250..c815d0a6acb 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -31,7 +31,6 @@
 #include <linux/slab.h>
 #include <linux/topology.h>
 #include <linux/types.h>
-#include <asm/bL_switcher.h>
 
 #include "arm_big_little.h"
 
@@ -41,12 +40,16 @@
 #define MAX_CLUSTERS	2
 
 #ifdef CONFIG_BL_SWITCHER
+#include <asm/bL_switcher.h>
 static bool bL_switching_enabled;
 #define is_bL_switching_enabled()	bL_switching_enabled
 #define set_switching_enabled(x)	(bL_switching_enabled = (x))
 #else
 #define is_bL_switching_enabled()	false
 #define set_switching_enabled(x)	do { } while (0)
+#define bL_switch_request(...)		do { } while (0)
+#define bL_switcher_put_enabled()	do { } while (0)
+#define bL_switcher_get_enabled()	do { } while (0)
 #endif
 
 #define ACTUAL_FREQ(cluster, freq)  ((cluster == A7_CLUSTER) ? freq << 1 : freq)
@@ -320,7 +323,6 @@ static void put_cluster_clk_and_freq_table(struct device *cpu_dev)
 static int _get_cluster_clk_and_freq_table(struct device *cpu_dev)
 {
 	u32 cluster = raw_cpu_to_cluster(cpu_dev->id);
-	char name[14] = "cpu-cluster.";
 	int ret;
 
 	if (freq_table[cluster])
@@ -340,8 +342,7 @@ static int _get_cluster_clk_and_freq_table(struct device *cpu_dev)
 		goto out;
 	}
 
-	name[12] = cluster + '0';
-	clk[cluster] = clk_get(cpu_dev, name);
+	clk[cluster] = clk_get(cpu_dev, NULL);
 	if (!IS_ERR(clk[cluster])) {
 		dev_dbg(cpu_dev, "%s: clk: %p & freq table: %p, cluster: %d\n",
 				__func__, clk[cluster], freq_table[cluster],
@@ -501,6 +502,7 @@ static struct cpufreq_driver bL_cpufreq_driver = {
 	.attr			= cpufreq_generic_attr,
 };
 
+#ifdef CONFIG_BL_SWITCHER
 static int bL_cpufreq_switcher_notifier(struct notifier_block *nfb,
 					unsigned long action, void *_arg)
 {
@@ -533,6 +535,20 @@ static struct notifier_block bL_switcher_notifier = {
 	.notifier_call = bL_cpufreq_switcher_notifier,
 };
 
+static int __bLs_register_notifier(void)
+{
+	return bL_switcher_register_notifier(&bL_switcher_notifier);
+}
+
+static int __bLs_unregister_notifier(void)
+{
+	return bL_switcher_unregister_notifier(&bL_switcher_notifier);
+}
+#else
+static int __bLs_register_notifier(void) { return 0; }
+static int __bLs_unregister_notifier(void) { return 0; }
+#endif
+
 int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops)
 {
 	int ret, i;
@@ -550,8 +566,7 @@ int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops)
 
 	arm_bL_ops = ops;
 
-	ret = bL_switcher_get_enabled();
-	set_switching_enabled(ret);
+	set_switching_enabled(bL_switcher_get_enabled());
 
 	for (i = 0; i < MAX_CLUSTERS; i++)
 		mutex_init(&cluster_lock[i]);
@@ -562,7 +577,7 @@ int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops)
 				__func__, ops->name, ret);
 		arm_bL_ops = NULL;
 	} else {
-		ret = bL_switcher_register_notifier(&bL_switcher_notifier);
+		ret = __bLs_register_notifier();
 		if (ret) {
 			cpufreq_unregister_driver(&bL_cpufreq_driver);
 			arm_bL_ops = NULL;
@@ -586,7 +601,7 @@ void bL_cpufreq_unregister(struct cpufreq_arm_bL_ops *ops)
 	}
 
 	bL_switcher_get_enabled();
-	bL_switcher_unregister_notifier(&bL_switcher_notifier);
+	__bLs_unregister_notifier();
 	cpufreq_unregister_driver(&bL_cpufreq_driver);
 	bL_switcher_put_enabled();
 	pr_info("%s: Un-registered platform driver: %s\n", __func__,
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 4473eba1d6b..90e8deb6c15 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1409,9 +1409,10 @@ static int __cpufreq_remove_dev_finish(struct device *dev,
 	unsigned long flags;
 	struct cpufreq_policy *policy;
 
-	read_lock_irqsave(&cpufreq_driver_lock, flags);
+	write_lock_irqsave(&cpufreq_driver_lock, flags);
 	policy = per_cpu(cpufreq_cpu_data, cpu);
-	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
+	per_cpu(cpufreq_cpu_data, cpu) = NULL;
+	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
 	if (!policy) {
 		pr_debug("%s: No cpu_data found\n", __func__);
@@ -1466,7 +1467,6 @@ static int __cpufreq_remove_dev_finish(struct device *dev,
 		}
 	}
 
-	per_cpu(cpufreq_cpu_data, cpu) = NULL;
 	return 0;
 }
 
@@ -1717,15 +1717,18 @@ void cpufreq_resume(void)
 		    || __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))
 			pr_err("%s: Failed to start governor for policy: %p\n",
 				__func__, policy);
-
-		/*
-		 * schedule call cpufreq_update_policy() for boot CPU, i.e. last
-		 * policy in list. It will verify that the current freq is in
-		 * sync with what we believe it to be.
-		 */
-		if (list_is_last(&policy->policy_list, &cpufreq_policy_list))
-			schedule_work(&policy->update);
 	}
+
+	/*
+	 * schedule call cpufreq_update_policy() for first-online CPU, as that
+	 * wouldn't be hotplugged-out on suspend. It will verify that the
+	 * current freq is in sync with what we believe it to be.
+	 */
+	policy = cpufreq_cpu_get_raw(cpumask_first(cpu_online_mask));
+	if (WARN_ON(!policy))
+		return;
+
+	schedule_work(&policy->update);
 }
 
 /**
diff --git a/drivers/cpufreq/cpufreq_interactive.c b/drivers/cpufreq/cpufreq_interactive.c
new file mode 100644
index 00000000000..e569e0b8c2c
--- /dev/null
+++ b/drivers/cpufreq/cpufreq_interactive.c
@@ -0,0 +1,1338 @@
+/*
+ * drivers/cpufreq/cpufreq_interactive.c
+ *
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Author: Mike Chan (mike@android.com)
+ *
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/cpufreq.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/sched/rt.h>
+#include <linux/tick.h>
+#include <linux/time.h>
+#include <linux/timer.h>
+#include <linux/workqueue.h>
+#include <linux/kthread.h>
+#include <linux/slab.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/cpufreq_interactive.h>
+
+struct cpufreq_interactive_cpuinfo {
+	struct timer_list cpu_timer;
+	struct timer_list cpu_slack_timer;
+	spinlock_t load_lock; /* protects the next 4 fields */
+	u64 time_in_idle;
+	u64 time_in_idle_timestamp;
+	u64 cputime_speedadj;
+	u64 cputime_speedadj_timestamp;
+	struct cpufreq_policy *policy;
+	struct cpufreq_frequency_table *freq_table;
+	spinlock_t target_freq_lock; /*protects target freq */
+	unsigned int target_freq;
+	unsigned int floor_freq;
+	u64 pol_floor_val_time; /* policy floor_validate_time */
+	u64 loc_floor_val_time; /* per-cpu floor_validate_time */
+	u64 pol_hispeed_val_time; /* policy hispeed_validate_time */
+	u64 loc_hispeed_val_time; /* per-cpu hispeed_validate_time */
+	struct rw_semaphore enable_sem;
+	int governor_enabled;
+};
+
+static DEFINE_PER_CPU(struct cpufreq_interactive_cpuinfo, cpuinfo);
+
+/* realtime thread handles frequency scaling */
+static struct task_struct *speedchange_task;
+static cpumask_t speedchange_cpumask;
+static spinlock_t speedchange_cpumask_lock;
+static struct mutex gov_lock;
+
+/* Target load.  Lower values result in higher CPU speeds. */
+#define DEFAULT_TARGET_LOAD 90
+static unsigned int default_target_loads[] = {DEFAULT_TARGET_LOAD};
+
+#define DEFAULT_TIMER_RATE (20 * USEC_PER_MSEC)
+#define DEFAULT_ABOVE_HISPEED_DELAY DEFAULT_TIMER_RATE
+static unsigned int default_above_hispeed_delay[] = {
+	DEFAULT_ABOVE_HISPEED_DELAY };
+
+struct cpufreq_interactive_tunables {
+	int usage_count;
+	/* Hi speed to bump to from lo speed when load burst (default max) */
+	unsigned int hispeed_freq;
+	/* Go to hi speed when CPU load at or above this value. */
+#define DEFAULT_GO_HISPEED_LOAD 99
+	unsigned long go_hispeed_load;
+	/* Target load. Lower values result in higher CPU speeds. */
+	spinlock_t target_loads_lock;
+	unsigned int *target_loads;
+	int ntarget_loads;
+	/*
+	 * The minimum amount of time to spend at a frequency before we can ramp
+	 * down.
+	 */
+#define DEFAULT_MIN_SAMPLE_TIME (80 * USEC_PER_MSEC)
+	unsigned long min_sample_time;
+	/*
+	 * The sample rate of the timer used to increase frequency
+	 */
+	unsigned long timer_rate;
+	/*
+	 * Wait this long before raising speed above hispeed, by default a
+	 * single timer interval.
+	 */
+	spinlock_t above_hispeed_delay_lock;
+	unsigned int *above_hispeed_delay;
+	int nabove_hispeed_delay;
+	/* Non-zero means indefinite speed boost active */
+	int boost_val;
+	/* Duration of a boot pulse in usecs */
+	int boostpulse_duration_val;
+	/* End time of boost pulse in ktime converted to usecs */
+	u64 boostpulse_endtime;
+	bool boosted;
+	/*
+	 * Max additional time to wait in idle, beyond timer_rate, at speeds
+	 * above minimum before wakeup to reduce speed, or -1 if unnecessary.
+	 */
+#define DEFAULT_TIMER_SLACK (4 * DEFAULT_TIMER_RATE)
+	int timer_slack_val;
+	bool io_is_busy;
+};
+
+/* For cases where we have single governor instance for system */
+static struct cpufreq_interactive_tunables *common_tunables;
+
+static struct attribute_group *get_sysfs_attr(void);
+
+static void cpufreq_interactive_timer_resched(
+	struct cpufreq_interactive_cpuinfo *pcpu)
+{
+	struct cpufreq_interactive_tunables *tunables =
+		pcpu->policy->governor_data;
+	unsigned long expires;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pcpu->load_lock, flags);
+	pcpu->time_in_idle =
+		get_cpu_idle_time(smp_processor_id(),
+				  &pcpu->time_in_idle_timestamp,
+				  tunables->io_is_busy);
+	pcpu->cputime_speedadj = 0;
+	pcpu->cputime_speedadj_timestamp = pcpu->time_in_idle_timestamp;
+	expires = jiffies + usecs_to_jiffies(tunables->timer_rate);
+	mod_timer_pinned(&pcpu->cpu_timer, expires);
+
+	if (tunables->timer_slack_val >= 0 &&
+	    pcpu->target_freq > pcpu->policy->min) {
+		expires += usecs_to_jiffies(tunables->timer_slack_val);
+		mod_timer_pinned(&pcpu->cpu_slack_timer, expires);
+	}
+
+	spin_unlock_irqrestore(&pcpu->load_lock, flags);
+}
+
+/* The caller shall take enable_sem write semaphore to avoid any timer race.
+ * The cpu_timer and cpu_slack_timer must be deactivated when calling this
+ * function.
+ */
+static void cpufreq_interactive_timer_start(
+	struct cpufreq_interactive_tunables *tunables, int cpu)
+{
+	struct cpufreq_interactive_cpuinfo *pcpu = &per_cpu(cpuinfo, cpu);
+	unsigned long expires = jiffies +
+		usecs_to_jiffies(tunables->timer_rate);
+	unsigned long flags;
+
+	pcpu->cpu_timer.expires = expires;
+	add_timer_on(&pcpu->cpu_timer, cpu);
+	if (tunables->timer_slack_val >= 0 &&
+	    pcpu->target_freq > pcpu->policy->min) {
+		expires += usecs_to_jiffies(tunables->timer_slack_val);
+		pcpu->cpu_slack_timer.expires = expires;
+		add_timer_on(&pcpu->cpu_slack_timer, cpu);
+	}
+
+	spin_lock_irqsave(&pcpu->load_lock, flags);
+	pcpu->time_in_idle =
+		get_cpu_idle_time(cpu, &pcpu->time_in_idle_timestamp,
+				  tunables->io_is_busy);
+	pcpu->cputime_speedadj = 0;
+	pcpu->cputime_speedadj_timestamp = pcpu->time_in_idle_timestamp;
+	spin_unlock_irqrestore(&pcpu->load_lock, flags);
+}
+
+static unsigned int freq_to_above_hispeed_delay(
+	struct cpufreq_interactive_tunables *tunables,
+	unsigned int freq)
+{
+	int i;
+	unsigned int ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tunables->above_hispeed_delay_lock, flags);
+
+	for (i = 0; i < tunables->nabove_hispeed_delay - 1 &&
+			freq >= tunables->above_hispeed_delay[i+1]; i += 2)
+		;
+
+	ret = tunables->above_hispeed_delay[i];
+	spin_unlock_irqrestore(&tunables->above_hispeed_delay_lock, flags);
+	return ret;
+}
+
+static unsigned int freq_to_targetload(
+	struct cpufreq_interactive_tunables *tunables, unsigned int freq)
+{
+	int i;
+	unsigned int ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tunables->target_loads_lock, flags);
+
+	for (i = 0; i < tunables->ntarget_loads - 1 &&
+		    freq >= tunables->target_loads[i+1]; i += 2)
+		;
+
+	ret = tunables->target_loads[i];
+	spin_unlock_irqrestore(&tunables->target_loads_lock, flags);
+	return ret;
+}
+
+/*
+ * If increasing frequencies never map to a lower target load then
+ * choose_freq() will find the minimum frequency that does not exceed its
+ * target load given the current load.
+ */
+static unsigned int choose_freq(struct cpufreq_interactive_cpuinfo *pcpu,
+		unsigned int loadadjfreq)
+{
+	unsigned int freq = pcpu->policy->cur;
+	unsigned int prevfreq, freqmin, freqmax;
+	unsigned int tl;
+	int index;
+
+	freqmin = 0;
+	freqmax = UINT_MAX;
+
+	do {
+		prevfreq = freq;
+		tl = freq_to_targetload(pcpu->policy->governor_data, freq);
+
+		/*
+		 * Find the lowest frequency where the computed load is less
+		 * than or equal to the target load.
+		 */
+
+		if (cpufreq_frequency_table_target(
+			    pcpu->policy, pcpu->freq_table, loadadjfreq / tl,
+			    CPUFREQ_RELATION_L, &index))
+			break;
+		freq = pcpu->freq_table[index].frequency;
+
+		if (freq > prevfreq) {
+			/* The previous frequency is too low. */
+			freqmin = prevfreq;
+
+			if (freq >= freqmax) {
+				/*
+				 * Find the highest frequency that is less
+				 * than freqmax.
+				 */
+				if (cpufreq_frequency_table_target(
+					    pcpu->policy, pcpu->freq_table,
+					    freqmax - 1, CPUFREQ_RELATION_H,
+					    &index))
+					break;
+				freq = pcpu->freq_table[index].frequency;
+
+				if (freq == freqmin) {
+					/*
+					 * The first frequency below freqmax
+					 * has already been found to be too
+					 * low.  freqmax is the lowest speed
+					 * we found that is fast enough.
+					 */
+					freq = freqmax;
+					break;
+				}
+			}
+		} else if (freq < prevfreq) {
+			/* The previous frequency is high enough. */
+			freqmax = prevfreq;
+
+			if (freq <= freqmin) {
+				/*
+				 * Find the lowest frequency that is higher
+				 * than freqmin.
+				 */
+				if (cpufreq_frequency_table_target(
+					    pcpu->policy, pcpu->freq_table,
+					    freqmin + 1, CPUFREQ_RELATION_L,
+					    &index))
+					break;
+				freq = pcpu->freq_table[index].frequency;
+
+				/*
+				 * If freqmax is the first frequency above
+				 * freqmin then we have already found that
+				 * this speed is fast enough.
+				 */
+				if (freq == freqmax)
+					break;
+			}
+		}
+
+		/* If same frequency chosen as previous then done. */
+	} while (freq != prevfreq);
+
+	return freq;
+}
+
+static u64 update_load(int cpu)
+{
+	struct cpufreq_interactive_cpuinfo *pcpu = &per_cpu(cpuinfo, cpu);
+	struct cpufreq_interactive_tunables *tunables =
+		pcpu->policy->governor_data;
+	u64 now;
+	u64 now_idle;
+	unsigned int delta_idle;
+	unsigned int delta_time;
+	u64 active_time;
+
+	now_idle = get_cpu_idle_time(cpu, &now, tunables->io_is_busy);
+	delta_idle = (unsigned int)(now_idle - pcpu->time_in_idle);
+	delta_time = (unsigned int)(now - pcpu->time_in_idle_timestamp);
+
+	if (delta_time <= delta_idle)
+		active_time = 0;
+	else
+		active_time = delta_time - delta_idle;
+
+	pcpu->cputime_speedadj += active_time * pcpu->policy->cur;
+
+	pcpu->time_in_idle = now_idle;
+	pcpu->time_in_idle_timestamp = now;
+	return now;
+}
+
+static void cpufreq_interactive_timer(unsigned long data)
+{
+	u64 now;
+	unsigned int delta_time;
+	u64 cputime_speedadj;
+	int cpu_load;
+	struct cpufreq_interactive_cpuinfo *pcpu =
+		&per_cpu(cpuinfo, data);
+	struct cpufreq_interactive_tunables *tunables =
+		pcpu->policy->governor_data;
+	unsigned int new_freq;
+	unsigned int loadadjfreq;
+	unsigned int index;
+	unsigned long flags;
+	u64 max_fvtime;
+
+	if (!down_read_trylock(&pcpu->enable_sem))
+		return;
+	if (!pcpu->governor_enabled)
+		goto exit;
+
+	spin_lock_irqsave(&pcpu->load_lock, flags);
+	now = update_load(data);
+	delta_time = (unsigned int)(now - pcpu->cputime_speedadj_timestamp);
+	cputime_speedadj = pcpu->cputime_speedadj;
+	spin_unlock_irqrestore(&pcpu->load_lock, flags);
+
+	if (WARN_ON_ONCE(!delta_time))
+		goto rearm;
+
+	spin_lock_irqsave(&pcpu->target_freq_lock, flags);
+	do_div(cputime_speedadj, delta_time);
+	loadadjfreq = (unsigned int)cputime_speedadj * 100;
+	cpu_load = loadadjfreq / pcpu->policy->cur;
+	tunables->boosted = tunables->boost_val || now < tunables->boostpulse_endtime;
+
+	if (cpu_load >= tunables->go_hispeed_load || tunables->boosted) {
+		if (pcpu->policy->cur < tunables->hispeed_freq) {
+			new_freq = tunables->hispeed_freq;
+		} else {
+			new_freq = choose_freq(pcpu, loadadjfreq);
+
+			if (new_freq < tunables->hispeed_freq)
+				new_freq = tunables->hispeed_freq;
+		}
+	} else {
+		new_freq = choose_freq(pcpu, loadadjfreq);
+		if (new_freq > tunables->hispeed_freq &&
+				pcpu->policy->cur < tunables->hispeed_freq)
+			new_freq = tunables->hispeed_freq;
+	}
+
+	if (pcpu->policy->cur >= tunables->hispeed_freq &&
+	    new_freq > pcpu->policy->cur &&
+	    now - pcpu->pol_hispeed_val_time <
+	    freq_to_above_hispeed_delay(tunables, pcpu->policy->cur)) {
+		trace_cpufreq_interactive_notyet(
+			data, cpu_load, pcpu->target_freq,
+			pcpu->policy->cur, new_freq);
+		spin_unlock_irqrestore(&pcpu->target_freq_lock, flags);
+		goto rearm;
+	}
+
+	pcpu->loc_hispeed_val_time = now;
+
+	if (cpufreq_frequency_table_target(pcpu->policy, pcpu->freq_table,
+					   new_freq, CPUFREQ_RELATION_L,
+					   &index)) {
+		spin_unlock_irqrestore(&pcpu->target_freq_lock, flags);
+		goto rearm;
+	}
+
+	new_freq = pcpu->freq_table[index].frequency;
+
+	/*
+	 * Do not scale below floor_freq unless we have been at or above the
+	 * floor frequency for the minimum sample time since last validated.
+	 */
+	max_fvtime = max(pcpu->pol_floor_val_time, pcpu->loc_floor_val_time);
+	if (new_freq < pcpu->floor_freq &&
+	    pcpu->target_freq >= pcpu->policy->cur) {
+		if (now - max_fvtime < tunables->min_sample_time) {
+			trace_cpufreq_interactive_notyet(
+				data, cpu_load, pcpu->target_freq,
+				pcpu->policy->cur, new_freq);
+			spin_unlock_irqrestore(&pcpu->target_freq_lock, flags);
+			goto rearm;
+		}
+	}
+
+	/*
+	 * Update the timestamp for checking whether speed has been held at
+	 * or above the selected frequency for a minimum of min_sample_time,
+	 * if not boosted to hispeed_freq.  If boosted to hispeed_freq then we
+	 * allow the speed to drop as soon as the boostpulse duration expires
+	 * (or the indefinite boost is turned off).
+	 */
+
+	if (!tunables->boosted || new_freq > tunables->hispeed_freq) {
+		pcpu->floor_freq = new_freq;
+		if (pcpu->target_freq >= pcpu->policy->cur ||
+		    new_freq >= pcpu->policy->cur)
+			pcpu->loc_floor_val_time = now;
+	}
+
+	if (pcpu->target_freq == new_freq &&
+			pcpu->target_freq <= pcpu->policy->cur) {
+		trace_cpufreq_interactive_already(
+			data, cpu_load, pcpu->target_freq,
+			pcpu->policy->cur, new_freq);
+		spin_unlock_irqrestore(&pcpu->target_freq_lock, flags);
+		goto rearm;
+	}
+
+	trace_cpufreq_interactive_target(data, cpu_load, pcpu->target_freq,
+					 pcpu->policy->cur, new_freq);
+
+	pcpu->target_freq = new_freq;
+	spin_unlock_irqrestore(&pcpu->target_freq_lock, flags);
+	spin_lock_irqsave(&speedchange_cpumask_lock, flags);
+	cpumask_set_cpu(data, &speedchange_cpumask);
+	spin_unlock_irqrestore(&speedchange_cpumask_lock, flags);
+	wake_up_process(speedchange_task);
+
+rearm:
+	if (!timer_pending(&pcpu->cpu_timer))
+		cpufreq_interactive_timer_resched(pcpu);
+
+exit:
+	up_read(&pcpu->enable_sem);
+	return;
+}
+
+static void cpufreq_interactive_idle_end(void)
+{
+	struct cpufreq_interactive_cpuinfo *pcpu =
+		&per_cpu(cpuinfo, smp_processor_id());
+
+	if (!down_read_trylock(&pcpu->enable_sem))
+		return;
+	if (!pcpu->governor_enabled) {
+		up_read(&pcpu->enable_sem);
+		return;
+	}
+
+	/* Arm the timer for 1-2 ticks later if not already. */
+	if (!timer_pending(&pcpu->cpu_timer)) {
+		cpufreq_interactive_timer_resched(pcpu);
+	} else if (time_after_eq(jiffies, pcpu->cpu_timer.expires)) {
+		del_timer(&pcpu->cpu_timer);
+		del_timer(&pcpu->cpu_slack_timer);
+		cpufreq_interactive_timer(smp_processor_id());
+	}
+
+	up_read(&pcpu->enable_sem);
+}
+
+static int cpufreq_interactive_speedchange_task(void *data)
+{
+	unsigned int cpu;
+	cpumask_t tmp_mask;
+	unsigned long flags;
+	struct cpufreq_interactive_cpuinfo *pcpu;
+
+	while (1) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		spin_lock_irqsave(&speedchange_cpumask_lock, flags);
+
+		if (cpumask_empty(&speedchange_cpumask)) {
+			spin_unlock_irqrestore(&speedchange_cpumask_lock,
+					       flags);
+			schedule();
+
+			if (kthread_should_stop())
+				break;
+
+			spin_lock_irqsave(&speedchange_cpumask_lock, flags);
+		}
+
+		set_current_state(TASK_RUNNING);
+		tmp_mask = speedchange_cpumask;
+		cpumask_clear(&speedchange_cpumask);
+		spin_unlock_irqrestore(&speedchange_cpumask_lock, flags);
+
+		for_each_cpu(cpu, &tmp_mask) {
+			unsigned int j;
+			unsigned int max_freq = 0;
+			struct cpufreq_interactive_cpuinfo *pjcpu;
+			u64 hvt = ~0ULL, fvt = 0;
+
+			pcpu = &per_cpu(cpuinfo, cpu);
+			if (!down_read_trylock(&pcpu->enable_sem))
+				continue;
+			if (!pcpu->governor_enabled) {
+				up_read(&pcpu->enable_sem);
+				continue;
+			}
+
+			for_each_cpu(j, pcpu->policy->cpus) {
+				pjcpu = &per_cpu(cpuinfo, j);
+
+				fvt = max(fvt, pjcpu->loc_floor_val_time);
+				if (pjcpu->target_freq > max_freq) {
+					max_freq = pjcpu->target_freq;
+					hvt = pjcpu->loc_hispeed_val_time;
+				} else if (pjcpu->target_freq == max_freq) {
+					hvt = min(hvt, pjcpu->loc_hispeed_val_time);
+				}
+			}
+			for_each_cpu(j, pcpu->policy->cpus) {
+				pjcpu = &per_cpu(cpuinfo, j);
+				pjcpu->pol_floor_val_time = fvt;
+			}
+
+			if (max_freq != pcpu->policy->cur) {
+				__cpufreq_driver_target(pcpu->policy,
+							max_freq,
+							CPUFREQ_RELATION_H);
+				for_each_cpu(j, pcpu->policy->cpus) {
+					pjcpu = &per_cpu(cpuinfo, j);
+					pjcpu->pol_hispeed_val_time = hvt;
+				}
+			}
+			trace_cpufreq_interactive_setspeed(cpu,
+						     pcpu->target_freq,
+						     pcpu->policy->cur);
+
+			up_read(&pcpu->enable_sem);
+		}
+	}
+
+	return 0;
+}
+
+static void cpufreq_interactive_boost(struct cpufreq_interactive_tunables *tunables)
+{
+	int i;
+	int anyboost = 0;
+	unsigned long flags[2];
+	struct cpufreq_interactive_cpuinfo *pcpu;
+
+	tunables->boosted = true;
+
+	spin_lock_irqsave(&speedchange_cpumask_lock, flags[0]);
+
+	for_each_online_cpu(i) {
+		pcpu = &per_cpu(cpuinfo, i);
+		if (tunables != pcpu->policy->governor_data)
+			continue;
+
+		spin_lock_irqsave(&pcpu->target_freq_lock, flags[1]);
+		if (pcpu->target_freq < tunables->hispeed_freq) {
+			pcpu->target_freq = tunables->hispeed_freq;
+			cpumask_set_cpu(i, &speedchange_cpumask);
+			pcpu->pol_hispeed_val_time =
+				ktime_to_us(ktime_get());
+			anyboost = 1;
+		}
+		spin_unlock_irqrestore(&pcpu->target_freq_lock, flags[1]);
+	}
+
+	spin_unlock_irqrestore(&speedchange_cpumask_lock, flags[0]);
+
+	if (anyboost)
+		wake_up_process(speedchange_task);
+}
+
+static int cpufreq_interactive_notifier(
+	struct notifier_block *nb, unsigned long val, void *data)
+{
+	struct cpufreq_freqs *freq = data;
+	struct cpufreq_interactive_cpuinfo *pcpu;
+	int cpu;
+	unsigned long flags;
+
+	if (val == CPUFREQ_POSTCHANGE) {
+		pcpu = &per_cpu(cpuinfo, freq->cpu);
+		if (!down_read_trylock(&pcpu->enable_sem))
+			return 0;
+		if (!pcpu->governor_enabled) {
+			up_read(&pcpu->enable_sem);
+			return 0;
+		}
+
+		for_each_cpu(cpu, pcpu->policy->cpus) {
+			struct cpufreq_interactive_cpuinfo *pjcpu =
+				&per_cpu(cpuinfo, cpu);
+			if (cpu != freq->cpu) {
+				if (!down_read_trylock(&pjcpu->enable_sem))
+					continue;
+				if (!pjcpu->governor_enabled) {
+					up_read(&pjcpu->enable_sem);
+					continue;
+				}
+			}
+			spin_lock_irqsave(&pjcpu->load_lock, flags);
+			update_load(cpu);
+			spin_unlock_irqrestore(&pjcpu->load_lock, flags);
+			if (cpu != freq->cpu)
+				up_read(&pjcpu->enable_sem);
+		}
+
+		up_read(&pcpu->enable_sem);
+	}
+	return 0;
+}
+
+static struct notifier_block cpufreq_notifier_block = {
+	.notifier_call = cpufreq_interactive_notifier,
+};
+
+static unsigned int *get_tokenized_data(const char *buf, int *num_tokens)
+{
+	const char *cp;
+	int i;
+	int ntokens = 1;
+	unsigned int *tokenized_data;
+	int err = -EINVAL;
+
+	cp = buf;
+	while ((cp = strpbrk(cp + 1, " :")))
+		ntokens++;
+
+	if (!(ntokens & 0x1))
+		goto err;
+
+	tokenized_data = kmalloc(ntokens * sizeof(unsigned int), GFP_KERNEL);
+	if (!tokenized_data) {
+		err = -ENOMEM;
+		goto err;
+	}
+
+	cp = buf;
+	i = 0;
+	while (i < ntokens) {
+		if (sscanf(cp, "%u", &tokenized_data[i++]) != 1)
+			goto err_kfree;
+
+		cp = strpbrk(cp, " :");
+		if (!cp)
+			break;
+		cp++;
+	}
+
+	if (i != ntokens)
+		goto err_kfree;
+
+	*num_tokens = ntokens;
+	return tokenized_data;
+
+err_kfree:
+	kfree(tokenized_data);
+err:
+	return ERR_PTR(err);
+}
+
+static ssize_t show_target_loads(
+	struct cpufreq_interactive_tunables *tunables,
+	char *buf)
+{
+	int i;
+	ssize_t ret = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tunables->target_loads_lock, flags);
+
+	for (i = 0; i < tunables->ntarget_loads; i++)
+		ret += sprintf(buf + ret, "%u%s", tunables->target_loads[i],
+			       i & 0x1 ? ":" : " ");
+
+	sprintf(buf + ret - 1, "\n");
+	spin_unlock_irqrestore(&tunables->target_loads_lock, flags);
+	return ret;
+}
+
+static ssize_t store_target_loads(
+	struct cpufreq_interactive_tunables *tunables,
+	const char *buf, size_t count)
+{
+	int ntokens;
+	unsigned int *new_target_loads = NULL;
+	unsigned long flags;
+
+	new_target_loads = get_tokenized_data(buf, &ntokens);
+	if (IS_ERR(new_target_loads))
+		return PTR_RET(new_target_loads);
+
+	spin_lock_irqsave(&tunables->target_loads_lock, flags);
+	if (tunables->target_loads != default_target_loads)
+		kfree(tunables->target_loads);
+	tunables->target_loads = new_target_loads;
+	tunables->ntarget_loads = ntokens;
+	spin_unlock_irqrestore(&tunables->target_loads_lock, flags);
+	return count;
+}
+
+static ssize_t show_above_hispeed_delay(
+	struct cpufreq_interactive_tunables *tunables, char *buf)
+{
+	int i;
+	ssize_t ret = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tunables->above_hispeed_delay_lock, flags);
+
+	for (i = 0; i < tunables->nabove_hispeed_delay; i++)
+		ret += sprintf(buf + ret, "%u%s",
+			       tunables->above_hispeed_delay[i],
+			       i & 0x1 ? ":" : " ");
+
+	sprintf(buf + ret - 1, "\n");
+	spin_unlock_irqrestore(&tunables->above_hispeed_delay_lock, flags);
+	return ret;
+}
+
+static ssize_t store_above_hispeed_delay(
+	struct cpufreq_interactive_tunables *tunables,
+	const char *buf, size_t count)
+{
+	int ntokens;
+	unsigned int *new_above_hispeed_delay = NULL;
+	unsigned long flags;
+
+	new_above_hispeed_delay = get_tokenized_data(buf, &ntokens);
+	if (IS_ERR(new_above_hispeed_delay))
+		return PTR_RET(new_above_hispeed_delay);
+
+	spin_lock_irqsave(&tunables->above_hispeed_delay_lock, flags);
+	if (tunables->above_hispeed_delay != default_above_hispeed_delay)
+		kfree(tunables->above_hispeed_delay);
+	tunables->above_hispeed_delay = new_above_hispeed_delay;
+	tunables->nabove_hispeed_delay = ntokens;
+	spin_unlock_irqrestore(&tunables->above_hispeed_delay_lock, flags);
+	return count;
+
+}
+
+static ssize_t show_hispeed_freq(struct cpufreq_interactive_tunables *tunables,
+		char *buf)
+{
+	return sprintf(buf, "%u\n", tunables->hispeed_freq);
+}
+
+static ssize_t store_hispeed_freq(struct cpufreq_interactive_tunables *tunables,
+		const char *buf, size_t count)
+{
+	int ret;
+	long unsigned int val;
+
+	ret = kstrtoul(buf, 0, &val);
+	if (ret < 0)
+		return ret;
+	tunables->hispeed_freq = val;
+	return count;
+}
+
+static ssize_t show_go_hispeed_load(struct cpufreq_interactive_tunables
+		*tunables, char *buf)
+{
+	return sprintf(buf, "%lu\n", tunables->go_hispeed_load);
+}
+
+static ssize_t store_go_hispeed_load(struct cpufreq_interactive_tunables
+		*tunables, const char *buf, size_t count)
+{
+	int ret;
+	unsigned long val;
+
+	ret = kstrtoul(buf, 0, &val);
+	if (ret < 0)
+		return ret;
+	tunables->go_hispeed_load = val;
+	return count;
+}
+
+static ssize_t show_min_sample_time(struct cpufreq_interactive_tunables
+		*tunables, char *buf)
+{
+	return sprintf(buf, "%lu\n", tunables->min_sample_time);
+}
+
+static ssize_t store_min_sample_time(struct cpufreq_interactive_tunables
+		*tunables, const char *buf, size_t count)
+{
+	int ret;
+	unsigned long val;
+
+	ret = kstrtoul(buf, 0, &val);
+	if (ret < 0)
+		return ret;
+	tunables->min_sample_time = val;
+	return count;
+}
+
+static ssize_t show_timer_rate(struct cpufreq_interactive_tunables *tunables,
+		char *buf)
+{
+	return sprintf(buf, "%lu\n", tunables->timer_rate);
+}
+
+static ssize_t store_timer_rate(struct cpufreq_interactive_tunables *tunables,
+		const char *buf, size_t count)
+{
+	int ret;
+	unsigned long val, val_round;
+
+	ret = kstrtoul(buf, 0, &val);
+	if (ret < 0)
+		return ret;
+
+	val_round = jiffies_to_usecs(usecs_to_jiffies(val));
+	if (val != val_round)
+		pr_warn("timer_rate not aligned to jiffy. Rounded up to %lu\n",
+			val_round);
+
+	tunables->timer_rate = val_round;
+	return count;
+}
+
+static ssize_t show_timer_slack(struct cpufreq_interactive_tunables *tunables,
+		char *buf)
+{
+	return sprintf(buf, "%d\n", tunables->timer_slack_val);
+}
+
+static ssize_t store_timer_slack(struct cpufreq_interactive_tunables *tunables,
+		const char *buf, size_t count)
+{
+	int ret;
+	unsigned long val;
+
+	ret = kstrtol(buf, 10, &val);
+	if (ret < 0)
+		return ret;
+
+	tunables->timer_slack_val = val;
+	return count;
+}
+
+static ssize_t show_boost(struct cpufreq_interactive_tunables *tunables,
+			  char *buf)
+{
+	return sprintf(buf, "%d\n", tunables->boost_val);
+}
+
+static ssize_t store_boost(struct cpufreq_interactive_tunables *tunables,
+			   const char *buf, size_t count)
+{
+	int ret;
+	unsigned long val;
+
+	ret = kstrtoul(buf, 0, &val);
+	if (ret < 0)
+		return ret;
+
+	tunables->boost_val = val;
+
+	if (tunables->boost_val) {
+		trace_cpufreq_interactive_boost("on");
+		if (!tunables->boosted)
+			cpufreq_interactive_boost(tunables);
+	} else {
+		tunables->boostpulse_endtime = ktime_to_us(ktime_get());
+		trace_cpufreq_interactive_unboost("off");
+	}
+
+	return count;
+}
+
+static ssize_t store_boostpulse(struct cpufreq_interactive_tunables *tunables,
+				const char *buf, size_t count)
+{
+	int ret;
+	unsigned long val;
+
+	ret = kstrtoul(buf, 0, &val);
+	if (ret < 0)
+		return ret;
+
+	tunables->boostpulse_endtime = ktime_to_us(ktime_get()) +
+		tunables->boostpulse_duration_val;
+	trace_cpufreq_interactive_boost("pulse");
+	if (!tunables->boosted)
+		cpufreq_interactive_boost(tunables);
+	return count;
+}
+
+static ssize_t show_boostpulse_duration(struct cpufreq_interactive_tunables
+		*tunables, char *buf)
+{
+	return sprintf(buf, "%d\n", tunables->boostpulse_duration_val);
+}
+
+static ssize_t store_boostpulse_duration(struct cpufreq_interactive_tunables
+		*tunables, const char *buf, size_t count)
+{
+	int ret;
+	unsigned long val;
+
+	ret = kstrtoul(buf, 0, &val);
+	if (ret < 0)
+		return ret;
+
+	tunables->boostpulse_duration_val = val;
+	return count;
+}
+
+static ssize_t show_io_is_busy(struct cpufreq_interactive_tunables *tunables,
+		char *buf)
+{
+	return sprintf(buf, "%u\n", tunables->io_is_busy);
+}
+
+static ssize_t store_io_is_busy(struct cpufreq_interactive_tunables *tunables,
+		const char *buf, size_t count)
+{
+	int ret;
+	unsigned long val;
+
+	ret = kstrtoul(buf, 0, &val);
+	if (ret < 0)
+		return ret;
+	tunables->io_is_busy = val;
+	return count;
+}
+
+/*
+ * Create show/store routines
+ * - sys: One governor instance for complete SYSTEM
+ * - pol: One governor instance per struct cpufreq_policy
+ */
+#define show_gov_pol_sys(file_name)					\
+static ssize_t show_##file_name##_gov_sys				\
+(struct kobject *kobj, struct attribute *attr, char *buf)		\
+{									\
+	return show_##file_name(common_tunables, buf);			\
+}									\
+									\
+static ssize_t show_##file_name##_gov_pol				\
+(struct cpufreq_policy *policy, char *buf)				\
+{									\
+	return show_##file_name(policy->governor_data, buf);		\
+}
+
+#define store_gov_pol_sys(file_name)					\
+static ssize_t store_##file_name##_gov_sys				\
+(struct kobject *kobj, struct attribute *attr, const char *buf,		\
+	size_t count)							\
+{									\
+	return store_##file_name(common_tunables, buf, count);		\
+}									\
+									\
+static ssize_t store_##file_name##_gov_pol				\
+(struct cpufreq_policy *policy, const char *buf, size_t count)		\
+{									\
+	return store_##file_name(policy->governor_data, buf, count);	\
+}
+
+#define show_store_gov_pol_sys(file_name)				\
+show_gov_pol_sys(file_name);						\
+store_gov_pol_sys(file_name)
+
+show_store_gov_pol_sys(target_loads);
+show_store_gov_pol_sys(above_hispeed_delay);
+show_store_gov_pol_sys(hispeed_freq);
+show_store_gov_pol_sys(go_hispeed_load);
+show_store_gov_pol_sys(min_sample_time);
+show_store_gov_pol_sys(timer_rate);
+show_store_gov_pol_sys(timer_slack);
+show_store_gov_pol_sys(boost);
+store_gov_pol_sys(boostpulse);
+show_store_gov_pol_sys(boostpulse_duration);
+show_store_gov_pol_sys(io_is_busy);
+
+#define gov_sys_attr_rw(_name)						\
+static struct global_attr _name##_gov_sys =				\
+__ATTR(_name, 0644, show_##_name##_gov_sys, store_##_name##_gov_sys)
+
+#define gov_pol_attr_rw(_name)						\
+static struct freq_attr _name##_gov_pol =				\
+__ATTR(_name, 0644, show_##_name##_gov_pol, store_##_name##_gov_pol)
+
+#define gov_sys_pol_attr_rw(_name)					\
+	gov_sys_attr_rw(_name);						\
+	gov_pol_attr_rw(_name)
+
+gov_sys_pol_attr_rw(target_loads);
+gov_sys_pol_attr_rw(above_hispeed_delay);
+gov_sys_pol_attr_rw(hispeed_freq);
+gov_sys_pol_attr_rw(go_hispeed_load);
+gov_sys_pol_attr_rw(min_sample_time);
+gov_sys_pol_attr_rw(timer_rate);
+gov_sys_pol_attr_rw(timer_slack);
+gov_sys_pol_attr_rw(boost);
+gov_sys_pol_attr_rw(boostpulse_duration);
+gov_sys_pol_attr_rw(io_is_busy);
+
+static struct global_attr boostpulse_gov_sys =
+	__ATTR(boostpulse, 0200, NULL, store_boostpulse_gov_sys);
+
+static struct freq_attr boostpulse_gov_pol =
+	__ATTR(boostpulse, 0200, NULL, store_boostpulse_gov_pol);
+
+/* One Governor instance for entire system */
+static struct attribute *interactive_attributes_gov_sys[] = {
+	&target_loads_gov_sys.attr,
+	&above_hispeed_delay_gov_sys.attr,
+	&hispeed_freq_gov_sys.attr,
+	&go_hispeed_load_gov_sys.attr,
+	&min_sample_time_gov_sys.attr,
+	&timer_rate_gov_sys.attr,
+	&timer_slack_gov_sys.attr,
+	&boost_gov_sys.attr,
+	&boostpulse_gov_sys.attr,
+	&boostpulse_duration_gov_sys.attr,
+	&io_is_busy_gov_sys.attr,
+	NULL,
+};
+
+static struct attribute_group interactive_attr_group_gov_sys = {
+	.attrs = interactive_attributes_gov_sys,
+	.name = "interactive",
+};
+
+/* Per policy governor instance */
+static struct attribute *interactive_attributes_gov_pol[] = {
+	&target_loads_gov_pol.attr,
+	&above_hispeed_delay_gov_pol.attr,
+	&hispeed_freq_gov_pol.attr,
+	&go_hispeed_load_gov_pol.attr,
+	&min_sample_time_gov_pol.attr,
+	&timer_rate_gov_pol.attr,
+	&timer_slack_gov_pol.attr,
+	&boost_gov_pol.attr,
+	&boostpulse_gov_pol.attr,
+	&boostpulse_duration_gov_pol.attr,
+	&io_is_busy_gov_pol.attr,
+	NULL,
+};
+
+static struct attribute_group interactive_attr_group_gov_pol = {
+	.attrs = interactive_attributes_gov_pol,
+	.name = "interactive",
+};
+
+static struct attribute_group *get_sysfs_attr(void)
+{
+	if (have_governor_per_policy())
+		return &interactive_attr_group_gov_pol;
+	else
+		return &interactive_attr_group_gov_sys;
+}
+
+static int cpufreq_interactive_idle_notifier(struct notifier_block *nb,
+					     unsigned long val,
+					     void *data)
+{
+	if (val == IDLE_END)
+		cpufreq_interactive_idle_end();
+
+	return 0;
+}
+
+static struct notifier_block cpufreq_interactive_idle_nb = {
+	.notifier_call = cpufreq_interactive_idle_notifier,
+};
+
+static int cpufreq_governor_interactive(struct cpufreq_policy *policy,
+		unsigned int event)
+{
+	int rc;
+	unsigned int j;
+	struct cpufreq_interactive_cpuinfo *pcpu;
+	struct cpufreq_frequency_table *freq_table;
+	struct cpufreq_interactive_tunables *tunables;
+	unsigned long flags;
+
+	if (have_governor_per_policy())
+		tunables = policy->governor_data;
+	else
+		tunables = common_tunables;
+
+	WARN_ON(!tunables && (event != CPUFREQ_GOV_POLICY_INIT));
+
+	switch (event) {
+	case CPUFREQ_GOV_POLICY_INIT:
+		if (have_governor_per_policy()) {
+			WARN_ON(tunables);
+		} else if (tunables) {
+			tunables->usage_count++;
+			policy->governor_data = tunables;
+			return 0;
+		}
+
+		tunables = kzalloc(sizeof(*tunables), GFP_KERNEL);
+		if (!tunables) {
+			pr_err("%s: POLICY_INIT: kzalloc failed\n", __func__);
+			return -ENOMEM;
+		}
+
+		tunables->usage_count = 1;
+		tunables->above_hispeed_delay = default_above_hispeed_delay;
+		tunables->nabove_hispeed_delay =
+			ARRAY_SIZE(default_above_hispeed_delay);
+		tunables->go_hispeed_load = DEFAULT_GO_HISPEED_LOAD;
+		tunables->target_loads = default_target_loads;
+		tunables->ntarget_loads = ARRAY_SIZE(default_target_loads);
+		tunables->min_sample_time = DEFAULT_MIN_SAMPLE_TIME;
+		tunables->timer_rate = DEFAULT_TIMER_RATE;
+		tunables->boostpulse_duration_val = DEFAULT_MIN_SAMPLE_TIME;
+		tunables->timer_slack_val = DEFAULT_TIMER_SLACK;
+
+		spin_lock_init(&tunables->target_loads_lock);
+		spin_lock_init(&tunables->above_hispeed_delay_lock);
+
+		policy->governor_data = tunables;
+		if (!have_governor_per_policy()) {
+			common_tunables = tunables;
+			WARN_ON(cpufreq_get_global_kobject());
+		}
+
+		rc = sysfs_create_group(get_governor_parent_kobj(policy),
+				get_sysfs_attr());
+		if (rc) {
+			kfree(tunables);
+			policy->governor_data = NULL;
+			if (!have_governor_per_policy()) {
+				common_tunables = NULL;
+				cpufreq_put_global_kobject();
+			}
+			return rc;
+		}
+
+		if (!policy->governor->initialized) {
+			idle_notifier_register(&cpufreq_interactive_idle_nb);
+			cpufreq_register_notifier(&cpufreq_notifier_block,
+					CPUFREQ_TRANSITION_NOTIFIER);
+		}
+
+		break;
+
+	case CPUFREQ_GOV_POLICY_EXIT:
+		if (!--tunables->usage_count) {
+			if (policy->governor->initialized == 1) {
+				cpufreq_unregister_notifier(&cpufreq_notifier_block,
+						CPUFREQ_TRANSITION_NOTIFIER);
+				idle_notifier_unregister(&cpufreq_interactive_idle_nb);
+			}
+
+			sysfs_remove_group(get_governor_parent_kobj(policy),
+					get_sysfs_attr());
+
+			if (!have_governor_per_policy())
+				cpufreq_put_global_kobject();
+
+			kfree(tunables);
+			common_tunables = NULL;
+		}
+
+		policy->governor_data = NULL;
+		break;
+
+	case CPUFREQ_GOV_START:
+		mutex_lock(&gov_lock);
+
+		freq_table = cpufreq_frequency_get_table(policy->cpu);
+		if (!tunables->hispeed_freq)
+			tunables->hispeed_freq = policy->max;
+
+		for_each_cpu(j, policy->cpus) {
+			pcpu = &per_cpu(cpuinfo, j);
+			pcpu->policy = policy;
+			pcpu->target_freq = policy->cur;
+			pcpu->freq_table = freq_table;
+			pcpu->floor_freq = pcpu->target_freq;
+			pcpu->pol_floor_val_time =
+				ktime_to_us(ktime_get());
+			pcpu->loc_floor_val_time = pcpu->pol_floor_val_time;
+			pcpu->pol_hispeed_val_time = pcpu->pol_floor_val_time;
+			pcpu->loc_hispeed_val_time = pcpu->pol_floor_val_time;
+			down_write(&pcpu->enable_sem);
+			del_timer_sync(&pcpu->cpu_timer);
+			del_timer_sync(&pcpu->cpu_slack_timer);
+			cpufreq_interactive_timer_start(tunables, j);
+			pcpu->governor_enabled = 1;
+			up_write(&pcpu->enable_sem);
+		}
+
+		mutex_unlock(&gov_lock);
+		break;
+
+	case CPUFREQ_GOV_STOP:
+		mutex_lock(&gov_lock);
+		for_each_cpu(j, policy->cpus) {
+			pcpu = &per_cpu(cpuinfo, j);
+			down_write(&pcpu->enable_sem);
+			pcpu->governor_enabled = 0;
+			del_timer_sync(&pcpu->cpu_timer);
+			del_timer_sync(&pcpu->cpu_slack_timer);
+			up_write(&pcpu->enable_sem);
+		}
+
+		mutex_unlock(&gov_lock);
+		break;
+
+	case CPUFREQ_GOV_LIMITS:
+		if (policy->max < policy->cur)
+			__cpufreq_driver_target(policy,
+					policy->max, CPUFREQ_RELATION_H);
+		else if (policy->min > policy->cur)
+			__cpufreq_driver_target(policy,
+					policy->min, CPUFREQ_RELATION_L);
+		for_each_cpu(j, policy->cpus) {
+			pcpu = &per_cpu(cpuinfo, j);
+
+			down_read(&pcpu->enable_sem);
+			if (pcpu->governor_enabled == 0) {
+				up_read(&pcpu->enable_sem);
+				continue;
+			}
+
+			spin_lock_irqsave(&pcpu->target_freq_lock, flags);
+			if (policy->max < pcpu->target_freq)
+				pcpu->target_freq = policy->max;
+			else if (policy->min > pcpu->target_freq)
+				pcpu->target_freq = policy->min;
+
+			spin_unlock_irqrestore(&pcpu->target_freq_lock, flags);
+			up_read(&pcpu->enable_sem);
+		}
+		break;
+	}
+	return 0;
+}
+
+#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE
+static
+#endif
+struct cpufreq_governor cpufreq_gov_interactive = {
+	.name = "interactive",
+	.governor = cpufreq_governor_interactive,
+	.max_transition_latency = 10000000,
+	.owner = THIS_MODULE,
+};
+
+static void cpufreq_interactive_nop_timer(unsigned long data)
+{
+}
+
+static int __init cpufreq_interactive_init(void)
+{
+	unsigned int i;
+	struct cpufreq_interactive_cpuinfo *pcpu;
+	struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
+
+	/* Initalize per-cpu timers */
+	for_each_possible_cpu(i) {
+		pcpu = &per_cpu(cpuinfo, i);
+		init_timer_deferrable(&pcpu->cpu_timer);
+		pcpu->cpu_timer.function = cpufreq_interactive_timer;
+		pcpu->cpu_timer.data = i;
+		init_timer(&pcpu->cpu_slack_timer);
+		pcpu->cpu_slack_timer.function = cpufreq_interactive_nop_timer;
+		spin_lock_init(&pcpu->load_lock);
+		spin_lock_init(&pcpu->target_freq_lock);
+		init_rwsem(&pcpu->enable_sem);
+	}
+
+	spin_lock_init(&speedchange_cpumask_lock);
+	mutex_init(&gov_lock);
+	speedchange_task =
+		kthread_create(cpufreq_interactive_speedchange_task, NULL,
+			       "cfinteractive");
+	if (IS_ERR(speedchange_task))
+		return PTR_ERR(speedchange_task);
+
+	sched_setscheduler_nocheck(speedchange_task, SCHED_FIFO, &param);
+	get_task_struct(speedchange_task);
+
+	/* NB: wake up so the thread does not look hung to the freezer */
+	wake_up_process(speedchange_task);
+
+	return cpufreq_register_governor(&cpufreq_gov_interactive);
+}
+
+#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE
+fs_initcall(cpufreq_interactive_init);
+#else
+module_init(cpufreq_interactive_init);
+#endif
+
+static void __exit cpufreq_interactive_exit(void)
+{
+	cpufreq_unregister_governor(&cpufreq_gov_interactive);
+	kthread_stop(speedchange_task);
+	put_task_struct(speedchange_task);
+}
+
+module_exit(cpufreq_interactive_exit);
+
+MODULE_AUTHOR("Mike Chan <mike@android.com>");
+MODULE_DESCRIPTION("'cpufreq_interactive' - A cpufreq governor for "
+	"Latency sensitive workloads");
+MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 0cd9b4dcef9..a2f1d41820b 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -13,6 +13,9 @@
 #include <linux/cpufreq.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/sort.h>
+#include <linux/of.h>
+#include <linux/sched.h>
 #include <linux/cputime.h>
 
 static spinlock_t cpufreq_stats_lock;
@@ -31,7 +34,28 @@ struct cpufreq_stats {
 #endif
 };
 
+struct all_cpufreq_stats {
+	unsigned int state_num;
+	cputime64_t *time_in_state;
+	unsigned int *freq_table;
+};
+
+struct cpufreq_power_stats {
+	unsigned int state_num;
+	unsigned int *curr;
+	unsigned int *freq_table;
+};
+
+struct all_freq_table {
+	unsigned int *freq_table;
+	unsigned int table_size;
+};
+
+static struct all_freq_table *all_freq_table;
+
+static DEFINE_PER_CPU(struct all_cpufreq_stats *, all_cpufreq_stats);
 static DEFINE_PER_CPU(struct cpufreq_stats *, cpufreq_stats_table);
+static DEFINE_PER_CPU(struct cpufreq_power_stats *, cpufreq_power_stats);
 
 struct cpufreq_stats_attribute {
 	struct attribute attr;
@@ -41,14 +65,24 @@ struct cpufreq_stats_attribute {
 static int cpufreq_stats_update(unsigned int cpu)
 {
 	struct cpufreq_stats *stat;
+	struct all_cpufreq_stats *all_stat;
 	unsigned long long cur_time;
 
 	cur_time = get_jiffies_64();
 	spin_lock(&cpufreq_stats_lock);
 	stat = per_cpu(cpufreq_stats_table, cpu);
-	if (stat->time_in_state)
+	all_stat = per_cpu(all_cpufreq_stats, cpu);
+	if (!stat) {
+		spin_unlock(&cpufreq_stats_lock);
+		return 0;
+	}
+	if (stat->time_in_state) {
 		stat->time_in_state[stat->last_index] +=
 			cur_time - stat->last_time;
+		if (all_stat)
+			all_stat->time_in_state[stat->last_index] +=
+					cur_time - stat->last_time;
+	}
 	stat->last_time = cur_time;
 	spin_unlock(&cpufreq_stats_lock);
 	return 0;
@@ -79,6 +113,104 @@ static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf)
 	return len;
 }
 
+static int get_index_all_cpufreq_stat(struct all_cpufreq_stats *all_stat,
+		unsigned int freq)
+{
+	int i;
+	if (!all_stat)
+		return -1;
+	for (i = 0; i < all_stat->state_num; i++) {
+		if (all_stat->freq_table[i] == freq)
+			return i;
+	}
+	return -1;
+}
+
+void acct_update_power(struct task_struct *task, cputime_t cputime) {
+	struct cpufreq_power_stats *powerstats;
+	struct cpufreq_stats *stats;
+	unsigned int cpu_num, curr;
+
+	if (!task)
+		return;
+	cpu_num = task_cpu(task);
+	powerstats = per_cpu(cpufreq_power_stats, cpu_num);
+	stats = per_cpu(cpufreq_stats_table, cpu_num);
+	if (!powerstats || !stats)
+		return;
+
+	curr = powerstats->curr[stats->last_index];
+	if (task->cpu_power != ULLONG_MAX)
+		task->cpu_power += curr * cputime_to_usecs(cputime);
+}
+EXPORT_SYMBOL_GPL(acct_update_power);
+
+static ssize_t show_current_in_state(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	ssize_t len = 0;
+	unsigned int i, cpu;
+	struct cpufreq_power_stats *powerstats;
+
+	spin_lock(&cpufreq_stats_lock);
+	for_each_possible_cpu(cpu) {
+		powerstats = per_cpu(cpufreq_power_stats, cpu);
+		if (!powerstats)
+			continue;
+		len += scnprintf(buf + len, PAGE_SIZE - len, "CPU%d:", cpu);
+		for (i = 0; i < powerstats->state_num; i++)
+			len += scnprintf(buf + len, PAGE_SIZE - len,
+					"%d=%d ", powerstats->freq_table[i],
+					powerstats->curr[i]);
+		len += scnprintf(buf + len, PAGE_SIZE - len, "\n");
+	}
+	spin_unlock(&cpufreq_stats_lock);
+	return len;
+}
+
+static ssize_t show_all_time_in_state(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	ssize_t len = 0;
+	unsigned int i, cpu, freq, index;
+	struct all_cpufreq_stats *all_stat;
+	struct cpufreq_policy *policy;
+
+	len += scnprintf(buf + len, PAGE_SIZE - len, "freq\t\t");
+	for_each_possible_cpu(cpu) {
+		len += scnprintf(buf + len, PAGE_SIZE - len, "cpu%d\t\t", cpu);
+		if (cpu_online(cpu))
+			cpufreq_stats_update(cpu);
+	}
+
+	if (!all_freq_table)
+		goto out;
+	for (i = 0; i < all_freq_table->table_size; i++) {
+		freq = all_freq_table->freq_table[i];
+		len += scnprintf(buf + len, PAGE_SIZE - len, "\n%u\t\t", freq);
+		for_each_possible_cpu(cpu) {
+			policy = cpufreq_cpu_get(cpu);
+			if (policy == NULL)
+				continue;
+			all_stat = per_cpu(all_cpufreq_stats, policy->cpu);
+			index = get_index_all_cpufreq_stat(all_stat, freq);
+			if (index != -1) {
+				len += scnprintf(buf + len, PAGE_SIZE - len,
+					"%llu\t\t", (unsigned long long)
+					cputime64_to_clock_t(all_stat->time_in_state[index]));
+			} else {
+				len += scnprintf(buf + len, PAGE_SIZE - len,
+						"N/A\t\t");
+			}
+			cpufreq_cpu_put(policy);
+		}
+	}
+
+out:
+	len += scnprintf(buf + len, PAGE_SIZE - len, "\n");
+	return len;
+}
+
 #ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
 {
@@ -142,6 +274,12 @@ static struct attribute_group stats_attr_group = {
 	.name = "stats"
 };
 
+static struct kobj_attribute _attr_all_time_in_state = __ATTR(all_time_in_state,
+		0444, show_all_time_in_state, NULL);
+
+static struct kobj_attribute _attr_current_in_state = __ATTR(current_in_state,
+		0444, show_current_in_state, NULL);
+
 static int freq_table_get_index(struct cpufreq_stats *stat, unsigned int freq)
 {
 	int index;
@@ -180,17 +318,54 @@ static void cpufreq_stats_free_table(unsigned int cpu)
 	cpufreq_cpu_put(policy);
 }
 
-static int __cpufreq_stats_create_table(struct cpufreq_policy *policy)
+static void cpufreq_allstats_free(void)
+{
+	int cpu;
+	struct all_cpufreq_stats *all_stat;
+
+	sysfs_remove_file(cpufreq_global_kobject,
+						&_attr_all_time_in_state.attr);
+
+	for_each_possible_cpu(cpu) {
+		all_stat = per_cpu(all_cpufreq_stats, cpu);
+		if (!all_stat)
+			continue;
+		kfree(all_stat->time_in_state);
+		kfree(all_stat);
+		per_cpu(all_cpufreq_stats, cpu) = NULL;
+	}
+	if (all_freq_table) {
+		kfree(all_freq_table->freq_table);
+		kfree(all_freq_table);
+		all_freq_table = NULL;
+	}
+}
+
+static void cpufreq_powerstats_free(void)
+{
+	int cpu;
+	struct cpufreq_power_stats *powerstats;
+
+	sysfs_remove_file(cpufreq_global_kobject, &_attr_current_in_state.attr);
+
+	for_each_possible_cpu(cpu) {
+		powerstats = per_cpu(cpufreq_power_stats, cpu);
+		if (!powerstats)
+			continue;
+		kfree(powerstats->curr);
+		kfree(powerstats);
+		per_cpu(cpufreq_power_stats, cpu) = NULL;
+	}
+}
+
+static int __cpufreq_stats_create_table(struct cpufreq_policy *policy,
+		struct cpufreq_frequency_table *table, int count)
 {
-	unsigned int i, count = 0, ret = 0;
+	unsigned int i, ret = 0;
 	struct cpufreq_stats *stat;
 	unsigned int alloc_size;
 	unsigned int cpu = policy->cpu;
-	struct cpufreq_frequency_table *pos, *table;
-
-	table = cpufreq_frequency_get_table(cpu);
-	if (unlikely(!table))
-		return 0;
+	struct cpufreq_frequency_table *pos;
 
 	if (per_cpu(cpufreq_stats_table, cpu))
 		return -EBUSY;
@@ -205,9 +380,6 @@ static int __cpufreq_stats_create_table(struct cpufreq_policy *policy)
 	stat->cpu = cpu;
 	per_cpu(cpufreq_stats_table, cpu) = stat;
 
-	cpufreq_for_each_valid_entry(pos, table)
-		count++;
-
 	alloc_size = count * sizeof(int) + count * sizeof(u64);
 
 #ifdef CONFIG_CPU_FREQ_STAT_DETAILS
@@ -242,10 +414,159 @@ error_out:
 	return ret;
 }
 
+static void cpufreq_stats_update_policy_cpu(struct cpufreq_policy *policy)
+{
+	struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table,
+			policy->last_cpu);
+
+	pr_debug("Updating stats_table for new_cpu %u from last_cpu %u\n",
+			policy->cpu, policy->last_cpu);
+	per_cpu(cpufreq_stats_table, policy->cpu) = per_cpu(cpufreq_stats_table,
+			policy->last_cpu);
+	per_cpu(cpufreq_stats_table, policy->last_cpu) = NULL;
+	stat->cpu = policy->cpu;
+}
+
+static void cpufreq_powerstats_create(unsigned int cpu,
+		struct cpufreq_frequency_table *table, int count) {
+	unsigned int alloc_size, i = 0, ret = 0;
+	struct cpufreq_power_stats *powerstats;
+	struct cpufreq_frequency_table *pos;
+	struct device_node *cpu_node;
+	char device_path[16];
+
+	powerstats = kzalloc(sizeof(struct cpufreq_power_stats),
+			GFP_KERNEL);
+	if (!powerstats)
+		return;
+
+	/* Allocate memory for freq table per cpu as well as clockticks per
+	 * freq*/
+	alloc_size = count * sizeof(unsigned int) +
+		count * sizeof(unsigned int);
+	powerstats->curr = kzalloc(alloc_size, GFP_KERNEL);
+	if (!powerstats->curr) {
+		kfree(powerstats);
+		return;
+	}
+	powerstats->freq_table = powerstats->curr + count;
+
+	spin_lock(&cpufreq_stats_lock);
+	i = 0;
+	cpufreq_for_each_valid_entry(pos, table)
+		powerstats->freq_table[i++] = pos->frequency;
+	powerstats->state_num = i;
+
+	snprintf(device_path, sizeof(device_path), "/cpus/cpu@%d", cpu);
+	cpu_node = of_find_node_by_path(device_path);
+	if (cpu_node) {
+		ret = of_property_read_u32_array(cpu_node, "current",
+				powerstats->curr, count);
+		if (ret) {
+			kfree(powerstats->curr);
+			kfree(powerstats);
+			powerstats = NULL;
+		}
+	}
+	per_cpu(cpufreq_power_stats, cpu) = powerstats;
+	spin_unlock(&cpufreq_stats_lock);
+}
+
+static int compare_for_sort(const void *lhs_ptr, const void *rhs_ptr)
+{
+	unsigned int lhs = *(const unsigned int *)(lhs_ptr);
+	unsigned int rhs = *(const unsigned int *)(rhs_ptr);
+	if (lhs < rhs)
+		return -1;
+	if (lhs > rhs)
+		return 1;
+	return 0;
+}
+
+static bool check_all_freq_table(unsigned int freq)
+{
+	int i;
+	for (i = 0; i < all_freq_table->table_size; i++) {
+		if (freq == all_freq_table->freq_table[i])
+			return true;
+	}
+	return false;
+}
+
+static void create_all_freq_table(void)
+{
+	all_freq_table = kzalloc(sizeof(struct all_freq_table),
+			GFP_KERNEL);
+	if (!all_freq_table)
+		pr_warn("could not allocate memory for all_freq_table\n");
+	return;
+}
+
+static void add_all_freq_table(unsigned int freq)
+{
+	unsigned int size;
+	size = sizeof(unsigned int) * (all_freq_table->table_size + 1);
+	all_freq_table->freq_table = krealloc(all_freq_table->freq_table,
+			size, GFP_ATOMIC);
+	if (IS_ERR(all_freq_table->freq_table)) {
+		pr_warn("Could not reallocate memory for freq_table\n");
+		all_freq_table->freq_table = NULL;
+		return;
+	}
+	all_freq_table->freq_table[all_freq_table->table_size++] = freq;
+}
+
+static void cpufreq_allstats_create(unsigned int cpu,
+		struct cpufreq_frequency_table *table, int count)
+{
+	int i , j = 0;
+	unsigned int alloc_size;
+	struct all_cpufreq_stats *all_stat;
+	bool sort_needed = false;
+
+	all_stat = kzalloc(sizeof(struct all_cpufreq_stats),
+			GFP_KERNEL);
+	if (!all_stat) {
+		pr_warn("Cannot allocate memory for cpufreq stats\n");
+		return;
+	}
+
+	/*Allocate memory for freq table per cpu as well as clockticks per freq*/
+	alloc_size = count * sizeof(int) + count * sizeof(cputime64_t);
+	all_stat->time_in_state = kzalloc(alloc_size, GFP_KERNEL);
+	if (!all_stat->time_in_state) {
+		pr_warn("Cannot allocate memory for cpufreq time_in_state\n");
+		kfree(all_stat);
+		all_stat = NULL;
+		return;
+	}
+	all_stat->freq_table = (unsigned int *)
+		(all_stat->time_in_state + count);
+
+	spin_lock(&cpufreq_stats_lock);
+	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
+		unsigned int freq = table[i].frequency;
+		if (freq == CPUFREQ_ENTRY_INVALID)
+			continue;
+		all_stat->freq_table[j++] = freq;
+		if (all_freq_table && !check_all_freq_table(freq)) {
+			add_all_freq_table(freq);
+			sort_needed = true;
+		}
+	}
+	if (sort_needed)
+		sort(all_freq_table->freq_table, all_freq_table->table_size,
+				sizeof(unsigned int), &compare_for_sort, NULL);
+	all_stat->state_num = j;
+	per_cpu(all_cpufreq_stats, cpu) = all_stat;
+	spin_unlock(&cpufreq_stats_lock);
+}
+
 static void cpufreq_stats_create_table(unsigned int cpu)
 {
 	struct cpufreq_policy *policy;
-
+	struct cpufreq_frequency_table *table, *pos;
+	int count = 0;
 	/*
 	 * "likely(!policy)" because normally cpufreq_stats will be registered
 	 * before cpufreq driver
@@ -254,37 +575,52 @@ static void cpufreq_stats_create_table(unsigned int cpu)
 	if (likely(!policy))
 		return;
 
-	__cpufreq_stats_create_table(policy);
+	table = cpufreq_frequency_get_table(policy->cpu);
+	if (likely(table)) {
+		cpufreq_for_each_valid_entry(pos, table)
+			count++;
 
-	cpufreq_cpu_put(policy);
-}
+		if (!per_cpu(all_cpufreq_stats, cpu))
+			cpufreq_allstats_create(cpu, table, count);
 
-static void cpufreq_stats_update_policy_cpu(struct cpufreq_policy *policy)
-{
-	struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table,
-			policy->last_cpu);
+		if (!per_cpu(cpufreq_power_stats, cpu))
+			cpufreq_powerstats_create(cpu, table, count);
 
-	pr_debug("Updating stats_table for new_cpu %u from last_cpu %u\n",
-			policy->cpu, policy->last_cpu);
-	per_cpu(cpufreq_stats_table, policy->cpu) = per_cpu(cpufreq_stats_table,
-			policy->last_cpu);
-	per_cpu(cpufreq_stats_table, policy->last_cpu) = NULL;
-	stat->cpu = policy->cpu;
+		__cpufreq_stats_create_table(policy, table, count);
+	}
+	cpufreq_cpu_put(policy);
 }
 
 static int cpufreq_stat_notifier_policy(struct notifier_block *nb,
 		unsigned long val, void *data)
 {
-	int ret = 0;
+	int ret = 0, count = 0;
 	struct cpufreq_policy *policy = data;
+	struct cpufreq_frequency_table *table, *pos;
+	unsigned int cpu_num, cpu = policy->cpu;
 
 	if (val == CPUFREQ_UPDATE_POLICY_CPU) {
 		cpufreq_stats_update_policy_cpu(policy);
 		return 0;
 	}
 
+	table = cpufreq_frequency_get_table(cpu);
+	if (!table)
+		return 0;
+
+	cpufreq_for_each_valid_entry(pos, table)
+		count++;
+
+	if (!per_cpu(all_cpufreq_stats, cpu))
+		cpufreq_allstats_create(cpu, table, count);
+
+	for_each_possible_cpu(cpu_num) {
+		if (!per_cpu(cpufreq_power_stats, cpu_num))
+			cpufreq_powerstats_create(cpu_num, table, count);
+	}
+
 	if (val == CPUFREQ_CREATE_POLICY)
-		ret = __cpufreq_stats_create_table(policy);
+		ret = __cpufreq_stats_create_table(policy, table, count);
 	else if (val == CPUFREQ_REMOVE_POLICY)
 		__cpufreq_stats_free_table(policy);
 
@@ -359,6 +695,18 @@ static int __init cpufreq_stats_init(void)
 		return ret;
 	}
 
+	create_all_freq_table();
+	WARN_ON(cpufreq_get_global_kobject());
+	ret = sysfs_create_file(cpufreq_global_kobject,
+			&_attr_all_time_in_state.attr);
+	if (ret)
+		pr_warn("Cannot create sysfs file for cpufreq stats\n");
+
+	ret = sysfs_create_file(cpufreq_global_kobject,
+			&_attr_current_in_state.attr);
+	if (ret)
+		pr_warn("Cannot create sysfs file for cpufreq current stats\n");
+
 	return 0;
 }
 static void __exit cpufreq_stats_exit(void)
@@ -371,6 +719,9 @@ static void __exit cpufreq_stats_exit(void)
 			CPUFREQ_TRANSITION_NOTIFIER);
 	for_each_online_cpu(cpu)
 		cpufreq_stats_free_table(cpu);
+	cpufreq_allstats_free();
+	cpufreq_powerstats_free();
+	cpufreq_put_global_kobject();
 }
 
 MODULE_AUTHOR("Zou Nan hai <nanhai.zou@intel.com>");
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 27bb6d3877e..d0d21363c63 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -443,7 +443,7 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate)
 
 	val |= vid;
 
-	wrmsrl(MSR_IA32_PERF_CTL, val);
+	wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val);
 }
 
 #define BYT_BCLK_FREQS 5
diff --git a/drivers/cpufreq/s3c2416-cpufreq.c b/drivers/cpufreq/s3c2416-cpufreq.c
index 2fd53eaaec2..d6d425773fa 100644
--- a/drivers/cpufreq/s3c2416-cpufreq.c
+++ b/drivers/cpufreq/s3c2416-cpufreq.c
@@ -263,7 +263,7 @@ out:
 }
 
 #ifdef CONFIG_ARM_S3C2416_CPUFREQ_VCORESCALE
-static void __init s3c2416_cpufreq_cfg_regulator(struct s3c2416_data *s3c_freq)
+static void s3c2416_cpufreq_cfg_regulator(struct s3c2416_data *s3c_freq)
 {
 	int count, v, i, found;
 	struct cpufreq_frequency_table *pos;
@@ -333,7 +333,7 @@ static struct notifier_block s3c2416_cpufreq_reboot_notifier = {
 	.notifier_call = s3c2416_cpufreq_reboot_notifier_evt,
 };
 
-static int __init s3c2416_cpufreq_driver_init(struct cpufreq_policy *policy)
+static int s3c2416_cpufreq_driver_init(struct cpufreq_policy *policy)
 {
 	struct s3c2416_data *s3c_freq = &s3c2416_cpufreq;
 	struct cpufreq_frequency_table *pos;
diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c
index d00f1cee450..733aa5153e7 100644
--- a/drivers/cpufreq/s3c24xx-cpufreq.c
+++ b/drivers/cpufreq/s3c24xx-cpufreq.c
@@ -144,11 +144,6 @@ static void s3c_cpufreq_setfvco(struct s3c_cpufreq_config *cfg)
 	(cfg->info->set_fvco)(cfg);
 }
 
-static inline void s3c_cpufreq_resume_clocks(void)
-{
-	cpu_cur.info->resume_clocks();
-}
-
 static inline void s3c_cpufreq_updateclk(struct clk *clk,
 					 unsigned int freq)
 {
@@ -417,9 +412,6 @@ static int s3c_cpufreq_resume(struct cpufreq_policy *policy)
 
 	last_target = ~0;	/* invalidate last_target setting */
 
-	/* first, find out what speed we resumed at. */
-	s3c_cpufreq_resume_clocks();
-
 	/* whilst we will be called later on, we try and re-set the
 	 * cpu frequencies as soon as possible so that we do not end
 	 * up resuming devices and then immediately having to re-set
@@ -454,7 +446,7 @@ static struct cpufreq_driver s3c24xx_driver = {
 };
 
 
-int __init s3c_cpufreq_register(struct s3c_cpufreq_info *info)
+int s3c_cpufreq_register(struct s3c_cpufreq_info *info)
 {
 	if (!info || !info->name) {
 		printk(KERN_ERR "%s: failed to pass valid information\n",
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
new file mode 100644
index 00000000000..304d2057163
--- /dev/null
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -0,0 +1,107 @@
+/*
+ * System Control and Power Interface (SCPI) based CPUFreq Interface driver
+ *
+ * It provides necessary ops to arm_big_little cpufreq driver.
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ * Sudeep Holla <sudeep.holla@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cpufreq.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/scpi_protocol.h>
+#include <linux/types.h>
+
+#include "arm_big_little.h"
+
+static struct scpi_ops *scpi_ops;
+
+static struct scpi_dvfs_info *scpi_get_dvfs_info(struct device *cpu_dev)
+{
+	u8 domain = topology_physical_package_id(cpu_dev->id);
+
+	if (domain < 0)
+		return ERR_PTR(-EINVAL);
+	return scpi_ops->dvfs_get_info(domain);
+}
+
+static int scpi_init_opp_table(struct device *cpu_dev)
+{
+	int idx, ret = 0;
+	struct scpi_opp *opp;
+	struct scpi_dvfs_info *info = scpi_get_dvfs_info(cpu_dev);
+
+	if (IS_ERR(info))
+		return PTR_ERR(info);
+
+	if (!info->opps)
+		return -EIO;
+
+	for (opp = info->opps, idx = 0; idx < info->count; idx++, opp++) {
+		ret = dev_pm_opp_add(cpu_dev, opp->freq, opp->m_volt * 1000);
+		if (ret) {
+			dev_warn(cpu_dev, "failed to add opp %uHz %umV\n",
+				 opp->freq, opp->m_volt);
+			return ret;
+		}
+	}
+	return ret;
+}
+
+static int scpi_get_transition_latency(struct device *cpu_dev)
+{
+	struct scpi_dvfs_info *info = scpi_get_dvfs_info(cpu_dev);
+
+	if (IS_ERR(info))
+		return PTR_ERR(info);
+	return info->latency;
+}
+
+static struct cpufreq_arm_bL_ops scpi_cpufreq_ops = {
+	.name	= "scpi",
+	.get_transition_latency = scpi_get_transition_latency,
+	.init_opp_table = scpi_init_opp_table,
+};
+
+static int scpi_cpufreq_probe(struct platform_device *pdev)
+{
+	scpi_ops = get_scpi_ops();
+	if (!scpi_ops)
+		return -EIO;
+
+	return bL_cpufreq_register(&scpi_cpufreq_ops);
+}
+
+static int scpi_cpufreq_remove(struct platform_device *pdev)
+{
+	bL_cpufreq_unregister(&scpi_cpufreq_ops);
+	scpi_ops = NULL;
+	return 0;
+}
+
+static struct platform_driver scpi_cpufreq_platdrv = {
+	.driver = {
+		.name	= "scpi-cpufreq",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= scpi_cpufreq_probe,
+	.remove		= scpi_cpufreq_remove,
+};
+module_platform_driver(scpi_cpufreq_platdrv);
+
+MODULE_AUTHOR("Sudeep Holla <sudeep.holla@arm.com>");
+MODULE_DESCRIPTION("ARM SCPI CPUFreq interface driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c
index 7047821a7f8..4ab7a215667 100644
--- a/drivers/cpufreq/speedstep-lib.c
+++ b/drivers/cpufreq/speedstep-lib.c
@@ -400,6 +400,7 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 
 	pr_debug("previous speed is %u\n", prev_speed);
 
+	preempt_disable();
 	local_irq_save(flags);
 
 	/* switch to low state */
@@ -464,6 +465,8 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 
 out:
 	local_irq_restore(flags);
+	preempt_enable();
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(speedstep_get_freqs);
diff --git a/drivers/cpufreq/speedstep-smi.c b/drivers/cpufreq/speedstep-smi.c
index 5fc96d5d656..819229e824f 100644
--- a/drivers/cpufreq/speedstep-smi.c
+++ b/drivers/cpufreq/speedstep-smi.c
@@ -156,6 +156,7 @@ static void speedstep_set_state(unsigned int state)
 		return;
 
 	/* Disable IRQs */
+	preempt_disable();
 	local_irq_save(flags);
 
 	command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff);
@@ -166,9 +167,19 @@ static void speedstep_set_state(unsigned int state)
 
 	do {
 		if (retry) {
+			/*
+			 * We need to enable interrupts, otherwise the blockage
+			 * won't resolve.
+			 *
+			 * We disable preemption so that other processes don't
+			 * run. If other processes were running, they could
+			 * submit more DMA requests, making the blockage worse.
+			 */
 			pr_debug("retry %u, previous result %u, waiting...\n",
 					retry, result);
+			local_irq_enable();
 			mdelay(retry * 50);
+			local_irq_disable();
 		}
 		retry++;
 		__asm__ __volatile__(
@@ -185,6 +196,7 @@ static void speedstep_set_state(unsigned int state)
 
 	/* enable IRQs */
 	local_irq_restore(flags);
+	preempt_enable();
 
 	if (new_state == state)
 		pr_debug("change to %u MHz succeeded after %u tries "
diff --git a/drivers/cpuidle/cpuidle-mvebu-v7.c b/drivers/cpuidle/cpuidle-mvebu-v7.c
index 45371bb1621..6066d790fd0 100644
--- a/drivers/cpuidle/cpuidle-mvebu-v7.c
+++ b/drivers/cpuidle/cpuidle-mvebu-v7.c
@@ -37,11 +37,11 @@ static int mvebu_v7_enter_idle(struct cpuidle_device *dev,
 		deepidle = true;
 
 	ret = mvebu_v7_cpu_suspend(deepidle);
+	cpu_pm_exit();
+
 	if (ret)
 		return ret;
 
-	cpu_pm_exit();
-
 	return index;
 }
 
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 125150dc6e8..9ab99642ca7 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -297,9 +297,6 @@ int cpuidle_enable_device(struct cpuidle_device *dev)
 	if (!dev->registered)
 		return -EINVAL;
 
-	if (!dev->state_count)
-		dev->state_count = drv->state_count;
-
 	ret = cpuidle_add_device_sysfs(dev);
 	if (ret)
 		return ret;
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 710a233b9b0..386261afe2d 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -178,7 +178,12 @@ static inline int performance_multiplier(unsigned long nr_iowaiters, unsigned lo
 
 	/* for higher loadavg, we are more reluctant */
 
-	mult += 2 * get_loadavg(load);
+	/*
+	 * this doesn't work as intended - it is almost always 0, but can
+	 * sometimes, depending on workload, spike very high into the hundreds
+	 * even when the average cpu load is under 10%.
+	 */
+	/* mult += 2 * get_loadavg(); */
 
 	/* for IO wait tasks (per cpu!) we add 5x each */
 	mult += 10 * nr_iowaiters;
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index 97c5903b460..832a2c3f01f 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -401,7 +401,7 @@ static int cpuidle_add_state_sysfs(struct cpuidle_device *device)
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(device);
 
 	/* state statistics */
-	for (i = 0; i < device->state_count; i++) {
+	for (i = 0; i < drv->state_count; i++) {
 		kobj = kzalloc(sizeof(struct cpuidle_state_kobj), GFP_KERNEL);
 		if (!kobj)
 			goto error_state;
@@ -433,9 +433,10 @@ error_state:
  */
 static void cpuidle_remove_state_sysfs(struct cpuidle_device *device)
 {
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(device);
 	int i;
 
-	for (i = 0; i < device->state_count; i++)
+	for (i = 0; i < drv->state_count; i++)
 		cpuidle_free_state_kobj(device, i);
 }
 
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index f347ab7eea9..08b0da23c4a 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -1543,6 +1543,8 @@ static int ahash_init(struct ahash_request *req)
 
 	state->current_buf = 0;
 	state->buf_dma = 0;
+	state->buflen_0 = 0;
+	state->buflen_1 = 0;
 
 	return 0;
 }
diff --git a/drivers/crypto/caam/caamrng.c b/drivers/crypto/caam/caamrng.c
index ae31e555793..a48dc251b14 100644
--- a/drivers/crypto/caam/caamrng.c
+++ b/drivers/crypto/caam/caamrng.c
@@ -56,7 +56,7 @@
 
 /* Buffer, its dma address and lock */
 struct buf_data {
-	u8 buf[RN_BUF_SIZE];
+	u8 buf[RN_BUF_SIZE] ____cacheline_aligned;
 	dma_addr_t addr;
 	struct completion filled;
 	u32 hw_desc[DESC_JOB_O_LEN];
diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c
index cb98fa54573..f7826ee3754 100644
--- a/drivers/crypto/omap-aes.c
+++ b/drivers/crypto/omap-aes.c
@@ -554,15 +554,23 @@ static int omap_aes_crypt_dma_stop(struct omap_aes_dev *dd)
 	return err;
 }
 
-static int omap_aes_check_aligned(struct scatterlist *sg)
+static int omap_aes_check_aligned(struct scatterlist *sg, int total)
 {
+	int len = 0;
+
 	while (sg) {
 		if (!IS_ALIGNED(sg->offset, 4))
 			return -1;
 		if (!IS_ALIGNED(sg->length, AES_BLOCK_SIZE))
 			return -1;
+
+		len += sg->length;
 		sg = sg_next(sg);
 	}
+
+	if (len != total)
+		return -1;
+
 	return 0;
 }
 
@@ -633,8 +641,8 @@ static int omap_aes_handle_queue(struct omap_aes_dev *dd,
 	dd->in_sg = req->src;
 	dd->out_sg = req->dst;
 
-	if (omap_aes_check_aligned(dd->in_sg) ||
-	    omap_aes_check_aligned(dd->out_sg)) {
+	if (omap_aes_check_aligned(dd->in_sg, dd->total) ||
+	    omap_aes_check_aligned(dd->out_sg, dd->total)) {
 		if (omap_aes_copy_sgs(dd))
 			pr_err("Failed to copy SGs for unaligned cases\n");
 		dd->sgs_copied = 1;
diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c
index 633ba945e15..c178ed8c390 100644
--- a/drivers/crypto/padlock-aes.c
+++ b/drivers/crypto/padlock-aes.c
@@ -563,4 +563,4 @@ MODULE_DESCRIPTION("VIA PadLock AES algorithm support");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Michal Ludvig");
 
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c
index bace885634f..95f7d27ce49 100644
--- a/drivers/crypto/padlock-sha.c
+++ b/drivers/crypto/padlock-sha.c
@@ -593,7 +593,7 @@ MODULE_DESCRIPTION("VIA PadLock SHA1/SHA256 algorithms support.");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Michal Ludvig");
 
-MODULE_ALIAS("sha1-all");
-MODULE_ALIAS("sha256-all");
-MODULE_ALIAS("sha1-padlock");
-MODULE_ALIAS("sha256-padlock");
+MODULE_ALIAS_CRYPTO("sha1-all");
+MODULE_ALIAS_CRYPTO("sha256-all");
+MODULE_ALIAS_CRYPTO("sha1-padlock");
+MODULE_ALIAS_CRYPTO("sha256-padlock");
diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
index 244d73378f0..7ee93f881db 100644
--- a/drivers/crypto/qat/qat_common/adf_ctl_drv.c
+++ b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
@@ -52,6 +52,7 @@
 #include <linux/pci.h>
 #include <linux/cdev.h>
 #include <linux/uaccess.h>
+#include <linux/crypto.h>
 
 #include "adf_accel_devices.h"
 #include "adf_common_drv.h"
@@ -487,4 +488,4 @@ module_exit(adf_unregister_ctl_device_driver);
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Intel");
 MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
-MODULE_ALIAS("intel_qat");
+MODULE_ALIAS_CRYPTO("intel_qat");
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 624b8be0c36..307931528eb 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -927,7 +927,8 @@ static int sg_to_link_tbl(struct scatterlist *sg, int sg_count,
 		sg_count--;
 		link_tbl_ptr--;
 	}
-	be16_add_cpu(&link_tbl_ptr->len, cryptlen);
+	link_tbl_ptr->len = cpu_to_be16(be16_to_cpu(link_tbl_ptr->len)
+					+ cryptlen);
 
 	/* tag end of link table */
 	link_tbl_ptr->j_extent = DESC_PTR_LNKTBL_RETURN;
@@ -2563,6 +2564,7 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev,
 		break;
 	default:
 		dev_err(dev, "unknown algorithm type %d\n", t_alg->algt.type);
+		kfree(t_alg);
 		return ERR_PTR(-EINVAL);
 	}
 
diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c
index 92105f3dc8e..e4cea7c4514 100644
--- a/drivers/crypto/ux500/cryp/cryp_core.c
+++ b/drivers/crypto/ux500/cryp/cryp_core.c
@@ -1810,7 +1810,7 @@ module_exit(ux500_cryp_mod_fini);
 module_param(cryp_mode, int, 0);
 
 MODULE_DESCRIPTION("Driver for ST-Ericsson UX500 CRYP crypto engine.");
-MODULE_ALIAS("aes-all");
-MODULE_ALIAS("des-all");
+MODULE_ALIAS_CRYPTO("aes-all");
+MODULE_ALIAS_CRYPTO("des-all");
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index 1c73f4fbc25..8e5e0187506 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -1995,7 +1995,7 @@ module_exit(ux500_hash_mod_fini);
 MODULE_DESCRIPTION("Driver for ST-Ericsson UX500 HASH engine.");
 MODULE_LICENSE("GPL");
 
-MODULE_ALIAS("sha1-all");
-MODULE_ALIAS("sha256-all");
-MODULE_ALIAS("hmac-sha1-all");
-MODULE_ALIAS("hmac-sha256-all");
+MODULE_ALIAS_CRYPTO("sha1-all");
+MODULE_ALIAS_CRYPTO("sha256-all");
+MODULE_ALIAS_CRYPTO("hmac-sha1-all");
+MODULE_ALIAS_CRYPTO("hmac-sha256-all");
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 30b538d8cc9..ebb53bc548e 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -769,6 +769,11 @@ err_out:
 }
 EXPORT_SYMBOL(devfreq_remove_governor);
 
+int devfreq_update_stats(struct devfreq *df)
+{
+	return df->profile->get_dev_status(df->dev.parent, &df->last_status);
+}
+
 static ssize_t governor_show(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
diff --git a/drivers/devfreq/governor_simpleondemand.c b/drivers/devfreq/governor_simpleondemand.c
index 0720ba84ca9..ae72ba5e78d 100644
--- a/drivers/devfreq/governor_simpleondemand.c
+++ b/drivers/devfreq/governor_simpleondemand.c
@@ -21,17 +21,20 @@
 static int devfreq_simple_ondemand_func(struct devfreq *df,
 					unsigned long *freq)
 {
-	struct devfreq_dev_status stat;
-	int err = df->profile->get_dev_status(df->dev.parent, &stat);
+	int err;
+	struct devfreq_dev_status *stat;
 	unsigned long long a, b;
 	unsigned int dfso_upthreshold = DFSO_UPTHRESHOLD;
 	unsigned int dfso_downdifferential = DFSO_DOWNDIFFERENCTIAL;
 	struct devfreq_simple_ondemand_data *data = df->data;
 	unsigned long max = (df->max_freq) ? df->max_freq : UINT_MAX;
 
+	err = devfreq_update_stats(df);
 	if (err)
 		return err;
 
+	stat = &df->last_status;
+
 	if (data) {
 		if (data->upthreshold)
 			dfso_upthreshold = data->upthreshold;
@@ -43,41 +46,41 @@ static int devfreq_simple_ondemand_func(struct devfreq *df,
 		return -EINVAL;
 
 	/* Assume MAX if it is going to be divided by zero */
-	if (stat.total_time == 0) {
+	if (stat->total_time == 0) {
 		*freq = max;
 		return 0;
 	}
 
 	/* Prevent overflow */
-	if (stat.busy_time >= (1 << 24) || stat.total_time >= (1 << 24)) {
-		stat.busy_time >>= 7;
-		stat.total_time >>= 7;
+	if (stat->busy_time >= (1 << 24) || stat->total_time >= (1 << 24)) {
+		stat->busy_time >>= 7;
+		stat->total_time >>= 7;
 	}
 
 	/* Set MAX if it's busy enough */
-	if (stat.busy_time * 100 >
-	    stat.total_time * dfso_upthreshold) {
+	if (stat->busy_time * 100 >
+	    stat->total_time * dfso_upthreshold) {
 		*freq = max;
 		return 0;
 	}
 
 	/* Set MAX if we do not know the initial frequency */
-	if (stat.current_frequency == 0) {
+	if (stat->current_frequency == 0) {
 		*freq = max;
 		return 0;
 	}
 
 	/* Keep the current frequency */
-	if (stat.busy_time * 100 >
-	    stat.total_time * (dfso_upthreshold - dfso_downdifferential)) {
-		*freq = stat.current_frequency;
+	if (stat->busy_time * 100 >
+	    stat->total_time * (dfso_upthreshold - dfso_downdifferential)) {
+		*freq = stat->current_frequency;
 		return 0;
 	}
 
 	/* Set the desired frequency based on the load */
-	a = stat.busy_time;
-	a *= stat.current_frequency;
-	b = div_u64(a, stat.total_time);
+	a = stat->busy_time;
+	a *= stat->current_frequency;
+	b = div_u64(a, stat->total_time);
 	b *= 100;
 	b = div_u64(b, (dfso_upthreshold - dfso_downdifferential / 2));
 	*freq = (unsigned long) b;
diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c
index 3c97c8fa8d0..8a37af92309 100644
--- a/drivers/dma-buf/reservation.c
+++ b/drivers/dma-buf/reservation.c
@@ -402,8 +402,6 @@ reservation_object_test_signaled_single(struct fence *passed_fence)
 	int ret = 1;
 
 	if (!test_bit(FENCE_FLAG_SIGNALED_BIT, &lfence->flags)) {
-		int ret;
-
 		fence = fence_get_rcu(lfence);
 		if (!fence)
 			return -1;
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index a630161473a..c396e1b69d9 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -25,6 +25,8 @@
 
 #include "internal.h"
 
+#define DRV_NAME	"dw_dmac"
+
 static struct dma_chan *dw_dma_of_xlate(struct of_phandle_args *dma_spec,
 					struct of_dma *ofdma)
 {
@@ -279,7 +281,7 @@ static struct platform_driver dw_driver = {
 	.remove		= dw_remove,
 	.shutdown       = dw_shutdown,
 	.driver = {
-		.name	= "dw_dmac",
+		.name	= DRV_NAME,
 		.pm	= &dw_dev_pm_ops,
 		.of_match_table = of_match_ptr(dw_dma_of_id_table),
 		.acpi_match_table = ACPI_PTR(dw_dma_acpi_id_table),
@@ -300,3 +302,4 @@ module_exit(dw_exit);
 
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller platform driver");
+MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 4cfaaa5a49b..abff66c1843 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -258,6 +258,13 @@ static int edma_terminate_all(struct edma_chan *echan)
 	 */
 	if (echan->edesc) {
 		int cyclic = echan->edesc->cyclic;
+
+		/*
+		 * free the running request descriptor
+		 * since it is not in any of the vdesc lists
+		 */
+		edma_desc_free(&echan->edesc->vdesc);
+
 		echan->edesc = NULL;
 		edma_stop(echan->ch_num);
 		/* Move the cyclic channel back to default queue */
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index a63837ca141..ede8e868016 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -277,7 +277,8 @@ static void mv_xor_slot_cleanup(struct mv_xor_chan *mv_chan)
 	dma_cookie_t cookie = 0;
 	int busy = mv_chan_is_busy(mv_chan);
 	u32 current_desc = mv_chan_get_current_desc(mv_chan);
-	int seen_current = 0;
+	int current_cleaned = 0;
+	struct mv_xor_desc *hw_desc;
 
 	dev_dbg(mv_chan_to_devp(mv_chan), "%s %d\n", __func__, __LINE__);
 	dev_dbg(mv_chan_to_devp(mv_chan), "current_desc %x\n", current_desc);
@@ -289,38 +290,57 @@ static void mv_xor_slot_cleanup(struct mv_xor_chan *mv_chan)
 
 	list_for_each_entry_safe(iter, _iter, &mv_chan->chain,
 					chain_node) {
-		prefetch(_iter);
-		prefetch(&_iter->async_tx);
 
-		/* do not advance past the current descriptor loaded into the
-		 * hardware channel, subsequent descriptors are either in
-		 * process or have not been submitted
-		 */
-		if (seen_current)
-			break;
+		/* clean finished descriptors */
+		hw_desc = iter->hw_desc;
+		if (hw_desc->status & XOR_DESC_SUCCESS) {
+			cookie = mv_xor_run_tx_complete_actions(iter, mv_chan,
+								cookie);
 
-		/* stop the search if we reach the current descriptor and the
-		 * channel is busy
-		 */
-		if (iter->async_tx.phys == current_desc) {
-			seen_current = 1;
-			if (busy)
+			/* done processing desc, clean slot */
+			mv_xor_clean_slot(iter, mv_chan);
+
+			/* break if we did cleaned the current */
+			if (iter->async_tx.phys == current_desc) {
+				current_cleaned = 1;
+				break;
+			}
+		} else {
+			if (iter->async_tx.phys == current_desc) {
+				current_cleaned = 0;
 				break;
+			}
 		}
-
-		cookie = mv_xor_run_tx_complete_actions(iter, mv_chan, cookie);
-
-		if (mv_xor_clean_slot(iter, mv_chan))
-			break;
 	}
 
 	if ((busy == 0) && !list_empty(&mv_chan->chain)) {
-		struct mv_xor_desc_slot *chain_head;
-		chain_head = list_entry(mv_chan->chain.next,
-					struct mv_xor_desc_slot,
-					chain_node);
-
-		mv_xor_start_new_chain(mv_chan, chain_head);
+		if (current_cleaned) {
+			/*
+			 * current descriptor cleaned and removed, run
+			 * from list head
+			 */
+			iter = list_entry(mv_chan->chain.next,
+					  struct mv_xor_desc_slot,
+					  chain_node);
+			mv_xor_start_new_chain(mv_chan, iter);
+		} else {
+			if (!list_is_last(&iter->chain_node, &mv_chan->chain)) {
+				/*
+				 * descriptors are still waiting after
+				 * current, trigger them
+				 */
+				iter = list_entry(iter->chain_node.next,
+						  struct mv_xor_desc_slot,
+						  chain_node);
+				mv_xor_start_new_chain(mv_chan, iter);
+			} else {
+				/*
+				 * some descriptors are still waiting
+				 * to be cleaned
+				 */
+				tasklet_schedule(&mv_chan->irq_tasklet);
+			}
+		}
 	}
 
 	if (cookie > 0)
diff --git a/drivers/dma/mv_xor.h b/drivers/dma/mv_xor.h
index 78edc7e4456..4fa0fe2e2f0 100644
--- a/drivers/dma/mv_xor.h
+++ b/drivers/dma/mv_xor.h
@@ -35,6 +35,7 @@
 #define XOR_OPERATION_MODE_XOR		0
 #define XOR_OPERATION_MODE_MEMCPY	2
 #define XOR_DESCRIPTOR_SWAP		BIT(14)
+#define XOR_DESC_SUCCESS		0x40000000
 
 #define XOR_DESC_DMA_OWNED		BIT(31)
 #define XOR_DESC_EOD_INT_EN		BIT(31)
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index bbea8243f9e..f477f3ba223 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -978,6 +978,7 @@ static int omap_dma_terminate_all(struct omap_chan *c)
 	 * c->desc is NULL and exit.)
 	 */
 	if (c->desc) {
+		omap_dma_desc_free(&c->desc->vd);
 		c->desc = NULL;
 		/* Avoid stopping the dma twice */
 		if (!c->paused)
diff --git a/drivers/dma/sh/shdmac.c b/drivers/dma/sh/shdmac.c
index 58eb85770eb..8a083aa2374 100644
--- a/drivers/dma/sh/shdmac.c
+++ b/drivers/dma/sh/shdmac.c
@@ -443,7 +443,7 @@ static bool sh_dmae_reset(struct sh_dmae_device *shdev)
 	return ret;
 }
 
-#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARM)
+#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE)
 static irqreturn_t sh_dmae_err(int irq, void *data)
 {
 	struct sh_dmae_device *shdev = data;
@@ -689,7 +689,7 @@ static int sh_dmae_probe(struct platform_device *pdev)
 	const struct sh_dmae_pdata *pdata;
 	unsigned long chan_flag[SH_DMAE_MAX_CHANNELS] = {};
 	int chan_irq[SH_DMAE_MAX_CHANNELS];
-#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARM)
+#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE)
 	unsigned long irqflags = 0;
 	int errirq;
 #endif
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index bbd65149cdb..c7236ba92b8 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -2039,14 +2039,20 @@ static void __log_bus_error(struct mem_ctl_info *mci, struct err_info *err,
 
 static inline void decode_bus_error(int node_id, struct mce *m)
 {
-	struct mem_ctl_info *mci = mcis[node_id];
-	struct amd64_pvt *pvt = mci->pvt_info;
+	struct mem_ctl_info *mci;
+	struct amd64_pvt *pvt;
 	u8 ecc_type = (m->status >> 45) & 0x3;
 	u8 xec = XEC(m->status, 0x1f);
 	u16 ec = EC(m->status);
 	u64 sys_addr;
 	struct err_info err;
 
+	mci = edac_mc_find(node_id);
+	if (!mci)
+		return;
+
+	pvt = mci->pvt_info;
+
 	/* Bail out early if this was an 'observed' error */
 	if (PP(ec) == NBSL_PP_OBS)
 		return;
diff --git a/drivers/edac/mce_amd.h b/drivers/edac/mce_amd.h
index 51b7e3a36e3..c2359a1ea6b 100644
--- a/drivers/edac/mce_amd.h
+++ b/drivers/edac/mce_amd.h
@@ -32,9 +32,6 @@
 #define R4(x)				(((x) >> 4) & 0xf)
 #define R4_MSG(x)			((R4(x) < 9) ?  rrrr_msgs[R4(x)] : "Wrong R4!")
 
-#define MCI_STATUS_DEFERRED		BIT_64(44)
-#define MCI_STATUS_POISON		BIT_64(43)
-
 extern const char * const pp_msgs[];
 
 enum tt_ids {
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index e9bb1af67c8..15697c63013 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -135,6 +135,7 @@ static inline int sad_pkg(const struct interleave_pkg *table, u32 reg,
 
 #define TOLM		0x80
 #define	TOHM		0x84
+#define HASWELL_TOLM	0xd0
 #define HASWELL_TOHM_0	0xd4
 #define HASWELL_TOHM_1	0xd8
 
@@ -706,8 +707,8 @@ static u64 haswell_get_tolm(struct sbridge_pvt *pvt)
 {
 	u32 reg;
 
-	pci_read_config_dword(pvt->info.pci_vtd, TOLM, &reg);
-	return (GET_BITFIELD(reg, 26, 31) << 26) | 0x1ffffff;
+	pci_read_config_dword(pvt->info.pci_vtd, HASWELL_TOLM, &reg);
+	return (GET_BITFIELD(reg, 26, 31) << 26) | 0x3ffffff;
 }
 
 static u64 haswell_get_tohm(struct sbridge_pvt *pvt)
@@ -848,7 +849,7 @@ static int get_dimm_config(struct mem_ctl_info *mci)
 	else
 		edac_dbg(0, "Memory is unregistered\n");
 
-	if (mtype == MEM_DDR4 || MEM_RDDR4)
+	if (mtype == MEM_DDR4 || mtype == MEM_RDDR4)
 		banks = 16;
 	else
 		banks = 8;
@@ -909,7 +910,7 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 	u32 reg;
 	u64 limit, prv = 0;
 	u64 tmp_mb;
-	u32 mb, kb;
+	u32 gb, mb;
 	u32 rir_way;
 
 	/*
@@ -919,15 +920,17 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 	pvt->tolm = pvt->info.get_tolm(pvt);
 	tmp_mb = (1 + pvt->tolm) >> 20;
 
-	mb = div_u64_rem(tmp_mb, 1000, &kb);
-	edac_dbg(0, "TOLM: %u.%03u GB (0x%016Lx)\n", mb, kb, (u64)pvt->tolm);
+	gb = div_u64_rem(tmp_mb, 1024, &mb);
+	edac_dbg(0, "TOLM: %u.%03u GB (0x%016Lx)\n",
+		gb, (mb*1000)/1024, (u64)pvt->tolm);
 
 	/* Address range is already 45:25 */
 	pvt->tohm = pvt->info.get_tohm(pvt);
 	tmp_mb = (1 + pvt->tohm) >> 20;
 
-	mb = div_u64_rem(tmp_mb, 1000, &kb);
-	edac_dbg(0, "TOHM: %u.%03u GB (0x%016Lx)\n", mb, kb, (u64)pvt->tohm);
+	gb = div_u64_rem(tmp_mb, 1024, &mb);
+	edac_dbg(0, "TOHM: %u.%03u GB (0x%016Lx)\n",
+		gb, (mb*1000)/1024, (u64)pvt->tohm);
 
 	/*
 	 * Step 2) Get SAD range and SAD Interleave list
@@ -949,11 +952,11 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 			break;
 
 		tmp_mb = (limit + 1) >> 20;
-		mb = div_u64_rem(tmp_mb, 1000, &kb);
+		gb = div_u64_rem(tmp_mb, 1024, &mb);
 		edac_dbg(0, "SAD#%d %s up to %u.%03u GB (0x%016Lx) Interleave: %s reg=0x%08x\n",
 			 n_sads,
 			 get_dram_attr(reg),
-			 mb, kb,
+			 gb, (mb*1000)/1024,
 			 ((u64)tmp_mb) << 20L,
 			 INTERLEAVE_MODE(reg) ? "8:6" : "[8:6]XOR[18:16]",
 			 reg);
@@ -984,9 +987,9 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 			break;
 		tmp_mb = (limit + 1) >> 20;
 
-		mb = div_u64_rem(tmp_mb, 1000, &kb);
+		gb = div_u64_rem(tmp_mb, 1024, &mb);
 		edac_dbg(0, "TAD#%d: up to %u.%03u GB (0x%016Lx), socket interleave %d, memory interleave %d, TGT: %d, %d, %d, %d, reg=0x%08x\n",
-			 n_tads, mb, kb,
+			 n_tads, gb, (mb*1000)/1024,
 			 ((u64)tmp_mb) << 20L,
 			 (u32)TAD_SOCK(reg),
 			 (u32)TAD_CH(reg),
@@ -1009,10 +1012,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 					      tad_ch_nilv_offset[j],
 					      &reg);
 			tmp_mb = TAD_OFFSET(reg) >> 20;
-			mb = div_u64_rem(tmp_mb, 1000, &kb);
+			gb = div_u64_rem(tmp_mb, 1024, &mb);
 			edac_dbg(0, "TAD CH#%d, offset #%d: %u.%03u GB (0x%016Lx), reg=0x%08x\n",
 				 i, j,
-				 mb, kb,
+				 gb, (mb*1000)/1024,
 				 ((u64)tmp_mb) << 20L,
 				 reg);
 		}
@@ -1034,10 +1037,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 
 			tmp_mb = pvt->info.rir_limit(reg) >> 20;
 			rir_way = 1 << RIR_WAY(reg);
-			mb = div_u64_rem(tmp_mb, 1000, &kb);
+			gb = div_u64_rem(tmp_mb, 1024, &mb);
 			edac_dbg(0, "CH#%d RIR#%d, limit: %u.%03u GB (0x%016Lx), way: %d, reg=0x%08x\n",
 				 i, j,
-				 mb, kb,
+				 gb, (mb*1000)/1024,
 				 ((u64)tmp_mb) << 20L,
 				 rir_way,
 				 reg);
@@ -1048,10 +1051,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 						      &reg);
 				tmp_mb = RIR_OFFSET(reg) << 6;
 
-				mb = div_u64_rem(tmp_mb, 1000, &kb);
+				gb = div_u64_rem(tmp_mb, 1024, &mb);
 				edac_dbg(0, "CH#%d RIR#%d INTL#%d, offset %u.%03u GB (0x%016Lx), tgt: %d, reg=0x%08x\n",
 					 i, j, k,
-					 mb, kb,
+					 gb, (mb*1000)/1024,
 					 ((u64)tmp_mb) << 20L,
 					 (u32)RIR_RNK_TGT(reg),
 					 reg);
@@ -1089,7 +1092,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 	u8			ch_way, sck_way, pkg, sad_ha = 0;
 	u32			tad_offset;
 	u32			rir_way;
-	u32			mb, kb;
+	u32			mb, gb;
 	u64			ch_addr, offset, limit = 0, prv = 0;
 
 
@@ -1358,10 +1361,10 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 			continue;
 
 		limit = pvt->info.rir_limit(reg);
-		mb = div_u64_rem(limit >> 20, 1000, &kb);
+		gb = div_u64_rem(limit >> 20, 1024, &mb);
 		edac_dbg(0, "RIR#%d, limit: %u.%03u GB (0x%016Lx), way: %d\n",
 			 n_rir,
-			 mb, kb,
+			 gb, (mb*1000)/1024,
 			 limit,
 			 1 << RIR_WAY(reg));
 		if  (ch_addr <= limit)
@@ -2297,7 +2300,7 @@ static int sbridge_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		rc = sbridge_get_all_devices(&num_mc, pci_dev_descr_ibridge_table);
 		type = IVY_BRIDGE;
 		break;
-	case PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA:
+	case PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0:
 		rc = sbridge_get_all_devices(&num_mc, pci_dev_descr_sbridge_table);
 		type = SANDY_BRIDGE;
 		break;
@@ -2306,8 +2309,11 @@ static int sbridge_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		type = HASWELL;
 		break;
 	}
-	if (unlikely(rc < 0))
+	if (unlikely(rc < 0)) {
+		edac_dbg(0, "couldn't get all devices for 0x%x\n", pdev->device);
 		goto fail0;
+	}
+
 	mc = 0;
 
 	list_for_each_entry(sbridge_dev, &sbridge_edac_list, list) {
@@ -2320,7 +2326,7 @@ static int sbridge_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 			goto fail1;
 	}
 
-	sbridge_printk(KERN_INFO, "Driver loaded.\n");
+	sbridge_printk(KERN_INFO, "%s\n", SBRIDGE_REVISION);
 
 	mutex_unlock(&sbridge_edac_lock);
 	return 0;
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index 41983883cef..38a2203cdf6 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -132,6 +132,25 @@ config ISCSI_IBFT
 	  detect iSCSI boot parameters dynamically during system boot, say Y.
 	  Otherwise, say N.
 
+config ARM_SCPI_PROTOCOL
+	tristate "ARM System Control and Power Interface (SCPI) Message Protocol"
+	depends on ARM_MHU
+	help
+	  System Control and Power Interface (SCPI) Message Protocol is
+	  defined for the purpose of communication between the Application
+	  Cores(AP) and the System Control Processor(SCP). The MHU peripheral
+	  provides a mechanism for inter-processor communication between SCP
+	  and AP.
+
+	  SCP controls most of the power managament on the Application
+	  Processors. It offers control and management of: the core/cluster
+	  power states, various power domain DVFS including the core/cluster,
+	  certain system clocks configuration, thermal sensors and many
+	  others.
+
+	  This protocol library provides interface for all the client drivers
+	  making use of the features offered by the SCP.
+
 source "drivers/firmware/google/Kconfig"
 source "drivers/firmware/efi/Kconfig"
 
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index 5373dc5b601..ee4ffa72584 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -1,6 +1,7 @@
 #
 # Makefile for the linux kernel.
 #
+obj-$(CONFIG_ARM_SCPI_PROTOCOL)	+= arm_scpi.o
 obj-$(CONFIG_DMI)		+= dmi_scan.o
 obj-$(CONFIG_DMI_SYSFS)		+= dmi-sysfs.o
 obj-$(CONFIG_EDD)		+= edd.o
diff --git a/drivers/firmware/arm_scpi.c b/drivers/firmware/arm_scpi.c
new file mode 100644
index 00000000000..71c56c0b513
--- /dev/null
+++ b/drivers/firmware/arm_scpi.c
@@ -0,0 +1,770 @@
+/*
+ * System Control and Power Interface (SCPI) Message Protocol driver
+ *
+ * SCPI Message Protocol is used between the System Control Processor(SCP)
+ * and the Application Processors(AP). The Message Handling Unit(MHU)
+ * provides a mechanism for inter-processor communication between SCP's
+ * Cortex M3 and AP.
+ *
+ * SCP offers control and management of the core/cluster power states,
+ * various power domain DVFS including the core/cluster, certain system
+ * clocks configuration, thermal sensors and many others.
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/bitmap.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/mailbox_client.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/printk.h>
+#include <linux/scpi_protocol.h>
+#include <linux/slab.h>
+#include <linux/sort.h>
+#include <linux/spinlock.h>
+
+#define CMD_ID_SHIFT		0
+#define CMD_ID_MASK		0x7f
+#define CMD_TOKEN_ID_SHIFT	8
+#define CMD_TOKEN_ID_MASK	0xff
+#define CMD_DATA_SIZE_SHIFT	16
+#define CMD_DATA_SIZE_MASK	0x1ff
+#define PACK_SCPI_CMD(cmd_id, tx_sz)			\
+	((((cmd_id) & CMD_ID_MASK) << CMD_ID_SHIFT) |	\
+	(((tx_sz) & CMD_DATA_SIZE_MASK) << CMD_DATA_SIZE_SHIFT))
+#define ADD_SCPI_TOKEN(cmd, token)			\
+	((cmd) |= (((token) & CMD_TOKEN_ID_MASK) << CMD_TOKEN_ID_SHIFT))
+
+#define CMD_SIZE(cmd)	(((cmd) >> CMD_DATA_SIZE_SHIFT) & CMD_DATA_SIZE_MASK)
+#define CMD_UNIQ_MASK	(CMD_TOKEN_ID_MASK << CMD_TOKEN_ID_SHIFT | CMD_ID_MASK)
+#define CMD_XTRACT_UNIQ(cmd)	((cmd) & CMD_UNIQ_MASK)
+
+#define SCPI_SLOT		0
+
+#define MAX_DVFS_DOMAINS	8
+#define MAX_DVFS_OPPS		8
+#define DVFS_LATENCY(hdr)	(le32_to_cpu(hdr) >> 16)
+#define DVFS_OPP_COUNT(hdr)	((le32_to_cpu(hdr) >> 8) & 0xff)
+
+#define PROTOCOL_REV_MINOR_BITS	16
+#define PROTOCOL_REV_MINOR_MASK	((1U << PROTOCOL_REV_MINOR_BITS) - 1)
+#define PROTOCOL_REV_MAJOR(x)	((x) >> PROTOCOL_REV_MINOR_BITS)
+#define PROTOCOL_REV_MINOR(x)	((x) & PROTOCOL_REV_MINOR_MASK)
+
+#define FW_REV_MAJOR_BITS	24
+#define FW_REV_MINOR_BITS	16
+#define FW_REV_PATCH_MASK	((1U << FW_REV_MINOR_BITS) - 1)
+#define FW_REV_MINOR_MASK	((1U << FW_REV_MAJOR_BITS) - 1)
+#define FW_REV_MAJOR(x)		((x) >> FW_REV_MAJOR_BITS)
+#define FW_REV_MINOR(x)		(((x) & FW_REV_MINOR_MASK) >> FW_REV_MINOR_BITS)
+#define FW_REV_PATCH(x)		((x) & FW_REV_PATCH_MASK)
+
+#define MAX_RX_TIMEOUT		(msecs_to_jiffies(20))
+
+enum scpi_error_codes {
+	SCPI_SUCCESS = 0, /* Success */
+	SCPI_ERR_PARAM = 1, /* Invalid parameter(s) */
+	SCPI_ERR_ALIGN = 2, /* Invalid alignment */
+	SCPI_ERR_SIZE = 3, /* Invalid size */
+	SCPI_ERR_HANDLER = 4, /* Invalid handler/callback */
+	SCPI_ERR_ACCESS = 5, /* Invalid access/permission denied */
+	SCPI_ERR_RANGE = 6, /* Value out of range */
+	SCPI_ERR_TIMEOUT = 7, /* Timeout has occurred */
+	SCPI_ERR_NOMEM = 8, /* Invalid memory area or pointer */
+	SCPI_ERR_PWRSTATE = 9, /* Invalid power state */
+	SCPI_ERR_SUPPORT = 10, /* Not supported or disabled */
+	SCPI_ERR_DEVICE = 11, /* Device error */
+	SCPI_ERR_BUSY = 12, /* Device busy */
+	SCPI_ERR_MAX
+};
+
+enum scpi_std_cmd {
+	SCPI_CMD_INVALID		= 0x00,
+	SCPI_CMD_SCPI_READY		= 0x01,
+	SCPI_CMD_SCPI_CAPABILITIES	= 0x02,
+	SCPI_CMD_SET_CSS_PWR_STATE	= 0x03,
+	SCPI_CMD_GET_CSS_PWR_STATE	= 0x04,
+	SCPI_CMD_SET_SYS_PWR_STATE	= 0x05,
+	SCPI_CMD_SET_CPU_TIMER		= 0x06,
+	SCPI_CMD_CANCEL_CPU_TIMER	= 0x07,
+	SCPI_CMD_DVFS_CAPABILITIES	= 0x08,
+	SCPI_CMD_GET_DVFS_INFO		= 0x09,
+	SCPI_CMD_SET_DVFS		= 0x0a,
+	SCPI_CMD_GET_DVFS		= 0x0b,
+	SCPI_CMD_GET_DVFS_STAT		= 0x0c,
+	SCPI_CMD_CLOCK_CAPABILITIES	= 0x0d,
+	SCPI_CMD_GET_CLOCK_INFO		= 0x0e,
+	SCPI_CMD_SET_CLOCK_VALUE	= 0x0f,
+	SCPI_CMD_GET_CLOCK_VALUE	= 0x10,
+	SCPI_CMD_PSU_CAPABILITIES	= 0x11,
+	SCPI_CMD_GET_PSU_INFO		= 0x12,
+	SCPI_CMD_SET_PSU		= 0x13,
+	SCPI_CMD_GET_PSU		= 0x14,
+	SCPI_CMD_SENSOR_CAPABILITIES	= 0x15,
+	SCPI_CMD_SENSOR_INFO		= 0x16,
+	SCPI_CMD_SENSOR_VALUE		= 0x17,
+	SCPI_CMD_SENSOR_CFG_PERIODIC	= 0x18,
+	SCPI_CMD_SENSOR_CFG_BOUNDS	= 0x19,
+	SCPI_CMD_SENSOR_ASYNC_VALUE	= 0x1a,
+	SCPI_CMD_SET_DEVICE_PWR_STATE	= 0x1b,
+	SCPI_CMD_GET_DEVICE_PWR_STATE	= 0x1c,
+	SCPI_CMD_COUNT
+};
+
+struct scpi_xfer {
+	u32 slot; /* has to be first element */
+	u32 cmd;
+	u32 status;
+	const void *tx_buf;
+	void *rx_buf;
+	unsigned int tx_len;
+	unsigned int rx_len;
+	struct list_head node;
+	struct completion done;
+};
+
+struct scpi_chan {
+	struct mbox_client cl;
+	struct mbox_chan *chan;
+	void __iomem *tx_payload;
+	void __iomem *rx_payload;
+	struct list_head rx_pending;
+	struct list_head xfers_list;
+	struct scpi_xfer *xfers;
+	spinlock_t rx_lock; /* locking for the rx pending list */
+	struct mutex xfers_lock;
+	u8 token;
+};
+
+struct scpi_drvinfo {
+	u32 protocol_version;
+	u32 firmware_version;
+	int num_chans;
+	atomic_t next_chan;
+	struct scpi_ops *scpi_ops;
+	struct scpi_chan *channels;
+	struct scpi_dvfs_info *dvfs[MAX_DVFS_DOMAINS];
+};
+
+/*
+ * The SCP firmware only executes in little-endian mode, so any buffers
+ * shared through SCPI should have their contents converted to little-endian
+ */
+struct scpi_shared_mem {
+	__le32 command;
+	__le32 status;
+	u8 payload[0];
+} __packed;
+
+struct scp_capabilities {
+	__le32 protocol_version;
+	__le32 event_version;
+	__le32 platform_version;
+	__le32 commands[4];
+} __packed;
+
+struct clk_get_info {
+	__le16 id;
+	__le16 flags;
+	__le32 min_rate;
+	__le32 max_rate;
+	u8 name[20];
+} __packed;
+
+struct clk_get_value {
+	__le32 rate;
+} __packed;
+
+struct clk_set_value {
+	__le16 id;
+	__le16 reserved;
+	__le32 rate;
+} __packed;
+
+struct dvfs_info {
+	__le32 header;
+	struct {
+		__le32 freq;
+		__le32 m_volt;
+	} opps[MAX_DVFS_OPPS];
+} __packed;
+
+struct dvfs_get {
+	u8 index;
+} __packed;
+
+struct dvfs_set {
+	u8 domain;
+	u8 index;
+} __packed;
+
+struct sensor_capabilities {
+	__le16 sensors;
+} __packed;
+
+struct sensor_info {
+	__le16 id;
+	u8 class;
+	u8 triggers;
+	u8 name[20];
+} __packed;
+
+struct sensor_value {
+	__le32 value;
+} __packed;
+
+static struct scpi_drvinfo *scpi_info;
+
+static int scpi_linux_errmap[SCPI_ERR_MAX] = {
+	/* better than switch case as long as return value is continuous */
+	0, /* SCPI_SUCCESS */
+	-EINVAL, /* SCPI_ERR_PARAM */
+	-ENOEXEC, /* SCPI_ERR_ALIGN */
+	-EMSGSIZE, /* SCPI_ERR_SIZE */
+	-EINVAL, /* SCPI_ERR_HANDLER */
+	-EACCES, /* SCPI_ERR_ACCESS */
+	-ERANGE, /* SCPI_ERR_RANGE */
+	-ETIMEDOUT, /* SCPI_ERR_TIMEOUT */
+	-ENOMEM, /* SCPI_ERR_NOMEM */
+	-EINVAL, /* SCPI_ERR_PWRSTATE */
+	-EOPNOTSUPP, /* SCPI_ERR_SUPPORT */
+	-EIO, /* SCPI_ERR_DEVICE */
+	-EBUSY, /* SCPI_ERR_BUSY */
+};
+
+static inline int scpi_to_linux_errno(int errno)
+{
+	if (errno >= SCPI_SUCCESS && errno < SCPI_ERR_MAX)
+		return scpi_linux_errmap[errno];
+	return -EIO;
+}
+
+static void scpi_process_cmd(struct scpi_chan *ch, u32 cmd)
+{
+	unsigned long flags;
+	struct scpi_xfer *t, *match = NULL;
+
+	spin_lock_irqsave(&ch->rx_lock, flags);
+	if (list_empty(&ch->rx_pending)) {
+		spin_unlock_irqrestore(&ch->rx_lock, flags);
+		return;
+	}
+
+	list_for_each_entry(t, &ch->rx_pending, node)
+		if (CMD_XTRACT_UNIQ(t->cmd) == CMD_XTRACT_UNIQ(cmd)) {
+			list_del(&t->node);
+			match = t;
+			break;
+		}
+	/* check if wait_for_completion is in progress or timed-out */
+	if (match && !completion_done(&match->done)) {
+		struct scpi_shared_mem *mem = ch->rx_payload;
+		unsigned int len = min(match->rx_len, CMD_SIZE(cmd));
+
+		match->status = le32_to_cpu(mem->status);
+		memcpy_fromio(match->rx_buf, mem->payload, len);
+		if (match->rx_len > len)
+			memset(match->rx_buf + len, 0, match->rx_len - len);
+		complete(&match->done);
+	}
+	spin_unlock_irqrestore(&ch->rx_lock, flags);
+}
+
+static void scpi_handle_remote_msg(struct mbox_client *c, void *msg)
+{
+	struct scpi_chan *ch = container_of(c, struct scpi_chan, cl);
+	struct scpi_shared_mem *mem = ch->rx_payload;
+	u32 cmd = le32_to_cpu(mem->command);
+
+	scpi_process_cmd(ch, cmd);
+}
+
+static void scpi_tx_prepare(struct mbox_client *c, void *msg)
+{
+	unsigned long flags;
+	struct scpi_xfer *t = msg;
+	struct scpi_chan *ch = container_of(c, struct scpi_chan, cl);
+	struct scpi_shared_mem *mem = (struct scpi_shared_mem *)ch->tx_payload;
+
+	if (t->tx_buf)
+		memcpy_toio(mem->payload, t->tx_buf, t->tx_len);
+	if (t->rx_buf) {
+		if (!(++ch->token))
+			++ch->token;
+		ADD_SCPI_TOKEN(t->cmd, ch->token);
+		spin_lock_irqsave(&ch->rx_lock, flags);
+		list_add_tail(&t->node, &ch->rx_pending);
+		spin_unlock_irqrestore(&ch->rx_lock, flags);
+	}
+	mem->command = cpu_to_le32(t->cmd);
+}
+
+static struct scpi_xfer *get_scpi_xfer(struct scpi_chan *ch)
+{
+	struct scpi_xfer *t;
+
+	mutex_lock(&ch->xfers_lock);
+	if (list_empty(&ch->xfers_list)) {
+		mutex_unlock(&ch->xfers_lock);
+		return NULL;
+	}
+	t = list_first_entry(&ch->xfers_list, struct scpi_xfer, node);
+	list_del(&t->node);
+	mutex_unlock(&ch->xfers_lock);
+	return t;
+}
+
+static void put_scpi_xfer(struct scpi_xfer *t, struct scpi_chan *ch)
+{
+	mutex_lock(&ch->xfers_lock);
+	list_add_tail(&t->node, &ch->xfers_list);
+	mutex_unlock(&ch->xfers_lock);
+}
+
+static int scpi_send_message(u8 cmd, void *tx_buf, unsigned int tx_len,
+			     void *rx_buf, unsigned int rx_len)
+{
+	int ret;
+	u8 chan;
+	struct scpi_xfer *msg;
+	struct scpi_chan *scpi_chan;
+
+	chan = atomic_inc_return(&scpi_info->next_chan) % scpi_info->num_chans;
+	scpi_chan = scpi_info->channels + chan;
+
+	msg = get_scpi_xfer(scpi_chan);
+	if (!msg)
+		return -ENOMEM;
+
+	msg->slot = BIT(SCPI_SLOT);
+	msg->cmd = PACK_SCPI_CMD(cmd, tx_len);
+	msg->tx_buf = tx_buf;
+	msg->tx_len = tx_len;
+	msg->rx_buf = rx_buf;
+	msg->rx_len = rx_len;
+	init_completion(&msg->done);
+
+	ret = mbox_send_message(scpi_chan->chan, msg);
+	if (ret < 0 || !rx_buf)
+		goto out;
+
+	if (!wait_for_completion_timeout(&msg->done, MAX_RX_TIMEOUT))
+		ret = -ETIMEDOUT;
+	else
+		/* first status word */
+		ret = le32_to_cpu(msg->status);
+out:
+	if (ret < 0 && rx_buf) /* remove entry from the list if timed-out */
+		scpi_process_cmd(scpi_chan, msg->cmd);
+
+	put_scpi_xfer(msg, scpi_chan);
+	/* SCPI error codes > 0, translate them to Linux scale*/
+	return ret > 0 ? scpi_to_linux_errno(ret) : ret;
+}
+
+static u32 scpi_get_version(void)
+{
+	return scpi_info->protocol_version;
+}
+
+static int
+scpi_clk_get_range(u16 clk_id, unsigned long *min, unsigned long *max)
+{
+	int ret;
+	struct clk_get_info clk;
+	__le16 le_clk_id = cpu_to_le16(clk_id);
+
+	ret = scpi_send_message(SCPI_CMD_GET_CLOCK_INFO, &le_clk_id,
+				sizeof(le_clk_id), &clk, sizeof(clk));
+	if (!ret) {
+		*min = le32_to_cpu(clk.min_rate);
+		*max = le32_to_cpu(clk.max_rate);
+	}
+	return ret;
+}
+
+static unsigned long scpi_clk_get_val(u16 clk_id)
+{
+	int ret;
+	struct clk_get_value clk;
+	__le16 le_clk_id = cpu_to_le16(clk_id);
+
+	ret = scpi_send_message(SCPI_CMD_GET_CLOCK_VALUE, &le_clk_id,
+				sizeof(le_clk_id), &clk, sizeof(clk));
+	return ret ? ret : le32_to_cpu(clk.rate);
+}
+
+static int scpi_clk_set_val(u16 clk_id, unsigned long rate)
+{
+	int stat;
+	struct clk_set_value clk = {
+		.id = cpu_to_le16(clk_id),
+		.rate = cpu_to_le32(rate)
+	};
+
+	return scpi_send_message(SCPI_CMD_SET_CLOCK_VALUE, &clk, sizeof(clk),
+				 &stat, sizeof(stat));
+}
+
+static int scpi_dvfs_get_idx(u8 domain)
+{
+	int ret;
+	struct dvfs_get dvfs;
+
+	ret = scpi_send_message(SCPI_CMD_GET_DVFS, &domain, sizeof(domain),
+				&dvfs, sizeof(dvfs));
+	return ret ? ret : dvfs.index;
+}
+
+static int scpi_dvfs_set_idx(u8 domain, u8 index)
+{
+	int stat;
+	struct dvfs_set dvfs = {domain, index};
+
+	return scpi_send_message(SCPI_CMD_SET_DVFS, &dvfs, sizeof(dvfs),
+				 &stat, sizeof(stat));
+}
+
+static int opp_cmp_func(const void *opp1, const void *opp2)
+{
+	const struct scpi_opp *t1 = opp1, *t2 = opp2;
+
+	return t1->freq - t2->freq;
+}
+
+static struct scpi_dvfs_info *scpi_dvfs_get_info(u8 domain)
+{
+	struct scpi_dvfs_info *info;
+	struct scpi_opp *opp;
+	struct dvfs_info buf;
+	int ret, i;
+
+	if (domain >= MAX_DVFS_DOMAINS)
+		return ERR_PTR(-EINVAL);
+
+	if (scpi_info->dvfs[domain])	/* data already populated */
+		return scpi_info->dvfs[domain];
+
+	ret = scpi_send_message(SCPI_CMD_GET_DVFS_INFO, &domain, sizeof(domain),
+				&buf, sizeof(buf));
+
+	if (ret)
+		return ERR_PTR(ret);
+
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return ERR_PTR(-ENOMEM);
+
+	info->count = DVFS_OPP_COUNT(buf.header);
+	info->latency = DVFS_LATENCY(buf.header) * 1000; /* uS to nS */
+
+	info->opps = kcalloc(info->count, sizeof(*opp), GFP_KERNEL);
+	if (!info->opps) {
+		kfree(info);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	for (i = 0, opp = info->opps; i < info->count; i++, opp++) {
+		opp->freq = le32_to_cpu(buf.opps[i].freq);
+		opp->m_volt = le32_to_cpu(buf.opps[i].m_volt);
+	}
+
+	sort(info->opps, info->count, sizeof(*opp), opp_cmp_func, NULL);
+
+	scpi_info->dvfs[domain] = info;
+	return info;
+}
+
+static int scpi_sensor_get_id(char *name)
+{
+	struct sensor_capabilities caps;
+	u16 sensors, sensor_id;
+	int ret;
+
+	ret = scpi_send_message(SCPI_CMD_SENSOR_CAPABILITIES,
+				NULL, 0, &caps, sizeof(caps));
+	if (ret)
+		return ret;
+	sensors = le16_to_cpu(caps.sensors);
+
+	for (sensor_id = 0; sensor_id < sensors; sensor_id++) {
+
+		struct sensor_info info;
+		__le16 le_sensor_id = cpu_to_le16(sensor_id);
+		ret = scpi_send_message(SCPI_CMD_SENSOR_INFO, &le_sensor_id,
+					sizeof(le_sensor_id), &info, sizeof(info));
+		if (ret)
+			return ret;
+
+		if (strcmp(name, info.name) == 0)
+			return sensor_id;
+	}
+
+	return -ENODEV;
+}
+
+static int scpi_sensor_get_value(u16 sensor_id, u32 *value)
+{
+	struct sensor_value val;
+	__le16 le_sensor_id = cpu_to_le16(sensor_id);
+	int ret;
+
+	ret = scpi_send_message(SCPI_CMD_SENSOR_VALUE, &le_sensor_id,
+				sizeof(le_sensor_id), &val, sizeof(val));
+	if (ret == 0)
+		*value = le32_to_cpu(val.value);
+
+	return ret;
+}
+
+static struct scpi_ops scpi_ops = {
+	.get_version = scpi_get_version,
+	.clk_get_range = scpi_clk_get_range,
+	.clk_get_val = scpi_clk_get_val,
+	.clk_set_val = scpi_clk_set_val,
+	.dvfs_get_idx = scpi_dvfs_get_idx,
+	.dvfs_set_idx = scpi_dvfs_set_idx,
+	.dvfs_get_info = scpi_dvfs_get_info,
+	.sensor_get_id = scpi_sensor_get_id,
+	.sensor_get_value = scpi_sensor_get_value,
+};
+
+struct scpi_ops *get_scpi_ops(void)
+{
+	return scpi_info ? scpi_info->scpi_ops : NULL;
+}
+EXPORT_SYMBOL_GPL(get_scpi_ops);
+
+static int scpi_init_versions(struct scpi_drvinfo *info)
+{
+	int ret;
+	struct scp_capabilities caps;
+
+	ret = scpi_send_message(SCPI_CMD_SCPI_CAPABILITIES, NULL, 0,
+				&caps, sizeof(caps));
+	if (!ret) {
+		info->protocol_version = le32_to_cpu(caps.protocol_version);
+		info->firmware_version = le32_to_cpu(caps.platform_version);
+	}
+	return ret;
+}
+
+static ssize_t protocol_version_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct scpi_drvinfo *scpi_info = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d.%d\n",
+		       PROTOCOL_REV_MAJOR(scpi_info->protocol_version),
+		       PROTOCOL_REV_MINOR(scpi_info->protocol_version));
+}
+static DEVICE_ATTR_RO(protocol_version);
+
+static ssize_t firmware_version_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct scpi_drvinfo *scpi_info = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d.%d.%d\n",
+		       FW_REV_MAJOR(scpi_info->firmware_version),
+		       FW_REV_MINOR(scpi_info->firmware_version),
+		       FW_REV_PATCH(scpi_info->firmware_version));
+}
+static DEVICE_ATTR_RO(firmware_version);
+
+static struct attribute *versions_attrs[] = {
+	&dev_attr_firmware_version.attr,
+	&dev_attr_protocol_version.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(versions);
+
+static void
+scpi_free_channels(struct device *dev, struct scpi_chan *pchan, int count)
+{
+	int i;
+
+	for (i = 0; i < count && pchan->chan; i++, pchan++) {
+		mbox_free_channel(pchan->chan);
+		devm_kfree(dev, pchan->xfers);
+		devm_iounmap(dev, pchan->rx_payload);
+	}
+}
+
+static int scpi_remove(struct platform_device *pdev)
+{
+	int i;
+	struct device *dev = &pdev->dev;
+	struct scpi_drvinfo *info = platform_get_drvdata(pdev);
+
+	scpi_info = NULL; /* stop exporting SCPI ops through get_scpi_ops */
+
+	of_platform_depopulate(dev);
+	sysfs_remove_groups(&dev->kobj, versions_groups);
+	scpi_free_channels(dev, info->channels, info->num_chans);
+	platform_set_drvdata(pdev, NULL);
+
+	for (i = 0; i < MAX_DVFS_DOMAINS && info->dvfs[i]; i++) {
+		kfree(info->dvfs[i]->opps);
+		kfree(info->dvfs[i]);
+	}
+	devm_kfree(dev, info->channels);
+	devm_kfree(dev, info);
+
+	return 0;
+}
+
+#define MAX_SCPI_XFERS		10
+static int scpi_alloc_xfer_list(struct device *dev, struct scpi_chan *ch)
+{
+	int i;
+	struct scpi_xfer *xfers;
+
+	xfers = devm_kzalloc(dev, MAX_SCPI_XFERS * sizeof(*xfers), GFP_KERNEL);
+	if (!xfers)
+		return -ENOMEM;
+
+	ch->xfers = xfers;
+	for (i = 0; i < MAX_SCPI_XFERS; i++, xfers++)
+		list_add_tail(&xfers->node, &ch->xfers_list);
+	return 0;
+}
+
+static int scpi_probe(struct platform_device *pdev)
+{
+	int count, idx, ret;
+	struct resource res;
+	struct scpi_chan *scpi_chan;
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+
+	scpi_info = devm_kzalloc(dev, sizeof(*scpi_info), GFP_KERNEL);
+	if (!scpi_info)
+		return -ENOMEM;
+
+	count = of_count_phandle_with_args(np, "mboxes", "#mbox-cells");
+	if (count < 0) {
+		dev_err(dev, "no mboxes property in '%s'\n", np->full_name);
+		return -ENODEV;
+	}
+
+	scpi_chan = devm_kcalloc(dev, count, sizeof(*scpi_chan), GFP_KERNEL);
+	if (!scpi_chan)
+		return -ENOMEM;
+
+	for (idx = 0; idx < count; idx++) {
+		resource_size_t size;
+		struct scpi_chan *pchan = scpi_chan + idx;
+		struct mbox_client *cl = &pchan->cl;
+		struct device_node *shmem = of_parse_phandle(np, "shmem", idx);
+
+		if (of_address_to_resource(shmem, 0, &res)) {
+			dev_err(dev, "failed to get SCPI payload mem resource\n");
+			ret = -EINVAL;
+			goto err;
+		}
+
+		size = resource_size(&res);
+		pchan->rx_payload = devm_ioremap(dev, res.start, size);
+		if (!pchan->rx_payload) {
+			dev_err(dev, "failed to ioremap SCPI payload\n");
+			ret = -EADDRNOTAVAIL;
+			goto err;
+		}
+		pchan->tx_payload = pchan->rx_payload + (size >> 1);
+
+		cl->dev = dev;
+		cl->rx_callback = scpi_handle_remote_msg;
+		cl->tx_prepare = scpi_tx_prepare;
+		cl->tx_block = true;
+		cl->tx_tout = 50;
+		cl->knows_txdone = false; /* controller can ack */
+
+		INIT_LIST_HEAD(&pchan->rx_pending);
+		INIT_LIST_HEAD(&pchan->xfers_list);
+		spin_lock_init(&pchan->rx_lock);
+		mutex_init(&pchan->xfers_lock);
+
+		ret = scpi_alloc_xfer_list(dev, pchan);
+		if (!ret) {
+			pchan->chan = mbox_request_channel(cl, idx);
+			if (!IS_ERR(pchan->chan))
+				continue;
+			ret = PTR_ERR(pchan->chan);
+			if (ret != -EPROBE_DEFER)
+				dev_err(dev, "failed to get channel%d err %d\n",
+					idx, ret);
+		}
+err:
+		scpi_free_channels(dev, scpi_chan, idx);
+		scpi_info = NULL;
+		return ret;
+	}
+
+	scpi_info->channels = scpi_chan;
+	scpi_info->num_chans = count;
+	platform_set_drvdata(pdev, scpi_info);
+
+	ret = scpi_init_versions(scpi_info);
+	if (ret) {
+		dev_err(dev, "incorrect or no SCP firmware found\n");
+		scpi_remove(pdev);
+		return ret;
+	}
+
+	_dev_info(dev, "SCP Protocol %d.%d Firmware %d.%d.%d version\n",
+		  PROTOCOL_REV_MAJOR(scpi_info->protocol_version),
+		  PROTOCOL_REV_MINOR(scpi_info->protocol_version),
+		  FW_REV_MAJOR(scpi_info->firmware_version),
+		  FW_REV_MINOR(scpi_info->firmware_version),
+		  FW_REV_PATCH(scpi_info->firmware_version));
+	scpi_info->scpi_ops = &scpi_ops;
+
+	ret = sysfs_create_groups(&dev->kobj, versions_groups);
+	if (ret)
+		dev_err(dev, "unable to create sysfs version group\n");
+
+	return of_platform_populate(dev->of_node, NULL, NULL, dev);
+}
+
+static const struct of_device_id scpi_of_match[] = {
+	{.compatible = "arm,scpi"},
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, scpi_of_match);
+
+static struct platform_driver scpi_driver = {
+	.driver = {
+		.name = "scpi_protocol",
+		.of_match_table = scpi_of_match,
+	},
+	.probe = scpi_probe,
+	.remove = scpi_remove,
+};
+module_platform_driver(scpi_driver);
+
+MODULE_AUTHOR("Sudeep Holla <sudeep.holla@arm.com>");
+MODULE_DESCRIPTION("ARM SCPI mailbox protocol driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index 17afc51f305..35286fe5282 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -489,6 +489,10 @@ static int __init dmi_present(const u8 *buf)
 	buf += 16;
 
 	if (memcmp(buf, "_DMI_", 5) == 0 && dmi_checksum(buf, 15)) {
+		if (smbios_ver)
+			dmi_ver = smbios_ver;
+		else
+			dmi_ver = (buf[14] & 0xF0) << 4 | (buf[14] & 0x0F);
 		dmi_num = (buf[13] << 8) | buf[12];
 		dmi_len = (buf[7] << 8) | buf[6];
 		dmi_base = (buf[11] << 24) | (buf[10] << 16) |
@@ -496,12 +500,9 @@ static int __init dmi_present(const u8 *buf)
 
 		if (dmi_walk_early(dmi_decode) == 0) {
 			if (smbios_ver) {
-				dmi_ver = smbios_ver;
 				pr_info("SMBIOS %d.%d present.\n",
 				       dmi_ver >> 8, dmi_ver & 0xFF);
 			} else {
-				dmi_ver = (buf[14] & 0xF0) << 4 |
-					   (buf[14] & 0x0F);
 				pr_info("Legacy DMI %d.%d present.\n",
 				       dmi_ver >> 8, dmi_ver & 0xFF);
 			}
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index a920fec8fe8..5186eb01945 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -170,12 +170,12 @@ again:
 		start = desc->phys_addr;
 		end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT);
 
-		if ((start + size) > end || (start + size) > max)
-			continue;
-
-		if (end - size > max)
+		if (end > max)
 			end = max;
 
+		if ((start + size) > end)
+			continue;
+
 		if (round_down(end - size, align) < start)
 			continue;
 
diff --git a/drivers/firmware/efi/runtime-map.c b/drivers/firmware/efi/runtime-map.c
index 018c29a2661..87b8e3b900d 100644
--- a/drivers/firmware/efi/runtime-map.c
+++ b/drivers/firmware/efi/runtime-map.c
@@ -191,7 +191,7 @@ int __init efi_runtime_map_init(struct kobject *efi_kobj)
 
 	return 0;
 out_add_entry:
-	for (j = i - 1; j > 0; j--) {
+	for (j = i - 1; j >= 0; j--) {
 		entry = *(map_entries + j);
 		kobject_put(&entry->kobj);
 	}
diff --git a/drivers/gator/COPYING b/drivers/gator/COPYING
new file mode 100644
index 00000000000..d159169d105
--- /dev/null
+++ b/drivers/gator/COPYING
@@ -0,0 +1,339 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users.  This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it.  (Some other Free Software Foundation software is covered by
+the GNU Lesser General Public License instead.)  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must show them these terms so they know their
+rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary.  To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                    GNU GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License.  The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language.  (Hereinafter, translation is included without limitation in
+the term "modification".)  Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+  1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+  2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) You must cause the modified files to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in
+    whole or in part contains or is derived from the Program or any
+    part thereof, to be licensed as a whole at no charge to all third
+    parties under the terms of this License.
+
+    c) If the modified program normally reads commands interactively
+    when run, you must cause it, when started running for such
+    interactive use in the most ordinary way, to print or display an
+    announcement including an appropriate copyright notice and a
+    notice that there is no warranty (or else, saying that you provide
+    a warranty) and that users may redistribute the program under
+    these conditions, and telling the user how to view a copy of this
+    License.  (Exception: if the Program itself is interactive but
+    does not normally print such an announcement, your work based on
+    the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+    a) Accompany it with the complete corresponding machine-readable
+    source code, which must be distributed under the terms of Sections
+    1 and 2 above on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three
+    years, to give any third party, for a charge no more than your
+    cost of physically performing source distribution, a complete
+    machine-readable copy of the corresponding source code, to be
+    distributed under the terms of Sections 1 and 2 above on a medium
+    customarily used for software interchange; or,
+
+    c) Accompany it with the information you received as to the offer
+    to distribute corresponding source code.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form with such
+    an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it.  For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable.  However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License.  Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+  5. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Program or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+  6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded.  In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+  9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+  10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this.  Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+                            NO WARRANTY
+
+  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License along
+    with this program; if not, write to the Free Software Foundation, Inc.,
+    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+    Gnomovision version 69, Copyright (C) year name of author
+    Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+  `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+  <signature of Ty Coon>, 1 April 1989
+  Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs.  If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.
diff --git a/drivers/gator/Kconfig b/drivers/gator/Kconfig
new file mode 100644
index 00000000000..a9503a9a4e9
--- /dev/null
+++ b/drivers/gator/Kconfig
@@ -0,0 +1,38 @@
+config GATOR
+	tristate "Gator module for ARM's Streamline Performance Analyzer"
+	default m if (ARM || ARM64)
+	depends on PROFILING
+	depends on HIGH_RES_TIMERS
+	depends on PERF_EVENTS
+	depends on HW_PERF_EVENTS || !(ARM || ARM64)
+	select TRACING
+	help
+	  Gator module for ARM's Streamline Performance Analyzer
+
+config GATOR_WITH_MALI_SUPPORT
+	bool
+
+choice
+	prompt "Enable Mali GPU support in Gator"
+	depends on GATOR
+	optional
+	help
+	  Enable Mali GPU support in Gator
+
+config GATOR_MALI_4XXMP
+	bool "Mali-400MP or Mali-450MP"
+	select GATOR_WITH_MALI_SUPPORT
+
+config GATOR_MALI_MIDGARD
+	bool "Mali-T60x, Mali-T62x, Mali-T72x or Mali-T76x"
+	select GATOR_WITH_MALI_SUPPORT
+
+endchoice
+
+config GATOR_MALI_PATH
+	string "Path to Mali driver"
+	depends on GATOR_WITH_MALI_SUPPORT
+	default "drivers/gpu/arm/mali400mp"
+	help
+	  The gator code adds this to its include path so it can get the Mali
+	  trace headers with: #include "linux/mali_linux_trace.h"
diff --git a/drivers/gator/Makefile b/drivers/gator/Makefile
new file mode 100644
index 00000000000..4f97237cb1e
--- /dev/null
+++ b/drivers/gator/Makefile
@@ -0,0 +1,95 @@
+ifneq ($(KERNELRELEASE),)
+
+# Uncomment the following line to enable kernel stack unwinding within gator, or update gator_backtrace.c
+# EXTRA_CFLAGS +=	-DGATOR_KERNEL_STACK_UNWINDING
+
+CONFIG_GATOR ?= m
+obj-$(CONFIG_GATOR) := gator.o
+
+gator-y :=	gator_main.o \
+		gator_events_block.o \
+		gator_events_irq.o \
+		gator_events_meminfo.o \
+		gator_events_mmapped.o \
+		gator_events_net.o \
+		gator_events_perf_pmu.o \
+		gator_events_sched.o \
+
+# Convert the old GATOR_WITH_MALI_SUPPORT to the new kernel flags
+ifneq ($(GATOR_WITH_MALI_SUPPORT),)
+  CONFIG_GATOR_WITH_MALI_SUPPORT := y
+  ifeq ($(GATOR_WITH_MALI_SUPPORT),MALI_MIDGARD)
+    CONFIG_GATOR_MALI_4XXMP := n
+    CONFIG_GATOR_MALI_MIDGARD := y
+  else
+    CONFIG_GATOR_MALI_4XXMP := y
+    CONFIG_GATOR_MALI_MIDGARD := n
+  endif
+  EXTRA_CFLAGS += -DMALI_SUPPORT=$(GATOR_WITH_MALI_SUPPORT)
+  ifneq ($(GATOR_MALI_INTERFACE_STYLE),)
+    EXTRA_CFLAGS += -DGATOR_MALI_INTERFACE_STYLE=$(GATOR_MALI_INTERFACE_STYLE)
+  endif
+endif
+
+ifeq ($(CONFIG_GATOR_WITH_MALI_SUPPORT),y)
+  ifeq ($(CONFIG_GATOR_MALI_MIDGARD),y)
+    gator-y +=	gator_events_mali_midgard.o \
+		gator_events_mali_midgard_hw.o
+    include $(src)/mali_midgard.mk
+  else
+    gator-y +=	gator_events_mali_4xx.o
+  endif
+  gator-y +=	gator_events_mali_common.o
+
+  ifneq ($(CONFIG_GATOR_MALI_PATH),)
+    ccflags-y += -I$(CONFIG_GATOR_MALI_PATH)
+  endif
+  ccflags-$(CONFIG_GATOR_MALI_4XXMP) += -DMALI_SUPPORT=MALI_4xx
+  ccflags-$(CONFIG_GATOR_MALI_MIDGARD) += -DMALI_SUPPORT=MALI_MIDGARD
+endif
+
+# GATOR_TEST controls whether to include (=1) or exclude (=0) test code.
+GATOR_TEST ?= 0
+EXTRA_CFLAGS +=	-DGATOR_TEST=$(GATOR_TEST)
+
+# Should the original or new block_rq_complete API be used?
+OLD_BLOCK_RQ_COMPLETE := $(shell grep -A3 block_rq_complete $(srctree)/include/trace/events/block.h | grep nr_bytes -q; echo $$?)
+EXTRA_CFLAGS += -DOLD_BLOCK_RQ_COMPLETE=$(OLD_BLOCK_RQ_COMPLETE)
+
+gator-$(CONFIG_ARM) +=	gator_events_armv6.o \
+			gator_events_armv7.o \
+			gator_events_l2c-310.o \
+			gator_events_scorpion.o
+
+gator-$(CONFIG_ARM64) +=
+
+$(obj)/gator_main.o: $(obj)/gator_src_md5.h
+
+clean-files := gator_src_md5.h
+
+# Note, in the recipe below we use "cd $(srctree) && cd $(src)" rather than
+# "cd $(srctree)/$(src)" because under DKMS $(src) is an absolute path, and we
+# can't just use $(src) because for normal kernel builds this is relative to
+# $(srctree)
+
+       chk_events.h = :
+ quiet_chk_events.h = echo '  CHK     $@'
+silent_chk_events.h = :
+$(obj)/gator_src_md5.h: FORCE
+	@$($(quiet)chk_events.h)
+	$(Q)cd $(srctree) && cd $(src) ; $(CONFIG_SHELL) -c "echo 'static char *gator_src_md5 = \"'\`ls *.c *.h mali/*.h | grep -Ev '^(gator_src_md5\.h|gator\.mod\.c)$$' | LC_ALL=C sort | xargs cat | md5sum | cut -b 1-32\`'\";'" > $(abspath $@)
+
+else
+
+all:
+	@echo
+	@echo "usage:"
+	@echo "      make -C <kernel_build_dir> M=\`pwd\` ARCH=arm CROSS_COMPILE=<...> modules"
+	@echo
+	$(error)
+
+clean:
+	rm -f *.o .*.cmd gator_src_md5.h modules.order Module.symvers gator.ko gator.mod.c
+	rm -rf .tmp_versions
+
+endif
diff --git a/drivers/gator/gator.h b/drivers/gator/gator.h
new file mode 100644
index 00000000000..50b0180fa82
--- /dev/null
+++ b/drivers/gator/gator.h
@@ -0,0 +1,159 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef GATOR_H_
+#define GATOR_H_
+
+#include <linux/version.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/list.h>
+
+#define GATOR_PERF_SUPPORT      (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 0, 0))
+#define GATOR_PERF_PMU_SUPPORT  (GATOR_PERF_SUPPORT && defined(CONFIG_PERF_EVENTS) && (!(defined(__arm__) || defined(__aarch64__)) || defined(CONFIG_HW_PERF_EVENTS)))
+#define GATOR_NO_PERF_SUPPORT   (!(GATOR_PERF_SUPPORT))
+#define GATOR_CPU_FREQ_SUPPORT  ((LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 38)) && defined(CONFIG_CPU_FREQ))
+#define GATOR_IKS_SUPPORT       defined(CONFIG_BL_SWITCHER)
+
+/* cpu ids */
+#define ARM1136      0x41b36
+#define ARM1156      0x41b56
+#define ARM1176      0x41b76
+#define ARM11MPCORE  0x41b02
+#define CORTEX_A5    0x41c05
+#define CORTEX_A7    0x41c07
+#define CORTEX_A8    0x41c08
+#define CORTEX_A9    0x41c09
+#define CORTEX_A15   0x41c0f
+#define CORTEX_A12   0x41c0d
+#define CORTEX_A17   0x41c0e
+#define SCORPION     0x5100f
+#define SCORPIONMP   0x5102d
+#define KRAITSIM     0x51049
+#define KRAIT        0x5104d
+#define KRAIT_S4_PRO 0x5106f
+#define CORTEX_A53   0x41d03
+#define CORTEX_A57   0x41d07
+#define CORTEX_A72   0x41d08
+#define OTHER        0xfffff
+
+/* gpu enums */
+#define MALI_4xx     1
+#define MALI_MIDGARD 2
+
+#define MAXSIZE_CORE_NAME 32
+
+struct gator_cpu {
+	const int cpuid;
+	/* Human readable name */
+	const char core_name[MAXSIZE_CORE_NAME];
+	/* gatorfs event and Perf PMU name */
+	const char *const pmnc_name;
+	/* compatible from Documentation/devicetree/bindings/arm/cpus.txt */
+	const char *const dt_name;
+	const int pmnc_counters;
+};
+
+const struct gator_cpu *gator_find_cpu_by_cpuid(const u32 cpuid);
+const struct gator_cpu *gator_find_cpu_by_pmu_name(const char *const name);
+
+/******************************************************************************
+ * Filesystem
+ ******************************************************************************/
+struct dentry *gatorfs_mkdir(struct super_block *sb, struct dentry *root,
+			     char const *name);
+
+int gatorfs_create_ulong(struct super_block *sb, struct dentry *root,
+			 char const *name, unsigned long *val);
+
+int gatorfs_create_ro_ulong(struct super_block *sb, struct dentry *root,
+			    char const *name, unsigned long *val);
+
+/******************************************************************************
+ * Tracepoints
+ ******************************************************************************/
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)
+#	error Kernels prior to 3.4.0 not supported. DS-5 v5.21 and earlier supported 2.6.32 and later.
+#elif LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 35)
+#	define GATOR_DEFINE_PROBE(probe_name, proto) \
+		static void probe_##probe_name(PARAMS(proto))
+#	define GATOR_REGISTER_TRACE(probe_name) \
+		register_trace_##probe_name(probe_##probe_name)
+#	define GATOR_UNREGISTER_TRACE(probe_name) \
+		unregister_trace_##probe_name(probe_##probe_name)
+#elif LINUX_VERSION_CODE < KERNEL_VERSION(3, 15, 0)
+#	define GATOR_DEFINE_PROBE(probe_name, proto) \
+		static void probe_##probe_name(void *data, PARAMS(proto))
+#	define GATOR_REGISTER_TRACE(probe_name) \
+		register_trace_##probe_name(probe_##probe_name, NULL)
+#	define GATOR_UNREGISTER_TRACE(probe_name) \
+		unregister_trace_##probe_name(probe_##probe_name, NULL)
+#else
+#	define GATOR_DEFINE_PROBE(probe_name, proto) \
+		extern struct tracepoint *gator_tracepoint_##probe_name; \
+		static void probe_##probe_name(void *data, PARAMS(proto))
+#	define GATOR_REGISTER_TRACE(probe_name) \
+		((gator_tracepoint_##probe_name == NULL) || tracepoint_probe_register(gator_tracepoint_##probe_name, probe_##probe_name, NULL))
+#	define GATOR_UNREGISTER_TRACE(probe_name) \
+		tracepoint_probe_unregister(gator_tracepoint_##probe_name, probe_##probe_name, NULL)
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+#define setup_deferrable_timer_on_stack setup_timer
+#endif
+
+/******************************************************************************
+ * Events
+ ******************************************************************************/
+struct gator_interface {
+	const char *const name;
+	/* Complementary function to init */
+	void (*shutdown)(void);
+	int (*create_files)(struct super_block *sb, struct dentry *root);
+	int (*start)(void);
+	/* Complementary function to start */
+	void (*stop)(void);
+	int (*online)(int **buffer, bool migrate);
+	int (*offline)(int **buffer, bool migrate);
+	/* called in process context but may not be running on core 'cpu' */
+	void (*online_dispatch)(int cpu, bool migrate);
+	/* called in process context but may not be running on core 'cpu' */
+	void (*offline_dispatch)(int cpu, bool migrate);
+	int (*read)(int **buffer, bool sched_switch);
+	int (*read64)(long long **buffer, bool sched_switch);
+	int (*read_proc)(long long **buffer, struct task_struct *);
+	struct list_head list;
+};
+
+u64 gator_get_time(void);
+int gator_events_install(struct gator_interface *interface);
+int gator_events_get_key(void);
+u32 gator_cpuid(void);
+
+void gator_backtrace_handler(struct pt_regs *const regs);
+
+void gator_marshal_activity_switch(int core, int key, int activity, int pid);
+
+#if !GATOR_IKS_SUPPORT
+
+#define get_physical_cpu() smp_processor_id()
+#define lcpu_to_pcpu(lcpu) lcpu
+#define pcpu_to_lcpu(pcpu) pcpu
+
+#else
+
+#define get_physical_cpu() lcpu_to_pcpu(get_logical_cpu())
+int lcpu_to_pcpu(const int lcpu);
+int pcpu_to_lcpu(const int pcpu);
+
+#endif
+
+#define get_logical_cpu() smp_processor_id()
+#define on_primary_core() (get_logical_cpu() == 0)
+
+#endif /* GATOR_H_ */
diff --git a/drivers/gator/gator_annotate.c b/drivers/gator/gator_annotate.c
new file mode 100644
index 00000000000..cc9ae02e5fb
--- /dev/null
+++ b/drivers/gator/gator_annotate.c
@@ -0,0 +1,189 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/uaccess.h>
+#include <asm/current.h>
+#include <linux/spinlock.h>
+
+static DEFINE_SPINLOCK(annotate_lock);
+static bool collect_annotations;
+
+static int annotate_copy(struct file *file, char const __user *buf, size_t count)
+{
+	int cpu = 0;
+	int write = per_cpu(gator_buffer_write, cpu)[ANNOTATE_BUF];
+
+	if (file == NULL) {
+		/* copy from kernel */
+		memcpy(&per_cpu(gator_buffer, cpu)[ANNOTATE_BUF][write], buf, count);
+	} else {
+		/* copy from user space */
+		if (copy_from_user(&per_cpu(gator_buffer, cpu)[ANNOTATE_BUF][write], buf, count) != 0)
+			return -1;
+	}
+	per_cpu(gator_buffer_write, cpu)[ANNOTATE_BUF] = (write + count) & gator_buffer_mask[ANNOTATE_BUF];
+
+	return 0;
+}
+
+static ssize_t annotate_write(struct file *file, char const __user *buf, size_t count_orig, loff_t *offset)
+{
+	int pid, cpu, header_size, available, contiguous, length1, length2, size, count = count_orig & 0x7fffffff;
+	bool interrupt_context;
+
+	if (*offset)
+		return -EINVAL;
+
+	interrupt_context = in_interrupt();
+	/* Annotations are not supported in interrupt context, but may work
+	 * if you comment out the the next four lines of code. By doing so,
+	 * annotations in interrupt context can result in deadlocks and lost
+	 * data.
+	 */
+	if (interrupt_context) {
+		pr_warning("gator: Annotations are not supported in interrupt context. Edit gator_annotate.c in the gator driver to enable annotations in interrupt context.\n");
+		return -EINVAL;
+	}
+
+ retry:
+	/* synchronize between cores and with collect_annotations */
+	spin_lock(&annotate_lock);
+
+	if (!collect_annotations) {
+		/* Not collecting annotations, tell the caller everything was written */
+		size = count_orig;
+		goto annotate_write_out;
+	}
+
+	/* Annotation only uses a single per-cpu buffer as the data must be in order to the engine */
+	cpu = 0;
+
+	if (current == NULL)
+		pid = 0;
+	else
+		pid = current->pid;
+
+	/* determine total size of the payload */
+	header_size = MAXSIZE_PACK32 * 3 + MAXSIZE_PACK64;
+	available = buffer_bytes_available(cpu, ANNOTATE_BUF) - header_size;
+	size = count < available ? count : available;
+
+	if (size <= 0) {
+		/* Buffer is full, wait until space is available */
+		spin_unlock(&annotate_lock);
+
+		/* Drop the annotation as blocking is not allowed in interrupt context */
+		if (interrupt_context)
+			return -EINVAL;
+
+		wait_event_interruptible(gator_annotate_wait, buffer_bytes_available(cpu, ANNOTATE_BUF) > header_size || !collect_annotations);
+
+		/* Check to see if a signal is pending */
+		if (signal_pending(current))
+			return -EINTR;
+
+		goto retry;
+	}
+
+	/* synchronize shared variables annotateBuf and annotatePos */
+	if (per_cpu(gator_buffer, cpu)[ANNOTATE_BUF]) {
+		u64 time = gator_get_time();
+
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, get_physical_cpu());
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, pid);
+		gator_buffer_write_packed_int64(cpu, ANNOTATE_BUF, time);
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, size);
+
+		/* determine the sizes to capture, length1 + length2 will equal size */
+		contiguous = contiguous_space_available(cpu, ANNOTATE_BUF);
+		if (size < contiguous) {
+			length1 = size;
+			length2 = 0;
+		} else {
+			length1 = contiguous;
+			length2 = size - contiguous;
+		}
+
+		if (annotate_copy(file, buf, length1) != 0) {
+			size = -EINVAL;
+			goto annotate_write_out;
+		}
+
+		if (length2 > 0 && annotate_copy(file, &buf[length1], length2) != 0) {
+			size = -EINVAL;
+			goto annotate_write_out;
+		}
+
+		/* Check and commit; commit is set to occur once buffer is 3/4 full */
+		buffer_check(cpu, ANNOTATE_BUF, time);
+	}
+
+annotate_write_out:
+	spin_unlock(&annotate_lock);
+
+	/* return the number of bytes written */
+	return size;
+}
+
+#include "gator_annotate_kernel.c"
+
+static int annotate_release(struct inode *inode, struct file *file)
+{
+	int cpu = 0;
+
+	/* synchronize between cores */
+	spin_lock(&annotate_lock);
+
+	if (per_cpu(gator_buffer, cpu)[ANNOTATE_BUF] && buffer_check_space(cpu, ANNOTATE_BUF, MAXSIZE_PACK64 + 3 * MAXSIZE_PACK32)) {
+		uint32_t pid = current->pid;
+
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, get_physical_cpu());
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, pid);
+		/* time */
+		gator_buffer_write_packed_int64(cpu, ANNOTATE_BUF, 0);
+		/* size */
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, 0);
+	}
+
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, ANNOTATE_BUF, gator_get_time());
+
+	spin_unlock(&annotate_lock);
+
+	return 0;
+}
+
+static const struct file_operations annotate_fops = {
+	.write = annotate_write,
+	.release = annotate_release
+};
+
+static int gator_annotate_create_files(struct super_block *sb, struct dentry *root)
+{
+	return gatorfs_create_file_perm(sb, root, "annotate", &annotate_fops, 0666);
+}
+
+static int gator_annotate_start(void)
+{
+	collect_annotations = true;
+	return 0;
+}
+
+static void gator_annotate_stop(void)
+{
+	/* the spinlock here will ensure that when this function exits, we are not in the middle of an annotation */
+	spin_lock(&annotate_lock);
+	collect_annotations = false;
+	wake_up(&gator_annotate_wait);
+	spin_unlock(&annotate_lock);
+}
diff --git a/drivers/gator/gator_annotate_kernel.c b/drivers/gator/gator_annotate_kernel.c
new file mode 100644
index 00000000000..54e8e86e34c
--- /dev/null
+++ b/drivers/gator/gator_annotate_kernel.c
@@ -0,0 +1,200 @@
+/**
+ * Copyright (C) ARM Limited 2012-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#define ESCAPE_CODE 0x1c
+#define STRING_ANNOTATION 0x06
+#define NAME_CHANNEL_ANNOTATION 0x07
+#define NAME_GROUP_ANNOTATION 0x08
+#define VISUAL_ANNOTATION 0x04
+#define MARKER_ANNOTATION 0x05
+
+static void kannotate_write(const char *ptr, unsigned int size)
+{
+	int retval;
+	int pos = 0;
+	loff_t offset = 0;
+
+	while (pos < size) {
+		retval = annotate_write(NULL, &ptr[pos], size - pos, &offset);
+		if (retval < 0) {
+			pr_warning("gator: kannotate_write failed with return value %d\n", retval);
+			return;
+		}
+		pos += retval;
+	}
+}
+
+static void marshal_u16(char *buf, u16 val)
+{
+	buf[0] = val & 0xff;
+	buf[1] = (val >> 8) & 0xff;
+}
+
+static void marshal_u32(char *buf, u32 val)
+{
+	buf[0] = val & 0xff;
+	buf[1] = (val >> 8) & 0xff;
+	buf[2] = (val >> 16) & 0xff;
+	buf[3] = (val >> 24) & 0xff;
+}
+
+void gator_annotate_channel(int channel, const char *str)
+{
+	const u16 str_size = strlen(str) & 0xffff;
+	char header[8];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = STRING_ANNOTATION;
+	marshal_u32(header + 2, channel);
+	marshal_u16(header + 6, str_size);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size);
+}
+EXPORT_SYMBOL(gator_annotate_channel);
+
+void gator_annotate(const char *str)
+{
+	gator_annotate_channel(0, str);
+}
+EXPORT_SYMBOL(gator_annotate);
+
+void gator_annotate_channel_color(int channel, int color, const char *str)
+{
+	const u16 str_size = (strlen(str) + 4) & 0xffff;
+	char header[12];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = STRING_ANNOTATION;
+	marshal_u32(header + 2, channel);
+	marshal_u16(header + 6, str_size);
+	marshal_u32(header + 8, color);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size - 4);
+}
+EXPORT_SYMBOL(gator_annotate_channel_color);
+
+void gator_annotate_color(int color, const char *str)
+{
+	gator_annotate_channel_color(0, color, str);
+}
+EXPORT_SYMBOL(gator_annotate_color);
+
+void gator_annotate_channel_end(int channel)
+{
+	char header[8];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = STRING_ANNOTATION;
+	marshal_u32(header + 2, channel);
+	marshal_u16(header + 6, 0);
+	kannotate_write(header, sizeof(header));
+}
+EXPORT_SYMBOL(gator_annotate_channel_end);
+
+void gator_annotate_end(void)
+{
+	gator_annotate_channel_end(0);
+}
+EXPORT_SYMBOL(gator_annotate_end);
+
+void gator_annotate_name_channel(int channel, int group, const char *str)
+{
+	const u16 str_size = strlen(str) & 0xffff;
+	char header[12];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = NAME_CHANNEL_ANNOTATION;
+	marshal_u32(header + 2, channel);
+	marshal_u32(header + 6, group);
+	marshal_u16(header + 10, str_size);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size);
+}
+EXPORT_SYMBOL(gator_annotate_name_channel);
+
+void gator_annotate_name_group(int group, const char *str)
+{
+	const u16 str_size = strlen(str) & 0xffff;
+	char header[8];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = NAME_GROUP_ANNOTATION;
+	marshal_u32(header + 2, group);
+	marshal_u16(header + 6, str_size);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size);
+}
+EXPORT_SYMBOL(gator_annotate_name_group);
+
+void gator_annotate_visual(const char *data, unsigned int length, const char *str)
+{
+	const u16 str_size = strlen(str) & 0xffff;
+	char header[4];
+	char header_length[4];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = VISUAL_ANNOTATION;
+	marshal_u16(header + 2, str_size);
+	marshal_u32(header_length, length);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size);
+	kannotate_write(header_length, sizeof(header_length));
+	kannotate_write(data, length);
+}
+EXPORT_SYMBOL(gator_annotate_visual);
+
+void gator_annotate_marker(void)
+{
+	char header[4];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = MARKER_ANNOTATION;
+	marshal_u16(header + 2, 0);
+	kannotate_write(header, sizeof(header));
+}
+EXPORT_SYMBOL(gator_annotate_marker);
+
+void gator_annotate_marker_str(const char *str)
+{
+	const u16 str_size = strlen(str) & 0xffff;
+	char header[4];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = MARKER_ANNOTATION;
+	marshal_u16(header + 2, str_size);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size);
+}
+EXPORT_SYMBOL(gator_annotate_marker_str);
+
+void gator_annotate_marker_color(int color)
+{
+	char header[8];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = MARKER_ANNOTATION;
+	marshal_u16(header + 2, 4);
+	marshal_u32(header + 4, color);
+	kannotate_write(header, sizeof(header));
+}
+EXPORT_SYMBOL(gator_annotate_marker_color);
+
+void gator_annotate_marker_color_str(int color, const char *str)
+{
+	const u16 str_size = (strlen(str) + 4) & 0xffff;
+	char header[8];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = MARKER_ANNOTATION;
+	marshal_u16(header + 2, str_size);
+	marshal_u32(header + 4, color);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size - 4);
+}
+EXPORT_SYMBOL(gator_annotate_marker_color_str);
diff --git a/drivers/gator/gator_backtrace.c b/drivers/gator/gator_backtrace.c
new file mode 100644
index 00000000000..5557ec0b29c
--- /dev/null
+++ b/drivers/gator/gator_backtrace.c
@@ -0,0 +1,208 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/*
+ * EABI backtrace stores {fp,lr} on the stack.
+ */
+struct stack_frame_eabi {
+	union {
+		struct {
+			unsigned long fp;
+			/* May be the fp in the case of a leaf function or clang */
+			unsigned long lr;
+			/* If lr is really the fp, lr2 is the corresponding lr */
+			unsigned long lr2;
+		};
+		/* Used to read 32 bit fp/lr from a 64 bit kernel */
+		struct {
+			u32 fp_32;
+			/* same as lr above */
+			u32 lr_32;
+			/* same as lr2 above */
+			u32 lr2_32;
+		};
+	};
+};
+
+static void gator_add_trace(int cpu, unsigned long address)
+{
+	off_t offset = 0;
+	unsigned long cookie = get_address_cookie(cpu, current, address & ~1, &offset);
+
+	if (cookie == NO_COOKIE || cookie == UNRESOLVED_COOKIE)
+		offset = address;
+
+	marshal_backtrace(offset & ~1, cookie, 0);
+}
+
+static void arm_backtrace_eabi(int cpu, struct pt_regs *const regs, unsigned int depth)
+{
+#if defined(__arm__) || defined(__aarch64__)
+	struct stack_frame_eabi *curr;
+	struct stack_frame_eabi bufcurr;
+#if defined(__arm__)
+	const bool is_compat = false;
+	unsigned long fp = regs->ARM_fp;
+	unsigned long sp = regs->ARM_sp;
+	unsigned long lr = regs->ARM_lr;
+	const int gcc_frame_offset = sizeof(unsigned long);
+#else
+	/* Is userspace aarch32 (32 bit) */
+	const bool is_compat = compat_user_mode(regs);
+	unsigned long fp = (is_compat ? regs->regs[11] : regs->regs[29]);
+	unsigned long sp = (is_compat ? regs->compat_sp : regs->sp);
+	unsigned long lr = (is_compat ? regs->compat_lr : regs->regs[30]);
+	const int gcc_frame_offset = (is_compat ? sizeof(u32) : 0);
+#endif
+	/* clang frame offset is always zero */
+	int is_user_mode = user_mode(regs);
+
+	/* pc (current function) has already been added */
+
+	if (!is_user_mode)
+		return;
+
+	/* Add the lr (parent function), entry preamble may not have
+	 * executed
+	 */
+	gator_add_trace(cpu, lr);
+
+	/* check fp is valid */
+	if (fp == 0 || fp < sp)
+		return;
+
+	/* Get the current stack frame */
+	curr = (struct stack_frame_eabi *)(fp - gcc_frame_offset);
+	if ((unsigned long)curr & 3)
+		return;
+
+	while (depth-- && curr) {
+		if (!access_ok(VERIFY_READ, curr, sizeof(struct stack_frame_eabi)) ||
+				__copy_from_user_inatomic(&bufcurr, curr, sizeof(struct stack_frame_eabi))) {
+			return;
+		}
+
+		fp = (is_compat ? bufcurr.fp_32 : bufcurr.fp);
+		lr = (is_compat ? bufcurr.lr_32 : bufcurr.lr);
+
+#define calc_next(reg) ((reg) - gcc_frame_offset)
+		/* Returns true if reg is a valid fp */
+#define validate_next(reg, curr) \
+		((reg) != 0 && (calc_next(reg) & 3) == 0 && (unsigned long)(curr) < calc_next(reg))
+
+		/* Try lr from the stack as the fp because gcc leaf functions do
+		 * not push lr. If gcc_frame_offset is non-zero, the lr will also
+		 * be the clang fp. This assumes code is at a lower address than
+		 * the stack
+		 */
+		if (validate_next(lr, curr)) {
+			fp = lr;
+			lr = (is_compat ? bufcurr.lr2_32 : bufcurr.lr2);
+		}
+
+		gator_add_trace(cpu, lr);
+
+		if (!validate_next(fp, curr))
+			return;
+
+		/* Move to the next stack frame */
+		curr = (struct stack_frame_eabi *)calc_next(fp);
+	}
+#endif
+}
+
+#if defined(__arm__) || defined(__aarch64__)
+static int report_trace(struct stackframe *frame, void *d)
+{
+	unsigned int *depth = d, cookie = NO_COOKIE;
+	unsigned long addr = frame->pc;
+
+	if (*depth) {
+#if defined(MODULE)
+		unsigned int cpu = get_physical_cpu();
+		struct module *mod = __module_address(addr);
+
+		if (mod) {
+			cookie = get_cookie(cpu, current, mod->name, false);
+			addr = addr - (unsigned long)mod->module_core;
+		}
+#endif
+		marshal_backtrace(addr & ~1, cookie, 1);
+		(*depth)--;
+	}
+
+	return *depth == 0;
+}
+#endif
+
+/* Uncomment the following line to enable kernel stack unwinding within gator, note it can also be defined from the Makefile */
+/* #define GATOR_KERNEL_STACK_UNWINDING */
+
+#if (defined(__arm__) || defined(__aarch64__)) && !defined(GATOR_KERNEL_STACK_UNWINDING)
+/* Disabled by default */
+MODULE_PARM_DESC(kernel_stack_unwinding, "Allow kernel stack unwinding.");
+static bool kernel_stack_unwinding;
+module_param(kernel_stack_unwinding, bool, 0644);
+#endif
+
+static void kernel_backtrace(int cpu, struct pt_regs *const regs)
+{
+#if defined(__arm__) || defined(__aarch64__)
+#ifdef GATOR_KERNEL_STACK_UNWINDING
+	int depth = gator_backtrace_depth;
+#else
+	int depth = (kernel_stack_unwinding ? gator_backtrace_depth : 1);
+#endif
+	struct stackframe frame;
+
+	if (depth == 0)
+		depth = 1;
+#if defined(__arm__)
+	frame.fp = regs->ARM_fp;
+	frame.sp = regs->ARM_sp;
+	frame.lr = regs->ARM_lr;
+	frame.pc = regs->ARM_pc;
+#else
+	frame.fp = regs->regs[29];
+	frame.sp = regs->sp;
+	frame.pc = regs->pc;
+#endif
+	walk_stackframe(&frame, report_trace, &depth);
+#else
+	marshal_backtrace(PC_REG & ~1, NO_COOKIE, 1);
+#endif
+}
+
+static void gator_add_sample(int cpu, struct pt_regs *const regs, u64 time)
+{
+	bool in_kernel;
+	unsigned long exec_cookie;
+
+	if (!regs)
+		return;
+
+	in_kernel = !user_mode(regs);
+	exec_cookie = get_exec_cookie(cpu, current);
+
+	if (!marshal_backtrace_header(exec_cookie, current->tgid, current->pid, time))
+		return;
+
+	if (in_kernel) {
+		kernel_backtrace(cpu, regs);
+	} else {
+		/* Cookie+PC */
+		gator_add_trace(cpu, PC_REG);
+
+		/* Backtrace */
+		if (gator_backtrace_depth)
+			arm_backtrace_eabi(cpu, regs, gator_backtrace_depth);
+	}
+
+	marshal_backtrace_footer(time);
+}
diff --git a/drivers/gator/gator_buffer.c b/drivers/gator/gator_buffer.c
new file mode 100644
index 00000000000..f335457638a
--- /dev/null
+++ b/drivers/gator/gator_buffer.c
@@ -0,0 +1,171 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+static void marshal_frame(int cpu, int buftype)
+{
+	int frame;
+	bool write_cpu;
+
+	if (!per_cpu(gator_buffer, cpu)[buftype])
+		return;
+
+	switch (buftype) {
+	case SUMMARY_BUF:
+		write_cpu = false;
+		frame = FRAME_SUMMARY;
+		break;
+	case BACKTRACE_BUF:
+		write_cpu = true;
+		frame = FRAME_BACKTRACE;
+		break;
+	case NAME_BUF:
+		write_cpu = true;
+		frame = FRAME_NAME;
+		break;
+	case COUNTER_BUF:
+		write_cpu = false;
+		frame = FRAME_COUNTER;
+		break;
+	case BLOCK_COUNTER_BUF:
+		write_cpu = true;
+		frame = FRAME_BLOCK_COUNTER;
+		break;
+	case ANNOTATE_BUF:
+		write_cpu = false;
+		frame = FRAME_ANNOTATE;
+		break;
+	case SCHED_TRACE_BUF:
+		write_cpu = true;
+		frame = FRAME_SCHED_TRACE;
+		break;
+	case IDLE_BUF:
+		write_cpu = false;
+		frame = FRAME_IDLE;
+		break;
+	case ACTIVITY_BUF:
+		write_cpu = false;
+		frame = FRAME_ACTIVITY;
+		break;
+	default:
+		write_cpu = false;
+		frame = -1;
+		break;
+	}
+
+	/* add response type */
+	if (gator_response_type > 0)
+		gator_buffer_write_packed_int(cpu, buftype, gator_response_type);
+
+	/* leave space for 4-byte unpacked length */
+	per_cpu(gator_buffer_write, cpu)[buftype] = (per_cpu(gator_buffer_write, cpu)[buftype] + sizeof(s32)) & gator_buffer_mask[buftype];
+
+	/* add frame type and core number */
+	gator_buffer_write_packed_int(cpu, buftype, frame);
+	if (write_cpu)
+		gator_buffer_write_packed_int(cpu, buftype, cpu);
+}
+
+static int buffer_bytes_available(int cpu, int buftype)
+{
+	int remaining, filled;
+
+	filled = per_cpu(gator_buffer_write, cpu)[buftype] - per_cpu(gator_buffer_read, cpu)[buftype];
+	if (filled < 0)
+		filled += gator_buffer_size[buftype];
+
+	remaining = gator_buffer_size[buftype] - filled;
+
+	if (per_cpu(buffer_space_available, cpu)[buftype])
+		/* Give some extra room; also allows space to insert the overflow error packet */
+		remaining -= 200;
+	else
+		/* Hysteresis, prevents multiple overflow messages */
+		remaining -= 2000;
+
+	return remaining;
+}
+
+static bool buffer_check_space(int cpu, int buftype, int bytes)
+{
+	int remaining = buffer_bytes_available(cpu, buftype);
+
+	if (remaining < bytes)
+		per_cpu(buffer_space_available, cpu)[buftype] = false;
+	else
+		per_cpu(buffer_space_available, cpu)[buftype] = true;
+
+	return per_cpu(buffer_space_available, cpu)[buftype];
+}
+
+static int contiguous_space_available(int cpu, int buftype)
+{
+	int remaining = buffer_bytes_available(cpu, buftype);
+	int contiguous = gator_buffer_size[buftype] - per_cpu(gator_buffer_write, cpu)[buftype];
+
+	if (remaining < contiguous)
+		return remaining;
+	return contiguous;
+}
+
+static void gator_commit_buffer(int cpu, int buftype, u64 time)
+{
+	int type_length, commit, length, byte;
+	unsigned long flags;
+
+	if (!per_cpu(gator_buffer, cpu)[buftype])
+		return;
+
+	/* post-populate the length, which does not include the response type length nor the length itself, i.e. only the length of the payload */
+	local_irq_save(flags);
+	type_length = gator_response_type ? 1 : 0;
+	commit = per_cpu(gator_buffer_commit, cpu)[buftype];
+	length = per_cpu(gator_buffer_write, cpu)[buftype] - commit;
+	if (length < 0)
+		length += gator_buffer_size[buftype];
+	length = length - type_length - sizeof(s32);
+
+	if (length <= FRAME_HEADER_SIZE) {
+		/* Nothing to write, only the frame header is present */
+		local_irq_restore(flags);
+		return;
+	}
+
+	for (byte = 0; byte < sizeof(s32); byte++)
+		per_cpu(gator_buffer, cpu)[buftype][(commit + type_length + byte) & gator_buffer_mask[buftype]] = (length >> byte * 8) & 0xFF;
+
+	per_cpu(gator_buffer_commit, cpu)[buftype] = per_cpu(gator_buffer_write, cpu)[buftype];
+
+	if (gator_live_rate > 0) {
+		while (time > per_cpu(gator_buffer_commit_time, cpu))
+			per_cpu(gator_buffer_commit_time, cpu) += gator_live_rate;
+	}
+
+	marshal_frame(cpu, buftype);
+	local_irq_restore(flags);
+
+	/* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */
+	if (per_cpu(in_scheduler_context, cpu)) {
+#ifndef CONFIG_PREEMPT_RT_FULL
+		/* mod_timer can not be used in interrupt context in RT-Preempt full */
+		mod_timer(&gator_buffer_wake_up_timer, jiffies + 1);
+#endif
+	} else {
+		up(&gator_buffer_wake_sem);
+	}
+}
+
+static void buffer_check(int cpu, int buftype, u64 time)
+{
+	int filled = per_cpu(gator_buffer_write, cpu)[buftype] - per_cpu(gator_buffer_commit, cpu)[buftype];
+
+	if (filled < 0)
+		filled += gator_buffer_size[buftype];
+	if (filled >= ((gator_buffer_size[buftype] * 3) / 4))
+		gator_commit_buffer(cpu, buftype, time);
+}
diff --git a/drivers/gator/gator_buffer_write.c b/drivers/gator/gator_buffer_write.c
new file mode 100644
index 00000000000..b731e6a414d
--- /dev/null
+++ b/drivers/gator/gator_buffer_write.c
@@ -0,0 +1,83 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+static void gator_buffer_write_packed_int(int cpu, int buftype, int x)
+{
+	uint32_t write = per_cpu(gator_buffer_write, cpu)[buftype];
+	uint32_t mask = gator_buffer_mask[buftype];
+	char *buffer = per_cpu(gator_buffer, cpu)[buftype];
+	int packedBytes = 0;
+	int more = true;
+
+	while (more) {
+		/* low order 7 bits of x */
+		char b = x & 0x7f;
+
+		x >>= 7;
+
+		if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0))
+			more = false;
+		else
+			b |= 0x80;
+
+		buffer[(write + packedBytes) & mask] = b;
+		packedBytes++;
+	}
+
+	per_cpu(gator_buffer_write, cpu)[buftype] = (write + packedBytes) & mask;
+}
+
+static void gator_buffer_write_packed_int64(int cpu, int buftype, long long x)
+{
+	uint32_t write = per_cpu(gator_buffer_write, cpu)[buftype];
+	uint32_t mask = gator_buffer_mask[buftype];
+	char *buffer = per_cpu(gator_buffer, cpu)[buftype];
+	int packedBytes = 0;
+	int more = true;
+
+	while (more) {
+		/* low order 7 bits of x */
+		char b = x & 0x7f;
+
+		x >>= 7;
+
+		if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0))
+			more = false;
+		else
+			b |= 0x80;
+
+		buffer[(write + packedBytes) & mask] = b;
+		packedBytes++;
+	}
+
+	per_cpu(gator_buffer_write, cpu)[buftype] = (write + packedBytes) & mask;
+}
+
+static void gator_buffer_write_bytes(int cpu, int buftype, const char *x, int len)
+{
+	int i;
+	u32 write = per_cpu(gator_buffer_write, cpu)[buftype];
+	u32 mask = gator_buffer_mask[buftype];
+	char *buffer = per_cpu(gator_buffer, cpu)[buftype];
+
+	for (i = 0; i < len; i++) {
+		buffer[write] = x[i];
+		write = (write + 1) & mask;
+	}
+
+	per_cpu(gator_buffer_write, cpu)[buftype] = write;
+}
+
+static void gator_buffer_write_string(int cpu, int buftype, const char *x)
+{
+	int len = strlen(x);
+
+	gator_buffer_write_packed_int(cpu, buftype, len);
+	gator_buffer_write_bytes(cpu, buftype, x, len);
+}
diff --git a/drivers/gator/gator_cookies.c b/drivers/gator/gator_cookies.c
new file mode 100644
index 00000000000..7636726b5c1
--- /dev/null
+++ b/drivers/gator/gator_cookies.c
@@ -0,0 +1,548 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/mount.h>
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 3, 0)
+
+struct mount {
+	struct mount *mnt_parent;
+	struct dentry *mnt_mountpoint;
+	struct vfsmount mnt;
+};
+
+static inline struct mount *real_mount(struct vfsmount *mnt)
+{
+	return container_of(mnt, struct mount, mnt);
+}
+
+#define GET_MNT_ROOT(mount) (mount)->mnt.mnt_root
+
+#else
+
+#define GET_MNT_ROOT(mount) (mount)->mnt_root
+
+#endif
+
+/* must be power of 2 */
+#define COOKIEMAP_ENTRIES	1024
+/* must be a power of 2 - 512/4 = 128 entries */
+#define TRANSLATE_BUFFER_SIZE 512
+#define TRANSLATE_TEXT_SIZE		256
+#define MAX_COLLISIONS		2
+
+static uint32_t *gator_crc32_table;
+static unsigned int translate_buffer_mask;
+
+struct cookie_args {
+	struct task_struct *task;
+	const char *text;
+};
+
+static DEFINE_PER_CPU(char *, translate_text);
+static DEFINE_PER_CPU(char *, scratch);
+static DEFINE_PER_CPU(uint32_t, cookie_next_key);
+static DEFINE_PER_CPU(uint64_t *, cookie_keys);
+static DEFINE_PER_CPU(uint32_t *, cookie_values);
+static DEFINE_PER_CPU(int, translate_buffer_read);
+static DEFINE_PER_CPU(int, translate_buffer_write);
+static DEFINE_PER_CPU(struct cookie_args *, translate_buffer);
+
+static uint32_t get_cookie(int cpu, struct task_struct *task, const char *text, bool from_wq);
+static void wq_cookie_handler(struct work_struct *unused);
+static DECLARE_WORK(cookie_work, wq_cookie_handler);
+static struct timer_list app_process_wake_up_timer;
+static void app_process_wake_up_handler(unsigned long unused_data);
+
+static uint32_t cookiemap_code(uint64_t value64)
+{
+	uint32_t value = (uint32_t)((value64 >> 32) + value64);
+	uint32_t cookiecode = (value >> 24) & 0xff;
+
+	cookiecode = cookiecode * 31 + ((value >> 16) & 0xff);
+	cookiecode = cookiecode * 31 + ((value >> 8) & 0xff);
+	cookiecode = cookiecode * 31 + ((value >> 0) & 0xff);
+	cookiecode &= (COOKIEMAP_ENTRIES - 1);
+	return cookiecode * MAX_COLLISIONS;
+}
+
+static uint32_t gator_chksum_crc32(const char *data)
+{
+	register unsigned long crc;
+	const unsigned char *block = data;
+	int i, length = strlen(data);
+
+	crc = 0xFFFFFFFF;
+	for (i = 0; i < length; i++)
+		crc = ((crc >> 8) & 0x00FFFFFF) ^ gator_crc32_table[(crc ^ *block++) & 0xFF];
+
+	return (crc ^ 0xFFFFFFFF);
+}
+
+/*
+ * Exists
+ *  Pre:  [0][1][v][3]..[n-1]
+ *  Post: [v][0][1][3]..[n-1]
+ */
+static uint32_t cookiemap_exists(uint64_t key)
+{
+	unsigned long x, flags, retval = 0;
+	int cpu = get_physical_cpu();
+	uint32_t cookiecode = cookiemap_code(key);
+	uint64_t *keys = &(per_cpu(cookie_keys, cpu)[cookiecode]);
+	uint32_t *values = &(per_cpu(cookie_values, cpu)[cookiecode]);
+
+	/* Can be called from interrupt handler or from work queue */
+	local_irq_save(flags);
+	for (x = 0; x < MAX_COLLISIONS; x++) {
+		if (keys[x] == key) {
+			uint32_t value = values[x];
+
+			for (; x > 0; x--) {
+				keys[x] = keys[x - 1];
+				values[x] = values[x - 1];
+			}
+			keys[0] = key;
+			values[0] = value;
+			retval = value;
+			break;
+		}
+	}
+	local_irq_restore(flags);
+
+	return retval;
+}
+
+/*
+ * Add
+ *  Pre:  [0][1][2][3]..[n-1]
+ *  Post: [v][0][1][2]..[n-2]
+ */
+static void cookiemap_add(uint64_t key, uint32_t value)
+{
+	int cpu = get_physical_cpu();
+	int cookiecode = cookiemap_code(key);
+	uint64_t *keys = &(per_cpu(cookie_keys, cpu)[cookiecode]);
+	uint32_t *values = &(per_cpu(cookie_values, cpu)[cookiecode]);
+	int x;
+
+	for (x = MAX_COLLISIONS - 1; x > 0; x--) {
+		keys[x] = keys[x - 1];
+		values[x] = values[x - 1];
+	}
+	keys[0] = key;
+	values[0] = value;
+}
+
+#ifndef CONFIG_PREEMPT_RT_FULL
+static void translate_buffer_write_args(int cpu, struct task_struct *task, const char *text)
+{
+	unsigned long flags;
+	int write;
+	int next_write;
+	struct cookie_args *args;
+
+	local_irq_save(flags);
+
+	write = per_cpu(translate_buffer_write, cpu);
+	next_write = (write + 1) & translate_buffer_mask;
+
+	/* At least one entry must always remain available as when read == write, the queue is empty not full */
+	if (next_write != per_cpu(translate_buffer_read, cpu)) {
+		args = &per_cpu(translate_buffer, cpu)[write];
+		args->task = task;
+		args->text = text;
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39)
+		get_task_struct(task);
+#endif
+		per_cpu(translate_buffer_write, cpu) = next_write;
+	}
+
+	local_irq_restore(flags);
+}
+#endif
+
+static void translate_buffer_read_args(int cpu, struct cookie_args *args)
+{
+	unsigned long flags;
+	int read;
+
+	local_irq_save(flags);
+
+	read = per_cpu(translate_buffer_read, cpu);
+	*args = per_cpu(translate_buffer, cpu)[read];
+	per_cpu(translate_buffer_read, cpu) = (read + 1) & translate_buffer_mask;
+
+	local_irq_restore(flags);
+}
+
+static void wq_cookie_handler(struct work_struct *unused)
+{
+	struct cookie_args args;
+	int cpu = get_physical_cpu(), cookie;
+
+	mutex_lock(&start_mutex);
+
+	if (gator_started != 0) {
+		while (per_cpu(translate_buffer_read, cpu) != per_cpu(translate_buffer_write, cpu)) {
+			translate_buffer_read_args(cpu, &args);
+			cookie = get_cookie(cpu, args.task, args.text, true);
+			marshal_link(cookie, args.task->tgid, args.task->pid);
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39)
+			put_task_struct(args.task);
+#endif
+		}
+	}
+
+	mutex_unlock(&start_mutex);
+}
+
+static void app_process_wake_up_handler(unsigned long unused_data)
+{
+	/* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */
+	schedule_work(&cookie_work);
+}
+
+/* Retrieve full name from proc/pid/cmdline for java processes on Android */
+static int translate_app_process(const char **text, int cpu, struct task_struct *task, bool from_wq)
+{
+	void *maddr;
+	unsigned int len;
+	unsigned long addr;
+	struct mm_struct *mm;
+	struct page *page = NULL;
+	struct vm_area_struct *page_vma;
+	int bytes, offset, retval = 0;
+	char *buf = per_cpu(translate_text, cpu);
+
+#ifndef CONFIG_PREEMPT_RT_FULL
+	/* Push work into a work queue if in atomic context as the kernel
+	 * functions below might sleep. Rely on the in_interrupt variable
+	 * rather than in_irq() or in_interrupt() kernel functions, as the
+	 * value of these functions seems inconsistent during a context
+	 * switch between android/linux versions
+	 */
+	if (!from_wq) {
+		/* Check if already in buffer */
+		int pos = per_cpu(translate_buffer_read, cpu);
+
+		while (pos != per_cpu(translate_buffer_write, cpu)) {
+			if (per_cpu(translate_buffer, cpu)[pos].task == task)
+				goto out;
+			pos = (pos + 1) & translate_buffer_mask;
+		}
+
+		translate_buffer_write_args(cpu, task, *text);
+
+		/* Not safe to call in RT-Preempt full in schedule switch context */
+		mod_timer(&app_process_wake_up_timer, jiffies + 1);
+		goto out;
+	}
+#endif
+
+	mm = get_task_mm(task);
+	if (!mm)
+		goto out;
+	if (!mm->arg_end)
+		goto outmm;
+	addr = mm->arg_start;
+	len = mm->arg_end - mm->arg_start;
+
+	if (len > TRANSLATE_TEXT_SIZE)
+		len = TRANSLATE_TEXT_SIZE;
+
+	down_read(&mm->mmap_sem);
+	while (len) {
+		if (get_user_pages(task, mm, addr, 1, 0, 1, &page, &page_vma) <= 0)
+			goto outsem;
+
+		maddr = kmap(page);
+		offset = addr & (PAGE_SIZE - 1);
+		bytes = len;
+		if (bytes > PAGE_SIZE - offset)
+			bytes = PAGE_SIZE - offset;
+
+		copy_from_user_page(page_vma, page, addr, buf, maddr + offset, bytes);
+
+		/* release page allocated by get_user_pages() */
+		kunmap(page);
+		page_cache_release(page);
+
+		len -= bytes;
+		buf += bytes;
+		addr += bytes;
+
+		*text = per_cpu(translate_text, cpu);
+		retval = 1;
+	}
+
+	/* On app_process startup, /proc/pid/cmdline is initially "zygote" then "<pre-initialized>" but changes after an initial startup period */
+	if (strcmp(*text, "zygote") == 0 || strcmp(*text, "<pre-initialized>") == 0)
+		retval = 0;
+
+outsem:
+	up_read(&mm->mmap_sem);
+outmm:
+	mmput(mm);
+out:
+	return retval;
+}
+
+static const char APP_PROCESS[] = "app_process";
+
+static uint32_t get_cookie(int cpu, struct task_struct *task, const char *text, bool from_wq)
+{
+	unsigned long flags, cookie;
+	uint64_t key;
+
+	key = gator_chksum_crc32(text);
+	key = (key << 32) | (uint32_t)task->tgid;
+
+	cookie = cookiemap_exists(key);
+	if (cookie)
+		return cookie;
+
+	/* On 64-bit android app_process can be app_process32 or app_process64 */
+	if (strstr(text, APP_PROCESS) != NULL) {
+		if (!translate_app_process(&text, cpu, task, from_wq))
+			return UNRESOLVED_COOKIE;
+	}
+
+	/* Can be called from interrupt handler or from work queue or from scheduler trace */
+	local_irq_save(flags);
+
+	cookie = UNRESOLVED_COOKIE;
+	if (marshal_cookie_header(text)) {
+		cookie = per_cpu(cookie_next_key, cpu) += nr_cpu_ids;
+		cookiemap_add(key, cookie);
+		marshal_cookie(cookie, text);
+	}
+
+	local_irq_restore(flags);
+
+	return cookie;
+}
+
+/* Can't call d_path in interrupt context so create something similar */
+static const char *gator_d_path(const struct path *path, char *buf, int buflen)
+{
+	struct dentry *dentry = path->dentry;
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 3, 0)
+	struct mount *mount = real_mount(path->mnt);
+#else
+	struct vfsmount *mount = path->mnt;
+#endif
+	int pos = buflen - 1;
+	int len;
+
+	buf[pos] = '\0';
+
+	for (;;) {
+		if (dentry == NULL) {
+			pr_err("gator: dentry is null!\n");
+			break;
+		}
+		if (dentry->d_name.name[0] == '\0') {
+			pr_err("gator: path is empty string\n");
+			break;
+		}
+		if (dentry->d_name.name[0] == '/' && dentry->d_name.name[1] == '\0') {
+			/* Normal operation */
+			/* pr_err("gator: path is /\n"); */
+			break;
+		}
+
+		len = strlen(dentry->d_name.name);
+		if (pos < len) {
+			pr_err("gator: path is too long\n");
+			break;
+		}
+		pos -= len;
+		memcpy(buf + pos, dentry->d_name.name, len);
+
+		if (pos == 0) {
+			pr_err("gator: no room for slash\n");
+			/* Fall back to name only */
+			return path->dentry->d_name.name;
+		}
+		--pos;
+		buf[pos] = '/';
+
+		if (dentry->d_parent == GET_MNT_ROOT(mount)) {
+			/* pr_err("gator: filesystem is complete, moving to next '%s'\n", buf + pos); */
+			dentry = mount->mnt_mountpoint;
+			mount = mount->mnt_parent;
+			continue;
+		}
+		if (dentry == dentry->d_parent) {
+			pr_err("gator: parent is self\n");
+			break;
+		}
+		dentry = dentry->d_parent;
+	}
+
+	if (pos < 0) {
+		pr_err("gator: pos is somenow negative\n");
+		/* Fall back to name only */
+		return path->dentry->d_name.name;
+	}
+
+	return buf + pos;
+}
+
+#define d_path gator_d_path
+
+static int get_exec_cookie(int cpu, struct task_struct *task)
+{
+	struct mm_struct *mm = task->mm;
+	const char *text;
+
+	/* kernel threads have no address space */
+	if (!mm)
+		return NO_COOKIE;
+
+	if (task && task->mm && task->mm->exe_file) {
+		text = d_path(&task->mm->exe_file->f_path, per_cpu(scratch, get_physical_cpu()), PAGE_SIZE);
+		return get_cookie(cpu, task, text, false);
+	}
+
+	return UNRESOLVED_COOKIE;
+}
+
+static unsigned long get_address_cookie(int cpu, struct task_struct *task, unsigned long addr, off_t *offset)
+{
+	unsigned long cookie = NO_COOKIE;
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
+	const char *text;
+
+	if (!mm)
+		return cookie;
+
+	for (vma = find_vma(mm, addr); vma; vma = vma->vm_next) {
+		if (addr < vma->vm_start || addr >= vma->vm_end)
+			continue;
+
+		if (vma->vm_file) {
+			text = d_path(&vma->vm_file->f_path, per_cpu(scratch, get_physical_cpu()), PAGE_SIZE);
+			cookie = get_cookie(cpu, task, text, false);
+			*offset = (vma->vm_pgoff << PAGE_SHIFT) + addr - vma->vm_start;
+		} else {
+			/* must be an anonymous map */
+			*offset = addr;
+		}
+
+		break;
+	}
+
+	if (!vma)
+		cookie = UNRESOLVED_COOKIE;
+
+	return cookie;
+}
+
+static int cookies_initialize(void)
+{
+	uint32_t crc, poly;
+	int i, j, cpu, size, err = 0;
+
+	translate_buffer_mask = TRANSLATE_BUFFER_SIZE / sizeof(per_cpu(translate_buffer, 0)[0]) - 1;
+
+	for_each_present_cpu(cpu) {
+		per_cpu(cookie_next_key, cpu) = nr_cpu_ids + cpu;
+
+		size = COOKIEMAP_ENTRIES * MAX_COLLISIONS * sizeof(uint64_t);
+		per_cpu(cookie_keys, cpu) = kmalloc(size, GFP_KERNEL);
+		if (!per_cpu(cookie_keys, cpu)) {
+			err = -ENOMEM;
+			goto cookie_setup_error;
+		}
+		memset(per_cpu(cookie_keys, cpu), 0, size);
+
+		size = COOKIEMAP_ENTRIES * MAX_COLLISIONS * sizeof(uint32_t);
+		per_cpu(cookie_values, cpu) = kmalloc(size, GFP_KERNEL);
+		if (!per_cpu(cookie_values, cpu)) {
+			err = -ENOMEM;
+			goto cookie_setup_error;
+		}
+		memset(per_cpu(cookie_values, cpu), 0, size);
+
+		per_cpu(translate_buffer, cpu) = kmalloc(TRANSLATE_BUFFER_SIZE, GFP_KERNEL);
+		if (!per_cpu(translate_buffer, cpu)) {
+			err = -ENOMEM;
+			goto cookie_setup_error;
+		}
+
+		per_cpu(translate_buffer_write, cpu) = 0;
+		per_cpu(translate_buffer_read, cpu) = 0;
+
+		per_cpu(translate_text, cpu) = kmalloc(TRANSLATE_TEXT_SIZE, GFP_KERNEL);
+		if (!per_cpu(translate_text, cpu)) {
+			err = -ENOMEM;
+			goto cookie_setup_error;
+		}
+
+		per_cpu(scratch, cpu) = kmalloc(PAGE_SIZE, GFP_KERNEL);
+		if (!per_cpu(scratch, cpu)) {
+			err = -ENOMEM;
+			goto cookie_setup_error;
+		}
+	}
+
+	/* build CRC32 table */
+	poly = 0x04c11db7;
+	gator_crc32_table = kmalloc(256 * sizeof(*gator_crc32_table), GFP_KERNEL);
+	if (!gator_crc32_table) {
+		err = -ENOMEM;
+		goto cookie_setup_error;
+	}
+	for (i = 0; i < 256; i++) {
+		crc = i;
+		for (j = 8; j > 0; j--) {
+			if (crc & 1)
+				crc = (crc >> 1) ^ poly;
+			else
+				crc >>= 1;
+		}
+		gator_crc32_table[i] = crc;
+	}
+
+	setup_deferrable_timer_on_stack(&app_process_wake_up_timer, app_process_wake_up_handler, 0);
+
+cookie_setup_error:
+	return err;
+}
+
+static void cookies_release(void)
+{
+	int cpu;
+
+	for_each_present_cpu(cpu) {
+		kfree(per_cpu(cookie_keys, cpu));
+		per_cpu(cookie_keys, cpu) = NULL;
+
+		kfree(per_cpu(cookie_values, cpu));
+		per_cpu(cookie_values, cpu) = NULL;
+
+		kfree(per_cpu(translate_buffer, cpu));
+		per_cpu(translate_buffer, cpu) = NULL;
+		per_cpu(translate_buffer_read, cpu) = 0;
+		per_cpu(translate_buffer_write, cpu) = 0;
+
+		kfree(per_cpu(translate_text, cpu));
+		per_cpu(translate_text, cpu) = NULL;
+
+		kfree(per_cpu(scratch, cpu));
+		per_cpu(scratch, cpu) = NULL;
+	}
+
+	del_timer_sync(&app_process_wake_up_timer);
+	kfree(gator_crc32_table);
+	gator_crc32_table = NULL;
+}
diff --git a/drivers/gator/gator_events_armv6.c b/drivers/gator/gator_events_armv6.c
new file mode 100644
index 00000000000..62bd6eb94f9
--- /dev/null
+++ b/drivers/gator/gator_events_armv6.c
@@ -0,0 +1,235 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+/* gator_events_perf_pmu.c is used if perf is supported */
+#if GATOR_NO_PERF_SUPPORT
+
+static const char *pmnc_name;
+
+/*
+ * Per-CPU PMCR
+ */
+#define PMCR_E			(1 << 0)	/* Enable */
+#define PMCR_P			(1 << 1)	/* Count reset */
+#define PMCR_C			(1 << 2)	/* Cycle counter reset */
+#define PMCR_OFL_PMN0	(1 << 8)	/* Count reg 0 overflow */
+#define PMCR_OFL_PMN1	(1 << 9)	/* Count reg 1 overflow */
+#define PMCR_OFL_CCNT	(1 << 10)	/* Cycle counter overflow */
+
+#define PMN0 0
+#define PMN1 1
+#define CCNT 2
+#define CNTMAX	(CCNT+1)
+
+static int pmnc_counters;
+static unsigned long pmnc_enabled[CNTMAX];
+static unsigned long pmnc_event[CNTMAX];
+static unsigned long pmnc_key[CNTMAX];
+
+static DEFINE_PER_CPU(int[CNTMAX * 2], perfCnt);
+
+static inline void armv6_pmnc_write(u32 val)
+{
+	/* upper 4bits and 7, 11 are write-as-0 */
+	val &= 0x0ffff77f;
+	asm volatile("mcr p15, 0, %0, c15, c12, 0" : : "r" (val));
+}
+
+static inline u32 armv6_pmnc_read(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c15, c12, 0" : "=r" (val));
+	return val;
+}
+
+static void armv6_pmnc_reset_counter(unsigned int cnt)
+{
+	u32 val = 0;
+
+	switch (cnt) {
+	case CCNT:
+		asm volatile("mcr p15, 0, %0, c15, c12, 1" : : "r" (val));
+		break;
+	case PMN0:
+		asm volatile("mcr p15, 0, %0, c15, c12, 2" : : "r" (val));
+		break;
+	case PMN1:
+		asm volatile("mcr p15, 0, %0, c15, c12, 3" : : "r" (val));
+		break;
+	}
+}
+
+int gator_events_armv6_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	int i;
+
+	pmnc_counters = 3;
+
+	for (i = PMN0; i <= CCNT; i++) {
+		char buf[40];
+
+		if (i == CCNT)
+			snprintf(buf, sizeof(buf), "ARM_%s_ccnt", pmnc_name);
+		else
+			snprintf(buf, sizeof(buf), "ARM_%s_cnt%d", pmnc_name, i);
+		dir = gatorfs_mkdir(sb, root, buf);
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &pmnc_enabled[i]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &pmnc_key[i]);
+		if (i != CCNT)
+			gatorfs_create_ulong(sb, dir, "event", &pmnc_event[i]);
+	}
+
+	return 0;
+}
+
+static int gator_events_armv6_online(int **buffer, bool migrate)
+{
+	unsigned int cnt, len = 0, cpu = smp_processor_id();
+	u32 pmnc;
+
+	if (armv6_pmnc_read() & PMCR_E)
+		armv6_pmnc_write(armv6_pmnc_read() & ~PMCR_E);
+
+	/* initialize PMNC, reset overflow, D bit, C bit and P bit. */
+	armv6_pmnc_write(PMCR_OFL_PMN0 | PMCR_OFL_PMN1 | PMCR_OFL_CCNT |
+			 PMCR_C | PMCR_P);
+
+	/* configure control register */
+	for (pmnc = 0, cnt = PMN0; cnt <= CCNT; cnt++) {
+		unsigned long event;
+
+		if (!pmnc_enabled[cnt])
+			continue;
+
+		event = pmnc_event[cnt] & 255;
+
+		/* Set event (if destined for PMNx counters) */
+		if (cnt == PMN0)
+			pmnc |= event << 20;
+		else if (cnt == PMN1)
+			pmnc |= event << 12;
+
+		/* Reset counter */
+		armv6_pmnc_reset_counter(cnt);
+	}
+	armv6_pmnc_write(pmnc | PMCR_E);
+
+	/* return zero values, no need to read as the counters were just reset */
+	for (cnt = PMN0; cnt <= CCNT; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = 0;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static int gator_events_armv6_offline(int **buffer, bool migrate)
+{
+	unsigned int cnt;
+
+	armv6_pmnc_write(armv6_pmnc_read() & ~PMCR_E);
+	for (cnt = PMN0; cnt <= CCNT; cnt++)
+		armv6_pmnc_reset_counter(cnt);
+
+	return 0;
+}
+
+static void gator_events_armv6_stop(void)
+{
+	unsigned int cnt;
+
+	for (cnt = PMN0; cnt <= CCNT; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+	}
+}
+
+static int gator_events_armv6_read(int **buffer, bool sched_switch)
+{
+	int cnt, len = 0;
+	int cpu = smp_processor_id();
+
+	/* a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled */
+	if (!(armv6_pmnc_read() & PMCR_E))
+		return 0;
+
+	for (cnt = PMN0; cnt <= CCNT; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			u32 value = 0;
+
+			switch (cnt) {
+			case CCNT:
+				asm volatile("mrc p15, 0, %0, c15, c12, 1" : "=r" (value));
+				break;
+			case PMN0:
+				asm volatile("mrc p15, 0, %0, c15, c12, 2" : "=r" (value));
+				break;
+			case PMN1:
+				asm volatile("mrc p15, 0, %0, c15, c12, 3" : "=r" (value));
+				break;
+			}
+			armv6_pmnc_reset_counter(cnt);
+
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = value;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_armv6_interface = {
+	.name = "armv6",
+	.create_files = gator_events_armv6_create_files,
+	.stop = gator_events_armv6_stop,
+	.online = gator_events_armv6_online,
+	.offline = gator_events_armv6_offline,
+	.read = gator_events_armv6_read,
+};
+
+int gator_events_armv6_init(void)
+{
+	unsigned int cnt;
+
+	switch (gator_cpuid()) {
+	case ARM1136:
+	case ARM1156:
+	case ARM1176:
+		pmnc_name = "ARM11";
+		break;
+	case ARM11MPCORE:
+		pmnc_name = "ARM11MPCore";
+		break;
+	default:
+		return -1;
+	}
+
+	for (cnt = PMN0; cnt <= CCNT; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+		pmnc_key[cnt] = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_armv6_interface);
+}
+
+#endif
diff --git a/drivers/gator/gator_events_armv7.c b/drivers/gator/gator_events_armv7.c
new file mode 100644
index 00000000000..0db857c71a6
--- /dev/null
+++ b/drivers/gator/gator_events_armv7.c
@@ -0,0 +1,315 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*  Disabling interrupts
+ *    Many of the functions below disable interrupts via local_irq_save(). This disabling of interrupts is done to prevent any race conditions
+ *    between multiple entities (e.g. hrtimer interrupts and event based interrupts) calling the same functions. As accessing the pmu involves
+ *    several steps (disable, select, read, enable), these steps must be performed atomically. Normal synchronization routines cannot be used
+ *    as these functions are being called from interrupt context.
+ */
+
+#include "gator.h"
+
+/* gator_events_perf_pmu.c is used if perf is supported */
+#if GATOR_NO_PERF_SUPPORT
+
+/* Per-CPU PMNC: config reg */
+#define PMNC_E		(1 << 0)	/* Enable all counters */
+#define PMNC_P		(1 << 1)	/* Reset all counters */
+#define PMNC_C		(1 << 2)	/* Cycle counter reset */
+#define	PMNC_MASK	0x3f	/* Mask for writable bits */
+
+/* ccnt reg */
+#define CCNT_REG	(1 << 31)
+
+#define CCNT		0
+#define CNT0		1
+#define CNTMAX		(6+1)
+
+static const char *pmnc_name;
+static int pmnc_counters;
+
+static unsigned long pmnc_enabled[CNTMAX];
+static unsigned long pmnc_event[CNTMAX];
+static unsigned long pmnc_key[CNTMAX];
+
+static DEFINE_PER_CPU(int[CNTMAX * 2], perfCnt);
+
+inline void armv7_pmnc_write(u32 val)
+{
+	val &= PMNC_MASK;
+	asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r" (val));
+}
+
+inline u32 armv7_pmnc_read(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val));
+	return val;
+}
+
+inline u32 armv7_ccnt_read(u32 reset_value)
+{
+	unsigned long flags;
+	u32 newval = -reset_value;
+	u32 den = CCNT_REG;
+	u32 val;
+
+	local_irq_save(flags);
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (den));	/* disable */
+	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));	/* read */
+	asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (newval));	/* new value */
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (den));	/* enable */
+	local_irq_restore(flags);
+
+	return val;
+}
+
+inline u32 armv7_cntn_read(unsigned int cnt, u32 reset_value)
+{
+	unsigned long flags;
+	u32 newval = -reset_value;
+	u32 sel = (cnt - CNT0);
+	u32 den = 1 << sel;
+	u32 oldval;
+
+	local_irq_save(flags);
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (den));	/* disable */
+	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (sel));	/* select */
+	asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (oldval));	/* read */
+	asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (newval));	/* new value */
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (den));	/* enable */
+	local_irq_restore(flags);
+
+	return oldval;
+}
+
+static inline void armv7_pmnc_disable_interrupt(unsigned int cnt)
+{
+	u32 val = cnt ? (1 << (cnt - CNT0)) : (1 << 31);
+
+	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (val));
+}
+
+inline u32 armv7_pmnc_reset_interrupt(void)
+{
+	/* Get and reset overflow status flags */
+	u32 flags;
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (flags));
+	flags &= 0x8000003f;
+	asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (flags));
+	return flags;
+}
+
+static inline u32 armv7_pmnc_enable_counter(unsigned int cnt)
+{
+	u32 val = cnt ? (1 << (cnt - CNT0)) : CCNT_REG;
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));
+	return cnt;
+}
+
+static inline u32 armv7_pmnc_disable_counter(unsigned int cnt)
+{
+	u32 val = cnt ? (1 << (cnt - CNT0)) : CCNT_REG;
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));
+	return cnt;
+}
+
+static inline int armv7_pmnc_select_counter(unsigned int cnt)
+{
+	u32 val = (cnt - CNT0);
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));
+	return cnt;
+}
+
+static inline void armv7_pmnc_write_evtsel(unsigned int cnt, u32 val)
+{
+	if (armv7_pmnc_select_counter(cnt) == cnt)
+		asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
+}
+
+static int gator_events_armv7_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	int i;
+
+	for (i = 0; i < pmnc_counters; i++) {
+		char buf[40];
+
+		if (i == 0)
+			snprintf(buf, sizeof(buf), "%s_ccnt", pmnc_name);
+		else
+			snprintf(buf, sizeof(buf), "%s_cnt%d", pmnc_name, i - 1);
+		dir = gatorfs_mkdir(sb, root, buf);
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &pmnc_enabled[i]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &pmnc_key[i]);
+		if (i > 0)
+			gatorfs_create_ulong(sb, dir, "event", &pmnc_event[i]);
+	}
+
+	return 0;
+}
+
+static int gator_events_armv7_online(int **buffer, bool migrate)
+{
+	unsigned int cnt, len = 0, cpu = smp_processor_id();
+
+	if (armv7_pmnc_read() & PMNC_E)
+		armv7_pmnc_write(armv7_pmnc_read() & ~PMNC_E);
+
+	/* Initialize & Reset PMNC: C bit and P bit */
+	armv7_pmnc_write(PMNC_P | PMNC_C);
+
+	/* Reset overflow flags */
+	armv7_pmnc_reset_interrupt();
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		unsigned long event;
+
+		if (!pmnc_enabled[cnt])
+			continue;
+
+		/* Disable counter */
+		armv7_pmnc_disable_counter(cnt);
+
+		event = pmnc_event[cnt] & 255;
+
+		/* Set event (if destined for PMNx counters), we don't need to set the event if it's a cycle count */
+		if (cnt != CCNT)
+			armv7_pmnc_write_evtsel(cnt, event);
+
+		armv7_pmnc_disable_interrupt(cnt);
+
+		/* Reset counter */
+		cnt ? armv7_cntn_read(cnt, 0) : armv7_ccnt_read(0);
+
+		/* Enable counter */
+		armv7_pmnc_enable_counter(cnt);
+	}
+
+	/* enable */
+	armv7_pmnc_write(armv7_pmnc_read() | PMNC_E);
+
+	/* return zero values, no need to read as the counters were just reset */
+	for (cnt = 0; cnt < pmnc_counters; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = 0;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static int gator_events_armv7_offline(int **buffer, bool migrate)
+{
+	/* disable all counters, including PMCCNTR; overflow IRQs will not be signaled */
+	armv7_pmnc_write(armv7_pmnc_read() & ~PMNC_E);
+
+	return 0;
+}
+
+static void gator_events_armv7_stop(void)
+{
+	unsigned int cnt;
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+	}
+}
+
+static int gator_events_armv7_read(int **buffer, bool sched_switch)
+{
+	int cnt, len = 0;
+	int cpu = smp_processor_id();
+
+	/* a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled */
+	if (!(armv7_pmnc_read() & PMNC_E))
+		return 0;
+
+	for (cnt = 0; cnt < pmnc_counters; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			int value;
+
+			if (cnt == CCNT)
+				value = armv7_ccnt_read(0);
+			else
+				value = armv7_cntn_read(cnt, 0);
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = value;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_armv7_interface = {
+	.name = "armv7",
+	.create_files = gator_events_armv7_create_files,
+	.stop = gator_events_armv7_stop,
+	.online = gator_events_armv7_online,
+	.offline = gator_events_armv7_offline,
+	.read = gator_events_armv7_read,
+};
+
+int gator_events_armv7_init(void)
+{
+	unsigned int cnt;
+
+	switch (gator_cpuid()) {
+	case CORTEX_A5:
+		pmnc_name = "ARMv7_Cortex_A5";
+		pmnc_counters = 2;
+		break;
+	case CORTEX_A7:
+		pmnc_name = "ARMv7_Cortex_A7";
+		pmnc_counters = 4;
+		break;
+	case CORTEX_A8:
+		pmnc_name = "ARMv7_Cortex_A8";
+		pmnc_counters = 4;
+		break;
+	case CORTEX_A9:
+		pmnc_name = "ARMv7_Cortex_A9";
+		pmnc_counters = 6;
+		break;
+	case CORTEX_A15:
+		pmnc_name = "ARMv7_Cortex_A15";
+		pmnc_counters = 6;
+		break;
+	/* ARM Cortex A17 is not supported by version of Linux before 3.0 */
+	default:
+		return -1;
+	}
+
+	pmnc_counters++;	/* CNT[n] + CCNT */
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+		pmnc_key[cnt] = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_armv7_interface);
+}
+
+#endif
diff --git a/drivers/gator/gator_events_block.c b/drivers/gator/gator_events_block.c
new file mode 100644
index 00000000000..0bb4085db53
--- /dev/null
+++ b/drivers/gator/gator_events_block.c
@@ -0,0 +1,161 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+#include <trace/events/block.h>
+
+#define BLOCK_RQ_WR		0
+#define BLOCK_RQ_RD		1
+
+#define BLOCK_TOTAL		(BLOCK_RQ_RD+1)
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+#define EVENTWRITE REQ_RW
+#else
+#define EVENTWRITE REQ_WRITE
+#endif
+
+static ulong block_rq_wr_enabled;
+static ulong block_rq_rd_enabled;
+static ulong block_rq_wr_key;
+static ulong block_rq_rd_key;
+static atomic_t blockCnt[BLOCK_TOTAL];
+static int blockGet[BLOCK_TOTAL * 4];
+
+/* Tracepoint changed in 3.15 backported to older kernels. The Makefile tries to autodetect the correct value, but if it fails change the #if below */
+#if OLD_BLOCK_RQ_COMPLETE
+GATOR_DEFINE_PROBE(block_rq_complete, TP_PROTO(struct request_queue *q, struct request *rq))
+#else
+GATOR_DEFINE_PROBE(block_rq_complete, TP_PROTO(struct request_queue *q, struct request *rq, unsigned int nr_bytes))
+#endif
+{
+	int write;
+	unsigned int size;
+
+	if (!rq)
+		return;
+
+	write = rq->cmd_flags & EVENTWRITE;
+#if OLD_BLOCK_RQ_COMPLETE
+	size = rq->resid_len;
+#else
+	size = nr_bytes;
+#endif
+
+	if (!size)
+		return;
+
+	if (write) {
+		if (block_rq_wr_enabled)
+			atomic_add(size, &blockCnt[BLOCK_RQ_WR]);
+	} else {
+		if (block_rq_rd_enabled)
+			atomic_add(size, &blockCnt[BLOCK_RQ_RD]);
+	}
+}
+
+static int gator_events_block_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+
+	/* block_complete_wr */
+	dir = gatorfs_mkdir(sb, root, "Linux_block_rq_wr");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &block_rq_wr_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &block_rq_wr_key);
+
+	/* block_complete_rd */
+	dir = gatorfs_mkdir(sb, root, "Linux_block_rq_rd");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &block_rq_rd_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &block_rq_rd_key);
+
+	return 0;
+}
+
+static int gator_events_block_start(void)
+{
+	/* register tracepoints */
+	if (block_rq_wr_enabled || block_rq_rd_enabled)
+		if (GATOR_REGISTER_TRACE(block_rq_complete))
+			goto fail_block_rq_exit;
+	pr_debug("gator: registered block event tracepoints\n");
+
+	return 0;
+
+	/* unregister tracepoints on error */
+fail_block_rq_exit:
+	pr_err("gator: block event tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+	return -1;
+}
+
+static void gator_events_block_stop(void)
+{
+	if (block_rq_wr_enabled || block_rq_rd_enabled)
+		GATOR_UNREGISTER_TRACE(block_rq_complete);
+	pr_debug("gator: unregistered block event tracepoints\n");
+
+	block_rq_wr_enabled = 0;
+	block_rq_rd_enabled = 0;
+}
+
+static int gator_events_block_read(int **buffer, bool sched_switch)
+{
+	int len, value, data = 0;
+
+	if (!on_primary_core())
+		return 0;
+
+	len = 0;
+	if (block_rq_wr_enabled && (value = atomic_read(&blockCnt[BLOCK_RQ_WR])) > 0) {
+		atomic_sub(value, &blockCnt[BLOCK_RQ_WR]);
+		blockGet[len++] = block_rq_wr_key;
+		/* Indicates to Streamline that value bytes were written now, not since the last message */
+		blockGet[len++] = 0;
+		blockGet[len++] = block_rq_wr_key;
+		blockGet[len++] = value;
+		data += value;
+	}
+	if (block_rq_rd_enabled && (value = atomic_read(&blockCnt[BLOCK_RQ_RD])) > 0) {
+		atomic_sub(value, &blockCnt[BLOCK_RQ_RD]);
+		blockGet[len++] = block_rq_rd_key;
+		/* Indicates to Streamline that value bytes were read now, not since the last message */
+		blockGet[len++] = 0;
+		blockGet[len++] = block_rq_rd_key;
+		blockGet[len++] = value;
+		data += value;
+	}
+
+	if (buffer)
+		*buffer = blockGet;
+
+	return len;
+}
+
+static struct gator_interface gator_events_block_interface = {
+	.name = "block",
+	.create_files = gator_events_block_create_files,
+	.start = gator_events_block_start,
+	.stop = gator_events_block_stop,
+	.read = gator_events_block_read,
+};
+
+int gator_events_block_init(void)
+{
+	block_rq_wr_enabled = 0;
+	block_rq_rd_enabled = 0;
+
+	block_rq_wr_key = gator_events_get_key();
+	block_rq_rd_key = gator_events_get_key();
+
+	return gator_events_install(&gator_events_block_interface);
+}
diff --git a/drivers/gator/gator_events_irq.c b/drivers/gator/gator_events_irq.c
new file mode 100644
index 00000000000..aa1ebbb290a
--- /dev/null
+++ b/drivers/gator/gator_events_irq.c
@@ -0,0 +1,164 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+#include <trace/events/irq.h>
+
+#define HARDIRQ		0
+#define SOFTIRQ		1
+#define TOTALIRQ	(SOFTIRQ+1)
+
+static ulong hardirq_enabled;
+static ulong softirq_enabled;
+static ulong hardirq_key;
+static ulong softirq_key;
+static DEFINE_PER_CPU(atomic_t[TOTALIRQ], irqCnt);
+static DEFINE_PER_CPU(int[TOTALIRQ * 2], irqGet);
+
+GATOR_DEFINE_PROBE(irq_handler_exit,
+		   TP_PROTO(int irq, struct irqaction *action, int ret))
+{
+	atomic_inc(&per_cpu(irqCnt, get_physical_cpu())[HARDIRQ]);
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 37)
+GATOR_DEFINE_PROBE(softirq_exit, TP_PROTO(struct softirq_action *h, struct softirq_action *vec))
+#else
+GATOR_DEFINE_PROBE(softirq_exit, TP_PROTO(unsigned int vec_nr))
+#endif
+{
+	atomic_inc(&per_cpu(irqCnt, get_physical_cpu())[SOFTIRQ]);
+}
+
+static int gator_events_irq_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+
+	/* irq */
+	dir = gatorfs_mkdir(sb, root, "Linux_irq_irq");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &hardirq_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &hardirq_key);
+
+	/* soft irq */
+	dir = gatorfs_mkdir(sb, root, "Linux_irq_softirq");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &softirq_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &softirq_key);
+
+	return 0;
+}
+
+static int gator_events_irq_online(int **buffer, bool migrate)
+{
+	int len = 0, cpu = get_physical_cpu();
+
+	/* synchronization with the irq_exit functions is not necessary as the values are being reset */
+	if (hardirq_enabled) {
+		atomic_set(&per_cpu(irqCnt, cpu)[HARDIRQ], 0);
+		per_cpu(irqGet, cpu)[len++] = hardirq_key;
+		per_cpu(irqGet, cpu)[len++] = 0;
+	}
+
+	if (softirq_enabled) {
+		atomic_set(&per_cpu(irqCnt, cpu)[SOFTIRQ], 0);
+		per_cpu(irqGet, cpu)[len++] = softirq_key;
+		per_cpu(irqGet, cpu)[len++] = 0;
+	}
+
+	if (buffer)
+		*buffer = per_cpu(irqGet, cpu);
+
+	return len;
+}
+
+static int gator_events_irq_start(void)
+{
+	/* register tracepoints */
+	if (hardirq_enabled)
+		if (GATOR_REGISTER_TRACE(irq_handler_exit))
+			goto fail_hardirq_exit;
+	if (softirq_enabled)
+		if (GATOR_REGISTER_TRACE(softirq_exit))
+			goto fail_softirq_exit;
+	pr_debug("gator: registered irq tracepoints\n");
+
+	return 0;
+
+	/* unregister tracepoints on error */
+fail_softirq_exit:
+	if (hardirq_enabled)
+		GATOR_UNREGISTER_TRACE(irq_handler_exit);
+fail_hardirq_exit:
+	pr_err("gator: irq tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+	return -1;
+}
+
+static void gator_events_irq_stop(void)
+{
+	if (hardirq_enabled)
+		GATOR_UNREGISTER_TRACE(irq_handler_exit);
+	if (softirq_enabled)
+		GATOR_UNREGISTER_TRACE(softirq_exit);
+	pr_debug("gator: unregistered irq tracepoints\n");
+
+	hardirq_enabled = 0;
+	softirq_enabled = 0;
+}
+
+static int gator_events_irq_read(int **buffer, bool sched_switch)
+{
+	int len, value;
+	int cpu = get_physical_cpu();
+
+	len = 0;
+	if (hardirq_enabled) {
+		value = atomic_read(&per_cpu(irqCnt, cpu)[HARDIRQ]);
+		atomic_sub(value, &per_cpu(irqCnt, cpu)[HARDIRQ]);
+
+		per_cpu(irqGet, cpu)[len++] = hardirq_key;
+		per_cpu(irqGet, cpu)[len++] = value;
+	}
+
+	if (softirq_enabled) {
+		value = atomic_read(&per_cpu(irqCnt, cpu)[SOFTIRQ]);
+		atomic_sub(value, &per_cpu(irqCnt, cpu)[SOFTIRQ]);
+
+		per_cpu(irqGet, cpu)[len++] = softirq_key;
+		per_cpu(irqGet, cpu)[len++] = value;
+	}
+
+	if (buffer)
+		*buffer = per_cpu(irqGet, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_irq_interface = {
+	.name = "irq",
+	.create_files = gator_events_irq_create_files,
+	.online = gator_events_irq_online,
+	.start = gator_events_irq_start,
+	.stop = gator_events_irq_stop,
+	.read = gator_events_irq_read,
+};
+
+int gator_events_irq_init(void)
+{
+	hardirq_key = gator_events_get_key();
+	softirq_key = gator_events_get_key();
+
+	hardirq_enabled = 0;
+	softirq_enabled = 0;
+
+	return gator_events_install(&gator_events_irq_interface);
+}
diff --git a/drivers/gator/gator_events_l2c-310.c b/drivers/gator/gator_events_l2c-310.c
new file mode 100644
index 00000000000..de3b383ad07
--- /dev/null
+++ b/drivers/gator/gator_events_l2c-310.c
@@ -0,0 +1,209 @@
+/**
+ * l2c310 (L2 Cache Controller) event counters for gator
+ *
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#if defined(CONFIG_OF)
+#include <linux/of.h>
+#include <linux/of_address.h>
+#endif
+#include <asm/hardware/cache-l2x0.h>
+
+#include "gator.h"
+
+#define L2C310_COUNTERS_NUM 2
+
+static struct {
+	unsigned long enabled;
+	unsigned long event;
+	unsigned long key;
+} l2c310_counters[L2C310_COUNTERS_NUM];
+
+static int l2c310_buffer[L2C310_COUNTERS_NUM * 2];
+
+static void __iomem *l2c310_base;
+
+static void gator_events_l2c310_reset_counters(void)
+{
+	u32 val = readl(l2c310_base + L2X0_EVENT_CNT_CTRL);
+
+	val |= ((1 << L2C310_COUNTERS_NUM) - 1) << 1;
+
+	writel(val, l2c310_base + L2X0_EVENT_CNT_CTRL);
+}
+
+static int gator_events_l2c310_create_files(struct super_block *sb,
+					    struct dentry *root)
+{
+	int i;
+
+	for (i = 0; i < L2C310_COUNTERS_NUM; i++) {
+		char buf[16];
+		struct dentry *dir;
+
+		snprintf(buf, sizeof(buf), "L2C-310_cnt%d", i);
+		dir = gatorfs_mkdir(sb, root, buf);
+		if (WARN_ON(!dir))
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled",
+				     &l2c310_counters[i].enabled);
+		gatorfs_create_ulong(sb, dir, "event",
+				     &l2c310_counters[i].event);
+		gatorfs_create_ro_ulong(sb, dir, "key",
+					&l2c310_counters[i].key);
+	}
+
+	return 0;
+}
+
+static int gator_events_l2c310_start(void)
+{
+	static const unsigned long l2x0_event_cntx_cfg[L2C310_COUNTERS_NUM] = {
+		L2X0_EVENT_CNT0_CFG,
+		L2X0_EVENT_CNT1_CFG,
+	};
+	int i;
+
+	/* Counter event sources */
+	for (i = 0; i < L2C310_COUNTERS_NUM; i++)
+		writel((l2c310_counters[i].event & 0xf) << 2,
+		       l2c310_base + l2x0_event_cntx_cfg[i]);
+
+	gator_events_l2c310_reset_counters();
+
+	/* Event counter enable */
+	writel(1, l2c310_base + L2X0_EVENT_CNT_CTRL);
+
+	return 0;
+}
+
+static void gator_events_l2c310_stop(void)
+{
+	/* Event counter disable */
+	writel(0, l2c310_base + L2X0_EVENT_CNT_CTRL);
+}
+
+static int gator_events_l2c310_read(int **buffer, bool sched_switch)
+{
+	static const unsigned long l2x0_event_cntx_val[L2C310_COUNTERS_NUM] = {
+		L2X0_EVENT_CNT0_VAL,
+		L2X0_EVENT_CNT1_VAL,
+	};
+	int i;
+	int len = 0;
+
+	if (!on_primary_core())
+		return 0;
+
+	for (i = 0; i < L2C310_COUNTERS_NUM; i++) {
+		if (l2c310_counters[i].enabled) {
+			l2c310_buffer[len++] = l2c310_counters[i].key;
+			l2c310_buffer[len++] = readl(l2c310_base +
+						     l2x0_event_cntx_val[i]);
+		}
+	}
+
+	/* l2c310 counters are saturating, not wrapping in case of overflow */
+	gator_events_l2c310_reset_counters();
+
+	if (buffer)
+		*buffer = l2c310_buffer;
+
+	return len;
+}
+
+static struct gator_interface gator_events_l2c310_interface = {
+	.name = "l2c-310",
+	.create_files = gator_events_l2c310_create_files,
+	.start = gator_events_l2c310_start,
+	.stop = gator_events_l2c310_stop,
+	.read = gator_events_l2c310_read,
+};
+
+#define L2C310_ADDR_PROBE (~0)
+
+MODULE_PARM_DESC(l2c310_addr, "L2C310 physical base address (0 to disable)");
+static unsigned long l2c310_addr = L2C310_ADDR_PROBE;
+module_param(l2c310_addr, ulong, 0444);
+
+static void __iomem *gator_events_l2c310_probe(void)
+{
+	phys_addr_t variants[] = {
+#if defined(CONFIG_ARCH_EXYNOS4) || defined(CONFIG_ARCH_S5PV310)
+		0x10502000,
+#endif
+#if defined(CONFIG_ARCH_OMAP4)
+		0x48242000,
+#endif
+#if defined(CONFIG_ARCH_TEGRA)
+		0x50043000,
+#endif
+#if defined(CONFIG_ARCH_U8500)
+		0xa0412000,
+#endif
+#if defined(CONFIG_ARCH_VEXPRESS)
+		0x1e00a000, /* A9x4 core tile (HBI-0191) */
+		0x2c0f0000, /* New memory map tiles */
+#endif
+	};
+	int i;
+	void __iomem *base;
+#if defined(CONFIG_OF)
+	struct device_node *node = of_find_all_nodes(NULL);
+
+	if (node) {
+		of_node_put(node);
+
+		node = of_find_compatible_node(NULL, NULL, "arm,pl310-cache");
+		base = of_iomap(node, 0);
+		of_node_put(node);
+
+		return base;
+	}
+#endif
+
+	for (i = 0; i < ARRAY_SIZE(variants); i++) {
+		base = ioremap(variants[i], SZ_4K);
+		if (base) {
+			u32 cache_id = readl(base + L2X0_CACHE_ID);
+
+			if ((cache_id & 0xff0003c0) == 0x410000c0)
+				return base;
+
+			iounmap(base);
+		}
+	}
+
+	return NULL;
+}
+
+int gator_events_l2c310_init(void)
+{
+	int i;
+
+	if (gator_cpuid() != CORTEX_A5 && gator_cpuid() != CORTEX_A9)
+		return -1;
+
+	if (l2c310_addr == L2C310_ADDR_PROBE)
+		l2c310_base = gator_events_l2c310_probe();
+	else if (l2c310_addr)
+		l2c310_base = ioremap(l2c310_addr, SZ_4K);
+
+	if (!l2c310_base)
+		return -1;
+
+	for (i = 0; i < L2C310_COUNTERS_NUM; i++) {
+		l2c310_counters[i].enabled = 0;
+		l2c310_counters[i].key = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_l2c310_interface);
+}
diff --git a/drivers/gator/gator_events_mali_4xx.c b/drivers/gator/gator_events_mali_4xx.c
new file mode 100644
index 00000000000..fb3909a004d
--- /dev/null
+++ b/drivers/gator/gator_events_mali_4xx.c
@@ -0,0 +1,624 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+
+#include "linux/mali_linux_trace.h"
+
+#include "gator_events_mali_common.h"
+#include "gator_events_mali_4xx.h"
+
+/*
+* There have been four different variants of the comms between gator and Mali depending on driver version:
+* # | DDK vsn range             | Support                                                             | Notes
+*
+* 1 | (obsolete)                | No software counter support                                         | Obsolete patches
+* 2 | (obsolete)                | Tracepoint called for each separate s/w counter value as it appears | Obsolete patches
+* 3 | r3p0-04rel0 - r3p2-01rel2 | Single tracepoint for all s/w counters in a bundle.                 |
+* 4 | r3p2-01rel3 - date        | As above but with extensions for MP devices (Mali-450)              | At least r4p0-00rel1
+*/
+
+#if !defined(GATOR_MALI_INTERFACE_STYLE)
+#define GATOR_MALI_INTERFACE_STYLE (4)
+#endif
+
+#if GATOR_MALI_INTERFACE_STYLE == 1
+#error GATOR_MALI_INTERFACE_STYLE 1 is obsolete
+#elif GATOR_MALI_INTERFACE_STYLE == 2
+#error GATOR_MALI_INTERFACE_STYLE 2 is obsolete
+#elif GATOR_MALI_INTERFACE_STYLE >= 3
+/* Valid GATOR_MALI_INTERFACE_STYLE */
+#else
+#error Unknown GATOR_MALI_INTERFACE_STYLE option.
+#endif
+
+#if GATOR_MALI_INTERFACE_STYLE < 4
+#include "mali/mali_mjollnir_profiling_gator_api.h"
+#else
+#include "mali/mali_utgard_profiling_gator_api.h"
+#endif
+
+/*
+ * Check that the MALI_SUPPORT define is set to one of the allowable device codes.
+ */
+#if (MALI_SUPPORT != MALI_4xx)
+#error MALI_SUPPORT set to an invalid device code: expecting MALI_4xx
+#endif
+
+static const char mali_name[] = "4xx";
+
+/* gatorfs variables for counter enable state,
+ * the event the counter should count and the
+ * 'key' (a unique id set by gatord and returned
+ * by gator.ko)
+ */
+static unsigned long counter_enabled[NUMBER_OF_EVENTS];
+static unsigned long counter_event[NUMBER_OF_EVENTS];
+static unsigned long counter_key[NUMBER_OF_EVENTS];
+
+/* The data we have recorded */
+static atomic_t counter_data[NUMBER_OF_EVENTS];
+
+/* An array used to return the data we recorded
+ * as key,value pairs hence the *2
+ */
+static int counter_dump[NUMBER_OF_EVENTS * 2];
+static int counter_prev[NUMBER_OF_EVENTS];
+static bool prev_set[NUMBER_OF_EVENTS];
+
+/* Note whether tracepoints have been registered */
+static int trace_registered;
+
+/*
+ * These numbers define the actual numbers of each block type that exist in the system. Initially
+ * these are set to the maxima defined above; if the driver is capable of being queried (newer
+ * drivers only) then the values may be revised.
+ */
+static unsigned int n_vp_cores = MAX_NUM_VP_CORES;
+static unsigned int n_l2_cores = MAX_NUM_L2_CACHE_CORES;
+static unsigned int n_fp_cores = MAX_NUM_FP_CORES;
+
+extern struct mali_counter mali_activity[2];
+static const char *const mali_activity_names[] = {
+	"fragment",
+	"vertex",
+};
+
+/**
+ * Returns non-zero if the given counter ID is an activity counter.
+ */
+static inline int is_activity_counter(unsigned int event_id)
+{
+	return (event_id >= FIRST_ACTIVITY_EVENT &&
+		event_id <= LAST_ACTIVITY_EVENT);
+}
+
+/**
+ * Returns non-zero if the given counter ID is a hardware counter.
+ */
+static inline int is_hw_counter(unsigned int event_id)
+{
+	return (event_id >= FIRST_HW_COUNTER && event_id <= LAST_HW_COUNTER);
+}
+
+/* Probe for hardware counter events */
+GATOR_DEFINE_PROBE(mali_hw_counter, TP_PROTO(unsigned int event_id, unsigned int value))
+{
+	if (is_hw_counter(event_id))
+		atomic_add(value, &counter_data[event_id]);
+}
+
+GATOR_DEFINE_PROBE(mali_sw_counters, TP_PROTO(pid_t pid, pid_t tid, void *surface_id, unsigned int *counters))
+{
+	u32 i;
+
+	/* Copy over the values for those counters which are enabled. */
+	for (i = FIRST_SW_COUNTER; i <= LAST_SW_COUNTER; i++) {
+		if (counter_enabled[i])
+			atomic_add(counters[i - FIRST_SW_COUNTER], &counter_data[i]);
+	}
+}
+
+/**
+ * Create a single filesystem entry for a specified event.
+ * @param sb the superblock
+ * @param root Filesystem root
+ * @param name The name of the entry to create
+ * @param event The ID of the event
+ * @param create_event_item boolean indicating whether to create an 'event' filesystem entry. True to create.
+ *
+ * @return 0 if ok, non-zero if the create failed.
+ */
+static int create_fs_entry(struct super_block *sb, struct dentry *root, const char *name, int event, int create_event_item)
+{
+	struct dentry *dir;
+
+	dir = gatorfs_mkdir(sb, root, name);
+
+	if (!dir)
+		return -1;
+
+	if (create_event_item)
+		gatorfs_create_ulong(sb, dir, "event", &counter_event[event]);
+
+	gatorfs_create_ulong(sb, dir, "enabled", &counter_enabled[event]);
+	gatorfs_create_ro_ulong(sb, dir, "key", &counter_key[event]);
+
+	return 0;
+}
+
+#if GATOR_MALI_INTERFACE_STYLE > 3
+/*
+ * Read the version info structure if available
+ */
+static void initialise_version_info(void)
+{
+	void (*mali_profiling_get_mali_version_symbol)(struct _mali_profiling_mali_version *values);
+
+	mali_profiling_get_mali_version_symbol = symbol_get(_mali_profiling_get_mali_version);
+
+	if (mali_profiling_get_mali_version_symbol) {
+		struct _mali_profiling_mali_version version_info;
+
+		pr_debug("gator: mali online _mali_profiling_get_mali_version symbol @ %p\n",
+				mali_profiling_get_mali_version_symbol);
+
+		/*
+		 * Revise the number of each different core type using information derived from the DDK.
+		 */
+		mali_profiling_get_mali_version_symbol(&version_info);
+
+		n_fp_cores = version_info.num_of_fp_cores;
+		n_vp_cores = version_info.num_of_vp_cores;
+		n_l2_cores = version_info.num_of_l2_cores;
+
+		/* Release the function - we're done with it. */
+		symbol_put(_mali_profiling_get_mali_version);
+	} else {
+		pr_err("gator: mali online _mali_profiling_get_mali_version symbol not found\n");
+		pr_err("gator:  check your Mali DDK version versus the GATOR_MALI_INTERFACE_STYLE setting\n");
+	}
+}
+#endif
+
+static int create_files(struct super_block *sb, struct dentry *root)
+{
+	int event;
+
+	char buf[40];
+	int core_id;
+	int counter_number;
+
+	pr_debug("gator: Initialising counters with style = %d\n", GATOR_MALI_INTERFACE_STYLE);
+
+#if GATOR_MALI_INTERFACE_STYLE > 3
+	/*
+	 * Initialise first: this sets up the number of cores available (on compatible DDK versions).
+	 * Ideally this would not need guarding but other parts of the code depend on the interface style being set
+	 * correctly; if it is not then the system can enter an inconsistent state.
+	 */
+	initialise_version_info();
+#endif
+
+	mali_activity[0].cores = n_fp_cores;
+	mali_activity[1].cores = n_vp_cores;
+	for (event = 0; event < ARRAY_SIZE(mali_activity); event++) {
+		if (gator_mali_create_file_system(mali_name, mali_activity_names[event], sb, root, &mali_activity[event], NULL) != 0)
+			return -1;
+	}
+
+	/* Vertex processor counters */
+	for (core_id = 0; core_id < n_vp_cores; core_id++) {
+		int activity_counter_id = ACTIVITY_VP_0;
+
+		snprintf(buf, sizeof(buf), "ARM_Mali-%s_VP_%d_active", mali_name, core_id);
+		if (create_fs_entry(sb, root, buf, activity_counter_id, 0) != 0)
+			return -1;
+
+		for (counter_number = 0; counter_number < 2; counter_number++) {
+			int counter_id = COUNTER_VP_0_C0 + (2 * core_id) + counter_number;
+
+			snprintf(buf, sizeof(buf), "ARM_Mali-%s_VP_%d_cnt%d", mali_name, core_id, counter_number);
+			if (create_fs_entry(sb, root, buf, counter_id, 1) != 0)
+				return -1;
+		}
+	}
+
+	/* Fragment processors' counters */
+	for (core_id = 0; core_id < n_fp_cores; core_id++) {
+		int activity_counter_id = ACTIVITY_FP_0 + core_id;
+
+		snprintf(buf, sizeof(buf), "ARM_Mali-%s_FP_%d_active", mali_name, core_id);
+		if (create_fs_entry(sb, root, buf, activity_counter_id, 0) != 0)
+			return -1;
+
+		for (counter_number = 0; counter_number < 2; counter_number++) {
+			int counter_id = COUNTER_FP_0_C0 + (2 * core_id) + counter_number;
+
+			snprintf(buf, sizeof(buf), "ARM_Mali-%s_FP_%d_cnt%d", mali_name, core_id, counter_number);
+			if (create_fs_entry(sb, root, buf, counter_id, 1) != 0)
+				return -1;
+		}
+	}
+
+	/* L2 Cache counters */
+	for (core_id = 0; core_id < n_l2_cores; core_id++) {
+		for (counter_number = 0; counter_number < 2; counter_number++) {
+			int counter_id = COUNTER_L2_0_C0 + (2 * core_id) + counter_number;
+
+			snprintf(buf, sizeof(buf), "ARM_Mali-%s_L2_%d_cnt%d", mali_name, core_id, counter_number);
+			if (create_fs_entry(sb, root, buf, counter_id, 1) != 0)
+				return -1;
+		}
+	}
+
+	/* Now set up the software counter entries */
+	for (event = FIRST_SW_COUNTER; event <= LAST_SW_COUNTER; event++) {
+		snprintf(buf, sizeof(buf), "ARM_Mali-%s_SW_%d", mali_name, event - FIRST_SW_COUNTER);
+
+		if (create_fs_entry(sb, root, buf, event, 0) != 0)
+			return -1;
+	}
+
+	/* Now set up the special counter entries */
+	snprintf(buf, sizeof(buf), "ARM_Mali-%s_Filmstrip_cnt0", mali_name);
+	if (create_fs_entry(sb, root, buf, COUNTER_FILMSTRIP, 1) != 0)
+		return -1;
+
+#ifdef DVFS_REPORTED_BY_DDK
+	snprintf(buf, sizeof(buf), "ARM_Mali-%s_Frequency", mali_name);
+	if (create_fs_entry(sb, root, buf, COUNTER_FREQUENCY, 1) != 0)
+		return -1;
+
+	snprintf(buf, sizeof(buf), "ARM_Mali-%s_Voltage", mali_name);
+	if (create_fs_entry(sb, root, buf, COUNTER_VOLTAGE, 1) != 0)
+		return -1;
+#endif
+
+	return 0;
+}
+
+/*
+ * Local store for the get_counters entry point into the DDK.
+ * This is stored here since it is used very regularly.
+ */
+static void (*mali_get_counters)(unsigned int *, unsigned int *, unsigned int *, unsigned int *);
+static u32 (*mali_get_l2_counters)(struct _mali_profiling_l2_counter_values *values);
+
+/*
+ * Examine list of counters between two index limits and determine if any one is enabled.
+ * Returns 1 if any counter is enabled, 0 if none is.
+ */
+static int is_any_counter_enabled(unsigned int first_counter, unsigned int last_counter)
+{
+	unsigned int i;
+
+	for (i = first_counter; i <= last_counter; i++) {
+		if (counter_enabled[i])
+			return 1;	/* At least one counter is enabled */
+	}
+
+	return 0;		/* No s/w counters enabled */
+}
+
+static void init_counters(unsigned int from_counter, unsigned int to_counter)
+{
+	unsigned int counter_id;
+
+	/* If a Mali driver is present and exporting the appropriate symbol
+	 * then we can request the HW counters (of which there are only 2)
+	 * be configured to count the desired events
+	 */
+	mali_profiling_set_event_type *mali_set_hw_event;
+
+	mali_set_hw_event = symbol_get(_mali_profiling_set_event);
+
+	if (mali_set_hw_event) {
+		pr_debug("gator: mali online _mali_profiling_set_event symbol @ %p\n", mali_set_hw_event);
+
+		for (counter_id = from_counter; counter_id <= to_counter; counter_id++) {
+			if (counter_enabled[counter_id])
+				mali_set_hw_event(counter_id, counter_event[counter_id]);
+			else
+				mali_set_hw_event(counter_id, 0xFFFFFFFF);
+		}
+
+		symbol_put(_mali_profiling_set_event);
+	} else {
+		pr_err("gator: mali online _mali_profiling_set_event symbol not found\n");
+	}
+}
+
+static void mali_counter_initialize(void)
+{
+	int i;
+
+	mali_profiling_control_type *mali_control;
+
+	init_counters(COUNTER_L2_0_C0, COUNTER_L2_0_C0 + (2 * n_l2_cores) - 1);
+	init_counters(COUNTER_VP_0_C0, COUNTER_VP_0_C0 + (2 * n_vp_cores) - 1);
+	init_counters(COUNTER_FP_0_C0, COUNTER_FP_0_C0 + (2 * n_fp_cores) - 1);
+
+	/* Generic control interface for Mali DDK. */
+	mali_control = symbol_get(_mali_profiling_control);
+	if (mali_control) {
+		/* The event attribute in the XML file keeps the actual frame rate. */
+		unsigned int rate = counter_event[COUNTER_FILMSTRIP] & 0xff;
+		unsigned int resize_factor = (counter_event[COUNTER_FILMSTRIP] >> 8) & 0xff;
+
+		pr_debug("gator: mali online _mali_profiling_control symbol @ %p\n", mali_control);
+
+		mali_control(SW_COUNTER_ENABLE, (is_any_counter_enabled(FIRST_SW_COUNTER, LAST_SW_COUNTER) ? 1 : 0));
+		mali_control(FBDUMP_CONTROL_ENABLE, (counter_enabled[COUNTER_FILMSTRIP] ? 1 : 0));
+		mali_control(FBDUMP_CONTROL_RATE, rate);
+		mali_control(FBDUMP_CONTROL_RESIZE_FACTOR, resize_factor);
+
+		pr_debug("gator: sent mali_control enabled=%d, rate=%d\n", (counter_enabled[COUNTER_FILMSTRIP] ? 1 : 0), rate);
+
+		symbol_put(_mali_profiling_control);
+	} else {
+		pr_err("gator: mali online _mali_profiling_control symbol not found\n");
+	}
+
+	mali_get_counters = symbol_get(_mali_profiling_get_counters);
+	if (mali_get_counters)
+		pr_debug("gator: mali online _mali_profiling_get_counters symbol @ %p\n", mali_get_counters);
+	else
+		pr_debug("gator: mali _mali_profiling_get_counters symbol not defined\n");
+
+	mali_get_l2_counters = symbol_get(_mali_profiling_get_l2_counters);
+	if (mali_get_l2_counters)
+		pr_debug("gator: mali online _mali_profiling_get_l2_counters symbol @ %p\n", mali_get_l2_counters);
+	else
+		pr_debug("gator: mali _mali_profiling_get_l2_counters symbol not defined\n");
+
+	if (!mali_get_counters && !mali_get_l2_counters) {
+		pr_err("gator: no L2 counters available\n");
+		n_l2_cores = 0;
+	}
+
+	/* Clear counters in the start */
+	for (i = 0; i < NUMBER_OF_EVENTS; i++) {
+		atomic_set(&counter_data[i], 0);
+		prev_set[i] = false;
+	}
+}
+
+static void mali_counter_deinitialize(void)
+{
+	mali_profiling_set_event_type *mali_set_hw_event;
+	mali_profiling_control_type *mali_control;
+
+	mali_set_hw_event = symbol_get(_mali_profiling_set_event);
+
+	if (mali_set_hw_event) {
+		int i;
+
+		pr_debug("gator: mali offline _mali_profiling_set_event symbol @ %p\n", mali_set_hw_event);
+		for (i = FIRST_HW_COUNTER; i <= LAST_HW_COUNTER; i++)
+			mali_set_hw_event(i, 0xFFFFFFFF);
+
+		symbol_put(_mali_profiling_set_event);
+	} else {
+		pr_err("gator: mali offline _mali_profiling_set_event symbol not found\n");
+	}
+
+	/* Generic control interface for Mali DDK. */
+	mali_control = symbol_get(_mali_profiling_control);
+
+	if (mali_control) {
+		pr_debug("gator: mali offline _mali_profiling_control symbol @ %p\n", mali_control);
+
+		/* Reset the DDK state - disable counter collection */
+		mali_control(SW_COUNTER_ENABLE, 0);
+
+		mali_control(FBDUMP_CONTROL_ENABLE, 0);
+
+		symbol_put(_mali_profiling_control);
+	} else {
+		pr_err("gator: mali offline _mali_profiling_control symbol not found\n");
+	}
+
+	if (mali_get_counters)
+		symbol_put(_mali_profiling_get_counters);
+
+	if (mali_get_l2_counters)
+		symbol_put(_mali_profiling_get_l2_counters);
+}
+
+static int start(void)
+{
+	/* register tracepoints */
+	if (GATOR_REGISTER_TRACE(mali_hw_counter)) {
+		pr_err("gator: mali_hw_counter tracepoint failed to activate\n");
+		return -1;
+	}
+
+	/* For Mali drivers with built-in support. */
+	if (GATOR_REGISTER_TRACE(mali_sw_counters)) {
+		pr_err("gator: mali_sw_counters tracepoint failed to activate\n");
+		return -1;
+	}
+
+	trace_registered = 1;
+
+	mali_counter_initialize();
+	return 0;
+}
+
+static void stop(void)
+{
+	unsigned int cnt;
+
+	pr_debug("gator: mali stop\n");
+
+	if (trace_registered) {
+		GATOR_UNREGISTER_TRACE(mali_hw_counter);
+
+		/* For Mali drivers with built-in support. */
+		GATOR_UNREGISTER_TRACE(mali_sw_counters);
+
+		pr_debug("gator: mali timeline tracepoint deactivated\n");
+
+		trace_registered = 0;
+	}
+
+	for (cnt = 0; cnt < NUMBER_OF_EVENTS; cnt++) {
+		counter_enabled[cnt] = 0;
+		counter_event[cnt] = 0;
+	}
+
+	mali_counter_deinitialize();
+}
+
+static void dump_counters(unsigned int from_counter, unsigned int to_counter, unsigned int *len)
+{
+	unsigned int counter_id;
+
+	for (counter_id = from_counter; counter_id <= to_counter; counter_id++) {
+		if (counter_enabled[counter_id]) {
+			unsigned int value;
+
+			counter_dump[(*len)++] = counter_key[counter_id];
+			value = atomic_read(&counter_data[counter_id]);
+			atomic_sub(value, &counter_data[counter_id]);
+			counter_dump[(*len)++] = value;
+		}
+	}
+}
+
+static int read(int **buffer, bool sched_switch)
+{
+	int len = 0;
+
+	if (!on_primary_core())
+		return 0;
+
+	/* Read the L2 C0 and C1 here. */
+	if (n_l2_cores > 0 && is_any_counter_enabled(COUNTER_L2_0_C0, COUNTER_L2_0_C0 + (2 * n_l2_cores))) {
+		unsigned int unavailable_l2_caches = 0;
+		struct _mali_profiling_l2_counter_values cache_values;
+		unsigned int cache_id;
+		struct _mali_profiling_core_counters *per_core;
+
+		/* Poke the driver to get the counter values - older style; only one L2 cache */
+		if (mali_get_l2_counters) {
+			unavailable_l2_caches = mali_get_l2_counters(&cache_values);
+		} else if (mali_get_counters) {
+			per_core = &cache_values.cores[0];
+			mali_get_counters(&per_core->source0, &per_core->value0, &per_core->source1, &per_core->value1);
+		} else {
+			/* This should never happen, as n_l2_caches is only set > 0 if one of the above functions is found. */
+		}
+
+		/* Fill in the two cache counter values for each cache block. */
+		for (cache_id = 0; cache_id < n_l2_cores; cache_id++) {
+			unsigned int counter_id_0 = COUNTER_L2_0_C0 + (2 * cache_id);
+			unsigned int counter_id_1 = counter_id_0 + 1;
+
+			if ((1 << cache_id) & unavailable_l2_caches)
+				continue; /* This cache is unavailable (powered-off, possibly). */
+
+			per_core = &cache_values.cores[cache_id];
+
+			if (counter_enabled[counter_id_0] && prev_set[counter_id_0]) {
+				/* Calculate and save src0's counter val0 */
+				counter_dump[len++] = counter_key[counter_id_0];
+				counter_dump[len++] = per_core->value0 - counter_prev[counter_id_0];
+			}
+
+			if (counter_enabled[counter_id_1] && prev_set[counter_id_1]) {
+				/* Calculate and save src1's counter val1 */
+				counter_dump[len++] = counter_key[counter_id_1];
+				counter_dump[len++] = per_core->value1 - counter_prev[counter_id_1];
+			}
+
+			/* Save the previous values for the counters. */
+			counter_prev[counter_id_0] = per_core->value0;
+			prev_set[counter_id_0] = true;
+			counter_prev[counter_id_1] = per_core->value1;
+			prev_set[counter_id_1] = true;
+		}
+	}
+
+	/* Process other (non-timeline) counters. */
+	dump_counters(COUNTER_VP_0_C0, COUNTER_VP_0_C0 + (2 * n_vp_cores) - 1, &len);
+	dump_counters(COUNTER_FP_0_C0, COUNTER_FP_0_C0 + (2 * n_fp_cores) - 1, &len);
+
+	dump_counters(FIRST_SW_COUNTER, LAST_SW_COUNTER, &len);
+
+#ifdef DVFS_REPORTED_BY_DDK
+	{
+		int cnt;
+		/*
+		 * Add in the voltage and frequency counters if enabled. Note
+		 * that, since these are actually passed as events, the counter
+		 * value should not be cleared.
+		 *
+		 * Intentionally use atomic_read as these are absolute counters
+		 */
+		cnt = COUNTER_FREQUENCY;
+		if (counter_enabled[cnt]) {
+			counter_dump[len++] = counter_key[cnt];
+			counter_dump[len++] = atomic_read(&counter_data[cnt]);
+		}
+
+		cnt = COUNTER_VOLTAGE;
+		if (counter_enabled[cnt]) {
+			counter_dump[len++] = counter_key[cnt];
+			counter_dump[len++] = atomic_read(&counter_data[cnt]);
+		}
+	}
+#endif
+
+	if (buffer)
+		*buffer = counter_dump;
+
+	return len;
+}
+
+static struct gator_interface gator_events_mali_interface = {
+	.name = "mali_4xx",
+	.create_files = create_files,
+	.start = start,
+	.stop = stop,
+	.read = read,
+};
+
+extern void gator_events_mali_log_dvfs_event(unsigned int frequency_mhz, unsigned int voltage_mv)
+{
+#ifdef DVFS_REPORTED_BY_DDK
+	/* Intentionally use atomic_set as these are absolute counters */
+	atomic_set(&counter_data[COUNTER_FREQUENCY], frequency_mhz);
+	atomic_set(&counter_data[COUNTER_VOLTAGE], voltage_mv);
+#endif
+}
+
+int gator_events_mali_init(void)
+{
+	unsigned int cnt;
+
+	pr_debug("gator: mali init\n");
+
+	gator_mali_initialise_counters(mali_activity, ARRAY_SIZE(mali_activity));
+
+	for (cnt = 0; cnt < NUMBER_OF_EVENTS; cnt++) {
+		counter_enabled[cnt] = 0;
+		counter_event[cnt] = 0;
+		counter_key[cnt] = gator_events_get_key();
+		atomic_set(&counter_data[cnt], 0);
+	}
+
+	trace_registered = 0;
+
+	return gator_events_install(&gator_events_mali_interface);
+}
diff --git a/drivers/gator/gator_events_mali_4xx.h b/drivers/gator/gator_events_mali_4xx.h
new file mode 100644
index 00000000000..8f6a870e6d0
--- /dev/null
+++ b/drivers/gator/gator_events_mali_4xx.h
@@ -0,0 +1,18 @@
+/**
+ * Copyright (C) ARM Limited 2011-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/*
+ * Header contains common definitions for the Mali-4xx processors.
+ */
+#if !defined(GATOR_EVENTS_MALI_4xx_H)
+#define GATOR_EVENTS_MALI_4xx_H
+
+extern void gator_events_mali_log_dvfs_event(unsigned int d0, unsigned int d1);
+
+#endif /* GATOR_EVENTS_MALI_4xx_H */
diff --git a/drivers/gator/gator_events_mali_common.c b/drivers/gator/gator_events_mali_common.c
new file mode 100644
index 00000000000..60fece814c2
--- /dev/null
+++ b/drivers/gator/gator_events_mali_common.c
@@ -0,0 +1,72 @@
+/**
+ * Copyright (C) ARM Limited 2012-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#include "gator_events_mali_common.h"
+
+extern int gator_mali_create_file_system(const char *mali_name, const char *event_name, struct super_block *sb, struct dentry *root, struct mali_counter *counter, unsigned long *event)
+{
+	int err;
+	char buf[255];
+	struct dentry *dir;
+
+	/* If the counter name is empty ignore it */
+	if (strlen(event_name) != 0) {
+		/* Set up the filesystem entry for this event. */
+		if (mali_name == NULL)
+			snprintf(buf, sizeof(buf), "ARM_Mali-%s", event_name);
+		else
+			snprintf(buf, sizeof(buf), "ARM_Mali-%s_%s", mali_name, event_name);
+
+		dir = gatorfs_mkdir(sb, root, buf);
+
+		if (dir == NULL) {
+			pr_err("gator: %s: error creating file system for: %s (%s)\n", mali_name, event_name, buf);
+			return -1;
+		}
+
+		err = gatorfs_create_ulong(sb, dir, "enabled", &counter->enabled);
+		if (err != 0) {
+			pr_err("gator: %s: error calling gatorfs_create_ulong for: %s (%s)\n", mali_name, event_name, buf);
+			return -1;
+		}
+		err = gatorfs_create_ro_ulong(sb, dir, "key", &counter->key);
+		if (err != 0) {
+			pr_err("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)\n", mali_name, event_name, buf);
+			return -1;
+		}
+		if (counter->cores != -1) {
+			err = gatorfs_create_ro_ulong(sb, dir, "cores", &counter->cores);
+			if (err != 0) {
+				pr_err("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)\n", mali_name, event_name, buf);
+				return -1;
+			}
+		}
+		if (event != NULL) {
+			err = gatorfs_create_ulong(sb, dir, "event", event);
+			if (err != 0) {
+				pr_err("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)\n", mali_name, event_name, buf);
+				return -1;
+			}
+		}
+	}
+
+	return 0;
+}
+
+extern void gator_mali_initialise_counters(struct mali_counter counters[], unsigned int n_counters)
+{
+	unsigned int cnt;
+
+	for (cnt = 0; cnt < n_counters; cnt++) {
+		struct mali_counter *counter = &counters[cnt];
+
+		counter->key = gator_events_get_key();
+		counter->enabled = 0;
+		counter->cores = -1;
+	}
+}
diff --git a/drivers/gator/gator_events_mali_common.h b/drivers/gator/gator_events_mali_common.h
new file mode 100644
index 00000000000..a4fc9d7d4cf
--- /dev/null
+++ b/drivers/gator/gator_events_mali_common.h
@@ -0,0 +1,77 @@
+/**
+ * Copyright (C) ARM Limited 2012-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#if !defined(GATOR_EVENTS_MALI_COMMON_H)
+#define GATOR_EVENTS_MALI_COMMON_H
+
+#include "gator.h"
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+
+/* Ensure that MALI_SUPPORT has been defined to something. */
+#ifndef MALI_SUPPORT
+#error MALI_SUPPORT not defined!
+#endif
+
+/* Values for the supported activity event types */
+#define ACTIVITY_START  (1)
+#define ACTIVITY_STOP   (2)
+
+/*
+ * Runtime state information for a counter.
+ */
+struct mali_counter {
+	/* 'key' (a unique id set by gatord and returned by gator.ko) */
+	unsigned long key;
+	/* counter enable state */
+	unsigned long enabled;
+	/* for activity counters, the number of cores, otherwise -1 */
+	unsigned long cores;
+};
+
+/*
+ * Mali-4xx
+ */
+typedef int mali_profiling_set_event_type(unsigned int, int);
+typedef void mali_profiling_control_type(unsigned int, unsigned int);
+
+/*
+ * Driver entry points for functions called directly by gator.
+ */
+extern int _mali_profiling_set_event(unsigned int, int);
+extern void _mali_profiling_control(unsigned int, unsigned int);
+extern void _mali_profiling_get_counters(unsigned int *, unsigned int *, unsigned int *, unsigned int *);
+
+/**
+ * Creates a filesystem entry under /dev/gator relating to the specified event name and key, and
+ * associate the key/enable values with this entry point.
+ *
+ * @param event_name The name of the event.
+ * @param sb Linux super block
+ * @param root Directory under which the entry will be created.
+ * @param counter_key Ptr to location which will be associated with the counter key.
+ * @param counter_enabled Ptr to location which will be associated with the counter enable state.
+ *
+ * @return 0 if entry point was created, non-zero if not.
+ */
+extern int gator_mali_create_file_system(const char *mali_name, const char *event_name, struct super_block *sb, struct dentry *root, struct mali_counter *counter, unsigned long *event);
+
+/**
+ * Initializes the counter array.
+ *
+ * @param keys The array of counters
+ * @param n_counters The number of entries in each of the arrays.
+ */
+extern void gator_mali_initialise_counters(struct mali_counter counters[], unsigned int n_counters);
+
+#endif /* GATOR_EVENTS_MALI_COMMON_H  */
diff --git a/drivers/gator/gator_events_mali_midgard.c b/drivers/gator/gator_events_mali_midgard.c
new file mode 100644
index 00000000000..5b84975f99e
--- /dev/null
+++ b/drivers/gator/gator_events_mali_midgard.c
@@ -0,0 +1,567 @@
+/**
+ * Copyright (C) ARM Limited 2011-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+
+#ifdef MALI_DIR_MIDGARD
+/* New DDK Directory structure with kernel/drivers/gpu/arm/midgard*/
+#include "mali_linux_trace.h"
+#else
+/* Old DDK Directory structure with kernel/drivers/gpu/arm/t6xx*/
+#include "linux/mali_linux_trace.h"
+#endif
+
+#include "gator_events_mali_common.h"
+
+/*
+ * Check that the MALI_SUPPORT define is set to one of the allowable device codes.
+ */
+#if (MALI_SUPPORT != MALI_MIDGARD)
+#error MALI_SUPPORT set to an invalid device code: expecting MALI_MIDGARD
+#endif
+
+static const char mali_name[] = "Midgard";
+
+/* Counters for Mali-Midgard:
+ *
+ *  - Timeline events
+ *    They are tracepoints, but instead of reporting a number they report a START/STOP event.
+ *    They are reported in Streamline as number of microseconds while that particular counter was active.
+ *
+ *  - SW counters
+ *    They are tracepoints reporting a particular number.
+ *    They are accumulated in sw_counter_data array until they are passed to Streamline, then they are zeroed.
+ *
+ *  - Accumulators
+ *    They are the same as software counters but their value is not zeroed.
+ */
+
+/* Timeline (start/stop) activity */
+static const char *const timeline_event_names[] = {
+	"PM_SHADER_0",
+	"PM_SHADER_1",
+	"PM_SHADER_2",
+	"PM_SHADER_3",
+	"PM_SHADER_4",
+	"PM_SHADER_5",
+	"PM_SHADER_6",
+	"PM_SHADER_7",
+	"PM_TILER_0",
+	"PM_L2_0",
+	"PM_L2_1",
+	"MMU_AS_0",
+	"MMU_AS_1",
+	"MMU_AS_2",
+	"MMU_AS_3"
+};
+
+enum {
+	PM_SHADER_0 = 0,
+	PM_SHADER_1,
+	PM_SHADER_2,
+	PM_SHADER_3,
+	PM_SHADER_4,
+	PM_SHADER_5,
+	PM_SHADER_6,
+	PM_SHADER_7,
+	PM_TILER_0,
+	PM_L2_0,
+	PM_L2_1,
+	MMU_AS_0,
+	MMU_AS_1,
+	MMU_AS_2,
+	MMU_AS_3
+};
+/* The number of shader blocks in the enum above */
+#define NUM_PM_SHADER (8)
+
+/* Software Counters */
+static const char *const software_counter_names[] = {
+	"MMU_PAGE_FAULT_0",
+	"MMU_PAGE_FAULT_1",
+	"MMU_PAGE_FAULT_2",
+	"MMU_PAGE_FAULT_3"
+};
+
+enum {
+	MMU_PAGE_FAULT_0 = 0,
+	MMU_PAGE_FAULT_1,
+	MMU_PAGE_FAULT_2,
+	MMU_PAGE_FAULT_3
+};
+
+/* Software Counters */
+static const char *const accumulators_names[] = {
+	"TOTAL_ALLOC_PAGES"
+};
+
+enum {
+	TOTAL_ALLOC_PAGES = 0
+};
+
+#define FIRST_TIMELINE_EVENT (0)
+#define NUMBER_OF_TIMELINE_EVENTS (sizeof(timeline_event_names) / sizeof(timeline_event_names[0]))
+#define FIRST_SOFTWARE_COUNTER (FIRST_TIMELINE_EVENT + NUMBER_OF_TIMELINE_EVENTS)
+#define NUMBER_OF_SOFTWARE_COUNTERS (sizeof(software_counter_names) / sizeof(software_counter_names[0]))
+#define FIRST_ACCUMULATOR (FIRST_SOFTWARE_COUNTER + NUMBER_OF_SOFTWARE_COUNTERS)
+#define NUMBER_OF_ACCUMULATORS (sizeof(accumulators_names) / sizeof(accumulators_names[0]))
+#define FILMSTRIP (NUMBER_OF_TIMELINE_EVENTS + NUMBER_OF_SOFTWARE_COUNTERS + NUMBER_OF_ACCUMULATORS)
+#define NUMBER_OF_EVENTS (NUMBER_OF_TIMELINE_EVENTS + NUMBER_OF_SOFTWARE_COUNTERS + NUMBER_OF_ACCUMULATORS + 1)
+
+/*
+ * gatorfs variables for counter enable state
+ */
+static struct mali_counter counters[NUMBER_OF_EVENTS];
+static unsigned long filmstrip_event;
+
+/* An array used to return the data we recorded
+ * as key,value pairs hence the *2
+ */
+static int counter_dump[NUMBER_OF_EVENTS * 2];
+
+/*
+ * Array holding counter start times (in ns) for each counter. A zero
+ * here indicates that the activity monitored by this counter is not
+ * running.
+ */
+static struct timespec timeline_event_starttime[NUMBER_OF_TIMELINE_EVENTS];
+
+/* The data we have recorded */
+static unsigned int timeline_data[NUMBER_OF_TIMELINE_EVENTS];
+static unsigned int sw_counter_data[NUMBER_OF_SOFTWARE_COUNTERS];
+static unsigned int accumulators_data[NUMBER_OF_ACCUMULATORS];
+
+/* Hold the previous timestamp, used to calculate the sample interval. */
+static struct timespec prev_timestamp;
+
+static unsigned long long previous_shader_bitmask;
+static unsigned long long previous_tiler_bitmask;
+static unsigned long long previous_l2_bitmask;
+
+/**
+ * Returns the timespan (in microseconds) between the two specified timestamps.
+ *
+ * @param start Ptr to the start timestamp
+ * @param end Ptr to the end timestamp
+ *
+ * @return Number of microseconds between the two timestamps (can be negative if start follows end).
+ */
+static inline long get_duration_us(const struct timespec *start, const struct timespec *end)
+{
+	long event_duration_us = (end->tv_nsec - start->tv_nsec) / 1000;
+
+	event_duration_us += (end->tv_sec - start->tv_sec) * 1000000;
+
+	return event_duration_us;
+}
+
+static void record_timeline_event(unsigned int timeline_index, unsigned int type)
+{
+	struct timespec event_timestamp;
+	struct timespec *event_start = &timeline_event_starttime[timeline_index];
+
+	switch (type) {
+	case ACTIVITY_START:
+		/* Get the event time... */
+		getnstimeofday(&event_timestamp);
+
+		/* Remember the start time if the activity is not already started */
+		if (event_start->tv_sec == 0)
+			*event_start = event_timestamp;	/* Structure copy */
+		break;
+
+	case ACTIVITY_STOP:
+		/* if the counter was started... */
+		if (event_start->tv_sec != 0) {
+			/* Get the event time... */
+			getnstimeofday(&event_timestamp);
+
+			/* Accumulate the duration in us */
+			timeline_data[timeline_index] += get_duration_us(event_start, &event_timestamp);
+
+			/* Reset the start time to indicate the activity is stopped. */
+			event_start->tv_sec = 0;
+		}
+		break;
+
+	default:
+		/* Other activity events are ignored. */
+		break;
+	}
+}
+
+/*
+ * Documentation about the following tracepoints is in mali_linux_trace.h
+ */
+
+GATOR_DEFINE_PROBE(mali_pm_status, TP_PROTO(unsigned int event_id, unsigned long long value))
+{
+#define SHADER_PRESENT_LO       0x100	/* (RO) Shader core present bitmap, low word */
+#define TILER_PRESENT_LO        0x110	/* (RO) Tiler core present bitmap, low word */
+#define L2_PRESENT_LO           0x120	/* (RO) Level 2 cache present bitmap, low word */
+#define BIT_AT(value, pos) ((value >> pos) & 1)
+
+	switch (event_id) {
+	case SHADER_PRESENT_LO:
+		{
+			unsigned long long changed_bitmask = previous_shader_bitmask ^ value;
+			int pos;
+
+			for (pos = 0; pos < NUM_PM_SHADER; ++pos) {
+				if (BIT_AT(changed_bitmask, pos))
+					record_timeline_event(PM_SHADER_0 + pos, BIT_AT(value, pos) ? ACTIVITY_START : ACTIVITY_STOP);
+			}
+
+			previous_shader_bitmask = value;
+			break;
+		}
+
+	case TILER_PRESENT_LO:
+		{
+			unsigned long long changed = previous_tiler_bitmask ^ value;
+
+			if (BIT_AT(changed, 0))
+				record_timeline_event(PM_TILER_0, BIT_AT(value, 0) ? ACTIVITY_START : ACTIVITY_STOP);
+
+			previous_tiler_bitmask = value;
+			break;
+		}
+
+	case L2_PRESENT_LO:
+		{
+			unsigned long long changed = previous_l2_bitmask ^ value;
+
+			if (BIT_AT(changed, 0))
+				record_timeline_event(PM_L2_0, BIT_AT(value, 0) ? ACTIVITY_START : ACTIVITY_STOP);
+			if (BIT_AT(changed, 4))
+				record_timeline_event(PM_L2_1, BIT_AT(value, 4) ? ACTIVITY_START : ACTIVITY_STOP);
+
+			previous_l2_bitmask = value;
+			break;
+		}
+
+	default:
+		/* No other blocks are supported at present */
+		break;
+	}
+
+#undef SHADER_PRESENT_LO
+#undef TILER_PRESENT_LO
+#undef L2_PRESENT_LO
+#undef BIT_AT
+}
+
+GATOR_DEFINE_PROBE(mali_page_fault_insert_pages, TP_PROTO(int event_id, unsigned long value))
+{
+	/* We add to the previous since we may receive many tracepoints in one sample period */
+	sw_counter_data[MMU_PAGE_FAULT_0 + event_id] += value;
+}
+
+GATOR_DEFINE_PROBE(mali_mmu_as_in_use, TP_PROTO(int event_id))
+{
+	record_timeline_event(MMU_AS_0 + event_id, ACTIVITY_START);
+}
+
+GATOR_DEFINE_PROBE(mali_mmu_as_released, TP_PROTO(int event_id))
+{
+	record_timeline_event(MMU_AS_0 + event_id, ACTIVITY_STOP);
+}
+
+GATOR_DEFINE_PROBE(mali_total_alloc_pages_change, TP_PROTO(long long int event_id))
+{
+	accumulators_data[TOTAL_ALLOC_PAGES] = event_id;
+}
+
+static int create_files(struct super_block *sb, struct dentry *root)
+{
+	int event;
+	/*
+	 * Create the filesystem for all events
+	 */
+	int counter_index = 0;
+	mali_profiling_control_type *mali_control;
+
+	for (event = FIRST_TIMELINE_EVENT; event < FIRST_TIMELINE_EVENT + NUMBER_OF_TIMELINE_EVENTS; event++) {
+		if (gator_mali_create_file_system(mali_name, timeline_event_names[counter_index], sb, root, &counters[event], NULL) != 0)
+			return -1;
+		counter_index++;
+	}
+	counter_index = 0;
+	for (event = FIRST_SOFTWARE_COUNTER; event < FIRST_SOFTWARE_COUNTER + NUMBER_OF_SOFTWARE_COUNTERS; event++) {
+		if (gator_mali_create_file_system(mali_name, software_counter_names[counter_index], sb, root, &counters[event], NULL) != 0)
+			return -1;
+		counter_index++;
+	}
+	counter_index = 0;
+	for (event = FIRST_ACCUMULATOR; event < FIRST_ACCUMULATOR + NUMBER_OF_ACCUMULATORS; event++) {
+		if (gator_mali_create_file_system(mali_name, accumulators_names[counter_index], sb, root, &counters[event], NULL) != 0)
+			return -1;
+		counter_index++;
+	}
+
+	mali_control = symbol_get(_mali_profiling_control);
+	if (mali_control) {
+		if (gator_mali_create_file_system(mali_name, "Filmstrip_cnt0", sb, root, &counters[FILMSTRIP], &filmstrip_event) != 0)
+			return -1;
+		symbol_put(_mali_profiling_control);
+	}
+
+	return 0;
+}
+
+static int register_tracepoints(void)
+{
+	if (GATOR_REGISTER_TRACE(mali_pm_status)) {
+		pr_err("gator: Mali-Midgard: mali_pm_status tracepoint failed to activate\n");
+		return 0;
+	}
+
+	if (GATOR_REGISTER_TRACE(mali_page_fault_insert_pages)) {
+		pr_err("gator: Mali-Midgard: mali_page_fault_insert_pages tracepoint failed to activate\n");
+		return 0;
+	}
+
+	if (GATOR_REGISTER_TRACE(mali_mmu_as_in_use)) {
+		pr_err("gator: Mali-Midgard: mali_mmu_as_in_use tracepoint failed to activate\n");
+		return 0;
+	}
+
+	if (GATOR_REGISTER_TRACE(mali_mmu_as_released)) {
+		pr_err("gator: Mali-Midgard: mali_mmu_as_released tracepoint failed to activate\n");
+		return 0;
+	}
+
+	if (GATOR_REGISTER_TRACE(mali_total_alloc_pages_change)) {
+		pr_err("gator: Mali-Midgard: mali_total_alloc_pages_change tracepoint failed to activate\n");
+		return 0;
+	}
+
+	pr_debug("gator: Mali-Midgard: start\n");
+	pr_debug("gator: Mali-Midgard: mali_pm_status probe is at %p\n", &probe_mali_pm_status);
+	pr_debug("gator: Mali-Midgard: mali_page_fault_insert_pages probe is at %p\n", &probe_mali_page_fault_insert_pages);
+	pr_debug("gator: Mali-Midgard: mali_mmu_as_in_use probe is at %p\n", &probe_mali_mmu_as_in_use);
+	pr_debug("gator: Mali-Midgard: mali_mmu_as_released probe is at %p\n", &probe_mali_mmu_as_released);
+	pr_debug("gator: Mali-Midgard: mali_total_alloc_pages_change probe is at %p\n", &probe_mali_total_alloc_pages_change);
+
+	return 1;
+}
+
+static int start(void)
+{
+	unsigned int cnt;
+	mali_profiling_control_type *mali_control;
+
+	previous_shader_bitmask = 0;
+	previous_tiler_bitmask = 0;
+	previous_l2_bitmask = 0;
+
+	/* Clean all data for the next capture */
+	for (cnt = 0; cnt < NUMBER_OF_TIMELINE_EVENTS; cnt++) {
+		timeline_event_starttime[cnt].tv_sec = timeline_event_starttime[cnt].tv_nsec = 0;
+		timeline_data[cnt] = 0;
+	}
+
+	for (cnt = 0; cnt < NUMBER_OF_SOFTWARE_COUNTERS; cnt++)
+		sw_counter_data[cnt] = 0;
+
+	for (cnt = 0; cnt < NUMBER_OF_ACCUMULATORS; cnt++)
+		accumulators_data[cnt] = 0;
+
+	/* Register tracepoints */
+	if (register_tracepoints() == 0)
+		return -1;
+
+	/* Generic control interface for Mali DDK. */
+	mali_control = symbol_get(_mali_profiling_control);
+	if (mali_control) {
+		/* The event attribute in the XML file keeps the actual frame rate. */
+		unsigned int enabled = counters[FILMSTRIP].enabled ? 1 : 0;
+		unsigned int rate = filmstrip_event & 0xff;
+		unsigned int resize_factor = (filmstrip_event >> 8) & 0xff;
+
+		pr_debug("gator: mali online _mali_profiling_control symbol @ %p\n", mali_control);
+
+#define FBDUMP_CONTROL_ENABLE (1)
+#define FBDUMP_CONTROL_RATE (2)
+#define FBDUMP_CONTROL_RESIZE_FACTOR (4)
+		mali_control(FBDUMP_CONTROL_ENABLE, enabled);
+		mali_control(FBDUMP_CONTROL_RATE, rate);
+		mali_control(FBDUMP_CONTROL_RESIZE_FACTOR, resize_factor);
+
+		pr_debug("gator: sent mali_control enabled=%d, rate=%d, resize_factor=%d\n", enabled, rate, resize_factor);
+
+		symbol_put(_mali_profiling_control);
+	} else {
+		pr_err("gator: mali online _mali_profiling_control symbol not found\n");
+	}
+
+	/*
+	 * Set the first timestamp for calculating the sample interval. The first interval could be quite long,
+	 * since it will be the time between 'start' and the first 'read'.
+	 * This means that timeline values will be divided by a big number for the first sample.
+	 */
+	getnstimeofday(&prev_timestamp);
+
+	return 0;
+}
+
+static void stop(void)
+{
+	mali_profiling_control_type *mali_control;
+
+	pr_debug("gator: Mali-Midgard: stop\n");
+
+	/*
+	 * It is safe to unregister traces even if they were not successfully
+	 * registered, so no need to check.
+	 */
+	GATOR_UNREGISTER_TRACE(mali_pm_status);
+	pr_debug("gator: Mali-Midgard: mali_pm_status tracepoint deactivated\n");
+
+	GATOR_UNREGISTER_TRACE(mali_page_fault_insert_pages);
+	pr_debug("gator: Mali-Midgard: mali_page_fault_insert_pages tracepoint deactivated\n");
+
+	GATOR_UNREGISTER_TRACE(mali_mmu_as_in_use);
+	pr_debug("gator: Mali-Midgard: mali_mmu_as_in_use tracepoint deactivated\n");
+
+	GATOR_UNREGISTER_TRACE(mali_mmu_as_released);
+	pr_debug("gator: Mali-Midgard: mali_mmu_as_released tracepoint deactivated\n");
+
+	GATOR_UNREGISTER_TRACE(mali_total_alloc_pages_change);
+	pr_debug("gator: Mali-Midgard: mali_total_alloc_pages_change tracepoint deactivated\n");
+
+	/* Generic control interface for Mali DDK. */
+	mali_control = symbol_get(_mali_profiling_control);
+	if (mali_control) {
+		pr_debug("gator: mali offline _mali_profiling_control symbol @ %p\n", mali_control);
+
+		mali_control(FBDUMP_CONTROL_ENABLE, 0);
+
+		symbol_put(_mali_profiling_control);
+	} else {
+		pr_err("gator: mali offline _mali_profiling_control symbol not found\n");
+	}
+}
+
+static int read(int **buffer, bool sched_switch)
+{
+	int cnt;
+	int len = 0;
+	long sample_interval_us = 0;
+	struct timespec read_timestamp;
+
+	if (!on_primary_core())
+		return 0;
+
+	/* Get the start of this sample period. */
+	getnstimeofday(&read_timestamp);
+
+	/*
+	 * Calculate the sample interval if the previous sample time is valid.
+	 * We use tv_sec since it will not be 0.
+	 */
+	if (prev_timestamp.tv_sec != 0)
+		sample_interval_us = get_duration_us(&prev_timestamp, &read_timestamp);
+
+	/* Structure copy. Update the previous timestamp. */
+	prev_timestamp = read_timestamp;
+
+	/*
+	 * Report the timeline counters (ACTIVITY_START/STOP)
+	 */
+	for (cnt = FIRST_TIMELINE_EVENT; cnt < (FIRST_TIMELINE_EVENT + NUMBER_OF_TIMELINE_EVENTS); cnt++) {
+		struct mali_counter *counter = &counters[cnt];
+
+		if (counter->enabled) {
+			const int index = cnt - FIRST_TIMELINE_EVENT;
+			unsigned int value;
+
+			/* If the activity is still running, reset its start time to the
+			 * start of this sample period to correct the count. Add the
+			 * time up to the end of the sample onto the count.
+			 */
+			if (timeline_event_starttime[index].tv_sec != 0) {
+				const long event_duration = get_duration_us(&timeline_event_starttime[index], &read_timestamp);
+
+				timeline_data[index] += event_duration;
+				timeline_event_starttime[index] = read_timestamp;	/* Activity is still running. */
+			}
+
+			if (sample_interval_us != 0) {
+				/* Convert the counter to a percent-of-sample value */
+				value = (timeline_data[index] * 100) / sample_interval_us;
+			} else {
+				pr_debug("gator: Mali-Midgard: setting value to zero\n");
+				value = 0;
+			}
+
+			/* Clear the counter value ready for the next sample. */
+			timeline_data[index] = 0;
+
+			counter_dump[len++] = counter->key;
+			counter_dump[len++] = value;
+		}
+	}
+
+	/* Report the software counters */
+	for (cnt = FIRST_SOFTWARE_COUNTER; cnt < (FIRST_SOFTWARE_COUNTER + NUMBER_OF_SOFTWARE_COUNTERS); cnt++) {
+		const struct mali_counter *counter = &counters[cnt];
+
+		if (counter->enabled) {
+			const int index = cnt - FIRST_SOFTWARE_COUNTER;
+
+			counter_dump[len++] = counter->key;
+			counter_dump[len++] = sw_counter_data[index];
+			/* Set the value to zero for the next time */
+			sw_counter_data[index] = 0;
+		}
+	}
+
+	/* Report the accumulators */
+	for (cnt = FIRST_ACCUMULATOR; cnt < (FIRST_ACCUMULATOR + NUMBER_OF_ACCUMULATORS); cnt++) {
+		const struct mali_counter *counter = &counters[cnt];
+
+		if (counter->enabled) {
+			const int index = cnt - FIRST_ACCUMULATOR;
+
+			counter_dump[len++] = counter->key;
+			counter_dump[len++] = accumulators_data[index];
+			/* Do not zero the accumulator */
+		}
+	}
+
+	/* Update the buffer */
+	if (buffer)
+		*buffer = counter_dump;
+
+	return len;
+}
+
+static struct gator_interface gator_events_mali_midgard_interface = {
+	.name = "mali_midgard",
+	.create_files = create_files,
+	.start = start,
+	.stop = stop,
+	.read = read
+};
+
+extern int gator_events_mali_midgard_init(void)
+{
+	pr_debug("gator: Mali-Midgard: sw_counters init\n");
+
+	gator_mali_initialise_counters(counters, NUMBER_OF_EVENTS);
+
+	return gator_events_install(&gator_events_mali_midgard_interface);
+}
diff --git a/drivers/gator/gator_events_mali_midgard_hw.c b/drivers/gator/gator_events_mali_midgard_hw.c
new file mode 100644
index 00000000000..db91c42c7d0
--- /dev/null
+++ b/drivers/gator/gator_events_mali_midgard_hw.c
@@ -0,0 +1,969 @@
+/**
+ * Copyright (C) ARM Limited 2012-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+
+/* Mali Midgard DDK includes */
+#if defined(MALI_SIMPLE_API)
+/* Header with wrapper functions to kbase structures and functions */
+#include "mali_kbase_gator_api.h"
+#elif defined(MALI_DIR_MIDGARD)
+/* New DDK Directory structure with kernel/drivers/gpu/arm/midgard */
+#include "mali_linux_trace.h"
+#include "mali_kbase.h"
+#include "mali_kbase_mem_linux.h"
+#else
+/* Old DDK Directory structure with kernel/drivers/gpu/arm/t6xx */
+#include "linux/mali_linux_trace.h"
+#include "kbase/src/common/mali_kbase.h"
+#include "kbase/src/linux/mali_kbase_mem_linux.h"
+#endif
+
+/* If API version is not specified then assume API version 1. */
+#ifndef MALI_DDK_GATOR_API_VERSION
+#define MALI_DDK_GATOR_API_VERSION 1
+#endif
+
+#if (MALI_DDK_GATOR_API_VERSION != 1) && (MALI_DDK_GATOR_API_VERSION != 2) && (MALI_DDK_GATOR_API_VERSION != 3)
+#error MALI_DDK_GATOR_API_VERSION is invalid (must be 1 for r1/r2 DDK, or 2 for r3/r4 DDK, or 3 for r5 and later DDK).
+#endif
+
+#if !defined(CONFIG_MALI_GATOR_SUPPORT)
+#error CONFIG_MALI_GATOR_SUPPORT is required for GPU activity and software counters
+#endif
+
+#include "gator_events_mali_common.h"
+
+/*
+ * Mali-Midgard
+ */
+#if MALI_DDK_GATOR_API_VERSION == 3
+static uint32_t (*kbase_gator_instr_hwcnt_dump_irq_symbol)(struct kbase_gator_hwcnt_handles *);
+static uint32_t (*kbase_gator_instr_hwcnt_dump_complete_symbol)(struct kbase_gator_hwcnt_handles *, uint32_t *const);
+static struct kbase_gator_hwcnt_handles *(*kbase_gator_hwcnt_init_symbol)(struct kbase_gator_hwcnt_info *);
+static void (*kbase_gator_hwcnt_term_symbol)(struct kbase_gator_hwcnt_info *, struct kbase_gator_hwcnt_handles *);
+
+#else
+static struct kbase_device *(*kbase_find_device_symbol)(int);
+static struct kbase_context *(*kbase_create_context_symbol)(struct kbase_device *);
+static void (*kbase_destroy_context_symbol)(struct kbase_context *);
+
+#if MALI_DDK_GATOR_API_VERSION == 1
+static void *(*kbase_va_alloc_symbol)(struct kbase_context *, u32);
+static void (*kbase_va_free_symbol)(struct kbase_context *, void *);
+#elif MALI_DDK_GATOR_API_VERSION == 2
+static void *(*kbase_va_alloc_symbol)(struct kbase_context *, u32, struct kbase_hwc_dma_mapping *);
+static void (*kbase_va_free_symbol)(struct kbase_context *, struct kbase_hwc_dma_mapping *);
+#endif
+
+static mali_error (*kbase_instr_hwcnt_enable_symbol)(struct kbase_context *, struct kbase_uk_hwcnt_setup *);
+static mali_error (*kbase_instr_hwcnt_disable_symbol)(struct kbase_context *);
+static mali_error (*kbase_instr_hwcnt_clear_symbol)(struct kbase_context *);
+static mali_error (*kbase_instr_hwcnt_dump_irq_symbol)(struct kbase_context *);
+static mali_bool (*kbase_instr_hwcnt_dump_complete_symbol)(struct kbase_context *, mali_bool *);
+
+static long shader_present_low;
+#endif
+
+/** The interval between reads, in ns.
+ *
+ * Earlier we introduced a 'hold off for 1ms after last read' to
+ * resolve MIDBASE-2178 and MALINE-724. However, the 1ms hold off is
+ * too long if no context switches occur as there is a race between
+ * this value and the tick of the read clock in gator which is also
+ * 1ms. If we 'miss' the current read, the counter values are
+ * effectively 'spread' over 2ms and the values seen are half what
+ * they should be (since Streamline averages over sample time). In the
+ * presence of context switches this spread can vary and markedly
+ * affect the counters. Currently there is no 'proper' solution to
+ * this, but empirically we have found that reducing the minimum read
+ * interval to 950us causes the counts to be much more stable.
+ */
+static const int READ_INTERVAL_NSEC = 950000;
+
+#if GATOR_TEST
+#include "gator_events_mali_midgard_hw_test.c"
+#endif
+
+#if MALI_DDK_GATOR_API_VERSION != 3
+/* Blocks for HW counters */
+enum {
+	JM_BLOCK = 0,
+	TILER_BLOCK,
+	SHADER_BLOCK,
+	MMU_BLOCK
+};
+#endif
+
+static const char *mali_name;
+
+/* Counters for Mali-Midgard:
+ *
+ *    For HW counters we need strings to create /dev/gator/events files.
+ *    Enums are not needed because the position of the HW name in the array is the same
+ *    of the corresponding value in the received block of memory.
+ *    HW counters are requested by calculating a bitmask, passed then to the driver.
+ *    Every millisecond a HW counters dump is requested, and if the previous has been completed they are read.
+ */
+
+/* Hardware Counters */
+#if MALI_DDK_GATOR_API_VERSION == 3
+
+static const char *const *hardware_counter_names;
+static int number_of_hardware_counters;
+
+#else
+
+static const char *const hardware_counter_names[] = {
+	/* Job Manager */
+	"",
+	"",
+	"",
+	"",
+	"MESSAGES_SENT",
+	"MESSAGES_RECEIVED",
+	"GPU_ACTIVE",		/* 6 */
+	"IRQ_ACTIVE",
+	"JS0_JOBS",
+	"JS0_TASKS",
+	"JS0_ACTIVE",
+	"",
+	"JS0_WAIT_READ",
+	"JS0_WAIT_ISSUE",
+	"JS0_WAIT_DEPEND",
+	"JS0_WAIT_FINISH",
+	"JS1_JOBS",
+	"JS1_TASKS",
+	"JS1_ACTIVE",
+	"",
+	"JS1_WAIT_READ",
+	"JS1_WAIT_ISSUE",
+	"JS1_WAIT_DEPEND",
+	"JS1_WAIT_FINISH",
+	"JS2_JOBS",
+	"JS2_TASKS",
+	"JS2_ACTIVE",
+	"",
+	"JS2_WAIT_READ",
+	"JS2_WAIT_ISSUE",
+	"JS2_WAIT_DEPEND",
+	"JS2_WAIT_FINISH",
+	"JS3_JOBS",
+	"JS3_TASKS",
+	"JS3_ACTIVE",
+	"",
+	"JS3_WAIT_READ",
+	"JS3_WAIT_ISSUE",
+	"JS3_WAIT_DEPEND",
+	"JS3_WAIT_FINISH",
+	"JS4_JOBS",
+	"JS4_TASKS",
+	"JS4_ACTIVE",
+	"",
+	"JS4_WAIT_READ",
+	"JS4_WAIT_ISSUE",
+	"JS4_WAIT_DEPEND",
+	"JS4_WAIT_FINISH",
+	"JS5_JOBS",
+	"JS5_TASKS",
+	"JS5_ACTIVE",
+	"",
+	"JS5_WAIT_READ",
+	"JS5_WAIT_ISSUE",
+	"JS5_WAIT_DEPEND",
+	"JS5_WAIT_FINISH",
+	"JS6_JOBS",
+	"JS6_TASKS",
+	"JS6_ACTIVE",
+	"",
+	"JS6_WAIT_READ",
+	"JS6_WAIT_ISSUE",
+	"JS6_WAIT_DEPEND",
+	"JS6_WAIT_FINISH",
+
+	/*Tiler */
+	"",
+	"",
+	"",
+	"JOBS_PROCESSED",
+	"TRIANGLES",
+	"QUADS",
+	"POLYGONS",
+	"POINTS",
+	"LINES",
+	"VCACHE_HIT",
+	"VCACHE_MISS",
+	"FRONT_FACING",
+	"BACK_FACING",
+	"PRIM_VISIBLE",
+	"PRIM_CULLED",
+	"PRIM_CLIPPED",
+	"LEVEL0",
+	"LEVEL1",
+	"LEVEL2",
+	"LEVEL3",
+	"LEVEL4",
+	"LEVEL5",
+	"LEVEL6",
+	"LEVEL7",
+	"COMMAND_1",
+	"COMMAND_2",
+	"COMMAND_3",
+	"COMMAND_4",
+	"COMMAND_4_7",
+	"COMMAND_8_15",
+	"COMMAND_16_63",
+	"COMMAND_64",
+	"COMPRESS_IN",
+	"COMPRESS_OUT",
+	"COMPRESS_FLUSH",
+	"TIMESTAMPS",
+	"PCACHE_HIT",
+	"PCACHE_MISS",
+	"PCACHE_LINE",
+	"PCACHE_STALL",
+	"WRBUF_HIT",
+	"WRBUF_MISS",
+	"WRBUF_LINE",
+	"WRBUF_PARTIAL",
+	"WRBUF_STALL",
+	"ACTIVE",
+	"LOADING_DESC",
+	"INDEX_WAIT",
+	"INDEX_RANGE_WAIT",
+	"VERTEX_WAIT",
+	"PCACHE_WAIT",
+	"WRBUF_WAIT",
+	"BUS_READ",
+	"BUS_WRITE",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"UTLB_STALL",
+	"UTLB_REPLAY_MISS",
+	"UTLB_REPLAY_FULL",
+	"UTLB_NEW_MISS",
+	"UTLB_HIT",
+
+	/* Shader Core */
+	"",
+	"",
+	"",
+	"SHADER_CORE_ACTIVE",
+	"FRAG_ACTIVE",
+	"FRAG_PRIMATIVES",
+	"FRAG_PRIMATIVES_DROPPED",
+	"FRAG_CYCLE_DESC",
+	"FRAG_CYCLES_PLR",
+	"FRAG_CYCLES_VERT",
+	"FRAG_CYCLES_TRISETUP",
+	"FRAG_CYCLES_RAST",
+	"FRAG_THREADS",
+	"FRAG_DUMMY_THREADS",
+	"FRAG_QUADS_RAST",
+	"FRAG_QUADS_EZS_TEST",
+	"FRAG_QUADS_EZS_KILLED",
+	"FRAG_QUADS_LZS_TEST",
+	"FRAG_QUADS_LZS_KILLED",
+	"FRAG_CYCLE_NO_TILE",
+	"FRAG_NUM_TILES",
+	"FRAG_TRANS_ELIM",
+	"COMPUTE_ACTIVE",
+	"COMPUTE_TASKS",
+	"COMPUTE_THREADS",
+	"COMPUTE_CYCLES_DESC",
+	"TRIPIPE_ACTIVE",
+	"ARITH_WORDS",
+	"ARITH_CYCLES_REG",
+	"ARITH_CYCLES_L0",
+	"ARITH_FRAG_DEPEND",
+	"LS_WORDS",
+	"LS_ISSUES",
+	"LS_RESTARTS",
+	"LS_REISSUES_MISS",
+	"LS_REISSUES_VD",
+	"LS_REISSUE_ATTRIB_MISS",
+	"LS_NO_WB",
+	"TEX_WORDS",
+	"TEX_BUBBLES",
+	"TEX_WORDS_L0",
+	"TEX_WORDS_DESC",
+	"TEX_THREADS",
+	"TEX_RECIRC_FMISS",
+	"TEX_RECIRC_DESC",
+	"TEX_RECIRC_MULTI",
+	"TEX_RECIRC_PMISS",
+	"TEX_RECIRC_CONF",
+	"LSC_READ_HITS",
+	"LSC_READ_MISSES",
+	"LSC_WRITE_HITS",
+	"LSC_WRITE_MISSES",
+	"LSC_ATOMIC_HITS",
+	"LSC_ATOMIC_MISSES",
+	"LSC_LINE_FETCHES",
+	"LSC_DIRTY_LINE",
+	"LSC_SNOOPS",
+	"AXI_TLB_STALL",
+	"AXI_TLB_MIESS",
+	"AXI_TLB_TRANSACTION",
+	"LS_TLB_MISS",
+	"LS_TLB_HIT",
+	"AXI_BEATS_READ",
+	"AXI_BEATS_WRITTEN",
+
+	/*L2 and MMU */
+	"",
+	"",
+	"",
+	"",
+	"MMU_HIT",
+	"MMU_NEW_MISS",
+	"MMU_REPLAY_FULL",
+	"MMU_REPLAY_MISS",
+	"MMU_TABLE_WALK",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"UTLB_HIT",
+	"UTLB_NEW_MISS",
+	"UTLB_REPLAY_FULL",
+	"UTLB_REPLAY_MISS",
+	"UTLB_STALL",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"L2_WRITE_BEATS",
+	"L2_READ_BEATS",
+	"L2_ANY_LOOKUP",
+	"L2_READ_LOOKUP",
+	"L2_SREAD_LOOKUP",
+	"L2_READ_REPLAY",
+	"L2_READ_SNOOP",
+	"L2_READ_HIT",
+	"L2_CLEAN_MISS",
+	"L2_WRITE_LOOKUP",
+	"L2_SWRITE_LOOKUP",
+	"L2_WRITE_REPLAY",
+	"L2_WRITE_SNOOP",
+	"L2_WRITE_HIT",
+	"L2_EXT_READ_FULL",
+	"L2_EXT_READ_HALF",
+	"L2_EXT_WRITE_FULL",
+	"L2_EXT_WRITE_HALF",
+	"L2_EXT_READ",
+	"L2_EXT_READ_LINE",
+	"L2_EXT_WRITE",
+	"L2_EXT_WRITE_LINE",
+	"L2_EXT_WRITE_SMALL",
+	"L2_EXT_BARRIER",
+	"L2_EXT_AR_STALL",
+	"L2_EXT_R_BUF_FULL",
+	"L2_EXT_RD_BUF_FULL",
+	"L2_EXT_R_RAW",
+	"L2_EXT_W_STALL",
+	"L2_EXT_W_BUF_FULL",
+	"L2_EXT_R_W_HAZARD",
+	"L2_TAG_HAZARD",
+	"L2_SNOOP_FULL",
+	"L2_REPLAY_FULL"
+};
+
+static const int number_of_hardware_counters = ARRAY_SIZE(hardware_counter_names);
+
+#endif
+
+#define GET_HW_BLOCK(c) (((c) >> 6) & 0x3)
+#define GET_COUNTER_OFFSET(c) ((c) & 0x3f)
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+/* Opaque handles for kbase_context and kbase_hwc_dma_mapping */
+static struct kbase_gator_hwcnt_handles *handles;
+
+/* Information about hardware counters */
+static struct kbase_gator_hwcnt_info *in_out_info;
+
+#else
+/* Memory to dump hardware counters into */
+static void *kernel_dump_buffer;
+
+#if MALI_DDK_GATOR_API_VERSION == 2
+/* DMA state used to manage lifetime of the buffer */
+struct kbase_hwc_dma_mapping kernel_dump_buffer_handle;
+#endif
+
+/* kbase context and device */
+static struct kbase_context *kbcontext;
+static struct kbase_device *kbdevice;
+
+/*
+ * The following function has no external prototype in older DDK
+ * revisions. When the DDK is updated then this should be removed.
+ */
+struct kbase_device *kbase_find_device(int minor);
+#endif
+
+static volatile bool kbase_device_busy;
+static unsigned int num_hardware_counters_enabled;
+
+/* gatorfs variables for counter enable state */
+static struct mali_counter *counters;
+
+/* An array used to return the data we recorded as key,value pairs */
+static long long *counter_dump;
+static uint64_t last_read_time;
+
+extern struct mali_counter mali_activity[3];
+
+static const char *const mali_activity_names[] = {
+	"fragment",
+	"vertex",
+	"opencl",
+};
+
+#define SYMBOL_GET(FUNCTION, ERROR_COUNT) \
+	do { \
+		if (FUNCTION ## _symbol) { \
+			pr_err("gator: mali " #FUNCTION " symbol was already registered\n"); \
+			(ERROR_COUNT)++; \
+		} else { \
+			FUNCTION ## _symbol = symbol_get(FUNCTION); \
+			if (!FUNCTION ## _symbol) { \
+				pr_err("gator: mali online " #FUNCTION " symbol not found\n"); \
+				(ERROR_COUNT)++; \
+			} \
+		} \
+	} while (0)
+
+#define SYMBOL_CLEANUP(FUNCTION) \
+	do { \
+		if (FUNCTION ## _symbol) { \
+			symbol_put(FUNCTION); \
+			FUNCTION ## _symbol = NULL; \
+		} \
+	} while (0)
+
+/**
+ * Execute symbol_get for all the Mali symbols and check for success.
+ * @return the number of symbols not loaded.
+ */
+static int init_symbols(void)
+{
+	int error_count = 0;
+#if MALI_DDK_GATOR_API_VERSION == 3
+	SYMBOL_GET(kbase_gator_instr_hwcnt_dump_irq, error_count);
+	SYMBOL_GET(kbase_gator_instr_hwcnt_dump_complete, error_count);
+	SYMBOL_GET(kbase_gator_hwcnt_init, error_count);
+	SYMBOL_GET(kbase_gator_hwcnt_term, error_count);
+#else
+	SYMBOL_GET(kbase_find_device, error_count);
+	SYMBOL_GET(kbase_create_context, error_count);
+	SYMBOL_GET(kbase_va_alloc, error_count);
+	SYMBOL_GET(kbase_instr_hwcnt_enable, error_count);
+	SYMBOL_GET(kbase_instr_hwcnt_clear, error_count);
+	SYMBOL_GET(kbase_instr_hwcnt_dump_irq, error_count);
+	SYMBOL_GET(kbase_instr_hwcnt_dump_complete, error_count);
+	SYMBOL_GET(kbase_instr_hwcnt_disable, error_count);
+	SYMBOL_GET(kbase_va_free, error_count);
+	SYMBOL_GET(kbase_destroy_context, error_count);
+#endif
+
+	return error_count;
+}
+
+/**
+ * Execute symbol_put for all the registered Mali symbols.
+ */
+static void clean_symbols(void)
+{
+#if MALI_DDK_GATOR_API_VERSION == 3
+	SYMBOL_CLEANUP(kbase_gator_instr_hwcnt_dump_irq);
+	SYMBOL_CLEANUP(kbase_gator_instr_hwcnt_dump_complete);
+	SYMBOL_CLEANUP(kbase_gator_hwcnt_init);
+	SYMBOL_CLEANUP(kbase_gator_hwcnt_term);
+#else
+	SYMBOL_CLEANUP(kbase_find_device);
+	SYMBOL_CLEANUP(kbase_create_context);
+	SYMBOL_CLEANUP(kbase_va_alloc);
+	SYMBOL_CLEANUP(kbase_instr_hwcnt_enable);
+	SYMBOL_CLEANUP(kbase_instr_hwcnt_clear);
+	SYMBOL_CLEANUP(kbase_instr_hwcnt_dump_irq);
+	SYMBOL_CLEANUP(kbase_instr_hwcnt_dump_complete);
+	SYMBOL_CLEANUP(kbase_instr_hwcnt_disable);
+	SYMBOL_CLEANUP(kbase_va_free);
+	SYMBOL_CLEANUP(kbase_destroy_context);
+#endif
+}
+
+static int start(void)
+{
+#if MALI_DDK_GATOR_API_VERSION != 3
+	struct kbase_uk_hwcnt_setup setup;
+	unsigned long long shadersPresent = 0;
+	u16 bitmask[] = { 0, 0, 0, 0 };
+	mali_error err;
+#endif
+	int cnt;
+
+	last_read_time = 0;
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+	/* Setup HW counters */
+	num_hardware_counters_enabled = 0;
+
+	/* Declare and initialise kbase_gator_hwcnt_info structure */
+	in_out_info = kmalloc(sizeof(*in_out_info), GFP_KERNEL);
+	for (cnt = 0; cnt < ARRAY_SIZE(in_out_info->bitmask); cnt++)
+		in_out_info->bitmask[cnt] = 0;
+
+	/* Calculate enable bitmasks based on counters_enabled array */
+	for (cnt = 0; cnt < number_of_hardware_counters; cnt++) {
+		if (counters[cnt].enabled) {
+			int block = GET_HW_BLOCK(cnt);
+			int enable_bit = GET_COUNTER_OFFSET(cnt) / 4;
+
+			in_out_info->bitmask[block] |= (1 << enable_bit);
+			pr_debug("gator: Mali-Midgard: hardware counter %s selected [%d]\n", hardware_counter_names[cnt], cnt);
+			num_hardware_counters_enabled++;
+		}
+	}
+
+	/* Create a kbase context for HW counters */
+	if (num_hardware_counters_enabled > 0) {
+		if (init_symbols() > 0) {
+			clean_symbols();
+			/* No Mali driver code entrypoints found - not a fault. */
+			return 0;
+		}
+
+		handles = kbase_gator_hwcnt_init_symbol(in_out_info);
+
+		if (handles == NULL)
+			goto out;
+
+		kbase_device_busy = false;
+	}
+
+	return 0;
+#else
+	/* Setup HW counters */
+	num_hardware_counters_enabled = 0;
+
+	/* Calculate enable bitmasks based on counters_enabled array */
+	for (cnt = 0; cnt < number_of_hardware_counters; cnt++) {
+		const struct mali_counter *counter = &counters[cnt];
+
+		if (counter->enabled) {
+			int block = GET_HW_BLOCK(cnt);
+			int enable_bit = GET_COUNTER_OFFSET(cnt) / 4;
+
+			bitmask[block] |= (1 << enable_bit);
+			pr_debug("gator: Mali-Midgard: hardware counter %s selected [%d]\n", hardware_counter_names[cnt], cnt);
+			num_hardware_counters_enabled++;
+		}
+	}
+
+	/* Create a kbase context for HW counters */
+	if (num_hardware_counters_enabled > 0) {
+		if (init_symbols() > 0) {
+			clean_symbols();
+			/* No Mali driver code entrypoints found - not a fault. */
+			return 0;
+		}
+
+		kbdevice = kbase_find_device_symbol(-1);
+
+		/* If we already got a context, fail */
+		if (kbcontext) {
+			pr_err("gator: Mali-Midgard: error context already present\n");
+			goto out;
+		}
+
+		/* kbcontext will only be valid after all the Mali symbols are loaded successfully */
+		kbcontext = kbase_create_context_symbol(kbdevice);
+		if (!kbcontext) {
+			pr_err("gator: Mali-Midgard: error creating kbase context\n");
+			goto out;
+		}
+
+		/* See if we can get the number of shader cores */
+		shadersPresent = kbdevice->shader_present_bitmap;
+		shader_present_low = (unsigned long)shadersPresent;
+
+		/*
+		 * The amount of memory needed to store the dump (bytes)
+		 * DUMP_SIZE = number of core groups
+		 *             * number of blocks (always 8 for midgard)
+		 *             * number of counters per block (always 64 for midgard)
+		 *             * number of bytes per counter (always 4 in midgard)
+		 * For a Mali-Midgard with a single core group = 1 * 8 * 64 * 4 = 2048
+		 * For a Mali-Midgard with a dual core group   = 2 * 8 * 64 * 4 = 4096
+		 */
+#if MALI_DDK_GATOR_API_VERSION == 1
+		kernel_dump_buffer = kbase_va_alloc_symbol(kbcontext, 4096);
+#elif MALI_DDK_GATOR_API_VERSION == 2
+		kernel_dump_buffer = kbase_va_alloc_symbol(kbcontext, 4096, &kernel_dump_buffer_handle);
+#endif
+		if (!kernel_dump_buffer) {
+			pr_err("gator: Mali-Midgard: error trying to allocate va\n");
+			goto destroy_context;
+		}
+
+		setup.dump_buffer = (uintptr_t)kernel_dump_buffer;
+		setup.jm_bm = bitmask[JM_BLOCK];
+		setup.tiler_bm = bitmask[TILER_BLOCK];
+		setup.shader_bm = bitmask[SHADER_BLOCK];
+		setup.mmu_l2_bm = bitmask[MMU_BLOCK];
+		/* These counters do not exist on Mali-T60x */
+		setup.l3_cache_bm = 0;
+
+		/* Use kbase API to enable hardware counters and provide dump buffer */
+		err = kbase_instr_hwcnt_enable_symbol(kbcontext, &setup);
+		if (err != MALI_ERROR_NONE) {
+			pr_err("gator: Mali-Midgard: can't setup hardware counters\n");
+			goto free_buffer;
+		}
+		pr_debug("gator: Mali-Midgard: hardware counters enabled\n");
+		kbase_instr_hwcnt_clear_symbol(kbcontext);
+		pr_debug("gator: Mali-Midgard: hardware counters cleared\n");
+
+		kbase_device_busy = false;
+	}
+
+	return 0;
+
+free_buffer:
+#if MALI_DDK_GATOR_API_VERSION == 1
+	kbase_va_free_symbol(kbcontext, kernel_dump_buffer);
+#elif MALI_DDK_GATOR_API_VERSION == 2
+	kbase_va_free_symbol(kbcontext, &kernel_dump_buffer_handle);
+#endif
+
+destroy_context:
+	kbase_destroy_context_symbol(kbcontext);
+#endif
+
+out:
+	clean_symbols();
+	return -1;
+}
+
+static void stop(void)
+{
+	unsigned int cnt;
+#if MALI_DDK_GATOR_API_VERSION == 3
+	struct kbase_gator_hwcnt_handles *temp_hand;
+#else
+	struct kbase_context *temp_kbcontext;
+#endif
+
+	pr_debug("gator: Mali-Midgard: stop\n");
+
+	/* Set all counters as disabled */
+	for (cnt = 0; cnt < number_of_hardware_counters; cnt++)
+		counters[cnt].enabled = 0;
+
+	/* Destroy the context for HW counters */
+#if MALI_DDK_GATOR_API_VERSION == 3
+	if (num_hardware_counters_enabled > 0 && handles != NULL) {
+		/*
+		 * Set the global variable to NULL before destroying it, because
+		 * other function will check this before using it.
+		 */
+		temp_hand = handles;
+		handles = NULL;
+
+		kbase_gator_hwcnt_term_symbol(in_out_info, temp_hand);
+
+		kfree(in_out_info);
+
+#else
+	if (num_hardware_counters_enabled > 0 && kbcontext != NULL) {
+		/*
+		 * Set the global variable to NULL before destroying it, because
+		 * other function will check this before using it.
+		 */
+		temp_kbcontext = kbcontext;
+		kbcontext = NULL;
+
+		kbase_instr_hwcnt_disable_symbol(temp_kbcontext);
+
+#if MALI_DDK_GATOR_API_VERSION == 1
+		kbase_va_free_symbol(temp_kbcontext, kernel_dump_buffer);
+#elif MALI_DDK_GATOR_API_VERSION == 2
+		kbase_va_free_symbol(temp_kbcontext, &kernel_dump_buffer_handle);
+#endif
+
+		kbase_destroy_context_symbol(temp_kbcontext);
+#endif
+
+		pr_debug("gator: Mali-Midgard: hardware counters stopped\n");
+
+		clean_symbols();
+	}
+}
+
+static int read_counter(const int cnt, const int len, const struct mali_counter *counter)
+{
+	const int block = GET_HW_BLOCK(cnt);
+	const int counter_offset = GET_COUNTER_OFFSET(cnt);
+	u32 value = 0;
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+	const char *block_base_address = (char *)in_out_info->kernel_dump_buffer;
+	int i;
+	int shader_core_count = 0;
+
+	for (i = 0; i < in_out_info->nr_hwc_blocks; i++) {
+		if (block == in_out_info->hwc_layout[i]) {
+			value += *((u32 *)(block_base_address + (0x100 * i)) + counter_offset);
+			if (block == SHADER_BLOCK)
+				++shader_core_count;
+		}
+	}
+
+	if (shader_core_count > 1)
+		value /= shader_core_count;
+#else
+	const unsigned int vithar_blocks[] = {
+		0x700,	/* VITHAR_JOB_MANAGER,     Block 0 */
+		0x400,	/* VITHAR_TILER,           Block 1 */
+		0x000,	/* VITHAR_SHADER_CORE,     Block 2 */
+		0x500	/* VITHAR_MEMORY_SYSTEM,   Block 3 */
+	};
+	const char *block_base_address = (char *)kernel_dump_buffer + vithar_blocks[block];
+
+	/* If counter belongs to shader block need to take into account all cores */
+	if (block == SHADER_BLOCK) {
+		int i = 0;
+		int shader_core_count = 0;
+
+		value = 0;
+
+		for (i = 0; i < 4; i++) {
+			if ((shader_present_low >> i) & 1) {
+				value += *((u32 *)(block_base_address + (0x100 * i)) + counter_offset);
+				shader_core_count++;
+			}
+		}
+
+		for (i = 0; i < 4; i++) {
+			if ((shader_present_low >> (i+4)) & 1) {
+				value += *((u32 *)(block_base_address + (0x100 * i) + 0x800) + counter_offset);
+				shader_core_count++;
+			}
+		}
+
+		/* Need to total by number of cores to produce an average */
+		if (shader_core_count != 0)
+			value /= shader_core_count;
+	} else {
+		value = *((u32 *)block_base_address + counter_offset);
+	}
+#endif
+
+	counter_dump[len + 0] = counter->key;
+	counter_dump[len + 1] = value;
+
+	return 2;
+}
+
+static int read(long long **buffer, bool sched_switch)
+{
+	int cnt;
+	int len = 0;
+	uint32_t success;
+
+	uint64_t curr_time;
+
+	if (!on_primary_core() || sched_switch)
+		return 0;
+
+	/*
+	 * Report the HW counters
+	 * Only process hardware counters if at least one of the hardware counters is enabled.
+	 */
+	if (num_hardware_counters_enabled <= 0)
+		return 0;
+
+	curr_time = gator_get_time();
+
+	/*
+	 * Discard reads unless a respectable time has passed. This
+	 * reduces the load on the GPU without sacrificing accuracy on
+	 * the Streamline display.
+	 */
+	if (curr_time - last_read_time < READ_INTERVAL_NSEC)
+		return 0;
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+	if (!handles)
+		return -1;
+
+	/* Mali symbols can be called safely since a kbcontext is valid */
+	if (kbase_gator_instr_hwcnt_dump_complete_symbol(handles, &success)) {
+#else
+	if (!kbcontext)
+		return -1;
+
+	/* Mali symbols can be called safely since a kbcontext is valid */
+	if (kbase_instr_hwcnt_dump_complete_symbol(kbcontext, &success)) {
+#endif
+		kbase_device_busy = false;
+
+		/*
+		 * If last_read_time is zero, then this result is from a previous
+		 * capture or in error.
+		 */
+		if (success && last_read_time > 0) {
+			/* Backdate these events to when they were requested */
+			counter_dump[len++] = 0;
+			counter_dump[len++] = last_read_time;
+
+			/* Cycle through hardware counters and accumulate totals */
+			for (cnt = 0; cnt < number_of_hardware_counters; cnt++) {
+				const struct mali_counter *counter = &counters[cnt];
+
+				if (counter->enabled)
+					len += read_counter(cnt, len, counter);
+			}
+
+			/* Restore the timestamp */
+			counter_dump[len++] = 0;
+			counter_dump[len++] = curr_time;
+		}
+	}
+
+	if (!kbase_device_busy) {
+		kbase_device_busy = true;
+		last_read_time = curr_time;
+#if MALI_DDK_GATOR_API_VERSION == 3
+		kbase_gator_instr_hwcnt_dump_irq_symbol(handles);
+#else
+		kbase_instr_hwcnt_dump_irq_symbol(kbcontext);
+#endif
+	}
+
+	/* Update the buffer */
+	if (buffer)
+		*buffer = counter_dump;
+
+	return len;
+}
+
+static int create_files(struct super_block *sb, struct dentry *root)
+{
+	unsigned int event;
+	/*
+	 * Create the filesystem for all events
+	 */
+	for (event = 0; event < ARRAY_SIZE(mali_activity); event++) {
+		if (gator_mali_create_file_system("Midgard", mali_activity_names[event], sb, root, &mali_activity[event], NULL) != 0)
+			return -1;
+	}
+
+	for (event = 0; event < number_of_hardware_counters; event++) {
+		if (gator_mali_create_file_system(mali_name, hardware_counter_names[event], sb, root, &counters[event], NULL) != 0)
+			return -1;
+	}
+
+	return 0;
+}
+
+static void shutdown(void)
+{
+#if MALI_DDK_GATOR_API_VERSION == 3
+	void (*kbase_gator_hwcnt_term_names_symbol)(void) = NULL;
+	int error_count = 0;
+#endif
+
+	kfree(counters);
+	kfree(counter_dump);
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+	SYMBOL_GET(kbase_gator_hwcnt_term_names, error_count);
+
+	number_of_hardware_counters = -1;
+	hardware_counter_names = NULL;
+	if (kbase_gator_hwcnt_term_names_symbol != NULL) {
+		kbase_gator_hwcnt_term_names_symbol();
+		pr_debug("gator: Released symbols\n");
+	}
+
+	SYMBOL_CLEANUP(kbase_gator_hwcnt_term_names);
+#endif
+}
+
+static struct gator_interface gator_events_mali_midgard_interface = {
+	.name = "mali_midgard_hw",
+	.shutdown = shutdown,
+	.create_files = create_files,
+	.start = start,
+	.stop = stop,
+	.read64 = read
+};
+
+int gator_events_mali_midgard_hw_init(void)
+{
+#if MALI_DDK_GATOR_API_VERSION == 3
+	const char *const *(*kbase_gator_hwcnt_init_names_symbol)(uint32_t *) = NULL;
+	int error_count = 0;
+#endif
+
+	pr_debug("gator: Mali-Midgard: sw_counters init\n");
+
+#if GATOR_TEST
+	test_all_is_read_scheduled();
+#endif
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+	SYMBOL_GET(kbase_gator_hwcnt_init_names, error_count);
+	if (error_count > 0) {
+		SYMBOL_CLEANUP(kbase_gator_hwcnt_init_names);
+		return 1;
+	}
+
+	number_of_hardware_counters = -1;
+	hardware_counter_names = kbase_gator_hwcnt_init_names_symbol(&number_of_hardware_counters);
+
+	SYMBOL_CLEANUP(kbase_gator_hwcnt_init_names);
+
+	if ((hardware_counter_names == NULL) || (number_of_hardware_counters <= 0)) {
+		pr_err("gator: Error reading hardware counters names: got %d names\n", number_of_hardware_counters);
+		return -1;
+	}
+#else
+	mali_name = "Midgard";
+#endif
+
+	counters = kmalloc(sizeof(*counters)*number_of_hardware_counters, GFP_KERNEL);
+	counter_dump = kmalloc(sizeof(*counter_dump)*number_of_hardware_counters*2 + 4, GFP_KERNEL);
+
+	gator_mali_initialise_counters(mali_activity, ARRAY_SIZE(mali_activity));
+	gator_mali_initialise_counters(counters, number_of_hardware_counters);
+
+	return gator_events_install(&gator_events_mali_midgard_interface);
+}
diff --git a/drivers/gator/gator_events_mali_midgard_hw_test.c b/drivers/gator/gator_events_mali_midgard_hw_test.c
new file mode 100644
index 00000000000..9fd44bc00e0
--- /dev/null
+++ b/drivers/gator/gator_events_mali_midgard_hw_test.c
@@ -0,0 +1,12 @@
+/**
+ * Copyright (C) ARM Limited 2012-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/**
+ * Test functions for mali_t600_hw code.
+ */
diff --git a/drivers/gator/gator_events_meminfo.c b/drivers/gator/gator_events_meminfo.c
new file mode 100644
index 00000000000..42a6947752f
--- /dev/null
+++ b/drivers/gator/gator_events_meminfo.c
@@ -0,0 +1,474 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+
+#include <linux/hardirq.h>
+#include <linux/kthread.h>
+#include <linux/sched.h>
+#include <linux/semaphore.h>
+#include <linux/workqueue.h>
+#include <trace/events/kmem.h>
+
+#define USE_THREAD defined(CONFIG_PREEMPT_RT_FULL)
+
+enum {
+	MEMINFO_MEMFREE,
+	MEMINFO_MEMUSED,
+	MEMINFO_BUFFERRAM,
+	MEMINFO_TOTAL,
+};
+
+enum {
+	PROC_SIZE,
+	PROC_SHARE,
+	PROC_TEXT,
+	PROC_DATA,
+	PROC_COUNT,
+};
+
+static const char * const meminfo_names[] = {
+	"Linux_meminfo_memfree",
+	"Linux_meminfo_memused",
+	"Linux_meminfo_bufferram",
+};
+
+static const char * const proc_names[] = {
+	"Linux_proc_statm_size",
+	"Linux_proc_statm_share",
+	"Linux_proc_statm_text",
+	"Linux_proc_statm_data",
+};
+
+static bool meminfo_global_enabled;
+static ulong meminfo_enabled[MEMINFO_TOTAL];
+static ulong meminfo_keys[MEMINFO_TOTAL];
+static long long meminfo_buffer[2 * (MEMINFO_TOTAL + 2)];
+static int meminfo_length;
+static bool new_data_avail;
+
+static bool proc_global_enabled;
+static ulong proc_enabled[PROC_COUNT];
+static ulong proc_keys[PROC_COUNT];
+static DEFINE_PER_CPU(long long, proc_buffer[2 * (PROC_COUNT + 3)]);
+
+static void do_read(void);
+
+#if USE_THREAD
+
+static int gator_meminfo_func(void *data);
+static bool gator_meminfo_run;
+/* Initialize semaphore unlocked to initialize memory values */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+static DECLARE_MUTEX(gator_meminfo_sem);
+#else
+static DEFINE_SEMAPHORE(gator_meminfo_sem);
+#endif
+
+static void notify(void)
+{
+	up(&gator_meminfo_sem);
+}
+
+#else
+
+static unsigned int mem_event;
+static void wq_sched_handler(struct work_struct *wsptr);
+static DECLARE_WORK(work, wq_sched_handler);
+static struct timer_list meminfo_wake_up_timer;
+static void meminfo_wake_up_handler(unsigned long unused_data);
+
+static void notify(void)
+{
+	mem_event++;
+}
+
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+GATOR_DEFINE_PROBE(mm_page_free_direct, TP_PROTO(struct page *page, unsigned int order))
+#else
+GATOR_DEFINE_PROBE(mm_page_free, TP_PROTO(struct page *page, unsigned int order))
+#endif
+{
+	notify();
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+GATOR_DEFINE_PROBE(mm_pagevec_free, TP_PROTO(struct page *page, int cold))
+#else
+GATOR_DEFINE_PROBE(mm_page_free_batched, TP_PROTO(struct page *page, int cold))
+#endif
+{
+	notify();
+}
+
+GATOR_DEFINE_PROBE(mm_page_alloc, TP_PROTO(struct page *page, unsigned int order, gfp_t gfp_flags, int migratetype))
+{
+	notify();
+}
+
+static int gator_events_meminfo_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	int i;
+
+	for (i = 0; i < MEMINFO_TOTAL; i++) {
+		dir = gatorfs_mkdir(sb, root, meminfo_names[i]);
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &meminfo_enabled[i]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &meminfo_keys[i]);
+	}
+
+	for (i = 0; i < PROC_COUNT; ++i) {
+		dir = gatorfs_mkdir(sb, root, proc_names[i]);
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &proc_enabled[i]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &proc_keys[i]);
+	}
+
+	return 0;
+}
+
+static int gator_events_meminfo_start(void)
+{
+	int i;
+
+	new_data_avail = false;
+	meminfo_global_enabled = 0;
+	for (i = 0; i < MEMINFO_TOTAL; i++) {
+		if (meminfo_enabled[i]) {
+			meminfo_global_enabled = 1;
+			break;
+		}
+	}
+
+	proc_global_enabled = 0;
+	for (i = 0; i < PROC_COUNT; ++i) {
+		if (proc_enabled[i]) {
+			proc_global_enabled = 1;
+			break;
+		}
+	}
+	if (meminfo_enabled[MEMINFO_MEMUSED])
+		proc_global_enabled = 1;
+
+	if (meminfo_global_enabled == 0)
+		return 0;
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+	if (GATOR_REGISTER_TRACE(mm_page_free_direct))
+#else
+	if (GATOR_REGISTER_TRACE(mm_page_free))
+#endif
+		goto mm_page_free_exit;
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+	if (GATOR_REGISTER_TRACE(mm_pagevec_free))
+#else
+	if (GATOR_REGISTER_TRACE(mm_page_free_batched))
+#endif
+		goto mm_page_free_batched_exit;
+	if (GATOR_REGISTER_TRACE(mm_page_alloc))
+		goto mm_page_alloc_exit;
+
+	do_read();
+#if USE_THREAD
+	/* Start worker thread */
+	gator_meminfo_run = true;
+	/* Since the mutex starts unlocked, memory values will be initialized */
+	if (IS_ERR(kthread_run(gator_meminfo_func, NULL, "gator_meminfo")))
+		goto kthread_run_exit;
+#else
+	setup_deferrable_timer_on_stack(&meminfo_wake_up_timer, meminfo_wake_up_handler, 0);
+#endif
+
+	return 0;
+
+#if USE_THREAD
+kthread_run_exit:
+	GATOR_UNREGISTER_TRACE(mm_page_alloc);
+#endif
+mm_page_alloc_exit:
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+	GATOR_UNREGISTER_TRACE(mm_pagevec_free);
+#else
+	GATOR_UNREGISTER_TRACE(mm_page_free_batched);
+#endif
+mm_page_free_batched_exit:
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+	GATOR_UNREGISTER_TRACE(mm_page_free_direct);
+#else
+	GATOR_UNREGISTER_TRACE(mm_page_free);
+#endif
+mm_page_free_exit:
+	return -1;
+}
+
+static void gator_events_meminfo_stop(void)
+{
+	if (meminfo_global_enabled) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+		GATOR_UNREGISTER_TRACE(mm_page_free_direct);
+		GATOR_UNREGISTER_TRACE(mm_pagevec_free);
+#else
+		GATOR_UNREGISTER_TRACE(mm_page_free);
+		GATOR_UNREGISTER_TRACE(mm_page_free_batched);
+#endif
+		GATOR_UNREGISTER_TRACE(mm_page_alloc);
+
+#if USE_THREAD
+		/* Stop worker thread */
+		gator_meminfo_run = false;
+		up(&gator_meminfo_sem);
+#else
+		del_timer_sync(&meminfo_wake_up_timer);
+#endif
+	}
+}
+
+static void do_read(void)
+{
+	struct sysinfo info;
+	int i, len;
+	unsigned long long value;
+
+	meminfo_length = len = 0;
+
+	si_meminfo(&info);
+	for (i = 0; i < MEMINFO_TOTAL; i++) {
+		if (meminfo_enabled[i]) {
+			switch (i) {
+			case MEMINFO_MEMFREE:
+				value = info.freeram * PAGE_SIZE;
+				break;
+			case MEMINFO_MEMUSED:
+				/* pid -1 means system wide */
+				meminfo_buffer[len++] = 1;
+				meminfo_buffer[len++] = -1;
+				/* Emit value */
+				meminfo_buffer[len++] = meminfo_keys[MEMINFO_MEMUSED];
+				meminfo_buffer[len++] = (info.totalram - info.freeram) * PAGE_SIZE;
+				/* Clear pid */
+				meminfo_buffer[len++] = 1;
+				meminfo_buffer[len++] = 0;
+				continue;
+			case MEMINFO_BUFFERRAM:
+				value = info.bufferram * PAGE_SIZE;
+				break;
+			default:
+				value = 0;
+				break;
+			}
+			meminfo_buffer[len++] = meminfo_keys[i];
+			meminfo_buffer[len++] = value;
+		}
+	}
+
+	meminfo_length = len;
+	new_data_avail = true;
+}
+
+#if USE_THREAD
+
+static int gator_meminfo_func(void *data)
+{
+	for (;;) {
+		if (down_killable(&gator_meminfo_sem))
+			break;
+
+		/* Eat up any pending events */
+		while (!down_trylock(&gator_meminfo_sem))
+			;
+
+		if (!gator_meminfo_run)
+			break;
+
+		do_read();
+	}
+
+	return 0;
+}
+
+#else
+
+/* Must be run in process context as the kernel function si_meminfo() can sleep */
+static void wq_sched_handler(struct work_struct *wsptr)
+{
+	do_read();
+}
+
+static void meminfo_wake_up_handler(unsigned long unused_data)
+{
+	/* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */
+	schedule_work(&work);
+}
+
+#endif
+
+static int gator_events_meminfo_read(long long **buffer, bool sched_switch)
+{
+#if !USE_THREAD
+	static unsigned int last_mem_event;
+#endif
+
+	if (!on_primary_core() || !meminfo_global_enabled)
+		return 0;
+
+#if !USE_THREAD
+	if (last_mem_event != mem_event) {
+		last_mem_event = mem_event;
+		mod_timer(&meminfo_wake_up_timer, jiffies + 1);
+	}
+#endif
+
+	if (!new_data_avail)
+		return 0;
+
+	new_data_avail = false;
+
+	if (buffer)
+		*buffer = meminfo_buffer;
+
+	return meminfo_length;
+}
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 34) && LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)
+
+static inline unsigned long gator_get_mm_counter(struct mm_struct *mm, int member)
+{
+#ifdef SPLIT_RSS_COUNTING
+	long val = atomic_long_read(&mm->rss_stat.count[member]);
+
+	if (val < 0)
+		val = 0;
+	return (unsigned long)val;
+#else
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 0, 0)
+	return mm->rss_stat.count[member];
+#else
+	return atomic_long_read(&mm->rss_stat.count[member]);
+#endif
+#endif
+}
+
+#define get_mm_counter(mm, member) gator_get_mm_counter(mm, member)
+
+#endif
+
+static int gator_events_meminfo_read_proc(long long **buffer, struct task_struct *task)
+{
+	struct mm_struct *mm;
+	u64 share = 0;
+	int i;
+	long long value;
+	int len = 0;
+	int cpu = get_physical_cpu();
+	long long *buf = per_cpu(proc_buffer, cpu);
+
+	if (!proc_global_enabled)
+		return 0;
+
+	/* Collect the memory stats of the process instead of the thread */
+	if (task->group_leader != NULL)
+		task = task->group_leader;
+
+	/* get_task_mm/mmput is not needed in this context because the task and it's mm are required as part of the sched_switch */
+	mm = task->mm;
+	if (mm == NULL)
+		return 0;
+
+	/* Derived from task_statm in fs/proc/task_mmu.c */
+	if (meminfo_enabled[MEMINFO_MEMUSED] || proc_enabled[PROC_SHARE]) {
+		share = get_mm_counter(mm,
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 32) && LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 34)
+							   file_rss
+#else
+							   MM_FILEPAGES
+#endif
+							   );
+	}
+
+	/* key of 1 indicates a pid */
+	buf[len++] = 1;
+	buf[len++] = task->pid;
+
+	for (i = 0; i < PROC_COUNT; ++i) {
+		if (proc_enabled[i]) {
+			switch (i) {
+			case PROC_SIZE:
+				value = mm->total_vm;
+				break;
+			case PROC_SHARE:
+				value = share;
+				break;
+			case PROC_TEXT:
+				value = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> PAGE_SHIFT;
+				break;
+			case PROC_DATA:
+				value = mm->total_vm - mm->shared_vm;
+				break;
+			}
+
+			buf[len++] = proc_keys[i];
+			buf[len++] = value * PAGE_SIZE;
+		}
+	}
+
+	if (meminfo_enabled[MEMINFO_MEMUSED]) {
+		value = share + get_mm_counter(mm,
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 32) && LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 34)
+									   anon_rss
+#else
+									   MM_ANONPAGES
+#endif
+									   );
+		/* Send resident for this pid */
+		buf[len++] = meminfo_keys[MEMINFO_MEMUSED];
+		buf[len++] = value * PAGE_SIZE;
+	}
+
+	/* Clear pid */
+	buf[len++] = 1;
+	buf[len++] = 0;
+
+	if (buffer)
+		*buffer = buf;
+
+	return len;
+}
+
+static struct gator_interface gator_events_meminfo_interface = {
+	.name = "meminfo",
+	.create_files = gator_events_meminfo_create_files,
+	.start = gator_events_meminfo_start,
+	.stop = gator_events_meminfo_stop,
+	.read64 = gator_events_meminfo_read,
+	.read_proc = gator_events_meminfo_read_proc,
+};
+
+int gator_events_meminfo_init(void)
+{
+	int i;
+
+	meminfo_global_enabled = 0;
+	for (i = 0; i < MEMINFO_TOTAL; i++) {
+		meminfo_enabled[i] = 0;
+		meminfo_keys[i] = gator_events_get_key();
+	}
+
+	proc_global_enabled = 0;
+	for (i = 0; i < PROC_COUNT; ++i) {
+		proc_enabled[i] = 0;
+		proc_keys[i] = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_meminfo_interface);
+}
diff --git a/drivers/gator/gator_events_mmapped.c b/drivers/gator/gator_events_mmapped.c
new file mode 100644
index 00000000000..30ca980c3dc
--- /dev/null
+++ b/drivers/gator/gator_events_mmapped.c
@@ -0,0 +1,210 @@
+/*
+ * Example events provider
+ *
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Similar entries to those below must be present in the events.xml file.
+ * To add them to the events.xml, create an events-mmap.xml with the
+ * following contents and rebuild gatord:
+ *
+ * <category name="mmapped">
+ *   <event counter="mmapped_cnt0" title="Simulated1" name="Sine" display="maximum" class="absolute" description="Sort-of-sine"/>
+ *   <event counter="mmapped_cnt1" title="Simulated2" name="Triangle" display="maximum" class="absolute" description="Triangular wave"/>
+ *   <event counter="mmapped_cnt2" title="Simulated3" name="PWM" display="maximum" class="absolute" description="PWM Signal"/>
+ * </category>
+ *
+ * When adding custom events, be sure to do the following:
+ * - add any needed .c files to the gator driver Makefile
+ * - call gator_events_install in the events init function
+ * - add the init function to GATOR_EVENTS_LIST in gator_main.c
+ * - add a new events-*.xml file to the gator daemon and rebuild
+ *
+ * Troubleshooting:
+ * - verify the new events are part of events.xml, which is created when building the daemon
+ * - verify the new events exist at /dev/gator/events/ once gatord is launched
+ * - verify the counter name in the XML matches the name at /dev/gator/events
+ */
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/ratelimit.h>
+
+#include "gator.h"
+
+#define MMAPPED_COUNTERS_NUM 3
+
+static int mmapped_global_enabled;
+
+static struct {
+	unsigned long enabled;
+	unsigned long key;
+} mmapped_counters[MMAPPED_COUNTERS_NUM];
+
+static int mmapped_buffer[MMAPPED_COUNTERS_NUM * 2];
+
+static s64 prev_time;
+
+/* Adds mmapped_cntX directories and enabled, event, and key files to /dev/gator/events */
+static int gator_events_mmapped_create_files(struct super_block *sb,
+					     struct dentry *root)
+{
+	int i;
+
+	for (i = 0; i < MMAPPED_COUNTERS_NUM; i++) {
+		char buf[16];
+		struct dentry *dir;
+
+		snprintf(buf, sizeof(buf), "mmapped_cnt%d", i);
+		dir = gatorfs_mkdir(sb, root, buf);
+		if (WARN_ON(!dir))
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled",
+				     &mmapped_counters[i].enabled);
+		gatorfs_create_ro_ulong(sb, dir, "key",
+					&mmapped_counters[i].key);
+	}
+
+	return 0;
+}
+
+static int gator_events_mmapped_start(void)
+{
+	int i;
+	struct timespec ts;
+
+	getnstimeofday(&ts);
+	prev_time = timespec_to_ns(&ts);
+
+	mmapped_global_enabled = 0;
+	for (i = 0; i < MMAPPED_COUNTERS_NUM; i++) {
+		if (mmapped_counters[i].enabled) {
+			mmapped_global_enabled = 1;
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static void gator_events_mmapped_stop(void)
+{
+}
+
+/* This function "simulates" counters, generating values of fancy
+ * functions like sine or triangle... */
+static int mmapped_simulate(int counter, int delta_in_us)
+{
+	int result = 0;
+
+	switch (counter) {
+	case 0:		/* sort-of-sine */
+		{
+			static int t;
+			int x;
+
+			t += delta_in_us;
+			if (t > 2048000)
+				t = 0;
+
+			if (t % 1024000 < 512000)
+				x = 512000 - (t % 512000);
+			else
+				x = t % 512000;
+
+			result = 32 * x / 512000;
+			result = result * result;
+
+			if (t < 1024000)
+				result = 1922 - result;
+		}
+		break;
+	case 1:		/* triangle */
+		{
+			static int v, d = 1;
+
+			v = v + d * delta_in_us;
+			if (v < 0) {
+				v = 0;
+				d = 1;
+			} else if (v > 1000000) {
+				v = 1000000;
+				d = -1;
+			}
+
+			result = v;
+		}
+		break;
+	case 2:		/* PWM signal */
+		{
+			static int dc, x, t;
+
+			t += delta_in_us;
+			if (t > 1000000)
+				t = 0;
+			if (x / 1000000 != (x + delta_in_us) / 1000000)
+				dc = (dc + 100000) % 1000000;
+			x += delta_in_us;
+
+			result = t < dc ? 0 : 10;
+		}
+		break;
+	}
+
+	return result;
+}
+
+static int gator_events_mmapped_read(int **buffer, bool sched_switch)
+{
+	int i;
+	int len = 0;
+	int delta_in_us;
+	struct timespec ts;
+	s64 time;
+
+	/* System wide counters - read from one core only */
+	if (!on_primary_core() || !mmapped_global_enabled)
+		return 0;
+
+	getnstimeofday(&ts);
+	time = timespec_to_ns(&ts);
+	delta_in_us = (int)(time - prev_time) / 1000;
+	prev_time = time;
+
+	for (i = 0; i < MMAPPED_COUNTERS_NUM; i++) {
+		if (mmapped_counters[i].enabled) {
+			mmapped_buffer[len++] = mmapped_counters[i].key;
+			mmapped_buffer[len++] =
+			    mmapped_simulate(i, delta_in_us);
+		}
+	}
+
+	if (buffer)
+		*buffer = mmapped_buffer;
+
+	return len;
+}
+
+static struct gator_interface gator_events_mmapped_interface = {
+	.name = "mmapped",
+	.create_files = gator_events_mmapped_create_files,
+	.start = gator_events_mmapped_start,
+	.stop = gator_events_mmapped_stop,
+	.read = gator_events_mmapped_read,
+};
+
+/* Must not be static! */
+int __init gator_events_mmapped_init(void)
+{
+	int i;
+
+	for (i = 0; i < MMAPPED_COUNTERS_NUM; i++) {
+		mmapped_counters[i].enabled = 0;
+		mmapped_counters[i].key = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_mmapped_interface);
+}
diff --git a/drivers/gator/gator_events_net.c b/drivers/gator/gator_events_net.c
new file mode 100644
index 00000000000..053f719419a
--- /dev/null
+++ b/drivers/gator/gator_events_net.c
@@ -0,0 +1,169 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+#include <linux/netdevice.h>
+#include <linux/hardirq.h>
+
+#define NETRX		0
+#define NETTX		1
+#define TOTALNET	2
+
+static ulong netrx_enabled;
+static ulong nettx_enabled;
+static ulong netrx_key;
+static ulong nettx_key;
+static int rx_total, tx_total;
+static ulong netPrev[TOTALNET];
+static int netGet[TOTALNET * 4];
+
+static struct timer_list net_wake_up_timer;
+
+/* Must be run in process context as the kernel function dev_get_stats() can sleep */
+static void get_network_stats(struct work_struct *wsptr)
+{
+	int rx = 0, tx = 0;
+	struct net_device *dev;
+
+	for_each_netdev(&init_net, dev) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+		const struct net_device_stats *stats = dev_get_stats(dev);
+#else
+		struct rtnl_link_stats64 temp;
+		const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp);
+#endif
+		rx += stats->rx_bytes;
+		tx += stats->tx_bytes;
+	}
+	rx_total = rx;
+	tx_total = tx;
+}
+
+static DECLARE_WORK(wq_get_stats, get_network_stats);
+
+static void net_wake_up_handler(unsigned long unused_data)
+{
+	/* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */
+	schedule_work(&wq_get_stats);
+}
+
+static void calculate_delta(int *rx, int *tx)
+{
+	int rx_calc, tx_calc;
+
+	rx_calc = (int)(rx_total - netPrev[NETRX]);
+	if (rx_calc < 0)
+		rx_calc = 0;
+	netPrev[NETRX] += rx_calc;
+
+	tx_calc = (int)(tx_total - netPrev[NETTX]);
+	if (tx_calc < 0)
+		tx_calc = 0;
+	netPrev[NETTX] += tx_calc;
+
+	*rx = rx_calc;
+	*tx = tx_calc;
+}
+
+static int gator_events_net_create_files(struct super_block *sb, struct dentry *root)
+{
+	/* Network counters are not currently supported in RT-Preempt full because mod_timer is used */
+#ifndef CONFIG_PREEMPT_RT_FULL
+	struct dentry *dir;
+
+	dir = gatorfs_mkdir(sb, root, "Linux_net_rx");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &netrx_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &netrx_key);
+
+	dir = gatorfs_mkdir(sb, root, "Linux_net_tx");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &nettx_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &nettx_key);
+#endif
+
+	return 0;
+}
+
+static int gator_events_net_start(void)
+{
+	get_network_stats(0);
+	netPrev[NETRX] = rx_total;
+	netPrev[NETTX] = tx_total;
+	setup_deferrable_timer_on_stack(&net_wake_up_timer, net_wake_up_handler, 0);
+	return 0;
+}
+
+static void gator_events_net_stop(void)
+{
+	del_timer_sync(&net_wake_up_timer);
+	netrx_enabled = 0;
+	nettx_enabled = 0;
+}
+
+static int gator_events_net_read(int **buffer, bool sched_switch)
+{
+	int len, rx_delta, tx_delta;
+	static int last_rx_delta, last_tx_delta;
+
+	if (!on_primary_core())
+		return 0;
+
+	if (!netrx_enabled && !nettx_enabled)
+		return 0;
+
+	mod_timer(&net_wake_up_timer, jiffies + 1);
+
+	calculate_delta(&rx_delta, &tx_delta);
+
+	len = 0;
+	if (netrx_enabled && last_rx_delta != rx_delta) {
+		last_rx_delta = rx_delta;
+		netGet[len++] = netrx_key;
+		/* indicates to Streamline that rx_delta bytes were transmitted now, not since the last message */
+		netGet[len++] = 0;
+		netGet[len++] = netrx_key;
+		netGet[len++] = rx_delta;
+	}
+
+	if (nettx_enabled && last_tx_delta != tx_delta) {
+		last_tx_delta = tx_delta;
+		netGet[len++] = nettx_key;
+		/* indicates to Streamline that tx_delta bytes were transmitted now, not since the last message */
+		netGet[len++] = 0;
+		netGet[len++] = nettx_key;
+		netGet[len++] = tx_delta;
+	}
+
+	if (buffer)
+		*buffer = netGet;
+
+	return len;
+}
+
+static struct gator_interface gator_events_net_interface = {
+	.name = "net",
+	.create_files = gator_events_net_create_files,
+	.start = gator_events_net_start,
+	.stop = gator_events_net_stop,
+	.read = gator_events_net_read,
+};
+
+int gator_events_net_init(void)
+{
+	netrx_key = gator_events_get_key();
+	nettx_key = gator_events_get_key();
+
+	netrx_enabled = 0;
+	nettx_enabled = 0;
+
+	return gator_events_install(&gator_events_net_interface);
+}
diff --git a/drivers/gator/gator_events_perf_pmu.c b/drivers/gator/gator_events_perf_pmu.c
new file mode 100644
index 00000000000..e62492bbd53
--- /dev/null
+++ b/drivers/gator/gator_events_perf_pmu.c
@@ -0,0 +1,591 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+/* gator_events_armvX.c is used for Linux 2.6.x */
+#if GATOR_PERF_PMU_SUPPORT
+
+#include <linux/io.h>
+#ifdef CONFIG_OF
+#include <linux/of_address.h>
+#endif
+#include <linux/perf_event.h>
+#include <linux/slab.h>
+
+extern bool event_based_sampling;
+
+/* Maximum number of per-core counters - currently reserves enough space for two full hardware PMUs for big.LITTLE */
+#define CNTMAX 16
+#define CCI_400 4
+#define CCI_500 8
+#define CCN_5XX 8
+/* Maximum number of uncore counters */
+/* + 1 for the cci-400 cycles counter */
+/* cci-500 has no cycles counter */
+/* + 1 for the CCN-5xx cycles counter */
+#define UCCNT (CCI_400 + 1 + CCI_500 + CCN_5XX + 1)
+
+/* Default to 0 if unable to probe the revision which was the previous behavior */
+#define DEFAULT_CCI_REVISION 0
+
+/* A gator_attr is needed for every counter */
+struct gator_attr {
+	/* Set once in gator_events_perf_pmu_*_init - the name of the event in the gatorfs */
+	char name[40];
+	/* Exposed in gatorfs - set by gatord to enable this counter */
+	unsigned long enabled;
+	/* Set once in gator_events_perf_pmu_*_init - the perf type to use, see perf_type_id in the perf_event.h header file. */
+	unsigned long type;
+	/* Exposed in gatorfs - set by gatord to select the event to collect */
+	unsigned long event;
+	/* Exposed in gatorfs - set by gatord with the sample period to use and enable EBS for this counter */
+	unsigned long count;
+	/* Exposed as read only in gatorfs - set once in __attr_init as the key to use in the APC data */
+	unsigned long key;
+};
+
+/* Per-core counter attributes */
+static struct gator_attr attrs[CNTMAX];
+/* Number of initialized per-core counters */
+static int attr_count;
+/* Uncore counter attributes */
+static struct gator_attr uc_attrs[UCCNT];
+/* Number of initialized uncore counters */
+static int uc_attr_count;
+
+struct gator_event {
+	uint32_t curr;
+	uint32_t prev;
+	uint32_t prev_delta;
+	bool zero;
+	struct perf_event *pevent;
+	struct perf_event_attr *pevent_attr;
+};
+
+static DEFINE_PER_CPU(struct gator_event[CNTMAX], events);
+static struct gator_event uc_events[UCCNT];
+static DEFINE_PER_CPU(int[(CNTMAX + UCCNT)*2], perf_cnt);
+
+static void gator_events_perf_pmu_stop(void);
+
+static int __create_files(struct super_block *sb, struct dentry *root, struct gator_attr *const attr)
+{
+	struct dentry *dir;
+
+	if (attr->name[0] == '\0')
+		return 0;
+	dir = gatorfs_mkdir(sb, root, attr->name);
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &attr->enabled);
+	gatorfs_create_ulong(sb, dir, "count", &attr->count);
+	gatorfs_create_ro_ulong(sb, dir, "key", &attr->key);
+	gatorfs_create_ulong(sb, dir, "event", &attr->event);
+
+	return 0;
+}
+
+static int gator_events_perf_pmu_create_files(struct super_block *sb, struct dentry *root)
+{
+	int cnt;
+
+	for (cnt = 0; cnt < attr_count; cnt++) {
+		if (__create_files(sb, root, &attrs[cnt]) != 0)
+			return -1;
+	}
+
+	for (cnt = 0; cnt < uc_attr_count; cnt++) {
+		if (__create_files(sb, root, &uc_attrs[cnt]) != 0)
+			return -1;
+	}
+
+	return 0;
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+static void ebs_overflow_handler(struct perf_event *event, int unused, struct perf_sample_data *data, struct pt_regs *regs)
+#else
+static void ebs_overflow_handler(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs)
+#endif
+{
+	gator_backtrace_handler(regs);
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+static void dummy_handler(struct perf_event *event, int unused, struct perf_sample_data *data, struct pt_regs *regs)
+#else
+static void dummy_handler(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs)
+#endif
+{
+	/* Required as perf_event_create_kernel_counter() requires an overflow handler, even though all we do is poll */
+}
+
+static int gator_events_perf_pmu_read(int **buffer, bool sched_switch);
+
+static int gator_events_perf_pmu_online(int **buffer, bool migrate)
+{
+	return gator_events_perf_pmu_read(buffer, false);
+}
+
+static void __online_dispatch(int cpu, bool migrate, struct gator_attr *const attr, struct gator_event *const event)
+{
+	perf_overflow_handler_t handler;
+	struct perf_event *pevent;
+
+	event->zero = true;
+
+	if (event->pevent != NULL || event->pevent_attr == 0 || migrate)
+		return;
+
+	if (attr->count > 0)
+		handler = ebs_overflow_handler;
+	else
+		handler = dummy_handler;
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+	pevent = perf_event_create_kernel_counter(event->pevent_attr, cpu, 0, handler);
+#else
+	pevent = perf_event_create_kernel_counter(event->pevent_attr, cpu, 0, handler, 0);
+#endif
+	if (IS_ERR(pevent)) {
+		pr_err("gator: unable to online a counter on cpu %d\n", cpu);
+		return;
+	}
+
+	if (pevent->state != PERF_EVENT_STATE_ACTIVE) {
+		pr_err("gator: inactive counter on cpu %d\n", cpu);
+		perf_event_release_kernel(pevent);
+		return;
+	}
+
+	event->pevent = pevent;
+}
+
+static void gator_events_perf_pmu_online_dispatch(int cpu, bool migrate)
+{
+	int cnt;
+
+	cpu = pcpu_to_lcpu(cpu);
+
+	for (cnt = 0; cnt < attr_count; cnt++)
+		__online_dispatch(cpu, migrate, &attrs[cnt], &per_cpu(events, cpu)[cnt]);
+
+	if (cpu == 0) {
+		for (cnt = 0; cnt < uc_attr_count; cnt++)
+			__online_dispatch(cpu, migrate, &uc_attrs[cnt], &uc_events[cnt]);
+	}
+}
+
+static void __offline_dispatch(int cpu, struct gator_event *const event)
+{
+	struct perf_event *pe = NULL;
+
+	if (event->pevent) {
+		pe = event->pevent;
+		event->pevent = NULL;
+	}
+
+	if (pe)
+		perf_event_release_kernel(pe);
+}
+
+static void gator_events_perf_pmu_offline_dispatch(int cpu, bool migrate)
+{
+	int cnt;
+
+	if (migrate)
+		return;
+	cpu = pcpu_to_lcpu(cpu);
+
+	for (cnt = 0; cnt < attr_count; cnt++)
+		__offline_dispatch(cpu, &per_cpu(events, cpu)[cnt]);
+
+	if (cpu == 0) {
+		for (cnt = 0; cnt < uc_attr_count; cnt++)
+			__offline_dispatch(cpu, &uc_events[cnt]);
+	}
+}
+
+static int __check_ebs(struct gator_attr *const attr)
+{
+	if (attr->count > 0) {
+		if (!event_based_sampling) {
+			event_based_sampling = true;
+		} else {
+			pr_warning("gator: Only one ebs counter is allowed\n");
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+static int __start(struct gator_attr *const attr, struct gator_event *const event)
+{
+	u32 size = sizeof(struct perf_event_attr);
+
+	event->pevent = NULL;
+	/* Skip disabled counters */
+	if (!attr->enabled)
+		return 0;
+
+	event->prev = 0;
+	event->curr = 0;
+	event->prev_delta = 0;
+	event->pevent_attr = kmalloc(size, GFP_KERNEL);
+	if (!event->pevent_attr) {
+		gator_events_perf_pmu_stop();
+		return -1;
+	}
+
+	memset(event->pevent_attr, 0, size);
+	event->pevent_attr->type = attr->type;
+	event->pevent_attr->size = size;
+	event->pevent_attr->config = attr->event;
+	event->pevent_attr->sample_period = attr->count;
+	event->pevent_attr->pinned = 1;
+
+	return 0;
+}
+
+static int gator_events_perf_pmu_start(void)
+{
+	int cnt, cpu;
+
+	event_based_sampling = false;
+	for (cnt = 0; cnt < attr_count; cnt++) {
+		if (__check_ebs(&attrs[cnt]) != 0)
+			return -1;
+	}
+
+	for (cnt = 0; cnt < uc_attr_count; cnt++) {
+		if (__check_ebs(&uc_attrs[cnt]) != 0)
+			return -1;
+	}
+
+	for_each_present_cpu(cpu) {
+		for (cnt = 0; cnt < attr_count; cnt++) {
+			if (__start(&attrs[cnt], &per_cpu(events, cpu)[cnt]) != 0)
+				return -1;
+		}
+	}
+
+	for (cnt = 0; cnt < uc_attr_count; cnt++) {
+		if (__start(&uc_attrs[cnt], &uc_events[cnt]) != 0)
+			return -1;
+	}
+
+	return 0;
+}
+
+static void __event_stop(struct gator_event *const event)
+{
+	kfree(event->pevent_attr);
+	event->pevent_attr = NULL;
+}
+
+static void __attr_stop(struct gator_attr *const attr)
+{
+	attr->enabled = 0;
+	attr->event = 0;
+	attr->count = 0;
+}
+
+static void gator_events_perf_pmu_stop(void)
+{
+	unsigned int cnt, cpu;
+
+	for_each_present_cpu(cpu) {
+		for (cnt = 0; cnt < attr_count; cnt++)
+			__event_stop(&per_cpu(events, cpu)[cnt]);
+	}
+
+	for (cnt = 0; cnt < uc_attr_count; cnt++)
+		__event_stop(&uc_events[cnt]);
+
+	for (cnt = 0; cnt < attr_count; cnt++)
+		__attr_stop(&attrs[cnt]);
+
+	for (cnt = 0; cnt < uc_attr_count; cnt++)
+		__attr_stop(&uc_attrs[cnt]);
+}
+
+static void __read(int *const len, int cpu, struct gator_attr *const attr, struct gator_event *const event)
+{
+	uint32_t delta;
+	struct perf_event *const ev = event->pevent;
+
+	if (ev != NULL && ev->state == PERF_EVENT_STATE_ACTIVE) {
+		/* After creating the perf counter in __online_dispatch, there
+		 * is a race condition between gator_events_perf_pmu_online and
+		 * gator_events_perf_pmu_read. So have
+		 * gator_events_perf_pmu_online call gator_events_perf_pmu_read
+		 * and in __read check to see if it's the first call after
+		 * __online_dispatch and if so, run the online code.
+		 */
+		if (event->zero) {
+			ev->pmu->read(ev);
+			event->prev = event->curr = local64_read(&ev->count);
+			event->prev_delta = 0;
+			per_cpu(perf_cnt, cpu)[(*len)++] = attr->key;
+			per_cpu(perf_cnt, cpu)[(*len)++] = 0;
+			event->zero = false;
+		} else {
+			ev->pmu->read(ev);
+			event->curr = local64_read(&ev->count);
+			delta = event->curr - event->prev;
+			if (delta != 0 || delta != event->prev_delta) {
+				event->prev_delta = delta;
+				event->prev = event->curr;
+				per_cpu(perf_cnt, cpu)[(*len)++] = attr->key;
+				per_cpu(perf_cnt, cpu)[(*len)++] = delta;
+			}
+		}
+	}
+}
+
+static int gator_events_perf_pmu_read(int **buffer, bool sched_switch)
+{
+	int cnt, len = 0;
+	const int cpu = get_logical_cpu();
+
+	for (cnt = 0; cnt < attr_count; cnt++)
+		__read(&len, cpu, &attrs[cnt], &per_cpu(events, cpu)[cnt]);
+
+	if (cpu == 0) {
+		for (cnt = 0; cnt < uc_attr_count; cnt++)
+			__read(&len, cpu, &uc_attrs[cnt], &uc_events[cnt]);
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perf_cnt, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_perf_pmu_interface = {
+	.name = "perf_pmu",
+	.create_files = gator_events_perf_pmu_create_files,
+	.start = gator_events_perf_pmu_start,
+	.stop = gator_events_perf_pmu_stop,
+	.online = gator_events_perf_pmu_online,
+	.online_dispatch = gator_events_perf_pmu_online_dispatch,
+	.offline_dispatch = gator_events_perf_pmu_offline_dispatch,
+	.read = gator_events_perf_pmu_read,
+};
+
+static void __attr_init(struct gator_attr *const attr)
+{
+	attr->name[0] = '\0';
+	attr->enabled = 0;
+	attr->type = 0;
+	attr->event = 0;
+	attr->count = 0;
+	attr->key = gator_events_get_key();
+}
+
+#ifdef CONFIG_OF
+
+static const struct of_device_id arm_cci_matches[] = {
+	{.compatible = "arm,cci-400" },
+	{},
+};
+
+static int probe_cci_revision(void)
+{
+	struct device_node *np;
+	struct resource res;
+	void __iomem *cci_ctrl_base;
+	int rev;
+	int ret = DEFAULT_CCI_REVISION;
+
+	np = of_find_matching_node(NULL, arm_cci_matches);
+	if (!np)
+		return ret;
+
+	if (of_address_to_resource(np, 0, &res))
+		goto node_put;
+
+	cci_ctrl_base = ioremap(res.start, resource_size(&res));
+
+	rev = (readl_relaxed(cci_ctrl_base + 0xfe8) >> 4) & 0xf;
+
+	if (rev <= 4)
+		ret = 0;
+	else if (rev <= 6)
+		ret = 1;
+
+	iounmap(cci_ctrl_base);
+
+ node_put:
+	of_node_put(np);
+
+	return ret;
+}
+
+#else
+
+static int probe_cci_revision(void)
+{
+	return DEFAULT_CCI_REVISION;
+}
+
+#endif
+
+static void gator_events_perf_pmu_uncore_init(const char *const name, const int type, const int count, const bool has_cycles_counter)
+{
+	int cnt;
+
+	if (has_cycles_counter) {
+		snprintf(uc_attrs[uc_attr_count].name, sizeof(uc_attrs[uc_attr_count].name), "%s_ccnt", name);
+		uc_attrs[uc_attr_count].type = type;
+		++uc_attr_count;
+	}
+
+	for (cnt = 0; cnt < count; ++cnt, ++uc_attr_count) {
+		struct gator_attr *const attr = &uc_attrs[uc_attr_count];
+
+		snprintf(attr->name, sizeof(attr->name), "%s_cnt%d", name, cnt);
+		attr->type = type;
+	}
+}
+
+static void gator_events_perf_pmu_cci_400_init(const int type)
+{
+	const char *cci_name;
+
+	switch (probe_cci_revision()) {
+	case 0:
+		cci_name = "CCI_400";
+		break;
+	case 1:
+		cci_name = "CCI_400_r1";
+		break;
+	default:
+		pr_err("gator: unrecognized cci-400 revision\n");
+		return;
+	}
+
+	gator_events_perf_pmu_uncore_init(cci_name, type, CCI_400, true);
+}
+
+static void gator_events_perf_pmu_cpu_init(const struct gator_cpu *const gator_cpu, const int type)
+{
+	int cnt;
+
+	snprintf(attrs[attr_count].name, sizeof(attrs[attr_count].name), "%s_ccnt", gator_cpu->pmnc_name);
+	attrs[attr_count].type = type;
+	++attr_count;
+
+	for (cnt = 0; cnt < gator_cpu->pmnc_counters; ++cnt, ++attr_count) {
+		struct gator_attr *const attr = &attrs[attr_count];
+
+		snprintf(attr->name, sizeof(attr->name), "%s_cnt%d", gator_cpu->pmnc_name, cnt);
+		attr->type = type;
+	}
+}
+
+int gator_events_perf_pmu_init(void)
+{
+	struct perf_event_attr pea;
+	struct perf_event *pe;
+	const struct gator_cpu *gator_cpu;
+	int type;
+	int cpu;
+	int cnt;
+	bool found_cpu = false;
+
+	for (cnt = 0; cnt < CNTMAX; cnt++)
+		__attr_init(&attrs[cnt]);
+	for (cnt = 0; cnt < UCCNT; cnt++)
+		__attr_init(&uc_attrs[cnt]);
+
+	memset(&pea, 0, sizeof(pea));
+	pea.size = sizeof(pea);
+	pea.config = 0xFF;
+	attr_count = 0;
+	uc_attr_count = 0;
+	for (type = PERF_TYPE_MAX; type < 0x20; ++type) {
+		pea.type = type;
+
+		/* A particular PMU may work on some but not all cores, so try on each core */
+		pe = NULL;
+		for_each_present_cpu(cpu) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+			pe = perf_event_create_kernel_counter(&pea, cpu, 0, dummy_handler);
+#else
+			pe = perf_event_create_kernel_counter(&pea, cpu, 0, dummy_handler, 0);
+#endif
+			if (!IS_ERR(pe))
+				break;
+		}
+		/* Assume that valid PMUs are contiguous */
+		if (IS_ERR(pe)) {
+			pea.config = 0xff00;
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+			pe = perf_event_create_kernel_counter(&pea, 0, 0, dummy_handler);
+#else
+			pe = perf_event_create_kernel_counter(&pea, 0, 0, dummy_handler, 0);
+#endif
+			if (IS_ERR(pe))
+				break;
+		}
+
+		if (pe->pmu != NULL && type == pe->pmu->type) {
+			pr_notice("gator: perf pmu: %s\n", pe->pmu->name);
+			if (strcmp("CCI", pe->pmu->name) == 0 || strcmp("CCI_400", pe->pmu->name) == 0 || strcmp("CCI_400_r1", pe->pmu->name) == 0) {
+				pr_notice("gator: Adding CCI-400 counters with type %i\n", type);
+				gator_events_perf_pmu_cci_400_init(type);
+			} else if (strcmp("CCI_500", pe->pmu->name) == 0) {
+				pr_notice("gator: Adding CCI-500 counters with type %i\n", type);
+				gator_events_perf_pmu_uncore_init("CCI_500", type, CCI_500, false);
+			} else if (strcmp("ccn", pe->pmu->name) == 0) {
+				pr_notice("gator: Adding CCN counters with type %i\n", type);
+				gator_events_perf_pmu_uncore_init("ARM_CCN_5XX", type, CCN_5XX, true);
+			} else if ((gator_cpu = gator_find_cpu_by_pmu_name(pe->pmu->name)) != NULL) {
+				found_cpu = true;
+				pr_notice("gator: Adding cpu counters for %s with type %i\n", gator_cpu->pmnc_name, type);
+				gator_events_perf_pmu_cpu_init(gator_cpu, type);
+			}
+			/* Initialize gator_attrs for dynamic PMUs here */
+		}
+
+		perf_event_release_kernel(pe);
+	}
+
+	if (!found_cpu) {
+		const struct gator_cpu *gator_cpu = gator_find_cpu_by_cpuid(gator_cpuid());
+
+		if (gator_cpu == NULL) {
+			gator_cpu = gator_find_cpu_by_cpuid(OTHER);
+			if (gator_cpu == NULL) {
+				pr_err("gator: Didn't find cpu\n");
+				return -1;
+			}
+		}
+		pr_notice("gator: Adding cpu counters (based on cpuid) for %s\n", gator_cpu->pmnc_name);
+		gator_events_perf_pmu_cpu_init(gator_cpu, PERF_TYPE_RAW);
+	}
+
+	/* Initialize gator_attrs for non-dynamic PMUs here */
+
+	if (attr_count > CNTMAX) {
+		pr_err("gator: Too many perf counters\n");
+		return -1;
+	}
+
+	if (uc_attr_count > UCCNT) {
+		pr_err("gator: Too many perf uncore counters\n");
+		return -1;
+	}
+
+	return gator_events_install(&gator_events_perf_pmu_interface);
+}
+
+#endif
diff --git a/drivers/gator/gator_events_sched.c b/drivers/gator/gator_events_sched.c
new file mode 100644
index 00000000000..d3524157ab4
--- /dev/null
+++ b/drivers/gator/gator_events_sched.c
@@ -0,0 +1,114 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+#include <trace/events/sched.h>
+
+#define SCHED_SWITCH	0
+#define SCHED_TOTAL		(SCHED_SWITCH+1)
+
+static ulong sched_switch_enabled;
+static ulong sched_switch_key;
+static DEFINE_PER_CPU(int[SCHED_TOTAL], schedCnt);
+static DEFINE_PER_CPU(int[SCHED_TOTAL * 2], schedGet);
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 35)
+GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct rq *rq, struct task_struct *prev, struct task_struct *next))
+#else
+GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct task_struct *prev, struct task_struct *next))
+#endif
+{
+	unsigned long flags;
+
+	/* disable interrupts to synchronize with gator_events_sched_read()
+	 * spinlocks not needed since percpu buffers are used
+	 */
+	local_irq_save(flags);
+	per_cpu(schedCnt, get_physical_cpu())[SCHED_SWITCH]++;
+	local_irq_restore(flags);
+}
+
+static int gator_events_sched_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+
+	/* switch */
+	dir = gatorfs_mkdir(sb, root, "Linux_sched_switch");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &sched_switch_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &sched_switch_key);
+
+	return 0;
+}
+
+static int gator_events_sched_start(void)
+{
+	/* register tracepoints */
+	if (sched_switch_enabled)
+		if (GATOR_REGISTER_TRACE(sched_switch))
+			goto sched_switch_exit;
+	pr_debug("gator: registered scheduler event tracepoints\n");
+
+	return 0;
+
+	/* unregister tracepoints on error */
+sched_switch_exit:
+	pr_err("gator: scheduler event tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+	return -1;
+}
+
+static void gator_events_sched_stop(void)
+{
+	if (sched_switch_enabled)
+		GATOR_UNREGISTER_TRACE(sched_switch);
+	pr_debug("gator: unregistered scheduler event tracepoints\n");
+
+	sched_switch_enabled = 0;
+}
+
+static int gator_events_sched_read(int **buffer, bool sched_switch)
+{
+	unsigned long flags;
+	int len, value;
+	int cpu = get_physical_cpu();
+
+	len = 0;
+	if (sched_switch_enabled) {
+		local_irq_save(flags);
+		value = per_cpu(schedCnt, cpu)[SCHED_SWITCH];
+		per_cpu(schedCnt, cpu)[SCHED_SWITCH] = 0;
+		local_irq_restore(flags);
+		per_cpu(schedGet, cpu)[len++] = sched_switch_key;
+		per_cpu(schedGet, cpu)[len++] = value;
+	}
+
+	if (buffer)
+		*buffer = per_cpu(schedGet, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_sched_interface = {
+	.name = "sched",
+	.create_files = gator_events_sched_create_files,
+	.start = gator_events_sched_start,
+	.stop = gator_events_sched_stop,
+	.read = gator_events_sched_read,
+};
+
+int gator_events_sched_init(void)
+{
+	sched_switch_enabled = 0;
+
+	sched_switch_key = gator_events_get_key();
+
+	return gator_events_install(&gator_events_sched_interface);
+}
diff --git a/drivers/gator/gator_events_scorpion.c b/drivers/gator/gator_events_scorpion.c
new file mode 100644
index 00000000000..efb5e7a0b87
--- /dev/null
+++ b/drivers/gator/gator_events_scorpion.c
@@ -0,0 +1,675 @@
+/**
+ * Copyright (C) ARM Limited 2011-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+/* gator_events_perf_pmu.c is used if perf is supported */
+#if GATOR_NO_PERF_SUPPORT
+
+static const char *pmnc_name;
+static int pmnc_counters;
+
+/* Per-CPU PMNC: config reg */
+#define PMNC_E		(1 << 0)	/* Enable all counters */
+#define PMNC_P		(1 << 1)	/* Reset all counters */
+#define PMNC_C		(1 << 2)	/* Cycle counter reset */
+#define PMNC_D		(1 << 3)	/* CCNT counts every 64th cpu cycle */
+#define PMNC_X		(1 << 4)	/* Export to ETM */
+#define PMNC_DP		(1 << 5)	/* Disable CCNT if non-invasive debug */
+#define	PMNC_MASK	0x3f	/* Mask for writable bits */
+
+/* ccnt reg */
+#define CCNT_REG	(1 << 31)
+
+#define CCNT		0
+#define CNT0		1
+#define CNTMAX		(4+1)
+
+static unsigned long pmnc_enabled[CNTMAX];
+static unsigned long pmnc_event[CNTMAX];
+static unsigned long pmnc_key[CNTMAX];
+
+static DEFINE_PER_CPU(int[CNTMAX * 2], perfCnt);
+
+enum scorpion_perf_types {
+	SCORPION_ICACHE_EXPL_INV = 0x4c,
+	SCORPION_ICACHE_MISS = 0x4d,
+	SCORPION_ICACHE_ACCESS = 0x4e,
+	SCORPION_ICACHE_CACHEREQ_L2 = 0x4f,
+	SCORPION_ICACHE_NOCACHE_L2 = 0x50,
+	SCORPION_HIQUP_NOPED = 0x51,
+	SCORPION_DATA_ABORT = 0x52,
+	SCORPION_IRQ = 0x53,
+	SCORPION_FIQ = 0x54,
+	SCORPION_ALL_EXCPT = 0x55,
+	SCORPION_UNDEF = 0x56,
+	SCORPION_SVC = 0x57,
+	SCORPION_SMC = 0x58,
+	SCORPION_PREFETCH_ABORT = 0x59,
+	SCORPION_INDEX_CHECK = 0x5a,
+	SCORPION_NULL_CHECK = 0x5b,
+	SCORPION_EXPL_ICIALLU = 0x5c,
+	SCORPION_IMPL_ICIALLU = 0x5d,
+	SCORPION_NONICIALLU_BTAC_INV = 0x5e,
+	SCORPION_ICIMVAU_IMPL_ICIALLU = 0x5f,
+	SCORPION_SPIPE_ONLY_CYCLES = 0x60,
+	SCORPION_XPIPE_ONLY_CYCLES = 0x61,
+	SCORPION_DUAL_CYCLES = 0x62,
+	SCORPION_DISPATCH_ANY_CYCLES = 0x63,
+	SCORPION_FIFO_FULLBLK_CMT = 0x64,
+	SCORPION_FAIL_COND_INST = 0x65,
+	SCORPION_PASS_COND_INST = 0x66,
+	SCORPION_ALLOW_VU_CLK = 0x67,
+	SCORPION_VU_IDLE = 0x68,
+	SCORPION_ALLOW_L2_CLK = 0x69,
+	SCORPION_L2_IDLE = 0x6a,
+	SCORPION_DTLB_IMPL_INV_SCTLR_DACR = 0x6b,
+	SCORPION_DTLB_EXPL_INV = 0x6c,
+	SCORPION_DTLB_MISS = 0x6d,
+	SCORPION_DTLB_ACCESS = 0x6e,
+	SCORPION_ITLB_MISS = 0x6f,
+	SCORPION_ITLB_IMPL_INV = 0x70,
+	SCORPION_ITLB_EXPL_INV = 0x71,
+	SCORPION_UTLB_D_MISS = 0x72,
+	SCORPION_UTLB_D_ACCESS = 0x73,
+	SCORPION_UTLB_I_MISS = 0x74,
+	SCORPION_UTLB_I_ACCESS = 0x75,
+	SCORPION_UTLB_INV_ASID = 0x76,
+	SCORPION_UTLB_INV_MVA = 0x77,
+	SCORPION_UTLB_INV_ALL = 0x78,
+	SCORPION_S2_HOLD_RDQ_UNAVAIL = 0x79,
+	SCORPION_S2_HOLD = 0x7a,
+	SCORPION_S2_HOLD_DEV_OP = 0x7b,
+	SCORPION_S2_HOLD_ORDER = 0x7c,
+	SCORPION_S2_HOLD_BARRIER = 0x7d,
+	SCORPION_VIU_DUAL_CYCLE = 0x7e,
+	SCORPION_VIU_SINGLE_CYCLE = 0x7f,
+	SCORPION_VX_PIPE_WAR_STALL_CYCLES = 0x80,
+	SCORPION_VX_PIPE_WAW_STALL_CYCLES = 0x81,
+	SCORPION_VX_PIPE_RAW_STALL_CYCLES = 0x82,
+	SCORPION_VX_PIPE_LOAD_USE_STALL = 0x83,
+	SCORPION_VS_PIPE_WAR_STALL_CYCLES = 0x84,
+	SCORPION_VS_PIPE_WAW_STALL_CYCLES = 0x85,
+	SCORPION_VS_PIPE_RAW_STALL_CYCLES = 0x86,
+	SCORPION_EXCEPTIONS_INV_OPERATION = 0x87,
+	SCORPION_EXCEPTIONS_DIV_BY_ZERO = 0x88,
+	SCORPION_COND_INST_FAIL_VX_PIPE = 0x89,
+	SCORPION_COND_INST_FAIL_VS_PIPE = 0x8a,
+	SCORPION_EXCEPTIONS_OVERFLOW = 0x8b,
+	SCORPION_EXCEPTIONS_UNDERFLOW = 0x8c,
+	SCORPION_EXCEPTIONS_DENORM = 0x8d,
+#ifdef CONFIG_ARCH_MSM_SCORPIONMP
+	SCORPIONMP_NUM_BARRIERS = 0x8e,
+	SCORPIONMP_BARRIER_CYCLES = 0x8f,
+#else
+	SCORPION_BANK_AB_HIT = 0x8e,
+	SCORPION_BANK_AB_ACCESS = 0x8f,
+	SCORPION_BANK_CD_HIT = 0x90,
+	SCORPION_BANK_CD_ACCESS = 0x91,
+	SCORPION_BANK_AB_DSIDE_HIT = 0x92,
+	SCORPION_BANK_AB_DSIDE_ACCESS = 0x93,
+	SCORPION_BANK_CD_DSIDE_HIT = 0x94,
+	SCORPION_BANK_CD_DSIDE_ACCESS = 0x95,
+	SCORPION_BANK_AB_ISIDE_HIT = 0x96,
+	SCORPION_BANK_AB_ISIDE_ACCESS = 0x97,
+	SCORPION_BANK_CD_ISIDE_HIT = 0x98,
+	SCORPION_BANK_CD_ISIDE_ACCESS = 0x99,
+	SCORPION_ISIDE_RD_WAIT = 0x9a,
+	SCORPION_DSIDE_RD_WAIT = 0x9b,
+	SCORPION_BANK_BYPASS_WRITE = 0x9c,
+	SCORPION_BANK_AB_NON_CASTOUT = 0x9d,
+	SCORPION_BANK_AB_L2_CASTOUT = 0x9e,
+	SCORPION_BANK_CD_NON_CASTOUT = 0x9f,
+	SCORPION_BANK_CD_L2_CASTOUT = 0xa0,
+#endif
+	MSM_MAX_EVT
+};
+
+struct scorp_evt {
+	u32 evt_type;
+	u32 val;
+	u8 grp;
+	u32 evt_type_act;
+};
+
+static const struct scorp_evt sc_evt[] = {
+	{SCORPION_ICACHE_EXPL_INV, 0x80000500, 0, 0x4d},
+	{SCORPION_ICACHE_MISS, 0x80050000, 0, 0x4e},
+	{SCORPION_ICACHE_ACCESS, 0x85000000, 0, 0x4f},
+	{SCORPION_ICACHE_CACHEREQ_L2, 0x86000000, 0, 0x4f},
+	{SCORPION_ICACHE_NOCACHE_L2, 0x87000000, 0, 0x4f},
+	{SCORPION_HIQUP_NOPED, 0x80080000, 0, 0x4e},
+	{SCORPION_DATA_ABORT, 0x8000000a, 0, 0x4c},
+	{SCORPION_IRQ, 0x80000a00, 0, 0x4d},
+	{SCORPION_FIQ, 0x800a0000, 0, 0x4e},
+	{SCORPION_ALL_EXCPT, 0x8a000000, 0, 0x4f},
+	{SCORPION_UNDEF, 0x8000000b, 0, 0x4c},
+	{SCORPION_SVC, 0x80000b00, 0, 0x4d},
+	{SCORPION_SMC, 0x800b0000, 0, 0x4e},
+	{SCORPION_PREFETCH_ABORT, 0x8b000000, 0, 0x4f},
+	{SCORPION_INDEX_CHECK, 0x8000000c, 0, 0x4c},
+	{SCORPION_NULL_CHECK, 0x80000c00, 0, 0x4d},
+	{SCORPION_EXPL_ICIALLU, 0x8000000d, 0, 0x4c},
+	{SCORPION_IMPL_ICIALLU, 0x80000d00, 0, 0x4d},
+	{SCORPION_NONICIALLU_BTAC_INV, 0x800d0000, 0, 0x4e},
+	{SCORPION_ICIMVAU_IMPL_ICIALLU, 0x8d000000, 0, 0x4f},
+
+	{SCORPION_SPIPE_ONLY_CYCLES, 0x80000600, 1, 0x51},
+	{SCORPION_XPIPE_ONLY_CYCLES, 0x80060000, 1, 0x52},
+	{SCORPION_DUAL_CYCLES, 0x86000000, 1, 0x53},
+	{SCORPION_DISPATCH_ANY_CYCLES, 0x89000000, 1, 0x53},
+	{SCORPION_FIFO_FULLBLK_CMT, 0x8000000d, 1, 0x50},
+	{SCORPION_FAIL_COND_INST, 0x800d0000, 1, 0x52},
+	{SCORPION_PASS_COND_INST, 0x8d000000, 1, 0x53},
+	{SCORPION_ALLOW_VU_CLK, 0x8000000e, 1, 0x50},
+	{SCORPION_VU_IDLE, 0x80000e00, 1, 0x51},
+	{SCORPION_ALLOW_L2_CLK, 0x800e0000, 1, 0x52},
+	{SCORPION_L2_IDLE, 0x8e000000, 1, 0x53},
+
+	{SCORPION_DTLB_IMPL_INV_SCTLR_DACR, 0x80000001, 2, 0x54},
+	{SCORPION_DTLB_EXPL_INV, 0x80000100, 2, 0x55},
+	{SCORPION_DTLB_MISS, 0x80010000, 2, 0x56},
+	{SCORPION_DTLB_ACCESS, 0x81000000, 2, 0x57},
+	{SCORPION_ITLB_MISS, 0x80000200, 2, 0x55},
+	{SCORPION_ITLB_IMPL_INV, 0x80020000, 2, 0x56},
+	{SCORPION_ITLB_EXPL_INV, 0x82000000, 2, 0x57},
+	{SCORPION_UTLB_D_MISS, 0x80000003, 2, 0x54},
+	{SCORPION_UTLB_D_ACCESS, 0x80000300, 2, 0x55},
+	{SCORPION_UTLB_I_MISS, 0x80030000, 2, 0x56},
+	{SCORPION_UTLB_I_ACCESS, 0x83000000, 2, 0x57},
+	{SCORPION_UTLB_INV_ASID, 0x80000400, 2, 0x55},
+	{SCORPION_UTLB_INV_MVA, 0x80040000, 2, 0x56},
+	{SCORPION_UTLB_INV_ALL, 0x84000000, 2, 0x57},
+	{SCORPION_S2_HOLD_RDQ_UNAVAIL, 0x80000800, 2, 0x55},
+	{SCORPION_S2_HOLD, 0x88000000, 2, 0x57},
+	{SCORPION_S2_HOLD_DEV_OP, 0x80000900, 2, 0x55},
+	{SCORPION_S2_HOLD_ORDER, 0x80090000, 2, 0x56},
+	{SCORPION_S2_HOLD_BARRIER, 0x89000000, 2, 0x57},
+
+	{SCORPION_VIU_DUAL_CYCLE, 0x80000001, 4, 0x5c},
+	{SCORPION_VIU_SINGLE_CYCLE, 0x80000100, 4, 0x5d},
+	{SCORPION_VX_PIPE_WAR_STALL_CYCLES, 0x80000005, 4, 0x5c},
+	{SCORPION_VX_PIPE_WAW_STALL_CYCLES, 0x80000500, 4, 0x5d},
+	{SCORPION_VX_PIPE_RAW_STALL_CYCLES, 0x80050000, 4, 0x5e},
+	{SCORPION_VX_PIPE_LOAD_USE_STALL, 0x80000007, 4, 0x5c},
+	{SCORPION_VS_PIPE_WAR_STALL_CYCLES, 0x80000008, 4, 0x5c},
+	{SCORPION_VS_PIPE_WAW_STALL_CYCLES, 0x80000800, 4, 0x5d},
+	{SCORPION_VS_PIPE_RAW_STALL_CYCLES, 0x80080000, 4, 0x5e},
+	{SCORPION_EXCEPTIONS_INV_OPERATION, 0x8000000b, 4, 0x5c},
+	{SCORPION_EXCEPTIONS_DIV_BY_ZERO, 0x80000b00, 4, 0x5d},
+	{SCORPION_COND_INST_FAIL_VX_PIPE, 0x800b0000, 4, 0x5e},
+	{SCORPION_COND_INST_FAIL_VS_PIPE, 0x8b000000, 4, 0x5f},
+	{SCORPION_EXCEPTIONS_OVERFLOW, 0x8000000c, 4, 0x5c},
+	{SCORPION_EXCEPTIONS_UNDERFLOW, 0x80000c00, 4, 0x5d},
+	{SCORPION_EXCEPTIONS_DENORM, 0x8c000000, 4, 0x5f},
+
+#ifdef CONFIG_ARCH_MSM_SCORPIONMP
+	{SCORPIONMP_NUM_BARRIERS, 0x80000e00, 3, 0x59},
+	{SCORPIONMP_BARRIER_CYCLES, 0x800e0000, 3, 0x5a},
+#else
+	{SCORPION_BANK_AB_HIT, 0x80000001, 3, 0x58},
+	{SCORPION_BANK_AB_ACCESS, 0x80000100, 3, 0x59},
+	{SCORPION_BANK_CD_HIT, 0x80010000, 3, 0x5a},
+	{SCORPION_BANK_CD_ACCESS, 0x81000000, 3, 0x5b},
+	{SCORPION_BANK_AB_DSIDE_HIT, 0x80000002, 3, 0x58},
+	{SCORPION_BANK_AB_DSIDE_ACCESS, 0x80000200, 3, 0x59},
+	{SCORPION_BANK_CD_DSIDE_HIT, 0x80020000, 3, 0x5a},
+	{SCORPION_BANK_CD_DSIDE_ACCESS, 0x82000000, 3, 0x5b},
+	{SCORPION_BANK_AB_ISIDE_HIT, 0x80000003, 3, 0x58},
+	{SCORPION_BANK_AB_ISIDE_ACCESS, 0x80000300, 3, 0x59},
+	{SCORPION_BANK_CD_ISIDE_HIT, 0x80030000, 3, 0x5a},
+	{SCORPION_BANK_CD_ISIDE_ACCESS, 0x83000000, 3, 0x5b},
+	{SCORPION_ISIDE_RD_WAIT, 0x80000009, 3, 0x58},
+	{SCORPION_DSIDE_RD_WAIT, 0x80090000, 3, 0x5a},
+	{SCORPION_BANK_BYPASS_WRITE, 0x8000000a, 3, 0x58},
+	{SCORPION_BANK_AB_NON_CASTOUT, 0x8000000c, 3, 0x58},
+	{SCORPION_BANK_AB_L2_CASTOUT, 0x80000c00, 3, 0x59},
+	{SCORPION_BANK_CD_NON_CASTOUT, 0x800c0000, 3, 0x5a},
+	{SCORPION_BANK_CD_L2_CASTOUT, 0x8c000000, 3, 0x5b},
+#endif
+};
+
+static inline void scorpion_pmnc_write(u32 val)
+{
+	val &= PMNC_MASK;
+	asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r" (val));
+}
+
+static inline u32 scorpion_pmnc_read(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val));
+	return val;
+}
+
+static inline u32 scorpion_ccnt_read(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));
+	return val;
+}
+
+static inline u32 scorpion_cntn_read(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val));
+	return val;
+}
+
+static inline u32 scorpion_pmnc_enable_counter(unsigned int cnt)
+{
+	u32 val;
+
+	if (cnt >= CNTMAX) {
+		pr_err("gator: CPU%u enabling wrong PMNC counter %d\n", smp_processor_id(), cnt);
+		return -1;
+	}
+
+	if (cnt == CCNT)
+		val = CCNT_REG;
+	else
+		val = (1 << (cnt - CNT0));
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));
+
+	return cnt;
+}
+
+static inline u32 scorpion_pmnc_disable_counter(unsigned int cnt)
+{
+	u32 val;
+
+	if (cnt >= CNTMAX) {
+		pr_err("gator: CPU%u disabling wrong PMNC counter %d\n", smp_processor_id(), cnt);
+		return -1;
+	}
+
+	if (cnt == CCNT)
+		val = CCNT_REG;
+	else
+		val = (1 << (cnt - CNT0));
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));
+
+	return cnt;
+}
+
+static inline int scorpion_pmnc_select_counter(unsigned int cnt)
+{
+	u32 val;
+
+	if ((cnt == CCNT) || (cnt >= CNTMAX)) {
+		pr_err("gator: CPU%u selecting wrong PMNC counter %d\n", smp_processor_id(), cnt);
+		return -1;
+	}
+
+	val = (cnt - CNT0);
+	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));
+
+	return cnt;
+}
+
+static u32 scorpion_read_lpm0(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c15, c0, 0" : "=r" (val));
+	return val;
+}
+
+static void scorpion_write_lpm0(u32 val)
+{
+	asm volatile("mcr p15, 0, %0, c15, c0, 0" : : "r" (val));
+}
+
+static u32 scorpion_read_lpm1(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 1, %0, c15, c0, 0" : "=r" (val));
+	return val;
+}
+
+static void scorpion_write_lpm1(u32 val)
+{
+	asm volatile("mcr p15, 1, %0, c15, c0, 0" : : "r" (val));
+}
+
+static u32 scorpion_read_lpm2(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 2, %0, c15, c0, 0" : "=r" (val));
+	return val;
+}
+
+static void scorpion_write_lpm2(u32 val)
+{
+	asm volatile("mcr p15, 2, %0, c15, c0, 0" : : "r" (val));
+}
+
+static u32 scorpion_read_l2lpm(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 3, %0, c15, c2, 0" : "=r" (val));
+	return val;
+}
+
+static void scorpion_write_l2lpm(u32 val)
+{
+	asm volatile("mcr p15, 3, %0, c15, c2, 0" : : "r" (val));
+}
+
+static u32 scorpion_read_vlpm(void)
+{
+	u32 val;
+
+	asm volatile("mrc p10, 7, %0, c11, c0, 0" : "=r" (val));
+	return val;
+}
+
+static void scorpion_write_vlpm(u32 val)
+{
+	asm volatile("mcr p10, 7, %0, c11, c0, 0" : : "r" (val));
+}
+
+struct scorpion_access_funcs {
+	u32 (*read)(void);
+	void (*write)(u32);
+};
+
+struct scorpion_access_funcs scor_func[] = {
+	{scorpion_read_lpm0, scorpion_write_lpm0},
+	{scorpion_read_lpm1, scorpion_write_lpm1},
+	{scorpion_read_lpm2, scorpion_write_lpm2},
+	{scorpion_read_l2lpm, scorpion_write_l2lpm},
+	{scorpion_read_vlpm, scorpion_write_vlpm},
+};
+
+u32 venum_orig_val;
+u32 fp_orig_val;
+
+static void scorpion_pre_vlpm(void)
+{
+	u32 venum_new_val;
+	u32 fp_new_val;
+
+	/* CPACR Enable CP10 access */
+	asm volatile("mrc p15, 0, %0, c1, c0, 2" : "=r" (venum_orig_val));
+	venum_new_val = venum_orig_val | 0x00300000;
+	asm volatile("mcr p15, 0, %0, c1, c0, 2" : : "r" (venum_new_val));
+	/* Enable FPEXC */
+	asm volatile("mrc p10, 7, %0, c8, c0, 0" : "=r" (fp_orig_val));
+	fp_new_val = fp_orig_val | 0x40000000;
+	asm volatile("mcr p10, 7, %0, c8, c0, 0" : : "r" (fp_new_val));
+}
+
+static void scorpion_post_vlpm(void)
+{
+	/* Restore FPEXC */
+	asm volatile("mcr p10, 7, %0, c8, c0, 0" : : "r" (fp_orig_val));
+	/* Restore CPACR */
+	asm volatile("mcr p15, 0, %0, c1, c0, 2" : : "r" (venum_orig_val));
+}
+
+#define COLMN0MASK 0x000000ff
+#define COLMN1MASK 0x0000ff00
+#define COLMN2MASK 0x00ff0000
+static u32 scorpion_get_columnmask(u32 setval)
+{
+	if (setval & COLMN0MASK)
+		return 0xffffff00;
+	if (setval & COLMN1MASK)
+		return 0xffff00ff;
+	if (setval & COLMN2MASK)
+		return 0xff00ffff;
+	return 0x80ffffff;
+}
+
+static void scorpion_evt_setup(u32 gr, u32 setval)
+{
+	u32 val;
+
+	if (gr == 4)
+		scorpion_pre_vlpm();
+	val = scorpion_get_columnmask(setval) & scor_func[gr].read();
+	val = val | setval;
+	scor_func[gr].write(val);
+	if (gr == 4)
+		scorpion_post_vlpm();
+}
+
+static int get_scorpion_evtinfo(unsigned int evt_type, struct scorp_evt *evtinfo)
+{
+	u32 idx;
+
+	if ((evt_type < 0x4c) || (evt_type >= MSM_MAX_EVT))
+		return 0;
+	idx = evt_type - 0x4c;
+	if (sc_evt[idx].evt_type == evt_type) {
+		evtinfo->val = sc_evt[idx].val;
+		evtinfo->grp = sc_evt[idx].grp;
+		evtinfo->evt_type_act = sc_evt[idx].evt_type_act;
+		return 1;
+	}
+	return 0;
+}
+
+static inline void scorpion_pmnc_write_evtsel(unsigned int cnt, u32 val)
+{
+	if (scorpion_pmnc_select_counter(cnt) == cnt) {
+		if (val < 0x40) {
+			asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
+		} else {
+			u32 zero = 0;
+			struct scorp_evt evtinfo;
+			/* extract evtinfo.grp and evtinfo.tevt_type_act from val */
+			if (get_scorpion_evtinfo(val, &evtinfo) == 0)
+				return;
+			asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (evtinfo.evt_type_act));
+			asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (zero));
+			scorpion_evt_setup(evtinfo.grp, val);
+		}
+	}
+}
+
+static void scorpion_pmnc_reset_counter(unsigned int cnt)
+{
+	u32 val = 0;
+
+	if (cnt == CCNT) {
+		scorpion_pmnc_disable_counter(cnt);
+
+		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (val));
+
+		if (pmnc_enabled[cnt] != 0)
+			scorpion_pmnc_enable_counter(cnt);
+
+	} else if (cnt >= CNTMAX) {
+		pr_err("gator: CPU%u resetting wrong PMNC counter %d\n", smp_processor_id(), cnt);
+	} else {
+		scorpion_pmnc_disable_counter(cnt);
+
+		if (scorpion_pmnc_select_counter(cnt) == cnt)
+			asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (val));
+
+		if (pmnc_enabled[cnt] != 0)
+			scorpion_pmnc_enable_counter(cnt);
+	}
+}
+
+static int gator_events_scorpion_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	int i;
+
+	for (i = 0; i < pmnc_counters; i++) {
+		char buf[40];
+
+		if (i == 0)
+			snprintf(buf, sizeof(buf), "%s_ccnt", pmnc_name);
+		else
+			snprintf(buf, sizeof(buf), "%s_cnt%d", pmnc_name, i - 1);
+		dir = gatorfs_mkdir(sb, root, buf);
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &pmnc_enabled[i]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &pmnc_key[i]);
+		if (i > 0)
+			gatorfs_create_ulong(sb, dir, "event", &pmnc_event[i]);
+	}
+
+	return 0;
+}
+
+static int gator_events_scorpion_online(int **buffer, bool migrate)
+{
+	unsigned int cnt, len = 0, cpu = smp_processor_id();
+
+	if (scorpion_pmnc_read() & PMNC_E)
+		scorpion_pmnc_write(scorpion_pmnc_read() & ~PMNC_E);
+
+	/* Initialize & Reset PMNC: C bit and P bit */
+	scorpion_pmnc_write(PMNC_P | PMNC_C);
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		unsigned long event;
+
+		if (!pmnc_enabled[cnt])
+			continue;
+
+		/* disable counter */
+		scorpion_pmnc_disable_counter(cnt);
+
+		event = pmnc_event[cnt] & 255;
+
+		/* Set event (if destined for PMNx counters), We don't need to set the event if it's a cycle count */
+		if (cnt != CCNT)
+			scorpion_pmnc_write_evtsel(cnt, event);
+
+		/* reset counter */
+		scorpion_pmnc_reset_counter(cnt);
+
+		/* Enable counter, do not enable interrupt for this counter */
+		scorpion_pmnc_enable_counter(cnt);
+	}
+
+	/* enable */
+	scorpion_pmnc_write(scorpion_pmnc_read() | PMNC_E);
+
+	/* read the counters and toss the invalid data, return zero instead */
+	for (cnt = 0; cnt < pmnc_counters; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			if (cnt == CCNT)
+				scorpion_ccnt_read();
+			else if (scorpion_pmnc_select_counter(cnt) == cnt)
+				scorpion_cntn_read();
+			scorpion_pmnc_reset_counter(cnt);
+
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = 0;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static int gator_events_scorpion_offline(int **buffer, bool migrate)
+{
+	scorpion_pmnc_write(scorpion_pmnc_read() & ~PMNC_E);
+	return 0;
+}
+
+static void gator_events_scorpion_stop(void)
+{
+	unsigned int cnt;
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+	}
+}
+
+static int gator_events_scorpion_read(int **buffer, bool sched_switch)
+{
+	int cnt, len = 0;
+	int cpu = smp_processor_id();
+
+	/* a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled */
+	if (!(scorpion_pmnc_read() & PMNC_E))
+		return 0;
+
+	for (cnt = 0; cnt < pmnc_counters; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			int value;
+
+			if (cnt == CCNT)
+				value = scorpion_ccnt_read();
+			else if (scorpion_pmnc_select_counter(cnt) == cnt)
+				value = scorpion_cntn_read();
+			else
+				value = 0;
+			scorpion_pmnc_reset_counter(cnt);
+
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = value;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_scorpion_interface = {
+	.name = "scorpion",
+	.create_files = gator_events_scorpion_create_files,
+	.stop = gator_events_scorpion_stop,
+	.online = gator_events_scorpion_online,
+	.offline = gator_events_scorpion_offline,
+	.read = gator_events_scorpion_read,
+};
+
+int gator_events_scorpion_init(void)
+{
+	unsigned int cnt;
+
+	switch (gator_cpuid()) {
+	case SCORPION:
+		pmnc_name = "Scorpion";
+		pmnc_counters = 4;
+		break;
+	case SCORPIONMP:
+		pmnc_name = "ScorpionMP";
+		pmnc_counters = 4;
+		break;
+	default:
+		return -1;
+	}
+
+	/* CNT[n] + CCNT */
+	pmnc_counters++;
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+		pmnc_key[cnt] = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_scorpion_interface);
+}
+
+#endif
diff --git a/drivers/gator/gator_fs.c b/drivers/gator/gator_fs.c
new file mode 100644
index 00000000000..205da8b3453
--- /dev/null
+++ b/drivers/gator/gator_fs.c
@@ -0,0 +1,370 @@
+/**
+ * @file gatorfs.c
+ *
+ * @remark Copyright 2002 OProfile authors
+ * @remark Read the file COPYING
+ *
+ * @author John Levon
+ *
+ * A simple filesystem for configuration and
+ * access of oprofile.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/uaccess.h>
+
+#define gatorfs_MAGIC 0x24051020
+#define TMPBUFSIZE 50
+static DEFINE_SPINLOCK(gatorfs_lock);
+
+static struct inode *gatorfs_get_inode(struct super_block *sb, int mode)
+{
+	struct inode *inode = new_inode(sb);
+
+	if (inode) {
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 37)
+		inode->i_ino = get_next_ino();
+#endif
+		inode->i_mode = mode;
+		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	}
+	return inode;
+}
+
+static const struct super_operations s_ops = {
+	.statfs = simple_statfs,
+	.drop_inode = generic_delete_inode,
+};
+
+static ssize_t gatorfs_ulong_to_user(unsigned long val, char __user *buf, size_t count, loff_t *offset)
+{
+	char tmpbuf[TMPBUFSIZE];
+	size_t maxlen = snprintf(tmpbuf, TMPBUFSIZE, "%lu\n", val);
+
+	if (maxlen > TMPBUFSIZE)
+		maxlen = TMPBUFSIZE;
+	return simple_read_from_buffer(buf, count, offset, tmpbuf, maxlen);
+}
+
+static ssize_t gatorfs_u64_to_user(u64 val, char __user *buf, size_t count, loff_t *offset)
+{
+	char tmpbuf[TMPBUFSIZE];
+	size_t maxlen = snprintf(tmpbuf, TMPBUFSIZE, "%llu\n", val);
+
+	if (maxlen > TMPBUFSIZE)
+		maxlen = TMPBUFSIZE;
+	return simple_read_from_buffer(buf, count, offset, tmpbuf, maxlen);
+}
+
+static int gatorfs_ulong_from_user(unsigned long *val, char const __user *buf, size_t count)
+{
+	char tmpbuf[TMPBUFSIZE];
+	unsigned long flags;
+
+	if (!count)
+		return 0;
+
+	if (count > TMPBUFSIZE - 1)
+		return -EINVAL;
+
+	memset(tmpbuf, 0x0, TMPBUFSIZE);
+
+	if (copy_from_user(tmpbuf, buf, count))
+		return -EFAULT;
+
+	spin_lock_irqsave(&gatorfs_lock, flags);
+	*val = simple_strtoul(tmpbuf, NULL, 0);
+	spin_unlock_irqrestore(&gatorfs_lock, flags);
+	return 0;
+}
+
+static int gatorfs_u64_from_user(u64 *val, char const __user *buf, size_t count)
+{
+	char tmpbuf[TMPBUFSIZE];
+	unsigned long flags;
+
+	if (!count)
+		return 0;
+
+	if (count > TMPBUFSIZE - 1)
+		return -EINVAL;
+
+	memset(tmpbuf, 0x0, TMPBUFSIZE);
+
+	if (copy_from_user(tmpbuf, buf, count))
+		return -EFAULT;
+
+	spin_lock_irqsave(&gatorfs_lock, flags);
+	*val = simple_strtoull(tmpbuf, NULL, 0);
+	spin_unlock_irqrestore(&gatorfs_lock, flags);
+	return 0;
+}
+
+static ssize_t ulong_read_file(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	unsigned long *val = file->private_data;
+
+	return gatorfs_ulong_to_user(*val, buf, count, offset);
+}
+
+static ssize_t u64_read_file(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	u64 *val = file->private_data;
+
+	return gatorfs_u64_to_user(*val, buf, count, offset);
+}
+
+static ssize_t ulong_write_file(struct file *file, char const __user *buf, size_t count, loff_t *offset)
+{
+	unsigned long *value = file->private_data;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = gatorfs_ulong_from_user(value, buf, count);
+
+	if (retval)
+		return retval;
+	return count;
+}
+
+static ssize_t u64_write_file(struct file *file, char const __user *buf, size_t count, loff_t *offset)
+{
+	u64 *value = file->private_data;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = gatorfs_u64_from_user(value, buf, count);
+
+	if (retval)
+		return retval;
+	return count;
+}
+
+static int default_open(struct inode *inode, struct file *filp)
+{
+	if (inode->i_private)
+		filp->private_data = inode->i_private;
+	return 0;
+}
+
+static const struct file_operations ulong_fops = {
+	.read = ulong_read_file,
+	.write = ulong_write_file,
+	.open = default_open,
+};
+
+static const struct file_operations u64_fops = {
+	.read = u64_read_file,
+	.write = u64_write_file,
+	.open = default_open,
+};
+
+static const struct file_operations ulong_ro_fops = {
+	.read = ulong_read_file,
+	.open = default_open,
+};
+
+static const struct file_operations u64_ro_fops = {
+	.read = u64_read_file,
+	.open = default_open,
+};
+
+static struct dentry *__gatorfs_create_file(struct super_block *sb,
+					    struct dentry *root,
+					    char const *name,
+					    const struct file_operations *fops,
+					    int perm)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+
+	dentry = d_alloc_name(root, name);
+	if (!dentry)
+		return NULL;
+	inode = gatorfs_get_inode(sb, S_IFREG | perm);
+	if (!inode) {
+		dput(dentry);
+		return NULL;
+	}
+	inode->i_fop = fops;
+	d_add(dentry, inode);
+	return dentry;
+}
+
+int gatorfs_create_ulong(struct super_block *sb, struct dentry *root,
+			 char const *name, unsigned long *val)
+{
+	struct dentry *d = __gatorfs_create_file(sb, root, name,
+						 &ulong_fops, 0644);
+	if (!d)
+		return -EFAULT;
+
+	d->d_inode->i_private = val;
+	return 0;
+}
+
+static int gatorfs_create_u64(struct super_block *sb, struct dentry *root,
+			      char const *name, u64 *val)
+{
+	struct dentry *d = __gatorfs_create_file(sb, root, name,
+						 &u64_fops, 0644);
+	if (!d)
+		return -EFAULT;
+
+	d->d_inode->i_private = val;
+	return 0;
+}
+
+int gatorfs_create_ro_ulong(struct super_block *sb, struct dentry *root,
+			    char const *name, unsigned long *val)
+{
+	struct dentry *d = __gatorfs_create_file(sb, root, name,
+						 &ulong_ro_fops, 0444);
+	if (!d)
+		return -EFAULT;
+
+	d->d_inode->i_private = val;
+	return 0;
+}
+
+static int gatorfs_create_ro_u64(struct super_block *sb, struct dentry *root,
+				 char const *name, u64 *val)
+{
+	struct dentry *d =
+	    __gatorfs_create_file(sb, root, name, &u64_ro_fops, 0444);
+	if (!d)
+		return -EFAULT;
+
+	d->d_inode->i_private = val;
+	return 0;
+}
+
+static ssize_t atomic_read_file(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	atomic_t *val = file->private_data;
+
+	return gatorfs_ulong_to_user(atomic_read(val), buf, count, offset);
+}
+
+static const struct file_operations atomic_ro_fops = {
+	.read = atomic_read_file,
+	.open = default_open,
+};
+
+static int gatorfs_create_file(struct super_block *sb, struct dentry *root,
+			       char const *name, const struct file_operations *fops)
+{
+	if (!__gatorfs_create_file(sb, root, name, fops, 0644))
+		return -EFAULT;
+	return 0;
+}
+
+static int gatorfs_create_file_perm(struct super_block *sb, struct dentry *root,
+				    char const *name,
+				    const struct file_operations *fops, int perm)
+{
+	if (!__gatorfs_create_file(sb, root, name, fops, perm))
+		return -EFAULT;
+	return 0;
+}
+
+struct dentry *gatorfs_mkdir(struct super_block *sb,
+			     struct dentry *root, char const *name)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+
+	dentry = d_alloc_name(root, name);
+	if (!dentry)
+		return NULL;
+	inode = gatorfs_get_inode(sb, S_IFDIR | 0755);
+	if (!inode) {
+		dput(dentry);
+		return NULL;
+	}
+	inode->i_op = &simple_dir_inode_operations;
+	inode->i_fop = &simple_dir_operations;
+	d_add(dentry, inode);
+	return dentry;
+}
+
+static int gatorfs_fill_super(struct super_block *sb, void *data, int silent)
+{
+	struct inode *root_inode;
+	struct dentry *root_dentry;
+
+	sb->s_blocksize = PAGE_CACHE_SIZE;
+	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+	sb->s_magic = gatorfs_MAGIC;
+	sb->s_op = &s_ops;
+	sb->s_time_gran = 1;
+
+	root_inode = gatorfs_get_inode(sb, S_IFDIR | 0755);
+	if (!root_inode)
+		return -ENOMEM;
+	root_inode->i_op = &simple_dir_inode_operations;
+	root_inode->i_fop = &simple_dir_operations;
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)
+	root_dentry = d_alloc_root(root_inode);
+#else
+	root_dentry = d_make_root(root_inode);
+#endif
+
+	if (!root_dentry) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)
+		iput(root_inode);
+#endif
+		return -ENOMEM;
+	}
+
+	sb->s_root = root_dentry;
+
+	gator_op_create_files(sb, root_dentry);
+
+	return 0;
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 39)
+static int gatorfs_get_sb(struct file_system_type *fs_type,
+			  int flags, const char *dev_name, void *data,
+			  struct vfsmount *mnt)
+{
+	return get_sb_single(fs_type, flags, data, gatorfs_fill_super, mnt);
+}
+#else
+static struct dentry *gatorfs_mount(struct file_system_type *fs_type,
+				    int flags, const char *dev_name, void *data)
+{
+	return mount_nodev(fs_type, flags, data, gatorfs_fill_super);
+}
+#endif
+
+static struct file_system_type gatorfs_type = {
+	.owner = THIS_MODULE,
+	.name = "gatorfs",
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 39)
+	.get_sb = gatorfs_get_sb,
+#else
+	.mount = gatorfs_mount,
+#endif
+
+	.kill_sb = kill_litter_super,
+};
+
+static int __init gatorfs_register(void)
+{
+	return register_filesystem(&gatorfs_type);
+}
+
+static void gatorfs_unregister(void)
+{
+	unregister_filesystem(&gatorfs_type);
+}
diff --git a/drivers/gator/gator_hrtimer_gator.c b/drivers/gator/gator_hrtimer_gator.c
new file mode 100644
index 00000000000..8b86edebfed
--- /dev/null
+++ b/drivers/gator/gator_hrtimer_gator.c
@@ -0,0 +1,80 @@
+/**
+ * Copyright (C) ARM Limited 2011-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+static void (*callback)(void);
+static DEFINE_PER_CPU(struct hrtimer, percpu_hrtimer);
+static DEFINE_PER_CPU(ktime_t, hrtimer_expire);
+static DEFINE_PER_CPU(int, hrtimer_is_active);
+static ktime_t profiling_interval;
+static void gator_hrtimer_online(void);
+static void gator_hrtimer_offline(void);
+
+static enum hrtimer_restart gator_hrtimer_notify(struct hrtimer *hrtimer)
+{
+	int cpu = get_logical_cpu();
+
+	hrtimer_forward(hrtimer, per_cpu(hrtimer_expire, cpu), profiling_interval);
+	per_cpu(hrtimer_expire, cpu) = ktime_add(per_cpu(hrtimer_expire, cpu), profiling_interval);
+	(*callback)();
+	return HRTIMER_RESTART;
+}
+
+static void gator_hrtimer_online(void)
+{
+	int cpu = get_logical_cpu();
+	struct hrtimer *hrtimer = &per_cpu(percpu_hrtimer, cpu);
+
+	if (per_cpu(hrtimer_is_active, cpu) || profiling_interval.tv64 == 0)
+		return;
+
+	per_cpu(hrtimer_is_active, cpu) = 1;
+	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer->function = gator_hrtimer_notify;
+#ifdef CONFIG_PREEMPT_RT_BASE
+	hrtimer->irqsafe = 1;
+#endif
+	per_cpu(hrtimer_expire, cpu) = ktime_add(hrtimer->base->get_time(), profiling_interval);
+	hrtimer_start(hrtimer, per_cpu(hrtimer_expire, cpu), HRTIMER_MODE_ABS_PINNED);
+}
+
+static void gator_hrtimer_offline(void)
+{
+	int cpu = get_logical_cpu();
+	struct hrtimer *hrtimer = &per_cpu(percpu_hrtimer, cpu);
+
+	if (!per_cpu(hrtimer_is_active, cpu))
+		return;
+
+	per_cpu(hrtimer_is_active, cpu) = 0;
+	hrtimer_cancel(hrtimer);
+}
+
+static int gator_hrtimer_init(int interval, void (*func)(void))
+{
+	int cpu;
+
+	(callback) = (func);
+
+	for_each_present_cpu(cpu) {
+		per_cpu(hrtimer_is_active, cpu) = 0;
+	}
+
+	/* calculate profiling interval */
+	if (interval > 0)
+		profiling_interval = ns_to_ktime(1000000000UL / interval);
+	else
+		profiling_interval.tv64 = 0;
+
+	return 0;
+}
+
+static void gator_hrtimer_shutdown(void)
+{
+	/* empty */
+}
diff --git a/drivers/gator/gator_iks.c b/drivers/gator/gator_iks.c
new file mode 100644
index 00000000000..80535c7b2b6
--- /dev/null
+++ b/drivers/gator/gator_iks.c
@@ -0,0 +1,197 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#if GATOR_IKS_SUPPORT
+
+#include <linux/of.h>
+#include <asm/bL_switcher.h>
+#include <asm/smp_plat.h>
+#include <trace/events/power_cpu_migrate.h>
+
+static bool map_cpuids;
+static int mpidr_cpuids[NR_CPUS];
+static const struct gator_cpu *mpidr_cpus[NR_CPUS];
+static int __lcpu_to_pcpu[NR_CPUS];
+
+static const struct gator_cpu *gator_find_cpu_by_dt_name(const char *const name)
+{
+	int i;
+
+	for (i = 0; gator_cpus[i].cpuid != 0; ++i) {
+		const struct gator_cpu *const gator_cpu = &gator_cpus[i];
+
+		if (gator_cpu->dt_name != NULL && strcmp(gator_cpu->dt_name, name) == 0)
+			return gator_cpu;
+	}
+
+	return NULL;
+}
+
+static void calc_first_cluster_size(void)
+{
+	int len;
+	const u32 *val;
+	const char *compatible;
+	struct device_node *cn = NULL;
+	int mpidr_cpuids_count = 0;
+
+	/* Zero is a valid cpuid, so initialize the array to 0xff's */
+	memset(&mpidr_cpuids, 0xff, sizeof(mpidr_cpuids));
+	memset(&mpidr_cpus, 0, sizeof(mpidr_cpus));
+
+	while ((cn = of_find_node_by_type(cn, "cpu"))) {
+		BUG_ON(mpidr_cpuids_count >= NR_CPUS);
+
+		val = of_get_property(cn, "reg", &len);
+		if (!val || len != 4) {
+			pr_err("%s missing reg property\n", cn->full_name);
+			continue;
+		}
+		compatible = of_get_property(cn, "compatible", NULL);
+		if (compatible == NULL) {
+			pr_err("%s missing compatible property\n", cn->full_name);
+			continue;
+		}
+
+		mpidr_cpuids[mpidr_cpuids_count] = be32_to_cpup(val);
+		mpidr_cpus[mpidr_cpuids_count] = gator_find_cpu_by_dt_name(compatible);
+		++mpidr_cpuids_count;
+	}
+
+	map_cpuids = (mpidr_cpuids_count == nr_cpu_ids);
+}
+
+static int linearize_mpidr(int mpidr)
+{
+	int i;
+
+	for (i = 0; i < nr_cpu_ids; ++i) {
+		if (mpidr_cpuids[i] == mpidr)
+			return i;
+	}
+
+	BUG();
+}
+
+int lcpu_to_pcpu(const int lcpu)
+{
+	int pcpu;
+
+	if (!map_cpuids)
+		return lcpu;
+
+	BUG_ON(lcpu >= nr_cpu_ids || lcpu < 0);
+	pcpu = __lcpu_to_pcpu[lcpu];
+	BUG_ON(pcpu >= nr_cpu_ids || pcpu < 0);
+	return pcpu;
+}
+
+int pcpu_to_lcpu(const int pcpu)
+{
+	int lcpu;
+
+	if (!map_cpuids)
+		return pcpu;
+
+	BUG_ON(pcpu >= nr_cpu_ids || pcpu < 0);
+	for (lcpu = 0; lcpu < nr_cpu_ids; ++lcpu) {
+		if (__lcpu_to_pcpu[lcpu] == pcpu) {
+			BUG_ON(lcpu >= nr_cpu_ids || lcpu < 0);
+			return lcpu;
+		}
+	}
+	BUG();
+}
+
+static void gator_update_cpu_mapping(u32 cpu_hwid)
+{
+	int lcpu = smp_processor_id();
+	int pcpu = linearize_mpidr(cpu_hwid & MPIDR_HWID_BITMASK);
+
+	BUG_ON(lcpu >= nr_cpu_ids || lcpu < 0);
+	BUG_ON(pcpu >= nr_cpu_ids || pcpu < 0);
+	__lcpu_to_pcpu[lcpu] = pcpu;
+}
+
+GATOR_DEFINE_PROBE(cpu_migrate_begin, TP_PROTO(u64 timestamp, u32 cpu_hwid))
+{
+	const int cpu = get_physical_cpu();
+
+	gator_timer_offline((void *)1);
+	gator_timer_offline_dispatch(cpu, true);
+}
+
+GATOR_DEFINE_PROBE(cpu_migrate_finish, TP_PROTO(u64 timestamp, u32 cpu_hwid))
+{
+	int cpu;
+
+	gator_update_cpu_mapping(cpu_hwid);
+
+	/* get_physical_cpu must be called after gator_update_cpu_mapping */
+	cpu = get_physical_cpu();
+	gator_timer_online_dispatch(cpu, true);
+	gator_timer_online((void *)1);
+}
+
+GATOR_DEFINE_PROBE(cpu_migrate_current, TP_PROTO(u64 timestamp, u32 cpu_hwid))
+{
+	gator_update_cpu_mapping(cpu_hwid);
+}
+
+static void gator_send_iks_core_names(void)
+{
+	int cpu;
+	/* Send the cpu names */
+	preempt_disable();
+	for (cpu = 0; cpu < nr_cpu_ids; ++cpu) {
+		if (mpidr_cpus[cpu] != NULL)
+			gator_send_core_name(cpu, mpidr_cpus[cpu]->cpuid);
+	}
+	preempt_enable();
+}
+
+static int gator_migrate_start(void)
+{
+	int retval = 0;
+
+	if (!map_cpuids)
+		return retval;
+
+	if (retval == 0)
+		retval = GATOR_REGISTER_TRACE(cpu_migrate_begin);
+	if (retval == 0)
+		retval = GATOR_REGISTER_TRACE(cpu_migrate_finish);
+	if (retval == 0)
+		retval = GATOR_REGISTER_TRACE(cpu_migrate_current);
+	if (retval == 0) {
+		/* Initialize the logical to physical cpu mapping */
+		memset(&__lcpu_to_pcpu, 0xff, sizeof(__lcpu_to_pcpu));
+		bL_switcher_trace_trigger();
+	}
+	return retval;
+}
+
+static void gator_migrate_stop(void)
+{
+	if (!map_cpuids)
+		return;
+
+	GATOR_UNREGISTER_TRACE(cpu_migrate_current);
+	GATOR_UNREGISTER_TRACE(cpu_migrate_finish);
+	GATOR_UNREGISTER_TRACE(cpu_migrate_begin);
+}
+
+#else
+
+#define calc_first_cluster_size()
+#define gator_send_iks_core_names()
+#define gator_migrate_start() 0
+#define gator_migrate_stop()
+
+#endif
diff --git a/drivers/gator/gator_main.c b/drivers/gator/gator_main.c
new file mode 100644
index 00000000000..2d55afea4b9
--- /dev/null
+++ b/drivers/gator/gator_main.c
@@ -0,0 +1,1509 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/* This version must match the gator daemon version */
+#define PROTOCOL_VERSION 22
+static unsigned long gator_protocol_version = PROTOCOL_VERSION;
+
+#include <linux/slab.h>
+#include <linux/cpu.h>
+#include <linux/sched.h>
+#include <linux/irq.h>
+#include <linux/vmalloc.h>
+#include <linux/hardirq.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include <linux/perf_event.h>
+#include <linux/utsname.h>
+#include <linux/kthread.h>
+#include <asm/stacktrace.h>
+#include <linux/uaccess.h>
+
+#include "gator.h"
+#include "gator_src_md5.h"
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 32)
+#error kernels prior to 2.6.32 are not supported
+#endif
+
+#if defined(MODULE) && !defined(CONFIG_MODULES)
+#error Cannot build a module against a kernel that does not support modules. To resolve, either rebuild the kernel to support modules or build gator as part of the kernel.
+#endif
+
+#if !defined(CONFIG_GENERIC_TRACER) && !defined(CONFIG_TRACING)
+#error gator requires the kernel to have CONFIG_GENERIC_TRACER or CONFIG_TRACING defined
+#endif
+
+#ifndef CONFIG_PROFILING
+#error gator requires the kernel to have CONFIG_PROFILING defined
+#endif
+
+#ifndef CONFIG_HIGH_RES_TIMERS
+#error gator requires the kernel to have CONFIG_HIGH_RES_TIMERS defined to support PC sampling
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 12, 0) && defined(__arm__) && defined(CONFIG_SMP) && !defined(CONFIG_LOCAL_TIMERS)
+#error gator requires the kernel to have CONFIG_LOCAL_TIMERS defined on SMP systems
+#endif
+
+#if (GATOR_PERF_SUPPORT) && (!(GATOR_PERF_PMU_SUPPORT))
+#ifndef CONFIG_PERF_EVENTS
+#error gator requires the kernel to have CONFIG_PERF_EVENTS defined to support pmu hardware counters
+#elif !defined CONFIG_HW_PERF_EVENTS
+#error gator requires the kernel to have CONFIG_HW_PERF_EVENTS defined to support pmu hardware counters
+#endif
+#endif
+
+/******************************************************************************
+ * DEFINES
+ ******************************************************************************/
+#define SUMMARY_BUFFER_SIZE       (1*1024)
+#define BACKTRACE_BUFFER_SIZE     (128*1024)
+#define NAME_BUFFER_SIZE          (64*1024)
+#define COUNTER_BUFFER_SIZE       (64*1024)	/* counters have the core as part of the data and the core value in the frame header may be discarded */
+#define BLOCK_COUNTER_BUFFER_SIZE (128*1024)
+#define ANNOTATE_BUFFER_SIZE      (128*1024)	/* annotate counters have the core as part of the data and the core value in the frame header may be discarded */
+#define SCHED_TRACE_BUFFER_SIZE   (128*1024)
+#define IDLE_BUFFER_SIZE          (32*1024)	/* idle counters have the core as part of the data and the core value in the frame header may be discarded */
+#define ACTIVITY_BUFFER_SIZE      (128*1024)
+
+#define NO_COOKIE      0U
+#define UNRESOLVED_COOKIE ~0U
+
+#define FRAME_SUMMARY       1
+#define FRAME_BACKTRACE     2
+#define FRAME_NAME          3
+#define FRAME_COUNTER       4
+#define FRAME_BLOCK_COUNTER 5
+#define FRAME_ANNOTATE      6
+#define FRAME_SCHED_TRACE   7
+#define FRAME_IDLE          9
+#define FRAME_ACTIVITY     13
+
+#define MESSAGE_END_BACKTRACE 1
+
+/* Name Frame Messages */
+#define MESSAGE_COOKIE      1
+#define MESSAGE_THREAD_NAME 2
+
+/* Scheduler Trace Frame Messages */
+#define MESSAGE_SCHED_SWITCH 1
+#define MESSAGE_SCHED_EXIT   2
+
+/* Summary Frame Messages */
+#define MESSAGE_SUMMARY   1
+#define MESSAGE_CORE_NAME 3
+
+/* Activity Frame Messages */
+#define MESSAGE_LINK   1
+#define MESSAGE_SWITCH 2
+#define MESSAGE_EXIT   3
+
+#define MAXSIZE_PACK32     5
+#define MAXSIZE_PACK64    10
+
+#define FRAME_HEADER_SIZE 3
+
+#if defined(__arm__)
+#define PC_REG regs->ARM_pc
+#elif defined(__aarch64__)
+#define PC_REG regs->pc
+#else
+#define PC_REG regs->ip
+#endif
+
+enum {
+	SUMMARY_BUF,
+	BACKTRACE_BUF,
+	NAME_BUF,
+	COUNTER_BUF,
+	BLOCK_COUNTER_BUF,
+	ANNOTATE_BUF,
+	SCHED_TRACE_BUF,
+	IDLE_BUF,
+	ACTIVITY_BUF,
+	NUM_GATOR_BUFS
+};
+
+/******************************************************************************
+ * Globals
+ ******************************************************************************/
+static unsigned long gator_cpu_cores;
+/* Size of the largest buffer. Effectively constant, set in gator_op_create_files */
+static unsigned long userspace_buffer_size;
+static unsigned long gator_backtrace_depth;
+/* How often to commit the buffers for live in nanoseconds */
+static u64 gator_live_rate;
+
+static unsigned long gator_started;
+static u64 gator_monotonic_started;
+static u64 gator_sync_time;
+static u64 gator_hibernate_time;
+static unsigned long gator_buffer_opened;
+static unsigned long gator_timer_count;
+static unsigned long gator_response_type;
+static DEFINE_MUTEX(start_mutex);
+static DEFINE_MUTEX(gator_buffer_mutex);
+
+bool event_based_sampling;
+
+static DECLARE_WAIT_QUEUE_HEAD(gator_buffer_wait);
+static DECLARE_WAIT_QUEUE_HEAD(gator_annotate_wait);
+static struct timer_list gator_buffer_wake_up_timer;
+static bool gator_buffer_wake_run;
+/* Initialize semaphore unlocked to initialize memory values */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+static DECLARE_MUTEX(gator_buffer_wake_sem);
+#else
+static DEFINE_SEMAPHORE(gator_buffer_wake_sem);
+#endif
+static struct task_struct *gator_buffer_wake_thread;
+static LIST_HEAD(gator_events);
+
+static DEFINE_PER_CPU(u64, last_timestamp);
+
+static bool printed_monotonic_warning;
+
+static u32 gator_cpuids[NR_CPUS];
+static bool sent_core_name[NR_CPUS];
+
+static DEFINE_PER_CPU(bool, in_scheduler_context);
+
+/******************************************************************************
+ * Prototypes
+ ******************************************************************************/
+static void gator_emit_perf_time(u64 time);
+static void gator_op_create_files(struct super_block *sb, struct dentry *root);
+
+/* gator_buffer is protected by being per_cpu and by having IRQs
+ * disabled when writing to it. Most marshal_* calls take care of this
+ * except for marshal_cookie*, marshal_backtrace* and marshal_frame
+ * where the caller is responsible for doing so. No synchronization is
+ * needed with the backtrace buffer as it is per cpu and is only used
+ * from the hrtimer. The annotate_lock must be held when using the
+ * annotation buffer as it is not per cpu. collect_counters which is
+ * the sole writer to the block counter frame is additionally
+ * protected by the per cpu collecting flag.
+ */
+
+/* Size of the buffer, must be a power of 2. Effectively constant, set in gator_op_setup. */
+static uint32_t gator_buffer_size[NUM_GATOR_BUFS];
+/* gator_buffer_size - 1, bitwise and with pos to get offset into the array. Effectively constant, set in gator_op_setup. */
+static uint32_t gator_buffer_mask[NUM_GATOR_BUFS];
+/* Read position in the buffer. Initialized to zero in gator_op_setup and incremented after bytes are read by userspace in userspace_buffer_read */
+static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], gator_buffer_read);
+/* Write position in the buffer. Initialized to zero in gator_op_setup and incremented after bytes are written to the buffer */
+static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], gator_buffer_write);
+/* Commit position in the buffer. Initialized to zero in gator_op_setup and incremented after a frame is ready to be read by userspace */
+static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], gator_buffer_commit);
+/* If set to false, decreases the number of bytes returned by
+ * buffer_bytes_available. Set in buffer_check_space if no space is
+ * remaining. Initialized to true in gator_op_setup. This means that
+ * if we run out of space, continue to report that no space is
+ * available until bytes are read by userspace
+ */
+static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], buffer_space_available);
+/* The buffer. Allocated in gator_op_setup */
+static DEFINE_PER_CPU(char *[NUM_GATOR_BUFS], gator_buffer);
+/* The time after which the buffer should be committed for live display */
+static DEFINE_PER_CPU(u64, gator_buffer_commit_time);
+
+/* List of all gator events - new events must be added to this list */
+#define GATOR_EVENTS_LIST \
+	GATOR_EVENT(gator_events_armv6_init) \
+	GATOR_EVENT(gator_events_armv7_init) \
+	GATOR_EVENT(gator_events_block_init) \
+	GATOR_EVENT(gator_events_ccn504_init) \
+	GATOR_EVENT(gator_events_irq_init) \
+	GATOR_EVENT(gator_events_l2c310_init) \
+	GATOR_EVENT(gator_events_mali_init) \
+	GATOR_EVENT(gator_events_mali_midgard_hw_init) \
+	GATOR_EVENT(gator_events_mali_midgard_init) \
+	GATOR_EVENT(gator_events_meminfo_init) \
+	GATOR_EVENT(gator_events_mmapped_init) \
+	GATOR_EVENT(gator_events_net_init) \
+	GATOR_EVENT(gator_events_perf_pmu_init) \
+	GATOR_EVENT(gator_events_sched_init) \
+	GATOR_EVENT(gator_events_scorpion_init) \
+
+#define GATOR_EVENT(EVENT_INIT) __weak int EVENT_INIT(void);
+GATOR_EVENTS_LIST
+#undef GATOR_EVENT
+
+static int (*gator_events_list[])(void) = {
+#define GATOR_EVENT(EVENT_INIT) EVENT_INIT,
+GATOR_EVENTS_LIST
+#undef GATOR_EVENT
+};
+
+/******************************************************************************
+ * Application Includes
+ ******************************************************************************/
+#include "gator_fs.c"
+#include "gator_buffer_write.c"
+#include "gator_buffer.c"
+#include "gator_marshaling.c"
+#include "gator_hrtimer_gator.c"
+#include "gator_cookies.c"
+#include "gator_annotate.c"
+#include "gator_trace_sched.c"
+#include "gator_trace_power.c"
+#include "gator_trace_gpu.c"
+#include "gator_backtrace.c"
+
+/******************************************************************************
+ * Misc
+ ******************************************************************************/
+
+MODULE_PARM_DESC(gator_src_md5, "Gator driver source code md5sum");
+module_param_named(src_md5, gator_src_md5, charp, 0444);
+
+static const struct gator_cpu gator_cpus[] = {
+	{
+		.cpuid = ARM1136,
+		.core_name = "ARM1136",
+		.pmnc_name = "ARM_ARM11",
+		.dt_name = "arm,arm1136",
+		.pmnc_counters = 3,
+	},
+	{
+		.cpuid = ARM1156,
+		.core_name = "ARM1156",
+		.pmnc_name = "ARM_ARM11",
+		.dt_name = "arm,arm1156",
+		.pmnc_counters = 3,
+	},
+	{
+		.cpuid = ARM1176,
+		.core_name = "ARM1176",
+		.pmnc_name = "ARM_ARM11",
+		.dt_name = "arm,arm1176",
+		.pmnc_counters = 3,
+	},
+	{
+		.cpuid = ARM11MPCORE,
+		.core_name = "ARM11MPCore",
+		.pmnc_name = "ARM_ARM11MPCore",
+		.dt_name = "arm,arm11mpcore",
+		.pmnc_counters = 3,
+	},
+	{
+		.cpuid = CORTEX_A5,
+		.core_name = "Cortex-A5",
+		.pmnc_name = "ARMv7_Cortex_A5",
+		.dt_name = "arm,cortex-a5",
+		.pmnc_counters = 2,
+	},
+	{
+		.cpuid = CORTEX_A7,
+		.core_name = "Cortex-A7",
+		.pmnc_name = "ARMv7_Cortex_A7",
+		.dt_name = "arm,cortex-a7",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = CORTEX_A8,
+		.core_name = "Cortex-A8",
+		.pmnc_name = "ARMv7_Cortex_A8",
+		.dt_name = "arm,cortex-a8",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = CORTEX_A9,
+		.core_name = "Cortex-A9",
+		.pmnc_name = "ARMv7_Cortex_A9",
+		.dt_name = "arm,cortex-a9",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = CORTEX_A15,
+		.core_name = "Cortex-A15",
+		.pmnc_name = "ARMv7_Cortex_A15",
+		.dt_name = "arm,cortex-a15",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = CORTEX_A12,
+		.core_name = "Cortex-A17",
+		.pmnc_name = "ARMv7_Cortex_A17",
+		.dt_name = "arm,cortex-a17",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = CORTEX_A17,
+		.core_name = "Cortex-A17",
+		.pmnc_name = "ARMv7_Cortex_A17",
+		.dt_name = "arm,cortex-a17",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = SCORPION,
+		.core_name = "Scorpion",
+		.pmnc_name = "Scorpion",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = SCORPIONMP,
+		.core_name = "ScorpionMP",
+		.pmnc_name = "ScorpionMP",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = KRAITSIM,
+		.core_name = "KraitSIM",
+		.pmnc_name = "Krait",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = KRAIT,
+		.core_name = "Krait",
+		.pmnc_name = "Krait",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = KRAIT_S4_PRO,
+		.core_name = "Krait S4 Pro",
+		.pmnc_name = "Krait",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = CORTEX_A53,
+		.core_name = "Cortex-A53",
+		.pmnc_name = "ARMv8_Cortex_A53",
+		.dt_name = "arm,cortex-a53",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = CORTEX_A57,
+		.core_name = "Cortex-A57",
+		.pmnc_name = "ARMv8_Cortex_A57",
+		.dt_name = "arm,cortex-a57",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = CORTEX_A72,
+		.core_name = "Cortex-A72",
+		.pmnc_name = "ARMv8_Cortex_A72",
+		.dt_name = "arm,cortex-a72",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = OTHER,
+		.core_name = "Other",
+		.pmnc_name = "Other",
+		.pmnc_counters = 6,
+	},
+	{}
+};
+
+const struct gator_cpu *gator_find_cpu_by_cpuid(const u32 cpuid)
+{
+	int i;
+
+	for (i = 0; gator_cpus[i].cpuid != 0; ++i) {
+		const struct gator_cpu *const gator_cpu = &gator_cpus[i];
+
+		if (gator_cpu->cpuid == cpuid)
+			return gator_cpu;
+	}
+
+	return NULL;
+}
+
+static const char OLD_PMU_PREFIX[] = "ARMv7 Cortex-";
+static const char NEW_PMU_PREFIX[] = "ARMv7_Cortex_";
+
+const struct gator_cpu *gator_find_cpu_by_pmu_name(const char *const name)
+{
+	int i;
+
+	for (i = 0; gator_cpus[i].cpuid != 0; ++i) {
+		const struct gator_cpu *const gator_cpu = &gator_cpus[i];
+
+		if (gator_cpu->pmnc_name != NULL &&
+		    /* Do the names match exactly? */
+		    (strcasecmp(gator_cpu->pmnc_name, name) == 0 ||
+		     /* Do these names match but have the old vs new prefix? */
+		     ((strncasecmp(name, OLD_PMU_PREFIX, sizeof(OLD_PMU_PREFIX) - 1) == 0 &&
+		       strncasecmp(gator_cpu->pmnc_name, NEW_PMU_PREFIX, sizeof(NEW_PMU_PREFIX) - 1) == 0 &&
+		       strcasecmp(name + sizeof(OLD_PMU_PREFIX) - 1, gator_cpu->pmnc_name + sizeof(NEW_PMU_PREFIX) - 1) == 0))))
+			return gator_cpu;
+	}
+
+	return NULL;
+}
+
+u32 gator_cpuid(void)
+{
+#if defined(__arm__) || defined(__aarch64__)
+	u32 val;
+#if !defined(__aarch64__)
+	asm volatile("mrc p15, 0, %0, c0, c0, 0" : "=r" (val));
+#else
+	asm volatile("mrs %0, midr_el1" : "=r" (val));
+#endif
+	return ((val & 0xff000000) >> 12) | ((val & 0xfff0) >> 4);
+#else
+	return OTHER;
+#endif
+}
+
+static void gator_buffer_wake_up(unsigned long data)
+{
+	wake_up(&gator_buffer_wait);
+}
+
+static int gator_buffer_wake_func(void *data)
+{
+	for (;;) {
+		if (down_killable(&gator_buffer_wake_sem))
+			break;
+
+		/* Eat up any pending events */
+		while (!down_trylock(&gator_buffer_wake_sem))
+			;
+
+		if (!gator_buffer_wake_run)
+			break;
+
+		gator_buffer_wake_up(0);
+	}
+
+	return 0;
+}
+
+/******************************************************************************
+ * Commit interface
+ ******************************************************************************/
+static bool buffer_commit_ready(int *cpu, int *buftype)
+{
+	int cpu_x, x;
+
+	for_each_present_cpu(cpu_x) {
+		for (x = 0; x < NUM_GATOR_BUFS; x++)
+			if (per_cpu(gator_buffer_commit, cpu_x)[x] != per_cpu(gator_buffer_read, cpu_x)[x]) {
+				*cpu = cpu_x;
+				*buftype = x;
+				return true;
+			}
+	}
+	*cpu = -1;
+	*buftype = -1;
+	return false;
+}
+
+/******************************************************************************
+ * hrtimer interrupt processing
+ ******************************************************************************/
+static void gator_timer_interrupt(void)
+{
+	struct pt_regs *const regs = get_irq_regs();
+
+	gator_backtrace_handler(regs);
+}
+
+void gator_backtrace_handler(struct pt_regs *const regs)
+{
+	u64 time = gator_get_time();
+	int cpu = get_physical_cpu();
+
+	/* Output backtrace */
+	gator_add_sample(cpu, regs, time);
+
+	/* Collect counters */
+	if (!per_cpu(collecting, cpu))
+		collect_counters(time, current, false);
+
+	/* No buffer flushing occurs during sched switch for RT-Preempt full. The block counter frame will be flushed by collect_counters, but the sched buffer needs to be explicitly flushed */
+#ifdef CONFIG_PREEMPT_RT_FULL
+	buffer_check(cpu, SCHED_TRACE_BUF, time);
+#endif
+}
+
+static int gator_running;
+
+/* This function runs in interrupt context and on the appropriate core */
+static void gator_timer_offline(void *migrate)
+{
+	struct gator_interface *gi;
+	int i, len, cpu = get_physical_cpu();
+	int *buffer;
+	u64 time;
+
+	gator_trace_sched_offline();
+	gator_trace_power_offline();
+
+	if (!migrate)
+		gator_hrtimer_offline();
+
+	/* Offline any events and output counters */
+	time = gator_get_time();
+	if (marshal_event_header(time)) {
+		list_for_each_entry(gi, &gator_events, list) {
+			if (gi->offline) {
+				len = gi->offline(&buffer, migrate);
+				if (len < 0)
+					pr_err("gator: offline failed for %s\n", gi->name);
+				marshal_event(len, buffer);
+			}
+		}
+		/* Only check after writing all counters so that time and corresponding counters appear in the same frame */
+		buffer_check(cpu, BLOCK_COUNTER_BUF, time);
+	}
+
+	/* Flush all buffers on this core */
+	for (i = 0; i < NUM_GATOR_BUFS; i++)
+		gator_commit_buffer(cpu, i, time);
+}
+
+/* This function runs in interrupt context and may be running on a core other than core 'cpu' */
+static void gator_timer_offline_dispatch(int cpu, bool migrate)
+{
+	struct gator_interface *gi;
+
+	list_for_each_entry(gi, &gator_events, list) {
+		if (gi->offline_dispatch)
+			gi->offline_dispatch(cpu, migrate);
+	}
+}
+
+static void gator_timer_stop(void)
+{
+	int cpu;
+
+	if (gator_running) {
+		on_each_cpu(gator_timer_offline, NULL, 1);
+		for_each_online_cpu(cpu) {
+			gator_timer_offline_dispatch(lcpu_to_pcpu(cpu), false);
+		}
+
+		gator_running = 0;
+		gator_hrtimer_shutdown();
+	}
+}
+
+static void gator_send_core_name(const int cpu, const u32 cpuid)
+{
+#if defined(__arm__) || defined(__aarch64__)
+	if (!sent_core_name[cpu] || (cpuid != gator_cpuids[cpu])) {
+		const struct gator_cpu *const gator_cpu = gator_find_cpu_by_cpuid(cpuid);
+		const char *core_name = NULL;
+		char core_name_buf[32];
+
+		/* Save off this cpuid */
+		gator_cpuids[cpu] = cpuid;
+		if (gator_cpu != NULL) {
+			core_name = gator_cpu->core_name;
+		} else {
+			if (cpuid == -1)
+				snprintf(core_name_buf, sizeof(core_name_buf), "Unknown");
+			else
+				snprintf(core_name_buf, sizeof(core_name_buf), "Unknown (0x%.5x)", cpuid);
+			core_name = core_name_buf;
+		}
+
+		marshal_core_name(cpu, cpuid, core_name);
+		sent_core_name[cpu] = true;
+	}
+#endif
+}
+
+static void gator_read_cpuid(void *arg)
+{
+	gator_cpuids[get_physical_cpu()] = gator_cpuid();
+}
+
+/* This function runs in interrupt context and on the appropriate core */
+static void gator_timer_online(void *migrate)
+{
+	struct gator_interface *gi;
+	int len, cpu = get_physical_cpu();
+	int *buffer;
+	u64 time;
+
+	/* Send what is currently running on this core */
+	marshal_sched_trace_switch(current->pid, 0);
+
+	gator_trace_power_online();
+
+	/* online any events and output counters */
+	time = gator_get_time();
+	if (marshal_event_header(time)) {
+		list_for_each_entry(gi, &gator_events, list) {
+			if (gi->online) {
+				len = gi->online(&buffer, migrate);
+				if (len < 0)
+					pr_err("gator: online failed for %s\n", gi->name);
+				marshal_event(len, buffer);
+			}
+		}
+		/* Only check after writing all counters so that time and corresponding counters appear in the same frame */
+		buffer_check(cpu, BLOCK_COUNTER_BUF, time);
+	}
+
+	if (!migrate)
+		gator_hrtimer_online();
+
+	gator_send_core_name(cpu, gator_cpuid());
+}
+
+/* This function runs in interrupt context and may be running on a core other than core 'cpu' */
+static void gator_timer_online_dispatch(int cpu, bool migrate)
+{
+	struct gator_interface *gi;
+
+	list_for_each_entry(gi, &gator_events, list) {
+		if (gi->online_dispatch)
+			gi->online_dispatch(cpu, migrate);
+	}
+}
+
+#include "gator_iks.c"
+
+static int gator_timer_start(unsigned long sample_rate)
+{
+	int cpu;
+
+	if (gator_running) {
+		pr_notice("gator: already running\n");
+		return 0;
+	}
+
+	gator_running = 1;
+
+	/* event based sampling trumps hr timer based sampling */
+	if (event_based_sampling)
+		sample_rate = 0;
+
+	if (gator_hrtimer_init(sample_rate, gator_timer_interrupt) == -1)
+		return -1;
+
+	/* Send off the previously saved cpuids */
+	for_each_present_cpu(cpu) {
+		preempt_disable();
+		gator_send_core_name(cpu, gator_cpuids[cpu]);
+		preempt_enable();
+	}
+
+	gator_send_iks_core_names();
+	for_each_online_cpu(cpu) {
+		gator_timer_online_dispatch(lcpu_to_pcpu(cpu), false);
+	}
+	on_each_cpu(gator_timer_online, NULL, 1);
+
+	return 0;
+}
+
+u64 gator_get_time(void)
+{
+	struct timespec ts;
+	u64 timestamp;
+	u64 prev_timestamp;
+	u64 delta;
+	int cpu = smp_processor_id();
+
+	/* Match clock_gettime(CLOCK_MONOTONIC_RAW, &ts) from userspace */
+	getrawmonotonic(&ts);
+	timestamp = timespec_to_ns(&ts);
+
+	/* getrawmonotonic is not monotonic on all systems. Detect and
+	 * attempt to correct these cases. up to 0.5ms delta has been seen
+	 * on some systems, which can skew Streamline data when viewing at
+	 * high resolution. This doesn't work well with interrupts, but that
+	 * it's OK - the real concern is to catch big jumps in time
+	 */
+	prev_timestamp = per_cpu(last_timestamp, cpu);
+	if (prev_timestamp <= timestamp) {
+		per_cpu(last_timestamp, cpu) = timestamp;
+	} else {
+		delta = prev_timestamp - timestamp;
+		/* Log the error once */
+		if (!printed_monotonic_warning && delta > 500000) {
+			pr_err("%s: getrawmonotonic is not monotonic  cpu: %i  delta: %lli\nSkew in Streamline data may be present at the fine zoom levels\n", __func__, cpu, delta);
+			printed_monotonic_warning = true;
+		}
+		timestamp = prev_timestamp;
+	}
+
+	return timestamp - gator_monotonic_started;
+}
+
+static void gator_emit_perf_time(u64 time)
+{
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 10, 0)
+	if (time >= gator_sync_time) {
+		marshal_event_single64(0, -1, local_clock());
+		gator_sync_time += NSEC_PER_SEC;
+		if (gator_live_rate <= 0) {
+			gator_commit_buffer(get_physical_cpu(), COUNTER_BUF, time);
+		}
+	}
+#endif
+}
+
+/******************************************************************************
+ * cpu hotplug and pm notifiers
+ ******************************************************************************/
+static int __cpuinit gator_hotcpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+	int cpu = lcpu_to_pcpu((long)hcpu);
+
+	switch (action) {
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+		smp_call_function_single(cpu, gator_timer_offline, NULL, 1);
+		gator_timer_offline_dispatch(cpu, false);
+		break;
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		gator_timer_online_dispatch(cpu, false);
+		smp_call_function_single(cpu, gator_timer_online, NULL, 1);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __refdata gator_hotcpu_notifier = {
+	.notifier_call = gator_hotcpu_notify,
+};
+
+/* n.b. calling "on_each_cpu" only runs on those that are online.
+ * Registered linux events are not disabled, so their counters will
+ * continue to collect
+ */
+static int gator_pm_notify(struct notifier_block *nb, unsigned long event, void *dummy)
+{
+	int cpu;
+	struct timespec ts;
+
+	switch (event) {
+	case PM_HIBERNATION_PREPARE:
+	case PM_SUSPEND_PREPARE:
+		unregister_hotcpu_notifier(&gator_hotcpu_notifier);
+		unregister_scheduler_tracepoints();
+		on_each_cpu(gator_timer_offline, NULL, 1);
+		for_each_online_cpu(cpu) {
+			gator_timer_offline_dispatch(lcpu_to_pcpu(cpu), false);
+		}
+
+		/* Record the wallclock hibernate time */
+		getnstimeofday(&ts);
+		gator_hibernate_time = timespec_to_ns(&ts) - gator_get_time();
+		break;
+	case PM_POST_HIBERNATION:
+	case PM_POST_SUSPEND:
+		/* Adjust gator_monotonic_started for the time spent sleeping, as gator_get_time does not account for it */
+		if (gator_hibernate_time > 0) {
+			getnstimeofday(&ts);
+			gator_monotonic_started += gator_hibernate_time + gator_get_time() - timespec_to_ns(&ts);
+			gator_hibernate_time = 0;
+		}
+
+		for_each_online_cpu(cpu) {
+			gator_timer_online_dispatch(lcpu_to_pcpu(cpu), false);
+		}
+		on_each_cpu(gator_timer_online, NULL, 1);
+		register_scheduler_tracepoints();
+		register_hotcpu_notifier(&gator_hotcpu_notifier);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block gator_pm_notifier = {
+	.notifier_call = gator_pm_notify,
+};
+
+static int gator_notifier_start(void)
+{
+	int retval;
+
+	retval = register_hotcpu_notifier(&gator_hotcpu_notifier);
+	if (retval == 0)
+		retval = register_pm_notifier(&gator_pm_notifier);
+	return retval;
+}
+
+static void gator_notifier_stop(void)
+{
+	unregister_pm_notifier(&gator_pm_notifier);
+	unregister_hotcpu_notifier(&gator_hotcpu_notifier);
+}
+
+/******************************************************************************
+ * Main
+ ******************************************************************************/
+static void gator_summary(void)
+{
+	u64 timestamp, uptime;
+	struct timespec ts;
+	char uname_buf[512];
+
+	snprintf(uname_buf, sizeof(uname_buf), "%s %s %s %s %s GNU/Linux", utsname()->sysname, utsname()->nodename, utsname()->release, utsname()->version, utsname()->machine);
+
+	getnstimeofday(&ts);
+	timestamp = timespec_to_ns(&ts);
+
+	/* Similar to reading /proc/uptime from fs/proc/uptime.c, calculate uptime */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 11, 0)
+	{
+		void (*m2b)(struct timespec *ts);
+
+		do_posix_clock_monotonic_gettime(&ts);
+		/* monotonic_to_bootbased is not defined for some versions of Android */
+		m2b = symbol_get(monotonic_to_bootbased);
+		if (m2b)
+			m2b(&ts);
+	}
+#else
+	get_monotonic_boottime(&ts);
+#endif
+	uptime = timespec_to_ns(&ts);
+
+	/* Disable preemption as gator_get_time calls smp_processor_id to verify time is monotonic */
+	preempt_disable();
+	/* Set monotonic_started to zero as gator_get_time is uptime minus monotonic_started */
+	gator_monotonic_started = 0;
+	gator_monotonic_started = gator_get_time();
+
+	marshal_summary(timestamp, uptime, gator_monotonic_started, uname_buf);
+	gator_sync_time = 0;
+	gator_emit_perf_time(gator_monotonic_started);
+	/* Always flush COUNTER_BUF so that the initial perf_time is received before it's used */
+	gator_commit_buffer(get_physical_cpu(), COUNTER_BUF, 0);
+	preempt_enable();
+}
+
+int gator_events_install(struct gator_interface *interface)
+{
+	list_add_tail(&interface->list, &gator_events);
+
+	return 0;
+}
+
+int gator_events_get_key(void)
+{
+	/* key 0 is reserved as a timestamp. key 1 is reserved as the marker
+	 * for thread specific counters. key 2 is reserved as the marker for
+	 * core. Odd keys are assigned by the driver, even keys by the
+	 * daemon.
+	 */
+	static int key = 3;
+	const int ret = key;
+
+	key += 2;
+	return ret;
+}
+
+static int gator_init(void)
+{
+	int i;
+
+	calc_first_cluster_size();
+
+	/* events sources */
+	for (i = 0; i < ARRAY_SIZE(gator_events_list); i++)
+		if (gator_events_list[i])
+			gator_events_list[i]();
+
+	gator_trace_sched_init();
+	gator_trace_power_init();
+
+	return 0;
+}
+
+static void gator_exit(void)
+{
+	struct gator_interface *gi;
+
+	list_for_each_entry(gi, &gator_events, list)
+		if (gi->shutdown)
+			gi->shutdown();
+}
+
+static int gator_start(void)
+{
+	unsigned long cpu, i;
+	struct gator_interface *gi;
+
+	gator_buffer_wake_run = true;
+	gator_buffer_wake_thread = kthread_run(gator_buffer_wake_func, NULL, "gator_bwake");
+	if (IS_ERR(gator_buffer_wake_thread))
+		goto bwake_failure;
+
+	if (gator_migrate_start())
+		goto migrate_failure;
+
+	/* Initialize the buffer with the frame type and core */
+	for_each_present_cpu(cpu) {
+		for (i = 0; i < NUM_GATOR_BUFS; i++)
+			marshal_frame(cpu, i);
+		per_cpu(last_timestamp, cpu) = 0;
+	}
+	printed_monotonic_warning = false;
+
+	/* Capture the start time */
+	gator_summary();
+
+	/* start all events */
+	list_for_each_entry(gi, &gator_events, list) {
+		if (gi->start && gi->start() != 0) {
+			struct list_head *ptr = gi->list.prev;
+
+			while (ptr != &gator_events) {
+				gi = list_entry(ptr, struct gator_interface, list);
+
+				if (gi->stop)
+					gi->stop();
+
+				ptr = ptr->prev;
+			}
+			goto events_failure;
+		}
+	}
+
+	/* cookies shall be initialized before trace_sched_start() and gator_timer_start() */
+	if (cookies_initialize())
+		goto cookies_failure;
+	if (gator_annotate_start())
+		goto annotate_failure;
+	if (gator_trace_sched_start())
+		goto sched_failure;
+	if (gator_trace_power_start())
+		goto power_failure;
+	if (gator_trace_gpu_start())
+		goto gpu_failure;
+	if (gator_timer_start(gator_timer_count))
+		goto timer_failure;
+	if (gator_notifier_start())
+		goto notifier_failure;
+
+	return 0;
+
+notifier_failure:
+	gator_timer_stop();
+timer_failure:
+	gator_trace_gpu_stop();
+gpu_failure:
+	gator_trace_power_stop();
+power_failure:
+	gator_trace_sched_stop();
+sched_failure:
+	gator_annotate_stop();
+annotate_failure:
+	cookies_release();
+cookies_failure:
+	/* stop all events */
+	list_for_each_entry(gi, &gator_events, list)
+		if (gi->stop)
+			gi->stop();
+events_failure:
+	gator_migrate_stop();
+migrate_failure:
+	gator_buffer_wake_run = false;
+	up(&gator_buffer_wake_sem);
+	gator_buffer_wake_thread = NULL;
+bwake_failure:
+
+	return -1;
+}
+
+static void gator_stop(void)
+{
+	struct gator_interface *gi;
+
+	gator_annotate_stop();
+	gator_trace_sched_stop();
+	gator_trace_power_stop();
+	gator_trace_gpu_stop();
+
+	/* stop all interrupt callback reads before tearing down other interfaces */
+	gator_notifier_stop();	/* should be called before gator_timer_stop to avoid re-enabling the hrtimer after it has been offlined */
+	gator_timer_stop();
+
+	/* stop all events */
+	list_for_each_entry(gi, &gator_events, list)
+		if (gi->stop)
+			gi->stop();
+
+	gator_migrate_stop();
+
+	gator_buffer_wake_run = false;
+	up(&gator_buffer_wake_sem);
+	gator_buffer_wake_thread = NULL;
+}
+
+/******************************************************************************
+ * Filesystem
+ ******************************************************************************/
+/* fopen("buffer") */
+static int gator_op_setup(void)
+{
+	int err = 0;
+	int cpu, i;
+
+	mutex_lock(&start_mutex);
+
+	gator_buffer_size[SUMMARY_BUF] = SUMMARY_BUFFER_SIZE;
+	gator_buffer_mask[SUMMARY_BUF] = SUMMARY_BUFFER_SIZE - 1;
+
+	gator_buffer_size[BACKTRACE_BUF] = BACKTRACE_BUFFER_SIZE;
+	gator_buffer_mask[BACKTRACE_BUF] = BACKTRACE_BUFFER_SIZE - 1;
+
+	gator_buffer_size[NAME_BUF] = NAME_BUFFER_SIZE;
+	gator_buffer_mask[NAME_BUF] = NAME_BUFFER_SIZE - 1;
+
+	gator_buffer_size[COUNTER_BUF] = COUNTER_BUFFER_SIZE;
+	gator_buffer_mask[COUNTER_BUF] = COUNTER_BUFFER_SIZE - 1;
+
+	gator_buffer_size[BLOCK_COUNTER_BUF] = BLOCK_COUNTER_BUFFER_SIZE;
+	gator_buffer_mask[BLOCK_COUNTER_BUF] = BLOCK_COUNTER_BUFFER_SIZE - 1;
+
+	gator_buffer_size[ANNOTATE_BUF] = ANNOTATE_BUFFER_SIZE;
+	gator_buffer_mask[ANNOTATE_BUF] = ANNOTATE_BUFFER_SIZE - 1;
+
+	gator_buffer_size[SCHED_TRACE_BUF] = SCHED_TRACE_BUFFER_SIZE;
+	gator_buffer_mask[SCHED_TRACE_BUF] = SCHED_TRACE_BUFFER_SIZE - 1;
+
+	gator_buffer_size[IDLE_BUF] = IDLE_BUFFER_SIZE;
+	gator_buffer_mask[IDLE_BUF] = IDLE_BUFFER_SIZE - 1;
+
+	gator_buffer_size[ACTIVITY_BUF] = ACTIVITY_BUFFER_SIZE;
+	gator_buffer_mask[ACTIVITY_BUF] = ACTIVITY_BUFFER_SIZE - 1;
+
+	/* Initialize percpu per buffer variables */
+	for (i = 0; i < NUM_GATOR_BUFS; i++) {
+		/* Verify buffers are a power of 2 */
+		if (gator_buffer_size[i] & (gator_buffer_size[i] - 1)) {
+			err = -ENOEXEC;
+			goto setup_error;
+		}
+
+		for_each_present_cpu(cpu) {
+			per_cpu(gator_buffer_read, cpu)[i] = 0;
+			per_cpu(gator_buffer_write, cpu)[i] = 0;
+			per_cpu(gator_buffer_commit, cpu)[i] = 0;
+			per_cpu(buffer_space_available, cpu)[i] = true;
+			per_cpu(gator_buffer_commit_time, cpu) = gator_live_rate;
+
+			/* Annotation is a special case that only uses a single buffer */
+			if (cpu > 0 && i == ANNOTATE_BUF) {
+				per_cpu(gator_buffer, cpu)[i] = NULL;
+				continue;
+			}
+
+			per_cpu(gator_buffer, cpu)[i] = vmalloc(gator_buffer_size[i]);
+			if (!per_cpu(gator_buffer, cpu)[i]) {
+				err = -ENOMEM;
+				goto setup_error;
+			}
+		}
+	}
+
+setup_error:
+	mutex_unlock(&start_mutex);
+	return err;
+}
+
+/* Actually start profiling (echo 1>/dev/gator/enable) */
+static int gator_op_start(void)
+{
+	int err = 0;
+
+	mutex_lock(&start_mutex);
+
+	if (gator_started || gator_start())
+		err = -EINVAL;
+	else
+		gator_started = 1;
+
+	mutex_unlock(&start_mutex);
+
+	return err;
+}
+
+/* echo 0>/dev/gator/enable */
+static void gator_op_stop(void)
+{
+	mutex_lock(&start_mutex);
+
+	if (gator_started) {
+		gator_stop();
+
+		mutex_lock(&gator_buffer_mutex);
+
+		gator_started = 0;
+		gator_monotonic_started = 0;
+		cookies_release();
+		wake_up(&gator_buffer_wait);
+
+		mutex_unlock(&gator_buffer_mutex);
+	}
+
+	mutex_unlock(&start_mutex);
+}
+
+static void gator_shutdown(void)
+{
+	int cpu, i;
+
+	mutex_lock(&start_mutex);
+
+	for_each_present_cpu(cpu) {
+		mutex_lock(&gator_buffer_mutex);
+		for (i = 0; i < NUM_GATOR_BUFS; i++) {
+			vfree(per_cpu(gator_buffer, cpu)[i]);
+			per_cpu(gator_buffer, cpu)[i] = NULL;
+			per_cpu(gator_buffer_read, cpu)[i] = 0;
+			per_cpu(gator_buffer_write, cpu)[i] = 0;
+			per_cpu(gator_buffer_commit, cpu)[i] = 0;
+			per_cpu(buffer_space_available, cpu)[i] = true;
+			per_cpu(gator_buffer_commit_time, cpu) = 0;
+		}
+		mutex_unlock(&gator_buffer_mutex);
+	}
+
+	memset(&sent_core_name, 0, sizeof(sent_core_name));
+
+	mutex_unlock(&start_mutex);
+}
+
+static int gator_set_backtrace(unsigned long val)
+{
+	int err = 0;
+
+	mutex_lock(&start_mutex);
+
+	if (gator_started)
+		err = -EBUSY;
+	else
+		gator_backtrace_depth = val;
+
+	mutex_unlock(&start_mutex);
+
+	return err;
+}
+
+static ssize_t enable_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	return gatorfs_ulong_to_user(gator_started, buf, count, offset);
+}
+
+static ssize_t enable_write(struct file *file, char const __user *buf, size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = gatorfs_ulong_from_user(&val, buf, count);
+	if (retval)
+		return retval;
+
+	if (val)
+		retval = gator_op_start();
+	else
+		gator_op_stop();
+
+	if (retval)
+		return retval;
+	return count;
+}
+
+static const struct file_operations enable_fops = {
+	.read = enable_read,
+	.write = enable_write,
+};
+
+static int userspace_buffer_open(struct inode *inode, struct file *file)
+{
+	int err = -EPERM;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (test_and_set_bit_lock(0, &gator_buffer_opened))
+		return -EBUSY;
+
+	err = gator_op_setup();
+	if (err)
+		goto fail;
+
+	/* NB: the actual start happens from userspace
+	 * echo 1 >/dev/gator/enable
+	 */
+
+	return 0;
+
+fail:
+	__clear_bit_unlock(0, &gator_buffer_opened);
+	return err;
+}
+
+static int userspace_buffer_release(struct inode *inode, struct file *file)
+{
+	gator_op_stop();
+	gator_shutdown();
+	__clear_bit_unlock(0, &gator_buffer_opened);
+	return 0;
+}
+
+static ssize_t userspace_buffer_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	int commit, length1, length2, read;
+	char *buffer1;
+	char *buffer2;
+	int cpu, buftype;
+	int written = 0;
+
+	/* ensure there is enough space for a whole frame */
+	if (count < userspace_buffer_size || *offset)
+		return -EINVAL;
+
+	/* sleep until the condition is true or a signal is received the
+	 * condition is checked each time gator_buffer_wait is woken up
+	 */
+	wait_event_interruptible(gator_buffer_wait, buffer_commit_ready(&cpu, &buftype) || !gator_started);
+
+	if (signal_pending(current))
+		return -EINTR;
+
+	if (buftype == -1 || cpu == -1)
+		return 0;
+
+	mutex_lock(&gator_buffer_mutex);
+
+	do {
+		read = per_cpu(gator_buffer_read, cpu)[buftype];
+		commit = per_cpu(gator_buffer_commit, cpu)[buftype];
+
+		/* May happen if the buffer is freed during pending reads. */
+		if (!per_cpu(gator_buffer, cpu)[buftype])
+			break;
+
+		/* determine the size of two halves */
+		length1 = commit - read;
+		length2 = 0;
+		buffer1 = &(per_cpu(gator_buffer, cpu)[buftype][read]);
+		buffer2 = &(per_cpu(gator_buffer, cpu)[buftype][0]);
+		if (length1 < 0) {
+			length1 = gator_buffer_size[buftype] - read;
+			length2 = commit;
+		}
+
+		if (length1 + length2 > count - written)
+			break;
+
+		/* start, middle or end */
+		if (length1 > 0 && copy_to_user(&buf[written], buffer1, length1))
+			break;
+
+		/* possible wrap around */
+		if (length2 > 0 && copy_to_user(&buf[written + length1], buffer2, length2))
+			break;
+
+		per_cpu(gator_buffer_read, cpu)[buftype] = commit;
+		written += length1 + length2;
+
+		/* Wake up annotate_write if more space is available */
+		if (buftype == ANNOTATE_BUF)
+			wake_up(&gator_annotate_wait);
+	} while (buffer_commit_ready(&cpu, &buftype));
+
+	mutex_unlock(&gator_buffer_mutex);
+
+	/* kick just in case we've lost an SMP event */
+	wake_up(&gator_buffer_wait);
+
+	return written > 0 ? written : -EFAULT;
+}
+
+static const struct file_operations gator_event_buffer_fops = {
+	.open = userspace_buffer_open,
+	.release = userspace_buffer_release,
+	.read = userspace_buffer_read,
+};
+
+static ssize_t depth_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	return gatorfs_ulong_to_user(gator_backtrace_depth, buf, count, offset);
+}
+
+static ssize_t depth_write(struct file *file, char const __user *buf, size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = gatorfs_ulong_from_user(&val, buf, count);
+	if (retval)
+		return retval;
+
+	retval = gator_set_backtrace(val);
+
+	if (retval)
+		return retval;
+	return count;
+}
+
+static const struct file_operations depth_fops = {
+	.read = depth_read,
+	.write = depth_write
+};
+
+static void gator_op_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	struct gator_interface *gi;
+	int cpu;
+	int err;
+
+	/* reinitialize default values */
+	gator_cpu_cores = 0;
+	for_each_present_cpu(cpu) {
+		gator_cpu_cores++;
+	}
+	userspace_buffer_size = BACKTRACE_BUFFER_SIZE;
+	gator_response_type = 1;
+	gator_live_rate = 0;
+
+	gatorfs_create_file(sb, root, "enable", &enable_fops);
+	gatorfs_create_file(sb, root, "buffer", &gator_event_buffer_fops);
+	gatorfs_create_file(sb, root, "backtrace_depth", &depth_fops);
+	gatorfs_create_ro_ulong(sb, root, "cpu_cores", &gator_cpu_cores);
+	gatorfs_create_ro_ulong(sb, root, "buffer_size", &userspace_buffer_size);
+	gatorfs_create_ulong(sb, root, "tick", &gator_timer_count);
+	gatorfs_create_ulong(sb, root, "response_type", &gator_response_type);
+	gatorfs_create_ro_ulong(sb, root, "version", &gator_protocol_version);
+	gatorfs_create_ro_u64(sb, root, "started", &gator_monotonic_started);
+	gatorfs_create_u64(sb, root, "live_rate", &gator_live_rate);
+
+	/* Annotate interface */
+	gator_annotate_create_files(sb, root);
+
+	/* Linux Events */
+	dir = gatorfs_mkdir(sb, root, "events");
+	list_for_each_entry(gi, &gator_events, list)
+		if (gi->create_files) {
+			err = gi->create_files(sb, dir);
+			if (err != 0) {
+				pr_err("gator: create_files failed for %s\n", gi->name);
+			}
+		}
+
+	/* Sched Events */
+	sched_trace_create_files(sb, dir);
+
+	/* Power interface */
+	gator_trace_power_create_files(sb, dir);
+}
+
+/******************************************************************************
+ * Module
+ ******************************************************************************/
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 15, 0)
+
+#define GATOR_TRACEPOINTS \
+	GATOR_HANDLE_TRACEPOINT(block_rq_complete); \
+	GATOR_HANDLE_TRACEPOINT(cpu_frequency); \
+	GATOR_HANDLE_TRACEPOINT(cpu_idle); \
+	GATOR_HANDLE_TRACEPOINT(cpu_migrate_begin); \
+	GATOR_HANDLE_TRACEPOINT(cpu_migrate_current); \
+	GATOR_HANDLE_TRACEPOINT(cpu_migrate_finish); \
+	GATOR_HANDLE_TRACEPOINT(irq_handler_exit); \
+	GATOR_HANDLE_TRACEPOINT(mali_hw_counter); \
+	GATOR_HANDLE_TRACEPOINT(mali_job_slots_event); \
+	GATOR_HANDLE_TRACEPOINT(mali_mmu_as_in_use); \
+	GATOR_HANDLE_TRACEPOINT(mali_mmu_as_released); \
+	GATOR_HANDLE_TRACEPOINT(mali_page_fault_insert_pages); \
+	GATOR_HANDLE_TRACEPOINT(mali_pm_status); \
+	GATOR_HANDLE_TRACEPOINT(mali_sw_counter); \
+	GATOR_HANDLE_TRACEPOINT(mali_sw_counters); \
+	GATOR_HANDLE_TRACEPOINT(mali_timeline_event); \
+	GATOR_HANDLE_TRACEPOINT(mali_total_alloc_pages_change); \
+	GATOR_HANDLE_TRACEPOINT(mm_page_alloc); \
+	GATOR_HANDLE_TRACEPOINT(mm_page_free); \
+	GATOR_HANDLE_TRACEPOINT(mm_page_free_batched); \
+	GATOR_HANDLE_TRACEPOINT(sched_process_exec); \
+	GATOR_HANDLE_TRACEPOINT(sched_process_fork); \
+	GATOR_HANDLE_TRACEPOINT(sched_process_free); \
+	GATOR_HANDLE_TRACEPOINT(sched_switch); \
+	GATOR_HANDLE_TRACEPOINT(softirq_exit); \
+	GATOR_HANDLE_TRACEPOINT(task_rename); \
+
+#define GATOR_HANDLE_TRACEPOINT(probe_name) \
+	struct tracepoint *gator_tracepoint_##probe_name
+GATOR_TRACEPOINTS;
+#undef GATOR_HANDLE_TRACEPOINT
+
+static void gator_save_tracepoint(struct tracepoint *tp, void *priv)
+{
+#define GATOR_HANDLE_TRACEPOINT(probe_name) \
+	do { \
+		if (strcmp(tp->name, #probe_name) == 0) { \
+			gator_tracepoint_##probe_name = tp; \
+			return; \
+		} \
+	} while (0)
+GATOR_TRACEPOINTS;
+#undef GATOR_HANDLE_TRACEPOINT
+}
+
+#else
+
+#define for_each_kernel_tracepoint(fct, priv)
+
+#endif
+
+static int __init gator_module_init(void)
+{
+	for_each_kernel_tracepoint(gator_save_tracepoint, NULL);
+
+	if (gatorfs_register())
+		return -1;
+
+	if (gator_init()) {
+		gatorfs_unregister();
+		return -1;
+	}
+
+	setup_deferrable_timer_on_stack(&gator_buffer_wake_up_timer, gator_buffer_wake_up, 0);
+
+	/* Initialize the list of cpuids */
+	memset(gator_cpuids, -1, sizeof(gator_cpuids));
+	on_each_cpu(gator_read_cpuid, NULL, 1);
+
+	return 0;
+}
+
+static void __exit gator_module_exit(void)
+{
+	del_timer_sync(&gator_buffer_wake_up_timer);
+	tracepoint_synchronize_unregister();
+	gator_exit();
+	gatorfs_unregister();
+}
+
+module_init(gator_module_init);
+module_exit(gator_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("ARM Ltd");
+MODULE_DESCRIPTION("Gator system profiler");
+#define STRIFY2(ARG) #ARG
+#define STRIFY(ARG) STRIFY2(ARG)
+MODULE_VERSION(STRIFY(PROTOCOL_VERSION));
diff --git a/drivers/gator/gator_marshaling.c b/drivers/gator/gator_marshaling.c
new file mode 100644
index 00000000000..cb75a349451
--- /dev/null
+++ b/drivers/gator/gator_marshaling.c
@@ -0,0 +1,375 @@
+/**
+ * Copyright (C) ARM Limited 2012-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#define NEWLINE_CANARY \
+	/* Unix */ \
+	"1\n" \
+	/* Windows */ \
+	"2\r\n" \
+	/* Mac OS */ \
+	"3\r" \
+	/* RISC OS */ \
+	"4\n\r" \
+	/* Add another character so the length isn't 0x0a bytes */ \
+	"5"
+
+#ifdef MALI_SUPPORT
+#include "gator_events_mali_common.h"
+#endif
+
+static void marshal_summary(long long timestamp, long long uptime, long long monotonic_delta, const char *uname)
+{
+	unsigned long flags;
+	int cpu = 0;
+	char buf[32];
+
+	local_irq_save(flags);
+	gator_buffer_write_packed_int(cpu, SUMMARY_BUF, MESSAGE_SUMMARY);
+	gator_buffer_write_string(cpu, SUMMARY_BUF, NEWLINE_CANARY);
+	gator_buffer_write_packed_int64(cpu, SUMMARY_BUF, timestamp);
+	gator_buffer_write_packed_int64(cpu, SUMMARY_BUF, uptime);
+	gator_buffer_write_packed_int64(cpu, SUMMARY_BUF, monotonic_delta);
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "uname");
+	gator_buffer_write_string(cpu, SUMMARY_BUF, uname);
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "PAGESIZE");
+	snprintf(buf, sizeof(buf), "%lu", PAGE_SIZE);
+	gator_buffer_write_string(cpu, SUMMARY_BUF, buf);
+#if GATOR_IKS_SUPPORT
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "iks");
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "");
+#endif
+#ifdef CONFIG_PREEMPT_RTB
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "preempt_rtb");
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "");
+#endif
+#ifdef CONFIG_PREEMPT_RT_FULL
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "preempt_rt_full");
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "");
+#endif
+	/* Let Streamline know which GPU is used so that it can label the GPU Activity appropriately. This is a temporary fix, to be improved in a future release. */
+#ifdef MALI_SUPPORT
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "mali_type");
+#if (MALI_SUPPORT == MALI_4xx)
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "4xx");
+#elif (MALI_SUPPORT == MALI_MIDGARD)
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "6xx");
+#else
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "unknown");
+#endif
+#endif
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "");
+	/* Commit the buffer now so it can be one of the first frames read by Streamline */
+	local_irq_restore(flags);
+	gator_commit_buffer(cpu, SUMMARY_BUF, gator_get_time());
+}
+
+static bool marshal_cookie_header(const char *text)
+{
+	int cpu = get_physical_cpu();
+
+	return buffer_check_space(cpu, NAME_BUF, strlen(text) + 3 * MAXSIZE_PACK32);
+}
+
+static void marshal_cookie(int cookie, const char *text)
+{
+	int cpu = get_physical_cpu();
+	/* buffer_check_space already called by marshal_cookie_header */
+	gator_buffer_write_packed_int(cpu, NAME_BUF, MESSAGE_COOKIE);
+	gator_buffer_write_packed_int(cpu, NAME_BUF, cookie);
+	gator_buffer_write_string(cpu, NAME_BUF, text);
+	buffer_check(cpu, NAME_BUF, gator_get_time());
+}
+
+static void marshal_thread_name(int pid, char *name)
+{
+	unsigned long flags, cpu;
+	u64 time;
+
+	local_irq_save(flags);
+	cpu = get_physical_cpu();
+	time = gator_get_time();
+	if (buffer_check_space(cpu, NAME_BUF, TASK_COMM_LEN + 3 * MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+		gator_buffer_write_packed_int(cpu, NAME_BUF, MESSAGE_THREAD_NAME);
+		gator_buffer_write_packed_int64(cpu, NAME_BUF, time);
+		gator_buffer_write_packed_int(cpu, NAME_BUF, pid);
+		gator_buffer_write_string(cpu, NAME_BUF, name);
+	}
+	local_irq_restore(flags);
+	buffer_check(cpu, NAME_BUF, time);
+}
+
+static void marshal_link(int cookie, int tgid, int pid)
+{
+	unsigned long cpu = get_physical_cpu(), flags;
+	u64 time;
+
+	local_irq_save(flags);
+	time = gator_get_time();
+	if (buffer_check_space(cpu, ACTIVITY_BUF, MAXSIZE_PACK64 + 5 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, MESSAGE_LINK);
+		gator_buffer_write_packed_int64(cpu, ACTIVITY_BUF, time);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, cookie);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, tgid);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, pid);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, ACTIVITY_BUF, time);
+}
+
+static bool marshal_backtrace_header(int exec_cookie, int tgid, int pid, u64 time)
+{
+	int cpu = get_physical_cpu();
+
+	if (!buffer_check_space(cpu, BACKTRACE_BUF, MAXSIZE_PACK64 + 5 * MAXSIZE_PACK32 + gator_backtrace_depth * 2 * MAXSIZE_PACK32)) {
+		/* Check and commit; commit is set to occur once buffer is 3/4 full */
+		buffer_check(cpu, BACKTRACE_BUF, time);
+
+		return false;
+	}
+
+	gator_buffer_write_packed_int64(cpu, BACKTRACE_BUF, time);
+	gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, exec_cookie);
+	gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, tgid);
+	gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, pid);
+
+	return true;
+}
+
+static void marshal_backtrace(unsigned long address, int cookie, int in_kernel)
+{
+	int cpu = get_physical_cpu();
+
+	if (cookie == 0 && !in_kernel)
+		cookie = UNRESOLVED_COOKIE;
+	gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, cookie);
+	gator_buffer_write_packed_int64(cpu, BACKTRACE_BUF, address);
+}
+
+static void marshal_backtrace_footer(u64 time)
+{
+	int cpu = get_physical_cpu();
+
+	gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, MESSAGE_END_BACKTRACE);
+
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, BACKTRACE_BUF, time);
+}
+
+static bool marshal_event_header(u64 time)
+{
+	unsigned long flags, cpu = get_physical_cpu();
+	bool retval = false;
+
+	local_irq_save(flags);
+	if (buffer_check_space(cpu, BLOCK_COUNTER_BUF, MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+		gator_buffer_write_packed_int(cpu, BLOCK_COUNTER_BUF, 0);	/* key of zero indicates a timestamp */
+		gator_buffer_write_packed_int64(cpu, BLOCK_COUNTER_BUF, time);
+		retval = true;
+	}
+	local_irq_restore(flags);
+
+	return retval;
+}
+
+static void marshal_event(int len, int *buffer)
+{
+	unsigned long i, flags, cpu = get_physical_cpu();
+
+	if (len <= 0)
+		return;
+
+	/* length must be even since all data is a (key, value) pair */
+	if (len & 0x1) {
+		pr_err("gator: invalid counter data detected and discarded\n");
+		return;
+	}
+
+	/* events must be written in key,value pairs */
+	local_irq_save(flags);
+	for (i = 0; i < len; i += 2) {
+		if (!buffer_check_space(cpu, BLOCK_COUNTER_BUF, 2 * MAXSIZE_PACK32))
+			break;
+		gator_buffer_write_packed_int(cpu, BLOCK_COUNTER_BUF, buffer[i]);
+		gator_buffer_write_packed_int(cpu, BLOCK_COUNTER_BUF, buffer[i + 1]);
+	}
+	local_irq_restore(flags);
+}
+
+static void marshal_event64(int len, long long *buffer64)
+{
+	unsigned long i, flags, cpu = get_physical_cpu();
+
+	if (len <= 0)
+		return;
+
+	/* length must be even since all data is a (key, value) pair */
+	if (len & 0x1) {
+		pr_err("gator: invalid counter data detected and discarded\n");
+		return;
+	}
+
+	/* events must be written in key,value pairs */
+	local_irq_save(flags);
+	for (i = 0; i < len; i += 2) {
+		if (!buffer_check_space(cpu, BLOCK_COUNTER_BUF, 2 * MAXSIZE_PACK64))
+			break;
+		gator_buffer_write_packed_int64(cpu, BLOCK_COUNTER_BUF, buffer64[i]);
+		gator_buffer_write_packed_int64(cpu, BLOCK_COUNTER_BUF, buffer64[i + 1]);
+	}
+	local_irq_restore(flags);
+}
+
+static void __maybe_unused marshal_event_single(int core, int key, int value)
+{
+	unsigned long flags, cpu;
+	u64 time;
+
+	local_irq_save(flags);
+	cpu = get_physical_cpu();
+	time = gator_get_time();
+	if (buffer_check_space(cpu, COUNTER_BUF, MAXSIZE_PACK64 + 3 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int64(cpu, COUNTER_BUF, time);
+		gator_buffer_write_packed_int(cpu, COUNTER_BUF, core);
+		gator_buffer_write_packed_int(cpu, COUNTER_BUF, key);
+		gator_buffer_write_packed_int(cpu, COUNTER_BUF, value);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, COUNTER_BUF, time);
+}
+
+static void __maybe_unused marshal_event_single64(int core, int key, long long value)
+{
+	unsigned long flags, cpu;
+	u64 time;
+
+	local_irq_save(flags);
+	cpu = get_physical_cpu();
+	time = gator_get_time();
+	if (buffer_check_space(cpu, COUNTER_BUF, 2 * MAXSIZE_PACK64 + 2 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int64(cpu, COUNTER_BUF, time);
+		gator_buffer_write_packed_int(cpu, COUNTER_BUF, core);
+		gator_buffer_write_packed_int(cpu, COUNTER_BUF, key);
+		gator_buffer_write_packed_int64(cpu, COUNTER_BUF, value);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, COUNTER_BUF, time);
+}
+
+static void marshal_sched_trace_switch(int pid, int state)
+{
+	unsigned long cpu = get_physical_cpu(), flags;
+	u64 time;
+
+	if (!per_cpu(gator_buffer, cpu)[SCHED_TRACE_BUF])
+		return;
+
+	local_irq_save(flags);
+	time = gator_get_time();
+	if (buffer_check_space(cpu, SCHED_TRACE_BUF, MAXSIZE_PACK64 + 5 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, MESSAGE_SCHED_SWITCH);
+		gator_buffer_write_packed_int64(cpu, SCHED_TRACE_BUF, time);
+		gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, pid);
+		gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, state);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, SCHED_TRACE_BUF, time);
+}
+
+static void marshal_sched_trace_exit(int tgid, int pid)
+{
+	unsigned long cpu = get_physical_cpu(), flags;
+	u64 time;
+
+	if (!per_cpu(gator_buffer, cpu)[SCHED_TRACE_BUF])
+		return;
+
+	local_irq_save(flags);
+	time = gator_get_time();
+	if (buffer_check_space(cpu, SCHED_TRACE_BUF, MAXSIZE_PACK64 + 2 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, MESSAGE_SCHED_EXIT);
+		gator_buffer_write_packed_int64(cpu, SCHED_TRACE_BUF, time);
+		gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, pid);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, SCHED_TRACE_BUF, time);
+}
+
+#if GATOR_CPU_FREQ_SUPPORT
+static void marshal_idle(int core, int state)
+{
+	unsigned long flags, cpu;
+	u64 time;
+
+	local_irq_save(flags);
+	cpu = get_physical_cpu();
+	time = gator_get_time();
+	if (buffer_check_space(cpu, IDLE_BUF, MAXSIZE_PACK64 + 2 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int(cpu, IDLE_BUF, state);
+		gator_buffer_write_packed_int64(cpu, IDLE_BUF, time);
+		gator_buffer_write_packed_int(cpu, IDLE_BUF, core);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, IDLE_BUF, time);
+}
+#endif
+
+#if defined(__arm__) || defined(__aarch64__)
+static void marshal_core_name(const int core, const int cpuid, const char *name)
+{
+	int cpu = get_physical_cpu();
+	unsigned long flags;
+
+	local_irq_save(flags);
+	if (buffer_check_space(cpu, SUMMARY_BUF, MAXSIZE_PACK32 + MAXSIZE_CORE_NAME)) {
+		gator_buffer_write_packed_int(cpu, SUMMARY_BUF, MESSAGE_CORE_NAME);
+		gator_buffer_write_packed_int(cpu, SUMMARY_BUF, core);
+		gator_buffer_write_packed_int(cpu, SUMMARY_BUF, cpuid);
+		gator_buffer_write_string(cpu, SUMMARY_BUF, name);
+	}
+	/* Commit core names now so that they can show up in live */
+	local_irq_restore(flags);
+	gator_commit_buffer(cpu, SUMMARY_BUF, gator_get_time());
+}
+#endif
+
+static void marshal_activity_switch(int core, int key, int activity, int pid, int state)
+{
+	unsigned long cpu = get_physical_cpu(), flags;
+	u64 time;
+
+	if (!per_cpu(gator_buffer, cpu)[ACTIVITY_BUF])
+		return;
+
+	local_irq_save(flags);
+	time = gator_get_time();
+	if (buffer_check_space(cpu, ACTIVITY_BUF, MAXSIZE_PACK64 + 5 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, MESSAGE_SWITCH);
+		gator_buffer_write_packed_int64(cpu, ACTIVITY_BUF, time);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, core);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, key);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, activity);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, pid);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, state);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, ACTIVITY_BUF, time);
+}
+
+void gator_marshal_activity_switch(int core, int key, int activity, int pid)
+{
+	/* state is reserved for cpu use only */
+	marshal_activity_switch(core, key, activity, pid, 0);
+}
diff --git a/drivers/gator/gator_trace_gpu.c b/drivers/gator/gator_trace_gpu.c
new file mode 100644
index 00000000000..b35ccd58f9d
--- /dev/null
+++ b/drivers/gator/gator_trace_gpu.c
@@ -0,0 +1,321 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+
+#ifdef MALI_SUPPORT
+#ifdef MALI_DIR_MIDGARD
+/* New DDK Directory structure with kernel/drivers/gpu/arm/midgard*/
+#include "mali_linux_trace.h"
+#else
+/* Old DDK Directory structure with kernel/drivers/gpu/arm/t6xx*/
+#include "linux/mali_linux_trace.h"
+#endif
+#endif
+
+/*
+ * Taken from MALI_PROFILING_EVENT_TYPE_* items in Mali DDK.
+ */
+#define EVENT_TYPE_SINGLE  0
+#define EVENT_TYPE_START   1
+#define EVENT_TYPE_STOP    2
+#define EVENT_TYPE_SUSPEND 3
+#define EVENT_TYPE_RESUME  4
+
+/* Note whether tracepoints have been registered */
+static int mali_timeline_trace_registered;
+static int mali_job_slots_trace_registered;
+
+enum {
+	GPU_UNIT_NONE = 0,
+	GPU_UNIT_VP,
+	GPU_UNIT_FP,
+	GPU_UNIT_CL,
+	NUMBER_OF_GPU_UNITS
+};
+
+#if defined(MALI_SUPPORT)
+
+struct mali_activity {
+	int core;
+	int key;
+	int count;
+	int last_activity;
+	int last_pid;
+};
+
+#define NUMBER_OF_GPU_CORES 16
+static struct mali_activity mali_activities[NUMBER_OF_GPU_UNITS*NUMBER_OF_GPU_CORES];
+static DEFINE_SPINLOCK(mali_activities_lock);
+
+/* Only one event should be running on a unit and core at a time (ie,
+ * a start event can only be followed by a stop and vice versa), but
+ * because the kernel only knows when a job is enqueued and not
+ * started, it is possible for a start1, start2, stop1, stop2. Change
+ * it back into start1, stop1, start2, stop2 by queueing up start2 and
+ * releasing it when stop1 is received.
+ */
+
+static int mali_activity_index(int core, int key)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(mali_activities); ++i) {
+		if ((mali_activities[i].core == core) && (mali_activities[i].key == key))
+			break;
+		if ((mali_activities[i].core == 0) && (mali_activities[i].key == 0)) {
+			mali_activities[i].core = core;
+			mali_activities[i].key = key;
+			break;
+		}
+	}
+	BUG_ON(i >= ARRAY_SIZE(mali_activities));
+
+	return i;
+}
+
+static void mali_activity_enqueue(int core, int key, int activity, int pid)
+{
+	int i;
+	int count;
+
+	spin_lock(&mali_activities_lock);
+	i = mali_activity_index(core, key);
+
+	count = mali_activities[i].count;
+	BUG_ON(count < 0);
+	++mali_activities[i].count;
+	if (count) {
+		mali_activities[i].last_activity = activity;
+		mali_activities[i].last_pid = pid;
+	}
+	spin_unlock(&mali_activities_lock);
+
+	if (!count)
+		gator_marshal_activity_switch(core, key, activity, pid);
+}
+
+static void mali_activity_stop(int core, int key)
+{
+	int i;
+	int count;
+	int last_activity = 0;
+	int last_pid = 0;
+
+	spin_lock(&mali_activities_lock);
+	i = mali_activity_index(core, key);
+
+	if (mali_activities[i].count == 0) {
+		spin_unlock(&mali_activities_lock);
+		return;
+	}
+	--mali_activities[i].count;
+	count = mali_activities[i].count;
+	if (count) {
+		last_activity = mali_activities[i].last_activity;
+		last_pid = mali_activities[i].last_pid;
+	}
+	spin_unlock(&mali_activities_lock);
+
+	gator_marshal_activity_switch(core, key, 0, 0);
+	if (count)
+		gator_marshal_activity_switch(core, key, last_activity, last_pid);
+}
+
+static void mali_activity_clear(struct mali_counter mali_activity[], size_t mali_activity_size)
+{
+	int activity;
+	int cores;
+	int core;
+
+	for (activity = 0; activity < mali_activity_size; ++activity) {
+		cores = mali_activity[activity].cores;
+		if (cores < 0)
+			cores = 1;
+		for (core = 0; core < cores; ++core) {
+			if (mali_activity[activity].enabled) {
+				preempt_disable();
+				gator_marshal_activity_switch(core, mali_activity[activity].key, 0, 0);
+				preempt_enable();
+			}
+		}
+	}
+}
+
+#endif
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_MIDGARD)
+#include "gator_events_mali_4xx.h"
+
+/*
+ * Taken from MALI_PROFILING_EVENT_CHANNEL_* in Mali DDK.
+ */
+enum {
+	EVENT_CHANNEL_SOFTWARE = 0,
+	EVENT_CHANNEL_VP0 = 1,
+	EVENT_CHANNEL_FP0 = 5,
+	EVENT_CHANNEL_FP1,
+	EVENT_CHANNEL_FP2,
+	EVENT_CHANNEL_FP3,
+	EVENT_CHANNEL_FP4,
+	EVENT_CHANNEL_FP5,
+	EVENT_CHANNEL_FP6,
+	EVENT_CHANNEL_FP7,
+	EVENT_CHANNEL_GPU = 21
+};
+
+/**
+ * These events are applicable when the type MALI_PROFILING_EVENT_TYPE_SINGLE is used from the GPU channel
+ */
+enum {
+	EVENT_REASON_SINGLE_GPU_NONE = 0,
+	EVENT_REASON_SINGLE_GPU_FREQ_VOLT_CHANGE = 1,
+};
+
+struct mali_counter mali_activity[2];
+
+GATOR_DEFINE_PROBE(mali_timeline_event, TP_PROTO(unsigned int event_id, unsigned int d0, unsigned int d1, unsigned int d2, unsigned int d3, unsigned int d4))
+{
+	unsigned int component, state;
+
+	/* do as much work as possible before disabling interrupts */
+	component = (event_id >> 16) & 0xFF;	/* component is an 8-bit field */
+	state = (event_id >> 24) & 0xF;	/* state is a 4-bit field */
+
+	switch (state) {
+	case EVENT_TYPE_START:
+		if (component == EVENT_CHANNEL_VP0) {
+			/* tgid = d0; pid = d1; */
+			if (mali_activity[1].enabled)
+				mali_activity_enqueue(0, mali_activity[1].key, 1, d1);
+		} else if (component >= EVENT_CHANNEL_FP0 && component <= EVENT_CHANNEL_FP7) {
+			/* tgid = d0; pid = d1; */
+			if (mali_activity[0].enabled)
+				mali_activity_enqueue(component - EVENT_CHANNEL_FP0, mali_activity[0].key, 1, d1);
+		}
+		break;
+
+	case EVENT_TYPE_STOP:
+		if (component == EVENT_CHANNEL_VP0) {
+			if (mali_activity[1].enabled)
+				mali_activity_stop(0, mali_activity[1].key);
+		} else if (component >= EVENT_CHANNEL_FP0 && component <= EVENT_CHANNEL_FP7) {
+			if (mali_activity[0].enabled)
+				mali_activity_stop(component - EVENT_CHANNEL_FP0, mali_activity[0].key);
+		}
+		break;
+
+	case EVENT_TYPE_SINGLE:
+		if (component == EVENT_CHANNEL_GPU) {
+			unsigned int reason = (event_id & 0xffff);
+
+			if (reason == EVENT_REASON_SINGLE_GPU_FREQ_VOLT_CHANGE)
+				gator_events_mali_log_dvfs_event(d0, d1);
+		}
+		break;
+
+	default:
+		break;
+	}
+}
+#endif
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_MIDGARD)
+
+struct mali_counter mali_activity[3];
+
+#if defined(MALI_JOB_SLOTS_EVENT_CHANGED)
+GATOR_DEFINE_PROBE(mali_job_slots_event, TP_PROTO(unsigned int event_id, unsigned int tgid, unsigned int pid, unsigned char job_id))
+#else
+GATOR_DEFINE_PROBE(mali_job_slots_event, TP_PROTO(unsigned int event_id, unsigned int tgid, unsigned int pid))
+#endif
+{
+	unsigned int component, state, unit;
+#if !defined(MALI_JOB_SLOTS_EVENT_CHANGED)
+	unsigned char job_id = 0;
+#endif
+
+	component = (event_id >> 16) & 0xFF;	/* component is an 8-bit field */
+	state = (event_id >> 24) & 0xF;	/* state is a 4-bit field */
+
+	switch (component) {
+	case 0:
+		unit = GPU_UNIT_FP;
+		break;
+	case 1:
+		unit = GPU_UNIT_VP;
+		break;
+	case 2:
+		unit = GPU_UNIT_CL;
+		break;
+	default:
+		unit = GPU_UNIT_NONE;
+	}
+
+	if (unit != GPU_UNIT_NONE) {
+		switch (state) {
+		case EVENT_TYPE_START:
+			if (mali_activity[component].enabled)
+				mali_activity_enqueue(0, mali_activity[component].key, 1, (pid != 0 ? pid : tgid));
+			break;
+		case EVENT_TYPE_STOP:
+		default: /* Some jobs can be soft-stopped, so ensure that this terminates the activity trace. */
+			if (mali_activity[component].enabled)
+				mali_activity_stop(0, mali_activity[component].key);
+			break;
+		}
+	}
+}
+#endif
+
+static int gator_trace_gpu_start(void)
+{
+	/*
+	 * Returns nonzero for installation failed
+	 * Absence of gpu trace points is not an error
+	 */
+
+#if defined(MALI_SUPPORT)
+	memset(&mali_activities, 0, sizeof(mali_activities));
+#endif
+	mali_timeline_trace_registered = mali_job_slots_trace_registered = 0;
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_MIDGARD)
+	mali_activity_clear(mali_activity, ARRAY_SIZE(mali_activity));
+	if (!GATOR_REGISTER_TRACE(mali_timeline_event))
+		mali_timeline_trace_registered = 1;
+#endif
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_MIDGARD)
+	mali_activity_clear(mali_activity, ARRAY_SIZE(mali_activity));
+	if (!GATOR_REGISTER_TRACE(mali_job_slots_event))
+		mali_job_slots_trace_registered = 1;
+#endif
+
+	return 0;
+}
+
+static void gator_trace_gpu_stop(void)
+{
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_MIDGARD)
+	if (mali_timeline_trace_registered)
+		GATOR_UNREGISTER_TRACE(mali_timeline_event);
+#endif
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_MIDGARD)
+	if (mali_job_slots_trace_registered)
+		GATOR_UNREGISTER_TRACE(mali_job_slots_event);
+#endif
+
+	mali_timeline_trace_registered = mali_job_slots_trace_registered = 0;
+}
diff --git a/drivers/gator/gator_trace_power.c b/drivers/gator/gator_trace_power.c
new file mode 100644
index 00000000000..aaa8f8636c8
--- /dev/null
+++ b/drivers/gator/gator_trace_power.c
@@ -0,0 +1,186 @@
+/**
+ * Copyright (C) ARM Limited 2011-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/cpufreq.h>
+#include <trace/events/power.h>
+
+#if defined(__arm__)
+
+#include <asm/mach-types.h>
+
+#define implements_wfi() (!machine_is_omap3_beagle())
+
+#else
+
+#define implements_wfi() false
+
+#endif
+
+/* cpu_frequency and cpu_idle trace points were introduced in Linux
+ * kernel v2.6.38 the now deprecated power_frequency trace point was
+ * available prior to 2.6.38, but only for x86
+ */
+#if GATOR_CPU_FREQ_SUPPORT
+enum {
+	POWER_CPU_FREQ,
+	POWER_TOTAL
+};
+
+static DEFINE_PER_CPU(ulong, idle_prev_state);
+static ulong power_cpu_enabled[POWER_TOTAL];
+static ulong power_cpu_key[POWER_TOTAL];
+static ulong power_cpu_cores;
+
+static int gator_trace_power_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	int cpu;
+	bool found_nonzero_freq = false;
+
+	/* Even if CONFIG_CPU_FREQ is defined, it still may not be
+	 * used. Check for non-zero values from cpufreq_quick_get
+	 */
+	for_each_online_cpu(cpu) {
+		if (cpufreq_quick_get(cpu) > 0) {
+			found_nonzero_freq = true;
+			break;
+		}
+	}
+
+	if (found_nonzero_freq) {
+		/* cpu_frequency */
+		dir = gatorfs_mkdir(sb, root, "Linux_power_cpu_freq");
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &power_cpu_enabled[POWER_CPU_FREQ]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &power_cpu_key[POWER_CPU_FREQ]);
+	}
+
+	return 0;
+}
+
+/* 'cpu' may not equal smp_processor_id(), i.e. may not be running on the core that is having the freq/idle state change */
+GATOR_DEFINE_PROBE(cpu_frequency, TP_PROTO(unsigned int frequency, unsigned int cpu))
+{
+	cpu = lcpu_to_pcpu(cpu);
+	marshal_event_single64(cpu, power_cpu_key[POWER_CPU_FREQ], frequency * 1000L);
+}
+
+GATOR_DEFINE_PROBE(cpu_idle, TP_PROTO(unsigned int state, unsigned int cpu))
+{
+	cpu = lcpu_to_pcpu(cpu);
+
+	if (state == per_cpu(idle_prev_state, cpu))
+		return;
+
+	if (implements_wfi()) {
+		marshal_idle(cpu, state);
+	}
+
+	per_cpu(idle_prev_state, cpu) = state;
+}
+
+static void gator_trace_power_online(void)
+{
+	int pcpu = get_physical_cpu();
+	int lcpu = get_logical_cpu();
+
+	if (power_cpu_enabled[POWER_CPU_FREQ])
+		marshal_event_single64(pcpu, power_cpu_key[POWER_CPU_FREQ], cpufreq_quick_get(lcpu) * 1000L);
+}
+
+static void gator_trace_power_offline(void)
+{
+	/* Set frequency to zero on an offline */
+	int cpu = get_physical_cpu();
+
+	if (power_cpu_enabled[POWER_CPU_FREQ])
+		marshal_event_single(cpu, power_cpu_key[POWER_CPU_FREQ], 0);
+}
+
+static int gator_trace_power_start(void)
+{
+	int cpu;
+
+	/* register tracepoints */
+	if (power_cpu_enabled[POWER_CPU_FREQ])
+		if (GATOR_REGISTER_TRACE(cpu_frequency))
+			goto fail_cpu_frequency_exit;
+
+	/* Always register for cpu_idle for detecting WFI */
+	if (GATOR_REGISTER_TRACE(cpu_idle))
+		goto fail_cpu_idle_exit;
+	pr_debug("gator: registered power event tracepoints\n");
+
+	for_each_present_cpu(cpu) {
+		per_cpu(idle_prev_state, cpu) = 0;
+	}
+
+	return 0;
+
+	/* unregister tracepoints on error */
+fail_cpu_idle_exit:
+	if (power_cpu_enabled[POWER_CPU_FREQ])
+		GATOR_UNREGISTER_TRACE(cpu_frequency);
+fail_cpu_frequency_exit:
+	pr_err("gator: power event tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+	return -1;
+}
+
+static void gator_trace_power_stop(void)
+{
+	int i;
+
+	if (power_cpu_enabled[POWER_CPU_FREQ])
+		GATOR_UNREGISTER_TRACE(cpu_frequency);
+	GATOR_UNREGISTER_TRACE(cpu_idle);
+	pr_debug("gator: unregistered power event tracepoints\n");
+
+	for (i = 0; i < POWER_TOTAL; i++)
+		power_cpu_enabled[i] = 0;
+}
+
+static void gator_trace_power_init(void)
+{
+	int i;
+
+	power_cpu_cores = nr_cpu_ids;
+	for (i = 0; i < POWER_TOTAL; i++) {
+		power_cpu_enabled[i] = 0;
+		power_cpu_key[i] = gator_events_get_key();
+	}
+}
+#else
+static int gator_trace_power_create_files(struct super_block *sb, struct dentry *root)
+{
+	return 0;
+}
+
+static void gator_trace_power_online(void)
+{
+}
+
+static void gator_trace_power_offline(void)
+{
+}
+
+static int gator_trace_power_start(void)
+{
+	return 0;
+}
+
+static void gator_trace_power_stop(void)
+{
+}
+
+static void gator_trace_power_init(void)
+{
+}
+#endif
diff --git a/drivers/gator/gator_trace_sched.c b/drivers/gator/gator_trace_sched.c
new file mode 100644
index 00000000000..700dd2ecdf0
--- /dev/null
+++ b/drivers/gator/gator_trace_sched.c
@@ -0,0 +1,327 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <trace/events/sched.h>
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+#include <trace/events/task.h>
+#endif
+
+#include "gator.h"
+
+#define TASK_MAP_ENTRIES		1024	/* must be power of 2 */
+#define TASK_MAX_COLLISIONS		2
+
+enum {
+	STATE_WAIT_ON_OTHER = 0,
+	STATE_CONTENTION,
+	STATE_WAIT_ON_IO,
+	CPU_WAIT_TOTAL
+};
+
+static DEFINE_PER_CPU(uint64_t *, taskname_keys);
+static DEFINE_PER_CPU(int, collecting);
+
+/* this array is never read as the cpu wait charts are derived
+ * counters the files are needed, nonetheless, to show that these
+ * counters are available
+ */
+static ulong cpu_wait_enabled[CPU_WAIT_TOTAL];
+static ulong sched_cpu_key[CPU_WAIT_TOTAL];
+
+static int sched_trace_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+
+	/* CPU Wait - Contention */
+	dir = gatorfs_mkdir(sb, root, "Linux_cpu_wait_contention");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &cpu_wait_enabled[STATE_CONTENTION]);
+	gatorfs_create_ro_ulong(sb, dir, "key", &sched_cpu_key[STATE_CONTENTION]);
+
+	/* CPU Wait - I/O */
+	dir = gatorfs_mkdir(sb, root, "Linux_cpu_wait_io");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &cpu_wait_enabled[STATE_WAIT_ON_IO]);
+	gatorfs_create_ro_ulong(sb, dir, "key", &sched_cpu_key[STATE_WAIT_ON_IO]);
+
+	return 0;
+}
+
+static void emit_pid_name(const char *comm, struct task_struct *task)
+{
+	bool found = false;
+	char taskcomm[TASK_COMM_LEN + 3];
+	unsigned long x, cpu = get_physical_cpu();
+	uint64_t *keys = &(per_cpu(taskname_keys, cpu)[(task->pid & 0xFF) * TASK_MAX_COLLISIONS]);
+	uint64_t value;
+
+	value = gator_chksum_crc32(comm);
+	value = (value << 32) | (uint32_t)task->pid;
+
+	/* determine if the thread name was emitted already */
+	for (x = 0; x < TASK_MAX_COLLISIONS; x++) {
+		if (keys[x] == value) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		/* shift values, new value always in front */
+		uint64_t oldv, newv = value;
+
+		for (x = 0; x < TASK_MAX_COLLISIONS; x++) {
+			oldv = keys[x];
+			keys[x] = newv;
+			newv = oldv;
+		}
+
+		/* emit pid names, cannot use get_task_comm, as it's not exported on all kernel versions */
+		if (strlcpy(taskcomm, comm, TASK_COMM_LEN) == TASK_COMM_LEN - 1) {
+			/* append ellipses if comm has length of TASK_COMM_LEN - 1 */
+			strcat(taskcomm, "...");
+		}
+
+		marshal_thread_name(task->pid, taskcomm);
+	}
+}
+
+static void collect_counters(u64 time, struct task_struct *task, bool sched_switch)
+{
+	int *buffer, len, cpu = get_physical_cpu();
+	long long *buffer64;
+	struct gator_interface *gi;
+
+	if (marshal_event_header(time)) {
+		list_for_each_entry(gi, &gator_events, list) {
+			if (gi->read) {
+				len = gi->read(&buffer, sched_switch);
+				if (len < 0)
+					pr_err("gator: read failed for %s\n", gi->name);
+				marshal_event(len, buffer);
+			} else if (gi->read64) {
+				len = gi->read64(&buffer64, sched_switch);
+				if (len < 0)
+					pr_err("gator: read64 failed for %s\n", gi->name);
+				marshal_event64(len, buffer64);
+			}
+			if (gi->read_proc && task != NULL) {
+				len = gi->read_proc(&buffer64, task);
+				if (len < 0)
+					pr_err("gator: read_proc failed for %s\n", gi->name);
+				marshal_event64(len, buffer64);
+			}
+		}
+		if (cpu == 0)
+			gator_emit_perf_time(time);
+		/* Only check after writing all counters so that time and corresponding counters appear in the same frame */
+		buffer_check(cpu, BLOCK_COUNTER_BUF, time);
+
+		/* Commit buffers on timeout */
+		if (gator_live_rate > 0 && time >= per_cpu(gator_buffer_commit_time, cpu)) {
+			static const int buftypes[] = { NAME_BUF, COUNTER_BUF, BLOCK_COUNTER_BUF, SCHED_TRACE_BUF, ACTIVITY_BUF };
+			int i;
+
+			for (i = 0; i < ARRAY_SIZE(buftypes); ++i)
+				gator_commit_buffer(cpu, buftypes[i], time);
+
+			/* spinlocks are noops on uniprocessor machines and mutexes do
+			 * not work in sched_switch context in RT-Preempt full, so
+			 * disable proactive flushing of the annotate frame on
+			 * uniprocessor machines.
+			 */
+#ifdef CONFIG_SMP
+			/* Try to preemptively flush the annotate buffer to reduce the chance of the buffer being full */
+			if (on_primary_core() && spin_trylock(&annotate_lock)) {
+				gator_commit_buffer(0, ANNOTATE_BUF, time);
+				spin_unlock(&annotate_lock);
+			}
+#endif
+		}
+	}
+}
+
+/* special case used during a suspend of the system */
+static void trace_sched_insert_idle(void)
+{
+	marshal_sched_trace_switch(0, 0);
+}
+
+static void gator_trace_emit_link(struct task_struct *p)
+{
+	int cookie;
+	int cpu = get_physical_cpu();
+
+	cookie = get_exec_cookie(cpu, p);
+	emit_pid_name(p->comm, p);
+
+	marshal_link(cookie, p->tgid, p->pid);
+}
+
+GATOR_DEFINE_PROBE(sched_process_fork, TP_PROTO(struct task_struct *parent, struct task_struct *child))
+{
+	gator_trace_emit_link(child);
+}
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+GATOR_DEFINE_PROBE(sched_process_exec, TP_PROTO(struct task_struct *p, pid_t old_pid, struct linux_binprm *bprm))
+{
+	gator_trace_emit_link(p);
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 15, 0)
+GATOR_DEFINE_PROBE(task_rename, TP_PROTO(struct task_struct *task, char *comm))
+#else
+GATOR_DEFINE_PROBE(task_rename, TP_PROTO(struct task_struct *task, const char *comm))
+#endif
+{
+	emit_pid_name(comm, task);
+}
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 35)
+GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct rq *rq, struct task_struct *prev, struct task_struct *next))
+#else
+GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct task_struct *prev, struct task_struct *next))
+#endif
+{
+	int state;
+	int cpu = get_physical_cpu();
+
+	per_cpu(in_scheduler_context, cpu) = true;
+
+	/* do as much work as possible before disabling interrupts */
+	if (prev->state == TASK_RUNNING)
+		state = STATE_CONTENTION;
+	else if (prev->in_iowait)
+		state = STATE_WAIT_ON_IO;
+	else
+		state = STATE_WAIT_ON_OTHER;
+
+	per_cpu(collecting, cpu) = 1;
+	collect_counters(gator_get_time(), prev, true);
+	per_cpu(collecting, cpu) = 0;
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)
+	gator_trace_emit_link(next);
+#endif
+	marshal_sched_trace_switch(next->pid, state);
+
+	per_cpu(in_scheduler_context, cpu) = false;
+}
+
+GATOR_DEFINE_PROBE(sched_process_free, TP_PROTO(struct task_struct *p))
+{
+	marshal_sched_trace_exit(p->tgid, p->pid);
+}
+
+static void do_nothing(void *info)
+{
+	/* Intentionally do nothing */
+	(void)info;
+}
+
+static int register_scheduler_tracepoints(void)
+{
+	/* register tracepoints */
+	if (GATOR_REGISTER_TRACE(sched_process_fork))
+		goto fail_sched_process_fork;
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+	if (GATOR_REGISTER_TRACE(sched_process_exec))
+		goto fail_sched_process_exec;
+	if (GATOR_REGISTER_TRACE(task_rename))
+		goto fail_task_rename;
+#endif
+	if (GATOR_REGISTER_TRACE(sched_switch))
+		goto fail_sched_switch;
+	if (GATOR_REGISTER_TRACE(sched_process_free))
+		goto fail_sched_process_free;
+	pr_debug("gator: registered tracepoints\n");
+
+	/* Now that the scheduler tracepoint is registered, force a context
+	 * switch on all cpus to capture what is currently running.
+	 */
+	on_each_cpu(do_nothing, NULL, 0);
+
+	return 0;
+
+	/* unregister tracepoints on error */
+fail_sched_process_free:
+	GATOR_UNREGISTER_TRACE(sched_switch);
+fail_sched_switch:
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+	GATOR_UNREGISTER_TRACE(task_rename);
+fail_task_rename:
+	GATOR_UNREGISTER_TRACE(sched_process_exec);
+fail_sched_process_exec:
+#endif
+	GATOR_UNREGISTER_TRACE(sched_process_fork);
+fail_sched_process_fork:
+	pr_err("gator: tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+	return -1;
+}
+
+static void unregister_scheduler_tracepoints(void)
+{
+	GATOR_UNREGISTER_TRACE(sched_process_fork);
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+	GATOR_UNREGISTER_TRACE(sched_process_exec);
+	GATOR_UNREGISTER_TRACE(task_rename);
+#endif
+	GATOR_UNREGISTER_TRACE(sched_switch);
+	GATOR_UNREGISTER_TRACE(sched_process_free);
+	pr_debug("gator: unregistered tracepoints\n");
+}
+
+static void gator_trace_sched_stop(void)
+{
+	int cpu;
+
+	unregister_scheduler_tracepoints();
+
+	for_each_present_cpu(cpu) {
+		kfree(per_cpu(taskname_keys, cpu));
+	}
+}
+
+static int gator_trace_sched_start(void)
+{
+	int cpu, size;
+	int ret;
+
+	for_each_present_cpu(cpu) {
+		size = TASK_MAP_ENTRIES * TASK_MAX_COLLISIONS * sizeof(uint64_t);
+		per_cpu(taskname_keys, cpu) = kmalloc(size, GFP_KERNEL);
+		if (!per_cpu(taskname_keys, cpu))
+			return -1;
+		memset(per_cpu(taskname_keys, cpu), 0, size);
+	}
+
+	ret = register_scheduler_tracepoints();
+
+	return ret;
+}
+
+static void gator_trace_sched_offline(void)
+{
+	trace_sched_insert_idle();
+}
+
+static void gator_trace_sched_init(void)
+{
+	int i;
+
+	for (i = 0; i < CPU_WAIT_TOTAL; i++) {
+		cpu_wait_enabled[i] = 0;
+		sched_cpu_key[i] = gator_events_get_key();
+	}
+}
diff --git a/drivers/gator/mali/mali_mjollnir_profiling_gator_api.h b/drivers/gator/mali/mali_mjollnir_profiling_gator_api.h
new file mode 100644
index 00000000000..a5d16515739
--- /dev/null
+++ b/drivers/gator/mali/mali_mjollnir_profiling_gator_api.h
@@ -0,0 +1,159 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __MALI_MJOLLNIR_PROFILING_GATOR_API_H__
+#define __MALI_MJOLLNIR_PROFILING_GATOR_API_H__
+
+#ifdef __cplusplus
+extern "C"
+{
+#endif
+
+
+/*
+ * The number of processor cores.  Update to suit your hardware implementation.
+ */
+#define MAX_NUM_FP_CORES            (4)
+#define MAX_NUM_VP_CORES            (1)
+#define MAX_NUM_L2_CACHE_CORES      (1)
+
+enum counters {
+	/* Timeline activity */
+	ACTIVITY_VP_0 = 0,
+	ACTIVITY_FP_0,
+	ACTIVITY_FP_1,
+	ACTIVITY_FP_2,
+	ACTIVITY_FP_3,
+
+	/* L2 cache counters */
+	COUNTER_L2_0_C0,
+	COUNTER_L2_0_C1,
+
+	/* Vertex processor counters */
+	COUNTER_VP_0_C0,
+	COUNTER_VP_0_C1,
+
+	/* Fragment processor counters */
+	COUNTER_FP_0_C0,
+	COUNTER_FP_0_C1,
+	COUNTER_FP_1_C0,
+	COUNTER_FP_1_C1,
+	COUNTER_FP_2_C0,
+	COUNTER_FP_2_C1,
+	COUNTER_FP_3_C0,
+	COUNTER_FP_3_C1,
+
+	/* EGL Software Counters */
+	COUNTER_EGL_BLIT_TIME,
+
+	/* GLES Software Counters */
+	COUNTER_GLES_DRAW_ELEMENTS_CALLS,
+	COUNTER_GLES_DRAW_ELEMENTS_NUM_INDICES,
+	COUNTER_GLES_DRAW_ELEMENTS_NUM_TRANSFORMED,
+	COUNTER_GLES_DRAW_ARRAYS_CALLS,
+	COUNTER_GLES_DRAW_ARRAYS_NUM_TRANSFORMED,
+	COUNTER_GLES_DRAW_POINTS,
+	COUNTER_GLES_DRAW_LINES,
+	COUNTER_GLES_DRAW_LINE_LOOP,
+	COUNTER_GLES_DRAW_LINE_STRIP,
+	COUNTER_GLES_DRAW_TRIANGLES,
+	COUNTER_GLES_DRAW_TRIANGLE_STRIP,
+	COUNTER_GLES_DRAW_TRIANGLE_FAN,
+	COUNTER_GLES_NON_VBO_DATA_COPY_TIME,
+	COUNTER_GLES_UNIFORM_BYTES_COPIED_TO_MALI,
+	COUNTER_GLES_UPLOAD_TEXTURE_TIME,
+	COUNTER_GLES_UPLOAD_VBO_TIME,
+	COUNTER_GLES_NUM_FLUSHES,
+	COUNTER_GLES_NUM_VSHADERS_GENERATED,
+	COUNTER_GLES_NUM_FSHADERS_GENERATED,
+	COUNTER_GLES_VSHADER_GEN_TIME,
+	COUNTER_GLES_FSHADER_GEN_TIME,
+	COUNTER_GLES_INPUT_TRIANGLES,
+	COUNTER_GLES_VXCACHE_HIT,
+	COUNTER_GLES_VXCACHE_MISS,
+	COUNTER_GLES_VXCACHE_COLLISION,
+	COUNTER_GLES_CULLED_TRIANGLES,
+	COUNTER_GLES_CULLED_LINES,
+	COUNTER_GLES_BACKFACE_TRIANGLES,
+	COUNTER_GLES_GBCLIP_TRIANGLES,
+	COUNTER_GLES_GBCLIP_LINES,
+	COUNTER_GLES_TRIANGLES_DRAWN,
+	COUNTER_GLES_DRAWCALL_TIME,
+	COUNTER_GLES_TRIANGLES_COUNT,
+	COUNTER_GLES_INDEPENDENT_TRIANGLES_COUNT,
+	COUNTER_GLES_STRIP_TRIANGLES_COUNT,
+	COUNTER_GLES_FAN_TRIANGLES_COUNT,
+	COUNTER_GLES_LINES_COUNT,
+	COUNTER_GLES_INDEPENDENT_LINES_COUNT,
+	COUNTER_GLES_STRIP_LINES_COUNT,
+	COUNTER_GLES_LOOP_LINES_COUNT,
+
+	COUNTER_FILMSTRIP,
+	COUNTER_FREQUENCY,
+	COUNTER_VOLTAGE,
+
+	NUMBER_OF_EVENTS
+};
+
+#define FIRST_ACTIVITY_EVENT    ACTIVITY_VP_0
+#define LAST_ACTIVITY_EVENT     ACTIVITY_FP_3
+
+#define FIRST_HW_COUNTER        COUNTER_L2_0_C0
+#define LAST_HW_COUNTER         COUNTER_FP_3_C1
+
+#define FIRST_SW_COUNTER        COUNTER_EGL_BLIT_TIME
+#define LAST_SW_COUNTER         COUNTER_GLES_LOOP_LINES_COUNT
+
+/* Signifies that the system is able to report voltage and frequency numbers. */
+#define DVFS_REPORTED_BY_DDK 1
+
+/**
+ * Structure to pass performance counter data of a Mali core
+ */
+struct _mali_profiling_core_counters {
+	u32 source0;
+	u32 value0;
+	u32 source1;
+	u32 value1;
+};
+
+/*
+ * For compatibility with utgard.
+ */
+struct _mali_profiling_l2_counter_values {
+	struct _mali_profiling_core_counters cores[MAX_NUM_L2_CACHE_CORES];
+};
+
+struct _mali_profiling_mali_version {
+	u32 mali_product_id;
+	u32 mali_version_major;
+	u32 mali_version_minor;
+	u32 num_of_l2_cores;
+	u32 num_of_fp_cores;
+	u32 num_of_vp_cores;
+};
+
+extern void _mali_profiling_get_mali_version(struct _mali_profiling_mali_version *values);
+extern u32 _mali_profiling_get_l2_counters(struct _mali_profiling_l2_counter_values *values);
+
+/*
+ * List of possible actions allowing DDK to be controlled by Streamline.
+ * The following numbers are used by DDK to control the frame buffer dumping.
+ */
+#define FBDUMP_CONTROL_ENABLE (1)
+#define FBDUMP_CONTROL_RATE (2)
+#define SW_COUNTER_ENABLE      (3)
+#define FBDUMP_CONTROL_RESIZE_FACTOR (4)
+
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __MALI_MJOLLNIR_PROFILING_GATOR_API_H__ */
diff --git a/drivers/gator/mali/mali_utgard_profiling_gator_api.h b/drivers/gator/mali/mali_utgard_profiling_gator_api.h
new file mode 100644
index 00000000000..f550490c2c3
--- /dev/null
+++ b/drivers/gator/mali/mali_utgard_profiling_gator_api.h
@@ -0,0 +1,197 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __MALI_UTGARD_PROFILING_GATOR_API_H__
+#define __MALI_UTGARD_PROFILING_GATOR_API_H__
+
+#ifdef __cplusplus
+extern "C"
+{
+#endif
+
+#define MALI_PROFILING_API_VERSION 4
+
+#define MAX_NUM_L2_CACHE_CORES 3
+#define MAX_NUM_FP_CORES 8
+#define MAX_NUM_VP_CORES 1
+
+/** The list of events supported by the Mali DDK. */
+enum {
+	/* Vertex processor activity */
+	ACTIVITY_VP_0 = 0,
+
+	/* Fragment processor activity */
+	ACTIVITY_FP_0, /* 1 */
+	ACTIVITY_FP_1,
+	ACTIVITY_FP_2,
+	ACTIVITY_FP_3,
+	ACTIVITY_FP_4,
+	ACTIVITY_FP_5,
+	ACTIVITY_FP_6,
+	ACTIVITY_FP_7,
+
+	/* L2 cache counters */
+	COUNTER_L2_0_C0,
+	COUNTER_L2_0_C1,
+	COUNTER_L2_1_C0,
+	COUNTER_L2_1_C1,
+	COUNTER_L2_2_C0,
+	COUNTER_L2_2_C1,
+
+	/* Vertex processor counters */
+	COUNTER_VP_0_C0, /*15*/
+	COUNTER_VP_0_C1,
+
+	/* Fragment processor counters */
+	COUNTER_FP_0_C0,
+	COUNTER_FP_0_C1,
+	COUNTER_FP_1_C0,
+	COUNTER_FP_1_C1,
+	COUNTER_FP_2_C0,
+	COUNTER_FP_2_C1,
+	COUNTER_FP_3_C0,
+	COUNTER_FP_3_C1,
+	COUNTER_FP_4_C0,
+	COUNTER_FP_4_C1,
+	COUNTER_FP_5_C0,
+	COUNTER_FP_5_C1,
+	COUNTER_FP_6_C0,
+	COUNTER_FP_6_C1,
+	COUNTER_FP_7_C0,
+	COUNTER_FP_7_C1, /* 32 */
+
+	/*
+	 * If more hardware counters are added, the _mali_osk_hw_counter_table
+	 * below should also be updated.
+	 */
+
+	/* EGL software counters */
+	COUNTER_EGL_BLIT_TIME,
+
+	/* GLES software counters */
+	COUNTER_GLES_DRAW_ELEMENTS_CALLS,
+	COUNTER_GLES_DRAW_ELEMENTS_NUM_INDICES,
+	COUNTER_GLES_DRAW_ELEMENTS_NUM_TRANSFORMED,
+	COUNTER_GLES_DRAW_ARRAYS_CALLS,
+	COUNTER_GLES_DRAW_ARRAYS_NUM_TRANSFORMED,
+	COUNTER_GLES_DRAW_POINTS,
+	COUNTER_GLES_DRAW_LINES,
+	COUNTER_GLES_DRAW_LINE_LOOP,
+	COUNTER_GLES_DRAW_LINE_STRIP,
+	COUNTER_GLES_DRAW_TRIANGLES,
+	COUNTER_GLES_DRAW_TRIANGLE_STRIP,
+	COUNTER_GLES_DRAW_TRIANGLE_FAN,
+	COUNTER_GLES_NON_VBO_DATA_COPY_TIME,
+	COUNTER_GLES_UNIFORM_BYTES_COPIED_TO_MALI,
+	COUNTER_GLES_UPLOAD_TEXTURE_TIME,
+	COUNTER_GLES_UPLOAD_VBO_TIME,
+	COUNTER_GLES_NUM_FLUSHES,
+	COUNTER_GLES_NUM_VSHADERS_GENERATED,
+	COUNTER_GLES_NUM_FSHADERS_GENERATED,
+	COUNTER_GLES_VSHADER_GEN_TIME,
+	COUNTER_GLES_FSHADER_GEN_TIME,
+	COUNTER_GLES_INPUT_TRIANGLES,
+	COUNTER_GLES_VXCACHE_HIT,
+	COUNTER_GLES_VXCACHE_MISS,
+	COUNTER_GLES_VXCACHE_COLLISION,
+	COUNTER_GLES_CULLED_TRIANGLES,
+	COUNTER_GLES_CULLED_LINES,
+	COUNTER_GLES_BACKFACE_TRIANGLES,
+	COUNTER_GLES_GBCLIP_TRIANGLES,
+	COUNTER_GLES_GBCLIP_LINES,
+	COUNTER_GLES_TRIANGLES_DRAWN,
+	COUNTER_GLES_DRAWCALL_TIME,
+	COUNTER_GLES_TRIANGLES_COUNT,
+	COUNTER_GLES_INDEPENDENT_TRIANGLES_COUNT,
+	COUNTER_GLES_STRIP_TRIANGLES_COUNT,
+	COUNTER_GLES_FAN_TRIANGLES_COUNT,
+	COUNTER_GLES_LINES_COUNT,
+	COUNTER_GLES_INDEPENDENT_LINES_COUNT,
+	COUNTER_GLES_STRIP_LINES_COUNT,
+	COUNTER_GLES_LOOP_LINES_COUNT,
+
+	/* Framebuffer capture pseudo-counter */
+	COUNTER_FILMSTRIP,
+
+	NUMBER_OF_EVENTS
+} _mali_osk_counter_id;
+
+#define FIRST_ACTIVITY_EVENT    ACTIVITY_VP_0
+#define LAST_ACTIVITY_EVENT     ACTIVITY_FP_7
+
+#define FIRST_HW_COUNTER        COUNTER_L2_0_C0
+#define LAST_HW_COUNTER         COUNTER_FP_7_C1
+
+#define FIRST_SW_COUNTER        COUNTER_EGL_BLIT_TIME
+#define LAST_SW_COUNTER         COUNTER_GLES_LOOP_LINES_COUNT
+
+#define FIRST_SPECIAL_COUNTER   COUNTER_FILMSTRIP
+#define LAST_SPECIAL_COUNTER    COUNTER_FILMSTRIP
+
+/**
+ * Structure to pass performance counter data of a Mali core
+ */
+struct _mali_profiling_core_counters {
+	u32 source0;
+	u32 value0;
+	u32 source1;
+	u32 value1;
+};
+
+/**
+ * Structure to pass performance counter data of Mali L2 cache cores
+ */
+struct _mali_profiling_l2_counter_values {
+	struct _mali_profiling_core_counters cores[MAX_NUM_L2_CACHE_CORES];
+};
+
+/**
+ * Structure to pass data defining Mali instance in use:
+ *
+ * mali_product_id - Mali product id
+ * mali_version_major - Mali version major number
+ * mali_version_minor - Mali version minor number
+ * num_of_l2_cores - number of L2 cache cores
+ * num_of_fp_cores - number of fragment processor cores
+ * num_of_vp_cores - number of vertex processor cores
+ */
+struct _mali_profiling_mali_version {
+	u32 mali_product_id;
+	u32 mali_version_major;
+	u32 mali_version_minor;
+	u32 num_of_l2_cores;
+	u32 num_of_fp_cores;
+	u32 num_of_vp_cores;
+};
+
+/*
+ * List of possible actions to be controlled by Streamline.
+ * The following numbers are used by gator to control the frame buffer dumping and s/w counter reporting.
+ * We cannot use the enums in mali_uk_types.h because they are unknown inside gator.
+ */
+#define FBDUMP_CONTROL_ENABLE (1)
+#define FBDUMP_CONTROL_RATE (2)
+#define SW_COUNTER_ENABLE (3)
+#define FBDUMP_CONTROL_RESIZE_FACTOR (4)
+
+void _mali_profiling_control(u32 action, u32 value);
+
+u32 _mali_profiling_get_l2_counters(struct _mali_profiling_l2_counter_values *values);
+
+int _mali_profiling_set_event(u32 counter_id, s32 event_id);
+
+u32 _mali_profiling_get_api_version(void);
+
+void _mali_profiling_get_mali_version(struct _mali_profiling_mali_version *values);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __MALI_UTGARD_PROFILING_GATOR_API_H__ */
diff --git a/drivers/gator/mali_midgard.mk b/drivers/gator/mali_midgard.mk
new file mode 100644
index 00000000000..bd0ac77d3b1
--- /dev/null
+++ b/drivers/gator/mali_midgard.mk
@@ -0,0 +1,41 @@
+# Defines for Mali-Midgard driver
+EXTRA_CFLAGS += -DMALI_USE_UMP=1 \
+                -DMALI_LICENSE_IS_GPL=1 \
+                -DMALI_BASE_TRACK_MEMLEAK=0 \
+                -DMALI_DEBUG=0 \
+                -DMALI_ERROR_INJECT_ON=0 \
+                -DMALI_CUSTOMER_RELEASE=1 \
+                -DMALI_UNIT_TEST=0 \
+                -DMALI_BACKEND_KERNEL=1 \
+                -DMALI_NO_MALI=0
+
+DDK_DIR ?= .
+ifneq ($(wildcard $(DDK_DIR)/drivers/gpu/arm/t6xx),)
+KBASE_DIR = $(DDK_DIR)/drivers/gpu/arm/t6xx/kbase
+OSK_DIR = $(DDK_DIR)/drivers/gpu/arm/t6xx/kbase/osk
+endif
+
+ifneq ($(wildcard $(DDK_DIR)/drivers/gpu/arm/midgard),)
+KBASE_DIR = $(DDK_DIR)/drivers/gpu/arm/midgard
+OSK_DIR = $(DDK_DIR)/drivers/gpu/arm/midgard/osk
+EXTRA_CFLAGS += -DMALI_DIR_MIDGARD=1
+endif
+
+ifneq ($(wildcard $(DDK_DIR)/drivers/gpu/arm/midgard/mali_kbase_gator_api.h),)
+EXTRA_CFLAGS += -DMALI_SIMPLE_API=1
+EXTRA_CFLAGS += -I$(DDK_DIR)/drivers/gpu/arm/midgard
+endif
+
+UMP_DIR = $(DDK_DIR)/include/linux
+
+# Include directories in the DDK
+EXTRA_CFLAGS += -I$(KBASE_DIR)/ \
+                -I$(KBASE_DIR)/.. \
+                -I$(OSK_DIR)/.. \
+                -I$(UMP_DIR)/.. \
+                -I$(DDK_DIR)/include \
+                -I$(KBASE_DIR)/osk/src/linux/include \
+                -I$(KBASE_DIR)/platform_dummy \
+                -I$(KBASE_DIR)/src \
+                -Idrivers/staging/android \
+
diff --git a/drivers/gpio/gpio-crystalcove.c b/drivers/gpio/gpio-crystalcove.c
index bbfe7f50850..2a8791cc138 100644
--- a/drivers/gpio/gpio-crystalcove.c
+++ b/drivers/gpio/gpio-crystalcove.c
@@ -250,6 +250,7 @@ static struct irq_chip crystalcove_irqchip = {
 	.irq_set_type		= crystalcove_irq_type,
 	.irq_bus_lock		= crystalcove_bus_lock,
 	.irq_bus_sync_unlock	= crystalcove_bus_sync_unlock,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
 static irqreturn_t crystalcove_gpio_irq_handler(int irq, void *data)
@@ -272,7 +273,7 @@ static irqreturn_t crystalcove_gpio_irq_handler(int irq, void *data)
 	for (gpio = 0; gpio < CRYSTALCOVE_GPIO_NUM; gpio++) {
 		if (pending & BIT(gpio)) {
 			virq = irq_find_mapping(cg->chip.irqdomain, gpio);
-			generic_handle_irq(virq);
+			handle_nested_irq(virq);
 		}
 	}
 
diff --git a/drivers/gpio/gpio-kempld.c b/drivers/gpio/gpio-kempld.c
index fd150adeebf..86a60079d31 100644
--- a/drivers/gpio/gpio-kempld.c
+++ b/drivers/gpio/gpio-kempld.c
@@ -117,7 +117,7 @@ static int kempld_gpio_get_direction(struct gpio_chip *chip, unsigned offset)
 		= container_of(chip, struct kempld_gpio_data, chip);
 	struct kempld_device_data *pld = gpio->pld;
 
-	return kempld_gpio_get_bit(pld, KEMPLD_GPIO_DIR_NUM(offset), offset);
+	return !kempld_gpio_get_bit(pld, KEMPLD_GPIO_DIR_NUM(offset), offset);
 }
 
 static int kempld_gpio_pincount(struct kempld_device_data *pld)
diff --git a/drivers/gpio/gpio-mcp23s08.c b/drivers/gpio/gpio-mcp23s08.c
index 8488e2fd307..36bc42942e8 100644
--- a/drivers/gpio/gpio-mcp23s08.c
+++ b/drivers/gpio/gpio-mcp23s08.c
@@ -785,9 +785,11 @@ static int mcp230xx_probe(struct i2c_client *client,
 		client->irq = irq_of_parse_and_map(client->dev.of_node, 0);
 	} else {
 		pdata = dev_get_platdata(&client->dev);
-		if (!pdata || !gpio_is_valid(pdata->base)) {
-			dev_dbg(&client->dev, "invalid platform data\n");
-			return -EINVAL;
+		if (!pdata) {
+			pdata = devm_kzalloc(&client->dev,
+					sizeof(struct mcp23s08_platform_data),
+					GFP_KERNEL);
+			pdata->base = -1;
 		}
 	}
 
@@ -908,10 +910,11 @@ static int mcp23s08_probe(struct spi_device *spi)
 	} else {
 		type = spi_get_device_id(spi)->driver_data;
 		pdata = dev_get_platdata(&spi->dev);
-		if (!pdata || !gpio_is_valid(pdata->base)) {
-			dev_dbg(&spi->dev,
-					"invalid or missing platform data\n");
-			return -EINVAL;
+		if (!pdata) {
+			pdata = devm_kzalloc(&spi->dev,
+					sizeof(struct mcp23s08_platform_data),
+					GFP_KERNEL);
+			pdata->base = -1;
 		}
 
 		for (addr = 0; addr < ARRAY_SIZE(pdata->chip); addr++) {
diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c
index 418e3865036..a93ddbc1948 100644
--- a/drivers/gpio/gpio-mvebu.c
+++ b/drivers/gpio/gpio-mvebu.c
@@ -305,11 +305,13 @@ static void mvebu_gpio_edge_irq_mask(struct irq_data *d)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct mvebu_gpio_chip *mvchip = gc->private;
+	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	u32 mask = 1 << (d->irq - gc->irq_base);
 
 	irq_gc_lock(gc);
-	gc->mask_cache &= ~mask;
-	writel_relaxed(gc->mask_cache, mvebu_gpioreg_edge_mask(mvchip));
+	ct->mask_cache_priv &= ~mask;
+
+	writel_relaxed(ct->mask_cache_priv, mvebu_gpioreg_edge_mask(mvchip));
 	irq_gc_unlock(gc);
 }
 
@@ -317,11 +319,13 @@ static void mvebu_gpio_edge_irq_unmask(struct irq_data *d)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct mvebu_gpio_chip *mvchip = gc->private;
+	struct irq_chip_type *ct = irq_data_get_chip_type(d);
+
 	u32 mask = 1 << (d->irq - gc->irq_base);
 
 	irq_gc_lock(gc);
-	gc->mask_cache |= mask;
-	writel_relaxed(gc->mask_cache, mvebu_gpioreg_edge_mask(mvchip));
+	ct->mask_cache_priv |= mask;
+	writel_relaxed(ct->mask_cache_priv, mvebu_gpioreg_edge_mask(mvchip));
 	irq_gc_unlock(gc);
 }
 
@@ -329,11 +333,13 @@ static void mvebu_gpio_level_irq_mask(struct irq_data *d)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct mvebu_gpio_chip *mvchip = gc->private;
+	struct irq_chip_type *ct = irq_data_get_chip_type(d);
+
 	u32 mask = 1 << (d->irq - gc->irq_base);
 
 	irq_gc_lock(gc);
-	gc->mask_cache &= ~mask;
-	writel_relaxed(gc->mask_cache, mvebu_gpioreg_level_mask(mvchip));
+	ct->mask_cache_priv &= ~mask;
+	writel_relaxed(ct->mask_cache_priv, mvebu_gpioreg_level_mask(mvchip));
 	irq_gc_unlock(gc);
 }
 
@@ -341,11 +347,13 @@ static void mvebu_gpio_level_irq_unmask(struct irq_data *d)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct mvebu_gpio_chip *mvchip = gc->private;
+	struct irq_chip_type *ct = irq_data_get_chip_type(d);
+
 	u32 mask = 1 << (d->irq - gc->irq_base);
 
 	irq_gc_lock(gc);
-	gc->mask_cache |= mask;
-	writel_relaxed(gc->mask_cache, mvebu_gpioreg_level_mask(mvchip));
+	ct->mask_cache_priv |= mask;
+	writel_relaxed(ct->mask_cache_priv, mvebu_gpioreg_level_mask(mvchip));
 	irq_gc_unlock(gc);
 }
 
diff --git a/drivers/gpio/gpio-tps65912.c b/drivers/gpio/gpio-tps65912.c
index 22052d84c63..a8c783099af 100644
--- a/drivers/gpio/gpio-tps65912.c
+++ b/drivers/gpio/gpio-tps65912.c
@@ -26,9 +26,12 @@ struct tps65912_gpio_data {
 	struct gpio_chip gpio_chip;
 };
 
+#define to_tgd(gc) container_of(gc, struct tps65912_gpio_data, gpio_chip)
+
 static int tps65912_gpio_get(struct gpio_chip *gc, unsigned offset)
 {
-	struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio);
+	struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc);
+	struct tps65912 *tps65912 = tps65912_gpio->tps65912;
 	int val;
 
 	val = tps65912_reg_read(tps65912, TPS65912_GPIO1 + offset);
@@ -42,7 +45,8 @@ static int tps65912_gpio_get(struct gpio_chip *gc, unsigned offset)
 static void tps65912_gpio_set(struct gpio_chip *gc, unsigned offset,
 			      int value)
 {
-	struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio);
+	struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc);
+	struct tps65912 *tps65912 = tps65912_gpio->tps65912;
 
 	if (value)
 		tps65912_set_bits(tps65912, TPS65912_GPIO1 + offset,
@@ -55,7 +59,8 @@ static void tps65912_gpio_set(struct gpio_chip *gc, unsigned offset,
 static int tps65912_gpio_output(struct gpio_chip *gc, unsigned offset,
 				int value)
 {
-	struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio);
+	struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc);
+	struct tps65912 *tps65912 = tps65912_gpio->tps65912;
 
 	/* Set the initial value */
 	tps65912_gpio_set(gc, offset, value);
@@ -66,7 +71,8 @@ static int tps65912_gpio_output(struct gpio_chip *gc, unsigned offset,
 
 static int tps65912_gpio_input(struct gpio_chip *gc, unsigned offset)
 {
-	struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio);
+	struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc);
+	struct tps65912 *tps65912 = tps65912_gpio->tps65912;
 
 	return tps65912_clear_bits(tps65912, TPS65912_GPIO1 + offset,
 								GPIO_CFG_MASK);
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 604dbe60bde..26645a847bb 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -45,8 +45,15 @@ static int of_gpiochip_find_and_xlate(struct gpio_chip *gc, void *data)
 		return false;
 
 	ret = gc->of_xlate(gc, &gg_data->gpiospec, gg_data->flags);
-	if (ret < 0)
+	if (ret < 0) {
+		/* We've found a gpio chip, but the translation failed.
+		 * Store translation error in out_gpio.
+		 * Return false to keep looking, as more than one gpio chip
+		 * could be registered per of-node.
+		 */
+		gg_data->out_gpio = ERR_PTR(ret);
 		return false;
+	 }
 
 	gg_data->out_gpio = gpiochip_get_desc(gc, ret);
 	return true;
diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c
index 5f2150b619a..d9fa798560b 100644
--- a/drivers/gpio/gpiolib-sysfs.c
+++ b/drivers/gpio/gpiolib-sysfs.c
@@ -128,7 +128,7 @@ static ssize_t gpio_value_store(struct device *dev,
 	return status;
 }
 
-static const DEVICE_ATTR(value, 0644,
+static DEVICE_ATTR(value, 0644,
 		gpio_value_show, gpio_value_store);
 
 static irqreturn_t gpio_sysfs_irq(int irq, void *priv)
@@ -353,18 +353,15 @@ static ssize_t gpio_active_low_store(struct device *dev,
 	return status ? : size;
 }
 
-static const DEVICE_ATTR(active_low, 0644,
+static DEVICE_ATTR(active_low, 0644,
 		gpio_active_low_show, gpio_active_low_store);
 
-static const struct attribute *gpio_attrs[] = {
+static struct attribute *gpio_attrs[] = {
 	&dev_attr_value.attr,
 	&dev_attr_active_low.attr,
 	NULL,
 };
-
-static const struct attribute_group gpio_attr_group = {
-	.attrs = (struct attribute **) gpio_attrs,
-};
+ATTRIBUTE_GROUPS(gpio);
 
 /*
  * /sys/class/gpio/gpiochipN/
@@ -400,16 +397,13 @@ static ssize_t chip_ngpio_show(struct device *dev,
 }
 static DEVICE_ATTR(ngpio, 0444, chip_ngpio_show, NULL);
 
-static const struct attribute *gpiochip_attrs[] = {
+static struct attribute *gpiochip_attrs[] = {
 	&dev_attr_base.attr,
 	&dev_attr_label.attr,
 	&dev_attr_ngpio.attr,
 	NULL,
 };
-
-static const struct attribute_group gpiochip_attr_group = {
-	.attrs = (struct attribute **) gpiochip_attrs,
-};
+ATTRIBUTE_GROUPS(gpiochip);
 
 /*
  * /sys/class/gpio/export ... write-only
@@ -525,6 +519,7 @@ static struct class gpio_class = {
  */
 int gpiod_export(struct gpio_desc *desc, bool direction_may_change)
 {
+	struct gpio_chip	*chip;
 	unsigned long		flags;
 	int			status;
 	const char		*ioname = NULL;
@@ -542,8 +537,16 @@ int gpiod_export(struct gpio_desc *desc, bool direction_may_change)
 		return -EINVAL;
 	}
 
+	chip = desc->chip;
+
 	mutex_lock(&sysfs_lock);
 
+	/* check if chip is being removed */
+	if (!chip || !chip->exported) {
+		status = -ENODEV;
+		goto fail_unlock;
+	}
+
 	spin_lock_irqsave(&gpio_lock, flags);
 	if (!test_bit(FLAG_REQUESTED, &desc->flags) ||
 	     test_bit(FLAG_EXPORT, &desc->flags)) {
@@ -564,18 +567,15 @@ int gpiod_export(struct gpio_desc *desc, bool direction_may_change)
 	if (desc->chip->names && desc->chip->names[offset])
 		ioname = desc->chip->names[offset];
 
-	dev = device_create(&gpio_class, desc->chip->dev, MKDEV(0, 0),
-			    desc, ioname ? ioname : "gpio%u",
-			    desc_to_gpio(desc));
+	dev = device_create_with_groups(&gpio_class, desc->chip->dev,
+					MKDEV(0, 0), desc, gpio_groups,
+					ioname ? ioname : "gpio%u",
+					desc_to_gpio(desc));
 	if (IS_ERR(dev)) {
 		status = PTR_ERR(dev);
 		goto fail_unlock;
 	}
 
-	status = sysfs_create_group(&dev->kobj, &gpio_attr_group);
-	if (status)
-		goto fail_unregister_device;
-
 	if (direction_may_change) {
 		status = device_create_file(dev, &dev_attr_direction);
 		if (status)
@@ -586,13 +586,15 @@ int gpiod_export(struct gpio_desc *desc, bool direction_may_change)
 				       !test_bit(FLAG_IS_OUT, &desc->flags))) {
 		status = device_create_file(dev, &dev_attr_edge);
 		if (status)
-			goto fail_unregister_device;
+			goto fail_remove_attr_direction;
 	}
 
 	set_bit(FLAG_EXPORT, &desc->flags);
 	mutex_unlock(&sysfs_lock);
 	return 0;
 
+fail_remove_attr_direction:
+	device_remove_file(dev, &dev_attr_direction);
 fail_unregister_device:
 	device_unregister(dev);
 fail_unlock:
@@ -637,6 +639,7 @@ int gpiod_export_link(struct device *dev, const char *name,
 		if (tdev != NULL) {
 			status = sysfs_create_link(&dev->kobj, &tdev->kobj,
 						name);
+			put_device(tdev);
 		} else {
 			status = -ENODEV;
 		}
@@ -684,7 +687,7 @@ int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value)
 	}
 
 	status = sysfs_set_active_low(desc, dev, value);
-
+	put_device(dev);
 unlock:
 	mutex_unlock(&sysfs_lock);
 
@@ -726,6 +729,8 @@ void gpiod_unexport(struct gpio_desc *desc)
 	mutex_unlock(&sysfs_lock);
 
 	if (dev) {
+		device_remove_file(dev, &dev_attr_edge);
+		device_remove_file(dev, &dev_attr_direction);
 		device_unregister(dev);
 		put_device(dev);
 	}
@@ -750,13 +755,13 @@ int gpiochip_export(struct gpio_chip *chip)
 
 	/* use chip->base for the ID; it's already known to be unique */
 	mutex_lock(&sysfs_lock);
-	dev = device_create(&gpio_class, chip->dev, MKDEV(0, 0), chip,
-				"gpiochip%d", chip->base);
-	if (!IS_ERR(dev)) {
-		status = sysfs_create_group(&dev->kobj,
-				&gpiochip_attr_group);
-	} else
+	dev = device_create_with_groups(&gpio_class, chip->dev, MKDEV(0, 0),
+					chip, gpiochip_groups,
+					"gpiochip%d", chip->base);
+	if (IS_ERR(dev))
 		status = PTR_ERR(dev);
+	else
+		status = 0;
 	chip->exported = (status == 0);
 	mutex_unlock(&sysfs_lock);
 
@@ -770,12 +775,15 @@ void gpiochip_unexport(struct gpio_chip *chip)
 {
 	int			status;
 	struct device		*dev;
+	struct gpio_desc *desc;
+	unsigned int i;
 
 	mutex_lock(&sysfs_lock);
 	dev = class_find_device(&gpio_class, NULL, chip, match_export);
 	if (dev) {
 		put_device(dev);
 		device_unregister(dev);
+		/* prevent further gpiod exports */
 		chip->exported = false;
 		status = 0;
 	} else
@@ -784,6 +792,13 @@ void gpiochip_unexport(struct gpio_chip *chip)
 
 	if (status)
 		chip_dbg(chip, "%s: status %d\n", __func__, status);
+
+	/* unregister gpiod class devices owned by sysfs */
+	for (i = 0; i < chip->ngpio; i++) {
+		desc = &chip->desc[i];
+		if (test_and_clear_bit(FLAG_SYSFS, &desc->flags))
+			gpiod_free(desc);
+	}
 }
 
 static int __init gpiolib_sysfs_init(void)
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index e8e98ca25ec..c81bda0ec2c 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -268,6 +268,9 @@ int gpiochip_add(struct gpio_chip *chip)
 
 	spin_unlock_irqrestore(&gpio_lock, flags);
 
+	if (status)
+		goto fail;
+
 #ifdef CONFIG_PINCTRL
 	INIT_LIST_HEAD(&chip->pin_ranges);
 #endif
@@ -275,12 +278,12 @@ int gpiochip_add(struct gpio_chip *chip)
 	of_gpiochip_add(chip);
 	acpi_gpiochip_add(chip);
 
-	if (status)
-		goto fail;
-
 	status = gpiochip_export(chip);
-	if (status)
+	if (status) {
+		acpi_gpiochip_remove(chip);
+		of_gpiochip_remove(chip);
 		goto fail;
+	}
 
 	pr_debug("%s: registered GPIOs %d to %d on device: %s\n", __func__,
 		chip->base, chip->base + chip->ngpio - 1,
@@ -313,14 +316,13 @@ void gpiochip_remove(struct gpio_chip *chip)
 	unsigned long	flags;
 	unsigned	id;
 
-	acpi_gpiochip_remove(chip);
-
-	spin_lock_irqsave(&gpio_lock, flags);
-
 	gpiochip_irqchip_remove(chip);
+
+	acpi_gpiochip_remove(chip);
 	gpiochip_remove_pin_ranges(chip);
 	of_gpiochip_remove(chip);
 
+	spin_lock_irqsave(&gpio_lock, flags);
 	for (id = 0; id < chip->ngpio; id++) {
 		if (test_bit(FLAG_REQUESTED, &chip->desc[id].flags))
 			dev_crit(chip->dev, "REMOVING GPIOCHIP WITH GPIOS STILL REQUESTED\n");
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index e79c8d3700d..0cd6e0d7dd1 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -42,9 +42,10 @@
 #include "drm_crtc_internal.h"
 #include "drm_internal.h"
 
-static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev,
-							struct drm_mode_fb_cmd2 *r,
-							struct drm_file *file_priv);
+static struct drm_framebuffer *
+internal_framebuffer_create(struct drm_device *dev,
+			    struct drm_mode_fb_cmd2 *r,
+			    struct drm_file *file_priv);
 
 /* Avoid boilerplate.  I'm tired of typing. */
 #define DRM_ENUM_NAME_FN(fnname, list)				\
@@ -530,17 +531,6 @@ void drm_framebuffer_reference(struct drm_framebuffer *fb)
 }
 EXPORT_SYMBOL(drm_framebuffer_reference);
 
-static void drm_framebuffer_free_bug(struct kref *kref)
-{
-	BUG();
-}
-
-static void __drm_framebuffer_unreference(struct drm_framebuffer *fb)
-{
-	DRM_DEBUG("%p: FB ID: %d (%d)\n", fb, fb->base.id, atomic_read(&fb->refcount.refcount));
-	kref_put(&fb->refcount, drm_framebuffer_free_bug);
-}
-
 /**
  * drm_framebuffer_unregister_private - unregister a private fb from the lookup idr
  * @fb: fb to unregister
@@ -1296,7 +1286,7 @@ void drm_plane_force_disable(struct drm_plane *plane)
 		return;
 	}
 	/* disconnect the plane from the fb and crtc: */
-	__drm_framebuffer_unreference(plane->old_fb);
+	drm_framebuffer_unreference(plane->old_fb);
 	plane->old_fb = NULL;
 	plane->fb = NULL;
 	plane->crtc = NULL;
@@ -2565,8 +2555,11 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EINVAL;
 
-	/* For some reason crtc x/y offsets are signed internally. */
-	if (crtc_req->x > INT_MAX || crtc_req->y > INT_MAX)
+	/*
+	 * Universal plane src offsets are only 16.16, prevent havoc for
+	 * drivers using universal plane code internally.
+	 */
+	if (crtc_req->x & 0xffff0000 || crtc_req->y & 0xffff0000)
 		return -ERANGE;
 
 	drm_modeset_lock_all(dev);
@@ -2739,13 +2732,11 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc,
 	 */
 	if (req->flags & DRM_MODE_CURSOR_BO) {
 		if (req->handle) {
-			fb = add_framebuffer_internal(dev, &fbreq, file_priv);
+			fb = internal_framebuffer_create(dev, &fbreq, file_priv);
 			if (IS_ERR(fb)) {
 				DRM_DEBUG_KMS("failed to wrap cursor buffer in drm framebuffer\n");
 				return PTR_ERR(fb);
 			}
-
-			drm_framebuffer_reference(fb);
 		} else {
 			fb = NULL;
 		}
@@ -3114,9 +3105,10 @@ static int framebuffer_check(const struct drm_mode_fb_cmd2 *r)
 	return 0;
 }
 
-static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev,
-							struct drm_mode_fb_cmd2 *r,
-							struct drm_file *file_priv)
+static struct drm_framebuffer *
+internal_framebuffer_create(struct drm_device *dev,
+			    struct drm_mode_fb_cmd2 *r,
+			    struct drm_file *file_priv)
 {
 	struct drm_mode_config *config = &dev->mode_config;
 	struct drm_framebuffer *fb;
@@ -3148,12 +3140,6 @@ static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev,
 		return fb;
 	}
 
-	mutex_lock(&file_priv->fbs_lock);
-	r->fb_id = fb->base.id;
-	list_add(&fb->filp_head, &file_priv->fbs);
-	DRM_DEBUG_KMS("[FB:%d]\n", fb->base.id);
-	mutex_unlock(&file_priv->fbs_lock);
-
 	return fb;
 }
 
@@ -3175,15 +3161,24 @@ static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev,
 int drm_mode_addfb2(struct drm_device *dev,
 		    void *data, struct drm_file *file_priv)
 {
+	struct drm_mode_fb_cmd2 *r = data;
 	struct drm_framebuffer *fb;
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EINVAL;
 
-	fb = add_framebuffer_internal(dev, data, file_priv);
+	fb = internal_framebuffer_create(dev, r, file_priv);
 	if (IS_ERR(fb))
 		return PTR_ERR(fb);
 
+	/* Transfer ownership to the filp for reaping on close */
+
+	DRM_DEBUG_KMS("[FB:%d]\n", fb->base.id);
+	mutex_lock(&file_priv->fbs_lock);
+	r->fb_id = fb->base.id;
+	list_add(&fb->filp_head, &file_priv->fbs);
+	mutex_unlock(&file_priv->fbs_lock);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 08e33b8b13a..9f59c9027eb 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -378,10 +378,11 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request,
 
 	/*
 	 * The specification doesn't give any recommendation on how often to
-	 * retry native transactions, so retry 7 times like for I2C-over-AUX
-	 * transactions.
+	 * retry native transactions. We used to retry 7 times like for
+	 * aux i2c transactions but real world devices this wasn't
+	 * sufficient, bump to 32 which makes Dell 4k monitors happier.
 	 */
-	for (retry = 0; retry < 7; retry++) {
+	for (retry = 0; retry < 32; retry++) {
 
 		mutex_lock(&aux->hw_mutex);
 		err = aux->transfer(aux, &msg);
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 070f913d2db..1f5e42a1f5b 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -839,6 +839,8 @@ static void drm_dp_put_mst_branch_device(struct drm_dp_mst_branch *mstb)
 
 static void drm_dp_port_teardown_pdt(struct drm_dp_mst_port *port, int old_pdt)
 {
+	struct drm_dp_mst_branch *mstb;
+
 	switch (old_pdt) {
 	case DP_PEER_DEVICE_DP_LEGACY_CONV:
 	case DP_PEER_DEVICE_SST_SINK:
@@ -846,8 +848,9 @@ static void drm_dp_port_teardown_pdt(struct drm_dp_mst_port *port, int old_pdt)
 		drm_dp_mst_unregister_i2c_bus(&port->aux);
 		break;
 	case DP_PEER_DEVICE_MST_BRANCHING:
-		drm_dp_put_mst_branch_device(port->mstb);
+		mstb = port->mstb;
 		port->mstb = NULL;
+		drm_dp_put_mst_branch_device(mstb);
 		break;
 	}
 }
@@ -1149,6 +1152,8 @@ static struct drm_dp_mst_branch *drm_dp_get_mst_branch_device(struct drm_dp_mst_
 	struct drm_dp_mst_port *port;
 	int i;
 	/* find the port by iterating down */
+
+	mutex_lock(&mgr->lock);
 	mstb = mgr->mst_primary;
 
 	for (i = 0; i < lct - 1; i++) {
@@ -1168,6 +1173,7 @@ static struct drm_dp_mst_branch *drm_dp_get_mst_branch_device(struct drm_dp_mst_
 		}
 	}
 	kref_get(&mstb->kref);
+	mutex_unlock(&mgr->lock);
 	return mstb;
 }
 
@@ -1175,7 +1181,7 @@ static void drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *m
 					       struct drm_dp_mst_branch *mstb)
 {
 	struct drm_dp_mst_port *port;
-
+	struct drm_dp_mst_branch *mstb_child;
 	if (!mstb->link_address_sent) {
 		drm_dp_send_link_address(mgr, mstb);
 		mstb->link_address_sent = true;
@@ -1190,17 +1196,31 @@ static void drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *m
 		if (!port->available_pbn)
 			drm_dp_send_enum_path_resources(mgr, mstb, port);
 
-		if (port->mstb)
-			drm_dp_check_and_send_link_address(mgr, port->mstb);
+		if (port->mstb) {
+			mstb_child = drm_dp_get_validated_mstb_ref(mgr, port->mstb);
+			if (mstb_child) {
+				drm_dp_check_and_send_link_address(mgr, mstb_child);
+				drm_dp_put_mst_branch_device(mstb_child);
+			}
+		}
 	}
 }
 
 static void drm_dp_mst_link_probe_work(struct work_struct *work)
 {
 	struct drm_dp_mst_topology_mgr *mgr = container_of(work, struct drm_dp_mst_topology_mgr, work);
+	struct drm_dp_mst_branch *mstb;
 
-	drm_dp_check_and_send_link_address(mgr, mgr->mst_primary);
-
+	mutex_lock(&mgr->lock);
+	mstb = mgr->mst_primary;
+	if (mstb) {
+		kref_get(&mstb->kref);
+	}
+	mutex_unlock(&mgr->lock);
+	if (mstb) {
+		drm_dp_check_and_send_link_address(mgr, mstb);
+		drm_dp_put_mst_branch_device(mstb);
+	}
 }
 
 static bool drm_dp_validate_guid(struct drm_dp_mst_topology_mgr *mgr,
diff --git a/drivers/gpu/drm/drm_edid_load.c b/drivers/gpu/drm/drm_edid_load.c
index 0a235fe61c9..144a0368ccd 100644
--- a/drivers/gpu/drm/drm_edid_load.c
+++ b/drivers/gpu/drm/drm_edid_load.c
@@ -288,6 +288,7 @@ int drm_load_edid_firmware(struct drm_connector *connector)
 
 	drm_mode_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
+	drm_edid_to_eld(connector, edid);
 	kfree(edid);
 
 	return ret;
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 0c0c39bac23..e9a2827ad1c 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -145,6 +145,31 @@ int drm_fb_helper_add_one_connector(struct drm_fb_helper *fb_helper, struct drm_
 }
 EXPORT_SYMBOL(drm_fb_helper_add_one_connector);
 
+static void remove_from_modeset(struct drm_mode_set *set,
+		struct drm_connector *connector)
+{
+	int i, j;
+
+	for (i = 0; i < set->num_connectors; i++) {
+		if (set->connectors[i] == connector)
+			break;
+	}
+
+	if (i == set->num_connectors)
+		return;
+
+	for (j = i + 1; j < set->num_connectors; j++) {
+		set->connectors[j - 1] = set->connectors[j];
+	}
+	set->num_connectors--;
+
+	/* because i915 is pissy about this..
+	 * TODO maybe need to makes sure we set it back to !=NULL somewhere?
+	 */
+	if (set->num_connectors == 0)
+		set->fb = NULL;
+}
+
 int drm_fb_helper_remove_one_connector(struct drm_fb_helper *fb_helper,
 				       struct drm_connector *connector)
 {
@@ -167,6 +192,11 @@ int drm_fb_helper_remove_one_connector(struct drm_fb_helper *fb_helper,
 	}
 	fb_helper->connector_count--;
 	kfree(fb_helper_connector);
+
+	/* also cleanup dangling references to the connector: */
+	for (i = 0; i < fb_helper->crtc_count; i++)
+		remove_from_modeset(&fb_helper->crtc_info[i].mode_set, connector);
+
 	return 0;
 }
 EXPORT_SYMBOL(drm_fb_helper_remove_one_connector);
@@ -347,9 +377,18 @@ bool drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper)
 {
 	struct drm_device *dev = fb_helper->dev;
 	bool ret;
+	bool do_delayed = false;
+
 	drm_modeset_lock_all(dev);
 	ret = restore_fbdev_mode(fb_helper);
+
+	do_delayed = fb_helper->delayed_hotplug;
+	if (do_delayed)
+		fb_helper->delayed_hotplug = false;
 	drm_modeset_unlock_all(dev);
+
+	if (do_delayed)
+		drm_fb_helper_hotplug_event(fb_helper);
 	return ret;
 }
 EXPORT_SYMBOL(drm_fb_helper_restore_fbdev_mode_unlocked);
@@ -888,10 +927,6 @@ int drm_fb_helper_set_par(struct fb_info *info)
 
 	drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper);
 
-	if (fb_helper->delayed_hotplug) {
-		fb_helper->delayed_hotplug = false;
-		drm_fb_helper_hotplug_event(fb_helper);
-	}
 	return 0;
 }
 EXPORT_SYMBOL(drm_fb_helper_set_par);
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 5ef03c216a2..7d64d22486e 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -131,12 +131,11 @@ static void drm_update_vblank_count(struct drm_device *dev, int crtc)
 
 	/* Reinitialize corresponding vblank timestamp if high-precision query
 	 * available. Skip this step if query unsupported or failed. Will
-	 * reinitialize delayed at next vblank interrupt in that case.
+	 * reinitialize delayed at next vblank interrupt in that case and
+	 * assign 0 for now, to mark the vblanktimestamp as invalid.
 	 */
-	if (rc) {
-		tslot = atomic_read(&vblank->count) + diff;
-		vblanktimestamp(dev, crtc, tslot) = t_vblank;
-	}
+	tslot = atomic_read(&vblank->count) + diff;
+	vblanktimestamp(dev, crtc, tslot) = rc ? t_vblank : (struct timeval) {0, 0};
 
 	smp_mb__before_atomic();
 	atomic_add(diff, &vblank->count);
@@ -1029,7 +1028,8 @@ void drm_vblank_put(struct drm_device *dev, int crtc)
 {
 	struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
 
-	BUG_ON(atomic_read(&vblank->refcount) == 0);
+	if (WARN_ON(atomic_read(&vblank->refcount) == 0))
+		return;
 
 	if (WARN_ON(crtc >= dev->num_crtcs))
 		return;
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index 6857e9ad633..5edc61f2f21 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -151,6 +151,7 @@ static int drm_helper_probe_single_connector_modes_merge_bits(struct drm_connect
 			struct edid *edid = (struct edid *) connector->edid_blob_ptr->data;
 
 			count = drm_add_edid_modes(connector, edid);
+			drm_edid_to_eld(connector, edid);
 		} else
 			count = (*connector_funcs->get_modes)(connector);
 	}
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 2318b4c7a8f..b51f0275883 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -692,11 +692,12 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 			spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 		}
 
-		intel_dp_mst_resume(dev);
 		drm_modeset_lock_all(dev);
 		intel_modeset_setup_hw_state(dev, true);
 		drm_modeset_unlock_all(dev);
 
+		intel_dp_mst_resume(dev);
+
 		/*
 		 * ... but also need to make sure that hotplug processing
 		 * doesn't cause havoc. Like in the driver load code we don't
@@ -1087,7 +1088,7 @@ static void vlv_save_gunit_s0ix_state(struct drm_i915_private *dev_priv)
 		s->lra_limits[i] = I915_READ(GEN7_LRA_LIMITS_BASE + i * 4);
 
 	s->media_max_req_count	= I915_READ(GEN7_MEDIA_MAX_REQ_COUNT);
-	s->gfx_max_req_count	= I915_READ(GEN7_MEDIA_MAX_REQ_COUNT);
+	s->gfx_max_req_count	= I915_READ(GEN7_GFX_MAX_REQ_COUNT);
 
 	s->render_hwsp		= I915_READ(RENDER_HWS_PGA_GEN7);
 	s->ecochk		= I915_READ(GAM_ECOCHK);
@@ -1140,6 +1141,7 @@ static void vlv_save_gunit_s0ix_state(struct drm_i915_private *dev_priv)
 	/* Gunit-Display CZ domain, 0x182028-0x1821CF */
 	s->gu_ctl0		= I915_READ(VLV_GU_CTL0);
 	s->gu_ctl1		= I915_READ(VLV_GU_CTL1);
+	s->pcbr			= I915_READ(VLV_PCBR);
 	s->clock_gate_dis2	= I915_READ(VLV_GUNIT_CLOCK_GATE2);
 
 	/*
@@ -1168,7 +1170,7 @@ static void vlv_restore_gunit_s0ix_state(struct drm_i915_private *dev_priv)
 		I915_WRITE(GEN7_LRA_LIMITS_BASE + i * 4, s->lra_limits[i]);
 
 	I915_WRITE(GEN7_MEDIA_MAX_REQ_COUNT, s->media_max_req_count);
-	I915_WRITE(GEN7_MEDIA_MAX_REQ_COUNT, s->gfx_max_req_count);
+	I915_WRITE(GEN7_GFX_MAX_REQ_COUNT, s->gfx_max_req_count);
 
 	I915_WRITE(RENDER_HWS_PGA_GEN7,	s->render_hwsp);
 	I915_WRITE(GAM_ECOCHK,		s->ecochk);
@@ -1234,6 +1236,7 @@ static void vlv_restore_gunit_s0ix_state(struct drm_i915_private *dev_priv)
 	/* Gunit-Display CZ domain, 0x182028-0x1821CF */
 	I915_WRITE(VLV_GU_CTL0,			s->gu_ctl0);
 	I915_WRITE(VLV_GU_CTL1,			s->gu_ctl1);
+	I915_WRITE(VLV_PCBR,			s->pcbr);
 	I915_WRITE(VLV_GUNIT_CLOCK_GATE2,	s->clock_gate_dis2);
 }
 
@@ -1242,19 +1245,7 @@ int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool force_on)
 	u32 val;
 	int err;
 
-	val = I915_READ(VLV_GTLC_SURVIVABILITY_REG);
-	WARN_ON(!!(val & VLV_GFX_CLK_FORCE_ON_BIT) == force_on);
-
 #define COND (I915_READ(VLV_GTLC_SURVIVABILITY_REG) & VLV_GFX_CLK_STATUS_BIT)
-	/* Wait for a previous force-off to settle */
-	if (force_on) {
-		err = wait_for(!COND, 20);
-		if (err) {
-			DRM_ERROR("timeout waiting for GFX clock force-off (%08x)\n",
-				  I915_READ(VLV_GTLC_SURVIVABILITY_REG));
-			return err;
-		}
-	}
 
 	val = I915_READ(VLV_GTLC_SURVIVABILITY_REG);
 	val &= ~VLV_GFX_CLK_FORCE_ON_BIT;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 16a6f6d187a..a84971351ee 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -877,6 +877,7 @@ struct i915_suspend_saved_registers {
 	u32 savePIPEB_LINK_N1;
 	u32 saveMCHBAR_RENDER_STANDBY;
 	u32 savePCH_PORT_HOTPLUG;
+	u16 saveGCDGMBUS;
 };
 
 struct vlv_s0ix_state {
@@ -937,6 +938,7 @@ struct vlv_s0ix_state {
 	/* Display 2 CZ domain */
 	u32 gu_ctl0;
 	u32 gu_ctl1;
+	u32 pcbr;
 	u32 clock_gate_dis2;
 };
 
@@ -1665,8 +1667,6 @@ struct drm_i915_private {
 	 */
 	struct workqueue_struct *dp_wq;
 
-	uint32_t bios_vgacntr;
-
 	/* Old dri1 support infrastructure, beware the dragons ya fools entering
 	 * here! */
 	struct i915_dri1_state dri1;
@@ -2077,8 +2077,8 @@ struct drm_i915_cmd_table {
 #define IS_HSW_EARLY_SDV(dev)	(IS_HASWELL(dev) && \
 				 (INTEL_DEVID(dev) & 0xFF00) == 0x0C00)
 #define IS_BDW_ULT(dev)		(IS_BROADWELL(dev) && \
-				 ((INTEL_DEVID(dev) & 0xf) == 0x2  || \
-				 (INTEL_DEVID(dev) & 0xf) == 0x6 || \
+				 ((INTEL_DEVID(dev) & 0xf) == 0x6 ||	\
+				 (INTEL_DEVID(dev) & 0xf) == 0xb ||	\
 				 (INTEL_DEVID(dev) & 0xf) == 0xe))
 #define IS_HSW_ULT(dev)		(IS_HASWELL(dev) && \
 				 (INTEL_DEVID(dev) & 0xFF00) == 0x0A00)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 28f91df2604..d88dbedeaa7 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3050,6 +3050,13 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg,
 		u32 size = i915_gem_obj_ggtt_size(obj);
 		uint64_t val;
 
+		/* Adjust fence size to match tiled area */
+		if (obj->tiling_mode != I915_TILING_NONE) {
+			uint32_t row_size = obj->stride *
+				(obj->tiling_mode == I915_TILING_Y ? 32 : 8);
+			size = (size / row_size) * row_size;
+		}
+
 		val = (uint64_t)((i915_gem_obj_ggtt_offset(obj) + size - 4096) &
 				 0xfffff000) << 32;
 		val |= i915_gem_obj_ggtt_offset(obj) & 0xfffff000;
@@ -4193,7 +4200,7 @@ i915_gem_pin_ioctl(struct drm_device *dev, void *data,
 	struct drm_i915_gem_object *obj;
 	int ret;
 
-	if (INTEL_INFO(dev)->gen >= 6)
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		return -ENODEV;
 
 	ret = i915_mutex_lock_interruptible(dev);
@@ -4249,6 +4256,9 @@ i915_gem_unpin_ioctl(struct drm_device *dev, void *data,
 	struct drm_i915_gem_object *obj;
 	int ret;
 
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return -ENODEV;
+
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
 		return ret;
@@ -4808,25 +4818,18 @@ i915_gem_init_hw(struct drm_device *dev)
 	for (i = 0; i < NUM_L3_SLICES(dev); i++)
 		i915_gem_l3_remap(&dev_priv->ring[RCS], i);
 
-	/*
-	 * XXX: Contexts should only be initialized once. Doing a switch to the
-	 * default context switch however is something we'd like to do after
-	 * reset or thaw (the latter may not actually be necessary for HW, but
-	 * goes with our code better). Context switching requires rings (for
-	 * the do_switch), but before enabling PPGTT. So don't move this.
-	 */
-	ret = i915_gem_context_enable(dev_priv);
+	ret = i915_ppgtt_init_hw(dev);
 	if (ret && ret != -EIO) {
-		DRM_ERROR("Context enable failed %d\n", ret);
+		DRM_ERROR("PPGTT enable failed %d\n", ret);
 		i915_gem_cleanup_ringbuffer(dev);
-
-		return ret;
 	}
 
-	ret = i915_ppgtt_init_hw(dev);
+	ret = i915_gem_context_enable(dev_priv);
 	if (ret && ret != -EIO) {
-		DRM_ERROR("PPGTT enable failed %d\n", ret);
+		DRM_ERROR("Context enable failed %d\n", ret);
 		i915_gem_cleanup_ringbuffer(dev);
+
+		return ret;
 	}
 
 	return ret;
@@ -5141,7 +5144,7 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
 	if (!mutex_is_locked(mutex))
 		return false;
 
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)
+#if defined(CONFIG_SMP) && !defined(CONFIG_DEBUG_MUTEXES)
 	return mutex->owner == task;
 #else
 	/* Since UP may be pre-empted, we cannot assume that we own the lock */
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index a5221d8f158..c12f087d7a1 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -468,7 +468,12 @@ mi_set_context(struct intel_engine_cs *ring,
 	       u32 hw_flags)
 {
 	u32 flags = hw_flags | MI_MM_SPACE_GTT;
-	int ret;
+	const int num_rings =
+		/* Use an extended w/a on ivb+ if signalling from other rings */
+		i915_semaphore_is_enabled(ring->dev) ?
+		hweight32(INTEL_INFO(ring->dev)->ring_mask) - 1 :
+		0;
+	int len, i, ret;
 
 	/* w/a: If Flush TLB Invalidation Mode is enabled, driver must do a TLB
 	 * invalidation prior to MI_SET_CONTEXT. On GEN6 we don't set the value
@@ -485,15 +490,31 @@ mi_set_context(struct intel_engine_cs *ring,
 	if (!IS_HASWELL(ring->dev) && INTEL_INFO(ring->dev)->gen < 8)
 		flags |= (MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN);
 
-	ret = intel_ring_begin(ring, 6);
+
+	len = 4;
+	if (INTEL_INFO(ring->dev)->gen >= 7)
+		len += 2 + (num_rings ? 4*num_rings + 2 : 0);
+
+	ret = intel_ring_begin(ring, len);
 	if (ret)
 		return ret;
 
 	/* WaProgramMiArbOnOffAroundMiSetContext:ivb,vlv,hsw,bdw,chv */
-	if (INTEL_INFO(ring->dev)->gen >= 7)
+	if (INTEL_INFO(ring->dev)->gen >= 7) {
 		intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_DISABLE);
-	else
-		intel_ring_emit(ring, MI_NOOP);
+		if (num_rings) {
+			struct intel_engine_cs *signaller;
+
+			intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(num_rings));
+			for_each_ring(signaller, to_i915(ring->dev), i) {
+				if (signaller == ring)
+					continue;
+
+				intel_ring_emit(ring, RING_PSMI_CTL(signaller->mmio_base));
+				intel_ring_emit(ring, _MASKED_BIT_ENABLE(GEN6_PSMI_SLEEP_MSG_DISABLE));
+			}
+		}
+	}
 
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_emit(ring, MI_SET_CONTEXT);
@@ -505,10 +526,21 @@ mi_set_context(struct intel_engine_cs *ring,
 	 */
 	intel_ring_emit(ring, MI_NOOP);
 
-	if (INTEL_INFO(ring->dev)->gen >= 7)
+	if (INTEL_INFO(ring->dev)->gen >= 7) {
+		if (num_rings) {
+			struct intel_engine_cs *signaller;
+
+			intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(num_rings));
+			for_each_ring(signaller, to_i915(ring->dev), i) {
+				if (signaller == ring)
+					continue;
+
+				intel_ring_emit(ring, RING_PSMI_CTL(signaller->mmio_base));
+				intel_ring_emit(ring, _MASKED_BIT_DISABLE(GEN6_PSMI_SLEEP_MSG_DISABLE));
+			}
+		}
 		intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
-	else
-		intel_ring_emit(ring, MI_NOOP);
+	}
 
 	intel_ring_advance(ring);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 85fda6b803e..360087eb83f 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -137,7 +137,11 @@ static unsigned long i915_stolen_to_physical(struct drm_device *dev)
 		r = devm_request_mem_region(dev->dev, base + 1,
 					    dev_priv->gtt.stolen_size - 1,
 					    "Graphics Stolen Memory");
-		if (r == NULL) {
+		/*
+		 * GEN3 firmware likes to smash pci bridges into the stolen
+		 * range. Apparently this works.
+		 */
+		if (r == NULL && !IS_GEN3(dev)) {
 			DRM_ERROR("conflict detected with stolen region: [0x%08x - 0x%08x]\n",
 				  base, base + (uint32_t)dev_priv->gtt.stolen_size);
 			base = 0;
@@ -481,10 +485,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 			stolen_offset, gtt_offset, size);
 
 	/* KISS and expect everything to be page-aligned */
-	BUG_ON(stolen_offset & 4095);
-	BUG_ON(size & 4095);
-
-	if (WARN_ON(size == 0))
+	if (WARN_ON(size == 0 || stolen_offset & 4095 || size & 4095))
 		return NULL;
 
 	stolen = kzalloc(sizeof(*stolen), GFP_KERNEL);
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 2b1eaa29ada..6765148ea5b 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -315,9 +315,10 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
+	mutex_lock(&dev->struct_mutex);
 	if (i915_gem_obj_is_pinned(obj) || obj->framebuffer_references) {
-		drm_gem_object_unreference_unlocked(&obj->base);
-		return -EBUSY;
+		ret = -EBUSY;
+		goto err;
 	}
 
 	if (args->tiling_mode == I915_TILING_NONE) {
@@ -349,7 +350,6 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		}
 	}
 
-	mutex_lock(&dev->struct_mutex);
 	if (args->tiling_mode != obj->tiling_mode ||
 	    args->stride != obj->stride) {
 		/* We need to rebind the object if its current allocation
@@ -395,6 +395,7 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		obj->bit_17 = NULL;
 	}
 
+err:
 	drm_gem_object_unreference(&obj->base);
 	mutex_unlock(&dev->struct_mutex);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index d182058383a..1719078c763 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -113,7 +113,10 @@ restart:
 			continue;
 
 		obj = mo->obj;
-		drm_gem_object_reference(&obj->base);
+
+		if (!kref_get_unless_zero(&obj->base.refcount))
+			continue;
+
 		spin_unlock(&mn->lock);
 
 		cancel_userptr(obj);
@@ -149,7 +152,20 @@ static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 			it = interval_tree_iter_first(&mn->objects, start, end);
 		if (it != NULL) {
 			obj = container_of(it, struct i915_mmu_object, it)->obj;
-			drm_gem_object_reference(&obj->base);
+
+			/* The mmu_object is released late when destroying the
+			 * GEM object so it is entirely possible to gain a
+			 * reference on an object in the process of being freed
+			 * since our serialisation is via the spinlock and not
+			 * the struct_mutex - and consequently use it after it
+			 * is freed and then double free it.
+			 */
+			if (!kref_get_unless_zero(&obj->base.refcount)) {
+				spin_unlock(&mn->lock);
+				serial = 0;
+				continue;
+			}
+
 			serial = mn->serial;
 		}
 		spin_unlock(&mn->lock);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index f66392b6e28..23329b48766 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2123,6 +2123,9 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 	u32 iir, gt_iir, pm_iir;
 	irqreturn_t ret = IRQ_NONE;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	while (true) {
 		/* Find, clear, then process each source of interrupt */
 
@@ -2167,6 +2170,9 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg)
 	u32 master_ctl, iir;
 	irqreturn_t ret = IRQ_NONE;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	for (;;) {
 		master_ctl = I915_READ(GEN8_MASTER_IRQ) & ~GEN8_MASTER_IRQ_CONTROL;
 		iir = I915_READ(VLV_IIR);
@@ -2455,6 +2461,9 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	u32 de_iir, gt_iir, de_ier, sde_ier = 0;
 	irqreturn_t ret = IRQ_NONE;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	/* We get interrupts on unclaimed registers, so check for this before we
 	 * do any I915_{READ,WRITE}. */
 	intel_uncore_check_errors(dev);
@@ -2525,6 +2534,9 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 	uint32_t tmp = 0;
 	enum pipe pipe;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	master_ctl = I915_READ(GEN8_MASTER_IRQ);
 	master_ctl &= ~GEN8_MASTER_IRQ_CONTROL;
 	if (!master_ctl)
@@ -3986,14 +3998,12 @@ static int i8xx_irq_postinstall(struct drm_device *dev)
 		~(I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
 		  I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
 		  I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT |
-		  I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT |
-		  I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT);
+		  I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT);
 	I915_WRITE16(IMR, dev_priv->irq_mask);
 
 	I915_WRITE16(IER,
 		     I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
 		     I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
-		     I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT |
 		     I915_USER_INTERRUPT);
 	POSTING_READ16(IER);
 
@@ -4022,8 +4032,6 @@ static bool i8xx_handle_vblank(struct drm_device *dev,
 	if ((iir & flip_pending) == 0)
 		goto check_page_flip;
 
-	intel_prepare_page_flip(dev, plane);
-
 	/* We detect FlipDone by looking for the change in PendingFlip from '1'
 	 * to '0' on the following vblank, i.e. IIR has the Pendingflip
 	 * asserted following the MI_DISPLAY_FLIP, but ISR is deasserted, hence
@@ -4033,6 +4041,7 @@ static bool i8xx_handle_vblank(struct drm_device *dev,
 	if (I915_READ16(ISR) & flip_pending)
 		goto check_page_flip;
 
+	intel_prepare_page_flip(dev, plane);
 	intel_finish_page_flip(dev, pipe);
 	return true;
 
@@ -4053,6 +4062,9 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 		I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT |
 		I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	iir = I915_READ16(IIR);
 	if (iir == 0)
 		return IRQ_NONE;
@@ -4159,14 +4171,12 @@ static int i915_irq_postinstall(struct drm_device *dev)
 		  I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
 		  I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
 		  I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT |
-		  I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT |
-		  I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT);
+		  I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT);
 
 	enable_mask =
 		I915_ASLE_INTERRUPT |
 		I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
 		I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
-		I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT |
 		I915_USER_INTERRUPT;
 
 	if (I915_HAS_HOTPLUG(dev)) {
@@ -4210,8 +4220,6 @@ static bool i915_handle_vblank(struct drm_device *dev,
 	if ((iir & flip_pending) == 0)
 		goto check_page_flip;
 
-	intel_prepare_page_flip(dev, plane);
-
 	/* We detect FlipDone by looking for the change in PendingFlip from '1'
 	 * to '0' on the following vblank, i.e. IIR has the Pendingflip
 	 * asserted following the MI_DISPLAY_FLIP, but ISR is deasserted, hence
@@ -4221,6 +4229,7 @@ static bool i915_handle_vblank(struct drm_device *dev,
 	if (I915_READ(ISR) & flip_pending)
 		goto check_page_flip;
 
+	intel_prepare_page_flip(dev, plane);
 	intel_finish_page_flip(dev, pipe);
 	return true;
 
@@ -4240,6 +4249,9 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 		I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT;
 	int pipe, ret = IRQ_NONE;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	iir = I915_READ(IIR);
 	do {
 		bool irq_received = (iir & ~flip_mask) != 0;
@@ -4468,6 +4480,9 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT |
 		I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	iir = I915_READ(IIR);
 
 	for (;;) {
@@ -4779,4 +4794,5 @@ void intel_runtime_pm_restore_interrupts(struct drm_device *dev)
 	dev_priv->pm._irqs_disabled = false;
 	dev->driver->irq_preinstall(dev);
 	dev->driver->irq_postinstall(dev);
+	synchronize_irq(dev_priv->dev->irq);
 }
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index c01e5f31430..9bf747f2a32 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -74,6 +74,7 @@
 #define   I915_GC_RENDER_CLOCK_166_MHZ	(0 << 0)
 #define   I915_GC_RENDER_CLOCK_200_MHZ	(1 << 0)
 #define   I915_GC_RENDER_CLOCK_333_MHZ	(4 << 0)
+#define GCDGMBUS 0xcc
 #define PCI_LBPC 0xf4 /* legacy/combination backlight modes, also called LBB */
 
 
@@ -370,6 +371,7 @@
 #define   PIPE_CONTROL_STORE_DATA_INDEX			(1<<21)
 #define   PIPE_CONTROL_CS_STALL				(1<<20)
 #define   PIPE_CONTROL_TLB_INVALIDATE			(1<<18)
+#define   PIPE_CONTROL_MEDIA_STATE_CLEAR		(1<<16)
 #define   PIPE_CONTROL_QW_WRITE				(1<<14)
 #define   PIPE_CONTROL_POST_SYNC_OP_MASK                (3<<14)
 #define   PIPE_CONTROL_DEPTH_STALL			(1<<13)
@@ -1071,6 +1073,7 @@ enum punit_power_well {
 #define GEN6_VERSYNC	(RING_SYNC_1(VEBOX_RING_BASE))
 #define GEN6_VEVSYNC	(RING_SYNC_2(VEBOX_RING_BASE))
 #define GEN6_NOSYNC 0
+#define RING_PSMI_CTL(base)	((base)+0x50)
 #define RING_MAX_IDLE(base)	((base)+0x54)
 #define RING_HWS_PGA(base)	((base)+0x80)
 #define RING_HWS_PGA_GEN6(base)	((base)+0x2080)
@@ -1401,6 +1404,7 @@ enum punit_power_well {
 #define   GEN6_BLITTER_FBC_NOTIFY			(1<<3)
 
 #define GEN6_RC_SLEEP_PSMI_CONTROL	0x2050
+#define   GEN6_PSMI_SLEEP_MSG_DISABLE	(1 << 0)
 #define   GEN8_RC_SEMA_IDLE_MSG_DISABLE	(1 << 12)
 #define   GEN8_FF_DOP_CLOCK_GATE_DISABLE	(1<<10)
 
@@ -1653,6 +1657,7 @@ enum punit_power_well {
 #define   GMBUS_CYCLE_INDEX	(2<<25)
 #define   GMBUS_CYCLE_STOP	(4<<25)
 #define   GMBUS_BYTE_COUNT_SHIFT 16
+#define   GMBUS_BYTE_COUNT_MAX   256U
 #define   GMBUS_SLAVE_INDEX_SHIFT 8
 #define   GMBUS_SLAVE_ADDR_SHIFT 1
 #define   GMBUS_SLAVE_READ	(1<<0)
@@ -5763,6 +5768,7 @@ enum punit_power_well {
 #define  HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE    (1 << 6)
 
 #define HALF_SLICE_CHICKEN3		0xe184
+#define   HSW_SAMPLE_C_PERFORMANCE	(1<<9)
 #define   GEN8_CENTROID_PIXEL_OPT_DIS	(1<<8)
 #define   GEN8_SAMPLER_POWER_BYPASS_DIS	(1<<1)
 
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index 043123c77a1..e22b0e825de 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -328,6 +328,10 @@ int i915_save_state(struct drm_device *dev)
 		}
 	}
 
+	if (IS_GEN4(dev))
+		pci_read_config_word(dev->pdev, GCDGMBUS,
+				     &dev_priv->regfile.saveGCDGMBUS);
+
 	/* Cache mode state */
 	if (INTEL_INFO(dev)->gen < 7)
 		dev_priv->regfile.saveCACHE_MODE_0 = I915_READ(CACHE_MODE_0);
@@ -356,6 +360,10 @@ int i915_restore_state(struct drm_device *dev)
 	mutex_lock(&dev->struct_mutex);
 
 	i915_gem_restore_fences(dev);
+
+	if (IS_GEN4(dev))
+		pci_write_config_word(dev->pdev, GCDGMBUS,
+				      dev_priv->regfile.saveGCDGMBUS);
 	i915_restore_display(dev);
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET)) {
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 9cb5c95d589..448327fe4d8 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2358,13 +2358,19 @@ static bool intel_alloc_plane_obj(struct intel_crtc *crtc,
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_gem_object *obj = NULL;
 	struct drm_mode_fb_cmd2 mode_cmd = { 0 };
-	u32 base = plane_config->base;
+	u32 base_aligned = round_down(plane_config->base, PAGE_SIZE);
+	u32 size_aligned = round_up(plane_config->base + plane_config->size,
+				    PAGE_SIZE);
+
+	size_aligned -= base_aligned;
 
 	if (plane_config->size == 0)
 		return false;
 
-	obj = i915_gem_object_create_stolen_for_preallocated(dev, base, base,
-							     plane_config->size);
+	obj = i915_gem_object_create_stolen_for_preallocated(dev,
+							     base_aligned,
+							     base_aligned,
+							     size_aligned);
 	if (!obj)
 		return false;
 
@@ -6383,8 +6389,7 @@ static void i9xx_get_plane_config(struct intel_crtc *crtc,
 	aligned_height = intel_align_height(dev, crtc->base.primary->fb->height,
 					    plane_config->tiled);
 
-	plane_config->size = PAGE_ALIGN(crtc->base.primary->fb->pitches[0] *
-					aligned_height);
+	plane_config->size = crtc->base.primary->fb->pitches[0] * aligned_height;
 
 	DRM_DEBUG_KMS("pipe/plane %d/%d with fb: size=%dx%d@%d, offset=%x, pitch %d, size 0x%x\n",
 		      pipe, plane, crtc->base.primary->fb->width,
@@ -7424,8 +7429,7 @@ static void ironlake_get_plane_config(struct intel_crtc *crtc,
 	aligned_height = intel_align_height(dev, crtc->base.primary->fb->height,
 					    plane_config->tiled);
 
-	plane_config->size = PAGE_ALIGN(crtc->base.primary->fb->pitches[0] *
-					aligned_height);
+	plane_config->size = crtc->base.primary->fb->pitches[0] * aligned_height;
 
 	DRM_DEBUG_KMS("pipe/plane %d/%d with fb: size=%dx%d@%d, offset=%x, pitch %d, size 0x%x\n",
 		      pipe, plane, crtc->base.primary->fb->width,
@@ -10019,7 +10023,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 		if (obj->tiling_mode != work->old_fb_obj->tiling_mode)
 			/* vlv: DISPLAY_FLIP fails to change tiling */
 			ring = NULL;
-	} else if (IS_IVYBRIDGE(dev)) {
+	} else if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev)) {
 		ring = &dev_priv->ring[BCS];
 	} else if (INTEL_INFO(dev)->gen >= 7) {
 		ring = obj->ring;
@@ -12895,6 +12899,9 @@ static struct intel_quirk intel_quirks[] = {
 
 	/* HP Chromebook 14 (Celeron 2955U) */
 	{ 0x0a06, 0x103c, 0x21ed, quirk_backlight_present },
+
+	/* Dell Chromebook 11 */
+	{ 0x0a06, 0x1028, 0x0a35, quirk_backlight_present },
 };
 
 static void intel_init_quirks(struct drm_device *dev)
@@ -12933,11 +12940,7 @@ static void i915_disable_vga(struct drm_device *dev)
 	vga_put(dev->pdev, VGA_RSRC_LEGACY_IO);
 	udelay(300);
 
-	/*
-	 * Fujitsu-Siemens Lifebook S6010 (830) has problems resuming
-	 * from S3 without preserving (some of?) the other bits.
-	 */
-	I915_WRITE(vga_reg, dev_priv->bios_vgacntr | VGA_DISP_DISABLE);
+	I915_WRITE(vga_reg, VGA_DISP_DISABLE);
 	POSTING_READ(vga_reg);
 }
 
@@ -13026,8 +13029,6 @@ void intel_modeset_init(struct drm_device *dev)
 
 	intel_shared_dpll_init(dev);
 
-	/* save the BIOS value before clobbering it */
-	dev_priv->bios_vgacntr = I915_READ(i915_vgacntrl_reg(dev));
 	/* Just disable it once at startup */
 	i915_disable_vga(dev);
 	intel_setup_outputs(dev);
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 4bcd9175732..3104d06aa20 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -778,10 +778,8 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 				      DP_AUX_CH_CTL_RECEIVE_ERROR))
 				continue;
 			if (status & DP_AUX_CH_CTL_DONE)
-				break;
+				goto done;
 		}
-		if (status & DP_AUX_CH_CTL_DONE)
-			break;
 	}
 
 	if ((status & DP_AUX_CH_CTL_DONE) == 0) {
@@ -790,6 +788,7 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 		goto out;
 	}
 
+done:
 	/* Check for timeout or receive error.
 	 * Timeouts occur when the sink is not connected
 	 */
@@ -1037,7 +1036,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 
 	pipe_config->has_dp_encoder = true;
 	pipe_config->has_drrs = false;
-	pipe_config->has_audio = intel_dp->has_audio;
+	pipe_config->has_audio = intel_dp->has_audio && port != PORT_A;
 
 	if (is_edp(intel_dp) && intel_connector->panel.fixed_mode) {
 		intel_fixed_panel_mode(intel_connector->panel.fixed_mode,
@@ -1879,8 +1878,8 @@ static void intel_dp_get_config(struct intel_encoder *encoder,
 	int dotclock;
 
 	tmp = I915_READ(intel_dp->output_reg);
-	if (tmp & DP_AUDIO_OUTPUT_ENABLE)
-		pipe_config->has_audio = true;
+
+	pipe_config->has_audio = tmp & DP_AUDIO_OUTPUT_ENABLE && port != PORT_A;
 
 	if ((port == PORT_A) || !HAS_PCH_CPT(dev)) {
 		if (tmp & DP_SYNC_HS_HIGH)
@@ -3645,8 +3644,6 @@ intel_dp_link_down(struct intel_dp *intel_dp)
 	enum port port = intel_dig_port->port;
 	struct drm_device *dev = intel_dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc =
-		to_intel_crtc(intel_dig_port->base.base.crtc);
 	uint32_t DP = intel_dp->DP;
 
 	if (WARN_ON(HAS_DDI(dev)))
@@ -3671,8 +3668,6 @@ intel_dp_link_down(struct intel_dp *intel_dp)
 
 	if (HAS_PCH_IBX(dev) &&
 	    I915_READ(intel_dp->output_reg) & DP_PIPEB_SELECT) {
-		struct drm_crtc *crtc = intel_dig_port->base.base.crtc;
-
 		/* Hardware workaround: leaving our transcoder select
 		 * set to transcoder B while it's off will prevent the
 		 * corresponding HDMI output on transcoder A.
@@ -3683,18 +3678,7 @@ intel_dp_link_down(struct intel_dp *intel_dp)
 		 */
 		DP &= ~DP_PIPEB_SELECT;
 		I915_WRITE(intel_dp->output_reg, DP);
-
-		/* Changes to enable or select take place the vblank
-		 * after being written.
-		 */
-		if (WARN_ON(crtc == NULL)) {
-			/* We should never try to disable a port without a crtc
-			 * attached. For paranoia keep the code around for a
-			 * bit. */
-			POSTING_READ(intel_dp->output_reg);
-			msleep(50);
-		} else
-			intel_wait_for_vblank(dev, intel_crtc->pipe);
+		POSTING_READ(intel_dp->output_reg);
 	}
 
 	DP &= ~DP_AUDIO_OUTPUT_ENABLE;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index ba715229a54..07ce04683c3 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -35,9 +35,6 @@
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_dp_mst_helper.h>
 
-#define DIV_ROUND_CLOSEST_ULL(ll, d)	\
-({ unsigned long long _tmp = (ll)+(d)/2; do_div(_tmp, d); _tmp; })
-
 /**
  * _wait_for - magic (register) wait macro
  *
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index b31088a551f..ae628001fd9 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -270,18 +270,17 @@ gmbus_wait_idle(struct drm_i915_private *dev_priv)
 }
 
 static int
-gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg,
-		u32 gmbus1_index)
+gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv,
+		      unsigned short addr, u8 *buf, unsigned int len,
+		      u32 gmbus1_index)
 {
 	int reg_offset = dev_priv->gpio_mmio_base;
-	u16 len = msg->len;
-	u8 *buf = msg->buf;
 
 	I915_WRITE(GMBUS1 + reg_offset,
 		   gmbus1_index |
 		   GMBUS_CYCLE_WAIT |
 		   (len << GMBUS_BYTE_COUNT_SHIFT) |
-		   (msg->addr << GMBUS_SLAVE_ADDR_SHIFT) |
+		   (addr << GMBUS_SLAVE_ADDR_SHIFT) |
 		   GMBUS_SLAVE_READ | GMBUS_SW_RDY);
 	while (len) {
 		int ret;
@@ -303,11 +302,35 @@ gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg,
 }
 
 static int
-gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg)
+gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg,
+		u32 gmbus1_index)
 {
-	int reg_offset = dev_priv->gpio_mmio_base;
-	u16 len = msg->len;
 	u8 *buf = msg->buf;
+	unsigned int rx_size = msg->len;
+	unsigned int len;
+	int ret;
+
+	do {
+		len = min(rx_size, GMBUS_BYTE_COUNT_MAX);
+
+		ret = gmbus_xfer_read_chunk(dev_priv, msg->addr,
+					    buf, len, gmbus1_index);
+		if (ret)
+			return ret;
+
+		rx_size -= len;
+		buf += len;
+	} while (rx_size != 0);
+
+	return 0;
+}
+
+static int
+gmbus_xfer_write_chunk(struct drm_i915_private *dev_priv,
+		       unsigned short addr, u8 *buf, unsigned int len)
+{
+	int reg_offset = dev_priv->gpio_mmio_base;
+	unsigned int chunk_size = len;
 	u32 val, loop;
 
 	val = loop = 0;
@@ -319,8 +342,8 @@ gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg)
 	I915_WRITE(GMBUS3 + reg_offset, val);
 	I915_WRITE(GMBUS1 + reg_offset,
 		   GMBUS_CYCLE_WAIT |
-		   (msg->len << GMBUS_BYTE_COUNT_SHIFT) |
-		   (msg->addr << GMBUS_SLAVE_ADDR_SHIFT) |
+		   (chunk_size << GMBUS_BYTE_COUNT_SHIFT) |
+		   (addr << GMBUS_SLAVE_ADDR_SHIFT) |
 		   GMBUS_SLAVE_WRITE | GMBUS_SW_RDY);
 	while (len) {
 		int ret;
@@ -337,6 +360,29 @@ gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg)
 		if (ret)
 			return ret;
 	}
+
+	return 0;
+}
+
+static int
+gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg)
+{
+	u8 *buf = msg->buf;
+	unsigned int tx_size = msg->len;
+	unsigned int len;
+	int ret;
+
+	do {
+		len = min(tx_size, GMBUS_BYTE_COUNT_MAX);
+
+		ret = gmbus_xfer_write_chunk(dev_priv, msg->addr, buf, len);
+		if (ret)
+			return ret;
+
+		buf += len;
+		tx_size -= len;
+	} while (tx_size != 0);
+
 	return 0;
 }
 
@@ -389,7 +435,7 @@ gmbus_xfer(struct i2c_adapter *adapter,
 					       struct intel_gmbus,
 					       adapter);
 	struct drm_i915_private *dev_priv = bus->dev_priv;
-	int i, reg_offset;
+	int i = 0, inc, try = 0, reg_offset;
 	int ret = 0;
 
 	intel_aux_display_runtime_get(dev_priv);
@@ -402,12 +448,14 @@ gmbus_xfer(struct i2c_adapter *adapter,
 
 	reg_offset = dev_priv->gpio_mmio_base;
 
+retry:
 	I915_WRITE(GMBUS0 + reg_offset, bus->reg0);
 
-	for (i = 0; i < num; i++) {
+	for (; i < num; i += inc) {
+		inc = 1;
 		if (gmbus_is_index_read(msgs, i, num)) {
 			ret = gmbus_xfer_index_read(dev_priv, &msgs[i]);
-			i += 1;  /* set i to the index of the read xfer */
+			inc = 2; /* an index read is two msgs */
 		} else if (msgs[i].flags & I2C_M_RD) {
 			ret = gmbus_xfer_read(dev_priv, &msgs[i], 0);
 		} else {
@@ -479,6 +527,18 @@ clear_err:
 			 adapter->name, msgs[i].addr,
 			 (msgs[i].flags & I2C_M_RD) ? 'r' : 'w', msgs[i].len);
 
+	/*
+	 * Passive adapters sometimes NAK the first probe. Retry the first
+	 * message once on -ENXIO for GMBUS transfers; the bit banging algorithm
+	 * has retries internally. See also the retry loop in
+	 * drm_do_probe_ddc_edid, which bails out on the first -ENXIO.
+	 */
+	if (ret == -ENXIO && i == 0 && try++ == 0) {
+		DRM_DEBUG_KMS("GMBUS [%s] NAK on first message, retry\n",
+			      adapter->name);
+		goto retry;
+	}
+
 	goto out;
 
 timeout:
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index bafd38b5703..a97b83b78ae 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1106,15 +1106,17 @@ static int gen8_emit_flush(struct intel_ringbuffer *ringbuf,
 
 	cmd = MI_FLUSH_DW + 1;
 
-	if (ring == &dev_priv->ring[VCS]) {
-		if (invalidate_domains & I915_GEM_GPU_DOMAINS)
-			cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD |
-				MI_FLUSH_DW_STORE_INDEX |
-				MI_FLUSH_DW_OP_STOREDW;
-	} else {
-		if (invalidate_domains & I915_GEM_DOMAIN_RENDER)
-			cmd |= MI_INVALIDATE_TLB | MI_FLUSH_DW_STORE_INDEX |
-				MI_FLUSH_DW_OP_STOREDW;
+	/* We always require a command barrier so that subsequent
+	 * commands, such as breadcrumb interrupts, are strictly ordered
+	 * wrt the contents of the write cache being flushed to memory
+	 * (and thus being coherent from the CPU).
+	 */
+	cmd |= MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
+
+	if (invalidate_domains & I915_GEM_GPU_DOMAINS) {
+		cmd |= MI_INVALIDATE_TLB;
+		if (ring == &dev_priv->ring[VCS])
+			cmd |= MI_INVALIDATE_BSD;
 	}
 
 	intel_logical_ring_emit(ringbuf, cmd);
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index c0bbf217244..b7e80bf190f 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -809,12 +809,28 @@ static int intel_dual_link_lvds_callback(const struct dmi_system_id *id)
 static const struct dmi_system_id intel_dual_link_lvds[] = {
 	{
 		.callback = intel_dual_link_lvds_callback,
-		.ident = "Apple MacBook Pro (Core i5/i7 Series)",
+		.ident = "Apple MacBook Pro 15\" (2010)",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro6,2"),
+		},
+	},
+	{
+		.callback = intel_dual_link_lvds_callback,
+		.ident = "Apple MacBook Pro 15\" (2011)",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro8,2"),
 		},
 	},
+	{
+		.callback = intel_dual_link_lvds_callback,
+		.ident = "Apple MacBook Pro 15\" (2012)",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro9,1"),
+		},
+	},
 	{ }	/* terminating entry */
 };
 
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 41b3be21749..ce5a385150c 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -30,6 +30,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/kernel.h>
 #include <linux/moduleparam.h>
 #include "intel_drv.h"
 
@@ -947,7 +948,7 @@ void intel_panel_enable_backlight(struct intel_connector *connector)
 
 	WARN_ON(panel->backlight.max == 0);
 
-	if (panel->backlight.level == 0) {
+	if (panel->backlight.level <= panel->backlight.min) {
 		panel->backlight.level = panel->backlight.max;
 		if (panel->backlight.device)
 			panel->backlight.device->props.brightness =
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index ad2fd605f76..c64f1942e8d 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -5691,6 +5691,10 @@ static void haswell_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN7_GT_MODE,
 		   GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
 
+	/* WaSampleCChickenBitEnable:hsw */
+	I915_WRITE(HALF_SLICE_CHICKEN3,
+		   _MASKED_BIT_ENABLE(HSW_SAMPLE_C_PERFORMANCE));
+
 	/* WaSwitchSolVfFArbitrationPriority:hsw */
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
 
@@ -6520,29 +6524,6 @@ static void chv_pipe_power_well_disable(struct drm_i915_private *dev_priv,
 	chv_set_pipe_power_well(dev_priv, power_well, false);
 }
 
-static void check_power_well_state(struct drm_i915_private *dev_priv,
-				   struct i915_power_well *power_well)
-{
-	bool enabled = power_well->ops->is_enabled(dev_priv, power_well);
-
-	if (power_well->always_on || !i915.disable_power_well) {
-		if (!enabled)
-			goto mismatch;
-
-		return;
-	}
-
-	if (enabled != (power_well->count > 0))
-		goto mismatch;
-
-	return;
-
-mismatch:
-	WARN(1, "state mismatch for '%s' (always_on %d hw state %d use-count %d disable_power_well %d\n",
-		  power_well->name, power_well->always_on, enabled,
-		  power_well->count, i915.disable_power_well);
-}
-
 void intel_display_power_get(struct drm_i915_private *dev_priv,
 			     enum intel_display_power_domain domain)
 {
@@ -6562,8 +6543,6 @@ void intel_display_power_get(struct drm_i915_private *dev_priv,
 			power_well->ops->enable(dev_priv, power_well);
 			power_well->hw_enabled = true;
 		}
-
-		check_power_well_state(dev_priv, power_well);
 	}
 
 	power_domains->domain_use_count[domain]++;
@@ -6593,8 +6572,6 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 			power_well->hw_enabled = false;
 			power_well->ops->disable(dev_priv, power_well);
 		}
-
-		check_power_well_state(dev_priv, power_well);
 	}
 
 	mutex_unlock(&power_domains->lock);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 0a80e419b58..9f10b771319 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -362,12 +362,15 @@ gen7_render_ring_flush(struct intel_engine_cs *ring,
 		flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_MEDIA_STATE_CLEAR;
 		/*
 		 * TLB invalidate requires a post-sync write.
 		 */
 		flags |= PIPE_CONTROL_QW_WRITE;
 		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
 
+		flags |= PIPE_CONTROL_STALL_AT_SCOREBOARD;
+
 		/* Workaround: we must issue a pipe_control with CS-stall bit
 		 * set before a pipe_control command that has the state cache
 		 * invalidate bit set. */
@@ -2136,6 +2139,14 @@ static int gen6_bsd_ring_flush(struct intel_engine_cs *ring,
 	cmd = MI_FLUSH_DW;
 	if (INTEL_INFO(ring->dev)->gen >= 8)
 		cmd += 1;
+
+	/* We always require a command barrier so that subsequent
+	 * commands, such as breadcrumb interrupts, are strictly ordered
+	 * wrt the contents of the write cache being flushed to memory
+	 * (and thus being coherent from the CPU).
+	 */
+	cmd |= MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
+
 	/*
 	 * Bspec vol 1c.5 - video engine command streamer:
 	 * "If ENABLED, all TLBs will be invalidated once the flush
@@ -2143,8 +2154,8 @@ static int gen6_bsd_ring_flush(struct intel_engine_cs *ring,
 	 * Post-Sync Operation field is a value of 1h or 3h."
 	 */
 	if (invalidate & I915_GEM_GPU_DOMAINS)
-		cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD |
-			MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
+		cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD;
+
 	intel_ring_emit(ring, cmd);
 	intel_ring_emit(ring, I915_GEM_HWS_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT);
 	if (INTEL_INFO(ring->dev)->gen >= 8) {
@@ -2239,6 +2250,14 @@ static int gen6_ring_flush(struct intel_engine_cs *ring,
 	cmd = MI_FLUSH_DW;
 	if (INTEL_INFO(ring->dev)->gen >= 8)
 		cmd += 1;
+
+	/* We always require a command barrier so that subsequent
+	 * commands, such as breadcrumb interrupts, are strictly ordered
+	 * wrt the contents of the write cache being flushed to memory
+	 * (and thus being coherent from the CPU).
+	 */
+	cmd |= MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
+
 	/*
 	 * Bspec vol 1c.3 - blitter engine command streamer:
 	 * "If ENABLED, all TLBs will be invalidated once the flush
@@ -2246,8 +2265,7 @@ static int gen6_ring_flush(struct intel_engine_cs *ring,
 	 * Post-Sync Operation field is a value of 1h or 3h."
 	 */
 	if (invalidate & I915_GEM_DOMAIN_RENDER)
-		cmd |= MI_INVALIDATE_TLB | MI_FLUSH_DW_STORE_INDEX |
-			MI_FLUSH_DW_OP_STOREDW;
+		cmd |= MI_INVALIDATE_TLB;
 	intel_ring_emit(ring, cmd);
 	intel_ring_emit(ring, I915_GEM_HWS_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT);
 	if (INTEL_INFO(ring->dev)->gen >= 8) {
diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c
index 01d841ea314..731b10a09aa 100644
--- a/drivers/gpu/drm/i915/intel_sideband.c
+++ b/drivers/gpu/drm/i915/intel_sideband.c
@@ -82,7 +82,7 @@ u32 vlv_punit_read(struct drm_i915_private *dev_priv, u8 addr)
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
 	mutex_lock(&dev_priv->dpio_lock);
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_PUNIT,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_PUNIT,
 			SB_CRRDDA_NP, addr, &val);
 	mutex_unlock(&dev_priv->dpio_lock);
 
@@ -94,7 +94,7 @@ void vlv_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val)
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
 	mutex_lock(&dev_priv->dpio_lock);
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_PUNIT,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_PUNIT,
 			SB_CRWRDA_NP, addr, &val);
 	mutex_unlock(&dev_priv->dpio_lock);
 }
@@ -103,7 +103,7 @@ u32 vlv_bunit_read(struct drm_i915_private *dev_priv, u32 reg)
 {
 	u32 val = 0;
 
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_BUNIT,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_BUNIT,
 			SB_CRRDDA_NP, reg, &val);
 
 	return val;
@@ -111,7 +111,7 @@ u32 vlv_bunit_read(struct drm_i915_private *dev_priv, u32 reg)
 
 void vlv_bunit_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 {
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_BUNIT,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_BUNIT,
 			SB_CRWRDA_NP, reg, &val);
 }
 
@@ -122,7 +122,7 @@ u32 vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr)
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
 	mutex_lock(&dev_priv->dpio_lock);
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_NC,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_NC,
 			SB_CRRDDA_NP, addr, &val);
 	mutex_unlock(&dev_priv->dpio_lock);
 
@@ -132,56 +132,56 @@ u32 vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr)
 u32 vlv_gpio_nc_read(struct drm_i915_private *dev_priv, u32 reg)
 {
 	u32 val = 0;
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPIO_NC,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_GPIO_NC,
 			SB_CRRDDA_NP, reg, &val);
 	return val;
 }
 
 void vlv_gpio_nc_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 {
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPIO_NC,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_GPIO_NC,
 			SB_CRWRDA_NP, reg, &val);
 }
 
 u32 vlv_cck_read(struct drm_i915_private *dev_priv, u32 reg)
 {
 	u32 val = 0;
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCK,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_CCK,
 			SB_CRRDDA_NP, reg, &val);
 	return val;
 }
 
 void vlv_cck_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 {
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCK,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_CCK,
 			SB_CRWRDA_NP, reg, &val);
 }
 
 u32 vlv_ccu_read(struct drm_i915_private *dev_priv, u32 reg)
 {
 	u32 val = 0;
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCU,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_CCU,
 			SB_CRRDDA_NP, reg, &val);
 	return val;
 }
 
 void vlv_ccu_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 {
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCU,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_CCU,
 			SB_CRWRDA_NP, reg, &val);
 }
 
 u32 vlv_gps_core_read(struct drm_i915_private *dev_priv, u32 reg)
 {
 	u32 val = 0;
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPS_CORE,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_GPS_CORE,
 			SB_CRRDDA_NP, reg, &val);
 	return val;
 }
 
 void vlv_gps_core_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 {
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPS_CORE,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_GPS_CORE,
 			SB_CRWRDA_NP, reg, &val);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 07a74ef589b..4edebce7f21 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -1178,7 +1178,7 @@ int intel_sprite_set_colorkey(struct drm_device *dev, void *data,
 	drm_modeset_lock_all(dev);
 
 	plane = drm_plane_find(dev, set->plane_id);
-	if (!plane) {
+	if (!plane || plane->type != DRM_PLANE_TYPE_OVERLAY) {
 		ret = -ENOENT;
 		goto out_unlock;
 	}
@@ -1205,7 +1205,7 @@ int intel_sprite_get_colorkey(struct drm_device *dev, void *data,
 	drm_modeset_lock_all(dev);
 
 	plane = drm_plane_find(dev, get->plane_id);
-	if (!plane) {
+	if (!plane || plane->type != DRM_PLANE_TYPE_OVERLAY) {
 		ret = -ENOENT;
 		goto out_unlock;
 	}
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 918b7616396..b29091b21a7 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -43,8 +43,8 @@
 static void
 assert_device_not_suspended(struct drm_i915_private *dev_priv)
 {
-	WARN(HAS_RUNTIME_PM(dev_priv->dev) && dev_priv->pm.suspended,
-	     "Device suspended\n");
+	WARN_ONCE(HAS_RUNTIME_PM(dev_priv->dev) && dev_priv->pm.suspended,
+		  "Device suspended\n");
 }
 
 static void __gen6_gt_wait_for_thread_c0(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 83485ab81ce..d8e693d1f6d 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -1525,6 +1525,11 @@ static int mga_vga_mode_valid(struct drm_connector *connector,
 		return MODE_BANDWIDTH;
 	}
 
+	if ((mode->hdisplay % 8) != 0 || (mode->hsync_start % 8) != 0 ||
+	    (mode->hsync_end % 8) != 0 || (mode->htotal % 8) != 0) {
+		return MODE_H_ILLEGAL;
+	}
+
 	if (mode->crtc_hdisplay > 2048 || mode->crtc_hsync_start > 4096 ||
 	    mode->crtc_hsync_end > 4096 || mode->crtc_htotal > 4096 ||
 	    mode->crtc_vdisplay > 2048 || mode->crtc_vsync_start > 4096 ||
diff --git a/drivers/gpu/drm/nouveau/core/core/event.c b/drivers/gpu/drm/nouveau/core/core/event.c
index ff2b434b3db..760947e380c 100644
--- a/drivers/gpu/drm/nouveau/core/core/event.c
+++ b/drivers/gpu/drm/nouveau/core/core/event.c
@@ -26,7 +26,7 @@
 void
 nvkm_event_put(struct nvkm_event *event, u32 types, int index)
 {
-	BUG_ON(!spin_is_locked(&event->refs_lock));
+	assert_spin_locked(&event->refs_lock);
 	while (types) {
 		int type = __ffs(types); types &= ~(1 << type);
 		if (--event->refs[index * event->types_nr + type] == 0) {
@@ -39,7 +39,7 @@ nvkm_event_put(struct nvkm_event *event, u32 types, int index)
 void
 nvkm_event_get(struct nvkm_event *event, u32 types, int index)
 {
-	BUG_ON(!spin_is_locked(&event->refs_lock));
+	assert_spin_locked(&event->refs_lock);
 	while (types) {
 		int type = __ffs(types); types &= ~(1 << type);
 		if (++event->refs[index * event->types_nr + type] == 1) {
diff --git a/drivers/gpu/drm/nouveau/core/core/notify.c b/drivers/gpu/drm/nouveau/core/core/notify.c
index d1bcde55e9d..839a3257768 100644
--- a/drivers/gpu/drm/nouveau/core/core/notify.c
+++ b/drivers/gpu/drm/nouveau/core/core/notify.c
@@ -98,7 +98,7 @@ nvkm_notify_send(struct nvkm_notify *notify, void *data, u32 size)
 	struct nvkm_event *event = notify->event;
 	unsigned long flags;
 
-	BUG_ON(!spin_is_locked(&event->list_lock));
+	assert_spin_locked(&event->list_lock);
 	BUG_ON(size != notify->size);
 
 	spin_lock_irqsave(&event->refs_lock, flags);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c
index a75c35ccf25..165401c4045 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c
@@ -24,13 +24,6 @@
 
 #include "nv04.h"
 
-static void
-nv4c_mc_msi_rearm(struct nouveau_mc *pmc)
-{
-	struct nv04_mc_priv *priv = (void *)pmc;
-	nv_wr08(priv, 0x088050, 0xff);
-}
-
 struct nouveau_oclass *
 nv4c_mc_oclass = &(struct nouveau_mc_oclass) {
 	.base.handle = NV_SUBDEV(MC, 0x4c),
@@ -41,5 +34,4 @@ nv4c_mc_oclass = &(struct nouveau_mc_oclass) {
 		.fini = _nouveau_mc_fini,
 	},
 	.intr = nv04_mc_intr,
-	.msi_rearm = nv4c_mc_msi_rearm,
 }.base;
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 753a6def61e..3d1cfcb96b6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -28,6 +28,7 @@
 #include "nouveau_ttm.h"
 #include "nouveau_gem.h"
 
+#include "drm_legacy.h"
 static int
 nouveau_vram_manager_init(struct ttm_mem_type_manager *man, unsigned long psize)
 {
@@ -281,7 +282,7 @@ nouveau_ttm_mmap(struct file *filp, struct vm_area_struct *vma)
 	struct nouveau_drm *drm = nouveau_drm(file_priv->minor->dev);
 
 	if (unlikely(vma->vm_pgoff < DRM_FILE_PAGE_OFFSET))
-		return -EINVAL;
+		return drm_legacy_mmap(filp, vma);
 
 	return ttm_bo_mmap(filp, vma, &drm->ttm.bdev);
 }
diff --git a/drivers/gpu/drm/qxl/qxl_cmd.c b/drivers/gpu/drm/qxl/qxl_cmd.c
index 97823644d34..f33251d6791 100644
--- a/drivers/gpu/drm/qxl/qxl_cmd.c
+++ b/drivers/gpu/drm/qxl/qxl_cmd.c
@@ -505,6 +505,7 @@ int qxl_hw_surface_alloc(struct qxl_device *qdev,
 
 	cmd = (struct qxl_surface_cmd *)qxl_release_map(qdev, release);
 	cmd->type = QXL_SURFACE_CMD_CREATE;
+	cmd->flags = QXL_SURF_FLAG_KEEP_DATA;
 	cmd->u.surface_create.format = surf->surf.format;
 	cmd->u.surface_create.width = surf->surf.width;
 	cmd->u.surface_create.height = surf->surf.height;
diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c
index b110883f825..7354a4cda59 100644
--- a/drivers/gpu/drm/qxl/qxl_ioctl.c
+++ b/drivers/gpu/drm/qxl/qxl_ioctl.c
@@ -122,8 +122,10 @@ static struct qxl_bo *qxlhw_handle_to_bo(struct qxl_device *qdev,
 	qobj = gem_to_qxl_bo(gobj);
 
 	ret = qxl_release_list_add(release, qobj);
-	if (ret)
+	if (ret) {
+		drm_gem_object_unreference_unlocked(gobj);
 		return NULL;
+	}
 
 	return qobj;
 }
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 30d242b2507..ce8cab52285 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -330,8 +330,10 @@ atombios_set_crtc_dtd_timing(struct drm_crtc *crtc,
 		misc |= ATOM_COMPOSITESYNC;
 	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
 		misc |= ATOM_INTERLACE;
-	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		misc |= ATOM_DOUBLE_CLOCK_MODE;
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		misc |= ATOM_H_REPLICATIONBY2 | ATOM_V_REPLICATIONBY2;
 
 	args.susModeMiscInfo.usAccess = cpu_to_le16(misc);
 	args.ucCRTC = radeon_crtc->crtc_id;
@@ -374,8 +376,10 @@ static void atombios_crtc_set_timing(struct drm_crtc *crtc,
 		misc |= ATOM_COMPOSITESYNC;
 	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
 		misc |= ATOM_INTERLACE;
-	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		misc |= ATOM_DOUBLE_CLOCK_MODE;
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		misc |= ATOM_H_REPLICATIONBY2 | ATOM_V_REPLICATIONBY2;
 
 	args.susModeMiscInfo.usAccess = cpu_to_le16(misc);
 	args.ucCRTC = radeon_crtc->crtc_id;
@@ -1405,6 +1409,9 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 	       (x << 16) | y);
 	viewport_w = crtc->mode.hdisplay;
 	viewport_h = (crtc->mode.vdisplay + 1) & ~1;
+	if ((rdev->family >= CHIP_BONAIRE) &&
+	    (crtc->mode.flags & DRM_MODE_FLAG_INTERLACE))
+		viewport_h *= 2;
 	WREG32(EVERGREEN_VIEWPORT_SIZE + radeon_crtc->crtc_offset,
 	       (viewport_w << 16) | viewport_h);
 
@@ -1851,10 +1858,9 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc)
 				return pll;
 		}
 		/* otherwise, pick one of the plls */
-		if ((rdev->family == CHIP_KAVERI) ||
-		    (rdev->family == CHIP_KABINI) ||
+		if ((rdev->family == CHIP_KABINI) ||
 		    (rdev->family == CHIP_MULLINS)) {
-			/* KB/KV/ML has PPLL1 and PPLL2 */
+			/* KB/ML has PPLL1 and PPLL2 */
 			pll_in_use = radeon_get_pll_use_mask(crtc);
 			if (!(pll_in_use & (1 << ATOM_PPLL2)))
 				return ATOM_PPLL2;
@@ -1863,7 +1869,7 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc)
 			DRM_ERROR("unable to allocate a PPLL\n");
 			return ATOM_PPLL_INVALID;
 		} else {
-			/* CI has PPLL0, PPLL1, and PPLL2 */
+			/* CI/KV has PPLL0, PPLL1, and PPLL2 */
 			pll_in_use = radeon_get_pll_use_mask(crtc);
 			if (!(pll_in_use & (1 << ATOM_PPLL2)))
 				return ATOM_PPLL2;
@@ -2154,6 +2160,7 @@ static void atombios_crtc_disable(struct drm_crtc *crtc)
 	case ATOM_PPLL0:
 		/* disable the ppll */
 		if ((rdev->family == CHIP_ARUBA) ||
+		    (rdev->family == CHIP_KAVERI) ||
 		    (rdev->family == CHIP_BONAIRE) ||
 		    (rdev->family == CHIP_HAWAII))
 			atombios_crtc_program_pll(crtc, radeon_crtc->crtc_id, radeon_crtc->pll_id,
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 11ba9d21b89..ceab25d5423 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -405,19 +405,21 @@ bool radeon_dp_getdpcd(struct radeon_connector *radeon_connector)
 {
 	struct radeon_connector_atom_dig *dig_connector = radeon_connector->con_priv;
 	u8 msg[DP_DPCD_SIZE];
-	int ret;
+	int ret, i;
 
-	ret = drm_dp_dpcd_read(&radeon_connector->ddc_bus->aux, DP_DPCD_REV, msg,
-			       DP_DPCD_SIZE);
-	if (ret > 0) {
-		memcpy(dig_connector->dpcd, msg, DP_DPCD_SIZE);
+	for (i = 0; i < 7; i++) {
+		ret = drm_dp_dpcd_read(&radeon_connector->ddc_bus->aux, DP_DPCD_REV, msg,
+				       DP_DPCD_SIZE);
+		if (ret == DP_DPCD_SIZE) {
+			memcpy(dig_connector->dpcd, msg, DP_DPCD_SIZE);
 
-		DRM_DEBUG_KMS("DPCD: %*ph\n", (int)sizeof(dig_connector->dpcd),
-			      dig_connector->dpcd);
+			DRM_DEBUG_KMS("DPCD: %*ph\n", (int)sizeof(dig_connector->dpcd),
+				      dig_connector->dpcd);
 
-		radeon_dp_probe_oui(radeon_connector);
+			radeon_dp_probe_oui(radeon_connector);
 
-		return true;
+			return true;
+		}
 	}
 	dig_connector->dpcd[0] = 0;
 	return false;
@@ -492,6 +494,10 @@ int radeon_dp_mode_valid_helper(struct drm_connector *connector,
 	struct radeon_connector_atom_dig *dig_connector;
 	int dp_clock;
 
+	if ((mode->clock > 340000) &&
+	    (!radeon_connector_is_dp12_capable(connector)))
+		return MODE_CLOCK_HIGH;
+
 	if (!radeon_connector->con_priv)
 		return MODE_CLOCK_HIGH;
 	dig_connector = radeon_connector->con_priv;
@@ -619,10 +625,8 @@ static int radeon_dp_link_train_init(struct radeon_dp_link_train_info *dp_info)
 		drm_dp_dpcd_writeb(dp_info->aux,
 				   DP_DOWNSPREAD_CTRL, 0);
 
-	if ((dp_info->connector->connector_type == DRM_MODE_CONNECTOR_eDP) &&
-	    (dig->panel_mode == DP_PANEL_MODE_INTERNAL_DP2_MODE)) {
+	if (dig->panel_mode == DP_PANEL_MODE_INTERNAL_DP2_MODE)
 		drm_dp_dpcd_writeb(dp_info->aux, DP_EDP_CONFIGURATION_SET, 1);
-	}
 
 	/* set the lane count on the sink */
 	tmp = dp_info->dp_lane_count;
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index 11a55e9dad7..c5699b59366 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -4729,7 +4729,7 @@ void ci_dpm_disable(struct radeon_device *rdev)
 	ci_enable_spread_spectrum(rdev, false);
 	ci_enable_auto_throttle_source(rdev, RADEON_DPM_AUTO_THROTTLE_SRC_THERMAL, false);
 	ci_stop_dpm(rdev);
-	ci_enable_ds_master_switch(rdev, true);
+	ci_enable_ds_master_switch(rdev, false);
 	ci_enable_ulv(rdev, false);
 	ci_clear_vc(rdev);
 	ci_reset_to_default(rdev);
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 89c01fa6dd8..87073e69fc0 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -3880,7 +3880,21 @@ void cik_fence_gfx_ring_emit(struct radeon_device *rdev,
 	struct radeon_ring *ring = &rdev->ring[fence->ring];
 	u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
 
-	/* EVENT_WRITE_EOP - flush caches, send int */
+	/* Workaround for cache flush problems. First send a dummy EOP
+	 * event down the pipe with seq one below.
+	 */
+	radeon_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4));
+	radeon_ring_write(ring, (EOP_TCL1_ACTION_EN |
+				 EOP_TC_ACTION_EN |
+				 EVENT_TYPE(CACHE_FLUSH_AND_INV_TS_EVENT) |
+				 EVENT_INDEX(5)));
+	radeon_ring_write(ring, addr & 0xfffffffc);
+	radeon_ring_write(ring, (upper_32_bits(addr) & 0xffff) |
+				DATA_SEL(1) | INT_SEL(0));
+	radeon_ring_write(ring, fence->seq - 1);
+	radeon_ring_write(ring, 0);
+
+	/* Then send the real EOP event down the pipe. */
 	radeon_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4));
 	radeon_ring_write(ring, (EOP_TCL1_ACTION_EN |
 				 EOP_TC_ACTION_EN |
@@ -4509,6 +4523,31 @@ void cik_compute_set_wptr(struct radeon_device *rdev,
 	WDOORBELL32(ring->doorbell_index, ring->wptr);
 }
 
+static void cik_compute_stop(struct radeon_device *rdev,
+			     struct radeon_ring *ring)
+{
+	u32 j, tmp;
+
+	cik_srbm_select(rdev, ring->me, ring->pipe, ring->queue, 0);
+	/* Disable wptr polling. */
+	tmp = RREG32(CP_PQ_WPTR_POLL_CNTL);
+	tmp &= ~WPTR_POLL_EN;
+	WREG32(CP_PQ_WPTR_POLL_CNTL, tmp);
+	/* Disable HQD. */
+	if (RREG32(CP_HQD_ACTIVE) & 1) {
+		WREG32(CP_HQD_DEQUEUE_REQUEST, 1);
+		for (j = 0; j < rdev->usec_timeout; j++) {
+			if (!(RREG32(CP_HQD_ACTIVE) & 1))
+				break;
+			udelay(1);
+		}
+		WREG32(CP_HQD_DEQUEUE_REQUEST, 0);
+		WREG32(CP_HQD_PQ_RPTR, 0);
+		WREG32(CP_HQD_PQ_WPTR, 0);
+	}
+	cik_srbm_select(rdev, 0, 0, 0, 0);
+}
+
 /**
  * cik_cp_compute_enable - enable/disable the compute CP MEs
  *
@@ -4522,6 +4561,15 @@ static void cik_cp_compute_enable(struct radeon_device *rdev, bool enable)
 	if (enable)
 		WREG32(CP_MEC_CNTL, 0);
 	else {
+		/*
+		 * To make hibernation reliable we need to clear compute ring
+		 * configuration before halting the compute ring.
+		 */
+		mutex_lock(&rdev->srbm_mutex);
+		cik_compute_stop(rdev,&rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX]);
+		cik_compute_stop(rdev,&rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX]);
+		mutex_unlock(&rdev->srbm_mutex);
+
 		WREG32(CP_MEC_CNTL, (MEC_ME1_HALT | MEC_ME2_HALT));
 		rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX].ready = false;
 		rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX].ready = false;
@@ -5750,7 +5798,7 @@ static int cik_pcie_gart_enable(struct radeon_device *rdev)
 	/* restore context1-15 */
 	/* set vm size, must be a multiple of 4 */
 	WREG32(VM_CONTEXT1_PAGE_TABLE_START_ADDR, 0);
-	WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn);
+	WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn - 1);
 	for (i = 1; i < 16; i++) {
 		if (i < 8)
 			WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2),
@@ -6314,6 +6362,7 @@ static void cik_enable_mgcg(struct radeon_device *rdev, bool enable)
 		}
 
 		orig = data = RREG32(RLC_CGTT_MGCG_OVERRIDE);
+		data |= 0x00000001;
 		data &= 0xfffffffd;
 		if (orig != data)
 			WREG32(RLC_CGTT_MGCG_OVERRIDE, data);
@@ -6345,7 +6394,7 @@ static void cik_enable_mgcg(struct radeon_device *rdev, bool enable)
 		}
 	} else {
 		orig = data = RREG32(RLC_CGTT_MGCG_OVERRIDE);
-		data |= 0x00000002;
+		data |= 0x00000003;
 		if (orig != data)
 			WREG32(RLC_CGTT_MGCG_OVERRIDE, data);
 
@@ -7294,7 +7343,6 @@ int cik_irq_set(struct radeon_device *rdev)
 	u32 hpd1, hpd2, hpd3, hpd4, hpd5, hpd6;
 	u32 grbm_int_cntl = 0;
 	u32 dma_cntl, dma_cntl1;
-	u32 thermal_int;
 
 	if (!rdev->irq.installed) {
 		WARN(1, "Can't enable IRQ/MSI because no handler is installed\n");
@@ -7331,13 +7379,6 @@ int cik_irq_set(struct radeon_device *rdev)
 	cp_m2p2 = RREG32(CP_ME2_PIPE2_INT_CNTL) & ~TIME_STAMP_INT_ENABLE;
 	cp_m2p3 = RREG32(CP_ME2_PIPE3_INT_CNTL) & ~TIME_STAMP_INT_ENABLE;
 
-	if (rdev->flags & RADEON_IS_IGP)
-		thermal_int = RREG32_SMC(CG_THERMAL_INT_CTRL) &
-			~(THERM_INTH_MASK | THERM_INTL_MASK);
-	else
-		thermal_int = RREG32_SMC(CG_THERMAL_INT) &
-			~(THERM_INT_MASK_HIGH | THERM_INT_MASK_LOW);
-
 	/* enable CP interrupts on all rings */
 	if (atomic_read(&rdev->irq.ring_int[RADEON_RING_TYPE_GFX_INDEX])) {
 		DRM_DEBUG("cik_irq_set: sw int gfx\n");
@@ -7495,14 +7536,6 @@ int cik_irq_set(struct radeon_device *rdev)
 		hpd6 |= DC_HPDx_INT_EN;
 	}
 
-	if (rdev->irq.dpm_thermal) {
-		DRM_DEBUG("dpm thermal\n");
-		if (rdev->flags & RADEON_IS_IGP)
-			thermal_int |= THERM_INTH_MASK | THERM_INTL_MASK;
-		else
-			thermal_int |= THERM_INT_MASK_HIGH | THERM_INT_MASK_LOW;
-	}
-
 	WREG32(CP_INT_CNTL_RING0, cp_int_cntl);
 
 	WREG32(SDMA0_CNTL + SDMA0_REGISTER_OFFSET, dma_cntl);
@@ -7556,10 +7589,8 @@ int cik_irq_set(struct radeon_device *rdev)
 	WREG32(DC_HPD5_INT_CONTROL, hpd5);
 	WREG32(DC_HPD6_INT_CONTROL, hpd6);
 
-	if (rdev->flags & RADEON_IS_IGP)
-		WREG32_SMC(CG_THERMAL_INT_CTRL, thermal_int);
-	else
-		WREG32_SMC(CG_THERMAL_INT, thermal_int);
+	/* posting read */
+	RREG32(SRBM_STATUS);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
index d748963af08..02246acba36 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -268,6 +268,17 @@ static void cik_sdma_gfx_stop(struct radeon_device *rdev)
 	}
 	rdev->ring[R600_RING_TYPE_DMA_INDEX].ready = false;
 	rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX].ready = false;
+
+	/* FIXME use something else than big hammer but after few days can not
+	 * seem to find good combination so reset SDMA blocks as it seems we
+	 * do not shut them down properly. This fix hibernation and does not
+	 * affect suspend to ram.
+	 */
+	WREG32(SRBM_SOFT_RESET, SOFT_RESET_SDMA | SOFT_RESET_SDMA1);
+	(void)RREG32(SRBM_SOFT_RESET);
+	udelay(50);
+	WREG32(SRBM_SOFT_RESET, 0);
+	(void)RREG32(SRBM_SOFT_RESET);
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/dce3_1_afmt.c b/drivers/gpu/drm/radeon/dce3_1_afmt.c
index 2fe8cfc966d..bafdf92a573 100644
--- a/drivers/gpu/drm/radeon/dce3_1_afmt.c
+++ b/drivers/gpu/drm/radeon/dce3_1_afmt.c
@@ -103,7 +103,7 @@ static void dce3_2_afmt_write_sad_regs(struct drm_encoder *encoder)
 	}
 
 	sad_count = drm_edid_to_sad(radeon_connector->edid, &sads);
-	if (sad_count < 0) {
+	if (sad_count <= 0) {
 		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
 		return;
 	}
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 85995b4e333..c674f63d7f1 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -4589,6 +4589,9 @@ int evergreen_irq_set(struct radeon_device *rdev)
 	WREG32(AFMT_AUDIO_PACKET_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, afmt5);
 	WREG32(AFMT_AUDIO_PACKET_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, afmt6);
 
+	/* posting read */
+	RREG32(SRBM_STATUS);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c
index 9b42001295b..85a109e1e56 100644
--- a/drivers/gpu/drm/radeon/kv_dpm.c
+++ b/drivers/gpu/drm/radeon/kv_dpm.c
@@ -1169,6 +1169,19 @@ void kv_dpm_enable_bapm(struct radeon_device *rdev, bool enable)
 	}
 }
 
+static void kv_enable_thermal_int(struct radeon_device *rdev, bool enable)
+{
+	u32 thermal_int;
+
+	thermal_int = RREG32_SMC(CG_THERMAL_INT_CTRL);
+	if (enable)
+		thermal_int |= THERM_INTH_MASK | THERM_INTL_MASK;
+	else
+		thermal_int &= ~(THERM_INTH_MASK | THERM_INTL_MASK);
+	WREG32_SMC(CG_THERMAL_INT_CTRL, thermal_int);
+
+}
+
 int kv_dpm_enable(struct radeon_device *rdev)
 {
 	struct kv_power_info *pi = kv_get_pi(rdev);
@@ -1280,8 +1293,7 @@ int kv_dpm_late_enable(struct radeon_device *rdev)
 			DRM_ERROR("kv_set_thermal_temperature_range failed\n");
 			return ret;
 		}
-		rdev->irq.dpm_thermal = true;
-		radeon_irq_set(rdev);
+		kv_enable_thermal_int(rdev, true);
 	}
 
 	/* powerdown unused blocks for now */
@@ -1312,6 +1324,7 @@ void kv_dpm_disable(struct radeon_device *rdev)
 	kv_stop_dpm(rdev);
 	kv_enable_ulv(rdev, false);
 	kv_reset_am(rdev);
+	kv_enable_thermal_int(rdev, false);
 
 	kv_update_current_ps(rdev, rdev->pm.dpm.boot_ps);
 }
@@ -2745,13 +2758,11 @@ int kv_dpm_init(struct radeon_device *rdev)
 	pi->enable_auto_thermal_throttling = true;
 	pi->disable_nb_ps3_in_battery = false;
 	if (radeon_bapm == -1) {
-		/* There are stability issues reported on with
-		 * bapm enabled on an asrock system.
-		 */
-		if (rdev->pdev->subsystem_vendor == 0x1849)
-			pi->bapm_enable = false;
-		else
+		/* only enable bapm on KB, ML by default */
+		if (rdev->family == CHIP_KABINI || rdev->family == CHIP_MULLINS)
 			pi->bapm_enable = true;
+		else
+			pi->bapm_enable = false;
 	} else if (radeon_bapm == 0) {
 		pi->bapm_enable = false;
 	} else {
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 3faee58946d..a019ba246e3 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1085,12 +1085,12 @@ static void cayman_gpu_init(struct radeon_device *rdev)
 
 	if ((rdev->config.cayman.max_backends_per_se == 1) &&
 	    (rdev->flags & RADEON_IS_IGP)) {
-		if ((disabled_rb_mask & 3) == 1) {
-			/* RB0 disabled, RB1 enabled */
-			tmp = 0x11111111;
-		} else {
+		if ((disabled_rb_mask & 3) == 2) {
 			/* RB1 disabled, RB0 enabled */
 			tmp = 0x00000000;
+		} else {
+			/* RB0 disabled, RB1 enabled */
+			tmp = 0x11111111;
 		}
 	} else {
 		tmp = gb_addr_config & NUM_PIPES_MASK;
@@ -1269,7 +1269,8 @@ static int cayman_pcie_gart_enable(struct radeon_device *rdev)
 	 */
 	for (i = 1; i < 8; i++) {
 		WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR + (i << 2), 0);
-		WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (i << 2), rdev->vm_manager.max_pfn);
+		WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (i << 2),
+			rdev->vm_manager.max_pfn - 1);
 		WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2),
 		       rdev->vm_manager.saved_table_addr[i]);
 	}
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index b53b31a7b76..a959cc1e7c8 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -644,6 +644,7 @@ int r100_pci_gart_init(struct radeon_device *rdev)
 		return r;
 	rdev->gart.table_size = rdev->gart.num_gpu_pages * 4;
 	rdev->asic->gart.tlb_flush = &r100_pci_gart_tlb_flush;
+	rdev->asic->gart.get_page_entry = &r100_pci_gart_get_page_entry;
 	rdev->asic->gart.set_page = &r100_pci_gart_set_page;
 	return radeon_gart_table_ram_alloc(rdev);
 }
@@ -681,11 +682,16 @@ void r100_pci_gart_disable(struct radeon_device *rdev)
 	WREG32(RADEON_AIC_HI_ADDR, 0);
 }
 
+uint64_t r100_pci_gart_get_page_entry(uint64_t addr, uint32_t flags)
+{
+	return addr;
+}
+
 void r100_pci_gart_set_page(struct radeon_device *rdev, unsigned i,
-			    uint64_t addr, uint32_t flags)
+			    uint64_t entry)
 {
 	u32 *gtt = rdev->gart.ptr;
-	gtt[i] = cpu_to_le32(lower_32_bits(addr));
+	gtt[i] = cpu_to_le32(lower_32_bits(entry));
 }
 
 void r100_pci_gart_fini(struct radeon_device *rdev)
@@ -722,6 +728,10 @@ int r100_irq_set(struct radeon_device *rdev)
 		tmp |= RADEON_FP2_DETECT_MASK;
 	}
 	WREG32(RADEON_GEN_INT_CNTL, tmp);
+
+	/* read back to post the write */
+	RREG32(RADEON_GEN_INT_CNTL);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 1bc4704034c..f3ef6257d66 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -73,11 +73,8 @@ void rv370_pcie_gart_tlb_flush(struct radeon_device *rdev)
 #define R300_PTE_WRITEABLE (1 << 2)
 #define R300_PTE_READABLE  (1 << 3)
 
-void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
-			      uint64_t addr, uint32_t flags)
+uint64_t rv370_pcie_gart_get_page_entry(uint64_t addr, uint32_t flags)
 {
-	void __iomem *ptr = rdev->gart.ptr;
-
 	addr = (lower_32_bits(addr) >> 8) |
 		((upper_32_bits(addr) & 0xff) << 24);
 	if (flags & RADEON_GART_PAGE_READ)
@@ -86,10 +83,18 @@ void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
 		addr |= R300_PTE_WRITEABLE;
 	if (!(flags & RADEON_GART_PAGE_SNOOP))
 		addr |= R300_PTE_UNSNOOPED;
+	return addr;
+}
+
+void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
+			      uint64_t entry)
+{
+	void __iomem *ptr = rdev->gart.ptr;
+
 	/* on x86 we want this to be CPU endian, on powerpc
 	 * on powerpc without HW swappers, it'll get swapped on way
 	 * into VRAM - so no need for cpu_to_le32 on VRAM tables */
-	writel(addr, ((void __iomem *)ptr) + (i * 4));
+	writel(entry, ((void __iomem *)ptr) + (i * 4));
 }
 
 int rv370_pcie_gart_init(struct radeon_device *rdev)
@@ -109,6 +114,7 @@ int rv370_pcie_gart_init(struct radeon_device *rdev)
 		DRM_ERROR("Failed to register debugfs file for PCIE gart !\n");
 	rdev->gart.table_size = rdev->gart.num_gpu_pages * 4;
 	rdev->asic->gart.tlb_flush = &rv370_pcie_gart_tlb_flush;
+	rdev->asic->gart.get_page_entry = &rv370_pcie_gart_get_page_entry;
 	rdev->asic->gart.set_page = &rv370_pcie_gart_set_page;
 	return radeon_gart_table_vram_alloc(rdev);
 }
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 56b02927cd3..ee0868dec2f 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -3787,6 +3787,9 @@ int r600_irq_set(struct radeon_device *rdev)
 		WREG32(RV770_CG_THERMAL_INT, thermal_int);
 	}
 
+	/* posting read */
+	RREG32(R_000E50_SRBM_STATUS);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c
index b5c73df8e20..65a0c1c03c6 100644
--- a/drivers/gpu/drm/radeon/r600_dpm.c
+++ b/drivers/gpu/drm/radeon/r600_dpm.c
@@ -188,7 +188,7 @@ u32 r600_dpm_get_vrefresh(struct radeon_device *rdev)
 		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 			radeon_crtc = to_radeon_crtc(crtc);
 			if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) {
-				vrefresh = radeon_crtc->hw_mode.vrefresh;
+				vrefresh = drm_mode_vrefresh(&radeon_crtc->hw_mode);
 				break;
 			}
 		}
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index a9717b3fbf1..d6f0e40db81 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -245,6 +245,7 @@ bool radeon_get_bios(struct radeon_device *rdev);
  * Dummy page
  */
 struct radeon_dummy_page {
+	uint64_t	entry;
 	struct page	*page;
 	dma_addr_t	addr;
 };
@@ -626,6 +627,7 @@ struct radeon_gart {
 	unsigned			table_size;
 	struct page			**pages;
 	dma_addr_t			*pages_addr;
+	uint64_t			*pages_entry;
 	bool				ready;
 };
 
@@ -1542,6 +1544,7 @@ struct radeon_dpm {
 	int			new_active_crtc_count;
 	u32			current_active_crtcs;
 	int			current_active_crtc_count;
+	bool single_display;
 	struct radeon_dpm_dynamic_state dyn_state;
 	struct radeon_dpm_fan fan;
 	u32 tdp_limit;
@@ -1819,8 +1822,9 @@ struct radeon_asic {
 	/* gart */
 	struct {
 		void (*tlb_flush)(struct radeon_device *rdev);
+		uint64_t (*get_page_entry)(uint64_t addr, uint32_t flags);
 		void (*set_page)(struct radeon_device *rdev, unsigned i,
-				 uint64_t addr, uint32_t flags);
+				 uint64_t entry);
 	} gart;
 	struct {
 		int (*init)(struct radeon_device *rdev);
@@ -2818,7 +2822,8 @@ static inline void radeon_ring_write(struct radeon_ring *ring, uint32_t v)
 #define radeon_vga_set_state(rdev, state) (rdev)->asic->vga_set_state((rdev), (state))
 #define radeon_asic_reset(rdev) (rdev)->asic->asic_reset((rdev))
 #define radeon_gart_tlb_flush(rdev) (rdev)->asic->gart.tlb_flush((rdev))
-#define radeon_gart_set_page(rdev, i, p, f) (rdev)->asic->gart.set_page((rdev), (i), (p), (f))
+#define radeon_gart_get_page_entry(a, f) (rdev)->asic->gart.get_page_entry((a), (f))
+#define radeon_gart_set_page(rdev, i, e) (rdev)->asic->gart.set_page((rdev), (i), (e))
 #define radeon_asic_vm_init(rdev) (rdev)->asic->vm.init((rdev))
 #define radeon_asic_vm_fini(rdev) (rdev)->asic->vm.fini((rdev))
 #define radeon_asic_vm_copy_pages(rdev, ib, pe, src, count) ((rdev)->asic->vm.copy_pages((rdev), (ib), (pe), (src), (count)))
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 850de57069b..c34ceb8d3d2 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -159,11 +159,13 @@ void radeon_agp_disable(struct radeon_device *rdev)
 		DRM_INFO("Forcing AGP to PCIE mode\n");
 		rdev->flags |= RADEON_IS_PCIE;
 		rdev->asic->gart.tlb_flush = &rv370_pcie_gart_tlb_flush;
+		rdev->asic->gart.get_page_entry = &rv370_pcie_gart_get_page_entry;
 		rdev->asic->gart.set_page = &rv370_pcie_gart_set_page;
 	} else {
 		DRM_INFO("Forcing AGP to PCI mode\n");
 		rdev->flags |= RADEON_IS_PCI;
 		rdev->asic->gart.tlb_flush = &r100_pci_gart_tlb_flush;
+		rdev->asic->gart.get_page_entry = &r100_pci_gart_get_page_entry;
 		rdev->asic->gart.set_page = &r100_pci_gart_set_page;
 	}
 	rdev->mc.gtt_size = radeon_gart_size * 1024 * 1024;
@@ -199,6 +201,7 @@ static struct radeon_asic r100_asic = {
 	.mc_wait_for_idle = &r100_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &r100_pci_gart_tlb_flush,
+		.get_page_entry = &r100_pci_gart_get_page_entry,
 		.set_page = &r100_pci_gart_set_page,
 	},
 	.ring = {
@@ -265,6 +268,7 @@ static struct radeon_asic r200_asic = {
 	.mc_wait_for_idle = &r100_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &r100_pci_gart_tlb_flush,
+		.get_page_entry = &r100_pci_gart_get_page_entry,
 		.set_page = &r100_pci_gart_set_page,
 	},
 	.ring = {
@@ -333,6 +337,20 @@ static struct radeon_asic_ring r300_gfx_ring = {
 	.set_wptr = &r100_gfx_set_wptr,
 };
 
+static struct radeon_asic_ring rv515_gfx_ring = {
+	.ib_execute = &r100_ring_ib_execute,
+	.emit_fence = &r300_fence_ring_emit,
+	.emit_semaphore = &r100_semaphore_ring_emit,
+	.cs_parse = &r300_cs_parse,
+	.ring_start = &rv515_ring_start,
+	.ring_test = &r100_ring_test,
+	.ib_test = &r100_ib_test,
+	.is_lockup = &r100_gpu_is_lockup,
+	.get_rptr = &r100_gfx_get_rptr,
+	.get_wptr = &r100_gfx_get_wptr,
+	.set_wptr = &r100_gfx_set_wptr,
+};
+
 static struct radeon_asic r300_asic = {
 	.init = &r300_init,
 	.fini = &r300_fini,
@@ -345,6 +363,7 @@ static struct radeon_asic r300_asic = {
 	.mc_wait_for_idle = &r300_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &r100_pci_gart_tlb_flush,
+		.get_page_entry = &r100_pci_gart_get_page_entry,
 		.set_page = &r100_pci_gart_set_page,
 	},
 	.ring = {
@@ -411,6 +430,7 @@ static struct radeon_asic r300_asic_pcie = {
 	.mc_wait_for_idle = &r300_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rv370_pcie_gart_tlb_flush,
+		.get_page_entry = &rv370_pcie_gart_get_page_entry,
 		.set_page = &rv370_pcie_gart_set_page,
 	},
 	.ring = {
@@ -477,6 +497,7 @@ static struct radeon_asic r420_asic = {
 	.mc_wait_for_idle = &r300_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rv370_pcie_gart_tlb_flush,
+		.get_page_entry = &rv370_pcie_gart_get_page_entry,
 		.set_page = &rv370_pcie_gart_set_page,
 	},
 	.ring = {
@@ -543,6 +564,7 @@ static struct radeon_asic rs400_asic = {
 	.mc_wait_for_idle = &rs400_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rs400_gart_tlb_flush,
+		.get_page_entry = &rs400_gart_get_page_entry,
 		.set_page = &rs400_gart_set_page,
 	},
 	.ring = {
@@ -609,6 +631,7 @@ static struct radeon_asic rs600_asic = {
 	.mc_wait_for_idle = &rs600_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rs600_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -677,6 +700,7 @@ static struct radeon_asic rs690_asic = {
 	.mc_wait_for_idle = &rs690_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rs400_gart_tlb_flush,
+		.get_page_entry = &rs400_gart_get_page_entry,
 		.set_page = &rs400_gart_set_page,
 	},
 	.ring = {
@@ -745,10 +769,11 @@ static struct radeon_asic rv515_asic = {
 	.mc_wait_for_idle = &rv515_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rv370_pcie_gart_tlb_flush,
+		.get_page_entry = &rv370_pcie_gart_get_page_entry,
 		.set_page = &rv370_pcie_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = &r300_gfx_ring
+		[RADEON_RING_TYPE_GFX_INDEX] = &rv515_gfx_ring
 	},
 	.irq = {
 		.set = &rs600_irq_set,
@@ -811,10 +836,11 @@ static struct radeon_asic r520_asic = {
 	.mc_wait_for_idle = &r520_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rv370_pcie_gart_tlb_flush,
+		.get_page_entry = &rv370_pcie_gart_get_page_entry,
 		.set_page = &rv370_pcie_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = &r300_gfx_ring
+		[RADEON_RING_TYPE_GFX_INDEX] = &rv515_gfx_ring
 	},
 	.irq = {
 		.set = &rs600_irq_set,
@@ -905,6 +931,7 @@ static struct radeon_asic r600_asic = {
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &r600_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -990,6 +1017,7 @@ static struct radeon_asic rv6xx_asic = {
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &r600_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1081,6 +1109,7 @@ static struct radeon_asic rs780_asic = {
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &r600_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1161,7 +1190,7 @@ static struct radeon_asic rs780_asic = {
 static struct radeon_asic_ring rv770_uvd_ring = {
 	.ib_execute = &uvd_v1_0_ib_execute,
 	.emit_fence = &uvd_v2_2_fence_emit,
-	.emit_semaphore = &uvd_v1_0_semaphore_emit,
+	.emit_semaphore = &uvd_v2_2_semaphore_emit,
 	.cs_parse = &radeon_uvd_cs_parse,
 	.ring_test = &uvd_v1_0_ring_test,
 	.ib_test = &uvd_v1_0_ib_test,
@@ -1185,6 +1214,7 @@ static struct radeon_asic rv770_asic = {
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &r600_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1303,6 +1333,7 @@ static struct radeon_asic evergreen_asic = {
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &evergreen_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1395,6 +1426,7 @@ static struct radeon_asic sumo_asic = {
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &evergreen_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1486,6 +1518,7 @@ static struct radeon_asic btc_asic = {
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &evergreen_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1621,6 +1654,7 @@ static struct radeon_asic cayman_asic = {
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &cayman_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.vm = {
@@ -1724,6 +1758,7 @@ static struct radeon_asic trinity_asic = {
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &cayman_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.vm = {
@@ -1857,6 +1892,7 @@ static struct radeon_asic si_asic = {
 	.get_gpu_clock_counter = &si_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &si_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.vm = {
@@ -2018,6 +2054,7 @@ static struct radeon_asic ci_asic = {
 	.get_gpu_clock_counter = &cik_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &cik_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.vm = {
@@ -2125,6 +2162,7 @@ static struct radeon_asic kv_asic = {
 	.get_gpu_clock_counter = &cik_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &cik_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.vm = {
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index d8ace5b28a5..6dd68f66318 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -67,8 +67,9 @@ bool r100_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *cp);
 int r100_asic_reset(struct radeon_device *rdev);
 u32 r100_get_vblank_counter(struct radeon_device *rdev, int crtc);
 void r100_pci_gart_tlb_flush(struct radeon_device *rdev);
+uint64_t r100_pci_gart_get_page_entry(uint64_t addr, uint32_t flags);
 void r100_pci_gart_set_page(struct radeon_device *rdev, unsigned i,
-			    uint64_t addr, uint32_t flags);
+			    uint64_t entry);
 void r100_ring_start(struct radeon_device *rdev, struct radeon_ring *ring);
 int r100_irq_set(struct radeon_device *rdev);
 int r100_irq_process(struct radeon_device *rdev);
@@ -172,8 +173,9 @@ extern void r300_fence_ring_emit(struct radeon_device *rdev,
 				struct radeon_fence *fence);
 extern int r300_cs_parse(struct radeon_cs_parser *p);
 extern void rv370_pcie_gart_tlb_flush(struct radeon_device *rdev);
+extern uint64_t rv370_pcie_gart_get_page_entry(uint64_t addr, uint32_t flags);
 extern void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
-				     uint64_t addr, uint32_t flags);
+				     uint64_t entry);
 extern void rv370_set_pcie_lanes(struct radeon_device *rdev, int lanes);
 extern int rv370_get_pcie_lanes(struct radeon_device *rdev);
 extern void r300_set_reg_safe(struct radeon_device *rdev);
@@ -208,8 +210,9 @@ extern void rs400_fini(struct radeon_device *rdev);
 extern int rs400_suspend(struct radeon_device *rdev);
 extern int rs400_resume(struct radeon_device *rdev);
 void rs400_gart_tlb_flush(struct radeon_device *rdev);
+uint64_t rs400_gart_get_page_entry(uint64_t addr, uint32_t flags);
 void rs400_gart_set_page(struct radeon_device *rdev, unsigned i,
-			 uint64_t addr, uint32_t flags);
+			 uint64_t entry);
 uint32_t rs400_mc_rreg(struct radeon_device *rdev, uint32_t reg);
 void rs400_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 int rs400_gart_init(struct radeon_device *rdev);
@@ -232,8 +235,9 @@ int rs600_irq_process(struct radeon_device *rdev);
 void rs600_irq_disable(struct radeon_device *rdev);
 u32 rs600_get_vblank_counter(struct radeon_device *rdev, int crtc);
 void rs600_gart_tlb_flush(struct radeon_device *rdev);
+uint64_t rs600_gart_get_page_entry(uint64_t addr, uint32_t flags);
 void rs600_gart_set_page(struct radeon_device *rdev, unsigned i,
-			 uint64_t addr, uint32_t flags);
+			 uint64_t entry);
 uint32_t rs600_mc_rreg(struct radeon_device *rdev, uint32_t reg);
 void rs600_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 void rs600_bandwidth_update(struct radeon_device *rdev);
@@ -904,6 +908,10 @@ void uvd_v1_0_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib);
 int uvd_v2_2_resume(struct radeon_device *rdev);
 void uvd_v2_2_fence_emit(struct radeon_device *rdev,
 			 struct radeon_fence *fence);
+bool uvd_v2_2_semaphore_emit(struct radeon_device *rdev,
+			     struct radeon_ring *ring,
+			     struct radeon_semaphore *semaphore,
+			     bool emit_wait);
 
 /* uvd v3.1 */
 bool uvd_v3_1_semaphore_emit(struct radeon_device *rdev,
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index df69b92ba16..d79e892093b 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -3280,6 +3280,7 @@ int radeon_atom_get_voltage_evv(struct radeon_device *rdev,
 
 	args.in.ucVoltageType = VOLTAGE_TYPE_VDDC;
 	args.in.ucVoltageMode = ATOM_GET_VOLTAGE_EVV_VOLTAGE;
+	args.in.usVoltageLevel = cpu_to_le16(virtual_voltage_id);
 	args.in.ulSCLKFreq =
 		cpu_to_le32(rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[entry_id].clk);
 
diff --git a/drivers/gpu/drm/radeon/radeon_benchmark.c b/drivers/gpu/drm/radeon/radeon_benchmark.c
index 9e7f23dd14b..87d5fb21cb6 100644
--- a/drivers/gpu/drm/radeon/radeon_benchmark.c
+++ b/drivers/gpu/drm/radeon/radeon_benchmark.c
@@ -34,7 +34,8 @@
 
 static int radeon_benchmark_do_move(struct radeon_device *rdev, unsigned size,
 				    uint64_t saddr, uint64_t daddr,
-				    int flag, int n)
+				    int flag, int n,
+				    struct reservation_object *resv)
 {
 	unsigned long start_jiffies;
 	unsigned long end_jiffies;
@@ -47,12 +48,12 @@ static int radeon_benchmark_do_move(struct radeon_device *rdev, unsigned size,
 		case RADEON_BENCHMARK_COPY_DMA:
 			fence = radeon_copy_dma(rdev, saddr, daddr,
 						size / RADEON_GPU_PAGE_SIZE,
-						NULL);
+						resv);
 			break;
 		case RADEON_BENCHMARK_COPY_BLIT:
 			fence = radeon_copy_blit(rdev, saddr, daddr,
 						 size / RADEON_GPU_PAGE_SIZE,
-						 NULL);
+						 resv);
 			break;
 		default:
 			DRM_ERROR("Unknown copy method\n");
@@ -120,7 +121,8 @@ static void radeon_benchmark_move(struct radeon_device *rdev, unsigned size,
 
 	if (rdev->asic->copy.dma) {
 		time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
-						RADEON_BENCHMARK_COPY_DMA, n);
+						RADEON_BENCHMARK_COPY_DMA, n,
+						dobj->tbo.resv);
 		if (time < 0)
 			goto out_cleanup;
 		if (time > 0)
@@ -130,7 +132,8 @@ static void radeon_benchmark_move(struct radeon_device *rdev, unsigned size,
 
 	if (rdev->asic->copy.blit) {
 		time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
-						RADEON_BENCHMARK_COPY_BLIT, n);
+						RADEON_BENCHMARK_COPY_BLIT, n,
+						dobj->tbo.resv);
 		if (time < 0)
 			goto out_cleanup;
 		if (time > 0)
diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c
index 63ccb8fa799..d27e4ccb848 100644
--- a/drivers/gpu/drm/radeon/radeon_bios.c
+++ b/drivers/gpu/drm/radeon/radeon_bios.c
@@ -76,7 +76,7 @@ static bool igp_read_bios_from_vram(struct radeon_device *rdev)
 
 static bool radeon_read_bios(struct radeon_device *rdev)
 {
-	uint8_t __iomem *bios;
+	uint8_t __iomem *bios, val1, val2;
 	size_t size;
 
 	rdev->bios = NULL;
@@ -86,15 +86,19 @@ static bool radeon_read_bios(struct radeon_device *rdev)
 		return false;
 	}
 
-	if (size == 0 || bios[0] != 0x55 || bios[1] != 0xaa) {
+	val1 = readb(&bios[0]);
+	val2 = readb(&bios[1]);
+
+	if (size == 0 || val1 != 0x55 || val2 != 0xaa) {
 		pci_unmap_rom(rdev->pdev, bios);
 		return false;
 	}
-	rdev->bios = kmemdup(bios, size, GFP_KERNEL);
+	rdev->bios = kzalloc(size, GFP_KERNEL);
 	if (rdev->bios == NULL) {
 		pci_unmap_rom(rdev->pdev, bios);
 		return false;
 	}
+	memcpy_fromio(rdev->bios, bios, size);
 	pci_unmap_rom(rdev->pdev, bios);
 	return true;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 6f377de099f..a5b7f6f98f5 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -275,11 +275,13 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 	u32 ring = RADEON_CS_RING_GFX;
 	s32 priority = 0;
 
+	INIT_LIST_HEAD(&p->validated);
+
 	if (!cs->num_chunks) {
 		return 0;
 	}
+
 	/* get chunks */
-	INIT_LIST_HEAD(&p->validated);
 	p->idx = 0;
 	p->ib.sa_bo = NULL;
 	p->ib.semaphore = NULL;
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 995a8b1770d..5d54ab0fbe2 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -743,6 +743,8 @@ int radeon_dummy_page_init(struct radeon_device *rdev)
 		rdev->dummy_page.page = NULL;
 		return -ENOMEM;
 	}
+	rdev->dummy_page.entry = radeon_gart_get_page_entry(rdev->dummy_page.addr,
+							    RADEON_GART_PAGE_DUMMY);
 	return 0;
 }
 
@@ -1424,6 +1426,21 @@ int radeon_device_init(struct radeon_device *rdev,
 	if (r)
 		DRM_ERROR("ib ring test failed (%d).\n", r);
 
+	/*
+	 * Turks/Thames GPU will freeze whole laptop if DPM is not restarted
+	 * after the CP ring have chew one packet at least. Hence here we stop
+	 * and restart DPM after the radeon_ib_ring_tests().
+	 */
+	if (rdev->pm.dpm_enabled &&
+	    (rdev->pm.pm_method == PM_METHOD_DPM) &&
+	    (rdev->family == CHIP_TURKS) &&
+	    (rdev->flags & RADEON_IS_MOBILITY)) {
+		mutex_lock(&rdev->pm.mutex);
+		radeon_dpm_disable(rdev);
+		radeon_dpm_enable(rdev);
+		mutex_unlock(&rdev->pm.mutex);
+	}
+
 	if ((radeon_testing & 1)) {
 		if (rdev->accel_working)
 			radeon_test_moves(rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 00ead8c2758..2e1e9aa79ce 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -959,6 +959,9 @@ void radeon_compute_pll_avivo(struct radeon_pll *pll,
 	if (pll->flags & RADEON_PLL_USE_FRAC_FB_DIV &&
 	    pll->flags & RADEON_PLL_USE_REF_DIV)
 		ref_div_max = pll->reference_div;
+	else if (pll->flags & RADEON_PLL_PREFER_MINM_OVER_MAXP)
+		/* fix for problems on RS880 */
+		ref_div_max = min(pll->max_ref_div, 7u);
 	else
 		ref_div_max = pll->max_ref_div;
 
diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c
index 6b670b0bc47..3a297037cc1 100644
--- a/drivers/gpu/drm/radeon/radeon_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_encoders.c
@@ -179,9 +179,12 @@ static void radeon_encoder_add_backlight(struct radeon_encoder *radeon_encoder,
 		    (rdev->pdev->subsystem_vendor == 0x1734) &&
 		    (rdev->pdev->subsystem_device == 0x1107))
 			use_bl = false;
+/* Older PPC macs use on-GPU backlight controller */
+#ifndef CONFIG_PPC_PMAC
 		/* disable native backlight control on older asics */
 		else if (rdev->family < CHIP_R600)
 			use_bl = false;
+#endif
 		else
 			use_bl = true;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index 99516702528..8569afaba68 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -1029,37 +1029,59 @@ static inline bool radeon_test_signaled(struct radeon_fence *fence)
 	return test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->base.flags);
 }
 
+struct radeon_wait_cb {
+	struct fence_cb base;
+	struct task_struct *task;
+};
+
+static void
+radeon_fence_wait_cb(struct fence *fence, struct fence_cb *cb)
+{
+	struct radeon_wait_cb *wait =
+		container_of(cb, struct radeon_wait_cb, base);
+
+	wake_up_process(wait->task);
+}
+
 static signed long radeon_fence_default_wait(struct fence *f, bool intr,
 					     signed long t)
 {
 	struct radeon_fence *fence = to_radeon_fence(f);
 	struct radeon_device *rdev = fence->rdev;
-	bool signaled;
+	struct radeon_wait_cb cb;
 
-	fence_enable_sw_signaling(&fence->base);
+	cb.task = current;
 
-	/*
-	 * This function has to return -EDEADLK, but cannot hold
-	 * exclusive_lock during the wait because some callers
-	 * may already hold it. This means checking needs_reset without
-	 * lock, and not fiddling with any gpu internals.
-	 *
-	 * The callback installed with fence_enable_sw_signaling will
-	 * run before our wait_event_*timeout call, so we will see
-	 * both the signaled fence and the changes to needs_reset.
-	 */
+	if (fence_add_callback(f, &cb.base, radeon_fence_wait_cb))
+		return t;
+
+	while (t > 0) {
+		if (intr)
+			set_current_state(TASK_INTERRUPTIBLE);
+		else
+			set_current_state(TASK_UNINTERRUPTIBLE);
+
+		/*
+		 * radeon_test_signaled must be called after
+		 * set_current_state to prevent a race with wake_up_process
+		 */
+		if (radeon_test_signaled(fence))
+			break;
+
+		if (rdev->needs_reset) {
+			t = -EDEADLK;
+			break;
+		}
+
+		t = schedule_timeout(t);
+
+		if (t > 0 && intr && signal_pending(current))
+			t = -ERESTARTSYS;
+	}
+
+	__set_current_state(TASK_RUNNING);
+	fence_remove_callback(f, &cb.base);
 
-	if (intr)
-		t = wait_event_interruptible_timeout(rdev->fence_queue,
-			((signaled = radeon_test_signaled(fence)) ||
-			 rdev->needs_reset), t);
-	else
-		t = wait_event_timeout(rdev->fence_queue,
-			((signaled = radeon_test_signaled(fence)) ||
-			 rdev->needs_reset), t);
-
-	if (t > 0 && !signaled)
-		return -EDEADLK;
 	return t;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index 84146d5901a..c7be612b60c 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -165,6 +165,19 @@ int radeon_gart_table_vram_pin(struct radeon_device *rdev)
 		radeon_bo_unpin(rdev->gart.robj);
 	radeon_bo_unreserve(rdev->gart.robj);
 	rdev->gart.table_addr = gpu_addr;
+
+	if (!r) {
+		int i;
+
+		/* We might have dropped some GART table updates while it wasn't
+		 * mapped, restore all entries
+		 */
+		for (i = 0; i < rdev->gart.num_gpu_pages; i++)
+			radeon_gart_set_page(rdev, i, rdev->gart.pages_entry[i]);
+		mb();
+		radeon_gart_tlb_flush(rdev);
+	}
+
 	return r;
 }
 
@@ -228,7 +241,6 @@ void radeon_gart_unbind(struct radeon_device *rdev, unsigned offset,
 	unsigned t;
 	unsigned p;
 	int i, j;
-	u64 page_base;
 
 	if (!rdev->gart.ready) {
 		WARN(1, "trying to unbind memory from uninitialized GART !\n");
@@ -240,13 +252,12 @@ void radeon_gart_unbind(struct radeon_device *rdev, unsigned offset,
 		if (rdev->gart.pages[p]) {
 			rdev->gart.pages[p] = NULL;
 			rdev->gart.pages_addr[p] = rdev->dummy_page.addr;
-			page_base = rdev->gart.pages_addr[p];
 			for (j = 0; j < (PAGE_SIZE / RADEON_GPU_PAGE_SIZE); j++, t++) {
+				rdev->gart.pages_entry[t] = rdev->dummy_page.entry;
 				if (rdev->gart.ptr) {
-					radeon_gart_set_page(rdev, t, page_base,
-							     RADEON_GART_PAGE_DUMMY);
+					radeon_gart_set_page(rdev, t,
+							     rdev->dummy_page.entry);
 				}
-				page_base += RADEON_GPU_PAGE_SIZE;
 			}
 		}
 	}
@@ -274,7 +285,7 @@ int radeon_gart_bind(struct radeon_device *rdev, unsigned offset,
 {
 	unsigned t;
 	unsigned p;
-	uint64_t page_base;
+	uint64_t page_base, page_entry;
 	int i, j;
 
 	if (!rdev->gart.ready) {
@@ -287,12 +298,14 @@ int radeon_gart_bind(struct radeon_device *rdev, unsigned offset,
 	for (i = 0; i < pages; i++, p++) {
 		rdev->gart.pages_addr[p] = dma_addr[i];
 		rdev->gart.pages[p] = pagelist[i];
-		if (rdev->gart.ptr) {
-			page_base = rdev->gart.pages_addr[p];
-			for (j = 0; j < (PAGE_SIZE / RADEON_GPU_PAGE_SIZE); j++, t++) {
-				radeon_gart_set_page(rdev, t, page_base, flags);
-				page_base += RADEON_GPU_PAGE_SIZE;
+		page_base = dma_addr[i];
+		for (j = 0; j < (PAGE_SIZE / RADEON_GPU_PAGE_SIZE); j++, t++) {
+			page_entry = radeon_gart_get_page_entry(page_base, flags);
+			rdev->gart.pages_entry[t] = page_entry;
+			if (rdev->gart.ptr) {
+				radeon_gart_set_page(rdev, t, page_entry);
 			}
+			page_base += RADEON_GPU_PAGE_SIZE;
 		}
 	}
 	mb();
@@ -340,10 +353,17 @@ int radeon_gart_init(struct radeon_device *rdev)
 		radeon_gart_fini(rdev);
 		return -ENOMEM;
 	}
+	rdev->gart.pages_entry = vmalloc(sizeof(uint64_t) *
+					 rdev->gart.num_gpu_pages);
+	if (rdev->gart.pages_entry == NULL) {
+		radeon_gart_fini(rdev);
+		return -ENOMEM;
+	}
 	/* set GART entry to point to the dummy page by default */
-	for (i = 0; i < rdev->gart.num_cpu_pages; i++) {
+	for (i = 0; i < rdev->gart.num_cpu_pages; i++)
 		rdev->gart.pages_addr[i] = rdev->dummy_page.addr;
-	}
+	for (i = 0; i < rdev->gart.num_gpu_pages; i++)
+		rdev->gart.pages_entry[i] = rdev->dummy_page.entry;
 	return 0;
 }
 
@@ -356,15 +376,17 @@ int radeon_gart_init(struct radeon_device *rdev)
  */
 void radeon_gart_fini(struct radeon_device *rdev)
 {
-	if (rdev->gart.pages && rdev->gart.pages_addr && rdev->gart.ready) {
+	if (rdev->gart.ready) {
 		/* unbind pages */
 		radeon_gart_unbind(rdev, 0, rdev->gart.num_cpu_pages);
 	}
 	rdev->gart.ready = false;
 	vfree(rdev->gart.pages);
 	vfree(rdev->gart.pages_addr);
+	vfree(rdev->gart.pages_entry);
 	rdev->gart.pages = NULL;
 	rdev->gart.pages_addr = NULL;
+	rdev->gart.pages_entry = NULL;
 
 	radeon_dummy_page_fini(rdev);
 }
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index c194497aa58..b4abff67c63 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -146,7 +146,8 @@ int radeon_gem_object_open(struct drm_gem_object *obj, struct drm_file *file_pri
 	struct radeon_bo_va *bo_va;
 	int r;
 
-	if (rdev->family < CHIP_CAYMAN) {
+	if ((rdev->family < CHIP_CAYMAN) ||
+	    (!rdev->accel_working)) {
 		return 0;
 	}
 
@@ -176,7 +177,8 @@ void radeon_gem_object_close(struct drm_gem_object *obj,
 	struct radeon_bo_va *bo_va;
 	int r;
 
-	if (rdev->family < CHIP_CAYMAN) {
+	if ((rdev->family < CHIP_CAYMAN) ||
+	    (!rdev->accel_working)) {
 		return;
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index 00fc59762e0..bbcd754dc7d 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -79,10 +79,12 @@ static void radeon_hotplug_work_func(struct work_struct *work)
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct drm_connector *connector;
 
+	mutex_lock(&mode_config->mutex);
 	if (mode_config->num_connector) {
 		list_for_each_entry(connector, &mode_config->connector_list, head)
 			radeon_connector_hotplug(connector);
 	}
+	mutex_unlock(&mode_config->mutex);
 	/* Just fire off a uevent and let userspace tell us what to do */
 	drm_helper_hpd_irq_event(dev);
 }
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 03586763ee8..46bcd5d38a1 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -540,6 +540,9 @@ static int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		else
 			*value = 1;
 		break;
+	case RADEON_INFO_VA_UNMAP_WORKING:
+		*value = true;
+		break;
 	default:
 		DRM_DEBUG_KMS("Invalid request %d\n", info->request);
 		return -EINVAL;
@@ -598,14 +601,14 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 			return -ENOMEM;
 		}
 
-		vm = &fpriv->vm;
-		r = radeon_vm_init(rdev, vm);
-		if (r) {
-			kfree(fpriv);
-			return r;
-		}
-
 		if (rdev->accel_working) {
+			vm = &fpriv->vm;
+			r = radeon_vm_init(rdev, vm);
+			if (r) {
+				kfree(fpriv);
+				return r;
+			}
+
 			r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
 			if (r) {
 				radeon_vm_fini(rdev, vm);
@@ -663,9 +666,9 @@ void radeon_driver_postclose_kms(struct drm_device *dev,
 					radeon_vm_bo_rmv(rdev, vm->ib_bo_va);
 				radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
 			}
+			radeon_vm_fini(rdev, vm);
 		}
 
-		radeon_vm_fini(rdev, vm);
 		kfree(fpriv);
 		file_priv->driver_priv = NULL;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c
index a69bd441dd2..572b4dbec18 100644
--- a/drivers/gpu/drm/radeon/radeon_mn.c
+++ b/drivers/gpu/drm/radeon/radeon_mn.c
@@ -122,7 +122,6 @@ static void radeon_mn_invalidate_range_start(struct mmu_notifier *mn,
 	it = interval_tree_iter_first(&rmn->objects, start, end);
 	while (it) {
 		struct radeon_bo *bo;
-		struct fence *fence;
 		int r;
 
 		bo = container_of(it, struct radeon_bo, mn_it);
@@ -134,12 +133,10 @@ static void radeon_mn_invalidate_range_start(struct mmu_notifier *mn,
 			continue;
 		}
 
-		fence = reservation_object_get_excl(bo->tbo.resv);
-		if (fence) {
-			r = radeon_fence_wait((struct radeon_fence *)fence, false);
-			if (r)
-				DRM_ERROR("(%d) failed to wait for user bo\n", r);
-		}
+		r = reservation_object_wait_timeout_rcu(bo->tbo.resv, true,
+			false, MAX_SCHEDULE_TIMEOUT);
+		if (r)
+			DRM_ERROR("(%d) failed to wait for user bo\n", r);
 
 		radeon_ttm_placement_from_domain(bo, RADEON_GEM_DOMAIN_CPU);
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 4c0d786d5c7..2a7ba30165c 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -151,19 +151,6 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
 		else
 			rbo->placements[i].lpfn = 0;
 	}
-
-	/*
-	 * Use two-ended allocation depending on the buffer size to
-	 * improve fragmentation quality.
-	 * 512kb was measured as the most optimal number.
-	 */
-	if (!((rbo->flags & RADEON_GEM_CPU_ACCESS) &&
-	      (rbo->placements[i].flags & TTM_PL_FLAG_VRAM)) &&
-	    rbo->tbo.mem.size > 512 * 1024) {
-		for (i = 0; i < c; i++) {
-			rbo->placements[i].flags |= TTM_PL_FLAG_TOPDOWN;
-		}
-	}
 }
 
 int radeon_bo_create(struct radeon_device *rdev,
@@ -218,6 +205,18 @@ int radeon_bo_create(struct radeon_device *rdev,
 	 * See https://bugs.freedesktop.org/show_bug.cgi?id=84627
 	 */
 	bo->flags &= ~RADEON_GEM_GTT_WC;
+#elif defined(CONFIG_X86) && !defined(CONFIG_X86_PAT)
+	/* Don't try to enable write-combining when it can't work, or things
+	 * may be slow
+	 * See https://bugs.freedesktop.org/show_bug.cgi?id=88758
+	 */
+
+#warning Please enable CONFIG_MTRR and CONFIG_X86_PAT for better performance \
+	 thanks to write-combining
+
+	DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for "
+		      "better performance thanks to write-combining\n");
+	bo->flags &= ~RADEON_GEM_GTT_WC;
 #endif
 
 	radeon_ttm_placement_from_domain(bo, domain);
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 32522cc940a..1d94b542cd8 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -704,12 +704,8 @@ static void radeon_dpm_thermal_work_handler(struct work_struct *work)
 	radeon_pm_compute_clocks(rdev);
 }
 
-static struct radeon_ps *radeon_dpm_pick_power_state(struct radeon_device *rdev,
-						     enum radeon_pm_state_type dpm_state)
+static bool radeon_dpm_single_display(struct radeon_device *rdev)
 {
-	int i;
-	struct radeon_ps *ps;
-	u32 ui_class;
 	bool single_display = (rdev->pm.dpm.new_active_crtc_count < 2) ?
 		true : false;
 
@@ -719,6 +715,17 @@ static struct radeon_ps *radeon_dpm_pick_power_state(struct radeon_device *rdev,
 			single_display = false;
 	}
 
+	return single_display;
+}
+
+static struct radeon_ps *radeon_dpm_pick_power_state(struct radeon_device *rdev,
+						     enum radeon_pm_state_type dpm_state)
+{
+	int i;
+	struct radeon_ps *ps;
+	u32 ui_class;
+	bool single_display = radeon_dpm_single_display(rdev);
+
 	/* certain older asics have a separare 3D performance state,
 	 * so try that first if the user selected performance
 	 */
@@ -844,6 +851,7 @@ static void radeon_dpm_change_power_state_locked(struct radeon_device *rdev)
 	struct radeon_ps *ps;
 	enum radeon_pm_state_type dpm_state;
 	int ret;
+	bool single_display = radeon_dpm_single_display(rdev);
 
 	/* if dpm init failed */
 	if (!rdev->pm.dpm_enabled)
@@ -868,6 +876,9 @@ static void radeon_dpm_change_power_state_locked(struct radeon_device *rdev)
 		/* vce just modifies an existing state so force a change */
 		if (ps->vce_active != rdev->pm.dpm.vce_active)
 			goto force;
+		/* user has made a display change (such as timing) */
+		if (rdev->pm.dpm.single_display != single_display)
+			goto force;
 		if ((rdev->family < CHIP_BARTS) || (rdev->flags & RADEON_IS_IGP)) {
 			/* for pre-BTC and APUs if the num crtcs changed but state is the same,
 			 * all we need to do is update the display configuration.
@@ -930,6 +941,7 @@ force:
 
 	rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs;
 	rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count;
+	rdev->pm.dpm.single_display = single_display;
 
 	/* wait for the rings to drain */
 	for (i = 0; i < RADEON_NUM_RINGS; i++) {
@@ -1287,8 +1299,39 @@ dpm_failed:
 	return ret;
 }
 
+struct radeon_dpm_quirk {
+	u32 chip_vendor;
+	u32 chip_device;
+	u32 subsys_vendor;
+	u32 subsys_device;
+};
+
+/* cards with dpm stability problems */
+static struct radeon_dpm_quirk radeon_dpm_quirk_list[] = {
+	/* TURKS - https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1386534 */
+	{ PCI_VENDOR_ID_ATI, 0x6759, 0x1682, 0x3195 },
+	/* TURKS - https://bugzilla.kernel.org/show_bug.cgi?id=83731 */
+	{ PCI_VENDOR_ID_ATI, 0x6840, 0x1179, 0xfb81 },
+	{ 0, 0, 0, 0 },
+};
+
 int radeon_pm_init(struct radeon_device *rdev)
 {
+	struct radeon_dpm_quirk *p = radeon_dpm_quirk_list;
+	bool disable_dpm = false;
+
+	/* Apply dpm quirks */
+	while (p && p->chip_device != 0) {
+		if (rdev->pdev->vendor == p->chip_vendor &&
+		    rdev->pdev->device == p->chip_device &&
+		    rdev->pdev->subsystem_vendor == p->subsys_vendor &&
+		    rdev->pdev->subsystem_device == p->subsys_device) {
+			disable_dpm = true;
+			break;
+		}
+		++p;
+	}
+
 	/* enable dpm on rv6xx+ */
 	switch (rdev->family) {
 	case CHIP_RV610:
@@ -1344,6 +1387,8 @@ int radeon_pm_init(struct radeon_device *rdev)
 			 (!(rdev->flags & RADEON_IS_IGP)) &&
 			 (!rdev->smc_fw))
 			rdev->pm.pm_method = PM_METHOD_PROFILE;
+		else if (disable_dpm && (radeon_dpm == -1))
+			rdev->pm.pm_method = PM_METHOD_PROFILE;
 		else if (radeon_dpm == 0)
 			rdev->pm.pm_method = PM_METHOD_PROFILE;
 		else
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index 07b506b4100..791818165c7 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -119,11 +119,11 @@ static void radeon_do_test_moves(struct radeon_device *rdev, int flag)
 		if (ring == R600_RING_TYPE_DMA_INDEX)
 			fence = radeon_copy_dma(rdev, gtt_addr, vram_addr,
 						size / RADEON_GPU_PAGE_SIZE,
-						NULL);
+						vram_obj->tbo.resv);
 		else
 			fence = radeon_copy_blit(rdev, gtt_addr, vram_addr,
 						 size / RADEON_GPU_PAGE_SIZE,
-						 NULL);
+						 vram_obj->tbo.resv);
 		if (IS_ERR(fence)) {
 			DRM_ERROR("Failed GTT->VRAM copy %d\n", i);
 			r = PTR_ERR(fence);
@@ -170,11 +170,11 @@ static void radeon_do_test_moves(struct radeon_device *rdev, int flag)
 		if (ring == R600_RING_TYPE_DMA_INDEX)
 			fence = radeon_copy_dma(rdev, vram_addr, gtt_addr,
 						size / RADEON_GPU_PAGE_SIZE,
-						NULL);
+						vram_obj->tbo.resv);
 		else
 			fence = radeon_copy_blit(rdev, vram_addr, gtt_addr,
 						 size / RADEON_GPU_PAGE_SIZE,
-						 NULL);
+						 vram_obj->tbo.resv);
 		if (IS_ERR(fence)) {
 			DRM_ERROR("Failed VRAM->GTT copy %d\n", i);
 			r = PTR_ERR(fence);
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 8624979afb6..13f69472e71 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -196,7 +196,7 @@ static void radeon_evict_flags(struct ttm_buffer_object *bo,
 	rbo = container_of(bo, struct radeon_bo, tbo);
 	switch (bo->mem.mem_type) {
 	case TTM_PL_VRAM:
-		if (rbo->rdev->ring[RADEON_RING_TYPE_GFX_INDEX].ready == false)
+		if (rbo->rdev->ring[radeon_copy_ring_index(rbo->rdev)].ready == false)
 			radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_CPU);
 		else
 			radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT);
@@ -568,19 +568,21 @@ static void radeon_ttm_tt_unpin_userptr(struct ttm_tt *ttm)
 {
 	struct radeon_device *rdev = radeon_get_rdev(ttm->bdev);
 	struct radeon_ttm_tt *gtt = (void *)ttm;
-	struct scatterlist *sg;
-	int i;
+	struct sg_page_iter sg_iter;
 
 	int write = !(gtt->userflags & RADEON_GEM_USERPTR_READONLY);
 	enum dma_data_direction direction = write ?
 		DMA_BIDIRECTIONAL : DMA_TO_DEVICE;
 
+	/* double check that we don't free the table twice */
+	if (!ttm->sg->sgl)
+		return;
+
 	/* free the sg table and pages again */
 	dma_unmap_sg(rdev->dev, ttm->sg->sgl, ttm->sg->nents, direction);
 
-	for_each_sg(ttm->sg->sgl, sg, ttm->sg->nents, i) {
-		struct page *page = sg_page(sg);
-
+	for_each_sg_page(ttm->sg->sgl, &sg_iter, ttm->sg->nents, 0) {
+		struct page *page = sg_page_iter_page(&sg_iter);
 		if (!(gtt->userflags & RADEON_GEM_USERPTR_READONLY))
 			set_page_dirty(page);
 
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 11b66246925..db6536f722f 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -396,6 +396,29 @@ static int radeon_uvd_cs_msg_decode(uint32_t *msg, unsigned buf_sizes[])
 	return 0;
 }
 
+static int radeon_uvd_validate_codec(struct radeon_cs_parser *p,
+				     unsigned stream_type)
+{
+	switch (stream_type) {
+	case 0: /* H264 */
+	case 1: /* VC1 */
+		/* always supported */
+		return 0;
+
+	case 3: /* MPEG2 */
+	case 4: /* MPEG4 */
+		/* only since UVD 3 */
+		if (p->rdev->family >= CHIP_PALM)
+			return 0;
+
+		/* fall through */
+	default:
+		DRM_ERROR("UVD codec not supported by hardware %d!\n",
+			  stream_type);
+		return -EINVAL;
+	}
+}
+
 static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo,
 			     unsigned offset, unsigned buf_sizes[])
 {
@@ -436,50 +459,70 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo,
 		return -EINVAL;
 	}
 
-	if (msg_type == 1) {
-		/* it's a decode msg, calc buffer sizes */
-		r = radeon_uvd_cs_msg_decode(msg, buf_sizes);
-		/* calc image size (width * height) */
-		img_size = msg[6] * msg[7];
+	switch (msg_type) {
+	case 0:
+		/* it's a create msg, calc image size (width * height) */
+		img_size = msg[7] * msg[8];
+
+		r = radeon_uvd_validate_codec(p, msg[4]);
+		radeon_bo_kunmap(bo);
+		if (r)
+			return r;
+
+		/* try to alloc a new handle */
+		for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
+			if (atomic_read(&p->rdev->uvd.handles[i]) == handle) {
+				DRM_ERROR("Handle 0x%x already in use!\n", handle);
+				return -EINVAL;
+			}
+
+			if (!atomic_cmpxchg(&p->rdev->uvd.handles[i], 0, handle)) {
+				p->rdev->uvd.filp[i] = p->filp;
+				p->rdev->uvd.img_size[i] = img_size;
+				return 0;
+			}
+		}
+
+		DRM_ERROR("No more free UVD handles!\n");
+		return -EINVAL;
+
+	case 1:
+		/* it's a decode msg, validate codec and calc buffer sizes */
+		r = radeon_uvd_validate_codec(p, msg[4]);
+		if (!r)
+			r = radeon_uvd_cs_msg_decode(msg, buf_sizes);
 		radeon_bo_kunmap(bo);
 		if (r)
 			return r;
 
-	} else if (msg_type == 2) {
+		/* validate the handle */
+		for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
+			if (atomic_read(&p->rdev->uvd.handles[i]) == handle) {
+				if (p->rdev->uvd.filp[i] != p->filp) {
+					DRM_ERROR("UVD handle collision detected!\n");
+					return -EINVAL;
+				}
+				return 0;
+			}
+		}
+
+		DRM_ERROR("Invalid UVD handle 0x%x!\n", handle);
+		return -ENOENT;
+
+	case 2:
 		/* it's a destroy msg, free the handle */
 		for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i)
 			atomic_cmpxchg(&p->rdev->uvd.handles[i], handle, 0);
 		radeon_bo_kunmap(bo);
 		return 0;
-	} else {
-		/* it's a create msg, calc image size (width * height) */
-		img_size = msg[7] * msg[8];
-		radeon_bo_kunmap(bo);
 
-		if (msg_type != 0) {
-			DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
-			return -EINVAL;
-		}
-
-		/* it's a create msg, no special handling needed */
-	}
-
-	/* create or decode, validate the handle */
-	for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
-		if (atomic_read(&p->rdev->uvd.handles[i]) == handle)
-			return 0;
-	}
+	default:
 
-	/* handle not found try to alloc a new one */
-	for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
-		if (!atomic_cmpxchg(&p->rdev->uvd.handles[i], 0, handle)) {
-			p->rdev->uvd.filp[i] = p->filp;
-			p->rdev->uvd.img_size[i] = img_size;
-			return 0;
-		}
+		DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
+		return -EINVAL;
 	}
 
-	DRM_ERROR("No more free UVD handles!\n");
+	BUG();
 	return -EINVAL;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_vce.c b/drivers/gpu/drm/radeon/radeon_vce.c
index 9e85757d559..1c0022a4948 100644
--- a/drivers/gpu/drm/radeon/radeon_vce.c
+++ b/drivers/gpu/drm/radeon/radeon_vce.c
@@ -493,18 +493,27 @@ int radeon_vce_cs_reloc(struct radeon_cs_parser *p, int lo, int hi,
  *
  * @p: parser context
  * @handle: handle to validate
+ * @allocated: allocated a new handle?
  *
  * Validates the handle and return the found session index or -EINVAL
  * we we don't have another free session index.
  */
-int radeon_vce_validate_handle(struct radeon_cs_parser *p, uint32_t handle)
+static int radeon_vce_validate_handle(struct radeon_cs_parser *p,
+				      uint32_t handle, bool *allocated)
 {
 	unsigned i;
 
+	*allocated = false;
+
 	/* validate the handle */
 	for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i) {
-		if (atomic_read(&p->rdev->vce.handles[i]) == handle)
+		if (atomic_read(&p->rdev->vce.handles[i]) == handle) {
+			if (p->rdev->vce.filp[i] != p->filp) {
+				DRM_ERROR("VCE handle collision detected!\n");
+				return -EINVAL;
+			}
 			return i;
+		}
 	}
 
 	/* handle not found try to alloc a new one */
@@ -512,6 +521,7 @@ int radeon_vce_validate_handle(struct radeon_cs_parser *p, uint32_t handle)
 		if (!atomic_cmpxchg(&p->rdev->vce.handles[i], 0, handle)) {
 			p->rdev->vce.filp[i] = p->filp;
 			p->rdev->vce.img_size[i] = 0;
+			*allocated = true;
 			return i;
 		}
 	}
@@ -529,10 +539,10 @@ int radeon_vce_validate_handle(struct radeon_cs_parser *p, uint32_t handle)
 int radeon_vce_cs_parse(struct radeon_cs_parser *p)
 {
 	int session_idx = -1;
-	bool destroyed = false;
+	bool destroyed = false, created = false, allocated = false;
 	uint32_t tmp, handle = 0;
 	uint32_t *size = &tmp;
-	int i, r;
+	int i, r = 0;
 
 	while (p->idx < p->chunks[p->chunk_ib_idx].length_dw) {
 		uint32_t len = radeon_get_ib_value(p, p->idx);
@@ -540,18 +550,21 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p)
 
 		if ((len < 8) || (len & 3)) {
 			DRM_ERROR("invalid VCE command length (%d)!\n", len);
-                	return -EINVAL;
+			r = -EINVAL;
+			goto out;
 		}
 
 		if (destroyed) {
 			DRM_ERROR("No other command allowed after destroy!\n");
-			return -EINVAL;
+			r = -EINVAL;
+			goto out;
 		}
 
 		switch (cmd) {
 		case 0x00000001: // session
 			handle = radeon_get_ib_value(p, p->idx + 2);
-			session_idx = radeon_vce_validate_handle(p, handle);
+			session_idx = radeon_vce_validate_handle(p, handle,
+								 &allocated);
 			if (session_idx < 0)
 				return session_idx;
 			size = &p->rdev->vce.img_size[session_idx];
@@ -561,6 +574,13 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p)
 			break;
 
 		case 0x01000001: // create
+			created = true;
+			if (!allocated) {
+				DRM_ERROR("Handle already in use!\n");
+				r = -EINVAL;
+				goto out;
+			}
+
 			*size = radeon_get_ib_value(p, p->idx + 8) *
 				radeon_get_ib_value(p, p->idx + 10) *
 				8 * 3 / 2;
@@ -577,12 +597,12 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p)
 			r = radeon_vce_cs_reloc(p, p->idx + 10, p->idx + 9,
 						*size);
 			if (r)
-				return r;
+				goto out;
 
 			r = radeon_vce_cs_reloc(p, p->idx + 12, p->idx + 11,
 						*size / 3);
 			if (r)
-				return r;
+				goto out;
 			break;
 
 		case 0x02000001: // destroy
@@ -593,7 +613,7 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p)
 			r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2,
 						*size * 2);
 			if (r)
-				return r;
+				goto out;
 			break;
 
 		case 0x05000004: // video bitstream buffer
@@ -601,36 +621,47 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p)
 			r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2,
 						tmp);
 			if (r)
-				return r;
+				goto out;
 			break;
 
 		case 0x05000005: // feedback buffer
 			r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2,
 						4096);
 			if (r)
-				return r;
+				goto out;
 			break;
 
 		default:
 			DRM_ERROR("invalid VCE command (0x%x)!\n", cmd);
-			return -EINVAL;
+			r = -EINVAL;
+			goto out;
 		}
 
 		if (session_idx == -1) {
 			DRM_ERROR("no session command at start of IB\n");
-			return -EINVAL;
+			r = -EINVAL;
+			goto out;
 		}
 
 		p->idx += len / 4;
 	}
 
-	if (destroyed) {
-		/* IB contains a destroy msg, free the handle */
+	if (allocated && !created) {
+		DRM_ERROR("New session without create command!\n");
+		r = -ENOENT;
+	}
+
+out:
+	if ((!r && destroyed) || (r && allocated)) {
+		/*
+		 * IB contains a destroy msg or we have allocated an
+		 * handle and got an error, anyway free the handle
+		 */
 		for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i)
 			atomic_cmpxchg(&p->rdev->vce.handles[i], handle, 0);
 	}
 
-	return 0;
+	return r;
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index dfde266529e..190eb5bee4e 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -481,6 +481,23 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev,
 	}
 
 	mutex_lock(&vm->mutex);
+	soffset /= RADEON_GPU_PAGE_SIZE;
+	eoffset /= RADEON_GPU_PAGE_SIZE;
+	if (soffset || eoffset) {
+		struct interval_tree_node *it;
+		it = interval_tree_iter_first(&vm->va, soffset, eoffset - 1);
+		if (it && it != &bo_va->it) {
+			struct radeon_bo_va *tmp;
+			tmp = container_of(it, struct radeon_bo_va, it);
+			/* bo and tmp overlap, invalid offset */
+			dev_err(rdev->dev, "bo %p va 0x%010Lx conflict with "
+				"(bo %p 0x%010lx 0x%010lx)\n", bo_va->bo,
+				soffset, tmp->bo, tmp->it.start, tmp->it.last);
+			mutex_unlock(&vm->mutex);
+			return -EINVAL;
+		}
+	}
+
 	if (bo_va->it.start || bo_va->it.last) {
 		if (bo_va->addr) {
 			/* add a clone of the bo_va to clear the old address */
@@ -496,6 +513,8 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev,
 			tmp->addr = bo_va->addr;
 			tmp->bo = radeon_bo_ref(bo_va->bo);
 			list_add(&tmp->vm_status, &vm->freed);
+
+			bo_va->addr = 0;
 		}
 
 		interval_tree_remove(&bo_va->it, &vm->va);
@@ -503,21 +522,7 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev,
 		bo_va->it.last = 0;
 	}
 
-	soffset /= RADEON_GPU_PAGE_SIZE;
-	eoffset /= RADEON_GPU_PAGE_SIZE;
 	if (soffset || eoffset) {
-		struct interval_tree_node *it;
-		it = interval_tree_iter_first(&vm->va, soffset, eoffset - 1);
-		if (it) {
-			struct radeon_bo_va *tmp;
-			tmp = container_of(it, struct radeon_bo_va, it);
-			/* bo and tmp overlap, invalid offset */
-			dev_err(rdev->dev, "bo %p va 0x%010Lx conflict with "
-				"(bo %p 0x%010lx 0x%010lx)\n", bo_va->bo,
-				soffset, tmp->bo, tmp->it.start, tmp->it.last);
-			mutex_unlock(&vm->mutex);
-			return -EINVAL;
-		}
 		bo_va->it.start = soffset;
 		bo_va->it.last = eoffset - 1;
 		interval_tree_insert(&bo_va->it, &vm->va);
@@ -753,9 +758,11 @@ static void radeon_vm_frag_ptes(struct radeon_device *rdev,
 	 */
 
 	/* NI is optimized for 256KB fragments, SI and newer for 64KB */
-	uint64_t frag_flags = rdev->family == CHIP_CAYMAN ?
+	uint64_t frag_flags = ((rdev->family == CHIP_CAYMAN) ||
+			       (rdev->family == CHIP_ARUBA)) ?
 			R600_PTE_FRAG_256KB : R600_PTE_FRAG_64KB;
-	uint64_t frag_align = rdev->family == CHIP_CAYMAN ? 0x200 : 0x80;
+	uint64_t frag_align = ((rdev->family == CHIP_CAYMAN) ||
+			       (rdev->family == CHIP_ARUBA)) ? 0x200 : 0x80;
 
 	uint64_t frag_start = ALIGN(pe_start, frag_align);
 	uint64_t frag_end = pe_end & ~(frag_align - 1);
@@ -1053,7 +1060,8 @@ void radeon_vm_bo_rmv(struct radeon_device *rdev,
 	list_del(&bo_va->bo_list);
 
 	mutex_lock(&vm->mutex);
-	interval_tree_remove(&bo_va->it, &vm->va);
+	if (bo_va->it.start || bo_va->it.last)
+		interval_tree_remove(&bo_va->it, &vm->va);
 	list_del(&bo_va->vm_status);
 
 	if (bo_va->addr) {
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index c5799f16aa4..34e3235f41d 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -212,11 +212,9 @@ void rs400_gart_fini(struct radeon_device *rdev)
 #define RS400_PTE_WRITEABLE (1 << 2)
 #define RS400_PTE_READABLE  (1 << 3)
 
-void rs400_gart_set_page(struct radeon_device *rdev, unsigned i,
-			 uint64_t addr, uint32_t flags)
+uint64_t rs400_gart_get_page_entry(uint64_t addr, uint32_t flags)
 {
 	uint32_t entry;
-	u32 *gtt = rdev->gart.ptr;
 
 	entry = (lower_32_bits(addr) & PAGE_MASK) |
 		((upper_32_bits(addr) & 0xff) << 4);
@@ -226,8 +224,14 @@ void rs400_gart_set_page(struct radeon_device *rdev, unsigned i,
 		entry |= RS400_PTE_WRITEABLE;
 	if (!(flags & RADEON_GART_PAGE_SNOOP))
 		entry |= RS400_PTE_UNSNOOPED;
-	entry = cpu_to_le32(entry);
-	gtt[i] = entry;
+	return entry;
+}
+
+void rs400_gart_set_page(struct radeon_device *rdev, unsigned i,
+			 uint64_t entry)
+{
+	u32 *gtt = rdev->gart.ptr;
+	gtt[i] = cpu_to_le32(lower_32_bits(entry));
 }
 
 int rs400_mc_wait_for_idle(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 9acb1c3c005..039660662ee 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -625,11 +625,8 @@ static void rs600_gart_fini(struct radeon_device *rdev)
 	radeon_gart_table_vram_free(rdev);
 }
 
-void rs600_gart_set_page(struct radeon_device *rdev, unsigned i,
-			 uint64_t addr, uint32_t flags)
+uint64_t rs600_gart_get_page_entry(uint64_t addr, uint32_t flags)
 {
-	void __iomem *ptr = (void *)rdev->gart.ptr;
-
 	addr = addr & 0xFFFFFFFFFFFFF000ULL;
 	addr |= R600_PTE_SYSTEM;
 	if (flags & RADEON_GART_PAGE_VALID)
@@ -640,7 +637,14 @@ void rs600_gart_set_page(struct radeon_device *rdev, unsigned i,
 		addr |= R600_PTE_WRITEABLE;
 	if (flags & RADEON_GART_PAGE_SNOOP)
 		addr |= R600_PTE_SNOOPED;
-	writeq(addr, ptr + (i * 8));
+	return addr;
+}
+
+void rs600_gart_set_page(struct radeon_device *rdev, unsigned i,
+			 uint64_t entry)
+{
+	void __iomem *ptr = (void *)rdev->gart.ptr;
+	writeq(entry, ptr + (i * 8));
 }
 
 int rs600_irq_set(struct radeon_device *rdev)
@@ -689,6 +693,10 @@ int rs600_irq_set(struct radeon_device *rdev)
 	WREG32(R_007D18_DC_HOT_PLUG_DETECT2_INT_CONTROL, hpd2);
 	if (ASIC_IS_DCE2(rdev))
 		WREG32(R_007408_HDMI0_AUDIO_PACKET_CONTROL, hdmi0);
+
+	/* posting read */
+	RREG32(R_000040_GEN_INT_CNTL);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/rv770d.h b/drivers/gpu/drm/radeon/rv770d.h
index 3cf1e292154..9ef2064b1c9 100644
--- a/drivers/gpu/drm/radeon/rv770d.h
+++ b/drivers/gpu/drm/radeon/rv770d.h
@@ -989,6 +989,9 @@
 			 ((n) & 0x3FFF) << 16)
 
 /* UVD */
+#define UVD_SEMA_ADDR_LOW				0xef00
+#define UVD_SEMA_ADDR_HIGH				0xef04
+#define UVD_SEMA_CMD					0xef08
 #define UVD_GPCOM_VCPU_CMD				0xef0c
 #define UVD_GPCOM_VCPU_DATA0				0xef10
 #define UVD_GPCOM_VCPU_DATA1				0xef14
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 7d5083dc4ac..3ad2e07fb48 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -4285,7 +4285,7 @@ static int si_pcie_gart_enable(struct radeon_device *rdev)
 	/* empty context1-15 */
 	/* set vm size, must be a multiple of 4 */
 	WREG32(VM_CONTEXT1_PAGE_TABLE_START_ADDR, 0);
-	WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn);
+	WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn - 1);
 	/* Assign the pt base to something valid for now; the pts used for
 	 * the VMs are determined by the application and setup and assigned
 	 * on the fly in the vm part of radeon_gart.c
@@ -6192,6 +6192,9 @@ int si_irq_set(struct radeon_device *rdev)
 
 	WREG32(CG_THERMAL_INT, thermal_int);
 
+	/* posting read */
+	RREG32(SRBM_STATUS);
+
 	return 0;
 }
 
@@ -7112,8 +7115,7 @@ int si_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk)
 	WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_BYPASS_EN_MASK, ~UPLL_BYPASS_EN_MASK);
 
 	if (!vclk || !dclk) {
-		/* keep the Bypass mode, put PLL to sleep */
-		WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_SLEEP_MASK, ~UPLL_SLEEP_MASK);
+		/* keep the Bypass mode */
 		return 0;
 	}
 
@@ -7129,8 +7131,7 @@ int si_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk)
 	/* set VCO_MODE to 1 */
 	WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_VCO_MODE_MASK, ~UPLL_VCO_MODE_MASK);
 
-	/* toggle UPLL_SLEEP to 1 then back to 0 */
-	WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_SLEEP_MASK, ~UPLL_SLEEP_MASK);
+	/* disable sleep mode */
 	WREG32_P(CG_UPLL_FUNC_CNTL, 0, ~UPLL_SLEEP_MASK);
 
 	/* deassert UPLL_RESET */
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 676e6c2ba90..c6ad8a9f145 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2908,6 +2908,24 @@ static int si_init_smc_spll_table(struct radeon_device *rdev)
 	return ret;
 }
 
+struct si_dpm_quirk {
+	u32 chip_vendor;
+	u32 chip_device;
+	u32 subsys_vendor;
+	u32 subsys_device;
+	u32 max_sclk;
+	u32 max_mclk;
+};
+
+/* cards with dpm stability problems */
+static struct si_dpm_quirk si_dpm_quirk_list[] = {
+	/* PITCAIRN - https://bugs.freedesktop.org/show_bug.cgi?id=76490 */
+	{ PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 },
+	{ PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 },
+	{ PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 },
+	{ 0, 0, 0, 0 },
+};
+
 static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 					struct radeon_ps *rps)
 {
@@ -2918,7 +2936,22 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 	u32 mclk, sclk;
 	u16 vddc, vddci;
 	u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
+	u32 max_sclk = 0, max_mclk = 0;
 	int i;
+	struct si_dpm_quirk *p = si_dpm_quirk_list;
+
+	/* Apply dpm quirks */
+	while (p && p->chip_device != 0) {
+		if (rdev->pdev->vendor == p->chip_vendor &&
+		    rdev->pdev->device == p->chip_device &&
+		    rdev->pdev->subsystem_vendor == p->subsys_vendor &&
+		    rdev->pdev->subsystem_device == p->subsys_device) {
+			max_sclk = p->max_sclk;
+			max_mclk = p->max_mclk;
+			break;
+		}
+		++p;
+	}
 
 	if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
 	    ni_dpm_vblank_too_short(rdev))
@@ -2972,6 +3005,14 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 			if (ps->performance_levels[i].mclk > max_mclk_vddc)
 				ps->performance_levels[i].mclk = max_mclk_vddc;
 		}
+		if (max_mclk) {
+			if (ps->performance_levels[i].mclk > max_mclk)
+				ps->performance_levels[i].mclk = max_mclk;
+		}
+		if (max_sclk) {
+			if (ps->performance_levels[i].sclk > max_sclk)
+				ps->performance_levels[i].sclk = max_sclk;
+		}
 	}
 
 	/* XXX validate the min clocks required for display */
diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c
index e72b3cb5935..c6b1cbca47f 100644
--- a/drivers/gpu/drm/radeon/uvd_v1_0.c
+++ b/drivers/gpu/drm/radeon/uvd_v1_0.c
@@ -466,18 +466,8 @@ bool uvd_v1_0_semaphore_emit(struct radeon_device *rdev,
 			     struct radeon_semaphore *semaphore,
 			     bool emit_wait)
 {
-	uint64_t addr = semaphore->gpu_addr;
-
-	radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_LOW, 0));
-	radeon_ring_write(ring, (addr >> 3) & 0x000FFFFF);
-
-	radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_HIGH, 0));
-	radeon_ring_write(ring, (addr >> 23) & 0x000FFFFF);
-
-	radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0));
-	radeon_ring_write(ring, emit_wait ? 1 : 0);
-
-	return true;
+	/* disable semaphores for UVD V1 hardware */
+	return false;
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/uvd_v2_2.c b/drivers/gpu/drm/radeon/uvd_v2_2.c
index 89193519f8a..7ed778cec7c 100644
--- a/drivers/gpu/drm/radeon/uvd_v2_2.c
+++ b/drivers/gpu/drm/radeon/uvd_v2_2.c
@@ -60,6 +60,35 @@ void uvd_v2_2_fence_emit(struct radeon_device *rdev,
 }
 
 /**
+ * uvd_v2_2_semaphore_emit - emit semaphore command
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring pointer
+ * @semaphore: semaphore to emit commands for
+ * @emit_wait: true if we should emit a wait command
+ *
+ * Emit a semaphore command (either wait or signal) to the UVD ring.
+ */
+bool uvd_v2_2_semaphore_emit(struct radeon_device *rdev,
+			     struct radeon_ring *ring,
+			     struct radeon_semaphore *semaphore,
+			     bool emit_wait)
+{
+	uint64_t addr = semaphore->gpu_addr;
+
+	radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_LOW, 0));
+	radeon_ring_write(ring, (addr >> 3) & 0x000FFFFF);
+
+	radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_HIGH, 0));
+	radeon_ring_write(ring, (addr >> 23) & 0x000FFFFF);
+
+	radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0));
+	radeon_ring_write(ring, emit_wait ? 1 : 0);
+
+	return true;
+}
+
+/**
  * uvd_v2_2_resume - memory controller programming
  *
  * @rdev: radeon_device pointer
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index 59736bb810c..1218419c12f 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -152,7 +152,7 @@ static int host1x_reloc_copy_from_user(struct host1x_reloc *dest,
 	if (err < 0)
 		return err;
 
-	err = get_user(dest->target.offset, &src->cmdbuf.offset);
+	err = get_user(dest->target.offset, &src->target.offset);
 	if (err < 0)
 		return err;
 
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index ce023fa3e8a..ab9a4539a44 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -259,16 +259,12 @@ void tegra_bo_free_object(struct drm_gem_object *gem)
 int tegra_bo_dumb_create(struct drm_file *file, struct drm_device *drm,
 			 struct drm_mode_create_dumb *args)
 {
-	int min_pitch = DIV_ROUND_UP(args->width * args->bpp, 8);
+	unsigned int min_pitch = DIV_ROUND_UP(args->width * args->bpp, 8);
 	struct tegra_drm *tegra = drm->dev_private;
 	struct tegra_bo *bo;
 
-	min_pitch = round_up(min_pitch, tegra->pitch_align);
-	if (args->pitch < min_pitch)
-		args->pitch = min_pitch;
-
-	if (args->size < args->pitch * args->height)
-		args->size = args->pitch * args->height;
+	args->pitch = round_up(min_pitch, tegra->pitch_align);
+	args->size = args->pitch * args->height;
 
 	bo = tegra_bo_create_with_handle(file, drm, args->size, 0,
 					 &args->handle);
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index 09874d69518..025c429050c 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -297,11 +297,12 @@ static void ttm_pool_update_free_locked(struct ttm_page_pool *pool,
  *
  * @pool: to free the pages from
  * @free_all: If set to true will free all pages in pool
- * @gfp: GFP flags.
+ * @use_static: Safe to use static buffer
  **/
 static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free,
-			      gfp_t gfp)
+			      bool use_static)
 {
+	static struct page *static_buf[NUM_PAGES_TO_ALLOC];
 	unsigned long irq_flags;
 	struct page *p;
 	struct page **pages_to_free;
@@ -311,7 +312,11 @@ static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free,
 	if (NUM_PAGES_TO_ALLOC < nr_free)
 		npages_to_free = NUM_PAGES_TO_ALLOC;
 
-	pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), gfp);
+	if (use_static)
+		pages_to_free = static_buf;
+	else
+		pages_to_free = kmalloc(npages_to_free * sizeof(struct page *),
+					GFP_KERNEL);
 	if (!pages_to_free) {
 		pr_err("Failed to allocate memory for pool free operation\n");
 		return 0;
@@ -374,7 +379,8 @@ restart:
 	if (freed_pages)
 		ttm_pages_put(pages_to_free, freed_pages);
 out:
-	kfree(pages_to_free);
+	if (pages_to_free != static_buf)
+		kfree(pages_to_free);
 	return nr_free;
 }
 
@@ -383,8 +389,6 @@ out:
  *
  * XXX: (dchinner) Deadlock warning!
  *
- * We need to pass sc->gfp_mask to ttm_page_pool_free().
- *
  * This code is crying out for a shrinker per pool....
  */
 static unsigned long
@@ -407,8 +411,8 @@ ttm_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 		if (shrink_pages == 0)
 			break;
 		pool = &_manager->pools[(i + pool_offset)%NUM_POOLS];
-		shrink_pages = ttm_page_pool_free(pool, nr_free,
-						  sc->gfp_mask);
+		/* OK to use static buffer since global mutex is held. */
+		shrink_pages = ttm_page_pool_free(pool, nr_free, true);
 		freed += nr_free - shrink_pages;
 	}
 	mutex_unlock(&lock);
@@ -710,7 +714,7 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags,
 	}
 	spin_unlock_irqrestore(&pool->lock, irq_flags);
 	if (npages)
-		ttm_page_pool_free(pool, npages, GFP_KERNEL);
+		ttm_page_pool_free(pool, npages, false);
 }
 
 /*
@@ -849,9 +853,9 @@ void ttm_page_alloc_fini(void)
 	pr_info("Finalizing pool allocator\n");
 	ttm_pool_mm_shrink_fini(_manager);
 
+	/* OK to use static buffer since global mutex is no longer used. */
 	for (i = 0; i < NUM_POOLS; ++i)
-		ttm_page_pool_free(&_manager->pools[i], FREE_ALL_PAGES,
-				   GFP_KERNEL);
+		ttm_page_pool_free(&_manager->pools[i], FREE_ALL_PAGES, true);
 
 	kobject_put(&_manager->kobj);
 	_manager = NULL;
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index c96db433f8a..01e1d27eb07 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -411,11 +411,12 @@ static void ttm_dma_page_put(struct dma_pool *pool, struct dma_page *d_page)
  *
  * @pool: to free the pages from
  * @nr_free: If set to true will free all pages in pool
- * @gfp: GFP flags.
+ * @use_static: Safe to use static buffer
  **/
 static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free,
-				       gfp_t gfp)
+				       bool use_static)
 {
+	static struct page *static_buf[NUM_PAGES_TO_ALLOC];
 	unsigned long irq_flags;
 	struct dma_page *dma_p, *tmp;
 	struct page **pages_to_free;
@@ -432,7 +433,11 @@ static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free,
 			 npages_to_free, nr_free);
 	}
 #endif
-	pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), gfp);
+	if (use_static)
+		pages_to_free = static_buf;
+	else
+		pages_to_free = kmalloc(npages_to_free * sizeof(struct page *),
+					GFP_KERNEL);
 
 	if (!pages_to_free) {
 		pr_err("%s: Failed to allocate memory for pool free operation\n",
@@ -502,7 +507,8 @@ restart:
 	if (freed_pages)
 		ttm_dma_pages_put(pool, &d_pages, pages_to_free, freed_pages);
 out:
-	kfree(pages_to_free);
+	if (pages_to_free != static_buf)
+		kfree(pages_to_free);
 	return nr_free;
 }
 
@@ -531,7 +537,8 @@ static void ttm_dma_free_pool(struct device *dev, enum pool_type type)
 		if (pool->type != type)
 			continue;
 		/* Takes a spinlock.. */
-		ttm_dma_page_pool_free(pool, FREE_ALL_PAGES, GFP_KERNEL);
+		/* OK to use static buffer since global mutex is held. */
+		ttm_dma_page_pool_free(pool, FREE_ALL_PAGES, true);
 		WARN_ON(((pool->npages_in_use + pool->npages_free) != 0));
 		/* This code path is called after _all_ references to the
 		 * struct device has been dropped - so nobody should be
@@ -986,7 +993,7 @@ void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 
 	/* shrink pool if necessary (only on !is_cached pools)*/
 	if (npages)
-		ttm_dma_page_pool_free(pool, npages, GFP_KERNEL);
+		ttm_dma_page_pool_free(pool, npages, false);
 	ttm->state = tt_unpopulated;
 }
 EXPORT_SYMBOL_GPL(ttm_dma_unpopulate);
@@ -996,8 +1003,6 @@ EXPORT_SYMBOL_GPL(ttm_dma_unpopulate);
  *
  * XXX: (dchinner) Deadlock warning!
  *
- * We need to pass sc->gfp_mask to ttm_dma_page_pool_free().
- *
  * I'm getting sadder as I hear more pathetical whimpers about needing per-pool
  * shrinkers
  */
@@ -1030,8 +1035,8 @@ ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 		if (++idx < pool_offset)
 			continue;
 		nr_free = shrink_pages;
-		shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free,
-						      sc->gfp_mask);
+		/* OK to use static buffer since global mutex is held. */
+		shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free, true);
 		freed += nr_free - shrink_pages;
 
 		pr_debug("%s: (%s:%d) Asked to shrink %d, have %d more to go\n",
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 25f3c250fd9..0426b5bed8f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -406,11 +406,9 @@ int vmw_3d_resource_inc(struct vmw_private *dev_priv,
 		if (unlikely(ret != 0))
 			--dev_priv->num_3d_resources;
 	} else if (unhide_svga) {
-		mutex_lock(&dev_priv->hw_mutex);
 		vmw_write(dev_priv, SVGA_REG_ENABLE,
 			  vmw_read(dev_priv, SVGA_REG_ENABLE) &
 			  ~SVGA_REG_ENABLE_HIDE);
-		mutex_unlock(&dev_priv->hw_mutex);
 	}
 
 	mutex_unlock(&dev_priv->release_mutex);
@@ -433,13 +431,10 @@ void vmw_3d_resource_dec(struct vmw_private *dev_priv,
 	mutex_lock(&dev_priv->release_mutex);
 	if (unlikely(--dev_priv->num_3d_resources == 0))
 		vmw_release_device(dev_priv);
-	else if (hide_svga) {
-		mutex_lock(&dev_priv->hw_mutex);
+	else if (hide_svga)
 		vmw_write(dev_priv, SVGA_REG_ENABLE,
 			  vmw_read(dev_priv, SVGA_REG_ENABLE) |
 			  SVGA_REG_ENABLE_HIDE);
-		mutex_unlock(&dev_priv->hw_mutex);
-	}
 
 	n3d = (int32_t) dev_priv->num_3d_resources;
 	mutex_unlock(&dev_priv->release_mutex);
@@ -600,12 +595,14 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	dev_priv->dev = dev;
 	dev_priv->vmw_chipset = chipset;
 	dev_priv->last_read_seqno = (uint32_t) -100;
-	mutex_init(&dev_priv->hw_mutex);
 	mutex_init(&dev_priv->cmdbuf_mutex);
 	mutex_init(&dev_priv->release_mutex);
 	mutex_init(&dev_priv->binding_mutex);
 	rwlock_init(&dev_priv->resource_lock);
 	ttm_lock_init(&dev_priv->reservation_sem);
+	spin_lock_init(&dev_priv->hw_lock);
+	spin_lock_init(&dev_priv->waiter_lock);
+	spin_lock_init(&dev_priv->cap_lock);
 
 	for (i = vmw_res_context; i < vmw_res_max; ++i) {
 		idr_init(&dev_priv->res_idr[i]);
@@ -626,14 +623,11 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 
 	dev_priv->enable_fb = enable_fbdev;
 
-	mutex_lock(&dev_priv->hw_mutex);
-
 	vmw_write(dev_priv, SVGA_REG_ID, SVGA_ID_2);
 	svga_id = vmw_read(dev_priv, SVGA_REG_ID);
 	if (svga_id != SVGA_ID_2) {
 		ret = -ENOSYS;
 		DRM_ERROR("Unsupported SVGA ID 0x%x\n", svga_id);
-		mutex_unlock(&dev_priv->hw_mutex);
 		goto out_err0;
 	}
 
@@ -683,10 +677,8 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 		dev_priv->prim_bb_mem = dev_priv->vram_size;
 
 	ret = vmw_dma_masks(dev_priv);
-	if (unlikely(ret != 0)) {
-		mutex_unlock(&dev_priv->hw_mutex);
+	if (unlikely(ret != 0))
 		goto out_err0;
-	}
 
 	/*
 	 * Limit back buffer size to VRAM size.  Remove this once
@@ -695,8 +687,6 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	if (dev_priv->prim_bb_mem > dev_priv->vram_size)
 		dev_priv->prim_bb_mem = dev_priv->vram_size;
 
-	mutex_unlock(&dev_priv->hw_mutex);
-
 	vmw_print_capabilities(dev_priv->capabilities);
 
 	if (dev_priv->capabilities & SVGA_CAP_GMR2) {
@@ -735,32 +725,6 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 		goto out_err1;
 	}
 
-	ret = ttm_bo_init_mm(&dev_priv->bdev, TTM_PL_VRAM,
-			     (dev_priv->vram_size >> PAGE_SHIFT));
-	if (unlikely(ret != 0)) {
-		DRM_ERROR("Failed initializing memory manager for VRAM.\n");
-		goto out_err2;
-	}
-
-	dev_priv->has_gmr = true;
-	if (((dev_priv->capabilities & (SVGA_CAP_GMR | SVGA_CAP_GMR2)) == 0) ||
-	    refuse_dma || ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_GMR,
-					 VMW_PL_GMR) != 0) {
-		DRM_INFO("No GMR memory available. "
-			 "Graphics memory resources are very limited.\n");
-		dev_priv->has_gmr = false;
-	}
-
-	if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) {
-		dev_priv->has_mob = true;
-		if (ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_MOB,
-				   VMW_PL_MOB) != 0) {
-			DRM_INFO("No MOB memory available. "
-				 "3D will be disabled.\n");
-			dev_priv->has_mob = false;
-		}
-	}
-
 	dev_priv->mmio_mtrr = arch_phys_wc_add(dev_priv->mmio_start,
 					       dev_priv->mmio_size);
 
@@ -823,6 +787,33 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 		goto out_no_fman;
 	}
 
+
+	ret = ttm_bo_init_mm(&dev_priv->bdev, TTM_PL_VRAM,
+			     (dev_priv->vram_size >> PAGE_SHIFT));
+	if (unlikely(ret != 0)) {
+		DRM_ERROR("Failed initializing memory manager for VRAM.\n");
+		goto out_no_vram;
+	}
+
+	dev_priv->has_gmr = true;
+	if (((dev_priv->capabilities & (SVGA_CAP_GMR | SVGA_CAP_GMR2)) == 0) ||
+	    refuse_dma || ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_GMR,
+					 VMW_PL_GMR) != 0) {
+		DRM_INFO("No GMR memory available. "
+			 "Graphics memory resources are very limited.\n");
+		dev_priv->has_gmr = false;
+	}
+
+	if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) {
+		dev_priv->has_mob = true;
+		if (ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_MOB,
+				   VMW_PL_MOB) != 0) {
+			DRM_INFO("No MOB memory available. "
+				 "3D will be disabled.\n");
+			dev_priv->has_mob = false;
+		}
+	}
+
 	vmw_kms_save_vga(dev_priv);
 
 	/* Start kms and overlay systems, needs fifo. */
@@ -848,6 +839,12 @@ out_no_fifo:
 	vmw_kms_close(dev_priv);
 out_no_kms:
 	vmw_kms_restore_vga(dev_priv);
+	if (dev_priv->has_mob)
+		(void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB);
+	if (dev_priv->has_gmr)
+		(void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR);
+	(void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM);
+out_no_vram:
 	vmw_fence_manager_takedown(dev_priv->fman);
 out_no_fman:
 	if (dev_priv->capabilities & SVGA_CAP_IRQMASK)
@@ -863,12 +860,6 @@ out_err4:
 	iounmap(dev_priv->mmio_virt);
 out_err3:
 	arch_phys_wc_del(dev_priv->mmio_mtrr);
-	if (dev_priv->has_mob)
-		(void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB);
-	if (dev_priv->has_gmr)
-		(void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR);
-	(void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM);
-out_err2:
 	(void)ttm_bo_device_release(&dev_priv->bdev);
 out_err1:
 	vmw_ttm_global_release(dev_priv);
@@ -898,6 +889,13 @@ static int vmw_driver_unload(struct drm_device *dev)
 	}
 	vmw_kms_close(dev_priv);
 	vmw_overlay_close(dev_priv);
+
+	if (dev_priv->has_mob)
+		(void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB);
+	if (dev_priv->has_gmr)
+		(void)ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR);
+	(void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM);
+
 	vmw_fence_manager_takedown(dev_priv->fman);
 	if (dev_priv->capabilities & SVGA_CAP_IRQMASK)
 		drm_irq_uninstall(dev_priv->dev);
@@ -909,11 +907,6 @@ static int vmw_driver_unload(struct drm_device *dev)
 	ttm_object_device_release(&dev_priv->tdev);
 	iounmap(dev_priv->mmio_virt);
 	arch_phys_wc_del(dev_priv->mmio_mtrr);
-	if (dev_priv->has_mob)
-		(void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB);
-	if (dev_priv->has_gmr)
-		(void)ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR);
-	(void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM);
 	(void)ttm_bo_device_release(&dev_priv->bdev);
 	vmw_ttm_global_release(dev_priv);
 
@@ -1063,8 +1056,12 @@ static long vmw_generic_ioctl(struct file *filp, unsigned int cmd,
 
 	vmaster = vmw_master_check(dev, file_priv, flags);
 	if (unlikely(IS_ERR(vmaster))) {
-		DRM_INFO("IOCTL ERROR %d\n", nr);
-		return PTR_ERR(vmaster);
+		ret = PTR_ERR(vmaster);
+
+		if (ret != -ERESTARTSYS)
+			DRM_INFO("IOCTL ERROR Command %d, Error %ld.\n",
+				 nr, ret);
+		return ret;
 	}
 
 	ret = ioctl_func(filp, cmd, arg);
@@ -1157,9 +1154,7 @@ static int vmw_master_set(struct drm_device *dev,
 		if (unlikely(ret != 0))
 			return ret;
 		vmw_kms_save_vga(dev_priv);
-		mutex_lock(&dev_priv->hw_mutex);
 		vmw_write(dev_priv, SVGA_REG_TRACES, 0);
-		mutex_unlock(&dev_priv->hw_mutex);
 	}
 
 	if (active) {
@@ -1193,9 +1188,7 @@ out_no_active_lock:
 	if (!dev_priv->enable_fb) {
 		vmw_kms_restore_vga(dev_priv);
 		vmw_3d_resource_dec(dev_priv, true);
-		mutex_lock(&dev_priv->hw_mutex);
 		vmw_write(dev_priv, SVGA_REG_TRACES, 1);
-		mutex_unlock(&dev_priv->hw_mutex);
 	}
 	return ret;
 }
@@ -1230,9 +1223,7 @@ static void vmw_master_drop(struct drm_device *dev,
 			DRM_ERROR("Unable to clean VRAM on master drop.\n");
 		vmw_kms_restore_vga(dev_priv);
 		vmw_3d_resource_dec(dev_priv, true);
-		mutex_lock(&dev_priv->hw_mutex);
 		vmw_write(dev_priv, SVGA_REG_TRACES, 1);
-		mutex_unlock(&dev_priv->hw_mutex);
 	}
 
 	dev_priv->active_master = &dev_priv->fbdev_master;
@@ -1364,10 +1355,8 @@ static void vmw_pm_complete(struct device *kdev)
 	struct drm_device *dev = pci_get_drvdata(pdev);
 	struct vmw_private *dev_priv = vmw_priv(dev);
 
-	mutex_lock(&dev_priv->hw_mutex);
 	vmw_write(dev_priv, SVGA_REG_ID, SVGA_ID_2);
 	(void) vmw_read(dev_priv, SVGA_REG_ID);
-	mutex_unlock(&dev_priv->hw_mutex);
 
 	/**
 	 * Reclaim 3d reference held by fbdev and potentially
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 4ee799b43d5..d26a6daa971 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -399,7 +399,8 @@ struct vmw_private {
 	uint32_t memory_size;
 	bool has_gmr;
 	bool has_mob;
-	struct mutex hw_mutex;
+	spinlock_t hw_lock;
+	spinlock_t cap_lock;
 
 	/*
 	 * VGA registers.
@@ -449,8 +450,9 @@ struct vmw_private {
 	atomic_t marker_seq;
 	wait_queue_head_t fence_queue;
 	wait_queue_head_t fifo_queue;
-	int fence_queue_waiters; /* Protected by hw_mutex */
-	int goal_queue_waiters; /* Protected by hw_mutex */
+	spinlock_t waiter_lock;
+	int fence_queue_waiters; /* Protected by waiter_lock */
+	int goal_queue_waiters; /* Protected by waiter_lock */
 	atomic_t fifo_queue_waiters;
 	uint32_t last_read_seqno;
 	spinlock_t irq_lock;
@@ -553,20 +555,35 @@ static inline struct vmw_master *vmw_master(struct drm_master *master)
 	return (struct vmw_master *) master->driver_priv;
 }
 
+/*
+ * The locking here is fine-grained, so that it is performed once
+ * for every read- and write operation. This is of course costly, but we
+ * don't perform much register access in the timing critical paths anyway.
+ * Instead we have the extra benefit of being sure that we don't forget
+ * the hw lock around register accesses.
+ */
 static inline void vmw_write(struct vmw_private *dev_priv,
 			     unsigned int offset, uint32_t value)
 {
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&dev_priv->hw_lock, irq_flags);
 	outl(offset, dev_priv->io_start + VMWGFX_INDEX_PORT);
 	outl(value, dev_priv->io_start + VMWGFX_VALUE_PORT);
+	spin_unlock_irqrestore(&dev_priv->hw_lock, irq_flags);
 }
 
 static inline uint32_t vmw_read(struct vmw_private *dev_priv,
 				unsigned int offset)
 {
-	uint32_t val;
+	unsigned long irq_flags;
+	u32 val;
 
+	spin_lock_irqsave(&dev_priv->hw_lock, irq_flags);
 	outl(offset, dev_priv->io_start + VMWGFX_INDEX_PORT);
 	val = inl(dev_priv->io_start + VMWGFX_VALUE_PORT);
+	spin_unlock_irqrestore(&dev_priv->hw_lock, irq_flags);
+
 	return val;
 }
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 596cd6dafd3..50b52802f47 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -2778,13 +2778,11 @@ int vmw_execbuf_ioctl(struct drm_device *dev, void *data,
 				  NULL, arg->command_size, arg->throttle_us,
 				  (void __user *)(unsigned long)arg->fence_rep,
 				  NULL);
-
+	ttm_read_unlock(&dev_priv->reservation_sem);
 	if (unlikely(ret != 0))
-		goto out_unlock;
+		return ret;
 
 	vmw_kms_cursor_post_execbuf(dev_priv);
 
-out_unlock:
-	ttm_read_unlock(&dev_priv->reservation_sem);
-	return ret;
+	return 0;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index 197164fd780..945f1e0dad9 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -35,7 +35,7 @@ struct vmw_fence_manager {
 	struct vmw_private *dev_priv;
 	spinlock_t lock;
 	struct list_head fence_list;
-	struct work_struct work, ping_work;
+	struct work_struct work;
 	u32 user_fence_size;
 	u32 fence_size;
 	u32 event_fence_action_size;
@@ -134,14 +134,6 @@ static const char *vmw_fence_get_timeline_name(struct fence *f)
 	return "svga";
 }
 
-static void vmw_fence_ping_func(struct work_struct *work)
-{
-	struct vmw_fence_manager *fman =
-		container_of(work, struct vmw_fence_manager, ping_work);
-
-	vmw_fifo_ping_host(fman->dev_priv, SVGA_SYNC_GENERIC);
-}
-
 static bool vmw_fence_enable_signaling(struct fence *f)
 {
 	struct vmw_fence_obj *fence =
@@ -155,11 +147,7 @@ static bool vmw_fence_enable_signaling(struct fence *f)
 	if (seqno - fence->base.seqno < VMW_FENCE_WRAP)
 		return false;
 
-	if (mutex_trylock(&dev_priv->hw_mutex)) {
-		vmw_fifo_ping_host_locked(dev_priv, SVGA_SYNC_GENERIC);
-		mutex_unlock(&dev_priv->hw_mutex);
-	} else
-		schedule_work(&fman->ping_work);
+	vmw_fifo_ping_host(dev_priv, SVGA_SYNC_GENERIC);
 
 	return true;
 }
@@ -305,7 +293,6 @@ struct vmw_fence_manager *vmw_fence_manager_init(struct vmw_private *dev_priv)
 	INIT_LIST_HEAD(&fman->fence_list);
 	INIT_LIST_HEAD(&fman->cleanup_list);
 	INIT_WORK(&fman->work, &vmw_fence_work_func);
-	INIT_WORK(&fman->ping_work, &vmw_fence_ping_func);
 	fman->fifo_down = true;
 	fman->user_fence_size = ttm_round_pot(sizeof(struct vmw_user_fence));
 	fman->fence_size = ttm_round_pot(sizeof(struct vmw_fence_obj));
@@ -323,7 +310,6 @@ void vmw_fence_manager_takedown(struct vmw_fence_manager *fman)
 	bool lists_empty;
 
 	(void) cancel_work_sync(&fman->work);
-	(void) cancel_work_sync(&fman->ping_work);
 
 	spin_lock_irqsave(&fman->lock, irq_flags);
 	lists_empty = list_empty(&fman->fence_list) &&
@@ -545,35 +531,19 @@ void vmw_fence_obj_flush(struct vmw_fence_obj *fence)
 
 static void vmw_fence_destroy(struct vmw_fence_obj *fence)
 {
-	struct vmw_fence_manager *fman = fman_from_fence(fence);
-
 	fence_free(&fence->base);
-
-	/*
-	 * Free kernel space accounting.
-	 */
-	ttm_mem_global_free(vmw_mem_glob(fman->dev_priv),
-			    fman->fence_size);
 }
 
 int vmw_fence_create(struct vmw_fence_manager *fman,
 		     uint32_t seqno,
 		     struct vmw_fence_obj **p_fence)
 {
-	struct ttm_mem_global *mem_glob = vmw_mem_glob(fman->dev_priv);
 	struct vmw_fence_obj *fence;
 	int ret;
 
-	ret = ttm_mem_global_alloc(mem_glob, fman->fence_size,
-				   false, false);
-	if (unlikely(ret != 0))
-		return ret;
-
 	fence = kzalloc(sizeof(*fence), GFP_KERNEL);
-	if (unlikely(fence == NULL)) {
-		ret = -ENOMEM;
-		goto out_no_object;
-	}
+	if (unlikely(fence == NULL))
+		return -ENOMEM;
 
 	ret = vmw_fence_obj_init(fman, fence, seqno,
 				 vmw_fence_destroy);
@@ -585,8 +555,6 @@ int vmw_fence_create(struct vmw_fence_manager *fman,
 
 out_err_init:
 	kfree(fence);
-out_no_object:
-	ttm_mem_global_free(mem_glob, fman->fence_size);
 	return ret;
 }
 
@@ -1105,6 +1073,8 @@ static int vmw_event_fence_action_create(struct drm_file *file_priv,
 	if (ret != 0)
 		goto out_no_queue;
 
+	return 0;
+
 out_no_queue:
 	event->base.destroy(&event->base);
 out_no_event:
@@ -1180,17 +1150,10 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data,
 
 	BUG_ON(fence == NULL);
 
-	if (arg->flags & DRM_VMW_FE_FLAG_REQ_TIME)
-		ret = vmw_event_fence_action_create(file_priv, fence,
-						    arg->flags,
-						    arg->user_data,
-						    true);
-	else
-		ret = vmw_event_fence_action_create(file_priv, fence,
-						    arg->flags,
-						    arg->user_data,
-						    true);
-
+	ret = vmw_event_fence_action_create(file_priv, fence,
+					    arg->flags,
+					    arg->user_data,
+					    true);
 	if (unlikely(ret != 0)) {
 		if (ret != -ERESTARTSYS)
 			DRM_ERROR("Failed to attach event to fence.\n");
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
index 09e10aefcd8..39f2b03888e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
@@ -44,10 +44,10 @@ bool vmw_fifo_have_3d(struct vmw_private *dev_priv)
 		if (!dev_priv->has_mob)
 			return false;
 
-		mutex_lock(&dev_priv->hw_mutex);
+		spin_lock(&dev_priv->cap_lock);
 		vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_3D);
 		result = vmw_read(dev_priv, SVGA_REG_DEV_CAP);
-		mutex_unlock(&dev_priv->hw_mutex);
+		spin_unlock(&dev_priv->cap_lock);
 
 		return (result != 0);
 	}
@@ -120,7 +120,6 @@ int vmw_fifo_init(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo)
 	DRM_INFO("height %d\n", vmw_read(dev_priv, SVGA_REG_HEIGHT));
 	DRM_INFO("bpp %d\n", vmw_read(dev_priv, SVGA_REG_BITS_PER_PIXEL));
 
-	mutex_lock(&dev_priv->hw_mutex);
 	dev_priv->enable_state = vmw_read(dev_priv, SVGA_REG_ENABLE);
 	dev_priv->config_done_state = vmw_read(dev_priv, SVGA_REG_CONFIG_DONE);
 	dev_priv->traces_state = vmw_read(dev_priv, SVGA_REG_TRACES);
@@ -143,7 +142,6 @@ int vmw_fifo_init(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo)
 	mb();
 
 	vmw_write(dev_priv, SVGA_REG_CONFIG_DONE, 1);
-	mutex_unlock(&dev_priv->hw_mutex);
 
 	max = ioread32(fifo_mem + SVGA_FIFO_MAX);
 	min = ioread32(fifo_mem  + SVGA_FIFO_MIN);
@@ -160,31 +158,28 @@ int vmw_fifo_init(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo)
 	return vmw_fifo_send_fence(dev_priv, &dummy);
 }
 
-void vmw_fifo_ping_host_locked(struct vmw_private *dev_priv, uint32_t reason)
+void vmw_fifo_ping_host(struct vmw_private *dev_priv, uint32_t reason)
 {
 	__le32 __iomem *fifo_mem = dev_priv->mmio_virt;
+	static DEFINE_SPINLOCK(ping_lock);
+	unsigned long irq_flags;
 
+	/*
+	 * The ping_lock is needed because we don't have an atomic
+	 * test-and-set of the SVGA_FIFO_BUSY register.
+	 */
+	spin_lock_irqsave(&ping_lock, irq_flags);
 	if (unlikely(ioread32(fifo_mem + SVGA_FIFO_BUSY) == 0)) {
 		iowrite32(1, fifo_mem + SVGA_FIFO_BUSY);
 		vmw_write(dev_priv, SVGA_REG_SYNC, reason);
 	}
-}
-
-void vmw_fifo_ping_host(struct vmw_private *dev_priv, uint32_t reason)
-{
-	mutex_lock(&dev_priv->hw_mutex);
-
-	vmw_fifo_ping_host_locked(dev_priv, reason);
-
-	mutex_unlock(&dev_priv->hw_mutex);
+	spin_unlock_irqrestore(&ping_lock, irq_flags);
 }
 
 void vmw_fifo_release(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo)
 {
 	__le32 __iomem *fifo_mem = dev_priv->mmio_virt;
 
-	mutex_lock(&dev_priv->hw_mutex);
-
 	vmw_write(dev_priv, SVGA_REG_SYNC, SVGA_SYNC_GENERIC);
 	while (vmw_read(dev_priv, SVGA_REG_BUSY) != 0)
 		;
@@ -198,7 +193,6 @@ void vmw_fifo_release(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo)
 	vmw_write(dev_priv, SVGA_REG_TRACES,
 		  dev_priv->traces_state);
 
-	mutex_unlock(&dev_priv->hw_mutex);
 	vmw_marker_queue_takedown(&fifo->marker_queue);
 
 	if (likely(fifo->static_buffer != NULL)) {
@@ -271,7 +265,7 @@ static int vmw_fifo_wait(struct vmw_private *dev_priv,
 		return vmw_fifo_wait_noirq(dev_priv, bytes,
 					   interruptible, timeout);
 
-	mutex_lock(&dev_priv->hw_mutex);
+	spin_lock(&dev_priv->waiter_lock);
 	if (atomic_add_return(1, &dev_priv->fifo_queue_waiters) > 0) {
 		spin_lock_irqsave(&dev_priv->irq_lock, irq_flags);
 		outl(SVGA_IRQFLAG_FIFO_PROGRESS,
@@ -280,7 +274,7 @@ static int vmw_fifo_wait(struct vmw_private *dev_priv,
 		vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask);
 		spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags);
 	}
-	mutex_unlock(&dev_priv->hw_mutex);
+	spin_unlock(&dev_priv->waiter_lock);
 
 	if (interruptible)
 		ret = wait_event_interruptible_timeout
@@ -296,14 +290,14 @@ static int vmw_fifo_wait(struct vmw_private *dev_priv,
 	else if (likely(ret > 0))
 		ret = 0;
 
-	mutex_lock(&dev_priv->hw_mutex);
+	spin_lock(&dev_priv->waiter_lock);
 	if (atomic_dec_and_test(&dev_priv->fifo_queue_waiters)) {
 		spin_lock_irqsave(&dev_priv->irq_lock, irq_flags);
 		dev_priv->irq_mask &= ~SVGA_IRQFLAG_FIFO_PROGRESS;
 		vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask);
 		spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags);
 	}
-	mutex_unlock(&dev_priv->hw_mutex);
+	spin_unlock(&dev_priv->waiter_lock);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
index 37881ecf5d7..69c8ce23123 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
@@ -135,13 +135,13 @@ static int vmw_fill_compat_cap(struct vmw_private *dev_priv, void *bounce,
 		(pair_offset + max_size * sizeof(SVGA3dCapPair)) / sizeof(u32);
 	compat_cap->header.type = SVGA3DCAPS_RECORD_DEVCAPS;
 
-	mutex_lock(&dev_priv->hw_mutex);
+	spin_lock(&dev_priv->cap_lock);
 	for (i = 0; i < max_size; ++i) {
 		vmw_write(dev_priv, SVGA_REG_DEV_CAP, i);
 		compat_cap->pairs[i][0] = i;
 		compat_cap->pairs[i][1] = vmw_read(dev_priv, SVGA_REG_DEV_CAP);
 	}
-	mutex_unlock(&dev_priv->hw_mutex);
+	spin_unlock(&dev_priv->cap_lock);
 
 	return 0;
 }
@@ -191,12 +191,12 @@ int vmw_get_cap_3d_ioctl(struct drm_device *dev, void *data,
 		if (num > SVGA3D_DEVCAP_MAX)
 			num = SVGA3D_DEVCAP_MAX;
 
-		mutex_lock(&dev_priv->hw_mutex);
+		spin_lock(&dev_priv->cap_lock);
 		for (i = 0; i < num; ++i) {
 			vmw_write(dev_priv, SVGA_REG_DEV_CAP, i);
 			*bounce32++ = vmw_read(dev_priv, SVGA_REG_DEV_CAP);
 		}
-		mutex_unlock(&dev_priv->hw_mutex);
+		spin_unlock(&dev_priv->cap_lock);
 	} else if (gb_objects) {
 		ret = vmw_fill_compat_cap(dev_priv, bounce, size);
 		if (unlikely(ret != 0))
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c
index 0c423766c44..9fe9827ee49 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c
@@ -62,13 +62,8 @@ irqreturn_t vmw_irq_handler(int irq, void *arg)
 
 static bool vmw_fifo_idle(struct vmw_private *dev_priv, uint32_t seqno)
 {
-	uint32_t busy;
 
-	mutex_lock(&dev_priv->hw_mutex);
-	busy = vmw_read(dev_priv, SVGA_REG_BUSY);
-	mutex_unlock(&dev_priv->hw_mutex);
-
-	return (busy == 0);
+	return (vmw_read(dev_priv, SVGA_REG_BUSY) == 0);
 }
 
 void vmw_update_seqno(struct vmw_private *dev_priv,
@@ -184,7 +179,7 @@ int vmw_fallback_wait(struct vmw_private *dev_priv,
 
 void vmw_seqno_waiter_add(struct vmw_private *dev_priv)
 {
-	mutex_lock(&dev_priv->hw_mutex);
+	spin_lock(&dev_priv->waiter_lock);
 	if (dev_priv->fence_queue_waiters++ == 0) {
 		unsigned long irq_flags;
 
@@ -195,12 +190,12 @@ void vmw_seqno_waiter_add(struct vmw_private *dev_priv)
 		vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask);
 		spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags);
 	}
-	mutex_unlock(&dev_priv->hw_mutex);
+	spin_unlock(&dev_priv->waiter_lock);
 }
 
 void vmw_seqno_waiter_remove(struct vmw_private *dev_priv)
 {
-	mutex_lock(&dev_priv->hw_mutex);
+	spin_lock(&dev_priv->waiter_lock);
 	if (--dev_priv->fence_queue_waiters == 0) {
 		unsigned long irq_flags;
 
@@ -209,13 +204,13 @@ void vmw_seqno_waiter_remove(struct vmw_private *dev_priv)
 		vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask);
 		spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags);
 	}
-	mutex_unlock(&dev_priv->hw_mutex);
+	spin_unlock(&dev_priv->waiter_lock);
 }
 
 
 void vmw_goal_waiter_add(struct vmw_private *dev_priv)
 {
-	mutex_lock(&dev_priv->hw_mutex);
+	spin_lock(&dev_priv->waiter_lock);
 	if (dev_priv->goal_queue_waiters++ == 0) {
 		unsigned long irq_flags;
 
@@ -226,12 +221,12 @@ void vmw_goal_waiter_add(struct vmw_private *dev_priv)
 		vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask);
 		spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags);
 	}
-	mutex_unlock(&dev_priv->hw_mutex);
+	spin_unlock(&dev_priv->waiter_lock);
 }
 
 void vmw_goal_waiter_remove(struct vmw_private *dev_priv)
 {
-	mutex_lock(&dev_priv->hw_mutex);
+	spin_lock(&dev_priv->waiter_lock);
 	if (--dev_priv->goal_queue_waiters == 0) {
 		unsigned long irq_flags;
 
@@ -240,7 +235,7 @@ void vmw_goal_waiter_remove(struct vmw_private *dev_priv)
 		vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask);
 		spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags);
 	}
-	mutex_unlock(&dev_priv->hw_mutex);
+	spin_unlock(&dev_priv->waiter_lock);
 }
 
 int vmw_wait_seqno(struct vmw_private *dev_priv,
@@ -315,9 +310,7 @@ void vmw_irq_uninstall(struct drm_device *dev)
 	if (!(dev_priv->capabilities & SVGA_CAP_IRQMASK))
 		return;
 
-	mutex_lock(&dev_priv->hw_mutex);
 	vmw_write(dev_priv, SVGA_REG_IRQMASK, 0);
-	mutex_unlock(&dev_priv->hw_mutex);
 
 	status = inl(dev_priv->io_start + VMWGFX_IRQSTATUS_PORT);
 	outl(status, dev_priv->io_start + VMWGFX_IRQSTATUS_PORT);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 941a7bc0b79..173ec3377e4 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1828,9 +1828,7 @@ vmw_du_connector_detect(struct drm_connector *connector, bool force)
 	struct vmw_private *dev_priv = vmw_priv(dev);
 	struct vmw_display_unit *du = vmw_connector_to_du(connector);
 
-	mutex_lock(&dev_priv->hw_mutex);
 	num_displays = vmw_read(dev_priv, SVGA_REG_NUM_DISPLAYS);
-	mutex_unlock(&dev_priv->hw_mutex);
 
 	return ((vmw_connector_to_du(connector)->unit < num_displays &&
 		 du->pref_active) ?
@@ -2035,23 +2033,17 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 	int i;
 	struct drm_mode_config *mode_config = &dev->mode_config;
 
-	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
-	if (unlikely(ret != 0))
-		return ret;
-
 	if (!arg->num_outputs) {
 		struct drm_vmw_rect def_rect = {0, 0, 800, 600};
 		vmw_du_update_layout(dev_priv, 1, &def_rect);
-		goto out_unlock;
+		return 0;
 	}
 
 	rects_size = arg->num_outputs * sizeof(struct drm_vmw_rect);
 	rects = kcalloc(arg->num_outputs, sizeof(struct drm_vmw_rect),
 			GFP_KERNEL);
-	if (unlikely(!rects)) {
-		ret = -ENOMEM;
-		goto out_unlock;
-	}
+	if (unlikely(!rects))
+		return -ENOMEM;
 
 	user_rects = (void __user *)(unsigned long)arg->rects;
 	ret = copy_from_user(rects, user_rects, rects_size);
@@ -2076,7 +2068,5 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 
 out_free:
 	kfree(rects);
-out_unlock:
-	ttm_read_unlock(&dev_priv->reservation_sem);
 	return ret;
 }
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index f42df4dd58d..6f299cd54e6 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -378,6 +378,17 @@ config HID_LOGITECH_DJ
 	generic USB_HID driver and all incoming events will be multiplexed
 	into a single mouse and a single keyboard device.
 
+config HID_LOGITECH_HIDPP
+	tristate "Logitech HID++ devices support"
+	depends on HID_LOGITECH
+	---help---
+	Support for Logitech devices relyingon the HID++ Logitech specification
+
+	Say Y if you want support for Logitech devices relying on the HID++
+	specification. Such devices are the various Logitech Touchpads (T650,
+	T651, TK820), some mice (Zone Touch mouse), or even keyboards (Solar
+	Keayboard).
+
 config LOGITECH_FF
 	bool "Logitech force feedback support"
 	depends on HID_LOGITECH
diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile
index e2850d8af9c..b102774b4e1 100644
--- a/drivers/hid/Makefile
+++ b/drivers/hid/Makefile
@@ -63,6 +63,7 @@ obj-$(CONFIG_HID_LCPOWER)       += hid-lcpower.o
 obj-$(CONFIG_HID_LENOVO)	+= hid-lenovo.o
 obj-$(CONFIG_HID_LOGITECH)	+= hid-logitech.o
 obj-$(CONFIG_HID_LOGITECH_DJ)	+= hid-logitech-dj.o
+obj-$(CONFIG_HID_LOGITECH_HIDPP)	+= hid-logitech-hidpp.o
 obj-$(CONFIG_HID_MAGICMOUSE)    += hid-magicmouse.o
 obj-$(CONFIG_HID_MICROSOFT)	+= hid-microsoft.o
 obj-$(CONFIG_HID_MONTEREY)	+= hid-monterey.o
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 3402033fa52..7eda03c1380 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1809,7 +1809,9 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_ERGO_525V) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_I405X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_PENSKETCH_M912) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LCPOWER, USB_DEVICE_ID_LCPOWER_LC1000 ) },
 #if IS_ENABLED(CONFIG_HID_LENOVO)
@@ -1822,6 +1824,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_S510_RECEIVER_2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_RECEIVER) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_HARMONY_PS3) },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_T651) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_DINOVO_DESKTOP) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_DINOVO_EDGE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_DINOVO_MINI) },
@@ -1857,6 +1860,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_SIDEWINDER_GV) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_NE4K) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_NE4K_JP) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_NE7K) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_LK6K) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_USB) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_DIGITAL_MEDIA_3K) },
@@ -1908,12 +1912,14 @@ static const struct hid_device_id hid_have_special_driver[] = {
 #endif
 #if IS_ENABLED(CONFIG_HID_SAITEK)
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_PS1000) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RAT7_OLD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RAT7) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_MMO7) },
 #endif
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SAMSUNG, USB_DEVICE_ID_SAMSUNG_IR_REMOTE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SAMSUNG, USB_DEVICE_ID_SAMSUNG_WIRELESS_KBD_MOUSE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SKYCABLE, USB_DEVICE_ID_SKYCABLE_WIRELESS_PRESENTER) },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SMK, USB_DEVICE_ID_SMK_PS3_BDREMOTE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_BUZZ_CONTROLLER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_WIRELESS_BUZZ_CONTROLLER) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_BDREMOTE) },
@@ -1953,6 +1959,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP_LTD, USB_DEVICE_ID_SUPER_JOY_BOX_3_PRO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP_LTD, USB_DEVICE_ID_SUPER_DUAL_BOX_PRO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP_LTD, USB_DEVICE_ID_SUPER_JOY_BOX_5_PRO) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_PLAYDOTCOM, USB_DEVICE_ID_PLAYDOTCOM_EMS_USBII) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_SLIM_TABLET_5_8_INCH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_SLIM_TABLET_12_1_INCH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_Q_PAD) },
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 7c863738e41..252a7ed40f8 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -164,6 +164,7 @@
 #define USB_DEVICE_ID_ATEN_2PORTKVM	0x2204
 #define USB_DEVICE_ID_ATEN_4PORTKVM	0x2205
 #define USB_DEVICE_ID_ATEN_4PORTKVMC	0x2208
+#define USB_DEVICE_ID_ATEN_CS682	0x2213
 
 #define USB_VENDOR_ID_ATMEL		0x03eb
 #define USB_DEVICE_ID_ATMEL_MULTITOUCH	0x211c
@@ -300,6 +301,7 @@
 #define USB_DEVICE_ID_ELAN_TOUCHSCREEN	0x0089
 #define USB_DEVICE_ID_ELAN_TOUCHSCREEN_009B	0x009b
 #define USB_DEVICE_ID_ELAN_TOUCHSCREEN_0103	0x0103
+#define USB_DEVICE_ID_ELAN_TOUCHSCREEN_010c	0x010c
 #define USB_DEVICE_ID_ELAN_TOUCHSCREEN_016F	0x016f
 
 #define USB_VENDOR_ID_ELECOM		0x056e
@@ -453,6 +455,11 @@
 #define USB_DEVICE_ID_UGCI_FLYING	0x0020
 #define USB_DEVICE_ID_UGCI_FIGHTING	0x0030
 
+#define USB_VENDOR_ID_HP		0x03f0
+#define USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0A4A	0x0a4a
+#define USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0B4A	0x0b4a
+#define USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE		0x134a
+
 #define USB_VENDOR_ID_HUION		0x256c
 #define USB_DEVICE_ID_HUION_TABLET	0x006e
 
@@ -525,7 +532,9 @@
 #define USB_DEVICE_ID_KYE_GPEN_560	0x5003
 #define USB_DEVICE_ID_KYE_EASYPEN_I405X	0x5010
 #define USB_DEVICE_ID_KYE_MOUSEPEN_I608X	0x5011
+#define USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2	0x501a
 #define USB_DEVICE_ID_KYE_EASYPEN_M610X	0x5013
+#define USB_DEVICE_ID_KYE_PENSKETCH_M912	0x5015
 
 #define USB_VENDOR_ID_LABTEC		0x1020
 #define USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD	0x0006
@@ -578,10 +587,15 @@
 
 #define USB_VENDOR_ID_LOGITECH		0x046d
 #define USB_DEVICE_ID_LOGITECH_AUDIOHUB 0x0a0e
+#define USB_DEVICE_ID_LOGITECH_T651	0xb00c
+#define USB_DEVICE_ID_LOGITECH_C077	0xc007
 #define USB_DEVICE_ID_LOGITECH_RECEIVER	0xc101
 #define USB_DEVICE_ID_LOGITECH_HARMONY_FIRST  0xc110
 #define USB_DEVICE_ID_LOGITECH_HARMONY_LAST 0xc14f
 #define USB_DEVICE_ID_LOGITECH_HARMONY_PS3 0x0306
+#define USB_DEVICE_ID_LOGITECH_MOUSE_C01A	0xc01a
+#define USB_DEVICE_ID_LOGITECH_MOUSE_C05A	0xc05a
+#define USB_DEVICE_ID_LOGITECH_MOUSE_C06A	0xc06a
 #define USB_DEVICE_ID_LOGITECH_RUMBLEPAD_CORD	0xc20a
 #define USB_DEVICE_ID_LOGITECH_RUMBLEPAD	0xc211
 #define USB_DEVICE_ID_LOGITECH_EXTREME_3D	0xc215
@@ -644,6 +658,7 @@
 #define USB_DEVICE_ID_MS_LK6K		0x00f9
 #define USB_DEVICE_ID_MS_PRESENTER_8K_BT	0x0701
 #define USB_DEVICE_ID_MS_PRESENTER_8K_USB	0x0713
+#define USB_DEVICE_ID_MS_NE7K		0x071d
 #define USB_DEVICE_ID_MS_DIGITAL_MEDIA_3K	0x0730
 #define USB_DEVICE_ID_MS_COMFORT_MOUSE_4500	0x076c
 #define USB_DEVICE_ID_MS_SURFACE_PRO_2   0x0799
@@ -785,6 +800,7 @@
 #define USB_VENDOR_ID_SAITEK		0x06a3
 #define USB_DEVICE_ID_SAITEK_RUMBLEPAD	0xff17
 #define USB_DEVICE_ID_SAITEK_PS1000	0x0621
+#define USB_DEVICE_ID_SAITEK_RAT7_OLD	0x0ccb
 #define USB_DEVICE_ID_SAITEK_RAT7	0x0cd7
 #define USB_DEVICE_ID_SAITEK_MMO7	0x0cd0
 
@@ -813,6 +829,9 @@
 #define USB_VENDOR_ID_SKYCABLE			0x1223
 #define	USB_DEVICE_ID_SKYCABLE_WIRELESS_PRESENTER	0x3F07
 
+#define USB_VENDOR_ID_SMK		0x0609
+#define USB_DEVICE_ID_SMK_PS3_BDREMOTE	0x0306
+
 #define USB_VENDOR_ID_SONY			0x054c
 #define USB_DEVICE_ID_SONY_VAIO_VGX_MOUSE	0x024b
 #define USB_DEVICE_ID_SONY_VAIO_VGP_MOUSE	0x0374
@@ -995,10 +1014,18 @@
 #define USB_DEVICE_ID_ZYTRONIC_ZXY100	0x0005
 
 #define USB_VENDOR_ID_PRIMAX	0x0461
+#define USB_DEVICE_ID_PRIMAX_MOUSE_4D22	0x4d22
 #define USB_DEVICE_ID_PRIMAX_KEYBOARD	0x4e05
 
 
 #define USB_VENDOR_ID_RISO_KAGAKU	0x1294	/* Riso Kagaku Corp. */
 #define USB_DEVICE_ID_RI_KA_WEBMAIL	0x1320	/* Webmail Notifier */
 
+#define USB_VENDOR_ID_MULTIPLE_1781	0x1781
+#define USB_DEVICE_ID_RAPHNET_4NES4SNES_OLD	0x0a8d
+
+#define USB_VENDOR_ID_DRACAL_RAPHNET	0x289b
+#define USB_DEVICE_ID_RAPHNET_2NES2SNES	0x0002
+#define USB_DEVICE_ID_RAPHNET_4NES4SNES	0x0003
+
 #endif
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 725f22ca47f..1def4bb1894 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -312,6 +312,9 @@ static const struct hid_device_id hid_battery_quirks[] = {
 			       USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI),
 	  HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE,
+			       USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO),
+	  HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE,
 		USB_DEVICE_ID_APPLE_ALU_WIRELESS_ANSI),
 	  HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE },
 	{}
@@ -1101,6 +1104,23 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct
 		return;
 	}
 
+	/*
+	 * Ignore reports for absolute data if the data didn't change. This is
+	 * not only an optimization but also fixes 'dead' key reports. Some
+	 * RollOver implementations for localized keys (like BACKSLASH/PIPE; HID
+	 * 0x31 and 0x32) report multiple keys, even though a localized keyboard
+	 * can only have one of them physically available. The 'dead' keys
+	 * report constant 0. As all map to the same keycode, they'd confuse
+	 * the input layer. If we filter the 'dead' keys on the HID level, we
+	 * skip the keycode translation and only forward real events.
+	 */
+	if (!(field->flags & (HID_MAIN_ITEM_RELATIVE |
+	                      HID_MAIN_ITEM_BUFFERED_BYTE)) &&
+			      (field->flags & HID_MAIN_ITEM_VARIABLE) &&
+	    usage->usage_index < field->maxusage &&
+	    value == field->value[usage->usage_index])
+		return;
+
 	/* report the usage code as scancode if the key status has changed */
 	if (usage->type == EV_KEY && !!test_bit(usage->code, input->key) != value)
 		input_event(input, EV_MSC, MSC_SCAN, usage->hid);
@@ -1448,8 +1468,9 @@ int hidinput_connect(struct hid_device *hid, unsigned int force)
 				 * UGCI) cram a lot of unrelated inputs into the
 				 * same interface. */
 				hidinput->report = report;
-				if (drv->input_configured)
-					drv->input_configured(hid, hidinput);
+				if (drv->input_configured &&
+				    drv->input_configured(hid, hidinput))
+					goto out_cleanup;
 				if (input_register_device(hidinput->input))
 					goto out_cleanup;
 				hidinput = NULL;
@@ -1470,8 +1491,9 @@ int hidinput_connect(struct hid_device *hid, unsigned int force)
 	}
 
 	if (hidinput) {
-		if (drv->input_configured)
-			drv->input_configured(hid, hidinput);
+		if (drv->input_configured &&
+		    drv->input_configured(hid, hidinput))
+			goto out_cleanup;
 		if (input_register_device(hidinput->input))
 			goto out_cleanup;
 	}
diff --git a/drivers/hid/hid-kye.c b/drivers/hid/hid-kye.c
index b92bf01a1ae..32e6d8d9ded 100644
--- a/drivers/hid/hid-kye.c
+++ b/drivers/hid/hid-kye.c
@@ -268,6 +268,137 @@ static __u8 easypen_m610x_rdesc_fixed[] = {
 	0xC0                          /*  End Collection                  */
 };
 
+
+/* Original PenSketch M912 report descriptor size */
+#define PENSKETCH_M912_RDESC_ORIG_SIZE	482
+
+/* Fixed PenSketch M912 report descriptor */
+static __u8 pensketch_m912_rdesc_fixed[] = {
+	0x05, 0x01,                   /*  Usage Page (Desktop),           */
+	0x08,                         /*  Usage (00h),                    */
+	0xA1, 0x01,                   /*  Collection (Application),       */
+	0x85, 0x05,                   /*    Report ID (5),                */
+	0x06, 0x00, 0xFF,             /*    Usage Page (FF00h),           */
+	0x09, 0x01,                   /*    Usage (01h),                  */
+	0x15, 0x81,                   /*    Logical Minimum (-127),       */
+	0x25, 0x7F,                   /*    Logical Maximum (127),        */
+	0x75, 0x08,                   /*    Report Size (8),              */
+	0x95, 0x07,                   /*    Report Count (7),             */
+	0xB1, 0x02,                   /*    Feature (Variable),           */
+	0xC0,                         /*  End Collection,                 */
+	0x05, 0x0D,                   /*  Usage Page (Digitizer),         */
+	0x09, 0x02,                   /*  Usage (Pen),                    */
+	0xA1, 0x01,                   /*  Collection (Application),       */
+	0x85, 0x10,                   /*    Report ID (16),               */
+	0x09, 0x20,                   /*    Usage (Stylus),               */
+	0xA0,                         /*    Collection (Physical),        */
+	0x09, 0x42,                   /*      Usage (Tip Switch),         */
+	0x09, 0x44,                   /*      Usage (Barrel Switch),      */
+	0x09, 0x46,                   /*      Usage (Tablet Pick),        */
+	0x14,                         /*      Logical Minimum (0),        */
+	0x25, 0x01,                   /*      Logical Maximum (1),        */
+	0x75, 0x01,                   /*      Report Size (1),            */
+	0x95, 0x03,                   /*      Report Count (3),           */
+	0x81, 0x02,                   /*      Input (Variable),           */
+	0x95, 0x04,                   /*      Report Count (4),           */
+	0x81, 0x03,                   /*      Input (Constant, Variable), */
+	0x09, 0x32,                   /*      Usage (In Range),           */
+	0x95, 0x01,                   /*      Report Count (1),           */
+	0x81, 0x02,                   /*      Input (Variable),           */
+	0x75, 0x10,                   /*      Report Size (16),           */
+	0x95, 0x01,                   /*      Report Count (1),           */
+	0xA4,                         /*      Push,                       */
+	0x05, 0x01,                   /*      Usage Page (Desktop),       */
+	0x55, 0xFD,                   /*      Unit Exponent (-3),         */
+	0x65, 0x13,                   /*      Unit (Inch),                */
+	0x14,                         /*      Logical Minimum (0),        */
+	0x34,                         /*      Physical Minimum (0),       */
+	0x09, 0x30,                   /*      Usage (X),                  */
+	0x27, 0x00, 0xF0, 0x00, 0x00, /*      Logical Maximum (61440),    */
+	0x46, 0xE0, 0x2E,             /*      Physical Maximum (12000),   */
+	0x81, 0x02,                   /*      Input (Variable),           */
+	0x09, 0x31,                   /*      Usage (Y),                  */
+	0x27, 0x00, 0xB4, 0x00, 0x00, /*      Logical Maximum (46080),    */
+	0x46, 0x28, 0x23,             /*      Physical Maximum (9000),    */
+	0x81, 0x02,                   /*      Input (Variable),           */
+	0xB4,                         /*      Pop,                        */
+	0x09, 0x30,                   /*      Usage (Tip Pressure),       */
+	0x14,                         /*      Logical Minimum (0),        */
+	0x26, 0xFF, 0x07,             /*      Logical Maximum (2047),     */
+	0x81, 0x02,                   /*      Input (Variable),           */
+	0xC0,                         /*    End Collection,               */
+	0xC0,                         /*  End Collection,                 */
+	0x05, 0x0D,                   /*  Usage Page (Digitizer),         */
+	0x09, 0x21,                   /*  Usage (Puck),                   */
+	0xA1, 0x01,                   /*  Collection (Application),       */
+	0x85, 0x11,                   /*    Report ID (17),               */
+	0x09, 0x21,                   /*    Usage (Puck),                 */
+	0xA0,                         /*    Collection (Physical),        */
+	0x05, 0x09,                   /*      Usage Page (Button),        */
+	0x75, 0x01,                   /*      Report Size (1),            */
+	0x19, 0x01,                   /*      Usage Minimum (01h),        */
+	0x29, 0x03,                   /*      Usage Maximum (03h),        */
+	0x14,                         /*      Logical Minimum (0),        */
+	0x25, 0x01,                   /*      Logical Maximum (1),        */
+	0x95, 0x03,                   /*      Report Count (3),           */
+	0x81, 0x02,                   /*      Input (Variable),           */
+	0x95, 0x04,                   /*      Report Count (4),           */
+	0x81, 0x01,                   /*      Input (Constant),           */
+	0x95, 0x01,                   /*      Report Count (1),           */
+	0x0B, 0x32, 0x00, 0x0D, 0x00, /*      Usage (Digitizer In Range), */
+	0x14,                         /*      Logical Minimum (0),        */
+	0x25, 0x01,                   /*      Logical Maximum (1),        */
+	0x81, 0x02,                   /*      Input (Variable),           */
+	0xA4,                         /*      Push,                       */
+	0x05, 0x01,                   /*      Usage Page (Desktop),       */
+	0x75, 0x10,                   /*      Report Size (16),           */
+	0x95, 0x01,                   /*      Report Count (1),           */
+	0x55, 0xFD,                   /*      Unit Exponent (-3),         */
+	0x65, 0x13,                   /*      Unit (Inch),                */
+	0x14,                         /*      Logical Minimum (0),        */
+	0x34,                         /*      Physical Minimum (0),       */
+	0x09, 0x30,                   /*      Usage (X),                  */
+	0x27, 0x00, 0xF0, 0x00, 0x00, /*      Logical Maximum (61440),    */
+	0x46, 0xE0, 0x2E,             /*      Physical Maximum (12000),   */
+	0x81, 0x02,                   /*      Input (Variable),           */
+	0x09, 0x31,                   /*      Usage (Y),                  */
+	0x27, 0x00, 0xB4, 0x00, 0x00, /*      Logical Maximum (46080),    */
+	0x46, 0x28, 0x23,             /*      Physical Maximum (9000),    */
+	0x81, 0x02,                   /*      Input (Variable),           */
+	0x09, 0x38,                   /*      Usage (Wheel),              */
+	0x75, 0x08,                   /*      Report Size (8),            */
+	0x95, 0x01,                   /*      Report Count (1),           */
+	0x15, 0xFF,                   /*      Logical Minimum (-1),       */
+	0x25, 0x01,                   /*      Logical Maximum (1),        */
+	0x34,                         /*      Physical Minimum (0),       */
+	0x44,                         /*      Physical Maximum (0),       */
+	0x81, 0x06,                   /*      Input (Variable, Relative), */
+	0xB4,                         /*      Pop,                        */
+	0xC0,                         /*    End Collection,               */
+	0xC0,                         /*  End Collection,                 */
+	0x05, 0x0C,                   /*  Usage Page (Consumer),          */
+	0x09, 0x01,                   /*  Usage (Consumer Control),       */
+	0xA1, 0x01,                   /*  Collection (Application),       */
+	0x85, 0x12,                   /*    Report ID (18),               */
+	0x14,                         /*    Logical Minimum (0),          */
+	0x25, 0x01,                   /*    Logical Maximum (1),          */
+	0x75, 0x01,                   /*    Report Size (1),              */
+	0x95, 0x08,                   /*    Report Count (8),             */
+	0x05, 0x0C,                   /*    Usage Page (Consumer),        */
+	0x0A, 0x6A, 0x02,             /*    Usage (AC Delete),            */
+	0x0A, 0x1A, 0x02,             /*    Usage (AC Undo),              */
+	0x0A, 0x01, 0x02,             /*    Usage (AC New),               */
+	0x0A, 0x2F, 0x02,             /*    Usage (AC Zoom),              */
+	0x0A, 0x25, 0x02,             /*    Usage (AC Forward),           */
+	0x0A, 0x24, 0x02,             /*    Usage (AC Back),              */
+	0x0A, 0x2D, 0x02,             /*    Usage (AC Zoom In),           */
+	0x0A, 0x2E, 0x02,             /*    Usage (AC Zoom Out),          */
+	0x81, 0x02,                   /*    Input (Variable),             */
+	0x95, 0x30,                   /*    Report Count (48),            */
+	0x81, 0x03,                   /*    Input (Constant, Variable),   */
+	0xC0                          /*  End Collection                  */
+};
+
 static __u8 *kye_consumer_control_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize, int offset, const char *device_name) {
 	/*
@@ -323,6 +454,7 @@ static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		}
 		break;
 	case USB_DEVICE_ID_KYE_MOUSEPEN_I608X:
+	case USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2:
 		if (*rsize == MOUSEPEN_I608X_RDESC_ORIG_SIZE) {
 			rdesc = mousepen_i608x_rdesc_fixed;
 			*rsize = sizeof(mousepen_i608x_rdesc_fixed);
@@ -334,6 +466,12 @@ static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 			*rsize = sizeof(easypen_m610x_rdesc_fixed);
 		}
 		break;
+	case USB_DEVICE_ID_KYE_PENSKETCH_M912:
+		if (*rsize == PENSKETCH_M912_RDESC_ORIG_SIZE) {
+			rdesc = pensketch_m912_rdesc_fixed;
+			*rsize = sizeof(pensketch_m912_rdesc_fixed);
+		}
+		break;
 	case USB_DEVICE_ID_GENIUS_GILA_GAMING_MOUSE:
 		rdesc = kye_consumer_control_fixup(hdev, rdesc, rsize, 104,
 					"Genius Gila Gaming Mouse");
@@ -415,7 +553,9 @@ static int kye_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	switch (id->product) {
 	case USB_DEVICE_ID_KYE_EASYPEN_I405X:
 	case USB_DEVICE_ID_KYE_MOUSEPEN_I608X:
+	case USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2:
 	case USB_DEVICE_ID_KYE_EASYPEN_M610X:
+	case USB_DEVICE_ID_KYE_PENSKETCH_M912:
 		ret = kye_tablet_enable(hdev);
 		if (ret) {
 			hid_err(hdev, "tablet enabling failed\n");
@@ -446,6 +586,8 @@ static const struct hid_device_id kye_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
 				USB_DEVICE_ID_KYE_MOUSEPEN_I608X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
+				USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
 				USB_DEVICE_ID_KYE_EASYPEN_M610X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
 				USB_DEVICE_ID_GENIUS_GILA_GAMING_MOUSE) },
@@ -453,6 +595,8 @@ static const struct hid_device_id kye_devices[] = {
 				USB_DEVICE_ID_GENIUS_GX_IMPERATOR) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
 				USB_DEVICE_ID_GENIUS_MANTICORE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
+				USB_DEVICE_ID_KYE_PENSKETCH_M912) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, kye_devices);
diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
new file mode 100644
index 00000000000..7dd9163f7e0
--- /dev/null
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -0,0 +1,842 @@
+/*
+ *  HIDPP protocol for Logitech Unifying receivers
+ *
+ *  Copyright (c) 2011 Logitech (c)
+ *  Copyright (c) 2012-2013 Google (c)
+ *  Copyright (c) 2013-2014 Red Hat Inc.
+ */
+
+/*
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; version 2 of the License.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/device.h>
+#include <linux/hid.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/kfifo.h>
+#include <linux/input/mt.h>
+#include <asm/unaligned.h>
+#include "hid-ids.h"
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Benjamin Tissoires <benjamin.tissoires@gmail.com>");
+MODULE_AUTHOR("Nestor Lopez Casado <nlopezcasad@logitech.com>");
+
+#define REPORT_ID_HIDPP_SHORT			0x10
+#define REPORT_ID_HIDPP_LONG			0x11
+
+#define HIDPP_REPORT_SHORT_LENGTH		7
+#define HIDPP_REPORT_LONG_LENGTH		20
+
+#define HIDPP_QUIRK_CLASS_WTP			BIT(0)
+
+/*
+ * There are two hidpp protocols in use, the first version hidpp10 is known
+ * as register access protocol or RAP, the second version hidpp20 is known as
+ * feature access protocol or FAP
+ *
+ * Most older devices (including the Unifying usb receiver) use the RAP protocol
+ * where as most newer devices use the FAP protocol. Both protocols are
+ * compatible with the underlying transport, which could be usb, Unifiying, or
+ * bluetooth. The message lengths are defined by the hid vendor specific report
+ * descriptor for the HIDPP_SHORT report type (total message lenth 7 bytes) and
+ * the HIDPP_LONG report type (total message length 20 bytes)
+ *
+ * The RAP protocol uses both report types, whereas the FAP only uses HIDPP_LONG
+ * messages. The Unifying receiver itself responds to RAP messages (device index
+ * is 0xFF for the receiver), and all messages (short or long) with a device
+ * index between 1 and 6 are passed untouched to the corresponding paired
+ * Unifying device.
+ *
+ * The paired device can be RAP or FAP, it will receive the message untouched
+ * from the Unifiying receiver.
+ */
+
+struct fap {
+	u8 feature_index;
+	u8 funcindex_clientid;
+	u8 params[HIDPP_REPORT_LONG_LENGTH - 4U];
+};
+
+struct rap {
+	u8 sub_id;
+	u8 reg_address;
+	u8 params[HIDPP_REPORT_LONG_LENGTH - 4U];
+};
+
+struct hidpp_report {
+	u8 report_id;
+	u8 device_index;
+	union {
+		struct fap fap;
+		struct rap rap;
+		u8 rawbytes[sizeof(struct fap)];
+	};
+} __packed;
+
+struct hidpp_device {
+	struct hid_device *hid_dev;
+	struct mutex send_mutex;
+	void *send_receive_buf;
+	wait_queue_head_t wait;
+	bool answer_available;
+	u8 protocol_major;
+	u8 protocol_minor;
+
+	void *private_data;
+
+	unsigned long quirks;
+};
+
+
+#define HIDPP_ERROR				0x8f
+#define HIDPP_ERROR_SUCCESS			0x00
+#define HIDPP_ERROR_INVALID_SUBID		0x01
+#define HIDPP_ERROR_INVALID_ADRESS		0x02
+#define HIDPP_ERROR_INVALID_VALUE		0x03
+#define HIDPP_ERROR_CONNECT_FAIL		0x04
+#define HIDPP_ERROR_TOO_MANY_DEVICES		0x05
+#define HIDPP_ERROR_ALREADY_EXISTS		0x06
+#define HIDPP_ERROR_BUSY			0x07
+#define HIDPP_ERROR_UNKNOWN_DEVICE		0x08
+#define HIDPP_ERROR_RESOURCE_ERROR		0x09
+#define HIDPP_ERROR_REQUEST_UNAVAILABLE		0x0a
+#define HIDPP_ERROR_INVALID_PARAM_VALUE		0x0b
+#define HIDPP_ERROR_WRONG_PIN_CODE		0x0c
+
+static int __hidpp_send_report(struct hid_device *hdev,
+				struct hidpp_report *hidpp_report)
+{
+	int fields_count, ret;
+
+	switch (hidpp_report->report_id) {
+	case REPORT_ID_HIDPP_SHORT:
+		fields_count = HIDPP_REPORT_SHORT_LENGTH;
+		break;
+	case REPORT_ID_HIDPP_LONG:
+		fields_count = HIDPP_REPORT_LONG_LENGTH;
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	/*
+	 * set the device_index as the receiver, it will be overwritten by
+	 * hid_hw_request if needed
+	 */
+	hidpp_report->device_index = 0xff;
+
+	ret = hid_hw_raw_request(hdev, hidpp_report->report_id,
+		(u8 *)hidpp_report, fields_count, HID_OUTPUT_REPORT,
+		HID_REQ_SET_REPORT);
+
+	return ret == fields_count ? 0 : -1;
+}
+
+static int hidpp_send_message_sync(struct hidpp_device *hidpp,
+	struct hidpp_report *message,
+	struct hidpp_report *response)
+{
+	int ret;
+
+	mutex_lock(&hidpp->send_mutex);
+
+	hidpp->send_receive_buf = response;
+	hidpp->answer_available = false;
+
+	/*
+	 * So that we can later validate the answer when it arrives
+	 * in hidpp_raw_event
+	 */
+	*response = *message;
+
+	ret = __hidpp_send_report(hidpp->hid_dev, message);
+
+	if (ret) {
+		dbg_hid("__hidpp_send_report returned err: %d\n", ret);
+		memset(response, 0, sizeof(struct hidpp_report));
+		goto exit;
+	}
+
+	if (!wait_event_timeout(hidpp->wait, hidpp->answer_available,
+				5*HZ)) {
+		dbg_hid("%s:timeout waiting for response\n", __func__);
+		memset(response, 0, sizeof(struct hidpp_report));
+		ret = -ETIMEDOUT;
+	}
+
+	if (response->report_id == REPORT_ID_HIDPP_SHORT &&
+	    response->fap.feature_index == HIDPP_ERROR) {
+		ret = response->fap.params[1];
+		dbg_hid("__hidpp_send_report got hidpp error %02X\n", ret);
+		goto exit;
+	}
+
+exit:
+	mutex_unlock(&hidpp->send_mutex);
+	return ret;
+
+}
+
+static int hidpp_send_fap_command_sync(struct hidpp_device *hidpp,
+	u8 feat_index, u8 funcindex_clientid, u8 *params, int param_count,
+	struct hidpp_report *response)
+{
+	struct hidpp_report *message = kzalloc(sizeof(struct hidpp_report),
+			GFP_KERNEL);
+	int ret;
+
+	if (param_count > sizeof(message->fap.params))
+		return -EINVAL;
+
+	message->report_id = REPORT_ID_HIDPP_LONG;
+	message->fap.feature_index = feat_index;
+	message->fap.funcindex_clientid = funcindex_clientid;
+	memcpy(&message->fap.params, params, param_count);
+
+	ret = hidpp_send_message_sync(hidpp, message, response);
+	kfree(message);
+	return ret;
+}
+
+static inline bool hidpp_match_answer(struct hidpp_report *question,
+		struct hidpp_report *answer)
+{
+	return (answer->fap.feature_index == question->fap.feature_index) &&
+	   (answer->fap.funcindex_clientid == question->fap.funcindex_clientid);
+}
+
+static inline bool hidpp_match_error(struct hidpp_report *question,
+		struct hidpp_report *answer)
+{
+	return (answer->fap.feature_index == HIDPP_ERROR) &&
+	    (answer->fap.funcindex_clientid == question->fap.feature_index) &&
+	    (answer->fap.params[0] == question->fap.funcindex_clientid);
+}
+
+/* -------------------------------------------------------------------------- */
+/* 0x0000: Root                                                               */
+/* -------------------------------------------------------------------------- */
+
+#define HIDPP_PAGE_ROOT					0x0000
+#define HIDPP_PAGE_ROOT_IDX				0x00
+
+#define CMD_ROOT_GET_FEATURE				0x01
+#define CMD_ROOT_GET_PROTOCOL_VERSION			0x11
+
+static int hidpp_root_get_feature(struct hidpp_device *hidpp, u16 feature,
+	u8 *feature_index, u8 *feature_type)
+{
+	struct hidpp_report response;
+	int ret;
+	u8 params[2] = { feature >> 8, feature & 0x00FF };
+
+	ret = hidpp_send_fap_command_sync(hidpp,
+			HIDPP_PAGE_ROOT_IDX,
+			CMD_ROOT_GET_FEATURE,
+			params, 2, &response);
+	if (ret)
+		return ret;
+
+	*feature_index = response.fap.params[0];
+	*feature_type = response.fap.params[1];
+
+	return ret;
+}
+
+static int hidpp_root_get_protocol_version(struct hidpp_device *hidpp)
+{
+	struct hidpp_report response;
+	int ret;
+
+	ret = hidpp_send_fap_command_sync(hidpp,
+			HIDPP_PAGE_ROOT_IDX,
+			CMD_ROOT_GET_PROTOCOL_VERSION,
+			NULL, 0, &response);
+
+	if (ret == 1) {
+		hidpp->protocol_major = 1;
+		hidpp->protocol_minor = 0;
+		return 0;
+	}
+
+	if (ret)
+		return -ret;
+
+	hidpp->protocol_major = response.fap.params[0];
+	hidpp->protocol_minor = response.fap.params[1];
+
+	return ret;
+}
+
+static bool hidpp_is_connected(struct hidpp_device *hidpp)
+{
+	int ret;
+
+	ret = hidpp_root_get_protocol_version(hidpp);
+	if (!ret)
+		hid_dbg(hidpp->hid_dev, "HID++ %u.%u device connected.\n",
+			hidpp->protocol_major, hidpp->protocol_minor);
+	return ret == 0;
+}
+
+/* -------------------------------------------------------------------------- */
+/* 0x0005: GetDeviceNameType                                                  */
+/* -------------------------------------------------------------------------- */
+
+#define HIDPP_PAGE_GET_DEVICE_NAME_TYPE			0x0005
+
+#define CMD_GET_DEVICE_NAME_TYPE_GET_COUNT		0x01
+#define CMD_GET_DEVICE_NAME_TYPE_GET_DEVICE_NAME	0x11
+#define CMD_GET_DEVICE_NAME_TYPE_GET_TYPE		0x21
+
+static int hidpp_devicenametype_get_count(struct hidpp_device *hidpp,
+	u8 feature_index, u8 *nameLength)
+{
+	struct hidpp_report response;
+	int ret;
+
+	ret = hidpp_send_fap_command_sync(hidpp, feature_index,
+		CMD_GET_DEVICE_NAME_TYPE_GET_COUNT, NULL, 0, &response);
+
+	if (ret)
+		return -ret;
+
+	*nameLength = response.fap.params[0];
+
+	return ret;
+}
+
+static int hidpp_devicenametype_get_device_name(struct hidpp_device *hidpp,
+	u8 feature_index, u8 char_index, char *device_name, int len_buf)
+{
+	struct hidpp_report response;
+	int ret, i;
+	int count;
+
+	ret = hidpp_send_fap_command_sync(hidpp, feature_index,
+		CMD_GET_DEVICE_NAME_TYPE_GET_DEVICE_NAME, &char_index, 1,
+		&response);
+
+	if (ret)
+		return -ret;
+
+	if (response.report_id == REPORT_ID_HIDPP_LONG)
+		count = HIDPP_REPORT_LONG_LENGTH - 4;
+	else
+		count = HIDPP_REPORT_SHORT_LENGTH - 4;
+
+	if (len_buf < count)
+		count = len_buf;
+
+	for (i = 0; i < count; i++)
+		device_name[i] = response.fap.params[i];
+
+	return count;
+}
+
+static char *hidpp_get_device_name(struct hidpp_device *hidpp, u8 *name_length)
+{
+	u8 feature_type;
+	u8 feature_index;
+	u8 __name_length;
+	char *name;
+	unsigned index = 0;
+	int ret;
+
+	ret = hidpp_root_get_feature(hidpp, HIDPP_PAGE_GET_DEVICE_NAME_TYPE,
+		&feature_index, &feature_type);
+	if (ret)
+		goto out_err;
+
+	ret = hidpp_devicenametype_get_count(hidpp, feature_index,
+		&__name_length);
+	if (ret)
+		goto out_err;
+
+	name = kzalloc(__name_length + 1, GFP_KERNEL);
+	if (!name)
+		goto out_err;
+
+	*name_length = __name_length + 1;
+	while (index < __name_length)
+		index += hidpp_devicenametype_get_device_name(hidpp,
+			feature_index, index, name + index,
+			__name_length - index);
+
+	return name;
+
+out_err:
+	*name_length = 0;
+	return NULL;
+}
+
+/* -------------------------------------------------------------------------- */
+/* 0x6100: TouchPadRawXY                                                      */
+/* -------------------------------------------------------------------------- */
+
+#define HIDPP_PAGE_TOUCHPAD_RAW_XY			0x6100
+
+#define CMD_TOUCHPAD_GET_RAW_INFO			0x01
+
+#define TOUCHPAD_RAW_XY_ORIGIN_LOWER_LEFT		0x01
+#define TOUCHPAD_RAW_XY_ORIGIN_UPPER_LEFT		0x03
+
+struct hidpp_touchpad_raw_info {
+	u16 x_size;
+	u16 y_size;
+	u8 z_range;
+	u8 area_range;
+	u8 timestamp_unit;
+	u8 maxcontacts;
+	u8 origin;
+	u16 res;
+};
+
+struct hidpp_touchpad_raw_xy_finger {
+	u8 contact_type;
+	u8 contact_status;
+	u16 x;
+	u16 y;
+	u8 z;
+	u8 area;
+	u8 finger_id;
+};
+
+struct hidpp_touchpad_raw_xy {
+	u16 timestamp;
+	struct hidpp_touchpad_raw_xy_finger fingers[2];
+	u8 spurious_flag;
+	u8 end_of_frame;
+	u8 finger_count;
+	u8 button;
+};
+
+static int hidpp_touchpad_get_raw_info(struct hidpp_device *hidpp,
+	u8 feature_index, struct hidpp_touchpad_raw_info *raw_info)
+{
+	struct hidpp_report response;
+	int ret;
+	u8 *params = (u8 *)response.fap.params;
+
+	ret = hidpp_send_fap_command_sync(hidpp, feature_index,
+		CMD_TOUCHPAD_GET_RAW_INFO, NULL, 0, &response);
+
+	if (ret)
+		return -ret;
+
+	raw_info->x_size = get_unaligned_be16(&params[0]);
+	raw_info->y_size = get_unaligned_be16(&params[2]);
+	raw_info->z_range = params[4];
+	raw_info->area_range = params[5];
+	raw_info->maxcontacts = params[7];
+	raw_info->origin = params[8];
+	/* res is given in unit per inch */
+	raw_info->res = get_unaligned_be16(&params[13]) * 2 / 51;
+
+	return ret;
+}
+
+/* ************************************************************************** */
+/*                                                                            */
+/* Device Support                                                             */
+/*                                                                            */
+/* ************************************************************************** */
+
+/* -------------------------------------------------------------------------- */
+/* Touchpad HID++ devices                                                     */
+/* -------------------------------------------------------------------------- */
+
+struct wtp_data {
+	struct input_dev *input;
+	u16 x_size, y_size;
+	u8 finger_count;
+	u8 mt_feature_index;
+	u8 button_feature_index;
+	u8 maxcontacts;
+	bool flip_y;
+	unsigned int resolution;
+};
+
+static int wtp_input_mapping(struct hid_device *hdev, struct hid_input *hi,
+		struct hid_field *field, struct hid_usage *usage,
+		unsigned long **bit, int *max)
+{
+	return -1;
+}
+
+static void wtp_input_configured(struct hid_device *hdev,
+				struct hid_input *hidinput)
+{
+	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
+	struct wtp_data *wd = hidpp->private_data;
+	struct input_dev *input_dev = hidinput->input;
+
+	__set_bit(EV_ABS, input_dev->evbit);
+	__set_bit(EV_KEY, input_dev->evbit);
+	__clear_bit(EV_REL, input_dev->evbit);
+	__clear_bit(EV_LED, input_dev->evbit);
+
+	input_set_abs_params(input_dev, ABS_MT_POSITION_X, 0, wd->x_size, 0, 0);
+	input_abs_set_res(input_dev, ABS_MT_POSITION_X, wd->resolution);
+	input_set_abs_params(input_dev, ABS_MT_POSITION_Y, 0, wd->y_size, 0, 0);
+	input_abs_set_res(input_dev, ABS_MT_POSITION_Y, wd->resolution);
+
+	/* Max pressure is not given by the devices, pick one */
+	input_set_abs_params(input_dev, ABS_MT_PRESSURE, 0, 50, 0, 0);
+
+	input_set_capability(input_dev, EV_KEY, BTN_LEFT);
+
+	__set_bit(INPUT_PROP_BUTTONPAD, input_dev->propbit);
+
+	input_mt_init_slots(input_dev, wd->maxcontacts, INPUT_MT_POINTER |
+		INPUT_MT_DROP_UNUSED);
+
+	wd->input = input_dev;
+}
+
+static void wtp_touch_event(struct wtp_data *wd,
+	struct hidpp_touchpad_raw_xy_finger *touch_report)
+{
+	int slot;
+
+	if (!touch_report->finger_id || touch_report->contact_type)
+		/* no actual data */
+		return;
+
+	slot = input_mt_get_slot_by_key(wd->input, touch_report->finger_id);
+
+	input_mt_slot(wd->input, slot);
+	input_mt_report_slot_state(wd->input, MT_TOOL_FINGER,
+					touch_report->contact_status);
+	if (touch_report->contact_status) {
+		input_event(wd->input, EV_ABS, ABS_MT_POSITION_X,
+				touch_report->x);
+		input_event(wd->input, EV_ABS, ABS_MT_POSITION_Y,
+				wd->flip_y ? wd->y_size - touch_report->y :
+					     touch_report->y);
+		input_event(wd->input, EV_ABS, ABS_MT_PRESSURE,
+				touch_report->area);
+	}
+}
+
+static void wtp_send_raw_xy_event(struct hidpp_device *hidpp,
+		struct hidpp_touchpad_raw_xy *raw)
+{
+	struct wtp_data *wd = hidpp->private_data;
+	int i;
+
+	for (i = 0; i < 2; i++)
+		wtp_touch_event(wd, &(raw->fingers[i]));
+
+	if (raw->end_of_frame)
+		input_event(wd->input, EV_KEY, BTN_LEFT, raw->button);
+
+	if (raw->end_of_frame || raw->finger_count <= 2) {
+		input_mt_sync_frame(wd->input);
+		input_sync(wd->input);
+	}
+}
+
+static int wtp_mouse_raw_xy_event(struct hidpp_device *hidpp, u8 *data)
+{
+	struct wtp_data *wd = hidpp->private_data;
+	u8 c1_area = ((data[7] & 0xf) * (data[7] & 0xf) +
+		      (data[7] >> 4) * (data[7] >> 4)) / 2;
+	u8 c2_area = ((data[13] & 0xf) * (data[13] & 0xf) +
+		      (data[13] >> 4) * (data[13] >> 4)) / 2;
+	struct hidpp_touchpad_raw_xy raw = {
+		.timestamp = data[1],
+		.fingers = {
+			{
+				.contact_type = 0,
+				.contact_status = !!data[7],
+				.x = get_unaligned_le16(&data[3]),
+				.y = get_unaligned_le16(&data[5]),
+				.z = c1_area,
+				.area = c1_area,
+				.finger_id = data[2],
+			}, {
+				.contact_type = 0,
+				.contact_status = !!data[13],
+				.x = get_unaligned_le16(&data[9]),
+				.y = get_unaligned_le16(&data[11]),
+				.z = c2_area,
+				.area = c2_area,
+				.finger_id = data[8],
+			}
+		},
+		.finger_count = wd->maxcontacts,
+		.spurious_flag = 0,
+		.end_of_frame = (data[0] >> 7) == 0,
+		.button = data[0] & 0x01,
+	};
+
+	wtp_send_raw_xy_event(hidpp, &raw);
+
+	return 1;
+}
+
+static int wtp_raw_event(struct hid_device *hdev, u8 *data, int size)
+{
+	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
+	struct wtp_data *wd = hidpp->private_data;
+
+	if (!wd || !wd->input || (data[0] != 0x02) || size < 21)
+		return 1;
+
+	return wtp_mouse_raw_xy_event(hidpp, &data[7]);
+}
+
+static int wtp_get_config(struct hidpp_device *hidpp)
+{
+	struct wtp_data *wd = hidpp->private_data;
+	struct hidpp_touchpad_raw_info raw_info = {0};
+	u8 feature_type;
+	int ret;
+
+	ret = hidpp_root_get_feature(hidpp, HIDPP_PAGE_TOUCHPAD_RAW_XY,
+		&wd->mt_feature_index, &feature_type);
+	if (ret)
+		/* means that the device is not powered up */
+		return ret;
+
+	ret = hidpp_touchpad_get_raw_info(hidpp, wd->mt_feature_index,
+		&raw_info);
+	if (ret)
+		return ret;
+
+	wd->x_size = raw_info.x_size;
+	wd->y_size = raw_info.y_size;
+	wd->maxcontacts = raw_info.maxcontacts;
+	wd->flip_y = raw_info.origin == TOUCHPAD_RAW_XY_ORIGIN_LOWER_LEFT;
+	wd->resolution = raw_info.res;
+
+	return 0;
+}
+
+static int wtp_allocate(struct hid_device *hdev, const struct hid_device_id *id)
+{
+	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
+	struct wtp_data *wd;
+
+	wd = devm_kzalloc(&hdev->dev, sizeof(struct wtp_data),
+			GFP_KERNEL);
+	if (!wd)
+		return -ENOMEM;
+
+	hidpp->private_data = wd;
+
+	return 0;
+};
+
+/* -------------------------------------------------------------------------- */
+/* Generic HID++ devices                                                      */
+/* -------------------------------------------------------------------------- */
+
+static int hidpp_input_mapping(struct hid_device *hdev, struct hid_input *hi,
+		struct hid_field *field, struct hid_usage *usage,
+		unsigned long **bit, int *max)
+{
+	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
+
+	if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP)
+		return wtp_input_mapping(hdev, hi, field, usage, bit, max);
+
+	return 0;
+}
+
+static void hidpp_input_configured(struct hid_device *hdev,
+				struct hid_input *hidinput)
+{
+	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
+
+	if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP)
+		wtp_input_configured(hdev, hidinput);
+}
+
+static int hidpp_raw_hidpp_event(struct hidpp_device *hidpp, u8 *data,
+		int size)
+{
+	struct hidpp_report *question = hidpp->send_receive_buf;
+	struct hidpp_report *answer = hidpp->send_receive_buf;
+	struct hidpp_report *report = (struct hidpp_report *)data;
+
+	/*
+	 * If the mutex is locked then we have a pending answer from a
+	 * previoulsly sent command
+	 */
+	if (unlikely(mutex_is_locked(&hidpp->send_mutex))) {
+		/*
+		 * Check for a correct hidpp20 answer or the corresponding
+		 * error
+		 */
+		if (hidpp_match_answer(question, report) ||
+				hidpp_match_error(question, report)) {
+			*answer = *report;
+			hidpp->answer_available = true;
+			wake_up(&hidpp->wait);
+			/*
+			 * This was an answer to a command that this driver sent
+			 * We return 1 to hid-core to avoid forwarding the
+			 * command upstream as it has been treated by the driver
+			 */
+
+			return 1;
+		}
+	}
+
+	if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP)
+		return wtp_raw_event(hidpp->hid_dev, data, size);
+
+	return 0;
+}
+
+static int hidpp_raw_event(struct hid_device *hdev, struct hid_report *report,
+		u8 *data, int size)
+{
+	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
+
+	switch (data[0]) {
+	case REPORT_ID_HIDPP_LONG:
+		if (size != HIDPP_REPORT_LONG_LENGTH) {
+			hid_err(hdev, "received hid++ report of bad size (%d)",
+				size);
+			return 1;
+		}
+		return hidpp_raw_hidpp_event(hidpp, data, size);
+	case REPORT_ID_HIDPP_SHORT:
+		if (size != HIDPP_REPORT_SHORT_LENGTH) {
+			hid_err(hdev, "received hid++ report of bad size (%d)",
+				size);
+			return 1;
+		}
+		return hidpp_raw_hidpp_event(hidpp, data, size);
+	}
+
+	if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP)
+		return wtp_raw_event(hdev, data, size);
+
+	return 0;
+}
+
+static void hidpp_overwrite_name(struct hid_device *hdev)
+{
+	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
+	char *name;
+	u8 name_length;
+
+	name = hidpp_get_device_name(hidpp, &name_length);
+
+	if (!name)
+		hid_err(hdev, "unable to retrieve the name of the device");
+	else
+		snprintf(hdev->name, sizeof(hdev->name), "%s", name);
+
+	kfree(name);
+}
+
+static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
+{
+	struct hidpp_device *hidpp;
+	int ret;
+	bool connected;
+
+	hidpp = devm_kzalloc(&hdev->dev, sizeof(struct hidpp_device),
+			GFP_KERNEL);
+	if (!hidpp)
+		return -ENOMEM;
+
+	hidpp->hid_dev = hdev;
+	hid_set_drvdata(hdev, hidpp);
+
+	hidpp->quirks = id->driver_data;
+
+	if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP) {
+		ret = wtp_allocate(hdev, id);
+		if (ret)
+			return ret;
+	}
+
+	mutex_init(&hidpp->send_mutex);
+	init_waitqueue_head(&hidpp->wait);
+
+	ret = hid_parse(hdev);
+	if (ret) {
+		hid_err(hdev, "%s:parse failed\n", __func__);
+		goto hid_parse_fail;
+	}
+
+	/* Allow incoming packets */
+	hid_device_io_start(hdev);
+
+	connected = hidpp_is_connected(hidpp);
+	if (!connected) {
+		hid_err(hdev, "Device not connected");
+		goto hid_parse_fail;
+	}
+
+	/* the device is connected, we can ask for its name */
+	hid_info(hdev, "HID++ %u.%u device connected.\n",
+		 hidpp->protocol_major, hidpp->protocol_minor);
+	hidpp_overwrite_name(hdev);
+
+	if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP) {
+		ret = wtp_get_config(hidpp);
+		if (ret)
+			goto hid_parse_fail;
+	}
+
+	/* Block incoming packets */
+	hid_device_io_stop(hdev);
+
+	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
+	if (ret) {
+		hid_err(hdev, "%s:hid_hw_start returned error\n", __func__);
+		goto hid_hw_start_fail;
+	}
+
+	return ret;
+
+hid_hw_start_fail:
+hid_parse_fail:
+	mutex_destroy(&hidpp->send_mutex);
+	hid_set_drvdata(hdev, NULL);
+	return ret;
+}
+
+static void hidpp_remove(struct hid_device *hdev)
+{
+	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
+
+	mutex_destroy(&hidpp->send_mutex);
+	hid_hw_stop(hdev);
+}
+
+static const struct hid_device_id hidpp_devices[] = {
+	{ /* wireless touchpad T651 */
+	  HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH,
+		USB_DEVICE_ID_LOGITECH_T651),
+	  .driver_data = HIDPP_QUIRK_CLASS_WTP },
+	{}
+};
+
+MODULE_DEVICE_TABLE(hid, hidpp_devices);
+
+static struct hid_driver hidpp_driver = {
+	.name = "logitech-hidpp-device",
+	.id_table = hidpp_devices,
+	.probe = hidpp_probe,
+	.remove = hidpp_remove,
+	.raw_event = hidpp_raw_event,
+	.input_configured = hidpp_input_configured,
+	.input_mapping = hidpp_input_mapping,
+};
+
+module_hid_driver(hidpp_driver);
diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c
index 8ba17a946f2..0dbc2a0c25c 100644
--- a/drivers/hid/hid-microsoft.c
+++ b/drivers/hid/hid-microsoft.c
@@ -264,6 +264,8 @@ static const struct hid_device_id ms_devices[] = {
 		.driver_data = MS_ERGONOMY },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_NE4K_JP),
 		.driver_data = MS_ERGONOMY },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_NE7K),
+		.driver_data = MS_ERGONOMY },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_LK6K),
 		.driver_data = MS_ERGONOMY | MS_RDESC },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_USB),
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 51e25b9407f..e6cab622fdf 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -372,6 +372,16 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 		td->inputmode_value = MT_INPUTMODE_TOUCHPAD;
 	}
 
+	/* Only map fields from TouchScreen or TouchPad collections.
+         * We need to ignore fields that belong to other collections
+         * such as Mouse that might have the same GenericDesktop usages. */
+	if (field->application == HID_DG_TOUCHSCREEN)
+		set_bit(INPUT_PROP_DIRECT, hi->input->propbit);
+	else if (field->application == HID_DG_TOUCHPAD)
+		set_bit(INPUT_PROP_POINTER, hi->input->propbit);
+	else
+		return 0;
+
 	if (usage->usage_index)
 		prev_usage = &field->usage[usage->usage_index - 1];
 
@@ -701,12 +711,13 @@ static void mt_touch_report(struct hid_device *hid, struct hid_report *report)
 		mt_sync_frame(td, report->field[0]->hidinput->input);
 }
 
-static void mt_touch_input_configured(struct hid_device *hdev,
+static int mt_touch_input_configured(struct hid_device *hdev,
 					struct hid_input *hi)
 {
 	struct mt_device *td = hid_get_drvdata(hdev);
 	struct mt_class *cls = &td->mtclass;
 	struct input_dev *input = hi->input;
+	int ret;
 
 	if (!td->maxcontacts)
 		td->maxcontacts = MT_DEFAULT_MAXCONTACT;
@@ -721,9 +732,12 @@ static void mt_touch_input_configured(struct hid_device *hdev,
 	if (cls->quirks & MT_QUIRK_NOT_SEEN_MEANS_UP)
 		td->mt_flags |= INPUT_MT_DROP_UNUSED;
 
-	input_mt_init_slots(input, td->maxcontacts, td->mt_flags);
+	ret = input_mt_init_slots(input, td->maxcontacts, td->mt_flags);
+	if (ret)
+		return ret;
 
 	td->mt_flags = 0;
+	return 0;
 }
 
 static int mt_input_mapping(struct hid_device *hdev, struct hid_input *hi,
@@ -877,15 +891,16 @@ static void mt_post_parse(struct mt_device *td)
 		cls->quirks &= ~MT_QUIRK_CONTACT_CNT_ACCURATE;
 }
 
-static void mt_input_configured(struct hid_device *hdev, struct hid_input *hi)
+static int mt_input_configured(struct hid_device *hdev, struct hid_input *hi)
 {
 	struct mt_device *td = hid_get_drvdata(hdev);
 	char *name;
 	const char *suffix = NULL;
 	struct hid_field *field = hi->report->field[0];
+	int ret = 0;
 
 	if (hi->report->id == td->mt_report_id)
-		mt_touch_input_configured(hdev, hi);
+		ret = mt_touch_input_configured(hdev, hi);
 
 	/*
 	 * some egalax touchscreens have "application == HID_DG_TOUCHSCREEN"
@@ -936,6 +951,7 @@ static void mt_input_configured(struct hid_device *hdev, struct hid_input *hi)
 			hi->input->name = name;
 		}
 	}
+	return ret;
 }
 
 static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id)
diff --git a/drivers/hid/hid-rmi.c b/drivers/hid/hid-rmi.c
index 3cccff73b9b..a994477bd25 100644
--- a/drivers/hid/hid-rmi.c
+++ b/drivers/hid/hid-rmi.c
@@ -584,11 +584,15 @@ static int rmi_populate_f11(struct hid_device *hdev)
 	bool has_query10 = false;
 	bool has_query11;
 	bool has_query12;
+	bool has_query27;
+	bool has_query28;
+	bool has_query36 = false;
 	bool has_physical_props;
 	bool has_gestures;
 	bool has_rel;
+	bool has_data40 = false;
 	unsigned x_size, y_size;
-	u16 query12_offset;
+	u16 query_offset;
 
 	if (!data->f11.query_base_addr) {
 		hid_err(hdev, "No 2D sensor found, giving up.\n");
@@ -604,6 +608,8 @@ static int rmi_populate_f11(struct hid_device *hdev)
 	has_query9 = !!(buf[0] & BIT(3));
 	has_query11 = !!(buf[0] & BIT(4));
 	has_query12 = !!(buf[0] & BIT(5));
+	has_query27 = !!(buf[0] & BIT(6));
+	has_query28 = !!(buf[0] & BIT(7));
 
 	/* query 1 to get the max number of fingers */
 	ret = rmi_read(hdev, data->f11.query_base_addr + 1, buf);
@@ -642,27 +648,27 @@ static int rmi_populate_f11(struct hid_device *hdev)
 	 * +1 for query 5 which is present since absolute events are
 	 * reported and +1 for query 12.
 	 */
-	query12_offset = 6;
+	query_offset = 6;
 
 	if (has_rel)
-		++query12_offset; /* query 6 is present */
+		++query_offset; /* query 6 is present */
 
 	if (has_gestures)
-		query12_offset += 2; /* query 7 and 8 are present */
+		query_offset += 2; /* query 7 and 8 are present */
 
 	if (has_query9)
-		++query12_offset;
+		++query_offset;
 
 	if (has_query10)
-		++query12_offset;
+		++query_offset;
 
 	if (has_query11)
-		++query12_offset;
+		++query_offset;
 
 	/* query 12 to know if the physical properties are reported */
 	if (has_query12) {
 		ret = rmi_read(hdev, data->f11.query_base_addr
-				+ query12_offset, buf);
+				+ query_offset, buf);
 		if (ret) {
 			hid_err(hdev, "can not get query 12: %d.\n", ret);
 			return ret;
@@ -670,9 +676,10 @@ static int rmi_populate_f11(struct hid_device *hdev)
 		has_physical_props = !!(buf[0] & BIT(5));
 
 		if (has_physical_props) {
+			query_offset += 1;
 			ret = rmi_read_block(hdev,
 					data->f11.query_base_addr
-						+ query12_offset + 1, buf, 4);
+						+ query_offset, buf, 4);
 			if (ret) {
 				hid_err(hdev, "can not read query 15-18: %d.\n",
 					ret);
@@ -687,9 +694,45 @@ static int rmi_populate_f11(struct hid_device *hdev)
 
 			hid_info(hdev, "%s: size in mm: %d x %d\n",
 				 __func__, data->x_size_mm, data->y_size_mm);
+
+			/*
+			 * query 15 - 18 contain the size of the sensor
+			 * and query 19 - 26 contain bezel dimensions
+			 */
+			query_offset += 12;
+		}
+	}
+
+	if (has_query27)
+		++query_offset;
+
+	if (has_query28) {
+		ret = rmi_read(hdev, data->f11.query_base_addr
+				+ query_offset, buf);
+		if (ret) {
+			hid_err(hdev, "can not get query 28: %d.\n", ret);
+			return ret;
+		}
+
+		has_query36 = !!(buf[0] & BIT(6));
+	}
+
+	if (has_query36) {
+		query_offset += 2;
+		ret = rmi_read(hdev, data->f11.query_base_addr
+				+ query_offset, buf);
+		if (ret) {
+			hid_err(hdev, "can not get query 36: %d.\n", ret);
+			return ret;
 		}
+
+		has_data40 = !!(buf[0] & BIT(5));
 	}
 
+
+	if (has_data40)
+		data->f11.report_size += data->max_fingers * 2;
+
 	/*
 	 * retrieve the ctrl registers
 	 * the ctrl register has a size of 20 but a fw bug split it into 16 + 4,
diff --git a/drivers/hid/hid-roccat-pyra.c b/drivers/hid/hid-roccat-pyra.c
index 1a07e07d99a..47d7e74231e 100644
--- a/drivers/hid/hid-roccat-pyra.c
+++ b/drivers/hid/hid-roccat-pyra.c
@@ -35,6 +35,8 @@ static struct class *pyra_class;
 static void profile_activated(struct pyra_device *pyra,
 		unsigned int new_profile)
 {
+	if (new_profile >= ARRAY_SIZE(pyra->profile_settings))
+		return;
 	pyra->actual_profile = new_profile;
 	pyra->actual_cpi = pyra->profile_settings[pyra->actual_profile].y_cpi;
 }
@@ -257,9 +259,11 @@ static ssize_t pyra_sysfs_write_settings(struct file *fp,
 	if (off != 0 || count != PYRA_SIZE_SETTINGS)
 		return -EINVAL;
 
-	mutex_lock(&pyra->pyra_lock);
-
 	settings = (struct pyra_settings const *)buf;
+	if (settings->startup_profile >= ARRAY_SIZE(pyra->profile_settings))
+		return -EINVAL;
+
+	mutex_lock(&pyra->pyra_lock);
 
 	retval = pyra_set_settings(usb_dev, settings);
 	if (retval) {
diff --git a/drivers/hid/hid-saitek.c b/drivers/hid/hid-saitek.c
index 69cca1476a0..ccd14204861 100644
--- a/drivers/hid/hid-saitek.c
+++ b/drivers/hid/hid-saitek.c
@@ -177,6 +177,8 @@ static int saitek_event(struct hid_device *hdev, struct hid_field *field,
 static const struct hid_device_id saitek_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_PS1000),
 		.driver_data = SAITEK_FIX_PS1000 },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RAT7_OLD),
+		.driver_data = SAITEK_RELEASE_MODE_RAT7 },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RAT7),
 		.driver_data = SAITEK_RELEASE_MODE_RAT7 },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_MMO7),
diff --git a/drivers/hid/hid-sjoy.c b/drivers/hid/hid-sjoy.c
index 37845eccddb..36b6470af94 100644
--- a/drivers/hid/hid-sjoy.c
+++ b/drivers/hid/hid-sjoy.c
@@ -166,6 +166,9 @@ static const struct hid_device_id sjoy_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_DUAL_USB_JOYPAD),
 		.driver_data = HID_QUIRK_MULTI_INPUT |
 			       HID_QUIRK_SKIP_OUTPUT_REPORTS },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_PLAYDOTCOM, USB_DEVICE_ID_PLAYDOTCOM_EMS_USBII),
+		.driver_data = HID_QUIRK_MULTI_INPUT |
+			       HID_QUIRK_SKIP_OUTPUT_REPORTS },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, sjoy_devices);
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index bc4269e559f..15b3475e641 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -2034,6 +2034,9 @@ static const struct hid_device_id sony_devices[] = {
 	/* Logitech Harmony Adapter for PS3 */
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_HARMONY_PS3),
 		.driver_data = PS3REMOTE },
+	/* SMK-Link PS3 BD Remote Control */
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SMK, USB_DEVICE_ID_SMK_PS3_BDREMOTE),
+		.driver_data = PS3REMOTE },
 	/* Sony Dualshock 4 controllers for PS4 */
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER),
 		.driver_data = DUALSHOCK4_CONTROLLER_USB },
diff --git a/drivers/hid/hid-steelseries.c b/drivers/hid/hid-steelseries.c
index 29f328f411f..8060650dcfe 100644
--- a/drivers/hid/hid-steelseries.c
+++ b/drivers/hid/hid-steelseries.c
@@ -254,6 +254,11 @@ static int steelseries_srws1_probe(struct hid_device *hdev,
 		goto err_free;
 	}
 
+	if (!hid_validate_values(hdev, HID_OUTPUT_REPORT, 0, 0, 16)) {
+		ret = -ENODEV;
+		goto err_free;
+	}
+
 	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
 	if (ret) {
 		hid_err(hdev, "hw start failed\n");
diff --git a/drivers/hid/hid-uclogic.c b/drivers/hid/hid-uclogic.c
index fb8b516ff0e..22dccce6a85 100644
--- a/drivers/hid/hid-uclogic.c
+++ b/drivers/hid/hid-uclogic.c
@@ -626,6 +626,32 @@ static __u8 *uclogic_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 	return rdesc;
 }
 
+static int uclogic_probe(struct hid_device *hdev,
+		const struct hid_device_id *id)
+{
+	int rc;
+
+	/*
+	 * libinput requires the pad interface to be on a different node
+	 * than the pen, so use QUIRK_MULTI_INPUT for all tablets.
+	 */
+	hdev->quirks |= HID_QUIRK_MULTI_INPUT;
+
+	rc = hid_parse(hdev);
+	if (rc) {
+		hid_err(hdev, "parse failed\n");
+		return rc;
+	}
+
+	rc = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
+	if (rc) {
+		hid_err(hdev, "hw start failed\n");
+		return rc;
+	}
+
+	return 0;
+}
+
 static const struct hid_device_id uclogic_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC,
 				USB_DEVICE_ID_UCLOGIC_TABLET_PF1209) },
@@ -648,6 +674,7 @@ MODULE_DEVICE_TABLE(hid, uclogic_devices);
 static struct hid_driver uclogic_driver = {
 	.name = "uclogic",
 	.id_table = uclogic_devices,
+	.probe = uclogic_probe,
 	.report_fixup = uclogic_report_fixup,
 };
 module_hid_driver(uclogic_driver);
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index 747d54421e7..6d7c9c580ce 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -137,6 +137,7 @@ struct i2c_hid {
 						   * descriptor. */
 	unsigned int		bufsize;	/* i2c buffer size */
 	char			*inbuf;		/* Input buffer */
+	char			*rawbuf;	/* Raw Input buffer */
 	char			*cmdbuf;	/* Command buffer */
 	char			*argsbuf;	/* Command arguments buffer */
 
@@ -371,6 +372,9 @@ static void i2c_hid_get_input(struct i2c_hid *ihid)
 	int ret, ret_size;
 	int size = le16_to_cpu(ihid->hdesc.wMaxInputLength);
 
+	if (size > ihid->bufsize)
+		size = ihid->bufsize;
+
 	ret = i2c_master_recv(ihid->client, ihid->inbuf, size);
 	if (ret != size) {
 		if (ret < 0)
@@ -504,9 +508,11 @@ static void i2c_hid_find_max_report(struct hid_device *hid, unsigned int type,
 static void i2c_hid_free_buffers(struct i2c_hid *ihid)
 {
 	kfree(ihid->inbuf);
+	kfree(ihid->rawbuf);
 	kfree(ihid->argsbuf);
 	kfree(ihid->cmdbuf);
 	ihid->inbuf = NULL;
+	ihid->rawbuf = NULL;
 	ihid->cmdbuf = NULL;
 	ihid->argsbuf = NULL;
 	ihid->bufsize = 0;
@@ -522,10 +528,11 @@ static int i2c_hid_alloc_buffers(struct i2c_hid *ihid, size_t report_size)
 		       report_size; /* report */
 
 	ihid->inbuf = kzalloc(report_size, GFP_KERNEL);
+	ihid->rawbuf = kzalloc(report_size, GFP_KERNEL);
 	ihid->argsbuf = kzalloc(args_len, GFP_KERNEL);
 	ihid->cmdbuf = kzalloc(sizeof(union command) + args_len, GFP_KERNEL);
 
-	if (!ihid->inbuf || !ihid->argsbuf || !ihid->cmdbuf) {
+	if (!ihid->inbuf || !ihid->rawbuf || !ihid->argsbuf || !ihid->cmdbuf) {
 		i2c_hid_free_buffers(ihid);
 		return -ENOMEM;
 	}
@@ -552,12 +559,12 @@ static int i2c_hid_get_raw_report(struct hid_device *hid,
 
 	ret = i2c_hid_get_report(client,
 			report_type == HID_FEATURE_REPORT ? 0x03 : 0x01,
-			report_number, ihid->inbuf, ask_count);
+			report_number, ihid->rawbuf, ask_count);
 
 	if (ret < 0)
 		return ret;
 
-	ret_count = ihid->inbuf[0] | (ihid->inbuf[1] << 8);
+	ret_count = ihid->rawbuf[0] | (ihid->rawbuf[1] << 8);
 
 	if (ret_count <= 2)
 		return 0;
@@ -566,7 +573,7 @@ static int i2c_hid_get_raw_report(struct hid_device *hid,
 
 	/* The query buffer contains the size, dropping it in the reply */
 	count = min(count, ret_count - 2);
-	memcpy(buf, ihid->inbuf + 2, count);
+	memcpy(buf, ihid->rawbuf + 2, count);
 
 	return count;
 }
@@ -702,12 +709,7 @@ static int i2c_hid_start(struct hid_device *hid)
 
 static void i2c_hid_stop(struct hid_device *hid)
 {
-	struct i2c_client *client = hid->driver_data;
-	struct i2c_hid *ihid = i2c_get_clientdata(client);
-
 	hid->claimed = 0;
-
-	i2c_hid_free_buffers(ihid);
 }
 
 static int i2c_hid_open(struct hid_device *hid)
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 552671ee7c5..509dee2e9b7 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -52,7 +52,6 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_ETURBOTOUCH, USB_DEVICE_ID_ETURBOTOUCH_2968, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_GREENASIA, USB_DEVICE_ID_GREENASIA_DUAL_USB_JOYPAD, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_PANTHERLORD, USB_DEVICE_ID_PANTHERLORD_TWIN_USB_JOYSTICK, HID_QUIRK_MULTI_INPUT | HID_QUIRK_SKIP_OUTPUT_REPORTS },
-	{ USB_VENDOR_ID_PLAYDOTCOM, USB_DEVICE_ID_PLAYDOTCOM_EMS_USBII, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_TOUCHPACK, USB_DEVICE_ID_TOUCHPACK_RTS, HID_QUIRK_MULTI_INPUT },
 
 	{ USB_VENDOR_ID_AIREN, USB_DEVICE_ID_AIREN_SLIMPLUS, HID_QUIRK_NOGET },
@@ -61,6 +60,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_2PORTKVM, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVM, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVMC, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_CS682, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FIGHTERSTICK, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_COMBATSTICK, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FLIGHT_SIM_ECLIPSE_YOKE, HID_QUIRK_NOGET },
@@ -73,10 +73,18 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_009B, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_0103, HID_QUIRK_ALWAYS_POLL },
+	{ USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_010c, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_016F, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2700, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0A4A, HID_QUIRK_ALWAYS_POLL },
+	{ USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0B4A, HID_QUIRK_ALWAYS_POLL },
+	{ USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL },
+	{ USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C077, HID_QUIRK_ALWAYS_POLL },
+	{ USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C01A, HID_QUIRK_ALWAYS_POLL },
+	{ USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C05A, HID_QUIRK_ALWAYS_POLL },
+	{ USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C06A, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_MSI, USB_DEVICE_ID_MSI_GT683R_LED_PANEL, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_NEXIO, USB_DEVICE_ID_NEXIO_MULTITOUCH_PTI0750, HID_QUIRK_NO_INIT_REPORTS },
@@ -88,6 +96,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_OPTICAL_TOUCH_SCREEN, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_OPTICAL_TOUCH_SCREEN1, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_OPTICAL_TOUCH_SCREEN2, HID_QUIRK_NO_INIT_REPORTS },
+	{ USB_VENDOR_ID_PRIMAX, USB_DEVICE_ID_PRIMAX_MOUSE_4D22, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_PRODIGE, USB_DEVICE_ID_PRODIGE_CORDLESS, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3001, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3008, HID_QUIRK_NOGET },
@@ -103,12 +112,8 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_SYMBOL, USB_DEVICE_ID_SYMBOL_SCANNER_2, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_TPV, USB_DEVICE_ID_TPV_OPTICAL_TOUCHSCREEN, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_TURBOX, USB_DEVICE_ID_TURBOX_KEYBOARD, HID_QUIRK_NOGET },
-	{ USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_TABLET_PF1209, HID_QUIRK_MULTI_INPUT },
-	{ USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_TABLET_WP4030U, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_TABLET_KNA5, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_TABLET_TWA60, HID_QUIRK_MULTI_INPUT },
-	{ USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_TABLET_WP5540U, HID_QUIRK_MULTI_INPUT },
-	{ USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_TABLET_WP8060U, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_MEDIA_TABLET_10_6_INCH, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_MEDIA_TABLET_14_1_INCH, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_SIRIUS_BATTERY_FREE_TABLET, HID_QUIRK_MULTI_INPUT },
@@ -122,7 +127,9 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_WIRELESS, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_SIGMA_MICRO, USB_DEVICE_ID_SIGMA_MICRO_KEYBOARD, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_PENSKETCH_M912, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_DUOSENSE, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS1, HID_QUIRK_NO_INIT_REPORTS },
@@ -131,6 +138,9 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_QUAD_HD, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_TP_V103, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD_A096, HID_QUIRK_NO_INIT_INPUT_REPORTS },
+	{ USB_VENDOR_ID_MULTIPLE_1781, USB_DEVICE_ID_RAPHNET_4NES4SNES_OLD, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_DRACAL_RAPHNET, USB_DEVICE_ID_RAPHNET_2NES2SNES, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_DRACAL_RAPHNET, USB_DEVICE_ID_RAPHNET_4NES4SNES, HID_QUIRK_MULTI_INPUT },
 
 	{ 0, 0 }
 };
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index 8593047bb72..b6bcd251c4a 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -70,22 +70,15 @@ static int wacom_raw_event(struct hid_device *hdev, struct hid_report *report,
 static int wacom_open(struct input_dev *dev)
 {
 	struct wacom *wacom = input_get_drvdata(dev);
-	int retval;
-
-	mutex_lock(&wacom->lock);
-	retval = hid_hw_open(wacom->hdev);
-	mutex_unlock(&wacom->lock);
 
-	return retval;
+	return hid_hw_open(wacom->hdev);
 }
 
 static void wacom_close(struct input_dev *dev)
 {
 	struct wacom *wacom = input_get_drvdata(dev);
 
-	mutex_lock(&wacom->lock);
 	hid_hw_close(wacom->hdev);
-	mutex_unlock(&wacom->lock);
 }
 
 /*
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 586b2405b0d..c673eda7146 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -756,6 +756,12 @@ static int wacom_intuos_irq(struct wacom_wac *wacom)
 			input_report_key(input, BTN_7, (data[4] & 0x40));  /* Left   */
 			input_report_key(input, BTN_8, (data[4] & 0x80));  /* Down   */
 			input_report_key(input, BTN_0, (data[3] & 0x01));  /* Center */
+
+			if (data[4] | (data[3] & 0x01)) {
+				input_report_abs(input, ABS_MISC, PAD_DEVICE_ID);
+			} else {
+				input_report_abs(input, ABS_MISC, 0);
+			}
 		} else if (features->type >= INTUOS5S && features->type <= INTUOSPL) {
 			int i;
 
@@ -3026,6 +3032,7 @@ const struct hid_device_id wacom_ids[] = {
 	{ USB_DEVICE_WACOM(0x4004) },
 	{ USB_DEVICE_WACOM(0x5000) },
 	{ USB_DEVICE_WACOM(0x5002) },
+	{ USB_DEVICE_LENOVO(0x6004) },
 
 	{ USB_DEVICE_WACOM(HID_ANY_ID) },
 	{ }
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 433f72a1c00..995e2a0cf09 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -135,7 +135,7 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 			   GFP_KERNEL);
 	if (!open_info) {
 		err = -ENOMEM;
-		goto error0;
+		goto error_gpadl;
 	}
 
 	init_completion(&open_info->waitevent);
@@ -151,7 +151,7 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 
 	if (userdatalen > MAX_USER_DEFINED_BYTES) {
 		err = -EINVAL;
-		goto error0;
+		goto error_gpadl;
 	}
 
 	if (userdatalen)
@@ -195,6 +195,9 @@ error1:
 	list_del(&open_info->msglistentry);
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
 
+error_gpadl:
+	vmbus_teardown_gpadl(newchannel, newchannel->ringbuffer_gpadlhandle);
+
 error0:
 	free_pages((unsigned long)out,
 		get_order(send_ringbuffer_size + recv_ringbuffer_size));
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index a2d1a9612c8..08b58defdb9 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -216,9 +216,16 @@ static void vmbus_process_rescind_offer(struct work_struct *work)
 	unsigned long flags;
 	struct vmbus_channel *primary_channel;
 	struct vmbus_channel_relid_released msg;
+	struct device *dev;
+
+	if (channel->device_obj) {
+		dev = get_device(&channel->device_obj->device);
+		if (dev) {
+			vmbus_device_unregister(channel->device_obj);
+			put_device(dev);
+		}
+	}
 
-	if (channel->device_obj)
-		vmbus_device_unregister(channel->device_obj);
 	memset(&msg, 0, sizeof(struct vmbus_channel_relid_released));
 	msg.child_relid = channel->offermsg.child_relid;
 	msg.header.msgtype = CHANNELMSG_RELID_RELEASED;
@@ -760,7 +767,7 @@ int vmbus_request_offers(void)
 {
 	struct vmbus_channel_message_header *msg;
 	struct vmbus_channel_msginfo *msginfo;
-	int ret, t;
+	int ret;
 
 	msginfo = kmalloc(sizeof(*msginfo) +
 			  sizeof(struct vmbus_channel_message_header),
@@ -768,8 +775,6 @@ int vmbus_request_offers(void)
 	if (!msginfo)
 		return -ENOMEM;
 
-	init_completion(&msginfo->waitevent);
-
 	msg = (struct vmbus_channel_message_header *)msginfo->msg;
 
 	msg->msgtype = CHANNELMSG_REQUESTOFFERS;
@@ -783,14 +788,6 @@ int vmbus_request_offers(void)
 		goto cleanup;
 	}
 
-	t = wait_for_completion_timeout(&msginfo->waitevent, 5*HZ);
-	if (t == 0) {
-		ret = -ETIMEDOUT;
-		goto cleanup;
-	}
-
-
-
 cleanup:
 	kfree(msginfo);
 
diff --git a/drivers/hwmon/lm75.c b/drivers/hwmon/lm75.c
index d16dbb33a53..e7c8bf9093e 100644
--- a/drivers/hwmon/lm75.c
+++ b/drivers/hwmon/lm75.c
@@ -176,6 +176,10 @@ static struct attribute *lm75_attrs[] = {
 };
 ATTRIBUTE_GROUPS(lm75);
 
+static const struct thermal_zone_of_device_ops lm75_of_thermal_ops = {
+	.get_temp = lm75_read_temp,
+};
+
 /*-----------------------------------------------------------------------*/
 
 /* device probe and removal */
@@ -291,10 +295,9 @@ lm75_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	if (IS_ERR(data->hwmon_dev))
 		return PTR_ERR(data->hwmon_dev);
 
-	data->tz = thermal_zone_of_sensor_register(data->hwmon_dev,
-						   0,
+	data->tz = thermal_zone_of_sensor_register(data->hwmon_dev, 0,
 						   data->hwmon_dev,
-						   lm75_read_temp, NULL);
+						   &lm75_of_thermal_ops);
 	if (IS_ERR(data->tz))
 		data->tz = NULL;
 
diff --git a/drivers/hwmon/mcp3021.c b/drivers/hwmon/mcp3021.c
index d219c06a857..972444a14cc 100644
--- a/drivers/hwmon/mcp3021.c
+++ b/drivers/hwmon/mcp3021.c
@@ -31,14 +31,11 @@
 /* output format */
 #define MCP3021_SAR_SHIFT	2
 #define MCP3021_SAR_MASK	0x3ff
-
 #define MCP3021_OUTPUT_RES	10	/* 10-bit resolution */
-#define MCP3021_OUTPUT_SCALE	4
 
 #define MCP3221_SAR_SHIFT	0
 #define MCP3221_SAR_MASK	0xfff
 #define MCP3221_OUTPUT_RES	12	/* 12-bit resolution */
-#define MCP3221_OUTPUT_SCALE	1
 
 enum chips {
 	mcp3021,
@@ -54,7 +51,6 @@ struct mcp3021_data {
 	u16 sar_shift;
 	u16 sar_mask;
 	u8 output_res;
-	u8 output_scale;
 };
 
 static int mcp3021_read16(struct i2c_client *client)
@@ -84,13 +80,7 @@ static int mcp3021_read16(struct i2c_client *client)
 
 static inline u16 volts_from_reg(struct mcp3021_data *data, u16 val)
 {
-	if (val == 0)
-		return 0;
-
-	val = val * data->output_scale - data->output_scale / 2;
-
-	return val * DIV_ROUND_CLOSEST(data->vdd,
-			(1 << data->output_res) * data->output_scale);
+	return DIV_ROUND_CLOSEST(data->vdd * val, 1 << data->output_res);
 }
 
 static ssize_t show_in_input(struct device *dev, struct device_attribute *attr,
@@ -132,14 +122,12 @@ static int mcp3021_probe(struct i2c_client *client,
 		data->sar_shift = MCP3021_SAR_SHIFT;
 		data->sar_mask = MCP3021_SAR_MASK;
 		data->output_res = MCP3021_OUTPUT_RES;
-		data->output_scale = MCP3021_OUTPUT_SCALE;
 		break;
 
 	case mcp3221:
 		data->sar_shift = MCP3221_SAR_SHIFT;
 		data->sar_mask = MCP3221_SAR_MASK;
 		data->output_res = MCP3221_OUTPUT_RES;
-		data->output_scale = MCP3221_OUTPUT_SCALE;
 		break;
 	}
 
diff --git a/drivers/hwmon/nct6683.c b/drivers/hwmon/nct6683.c
index 7710f4694ba..718953bb657 100644
--- a/drivers/hwmon/nct6683.c
+++ b/drivers/hwmon/nct6683.c
@@ -439,6 +439,7 @@ nct6683_create_attr_group(struct device *dev, struct sensor_template_group *tg,
 				 (*t)->dev_attr.attr.name, tg->base + i);
 			if ((*t)->s2) {
 				a2 = &su->u.a2;
+				sysfs_attr_init(&a2->dev_attr.attr);
 				a2->dev_attr.attr.name = su->name;
 				a2->nr = (*t)->u.s.nr + i;
 				a2->index = (*t)->u.s.index;
@@ -449,6 +450,7 @@ nct6683_create_attr_group(struct device *dev, struct sensor_template_group *tg,
 				*attrs = &a2->dev_attr.attr;
 			} else {
 				a = &su->u.a1;
+				sysfs_attr_init(&a->dev_attr.attr);
 				a->dev_attr.attr.name = su->name;
 				a->index = (*t)->u.index + i;
 				a->dev_attr.attr.mode =
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index 504cbddbdd9..6461964f49a 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -985,6 +985,7 @@ nct6775_create_attr_group(struct device *dev, struct sensor_template_group *tg,
 				 (*t)->dev_attr.attr.name, tg->base + i);
 			if ((*t)->s2) {
 				a2 = &su->u.a2;
+				sysfs_attr_init(&a2->dev_attr.attr);
 				a2->dev_attr.attr.name = su->name;
 				a2->nr = (*t)->u.s.nr + i;
 				a2->index = (*t)->u.s.index;
@@ -995,6 +996,7 @@ nct6775_create_attr_group(struct device *dev, struct sensor_template_group *tg,
 				*attrs = &a2->dev_attr.attr;
 			} else {
 				a = &su->u.a1;
+				sysfs_attr_init(&a->dev_attr.attr);
 				a->dev_attr.attr.name = su->name;
 				a->index = (*t)->u.index + i;
 				a->dev_attr.attr.mode =
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index 4ff89b2482e..b2c90bdc2dd 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -239,8 +239,10 @@ static struct ntc_thermistor_platform_data *
 ntc_thermistor_parse_dt(struct platform_device *pdev)
 {
 	struct iio_channel *chan;
+	enum iio_chan_type type;
 	struct device_node *np = pdev->dev.of_node;
 	struct ntc_thermistor_platform_data *pdata;
+	int ret;
 
 	if (!np)
 		return NULL;
@@ -253,6 +255,13 @@ ntc_thermistor_parse_dt(struct platform_device *pdev)
 	if (IS_ERR(chan))
 		return ERR_CAST(chan);
 
+	ret = iio_get_channel_type(chan, &type);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	if (type != IIO_VOLTAGE)
+		return ERR_PTR(-EINVAL);
+
 	if (of_property_read_u32(np, "pullup-uv", &pdata->pullup_uv))
 		return ERR_PTR(-ENODEV);
 	if (of_property_read_u32(np, "pullup-ohm", &pdata->pullup_ohm))
@@ -486,6 +495,10 @@ static const struct attribute_group ntc_attr_group = {
 	.attrs = ntc_attributes,
 };
 
+static const struct thermal_zone_of_device_ops ntc_of_thermal_ops = {
+	.get_temp = ntc_read_temp,
+};
+
 static int ntc_thermistor_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id =
@@ -579,7 +592,7 @@ static int ntc_thermistor_probe(struct platform_device *pdev)
 								pdev_id->name);
 
 	data->tz = thermal_zone_of_sensor_register(data->dev, 0, data->dev,
-						ntc_read_temp, NULL);
+						   &ntc_of_thermal_ops);
 	if (IS_ERR(data->tz)) {
 		dev_dbg(&pdev->dev, "Failed to register to thermal fw.\n");
 		data->tz = NULL;
diff --git a/drivers/hwmon/tmp102.c b/drivers/hwmon/tmp102.c
index 51719956cc0..ba9f478f64e 100644
--- a/drivers/hwmon/tmp102.c
+++ b/drivers/hwmon/tmp102.c
@@ -158,6 +158,10 @@ ATTRIBUTE_GROUPS(tmp102);
 #define TMP102_CONFIG  (TMP102_CONF_TM | TMP102_CONF_EM | TMP102_CONF_CR1)
 #define TMP102_CONFIG_RD_ONLY (TMP102_CONF_R0 | TMP102_CONF_R1 | TMP102_CONF_AL)
 
+static const struct thermal_zone_of_device_ops tmp102_of_thermal_ops = {
+	.get_temp = tmp102_read_temp,
+};
+
 static int tmp102_probe(struct i2c_client *client,
 				  const struct i2c_device_id *id)
 {
@@ -215,7 +219,7 @@ static int tmp102_probe(struct i2c_client *client,
 	}
 	tmp102->hwmon_dev = hwmon_dev;
 	tmp102->tz = thermal_zone_of_sensor_register(hwmon_dev, 0, hwmon_dev,
-						     tmp102_read_temp, NULL);
+						     &tmp102_of_thermal_ops);
 	if (IS_ERR(tmp102->tz))
 		tmp102->tz = NULL;
 
diff --git a/drivers/hwtracing/coresight/Kconfig b/drivers/hwtracing/coresight/Kconfig
new file mode 100644
index 00000000000..fc1f1ae7a49
--- /dev/null
+++ b/drivers/hwtracing/coresight/Kconfig
@@ -0,0 +1,61 @@
+#
+# Coresight configuration
+#
+menuconfig CORESIGHT
+	bool "CoreSight Tracing Support"
+	select ARM_AMBA
+	help
+	  This framework provides a kernel interface for the CoreSight debug
+	  and trace drivers to register themselves with. It's intended to build
+	  a topological view of the CoreSight components based on a DT
+	  specification and configure the right serie of components when a
+	  trace source gets enabled.
+
+if CORESIGHT
+config CORESIGHT_LINKS_AND_SINKS
+	bool "CoreSight Link and Sink drivers"
+	help
+	  This enables support for CoreSight link and sink drivers that are
+	  responsible for transporting and collecting the trace data
+	  respectively.  Link and sinks are dynamically aggregated with a trace
+	  entity at run time to form a complete trace path.
+
+config CORESIGHT_LINK_AND_SINK_TMC
+	bool "Coresight generic TMC driver"
+	depends on CORESIGHT_LINKS_AND_SINKS
+	help
+	  This enables support for the Trace Memory Controller driver.
+	  Depending on its configuration the device can act as a link (embedded
+	  trace router - ETR) or sink (embedded trace FIFO).  The driver
+	  complies with the generic implementation of the component without
+	  special enhancement or added features.
+
+config CORESIGHT_SINK_TPIU
+	bool "Coresight generic TPIU driver"
+	depends on CORESIGHT_LINKS_AND_SINKS
+	help
+	  This enables support for the Trace Port Interface Unit driver,
+	  responsible for bridging the gap between the on-chip coresight
+	  components and a trace for bridging the gap between the on-chip
+	  coresight components and a trace port collection engine, typically
+	  connected to an external host for use case capturing more traces than
+	  the on-board coresight memory can handle.
+
+config CORESIGHT_SINK_ETBV10
+	bool "Coresight ETBv1.0 driver"
+	depends on CORESIGHT_LINKS_AND_SINKS
+	help
+	  This enables support for the Embedded Trace Buffer version 1.0 driver
+	  that complies with the generic implementation of the component without
+	  special enhancement or added features.
+
+config CORESIGHT_SOURCE_ETM3X
+	bool "CoreSight Embedded Trace Macrocell 3.x driver"
+	depends on !ARM64
+	select CORESIGHT_LINKS_AND_SINKS
+	help
+	  This driver provides support for processor ETM3.x and PTM1.x modules,
+	  which allows tracing the instructions that a processor is executing
+	  This is primarily useful for instruction level tracing.  Depending
+	  the ETM version data tracing may also be available.
+endif
diff --git a/drivers/hwtracing/coresight/Makefile b/drivers/hwtracing/coresight/Makefile
new file mode 100644
index 00000000000..4b4bec890ef
--- /dev/null
+++ b/drivers/hwtracing/coresight/Makefile
@@ -0,0 +1,11 @@
+#
+# Makefile for CoreSight drivers.
+#
+obj-$(CONFIG_CORESIGHT) += coresight.o
+obj-$(CONFIG_OF) += of_coresight.o
+obj-$(CONFIG_CORESIGHT_LINK_AND_SINK_TMC) += coresight-tmc.o
+obj-$(CONFIG_CORESIGHT_SINK_TPIU) += coresight-tpiu.o
+obj-$(CONFIG_CORESIGHT_SINK_ETBV10) += coresight-etb10.o
+obj-$(CONFIG_CORESIGHT_LINKS_AND_SINKS) += coresight-funnel.o \
+					   coresight-replicator.o
+obj-$(CONFIG_CORESIGHT_SOURCE_ETM3X) += coresight-etm3x.o coresight-etm-cp14.o
diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c
new file mode 100644
index 00000000000..40049869aec
--- /dev/null
+++ b/drivers/hwtracing/coresight/coresight-etb10.c
@@ -0,0 +1,527 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/clk.h>
+#include <linux/seq_file.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+
+#include "coresight-priv.h"
+
+#define ETB_RAM_DEPTH_REG	0x004
+#define ETB_STATUS_REG		0x00c
+#define ETB_RAM_READ_DATA_REG	0x010
+#define ETB_RAM_READ_POINTER	0x014
+#define ETB_RAM_WRITE_POINTER	0x018
+#define ETB_TRG			0x01c
+#define ETB_CTL_REG		0x020
+#define ETB_RWD_REG		0x024
+#define ETB_FFSR		0x300
+#define ETB_FFCR		0x304
+#define ETB_ITMISCOP0		0xee0
+#define ETB_ITTRFLINACK		0xee4
+#define ETB_ITTRFLIN		0xee8
+#define ETB_ITATBDATA0		0xeeC
+#define ETB_ITATBCTR2		0xef0
+#define ETB_ITATBCTR1		0xef4
+#define ETB_ITATBCTR0		0xef8
+
+/* register description */
+/* STS - 0x00C */
+#define ETB_STATUS_RAM_FULL	BIT(0)
+/* CTL - 0x020 */
+#define ETB_CTL_CAPT_EN		BIT(0)
+/* FFCR - 0x304 */
+#define ETB_FFCR_EN_FTC		BIT(0)
+#define ETB_FFCR_FON_MAN	BIT(6)
+#define ETB_FFCR_STOP_FI	BIT(12)
+#define ETB_FFCR_STOP_TRIGGER	BIT(13)
+
+#define ETB_FFCR_BIT		6
+#define ETB_FFSR_BIT		1
+#define ETB_FRAME_SIZE_WORDS	4
+
+/**
+ * struct etb_drvdata - specifics associated to an ETB component
+ * @base:	memory mapped base address for this component.
+ * @dev:	the device entity associated to this component.
+ * @csdev:	component vitals needed by the framework.
+ * @miscdev:	specifics to handle "/dev/xyz.etb" entry.
+ * @clk:	the clock this component is associated to.
+ * @spinlock:	only one at a time pls.
+ * @in_use:	synchronise user space access to etb buffer.
+ * @buf:	area of memory where ETB buffer content gets sent.
+ * @buffer_depth: size of @buf.
+ * @enable:	this ETB is being used.
+ * @trigger_cntr: amount of words to store after a trigger.
+ */
+struct etb_drvdata {
+	void __iomem		*base;
+	struct device		*dev;
+	struct coresight_device	*csdev;
+	struct miscdevice	miscdev;
+	struct clk		*clk;
+	spinlock_t		spinlock;
+	atomic_t		in_use;
+	u8			*buf;
+	u32			buffer_depth;
+	bool			enable;
+	u32			trigger_cntr;
+};
+
+static unsigned int etb_get_buffer_depth(struct etb_drvdata *drvdata)
+{
+	int ret;
+	u32 depth = 0;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	/* RO registers don't need locking */
+	depth = readl_relaxed(drvdata->base + ETB_RAM_DEPTH_REG);
+
+	clk_disable_unprepare(drvdata->clk);
+	return depth;
+}
+
+static void etb_enable_hw(struct etb_drvdata *drvdata)
+{
+	int i;
+	u32 depth;
+
+	CS_UNLOCK(drvdata->base);
+
+	depth = drvdata->buffer_depth;
+	/* reset write RAM pointer address */
+	writel_relaxed(0x0, drvdata->base + ETB_RAM_WRITE_POINTER);
+	/* clear entire RAM buffer */
+	for (i = 0; i < depth; i++)
+		writel_relaxed(0x0, drvdata->base + ETB_RWD_REG);
+
+	/* reset write RAM pointer address */
+	writel_relaxed(0x0, drvdata->base + ETB_RAM_WRITE_POINTER);
+	/* reset read RAM pointer address */
+	writel_relaxed(0x0, drvdata->base + ETB_RAM_READ_POINTER);
+
+	writel_relaxed(drvdata->trigger_cntr, drvdata->base + ETB_TRG);
+	writel_relaxed(ETB_FFCR_EN_FTC | ETB_FFCR_STOP_TRIGGER,
+		       drvdata->base + ETB_FFCR);
+	/* ETB trace capture enable */
+	writel_relaxed(ETB_CTL_CAPT_EN, drvdata->base + ETB_CTL_REG);
+
+	CS_LOCK(drvdata->base);
+}
+
+static int etb_enable(struct coresight_device *csdev)
+{
+	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	int ret;
+	unsigned long flags;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	etb_enable_hw(drvdata);
+	drvdata->enable = true;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	dev_info(drvdata->dev, "ETB enabled\n");
+	return 0;
+}
+
+static void etb_disable_hw(struct etb_drvdata *drvdata)
+{
+	u32 ffcr;
+
+	CS_UNLOCK(drvdata->base);
+
+	ffcr = readl_relaxed(drvdata->base + ETB_FFCR);
+	/* stop formatter when a stop has completed */
+	ffcr |= ETB_FFCR_STOP_FI;
+	writel_relaxed(ffcr, drvdata->base + ETB_FFCR);
+	/* manually generate a flush of the system */
+	ffcr |= ETB_FFCR_FON_MAN;
+	writel_relaxed(ffcr, drvdata->base + ETB_FFCR);
+
+	if (coresight_timeout(drvdata->base, ETB_FFCR, ETB_FFCR_BIT, 0)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n",
+			ETB_FFCR);
+	}
+
+	/* disable trace capture */
+	writel_relaxed(0x0, drvdata->base + ETB_CTL_REG);
+
+	if (coresight_timeout(drvdata->base, ETB_FFSR, ETB_FFSR_BIT, 1)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n",
+			ETB_FFCR);
+	}
+
+	CS_LOCK(drvdata->base);
+}
+
+static void etb_dump_hw(struct etb_drvdata *drvdata)
+{
+	int i;
+	u8 *buf_ptr;
+	u32 read_data, depth;
+	u32 read_ptr, write_ptr;
+	u32 frame_off, frame_endoff;
+
+	CS_UNLOCK(drvdata->base);
+
+	read_ptr = readl_relaxed(drvdata->base + ETB_RAM_READ_POINTER);
+	write_ptr = readl_relaxed(drvdata->base + ETB_RAM_WRITE_POINTER);
+
+	frame_off = write_ptr % ETB_FRAME_SIZE_WORDS;
+	frame_endoff = ETB_FRAME_SIZE_WORDS - frame_off;
+	if (frame_off) {
+		dev_err(drvdata->dev,
+			"write_ptr: %lu not aligned to formatter frame size\n",
+			(unsigned long)write_ptr);
+		dev_err(drvdata->dev, "frameoff: %lu, frame_endoff: %lu\n",
+			(unsigned long)frame_off, (unsigned long)frame_endoff);
+		write_ptr += frame_endoff;
+	}
+
+	if ((readl_relaxed(drvdata->base + ETB_STATUS_REG)
+		      & ETB_STATUS_RAM_FULL) == 0)
+		writel_relaxed(0x0, drvdata->base + ETB_RAM_READ_POINTER);
+	else
+		writel_relaxed(write_ptr, drvdata->base + ETB_RAM_READ_POINTER);
+
+	depth = drvdata->buffer_depth;
+	buf_ptr = drvdata->buf;
+	for (i = 0; i < depth; i++) {
+		read_data = readl_relaxed(drvdata->base +
+					  ETB_RAM_READ_DATA_REG);
+		*buf_ptr++ = read_data >> 0;
+		*buf_ptr++ = read_data >> 8;
+		*buf_ptr++ = read_data >> 16;
+		*buf_ptr++ = read_data >> 24;
+	}
+
+	if (frame_off) {
+		buf_ptr -= (frame_endoff * 4);
+		for (i = 0; i < frame_endoff; i++) {
+			*buf_ptr++ = 0x0;
+			*buf_ptr++ = 0x0;
+			*buf_ptr++ = 0x0;
+			*buf_ptr++ = 0x0;
+		}
+	}
+
+	writel_relaxed(read_ptr, drvdata->base + ETB_RAM_READ_POINTER);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void etb_disable(struct coresight_device *csdev)
+{
+	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	unsigned long flags;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	etb_disable_hw(drvdata);
+	etb_dump_hw(drvdata);
+	drvdata->enable = false;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	dev_info(drvdata->dev, "ETB disabled\n");
+}
+
+static const struct coresight_ops_sink etb_sink_ops = {
+	.enable		= etb_enable,
+	.disable	= etb_disable,
+};
+
+static const struct coresight_ops etb_cs_ops = {
+	.sink_ops	= &etb_sink_ops,
+};
+
+static void etb_dump(struct etb_drvdata *drvdata)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (drvdata->enable) {
+		etb_disable_hw(drvdata);
+		etb_dump_hw(drvdata);
+		etb_enable_hw(drvdata);
+	}
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	dev_info(drvdata->dev, "ETB dumped\n");
+}
+
+static int etb_open(struct inode *inode, struct file *file)
+{
+	struct etb_drvdata *drvdata = container_of(file->private_data,
+						   struct etb_drvdata, miscdev);
+
+	if (atomic_cmpxchg(&drvdata->in_use, 0, 1))
+		return -EBUSY;
+
+	dev_dbg(drvdata->dev, "%s: successfully opened\n", __func__);
+	return 0;
+}
+
+static ssize_t etb_read(struct file *file, char __user *data,
+				size_t len, loff_t *ppos)
+{
+	u32 depth;
+	struct etb_drvdata *drvdata = container_of(file->private_data,
+						   struct etb_drvdata, miscdev);
+
+	etb_dump(drvdata);
+
+	depth = drvdata->buffer_depth;
+	if (*ppos + len > depth * 4)
+		len = depth * 4 - *ppos;
+
+	if (copy_to_user(data, drvdata->buf + *ppos, len)) {
+		dev_dbg(drvdata->dev, "%s: copy_to_user failed\n", __func__);
+		return -EFAULT;
+	}
+
+	*ppos += len;
+
+	dev_dbg(drvdata->dev, "%s: %zu bytes copied, %d bytes left\n",
+		__func__, len, (int)(depth * 4 - *ppos));
+	return len;
+}
+
+static int etb_release(struct inode *inode, struct file *file)
+{
+	struct etb_drvdata *drvdata = container_of(file->private_data,
+						   struct etb_drvdata, miscdev);
+	atomic_set(&drvdata->in_use, 0);
+
+	dev_dbg(drvdata->dev, "%s: released\n", __func__);
+	return 0;
+}
+
+static const struct file_operations etb_fops = {
+	.owner		= THIS_MODULE,
+	.open		= etb_open,
+	.read		= etb_read,
+	.release	= etb_release,
+	.llseek		= no_llseek,
+};
+
+static ssize_t status_show(struct device *dev,
+			   struct device_attribute *attr, char *buf)
+{
+	int ret;
+	unsigned long flags;
+	u32 etb_rdr, etb_sr, etb_rrp, etb_rwp;
+	u32 etb_trg, etb_cr, etb_ffsr, etb_ffcr;
+	struct etb_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		goto out;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	CS_UNLOCK(drvdata->base);
+
+	etb_rdr = readl_relaxed(drvdata->base + ETB_RAM_DEPTH_REG);
+	etb_sr = readl_relaxed(drvdata->base + ETB_STATUS_REG);
+	etb_rrp = readl_relaxed(drvdata->base + ETB_RAM_READ_POINTER);
+	etb_rwp = readl_relaxed(drvdata->base + ETB_RAM_WRITE_POINTER);
+	etb_trg = readl_relaxed(drvdata->base + ETB_TRG);
+	etb_cr = readl_relaxed(drvdata->base + ETB_CTL_REG);
+	etb_ffsr = readl_relaxed(drvdata->base + ETB_FFSR);
+	etb_ffcr = readl_relaxed(drvdata->base + ETB_FFCR);
+
+	CS_LOCK(drvdata->base);
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	return sprintf(buf,
+		       "Depth:\t\t0x%x\n"
+		       "Status:\t\t0x%x\n"
+		       "RAM read ptr:\t0x%x\n"
+		       "RAM wrt ptr:\t0x%x\n"
+		       "Trigger cnt:\t0x%x\n"
+		       "Control:\t0x%x\n"
+		       "Flush status:\t0x%x\n"
+		       "Flush ctrl:\t0x%x\n",
+		       etb_rdr, etb_sr, etb_rrp, etb_rwp,
+		       etb_trg, etb_cr, etb_ffsr, etb_ffcr);
+out:
+	return -EINVAL;
+}
+static DEVICE_ATTR_RO(status);
+
+static ssize_t trigger_cntr_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	struct etb_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val = drvdata->trigger_cntr;
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t trigger_cntr_store(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etb_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->trigger_cntr = val;
+	return size;
+}
+static DEVICE_ATTR_RW(trigger_cntr);
+
+static struct attribute *coresight_etb_attrs[] = {
+	&dev_attr_trigger_cntr.attr,
+	&dev_attr_status.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etb);
+
+static int etb_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	int ret;
+	void __iomem *base;
+	struct device *dev = &adev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct etb_drvdata *drvdata;
+	struct resource *res = &adev->res;
+	struct coresight_desc *desc;
+	struct device_node *np = adev->dev.of_node;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+		adev->dev.platform_data = pdata;
+	}
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->dev = &adev->dev;
+	dev_set_drvdata(dev, drvdata);
+
+	/* validity for the resource is already checked by the AMBA core */
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drvdata->base = base;
+
+	spin_lock_init(&drvdata->spinlock);
+
+	drvdata->clk = adev->pclk;
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	drvdata->buffer_depth = etb_get_buffer_depth(drvdata);
+	clk_disable_unprepare(drvdata->clk);
+
+	if (drvdata->buffer_depth < 0)
+		return -EINVAL;
+
+	drvdata->buf = devm_kzalloc(dev,
+				    drvdata->buffer_depth * 4, GFP_KERNEL);
+	if (!drvdata->buf)
+		return -ENOMEM;
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	desc->type = CORESIGHT_DEV_TYPE_SINK;
+	desc->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
+	desc->ops = &etb_cs_ops;
+	desc->pdata = pdata;
+	desc->dev = dev;
+	desc->groups = coresight_etb_groups;
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev))
+		return PTR_ERR(drvdata->csdev);
+
+	drvdata->miscdev.name = pdata->name;
+	drvdata->miscdev.minor = MISC_DYNAMIC_MINOR;
+	drvdata->miscdev.fops = &etb_fops;
+	ret = misc_register(&drvdata->miscdev);
+	if (ret)
+		goto err_misc_register;
+
+	dev_info(dev, "ETB initialized\n");
+	return 0;
+
+err_misc_register:
+	coresight_unregister(drvdata->csdev);
+	return ret;
+}
+
+static int etb_remove(struct amba_device *adev)
+{
+	struct etb_drvdata *drvdata = amba_get_drvdata(adev);
+
+	misc_deregister(&drvdata->miscdev);
+	coresight_unregister(drvdata->csdev);
+	return 0;
+}
+
+static struct amba_id etb_ids[] = {
+	{
+		.id	= 0x0003b907,
+		.mask	= 0x0003ffff,
+	},
+	{ 0, 0},
+};
+
+static struct amba_driver etb_driver = {
+	.drv = {
+		.name	= "coresight-etb10",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= etb_probe,
+	.remove		= etb_remove,
+	.id_table	= etb_ids,
+};
+
+module_amba_driver(etb_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Embedded Trace Buffer driver");
diff --git a/drivers/hwtracing/coresight/coresight-etm-cp14.c b/drivers/hwtracing/coresight/coresight-etm-cp14.c
new file mode 100644
index 00000000000..12a22068211
--- /dev/null
+++ b/drivers/hwtracing/coresight/coresight-etm-cp14.c
@@ -0,0 +1,591 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bug.h>
+#include <asm/hardware/cp14.h>
+
+#include "coresight-etm.h"
+
+int etm_readl_cp14(u32 reg, unsigned int *val)
+{
+	switch (reg) {
+	case ETMCR:
+		*val = etm_read(ETMCR);
+		return 0;
+	case ETMCCR:
+		*val = etm_read(ETMCCR);
+		return 0;
+	case ETMTRIGGER:
+		*val = etm_read(ETMTRIGGER);
+		return 0;
+	case ETMSR:
+		*val = etm_read(ETMSR);
+		return 0;
+	case ETMSCR:
+		*val = etm_read(ETMSCR);
+		return 0;
+	case ETMTSSCR:
+		*val = etm_read(ETMTSSCR);
+		return 0;
+	case ETMTEEVR:
+		*val = etm_read(ETMTEEVR);
+		return 0;
+	case ETMTECR1:
+		*val = etm_read(ETMTECR1);
+		return 0;
+	case ETMFFLR:
+		*val = etm_read(ETMFFLR);
+		return 0;
+	case ETMACVRn(0):
+		*val = etm_read(ETMACVR0);
+		return 0;
+	case ETMACVRn(1):
+		*val = etm_read(ETMACVR1);
+		return 0;
+	case ETMACVRn(2):
+		*val = etm_read(ETMACVR2);
+		return 0;
+	case ETMACVRn(3):
+		*val = etm_read(ETMACVR3);
+		return 0;
+	case ETMACVRn(4):
+		*val = etm_read(ETMACVR4);
+		return 0;
+	case ETMACVRn(5):
+		*val = etm_read(ETMACVR5);
+		return 0;
+	case ETMACVRn(6):
+		*val = etm_read(ETMACVR6);
+		return 0;
+	case ETMACVRn(7):
+		*val = etm_read(ETMACVR7);
+		return 0;
+	case ETMACVRn(8):
+		*val = etm_read(ETMACVR8);
+		return 0;
+	case ETMACVRn(9):
+		*val = etm_read(ETMACVR9);
+		return 0;
+	case ETMACVRn(10):
+		*val = etm_read(ETMACVR10);
+		return 0;
+	case ETMACVRn(11):
+		*val = etm_read(ETMACVR11);
+		return 0;
+	case ETMACVRn(12):
+		*val = etm_read(ETMACVR12);
+		return 0;
+	case ETMACVRn(13):
+		*val = etm_read(ETMACVR13);
+		return 0;
+	case ETMACVRn(14):
+		*val = etm_read(ETMACVR14);
+		return 0;
+	case ETMACVRn(15):
+		*val = etm_read(ETMACVR15);
+		return 0;
+	case ETMACTRn(0):
+		*val = etm_read(ETMACTR0);
+		return 0;
+	case ETMACTRn(1):
+		*val = etm_read(ETMACTR1);
+		return 0;
+	case ETMACTRn(2):
+		*val = etm_read(ETMACTR2);
+		return 0;
+	case ETMACTRn(3):
+		*val = etm_read(ETMACTR3);
+		return 0;
+	case ETMACTRn(4):
+		*val = etm_read(ETMACTR4);
+		return 0;
+	case ETMACTRn(5):
+		*val = etm_read(ETMACTR5);
+		return 0;
+	case ETMACTRn(6):
+		*val = etm_read(ETMACTR6);
+		return 0;
+	case ETMACTRn(7):
+		*val = etm_read(ETMACTR7);
+		return 0;
+	case ETMACTRn(8):
+		*val = etm_read(ETMACTR8);
+		return 0;
+	case ETMACTRn(9):
+		*val = etm_read(ETMACTR9);
+		return 0;
+	case ETMACTRn(10):
+		*val = etm_read(ETMACTR10);
+		return 0;
+	case ETMACTRn(11):
+		*val = etm_read(ETMACTR11);
+		return 0;
+	case ETMACTRn(12):
+		*val = etm_read(ETMACTR12);
+		return 0;
+	case ETMACTRn(13):
+		*val = etm_read(ETMACTR13);
+		return 0;
+	case ETMACTRn(14):
+		*val = etm_read(ETMACTR14);
+		return 0;
+	case ETMACTRn(15):
+		*val = etm_read(ETMACTR15);
+		return 0;
+	case ETMCNTRLDVRn(0):
+		*val = etm_read(ETMCNTRLDVR0);
+		return 0;
+	case ETMCNTRLDVRn(1):
+		*val = etm_read(ETMCNTRLDVR1);
+		return 0;
+	case ETMCNTRLDVRn(2):
+		*val = etm_read(ETMCNTRLDVR2);
+		return 0;
+	case ETMCNTRLDVRn(3):
+		*val = etm_read(ETMCNTRLDVR3);
+		return 0;
+	case ETMCNTENRn(0):
+		*val = etm_read(ETMCNTENR0);
+		return 0;
+	case ETMCNTENRn(1):
+		*val = etm_read(ETMCNTENR1);
+		return 0;
+	case ETMCNTENRn(2):
+		*val = etm_read(ETMCNTENR2);
+		return 0;
+	case ETMCNTENRn(3):
+		*val = etm_read(ETMCNTENR3);
+		return 0;
+	case ETMCNTRLDEVRn(0):
+		*val = etm_read(ETMCNTRLDEVR0);
+		return 0;
+	case ETMCNTRLDEVRn(1):
+		*val = etm_read(ETMCNTRLDEVR1);
+		return 0;
+	case ETMCNTRLDEVRn(2):
+		*val = etm_read(ETMCNTRLDEVR2);
+		return 0;
+	case ETMCNTRLDEVRn(3):
+		*val = etm_read(ETMCNTRLDEVR3);
+		return 0;
+	case ETMCNTVRn(0):
+		*val = etm_read(ETMCNTVR0);
+		return 0;
+	case ETMCNTVRn(1):
+		*val = etm_read(ETMCNTVR1);
+		return 0;
+	case ETMCNTVRn(2):
+		*val = etm_read(ETMCNTVR2);
+		return 0;
+	case ETMCNTVRn(3):
+		*val = etm_read(ETMCNTVR3);
+		return 0;
+	case ETMSQ12EVR:
+		*val = etm_read(ETMSQ12EVR);
+		return 0;
+	case ETMSQ21EVR:
+		*val = etm_read(ETMSQ21EVR);
+		return 0;
+	case ETMSQ23EVR:
+		*val = etm_read(ETMSQ23EVR);
+		return 0;
+	case ETMSQ31EVR:
+		*val = etm_read(ETMSQ31EVR);
+		return 0;
+	case ETMSQ32EVR:
+		*val = etm_read(ETMSQ32EVR);
+		return 0;
+	case ETMSQ13EVR:
+		*val = etm_read(ETMSQ13EVR);
+		return 0;
+	case ETMSQR:
+		*val = etm_read(ETMSQR);
+		return 0;
+	case ETMEXTOUTEVRn(0):
+		*val = etm_read(ETMEXTOUTEVR0);
+		return 0;
+	case ETMEXTOUTEVRn(1):
+		*val = etm_read(ETMEXTOUTEVR1);
+		return 0;
+	case ETMEXTOUTEVRn(2):
+		*val = etm_read(ETMEXTOUTEVR2);
+		return 0;
+	case ETMEXTOUTEVRn(3):
+		*val = etm_read(ETMEXTOUTEVR3);
+		return 0;
+	case ETMCIDCVRn(0):
+		*val = etm_read(ETMCIDCVR0);
+		return 0;
+	case ETMCIDCVRn(1):
+		*val = etm_read(ETMCIDCVR1);
+		return 0;
+	case ETMCIDCVRn(2):
+		*val = etm_read(ETMCIDCVR2);
+		return 0;
+	case ETMCIDCMR:
+		*val = etm_read(ETMCIDCMR);
+		return 0;
+	case ETMIMPSPEC0:
+		*val = etm_read(ETMIMPSPEC0);
+		return 0;
+	case ETMIMPSPEC1:
+		*val = etm_read(ETMIMPSPEC1);
+		return 0;
+	case ETMIMPSPEC2:
+		*val = etm_read(ETMIMPSPEC2);
+		return 0;
+	case ETMIMPSPEC3:
+		*val = etm_read(ETMIMPSPEC3);
+		return 0;
+	case ETMIMPSPEC4:
+		*val = etm_read(ETMIMPSPEC4);
+		return 0;
+	case ETMIMPSPEC5:
+		*val = etm_read(ETMIMPSPEC5);
+		return 0;
+	case ETMIMPSPEC6:
+		*val = etm_read(ETMIMPSPEC6);
+		return 0;
+	case ETMIMPSPEC7:
+		*val = etm_read(ETMIMPSPEC7);
+		return 0;
+	case ETMSYNCFR:
+		*val = etm_read(ETMSYNCFR);
+		return 0;
+	case ETMIDR:
+		*val = etm_read(ETMIDR);
+		return 0;
+	case ETMCCER:
+		*val = etm_read(ETMCCER);
+		return 0;
+	case ETMEXTINSELR:
+		*val = etm_read(ETMEXTINSELR);
+		return 0;
+	case ETMTESSEICR:
+		*val = etm_read(ETMTESSEICR);
+		return 0;
+	case ETMEIBCR:
+		*val = etm_read(ETMEIBCR);
+		return 0;
+	case ETMTSEVR:
+		*val = etm_read(ETMTSEVR);
+		return 0;
+	case ETMAUXCR:
+		*val = etm_read(ETMAUXCR);
+		return 0;
+	case ETMTRACEIDR:
+		*val = etm_read(ETMTRACEIDR);
+		return 0;
+	case ETMVMIDCVR:
+		*val = etm_read(ETMVMIDCVR);
+		return 0;
+	case ETMOSLSR:
+		*val = etm_read(ETMOSLSR);
+		return 0;
+	case ETMOSSRR:
+		*val = etm_read(ETMOSSRR);
+		return 0;
+	case ETMPDCR:
+		*val = etm_read(ETMPDCR);
+		return 0;
+	case ETMPDSR:
+		*val = etm_read(ETMPDSR);
+		return 0;
+	default:
+		*val = 0;
+		return -EINVAL;
+	}
+}
+
+int etm_writel_cp14(u32 reg, u32 val)
+{
+	switch (reg) {
+	case ETMCR:
+		etm_write(val, ETMCR);
+		break;
+	case ETMTRIGGER:
+		etm_write(val, ETMTRIGGER);
+		break;
+	case ETMSR:
+		etm_write(val, ETMSR);
+		break;
+	case ETMTSSCR:
+		etm_write(val, ETMTSSCR);
+		break;
+	case ETMTEEVR:
+		etm_write(val, ETMTEEVR);
+		break;
+	case ETMTECR1:
+		etm_write(val, ETMTECR1);
+		break;
+	case ETMFFLR:
+		etm_write(val, ETMFFLR);
+		break;
+	case ETMACVRn(0):
+		etm_write(val, ETMACVR0);
+		break;
+	case ETMACVRn(1):
+		etm_write(val, ETMACVR1);
+		break;
+	case ETMACVRn(2):
+		etm_write(val, ETMACVR2);
+		break;
+	case ETMACVRn(3):
+		etm_write(val, ETMACVR3);
+		break;
+	case ETMACVRn(4):
+		etm_write(val, ETMACVR4);
+		break;
+	case ETMACVRn(5):
+		etm_write(val, ETMACVR5);
+		break;
+	case ETMACVRn(6):
+		etm_write(val, ETMACVR6);
+		break;
+	case ETMACVRn(7):
+		etm_write(val, ETMACVR7);
+		break;
+	case ETMACVRn(8):
+		etm_write(val, ETMACVR8);
+		break;
+	case ETMACVRn(9):
+		etm_write(val, ETMACVR9);
+		break;
+	case ETMACVRn(10):
+		etm_write(val, ETMACVR10);
+		break;
+	case ETMACVRn(11):
+		etm_write(val, ETMACVR11);
+		break;
+	case ETMACVRn(12):
+		etm_write(val, ETMACVR12);
+		break;
+	case ETMACVRn(13):
+		etm_write(val, ETMACVR13);
+		break;
+	case ETMACVRn(14):
+		etm_write(val, ETMACVR14);
+		break;
+	case ETMACVRn(15):
+		etm_write(val, ETMACVR15);
+		break;
+	case ETMACTRn(0):
+		etm_write(val, ETMACTR0);
+		break;
+	case ETMACTRn(1):
+		etm_write(val, ETMACTR1);
+		break;
+	case ETMACTRn(2):
+		etm_write(val, ETMACTR2);
+		break;
+	case ETMACTRn(3):
+		etm_write(val, ETMACTR3);
+		break;
+	case ETMACTRn(4):
+		etm_write(val, ETMACTR4);
+		break;
+	case ETMACTRn(5):
+		etm_write(val, ETMACTR5);
+		break;
+	case ETMACTRn(6):
+		etm_write(val, ETMACTR6);
+		break;
+	case ETMACTRn(7):
+		etm_write(val, ETMACTR7);
+		break;
+	case ETMACTRn(8):
+		etm_write(val, ETMACTR8);
+		break;
+	case ETMACTRn(9):
+		etm_write(val, ETMACTR9);
+		break;
+	case ETMACTRn(10):
+		etm_write(val, ETMACTR10);
+		break;
+	case ETMACTRn(11):
+		etm_write(val, ETMACTR11);
+		break;
+	case ETMACTRn(12):
+		etm_write(val, ETMACTR12);
+		break;
+	case ETMACTRn(13):
+		etm_write(val, ETMACTR13);
+		break;
+	case ETMACTRn(14):
+		etm_write(val, ETMACTR14);
+		break;
+	case ETMACTRn(15):
+		etm_write(val, ETMACTR15);
+		break;
+	case ETMCNTRLDVRn(0):
+		etm_write(val, ETMCNTRLDVR0);
+		break;
+	case ETMCNTRLDVRn(1):
+		etm_write(val, ETMCNTRLDVR1);
+		break;
+	case ETMCNTRLDVRn(2):
+		etm_write(val, ETMCNTRLDVR2);
+		break;
+	case ETMCNTRLDVRn(3):
+		etm_write(val, ETMCNTRLDVR3);
+		break;
+	case ETMCNTENRn(0):
+		etm_write(val, ETMCNTENR0);
+		break;
+	case ETMCNTENRn(1):
+		etm_write(val, ETMCNTENR1);
+		break;
+	case ETMCNTENRn(2):
+		etm_write(val, ETMCNTENR2);
+		break;
+	case ETMCNTENRn(3):
+		etm_write(val, ETMCNTENR3);
+		break;
+	case ETMCNTRLDEVRn(0):
+		etm_write(val, ETMCNTRLDEVR0);
+		break;
+	case ETMCNTRLDEVRn(1):
+		etm_write(val, ETMCNTRLDEVR1);
+		break;
+	case ETMCNTRLDEVRn(2):
+		etm_write(val, ETMCNTRLDEVR2);
+		break;
+	case ETMCNTRLDEVRn(3):
+		etm_write(val, ETMCNTRLDEVR3);
+		break;
+	case ETMCNTVRn(0):
+		etm_write(val, ETMCNTVR0);
+		break;
+	case ETMCNTVRn(1):
+		etm_write(val, ETMCNTVR1);
+		break;
+	case ETMCNTVRn(2):
+		etm_write(val, ETMCNTVR2);
+		break;
+	case ETMCNTVRn(3):
+		etm_write(val, ETMCNTVR3);
+		break;
+	case ETMSQ12EVR:
+		etm_write(val, ETMSQ12EVR);
+		break;
+	case ETMSQ21EVR:
+		etm_write(val, ETMSQ21EVR);
+		break;
+	case ETMSQ23EVR:
+		etm_write(val, ETMSQ23EVR);
+		break;
+	case ETMSQ31EVR:
+		etm_write(val, ETMSQ31EVR);
+		break;
+	case ETMSQ32EVR:
+		etm_write(val, ETMSQ32EVR);
+		break;
+	case ETMSQ13EVR:
+		etm_write(val, ETMSQ13EVR);
+		break;
+	case ETMSQR:
+		etm_write(val, ETMSQR);
+		break;
+	case ETMEXTOUTEVRn(0):
+		etm_write(val, ETMEXTOUTEVR0);
+		break;
+	case ETMEXTOUTEVRn(1):
+		etm_write(val, ETMEXTOUTEVR1);
+		break;
+	case ETMEXTOUTEVRn(2):
+		etm_write(val, ETMEXTOUTEVR2);
+		break;
+	case ETMEXTOUTEVRn(3):
+		etm_write(val, ETMEXTOUTEVR3);
+		break;
+	case ETMCIDCVRn(0):
+		etm_write(val, ETMCIDCVR0);
+		break;
+	case ETMCIDCVRn(1):
+		etm_write(val, ETMCIDCVR1);
+		break;
+	case ETMCIDCVRn(2):
+		etm_write(val, ETMCIDCVR2);
+		break;
+	case ETMCIDCMR:
+		etm_write(val, ETMCIDCMR);
+		break;
+	case ETMIMPSPEC0:
+		etm_write(val, ETMIMPSPEC0);
+		break;
+	case ETMIMPSPEC1:
+		etm_write(val, ETMIMPSPEC1);
+		break;
+	case ETMIMPSPEC2:
+		etm_write(val, ETMIMPSPEC2);
+		break;
+	case ETMIMPSPEC3:
+		etm_write(val, ETMIMPSPEC3);
+		break;
+	case ETMIMPSPEC4:
+		etm_write(val, ETMIMPSPEC4);
+		break;
+	case ETMIMPSPEC5:
+		etm_write(val, ETMIMPSPEC5);
+		break;
+	case ETMIMPSPEC6:
+		etm_write(val, ETMIMPSPEC6);
+		break;
+	case ETMIMPSPEC7:
+		etm_write(val, ETMIMPSPEC7);
+		break;
+	case ETMSYNCFR:
+		etm_write(val, ETMSYNCFR);
+		break;
+	case ETMEXTINSELR:
+		etm_write(val, ETMEXTINSELR);
+		break;
+	case ETMTESSEICR:
+		etm_write(val, ETMTESSEICR);
+		break;
+	case ETMEIBCR:
+		etm_write(val, ETMEIBCR);
+		break;
+	case ETMTSEVR:
+		etm_write(val, ETMTSEVR);
+		break;
+	case ETMAUXCR:
+		etm_write(val, ETMAUXCR);
+		break;
+	case ETMTRACEIDR:
+		etm_write(val, ETMTRACEIDR);
+		break;
+	case ETMVMIDCVR:
+		etm_write(val, ETMVMIDCVR);
+		break;
+	case ETMOSLAR:
+		etm_write(val, ETMOSLAR);
+		break;
+	case ETMOSSRR:
+		etm_write(val, ETMOSSRR);
+		break;
+	case ETMPDCR:
+		etm_write(val, ETMPDCR);
+		break;
+	case ETMPDSR:
+		etm_write(val, ETMPDSR);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
diff --git a/drivers/hwtracing/coresight/coresight-etm.h b/drivers/hwtracing/coresight/coresight-etm.h
new file mode 100644
index 00000000000..501c5fac8a4
--- /dev/null
+++ b/drivers/hwtracing/coresight/coresight-etm.h
@@ -0,0 +1,251 @@
+/* Copyright (c) 2014-2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CORESIGHT_CORESIGHT_ETM_H
+#define _CORESIGHT_CORESIGHT_ETM_H
+
+#include <linux/spinlock.h>
+#include "coresight-priv.h"
+
+/*
+ * Device registers:
+ * 0x000 - 0x2FC: Trace         registers
+ * 0x300 - 0x314: Management    registers
+ * 0x318 - 0xEFC: Trace         registers
+ *
+ * Coresight registers
+ * 0xF00 - 0xF9C: Management    registers
+ * 0xFA0 - 0xFA4: Management    registers in PFTv1.0
+ *                Trace         registers in PFTv1.1
+ * 0xFA8 - 0xFFC: Management    registers
+ */
+
+/* Trace registers (0x000-0x2FC) */
+#define ETMCR			0x000
+#define ETMCCR			0x004
+#define ETMTRIGGER		0x008
+#define ETMSR			0x010
+#define ETMSCR			0x014
+#define ETMTSSCR		0x018
+#define ETMTECR2		0x01c
+#define ETMTEEVR		0x020
+#define ETMTECR1		0x024
+#define ETMFFLR			0x02c
+#define ETMACVRn(n)		(0x040 + (n * 4))
+#define ETMACTRn(n)		(0x080 + (n * 4))
+#define ETMCNTRLDVRn(n)		(0x140 + (n * 4))
+#define ETMCNTENRn(n)		(0x150 + (n * 4))
+#define ETMCNTRLDEVRn(n)	(0x160 + (n * 4))
+#define ETMCNTVRn(n)		(0x170 + (n * 4))
+#define ETMSQ12EVR		0x180
+#define ETMSQ21EVR		0x184
+#define ETMSQ23EVR		0x188
+#define ETMSQ31EVR		0x18c
+#define ETMSQ32EVR		0x190
+#define ETMSQ13EVR		0x194
+#define ETMSQR			0x19c
+#define ETMEXTOUTEVRn(n)	(0x1a0 + (n * 4))
+#define ETMCIDCVRn(n)		(0x1b0 + (n * 4))
+#define ETMCIDCMR		0x1bc
+#define ETMIMPSPEC0		0x1c0
+#define ETMIMPSPEC1		0x1c4
+#define ETMIMPSPEC2		0x1c8
+#define ETMIMPSPEC3		0x1cc
+#define ETMIMPSPEC4		0x1d0
+#define ETMIMPSPEC5		0x1d4
+#define ETMIMPSPEC6		0x1d8
+#define ETMIMPSPEC7		0x1dc
+#define ETMSYNCFR		0x1e0
+#define ETMIDR			0x1e4
+#define ETMCCER			0x1e8
+#define ETMEXTINSELR		0x1ec
+#define ETMTESSEICR		0x1f0
+#define ETMEIBCR		0x1f4
+#define ETMTSEVR		0x1f8
+#define ETMAUXCR		0x1fc
+#define ETMTRACEIDR		0x200
+#define ETMVMIDCVR		0x240
+/* Management registers (0x300-0x314) */
+#define ETMOSLAR		0x300
+#define ETMOSLSR		0x304
+#define ETMOSSRR		0x308
+#define ETMPDCR			0x310
+#define ETMPDSR			0x314
+#define ETM_MAX_ADDR_CMP	16
+#define ETM_MAX_CNTR		4
+#define ETM_MAX_CTXID_CMP	3
+
+/* Register definition */
+/* ETMCR - 0x00 */
+#define ETMCR_PWD_DWN		BIT(0)
+#define ETMCR_STALL_MODE	BIT(7)
+#define ETMCR_ETM_PRG		BIT(10)
+#define ETMCR_ETM_EN		BIT(11)
+#define ETMCR_CYC_ACC		BIT(12)
+#define ETMCR_CTXID_SIZE	(BIT(14)|BIT(15))
+#define ETMCR_TIMESTAMP_EN	BIT(28)
+/* ETMCCR - 0x04 */
+#define ETMCCR_FIFOFULL		BIT(23)
+/* ETMPDCR - 0x310 */
+#define ETMPDCR_PWD_UP		BIT(3)
+/* ETMTECR1 - 0x024 */
+#define ETMTECR1_ADDR_COMP_1	BIT(0)
+#define ETMTECR1_INC_EXC	BIT(24)
+#define ETMTECR1_START_STOP	BIT(25)
+/* ETMCCER - 0x1E8 */
+#define ETMCCER_TIMESTAMP	BIT(22)
+
+#define ETM_MODE_EXCLUDE	BIT(0)
+#define ETM_MODE_CYCACC		BIT(1)
+#define ETM_MODE_STALL		BIT(2)
+#define ETM_MODE_TIMESTAMP	BIT(3)
+#define ETM_MODE_CTXID		BIT(4)
+#define ETM_MODE_ALL		0x1f
+
+#define ETM_SQR_MASK		0x3
+#define ETM_TRACEID_MASK	0x3f
+#define ETM_EVENT_MASK		0x1ffff
+#define ETM_SYNC_MASK		0xfff
+#define ETM_ALL_MASK		0xffffffff
+
+#define ETMSR_PROG_BIT		1
+#define ETM_SEQ_STATE_MAX_VAL	(0x2)
+#define PORT_SIZE_MASK		(GENMASK(21, 21) | GENMASK(6, 4))
+
+#define ETM_HARD_WIRE_RES_A	/* Hard wired, always true */	\
+				((0x0f << 0)	|		\
+				/* Resource index A */		\
+				(0x06 << 4))
+
+#define ETM_ADD_COMP_0		/* Single addr comparator 1 */	\
+				((0x00 << 7)	|		\
+				/* Resource index B */		\
+				(0x00 << 11))
+
+#define ETM_EVENT_NOT_A		BIT(14) /* NOT(A) */
+
+#define ETM_DEFAULT_EVENT_VAL	(ETM_HARD_WIRE_RES_A	|	\
+				 ETM_ADD_COMP_0		|	\
+				 ETM_EVENT_NOT_A)
+/**
+ * struct etm_drvdata - specifics associated to an ETM component
+ * @base:	memory mapped base address for this component.
+ * @dev:	the device entity associated to this component.
+ * @csdev:	component vitals needed by the framework.
+ * @clk:	the clock this component is associated to.
+ * @spinlock:	only one at a time pls.
+ * @cpu:	the cpu this component is affined to.
+ * @port_size:	port size as reported by ETMCR bit 4-6 and 21.
+ * @arch:	ETM/PTM version number.
+ * @use_cpu14:	true if management registers need to be accessed via CP14.
+ * @enable:	is this ETM/PTM currently tracing.
+ * @sticky_enable: true if ETM base configuration has been done.
+ * @boot_enable:true if we should start tracing at boot time.
+ * @os_unlock:	true if access to management registers is allowed.
+ * @nr_addr_cmp:Number of pairs of address comparators as found in ETMCCR.
+ * @nr_cntr:	Number of counters as found in ETMCCR bit 13-15.
+ * @nr_ext_inp:	Number of external input as found in ETMCCR bit 17-19.
+ * @nr_ext_out:	Number of external output as found in ETMCCR bit 20-22.
+ * @nr_ctxid_cmp: Number of contextID comparators as found in ETMCCR bit 24-25.
+ * @etmccr:	value of register ETMCCR.
+ * @etmccer:	value of register ETMCCER.
+ * @traceid:	value of the current ID for this component.
+ * @mode:	controls various modes supported by this ETM/PTM.
+ * @ctrl:	used in conjunction with @mode.
+ * @trigger_event: setting for register ETMTRIGGER.
+ * @startstop_ctrl: setting for register ETMTSSCR.
+ * @enable_event: setting for register ETMTEEVR.
+ * @enable_ctrl1: setting for register ETMTECR1.
+ * @fifofull_level: setting for register ETMFFLR.
+ * @addr_idx:	index for the address comparator selection.
+ * @addr_val:	value for address comparator register.
+ * @addr_acctype: access type for address comparator register.
+ * @addr_type:	current status of the comparator register.
+ * @cntr_idx:	index for the counter register selection.
+ * @cntr_rld_val: reload value of a counter register.
+ * @cntr_event:	control for counter enable register.
+ * @cntr_rld_event: value for counter reload event register.
+ * @cntr_val:	counter value register.
+ * @seq_12_event: event causing the transition from 1 to 2.
+ * @seq_21_event: event causing the transition from 2 to 1.
+ * @seq_23_event: event causing the transition from 2 to 3.
+ * @seq_31_event: event causing the transition from 3 to 1.
+ * @seq_32_event: event causing the transition from 3 to 2.
+ * @seq_13_event: event causing the transition from 1 to 3.
+ * @seq_curr_state: current value of the sequencer register.
+ * @ctxid_idx: index for the context ID registers.
+ * @ctxid_val: value for the context ID to trigger on.
+ * @ctxid_mask: mask applicable to all the context IDs.
+ * @sync_freq:	Synchronisation frequency.
+ * @timestamp_event: Defines an event that requests the insertion
+		     of a timestamp into the trace stream.
+ */
+struct etm_drvdata {
+	void __iomem			*base;
+	struct device			*dev;
+	struct coresight_device		*csdev;
+	struct clk			*clk;
+	spinlock_t			spinlock;
+	int				cpu;
+	int				port_size;
+	u8				arch;
+	bool				use_cp14;
+	bool				enable;
+	bool				sticky_enable;
+	bool				boot_enable;
+	bool				os_unlock;
+	u8				nr_addr_cmp;
+	u8				nr_cntr;
+	u8				nr_ext_inp;
+	u8				nr_ext_out;
+	u8				nr_ctxid_cmp;
+	u32				etmccr;
+	u32				etmccer;
+	u32				traceid;
+	u32				mode;
+	u32				ctrl;
+	u32				trigger_event;
+	u32				startstop_ctrl;
+	u32				enable_event;
+	u32				enable_ctrl1;
+	u32				fifofull_level;
+	u8				addr_idx;
+	u32				addr_val[ETM_MAX_ADDR_CMP];
+	u32				addr_acctype[ETM_MAX_ADDR_CMP];
+	u32				addr_type[ETM_MAX_ADDR_CMP];
+	u8				cntr_idx;
+	u32				cntr_rld_val[ETM_MAX_CNTR];
+	u32				cntr_event[ETM_MAX_CNTR];
+	u32				cntr_rld_event[ETM_MAX_CNTR];
+	u32				cntr_val[ETM_MAX_CNTR];
+	u32				seq_12_event;
+	u32				seq_21_event;
+	u32				seq_23_event;
+	u32				seq_31_event;
+	u32				seq_32_event;
+	u32				seq_13_event;
+	u32				seq_curr_state;
+	u8				ctxid_idx;
+	u32				ctxid_val[ETM_MAX_CTXID_CMP];
+	u32				ctxid_mask;
+	u32				sync_freq;
+	u32				timestamp_event;
+};
+
+enum etm_addr_type {
+	ETM_ADDR_TYPE_NONE,
+	ETM_ADDR_TYPE_SINGLE,
+	ETM_ADDR_TYPE_RANGE,
+	ETM_ADDR_TYPE_START,
+	ETM_ADDR_TYPE_STOP,
+};
+#endif
diff --git a/drivers/hwtracing/coresight/coresight-etm3x.c b/drivers/hwtracing/coresight/coresight-etm3x.c
new file mode 100644
index 00000000000..c965f5724ab
--- /dev/null
+++ b/drivers/hwtracing/coresight/coresight-etm3x.c
@@ -0,0 +1,1932 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/smp.h>
+#include <linux/sysfs.h>
+#include <linux/stat.h>
+#include <linux/clk.h>
+#include <linux/cpu.h>
+#include <linux/of.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
+#include <asm/sections.h>
+
+#include "coresight-etm.h"
+
+static int boot_enable;
+module_param_named(boot_enable, boot_enable, int, S_IRUGO);
+
+/* The number of ETM/PTM currently registered */
+static int etm_count;
+static struct etm_drvdata *etmdrvdata[NR_CPUS];
+
+static inline void etm_writel(struct etm_drvdata *drvdata,
+			      u32 val, u32 off)
+{
+	if (drvdata->use_cp14) {
+		if (etm_writel_cp14(off, val)) {
+			dev_err(drvdata->dev,
+				"invalid CP14 access to ETM reg: %#x", off);
+		}
+	} else {
+		writel_relaxed(val, drvdata->base + off);
+	}
+}
+
+static inline unsigned int etm_readl(struct etm_drvdata *drvdata, u32 off)
+{
+	u32 val;
+
+	if (drvdata->use_cp14) {
+		if (etm_readl_cp14(off, &val)) {
+			dev_err(drvdata->dev,
+				"invalid CP14 access to ETM reg: %#x", off);
+		}
+	} else {
+		val = readl_relaxed(drvdata->base + off);
+	}
+
+	return val;
+}
+
+/*
+ * Memory mapped writes to clear os lock are not supported on some processors
+ * and OS lock must be unlocked before any memory mapped access on such
+ * processors, otherwise memory mapped reads/writes will be invalid.
+ */
+static void etm_os_unlock(void *info)
+{
+	struct etm_drvdata *drvdata = (struct etm_drvdata *)info;
+	/* Writing any value to ETMOSLAR unlocks the trace registers */
+	etm_writel(drvdata, 0x0, ETMOSLAR);
+	isb();
+}
+
+static void etm_set_pwrdwn(struct etm_drvdata *drvdata)
+{
+	u32 etmcr;
+
+	/* Ensure pending cp14 accesses complete before setting pwrdwn */
+	mb();
+	isb();
+	etmcr = etm_readl(drvdata, ETMCR);
+	etmcr |= ETMCR_PWD_DWN;
+	etm_writel(drvdata, etmcr, ETMCR);
+}
+
+static void etm_clr_pwrdwn(struct etm_drvdata *drvdata)
+{
+	u32 etmcr;
+
+	etmcr = etm_readl(drvdata, ETMCR);
+	etmcr &= ~ETMCR_PWD_DWN;
+	etm_writel(drvdata, etmcr, ETMCR);
+	/* Ensure pwrup completes before subsequent cp14 accesses */
+	mb();
+	isb();
+}
+
+static void etm_set_pwrup(struct etm_drvdata *drvdata)
+{
+	u32 etmpdcr;
+
+	etmpdcr = readl_relaxed(drvdata->base + ETMPDCR);
+	etmpdcr |= ETMPDCR_PWD_UP;
+	writel_relaxed(etmpdcr, drvdata->base + ETMPDCR);
+	/* Ensure pwrup completes before subsequent cp14 accesses */
+	mb();
+	isb();
+}
+
+static void etm_clr_pwrup(struct etm_drvdata *drvdata)
+{
+	u32 etmpdcr;
+
+	/* Ensure pending cp14 accesses complete before clearing pwrup */
+	mb();
+	isb();
+	etmpdcr = readl_relaxed(drvdata->base + ETMPDCR);
+	etmpdcr &= ~ETMPDCR_PWD_UP;
+	writel_relaxed(etmpdcr, drvdata->base + ETMPDCR);
+}
+
+/**
+ * coresight_timeout_etm - loop until a bit has changed to a specific state.
+ * @drvdata: etm's private data structure.
+ * @offset: address of a register, starting from @addr.
+ * @position: the position of the bit of interest.
+ * @value: the value the bit should have.
+ *
+ * Basically the same as @coresight_timeout except for the register access
+ * method where we have to account for CP14 configurations.
+
+ * Return: 0 as soon as the bit has taken the desired state or -EAGAIN if
+ * TIMEOUT_US has elapsed, which ever happens first.
+ */
+
+static int coresight_timeout_etm(struct etm_drvdata *drvdata, u32 offset,
+				  int position, int value)
+{
+	int i;
+	u32 val;
+
+	for (i = TIMEOUT_US; i > 0; i--) {
+		val = etm_readl(drvdata, offset);
+		/* Waiting on the bit to go from 0 to 1 */
+		if (value) {
+			if (val & BIT(position))
+				return 0;
+		/* Waiting on the bit to go from 1 to 0 */
+		} else {
+			if (!(val & BIT(position)))
+				return 0;
+		}
+
+		/*
+		 * Delay is arbitrary - the specification doesn't say how long
+		 * we are expected to wait.  Extra check required to make sure
+		 * we don't wait needlessly on the last iteration.
+		 */
+		if (i - 1)
+			udelay(1);
+	}
+
+	return -EAGAIN;
+}
+
+
+static void etm_set_prog(struct etm_drvdata *drvdata)
+{
+	u32 etmcr;
+
+	etmcr = etm_readl(drvdata, ETMCR);
+	etmcr |= ETMCR_ETM_PRG;
+	etm_writel(drvdata, etmcr, ETMCR);
+	/*
+	 * Recommended by spec for cp14 accesses to ensure etmcr write is
+	 * complete before polling etmsr
+	 */
+	isb();
+	if (coresight_timeout_etm(drvdata, ETMSR, ETMSR_PROG_BIT, 1)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n", ETMSR);
+	}
+}
+
+static void etm_clr_prog(struct etm_drvdata *drvdata)
+{
+	u32 etmcr;
+
+	etmcr = etm_readl(drvdata, ETMCR);
+	etmcr &= ~ETMCR_ETM_PRG;
+	etm_writel(drvdata, etmcr, ETMCR);
+	/*
+	 * Recommended by spec for cp14 accesses to ensure etmcr write is
+	 * complete before polling etmsr
+	 */
+	isb();
+	if (coresight_timeout_etm(drvdata, ETMSR, ETMSR_PROG_BIT, 0)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n", ETMSR);
+	}
+}
+
+static void etm_set_default(struct etm_drvdata *drvdata)
+{
+	int i;
+
+	drvdata->trigger_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->enable_event = ETM_HARD_WIRE_RES_A;
+
+	drvdata->seq_12_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->seq_21_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->seq_23_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->seq_31_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->seq_32_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->seq_13_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->timestamp_event = ETM_DEFAULT_EVENT_VAL;
+
+	for (i = 0; i < drvdata->nr_cntr; i++) {
+		drvdata->cntr_rld_val[i] = 0x0;
+		drvdata->cntr_event[i] = ETM_DEFAULT_EVENT_VAL;
+		drvdata->cntr_rld_event[i] = ETM_DEFAULT_EVENT_VAL;
+		drvdata->cntr_val[i] = 0x0;
+	}
+
+	drvdata->seq_curr_state = 0x0;
+	drvdata->ctxid_idx = 0x0;
+	for (i = 0; i < drvdata->nr_ctxid_cmp; i++)
+		drvdata->ctxid_val[i] = 0x0;
+	drvdata->ctxid_mask = 0x0;
+}
+
+static void etm_enable_hw(void *info)
+{
+	int i;
+	u32 etmcr;
+	struct etm_drvdata *drvdata = info;
+
+	CS_UNLOCK(drvdata->base);
+
+	/* Turn engine on */
+	etm_clr_pwrdwn(drvdata);
+	/* Apply power to trace registers */
+	etm_set_pwrup(drvdata);
+	/* Make sure all registers are accessible */
+	etm_os_unlock(drvdata);
+
+	etm_set_prog(drvdata);
+
+	etmcr = etm_readl(drvdata, ETMCR);
+	etmcr &= (ETMCR_PWD_DWN | ETMCR_ETM_PRG);
+	etmcr |= drvdata->port_size;
+	etm_writel(drvdata, drvdata->ctrl | etmcr, ETMCR);
+	etm_writel(drvdata, drvdata->trigger_event, ETMTRIGGER);
+	etm_writel(drvdata, drvdata->startstop_ctrl, ETMTSSCR);
+	etm_writel(drvdata, drvdata->enable_event, ETMTEEVR);
+	etm_writel(drvdata, drvdata->enable_ctrl1, ETMTECR1);
+	etm_writel(drvdata, drvdata->fifofull_level, ETMFFLR);
+	for (i = 0; i < drvdata->nr_addr_cmp; i++) {
+		etm_writel(drvdata, drvdata->addr_val[i], ETMACVRn(i));
+		etm_writel(drvdata, drvdata->addr_acctype[i], ETMACTRn(i));
+	}
+	for (i = 0; i < drvdata->nr_cntr; i++) {
+		etm_writel(drvdata, drvdata->cntr_rld_val[i], ETMCNTRLDVRn(i));
+		etm_writel(drvdata, drvdata->cntr_event[i], ETMCNTENRn(i));
+		etm_writel(drvdata, drvdata->cntr_rld_event[i],
+			   ETMCNTRLDEVRn(i));
+		etm_writel(drvdata, drvdata->cntr_val[i], ETMCNTVRn(i));
+	}
+	etm_writel(drvdata, drvdata->seq_12_event, ETMSQ12EVR);
+	etm_writel(drvdata, drvdata->seq_21_event, ETMSQ21EVR);
+	etm_writel(drvdata, drvdata->seq_23_event, ETMSQ23EVR);
+	etm_writel(drvdata, drvdata->seq_31_event, ETMSQ31EVR);
+	etm_writel(drvdata, drvdata->seq_32_event, ETMSQ32EVR);
+	etm_writel(drvdata, drvdata->seq_13_event, ETMSQ13EVR);
+	etm_writel(drvdata, drvdata->seq_curr_state, ETMSQR);
+	for (i = 0; i < drvdata->nr_ext_out; i++)
+		etm_writel(drvdata, ETM_DEFAULT_EVENT_VAL, ETMEXTOUTEVRn(i));
+	for (i = 0; i < drvdata->nr_ctxid_cmp; i++)
+		etm_writel(drvdata, drvdata->ctxid_val[i], ETMCIDCVRn(i));
+	etm_writel(drvdata, drvdata->ctxid_mask, ETMCIDCMR);
+	etm_writel(drvdata, drvdata->sync_freq, ETMSYNCFR);
+	/* No external input selected */
+	etm_writel(drvdata, 0x0, ETMEXTINSELR);
+	etm_writel(drvdata, drvdata->timestamp_event, ETMTSEVR);
+	/* No auxiliary control selected */
+	etm_writel(drvdata, 0x0, ETMAUXCR);
+	etm_writel(drvdata, drvdata->traceid, ETMTRACEIDR);
+	/* No VMID comparator value selected */
+	etm_writel(drvdata, 0x0, ETMVMIDCVR);
+
+	/* Ensures trace output is enabled from this ETM */
+	etm_writel(drvdata, drvdata->ctrl | ETMCR_ETM_EN | etmcr, ETMCR);
+
+	etm_clr_prog(drvdata);
+	CS_LOCK(drvdata->base);
+
+	dev_dbg(drvdata->dev, "cpu: %d enable smp call done\n", drvdata->cpu);
+}
+
+static int etm_trace_id_simple(struct etm_drvdata *drvdata)
+{
+	if (!drvdata->enable)
+		return drvdata->traceid;
+
+	return (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK);
+}
+
+static int etm_trace_id(struct coresight_device *csdev)
+{
+	struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	unsigned long flags;
+	int trace_id = -1;
+
+	if (!drvdata->enable)
+		return drvdata->traceid;
+
+	if (clk_prepare_enable(drvdata->clk))
+		goto out;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+
+	CS_UNLOCK(drvdata->base);
+	trace_id = (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK);
+	CS_LOCK(drvdata->base);
+
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	clk_disable_unprepare(drvdata->clk);
+out:
+	return trace_id;
+}
+
+static int etm_enable(struct coresight_device *csdev)
+{
+	struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	int ret;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		goto err_clk;
+
+	spin_lock(&drvdata->spinlock);
+
+	/*
+	 * Configure the ETM only if the CPU is online.  If it isn't online
+	 * hw configuration will take place when 'CPU_STARTING' is received
+	 * in @etm_cpu_callback.
+	 */
+	if (cpu_online(drvdata->cpu)) {
+		ret = smp_call_function_single(drvdata->cpu,
+					       etm_enable_hw, drvdata, 1);
+		if (ret)
+			goto err;
+	}
+
+	drvdata->enable = true;
+	drvdata->sticky_enable = true;
+
+	spin_unlock(&drvdata->spinlock);
+
+	dev_info(drvdata->dev, "ETM tracing enabled\n");
+	return 0;
+err:
+	spin_unlock(&drvdata->spinlock);
+	clk_disable_unprepare(drvdata->clk);
+err_clk:
+	return ret;
+}
+
+static void etm_disable_hw(void *info)
+{
+	int i;
+	struct etm_drvdata *drvdata = info;
+
+	CS_UNLOCK(drvdata->base);
+	etm_set_prog(drvdata);
+
+	/* Program trace enable to low by using always false event */
+	etm_writel(drvdata, ETM_HARD_WIRE_RES_A | ETM_EVENT_NOT_A, ETMTEEVR);
+
+	/* Read back sequencer and counters for post trace analysis */
+	drvdata->seq_curr_state = (etm_readl(drvdata, ETMSQR) & ETM_SQR_MASK);
+
+	for (i = 0; i < drvdata->nr_cntr; i++)
+		drvdata->cntr_val[i] = etm_readl(drvdata, ETMCNTVRn(i));
+
+	etm_set_pwrdwn(drvdata);
+	CS_LOCK(drvdata->base);
+
+	dev_dbg(drvdata->dev, "cpu: %d disable smp call done\n", drvdata->cpu);
+}
+
+static void etm_disable(struct coresight_device *csdev)
+{
+	struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	/*
+	 * Taking hotplug lock here protects from clocks getting disabled
+	 * with tracing being left on (crash scenario) if user disable occurs
+	 * after cpu online mask indicates the cpu is offline but before the
+	 * DYING hotplug callback is serviced by the ETM driver.
+	 */
+	get_online_cpus();
+	spin_lock(&drvdata->spinlock);
+
+	/*
+	 * Executing etm_disable_hw on the cpu whose ETM is being disabled
+	 * ensures that register writes occur when cpu is powered.
+	 */
+	smp_call_function_single(drvdata->cpu, etm_disable_hw, drvdata, 1);
+	drvdata->enable = false;
+
+	spin_unlock(&drvdata->spinlock);
+	put_online_cpus();
+
+	clk_disable_unprepare(drvdata->clk);
+
+	dev_info(drvdata->dev, "ETM tracing disabled\n");
+}
+
+static const struct coresight_ops_source etm_source_ops = {
+	.trace_id	= etm_trace_id,
+	.enable		= etm_enable,
+	.disable	= etm_disable,
+};
+
+static const struct coresight_ops etm_cs_ops = {
+	.source_ops	= &etm_source_ops,
+};
+
+static ssize_t nr_addr_cmp_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->nr_addr_cmp;
+	return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(nr_addr_cmp);
+
+static ssize_t nr_cntr_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->nr_cntr;
+	return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(nr_cntr);
+
+static ssize_t nr_ctxid_cmp_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->nr_ctxid_cmp;
+	return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(nr_ctxid_cmp);
+
+static ssize_t etmsr_show(struct device *dev,
+			  struct device_attribute *attr, char *buf)
+{
+	int ret;
+	unsigned long flags, val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	CS_UNLOCK(drvdata->base);
+
+	val = etm_readl(drvdata, ETMSR);
+
+	CS_LOCK(drvdata->base);
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	clk_disable_unprepare(drvdata->clk);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(etmsr);
+
+static ssize_t reset_store(struct device *dev,
+			   struct device_attribute *attr,
+			   const char *buf, size_t size)
+{
+	int i, ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val) {
+		spin_lock(&drvdata->spinlock);
+		drvdata->mode = ETM_MODE_EXCLUDE;
+		drvdata->ctrl = 0x0;
+		drvdata->trigger_event = ETM_DEFAULT_EVENT_VAL;
+		drvdata->startstop_ctrl = 0x0;
+		drvdata->addr_idx = 0x0;
+		for (i = 0; i < drvdata->nr_addr_cmp; i++) {
+			drvdata->addr_val[i] = 0x0;
+			drvdata->addr_acctype[i] = 0x0;
+			drvdata->addr_type[i] = ETM_ADDR_TYPE_NONE;
+		}
+		drvdata->cntr_idx = 0x0;
+
+		etm_set_default(drvdata);
+		spin_unlock(&drvdata->spinlock);
+	}
+
+	return size;
+}
+static DEVICE_ATTR_WO(reset);
+
+static ssize_t mode_show(struct device *dev,
+			 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->mode;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t mode_store(struct device *dev,
+			  struct device_attribute *attr,
+			  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->mode = val & ETM_MODE_ALL;
+
+	if (drvdata->mode & ETM_MODE_EXCLUDE)
+		drvdata->enable_ctrl1 |= ETMTECR1_INC_EXC;
+	else
+		drvdata->enable_ctrl1 &= ~ETMTECR1_INC_EXC;
+
+	if (drvdata->mode & ETM_MODE_CYCACC)
+		drvdata->ctrl |= ETMCR_CYC_ACC;
+	else
+		drvdata->ctrl &= ~ETMCR_CYC_ACC;
+
+	if (drvdata->mode & ETM_MODE_STALL) {
+		if (!(drvdata->etmccr & ETMCCR_FIFOFULL)) {
+			dev_warn(drvdata->dev, "stall mode not supported\n");
+			ret = -EINVAL;
+			goto err_unlock;
+		}
+		drvdata->ctrl |= ETMCR_STALL_MODE;
+	 } else
+		drvdata->ctrl &= ~ETMCR_STALL_MODE;
+
+	if (drvdata->mode & ETM_MODE_TIMESTAMP) {
+		if (!(drvdata->etmccer & ETMCCER_TIMESTAMP)) {
+			dev_warn(drvdata->dev, "timestamp not supported\n");
+			ret = -EINVAL;
+			goto err_unlock;
+		}
+		drvdata->ctrl |= ETMCR_TIMESTAMP_EN;
+	} else
+		drvdata->ctrl &= ~ETMCR_TIMESTAMP_EN;
+
+	if (drvdata->mode & ETM_MODE_CTXID)
+		drvdata->ctrl |= ETMCR_CTXID_SIZE;
+	else
+		drvdata->ctrl &= ~ETMCR_CTXID_SIZE;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+
+err_unlock:
+	spin_unlock(&drvdata->spinlock);
+	return ret;
+}
+static DEVICE_ATTR_RW(mode);
+
+static ssize_t trigger_event_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->trigger_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t trigger_event_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->trigger_event = val & ETM_EVENT_MASK;
+
+	return size;
+}
+static DEVICE_ATTR_RW(trigger_event);
+
+static ssize_t enable_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->enable_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t enable_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->enable_event = val & ETM_EVENT_MASK;
+
+	return size;
+}
+static DEVICE_ATTR_RW(enable_event);
+
+static ssize_t fifofull_level_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->fifofull_level;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t fifofull_level_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->fifofull_level = val;
+
+	return size;
+}
+static DEVICE_ATTR_RW(fifofull_level);
+
+static ssize_t addr_idx_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->addr_idx;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_idx_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val >= drvdata->nr_addr_cmp)
+		return -EINVAL;
+
+	/*
+	 * Use spinlock to ensure index doesn't change while it gets
+	 * dereferenced multiple times within a spinlock block elsewhere.
+	 */
+	spin_lock(&drvdata->spinlock);
+	drvdata->addr_idx = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_idx);
+
+static ssize_t addr_single_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	u8 idx;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_SINGLE)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EINVAL;
+	}
+
+	val = drvdata->addr_val[idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_single_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t size)
+{
+	u8 idx;
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_SINGLE)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EINVAL;
+	}
+
+	drvdata->addr_val[idx] = val;
+	drvdata->addr_type[idx] = ETM_ADDR_TYPE_SINGLE;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_single);
+
+static ssize_t addr_range_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	u8 idx;
+	unsigned long val1, val2;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (idx % 2 != 0) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+	if (!((drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE &&
+	       drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_NONE) ||
+	      (drvdata->addr_type[idx] == ETM_ADDR_TYPE_RANGE &&
+	       drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_RANGE))) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	val1 = drvdata->addr_val[idx];
+	val2 = drvdata->addr_val[idx + 1];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx %#lx\n", val1, val2);
+}
+
+static ssize_t addr_range_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	u8 idx;
+	unsigned long val1, val2;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	if (sscanf(buf, "%lx %lx", &val1, &val2) != 2)
+		return -EINVAL;
+	/* Lower address comparator cannot have a higher address value */
+	if (val1 > val2)
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (idx % 2 != 0) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+	if (!((drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE &&
+	       drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_NONE) ||
+	      (drvdata->addr_type[idx] == ETM_ADDR_TYPE_RANGE &&
+	       drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_RANGE))) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	drvdata->addr_val[idx] = val1;
+	drvdata->addr_type[idx] = ETM_ADDR_TYPE_RANGE;
+	drvdata->addr_val[idx + 1] = val2;
+	drvdata->addr_type[idx + 1] = ETM_ADDR_TYPE_RANGE;
+	drvdata->enable_ctrl1 |= (1 << (idx/2));
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_range);
+
+static ssize_t addr_start_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	u8 idx;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_START)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	val = drvdata->addr_val[idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_start_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t size)
+{
+	u8 idx;
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_START)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	drvdata->addr_val[idx] = val;
+	drvdata->addr_type[idx] = ETM_ADDR_TYPE_START;
+	drvdata->startstop_ctrl |= (1 << idx);
+	drvdata->enable_ctrl1 |= BIT(25);
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_start);
+
+static ssize_t addr_stop_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	u8 idx;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_STOP)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	val = drvdata->addr_val[idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_stop_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t size)
+{
+	u8 idx;
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_STOP)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	drvdata->addr_val[idx] = val;
+	drvdata->addr_type[idx] = ETM_ADDR_TYPE_STOP;
+	drvdata->startstop_ctrl |= (1 << (idx + 16));
+	drvdata->enable_ctrl1 |= ETMTECR1_START_STOP;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_stop);
+
+static ssize_t addr_acctype_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	val = drvdata->addr_acctype[drvdata->addr_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_acctype_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->addr_acctype[drvdata->addr_idx] = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_acctype);
+
+static ssize_t cntr_idx_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->cntr_idx;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_idx_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val >= drvdata->nr_cntr)
+		return -EINVAL;
+	/*
+	 * Use spinlock to ensure index doesn't change while it gets
+	 * dereferenced multiple times within a spinlock block elsewhere.
+	 */
+	spin_lock(&drvdata->spinlock);
+	drvdata->cntr_idx = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_idx);
+
+static ssize_t cntr_rld_val_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	val = drvdata->cntr_rld_val[drvdata->cntr_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_rld_val_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->cntr_rld_val[drvdata->cntr_idx] = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_rld_val);
+
+static ssize_t cntr_event_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	val = drvdata->cntr_event[drvdata->cntr_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_event_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->cntr_event[drvdata->cntr_idx] = val & ETM_EVENT_MASK;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_event);
+
+static ssize_t cntr_rld_event_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	val = drvdata->cntr_rld_event[drvdata->cntr_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_rld_event_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->cntr_rld_event[drvdata->cntr_idx] = val & ETM_EVENT_MASK;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_rld_event);
+
+static ssize_t cntr_val_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	int i, ret = 0;
+	u32 val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	if (!drvdata->enable) {
+		spin_lock(&drvdata->spinlock);
+		for (i = 0; i < drvdata->nr_cntr; i++)
+			ret += sprintf(buf, "counter %d: %x\n",
+				       i, drvdata->cntr_val[i]);
+		spin_unlock(&drvdata->spinlock);
+		return ret;
+	}
+
+	for (i = 0; i < drvdata->nr_cntr; i++) {
+		val = etm_readl(drvdata, ETMCNTVRn(i));
+		ret += sprintf(buf, "counter %d: %x\n", i, val);
+	}
+
+	return ret;
+}
+
+static ssize_t cntr_val_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->cntr_val[drvdata->cntr_idx] = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_val);
+
+static ssize_t seq_12_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_12_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_12_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_12_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_12_event);
+
+static ssize_t seq_21_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_21_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_21_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_21_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_21_event);
+
+static ssize_t seq_23_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_23_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_23_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_23_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_23_event);
+
+static ssize_t seq_31_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_31_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_31_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_31_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_31_event);
+
+static ssize_t seq_32_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_32_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_32_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_32_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_32_event);
+
+static ssize_t seq_13_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_13_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_13_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_13_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_13_event);
+
+static ssize_t seq_curr_state_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	int ret;
+	unsigned long val, flags;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	if (!drvdata->enable) {
+		val = drvdata->seq_curr_state;
+		goto out;
+	}
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+
+	CS_UNLOCK(drvdata->base);
+	val = (etm_readl(drvdata, ETMSQR) & ETM_SQR_MASK);
+	CS_LOCK(drvdata->base);
+
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	clk_disable_unprepare(drvdata->clk);
+out:
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_curr_state_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val > ETM_SEQ_STATE_MAX_VAL)
+		return -EINVAL;
+
+	drvdata->seq_curr_state = val;
+
+	return size;
+}
+static DEVICE_ATTR_RW(seq_curr_state);
+
+static ssize_t ctxid_idx_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->ctxid_idx;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t ctxid_idx_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val >= drvdata->nr_ctxid_cmp)
+		return -EINVAL;
+
+	/*
+	 * Use spinlock to ensure index doesn't change while it gets
+	 * dereferenced multiple times within a spinlock block elsewhere.
+	 */
+	spin_lock(&drvdata->spinlock);
+	drvdata->ctxid_idx = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(ctxid_idx);
+
+static ssize_t ctxid_val_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	val = drvdata->ctxid_val[drvdata->ctxid_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t ctxid_val_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->ctxid_val[drvdata->ctxid_idx] = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(ctxid_val);
+
+static ssize_t ctxid_mask_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->ctxid_mask;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t ctxid_mask_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->ctxid_mask = val;
+	return size;
+}
+static DEVICE_ATTR_RW(ctxid_mask);
+
+static ssize_t sync_freq_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->sync_freq;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t sync_freq_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->sync_freq = val & ETM_SYNC_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(sync_freq);
+
+static ssize_t timestamp_event_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->timestamp_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t timestamp_event_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->timestamp_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(timestamp_event);
+
+static ssize_t status_show(struct device *dev,
+			   struct device_attribute *attr, char *buf)
+{
+	int ret;
+	unsigned long flags;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+
+	CS_UNLOCK(drvdata->base);
+	ret = sprintf(buf,
+		      "ETMCCR: 0x%08x\n"
+		      "ETMCCER: 0x%08x\n"
+		      "ETMSCR: 0x%08x\n"
+		      "ETMIDR: 0x%08x\n"
+		      "ETMCR: 0x%08x\n"
+		      "ETMTRACEIDR: 0x%08x\n"
+		      "Enable event: 0x%08x\n"
+		      "Enable start/stop: 0x%08x\n"
+		      "Enable control: CR1 0x%08x CR2 0x%08x\n"
+		      "CPU affinity: %d\n",
+		      drvdata->etmccr, drvdata->etmccer,
+		      etm_readl(drvdata, ETMSCR), etm_readl(drvdata, ETMIDR),
+		      etm_readl(drvdata, ETMCR), etm_trace_id_simple(drvdata),
+		      etm_readl(drvdata, ETMTEEVR),
+		      etm_readl(drvdata, ETMTSSCR),
+		      etm_readl(drvdata, ETMTECR1),
+		      etm_readl(drvdata, ETMTECR2),
+		      drvdata->cpu);
+	CS_LOCK(drvdata->base);
+
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	clk_disable_unprepare(drvdata->clk);
+
+	return ret;
+}
+static DEVICE_ATTR_RO(status);
+
+static ssize_t traceid_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	int ret;
+	unsigned long val, flags;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	if (!drvdata->enable) {
+		val = drvdata->traceid;
+		goto out;
+	}
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	CS_UNLOCK(drvdata->base);
+
+	val = (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK);
+
+	CS_LOCK(drvdata->base);
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	clk_disable_unprepare(drvdata->clk);
+out:
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t traceid_store(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->traceid = val & ETM_TRACEID_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(traceid);
+
+static struct attribute *coresight_etm_attrs[] = {
+	&dev_attr_nr_addr_cmp.attr,
+	&dev_attr_nr_cntr.attr,
+	&dev_attr_nr_ctxid_cmp.attr,
+	&dev_attr_etmsr.attr,
+	&dev_attr_reset.attr,
+	&dev_attr_mode.attr,
+	&dev_attr_trigger_event.attr,
+	&dev_attr_enable_event.attr,
+	&dev_attr_fifofull_level.attr,
+	&dev_attr_addr_idx.attr,
+	&dev_attr_addr_single.attr,
+	&dev_attr_addr_range.attr,
+	&dev_attr_addr_start.attr,
+	&dev_attr_addr_stop.attr,
+	&dev_attr_addr_acctype.attr,
+	&dev_attr_cntr_idx.attr,
+	&dev_attr_cntr_rld_val.attr,
+	&dev_attr_cntr_event.attr,
+	&dev_attr_cntr_rld_event.attr,
+	&dev_attr_cntr_val.attr,
+	&dev_attr_seq_12_event.attr,
+	&dev_attr_seq_21_event.attr,
+	&dev_attr_seq_23_event.attr,
+	&dev_attr_seq_31_event.attr,
+	&dev_attr_seq_32_event.attr,
+	&dev_attr_seq_13_event.attr,
+	&dev_attr_seq_curr_state.attr,
+	&dev_attr_ctxid_idx.attr,
+	&dev_attr_ctxid_val.attr,
+	&dev_attr_ctxid_mask.attr,
+	&dev_attr_sync_freq.attr,
+	&dev_attr_timestamp_event.attr,
+	&dev_attr_status.attr,
+	&dev_attr_traceid.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etm);
+
+static int etm_cpu_callback(struct notifier_block *nfb, unsigned long action,
+			    void *hcpu)
+{
+	unsigned int cpu = (unsigned long)hcpu;
+
+	if (!etmdrvdata[cpu])
+		goto out;
+
+	switch (action & (~CPU_TASKS_FROZEN)) {
+	case CPU_STARTING:
+		spin_lock(&etmdrvdata[cpu]->spinlock);
+		if (!etmdrvdata[cpu]->os_unlock) {
+			etm_os_unlock(etmdrvdata[cpu]);
+			etmdrvdata[cpu]->os_unlock = true;
+		}
+
+		if (etmdrvdata[cpu]->enable)
+			etm_enable_hw(etmdrvdata[cpu]);
+		spin_unlock(&etmdrvdata[cpu]->spinlock);
+		break;
+
+	case CPU_ONLINE:
+		if (etmdrvdata[cpu]->boot_enable &&
+		    !etmdrvdata[cpu]->sticky_enable)
+			coresight_enable(etmdrvdata[cpu]->csdev);
+		break;
+
+	case CPU_DYING:
+		spin_lock(&etmdrvdata[cpu]->spinlock);
+		if (etmdrvdata[cpu]->enable)
+			etm_disable_hw(etmdrvdata[cpu]);
+		spin_unlock(&etmdrvdata[cpu]->spinlock);
+		break;
+	}
+out:
+	return NOTIFY_OK;
+}
+
+static struct notifier_block etm_cpu_notifier = {
+	.notifier_call = etm_cpu_callback,
+};
+
+static bool etm_arch_supported(u8 arch)
+{
+	switch (arch) {
+	case ETM_ARCH_V3_3:
+		break;
+	case ETM_ARCH_V3_5:
+		break;
+	case PFT_ARCH_V1_0:
+		break;
+	case PFT_ARCH_V1_1:
+		break;
+	default:
+		return false;
+	}
+	return true;
+}
+
+static void etm_init_arch_data(void *info)
+{
+	u32 etmidr;
+	u32 etmccr;
+	struct etm_drvdata *drvdata = info;
+
+	CS_UNLOCK(drvdata->base);
+
+	/* First dummy read */
+	(void)etm_readl(drvdata, ETMPDSR);
+	/* Provide power to ETM: ETMPDCR[3] == 1 */
+	etm_set_pwrup(drvdata);
+	/*
+	 * Clear power down bit since when this bit is set writes to
+	 * certain registers might be ignored.
+	 */
+	etm_clr_pwrdwn(drvdata);
+	/*
+	 * Set prog bit. It will be set from reset but this is included to
+	 * ensure it is set
+	 */
+	etm_set_prog(drvdata);
+
+	/* Find all capabilities */
+	etmidr = etm_readl(drvdata, ETMIDR);
+	drvdata->arch = BMVAL(etmidr, 4, 11);
+	drvdata->port_size = etm_readl(drvdata, ETMCR) & PORT_SIZE_MASK;
+
+	drvdata->etmccer = etm_readl(drvdata, ETMCCER);
+	etmccr = etm_readl(drvdata, ETMCCR);
+	drvdata->etmccr = etmccr;
+	drvdata->nr_addr_cmp = BMVAL(etmccr, 0, 3) * 2;
+	drvdata->nr_cntr = BMVAL(etmccr, 13, 15);
+	drvdata->nr_ext_inp = BMVAL(etmccr, 17, 19);
+	drvdata->nr_ext_out = BMVAL(etmccr, 20, 22);
+	drvdata->nr_ctxid_cmp = BMVAL(etmccr, 24, 25);
+
+	etm_set_pwrdwn(drvdata);
+	etm_clr_pwrup(drvdata);
+	CS_LOCK(drvdata->base);
+}
+
+static void etm_init_default_data(struct etm_drvdata *drvdata)
+{
+	/*
+	 * A trace ID of value 0 is invalid, so let's start at some
+	 * random value that fits in 7 bits and will be just as good.
+	 */
+	static int etm3x_traceid = 0x10;
+
+	u32 flags = (1 << 0 | /* instruction execute*/
+		     3 << 3 | /* ARM instruction */
+		     0 << 5 | /* No data value comparison */
+		     0 << 7 | /* No exact mach */
+		     0 << 8 | /* Ignore context ID */
+		     0 << 10); /* Security ignored */
+
+	/*
+	 * Initial configuration only - guarantees sources handled by
+	 * this driver have a unique ID at startup time but not between
+	 * all other types of sources.  For that we lean on the core
+	 * framework.
+	 */
+	drvdata->traceid = etm3x_traceid++;
+	drvdata->ctrl = (ETMCR_CYC_ACC | ETMCR_TIMESTAMP_EN);
+	drvdata->enable_ctrl1 = ETMTECR1_ADDR_COMP_1;
+	if (drvdata->nr_addr_cmp >= 2) {
+		drvdata->addr_val[0] = (u32) _stext;
+		drvdata->addr_val[1] = (u32) _etext;
+		drvdata->addr_acctype[0] = flags;
+		drvdata->addr_acctype[1] = flags;
+		drvdata->addr_type[0] = ETM_ADDR_TYPE_RANGE;
+		drvdata->addr_type[1] = ETM_ADDR_TYPE_RANGE;
+	}
+
+	etm_set_default(drvdata);
+}
+
+static int etm_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	int ret;
+	void __iomem *base;
+	struct device *dev = &adev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct etm_drvdata *drvdata;
+	struct resource *res = &adev->res;
+	struct coresight_desc *desc;
+	struct device_node *np = adev->dev.of_node;
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+
+		adev->dev.platform_data = pdata;
+		drvdata->use_cp14 = of_property_read_bool(np, "arm,cp14");
+	}
+
+	drvdata->dev = &adev->dev;
+	dev_set_drvdata(dev, drvdata);
+
+	/* Validity for the resource is already checked by the AMBA core */
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drvdata->base = base;
+
+	spin_lock_init(&drvdata->spinlock);
+
+	drvdata->clk = adev->pclk;
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	drvdata->cpu = pdata ? pdata->cpu : 0;
+
+	get_online_cpus();
+	etmdrvdata[drvdata->cpu] = drvdata;
+
+	if (!smp_call_function_single(drvdata->cpu, etm_os_unlock, drvdata, 1))
+		drvdata->os_unlock = true;
+
+	if (smp_call_function_single(drvdata->cpu,
+				     etm_init_arch_data,  drvdata, 1))
+		dev_err(dev, "ETM arch init failed\n");
+
+	if (!etm_count++)
+		register_hotcpu_notifier(&etm_cpu_notifier);
+
+	put_online_cpus();
+
+	if (etm_arch_supported(drvdata->arch) == false) {
+		ret = -EINVAL;
+		goto err_arch_supported;
+	}
+	etm_init_default_data(drvdata);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	desc->type = CORESIGHT_DEV_TYPE_SOURCE;
+	desc->subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_PROC;
+	desc->ops = &etm_cs_ops;
+	desc->pdata = pdata;
+	desc->dev = dev;
+	desc->groups = coresight_etm_groups;
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev)) {
+		ret = PTR_ERR(drvdata->csdev);
+		goto err_arch_supported;
+	}
+
+	dev_info(dev, "ETM initialized\n");
+
+	if (boot_enable) {
+		coresight_enable(drvdata->csdev);
+		drvdata->boot_enable = true;
+	}
+
+	return 0;
+
+err_arch_supported:
+	clk_disable_unprepare(drvdata->clk);
+	if (--etm_count == 0)
+		unregister_hotcpu_notifier(&etm_cpu_notifier);
+	return ret;
+}
+
+static int etm_remove(struct amba_device *adev)
+{
+	struct etm_drvdata *drvdata = amba_get_drvdata(adev);
+
+	coresight_unregister(drvdata->csdev);
+	if (--etm_count == 0)
+		unregister_hotcpu_notifier(&etm_cpu_notifier);
+
+	return 0;
+}
+
+static struct amba_id etm_ids[] = {
+	{	/* ETM 3.3 */
+		.id	= 0x0003b921,
+		.mask	= 0x0003ffff,
+	},
+	{	/* ETM 3.5 */
+		.id	= 0x0003b956,
+		.mask	= 0x0003ffff,
+	},
+	{	/* PTM 1.0 */
+		.id	= 0x0003b950,
+		.mask	= 0x0003ffff,
+	},
+	{	/* PTM 1.1 */
+		.id	= 0x0003b95f,
+		.mask	= 0x0003ffff,
+	},
+	{ 0, 0},
+};
+
+static struct amba_driver etm_driver = {
+	.drv = {
+		.name	= "coresight-etm3x",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= etm_probe,
+	.remove		= etm_remove,
+	.id_table	= etm_ids,
+};
+
+int __init etm_init(void)
+{
+	return amba_driver_register(&etm_driver);
+}
+module_init(etm_init);
+
+void __exit etm_exit(void)
+{
+	amba_driver_unregister(&etm_driver);
+}
+module_exit(etm_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Program Flow Trace driver");
diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c
new file mode 100644
index 00000000000..3db36f70b66
--- /dev/null
+++ b/drivers/hwtracing/coresight/coresight-funnel.c
@@ -0,0 +1,258 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+
+#include "coresight-priv.h"
+
+#define FUNNEL_FUNCTL		0x000
+#define FUNNEL_PRICTL		0x004
+
+#define FUNNEL_HOLDTIME_MASK	0xf00
+#define FUNNEL_HOLDTIME_SHFT	0x8
+#define FUNNEL_HOLDTIME		(0x7 << FUNNEL_HOLDTIME_SHFT)
+
+/**
+ * struct funnel_drvdata - specifics associated to a funnel component
+ * @base:	memory mapped base address for this component.
+ * @dev:	the device entity associated to this component.
+ * @csdev:	component vitals needed by the framework.
+ * @clk:	the clock this component is associated to.
+ * @priority:	port selection order.
+ */
+struct funnel_drvdata {
+	void __iomem		*base;
+	struct device		*dev;
+	struct coresight_device	*csdev;
+	struct clk		*clk;
+	unsigned long		priority;
+};
+
+static void funnel_enable_hw(struct funnel_drvdata *drvdata, int port)
+{
+	u32 functl;
+
+	CS_UNLOCK(drvdata->base);
+
+	functl = readl_relaxed(drvdata->base + FUNNEL_FUNCTL);
+	functl &= ~FUNNEL_HOLDTIME_MASK;
+	functl |= FUNNEL_HOLDTIME;
+	functl |= (1 << port);
+	writel_relaxed(functl, drvdata->base + FUNNEL_FUNCTL);
+	writel_relaxed(drvdata->priority, drvdata->base + FUNNEL_PRICTL);
+
+	CS_LOCK(drvdata->base);
+}
+
+static int funnel_enable(struct coresight_device *csdev, int inport,
+			 int outport)
+{
+	struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	int ret;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	funnel_enable_hw(drvdata, inport);
+
+	dev_info(drvdata->dev, "FUNNEL inport %d enabled\n", inport);
+	return 0;
+}
+
+static void funnel_disable_hw(struct funnel_drvdata *drvdata, int inport)
+{
+	u32 functl;
+
+	CS_UNLOCK(drvdata->base);
+
+	functl = readl_relaxed(drvdata->base + FUNNEL_FUNCTL);
+	functl &= ~(1 << inport);
+	writel_relaxed(functl, drvdata->base + FUNNEL_FUNCTL);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void funnel_disable(struct coresight_device *csdev, int inport,
+			   int outport)
+{
+	struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	funnel_disable_hw(drvdata, inport);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	dev_info(drvdata->dev, "FUNNEL inport %d disabled\n", inport);
+}
+
+static const struct coresight_ops_link funnel_link_ops = {
+	.enable		= funnel_enable,
+	.disable	= funnel_disable,
+};
+
+static const struct coresight_ops funnel_cs_ops = {
+	.link_ops	= &funnel_link_ops,
+};
+
+static ssize_t priority_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	struct funnel_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val = drvdata->priority;
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t priority_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct funnel_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->priority = val;
+	return size;
+}
+static DEVICE_ATTR_RW(priority);
+
+static u32 get_funnel_ctrl_hw(struct funnel_drvdata *drvdata)
+{
+	u32 functl;
+
+	CS_UNLOCK(drvdata->base);
+	functl = readl_relaxed(drvdata->base + FUNNEL_FUNCTL);
+	CS_LOCK(drvdata->base);
+
+	return functl;
+}
+
+static ssize_t funnel_ctrl_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	int ret;
+	u32 val;
+	struct funnel_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	val = get_funnel_ctrl_hw(drvdata);
+	clk_disable_unprepare(drvdata->clk);
+
+	return sprintf(buf, "%#x\n", val);
+}
+static DEVICE_ATTR_RO(funnel_ctrl);
+
+static struct attribute *coresight_funnel_attrs[] = {
+	&dev_attr_funnel_ctrl.attr,
+	&dev_attr_priority.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_funnel);
+
+static int funnel_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	void __iomem *base;
+	struct device *dev = &adev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct funnel_drvdata *drvdata;
+	struct resource *res = &adev->res;
+	struct coresight_desc *desc;
+	struct device_node *np = adev->dev.of_node;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+		adev->dev.platform_data = pdata;
+	}
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->dev = &adev->dev;
+	dev_set_drvdata(dev, drvdata);
+
+	/* Validity for the resource is already checked by the AMBA core */
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drvdata->base = base;
+
+	drvdata->clk = adev->pclk;
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	desc->type = CORESIGHT_DEV_TYPE_LINK;
+	desc->subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_MERG;
+	desc->ops = &funnel_cs_ops;
+	desc->pdata = pdata;
+	desc->dev = dev;
+	desc->groups = coresight_funnel_groups;
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev))
+		return PTR_ERR(drvdata->csdev);
+
+	dev_info(dev, "FUNNEL initialized\n");
+	return 0;
+}
+
+static int funnel_remove(struct amba_device *adev)
+{
+	struct funnel_drvdata *drvdata = amba_get_drvdata(adev);
+
+	coresight_unregister(drvdata->csdev);
+	return 0;
+}
+
+static struct amba_id funnel_ids[] = {
+	{
+		.id     = 0x0003b908,
+		.mask   = 0x0003ffff,
+	},
+	{ 0, 0},
+};
+
+static struct amba_driver funnel_driver = {
+	.drv = {
+		.name	= "coresight-funnel",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= funnel_probe,
+	.remove		= funnel_remove,
+	.id_table	= funnel_ids,
+};
+
+module_amba_driver(funnel_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Funnel driver");
diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h
new file mode 100644
index 00000000000..62fcd98cc7c
--- /dev/null
+++ b/drivers/hwtracing/coresight/coresight-priv.h
@@ -0,0 +1,63 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CORESIGHT_PRIV_H
+#define _CORESIGHT_PRIV_H
+
+#include <linux/bitops.h>
+#include <linux/io.h>
+#include <linux/coresight.h>
+
+/*
+ * Coresight management registers (0xf00-0xfcc)
+ * 0xfa0 - 0xfa4: Management	registers in PFTv1.0
+ *		  Trace		registers in PFTv1.1
+ */
+#define CORESIGHT_ITCTRL	0xf00
+#define CORESIGHT_CLAIMSET	0xfa0
+#define CORESIGHT_CLAIMCLR	0xfa4
+#define CORESIGHT_LAR		0xfb0
+#define CORESIGHT_LSR		0xfb4
+#define CORESIGHT_AUTHSTATUS	0xfb8
+#define CORESIGHT_DEVID		0xfc8
+#define CORESIGHT_DEVTYPE	0xfcc
+
+#define TIMEOUT_US		100
+#define BMVAL(val, lsb, msb)	((val & GENMASK(msb, lsb)) >> lsb)
+
+static inline void CS_LOCK(void __iomem *addr)
+{
+	do {
+		/* Wait for things to settle */
+		mb();
+		writel_relaxed(0x0, addr + CORESIGHT_LAR);
+	} while (0);
+}
+
+static inline void CS_UNLOCK(void __iomem *addr)
+{
+	do {
+		writel_relaxed(CORESIGHT_UNLOCK, addr + CORESIGHT_LAR);
+		/* Make sure everyone has seen this */
+		mb();
+	} while (0);
+}
+
+#ifdef CONFIG_CORESIGHT_SOURCE_ETM3X
+extern int etm_readl_cp14(u32 off, unsigned int *val);
+extern int etm_writel_cp14(u32 off, u32 val);
+#else
+static inline int etm_readl_cp14(u32 off, unsigned int *val) { return 0; }
+static inline int etm_writel_cp14(u32 off, u32 val) { return 0; }
+#endif
+
+#endif
diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c
new file mode 100644
index 00000000000..cdf05537d57
--- /dev/null
+++ b/drivers/hwtracing/coresight/coresight-replicator.c
@@ -0,0 +1,137 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/coresight.h>
+
+#include "coresight-priv.h"
+
+/**
+ * struct replicator_drvdata - specifics associated to a replicator component
+ * @dev:	the device entity associated with this component
+ * @csdev:	component vitals needed by the framework
+ */
+struct replicator_drvdata {
+	struct device		*dev;
+	struct coresight_device	*csdev;
+};
+
+static int replicator_enable(struct coresight_device *csdev, int inport,
+			     int outport)
+{
+	struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	dev_info(drvdata->dev, "REPLICATOR enabled\n");
+	return 0;
+}
+
+static void replicator_disable(struct coresight_device *csdev, int inport,
+			       int outport)
+{
+	struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	dev_info(drvdata->dev, "REPLICATOR disabled\n");
+}
+
+static const struct coresight_ops_link replicator_link_ops = {
+	.enable		= replicator_enable,
+	.disable	= replicator_disable,
+};
+
+static const struct coresight_ops replicator_cs_ops = {
+	.link_ops	= &replicator_link_ops,
+};
+
+static int replicator_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct replicator_drvdata *drvdata;
+	struct coresight_desc *desc;
+	struct device_node *np = pdev->dev.of_node;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+		pdev->dev.platform_data = pdata;
+	}
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->dev = &pdev->dev;
+	platform_set_drvdata(pdev, drvdata);
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	desc->type = CORESIGHT_DEV_TYPE_LINK;
+	desc->subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_SPLIT;
+	desc->ops = &replicator_cs_ops;
+	desc->pdata = pdev->dev.platform_data;
+	desc->dev = &pdev->dev;
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev))
+		return PTR_ERR(drvdata->csdev);
+
+	dev_info(dev, "REPLICATOR initialized\n");
+	return 0;
+}
+
+static int replicator_remove(struct platform_device *pdev)
+{
+	struct replicator_drvdata *drvdata = platform_get_drvdata(pdev);
+
+	coresight_unregister(drvdata->csdev);
+	return 0;
+}
+
+static struct of_device_id replicator_match[] = {
+	{.compatible = "arm,coresight-replicator"},
+	{}
+};
+
+static struct platform_driver replicator_driver = {
+	.probe          = replicator_probe,
+	.remove         = replicator_remove,
+	.driver         = {
+		.name   = "coresight-replicator",
+		.of_match_table = replicator_match,
+	},
+};
+
+static int __init replicator_init(void)
+{
+	return platform_driver_register(&replicator_driver);
+}
+module_init(replicator_init);
+
+static void __exit replicator_exit(void)
+{
+	platform_driver_unregister(&replicator_driver);
+}
+module_exit(replicator_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Replicator driver");
diff --git a/drivers/hwtracing/coresight/coresight-tmc.c b/drivers/hwtracing/coresight/coresight-tmc.c
new file mode 100644
index 00000000000..7147f3dd363
--- /dev/null
+++ b/drivers/hwtracing/coresight/coresight-tmc.c
@@ -0,0 +1,822 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+#include <linux/spinlock.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+
+#include "coresight-priv.h"
+
+#define TMC_RSZ			0x004
+#define TMC_STS			0x00c
+#define TMC_RRD			0x010
+#define TMC_RRP			0x014
+#define TMC_RWP			0x018
+#define TMC_TRG			0x01c
+#define TMC_CTL			0x020
+#define TMC_RWD			0x024
+#define TMC_MODE		0x028
+#define TMC_LBUFLEVEL		0x02c
+#define TMC_CBUFLEVEL		0x030
+#define TMC_BUFWM		0x034
+#define TMC_RRPHI		0x038
+#define TMC_RWPHI		0x03c
+#define TMC_AXICTL		0x110
+#define TMC_DBALO		0x118
+#define TMC_DBAHI		0x11c
+#define TMC_FFSR		0x300
+#define TMC_FFCR		0x304
+#define TMC_PSCR		0x308
+#define TMC_ITMISCOP0		0xee0
+#define TMC_ITTRFLIN		0xee8
+#define TMC_ITATBDATA0		0xeec
+#define TMC_ITATBCTR2		0xef0
+#define TMC_ITATBCTR1		0xef4
+#define TMC_ITATBCTR0		0xef8
+
+/* register description */
+/* TMC_CTL - 0x020 */
+#define TMC_CTL_CAPT_EN		BIT(0)
+/* TMC_STS - 0x00C */
+#define TMC_STS_TRIGGERED	BIT(1)
+/* TMC_AXICTL - 0x110 */
+#define TMC_AXICTL_PROT_CTL_B0	BIT(0)
+#define TMC_AXICTL_PROT_CTL_B1	BIT(1)
+#define TMC_AXICTL_SCT_GAT_MODE	BIT(7)
+#define TMC_AXICTL_WR_BURST_LEN 0xF00
+/* TMC_FFCR - 0x304 */
+#define TMC_FFCR_EN_FMT		BIT(0)
+#define TMC_FFCR_EN_TI		BIT(1)
+#define TMC_FFCR_FON_FLIN	BIT(4)
+#define TMC_FFCR_FON_TRIG_EVT	BIT(5)
+#define TMC_FFCR_FLUSHMAN	BIT(6)
+#define TMC_FFCR_TRIGON_TRIGIN	BIT(8)
+#define TMC_FFCR_STOP_ON_FLUSH	BIT(12)
+
+#define TMC_STS_TRIGGERED_BIT	2
+#define TMC_FFCR_FLUSHMAN_BIT	6
+
+enum tmc_config_type {
+	TMC_CONFIG_TYPE_ETB,
+	TMC_CONFIG_TYPE_ETR,
+	TMC_CONFIG_TYPE_ETF,
+};
+
+enum tmc_mode {
+	TMC_MODE_CIRCULAR_BUFFER,
+	TMC_MODE_SOFTWARE_FIFO,
+	TMC_MODE_HARDWARE_FIFO,
+};
+
+enum tmc_mem_intf_width {
+	TMC_MEM_INTF_WIDTH_32BITS	= 0x2,
+	TMC_MEM_INTF_WIDTH_64BITS	= 0x3,
+	TMC_MEM_INTF_WIDTH_128BITS	= 0x4,
+	TMC_MEM_INTF_WIDTH_256BITS	= 0x5,
+};
+
+/**
+ * struct tmc_drvdata - specifics associated to an TMC component
+ * @base:	memory mapped base address for this component.
+ * @dev:	the device entity associated to this component.
+ * @csdev:	component vitals needed by the framework.
+ * @miscdev:	specifics to handle "/dev/xyz.tmc" entry.
+ * @clk:	the clock this component is associated to.
+ * @spinlock:	only one at a time pls.
+ * @read_count:	manages preparation of buffer for reading.
+ * @buf:	area of memory where trace data get sent.
+ * @paddr:	DMA start location in RAM.
+ * @vaddr:	virtual representation of @paddr.
+ * @size:	@buf size.
+ * @enable:	this TMC is being used.
+ * @config_type: TMC variant, must be of type @tmc_config_type.
+ * @trigger_cntr: amount of words to store after a trigger.
+ */
+struct tmc_drvdata {
+	void __iomem		*base;
+	struct device		*dev;
+	struct coresight_device	*csdev;
+	struct miscdevice	miscdev;
+	struct clk		*clk;
+	spinlock_t		spinlock;
+	int			read_count;
+	bool			reading;
+	char			*buf;
+	dma_addr_t		paddr;
+	void __iomem		*vaddr;
+	u32			size;
+	bool			enable;
+	enum tmc_config_type	config_type;
+	u32			trigger_cntr;
+};
+
+static void tmc_wait_for_ready(struct tmc_drvdata *drvdata)
+{
+	/* Ensure formatter, unformatter and hardware fifo are empty */
+	if (coresight_timeout(drvdata->base,
+			      TMC_STS, TMC_STS_TRIGGERED_BIT, 1)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n",
+			TMC_STS);
+	}
+}
+
+static void tmc_flush_and_stop(struct tmc_drvdata *drvdata)
+{
+	u32 ffcr;
+
+	ffcr = readl_relaxed(drvdata->base + TMC_FFCR);
+	ffcr |= TMC_FFCR_STOP_ON_FLUSH;
+	writel_relaxed(ffcr, drvdata->base + TMC_FFCR);
+	ffcr |= TMC_FFCR_FLUSHMAN;
+	writel_relaxed(ffcr, drvdata->base + TMC_FFCR);
+	/* Ensure flush completes */
+	if (coresight_timeout(drvdata->base,
+			      TMC_FFCR, TMC_FFCR_FLUSHMAN_BIT, 0)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n",
+			TMC_FFCR);
+	}
+
+	tmc_wait_for_ready(drvdata);
+}
+
+static void tmc_enable_hw(struct tmc_drvdata *drvdata)
+{
+	writel_relaxed(TMC_CTL_CAPT_EN, drvdata->base + TMC_CTL);
+}
+
+static void tmc_disable_hw(struct tmc_drvdata *drvdata)
+{
+	writel_relaxed(0x0, drvdata->base + TMC_CTL);
+}
+
+static void tmc_etb_enable_hw(struct tmc_drvdata *drvdata)
+{
+	/* Zero out the memory to help with debug */
+	memset(drvdata->buf, 0, drvdata->size);
+
+	CS_UNLOCK(drvdata->base);
+
+	writel_relaxed(TMC_MODE_CIRCULAR_BUFFER, drvdata->base + TMC_MODE);
+	writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI |
+		       TMC_FFCR_FON_FLIN | TMC_FFCR_FON_TRIG_EVT |
+		       TMC_FFCR_TRIGON_TRIGIN,
+		       drvdata->base + TMC_FFCR);
+
+	writel_relaxed(drvdata->trigger_cntr, drvdata->base + TMC_TRG);
+	tmc_enable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tmc_etr_enable_hw(struct tmc_drvdata *drvdata)
+{
+	u32 axictl;
+
+	/* Zero out the memory to help with debug */
+	memset(drvdata->vaddr, 0, drvdata->size);
+
+	CS_UNLOCK(drvdata->base);
+
+	writel_relaxed(drvdata->size / 4, drvdata->base + TMC_RSZ);
+	writel_relaxed(TMC_MODE_CIRCULAR_BUFFER, drvdata->base + TMC_MODE);
+
+	axictl = readl_relaxed(drvdata->base + TMC_AXICTL);
+	axictl |= TMC_AXICTL_WR_BURST_LEN;
+	writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
+	axictl &= ~TMC_AXICTL_SCT_GAT_MODE;
+	writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
+	axictl = (axictl &
+		  ~(TMC_AXICTL_PROT_CTL_B0 | TMC_AXICTL_PROT_CTL_B1)) |
+		  TMC_AXICTL_PROT_CTL_B1;
+	writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
+
+	writel_relaxed(drvdata->paddr, drvdata->base + TMC_DBALO);
+	writel_relaxed(0x0, drvdata->base + TMC_DBAHI);
+	writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI |
+		       TMC_FFCR_FON_FLIN | TMC_FFCR_FON_TRIG_EVT |
+		       TMC_FFCR_TRIGON_TRIGIN,
+		       drvdata->base + TMC_FFCR);
+	writel_relaxed(drvdata->trigger_cntr, drvdata->base + TMC_TRG);
+	tmc_enable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tmc_etf_enable_hw(struct tmc_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	writel_relaxed(TMC_MODE_HARDWARE_FIFO, drvdata->base + TMC_MODE);
+	writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI,
+		       drvdata->base + TMC_FFCR);
+	writel_relaxed(0x0, drvdata->base + TMC_BUFWM);
+	tmc_enable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static int tmc_enable(struct tmc_drvdata *drvdata, enum tmc_mode mode)
+{
+	int ret;
+	unsigned long flags;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (drvdata->reading) {
+		spin_unlock_irqrestore(&drvdata->spinlock, flags);
+		clk_disable_unprepare(drvdata->clk);
+		return -EBUSY;
+	}
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+		tmc_etb_enable_hw(drvdata);
+	} else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		tmc_etr_enable_hw(drvdata);
+	} else {
+		if (mode == TMC_MODE_CIRCULAR_BUFFER)
+			tmc_etb_enable_hw(drvdata);
+		else
+			tmc_etf_enable_hw(drvdata);
+	}
+	drvdata->enable = true;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	dev_info(drvdata->dev, "TMC enabled\n");
+	return 0;
+}
+
+static int tmc_enable_sink(struct coresight_device *csdev)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	return tmc_enable(drvdata, TMC_MODE_CIRCULAR_BUFFER);
+}
+
+static int tmc_enable_link(struct coresight_device *csdev, int inport,
+			   int outport)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	return tmc_enable(drvdata, TMC_MODE_HARDWARE_FIFO);
+}
+
+static void tmc_etb_dump_hw(struct tmc_drvdata *drvdata)
+{
+	enum tmc_mem_intf_width memwidth;
+	u8 memwords;
+	char *bufp;
+	u32 read_data;
+	int i;
+
+	memwidth = BMVAL(readl_relaxed(drvdata->base + CORESIGHT_DEVID), 8, 10);
+	if (memwidth == TMC_MEM_INTF_WIDTH_32BITS)
+		memwords = 1;
+	else if (memwidth == TMC_MEM_INTF_WIDTH_64BITS)
+		memwords = 2;
+	else if (memwidth == TMC_MEM_INTF_WIDTH_128BITS)
+		memwords = 4;
+	else
+		memwords = 8;
+
+	bufp = drvdata->buf;
+	while (1) {
+		for (i = 0; i < memwords; i++) {
+			read_data = readl_relaxed(drvdata->base + TMC_RRD);
+			if (read_data == 0xFFFFFFFF)
+				return;
+			memcpy(bufp, &read_data, 4);
+			bufp += 4;
+		}
+	}
+}
+
+static void tmc_etb_disable_hw(struct tmc_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	tmc_flush_and_stop(drvdata);
+	tmc_etb_dump_hw(drvdata);
+	tmc_disable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tmc_etr_dump_hw(struct tmc_drvdata *drvdata)
+{
+	u32 rwp, val;
+
+	rwp = readl_relaxed(drvdata->base + TMC_RWP);
+	val = readl_relaxed(drvdata->base + TMC_STS);
+
+	/* How much memory do we still have */
+	if (val & BIT(0))
+		drvdata->buf = drvdata->vaddr + rwp - drvdata->paddr;
+	else
+		drvdata->buf = drvdata->vaddr;
+}
+
+static void tmc_etr_disable_hw(struct tmc_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	tmc_flush_and_stop(drvdata);
+	tmc_etr_dump_hw(drvdata);
+	tmc_disable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tmc_etf_disable_hw(struct tmc_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	tmc_flush_and_stop(drvdata);
+	tmc_disable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tmc_disable(struct tmc_drvdata *drvdata, enum tmc_mode mode)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (drvdata->reading)
+		goto out;
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+		tmc_etb_disable_hw(drvdata);
+	} else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		tmc_etr_disable_hw(drvdata);
+	} else {
+		if (mode == TMC_MODE_CIRCULAR_BUFFER)
+			tmc_etb_disable_hw(drvdata);
+		else
+			tmc_etf_disable_hw(drvdata);
+	}
+out:
+	drvdata->enable = false;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	dev_info(drvdata->dev, "TMC disabled\n");
+}
+
+static void tmc_disable_sink(struct coresight_device *csdev)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	tmc_disable(drvdata, TMC_MODE_CIRCULAR_BUFFER);
+}
+
+static void tmc_disable_link(struct coresight_device *csdev, int inport,
+			     int outport)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	tmc_disable(drvdata, TMC_MODE_HARDWARE_FIFO);
+}
+
+static const struct coresight_ops_sink tmc_sink_ops = {
+	.enable		= tmc_enable_sink,
+	.disable	= tmc_disable_sink,
+};
+
+static const struct coresight_ops_link tmc_link_ops = {
+	.enable		= tmc_enable_link,
+	.disable	= tmc_disable_link,
+};
+
+static const struct coresight_ops tmc_etb_cs_ops = {
+	.sink_ops	= &tmc_sink_ops,
+};
+
+static const struct coresight_ops tmc_etr_cs_ops = {
+	.sink_ops	= &tmc_sink_ops,
+};
+
+static const struct coresight_ops tmc_etf_cs_ops = {
+	.sink_ops	= &tmc_sink_ops,
+	.link_ops	= &tmc_link_ops,
+};
+
+static int tmc_read_prepare(struct tmc_drvdata *drvdata)
+{
+	int ret;
+	unsigned long flags;
+	enum tmc_mode mode;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (!drvdata->enable)
+		goto out;
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+		tmc_etb_disable_hw(drvdata);
+	} else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		tmc_etr_disable_hw(drvdata);
+	} else {
+		mode = readl_relaxed(drvdata->base + TMC_MODE);
+		if (mode == TMC_MODE_CIRCULAR_BUFFER) {
+			tmc_etb_disable_hw(drvdata);
+		} else {
+			ret = -ENODEV;
+			goto err;
+		}
+	}
+out:
+	drvdata->reading = true;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	dev_info(drvdata->dev, "TMC read start\n");
+	return 0;
+err:
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	return ret;
+}
+
+static void tmc_read_unprepare(struct tmc_drvdata *drvdata)
+{
+	unsigned long flags;
+	enum tmc_mode mode;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (!drvdata->enable)
+		goto out;
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+		tmc_etb_enable_hw(drvdata);
+	} else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		tmc_etr_enable_hw(drvdata);
+	} else {
+		mode = readl_relaxed(drvdata->base + TMC_MODE);
+		if (mode == TMC_MODE_CIRCULAR_BUFFER)
+			tmc_etb_enable_hw(drvdata);
+	}
+out:
+	drvdata->reading = false;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	dev_info(drvdata->dev, "TMC read end\n");
+}
+
+static int tmc_open(struct inode *inode, struct file *file)
+{
+	struct tmc_drvdata *drvdata = container_of(file->private_data,
+						   struct tmc_drvdata, miscdev);
+	int ret = 0;
+
+	if (drvdata->read_count++)
+		goto out;
+
+	ret = tmc_read_prepare(drvdata);
+	if (ret)
+		return ret;
+out:
+	nonseekable_open(inode, file);
+
+	dev_dbg(drvdata->dev, "%s: successfully opened\n", __func__);
+	return 0;
+}
+
+static ssize_t tmc_read(struct file *file, char __user *data, size_t len,
+			loff_t *ppos)
+{
+	struct tmc_drvdata *drvdata = container_of(file->private_data,
+						   struct tmc_drvdata, miscdev);
+	char *bufp = drvdata->buf + *ppos;
+
+	if (*ppos + len > drvdata->size)
+		len = drvdata->size - *ppos;
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		if (bufp == (char *)(drvdata->vaddr + drvdata->size))
+			bufp = drvdata->vaddr;
+		else if (bufp > (char *)(drvdata->vaddr + drvdata->size))
+			bufp -= drvdata->size;
+		if ((bufp + len) > (char *)(drvdata->vaddr + drvdata->size))
+			len = (char *)(drvdata->vaddr + drvdata->size) - bufp;
+	}
+
+	if (copy_to_user(data, bufp, len)) {
+		dev_dbg(drvdata->dev, "%s: copy_to_user failed\n", __func__);
+		return -EFAULT;
+	}
+
+	*ppos += len;
+
+	dev_dbg(drvdata->dev, "%s: %zu bytes copied, %d bytes left\n",
+		__func__, len, (int)(drvdata->size - *ppos));
+	return len;
+}
+
+static int tmc_release(struct inode *inode, struct file *file)
+{
+	struct tmc_drvdata *drvdata = container_of(file->private_data,
+						   struct tmc_drvdata, miscdev);
+
+	if (--drvdata->read_count) {
+		if (drvdata->read_count < 0) {
+			dev_err(drvdata->dev, "mismatched close\n");
+			drvdata->read_count = 0;
+		}
+		goto out;
+	}
+
+	tmc_read_unprepare(drvdata);
+out:
+	dev_dbg(drvdata->dev, "%s: released\n", __func__);
+	return 0;
+}
+
+static const struct file_operations tmc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= tmc_open,
+	.read		= tmc_read,
+	.release	= tmc_release,
+	.llseek		= no_llseek,
+};
+
+static ssize_t status_show(struct device *dev,
+			   struct device_attribute *attr, char *buf)
+{
+	int ret;
+	unsigned long flags;
+	u32 tmc_rsz, tmc_sts, tmc_rrp, tmc_rwp, tmc_trg;
+	u32 tmc_ctl, tmc_ffsr, tmc_ffcr, tmc_mode, tmc_pscr;
+	u32 devid;
+	struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		goto out;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	CS_UNLOCK(drvdata->base);
+
+	tmc_rsz = readl_relaxed(drvdata->base + TMC_RSZ);
+	tmc_sts = readl_relaxed(drvdata->base + TMC_STS);
+	tmc_rrp = readl_relaxed(drvdata->base + TMC_RRP);
+	tmc_rwp = readl_relaxed(drvdata->base + TMC_RWP);
+	tmc_trg = readl_relaxed(drvdata->base + TMC_TRG);
+	tmc_ctl = readl_relaxed(drvdata->base + TMC_CTL);
+	tmc_ffsr = readl_relaxed(drvdata->base + TMC_FFSR);
+	tmc_ffcr = readl_relaxed(drvdata->base + TMC_FFCR);
+	tmc_mode = readl_relaxed(drvdata->base + TMC_MODE);
+	tmc_pscr = readl_relaxed(drvdata->base + TMC_PSCR);
+	devid = readl_relaxed(drvdata->base + CORESIGHT_DEVID);
+
+	CS_LOCK(drvdata->base);
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	return sprintf(buf,
+		       "Depth:\t\t0x%x\n"
+		       "Status:\t\t0x%x\n"
+		       "RAM read ptr:\t0x%x\n"
+		       "RAM wrt ptr:\t0x%x\n"
+		       "Trigger cnt:\t0x%x\n"
+		       "Control:\t0x%x\n"
+		       "Flush status:\t0x%x\n"
+		       "Flush ctrl:\t0x%x\n"
+		       "Mode:\t\t0x%x\n"
+		       "PSRC:\t\t0x%x\n"
+		       "DEVID:\t\t0x%x\n",
+			tmc_rsz, tmc_sts, tmc_rrp, tmc_rwp, tmc_trg,
+			tmc_ctl, tmc_ffsr, tmc_ffcr, tmc_mode, tmc_pscr, devid);
+out:
+	return -EINVAL;
+}
+static DEVICE_ATTR_RO(status);
+
+static ssize_t trigger_cntr_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val = drvdata->trigger_cntr;
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t trigger_cntr_store(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->trigger_cntr = val;
+	return size;
+}
+static DEVICE_ATTR_RW(trigger_cntr);
+
+static struct attribute *coresight_etb_attrs[] = {
+	&dev_attr_trigger_cntr.attr,
+	&dev_attr_status.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etb);
+
+static struct attribute *coresight_etr_attrs[] = {
+	&dev_attr_trigger_cntr.attr,
+	&dev_attr_status.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etr);
+
+static struct attribute *coresight_etf_attrs[] = {
+	&dev_attr_trigger_cntr.attr,
+	&dev_attr_status.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etf);
+
+static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	int ret = 0;
+	u32 devid;
+	void __iomem *base;
+	struct device *dev = &adev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct tmc_drvdata *drvdata;
+	struct resource *res = &adev->res;
+	struct coresight_desc *desc;
+	struct device_node *np = adev->dev.of_node;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+		adev->dev.platform_data = pdata;
+	}
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->dev = &adev->dev;
+	dev_set_drvdata(dev, drvdata);
+
+	/* Validity for the resource is already checked by the AMBA core */
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drvdata->base = base;
+
+	spin_lock_init(&drvdata->spinlock);
+
+	drvdata->clk = adev->pclk;
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	devid = readl_relaxed(drvdata->base + CORESIGHT_DEVID);
+	drvdata->config_type = BMVAL(devid, 6, 7);
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		if (np)
+			ret = of_property_read_u32(np,
+						   "arm,buffer-size",
+						   &drvdata->size);
+		if (ret)
+			drvdata->size = SZ_1M;
+	} else {
+		drvdata->size = readl_relaxed(drvdata->base + TMC_RSZ) * 4;
+	}
+
+	clk_disable_unprepare(drvdata->clk);
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		drvdata->vaddr = dma_alloc_coherent(dev, drvdata->size,
+						&drvdata->paddr, GFP_KERNEL);
+		if (!drvdata->vaddr)
+			return -ENOMEM;
+
+		memset(drvdata->vaddr, 0, drvdata->size);
+		drvdata->buf = drvdata->vaddr;
+	} else {
+		drvdata->buf = devm_kzalloc(dev, drvdata->size, GFP_KERNEL);
+		if (!drvdata->buf)
+			return -ENOMEM;
+	}
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc) {
+		ret = -ENOMEM;
+		goto err_devm_kzalloc;
+	}
+
+	desc->pdata = pdata;
+	desc->dev = dev;
+	desc->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+		desc->type = CORESIGHT_DEV_TYPE_SINK;
+		desc->ops = &tmc_etb_cs_ops;
+		desc->groups = coresight_etb_groups;
+	} else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		desc->type = CORESIGHT_DEV_TYPE_SINK;
+		desc->ops = &tmc_etr_cs_ops;
+		desc->groups = coresight_etr_groups;
+	} else {
+		desc->type = CORESIGHT_DEV_TYPE_LINKSINK;
+		desc->subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_FIFO;
+		desc->ops = &tmc_etf_cs_ops;
+		desc->groups = coresight_etf_groups;
+	}
+
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev)) {
+		ret = PTR_ERR(drvdata->csdev);
+		goto err_devm_kzalloc;
+	}
+
+	drvdata->miscdev.name = pdata->name;
+	drvdata->miscdev.minor = MISC_DYNAMIC_MINOR;
+	drvdata->miscdev.fops = &tmc_fops;
+	ret = misc_register(&drvdata->miscdev);
+	if (ret)
+		goto err_misc_register;
+
+	dev_info(dev, "TMC initialized\n");
+	return 0;
+
+err_misc_register:
+	coresight_unregister(drvdata->csdev);
+err_devm_kzalloc:
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR)
+		dma_free_coherent(dev, drvdata->size,
+				&drvdata->paddr, GFP_KERNEL);
+	return ret;
+}
+
+static int tmc_remove(struct amba_device *adev)
+{
+	struct tmc_drvdata *drvdata = amba_get_drvdata(adev);
+
+	misc_deregister(&drvdata->miscdev);
+	coresight_unregister(drvdata->csdev);
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR)
+		dma_free_coherent(drvdata->dev, drvdata->size,
+				  &drvdata->paddr, GFP_KERNEL);
+
+	return 0;
+}
+
+static struct amba_id tmc_ids[] = {
+	{
+		.id     = 0x0003b961,
+		.mask   = 0x0003ffff,
+	},
+	{ 0, 0},
+};
+
+static struct amba_driver tmc_driver = {
+	.drv = {
+		.name   = "coresight-tmc",
+		.owner  = THIS_MODULE,
+	},
+	.probe		= tmc_probe,
+	.remove		= tmc_remove,
+	.id_table	= tmc_ids,
+};
+
+module_amba_driver(tmc_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Trace Memory Controller driver");
diff --git a/drivers/hwtracing/coresight/coresight-tpiu.c b/drivers/hwtracing/coresight/coresight-tpiu.c
new file mode 100644
index 00000000000..3b33af2416b
--- /dev/null
+++ b/drivers/hwtracing/coresight/coresight-tpiu.c
@@ -0,0 +1,207 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+
+#include "coresight-priv.h"
+
+#define TPIU_SUPP_PORTSZ	0x000
+#define TPIU_CURR_PORTSZ	0x004
+#define TPIU_SUPP_TRIGMODES	0x100
+#define TPIU_TRIG_CNTRVAL	0x104
+#define TPIU_TRIG_MULT		0x108
+#define TPIU_SUPP_TESTPATM	0x200
+#define TPIU_CURR_TESTPATM	0x204
+#define TPIU_TEST_PATREPCNTR	0x208
+#define TPIU_FFSR		0x300
+#define TPIU_FFCR		0x304
+#define TPIU_FSYNC_CNTR		0x308
+#define TPIU_EXTCTL_INPORT	0x400
+#define TPIU_EXTCTL_OUTPORT	0x404
+#define TPIU_ITTRFLINACK	0xee4
+#define TPIU_ITTRFLIN		0xee8
+#define TPIU_ITATBDATA0		0xeec
+#define TPIU_ITATBCTR2		0xef0
+#define TPIU_ITATBCTR1		0xef4
+#define TPIU_ITATBCTR0		0xef8
+
+/** register definition **/
+/* FFCR - 0x304 */
+#define FFCR_FON_MAN		BIT(6)
+
+/**
+ * @base:	memory mapped base address for this component.
+ * @dev:	the device entity associated to this component.
+ * @csdev:	component vitals needed by the framework.
+ * @clk:	the clock this component is associated to.
+ */
+struct tpiu_drvdata {
+	void __iomem		*base;
+	struct device		*dev;
+	struct coresight_device	*csdev;
+	struct clk		*clk;
+};
+
+static void tpiu_enable_hw(struct tpiu_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	/* TODO: fill this up */
+
+	CS_LOCK(drvdata->base);
+}
+
+static int tpiu_enable(struct coresight_device *csdev)
+{
+	struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	int ret;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	tpiu_enable_hw(drvdata);
+
+	dev_info(drvdata->dev, "TPIU enabled\n");
+	return 0;
+}
+
+static void tpiu_disable_hw(struct tpiu_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	/* Clear formatter controle reg. */
+	writel_relaxed(0x0, drvdata->base + TPIU_FFCR);
+	/* Generate manual flush */
+	writel_relaxed(FFCR_FON_MAN, drvdata->base + TPIU_FFCR);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tpiu_disable(struct coresight_device *csdev)
+{
+	struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	tpiu_disable_hw(drvdata);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	dev_info(drvdata->dev, "TPIU disabled\n");
+}
+
+static const struct coresight_ops_sink tpiu_sink_ops = {
+	.enable		= tpiu_enable,
+	.disable	= tpiu_disable,
+};
+
+static const struct coresight_ops tpiu_cs_ops = {
+	.sink_ops	= &tpiu_sink_ops,
+};
+
+static int tpiu_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	int ret;
+	void __iomem *base;
+	struct device *dev = &adev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct tpiu_drvdata *drvdata;
+	struct resource *res = &adev->res;
+	struct coresight_desc *desc;
+	struct device_node *np = adev->dev.of_node;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+		adev->dev.platform_data = pdata;
+	}
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->dev = &adev->dev;
+	dev_set_drvdata(dev, drvdata);
+
+	/* Validity for the resource is already checked by the AMBA core */
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drvdata->base = base;
+
+	drvdata->clk = adev->pclk;
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	/* Disable tpiu to support older devices */
+	tpiu_disable_hw(drvdata);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	desc->type = CORESIGHT_DEV_TYPE_SINK;
+	desc->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_PORT;
+	desc->ops = &tpiu_cs_ops;
+	desc->pdata = pdata;
+	desc->dev = dev;
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev))
+		return PTR_ERR(drvdata->csdev);
+
+	dev_info(dev, "TPIU initialized\n");
+	return 0;
+}
+
+static int tpiu_remove(struct amba_device *adev)
+{
+	struct tpiu_drvdata *drvdata = amba_get_drvdata(adev);
+
+	coresight_unregister(drvdata->csdev);
+	return 0;
+}
+
+static struct amba_id tpiu_ids[] = {
+	{
+		.id	= 0x0003b912,
+		.mask	= 0x0003ffff,
+	},
+	{ 0, 0},
+};
+
+static struct amba_driver tpiu_driver = {
+	.drv = {
+		.name	= "coresight-tpiu",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= tpiu_probe,
+	.remove		= tpiu_remove,
+	.id_table	= tpiu_ids,
+};
+
+module_amba_driver(tpiu_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Trace Port Interface Unit driver");
diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c
new file mode 100644
index 00000000000..894531d315b
--- /dev/null
+++ b/drivers/hwtracing/coresight/coresight.c
@@ -0,0 +1,720 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/clk.h>
+#include <linux/coresight.h>
+#include <linux/of_platform.h>
+#include <linux/delay.h>
+
+#include "coresight-priv.h"
+
+static DEFINE_MUTEX(coresight_mutex);
+
+static int coresight_id_match(struct device *dev, void *data)
+{
+	int trace_id, i_trace_id;
+	struct coresight_device *csdev, *i_csdev;
+
+	csdev = data;
+	i_csdev = to_coresight_device(dev);
+
+	/*
+	 * No need to care about oneself and components that are not
+	 * sources or not enabled
+	 */
+	if (i_csdev == csdev || !i_csdev->enable ||
+	    i_csdev->type != CORESIGHT_DEV_TYPE_SOURCE)
+		return 0;
+
+	/* Get the source ID for both compoment */
+	trace_id = source_ops(csdev)->trace_id(csdev);
+	i_trace_id = source_ops(i_csdev)->trace_id(i_csdev);
+
+	/* All you need is one */
+	if (trace_id == i_trace_id)
+		return 1;
+
+	return 0;
+}
+
+static int coresight_source_is_unique(struct coresight_device *csdev)
+{
+	int trace_id = source_ops(csdev)->trace_id(csdev);
+
+	/* this shouldn't happen */
+	if (trace_id < 0)
+		return 0;
+
+	return !bus_for_each_dev(&coresight_bustype, NULL,
+				 csdev, coresight_id_match);
+}
+
+static int coresight_find_link_inport(struct coresight_device *csdev)
+{
+	int i;
+	struct coresight_device *parent;
+	struct coresight_connection *conn;
+
+	parent = container_of(csdev->path_link.next,
+			      struct coresight_device, path_link);
+
+	for (i = 0; i < parent->nr_outport; i++) {
+		conn = &parent->conns[i];
+		if (conn->child_dev == csdev)
+			return conn->child_port;
+	}
+
+	dev_err(&csdev->dev, "couldn't find inport, parent: %s, child: %s\n",
+		dev_name(&parent->dev), dev_name(&csdev->dev));
+
+	return 0;
+}
+
+static int coresight_find_link_outport(struct coresight_device *csdev)
+{
+	int i;
+	struct coresight_device *child;
+	struct coresight_connection *conn;
+
+	child = container_of(csdev->path_link.prev,
+			     struct coresight_device, path_link);
+
+	for (i = 0; i < csdev->nr_outport; i++) {
+		conn = &csdev->conns[i];
+		if (conn->child_dev == child)
+			return conn->outport;
+	}
+
+	dev_err(&csdev->dev, "couldn't find outport, parent: %s, child: %s\n",
+		dev_name(&csdev->dev), dev_name(&child->dev));
+
+	return 0;
+}
+
+static int coresight_enable_sink(struct coresight_device *csdev)
+{
+	int ret;
+
+	if (!csdev->enable) {
+		if (sink_ops(csdev)->enable) {
+			ret = sink_ops(csdev)->enable(csdev);
+			if (ret)
+				return ret;
+		}
+		csdev->enable = true;
+	}
+
+	atomic_inc(csdev->refcnt);
+
+	return 0;
+}
+
+static void coresight_disable_sink(struct coresight_device *csdev)
+{
+	if (atomic_dec_return(csdev->refcnt) == 0) {
+		if (sink_ops(csdev)->disable) {
+			sink_ops(csdev)->disable(csdev);
+			csdev->enable = false;
+		}
+	}
+}
+
+static int coresight_enable_link(struct coresight_device *csdev)
+{
+	int ret;
+	int link_subtype;
+	int refport, inport, outport;
+
+	inport = coresight_find_link_inport(csdev);
+	outport = coresight_find_link_outport(csdev);
+	link_subtype = csdev->subtype.link_subtype;
+
+	if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG)
+		refport = inport;
+	else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT)
+		refport = outport;
+	else
+		refport = 0;
+
+	if (atomic_inc_return(&csdev->refcnt[refport]) == 1) {
+		if (link_ops(csdev)->enable) {
+			ret = link_ops(csdev)->enable(csdev, inport, outport);
+			if (ret)
+				return ret;
+		}
+	}
+
+	csdev->enable = true;
+
+	return 0;
+}
+
+static void coresight_disable_link(struct coresight_device *csdev)
+{
+	int i, nr_conns;
+	int link_subtype;
+	int refport, inport, outport;
+
+	inport = coresight_find_link_inport(csdev);
+	outport = coresight_find_link_outport(csdev);
+	link_subtype = csdev->subtype.link_subtype;
+
+	if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG) {
+		refport = inport;
+		nr_conns = csdev->nr_inport;
+	} else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT) {
+		refport = outport;
+		nr_conns = csdev->nr_outport;
+	} else {
+		refport = 0;
+		nr_conns = 1;
+	}
+
+	if (atomic_dec_return(&csdev->refcnt[refport]) == 0) {
+		if (link_ops(csdev)->disable)
+			link_ops(csdev)->disable(csdev, inport, outport);
+	}
+
+	for (i = 0; i < nr_conns; i++)
+		if (atomic_read(&csdev->refcnt[i]) != 0)
+			return;
+
+	csdev->enable = false;
+}
+
+static int coresight_enable_source(struct coresight_device *csdev)
+{
+	int ret;
+
+	if (!coresight_source_is_unique(csdev)) {
+		dev_warn(&csdev->dev, "traceID %d not unique\n",
+			 source_ops(csdev)->trace_id(csdev));
+		return -EINVAL;
+	}
+
+	if (!csdev->enable) {
+		if (source_ops(csdev)->enable) {
+			ret = source_ops(csdev)->enable(csdev);
+			if (ret)
+				return ret;
+		}
+		csdev->enable = true;
+	}
+
+	atomic_inc(csdev->refcnt);
+
+	return 0;
+}
+
+static void coresight_disable_source(struct coresight_device *csdev)
+{
+	if (atomic_dec_return(csdev->refcnt) == 0) {
+		if (source_ops(csdev)->disable) {
+			source_ops(csdev)->disable(csdev);
+			csdev->enable = false;
+		}
+	}
+}
+
+static int coresight_enable_path(struct list_head *path)
+{
+	int ret = 0;
+	struct coresight_device *cd;
+
+	list_for_each_entry(cd, path, path_link) {
+		if (cd == list_first_entry(path, struct coresight_device,
+					   path_link)) {
+			ret = coresight_enable_sink(cd);
+		} else if (list_is_last(&cd->path_link, path)) {
+			/*
+			 * Don't enable the source just yet - this needs to
+			 * happen at the very end when all links and sink
+			 * along the path have been configured properly.
+			 */
+			;
+		} else {
+			ret = coresight_enable_link(cd);
+		}
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+err:
+	list_for_each_entry_continue_reverse(cd, path, path_link) {
+		if (cd == list_first_entry(path, struct coresight_device,
+					   path_link)) {
+			coresight_disable_sink(cd);
+		} else if (list_is_last(&cd->path_link, path)) {
+			;
+		} else {
+			coresight_disable_link(cd);
+		}
+	}
+
+	return ret;
+}
+
+static int coresight_disable_path(struct list_head *path)
+{
+	struct coresight_device *cd;
+
+	list_for_each_entry_reverse(cd, path, path_link) {
+		if (cd == list_first_entry(path, struct coresight_device,
+					   path_link)) {
+			coresight_disable_sink(cd);
+		} else if (list_is_last(&cd->path_link, path)) {
+			/*
+			 * The source has already been stopped, no need
+			 * to do it again here.
+			 */
+			;
+		} else {
+			coresight_disable_link(cd);
+		}
+	}
+
+	return 0;
+}
+
+static int coresight_build_paths(struct coresight_device *csdev,
+				 struct list_head *path,
+				 bool enable)
+{
+	int i, ret = -EINVAL;
+	struct coresight_connection *conn;
+
+	list_add(&csdev->path_link, path);
+
+	if ((csdev->type == CORESIGHT_DEV_TYPE_SINK ||
+	    csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) &&
+	    csdev->activated) {
+		if (enable)
+			ret = coresight_enable_path(path);
+		else
+			ret = coresight_disable_path(path);
+	} else {
+		for (i = 0; i < csdev->nr_outport; i++) {
+			conn = &csdev->conns[i];
+			if (coresight_build_paths(conn->child_dev,
+						    path, enable) == 0)
+				ret = 0;
+		}
+	}
+
+	if (list_first_entry(path, struct coresight_device, path_link) != csdev)
+		dev_err(&csdev->dev, "wrong device in %s\n", __func__);
+
+	list_del(&csdev->path_link);
+
+	return ret;
+}
+
+int coresight_enable(struct coresight_device *csdev)
+{
+	int ret = 0;
+	LIST_HEAD(path);
+
+	mutex_lock(&coresight_mutex);
+	if (csdev->type != CORESIGHT_DEV_TYPE_SOURCE) {
+		ret = -EINVAL;
+		dev_err(&csdev->dev, "wrong device type in %s\n", __func__);
+		goto out;
+	}
+	if (csdev->enable)
+		goto out;
+
+	if (coresight_build_paths(csdev, &path, true)) {
+		dev_err(&csdev->dev, "building path(s) failed\n");
+		goto out;
+	}
+
+	if (coresight_enable_source(csdev))
+		dev_err(&csdev->dev, "source enable failed\n");
+out:
+	mutex_unlock(&coresight_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(coresight_enable);
+
+void coresight_disable(struct coresight_device *csdev)
+{
+	LIST_HEAD(path);
+
+	mutex_lock(&coresight_mutex);
+	if (csdev->type != CORESIGHT_DEV_TYPE_SOURCE) {
+		dev_err(&csdev->dev, "wrong device type in %s\n", __func__);
+		goto out;
+	}
+	if (!csdev->enable)
+		goto out;
+
+	coresight_disable_source(csdev);
+	if (coresight_build_paths(csdev, &path, false))
+		dev_err(&csdev->dev, "releasing path(s) failed\n");
+
+out:
+	mutex_unlock(&coresight_mutex);
+}
+EXPORT_SYMBOL_GPL(coresight_disable);
+
+static ssize_t enable_sink_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n", (unsigned)csdev->activated);
+}
+
+static ssize_t enable_sink_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	ret = kstrtoul(buf, 10, &val);
+	if (ret)
+		return ret;
+
+	if (val)
+		csdev->activated = true;
+	else
+		csdev->activated = false;
+
+	return size;
+
+}
+static DEVICE_ATTR_RW(enable_sink);
+
+static ssize_t enable_source_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n", (unsigned)csdev->enable);
+}
+
+static ssize_t enable_source_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t size)
+{
+	int ret = 0;
+	unsigned long val;
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	ret = kstrtoul(buf, 10, &val);
+	if (ret)
+		return ret;
+
+	if (val) {
+		ret = coresight_enable(csdev);
+		if (ret)
+			return ret;
+	} else {
+		coresight_disable(csdev);
+	}
+
+	return size;
+}
+static DEVICE_ATTR_RW(enable_source);
+
+static struct attribute *coresight_sink_attrs[] = {
+	&dev_attr_enable_sink.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_sink);
+
+static struct attribute *coresight_source_attrs[] = {
+	&dev_attr_enable_source.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_source);
+
+static struct device_type coresight_dev_type[] = {
+	{
+		.name = "none",
+	},
+	{
+		.name = "sink",
+		.groups = coresight_sink_groups,
+	},
+	{
+		.name = "link",
+	},
+	{
+		.name = "linksink",
+		.groups = coresight_sink_groups,
+	},
+	{
+		.name = "source",
+		.groups = coresight_source_groups,
+	},
+};
+
+static void coresight_device_release(struct device *dev)
+{
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	kfree(csdev);
+}
+
+static int coresight_orphan_match(struct device *dev, void *data)
+{
+	int i;
+	bool still_orphan = false;
+	struct coresight_device *csdev, *i_csdev;
+	struct coresight_connection *conn;
+
+	csdev = data;
+	i_csdev = to_coresight_device(dev);
+
+	/* No need to check oneself */
+	if (csdev == i_csdev)
+		return 0;
+
+	/* Move on to another component if no connection is orphan */
+	if (!i_csdev->orphan)
+		return 0;
+	/*
+	 * Circle throuch all the connection of that component.  If we find
+	 * an orphan connection whose name matches @csdev, link it.
+	 */
+	for (i = 0; i < i_csdev->nr_outport; i++) {
+		conn = &i_csdev->conns[i];
+
+		/* We have found at least one orphan connection */
+		if (conn->child_dev == NULL) {
+			/* Does it match this newly added device? */
+			if (!strcmp(dev_name(&csdev->dev), conn->child_name)) {
+				conn->child_dev = csdev;
+			} else {
+				/* This component still has an orphan */
+				still_orphan = true;
+			}
+		}
+	}
+
+	i_csdev->orphan = still_orphan;
+
+	/*
+	 * Returning '0' ensures that all known component on the
+	 * bus will be checked.
+	 */
+	return 0;
+}
+
+static void coresight_fixup_orphan_conns(struct coresight_device *csdev)
+{
+	/*
+	 * No need to check for a return value as orphan connection(s)
+	 * are hooked-up with each newly added component.
+	 */
+	bus_for_each_dev(&coresight_bustype, NULL,
+				 csdev, coresight_orphan_match);
+}
+
+
+static int coresight_name_match(struct device *dev, void *data)
+{
+	char *to_match;
+	struct coresight_device *i_csdev;
+
+	to_match = data;
+	i_csdev = to_coresight_device(dev);
+
+	if (!strcmp(to_match, dev_name(&i_csdev->dev)))
+		return 1;
+
+	return 0;
+}
+
+static void coresight_fixup_device_conns(struct coresight_device *csdev)
+{
+	int i;
+	struct device *dev = NULL;
+	struct coresight_connection *conn;
+
+	for (i = 0; i < csdev->nr_outport; i++) {
+		conn = &csdev->conns[i];
+		dev = bus_find_device(&coresight_bustype, NULL,
+				      (void *)conn->child_name,
+				      coresight_name_match);
+
+		if (dev) {
+			conn->child_dev = to_coresight_device(dev);
+		} else {
+			csdev->orphan = true;
+			conn->child_dev = NULL;
+		}
+	}
+}
+
+/**
+ * coresight_timeout - loop until a bit has changed to a specific state.
+ * @addr: base address of the area of interest.
+ * @offset: address of a register, starting from @addr.
+ * @position: the position of the bit of interest.
+ * @value: the value the bit should have.
+ *
+ * Return: 0 as soon as the bit has taken the desired state or -EAGAIN if
+ * TIMEOUT_US has elapsed, which ever happens first.
+ */
+
+int coresight_timeout(void __iomem *addr, u32 offset, int position, int value)
+{
+	int i;
+	u32 val;
+
+	for (i = TIMEOUT_US; i > 0; i--) {
+		val = __raw_readl(addr + offset);
+		/* waiting on the bit to go from 0 to 1 */
+		if (value) {
+			if (val & BIT(position))
+				return 0;
+		/* waiting on the bit to go from 1 to 0 */
+		} else {
+			if (!(val & BIT(position)))
+				return 0;
+		}
+
+		/*
+		 * Delay is arbitrary - the specification doesn't say how long
+		 * we are expected to wait.  Extra check required to make sure
+		 * we don't wait needlessly on the last iteration.
+		 */
+		if (i - 1)
+			udelay(1);
+	}
+
+	return -EAGAIN;
+}
+
+struct bus_type coresight_bustype = {
+	.name	= "coresight",
+};
+
+static int __init coresight_init(void)
+{
+	return bus_register(&coresight_bustype);
+}
+postcore_initcall(coresight_init);
+
+struct coresight_device *coresight_register(struct coresight_desc *desc)
+{
+	int i;
+	int ret;
+	int link_subtype;
+	int nr_refcnts = 1;
+	atomic_t *refcnts = NULL;
+	struct coresight_device *csdev;
+	struct coresight_connection *conns;
+
+	csdev = kzalloc(sizeof(*csdev), GFP_KERNEL);
+	if (!csdev) {
+		ret = -ENOMEM;
+		goto err_kzalloc_csdev;
+	}
+
+	if (desc->type == CORESIGHT_DEV_TYPE_LINK ||
+	    desc->type == CORESIGHT_DEV_TYPE_LINKSINK) {
+		link_subtype = desc->subtype.link_subtype;
+
+		if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG)
+			nr_refcnts = desc->pdata->nr_inport;
+		else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT)
+			nr_refcnts = desc->pdata->nr_outport;
+	}
+
+	refcnts = kcalloc(nr_refcnts, sizeof(*refcnts), GFP_KERNEL);
+	if (!refcnts) {
+		ret = -ENOMEM;
+		goto err_kzalloc_refcnts;
+	}
+
+	csdev->refcnt = refcnts;
+
+	csdev->nr_inport = desc->pdata->nr_inport;
+	csdev->nr_outport = desc->pdata->nr_outport;
+	conns = kcalloc(csdev->nr_outport, sizeof(*conns), GFP_KERNEL);
+	if (!conns) {
+		ret = -ENOMEM;
+		goto err_kzalloc_conns;
+	}
+
+	for (i = 0; i < csdev->nr_outport; i++) {
+		conns[i].outport = desc->pdata->outports[i];
+		conns[i].child_name = desc->pdata->child_names[i];
+		conns[i].child_port = desc->pdata->child_ports[i];
+	}
+
+	csdev->conns = conns;
+
+	csdev->type = desc->type;
+	csdev->subtype = desc->subtype;
+	csdev->ops = desc->ops;
+	csdev->orphan = false;
+
+	csdev->dev.type = &coresight_dev_type[desc->type];
+	csdev->dev.groups = desc->groups;
+	csdev->dev.parent = desc->dev;
+	csdev->dev.release = coresight_device_release;
+	csdev->dev.bus = &coresight_bustype;
+	dev_set_name(&csdev->dev, "%s", desc->pdata->name);
+
+	ret = device_register(&csdev->dev);
+	if (ret)
+		goto err_device_register;
+
+	mutex_lock(&coresight_mutex);
+
+	coresight_fixup_device_conns(csdev);
+	coresight_fixup_orphan_conns(csdev);
+
+	mutex_unlock(&coresight_mutex);
+
+	return csdev;
+
+err_device_register:
+	kfree(conns);
+err_kzalloc_conns:
+	kfree(refcnts);
+err_kzalloc_refcnts:
+	kfree(csdev);
+err_kzalloc_csdev:
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(coresight_register);
+
+void coresight_unregister(struct coresight_device *csdev)
+{
+	mutex_lock(&coresight_mutex);
+
+	kfree(csdev->conns);
+	device_unregister(&csdev->dev);
+
+	mutex_unlock(&coresight_mutex);
+}
+EXPORT_SYMBOL_GPL(coresight_unregister);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/hwtracing/coresight/of_coresight.c b/drivers/hwtracing/coresight/of_coresight.c
new file mode 100644
index 00000000000..f3cc8e97a0f
--- /dev/null
+++ b/drivers/hwtracing/coresight/of_coresight.c
@@ -0,0 +1,200 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_graph.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/amba/bus.h>
+#include <linux/coresight.h>
+#include <linux/cpumask.h>
+#include <asm/smp_plat.h>
+
+
+static int of_dev_node_match(struct device *dev, void *data)
+{
+	return dev->of_node == data;
+}
+
+static struct device *
+of_coresight_get_endpoint_device(struct device_node *endpoint)
+{
+	struct device *dev = NULL;
+
+	/*
+	 * If we have a non-configuable replicator, it will be found on the
+	 * platform bus.
+	 */
+	dev = bus_find_device(&platform_bus_type, NULL,
+			      endpoint, of_dev_node_match);
+	if (dev)
+		return dev;
+
+	/*
+	 * We have a configurable component - circle through the AMBA bus
+	 * looking for the device that matches the endpoint node.
+	 */
+	return bus_find_device(&amba_bustype, NULL,
+			       endpoint, of_dev_node_match);
+}
+
+static struct device_node *of_get_coresight_endpoint(
+		const struct device_node *parent, struct device_node *prev)
+{
+	struct device_node *node = of_graph_get_next_endpoint(parent, prev);
+
+	of_node_put(prev);
+	return node;
+}
+
+static void of_coresight_get_ports(struct device_node *node,
+				   int *nr_inport, int *nr_outport)
+{
+	struct device_node *ep = NULL;
+	int in = 0, out = 0;
+
+	do {
+		ep = of_get_coresight_endpoint(node, ep);
+		if (!ep)
+			break;
+
+		if (of_property_read_bool(ep, "slave-mode"))
+			in++;
+		else
+			out++;
+
+	} while (ep);
+
+	*nr_inport = in;
+	*nr_outport = out;
+}
+
+static int of_coresight_alloc_memory(struct device *dev,
+			struct coresight_platform_data *pdata)
+{
+	/* List of output port on this component */
+	pdata->outports = devm_kzalloc(dev, pdata->nr_outport *
+				       sizeof(*pdata->outports),
+				       GFP_KERNEL);
+	if (!pdata->outports)
+		return -ENOMEM;
+
+	/* Children connected to this component via @outports */
+	 pdata->child_names = devm_kzalloc(dev, pdata->nr_outport *
+					  sizeof(*pdata->child_names),
+					  GFP_KERNEL);
+	if (!pdata->child_names)
+		return -ENOMEM;
+
+	/* Port number on the child this component is connected to */
+	pdata->child_ports = devm_kzalloc(dev, pdata->nr_outport *
+					  sizeof(*pdata->child_ports),
+					  GFP_KERNEL);
+	if (!pdata->child_ports)
+		return -ENOMEM;
+
+	return 0;
+}
+
+struct coresight_platform_data *of_get_coresight_platform_data(
+				struct device *dev, struct device_node *node)
+{
+	int i = 0, ret = 0, cpu;
+	struct coresight_platform_data *pdata;
+	struct of_endpoint endpoint, rendpoint;
+	struct device *rdev;
+	struct device_node *dn;
+	struct device_node *ep = NULL;
+	struct device_node *rparent = NULL;
+	struct device_node *rport = NULL;
+
+	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return ERR_PTR(-ENOMEM);
+
+	/* Use device name as sysfs handle */
+	pdata->name = dev_name(dev);
+
+	/* Get the number of input and output port for this component */
+	of_coresight_get_ports(node, &pdata->nr_inport, &pdata->nr_outport);
+
+	if (pdata->nr_outport) {
+		ret = of_coresight_alloc_memory(dev, pdata);
+		if (ret)
+			return ERR_PTR(ret);
+
+		/* Iterate through each port to discover topology */
+		do {
+			/* Get a handle on a port */
+			ep = of_get_coresight_endpoint(node, ep);
+			if (!ep)
+				break;
+
+			/*
+			 * No need to deal with input ports, processing for as
+			 * processing for output ports will deal with them.
+			 */
+			if (of_find_property(ep, "slave-mode", NULL))
+				continue;
+
+			/* Get a handle on the local endpoint */
+			ret = of_graph_parse_endpoint(ep, &endpoint);
+
+			if (ret)
+				continue;
+
+			/* The local out port number */
+			pdata->outports[i] = endpoint.id;
+
+			/*
+			 * Get a handle on the remote port and parent
+			 * attached to it.
+			 */
+			rparent = of_graph_get_remote_port_parent(ep);
+			rport = of_graph_get_remote_port(ep);
+
+			if (!rparent || !rport)
+				continue;
+
+			if (of_graph_parse_endpoint(rport, &rendpoint))
+				continue;
+
+			rdev = of_coresight_get_endpoint_device(rparent);
+			if (!rdev)
+				continue;
+
+			pdata->child_names[i] = dev_name(rdev);
+			pdata->child_ports[i] = rendpoint.id;
+
+			i++;
+		} while (ep);
+	}
+
+	/* Affinity defaults to CPU0 */
+	pdata->cpu = 0;
+	dn = of_parse_phandle(node, "cpu", 0);
+	for (cpu = 0; dn && cpu < nr_cpu_ids; cpu++) {
+		if (dn == of_get_cpu_node(cpu, NULL)) {
+			pdata->cpu = cpu;
+			break;
+		}
+	}
+
+	return pdata;
+}
+EXPORT_SYMBOL_GPL(of_get_coresight_platform_data);
diff --git a/drivers/i2c/busses/i2c-at91.c b/drivers/i2c/busses/i2c-at91.c
index e05a672db3e..85d2f6b51c3 100644
--- a/drivers/i2c/busses/i2c-at91.c
+++ b/drivers/i2c/busses/i2c-at91.c
@@ -62,6 +62,9 @@
 #define	AT91_TWI_UNRE		0x0080	/* Underrun Error */
 #define	AT91_TWI_NACK		0x0100	/* Not Acknowledged */
 
+#define	AT91_TWI_INT_MASK \
+	(AT91_TWI_TXCOMP | AT91_TWI_RXRDY | AT91_TWI_TXRDY | AT91_TWI_NACK)
+
 #define	AT91_TWI_IER		0x0024	/* Interrupt Enable Register */
 #define	AT91_TWI_IDR		0x0028	/* Interrupt Disable Register */
 #define	AT91_TWI_IMR		0x002c	/* Interrupt Mask Register */
@@ -117,13 +120,12 @@ static void at91_twi_write(struct at91_twi_dev *dev, unsigned reg, unsigned val)
 
 static void at91_disable_twi_interrupts(struct at91_twi_dev *dev)
 {
-	at91_twi_write(dev, AT91_TWI_IDR,
-		       AT91_TWI_TXCOMP | AT91_TWI_RXRDY | AT91_TWI_TXRDY);
+	at91_twi_write(dev, AT91_TWI_IDR, AT91_TWI_INT_MASK);
 }
 
 static void at91_twi_irq_save(struct at91_twi_dev *dev)
 {
-	dev->imr = at91_twi_read(dev, AT91_TWI_IMR) & 0x7;
+	dev->imr = at91_twi_read(dev, AT91_TWI_IMR) & AT91_TWI_INT_MASK;
 	at91_disable_twi_interrupts(dev);
 }
 
@@ -213,6 +215,14 @@ static void at91_twi_write_data_dma_callback(void *data)
 	dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg),
 			 dev->buf_len, DMA_TO_DEVICE);
 
+	/*
+	 * When this callback is called, THR/TX FIFO is likely not to be empty
+	 * yet. So we have to wait for TXCOMP or NACK bits to be set into the
+	 * Status Register to be sure that the STOP bit has been sent and the
+	 * transfer is completed. The NACK interrupt has already been enabled,
+	 * we just have to enable TXCOMP one.
+	 */
+	at91_twi_write(dev, AT91_TWI_IER, AT91_TWI_TXCOMP);
 	at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP);
 }
 
@@ -307,7 +317,7 @@ static void at91_twi_read_data_dma_callback(void *data)
 	/* The last two bytes have to be read without using dma */
 	dev->buf += dev->buf_len - 2;
 	dev->buf_len = 2;
-	at91_twi_write(dev, AT91_TWI_IER, AT91_TWI_RXRDY);
+	at91_twi_write(dev, AT91_TWI_IER, AT91_TWI_RXRDY | AT91_TWI_TXCOMP);
 }
 
 static void at91_twi_read_data_dma(struct at91_twi_dev *dev)
@@ -368,7 +378,7 @@ static irqreturn_t atmel_twi_interrupt(int irq, void *dev_id)
 	/* catch error flags */
 	dev->transfer_status |= status;
 
-	if (irqstatus & AT91_TWI_TXCOMP) {
+	if (irqstatus & (AT91_TWI_TXCOMP | AT91_TWI_NACK)) {
 		at91_disable_twi_interrupts(dev);
 		complete(&dev->cmd_complete);
 	}
@@ -381,6 +391,34 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev)
 	int ret;
 	bool has_unre_flag = dev->pdata->has_unre_flag;
 
+	/*
+	 * WARNING: the TXCOMP bit in the Status Register is NOT a clear on
+	 * read flag but shows the state of the transmission at the time the
+	 * Status Register is read. According to the programmer datasheet,
+	 * TXCOMP is set when both holding register and internal shifter are
+	 * empty and STOP condition has been sent.
+	 * Consequently, we should enable NACK interrupt rather than TXCOMP to
+	 * detect transmission failure.
+	 *
+	 * Besides, the TXCOMP bit is already set before the i2c transaction
+	 * has been started. For read transactions, this bit is cleared when
+	 * writing the START bit into the Control Register. So the
+	 * corresponding interrupt can safely be enabled just after.
+	 * However for write transactions managed by the CPU, we first write
+	 * into THR, so TXCOMP is cleared. Then we can safely enable TXCOMP
+	 * interrupt. If TXCOMP interrupt were enabled before writing into THR,
+	 * the interrupt handler would be called immediately and the i2c command
+	 * would be reported as completed.
+	 * Also when a write transaction is managed by the DMA controller,
+	 * enabling the TXCOMP interrupt in this function may lead to a race
+	 * condition since we don't know whether the TXCOMP interrupt is enabled
+	 * before or after the DMA has started to write into THR. So the TXCOMP
+	 * interrupt is enabled later by at91_twi_write_data_dma_callback().
+	 * Immediately after in that DMA callback, we still need to send the
+	 * STOP condition manually writing the corresponding bit into the
+	 * Control Register.
+	 */
+
 	dev_dbg(dev->dev, "transfer: %s %d bytes.\n",
 		(dev->msg->flags & I2C_M_RD) ? "read" : "write", dev->buf_len);
 
@@ -411,26 +449,24 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev)
 		 * seems to be the best solution.
 		 */
 		if (dev->use_dma && (dev->buf_len > AT91_I2C_DMA_THRESHOLD)) {
+			at91_twi_write(dev, AT91_TWI_IER, AT91_TWI_NACK);
 			at91_twi_read_data_dma(dev);
-			/*
-			 * It is important to enable TXCOMP irq here because
-			 * doing it only when transferring the last two bytes
-			 * will mask NACK errors since TXCOMP is set when a
-			 * NACK occurs.
-			 */
-			at91_twi_write(dev, AT91_TWI_IER,
-			       AT91_TWI_TXCOMP);
-		} else
+		} else {
 			at91_twi_write(dev, AT91_TWI_IER,
-			       AT91_TWI_TXCOMP | AT91_TWI_RXRDY);
+				       AT91_TWI_TXCOMP |
+				       AT91_TWI_NACK |
+				       AT91_TWI_RXRDY);
+		}
 	} else {
 		if (dev->use_dma && (dev->buf_len > AT91_I2C_DMA_THRESHOLD)) {
+			at91_twi_write(dev, AT91_TWI_IER, AT91_TWI_NACK);
 			at91_twi_write_data_dma(dev);
-			at91_twi_write(dev, AT91_TWI_IER, AT91_TWI_TXCOMP);
 		} else {
 			at91_twi_write_next_byte(dev);
 			at91_twi_write(dev, AT91_TWI_IER,
-				AT91_TWI_TXCOMP | AT91_TWI_TXRDY);
+				       AT91_TWI_TXCOMP |
+				       AT91_TWI_NACK |
+				       AT91_TWI_TXRDY);
 		}
 	}
 
diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c
index f486d0eac4d..3ba933396c2 100644
--- a/drivers/i2c/busses/i2c-rk3x.c
+++ b/drivers/i2c/busses/i2c-rk3x.c
@@ -588,7 +588,7 @@ static int rk3x_i2c_xfer(struct i2c_adapter *adap,
 	clk_disable(i2c->clk);
 	spin_unlock_irqrestore(&i2c->lock, flags);
 
-	return ret;
+	return ret < 0 ? ret : num;
 }
 
 static u32 rk3x_i2c_func(struct i2c_adapter *adap)
diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index 65244774bfa..c127af99a0e 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -778,14 +778,16 @@ static int s3c24xx_i2c_xfer(struct i2c_adapter *adap,
 	int ret;
 
 	pm_runtime_get_sync(&adap->dev);
-	clk_prepare_enable(i2c->clk);
+	ret = clk_enable(i2c->clk);
+	if (ret)
+		return ret;
 
 	for (retry = 0; retry < adap->retries; retry++) {
 
 		ret = s3c24xx_i2c_doxfer(i2c, msgs, num);
 
 		if (ret != -EAGAIN) {
-			clk_disable_unprepare(i2c->clk);
+			clk_disable(i2c->clk);
 			pm_runtime_put(&adap->dev);
 			return ret;
 		}
@@ -795,7 +797,7 @@ static int s3c24xx_i2c_xfer(struct i2c_adapter *adap,
 		udelay(100);
 	}
 
-	clk_disable_unprepare(i2c->clk);
+	clk_disable(i2c->clk);
 	pm_runtime_put(&adap->dev);
 	return -EREMOTEIO;
 }
@@ -1174,7 +1176,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev)
 
 	clk_prepare_enable(i2c->clk);
 	ret = s3c24xx_i2c_init(i2c);
-	clk_disable_unprepare(i2c->clk);
+	clk_disable(i2c->clk);
 	if (ret != 0) {
 		dev_err(&pdev->dev, "I2C controller init failed\n");
 		return ret;
@@ -1187,6 +1189,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev)
 		i2c->irq = ret = platform_get_irq(pdev, 0);
 		if (ret <= 0) {
 			dev_err(&pdev->dev, "cannot find IRQ\n");
+			clk_unprepare(i2c->clk);
 			return ret;
 		}
 
@@ -1195,6 +1198,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev)
 
 		if (ret != 0) {
 			dev_err(&pdev->dev, "cannot claim IRQ %d\n", i2c->irq);
+			clk_unprepare(i2c->clk);
 			return ret;
 		}
 	}
@@ -1202,6 +1206,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev)
 	ret = s3c24xx_i2c_register_cpufreq(i2c);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to register cpufreq notifier\n");
+		clk_unprepare(i2c->clk);
 		return ret;
 	}
 
@@ -1218,6 +1223,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev)
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to add bus to i2c core\n");
 		s3c24xx_i2c_deregister_cpufreq(i2c);
+		clk_unprepare(i2c->clk);
 		return ret;
 	}
 
@@ -1239,6 +1245,8 @@ static int s3c24xx_i2c_remove(struct platform_device *pdev)
 {
 	struct s3c24xx_i2c *i2c = platform_get_drvdata(pdev);
 
+	clk_unprepare(i2c->clk);
+
 	pm_runtime_disable(&i2c->adap.dev);
 	pm_runtime_disable(&pdev->dev);
 
@@ -1267,10 +1275,13 @@ static int s3c24xx_i2c_resume_noirq(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct s3c24xx_i2c *i2c = platform_get_drvdata(pdev);
+	int ret;
 
-	clk_prepare_enable(i2c->clk);
+	ret = clk_enable(i2c->clk);
+	if (ret)
+		return ret;
 	s3c24xx_i2c_init(i2c);
-	clk_disable_unprepare(i2c->clk);
+	clk_disable(i2c->clk);
 	i2c->suspended = 0;
 
 	return 0;
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index f43b4e11647..7bd1b5cfb8d 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -593,6 +593,7 @@ int i2c_generic_scl_recovery(struct i2c_adapter *adap)
 	adap->bus_recovery_info->set_scl(adap, 1);
 	return i2c_generic_recovery(adap);
 }
+EXPORT_SYMBOL_GPL(i2c_generic_scl_recovery);
 
 int i2c_generic_gpio_recovery(struct i2c_adapter *adap)
 {
@@ -607,6 +608,7 @@ int i2c_generic_gpio_recovery(struct i2c_adapter *adap)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(i2c_generic_gpio_recovery);
 
 int i2c_recover_bus(struct i2c_adapter *adap)
 {
@@ -616,6 +618,7 @@ int i2c_recover_bus(struct i2c_adapter *adap)
 	dev_dbg(&adap->dev, "Trying i2c bus recovery\n");
 	return adap->bus_recovery_info->recover_bus(adap);
 }
+EXPORT_SYMBOL_GPL(i2c_recover_bus);
 
 static int i2c_device_probe(struct device *dev)
 {
@@ -665,9 +668,6 @@ static int i2c_device_remove(struct device *dev)
 		status = driver->remove(client);
 	}
 
-	if (dev->of_node)
-		irq_dispose_mapping(client->irq);
-
 	dev_pm_domain_detach(&client->dev, true);
 	return status;
 }
diff --git a/drivers/iio/accel/bmc150-accel.c b/drivers/iio/accel/bmc150-accel.c
index 513bd6d1429..eaf46ea3117 100644
--- a/drivers/iio/accel/bmc150-accel.c
+++ b/drivers/iio/accel/bmc150-accel.c
@@ -168,14 +168,14 @@ static const struct {
 	int val;
 	int val2;
 	u8 bw_bits;
-} bmc150_accel_samp_freq_table[] = { {7, 810000, 0x08},
-				     {15, 630000, 0x09},
-				     {31, 250000, 0x0A},
-				     {62, 500000, 0x0B},
-				     {125, 0, 0x0C},
-				     {250, 0, 0x0D},
-				     {500, 0, 0x0E},
-				     {1000, 0, 0x0F} };
+} bmc150_accel_samp_freq_table[] = { {15, 620000, 0x08},
+				     {31, 260000, 0x09},
+				     {62, 500000, 0x0A},
+				     {125, 0, 0x0B},
+				     {250, 0, 0x0C},
+				     {500, 0, 0x0D},
+				     {1000, 0, 0x0E},
+				     {2000, 0, 0x0F} };
 
 static const struct {
 	int bw_bits;
@@ -840,7 +840,7 @@ static int bmc150_accel_validate_trigger(struct iio_dev *indio_dev,
 }
 
 static IIO_CONST_ATTR_SAMP_FREQ_AVAIL(
-		"7.810000 15.630000 31.250000 62.500000 125 250 500 1000");
+		"15.620000 31.260000 62.50000 125 250 500 1000 2000");
 
 static struct attribute *bmc150_accel_attributes[] = {
 	&iio_const_attr_sampling_frequency_available.dev_attr.attr,
diff --git a/drivers/iio/adc/ad799x.c b/drivers/iio/adc/ad799x.c
index e37412da15f..b99de00e57b 100644
--- a/drivers/iio/adc/ad799x.c
+++ b/drivers/iio/adc/ad799x.c
@@ -143,9 +143,15 @@ static int ad799x_write_config(struct ad799x_state *st, u16 val)
 	case ad7998:
 		return i2c_smbus_write_word_swapped(st->client, AD7998_CONF_REG,
 			val);
-	default:
+	case ad7992:
+	case ad7993:
+	case ad7994:
 		return i2c_smbus_write_byte_data(st->client, AD7998_CONF_REG,
 			val);
+	default:
+		/* Will be written when doing a conversion */
+		st->config = val;
+		return 0;
 	}
 }
 
@@ -155,8 +161,13 @@ static int ad799x_read_config(struct ad799x_state *st)
 	case ad7997:
 	case ad7998:
 		return i2c_smbus_read_word_swapped(st->client, AD7998_CONF_REG);
-	default:
+	case ad7992:
+	case ad7993:
+	case ad7994:
 		return i2c_smbus_read_byte_data(st->client, AD7998_CONF_REG);
+	default:
+		/* No readback support */
+		return st->config;
 	}
 }
 
diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c
index ff61ae55dd3..0047db49ee5 100644
--- a/drivers/iio/adc/at91_adc.c
+++ b/drivers/iio/adc/at91_adc.c
@@ -182,7 +182,7 @@ struct at91_adc_caps {
 	u8	ts_pen_detect_sensitivity;
 
 	/* startup time calculate function */
-	u32 (*calc_startup_ticks)(u8 startup_time, u32 adc_clk_khz);
+	u32 (*calc_startup_ticks)(u32 startup_time, u32 adc_clk_khz);
 
 	u8	num_channels;
 	struct at91_adc_reg_desc registers;
@@ -201,7 +201,7 @@ struct at91_adc_state {
 	u8			num_channels;
 	void __iomem		*reg_base;
 	struct at91_adc_reg_desc *registers;
-	u8			startup_time;
+	u32			startup_time;
 	u8			sample_hold_time;
 	bool			sleep_mode;
 	struct iio_trigger	**trig;
@@ -780,7 +780,7 @@ ret:
 	return ret;
 }
 
-static u32 calc_startup_ticks_9260(u8 startup_time, u32 adc_clk_khz)
+static u32 calc_startup_ticks_9260(u32 startup_time, u32 adc_clk_khz)
 {
 	/*
 	 * Number of ticks needed to cover the startup time of the ADC
@@ -791,7 +791,7 @@ static u32 calc_startup_ticks_9260(u8 startup_time, u32 adc_clk_khz)
 	return round_up((startup_time * adc_clk_khz / 1000) - 1, 8) / 8;
 }
 
-static u32 calc_startup_ticks_9x5(u8 startup_time, u32 adc_clk_khz)
+static u32 calc_startup_ticks_9x5(u32 startup_time, u32 adc_clk_khz)
 {
 	/*
 	 * For sama5d3x and at91sam9x5, the formula changes to:
diff --git a/drivers/iio/adc/mcp3422.c b/drivers/iio/adc/mcp3422.c
index 51672256072..b96c636470e 100644
--- a/drivers/iio/adc/mcp3422.c
+++ b/drivers/iio/adc/mcp3422.c
@@ -58,20 +58,11 @@
 		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SAMP_FREQ), \
 	}
 
-/* LSB is in nV to eliminate floating point */
-static const u32 rates_to_lsb[] = {1000000, 250000, 62500, 15625};
-
-/*
- *  scales calculated as:
- *  rates_to_lsb[sample_rate] / (1 << pga);
- *  pga is 1 for 0, 2
- */
-
 static const int mcp3422_scales[4][4] = {
-	{ 1000000, 250000, 62500, 15625 },
-	{ 500000 , 125000, 31250, 7812 },
-	{ 250000 , 62500 , 15625, 3906 },
-	{ 125000 , 31250 , 7812 , 1953 } };
+	{ 1000000, 500000, 250000, 125000 },
+	{ 250000 , 125000, 62500 , 31250  },
+	{ 62500  , 31250 , 15625 , 7812   },
+	{ 15625  , 7812  , 3906  , 1953   } };
 
 /* Constant msleep times for data acquisitions */
 static const int mcp3422_read_times[4] = {
diff --git a/drivers/iio/adc/vf610_adc.c b/drivers/iio/adc/vf610_adc.c
index 4a10ae97dbf..38e60860165 100644
--- a/drivers/iio/adc/vf610_adc.c
+++ b/drivers/iio/adc/vf610_adc.c
@@ -141,9 +141,13 @@ struct vf610_adc {
 	struct regulator *vref;
 	struct vf610_adc_feature adc_feature;
 
+	u32 sample_freq_avail[5];
+
 	struct completion completion;
 };
 
+static const u32 vf610_hw_avgs[] = { 1, 4, 8, 16, 32 };
+
 #define VF610_ADC_CHAN(_idx, _chan_type) {			\
 	.type = (_chan_type),					\
 	.indexed = 1,						\
@@ -173,35 +177,47 @@ static const struct iio_chan_spec vf610_adc_iio_channels[] = {
 	/* sentinel */
 };
 
-/*
- * ADC sample frequency, unit is ADCK cycles.
- * ADC clk source is ipg clock, which is the same as bus clock.
- *
- * ADC conversion time = SFCAdder + AverageNum x (BCT + LSTAdder)
- * SFCAdder: fixed to 6 ADCK cycles
- * AverageNum: 1, 4, 8, 16, 32 samples for hardware average.
- * BCT (Base Conversion Time): fixed to 25 ADCK cycles for 12 bit mode
- * LSTAdder(Long Sample Time): fixed to 3 ADCK cycles
- *
- * By default, enable 12 bit resolution mode, clock source
- * set to ipg clock, So get below frequency group:
- */
-static const u32 vf610_sample_freq_avail[5] =
-{1941176, 559332, 286957, 145374, 73171};
+static inline void vf610_adc_calculate_rates(struct vf610_adc *info)
+{
+	unsigned long adck_rate, ipg_rate = clk_get_rate(info->clk);
+	int i;
+
+	/*
+	 * Calculate ADC sample frequencies
+	 * Sample time unit is ADCK cycles. ADCK clk source is ipg clock,
+	 * which is the same as bus clock.
+	 *
+	 * ADC conversion time = SFCAdder + AverageNum x (BCT + LSTAdder)
+	 * SFCAdder: fixed to 6 ADCK cycles
+	 * AverageNum: 1, 4, 8, 16, 32 samples for hardware average.
+	 * BCT (Base Conversion Time): fixed to 25 ADCK cycles for 12 bit mode
+	 * LSTAdder(Long Sample Time): fixed to 3 ADCK cycles
+	 */
+	adck_rate = ipg_rate / info->adc_feature.clk_div;
+	for (i = 0; i < ARRAY_SIZE(vf610_hw_avgs); i++)
+		info->sample_freq_avail[i] =
+			adck_rate / (6 + vf610_hw_avgs[i] * (25 + 3));
+}
 
 static inline void vf610_adc_cfg_init(struct vf610_adc *info)
 {
+	struct vf610_adc_feature *adc_feature = &info->adc_feature;
+
 	/* set default Configuration for ADC controller */
-	info->adc_feature.clk_sel = VF610_ADCIOC_BUSCLK_SET;
-	info->adc_feature.vol_ref = VF610_ADCIOC_VR_VREF_SET;
+	adc_feature->clk_sel = VF610_ADCIOC_BUSCLK_SET;
+	adc_feature->vol_ref = VF610_ADCIOC_VR_VREF_SET;
+
+	adc_feature->calibration = true;
+	adc_feature->ovwren = true;
+
+	adc_feature->res_mode = 12;
+	adc_feature->sample_rate = 1;
+	adc_feature->lpm = true;
 
-	info->adc_feature.calibration = true;
-	info->adc_feature.ovwren = true;
+	/* Use a save ADCK which is below 20MHz on all devices */
+	adc_feature->clk_div = 8;
 
-	info->adc_feature.clk_div = 1;
-	info->adc_feature.res_mode = 12;
-	info->adc_feature.sample_rate = 1;
-	info->adc_feature.lpm = true;
+	vf610_adc_calculate_rates(info);
 }
 
 static void vf610_adc_cfg_post_set(struct vf610_adc *info)
@@ -283,12 +299,10 @@ static void vf610_adc_cfg_set(struct vf610_adc *info)
 
 	cfg_data = readl(info->regs + VF610_REG_ADC_CFG);
 
-	/* low power configuration */
 	cfg_data &= ~VF610_ADC_ADLPC_EN;
 	if (adc_feature->lpm)
 		cfg_data |= VF610_ADC_ADLPC_EN;
 
-	/* disable high speed */
 	cfg_data &= ~VF610_ADC_ADHSC_EN;
 
 	writel(cfg_data, info->regs + VF610_REG_ADC_CFG);
@@ -428,10 +442,27 @@ static irqreturn_t vf610_adc_isr(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static IIO_CONST_ATTR_SAMP_FREQ_AVAIL("1941176, 559332, 286957, 145374, 73171");
+static ssize_t vf610_show_samp_freq_avail(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct vf610_adc *info = iio_priv(dev_to_iio_dev(dev));
+	size_t len = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(info->sample_freq_avail); i++)
+		len += scnprintf(buf + len, PAGE_SIZE - len,
+			"%u ", info->sample_freq_avail[i]);
+
+	/* replace trailing space by newline */
+	buf[len - 1] = '\n';
+
+	return len;
+}
+
+static IIO_DEV_ATTR_SAMP_FREQ_AVAIL(vf610_show_samp_freq_avail);
 
 static struct attribute *vf610_attributes[] = {
-	&iio_const_attr_sampling_frequency_available.dev_attr.attr,
+	&iio_dev_attr_sampling_frequency_available.dev_attr.attr,
 	NULL
 };
 
@@ -478,7 +509,7 @@ static int vf610_read_raw(struct iio_dev *indio_dev,
 		return IIO_VAL_FRACTIONAL_LOG2;
 
 	case IIO_CHAN_INFO_SAMP_FREQ:
-		*val = vf610_sample_freq_avail[info->adc_feature.sample_rate];
+		*val = info->sample_freq_avail[info->adc_feature.sample_rate];
 		*val2 = 0;
 		return IIO_VAL_INT;
 
@@ -501,9 +532,9 @@ static int vf610_write_raw(struct iio_dev *indio_dev,
 	switch (mask) {
 		case IIO_CHAN_INFO_SAMP_FREQ:
 			for (i = 0;
-				i < ARRAY_SIZE(vf610_sample_freq_avail);
+				i < ARRAY_SIZE(info->sample_freq_avail);
 				i++)
-				if (val == vf610_sample_freq_avail[i]) {
+				if (val == info->sample_freq_avail[i]) {
 					info->adc_feature.sample_rate = i;
 					vf610_adc_sample_set(info);
 					return 0;
diff --git a/drivers/iio/adc/xilinx-xadc-core.c b/drivers/iio/adc/xilinx-xadc-core.c
index a221f7329b7..ce93bd8e3f6 100644
--- a/drivers/iio/adc/xilinx-xadc-core.c
+++ b/drivers/iio/adc/xilinx-xadc-core.c
@@ -856,6 +856,7 @@ static int xadc_read_raw(struct iio_dev *indio_dev,
 			switch (chan->address) {
 			case XADC_REG_VCCINT:
 			case XADC_REG_VCCAUX:
+			case XADC_REG_VREFP:
 			case XADC_REG_VCCBRAM:
 			case XADC_REG_VCCPINT:
 			case XADC_REG_VCCPAUX:
@@ -996,7 +997,7 @@ static const struct iio_event_spec xadc_voltage_events[] = {
 	.num_event_specs = (_alarm) ? ARRAY_SIZE(xadc_voltage_events) : 0, \
 	.scan_index = (_scan_index), \
 	.scan_type = { \
-		.sign = 'u', \
+		.sign = ((_addr) == XADC_REG_VREFN) ? 's' : 'u', \
 		.realbits = 12, \
 		.storagebits = 16, \
 		.shift = 4, \
@@ -1008,7 +1009,7 @@ static const struct iio_event_spec xadc_voltage_events[] = {
 static const struct iio_chan_spec xadc_channels[] = {
 	XADC_CHAN_TEMP(0, 8, XADC_REG_TEMP),
 	XADC_CHAN_VOLTAGE(0, 9, XADC_REG_VCCINT, "vccint", true),
-	XADC_CHAN_VOLTAGE(1, 10, XADC_REG_VCCINT, "vccaux", true),
+	XADC_CHAN_VOLTAGE(1, 10, XADC_REG_VCCAUX, "vccaux", true),
 	XADC_CHAN_VOLTAGE(2, 14, XADC_REG_VCCBRAM, "vccbram", true),
 	XADC_CHAN_VOLTAGE(3, 5, XADC_REG_VCCPINT, "vccpint", true),
 	XADC_CHAN_VOLTAGE(4, 6, XADC_REG_VCCPAUX, "vccpaux", true),
diff --git a/drivers/iio/adc/xilinx-xadc.h b/drivers/iio/adc/xilinx-xadc.h
index c7487e8d7f8..54adc508721 100644
--- a/drivers/iio/adc/xilinx-xadc.h
+++ b/drivers/iio/adc/xilinx-xadc.h
@@ -145,9 +145,9 @@ static inline int xadc_write_adc_reg(struct xadc *xadc, unsigned int reg,
 #define XADC_REG_MAX_VCCPINT	0x28
 #define XADC_REG_MAX_VCCPAUX	0x29
 #define XADC_REG_MAX_VCCO_DDR	0x2a
-#define XADC_REG_MIN_VCCPINT	0x2b
-#define XADC_REG_MIN_VCCPAUX	0x2c
-#define XADC_REG_MIN_VCCO_DDR	0x2d
+#define XADC_REG_MIN_VCCPINT	0x2c
+#define XADC_REG_MIN_VCCPAUX	0x2d
+#define XADC_REG_MIN_VCCO_DDR	0x2e
 
 #define XADC_REG_CONF0		0x40
 #define XADC_REG_CONF1		0x41
diff --git a/drivers/iio/dac/ad5624r_spi.c b/drivers/iio/dac/ad5624r_spi.c
index 61bb9d4239e..e98428df0d4 100644
--- a/drivers/iio/dac/ad5624r_spi.c
+++ b/drivers/iio/dac/ad5624r_spi.c
@@ -22,7 +22,7 @@
 #include "ad5624r.h"
 
 static int ad5624r_spi_write(struct spi_device *spi,
-			     u8 cmd, u8 addr, u16 val, u8 len)
+			     u8 cmd, u8 addr, u16 val, u8 shift)
 {
 	u32 data;
 	u8 msg[3];
@@ -35,7 +35,7 @@ static int ad5624r_spi_write(struct spi_device *spi,
 	 * 14-, 12-bit input code followed by 0, 2, or 4 don't care bits,
 	 * for the AD5664R, AD5644R, and AD5624R, respectively.
 	 */
-	data = (0 << 22) | (cmd << 19) | (addr << 16) | (val << (16 - len));
+	data = (0 << 22) | (cmd << 19) | (addr << 16) | (val << shift);
 	msg[0] = data >> 16;
 	msg[1] = data >> 8;
 	msg[2] = data;
diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
index f57562aa396..15c73e20272 100644
--- a/drivers/iio/dac/ad5686.c
+++ b/drivers/iio/dac/ad5686.c
@@ -322,7 +322,7 @@ static int ad5686_probe(struct spi_device *spi)
 	st = iio_priv(indio_dev);
 	spi_set_drvdata(spi, indio_dev);
 
-	st->reg = devm_regulator_get(&spi->dev, "vcc");
+	st->reg = devm_regulator_get_optional(&spi->dev, "vcc");
 	if (!IS_ERR(st->reg)) {
 		ret = regulator_enable(st->reg);
 		if (ret)
diff --git a/drivers/iio/imu/adis16400.h b/drivers/iio/imu/adis16400.h
index 0916bf6b6c3..1e8fd2e81d4 100644
--- a/drivers/iio/imu/adis16400.h
+++ b/drivers/iio/imu/adis16400.h
@@ -165,6 +165,7 @@ struct adis16400_state {
 	int				filt_int;
 
 	struct adis adis;
+	unsigned long avail_scan_mask[2];
 };
 
 /* At the moment triggers are only used for ring buffer
diff --git a/drivers/iio/imu/adis16400_core.c b/drivers/iio/imu/adis16400_core.c
index b70873de04e..7b06e058b00 100644
--- a/drivers/iio/imu/adis16400_core.c
+++ b/drivers/iio/imu/adis16400_core.c
@@ -26,6 +26,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/debugfs.h>
+#include <linux/bitops.h>
 
 #include <linux/iio/iio.h>
 #include <linux/iio/sysfs.h>
@@ -404,6 +405,11 @@ static int adis16400_read_raw(struct iio_dev *indio_dev,
 			*val = st->variant->temp_scale_nano / 1000000;
 			*val2 = (st->variant->temp_scale_nano % 1000000);
 			return IIO_VAL_INT_PLUS_MICRO;
+		case IIO_PRESSURE:
+			/* 20 uBar = 0.002kPascal */
+			*val = 0;
+			*val2 = 2000;
+			return IIO_VAL_INT_PLUS_MICRO;
 		default:
 			return -EINVAL;
 		}
@@ -414,7 +420,7 @@ static int adis16400_read_raw(struct iio_dev *indio_dev,
 		mutex_unlock(&indio_dev->mlock);
 		if (ret)
 			return ret;
-		val16 = ((val16 & 0xFFF) << 4) >> 4;
+		val16 = sign_extend32(val16, 11);
 		*val = val16;
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_OFFSET:
@@ -453,10 +459,10 @@ static int adis16400_read_raw(struct iio_dev *indio_dev,
 	}
 }
 
-#define ADIS16400_VOLTAGE_CHAN(addr, bits, name, si) { \
+#define ADIS16400_VOLTAGE_CHAN(addr, bits, name, si, chn) { \
 	.type = IIO_VOLTAGE, \
 	.indexed = 1, \
-	.channel = 0, \
+	.channel = chn, \
 	.extend_name = name, \
 	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \
 		BIT(IIO_CHAN_INFO_SCALE), \
@@ -473,10 +479,10 @@ static int adis16400_read_raw(struct iio_dev *indio_dev,
 }
 
 #define ADIS16400_SUPPLY_CHAN(addr, bits) \
-	ADIS16400_VOLTAGE_CHAN(addr, bits, "supply", ADIS16400_SCAN_SUPPLY)
+	ADIS16400_VOLTAGE_CHAN(addr, bits, "supply", ADIS16400_SCAN_SUPPLY, 0)
 
 #define ADIS16400_AUX_ADC_CHAN(addr, bits) \
-	ADIS16400_VOLTAGE_CHAN(addr, bits, NULL, ADIS16400_SCAN_ADC)
+	ADIS16400_VOLTAGE_CHAN(addr, bits, NULL, ADIS16400_SCAN_ADC, 1)
 
 #define ADIS16400_GYRO_CHAN(mod, addr, bits) { \
 	.type = IIO_ANGL_VEL, \
@@ -790,11 +796,6 @@ static const struct iio_info adis16400_info = {
 	.debugfs_reg_access = adis_debugfs_reg_access,
 };
 
-static const unsigned long adis16400_burst_scan_mask[] = {
-	~0UL,
-	0,
-};
-
 static const char * const adis16400_status_error_msgs[] = {
 	[ADIS16400_DIAG_STAT_ZACCL_FAIL] = "Z-axis accelerometer self-test failure",
 	[ADIS16400_DIAG_STAT_YACCL_FAIL] = "Y-axis accelerometer self-test failure",
@@ -842,6 +843,20 @@ static const struct adis_data adis16400_data = {
 		BIT(ADIS16400_DIAG_STAT_POWER_LOW),
 };
 
+static void adis16400_setup_chan_mask(struct adis16400_state *st)
+{
+	const struct adis16400_chip_info *chip_info = st->variant;
+	unsigned i;
+
+	for (i = 0; i < chip_info->num_channels; i++) {
+		const struct iio_chan_spec *ch = &chip_info->channels[i];
+
+		if (ch->scan_index >= 0 &&
+		    ch->scan_index != ADIS16400_SCAN_TIMESTAMP)
+			st->avail_scan_mask[0] |= BIT(ch->scan_index);
+	}
+}
+
 static int adis16400_probe(struct spi_device *spi)
 {
 	struct adis16400_state *st;
@@ -865,8 +880,10 @@ static int adis16400_probe(struct spi_device *spi)
 	indio_dev->info = &adis16400_info;
 	indio_dev->modes = INDIO_DIRECT_MODE;
 
-	if (!(st->variant->flags & ADIS16400_NO_BURST))
-		indio_dev->available_scan_masks = adis16400_burst_scan_mask;
+	if (!(st->variant->flags & ADIS16400_NO_BURST)) {
+		adis16400_setup_chan_mask(st);
+		indio_dev->available_scan_masks = st->avail_scan_mask;
+	}
 
 	ret = adis_init(&st->adis, indio_dev, spi, &adis16400_data);
 	if (ret)
diff --git a/drivers/iio/imu/adis_trigger.c b/drivers/iio/imu/adis_trigger.c
index e0017c22bb9..f53e9a803a0 100644
--- a/drivers/iio/imu/adis_trigger.c
+++ b/drivers/iio/imu/adis_trigger.c
@@ -60,7 +60,7 @@ int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev)
 	iio_trigger_set_drvdata(adis->trig, adis);
 	ret = iio_trigger_register(adis->trig);
 
-	indio_dev->trig = adis->trig;
+	indio_dev->trig = iio_trigger_get(adis->trig);
 	if (ret)
 		goto error_free_irq;
 
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
index 0cd306a72a6..ba27e277511 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
@@ -24,6 +24,16 @@
 #include <linux/poll.h>
 #include "inv_mpu_iio.h"
 
+static void inv_clear_kfifo(struct inv_mpu6050_state *st)
+{
+	unsigned long flags;
+
+	/* take the spin lock sem to avoid interrupt kick in */
+	spin_lock_irqsave(&st->time_stamp_lock, flags);
+	kfifo_reset(&st->timestamps);
+	spin_unlock_irqrestore(&st->time_stamp_lock, flags);
+}
+
 int inv_reset_fifo(struct iio_dev *indio_dev)
 {
 	int result;
@@ -50,6 +60,10 @@ int inv_reset_fifo(struct iio_dev *indio_dev)
 					INV_MPU6050_BIT_FIFO_RST);
 	if (result)
 		goto reset_fifo_fail;
+
+	/* clear timestamps fifo */
+	inv_clear_kfifo(st);
+
 	/* enable interrupt */
 	if (st->chip_config.accl_fifo_enable ||
 	    st->chip_config.gyro_fifo_enable) {
@@ -83,16 +97,6 @@ reset_fifo_fail:
 	return result;
 }
 
-static void inv_clear_kfifo(struct inv_mpu6050_state *st)
-{
-	unsigned long flags;
-
-	/* take the spin lock sem to avoid interrupt kick in */
-	spin_lock_irqsave(&st->time_stamp_lock, flags);
-	kfifo_reset(&st->timestamps);
-	spin_unlock_irqrestore(&st->time_stamp_lock, flags);
-}
-
 /**
  * inv_mpu6050_irq_handler() - Cache a timestamp at each data ready interrupt.
  */
@@ -184,7 +188,6 @@ end_session:
 flush_fifo:
 	/* Flush HW and SW FIFOs. */
 	inv_reset_fifo(indio_dev);
-	inv_clear_kfifo(st);
 	mutex_unlock(&indio_dev->mlock);
 	iio_trigger_notify_done(indio_dev->trig);
 
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index af3e76d652b..f009d053384 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -832,8 +832,7 @@ static int iio_device_add_channel_sysfs(struct iio_dev *indio_dev,
  * @attr_list: List of IIO device attributes
  *
  * This function frees the memory allocated for each of the IIO device
- * attributes in the list. Note: if you want to reuse the list after calling
- * this function you have to reinitialize it using INIT_LIST_HEAD().
+ * attributes in the list.
  */
 void iio_free_chan_devattr_list(struct list_head *attr_list)
 {
@@ -841,6 +840,7 @@ void iio_free_chan_devattr_list(struct list_head *attr_list)
 
 	list_for_each_entry_safe(p, n, attr_list, l) {
 		kfree(p->dev_attr.attr.name);
+		list_del(&p->l);
 		kfree(p);
 	}
 }
@@ -921,6 +921,7 @@ static void iio_device_unregister_sysfs(struct iio_dev *indio_dev)
 
 	iio_free_chan_devattr_list(&indio_dev->channel_attr_list);
 	kfree(indio_dev->chan_attr_group.attrs);
+	indio_dev->chan_attr_group.attrs = NULL;
 }
 
 static void iio_dev_release(struct device *device)
diff --git a/drivers/iio/industrialio-event.c b/drivers/iio/industrialio-event.c
index 0c1e37e3120..6da54921a48 100644
--- a/drivers/iio/industrialio-event.c
+++ b/drivers/iio/industrialio-event.c
@@ -492,7 +492,9 @@ int iio_device_register_eventset(struct iio_dev *indio_dev)
 
 error_free_setup_event_lines:
 	iio_free_chan_devattr_list(&indio_dev->event_interface->dev_attr_list);
+	mutex_destroy(&indio_dev->event_interface->read_lock);
 	kfree(indio_dev->event_interface);
+	indio_dev->event_interface = NULL;
 	return ret;
 }
 
@@ -516,5 +518,6 @@ void iio_device_unregister_eventset(struct iio_dev *indio_dev)
 		return;
 	iio_free_chan_devattr_list(&indio_dev->event_interface->dev_attr_list);
 	kfree(indio_dev->event_interface->group.attrs);
+	mutex_destroy(&indio_dev->event_interface->read_lock);
 	kfree(indio_dev->event_interface);
 }
diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c
index f5a514698fd..d403c988463 100644
--- a/drivers/iio/light/hid-sensor-prox.c
+++ b/drivers/iio/light/hid-sensor-prox.c
@@ -43,8 +43,6 @@ struct prox_state {
 static const struct iio_chan_spec prox_channels[] = {
 	{
 		.type = IIO_PROXIMITY,
-		.modified = 1,
-		.channel2 = IIO_NO_MOD,
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
 		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |
 		BIT(IIO_CHAN_INFO_SCALE) |
diff --git a/drivers/iio/pressure/hid-sensor-press.c b/drivers/iio/pressure/hid-sensor-press.c
index 764928682df..127db532f35 100644
--- a/drivers/iio/pressure/hid-sensor-press.c
+++ b/drivers/iio/pressure/hid-sensor-press.c
@@ -47,8 +47,6 @@ struct press_state {
 static const struct iio_chan_spec press_channels[] = {
 	{
 		.type = IIO_PRESSURE,
-		.modified = 1,
-		.channel2 = IIO_NO_MOD,
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
 		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |
 		BIT(IIO_CHAN_INFO_SCALE) |
diff --git a/drivers/iio/temperature/tmp006.c b/drivers/iio/temperature/tmp006.c
index 84a0789c3d9..7a8050996b4 100644
--- a/drivers/iio/temperature/tmp006.c
+++ b/drivers/iio/temperature/tmp006.c
@@ -132,6 +132,9 @@ static int tmp006_write_raw(struct iio_dev *indio_dev,
 	struct tmp006_data *data = iio_priv(indio_dev);
 	int i;
 
+	if (mask != IIO_CHAN_INFO_SAMP_FREQ)
+		return -EINVAL;
+
 	for (i = 0; i < ARRAY_SIZE(tmp006_freqs); i++)
 		if ((val == tmp006_freqs[i][0]) &&
 		    (val2 == tmp006_freqs[i][1])) {
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index d570030d899..06441a43c3a 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -859,19 +859,27 @@ static void cma_save_ib_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id
 	memcpy(&ib->sib_addr, &path->dgid, 16);
 }
 
+static __be16 ss_get_port(const struct sockaddr_storage *ss)
+{
+	if (ss->ss_family == AF_INET)
+		return ((struct sockaddr_in *)ss)->sin_port;
+	else if (ss->ss_family == AF_INET6)
+		return ((struct sockaddr_in6 *)ss)->sin6_port;
+	BUG();
+}
+
 static void cma_save_ip4_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id,
 			      struct cma_hdr *hdr)
 {
-	struct sockaddr_in *listen4, *ip4;
+	struct sockaddr_in *ip4;
 
-	listen4 = (struct sockaddr_in *) &listen_id->route.addr.src_addr;
 	ip4 = (struct sockaddr_in *) &id->route.addr.src_addr;
-	ip4->sin_family = listen4->sin_family;
+	ip4->sin_family = AF_INET;
 	ip4->sin_addr.s_addr = hdr->dst_addr.ip4.addr;
-	ip4->sin_port = listen4->sin_port;
+	ip4->sin_port = ss_get_port(&listen_id->route.addr.src_addr);
 
 	ip4 = (struct sockaddr_in *) &id->route.addr.dst_addr;
-	ip4->sin_family = listen4->sin_family;
+	ip4->sin_family = AF_INET;
 	ip4->sin_addr.s_addr = hdr->src_addr.ip4.addr;
 	ip4->sin_port = hdr->port;
 }
@@ -879,16 +887,15 @@ static void cma_save_ip4_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_i
 static void cma_save_ip6_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id,
 			      struct cma_hdr *hdr)
 {
-	struct sockaddr_in6 *listen6, *ip6;
+	struct sockaddr_in6 *ip6;
 
-	listen6 = (struct sockaddr_in6 *) &listen_id->route.addr.src_addr;
 	ip6 = (struct sockaddr_in6 *) &id->route.addr.src_addr;
-	ip6->sin6_family = listen6->sin6_family;
+	ip6->sin6_family = AF_INET6;
 	ip6->sin6_addr = hdr->dst_addr.ip6;
-	ip6->sin6_port = listen6->sin6_port;
+	ip6->sin6_port = ss_get_port(&listen_id->route.addr.src_addr);
 
 	ip6 = (struct sockaddr_in6 *) &id->route.addr.dst_addr;
-	ip6->sin6_family = listen6->sin6_family;
+	ip6->sin6_family = AF_INET6;
 	ip6->sin6_addr = hdr->src_addr.ip6;
 	ip6->sin6_port = hdr->port;
 }
diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
index b85ddbc979e..e5558b2660f 100644
--- a/drivers/infiniband/core/iwpm_msg.c
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -33,7 +33,7 @@
 
 #include "iwpm_util.h"
 
-static const char iwpm_ulib_name[] = "iWarpPortMapperUser";
+static const char iwpm_ulib_name[IWPM_ULIBNAME_SIZE] = "iWarpPortMapperUser";
 static int iwpm_ulib_version = 3;
 static int iwpm_user_pid = IWPM_PID_UNDEFINED;
 static atomic_t echo_nlmsg_seq;
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 56a4b7ca7ee..45d67e9228d 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -1124,6 +1124,9 @@ static int ucma_set_ib_path(struct ucma_context *ctx,
 	if (!optlen)
 		return -EINVAL;
 
+	memset(&sa_path, 0, sizeof(sa_path));
+	sa_path.vlan_id = 0xffff;
+
 	ib_sa_unpack_path(path_data->path_rec, &sa_path);
 	ret = rdma_set_ib_paths(ctx->cm_id, &sa_path, 1);
 	if (ret)
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index df0c4f605a2..49df6af0f03 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -94,6 +94,17 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	if (dmasync)
 		dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs);
 
+	if (!size)
+		return ERR_PTR(-EINVAL);
+
+	/*
+	 * If the combination of the addr and size requested for this memory
+	 * region causes an integer overflow, return error.
+	 */
+	if (((addr + size) < addr) ||
+	    PAGE_ALIGN(addr + size) < (addr + size))
+		return ERR_PTR(-EINVAL);
+
 	if (!can_do_mlock())
 		return ERR_PTR(-EPERM);
 
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 5ba2a86aab6..63a9f04bdb6 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2057,20 +2057,21 @@ ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file,
 	if (qp->real_qp == qp) {
 		ret = ib_resolve_eth_l2_attrs(qp, attr, &cmd.attr_mask);
 		if (ret)
-			goto out;
+			goto release_qp;
 		ret = qp->device->modify_qp(qp, attr,
 			modify_qp_mask(qp->qp_type, cmd.attr_mask), &udata);
 	} else {
 		ret = ib_modify_qp(qp, attr, modify_qp_mask(qp->qp_type, cmd.attr_mask));
 	}
 
-	put_qp_read(qp);
-
 	if (ret)
-		goto out;
+		goto release_qp;
 
 	ret = in_len;
 
+release_qp:
+	put_qp_read(qp);
+
 out:
 	kfree(attr);
 
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 82a7dd87089..729382c06c5 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -64,6 +64,14 @@ enum {
 #define GUID_TBL_BLK_NUM_ENTRIES 8
 #define GUID_TBL_BLK_SIZE (GUID_TBL_ENTRY_SIZE * GUID_TBL_BLK_NUM_ENTRIES)
 
+/* Counters should be saturate once they reach their maximum value */
+#define ASSIGN_32BIT_COUNTER(counter, value) do {\
+	if ((value) > U32_MAX)			 \
+		counter = cpu_to_be32(U32_MAX); \
+	else					 \
+		counter = cpu_to_be32(value);	 \
+} while (0)
+
 struct mlx4_mad_rcv_buf {
 	struct ib_grh grh;
 	u8 payload[256];
@@ -806,10 +814,14 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 static void edit_counter(struct mlx4_counter *cnt,
 					struct ib_pma_portcounters *pma_cnt)
 {
-	pma_cnt->port_xmit_data = cpu_to_be32((be64_to_cpu(cnt->tx_bytes)>>2));
-	pma_cnt->port_rcv_data  = cpu_to_be32((be64_to_cpu(cnt->rx_bytes)>>2));
-	pma_cnt->port_xmit_packets = cpu_to_be32(be64_to_cpu(cnt->tx_frames));
-	pma_cnt->port_rcv_packets  = cpu_to_be32(be64_to_cpu(cnt->rx_frames));
+	ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_data,
+			     (be64_to_cpu(cnt->tx_bytes) >> 2));
+	ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_data,
+			     (be64_to_cpu(cnt->rx_bytes) >> 2));
+	ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_packets,
+			     be64_to_cpu(cnt->tx_frames));
+	ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_packets,
+			     be64_to_cpu(cnt->rx_frames));
 }
 
 static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 8b72cf392b3..3b619b10a37 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1221,8 +1221,7 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	struct mlx4_ib_qp *mqp = to_mqp(ibqp);
 	u64 reg_id;
 	struct mlx4_ib_steering *ib_steering = NULL;
-	enum mlx4_protocol prot = (gid->raw[1] == 0x0e) ?
-		MLX4_PROT_IB_IPV4 : MLX4_PROT_IB_IPV6;
+	enum mlx4_protocol prot = MLX4_PROT_IB_IPV6;
 
 	if (mdev->dev->caps.steering_mode ==
 	    MLX4_STEERING_MODE_DEVICE_MANAGED) {
@@ -1235,8 +1234,10 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 				    !!(mqp->flags &
 				       MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK),
 				    prot, &reg_id);
-	if (err)
+	if (err) {
+		pr_err("multicast attach op failed, err %d\n", err);
 		goto err_malloc;
+	}
 
 	err = add_gid_entry(ibqp, gid);
 	if (err)
@@ -1284,8 +1285,7 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	struct net_device *ndev;
 	struct mlx4_ib_gid_entry *ge;
 	u64 reg_id = 0;
-	enum mlx4_protocol prot = (gid->raw[1] == 0x0e) ?
-		MLX4_PROT_IB_IPV4 : MLX4_PROT_IB_IPV6;
+	enum mlx4_protocol prot =  MLX4_PROT_IB_IPV6;
 
 	if (mdev->dev->caps.steering_mode ==
 	    MLX4_STEERING_MODE_DEVICE_MANAGED) {
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 9c5150c3cb3..33cbb7611d6 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1669,8 +1669,10 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 			    qp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_GSI ||
 			    qp->mlx4_ib_qp_type == MLX4_IB_QPT_TUN_GSI) {
 				err = handle_eth_ud_smac_index(dev, qp, (u8 *)attr->smac, context);
-				if (err)
-					return -EINVAL;
+				if (err) {
+					err = -EINVAL;
+					goto out;
+				}
 				if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_GSI)
 					dev->qp1_proxy[qp->port - 1] = qp;
 			}
@@ -2557,8 +2559,7 @@ static int build_lso_seg(struct mlx4_wqe_lso_seg *wqe, struct ib_send_wr *wr,
 
 	memcpy(wqe->header, wr->wr.ud.header, wr->wr.ud.hlen);
 
-	*lso_hdr_sz  = cpu_to_be32((wr->wr.ud.mss - wr->wr.ud.hlen) << 16 |
-				   wr->wr.ud.hlen);
+	*lso_hdr_sz  = cpu_to_be32(wr->wr.ud.mss << 16 | wr->wr.ud.hlen);
 	*lso_seg_len = halign;
 	return 0;
 }
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 1ba6c42e4df..820fb8009ed 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -987,7 +987,7 @@ static int get_port_caps(struct mlx5_ib_dev *dev)
 	struct ib_device_attr *dprops = NULL;
 	struct ib_port_attr *pprops = NULL;
 	struct mlx5_general_caps *gen;
-	int err = 0;
+	int err = -ENOMEM;
 	int port;
 
 	gen = &dev->mdev->caps.gen;
diff --git a/drivers/infiniband/hw/qib/qib.h b/drivers/infiniband/hw/qib/qib.h
index c00ae093b6f..b218254ee41 100644
--- a/drivers/infiniband/hw/qib/qib.h
+++ b/drivers/infiniband/hw/qib/qib.h
@@ -1082,12 +1082,6 @@ struct qib_devdata {
 	/* control high-level access to EEPROM */
 	struct mutex eep_lock;
 	uint64_t traffic_wds;
-	/* active time is kept in seconds, but logged in hours */
-	atomic_t active_time;
-	/* Below are nominal shadow of EEPROM, new since last EEPROM update */
-	uint8_t eep_st_errs[QIB_EEP_LOG_CNT];
-	uint8_t eep_st_new_errs[QIB_EEP_LOG_CNT];
-	uint16_t eep_hrs;
 	/*
 	 * masks for which bits of errs, hwerrs that cause
 	 * each of the counters to increment.
@@ -1309,8 +1303,7 @@ int qib_twsi_blk_rd(struct qib_devdata *dd, int dev, int addr, void *buffer,
 int qib_twsi_blk_wr(struct qib_devdata *dd, int dev, int addr,
 		    const void *buffer, int len);
 void qib_get_eeprom_info(struct qib_devdata *);
-int qib_update_eeprom_log(struct qib_devdata *dd);
-void qib_inc_eeprom_err(struct qib_devdata *dd, u32 eidx, u32 incr);
+#define qib_inc_eeprom_err(dd, eidx, incr)
 void qib_dump_lookup_output_queue(struct qib_devdata *);
 void qib_force_pio_avail_update(struct qib_devdata *);
 void qib_clear_symerror_on_linkup(unsigned long opaque);
diff --git a/drivers/infiniband/hw/qib/qib_eeprom.c b/drivers/infiniband/hw/qib/qib_eeprom.c
index 4d5d71aaa2b..e2280b07df0 100644
--- a/drivers/infiniband/hw/qib/qib_eeprom.c
+++ b/drivers/infiniband/hw/qib/qib_eeprom.c
@@ -267,190 +267,9 @@ void qib_get_eeprom_info(struct qib_devdata *dd)
 			"Board SN %s did not pass functional test: %s\n",
 			dd->serial, ifp->if_comment);
 
-	memcpy(&dd->eep_st_errs, &ifp->if_errcntp, QIB_EEP_LOG_CNT);
-	/*
-	 * Power-on (actually "active") hours are kept as little-endian value
-	 * in EEPROM, but as seconds in a (possibly as small as 24-bit)
-	 * atomic_t while running.
-	 */
-	atomic_set(&dd->active_time, 0);
-	dd->eep_hrs = ifp->if_powerhour[0] | (ifp->if_powerhour[1] << 8);
-
 done:
 	vfree(buf);
 
 bail:;
 }
 
-/**
- * qib_update_eeprom_log - copy active-time and error counters to eeprom
- * @dd: the qlogic_ib device
- *
- * Although the time is kept as seconds in the qib_devdata struct, it is
- * rounded to hours for re-write, as we have only 16 bits in EEPROM.
- * First-cut code reads whole (expected) struct qib_flash, modifies,
- * re-writes. Future direction: read/write only what we need, assuming
- * that the EEPROM had to have been "good enough" for driver init, and
- * if not, we aren't making it worse.
- *
- */
-int qib_update_eeprom_log(struct qib_devdata *dd)
-{
-	void *buf;
-	struct qib_flash *ifp;
-	int len, hi_water;
-	uint32_t new_time, new_hrs;
-	u8 csum;
-	int ret, idx;
-	unsigned long flags;
-
-	/* first, check if we actually need to do anything. */
-	ret = 0;
-	for (idx = 0; idx < QIB_EEP_LOG_CNT; ++idx) {
-		if (dd->eep_st_new_errs[idx]) {
-			ret = 1;
-			break;
-		}
-	}
-	new_time = atomic_read(&dd->active_time);
-
-	if (ret == 0 && new_time < 3600)
-		goto bail;
-
-	/*
-	 * The quick-check above determined that there is something worthy
-	 * of logging, so get current contents and do a more detailed idea.
-	 * read full flash, not just currently used part, since it may have
-	 * been written with a newer definition
-	 */
-	len = sizeof(struct qib_flash);
-	buf = vmalloc(len);
-	ret = 1;
-	if (!buf) {
-		qib_dev_err(dd,
-			"Couldn't allocate memory to read %u bytes from eeprom for logging\n",
-			len);
-		goto bail;
-	}
-
-	/* Grab semaphore and read current EEPROM. If we get an
-	 * error, let go, but if not, keep it until we finish write.
-	 */
-	ret = mutex_lock_interruptible(&dd->eep_lock);
-	if (ret) {
-		qib_dev_err(dd, "Unable to acquire EEPROM for logging\n");
-		goto free_bail;
-	}
-	ret = qib_twsi_blk_rd(dd, dd->twsi_eeprom_dev, 0, buf, len);
-	if (ret) {
-		mutex_unlock(&dd->eep_lock);
-		qib_dev_err(dd, "Unable read EEPROM for logging\n");
-		goto free_bail;
-	}
-	ifp = (struct qib_flash *)buf;
-
-	csum = flash_csum(ifp, 0);
-	if (csum != ifp->if_csum) {
-		mutex_unlock(&dd->eep_lock);
-		qib_dev_err(dd, "EEPROM cks err (0x%02X, S/B 0x%02X)\n",
-			    csum, ifp->if_csum);
-		ret = 1;
-		goto free_bail;
-	}
-	hi_water = 0;
-	spin_lock_irqsave(&dd->eep_st_lock, flags);
-	for (idx = 0; idx < QIB_EEP_LOG_CNT; ++idx) {
-		int new_val = dd->eep_st_new_errs[idx];
-		if (new_val) {
-			/*
-			 * If we have seen any errors, add to EEPROM values
-			 * We need to saturate at 0xFF (255) and we also
-			 * would need to adjust the checksum if we were
-			 * trying to minimize EEPROM traffic
-			 * Note that we add to actual current count in EEPROM,
-			 * in case it was altered while we were running.
-			 */
-			new_val += ifp->if_errcntp[idx];
-			if (new_val > 0xFF)
-				new_val = 0xFF;
-			if (ifp->if_errcntp[idx] != new_val) {
-				ifp->if_errcntp[idx] = new_val;
-				hi_water = offsetof(struct qib_flash,
-						    if_errcntp) + idx;
-			}
-			/*
-			 * update our shadow (used to minimize EEPROM
-			 * traffic), to match what we are about to write.
-			 */
-			dd->eep_st_errs[idx] = new_val;
-			dd->eep_st_new_errs[idx] = 0;
-		}
-	}
-	/*
-	 * Now update active-time. We would like to round to the nearest hour
-	 * but unless atomic_t are sure to be proper signed ints we cannot,
-	 * because we need to account for what we "transfer" to EEPROM and
-	 * if we log an hour at 31 minutes, then we would need to set
-	 * active_time to -29 to accurately count the _next_ hour.
-	 */
-	if (new_time >= 3600) {
-		new_hrs = new_time / 3600;
-		atomic_sub((new_hrs * 3600), &dd->active_time);
-		new_hrs += dd->eep_hrs;
-		if (new_hrs > 0xFFFF)
-			new_hrs = 0xFFFF;
-		dd->eep_hrs = new_hrs;
-		if ((new_hrs & 0xFF) != ifp->if_powerhour[0]) {
-			ifp->if_powerhour[0] = new_hrs & 0xFF;
-			hi_water = offsetof(struct qib_flash, if_powerhour);
-		}
-		if ((new_hrs >> 8) != ifp->if_powerhour[1]) {
-			ifp->if_powerhour[1] = new_hrs >> 8;
-			hi_water = offsetof(struct qib_flash, if_powerhour) + 1;
-		}
-	}
-	/*
-	 * There is a tiny possibility that we could somehow fail to write
-	 * the EEPROM after updating our shadows, but problems from holding
-	 * the spinlock too long are a much bigger issue.
-	 */
-	spin_unlock_irqrestore(&dd->eep_st_lock, flags);
-	if (hi_water) {
-		/* we made some change to the data, uopdate cksum and write */
-		csum = flash_csum(ifp, 1);
-		ret = eeprom_write_with_enable(dd, 0, buf, hi_water + 1);
-	}
-	mutex_unlock(&dd->eep_lock);
-	if (ret)
-		qib_dev_err(dd, "Failed updating EEPROM\n");
-
-free_bail:
-	vfree(buf);
-bail:
-	return ret;
-}
-
-/**
- * qib_inc_eeprom_err - increment one of the four error counters
- * that are logged to EEPROM.
- * @dd: the qlogic_ib device
- * @eidx: 0..3, the counter to increment
- * @incr: how much to add
- *
- * Each counter is 8-bits, and saturates at 255 (0xFF). They
- * are copied to the EEPROM (aka flash) whenever qib_update_eeprom_log()
- * is called, but it can only be called in a context that allows sleep.
- * This function can be called even at interrupt level.
- */
-void qib_inc_eeprom_err(struct qib_devdata *dd, u32 eidx, u32 incr)
-{
-	uint new_val;
-	unsigned long flags;
-
-	spin_lock_irqsave(&dd->eep_st_lock, flags);
-	new_val = dd->eep_st_new_errs[eidx] + incr;
-	if (new_val > 255)
-		new_val = 255;
-	dd->eep_st_new_errs[eidx] = new_val;
-	spin_unlock_irqrestore(&dd->eep_st_lock, flags);
-}
diff --git a/drivers/infiniband/hw/qib/qib_iba6120.c b/drivers/infiniband/hw/qib/qib_iba6120.c
index d68266ac761..f7f49a6c34b 100644
--- a/drivers/infiniband/hw/qib/qib_iba6120.c
+++ b/drivers/infiniband/hw/qib/qib_iba6120.c
@@ -2681,8 +2681,6 @@ static void qib_get_6120_faststats(unsigned long opaque)
 	spin_lock_irqsave(&dd->eep_st_lock, flags);
 	traffic_wds -= dd->traffic_wds;
 	dd->traffic_wds += traffic_wds;
-	if (traffic_wds  >= QIB_TRAFFIC_ACTIVE_THRESHOLD)
-		atomic_add(5, &dd->active_time); /* S/B #define */
 	spin_unlock_irqrestore(&dd->eep_st_lock, flags);
 
 	qib_chk_6120_errormask(dd);
diff --git a/drivers/infiniband/hw/qib/qib_iba7220.c b/drivers/infiniband/hw/qib/qib_iba7220.c
index 7dec89fdc12..f5fa106e199 100644
--- a/drivers/infiniband/hw/qib/qib_iba7220.c
+++ b/drivers/infiniband/hw/qib/qib_iba7220.c
@@ -3297,8 +3297,6 @@ static void qib_get_7220_faststats(unsigned long opaque)
 	spin_lock_irqsave(&dd->eep_st_lock, flags);
 	traffic_wds -= dd->traffic_wds;
 	dd->traffic_wds += traffic_wds;
-	if (traffic_wds  >= QIB_TRAFFIC_ACTIVE_THRESHOLD)
-		atomic_add(5, &dd->active_time); /* S/B #define */
 	spin_unlock_irqrestore(&dd->eep_st_lock, flags);
 done:
 	mod_timer(&dd->stats_timer, jiffies + HZ * ACTIVITY_TIMER);
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index a7eb32517a0..23ca2aca1ad 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -5178,8 +5178,6 @@ static void qib_get_7322_faststats(unsigned long opaque)
 		spin_lock_irqsave(&ppd->dd->eep_st_lock, flags);
 		traffic_wds -= ppd->dd->traffic_wds;
 		ppd->dd->traffic_wds += traffic_wds;
-		if (traffic_wds >= QIB_TRAFFIC_ACTIVE_THRESHOLD)
-			atomic_add(ACTIVITY_TIMER, &ppd->dd->active_time);
 		spin_unlock_irqrestore(&ppd->dd->eep_st_lock, flags);
 		if (ppd->cpspec->qdr_dfe_on && (ppd->link_speed_active &
 						QIB_IB_QDR) &&
diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c
index 729da39c49e..738269b46d8 100644
--- a/drivers/infiniband/hw/qib/qib_init.c
+++ b/drivers/infiniband/hw/qib/qib_init.c
@@ -931,7 +931,6 @@ static void qib_shutdown_device(struct qib_devdata *dd)
 		qib_free_pportdata(ppd);
 	}
 
-	qib_update_eeprom_log(dd);
 }
 
 /**
diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c
index 3c8e4e3caca..b9ccbda7817 100644
--- a/drivers/infiniband/hw/qib/qib_sysfs.c
+++ b/drivers/infiniband/hw/qib/qib_sysfs.c
@@ -611,28 +611,6 @@ bail:
 	return ret < 0 ? ret : count;
 }
 
-static ssize_t show_logged_errs(struct device *device,
-				struct device_attribute *attr, char *buf)
-{
-	struct qib_ibdev *dev =
-		container_of(device, struct qib_ibdev, ibdev.dev);
-	struct qib_devdata *dd = dd_from_dev(dev);
-	int idx, count;
-
-	/* force consistency with actual EEPROM */
-	if (qib_update_eeprom_log(dd) != 0)
-		return -ENXIO;
-
-	count = 0;
-	for (idx = 0; idx < QIB_EEP_LOG_CNT; ++idx) {
-		count += scnprintf(buf + count, PAGE_SIZE - count, "%d%c",
-				   dd->eep_st_errs[idx],
-				   idx == (QIB_EEP_LOG_CNT - 1) ? '\n' : ' ');
-	}
-
-	return count;
-}
-
 /*
  * Dump tempsense regs. in decimal, to ease shell-scripts.
  */
@@ -679,7 +657,6 @@ static DEVICE_ATTR(nctxts, S_IRUGO, show_nctxts, NULL);
 static DEVICE_ATTR(nfreectxts, S_IRUGO, show_nfreectxts, NULL);
 static DEVICE_ATTR(serial, S_IRUGO, show_serial, NULL);
 static DEVICE_ATTR(boardversion, S_IRUGO, show_boardversion, NULL);
-static DEVICE_ATTR(logged_errors, S_IRUGO, show_logged_errs, NULL);
 static DEVICE_ATTR(tempsense, S_IRUGO, show_tempsense, NULL);
 static DEVICE_ATTR(localbus_info, S_IRUGO, show_localbus_info, NULL);
 static DEVICE_ATTR(chip_reset, S_IWUSR, NULL, store_chip_reset);
@@ -693,7 +670,6 @@ static struct device_attribute *qib_attributes[] = {
 	&dev_attr_nfreectxts,
 	&dev_attr_serial,
 	&dev_attr_boardversion,
-	&dev_attr_logged_errors,
 	&dev_attr_tempsense,
 	&dev_attr_localbus_info,
 	&dev_attr_chip_reset,
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index cd4174ca9a7..e4bc9409243 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -432,6 +432,7 @@ struct fast_reg_descriptor {
  * @cma_id:              rdma_cm connection maneger handle
  * @qp:                  Connection Queue-pair
  * @post_recv_buf_count: post receive counter
+ * @sig_count:           send work request signal count
  * @rx_wr:               receive work request for batch posts
  * @device:              reference to iser device
  * @comp:                iser completion context
@@ -452,6 +453,7 @@ struct ib_conn {
 	struct rdma_cm_id           *cma_id;
 	struct ib_qp	            *qp;
 	int                          post_recv_buf_count;
+	u8                           sig_count;
 	struct ib_recv_wr	     rx_wr[ISER_MIN_POSTED_RX];
 	struct iser_device          *device;
 	struct iser_comp	    *comp;
@@ -652,7 +654,9 @@ int iser_dma_map_task_data(struct iscsi_iser_task *iser_task,
 			   enum dma_data_direction dma_dir);
 
 void iser_dma_unmap_task_data(struct iscsi_iser_task *iser_task,
-			      struct iser_data_buf *data);
+			      struct iser_data_buf *data,
+			      enum dma_data_direction dir);
+
 int  iser_initialize_task_headers(struct iscsi_task *task,
 			struct iser_tx_desc *tx_desc);
 int iser_alloc_rx_descriptors(struct iser_conn *iser_conn,
diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c
index 5a489ea6373..76eb57b31a5 100644
--- a/drivers/infiniband/ulp/iser/iser_initiator.c
+++ b/drivers/infiniband/ulp/iser/iser_initiator.c
@@ -320,9 +320,6 @@ void iser_free_rx_descriptors(struct iser_conn *iser_conn)
 	struct ib_conn *ib_conn = &iser_conn->ib_conn;
 	struct iser_device *device = ib_conn->device;
 
-	if (!iser_conn->rx_descs)
-		goto free_login_buf;
-
 	if (device->iser_free_rdma_reg_res)
 		device->iser_free_rdma_reg_res(ib_conn);
 
@@ -334,7 +331,6 @@ void iser_free_rx_descriptors(struct iser_conn *iser_conn)
 	/* make sure we never redo any unmapping */
 	iser_conn->rx_descs = NULL;
 
-free_login_buf:
 	iser_free_login_buf(iser_conn);
 }
 
@@ -369,7 +365,7 @@ static int iser_post_rx_bufs(struct iscsi_conn *conn, struct iscsi_hdr *req)
 	return 0;
 }
 
-static inline bool iser_signal_comp(int sig_count)
+static inline bool iser_signal_comp(u8 sig_count)
 {
 	return ((sig_count % ISER_SIGNAL_CMD_COUNT) == 0);
 }
@@ -388,7 +384,7 @@ int iser_send_command(struct iscsi_conn *conn,
 	struct iscsi_scsi_req *hdr = (struct iscsi_scsi_req *)task->hdr;
 	struct scsi_cmnd *sc  =  task->sc;
 	struct iser_tx_desc *tx_desc = &iser_task->desc;
-	static unsigned sig_count;
+	u8 sig_count = ++iser_conn->ib_conn.sig_count;
 
 	edtl = ntohl(hdr->data_length);
 
@@ -413,8 +409,8 @@ int iser_send_command(struct iscsi_conn *conn,
 	if (scsi_prot_sg_count(sc)) {
 		prot_buf->buf  = scsi_prot_sglist(sc);
 		prot_buf->size = scsi_prot_sg_count(sc);
-		prot_buf->data_len = data_buf->data_len >>
-				     ilog2(sc->device->sector_size) * 8;
+		prot_buf->data_len = (data_buf->data_len >>
+				     ilog2(sc->device->sector_size)) * 8;
 	}
 
 	if (hdr->flags & ISCSI_FLAG_CMD_READ) {
@@ -435,7 +431,7 @@ int iser_send_command(struct iscsi_conn *conn,
 	iser_task->status = ISER_TASK_STATUS_STARTED;
 
 	err = iser_post_send(&iser_conn->ib_conn, tx_desc,
-			     iser_signal_comp(++sig_count));
+			     iser_signal_comp(sig_count));
 	if (!err)
 		return 0;
 
@@ -714,19 +710,23 @@ void iser_task_rdma_finalize(struct iscsi_iser_task *iser_task)
 		device->iser_unreg_rdma_mem(iser_task, ISER_DIR_IN);
 		if (is_rdma_data_aligned)
 			iser_dma_unmap_task_data(iser_task,
-						 &iser_task->data[ISER_DIR_IN]);
+						 &iser_task->data[ISER_DIR_IN],
+						 DMA_FROM_DEVICE);
 		if (prot_count && is_rdma_prot_aligned)
 			iser_dma_unmap_task_data(iser_task,
-						 &iser_task->prot[ISER_DIR_IN]);
+						 &iser_task->prot[ISER_DIR_IN],
+						 DMA_FROM_DEVICE);
 	}
 
 	if (iser_task->dir[ISER_DIR_OUT]) {
 		device->iser_unreg_rdma_mem(iser_task, ISER_DIR_OUT);
 		if (is_rdma_data_aligned)
 			iser_dma_unmap_task_data(iser_task,
-						 &iser_task->data[ISER_DIR_OUT]);
+						 &iser_task->data[ISER_DIR_OUT],
+						 DMA_TO_DEVICE);
 		if (prot_count && is_rdma_prot_aligned)
 			iser_dma_unmap_task_data(iser_task,
-						 &iser_task->prot[ISER_DIR_OUT]);
+						 &iser_task->prot[ISER_DIR_OUT],
+						 DMA_TO_DEVICE);
 	}
 }
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index 6c5ce357fba..424783f3e0a 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -333,12 +333,13 @@ int iser_dma_map_task_data(struct iscsi_iser_task *iser_task,
 }
 
 void iser_dma_unmap_task_data(struct iscsi_iser_task *iser_task,
-			      struct iser_data_buf *data)
+			      struct iser_data_buf *data,
+			      enum dma_data_direction dir)
 {
 	struct ib_device *dev;
 
 	dev = iser_task->iser_conn->ib_conn.device->ib_device;
-	ib_dma_unmap_sg(dev, data->buf, data->size, DMA_FROM_DEVICE);
+	ib_dma_unmap_sg(dev, data->buf, data->size, dir);
 }
 
 static int fall_to_bounce_buf(struct iscsi_iser_task *iser_task,
@@ -358,7 +359,9 @@ static int fall_to_bounce_buf(struct iscsi_iser_task *iser_task,
 		iser_data_buf_dump(mem, ibdev);
 
 	/* unmap the command data before accessing it */
-	iser_dma_unmap_task_data(iser_task, mem);
+	iser_dma_unmap_task_data(iser_task, mem,
+				 (cmd_dir == ISER_DIR_OUT) ?
+				 DMA_TO_DEVICE : DMA_FROM_DEVICE);
 
 	/* allocate copy buf, if we are writing, copy the */
 	/* unaligned scatterlist, dma map the copy        */
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 67225bb82bb..d004d6ee2c1 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -567,16 +567,16 @@ void iser_release_work(struct work_struct *work)
 /**
  * iser_free_ib_conn_res - release IB related resources
  * @iser_conn: iser connection struct
- * @destroy_device: indicator if we need to try to release
- *     the iser device (only iscsi shutdown and DEVICE_REMOVAL
- *     will use this.
+ * @destroy: indicator if we need to try to release the
+ *     iser device and memory regoins pool (only iscsi
+ *     shutdown and DEVICE_REMOVAL will use this).
  *
  * This routine is called with the iser state mutex held
  * so the cm_id removal is out of here. It is Safe to
  * be invoked multiple times.
  */
 static void iser_free_ib_conn_res(struct iser_conn *iser_conn,
-				  bool destroy_device)
+				  bool destroy)
 {
 	struct ib_conn *ib_conn = &iser_conn->ib_conn;
 	struct iser_device *device = ib_conn->device;
@@ -584,17 +584,20 @@ static void iser_free_ib_conn_res(struct iser_conn *iser_conn,
 	iser_info("freeing conn %p cma_id %p qp %p\n",
 		  iser_conn, ib_conn->cma_id, ib_conn->qp);
 
-	iser_free_rx_descriptors(iser_conn);
-
 	if (ib_conn->qp != NULL) {
 		ib_conn->comp->active_qps--;
 		rdma_destroy_qp(ib_conn->cma_id);
 		ib_conn->qp = NULL;
 	}
 
-	if (destroy_device && device != NULL) {
-		iser_device_try_release(device);
-		ib_conn->device = NULL;
+	if (destroy) {
+		if (iser_conn->rx_descs)
+			iser_free_rx_descriptors(iser_conn);
+
+		if (device != NULL) {
+			iser_device_try_release(device);
+			ib_conn->device = NULL;
+		}
 	}
 }
 
@@ -803,7 +806,7 @@ static void iser_disconnected_handler(struct rdma_cm_id *cma_id)
 }
 
 static void iser_cleanup_handler(struct rdma_cm_id *cma_id,
-				 bool destroy_device)
+				 bool destroy)
 {
 	struct iser_conn *iser_conn = (struct iser_conn *)cma_id->context;
 
@@ -813,7 +816,7 @@ static void iser_cleanup_handler(struct rdma_cm_id *cma_id,
 	 * and flush errors.
 	 */
 	iser_disconnected_handler(cma_id);
-	iser_free_ib_conn_res(iser_conn, destroy_device);
+	iser_free_ib_conn_res(iser_conn, destroy);
 	complete(&iser_conn->ib_completion);
 };
 
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 10641b7816f..7b8c29b295a 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -41,6 +41,7 @@ static DEFINE_MUTEX(device_list_mutex);
 static LIST_HEAD(device_list);
 static struct workqueue_struct *isert_rx_wq;
 static struct workqueue_struct *isert_comp_wq;
+static struct workqueue_struct *isert_release_wq;
 
 static void
 isert_unmap_cmd(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn);
@@ -54,6 +55,21 @@ isert_reg_rdma(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	       struct isert_rdma_wr *wr);
 static int
 isert_put_response(struct iscsi_conn *conn, struct iscsi_cmd *cmd);
+static int
+isert_rdma_post_recvl(struct isert_conn *isert_conn);
+static int
+isert_rdma_accept(struct isert_conn *isert_conn);
+struct rdma_cm_id *isert_setup_id(struct isert_np *isert_np);
+
+static void isert_release_work(struct work_struct *work);
+
+static inline bool
+isert_prot_cmd(struct isert_conn *conn, struct se_cmd *cmd)
+{
+	return (conn->pi_support &&
+		cmd->prot_op != TARGET_PROT_NORMAL);
+}
+
 
 static void
 isert_qp_event_callback(struct ib_event *e, void *context)
@@ -90,8 +106,7 @@ isert_query_device(struct ib_device *ib_dev, struct ib_device_attr *devattr)
 }
 
 static int
-isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id,
-		    u8 protection)
+isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id)
 {
 	struct isert_device *device = isert_conn->conn_device;
 	struct ib_qp_init_attr attr;
@@ -126,7 +141,7 @@ isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id,
 	attr.cap.max_recv_sge = 1;
 	attr.sq_sig_type = IB_SIGNAL_REQ_WR;
 	attr.qp_type = IB_QPT_RC;
-	if (protection)
+	if (device->pi_capable)
 		attr.create_flags |= IB_QP_CREATE_SIGNATURE_EN;
 
 	pr_debug("isert_conn_setup_qp cma_id->device: %p\n",
@@ -137,12 +152,18 @@ isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id,
 	ret = rdma_create_qp(cma_id, isert_conn->conn_pd, &attr);
 	if (ret) {
 		pr_err("rdma_create_qp failed for cma_id %d\n", ret);
-		return ret;
+		goto err;
 	}
 	isert_conn->conn_qp = cma_id->qp;
 	pr_debug("rdma_create_qp() returned success >>>>>>>>>>>>>>>>>>>>>>>>>.\n");
 
 	return 0;
+err:
+	mutex_lock(&device_list_mutex);
+	device->cq_active_qps[min_index]--;
+	mutex_unlock(&device_list_mutex);
+
+	return ret;
 }
 
 static void
@@ -199,7 +220,7 @@ fail:
 static void
 isert_free_rx_descriptors(struct isert_conn *isert_conn)
 {
-	struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
+	struct ib_device *ib_dev = isert_conn->conn_device->ib_device;
 	struct iser_rx_desc *rx_desc;
 	int i;
 
@@ -430,8 +451,68 @@ isert_conn_free_fastreg_pool(struct isert_conn *isert_conn)
 }
 
 static int
+isert_create_pi_ctx(struct fast_reg_descriptor *desc,
+		    struct ib_device *device,
+		    struct ib_pd *pd)
+{
+	struct ib_mr_init_attr mr_init_attr;
+	struct pi_context *pi_ctx;
+	int ret;
+
+	pi_ctx = kzalloc(sizeof(*desc->pi_ctx), GFP_KERNEL);
+	if (!pi_ctx) {
+		pr_err("Failed to allocate pi context\n");
+		return -ENOMEM;
+	}
+
+	pi_ctx->prot_frpl = ib_alloc_fast_reg_page_list(device,
+					    ISCSI_ISER_SG_TABLESIZE);
+	if (IS_ERR(pi_ctx->prot_frpl)) {
+		pr_err("Failed to allocate prot frpl err=%ld\n",
+			  PTR_ERR(pi_ctx->prot_frpl));
+		ret = PTR_ERR(pi_ctx->prot_frpl);
+		goto err_pi_ctx;
+	}
+
+	pi_ctx->prot_mr = ib_alloc_fast_reg_mr(pd, ISCSI_ISER_SG_TABLESIZE);
+	if (IS_ERR(pi_ctx->prot_mr)) {
+		pr_err("Failed to allocate prot frmr err=%ld\n",
+			  PTR_ERR(pi_ctx->prot_mr));
+		ret = PTR_ERR(pi_ctx->prot_mr);
+		goto err_prot_frpl;
+	}
+	desc->ind |= ISERT_PROT_KEY_VALID;
+
+	memset(&mr_init_attr, 0, sizeof(mr_init_attr));
+	mr_init_attr.max_reg_descriptors = 2;
+	mr_init_attr.flags |= IB_MR_SIGNATURE_EN;
+	pi_ctx->sig_mr = ib_create_mr(pd, &mr_init_attr);
+	if (IS_ERR(pi_ctx->sig_mr)) {
+		pr_err("Failed to allocate signature enabled mr err=%ld\n",
+			  PTR_ERR(pi_ctx->sig_mr));
+		ret = PTR_ERR(pi_ctx->sig_mr);
+		goto err_prot_mr;
+	}
+
+	desc->pi_ctx = pi_ctx;
+	desc->ind |= ISERT_SIG_KEY_VALID;
+	desc->ind &= ~ISERT_PROTECTED;
+
+	return 0;
+
+err_prot_mr:
+	ib_dereg_mr(desc->pi_ctx->prot_mr);
+err_prot_frpl:
+	ib_free_fast_reg_page_list(desc->pi_ctx->prot_frpl);
+err_pi_ctx:
+	kfree(desc->pi_ctx);
+
+	return ret;
+}
+
+static int
 isert_create_fr_desc(struct ib_device *ib_device, struct ib_pd *pd,
-		     struct fast_reg_descriptor *fr_desc, u8 protection)
+		     struct fast_reg_descriptor *fr_desc)
 {
 	int ret;
 
@@ -450,62 +531,12 @@ isert_create_fr_desc(struct ib_device *ib_device, struct ib_pd *pd,
 		ret = PTR_ERR(fr_desc->data_mr);
 		goto err_data_frpl;
 	}
-	pr_debug("Create fr_desc %p page_list %p\n",
-		 fr_desc, fr_desc->data_frpl->page_list);
 	fr_desc->ind |= ISERT_DATA_KEY_VALID;
 
-	if (protection) {
-		struct ib_mr_init_attr mr_init_attr = {0};
-		struct pi_context *pi_ctx;
-
-		fr_desc->pi_ctx = kzalloc(sizeof(*fr_desc->pi_ctx), GFP_KERNEL);
-		if (!fr_desc->pi_ctx) {
-			pr_err("Failed to allocate pi context\n");
-			ret = -ENOMEM;
-			goto err_data_mr;
-		}
-		pi_ctx = fr_desc->pi_ctx;
-
-		pi_ctx->prot_frpl = ib_alloc_fast_reg_page_list(ib_device,
-						    ISCSI_ISER_SG_TABLESIZE);
-		if (IS_ERR(pi_ctx->prot_frpl)) {
-			pr_err("Failed to allocate prot frpl err=%ld\n",
-			       PTR_ERR(pi_ctx->prot_frpl));
-			ret = PTR_ERR(pi_ctx->prot_frpl);
-			goto err_pi_ctx;
-		}
-
-		pi_ctx->prot_mr = ib_alloc_fast_reg_mr(pd, ISCSI_ISER_SG_TABLESIZE);
-		if (IS_ERR(pi_ctx->prot_mr)) {
-			pr_err("Failed to allocate prot frmr err=%ld\n",
-			       PTR_ERR(pi_ctx->prot_mr));
-			ret = PTR_ERR(pi_ctx->prot_mr);
-			goto err_prot_frpl;
-		}
-		fr_desc->ind |= ISERT_PROT_KEY_VALID;
-
-		mr_init_attr.max_reg_descriptors = 2;
-		mr_init_attr.flags |= IB_MR_SIGNATURE_EN;
-		pi_ctx->sig_mr = ib_create_mr(pd, &mr_init_attr);
-		if (IS_ERR(pi_ctx->sig_mr)) {
-			pr_err("Failed to allocate signature enabled mr err=%ld\n",
-			       PTR_ERR(pi_ctx->sig_mr));
-			ret = PTR_ERR(pi_ctx->sig_mr);
-			goto err_prot_mr;
-		}
-		fr_desc->ind |= ISERT_SIG_KEY_VALID;
-	}
-	fr_desc->ind &= ~ISERT_PROTECTED;
+	pr_debug("Created fr_desc %p\n", fr_desc);
 
 	return 0;
-err_prot_mr:
-	ib_dereg_mr(fr_desc->pi_ctx->prot_mr);
-err_prot_frpl:
-	ib_free_fast_reg_page_list(fr_desc->pi_ctx->prot_frpl);
-err_pi_ctx:
-	kfree(fr_desc->pi_ctx);
-err_data_mr:
-	ib_dereg_mr(fr_desc->data_mr);
+
 err_data_frpl:
 	ib_free_fast_reg_page_list(fr_desc->data_frpl);
 
@@ -513,7 +544,7 @@ err_data_frpl:
 }
 
 static int
-isert_conn_create_fastreg_pool(struct isert_conn *isert_conn, u8 pi_support)
+isert_conn_create_fastreg_pool(struct isert_conn *isert_conn)
 {
 	struct fast_reg_descriptor *fr_desc;
 	struct isert_device *device = isert_conn->conn_device;
@@ -537,8 +568,7 @@ isert_conn_create_fastreg_pool(struct isert_conn *isert_conn, u8 pi_support)
 		}
 
 		ret = isert_create_fr_desc(device->ib_device,
-					   isert_conn->conn_pd, fr_desc,
-					   pi_support);
+					   isert_conn->conn_pd, fr_desc);
 		if (ret) {
 			pr_err("Failed to create fastreg descriptor err=%d\n",
 			       ret);
@@ -563,13 +593,12 @@ err:
 static int
 isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 {
-	struct iscsi_np *np = cma_id->context;
-	struct isert_np *isert_np = np->np_context;
+	struct isert_np *isert_np = cma_id->context;
+	struct iscsi_np *np = isert_np->np;
 	struct isert_conn *isert_conn;
 	struct isert_device *device;
 	struct ib_device *ib_dev = cma_id->device;
 	int ret = 0;
-	u8 pi_support;
 
 	spin_lock_bh(&np->np_thread_lock);
 	if (!np->enabled) {
@@ -590,14 +619,15 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	isert_conn->state = ISER_CONN_INIT;
 	INIT_LIST_HEAD(&isert_conn->conn_accept_node);
 	init_completion(&isert_conn->conn_login_comp);
+	init_completion(&isert_conn->login_req_comp);
 	init_completion(&isert_conn->conn_wait);
 	init_completion(&isert_conn->conn_wait_comp_err);
 	kref_init(&isert_conn->conn_kref);
 	mutex_init(&isert_conn->conn_mutex);
 	spin_lock_init(&isert_conn->conn_lock);
 	INIT_LIST_HEAD(&isert_conn->conn_fr_pool);
+	INIT_WORK(&isert_conn->release_work, isert_release_work);
 
-	cma_id->context = isert_conn;
 	isert_conn->conn_cm_id = cma_id;
 
 	isert_conn->login_buf = kzalloc(ISCSI_DEF_MAX_RECV_SEG_LEN +
@@ -669,15 +699,15 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 		goto out_mr;
 	}
 
-	pi_support = np->tpg_np->tpg->tpg_attrib.t10_pi;
-	if (pi_support && !device->pi_capable) {
-		pr_err("Protection information requested but not supported, "
-		       "rejecting connect request\n");
-		ret = rdma_reject(cma_id, NULL, 0);
-		goto out_mr;
-	}
+	ret = isert_conn_setup_qp(isert_conn, cma_id);
+	if (ret)
+		goto out_conn_dev;
+
+	ret = isert_rdma_post_recvl(isert_conn);
+	if (ret)
+		goto out_conn_dev;
 
-	ret = isert_conn_setup_qp(isert_conn, cma_id, pi_support);
+	ret = isert_rdma_accept(isert_conn);
 	if (ret)
 		goto out_conn_dev;
 
@@ -705,33 +735,37 @@ out_login_buf:
 	kfree(isert_conn->login_buf);
 out:
 	kfree(isert_conn);
+	rdma_reject(cma_id, NULL, 0);
 	return ret;
 }
 
 static void
 isert_connect_release(struct isert_conn *isert_conn)
 {
-	struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
 	struct isert_device *device = isert_conn->conn_device;
 	int cq_index;
+	struct ib_device *ib_dev = device->ib_device;
 
 	pr_debug("Entering isert_connect_release(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n");
 
 	if (device && device->use_fastreg)
 		isert_conn_free_fastreg_pool(isert_conn);
 
+	isert_free_rx_descriptors(isert_conn);
+	if (isert_conn->conn_cm_id)
+		rdma_destroy_id(isert_conn->conn_cm_id);
+
 	if (isert_conn->conn_qp) {
 		cq_index = ((struct isert_cq_desc *)
 			isert_conn->conn_qp->recv_cq->cq_context)->cq_index;
 		pr_debug("isert_connect_release: cq_index: %d\n", cq_index);
+		mutex_lock(&device_list_mutex);
 		isert_conn->conn_device->cq_active_qps[cq_index]--;
+		mutex_unlock(&device_list_mutex);
 
-		rdma_destroy_qp(isert_conn->conn_cm_id);
+		ib_destroy_qp(isert_conn->conn_qp);
 	}
 
-	isert_free_rx_descriptors(isert_conn);
-	rdma_destroy_id(isert_conn->conn_cm_id);
-
 	ib_dereg_mr(isert_conn->conn_mr);
 	ib_dealloc_pd(isert_conn->conn_pd);
 
@@ -754,9 +788,19 @@ isert_connect_release(struct isert_conn *isert_conn)
 static void
 isert_connected_handler(struct rdma_cm_id *cma_id)
 {
-	struct isert_conn *isert_conn = cma_id->context;
+	struct isert_conn *isert_conn = cma_id->qp->qp_context;
+
+	pr_info("conn %p\n", isert_conn);
 
-	kref_get(&isert_conn->conn_kref);
+	if (!kref_get_unless_zero(&isert_conn->conn_kref)) {
+		pr_warn("conn %p connect_release is running\n", isert_conn);
+		return;
+	}
+
+	mutex_lock(&isert_conn->conn_mutex);
+	if (isert_conn->state != ISER_CONN_FULL_FEATURE)
+		isert_conn->state = ISER_CONN_UP;
+	mutex_unlock(&isert_conn->conn_mutex);
 }
 
 static void
@@ -777,65 +821,125 @@ isert_put_conn(struct isert_conn *isert_conn)
 	kref_put(&isert_conn->conn_kref, isert_release_conn_kref);
 }
 
+/**
+ * isert_conn_terminate() - Initiate connection termination
+ * @isert_conn: isert connection struct
+ *
+ * Notes:
+ * In case the connection state is FULL_FEATURE, move state
+ * to TEMINATING and start teardown sequence (rdma_disconnect).
+ * In case the connection state is UP, complete flush as well.
+ *
+ * This routine must be called with conn_mutex held. Thus it is
+ * safe to call multiple times.
+ */
 static void
-isert_disconnect_work(struct work_struct *work)
+isert_conn_terminate(struct isert_conn *isert_conn)
 {
-	struct isert_conn *isert_conn = container_of(work,
-				struct isert_conn, conn_logout_work);
+	int err;
 
-	pr_debug("isert_disconnect_work(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n");
-	mutex_lock(&isert_conn->conn_mutex);
-	if (isert_conn->state == ISER_CONN_UP)
+	switch (isert_conn->state) {
+	case ISER_CONN_TERMINATING:
+		break;
+	case ISER_CONN_UP:
+		/*
+		 * No flush completions will occur as we didn't
+		 * get to ISER_CONN_FULL_FEATURE yet, complete
+		 * to allow teardown progress.
+		 */
+		complete(&isert_conn->conn_wait_comp_err);
+	case ISER_CONN_FULL_FEATURE: /* FALLTHRU */
+		pr_info("Terminating conn %p state %d\n",
+			   isert_conn, isert_conn->state);
 		isert_conn->state = ISER_CONN_TERMINATING;
-
-	if (isert_conn->post_recv_buf_count == 0 &&
-	    atomic_read(&isert_conn->post_send_buf_count) == 0) {
-		mutex_unlock(&isert_conn->conn_mutex);
-		goto wake_up;
-	}
-	if (!isert_conn->conn_cm_id) {
-		mutex_unlock(&isert_conn->conn_mutex);
-		isert_put_conn(isert_conn);
-		return;
+		err = rdma_disconnect(isert_conn->conn_cm_id);
+		if (err)
+			pr_warn("Failed rdma_disconnect isert_conn %p\n",
+				   isert_conn);
+		break;
+	default:
+		pr_warn("conn %p teminating in state %d\n",
+			   isert_conn, isert_conn->state);
 	}
+}
 
-	if (isert_conn->disconnect) {
-		/* Send DREQ/DREP towards our initiator */
-		rdma_disconnect(isert_conn->conn_cm_id);
-	}
+static int
+isert_np_cma_handler(struct isert_np *isert_np,
+		     enum rdma_cm_event_type event)
+{
+	pr_debug("isert np %p, handling event %d\n", isert_np, event);
 
-	mutex_unlock(&isert_conn->conn_mutex);
+	switch (event) {
+	case RDMA_CM_EVENT_DEVICE_REMOVAL:
+		isert_np->np_cm_id = NULL;
+		break;
+	case RDMA_CM_EVENT_ADDR_CHANGE:
+		isert_np->np_cm_id = isert_setup_id(isert_np);
+		if (IS_ERR(isert_np->np_cm_id)) {
+			pr_err("isert np %p setup id failed: %ld\n",
+				 isert_np, PTR_ERR(isert_np->np_cm_id));
+			isert_np->np_cm_id = NULL;
+		}
+		break;
+	default:
+		pr_err("isert np %p Unexpected event %d\n",
+			  isert_np, event);
+	}
 
-wake_up:
-	complete(&isert_conn->conn_wait);
+	return -1;
 }
 
 static int
-isert_disconnected_handler(struct rdma_cm_id *cma_id, bool disconnect)
+isert_disconnected_handler(struct rdma_cm_id *cma_id,
+			   enum rdma_cm_event_type event)
 {
+	struct isert_np *isert_np = cma_id->context;
 	struct isert_conn *isert_conn;
+	bool terminating = false;
 
-	if (!cma_id->qp) {
-		struct isert_np *isert_np = cma_id->context;
+	if (isert_np->np_cm_id == cma_id)
+		return isert_np_cma_handler(cma_id->context, event);
 
-		isert_np->np_cm_id = NULL;
-		return -1;
-	}
+	isert_conn = cma_id->qp->qp_context;
 
-	isert_conn = (struct isert_conn *)cma_id->context;
+	mutex_lock(&isert_conn->conn_mutex);
+	terminating = (isert_conn->state == ISER_CONN_TERMINATING);
+	isert_conn_terminate(isert_conn);
+	mutex_unlock(&isert_conn->conn_mutex);
+
+	pr_info("conn %p completing conn_wait\n", isert_conn);
+	complete(&isert_conn->conn_wait);
 
-	isert_conn->disconnect = disconnect;
-	INIT_WORK(&isert_conn->conn_logout_work, isert_disconnect_work);
-	schedule_work(&isert_conn->conn_logout_work);
+	if (terminating)
+		goto out;
+
+	mutex_lock(&isert_np->np_accept_mutex);
+	if (!list_empty(&isert_conn->conn_accept_node)) {
+		list_del_init(&isert_conn->conn_accept_node);
+		isert_put_conn(isert_conn);
+		queue_work(isert_release_wq, &isert_conn->release_work);
+	}
+	mutex_unlock(&isert_np->np_accept_mutex);
 
+out:
 	return 0;
 }
 
 static int
+isert_connect_error(struct rdma_cm_id *cma_id)
+{
+	struct isert_conn *isert_conn = cma_id->qp->qp_context;
+
+	isert_conn->conn_cm_id = NULL;
+	isert_put_conn(isert_conn);
+
+	return -1;
+}
+
+static int
 isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 {
 	int ret = 0;
-	bool disconnect = false;
 
 	pr_debug("isert_cma_handler: event %d status %d conn %p id %p\n",
 		 event->event, event->status, cma_id->context, cma_id);
@@ -853,11 +957,14 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	case RDMA_CM_EVENT_ADDR_CHANGE:    /* FALLTHRU */
 	case RDMA_CM_EVENT_DISCONNECTED:   /* FALLTHRU */
 	case RDMA_CM_EVENT_DEVICE_REMOVAL: /* FALLTHRU */
-		disconnect = true;
 	case RDMA_CM_EVENT_TIMEWAIT_EXIT:  /* FALLTHRU */
-		ret = isert_disconnected_handler(cma_id, disconnect);
+		ret = isert_disconnected_handler(cma_id, event->event);
 		break;
+	case RDMA_CM_EVENT_REJECTED:       /* FALLTHRU */
+	case RDMA_CM_EVENT_UNREACHABLE:    /* FALLTHRU */
 	case RDMA_CM_EVENT_CONNECT_ERROR:
+		ret = isert_connect_error(cma_id);
+		break;
 	default:
 		pr_err("Unhandled RDMA CMA event: %d\n", event->event);
 		break;
@@ -991,7 +1098,7 @@ isert_init_send_wr(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd,
 	 * bit for every ISERT_COMP_BATCH_COUNT number of ib_post_send() calls.
 	 */
 	mutex_lock(&isert_conn->conn_mutex);
-	if (coalesce && isert_conn->state == ISER_CONN_UP &&
+	if (coalesce && isert_conn->state == ISER_CONN_FULL_FEATURE &&
 	    ++isert_conn->conn_comp_batch < ISERT_COMP_BATCH_COUNT) {
 		tx_desc->llnode_active = true;
 		llist_add(&tx_desc->comp_llnode, &isert_conn->conn_comp_llist);
@@ -1072,11 +1179,7 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login,
 		if (login->login_complete) {
 			if (!conn->sess->sess_ops->SessionType &&
 			    isert_conn->conn_device->use_fastreg) {
-				/* Normal Session and fastreg is used */
-				u8 pi_support = login->np->tpg_np->tpg->tpg_attrib.t10_pi;
-
-				ret = isert_conn_create_fastreg_pool(isert_conn,
-								     pi_support);
+				ret = isert_conn_create_fastreg_pool(isert_conn);
 				if (ret) {
 					pr_err("Conn: %p failed to create"
 					       " fastreg pool\n", isert_conn);
@@ -1092,7 +1195,10 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login,
 			if (ret)
 				return ret;
 
-			isert_conn->state = ISER_CONN_UP;
+			/* Now we are in FULL_FEATURE phase */
+			mutex_lock(&isert_conn->conn_mutex);
+			isert_conn->state = ISER_CONN_FULL_FEATURE;
+			mutex_unlock(&isert_conn->conn_mutex);
 			goto post_send;
 		}
 
@@ -1109,18 +1215,17 @@ post_send:
 }
 
 static void
-isert_rx_login_req(struct iser_rx_desc *rx_desc, int rx_buflen,
-		   struct isert_conn *isert_conn)
+isert_rx_login_req(struct isert_conn *isert_conn)
 {
+	struct iser_rx_desc *rx_desc = (void *)isert_conn->login_req_buf;
+	int rx_buflen = isert_conn->login_req_len;
 	struct iscsi_conn *conn = isert_conn->conn;
 	struct iscsi_login *login = conn->conn_login;
 	int size;
 
-	if (!login) {
-		pr_err("conn->conn_login is NULL\n");
-		dump_stack();
-		return;
-	}
+	pr_info("conn %p\n", isert_conn);
+
+	WARN_ON_ONCE(!login);
 
 	if (login->first_request) {
 		struct iscsi_login_req *login_req =
@@ -1483,11 +1588,20 @@ isert_rx_completion(struct iser_rx_desc *desc, struct isert_conn *isert_conn,
 		 hdr->opcode, hdr->itt, hdr->flags,
 		 (int)(xfer_len - ISER_HEADERS_LEN));
 
-	if ((char *)desc == isert_conn->login_req_buf)
-		isert_rx_login_req(desc, xfer_len - ISER_HEADERS_LEN,
-				   isert_conn);
-	else
+	if ((char *)desc == isert_conn->login_req_buf) {
+		isert_conn->login_req_len = xfer_len - ISER_HEADERS_LEN;
+		if (isert_conn->conn) {
+			struct iscsi_login *login = isert_conn->conn->conn_login;
+
+			if (login && !login->first_request)
+				isert_rx_login_req(isert_conn);
+		}
+		mutex_lock(&isert_conn->conn_mutex);
+		complete(&isert_conn->login_req_comp);
+		mutex_unlock(&isert_conn->conn_mutex);
+	} else {
 		isert_rx_do_work(desc, isert_conn);
+	}
 
 	ib_dma_sync_single_for_device(ib_dev, rx_dma, rx_buflen,
 				      DMA_FROM_DEVICE);
@@ -1807,11 +1921,13 @@ isert_completion_rdma_read(struct iser_tx_desc *tx_desc,
 	cmd->i_state = ISTATE_RECEIVED_LAST_DATAOUT;
 	spin_unlock_bh(&cmd->istate_lock);
 
-	if (ret)
+	if (ret) {
+		target_put_sess_cmd(se_cmd->se_sess, se_cmd);
 		transport_send_check_condition_and_sense(se_cmd,
 							 se_cmd->pi_err, 0);
-	else
+	} else {
 		target_execute_cmd(se_cmd);
+	}
 }
 
 static void
@@ -2046,7 +2162,7 @@ isert_cq_rx_comp_err(struct isert_conn *isert_conn)
 		msleep(3000);
 
 	mutex_lock(&isert_conn->conn_mutex);
-	isert_conn->state = ISER_CONN_DOWN;
+	isert_conn_terminate(isert_conn);
 	mutex_unlock(&isert_conn->conn_mutex);
 
 	iscsit_cause_connection_reinstatement(isert_conn->conn, 0);
@@ -2231,8 +2347,16 @@ isert_get_sup_prot_ops(struct iscsi_conn *conn)
 	struct isert_conn *isert_conn = (struct isert_conn *)conn->context;
 	struct isert_device *device = isert_conn->conn_device;
 
-	if (device->pi_capable)
-		return TARGET_PROT_ALL;
+	if (conn->tpg->tpg_attrib.t10_pi) {
+		if (device->pi_capable) {
+			pr_info("conn %p PI offload enabled\n", isert_conn);
+			isert_conn->pi_support = true;
+			return TARGET_PROT_ALL;
+		}
+	}
+
+	pr_info("conn %p PI offload disabled\n", isert_conn);
+	isert_conn->pi_support = false;
 
 	return TARGET_PROT_NORMAL;
 }
@@ -2382,7 +2506,6 @@ isert_build_rdma_wr(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd,
 	page_off = offset % PAGE_SIZE;
 
 	send_wr->sg_list = ib_sge;
-	send_wr->num_sge = sg_nents;
 	send_wr->wr_id = (unsigned long)&isert_cmd->tx_desc;
 	/*
 	 * Perform mapping of TCM scatterlist memory ib_sge dma_addr.
@@ -2401,14 +2524,17 @@ isert_build_rdma_wr(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd,
 			 ib_sge->addr, ib_sge->length, ib_sge->lkey);
 		page_off = 0;
 		data_left -= ib_sge->length;
+		if (!data_left)
+			break;
 		ib_sge++;
 		pr_debug("Incrementing ib_sge pointer to %p\n", ib_sge);
 	}
 
+	send_wr->num_sge = ++i;
 	pr_debug("Set outgoing sg_list: %p num_sg: %u from TCM SGLs\n",
 		 send_wr->sg_list, send_wr->num_sge);
 
-	return sg_nents;
+	return send_wr->num_sge;
 }
 
 static int
@@ -2681,10 +2807,10 @@ isert_set_prot_checks(u8 prot_checks)
 }
 
 static int
-isert_reg_sig_mr(struct isert_conn *isert_conn, struct se_cmd *se_cmd,
-		 struct fast_reg_descriptor *fr_desc,
-		 struct ib_sge *data_sge, struct ib_sge *prot_sge,
-		 struct ib_sge *sig_sge)
+isert_reg_sig_mr(struct isert_conn *isert_conn,
+		 struct se_cmd *se_cmd,
+		 struct isert_rdma_wr *rdma_wr,
+		 struct fast_reg_descriptor *fr_desc)
 {
 	struct ib_send_wr sig_wr, inv_wr;
 	struct ib_send_wr *bad_wr, *wr = NULL;
@@ -2714,13 +2840,13 @@ isert_reg_sig_mr(struct isert_conn *isert_conn, struct se_cmd *se_cmd,
 	memset(&sig_wr, 0, sizeof(sig_wr));
 	sig_wr.opcode = IB_WR_REG_SIG_MR;
 	sig_wr.wr_id = ISER_FASTREG_LI_WRID;
-	sig_wr.sg_list = data_sge;
+	sig_wr.sg_list = &rdma_wr->ib_sg[DATA];
 	sig_wr.num_sge = 1;
 	sig_wr.wr.sig_handover.access_flags = IB_ACCESS_LOCAL_WRITE;
 	sig_wr.wr.sig_handover.sig_attrs = &sig_attrs;
 	sig_wr.wr.sig_handover.sig_mr = pi_ctx->sig_mr;
 	if (se_cmd->t_prot_sg)
-		sig_wr.wr.sig_handover.prot = prot_sge;
+		sig_wr.wr.sig_handover.prot = &rdma_wr->ib_sg[PROT];
 
 	if (!wr)
 		wr = &sig_wr;
@@ -2734,34 +2860,93 @@ isert_reg_sig_mr(struct isert_conn *isert_conn, struct se_cmd *se_cmd,
 	}
 	fr_desc->ind &= ~ISERT_SIG_KEY_VALID;
 
-	sig_sge->lkey = pi_ctx->sig_mr->lkey;
-	sig_sge->addr = 0;
-	sig_sge->length = se_cmd->data_length;
+	rdma_wr->ib_sg[SIG].lkey = pi_ctx->sig_mr->lkey;
+	rdma_wr->ib_sg[SIG].addr = 0;
+	rdma_wr->ib_sg[SIG].length = se_cmd->data_length;
 	if (se_cmd->prot_op != TARGET_PROT_DIN_STRIP &&
 	    se_cmd->prot_op != TARGET_PROT_DOUT_INSERT)
 		/*
 		 * We have protection guards on the wire
 		 * so we need to set a larget transfer
 		 */
-		sig_sge->length += se_cmd->prot_length;
+		rdma_wr->ib_sg[SIG].length += se_cmd->prot_length;
 
 	pr_debug("sig_sge: addr: 0x%llx  length: %u lkey: %x\n",
-		 sig_sge->addr, sig_sge->length,
-		 sig_sge->lkey);
+		  rdma_wr->ib_sg[SIG].addr, rdma_wr->ib_sg[SIG].length,
+		  rdma_wr->ib_sg[SIG].lkey);
 err:
 	return ret;
 }
 
 static int
+isert_handle_prot_cmd(struct isert_conn *isert_conn,
+		      struct isert_cmd *isert_cmd,
+		      struct isert_rdma_wr *wr)
+{
+	struct isert_device *device = isert_conn->conn_device;
+	struct se_cmd *se_cmd = &isert_cmd->iscsi_cmd->se_cmd;
+	int ret;
+
+	if (!wr->fr_desc->pi_ctx) {
+		ret = isert_create_pi_ctx(wr->fr_desc,
+					  device->ib_device,
+					  isert_conn->conn_pd);
+		if (ret) {
+			pr_err("conn %p failed to allocate pi_ctx\n",
+				  isert_conn);
+			return ret;
+		}
+	}
+
+	if (se_cmd->t_prot_sg) {
+		ret = isert_map_data_buf(isert_conn, isert_cmd,
+					 se_cmd->t_prot_sg,
+					 se_cmd->t_prot_nents,
+					 se_cmd->prot_length,
+					 0, wr->iser_ib_op, &wr->prot);
+		if (ret) {
+			pr_err("conn %p failed to map protection buffer\n",
+				  isert_conn);
+			return ret;
+		}
+
+		memset(&wr->ib_sg[PROT], 0, sizeof(wr->ib_sg[PROT]));
+		ret = isert_fast_reg_mr(isert_conn, wr->fr_desc, &wr->prot,
+					ISERT_PROT_KEY_VALID, &wr->ib_sg[PROT]);
+		if (ret) {
+			pr_err("conn %p failed to fast reg mr\n",
+				  isert_conn);
+			goto unmap_prot_cmd;
+		}
+	}
+
+	ret = isert_reg_sig_mr(isert_conn, se_cmd, wr, wr->fr_desc);
+	if (ret) {
+		pr_err("conn %p failed to fast reg mr\n",
+			  isert_conn);
+		goto unmap_prot_cmd;
+	}
+	wr->fr_desc->ind |= ISERT_PROTECTED;
+
+	return 0;
+
+unmap_prot_cmd:
+	if (se_cmd->t_prot_sg)
+		isert_unmap_data_buf(isert_conn, &wr->prot);
+
+	return ret;
+}
+
+static int
 isert_reg_rdma(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	       struct isert_rdma_wr *wr)
 {
 	struct se_cmd *se_cmd = &cmd->se_cmd;
 	struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
 	struct isert_conn *isert_conn = conn->context;
-	struct ib_sge data_sge;
-	struct ib_send_wr *send_wr;
 	struct fast_reg_descriptor *fr_desc = NULL;
+	struct ib_send_wr *send_wr;
+	struct ib_sge *ib_sg;
 	u32 offset;
 	int ret = 0;
 	unsigned long flags;
@@ -2775,8 +2960,7 @@ isert_reg_rdma(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	if (ret)
 		return ret;
 
-	if (wr->data.dma_nents != 1 ||
-	    se_cmd->prot_op != TARGET_PROT_NORMAL) {
+	if (wr->data.dma_nents != 1 || isert_prot_cmd(isert_conn, se_cmd)) {
 		spin_lock_irqsave(&isert_conn->conn_lock, flags);
 		fr_desc = list_first_entry(&isert_conn->conn_fr_pool,
 					   struct fast_reg_descriptor, list);
@@ -2786,38 +2970,21 @@ isert_reg_rdma(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	}
 
 	ret = isert_fast_reg_mr(isert_conn, fr_desc, &wr->data,
-				ISERT_DATA_KEY_VALID, &data_sge);
+				ISERT_DATA_KEY_VALID, &wr->ib_sg[DATA]);
 	if (ret)
 		goto unmap_cmd;
 
-	if (se_cmd->prot_op != TARGET_PROT_NORMAL) {
-		struct ib_sge prot_sge, sig_sge;
-
-		if (se_cmd->t_prot_sg) {
-			ret = isert_map_data_buf(isert_conn, isert_cmd,
-						 se_cmd->t_prot_sg,
-						 se_cmd->t_prot_nents,
-						 se_cmd->prot_length,
-						 0, wr->iser_ib_op, &wr->prot);
-			if (ret)
-				goto unmap_cmd;
-
-			ret = isert_fast_reg_mr(isert_conn, fr_desc, &wr->prot,
-						ISERT_PROT_KEY_VALID, &prot_sge);
-			if (ret)
-				goto unmap_prot_cmd;
-		}
-
-		ret = isert_reg_sig_mr(isert_conn, se_cmd, fr_desc,
-				       &data_sge, &prot_sge, &sig_sge);
+	if (isert_prot_cmd(isert_conn, se_cmd)) {
+		ret = isert_handle_prot_cmd(isert_conn, isert_cmd, wr);
 		if (ret)
-			goto unmap_prot_cmd;
+			goto unmap_cmd;
 
-		fr_desc->ind |= ISERT_PROTECTED;
-		memcpy(&wr->s_ib_sge, &sig_sge, sizeof(sig_sge));
-	} else
-		memcpy(&wr->s_ib_sge, &data_sge, sizeof(data_sge));
+		ib_sg = &wr->ib_sg[SIG];
+	} else {
+		ib_sg = &wr->ib_sg[DATA];
+	}
 
+	memcpy(&wr->s_ib_sge, ib_sg, sizeof(*ib_sg));
 	wr->ib_sge = &wr->s_ib_sge;
 	wr->send_wr_num = 1;
 	memset(&wr->s_send_wr, 0, sizeof(*send_wr));
@@ -2832,7 +2999,7 @@ isert_reg_rdma(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 		send_wr->opcode = IB_WR_RDMA_WRITE;
 		send_wr->wr.rdma.remote_addr = isert_cmd->read_va;
 		send_wr->wr.rdma.rkey = isert_cmd->read_stag;
-		send_wr->send_flags = se_cmd->prot_op == TARGET_PROT_NORMAL ?
+		send_wr->send_flags = !isert_prot_cmd(isert_conn, se_cmd) ?
 				      0 : IB_SEND_SIGNALED;
 	} else {
 		send_wr->opcode = IB_WR_RDMA_READ;
@@ -2842,9 +3009,7 @@ isert_reg_rdma(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	}
 
 	return 0;
-unmap_prot_cmd:
-	if (se_cmd->t_prot_sg)
-		isert_unmap_data_buf(isert_conn, &wr->prot);
+
 unmap_cmd:
 	if (fr_desc) {
 		spin_lock_irqsave(&isert_conn->conn_lock, flags);
@@ -2876,7 +3041,7 @@ isert_put_datain(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
 		return rc;
 	}
 
-	if (se_cmd->prot_op == TARGET_PROT_NORMAL) {
+	if (!isert_prot_cmd(isert_conn, se_cmd)) {
 		/*
 		 * Build isert_conn->tx_desc for iSCSI response PDU and attach
 		 */
@@ -2899,7 +3064,7 @@ isert_put_datain(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
 		atomic_sub(wr->send_wr_num, &isert_conn->post_send_buf_count);
 	}
 
-	if (se_cmd->prot_op == TARGET_PROT_NORMAL)
+	if (!isert_prot_cmd(isert_conn, se_cmd))
 		pr_debug("Cmd: %p posted RDMA_WRITE + Response for iSER Data "
 			 "READ\n", isert_cmd);
 	else
@@ -3001,13 +3166,51 @@ isert_response_queue(struct iscsi_conn *conn, struct iscsi_cmd *cmd, int state)
 	return ret;
 }
 
+struct rdma_cm_id *
+isert_setup_id(struct isert_np *isert_np)
+{
+	struct iscsi_np *np = isert_np->np;
+	struct rdma_cm_id *id;
+	struct sockaddr *sa;
+	int ret;
+
+	sa = (struct sockaddr *)&np->np_sockaddr;
+	pr_debug("ksockaddr: %p, sa: %p\n", &np->np_sockaddr, sa);
+
+	id = rdma_create_id(isert_cma_handler, isert_np,
+			    RDMA_PS_TCP, IB_QPT_RC);
+	if (IS_ERR(id)) {
+		pr_err("rdma_create_id() failed: %ld\n", PTR_ERR(id));
+		ret = PTR_ERR(id);
+		goto out;
+	}
+	pr_debug("id %p context %p\n", id, id->context);
+
+	ret = rdma_bind_addr(id, sa);
+	if (ret) {
+		pr_err("rdma_bind_addr() failed: %d\n", ret);
+		goto out_id;
+	}
+
+	ret = rdma_listen(id, ISERT_RDMA_LISTEN_BACKLOG);
+	if (ret) {
+		pr_err("rdma_listen() failed: %d\n", ret);
+		goto out_id;
+	}
+
+	return id;
+out_id:
+	rdma_destroy_id(id);
+out:
+	return ERR_PTR(ret);
+}
+
 static int
 isert_setup_np(struct iscsi_np *np,
 	       struct __kernel_sockaddr_storage *ksockaddr)
 {
 	struct isert_np *isert_np;
 	struct rdma_cm_id *isert_lid;
-	struct sockaddr *sa;
 	int ret;
 
 	isert_np = kzalloc(sizeof(struct isert_np), GFP_KERNEL);
@@ -3019,9 +3222,8 @@ isert_setup_np(struct iscsi_np *np,
 	mutex_init(&isert_np->np_accept_mutex);
 	INIT_LIST_HEAD(&isert_np->np_accept_list);
 	init_completion(&isert_np->np_login_comp);
+	isert_np->np = np;
 
-	sa = (struct sockaddr *)ksockaddr;
-	pr_debug("ksockaddr: %p, sa: %p\n", ksockaddr, sa);
 	/*
 	 * Setup the np->np_sockaddr from the passed sockaddr setup
 	 * in iscsi_target_configfs.c code..
@@ -3029,37 +3231,20 @@ isert_setup_np(struct iscsi_np *np,
 	memcpy(&np->np_sockaddr, ksockaddr,
 	       sizeof(struct __kernel_sockaddr_storage));
 
-	isert_lid = rdma_create_id(isert_cma_handler, np, RDMA_PS_TCP,
-				IB_QPT_RC);
+	isert_lid = isert_setup_id(isert_np);
 	if (IS_ERR(isert_lid)) {
-		pr_err("rdma_create_id() for isert_listen_handler failed: %ld\n",
-		       PTR_ERR(isert_lid));
 		ret = PTR_ERR(isert_lid);
 		goto out;
 	}
 
-	ret = rdma_bind_addr(isert_lid, sa);
-	if (ret) {
-		pr_err("rdma_bind_addr() for isert_lid failed: %d\n", ret);
-		goto out_lid;
-	}
-
-	ret = rdma_listen(isert_lid, ISERT_RDMA_LISTEN_BACKLOG);
-	if (ret) {
-		pr_err("rdma_listen() for isert_lid failed: %d\n", ret);
-		goto out_lid;
-	}
-
 	isert_np->np_cm_id = isert_lid;
 	np->np_context = isert_np;
-	pr_debug("Setup isert_lid->context: %p\n", isert_lid->context);
 
 	return 0;
 
-out_lid:
-	rdma_destroy_id(isert_lid);
 out:
 	kfree(isert_np);
+
 	return ret;
 }
 
@@ -3094,7 +3279,15 @@ isert_get_login_rx(struct iscsi_conn *conn, struct iscsi_login *login)
 	struct isert_conn *isert_conn = (struct isert_conn *)conn->context;
 	int ret;
 
-	pr_debug("isert_get_login_rx before conn_login_comp conn: %p\n", conn);
+	pr_info("before login_req comp conn: %p\n", isert_conn);
+	ret = wait_for_completion_interruptible(&isert_conn->login_req_comp);
+	if (ret) {
+		pr_err("isert_conn %p interrupted before got login req\n",
+			  isert_conn);
+		return ret;
+	}
+	reinit_completion(&isert_conn->login_req_comp);
+
 	/*
 	 * For login requests after the first PDU, isert_rx_login_req() will
 	 * kick schedule_delayed_work(&conn->login_work) as the packet is
@@ -3104,11 +3297,15 @@ isert_get_login_rx(struct iscsi_conn *conn, struct iscsi_login *login)
 	if (!login->first_request)
 		return 0;
 
+	isert_rx_login_req(isert_conn);
+
+	pr_info("before conn_login_comp conn: %p\n", conn);
 	ret = wait_for_completion_interruptible(&isert_conn->conn_login_comp);
 	if (ret)
 		return ret;
 
-	pr_debug("isert_get_login_rx processing login->req: %p\n", login->req);
+	pr_info("processing login->req: %p\n", login->req);
+
 	return 0;
 }
 
@@ -3186,17 +3383,10 @@ accept_wait:
 	isert_conn->conn = conn;
 	max_accept = 0;
 
-	ret = isert_rdma_post_recvl(isert_conn);
-	if (ret)
-		return ret;
-
-	ret = isert_rdma_accept(isert_conn);
-	if (ret)
-		return ret;
-
 	isert_set_conn_info(np, conn, isert_conn);
 
-	pr_debug("Processing isert_accept_np: isert_conn: %p\n", isert_conn);
+	pr_debug("Processing isert_conn: %p\n", isert_conn);
+
 	return 0;
 }
 
@@ -3212,6 +3402,24 @@ isert_free_np(struct iscsi_np *np)
 	kfree(isert_np);
 }
 
+static void isert_release_work(struct work_struct *work)
+{
+	struct isert_conn *isert_conn = container_of(work,
+						     struct isert_conn,
+						     release_work);
+
+	pr_info("Starting release conn %p\n", isert_conn);
+
+	wait_for_completion(&isert_conn->conn_wait);
+
+	mutex_lock(&isert_conn->conn_mutex);
+	isert_conn->state = ISER_CONN_DOWN;
+	mutex_unlock(&isert_conn->conn_mutex);
+
+	pr_info("Destroying conn %p\n", isert_conn);
+	isert_put_conn(isert_conn);
+}
+
 static void isert_wait_conn(struct iscsi_conn *conn)
 {
 	struct isert_conn *isert_conn = conn->context;
@@ -3219,10 +3427,6 @@ static void isert_wait_conn(struct iscsi_conn *conn)
 	pr_debug("isert_wait_conn: Starting \n");
 
 	mutex_lock(&isert_conn->conn_mutex);
-	if (isert_conn->conn_cm_id && !isert_conn->disconnect) {
-		pr_debug("Calling rdma_disconnect from isert_wait_conn\n");
-		rdma_disconnect(isert_conn->conn_cm_id);
-	}
 	/*
 	 * Only wait for conn_wait_comp_err if the isert_conn made it
 	 * into full feature phase..
@@ -3231,14 +3435,12 @@ static void isert_wait_conn(struct iscsi_conn *conn)
 		mutex_unlock(&isert_conn->conn_mutex);
 		return;
 	}
-	if (isert_conn->state == ISER_CONN_UP)
-		isert_conn->state = ISER_CONN_TERMINATING;
+	isert_conn_terminate(isert_conn);
 	mutex_unlock(&isert_conn->conn_mutex);
 
 	wait_for_completion(&isert_conn->conn_wait_comp_err);
 
-	wait_for_completion(&isert_conn->conn_wait);
-	isert_put_conn(isert_conn);
+	queue_work(isert_release_wq, &isert_conn->release_work);
 }
 
 static void isert_free_conn(struct iscsi_conn *conn)
@@ -3286,10 +3488,21 @@ static int __init isert_init(void)
 		goto destroy_rx_wq;
 	}
 
+	isert_release_wq = alloc_workqueue("isert_release_wq", WQ_UNBOUND,
+					WQ_UNBOUND_MAX_ACTIVE);
+	if (!isert_release_wq) {
+		pr_err("Unable to allocate isert_release_wq\n");
+		ret = -ENOMEM;
+		goto destroy_comp_wq;
+	}
+
 	iscsit_register_transport(&iser_target_transport);
-	pr_debug("iSER_TARGET[0] - Loaded iser_target_transport\n");
+	pr_info("iSER_TARGET[0] - Loaded iser_target_transport\n");
+
 	return 0;
 
+destroy_comp_wq:
+	destroy_workqueue(isert_comp_wq);
 destroy_rx_wq:
 	destroy_workqueue(isert_rx_wq);
 	return ret;
@@ -3298,6 +3511,7 @@ destroy_rx_wq:
 static void __exit isert_exit(void)
 {
 	flush_scheduled_work();
+	destroy_workqueue(isert_release_wq);
 	destroy_workqueue(isert_comp_wq);
 	destroy_workqueue(isert_rx_wq);
 	iscsit_unregister_transport(&iser_target_transport);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index 04f51f7bf61..141905f446d 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -23,6 +23,7 @@ enum iser_ib_op_code {
 enum iser_conn_state {
 	ISER_CONN_INIT,
 	ISER_CONN_UP,
+	ISER_CONN_FULL_FEATURE,
 	ISER_CONN_TERMINATING,
 	ISER_CONN_DOWN,
 };
@@ -81,6 +82,12 @@ struct isert_data_buf {
 	enum dma_data_direction dma_dir;
 };
 
+enum {
+	DATA = 0,
+	PROT = 1,
+	SIG = 2,
+};
+
 struct isert_rdma_wr {
 	struct list_head	wr_list;
 	struct isert_cmd	*isert_cmd;
@@ -90,6 +97,7 @@ struct isert_rdma_wr {
 	int			send_wr_num;
 	struct ib_send_wr	*send_wr;
 	struct ib_send_wr	s_send_wr;
+	struct ib_sge		ib_sg[3];
 	struct isert_data_buf	data;
 	struct isert_data_buf	prot;
 	struct fast_reg_descriptor *fr_desc;
@@ -120,11 +128,13 @@ struct isert_conn {
 	atomic_t		post_send_buf_count;
 	u32			responder_resources;
 	u32			initiator_depth;
+	bool			pi_support;
 	u32			max_sge;
 	char			*login_buf;
 	char			*login_req_buf;
 	char			*login_rsp_buf;
 	u64			login_req_dma;
+	int			login_req_len;
 	u64			login_rsp_dma;
 	unsigned int		conn_rx_desc_head;
 	struct iser_rx_desc	*conn_rx_descs;
@@ -132,13 +142,13 @@ struct isert_conn {
 	struct iscsi_conn	*conn;
 	struct list_head	conn_accept_node;
 	struct completion	conn_login_comp;
+	struct completion	login_req_comp;
 	struct iser_tx_desc	conn_login_tx_desc;
 	struct rdma_cm_id	*conn_cm_id;
 	struct ib_pd		*conn_pd;
 	struct ib_mr		*conn_mr;
 	struct ib_qp		*conn_qp;
 	struct isert_device	*conn_device;
-	struct work_struct	conn_logout_work;
 	struct mutex		conn_mutex;
 	struct completion	conn_wait;
 	struct completion	conn_wait_comp_err;
@@ -147,10 +157,10 @@ struct isert_conn {
 	int			conn_fr_pool_size;
 	/* lock to protect fastreg pool */
 	spinlock_t		conn_lock;
+	struct work_struct	release_work;
 #define ISERT_COMP_BATCH_COUNT	8
 	int			conn_comp_batch;
 	struct llist_head	conn_comp_llist;
-	bool                    disconnect;
 };
 
 #define ISERT_MAX_CQ 64
@@ -182,6 +192,7 @@ struct isert_device {
 };
 
 struct isert_np {
+	struct iscsi_np         *np;
 	struct semaphore	np_sem;
 	struct rdma_cm_id	*np_cm_id;
 	struct mutex		np_accept_mutex;
diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig
index a11ff74a512..518efa2a9f5 100644
--- a/drivers/input/Kconfig
+++ b/drivers/input/Kconfig
@@ -174,6 +174,25 @@ config INPUT_APMPOWER
 	  To compile this driver as a module, choose M here: the
 	  module will be called apm-power.
 
+config INPUT_KEYRESET
+	tristate "Reset key"
+	depends on INPUT
+	select INPUT_KEYCOMBO
+	---help---
+	  Say Y here if you want to reboot when some keys are pressed;
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called keyreset.
+
+config INPUT_KEYCOMBO
+	tristate "Key combo"
+	depends on INPUT
+	---help---
+	  Say Y here if you want to take action when some keys are pressed;
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called keycombo.
+
 comment "Input Device Drivers"
 
 source "drivers/input/keyboard/Kconfig"
diff --git a/drivers/input/Makefile b/drivers/input/Makefile
index 5ca3f631497..ee4c06520bb 100644
--- a/drivers/input/Makefile
+++ b/drivers/input/Makefile
@@ -25,3 +25,6 @@ obj-$(CONFIG_INPUT_TOUCHSCREEN)	+= touchscreen/
 obj-$(CONFIG_INPUT_MISC)	+= misc/
 
 obj-$(CONFIG_INPUT_APMPOWER)	+= apm-power.o
+obj-$(CONFIG_INPUT_KEYRESET)	+= keyreset.o
+obj-$(CONFIG_INPUT_KEYCOMBO)	+= keycombo.o
+
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index 8afa28e4570..738a2a3325d 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -26,6 +26,7 @@
 #include <linux/major.h>
 #include <linux/device.h>
 #include <linux/cdev.h>
+#include <linux/wakelock.h>
 #include "input-compat.h"
 
 struct evdev {
@@ -46,6 +47,9 @@ struct evdev_client {
 	unsigned int tail;
 	unsigned int packet_head; /* [future] position of the first element of next packet */
 	spinlock_t buffer_lock; /* protects access to buffer, head and tail */
+	struct wake_lock wake_lock;
+	bool use_wake_lock;
+	char name[28];
 	struct fasync_struct *fasync;
 	struct evdev *evdev;
 	struct list_head node;
@@ -149,10 +153,14 @@ static void __pass_event(struct evdev_client *client,
 		client->buffer[client->tail].value = 0;
 
 		client->packet_head = client->tail;
+		if (client->use_wake_lock)
+			wake_unlock(&client->wake_lock);
 	}
 
 	if (event->type == EV_SYN && event->code == SYN_REPORT) {
 		client->packet_head = client->head;
+		if (client->use_wake_lock)
+			wake_lock(&client->wake_lock);
 		kill_fasync(&client->fasync, SIGIO, POLL_IN);
 	}
 }
@@ -371,6 +379,9 @@ static int evdev_release(struct inode *inode, struct file *file)
 
 	evdev_detach_client(evdev, client);
 
+	if (client->use_wake_lock)
+		wake_lock_destroy(&client->wake_lock);
+
 	if (is_vmalloc_addr(client))
 		vfree(client);
 	else
@@ -407,6 +418,8 @@ static int evdev_open(struct inode *inode, struct file *file)
 
 	client->bufsize = bufsize;
 	spin_lock_init(&client->buffer_lock);
+	snprintf(client->name, sizeof(client->name), "%s-%d",
+			dev_name(&evdev->dev), task_tgid_vnr(current));
 	client->evdev = evdev;
 	evdev_attach_client(evdev, client);
 
@@ -473,6 +486,9 @@ static int evdev_fetch_next_event(struct evdev_client *client,
 	if (have_event) {
 		*event = client->buffer[client->tail++];
 		client->tail &= client->bufsize - 1;
+		if (client->use_wake_lock &&
+		    client->packet_head == client->tail)
+			wake_unlock(&client->wake_lock);
 	}
 
 	spin_unlock_irq(&client->buffer_lock);
@@ -795,6 +811,11 @@ static int evdev_handle_mt_request(struct input_dev *dev,
 	return 0;
 }
 
+/*
+ * HACK: disable conflicting EVIOCREVOKE until Android userspace stops using
+ * EVIOCSSUSPENDBLOCK
+ */
+/*
 static int evdev_revoke(struct evdev *evdev, struct evdev_client *client,
 			struct file *file)
 {
@@ -805,6 +826,36 @@ static int evdev_revoke(struct evdev *evdev, struct evdev_client *client,
 
 	return 0;
 }
+*/
+
+static int evdev_enable_suspend_block(struct evdev *evdev,
+				      struct evdev_client *client)
+{
+	if (client->use_wake_lock)
+		return 0;
+
+	spin_lock_irq(&client->buffer_lock);
+	wake_lock_init(&client->wake_lock, WAKE_LOCK_SUSPEND, client->name);
+	client->use_wake_lock = true;
+	if (client->packet_head != client->tail)
+		wake_lock(&client->wake_lock);
+	spin_unlock_irq(&client->buffer_lock);
+	return 0;
+}
+
+static int evdev_disable_suspend_block(struct evdev *evdev,
+				       struct evdev_client *client)
+{
+	if (!client->use_wake_lock)
+		return 0;
+
+	spin_lock_irq(&client->buffer_lock);
+	client->use_wake_lock = false;
+	wake_lock_destroy(&client->wake_lock);
+	spin_unlock_irq(&client->buffer_lock);
+
+	return 0;
+}
 
 static long evdev_do_ioctl(struct file *file, unsigned int cmd,
 			   void __user *p, int compat_mode)
@@ -868,12 +919,17 @@ static long evdev_do_ioctl(struct file *file, unsigned int cmd,
 		else
 			return evdev_ungrab(evdev, client);
 
+	/*
+	 * HACK: disable conflicting EVIOCREVOKE until Android userspace stops
+	 * using EVIOCSSUSPENDBLOCK
+	 */
+	/*
 	case EVIOCREVOKE:
 		if (p)
 			return -EINVAL;
 		else
 			return evdev_revoke(evdev, client, file);
-
+	*/
 	case EVIOCSCLOCKID:
 		if (copy_from_user(&i, p, sizeof(unsigned int)))
 			return -EFAULT;
@@ -893,6 +949,15 @@ static long evdev_do_ioctl(struct file *file, unsigned int cmd,
 
 	case EVIOCSKEYCODE_V2:
 		return evdev_handle_set_keycode_v2(dev, p);
+
+	case EVIOCGSUSPENDBLOCK:
+		return put_user(client->use_wake_lock, ip);
+
+	case EVIOCSSUSPENDBLOCK:
+		if (p)
+			return evdev_enable_suspend_block(evdev, client);
+		else
+			return evdev_disable_suspend_block(evdev, client);
 	}
 
 	size = _IOC_SIZE(cmd);
diff --git a/drivers/input/keycombo.c b/drivers/input/keycombo.c
new file mode 100644
index 00000000000..2fba451b91d
--- /dev/null
+++ b/drivers/input/keycombo.c
@@ -0,0 +1,261 @@
+/* drivers/input/keycombo.c
+ *
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/input.h>
+#include <linux/keycombo.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/reboot.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+struct keycombo_state {
+	struct input_handler input_handler;
+	unsigned long keybit[BITS_TO_LONGS(KEY_CNT)];
+	unsigned long upbit[BITS_TO_LONGS(KEY_CNT)];
+	unsigned long key[BITS_TO_LONGS(KEY_CNT)];
+	spinlock_t lock;
+	struct  workqueue_struct *wq;
+	int key_down_target;
+	int key_down;
+	int key_up;
+	struct delayed_work key_down_work;
+	int delay;
+	struct work_struct key_up_work;
+	void (*key_up_fn)(void *);
+	void (*key_down_fn)(void *);
+	void *priv;
+	int key_is_down;
+	struct wakeup_source combo_held_wake_source;
+	struct wakeup_source combo_up_wake_source;
+};
+
+static void do_key_down(struct work_struct *work)
+{
+	struct delayed_work *dwork = container_of(work, struct delayed_work,
+									work);
+	struct keycombo_state *state = container_of(dwork,
+					struct keycombo_state, key_down_work);
+	if (state->key_down_fn)
+		state->key_down_fn(state->priv);
+}
+
+static void do_key_up(struct work_struct *work)
+{
+	struct keycombo_state *state = container_of(work, struct keycombo_state,
+								key_up_work);
+	if (state->key_up_fn)
+		state->key_up_fn(state->priv);
+	__pm_relax(&state->combo_up_wake_source);
+}
+
+static void keycombo_event(struct input_handle *handle, unsigned int type,
+		unsigned int code, int value)
+{
+	unsigned long flags;
+	struct keycombo_state *state = handle->private;
+
+	if (type != EV_KEY)
+		return;
+
+	if (code >= KEY_MAX)
+		return;
+
+	if (!test_bit(code, state->keybit))
+		return;
+
+	spin_lock_irqsave(&state->lock, flags);
+	if (!test_bit(code, state->key) == !value)
+		goto done;
+	__change_bit(code, state->key);
+	if (test_bit(code, state->upbit)) {
+		if (value)
+			state->key_up++;
+		else
+			state->key_up--;
+	} else {
+		if (value)
+			state->key_down++;
+		else
+			state->key_down--;
+	}
+	if (state->key_down == state->key_down_target && state->key_up == 0) {
+		__pm_stay_awake(&state->combo_held_wake_source);
+		state->key_is_down = 1;
+		if (queue_delayed_work(state->wq, &state->key_down_work,
+								state->delay))
+			pr_debug("Key down work already queued!");
+	} else if (state->key_is_down) {
+		if (!cancel_delayed_work(&state->key_down_work)) {
+			__pm_stay_awake(&state->combo_up_wake_source);
+			queue_work(state->wq, &state->key_up_work);
+		}
+		__pm_relax(&state->combo_held_wake_source);
+		state->key_is_down = 0;
+	}
+done:
+	spin_unlock_irqrestore(&state->lock, flags);
+}
+
+static int keycombo_connect(struct input_handler *handler,
+		struct input_dev *dev,
+		const struct input_device_id *id)
+{
+	int i;
+	int ret;
+	struct input_handle *handle;
+	struct keycombo_state *state =
+		container_of(handler, struct keycombo_state, input_handler);
+	for (i = 0; i < KEY_MAX; i++) {
+		if (test_bit(i, state->keybit) && test_bit(i, dev->keybit))
+			break;
+	}
+	if (i == KEY_MAX)
+		return -ENODEV;
+
+	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+	if (!handle)
+		return -ENOMEM;
+
+	handle->dev = dev;
+	handle->handler = handler;
+	handle->name = KEYCOMBO_NAME;
+	handle->private = state;
+
+	ret = input_register_handle(handle);
+	if (ret)
+		goto err_input_register_handle;
+
+	ret = input_open_device(handle);
+	if (ret)
+		goto err_input_open_device;
+
+	return 0;
+
+err_input_open_device:
+	input_unregister_handle(handle);
+err_input_register_handle:
+	kfree(handle);
+	return ret;
+}
+
+static void keycombo_disconnect(struct input_handle *handle)
+{
+	input_close_device(handle);
+	input_unregister_handle(handle);
+	kfree(handle);
+}
+
+static const struct input_device_id keycombo_ids[] = {
+		{
+				.flags = INPUT_DEVICE_ID_MATCH_EVBIT,
+				.evbit = { BIT_MASK(EV_KEY) },
+		},
+		{ },
+};
+MODULE_DEVICE_TABLE(input, keycombo_ids);
+
+static int keycombo_probe(struct platform_device *pdev)
+{
+	int ret;
+	int key, *keyp;
+	struct keycombo_state *state;
+	struct keycombo_platform_data *pdata = pdev->dev.platform_data;
+
+	if (!pdata)
+		return -EINVAL;
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return -ENOMEM;
+
+	spin_lock_init(&state->lock);
+	keyp = pdata->keys_down;
+	while ((key = *keyp++)) {
+		if (key >= KEY_MAX)
+			continue;
+		state->key_down_target++;
+		__set_bit(key, state->keybit);
+	}
+	if (pdata->keys_up) {
+		keyp = pdata->keys_up;
+		while ((key = *keyp++)) {
+			if (key >= KEY_MAX)
+				continue;
+			__set_bit(key, state->keybit);
+			__set_bit(key, state->upbit);
+		}
+	}
+
+	state->wq = alloc_ordered_workqueue("keycombo", 0);
+	if (!state->wq)
+		return -ENOMEM;
+
+	state->priv = pdata->priv;
+
+	if (pdata->key_down_fn)
+		state->key_down_fn = pdata->key_down_fn;
+	INIT_DELAYED_WORK(&state->key_down_work, do_key_down);
+
+	if (pdata->key_up_fn)
+		state->key_up_fn = pdata->key_up_fn;
+	INIT_WORK(&state->key_up_work, do_key_up);
+
+	wakeup_source_init(&state->combo_held_wake_source, "key combo");
+	wakeup_source_init(&state->combo_up_wake_source, "key combo up");
+	state->delay = msecs_to_jiffies(pdata->key_down_delay);
+
+	state->input_handler.event = keycombo_event;
+	state->input_handler.connect = keycombo_connect;
+	state->input_handler.disconnect = keycombo_disconnect;
+	state->input_handler.name = KEYCOMBO_NAME;
+	state->input_handler.id_table = keycombo_ids;
+	ret = input_register_handler(&state->input_handler);
+	if (ret) {
+		kfree(state);
+		return ret;
+	}
+	platform_set_drvdata(pdev, state);
+	return 0;
+}
+
+int keycombo_remove(struct platform_device *pdev)
+{
+	struct keycombo_state *state = platform_get_drvdata(pdev);
+	input_unregister_handler(&state->input_handler);
+	destroy_workqueue(state->wq);
+	kfree(state);
+	return 0;
+}
+
+
+struct platform_driver keycombo_driver = {
+		.driver.name = KEYCOMBO_NAME,
+		.probe = keycombo_probe,
+		.remove = keycombo_remove,
+};
+
+static int __init keycombo_init(void)
+{
+	return platform_driver_register(&keycombo_driver);
+}
+
+static void __exit keycombo_exit(void)
+{
+	return platform_driver_unregister(&keycombo_driver);
+}
+
+module_init(keycombo_init);
+module_exit(keycombo_exit);
diff --git a/drivers/input/keyreset.c b/drivers/input/keyreset.c
new file mode 100644
index 00000000000..7fbf7247e65
--- /dev/null
+++ b/drivers/input/keyreset.c
@@ -0,0 +1,145 @@
+/* drivers/input/keyreset.c
+ *
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/input.h>
+#include <linux/keyreset.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/reboot.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/keycombo.h>
+
+struct keyreset_state {
+	int restart_requested;
+	int (*reset_fn)(void);
+	struct platform_device *pdev_child;
+	struct work_struct restart_work;
+};
+
+static void do_restart(struct work_struct *unused)
+{
+	sys_sync();
+	kernel_restart(NULL);
+}
+
+static void do_reset_fn(void *priv)
+{
+	struct keyreset_state *state = priv;
+	if (state->restart_requested)
+		panic("keyboard reset failed, %d", state->restart_requested);
+	if (state->reset_fn) {
+		state->restart_requested = state->reset_fn();
+	} else {
+		pr_info("keyboard reset\n");
+		schedule_work(&state->restart_work);
+		state->restart_requested = 1;
+	}
+}
+
+static int keyreset_probe(struct platform_device *pdev)
+{
+	int ret = -ENOMEM;
+	struct keycombo_platform_data *pdata_child;
+	struct keyreset_platform_data *pdata = pdev->dev.platform_data;
+	int up_size = 0, down_size = 0, size;
+	int key, *keyp;
+	struct keyreset_state *state;
+
+	if (!pdata)
+		return -EINVAL;
+	state = devm_kzalloc(&pdev->dev, sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return -ENOMEM;
+
+	state->pdev_child = platform_device_alloc(KEYCOMBO_NAME,
+							PLATFORM_DEVID_AUTO);
+	if (!state->pdev_child)
+		return -ENOMEM;
+	state->pdev_child->dev.parent = &pdev->dev;
+	INIT_WORK(&state->restart_work, do_restart);
+
+	keyp = pdata->keys_down;
+	while ((key = *keyp++)) {
+		if (key >= KEY_MAX)
+			continue;
+		down_size++;
+	}
+	if (pdata->keys_up) {
+		keyp = pdata->keys_up;
+		while ((key = *keyp++)) {
+			if (key >= KEY_MAX)
+				continue;
+			up_size++;
+		}
+	}
+	size = sizeof(struct keycombo_platform_data)
+			+ sizeof(int) * (down_size + 1);
+	pdata_child = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
+	if (!pdata_child)
+		goto error;
+	memcpy(pdata_child->keys_down, pdata->keys_down,
+						sizeof(int) * down_size);
+	if (up_size > 0) {
+		pdata_child->keys_up = devm_kzalloc(&pdev->dev, up_size + 1,
+								GFP_KERNEL);
+		if (!pdata_child->keys_up)
+			goto error;
+		memcpy(pdata_child->keys_up, pdata->keys_up,
+							sizeof(int) * up_size);
+		if (!pdata_child->keys_up)
+			goto error;
+	}
+	state->reset_fn = pdata->reset_fn;
+	pdata_child->key_down_fn = do_reset_fn;
+	pdata_child->priv = state;
+	pdata_child->key_down_delay = pdata->key_down_delay;
+	ret = platform_device_add_data(state->pdev_child, pdata_child, size);
+	if (ret)
+		goto error;
+	platform_set_drvdata(pdev, state);
+	return platform_device_add(state->pdev_child);
+error:
+	platform_device_put(state->pdev_child);
+	return ret;
+}
+
+int keyreset_remove(struct platform_device *pdev)
+{
+	struct keyreset_state *state = platform_get_drvdata(pdev);
+	platform_device_put(state->pdev_child);
+	return 0;
+}
+
+
+struct platform_driver keyreset_driver = {
+	.driver.name = KEYRESET_NAME,
+	.probe = keyreset_probe,
+	.remove = keyreset_remove,
+};
+
+static int __init keyreset_init(void)
+{
+	return platform_driver_register(&keyreset_driver);
+}
+
+static void __exit keyreset_exit(void)
+{
+	return platform_driver_unregister(&keyreset_driver);
+}
+
+module_init(keyreset_init);
+module_exit(keyreset_exit);
diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig
index 23297ab6163..838824bc7d3 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -319,6 +319,17 @@ config INPUT_ATI_REMOTE2
 	  To compile this driver as a module, choose M here: the module will be
 	  called ati_remote2.
 
+config INPUT_KEYCHORD
+	tristate "Key chord input driver support"
+	help
+	  Say Y here if you want to enable the key chord driver
+	  accessible at /dev/keychord.  This driver can be used
+	  for receiving notifications when client specified key
+	  combinations are pressed.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called keychord.
+
 config INPUT_KEYSPAN_REMOTE
 	tristate "Keyspan DMR USB remote control"
 	depends on USB_ARCH_HAS_HCD
@@ -454,6 +465,11 @@ config INPUT_SGI_BTNS
 	  To compile this driver as a module, choose M here: the
 	  module will be called sgi_btns.
 
+config INPUT_GPIO
+	tristate "GPIO driver support"
+	help
+	  Say Y here if you want to support gpio based keys, wheels etc...
+
 config HP_SDC_RTC
 	tristate "HP SDC Real Time Clock"
 	depends on (GSC || HP300) && SERIO
diff --git a/drivers/input/misc/Makefile b/drivers/input/misc/Makefile
index 19c760361f8..f77268edd9c 100644
--- a/drivers/input/misc/Makefile
+++ b/drivers/input/misc/Makefile
@@ -31,9 +31,11 @@ obj-$(CONFIG_INPUT_DRV2667_HAPTICS)	+= drv2667.o
 obj-$(CONFIG_INPUT_GP2A)		+= gp2ap002a00f.o
 obj-$(CONFIG_INPUT_GPIO_BEEPER)		+= gpio-beeper.o
 obj-$(CONFIG_INPUT_GPIO_TILT_POLLED)	+= gpio_tilt_polled.o
+obj-$(CONFIG_INPUT_GPIO)		+= gpio_event.o gpio_matrix.o gpio_input.o gpio_output.o gpio_axis.o
 obj-$(CONFIG_HP_SDC_RTC)		+= hp_sdc_rtc.o
 obj-$(CONFIG_INPUT_IMS_PCU)		+= ims-pcu.o
 obj-$(CONFIG_INPUT_IXP4XX_BEEPER)	+= ixp4xx-beeper.o
+obj-$(CONFIG_INPUT_KEYCHORD)		+= keychord.o
 obj-$(CONFIG_INPUT_KEYSPAN_REMOTE)	+= keyspan_remote.o
 obj-$(CONFIG_INPUT_KXTJ9)		+= kxtj9.o
 obj-$(CONFIG_INPUT_M68K_BEEP)		+= m68kspkr.o
diff --git a/drivers/input/misc/gpio_axis.c b/drivers/input/misc/gpio_axis.c
new file mode 100644
index 00000000000..0acf4a576f5
--- /dev/null
+++ b/drivers/input/misc/gpio_axis.c
@@ -0,0 +1,192 @@
+/* drivers/input/misc/gpio_axis.c
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/gpio_event.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+
+struct gpio_axis_state {
+	struct gpio_event_input_devs *input_devs;
+	struct gpio_event_axis_info *info;
+	uint32_t pos;
+};
+
+uint16_t gpio_axis_4bit_gray_map_table[] = {
+	[0x0] = 0x0, [0x1] = 0x1, /* 0000 0001 */
+	[0x3] = 0x2, [0x2] = 0x3, /* 0011 0010 */
+	[0x6] = 0x4, [0x7] = 0x5, /* 0110 0111 */
+	[0x5] = 0x6, [0x4] = 0x7, /* 0101 0100 */
+	[0xc] = 0x8, [0xd] = 0x9, /* 1100 1101 */
+	[0xf] = 0xa, [0xe] = 0xb, /* 1111 1110 */
+	[0xa] = 0xc, [0xb] = 0xd, /* 1010 1011 */
+	[0x9] = 0xe, [0x8] = 0xf, /* 1001 1000 */
+};
+uint16_t gpio_axis_4bit_gray_map(struct gpio_event_axis_info *info, uint16_t in)
+{
+	return gpio_axis_4bit_gray_map_table[in];
+}
+
+uint16_t gpio_axis_5bit_singletrack_map_table[] = {
+	[0x10] = 0x00, [0x14] = 0x01, [0x1c] = 0x02, /*     10000 10100 11100 */
+	[0x1e] = 0x03, [0x1a] = 0x04, [0x18] = 0x05, /*     11110 11010 11000 */
+	[0x08] = 0x06, [0x0a] = 0x07, [0x0e] = 0x08, /*    01000 01010 01110  */
+	[0x0f] = 0x09, [0x0d] = 0x0a, [0x0c] = 0x0b, /*    01111 01101 01100  */
+	[0x04] = 0x0c, [0x05] = 0x0d, [0x07] = 0x0e, /*   00100 00101 00111   */
+	[0x17] = 0x0f, [0x16] = 0x10, [0x06] = 0x11, /*   10111 10110 00110   */
+	[0x02] = 0x12, [0x12] = 0x13, [0x13] = 0x14, /*  00010 10010 10011    */
+	[0x1b] = 0x15, [0x0b] = 0x16, [0x03] = 0x17, /*  11011 01011 00011    */
+	[0x01] = 0x18, [0x09] = 0x19, [0x19] = 0x1a, /* 00001 01001 11001     */
+	[0x1d] = 0x1b, [0x15] = 0x1c, [0x11] = 0x1d, /* 11101 10101 10001     */
+};
+uint16_t gpio_axis_5bit_singletrack_map(
+	struct gpio_event_axis_info *info, uint16_t in)
+{
+	return gpio_axis_5bit_singletrack_map_table[in];
+}
+
+static void gpio_event_update_axis(struct gpio_axis_state *as, int report)
+{
+	struct gpio_event_axis_info *ai = as->info;
+	int i;
+	int change;
+	uint16_t state = 0;
+	uint16_t pos;
+	uint16_t old_pos = as->pos;
+	for (i = ai->count - 1; i >= 0; i--)
+		state = (state << 1) | gpio_get_value(ai->gpio[i]);
+	pos = ai->map(ai, state);
+	if (ai->flags & GPIOEAF_PRINT_RAW)
+		pr_info("axis %d-%d raw %x, pos %d -> %d\n",
+			ai->type, ai->code, state, old_pos, pos);
+	if (report && pos != old_pos) {
+		if (ai->type == EV_REL) {
+			change = (ai->decoded_size + pos - old_pos) %
+				  ai->decoded_size;
+			if (change > ai->decoded_size / 2)
+				change -= ai->decoded_size;
+			if (change == ai->decoded_size / 2) {
+				if (ai->flags & GPIOEAF_PRINT_EVENT)
+					pr_info("axis %d-%d unknown direction, "
+						"pos %d -> %d\n", ai->type,
+						ai->code, old_pos, pos);
+				change = 0; /* no closest direction */
+			}
+			if (ai->flags & GPIOEAF_PRINT_EVENT)
+				pr_info("axis %d-%d change %d\n",
+					ai->type, ai->code, change);
+			input_report_rel(as->input_devs->dev[ai->dev],
+						ai->code, change);
+		} else {
+			if (ai->flags & GPIOEAF_PRINT_EVENT)
+				pr_info("axis %d-%d now %d\n",
+					ai->type, ai->code, pos);
+			input_event(as->input_devs->dev[ai->dev],
+					ai->type, ai->code, pos);
+		}
+		input_sync(as->input_devs->dev[ai->dev]);
+	}
+	as->pos = pos;
+}
+
+static irqreturn_t gpio_axis_irq_handler(int irq, void *dev_id)
+{
+	struct gpio_axis_state *as = dev_id;
+	gpio_event_update_axis(as, 1);
+	return IRQ_HANDLED;
+}
+
+int gpio_event_axis_func(struct gpio_event_input_devs *input_devs,
+			 struct gpio_event_info *info, void **data, int func)
+{
+	int ret;
+	int i;
+	int irq;
+	struct gpio_event_axis_info *ai;
+	struct gpio_axis_state *as;
+
+	ai = container_of(info, struct gpio_event_axis_info, info);
+	if (func == GPIO_EVENT_FUNC_SUSPEND) {
+		for (i = 0; i < ai->count; i++)
+			disable_irq(gpio_to_irq(ai->gpio[i]));
+		return 0;
+	}
+	if (func == GPIO_EVENT_FUNC_RESUME) {
+		for (i = 0; i < ai->count; i++)
+			enable_irq(gpio_to_irq(ai->gpio[i]));
+		return 0;
+	}
+
+	if (func == GPIO_EVENT_FUNC_INIT) {
+		*data = as = kmalloc(sizeof(*as), GFP_KERNEL);
+		if (as == NULL) {
+			ret = -ENOMEM;
+			goto err_alloc_axis_state_failed;
+		}
+		as->input_devs = input_devs;
+		as->info = ai;
+		if (ai->dev >= input_devs->count) {
+			pr_err("gpio_event_axis: bad device index %d >= %d "
+				"for %d:%d\n", ai->dev, input_devs->count,
+				ai->type, ai->code);
+			ret = -EINVAL;
+			goto err_bad_device_index;
+		}
+
+		input_set_capability(input_devs->dev[ai->dev],
+				     ai->type, ai->code);
+		if (ai->type == EV_ABS) {
+			input_set_abs_params(input_devs->dev[ai->dev], ai->code,
+					     0, ai->decoded_size - 1, 0, 0);
+		}
+		for (i = 0; i < ai->count; i++) {
+			ret = gpio_request(ai->gpio[i], "gpio_event_axis");
+			if (ret < 0)
+				goto err_request_gpio_failed;
+			ret = gpio_direction_input(ai->gpio[i]);
+			if (ret < 0)
+				goto err_gpio_direction_input_failed;
+			ret = irq = gpio_to_irq(ai->gpio[i]);
+			if (ret < 0)
+				goto err_get_irq_num_failed;
+			ret = request_irq(irq, gpio_axis_irq_handler,
+					  IRQF_TRIGGER_RISING |
+					  IRQF_TRIGGER_FALLING,
+					  "gpio_event_axis", as);
+			if (ret < 0)
+				goto err_request_irq_failed;
+		}
+		gpio_event_update_axis(as, 0);
+		return 0;
+	}
+
+	ret = 0;
+	as = *data;
+	for (i = ai->count - 1; i >= 0; i--) {
+		free_irq(gpio_to_irq(ai->gpio[i]), as);
+err_request_irq_failed:
+err_get_irq_num_failed:
+err_gpio_direction_input_failed:
+		gpio_free(ai->gpio[i]);
+err_request_gpio_failed:
+		;
+	}
+err_bad_device_index:
+	kfree(as);
+	*data = NULL;
+err_alloc_axis_state_failed:
+	return ret;
+}
diff --git a/drivers/input/misc/gpio_event.c b/drivers/input/misc/gpio_event.c
new file mode 100644
index 00000000000..90f07eba3ce
--- /dev/null
+++ b/drivers/input/misc/gpio_event.c
@@ -0,0 +1,228 @@
+/* drivers/input/misc/gpio_event.c
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/input.h>
+#include <linux/gpio_event.h>
+#include <linux/hrtimer.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+struct gpio_event {
+	struct gpio_event_input_devs *input_devs;
+	const struct gpio_event_platform_data *info;
+	void *state[0];
+};
+
+static int gpio_input_event(
+	struct input_dev *dev, unsigned int type, unsigned int code, int value)
+{
+	int i;
+	int devnr;
+	int ret = 0;
+	int tmp_ret;
+	struct gpio_event_info **ii;
+	struct gpio_event *ip = input_get_drvdata(dev);
+
+	for (devnr = 0; devnr < ip->input_devs->count; devnr++)
+		if (ip->input_devs->dev[devnr] == dev)
+			break;
+	if (devnr == ip->input_devs->count) {
+		pr_err("gpio_input_event: unknown device %p\n", dev);
+		return -EIO;
+	}
+
+	for (i = 0, ii = ip->info->info; i < ip->info->info_count; i++, ii++) {
+		if ((*ii)->event) {
+			tmp_ret = (*ii)->event(ip->input_devs, *ii,
+						&ip->state[i],
+						devnr, type, code, value);
+			if (tmp_ret)
+				ret = tmp_ret;
+		}
+	}
+	return ret;
+}
+
+static int gpio_event_call_all_func(struct gpio_event *ip, int func)
+{
+	int i;
+	int ret;
+	struct gpio_event_info **ii;
+
+	if (func == GPIO_EVENT_FUNC_INIT || func == GPIO_EVENT_FUNC_RESUME) {
+		ii = ip->info->info;
+		for (i = 0; i < ip->info->info_count; i++, ii++) {
+			if ((*ii)->func == NULL) {
+				ret = -ENODEV;
+				pr_err("gpio_event_probe: Incomplete pdata, "
+					"no function\n");
+				goto err_no_func;
+			}
+			if (func == GPIO_EVENT_FUNC_RESUME && (*ii)->no_suspend)
+				continue;
+			ret = (*ii)->func(ip->input_devs, *ii, &ip->state[i],
+					  func);
+			if (ret) {
+				pr_err("gpio_event_probe: function failed\n");
+				goto err_func_failed;
+			}
+		}
+		return 0;
+	}
+
+	ret = 0;
+	i = ip->info->info_count;
+	ii = ip->info->info + i;
+	while (i > 0) {
+		i--;
+		ii--;
+		if ((func & ~1) == GPIO_EVENT_FUNC_SUSPEND && (*ii)->no_suspend)
+			continue;
+		(*ii)->func(ip->input_devs, *ii, &ip->state[i], func & ~1);
+err_func_failed:
+err_no_func:
+		;
+	}
+	return ret;
+}
+
+static void __maybe_unused gpio_event_suspend(struct gpio_event *ip)
+{
+	gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_SUSPEND);
+	if (ip->info->power)
+		ip->info->power(ip->info, 0);
+}
+
+static void __maybe_unused gpio_event_resume(struct gpio_event *ip)
+{
+	if (ip->info->power)
+		ip->info->power(ip->info, 1);
+	gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_RESUME);
+}
+
+static int gpio_event_probe(struct platform_device *pdev)
+{
+	int err;
+	struct gpio_event *ip;
+	struct gpio_event_platform_data *event_info;
+	int dev_count = 1;
+	int i;
+	int registered = 0;
+
+	event_info = pdev->dev.platform_data;
+	if (event_info == NULL) {
+		pr_err("gpio_event_probe: No pdata\n");
+		return -ENODEV;
+	}
+	if ((!event_info->name && !event_info->names[0]) ||
+	    !event_info->info || !event_info->info_count) {
+		pr_err("gpio_event_probe: Incomplete pdata\n");
+		return -ENODEV;
+	}
+	if (!event_info->name)
+		while (event_info->names[dev_count])
+			dev_count++;
+	ip = kzalloc(sizeof(*ip) +
+		     sizeof(ip->state[0]) * event_info->info_count +
+		     sizeof(*ip->input_devs) +
+		     sizeof(ip->input_devs->dev[0]) * dev_count, GFP_KERNEL);
+	if (ip == NULL) {
+		err = -ENOMEM;
+		pr_err("gpio_event_probe: Failed to allocate private data\n");
+		goto err_kp_alloc_failed;
+	}
+	ip->input_devs = (void*)&ip->state[event_info->info_count];
+	platform_set_drvdata(pdev, ip);
+
+	for (i = 0; i < dev_count; i++) {
+		struct input_dev *input_dev = input_allocate_device();
+		if (input_dev == NULL) {
+			err = -ENOMEM;
+			pr_err("gpio_event_probe: "
+				"Failed to allocate input device\n");
+			goto err_input_dev_alloc_failed;
+		}
+		input_set_drvdata(input_dev, ip);
+		input_dev->name = event_info->name ?
+					event_info->name : event_info->names[i];
+		input_dev->event = gpio_input_event;
+		ip->input_devs->dev[i] = input_dev;
+	}
+	ip->input_devs->count = dev_count;
+	ip->info = event_info;
+	if (event_info->power)
+		ip->info->power(ip->info, 1);
+
+	err = gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_INIT);
+	if (err)
+		goto err_call_all_func_failed;
+
+	for (i = 0; i < dev_count; i++) {
+		err = input_register_device(ip->input_devs->dev[i]);
+		if (err) {
+			pr_err("gpio_event_probe: Unable to register %s "
+				"input device\n", ip->input_devs->dev[i]->name);
+			goto err_input_register_device_failed;
+		}
+		registered++;
+	}
+
+	return 0;
+
+err_input_register_device_failed:
+	gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_UNINIT);
+err_call_all_func_failed:
+	if (event_info->power)
+		ip->info->power(ip->info, 0);
+	for (i = 0; i < registered; i++)
+		input_unregister_device(ip->input_devs->dev[i]);
+	for (i = dev_count - 1; i >= registered; i--) {
+		input_free_device(ip->input_devs->dev[i]);
+err_input_dev_alloc_failed:
+		;
+	}
+	kfree(ip);
+err_kp_alloc_failed:
+	return err;
+}
+
+static int gpio_event_remove(struct platform_device *pdev)
+{
+	struct gpio_event *ip = platform_get_drvdata(pdev);
+	int i;
+
+	gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_UNINIT);
+	if (ip->info->power)
+		ip->info->power(ip->info, 0);
+	for (i = 0; i < ip->input_devs->count; i++)
+		input_unregister_device(ip->input_devs->dev[i]);
+	kfree(ip);
+	return 0;
+}
+
+static struct platform_driver gpio_event_driver = {
+	.probe		= gpio_event_probe,
+	.remove		= gpio_event_remove,
+	.driver		= {
+		.name	= GPIO_EVENT_DEV_NAME,
+	},
+};
+
+module_platform_driver(gpio_event_driver);
+
+MODULE_DESCRIPTION("GPIO Event Driver");
+MODULE_LICENSE("GPL");
+
diff --git a/drivers/input/misc/gpio_input.c b/drivers/input/misc/gpio_input.c
new file mode 100644
index 00000000000..eefd02725af
--- /dev/null
+++ b/drivers/input/misc/gpio_input.c
@@ -0,0 +1,390 @@
+/* drivers/input/misc/gpio_input.c
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/gpio_event.h>
+#include <linux/hrtimer.h>
+#include <linux/input.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/pm_wakeup.h>
+
+enum {
+	DEBOUNCE_UNSTABLE     = BIT(0),	/* Got irq, while debouncing */
+	DEBOUNCE_PRESSED      = BIT(1),
+	DEBOUNCE_NOTPRESSED   = BIT(2),
+	DEBOUNCE_WAIT_IRQ     = BIT(3),	/* Stable irq state */
+	DEBOUNCE_POLL         = BIT(4),	/* Stable polling state */
+
+	DEBOUNCE_UNKNOWN =
+		DEBOUNCE_PRESSED | DEBOUNCE_NOTPRESSED,
+};
+
+struct gpio_key_state {
+	struct gpio_input_state *ds;
+	uint8_t debounce;
+};
+
+struct gpio_input_state {
+	struct gpio_event_input_devs *input_devs;
+	const struct gpio_event_input_info *info;
+	struct hrtimer timer;
+	int use_irq;
+	int debounce_count;
+	spinlock_t irq_lock;
+	struct wakeup_source *ws;
+	struct gpio_key_state key_state[0];
+};
+
+static enum hrtimer_restart gpio_event_input_timer_func(struct hrtimer *timer)
+{
+	int i;
+	int pressed;
+	struct gpio_input_state *ds =
+		container_of(timer, struct gpio_input_state, timer);
+	unsigned gpio_flags = ds->info->flags;
+	unsigned npolarity;
+	int nkeys = ds->info->keymap_size;
+	const struct gpio_event_direct_entry *key_entry;
+	struct gpio_key_state *key_state;
+	unsigned long irqflags;
+	uint8_t debounce;
+	bool sync_needed;
+
+#if 0
+	key_entry = kp->keys_info->keymap;
+	key_state = kp->key_state;
+	for (i = 0; i < nkeys; i++, key_entry++, key_state++)
+		pr_info("gpio_read_detect_status %d %d\n", key_entry->gpio,
+			gpio_read_detect_status(key_entry->gpio));
+#endif
+	key_entry = ds->info->keymap;
+	key_state = ds->key_state;
+	sync_needed = false;
+	spin_lock_irqsave(&ds->irq_lock, irqflags);
+	for (i = 0; i < nkeys; i++, key_entry++, key_state++) {
+		debounce = key_state->debounce;
+		if (debounce & DEBOUNCE_WAIT_IRQ)
+			continue;
+		if (key_state->debounce & DEBOUNCE_UNSTABLE) {
+			debounce = key_state->debounce = DEBOUNCE_UNKNOWN;
+			enable_irq(gpio_to_irq(key_entry->gpio));
+			if (gpio_flags & GPIOEDF_PRINT_KEY_UNSTABLE)
+				pr_info("gpio_keys_scan_keys: key %x-%x, %d "
+					"(%d) continue debounce\n",
+					ds->info->type, key_entry->code,
+					i, key_entry->gpio);
+		}
+		npolarity = !(gpio_flags & GPIOEDF_ACTIVE_HIGH);
+		pressed = gpio_get_value(key_entry->gpio) ^ npolarity;
+		if (debounce & DEBOUNCE_POLL) {
+			if (pressed == !(debounce & DEBOUNCE_PRESSED)) {
+				ds->debounce_count++;
+				key_state->debounce = DEBOUNCE_UNKNOWN;
+				if (gpio_flags & GPIOEDF_PRINT_KEY_DEBOUNCE)
+					pr_info("gpio_keys_scan_keys: key %x-"
+						"%x, %d (%d) start debounce\n",
+						ds->info->type, key_entry->code,
+						i, key_entry->gpio);
+			}
+			continue;
+		}
+		if (pressed && (debounce & DEBOUNCE_NOTPRESSED)) {
+			if (gpio_flags & GPIOEDF_PRINT_KEY_DEBOUNCE)
+				pr_info("gpio_keys_scan_keys: key %x-%x, %d "
+					"(%d) debounce pressed 1\n",
+					ds->info->type, key_entry->code,
+					i, key_entry->gpio);
+			key_state->debounce = DEBOUNCE_PRESSED;
+			continue;
+		}
+		if (!pressed && (debounce & DEBOUNCE_PRESSED)) {
+			if (gpio_flags & GPIOEDF_PRINT_KEY_DEBOUNCE)
+				pr_info("gpio_keys_scan_keys: key %x-%x, %d "
+					"(%d) debounce pressed 0\n",
+					ds->info->type, key_entry->code,
+					i, key_entry->gpio);
+			key_state->debounce = DEBOUNCE_NOTPRESSED;
+			continue;
+		}
+		/* key is stable */
+		ds->debounce_count--;
+		if (ds->use_irq)
+			key_state->debounce |= DEBOUNCE_WAIT_IRQ;
+		else
+			key_state->debounce |= DEBOUNCE_POLL;
+		if (gpio_flags & GPIOEDF_PRINT_KEYS)
+			pr_info("gpio_keys_scan_keys: key %x-%x, %d (%d) "
+				"changed to %d\n", ds->info->type,
+				key_entry->code, i, key_entry->gpio, pressed);
+		input_event(ds->input_devs->dev[key_entry->dev], ds->info->type,
+			    key_entry->code, pressed);
+		sync_needed = true;
+	}
+	if (sync_needed) {
+		for (i = 0; i < ds->input_devs->count; i++)
+			input_sync(ds->input_devs->dev[i]);
+	}
+
+#if 0
+	key_entry = kp->keys_info->keymap;
+	key_state = kp->key_state;
+	for (i = 0; i < nkeys; i++, key_entry++, key_state++) {
+		pr_info("gpio_read_detect_status %d %d\n", key_entry->gpio,
+			gpio_read_detect_status(key_entry->gpio));
+	}
+#endif
+
+	if (ds->debounce_count)
+		hrtimer_start(timer, ds->info->debounce_time, HRTIMER_MODE_REL);
+	else if (!ds->use_irq)
+		hrtimer_start(timer, ds->info->poll_time, HRTIMER_MODE_REL);
+	else
+		__pm_relax(ds->ws);
+
+	spin_unlock_irqrestore(&ds->irq_lock, irqflags);
+
+	return HRTIMER_NORESTART;
+}
+
+static irqreturn_t gpio_event_input_irq_handler(int irq, void *dev_id)
+{
+	struct gpio_key_state *ks = dev_id;
+	struct gpio_input_state *ds = ks->ds;
+	int keymap_index = ks - ds->key_state;
+	const struct gpio_event_direct_entry *key_entry;
+	unsigned long irqflags;
+	int pressed;
+
+	if (!ds->use_irq)
+		return IRQ_HANDLED;
+
+	key_entry = &ds->info->keymap[keymap_index];
+
+	if (ds->info->debounce_time.tv64) {
+		spin_lock_irqsave(&ds->irq_lock, irqflags);
+		if (ks->debounce & DEBOUNCE_WAIT_IRQ) {
+			ks->debounce = DEBOUNCE_UNKNOWN;
+			if (ds->debounce_count++ == 0) {
+				__pm_stay_awake(ds->ws);
+				hrtimer_start(
+					&ds->timer, ds->info->debounce_time,
+					HRTIMER_MODE_REL);
+			}
+			if (ds->info->flags & GPIOEDF_PRINT_KEY_DEBOUNCE)
+				pr_info("gpio_event_input_irq_handler: "
+					"key %x-%x, %d (%d) start debounce\n",
+					ds->info->type, key_entry->code,
+					keymap_index, key_entry->gpio);
+		} else {
+			disable_irq_nosync(irq);
+			ks->debounce = DEBOUNCE_UNSTABLE;
+		}
+		spin_unlock_irqrestore(&ds->irq_lock, irqflags);
+	} else {
+		pressed = gpio_get_value(key_entry->gpio) ^
+			!(ds->info->flags & GPIOEDF_ACTIVE_HIGH);
+		if (ds->info->flags & GPIOEDF_PRINT_KEYS)
+			pr_info("gpio_event_input_irq_handler: key %x-%x, %d "
+				"(%d) changed to %d\n",
+				ds->info->type, key_entry->code, keymap_index,
+				key_entry->gpio, pressed);
+		input_event(ds->input_devs->dev[key_entry->dev], ds->info->type,
+			    key_entry->code, pressed);
+		input_sync(ds->input_devs->dev[key_entry->dev]);
+	}
+	return IRQ_HANDLED;
+}
+
+static int gpio_event_input_request_irqs(struct gpio_input_state *ds)
+{
+	int i;
+	int err;
+	unsigned int irq;
+	unsigned long req_flags = IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING;
+
+	for (i = 0; i < ds->info->keymap_size; i++) {
+		err = irq = gpio_to_irq(ds->info->keymap[i].gpio);
+		if (err < 0)
+			goto err_gpio_get_irq_num_failed;
+		err = request_irq(irq, gpio_event_input_irq_handler,
+				  req_flags, "gpio_keys", &ds->key_state[i]);
+		if (err) {
+			pr_err("gpio_event_input_request_irqs: request_irq "
+				"failed for input %d, irq %d\n",
+				ds->info->keymap[i].gpio, irq);
+			goto err_request_irq_failed;
+		}
+		if (ds->info->info.no_suspend) {
+			err = enable_irq_wake(irq);
+			if (err) {
+				pr_err("gpio_event_input_request_irqs: "
+					"enable_irq_wake failed for input %d, "
+					"irq %d\n",
+					ds->info->keymap[i].gpio, irq);
+				goto err_enable_irq_wake_failed;
+			}
+		}
+	}
+	return 0;
+
+	for (i = ds->info->keymap_size - 1; i >= 0; i--) {
+		irq = gpio_to_irq(ds->info->keymap[i].gpio);
+		if (ds->info->info.no_suspend)
+			disable_irq_wake(irq);
+err_enable_irq_wake_failed:
+		free_irq(irq, &ds->key_state[i]);
+err_request_irq_failed:
+err_gpio_get_irq_num_failed:
+		;
+	}
+	return err;
+}
+
+int gpio_event_input_func(struct gpio_event_input_devs *input_devs,
+			struct gpio_event_info *info, void **data, int func)
+{
+	int ret;
+	int i;
+	unsigned long irqflags;
+	struct gpio_event_input_info *di;
+	struct gpio_input_state *ds = *data;
+	char *wlname;
+
+	di = container_of(info, struct gpio_event_input_info, info);
+
+	if (func == GPIO_EVENT_FUNC_SUSPEND) {
+		if (ds->use_irq)
+			for (i = 0; i < di->keymap_size; i++)
+				disable_irq(gpio_to_irq(di->keymap[i].gpio));
+		hrtimer_cancel(&ds->timer);
+		return 0;
+	}
+	if (func == GPIO_EVENT_FUNC_RESUME) {
+		spin_lock_irqsave(&ds->irq_lock, irqflags);
+		if (ds->use_irq)
+			for (i = 0; i < di->keymap_size; i++)
+				enable_irq(gpio_to_irq(di->keymap[i].gpio));
+		hrtimer_start(&ds->timer, ktime_set(0, 0), HRTIMER_MODE_REL);
+		spin_unlock_irqrestore(&ds->irq_lock, irqflags);
+		return 0;
+	}
+
+	if (func == GPIO_EVENT_FUNC_INIT) {
+		if (ktime_to_ns(di->poll_time) <= 0)
+			di->poll_time = ktime_set(0, 20 * NSEC_PER_MSEC);
+
+		*data = ds = kzalloc(sizeof(*ds) + sizeof(ds->key_state[0]) *
+					di->keymap_size, GFP_KERNEL);
+		if (ds == NULL) {
+			ret = -ENOMEM;
+			pr_err("gpio_event_input_func: "
+				"Failed to allocate private data\n");
+			goto err_ds_alloc_failed;
+		}
+		ds->debounce_count = di->keymap_size;
+		ds->input_devs = input_devs;
+		ds->info = di;
+		wlname = kasprintf(GFP_KERNEL, "gpio_input:%s%s",
+				   input_devs->dev[0]->name,
+				   (input_devs->count > 1) ? "..." : "");
+
+		ds->ws = wakeup_source_register(wlname);
+		kfree(wlname);
+		if (!ds->ws) {
+			ret = -ENOMEM;
+			pr_err("gpio_event_input_func: "
+				"Failed to allocate wakeup source\n");
+			goto err_ws_failed;
+		}
+
+		spin_lock_init(&ds->irq_lock);
+
+		for (i = 0; i < di->keymap_size; i++) {
+			int dev = di->keymap[i].dev;
+			if (dev >= input_devs->count) {
+				pr_err("gpio_event_input_func: bad device "
+					"index %d >= %d for key code %d\n",
+					dev, input_devs->count,
+					di->keymap[i].code);
+				ret = -EINVAL;
+				goto err_bad_keymap;
+			}
+			input_set_capability(input_devs->dev[dev], di->type,
+					     di->keymap[i].code);
+			ds->key_state[i].ds = ds;
+			ds->key_state[i].debounce = DEBOUNCE_UNKNOWN;
+		}
+
+		for (i = 0; i < di->keymap_size; i++) {
+			ret = gpio_request(di->keymap[i].gpio, "gpio_kp_in");
+			if (ret) {
+				pr_err("gpio_event_input_func: gpio_request "
+					"failed for %d\n", di->keymap[i].gpio);
+				goto err_gpio_request_failed;
+			}
+			ret = gpio_direction_input(di->keymap[i].gpio);
+			if (ret) {
+				pr_err("gpio_event_input_func: "
+					"gpio_direction_input failed for %d\n",
+					di->keymap[i].gpio);
+				goto err_gpio_configure_failed;
+			}
+		}
+
+		ret = gpio_event_input_request_irqs(ds);
+
+		spin_lock_irqsave(&ds->irq_lock, irqflags);
+		ds->use_irq = ret == 0;
+
+		pr_info("GPIO Input Driver: Start gpio inputs for %s%s in %s "
+			"mode\n", input_devs->dev[0]->name,
+			(input_devs->count > 1) ? "..." : "",
+			ret == 0 ? "interrupt" : "polling");
+
+		hrtimer_init(&ds->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+		ds->timer.function = gpio_event_input_timer_func;
+		hrtimer_start(&ds->timer, ktime_set(0, 0), HRTIMER_MODE_REL);
+		spin_unlock_irqrestore(&ds->irq_lock, irqflags);
+		return 0;
+	}
+
+	ret = 0;
+	spin_lock_irqsave(&ds->irq_lock, irqflags);
+	hrtimer_cancel(&ds->timer);
+	if (ds->use_irq) {
+		for (i = di->keymap_size - 1; i >= 0; i--) {
+			int irq = gpio_to_irq(di->keymap[i].gpio);
+			if (ds->info->info.no_suspend)
+				disable_irq_wake(irq);
+			free_irq(irq, &ds->key_state[i]);
+		}
+	}
+	spin_unlock_irqrestore(&ds->irq_lock, irqflags);
+
+	for (i = di->keymap_size - 1; i >= 0; i--) {
+err_gpio_configure_failed:
+		gpio_free(di->keymap[i].gpio);
+err_gpio_request_failed:
+		;
+	}
+err_bad_keymap:
+	wakeup_source_unregister(ds->ws);
+err_ws_failed:
+	kfree(ds);
+err_ds_alloc_failed:
+	return ret;
+}
diff --git a/drivers/input/misc/gpio_matrix.c b/drivers/input/misc/gpio_matrix.c
new file mode 100644
index 00000000000..eaa9e89d473
--- /dev/null
+++ b/drivers/input/misc/gpio_matrix.c
@@ -0,0 +1,441 @@
+/* drivers/input/misc/gpio_matrix.c
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/gpio_event.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/wakelock.h>
+
+struct gpio_kp {
+	struct gpio_event_input_devs *input_devs;
+	struct gpio_event_matrix_info *keypad_info;
+	struct hrtimer timer;
+	struct wake_lock wake_lock;
+	int current_output;
+	unsigned int use_irq:1;
+	unsigned int key_state_changed:1;
+	unsigned int last_key_state_changed:1;
+	unsigned int some_keys_pressed:2;
+	unsigned int disabled_irq:1;
+	unsigned long keys_pressed[0];
+};
+
+static void clear_phantom_key(struct gpio_kp *kp, int out, int in)
+{
+	struct gpio_event_matrix_info *mi = kp->keypad_info;
+	int key_index = out * mi->ninputs + in;
+	unsigned short keyentry = mi->keymap[key_index];
+	unsigned short keycode = keyentry & MATRIX_KEY_MASK;
+	unsigned short dev = keyentry >> MATRIX_CODE_BITS;
+
+	if (!test_bit(keycode, kp->input_devs->dev[dev]->key)) {
+		if (mi->flags & GPIOKPF_PRINT_PHANTOM_KEYS)
+			pr_info("gpiomatrix: phantom key %x, %d-%d (%d-%d) "
+				"cleared\n", keycode, out, in,
+				mi->output_gpios[out], mi->input_gpios[in]);
+		__clear_bit(key_index, kp->keys_pressed);
+	} else {
+		if (mi->flags & GPIOKPF_PRINT_PHANTOM_KEYS)
+			pr_info("gpiomatrix: phantom key %x, %d-%d (%d-%d) "
+				"not cleared\n", keycode, out, in,
+				mi->output_gpios[out], mi->input_gpios[in]);
+	}
+}
+
+static int restore_keys_for_input(struct gpio_kp *kp, int out, int in)
+{
+	int rv = 0;
+	int key_index;
+
+	key_index = out * kp->keypad_info->ninputs + in;
+	while (out < kp->keypad_info->noutputs) {
+		if (test_bit(key_index, kp->keys_pressed)) {
+			rv = 1;
+			clear_phantom_key(kp, out, in);
+		}
+		key_index += kp->keypad_info->ninputs;
+		out++;
+	}
+	return rv;
+}
+
+static void remove_phantom_keys(struct gpio_kp *kp)
+{
+	int out, in, inp;
+	int key_index;
+
+	if (kp->some_keys_pressed < 3)
+		return;
+
+	for (out = 0; out < kp->keypad_info->noutputs; out++) {
+		inp = -1;
+		key_index = out * kp->keypad_info->ninputs;
+		for (in = 0; in < kp->keypad_info->ninputs; in++, key_index++) {
+			if (test_bit(key_index, kp->keys_pressed)) {
+				if (inp == -1) {
+					inp = in;
+					continue;
+				}
+				if (inp >= 0) {
+					if (!restore_keys_for_input(kp, out + 1,
+									inp))
+						break;
+					clear_phantom_key(kp, out, inp);
+					inp = -2;
+				}
+				restore_keys_for_input(kp, out, in);
+			}
+		}
+	}
+}
+
+static void report_key(struct gpio_kp *kp, int key_index, int out, int in)
+{
+	struct gpio_event_matrix_info *mi = kp->keypad_info;
+	int pressed = test_bit(key_index, kp->keys_pressed);
+	unsigned short keyentry = mi->keymap[key_index];
+	unsigned short keycode = keyentry & MATRIX_KEY_MASK;
+	unsigned short dev = keyentry >> MATRIX_CODE_BITS;
+
+	if (pressed != test_bit(keycode, kp->input_devs->dev[dev]->key)) {
+		if (keycode == KEY_RESERVED) {
+			if (mi->flags & GPIOKPF_PRINT_UNMAPPED_KEYS)
+				pr_info("gpiomatrix: unmapped key, %d-%d "
+					"(%d-%d) changed to %d\n",
+					out, in, mi->output_gpios[out],
+					mi->input_gpios[in], pressed);
+		} else {
+			if (mi->flags & GPIOKPF_PRINT_MAPPED_KEYS)
+				pr_info("gpiomatrix: key %x, %d-%d (%d-%d) "
+					"changed to %d\n", keycode,
+					out, in, mi->output_gpios[out],
+					mi->input_gpios[in], pressed);
+			input_report_key(kp->input_devs->dev[dev], keycode, pressed);
+		}
+	}
+}
+
+static void report_sync(struct gpio_kp *kp)
+{
+	int i;
+
+	for (i = 0; i < kp->input_devs->count; i++)
+		input_sync(kp->input_devs->dev[i]);
+}
+
+static enum hrtimer_restart gpio_keypad_timer_func(struct hrtimer *timer)
+{
+	int out, in;
+	int key_index;
+	int gpio;
+	struct gpio_kp *kp = container_of(timer, struct gpio_kp, timer);
+	struct gpio_event_matrix_info *mi = kp->keypad_info;
+	unsigned gpio_keypad_flags = mi->flags;
+	unsigned polarity = !!(gpio_keypad_flags & GPIOKPF_ACTIVE_HIGH);
+
+	out = kp->current_output;
+	if (out == mi->noutputs) {
+		out = 0;
+		kp->last_key_state_changed = kp->key_state_changed;
+		kp->key_state_changed = 0;
+		kp->some_keys_pressed = 0;
+	} else {
+		key_index = out * mi->ninputs;
+		for (in = 0; in < mi->ninputs; in++, key_index++) {
+			gpio = mi->input_gpios[in];
+			if (gpio_get_value(gpio) ^ !polarity) {
+				if (kp->some_keys_pressed < 3)
+					kp->some_keys_pressed++;
+				kp->key_state_changed |= !__test_and_set_bit(
+						key_index, kp->keys_pressed);
+			} else
+				kp->key_state_changed |= __test_and_clear_bit(
+						key_index, kp->keys_pressed);
+		}
+		gpio = mi->output_gpios[out];
+		if (gpio_keypad_flags & GPIOKPF_DRIVE_INACTIVE)
+			gpio_set_value(gpio, !polarity);
+		else
+			gpio_direction_input(gpio);
+		out++;
+	}
+	kp->current_output = out;
+	if (out < mi->noutputs) {
+		gpio = mi->output_gpios[out];
+		if (gpio_keypad_flags & GPIOKPF_DRIVE_INACTIVE)
+			gpio_set_value(gpio, polarity);
+		else
+			gpio_direction_output(gpio, polarity);
+		hrtimer_start(timer, mi->settle_time, HRTIMER_MODE_REL);
+		return HRTIMER_NORESTART;
+	}
+	if (gpio_keypad_flags & GPIOKPF_DEBOUNCE) {
+		if (kp->key_state_changed) {
+			hrtimer_start(&kp->timer, mi->debounce_delay,
+				      HRTIMER_MODE_REL);
+			return HRTIMER_NORESTART;
+		}
+		kp->key_state_changed = kp->last_key_state_changed;
+	}
+	if (kp->key_state_changed) {
+		if (gpio_keypad_flags & GPIOKPF_REMOVE_SOME_PHANTOM_KEYS)
+			remove_phantom_keys(kp);
+		key_index = 0;
+		for (out = 0; out < mi->noutputs; out++)
+			for (in = 0; in < mi->ninputs; in++, key_index++)
+				report_key(kp, key_index, out, in);
+		report_sync(kp);
+	}
+	if (!kp->use_irq || kp->some_keys_pressed) {
+		hrtimer_start(timer, mi->poll_time, HRTIMER_MODE_REL);
+		return HRTIMER_NORESTART;
+	}
+
+	/* No keys are pressed, reenable interrupt */
+	for (out = 0; out < mi->noutputs; out++) {
+		if (gpio_keypad_flags & GPIOKPF_DRIVE_INACTIVE)
+			gpio_set_value(mi->output_gpios[out], polarity);
+		else
+			gpio_direction_output(mi->output_gpios[out], polarity);
+	}
+	for (in = 0; in < mi->ninputs; in++)
+		enable_irq(gpio_to_irq(mi->input_gpios[in]));
+	wake_unlock(&kp->wake_lock);
+	return HRTIMER_NORESTART;
+}
+
+static irqreturn_t gpio_keypad_irq_handler(int irq_in, void *dev_id)
+{
+	int i;
+	struct gpio_kp *kp = dev_id;
+	struct gpio_event_matrix_info *mi = kp->keypad_info;
+	unsigned gpio_keypad_flags = mi->flags;
+
+	if (!kp->use_irq) {
+		/* ignore interrupt while registering the handler */
+		kp->disabled_irq = 1;
+		disable_irq_nosync(irq_in);
+		return IRQ_HANDLED;
+	}
+
+	for (i = 0; i < mi->ninputs; i++)
+		disable_irq_nosync(gpio_to_irq(mi->input_gpios[i]));
+	for (i = 0; i < mi->noutputs; i++) {
+		if (gpio_keypad_flags & GPIOKPF_DRIVE_INACTIVE)
+			gpio_set_value(mi->output_gpios[i],
+				!(gpio_keypad_flags & GPIOKPF_ACTIVE_HIGH));
+		else
+			gpio_direction_input(mi->output_gpios[i]);
+	}
+	wake_lock(&kp->wake_lock);
+	hrtimer_start(&kp->timer, ktime_set(0, 0), HRTIMER_MODE_REL);
+	return IRQ_HANDLED;
+}
+
+static int gpio_keypad_request_irqs(struct gpio_kp *kp)
+{
+	int i;
+	int err;
+	unsigned int irq;
+	unsigned long request_flags;
+	struct gpio_event_matrix_info *mi = kp->keypad_info;
+
+	switch (mi->flags & (GPIOKPF_ACTIVE_HIGH|GPIOKPF_LEVEL_TRIGGERED_IRQ)) {
+	default:
+		request_flags = IRQF_TRIGGER_FALLING;
+		break;
+	case GPIOKPF_ACTIVE_HIGH:
+		request_flags = IRQF_TRIGGER_RISING;
+		break;
+	case GPIOKPF_LEVEL_TRIGGERED_IRQ:
+		request_flags = IRQF_TRIGGER_LOW;
+		break;
+	case GPIOKPF_LEVEL_TRIGGERED_IRQ | GPIOKPF_ACTIVE_HIGH:
+		request_flags = IRQF_TRIGGER_HIGH;
+		break;
+	}
+
+	for (i = 0; i < mi->ninputs; i++) {
+		err = irq = gpio_to_irq(mi->input_gpios[i]);
+		if (err < 0)
+			goto err_gpio_get_irq_num_failed;
+		err = request_irq(irq, gpio_keypad_irq_handler, request_flags,
+				  "gpio_kp", kp);
+		if (err) {
+			pr_err("gpiomatrix: request_irq failed for input %d, "
+				"irq %d\n", mi->input_gpios[i], irq);
+			goto err_request_irq_failed;
+		}
+		err = enable_irq_wake(irq);
+		if (err) {
+			pr_err("gpiomatrix: set_irq_wake failed for input %d, "
+				"irq %d\n", mi->input_gpios[i], irq);
+		}
+		disable_irq(irq);
+		if (kp->disabled_irq) {
+			kp->disabled_irq = 0;
+			enable_irq(irq);
+		}
+	}
+	return 0;
+
+	for (i = mi->noutputs - 1; i >= 0; i--) {
+		free_irq(gpio_to_irq(mi->input_gpios[i]), kp);
+err_request_irq_failed:
+err_gpio_get_irq_num_failed:
+		;
+	}
+	return err;
+}
+
+int gpio_event_matrix_func(struct gpio_event_input_devs *input_devs,
+	struct gpio_event_info *info, void **data, int func)
+{
+	int i;
+	int err;
+	int key_count;
+	struct gpio_kp *kp;
+	struct gpio_event_matrix_info *mi;
+
+	mi = container_of(info, struct gpio_event_matrix_info, info);
+	if (func == GPIO_EVENT_FUNC_SUSPEND || func == GPIO_EVENT_FUNC_RESUME) {
+		/* TODO: disable scanning */
+		return 0;
+	}
+
+	if (func == GPIO_EVENT_FUNC_INIT) {
+		if (mi->keymap == NULL ||
+		   mi->input_gpios == NULL ||
+		   mi->output_gpios == NULL) {
+			err = -ENODEV;
+			pr_err("gpiomatrix: Incomplete pdata\n");
+			goto err_invalid_platform_data;
+		}
+		key_count = mi->ninputs * mi->noutputs;
+
+		*data = kp = kzalloc(sizeof(*kp) + sizeof(kp->keys_pressed[0]) *
+				     BITS_TO_LONGS(key_count), GFP_KERNEL);
+		if (kp == NULL) {
+			err = -ENOMEM;
+			pr_err("gpiomatrix: Failed to allocate private data\n");
+			goto err_kp_alloc_failed;
+		}
+		kp->input_devs = input_devs;
+		kp->keypad_info = mi;
+		for (i = 0; i < key_count; i++) {
+			unsigned short keyentry = mi->keymap[i];
+			unsigned short keycode = keyentry & MATRIX_KEY_MASK;
+			unsigned short dev = keyentry >> MATRIX_CODE_BITS;
+			if (dev >= input_devs->count) {
+				pr_err("gpiomatrix: bad device index %d >= "
+					"%d for key code %d\n",
+					dev, input_devs->count, keycode);
+				err = -EINVAL;
+				goto err_bad_keymap;
+			}
+			if (keycode && keycode <= KEY_MAX)
+				input_set_capability(input_devs->dev[dev],
+							EV_KEY, keycode);
+		}
+
+		for (i = 0; i < mi->noutputs; i++) {
+			err = gpio_request(mi->output_gpios[i], "gpio_kp_out");
+			if (err) {
+				pr_err("gpiomatrix: gpio_request failed for "
+					"output %d\n", mi->output_gpios[i]);
+				goto err_request_output_gpio_failed;
+			}
+			if (gpio_cansleep(mi->output_gpios[i])) {
+				pr_err("gpiomatrix: unsupported output gpio %d,"
+					" can sleep\n", mi->output_gpios[i]);
+				err = -EINVAL;
+				goto err_output_gpio_configure_failed;
+			}
+			if (mi->flags & GPIOKPF_DRIVE_INACTIVE)
+				err = gpio_direction_output(mi->output_gpios[i],
+					!(mi->flags & GPIOKPF_ACTIVE_HIGH));
+			else
+				err = gpio_direction_input(mi->output_gpios[i]);
+			if (err) {
+				pr_err("gpiomatrix: gpio_configure failed for "
+					"output %d\n", mi->output_gpios[i]);
+				goto err_output_gpio_configure_failed;
+			}
+		}
+		for (i = 0; i < mi->ninputs; i++) {
+			err = gpio_request(mi->input_gpios[i], "gpio_kp_in");
+			if (err) {
+				pr_err("gpiomatrix: gpio_request failed for "
+					"input %d\n", mi->input_gpios[i]);
+				goto err_request_input_gpio_failed;
+			}
+			err = gpio_direction_input(mi->input_gpios[i]);
+			if (err) {
+				pr_err("gpiomatrix: gpio_direction_input failed"
+					" for input %d\n", mi->input_gpios[i]);
+				goto err_gpio_direction_input_failed;
+			}
+		}
+		kp->current_output = mi->noutputs;
+		kp->key_state_changed = 1;
+
+		hrtimer_init(&kp->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+		kp->timer.function = gpio_keypad_timer_func;
+		wake_lock_init(&kp->wake_lock, WAKE_LOCK_SUSPEND, "gpio_kp");
+		err = gpio_keypad_request_irqs(kp);
+		kp->use_irq = err == 0;
+
+		pr_info("GPIO Matrix Keypad Driver: Start keypad matrix for "
+			"%s%s in %s mode\n", input_devs->dev[0]->name,
+			(input_devs->count > 1) ? "..." : "",
+			kp->use_irq ? "interrupt" : "polling");
+
+		if (kp->use_irq)
+			wake_lock(&kp->wake_lock);
+		hrtimer_start(&kp->timer, ktime_set(0, 0), HRTIMER_MODE_REL);
+
+		return 0;
+	}
+
+	err = 0;
+	kp = *data;
+
+	if (kp->use_irq)
+		for (i = mi->noutputs - 1; i >= 0; i--)
+			free_irq(gpio_to_irq(mi->input_gpios[i]), kp);
+
+	hrtimer_cancel(&kp->timer);
+	wake_lock_destroy(&kp->wake_lock);
+	for (i = mi->noutputs - 1; i >= 0; i--) {
+err_gpio_direction_input_failed:
+		gpio_free(mi->input_gpios[i]);
+err_request_input_gpio_failed:
+		;
+	}
+	for (i = mi->noutputs - 1; i >= 0; i--) {
+err_output_gpio_configure_failed:
+		gpio_free(mi->output_gpios[i]);
+err_request_output_gpio_failed:
+		;
+	}
+err_bad_keymap:
+	kfree(kp);
+err_kp_alloc_failed:
+err_invalid_platform_data:
+	return err;
+}
diff --git a/drivers/input/misc/gpio_output.c b/drivers/input/misc/gpio_output.c
new file mode 100644
index 00000000000..2aac2fad0a1
--- /dev/null
+++ b/drivers/input/misc/gpio_output.c
@@ -0,0 +1,97 @@
+/* drivers/input/misc/gpio_output.c
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/gpio_event.h>
+
+int gpio_event_output_event(
+	struct gpio_event_input_devs *input_devs, struct gpio_event_info *info,
+	void **data, unsigned int dev, unsigned int type,
+	unsigned int code, int value)
+{
+	int i;
+	struct gpio_event_output_info *oi;
+	oi = container_of(info, struct gpio_event_output_info, info);
+	if (type != oi->type)
+		return 0;
+	if (!(oi->flags & GPIOEDF_ACTIVE_HIGH))
+		value = !value;
+	for (i = 0; i < oi->keymap_size; i++)
+		if (dev == oi->keymap[i].dev && code == oi->keymap[i].code)
+			gpio_set_value(oi->keymap[i].gpio, value);
+	return 0;
+}
+
+int gpio_event_output_func(
+	struct gpio_event_input_devs *input_devs, struct gpio_event_info *info,
+	void **data, int func)
+{
+	int ret;
+	int i;
+	struct gpio_event_output_info *oi;
+	oi = container_of(info, struct gpio_event_output_info, info);
+
+	if (func == GPIO_EVENT_FUNC_SUSPEND || func == GPIO_EVENT_FUNC_RESUME)
+		return 0;
+
+	if (func == GPIO_EVENT_FUNC_INIT) {
+		int output_level = !(oi->flags & GPIOEDF_ACTIVE_HIGH);
+
+		for (i = 0; i < oi->keymap_size; i++) {
+			int dev = oi->keymap[i].dev;
+			if (dev >= input_devs->count) {
+				pr_err("gpio_event_output_func: bad device "
+					"index %d >= %d for key code %d\n",
+					dev, input_devs->count,
+					oi->keymap[i].code);
+				ret = -EINVAL;
+				goto err_bad_keymap;
+			}
+			input_set_capability(input_devs->dev[dev], oi->type,
+					     oi->keymap[i].code);
+		}
+
+		for (i = 0; i < oi->keymap_size; i++) {
+			ret = gpio_request(oi->keymap[i].gpio,
+					   "gpio_event_output");
+			if (ret) {
+				pr_err("gpio_event_output_func: gpio_request "
+					"failed for %d\n", oi->keymap[i].gpio);
+				goto err_gpio_request_failed;
+			}
+			ret = gpio_direction_output(oi->keymap[i].gpio,
+						    output_level);
+			if (ret) {
+				pr_err("gpio_event_output_func: "
+					"gpio_direction_output failed for %d\n",
+					oi->keymap[i].gpio);
+				goto err_gpio_direction_output_failed;
+			}
+		}
+		return 0;
+	}
+
+	ret = 0;
+	for (i = oi->keymap_size - 1; i >= 0; i--) {
+err_gpio_direction_output_failed:
+		gpio_free(oi->keymap[i].gpio);
+err_gpio_request_failed:
+		;
+	}
+err_bad_keymap:
+	return ret;
+}
+
diff --git a/drivers/input/misc/keychord.c b/drivers/input/misc/keychord.c
new file mode 100644
index 00000000000..a5ea27ad0e1
--- /dev/null
+++ b/drivers/input/misc/keychord.c
@@ -0,0 +1,391 @@
+/*
+ *  drivers/input/misc/keychord.c
+ *
+ * Copyright (C) 2008 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+*/
+
+#include <linux/poll.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/keychord.h>
+#include <linux/sched.h>
+
+#define KEYCHORD_NAME		"keychord"
+#define BUFFER_SIZE			16
+
+MODULE_AUTHOR("Mike Lockwood <lockwood@android.com>");
+MODULE_DESCRIPTION("Key chord input driver");
+MODULE_SUPPORTED_DEVICE("keychord");
+MODULE_LICENSE("GPL");
+
+#define NEXT_KEYCHORD(kc) ((struct input_keychord *) \
+		((char *)kc + sizeof(struct input_keychord) + \
+		kc->count * sizeof(kc->keycodes[0])))
+
+struct keychord_device {
+	struct input_handler	input_handler;
+	int			registered;
+
+	/* list of keychords to monitor */
+	struct input_keychord	*keychords;
+	int			keychord_count;
+
+	/* bitmask of keys contained in our keychords */
+	unsigned long keybit[BITS_TO_LONGS(KEY_CNT)];
+	/* current state of the keys */
+	unsigned long keystate[BITS_TO_LONGS(KEY_CNT)];
+	/* number of keys that are currently pressed */
+	int key_down;
+
+	/* second input_device_id is needed for null termination */
+	struct input_device_id  device_ids[2];
+
+	spinlock_t		lock;
+	wait_queue_head_t	waitq;
+	unsigned char		head;
+	unsigned char		tail;
+	__u16			buff[BUFFER_SIZE];
+};
+
+static int check_keychord(struct keychord_device *kdev,
+		struct input_keychord *keychord)
+{
+	int i;
+
+	if (keychord->count != kdev->key_down)
+		return 0;
+
+	for (i = 0; i < keychord->count; i++) {
+		if (!test_bit(keychord->keycodes[i], kdev->keystate))
+			return 0;
+	}
+
+	/* we have a match */
+	return 1;
+}
+
+static void keychord_event(struct input_handle *handle, unsigned int type,
+			   unsigned int code, int value)
+{
+	struct keychord_device *kdev = handle->private;
+	struct input_keychord *keychord;
+	unsigned long flags;
+	int i, got_chord = 0;
+
+	if (type != EV_KEY || code >= KEY_MAX)
+		return;
+
+	spin_lock_irqsave(&kdev->lock, flags);
+	/* do nothing if key state did not change */
+	if (!test_bit(code, kdev->keystate) == !value)
+		goto done;
+	__change_bit(code, kdev->keystate);
+	if (value)
+		kdev->key_down++;
+	else
+		kdev->key_down--;
+
+	/* don't notify on key up */
+	if (!value)
+		goto done;
+	/* ignore this event if it is not one of the keys we are monitoring */
+	if (!test_bit(code, kdev->keybit))
+		goto done;
+
+	keychord = kdev->keychords;
+	if (!keychord)
+		goto done;
+
+	/* check to see if the keyboard state matches any keychords */
+	for (i = 0; i < kdev->keychord_count; i++) {
+		if (check_keychord(kdev, keychord)) {
+			kdev->buff[kdev->head] = keychord->id;
+			kdev->head = (kdev->head + 1) % BUFFER_SIZE;
+			got_chord = 1;
+			break;
+		}
+		/* skip to next keychord */
+		keychord = NEXT_KEYCHORD(keychord);
+	}
+
+done:
+	spin_unlock_irqrestore(&kdev->lock, flags);
+
+	if (got_chord) {
+		pr_info("keychord: got keychord id %d. Any tasks: %d\n",
+			keychord->id,
+			!list_empty_careful(&kdev->waitq.task_list));
+		wake_up_interruptible(&kdev->waitq);
+	}
+}
+
+static int keychord_connect(struct input_handler *handler,
+					  struct input_dev *dev,
+					  const struct input_device_id *id)
+{
+	int i, ret;
+	struct input_handle *handle;
+	struct keychord_device *kdev =
+		container_of(handler, struct keychord_device, input_handler);
+
+	/*
+	 * ignore this input device if it does not contain any keycodes
+	 * that we are monitoring
+	 */
+	for (i = 0; i < KEY_MAX; i++) {
+		if (test_bit(i, kdev->keybit) && test_bit(i, dev->keybit))
+			break;
+	}
+	if (i == KEY_MAX)
+		return -ENODEV;
+
+	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+	if (!handle)
+		return -ENOMEM;
+
+	handle->dev = dev;
+	handle->handler = handler;
+	handle->name = KEYCHORD_NAME;
+	handle->private = kdev;
+
+	ret = input_register_handle(handle);
+	if (ret)
+		goto err_input_register_handle;
+
+	ret = input_open_device(handle);
+	if (ret)
+		goto err_input_open_device;
+
+	pr_info("keychord: using input dev %s for fevent\n", dev->name);
+
+	return 0;
+
+err_input_open_device:
+	input_unregister_handle(handle);
+err_input_register_handle:
+	kfree(handle);
+	return ret;
+}
+
+static void keychord_disconnect(struct input_handle *handle)
+{
+	input_close_device(handle);
+	input_unregister_handle(handle);
+	kfree(handle);
+}
+
+/*
+ * keychord_read is used to read keychord events from the driver
+ */
+static ssize_t keychord_read(struct file *file, char __user *buffer,
+		size_t count, loff_t *ppos)
+{
+	struct keychord_device *kdev = file->private_data;
+	__u16   id;
+	int retval;
+	unsigned long flags;
+
+	if (count < sizeof(id))
+		return -EINVAL;
+	count = sizeof(id);
+
+	if (kdev->head == kdev->tail && (file->f_flags & O_NONBLOCK))
+		return -EAGAIN;
+
+	retval = wait_event_interruptible(kdev->waitq,
+			kdev->head != kdev->tail);
+	if (retval)
+		return retval;
+
+	spin_lock_irqsave(&kdev->lock, flags);
+	/* pop a keychord ID off the queue */
+	id = kdev->buff[kdev->tail];
+	kdev->tail = (kdev->tail + 1) % BUFFER_SIZE;
+	spin_unlock_irqrestore(&kdev->lock, flags);
+
+	if (copy_to_user(buffer, &id, count))
+		return -EFAULT;
+
+	return count;
+}
+
+/*
+ * keychord_write is used to configure the driver
+ */
+static ssize_t keychord_write(struct file *file, const char __user *buffer,
+		size_t count, loff_t *ppos)
+{
+	struct keychord_device *kdev = file->private_data;
+	struct input_keychord *keychords = 0;
+	struct input_keychord *keychord, *next, *end;
+	int ret, i, key;
+	unsigned long flags;
+
+	if (count < sizeof(struct input_keychord))
+		return -EINVAL;
+	keychords = kzalloc(count, GFP_KERNEL);
+	if (!keychords)
+		return -ENOMEM;
+
+	/* read list of keychords from userspace */
+	if (copy_from_user(keychords, buffer, count)) {
+		kfree(keychords);
+		return -EFAULT;
+	}
+
+	/* unregister handler before changing configuration */
+	if (kdev->registered) {
+		input_unregister_handler(&kdev->input_handler);
+		kdev->registered = 0;
+	}
+
+	spin_lock_irqsave(&kdev->lock, flags);
+	/* clear any existing configuration */
+	kfree(kdev->keychords);
+	kdev->keychords = 0;
+	kdev->keychord_count = 0;
+	kdev->key_down = 0;
+	memset(kdev->keybit, 0, sizeof(kdev->keybit));
+	memset(kdev->keystate, 0, sizeof(kdev->keystate));
+	kdev->head = kdev->tail = 0;
+
+	keychord = keychords;
+	end = (struct input_keychord *)((char *)keychord + count);
+
+	while (keychord < end) {
+		next = NEXT_KEYCHORD(keychord);
+		if (keychord->count <= 0 || next > end) {
+			pr_err("keychord: invalid keycode count %d\n",
+				keychord->count);
+			goto err_unlock_return;
+		}
+		if (keychord->version != KEYCHORD_VERSION) {
+			pr_err("keychord: unsupported version %d\n",
+				keychord->version);
+			goto err_unlock_return;
+		}
+
+		/* keep track of the keys we are monitoring in keybit */
+		for (i = 0; i < keychord->count; i++) {
+			key = keychord->keycodes[i];
+			if (key < 0 || key >= KEY_CNT) {
+				pr_err("keychord: keycode %d out of range\n",
+					key);
+				goto err_unlock_return;
+			}
+			__set_bit(key, kdev->keybit);
+		}
+
+		kdev->keychord_count++;
+		keychord = next;
+	}
+
+	kdev->keychords = keychords;
+	spin_unlock_irqrestore(&kdev->lock, flags);
+
+	ret = input_register_handler(&kdev->input_handler);
+	if (ret) {
+		kfree(keychords);
+		kdev->keychords = 0;
+		return ret;
+	}
+	kdev->registered = 1;
+
+	return count;
+
+err_unlock_return:
+	spin_unlock_irqrestore(&kdev->lock, flags);
+	kfree(keychords);
+	return -EINVAL;
+}
+
+static unsigned int keychord_poll(struct file *file, poll_table *wait)
+{
+	struct keychord_device *kdev = file->private_data;
+
+	poll_wait(file, &kdev->waitq, wait);
+
+	if (kdev->head != kdev->tail)
+		return POLLIN | POLLRDNORM;
+
+	return 0;
+}
+
+static int keychord_open(struct inode *inode, struct file *file)
+{
+	struct keychord_device *kdev;
+
+	kdev = kzalloc(sizeof(struct keychord_device), GFP_KERNEL);
+	if (!kdev)
+		return -ENOMEM;
+
+	spin_lock_init(&kdev->lock);
+	init_waitqueue_head(&kdev->waitq);
+
+	kdev->input_handler.event = keychord_event;
+	kdev->input_handler.connect = keychord_connect;
+	kdev->input_handler.disconnect = keychord_disconnect;
+	kdev->input_handler.name = KEYCHORD_NAME;
+	kdev->input_handler.id_table = kdev->device_ids;
+
+	kdev->device_ids[0].flags = INPUT_DEVICE_ID_MATCH_EVBIT;
+	__set_bit(EV_KEY, kdev->device_ids[0].evbit);
+
+	file->private_data = kdev;
+
+	return 0;
+}
+
+static int keychord_release(struct inode *inode, struct file *file)
+{
+	struct keychord_device *kdev = file->private_data;
+
+	if (kdev->registered)
+		input_unregister_handler(&kdev->input_handler);
+	kfree(kdev);
+
+	return 0;
+}
+
+static const struct file_operations keychord_fops = {
+	.owner		= THIS_MODULE,
+	.open		= keychord_open,
+	.release	= keychord_release,
+	.read		= keychord_read,
+	.write		= keychord_write,
+	.poll		= keychord_poll,
+};
+
+static struct miscdevice keychord_misc = {
+	.fops		= &keychord_fops,
+	.name		= KEYCHORD_NAME,
+	.minor		= MISC_DYNAMIC_MINOR,
+};
+
+static int __init keychord_init(void)
+{
+	return misc_register(&keychord_misc);
+}
+
+static void __exit keychord_exit(void)
+{
+	misc_deregister(&keychord_misc);
+}
+
+module_init(keychord_init);
+module_exit(keychord_exit);
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index d125a019383..54ff0379194 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -919,18 +919,21 @@ static void alps_get_finger_coordinate_v7(struct input_mt_pos *mt,
 
 static int alps_get_mt_count(struct input_mt_pos *mt)
 {
-	int i;
+	int i, fingers = 0;
 
-	for (i = 0; i < MAX_TOUCHES && mt[i].x != 0 && mt[i].y != 0; i++)
-		/* empty */;
+	for (i = 0; i < MAX_TOUCHES; i++) {
+		if (mt[i].x != 0 || mt[i].y != 0)
+			fingers++;
+	}
 
-	return i;
+	return fingers;
 }
 
 static int alps_decode_packet_v7(struct alps_fields *f,
 				  unsigned char *p,
 				  struct psmouse *psmouse)
 {
+	struct alps_data *priv = psmouse->private;
 	unsigned char pkt_id;
 
 	pkt_id = alps_get_packet_id_v7(p);
@@ -938,19 +941,52 @@ static int alps_decode_packet_v7(struct alps_fields *f,
 		return 0;
 	if (pkt_id == V7_PACKET_ID_UNKNOWN)
 		return -1;
+	/*
+	 * NEW packets are send to indicate a discontinuity in the finger
+	 * coordinate reporting. Specifically a finger may have moved from
+	 * slot 0 to 1 or vice versa. INPUT_MT_TRACK takes care of this for
+	 * us.
+	 *
+	 * NEW packets have 3 problems:
+	 * 1) They do not contain middle / right button info (on non clickpads)
+	 *    this can be worked around by preserving the old button state
+	 * 2) They do not contain an accurate fingercount, and they are
+	 *    typically send when the number of fingers changes. We cannot use
+	 *    the old finger count as that may mismatch with the amount of
+	 *    touch coordinates we've available in the NEW packet
+	 * 3) Their x data for the second touch is inaccurate leading to
+	 *    a possible jump of the x coordinate by 16 units when the first
+	 *    non NEW packet comes in
+	 * Since problems 2 & 3 cannot be worked around, just ignore them.
+	 */
+	if (pkt_id == V7_PACKET_ID_NEW)
+		return 1;
 
 	alps_get_finger_coordinate_v7(f->mt, p, pkt_id);
 
-	if (pkt_id == V7_PACKET_ID_TWO || pkt_id == V7_PACKET_ID_MULTI) {
-		f->left = (p[0] & 0x80) >> 7;
+	if (pkt_id == V7_PACKET_ID_TWO)
+		f->fingers = alps_get_mt_count(f->mt);
+	else /* pkt_id == V7_PACKET_ID_MULTI */
+		f->fingers = 3 + (p[5] & 0x03);
+
+	f->left = (p[0] & 0x80) >> 7;
+	if (priv->flags & ALPS_BUTTONPAD) {
+		if (p[0] & 0x20)
+			f->fingers++;
+		if (p[0] & 0x10)
+			f->fingers++;
+	} else {
 		f->right = (p[0] & 0x20) >> 5;
 		f->middle = (p[0] & 0x10) >> 4;
 	}
 
-	if (pkt_id == V7_PACKET_ID_TWO)
-		f->fingers = alps_get_mt_count(f->mt);
-	else if (pkt_id == V7_PACKET_ID_MULTI)
-		f->fingers = 3 + (p[5] & 0x03);
+	/* Sometimes a single touch is reported in mt[1] rather then mt[0] */
+	if (f->fingers == 1 && f->mt[0].x == 0 && f->mt[0].y == 0) {
+		f->mt[0].x = f->mt[1].x;
+		f->mt[0].y = f->mt[1].y;
+		f->mt[1].x = 0;
+		f->mt[1].y = 0;
+	}
 
 	return 0;
 }
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index f2b97802640..aa7f9209ac6 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -893,6 +893,21 @@ static psmouse_ret_t elantech_process_byte(struct psmouse *psmouse)
 }
 
 /*
+ * This writes the reg_07 value again to the hardware at the end of every
+ * set_rate call because the register loses its value. reg_07 allows setting
+ * absolute mode on v4 hardware
+ */
+static void elantech_set_rate_restore_reg_07(struct psmouse *psmouse,
+		unsigned int rate)
+{
+	struct elantech_data *etd = psmouse->private;
+
+	etd->original_set_rate(psmouse, rate);
+	if (elantech_write_reg(psmouse, 0x07, etd->reg_07))
+		psmouse_err(psmouse, "restoring reg_07 failed\n");
+}
+
+/*
  * Put the touchpad into absolute mode
  */
 static int elantech_set_absolute_mode(struct psmouse *psmouse)
@@ -1094,9 +1109,13 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse,
  * Asus K53SV              0x450f01        78, 15, 0c      2 hw buttons
  * Asus G46VW              0x460f02        00, 18, 0c      2 hw buttons
  * Asus G750JX             0x360f00        00, 16, 0c      2 hw buttons
+ * Asus TP500LN            0x381f17        10, 14, 0e      clickpad
+ * Asus X750JN             0x381f17        10, 14, 0e      clickpad
  * Asus UX31               0x361f00        20, 15, 0e      clickpad
  * Asus UX32VD             0x361f02        00, 15, 0e      clickpad
  * Avatar AVIU-145A2       0x361f00        ?               clickpad
+ * Fujitsu LIFEBOOK E544   0x470f00        d0, 12, 09      2 hw buttons
+ * Fujitsu LIFEBOOK E554   0x570f01        40, 14, 0c      2 hw buttons
  * Fujitsu H730            0x570f00        c0, 14, 0c      3 hw buttons (**)
  * Gigabyte U2442          0x450f01        58, 17, 0c      2 hw buttons
  * Lenovo L430             0x350f02        b9, 15, 0c      2 hw buttons (*)
@@ -1357,10 +1376,11 @@ static bool elantech_is_signature_valid(const unsigned char *param)
 		return true;
 
 	/*
-	 * Some models have a revision higher then 20. Meaning param[2] may
-	 * be 10 or 20, skip the rates check for these.
+	 * Some hw_version >= 4 models have a revision higher then 20. Meaning
+	 * that param[2] may be 10 or 20, skip the rates check for these.
 	 */
-	if (param[0] == 0x46 && (param[1] & 0xef) == 0x0f && param[2] < 40)
+	if ((param[0] & 0x0f) >= 0x06 && (param[1] & 0xaf) == 0x0f &&
+	    param[2] < 40)
 		return true;
 
 	for (i = 0; i < ARRAY_SIZE(rates); i++)
@@ -1475,6 +1495,20 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "CELSIUS H730"),
 		},
 	},
+	{
+		/* Fujitsu LIFEBOOK E554  does not work with crc_enabled == 0 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E554"),
+		},
+	},
+	{
+		/* Fujitsu LIFEBOOK E544  does not work with crc_enabled == 0 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E544"),
+		},
+	},
 #endif
 	{ }
 };
@@ -1520,6 +1554,8 @@ static int elantech_set_properties(struct elantech_data *etd)
 		case 7:
 		case 8:
 		case 9:
+		case 10:
+		case 13:
 			etd->hw_version = 4;
 			break;
 		default:
@@ -1617,6 +1653,11 @@ int elantech_init(struct psmouse *psmouse)
 		goto init_fail;
 	}
 
+	if (etd->fw_version == 0x381f17) {
+		etd->original_set_rate = psmouse->set_rate;
+		psmouse->set_rate = elantech_set_rate_restore_reg_07;
+	}
+
 	if (elantech_set_input_params(psmouse)) {
 		psmouse_err(psmouse, "failed to query touchpad range.\n");
 		goto init_fail;
diff --git a/drivers/input/mouse/elantech.h b/drivers/input/mouse/elantech.h
index 6f3afec02f0..f965d1569cc 100644
--- a/drivers/input/mouse/elantech.h
+++ b/drivers/input/mouse/elantech.h
@@ -142,6 +142,7 @@ struct elantech_data {
 	struct finger_pos mt[ETP_MAX_FINGERS];
 	unsigned char parity[256];
 	int (*send_cmd)(struct psmouse *psmouse, unsigned char c, unsigned char *param);
+	void (*original_set_rate)(struct psmouse *psmouse, unsigned int rate);
 };
 
 #ifdef CONFIG_MOUSE_PS2_ELANTECH
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index f9472920d98..826ef3df2dc 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -120,31 +120,46 @@ void synaptics_reset(struct psmouse *psmouse)
 
 static bool cr48_profile_sensor;
 
+#define ANY_BOARD_ID 0
 struct min_max_quirk {
 	const char * const *pnp_ids;
+	struct {
+		unsigned long int min, max;
+	} board_id;
 	int x_min, x_max, y_min, y_max;
 };
 
 static const struct min_max_quirk min_max_pnpid_table[] = {
 	{
 		(const char * const []){"LEN0033", NULL},
+		{ANY_BOARD_ID, ANY_BOARD_ID},
 		1024, 5052, 2258, 4832
 	},
 	{
-		(const char * const []){"LEN0035", "LEN0042", NULL},
+		(const char * const []){"LEN0042", NULL},
+		{ANY_BOARD_ID, ANY_BOARD_ID},
 		1232, 5710, 1156, 4696
 	},
 	{
-		(const char * const []){"LEN0034", "LEN0036", "LEN0039",
-					"LEN2002", "LEN2004", NULL},
+		(const char * const []){"LEN0034", "LEN0036", "LEN0037",
+					"LEN0039", "LEN2002", "LEN2004",
+					NULL},
+		{ANY_BOARD_ID, 2961},
 		1024, 5112, 2024, 4832
 	},
 	{
+		(const char * const []){"LEN2000", NULL},
+		{ANY_BOARD_ID, ANY_BOARD_ID},
+		1024, 5113, 2021, 4832
+	},
+	{
 		(const char * const []){"LEN2001", NULL},
+		{ANY_BOARD_ID, ANY_BOARD_ID},
 		1024, 5022, 2508, 4832
 	},
 	{
 		(const char * const []){"LEN2006", NULL},
+		{ANY_BOARD_ID, ANY_BOARD_ID},
 		1264, 5675, 1171, 4688
 	},
 	{ }
@@ -165,7 +180,7 @@ static const char * const topbuttonpad_pnp_ids[] = {
 	"LEN0034", /* T431s, L440, L540, T540, W540, X1 Carbon 2nd */
 	"LEN0035", /* X240 */
 	"LEN0036", /* T440 */
-	"LEN0037",
+	"LEN0037", /* X1 Carbon 2nd */
 	"LEN0038",
 	"LEN0039", /* T440s */
 	"LEN0041",
@@ -175,7 +190,7 @@ static const char * const topbuttonpad_pnp_ids[] = {
 	"LEN0047",
 	"LEN0048",
 	"LEN0049",
-	"LEN2000",
+	"LEN2000", /* S540 */
 	"LEN2001", /* Edge E431 */
 	"LEN2002", /* Edge E531 */
 	"LEN2003",
@@ -240,6 +255,10 @@ static int synaptics_board_id(struct psmouse *psmouse)
 	struct synaptics_data *priv = psmouse->private;
 	unsigned char bid[3];
 
+	/* firmwares prior 7.5 have no board_id encoded */
+	if (SYN_ID_FULL(priv->identity) < 0x705)
+		return 0;
+
 	if (synaptics_send_cmd(psmouse, SYN_QUE_MODES, bid))
 		return -1;
 	priv->board_id = ((bid[0] & 0xfc) << 6) | bid[1];
@@ -342,7 +361,6 @@ static int synaptics_resolution(struct psmouse *psmouse)
 {
 	struct synaptics_data *priv = psmouse->private;
 	unsigned char resp[3];
-	int i;
 
 	if (SYN_ID_MAJOR(priv->identity) < 4)
 		return 0;
@@ -354,17 +372,6 @@ static int synaptics_resolution(struct psmouse *psmouse)
 		}
 	}
 
-	for (i = 0; min_max_pnpid_table[i].pnp_ids; i++) {
-		if (psmouse_matches_pnp_id(psmouse,
-					   min_max_pnpid_table[i].pnp_ids)) {
-			priv->x_min = min_max_pnpid_table[i].x_min;
-			priv->x_max = min_max_pnpid_table[i].x_max;
-			priv->y_min = min_max_pnpid_table[i].y_min;
-			priv->y_max = min_max_pnpid_table[i].y_max;
-			return 0;
-		}
-	}
-
 	if (SYN_EXT_CAP_REQUESTS(priv->capabilities) >= 5 &&
 	    SYN_CAP_MAX_DIMENSIONS(priv->ext_cap_0c)) {
 		if (synaptics_send_cmd(psmouse, SYN_QUE_EXT_MAX_COORDS, resp)) {
@@ -373,23 +380,69 @@ static int synaptics_resolution(struct psmouse *psmouse)
 		} else {
 			priv->x_max = (resp[0] << 5) | ((resp[1] & 0x0f) << 1);
 			priv->y_max = (resp[2] << 5) | ((resp[1] & 0xf0) >> 3);
+			psmouse_info(psmouse,
+				     "queried max coordinates: x [..%d], y [..%d]\n",
+				     priv->x_max, priv->y_max);
 		}
 	}
 
-	if (SYN_EXT_CAP_REQUESTS(priv->capabilities) >= 7 &&
-	    SYN_CAP_MIN_DIMENSIONS(priv->ext_cap_0c)) {
+	if (SYN_CAP_MIN_DIMENSIONS(priv->ext_cap_0c) &&
+	    (SYN_EXT_CAP_REQUESTS(priv->capabilities) >= 7 ||
+	     /*
+	      * Firmware v8.1 does not report proper number of extended
+	      * capabilities, but has been proven to report correct min
+	      * coordinates.
+	      */
+	     SYN_ID_FULL(priv->identity) == 0x801)) {
 		if (synaptics_send_cmd(psmouse, SYN_QUE_EXT_MIN_COORDS, resp)) {
 			psmouse_warn(psmouse,
 				     "device claims to have min coordinates query, but I'm not able to read it.\n");
 		} else {
 			priv->x_min = (resp[0] << 5) | ((resp[1] & 0x0f) << 1);
 			priv->y_min = (resp[2] << 5) | ((resp[1] & 0xf0) >> 3);
+			psmouse_info(psmouse,
+				     "queried min coordinates: x [%d..], y [%d..]\n",
+				     priv->x_min, priv->y_min);
 		}
 	}
 
 	return 0;
 }
 
+/*
+ * Apply quirk(s) if the hardware matches
+ */
+
+static void synaptics_apply_quirks(struct psmouse *psmouse)
+{
+	struct synaptics_data *priv = psmouse->private;
+	int i;
+
+	for (i = 0; min_max_pnpid_table[i].pnp_ids; i++) {
+		if (!psmouse_matches_pnp_id(psmouse,
+					    min_max_pnpid_table[i].pnp_ids))
+			continue;
+
+		if (min_max_pnpid_table[i].board_id.min != ANY_BOARD_ID &&
+		    priv->board_id < min_max_pnpid_table[i].board_id.min)
+			continue;
+
+		if (min_max_pnpid_table[i].board_id.max != ANY_BOARD_ID &&
+		    priv->board_id > min_max_pnpid_table[i].board_id.max)
+			continue;
+
+		priv->x_min = min_max_pnpid_table[i].x_min;
+		priv->x_max = min_max_pnpid_table[i].x_max;
+		priv->y_min = min_max_pnpid_table[i].y_min;
+		priv->y_max = min_max_pnpid_table[i].y_max;
+		psmouse_info(psmouse,
+			     "quirked min/max coordinates: x [%d..%d], y [%d..%d]\n",
+			     priv->x_min, priv->x_max,
+			     priv->y_min, priv->y_max);
+		break;
+	}
+}
+
 static int synaptics_query_hardware(struct psmouse *psmouse)
 {
 	if (synaptics_identify(psmouse))
@@ -405,6 +458,8 @@ static int synaptics_query_hardware(struct psmouse *psmouse)
 	if (synaptics_resolution(psmouse))
 		return -1;
 
+	synaptics_apply_quirks(psmouse);
+
 	return 0;
 }
 
@@ -612,6 +667,18 @@ static void synaptics_parse_agm(const unsigned char buf[],
 	priv->agm_pending = true;
 }
 
+static void synaptics_parse_ext_buttons(const unsigned char buf[],
+					struct synaptics_data *priv,
+					struct synaptics_hw_state *hw)
+{
+	unsigned int ext_bits =
+		(SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) + 1) >> 1;
+	unsigned int ext_mask = GENMASK(ext_bits - 1, 0);
+
+	hw->ext_buttons = buf[4] & ext_mask;
+	hw->ext_buttons |= (buf[5] & ext_mask) << ext_bits;
+}
+
 static bool is_forcepad;
 
 static int synaptics_parse_hw_state(const unsigned char buf[],
@@ -698,28 +765,9 @@ static int synaptics_parse_hw_state(const unsigned char buf[],
 			hw->down = ((buf[0] ^ buf[3]) & 0x02) ? 1 : 0;
 		}
 
-		if (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) &&
+		if (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) > 0 &&
 		    ((buf[0] ^ buf[3]) & 0x02)) {
-			switch (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) & ~0x01) {
-			default:
-				/*
-				 * if nExtBtn is greater than 8 it should be
-				 * considered invalid and treated as 0
-				 */
-				break;
-			case 8:
-				hw->ext_buttons |= ((buf[5] & 0x08)) ? 0x80 : 0;
-				hw->ext_buttons |= ((buf[4] & 0x08)) ? 0x40 : 0;
-			case 6:
-				hw->ext_buttons |= ((buf[5] & 0x04)) ? 0x20 : 0;
-				hw->ext_buttons |= ((buf[4] & 0x04)) ? 0x10 : 0;
-			case 4:
-				hw->ext_buttons |= ((buf[5] & 0x02)) ? 0x08 : 0;
-				hw->ext_buttons |= ((buf[4] & 0x02)) ? 0x04 : 0;
-			case 2:
-				hw->ext_buttons |= ((buf[5] & 0x01)) ? 0x02 : 0;
-				hw->ext_buttons |= ((buf[4] & 0x01)) ? 0x01 : 0;
-			}
+			synaptics_parse_ext_buttons(buf, priv, hw);
 		}
 	} else {
 		hw->x = (((buf[1] & 0x1f) << 8) | buf[2]);
@@ -781,12 +829,35 @@ static void synaptics_report_semi_mt_data(struct input_dev *dev,
 	}
 }
 
+static void synaptics_report_ext_buttons(struct psmouse *psmouse,
+					 const struct synaptics_hw_state *hw)
+{
+	struct input_dev *dev = psmouse->dev;
+	struct synaptics_data *priv = psmouse->private;
+	int ext_bits = (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) + 1) >> 1;
+	int i;
+
+	if (!SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap))
+		return;
+
+	/* Bug in FW 8.1, buttons are reported only when ExtBit is 1 */
+	if (SYN_ID_FULL(priv->identity) == 0x801 &&
+	    !((psmouse->packet[0] ^ psmouse->packet[3]) & 0x02))
+		return;
+
+	for (i = 0; i < ext_bits; i++) {
+		input_report_key(dev, BTN_0 + 2 * i,
+			hw->ext_buttons & (1 << i));
+		input_report_key(dev, BTN_1 + 2 * i,
+			hw->ext_buttons & (1 << (i + ext_bits)));
+	}
+}
+
 static void synaptics_report_buttons(struct psmouse *psmouse,
 				     const struct synaptics_hw_state *hw)
 {
 	struct input_dev *dev = psmouse->dev;
 	struct synaptics_data *priv = psmouse->private;
-	int i;
 
 	input_report_key(dev, BTN_LEFT, hw->left);
 	input_report_key(dev, BTN_RIGHT, hw->right);
@@ -799,8 +870,7 @@ static void synaptics_report_buttons(struct psmouse *psmouse,
 		input_report_key(dev, BTN_BACK, hw->down);
 	}
 
-	for (i = 0; i < SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap); i++)
-		input_report_key(dev, BTN_0 + i, hw->ext_buttons & (1 << i));
+	synaptics_report_ext_buttons(psmouse, hw);
 }
 
 static void synaptics_report_slot(struct input_dev *dev, int slot,
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index faeeb137246..39bec4715f2 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -152,6 +152,14 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = {
 		},
 	},
 	{
+		/* Medion Akoya E7225 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Medion"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Akoya E7225"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"),
+		},
+	},
+	{
 		/* Blue FB5601 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "blue"),
@@ -415,6 +423,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = {
 		},
 	},
 	{
+		/* Acer Aspire 7738 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 7738"),
+		},
+	},
+	{
 		/* Gericom Bellagio */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Gericom"),
@@ -735,6 +750,35 @@ static const struct dmi_system_id __initconst i8042_dmi_dritek_table[] = {
 	{ }
 };
 
+/*
+ * Some laptops need keyboard reset before probing for the trackpad to get
+ * it detected, initialised & finally work.
+ */
+static const struct dmi_system_id __initconst i8042_dmi_kbdreset_table[] = {
+	{
+		/* Gigabyte P35 v2 - Elantech touchpad */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P35V2"),
+		},
+	},
+		{
+		/* Aorus branded Gigabyte X3 Plus - Elantech touchpad */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X3"),
+		},
+	},
+	{
+		/* Gigabyte P34 - Elantech touchpad */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P34"),
+		},
+	},
+	{ }
+};
+
 #endif /* CONFIG_X86 */
 
 #ifdef CONFIG_PNP
@@ -1030,6 +1074,9 @@ static int __init i8042_platform_init(void)
 	if (dmi_check_system(i8042_dmi_dritek_table))
 		i8042_dritek = true;
 
+	if (dmi_check_system(i8042_dmi_kbdreset_table))
+		i8042_kbdreset = true;
+
 	/*
 	 * A20 was already enabled during early kernel init. But some buggy
 	 * BIOSes (in MSI Laptops) require A20 to be enabled using 8042 to
diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index f5a98af3b32..804d2e02010 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -67,6 +67,10 @@ static bool i8042_notimeout;
 module_param_named(notimeout, i8042_notimeout, bool, 0);
 MODULE_PARM_DESC(notimeout, "Ignore timeouts signalled by i8042");
 
+static bool i8042_kbdreset;
+module_param_named(kbdreset, i8042_kbdreset, bool, 0);
+MODULE_PARM_DESC(kbdreset, "Reset device connected to KBD port");
+
 #ifdef CONFIG_X86
 static bool i8042_dritek;
 module_param_named(dritek, i8042_dritek, bool, 0);
@@ -790,6 +794,16 @@ static int __init i8042_check_aux(void)
 		return -1;
 
 /*
+ * Reset keyboard (needed on some laptops to successfully detect
+ * touchpad, e.g., some Gigabyte laptop models with Elantech
+ * touchpads).
+ */
+	if (i8042_kbdreset) {
+		pr_warn("Attempting to reset device connected to KBD port\n");
+		i8042_kbd_write(NULL, (unsigned char) 0xff);
+	}
+
+/*
  * Test AUX IRQ delivery to make sure BIOS did not grab the IRQ and
  * used it for a PCI card or somethig else.
  */
diff --git a/drivers/input/touchscreen/pixcir_i2c_ts.c b/drivers/input/touchscreen/pixcir_i2c_ts.c
index fc49c75317d..9788a9b4a61 100644
--- a/drivers/input/touchscreen/pixcir_i2c_ts.c
+++ b/drivers/input/touchscreen/pixcir_i2c_ts.c
@@ -78,7 +78,7 @@ static void pixcir_ts_parse(struct pixcir_i2c_ts_data *tsdata,
 	}
 
 	ret = i2c_master_recv(tsdata->client, rdbuf, readsize);
-	if (ret != sizeof(rdbuf)) {
+	if (ret != readsize) {
 		dev_err(&tsdata->client->dev,
 			"%s: i2c_master_recv failed(), ret=%d\n",
 			__func__, ret);
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index dd5112265cc..7e1bc326266 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -13,6 +13,32 @@ menuconfig IOMMU_SUPPORT
 
 if IOMMU_SUPPORT
 
+menu "Generic IOMMU Pagetable Support"
+
+# Selected by the actual pagetable implementations
+config IOMMU_IO_PGTABLE
+	bool
+
+config IOMMU_IO_PGTABLE_LPAE
+	bool "ARMv7/v8 Long Descriptor Format"
+	select IOMMU_IO_PGTABLE
+	help
+	  Enable support for the ARM long descriptor pagetable format.
+	  This allocator supports 4K/2M/1G, 16K/32M and 64K/512M page
+	  sizes at both stage-1 and stage-2, as well as address spaces
+	  up to 48-bits in size.
+
+config IOMMU_IO_PGTABLE_LPAE_SELFTEST
+	bool "LPAE selftests"
+	depends on IOMMU_IO_PGTABLE_LPAE
+	help
+	  Enable self-tests for LPAE page table allocator. This performs
+	  a series of page-table consistency checks during boot.
+
+	  If unsure, say N here.
+
+endmenu
+
 config OF_IOMMU
        def_bool y
        depends on OF
@@ -291,13 +317,13 @@ config SPAPR_TCE_IOMMU
 
 config ARM_SMMU
 	bool "ARM Ltd. System MMU (SMMU) Support"
-	depends on ARM64 || (ARM_LPAE && OF)
+	depends on ARM64 || ARM
 	select IOMMU_API
+	select IOMMU_IO_PGTABLE_LPAE
 	select ARM_DMA_USE_IOMMU if ARM
 	help
 	  Support for implementations of the ARM System MMU architecture
-	  versions 1 and 2. The driver supports both v7l and v8l table
-	  formats with 4k and 64k page sizes.
+	  versions 1 and 2.
 
 	  Say Y here if your SoC includes an IOMMU device implementing
 	  the ARM SMMU architecture.
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 16edef74b8e..269cdd82b67 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -1,6 +1,8 @@
 obj-$(CONFIG_IOMMU_API) += iommu.o
 obj-$(CONFIG_IOMMU_API) += iommu-traces.o
 obj-$(CONFIG_IOMMU_API) += iommu-sysfs.o
+obj-$(CONFIG_IOMMU_IO_PGTABLE) += io-pgtable.o
+obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o
 obj-$(CONFIG_OF_IOMMU)	+= of_iommu.o
 obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o msm_iommu_dev.o
 obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 505a9adac2d..fab0ea1a46d 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -1870,9 +1870,15 @@ static void free_pt_##LVL (unsigned long __pt)			\
 	pt = (u64 *)__pt;					\
 								\
 	for (i = 0; i < 512; ++i) {				\
+		/* PTE present? */				\
 		if (!IOMMU_PTE_PRESENT(pt[i]))			\
 			continue;				\
 								\
+		/* Large PTE? */				\
+		if (PM_PTE_LEVEL(pt[i]) == 0 ||			\
+		    PM_PTE_LEVEL(pt[i]) == 7)			\
+			continue;				\
+								\
 		p = (unsigned long)IOMMU_PTE_PAGE(pt[i]);	\
 		FN(p);						\
 	}							\
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 60558f79492..49c03a37655 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -23,8 +23,6 @@
  *	- Stream-matching and stream-indexing
  *	- v7/v8 long-descriptor format
  *	- Non-secure access to the SMMU
- *	- 4k and 64k pages, with contiguous pte hints.
- *	- Up to 48-bit addressing (dependent on VA_BITS)
  *	- Context fault reporting
  */
 
@@ -36,7 +34,6 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/iommu.h>
-#include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/pci.h>
@@ -46,7 +43,7 @@
 
 #include <linux/amba/bus.h>
 
-#include <asm/pgalloc.h>
+#include "io-pgtable.h"
 
 /* Maximum number of stream IDs assigned to a single device */
 #define MAX_MASTER_STREAMIDS		MAX_PHANDLE_ARGS
@@ -71,40 +68,6 @@
 		((smmu->options & ARM_SMMU_OPT_SECURE_CFG_ACCESS)	\
 			? 0x400 : 0))
 
-/* Page table bits */
-#define ARM_SMMU_PTE_XN			(((pteval_t)3) << 53)
-#define ARM_SMMU_PTE_CONT		(((pteval_t)1) << 52)
-#define ARM_SMMU_PTE_AF			(((pteval_t)1) << 10)
-#define ARM_SMMU_PTE_SH_NS		(((pteval_t)0) << 8)
-#define ARM_SMMU_PTE_SH_OS		(((pteval_t)2) << 8)
-#define ARM_SMMU_PTE_SH_IS		(((pteval_t)3) << 8)
-#define ARM_SMMU_PTE_PAGE		(((pteval_t)3) << 0)
-
-#if PAGE_SIZE == SZ_4K
-#define ARM_SMMU_PTE_CONT_ENTRIES	16
-#elif PAGE_SIZE == SZ_64K
-#define ARM_SMMU_PTE_CONT_ENTRIES	32
-#else
-#define ARM_SMMU_PTE_CONT_ENTRIES	1
-#endif
-
-#define ARM_SMMU_PTE_CONT_SIZE		(PAGE_SIZE * ARM_SMMU_PTE_CONT_ENTRIES)
-#define ARM_SMMU_PTE_CONT_MASK		(~(ARM_SMMU_PTE_CONT_SIZE - 1))
-
-/* Stage-1 PTE */
-#define ARM_SMMU_PTE_AP_UNPRIV		(((pteval_t)1) << 6)
-#define ARM_SMMU_PTE_AP_RDONLY		(((pteval_t)2) << 6)
-#define ARM_SMMU_PTE_ATTRINDX_SHIFT	2
-#define ARM_SMMU_PTE_nG			(((pteval_t)1) << 11)
-
-/* Stage-2 PTE */
-#define ARM_SMMU_PTE_HAP_FAULT		(((pteval_t)0) << 6)
-#define ARM_SMMU_PTE_HAP_READ		(((pteval_t)1) << 6)
-#define ARM_SMMU_PTE_HAP_WRITE		(((pteval_t)2) << 6)
-#define ARM_SMMU_PTE_MEMATTR_OIWB	(((pteval_t)0xf) << 2)
-#define ARM_SMMU_PTE_MEMATTR_NC		(((pteval_t)0x5) << 2)
-#define ARM_SMMU_PTE_MEMATTR_DEV	(((pteval_t)0x1) << 2)
-
 /* Configuration registers */
 #define ARM_SMMU_GR0_sCR0		0x0
 #define sCR0_CLIENTPD			(1 << 0)
@@ -132,17 +95,11 @@
 #define ARM_SMMU_GR0_sGFSYNR0		0x50
 #define ARM_SMMU_GR0_sGFSYNR1		0x54
 #define ARM_SMMU_GR0_sGFSYNR2		0x58
-#define ARM_SMMU_GR0_PIDR0		0xfe0
-#define ARM_SMMU_GR0_PIDR1		0xfe4
-#define ARM_SMMU_GR0_PIDR2		0xfe8
 
 #define ID0_S1TS			(1 << 30)
 #define ID0_S2TS			(1 << 29)
 #define ID0_NTS				(1 << 28)
 #define ID0_SMS				(1 << 27)
-#define ID0_PTFS_SHIFT			24
-#define ID0_PTFS_MASK			0x2
-#define ID0_PTFS_V8_ONLY		0x2
 #define ID0_CTTW			(1 << 14)
 #define ID0_NUMIRPT_SHIFT		16
 #define ID0_NUMIRPT_MASK		0xff
@@ -169,11 +126,7 @@
 #define ID2_PTFS_16K			(1 << 13)
 #define ID2_PTFS_64K			(1 << 14)
 
-#define PIDR2_ARCH_SHIFT		4
-#define PIDR2_ARCH_MASK			0xf
-
 /* Global TLB invalidation */
-#define ARM_SMMU_GR0_STLBIALL		0x60
 #define ARM_SMMU_GR0_TLBIVMID		0x64
 #define ARM_SMMU_GR0_TLBIALLNSNH	0x68
 #define ARM_SMMU_GR0_TLBIALLH		0x6c
@@ -231,13 +184,20 @@
 #define ARM_SMMU_CB_TTBCR2		0x10
 #define ARM_SMMU_CB_TTBR0_LO		0x20
 #define ARM_SMMU_CB_TTBR0_HI		0x24
+#define ARM_SMMU_CB_TTBR1_LO		0x28
+#define ARM_SMMU_CB_TTBR1_HI		0x2c
 #define ARM_SMMU_CB_TTBCR		0x30
 #define ARM_SMMU_CB_S1_MAIR0		0x38
+#define ARM_SMMU_CB_S1_MAIR1		0x3c
 #define ARM_SMMU_CB_FSR			0x58
 #define ARM_SMMU_CB_FAR_LO		0x60
 #define ARM_SMMU_CB_FAR_HI		0x64
 #define ARM_SMMU_CB_FSYNR0		0x68
+#define ARM_SMMU_CB_S1_TLBIVA		0x600
 #define ARM_SMMU_CB_S1_TLBIASID		0x610
+#define ARM_SMMU_CB_S1_TLBIVAL		0x620
+#define ARM_SMMU_CB_S2_TLBIIPAS2	0x630
+#define ARM_SMMU_CB_S2_TLBIIPAS2L	0x638
 
 #define SCTLR_S1_ASIDPNE		(1 << 12)
 #define SCTLR_CFCFG			(1 << 7)
@@ -252,44 +212,9 @@
 #define RESUME_RETRY			(0 << 0)
 #define RESUME_TERMINATE		(1 << 0)
 
-#define TTBCR_EAE			(1 << 31)
-
-#define TTBCR_PASIZE_SHIFT		16
-#define TTBCR_PASIZE_MASK		0x7
-
-#define TTBCR_TG0_4K			(0 << 14)
-#define TTBCR_TG0_64K			(1 << 14)
-
-#define TTBCR_SH0_SHIFT			12
-#define TTBCR_SH0_MASK			0x3
-#define TTBCR_SH_NS			0
-#define TTBCR_SH_OS			2
-#define TTBCR_SH_IS			3
-
-#define TTBCR_ORGN0_SHIFT		10
-#define TTBCR_IRGN0_SHIFT		8
-#define TTBCR_RGN_MASK			0x3
-#define TTBCR_RGN_NC			0
-#define TTBCR_RGN_WBWA			1
-#define TTBCR_RGN_WT			2
-#define TTBCR_RGN_WB			3
-
-#define TTBCR_SL0_SHIFT			6
-#define TTBCR_SL0_MASK			0x3
-#define TTBCR_SL0_LVL_2			0
-#define TTBCR_SL0_LVL_1			1
-
-#define TTBCR_T1SZ_SHIFT		16
-#define TTBCR_T0SZ_SHIFT		0
-#define TTBCR_SZ_MASK			0xf
-
 #define TTBCR2_SEP_SHIFT		15
 #define TTBCR2_SEP_MASK			0x7
 
-#define TTBCR2_PASIZE_SHIFT		0
-#define TTBCR2_PASIZE_MASK		0x7
-
-/* Common definitions for PASize and SEP fields */
 #define TTBCR2_ADDR_32			0
 #define TTBCR2_ADDR_36			1
 #define TTBCR2_ADDR_40			2
@@ -297,16 +222,7 @@
 #define TTBCR2_ADDR_44			4
 #define TTBCR2_ADDR_48			5
 
-#define TTBRn_HI_ASID_SHIFT		16
-
-#define MAIR_ATTR_SHIFT(n)		((n) << 3)
-#define MAIR_ATTR_MASK			0xff
-#define MAIR_ATTR_DEVICE		0x04
-#define MAIR_ATTR_NC			0x44
-#define MAIR_ATTR_WBRWA			0xff
-#define MAIR_ATTR_IDX_NC		0
-#define MAIR_ATTR_IDX_CACHE		1
-#define MAIR_ATTR_IDX_DEV		2
+#define TTBRn_HI_ASID_SHIFT            16
 
 #define FSR_MULTI			(1 << 31)
 #define FSR_SS				(1 << 30)
@@ -380,10 +296,9 @@ struct arm_smmu_device {
 	u32				num_mapping_groups;
 	DECLARE_BITMAP(smr_map, ARM_SMMU_MAX_SMRS);
 
-	unsigned long			s1_input_size;
-	unsigned long			s1_output_size;
-	unsigned long			s2_input_size;
-	unsigned long			s2_output_size;
+	unsigned long			va_size;
+	unsigned long			ipa_size;
+	unsigned long			pa_size;
 
 	u32				num_global_irqs;
 	u32				num_context_irqs;
@@ -397,19 +312,29 @@ struct arm_smmu_cfg {
 	u8				cbndx;
 	u8				irptndx;
 	u32				cbar;
-	pgd_t				*pgd;
 };
 #define INVALID_IRPTNDX			0xff
 
 #define ARM_SMMU_CB_ASID(cfg)		((cfg)->cbndx)
 #define ARM_SMMU_CB_VMID(cfg)		((cfg)->cbndx + 1)
 
+enum arm_smmu_domain_stage {
+	ARM_SMMU_DOMAIN_S1 = 0,
+	ARM_SMMU_DOMAIN_S2,
+	ARM_SMMU_DOMAIN_NESTED,
+};
+
 struct arm_smmu_domain {
 	struct arm_smmu_device		*smmu;
+	struct io_pgtable_ops		*pgtbl_ops;
+	spinlock_t			pgtbl_lock;
 	struct arm_smmu_cfg		cfg;
-	spinlock_t			lock;
+	enum arm_smmu_domain_stage	stage;
+	struct mutex			init_mutex; /* Protects smmu pointer */
 };
 
+static struct iommu_ops arm_smmu_ops;
+
 static DEFINE_SPINLOCK(arm_smmu_devices_lock);
 static LIST_HEAD(arm_smmu_devices);
 
@@ -590,7 +515,7 @@ static void __arm_smmu_free_bitmap(unsigned long *map, int idx)
 }
 
 /* Wait for any pending TLB invalidations to complete */
-static void arm_smmu_tlb_sync(struct arm_smmu_device *smmu)
+static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu)
 {
 	int count = 0;
 	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
@@ -608,12 +533,19 @@ static void arm_smmu_tlb_sync(struct arm_smmu_device *smmu)
 	}
 }
 
-static void arm_smmu_tlb_inv_context(struct arm_smmu_domain *smmu_domain)
+static void arm_smmu_tlb_sync(void *cookie)
 {
+	struct arm_smmu_domain *smmu_domain = cookie;
+	__arm_smmu_tlb_sync(smmu_domain->smmu);
+}
+
+static void arm_smmu_tlb_inv_context(void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
-	void __iomem *base = ARM_SMMU_GR0(smmu);
 	bool stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
+	void __iomem *base;
 
 	if (stage1) {
 		base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
@@ -625,9 +557,76 @@ static void arm_smmu_tlb_inv_context(struct arm_smmu_domain *smmu_domain)
 			       base + ARM_SMMU_GR0_TLBIVMID);
 	}
 
-	arm_smmu_tlb_sync(smmu);
+	__arm_smmu_tlb_sync(smmu);
+}
+
+static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
+					  bool leaf, void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	bool stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
+	void __iomem *reg;
+
+	if (stage1) {
+		reg = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
+		reg += leaf ? ARM_SMMU_CB_S1_TLBIVAL : ARM_SMMU_CB_S1_TLBIVA;
+
+		if (!IS_ENABLED(CONFIG_64BIT) || smmu->version == ARM_SMMU_V1) {
+			iova &= ~12UL;
+			iova |= ARM_SMMU_CB_ASID(cfg);
+			writel_relaxed(iova, reg);
+#ifdef CONFIG_64BIT
+		} else {
+			iova >>= 12;
+			iova |= (u64)ARM_SMMU_CB_ASID(cfg) << 48;
+			writeq_relaxed(iova, reg);
+#endif
+		}
+#ifdef CONFIG_64BIT
+	} else if (smmu->version == ARM_SMMU_V2) {
+		reg = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
+		reg += leaf ? ARM_SMMU_CB_S2_TLBIIPAS2L :
+			      ARM_SMMU_CB_S2_TLBIIPAS2;
+		writeq_relaxed(iova >> 12, reg);
+#endif
+	} else {
+		reg = ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_TLBIVMID;
+		writel_relaxed(ARM_SMMU_CB_VMID(cfg), reg);
+	}
+}
+
+static void arm_smmu_flush_pgtable(void *addr, size_t size, void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	unsigned long offset = (unsigned long)addr & ~PAGE_MASK;
+
+
+	/* Ensure new page tables are visible to the hardware walker */
+	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) {
+		dsb(ishst);
+	} else {
+		/*
+		 * If the SMMU can't walk tables in the CPU caches, treat them
+		 * like non-coherent DMA since we need to flush the new entries
+		 * all the way out to memory. There's no possibility of
+		 * recursion here as the SMMU table walker will not be wired
+		 * through another SMMU.
+		 */
+		dma_map_page(smmu->dev, virt_to_page(addr), offset, size,
+			     DMA_TO_DEVICE);
+	}
 }
 
+static struct iommu_gather_ops arm_smmu_gather_ops = {
+	.tlb_flush_all	= arm_smmu_tlb_inv_context,
+	.tlb_add_flush	= arm_smmu_tlb_inv_range_nosync,
+	.tlb_sync	= arm_smmu_tlb_sync,
+	.flush_pgtable	= arm_smmu_flush_pgtable,
+};
+
 static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
 {
 	int flags, ret;
@@ -705,29 +704,8 @@ static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
 	return IRQ_HANDLED;
 }
 
-static void arm_smmu_flush_pgtable(struct arm_smmu_device *smmu, void *addr,
-				   size_t size)
-{
-	unsigned long offset = (unsigned long)addr & ~PAGE_MASK;
-
-
-	/* Ensure new page tables are visible to the hardware walker */
-	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) {
-		dsb(ishst);
-	} else {
-		/*
-		 * If the SMMU can't walk tables in the CPU caches, treat them
-		 * like non-coherent DMA since we need to flush the new entries
-		 * all the way out to memory. There's no possibility of
-		 * recursion here as the SMMU table walker will not be wired
-		 * through another SMMU.
-		 */
-		dma_map_page(smmu->dev, virt_to_page(addr), offset, size,
-				DMA_TO_DEVICE);
-	}
-}
-
-static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
+static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
+				       struct io_pgtable_cfg *pgtbl_cfg)
 {
 	u32 reg;
 	bool stage1;
@@ -764,124 +742,68 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 #else
 		reg = CBA2R_RW64_32BIT;
 #endif
-		writel_relaxed(reg,
-			       gr1_base + ARM_SMMU_GR1_CBA2R(cfg->cbndx));
-
-		/* TTBCR2 */
-		switch (smmu->s1_input_size) {
-		case 32:
-			reg = (TTBCR2_ADDR_32 << TTBCR2_SEP_SHIFT);
-			break;
-		case 36:
-			reg = (TTBCR2_ADDR_36 << TTBCR2_SEP_SHIFT);
-			break;
-		case 39:
-		case 40:
-			reg = (TTBCR2_ADDR_40 << TTBCR2_SEP_SHIFT);
-			break;
-		case 42:
-			reg = (TTBCR2_ADDR_42 << TTBCR2_SEP_SHIFT);
-			break;
-		case 44:
-			reg = (TTBCR2_ADDR_44 << TTBCR2_SEP_SHIFT);
-			break;
-		case 48:
-			reg = (TTBCR2_ADDR_48 << TTBCR2_SEP_SHIFT);
-			break;
-		}
-
-		switch (smmu->s1_output_size) {
-		case 32:
-			reg |= (TTBCR2_ADDR_32 << TTBCR2_PASIZE_SHIFT);
-			break;
-		case 36:
-			reg |= (TTBCR2_ADDR_36 << TTBCR2_PASIZE_SHIFT);
-			break;
-		case 39:
-		case 40:
-			reg |= (TTBCR2_ADDR_40 << TTBCR2_PASIZE_SHIFT);
-			break;
-		case 42:
-			reg |= (TTBCR2_ADDR_42 << TTBCR2_PASIZE_SHIFT);
-			break;
-		case 44:
-			reg |= (TTBCR2_ADDR_44 << TTBCR2_PASIZE_SHIFT);
-			break;
-		case 48:
-			reg |= (TTBCR2_ADDR_48 << TTBCR2_PASIZE_SHIFT);
-			break;
-		}
-
-		if (stage1)
-			writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR2);
+		writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBA2R(cfg->cbndx));
 	}
 
-	/* TTBR0 */
-	arm_smmu_flush_pgtable(smmu, cfg->pgd,
-			       PTRS_PER_PGD * sizeof(pgd_t));
-	reg = __pa(cfg->pgd);
-	writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
-	reg = (phys_addr_t)__pa(cfg->pgd) >> 32;
-	if (stage1)
+	/* TTBRs */
+	if (stage1) {
+		reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
+		reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0] >> 32;
 		reg |= ARM_SMMU_CB_ASID(cfg) << TTBRn_HI_ASID_SHIFT;
-	writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);
 
-	/*
-	 * TTBCR
-	 * We use long descriptor, with inner-shareable WBWA tables in TTBR0.
-	 */
-	if (smmu->version > ARM_SMMU_V1) {
-		if (PAGE_SIZE == SZ_4K)
-			reg = TTBCR_TG0_4K;
-		else
-			reg = TTBCR_TG0_64K;
-
-		if (!stage1) {
-			reg |= (64 - smmu->s2_input_size) << TTBCR_T0SZ_SHIFT;
+		reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[1];
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR1_LO);
+		reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[1] >> 32;
+		reg |= ARM_SMMU_CB_ASID(cfg) << TTBRn_HI_ASID_SHIFT;
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR1_HI);
+	} else {
+		reg = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
+		reg = pgtbl_cfg->arm_lpae_s2_cfg.vttbr >> 32;
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);
+	}
 
-			switch (smmu->s2_output_size) {
+	/* TTBCR */
+	if (stage1) {
+		reg = pgtbl_cfg->arm_lpae_s1_cfg.tcr;
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR);
+		if (smmu->version > ARM_SMMU_V1) {
+			reg = pgtbl_cfg->arm_lpae_s1_cfg.tcr >> 32;
+			switch (smmu->va_size) {
 			case 32:
-				reg |= (TTBCR2_ADDR_32 << TTBCR_PASIZE_SHIFT);
+				reg |= (TTBCR2_ADDR_32 << TTBCR2_SEP_SHIFT);
 				break;
 			case 36:
-				reg |= (TTBCR2_ADDR_36 << TTBCR_PASIZE_SHIFT);
+				reg |= (TTBCR2_ADDR_36 << TTBCR2_SEP_SHIFT);
 				break;
 			case 40:
-				reg |= (TTBCR2_ADDR_40 << TTBCR_PASIZE_SHIFT);
+				reg |= (TTBCR2_ADDR_40 << TTBCR2_SEP_SHIFT);
 				break;
 			case 42:
-				reg |= (TTBCR2_ADDR_42 << TTBCR_PASIZE_SHIFT);
+				reg |= (TTBCR2_ADDR_42 << TTBCR2_SEP_SHIFT);
 				break;
 			case 44:
-				reg |= (TTBCR2_ADDR_44 << TTBCR_PASIZE_SHIFT);
+				reg |= (TTBCR2_ADDR_44 << TTBCR2_SEP_SHIFT);
 				break;
 			case 48:
-				reg |= (TTBCR2_ADDR_48 << TTBCR_PASIZE_SHIFT);
+				reg |= (TTBCR2_ADDR_48 << TTBCR2_SEP_SHIFT);
 				break;
 			}
-		} else {
-			reg |= (64 - smmu->s1_input_size) << TTBCR_T0SZ_SHIFT;
+			writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR2);
 		}
 	} else {
-		reg = 0;
+		reg = pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR);
 	}
 
-	reg |= TTBCR_EAE |
-	      (TTBCR_SH_IS << TTBCR_SH0_SHIFT) |
-	      (TTBCR_RGN_WBWA << TTBCR_ORGN0_SHIFT) |
-	      (TTBCR_RGN_WBWA << TTBCR_IRGN0_SHIFT);
-
-	if (!stage1)
-		reg |= (TTBCR_SL0_LVL_1 << TTBCR_SL0_SHIFT);
-
-	writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR);
-
-	/* MAIR0 (stage-1 only) */
+	/* MAIRs (stage-1 only) */
 	if (stage1) {
-		reg = (MAIR_ATTR_NC << MAIR_ATTR_SHIFT(MAIR_ATTR_IDX_NC)) |
-		      (MAIR_ATTR_WBRWA << MAIR_ATTR_SHIFT(MAIR_ATTR_IDX_CACHE)) |
-		      (MAIR_ATTR_DEVICE << MAIR_ATTR_SHIFT(MAIR_ATTR_IDX_DEV));
+		reg = pgtbl_cfg->arm_lpae_s1_cfg.mair[0];
 		writel_relaxed(reg, cb_base + ARM_SMMU_CB_S1_MAIR0);
+		reg = pgtbl_cfg->arm_lpae_s1_cfg.mair[1];
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_S1_MAIR1);
 	}
 
 	/* SCTLR */
@@ -898,27 +820,69 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 					struct arm_smmu_device *smmu)
 {
 	int irq, start, ret = 0;
-	unsigned long flags;
+	unsigned long ias, oas;
+	struct io_pgtable_ops *pgtbl_ops;
+	struct io_pgtable_cfg pgtbl_cfg;
+	enum io_pgtable_fmt fmt;
 	struct arm_smmu_domain *smmu_domain = domain->priv;
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 
-	spin_lock_irqsave(&smmu_domain->lock, flags);
+	mutex_lock(&smmu_domain->init_mutex);
 	if (smmu_domain->smmu)
 		goto out_unlock;
 
-	if (smmu->features & ARM_SMMU_FEAT_TRANS_NESTED) {
+	/*
+	 * Mapping the requested stage onto what we support is surprisingly
+	 * complicated, mainly because the spec allows S1+S2 SMMUs without
+	 * support for nested translation. That means we end up with the
+	 * following table:
+	 *
+	 * Requested        Supported        Actual
+	 *     S1               N              S1
+	 *     S1             S1+S2            S1
+	 *     S1               S2             S2
+	 *     S1               S1             S1
+	 *     N                N              N
+	 *     N              S1+S2            S2
+	 *     N                S2             S2
+	 *     N                S1             S1
+	 *
+	 * Note that you can't actually request stage-2 mappings.
+	 */
+	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S1))
+		smmu_domain->stage = ARM_SMMU_DOMAIN_S2;
+	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S2))
+		smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
+
+	switch (smmu_domain->stage) {
+	case ARM_SMMU_DOMAIN_S1:
+		cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS;
+		start = smmu->num_s2_context_banks;
+		ias = smmu->va_size;
+		oas = smmu->ipa_size;
+		if (IS_ENABLED(CONFIG_64BIT))
+			fmt = ARM_64_LPAE_S1;
+		else
+			fmt = ARM_32_LPAE_S1;
+		break;
+	case ARM_SMMU_DOMAIN_NESTED:
 		/*
 		 * We will likely want to change this if/when KVM gets
 		 * involved.
 		 */
-		cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS;
-		start = smmu->num_s2_context_banks;
-	} else if (smmu->features & ARM_SMMU_FEAT_TRANS_S1) {
-		cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS;
-		start = smmu->num_s2_context_banks;
-	} else {
+	case ARM_SMMU_DOMAIN_S2:
 		cfg->cbar = CBAR_TYPE_S2_TRANS;
 		start = 0;
+		ias = smmu->ipa_size;
+		oas = smmu->pa_size;
+		if (IS_ENABLED(CONFIG_64BIT))
+			fmt = ARM_64_LPAE_S2;
+		else
+			fmt = ARM_32_LPAE_S2;
+		break;
+	default:
+		ret = -EINVAL;
+		goto out_unlock;
 	}
 
 	ret = __arm_smmu_alloc_bitmap(smmu->context_map, start,
@@ -934,10 +898,30 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		cfg->irptndx = cfg->cbndx;
 	}
 
-	ACCESS_ONCE(smmu_domain->smmu) = smmu;
-	arm_smmu_init_context_bank(smmu_domain);
-	spin_unlock_irqrestore(&smmu_domain->lock, flags);
+	pgtbl_cfg = (struct io_pgtable_cfg) {
+		.pgsize_bitmap	= arm_smmu_ops.pgsize_bitmap,
+		.ias		= ias,
+		.oas		= oas,
+		.tlb		= &arm_smmu_gather_ops,
+	};
+
+	smmu_domain->smmu = smmu;
+	pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
+	if (!pgtbl_ops) {
+		ret = -ENOMEM;
+		goto out_clear_smmu;
+	}
+
+	/* Update our support page sizes to reflect the page table format */
+	arm_smmu_ops.pgsize_bitmap = pgtbl_cfg.pgsize_bitmap;
 
+	/* Initialise the context bank with our page table cfg */
+	arm_smmu_init_context_bank(smmu_domain, &pgtbl_cfg);
+
+	/*
+	 * Request context fault interrupt. Do this last to avoid the
+	 * handler seeing a half-initialised domain state.
+	 */
 	irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
 	ret = request_irq(irq, arm_smmu_context_fault, IRQF_SHARED,
 			  "arm-smmu-context-fault", domain);
@@ -947,10 +931,16 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		cfg->irptndx = INVALID_IRPTNDX;
 	}
 
+	mutex_unlock(&smmu_domain->init_mutex);
+
+	/* Publish page table ops for map/unmap */
+	smmu_domain->pgtbl_ops = pgtbl_ops;
 	return 0;
 
+out_clear_smmu:
+	smmu_domain->smmu = NULL;
 out_unlock:
-	spin_unlock_irqrestore(&smmu_domain->lock, flags);
+	mutex_unlock(&smmu_domain->init_mutex);
 	return ret;
 }
 
@@ -965,23 +955,27 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 	if (!smmu)
 		return;
 
-	/* Disable the context bank and nuke the TLB before freeing it. */
+	/*
+	 * Disable the context bank and free the page tables before freeing
+	 * it.
+	 */
 	cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
 	writel_relaxed(0, cb_base + ARM_SMMU_CB_SCTLR);
-	arm_smmu_tlb_inv_context(smmu_domain);
 
 	if (cfg->irptndx != INVALID_IRPTNDX) {
 		irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
 		free_irq(irq, domain);
 	}
 
+	if (smmu_domain->pgtbl_ops)
+		free_io_pgtable_ops(smmu_domain->pgtbl_ops);
+
 	__arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx);
 }
 
 static int arm_smmu_domain_init(struct iommu_domain *domain)
 {
 	struct arm_smmu_domain *smmu_domain;
-	pgd_t *pgd;
 
 	/*
 	 * Allocate the domain and initialise some of its data structures.
@@ -992,81 +986,10 @@ static int arm_smmu_domain_init(struct iommu_domain *domain)
 	if (!smmu_domain)
 		return -ENOMEM;
 
-	pgd = kcalloc(PTRS_PER_PGD, sizeof(pgd_t), GFP_KERNEL);
-	if (!pgd)
-		goto out_free_domain;
-	smmu_domain->cfg.pgd = pgd;
-
-	spin_lock_init(&smmu_domain->lock);
+	mutex_init(&smmu_domain->init_mutex);
+	spin_lock_init(&smmu_domain->pgtbl_lock);
 	domain->priv = smmu_domain;
 	return 0;
-
-out_free_domain:
-	kfree(smmu_domain);
-	return -ENOMEM;
-}
-
-static void arm_smmu_free_ptes(pmd_t *pmd)
-{
-	pgtable_t table = pmd_pgtable(*pmd);
-
-	__free_page(table);
-}
-
-static void arm_smmu_free_pmds(pud_t *pud)
-{
-	int i;
-	pmd_t *pmd, *pmd_base = pmd_offset(pud, 0);
-
-	pmd = pmd_base;
-	for (i = 0; i < PTRS_PER_PMD; ++i) {
-		if (pmd_none(*pmd))
-			continue;
-
-		arm_smmu_free_ptes(pmd);
-		pmd++;
-	}
-
-	pmd_free(NULL, pmd_base);
-}
-
-static void arm_smmu_free_puds(pgd_t *pgd)
-{
-	int i;
-	pud_t *pud, *pud_base = pud_offset(pgd, 0);
-
-	pud = pud_base;
-	for (i = 0; i < PTRS_PER_PUD; ++i) {
-		if (pud_none(*pud))
-			continue;
-
-		arm_smmu_free_pmds(pud);
-		pud++;
-	}
-
-	pud_free(NULL, pud_base);
-}
-
-static void arm_smmu_free_pgtables(struct arm_smmu_domain *smmu_domain)
-{
-	int i;
-	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
-	pgd_t *pgd, *pgd_base = cfg->pgd;
-
-	/*
-	 * Recursively free the page tables for this domain. We don't
-	 * care about speculative TLB filling because the tables should
-	 * not be active in any context bank at this point (SCTLR.M is 0).
-	 */
-	pgd = pgd_base;
-	for (i = 0; i < PTRS_PER_PGD; ++i) {
-		if (pgd_none(*pgd))
-			continue;
-		arm_smmu_free_puds(pgd);
-		pgd++;
-	}
-
-	kfree(pgd_base);
 }
 
 static void arm_smmu_domain_destroy(struct iommu_domain *domain)
@@ -1078,7 +1001,6 @@ static void arm_smmu_domain_destroy(struct iommu_domain *domain)
 	 * already been detached.
 	 */
 	arm_smmu_destroy_domain_context(domain);
-	arm_smmu_free_pgtables(smmu_domain);
 	kfree(smmu_domain);
 }
 
@@ -1210,7 +1132,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 {
 	int ret;
 	struct arm_smmu_domain *smmu_domain = domain->priv;
-	struct arm_smmu_device *smmu, *dom_smmu;
+	struct arm_smmu_device *smmu;
 	struct arm_smmu_master_cfg *cfg;
 
 	smmu = find_smmu_for_device(dev);
@@ -1224,21 +1146,16 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		return -EEXIST;
 	}
 
+	/* Ensure that the domain is finalised */
+	ret = arm_smmu_init_domain_context(domain, smmu);
+	if (IS_ERR_VALUE(ret))
+		return ret;
+
 	/*
 	 * Sanity check the domain. We don't support domains across
 	 * different SMMUs.
 	 */
-	dom_smmu = ACCESS_ONCE(smmu_domain->smmu);
-	if (!dom_smmu) {
-		/* Now that we have a master, we can finalise the domain */
-		ret = arm_smmu_init_domain_context(domain, smmu);
-		if (IS_ERR_VALUE(ret))
-			return ret;
-
-		dom_smmu = smmu_domain->smmu;
-	}
-
-	if (dom_smmu != smmu) {
+	if (smmu_domain->smmu != smmu) {
 		dev_err(dev,
 			"cannot attach to SMMU %s whilst already attached to domain on SMMU %s\n",
 			dev_name(smmu_domain->smmu->dev), dev_name(smmu->dev));
@@ -1269,292 +1186,55 @@ static void arm_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
 	arm_smmu_domain_remove_master(smmu_domain, cfg);
 }
 
-static bool arm_smmu_pte_is_contiguous_range(unsigned long addr,
-					     unsigned long end)
-{
-	return !(addr & ~ARM_SMMU_PTE_CONT_MASK) &&
-		(addr + ARM_SMMU_PTE_CONT_SIZE <= end);
-}
-
-static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
-				   unsigned long addr, unsigned long end,
-				   unsigned long pfn, int prot, int stage)
-{
-	pte_t *pte, *start;
-	pteval_t pteval = ARM_SMMU_PTE_PAGE | ARM_SMMU_PTE_AF | ARM_SMMU_PTE_XN;
-
-	if (pmd_none(*pmd)) {
-		/* Allocate a new set of tables */
-		pgtable_t table = alloc_page(GFP_ATOMIC|__GFP_ZERO);
-
-		if (!table)
-			return -ENOMEM;
-
-		arm_smmu_flush_pgtable(smmu, page_address(table), PAGE_SIZE);
-		pmd_populate(NULL, pmd, table);
-		arm_smmu_flush_pgtable(smmu, pmd, sizeof(*pmd));
-	}
-
-	if (stage == 1) {
-		pteval |= ARM_SMMU_PTE_AP_UNPRIV | ARM_SMMU_PTE_nG;
-		if (!(prot & IOMMU_WRITE) && (prot & IOMMU_READ))
-			pteval |= ARM_SMMU_PTE_AP_RDONLY;
-
-		if (prot & IOMMU_CACHE)
-			pteval |= (MAIR_ATTR_IDX_CACHE <<
-				   ARM_SMMU_PTE_ATTRINDX_SHIFT);
-	} else {
-		pteval |= ARM_SMMU_PTE_HAP_FAULT;
-		if (prot & IOMMU_READ)
-			pteval |= ARM_SMMU_PTE_HAP_READ;
-		if (prot & IOMMU_WRITE)
-			pteval |= ARM_SMMU_PTE_HAP_WRITE;
-		if (prot & IOMMU_CACHE)
-			pteval |= ARM_SMMU_PTE_MEMATTR_OIWB;
-		else
-			pteval |= ARM_SMMU_PTE_MEMATTR_NC;
-	}
-
-	/* If no access, create a faulting entry to avoid TLB fills */
-	if (prot & IOMMU_EXEC)
-		pteval &= ~ARM_SMMU_PTE_XN;
-	else if (!(prot & (IOMMU_READ | IOMMU_WRITE)))
-		pteval &= ~ARM_SMMU_PTE_PAGE;
-
-	pteval |= ARM_SMMU_PTE_SH_IS;
-	start = pmd_page_vaddr(*pmd) + pte_index(addr);
-	pte = start;
-
-	/*
-	 * Install the page table entries. This is fairly complicated
-	 * since we attempt to make use of the contiguous hint in the
-	 * ptes where possible. The contiguous hint indicates a series
-	 * of ARM_SMMU_PTE_CONT_ENTRIES ptes mapping a physically
-	 * contiguous region with the following constraints:
-	 *
-	 *   - The region start is aligned to ARM_SMMU_PTE_CONT_SIZE
-	 *   - Each pte in the region has the contiguous hint bit set
-	 *
-	 * This complicates unmapping (also handled by this code, when
-	 * neither IOMMU_READ or IOMMU_WRITE are set) because it is
-	 * possible, yet highly unlikely, that a client may unmap only
-	 * part of a contiguous range. This requires clearing of the
-	 * contiguous hint bits in the range before installing the new
-	 * faulting entries.
-	 *
-	 * Note that re-mapping an address range without first unmapping
-	 * it is not supported, so TLB invalidation is not required here
-	 * and is instead performed at unmap and domain-init time.
-	 */
-	do {
-		int i = 1;
-
-		pteval &= ~ARM_SMMU_PTE_CONT;
-
-		if (arm_smmu_pte_is_contiguous_range(addr, end)) {
-			i = ARM_SMMU_PTE_CONT_ENTRIES;
-			pteval |= ARM_SMMU_PTE_CONT;
-		} else if (pte_val(*pte) &
-			   (ARM_SMMU_PTE_CONT | ARM_SMMU_PTE_PAGE)) {
-			int j;
-			pte_t *cont_start;
-			unsigned long idx = pte_index(addr);
-
-			idx &= ~(ARM_SMMU_PTE_CONT_ENTRIES - 1);
-			cont_start = pmd_page_vaddr(*pmd) + idx;
-			for (j = 0; j < ARM_SMMU_PTE_CONT_ENTRIES; ++j)
-				pte_val(*(cont_start + j)) &=
-					~ARM_SMMU_PTE_CONT;
-
-			arm_smmu_flush_pgtable(smmu, cont_start,
-					       sizeof(*pte) *
-					       ARM_SMMU_PTE_CONT_ENTRIES);
-		}
-
-		do {
-			*pte = pfn_pte(pfn, __pgprot(pteval));
-		} while (pte++, pfn++, addr += PAGE_SIZE, --i);
-	} while (addr != end);
-
-	arm_smmu_flush_pgtable(smmu, start, sizeof(*pte) * (pte - start));
-	return 0;
-}
-
-static int arm_smmu_alloc_init_pmd(struct arm_smmu_device *smmu, pud_t *pud,
-				   unsigned long addr, unsigned long end,
-				   phys_addr_t phys, int prot, int stage)
-{
-	int ret;
-	pmd_t *pmd;
-	unsigned long next, pfn = __phys_to_pfn(phys);
-
-#ifndef __PAGETABLE_PMD_FOLDED
-	if (pud_none(*pud)) {
-		pmd = (pmd_t *)get_zeroed_page(GFP_ATOMIC);
-		if (!pmd)
-			return -ENOMEM;
-
-		arm_smmu_flush_pgtable(smmu, pmd, PAGE_SIZE);
-		pud_populate(NULL, pud, pmd);
-		arm_smmu_flush_pgtable(smmu, pud, sizeof(*pud));
-
-		pmd += pmd_index(addr);
-	} else
-#endif
-		pmd = pmd_offset(pud, addr);
-
-	do {
-		next = pmd_addr_end(addr, end);
-		ret = arm_smmu_alloc_init_pte(smmu, pmd, addr, next, pfn,
-					      prot, stage);
-		phys += next - addr;
-		pfn = __phys_to_pfn(phys);
-	} while (pmd++, addr = next, addr < end);
-
-	return ret;
-}
-
-static int arm_smmu_alloc_init_pud(struct arm_smmu_device *smmu, pgd_t *pgd,
-				   unsigned long addr, unsigned long end,
-				   phys_addr_t phys, int prot, int stage)
-{
-	int ret = 0;
-	pud_t *pud;
-	unsigned long next;
-
-#ifndef __PAGETABLE_PUD_FOLDED
-	if (pgd_none(*pgd)) {
-		pud = (pud_t *)get_zeroed_page(GFP_ATOMIC);
-		if (!pud)
-			return -ENOMEM;
-
-		arm_smmu_flush_pgtable(smmu, pud, PAGE_SIZE);
-		pgd_populate(NULL, pgd, pud);
-		arm_smmu_flush_pgtable(smmu, pgd, sizeof(*pgd));
-
-		pud += pud_index(addr);
-	} else
-#endif
-		pud = pud_offset(pgd, addr);
-
-	do {
-		next = pud_addr_end(addr, end);
-		ret = arm_smmu_alloc_init_pmd(smmu, pud, addr, next, phys,
-					      prot, stage);
-		phys += next - addr;
-	} while (pud++, addr = next, addr < end);
-
-	return ret;
-}
-
-static int arm_smmu_handle_mapping(struct arm_smmu_domain *smmu_domain,
-				   unsigned long iova, phys_addr_t paddr,
-				   size_t size, int prot)
-{
-	int ret, stage;
-	unsigned long end;
-	phys_addr_t input_mask, output_mask;
-	struct arm_smmu_device *smmu = smmu_domain->smmu;
-	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
-	pgd_t *pgd = cfg->pgd;
-	unsigned long flags;
-
-	if (cfg->cbar == CBAR_TYPE_S2_TRANS) {
-		stage = 2;
-		input_mask = (1ULL << smmu->s2_input_size) - 1;
-		output_mask = (1ULL << smmu->s2_output_size) - 1;
-	} else {
-		stage = 1;
-		input_mask = (1ULL << smmu->s1_input_size) - 1;
-		output_mask = (1ULL << smmu->s1_output_size) - 1;
-	}
-
-	if (!pgd)
-		return -EINVAL;
-
-	if (size & ~PAGE_MASK)
-		return -EINVAL;
-
-	if ((phys_addr_t)iova & ~input_mask)
-		return -ERANGE;
-
-	if (paddr & ~output_mask)
-		return -ERANGE;
-
-	spin_lock_irqsave(&smmu_domain->lock, flags);
-	pgd += pgd_index(iova);
-	end = iova + size;
-	do {
-		unsigned long next = pgd_addr_end(iova, end);
-
-		ret = arm_smmu_alloc_init_pud(smmu, pgd, iova, next, paddr,
-					      prot, stage);
-		if (ret)
-			goto out_unlock;
-
-		paddr += next - iova;
-		iova = next;
-	} while (pgd++, iova != end);
-
-out_unlock:
-	spin_unlock_irqrestore(&smmu_domain->lock, flags);
-
-	return ret;
-}
-
 static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
 			phys_addr_t paddr, size_t size, int prot)
 {
+	int ret;
+	unsigned long flags;
 	struct arm_smmu_domain *smmu_domain = domain->priv;
+	struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;
 
-	if (!smmu_domain)
+	if (!ops)
 		return -ENODEV;
 
-	return arm_smmu_handle_mapping(smmu_domain, iova, paddr, size, prot);
+	spin_lock_irqsave(&smmu_domain->pgtbl_lock, flags);
+	ret = ops->map(ops, iova, paddr, size, prot);
+	spin_unlock_irqrestore(&smmu_domain->pgtbl_lock, flags);
+	return ret;
 }
 
 static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
 			     size_t size)
 {
-	int ret;
+	size_t ret;
+	unsigned long flags;
 	struct arm_smmu_domain *smmu_domain = domain->priv;
+	struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;
+
+	if (!ops)
+		return 0;
 
-	ret = arm_smmu_handle_mapping(smmu_domain, iova, 0, size, 0);
-	arm_smmu_tlb_inv_context(smmu_domain);
-	return ret ? 0 : size;
+	spin_lock_irqsave(&smmu_domain->pgtbl_lock, flags);
+	ret = ops->unmap(ops, iova, size);
+	spin_unlock_irqrestore(&smmu_domain->pgtbl_lock, flags);
+	return ret;
 }
 
 static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain,
 					 dma_addr_t iova)
 {
-	pgd_t *pgdp, pgd;
-	pud_t pud;
-	pmd_t pmd;
-	pte_t pte;
+	phys_addr_t ret;
+	unsigned long flags;
 	struct arm_smmu_domain *smmu_domain = domain->priv;
-	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
-
-	pgdp = cfg->pgd;
-	if (!pgdp)
-		return 0;
-
-	pgd = *(pgdp + pgd_index(iova));
-	if (pgd_none(pgd))
-		return 0;
+	struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;
 
-	pud = *pud_offset(&pgd, iova);
-	if (pud_none(pud))
+	if (!ops)
 		return 0;
 
-	pmd = *pmd_offset(&pud, iova);
-	if (pmd_none(pmd))
-		return 0;
-
-	pte = *(pmd_page_vaddr(pmd) + pte_index(iova));
-	if (pte_none(pte))
-		return 0;
-
-	return __pfn_to_phys(pte_pfn(pte)) | (iova & ~PAGE_MASK);
+	spin_lock_irqsave(&smmu_domain->pgtbl_lock, flags);
+	ret = ops->iova_to_phys(ops, iova);
+	spin_unlock_irqrestore(&smmu_domain->pgtbl_lock, flags);
+	return ret;
 }
 
 static bool arm_smmu_capable(enum iommu_cap cap)
@@ -1568,6 +1248,8 @@ static bool arm_smmu_capable(enum iommu_cap cap)
 		return true;
 	case IOMMU_CAP_INTR_REMAP:
 		return true; /* MSIs are just memory writes */
+	case IOMMU_CAP_NOEXEC:
+		return true;
 	default:
 		return false;
 	}
@@ -1644,20 +1326,64 @@ static void arm_smmu_remove_device(struct device *dev)
 	iommu_group_remove_device(dev);
 }
 
-static const struct iommu_ops arm_smmu_ops = {
-	.capable	= arm_smmu_capable,
-	.domain_init	= arm_smmu_domain_init,
-	.domain_destroy	= arm_smmu_domain_destroy,
-	.attach_dev	= arm_smmu_attach_dev,
-	.detach_dev	= arm_smmu_detach_dev,
-	.map		= arm_smmu_map,
-	.unmap		= arm_smmu_unmap,
-	.iova_to_phys	= arm_smmu_iova_to_phys,
-	.add_device	= arm_smmu_add_device,
-	.remove_device	= arm_smmu_remove_device,
-	.pgsize_bitmap	= (SECTION_SIZE |
-			   ARM_SMMU_PTE_CONT_SIZE |
-			   PAGE_SIZE),
+static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
+				    enum iommu_attr attr, void *data)
+{
+	struct arm_smmu_domain *smmu_domain = domain->priv;
+
+	switch (attr) {
+	case DOMAIN_ATTR_NESTING:
+		*(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED);
+		return 0;
+	default:
+		return -ENODEV;
+	}
+}
+
+static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
+				    enum iommu_attr attr, void *data)
+{
+	int ret = 0;
+	struct arm_smmu_domain *smmu_domain = domain->priv;
+
+	mutex_lock(&smmu_domain->init_mutex);
+
+	switch (attr) {
+	case DOMAIN_ATTR_NESTING:
+		if (smmu_domain->smmu) {
+			ret = -EPERM;
+			goto out_unlock;
+		}
+
+		if (*(int *)data)
+			smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
+		else
+			smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
+
+		break;
+	default:
+		ret = -ENODEV;
+	}
+
+out_unlock:
+	mutex_unlock(&smmu_domain->init_mutex);
+	return ret;
+}
+
+static struct iommu_ops arm_smmu_ops = {
+	.capable		= arm_smmu_capable,
+	.domain_init		= arm_smmu_domain_init,
+	.domain_destroy		= arm_smmu_domain_destroy,
+	.attach_dev		= arm_smmu_attach_dev,
+	.detach_dev		= arm_smmu_detach_dev,
+	.map			= arm_smmu_map,
+	.unmap			= arm_smmu_unmap,
+	.iova_to_phys		= arm_smmu_iova_to_phys,
+	.add_device		= arm_smmu_add_device,
+	.remove_device		= arm_smmu_remove_device,
+	.domain_get_attr	= arm_smmu_domain_get_attr,
+	.domain_set_attr	= arm_smmu_domain_set_attr,
+	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
 };
 
 static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
@@ -1686,7 +1412,6 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 	}
 
 	/* Invalidate the TLB, just in case */
-	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_STLBIALL);
 	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_TLBIALLH);
 	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_TLBIALLNSNH);
 
@@ -1708,7 +1433,7 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 	reg &= ~(sCR0_BSU_MASK << sCR0_BSU_SHIFT);
 
 	/* Push the button */
-	arm_smmu_tlb_sync(smmu);
+	__arm_smmu_tlb_sync(smmu);
 	writel(reg, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
 }
 
@@ -1742,12 +1467,6 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 
 	/* ID0 */
 	id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID0);
-#ifndef CONFIG_64BIT
-	if (((id >> ID0_PTFS_SHIFT) & ID0_PTFS_MASK) == ID0_PTFS_V8_ONLY) {
-		dev_err(smmu->dev, "\tno v7 descriptor support!\n");
-		return -ENODEV;
-	}
-#endif
 
 	/* Restrict available stages based on module parameter */
 	if (force_stage == 1)
@@ -1820,16 +1539,14 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	smmu->pgshift = (id & ID1_PAGESIZE) ? 16 : 12;
 
 	/* Check for size mismatch of SMMU address space from mapped region */
-	size = 1 <<
-		(((id >> ID1_NUMPAGENDXB_SHIFT) & ID1_NUMPAGENDXB_MASK) + 1);
+	size = 1 << (((id >> ID1_NUMPAGENDXB_SHIFT) & ID1_NUMPAGENDXB_MASK) + 1);
 	size *= 2 << smmu->pgshift;
 	if (smmu->size != size)
 		dev_warn(smmu->dev,
 			"SMMU address space size (0x%lx) differs from mapped region size (0x%lx)!\n",
 			size, smmu->size);
 
-	smmu->num_s2_context_banks = (id >> ID1_NUMS2CB_SHIFT) &
-				      ID1_NUMS2CB_MASK;
+	smmu->num_s2_context_banks = (id >> ID1_NUMS2CB_SHIFT) & ID1_NUMS2CB_MASK;
 	smmu->num_context_banks = (id >> ID1_NUMCB_SHIFT) & ID1_NUMCB_MASK;
 	if (smmu->num_s2_context_banks > smmu->num_context_banks) {
 		dev_err(smmu->dev, "impossible number of S2 context banks!\n");
@@ -1841,46 +1558,47 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	/* ID2 */
 	id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID2);
 	size = arm_smmu_id_size_to_bits((id >> ID2_IAS_SHIFT) & ID2_IAS_MASK);
-	smmu->s1_output_size = min_t(unsigned long, PHYS_MASK_SHIFT, size);
-
-	/* Stage-2 input size limited due to pgd allocation (PTRS_PER_PGD) */
-#ifdef CONFIG_64BIT
-	smmu->s2_input_size = min_t(unsigned long, VA_BITS, size);
-#else
-	smmu->s2_input_size = min(32UL, size);
-#endif
+	smmu->ipa_size = size;
 
-	/* The stage-2 output mask is also applied for bypass */
+	/* The output mask is also applied for bypass */
 	size = arm_smmu_id_size_to_bits((id >> ID2_OAS_SHIFT) & ID2_OAS_MASK);
-	smmu->s2_output_size = min_t(unsigned long, PHYS_MASK_SHIFT, size);
+	smmu->pa_size = size;
+
+	/*
+	 * What the page table walker can address actually depends on which
+	 * descriptor format is in use, but since a) we don't know that yet,
+	 * and b) it can vary per context bank, this will have to do...
+	 */
+	dma_set_mask_and_coherent(smmu->dev, DMA_BIT_MASK(size));
 
 	if (smmu->version == ARM_SMMU_V1) {
-		smmu->s1_input_size = 32;
+		smmu->va_size = smmu->ipa_size;
+		size = SZ_4K | SZ_2M | SZ_1G;
 	} else {
-#ifdef CONFIG_64BIT
 		size = (id >> ID2_UBS_SHIFT) & ID2_UBS_MASK;
-		size = min(VA_BITS, arm_smmu_id_size_to_bits(size));
-#else
-		size = 32;
+		smmu->va_size = arm_smmu_id_size_to_bits(size);
+#ifndef CONFIG_64BIT
+		smmu->va_size = min(32UL, smmu->va_size);
 #endif
-		smmu->s1_input_size = size;
-
-		if ((PAGE_SIZE == SZ_4K && !(id & ID2_PTFS_4K)) ||
-		    (PAGE_SIZE == SZ_64K && !(id & ID2_PTFS_64K)) ||
-		    (PAGE_SIZE != SZ_4K && PAGE_SIZE != SZ_64K)) {
-			dev_err(smmu->dev, "CPU page size 0x%lx unsupported\n",
-				PAGE_SIZE);
-			return -ENODEV;
-		}
+		size = 0;
+		if (id & ID2_PTFS_4K)
+			size |= SZ_4K | SZ_2M | SZ_1G;
+		if (id & ID2_PTFS_16K)
+			size |= SZ_16K | SZ_32M;
+		if (id & ID2_PTFS_64K)
+			size |= SZ_64K | SZ_512M;
 	}
 
+	arm_smmu_ops.pgsize_bitmap &= size;
+	dev_notice(smmu->dev, "\tSupported page sizes: 0x%08lx\n", size);
+
 	if (smmu->features & ARM_SMMU_FEAT_TRANS_S1)
 		dev_notice(smmu->dev, "\tStage-1: %lu-bit VA -> %lu-bit IPA\n",
-			   smmu->s1_input_size, smmu->s1_output_size);
+			   smmu->va_size, smmu->ipa_size);
 
 	if (smmu->features & ARM_SMMU_FEAT_TRANS_S2)
 		dev_notice(smmu->dev, "\tStage-2: %lu-bit IPA -> %lu-bit PA\n",
-			   smmu->s2_input_size, smmu->s2_output_size);
+			   smmu->ipa_size, smmu->pa_size);
 
 	return 0;
 }
@@ -2072,8 +1790,20 @@ static struct platform_driver arm_smmu_driver = {
 
 static int __init arm_smmu_init(void)
 {
+	struct device_node *np;
 	int ret;
 
+	/*
+	 * Play nice with systems that don't have an ARM SMMU by checking that
+	 * an ARM SMMU exists in the system before proceeding with the driver
+	 * and IOMMU bus operation registration.
+	 */
+	np = of_find_matching_node(NULL, arm_smmu_of_match);
+	if (!np)
+		return 0;
+
+	of_node_put(np);
+
 	ret = platform_driver_register(&arm_smmu_driver);
 	if (ret)
 		return ret;
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index a27d6cb1a79..3d1fc736a42 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -50,6 +50,7 @@
 #define CONTEXT_SIZE		VTD_PAGE_SIZE
 
 #define IS_GFX_DEVICE(pdev) ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY)
+#define IS_USB_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_SERIAL_USB)
 #define IS_ISA_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA)
 #define IS_AZALIA(pdev) ((pdev)->vendor == 0x8086 && (pdev)->device == 0x3a3e)
 
@@ -1746,8 +1747,8 @@ static int domain_init(struct dmar_domain *domain, int guest_width)
 static void domain_exit(struct dmar_domain *domain)
 {
 	struct dmar_drhd_unit *drhd;
-	struct intel_iommu *iommu;
 	struct page *freelist = NULL;
+	int i;
 
 	/* Domain 0 is reserved, so dont process it */
 	if (!domain)
@@ -1767,8 +1768,8 @@ static void domain_exit(struct dmar_domain *domain)
 
 	/* clear attached or cached domains */
 	rcu_read_lock();
-	for_each_active_iommu(iommu, drhd)
-		iommu_detach_domain(domain, iommu);
+	for_each_set_bit(i, domain->iommu_bmp, g_num_of_iommus)
+		iommu_detach_domain(domain, g_iommus[i]);
 	rcu_read_unlock();
 
 	dma_free_pagelist(freelist);
@@ -1983,7 +1984,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 {
 	struct dma_pte *first_pte = NULL, *pte = NULL;
 	phys_addr_t uninitialized_var(pteval);
-	unsigned long sg_res;
+	unsigned long sg_res = 0;
 	unsigned int largepage_lvl = 0;
 	unsigned long lvl_pages = 0;
 
@@ -1994,10 +1995,8 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 
 	prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP;
 
-	if (sg)
-		sg_res = 0;
-	else {
-		sg_res = nr_pages + 1;
+	if (!sg) {
+		sg_res = nr_pages;
 		pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot;
 	}
 
@@ -2560,6 +2559,10 @@ static bool device_has_rmrr(struct device *dev)
  * In both cases we assume that PCI USB devices with RMRRs have them largely
  * for historical reasons and that the RMRR space is not actively used post
  * boot.  This exclusion may change if vendors begin to abuse it.
+ *
+ * The same exception is made for graphics devices, with the requirement that
+ * any use of the RMRR regions will be torn down before assigning the device
+ * to a guest.
  */
 static bool device_is_rmrr_locked(struct device *dev)
 {
@@ -2569,7 +2572,7 @@ static bool device_is_rmrr_locked(struct device *dev)
 	if (dev_is_pci(dev)) {
 		struct pci_dev *pdev = to_pci_dev(dev);
 
-		if ((pdev->class >> 8) == PCI_CLASS_SERIAL_USB)
+		if (IS_USB_DEVICE(pdev) || IS_GFX_DEVICE(pdev))
 			return false;
 	}
 
@@ -4267,6 +4270,10 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
 				domain_remove_one_dev_info(old_domain, dev);
 			else
 				domain_remove_dev_info(old_domain);
+
+			if (!domain_type_is_vm_or_si(old_domain) &&
+			     list_empty(&old_domain->devices))
+				domain_exit(old_domain);
 		}
 	}
 
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
new file mode 100644
index 00000000000..5a500edf00c
--- /dev/null
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -0,0 +1,986 @@
+/*
+ * CPU-agnostic ARM page table allocator.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * Copyright (C) 2014 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#define pr_fmt(fmt)	"arm-lpae io-pgtable: " fmt
+
+#include <linux/iommu.h>
+#include <linux/kernel.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include "io-pgtable.h"
+
+#define ARM_LPAE_MAX_ADDR_BITS		48
+#define ARM_LPAE_S2_MAX_CONCAT_PAGES	16
+#define ARM_LPAE_MAX_LEVELS		4
+
+/* Struct accessors */
+#define io_pgtable_to_data(x)						\
+	container_of((x), struct arm_lpae_io_pgtable, iop)
+
+#define io_pgtable_ops_to_pgtable(x)					\
+	container_of((x), struct io_pgtable, ops)
+
+#define io_pgtable_ops_to_data(x)					\
+	io_pgtable_to_data(io_pgtable_ops_to_pgtable(x))
+
+/*
+ * For consistency with the architecture, we always consider
+ * ARM_LPAE_MAX_LEVELS levels, with the walk starting at level n >=0
+ */
+#define ARM_LPAE_START_LVL(d)		(ARM_LPAE_MAX_LEVELS - (d)->levels)
+
+/*
+ * Calculate the right shift amount to get to the portion describing level l
+ * in a virtual address mapped by the pagetable in d.
+ */
+#define ARM_LPAE_LVL_SHIFT(l,d)						\
+	((((d)->levels - ((l) - ARM_LPAE_START_LVL(d) + 1))		\
+	  * (d)->bits_per_level) + (d)->pg_shift)
+
+#define ARM_LPAE_PAGES_PER_PGD(d)	((d)->pgd_size >> (d)->pg_shift)
+
+/*
+ * Calculate the index at level l used to map virtual address a using the
+ * pagetable in d.
+ */
+#define ARM_LPAE_PGD_IDX(l,d)						\
+	((l) == ARM_LPAE_START_LVL(d) ? ilog2(ARM_LPAE_PAGES_PER_PGD(d)) : 0)
+
+#define ARM_LPAE_LVL_IDX(a,l,d)						\
+	(((a) >> ARM_LPAE_LVL_SHIFT(l,d)) &				\
+	 ((1 << ((d)->bits_per_level + ARM_LPAE_PGD_IDX(l,d))) - 1))
+
+/* Calculate the block/page mapping size at level l for pagetable in d. */
+#define ARM_LPAE_BLOCK_SIZE(l,d)					\
+	(1 << (ilog2(sizeof(arm_lpae_iopte)) +				\
+		((ARM_LPAE_MAX_LEVELS - (l)) * (d)->bits_per_level)))
+
+/* Page table bits */
+#define ARM_LPAE_PTE_TYPE_SHIFT		0
+#define ARM_LPAE_PTE_TYPE_MASK		0x3
+
+#define ARM_LPAE_PTE_TYPE_BLOCK		1
+#define ARM_LPAE_PTE_TYPE_TABLE		3
+#define ARM_LPAE_PTE_TYPE_PAGE		3
+
+#define ARM_LPAE_PTE_NSTABLE		(((arm_lpae_iopte)1) << 63)
+#define ARM_LPAE_PTE_XN			(((arm_lpae_iopte)3) << 53)
+#define ARM_LPAE_PTE_AF			(((arm_lpae_iopte)1) << 10)
+#define ARM_LPAE_PTE_SH_NS		(((arm_lpae_iopte)0) << 8)
+#define ARM_LPAE_PTE_SH_OS		(((arm_lpae_iopte)2) << 8)
+#define ARM_LPAE_PTE_SH_IS		(((arm_lpae_iopte)3) << 8)
+#define ARM_LPAE_PTE_NS			(((arm_lpae_iopte)1) << 5)
+#define ARM_LPAE_PTE_VALID		(((arm_lpae_iopte)1) << 0)
+
+#define ARM_LPAE_PTE_ATTR_LO_MASK	(((arm_lpae_iopte)0x3ff) << 2)
+/* Ignore the contiguous bit for block splitting */
+#define ARM_LPAE_PTE_ATTR_HI_MASK	(((arm_lpae_iopte)6) << 52)
+#define ARM_LPAE_PTE_ATTR_MASK		(ARM_LPAE_PTE_ATTR_LO_MASK |	\
+					 ARM_LPAE_PTE_ATTR_HI_MASK)
+
+/* Stage-1 PTE */
+#define ARM_LPAE_PTE_AP_UNPRIV		(((arm_lpae_iopte)1) << 6)
+#define ARM_LPAE_PTE_AP_RDONLY		(((arm_lpae_iopte)2) << 6)
+#define ARM_LPAE_PTE_ATTRINDX_SHIFT	2
+#define ARM_LPAE_PTE_nG			(((arm_lpae_iopte)1) << 11)
+
+/* Stage-2 PTE */
+#define ARM_LPAE_PTE_HAP_FAULT		(((arm_lpae_iopte)0) << 6)
+#define ARM_LPAE_PTE_HAP_READ		(((arm_lpae_iopte)1) << 6)
+#define ARM_LPAE_PTE_HAP_WRITE		(((arm_lpae_iopte)2) << 6)
+#define ARM_LPAE_PTE_MEMATTR_OIWB	(((arm_lpae_iopte)0xf) << 2)
+#define ARM_LPAE_PTE_MEMATTR_NC		(((arm_lpae_iopte)0x5) << 2)
+#define ARM_LPAE_PTE_MEMATTR_DEV	(((arm_lpae_iopte)0x1) << 2)
+
+/* Register bits */
+#define ARM_32_LPAE_TCR_EAE		(1 << 31)
+#define ARM_64_LPAE_S2_TCR_RES1		(1 << 31)
+
+#define ARM_LPAE_TCR_TG0_4K		(0 << 14)
+#define ARM_LPAE_TCR_TG0_64K		(1 << 14)
+#define ARM_LPAE_TCR_TG0_16K		(2 << 14)
+
+#define ARM_LPAE_TCR_SH0_SHIFT		12
+#define ARM_LPAE_TCR_SH0_MASK		0x3
+#define ARM_LPAE_TCR_SH_NS		0
+#define ARM_LPAE_TCR_SH_OS		2
+#define ARM_LPAE_TCR_SH_IS		3
+
+#define ARM_LPAE_TCR_ORGN0_SHIFT	10
+#define ARM_LPAE_TCR_IRGN0_SHIFT	8
+#define ARM_LPAE_TCR_RGN_MASK		0x3
+#define ARM_LPAE_TCR_RGN_NC		0
+#define ARM_LPAE_TCR_RGN_WBWA		1
+#define ARM_LPAE_TCR_RGN_WT		2
+#define ARM_LPAE_TCR_RGN_WB		3
+
+#define ARM_LPAE_TCR_SL0_SHIFT		6
+#define ARM_LPAE_TCR_SL0_MASK		0x3
+
+#define ARM_LPAE_TCR_T0SZ_SHIFT		0
+#define ARM_LPAE_TCR_SZ_MASK		0xf
+
+#define ARM_LPAE_TCR_PS_SHIFT		16
+#define ARM_LPAE_TCR_PS_MASK		0x7
+
+#define ARM_LPAE_TCR_IPS_SHIFT		32
+#define ARM_LPAE_TCR_IPS_MASK		0x7
+
+#define ARM_LPAE_TCR_PS_32_BIT		0x0ULL
+#define ARM_LPAE_TCR_PS_36_BIT		0x1ULL
+#define ARM_LPAE_TCR_PS_40_BIT		0x2ULL
+#define ARM_LPAE_TCR_PS_42_BIT		0x3ULL
+#define ARM_LPAE_TCR_PS_44_BIT		0x4ULL
+#define ARM_LPAE_TCR_PS_48_BIT		0x5ULL
+
+#define ARM_LPAE_MAIR_ATTR_SHIFT(n)	((n) << 3)
+#define ARM_LPAE_MAIR_ATTR_MASK		0xff
+#define ARM_LPAE_MAIR_ATTR_DEVICE	0x04
+#define ARM_LPAE_MAIR_ATTR_NC		0x44
+#define ARM_LPAE_MAIR_ATTR_WBRWA	0xff
+#define ARM_LPAE_MAIR_ATTR_IDX_NC	0
+#define ARM_LPAE_MAIR_ATTR_IDX_CACHE	1
+#define ARM_LPAE_MAIR_ATTR_IDX_DEV	2
+
+/* IOPTE accessors */
+#define iopte_deref(pte,d)					\
+	(__va((pte) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1)	\
+	& ~((1ULL << (d)->pg_shift) - 1)))
+
+#define iopte_type(pte,l)					\
+	(((pte) >> ARM_LPAE_PTE_TYPE_SHIFT) & ARM_LPAE_PTE_TYPE_MASK)
+
+#define iopte_prot(pte)	((pte) & ARM_LPAE_PTE_ATTR_MASK)
+
+#define iopte_leaf(pte,l)					\
+	(l == (ARM_LPAE_MAX_LEVELS - 1) ?			\
+		(iopte_type(pte,l) == ARM_LPAE_PTE_TYPE_PAGE) :	\
+		(iopte_type(pte,l) == ARM_LPAE_PTE_TYPE_BLOCK))
+
+#define iopte_to_pfn(pte,d)					\
+	(((pte) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1)) >> (d)->pg_shift)
+
+#define pfn_to_iopte(pfn,d)					\
+	(((pfn) << (d)->pg_shift) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1))
+
+struct arm_lpae_io_pgtable {
+	struct io_pgtable	iop;
+
+	int			levels;
+	size_t			pgd_size;
+	unsigned long		pg_shift;
+	unsigned long		bits_per_level;
+
+	void			*pgd;
+};
+
+typedef u64 arm_lpae_iopte;
+
+static bool selftest_running = false;
+
+static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
+			     unsigned long iova, phys_addr_t paddr,
+			     arm_lpae_iopte prot, int lvl,
+			     arm_lpae_iopte *ptep)
+{
+	arm_lpae_iopte pte = prot;
+
+	/* We require an unmap first */
+	if (iopte_leaf(*ptep, lvl)) {
+		WARN_ON(!selftest_running);
+		return -EEXIST;
+	}
+
+	if (data->iop.cfg.quirks & IO_PGTABLE_QUIRK_ARM_NS)
+		pte |= ARM_LPAE_PTE_NS;
+
+	if (lvl == ARM_LPAE_MAX_LEVELS - 1)
+		pte |= ARM_LPAE_PTE_TYPE_PAGE;
+	else
+		pte |= ARM_LPAE_PTE_TYPE_BLOCK;
+
+	pte |= ARM_LPAE_PTE_AF | ARM_LPAE_PTE_SH_IS;
+	pte |= pfn_to_iopte(paddr >> data->pg_shift, data);
+
+	*ptep = pte;
+	data->iop.cfg.tlb->flush_pgtable(ptep, sizeof(*ptep), data->iop.cookie);
+	return 0;
+}
+
+static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
+			  phys_addr_t paddr, size_t size, arm_lpae_iopte prot,
+			  int lvl, arm_lpae_iopte *ptep)
+{
+	arm_lpae_iopte *cptep, pte;
+	void *cookie = data->iop.cookie;
+	size_t block_size = ARM_LPAE_BLOCK_SIZE(lvl, data);
+
+	/* Find our entry at the current level */
+	ptep += ARM_LPAE_LVL_IDX(iova, lvl, data);
+
+	/* If we can install a leaf entry at this level, then do so */
+	if (size == block_size && (size & data->iop.cfg.pgsize_bitmap))
+		return arm_lpae_init_pte(data, iova, paddr, prot, lvl, ptep);
+
+	/* We can't allocate tables at the final level */
+	if (WARN_ON(lvl >= ARM_LPAE_MAX_LEVELS - 1))
+		return -EINVAL;
+
+	/* Grab a pointer to the next level */
+	pte = *ptep;
+	if (!pte) {
+		cptep = alloc_pages_exact(1UL << data->pg_shift,
+					 GFP_ATOMIC | __GFP_ZERO);
+		if (!cptep)
+			return -ENOMEM;
+
+		data->iop.cfg.tlb->flush_pgtable(cptep, 1UL << data->pg_shift,
+						 cookie);
+		pte = __pa(cptep) | ARM_LPAE_PTE_TYPE_TABLE;
+		if (data->iop.cfg.quirks & IO_PGTABLE_QUIRK_ARM_NS)
+			pte |= ARM_LPAE_PTE_NSTABLE;
+		*ptep = pte;
+		data->iop.cfg.tlb->flush_pgtable(ptep, sizeof(*ptep), cookie);
+	} else {
+		cptep = iopte_deref(pte, data);
+	}
+
+	/* Rinse, repeat */
+	return __arm_lpae_map(data, iova, paddr, size, prot, lvl + 1, cptep);
+}
+
+static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
+					   int prot)
+{
+	arm_lpae_iopte pte;
+
+	if (data->iop.fmt == ARM_64_LPAE_S1 ||
+	    data->iop.fmt == ARM_32_LPAE_S1) {
+		pte = ARM_LPAE_PTE_AP_UNPRIV | ARM_LPAE_PTE_nG;
+
+		if (!(prot & IOMMU_WRITE) && (prot & IOMMU_READ))
+			pte |= ARM_LPAE_PTE_AP_RDONLY;
+
+		if (prot & IOMMU_CACHE)
+			pte |= (ARM_LPAE_MAIR_ATTR_IDX_CACHE
+				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
+	} else {
+		pte = ARM_LPAE_PTE_HAP_FAULT;
+		if (prot & IOMMU_READ)
+			pte |= ARM_LPAE_PTE_HAP_READ;
+		if (prot & IOMMU_WRITE)
+			pte |= ARM_LPAE_PTE_HAP_WRITE;
+		if (prot & IOMMU_CACHE)
+			pte |= ARM_LPAE_PTE_MEMATTR_OIWB;
+		else
+			pte |= ARM_LPAE_PTE_MEMATTR_NC;
+	}
+
+	if (prot & IOMMU_NOEXEC)
+		pte |= ARM_LPAE_PTE_XN;
+
+	return pte;
+}
+
+static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
+			phys_addr_t paddr, size_t size, int iommu_prot)
+{
+	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	arm_lpae_iopte *ptep = data->pgd;
+	int lvl = ARM_LPAE_START_LVL(data);
+	arm_lpae_iopte prot;
+
+	/* If no access, then nothing to do */
+	if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
+		return 0;
+
+	prot = arm_lpae_prot_to_pte(data, iommu_prot);
+	return __arm_lpae_map(data, iova, paddr, size, prot, lvl, ptep);
+}
+
+static void __arm_lpae_free_pgtable(struct arm_lpae_io_pgtable *data, int lvl,
+				    arm_lpae_iopte *ptep)
+{
+	arm_lpae_iopte *start, *end;
+	unsigned long table_size;
+
+	/* Only leaf entries at the last level */
+	if (lvl == ARM_LPAE_MAX_LEVELS - 1)
+		return;
+
+	if (lvl == ARM_LPAE_START_LVL(data))
+		table_size = data->pgd_size;
+	else
+		table_size = 1UL << data->pg_shift;
+
+	start = ptep;
+	end = (void *)ptep + table_size;
+
+	while (ptep != end) {
+		arm_lpae_iopte pte = *ptep++;
+
+		if (!pte || iopte_leaf(pte, lvl))
+			continue;
+
+		__arm_lpae_free_pgtable(data, lvl + 1, iopte_deref(pte, data));
+	}
+
+	free_pages_exact(start, table_size);
+}
+
+static void arm_lpae_free_pgtable(struct io_pgtable *iop)
+{
+	struct arm_lpae_io_pgtable *data = io_pgtable_to_data(iop);
+
+	__arm_lpae_free_pgtable(data, ARM_LPAE_START_LVL(data), data->pgd);
+	kfree(data);
+}
+
+static int arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
+				    unsigned long iova, size_t size,
+				    arm_lpae_iopte prot, int lvl,
+				    arm_lpae_iopte *ptep, size_t blk_size)
+{
+	unsigned long blk_start, blk_end;
+	phys_addr_t blk_paddr;
+	arm_lpae_iopte table = 0;
+	void *cookie = data->iop.cookie;
+	const struct iommu_gather_ops *tlb = data->iop.cfg.tlb;
+
+	blk_start = iova & ~(blk_size - 1);
+	blk_end = blk_start + blk_size;
+	blk_paddr = iopte_to_pfn(*ptep, data) << data->pg_shift;
+
+	for (; blk_start < blk_end; blk_start += size, blk_paddr += size) {
+		arm_lpae_iopte *tablep;
+
+		/* Unmap! */
+		if (blk_start == iova)
+			continue;
+
+		/* __arm_lpae_map expects a pointer to the start of the table */
+		tablep = &table - ARM_LPAE_LVL_IDX(blk_start, lvl, data);
+		if (__arm_lpae_map(data, blk_start, blk_paddr, size, prot, lvl,
+				   tablep) < 0) {
+			if (table) {
+				/* Free the table we allocated */
+				tablep = iopte_deref(table, data);
+				__arm_lpae_free_pgtable(data, lvl + 1, tablep);
+			}
+			return 0; /* Bytes unmapped */
+		}
+	}
+
+	*ptep = table;
+	tlb->flush_pgtable(ptep, sizeof(*ptep), cookie);
+	iova &= ~(blk_size - 1);
+	tlb->tlb_add_flush(iova, blk_size, true, cookie);
+	return size;
+}
+
+static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
+			    unsigned long iova, size_t size, int lvl,
+			    arm_lpae_iopte *ptep)
+{
+	arm_lpae_iopte pte;
+	const struct iommu_gather_ops *tlb = data->iop.cfg.tlb;
+	void *cookie = data->iop.cookie;
+	size_t blk_size = ARM_LPAE_BLOCK_SIZE(lvl, data);
+
+	ptep += ARM_LPAE_LVL_IDX(iova, lvl, data);
+	pte = *ptep;
+
+	/* Something went horribly wrong and we ran out of page table */
+	if (WARN_ON(!pte || (lvl == ARM_LPAE_MAX_LEVELS)))
+		return 0;
+
+	/* If the size matches this level, we're in the right place */
+	if (size == blk_size) {
+		*ptep = 0;
+		tlb->flush_pgtable(ptep, sizeof(*ptep), cookie);
+
+		if (!iopte_leaf(pte, lvl)) {
+			/* Also flush any partial walks */
+			tlb->tlb_add_flush(iova, size, false, cookie);
+			tlb->tlb_sync(data->iop.cookie);
+			ptep = iopte_deref(pte, data);
+			__arm_lpae_free_pgtable(data, lvl + 1, ptep);
+		} else {
+			tlb->tlb_add_flush(iova, size, true, cookie);
+		}
+
+		return size;
+	} else if (iopte_leaf(pte, lvl)) {
+		/*
+		 * Insert a table at the next level to map the old region,
+		 * minus the part we want to unmap
+		 */
+		return arm_lpae_split_blk_unmap(data, iova, size,
+						iopte_prot(pte), lvl, ptep,
+						blk_size);
+	}
+
+	/* Keep on walkin' */
+	ptep = iopte_deref(pte, data);
+	return __arm_lpae_unmap(data, iova, size, lvl + 1, ptep);
+}
+
+static int arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
+			  size_t size)
+{
+	size_t unmapped;
+	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	struct io_pgtable *iop = &data->iop;
+	arm_lpae_iopte *ptep = data->pgd;
+	int lvl = ARM_LPAE_START_LVL(data);
+
+	unmapped = __arm_lpae_unmap(data, iova, size, lvl, ptep);
+	if (unmapped)
+		iop->cfg.tlb->tlb_sync(iop->cookie);
+
+	return unmapped;
+}
+
+static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
+					 unsigned long iova)
+{
+	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	arm_lpae_iopte pte, *ptep = data->pgd;
+	int lvl = ARM_LPAE_START_LVL(data);
+
+	do {
+		/* Valid IOPTE pointer? */
+		if (!ptep)
+			return 0;
+
+		/* Grab the IOPTE we're interested in */
+		pte = *(ptep + ARM_LPAE_LVL_IDX(iova, lvl, data));
+
+		/* Valid entry? */
+		if (!pte)
+			return 0;
+
+		/* Leaf entry? */
+		if (iopte_leaf(pte,lvl))
+			goto found_translation;
+
+		/* Take it to the next level */
+		ptep = iopte_deref(pte, data);
+	} while (++lvl < ARM_LPAE_MAX_LEVELS);
+
+	/* Ran out of page tables to walk */
+	return 0;
+
+found_translation:
+	iova &= ((1 << data->pg_shift) - 1);
+	return ((phys_addr_t)iopte_to_pfn(pte,data) << data->pg_shift) | iova;
+}
+
+static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg)
+{
+	unsigned long granule;
+
+	/*
+	 * We need to restrict the supported page sizes to match the
+	 * translation regime for a particular granule. Aim to match
+	 * the CPU page size if possible, otherwise prefer smaller sizes.
+	 * While we're at it, restrict the block sizes to match the
+	 * chosen granule.
+	 */
+	if (cfg->pgsize_bitmap & PAGE_SIZE)
+		granule = PAGE_SIZE;
+	else if (cfg->pgsize_bitmap & ~PAGE_MASK)
+		granule = 1UL << __fls(cfg->pgsize_bitmap & ~PAGE_MASK);
+	else if (cfg->pgsize_bitmap & PAGE_MASK)
+		granule = 1UL << __ffs(cfg->pgsize_bitmap & PAGE_MASK);
+	else
+		granule = 0;
+
+	switch (granule) {
+	case SZ_4K:
+		cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
+		break;
+	case SZ_16K:
+		cfg->pgsize_bitmap &= (SZ_16K | SZ_32M);
+		break;
+	case SZ_64K:
+		cfg->pgsize_bitmap &= (SZ_64K | SZ_512M);
+		break;
+	default:
+		cfg->pgsize_bitmap = 0;
+	}
+}
+
+static struct arm_lpae_io_pgtable *
+arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
+{
+	unsigned long va_bits, pgd_bits;
+	struct arm_lpae_io_pgtable *data;
+
+	arm_lpae_restrict_pgsizes(cfg);
+
+	if (!(cfg->pgsize_bitmap & (SZ_4K | SZ_16K | SZ_64K)))
+		return NULL;
+
+	if (cfg->ias > ARM_LPAE_MAX_ADDR_BITS)
+		return NULL;
+
+	if (cfg->oas > ARM_LPAE_MAX_ADDR_BITS)
+		return NULL;
+
+	data = kmalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return NULL;
+
+	data->pg_shift = __ffs(cfg->pgsize_bitmap);
+	data->bits_per_level = data->pg_shift - ilog2(sizeof(arm_lpae_iopte));
+
+	va_bits = cfg->ias - data->pg_shift;
+	data->levels = DIV_ROUND_UP(va_bits, data->bits_per_level);
+
+	/* Calculate the actual size of our pgd (without concatenation) */
+	pgd_bits = va_bits - (data->bits_per_level * (data->levels - 1));
+	data->pgd_size = 1UL << (pgd_bits + ilog2(sizeof(arm_lpae_iopte)));
+
+	data->iop.ops = (struct io_pgtable_ops) {
+		.map		= arm_lpae_map,
+		.unmap		= arm_lpae_unmap,
+		.iova_to_phys	= arm_lpae_iova_to_phys,
+	};
+
+	return data;
+}
+
+static struct io_pgtable *
+arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
+{
+	u64 reg;
+	struct arm_lpae_io_pgtable *data = arm_lpae_alloc_pgtable(cfg);
+
+	if (!data)
+		return NULL;
+
+	/* TCR */
+	reg = (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
+	      (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
+	      (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
+
+	switch (1 << data->pg_shift) {
+	case SZ_4K:
+		reg |= ARM_LPAE_TCR_TG0_4K;
+		break;
+	case SZ_16K:
+		reg |= ARM_LPAE_TCR_TG0_16K;
+		break;
+	case SZ_64K:
+		reg |= ARM_LPAE_TCR_TG0_64K;
+		break;
+	}
+
+	switch (cfg->oas) {
+	case 32:
+		reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		break;
+	case 36:
+		reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		break;
+	case 40:
+		reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		break;
+	case 42:
+		reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		break;
+	case 44:
+		reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		break;
+	case 48:
+		reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		break;
+	default:
+		goto out_free_data;
+	}
+
+	reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT;
+	cfg->arm_lpae_s1_cfg.tcr = reg;
+
+	/* MAIRs */
+	reg = (ARM_LPAE_MAIR_ATTR_NC
+	       << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_NC)) |
+	      (ARM_LPAE_MAIR_ATTR_WBRWA
+	       << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_CACHE)) |
+	      (ARM_LPAE_MAIR_ATTR_DEVICE
+	       << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_DEV));
+
+	cfg->arm_lpae_s1_cfg.mair[0] = reg;
+	cfg->arm_lpae_s1_cfg.mair[1] = 0;
+
+	/* Looking good; allocate a pgd */
+	data->pgd = alloc_pages_exact(data->pgd_size, GFP_KERNEL | __GFP_ZERO);
+	if (!data->pgd)
+		goto out_free_data;
+
+	cfg->tlb->flush_pgtable(data->pgd, data->pgd_size, cookie);
+
+	/* TTBRs */
+	cfg->arm_lpae_s1_cfg.ttbr[0] = virt_to_phys(data->pgd);
+	cfg->arm_lpae_s1_cfg.ttbr[1] = 0;
+	return &data->iop;
+
+out_free_data:
+	kfree(data);
+	return NULL;
+}
+
+static struct io_pgtable *
+arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
+{
+	u64 reg, sl;
+	struct arm_lpae_io_pgtable *data = arm_lpae_alloc_pgtable(cfg);
+
+	if (!data)
+		return NULL;
+
+	/*
+	 * Concatenate PGDs at level 1 if possible in order to reduce
+	 * the depth of the stage-2 walk.
+	 */
+	if (data->levels == ARM_LPAE_MAX_LEVELS) {
+		unsigned long pgd_pages;
+
+		pgd_pages = data->pgd_size >> ilog2(sizeof(arm_lpae_iopte));
+		if (pgd_pages <= ARM_LPAE_S2_MAX_CONCAT_PAGES) {
+			data->pgd_size = pgd_pages << data->pg_shift;
+			data->levels--;
+		}
+	}
+
+	/* VTCR */
+	reg = ARM_64_LPAE_S2_TCR_RES1 |
+	     (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
+	     (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
+	     (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
+
+	sl = ARM_LPAE_START_LVL(data);
+
+	switch (1 << data->pg_shift) {
+	case SZ_4K:
+		reg |= ARM_LPAE_TCR_TG0_4K;
+		sl++; /* SL0 format is different for 4K granule size */
+		break;
+	case SZ_16K:
+		reg |= ARM_LPAE_TCR_TG0_16K;
+		break;
+	case SZ_64K:
+		reg |= ARM_LPAE_TCR_TG0_64K;
+		break;
+	}
+
+	switch (cfg->oas) {
+	case 32:
+		reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		break;
+	case 36:
+		reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		break;
+	case 40:
+		reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		break;
+	case 42:
+		reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		break;
+	case 44:
+		reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		break;
+	case 48:
+		reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		break;
+	default:
+		goto out_free_data;
+	}
+
+	reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT;
+	reg |= (~sl & ARM_LPAE_TCR_SL0_MASK) << ARM_LPAE_TCR_SL0_SHIFT;
+	cfg->arm_lpae_s2_cfg.vtcr = reg;
+
+	/* Allocate pgd pages */
+	data->pgd = alloc_pages_exact(data->pgd_size, GFP_KERNEL | __GFP_ZERO);
+	if (!data->pgd)
+		goto out_free_data;
+
+	cfg->tlb->flush_pgtable(data->pgd, data->pgd_size, cookie);
+
+	/* VTTBR */
+	cfg->arm_lpae_s2_cfg.vttbr = virt_to_phys(data->pgd);
+	return &data->iop;
+
+out_free_data:
+	kfree(data);
+	return NULL;
+}
+
+static struct io_pgtable *
+arm_32_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
+{
+	struct io_pgtable *iop;
+
+	if (cfg->ias > 32 || cfg->oas > 40)
+		return NULL;
+
+	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
+	iop = arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
+	if (iop) {
+		cfg->arm_lpae_s1_cfg.tcr |= ARM_32_LPAE_TCR_EAE;
+		cfg->arm_lpae_s1_cfg.tcr &= 0xffffffff;
+	}
+
+	return iop;
+}
+
+static struct io_pgtable *
+arm_32_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
+{
+	struct io_pgtable *iop;
+
+	if (cfg->ias > 40 || cfg->oas > 40)
+		return NULL;
+
+	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
+	iop = arm_64_lpae_alloc_pgtable_s2(cfg, cookie);
+	if (iop)
+		cfg->arm_lpae_s2_cfg.vtcr &= 0xffffffff;
+
+	return iop;
+}
+
+struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns = {
+	.alloc	= arm_64_lpae_alloc_pgtable_s1,
+	.free	= arm_lpae_free_pgtable,
+};
+
+struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns = {
+	.alloc	= arm_64_lpae_alloc_pgtable_s2,
+	.free	= arm_lpae_free_pgtable,
+};
+
+struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns = {
+	.alloc	= arm_32_lpae_alloc_pgtable_s1,
+	.free	= arm_lpae_free_pgtable,
+};
+
+struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s2_init_fns = {
+	.alloc	= arm_32_lpae_alloc_pgtable_s2,
+	.free	= arm_lpae_free_pgtable,
+};
+
+#ifdef CONFIG_IOMMU_IO_PGTABLE_LPAE_SELFTEST
+
+static struct io_pgtable_cfg *cfg_cookie;
+
+static void dummy_tlb_flush_all(void *cookie)
+{
+	WARN_ON(cookie != cfg_cookie);
+}
+
+static void dummy_tlb_add_flush(unsigned long iova, size_t size, bool leaf,
+				void *cookie)
+{
+	WARN_ON(cookie != cfg_cookie);
+	WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
+}
+
+static void dummy_tlb_sync(void *cookie)
+{
+	WARN_ON(cookie != cfg_cookie);
+}
+
+static void dummy_flush_pgtable(void *ptr, size_t size, void *cookie)
+{
+	WARN_ON(cookie != cfg_cookie);
+}
+
+static struct iommu_gather_ops dummy_tlb_ops __initdata = {
+	.tlb_flush_all	= dummy_tlb_flush_all,
+	.tlb_add_flush	= dummy_tlb_add_flush,
+	.tlb_sync	= dummy_tlb_sync,
+	.flush_pgtable	= dummy_flush_pgtable,
+};
+
+static void __init arm_lpae_dump_ops(struct io_pgtable_ops *ops)
+{
+	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	struct io_pgtable_cfg *cfg = &data->iop.cfg;
+
+	pr_err("cfg: pgsize_bitmap 0x%lx, ias %u-bit\n",
+		cfg->pgsize_bitmap, cfg->ias);
+	pr_err("data: %d levels, 0x%zx pgd_size, %lu pg_shift, %lu bits_per_level, pgd @ %p\n",
+		data->levels, data->pgd_size, data->pg_shift,
+		data->bits_per_level, data->pgd);
+}
+
+#define __FAIL(ops, i)	({						\
+		WARN(1, "selftest: test failed for fmt idx %d\n", (i));	\
+		arm_lpae_dump_ops(ops);					\
+		selftest_running = false;				\
+		-EFAULT;						\
+})
+
+static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
+{
+	static const enum io_pgtable_fmt fmts[] = {
+		ARM_64_LPAE_S1,
+		ARM_64_LPAE_S2,
+	};
+
+	int i, j;
+	unsigned long iova;
+	size_t size;
+	struct io_pgtable_ops *ops;
+
+	selftest_running = true;
+
+	for (i = 0; i < ARRAY_SIZE(fmts); ++i) {
+		cfg_cookie = cfg;
+		ops = alloc_io_pgtable_ops(fmts[i], cfg, cfg);
+		if (!ops) {
+			pr_err("selftest: failed to allocate io pgtable ops\n");
+			return -ENOMEM;
+		}
+
+		/*
+		 * Initial sanity checks.
+		 * Empty page tables shouldn't provide any translations.
+		 */
+		if (ops->iova_to_phys(ops, 42))
+			return __FAIL(ops, i);
+
+		if (ops->iova_to_phys(ops, SZ_1G + 42))
+			return __FAIL(ops, i);
+
+		if (ops->iova_to_phys(ops, SZ_2G + 42))
+			return __FAIL(ops, i);
+
+		/*
+		 * Distinct mappings of different granule sizes.
+		 */
+		iova = 0;
+		j = find_first_bit(&cfg->pgsize_bitmap, BITS_PER_LONG);
+		while (j != BITS_PER_LONG) {
+			size = 1UL << j;
+
+			if (ops->map(ops, iova, iova, size, IOMMU_READ |
+							    IOMMU_WRITE |
+							    IOMMU_NOEXEC |
+							    IOMMU_CACHE))
+				return __FAIL(ops, i);
+
+			/* Overlapping mappings */
+			if (!ops->map(ops, iova, iova + size, size,
+				      IOMMU_READ | IOMMU_NOEXEC))
+				return __FAIL(ops, i);
+
+			if (ops->iova_to_phys(ops, iova + 42) != (iova + 42))
+				return __FAIL(ops, i);
+
+			iova += SZ_1G;
+			j++;
+			j = find_next_bit(&cfg->pgsize_bitmap, BITS_PER_LONG, j);
+		}
+
+		/* Partial unmap */
+		size = 1UL << __ffs(cfg->pgsize_bitmap);
+		if (ops->unmap(ops, SZ_1G + size, size) != size)
+			return __FAIL(ops, i);
+
+		/* Remap of partial unmap */
+		if (ops->map(ops, SZ_1G + size, size, size, IOMMU_READ))
+			return __FAIL(ops, i);
+
+		if (ops->iova_to_phys(ops, SZ_1G + size + 42) != (size + 42))
+			return __FAIL(ops, i);
+
+		/* Full unmap */
+		iova = 0;
+		j = find_first_bit(&cfg->pgsize_bitmap, BITS_PER_LONG);
+		while (j != BITS_PER_LONG) {
+			size = 1UL << j;
+
+			if (ops->unmap(ops, iova, size) != size)
+				return __FAIL(ops, i);
+
+			if (ops->iova_to_phys(ops, iova + 42))
+				return __FAIL(ops, i);
+
+			/* Remap full block */
+			if (ops->map(ops, iova, iova, size, IOMMU_WRITE))
+				return __FAIL(ops, i);
+
+			if (ops->iova_to_phys(ops, iova + 42) != (iova + 42))
+				return __FAIL(ops, i);
+
+			iova += SZ_1G;
+			j++;
+			j = find_next_bit(&cfg->pgsize_bitmap, BITS_PER_LONG, j);
+		}
+
+		free_io_pgtable_ops(ops);
+	}
+
+	selftest_running = false;
+	return 0;
+}
+
+static int __init arm_lpae_do_selftests(void)
+{
+	static const unsigned long pgsize[] = {
+		SZ_4K | SZ_2M | SZ_1G,
+		SZ_16K | SZ_32M,
+		SZ_64K | SZ_512M,
+	};
+
+	static const unsigned int ias[] = {
+		32, 36, 40, 42, 44, 48,
+	};
+
+	int i, j, pass = 0, fail = 0;
+	struct io_pgtable_cfg cfg = {
+		.tlb = &dummy_tlb_ops,
+		.oas = 48,
+	};
+
+	for (i = 0; i < ARRAY_SIZE(pgsize); ++i) {
+		for (j = 0; j < ARRAY_SIZE(ias); ++j) {
+			cfg.pgsize_bitmap = pgsize[i];
+			cfg.ias = ias[j];
+			pr_info("selftest: pgsize_bitmap 0x%08lx, IAS %u\n",
+				pgsize[i], ias[j]);
+			if (arm_lpae_run_tests(&cfg))
+				fail++;
+			else
+				pass++;
+		}
+	}
+
+	pr_info("selftest: completed with %d PASS %d FAIL\n", pass, fail);
+	return fail ? -EFAULT : 0;
+}
+subsys_initcall(arm_lpae_do_selftests);
+#endif
diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c
new file mode 100644
index 00000000000..6436fe24bc2
--- /dev/null
+++ b/drivers/iommu/io-pgtable.c
@@ -0,0 +1,82 @@
+/*
+ * Generic page table allocator for IOMMUs.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * Copyright (C) 2014 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#include <linux/bug.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+#include "io-pgtable.h"
+
+extern struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns;
+extern struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s2_init_fns;
+extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns;
+extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns;
+
+static const struct io_pgtable_init_fns *
+io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] =
+{
+#ifdef CONFIG_IOMMU_IO_PGTABLE_LPAE
+	[ARM_32_LPAE_S1] = &io_pgtable_arm_32_lpae_s1_init_fns,
+	[ARM_32_LPAE_S2] = &io_pgtable_arm_32_lpae_s2_init_fns,
+	[ARM_64_LPAE_S1] = &io_pgtable_arm_64_lpae_s1_init_fns,
+	[ARM_64_LPAE_S2] = &io_pgtable_arm_64_lpae_s2_init_fns,
+#endif
+};
+
+struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
+					    struct io_pgtable_cfg *cfg,
+					    void *cookie)
+{
+	struct io_pgtable *iop;
+	const struct io_pgtable_init_fns *fns;
+
+	if (fmt >= IO_PGTABLE_NUM_FMTS)
+		return NULL;
+
+	fns = io_pgtable_init_table[fmt];
+	if (!fns)
+		return NULL;
+
+	iop = fns->alloc(cfg, cookie);
+	if (!iop)
+		return NULL;
+
+	iop->fmt	= fmt;
+	iop->cookie	= cookie;
+	iop->cfg	= *cfg;
+
+	return &iop->ops;
+}
+
+/*
+ * It is the IOMMU driver's responsibility to ensure that the page table
+ * is no longer accessible to the walker by this point.
+ */
+void free_io_pgtable_ops(struct io_pgtable_ops *ops)
+{
+	struct io_pgtable *iop;
+
+	if (!ops)
+		return;
+
+	iop = container_of(ops, struct io_pgtable, ops);
+	iop->cfg.tlb->tlb_flush_all(iop->cookie);
+	io_pgtable_init_table[iop->fmt]->free(iop);
+}
diff --git a/drivers/iommu/io-pgtable.h b/drivers/iommu/io-pgtable.h
new file mode 100644
index 00000000000..10e32f69c66
--- /dev/null
+++ b/drivers/iommu/io-pgtable.h
@@ -0,0 +1,143 @@
+#ifndef __IO_PGTABLE_H
+#define __IO_PGTABLE_H
+
+/*
+ * Public API for use by IOMMU drivers
+ */
+enum io_pgtable_fmt {
+	ARM_32_LPAE_S1,
+	ARM_32_LPAE_S2,
+	ARM_64_LPAE_S1,
+	ARM_64_LPAE_S2,
+	IO_PGTABLE_NUM_FMTS,
+};
+
+/**
+ * struct iommu_gather_ops - IOMMU callbacks for TLB and page table management.
+ *
+ * @tlb_flush_all: Synchronously invalidate the entire TLB context.
+ * @tlb_add_flush: Queue up a TLB invalidation for a virtual address range.
+ * @tlb_sync:      Ensure any queue TLB invalidation has taken effect.
+ * @flush_pgtable: Ensure page table updates are visible to the IOMMU.
+ *
+ * Note that these can all be called in atomic context and must therefore
+ * not block.
+ */
+struct iommu_gather_ops {
+	void (*tlb_flush_all)(void *cookie);
+	void (*tlb_add_flush)(unsigned long iova, size_t size, bool leaf,
+			      void *cookie);
+	void (*tlb_sync)(void *cookie);
+	void (*flush_pgtable)(void *ptr, size_t size, void *cookie);
+};
+
+/**
+ * struct io_pgtable_cfg - Configuration data for a set of page tables.
+ *
+ * @quirks:        A bitmap of hardware quirks that require some special
+ *                 action by the low-level page table allocator.
+ * @pgsize_bitmap: A bitmap of page sizes supported by this set of page
+ *                 tables.
+ * @ias:           Input address (iova) size, in bits.
+ * @oas:           Output address (paddr) size, in bits.
+ * @tlb:           TLB management callbacks for this set of tables.
+ */
+struct io_pgtable_cfg {
+	#define IO_PGTABLE_QUIRK_ARM_NS	(1 << 0)	/* Set NS bit in PTEs */
+	int				quirks;
+	unsigned long			pgsize_bitmap;
+	unsigned int			ias;
+	unsigned int			oas;
+	const struct iommu_gather_ops	*tlb;
+
+	/* Low-level data specific to the table format */
+	union {
+		struct {
+			u64	ttbr[2];
+			u64	tcr;
+			u64	mair[2];
+		} arm_lpae_s1_cfg;
+
+		struct {
+			u64	vttbr;
+			u64	vtcr;
+		} arm_lpae_s2_cfg;
+	};
+};
+
+/**
+ * struct io_pgtable_ops - Page table manipulation API for IOMMU drivers.
+ *
+ * @map:          Map a physically contiguous memory region.
+ * @unmap:        Unmap a physically contiguous memory region.
+ * @iova_to_phys: Translate iova to physical address.
+ *
+ * These functions map directly onto the iommu_ops member functions with
+ * the same names.
+ */
+struct io_pgtable_ops {
+	int (*map)(struct io_pgtable_ops *ops, unsigned long iova,
+		   phys_addr_t paddr, size_t size, int prot);
+	int (*unmap)(struct io_pgtable_ops *ops, unsigned long iova,
+		     size_t size);
+	phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops,
+				    unsigned long iova);
+};
+
+/**
+ * alloc_io_pgtable_ops() - Allocate a page table allocator for use by an IOMMU.
+ *
+ * @fmt:    The page table format.
+ * @cfg:    The page table configuration. This will be modified to represent
+ *          the configuration actually provided by the allocator (e.g. the
+ *          pgsize_bitmap may be restricted).
+ * @cookie: An opaque token provided by the IOMMU driver and passed back to
+ *          the callback routines in cfg->tlb.
+ */
+struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
+					    struct io_pgtable_cfg *cfg,
+					    void *cookie);
+
+/**
+ * free_io_pgtable_ops() - Free an io_pgtable_ops structure. The caller
+ *                         *must* ensure that the page table is no longer
+ *                         live, but the TLB can be dirty.
+ *
+ * @ops: The ops returned from alloc_io_pgtable_ops.
+ */
+void free_io_pgtable_ops(struct io_pgtable_ops *ops);
+
+
+/*
+ * Internal structures for page table allocator implementations.
+ */
+
+/**
+ * struct io_pgtable - Internal structure describing a set of page tables.
+ *
+ * @fmt:    The page table format.
+ * @cookie: An opaque token provided by the IOMMU driver and passed back to
+ *          any callback routines.
+ * @cfg:    A copy of the page table configuration.
+ * @ops:    The page table operations in use for this set of page tables.
+ */
+struct io_pgtable {
+	enum io_pgtable_fmt	fmt;
+	void			*cookie;
+	struct io_pgtable_cfg	cfg;
+	struct io_pgtable_ops	ops;
+};
+
+/**
+ * struct io_pgtable_init_fns - Alloc/free a set of page tables for a
+ *                              particular format.
+ *
+ * @alloc: Allocate a set of page tables described by cfg.
+ * @free:  Free the page tables associated with iop.
+ */
+struct io_pgtable_init_fns {
+	struct io_pgtable *(*alloc)(struct io_pgtable_cfg *cfg, void *cookie);
+	void (*free)(struct io_pgtable *iop);
+};
+
+#endif /* __IO_PGTABLE_H */
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 6a2e168c3ab..41ac85af043 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -67,6 +67,7 @@
 static void __iomem *per_cpu_int_base;
 static void __iomem *main_int_base;
 static struct irq_domain *armada_370_xp_mpic_domain;
+static int parent_irq;
 #ifdef CONFIG_PCI_MSI
 static struct irq_domain *armada_370_xp_msi_domain;
 static DECLARE_BITMAP(msi_used, PCI_MSI_DOORBELL_NR);
@@ -354,6 +355,7 @@ static int armada_xp_mpic_secondary_init(struct notifier_block *nfb,
 {
 	if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
 		armada_xp_mpic_smp_cpu_init();
+
 	return NOTIFY_OK;
 }
 
@@ -362,6 +364,20 @@ static struct notifier_block armada_370_xp_mpic_cpu_notifier = {
 	.priority = 100,
 };
 
+static int mpic_cascaded_secondary_init(struct notifier_block *nfb,
+					unsigned long action, void *hcpu)
+{
+	if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
+		enable_percpu_irq(parent_irq, IRQ_TYPE_NONE);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block mpic_cascaded_cpu_notifier = {
+	.notifier_call = mpic_cascaded_secondary_init,
+	.priority = 100,
+};
+
 #endif /* CONFIG_SMP */
 
 static struct irq_domain_ops armada_370_xp_mpic_irq_ops = {
@@ -489,7 +505,7 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 					     struct device_node *parent)
 {
 	struct resource main_int_res, per_cpu_int_res;
-	int parent_irq, nr_irqs, i;
+	int nr_irqs, i;
 	u32 control;
 
 	BUG_ON(of_address_to_resource(node, 0, &main_int_res));
@@ -537,6 +553,9 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 		register_cpu_notifier(&armada_370_xp_mpic_cpu_notifier);
 #endif
 	} else {
+#ifdef CONFIG_SMP
+		register_cpu_notifier(&mpic_cascaded_cpu_notifier);
+#endif
 		irq_set_chained_handler(parent_irq,
 					armada_370_xp_mpic_handle_cascade_irq);
 	}
diff --git a/drivers/irqchip/irq-atmel-aic-common.c b/drivers/irqchip/irq-atmel-aic-common.c
index cc4f9d80122..fa22e5ba3d3 100644
--- a/drivers/irqchip/irq-atmel-aic-common.c
+++ b/drivers/irqchip/irq-atmel-aic-common.c
@@ -28,7 +28,7 @@
 #define AT91_AIC_IRQ_MIN_PRIORITY	0
 #define AT91_AIC_IRQ_MAX_PRIORITY	7
 
-#define AT91_AIC_SRCTYPE		GENMASK(7, 6)
+#define AT91_AIC_SRCTYPE		GENMASK(6, 5)
 #define AT91_AIC_SRCTYPE_LOW		(0 << 5)
 #define AT91_AIC_SRCTYPE_FALLING	(1 << 5)
 #define AT91_AIC_SRCTYPE_HIGH		(2 << 5)
@@ -74,7 +74,7 @@ int aic_common_set_type(struct irq_data *d, unsigned type, unsigned *val)
 		return -EINVAL;
 	}
 
-	*val &= AT91_AIC_SRCTYPE;
+	*val &= ~AT91_AIC_SRCTYPE;
 	*val |= aic_type;
 
 	return 0;
diff --git a/drivers/irqchip/irq-omap-intc.c b/drivers/irqchip/irq-omap-intc.c
index 28718d3e828..c03f140acba 100644
--- a/drivers/irqchip/irq-omap-intc.c
+++ b/drivers/irqchip/irq-omap-intc.c
@@ -263,7 +263,7 @@ static int __init omap_init_irq_of(struct device_node *node)
 	return ret;
 }
 
-static int __init omap_init_irq_legacy(u32 base)
+static int __init omap_init_irq_legacy(u32 base, struct device_node *node)
 {
 	int j, irq_base;
 
@@ -277,7 +277,7 @@ static int __init omap_init_irq_legacy(u32 base)
 		irq_base = 0;
 	}
 
-	domain = irq_domain_add_legacy(NULL, omap_nr_irqs, irq_base, 0,
+	domain = irq_domain_add_legacy(node, omap_nr_irqs, irq_base, 0,
 			&irq_domain_simple_ops, NULL);
 
 	omap_irq_soft_reset();
@@ -301,10 +301,26 @@ static int __init omap_init_irq(u32 base, struct device_node *node)
 {
 	int ret;
 
-	if (node)
+	/*
+	 * FIXME legacy OMAP DMA driver sitting under arch/arm/plat-omap/dma.c
+	 * depends is still not ready for linear IRQ domains; because of that
+	 * we need to temporarily "blacklist" OMAP2 and OMAP3 devices from using
+	 * linear IRQ Domain until that driver is finally fixed.
+	 */
+	if (of_device_is_compatible(node, "ti,omap2-intc") ||
+			of_device_is_compatible(node, "ti,omap3-intc")) {
+		struct resource res;
+
+		if (of_address_to_resource(node, 0, &res))
+			return -ENOMEM;
+
+		base = res.start;
+		ret = omap_init_irq_legacy(base, node);
+	} else if (node) {
 		ret = omap_init_irq_of(node);
-	else
-		ret = omap_init_irq_legacy(base);
+	} else {
+		ret = omap_init_irq_legacy(base, NULL);
+	}
 
 	if (ret == 0)
 		omap_irq_enable_protection();
diff --git a/drivers/irqchip/irq-sunxi-nmi.c b/drivers/irqchip/irq-sunxi-nmi.c
index 12f547a44ae..eb9b59e8f12 100644
--- a/drivers/irqchip/irq-sunxi-nmi.c
+++ b/drivers/irqchip/irq-sunxi-nmi.c
@@ -104,7 +104,7 @@ static int sunxi_sc_nmi_set_type(struct irq_data *data, unsigned int flow_type)
 	irqd_set_trigger_type(data, flow_type);
 	irq_setup_alt_chip(data, flow_type);
 
-	for (i = 0; i <= gc->num_ct; i++, ct++)
+	for (i = 0; i < gc->num_ct; i++, ct++)
 		if (ct->type & flow_type)
 			ctrl_off = ct->regs.type;
 
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index 7440c58b8e6..f5dfb8f7fe3 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -173,6 +173,7 @@ void led_classdev_resume(struct led_classdev *led_cdev)
 }
 EXPORT_SYMBOL_GPL(led_classdev_resume);
 
+#ifdef CONFIG_PM_SLEEP
 static int led_suspend(struct device *dev)
 {
 	struct led_classdev *led_cdev = dev_get_drvdata(dev);
@@ -192,11 +193,9 @@ static int led_resume(struct device *dev)
 
 	return 0;
 }
+#endif
 
-static const struct dev_pm_ops leds_class_dev_pm_ops = {
-	.suspend        = led_suspend,
-	.resume         = led_resume,
-};
+static SIMPLE_DEV_PM_OPS(leds_class_dev_pm_ops, led_suspend, led_resume);
 
 /**
  * led_classdev_register - register a new object of led_classdev class.
diff --git a/drivers/leds/leds-netxbig.c b/drivers/leds/leds-netxbig.c
index 64fde485dca..4c794f15a57 100644
--- a/drivers/leds/leds-netxbig.c
+++ b/drivers/leds/leds-netxbig.c
@@ -330,18 +330,18 @@ create_netxbig_led(struct platform_device *pdev,
 	led_dat->sata = 0;
 	led_dat->cdev.brightness = LED_OFF;
 	led_dat->cdev.flags |= LED_CORE_SUSPENDRESUME;
-	/*
-	 * If available, expose the SATA activity blink capability through
-	 * a "sata" sysfs attribute.
-	 */
-	if (led_dat->mode_val[NETXBIG_LED_SATA] != NETXBIG_LED_INVALID_MODE)
-		led_dat->cdev.groups = netxbig_led_groups;
 	led_dat->mode_addr = template->mode_addr;
 	led_dat->mode_val = template->mode_val;
 	led_dat->bright_addr = template->bright_addr;
 	led_dat->bright_max = (1 << pdata->gpio_ext->num_data) - 1;
 	led_dat->timer = pdata->timer;
 	led_dat->num_timer = pdata->num_timer;
+	/*
+	 * If available, expose the SATA activity blink capability through
+	 * a "sata" sysfs attribute.
+	 */
+	if (led_dat->mode_val[NETXBIG_LED_SATA] != NETXBIG_LED_INVALID_MODE)
+		led_dat->cdev.groups = netxbig_led_groups;
 
 	return led_classdev_register(&pdev->dev, &led_dat->cdev);
 }
diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c
index 6590558d1d3..ed70f1e72b2 100644
--- a/drivers/lguest/core.c
+++ b/drivers/lguest/core.c
@@ -173,7 +173,7 @@ static void unmap_switcher(void)
 bool lguest_address_ok(const struct lguest *lg,
 		       unsigned long addr, unsigned long len)
 {
-	return (addr+len) / PAGE_SIZE < lg->pfn_limit && (addr+len >= addr);
+	return addr+len <= lg->pfn_limit * PAGE_SIZE && (addr+len >= addr);
 }
 
 /*
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index 922a1acbf65..6adfd7ba4c9 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -47,6 +47,7 @@
 #include <asm/lguest.h>
 #include <asm/uaccess.h>
 #include <asm/i387.h>
+#include <asm/tlbflush.h>
 #include "../lg.h"
 
 static int cpu_had_pge;
@@ -452,9 +453,9 @@ void lguest_arch_handle_trap(struct lg_cpu *cpu)
 static void adjust_pge(void *on)
 {
 	if (on)
-		write_cr4(read_cr4() | X86_CR4_PGE);
+		cr4_set_bits(X86_CR4_PGE);
 	else
-		write_cr4(read_cr4() & ~X86_CR4_PGE);
+		cr4_clear_bits(X86_CR4_PGE);
 }
 
 /*H:020
diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig
index 9fd9c6717e0..54527f23157 100644
--- a/drivers/mailbox/Kconfig
+++ b/drivers/mailbox/Kconfig
@@ -6,6 +6,15 @@ menuconfig MAILBOX
 	  signals. Say Y if your platform supports hardware mailboxes.
 
 if MAILBOX
+
+config ARM_MHU
+	tristate "ARM MHU Mailbox"
+	depends on ARM_AMBA
+	help
+	  Say Y here if you want to build the ARM MHU controller driver.
+	  The controller has 3 mailbox channels, the last of which can be
+	  used in Secure mode only.
+
 config PL320_MBOX
 	bool "ARM PL320 Mailbox"
 	depends on ARM_AMBA
diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile
index 94ed7cefb14..43fd9318037 100644
--- a/drivers/mailbox/Makefile
+++ b/drivers/mailbox/Makefile
@@ -2,6 +2,8 @@
 
 obj-$(CONFIG_MAILBOX)		+= mailbox.o
 
+obj-$(CONFIG_ARM_MHU)	+= arm_mhu.o
+
 obj-$(CONFIG_PL320_MBOX)	+= pl320-ipc.o
 
 obj-$(CONFIG_OMAP2PLUS_MBOX)	+= omap-mailbox.o
diff --git a/drivers/mailbox/arm_mhu.c b/drivers/mailbox/arm_mhu.c
new file mode 100644
index 00000000000..ac693c63535
--- /dev/null
+++ b/drivers/mailbox/arm_mhu.c
@@ -0,0 +1,195 @@
+/*
+ * Copyright (C) 2013-2015 Fujitsu Semiconductor Ltd.
+ * Copyright (C) 2015 Linaro Ltd.
+ * Author: Jassi Brar <jaswinder.singh@linaro.org>
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/amba/bus.h>
+#include <linux/mailbox_controller.h>
+
+#define INTR_STAT_OFS	0x0
+#define INTR_SET_OFS	0x8
+#define INTR_CLR_OFS	0x10
+
+#define MHU_LP_OFFSET	0x0
+#define MHU_HP_OFFSET	0x20
+#define MHU_SEC_OFFSET	0x200
+#define TX_REG_OFFSET	0x100
+
+#define MHU_CHANS	3
+
+struct mhu_link {
+	unsigned irq;
+	void __iomem *tx_reg;
+	void __iomem *rx_reg;
+};
+
+struct arm_mhu {
+	void __iomem *base;
+	struct mhu_link mlink[MHU_CHANS];
+	struct mbox_chan chan[MHU_CHANS];
+	struct mbox_controller mbox;
+};
+
+static irqreturn_t mhu_rx_interrupt(int irq, void *p)
+{
+	struct mbox_chan *chan = p;
+	struct mhu_link *mlink = chan->con_priv;
+	u32 val;
+
+	val = readl_relaxed(mlink->rx_reg + INTR_STAT_OFS);
+	if (!val)
+		return IRQ_NONE;
+
+	mbox_chan_received_data(chan, (void *)&val);
+
+	writel_relaxed(val, mlink->rx_reg + INTR_CLR_OFS);
+
+	return IRQ_HANDLED;
+}
+
+static bool mhu_last_tx_done(struct mbox_chan *chan)
+{
+	struct mhu_link *mlink = chan->con_priv;
+	u32 val = readl_relaxed(mlink->tx_reg + INTR_STAT_OFS);
+
+	return (val == 0);
+}
+
+static int mhu_send_data(struct mbox_chan *chan, void *data)
+{
+	struct mhu_link *mlink = chan->con_priv;
+	u32 *arg = data;
+
+	writel_relaxed(*arg, mlink->tx_reg + INTR_SET_OFS);
+
+	return 0;
+}
+
+static int mhu_startup(struct mbox_chan *chan)
+{
+	struct mhu_link *mlink = chan->con_priv;
+	u32 val;
+	int ret;
+
+	val = readl_relaxed(mlink->tx_reg + INTR_STAT_OFS);
+	writel_relaxed(val, mlink->tx_reg + INTR_CLR_OFS);
+
+	ret = request_irq(mlink->irq, mhu_rx_interrupt,
+			  IRQF_SHARED, "mhu_link", chan);
+	if (ret) {
+		dev_err(chan->mbox->dev,
+			"Unable to aquire IRQ %d\n", mlink->irq);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void mhu_shutdown(struct mbox_chan *chan)
+{
+	struct mhu_link *mlink = chan->con_priv;
+
+	free_irq(mlink->irq, chan);
+}
+
+static struct mbox_chan_ops mhu_ops = {
+	.send_data = mhu_send_data,
+	.startup = mhu_startup,
+	.shutdown = mhu_shutdown,
+	.last_tx_done = mhu_last_tx_done,
+};
+
+static int mhu_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	int i, err;
+	struct arm_mhu *mhu;
+	struct device *dev = &adev->dev;
+	int mhu_reg[MHU_CHANS] = {MHU_LP_OFFSET, MHU_HP_OFFSET, MHU_SEC_OFFSET};
+
+	/* Allocate memory for device */
+	mhu = devm_kzalloc(dev, sizeof(*mhu), GFP_KERNEL);
+	if (!mhu)
+		return -ENOMEM;
+
+	mhu->base = devm_ioremap_resource(dev, &adev->res);
+	if (IS_ERR(mhu->base)) {
+		dev_err(dev, "ioremap failed\n");
+		return PTR_ERR(mhu->base);
+	}
+
+	for (i = 0; i < MHU_CHANS; i++) {
+		mhu->chan[i].con_priv = &mhu->mlink[i];
+		mhu->mlink[i].irq = adev->irq[i];
+		mhu->mlink[i].rx_reg = mhu->base + mhu_reg[i];
+		mhu->mlink[i].tx_reg = mhu->mlink[i].rx_reg + TX_REG_OFFSET;
+	}
+
+	mhu->mbox.dev = dev;
+	mhu->mbox.chans = &mhu->chan[0];
+	mhu->mbox.num_chans = MHU_CHANS;
+	mhu->mbox.ops = &mhu_ops;
+	mhu->mbox.txdone_irq = false;
+	mhu->mbox.txdone_poll = true;
+	mhu->mbox.txpoll_period = 10;
+
+	amba_set_drvdata(adev, mhu);
+
+	err = mbox_controller_register(&mhu->mbox);
+	if (err) {
+		dev_err(dev, "Failed to register mailboxes %d\n", err);
+		return err;
+	}
+
+	dev_info(dev, "ARM MHU Mailbox registered\n");
+	return 0;
+}
+
+static int mhu_remove(struct amba_device *adev)
+{
+	struct arm_mhu *mhu = amba_get_drvdata(adev);
+
+	mbox_controller_unregister(&mhu->mbox);
+
+	return 0;
+}
+
+static struct amba_id mhu_ids[] = {
+	{
+		.id	= 0x1bb098,
+		.mask	= 0xffffff,
+	},
+	{ 0, 0 },
+};
+MODULE_DEVICE_TABLE(amba, mhu_ids);
+
+static struct amba_driver arm_mhu_driver = {
+	.drv = {
+		.name	= "mhu",
+	},
+	.id_table	= mhu_ids,
+	.probe		= mhu_probe,
+	.remove		= mhu_remove,
+};
+module_amba_driver(arm_mhu_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("ARM MHU Driver");
+MODULE_AUTHOR("Jassi Brar <jassisinghbrar@gmail.com>");
diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c
index afcb430508e..1067d9df5b9 100644
--- a/drivers/mailbox/mailbox.c
+++ b/drivers/mailbox/mailbox.c
@@ -28,6 +28,8 @@
 static LIST_HEAD(mbox_cons);
 static DEFINE_MUTEX(con_mutex);
 
+static void poll_txdone(unsigned long data);
+
 static int add_to_rbuf(struct mbox_chan *chan, void *mssg)
 {
 	int idx;
@@ -60,7 +62,7 @@ static void msg_submit(struct mbox_chan *chan)
 	unsigned count, idx;
 	unsigned long flags;
 	void *data;
-	int err;
+	int err = -EBUSY;
 
 	spin_lock_irqsave(&chan->lock, flags);
 
@@ -76,6 +78,8 @@ static void msg_submit(struct mbox_chan *chan)
 
 	data = chan->msg_data[idx];
 
+	if (chan->cl->tx_prepare)
+		chan->cl->tx_prepare(chan->cl, data);
 	/* Try to submit a message to the MBOX controller */
 	err = chan->mbox->ops->send_data(chan, data);
 	if (!err) {
@@ -84,6 +88,9 @@ static void msg_submit(struct mbox_chan *chan)
 	}
 exit:
 	spin_unlock_irqrestore(&chan->lock, flags);
+
+	if (!err && (chan->txdone_method & TXDONE_BY_POLL))
+		poll_txdone((unsigned long)chan->mbox);
 }
 
 static void tx_tick(struct mbox_chan *chan, int r)
@@ -117,10 +124,11 @@ static void poll_txdone(unsigned long data)
 		struct mbox_chan *chan = &mbox->chans[i];
 
 		if (chan->active_req && chan->cl) {
-			resched = true;
 			txdone = chan->mbox->ops->last_tx_done(chan);
 			if (txdone)
 				tx_tick(chan, 0);
+			else
+				resched = true;
 		}
 	}
 
@@ -252,9 +260,6 @@ int mbox_send_message(struct mbox_chan *chan, void *mssg)
 
 	msg_submit(chan);
 
-	if (chan->txdone_method	== TXDONE_BY_POLL)
-		poll_txdone((unsigned long)chan->mbox);
-
 	if (chan->cl->tx_block && chan->active_req) {
 		unsigned long wait;
 		int ret;
@@ -315,7 +320,7 @@ struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index)
 		return ERR_PTR(-ENODEV);
 	}
 
-	chan = NULL;
+	chan = ERR_PTR(-EPROBE_DEFER);
 	list_for_each_entry(mbox, &mbox_cons, node)
 		if (mbox->dev->of_node == spec.np) {
 			chan = mbox->of_xlate(mbox, &spec);
@@ -324,7 +329,12 @@ struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index)
 
 	of_node_put(spec.np);
 
-	if (!chan || chan->cl || !try_module_get(mbox->dev->driver->owner)) {
+	if (IS_ERR(chan)) {
+		mutex_unlock(&con_mutex);
+		return chan;
+	}
+
+	if (chan->cl || !try_module_get(mbox->dev->driver->owner)) {
 		dev_dbg(dev, "%s: mailbox not free\n", __func__);
 		mutex_unlock(&con_mutex);
 		return ERR_PTR(-EBUSY);
@@ -387,7 +397,7 @@ of_mbox_index_xlate(struct mbox_controller *mbox,
 	int ind = sp->args[0];
 
 	if (ind >= mbox->num_chans)
-		return NULL;
+		return ERR_PTR(-EINVAL);
 
 	return &mbox->chans[ind];
 }
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index afe79719ea3..ecbd3ffcf35 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -532,6 +532,19 @@ static void use_dmio(struct dm_buffer *b, int rw, sector_t block,
 		end_io(&b->bio, r);
 }
 
+static void inline_endio(struct bio *bio, int error)
+{
+	bio_end_io_t *end_fn = bio->bi_private;
+
+	/*
+	 * Reset the bio to free any attached resources
+	 * (e.g. bio integrity profiles).
+	 */
+	bio_reset(bio);
+
+	end_fn(bio, error);
+}
+
 static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
 			   bio_end_io_t *end_io)
 {
@@ -543,7 +556,12 @@ static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
 	b->bio.bi_max_vecs = DM_BUFIO_INLINE_VECS;
 	b->bio.bi_iter.bi_sector = block << b->c->sectors_per_block_bits;
 	b->bio.bi_bdev = b->c->bdev;
-	b->bio.bi_end_io = end_io;
+	b->bio.bi_end_io = inline_endio;
+	/*
+	 * Use of .bi_private isn't a problem here because
+	 * the dm_buffer's inline bio is local to bufio.
+	 */
+	b->bio.bi_private = end_io;
 
 	/*
 	 * We assume that if len >= PAGE_SIZE ptr is page-aligned.
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index 06709257add..1e64e9c50d8 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -94,6 +94,9 @@ struct cache_disk_superblock {
 } __packed;
 
 struct dm_cache_metadata {
+	atomic_t ref_count;
+	struct list_head list;
+
 	struct block_device *bdev;
 	struct dm_block_manager *bm;
 	struct dm_space_map *metadata_sm;
@@ -669,10 +672,10 @@ static void unpack_value(__le64 value_le, dm_oblock_t *block, unsigned *flags)
 
 /*----------------------------------------------------------------*/
 
-struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev,
-						 sector_t data_block_size,
-						 bool may_format_device,
-						 size_t policy_hint_size)
+static struct dm_cache_metadata *metadata_open(struct block_device *bdev,
+					       sector_t data_block_size,
+					       bool may_format_device,
+					       size_t policy_hint_size)
 {
 	int r;
 	struct dm_cache_metadata *cmd;
@@ -680,9 +683,10 @@ struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev,
 	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
 	if (!cmd) {
 		DMERR("could not allocate metadata struct");
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 
+	atomic_set(&cmd->ref_count, 1);
 	init_rwsem(&cmd->root_lock);
 	cmd->bdev = bdev;
 	cmd->data_block_size = data_block_size;
@@ -705,10 +709,96 @@ struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev,
 	return cmd;
 }
 
+/*
+ * We keep a little list of ref counted metadata objects to prevent two
+ * different target instances creating separate bufio instances.  This is
+ * an issue if a table is reloaded before the suspend.
+ */
+static DEFINE_MUTEX(table_lock);
+static LIST_HEAD(table);
+
+static struct dm_cache_metadata *lookup(struct block_device *bdev)
+{
+	struct dm_cache_metadata *cmd;
+
+	list_for_each_entry(cmd, &table, list)
+		if (cmd->bdev == bdev) {
+			atomic_inc(&cmd->ref_count);
+			return cmd;
+		}
+
+	return NULL;
+}
+
+static struct dm_cache_metadata *lookup_or_open(struct block_device *bdev,
+						sector_t data_block_size,
+						bool may_format_device,
+						size_t policy_hint_size)
+{
+	struct dm_cache_metadata *cmd, *cmd2;
+
+	mutex_lock(&table_lock);
+	cmd = lookup(bdev);
+	mutex_unlock(&table_lock);
+
+	if (cmd)
+		return cmd;
+
+	cmd = metadata_open(bdev, data_block_size, may_format_device, policy_hint_size);
+	if (!IS_ERR(cmd)) {
+		mutex_lock(&table_lock);
+		cmd2 = lookup(bdev);
+		if (cmd2) {
+			mutex_unlock(&table_lock);
+			__destroy_persistent_data_objects(cmd);
+			kfree(cmd);
+			return cmd2;
+		}
+		list_add(&cmd->list, &table);
+		mutex_unlock(&table_lock);
+	}
+
+	return cmd;
+}
+
+static bool same_params(struct dm_cache_metadata *cmd, sector_t data_block_size)
+{
+	if (cmd->data_block_size != data_block_size) {
+		DMERR("data_block_size (%llu) different from that in metadata (%llu)\n",
+		      (unsigned long long) data_block_size,
+		      (unsigned long long) cmd->data_block_size);
+		return false;
+	}
+
+	return true;
+}
+
+struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev,
+						 sector_t data_block_size,
+						 bool may_format_device,
+						 size_t policy_hint_size)
+{
+	struct dm_cache_metadata *cmd = lookup_or_open(bdev, data_block_size,
+						       may_format_device, policy_hint_size);
+
+	if (!IS_ERR(cmd) && !same_params(cmd, data_block_size)) {
+		dm_cache_metadata_close(cmd);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return cmd;
+}
+
 void dm_cache_metadata_close(struct dm_cache_metadata *cmd)
 {
-	__destroy_persistent_data_objects(cmd);
-	kfree(cmd);
+	if (atomic_dec_and_test(&cmd->ref_count)) {
+		mutex_lock(&table_lock);
+		list_del(&cmd->list);
+		mutex_unlock(&table_lock);
+
+		__destroy_persistent_data_objects(cmd);
+		kfree(cmd);
+	}
 }
 
 /*
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 7130505c242..3baed67cf26 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -222,7 +222,13 @@ struct cache {
 	struct list_head need_commit_migrations;
 	sector_t migration_threshold;
 	wait_queue_head_t migration_wait;
-	atomic_t nr_migrations;
+	atomic_t nr_allocated_migrations;
+
+	/*
+	 * The number of in flight migrations that are performing
+	 * background io. eg, promotion, writeback.
+	 */
+	atomic_t nr_io_migrations;
 
 	wait_queue_head_t quiescing_wait;
 	atomic_t quiescing;
@@ -258,7 +264,6 @@ struct cache {
 	struct dm_deferred_set *all_io_ds;
 
 	mempool_t *migration_pool;
-	struct dm_cache_migration *next_migration;
 
 	struct dm_cache_policy *policy;
 	unsigned policy_nr_args;
@@ -349,10 +354,31 @@ static void free_prison_cell(struct cache *cache, struct dm_bio_prison_cell *cel
 	dm_bio_prison_free_cell(cache->prison, cell);
 }
 
+static struct dm_cache_migration *alloc_migration(struct cache *cache)
+{
+	struct dm_cache_migration *mg;
+
+	mg = mempool_alloc(cache->migration_pool, GFP_NOWAIT);
+	if (mg) {
+		mg->cache = cache;
+		atomic_inc(&mg->cache->nr_allocated_migrations);
+	}
+
+	return mg;
+}
+
+static void free_migration(struct dm_cache_migration *mg)
+{
+	if (atomic_dec_and_test(&mg->cache->nr_allocated_migrations))
+		wake_up(&mg->cache->migration_wait);
+
+	mempool_free(mg, mg->cache->migration_pool);
+}
+
 static int prealloc_data_structs(struct cache *cache, struct prealloc *p)
 {
 	if (!p->mg) {
-		p->mg = mempool_alloc(cache->migration_pool, GFP_NOWAIT);
+		p->mg = alloc_migration(cache);
 		if (!p->mg)
 			return -ENOMEM;
 	}
@@ -381,7 +407,7 @@ static void prealloc_free_structs(struct cache *cache, struct prealloc *p)
 		free_prison_cell(cache, p->cell1);
 
 	if (p->mg)
-		mempool_free(p->mg, cache->migration_pool);
+		free_migration(p->mg);
 }
 
 static struct dm_cache_migration *prealloc_get_migration(struct prealloc *p)
@@ -817,24 +843,14 @@ static void remap_to_origin_then_cache(struct cache *cache, struct bio *bio,
  * Migration covers moving data from the origin device to the cache, or
  * vice versa.
  *--------------------------------------------------------------*/
-static void free_migration(struct dm_cache_migration *mg)
-{
-	mempool_free(mg, mg->cache->migration_pool);
-}
-
-static void inc_nr_migrations(struct cache *cache)
+static void inc_io_migrations(struct cache *cache)
 {
-	atomic_inc(&cache->nr_migrations);
+	atomic_inc(&cache->nr_io_migrations);
 }
 
-static void dec_nr_migrations(struct cache *cache)
+static void dec_io_migrations(struct cache *cache)
 {
-	atomic_dec(&cache->nr_migrations);
-
-	/*
-	 * Wake the worker in case we're suspending the target.
-	 */
-	wake_up(&cache->migration_wait);
+	atomic_dec(&cache->nr_io_migrations);
 }
 
 static void __cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell,
@@ -857,11 +873,10 @@ static void cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell,
 	wake_worker(cache);
 }
 
-static void cleanup_migration(struct dm_cache_migration *mg)
+static void free_io_migration(struct dm_cache_migration *mg)
 {
-	struct cache *cache = mg->cache;
+	dec_io_migrations(mg->cache);
 	free_migration(mg);
-	dec_nr_migrations(cache);
 }
 
 static void migration_failure(struct dm_cache_migration *mg)
@@ -886,7 +901,7 @@ static void migration_failure(struct dm_cache_migration *mg)
 		cell_defer(cache, mg->new_ocell, true);
 	}
 
-	cleanup_migration(mg);
+	free_io_migration(mg);
 }
 
 static void migration_success_pre_commit(struct dm_cache_migration *mg)
@@ -897,7 +912,7 @@ static void migration_success_pre_commit(struct dm_cache_migration *mg)
 	if (mg->writeback) {
 		clear_dirty(cache, mg->old_oblock, mg->cblock);
 		cell_defer(cache, mg->old_ocell, false);
-		cleanup_migration(mg);
+		free_io_migration(mg);
 		return;
 
 	} else if (mg->demote) {
@@ -907,14 +922,14 @@ static void migration_success_pre_commit(struct dm_cache_migration *mg)
 					     mg->old_oblock);
 			if (mg->promote)
 				cell_defer(cache, mg->new_ocell, true);
-			cleanup_migration(mg);
+			free_io_migration(mg);
 			return;
 		}
 	} else {
 		if (dm_cache_insert_mapping(cache->cmd, mg->cblock, mg->new_oblock)) {
 			DMWARN_LIMIT("promotion failed; couldn't update on disk metadata");
 			policy_remove_mapping(cache->policy, mg->new_oblock);
-			cleanup_migration(mg);
+			free_io_migration(mg);
 			return;
 		}
 	}
@@ -947,18 +962,22 @@ static void migration_success_post_commit(struct dm_cache_migration *mg)
 		} else {
 			if (mg->invalidate)
 				policy_remove_mapping(cache->policy, mg->old_oblock);
-			cleanup_migration(mg);
+			free_io_migration(mg);
 		}
 
 	} else {
-		clear_dirty(cache, mg->new_oblock, mg->cblock);
-		if (mg->requeue_holder)
+		if (mg->requeue_holder) {
+			clear_dirty(cache, mg->new_oblock, mg->cblock);
 			cell_defer(cache, mg->new_ocell, true);
-		else {
+		} else {
+			/*
+			 * The block was promoted via an overwrite, so it's dirty.
+			 */
+			set_dirty(cache, mg->new_oblock, mg->cblock);
 			bio_endio(mg->new_ocell->holder, 0);
 			cell_defer(cache, mg->new_ocell, false);
 		}
-		cleanup_migration(mg);
+		free_io_migration(mg);
 	}
 }
 
@@ -1070,7 +1089,8 @@ static void issue_copy(struct dm_cache_migration *mg)
 
 		avoid = is_discarded_oblock(cache, mg->new_oblock);
 
-		if (!avoid && bio_writes_complete_block(cache, bio)) {
+		if (writeback_mode(&cache->features) &&
+		    !avoid && bio_writes_complete_block(cache, bio)) {
 			issue_overwrite(mg, bio);
 			return;
 		}
@@ -1173,7 +1193,7 @@ static void promote(struct cache *cache, struct prealloc *structs,
 	mg->new_ocell = cell;
 	mg->start_jiffies = jiffies;
 
-	inc_nr_migrations(cache);
+	inc_io_migrations(cache);
 	quiesce_migration(mg);
 }
 
@@ -1196,7 +1216,7 @@ static void writeback(struct cache *cache, struct prealloc *structs,
 	mg->new_ocell = NULL;
 	mg->start_jiffies = jiffies;
 
-	inc_nr_migrations(cache);
+	inc_io_migrations(cache);
 	quiesce_migration(mg);
 }
 
@@ -1222,7 +1242,7 @@ static void demote_then_promote(struct cache *cache, struct prealloc *structs,
 	mg->new_ocell = new_ocell;
 	mg->start_jiffies = jiffies;
 
-	inc_nr_migrations(cache);
+	inc_io_migrations(cache);
 	quiesce_migration(mg);
 }
 
@@ -1249,7 +1269,7 @@ static void invalidate(struct cache *cache, struct prealloc *structs,
 	mg->new_ocell = NULL;
 	mg->start_jiffies = jiffies;
 
-	inc_nr_migrations(cache);
+	inc_io_migrations(cache);
 	quiesce_migration(mg);
 }
 
@@ -1315,7 +1335,7 @@ static void process_discard_bio(struct cache *cache, struct bio *bio)
 
 static bool spare_migration_bandwidth(struct cache *cache)
 {
-	sector_t current_volume = (atomic_read(&cache->nr_migrations) + 1) *
+	sector_t current_volume = (atomic_read(&cache->nr_io_migrations) + 1) *
 		cache->sectors_per_block;
 	return current_volume < cache->migration_threshold;
 }
@@ -1665,7 +1685,7 @@ static void stop_quiescing(struct cache *cache)
 
 static void wait_for_migrations(struct cache *cache)
 {
-	wait_event(cache->migration_wait, !atomic_read(&cache->nr_migrations));
+	wait_event(cache->migration_wait, !atomic_read(&cache->nr_allocated_migrations));
 }
 
 static void stop_worker(struct cache *cache)
@@ -1777,9 +1797,6 @@ static void destroy(struct cache *cache)
 {
 	unsigned i;
 
-	if (cache->next_migration)
-		mempool_free(cache->next_migration, cache->migration_pool);
-
 	if (cache->migration_pool)
 		mempool_destroy(cache->migration_pool);
 
@@ -2287,7 +2304,8 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 	INIT_LIST_HEAD(&cache->quiesced_migrations);
 	INIT_LIST_HEAD(&cache->completed_migrations);
 	INIT_LIST_HEAD(&cache->need_commit_migrations);
-	atomic_set(&cache->nr_migrations, 0);
+	atomic_set(&cache->nr_allocated_migrations, 0);
+	atomic_set(&cache->nr_io_migrations, 0);
 	init_waitqueue_head(&cache->migration_wait);
 
 	init_waitqueue_head(&cache->quiescing_wait);
@@ -2346,8 +2364,6 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 		goto bad;
 	}
 
-	cache->next_migration = NULL;
-
 	cache->need_tick_bio = true;
 	cache->sized = false;
 	cache->invalidate = false;
@@ -2549,11 +2565,11 @@ static int __cache_map(struct cache *cache, struct bio *bio, struct dm_bio_priso
 static int cache_map(struct dm_target *ti, struct bio *bio)
 {
 	int r;
-	struct dm_bio_prison_cell *cell;
+	struct dm_bio_prison_cell *cell = NULL;
 	struct cache *cache = ti->private;
 
 	r = __cache_map(cache, bio, &cell);
-	if (r == DM_MAPIO_REMAPPED) {
+	if (r == DM_MAPIO_REMAPPED && cell) {
 		inc_ds(cache, bio, cell);
 		cell_defer(cache, cell, false);
 	}
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index fc93b9330af..5503e43e5f2 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -18,9 +18,11 @@
 #include <linux/slab.h>
 #include <linux/crypto.h>
 #include <linux/workqueue.h>
+#include <linux/kthread.h>
 #include <linux/backing-dev.h>
 #include <linux/atomic.h>
 #include <linux/scatterlist.h>
+#include <linux/rbtree.h>
 #include <asm/page.h>
 #include <asm/unaligned.h>
 #include <crypto/hash.h>
@@ -58,7 +60,8 @@ struct dm_crypt_io {
 	atomic_t io_pending;
 	int error;
 	sector_t sector;
-	struct dm_crypt_io *base_io;
+
+	struct rb_node rb_node;
 } CRYPTO_MINALIGN_ATTR;
 
 struct dm_crypt_request {
@@ -108,7 +111,8 @@ struct iv_tcw_private {
  * Crypt: maps a linear range of a block device
  * and encrypts / decrypts at the same time.
  */
-enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID };
+enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID,
+	     DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD };
 
 /*
  * The fields in here must be read only after initialization.
@@ -121,14 +125,18 @@ struct crypt_config {
 	 * pool for per bio private data, crypto requests and
 	 * encryption requeusts/buffer pages
 	 */
-	mempool_t *io_pool;
 	mempool_t *req_pool;
 	mempool_t *page_pool;
 	struct bio_set *bs;
+	struct mutex bio_alloc_lock;
 
 	struct workqueue_struct *io_queue;
 	struct workqueue_struct *crypt_queue;
 
+	struct task_struct *write_thread;
+	wait_queue_head_t write_thread_wait;
+	struct rb_root write_tree;
+
 	char *cipher;
 	char *cipher_string;
 
@@ -172,9 +180,6 @@ struct crypt_config {
 };
 
 #define MIN_IOS        16
-#define MIN_POOL_PAGES 32
-
-static struct kmem_cache *_crypt_io_pool;
 
 static void clone_init(struct dm_crypt_io *, struct bio *);
 static void kcryptd_queue_crypt(struct dm_crypt_io *io);
@@ -223,7 +228,7 @@ static struct crypto_ablkcipher *any_tfm(struct crypt_config *cc)
  *
  * tcw:  Compatible implementation of the block chaining mode used
  *       by the TrueCrypt device encryption system (prior to version 4.1).
- *       For more info see: http://www.truecrypt.org
+ *       For more info see: https://gitlab.com/cryptsetup/cryptsetup/wikis/TrueCryptOnDiskFormat
  *       It operates on full 512 byte sectors and uses CBC
  *       with an IV derived from initial key and the sector number.
  *       In addition, whitening value is applied on every sector, whitening
@@ -705,7 +710,7 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc,
 	for (i = 0; i < ((1 << SECTOR_SHIFT) / 8); i++)
 		crypto_xor(data + i * 8, buf, 8);
 out:
-	memset(buf, 0, sizeof(buf));
+	memzero_explicit(buf, sizeof(buf));
 	return r;
 }
 
@@ -946,57 +951,70 @@ static int crypt_convert(struct crypt_config *cc,
 	return 0;
 }
 
+static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone);
+
 /*
  * Generate a new unfragmented bio with the given size
  * This should never violate the device limitations
- * May return a smaller bio when running out of pages, indicated by
- * *out_of_pages set to 1.
+ *
+ * This function may be called concurrently. If we allocate from the mempool
+ * concurrently, there is a possibility of deadlock. For example, if we have
+ * mempool of 256 pages, two processes, each wanting 256, pages allocate from
+ * the mempool concurrently, it may deadlock in a situation where both processes
+ * have allocated 128 pages and the mempool is exhausted.
+ *
+ * In order to avoid this scenario we allocate the pages under a mutex.
+ *
+ * In order to not degrade performance with excessive locking, we try
+ * non-blocking allocations without a mutex first but on failure we fallback
+ * to blocking allocations with a mutex.
  */
-static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size,
-				      unsigned *out_of_pages)
+static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size)
 {
 	struct crypt_config *cc = io->cc;
 	struct bio *clone;
 	unsigned int nr_iovecs = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	gfp_t gfp_mask = GFP_NOIO | __GFP_HIGHMEM;
-	unsigned i, len;
+	gfp_t gfp_mask = GFP_NOWAIT | __GFP_HIGHMEM;
+	unsigned i, len, remaining_size;
 	struct page *page;
+	struct bio_vec *bvec;
+
+retry:
+	if (unlikely(gfp_mask & __GFP_WAIT))
+		mutex_lock(&cc->bio_alloc_lock);
 
 	clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, cc->bs);
 	if (!clone)
-		return NULL;
+		goto return_clone;
 
 	clone_init(io, clone);
-	*out_of_pages = 0;
+
+	remaining_size = size;
 
 	for (i = 0; i < nr_iovecs; i++) {
 		page = mempool_alloc(cc->page_pool, gfp_mask);
 		if (!page) {
-			*out_of_pages = 1;
-			break;
+			crypt_free_buffer_pages(cc, clone);
+			bio_put(clone);
+			gfp_mask |= __GFP_WAIT;
+			goto retry;
 		}
 
-		/*
-		 * If additional pages cannot be allocated without waiting,
-		 * return a partially-allocated bio.  The caller will then try
-		 * to allocate more bios while submitting this partial bio.
-		 */
-		gfp_mask = (gfp_mask | __GFP_NOWARN) & ~__GFP_WAIT;
+		len = (remaining_size > PAGE_SIZE) ? PAGE_SIZE : remaining_size;
 
-		len = (size > PAGE_SIZE) ? PAGE_SIZE : size;
+		bvec = &clone->bi_io_vec[clone->bi_vcnt++];
+		bvec->bv_page = page;
+		bvec->bv_len = len;
+		bvec->bv_offset = 0;
 
-		if (!bio_add_page(clone, page, len, 0)) {
-			mempool_free(page, cc->page_pool);
-			break;
-		}
+		clone->bi_iter.bi_size += len;
 
-		size -= len;
+		remaining_size -= len;
 	}
 
-	if (!clone->bi_iter.bi_size) {
-		bio_put(clone);
-		return NULL;
-	}
+return_clone:
+	if (unlikely(gfp_mask & __GFP_WAIT))
+		mutex_unlock(&cc->bio_alloc_lock);
 
 	return clone;
 }
@@ -1020,7 +1038,6 @@ static void crypt_io_init(struct dm_crypt_io *io, struct crypt_config *cc,
 	io->base_bio = bio;
 	io->sector = sector;
 	io->error = 0;
-	io->base_io = NULL;
 	io->ctx.req = NULL;
 	atomic_set(&io->io_pending, 0);
 }
@@ -1033,13 +1050,11 @@ static void crypt_inc_pending(struct dm_crypt_io *io)
 /*
  * One of the bios was finished. Check for completion of
  * the whole request and correctly clean up the buffer.
- * If base_io is set, wait for the last fragment to complete.
  */
 static void crypt_dec_pending(struct dm_crypt_io *io)
 {
 	struct crypt_config *cc = io->cc;
 	struct bio *base_bio = io->base_bio;
-	struct dm_crypt_io *base_io = io->base_io;
 	int error = io->error;
 
 	if (!atomic_dec_and_test(&io->io_pending))
@@ -1047,16 +1062,8 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 
 	if (io->ctx.req)
 		crypt_free_req(cc, io->ctx.req, base_bio);
-	if (io != dm_per_bio_data(base_bio, cc->per_bio_data_size))
-		mempool_free(io, cc->io_pool);
-
-	if (likely(!base_io))
-		bio_endio(base_bio, error);
-	else {
-		if (error && !base_io->error)
-			base_io->error = error;
-		crypt_dec_pending(base_io);
-	}
+
+	bio_endio(base_bio, error);
 }
 
 /*
@@ -1117,15 +1124,15 @@ static void clone_init(struct dm_crypt_io *io, struct bio *clone)
 static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
 {
 	struct crypt_config *cc = io->cc;
-	struct bio *base_bio = io->base_bio;
 	struct bio *clone;
 
 	/*
-	 * The block layer might modify the bvec array, so always
-	 * copy the required bvecs because we need the original
-	 * one in order to decrypt the whole bio data *afterwards*.
+	 * We need the original biovec array in order to decrypt
+	 * the whole bio data *afterwards* -- thanks to immutable
+	 * biovecs we don't need to worry about the block layer
+	 * modifying the biovec array; so leverage bio_clone_fast().
 	 */
-	clone = bio_clone_bioset(base_bio, gfp, cc->bs);
+	clone = bio_clone_fast(io->base_bio, gfp, cc->bs);
 	if (!clone)
 		return 1;
 
@@ -1138,37 +1145,97 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
 	return 0;
 }
 
+static void kcryptd_io_read_work(struct work_struct *work)
+{
+	struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
+
+	crypt_inc_pending(io);
+	if (kcryptd_io_read(io, GFP_NOIO))
+		io->error = -ENOMEM;
+	crypt_dec_pending(io);
+}
+
+static void kcryptd_queue_read(struct dm_crypt_io *io)
+{
+	struct crypt_config *cc = io->cc;
+
+	INIT_WORK(&io->work, kcryptd_io_read_work);
+	queue_work(cc->io_queue, &io->work);
+}
+
 static void kcryptd_io_write(struct dm_crypt_io *io)
 {
 	struct bio *clone = io->ctx.bio_out;
+
 	generic_make_request(clone);
 }
 
-static void kcryptd_io(struct work_struct *work)
+#define crypt_io_from_node(node) rb_entry((node), struct dm_crypt_io, rb_node)
+
+static int dmcrypt_write(void *data)
 {
-	struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
+	struct crypt_config *cc = data;
+	struct dm_crypt_io *io;
 
-	if (bio_data_dir(io->base_bio) == READ) {
-		crypt_inc_pending(io);
-		if (kcryptd_io_read(io, GFP_NOIO))
-			io->error = -ENOMEM;
-		crypt_dec_pending(io);
-	} else
-		kcryptd_io_write(io);
-}
+	while (1) {
+		struct rb_root write_tree;
+		struct blk_plug plug;
 
-static void kcryptd_queue_io(struct dm_crypt_io *io)
-{
-	struct crypt_config *cc = io->cc;
+		DECLARE_WAITQUEUE(wait, current);
 
-	INIT_WORK(&io->work, kcryptd_io);
-	queue_work(cc->io_queue, &io->work);
+		spin_lock_irq(&cc->write_thread_wait.lock);
+continue_locked:
+
+		if (!RB_EMPTY_ROOT(&cc->write_tree))
+			goto pop_from_list;
+
+		__set_current_state(TASK_INTERRUPTIBLE);
+		__add_wait_queue(&cc->write_thread_wait, &wait);
+
+		spin_unlock_irq(&cc->write_thread_wait.lock);
+
+		if (unlikely(kthread_should_stop())) {
+			set_task_state(current, TASK_RUNNING);
+			remove_wait_queue(&cc->write_thread_wait, &wait);
+			break;
+		}
+
+		schedule();
+
+		set_task_state(current, TASK_RUNNING);
+		spin_lock_irq(&cc->write_thread_wait.lock);
+		__remove_wait_queue(&cc->write_thread_wait, &wait);
+		goto continue_locked;
+
+pop_from_list:
+		write_tree = cc->write_tree;
+		cc->write_tree = RB_ROOT;
+		spin_unlock_irq(&cc->write_thread_wait.lock);
+
+		BUG_ON(rb_parent(write_tree.rb_node));
+
+		/*
+		 * Note: we cannot walk the tree here with rb_next because
+		 * the structures may be freed when kcryptd_io_write is called.
+		 */
+		blk_start_plug(&plug);
+		do {
+			io = crypt_io_from_node(rb_first(&write_tree));
+			rb_erase(&io->rb_node, &write_tree);
+			kcryptd_io_write(io);
+		} while (!RB_EMPTY_ROOT(&write_tree));
+		blk_finish_plug(&plug);
+	}
+	return 0;
 }
 
 static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async)
 {
 	struct bio *clone = io->ctx.bio_out;
 	struct crypt_config *cc = io->cc;
+	unsigned long flags;
+	sector_t sector;
+	struct rb_node **rbp, *parent;
 
 	if (unlikely(io->error < 0)) {
 		crypt_free_buffer_pages(cc, clone);
@@ -1182,20 +1249,34 @@ static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async)
 
 	clone->bi_iter.bi_sector = cc->start + io->sector;
 
-	if (async)
-		kcryptd_queue_io(io);
-	else
+	if (likely(!async) && test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags)) {
 		generic_make_request(clone);
+		return;
+	}
+
+	spin_lock_irqsave(&cc->write_thread_wait.lock, flags);
+	rbp = &cc->write_tree.rb_node;
+	parent = NULL;
+	sector = io->sector;
+	while (*rbp) {
+		parent = *rbp;
+		if (sector < crypt_io_from_node(parent)->sector)
+			rbp = &(*rbp)->rb_left;
+		else
+			rbp = &(*rbp)->rb_right;
+	}
+	rb_link_node(&io->rb_node, parent, rbp);
+	rb_insert_color(&io->rb_node, &cc->write_tree);
+
+	wake_up_locked(&cc->write_thread_wait);
+	spin_unlock_irqrestore(&cc->write_thread_wait.lock, flags);
 }
 
 static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 {
 	struct crypt_config *cc = io->cc;
 	struct bio *clone;
-	struct dm_crypt_io *new_io;
 	int crypt_finished;
-	unsigned out_of_pages = 0;
-	unsigned remaining = io->base_bio->bi_iter.bi_size;
 	sector_t sector = io->sector;
 	int r;
 
@@ -1205,80 +1286,30 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 	crypt_inc_pending(io);
 	crypt_convert_init(cc, &io->ctx, NULL, io->base_bio, sector);
 
-	/*
-	 * The allocated buffers can be smaller than the whole bio,
-	 * so repeat the whole process until all the data can be handled.
-	 */
-	while (remaining) {
-		clone = crypt_alloc_buffer(io, remaining, &out_of_pages);
-		if (unlikely(!clone)) {
-			io->error = -ENOMEM;
-			break;
-		}
-
-		io->ctx.bio_out = clone;
-		io->ctx.iter_out = clone->bi_iter;
-
-		remaining -= clone->bi_iter.bi_size;
-		sector += bio_sectors(clone);
-
-		crypt_inc_pending(io);
-
-		r = crypt_convert(cc, &io->ctx);
-		if (r < 0)
-			io->error = -EIO;
-
-		crypt_finished = atomic_dec_and_test(&io->ctx.cc_pending);
-
-		/* Encryption was already finished, submit io now */
-		if (crypt_finished) {
-			kcryptd_crypt_write_io_submit(io, 0);
+	clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size);
+	if (unlikely(!clone)) {
+		io->error = -EIO;
+		goto dec;
+	}
 
-			/*
-			 * If there was an error, do not try next fragments.
-			 * For async, error is processed in async handler.
-			 */
-			if (unlikely(r < 0))
-				break;
+	io->ctx.bio_out = clone;
+	io->ctx.iter_out = clone->bi_iter;
 
-			io->sector = sector;
-		}
+	sector += bio_sectors(clone);
 
-		/*
-		 * Out of memory -> run queues
-		 * But don't wait if split was due to the io size restriction
-		 */
-		if (unlikely(out_of_pages))
-			congestion_wait(BLK_RW_ASYNC, HZ/100);
-
-		/*
-		 * With async crypto it is unsafe to share the crypto context
-		 * between fragments, so switch to a new dm_crypt_io structure.
-		 */
-		if (unlikely(!crypt_finished && remaining)) {
-			new_io = mempool_alloc(cc->io_pool, GFP_NOIO);
-			crypt_io_init(new_io, io->cc, io->base_bio, sector);
-			crypt_inc_pending(new_io);
-			crypt_convert_init(cc, &new_io->ctx, NULL,
-					   io->base_bio, sector);
-			new_io->ctx.iter_in = io->ctx.iter_in;
-
-			/*
-			 * Fragments after the first use the base_io
-			 * pending count.
-			 */
-			if (!io->base_io)
-				new_io->base_io = io;
-			else {
-				new_io->base_io = io->base_io;
-				crypt_inc_pending(io->base_io);
-				crypt_dec_pending(io);
-			}
+	crypt_inc_pending(io);
+	r = crypt_convert(cc, &io->ctx);
+	if (r)
+		io->error = -EIO;
+	crypt_finished = atomic_dec_and_test(&io->ctx.cc_pending);
 
-			io = new_io;
-		}
+	/* Encryption was already finished, submit io now */
+	if (crypt_finished) {
+		kcryptd_crypt_write_io_submit(io, 0);
+		io->sector = sector;
 	}
 
+dec:
 	crypt_dec_pending(io);
 }
 
@@ -1481,6 +1512,9 @@ static void crypt_dtr(struct dm_target *ti)
 	if (!cc)
 		return;
 
+	if (cc->write_thread)
+		kthread_stop(cc->write_thread);
+
 	if (cc->io_queue)
 		destroy_workqueue(cc->io_queue);
 	if (cc->crypt_queue)
@@ -1495,8 +1529,6 @@ static void crypt_dtr(struct dm_target *ti)
 		mempool_destroy(cc->page_pool);
 	if (cc->req_pool)
 		mempool_destroy(cc->req_pool);
-	if (cc->io_pool)
-		mempool_destroy(cc->io_pool);
 
 	if (cc->iv_gen_ops && cc->iv_gen_ops->dtr)
 		cc->iv_gen_ops->dtr(cc);
@@ -1688,7 +1720,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	char dummy;
 
 	static struct dm_arg _args[] = {
-		{0, 1, "Invalid number of feature args"},
+		{0, 3, "Invalid number of feature args"},
 	};
 
 	if (argc < 5) {
@@ -1710,13 +1742,6 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	if (ret < 0)
 		goto bad;
 
-	ret = -ENOMEM;
-	cc->io_pool = mempool_create_slab_pool(MIN_IOS, _crypt_io_pool);
-	if (!cc->io_pool) {
-		ti->error = "Cannot allocate crypt io mempool";
-		goto bad;
-	}
-
 	cc->dmreq_start = sizeof(struct ablkcipher_request);
 	cc->dmreq_start += crypto_ablkcipher_reqsize(any_tfm(cc));
 	cc->dmreq_start = ALIGN(cc->dmreq_start, __alignof__(struct dm_crypt_request));
@@ -1734,6 +1759,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		iv_size_padding = crypto_ablkcipher_alignmask(any_tfm(cc));
 	}
 
+	ret = -ENOMEM;
 	cc->req_pool = mempool_create_kmalloc_pool(MIN_IOS, cc->dmreq_start +
 			sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size);
 	if (!cc->req_pool) {
@@ -1746,7 +1772,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		      sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size,
 		      ARCH_KMALLOC_MINALIGN);
 
-	cc->page_pool = mempool_create_page_pool(MIN_POOL_PAGES, 0);
+	cc->page_pool = mempool_create_page_pool(BIO_MAX_PAGES, 0);
 	if (!cc->page_pool) {
 		ti->error = "Cannot allocate page mempool";
 		goto bad;
@@ -1758,6 +1784,8 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad;
 	}
 
+	mutex_init(&cc->bio_alloc_lock);
+
 	ret = -EINVAL;
 	if (sscanf(argv[2], "%llu%c", &tmpll, &dummy) != 1) {
 		ti->error = "Invalid iv_offset sector";
@@ -1788,15 +1816,27 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		if (ret)
 			goto bad;
 
-		opt_string = dm_shift_arg(&as);
+		ret = -EINVAL;
+		while (opt_params--) {
+			opt_string = dm_shift_arg(&as);
+			if (!opt_string) {
+				ti->error = "Not enough feature arguments";
+				goto bad;
+			}
 
-		if (opt_params == 1 && opt_string &&
-		    !strcasecmp(opt_string, "allow_discards"))
-			ti->num_discard_bios = 1;
-		else if (opt_params) {
-			ret = -EINVAL;
-			ti->error = "Invalid feature arguments";
-			goto bad;
+			if (!strcasecmp(opt_string, "allow_discards"))
+				ti->num_discard_bios = 1;
+
+			else if (!strcasecmp(opt_string, "same_cpu_crypt"))
+				set_bit(DM_CRYPT_SAME_CPU, &cc->flags);
+
+			else if (!strcasecmp(opt_string, "submit_from_crypt_cpus"))
+				set_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags);
+
+			else {
+				ti->error = "Invalid feature arguments";
+				goto bad;
+			}
 		}
 	}
 
@@ -1807,13 +1847,28 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad;
 	}
 
-	cc->crypt_queue = alloc_workqueue("kcryptd",
-					  WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 1);
+	if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags))
+		cc->crypt_queue = alloc_workqueue("kcryptd", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 1);
+	else
+		cc->crypt_queue = alloc_workqueue("kcryptd", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND,
+						  num_online_cpus());
 	if (!cc->crypt_queue) {
 		ti->error = "Couldn't create kcryptd queue";
 		goto bad;
 	}
 
+	init_waitqueue_head(&cc->write_thread_wait);
+	cc->write_tree = RB_ROOT;
+
+	cc->write_thread = kthread_create(dmcrypt_write, cc, "dmcrypt_write");
+	if (IS_ERR(cc->write_thread)) {
+		ret = PTR_ERR(cc->write_thread);
+		cc->write_thread = NULL;
+		ti->error = "Couldn't spawn write thread";
+		goto bad;
+	}
+	wake_up_process(cc->write_thread);
+
 	ti->num_flush_bios = 1;
 	ti->discard_zeroes_data_unsupported = true;
 
@@ -1848,7 +1903,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
 
 	if (bio_data_dir(io->base_bio) == READ) {
 		if (kcryptd_io_read(io, GFP_NOWAIT))
-			kcryptd_queue_io(io);
+			kcryptd_queue_read(io);
 	} else
 		kcryptd_queue_crypt(io);
 
@@ -1860,6 +1915,7 @@ static void crypt_status(struct dm_target *ti, status_type_t type,
 {
 	struct crypt_config *cc = ti->private;
 	unsigned i, sz = 0;
+	int num_feature_args = 0;
 
 	switch (type) {
 	case STATUSTYPE_INFO:
@@ -1878,8 +1934,18 @@ static void crypt_status(struct dm_target *ti, status_type_t type,
 		DMEMIT(" %llu %s %llu", (unsigned long long)cc->iv_offset,
 				cc->dev->name, (unsigned long long)cc->start);
 
-		if (ti->num_discard_bios)
-			DMEMIT(" 1 allow_discards");
+		num_feature_args += !!ti->num_discard_bios;
+		num_feature_args += test_bit(DM_CRYPT_SAME_CPU, &cc->flags);
+		num_feature_args += test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags);
+		if (num_feature_args) {
+			DMEMIT(" %d", num_feature_args);
+			if (ti->num_discard_bios)
+				DMEMIT(" allow_discards");
+			if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags))
+				DMEMIT(" same_cpu_crypt");
+			if (test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags))
+				DMEMIT(" submit_from_crypt_cpus");
+		}
 
 		break;
 	}
@@ -1976,7 +2042,7 @@ static int crypt_iterate_devices(struct dm_target *ti,
 
 static struct target_type crypt_target = {
 	.name   = "crypt",
-	.version = {1, 13, 0},
+	.version = {1, 14, 0},
 	.module = THIS_MODULE,
 	.ctr    = crypt_ctr,
 	.dtr    = crypt_dtr,
@@ -1994,15 +2060,9 @@ static int __init dm_crypt_init(void)
 {
 	int r;
 
-	_crypt_io_pool = KMEM_CACHE(dm_crypt_io, 0);
-	if (!_crypt_io_pool)
-		return -ENOMEM;
-
 	r = dm_register_target(&crypt_target);
-	if (r < 0) {
+	if (r < 0)
 		DMERR("register failed %d", r);
-		kmem_cache_destroy(_crypt_io_pool);
-	}
 
 	return r;
 }
@@ -2010,7 +2070,6 @@ static int __init dm_crypt_init(void)
 static void __exit dm_crypt_exit(void)
 {
 	dm_unregister_target(&crypt_target);
-	kmem_cache_destroy(_crypt_io_pool);
 }
 
 module_init(dm_crypt_init);
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index c09359db3a9..74adcd2c967 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -289,6 +289,19 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 	struct request_queue *q = bdev_get_queue(where->bdev);
 	unsigned short logical_block_size = queue_logical_block_size(q);
 	sector_t num_sectors;
+	unsigned int uninitialized_var(special_cmd_max_sectors);
+
+	/*
+	 * Reject unsupported discard and write same requests.
+	 */
+	if (rw & REQ_DISCARD)
+		special_cmd_max_sectors = q->limits.max_discard_sectors;
+	else if (rw & REQ_WRITE_SAME)
+		special_cmd_max_sectors = q->limits.max_write_same_sectors;
+	if ((rw & (REQ_DISCARD | REQ_WRITE_SAME)) && special_cmd_max_sectors == 0) {
+		dec_count(io, region, -EOPNOTSUPP);
+		return;
+	}
 
 	/*
 	 * where->count may be zero if rw holds a flush and we need to
@@ -311,7 +324,7 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 		store_io_and_region_in_bio(bio, io, region);
 
 		if (rw & REQ_DISCARD) {
-			num_sectors = min_t(sector_t, q->limits.max_discard_sectors, remaining);
+			num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining);
 			bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT;
 			remaining -= num_sectors;
 		} else if (rw & REQ_WRITE_SAME) {
@@ -320,7 +333,7 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 			 */
 			dp->get_page(dp, &page, &len, &offset);
 			bio_add_page(bio, page, logical_block_size, offset);
-			num_sectors = min_t(sector_t, q->limits.max_write_same_sectors, remaining);
+			num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining);
 			bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT;
 
 			offset = 0;
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 7dfdb5c746d..089d62751f7 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -604,6 +604,15 @@ static void write_callback(unsigned long error, void *context)
 		return;
 	}
 
+	/*
+	 * If the bio is discard, return an error, but do not
+	 * degrade the array.
+	 */
+	if (bio->bi_rw & REQ_DISCARD) {
+		bio_endio(bio, -EOPNOTSUPP);
+		return;
+	}
+
 	for (i = 0; i < ms->nr_mirrors; i++)
 		if (test_bit(i, &error))
 			fail_mirror(ms->mirror + i, DM_RAID1_WRITE_ERROR);
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 864b03f4772..33de9f7a718 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -20,6 +20,8 @@
 #include <linux/log2.h>
 #include <linux/dm-kcopyd.h>
 
+#include "dm.h"
+
 #include "dm-exception-store.h"
 
 #define DM_MSG_PREFIX "snapshots"
@@ -291,12 +293,23 @@ struct origin {
 };
 
 /*
+ * This structure is allocated for each origin target
+ */
+struct dm_origin {
+	struct dm_dev *dev;
+	struct dm_target *ti;
+	unsigned split_boundary;
+	struct list_head hash_list;
+};
+
+/*
  * Size of the hash table for origin volumes. If we make this
  * the size of the minors list then it should be nearly perfect
  */
 #define ORIGIN_HASH_SIZE 256
 #define ORIGIN_MASK      0xFF
 static struct list_head *_origins;
+static struct list_head *_dm_origins;
 static struct rw_semaphore _origins_lock;
 
 static DECLARE_WAIT_QUEUE_HEAD(_pending_exceptions_done);
@@ -310,12 +323,22 @@ static int init_origin_hash(void)
 	_origins = kmalloc(ORIGIN_HASH_SIZE * sizeof(struct list_head),
 			   GFP_KERNEL);
 	if (!_origins) {
-		DMERR("unable to allocate memory");
+		DMERR("unable to allocate memory for _origins");
 		return -ENOMEM;
 	}
-
 	for (i = 0; i < ORIGIN_HASH_SIZE; i++)
 		INIT_LIST_HEAD(_origins + i);
+
+	_dm_origins = kmalloc(ORIGIN_HASH_SIZE * sizeof(struct list_head),
+			      GFP_KERNEL);
+	if (!_dm_origins) {
+		DMERR("unable to allocate memory for _dm_origins");
+		kfree(_origins);
+		return -ENOMEM;
+	}
+	for (i = 0; i < ORIGIN_HASH_SIZE; i++)
+		INIT_LIST_HEAD(_dm_origins + i);
+
 	init_rwsem(&_origins_lock);
 
 	return 0;
@@ -324,6 +347,7 @@ static int init_origin_hash(void)
 static void exit_origin_hash(void)
 {
 	kfree(_origins);
+	kfree(_dm_origins);
 }
 
 static unsigned origin_hash(struct block_device *bdev)
@@ -350,6 +374,30 @@ static void __insert_origin(struct origin *o)
 	list_add_tail(&o->hash_list, sl);
 }
 
+static struct dm_origin *__lookup_dm_origin(struct block_device *origin)
+{
+	struct list_head *ol;
+	struct dm_origin *o;
+
+	ol = &_dm_origins[origin_hash(origin)];
+	list_for_each_entry (o, ol, hash_list)
+		if (bdev_equal(o->dev->bdev, origin))
+			return o;
+
+	return NULL;
+}
+
+static void __insert_dm_origin(struct dm_origin *o)
+{
+	struct list_head *sl = &_dm_origins[origin_hash(o->dev->bdev)];
+	list_add_tail(&o->hash_list, sl);
+}
+
+static void __remove_dm_origin(struct dm_origin *o)
+{
+	list_del(&o->hash_list);
+}
+
 /*
  * _origins_lock must be held when calling this function.
  * Returns number of snapshots registered using the supplied cow device, plus:
@@ -1432,8 +1480,6 @@ out:
 		full_bio->bi_private = pe->full_bio_private;
 		atomic_inc(&full_bio->bi_remaining);
 	}
-	free_pending_exception(pe);
-
 	increment_pending_exceptions_done_count();
 
 	up_write(&s->lock);
@@ -1450,6 +1496,8 @@ out:
 	}
 
 	retry_origin_bios(s, origin_bios);
+
+	free_pending_exception(pe);
 }
 
 static void commit_callback(void *context, int success)
@@ -1840,9 +1888,40 @@ static int snapshot_preresume(struct dm_target *ti)
 static void snapshot_resume(struct dm_target *ti)
 {
 	struct dm_snapshot *s = ti->private;
-	struct dm_snapshot *snap_src = NULL, *snap_dest = NULL;
+	struct dm_snapshot *snap_src = NULL, *snap_dest = NULL, *snap_merging = NULL;
+	struct dm_origin *o;
+	struct mapped_device *origin_md = NULL;
+	bool must_restart_merging = false;
+
+	down_read(&_origins_lock);
+
+	o = __lookup_dm_origin(s->origin->bdev);
+	if (o)
+		origin_md = dm_table_get_md(o->ti->table);
+	if (!origin_md) {
+		(void) __find_snapshots_sharing_cow(s, NULL, NULL, &snap_merging);
+		if (snap_merging)
+			origin_md = dm_table_get_md(snap_merging->ti->table);
+	}
+	if (origin_md == dm_table_get_md(ti->table))
+		origin_md = NULL;
+	if (origin_md) {
+		if (dm_hold(origin_md))
+			origin_md = NULL;
+	}
+
+	up_read(&_origins_lock);
+
+	if (origin_md) {
+		dm_internal_suspend(origin_md);
+		if (snap_merging && test_bit(RUNNING_MERGE, &snap_merging->state_bits)) {
+			must_restart_merging = true;
+			stop_merge(snap_merging);
+		}
+	}
 
 	down_read(&_origins_lock);
+
 	(void) __find_snapshots_sharing_cow(s, &snap_src, &snap_dest, NULL);
 	if (snap_src && snap_dest) {
 		down_write(&snap_src->lock);
@@ -1851,8 +1930,16 @@ static void snapshot_resume(struct dm_target *ti)
 		up_write(&snap_dest->lock);
 		up_write(&snap_src->lock);
 	}
+
 	up_read(&_origins_lock);
 
+	if (origin_md) {
+		if (must_restart_merging)
+			start_merge(snap_merging);
+		dm_internal_resume(origin_md);
+		dm_put(origin_md);
+	}
+
 	/* Now we have correct chunk size, reregister */
 	reregister_snapshot(s);
 
@@ -2133,11 +2220,6 @@ static int origin_write_extent(struct dm_snapshot *merging_snap,
  * Origin: maps a linear range of a device, with hooks for snapshotting.
  */
 
-struct dm_origin {
-	struct dm_dev *dev;
-	unsigned split_boundary;
-};
-
 /*
  * Construct an origin mapping: <dev_path>
  * The context for an origin is merely a 'struct dm_dev *'
@@ -2166,6 +2248,7 @@ static int origin_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad_open;
 	}
 
+	o->ti = ti;
 	ti->private = o;
 	ti->num_flush_bios = 1;
 
@@ -2180,6 +2263,7 @@ bad_alloc:
 static void origin_dtr(struct dm_target *ti)
 {
 	struct dm_origin *o = ti->private;
+
 	dm_put_device(ti, o->dev);
 	kfree(o);
 }
@@ -2216,6 +2300,19 @@ static void origin_resume(struct dm_target *ti)
 	struct dm_origin *o = ti->private;
 
 	o->split_boundary = get_origin_minimum_chunksize(o->dev->bdev);
+
+	down_write(&_origins_lock);
+	__insert_dm_origin(o);
+	up_write(&_origins_lock);
+}
+
+static void origin_postsuspend(struct dm_target *ti)
+{
+	struct dm_origin *o = ti->private;
+
+	down_write(&_origins_lock);
+	__remove_dm_origin(o);
+	up_write(&_origins_lock);
 }
 
 static void origin_status(struct dm_target *ti, status_type_t type,
@@ -2258,12 +2355,13 @@ static int origin_iterate_devices(struct dm_target *ti,
 
 static struct target_type origin_target = {
 	.name    = "snapshot-origin",
-	.version = {1, 8, 1},
+	.version = {1, 9, 0},
 	.module  = THIS_MODULE,
 	.ctr     = origin_ctr,
 	.dtr     = origin_dtr,
 	.map     = origin_map,
 	.resume  = origin_resume,
+	.postsuspend = origin_postsuspend,
 	.status  = origin_status,
 	.merge	 = origin_merge,
 	.iterate_devices = origin_iterate_devices,
@@ -2271,7 +2369,7 @@ static struct target_type origin_target = {
 
 static struct target_type snapshot_target = {
 	.name    = "snapshot",
-	.version = {1, 12, 0},
+	.version = {1, 13, 0},
 	.module  = THIS_MODULE,
 	.ctr     = snapshot_ctr,
 	.dtr     = snapshot_dtr,
@@ -2285,7 +2383,7 @@ static struct target_type snapshot_target = {
 
 static struct target_type merge_target = {
 	.name    = dm_snapshot_merge_target_name,
-	.version = {1, 2, 0},
+	.version = {1, 3, 0},
 	.module  = THIS_MODULE,
 	.ctr     = snapshot_ctr,
 	.dtr     = snapshot_dtr,
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index 87f86c77b09..6f2a4ce413f 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -795,6 +795,8 @@ static int message_stats_create(struct mapped_device *md,
 		return -EINVAL;
 
 	if (sscanf(argv[2], "/%u%c", &divisor, &dummy) == 1) {
+		if (!divisor)
+			return -EINVAL;
 		step = end - start;
 		if (do_div(step, divisor))
 			step++;
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 0f86d802b53..0801e35b994 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -990,6 +990,24 @@ static void schedule_external_copy(struct thin_c *tc, dm_block_t virt_block,
 		schedule_zero(tc, virt_block, data_dest, cell, bio);
 }
 
+static void set_pool_mode(struct pool *pool, enum pool_mode new_mode);
+
+static void check_for_space(struct pool *pool)
+{
+	int r;
+	dm_block_t nr_free;
+
+	if (get_pool_mode(pool) != PM_OUT_OF_DATA_SPACE)
+		return;
+
+	r = dm_pool_get_free_block_count(pool->pmd, &nr_free);
+	if (r)
+		return;
+
+	if (nr_free)
+		set_pool_mode(pool, PM_WRITE);
+}
+
 /*
  * A non-zero return indicates read_only or fail_io mode.
  * Many callers don't care about the return value.
@@ -1004,6 +1022,8 @@ static int commit(struct pool *pool)
 	r = dm_pool_commit_metadata(pool->pmd);
 	if (r)
 		metadata_operation_failed(pool, "dm_pool_commit_metadata", r);
+	else
+		check_for_space(pool);
 
 	return r;
 }
@@ -1022,8 +1042,6 @@ static void check_low_water_mark(struct pool *pool, dm_block_t free_blocks)
 	}
 }
 
-static void set_pool_mode(struct pool *pool, enum pool_mode new_mode);
-
 static int alloc_data_block(struct thin_c *tc, dm_block_t *result)
 {
 	int r;
@@ -1824,7 +1842,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 		pool->process_bio = process_bio_read_only;
 		pool->process_discard = process_discard;
 		pool->process_prepared_mapping = process_prepared_mapping;
-		pool->process_prepared_discard = process_prepared_discard_passdown;
+		pool->process_prepared_discard = process_prepared_discard;
 
 		if (!pool->pf.error_if_no_space && no_space_timeout)
 			queue_delayed_work(pool->wq, &pool->no_space_timeout, no_space_timeout);
@@ -1985,17 +2003,6 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
 		return DM_MAPIO_REMAPPED;
 
 	case -ENODATA:
-		if (get_pool_mode(tc->pool) == PM_READ_ONLY) {
-			/*
-			 * This block isn't provisioned, and we have no way
-			 * of doing so.
-			 */
-			handle_unserviceable_bio(tc->pool, bio);
-			cell_defer_no_holder_no_free(tc, &cell1);
-			return DM_MAPIO_SUBMITTED;
-		}
-		/* fall through */
-
 	case -EWOULDBLOCK:
 		/*
 		 * In future, the failed dm_thin_find_block above could
@@ -2960,6 +2967,12 @@ static int pool_message(struct dm_target *ti, unsigned argc, char **argv)
 	struct pool_c *pt = ti->private;
 	struct pool *pool = pt->pool;
 
+	if (get_pool_mode(pool) >= PM_READ_ONLY) {
+		DMERR("%s: unable to service pool target messages in READ_ONLY or FAIL mode",
+		      dm_device_name(pool->pool_md));
+		return -EINVAL;
+	}
+
 	if (!strcasecmp(argv[0], "create_thin"))
 		r = process_create_thin_mesg(argc, argv, pool);
 
@@ -3248,14 +3261,14 @@ static void thin_dtr(struct dm_target *ti)
 	struct thin_c *tc = ti->private;
 	unsigned long flags;
 
-	thin_put(tc);
-	wait_for_completion(&tc->can_destroy);
-
 	spin_lock_irqsave(&tc->pool->lock, flags);
 	list_del_rcu(&tc->list);
 	spin_unlock_irqrestore(&tc->pool->lock, flags);
 	synchronize_rcu();
 
+	thin_put(tc);
+	wait_for_completion(&tc->can_destroy);
+
 	mutex_lock(&dm_thin_pool_table.mutex);
 
 	__pool_dec(tc->pool);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 58f3927fd7c..042114fbd20 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -899,7 +899,7 @@ static void disable_write_same(struct mapped_device *md)
 
 static void clone_endio(struct bio *bio, int error)
 {
-	int r = 0;
+	int r = error;
 	struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
 	struct dm_io *io = tio->io;
 	struct mapped_device *md = tio->io->md;
@@ -2462,7 +2462,7 @@ int dm_setup_md_queue(struct mapped_device *md)
 	return 0;
 }
 
-static struct mapped_device *dm_find_md(dev_t dev)
+struct mapped_device *dm_get_md(dev_t dev)
 {
 	struct mapped_device *md;
 	unsigned minor = MINOR(dev);
@@ -2473,12 +2473,15 @@ static struct mapped_device *dm_find_md(dev_t dev)
 	spin_lock(&_minor_lock);
 
 	md = idr_find(&_minor_idr, minor);
-	if (md && (md == MINOR_ALLOCED ||
-		   (MINOR(disk_devt(dm_disk(md))) != minor) ||
-		   dm_deleting_md(md) ||
-		   test_bit(DMF_FREEING, &md->flags))) {
-		md = NULL;
-		goto out;
+	if (md) {
+		if ((md == MINOR_ALLOCED ||
+		     (MINOR(disk_devt(dm_disk(md))) != minor) ||
+		     dm_deleting_md(md) ||
+		     test_bit(DMF_FREEING, &md->flags))) {
+			md = NULL;
+			goto out;
+		}
+		dm_get(md);
 	}
 
 out:
@@ -2486,16 +2489,6 @@ out:
 
 	return md;
 }
-
-struct mapped_device *dm_get_md(dev_t dev)
-{
-	struct mapped_device *md = dm_find_md(dev);
-
-	if (md)
-		dm_get(md);
-
-	return md;
-}
 EXPORT_SYMBOL_GPL(dm_get_md);
 
 void *dm_get_mdptr(struct mapped_device *md)
@@ -2514,6 +2507,19 @@ void dm_get(struct mapped_device *md)
 	BUG_ON(test_bit(DMF_FREEING, &md->flags));
 }
 
+int dm_hold(struct mapped_device *md)
+{
+	spin_lock(&_minor_lock);
+	if (test_bit(DMF_FREEING, &md->flags)) {
+		spin_unlock(&_minor_lock);
+		return -EBUSY;
+	}
+	dm_get(md);
+	spin_unlock(&_minor_lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dm_hold);
+
 const char *dm_device_name(struct mapped_device *md)
 {
 	return md->name;
@@ -2533,10 +2539,16 @@ static void __dm_destroy(struct mapped_device *md, bool wait)
 	set_bit(DMF_FREEING, &md->flags);
 	spin_unlock(&_minor_lock);
 
+	/*
+	 * Take suspend_lock so that presuspend and postsuspend methods
+	 * do not race with internal suspend.
+	 */
+	mutex_lock(&md->suspend_lock);
 	if (!dm_suspended_md(md)) {
 		dm_table_presuspend_targets(map);
 		dm_table_postsuspend_targets(map);
 	}
+	mutex_unlock(&md->suspend_lock);
 
 	/* dm_put_live_table must be before msleep, otherwise deadlock is possible */
 	dm_put_live_table(md, srcu_idx);
@@ -2888,6 +2900,7 @@ void dm_internal_suspend(struct mapped_device *md)
 	flush_workqueue(md->wq);
 	dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE);
 }
+EXPORT_SYMBOL_GPL(dm_internal_suspend);
 
 void dm_internal_resume(struct mapped_device *md)
 {
@@ -2899,6 +2912,7 @@ void dm_internal_resume(struct mapped_device *md)
 done:
 	mutex_unlock(&md->suspend_lock);
 }
+EXPORT_SYMBOL_GPL(dm_internal_resume);
 
 /*-----------------------------------------------------------------
  * Event notification.
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 9233c71138f..43390353d62 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -6031,7 +6031,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
 	    mddev->ctime         != info->ctime         ||
 	    mddev->level         != info->level         ||
 /*	    mddev->layout        != info->layout        || */
-	    !mddev->persistent	 != info->not_persistent||
+	    mddev->persistent	 != !info->not_persistent ||
 	    mddev->chunk_sectors != info->chunk_size >> 9 ||
 	    /* ignore bottom 8 bits of state, and allow SB_BITMAP_PRESENT to change */
 	    ((state^info->state) & 0xfffffe00)
diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c
index b88757cd0d1..a03178e91a7 100644
--- a/drivers/md/persistent-data/dm-btree-remove.c
+++ b/drivers/md/persistent-data/dm-btree-remove.c
@@ -309,8 +309,8 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent,
 
 		if (s < 0 && nr_center < -s) {
 			/* not enough in central node */
-			shift(left, center, nr_center);
-			s = nr_center - target;
+			shift(left, center, -nr_center);
+			s += nr_center;
 			shift(left, right, s);
 			nr_right += s;
 		} else
@@ -323,7 +323,7 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent,
 		if (s > 0 && nr_center < s) {
 			/* not enough in central node */
 			shift(center, right, nr_center);
-			s = target - nr_center;
+			s -= nr_center;
 			shift(left, right, s);
 			nr_left -= s;
 		} else
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index 200ac12a1d4..fdd3793e22f 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -255,7 +255,7 @@ int dm_btree_del(struct dm_btree_info *info, dm_block_t root)
 	int r;
 	struct del_stack *s;
 
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	s = kmalloc(sizeof(*s), GFP_NOIO);
 	if (!s)
 		return -ENOMEM;
 	s->info = info;
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index 786b689bdfc..199c9ccd1f5 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -204,6 +204,27 @@ static void in(struct sm_metadata *smm)
 	smm->recursion_count++;
 }
 
+static int apply_bops(struct sm_metadata *smm)
+{
+	int r = 0;
+
+	while (!brb_empty(&smm->uncommitted)) {
+		struct block_op bop;
+
+		r = brb_pop(&smm->uncommitted, &bop);
+		if (r) {
+			DMERR("bug in bop ring buffer");
+			break;
+		}
+
+		r = commit_bop(smm, &bop);
+		if (r)
+			break;
+	}
+
+	return r;
+}
+
 static int out(struct sm_metadata *smm)
 {
 	int r = 0;
@@ -216,21 +237,8 @@ static int out(struct sm_metadata *smm)
 		return -ENOMEM;
 	}
 
-	if (smm->recursion_count == 1) {
-		while (!brb_empty(&smm->uncommitted)) {
-			struct block_op bop;
-
-			r = brb_pop(&smm->uncommitted, &bop);
-			if (r) {
-				DMERR("bug in bop ring buffer");
-				break;
-			}
-
-			r = commit_bop(smm, &bop);
-			if (r)
-				break;
-		}
-	}
+	if (smm->recursion_count == 1)
+		apply_bops(smm);
 
 	smm->recursion_count--;
 
@@ -564,7 +572,9 @@ static int sm_bootstrap_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count
 {
 	struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
 
-	return smm->ll.nr_blocks;
+	*count = smm->ll.nr_blocks;
+
+	return 0;
 }
 
 static int sm_bootstrap_get_nr_free(struct dm_space_map *sm, dm_block_t *count)
@@ -700,6 +710,12 @@ static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks)
 		}
 		old_len = smm->begin;
 
+		r = apply_bops(smm);
+		if (r) {
+			DMERR("%s: apply_bops failed", __func__);
+			goto out;
+		}
+
 		r = sm_ll_commit(&smm->ll);
 		if (r)
 			goto out;
@@ -769,6 +785,12 @@ int dm_sm_metadata_create(struct dm_space_map *sm,
 	if (r)
 		return r;
 
+	r = apply_bops(smm);
+	if (r) {
+		DMERR("%s: apply_bops failed", __func__);
+		return r;
+	}
+
 	return sm_metadata_commit(sm);
 }
 
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index ba6b85de96d..b974ff29b55 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -319,7 +319,7 @@ static struct strip_zone *find_zone(struct r0conf *conf,
 
 /*
  * remaps the bio to the target device. we separate two flows.
- * power 2 flow and a general flow for the sake of perfromance
+ * power 2 flow and a general flow for the sake of performance
 */
 static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone,
 				sector_t sector, sector_t *sector_offset)
@@ -530,6 +530,9 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 			 ? (sector & (chunk_sects-1))
 			 : sector_div(sector, chunk_sects));
 
+		/* Restore due to sector_div */
+		sector = bio->bi_iter.bi_sector;
+
 		if (sectors < bio_sectors(bio)) {
 			split = bio_split(bio, sectors, GFP_NOIO, fs_bio_set);
 			bio_chain(split, bio);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 40b35be34f8..2f2f38f4d83 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -560,7 +560,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 		if (test_bit(WriteMostly, &rdev->flags)) {
 			/* Don't balance among write-mostly, just
 			 * use the first as a last resort */
-			if (best_disk < 0) {
+			if (best_dist_disk < 0) {
 				if (is_badblock(rdev, this_sector, sectors,
 						&first_bad, &bad_sectors)) {
 					if (first_bad < this_sector)
@@ -569,7 +569,8 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 					best_good_sectors = first_bad - this_sector;
 				} else
 					best_good_sectors = sectors;
-				best_disk = disk;
+				best_dist_disk = disk;
+				best_pending_disk = disk;
 			}
 			continue;
 		}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 9c66e5997fc..e421016bab7 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1936,7 +1936,8 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 
 	conf->slab_cache = sc;
 	conf->active_name = 1-conf->active_name;
-	conf->pool_size = newsize;
+	if (!err)
+		conf->pool_size = newsize;
 	return err;
 }
 
@@ -2917,8 +2918,11 @@ static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
 	     (sh->raid_conf->level <= 5 && s->failed && fdev[0]->towrite &&
 	      (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) &&
 	      !test_bit(R5_OVERWRITE, &fdev[0]->flags)) ||
-	     (sh->raid_conf->level == 6 && s->failed && s->to_write &&
-	      s->to_write - s->non_overwrite < sh->raid_conf->raid_disks - 2 &&
+	     ((sh->raid_conf->level == 6 ||
+	       sh->sector >= sh->raid_conf->mddev->recovery_cp)
+	      && s->failed && s->to_write &&
+	      (s->to_write - s->non_overwrite <
+	       sh->raid_conf->raid_disks - sh->raid_conf->max_degraded) &&
 	      (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))))) {
 		/* we would like to get this block, possibly by computing it,
 		 * otherwise read it if the backing disk is insync
@@ -3099,7 +3103,8 @@ static void handle_stripe_dirtying(struct r5conf *conf,
 	 * generate correct data from the parity.
 	 */
 	if (conf->max_degraded == 2 ||
-	    (recovery_cp < MaxSector && sh->sector >= recovery_cp)) {
+	    (recovery_cp < MaxSector && sh->sector >= recovery_cp &&
+	     s->failed == 0)) {
 		/* Calculate the real rcw later - for now make it
 		 * look like rcw is cheaper
 		 */
@@ -3192,6 +3197,11 @@ static void handle_stripe_dirtying(struct r5conf *conf,
 					  (unsigned long long)sh->sector,
 					  rcw, qread, test_bit(STRIPE_DELAYED, &sh->state));
 	}
+
+	if (rcw > disks && rmw > disks &&
+	    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+		set_bit(STRIPE_DELAYED, &sh->state);
+
 	/* now if nothing is locked, and if we have enough data,
 	 * we can start a write request
 	 */
diff --git a/drivers/media/dvb-frontends/a8293.h b/drivers/media/dvb-frontends/a8293.h
index b6ef6427cfa..5f0411939ff 100644
--- a/drivers/media/dvb-frontends/a8293.h
+++ b/drivers/media/dvb-frontends/a8293.h
@@ -27,7 +27,7 @@ struct a8293_config {
 	u8 i2c_addr;
 };
 
-#if IS_ENABLED(CONFIG_DVB_A8293)
+#if IS_REACHABLE(CONFIG_DVB_A8293)
 extern struct dvb_frontend *a8293_attach(struct dvb_frontend *fe,
 	struct i2c_adapter *i2c, const struct a8293_config *cfg);
 #else
diff --git a/drivers/media/dvb-frontends/af9013.c b/drivers/media/dvb-frontends/af9013.c
index 8001690d757..ba6c8f6c42a 100644
--- a/drivers/media/dvb-frontends/af9013.c
+++ b/drivers/media/dvb-frontends/af9013.c
@@ -605,6 +605,10 @@ static int af9013_set_frontend(struct dvb_frontend *fe)
 			}
 		}
 
+		/* Return an error if can't find bandwidth or the right clock */
+		if (i == ARRAY_SIZE(coeff_lut))
+			return -EINVAL;
+
 		ret = af9013_wr_regs(state, 0xae00, coeff_lut[i].val,
 			sizeof(coeff_lut[i].val));
 	}
diff --git a/drivers/media/dvb-frontends/af9013.h b/drivers/media/dvb-frontends/af9013.h
index 09273b2cd31..1dcc936e166 100644
--- a/drivers/media/dvb-frontends/af9013.h
+++ b/drivers/media/dvb-frontends/af9013.h
@@ -103,7 +103,7 @@ struct af9013_config {
 	u8 gpio[4];
 };
 
-#if IS_ENABLED(CONFIG_DVB_AF9013)
+#if IS_REACHABLE(CONFIG_DVB_AF9013)
 extern struct dvb_frontend *af9013_attach(const struct af9013_config *config,
 	struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/atbm8830.h b/drivers/media/dvb-frontends/atbm8830.h
index 8e0ac98f8d0..5446d13fdfe 100644
--- a/drivers/media/dvb-frontends/atbm8830.h
+++ b/drivers/media/dvb-frontends/atbm8830.h
@@ -61,7 +61,7 @@ struct atbm8830_config {
 	u8 agc_hold_loop;
 };
 
-#if IS_ENABLED(CONFIG_DVB_ATBM8830)
+#if IS_REACHABLE(CONFIG_DVB_ATBM8830)
 extern struct dvb_frontend *atbm8830_attach(const struct atbm8830_config *config,
 		struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/au8522.h b/drivers/media/dvb-frontends/au8522.h
index 83fe9a61561..5f48bd4fc51 100644
--- a/drivers/media/dvb-frontends/au8522.h
+++ b/drivers/media/dvb-frontends/au8522.h
@@ -61,7 +61,7 @@ struct au8522_config {
 	enum au8522_if_freq qam_if;
 };
 
-#if IS_ENABLED(CONFIG_DVB_AU8522_DTV)
+#if IS_REACHABLE(CONFIG_DVB_AU8522_DTV)
 extern struct dvb_frontend *au8522_attach(const struct au8522_config *config,
 					  struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/bcm3510.h b/drivers/media/dvb-frontends/bcm3510.h
index 5bd56b1623b..ff66492fb94 100644
--- a/drivers/media/dvb-frontends/bcm3510.h
+++ b/drivers/media/dvb-frontends/bcm3510.h
@@ -34,7 +34,7 @@ struct bcm3510_config
 	int (*request_firmware)(struct dvb_frontend* fe, const struct firmware **fw, char* name);
 };
 
-#if IS_ENABLED(CONFIG_DVB_BCM3510)
+#if IS_REACHABLE(CONFIG_DVB_BCM3510)
 extern struct dvb_frontend* bcm3510_attach(const struct bcm3510_config* config,
 					   struct i2c_adapter* i2c);
 #else
diff --git a/drivers/media/dvb-frontends/cx22700.h b/drivers/media/dvb-frontends/cx22700.h
index 382a7b1f361..e0a764868e6 100644
--- a/drivers/media/dvb-frontends/cx22700.h
+++ b/drivers/media/dvb-frontends/cx22700.h
@@ -31,7 +31,7 @@ struct cx22700_config
 	u8 demod_address;
 };
 
-#if IS_ENABLED(CONFIG_DVB_CX22700)
+#if IS_REACHABLE(CONFIG_DVB_CX22700)
 extern struct dvb_frontend* cx22700_attach(const struct cx22700_config* config,
 					   struct i2c_adapter* i2c);
 #else
diff --git a/drivers/media/dvb-frontends/cx22702.h b/drivers/media/dvb-frontends/cx22702.h
index 0b1a6c2f9d5..68b69a7660d 100644
--- a/drivers/media/dvb-frontends/cx22702.h
+++ b/drivers/media/dvb-frontends/cx22702.h
@@ -41,7 +41,7 @@ struct cx22702_config {
 	u8 output_mode;
 };
 
-#if IS_ENABLED(CONFIG_DVB_CX22702)
+#if IS_REACHABLE(CONFIG_DVB_CX22702)
 extern struct dvb_frontend *cx22702_attach(
 	const struct cx22702_config *config,
 	struct i2c_adapter *i2c);
diff --git a/drivers/media/dvb-frontends/cx24110.h b/drivers/media/dvb-frontends/cx24110.h
index 527aff1f272..d5453ed20b2 100644
--- a/drivers/media/dvb-frontends/cx24110.h
+++ b/drivers/media/dvb-frontends/cx24110.h
@@ -46,7 +46,7 @@ static inline int cx24110_pll_write(struct dvb_frontend *fe, u32 val)
 	return 0;
 }
 
-#if IS_ENABLED(CONFIG_DVB_CX24110)
+#if IS_REACHABLE(CONFIG_DVB_CX24110)
 extern struct dvb_frontend* cx24110_attach(const struct cx24110_config* config,
 					   struct i2c_adapter* i2c);
 #else
diff --git a/drivers/media/dvb-frontends/cx24113.h b/drivers/media/dvb-frontends/cx24113.h
index 782711ba1a3..962919b9b6e 100644
--- a/drivers/media/dvb-frontends/cx24113.h
+++ b/drivers/media/dvb-frontends/cx24113.h
@@ -32,7 +32,7 @@ struct cx24113_config {
 	u32 xtal_khz;
 };
 
-#if IS_ENABLED(CONFIG_DVB_TUNER_CX24113)
+#if IS_REACHABLE(CONFIG_DVB_TUNER_CX24113)
 extern struct dvb_frontend *cx24113_attach(struct dvb_frontend *,
 	const struct cx24113_config *config, struct i2c_adapter *i2c);
 
diff --git a/drivers/media/dvb-frontends/cx24116.c b/drivers/media/dvb-frontends/cx24116.c
index 2916d7c74a1..7bc68b355c0 100644
--- a/drivers/media/dvb-frontends/cx24116.c
+++ b/drivers/media/dvb-frontends/cx24116.c
@@ -963,6 +963,10 @@ static int cx24116_send_diseqc_msg(struct dvb_frontend *fe,
 	struct cx24116_state *state = fe->demodulator_priv;
 	int i, ret;
 
+	/* Validate length */
+	if (d->msg_len > sizeof(d->msg))
+                return -EINVAL;
+
 	/* Dump DiSEqC message */
 	if (debug) {
 		printk(KERN_INFO "cx24116: %s(", __func__);
@@ -974,10 +978,6 @@ static int cx24116_send_diseqc_msg(struct dvb_frontend *fe,
 		printk(") toneburst=%d\n", toneburst);
 	}
 
-	/* Validate length */
-	if (d->msg_len > (CX24116_ARGLEN - CX24116_DISEQC_MSGOFS))
-		return -EINVAL;
-
 	/* DiSEqC message */
 	for (i = 0; i < d->msg_len; i++)
 		state->dsec_cmd.args[CX24116_DISEQC_MSGOFS + i] = d->msg[i];
diff --git a/drivers/media/dvb-frontends/cx24116.h b/drivers/media/dvb-frontends/cx24116.h
index 2ec84fae3f9..f6dbabc1d62 100644
--- a/drivers/media/dvb-frontends/cx24116.h
+++ b/drivers/media/dvb-frontends/cx24116.h
@@ -41,7 +41,7 @@ struct cx24116_config {
 	u16 i2c_wr_max;
 };
 
-#if IS_ENABLED(CONFIG_DVB_CX24116)
+#if IS_REACHABLE(CONFIG_DVB_CX24116)
 extern struct dvb_frontend *cx24116_attach(
 	const struct cx24116_config *config,
 	struct i2c_adapter *i2c);
diff --git a/drivers/media/dvb-frontends/cx24117.c b/drivers/media/dvb-frontends/cx24117.c
index a6c3c9e2e89..d2eab0676d3 100644
--- a/drivers/media/dvb-frontends/cx24117.c
+++ b/drivers/media/dvb-frontends/cx24117.c
@@ -1043,7 +1043,7 @@ static int cx24117_send_diseqc_msg(struct dvb_frontend *fe,
 	dev_dbg(&state->priv->i2c->dev, ")\n");
 
 	/* Validate length */
-	if (d->msg_len > 15)
+	if (d->msg_len > sizeof(d->msg))
 		return -EINVAL;
 
 	/* DiSEqC message */
diff --git a/drivers/media/dvb-frontends/cx24117.h b/drivers/media/dvb-frontends/cx24117.h
index 4e59e9574fa..1648ab43216 100644
--- a/drivers/media/dvb-frontends/cx24117.h
+++ b/drivers/media/dvb-frontends/cx24117.h
@@ -30,7 +30,7 @@ struct cx24117_config {
 	u8 demod_address;
 };
 
-#if IS_ENABLED(CONFIG_DVB_CX24117)
+#if IS_REACHABLE(CONFIG_DVB_CX24117)
 extern struct dvb_frontend *cx24117_attach(
 	const struct cx24117_config *config,
 	struct i2c_adapter *i2c);
diff --git a/drivers/media/dvb-frontends/cx24123.h b/drivers/media/dvb-frontends/cx24123.h
index 102e70d17c4..758aee5a072 100644
--- a/drivers/media/dvb-frontends/cx24123.h
+++ b/drivers/media/dvb-frontends/cx24123.h
@@ -39,7 +39,7 @@ struct cx24123_config {
 	void (*agc_callback) (struct dvb_frontend *);
 };
 
-#if IS_ENABLED(CONFIG_DVB_CX24123)
+#if IS_REACHABLE(CONFIG_DVB_CX24123)
 extern struct dvb_frontend *cx24123_attach(const struct cx24123_config *config,
 					   struct i2c_adapter *i2c);
 extern struct i2c_adapter *cx24123_get_tuner_i2c_adapter(struct dvb_frontend *);
diff --git a/drivers/media/dvb-frontends/cxd2820r.h b/drivers/media/dvb-frontends/cxd2820r.h
index 6095dbcf785..56d42760263 100644
--- a/drivers/media/dvb-frontends/cxd2820r.h
+++ b/drivers/media/dvb-frontends/cxd2820r.h
@@ -72,7 +72,7 @@ struct cxd2820r_config {
 };
 
 
-#if IS_ENABLED(CONFIG_DVB_CXD2820R)
+#if IS_REACHABLE(CONFIG_DVB_CXD2820R)
 extern struct dvb_frontend *cxd2820r_attach(
 	const struct cxd2820r_config *config,
 	struct i2c_adapter *i2c,
diff --git a/drivers/media/dvb-frontends/dib0070.h b/drivers/media/dvb-frontends/dib0070.h
index 0c6befcc914..6c0b6672b1d 100644
--- a/drivers/media/dvb-frontends/dib0070.h
+++ b/drivers/media/dvb-frontends/dib0070.h
@@ -48,7 +48,7 @@ struct dib0070_config {
 	u8 vga_filter;
 };
 
-#if IS_ENABLED(CONFIG_DVB_TUNER_DIB0070)
+#if IS_REACHABLE(CONFIG_DVB_TUNER_DIB0070)
 extern struct dvb_frontend *dib0070_attach(struct dvb_frontend *fe, struct i2c_adapter *i2c, struct dib0070_config *cfg);
 extern u16 dib0070_wbd_offset(struct dvb_frontend *);
 extern void dib0070_ctrl_agc_filter(struct dvb_frontend *, u8 open);
diff --git a/drivers/media/dvb-frontends/dib0090.h b/drivers/media/dvb-frontends/dib0090.h
index 6a090954fa1..ad74bc823f0 100644
--- a/drivers/media/dvb-frontends/dib0090.h
+++ b/drivers/media/dvb-frontends/dib0090.h
@@ -75,7 +75,7 @@ struct dib0090_config {
 	u8 force_crystal_mode;
 };
 
-#if IS_ENABLED(CONFIG_DVB_TUNER_DIB0090)
+#if IS_REACHABLE(CONFIG_DVB_TUNER_DIB0090)
 extern struct dvb_frontend *dib0090_register(struct dvb_frontend *fe, struct i2c_adapter *i2c, const struct dib0090_config *config);
 extern struct dvb_frontend *dib0090_fw_register(struct dvb_frontend *fe, struct i2c_adapter *i2c, const struct dib0090_config *config);
 extern void dib0090_dcc_freq(struct dvb_frontend *fe, u8 fast);
diff --git a/drivers/media/dvb-frontends/dib3000.h b/drivers/media/dvb-frontends/dib3000.h
index 9b6c3bbc983..6ae9899b5b4 100644
--- a/drivers/media/dvb-frontends/dib3000.h
+++ b/drivers/media/dvb-frontends/dib3000.h
@@ -41,7 +41,7 @@ struct dib_fe_xfer_ops
 	int (*tuner_pass_ctrl)(struct dvb_frontend *fe, int onoff, u8 pll_ctrl);
 };
 
-#if IS_ENABLED(CONFIG_DVB_DIB3000MB)
+#if IS_REACHABLE(CONFIG_DVB_DIB3000MB)
 extern struct dvb_frontend* dib3000mb_attach(const struct dib3000_config* config,
 					     struct i2c_adapter* i2c, struct dib_fe_xfer_ops *xfer_ops);
 #else
diff --git a/drivers/media/dvb-frontends/dib3000mc.h b/drivers/media/dvb-frontends/dib3000mc.h
index 129d1425516..74816f79361 100644
--- a/drivers/media/dvb-frontends/dib3000mc.h
+++ b/drivers/media/dvb-frontends/dib3000mc.h
@@ -41,7 +41,7 @@ struct dib3000mc_config {
 #define DEFAULT_DIB3000MC_I2C_ADDRESS 16
 #define DEFAULT_DIB3000P_I2C_ADDRESS  24
 
-#if IS_ENABLED(CONFIG_DVB_DIB3000MC)
+#if IS_REACHABLE(CONFIG_DVB_DIB3000MC)
 extern struct dvb_frontend *dib3000mc_attach(struct i2c_adapter *i2c_adap,
 					     u8 i2c_addr,
 					     struct dib3000mc_config *cfg);
diff --git a/drivers/media/dvb-frontends/dib7000m.h b/drivers/media/dvb-frontends/dib7000m.h
index b585413f9a2..6468c278cc4 100644
--- a/drivers/media/dvb-frontends/dib7000m.h
+++ b/drivers/media/dvb-frontends/dib7000m.h
@@ -40,7 +40,7 @@ struct dib7000m_config {
 
 #define DEFAULT_DIB7000M_I2C_ADDRESS 18
 
-#if IS_ENABLED(CONFIG_DVB_DIB7000M)
+#if IS_REACHABLE(CONFIG_DVB_DIB7000M)
 extern struct dvb_frontend *dib7000m_attach(struct i2c_adapter *i2c_adap,
 					    u8 i2c_addr,
 					    struct dib7000m_config *cfg);
diff --git a/drivers/media/dvb-frontends/dib7000p.h b/drivers/media/dvb-frontends/dib7000p.h
index 1fea0e97265..baa278928cf 100644
--- a/drivers/media/dvb-frontends/dib7000p.h
+++ b/drivers/media/dvb-frontends/dib7000p.h
@@ -66,7 +66,7 @@ struct dib7000p_ops {
 	struct dvb_frontend *(*init)(struct i2c_adapter *i2c_adap, u8 i2c_addr, struct dib7000p_config *cfg);
 };
 
-#if IS_ENABLED(CONFIG_DVB_DIB7000P)
+#if IS_REACHABLE(CONFIG_DVB_DIB7000P)
 void *dib7000p_attach(struct dib7000p_ops *ops);
 #else
 static inline void *dib7000p_attach(struct dib7000p_ops *ops)
diff --git a/drivers/media/dvb-frontends/dib8000.h b/drivers/media/dvb-frontends/dib8000.h
index 84cc10383dc..780c37bdcb7 100644
--- a/drivers/media/dvb-frontends/dib8000.h
+++ b/drivers/media/dvb-frontends/dib8000.h
@@ -63,7 +63,7 @@ struct dib8000_ops {
 	struct dvb_frontend *(*init)(struct i2c_adapter *i2c_adap, u8 i2c_addr, struct dib8000_config *cfg);
 };
 
-#if IS_ENABLED(CONFIG_DVB_DIB8000)
+#if IS_REACHABLE(CONFIG_DVB_DIB8000)
 void *dib8000_attach(struct dib8000_ops *ops);
 #else
 static inline int dib8000_attach(struct dib8000_ops *ops)
diff --git a/drivers/media/dvb-frontends/dib9000.h b/drivers/media/dvb-frontends/dib9000.h
index f3639f045ff..b10a70aa7c9 100644
--- a/drivers/media/dvb-frontends/dib9000.h
+++ b/drivers/media/dvb-frontends/dib9000.h
@@ -27,7 +27,7 @@ struct dib9000_config {
 
 #define DEFAULT_DIB9000_I2C_ADDRESS 18
 
-#if IS_ENABLED(CONFIG_DVB_DIB9000)
+#if IS_REACHABLE(CONFIG_DVB_DIB9000)
 extern struct dvb_frontend *dib9000_attach(struct i2c_adapter *i2c_adap, u8 i2c_addr, const struct dib9000_config *cfg);
 extern int dib9000_i2c_enumeration(struct i2c_adapter *host, int no_of_demods, u8 default_addr, u8 first_addr);
 extern struct i2c_adapter *dib9000_get_tuner_interface(struct dvb_frontend *fe);
diff --git a/drivers/media/dvb-frontends/drxd.h b/drivers/media/dvb-frontends/drxd.h
index d998e4d5a7f..a47c22d6667 100644
--- a/drivers/media/dvb-frontends/drxd.h
+++ b/drivers/media/dvb-frontends/drxd.h
@@ -52,7 +52,7 @@ struct drxd_config {
 	 s16(*osc_deviation) (void *priv, s16 dev, int flag);
 };
 
-#if IS_ENABLED(CONFIG_DVB_DRXD)
+#if IS_REACHABLE(CONFIG_DVB_DRXD)
 extern
 struct dvb_frontend *drxd_attach(const struct drxd_config *config,
 				 void *priv, struct i2c_adapter *i2c,
diff --git a/drivers/media/dvb-frontends/drxk.h b/drivers/media/dvb-frontends/drxk.h
index f6cb3466032..8f0b9eec528 100644
--- a/drivers/media/dvb-frontends/drxk.h
+++ b/drivers/media/dvb-frontends/drxk.h
@@ -51,7 +51,7 @@ struct drxk_config {
 	int		 qam_demod_parameter_count;
 };
 
-#if IS_ENABLED(CONFIG_DVB_DRXK)
+#if IS_REACHABLE(CONFIG_DVB_DRXK)
 extern struct dvb_frontend *drxk_attach(const struct drxk_config *config,
 					struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/ds3000.h b/drivers/media/dvb-frontends/ds3000.h
index f9c21fb7af1..153169da901 100644
--- a/drivers/media/dvb-frontends/ds3000.h
+++ b/drivers/media/dvb-frontends/ds3000.h
@@ -35,7 +35,7 @@ struct ds3000_config {
 	void (*set_lock_led)(struct dvb_frontend *fe, int offon);
 };
 
-#if IS_ENABLED(CONFIG_DVB_DS3000)
+#if IS_REACHABLE(CONFIG_DVB_DS3000)
 extern struct dvb_frontend *ds3000_attach(const struct ds3000_config *config,
 					struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/dvb-pll.h b/drivers/media/dvb-frontends/dvb-pll.h
index f4b5a0601c3..bf9602a88b6 100644
--- a/drivers/media/dvb-frontends/dvb-pll.h
+++ b/drivers/media/dvb-frontends/dvb-pll.h
@@ -38,7 +38,7 @@
  * @param pll_desc_id dvb_pll_desc to use.
  * @return Frontend pointer on success, NULL on failure
  */
-#if IS_ENABLED(CONFIG_DVB_PLL)
+#if IS_REACHABLE(CONFIG_DVB_PLL)
 extern struct dvb_frontend *dvb_pll_attach(struct dvb_frontend *fe,
 					   int pll_addr,
 					   struct i2c_adapter *i2c,
diff --git a/drivers/media/dvb-frontends/dvb_dummy_fe.h b/drivers/media/dvb-frontends/dvb_dummy_fe.h
index 0cbf9610563..15e4ceab869 100644
--- a/drivers/media/dvb-frontends/dvb_dummy_fe.h
+++ b/drivers/media/dvb-frontends/dvb_dummy_fe.h
@@ -26,7 +26,7 @@
 #include <linux/dvb/frontend.h>
 #include "dvb_frontend.h"
 
-#if IS_ENABLED(CONFIG_DVB_DUMMY_FE)
+#if IS_REACHABLE(CONFIG_DVB_DUMMY_FE)
 extern struct dvb_frontend* dvb_dummy_fe_ofdm_attach(void);
 extern struct dvb_frontend* dvb_dummy_fe_qpsk_attach(void);
 extern struct dvb_frontend* dvb_dummy_fe_qam_attach(void);
diff --git a/drivers/media/dvb-frontends/ec100.h b/drivers/media/dvb-frontends/ec100.h
index 37558403068..9544bab5cd1 100644
--- a/drivers/media/dvb-frontends/ec100.h
+++ b/drivers/media/dvb-frontends/ec100.h
@@ -31,7 +31,7 @@ struct ec100_config {
 };
 
 
-#if IS_ENABLED(CONFIG_DVB_EC100)
+#if IS_REACHABLE(CONFIG_DVB_EC100)
 extern struct dvb_frontend *ec100_attach(const struct ec100_config *config,
 	struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/hd29l2.h b/drivers/media/dvb-frontends/hd29l2.h
index 05cd13028a9..48e9ab74c88 100644
--- a/drivers/media/dvb-frontends/hd29l2.h
+++ b/drivers/media/dvb-frontends/hd29l2.h
@@ -51,7 +51,7 @@ struct hd29l2_config {
 };
 
 
-#if IS_ENABLED(CONFIG_DVB_HD29L2)
+#if IS_REACHABLE(CONFIG_DVB_HD29L2)
 extern struct dvb_frontend *hd29l2_attach(const struct hd29l2_config *config,
 	struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/isl6405.h b/drivers/media/dvb-frontends/isl6405.h
index 8abb70c26fd..3c148b830bd 100644
--- a/drivers/media/dvb-frontends/isl6405.h
+++ b/drivers/media/dvb-frontends/isl6405.h
@@ -55,7 +55,7 @@
 #define ISL6405_ENT2	0x20
 #define ISL6405_ISEL2	0x40
 
-#if IS_ENABLED(CONFIG_DVB_ISL6405)
+#if IS_REACHABLE(CONFIG_DVB_ISL6405)
 /* override_set and override_clear control which system register bits (above)
  * to always set & clear
  */
diff --git a/drivers/media/dvb-frontends/isl6421.h b/drivers/media/dvb-frontends/isl6421.h
index 630e7f8a150..3273597833f 100644
--- a/drivers/media/dvb-frontends/isl6421.h
+++ b/drivers/media/dvb-frontends/isl6421.h
@@ -39,7 +39,7 @@
 #define ISL6421_ISEL1	0x20
 #define ISL6421_DCL	0x40
 
-#if IS_ENABLED(CONFIG_DVB_ISL6421)
+#if IS_REACHABLE(CONFIG_DVB_ISL6421)
 /* override_set and override_clear control which system register bits (above) to always set & clear */
 extern struct dvb_frontend *isl6421_attach(struct dvb_frontend *fe, struct i2c_adapter *i2c, u8 i2c_addr,
 			  u8 override_set, u8 override_clear, bool override_tone);
diff --git a/drivers/media/dvb-frontends/isl6423.h b/drivers/media/dvb-frontends/isl6423.h
index 80dfd9cc4f4..a64df0ee256 100644
--- a/drivers/media/dvb-frontends/isl6423.h
+++ b/drivers/media/dvb-frontends/isl6423.h
@@ -42,7 +42,7 @@ struct isl6423_config {
 	u8 mod_extern;
 };
 
-#if IS_ENABLED(CONFIG_DVB_ISL6423)
+#if IS_REACHABLE(CONFIG_DVB_ISL6423)
 
 
 extern struct dvb_frontend *isl6423_attach(struct dvb_frontend *fe,
diff --git a/drivers/media/dvb-frontends/itd1000.h b/drivers/media/dvb-frontends/itd1000.h
index edae0902f4f..a691bb6f26d 100644
--- a/drivers/media/dvb-frontends/itd1000.h
+++ b/drivers/media/dvb-frontends/itd1000.h
@@ -29,7 +29,7 @@ struct itd1000_config {
 	u8 i2c_address;
 };
 
-#if IS_ENABLED(CONFIG_DVB_TUNER_ITD1000)
+#if IS_REACHABLE(CONFIG_DVB_TUNER_ITD1000)
 extern struct dvb_frontend *itd1000_attach(struct dvb_frontend *fe, struct i2c_adapter *i2c, struct itd1000_config *cfg);
 #else
 static inline struct dvb_frontend *itd1000_attach(struct dvb_frontend *fe, struct i2c_adapter *i2c, struct itd1000_config *cfg)
diff --git a/drivers/media/dvb-frontends/ix2505v.h b/drivers/media/dvb-frontends/ix2505v.h
index 1a735a75aa9..af107a2dd35 100644
--- a/drivers/media/dvb-frontends/ix2505v.h
+++ b/drivers/media/dvb-frontends/ix2505v.h
@@ -49,7 +49,7 @@ struct ix2505v_config {
 
 };
 
-#if IS_ENABLED(CONFIG_DVB_IX2505V)
+#if IS_REACHABLE(CONFIG_DVB_IX2505V)
 extern struct dvb_frontend *ix2505v_attach(struct dvb_frontend *fe,
 	const struct ix2505v_config *config, struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/l64781.h b/drivers/media/dvb-frontends/l64781.h
index 6813b08a774..8697e2c2ba3 100644
--- a/drivers/media/dvb-frontends/l64781.h
+++ b/drivers/media/dvb-frontends/l64781.h
@@ -31,7 +31,7 @@ struct l64781_config
 	u8 demod_address;
 };
 
-#if IS_ENABLED(CONFIG_DVB_L64781)
+#if IS_REACHABLE(CONFIG_DVB_L64781)
 extern struct dvb_frontend* l64781_attach(const struct l64781_config* config,
 					  struct i2c_adapter* i2c);
 #else
diff --git a/drivers/media/dvb-frontends/lg2160.h b/drivers/media/dvb-frontends/lg2160.h
index 194a07a78dc..d20bd909de3 100644
--- a/drivers/media/dvb-frontends/lg2160.h
+++ b/drivers/media/dvb-frontends/lg2160.h
@@ -67,7 +67,7 @@ struct lg2160_config {
 	enum lg_chip_type lg_chip;
 };
 
-#if IS_ENABLED(CONFIG_DVB_LG2160)
+#if IS_REACHABLE(CONFIG_DVB_LG2160)
 extern
 struct dvb_frontend *lg2160_attach(const struct lg2160_config *config,
 				     struct i2c_adapter *i2c_adap);
diff --git a/drivers/media/dvb-frontends/lgdt3305.h b/drivers/media/dvb-frontends/lgdt3305.h
index d9ab556c1b2..d8666043b3d 100644
--- a/drivers/media/dvb-frontends/lgdt3305.h
+++ b/drivers/media/dvb-frontends/lgdt3305.h
@@ -74,7 +74,7 @@ struct lgdt3305_config {
 	enum lgdt_demod_chip_type demod_chip;
 };
 
-#if IS_ENABLED(CONFIG_DVB_LGDT3305)
+#if IS_REACHABLE(CONFIG_DVB_LGDT3305)
 extern
 struct dvb_frontend *lgdt3305_attach(const struct lgdt3305_config *config,
 				     struct i2c_adapter *i2c_adap);
diff --git a/drivers/media/dvb-frontends/lgdt330x.h b/drivers/media/dvb-frontends/lgdt330x.h
index ca0eab562e1..b4ee363b657 100644
--- a/drivers/media/dvb-frontends/lgdt330x.h
+++ b/drivers/media/dvb-frontends/lgdt330x.h
@@ -52,7 +52,7 @@ struct lgdt330x_config
 	int clock_polarity_flip;
 };
 
-#if IS_ENABLED(CONFIG_DVB_LGDT330X)
+#if IS_REACHABLE(CONFIG_DVB_LGDT330X)
 extern struct dvb_frontend* lgdt330x_attach(const struct lgdt330x_config* config,
 					    struct i2c_adapter* i2c);
 #else
diff --git a/drivers/media/dvb-frontends/lgs8gl5.h b/drivers/media/dvb-frontends/lgs8gl5.h
index c2da5961472..a5b3faf121f 100644
--- a/drivers/media/dvb-frontends/lgs8gl5.h
+++ b/drivers/media/dvb-frontends/lgs8gl5.h
@@ -31,7 +31,7 @@ struct lgs8gl5_config {
 	u8 demod_address;
 };
 
-#if IS_ENABLED(CONFIG_DVB_LGS8GL5)
+#if IS_REACHABLE(CONFIG_DVB_LGS8GL5)
 extern struct dvb_frontend *lgs8gl5_attach(
 	const struct lgs8gl5_config *config, struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/lgs8gxx.h b/drivers/media/dvb-frontends/lgs8gxx.h
index dadb78bf61a..368c9928ef7 100644
--- a/drivers/media/dvb-frontends/lgs8gxx.h
+++ b/drivers/media/dvb-frontends/lgs8gxx.h
@@ -80,7 +80,7 @@ struct lgs8gxx_config {
 	u8 tuner_address;
 };
 
-#if IS_ENABLED(CONFIG_DVB_LGS8GXX)
+#if IS_REACHABLE(CONFIG_DVB_LGS8GXX)
 extern struct dvb_frontend *lgs8gxx_attach(const struct lgs8gxx_config *config,
 					   struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/lnbh24.h b/drivers/media/dvb-frontends/lnbh24.h
index b327a4f31d1..a088b8ec1e5 100644
--- a/drivers/media/dvb-frontends/lnbh24.h
+++ b/drivers/media/dvb-frontends/lnbh24.h
@@ -37,7 +37,7 @@
 
 #include <linux/dvb/frontend.h>
 
-#if IS_ENABLED(CONFIG_DVB_LNBP21)
+#if IS_REACHABLE(CONFIG_DVB_LNBP21)
 /* override_set and override_clear control which
    system register bits (above) to always set & clear */
 extern struct dvb_frontend *lnbh24_attach(struct dvb_frontend *fe,
diff --git a/drivers/media/dvb-frontends/lnbp21.h b/drivers/media/dvb-frontends/lnbp21.h
index dbcbcc2f20a..a9b530de62a 100644
--- a/drivers/media/dvb-frontends/lnbp21.h
+++ b/drivers/media/dvb-frontends/lnbp21.h
@@ -57,7 +57,7 @@
 
 #include <linux/dvb/frontend.h>
 
-#if IS_ENABLED(CONFIG_DVB_LNBP21)
+#if IS_REACHABLE(CONFIG_DVB_LNBP21)
 /* override_set and override_clear control which
  system register bits (above) to always set & clear */
 extern struct dvb_frontend *lnbp21_attach(struct dvb_frontend *fe,
diff --git a/drivers/media/dvb-frontends/lnbp22.h b/drivers/media/dvb-frontends/lnbp22.h
index 63861b311dd..62814838518 100644
--- a/drivers/media/dvb-frontends/lnbp22.h
+++ b/drivers/media/dvb-frontends/lnbp22.h
@@ -39,7 +39,7 @@
 
 #include <linux/dvb/frontend.h>
 
-#if IS_ENABLED(CONFIG_DVB_LNBP22)
+#if IS_REACHABLE(CONFIG_DVB_LNBP22)
 /*
  * override_set and override_clear control which system register bits (above)
  * to always set & clear
diff --git a/drivers/media/dvb-frontends/m88rs2000.h b/drivers/media/dvb-frontends/m88rs2000.h
index 0a50ea90736..de7430178e9 100644
--- a/drivers/media/dvb-frontends/m88rs2000.h
+++ b/drivers/media/dvb-frontends/m88rs2000.h
@@ -41,7 +41,7 @@ enum {
 	CALL_IS_READ,
 };
 
-#if IS_ENABLED(CONFIG_DVB_M88RS2000)
+#if IS_REACHABLE(CONFIG_DVB_M88RS2000)
 extern struct dvb_frontend *m88rs2000_attach(
 	const struct m88rs2000_config *config, struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/mb86a16.h b/drivers/media/dvb-frontends/mb86a16.h
index 277ce061acf..e486dc0d8e6 100644
--- a/drivers/media/dvb-frontends/mb86a16.h
+++ b/drivers/media/dvb-frontends/mb86a16.h
@@ -33,7 +33,7 @@ struct mb86a16_config {
 
 
 
-#if IS_ENABLED(CONFIG_DVB_MB86A16)
+#if IS_REACHABLE(CONFIG_DVB_MB86A16)
 
 extern struct dvb_frontend *mb86a16_attach(const struct mb86a16_config *config,
 					   struct i2c_adapter *i2c_adap);
diff --git a/drivers/media/dvb-frontends/mb86a20s.h b/drivers/media/dvb-frontends/mb86a20s.h
index cbeb941fba7..f749c8ac5f3 100644
--- a/drivers/media/dvb-frontends/mb86a20s.h
+++ b/drivers/media/dvb-frontends/mb86a20s.h
@@ -34,7 +34,7 @@ struct mb86a20s_config {
 	bool	is_serial;
 };
 
-#if IS_ENABLED(CONFIG_DVB_MB86A20S)
+#if IS_REACHABLE(CONFIG_DVB_MB86A20S)
 extern struct dvb_frontend *mb86a20s_attach(const struct mb86a20s_config *config,
 					   struct i2c_adapter *i2c);
 extern struct i2c_adapter *mb86a20s_get_tuner_i2c_adapter(struct dvb_frontend *);
diff --git a/drivers/media/dvb-frontends/mt312.h b/drivers/media/dvb-frontends/mt312.h
index 5706621ad79..386939a9055 100644
--- a/drivers/media/dvb-frontends/mt312.h
+++ b/drivers/media/dvb-frontends/mt312.h
@@ -36,7 +36,7 @@ struct mt312_config {
 	unsigned int voltage_inverted:1;
 };
 
-#if IS_ENABLED(CONFIG_DVB_MT312)
+#if IS_REACHABLE(CONFIG_DVB_MT312)
 struct dvb_frontend *mt312_attach(const struct mt312_config *config,
 					struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/mt352.h b/drivers/media/dvb-frontends/mt352.h
index 451d904e150..5873263bd1a 100644
--- a/drivers/media/dvb-frontends/mt352.h
+++ b/drivers/media/dvb-frontends/mt352.h
@@ -51,7 +51,7 @@ struct mt352_config
 	int (*demod_init)(struct dvb_frontend* fe);
 };
 
-#if IS_ENABLED(CONFIG_DVB_MT352)
+#if IS_REACHABLE(CONFIG_DVB_MT352)
 extern struct dvb_frontend* mt352_attach(const struct mt352_config* config,
 					 struct i2c_adapter* i2c);
 #else
diff --git a/drivers/media/dvb-frontends/nxt200x.h b/drivers/media/dvb-frontends/nxt200x.h
index b518d545609..3b3d7a7fa59 100644
--- a/drivers/media/dvb-frontends/nxt200x.h
+++ b/drivers/media/dvb-frontends/nxt200x.h
@@ -42,7 +42,7 @@ struct nxt200x_config
 	int (*set_ts_params)(struct dvb_frontend* fe, int is_punctured);
 };
 
-#if IS_ENABLED(CONFIG_DVB_NXT200X)
+#if IS_REACHABLE(CONFIG_DVB_NXT200X)
 extern struct dvb_frontend* nxt200x_attach(const struct nxt200x_config* config,
 					   struct i2c_adapter* i2c);
 #else
diff --git a/drivers/media/dvb-frontends/nxt6000.h b/drivers/media/dvb-frontends/nxt6000.h
index b5867c2ae68..a94cefcc6df 100644
--- a/drivers/media/dvb-frontends/nxt6000.h
+++ b/drivers/media/dvb-frontends/nxt6000.h
@@ -33,7 +33,7 @@ struct nxt6000_config
 	u8 clock_inversion:1;
 };
 
-#if IS_ENABLED(CONFIG_DVB_NXT6000)
+#if IS_REACHABLE(CONFIG_DVB_NXT6000)
 extern struct dvb_frontend* nxt6000_attach(const struct nxt6000_config* config,
 					   struct i2c_adapter* i2c);
 #else
diff --git a/drivers/media/dvb-frontends/or51132.h b/drivers/media/dvb-frontends/or51132.h
index 938958386cb..aeaaffc84c2 100644
--- a/drivers/media/dvb-frontends/or51132.h
+++ b/drivers/media/dvb-frontends/or51132.h
@@ -34,7 +34,7 @@ struct or51132_config
 	int (*set_ts_params)(struct dvb_frontend* fe, int is_punctured);
 };
 
-#if IS_ENABLED(CONFIG_DVB_OR51132)
+#if IS_REACHABLE(CONFIG_DVB_OR51132)
 extern struct dvb_frontend* or51132_attach(const struct or51132_config* config,
 					   struct i2c_adapter* i2c);
 #else
diff --git a/drivers/media/dvb-frontends/or51211.h b/drivers/media/dvb-frontends/or51211.h
index 9a8ae936b62..cc6adab6324 100644
--- a/drivers/media/dvb-frontends/or51211.h
+++ b/drivers/media/dvb-frontends/or51211.h
@@ -37,7 +37,7 @@ struct or51211_config
 	void (*sleep)(struct dvb_frontend * fe);
 };
 
-#if IS_ENABLED(CONFIG_DVB_OR51211)
+#if IS_REACHABLE(CONFIG_DVB_OR51211)
 extern struct dvb_frontend* or51211_attach(const struct or51211_config* config,
 					   struct i2c_adapter* i2c);
 #else
diff --git a/drivers/media/dvb-frontends/s5h1409.h b/drivers/media/dvb-frontends/s5h1409.h
index 63b1e0a34e4..7749efbeba2 100644
--- a/drivers/media/dvb-frontends/s5h1409.h
+++ b/drivers/media/dvb-frontends/s5h1409.h
@@ -67,7 +67,7 @@ struct s5h1409_config {
 	u8 hvr1600_opt;
 };
 
-#if IS_ENABLED(CONFIG_DVB_S5H1409)
+#if IS_REACHABLE(CONFIG_DVB_S5H1409)
 extern struct dvb_frontend *s5h1409_attach(const struct s5h1409_config *config,
 					   struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/s5h1411.h b/drivers/media/dvb-frontends/s5h1411.h
index e4f56871f98..d63b5b590ab 100644
--- a/drivers/media/dvb-frontends/s5h1411.h
+++ b/drivers/media/dvb-frontends/s5h1411.h
@@ -69,7 +69,7 @@ struct s5h1411_config {
 	u8 status_mode;
 };
 
-#if IS_ENABLED(CONFIG_DVB_S5H1411)
+#if IS_REACHABLE(CONFIG_DVB_S5H1411)
 extern struct dvb_frontend *s5h1411_attach(const struct s5h1411_config *config,
 					   struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/s5h1420.c b/drivers/media/dvb-frontends/s5h1420.c
index 93eeaf7118f..0b4f8fe6bf9 100644
--- a/drivers/media/dvb-frontends/s5h1420.c
+++ b/drivers/media/dvb-frontends/s5h1420.c
@@ -180,7 +180,7 @@ static int s5h1420_send_master_cmd (struct dvb_frontend* fe,
 	int result = 0;
 
 	dprintk("enter %s\n", __func__);
-	if (cmd->msg_len > 8)
+	if (cmd->msg_len > sizeof(cmd->msg))
 		return -EINVAL;
 
 	/* setup for DISEQC */
diff --git a/drivers/media/dvb-frontends/s5h1420.h b/drivers/media/dvb-frontends/s5h1420.h
index 210049b5cf3..142d93e7d02 100644
--- a/drivers/media/dvb-frontends/s5h1420.h
+++ b/drivers/media/dvb-frontends/s5h1420.h
@@ -40,7 +40,7 @@ struct s5h1420_config
 	u8 serial_mpeg:1;
 };
 
-#if IS_ENABLED(CONFIG_DVB_S5H1420)
+#if IS_REACHABLE(CONFIG_DVB_S5H1420)
 extern struct dvb_frontend *s5h1420_attach(const struct s5h1420_config *config,
 	     struct i2c_adapter *i2c);
 extern struct i2c_adapter *s5h1420_get_tuner_i2c_adapter(struct dvb_frontend *fe);
diff --git a/drivers/media/dvb-frontends/s5h1432.h b/drivers/media/dvb-frontends/s5h1432.h
index 70917dd2533..f490c5ee580 100644
--- a/drivers/media/dvb-frontends/s5h1432.h
+++ b/drivers/media/dvb-frontends/s5h1432.h
@@ -75,7 +75,7 @@ struct s5h1432_config {
 	u8 status_mode;
 };
 
-#if IS_ENABLED(CONFIG_DVB_S5H1432)
+#if IS_REACHABLE(CONFIG_DVB_S5H1432)
 extern struct dvb_frontend *s5h1432_attach(const struct s5h1432_config *config,
 					   struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/s921.h b/drivers/media/dvb-frontends/s921.h
index 9b20c9e0eb8..7d3999a4e97 100644
--- a/drivers/media/dvb-frontends/s921.h
+++ b/drivers/media/dvb-frontends/s921.h
@@ -25,7 +25,7 @@ struct s921_config {
 	u8 demod_address;
 };
 
-#if IS_ENABLED(CONFIG_DVB_S921)
+#if IS_REACHABLE(CONFIG_DVB_S921)
 extern struct dvb_frontend *s921_attach(const struct s921_config *config,
 					   struct i2c_adapter *i2c);
 extern struct i2c_adapter *s921_get_tuner_i2c_adapter(struct dvb_frontend *);
diff --git a/drivers/media/dvb-frontends/si2168.c b/drivers/media/dvb-frontends/si2168.c
index 1cd93be281e..64a759c017d 100644
--- a/drivers/media/dvb-frontends/si2168.c
+++ b/drivers/media/dvb-frontends/si2168.c
@@ -605,6 +605,8 @@ static const struct dvb_frontend_ops si2168_ops = {
 	.delsys = {SYS_DVBT, SYS_DVBT2, SYS_DVBC_ANNEX_A},
 	.info = {
 		.name = "Silicon Labs Si2168",
+		.symbol_rate_min = 1000000,
+		.symbol_rate_max = 7200000,
 		.caps =	FE_CAN_FEC_1_2 |
 			FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 |
diff --git a/drivers/media/dvb-frontends/si21xx.h b/drivers/media/dvb-frontends/si21xx.h
index 1509fed44a3..ef5f351ca68 100644
--- a/drivers/media/dvb-frontends/si21xx.h
+++ b/drivers/media/dvb-frontends/si21xx.h
@@ -13,7 +13,7 @@ struct si21xx_config {
 	int min_delay_ms;
 };
 
-#if IS_ENABLED(CONFIG_DVB_SI21XX)
+#if IS_REACHABLE(CONFIG_DVB_SI21XX)
 extern struct dvb_frontend *si21xx_attach(const struct si21xx_config *config,
 						struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/sp8870.h b/drivers/media/dvb-frontends/sp8870.h
index 065ec67d4e3..f507b9fd707 100644
--- a/drivers/media/dvb-frontends/sp8870.h
+++ b/drivers/media/dvb-frontends/sp8870.h
@@ -35,7 +35,7 @@ struct sp8870_config
 	int (*request_firmware)(struct dvb_frontend* fe, const struct firmware **fw, char* name);
 };
 
-#if IS_ENABLED(CONFIG_DVB_SP8870)
+#if IS_REACHABLE(CONFIG_DVB_SP8870)
 extern struct dvb_frontend* sp8870_attach(const struct sp8870_config* config,
 					  struct i2c_adapter* i2c);
 #else
diff --git a/drivers/media/dvb-frontends/sp887x.h b/drivers/media/dvb-frontends/sp887x.h
index 2cdc4e8bc9c..412f011e6df 100644
--- a/drivers/media/dvb-frontends/sp887x.h
+++ b/drivers/media/dvb-frontends/sp887x.h
@@ -17,7 +17,7 @@ struct sp887x_config
 	int (*request_firmware)(struct dvb_frontend* fe, const struct firmware **fw, char* name);
 };
 
-#if IS_ENABLED(CONFIG_DVB_SP887X)
+#if IS_REACHABLE(CONFIG_DVB_SP887X)
 extern struct dvb_frontend* sp887x_attach(const struct sp887x_config* config,
 					  struct i2c_adapter* i2c);
 #else
diff --git a/drivers/media/dvb-frontends/stb0899_drv.h b/drivers/media/dvb-frontends/stb0899_drv.h
index 139264d1926..0a72131a57d 100644
--- a/drivers/media/dvb-frontends/stb0899_drv.h
+++ b/drivers/media/dvb-frontends/stb0899_drv.h
@@ -141,7 +141,7 @@ struct stb0899_config {
 	int (*tuner_set_rfsiggain)(struct dvb_frontend *fe, u32 rf_gain);
 };
 
-#if IS_ENABLED(CONFIG_DVB_STB0899)
+#if IS_REACHABLE(CONFIG_DVB_STB0899)
 
 extern struct dvb_frontend *stb0899_attach(struct stb0899_config *config,
 					   struct i2c_adapter *i2c);
diff --git a/drivers/media/dvb-frontends/stb6000.h b/drivers/media/dvb-frontends/stb6000.h
index a768189bfaa..da581b652cb 100644
--- a/drivers/media/dvb-frontends/stb6000.h
+++ b/drivers/media/dvb-frontends/stb6000.h
@@ -35,7 +35,7 @@
  * @param i2c i2c adapter to use.
  * @return FE pointer on success, NULL on failure.
  */
-#if IS_ENABLED(CONFIG_DVB_STB6000)
+#if IS_REACHABLE(CONFIG_DVB_STB6000)
 extern struct dvb_frontend *stb6000_attach(struct dvb_frontend *fe, int addr,
 					   struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/stb6100.h b/drivers/media/dvb-frontends/stb6100.h
index 3a1e40f3b8b..218c8188865 100644
--- a/drivers/media/dvb-frontends/stb6100.h
+++ b/drivers/media/dvb-frontends/stb6100.h
@@ -94,7 +94,7 @@ struct stb6100_state {
 	u32 reference;
 };
 
-#if IS_ENABLED(CONFIG_DVB_STB6100)
+#if IS_REACHABLE(CONFIG_DVB_STB6100)
 
 extern struct dvb_frontend *stb6100_attach(struct dvb_frontend *fe,
 					   const struct stb6100_config *config,
diff --git a/drivers/media/dvb-frontends/stv0288.h b/drivers/media/dvb-frontends/stv0288.h
index a0bd9310715..b58603c00c8 100644
--- a/drivers/media/dvb-frontends/stv0288.h
+++ b/drivers/media/dvb-frontends/stv0288.h
@@ -43,7 +43,7 @@ struct stv0288_config {
 	int (*set_ts_params)(struct dvb_frontend *fe, int is_punctured);
 };
 
-#if IS_ENABLED(CONFIG_DVB_STV0288)
+#if IS_REACHABLE(CONFIG_DVB_STV0288)
 extern struct dvb_frontend *stv0288_attach(const struct stv0288_config *config,
 					   struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/stv0297.h b/drivers/media/dvb-frontends/stv0297.h
index c8ff3639ce0..b30632a6733 100644
--- a/drivers/media/dvb-frontends/stv0297.h
+++ b/drivers/media/dvb-frontends/stv0297.h
@@ -42,7 +42,7 @@ struct stv0297_config
 	u8 stop_during_read:1;
 };
 
-#if IS_ENABLED(CONFIG_DVB_STV0297)
+#if IS_REACHABLE(CONFIG_DVB_STV0297)
 extern struct dvb_frontend* stv0297_attach(const struct stv0297_config* config,
 					   struct i2c_adapter* i2c);
 #else
diff --git a/drivers/media/dvb-frontends/stv0299.h b/drivers/media/dvb-frontends/stv0299.h
index 06f70fc8327..0aca30a8ec2 100644
--- a/drivers/media/dvb-frontends/stv0299.h
+++ b/drivers/media/dvb-frontends/stv0299.h
@@ -95,7 +95,7 @@ struct stv0299_config
 	int (*set_ts_params)(struct dvb_frontend *fe, int is_punctured);
 };
 
-#if IS_ENABLED(CONFIG_DVB_STV0299)
+#if IS_REACHABLE(CONFIG_DVB_STV0299)
 extern struct dvb_frontend *stv0299_attach(const struct stv0299_config *config,
 					   struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/stv0367.h b/drivers/media/dvb-frontends/stv0367.h
index ea80b341f09..92b3e85fb81 100644
--- a/drivers/media/dvb-frontends/stv0367.h
+++ b/drivers/media/dvb-frontends/stv0367.h
@@ -39,7 +39,7 @@ struct stv0367_config {
 	int clk_pol;
 };
 
-#if IS_ENABLED(CONFIG_DVB_STV0367)
+#if IS_REACHABLE(CONFIG_DVB_STV0367)
 extern struct
 dvb_frontend *stv0367ter_attach(const struct stv0367_config *config,
 					struct i2c_adapter *i2c);
diff --git a/drivers/media/dvb-frontends/stv0900.h b/drivers/media/dvb-frontends/stv0900.h
index e2a6dc69ecb..c90bf00ea9c 100644
--- a/drivers/media/dvb-frontends/stv0900.h
+++ b/drivers/media/dvb-frontends/stv0900.h
@@ -58,7 +58,7 @@ struct stv0900_config {
 	void (*set_lock_led)(struct dvb_frontend *fe, int offon);
 };
 
-#if IS_ENABLED(CONFIG_DVB_STV0900)
+#if IS_REACHABLE(CONFIG_DVB_STV0900)
 extern struct dvb_frontend *stv0900_attach(const struct stv0900_config *config,
 					struct i2c_adapter *i2c, int demod);
 #else
diff --git a/drivers/media/dvb-frontends/stv090x.h b/drivers/media/dvb-frontends/stv090x.h
index 0bd6adcfee8..97ada6b246b 100644
--- a/drivers/media/dvb-frontends/stv090x.h
+++ b/drivers/media/dvb-frontends/stv090x.h
@@ -103,7 +103,7 @@ struct stv090x_config {
 	void (*tuner_i2c_lock) (struct dvb_frontend *fe, int lock);
 };
 
-#if IS_ENABLED(CONFIG_DVB_STV090x)
+#if IS_REACHABLE(CONFIG_DVB_STV090x)
 
 extern struct dvb_frontend *stv090x_attach(const struct stv090x_config *config,
 					   struct i2c_adapter *i2c,
diff --git a/drivers/media/dvb-frontends/stv6110.h b/drivers/media/dvb-frontends/stv6110.h
index 8fa07e6a674..f3c8a5c6b77 100644
--- a/drivers/media/dvb-frontends/stv6110.h
+++ b/drivers/media/dvb-frontends/stv6110.h
@@ -46,7 +46,7 @@ struct stv6110_config {
 	u8 clk_div;	/* divisor value for the output clock */
 };
 
-#if IS_ENABLED(CONFIG_DVB_STV6110)
+#if IS_REACHABLE(CONFIG_DVB_STV6110)
 extern struct dvb_frontend *stv6110_attach(struct dvb_frontend *fe,
 					const struct stv6110_config *config,
 					struct i2c_adapter *i2c);
diff --git a/drivers/media/dvb-frontends/stv6110x.h b/drivers/media/dvb-frontends/stv6110x.h
index bc4766db29c..9f7eb251aec 100644
--- a/drivers/media/dvb-frontends/stv6110x.h
+++ b/drivers/media/dvb-frontends/stv6110x.h
@@ -53,7 +53,7 @@ struct stv6110x_devctl {
 };
 
 
-#if IS_ENABLED(CONFIG_DVB_STV6110x)
+#if IS_REACHABLE(CONFIG_DVB_STV6110x)
 
 extern struct stv6110x_devctl *stv6110x_attach(struct dvb_frontend *fe,
 					       const struct stv6110x_config *config,
diff --git a/drivers/media/dvb-frontends/tda1002x.h b/drivers/media/dvb-frontends/tda1002x.h
index e404b6e4480..0d334613de1 100644
--- a/drivers/media/dvb-frontends/tda1002x.h
+++ b/drivers/media/dvb-frontends/tda1002x.h
@@ -57,7 +57,7 @@ struct tda10023_config {
 	u16 deltaf;
 };
 
-#if IS_ENABLED(CONFIG_DVB_TDA10021)
+#if IS_REACHABLE(CONFIG_DVB_TDA10021)
 extern struct dvb_frontend* tda10021_attach(const struct tda1002x_config* config,
 					    struct i2c_adapter* i2c, u8 pwm);
 #else
@@ -69,7 +69,7 @@ static inline struct dvb_frontend* tda10021_attach(const struct tda1002x_config*
 }
 #endif // CONFIG_DVB_TDA10021
 
-#if IS_ENABLED(CONFIG_DVB_TDA10023)
+#if IS_REACHABLE(CONFIG_DVB_TDA10023)
 extern struct dvb_frontend *tda10023_attach(
 	const struct tda10023_config *config,
 	struct i2c_adapter *i2c, u8 pwm);
diff --git a/drivers/media/dvb-frontends/tda10048.h b/drivers/media/dvb-frontends/tda10048.h
index 5e7bf4e47cb..bc77a7311de 100644
--- a/drivers/media/dvb-frontends/tda10048.h
+++ b/drivers/media/dvb-frontends/tda10048.h
@@ -73,7 +73,7 @@ struct tda10048_config {
 	u8 pll_n;
 };
 
-#if IS_ENABLED(CONFIG_DVB_TDA10048)
+#if IS_REACHABLE(CONFIG_DVB_TDA10048)
 extern struct dvb_frontend *tda10048_attach(
 	const struct tda10048_config *config,
 	struct i2c_adapter *i2c);
diff --git a/drivers/media/dvb-frontends/tda1004x.h b/drivers/media/dvb-frontends/tda1004x.h
index dd283fbb61c..efd7659dace 100644
--- a/drivers/media/dvb-frontends/tda1004x.h
+++ b/drivers/media/dvb-frontends/tda1004x.h
@@ -117,7 +117,7 @@ struct tda1004x_state {
 	enum tda1004x_demod demod_type;
 };
 
-#if IS_ENABLED(CONFIG_DVB_TDA1004X)
+#if IS_REACHABLE(CONFIG_DVB_TDA1004X)
 extern struct dvb_frontend* tda10045_attach(const struct tda1004x_config* config,
 					    struct i2c_adapter* i2c);
 
diff --git a/drivers/media/dvb-frontends/tda10071.h b/drivers/media/dvb-frontends/tda10071.h
index 331b5a81938..da89f424984 100644
--- a/drivers/media/dvb-frontends/tda10071.h
+++ b/drivers/media/dvb-frontends/tda10071.h
@@ -72,7 +72,7 @@ struct tda10071_config {
 };
 
 
-#if IS_ENABLED(CONFIG_DVB_TDA10071)
+#if IS_REACHABLE(CONFIG_DVB_TDA10071)
 extern struct dvb_frontend *tda10071_attach(
 	const struct tda10071_config *config, struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/tda10086.h b/drivers/media/dvb-frontends/tda10086.h
index 458fe91c1b8..690e469995b 100644
--- a/drivers/media/dvb-frontends/tda10086.h
+++ b/drivers/media/dvb-frontends/tda10086.h
@@ -46,7 +46,7 @@ struct tda10086_config
 	enum tda10086_xtal xtal_freq;
 };
 
-#if IS_ENABLED(CONFIG_DVB_TDA10086)
+#if IS_REACHABLE(CONFIG_DVB_TDA10086)
 extern struct dvb_frontend* tda10086_attach(const struct tda10086_config* config,
 					    struct i2c_adapter* i2c);
 #else
diff --git a/drivers/media/dvb-frontends/tda18271c2dd.h b/drivers/media/dvb-frontends/tda18271c2dd.h
index dd84f7b69be..7ebd8eaff4e 100644
--- a/drivers/media/dvb-frontends/tda18271c2dd.h
+++ b/drivers/media/dvb-frontends/tda18271c2dd.h
@@ -3,7 +3,7 @@
 
 #include <linux/kconfig.h>
 
-#if IS_ENABLED(CONFIG_DVB_TDA18271C2DD)
+#if IS_REACHABLE(CONFIG_DVB_TDA18271C2DD)
 struct dvb_frontend *tda18271c2dd_attach(struct dvb_frontend *fe,
 					 struct i2c_adapter *i2c, u8 adr);
 #else
diff --git a/drivers/media/dvb-frontends/tda665x.h b/drivers/media/dvb-frontends/tda665x.h
index 03a0da6d5cf..baf520baa42 100644
--- a/drivers/media/dvb-frontends/tda665x.h
+++ b/drivers/media/dvb-frontends/tda665x.h
@@ -31,7 +31,7 @@ struct tda665x_config {
 	u32	ref_divider;
 };
 
-#if IS_ENABLED(CONFIG_DVB_TDA665x)
+#if IS_REACHABLE(CONFIG_DVB_TDA665x)
 
 extern struct dvb_frontend *tda665x_attach(struct dvb_frontend *fe,
 					   const struct tda665x_config *config,
diff --git a/drivers/media/dvb-frontends/tda8083.h b/drivers/media/dvb-frontends/tda8083.h
index de6b1860dfd..46be06fa7e0 100644
--- a/drivers/media/dvb-frontends/tda8083.h
+++ b/drivers/media/dvb-frontends/tda8083.h
@@ -35,7 +35,7 @@ struct tda8083_config
 	u8 demod_address;
 };
 
-#if IS_ENABLED(CONFIG_DVB_TDA8083)
+#if IS_REACHABLE(CONFIG_DVB_TDA8083)
 extern struct dvb_frontend* tda8083_attach(const struct tda8083_config* config,
 					   struct i2c_adapter* i2c);
 #else
diff --git a/drivers/media/dvb-frontends/tda8261.h b/drivers/media/dvb-frontends/tda8261.h
index 55cf4ffcbfd..9fa5b3076d5 100644
--- a/drivers/media/dvb-frontends/tda8261.h
+++ b/drivers/media/dvb-frontends/tda8261.h
@@ -34,7 +34,7 @@ struct tda8261_config {
 	enum tda8261_step	step_size;
 };
 
-#if IS_ENABLED(CONFIG_DVB_TDA8261)
+#if IS_REACHABLE(CONFIG_DVB_TDA8261)
 
 extern struct dvb_frontend *tda8261_attach(struct dvb_frontend *fe,
 					   const struct tda8261_config *config,
diff --git a/drivers/media/dvb-frontends/tda826x.h b/drivers/media/dvb-frontends/tda826x.h
index 5f0f20e7e4f..81abe1aebe9 100644
--- a/drivers/media/dvb-frontends/tda826x.h
+++ b/drivers/media/dvb-frontends/tda826x.h
@@ -35,7 +35,7 @@
  * @param has_loopthrough Set to 1 if the card has a loopthrough RF connector.
  * @return FE pointer on success, NULL on failure.
  */
-#if IS_ENABLED(CONFIG_DVB_TDA826X)
+#if IS_REACHABLE(CONFIG_DVB_TDA826X)
 extern struct dvb_frontend* tda826x_attach(struct dvb_frontend *fe, int addr,
 					   struct i2c_adapter *i2c,
 					   int has_loopthrough);
diff --git a/drivers/media/dvb-frontends/ts2020.h b/drivers/media/dvb-frontends/ts2020.h
index b2fe6bb3a38..595841def66 100644
--- a/drivers/media/dvb-frontends/ts2020.h
+++ b/drivers/media/dvb-frontends/ts2020.h
@@ -31,7 +31,7 @@ struct ts2020_config {
 	u32 frequency_div;
 };
 
-#if IS_ENABLED(CONFIG_DVB_TS2020)
+#if IS_REACHABLE(CONFIG_DVB_TS2020)
 
 extern struct dvb_frontend *ts2020_attach(
 	struct dvb_frontend *fe,
diff --git a/drivers/media/dvb-frontends/tua6100.h b/drivers/media/dvb-frontends/tua6100.h
index 83a9c30e67c..52919e04e25 100644
--- a/drivers/media/dvb-frontends/tua6100.h
+++ b/drivers/media/dvb-frontends/tua6100.h
@@ -34,7 +34,7 @@
 #include <linux/i2c.h>
 #include "dvb_frontend.h"
 
-#if IS_ENABLED(CONFIG_DVB_TUA6100)
+#if IS_REACHABLE(CONFIG_DVB_TUA6100)
 extern struct dvb_frontend *tua6100_attach(struct dvb_frontend *fe, int addr, struct i2c_adapter *i2c);
 #else
 static inline struct dvb_frontend* tua6100_attach(struct dvb_frontend *fe, int addr, struct i2c_adapter *i2c)
diff --git a/drivers/media/dvb-frontends/ves1820.h b/drivers/media/dvb-frontends/ves1820.h
index c073f353ac3..ece46fdcd71 100644
--- a/drivers/media/dvb-frontends/ves1820.h
+++ b/drivers/media/dvb-frontends/ves1820.h
@@ -41,7 +41,7 @@ struct ves1820_config
 	u8 selagc:1;
 };
 
-#if IS_ENABLED(CONFIG_DVB_VES1820)
+#if IS_REACHABLE(CONFIG_DVB_VES1820)
 extern struct dvb_frontend* ves1820_attach(const struct ves1820_config* config,
 					   struct i2c_adapter* i2c, u8 pwm);
 #else
diff --git a/drivers/media/dvb-frontends/ves1x93.h b/drivers/media/dvb-frontends/ves1x93.h
index 2307caea6ae..4510fe2f667 100644
--- a/drivers/media/dvb-frontends/ves1x93.h
+++ b/drivers/media/dvb-frontends/ves1x93.h
@@ -40,7 +40,7 @@ struct ves1x93_config
 	u8 invert_pwm:1;
 };
 
-#if IS_ENABLED(CONFIG_DVB_VES1X93)
+#if IS_REACHABLE(CONFIG_DVB_VES1X93)
 extern struct dvb_frontend* ves1x93_attach(const struct ves1x93_config* config,
 					   struct i2c_adapter* i2c);
 #else
diff --git a/drivers/media/dvb-frontends/zl10036.h b/drivers/media/dvb-frontends/zl10036.h
index 5f1e8217eeb..670e76a654e 100644
--- a/drivers/media/dvb-frontends/zl10036.h
+++ b/drivers/media/dvb-frontends/zl10036.h
@@ -38,7 +38,7 @@ struct zl10036_config {
 	int rf_loop_enable;
 };
 
-#if IS_ENABLED(CONFIG_DVB_ZL10036)
+#if IS_REACHABLE(CONFIG_DVB_ZL10036)
 extern struct dvb_frontend *zl10036_attach(struct dvb_frontend *fe,
 	const struct zl10036_config *config, struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/dvb-frontends/zl10039.h b/drivers/media/dvb-frontends/zl10039.h
index 750b9bca9d0..070929444e7 100644
--- a/drivers/media/dvb-frontends/zl10039.h
+++ b/drivers/media/dvb-frontends/zl10039.h
@@ -24,7 +24,7 @@
 
 #include <linux/kconfig.h>
 
-#if IS_ENABLED(CONFIG_DVB_ZL10039)
+#if IS_REACHABLE(CONFIG_DVB_ZL10039)
 struct dvb_frontend *zl10039_attach(struct dvb_frontend *fe,
 					u8 i2c_addr,
 					struct i2c_adapter *i2c);
diff --git a/drivers/media/dvb-frontends/zl10353.h b/drivers/media/dvb-frontends/zl10353.h
index 50c1004aef3..37aa6e8f454 100644
--- a/drivers/media/dvb-frontends/zl10353.h
+++ b/drivers/media/dvb-frontends/zl10353.h
@@ -47,7 +47,7 @@ struct zl10353_config
 	u8 pll_0;        /* default: 0x15 */
 };
 
-#if IS_ENABLED(CONFIG_DVB_ZL10353)
+#if IS_REACHABLE(CONFIG_DVB_ZL10353)
 extern struct dvb_frontend* zl10353_attach(const struct zl10353_config *config,
 					   struct i2c_adapter *i2c);
 #else
diff --git a/drivers/media/i2c/smiapp-pll.c b/drivers/media/i2c/smiapp-pll.c
index 2335529b195..ab5d9a3adeb 100644
--- a/drivers/media/i2c/smiapp-pll.c
+++ b/drivers/media/i2c/smiapp-pll.c
@@ -67,7 +67,7 @@ static void print_pll(struct device *dev, struct smiapp_pll *pll)
 {
 	dev_dbg(dev, "pre_pll_clk_div\t%d\n",  pll->pre_pll_clk_div);
 	dev_dbg(dev, "pll_multiplier \t%d\n",  pll->pll_multiplier);
-	if (pll->flags != SMIAPP_PLL_FLAG_NO_OP_CLOCKS) {
+	if (!(pll->flags & SMIAPP_PLL_FLAG_NO_OP_CLOCKS)) {
 		dev_dbg(dev, "op_sys_clk_div \t%d\n", pll->op_sys_clk_div);
 		dev_dbg(dev, "op_pix_clk_div \t%d\n", pll->op_pix_clk_div);
 	}
@@ -77,7 +77,7 @@ static void print_pll(struct device *dev, struct smiapp_pll *pll)
 	dev_dbg(dev, "ext_clk_freq_hz \t%d\n", pll->ext_clk_freq_hz);
 	dev_dbg(dev, "pll_ip_clk_freq_hz \t%d\n", pll->pll_ip_clk_freq_hz);
 	dev_dbg(dev, "pll_op_clk_freq_hz \t%d\n", pll->pll_op_clk_freq_hz);
-	if (pll->flags & SMIAPP_PLL_FLAG_NO_OP_CLOCKS) {
+	if (!(pll->flags & SMIAPP_PLL_FLAG_NO_OP_CLOCKS)) {
 		dev_dbg(dev, "op_sys_clk_freq_hz \t%d\n",
 			pll->op_sys_clk_freq_hz);
 		dev_dbg(dev, "op_pix_clk_freq_hz \t%d\n",
diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c
index b10aaeda2bb..b49254e4ea0 100644
--- a/drivers/media/i2c/smiapp/smiapp-core.c
+++ b/drivers/media/i2c/smiapp/smiapp-core.c
@@ -2677,7 +2677,9 @@ static int smiapp_registered(struct v4l2_subdev *subdev)
 		pll->flags |= SMIAPP_PLL_FLAG_NO_OP_CLOCKS;
 	pll->scale_n = sensor->limits[SMIAPP_LIMIT_SCALER_N_MIN];
 
+	mutex_lock(&sensor->mutex);
 	rval = smiapp_update_mode(sensor);
+	mutex_unlock(&sensor->mutex);
 	if (rval) {
 		dev_err(&client->dev, "update mode failed\n");
 		goto out_nvm_release;
diff --git a/drivers/media/pci/cx23885/altera-ci.h b/drivers/media/pci/cx23885/altera-ci.h
index 5028f0cf83f..6c511723fd1 100644
--- a/drivers/media/pci/cx23885/altera-ci.h
+++ b/drivers/media/pci/cx23885/altera-ci.h
@@ -39,7 +39,7 @@ struct altera_ci_config {
 	int (*fpga_rw) (void *dev, int ad_rg, int val, int rw);
 };
 
-#if IS_ENABLED(CONFIG_MEDIA_ALTERA_CI)
+#if IS_REACHABLE(CONFIG_MEDIA_ALTERA_CI)
 
 extern int altera_ci_init(struct altera_ci_config *config, int ci_nr);
 extern void altera_ci_release(void *dev, int ci_nr);
diff --git a/drivers/media/pci/cx23885/cx23885-cards.c b/drivers/media/pci/cx23885/cx23885-cards.c
index 88c257d1161..377818887ed 100644
--- a/drivers/media/pci/cx23885/cx23885-cards.c
+++ b/drivers/media/pci/cx23885/cx23885-cards.c
@@ -614,7 +614,7 @@ struct cx23885_board cx23885_boards[] = {
 		.portb		= CX23885_MPEG_DVB,
 	},
 	[CX23885_BOARD_HAUPPAUGE_HVR4400] = {
-		.name		= "Hauppauge WinTV-HVR4400",
+		.name		= "Hauppauge WinTV-HVR4400/HVR5500",
 		.porta		= CX23885_ANALOG_VIDEO,
 		.portb		= CX23885_MPEG_DVB,
 		.portc		= CX23885_MPEG_DVB,
@@ -622,6 +622,10 @@ struct cx23885_board cx23885_boards[] = {
 		.tuner_addr	= 0x60, /* 0xc0 >> 1 */
 		.tuner_bus	= 1,
 	},
+	[CX23885_BOARD_HAUPPAUGE_STARBURST] = {
+		.name		= "Hauppauge WinTV Starburst",
+		.portb		= CX23885_MPEG_DVB,
+	},
 	[CX23885_BOARD_AVERMEDIA_HC81R] = {
 		.name		= "AVerTV Hybrid Express Slim HC81R",
 		.tuner_type	= TUNER_XC2028,
@@ -910,19 +914,19 @@ struct cx23885_subid cx23885_subids[] = {
 	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0xc108,
-		.card      = CX23885_BOARD_HAUPPAUGE_HVR4400,
+		.card      = CX23885_BOARD_HAUPPAUGE_HVR4400, /* Hauppauge WinTV HVR-4400 (Model 121xxx, Hybrid DVB-T/S2, IR) */
 	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0xc138,
-		.card      = CX23885_BOARD_HAUPPAUGE_HVR4400,
+		.card      = CX23885_BOARD_HAUPPAUGE_HVR4400, /* Hauppauge WinTV HVR-5500 (Model 121xxx, Hybrid DVB-T/C/S2, IR) */
 	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0xc12a,
-		.card      = CX23885_BOARD_HAUPPAUGE_HVR4400,
+		.card      = CX23885_BOARD_HAUPPAUGE_STARBURST, /* Hauppauge WinTV Starburst (Model 121x00, DVB-S2, IR) */
 	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0xc1f8,
-		.card      = CX23885_BOARD_HAUPPAUGE_HVR4400,
+		.card      = CX23885_BOARD_HAUPPAUGE_HVR4400, /* Hauppauge WinTV HVR-5500 (Model 121xxx, Hybrid DVB-T/C/S2, IR) */
 	}, {
 		.subvendor = 0x1461,
 		.subdevice = 0xd939,
@@ -1495,8 +1499,9 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 		cx_write(GPIO_ISM, 0x00000000);/* INTERRUPTS active low*/
 		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR4400:
+	case CX23885_BOARD_HAUPPAUGE_STARBURST:
 		/* GPIO-8 tda10071 demod reset */
-		/* GPIO-9 si2165 demod reset */
+		/* GPIO-9 si2165 demod reset (only HVR4400/HVR5500)*/
 
 		/* Put the parts into reset and back */
 		cx23885_gpio_enable(dev, GPIO_8 | GPIO_9, 1);
@@ -1760,6 +1765,7 @@ void cx23885_card_setup(struct cx23885_dev *dev)
 	case CX23885_BOARD_HAUPPAUGE_HVR1850:
 	case CX23885_BOARD_HAUPPAUGE_HVR1290:
 	case CX23885_BOARD_HAUPPAUGE_HVR4400:
+	case CX23885_BOARD_HAUPPAUGE_STARBURST:
 	case CX23885_BOARD_HAUPPAUGE_IMPACTVCBE:
 		if (dev->i2c_bus[0].i2c_rc == 0)
 			hauppauge_eeprom(dev, eeprom+0xc0);
@@ -1864,6 +1870,11 @@ void cx23885_card_setup(struct cx23885_dev *dev)
 		ts2->ts_clk_en_val = 0x1; /* Enable TS_CLK */
 		ts2->src_sel_val   = CX23885_SRC_SEL_PARALLEL_MPEG_VIDEO;
 		break;
+	case CX23885_BOARD_HAUPPAUGE_STARBURST:
+		ts1->gen_ctrl_val  = 0xc; /* Serial bus + punctured clock */
+		ts1->ts_clk_en_val = 0x1; /* Enable TS_CLK */
+		ts1->src_sel_val   = CX23885_SRC_SEL_PARALLEL_MPEG_VIDEO;
+		break;
 	case CX23885_BOARD_DVBSKY_T9580:
 		ts1->gen_ctrl_val  = 0x5; /* Parallel */
 		ts1->ts_clk_en_val = 0x1; /* Enable TS_CLK */
diff --git a/drivers/media/pci/cx23885/cx23885-dvb.c b/drivers/media/pci/cx23885/cx23885-dvb.c
index 4cb90317ff4..a8d20792929 100644
--- a/drivers/media/pci/cx23885/cx23885-dvb.c
+++ b/drivers/media/pci/cx23885/cx23885-dvb.c
@@ -1586,6 +1586,17 @@ static int dvb_register(struct cx23885_tsport *port)
 			break;
 		}
 		break;
+	case CX23885_BOARD_HAUPPAUGE_STARBURST:
+		i2c_bus = &dev->i2c_bus[0];
+		fe0->dvb.frontend = dvb_attach(tda10071_attach,
+						&hauppauge_tda10071_config,
+						&i2c_bus->i2c_adap);
+		if (fe0->dvb.frontend != NULL) {
+			dvb_attach(a8293_attach, fe0->dvb.frontend,
+				   &i2c_bus->i2c_adap,
+				   &hauppauge_a8293_config);
+		}
+		break;
 	case CX23885_BOARD_DVBSKY_T9580:
 		i2c_bus = &dev->i2c_bus[0];
 		i2c_bus2 = &dev->i2c_bus[1];
diff --git a/drivers/media/pci/cx23885/cx23885.h b/drivers/media/pci/cx23885/cx23885.h
index 6c35e611596..a33bead82ec 100644
--- a/drivers/media/pci/cx23885/cx23885.h
+++ b/drivers/media/pci/cx23885/cx23885.h
@@ -93,6 +93,7 @@
 #define CX23885_BOARD_HAUPPAUGE_IMPACTVCBE     43
 #define CX23885_BOARD_DVICO_FUSIONHDTV_DVB_T_DUAL_EXP2 44
 #define CX23885_BOARD_DVBSKY_T9580             45
+#define CX23885_BOARD_HAUPPAUGE_STARBURST      52
 
 #define GPIO_0 0x00000001
 #define GPIO_1 0x00000002
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 3aac88f1d54..736277236ba 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -56,10 +56,8 @@ config VIDEO_VIU
 
 config VIDEO_TIMBERDALE
 	tristate "Support for timberdale Video In/LogiWIN"
-	depends on VIDEO_V4L2 && I2C && DMADEVICES
-	depends on MFD_TIMBERDALE || COMPILE_TEST
-	select DMA_ENGINE
-	select TIMB_DMA
+	depends on VIDEO_V4L2 && I2C
+	depends on (MFD_TIMBERDALE && TIMB_DMA) || COMPILE_TEST
 	select VIDEO_ADV7180
 	select VIDEOBUF_DMA_CONTIG
 	---help---
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
index 3e41ca1293e..6849c7e79bb 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
@@ -29,7 +29,7 @@
 
 /* Offset base used to differentiate between CAPTURE and OUTPUT
 *  while mmaping */
-#define DST_QUEUE_OFF_BASE      (TASK_SIZE / 2)
+#define DST_QUEUE_OFF_BASE	(1 << 30)
 
 #define MFC_BANK1_ALLOC_CTX	0
 #define MFC_BANK2_ALLOC_CTX	1
diff --git a/drivers/media/platform/sh_veu.c b/drivers/media/platform/sh_veu.c
index be3b3bc71a0..54cb88a39af 100644
--- a/drivers/media/platform/sh_veu.c
+++ b/drivers/media/platform/sh_veu.c
@@ -1179,6 +1179,7 @@ static int sh_veu_probe(struct platform_device *pdev)
 	}
 
 	*vdev = sh_veu_videodev;
+	vdev->v4l2_dev = &veu->v4l2_dev;
 	spin_lock_init(&veu->lock);
 	mutex_init(&veu->fop_lock);
 	vdev->lock = &veu->fop_lock;
diff --git a/drivers/media/platform/soc_camera/soc_camera.c b/drivers/media/platform/soc_camera/soc_camera.c
index 8e61b976da1..139704727e3 100644
--- a/drivers/media/platform/soc_camera/soc_camera.c
+++ b/drivers/media/platform/soc_camera/soc_camera.c
@@ -1681,7 +1681,7 @@ eclkreg:
 eaddpdev:
 	platform_device_put(sasc->pdev);
 eallocpdev:
-	devm_kfree(ici->v4l2_dev.dev, sasc);
+	devm_kfree(ici->v4l2_dev.dev, info);
 	dev_err(ici->v4l2_dev.dev, "group probe failed: %d\n", ret);
 
 	return ret;
diff --git a/drivers/media/platform/vivid/vivid-vid-out.c b/drivers/media/platform/vivid/vivid-vid-out.c
index 69c2dbd2d16..501d5ef682e 100644
--- a/drivers/media/platform/vivid/vivid-vid-out.c
+++ b/drivers/media/platform/vivid/vivid-vid-out.c
@@ -612,7 +612,7 @@ int vivid_vid_out_g_selection(struct file *file, void *priv,
 		sel->r = dev->fmt_out_rect;
 		break;
 	case V4L2_SEL_TGT_CROP_BOUNDS:
-		if (!dev->has_compose_out)
+		if (!dev->has_crop_out)
 			return -EINVAL;
 		sel->r = vivid_max_rect;
 		break;
diff --git a/drivers/media/rc/img-ir/img-ir-core.c b/drivers/media/rc/img-ir/img-ir-core.c
index a0cac2f0910..9971dda621f 100644
--- a/drivers/media/rc/img-ir/img-ir-core.c
+++ b/drivers/media/rc/img-ir/img-ir-core.c
@@ -146,7 +146,7 @@ static int img_ir_remove(struct platform_device *pdev)
 {
 	struct img_ir_priv *priv = platform_get_drvdata(pdev);
 
-	free_irq(priv->irq, img_ir_isr);
+	free_irq(priv->irq, priv);
 	img_ir_remove_hw(priv);
 	img_ir_remove_raw(priv);
 
diff --git a/drivers/media/rc/img-ir/img-ir-hw.c b/drivers/media/rc/img-ir/img-ir-hw.c
index ec49f94425f..2fd47c9bf5d 100644
--- a/drivers/media/rc/img-ir/img-ir-hw.c
+++ b/drivers/media/rc/img-ir/img-ir-hw.c
@@ -530,6 +530,22 @@ static void img_ir_set_decoder(struct img_ir_priv *priv,
 	u32 ir_status, irq_en;
 	spin_lock_irq(&priv->lock);
 
+	/*
+	 * First record that the protocol is being stopped so that the end timer
+	 * isn't restarted while we're trying to stop it.
+	 */
+	hw->stopping = true;
+
+	/*
+	 * Release the lock to stop the end timer, since the end timer handler
+	 * acquires the lock and we don't want to deadlock waiting for it.
+	 */
+	spin_unlock_irq(&priv->lock);
+	del_timer_sync(&hw->end_timer);
+	spin_lock_irq(&priv->lock);
+
+	hw->stopping = false;
+
 	/* switch off and disable interrupts */
 	img_ir_write(priv, IMG_IR_CONTROL, 0);
 	irq_en = img_ir_read(priv, IMG_IR_IRQ_ENABLE);
@@ -541,12 +557,13 @@ static void img_ir_set_decoder(struct img_ir_priv *priv,
 	if (ir_status & (IMG_IR_RXDVAL | IMG_IR_RXDVALD2)) {
 		ir_status &= ~(IMG_IR_RXDVAL | IMG_IR_RXDVALD2);
 		img_ir_write(priv, IMG_IR_STATUS, ir_status);
-		img_ir_read(priv, IMG_IR_DATA_LW);
-		img_ir_read(priv, IMG_IR_DATA_UP);
 	}
 
-	/* stop the end timer and switch back to normal mode */
-	del_timer_sync(&hw->end_timer);
+	/* always read data to clear buffer if IR wakes the device */
+	img_ir_read(priv, IMG_IR_DATA_LW);
+	img_ir_read(priv, IMG_IR_DATA_UP);
+
+	/* switch back to normal mode */
 	hw->mode = IMG_IR_M_NORMAL;
 
 	/* clear the wakeup scancode filter */
@@ -817,7 +834,8 @@ static void img_ir_handle_data(struct img_ir_priv *priv, u32 len, u64 raw)
 	}
 
 
-	if (dec->repeat) {
+	/* we mustn't update the end timer while trying to stop it */
+	if (dec->repeat && !hw->stopping) {
 		unsigned long interval;
 
 		img_ir_begin_repeat(priv);
diff --git a/drivers/media/rc/img-ir/img-ir-hw.h b/drivers/media/rc/img-ir/img-ir-hw.h
index 8fcc16c32c5..307ddcd1a99 100644
--- a/drivers/media/rc/img-ir/img-ir-hw.h
+++ b/drivers/media/rc/img-ir/img-ir-hw.h
@@ -214,6 +214,8 @@ enum img_ir_mode {
  * @flags:		IMG_IR_F_*.
  * @filters:		HW filters (derived from scancode filters).
  * @mode:		Current decode mode.
+ * @stopping:		Indicates that decoder is being taken down and timers
+ *			should not be restarted.
  * @suspend_irqen:	Saved IRQ enable mask over suspend.
  */
 struct img_ir_priv_hw {
@@ -229,6 +231,7 @@ struct img_ir_priv_hw {
 	struct img_ir_filter		filters[RC_FILTER_MAX];
 
 	enum img_ir_mode		mode;
+	bool				stopping;
 	u32				suspend_irqen;
 };
 
diff --git a/drivers/media/rc/ir-lirc-codec.c b/drivers/media/rc/ir-lirc-codec.c
index ed2c8a1ed8c..98893a8332c 100644
--- a/drivers/media/rc/ir-lirc-codec.c
+++ b/drivers/media/rc/ir-lirc-codec.c
@@ -42,11 +42,17 @@ static int ir_lirc_decode(struct rc_dev *dev, struct ir_raw_event ev)
 		return -EINVAL;
 
 	/* Packet start */
-	if (ev.reset)
-		return 0;
+	if (ev.reset) {
+		/* Userspace expects a long space event before the start of
+		 * the signal to use as a sync.  This may be done with repeat
+		 * packets and normal samples.  But if a reset has been sent
+		 * then we assume that a long time has passed, so we send a
+		 * space with the maximum time value. */
+		sample = LIRC_SPACE(LIRC_VALUE_MASK);
+		IR_dprintk(2, "delivering reset sync space to lirc_dev\n");
 
 	/* Carrier reports */
-	if (ev.carrier_report) {
+	} else if (ev.carrier_report) {
 		sample = LIRC_FREQUENCY(ev.carrier);
 		IR_dprintk(2, "carrier report (freq: %d)\n", sample);
 
diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index 8d3b74c5a71..fc369b03348 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -1021,16 +1021,16 @@ static ssize_t store_protocols(struct device *device,
 		goto out;
 	}
 
-	if (new_protocols == old_protocols) {
-		rc = len;
-		goto out;
+	if (new_protocols != old_protocols) {
+		*current_protocols = new_protocols;
+		IR_dprintk(1, "Protocols changed to 0x%llx\n",
+			   (long long)new_protocols);
 	}
 
-	*current_protocols = new_protocols;
-	IR_dprintk(1, "Protocols changed to 0x%llx\n", (long long)new_protocols);
-
 	/*
-	 * If the protocol is changed the filter needs updating.
+	 * If a protocol change was attempted the filter may need updating, even
+	 * if the actual protocol mask hasn't changed (since the driver may have
+	 * cleared the filter).
 	 * Try setting the same filter with the new protocol (if any).
 	 * Fall back to clearing the filter.
 	 */
diff --git a/drivers/media/tuners/fc0011.h b/drivers/media/tuners/fc0011.h
index 43ec893a687..81bb568d694 100644
--- a/drivers/media/tuners/fc0011.h
+++ b/drivers/media/tuners/fc0011.h
@@ -23,7 +23,7 @@ enum fc0011_fe_callback_commands {
 	FC0011_FE_CALLBACK_RESET,
 };
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_FC0011)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_FC0011)
 struct dvb_frontend *fc0011_attach(struct dvb_frontend *fe,
 				   struct i2c_adapter *i2c,
 				   const struct fc0011_config *config);
diff --git a/drivers/media/tuners/fc0012.h b/drivers/media/tuners/fc0012.h
index 1d08057e327..9ad32859bab 100644
--- a/drivers/media/tuners/fc0012.h
+++ b/drivers/media/tuners/fc0012.h
@@ -49,7 +49,7 @@ struct fc0012_config {
 	bool clock_out;
 };
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_FC0012)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_FC0012)
 extern struct dvb_frontend *fc0012_attach(struct dvb_frontend *fe,
 					struct i2c_adapter *i2c,
 					const struct fc0012_config *cfg);
diff --git a/drivers/media/tuners/fc0013.h b/drivers/media/tuners/fc0013.h
index d65d5b37f56..e130bd7a323 100644
--- a/drivers/media/tuners/fc0013.h
+++ b/drivers/media/tuners/fc0013.h
@@ -26,7 +26,7 @@
 #include "dvb_frontend.h"
 #include "fc001x-common.h"
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_FC0013)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_FC0013)
 extern struct dvb_frontend *fc0013_attach(struct dvb_frontend *fe,
 					struct i2c_adapter *i2c,
 					u8 i2c_address, int dual_master,
diff --git a/drivers/media/tuners/fc2580.h b/drivers/media/tuners/fc2580.h
index 9c43c1cc82d..b1ce6770f88 100644
--- a/drivers/media/tuners/fc2580.h
+++ b/drivers/media/tuners/fc2580.h
@@ -37,7 +37,7 @@ struct fc2580_config {
 	u32 clock;
 };
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_FC2580)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_FC2580)
 extern struct dvb_frontend *fc2580_attach(struct dvb_frontend *fe,
 	struct i2c_adapter *i2c, const struct fc2580_config *cfg);
 #else
diff --git a/drivers/media/tuners/max2165.h b/drivers/media/tuners/max2165.h
index 26e1dc64bb6..5054f01a78f 100644
--- a/drivers/media/tuners/max2165.h
+++ b/drivers/media/tuners/max2165.h
@@ -32,7 +32,7 @@ struct max2165_config {
 	u8 osc_clk; /* in MHz, selectable values: 4,16,18,20,22,24,26,28 */
 };
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_MAX2165)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_MAX2165)
 extern struct dvb_frontend *max2165_attach(struct dvb_frontend *fe,
 	struct i2c_adapter *i2c,
 	struct max2165_config *cfg);
diff --git a/drivers/media/tuners/mc44s803.h b/drivers/media/tuners/mc44s803.h
index 9aae50aca2b..b3e614be657 100644
--- a/drivers/media/tuners/mc44s803.h
+++ b/drivers/media/tuners/mc44s803.h
@@ -32,7 +32,7 @@ struct mc44s803_config {
 	u8 dig_out;
 };
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_MC44S803)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_MC44S803)
 extern struct dvb_frontend *mc44s803_attach(struct dvb_frontend *fe,
 	 struct i2c_adapter *i2c, struct mc44s803_config *cfg);
 #else
diff --git a/drivers/media/tuners/mt2060.h b/drivers/media/tuners/mt2060.h
index c64fc19cb27..6efed359a24 100644
--- a/drivers/media/tuners/mt2060.h
+++ b/drivers/media/tuners/mt2060.h
@@ -30,7 +30,7 @@ struct mt2060_config {
 	u8 clock_out; /* 0 = off, 1 = CLK/4, 2 = CLK/2, 3 = CLK/1 */
 };
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_MT2060)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_MT2060)
 extern struct dvb_frontend * mt2060_attach(struct dvb_frontend *fe, struct i2c_adapter *i2c, struct mt2060_config *cfg, u16 if1);
 #else
 static inline struct dvb_frontend * mt2060_attach(struct dvb_frontend *fe, struct i2c_adapter *i2c, struct mt2060_config *cfg, u16 if1)
diff --git a/drivers/media/tuners/mt2063.h b/drivers/media/tuners/mt2063.h
index e1acfc8e7ae..e55e0a6dd1b 100644
--- a/drivers/media/tuners/mt2063.h
+++ b/drivers/media/tuners/mt2063.h
@@ -8,7 +8,7 @@ struct mt2063_config {
 	u32 refclock;
 };
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_MT2063)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_MT2063)
 struct dvb_frontend *mt2063_attach(struct dvb_frontend *fe,
 				   struct mt2063_config *config,
 				   struct i2c_adapter *i2c);
diff --git a/drivers/media/tuners/mt20xx.h b/drivers/media/tuners/mt20xx.h
index f56241ccaa0..9912362b415 100644
--- a/drivers/media/tuners/mt20xx.h
+++ b/drivers/media/tuners/mt20xx.h
@@ -20,7 +20,7 @@
 #include <linux/i2c.h>
 #include "dvb_frontend.h"
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_MT20XX)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_MT20XX)
 extern struct dvb_frontend *microtune_attach(struct dvb_frontend *fe,
 					     struct i2c_adapter* i2c_adap,
 					     u8 i2c_addr);
diff --git a/drivers/media/tuners/mt2131.h b/drivers/media/tuners/mt2131.h
index 09ceaf68e47..f5896c93197 100644
--- a/drivers/media/tuners/mt2131.h
+++ b/drivers/media/tuners/mt2131.h
@@ -30,7 +30,7 @@ struct mt2131_config {
 	u8 clock_out; /* 0 = off, 1 = CLK/4, 2 = CLK/2, 3 = CLK/1 */
 };
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_MT2131)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_MT2131)
 extern struct dvb_frontend* mt2131_attach(struct dvb_frontend *fe,
 					  struct i2c_adapter *i2c,
 					  struct mt2131_config *cfg,
diff --git a/drivers/media/tuners/mt2266.h b/drivers/media/tuners/mt2266.h
index fad6dd657d7..69abefa18c3 100644
--- a/drivers/media/tuners/mt2266.h
+++ b/drivers/media/tuners/mt2266.h
@@ -24,7 +24,7 @@ struct mt2266_config {
 	u8 i2c_address;
 };
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_MT2266)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_MT2266)
 extern struct dvb_frontend * mt2266_attach(struct dvb_frontend *fe, struct i2c_adapter *i2c, struct mt2266_config *cfg);
 #else
 static inline struct dvb_frontend * mt2266_attach(struct dvb_frontend *fe, struct i2c_adapter *i2c, struct mt2266_config *cfg)
diff --git a/drivers/media/tuners/mxl5005s.h b/drivers/media/tuners/mxl5005s.h
index ae8db885ad8..5764b12c5c7 100644
--- a/drivers/media/tuners/mxl5005s.h
+++ b/drivers/media/tuners/mxl5005s.h
@@ -118,7 +118,7 @@ struct mxl5005s_config {
 	u8 AgcMasterByte;
 };
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_MXL5005S)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_MXL5005S)
 extern struct dvb_frontend *mxl5005s_attach(struct dvb_frontend *fe,
 					    struct i2c_adapter *i2c,
 					    struct mxl5005s_config *config);
diff --git a/drivers/media/tuners/mxl5007t.h b/drivers/media/tuners/mxl5007t.h
index 37b0942e238..d4861d74152 100644
--- a/drivers/media/tuners/mxl5007t.h
+++ b/drivers/media/tuners/mxl5007t.h
@@ -77,7 +77,7 @@ struct mxl5007t_config {
 	unsigned int clk_out_enable:1;
 };
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_MXL5007T)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_MXL5007T)
 extern struct dvb_frontend *mxl5007t_attach(struct dvb_frontend *fe,
 					    struct i2c_adapter *i2c, u8 addr,
 					    struct mxl5007t_config *cfg);
diff --git a/drivers/media/tuners/qt1010.h b/drivers/media/tuners/qt1010.h
index 8ab5d479749..e3198f23437 100644
--- a/drivers/media/tuners/qt1010.h
+++ b/drivers/media/tuners/qt1010.h
@@ -36,7 +36,7 @@ struct qt1010_config {
  * @param cfg  tuner hw based configuration
  * @return fe  pointer on success, NULL on failure
  */
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_QT1010)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_QT1010)
 extern struct dvb_frontend *qt1010_attach(struct dvb_frontend *fe,
 					  struct i2c_adapter *i2c,
 					  struct qt1010_config *cfg);
diff --git a/drivers/media/tuners/r820t.h b/drivers/media/tuners/r820t.h
index 48af3548027..b1e5661af1c 100644
--- a/drivers/media/tuners/r820t.h
+++ b/drivers/media/tuners/r820t.h
@@ -42,7 +42,7 @@ struct r820t_config {
 	bool use_predetect;
 };
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_R820T)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_R820T)
 struct dvb_frontend *r820t_attach(struct dvb_frontend *fe,
 				  struct i2c_adapter *i2c,
 				  const struct r820t_config *cfg);
diff --git a/drivers/media/tuners/tda18218.h b/drivers/media/tuners/tda18218.h
index 366410e0cc9..1eacb4f84e9 100644
--- a/drivers/media/tuners/tda18218.h
+++ b/drivers/media/tuners/tda18218.h
@@ -30,7 +30,7 @@ struct tda18218_config {
 	u8 loop_through:1;
 };
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_TDA18218)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_TDA18218)
 extern struct dvb_frontend *tda18218_attach(struct dvb_frontend *fe,
 	struct i2c_adapter *i2c, struct tda18218_config *cfg);
 #else
diff --git a/drivers/media/tuners/tda18271.h b/drivers/media/tuners/tda18271.h
index 4c418d63f54..0a846333ce5 100644
--- a/drivers/media/tuners/tda18271.h
+++ b/drivers/media/tuners/tda18271.h
@@ -121,7 +121,7 @@ enum tda18271_mode {
 	TDA18271_DIGITAL,
 };
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_TDA18271)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_TDA18271)
 extern struct dvb_frontend *tda18271_attach(struct dvb_frontend *fe, u8 addr,
 					    struct i2c_adapter *i2c,
 					    struct tda18271_config *cfg);
diff --git a/drivers/media/tuners/tda827x.h b/drivers/media/tuners/tda827x.h
index b64292152ba..abf2e2fe535 100644
--- a/drivers/media/tuners/tda827x.h
+++ b/drivers/media/tuners/tda827x.h
@@ -51,7 +51,7 @@ struct tda827x_config
  * @param cfg optional callback function pointers.
  * @return FE pointer on success, NULL on failure.
  */
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_TDA827X)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_TDA827X)
 extern struct dvb_frontend* tda827x_attach(struct dvb_frontend *fe, int addr,
 					   struct i2c_adapter *i2c,
 					   struct tda827x_config *cfg);
diff --git a/drivers/media/tuners/tda8290.h b/drivers/media/tuners/tda8290.h
index cf96e585785..901b8cac710 100644
--- a/drivers/media/tuners/tda8290.h
+++ b/drivers/media/tuners/tda8290.h
@@ -38,7 +38,7 @@ struct tda829x_config {
 	struct tda18271_std_map *tda18271_std_map;
 };
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_TDA8290)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_TDA8290)
 extern int tda829x_probe(struct i2c_adapter *i2c_adap, u8 i2c_addr);
 
 extern struct dvb_frontend *tda829x_attach(struct dvb_frontend *fe,
diff --git a/drivers/media/tuners/tda9887.h b/drivers/media/tuners/tda9887.h
index 37a4a1123e0..95070eca02c 100644
--- a/drivers/media/tuners/tda9887.h
+++ b/drivers/media/tuners/tda9887.h
@@ -21,7 +21,7 @@
 #include "dvb_frontend.h"
 
 /* ------------------------------------------------------------------------ */
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_TDA9887)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_TDA9887)
 extern struct dvb_frontend *tda9887_attach(struct dvb_frontend *fe,
 					   struct i2c_adapter *i2c_adap,
 					   u8 i2c_addr);
diff --git a/drivers/media/tuners/tea5761.h b/drivers/media/tuners/tea5761.h
index 933228ffb50..2d624d9919e 100644
--- a/drivers/media/tuners/tea5761.h
+++ b/drivers/media/tuners/tea5761.h
@@ -20,7 +20,7 @@
 #include <linux/i2c.h>
 #include "dvb_frontend.h"
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_TEA5761)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_TEA5761)
 extern int tea5761_autodetection(struct i2c_adapter* i2c_adap, u8 i2c_addr);
 
 extern struct dvb_frontend *tea5761_attach(struct dvb_frontend *fe,
diff --git a/drivers/media/tuners/tea5767.h b/drivers/media/tuners/tea5767.h
index c3910119938..4f6f6c92db7 100644
--- a/drivers/media/tuners/tea5767.h
+++ b/drivers/media/tuners/tea5767.h
@@ -39,7 +39,7 @@ struct tea5767_ctrl {
 	enum tea5767_xtal	xtal_freq;
 };
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_TEA5767)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_TEA5767)
 extern int tea5767_autodetection(struct i2c_adapter* i2c_adap, u8 i2c_addr);
 
 extern struct dvb_frontend *tea5767_attach(struct dvb_frontend *fe,
diff --git a/drivers/media/tuners/tua9001.h b/drivers/media/tuners/tua9001.h
index 26358da1c10..2c3375c7aeb 100644
--- a/drivers/media/tuners/tua9001.h
+++ b/drivers/media/tuners/tua9001.h
@@ -51,7 +51,7 @@ struct tua9001_config {
 #define TUA9001_CMD_RESETN  1
 #define TUA9001_CMD_RXEN    2
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_TUA9001)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_TUA9001)
 extern struct dvb_frontend *tua9001_attach(struct dvb_frontend *fe,
 		struct i2c_adapter *i2c, struct tua9001_config *cfg);
 #else
diff --git a/drivers/media/tuners/tuner-simple.h b/drivers/media/tuners/tuner-simple.h
index ffd12cfe650..6399b45b059 100644
--- a/drivers/media/tuners/tuner-simple.h
+++ b/drivers/media/tuners/tuner-simple.h
@@ -20,7 +20,7 @@
 #include <linux/i2c.h>
 #include "dvb_frontend.h"
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_SIMPLE)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_SIMPLE)
 extern struct dvb_frontend *simple_tuner_attach(struct dvb_frontend *fe,
 						struct i2c_adapter *i2c_adap,
 						u8 i2c_addr,
diff --git a/drivers/media/tuners/tuner-xc2028.h b/drivers/media/tuners/tuner-xc2028.h
index 181d087faec..98e4effca89 100644
--- a/drivers/media/tuners/tuner-xc2028.h
+++ b/drivers/media/tuners/tuner-xc2028.h
@@ -56,7 +56,7 @@ struct xc2028_config {
 #define XC2028_RESET_CLK	1
 #define XC2028_I2C_FLUSH	2
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_XC2028)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_XC2028)
 extern struct dvb_frontend *xc2028_attach(struct dvb_frontend *fe,
 					  struct xc2028_config *cfg);
 #else
diff --git a/drivers/media/tuners/xc4000.h b/drivers/media/tuners/xc4000.h
index 97c23de5296..40517860cf6 100644
--- a/drivers/media/tuners/xc4000.h
+++ b/drivers/media/tuners/xc4000.h
@@ -50,7 +50,7 @@ struct xc4000_config {
  * it's passed back to a bridge during tuner_callback().
  */
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_XC4000)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_XC4000)
 extern struct dvb_frontend *xc4000_attach(struct dvb_frontend *fe,
 					  struct i2c_adapter *i2c,
 					  struct xc4000_config *cfg);
diff --git a/drivers/media/tuners/xc5000.h b/drivers/media/tuners/xc5000.h
index 7245cae19f0..f746a97e90b 100644
--- a/drivers/media/tuners/xc5000.h
+++ b/drivers/media/tuners/xc5000.h
@@ -57,7 +57,7 @@ struct xc5000_config {
  * it's passed back to a bridge during tuner_callback().
  */
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_XC5000)
+#if IS_REACHABLE(CONFIG_MEDIA_TUNER_XC5000)
 extern struct dvb_frontend *xc5000_attach(struct dvb_frontend *fe,
 					  struct i2c_adapter *i2c,
 					  const struct xc5000_config *cfg);
diff --git a/drivers/media/usb/au0828/au0828-cards.c b/drivers/media/usb/au0828/au0828-cards.c
index 9eb77ac2153..da87f1cc31a 100644
--- a/drivers/media/usb/au0828/au0828-cards.c
+++ b/drivers/media/usb/au0828/au0828-cards.c
@@ -36,6 +36,11 @@ static void hvr950q_cs5340_audio(void *priv, int enable)
 		au0828_clear(dev, REG_000, 0x10);
 }
 
+/*
+ * WARNING: There's a quirks table at sound/usb/quirks-table.h
+ * that should also be updated every time a new device with V4L2 support
+ * is added here.
+ */
 struct au0828_board au0828_boards[] = {
 	[AU0828_BOARD_UNKNOWN] = {
 		.name	= "Unknown board",
diff --git a/drivers/media/usb/dvb-usb-v2/lmedm04.c b/drivers/media/usb/dvb-usb-v2/lmedm04.c
index 9f2c5459b73..2273ce78f5c 100644
--- a/drivers/media/usb/dvb-usb-v2/lmedm04.c
+++ b/drivers/media/usb/dvb-usb-v2/lmedm04.c
@@ -344,15 +344,17 @@ static void lme2510_int_response(struct urb *lme_urb)
 
 	usb_submit_urb(lme_urb, GFP_ATOMIC);
 
-	/* interrupt urb is due every 48 msecs while streaming
-	 *	add 12msecs for system lag */
-	st->int_urb_due = jiffies + msecs_to_jiffies(60);
+	/* Interrupt urb is due every 48 msecs while streaming the buffer
+	 * stores up to 4 periods if missed. Allow 200 msec for next interrupt.
+	 */
+	st->int_urb_due = jiffies + msecs_to_jiffies(200);
 }
 
 static int lme2510_int_read(struct dvb_usb_adapter *adap)
 {
 	struct dvb_usb_device *d = adap_to_d(adap);
 	struct lme2510_state *lme_int = adap_to_priv(adap);
+	struct usb_host_endpoint *ep;
 
 	lme_int->lme_urb = usb_alloc_urb(0, GFP_ATOMIC);
 
@@ -374,6 +376,12 @@ static int lme2510_int_read(struct dvb_usb_adapter *adap)
 				adap,
 				8);
 
+	/* Quirk of pipe reporting PIPE_BULK but behaves as interrupt */
+	ep = usb_pipe_endpoint(d->udev, lme_int->lme_urb->pipe);
+
+	if (usb_endpoint_type(&ep->desc) == USB_ENDPOINT_XFER_BULK)
+		lme_int->lme_urb->pipe = usb_rcvbulkpipe(d->udev, 0xa),
+
 	lme_int->lme_urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
 
 	usb_submit_urb(lme_int->lme_urb, GFP_ATOMIC);
diff --git a/drivers/media/usb/dvb-usb/af9005.c b/drivers/media/usb/dvb-usb/af9005.c
index 3f4361e48a3..efa782ed6e2 100644
--- a/drivers/media/usb/dvb-usb/af9005.c
+++ b/drivers/media/usb/dvb-usb/af9005.c
@@ -1081,9 +1081,12 @@ static int __init af9005_usb_module_init(void)
 		err("usb_register failed. (%d)", result);
 		return result;
 	}
+#if IS_MODULE(CONFIG_DVB_USB_AF9005) || defined(CONFIG_DVB_USB_AF9005_REMOTE)
+	/* FIXME: convert to todays kernel IR infrastructure */
 	rc_decode = symbol_request(af9005_rc_decode);
 	rc_keys = symbol_request(rc_map_af9005_table);
 	rc_keys_size = symbol_request(rc_map_af9005_table_size);
+#endif
 	if (rc_decode == NULL || rc_keys == NULL || rc_keys_size == NULL) {
 		err("af9005_rc_decode function not found, disabling remote");
 		af9005_properties.rc.legacy.rc_query = NULL;
diff --git a/drivers/media/usb/dvb-usb/dib0700_core.c b/drivers/media/usb/dvb-usb/dib0700_core.c
index 50856dbf549..605b090c618 100644
--- a/drivers/media/usb/dvb-usb/dib0700_core.c
+++ b/drivers/media/usb/dvb-usb/dib0700_core.c
@@ -658,10 +658,20 @@ out:
 struct dib0700_rc_response {
 	u8 report_id;
 	u8 data_state;
-	u8 system;
-	u8 not_system;
-	u8 data;
-	u8 not_data;
+	union {
+		struct {
+			u8 system;
+			u8 not_system;
+			u8 data;
+			u8 not_data;
+		} nec;
+		struct {
+			u8 not_used;
+			u8 system;
+			u8 data;
+			u8 not_data;
+		} rc5;
+	};
 };
 #define RC_MSG_SIZE_V1_20 6
 
@@ -697,8 +707,8 @@ static void dib0700_rc_urb_completion(struct urb *purb)
 
 	deb_data("IR ID = %02X state = %02X System = %02X %02X Cmd = %02X %02X (len %d)\n",
 		 poll_reply->report_id, poll_reply->data_state,
-		 poll_reply->system, poll_reply->not_system,
-		 poll_reply->data, poll_reply->not_data,
+		 poll_reply->nec.system, poll_reply->nec.not_system,
+		 poll_reply->nec.data, poll_reply->nec.not_data,
 		 purb->actual_length);
 
 	switch (d->props.rc.core.protocol) {
@@ -707,30 +717,30 @@ static void dib0700_rc_urb_completion(struct urb *purb)
 		toggle = 0;
 
 		/* NEC protocol sends repeat code as 0 0 0 FF */
-		if (poll_reply->system     == 0x00 &&
-		    poll_reply->not_system == 0x00 &&
-		    poll_reply->data       == 0x00 &&
-		    poll_reply->not_data   == 0xff) {
+		if (poll_reply->nec.system     == 0x00 &&
+		    poll_reply->nec.not_system == 0x00 &&
+		    poll_reply->nec.data       == 0x00 &&
+		    poll_reply->nec.not_data   == 0xff) {
 			poll_reply->data_state = 2;
 			break;
 		}
 
-		if ((poll_reply->data ^ poll_reply->not_data) != 0xff) {
+		if ((poll_reply->nec.data ^ poll_reply->nec.not_data) != 0xff) {
 			deb_data("NEC32 protocol\n");
-			keycode = RC_SCANCODE_NEC32(poll_reply->system     << 24 |
-						     poll_reply->not_system << 16 |
-						     poll_reply->data       << 8  |
-						     poll_reply->not_data);
-		} else if ((poll_reply->system ^ poll_reply->not_system) != 0xff) {
+			keycode = RC_SCANCODE_NEC32(poll_reply->nec.system     << 24 |
+						     poll_reply->nec.not_system << 16 |
+						     poll_reply->nec.data       << 8  |
+						     poll_reply->nec.not_data);
+		} else if ((poll_reply->nec.system ^ poll_reply->nec.not_system) != 0xff) {
 			deb_data("NEC extended protocol\n");
-			keycode = RC_SCANCODE_NECX(poll_reply->system << 8 |
-						    poll_reply->not_system,
-						    poll_reply->data);
+			keycode = RC_SCANCODE_NECX(poll_reply->nec.system << 8 |
+						    poll_reply->nec.not_system,
+						    poll_reply->nec.data);
 
 		} else {
 			deb_data("NEC normal protocol\n");
-			keycode = RC_SCANCODE_NEC(poll_reply->system,
-						   poll_reply->data);
+			keycode = RC_SCANCODE_NEC(poll_reply->nec.system,
+						   poll_reply->nec.data);
 		}
 
 		break;
@@ -738,19 +748,19 @@ static void dib0700_rc_urb_completion(struct urb *purb)
 		deb_data("RC5 protocol\n");
 		protocol = RC_TYPE_RC5;
 		toggle = poll_reply->report_id;
-		keycode = RC_SCANCODE_RC5(poll_reply->system, poll_reply->data);
+		keycode = RC_SCANCODE_RC5(poll_reply->rc5.system, poll_reply->rc5.data);
+
+		if ((poll_reply->rc5.data ^ poll_reply->rc5.not_data) != 0xff) {
+			/* Key failed integrity check */
+			err("key failed integrity check: %02x %02x %02x %02x",
+			    poll_reply->rc5.not_used, poll_reply->rc5.system,
+			    poll_reply->rc5.data, poll_reply->rc5.not_data);
+			goto resubmit;
+		}
 
 		break;
 	}
 
-	if ((poll_reply->data + poll_reply->not_data) != 0xff) {
-		/* Key failed integrity check */
-		err("key failed integrity check: %02x %02x %02x %02x",
-		    poll_reply->system,  poll_reply->not_system,
-		    poll_reply->data, poll_reply->not_data);
-		goto resubmit;
-	}
-
 	rc_keydown(d->rc_dev, protocol, keycode, toggle);
 
 resubmit:
diff --git a/drivers/media/usb/dvb-usb/dib0700_devices.c b/drivers/media/usb/dvb-usb/dib0700_devices.c
index e1757b8f5f5..6aa4e9f4e44 100644
--- a/drivers/media/usb/dvb-usb/dib0700_devices.c
+++ b/drivers/media/usb/dvb-usb/dib0700_devices.c
@@ -3947,6 +3947,8 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 
 				DIB0700_DEFAULT_STREAMING_CONFIG(0x02),
 			}},
+				.size_of_priv = sizeof(struct
+						dib0700_adapter_state),
 			}, {
 			.num_frontends = 1,
 			.fe = {{
@@ -3959,6 +3961,8 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 
 				DIB0700_DEFAULT_STREAMING_CONFIG(0x03),
 			}},
+				.size_of_priv = sizeof(struct
+						dib0700_adapter_state),
 			}
 		},
 
@@ -4012,6 +4016,8 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 
 				DIB0700_DEFAULT_STREAMING_CONFIG(0x02),
 			}},
+				.size_of_priv = sizeof(struct
+						dib0700_adapter_state),
 			},
 		},
 
diff --git a/drivers/media/usb/em28xx/em28xx-audio.c b/drivers/media/usb/em28xx/em28xx-audio.c
index 957c7ae30ef..1ead904a704 100644
--- a/drivers/media/usb/em28xx/em28xx-audio.c
+++ b/drivers/media/usb/em28xx/em28xx-audio.c
@@ -821,7 +821,7 @@ static int em28xx_audio_urb_init(struct em28xx *dev)
 	if (urb_size > ep_size * npackets)
 		npackets = DIV_ROUND_UP(urb_size, ep_size);
 
-	em28xx_info("Number of URBs: %d, with %d packets and %d size",
+	em28xx_info("Number of URBs: %d, with %d packets and %d size\n",
 		    num_urb, npackets, urb_size);
 
 	/* Estimate the bytes per period */
@@ -982,7 +982,7 @@ static int em28xx_audio_fini(struct em28xx *dev)
 		return 0;
 	}
 
-	em28xx_info("Closing audio extension");
+	em28xx_info("Closing audio extension\n");
 
 	if (dev->adev.sndcard) {
 		snd_card_disconnect(dev->adev.sndcard);
@@ -1006,7 +1006,7 @@ static int em28xx_audio_suspend(struct em28xx *dev)
 	if (dev->usb_audio_type != EM28XX_USB_AUDIO_VENDOR)
 		return 0;
 
-	em28xx_info("Suspending audio extension");
+	em28xx_info("Suspending audio extension\n");
 	em28xx_deinit_isoc_audio(dev);
 	atomic_set(&dev->adev.stream_started, 0);
 	return 0;
@@ -1020,7 +1020,7 @@ static int em28xx_audio_resume(struct em28xx *dev)
 	if (dev->usb_audio_type != EM28XX_USB_AUDIO_VENDOR)
 		return 0;
 
-	em28xx_info("Resuming audio extension");
+	em28xx_info("Resuming audio extension\n");
 	/* Nothing to do other than schedule_work() ?? */
 	schedule_work(&dev->adev.wq_trigger);
 	return 0;
diff --git a/drivers/media/usb/em28xx/em28xx-core.c b/drivers/media/usb/em28xx/em28xx-core.c
index 901cf2b952d..84dd4aec70f 100644
--- a/drivers/media/usb/em28xx/em28xx-core.c
+++ b/drivers/media/usb/em28xx/em28xx-core.c
@@ -1122,7 +1122,7 @@ int em28xx_suspend_extension(struct em28xx *dev)
 {
 	const struct em28xx_ops *ops = NULL;
 
-	em28xx_info("Suspending extensions");
+	em28xx_info("Suspending extensions\n");
 	mutex_lock(&em28xx_devlist_mutex);
 	list_for_each_entry(ops, &em28xx_extension_devlist, next) {
 		if (ops->suspend)
@@ -1136,7 +1136,7 @@ int em28xx_resume_extension(struct em28xx *dev)
 {
 	const struct em28xx_ops *ops = NULL;
 
-	em28xx_info("Resuming extensions");
+	em28xx_info("Resuming extensions\n");
 	mutex_lock(&em28xx_devlist_mutex);
 	list_for_each_entry(ops, &em28xx_extension_devlist, next) {
 		if (ops->resume)
diff --git a/drivers/media/usb/em28xx/em28xx-dvb.c b/drivers/media/usb/em28xx/em28xx-dvb.c
index 9682c52d67d..41a6864ab8d 100644
--- a/drivers/media/usb/em28xx/em28xx-dvb.c
+++ b/drivers/media/usb/em28xx/em28xx-dvb.c
@@ -1667,7 +1667,7 @@ static int em28xx_dvb_fini(struct em28xx *dev)
 	if (!dev->dvb)
 		return 0;
 
-	em28xx_info("Closing DVB extension");
+	em28xx_info("Closing DVB extension\n");
 
 	dvb = dev->dvb;
 	client = dvb->i2c_client_tuner;
@@ -1718,17 +1718,17 @@ static int em28xx_dvb_suspend(struct em28xx *dev)
 	if (!dev->board.has_dvb)
 		return 0;
 
-	em28xx_info("Suspending DVB extension");
+	em28xx_info("Suspending DVB extension\n");
 	if (dev->dvb) {
 		struct em28xx_dvb *dvb = dev->dvb;
 
 		if (dvb->fe[0]) {
 			ret = dvb_frontend_suspend(dvb->fe[0]);
-			em28xx_info("fe0 suspend %d", ret);
+			em28xx_info("fe0 suspend %d\n", ret);
 		}
 		if (dvb->fe[1]) {
 			dvb_frontend_suspend(dvb->fe[1]);
-			em28xx_info("fe1 suspend %d", ret);
+			em28xx_info("fe1 suspend %d\n", ret);
 		}
 	}
 
@@ -1745,18 +1745,18 @@ static int em28xx_dvb_resume(struct em28xx *dev)
 	if (!dev->board.has_dvb)
 		return 0;
 
-	em28xx_info("Resuming DVB extension");
+	em28xx_info("Resuming DVB extension\n");
 	if (dev->dvb) {
 		struct em28xx_dvb *dvb = dev->dvb;
 
 		if (dvb->fe[0]) {
 			ret = dvb_frontend_resume(dvb->fe[0]);
-			em28xx_info("fe0 resume %d", ret);
+			em28xx_info("fe0 resume %d\n", ret);
 		}
 
 		if (dvb->fe[1]) {
 			ret = dvb_frontend_resume(dvb->fe[1]);
-			em28xx_info("fe1 resume %d", ret);
+			em28xx_info("fe1 resume %d\n", ret);
 		}
 	}
 
diff --git a/drivers/media/usb/em28xx/em28xx-input.c b/drivers/media/usb/em28xx/em28xx-input.c
index 23f8f6afa2e..b31e275faa2 100644
--- a/drivers/media/usb/em28xx/em28xx-input.c
+++ b/drivers/media/usb/em28xx/em28xx-input.c
@@ -833,7 +833,7 @@ static int em28xx_ir_fini(struct em28xx *dev)
 		return 0;
 	}
 
-	em28xx_info("Closing input extension");
+	em28xx_info("Closing input extension\n");
 
 	em28xx_shutdown_buttons(dev);
 
@@ -863,7 +863,7 @@ static int em28xx_ir_suspend(struct em28xx *dev)
 	if (dev->is_audio_only)
 		return 0;
 
-	em28xx_info("Suspending input extension");
+	em28xx_info("Suspending input extension\n");
 	if (ir)
 		cancel_delayed_work_sync(&ir->work);
 	cancel_delayed_work_sync(&dev->buttons_query_work);
@@ -880,7 +880,7 @@ static int em28xx_ir_resume(struct em28xx *dev)
 	if (dev->is_audio_only)
 		return 0;
 
-	em28xx_info("Resuming input extension");
+	em28xx_info("Resuming input extension\n");
 	/* if suspend calls ir_raw_event_unregister(), the should call
 	   ir_raw_event_register() */
 	if (ir)
diff --git a/drivers/media/usb/em28xx/em28xx-video.c b/drivers/media/usb/em28xx/em28xx-video.c
index 03d5ece0319..e0f4be8c5a1 100644
--- a/drivers/media/usb/em28xx/em28xx-video.c
+++ b/drivers/media/usb/em28xx/em28xx-video.c
@@ -1956,7 +1956,7 @@ static int em28xx_v4l2_fini(struct em28xx *dev)
 	if (v4l2 == NULL)
 		return 0;
 
-	em28xx_info("Closing video extension");
+	em28xx_info("Closing video extension\n");
 
 	mutex_lock(&dev->lock);
 
@@ -2005,7 +2005,7 @@ static int em28xx_v4l2_suspend(struct em28xx *dev)
 	if (!dev->has_video)
 		return 0;
 
-	em28xx_info("Suspending video extension");
+	em28xx_info("Suspending video extension\n");
 	em28xx_stop_urbs(dev);
 	return 0;
 }
@@ -2018,7 +2018,7 @@ static int em28xx_v4l2_resume(struct em28xx *dev)
 	if (!dev->has_video)
 		return 0;
 
-	em28xx_info("Resuming video extension");
+	em28xx_info("Resuming video extension\n");
 	/* what do we do here */
 	return 0;
 }
diff --git a/drivers/media/usb/stk1160/stk1160-v4l.c b/drivers/media/usb/stk1160/stk1160-v4l.c
index 233054311a6..f6d0334f246 100644
--- a/drivers/media/usb/stk1160/stk1160-v4l.c
+++ b/drivers/media/usb/stk1160/stk1160-v4l.c
@@ -244,6 +244,11 @@ static int stk1160_stop_streaming(struct stk1160 *dev)
 	if (mutex_lock_interruptible(&dev->v4l_lock))
 		return -ERESTARTSYS;
 
+	/*
+	 * Once URBs are cancelled, the URB complete handler
+	 * won't be running. This is required to safely release the
+	 * current buffer (dev->isoc_ctl.buf).
+	 */
 	stk1160_cancel_isoc(dev);
 
 	/*
@@ -624,8 +629,16 @@ void stk1160_clear_queue(struct stk1160 *dev)
 		stk1160_info("buffer [%p/%d] aborted\n",
 				buf, buf->vb.v4l2_buf.index);
 	}
-	/* It's important to clear current buffer */
-	dev->isoc_ctl.buf = NULL;
+
+	/* It's important to release the current buffer */
+	if (dev->isoc_ctl.buf) {
+		buf = dev->isoc_ctl.buf;
+		dev->isoc_ctl.buf = NULL;
+
+		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
+		stk1160_info("buffer [%p/%d] aborted\n",
+				buf, buf->vb.v4l2_buf.index);
+	}
 	spin_unlock_irqrestore(&dev->buf_lock, flags);
 }
 
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index 7c8322d4fc6..3c07af96b30 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -1623,12 +1623,12 @@ static void uvc_delete(struct uvc_device *dev)
 {
 	struct list_head *p, *n;
 
-	usb_put_intf(dev->intf);
-	usb_put_dev(dev->udev);
-
 	uvc_status_cleanup(dev);
 	uvc_ctrl_cleanup_device(dev);
 
+	usb_put_intf(dev->intf);
+	usb_put_dev(dev->udev);
+
 	if (dev->vdev.dev)
 		v4l2_device_unregister(&dev->vdev);
 #ifdef CONFIG_MEDIA_CONTROLLER
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index f2e43de3dd8..c59f9391dd8 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -3142,27 +3142,26 @@ static int vb2_thread(void *data)
 			prequeue--;
 		} else {
 			call_void_qop(q, wait_finish, q);
-			ret = vb2_internal_dqbuf(q, &fileio->b, 0);
+			if (!threadio->stop)
+				ret = vb2_internal_dqbuf(q, &fileio->b, 0);
 			call_void_qop(q, wait_prepare, q);
 			dprintk(5, "file io: vb2_dqbuf result: %d\n", ret);
 		}
-		if (threadio->stop)
-			break;
-		if (ret)
+		if (ret || threadio->stop)
 			break;
 		try_to_freeze();
 
 		vb = q->bufs[fileio->b.index];
 		if (!(fileio->b.flags & V4L2_BUF_FLAG_ERROR))
-			ret = threadio->fnc(vb, threadio->priv);
-		if (ret)
-			break;
+			if (threadio->fnc(vb, threadio->priv))
+				break;
 		call_void_qop(q, wait_finish, q);
 		if (set_timestamp)
 			v4l2_get_timestamp(&fileio->b.timestamp);
-		ret = vb2_internal_qbuf(q, &fileio->b);
+		if (!threadio->stop)
+			ret = vb2_internal_qbuf(q, &fileio->b);
 		call_void_qop(q, wait_prepare, q);
-		if (ret)
+		if (ret || threadio->stop)
 			break;
 	}
 
@@ -3222,23 +3221,17 @@ EXPORT_SYMBOL_GPL(vb2_thread_start);
 int vb2_thread_stop(struct vb2_queue *q)
 {
 	struct vb2_threadio_data *threadio = q->threadio;
-	struct vb2_fileio_data *fileio = q->fileio;
 	int err;
 
 	if (threadio == NULL)
 		return 0;
-	call_void_qop(q, wait_finish, q);
 	threadio->stop = true;
-	vb2_internal_streamoff(q, q->type);
-	call_void_qop(q, wait_prepare, q);
-	q->fileio = NULL;
-	fileio->req.count = 0;
-	vb2_reqbufs(q, &fileio->req);
-	kfree(fileio);
+	/* Wake up all pending sleeps in the thread */
+	vb2_queue_error(q);
 	err = kthread_stop(threadio->thread);
+	__vb2_cleanup_fileio(q);
 	threadio->thread = NULL;
 	kfree(threadio);
-	q->fileio = NULL;
 	q->threadio = NULL;
 	return err;
 }
diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c
index fc145d202c4..922a750640e 100644
--- a/drivers/memstick/core/mspro_block.c
+++ b/drivers/memstick/core/mspro_block.c
@@ -758,7 +758,7 @@ static int mspro_block_complete_req(struct memstick_dev *card, int error)
 
 		if (error || (card->current_mrq.tpc == MSPRO_CMD_STOP)) {
 			if (msb->data_dir == READ) {
-				for (cnt = 0; cnt < msb->current_seg; cnt++)
+				for (cnt = 0; cnt < msb->current_seg; cnt++) {
 					t_len += msb->req_sg[cnt].length
 						 / msb->page_size;
 
@@ -766,6 +766,7 @@ static int mspro_block_complete_req(struct memstick_dev *card, int error)
 						t_len += msb->current_page - 1;
 
 					t_len *= msb->page_size;
+				}
 			}
 		} else
 			t_len = blk_rq_bytes(msb->block_req);
diff --git a/drivers/mfd/kempld-core.c b/drivers/mfd/kempld-core.c
index bd2696136ee..177fa31e5aa 100644
--- a/drivers/mfd/kempld-core.c
+++ b/drivers/mfd/kempld-core.c
@@ -740,7 +740,7 @@ static int __init kempld_init(void)
 		for (id = kempld_dmi_table;
 		     id->matches[0].slot != DMI_NONE; id++)
 			if (strstr(id->ident, force_device_id))
-				if (id->callback && id->callback(id))
+				if (id->callback && !id->callback(id))
 					break;
 		if (id->matches[0].slot == DMI_NONE)
 			return -ENODEV;
diff --git a/drivers/mfd/rtsx_usb.c b/drivers/mfd/rtsx_usb.c
index 9cf98d142d9..c2474cf6bfe 100644
--- a/drivers/mfd/rtsx_usb.c
+++ b/drivers/mfd/rtsx_usb.c
@@ -681,21 +681,9 @@ static void rtsx_usb_disconnect(struct usb_interface *intf)
 #ifdef CONFIG_PM
 static int rtsx_usb_suspend(struct usb_interface *intf, pm_message_t message)
 {
-	struct rtsx_ucr *ucr =
-		(struct rtsx_ucr *)usb_get_intfdata(intf);
-
 	dev_dbg(&intf->dev, "%s called with pm message 0x%04x\n",
 			__func__, message.event);
 
-	/*
-	 * Call to make sure LED is off during suspend to save more power.
-	 * It is NOT a permanent state and could be turned on anytime later.
-	 * Thus no need to call turn_on when resunming.
-	 */
-	mutex_lock(&ucr->dev_mutex);
-	rtsx_usb_turn_off_led(ucr);
-	mutex_unlock(&ucr->dev_mutex);
-
 	return 0;
 }
 
diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c
index 4fac16bcd73..0afddf6c37a 100644
--- a/drivers/mfd/tc6393xb.c
+++ b/drivers/mfd/tc6393xb.c
@@ -263,6 +263,17 @@ static int tc6393xb_ohci_disable(struct platform_device *dev)
 	return 0;
 }
 
+static int tc6393xb_ohci_suspend(struct platform_device *dev)
+{
+	struct tc6393xb_platform_data *tcpd = dev_get_platdata(dev->dev.parent);
+
+	/* We can't properly store/restore OHCI state, so fail here */
+	if (tcpd->resume_restore)
+		return -EBUSY;
+
+	return tc6393xb_ohci_disable(dev);
+}
+
 static int tc6393xb_fb_enable(struct platform_device *dev)
 {
 	struct tc6393xb *tc6393xb = dev_get_drvdata(dev->dev.parent);
@@ -403,7 +414,7 @@ static struct mfd_cell tc6393xb_cells[] = {
 		.num_resources = ARRAY_SIZE(tc6393xb_ohci_resources),
 		.resources = tc6393xb_ohci_resources,
 		.enable = tc6393xb_ohci_enable,
-		.suspend = tc6393xb_ohci_disable,
+		.suspend = tc6393xb_ohci_suspend,
 		.resume = tc6393xb_ohci_enable,
 		.disable = tc6393xb_ohci_disable,
 	},
diff --git a/drivers/mfd/tps65218.c b/drivers/mfd/tps65218.c
index 0d256cb002e..d6b764349f9 100644
--- a/drivers/mfd/tps65218.c
+++ b/drivers/mfd/tps65218.c
@@ -125,10 +125,21 @@ int tps65218_clear_bits(struct tps65218 *tps, unsigned int reg,
 }
 EXPORT_SYMBOL_GPL(tps65218_clear_bits);
 
+static const struct regmap_range tps65218_yes_ranges[] = {
+	regmap_reg_range(TPS65218_REG_INT1, TPS65218_REG_INT2),
+	regmap_reg_range(TPS65218_REG_STATUS, TPS65218_REG_STATUS),
+};
+
+static const struct regmap_access_table tps65218_volatile_table = {
+	.yes_ranges = tps65218_yes_ranges,
+	.n_yes_ranges = ARRAY_SIZE(tps65218_yes_ranges),
+};
+
 static struct regmap_config tps65218_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
 	.cache_type = REGCACHE_RBTREE,
+	.volatile_table = &tps65218_volatile_table,
 };
 
 static const struct regmap_irq tps65218_irqs[] = {
@@ -193,6 +204,7 @@ static struct regmap_irq_chip tps65218_irq_chip = {
 
 	.num_regs = 2,
 	.mask_base = TPS65218_REG_INT_MASK1,
+	.status_base = TPS65218_REG_INT1,
 };
 
 static const struct of_device_id of_tps65218_match_table[] = {
diff --git a/drivers/mfd/twl4030-power.c b/drivers/mfd/twl4030-power.c
index 50f9091bcd3..7d63e324e6a 100644
--- a/drivers/mfd/twl4030-power.c
+++ b/drivers/mfd/twl4030-power.c
@@ -831,6 +831,9 @@ static struct twl4030_power_data osc_off_idle = {
 
 static struct of_device_id twl4030_power_of_match[] = {
 	{
+		.compatible = "ti,twl4030-power",
+	},
+	{
 		.compatible = "ti,twl4030-power-reset",
 		.data = &omap3_reset,
 	},
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index bbeb4516fac..114e0b860dc 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -402,6 +402,10 @@ config TI_DAC7512
 	  This driver can also be built as a module. If so, the module
 	  will be called ti_dac7512.
 
+config UID_STAT
+	bool "UID based statistics tracking exported to /proc/uid_stat"
+	default n
+
 config VMWARE_BALLOON
 	tristate "VMware Balloon Driver"
 	depends on X86 && HYPERVISOR_GUEST
@@ -515,6 +519,12 @@ config VEXPRESS_SYSCFG
 	  bus. System Configuration interface is one of the possible means
 	  of generating transactions on this bus.
 
+config UID_CPUTIME
+	tristate "Per-UID cpu time statistics"
+	depends on PROFILING
+	help
+	  Per UID based cpu time statistics exported to /proc/uid_cputime
+
 source "drivers/misc/c2port/Kconfig"
 source "drivers/misc/eeprom/Kconfig"
 source "drivers/misc/cb710/Kconfig"
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index 7d5c4cd118c..d6911153de2 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -34,6 +34,7 @@ obj-$(CONFIG_ISL29020)		+= isl29020.o
 obj-$(CONFIG_SENSORS_TSL2550)	+= tsl2550.o
 obj-$(CONFIG_DS1682)		+= ds1682.o
 obj-$(CONFIG_TI_DAC7512)	+= ti_dac7512.o
+obj-$(CONFIG_UID_STAT)		+= uid_stat.o
 obj-$(CONFIG_C2PORT)		+= c2port/
 obj-$(CONFIG_HMC6352)		+= hmc6352.o
 obj-y				+= eeprom/
@@ -56,3 +57,4 @@ obj-$(CONFIG_GENWQE)		+= genwqe/
 obj-$(CONFIG_ECHO)		+= echo/
 obj-$(CONFIG_VEXPRESS_SYSCFG)	+= vexpress-syscfg.o
 obj-$(CONFIG_CXL_BASE)		+= cxl/
+obj-$(CONFIG_UID_CPUTIME) += uid_cputime.o
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
index cca47210913..51fd6b52437 100644
--- a/drivers/misc/cxl/context.c
+++ b/drivers/misc/cxl/context.c
@@ -34,7 +34,8 @@ struct cxl_context *cxl_context_alloc(void)
 /*
  * Initialises a CXL context.
  */
-int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master)
+int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master,
+		     struct address_space *mapping)
 {
 	int i;
 
@@ -42,6 +43,8 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master)
 	ctx->afu = afu;
 	ctx->master = master;
 	ctx->pid = NULL; /* Set in start work ioctl */
+	mutex_init(&ctx->mapping_lock);
+	ctx->mapping = mapping;
 
 	/*
 	 * Allocate the segment table before we put it in the IDR so that we
@@ -82,12 +85,12 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master)
 	 * Allocating IDR! We better make sure everything's setup that
 	 * dereferences from it.
 	 */
+	mutex_lock(&afu->contexts_lock);
 	idr_preload(GFP_KERNEL);
-	spin_lock(&afu->contexts_lock);
 	i = idr_alloc(&ctx->afu->contexts_idr, ctx, 0,
 		      ctx->afu->num_procs, GFP_NOWAIT);
-	spin_unlock(&afu->contexts_lock);
 	idr_preload_end();
+	mutex_unlock(&afu->contexts_lock);
 	if (i < 0)
 		return i;
 
@@ -147,6 +150,12 @@ static void __detach_context(struct cxl_context *ctx)
 	afu_release_irqs(ctx);
 	flush_work(&ctx->fault_work); /* Only needed for dedicated process */
 	wake_up_all(&ctx->wq);
+
+	/* Release Problem State Area mapping */
+	mutex_lock(&ctx->mapping_lock);
+	if (ctx->mapping)
+		unmap_mapping_range(ctx->mapping, 0, 0, 1);
+	mutex_unlock(&ctx->mapping_lock);
 }
 
 /*
@@ -168,21 +177,22 @@ void cxl_context_detach_all(struct cxl_afu *afu)
 	struct cxl_context *ctx;
 	int tmp;
 
-	rcu_read_lock();
-	idr_for_each_entry(&afu->contexts_idr, ctx, tmp)
+	mutex_lock(&afu->contexts_lock);
+	idr_for_each_entry(&afu->contexts_idr, ctx, tmp) {
 		/*
 		 * Anything done in here needs to be setup before the IDR is
 		 * created and torn down after the IDR removed
 		 */
 		__detach_context(ctx);
-	rcu_read_unlock();
+	}
+	mutex_unlock(&afu->contexts_lock);
 }
 
 void cxl_context_free(struct cxl_context *ctx)
 {
-	spin_lock(&ctx->afu->contexts_lock);
+	mutex_lock(&ctx->afu->contexts_lock);
 	idr_remove(&ctx->afu->contexts_idr, ctx->pe);
-	spin_unlock(&ctx->afu->contexts_lock);
+	mutex_unlock(&ctx->afu->contexts_lock);
 	synchronize_rcu();
 
 	free_page((u64)ctx->sstp);
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index 3d2b8677ec8..9ff67b1e1d3 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -349,7 +349,7 @@ struct cxl_afu {
 	struct device *chardev_s, *chardev_m, *chardev_d;
 	struct idr contexts_idr;
 	struct dentry *debugfs;
-	spinlock_t contexts_lock;
+	struct mutex contexts_lock;
 	struct mutex spa_mutex;
 	spinlock_t afu_cntl_lock;
 
@@ -390,6 +390,10 @@ struct cxl_context {
 	phys_addr_t psn_phys;
 	u64 psn_size;
 
+	/* Used to unmap any mmaps when force detaching */
+	struct address_space *mapping;
+	struct mutex mapping_lock;
+
 	spinlock_t sste_lock; /* Protects segment table entries */
 	struct cxl_sste *sstp;
 	u64 sstp0, sstp1;
@@ -467,6 +471,7 @@ void cxl_release_one_irq(struct cxl *adapter, int hwirq);
 int cxl_alloc_irq_ranges(struct cxl_irq_ranges *irqs, struct cxl *adapter, unsigned int num);
 void cxl_release_irq_ranges(struct cxl_irq_ranges *irqs, struct cxl *adapter);
 int cxl_setup_irq(struct cxl *adapter, unsigned int hwirq, unsigned int virq);
+int cxl_update_image_control(struct cxl *adapter);
 
 /* common == phyp + powernv */
 struct cxl_process_element_common {
@@ -592,7 +597,8 @@ int cxl_alloc_sst(struct cxl_context *ctx);
 void init_cxl_native(void);
 
 struct cxl_context *cxl_context_alloc(void);
-int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master);
+int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master,
+		     struct address_space *mapping);
 void cxl_context_free(struct cxl_context *ctx);
 int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma);
 
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index 378b099e7c0..e9f2f10dbb3 100644
--- a/drivers/misc/cxl/file.c
+++ b/drivers/misc/cxl/file.c
@@ -77,7 +77,7 @@ static int __afu_open(struct inode *inode, struct file *file, bool master)
 		goto err_put_afu;
 	}
 
-	if ((rc = cxl_context_init(ctx, afu, master)))
+	if ((rc = cxl_context_init(ctx, afu, master, inode->i_mapping)))
 		goto err_put_afu;
 
 	pr_devel("afu_open pe: %i\n", ctx->pe);
@@ -113,6 +113,10 @@ static int afu_release(struct inode *inode, struct file *file)
 		 __func__, ctx->pe);
 	cxl_context_detach(ctx);
 
+	mutex_lock(&ctx->mapping_lock);
+	ctx->mapping = NULL;
+	mutex_unlock(&ctx->mapping_lock);
+
 	put_device(&ctx->afu->dev);
 
 	/*
diff --git a/drivers/misc/cxl/irq.c b/drivers/misc/cxl/irq.c
index 336020c8e1a..6fe4027feb7 100644
--- a/drivers/misc/cxl/irq.c
+++ b/drivers/misc/cxl/irq.c
@@ -174,6 +174,7 @@ static irqreturn_t cxl_irq(int irq, void *data)
 		}
 
 		cxl_ack_irq(ctx, CXL_PSL_TFC_An_A, 0);
+		return IRQ_HANDLED;
 	}
 	if (dsisr & CXL_PSL_DSISR_An_OC)
 		pr_devel("CXL interrupt: OS Context Warning\n");
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
index d47532e8f4f..1d9717b4d67 100644
--- a/drivers/misc/cxl/native.c
+++ b/drivers/misc/cxl/native.c
@@ -277,6 +277,7 @@ static int do_process_element_cmd(struct cxl_context *ctx,
 				  u64 cmd, u64 pe_state)
 {
 	u64 state;
+	unsigned long timeout = jiffies + (HZ * CXL_TIMEOUT);
 
 	WARN_ON(!ctx->afu->enabled);
 
@@ -286,6 +287,10 @@ static int do_process_element_cmd(struct cxl_context *ctx,
 	smp_mb();
 	cxl_p1n_write(ctx->afu, CXL_PSL_LLCMD_An, cmd | ctx->pe);
 	while (1) {
+		if (time_after_eq(jiffies, timeout)) {
+			dev_warn(&ctx->afu->dev, "WARNING: Process Element Command timed out!\n");
+			return -EBUSY;
+		}
 		state = be64_to_cpup(ctx->afu->sw_command_status);
 		if (state == ~0ULL) {
 			pr_err("cxl: Error adding process element to AFU\n");
@@ -610,13 +615,6 @@ static inline int detach_process_native_dedicated(struct cxl_context *ctx)
 	return 0;
 }
 
-/*
- * TODO: handle case when this is called inside a rcu_read_lock() which may
- * happen when we unbind the driver (ie. cxl_context_detach_all()) .  Terminate
- * & remove use a mutex lock and schedule which will not good with lock held.
- * May need to write do_process_element_cmd() that handles outstanding page
- * faults synchronously.
- */
 static inline int detach_process_native_afu_directed(struct cxl_context *ctx)
 {
 	if (!ctx->pe_inserted)
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 10c98ab7f46..eee4fd606dc 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -316,7 +316,7 @@ static int init_implementation_adapter_regs(struct cxl *adapter, struct pci_dev
 	u64 psl_dsnctl;
 	u64 chipid;
 
-	if (!(np = pnv_pci_to_phb_node(dev)))
+	if (!(np = pnv_pci_get_phb_node(dev)))
 		return -ENODEV;
 
 	while (np && !(prop = of_get_property(np, "ibm,chip-id", NULL)))
@@ -361,6 +361,41 @@ int cxl_setup_irq(struct cxl *adapter, unsigned int hwirq,
 	return pnv_cxl_ioda_msi_setup(dev, hwirq, virq);
 }
 
+int cxl_update_image_control(struct cxl *adapter)
+{
+	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
+	int rc;
+	int vsec;
+	u8 image_state;
+
+	if (!(vsec = find_cxl_vsec(dev))) {
+		dev_err(&dev->dev, "ABORTING: CXL VSEC not found!\n");
+		return -ENODEV;
+	}
+
+	if ((rc = CXL_READ_VSEC_IMAGE_STATE(dev, vsec, &image_state))) {
+		dev_err(&dev->dev, "failed to read image state: %i\n", rc);
+		return rc;
+	}
+
+	if (adapter->perst_loads_image)
+		image_state |= CXL_VSEC_PERST_LOADS_IMAGE;
+	else
+		image_state &= ~CXL_VSEC_PERST_LOADS_IMAGE;
+
+	if (adapter->perst_select_user)
+		image_state |= CXL_VSEC_PERST_SELECT_USER;
+	else
+		image_state &= ~CXL_VSEC_PERST_SELECT_USER;
+
+	if ((rc = CXL_WRITE_VSEC_IMAGE_STATE(dev, vsec, image_state))) {
+		dev_err(&dev->dev, "failed to update image control: %i\n", rc);
+		return rc;
+	}
+
+	return 0;
+}
+
 int cxl_alloc_one_irq(struct cxl *adapter)
 {
 	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
@@ -502,7 +537,7 @@ static struct cxl_afu *cxl_alloc_afu(struct cxl *adapter, int slice)
 	afu->dev.release = cxl_release_afu;
 	afu->slice = slice;
 	idr_init(&afu->contexts_idr);
-	spin_lock_init(&afu->contexts_lock);
+	mutex_init(&afu->contexts_lock);
 	spin_lock_init(&afu->afu_cntl_lock);
 	mutex_init(&afu->spa_mutex);
 
@@ -770,8 +805,8 @@ static int cxl_read_vsec(struct cxl *adapter, struct pci_dev *dev)
 	CXL_READ_VSEC_BASE_IMAGE(dev, vsec, &adapter->base_image);
 	CXL_READ_VSEC_IMAGE_STATE(dev, vsec, &image_state);
 	adapter->user_image_loaded = !!(image_state & CXL_VSEC_USER_IMAGE_LOADED);
-	adapter->perst_loads_image = !!(image_state & CXL_VSEC_PERST_LOADS_IMAGE);
-	adapter->perst_select_user = !!(image_state & CXL_VSEC_PERST_SELECT_USER);
+	adapter->perst_loads_image = true;
+	adapter->perst_select_user = !!(image_state & CXL_VSEC_USER_IMAGE_LOADED);
 
 	CXL_READ_VSEC_NAFUS(dev, vsec, &adapter->slices);
 	CXL_READ_VSEC_AFU_DESC_OFF(dev, vsec, &afu_desc_off);
@@ -879,6 +914,9 @@ static struct cxl *cxl_init_adapter(struct pci_dev *dev)
 	if ((rc = cxl_vsec_looks_ok(adapter, dev)))
 		goto err2;
 
+	if ((rc = cxl_update_image_control(adapter)))
+		goto err2;
+
 	if ((rc = cxl_map_adapter_regs(adapter, dev)))
 		goto err2;
 
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
index ce7ec06d87d..461bdbd5d48 100644
--- a/drivers/misc/cxl/sysfs.c
+++ b/drivers/misc/cxl/sysfs.c
@@ -121,7 +121,7 @@ static ssize_t reset_store_afu(struct device *device,
 	int rc;
 
 	/* Not safe to reset if it is currently in use */
-	spin_lock(&afu->contexts_lock);
+	mutex_lock(&afu->contexts_lock);
 	if (!idr_is_empty(&afu->contexts_idr)) {
 		rc = -EBUSY;
 		goto err;
@@ -132,7 +132,7 @@ static ssize_t reset_store_afu(struct device *device,
 
 	rc = count;
 err:
-	spin_unlock(&afu->contexts_lock);
+	mutex_unlock(&afu->contexts_lock);
 	return rc;
 }
 
@@ -247,7 +247,7 @@ static ssize_t mode_store(struct device *device, struct device_attribute *attr,
 	int rc = -EBUSY;
 
 	/* can't change this if we have a user */
-	spin_lock(&afu->contexts_lock);
+	mutex_lock(&afu->contexts_lock);
 	if (!idr_is_empty(&afu->contexts_idr))
 		goto err;
 
@@ -271,7 +271,7 @@ static ssize_t mode_store(struct device *device, struct device_attribute *attr,
 	afu->current_mode = 0;
 	afu->num_procs = 0;
 
-	spin_unlock(&afu->contexts_lock);
+	mutex_unlock(&afu->contexts_lock);
 
 	if ((rc = _cxl_afu_deactivate_mode(afu, old_mode)))
 		return rc;
@@ -280,7 +280,7 @@ static ssize_t mode_store(struct device *device, struct device_attribute *attr,
 
 	return count;
 err:
-	spin_unlock(&afu->contexts_lock);
+	mutex_unlock(&afu->contexts_lock);
 	return rc;
 }
 
diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c
index 7cb3b7e4173..1ca94e6fa8f 100644
--- a/drivers/misc/genwqe/card_utils.c
+++ b/drivers/misc/genwqe/card_utils.c
@@ -590,6 +590,8 @@ int genwqe_user_vmap(struct genwqe_dev *cd, struct dma_mapping *m, void *uaddr,
 				 m->nr_pages,
 				 1,		/* write by caller */
 				 m->page_list);	/* ptrs to pages */
+	if (rc < 0)
+		goto fail_get_user_pages;
 
 	/* assumption: get_user_pages can be killed by signals. */
 	if (rc < m->nr_pages) {
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index bc9ba5359bc..351e4bc07a5 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -478,7 +478,7 @@ void mei_host_client_init(struct work_struct *work)
 bool mei_hbuf_acquire(struct mei_device *dev)
 {
 	if (mei_pg_state(dev) == MEI_PG_ON ||
-	    dev->pg_event == MEI_PG_EVENT_WAIT) {
+	    mei_pg_in_transition(dev)) {
 		dev_dbg(dev->dev, "device is in pg\n");
 		return false;
 	}
diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c
index 4f2fd6fc1e2..c1ef64c5e81 100644
--- a/drivers/misc/mei/hw-me.c
+++ b/drivers/misc/mei/hw-me.c
@@ -234,6 +234,18 @@ static int mei_me_hw_reset(struct mei_device *dev, bool intr_enable)
 	struct mei_me_hw *hw = to_me_hw(dev);
 	u32 hcsr = mei_hcsr_read(hw);
 
+	/* H_RST may be found lit before reset is started,
+	 * for example if preceding reset flow hasn't completed.
+	 * In that case asserting H_RST will be ignored, therefore
+	 * we need to clean H_RST bit to start a successful reset sequence.
+	 */
+	if ((hcsr & H_RST) == H_RST) {
+		dev_warn(dev->dev, "H_RST is set = 0x%08X", hcsr);
+		hcsr &= ~H_RST;
+		mei_hcsr_set(hw, hcsr);
+		hcsr = mei_hcsr_read(hw);
+	}
+
 	hcsr |= H_RST | H_IG | H_IS;
 
 	if (intr_enable)
@@ -323,6 +335,7 @@ static int mei_me_hw_ready_wait(struct mei_device *dev)
 		return -ETIME;
 	}
 
+	mei_me_hw_reset_release(dev);
 	dev->recvd_hw_ready = false;
 	return 0;
 }
@@ -614,11 +627,27 @@ int mei_me_pg_unset_sync(struct mei_device *dev)
 	mutex_lock(&dev->device_lock);
 
 reply:
-	if (dev->pg_event == MEI_PG_EVENT_RECEIVED)
-		ret = mei_hbm_pg(dev, MEI_PG_ISOLATION_EXIT_RES_CMD);
+	if (dev->pg_event != MEI_PG_EVENT_RECEIVED) {
+		ret = -ETIME;
+		goto out;
+	}
+
+	dev->pg_event = MEI_PG_EVENT_INTR_WAIT;
+	ret = mei_hbm_pg(dev, MEI_PG_ISOLATION_EXIT_RES_CMD);
+	if (ret)
+		return ret;
+
+	mutex_unlock(&dev->device_lock);
+	wait_event_timeout(dev->wait_pg,
+		dev->pg_event == MEI_PG_EVENT_INTR_RECEIVED, timeout);
+	mutex_lock(&dev->device_lock);
+
+	if (dev->pg_event == MEI_PG_EVENT_INTR_RECEIVED)
+		ret = 0;
 	else
 		ret = -ETIME;
 
+out:
 	dev->pg_event = MEI_PG_EVENT_IDLE;
 	hw->pg_state = MEI_PG_OFF;
 
@@ -626,6 +655,19 @@ reply:
 }
 
 /**
+ * mei_me_pg_in_transition - is device now in pg transition
+ *
+ * @dev: the device structure
+ *
+ * Return: true if in pg transition, false otherwise
+ */
+static bool mei_me_pg_in_transition(struct mei_device *dev)
+{
+	return dev->pg_event >= MEI_PG_EVENT_WAIT &&
+	       dev->pg_event <= MEI_PG_EVENT_INTR_WAIT;
+}
+
+/**
  * mei_me_pg_is_enabled - detect if PG is supported by HW
  *
  * @dev: the device structure
@@ -657,6 +699,24 @@ notsupported:
 }
 
 /**
+ * mei_me_pg_intr - perform pg processing in interrupt thread handler
+ *
+ * @dev: the device structure
+ */
+static void mei_me_pg_intr(struct mei_device *dev)
+{
+	struct mei_me_hw *hw = to_me_hw(dev);
+
+	if (dev->pg_event != MEI_PG_EVENT_INTR_WAIT)
+		return;
+
+	dev->pg_event = MEI_PG_EVENT_INTR_RECEIVED;
+	hw->pg_state = MEI_PG_OFF;
+	if (waitqueue_active(&dev->wait_pg))
+		wake_up(&dev->wait_pg);
+}
+
+/**
  * mei_me_irq_quick_handler - The ISR of the MEI device
  *
  * @irq: The irq number
@@ -714,12 +774,12 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id)
 		goto end;
 	}
 
+	mei_me_pg_intr(dev);
+
 	/*  check if we need to start the dev */
 	if (!mei_host_is_ready(dev)) {
 		if (mei_hw_is_ready(dev)) {
-			mei_me_hw_reset_release(dev);
 			dev_dbg(dev->dev, "we need to start the dev.\n");
-
 			dev->recvd_hw_ready = true;
 			wake_up(&dev->wait_hw_ready);
 		} else {
@@ -752,9 +812,10 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id)
 	/*
 	 * During PG handshake only allowed write is the replay to the
 	 * PG exit message, so block calling write function
-	 * if the pg state is not idle
+	 * if the pg event is in PG handshake
 	 */
-	if (dev->pg_event == MEI_PG_EVENT_IDLE) {
+	if (dev->pg_event != MEI_PG_EVENT_WAIT &&
+	    dev->pg_event != MEI_PG_EVENT_RECEIVED) {
 		rets = mei_irq_write_handler(dev, &complete_list);
 		dev->hbuf_is_ready = mei_hbuf_is_ready(dev);
 	}
@@ -779,6 +840,7 @@ static const struct mei_hw_ops mei_me_hw_ops = {
 	.hw_config = mei_me_hw_config,
 	.hw_start = mei_me_hw_start,
 
+	.pg_in_transition = mei_me_pg_in_transition,
 	.pg_is_enabled = mei_me_pg_is_enabled,
 
 	.intr_clear = mei_me_intr_clear,
diff --git a/drivers/misc/mei/hw-txe.c b/drivers/misc/mei/hw-txe.c
index c5e1902e493..c11a01a1ec2 100644
--- a/drivers/misc/mei/hw-txe.c
+++ b/drivers/misc/mei/hw-txe.c
@@ -16,6 +16,7 @@
 
 #include <linux/pci.h>
 #include <linux/jiffies.h>
+#include <linux/ktime.h>
 #include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/irqreturn.h>
@@ -218,26 +219,25 @@ static u32 mei_txe_aliveness_get(struct mei_device *dev)
  *
  * Polls for HICR_HOST_ALIVENESS_RESP.ALIVENESS_RESP to be set
  *
- * Return: > 0 if the expected value was received, -ETIME otherwise
+ * Return: 0 if the expected value was received, -ETIME otherwise
  */
 static int mei_txe_aliveness_poll(struct mei_device *dev, u32 expected)
 {
 	struct mei_txe_hw *hw = to_txe_hw(dev);
-	int t = 0;
+	ktime_t stop, start;
 
+	start = ktime_get();
+	stop = ktime_add(start, ms_to_ktime(SEC_ALIVENESS_WAIT_TIMEOUT));
 	do {
 		hw->aliveness = mei_txe_aliveness_get(dev);
 		if (hw->aliveness == expected) {
 			dev->pg_event = MEI_PG_EVENT_IDLE;
-			dev_dbg(dev->dev,
-				"aliveness settled after %d msecs\n", t);
-			return t;
+			dev_dbg(dev->dev, "aliveness settled after %lld usecs\n",
+				ktime_to_us(ktime_sub(ktime_get(), start)));
+			return 0;
 		}
-		mutex_unlock(&dev->device_lock);
-		msleep(MSEC_PER_SEC / 5);
-		mutex_lock(&dev->device_lock);
-		t += MSEC_PER_SEC / 5;
-	} while (t < SEC_ALIVENESS_WAIT_TIMEOUT);
+		usleep_range(20, 50);
+	} while (ktime_before(ktime_get(), stop));
 
 	dev->pg_event = MEI_PG_EVENT_IDLE;
 	dev_err(dev->dev, "aliveness timed out\n");
@@ -302,6 +302,18 @@ int mei_txe_aliveness_set_sync(struct mei_device *dev, u32 req)
 }
 
 /**
+ * mei_txe_pg_in_transition - is device now in pg transition
+ *
+ * @dev: the device structure
+ *
+ * Return: true if in pg transition, false otherwise
+ */
+static bool mei_txe_pg_in_transition(struct mei_device *dev)
+{
+	return dev->pg_event == MEI_PG_EVENT_WAIT;
+}
+
+/**
  * mei_txe_pg_is_enabled - detect if PG is supported by HW
  *
  * @dev: the device structure
@@ -1139,6 +1151,7 @@ static const struct mei_hw_ops mei_txe_hw_ops = {
 	.hw_config = mei_txe_hw_config,
 	.hw_start = mei_txe_hw_start,
 
+	.pg_in_transition = mei_txe_pg_in_transition,
 	.pg_is_enabled = mei_txe_pg_is_enabled,
 
 	.intr_clear = mei_txe_intr_clear,
diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c
index 7901d076c12..6c267162f15 100644
--- a/drivers/misc/mei/init.c
+++ b/drivers/misc/mei/init.c
@@ -313,6 +313,8 @@ void mei_stop(struct mei_device *dev)
 
 	dev->dev_state = MEI_DEV_POWER_DOWN;
 	mei_reset(dev);
+	/* move device to disabled state unconditionally */
+	dev->dev_state = MEI_DEV_DISABLED;
 
 	mutex_unlock(&dev->device_lock);
 
diff --git a/drivers/misc/mei/mei_dev.h b/drivers/misc/mei/mei_dev.h
index 71744b16cc8..909b2d81895 100644
--- a/drivers/misc/mei/mei_dev.h
+++ b/drivers/misc/mei/mei_dev.h
@@ -264,6 +264,7 @@ struct mei_cl {
 
  * @fw_status        : get fw status registers
  * @pg_state         : power gating state of the device
+ * @pg_in_transition : is device now in pg transition
  * @pg_is_enabled    : is power gating enabled
 
  * @intr_clear       : clear pending interrupts
@@ -293,6 +294,7 @@ struct mei_hw_ops {
 
 	int (*fw_status)(struct mei_device *dev, struct mei_fw_status *fw_sts);
 	enum mei_pg_state (*pg_state)(struct mei_device *dev);
+	bool (*pg_in_transition)(struct mei_device *dev);
 	bool (*pg_is_enabled)(struct mei_device *dev);
 
 	void (*intr_clear)(struct mei_device *dev);
@@ -390,11 +392,15 @@ struct mei_cl_device {
  * @MEI_PG_EVENT_IDLE: the driver is not in power gating transition
  * @MEI_PG_EVENT_WAIT: the driver is waiting for a pg event to complete
  * @MEI_PG_EVENT_RECEIVED: the driver received pg event
+ * @MEI_PG_EVENT_INTR_WAIT: the driver is waiting for a pg event interrupt
+ * @MEI_PG_EVENT_INTR_RECEIVED: the driver received pg event interrupt
  */
 enum mei_pg_event {
 	MEI_PG_EVENT_IDLE,
 	MEI_PG_EVENT_WAIT,
 	MEI_PG_EVENT_RECEIVED,
+	MEI_PG_EVENT_INTR_WAIT,
+	MEI_PG_EVENT_INTR_RECEIVED,
 };
 
 /**
@@ -721,6 +727,11 @@ static inline enum mei_pg_state mei_pg_state(struct mei_device *dev)
 	return dev->ops->pg_state(dev);
 }
 
+static inline bool mei_pg_in_transition(struct mei_device *dev)
+{
+	return dev->ops->pg_in_transition(dev);
+}
+
 static inline bool mei_pg_is_enabled(struct mei_device *dev)
 {
 	return dev->ops->pg_is_enabled(dev);
diff --git a/drivers/misc/uid_cputime.c b/drivers/misc/uid_cputime.c
new file mode 100644
index 00000000000..43298a43ecc
--- /dev/null
+++ b/drivers/misc/uid_cputime.c
@@ -0,0 +1,253 @@
+/* drivers/misc/uid_cputime.c
+ *
+ * Copyright (C) 2014 - 2015 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/atomic.h>
+#include <linux/err.h>
+#include <linux/hashtable.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/proc_fs.h>
+#include <linux/profile.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+#define UID_HASH_BITS	10
+DECLARE_HASHTABLE(hash_table, UID_HASH_BITS);
+
+static DEFINE_MUTEX(uid_lock);
+static struct proc_dir_entry *parent;
+
+struct uid_entry {
+	uid_t uid;
+	cputime_t utime;
+	cputime_t stime;
+	cputime_t active_utime;
+	cputime_t active_stime;
+	unsigned long long active_power;
+	unsigned long long power;
+	struct hlist_node hash;
+};
+
+static struct uid_entry *find_uid_entry(uid_t uid)
+{
+	struct uid_entry *uid_entry;
+	hash_for_each_possible(hash_table, uid_entry, hash, uid) {
+		if (uid_entry->uid == uid)
+			return uid_entry;
+	}
+	return NULL;
+}
+
+static struct uid_entry *find_or_register_uid(uid_t uid)
+{
+	struct uid_entry *uid_entry;
+
+	uid_entry = find_uid_entry(uid);
+	if (uid_entry)
+		return uid_entry;
+
+	uid_entry = kzalloc(sizeof(struct uid_entry), GFP_ATOMIC);
+	if (!uid_entry)
+		return NULL;
+
+	uid_entry->uid = uid;
+
+	hash_add(hash_table, &uid_entry->hash, uid);
+
+	return uid_entry;
+}
+
+static int uid_stat_show(struct seq_file *m, void *v)
+{
+	struct uid_entry *uid_entry;
+	struct task_struct *task, *temp;
+	cputime_t utime;
+	cputime_t stime;
+	unsigned long bkt;
+
+	mutex_lock(&uid_lock);
+
+	hash_for_each(hash_table, bkt, uid_entry, hash) {
+		uid_entry->active_stime = 0;
+		uid_entry->active_utime = 0;
+		uid_entry->active_power = 0;
+	}
+
+	read_lock(&tasklist_lock);
+	do_each_thread(temp, task) {
+		uid_entry = find_or_register_uid(from_kuid_munged(
+			current_user_ns(), task_uid(task)));
+		if (!uid_entry) {
+			read_unlock(&tasklist_lock);
+			mutex_unlock(&uid_lock);
+			pr_err("%s: failed to find the uid_entry for uid %d\n",
+				__func__, from_kuid_munged(current_user_ns(),
+				task_uid(task)));
+			return -ENOMEM;
+		}
+		/* if this task is exiting, we have already accounted for the
+		 * time and power.
+		 */
+		if (task->cpu_power == ULLONG_MAX)
+			continue;
+		task_cputime_adjusted(task, &utime, &stime);
+		uid_entry->active_utime += utime;
+		uid_entry->active_stime += stime;
+		uid_entry->active_power += task->cpu_power;
+	} while_each_thread(temp, task);
+	read_unlock(&tasklist_lock);
+
+	hash_for_each(hash_table, bkt, uid_entry, hash) {
+		cputime_t total_utime = uid_entry->utime +
+							uid_entry->active_utime;
+		cputime_t total_stime = uid_entry->stime +
+							uid_entry->active_stime;
+		unsigned long long total_power = uid_entry->power +
+							uid_entry->active_power;
+		seq_printf(m, "%d: %llu %llu %llu\n", uid_entry->uid,
+			(unsigned long long)jiffies_to_msecs(
+				cputime_to_jiffies(total_utime)) * USEC_PER_MSEC,
+			(unsigned long long)jiffies_to_msecs(
+				cputime_to_jiffies(total_stime)) * USEC_PER_MSEC,
+			total_power);
+	}
+
+	mutex_unlock(&uid_lock);
+	return 0;
+}
+
+static int uid_stat_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, uid_stat_show, PDE_DATA(inode));
+}
+
+static const struct file_operations uid_stat_fops = {
+	.open		= uid_stat_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int uid_remove_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, NULL, NULL);
+}
+
+static ssize_t uid_remove_write(struct file *file,
+			const char __user *buffer, size_t count, loff_t *ppos)
+{
+	struct uid_entry *uid_entry;
+	struct hlist_node *tmp;
+	char uids[128];
+	char *start_uid, *end_uid = NULL;
+	long int uid_start = 0, uid_end = 0;
+
+	if (count >= sizeof(uids))
+		count = sizeof(uids) - 1;
+
+	if (copy_from_user(uids, buffer, count))
+		return -EFAULT;
+
+	uids[count] = '\0';
+	end_uid = uids;
+	start_uid = strsep(&end_uid, "-");
+
+	if (!start_uid || !end_uid)
+		return -EINVAL;
+
+	if (kstrtol(start_uid, 10, &uid_start) != 0 ||
+		kstrtol(end_uid, 10, &uid_end) != 0) {
+		return -EINVAL;
+	}
+
+	mutex_lock(&uid_lock);
+
+	for (; uid_start <= uid_end; uid_start++) {
+		hash_for_each_possible_safe(hash_table, uid_entry, tmp,
+							hash, uid_start) {
+			hash_del(&uid_entry->hash);
+			kfree(uid_entry);
+		}
+	}
+
+	mutex_unlock(&uid_lock);
+	return count;
+}
+
+static const struct file_operations uid_remove_fops = {
+	.open		= uid_remove_open,
+	.release	= single_release,
+	.write		= uid_remove_write,
+};
+
+static int process_notifier(struct notifier_block *self,
+			unsigned long cmd, void *v)
+{
+	struct task_struct *task = v;
+	struct uid_entry *uid_entry;
+	cputime_t utime, stime;
+	uid_t uid;
+
+	if (!task)
+		return NOTIFY_OK;
+
+	mutex_lock(&uid_lock);
+	uid = from_kuid_munged(current_user_ns(), task_uid(task));
+	uid_entry = find_or_register_uid(uid);
+	if (!uid_entry) {
+		pr_err("%s: failed to find uid %d\n", __func__, uid);
+		goto exit;
+	}
+
+	task_cputime_adjusted(task, &utime, &stime);
+	uid_entry->utime += utime;
+	uid_entry->stime += stime;
+	uid_entry->power += task->cpu_power;
+	task->cpu_power = ULLONG_MAX;
+
+exit:
+	mutex_unlock(&uid_lock);
+	return NOTIFY_OK;
+}
+
+static struct notifier_block process_notifier_block = {
+	.notifier_call	= process_notifier,
+};
+
+static int __init proc_uid_cputime_init(void)
+{
+	hash_init(hash_table);
+
+	parent = proc_mkdir("uid_cputime", NULL);
+	if (!parent) {
+		pr_err("%s: failed to create proc entry\n", __func__);
+		return -ENOMEM;
+	}
+
+	proc_create_data("remove_uid_range", S_IWUGO, parent, &uid_remove_fops,
+					NULL);
+
+	proc_create_data("show_uid_stat", S_IRUGO, parent, &uid_stat_fops,
+					NULL);
+
+	profile_event_register(PROFILE_TASK_EXIT, &process_notifier_block);
+
+	return 0;
+}
+
+early_initcall(proc_uid_cputime_init);
diff --git a/drivers/misc/uid_stat.c b/drivers/misc/uid_stat.c
new file mode 100644
index 00000000000..4766c1f83b9
--- /dev/null
+++ b/drivers/misc/uid_stat.c
@@ -0,0 +1,152 @@
+/* drivers/misc/uid_stat.c
+ *
+ * Copyright (C) 2008 - 2009 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <asm/atomic.h>
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stat.h>
+#include <linux/uid_stat.h>
+#include <net/activity_stats.h>
+
+static DEFINE_SPINLOCK(uid_lock);
+static LIST_HEAD(uid_list);
+static struct proc_dir_entry *parent;
+
+struct uid_stat {
+	struct list_head link;
+	uid_t uid;
+	atomic_t tcp_rcv;
+	atomic_t tcp_snd;
+};
+
+static struct uid_stat *find_uid_stat(uid_t uid) {
+	struct uid_stat *entry;
+
+	list_for_each_entry(entry, &uid_list, link) {
+		if (entry->uid == uid) {
+			return entry;
+		}
+	}
+	return NULL;
+}
+
+static int uid_stat_atomic_int_show(struct seq_file *m, void *v)
+{
+	unsigned int bytes;
+	atomic_t *counter = m->private;
+
+	bytes = (unsigned int) (atomic_read(counter) + INT_MIN);
+	return seq_printf(m, "%u\n", bytes);
+}
+
+static int uid_stat_read_atomic_int_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, uid_stat_atomic_int_show, PDE_DATA(inode));
+}
+
+static const struct file_operations uid_stat_read_atomic_int_fops = {
+	.open		= uid_stat_read_atomic_int_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+/* Create a new entry for tracking the specified uid. */
+static struct uid_stat *create_stat(uid_t uid) {
+	struct uid_stat *new_uid;
+	/* Create the uid stat struct and append it to the list. */
+	new_uid = kmalloc(sizeof(struct uid_stat), GFP_ATOMIC);
+	if (!new_uid)
+		return NULL;
+
+	new_uid->uid = uid;
+	/* Counters start at INT_MIN, so we can track 4GB of network traffic. */
+	atomic_set(&new_uid->tcp_rcv, INT_MIN);
+	atomic_set(&new_uid->tcp_snd, INT_MIN);
+
+	list_add_tail(&new_uid->link, &uid_list);
+	return new_uid;
+}
+
+static void create_stat_proc(struct uid_stat *new_uid)
+{
+	char uid_s[32];
+	struct proc_dir_entry *entry;
+	sprintf(uid_s, "%d", new_uid->uid);
+	entry = proc_mkdir(uid_s, parent);
+
+	/* Keep reference to uid_stat so we know what uid to read stats from. */
+	proc_create_data("tcp_snd", S_IRUGO, entry,
+			 &uid_stat_read_atomic_int_fops, &new_uid->tcp_snd);
+
+	proc_create_data("tcp_rcv", S_IRUGO, entry,
+			 &uid_stat_read_atomic_int_fops, &new_uid->tcp_rcv);
+}
+
+static struct uid_stat *find_or_create_uid_stat(uid_t uid)
+{
+	struct uid_stat *entry;
+	unsigned long flags;
+	spin_lock_irqsave(&uid_lock, flags);
+	entry = find_uid_stat(uid);
+	if (entry) {
+		spin_unlock_irqrestore(&uid_lock, flags);
+		return entry;
+	}
+	entry = create_stat(uid);
+	spin_unlock_irqrestore(&uid_lock, flags);
+	if (entry)
+		create_stat_proc(entry);
+	return entry;
+}
+
+int uid_stat_tcp_snd(uid_t uid, int size) {
+	struct uid_stat *entry;
+	activity_stats_update();
+	entry = find_or_create_uid_stat(uid);
+	if (!entry)
+		return -1;
+	atomic_add(size, &entry->tcp_snd);
+	return 0;
+}
+
+int uid_stat_tcp_rcv(uid_t uid, int size) {
+	struct uid_stat *entry;
+	activity_stats_update();
+	entry = find_or_create_uid_stat(uid);
+	if (!entry)
+		return -1;
+	atomic_add(size, &entry->tcp_rcv);
+	return 0;
+}
+
+static int __init uid_stat_init(void)
+{
+	parent = proc_mkdir("uid_stat", NULL);
+	if (!parent) {
+		pr_err("uid_stat: failed to create proc entry\n");
+		return -1;
+	}
+	return 0;
+}
+
+__initcall(uid_stat_init);
diff --git a/drivers/mmc/card/Kconfig b/drivers/mmc/card/Kconfig
index 5562308699b..79d82124413 100644
--- a/drivers/mmc/card/Kconfig
+++ b/drivers/mmc/card/Kconfig
@@ -50,6 +50,15 @@ config MMC_BLOCK_BOUNCE
 
 	  If unsure, say Y here.
 
+config MMC_BLOCK_DEFERRED_RESUME
+	bool "Deferr MMC layer resume until I/O is requested"
+	depends on MMC_BLOCK
+	default n
+	help
+	  Say Y here to enable deferred MMC resume until I/O
+	  is requested. This will reduce overall resume latency and
+	  save power when theres an SD card inserted but not being used.
+
 config SDIO_UART
 	tristate "SDIO UART/GPS class support"
 	depends on TTY
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 1fa4c80ff88..ded5e5ec0a3 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -36,6 +36,9 @@
 #include <linux/compat.h>
 #include <linux/pm_runtime.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/mmc.h>
+
 #include <linux/mmc/ioctl.h>
 #include <linux/mmc/card.h>
 #include <linux/mmc/host.h>
@@ -166,11 +169,7 @@ static struct mmc_blk_data *mmc_blk_get(struct gendisk *disk)
 
 static inline int mmc_get_devidx(struct gendisk *disk)
 {
-	int devmaj = MAJOR(disk_devt(disk));
-	int devidx = MINOR(disk_devt(disk)) / perdev_minors;
-
-	if (!devmaj)
-		devidx = disk->first_minor / perdev_minors;
+	int devidx = disk->first_minor / perdev_minors;
 	return devidx;
 }
 
@@ -205,6 +204,8 @@ static ssize_t power_ro_lock_show(struct device *dev,
 
 	ret = snprintf(buf, PAGE_SIZE, "%d\n", locked);
 
+	mmc_blk_put(md);
+
 	return ret;
 }
 
@@ -260,7 +261,7 @@ static ssize_t force_ro_show(struct device *dev, struct device_attribute *attr,
 	int ret;
 	struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev));
 
-	ret = snprintf(buf, PAGE_SIZE, "%d",
+	ret = snprintf(buf, PAGE_SIZE, "%d\n",
 		       get_disk_ro(dev_to_disk(dev)) ^
 		       md->read_only);
 	mmc_blk_put(md);
@@ -425,9 +426,11 @@ static int ioctl_do_sanitize(struct mmc_card *card)
 	pr_debug("%s: %s - SANITIZE IN PROGRESS...\n",
 		mmc_hostname(card->host), __func__);
 
+	trace_mmc_blk_erase_start(EXT_CSD_SANITIZE_START, 0, 0);
 	err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 					EXT_CSD_SANITIZE_START, 1,
 					MMC_SANITIZE_REQ_TIMEOUT);
+	trace_mmc_blk_erase_end(EXT_CSD_SANITIZE_START, 0, 0);
 
 	if (err)
 		pr_err("%s: %s - EXT_CSD_SANITIZE_START failed. err=%d\n",
@@ -850,18 +853,22 @@ static int mmc_blk_cmd_error(struct request *req, const char *name, int error,
 			req->rq_disk->disk_name, "timed out", name, status);
 
 		/* If the status cmd initially failed, retry the r/w cmd */
-		if (!status_valid)
+		if (!status_valid) {
+			pr_err("%s: status not valid, retrying timeout\n", req->rq_disk->disk_name);
 			return ERR_RETRY;
-
+		}
 		/*
 		 * If it was a r/w cmd crc error, or illegal command
 		 * (eg, issued in wrong state) then retry - we should
 		 * have corrected the state problem above.
 		 */
-		if (status & (R1_COM_CRC_ERROR | R1_ILLEGAL_COMMAND))
+		if (status & (R1_COM_CRC_ERROR | R1_ILLEGAL_COMMAND)) {
+			pr_err("%s: command error, retrying timeout\n", req->rq_disk->disk_name);
 			return ERR_RETRY;
+		}
 
 		/* Otherwise abort the command */
+		pr_err("%s: not retrying timeout\n", req->rq_disk->disk_name);
 		return ERR_ABORT;
 
 	default:
@@ -1025,6 +1032,18 @@ static inline void mmc_blk_reset_success(struct mmc_blk_data *md, int type)
 	md->reset_done &= ~type;
 }
 
+int mmc_access_rpmb(struct mmc_queue *mq)
+{
+	struct mmc_blk_data *md = mq->data;
+	/*
+	 * If this is a RPMB partition access, return ture
+	 */
+	if (md && md->part_type == EXT_CSD_PART_CONFIG_ACC_RPMB)
+		return true;
+
+	return false;
+}
+
 static int mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req)
 {
 	struct mmc_blk_data *md = mq->data;
@@ -1903,9 +1922,11 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 			break;
 		case MMC_BLK_CMD_ERR:
 			ret = mmc_blk_cmd_err(md, card, brq, req, ret);
-			if (!mmc_blk_reset(md, card->host, type))
-				break;
-			goto cmd_abort;
+			if (mmc_blk_reset(md, card->host, type))
+				goto cmd_abort;
+			if (!ret)
+				goto start_new_req;
+			break;
 		case MMC_BLK_RETRY:
 			if (retry++ < 5)
 				break;
@@ -2015,6 +2036,11 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 	unsigned long flags;
 	unsigned int cmd_flags = req ? req->cmd_flags : 0;
 
+#ifdef CONFIG_MMC_BLOCK_DEFERRED_RESUME
+	if (mmc_bus_needs_resume(card->host))
+		mmc_resume_bus(card->host);
+#endif
+
 	if (req && !mq->mqrq_prev->req)
 		/* claim host only for the first request */
 		mmc_get_card(card);
@@ -2136,6 +2162,7 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
 	md->disk->queue = md->queue.queue;
 	md->disk->driverfs_dev = parent;
 	set_disk_ro(md->disk, md->read_only || default_ro);
+	md->disk->flags = GENHD_FL_EXT_DEVT;
 	if (area_type & (MMC_BLK_DATA_AREA_RPMB | MMC_BLK_DATA_AREA_BOOT))
 		md->disk->flags |= GENHD_FL_NO_PART_SCAN;
 
@@ -2453,6 +2480,9 @@ static int mmc_blk_probe(struct mmc_card *card)
 
 	mmc_set_drvdata(card, md);
 
+#ifdef CONFIG_MMC_BLOCK_DEFERRED_RESUME
+	mmc_set_bus_resume_policy(card->host, 1);
+#endif
 	if (mmc_add_disk(md))
 		goto out;
 
@@ -2495,6 +2525,9 @@ static void mmc_blk_remove(struct mmc_card *card)
 	pm_runtime_put_noidle(&card->dev);
 	mmc_blk_remove_req(md);
 	mmc_set_drvdata(card, NULL);
+#ifdef CONFIG_MMC_BLOCK_DEFERRED_RESUME
+	mmc_set_bus_resume_policy(card->host, 0);
+#endif
 }
 
 static int _mmc_blk_suspend(struct mmc_card *card)
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index cfa6110632c..7a41a221d24 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -38,7 +38,7 @@ static int mmc_prep_request(struct request_queue *q, struct request *req)
 		return BLKPREP_KILL;
 	}
 
-	if (mq && mmc_card_removed(mq->card))
+	if (mq && (mmc_card_removed(mq->card) || mmc_access_rpmb(mq)))
 		return BLKPREP_KILL;
 
 	req->cmd_flags |= REQ_DONTPREP;
diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index 5752d50049a..99e6521e616 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -73,4 +73,6 @@ extern void mmc_queue_bounce_post(struct mmc_queue_req *);
 extern int mmc_packed_init(struct mmc_queue *, struct mmc_card *);
 extern void mmc_packed_clean(struct mmc_queue *);
 
+extern int mmc_access_rpmb(struct mmc_queue *);
+
 #endif
diff --git a/drivers/mmc/core/Kconfig b/drivers/mmc/core/Kconfig
index 9ebee72d9c3..f771bc3496a 100644
--- a/drivers/mmc/core/Kconfig
+++ b/drivers/mmc/core/Kconfig
@@ -11,3 +11,18 @@ config MMC_CLKGATE
 	  support handling this in order for it to be of any use.
 
 	  If unsure, say N.
+
+config MMC_EMBEDDED_SDIO
+	boolean "MMC embedded SDIO device support (EXPERIMENTAL)"
+	help
+	  If you say Y here, support will be added for embedded SDIO
+	  devices which do not contain the necessary enumeration
+	  support in hardware to be properly detected.
+
+config MMC_PARANOID_SD_INIT
+	bool "Enable paranoid SD card initialization (EXPERIMENTAL)"
+	help
+	  If you say Y here, the MMC layer will be extra paranoid
+	  about re-trying SD init requests. This can be a useful
+	  work-around for buggy controllers and hardware. Enable
+	  if you are experiencing issues with SD detection.
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index f26a5f1d926..12a9b35c6ca 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -29,6 +29,9 @@
 #include <linux/random.h>
 #include <linux/slab.h>
 #include <linux/of.h>
+#include <linux/wakelock.h>
+
+#include <trace/events/mmc.h>
 
 #include <linux/mmc/card.h>
 #include <linux/mmc/host.h>
@@ -55,6 +58,7 @@
 #define MMC_BKOPS_MAX_TIMEOUT	(4 * 60 * 1000) /* max time to wait in ms */
 
 static struct workqueue_struct *workqueue;
+static struct wake_lock mmc_delayed_work_wake_lock;
 static const unsigned freqs[] = { 400000, 300000, 200000, 100000 };
 
 /*
@@ -71,6 +75,7 @@ module_param(use_spi_crc, bool, 0);
 static int mmc_schedule_delayed_work(struct delayed_work *work,
 				     unsigned long delay)
 {
+	wake_lock(&mmc_delayed_work_wake_lock);
 	return queue_delayed_work(workqueue, work, delay);
 }
 
@@ -158,6 +163,7 @@ void mmc_request_done(struct mmc_host *host, struct mmc_request *mrq)
 			pr_debug("%s:     %d bytes transferred: %d\n",
 				mmc_hostname(host),
 				mrq->data->bytes_xfered, mrq->data->error);
+			trace_mmc_blk_rw_end(cmd->opcode, cmd->arg, mrq->data);
 		}
 
 		if (mrq->stop) {
@@ -542,8 +548,12 @@ struct mmc_async_req *mmc_start_req(struct mmc_host *host,
 			mmc_start_bkops(host->card, true);
 	}
 
-	if (!err && areq)
+	if (!err && areq) {
+		trace_mmc_blk_rw_start(areq->mrq->cmd->opcode,
+				       areq->mrq->cmd->arg,
+				       areq->mrq->data);
 		start_err = __mmc_start_data_req(host, areq->mrq);
+	}
 
 	if (host->areq)
 		mmc_post_req(host, host->areq->mrq, 0);
@@ -1879,8 +1889,13 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from,
 	struct mmc_command cmd = {0};
 	unsigned int qty = 0;
 	unsigned long timeout;
+	unsigned int fr, nr;
 	int err;
 
+	fr = from;
+	nr = to - from + 1;
+	trace_mmc_blk_erase_start(arg, fr, nr);
+
 	/*
 	 * qty is used to calculate the erase timeout which depends on how many
 	 * erase groups (or allocation units in SD terminology) are affected.
@@ -1984,6 +1999,8 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from,
 	} while (!(cmd.resp[0] & R1_READY_FOR_DATA) ||
 		 (R1_CURRENT_STATE(cmd.resp[0]) == R1_STATE_PRG));
 out:
+
+	trace_mmc_blk_erase_end(arg, fr, nr);
 	return err;
 }
 
@@ -2411,6 +2428,7 @@ void mmc_rescan(struct work_struct *work)
 	struct mmc_host *host =
 		container_of(work, struct mmc_host, detect.work);
 	int i;
+	bool extend_wakelock = false;
 
 	if (host->trigger_card_event && host->ops->card_event) {
 		host->ops->card_event(host);
@@ -2437,6 +2455,12 @@ void mmc_rescan(struct work_struct *work)
 
 	host->detect_change = 0;
 
+	/* If the card was removed the bus will be marked
+	 * as dead - extend the wakelock so userspace
+	 * can respond */
+	if (host->bus_dead)
+		extend_wakelock = 1;
+
 	/*
 	 * Let mmc_bus_put() free the bus/bus_ops if we've found that
 	 * the card is no longer present.
@@ -2466,14 +2490,20 @@ void mmc_rescan(struct work_struct *work)
 
 	mmc_claim_host(host);
 	for (i = 0; i < ARRAY_SIZE(freqs); i++) {
-		if (!mmc_rescan_try_freq(host, max(freqs[i], host->f_min)))
+		if (!mmc_rescan_try_freq(host, max(freqs[i], host->f_min))) {
+			extend_wakelock = true;
 			break;
+		}
 		if (freqs[i] <= host->f_min)
 			break;
 	}
 	mmc_release_host(host);
 
  out:
+	if (extend_wakelock)
+		wake_lock_timeout(&mmc_delayed_work_wake_lock, HZ / 2);
+	else
+		wake_unlock(&mmc_delayed_work_wake_lock);
 	if (host->caps & MMC_CAP_NEEDS_POLL)
 		mmc_schedule_delayed_work(&host->detect, HZ);
 }
@@ -2615,6 +2645,7 @@ int mmc_pm_notify(struct notifier_block *notify_block,
 	switch (mode) {
 	case PM_HIBERNATION_PREPARE:
 	case PM_SUSPEND_PREPARE:
+	case PM_RESTORE_PREPARE:
 		spin_lock_irqsave(&host->lock, flags);
 		host->rescan_disable = 1;
 		spin_unlock_irqrestore(&host->lock, flags);
@@ -2670,6 +2701,22 @@ void mmc_init_context_info(struct mmc_host *host)
 	init_waitqueue_head(&host->context_info.wait);
 }
 
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+void mmc_set_embedded_sdio_data(struct mmc_host *host,
+				struct sdio_cis *cis,
+				struct sdio_cccr *cccr,
+				struct sdio_embedded_func *funcs,
+				int num_funcs)
+{
+	host->embedded_sdio_data.cis = cis;
+	host->embedded_sdio_data.cccr = cccr;
+	host->embedded_sdio_data.funcs = funcs;
+	host->embedded_sdio_data.num_funcs = num_funcs;
+}
+
+EXPORT_SYMBOL(mmc_set_embedded_sdio_data);
+#endif
+
 static int __init mmc_init(void)
 {
 	int ret;
@@ -2678,6 +2725,9 @@ static int __init mmc_init(void)
 	if (!workqueue)
 		return -ENOMEM;
 
+	wake_lock_init(&mmc_delayed_work_wake_lock, WAKE_LOCK_SUSPEND,
+		       "mmc_delayed_work");
+
 	ret = mmc_register_bus();
 	if (ret)
 		goto destroy_workqueue;
@@ -2698,6 +2748,7 @@ unregister_bus:
 	mmc_unregister_bus();
 destroy_workqueue:
 	destroy_workqueue(workqueue);
+	wake_lock_destroy(&mmc_delayed_work_wake_lock);
 
 	return ret;
 }
@@ -2708,6 +2759,7 @@ static void __exit mmc_exit(void)
 	mmc_unregister_host_class();
 	mmc_unregister_bus();
 	destroy_workqueue(workqueue);
+	wake_lock_destroy(&mmc_delayed_work_wake_lock);
 }
 
 subsys_initcall(mmc_init);
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 270d58a4c43..69664ec2276 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -560,7 +560,8 @@ int mmc_add_host(struct mmc_host *host)
 	mmc_host_clk_sysfs_init(host);
 
 	mmc_start_host(host);
-	register_pm_notifier(&host->pm_notify);
+	if (!(host->pm_flags & MMC_PM_IGNORE_PM_NOTIFY))
+		register_pm_notifier(&host->pm_notify);
 
 	return 0;
 }
@@ -577,7 +578,9 @@ EXPORT_SYMBOL(mmc_add_host);
  */
 void mmc_remove_host(struct mmc_host *host)
 {
-	unregister_pm_notifier(&host->pm_notify);
+	if (!(host->pm_flags & MMC_PM_IGNORE_PM_NOTIFY))
+		unregister_pm_notifier(&host->pm_notify);
+
 	mmc_stop_host(host);
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index d90a6de7901..70e389b23bd 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -813,6 +813,9 @@ int mmc_sd_setup_card(struct mmc_host *host, struct mmc_card *card,
 	bool reinit)
 {
 	int err;
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+	int retries;
+#endif
 
 	if (!reinit) {
 		/*
@@ -839,7 +842,26 @@ int mmc_sd_setup_card(struct mmc_host *host, struct mmc_card *card,
 		/*
 		 * Fetch switch information from card.
 		 */
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+		for (retries = 1; retries <= 3; retries++) {
+			err = mmc_read_switch(card);
+			if (!err) {
+				if (retries > 1) {
+					printk(KERN_WARNING
+					       "%s: recovered\n", 
+					       mmc_hostname(host));
+				}
+				break;
+			} else {
+				printk(KERN_WARNING
+				       "%s: read switch failed (attempt %d)\n",
+				       mmc_hostname(host), retries);
+			}
+		}
+#else
 		err = mmc_read_switch(card);
+#endif
+
 		if (err)
 			return err;
 	}
@@ -1037,7 +1059,10 @@ static int mmc_sd_alive(struct mmc_host *host)
  */
 static void mmc_sd_detect(struct mmc_host *host)
 {
-	int err;
+	int err = 0;
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+	int retries = 5;
+#endif
 
 	BUG_ON(!host);
 	BUG_ON(!host->card);
@@ -1047,7 +1072,23 @@ static void mmc_sd_detect(struct mmc_host *host)
 	/*
 	 * Just check if our card has been removed.
 	 */
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+	while(retries) {
+		err = mmc_send_status(host->card, NULL);
+		if (err) {
+			retries--;
+			udelay(5);
+			continue;
+		}
+		break;
+	}
+	if (!retries) {
+		printk(KERN_ERR "%s(%s): Unable to re-detect card (%d)\n",
+		       __func__, mmc_hostname(host), err);
+	}
+#else
 	err = _mmc_detect_card_removed(host);
+#endif
 
 	mmc_put_card(host->card);
 
@@ -1109,6 +1150,9 @@ static int mmc_sd_suspend(struct mmc_host *host)
 static int _mmc_sd_resume(struct mmc_host *host)
 {
 	int err = 0;
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+	int retries;
+#endif
 
 	BUG_ON(!host);
 	BUG_ON(!host->card);
@@ -1119,7 +1163,23 @@ static int _mmc_sd_resume(struct mmc_host *host)
 		goto out;
 
 	mmc_power_up(host, host->card->ocr);
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+	retries = 5;
+	while (retries) {
+		err = mmc_sd_init_card(host, host->card->ocr, host->card);
+
+		if (err) {
+			printk(KERN_ERR "%s: Re-init card rc = %d (retries = %d)\n",
+			       mmc_hostname(host), err, retries);
+			mdelay(5);
+			retries--;
+			continue;
+		}
+		break;
+	}
+#else
 	err = mmc_sd_init_card(host, host->card->ocr, host->card);
+#endif
 	mmc_card_clr_suspended(host->card);
 
 out:
@@ -1210,6 +1270,9 @@ int mmc_attach_sd(struct mmc_host *host)
 {
 	int err;
 	u32 ocr, rocr;
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+	int retries;
+#endif
 
 	BUG_ON(!host);
 	WARN_ON(!host->claimed);
@@ -1246,9 +1309,27 @@ int mmc_attach_sd(struct mmc_host *host)
 	/*
 	 * Detect and init the card.
 	 */
+#ifdef CONFIG_MMC_PARANOID_SD_INIT
+	retries = 5;
+	while (retries) {
+		err = mmc_sd_init_card(host, rocr, NULL);
+		if (err) {
+			retries--;
+			continue;
+		}
+		break;
+	}
+
+	if (!retries) {
+		printk(KERN_ERR "%s: mmc_sd_init_card() failure (err = %d)\n",
+		       mmc_hostname(host), err);
+		goto err;
+	}
+#else
 	err = mmc_sd_init_card(host, rocr, NULL);
 	if (err)
 		goto err;
+#endif
 
 	mmc_release_host(host);
 	err = mmc_add_card(host->card);
diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c
index 2439e717655..7c7e5442e10 100644
--- a/drivers/mmc/core/sdio.c
+++ b/drivers/mmc/core/sdio.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/err.h>
+#include <linux/module.h>
 #include <linux/pm_runtime.h>
 
 #include <linux/mmc/host.h>
@@ -28,6 +29,10 @@
 #include "sdio_ops.h"
 #include "sdio_cis.h"
 
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+#include <linux/mmc/sdio_ids.h>
+#endif
+
 static int sdio_read_fbr(struct sdio_func *func)
 {
 	int ret;
@@ -738,19 +743,35 @@ try_again:
 		goto finish;
 	}
 
-	/*
-	 * Read the common registers.
-	 */
-	err = sdio_read_cccr(card, ocr);
-	if (err)
-		goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+	if (host->embedded_sdio_data.cccr)
+		memcpy(&card->cccr, host->embedded_sdio_data.cccr, sizeof(struct sdio_cccr));
+	else {
+#endif
+		/*
+		 * Read the common registers.
+		 */
+		err = sdio_read_cccr(card,  ocr);
+		if (err)
+			goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+	}
+#endif
 
-	/*
-	 * Read the common CIS tuples.
-	 */
-	err = sdio_read_common_cis(card);
-	if (err)
-		goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+	if (host->embedded_sdio_data.cis)
+		memcpy(&card->cis, host->embedded_sdio_data.cis, sizeof(struct sdio_cis));
+	else {
+#endif
+		/*
+		 * Read the common CIS tuples.
+		 */
+		err = sdio_read_common_cis(card);
+		if (err)
+			goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+	}
+#endif
 
 	if (oldcard) {
 		int same = (card->cis.vendor == oldcard->cis.vendor &&
@@ -1143,14 +1164,36 @@ int mmc_attach_sdio(struct mmc_host *host)
 	funcs = (ocr & 0x70000000) >> 28;
 	card->sdio_funcs = 0;
 
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+	if (host->embedded_sdio_data.funcs)
+		card->sdio_funcs = funcs = host->embedded_sdio_data.num_funcs;
+#endif
+
 	/*
 	 * Initialize (but don't add) all present functions.
 	 */
 	for (i = 0; i < funcs; i++, card->sdio_funcs++) {
-		err = sdio_init_func(host->card, i + 1);
-		if (err)
-			goto remove;
-
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+		if (host->embedded_sdio_data.funcs) {
+			struct sdio_func *tmp;
+
+			tmp = sdio_alloc_func(host->card);
+			if (IS_ERR(tmp))
+				goto remove;
+			tmp->num = (i + 1);
+			card->sdio_func[i] = tmp;
+			tmp->class = host->embedded_sdio_data.funcs[i].f_class;
+			tmp->max_blksize = host->embedded_sdio_data.funcs[i].f_maxblksize;
+			tmp->vendor = card->cis.vendor;
+			tmp->device = card->cis.device;
+		} else {
+#endif
+			err = sdio_init_func(host->card, i + 1);
+			if (err)
+				goto remove;
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+		}
+#endif
 		/*
 		 * Enable Runtime PM for this func (if supported)
 		 */
@@ -1198,3 +1241,40 @@ err:
 	return err;
 }
 
+int sdio_reset_comm(struct mmc_card *card)
+{
+	struct mmc_host *host = card->host;
+	u32 ocr;
+	u32 rocr;
+	int err;
+
+	printk("%s():\n", __func__);
+	mmc_claim_host(host);
+
+	mmc_go_idle(host);
+
+	mmc_set_clock(host, host->f_min);
+
+	err = mmc_send_io_op_cond(host, 0, &ocr);
+	if (err)
+		goto err;
+
+	rocr = mmc_select_voltage(host, ocr);
+	if (!rocr) {
+		err = -EINVAL;
+		goto err;
+	}
+
+	err = mmc_sdio_init_card(host, rocr, card, 0);
+	if (err)
+		goto err;
+
+	mmc_release_host(host);
+	return 0;
+err:
+	printk("%s: Error resetting SDIO communications (%d)\n",
+	       mmc_hostname(host), err);
+	mmc_release_host(host);
+	return err;
+}
+EXPORT_SYMBOL(sdio_reset_comm);
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index 6da97b17056..a735f892dfb 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -26,6 +26,10 @@
 #include "sdio_cis.h"
 #include "sdio_bus.h"
 
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+#include <linux/mmc/host.h>
+#endif
+
 /* show configuration fields */
 #define sdio_config_attr(field, format_string)				\
 static ssize_t								\
@@ -262,7 +266,14 @@ static void sdio_release_func(struct device *dev)
 {
 	struct sdio_func *func = dev_to_sdio_func(dev);
 
-	sdio_free_func_cis(func);
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+	/*
+	 * If this device is embedded then we never allocated
+	 * cis tables for this func
+	 */
+	if (!func->card->host->embedded_sdio_data.funcs)
+#endif
+		sdio_free_func_cis(func);
 
 	kfree(func->info);
 
diff --git a/drivers/mmc/core/sdio_io.c b/drivers/mmc/core/sdio_io.c
index 78cb4d5d9d5..8fdeb07723a 100644..100755
--- a/drivers/mmc/core/sdio_io.c
+++ b/drivers/mmc/core/sdio_io.c
@@ -384,6 +384,39 @@ u8 sdio_readb(struct sdio_func *func, unsigned int addr, int *err_ret)
 EXPORT_SYMBOL_GPL(sdio_readb);
 
 /**
+ *	sdio_readb_ext - read a single byte from a SDIO function
+ *	@func: SDIO function to access
+ *	@addr: address to read
+ *	@err_ret: optional status value from transfer
+ *	@in: value to add to argument
+ *
+ *	Reads a single byte from the address space of a given SDIO
+ *	function. If there is a problem reading the address, 0xff
+ *	is returned and @err_ret will contain the error code.
+ */
+unsigned char sdio_readb_ext(struct sdio_func *func, unsigned int addr,
+	int *err_ret, unsigned in)
+{
+	int ret;
+	unsigned char val;
+
+	BUG_ON(!func);
+
+	if (err_ret)
+		*err_ret = 0;
+
+	ret = mmc_io_rw_direct(func->card, 0, func->num, addr, (u8)in, &val);
+	if (ret) {
+		if (err_ret)
+			*err_ret = ret;
+		return 0xFF;
+	}
+
+	return val;
+}
+EXPORT_SYMBOL_GPL(sdio_readb_ext);
+
+/**
  *	sdio_writeb - write a single byte to a SDIO function
  *	@func: SDIO function to access
  *	@b: byte to write
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index 77250d4b197..6423083c523 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -1295,7 +1295,7 @@ static void atmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 
 	if (ios->clock) {
 		unsigned int clock_min = ~0U;
-		u32 clkdiv;
+		int clkdiv;
 
 		clk_prepare(host->mck);
 		unprepare_clk = true;
@@ -1324,7 +1324,12 @@ static void atmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		/* Calculate clock divider */
 		if (host->caps.has_odd_clk_div) {
 			clkdiv = DIV_ROUND_UP(host->bus_hz, clock_min) - 2;
-			if (clkdiv > 511) {
+			if (clkdiv < 0) {
+				dev_warn(&mmc->class_dev,
+					 "clock %u too fast; using %lu\n",
+					 clock_min, host->bus_hz / 2);
+				clkdiv = 0;
+			} else if (clkdiv > 511) {
 				dev_warn(&mmc->class_dev,
 				         "clock %u too slow; using %lu\n",
 				         clock_min, host->bus_hz / (511 + 2));
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 69f0cc68d5b..f7c95abc8c1 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -626,6 +626,13 @@ static void dw_mci_ctrl_rd_thld(struct dw_mci *host, struct mmc_data *data)
 
 	WARN_ON(!(data->flags & MMC_DATA_READ));
 
+	/*
+	 * CDTHRCTL doesn't exist prior to 240A (in fact that register offset is
+	 * in the FIFO region, so we really shouldn't access it).
+	 */
+	if (host->verid < DW_MMC_240A)
+		return;
+
 	if (host->timing != MMC_TIMING_MMC_HS200 &&
 	    host->timing != MMC_TIMING_UHS_SDR104)
 		goto disable;
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index df27bb4fc09..9c2b9cbcbce 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -609,6 +609,7 @@ static void omap_hsmmc_set_clock(struct omap_hsmmc_host *host)
 	 */
 	if ((mmc_slot(host).features & HSMMC_HAS_HSPE_SUPPORT) &&
 	    (ios->timing != MMC_TIMING_MMC_DDR52) &&
+	    (ios->timing != MMC_TIMING_UHS_DDR50) &&
 	    ((OMAP_HSMMC_READ(host->base, CAPA) & HSS) == HSS)) {
 		regval = OMAP_HSMMC_READ(host->base, HCTL);
 		if (clkdiv && (clk_get_rate(host->fclk)/clkdiv) > 25000000)
@@ -628,7 +629,8 @@ static void omap_hsmmc_set_bus_width(struct omap_hsmmc_host *host)
 	u32 con;
 
 	con = OMAP_HSMMC_READ(host->base, CON);
-	if (ios->timing == MMC_TIMING_MMC_DDR52)
+	if (ios->timing == MMC_TIMING_MMC_DDR52 ||
+	    ios->timing == MMC_TIMING_UHS_DDR50)
 		con |= DDR;	/* configure in DDR mode */
 	else
 		con &= ~DDR;
diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c
index 5670e381b0c..e2ec108dba0 100644
--- a/drivers/mmc/host/sdhci-pci-o2micro.c
+++ b/drivers/mmc/host/sdhci-pci-o2micro.c
@@ -127,8 +127,6 @@ void sdhci_pci_o2_fujin2_pci_init(struct sdhci_pci_chip *chip)
 		return;
 	scratch_32 &= ~((1 << 21) | (1 << 30));
 
-	/* Set RTD3 function disabled */
-	scratch_32 |= ((1 << 29) | (1 << 28));
 	pci_write_config_dword(chip->pdev, O2_SD_FUNC_REG3, scratch_32);
 
 	/* Set L1 Entrance Timer */
diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index 5036d7d3952..29708b82cee 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -112,6 +112,38 @@ static int mv_conf_mbus_windows(struct platform_device *pdev,
 	return 0;
 }
 
+static int armada_38x_quirks(struct platform_device *pdev,
+			     struct sdhci_host *host)
+{
+	struct device_node *np = pdev->dev.of_node;
+
+	host->quirks |= SDHCI_QUIRK_MISSING_CAPS;
+	/*
+	 * According to erratum 'FE-2946959' both SDR50 and DDR50
+	 * modes require specific clock adjustments in SDIO3
+	 * Configuration register, if the adjustment is not done,
+	 * remove them from the capabilities.
+	 */
+	host->caps1 = sdhci_readl(host, SDHCI_CAPABILITIES_1);
+	host->caps1 &= ~(SDHCI_SUPPORT_SDR50 | SDHCI_SUPPORT_DDR50);
+
+	/*
+	 * According to erratum 'ERR-7878951' Armada 38x SDHCI
+	 * controller has different capabilities than the ones shown
+	 * in its registers
+	 */
+	host->caps = sdhci_readl(host, SDHCI_CAPABILITIES);
+	if (of_property_read_bool(np, "no-1-8-v")) {
+		host->caps &= ~SDHCI_CAN_VDD_180;
+		host->mmc->caps &= ~MMC_CAP_1_8V_DDR;
+	} else {
+		host->caps &= ~SDHCI_CAN_VDD_330;
+	}
+	host->caps1 &= ~(SDHCI_SUPPORT_SDR104 | SDHCI_USE_SDR50_TUNING);
+
+	return 0;
+}
+
 static void pxav3_reset(struct sdhci_host *host, u8 mask)
 {
 	struct platform_device *pdev = to_platform_device(mmc_dev(host->mmc));
@@ -261,8 +293,8 @@ static struct sdhci_pxa_platdata *pxav3_get_mmc_pdata(struct device *dev)
 	if (!pdata)
 		return NULL;
 
-	of_property_read_u32(np, "mrvl,clk-delay-cycles", &clk_delay_cycles);
-	if (clk_delay_cycles > 0)
+	if (!of_property_read_u32(np, "mrvl,clk-delay-cycles",
+				  &clk_delay_cycles))
 		pdata->clk_delay_cycles = clk_delay_cycles;
 
 	return pdata;
@@ -295,12 +327,8 @@ static int sdhci_pxav3_probe(struct platform_device *pdev)
 	if (IS_ERR(host))
 		return PTR_ERR(host);
 
-	if (of_device_is_compatible(np, "marvell,armada-380-sdhci")) {
-		ret = mv_conf_mbus_windows(pdev, mv_mbus_dram_info());
-		if (ret < 0)
-			goto err_mbus_win;
-	}
-
+	/* enable 1/8V DDR capable */
+	host->mmc->caps |= MMC_CAP_1_8V_DDR;
 
 	pltfm_host = sdhci_priv(host);
 	pltfm_host->priv = pxa;
@@ -314,8 +342,14 @@ static int sdhci_pxav3_probe(struct platform_device *pdev)
 	pltfm_host->clk = clk;
 	clk_prepare_enable(clk);
 
-	/* enable 1/8V DDR capable */
-	host->mmc->caps |= MMC_CAP_1_8V_DDR;
+	if (of_device_is_compatible(np, "marvell,armada-380-sdhci")) {
+		ret = armada_38x_quirks(pdev, host);
+		if (ret < 0)
+			goto err_clk_get;
+		ret = mv_conf_mbus_windows(pdev, mv_mbus_dram_info());
+		if (ret < 0)
+			goto err_mbus_win;
+	}
 
 	match = of_match_device(of_match_ptr(sdhci_pxav3_of_match), &pdev->dev);
 	if (match) {
@@ -355,10 +389,11 @@ static int sdhci_pxav3_probe(struct platform_device *pdev)
 		}
 	}
 
-	pm_runtime_enable(&pdev->dev);
-	pm_runtime_get_sync(&pdev->dev);
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
 	pm_runtime_set_autosuspend_delay(&pdev->dev, PXAV3_RPM_DELAY_MS);
 	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
 	pm_suspend_ignore_children(&pdev->dev, 1);
 
 	ret = sdhci_add_host(host);
@@ -381,13 +416,13 @@ static int sdhci_pxav3_probe(struct platform_device *pdev)
 	return 0;
 
 err_add_host:
-	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+	pm_runtime_put_noidle(&pdev->dev);
 err_of_parse:
 err_cd_req:
+err_mbus_win:
 	clk_disable_unprepare(clk);
 err_clk_get:
-err_mbus_win:
 	sdhci_pltfm_free(pdev);
 	return ret;
 }
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index ada1a3ea3a8..023c2010cd7 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1239,6 +1239,12 @@ static void sdhci_set_power(struct sdhci_host *host, unsigned char mode,
 		spin_unlock_irq(&host->lock);
 		mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, vdd);
 		spin_lock_irq(&host->lock);
+
+		if (mode != MMC_POWER_OFF)
+			sdhci_writeb(host, SDHCI_POWER_ON, SDHCI_POWER_CONTROL);
+		else
+			sdhci_writeb(host, 0, SDHCI_POWER_CONTROL);
+
 		return;
 	}
 
@@ -1319,6 +1325,8 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 
 	sdhci_runtime_pm_get(host);
 
+	present = mmc_gpio_get_cd(host->mmc);
+
 	spin_lock_irqsave(&host->lock, flags);
 
 	WARN_ON(host->mrq != NULL);
@@ -1347,7 +1355,6 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	 *     zero: cd-gpio is used, and card is removed
 	 *     one: cd-gpio is used, and card is present
 	 */
-	present = mmc_gpio_get_cd(host->mmc);
 	if (present < 0) {
 		/* If polling, assume that the card is always present. */
 		if (host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION)
@@ -2072,15 +2079,18 @@ static void sdhci_card_event(struct mmc_host *mmc)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
 	unsigned long flags;
+	int present;
 
 	/* First check if client has provided their own card event */
 	if (host->ops->card_event)
 		host->ops->card_event(host);
 
+	present = sdhci_do_get_cd(host);
+
 	spin_lock_irqsave(&host->lock, flags);
 
 	/* Check host->mrq first in case we are runtime suspended */
-	if (host->mrq && !sdhci_do_get_cd(host)) {
+	if (host->mrq && !present) {
 		pr_err("%s: Card removed during transfer!\n",
 			mmc_hostname(host->mmc));
 		pr_err("%s: Resetting controller.\n",
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index 7d9d6a32152..5165ae75d54 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -1402,7 +1402,7 @@ static int sh_mmcif_probe(struct platform_device *pdev)
 	host		= mmc_priv(mmc);
 	host->mmc	= mmc;
 	host->addr	= reg;
-	host->timeout	= msecs_to_jiffies(1000);
+	host->timeout	= msecs_to_jiffies(10000);
 	host->ccs_enable = !pd || !pd->ccs_unsupported;
 	host->clk_ctrl2_enable = pd && pd->clk_ctrl2_present;
 
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index d1663b3c414..aac659bdd08 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -909,7 +909,9 @@ static int sunxi_mmc_resource_request(struct sunxi_mmc_host *host,
 		return PTR_ERR(host->clk_mmc);
 	}
 
-	host->reset = devm_reset_control_get(&pdev->dev, "ahb");
+	host->reset = devm_reset_control_get_optional(&pdev->dev, "ahb");
+	if (PTR_ERR(host->reset) == -EPROBE_DEFER)
+		return PTR_ERR(host->reset);
 
 	ret = clk_prepare_enable(host->clk_ahb);
 	if (ret) {
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index ed827cf894e..dd8f66ccd2d 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -300,11 +300,11 @@ static const struct spi_device_id m25p_ids[] = {
 	{"m45pe10"},	{"m45pe80"},	{"m45pe16"},
 	{"m25pe20"},	{"m25pe80"},	{"m25pe16"},
 	{"m25px16"},	{"m25px32"},	{"m25px32-s0"},	{"m25px32-s1"},
-	{"m25px64"},
+	{"m25px64"},	{"m25px80"},
 	{"w25x10"},	{"w25x20"},	{"w25x40"},	{"w25x80"},
 	{"w25x16"},	{"w25x32"},	{"w25q32"},	{"w25q32dw"},
-	{"w25x64"},	{"w25q64"},	{"w25q128"},	{"w25q80"},
-	{"w25q80bl"},	{"w25q128"},	{"w25q256"},	{"cat25c11"},
+	{"w25x64"},	{"w25q64"},	{"w25q80"},	{"w25q80bl"},
+	{"w25q128"},	{"w25q256"},	{"cat25c11"},
 	{"cat25c03"},	{"cat25c09"},	{"cat25c17"},	{"cat25128"},
 	{ },
 };
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index d08229eb44d..3a69b1e5690 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -200,6 +200,7 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode)
 		return -ERESTARTSYS; /* FIXME: busy loop! -arnd*/
 
 	mutex_lock(&dev->lock);
+	mutex_lock(&mtd_table_mutex);
 
 	if (dev->open)
 		goto unlock;
@@ -223,6 +224,7 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode)
 
 unlock:
 	dev->open++;
+	mutex_unlock(&mtd_table_mutex);
 	mutex_unlock(&dev->lock);
 	blktrans_dev_put(dev);
 	return ret;
@@ -233,6 +235,7 @@ error_release:
 error_put:
 	module_put(dev->tr->owner);
 	kref_put(&dev->ref, blktrans_dev_release);
+	mutex_unlock(&mtd_table_mutex);
 	mutex_unlock(&dev->lock);
 	blktrans_dev_put(dev);
 	return ret;
@@ -246,6 +249,7 @@ static void blktrans_release(struct gendisk *disk, fmode_t mode)
 		return;
 
 	mutex_lock(&dev->lock);
+	mutex_lock(&mtd_table_mutex);
 
 	if (--dev->open)
 		goto unlock;
@@ -259,6 +263,7 @@ static void blktrans_release(struct gendisk *disk, fmode_t mode)
 		__put_mtd_device(dev->mtd);
 	}
 unlock:
+	mutex_unlock(&mtd_table_mutex);
 	mutex_unlock(&dev->lock);
 	blktrans_dev_put(dev);
 }
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index dd10646982a..0f7c07abc3e 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -1,3 +1,10 @@
+config MTD_NAND_IDS
+	tristate "Include chip ids for known NAND devices."
+	depends on MTD
+	help
+	  Useful for NAND drivers that do not use the NAND subsystem but
+	  still like to take advantage of the known chip information.
+
 config MTD_NAND_ECC
 	tristate
 
@@ -109,9 +116,6 @@ config MTD_NAND_OMAP_BCH
 config MTD_NAND_OMAP_BCH_BUILD
 	def_tristate MTD_NAND_OMAP2 && MTD_NAND_OMAP_BCH
 
-config MTD_NAND_IDS
-	tristate
-
 config MTD_NAND_RICOH
 	tristate "Ricoh xD card reader"
 	default n
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index 3b357e920a0..10d07dd20f7 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -1741,13 +1741,6 @@ static int omap_nand_probe(struct platform_device *pdev)
 		goto return_error;
 	}
 
-	/* check for small page devices */
-	if ((mtd->oobsize < 64) && (pdata->ecc_opt != OMAP_ECC_HAM1_CODE_HW)) {
-		dev_err(&info->pdev->dev, "small page devices are not supported\n");
-		err = -EINVAL;
-		goto return_error;
-	}
-
 	/* re-populate low-level callbacks based on xfer modes */
 	switch (pdata->xfer_type) {
 	case NAND_OMAP_PREFETCH_POLLED:
diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c
index 96b0b1d27df..bc677362bc7 100644
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
@@ -480,6 +480,42 @@ static void disable_int(struct pxa3xx_nand_info *info, uint32_t int_mask)
 	nand_writel(info, NDCR, ndcr | int_mask);
 }
 
+static void drain_fifo(struct pxa3xx_nand_info *info, void *data, int len)
+{
+	if (info->ecc_bch) {
+		int timeout;
+
+		/*
+		 * According to the datasheet, when reading from NDDB
+		 * with BCH enabled, after each 32 bytes reads, we
+		 * have to make sure that the NDSR.RDDREQ bit is set.
+		 *
+		 * Drain the FIFO 8 32 bits reads at a time, and skip
+		 * the polling on the last read.
+		 */
+		while (len > 8) {
+			__raw_readsl(info->mmio_base + NDDB, data, 8);
+
+			for (timeout = 0;
+			     !(nand_readl(info, NDSR) & NDSR_RDDREQ);
+			     timeout++) {
+				if (timeout >= 5) {
+					dev_err(&info->pdev->dev,
+						"Timeout on RDDREQ while draining the FIFO\n");
+					return;
+				}
+
+				mdelay(1);
+			}
+
+			data += 32;
+			len -= 8;
+		}
+	}
+
+	__raw_readsl(info->mmio_base + NDDB, data, len);
+}
+
 static void handle_data_pio(struct pxa3xx_nand_info *info)
 {
 	unsigned int do_bytes = min(info->data_size, info->chunk_size);
@@ -496,14 +532,14 @@ static void handle_data_pio(struct pxa3xx_nand_info *info)
 				      DIV_ROUND_UP(info->oob_size, 4));
 		break;
 	case STATE_PIO_READING:
-		__raw_readsl(info->mmio_base + NDDB,
-			     info->data_buff + info->data_buff_pos,
-			     DIV_ROUND_UP(do_bytes, 4));
+		drain_fifo(info,
+			   info->data_buff + info->data_buff_pos,
+			   DIV_ROUND_UP(do_bytes, 4));
 
 		if (info->oob_size > 0)
-			__raw_readsl(info->mmio_base + NDDB,
-				     info->oob_buff + info->oob_buff_pos,
-				     DIV_ROUND_UP(info->oob_size, 4));
+			drain_fifo(info,
+				   info->oob_buff + info->oob_buff_pos,
+				   DIV_ROUND_UP(info->oob_size, 4));
 		break;
 	default:
 		dev_err(&info->pdev->dev, "%s: invalid state %d\n", __func__,
diff --git a/drivers/mtd/tests/torturetest.c b/drivers/mtd/tests/torturetest.c
index eeab96973cf..b55bc52a134 100644
--- a/drivers/mtd/tests/torturetest.c
+++ b/drivers/mtd/tests/torturetest.c
@@ -264,7 +264,9 @@ static int __init tort_init(void)
 		int i;
 		void *patt;
 
-		mtdtest_erase_good_eraseblocks(mtd, bad_ebs, eb, ebcnt);
+		err = mtdtest_erase_good_eraseblocks(mtd, bad_ebs, eb, ebcnt);
+		if (err)
+			goto out;
 
 		/* Check if the eraseblocks contain only 0xFF bytes */
 		if (check) {
diff --git a/drivers/mtd/ubi/attach.c b/drivers/mtd/ubi/attach.c
index 6f27d9a1be3..21841fe25ad 100644
--- a/drivers/mtd/ubi/attach.c
+++ b/drivers/mtd/ubi/attach.c
@@ -408,7 +408,7 @@ int ubi_compare_lebs(struct ubi_device *ubi, const struct ubi_ainf_peb *aeb,
 		second_is_newer = !second_is_newer;
 	} else {
 		dbg_bld("PEB %d CRC is OK", pnum);
-		bitflips = !!err;
+		bitflips |= !!err;
 	}
 	mutex_unlock(&ubi->buf_mutex);
 
diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c
index 59de69a24e4..3946d78e6a8 100644
--- a/drivers/mtd/ubi/cdev.c
+++ b/drivers/mtd/ubi/cdev.c
@@ -453,7 +453,7 @@ static long vol_cdev_ioctl(struct file *file, unsigned int cmd,
 		/* Validate the request */
 		err = -EINVAL;
 		if (req.lnum < 0 || req.lnum >= vol->reserved_pebs ||
-		    req.bytes < 0 || req.lnum >= vol->usable_leb_size)
+		    req.bytes < 0 || req.bytes > vol->usable_leb_size)
 			break;
 
 		err = get_exclusive(desc);
diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c
index 2402d3b5017..493f7b3dbc3 100644
--- a/drivers/mtd/ubi/eba.c
+++ b/drivers/mtd/ubi/eba.c
@@ -1361,7 +1361,8 @@ int ubi_eba_init(struct ubi_device *ubi, struct ubi_attach_info *ai)
 				 * during re-size.
 				 */
 				ubi_move_aeb_to_list(av, aeb, &ai->erase);
-			vol->eba_tbl[aeb->lnum] = aeb->pnum;
+			else
+				vol->eba_tbl[aeb->lnum] = aeb->pnum;
 		}
 	}
 
diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c
index ec2c2dc1c1c..2a1b6e037e1 100644
--- a/drivers/mtd/ubi/upd.c
+++ b/drivers/mtd/ubi/upd.c
@@ -133,6 +133,10 @@ int ubi_start_update(struct ubi_device *ubi, struct ubi_volume *vol,
 	ubi_assert(!vol->updating && !vol->changing_leb);
 	vol->updating = 1;
 
+	vol->upd_buf = vmalloc(ubi->leb_size);
+	if (!vol->upd_buf)
+		return -ENOMEM;
+
 	err = set_update_marker(ubi, vol);
 	if (err)
 		return err;
@@ -152,14 +156,12 @@ int ubi_start_update(struct ubi_device *ubi, struct ubi_volume *vol,
 		err = clear_update_marker(ubi, vol, 0);
 		if (err)
 			return err;
+
+		vfree(vol->upd_buf);
 		vol->updating = 0;
 		return 0;
 	}
 
-	vol->upd_buf = vmalloc(ubi->leb_size);
-	if (!vol->upd_buf)
-		return -ENOMEM;
-
 	vol->upd_ebs = div_u64(bytes + vol->usable_leb_size - 1,
 			       vol->usable_leb_size);
 	vol->upd_bytes = bytes;
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index 6654f191868..ef670560971 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -1001,7 +1001,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 				int shutdown)
 {
 	int err, scrubbing = 0, torture = 0, protect = 0, erroneous = 0;
-	int vol_id = -1, uninitialized_var(lnum);
+	int vol_id = -1, lnum = -1;
 #ifdef CONFIG_MTD_UBI_FASTMAP
 	int anchor = wrk->anchor;
 #endif
@@ -1212,7 +1212,6 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 
 	err = do_sync_erase(ubi, e1, vol_id, lnum, 0);
 	if (err) {
-		kmem_cache_free(ubi_wl_entry_slab, e1);
 		if (e2)
 			kmem_cache_free(ubi_wl_entry_slab, e2);
 		goto out_ro;
@@ -1226,10 +1225,8 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 		dbg_wl("PEB %d (LEB %d:%d) was put meanwhile, erase",
 		       e2->pnum, vol_id, lnum);
 		err = do_sync_erase(ubi, e2, vol_id, lnum, 0);
-		if (err) {
-			kmem_cache_free(ubi_wl_entry_slab, e2);
+		if (err)
 			goto out_ro;
-		}
 	}
 
 	dbg_wl("done");
@@ -1265,10 +1262,9 @@ out_not_moved:
 
 	ubi_free_vid_hdr(ubi, vid_hdr);
 	err = do_sync_erase(ubi, e2, vol_id, lnum, torture);
-	if (err) {
-		kmem_cache_free(ubi_wl_entry_slab, e2);
+	if (err)
 		goto out_ro;
-	}
+
 	mutex_unlock(&ubi->move_mutex);
 	return 0;
 
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index d2eadab787c..4a692845701 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -475,12 +475,8 @@ static void rlb_update_client(struct rlb_client_info *client_info)
 		skb->dev = client_info->slave->dev;
 
 		if (client_info->vlan_id) {
-			skb = vlan_put_tag(skb, htons(ETH_P_8021Q), client_info->vlan_id);
-			if (!skb) {
-				netdev_err(client_info->slave->bond->dev,
-					   "failed to insert VLAN tag\n");
-				continue;
-			}
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+					       client_info->vlan_id);
 		}
 
 		arp_xmit(skb);
@@ -951,13 +947,8 @@ static void alb_send_lp_vid(struct slave *slave, u8 mac_addr[],
 	skb->priority = TC_PRIO_CONTROL;
 	skb->dev = slave->dev;
 
-	if (vid) {
-		skb = vlan_put_tag(skb, vlan_proto, vid);
-		if (!skb) {
-			netdev_err(slave->bond->dev, "failed to insert VLAN tag\n");
-			return;
-		}
-	}
+	if (vid)
+		__vlan_hwaccel_put_tag(skb, vlan_proto, vid);
 
 	dev_queue_xmit(skb);
 }
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index a5115fb7cf3..1cc06c0e3e9 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2143,8 +2143,8 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op,
 
 		netdev_dbg(slave_dev, "inner tag: proto %X vid %X\n",
 			   ntohs(outer_tag->vlan_proto), tags->vlan_id);
-		skb = __vlan_put_tag(skb, tags->vlan_proto,
-				     tags->vlan_id);
+		skb = vlan_insert_tag_set_proto(skb, tags->vlan_proto,
+						tags->vlan_id);
 		if (!skb) {
 			net_err_ratelimited("failed to insert inner VLAN tag\n");
 			return;
@@ -2156,12 +2156,8 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op,
 	if (outer_tag->vlan_id) {
 		netdev_dbg(slave_dev, "outer tag: proto %X vid %X\n",
 			   ntohs(outer_tag->vlan_proto), outer_tag->vlan_id);
-		skb = vlan_put_tag(skb, outer_tag->vlan_proto,
-				   outer_tag->vlan_id);
-		if (!skb) {
-			net_err_ratelimited("failed to insert outer VLAN tag\n");
-			return;
-		}
+		__vlan_hwaccel_put_tag(skb, outer_tag->vlan_proto,
+				       outer_tag->vlan_id);
 	}
 
 xmit:
@@ -3799,7 +3795,8 @@ static inline int bond_slave_override(struct bonding *bond,
 	/* Find out if any slaves have the same mapping as this skb. */
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		if (slave->queue_id == skb->queue_mapping) {
-			if (bond_slave_can_tx(slave)) {
+			if (bond_slave_is_up(slave) &&
+			    slave->link == BOND_LINK_UP) {
 				bond_dev_queue_xmit(bond, skb, slave->dev);
 				return 0;
 			}
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index b62697f4a3d..f1c53944a2c 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -625,7 +625,7 @@ int __bond_opt_set(struct bonding *bond,
 out:
 	if (ret)
 		bond_opt_error_interpret(bond, opt, ret, val);
-	else
+	else if (bond->dev->reg_state == NETREG_REGISTERED)
 		call_netdevice_notifiers(NETDEV_CHANGEINFODATA, bond->dev);
 
 	return ret;
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index 8e78bb48f5a..60285820f7b 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -611,6 +611,10 @@ static void c_can_stop(struct net_device *dev)
 	struct c_can_priv *priv = netdev_priv(dev);
 
 	c_can_irq_control(priv, false);
+
+	/* put ctrl to init on stop to end ongoing transmission */
+	priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_INIT);
+
 	priv->can.state = CAN_STATE_STOPPED;
 }
 
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 2cfe5012e4e..573b53b38af 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -500,6 +500,10 @@ struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf)
 	skb->pkt_type = PACKET_BROADCAST;
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
 
+	skb_reset_mac_header(skb);
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+
 	can_skb_reserve(skb);
 	can_skb_prv(skb)->ifindex = dev->ifindex;
 
@@ -524,6 +528,10 @@ struct sk_buff *alloc_canfd_skb(struct net_device *dev,
 	skb->pkt_type = PACKET_BROADCAST;
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
 
+	skb_reset_mac_header(skb);
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+
 	can_skb_reserve(skb);
 	can_skb_prv(skb)->ifindex = dev->ifindex;
 
@@ -729,10 +737,14 @@ static int can_changelink(struct net_device *dev,
 		if (dev->flags & IFF_UP)
 			return -EBUSY;
 		cm = nla_data(data[IFLA_CAN_CTRLMODE]);
-		if (cm->flags & ~priv->ctrlmode_supported)
+
+		/* check whether changed bits are allowed to be modified */
+		if (cm->mask & ~priv->ctrlmode_supported)
 			return -EOPNOTSUPP;
+
+		/* clear bits to be modified and copy the flag values */
 		priv->ctrlmode &= ~cm->mask;
-		priv->ctrlmode |= cm->flags;
+		priv->ctrlmode |= (cm->flags & cm->mask);
 
 		/* CAN_CTRLMODE_FD can only be set when driver supports FD */
 		if (priv->ctrlmode & CAN_CTRLMODE_FD)
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 60f86bd0434..9768ba6387a 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -1224,12 +1224,19 @@ static int flexcan_probe(struct platform_device *pdev)
 	const struct flexcan_devtype_data *devtype_data;
 	struct net_device *dev;
 	struct flexcan_priv *priv;
+	struct regulator *reg_xceiver;
 	struct resource *mem;
 	struct clk *clk_ipg = NULL, *clk_per = NULL;
 	void __iomem *base;
 	int err, irq;
 	u32 clock_freq = 0;
 
+	reg_xceiver = devm_regulator_get(&pdev->dev, "xceiver");
+	if (PTR_ERR(reg_xceiver) == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+	else if (IS_ERR(reg_xceiver))
+		reg_xceiver = NULL;
+
 	if (pdev->dev.of_node)
 		of_property_read_u32(pdev->dev.of_node,
 						"clock-frequency", &clock_freq);
@@ -1291,9 +1298,7 @@ static int flexcan_probe(struct platform_device *pdev)
 	priv->pdata = dev_get_platdata(&pdev->dev);
 	priv->devtype_data = devtype_data;
 
-	priv->reg_xceiver = devm_regulator_get(&pdev->dev, "xceiver");
-	if (IS_ERR(priv->reg_xceiver))
-		priv->reg_xceiver = NULL;
+	priv->reg_xceiver = reg_xceiver;
 
 	netif_napi_add(dev, &priv->napi, flexcan_poll, FLEXCAN_NAPI_WEIGHT);
 
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index d7bc462aafd..244529881be 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -955,6 +955,11 @@ static struct net_device *alloc_m_can_dev(void)
 	priv->can.data_bittiming_const = &m_can_data_bittiming_const;
 	priv->can.do_set_mode = m_can_set_mode;
 	priv->can.do_get_berr_counter = m_can_get_berr_counter;
+
+	/* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.0.1 */
+	priv->can.ctrlmode = CAN_CTRLMODE_FD_NON_ISO;
+
+	/* CAN_CTRLMODE_FD_NON_ISO can not be changed with M_CAN IP v3.0.1 */
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
 					CAN_CTRLMODE_LISTENONLY |
 					CAN_CTRLMODE_BERR_REPORTING |
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 541fb7a0562..5d777956ae1 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -12,6 +12,7 @@
  * Copyright (C) 2012 Olivier Sobrie <olivier@sobrie.be>
  */
 
+#include <linux/kernel.h>
 #include <linux/completion.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
@@ -403,8 +404,15 @@ static int kvaser_usb_wait_msg(const struct kvaser_usb *dev, u8 id,
 		while (pos <= actual_len - MSG_HEADER_LEN) {
 			tmp = buf + pos;
 
-			if (!tmp->len)
-				break;
+			/* Handle messages crossing the USB endpoint max packet
+			 * size boundary. Check kvaser_usb_read_bulk_callback()
+			 * for further details.
+			 */
+			if (tmp->len == 0) {
+				pos = round_up(pos,
+					       dev->bulk_in->wMaxPacketSize);
+				continue;
+			}
 
 			if (pos + tmp->len > actual_len) {
 				dev_err(dev->udev->dev.parent,
@@ -587,7 +595,7 @@ static int kvaser_usb_simple_msg_async(struct kvaser_usb_net_priv *priv,
 			  usb_sndbulkpipe(dev->udev,
 					  dev->bulk_out->bEndpointAddress),
 			  buf, msg->len,
-			  kvaser_usb_simple_msg_callback, priv);
+			  kvaser_usb_simple_msg_callback, netdev);
 	usb_anchor_urb(urb, &priv->tx_submitted);
 
 	err = usb_submit_urb(urb, GFP_ATOMIC);
@@ -662,11 +670,6 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev,
 	priv = dev->nets[channel];
 	stats = &priv->netdev->stats;
 
-	if (status & M16C_STATE_BUS_RESET) {
-		kvaser_usb_unlink_tx_urbs(priv);
-		return;
-	}
-
 	skb = alloc_can_err_skb(priv->netdev, &cf);
 	if (!skb) {
 		stats->rx_dropped++;
@@ -677,7 +680,7 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev,
 
 	netdev_dbg(priv->netdev, "Error status: 0x%02x\n", status);
 
-	if (status & M16C_STATE_BUS_OFF) {
+	if (status & (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) {
 		cf->can_id |= CAN_ERR_BUSOFF;
 
 		priv->can.can_stats.bus_off++;
@@ -703,9 +706,7 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev,
 		}
 
 		new_state = CAN_STATE_ERROR_PASSIVE;
-	}
-
-	if (status == M16C_STATE_BUS_ERROR) {
+	} else if (status & M16C_STATE_BUS_ERROR) {
 		if ((priv->can.state < CAN_STATE_ERROR_WARNING) &&
 		    ((txerr >= 96) || (rxerr >= 96))) {
 			cf->can_id |= CAN_ERR_CRTL;
@@ -715,7 +716,8 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev,
 
 			priv->can.can_stats.error_warning++;
 			new_state = CAN_STATE_ERROR_WARNING;
-		} else if (priv->can.state > CAN_STATE_ERROR_ACTIVE) {
+		} else if ((priv->can.state > CAN_STATE_ERROR_ACTIVE) &&
+			   ((txerr < 96) && (rxerr < 96))) {
 			cf->can_id |= CAN_ERR_PROT;
 			cf->data[2] = CAN_ERR_PROT_ACTIVE;
 
@@ -989,8 +991,19 @@ static void kvaser_usb_read_bulk_callback(struct urb *urb)
 	while (pos <= urb->actual_length - MSG_HEADER_LEN) {
 		msg = urb->transfer_buffer + pos;
 
-		if (!msg->len)
-			break;
+		/* The Kvaser firmware can only read and write messages that
+		 * does not cross the USB's endpoint wMaxPacketSize boundary.
+		 * If a follow-up command crosses such boundary, firmware puts
+		 * a placeholder zero-length command in its place then aligns
+		 * the real command to the next max packet size.
+		 *
+		 * Handle such cases or we're going to miss a significant
+		 * number of events in case of a heavy rx load on the bus.
+		 */
+		if (msg->len == 0) {
+			pos = round_up(pos, dev->bulk_in->wMaxPacketSize);
+			continue;
+		}
 
 		if (pos + msg->len > urb->actual_length) {
 			dev_err(dev->udev->dev.parent, "Format error\n");
@@ -998,7 +1011,6 @@ static void kvaser_usb_read_bulk_callback(struct urb *urb)
 		}
 
 		kvaser_usb_handle_message(dev, msg);
-
 		pos += msg->len;
 	}
 
@@ -1246,6 +1258,9 @@ static int kvaser_usb_close(struct net_device *netdev)
 	if (err)
 		netdev_warn(netdev, "Cannot stop device, error %d\n", err);
 
+	/* reset tx contexts */
+	kvaser_usb_unlink_tx_urbs(priv);
+
 	priv->can.state = CAN_STATE_STOPPED;
 	close_candev(priv->netdev);
 
@@ -1294,12 +1309,14 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb,
 	if (!urb) {
 		netdev_err(netdev, "No memory left for URBs\n");
 		stats->tx_dropped++;
-		goto nourbmem;
+		dev_kfree_skb(skb);
+		return NETDEV_TX_OK;
 	}
 
 	buf = kmalloc(sizeof(struct kvaser_msg), GFP_ATOMIC);
 	if (!buf) {
 		stats->tx_dropped++;
+		dev_kfree_skb(skb);
 		goto nobufmem;
 	}
 
@@ -1334,6 +1351,7 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb,
 		}
 	}
 
+	/* This should never happen; it implies a flow control bug */
 	if (!context) {
 		netdev_warn(netdev, "cannot find free context\n");
 		ret =  NETDEV_TX_BUSY;
@@ -1364,9 +1382,6 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb,
 	if (unlikely(err)) {
 		can_free_echo_skb(netdev, context->echo_index);
 
-		skb = NULL; /* set to NULL to avoid double free in
-			     * dev_kfree_skb(skb) */
-
 		atomic_dec(&priv->active_tx_urbs);
 		usb_unanchor_urb(urb);
 
@@ -1388,8 +1403,6 @@ releasebuf:
 	kfree(buf);
 nobufmem:
 	usb_free_urb(urb);
-nourbmem:
-	dev_kfree_skb(skb);
 	return ret;
 }
 
@@ -1502,6 +1515,10 @@ static int kvaser_usb_init_one(struct usb_interface *intf,
 	struct kvaser_usb_net_priv *priv;
 	int i, err;
 
+	err = kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, channel);
+	if (err)
+		return err;
+
 	netdev = alloc_candev(sizeof(*priv), MAX_TX_URBS);
 	if (!netdev) {
 		dev_err(&intf->dev, "Cannot alloc candev\n");
@@ -1588,7 +1605,7 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 {
 	struct kvaser_usb *dev;
 	int err = -ENOMEM;
-	int i;
+	int i, retry = 3;
 
 	dev = devm_kzalloc(&intf->dev, sizeof(*dev), GFP_KERNEL);
 	if (!dev)
@@ -1606,10 +1623,15 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 
 	usb_set_intfdata(intf, dev);
 
-	for (i = 0; i < MAX_NET_DEVICES; i++)
-		kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, i);
+	/* On some x86 laptops, plugging a Kvaser device again after
+	 * an unplug makes the firmware always ignore the very first
+	 * command. For such a case, provide some room for retries
+	 * instead of completely exiting the driver.
+	 */
+	do {
+		err = kvaser_usb_get_software_info(dev);
+	} while (--retry && err == -ETIMEDOUT);
 
-	err = kvaser_usb_get_software_info(dev);
 	if (err) {
 		dev_err(&intf->dev,
 			"Cannot get software infos, error %d\n", err);
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index 644e6ab8a48..dc807e10f80 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -735,7 +735,7 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter,
 	dev->cmd_buf = kmalloc(PCAN_USB_MAX_CMD_LEN, GFP_KERNEL);
 	if (!dev->cmd_buf) {
 		err = -ENOMEM;
-		goto lbl_set_intf_data;
+		goto lbl_free_candev;
 	}
 
 	dev->udev = usb_dev;
@@ -775,7 +775,7 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter,
 	err = register_candev(netdev);
 	if (err) {
 		dev_err(&intf->dev, "couldn't register CAN device: %d\n", err);
-		goto lbl_free_cmd_buf;
+		goto lbl_restore_intf_data;
 	}
 
 	if (dev->prev_siblings)
@@ -788,14 +788,14 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter,
 	if (dev->adapter->dev_init) {
 		err = dev->adapter->dev_init(dev);
 		if (err)
-			goto lbl_free_cmd_buf;
+			goto lbl_unregister_candev;
 	}
 
 	/* set bus off */
 	if (dev->adapter->dev_set_bus) {
 		err = dev->adapter->dev_set_bus(dev, 0);
 		if (err)
-			goto lbl_free_cmd_buf;
+			goto lbl_unregister_candev;
 	}
 
 	/* get device number early */
@@ -807,11 +807,14 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter,
 
 	return 0;
 
-lbl_free_cmd_buf:
-	kfree(dev->cmd_buf);
+lbl_unregister_candev:
+	unregister_candev(netdev);
 
-lbl_set_intf_data:
+lbl_restore_intf_data:
 	usb_set_intfdata(intf, dev->prev_siblings);
+	kfree(dev->cmd_buf);
+
+lbl_free_candev:
 	free_candev(netdev);
 
 	return err;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
index 263dd921edc..f7f796a2c50 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
@@ -333,8 +333,6 @@ static int pcan_usb_pro_send_req(struct peak_usb_device *dev, int req_id,
 	if (!(dev->state & PCAN_USB_STATE_CONNECTED))
 		return 0;
 
-	memset(req_addr, '\0', req_size);
-
 	req_type = USB_TYPE_VENDOR | USB_RECIP_OTHER;
 
 	switch (req_id) {
@@ -345,6 +343,7 @@ static int pcan_usb_pro_send_req(struct peak_usb_device *dev, int req_id,
 	default:
 		p = usb_rcvctrlpipe(dev->udev, 0);
 		req_type |= USB_DIR_IN;
+		memset(req_addr, '\0', req_size);
 		break;
 	}
 
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index e2e3aaf501a..30f088be6a1 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -1543,7 +1543,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
 {
 	struct pcnet32_private *lp;
 	int i, media;
-	int fdx, mii, fset, dxsuflo;
+	int fdx, mii, fset, dxsuflo, sram;
 	int chip_version;
 	char *chipname;
 	struct net_device *dev;
@@ -1580,7 +1580,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
 	}
 
 	/* initialize variables */
-	fdx = mii = fset = dxsuflo = 0;
+	fdx = mii = fset = dxsuflo = sram = 0;
 	chip_version = (chip_version >> 12) & 0xffff;
 
 	switch (chip_version) {
@@ -1613,6 +1613,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
 		chipname = "PCnet/FAST III 79C973";	/* PCI */
 		fdx = 1;
 		mii = 1;
+		sram = 1;
 		break;
 	case 0x2626:
 		chipname = "PCnet/Home 79C978";	/* PCI */
@@ -1636,6 +1637,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
 		chipname = "PCnet/FAST III 79C975";	/* PCI */
 		fdx = 1;
 		mii = 1;
+		sram = 1;
 		break;
 	case 0x2628:
 		chipname = "PCnet/PRO 79C976";
@@ -1664,6 +1666,31 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
 		dxsuflo = 1;
 	}
 
+	/*
+	 * The Am79C973/Am79C975 controllers come with 12K of SRAM
+	 * which we can use for the Tx/Rx buffers but most importantly,
+	 * the use of SRAM allow us to use the BCR18:NOUFLO bit to avoid
+	 * Tx fifo underflows.
+	 */
+	if (sram) {
+		/*
+		 * The SRAM is being configured in two steps. First we
+		 * set the SRAM size in the BCR25:SRAM_SIZE bits. According
+		 * to the datasheet, each bit corresponds to a 512-byte
+		 * page so we can have at most 24 pages. The SRAM_SIZE
+		 * holds the value of the upper 8 bits of the 16-bit SRAM size.
+		 * The low 8-bits start at 0x00 and end at 0xff. So the
+		 * address range is from 0x0000 up to 0x17ff. Therefore,
+		 * the SRAM_SIZE is set to 0x17. The next step is to set
+		 * the BCR26:SRAM_BND midway through so the Tx and Rx
+		 * buffers can share the SRAM equally.
+		 */
+		a->write_bcr(ioaddr, 25, 0x17);
+		a->write_bcr(ioaddr, 26, 0xc);
+		/* And finally enable the NOUFLO bit */
+		a->write_bcr(ioaddr, 18, a->read_bcr(ioaddr, 18) | (1 << 11));
+	}
+
 	dev = alloc_etherdev(sizeof(*lp));
 	if (!dev) {
 		ret = -ENOMEM;
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index e398eda0729..c8af3ce3ea3 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -184,15 +184,16 @@ static void alx_schedule_reset(struct alx_priv *alx)
 	schedule_work(&alx->reset_wk);
 }
 
-static bool alx_clean_rx_irq(struct alx_priv *alx, int budget)
+static int alx_clean_rx_irq(struct alx_priv *alx, int budget)
 {
 	struct alx_rx_queue *rxq = &alx->rxq;
 	struct alx_rrd *rrd;
 	struct alx_buffer *rxb;
 	struct sk_buff *skb;
 	u16 length, rfd_cleaned = 0;
+	int work = 0;
 
-	while (budget > 0) {
+	while (work < budget) {
 		rrd = &rxq->rrd[rxq->rrd_read_idx];
 		if (!(rrd->word3 & cpu_to_le32(1 << RRD_UPDATED_SHIFT)))
 			break;
@@ -203,7 +204,7 @@ static bool alx_clean_rx_irq(struct alx_priv *alx, int budget)
 		    ALX_GET_FIELD(le32_to_cpu(rrd->word0),
 				  RRD_NOR) != 1) {
 			alx_schedule_reset(alx);
-			return 0;
+			return work;
 		}
 
 		rxb = &rxq->bufs[rxq->read_idx];
@@ -243,7 +244,7 @@ static bool alx_clean_rx_irq(struct alx_priv *alx, int budget)
 		}
 
 		napi_gro_receive(&alx->napi, skb);
-		budget--;
+		work++;
 
 next_pkt:
 		if (++rxq->read_idx == alx->rx_ringsz)
@@ -258,21 +259,22 @@ next_pkt:
 	if (rfd_cleaned)
 		alx_refill_rx_ring(alx, GFP_ATOMIC);
 
-	return budget > 0;
+	return work;
 }
 
 static int alx_poll(struct napi_struct *napi, int budget)
 {
 	struct alx_priv *alx = container_of(napi, struct alx_priv, napi);
 	struct alx_hw *hw = &alx->hw;
-	bool complete = true;
 	unsigned long flags;
+	bool tx_complete;
+	int work;
 
-	complete = alx_clean_tx_irq(alx) &&
-		   alx_clean_rx_irq(alx, budget);
+	tx_complete = alx_clean_tx_irq(alx);
+	work = alx_clean_rx_irq(alx, budget);
 
-	if (!complete)
-		return 1;
+	if (!tx_complete || work == budget)
+		return budget;
 
 	napi_complete(&alx->napi);
 
@@ -284,7 +286,7 @@ static int alx_poll(struct napi_struct *napi, int budget)
 
 	alx_post_write(hw);
 
-	return 0;
+	return work;
 }
 
 static irqreturn_t alx_intr_handle(struct alx_priv *alx, u32 intr)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index c3a6072134f..2559206d870 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -531,20 +531,8 @@ struct bnx2x_fastpath {
 	struct napi_struct	napi;
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
-	unsigned int state;
-#define BNX2X_FP_STATE_IDLE		      0
-#define BNX2X_FP_STATE_NAPI		(1 << 0)    /* NAPI owns this FP */
-#define BNX2X_FP_STATE_POLL		(1 << 1)    /* poll owns this FP */
-#define BNX2X_FP_STATE_DISABLED		(1 << 2)
-#define BNX2X_FP_STATE_NAPI_YIELD	(1 << 3)    /* NAPI yielded this FP */
-#define BNX2X_FP_STATE_POLL_YIELD	(1 << 4)    /* poll yielded this FP */
-#define BNX2X_FP_OWNED	(BNX2X_FP_STATE_NAPI | BNX2X_FP_STATE_POLL)
-#define BNX2X_FP_YIELD	(BNX2X_FP_STATE_NAPI_YIELD | BNX2X_FP_STATE_POLL_YIELD)
-#define BNX2X_FP_LOCKED	(BNX2X_FP_OWNED | BNX2X_FP_STATE_DISABLED)
-#define BNX2X_FP_USER_PEND (BNX2X_FP_STATE_POLL | BNX2X_FP_STATE_POLL_YIELD)
-	/* protect state */
-	spinlock_t lock;
-#endif /* CONFIG_NET_RX_BUSY_POLL */
+	unsigned long		busy_poll_state;
+#endif
 
 	union host_hc_status_block	status_blk;
 	/* chip independent shortcuts into sb structure */
@@ -619,104 +607,83 @@ struct bnx2x_fastpath {
 #define bnx2x_fp_qstats(bp, fp)	(&((bp)->fp_stats[(fp)->index].eth_q_stats))
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
-static inline void bnx2x_fp_init_lock(struct bnx2x_fastpath *fp)
+
+enum bnx2x_fp_state {
+	BNX2X_STATE_FP_NAPI	= BIT(0), /* NAPI handler owns the queue */
+
+	BNX2X_STATE_FP_NAPI_REQ_BIT = 1, /* NAPI would like to own the queue */
+	BNX2X_STATE_FP_NAPI_REQ = BIT(1),
+
+	BNX2X_STATE_FP_POLL_BIT = 2,
+	BNX2X_STATE_FP_POLL     = BIT(2), /* busy_poll owns the queue */
+
+	BNX2X_STATE_FP_DISABLE_BIT = 3, /* queue is dismantled */
+};
+
+static inline void bnx2x_fp_busy_poll_init(struct bnx2x_fastpath *fp)
 {
-	spin_lock_init(&fp->lock);
-	fp->state = BNX2X_FP_STATE_IDLE;
+	WRITE_ONCE(fp->busy_poll_state, 0);
 }
 
 /* called from the device poll routine to get ownership of a FP */
 static inline bool bnx2x_fp_lock_napi(struct bnx2x_fastpath *fp)
 {
-	bool rc = true;
-
-	spin_lock_bh(&fp->lock);
-	if (fp->state & BNX2X_FP_LOCKED) {
-		WARN_ON(fp->state & BNX2X_FP_STATE_NAPI);
-		fp->state |= BNX2X_FP_STATE_NAPI_YIELD;
-		rc = false;
-	} else {
-		/* we don't care if someone yielded */
-		fp->state = BNX2X_FP_STATE_NAPI;
+	unsigned long prev, old = READ_ONCE(fp->busy_poll_state);
+
+	while (1) {
+		switch (old) {
+		case BNX2X_STATE_FP_POLL:
+			/* make sure bnx2x_fp_lock_poll() wont starve us */
+			set_bit(BNX2X_STATE_FP_NAPI_REQ_BIT,
+				&fp->busy_poll_state);
+			/* fallthrough */
+		case BNX2X_STATE_FP_POLL | BNX2X_STATE_FP_NAPI_REQ:
+			return false;
+		default:
+			break;
+		}
+		prev = cmpxchg(&fp->busy_poll_state, old, BNX2X_STATE_FP_NAPI);
+		if (unlikely(prev != old)) {
+			old = prev;
+			continue;
+		}
+		return true;
 	}
-	spin_unlock_bh(&fp->lock);
-	return rc;
 }
 
-/* returns true is someone tried to get the FP while napi had it */
-static inline bool bnx2x_fp_unlock_napi(struct bnx2x_fastpath *fp)
+static inline void bnx2x_fp_unlock_napi(struct bnx2x_fastpath *fp)
 {
-	bool rc = false;
-
-	spin_lock_bh(&fp->lock);
-	WARN_ON(fp->state &
-		(BNX2X_FP_STATE_POLL | BNX2X_FP_STATE_NAPI_YIELD));
-
-	if (fp->state & BNX2X_FP_STATE_POLL_YIELD)
-		rc = true;
-
-	/* state ==> idle, unless currently disabled */
-	fp->state &= BNX2X_FP_STATE_DISABLED;
-	spin_unlock_bh(&fp->lock);
-	return rc;
+	smp_wmb();
+	fp->busy_poll_state = 0;
 }
 
 /* called from bnx2x_low_latency_poll() */
 static inline bool bnx2x_fp_lock_poll(struct bnx2x_fastpath *fp)
 {
-	bool rc = true;
-
-	spin_lock_bh(&fp->lock);
-	if ((fp->state & BNX2X_FP_LOCKED)) {
-		fp->state |= BNX2X_FP_STATE_POLL_YIELD;
-		rc = false;
-	} else {
-		/* preserve yield marks */
-		fp->state |= BNX2X_FP_STATE_POLL;
-	}
-	spin_unlock_bh(&fp->lock);
-	return rc;
+	return cmpxchg(&fp->busy_poll_state, 0, BNX2X_STATE_FP_POLL) == 0;
 }
 
-/* returns true if someone tried to get the FP while it was locked */
-static inline bool bnx2x_fp_unlock_poll(struct bnx2x_fastpath *fp)
+static inline void bnx2x_fp_unlock_poll(struct bnx2x_fastpath *fp)
 {
-	bool rc = false;
-
-	spin_lock_bh(&fp->lock);
-	WARN_ON(fp->state & BNX2X_FP_STATE_NAPI);
-
-	if (fp->state & BNX2X_FP_STATE_POLL_YIELD)
-		rc = true;
-
-	/* state ==> idle, unless currently disabled */
-	fp->state &= BNX2X_FP_STATE_DISABLED;
-	spin_unlock_bh(&fp->lock);
-	return rc;
+	smp_mb__before_atomic();
+	clear_bit(BNX2X_STATE_FP_POLL_BIT, &fp->busy_poll_state);
 }
 
-/* true if a socket is polling, even if it did not get the lock */
+/* true if a socket is polling */
 static inline bool bnx2x_fp_ll_polling(struct bnx2x_fastpath *fp)
 {
-	WARN_ON(!(fp->state & BNX2X_FP_OWNED));
-	return fp->state & BNX2X_FP_USER_PEND;
+	return READ_ONCE(fp->busy_poll_state) & BNX2X_STATE_FP_POLL;
 }
 
 /* false if fp is currently owned */
 static inline bool bnx2x_fp_ll_disable(struct bnx2x_fastpath *fp)
 {
-	int rc = true;
-
-	spin_lock_bh(&fp->lock);
-	if (fp->state & BNX2X_FP_OWNED)
-		rc = false;
-	fp->state |= BNX2X_FP_STATE_DISABLED;
-	spin_unlock_bh(&fp->lock);
+	set_bit(BNX2X_STATE_FP_DISABLE_BIT, &fp->busy_poll_state);
+	return !bnx2x_fp_ll_polling(fp);
 
-	return rc;
 }
 #else
-static inline void bnx2x_fp_init_lock(struct bnx2x_fastpath *fp)
+static inline void bnx2x_fp_busy_poll_init(struct bnx2x_fastpath *fp)
 {
 }
 
@@ -725,9 +692,8 @@ static inline bool bnx2x_fp_lock_napi(struct bnx2x_fastpath *fp)
 	return true;
 }
 
-static inline bool bnx2x_fp_unlock_napi(struct bnx2x_fastpath *fp)
+static inline void bnx2x_fp_unlock_napi(struct bnx2x_fastpath *fp)
 {
-	return false;
 }
 
 static inline bool bnx2x_fp_lock_poll(struct bnx2x_fastpath *fp)
@@ -735,9 +701,8 @@ static inline bool bnx2x_fp_lock_poll(struct bnx2x_fastpath *fp)
 	return false;
 }
 
-static inline bool bnx2x_fp_unlock_poll(struct bnx2x_fastpath *fp)
+static inline void bnx2x_fp_unlock_poll(struct bnx2x_fastpath *fp)
 {
-	return false;
 }
 
 static inline bool bnx2x_fp_ll_polling(struct bnx2x_fastpath *fp)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 40beef5bca8..e36e3a50b34 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1849,7 +1849,7 @@ static void bnx2x_napi_enable_cnic(struct bnx2x *bp)
 	int i;
 
 	for_each_rx_queue_cnic(bp, i) {
-		bnx2x_fp_init_lock(&bp->fp[i]);
+		bnx2x_fp_busy_poll_init(&bp->fp[i]);
 		napi_enable(&bnx2x_fp(bp, i, napi));
 	}
 }
@@ -1859,7 +1859,7 @@ static void bnx2x_napi_enable(struct bnx2x *bp)
 	int i;
 
 	for_each_eth_queue(bp, i) {
-		bnx2x_fp_init_lock(&bp->fp[i]);
+		bnx2x_fp_busy_poll_init(&bp->fp[i]);
 		napi_enable(&bnx2x_fp(bp, i, napi));
 	}
 }
@@ -3175,7 +3175,7 @@ static int bnx2x_poll(struct napi_struct *napi, int budget)
 		}
 #endif
 		if (!bnx2x_fp_lock_napi(fp))
-			return work_done;
+			return budget;
 
 		for_each_cos_in_tx_queue(fp, cos)
 			if (bnx2x_tx_queue_has_work(fp->txdata_ptr[cos]))
@@ -3191,9 +3191,10 @@ static int bnx2x_poll(struct napi_struct *napi, int budget)
 			}
 		}
 
+		bnx2x_fp_unlock_napi(fp);
+
 		/* Fall out from the NAPI loop if needed */
-		if (!bnx2x_fp_unlock_napi(fp) &&
-		    !(bnx2x_has_rx_work(fp) || bnx2x_has_tx_work(fp))) {
+		if (!(bnx2x_has_rx_work(fp) || bnx2x_has_tx_work(fp))) {
 
 			/* No need to update SB for FCoE L2 ring as long as
 			 * it's connected to the default SB and the SB
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 74fbf9ea7bd..1217eafb61a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -9307,7 +9307,8 @@ unload_error:
 	 * function stop ramrod is sent, since as part of this ramrod FW access
 	 * PTP registers.
 	 */
-	bnx2x_stop_ptp(bp);
+	if (bp->flags & PTP_SUPPORTED)
+		bnx2x_stop_ptp(bp);
 
 	/* Disable HW interrupts, NAPI */
 	bnx2x_netif_stop(bp, 1);
@@ -12711,6 +12712,9 @@ static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev,
 	pci_write_config_dword(bp->pdev, PCICFG_GRC_ADDRESS,
 			       PCICFG_VENDOR_ID_OFFSET);
 
+	/* Set PCIe reset type to fundamental for EEH recovery */
+	pdev->needs_freset = 1;
+
 	/* AER (Advanced Error reporting) configuration */
 	rc = pci_enable_pcie_error_reporting(pdev);
 	if (!rc)
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index da1a2500c91..bb27028d392 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -872,13 +872,14 @@ static inline void bcmgenet_tx_ring_int_disable(struct bcmgenet_priv *priv,
 }
 
 /* Unlocked version of the reclaim routine */
-static void __bcmgenet_tx_reclaim(struct net_device *dev,
-				  struct bcmgenet_tx_ring *ring)
+static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
+					  struct bcmgenet_tx_ring *ring)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	int last_tx_cn, last_c_index, num_tx_bds;
 	struct enet_cb *tx_cb_ptr;
 	struct netdev_queue *txq;
+	unsigned int pkts_compl = 0;
 	unsigned int bds_compl;
 	unsigned int c_index;
 
@@ -906,6 +907,7 @@ static void __bcmgenet_tx_reclaim(struct net_device *dev,
 		tx_cb_ptr = ring->cbs + last_c_index;
 		bds_compl = 0;
 		if (tx_cb_ptr->skb) {
+			pkts_compl++;
 			bds_compl = skb_shinfo(tx_cb_ptr->skb)->nr_frags + 1;
 			dev->stats.tx_bytes += tx_cb_ptr->skb->len;
 			dma_unmap_single(&dev->dev,
@@ -929,23 +931,45 @@ static void __bcmgenet_tx_reclaim(struct net_device *dev,
 		last_c_index &= (num_tx_bds - 1);
 	}
 
-	if (ring->free_bds > (MAX_SKB_FRAGS + 1))
-		ring->int_disable(priv, ring);
-
-	if (netif_tx_queue_stopped(txq))
-		netif_tx_wake_queue(txq);
+	if (ring->free_bds > (MAX_SKB_FRAGS + 1)) {
+		if (netif_tx_queue_stopped(txq))
+			netif_tx_wake_queue(txq);
+	}
 
 	ring->c_index = c_index;
+
+	return pkts_compl;
 }
 
-static void bcmgenet_tx_reclaim(struct net_device *dev,
+static unsigned int bcmgenet_tx_reclaim(struct net_device *dev,
 				struct bcmgenet_tx_ring *ring)
 {
+	unsigned int released;
 	unsigned long flags;
 
 	spin_lock_irqsave(&ring->lock, flags);
-	__bcmgenet_tx_reclaim(dev, ring);
+	released = __bcmgenet_tx_reclaim(dev, ring);
 	spin_unlock_irqrestore(&ring->lock, flags);
+
+	return released;
+}
+
+static int bcmgenet_tx_poll(struct napi_struct *napi, int budget)
+{
+	struct bcmgenet_tx_ring *ring =
+		container_of(napi, struct bcmgenet_tx_ring, napi);
+	unsigned int work_done = 0;
+
+	work_done = bcmgenet_tx_reclaim(ring->priv->dev, ring);
+
+	if (work_done == 0) {
+		napi_complete(napi);
+		ring->int_enable(ring->priv, ring);
+
+		return 0;
+	}
+
+	return budget;
 }
 
 static void bcmgenet_tx_reclaim_all(struct net_device *dev)
@@ -1201,10 +1225,8 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 	bcmgenet_tdma_ring_writel(priv, ring->index,
 				  ring->prod_index, TDMA_PROD_INDEX);
 
-	if (ring->free_bds <= (MAX_SKB_FRAGS + 1)) {
+	if (ring->free_bds <= (MAX_SKB_FRAGS + 1))
 		netif_tx_stop_queue(txq);
-		ring->int_enable(priv, ring);
-	}
 
 out:
 	spin_unlock_irqrestore(&ring->lock, flags);
@@ -1517,6 +1539,7 @@ static int init_umac(struct bcmgenet_priv *priv)
 	struct device *kdev = &priv->pdev->dev;
 	int ret;
 	u32 reg, cpu_mask_clear;
+	int index;
 
 	dev_dbg(&priv->pdev->dev, "bcmgenet: init_umac\n");
 
@@ -1543,7 +1566,7 @@ static int init_umac(struct bcmgenet_priv *priv)
 
 	bcmgenet_intr_disable(priv);
 
-	cpu_mask_clear = UMAC_IRQ_RXDMA_BDONE;
+	cpu_mask_clear = UMAC_IRQ_RXDMA_BDONE | UMAC_IRQ_TXDMA_BDONE;
 
 	dev_dbg(kdev, "%s:Enabling RXDMA_BDONE interrupt\n", __func__);
 
@@ -1570,6 +1593,10 @@ static int init_umac(struct bcmgenet_priv *priv)
 
 	bcmgenet_intrl2_0_writel(priv, cpu_mask_clear, INTRL2_CPU_MASK_CLEAR);
 
+	for (index = 0; index < priv->hw_params->tx_queues; index++)
+		bcmgenet_intrl2_1_writel(priv, (1 << index),
+					 INTRL2_CPU_MASK_CLEAR);
+
 	/* Enable rx/tx engine.*/
 	dev_dbg(kdev, "done init umac\n");
 
@@ -1589,6 +1616,8 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
 	unsigned int first_bd;
 
 	spin_lock_init(&ring->lock);
+	ring->priv = priv;
+	netif_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll, 64);
 	ring->index = index;
 	if (index == DESC_INDEX) {
 		ring->queue = 0;
@@ -1634,6 +1663,17 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
 				  TDMA_WRITE_PTR);
 	bcmgenet_tdma_ring_writel(priv, index, end_ptr * words_per_bd - 1,
 				  DMA_END_ADDR);
+
+	napi_enable(&ring->napi);
+}
+
+static void bcmgenet_fini_tx_ring(struct bcmgenet_priv *priv,
+				  unsigned int index)
+{
+	struct bcmgenet_tx_ring *ring = &priv->tx_rings[index];
+
+	napi_disable(&ring->napi);
+	netif_napi_del(&ring->napi);
 }
 
 /* Initialize a RDMA ring */
@@ -1803,7 +1843,7 @@ static int bcmgenet_dma_teardown(struct bcmgenet_priv *priv)
 	return ret;
 }
 
-static void bcmgenet_fini_dma(struct bcmgenet_priv *priv)
+static void __bcmgenet_fini_dma(struct bcmgenet_priv *priv)
 {
 	int i;
 
@@ -1822,6 +1862,18 @@ static void bcmgenet_fini_dma(struct bcmgenet_priv *priv)
 	kfree(priv->tx_cbs);
 }
 
+static void bcmgenet_fini_dma(struct bcmgenet_priv *priv)
+{
+	int i;
+
+	bcmgenet_fini_tx_ring(priv, DESC_INDEX);
+
+	for (i = 0; i < priv->hw_params->tx_queues; i++)
+		bcmgenet_fini_tx_ring(priv, i);
+
+	__bcmgenet_fini_dma(priv);
+}
+
 /* init_edma: Initialize DMA control register */
 static int bcmgenet_init_dma(struct bcmgenet_priv *priv)
 {
@@ -1848,7 +1900,7 @@ static int bcmgenet_init_dma(struct bcmgenet_priv *priv)
 	priv->tx_cbs = kcalloc(priv->num_tx_bds, sizeof(struct enet_cb),
 			       GFP_KERNEL);
 	if (!priv->tx_cbs) {
-		bcmgenet_fini_dma(priv);
+		__bcmgenet_fini_dma(priv);
 		return -ENOMEM;
 	}
 
@@ -1871,9 +1923,6 @@ static int bcmgenet_poll(struct napi_struct *napi, int budget)
 			struct bcmgenet_priv, napi);
 	unsigned int work_done;
 
-	/* tx reclaim */
-	bcmgenet_tx_reclaim(priv->dev, &priv->tx_rings[DESC_INDEX]);
-
 	work_done = bcmgenet_desc_rx(priv, budget);
 
 	/* Advancing our consumer index*/
@@ -1918,28 +1967,34 @@ static void bcmgenet_irq_task(struct work_struct *work)
 static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
 {
 	struct bcmgenet_priv *priv = dev_id;
+	struct bcmgenet_tx_ring *ring;
 	unsigned int index;
 
 	/* Save irq status for bottom-half processing. */
 	priv->irq1_stat =
 		bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_STAT) &
-		~priv->int1_mask;
+		~bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_MASK_STATUS);
 	/* clear interrupts */
 	bcmgenet_intrl2_1_writel(priv, priv->irq1_stat, INTRL2_CPU_CLEAR);
 
 	netif_dbg(priv, intr, priv->dev,
 		  "%s: IRQ=0x%x\n", __func__, priv->irq1_stat);
+
 	/* Check the MBDONE interrupts.
 	 * packet is done, reclaim descriptors
 	 */
-	if (priv->irq1_stat & 0x0000ffff) {
-		index = 0;
-		for (index = 0; index < 16; index++) {
-			if (priv->irq1_stat & (1 << index))
-				bcmgenet_tx_reclaim(priv->dev,
-						    &priv->tx_rings[index]);
+	for (index = 0; index < priv->hw_params->tx_queues; index++) {
+		if (!(priv->irq1_stat & BIT(index)))
+			continue;
+
+		ring = &priv->tx_rings[index];
+
+		if (likely(napi_schedule_prep(&ring->napi))) {
+			ring->int_disable(priv, ring);
+			__napi_schedule(&ring->napi);
 		}
 	}
+
 	return IRQ_HANDLED;
 }
 
@@ -1971,8 +2026,12 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 	}
 	if (priv->irq0_stat &
 			(UMAC_IRQ_TXDMA_BDONE | UMAC_IRQ_TXDMA_PDONE)) {
-		/* Tx reclaim */
-		bcmgenet_tx_reclaim(priv->dev, &priv->tx_rings[DESC_INDEX]);
+		struct bcmgenet_tx_ring *ring = &priv->tx_rings[DESC_INDEX];
+
+		if (likely(napi_schedule_prep(&ring->napi))) {
+			ring->int_disable(priv, ring);
+			__napi_schedule(&ring->napi);
+		}
 	}
 	if (priv->irq0_stat & (UMAC_IRQ_PHY_DET_R |
 				UMAC_IRQ_PHY_DET_F |
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 31b2da5f9b8..eeda0281c68 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -495,6 +495,7 @@ struct bcmgenet_hw_params {
 
 struct bcmgenet_tx_ring {
 	spinlock_t	lock;		/* ring lock */
+	struct napi_struct napi;	/* NAPI per tx queue */
 	unsigned int	index;		/* ring index */
 	unsigned int	queue;		/* queue index */
 	struct enet_cb	*cbs;		/* tx ring buffer control block*/
@@ -509,6 +510,7 @@ struct bcmgenet_tx_ring {
 			   struct bcmgenet_tx_ring *);
 	void (*int_disable)(struct bcmgenet_priv *priv,
 			    struct bcmgenet_tx_ring *);
+	struct bcmgenet_priv *priv;
 };
 
 /* device context */
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 77f8f836cbb..a37800ecb27 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -17789,23 +17789,6 @@ static int tg3_init_one(struct pci_dev *pdev,
 		goto err_out_apeunmap;
 	}
 
-	/*
-	 * Reset chip in case UNDI or EFI driver did not shutdown
-	 * DMA self test will enable WDMAC and we'll see (spurious)
-	 * pending DMA on the PCI bus at that point.
-	 */
-	if ((tr32(HOSTCC_MODE) & HOSTCC_MODE_ENABLE) ||
-	    (tr32(WDMAC_MODE) & WDMAC_MODE_ENABLE)) {
-		tw32(MEMARB_MODE, MEMARB_MODE_ENABLE);
-		tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
-	}
-
-	err = tg3_test_dma(tp);
-	if (err) {
-		dev_err(&pdev->dev, "DMA engine test failed, aborting\n");
-		goto err_out_apeunmap;
-	}
-
 	intmbx = MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW;
 	rcvmbx = MAILBOX_RCVRET_CON_IDX_0 + TG3_64BIT_REG_LOW;
 	sndmbx = MAILBOX_SNDHOST_PROD_IDX_0 + TG3_64BIT_REG_LOW;
@@ -17850,6 +17833,25 @@ static int tg3_init_one(struct pci_dev *pdev,
 			sndmbx += 0xc;
 	}
 
+	/*
+	 * Reset chip in case UNDI or EFI driver did not shutdown
+	 * DMA self test will enable WDMAC and we'll see (spurious)
+	 * pending DMA on the PCI bus at that point.
+	 */
+	if ((tr32(HOSTCC_MODE) & HOSTCC_MODE_ENABLE) ||
+	    (tr32(WDMAC_MODE) & WDMAC_MODE_ENABLE)) {
+		tg3_full_lock(tp, 0);
+		tw32(MEMARB_MODE, MEMARB_MODE_ENABLE);
+		tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
+		tg3_full_unlock(tp);
+	}
+
+	err = tg3_test_dma(tp);
+	if (err) {
+		dev_err(&pdev->dev, "DMA engine test failed, aborting\n");
+		goto err_out_apeunmap;
+	}
+
 	tg3_init_coal(tp);
 
 	pci_set_drvdata(pdev, dev);
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 73cf1653a4a..167cd8ede39 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -1059,10 +1059,14 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
 				     PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3);
 		}
 
-		if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc) {
-			skb->csum = htons(checksum);
-			skb->ip_summed = CHECKSUM_COMPLETE;
-		}
+		/* Hardware does not provide whole packet checksum. It only
+		 * provides pseudo checksum. Since hw validates the packet
+		 * checksum but not provide us the checksum value. use
+		 * CHECSUM_UNNECESSARY.
+		 */
+		if ((netdev->features & NETIF_F_RXCSUM) && tcp_udp_csum_ok &&
+		    ipv4_csum_ok)
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 		if (vlan_stripped)
 			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci);
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index fead5c65a4f..9c827b7642e 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1705,9 +1705,9 @@ int be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf)
 	total_size = buf_len;
 
 	get_fat_cmd.size = sizeof(struct be_cmd_req_get_fat) + 60*1024;
-	get_fat_cmd.va = pci_alloc_consistent(adapter->pdev,
-					      get_fat_cmd.size,
-					      &get_fat_cmd.dma);
+	get_fat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					     get_fat_cmd.size,
+					     &get_fat_cmd.dma, GFP_ATOMIC);
 	if (!get_fat_cmd.va) {
 		dev_err(&adapter->pdev->dev,
 			"Memory allocation failure while reading FAT data\n");
@@ -1752,8 +1752,8 @@ int be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf)
 		log_offset += buf_size;
 	}
 err:
-	pci_free_consistent(adapter->pdev, get_fat_cmd.size,
-			    get_fat_cmd.va, get_fat_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, get_fat_cmd.size,
+			  get_fat_cmd.va, get_fat_cmd.dma);
 	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
@@ -2223,12 +2223,12 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 		return -EINVAL;
 
 	cmd.size = sizeof(struct be_cmd_resp_port_type);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory allocation failed\n");
 		return -ENOMEM;
 	}
-	memset(cmd.va, 0, cmd.size);
 
 	spin_lock_bh(&adapter->mcc_lock);
 
@@ -2253,7 +2253,7 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 	}
 err:
 	spin_unlock_bh(&adapter->mcc_lock);
-	pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 	return status;
 }
 
@@ -2702,7 +2702,8 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 		goto err;
 	}
 	cmd.size = sizeof(struct be_cmd_req_get_phy_info);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
 		status = -ENOMEM;
@@ -2736,7 +2737,7 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 				BE_SUPPORTED_SPEED_1GBPS;
 		}
 	}
-	pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 err:
 	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
@@ -2787,8 +2788,9 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter)
 
 	memset(&attribs_cmd, 0, sizeof(struct be_dma_mem));
 	attribs_cmd.size = sizeof(struct be_cmd_resp_cntl_attribs);
-	attribs_cmd.va = pci_alloc_consistent(adapter->pdev, attribs_cmd.size,
-					      &attribs_cmd.dma);
+	attribs_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					     attribs_cmd.size,
+					     &attribs_cmd.dma, GFP_ATOMIC);
 	if (!attribs_cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory allocation failure\n");
 		status = -ENOMEM;
@@ -2815,8 +2817,8 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter)
 err:
 	mutex_unlock(&adapter->mbox_lock);
 	if (attribs_cmd.va)
-		pci_free_consistent(adapter->pdev, attribs_cmd.size,
-				    attribs_cmd.va, attribs_cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, attribs_cmd.size,
+				  attribs_cmd.va, attribs_cmd.dma);
 	return status;
 }
 
@@ -2954,9 +2956,10 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 
 	memset(&get_mac_list_cmd, 0, sizeof(struct be_dma_mem));
 	get_mac_list_cmd.size = sizeof(struct be_cmd_resp_get_mac_list);
-	get_mac_list_cmd.va = pci_alloc_consistent(adapter->pdev,
-						   get_mac_list_cmd.size,
-						   &get_mac_list_cmd.dma);
+	get_mac_list_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+						  get_mac_list_cmd.size,
+						  &get_mac_list_cmd.dma,
+						  GFP_ATOMIC);
 
 	if (!get_mac_list_cmd.va) {
 		dev_err(&adapter->pdev->dev,
@@ -3029,8 +3032,8 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 
 out:
 	spin_unlock_bh(&adapter->mcc_lock);
-	pci_free_consistent(adapter->pdev, get_mac_list_cmd.size,
-			    get_mac_list_cmd.va, get_mac_list_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, get_mac_list_cmd.size,
+			  get_mac_list_cmd.va, get_mac_list_cmd.dma);
 	return status;
 }
 
@@ -3083,8 +3086,8 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_req_set_mac_list);
-	cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size,
-				    &cmd.dma, GFP_KERNEL);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_KERNEL);
 	if (!cmd.va)
 		return -ENOMEM;
 
@@ -3255,7 +3258,8 @@ int be_cmd_get_acpi_wol_cap(struct be_adapter *adapter)
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_acpi_wol_magic_config_v1);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory allocation failure\n");
 		status = -ENOMEM;
@@ -3290,7 +3294,8 @@ int be_cmd_get_acpi_wol_cap(struct be_adapter *adapter)
 err:
 	mutex_unlock(&adapter->mbox_lock);
 	if (cmd.va)
-		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+				  cmd.dma);
 	return status;
 
 }
@@ -3304,8 +3309,9 @@ int be_cmd_set_fw_log_level(struct be_adapter *adapter, u32 level)
 
 	memset(&extfat_cmd, 0, sizeof(struct be_dma_mem));
 	extfat_cmd.size = sizeof(struct be_cmd_resp_get_ext_fat_caps);
-	extfat_cmd.va = pci_alloc_consistent(adapter->pdev, extfat_cmd.size,
-					     &extfat_cmd.dma);
+	extfat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					    extfat_cmd.size, &extfat_cmd.dma,
+					    GFP_ATOMIC);
 	if (!extfat_cmd.va)
 		return -ENOMEM;
 
@@ -3327,8 +3333,8 @@ int be_cmd_set_fw_log_level(struct be_adapter *adapter, u32 level)
 
 	status = be_cmd_set_ext_fat_capabilites(adapter, &extfat_cmd, cfgs);
 err:
-	pci_free_consistent(adapter->pdev, extfat_cmd.size, extfat_cmd.va,
-			    extfat_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, extfat_cmd.size, extfat_cmd.va,
+			  extfat_cmd.dma);
 	return status;
 }
 
@@ -3341,8 +3347,9 @@ int be_cmd_get_fw_log_level(struct be_adapter *adapter)
 
 	memset(&extfat_cmd, 0, sizeof(struct be_dma_mem));
 	extfat_cmd.size = sizeof(struct be_cmd_resp_get_ext_fat_caps);
-	extfat_cmd.va = pci_alloc_consistent(adapter->pdev, extfat_cmd.size,
-					     &extfat_cmd.dma);
+	extfat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					    extfat_cmd.size, &extfat_cmd.dma,
+					    GFP_ATOMIC);
 
 	if (!extfat_cmd.va) {
 		dev_err(&adapter->pdev->dev, "%s: Memory allocation failure\n",
@@ -3360,8 +3367,8 @@ int be_cmd_get_fw_log_level(struct be_adapter *adapter)
 				level = cfgs->module[0].trace_lvl[j].dbg_lvl;
 		}
 	}
-	pci_free_consistent(adapter->pdev, extfat_cmd.size, extfat_cmd.va,
-			    extfat_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, extfat_cmd.size, extfat_cmd.va,
+			  extfat_cmd.dma);
 err:
 	return level;
 }
@@ -3567,7 +3574,8 @@ int be_cmd_get_func_config(struct be_adapter *adapter, struct be_resources *res)
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_get_func_config);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
 		status = -ENOMEM;
@@ -3607,7 +3615,8 @@ int be_cmd_get_func_config(struct be_adapter *adapter, struct be_resources *res)
 err:
 	mutex_unlock(&adapter->mbox_lock);
 	if (cmd.va)
-		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+				  cmd.dma);
 	return status;
 }
 
@@ -3628,7 +3637,8 @@ int be_cmd_get_profile_config(struct be_adapter *adapter,
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_get_profile_config);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va)
 		return -ENOMEM;
 
@@ -3667,7 +3677,8 @@ int be_cmd_get_profile_config(struct be_adapter *adapter,
 		res->vf_if_cap_flags = vf_res->cap_flags;
 err:
 	if (cmd.va)
-		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+				  cmd.dma);
 	return status;
 }
 
@@ -3682,7 +3693,8 @@ static int be_cmd_set_profile_config(struct be_adapter *adapter, void *desc,
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_req_set_profile_config);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va)
 		return -ENOMEM;
 
@@ -3698,7 +3710,8 @@ static int be_cmd_set_profile_config(struct be_adapter *adapter, void *desc,
 	status = be_cmd_notify_wait(adapter, &wrb);
 
 	if (cmd.va)
-		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+				  cmd.dma);
 	return status;
 }
 
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index e42a791c183..a11c5e05634 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -266,8 +266,8 @@ static int lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name,
 	int status = 0;
 
 	read_cmd.size = LANCER_READ_FILE_CHUNK;
-	read_cmd.va = pci_alloc_consistent(adapter->pdev, read_cmd.size,
-					   &read_cmd.dma);
+	read_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, read_cmd.size,
+					  &read_cmd.dma, GFP_ATOMIC);
 
 	if (!read_cmd.va) {
 		dev_err(&adapter->pdev->dev,
@@ -291,8 +291,8 @@ static int lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name,
 			break;
 		}
 	}
-	pci_free_consistent(adapter->pdev, read_cmd.size, read_cmd.va,
-			    read_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, read_cmd.size, read_cmd.va,
+			  read_cmd.dma);
 
 	return status;
 }
@@ -818,8 +818,9 @@ static int be_test_ddr_dma(struct be_adapter *adapter)
 	};
 
 	ddrdma_cmd.size = sizeof(struct be_cmd_req_ddrdma_test);
-	ddrdma_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, ddrdma_cmd.size,
-					   &ddrdma_cmd.dma, GFP_KERNEL);
+	ddrdma_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					    ddrdma_cmd.size, &ddrdma_cmd.dma,
+					    GFP_KERNEL);
 	if (!ddrdma_cmd.va)
 		return -ENOMEM;
 
@@ -941,8 +942,9 @@ static int be_read_eeprom(struct net_device *netdev,
 
 	memset(&eeprom_cmd, 0, sizeof(struct be_dma_mem));
 	eeprom_cmd.size = sizeof(struct be_cmd_req_seeprom_read);
-	eeprom_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, eeprom_cmd.size,
-					   &eeprom_cmd.dma, GFP_KERNEL);
+	eeprom_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					    eeprom_cmd.size, &eeprom_cmd.dma,
+					    GFP_KERNEL);
 
 	if (!eeprom_cmd.va)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 597c463e384..fdd36794c53 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -887,7 +887,8 @@ static struct sk_buff *be_insert_vlan_in_pkt(struct be_adapter *adapter,
 	}
 
 	if (vlan_tag) {
-		skb = __vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
+		skb = vlan_insert_tag_set_proto(skb, htons(ETH_P_8021Q),
+						vlan_tag);
 		if (unlikely(!skb))
 			return skb;
 		skb->vlan_tci = 0;
@@ -896,7 +897,8 @@ static struct sk_buff *be_insert_vlan_in_pkt(struct be_adapter *adapter,
 	/* Insert the outer VLAN, if any */
 	if (adapter->qnq_vid) {
 		vlan_tag = adapter->qnq_vid;
-		skb = __vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
+		skb = vlan_insert_tag_set_proto(skb, htons(ETH_P_8021Q),
+						vlan_tag);
 		if (unlikely(!skb))
 			return skb;
 		if (skip_hw_vlan)
@@ -4111,8 +4113,8 @@ static int lancer_fw_download(struct be_adapter *adapter,
 
 	flash_cmd.size = sizeof(struct lancer_cmd_req_write_object)
 				+ LANCER_FW_DOWNLOAD_CHUNK;
-	flash_cmd.va = dma_alloc_coherent(dev, flash_cmd.size,
-					  &flash_cmd.dma, GFP_KERNEL);
+	flash_cmd.va = dma_zalloc_coherent(dev, flash_cmd.size,
+					   &flash_cmd.dma, GFP_KERNEL);
 	if (!flash_cmd.va)
 		return -ENOMEM;
 
@@ -4207,8 +4209,8 @@ static int be_fw_download(struct be_adapter *adapter, const struct firmware* fw)
 	int status = 0, i = 0, num_imgs = 0, ufi_type = 0;
 
 	flash_cmd.size = sizeof(struct be_cmd_write_flashrom);
-	flash_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, flash_cmd.size,
-					  &flash_cmd.dma, GFP_KERNEL);
+	flash_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, flash_cmd.size,
+					   &flash_cmd.dma, GFP_KERNEL);
 	if (!flash_cmd.va) {
 		status = -ENOMEM;
 		goto be_fw_exit;
@@ -4427,9 +4429,11 @@ static void be_del_vxlan_port(struct net_device *netdev, sa_family_t sa_family,
 		 be16_to_cpu(port));
 }
 
-static bool be_gso_check(struct sk_buff *skb, struct net_device *dev)
+static netdev_features_t be_features_check(struct sk_buff *skb,
+					   struct net_device *dev,
+					   netdev_features_t features)
 {
-	return vxlan_gso_check(skb);
+	return vxlan_features_check(skb, features);
 }
 #endif
 
@@ -4460,7 +4464,7 @@ static const struct net_device_ops be_netdev_ops = {
 #ifdef CONFIG_BE2NET_VXLAN
 	.ndo_add_vxlan_port	= be_add_vxlan_port,
 	.ndo_del_vxlan_port	= be_del_vxlan_port,
-	.ndo_gso_check		= be_gso_check,
+	.ndo_features_check	= be_features_check,
 #endif
 };
 
@@ -4583,10 +4587,10 @@ static int be_ctrl_init(struct be_adapter *adapter)
 		goto done;
 
 	mbox_mem_alloc->size = sizeof(struct be_mcc_mailbox) + 16;
-	mbox_mem_alloc->va = dma_alloc_coherent(&adapter->pdev->dev,
-						mbox_mem_alloc->size,
-						&mbox_mem_alloc->dma,
-						GFP_KERNEL);
+	mbox_mem_alloc->va = dma_zalloc_coherent(&adapter->pdev->dev,
+						 mbox_mem_alloc->size,
+						 &mbox_mem_alloc->dma,
+						 GFP_KERNEL);
 	if (!mbox_mem_alloc->va) {
 		status = -ENOMEM;
 		goto unmap_pci_bars;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 3dca494797b..96ba23e9011 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1464,8 +1464,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 
 			vlan_packet_rcvd = true;
 
-			skb_copy_to_linear_data_offset(skb, VLAN_HLEN,
-						       data, (2 * ETH_ALEN));
+			memmove(skb->data + VLAN_HLEN, data, ETH_ALEN * 2);
 			skb_pull(skb, VLAN_HLEN);
 		}
 
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 5b8300a32bf..4d61ef50b46 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -281,6 +281,17 @@ config I40E_DCB
 
 	  If unsure, say N.
 
+config I40E_FCOE
+	bool "Fibre Channel over Ethernet (FCoE)"
+	default n
+	depends on I40E && DCB && FCOE
+	---help---
+	  Say Y here if you want to use Fibre Channel over Ethernet (FCoE)
+	  in the driver. This will create new netdev for exclusive FCoE
+	  use with XL710 FCoE offloads enabled.
+
+	  If unsure, say N.
+
 config I40EVF
 	tristate "Intel(R) XL710 X710 Virtual Function Ethernet support"
 	depends on PCI_MSI
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 24f3986cfae..3a06cae4ff6 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -144,6 +144,11 @@ static bool e1000_clean_rx_irq(struct e1000_adapter *adapter,
 static bool e1000_clean_jumbo_rx_irq(struct e1000_adapter *adapter,
 				     struct e1000_rx_ring *rx_ring,
 				     int *work_done, int work_to_do);
+static void e1000_alloc_dummy_rx_buffers(struct e1000_adapter *adapter,
+					 struct e1000_rx_ring *rx_ring,
+					 int cleaned_count)
+{
+}
 static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter,
 				   struct e1000_rx_ring *rx_ring,
 				   int cleaned_count);
@@ -3552,8 +3557,11 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu)
 		msleep(1);
 	/* e1000_down has a dependency on max_frame_size */
 	hw->max_frame_size = max_frame;
-	if (netif_running(netdev))
+	if (netif_running(netdev)) {
+		/* prevent buffers from being reallocated */
+		adapter->alloc_rx_buf = e1000_alloc_dummy_rx_buffers;
 		e1000_down(adapter);
+	}
 
 	/* NOTE: netdev_alloc_skb reserves 16 bytes, and typically NET_IP_ALIGN
 	 * means we reserve 2 more, this pushes us to allocate from the next
diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile
index 4b94ddb29c2..c4058199912 100644
--- a/drivers/net/ethernet/intel/i40e/Makefile
+++ b/drivers/net/ethernet/intel/i40e/Makefile
@@ -44,4 +44,4 @@ i40e-objs := i40e_main.o \
 	i40e_virtchnl_pf.o
 
 i40e-$(CONFIG_I40E_DCB) += i40e_dcb.o i40e_dcb_nl.o
-i40e-$(CONFIG_FCOE:m=y) += i40e_fcoe.o
+i40e-$(CONFIG_I40E_FCOE) += i40e_fcoe.o
diff --git a/drivers/net/ethernet/intel/i40e/i40e_osdep.h b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
index 045b5c4b98b..ad802dd0f67 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_osdep.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
@@ -78,7 +78,7 @@ do {                                                            \
 } while (0)
 
 typedef enum i40e_status_code i40e_status;
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#ifdef CONFIG_I40E_FCOE
 #define I40E_FCOE
-#endif /* CONFIG_FCOE or CONFIG_FCOE_MODULE */
+#endif
 #endif /* _I40E_OSDEP_H_ */
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index ade067de168..fb34708aa5f 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -216,7 +216,7 @@
 /* Various constants */
 
 /* Coalescing */
-#define MVNETA_TXDONE_COAL_PKTS		16
+#define MVNETA_TXDONE_COAL_PKTS		1
 #define MVNETA_RX_COAL_PKTS		32
 #define MVNETA_RX_COAL_USEC		100
 
@@ -304,6 +304,7 @@ struct mvneta_port {
 	unsigned int link;
 	unsigned int duplex;
 	unsigned int speed;
+	unsigned int tx_csum_limit;
 };
 
 /* The mvneta_tx_desc and mvneta_rx_desc structures describe the
@@ -1721,6 +1722,7 @@ static int mvneta_tx(struct sk_buff *skb, struct net_device *dev)
 	u16 txq_id = skb_get_queue_mapping(skb);
 	struct mvneta_tx_queue *txq = &pp->txqs[txq_id];
 	struct mvneta_tx_desc *tx_desc;
+	int len = skb->len;
 	int frags = 0;
 	u32 tx_cmd;
 
@@ -1788,7 +1790,7 @@ out:
 
 		u64_stats_update_begin(&stats->syncp);
 		stats->tx_packets++;
-		stats->tx_bytes  += skb->len;
+		stats->tx_bytes  += len;
 		u64_stats_update_end(&stats->syncp);
 	} else {
 		dev->stats.tx_dropped++;
@@ -2440,8 +2442,10 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu)
 
 	dev->mtu = mtu;
 
-	if (!netif_running(dev))
+	if (!netif_running(dev)) {
+		netdev_update_features(dev);
 		return 0;
+	}
 
 	/* The interface is running, so we have to force a
 	 * reallocation of the queues
@@ -2470,9 +2474,26 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu)
 	mvneta_start_dev(pp);
 	mvneta_port_up(pp);
 
+	netdev_update_features(dev);
+
 	return 0;
 }
 
+static netdev_features_t mvneta_fix_features(struct net_device *dev,
+					     netdev_features_t features)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+
+	if (pp->tx_csum_limit && dev->mtu > pp->tx_csum_limit) {
+		features &= ~(NETIF_F_IP_CSUM | NETIF_F_TSO);
+		netdev_info(dev,
+			    "Disable IP checksum for MTU greater than %dB\n",
+			    pp->tx_csum_limit);
+	}
+
+	return features;
+}
+
 /* Get mac address */
 static void mvneta_get_mac_addr(struct mvneta_port *pp, unsigned char *addr)
 {
@@ -2790,6 +2811,7 @@ static const struct net_device_ops mvneta_netdev_ops = {
 	.ndo_set_rx_mode     = mvneta_set_rx_mode,
 	.ndo_set_mac_address = mvneta_set_mac_addr,
 	.ndo_change_mtu      = mvneta_change_mtu,
+	.ndo_fix_features    = mvneta_fix_features,
 	.ndo_get_stats64     = mvneta_get_stats64,
 	.ndo_do_ioctl        = mvneta_ioctl,
 };
@@ -3028,6 +3050,9 @@ static int mvneta_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (of_device_is_compatible(dn, "marvell,armada-370-neta"))
+		pp->tx_csum_limit = 1600;
+
 	pp->tx_ring_size = MVNETA_MAX_TXD;
 	pp->rx_ring_size = MVNETA_MAX_RXD;
 
@@ -3100,6 +3125,7 @@ static int mvneta_remove(struct platform_device *pdev)
 
 static const struct of_device_id mvneta_match[] = {
 	{ .compatible = "marvell,armada-370-neta" },
+	{ .compatible = "marvell,armada-xp-neta" },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, mvneta_match);
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index b16e1b95566..61ebb038fb7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -585,7 +585,8 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 		 * on the host, we deprecate the error message for this
 		 * specific command/input_mod/opcode_mod/fw-status to be debug.
 		 */
-		if (op == MLX4_CMD_SET_PORT && in_modifier == 1 &&
+		if (op == MLX4_CMD_SET_PORT &&
+		    (in_modifier == 1 || in_modifier == 2) &&
 		    op_modifier == 0 && context->fw_status == CMD_STAT_BAD_SIZE)
 			mlx4_dbg(dev, "command 0x%x failed: fw status = 0x%x\n",
 				 op, context->fw_status);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 4d69e382b4e..68fef1151dd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1466,6 +1466,7 @@ static void mlx4_en_service_task(struct work_struct *work)
 		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
 			mlx4_en_ptp_overflow_check(mdev);
 
+		mlx4_en_recover_from_oom(priv);
 		queue_delayed_work(mdev->workqueue, &priv->service_task,
 				   SERVICE_TASK_DELAY);
 	}
@@ -1569,8 +1570,15 @@ int mlx4_en_start_port(struct net_device *dev)
 			mlx4_en_free_affinity_hint(priv, i);
 			goto cq_err;
 		}
-		for (j = 0; j < cq->size; j++)
-			cq->buf[j].owner_sr_opcode = MLX4_CQE_OWNER_MASK;
+
+		for (j = 0; j < cq->size; j++) {
+			struct mlx4_cqe *cqe = NULL;
+
+			cqe = mlx4_en_get_cqe(cq->buf, j, priv->cqe_size) +
+			      priv->cqe_factor;
+			cqe->owner_sr_opcode = MLX4_CQE_OWNER_MASK;
+		}
+
 		err = mlx4_en_set_cq_moder(priv, cq);
 		if (err) {
 			en_err(priv, "Failed setting cq moderation parameters\n");
@@ -2356,9 +2364,11 @@ static void mlx4_en_del_vxlan_port(struct  net_device *dev,
 	queue_work(priv->mdev->workqueue, &priv->vxlan_del_task);
 }
 
-static bool mlx4_en_gso_check(struct sk_buff *skb, struct net_device *dev)
+static netdev_features_t mlx4_en_features_check(struct sk_buff *skb,
+						struct net_device *dev,
+						netdev_features_t features)
 {
-	return vxlan_gso_check(skb);
+	return vxlan_features_check(skb, features);
 }
 #endif
 
@@ -2391,7 +2401,7 @@ static const struct net_device_ops mlx4_netdev_ops = {
 #ifdef CONFIG_MLX4_EN_VXLAN
 	.ndo_add_vxlan_port	= mlx4_en_add_vxlan_port,
 	.ndo_del_vxlan_port	= mlx4_en_del_vxlan_port,
-	.ndo_gso_check		= mlx4_en_gso_check,
+	.ndo_features_check	= mlx4_en_features_check,
 #endif
 };
 
@@ -2425,7 +2435,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = {
 #ifdef CONFIG_MLX4_EN_VXLAN
 	.ndo_add_vxlan_port	= mlx4_en_add_vxlan_port,
 	.ndo_del_vxlan_port	= mlx4_en_del_vxlan_port,
-	.ndo_gso_check		= mlx4_en_gso_check,
+	.ndo_features_check	= mlx4_en_features_check,
 #endif
 };
 
@@ -2597,13 +2607,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	netif_carrier_off(dev);
 	mlx4_en_set_default_moderation(priv);
 
-	err = register_netdev(dev);
-	if (err) {
-		en_err(priv, "Netdev registration failed for port %d\n", port);
-		goto out;
-	}
-	priv->registered = 1;
-
 	en_warn(priv, "Using %d TX rings\n", prof->tx_ring_num);
 	en_warn(priv, "Using %d RX rings\n", prof->rx_ring_num);
 
@@ -2643,6 +2646,14 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 		queue_delayed_work(mdev->workqueue, &priv->service_task,
 				   SERVICE_TASK_DELAY);
 
+	err = register_netdev(dev);
+	if (err) {
+		en_err(priv, "Netdev registration failed for port %d\n", port);
+		goto out;
+	}
+
+	priv->registered = 1;
+
 	return 0;
 
 out:
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 01660c595f5..5bbb59dce4d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -237,6 +237,12 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
 	return mlx4_en_alloc_frags(priv, rx_desc, frags, ring->page_alloc, gfp);
 }
 
+static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring)
+{
+	BUG_ON((u32)(ring->prod - ring->cons) > ring->actual_size);
+	return ring->prod == ring->cons;
+}
+
 static inline void mlx4_en_update_rx_prod_db(struct mlx4_en_rx_ring *ring)
 {
 	*ring->wqres.db.db = cpu_to_be32(ring->prod & 0xffff);
@@ -308,8 +314,7 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv,
 	       ring->cons, ring->prod);
 
 	/* Unmap and free Rx buffers */
-	BUG_ON((u32) (ring->prod - ring->cons) > ring->actual_size);
-	while (ring->cons != ring->prod) {
+	while (!mlx4_en_is_ring_empty(ring)) {
 		index = ring->cons & ring->size_mask;
 		en_dbg(DRV, priv, "Processing descriptor:%d\n", index);
 		mlx4_en_free_rx_desc(priv, ring, index);
@@ -484,6 +489,23 @@ err_allocator:
 	return err;
 }
 
+/* We recover from out of memory by scheduling our napi poll
+ * function (mlx4_en_process_cq), which tries to allocate
+ * all missing RX buffers (call to mlx4_en_refill_rx_buffers).
+ */
+void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv)
+{
+	int ring;
+
+	if (!priv->port_up)
+		return;
+
+	for (ring = 0; ring < priv->rx_ring_num; ring++) {
+		if (mlx4_en_is_ring_empty(priv->rx_ring[ring]))
+			napi_reschedule(&priv->rx_cq[ring]->napi);
+	}
+}
+
 void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_rx_ring **pring,
 			     u32 size, u16 stride)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 454d9fea640..5980d3fe597 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -66,6 +66,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	ring->size = size;
 	ring->size_mask = size - 1;
 	ring->stride = stride;
+	ring->full_size = ring->size - HEADROOM - MAX_DESC_TXBBS;
 
 	tmp = size * sizeof(struct mlx4_en_tx_info);
 	ring->tx_info = kmalloc_node(tmp, GFP_KERNEL | __GFP_NOWARN, node);
@@ -137,8 +138,10 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	ring->hwtstamp_tx_type = priv->hwtstamp_config.tx_type;
 	ring->queue_index = queue_index;
 
-	if (queue_index < priv->num_tx_rings_p_up && cpu_online(queue_index))
-		cpumask_set_cpu(queue_index, &ring->affinity_mask);
+	if (queue_index < priv->num_tx_rings_p_up)
+		cpumask_set_cpu_local_first(queue_index,
+					    priv->mdev->dev->numa_node,
+					    &ring->affinity_mask);
 
 	*pring = ring;
 	return 0;
@@ -205,7 +208,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 
 	err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, &ring->context,
 			       &ring->qp, &ring->qp_state);
-	if (!user_prio && cpu_online(ring->queue_index))
+	if (!cpumask_empty(&ring->affinity_mask))
 		netif_set_xps_queue(priv->dev, &ring->affinity_mask,
 				    ring->queue_index);
 
@@ -221,6 +224,11 @@ void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
 		       MLX4_QP_STATE_RST, NULL, 0, 0, &ring->qp);
 }
 
+static inline bool mlx4_en_is_tx_ring_full(struct mlx4_en_tx_ring *ring)
+{
+	return ring->prod - ring->cons > ring->full_size;
+}
+
 static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv,
 			      struct mlx4_en_tx_ring *ring, int index,
 			      u8 owner)
@@ -463,11 +471,10 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 
 	netdev_tx_completed_queue(ring->tx_queue, packets, bytes);
 
-	/*
-	 * Wakeup Tx queue if this stopped, and at least 1 packet
-	 * was completed
+	/* Wakeup Tx queue if this stopped, and ring is not full.
 	 */
-	if (netif_tx_queue_stopped(ring->tx_queue) && txbbs_skipped > 0) {
+	if (netif_tx_queue_stopped(ring->tx_queue) &&
+	    !mlx4_en_is_tx_ring_full(ring)) {
 		netif_tx_wake_queue(ring->tx_queue);
 		ring->wake_queue++;
 	}
@@ -911,8 +918,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	skb_tx_timestamp(skb);
 
 	/* Check available TXBBs And 2K spare for prefetch */
-	stop_queue = (int)(ring->prod - ring_cons) >
-		      ring->size - HEADROOM - MAX_DESC_TXBBS;
+	stop_queue = mlx4_en_is_tx_ring_full(ring);
 	if (unlikely(stop_queue)) {
 		netif_tx_stop_queue(ring->tx_queue);
 		ring->queue_stopped++;
@@ -954,7 +960,17 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		tx_desc->ctrl.owner_opcode = op_own;
 		if (send_doorbell) {
 			wmb();
-			iowrite32(ring->doorbell_qpn,
+			/* Since there is no iowrite*_native() that writes the
+			 * value as is, without byteswapping - using the one
+			 * the doesn't do byteswapping in the relevant arch
+			 * endianness.
+			 */
+#if defined(__LITTLE_ENDIAN)
+			iowrite32(
+#else
+			iowrite32be(
+#endif
+				  ring->doorbell_qpn,
 				  ring->bf.uar->map + MLX4_SEND_DOORBELL);
 		} else {
 			ring->xmit_more++;
@@ -971,8 +987,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		smp_rmb();
 
 		ring_cons = ACCESS_ONCE(ring->cons);
-		if (unlikely(((int)(ring->prod - ring_cons)) <=
-			     ring->size - HEADROOM - MAX_DESC_TXBBS)) {
+		if (unlikely(!mlx4_en_is_tx_ring_full(ring))) {
 			netif_tx_wake_queue(ring->tx_queue);
 			ring->wake_queue++;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 2e88a235e26..5f122879432 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -1647,8 +1647,8 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 	/* CX3 is capable of extending CQEs\EQEs to strides larger than 64B */
 	MLX4_GET(byte_field, outbox, INIT_HCA_EQE_CQE_STRIDE_OFFSET);
 	if (byte_field) {
-		param->dev_cap_enabled |= MLX4_DEV_CAP_64B_EQE_ENABLED;
-		param->dev_cap_enabled |= MLX4_DEV_CAP_64B_CQE_ENABLED;
+		param->dev_cap_enabled |= MLX4_DEV_CAP_EQE_STRIDE_ENABLED;
+		param->dev_cap_enabled |= MLX4_DEV_CAP_CQE_STRIDE_ENABLED;
 		param->cqe_size = 1 << ((byte_field &
 					 MLX4_CQE_SIZE_MASK_STRIDE) + 5);
 		param->eqe_size = 1 << (((byte_field &
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 8fef65840b3..4f908065acc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -280,6 +280,7 @@ struct mlx4_en_tx_ring {
 	u32			size; /* number of TXBBs */
 	u32			size_mask;
 	u16			stride;
+	u32			full_size;
 	u16			cqn;	/* index of port CQ associated with this ring */
 	u32			buf_size;
 	__be32			doorbell_qpn;
@@ -779,6 +780,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
 				struct mlx4_en_tx_ring *ring);
 void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev);
+void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv);
 int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_rx_ring **pring,
 			   u32 size, u16 stride, int node);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index 193a6adb5d0..b7cdef0aebd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -590,6 +590,7 @@ EXPORT_SYMBOL_GPL(mlx4_mr_free);
 void mlx4_mr_rereg_mem_cleanup(struct mlx4_dev *dev, struct mlx4_mr *mr)
 {
 	mlx4_mtt_cleanup(dev, &mr->mtt);
+	mr->mtt.order = -1;
 }
 EXPORT_SYMBOL_GPL(mlx4_mr_rereg_mem_cleanup);
 
@@ -599,14 +600,14 @@ int mlx4_mr_rereg_mem_write(struct mlx4_dev *dev, struct mlx4_mr *mr,
 {
 	int err;
 
-	mpt_entry->start       = cpu_to_be64(iova);
-	mpt_entry->length      = cpu_to_be64(size);
-	mpt_entry->entity_size = cpu_to_be32(page_shift);
-
 	err = mlx4_mtt_init(dev, npages, page_shift, &mr->mtt);
 	if (err)
 		return err;
 
+	mpt_entry->start       = cpu_to_be64(mr->iova);
+	mpt_entry->length      = cpu_to_be64(mr->size);
+	mpt_entry->entity_size = cpu_to_be32(mr->mtt.page_shift);
+
 	mpt_entry->pd_flags &= cpu_to_be32(MLX4_MPT_PD_MASK |
 					   MLX4_MPT_PD_FLAG_EN_INV);
 	mpt_entry->flags    &= cpu_to_be32(MLX4_MPT_FLAG_FREE |
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index d476918ef26..aa78f07d3d5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -211,26 +211,28 @@ static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr)
 	return 0;
 }
 
+#define MLX5_U64_4K_PAGE_MASK ((~(u64)0U) << PAGE_SHIFT)
+
 static void free_4k(struct mlx5_core_dev *dev, u64 addr)
 {
 	struct fw_page *fwp;
 	int n;
 
-	fwp = find_fw_page(dev, addr & PAGE_MASK);
+	fwp = find_fw_page(dev, addr & MLX5_U64_4K_PAGE_MASK);
 	if (!fwp) {
 		mlx5_core_warn(dev, "page not found\n");
 		return;
 	}
 
-	n = (addr & ~PAGE_MASK) >> MLX5_ADAPTER_PAGE_SHIFT;
+	n = (addr & ~MLX5_U64_4K_PAGE_MASK) >> MLX5_ADAPTER_PAGE_SHIFT;
 	fwp->free_count++;
 	set_bit(n, &fwp->bitmask);
 	if (fwp->free_count == MLX5_NUM_4K_IN_PAGE) {
 		rb_erase(&fwp->rb_node, &dev->priv.page_root);
 		if (fwp->free_count != 1)
 			list_del(&fwp->list);
-		dma_unmap_page(&dev->pdev->dev, addr & PAGE_MASK, PAGE_SIZE,
-			       DMA_BIDIRECTIONAL);
+		dma_unmap_page(&dev->pdev->dev, addr & MLX5_U64_4K_PAGE_MASK,
+			       PAGE_SIZE, DMA_BIDIRECTIONAL);
 		__free_page(fwp->page);
 		kfree(fwp);
 	} else if (fwp->free_count == 1) {
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index 613037584d0..c531c8ae1be 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -2388,7 +2388,10 @@ static int netxen_nic_poll(struct napi_struct *napi, int budget)
 
 	work_done = netxen_process_rcv_ring(sds_ring, budget);
 
-	if ((work_done < budget) && tx_complete) {
+	if (!tx_complete)
+		work_done = budget;
+
+	if (work_done < budget) {
 		napi_complete(&sds_ring->napi);
 		if (test_bit(__NX_DEV_UP, &adapter->state))
 			netxen_nic_enable_int(sds_ring);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index a913b3ad2f8..477a5d33d79 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -504,9 +504,11 @@ static void qlcnic_del_vxlan_port(struct net_device *netdev,
 	adapter->flags |= QLCNIC_DEL_VXLAN_PORT;
 }
 
-static bool qlcnic_gso_check(struct sk_buff *skb, struct net_device *dev)
+static netdev_features_t qlcnic_features_check(struct sk_buff *skb,
+					       struct net_device *dev,
+					       netdev_features_t features)
 {
-	return vxlan_gso_check(skb);
+	return vxlan_features_check(skb, features);
 }
 #endif
 
@@ -531,7 +533,7 @@ static const struct net_device_ops qlcnic_netdev_ops = {
 #ifdef CONFIG_QLCNIC_VXLAN
 	.ndo_add_vxlan_port	= qlcnic_add_vxlan_port,
 	.ndo_del_vxlan_port	= qlcnic_del_vxlan_port,
-	.ndo_gso_check		= qlcnic_gso_check,
+	.ndo_features_check	= qlcnic_features_check,
 #endif
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = qlcnic_poll_controller,
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index cf154f74cba..54390b3e034 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -5062,8 +5062,6 @@ static void rtl_hw_reset(struct rtl8169_private *tp)
 	RTL_W8(ChipCmd, CmdReset);
 
 	rtl_udelay_loop_wait_low(tp, &rtl_chipcmd_cond, 100, 100);
-
-	netdev_reset_queue(tp->dev);
 }
 
 static void rtl_request_uncached_firmware(struct rtl8169_private *tp)
@@ -7073,8 +7071,6 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 
 	txd->opts2 = cpu_to_le32(opts[1]);
 
-	netdev_sent_queue(dev, skb->len);
-
 	skb_tx_timestamp(skb);
 
 	wmb();
@@ -7174,7 +7170,6 @@ static void rtl8169_pcierr_interrupt(struct net_device *dev)
 static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp)
 {
 	unsigned int dirty_tx, tx_left;
-	unsigned int bytes_compl = 0, pkts_compl = 0;
 
 	dirty_tx = tp->dirty_tx;
 	smp_rmb();
@@ -7193,8 +7188,10 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp)
 		rtl8169_unmap_tx_skb(&tp->pci_dev->dev, tx_skb,
 				     tp->TxDescArray + entry);
 		if (status & LastFrag) {
-			pkts_compl++;
-			bytes_compl += tx_skb->skb->len;
+			u64_stats_update_begin(&tp->tx_stats.syncp);
+			tp->tx_stats.packets++;
+			tp->tx_stats.bytes += tx_skb->skb->len;
+			u64_stats_update_end(&tp->tx_stats.syncp);
 			dev_kfree_skb_any(tx_skb->skb);
 			tx_skb->skb = NULL;
 		}
@@ -7203,13 +7200,6 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp)
 	}
 
 	if (tp->dirty_tx != dirty_tx) {
-		netdev_completed_queue(tp->dev, pkts_compl, bytes_compl);
-
-		u64_stats_update_begin(&tp->tx_stats.syncp);
-		tp->tx_stats.packets += pkts_compl;
-		tp->tx_stats.bytes += bytes_compl;
-		u64_stats_update_end(&tp->tx_stats.syncp);
-
 		tp->dirty_tx = dirty_tx;
 		/* Sync with rtl8169_start_xmit:
 		 * - publish dirty_tx ring index (write barrier)
diff --git a/drivers/net/ethernet/stmicro/stmmac/descs.h b/drivers/net/ethernet/stmicro/stmmac/descs.h
index ad399603801..799c2929c53 100644
--- a/drivers/net/ethernet/stmicro/stmmac/descs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/descs.h
@@ -158,6 +158,8 @@ struct dma_desc {
 			u32 buffer2_size:13;
 			u32 reserved4:3;
 		} etx;		/* -- enhanced -- */
+
+		u64 all_flags;
 	} des01;
 	unsigned int des2;
 	unsigned int des3;
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index 1e2bcf5f89e..7d944449f5e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -240,6 +240,7 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 static void enh_desc_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
 				  int mode, int end)
 {
+	p->des01.all_flags = 0;
 	p->des01.erx.own = 1;
 	p->des01.erx.buffer1_size = BUF_SIZE_8KiB - 1;
 
@@ -254,7 +255,7 @@ static void enh_desc_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
 
 static void enh_desc_init_tx_desc(struct dma_desc *p, int mode, int end)
 {
-	p->des01.etx.own = 0;
+	p->des01.all_flags = 0;
 	if (mode == STMMAC_CHAIN_MODE)
 		ehn_desc_tx_set_on_chain(p, end);
 	else
diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
index 35ad4f427ae..48c3456445b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -123,6 +123,7 @@ static int ndesc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 static void ndesc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode,
 			       int end)
 {
+	p->des01.all_flags = 0;
 	p->des01.rx.own = 1;
 	p->des01.rx.buffer1_size = BUF_SIZE_2KiB - 1;
 
@@ -137,7 +138,7 @@ static void ndesc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode,
 
 static void ndesc_init_tx_desc(struct dma_desc *p, int mode, int end)
 {
-	p->des01.tx.own = 0;
+	p->des01.all_flags = 0;
 	if (mode == STMMAC_CHAIN_MODE)
 		ndesc_tx_set_on_chain(p, end);
 	else
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 18c46bb0f3b..c769da8d6f3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1172,41 +1172,41 @@ static int alloc_dma_desc_resources(struct stmmac_priv *priv)
 		goto err_tx_skbuff;
 
 	if (priv->extend_desc) {
-		priv->dma_erx = dma_alloc_coherent(priv->device, rxsize *
-						   sizeof(struct
-							  dma_extended_desc),
-						   &priv->dma_rx_phy,
-						   GFP_KERNEL);
+		priv->dma_erx = dma_zalloc_coherent(priv->device, rxsize *
+						    sizeof(struct
+							   dma_extended_desc),
+						    &priv->dma_rx_phy,
+						    GFP_KERNEL);
 		if (!priv->dma_erx)
 			goto err_dma;
 
-		priv->dma_etx = dma_alloc_coherent(priv->device, txsize *
-						   sizeof(struct
-							  dma_extended_desc),
-						   &priv->dma_tx_phy,
-						   GFP_KERNEL);
+		priv->dma_etx = dma_zalloc_coherent(priv->device, txsize *
+						    sizeof(struct
+							   dma_extended_desc),
+						    &priv->dma_tx_phy,
+						    GFP_KERNEL);
 		if (!priv->dma_etx) {
 			dma_free_coherent(priv->device, priv->dma_rx_size *
-					sizeof(struct dma_extended_desc),
-					priv->dma_erx, priv->dma_rx_phy);
+					  sizeof(struct dma_extended_desc),
+					  priv->dma_erx, priv->dma_rx_phy);
 			goto err_dma;
 		}
 	} else {
-		priv->dma_rx = dma_alloc_coherent(priv->device, rxsize *
-						  sizeof(struct dma_desc),
-						  &priv->dma_rx_phy,
-						  GFP_KERNEL);
+		priv->dma_rx = dma_zalloc_coherent(priv->device, rxsize *
+						   sizeof(struct dma_desc),
+						   &priv->dma_rx_phy,
+						   GFP_KERNEL);
 		if (!priv->dma_rx)
 			goto err_dma;
 
-		priv->dma_tx = dma_alloc_coherent(priv->device, txsize *
-						  sizeof(struct dma_desc),
-						  &priv->dma_tx_phy,
-						  GFP_KERNEL);
+		priv->dma_tx = dma_zalloc_coherent(priv->device, txsize *
+						   sizeof(struct dma_desc),
+						   &priv->dma_tx_phy,
+						   GFP_KERNEL);
 		if (!priv->dma_tx) {
 			dma_free_coherent(priv->device, priv->dma_rx_size *
-					sizeof(struct dma_desc),
-					priv->dma_rx, priv->dma_rx_phy);
+					  sizeof(struct dma_desc),
+					  priv->dma_rx, priv->dma_rx_phy);
 			goto err_dma;
 		}
 	}
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index c560f9aeb55..48645504106 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -610,7 +610,7 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable)
 
 			/* Clear all mcast from ALE */
 			cpsw_ale_flush_multicast(ale, ALE_ALL_PORTS <<
-						 priv->host_port);
+						 priv->host_port, -1);
 
 			/* Flood All Unicast Packets to Host port */
 			cpsw_ale_control_set(ale, 0, ALE_P0_UNI_FLOOD, 1);
@@ -634,6 +634,12 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable)
 static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
+	int vid;
+
+	if (priv->data.dual_emac)
+		vid = priv->slaves[priv->emac_port].port_vlan;
+	else
+		vid = priv->data.default_vlan;
 
 	if (ndev->flags & IFF_PROMISC) {
 		/* Enable promiscuous mode */
@@ -649,7 +655,8 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
 	cpsw_ale_set_allmulti(priv->ale, priv->ndev->flags & IFF_ALLMULTI);
 
 	/* Clear all mcast from ALE */
-	cpsw_ale_flush_multicast(priv->ale, ALE_ALL_PORTS << priv->host_port);
+	cpsw_ale_flush_multicast(priv->ale, ALE_ALL_PORTS << priv->host_port,
+				 vid);
 
 	if (!netdev_mc_empty(ndev)) {
 		struct netdev_hw_addr *ha;
@@ -757,6 +764,14 @@ requeue:
 static irqreturn_t cpsw_interrupt(int irq, void *dev_id)
 {
 	struct cpsw_priv *priv = dev_id;
+	int value = irq - priv->irqs_table[0];
+
+	/* NOTICE: Ending IRQ here. The trick with the 'value' variable above
+	 * is to make sure we will always write the correct value to the EOI
+	 * register. Namely 0 for RX_THRESH Interrupt, 1 for RX Interrupt, 2
+	 * for TX Interrupt and 3 for MISC Interrupt.
+	 */
+	cpdma_ctlr_eoi(priv->dma, value);
 
 	cpsw_intr_disable(priv);
 	if (priv->irq_enabled == true) {
@@ -786,8 +801,6 @@ static int cpsw_poll(struct napi_struct *napi, int budget)
 	int			num_tx, num_rx;
 
 	num_tx = cpdma_chan_process(priv->txch, 128);
-	if (num_tx)
-		cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_TX);
 
 	num_rx = cpdma_chan_process(priv->rxch, budget);
 	if (num_rx < budget) {
@@ -795,7 +808,6 @@ static int cpsw_poll(struct napi_struct *napi, int budget)
 
 		napi_complete(napi);
 		cpsw_intr_enable(priv);
-		cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_RX);
 		prim_cpsw = cpsw_get_slave_priv(priv, 0);
 		if (prim_cpsw->irq_enabled == false) {
 			prim_cpsw->irq_enabled = true;
@@ -1310,8 +1322,6 @@ static int cpsw_ndo_open(struct net_device *ndev)
 	napi_enable(&priv->napi);
 	cpdma_ctlr_start(priv->dma);
 	cpsw_intr_enable(priv);
-	cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_RX);
-	cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_TX);
 
 	prim_cpsw = cpsw_get_slave_priv(priv, 0);
 	if (prim_cpsw->irq_enabled == false) {
@@ -1578,9 +1588,6 @@ static void cpsw_ndo_tx_timeout(struct net_device *ndev)
 	cpdma_chan_start(priv->txch);
 	cpdma_ctlr_int_ctrl(priv->dma, true);
 	cpsw_intr_enable(priv);
-	cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_RX);
-	cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_TX);
-
 }
 
 static int cpsw_ndo_set_mac_address(struct net_device *ndev, void *p)
@@ -1620,9 +1627,6 @@ static void cpsw_ndo_poll_controller(struct net_device *ndev)
 	cpsw_interrupt(ndev->irq, priv);
 	cpdma_ctlr_int_ctrl(priv->dma, true);
 	cpsw_intr_enable(priv);
-	cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_RX);
-	cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_TX);
-
 }
 #endif
 
@@ -1672,6 +1676,19 @@ static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev,
 	if (vid == priv->data.default_vlan)
 		return 0;
 
+	if (priv->data.dual_emac) {
+		/* In dual EMAC, reserved VLAN id should not be used for
+		 * creating VLAN interfaces as this can break the dual
+		 * EMAC port separation
+		 */
+		int i;
+
+		for (i = 0; i < priv->data.slaves; i++) {
+			if (vid == priv->slaves[i].port_vlan)
+				return -EINVAL;
+		}
+	}
+
 	dev_info(priv->dev, "Adding vlanid %d to vlan filter\n", vid);
 	return cpsw_add_vlan_ale_entry(priv, vid);
 }
@@ -1685,6 +1702,15 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev,
 	if (vid == priv->data.default_vlan)
 		return 0;
 
+	if (priv->data.dual_emac) {
+		int i;
+
+		for (i = 0; i < priv->data.slaves; i++) {
+			if (vid == priv->slaves[i].port_vlan)
+				return -EINVAL;
+		}
+	}
+
 	dev_info(priv->dev, "removing vlanid %d from vlan filter\n", vid);
 	ret = cpsw_ale_del_vlan(priv->ale, vid, 0);
 	if (ret != 0)
diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index 097ebe7077a..5246b3a18ff 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -234,7 +234,7 @@ static void cpsw_ale_flush_mcast(struct cpsw_ale *ale, u32 *ale_entry,
 		cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE);
 }
 
-int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask)
+int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid)
 {
 	u32 ale_entry[ALE_ENTRY_WORDS];
 	int ret, idx;
@@ -245,6 +245,14 @@ int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask)
 		if (ret != ALE_TYPE_ADDR && ret != ALE_TYPE_VLAN_ADDR)
 			continue;
 
+		/* if vid passed is -1 then remove all multicast entry from
+		 * the table irrespective of vlan id, if a valid vlan id is
+		 * passed then remove only multicast added to that vlan id.
+		 * if vlan id doesn't match then move on to next entry.
+		 */
+		if (vid != -1 && cpsw_ale_get_vlan_id(ale_entry) != vid)
+			continue;
+
 		if (cpsw_ale_get_mcast(ale_entry)) {
 			u8 addr[6];
 
diff --git a/drivers/net/ethernet/ti/cpsw_ale.h b/drivers/net/ethernet/ti/cpsw_ale.h
index c0d4127aa54..af1e7ecd87c 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.h
+++ b/drivers/net/ethernet/ti/cpsw_ale.h
@@ -92,7 +92,7 @@ void cpsw_ale_stop(struct cpsw_ale *ale);
 
 int cpsw_ale_set_ageout(struct cpsw_ale *ale, int ageout);
 int cpsw_ale_flush(struct cpsw_ale *ale, int port_mask);
-int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask);
+int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid);
 int cpsw_ale_add_ucast(struct cpsw_ale *ale, u8 *addr, int port,
 		       int flags, u16 vid);
 int cpsw_ale_del_ucast(struct cpsw_ale *ale, u8 *addr, int port,
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 7d76c952339..63d7a642733 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -716,7 +716,7 @@ int netvsc_send(struct hv_device *device,
 	u64 req_id;
 	unsigned int section_index = NETVSC_INVALID_INDEX;
 	u32 msg_size = 0;
-	struct sk_buff *skb;
+	struct sk_buff *skb = NULL;
 	u16 q_idx = packet->q_idx;
 
 
@@ -743,8 +743,6 @@ int netvsc_send(struct hv_device *device,
 							   packet);
 			skb = (struct sk_buff *)
 			      (unsigned long)packet->send_completion_tid;
-			if (skb)
-				dev_kfree_skb_any(skb);
 			packet->page_buf_cnt = 0;
 		}
 	}
@@ -807,6 +805,13 @@ int netvsc_send(struct hv_device *device,
 			   packet, ret);
 	}
 
+	if (ret != 0) {
+		if (section_index != NETVSC_INVALID_INDEX)
+			netvsc_free_send_slot(net_device, section_index);
+	} else if (skb) {
+		dev_kfree_skb_any(skb);
+	}
+
 	return ret;
 }
 
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 880cc090dc4..91d0c6a86e3 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -637,12 +637,15 @@ static void macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
 	} /* else everything is zero */
 }
 
+/* Neighbour code has some assumptions on HH_DATA_MOD alignment */
+#define MACVTAP_RESERVE HH_DATA_OFF(ETH_HLEN)
+
 /* Get packet from user space buffer */
 static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 				const struct iovec *iv, unsigned long total_len,
 				size_t count, int noblock)
 {
-	int good_linear = SKB_MAX_HEAD(NET_IP_ALIGN);
+	int good_linear = SKB_MAX_HEAD(MACVTAP_RESERVE);
 	struct sk_buff *skb;
 	struct macvlan_dev *vlan;
 	unsigned long len = total_len;
@@ -701,7 +704,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 			linear = vnet_hdr.hdr_len;
 	}
 
-	skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, copylen,
+	skb = macvtap_alloc_skb(&q->sk, MACVTAP_RESERVE, copylen,
 				linear, noblock, &err);
 	if (!skb)
 		goto err;
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index e22e602beef..c5789cdf777 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -47,7 +47,7 @@
 #define PSF_TX		0x1000
 #define EXT_EVENT	1
 #define CAL_EVENT	7
-#define CAL_TRIGGER	7
+#define CAL_TRIGGER	1
 #define DP83640_N_PINS	12
 
 #define MII_DP83640_MICR 0x11
@@ -495,7 +495,9 @@ static int ptp_dp83640_enable(struct ptp_clock_info *ptp,
 			else
 				evnt |= EVNT_RISE;
 		}
+		mutex_lock(&clock->extreg_lock);
 		ext_write(0, phydev, PAGE5, PTP_EVNT, evnt);
+		mutex_unlock(&clock->extreg_lock);
 		return 0;
 
 	case PTP_CLK_REQ_PEROUT:
@@ -531,6 +533,8 @@ static u8 status_frame_src[6] = { 0x08, 0x00, 0x17, 0x0B, 0x6B, 0x0F };
 
 static void enable_status_frames(struct phy_device *phydev, bool on)
 {
+	struct dp83640_private *dp83640 = phydev->priv;
+	struct dp83640_clock *clock = dp83640->clock;
 	u16 cfg0 = 0, ver;
 
 	if (on)
@@ -538,9 +542,13 @@ static void enable_status_frames(struct phy_device *phydev, bool on)
 
 	ver = (PSF_PTPVER & VERSIONPTP_MASK) << VERSIONPTP_SHIFT;
 
+	mutex_lock(&clock->extreg_lock);
+
 	ext_write(0, phydev, PAGE5, PSF_CFG0, cfg0);
 	ext_write(0, phydev, PAGE6, PSF_CFG1, ver);
 
+	mutex_unlock(&clock->extreg_lock);
+
 	if (!phydev->attached_dev) {
 		pr_warn("expected to find an attached netdevice\n");
 		return;
@@ -837,7 +845,7 @@ static void decode_rxts(struct dp83640_private *dp83640,
 	list_del_init(&rxts->list);
 	phy2rxts(phy_rxts, rxts);
 
-	spin_lock_irqsave(&dp83640->rx_queue.lock, flags);
+	spin_lock(&dp83640->rx_queue.lock);
 	skb_queue_walk(&dp83640->rx_queue, skb) {
 		struct dp83640_skb_info *skb_info;
 
@@ -852,7 +860,7 @@ static void decode_rxts(struct dp83640_private *dp83640,
 			break;
 		}
 	}
-	spin_unlock_irqrestore(&dp83640->rx_queue.lock, flags);
+	spin_unlock(&dp83640->rx_queue.lock);
 
 	if (!shhwtstamps)
 		list_add_tail(&rxts->list, &dp83640->rxts);
@@ -1172,11 +1180,18 @@ static int dp83640_config_init(struct phy_device *phydev)
 
 	if (clock->chosen && !list_empty(&clock->phylist))
 		recalibrate(clock);
-	else
+	else {
+		mutex_lock(&clock->extreg_lock);
 		enable_broadcast(phydev, clock->page, 1);
+		mutex_unlock(&clock->extreg_lock);
+	}
 
 	enable_status_frames(phydev, true);
+
+	mutex_lock(&clock->extreg_lock);
 	ext_write(0, phydev, PAGE4, PTP_CTL, PTP_ENABLE);
+	mutex_unlock(&clock->extreg_lock);
+
 	return 0;
 }
 
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 767cd110f49..91d6d03da96 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -236,6 +236,25 @@ static inline unsigned int phy_find_valid(unsigned int idx, u32 features)
 }
 
 /**
+ * phy_check_valid - check if there is a valid PHY setting which matches
+ *		     speed, duplex, and feature mask
+ * @speed: speed to match
+ * @duplex: duplex to match
+ * @features: A mask of the valid settings
+ *
+ * Description: Returns true if there is a valid setting, false otherwise.
+ */
+static inline bool phy_check_valid(int speed, int duplex, u32 features)
+{
+	unsigned int idx;
+
+	idx = phy_find_valid(phy_find_setting(speed, duplex), features);
+
+	return settings[idx].speed == speed && settings[idx].duplex == duplex &&
+		(settings[idx].setting & features);
+}
+
+/**
  * phy_sanitize_settings - make sure the PHY is set to supported speed and duplex
  * @phydev: the target phy_device struct
  *
@@ -1031,18 +1050,18 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
 {
 	/* According to 802.3az,the EEE is supported only in full duplex-mode.
 	 * Also EEE feature is active when core is operating with MII, GMII
-	 * or RGMII. Internal PHYs are also allowed to proceed and should
-	 * return an error if they do not support EEE.
+	 * or RGMII (all kinds). Internal PHYs are also allowed to proceed and
+	 * should return an error if they do not support EEE.
 	 */
 	if ((phydev->duplex == DUPLEX_FULL) &&
 	    ((phydev->interface == PHY_INTERFACE_MODE_MII) ||
 	    (phydev->interface == PHY_INTERFACE_MODE_GMII) ||
-	    (phydev->interface == PHY_INTERFACE_MODE_RGMII) ||
+	    (phydev->interface >= PHY_INTERFACE_MODE_RGMII &&
+	     phydev->interface <= PHY_INTERFACE_MODE_RGMII_TXID) ||
 	     phy_is_internal(phydev))) {
 		int eee_lp, eee_cap, eee_adv;
 		u32 lp, cap, adv;
 		int status;
-		unsigned int idx;
 
 		/* Read phy status to properly get the right settings */
 		status = phy_read_status(phydev);
@@ -1074,8 +1093,7 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
 
 		adv = mmd_eee_adv_to_ethtool_adv_t(eee_adv);
 		lp = mmd_eee_adv_to_ethtool_adv_t(eee_lp);
-		idx = phy_find_setting(phydev->speed, phydev->duplex);
-		if (!(lp & adv & settings[idx].setting))
+		if (!phy_check_valid(phydev->speed, phydev->duplex, lp & adv))
 			goto eee_exit_err;
 
 		if (clk_stop_enable) {
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 3fc91e89f5a..70a0d88de65 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -782,10 +782,11 @@ static int genphy_config_advert(struct phy_device *phydev)
 	if (phydev->supported & (SUPPORTED_1000baseT_Half |
 				 SUPPORTED_1000baseT_Full)) {
 		adv |= ethtool_adv_to_mii_ctrl1000_t(advertise);
-		if (adv != oldadv)
-			changed = 1;
 	}
 
+	if (adv != oldadv)
+		changed = 1;
+
 	err = phy_write(phydev, MII_CTRL1000, adv);
 	if (err < 0)
 		return err;
diff --git a/drivers/net/ppp/Kconfig b/drivers/net/ppp/Kconfig
index 1373c6d7278..282aec4860e 100644
--- a/drivers/net/ppp/Kconfig
+++ b/drivers/net/ppp/Kconfig
@@ -149,6 +149,23 @@ config PPPOL2TP
 	  tunnels. L2TP is replacing PPTP for VPN uses.
 if TTY
 
+config PPPOLAC
+	tristate "PPP on L2TP Access Concentrator"
+	depends on PPP && INET
+	help
+	  L2TP (RFC 2661) is a tunneling protocol widely used in virtual private
+	  networks. This driver handles L2TP data packets between a UDP socket
+	  and a PPP channel, but only permits one session per socket. Thus it is
+	  fairly simple and suited for clients.
+
+config PPPOPNS
+	tristate "PPP on PPTP Network Server"
+	depends on PPP && INET
+	help
+	  PPTP (RFC 2637) is a tunneling protocol widely used in virtual private
+	  networks. This driver handles PPTP data packets between a RAW socket
+	  and a PPP channel. It is fairly simple and easy to use.
+
 config PPP_ASYNC
 	tristate "PPP support for async serial ports"
 	depends on PPP
diff --git a/drivers/net/ppp/Makefile b/drivers/net/ppp/Makefile
index a6b6297b006..d283d03c468 100644
--- a/drivers/net/ppp/Makefile
+++ b/drivers/net/ppp/Makefile
@@ -11,3 +11,5 @@ obj-$(CONFIG_PPP_SYNC_TTY) += ppp_synctty.o
 obj-$(CONFIG_PPPOE) += pppox.o pppoe.o
 obj-$(CONFIG_PPPOL2TP) += pppox.o
 obj-$(CONFIG_PPTP) += pppox.o pptp.o
+obj-$(CONFIG_PPPOLAC) += pppox.o pppolac.o
+obj-$(CONFIG_PPPOPNS) += pppox.o pppopns.o
diff --git a/drivers/net/ppp/ppp_deflate.c b/drivers/net/ppp/ppp_deflate.c
index 602c625d95d..b5edc7f96a3 100644
--- a/drivers/net/ppp/ppp_deflate.c
+++ b/drivers/net/ppp/ppp_deflate.c
@@ -246,7 +246,7 @@ static int z_compress(void *arg, unsigned char *rptr, unsigned char *obuf,
 	/*
 	 * See if we managed to reduce the size of the packet.
 	 */
-	if (olen < isize) {
+	if (olen < isize && olen <= osize) {
 		state->stats.comp_bytes += olen;
 		state->stats.comp_packets++;
 	} else {
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 794a4732936..6d6c20c3ef7 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1714,6 +1714,7 @@ ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch)
 {
 	/* note: a 0-length skb is used as an error indication */
 	if (skb->len > 0) {
+		skb_checksum_complete_unset(skb);
 #ifdef CONFIG_PPP_MULTILINK
 		/* XXX do channel-level decompression here */
 		if (PPP_PROTO(skb) == PPP_MP)
diff --git a/drivers/net/ppp/pppolac.c b/drivers/net/ppp/pppolac.c
new file mode 100644
index 00000000000..a5d3d634fd9
--- /dev/null
+++ b/drivers/net/ppp/pppolac.c
@@ -0,0 +1,449 @@
+/* drivers/net/pppolac.c
+ *
+ * Driver for PPP on L2TP Access Concentrator / PPPoLAC Socket (RFC 2661)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+/* This driver handles L2TP data packets between a UDP socket and a PPP channel.
+ * The socket must keep connected, and only one session per socket is permitted.
+ * Sequencing of outgoing packets is controlled by LNS. Incoming packets with
+ * sequences are reordered within a sliding window of one second. Currently
+ * reordering only happens when a packet is received. It is done for simplicity
+ * since no additional locks or threads are required. This driver only works on
+ * IPv4 due to the lack of UDP encapsulation support in IPv6. */
+
+#include <linux/module.h>
+#include <linux/jiffies.h>
+#include <linux/workqueue.h>
+#include <linux/skbuff.h>
+#include <linux/file.h>
+#include <linux/netdevice.h>
+#include <linux/net.h>
+#include <linux/udp.h>
+#include <linux/ppp_defs.h>
+#include <linux/if_ppp.h>
+#include <linux/if_pppox.h>
+#include <linux/ppp_channel.h>
+#include <net/tcp_states.h>
+#include <asm/uaccess.h>
+
+#define L2TP_CONTROL_BIT	0x80
+#define L2TP_LENGTH_BIT		0x40
+#define L2TP_SEQUENCE_BIT	0x08
+#define L2TP_OFFSET_BIT		0x02
+#define L2TP_VERSION		0x02
+#define L2TP_VERSION_MASK	0x0F
+
+#define PPP_ADDR	0xFF
+#define PPP_CTRL	0x03
+
+union unaligned {
+	__u32 u32;
+} __attribute__((packed));
+
+static inline union unaligned *unaligned(void *ptr)
+{
+	return (union unaligned *)ptr;
+}
+
+struct meta {
+	__u32 sequence;
+	__u32 timestamp;
+};
+
+static inline struct meta *skb_meta(struct sk_buff *skb)
+{
+	return (struct meta *)skb->cb;
+}
+
+/******************************************************************************/
+
+static int pppolac_recv_core(struct sock *sk_udp, struct sk_buff *skb)
+{
+	struct sock *sk = (struct sock *)sk_udp->sk_user_data;
+	struct pppolac_opt *opt = &pppox_sk(sk)->proto.lac;
+	struct meta *meta = skb_meta(skb);
+	__u32 now = jiffies;
+	__u8 bits;
+	__u8 *ptr;
+
+	/* Drop the packet if L2TP header is missing. */
+	if (skb->len < sizeof(struct udphdr) + 6)
+		goto drop;
+
+	/* Put it back if it is a control packet. */
+	if (skb->data[sizeof(struct udphdr)] & L2TP_CONTROL_BIT)
+		return opt->backlog_rcv(sk_udp, skb);
+
+	/* Skip UDP header. */
+	skb_pull(skb, sizeof(struct udphdr));
+
+	/* Check the version. */
+	if ((skb->data[1] & L2TP_VERSION_MASK) != L2TP_VERSION)
+		goto drop;
+	bits = skb->data[0];
+	ptr = &skb->data[2];
+
+	/* Check the length if it is present. */
+	if (bits & L2TP_LENGTH_BIT) {
+		if ((ptr[0] << 8 | ptr[1]) != skb->len)
+			goto drop;
+		ptr += 2;
+	}
+
+	/* Skip all fields including optional ones. */
+	if (!skb_pull(skb, 6 + (bits & L2TP_SEQUENCE_BIT ? 4 : 0) +
+			(bits & L2TP_LENGTH_BIT ? 2 : 0) +
+			(bits & L2TP_OFFSET_BIT ? 2 : 0)))
+		goto drop;
+
+	/* Skip the offset padding if it is present. */
+	if (bits & L2TP_OFFSET_BIT &&
+			!skb_pull(skb, skb->data[-2] << 8 | skb->data[-1]))
+		goto drop;
+
+	/* Check the tunnel and the session. */
+	if (unaligned(ptr)->u32 != opt->local)
+		goto drop;
+
+	/* Check the sequence if it is present. */
+	if (bits & L2TP_SEQUENCE_BIT) {
+		meta->sequence = ptr[4] << 8 | ptr[5];
+		if ((__s16)(meta->sequence - opt->recv_sequence) < 0)
+			goto drop;
+	}
+
+	/* Skip PPP address and control if they are present. */
+	if (skb->len >= 2 && skb->data[0] == PPP_ADDR &&
+			skb->data[1] == PPP_CTRL)
+		skb_pull(skb, 2);
+
+	/* Fix PPP protocol if it is compressed. */
+	if (skb->len >= 1 && skb->data[0] & 1)
+		skb_push(skb, 1)[0] = 0;
+
+	/* Drop the packet if PPP protocol is missing. */
+	if (skb->len < 2)
+		goto drop;
+
+	/* Perform reordering if sequencing is enabled. */
+	atomic_set(&opt->sequencing, bits & L2TP_SEQUENCE_BIT);
+	if (bits & L2TP_SEQUENCE_BIT) {
+		struct sk_buff *skb1;
+
+		/* Insert the packet into receive queue in order. */
+		skb_set_owner_r(skb, sk);
+		skb_queue_walk(&sk->sk_receive_queue, skb1) {
+			struct meta *meta1 = skb_meta(skb1);
+			__s16 order = meta->sequence - meta1->sequence;
+			if (order == 0)
+				goto drop;
+			if (order < 0) {
+				meta->timestamp = meta1->timestamp;
+				skb_insert(skb1, skb, &sk->sk_receive_queue);
+				skb = NULL;
+				break;
+			}
+		}
+		if (skb) {
+			meta->timestamp = now;
+			skb_queue_tail(&sk->sk_receive_queue, skb);
+		}
+
+		/* Remove packets from receive queue as long as
+		 * 1. the receive buffer is full,
+		 * 2. they are queued longer than one second, or
+		 * 3. there are no missing packets before them. */
+		skb_queue_walk_safe(&sk->sk_receive_queue, skb, skb1) {
+			meta = skb_meta(skb);
+			if (atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
+					now - meta->timestamp < HZ &&
+					meta->sequence != opt->recv_sequence)
+				break;
+			skb_unlink(skb, &sk->sk_receive_queue);
+			opt->recv_sequence = (__u16)(meta->sequence + 1);
+			skb_orphan(skb);
+			ppp_input(&pppox_sk(sk)->chan, skb);
+		}
+		return NET_RX_SUCCESS;
+	}
+
+	/* Flush receive queue if sequencing is disabled. */
+	skb_queue_purge(&sk->sk_receive_queue);
+	skb_orphan(skb);
+	ppp_input(&pppox_sk(sk)->chan, skb);
+	return NET_RX_SUCCESS;
+drop:
+	kfree_skb(skb);
+	return NET_RX_DROP;
+}
+
+static int pppolac_recv(struct sock *sk_udp, struct sk_buff *skb)
+{
+	sock_hold(sk_udp);
+	sk_receive_skb(sk_udp, skb, 0);
+	return 0;
+}
+
+static struct sk_buff_head delivery_queue;
+
+static void pppolac_xmit_core(struct work_struct *delivery_work)
+{
+	mm_segment_t old_fs = get_fs();
+	struct sk_buff *skb;
+
+	set_fs(KERNEL_DS);
+	while ((skb = skb_dequeue(&delivery_queue))) {
+		struct sock *sk_udp = skb->sk;
+		struct kvec iov = {.iov_base = skb->data, .iov_len = skb->len};
+		struct msghdr msg = {
+			.msg_iov = (struct iovec *)&iov,
+			.msg_iovlen = 1,
+			.msg_flags = MSG_NOSIGNAL | MSG_DONTWAIT,
+		};
+		sk_udp->sk_prot->sendmsg(NULL, sk_udp, &msg, skb->len);
+		kfree_skb(skb);
+	}
+	set_fs(old_fs);
+}
+
+static DECLARE_WORK(delivery_work, pppolac_xmit_core);
+
+static int pppolac_xmit(struct ppp_channel *chan, struct sk_buff *skb)
+{
+	struct sock *sk_udp = (struct sock *)chan->private;
+	struct pppolac_opt *opt = &pppox_sk(sk_udp->sk_user_data)->proto.lac;
+
+	/* Install PPP address and control. */
+	skb_push(skb, 2);
+	skb->data[0] = PPP_ADDR;
+	skb->data[1] = PPP_CTRL;
+
+	/* Install L2TP header. */
+	if (atomic_read(&opt->sequencing)) {
+		skb_push(skb, 10);
+		skb->data[0] = L2TP_SEQUENCE_BIT;
+		skb->data[6] = opt->xmit_sequence >> 8;
+		skb->data[7] = opt->xmit_sequence;
+		skb->data[8] = 0;
+		skb->data[9] = 0;
+		opt->xmit_sequence++;
+	} else {
+		skb_push(skb, 6);
+		skb->data[0] = 0;
+	}
+	skb->data[1] = L2TP_VERSION;
+	unaligned(&skb->data[2])->u32 = opt->remote;
+
+	/* Now send the packet via the delivery queue. */
+	skb_set_owner_w(skb, sk_udp);
+	skb_queue_tail(&delivery_queue, skb);
+	schedule_work(&delivery_work);
+	return 1;
+}
+
+/******************************************************************************/
+
+static struct ppp_channel_ops pppolac_channel_ops = {
+	.start_xmit = pppolac_xmit,
+};
+
+static int pppolac_connect(struct socket *sock, struct sockaddr *useraddr,
+	int addrlen, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct pppox_sock *po = pppox_sk(sk);
+	struct sockaddr_pppolac *addr = (struct sockaddr_pppolac *)useraddr;
+	struct socket *sock_udp = NULL;
+	struct sock *sk_udp;
+	int error;
+
+	if (addrlen != sizeof(struct sockaddr_pppolac) ||
+			!addr->local.tunnel || !addr->local.session ||
+			!addr->remote.tunnel || !addr->remote.session) {
+		return -EINVAL;
+	}
+
+	lock_sock(sk);
+	error = -EALREADY;
+	if (sk->sk_state != PPPOX_NONE)
+		goto out;
+
+	sock_udp = sockfd_lookup(addr->udp_socket, &error);
+	if (!sock_udp)
+		goto out;
+	sk_udp = sock_udp->sk;
+	lock_sock(sk_udp);
+
+	/* Remove this check when IPv6 supports UDP encapsulation. */
+	error = -EAFNOSUPPORT;
+	if (sk_udp->sk_family != AF_INET)
+		goto out;
+	error = -EPROTONOSUPPORT;
+	if (sk_udp->sk_protocol != IPPROTO_UDP)
+		goto out;
+	error = -EDESTADDRREQ;
+	if (sk_udp->sk_state != TCP_ESTABLISHED)
+		goto out;
+	error = -EBUSY;
+	if (udp_sk(sk_udp)->encap_type || sk_udp->sk_user_data)
+		goto out;
+	if (!sk_udp->sk_bound_dev_if) {
+		struct dst_entry *dst = sk_dst_get(sk_udp);
+		error = -ENODEV;
+		if (!dst)
+			goto out;
+		sk_udp->sk_bound_dev_if = dst->dev->ifindex;
+		dst_release(dst);
+	}
+
+	po->chan.hdrlen = 12;
+	po->chan.private = sk_udp;
+	po->chan.ops = &pppolac_channel_ops;
+	po->chan.mtu = PPP_MRU - 80;
+	po->proto.lac.local = unaligned(&addr->local)->u32;
+	po->proto.lac.remote = unaligned(&addr->remote)->u32;
+	atomic_set(&po->proto.lac.sequencing, 1);
+	po->proto.lac.backlog_rcv = sk_udp->sk_backlog_rcv;
+
+	error = ppp_register_channel(&po->chan);
+	if (error)
+		goto out;
+
+	sk->sk_state = PPPOX_CONNECTED;
+	udp_sk(sk_udp)->encap_type = UDP_ENCAP_L2TPINUDP;
+	udp_sk(sk_udp)->encap_rcv = pppolac_recv;
+	sk_udp->sk_backlog_rcv = pppolac_recv_core;
+	sk_udp->sk_user_data = sk;
+out:
+	if (sock_udp) {
+		release_sock(sk_udp);
+		if (error)
+			sockfd_put(sock_udp);
+	}
+	release_sock(sk);
+	return error;
+}
+
+static int pppolac_release(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+
+	if (!sk)
+		return 0;
+
+	lock_sock(sk);
+	if (sock_flag(sk, SOCK_DEAD)) {
+		release_sock(sk);
+		return -EBADF;
+	}
+
+	if (sk->sk_state != PPPOX_NONE) {
+		struct sock *sk_udp = (struct sock *)pppox_sk(sk)->chan.private;
+		lock_sock(sk_udp);
+		skb_queue_purge(&sk->sk_receive_queue);
+		pppox_unbind_sock(sk);
+		udp_sk(sk_udp)->encap_type = 0;
+		udp_sk(sk_udp)->encap_rcv = NULL;
+		sk_udp->sk_backlog_rcv = pppox_sk(sk)->proto.lac.backlog_rcv;
+		sk_udp->sk_user_data = NULL;
+		release_sock(sk_udp);
+		sockfd_put(sk_udp->sk_socket);
+	}
+
+	sock_orphan(sk);
+	sock->sk = NULL;
+	release_sock(sk);
+	sock_put(sk);
+	return 0;
+}
+
+/******************************************************************************/
+
+static struct proto pppolac_proto = {
+	.name = "PPPOLAC",
+	.owner = THIS_MODULE,
+	.obj_size = sizeof(struct pppox_sock),
+};
+
+static struct proto_ops pppolac_proto_ops = {
+	.family = PF_PPPOX,
+	.owner = THIS_MODULE,
+	.release = pppolac_release,
+	.bind = sock_no_bind,
+	.connect = pppolac_connect,
+	.socketpair = sock_no_socketpair,
+	.accept = sock_no_accept,
+	.getname = sock_no_getname,
+	.poll = sock_no_poll,
+	.ioctl = pppox_ioctl,
+	.listen = sock_no_listen,
+	.shutdown = sock_no_shutdown,
+	.setsockopt = sock_no_setsockopt,
+	.getsockopt = sock_no_getsockopt,
+	.sendmsg = sock_no_sendmsg,
+	.recvmsg = sock_no_recvmsg,
+	.mmap = sock_no_mmap,
+};
+
+static int pppolac_create(struct net *net, struct socket *sock)
+{
+	struct sock *sk;
+
+	sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppolac_proto);
+	if (!sk)
+		return -ENOMEM;
+
+	sock_init_data(sock, sk);
+	sock->state = SS_UNCONNECTED;
+	sock->ops = &pppolac_proto_ops;
+	sk->sk_protocol = PX_PROTO_OLAC;
+	sk->sk_state = PPPOX_NONE;
+	return 0;
+}
+
+/******************************************************************************/
+
+static struct pppox_proto pppolac_pppox_proto = {
+	.create = pppolac_create,
+	.owner = THIS_MODULE,
+};
+
+static int __init pppolac_init(void)
+{
+	int error;
+
+	error = proto_register(&pppolac_proto, 0);
+	if (error)
+		return error;
+
+	error = register_pppox_proto(PX_PROTO_OLAC, &pppolac_pppox_proto);
+	if (error)
+		proto_unregister(&pppolac_proto);
+	else
+		skb_queue_head_init(&delivery_queue);
+	return error;
+}
+
+static void __exit pppolac_exit(void)
+{
+	unregister_pppox_proto(PX_PROTO_OLAC);
+	proto_unregister(&pppolac_proto);
+}
+
+module_init(pppolac_init);
+module_exit(pppolac_exit);
+
+MODULE_DESCRIPTION("PPP on L2TP Access Concentrator (PPPoLAC)");
+MODULE_AUTHOR("Chia-chi Yeh <chiachi@android.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ppp/pppopns.c b/drivers/net/ppp/pppopns.c
new file mode 100644
index 00000000000..dc15f978c92
--- /dev/null
+++ b/drivers/net/ppp/pppopns.c
@@ -0,0 +1,428 @@
+/* drivers/net/pppopns.c
+ *
+ * Driver for PPP on PPTP Network Server / PPPoPNS Socket (RFC 2637)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+/* This driver handles PPTP data packets between a RAW socket and a PPP channel.
+ * The socket is created in the kernel space and connected to the same address
+ * of the control socket. Outgoing packets are always sent with sequences but
+ * without acknowledgements. Incoming packets with sequences are reordered
+ * within a sliding window of one second. Currently reordering only happens when
+ * a packet is received. It is done for simplicity since no additional locks or
+ * threads are required. This driver should work on both IPv4 and IPv6. */
+
+#include <linux/module.h>
+#include <linux/jiffies.h>
+#include <linux/workqueue.h>
+#include <linux/skbuff.h>
+#include <linux/file.h>
+#include <linux/netdevice.h>
+#include <linux/net.h>
+#include <linux/ppp_defs.h>
+#include <linux/if.h>
+#include <linux/if_ppp.h>
+#include <linux/if_pppox.h>
+#include <linux/ppp_channel.h>
+#include <asm/uaccess.h>
+
+#define GRE_HEADER_SIZE		8
+
+#define PPTP_GRE_BITS		htons(0x2001)
+#define PPTP_GRE_BITS_MASK	htons(0xEF7F)
+#define PPTP_GRE_SEQ_BIT	htons(0x1000)
+#define PPTP_GRE_ACK_BIT	htons(0x0080)
+#define PPTP_GRE_TYPE		htons(0x880B)
+
+#define PPP_ADDR	0xFF
+#define PPP_CTRL	0x03
+
+struct header {
+	__u16	bits;
+	__u16	type;
+	__u16	length;
+	__u16	call;
+	__u32	sequence;
+} __attribute__((packed));
+
+struct meta {
+	__u32 sequence;
+	__u32 timestamp;
+};
+
+static inline struct meta *skb_meta(struct sk_buff *skb)
+{
+	return (struct meta *)skb->cb;
+}
+
+/******************************************************************************/
+
+static int pppopns_recv_core(struct sock *sk_raw, struct sk_buff *skb)
+{
+	struct sock *sk = (struct sock *)sk_raw->sk_user_data;
+	struct pppopns_opt *opt = &pppox_sk(sk)->proto.pns;
+	struct meta *meta = skb_meta(skb);
+	__u32 now = jiffies;
+	struct header *hdr;
+
+	/* Skip transport header */
+	skb_pull(skb, skb_transport_header(skb) - skb->data);
+
+	/* Drop the packet if GRE header is missing. */
+	if (skb->len < GRE_HEADER_SIZE)
+		goto drop;
+	hdr = (struct header *)skb->data;
+
+	/* Check the header. */
+	if (hdr->type != PPTP_GRE_TYPE || hdr->call != opt->local ||
+			(hdr->bits & PPTP_GRE_BITS_MASK) != PPTP_GRE_BITS)
+		goto drop;
+
+	/* Skip all fields including optional ones. */
+	if (!skb_pull(skb, GRE_HEADER_SIZE +
+			(hdr->bits & PPTP_GRE_SEQ_BIT ? 4 : 0) +
+			(hdr->bits & PPTP_GRE_ACK_BIT ? 4 : 0)))
+		goto drop;
+
+	/* Check the length. */
+	if (skb->len != ntohs(hdr->length))
+		goto drop;
+
+	/* Check the sequence if it is present. */
+	if (hdr->bits & PPTP_GRE_SEQ_BIT) {
+		meta->sequence = ntohl(hdr->sequence);
+		if ((__s32)(meta->sequence - opt->recv_sequence) < 0)
+			goto drop;
+	}
+
+	/* Skip PPP address and control if they are present. */
+	if (skb->len >= 2 && skb->data[0] == PPP_ADDR &&
+			skb->data[1] == PPP_CTRL)
+		skb_pull(skb, 2);
+
+	/* Fix PPP protocol if it is compressed. */
+	if (skb->len >= 1 && skb->data[0] & 1)
+		skb_push(skb, 1)[0] = 0;
+
+	/* Drop the packet if PPP protocol is missing. */
+	if (skb->len < 2)
+		goto drop;
+
+	/* Perform reordering if sequencing is enabled. */
+	if (hdr->bits & PPTP_GRE_SEQ_BIT) {
+		struct sk_buff *skb1;
+
+		/* Insert the packet into receive queue in order. */
+		skb_set_owner_r(skb, sk);
+		skb_queue_walk(&sk->sk_receive_queue, skb1) {
+			struct meta *meta1 = skb_meta(skb1);
+			__s32 order = meta->sequence - meta1->sequence;
+			if (order == 0)
+				goto drop;
+			if (order < 0) {
+				meta->timestamp = meta1->timestamp;
+				skb_insert(skb1, skb, &sk->sk_receive_queue);
+				skb = NULL;
+				break;
+			}
+		}
+		if (skb) {
+			meta->timestamp = now;
+			skb_queue_tail(&sk->sk_receive_queue, skb);
+		}
+
+		/* Remove packets from receive queue as long as
+		 * 1. the receive buffer is full,
+		 * 2. they are queued longer than one second, or
+		 * 3. there are no missing packets before them. */
+		skb_queue_walk_safe(&sk->sk_receive_queue, skb, skb1) {
+			meta = skb_meta(skb);
+			if (atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
+					now - meta->timestamp < HZ &&
+					meta->sequence != opt->recv_sequence)
+				break;
+			skb_unlink(skb, &sk->sk_receive_queue);
+			opt->recv_sequence = meta->sequence + 1;
+			skb_orphan(skb);
+			ppp_input(&pppox_sk(sk)->chan, skb);
+		}
+		return NET_RX_SUCCESS;
+	}
+
+	/* Flush receive queue if sequencing is disabled. */
+	skb_queue_purge(&sk->sk_receive_queue);
+	skb_orphan(skb);
+	ppp_input(&pppox_sk(sk)->chan, skb);
+	return NET_RX_SUCCESS;
+drop:
+	kfree_skb(skb);
+	return NET_RX_DROP;
+}
+
+static void pppopns_recv(struct sock *sk_raw)
+{
+	struct sk_buff *skb;
+	while ((skb = skb_dequeue(&sk_raw->sk_receive_queue))) {
+		sock_hold(sk_raw);
+		sk_receive_skb(sk_raw, skb, 0);
+	}
+}
+
+static struct sk_buff_head delivery_queue;
+
+static void pppopns_xmit_core(struct work_struct *delivery_work)
+{
+	mm_segment_t old_fs = get_fs();
+	struct sk_buff *skb;
+
+	set_fs(KERNEL_DS);
+	while ((skb = skb_dequeue(&delivery_queue))) {
+		struct sock *sk_raw = skb->sk;
+		struct kvec iov = {.iov_base = skb->data, .iov_len = skb->len};
+		struct msghdr msg = {
+			.msg_iov = (struct iovec *)&iov,
+			.msg_iovlen = 1,
+			.msg_flags = MSG_NOSIGNAL | MSG_DONTWAIT,
+		};
+		sk_raw->sk_prot->sendmsg(NULL, sk_raw, &msg, skb->len);
+		kfree_skb(skb);
+	}
+	set_fs(old_fs);
+}
+
+static DECLARE_WORK(delivery_work, pppopns_xmit_core);
+
+static int pppopns_xmit(struct ppp_channel *chan, struct sk_buff *skb)
+{
+	struct sock *sk_raw = (struct sock *)chan->private;
+	struct pppopns_opt *opt = &pppox_sk(sk_raw->sk_user_data)->proto.pns;
+	struct header *hdr;
+	__u16 length;
+
+	/* Install PPP address and control. */
+	skb_push(skb, 2);
+	skb->data[0] = PPP_ADDR;
+	skb->data[1] = PPP_CTRL;
+	length = skb->len;
+
+	/* Install PPTP GRE header. */
+	hdr = (struct header *)skb_push(skb, 12);
+	hdr->bits = PPTP_GRE_BITS | PPTP_GRE_SEQ_BIT;
+	hdr->type = PPTP_GRE_TYPE;
+	hdr->length = htons(length);
+	hdr->call = opt->remote;
+	hdr->sequence = htonl(opt->xmit_sequence);
+	opt->xmit_sequence++;
+
+	/* Now send the packet via the delivery queue. */
+	skb_set_owner_w(skb, sk_raw);
+	skb_queue_tail(&delivery_queue, skb);
+	schedule_work(&delivery_work);
+	return 1;
+}
+
+/******************************************************************************/
+
+static struct ppp_channel_ops pppopns_channel_ops = {
+	.start_xmit = pppopns_xmit,
+};
+
+static int pppopns_connect(struct socket *sock, struct sockaddr *useraddr,
+	int addrlen, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct pppox_sock *po = pppox_sk(sk);
+	struct sockaddr_pppopns *addr = (struct sockaddr_pppopns *)useraddr;
+	struct sockaddr_storage ss;
+	struct socket *sock_tcp = NULL;
+	struct socket *sock_raw = NULL;
+	struct sock *sk_tcp;
+	struct sock *sk_raw;
+	int error;
+
+	if (addrlen != sizeof(struct sockaddr_pppopns))
+		return -EINVAL;
+
+	lock_sock(sk);
+	error = -EALREADY;
+	if (sk->sk_state != PPPOX_NONE)
+		goto out;
+
+	sock_tcp = sockfd_lookup(addr->tcp_socket, &error);
+	if (!sock_tcp)
+		goto out;
+	sk_tcp = sock_tcp->sk;
+	error = -EPROTONOSUPPORT;
+	if (sk_tcp->sk_protocol != IPPROTO_TCP)
+		goto out;
+	addrlen = sizeof(struct sockaddr_storage);
+	error = kernel_getpeername(sock_tcp, (struct sockaddr *)&ss, &addrlen);
+	if (error)
+		goto out;
+	if (!sk_tcp->sk_bound_dev_if) {
+		struct dst_entry *dst = sk_dst_get(sk_tcp);
+		error = -ENODEV;
+		if (!dst)
+			goto out;
+		sk_tcp->sk_bound_dev_if = dst->dev->ifindex;
+		dst_release(dst);
+	}
+
+	error = sock_create(ss.ss_family, SOCK_RAW, IPPROTO_GRE, &sock_raw);
+	if (error)
+		goto out;
+	sk_raw = sock_raw->sk;
+	sk_raw->sk_bound_dev_if = sk_tcp->sk_bound_dev_if;
+	error = kernel_connect(sock_raw, (struct sockaddr *)&ss, addrlen, 0);
+	if (error)
+		goto out;
+
+	po->chan.hdrlen = 14;
+	po->chan.private = sk_raw;
+	po->chan.ops = &pppopns_channel_ops;
+	po->chan.mtu = PPP_MRU - 80;
+	po->proto.pns.local = addr->local;
+	po->proto.pns.remote = addr->remote;
+	po->proto.pns.data_ready = sk_raw->sk_data_ready;
+	po->proto.pns.backlog_rcv = sk_raw->sk_backlog_rcv;
+
+	error = ppp_register_channel(&po->chan);
+	if (error)
+		goto out;
+
+	sk->sk_state = PPPOX_CONNECTED;
+	lock_sock(sk_raw);
+	sk_raw->sk_data_ready = pppopns_recv;
+	sk_raw->sk_backlog_rcv = pppopns_recv_core;
+	sk_raw->sk_user_data = sk;
+	release_sock(sk_raw);
+out:
+	if (sock_tcp)
+		sockfd_put(sock_tcp);
+	if (error && sock_raw)
+		sock_release(sock_raw);
+	release_sock(sk);
+	return error;
+}
+
+static int pppopns_release(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+
+	if (!sk)
+		return 0;
+
+	lock_sock(sk);
+	if (sock_flag(sk, SOCK_DEAD)) {
+		release_sock(sk);
+		return -EBADF;
+	}
+
+	if (sk->sk_state != PPPOX_NONE) {
+		struct sock *sk_raw = (struct sock *)pppox_sk(sk)->chan.private;
+		lock_sock(sk_raw);
+		skb_queue_purge(&sk->sk_receive_queue);
+		pppox_unbind_sock(sk);
+		sk_raw->sk_data_ready = pppox_sk(sk)->proto.pns.data_ready;
+		sk_raw->sk_backlog_rcv = pppox_sk(sk)->proto.pns.backlog_rcv;
+		sk_raw->sk_user_data = NULL;
+		release_sock(sk_raw);
+		sock_release(sk_raw->sk_socket);
+	}
+
+	sock_orphan(sk);
+	sock->sk = NULL;
+	release_sock(sk);
+	sock_put(sk);
+	return 0;
+}
+
+/******************************************************************************/
+
+static struct proto pppopns_proto = {
+	.name = "PPPOPNS",
+	.owner = THIS_MODULE,
+	.obj_size = sizeof(struct pppox_sock),
+};
+
+static struct proto_ops pppopns_proto_ops = {
+	.family = PF_PPPOX,
+	.owner = THIS_MODULE,
+	.release = pppopns_release,
+	.bind = sock_no_bind,
+	.connect = pppopns_connect,
+	.socketpair = sock_no_socketpair,
+	.accept = sock_no_accept,
+	.getname = sock_no_getname,
+	.poll = sock_no_poll,
+	.ioctl = pppox_ioctl,
+	.listen = sock_no_listen,
+	.shutdown = sock_no_shutdown,
+	.setsockopt = sock_no_setsockopt,
+	.getsockopt = sock_no_getsockopt,
+	.sendmsg = sock_no_sendmsg,
+	.recvmsg = sock_no_recvmsg,
+	.mmap = sock_no_mmap,
+};
+
+static int pppopns_create(struct net *net, struct socket *sock)
+{
+	struct sock *sk;
+
+	sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppopns_proto);
+	if (!sk)
+		return -ENOMEM;
+
+	sock_init_data(sock, sk);
+	sock->state = SS_UNCONNECTED;
+	sock->ops = &pppopns_proto_ops;
+	sk->sk_protocol = PX_PROTO_OPNS;
+	sk->sk_state = PPPOX_NONE;
+	return 0;
+}
+
+/******************************************************************************/
+
+static struct pppox_proto pppopns_pppox_proto = {
+	.create = pppopns_create,
+	.owner = THIS_MODULE,
+};
+
+static int __init pppopns_init(void)
+{
+	int error;
+
+	error = proto_register(&pppopns_proto, 0);
+	if (error)
+		return error;
+
+	error = register_pppox_proto(PX_PROTO_OPNS, &pppopns_pppox_proto);
+	if (error)
+		proto_unregister(&pppopns_proto);
+	else
+		skb_queue_head_init(&delivery_queue);
+	return error;
+}
+
+static void __exit pppopns_exit(void)
+{
+	unregister_pppox_proto(PX_PROTO_OPNS);
+	proto_unregister(&pppopns_proto);
+}
+
+module_init(pppopns_init);
+module_exit(pppopns_exit);
+
+MODULE_DESCRIPTION("PPP on PPTP Network Server (PPPoPNS)");
+MODULE_AUTHOR("Chia-chi Yeh <chiachi@android.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 2368395d8ae..ebc95a3771a 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -42,9 +42,7 @@
 
 static struct team_port *team_port_get_rcu(const struct net_device *dev)
 {
-	struct team_port *port = rcu_dereference(dev->rx_handler_data);
-
-	return team_port_exists(dev) ? port : NULL;
+	return rcu_dereference(dev->rx_handler_data);
 }
 
 static struct team_port *team_port_get_rtnl(const struct net_device *dev)
@@ -629,6 +627,7 @@ static int team_change_mode(struct team *team, const char *kind)
 static void team_notify_peers_work(struct work_struct *work)
 {
 	struct team *team;
+	int val;
 
 	team = container_of(work, struct team, notify_peers.dw.work);
 
@@ -636,9 +635,14 @@ static void team_notify_peers_work(struct work_struct *work)
 		schedule_delayed_work(&team->notify_peers.dw, 0);
 		return;
 	}
+	val = atomic_dec_if_positive(&team->notify_peers.count_pending);
+	if (val < 0) {
+		rtnl_unlock();
+		return;
+	}
 	call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, team->dev);
 	rtnl_unlock();
-	if (!atomic_dec_and_test(&team->notify_peers.count_pending))
+	if (val)
 		schedule_delayed_work(&team->notify_peers.dw,
 				      msecs_to_jiffies(team->notify_peers.interval));
 }
@@ -669,6 +673,7 @@ static void team_notify_peers_fini(struct team *team)
 static void team_mcast_rejoin_work(struct work_struct *work)
 {
 	struct team *team;
+	int val;
 
 	team = container_of(work, struct team, mcast_rejoin.dw.work);
 
@@ -676,9 +681,14 @@ static void team_mcast_rejoin_work(struct work_struct *work)
 		schedule_delayed_work(&team->mcast_rejoin.dw, 0);
 		return;
 	}
+	val = atomic_dec_if_positive(&team->mcast_rejoin.count_pending);
+	if (val < 0) {
+		rtnl_unlock();
+		return;
+	}
 	call_netdevice_notifiers(NETDEV_RESEND_IGMP, team->dev);
 	rtnl_unlock();
-	if (!atomic_dec_and_test(&team->mcast_rejoin.count_pending))
+	if (val)
 		schedule_delayed_work(&team->mcast_rejoin.dw,
 				      msecs_to_jiffies(team->mcast_rejoin.interval));
 }
@@ -1723,11 +1733,11 @@ static int team_set_mac_address(struct net_device *dev, void *p)
 	if (dev->type == ARPHRD_ETHER && !is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
-	rcu_read_lock();
-	list_for_each_entry_rcu(port, &team->port_list, list)
+	mutex_lock(&team->lock);
+	list_for_each_entry(port, &team->port_list, list)
 		if (team->ops.port_change_dev_addr)
 			team->ops.port_change_dev_addr(team, port);
-	rcu_read_unlock();
+	mutex_unlock(&team->lock);
 	return 0;
 }
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9dd3746994a..cae87f0502c 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1881,6 +1881,12 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 	unsigned int ifindex;
 	int ret;
 
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+	if (cmd != TUNGETIFF && !capable(CAP_NET_ADMIN)) {
+		return -EPERM;
+	}
+#endif
+
 	if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == 0x89) {
 		if (copy_from_user(&ifr, argp, ifreq_len))
 			return -EFAULT;
diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c
index 5c55f11572b..75d6f26729a 100644
--- a/drivers/net/usb/asix_common.c
+++ b/drivers/net/usb/asix_common.c
@@ -188,6 +188,8 @@ struct sk_buff *asix_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 		memcpy(skb_tail_pointer(skb), &padbytes, sizeof(padbytes));
 		skb_put(skb, sizeof(padbytes));
 	}
+
+	usbnet_set_skb_tx_stats(skb, 1, 0);
 	return skb;
 }
 
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 5ee7a1dbc02..96fc8a5bde8 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -402,7 +402,7 @@ static struct sk_buff *cdc_mbim_process_dgram(struct usbnet *dev, u8 *buf, size_
 
 	/* map MBIM session to VLAN */
 	if (tci)
-		vlan_put_tag(skb, htons(ETH_P_8021Q), tci);
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), tci);
 err:
 	return skb;
 }
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 80a844e0ae0..8067b8fbb0e 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -1172,17 +1172,17 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 
 	/* return skb */
 	ctx->tx_curr_skb = NULL;
-	dev->net->stats.tx_packets += ctx->tx_curr_frame_num;
 
 	/* keep private stats: framing overhead and number of NTBs */
 	ctx->tx_overhead += skb_out->len - ctx->tx_curr_frame_payload;
 	ctx->tx_ntbs++;
 
-	/* usbnet has already counted all the framing overhead.
+	/* usbnet will count all the framing overhead by default.
 	 * Adjust the stats so that the tx_bytes counter show real
 	 * payload data instead.
 	 */
-	dev->net->stats.tx_bytes -= skb_out->len - ctx->tx_curr_frame_payload;
+	usbnet_set_skb_tx_stats(skb_out, n,
+				(long)ctx->tx_curr_frame_payload - skb_out->len);
 
 	return skb_out;
 
diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c
index 3eed708a618..fe48f4c5137 100644
--- a/drivers/net/usb/cx82310_eth.c
+++ b/drivers/net/usb/cx82310_eth.c
@@ -300,9 +300,18 @@ static const struct driver_info	cx82310_info = {
 	.tx_fixup	= cx82310_tx_fixup,
 };
 
+#define USB_DEVICE_CLASS(vend, prod, cl, sc, pr) \
+	.match_flags = USB_DEVICE_ID_MATCH_DEVICE | \
+		       USB_DEVICE_ID_MATCH_DEV_INFO, \
+	.idVendor = (vend), \
+	.idProduct = (prod), \
+	.bDeviceClass = (cl), \
+	.bDeviceSubClass = (sc), \
+	.bDeviceProtocol = (pr)
+
 static const struct usb_device_id products[] = {
 	{
-		USB_DEVICE_AND_INTERFACE_INFO(0x0572, 0xcb01, 0xff, 0, 0),
+		USB_DEVICE_CLASS(0x0572, 0xcb01, 0xff, 0, 0),
 		.driver_info = (unsigned long) &cx82310_info
 	},
 	{ },
diff --git a/drivers/net/usb/plusb.c b/drivers/net/usb/plusb.c
index 3d18bb0eee8..1bfe0fcaccf 100644
--- a/drivers/net/usb/plusb.c
+++ b/drivers/net/usb/plusb.c
@@ -134,6 +134,11 @@ static const struct usb_device_id	products [] = {
 }, {
 	USB_DEVICE(0x050d, 0x258a),     /* Belkin F5U258/F5U279 (PL-25A1) */
 	.driver_info =  (unsigned long) &prolific_info,
+}, {
+	USB_DEVICE(0x3923, 0x7825),     /* National Instruments USB
+					 * Host-to-Host Cable
+					 */
+	.driver_info =  (unsigned long) &prolific_info,
 },
 
 	{ },		// END
diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c
index b94a0fbb8b3..953de13267d 100644
--- a/drivers/net/usb/sr9800.c
+++ b/drivers/net/usb/sr9800.c
@@ -144,6 +144,7 @@ static struct sk_buff *sr_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 		skb_put(skb, sizeof(padbytes));
 	}
 
+	usbnet_set_skb_tx_stats(skb, 1, 0);
 	return skb;
 }
 
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 3a6770a65d7..e7ed2513b1d 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1189,8 +1189,7 @@ static void tx_complete (struct urb *urb)
 	struct usbnet		*dev = entry->dev;
 
 	if (urb->status == 0) {
-		if (!(dev->driver_info->flags & FLAG_MULTI_PACKET))
-			dev->net->stats.tx_packets++;
+		dev->net->stats.tx_packets += entry->packets;
 		dev->net->stats.tx_bytes += entry->length;
 	} else {
 		dev->net->stats.tx_errors++;
@@ -1348,7 +1347,19 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb,
 		} else
 			urb->transfer_flags |= URB_ZERO_PACKET;
 	}
-	entry->length = urb->transfer_buffer_length = length;
+	urb->transfer_buffer_length = length;
+
+	if (info->flags & FLAG_MULTI_PACKET) {
+		/* Driver has set number of packets and a length delta.
+		 * Calculate the complete length and ensure that it's
+		 * positive.
+		 */
+		entry->length += length;
+		if (WARN_ON_ONCE(entry->length <= 0))
+			entry->length = length;
+	} else {
+		usbnet_set_skb_tx_stats(skb, 1, length);
+	}
 
 	spin_lock_irqsave(&dev->txq.lock, flags);
 	retval = usb_autopm_get_interface_async(dev->intf);
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index b0bc8ead47d..484ecce7802 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1452,8 +1452,10 @@ static void virtnet_free_queues(struct virtnet_info *vi)
 {
 	int i;
 
-	for (i = 0; i < vi->max_queue_pairs; i++)
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		napi_hash_del(&vi->rq[i].napi);
 		netif_napi_del(&vi->rq[i].napi);
+	}
 
 	kfree(vi->rq);
 	kfree(vi->sq);
@@ -1939,11 +1941,8 @@ static int virtnet_freeze(struct virtio_device *vdev)
 	cancel_delayed_work_sync(&vi->refill);
 
 	if (netif_running(vi->dev)) {
-		for (i = 0; i < vi->max_queue_pairs; i++) {
+		for (i = 0; i < vi->max_queue_pairs; i++)
 			napi_disable(&vi->rq[i].napi);
-			napi_hash_del(&vi->rq[i].napi);
-			netif_napi_del(&vi->rq[i].napi);
-		}
 	}
 
 	remove_vq_common(vi);
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index be4649a49c5..2826c550876 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1578,10 +1578,6 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 	int err;
 	bool udp_sum = !udp_get_no_check6_tx(vs->sock->sk);
 
-	skb = udp_tunnel_handle_offloads(skb, udp_sum);
-	if (IS_ERR(skb))
-		return -EINVAL;
-
 	skb_scrub_packet(skb, xnet);
 
 	min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len
@@ -1590,16 +1586,21 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 
 	/* Need space for new headers (invalidates iph ptr) */
 	err = skb_cow_head(skb, min_headroom);
-	if (unlikely(err))
-		return err;
+	if (unlikely(err)) {
+		kfree_skb(skb);
+		goto err;
+	}
 
-	if (vlan_tx_tag_present(skb)) {
-		if (WARN_ON(!__vlan_put_tag(skb,
-					    skb->vlan_proto,
-					    vlan_tx_tag_get(skb))))
-			return -ENOMEM;
+	skb = vlan_hwaccel_push_inside(skb);
+	if (WARN_ON(!skb)) {
+		err = -ENOMEM;
+		goto err;
+	}
 
-		skb->vlan_tci = 0;
+	skb = udp_tunnel_handle_offloads(skb, udp_sum);
+	if (IS_ERR(skb)) {
+		err = -EINVAL;
+		goto err;
 	}
 
 	vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
@@ -1611,6 +1612,9 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 	udp_tunnel6_xmit_skb(vs->sock, dst, skb, dev, saddr, daddr, prio,
 			     ttl, src_port, dst_port);
 	return 0;
+err:
+	dst_release(dst);
+	return err;
 }
 #endif
 
@@ -1624,27 +1628,24 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 	int err;
 	bool udp_sum = !vs->sock->sk->sk_no_check_tx;
 
-	skb = udp_tunnel_handle_offloads(skb, udp_sum);
-	if (IS_ERR(skb))
-		return -EINVAL;
-
 	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
 			+ VXLAN_HLEN + sizeof(struct iphdr)
 			+ (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
 
 	/* Need space for new headers (invalidates iph ptr) */
 	err = skb_cow_head(skb, min_headroom);
-	if (unlikely(err))
+	if (unlikely(err)) {
+		kfree_skb(skb);
 		return err;
+	}
 
-	if (vlan_tx_tag_present(skb)) {
-		if (WARN_ON(!__vlan_put_tag(skb,
-					    skb->vlan_proto,
-					    vlan_tx_tag_get(skb))))
-			return -ENOMEM;
+	skb = vlan_hwaccel_push_inside(skb);
+	if (WARN_ON(!skb))
+		return -ENOMEM;
 
-		skb->vlan_tci = 0;
-	}
+	skb = udp_tunnel_handle_offloads(skb, udp_sum);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
 
 	vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
 	vxh->vx_flags = htonl(VXLAN_FLAGS);
@@ -1786,9 +1787,12 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 				     tos, ttl, df, src_port, dst_port,
 				     htonl(vni << 8),
 				     !net_eq(vxlan->net, dev_net(vxlan->dev)));
-
-		if (err < 0)
+		if (err < 0) {
+			/* skb is already freed. */
+			skb = NULL;
 			goto rt_tx_error;
+		}
+
 		iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
@@ -1995,9 +1999,8 @@ static int vxlan_init(struct net_device *dev)
 	spin_lock(&vn->sock_lock);
 	vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET,
 			     vxlan->dst_port);
-	if (vs) {
+	if (vs && atomic_add_unless(&vs->refcnt, 1, 0)) {
 		/* If we have a socket with same port already, reuse it */
-		atomic_inc(&vs->refcnt);
 		vxlan_vs_add_dev(vs, vxlan);
 	} else {
 		/* otherwise make new socket outside of RTNL */
@@ -2396,12 +2399,9 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 
 	spin_lock(&vn->sock_lock);
 	vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port);
-	if (vs) {
-		if (vs->rcv == rcv)
-			atomic_inc(&vs->refcnt);
-		else
+	if (vs && ((vs->rcv != rcv) ||
+		   !atomic_add_unless(&vs->refcnt, 1, 0)))
 			vs = ERR_PTR(-EBUSY);
-	}
 	spin_unlock(&vn->sock_lock);
 
 	if (!vs)
diff --git a/drivers/net/wireless/Kconfig b/drivers/net/wireless/Kconfig
index 16604bdf519..710733f034f 100644
--- a/drivers/net/wireless/Kconfig
+++ b/drivers/net/wireless/Kconfig
@@ -265,6 +265,11 @@ config MWL8K
 	  To compile this driver as a module, choose M here: the module
 	  will be called mwl8k.  If unsure, say N.
 
+config WIFI_CONTROL_FUNC
+	bool "Enable WiFi control function abstraction"
+	help
+	  Enables Power/Reset/Carddetect function abstraction
+
 source "drivers/net/wireless/ath/Kconfig"
 source "drivers/net/wireless/b43/Kconfig"
 source "drivers/net/wireless/b43legacy/Kconfig"
diff --git a/drivers/net/wireless/ath/ath5k/qcu.c b/drivers/net/wireless/ath/ath5k/qcu.c
index 0583c69d26d..ddaad712c59 100644
--- a/drivers/net/wireless/ath/ath5k/qcu.c
+++ b/drivers/net/wireless/ath/ath5k/qcu.c
@@ -225,13 +225,7 @@ ath5k_hw_setup_tx_queue(struct ath5k_hw *ah, enum ath5k_tx_queue queue_type,
 	} else {
 		switch (queue_type) {
 		case AR5K_TX_QUEUE_DATA:
-			for (queue = AR5K_TX_QUEUE_ID_DATA_MIN;
-				ah->ah_txq[queue].tqi_type !=
-				AR5K_TX_QUEUE_INACTIVE; queue++) {
-
-				if (queue > AR5K_TX_QUEUE_ID_DATA_MAX)
-					return -EINVAL;
-			}
+			queue = queue_info->tqi_subtype;
 			break;
 		case AR5K_TX_QUEUE_UAPSD:
 			queue = AR5K_TX_QUEUE_ID_UAPSD;
diff --git a/drivers/net/wireless/ath/ath5k/reset.c b/drivers/net/wireless/ath/ath5k/reset.c
index a3399c4f13a..b9b651ea985 100644
--- a/drivers/net/wireless/ath/ath5k/reset.c
+++ b/drivers/net/wireless/ath/ath5k/reset.c
@@ -478,7 +478,7 @@ ath5k_hw_wisoc_reset(struct ath5k_hw *ah, u32 flags)
 	regval = ioread32(reg);
 	iowrite32(regval | val, reg);
 	regval = ioread32(reg);
-	usleep_range(100, 150);
+	udelay(100);	/* NB: should be atomic */
 
 	/* Bring BB/MAC out of reset */
 	iowrite32(regval & ~val, reg);
diff --git a/drivers/net/wireless/ath/ath9k/beacon.c b/drivers/net/wireless/ath/ath9k/beacon.c
index ecb783beeec..9ee8ed0ffb9 100644
--- a/drivers/net/wireless/ath/ath9k/beacon.c
+++ b/drivers/net/wireless/ath/ath9k/beacon.c
@@ -218,12 +218,15 @@ void ath9k_beacon_remove_slot(struct ath_softc *sc, struct ieee80211_vif *vif)
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
 	struct ath_vif *avp = (void *)vif->drv_priv;
 	struct ath_buf *bf = avp->av_bcbuf;
+	struct ath_beacon_config *cur_conf = &sc->cur_chan->beacon;
 
 	ath_dbg(common, CONFIG, "Removing interface at beacon slot: %d\n",
 		avp->av_bslot);
 
 	tasklet_disable(&sc->bcon_tasklet);
 
+	cur_conf->enable_beacon &= ~BIT(avp->av_bslot);
+
 	if (bf && bf->bf_mpdu) {
 		struct sk_buff *skb = bf->bf_mpdu;
 		dma_unmap_single(sc->dev, bf->bf_buf_addr,
@@ -520,8 +523,7 @@ static bool ath9k_allow_beacon_config(struct ath_softc *sc,
 	}
 
 	if (sc->sc_ah->opmode == NL80211_IFTYPE_AP) {
-		if ((vif->type != NL80211_IFTYPE_AP) ||
-		    (sc->nbcnvifs > 1)) {
+		if (vif->type != NL80211_IFTYPE_AP) {
 			ath_dbg(common, CONFIG,
 				"An AP interface is already present !\n");
 			return false;
@@ -615,12 +617,14 @@ void ath9k_beacon_config(struct ath_softc *sc, struct ieee80211_vif *vif,
 	 * enabling/disabling SWBA.
 	 */
 	if (changed & BSS_CHANGED_BEACON_ENABLED) {
-		if (!bss_conf->enable_beacon &&
-		    (sc->nbcnvifs <= 1)) {
-			cur_conf->enable_beacon = false;
-		} else if (bss_conf->enable_beacon) {
-			cur_conf->enable_beacon = true;
-			ath9k_cache_beacon_config(sc, ctx, bss_conf);
+		bool enabled = cur_conf->enable_beacon;
+
+		if (!bss_conf->enable_beacon) {
+			cur_conf->enable_beacon &= ~BIT(avp->av_bslot);
+		} else {
+			cur_conf->enable_beacon |= BIT(avp->av_bslot);
+			if (!enabled)
+				ath9k_cache_beacon_config(sc, ctx, bss_conf);
 		}
 	}
 
diff --git a/drivers/net/wireless/ath/ath9k/common.h b/drivers/net/wireless/ath/ath9k/common.h
index ffc454b1863..81899e7e2a2 100644
--- a/drivers/net/wireless/ath/ath9k/common.h
+++ b/drivers/net/wireless/ath/ath9k/common.h
@@ -53,7 +53,7 @@ struct ath_beacon_config {
 	u16 dtim_period;
 	u16 bmiss_timeout;
 	u8 dtim_count;
-	bool enable_beacon;
+	u8 enable_beacon;
 	bool ibss_creator;
 	u32 nexttbtt;
 	u32 intval;
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index 975074fc11b..e8e8dd28bad 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -217,8 +217,8 @@
 #define AH_WOW_BEACON_MISS		BIT(3)
 
 enum ath_hw_txq_subtype {
-	ATH_TXQ_AC_BE = 0,
-	ATH_TXQ_AC_BK = 1,
+	ATH_TXQ_AC_BK = 0,
+	ATH_TXQ_AC_BE = 1,
 	ATH_TXQ_AC_VI = 2,
 	ATH_TXQ_AC_VO = 3,
 };
diff --git a/drivers/net/wireless/ath/ath9k/mac.c b/drivers/net/wireless/ath/ath9k/mac.c
index 275205ab5f1..3e58bfa0c1f 100644
--- a/drivers/net/wireless/ath/ath9k/mac.c
+++ b/drivers/net/wireless/ath/ath9k/mac.c
@@ -311,14 +311,7 @@ int ath9k_hw_setuptxqueue(struct ath_hw *ah, enum ath9k_tx_queue type,
 		q = ATH9K_NUM_TX_QUEUES - 3;
 		break;
 	case ATH9K_TX_QUEUE_DATA:
-		for (q = 0; q < ATH9K_NUM_TX_QUEUES; q++)
-			if (ah->txq[q].tqi_type ==
-			    ATH9K_TX_QUEUE_INACTIVE)
-				break;
-		if (q == ATH9K_NUM_TX_QUEUES) {
-			ath_err(common, "No available TX queue\n");
-			return -1;
-		}
+		q = qinfo->tqi_subtype;
 		break;
 	default:
 		ath_err(common, "Invalid TX queue type: %u\n", type);
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 4f18a6be0c7..2cf58993da8 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -212,11 +212,13 @@ static bool ath_prepare_reset(struct ath_softc *sc)
 	ath_stop_ani(sc);
 	ath9k_hw_disable_interrupts(ah);
 
-	if (!ath_drain_all_txq(sc))
-		ret = false;
-
-	if (!ath_stoprecv(sc))
-		ret = false;
+	if (AR_SREV_9300_20_OR_LATER(ah)) {
+		ret &= ath_stoprecv(sc);
+		ret &= ath_drain_all_txq(sc);
+	} else {
+		ret &= ath_drain_all_txq(sc);
+		ret &= ath_stoprecv(sc);
+	}
 
 	return ret;
 }
diff --git a/drivers/net/wireless/b43/main.c b/drivers/net/wireless/b43/main.c
index 5d4173ee55b..614d62ebc0b 100644
--- a/drivers/net/wireless/b43/main.c
+++ b/drivers/net/wireless/b43/main.c
@@ -5314,6 +5314,10 @@ static void b43_supported_bands(struct b43_wldev *dev, bool *have_2ghz_phy,
 		*have_5ghz_phy = true;
 		return;
 	case 0x4321: /* BCM4306 */
+		/* There are 14e4:4321 PCI devs with 2.4 GHz BCM4321 (N-PHY) */
+		if (dev->phy.type != B43_PHYTYPE_G)
+			break;
+		/* fall through */
 	case 0x4313: /* BCM4311 */
 	case 0x431a: /* BCM4318 */
 	case 0x432a: /* BCM4321 */
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c b/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c
index 11cc051f97c..0c9671f2f01 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/msgbuf.c
@@ -1081,8 +1081,17 @@ brcmf_msgbuf_rx_skb(struct brcmf_msgbuf *msgbuf, struct sk_buff *skb,
 {
 	struct brcmf_if *ifp;
 
+	/* The ifidx is the idx to map to matching netdev/ifp. When receiving
+	 * events this is easy because it contains the bssidx which maps
+	 * 1-on-1 to the netdev/ifp. But for data frames the ifidx is rcvd.
+	 * bssidx 1 is used for p2p0 and no data can be received or
+	 * transmitted on it. Therefor bssidx is ifidx + 1 if ifidx > 0
+	 */
+	if (ifidx)
+		(ifidx)++;
 	ifp = msgbuf->drvr->iflist[ifidx];
 	if (!ifp || !ifp->ndev) {
+		brcmf_err("Received pkt for invalid ifidx %d\n", ifidx);
 		brcmu_pkt_buf_free_skb(skb);
 		return;
 	}
@@ -1355,6 +1364,7 @@ int brcmf_proto_msgbuf_attach(struct brcmf_pub *drvr)
 	}
 	INIT_WORK(&msgbuf->txflow_work, brcmf_msgbuf_txflow_worker);
 	count = BITS_TO_LONGS(if_msgbuf->nrof_flowrings);
+	count = count * sizeof(unsigned long);
 	msgbuf->flow_map = kzalloc(count, GFP_KERNEL);
 	if (!msgbuf->flow_map)
 		goto fail;
diff --git a/drivers/net/wireless/iwlwifi/dvm/commands.h b/drivers/net/wireless/iwlwifi/dvm/commands.h
index 751ae1d10b7..7a34e4d158d 100644
--- a/drivers/net/wireless/iwlwifi/dvm/commands.h
+++ b/drivers/net/wireless/iwlwifi/dvm/commands.h
@@ -966,21 +966,21 @@ struct iwl_rem_sta_cmd {
 
 
 /* WiFi queues mask */
-#define IWL_SCD_BK_MSK			cpu_to_le32(BIT(0))
-#define IWL_SCD_BE_MSK			cpu_to_le32(BIT(1))
-#define IWL_SCD_VI_MSK			cpu_to_le32(BIT(2))
-#define IWL_SCD_VO_MSK			cpu_to_le32(BIT(3))
-#define IWL_SCD_MGMT_MSK		cpu_to_le32(BIT(3))
+#define IWL_SCD_BK_MSK			BIT(0)
+#define IWL_SCD_BE_MSK			BIT(1)
+#define IWL_SCD_VI_MSK			BIT(2)
+#define IWL_SCD_VO_MSK			BIT(3)
+#define IWL_SCD_MGMT_MSK		BIT(3)
 
 /* PAN queues mask */
-#define IWL_PAN_SCD_BK_MSK		cpu_to_le32(BIT(4))
-#define IWL_PAN_SCD_BE_MSK		cpu_to_le32(BIT(5))
-#define IWL_PAN_SCD_VI_MSK		cpu_to_le32(BIT(6))
-#define IWL_PAN_SCD_VO_MSK		cpu_to_le32(BIT(7))
-#define IWL_PAN_SCD_MGMT_MSK		cpu_to_le32(BIT(7))
-#define IWL_PAN_SCD_MULTICAST_MSK	cpu_to_le32(BIT(8))
+#define IWL_PAN_SCD_BK_MSK		BIT(4)
+#define IWL_PAN_SCD_BE_MSK		BIT(5)
+#define IWL_PAN_SCD_VI_MSK		BIT(6)
+#define IWL_PAN_SCD_VO_MSK		BIT(7)
+#define IWL_PAN_SCD_MGMT_MSK		BIT(7)
+#define IWL_PAN_SCD_MULTICAST_MSK	BIT(8)
 
-#define IWL_AGG_TX_QUEUE_MSK		cpu_to_le32(0xffc00)
+#define IWL_AGG_TX_QUEUE_MSK		0xffc00
 
 #define IWL_DROP_ALL			BIT(1)
 
@@ -1005,12 +1005,17 @@ struct iwl_rem_sta_cmd {
  *	1: Dump multiple MSDU according to PS, INVALID STA, TTL, TID disable.
  *	2: Dump all FIFO
  */
-struct iwl_txfifo_flush_cmd {
+struct iwl_txfifo_flush_cmd_v3 {
 	__le32 queue_control;
 	__le16 flush_control;
 	__le16 reserved;
 } __packed;
 
+struct iwl_txfifo_flush_cmd_v2 {
+	__le16 queue_control;
+	__le16 flush_control;
+} __packed;
+
 /*
  * REPLY_WEP_KEY = 0x20
  */
diff --git a/drivers/net/wireless/iwlwifi/dvm/dev.h b/drivers/net/wireless/iwlwifi/dvm/dev.h
index a6f22c32a27..3811878ab9c 100644
--- a/drivers/net/wireless/iwlwifi/dvm/dev.h
+++ b/drivers/net/wireless/iwlwifi/dvm/dev.h
@@ -708,7 +708,6 @@ struct iwl_priv {
 	unsigned long reload_jiffies;
 	int reload_count;
 	bool ucode_loaded;
-	bool init_ucode_run;		/* Don't run init uCode again */
 
 	u8 plcp_delta_threshold;
 
diff --git a/drivers/net/wireless/iwlwifi/dvm/lib.c b/drivers/net/wireless/iwlwifi/dvm/lib.c
index 2191621d69c..cfe1293692f 100644
--- a/drivers/net/wireless/iwlwifi/dvm/lib.c
+++ b/drivers/net/wireless/iwlwifi/dvm/lib.c
@@ -137,37 +137,38 @@ int iwlagn_manage_ibss_station(struct iwl_priv *priv,
  */
 int iwlagn_txfifo_flush(struct iwl_priv *priv, u32 scd_q_msk)
 {
-	struct iwl_txfifo_flush_cmd flush_cmd;
-	struct iwl_host_cmd cmd = {
-		.id = REPLY_TXFIFO_FLUSH,
-		.len = { sizeof(struct iwl_txfifo_flush_cmd), },
-		.data = { &flush_cmd, },
+	struct iwl_txfifo_flush_cmd_v3 flush_cmd_v3 = {
+		.flush_control = cpu_to_le16(IWL_DROP_ALL),
+	};
+	struct iwl_txfifo_flush_cmd_v2 flush_cmd_v2 = {
+		.flush_control = cpu_to_le16(IWL_DROP_ALL),
 	};
 
-	memset(&flush_cmd, 0, sizeof(flush_cmd));
+	u32 queue_control = IWL_SCD_VO_MSK | IWL_SCD_VI_MSK |
+			    IWL_SCD_BE_MSK | IWL_SCD_BK_MSK | IWL_SCD_MGMT_MSK;
 
-	flush_cmd.queue_control = IWL_SCD_VO_MSK | IWL_SCD_VI_MSK |
-				  IWL_SCD_BE_MSK | IWL_SCD_BK_MSK |
-				  IWL_SCD_MGMT_MSK;
 	if ((priv->valid_contexts != BIT(IWL_RXON_CTX_BSS)))
-		flush_cmd.queue_control |= IWL_PAN_SCD_VO_MSK |
-					   IWL_PAN_SCD_VI_MSK |
-					   IWL_PAN_SCD_BE_MSK |
-					   IWL_PAN_SCD_BK_MSK |
-					   IWL_PAN_SCD_MGMT_MSK |
-					   IWL_PAN_SCD_MULTICAST_MSK;
+		queue_control |= IWL_PAN_SCD_VO_MSK | IWL_PAN_SCD_VI_MSK |
+				 IWL_PAN_SCD_BE_MSK | IWL_PAN_SCD_BK_MSK |
+				 IWL_PAN_SCD_MGMT_MSK |
+				 IWL_PAN_SCD_MULTICAST_MSK;
 
 	if (priv->nvm_data->sku_cap_11n_enable)
-		flush_cmd.queue_control |= IWL_AGG_TX_QUEUE_MSK;
+		queue_control |= IWL_AGG_TX_QUEUE_MSK;
 
 	if (scd_q_msk)
-		flush_cmd.queue_control = cpu_to_le32(scd_q_msk);
-
-	IWL_DEBUG_INFO(priv, "queue control: 0x%x\n",
-		       flush_cmd.queue_control);
-	flush_cmd.flush_control = cpu_to_le16(IWL_DROP_ALL);
-
-	return iwl_dvm_send_cmd(priv, &cmd);
+		queue_control = scd_q_msk;
+
+	IWL_DEBUG_INFO(priv, "queue control: 0x%x\n", queue_control);
+	flush_cmd_v3.queue_control = cpu_to_le32(queue_control);
+	flush_cmd_v2.queue_control = cpu_to_le16((u16)queue_control);
+
+	if (IWL_UCODE_API(priv->fw->ucode_ver) > 2)
+		return iwl_dvm_send_cmd_pdu(priv, REPLY_TXFIFO_FLUSH, 0,
+					    sizeof(flush_cmd_v3),
+					    &flush_cmd_v3);
+	return iwl_dvm_send_cmd_pdu(priv, REPLY_TXFIFO_FLUSH, 0,
+				    sizeof(flush_cmd_v2), &flush_cmd_v2);
 }
 
 void iwlagn_dev_txfifo_flush(struct iwl_priv *priv)
diff --git a/drivers/net/wireless/iwlwifi/dvm/ucode.c b/drivers/net/wireless/iwlwifi/dvm/ucode.c
index d5cee153059..80b8094deed 100644
--- a/drivers/net/wireless/iwlwifi/dvm/ucode.c
+++ b/drivers/net/wireless/iwlwifi/dvm/ucode.c
@@ -418,9 +418,6 @@ int iwl_run_init_ucode(struct iwl_priv *priv)
 	if (!priv->fw->img[IWL_UCODE_INIT].sec[0].len)
 		return 0;
 
-	if (priv->init_ucode_run)
-		return 0;
-
 	iwl_init_notification_wait(&priv->notif_wait, &calib_wait,
 				   calib_complete, ARRAY_SIZE(calib_complete),
 				   iwlagn_wait_calib, priv);
@@ -440,8 +437,6 @@ int iwl_run_init_ucode(struct iwl_priv *priv)
 	 */
 	ret = iwl_wait_notification(&priv->notif_wait, &calib_wait,
 					UCODE_CALIB_TIMEOUT);
-	if (!ret)
-		priv->init_ucode_run = true;
 
 	goto out;
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
index 1354c68f646..be052773417 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
@@ -672,6 +672,7 @@ struct iwl_scan_channel_opt {
  * @IWL_MVM_LMAC_SCAN_FLAG_FRAGMENTED: all passive scans will be fragmented
  * @IWL_MVM_LMAC_SCAN_FLAGS_RRM_ENABLED: insert WFA vendor-specific TPC report
  *	and DS parameter set IEs into probe requests.
+ * @IWL_MVM_LMAC_SCAN_FLAG_MATCH: Send match found notification on matches
  */
 enum iwl_mvm_lmac_scan_flags {
 	IWL_MVM_LMAC_SCAN_FLAG_PASS_ALL		= BIT(0),
@@ -681,6 +682,7 @@ enum iwl_mvm_lmac_scan_flags {
 	IWL_MVM_LMAC_SCAN_FLAG_MULTIPLE_SSIDS	= BIT(4),
 	IWL_MVM_LMAC_SCAN_FLAG_FRAGMENTED	= BIT(5),
 	IWL_MVM_LMAC_SCAN_FLAGS_RRM_ENABLED	= BIT(6),
+	IWL_MVM_LMAC_SCAN_FLAG_MATCH		= BIT(9),
 };
 
 enum iwl_scan_priority {
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api.h b/drivers/net/wireless/iwlwifi/mvm/fw-api.h
index c62575d86bc..5bd902c976e 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api.h
@@ -1589,7 +1589,7 @@ enum iwl_sf_scenario {
 #define SF_NUM_TIMEOUT_TYPES 2		/* Aging timer and Idle timer */
 
 /* smart FIFO default values */
-#define SF_W_MARK_SISO 4096
+#define SF_W_MARK_SISO 6144
 #define SF_W_MARK_MIMO2 8192
 #define SF_W_MARK_MIMO3 6144
 #define SF_W_MARK_LEGACY 4096
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index b6d2683da3a..f71c22f8bee 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -668,9 +668,6 @@ static void iwl_mvm_cleanup_iterator(void *data, u8 *mac,
 	mvmvif->uploaded = false;
 	mvmvif->ap_sta_id = IWL_MVM_STATION_COUNT;
 
-	/* does this make sense at all? */
-	mvmvif->color++;
-
 	spin_lock_bh(&mvm->time_event_lock);
 	iwl_mvm_te_clear_data(mvm, &mvmvif->time_event_data);
 	spin_unlock_bh(&mvm->time_event_lock);
@@ -1014,7 +1011,7 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw,
 
 	ret = iwl_mvm_power_update_mac(mvm);
 	if (ret)
-		goto out_release;
+		goto out_remove_mac;
 
 	/* beacon filtering */
 	ret = iwl_mvm_disable_beacon_filter(mvm, vif, 0);
diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c
index 7554f705383..886b6471044 100644
--- a/drivers/net/wireless/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/iwlwifi/mvm/scan.c
@@ -1334,6 +1334,7 @@ int iwl_mvm_unified_sched_scan_lmac(struct iwl_mvm *mvm,
 		IWL_DEBUG_SCAN(mvm,
 			       "Sending scheduled scan with filtering, n_match_sets %d\n",
 			       req->n_match_sets);
+		flags |= IWL_MVM_LMAC_SCAN_FLAG_MATCH;
 	} else {
 		IWL_DEBUG_SCAN(mvm,
 			       "Sending Scheduled scan without filtering\n");
diff --git a/drivers/net/wireless/iwlwifi/mvm/tx.c b/drivers/net/wireless/iwlwifi/mvm/tx.c
index c6a517c771d..5928c9db49c 100644
--- a/drivers/net/wireless/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/mvm/tx.c
@@ -902,6 +902,11 @@ int iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb,
 	sta_id = ba_notif->sta_id;
 	tid = ba_notif->tid;
 
+	if (WARN_ONCE(sta_id >= IWL_MVM_STATION_COUNT ||
+		      tid >= IWL_MAX_TID_COUNT,
+		      "sta_id %d tid %d", sta_id, tid))
+		return 0;
+
 	rcu_read_lock();
 
 	sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_id]);
diff --git a/drivers/net/wireless/iwlwifi/mvm/utils.c b/drivers/net/wireless/iwlwifi/mvm/utils.c
index 8021f6eec27..41ae1643530 100644
--- a/drivers/net/wireless/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/iwlwifi/mvm/utils.c
@@ -665,7 +665,7 @@ bool iwl_mvm_rx_diversity_allowed(struct iwl_mvm *mvm)
 	if (num_of_ant(mvm->fw->valid_rx_ant) == 1)
 		return false;
 
-	if (!mvm->cfg->rx_with_siso_diversity)
+	if (mvm->cfg->rx_with_siso_diversity)
 		return false;
 
 	ieee80211_iterate_active_interfaces_atomic(
diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c
index 6ced8549eb3..05cba8c05d3 100644
--- a/drivers/net/wireless/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/iwlwifi/pcie/drv.c
@@ -367,7 +367,11 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 
 /* 3165 Series */
 	{IWL_PCI_DEVICE(0x3165, 0x4010, iwl3165_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x3165, 0x4012, iwl3165_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x3165, 0x4110, iwl3165_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x3165, 0x4210, iwl3165_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x3165, 0x4410, iwl3165_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x3165, 0x4510, iwl3165_2ac_cfg)},
 
 /* 7265 Series */
 	{IWL_PCI_DEVICE(0x095A, 0x5010, iwl7265_2ac_cfg)},
diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c
index dd2f3f8baa9..c943baa4e9f 100644
--- a/drivers/net/wireless/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/iwlwifi/pcie/trans.c
@@ -5,8 +5,8 @@
  *
  * GPL LICENSE SUMMARY
  *
- * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2007 - 2015 Intel Corporation. All rights reserved.
+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,8 +31,8 @@
  *
  * BSD LICENSE
  *
- * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2005 - 2015 Intel Corporation. All rights reserved.
+ * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -98,7 +98,7 @@ static void iwl_pcie_free_fw_monitor(struct iwl_trans *trans)
 static void iwl_pcie_alloc_fw_monitor(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct page *page;
+	struct page *page = NULL;
 	dma_addr_t phys;
 	u32 size;
 	u8 power;
@@ -125,6 +125,7 @@ static void iwl_pcie_alloc_fw_monitor(struct iwl_trans *trans)
 				    DMA_FROM_DEVICE);
 		if (dma_mapping_error(trans->dev, phys)) {
 			__free_pages(page, order);
+			page = NULL;
 			continue;
 		}
 		IWL_INFO(trans,
diff --git a/drivers/net/wireless/iwlwifi/pcie/tx.c b/drivers/net/wireless/iwlwifi/pcie/tx.c
index eb8e2984c5e..62ea2b55083 100644
--- a/drivers/net/wireless/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/iwlwifi/pcie/tx.c
@@ -722,7 +722,12 @@ void iwl_trans_pcie_tx_reset(struct iwl_trans *trans)
 	iwl_write_direct32(trans, FH_KW_MEM_ADDR_REG,
 			   trans_pcie->kw.dma >> 4);
 
-	iwl_pcie_tx_start(trans, trans_pcie->scd_base_addr);
+	/*
+	 * Send 0 as the scd_base_addr since the device may have be reset
+	 * while we were in WoWLAN in which case SCD_SRAM_BASE_ADDR will
+	 * contain garbage.
+	 */
+	iwl_pcie_tx_start(trans, 0);
 }
 
 /*
diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c
index 8444313eabe..8694dddcce9 100644
--- a/drivers/net/wireless/rt2x00/rt2800usb.c
+++ b/drivers/net/wireless/rt2x00/rt2800usb.c
@@ -1040,6 +1040,7 @@ static struct usb_device_id rt2800usb_device_table[] = {
 	{ USB_DEVICE(0x07d1, 0x3c17) },
 	{ USB_DEVICE(0x2001, 0x3317) },
 	{ USB_DEVICE(0x2001, 0x3c1b) },
+	{ USB_DEVICE(0x2001, 0x3c25) },
 	/* Draytek */
 	{ USB_DEVICE(0x07fa, 0x7712) },
 	/* DVICO */
diff --git a/drivers/net/wireless/rtlwifi/base.c b/drivers/net/wireless/rtlwifi/base.c
index 40b6d1d006d..af248696578 100644
--- a/drivers/net/wireless/rtlwifi/base.c
+++ b/drivers/net/wireless/rtlwifi/base.c
@@ -1314,8 +1314,11 @@ u8 rtl_is_special_data(struct ieee80211_hw *hw, struct sk_buff *skb, u8 is_tx)
 		}
 
 		return true;
-	} else if (0x86DD == ether_type) {
-		return true;
+	} else if (ETH_P_IPV6 == ether_type) {
+		/* TODO: Handle any IPv6 cases that need special handling.
+		 * For now, always return false
+		 */
+		goto end;
 	}
 
 end:
diff --git a/drivers/net/wireless/rtlwifi/pci.c b/drivers/net/wireless/rtlwifi/pci.c
index 846a2e6e34d..8c45cf44ce2 100644
--- a/drivers/net/wireless/rtlwifi/pci.c
+++ b/drivers/net/wireless/rtlwifi/pci.c
@@ -578,6 +578,13 @@ static void _rtl_pci_tx_isr(struct ieee80211_hw *hw, int prio)
 		else
 			entry = (u8 *)(&ring->desc[ring->idx]);
 
+		if (rtlpriv->cfg->ops->get_available_desc &&
+		    rtlpriv->cfg->ops->get_available_desc(hw, prio) <= 1) {
+			RT_TRACE(rtlpriv, (COMP_INTR | COMP_SEND), DBG_DMESG,
+				 "no available desc!\n");
+			return;
+		}
+
 		if (!rtlpriv->cfg->ops->is_tx_desc_closed(hw, prio, ring->idx))
 			return;
 		ring->idx = (ring->idx + 1) % ring->entries;
@@ -641,10 +648,9 @@ static void _rtl_pci_tx_isr(struct ieee80211_hw *hw, int prio)
 
 		ieee80211_tx_status_irqsafe(hw, skb);
 
-		if ((ring->entries - skb_queue_len(&ring->queue))
-				== 2) {
+		if ((ring->entries - skb_queue_len(&ring->queue)) <= 4) {
 
-			RT_TRACE(rtlpriv, COMP_ERR, DBG_LOUD,
+			RT_TRACE(rtlpriv, COMP_ERR, DBG_DMESG,
 				 "more desc left, wake skb_queue@%d, ring->idx = %d, skb_queue_len = 0x%x\n",
 				 prio, ring->idx,
 				 skb_queue_len(&ring->queue));
@@ -666,7 +672,8 @@ tx_status_ok:
 }
 
 static int _rtl_pci_init_one_rxdesc(struct ieee80211_hw *hw,
-				    u8 *entry, int rxring_idx, int desc_idx)
+				    struct sk_buff *new_skb, u8 *entry,
+				    int rxring_idx, int desc_idx)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
@@ -674,11 +681,15 @@ static int _rtl_pci_init_one_rxdesc(struct ieee80211_hw *hw,
 	u8 tmp_one = 1;
 	struct sk_buff *skb;
 
+	if (likely(new_skb)) {
+		skb = new_skb;
+		goto remap;
+	}
 	skb = dev_alloc_skb(rtlpci->rxbuffersize);
 	if (!skb)
 		return 0;
-	rtlpci->rx_ring[rxring_idx].rx_buf[desc_idx] = skb;
 
+remap:
 	/* just set skb->cb to mapping addr for pci_unmap_single use */
 	*((dma_addr_t *)skb->cb) =
 		pci_map_single(rtlpci->pdev, skb_tail_pointer(skb),
@@ -686,6 +697,7 @@ static int _rtl_pci_init_one_rxdesc(struct ieee80211_hw *hw,
 	bufferaddress = *((dma_addr_t *)skb->cb);
 	if (pci_dma_mapping_error(rtlpci->pdev, bufferaddress))
 		return 0;
+	rtlpci->rx_ring[rxring_idx].rx_buf[desc_idx] = skb;
 	if (rtlpriv->use_new_trx_flow) {
 		rtlpriv->cfg->ops->set_desc(hw, (u8 *)entry, false,
 					    HW_DESC_RX_PREPARE,
@@ -781,12 +793,13 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 		/*rx pkt */
 		struct sk_buff *skb = rtlpci->rx_ring[rxring_idx].rx_buf[
 				      rtlpci->rx_ring[rxring_idx].idx];
+		struct sk_buff *new_skb;
 
 		if (rtlpriv->use_new_trx_flow) {
 			rx_remained_cnt =
 				rtlpriv->cfg->ops->rx_desc_buff_remained_cnt(hw,
 								      hw_queue);
-			if (rx_remained_cnt < 1)
+			if (rx_remained_cnt == 0)
 				return;
 
 		} else {	/* rx descriptor */
@@ -807,6 +820,10 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 		pci_unmap_single(rtlpci->pdev, *((dma_addr_t *)skb->cb),
 				 rtlpci->rxbuffersize, PCI_DMA_FROMDEVICE);
 
+		/* get a new skb - if fail, old one will be reused */
+		new_skb = dev_alloc_skb(rtlpci->rxbuffersize);
+		if (unlikely(!new_skb))
+			goto no_new;
 		if (rtlpriv->use_new_trx_flow) {
 			buffer_desc =
 			  &rtlpci->rx_ring[rxring_idx].buffer_desc
@@ -834,18 +851,18 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 			else
 				skb_reserve(skb, stats.rx_drvinfo_size +
 					    stats.rx_bufshift);
-
 		} else {
 			RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
 				 "skb->end - skb->tail = %d, len is %d\n",
 				 skb->end - skb->tail, len);
-			break;
+			dev_kfree_skb_any(skb);
+			goto new_trx_end;
 		}
 		/* handle command packet here */
 		if (rtlpriv->cfg->ops->rx_command_packet &&
 		    rtlpriv->cfg->ops->rx_command_packet(hw, stats, skb)) {
 				dev_kfree_skb_any(skb);
-				goto end;
+				goto new_trx_end;
 		}
 
 		/*
@@ -895,6 +912,7 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 		} else {
 			dev_kfree_skb_any(skb);
 		}
+new_trx_end:
 		if (rtlpriv->use_new_trx_flow) {
 			rtlpci->rx_ring[hw_queue].next_rx_rp += 1;
 			rtlpci->rx_ring[hw_queue].next_rx_rp %=
@@ -910,15 +928,16 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 			rtlpriv->enter_ps = false;
 			schedule_work(&rtlpriv->works.lps_change_work);
 		}
-end:
+		skb = new_skb;
+no_new:
 		if (rtlpriv->use_new_trx_flow) {
-			_rtl_pci_init_one_rxdesc(hw, (u8 *)buffer_desc,
+			_rtl_pci_init_one_rxdesc(hw, skb, (u8 *)buffer_desc,
 						 rxring_idx,
-					       rtlpci->rx_ring[rxring_idx].idx);
+						 rtlpci->rx_ring[rxring_idx].idx);
 		} else {
-			_rtl_pci_init_one_rxdesc(hw, (u8 *)pdesc, rxring_idx,
+			_rtl_pci_init_one_rxdesc(hw, skb, (u8 *)pdesc,
+						 rxring_idx,
 						 rtlpci->rx_ring[rxring_idx].idx);
-
 			if (rtlpci->rx_ring[rxring_idx].idx ==
 			    rtlpci->rxringcount - 1)
 				rtlpriv->cfg->ops->set_desc(hw, (u8 *)pdesc,
@@ -1105,12 +1124,22 @@ static void _rtl_pci_prepare_bcn_tasklet(struct ieee80211_hw *hw)
 	/*This is for new trx flow*/
 	struct rtl_tx_buffer_desc *pbuffer_desc = NULL;
 	u8 temp_one = 1;
+	u8 *entry;
 
 	memset(&tcb_desc, 0, sizeof(struct rtl_tcb_desc));
 	ring = &rtlpci->tx_ring[BEACON_QUEUE];
 	pskb = __skb_dequeue(&ring->queue);
-	if (pskb)
+	if (rtlpriv->use_new_trx_flow)
+		entry = (u8 *)(&ring->buffer_desc[ring->idx]);
+	else
+		entry = (u8 *)(&ring->desc[ring->idx]);
+	if (pskb) {
+		pci_unmap_single(rtlpci->pdev,
+				 rtlpriv->cfg->ops->get_desc(
+				 (u8 *)entry, true, HW_DESC_TXBUFF_ADDR),
+				 pskb->len, PCI_DMA_TODEVICE);
 		kfree_skb(pskb);
+	}
 
 	/*NB: the beacon data buffer must be 32-bit aligned. */
 	pskb = ieee80211_beacon_get(hw, mac->vif);
@@ -1307,7 +1336,7 @@ static int _rtl_pci_init_rx_ring(struct ieee80211_hw *hw, int rxring_idx)
 		rtlpci->rx_ring[rxring_idx].idx = 0;
 		for (i = 0; i < rtlpci->rxringcount; i++) {
 			entry = &rtlpci->rx_ring[rxring_idx].buffer_desc[i];
-			if (!_rtl_pci_init_one_rxdesc(hw, (u8 *)entry,
+			if (!_rtl_pci_init_one_rxdesc(hw, NULL, (u8 *)entry,
 						      rxring_idx, i))
 				return -ENOMEM;
 		}
@@ -1332,7 +1361,7 @@ static int _rtl_pci_init_rx_ring(struct ieee80211_hw *hw, int rxring_idx)
 
 		for (i = 0; i < rtlpci->rxringcount; i++) {
 			entry = &rtlpci->rx_ring[rxring_idx].desc[i];
-			if (!_rtl_pci_init_one_rxdesc(hw, (u8 *)entry,
+			if (!_rtl_pci_init_one_rxdesc(hw, NULL, (u8 *)entry,
 						      rxring_idx, i))
 				return -ENOMEM;
 		}
@@ -1672,6 +1701,15 @@ static int rtl_pci_tx(struct ieee80211_hw *hw,
 		}
 	}
 
+	if (rtlpriv->cfg->ops->get_available_desc &&
+	    rtlpriv->cfg->ops->get_available_desc(hw, hw_queue) == 0) {
+			RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
+				 "get_available_desc fail\n");
+			spin_unlock_irqrestore(&rtlpriv->locks.irq_th_lock,
+					       flags);
+			return skb->len;
+	}
+
 	if (ieee80211_is_data_qos(fc)) {
 		tid = rtl_get_tid(skb);
 		if (sta) {
diff --git a/drivers/net/wireless/rtlwifi/pci.h b/drivers/net/wireless/rtlwifi/pci.h
index 5e832306dba..d4567d12e07 100644
--- a/drivers/net/wireless/rtlwifi/pci.h
+++ b/drivers/net/wireless/rtlwifi/pci.h
@@ -325,4 +325,11 @@ static inline void pci_write32_async(struct rtl_priv *rtlpriv,
 	writel(val, (u8 __iomem *) rtlpriv->io.pci_mem_start + addr);
 }
 
+static inline u16 calc_fifo_space(u16 rp, u16 wp)
+{
+	if (rp <= wp)
+		return RTL_PCI_MAX_RX_COUNT - 1 + rp - wp;
+	return rp - wp - 1;
+}
+
 #endif
diff --git a/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c b/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
index f2b9713c456..425ccb30170 100644
--- a/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
@@ -1353,27 +1353,11 @@ void rtl88ee_set_qos(struct ieee80211_hw *hw, int aci)
 	}
 }
 
-static void rtl88ee_clear_interrupt(struct ieee80211_hw *hw)
-{
-	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	u32 tmp;
-
-	tmp = rtl_read_dword(rtlpriv, REG_HISR);
-	rtl_write_dword(rtlpriv, REG_HISR, tmp);
-
-	tmp = rtl_read_dword(rtlpriv, REG_HISRE);
-	rtl_write_dword(rtlpriv, REG_HISRE, tmp);
-
-	tmp = rtl_read_dword(rtlpriv, REG_HSISR);
-	rtl_write_dword(rtlpriv, REG_HSISR, tmp);
-}
-
 void rtl88ee_enable_interrupt(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
-	rtl88ee_clear_interrupt(hw);/*clear it here first*/
 	rtl_write_dword(rtlpriv, REG_HIMR,
 			rtlpci->irq_mask[0] & 0xFFFFFFFF);
 	rtl_write_dword(rtlpriv, REG_HIMRE,
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c b/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c
index 55357d69397..5c646d5f7bb 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c
@@ -955,6 +955,7 @@ int rtl92ce_hw_init(struct ieee80211_hw *hw)
 	local_save_flags(flags);
 	local_irq_enable();
 
+	rtlhal->fw_ready = false;
 	rtlpriv->intf_ops->disable_aspm(hw);
 	rtstatus = _rtl92ce_init_mac(hw);
 	if (!rtstatus) {
@@ -971,6 +972,7 @@ int rtl92ce_hw_init(struct ieee80211_hw *hw)
 		goto exit;
 	}
 
+	rtlhal->fw_ready = true;
 	rtlhal->last_hmeboxnum = 0;
 	rtl92c_phy_mac_config(hw);
 	/* because last function modify RCR, so we update
@@ -1287,6 +1289,7 @@ void rtl92ce_enable_interrupt(struct ieee80211_hw *hw)
 
 	rtl_write_dword(rtlpriv, REG_HIMR, rtlpci->irq_mask[0] & 0xFFFFFFFF);
 	rtl_write_dword(rtlpriv, REG_HIMRE, rtlpci->irq_mask[1] & 0xFFFFFFFF);
+	rtlpci->irq_enabled = true;
 }
 
 void rtl92ce_disable_interrupt(struct ieee80211_hw *hw)
@@ -1296,7 +1299,7 @@ void rtl92ce_disable_interrupt(struct ieee80211_hw *hw)
 
 	rtl_write_dword(rtlpriv, REG_HIMR, IMR8190_DISABLED);
 	rtl_write_dword(rtlpriv, REG_HIMRE, IMR8190_DISABLED);
-	synchronize_irq(rtlpci->pdev->irq);
+	rtlpci->irq_enabled = false;
 }
 
 static void _rtl92ce_poweroff_adapter(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/sw.c b/drivers/net/wireless/rtlwifi/rtl8192ce/sw.c
index 46ea07605eb..dd5aa089126 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ce/sw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192ce/sw.c
@@ -228,6 +228,7 @@ static struct rtl_hal_ops rtl8192ce_hal_ops = {
 	.led_control = rtl92ce_led_control,
 	.set_desc = rtl92ce_set_desc,
 	.get_desc = rtl92ce_get_desc,
+	.is_tx_desc_closed = rtl92ce_is_tx_desc_closed,
 	.tx_polling = rtl92ce_tx_polling,
 	.enable_hw_sec = rtl92ce_enable_hw_security_config,
 	.set_key = rtl92ce_set_key,
@@ -271,6 +272,8 @@ static struct rtl_hal_cfg rtl92ce_hal_cfg = {
 	.maps[MAC_RCR_ACRC32] = ACRC32,
 	.maps[MAC_RCR_ACF] = ACF,
 	.maps[MAC_RCR_AAP] = AAP,
+	.maps[MAC_HIMR] = REG_HIMR,
+	.maps[MAC_HIMRE] = REG_HIMRE,
 
 	.maps[EFUSE_TEST] = REG_EFUSE_TEST,
 	.maps[EFUSE_CTRL] = REG_EFUSE_CTRL,
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/trx.c b/drivers/net/wireless/rtlwifi/rtl8192ce/trx.c
index dc3d20b17a2..e88dcd0e0af 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ce/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192ce/trx.c
@@ -720,16 +720,15 @@ u32 rtl92ce_get_desc(u8 *p_desc, bool istx, u8 desc_name)
 			break;
 		}
 	} else {
-		struct rx_desc_92c *pdesc = (struct rx_desc_92c *)p_desc;
 		switch (desc_name) {
 		case HW_DESC_OWN:
-			ret = GET_RX_DESC_OWN(pdesc);
+			ret = GET_RX_DESC_OWN(p_desc);
 			break;
 		case HW_DESC_RXPKT_LEN:
-			ret = GET_RX_DESC_PKT_LEN(pdesc);
+			ret = GET_RX_DESC_PKT_LEN(p_desc);
 			break;
 		case HW_DESC_RXBUFF_ADDR:
-			ret = GET_RX_STATUS_DESC_BUFF_ADDR(pdesc);
+			ret = GET_RX_DESC_BUFF_ADDR(p_desc);
 			break;
 		default:
 			RT_ASSERT(false, "ERR rxdesc :%d not process\n",
@@ -740,6 +739,23 @@ u32 rtl92ce_get_desc(u8 *p_desc, bool istx, u8 desc_name)
 	return ret;
 }
 
+bool rtl92ce_is_tx_desc_closed(struct ieee80211_hw *hw,
+			       u8 hw_queue, u16 index)
+{
+	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
+	struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[hw_queue];
+	u8 *entry = (u8 *)(&ring->desc[ring->idx]);
+	u8 own = (u8)rtl92ce_get_desc(entry, true, HW_DESC_OWN);
+
+	/*beacon packet will only use the first
+	 *descriptor defautly,and the own may not
+	 *be cleared by the hardware
+	 */
+	if (own)
+		return false;
+	return true;
+}
+
 void rtl92ce_tx_polling(struct ieee80211_hw *hw, u8 hw_queue)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/trx.h b/drivers/net/wireless/rtlwifi/rtl8192ce/trx.h
index 9a39ec4204d..4bec4b07e3e 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ce/trx.h
+++ b/drivers/net/wireless/rtlwifi/rtl8192ce/trx.h
@@ -723,6 +723,8 @@ bool rtl92ce_rx_query_desc(struct ieee80211_hw *hw,
 void rtl92ce_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx,
 		      u8 desc_name, u8 *val);
 u32 rtl92ce_get_desc(u8 *pdesc, bool istx, u8 desc_name);
+bool rtl92ce_is_tx_desc_closed(struct ieee80211_hw *hw,
+			       u8 hw_queue, u16 index);
 void rtl92ce_tx_polling(struct ieee80211_hw *hw, u8 hw_queue);
 void rtl92ce_tx_fill_cmddesc(struct ieee80211_hw *hw, u8 *pdesc,
 			     bool b_firstseg, bool b_lastseg,
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c
index e06bafee37f..5034660bf41 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c
@@ -321,6 +321,7 @@ static struct usb_device_id rtl8192c_usb_ids[] = {
 	{RTL_USB_DEVICE(0x07b8, 0x8188, rtl92cu_hal_cfg)}, /*Abocom - Abocom*/
 	{RTL_USB_DEVICE(0x07b8, 0x8189, rtl92cu_hal_cfg)}, /*Funai - Abocom*/
 	{RTL_USB_DEVICE(0x0846, 0x9041, rtl92cu_hal_cfg)}, /*NetGear WNA1000M*/
+	{RTL_USB_DEVICE(0x0b05, 0x17ba, rtl92cu_hal_cfg)}, /*ASUS-Edimax*/
 	{RTL_USB_DEVICE(0x0bda, 0x5088, rtl92cu_hal_cfg)}, /*Thinkware-CC&C*/
 	{RTL_USB_DEVICE(0x0df6, 0x0052, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/
 	{RTL_USB_DEVICE(0x0df6, 0x005c, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/
@@ -377,6 +378,7 @@ static struct usb_device_id rtl8192c_usb_ids[] = {
 	{RTL_USB_DEVICE(0x2001, 0x3307, rtl92cu_hal_cfg)}, /*D-Link-Cameo*/
 	{RTL_USB_DEVICE(0x2001, 0x3309, rtl92cu_hal_cfg)}, /*D-Link-Alpha*/
 	{RTL_USB_DEVICE(0x2001, 0x330a, rtl92cu_hal_cfg)}, /*D-Link-Alpha*/
+	{RTL_USB_DEVICE(0x2001, 0x330d, rtl92cu_hal_cfg)}, /*D-Link DWA-131 */
 	{RTL_USB_DEVICE(0x2019, 0xab2b, rtl92cu_hal_cfg)}, /*Planex -Abocom*/
 	{RTL_USB_DEVICE(0x20f4, 0x624d, rtl92cu_hal_cfg)}, /*TRENDNet*/
 	{RTL_USB_DEVICE(0x2357, 0x0100, rtl92cu_hal_cfg)}, /*TP-Link WN8200ND*/
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ee/fw.c b/drivers/net/wireless/rtlwifi/rtl8192ee/fw.c
index 45c128b91f7..c5d4b8013cd 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ee/fw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192ee/fw.c
@@ -666,7 +666,6 @@ void rtl92ee_set_fw_rsvdpagepkt(struct ieee80211_hw *hw, bool b_dl_finished)
 	struct sk_buff *skb = NULL;
 
 	u32 totalpacketlen;
-	bool rtstatus;
 	u8 u1rsvdpageloc[5] = { 0 };
 	bool b_dlok = false;
 
@@ -728,10 +727,7 @@ void rtl92ee_set_fw_rsvdpagepkt(struct ieee80211_hw *hw, bool b_dl_finished)
 	memcpy((u8 *)skb_put(skb, totalpacketlen),
 	       &reserved_page_packet, totalpacketlen);
 
-	rtstatus = rtl_cmd_send_packet(hw, skb);
-
-	if (rtstatus)
-		b_dlok = true;
+	b_dlok = true;
 
 	if (b_dlok) {
 		RT_TRACE(rtlpriv, COMP_POWER, DBG_LOUD ,
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ee/hw.c b/drivers/net/wireless/rtlwifi/rtl8192ee/hw.c
index 1a87edca2c3..93624541e49 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ee/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192ee/hw.c
@@ -85,29 +85,6 @@ static void _rtl92ee_enable_bcn_sub_func(struct ieee80211_hw *hw)
 	_rtl92ee_set_bcn_ctrl_reg(hw, 0, BIT(1));
 }
 
-static void _rtl92ee_return_beacon_queue_skb(struct ieee80211_hw *hw)
-{
-	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
-	struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[BEACON_QUEUE];
-	unsigned long flags;
-
-	spin_lock_irqsave(&rtlpriv->locks.irq_th_lock, flags);
-	while (skb_queue_len(&ring->queue)) {
-		struct rtl_tx_buffer_desc *entry =
-						&ring->buffer_desc[ring->idx];
-		struct sk_buff *skb = __skb_dequeue(&ring->queue);
-
-		pci_unmap_single(rtlpci->pdev,
-				 rtlpriv->cfg->ops->get_desc(
-				 (u8 *)entry, true, HW_DESC_TXBUFF_ADDR),
-				 skb->len, PCI_DMA_TODEVICE);
-		kfree_skb(skb);
-		ring->idx = (ring->idx + 1) % ring->entries;
-	}
-	spin_unlock_irqrestore(&rtlpriv->locks.irq_th_lock, flags);
-}
-
 static void _rtl92ee_disable_bcn_sub_func(struct ieee80211_hw *hw)
 {
 	_rtl92ee_set_bcn_ctrl_reg(hw, BIT(1), 0);
@@ -403,9 +380,6 @@ static void _rtl92ee_download_rsvd_page(struct ieee80211_hw *hw)
 		rtl_write_byte(rtlpriv, REG_DWBCN0_CTRL + 2,
 			       bcnvalid_reg | BIT(0));
 
-		/* Return Beacon TCB */
-		_rtl92ee_return_beacon_queue_skb(hw);
-
 		/* download rsvd page */
 		rtl92ee_set_fw_rsvdpagepkt(hw, false);
 
@@ -1163,6 +1137,139 @@ void rtl92ee_enable_hw_security_config(struct ieee80211_hw *hw)
 	rtlpriv->cfg->ops->set_hw_reg(hw, HW_VAR_WPA_CONFIG, &sec_reg_value);
 }
 
+static bool _rtl8192ee_check_pcie_dma_hang(struct rtl_priv *rtlpriv)
+{
+	u8 tmp;
+
+	/* write reg 0x350 Bit[26]=1. Enable debug port. */
+	tmp = rtl_read_byte(rtlpriv, REG_BACKDOOR_DBI_DATA + 3);
+	if (!(tmp & BIT(2))) {
+		rtl_write_byte(rtlpriv, REG_BACKDOOR_DBI_DATA + 3,
+			       tmp | BIT(2));
+		mdelay(100); /* Suggested by DD Justin_tsai. */
+	}
+
+	/* read reg 0x350 Bit[25] if 1 : RX hang
+	 * read reg 0x350 Bit[24] if 1 : TX hang
+	 */
+	tmp = rtl_read_byte(rtlpriv, REG_BACKDOOR_DBI_DATA + 3);
+	if ((tmp & BIT(0)) || (tmp & BIT(1))) {
+		RT_TRACE(rtlpriv, COMP_INIT, DBG_LOUD,
+			 "CheckPcieDMAHang8192EE(): true!!\n");
+		return true;
+	}
+	return false;
+}
+
+static void _rtl8192ee_reset_pcie_interface_dma(struct rtl_priv *rtlpriv,
+						bool mac_power_on)
+{
+	u8 tmp;
+	bool release_mac_rx_pause;
+	u8 backup_pcie_dma_pause;
+
+	RT_TRACE(rtlpriv, COMP_INIT, DBG_LOUD,
+		 "ResetPcieInterfaceDMA8192EE()\n");
+
+	/* Revise Note: Follow the document "PCIe RX DMA Hang Reset Flow_v03"
+	 * released by SD1 Alan.
+	 */
+
+	/* 1. disable register write lock
+	 *	write 0x1C bit[1:0] = 2'h0
+	 *	write 0xCC bit[2] = 1'b1
+	 */
+	tmp = rtl_read_byte(rtlpriv, REG_RSV_CTRL);
+	tmp &= ~(BIT(1) | BIT(0));
+	rtl_write_byte(rtlpriv, REG_RSV_CTRL, tmp);
+	tmp = rtl_read_byte(rtlpriv, REG_PMC_DBG_CTRL2);
+	tmp |= BIT(2);
+	rtl_write_byte(rtlpriv, REG_PMC_DBG_CTRL2, tmp);
+
+	/* 2. Check and pause TRX DMA
+	 *	write 0x284 bit[18] = 1'b1
+	 *	write 0x301 = 0xFF
+	 */
+	tmp = rtl_read_byte(rtlpriv, REG_RXDMA_CONTROL);
+	if (tmp & BIT(2)) {
+		/* Already pause before the function for another reason. */
+		release_mac_rx_pause = false;
+	} else {
+		rtl_write_byte(rtlpriv, REG_RXDMA_CONTROL, (tmp | BIT(2)));
+		release_mac_rx_pause = true;
+	}
+
+	backup_pcie_dma_pause = rtl_read_byte(rtlpriv, REG_PCIE_CTRL_REG + 1);
+	if (backup_pcie_dma_pause != 0xFF)
+		rtl_write_byte(rtlpriv, REG_PCIE_CTRL_REG + 1, 0xFF);
+
+	if (mac_power_on) {
+		/* 3. reset TRX function
+		 *	write 0x100 = 0x00
+		 */
+		rtl_write_byte(rtlpriv, REG_CR, 0);
+	}
+
+	/* 4. Reset PCIe DMA
+	 *	write 0x003 bit[0] = 0
+	 */
+	tmp = rtl_read_byte(rtlpriv, REG_SYS_FUNC_EN + 1);
+	tmp &= ~(BIT(0));
+	rtl_write_byte(rtlpriv, REG_SYS_FUNC_EN + 1, tmp);
+
+	/* 5. Enable PCIe DMA
+	 *	write 0x003 bit[0] = 1
+	 */
+	tmp = rtl_read_byte(rtlpriv, REG_SYS_FUNC_EN + 1);
+	tmp |= BIT(0);
+	rtl_write_byte(rtlpriv, REG_SYS_FUNC_EN + 1, tmp);
+
+	if (mac_power_on) {
+		/* 6. enable TRX function
+		 *	write 0x100 = 0xFF
+		 */
+		rtl_write_byte(rtlpriv, REG_CR, 0xFF);
+
+		/* We should init LLT & RQPN and
+		 * prepare Tx/Rx descrptor address later
+		 * because MAC function is reset.
+		 */
+	}
+
+	/* 7. Restore PCIe autoload down bit
+	 *	write 0xF8 bit[17] = 1'b1
+	 */
+	tmp = rtl_read_byte(rtlpriv, REG_MAC_PHY_CTRL_NORMAL + 2);
+	tmp |= BIT(1);
+	rtl_write_byte(rtlpriv, REG_MAC_PHY_CTRL_NORMAL + 2, tmp);
+
+	/* In MAC power on state, BB and RF maybe in ON state,
+	 * if we release TRx DMA here
+	 * it will cause packets to be started to Tx/Rx,
+	 * so we release Tx/Rx DMA later.
+	 */
+	if (!mac_power_on) {
+		/* 8. release TRX DMA
+		 *	write 0x284 bit[18] = 1'b0
+		 *	write 0x301 = 0x00
+		 */
+		if (release_mac_rx_pause) {
+			tmp = rtl_read_byte(rtlpriv, REG_RXDMA_CONTROL);
+			rtl_write_byte(rtlpriv, REG_RXDMA_CONTROL,
+				       (tmp & (~BIT(2))));
+		}
+		rtl_write_byte(rtlpriv, REG_PCIE_CTRL_REG + 1,
+			       backup_pcie_dma_pause);
+	}
+
+	/* 9. lock system register
+	 *	write 0xCC bit[2] = 1'b0
+	 */
+	tmp = rtl_read_byte(rtlpriv, REG_PMC_DBG_CTRL2);
+	tmp &= ~(BIT(2));
+	rtl_write_byte(rtlpriv, REG_PMC_DBG_CTRL2, tmp);
+}
+
 int rtl92ee_hw_init(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
@@ -1188,6 +1295,13 @@ int rtl92ee_hw_init(struct ieee80211_hw *hw)
 		rtlhal->fw_ps_state = FW_PS_STATE_ALL_ON_92E;
 	}
 
+	if (_rtl8192ee_check_pcie_dma_hang(rtlpriv)) {
+		RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG, "92ee dma hang!\n");
+		_rtl8192ee_reset_pcie_interface_dma(rtlpriv,
+						    rtlhal->mac_func_enable);
+		rtlhal->mac_func_enable = false;
+	}
+
 	rtstatus = _rtl92ee_init_mac(hw);
 
 	rtl_write_byte(rtlpriv, 0x577, 0x03);
@@ -1470,28 +1584,11 @@ void rtl92ee_set_qos(struct ieee80211_hw *hw, int aci)
 	}
 }
 
-static void rtl92ee_clear_interrupt(struct ieee80211_hw *hw)
-{
-	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	u32 tmp;
-
-	tmp = rtl_read_dword(rtlpriv, REG_HISR);
-	rtl_write_dword(rtlpriv, REG_HISR, tmp);
-
-	tmp = rtl_read_dword(rtlpriv, REG_HISRE);
-	rtl_write_dword(rtlpriv, REG_HISRE, tmp);
-
-	tmp = rtl_read_dword(rtlpriv, REG_HSISR);
-	rtl_write_dword(rtlpriv, REG_HSISR, tmp);
-}
-
 void rtl92ee_enable_interrupt(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
-	rtl92ee_clear_interrupt(hw);/*clear it here first*/
-
 	rtl_write_dword(rtlpriv, REG_HIMR, rtlpci->irq_mask[0] & 0xFFFFFFFF);
 	rtl_write_dword(rtlpriv, REG_HIMRE, rtlpci->irq_mask[1] & 0xFFFFFFFF);
 	rtlpci->irq_enabled = true;
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ee/reg.h b/drivers/net/wireless/rtlwifi/rtl8192ee/reg.h
index 3f2a9596e7c..1eaa1fab550 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ee/reg.h
+++ b/drivers/net/wireless/rtlwifi/rtl8192ee/reg.h
@@ -77,9 +77,11 @@
 #define REG_HIMRE				0x00B8
 #define REG_HISRE				0x00BC
 
+#define REG_PMC_DBG_CTRL2			0x00CC
 #define REG_EFUSE_ACCESS			0x00CF
 #define REG_HPON_FSM				0x00EC
 #define REG_SYS_CFG1				0x00F0
+#define REG_MAC_PHY_CTRL_NORMAL			0x00F8
 #define REG_SYS_CFG2				0x00FC
 
 #define REG_CR					0x0100
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ee/sw.c b/drivers/net/wireless/rtlwifi/rtl8192ee/sw.c
index 9b5a7d5be12..c31c6bfb536 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ee/sw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192ee/sw.c
@@ -113,8 +113,6 @@ int rtl92ee_init_sw_vars(struct ieee80211_hw *hw)
 				  RCR_HTC_LOC_CTRL		|
 				  RCR_AMF			|
 				  RCR_ACF			|
-				  RCR_ADF			|
-				  RCR_AICV			|
 				  RCR_ACRC32			|
 				  RCR_AB			|
 				  RCR_AM			|
@@ -241,6 +239,7 @@ static struct rtl_hal_ops rtl8192ee_hal_ops = {
 	.set_desc = rtl92ee_set_desc,
 	.get_desc = rtl92ee_get_desc,
 	.is_tx_desc_closed = rtl92ee_is_tx_desc_closed,
+	.get_available_desc = rtl92ee_get_available_desc,
 	.tx_polling = rtl92ee_tx_polling,
 	.enable_hw_sec = rtl92ee_enable_hw_security_config,
 	.set_key = rtl92ee_set_key,
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ee/trx.c b/drivers/net/wireless/rtlwifi/rtl8192ee/trx.c
index 2fcbef1d029..1f6d160877e 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ee/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192ee/trx.c
@@ -512,6 +512,10 @@ bool rtl92ee_rx_query_desc(struct ieee80211_hw *hw,
 	struct ieee80211_hdr *hdr;
 	u32 phystatus = GET_RX_DESC_PHYST(pdesc);
 
+	if (GET_RX_STATUS_DESC_RPT_SEL(pdesc) == 0)
+		status->packet_report_type = NORMAL_RX;
+	else
+		status->packet_report_type = C2H_PACKET;
 	status->length = (u16)GET_RX_DESC_PKT_LEN(pdesc);
 	status->rx_drvinfo_size = (u8)GET_RX_DESC_DRV_INFO_SIZE(pdesc) *
 				  RX_DRV_INFO_SIZE_UNIT;
@@ -654,14 +658,7 @@ u16 rtl92ee_rx_desc_buff_remained_cnt(struct ieee80211_hw *hw, u8 queue_index)
 	if (!start_rx)
 		return 0;
 
-	if ((last_read_point > (RX_DESC_NUM_92E / 2)) &&
-	    (read_point <= (RX_DESC_NUM_92E / 2))) {
-		remind_cnt = RX_DESC_NUM_92E - write_point;
-	} else {
-		remind_cnt = (read_point >= write_point) ?
-			     (read_point - write_point) :
-			     (RX_DESC_NUM_92E - write_point + read_point);
-	}
+	remind_cnt = calc_fifo_space(read_point, write_point);
 
 	if (remind_cnt == 0)
 		return 0;
@@ -710,7 +707,7 @@ static u16 get_desc_addr_fr_q_idx(u16 queue_index)
 	return desc_address;
 }
 
-void rtl92ee_get_available_desc(struct ieee80211_hw *hw, u8 q_idx)
+u16 rtl92ee_get_available_desc(struct ieee80211_hw *hw, u8 q_idx)
 {
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
@@ -724,11 +721,12 @@ void rtl92ee_get_available_desc(struct ieee80211_hw *hw, u8 q_idx)
 	current_tx_write_point = (u16)((tmp_4byte) & 0x0fff);
 
 	point_diff = ((current_tx_read_point > current_tx_write_point) ?
-		      (current_tx_read_point - current_tx_write_point) :
-		      (TX_DESC_NUM_92E - current_tx_write_point +
+		      (current_tx_read_point - current_tx_write_point - 1) :
+		      (TX_DESC_NUM_92E - 1 - current_tx_write_point +
 		       current_tx_read_point));
 
 	rtlpci->tx_ring[q_idx].avl_desc = point_diff;
+	return point_diff;
 }
 
 void rtl92ee_pre_fill_tx_bd_desc(struct ieee80211_hw *hw,
@@ -1207,8 +1205,7 @@ bool rtl92ee_is_tx_desc_closed(struct ieee80211_hw *hw, u8 hw_queue, u16 index)
 	static u8 stop_report_cnt;
 	struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[hw_queue];
 
-	/*checking Read/Write Point each interrupt wastes CPU */
-	if (stop_report_cnt > 15 || !rtlpriv->link_info.busytraffic) {
+	{
 		u16 point_diff = 0;
 		u16 cur_tx_rp, cur_tx_wp;
 		u32 tmpu32 = 0;
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ee/trx.h b/drivers/net/wireless/rtlwifi/rtl8192ee/trx.h
index 6f9be1c7515..b489dd9c840 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ee/trx.h
+++ b/drivers/net/wireless/rtlwifi/rtl8192ee/trx.h
@@ -542,6 +542,8 @@
 	LE_BITS_TO_4BYTE(__pdesc+8, 12, 4)
 #define GET_RX_DESC_RX_IS_QOS(__pdesc)			\
 	LE_BITS_TO_4BYTE(__pdesc+8, 16, 1)
+#define GET_RX_STATUS_DESC_RPT_SEL(__pdesc)		\
+	LE_BITS_TO_4BYTE(__pdesc+8, 28, 1)
 
 #define GET_RX_DESC_RXMCS(__pdesc)			\
 	LE_BITS_TO_4BYTE(__pdesc+12, 0, 7)
@@ -829,7 +831,7 @@ void rtl92ee_rx_check_dma_ok(struct ieee80211_hw *hw, u8 *header_desc,
 			     u8 queue_index);
 u16	rtl92ee_rx_desc_buff_remained_cnt(struct ieee80211_hw *hw,
 					  u8 queue_index);
-void rtl92ee_get_available_desc(struct ieee80211_hw *hw, u8 queue_index);
+u16 rtl92ee_get_available_desc(struct ieee80211_hw *hw, u8 queue_index);
 void rtl92ee_pre_fill_tx_bd_desc(struct ieee80211_hw *hw,
 				 u8 *tx_bd_desc, u8 *desc, u8 queue_index,
 				 struct sk_buff *skb, dma_addr_t addr);
diff --git a/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c b/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
index aa085462d0e..5e133408257 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
@@ -1258,18 +1258,6 @@ void rtl8723e_set_qos(struct ieee80211_hw *hw, int aci)
 	}
 }
 
-static void rtl8723e_clear_interrupt(struct ieee80211_hw *hw)
-{
-	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	u32 tmp;
-
-	tmp = rtl_read_dword(rtlpriv, REG_HISR);
-	rtl_write_dword(rtlpriv, REG_HISR, tmp);
-
-	tmp = rtl_read_dword(rtlpriv, REG_HISRE);
-	rtl_write_dword(rtlpriv, REG_HISRE, tmp);
-}
-
 void rtl8723e_enable_interrupt(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
@@ -1284,7 +1272,6 @@ void rtl8723e_disable_interrupt(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
-	rtl8723e_clear_interrupt(hw);/*clear it here first*/
 	rtl_write_dword(rtlpriv, 0x3a8, IMR8190_DISABLED);
 	rtl_write_dword(rtlpriv, 0x3ac, IMR8190_DISABLED);
 	rtlpci->irq_enabled = false;
diff --git a/drivers/net/wireless/rtlwifi/rtl8723be/hw.c b/drivers/net/wireless/rtlwifi/rtl8723be/hw.c
index 6dad28e77bb..cfe67996367 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723be/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8723be/hw.c
@@ -1634,28 +1634,11 @@ void rtl8723be_set_qos(struct ieee80211_hw *hw, int aci)
 	}
 }
 
-static void rtl8723be_clear_interrupt(struct ieee80211_hw *hw)
-{
-	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	u32 tmp;
-
-	tmp = rtl_read_dword(rtlpriv, REG_HISR);
-	rtl_write_dword(rtlpriv, REG_HISR, tmp);
-
-	tmp = rtl_read_dword(rtlpriv, REG_HISRE);
-	rtl_write_dword(rtlpriv, REG_HISRE, tmp);
-
-	tmp = rtl_read_dword(rtlpriv, REG_HSISR);
-	rtl_write_dword(rtlpriv, REG_HSISR, tmp);
-}
-
 void rtl8723be_enable_interrupt(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
-	rtl8723be_clear_interrupt(hw);/*clear it here first*/
-
 	rtl_write_dword(rtlpriv, REG_HIMR, rtlpci->irq_mask[0] & 0xFFFFFFFF);
 	rtl_write_dword(rtlpriv, REG_HIMRE, rtlpci->irq_mask[1] & 0xFFFFFFFF);
 	rtlpci->irq_enabled = true;
diff --git a/drivers/net/wireless/rtlwifi/rtl8821ae/hw.c b/drivers/net/wireless/rtlwifi/rtl8821ae/hw.c
index 8ec8200002c..43c14d4da56 100644
--- a/drivers/net/wireless/rtlwifi/rtl8821ae/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8821ae/hw.c
@@ -2253,31 +2253,11 @@ void rtl8821ae_set_qos(struct ieee80211_hw *hw, int aci)
 	}
 }
 
-static void rtl8821ae_clear_interrupt(struct ieee80211_hw *hw)
-{
-	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	u32 tmp;
-	tmp = rtl_read_dword(rtlpriv, REG_HISR);
-	/*printk("clear interrupt first:\n");
-	printk("0x%x = 0x%08x\n",REG_HISR, tmp);*/
-	rtl_write_dword(rtlpriv, REG_HISR, tmp);
-
-	tmp = rtl_read_dword(rtlpriv, REG_HISRE);
-	/*printk("0x%x = 0x%08x\n",REG_HISRE, tmp);*/
-	rtl_write_dword(rtlpriv, REG_HISRE, tmp);
-
-	tmp = rtl_read_dword(rtlpriv, REG_HSISR);
-	/*printk("0x%x = 0x%08x\n",REG_HSISR, tmp);*/
-	rtl_write_dword(rtlpriv, REG_HSISR, tmp);
-}
-
 void rtl8821ae_enable_interrupt(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
-	rtl8821ae_clear_interrupt(hw);/*clear it here first*/
-
 	rtl_write_dword(rtlpriv, REG_HIMR, rtlpci->irq_mask[0] & 0xFFFFFFFF);
 	rtl_write_dword(rtlpriv, REG_HIMRE, rtlpci->irq_mask[1] & 0xFFFFFFFF);
 	rtlpci->irq_enabled = true;
diff --git a/drivers/net/wireless/rtlwifi/usb.c b/drivers/net/wireless/rtlwifi/usb.c
index 46ee956d023..27cd6cabf6c 100644
--- a/drivers/net/wireless/rtlwifi/usb.c
+++ b/drivers/net/wireless/rtlwifi/usb.c
@@ -126,7 +126,7 @@ static int _usbctrl_vendorreq_sync_read(struct usb_device *udev, u8 request,
 
 	do {
 		status = usb_control_msg(udev, pipe, request, reqtype, value,
-					 index, pdata, len, 0); /*max. timeout*/
+					 index, pdata, len, 1000);
 		if (status < 0) {
 			/* firmware download is checksumed, don't retry */
 			if ((value >= FW_8192C_START_ADDRESS &&
diff --git a/drivers/net/wireless/rtlwifi/wifi.h b/drivers/net/wireless/rtlwifi/wifi.h
index 6866dcf2434..27822fe34d9 100644
--- a/drivers/net/wireless/rtlwifi/wifi.h
+++ b/drivers/net/wireless/rtlwifi/wifi.h
@@ -2161,6 +2161,7 @@ struct rtl_hal_ops {
 	void (*add_wowlan_pattern)(struct ieee80211_hw *hw,
 				   struct rtl_wow_pattern *rtl_pattern,
 				   u8 index);
+	u16 (*get_available_desc)(struct ieee80211_hw *hw, u8 q_idx);
 };
 
 struct rtl_intf_ops {
diff --git a/drivers/net/wireless/ti/wl18xx/debugfs.c b/drivers/net/wireless/ti/wl18xx/debugfs.c
index 7f1669cdea0..779dc2b2ca7 100644
--- a/drivers/net/wireless/ti/wl18xx/debugfs.c
+++ b/drivers/net/wireless/ti/wl18xx/debugfs.c
@@ -136,7 +136,7 @@ WL18XX_DEBUGFS_FWSTATS_FILE(rx_filter, protection_filter, "%u");
 WL18XX_DEBUGFS_FWSTATS_FILE(rx_filter, accum_arp_pend_requests, "%u");
 WL18XX_DEBUGFS_FWSTATS_FILE(rx_filter, max_arp_queue_dep, "%u");
 
-WL18XX_DEBUGFS_FWSTATS_FILE(rx_rate, rx_frames_per_rates, "%u");
+WL18XX_DEBUGFS_FWSTATS_FILE_ARRAY(rx_rate, rx_frames_per_rates, 50);
 
 WL18XX_DEBUGFS_FWSTATS_FILE_ARRAY(aggr_size, tx_agg_vs_rate,
 				  AGGR_STATS_TX_AGG*AGGR_STATS_TX_RATE);
diff --git a/drivers/net/wireless/ti/wlcore/debugfs.h b/drivers/net/wireless/ti/wlcore/debugfs.h
index 0f2cfb0d2a9..bf14676e651 100644
--- a/drivers/net/wireless/ti/wlcore/debugfs.h
+++ b/drivers/net/wireless/ti/wlcore/debugfs.h
@@ -26,8 +26,8 @@
 
 #include "wlcore.h"
 
-int wl1271_format_buffer(char __user *userbuf, size_t count,
-			 loff_t *ppos, char *fmt, ...);
+__printf(4, 5) int wl1271_format_buffer(char __user *userbuf, size_t count,
+					loff_t *ppos, char *fmt, ...);
 
 int wl1271_debugfs_init(struct wl1271 *wl);
 void wl1271_debugfs_exit(struct wl1271 *wl);
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 083ecc93fe5..5f1fda44882 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -230,6 +230,8 @@ struct xenvif {
 	 */
 	bool disabled;
 	unsigned long status;
+	unsigned long drain_timeout;
+	unsigned long stall_timeout;
 
 	/* Queues */
 	struct xenvif_queue *queues;
@@ -328,7 +330,7 @@ irqreturn_t xenvif_interrupt(int irq, void *dev_id);
 extern bool separate_tx_rx_irq;
 
 extern unsigned int rx_drain_timeout_msecs;
-extern unsigned int rx_drain_timeout_jiffies;
+extern unsigned int rx_stall_timeout_msecs;
 extern unsigned int xenvif_max_queues;
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 895fe84011e..d752d1c5c8b 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -166,7 +166,7 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto drop;
 
 	cb = XENVIF_RX_CB(skb);
-	cb->expires = jiffies + rx_drain_timeout_jiffies;
+	cb->expires = jiffies + vif->drain_timeout;
 
 	xenvif_rx_queue_tail(queue, skb);
 	xenvif_kick_thread(queue);
@@ -414,6 +414,8 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	vif->ip_csum = 1;
 	vif->dev = dev;
 	vif->disabled = false;
+	vif->drain_timeout = msecs_to_jiffies(rx_drain_timeout_msecs);
+	vif->stall_timeout = msecs_to_jiffies(rx_stall_timeout_msecs);
 
 	/* Start out with no queues. */
 	vif->queues = NULL;
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 6563f0713fc..c39aace4f64 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -60,14 +60,12 @@ module_param(separate_tx_rx_irq, bool, 0644);
  */
 unsigned int rx_drain_timeout_msecs = 10000;
 module_param(rx_drain_timeout_msecs, uint, 0444);
-unsigned int rx_drain_timeout_jiffies;
 
 /* The length of time before the frontend is considered unresponsive
  * because it isn't providing Rx slots.
  */
-static unsigned int rx_stall_timeout_msecs = 60000;
+unsigned int rx_stall_timeout_msecs = 60000;
 module_param(rx_stall_timeout_msecs, uint, 0444);
-static unsigned int rx_stall_timeout_jiffies;
 
 unsigned int xenvif_max_queues;
 module_param_named(max_queues, xenvif_max_queues, uint, 0644);
@@ -2022,7 +2020,7 @@ static bool xenvif_rx_queue_stalled(struct xenvif_queue *queue)
 	return !queue->stalled
 		&& prod - cons < XEN_NETBK_RX_SLOTS_MAX
 		&& time_after(jiffies,
-			      queue->last_rx_time + rx_stall_timeout_jiffies);
+			      queue->last_rx_time + queue->vif->stall_timeout);
 }
 
 static bool xenvif_rx_queue_ready(struct xenvif_queue *queue)
@@ -2040,8 +2038,9 @@ static bool xenvif_have_rx_work(struct xenvif_queue *queue)
 {
 	return (!skb_queue_empty(&queue->rx_queue)
 		&& xenvif_rx_ring_slots_available(queue, XEN_NETBK_RX_SLOTS_MAX))
-		|| xenvif_rx_queue_stalled(queue)
-		|| xenvif_rx_queue_ready(queue)
+		|| (queue->vif->stall_timeout &&
+		    (xenvif_rx_queue_stalled(queue)
+		     || xenvif_rx_queue_ready(queue)))
 		|| kthread_should_stop()
 		|| queue->vif->disabled;
 }
@@ -2094,6 +2093,9 @@ int xenvif_kthread_guest_rx(void *data)
 	struct xenvif_queue *queue = data;
 	struct xenvif *vif = queue->vif;
 
+	if (!vif->stall_timeout)
+		xenvif_queue_carrier_on(queue);
+
 	for (;;) {
 		xenvif_wait_for_rx_work(queue);
 
@@ -2120,10 +2122,12 @@ int xenvif_kthread_guest_rx(void *data)
 		 * while it's probably not responsive, drop the
 		 * carrier so packets are dropped earlier.
 		 */
-		if (xenvif_rx_queue_stalled(queue))
-			xenvif_queue_carrier_off(queue);
-		else if (xenvif_rx_queue_ready(queue))
-			xenvif_queue_carrier_on(queue);
+		if (vif->stall_timeout) {
+			if (xenvif_rx_queue_stalled(queue))
+				xenvif_queue_carrier_off(queue);
+			else if (xenvif_rx_queue_ready(queue))
+				xenvif_queue_carrier_on(queue);
+		}
 
 		/* Queued packets may have foreign pages from other
 		 * domains.  These cannot be queued indefinitely as
@@ -2194,9 +2198,6 @@ static int __init netback_init(void)
 	if (rc)
 		goto failed_init;
 
-	rx_drain_timeout_jiffies = msecs_to_jiffies(rx_drain_timeout_msecs);
-	rx_stall_timeout_jiffies = msecs_to_jiffies(rx_stall_timeout_msecs);
-
 #ifdef CONFIG_DEBUG_FS
 	xen_netback_dbg_root = debugfs_create_dir("xen-netback", NULL);
 	if (IS_ERR_OR_NULL(xen_netback_dbg_root))
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index fab0d4b42f5..d9d1e2af50d 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -34,6 +34,8 @@ struct backend_info {
 	enum xenbus_state frontend_state;
 	struct xenbus_watch hotplug_status_watch;
 	u8 have_hotplug_status_watch:1;
+
+	const char *hotplug_script;
 };
 
 static int connect_rings(struct backend_info *be, struct xenvif_queue *queue);
@@ -236,6 +238,7 @@ static int netback_remove(struct xenbus_device *dev)
 		xenvif_free(be->vif);
 		be->vif = NULL;
 	}
+	kfree(be->hotplug_script);
 	kfree(be);
 	dev_set_drvdata(&dev->dev, NULL);
 	return 0;
@@ -253,6 +256,7 @@ static int netback_probe(struct xenbus_device *dev,
 	struct xenbus_transaction xbt;
 	int err;
 	int sg;
+	const char *script;
 	struct backend_info *be = kzalloc(sizeof(struct backend_info),
 					  GFP_KERNEL);
 	if (!be) {
@@ -345,6 +349,15 @@ static int netback_probe(struct xenbus_device *dev,
 	if (err)
 		pr_debug("Error writing multi-queue-max-queues\n");
 
+	script = xenbus_read(XBT_NIL, dev->nodename, "script", NULL);
+	if (IS_ERR(script)) {
+		err = PTR_ERR(script);
+		xenbus_dev_fatal(dev, err, "reading script");
+		goto fail;
+	}
+
+	be->hotplug_script = script;
+
 	err = xenbus_switch_state(dev, XenbusStateInitWait);
 	if (err)
 		goto fail;
@@ -377,22 +390,14 @@ static int netback_uevent(struct xenbus_device *xdev,
 			  struct kobj_uevent_env *env)
 {
 	struct backend_info *be = dev_get_drvdata(&xdev->dev);
-	char *val;
 
-	val = xenbus_read(XBT_NIL, xdev->nodename, "script", NULL);
-	if (IS_ERR(val)) {
-		int err = PTR_ERR(val);
-		xenbus_dev_fatal(xdev, err, "reading script");
-		return err;
-	} else {
-		if (add_uevent_var(env, "script=%s", val)) {
-			kfree(val);
-			return -ENOMEM;
-		}
-		kfree(val);
-	}
+	if (!be)
+		return 0;
 
-	if (!be || !be->vif)
+	if (add_uevent_var(env, "script=%s", be->hotplug_script))
+		return -ENOMEM;
+
+	if (!be->vif)
 		return 0;
 
 	return add_uevent_var(env, "vif=%s", be->vif->dev->name);
@@ -735,7 +740,9 @@ static void connect(struct backend_info *be)
 			goto err;
 		}
 
+		queue->credit_bytes = credit_bytes;
 		queue->remaining_credit = credit_bytes;
+		queue->credit_usec = credit_usec;
 
 		err = connect_rings(be, queue);
 		if (err) {
@@ -886,9 +893,15 @@ static int read_xenbus_vif_flags(struct backend_info *be)
 		return -EOPNOTSUPP;
 
 	if (xenbus_scanf(XBT_NIL, dev->otherend,
-			 "feature-rx-notify", "%d", &val) < 0 || val == 0) {
-		xenbus_dev_fatal(dev, -EINVAL, "feature-rx-notify is mandatory");
-		return -EINVAL;
+			 "feature-rx-notify", "%d", &val) < 0)
+		val = 0;
+	if (!val) {
+		/* - Reduce drain timeout to poll more frequently for
+		 *   Rx requests.
+		 * - Disable Rx stall detection.
+		 */
+		be->vif->drain_timeout = msecs_to_jiffies(30);
+		be->vif->stall_timeout = 0;
 	}
 
 	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-sg",
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index ece8d1804d1..2b0b4e62f17 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -627,6 +627,9 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 				    slots, skb->len);
 		if (skb_linearize(skb))
 			goto drop;
+		data = skb->data;
+		offset = offset_in_page(data);
+		len = skb_headlen(skb);
 	}
 
 	spin_lock_irqsave(&queue->tx_lock, flags);
@@ -1095,8 +1098,7 @@ err:
 
 static int xennet_change_mtu(struct net_device *dev, int mtu)
 {
-	int max = xennet_can_sg(dev) ?
-		XEN_NETIF_MAX_TX_SIZE - MAX_TCP_HEADER : ETH_DATA_LEN;
+	int max = xennet_can_sg(dev) ? XEN_NETIF_MAX_TX_SIZE : ETH_DATA_LEN;
 
 	if (mtu > max)
 		return -EINVAL;
@@ -1350,8 +1352,6 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 	netdev->ethtool_ops = &xennet_ethtool_ops;
 	SET_NETDEV_DEV(netdev, &dev->dev);
 
-	netif_set_gso_max_size(netdev, XEN_NETIF_MAX_TX_SIZE - MAX_TCP_HEADER);
-
 	np->netdev = netdev;
 
 	netif_carrier_off(netdev);
diff --git a/drivers/nfc/st21nfcb/i2c.c b/drivers/nfc/st21nfcb/i2c.c
index c5d2427a3db..157259d5fa2 100644
--- a/drivers/nfc/st21nfcb/i2c.c
+++ b/drivers/nfc/st21nfcb/i2c.c
@@ -90,11 +90,6 @@ static void st21nfcb_nci_i2c_disable(void *phy_id)
 	gpio_set_value(phy->gpio_reset, 1);
 }
 
-static void st21nfcb_nci_remove_header(struct sk_buff *skb)
-{
-	skb_pull(skb, ST21NFCB_FRAME_HEADROOM);
-}
-
 /*
  * Writing a frame must not return the number of written bytes.
  * It must return either zero for success, or <0 for error.
@@ -112,7 +107,7 @@ static int st21nfcb_nci_i2c_write(void *phy_id, struct sk_buff *skb)
 		return phy->ndlc->hard_fault;
 
 	r = i2c_master_send(client, skb->data, skb->len);
-	if (r == -EREMOTEIO) {  /* Retry, chip was in standby */
+	if (r < 0) {  /* Retry, chip was in standby */
 		usleep_range(1000, 4000);
 		r = i2c_master_send(client, skb->data, skb->len);
 	}
@@ -124,8 +119,6 @@ static int st21nfcb_nci_i2c_write(void *phy_id, struct sk_buff *skb)
 			r = 0;
 	}
 
-	st21nfcb_nci_remove_header(skb);
-
 	return r;
 }
 
@@ -151,7 +144,7 @@ static int st21nfcb_nci_i2c_read(struct st21nfcb_i2c_phy *phy,
 	struct i2c_client *client = phy->i2c_dev;
 
 	r = i2c_master_recv(client, buf, ST21NFCB_NCI_I2C_MIN_SIZE);
-	if (r == -EREMOTEIO) {  /* Retry, chip was in standby */
+	if (r < 0) {  /* Retry, chip was in standby */
 		usleep_range(1000, 4000);
 		r = i2c_master_recv(client, buf, ST21NFCB_NCI_I2C_MIN_SIZE);
 	}
@@ -395,9 +388,6 @@ static int st21nfcb_nci_i2c_remove(struct i2c_client *client)
 
 	ndlc_remove(phy->ndlc);
 
-	if (phy->powered)
-		st21nfcb_nci_i2c_disable(phy);
-
 	return 0;
 }
 
diff --git a/drivers/nfc/st21nfcb/st21nfcb.c b/drivers/nfc/st21nfcb/st21nfcb.c
index ea63d587783..28b39143a83 100644
--- a/drivers/nfc/st21nfcb/st21nfcb.c
+++ b/drivers/nfc/st21nfcb/st21nfcb.c
@@ -122,11 +122,8 @@ EXPORT_SYMBOL_GPL(st21nfcb_nci_probe);
 
 void st21nfcb_nci_remove(struct nci_dev *ndev)
 {
-	struct st21nfcb_nci_info *info = nci_get_drvdata(ndev);
-
 	nci_unregister_device(ndev);
 	nci_free_device(ndev);
-	kfree(info);
 }
 EXPORT_SYMBOL_GPL(st21nfcb_nci_remove);
 
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 06af494184d..1dba1a9c1fc 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -450,12 +450,17 @@ static struct of_bus *of_match_bus(struct device_node *np)
 	return NULL;
 }
 
-static int of_empty_ranges_quirk(void)
+static int of_empty_ranges_quirk(struct device_node *np)
 {
 	if (IS_ENABLED(CONFIG_PPC)) {
-		/* To save cycles, we cache the result */
+		/* To save cycles, we cache the result for global "Mac" setting */
 		static int quirk_state = -1;
 
+		/* PA-SEMI sdc DT bug */
+		if (of_device_is_compatible(np, "1682m-sdc"))
+			return true;
+
+		/* Make quirk cached */
 		if (quirk_state < 0)
 			quirk_state =
 				of_machine_is_compatible("Power Macintosh") ||
@@ -490,7 +495,7 @@ static int of_translate_one(struct device_node *parent, struct of_bus *bus,
 	 * This code is only enabled on powerpc. --gcl
 	 */
 	ranges = of_get_property(parent, rprop, &rlen);
-	if (ranges == NULL && !of_empty_ranges_quirk()) {
+	if (ranges == NULL && !of_empty_ranges_quirk(parent)) {
 		pr_err("OF: no ranges; cannot translate\n");
 		return 1;
 	}
@@ -707,7 +712,7 @@ int __weak pci_register_io_range(phys_addr_t addr, resource_size_t size)
 	}
 
 	/* add the range to the list */
-	range = kzalloc(sizeof(*range), GFP_KERNEL);
+	range = kzalloc(sizeof(*range), GFP_ATOMIC);
 	if (!range) {
 		err = -ENOMEM;
 		goto end_register;
@@ -760,7 +765,7 @@ unsigned long __weak pci_address_to_pio(phys_addr_t address)
 	spin_lock(&io_range_lock);
 	list_for_each_entry(res, &io_range_list, list) {
 		if (address >= res->start && address < res->start + res->size) {
-			addr = res->start - address + offset;
+			addr = address - res->start + offset;
 			break;
 		}
 		offset += res->size;
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 3823edf2d01..469d2b7f47e 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -88,7 +88,7 @@ EXPORT_SYMBOL(of_n_size_cells);
 #ifdef CONFIG_NUMA
 int __weak of_node_to_nid(struct device_node *np)
 {
-	return numa_node_id();
+	return NUMA_NO_NODE;
 }
 #endif
 
@@ -1250,6 +1250,39 @@ int of_property_read_u64(const struct device_node *np, const char *propname,
 EXPORT_SYMBOL_GPL(of_property_read_u64);
 
 /**
+ * of_property_read_u64_array - Find and read an array of 64 bit integers
+ * from a property.
+ *
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ * @out_values:	pointer to return value, modified only if return value is 0.
+ * @sz:		number of array elements to read
+ *
+ * Search for a property in a device node and read 64-bit value(s) from
+ * it. Returns 0 on success, -EINVAL if the property does not exist,
+ * -ENODATA if property does not have a value, and -EOVERFLOW if the
+ * property data isn't large enough.
+ *
+ * The out_values is modified only if a valid u64 value can be decoded.
+ */
+int of_property_read_u64_array(const struct device_node *np,
+			       const char *propname, u64 *out_values,
+			       size_t sz)
+{
+	const __be32 *val = of_find_property_value_of_size(np, propname,
+						(sz * sizeof(*out_values)));
+
+	if (IS_ERR(val))
+		return PTR_ERR(val);
+
+	while (sz--) {
+		*out_values++ = of_read_number(val, 2);
+		val += 2;
+	}
+	return 0;
+}
+
+/**
  * of_property_read_string - Find and read a string from a property
  * @np:		device node from which the property value is to be read.
  * @propname:	name of the property to be searched.
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index d134710de96..821f6b591ce 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -885,36 +885,66 @@ int __init early_init_dt_scan_memory(unsigned long node, const char *uname,
 	return 0;
 }
 
+/*
+ * Convert configs to something easy to use in C code
+ */
+#if defined(CONFIG_CMDLINE_FORCE)
+static const int overwrite_incoming_cmdline = 1;
+static const int read_dt_cmdline;
+static const int concat_cmdline;
+#elif defined(CONFIG_CMDLINE_EXTEND)
+static const int overwrite_incoming_cmdline;
+static const int read_dt_cmdline = 1;
+static const int concat_cmdline = 1;
+#else /* CMDLINE_FROM_BOOTLOADER */
+static const int overwrite_incoming_cmdline;
+static const int read_dt_cmdline = 1;
+static const int concat_cmdline;
+#endif
+
+#ifdef CONFIG_CMDLINE
+static const char *config_cmdline = CONFIG_CMDLINE;
+#else
+static const char *config_cmdline = "";
+#endif
+
 int __init early_init_dt_scan_chosen(unsigned long node, const char *uname,
 				     int depth, void *data)
 {
-	int l;
-	const char *p;
+	int l = 0;
+	const char *p = NULL;
+	char *cmdline = data;
 
 	pr_debug("search \"chosen\", depth: %d, uname: %s\n", depth, uname);
 
-	if (depth != 1 || !data ||
+	if (depth != 1 || !cmdline ||
 	    (strcmp(uname, "chosen") != 0 && strcmp(uname, "chosen@0") != 0))
 		return 0;
 
 	early_init_dt_check_for_initrd(node);
 
-	/* Retrieve command line */
-	p = of_get_flat_dt_prop(node, "bootargs", &l);
-	if (p != NULL && l > 0)
-		strlcpy(data, p, min((int)l, COMMAND_LINE_SIZE));
-
-	/*
-	 * CONFIG_CMDLINE is meant to be a default in case nothing else
-	 * managed to set the command line, unless CONFIG_CMDLINE_FORCE
-	 * is set in which case we override whatever was found earlier.
-	 */
-#ifdef CONFIG_CMDLINE
-#ifndef CONFIG_CMDLINE_FORCE
-	if (!((char *)data)[0])
-#endif
-		strlcpy(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#endif /* CONFIG_CMDLINE */
+	/* Put CONFIG_CMDLINE in if forced or if data had nothing in it to start */
+	if (overwrite_incoming_cmdline || !cmdline[0])
+		strlcpy(cmdline, config_cmdline, COMMAND_LINE_SIZE);
+
+	/* Retrieve command line unless forcing */
+	if (read_dt_cmdline)
+		p = of_get_flat_dt_prop(node, "bootargs", &l);
+
+	if (p != NULL && l > 0) {
+		if (concat_cmdline) {
+			int cmdline_len;
+			int copy_len;
+			strlcat(cmdline, " ", COMMAND_LINE_SIZE);
+			cmdline_len = strlen(cmdline);
+			copy_len = COMMAND_LINE_SIZE - cmdline_len - 1;
+			copy_len = min((int)l, copy_len);
+			strncpy(cmdline + cmdline_len, p, copy_len);
+			cmdline[cmdline_len + copy_len] = '\0';
+		} else {
+			strlcpy(cmdline, p, min((int)l, COMMAND_LINE_SIZE));
+		}
+	}
 
 	pr_debug("Command line is: %s\n", (char*)data);
 
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 1471e0a223a..b97363adca0 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -290,7 +290,7 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
 	struct device_node *p;
 	const __be32 *intspec, *tmp, *addr;
 	u32 intsize, intlen;
-	int i, res = -EINVAL;
+	int i, res;
 
 	pr_debug("of_irq_parse_one: dev=%s, index=%d\n", of_node_full_name(device), index);
 
@@ -323,15 +323,19 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
 
 	/* Get size of interrupt specifier */
 	tmp = of_get_property(p, "#interrupt-cells", NULL);
-	if (tmp == NULL)
+	if (tmp == NULL) {
+		res = -EINVAL;
 		goto out;
+	}
 	intsize = be32_to_cpu(*tmp);
 
 	pr_debug(" intsize=%d intlen=%d\n", intsize, intlen);
 
 	/* Check index */
-	if ((index + 1) * intsize > intlen)
+	if ((index + 1) * intsize > intlen) {
+		res = -EINVAL;
 		goto out;
+	}
 
 	/* Copy intspec into irq structure */
 	intspec += index * intsize;
diff --git a/drivers/of/of_pci.c b/drivers/of/of_pci.c
index 8882b467be9..ecc5fa5640d 100644
--- a/drivers/of/of_pci.c
+++ b/drivers/of/of_pci.c
@@ -140,6 +140,7 @@ int of_pci_get_host_bridge_resources(struct device_node *dev,
 			unsigned char busno, unsigned char bus_max,
 			struct list_head *resources, resource_size_t *io_base)
 {
+	struct pci_host_bridge_window *window;
 	struct resource *res;
 	struct resource *bus_range;
 	struct of_pci_range range;
@@ -225,7 +226,10 @@ int of_pci_get_host_bridge_resources(struct device_node *dev,
 conversion_failed:
 	kfree(res);
 parse_failed:
+	list_for_each_entry(window, resources, list)
+		kfree(window->res);
 	pci_free_resource_list(resources);
+	kfree(bus_range);
 	return err;
 }
 EXPORT_SYMBOL_GPL(of_pci_get_host_bridge_resources);
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 73aef51a28f..8fb16188cd8 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -228,6 +228,49 @@ int pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res,
 }
 EXPORT_SYMBOL(pci_bus_alloc_resource);
 
+/*
+ * The @idx resource of @dev should be a PCI-PCI bridge window.  If this
+ * resource fits inside a window of an upstream bridge, do nothing.  If it
+ * overlaps an upstream window but extends outside it, clip the resource so
+ * it fits completely inside.
+ */
+bool pci_bus_clip_resource(struct pci_dev *dev, int idx)
+{
+	struct pci_bus *bus = dev->bus;
+	struct resource *res = &dev->resource[idx];
+	struct resource orig_res = *res;
+	struct resource *r;
+	int i;
+
+	pci_bus_for_each_resource(bus, r, i) {
+		resource_size_t start, end;
+
+		if (!r)
+			continue;
+
+		if (resource_type(res) != resource_type(r))
+			continue;
+
+		start = max(r->start, res->start);
+		end = min(r->end, res->end);
+
+		if (start > end)
+			continue;	/* no overlap */
+
+		if (res->start == start && res->end == end)
+			return false;	/* no change */
+
+		res->start = start;
+		res->end = end;
+		dev_printk(KERN_DEBUG, &dev->dev, "%pR clipped to %pR\n",
+				 &orig_res, res);
+
+		return true;
+	}
+
+	return false;
+}
+
 void __weak pcibios_resource_survey_bus(struct pci_bus *bus) { }
 
 /**
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index dfed00aa3ac..f69b0d0a5ee 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -283,6 +283,9 @@ static int dw_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev,
 	struct msi_msg msg;
 	struct pcie_port *pp = sys_to_pcie(pdev->bus->sysdata);
 
+	if (desc->msi_attrib.is_msix)
+		return -EINVAL;
+
 	irq = assign_irq(1, desc, &pos);
 	if (irq < 0)
 		return irq;
@@ -339,7 +342,7 @@ static const struct irq_domain_ops msi_domain_ops = {
 	.map = dw_pcie_msi_map,
 };
 
-int __init dw_pcie_host_init(struct pcie_port *pp)
+int dw_pcie_host_init(struct pcie_port *pp)
 {
 	struct device_node *np = pp->dev->of_node;
 	struct platform_device *pdev = to_platform_device(pp->dev);
diff --git a/drivers/pci/host/pcie-spear13xx.c b/drivers/pci/host/pcie-spear13xx.c
index 85f594e1708..b4ba6ff56cf 100644
--- a/drivers/pci/host/pcie-spear13xx.c
+++ b/drivers/pci/host/pcie-spear13xx.c
@@ -298,7 +298,7 @@ static int add_pcie_port(struct pcie_port *pp, struct platform_device *pdev)
 	return 0;
 }
 
-static int __init spear13xx_pcie_probe(struct platform_device *pdev)
+static int spear13xx_pcie_probe(struct platform_device *pdev)
 {
 	struct spear13xx_pcie *spear13xx_pcie;
 	struct pcie_port *pp;
@@ -371,7 +371,7 @@ static const struct of_device_id spear13xx_pcie_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, spear13xx_pcie_of_match);
 
-static struct platform_driver spear13xx_pcie_driver __initdata = {
+static struct platform_driver spear13xx_pcie_driver = {
 	.probe		= spear13xx_pcie_probe,
 	.driver = {
 		.name	= "spear-pcie",
diff --git a/drivers/pci/hotplug/cpci_hotplug_pci.c b/drivers/pci/hotplug/cpci_hotplug_pci.c
index 7d48ecae669..788db48dbba 100644
--- a/drivers/pci/hotplug/cpci_hotplug_pci.c
+++ b/drivers/pci/hotplug/cpci_hotplug_pci.c
@@ -286,11 +286,12 @@ int cpci_configure_slot(struct slot *slot)
 	}
 	parent = slot->dev->bus;
 
-	list_for_each_entry(dev, &parent->devices, bus_list)
+	list_for_each_entry(dev, &parent->devices, bus_list) {
 		if (PCI_SLOT(dev->devfn) != PCI_SLOT(slot->devfn))
 			continue;
 		if (pci_is_bridge(dev))
 			pci_hp_add_bridge(dev);
+	}
 
 
 	pci_assign_unassigned_bridge_resources(parent->self);
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 0ebf754fc17..6d6868811e5 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -176,20 +176,17 @@ static void pcie_wait_cmd(struct controller *ctrl)
 			  jiffies_to_msecs(jiffies - ctrl->cmd_started));
 }
 
-/**
- * pcie_write_cmd - Issue controller command
- * @ctrl: controller to which the command is issued
- * @cmd:  command value written to slot control register
- * @mask: bitmask of slot control register to be modified
- */
-static void pcie_write_cmd(struct controller *ctrl, u16 cmd, u16 mask)
+static void pcie_do_write_cmd(struct controller *ctrl, u16 cmd,
+			      u16 mask, bool wait)
 {
 	struct pci_dev *pdev = ctrl_dev(ctrl);
 	u16 slot_ctrl;
 
 	mutex_lock(&ctrl->ctrl_lock);
 
-	/* Wait for any previous command that might still be in progress */
+	/*
+	 * Always wait for any previous command that might still be in progress
+	 */
 	pcie_wait_cmd(ctrl);
 
 	pcie_capability_read_word(pdev, PCI_EXP_SLTCTL, &slot_ctrl);
@@ -201,9 +198,33 @@ static void pcie_write_cmd(struct controller *ctrl, u16 cmd, u16 mask)
 	ctrl->cmd_started = jiffies;
 	ctrl->slot_ctrl = slot_ctrl;
 
+	/*
+	 * Optionally wait for the hardware to be ready for a new command,
+	 * indicating completion of the above issued command.
+	 */
+	if (wait)
+		pcie_wait_cmd(ctrl);
+
 	mutex_unlock(&ctrl->ctrl_lock);
 }
 
+/**
+ * pcie_write_cmd - Issue controller command
+ * @ctrl: controller to which the command is issued
+ * @cmd:  command value written to slot control register
+ * @mask: bitmask of slot control register to be modified
+ */
+static void pcie_write_cmd(struct controller *ctrl, u16 cmd, u16 mask)
+{
+	pcie_do_write_cmd(ctrl, cmd, mask, true);
+}
+
+/* Same as above without waiting for the hardware to latch */
+static void pcie_write_cmd_nowait(struct controller *ctrl, u16 cmd, u16 mask)
+{
+	pcie_do_write_cmd(ctrl, cmd, mask, false);
+}
+
 bool pciehp_check_link_active(struct controller *ctrl)
 {
 	struct pci_dev *pdev = ctrl_dev(ctrl);
@@ -422,7 +443,7 @@ void pciehp_set_attention_status(struct slot *slot, u8 value)
 	default:
 		return;
 	}
-	pcie_write_cmd(ctrl, slot_cmd, PCI_EXP_SLTCTL_AIC);
+	pcie_write_cmd_nowait(ctrl, slot_cmd, PCI_EXP_SLTCTL_AIC);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_cmd);
 }
@@ -434,7 +455,8 @@ void pciehp_green_led_on(struct slot *slot)
 	if (!PWR_LED(ctrl))
 		return;
 
-	pcie_write_cmd(ctrl, PCI_EXP_SLTCTL_PWR_IND_ON, PCI_EXP_SLTCTL_PIC);
+	pcie_write_cmd_nowait(ctrl, PCI_EXP_SLTCTL_PWR_IND_ON,
+			      PCI_EXP_SLTCTL_PIC);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL,
 		 PCI_EXP_SLTCTL_PWR_IND_ON);
@@ -447,7 +469,8 @@ void pciehp_green_led_off(struct slot *slot)
 	if (!PWR_LED(ctrl))
 		return;
 
-	pcie_write_cmd(ctrl, PCI_EXP_SLTCTL_PWR_IND_OFF, PCI_EXP_SLTCTL_PIC);
+	pcie_write_cmd_nowait(ctrl, PCI_EXP_SLTCTL_PWR_IND_OFF,
+			      PCI_EXP_SLTCTL_PIC);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL,
 		 PCI_EXP_SLTCTL_PWR_IND_OFF);
@@ -460,7 +483,8 @@ void pciehp_green_led_blink(struct slot *slot)
 	if (!PWR_LED(ctrl))
 		return;
 
-	pcie_write_cmd(ctrl, PCI_EXP_SLTCTL_PWR_IND_BLINK, PCI_EXP_SLTCTL_PIC);
+	pcie_write_cmd_nowait(ctrl, PCI_EXP_SLTCTL_PWR_IND_BLINK,
+			      PCI_EXP_SLTCTL_PIC);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL,
 		 PCI_EXP_SLTCTL_PWR_IND_BLINK);
@@ -613,7 +637,7 @@ void pcie_enable_notification(struct controller *ctrl)
 		PCI_EXP_SLTCTL_HPIE | PCI_EXP_SLTCTL_CCIE |
 		PCI_EXP_SLTCTL_DLLSCE);
 
-	pcie_write_cmd(ctrl, cmd, mask);
+	pcie_write_cmd_nowait(ctrl, cmd, mask);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, cmd);
 }
@@ -664,7 +688,7 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 	pci_reset_bridge_secondary_bus(ctrl->pcie->port);
 
 	pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, stat_mask);
-	pcie_write_cmd(ctrl, ctrl_mask, ctrl_mask);
+	pcie_write_cmd_nowait(ctrl, ctrl_mask, ctrl_mask);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, ctrl_mask);
 	if (pciehp_poll_mode)
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 6ebf8edc5f3..09499548d42 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -248,6 +248,9 @@ int pci_get_hp_params(struct pci_dev *dev, struct hotplug_params *hpp)
 	acpi_handle handle, phandle;
 	struct pci_bus *pbus;
 
+	if (acpi_pci_disabled)
+		return -ENODEV;
+
 	handle = NULL;
 	for (pbus = dev->bus; pbus; pbus = pbus->parent) {
 		handle = acpi_pci_get_bridge_handle(pbus);
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 2b3c89425bb..b720e7816a7 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -1389,7 +1389,7 @@ static int pci_uevent(struct device *dev, struct kobj_uevent_env *env)
 	if (add_uevent_var(env, "PCI_SLOT_NAME=%s", pci_name(pdev)))
 		return -ENOMEM;
 
-	if (add_uevent_var(env, "MODALIAS=pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02x",
+	if (add_uevent_var(env, "MODALIAS=pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02X",
 			   pdev->vendor, pdev->device,
 			   pdev->subsystem_vendor, pdev->subsystem_device,
 			   (u8)(pdev->class >> 16), (u8)(pdev->class >> 8),
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 2c6643fdc0c..eb1543841e3 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -515,7 +515,8 @@ static ssize_t driver_override_store(struct device *dev,
 	struct pci_dev *pdev = to_pci_dev(dev);
 	char *driver_override, *old = pdev->driver_override, *cp;
 
-	if (count > PATH_MAX)
+	/* We need to keep extra room for a newline */
+	if (count >= (PAGE_SIZE - 1))
 		return -EINVAL;
 
 	driver_override = kstrndup(buf, count, GFP_KERNEL);
@@ -543,7 +544,7 @@ static ssize_t driver_override_show(struct device *dev,
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 
-	return sprintf(buf, "%s\n", pdev->driver_override);
+	return snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override);
 }
 static DEVICE_ATTR_RW(driver_override);
 
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 625a4ace10b..ff7af33f235 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3280,7 +3280,8 @@ static int pci_parent_bus_reset(struct pci_dev *dev, int probe)
 {
 	struct pci_dev *pdev;
 
-	if (pci_is_root_bus(dev->bus) || dev->subordinate || !dev->bus->self)
+	if (pci_is_root_bus(dev->bus) || dev->subordinate ||
+	    !dev->bus->self || dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET)
 		return -ENOTTY;
 
 	list_for_each_entry(pdev, &dev->bus->devices, bus_list)
@@ -3314,7 +3315,8 @@ static int pci_dev_reset_slot_function(struct pci_dev *dev, int probe)
 {
 	struct pci_dev *pdev;
 
-	if (dev->subordinate || !dev->slot)
+	if (dev->subordinate || !dev->slot ||
+	    dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET)
 		return -ENOTTY;
 
 	list_for_each_entry(pdev, &dev->bus->devices, bus_list)
@@ -3566,6 +3568,20 @@ int pci_try_reset_function(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_try_reset_function);
 
+/* Do any devices on or below this bus prevent a bus reset? */
+static bool pci_bus_resetable(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET ||
+		    (dev->subordinate && !pci_bus_resetable(dev->subordinate)))
+			return false;
+	}
+
+	return true;
+}
+
 /* Lock devices from the top of the tree down */
 static void pci_bus_lock(struct pci_bus *bus)
 {
@@ -3616,6 +3632,22 @@ unlock:
 	return 0;
 }
 
+/* Do any devices on or below this slot prevent a bus reset? */
+static bool pci_slot_resetable(struct pci_slot *slot)
+{
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &slot->bus->devices, bus_list) {
+		if (!dev->slot || dev->slot != slot)
+			continue;
+		if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET ||
+		    (dev->subordinate && !pci_bus_resetable(dev->subordinate)))
+			return false;
+	}
+
+	return true;
+}
+
 /* Lock devices from the top of the tree down */
 static void pci_slot_lock(struct pci_slot *slot)
 {
@@ -3737,7 +3769,7 @@ static int pci_slot_reset(struct pci_slot *slot, int probe)
 {
 	int rc;
 
-	if (!slot)
+	if (!slot || !pci_slot_resetable(slot))
 		return -ENOTTY;
 
 	if (!probe)
@@ -3829,7 +3861,7 @@ EXPORT_SYMBOL_GPL(pci_try_reset_slot);
 
 static int pci_bus_reset(struct pci_bus *bus, int probe)
 {
-	if (!bus->self)
+	if (!bus->self || !pci_bus_resetable(bus))
 		return -ENOTTY;
 
 	if (probe)
@@ -4267,6 +4299,17 @@ bool pci_device_is_present(struct pci_dev *pdev)
 }
 EXPORT_SYMBOL_GPL(pci_device_is_present);
 
+void pci_ignore_hotplug(struct pci_dev *dev)
+{
+	struct pci_dev *bridge = dev->bus->self;
+
+	dev->ignore_hotplug = 1;
+	/* Propagate the "ignore hotplug" setting to the parent bridge. */
+	if (bridge)
+		bridge->ignore_hotplug = 1;
+}
+EXPORT_SYMBOL_GPL(pci_ignore_hotplug);
+
 #define RESOURCE_ALIGNMENT_PARAM_SIZE COMMAND_LINE_SIZE
 static char resource_alignment_param[RESOURCE_ALIGNMENT_PARAM_SIZE] = {0};
 static DEFINE_SPINLOCK(resource_alignment_lock);
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 4a3902d8e6f..b5defca8679 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -208,6 +208,7 @@ void __pci_bus_size_bridges(struct pci_bus *bus,
 void __pci_bus_assign_resources(const struct pci_bus *bus,
 				struct list_head *realloc_head,
 				struct list_head *fail_head);
+bool pci_bus_clip_resource(struct pci_dev *dev, int idx);
 
 /**
  * pci_ari_enabled - query ARI forwarding status
diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c
index c6849d9e86c..167fe411ce2 100644
--- a/drivers/pci/pcie/aer/aerdrv_errprint.c
+++ b/drivers/pci/pcie/aer/aerdrv_errprint.c
@@ -132,16 +132,8 @@ static const char *aer_agent_string[] = {
 static void __print_tlp_header(struct pci_dev *dev,
 			       struct aer_header_log_regs *t)
 {
-	unsigned char *tlp = (unsigned char *)&t;
-
-	dev_err(&dev->dev, "  TLP Header:"
-		" %02x%02x%02x%02x %02x%02x%02x%02x"
-		" %02x%02x%02x%02x %02x%02x%02x%02x\n",
-		*(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp,
-		*(tlp + 7), *(tlp + 6), *(tlp + 5), *(tlp + 4),
-		*(tlp + 11), *(tlp + 10), *(tlp + 9),
-		*(tlp + 8), *(tlp + 15), *(tlp + 14),
-		*(tlp + 13), *(tlp + 12));
+	dev_err(&dev->dev, "  TLP Header: %08x %08x %08x %08x\n",
+		t->dw0, t->dw1, t->dw2, t->dw3);
 }
 
 static void __aer_print_error(struct pci_dev *dev,
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index c8ca98c2b48..3010ffc9029 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -216,14 +216,17 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 		res->flags |= IORESOURCE_SIZEALIGN;
 		if (res->flags & IORESOURCE_IO) {
 			l &= PCI_BASE_ADDRESS_IO_MASK;
+			sz &= PCI_BASE_ADDRESS_IO_MASK;
 			mask = PCI_BASE_ADDRESS_IO_MASK & (u32) IO_SPACE_LIMIT;
 		} else {
 			l &= PCI_BASE_ADDRESS_MEM_MASK;
+			sz &= PCI_BASE_ADDRESS_MEM_MASK;
 			mask = (u32)PCI_BASE_ADDRESS_MEM_MASK;
 		}
 	} else {
 		res->flags |= (l & IORESOURCE_ROM_ENABLE);
 		l &= PCI_ROM_ADDRESS_MASK;
+		sz &= PCI_ROM_ADDRESS_MASK;
 		mask = (u32)PCI_ROM_ADDRESS_MASK;
 	}
 
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 90acb32c85b..04ea682ab2a 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -324,18 +324,52 @@ static void quirk_s3_64M(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_S3,	PCI_DEVICE_ID_S3_868,		quirk_s3_64M);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_S3,	PCI_DEVICE_ID_S3_968,		quirk_s3_64M);
 
+static void quirk_io(struct pci_dev *dev, int pos, unsigned size,
+		     const char *name)
+{
+	u32 region;
+	struct pci_bus_region bus_region;
+	struct resource *res = dev->resource + pos;
+
+	pci_read_config_dword(dev, PCI_BASE_ADDRESS_0 + (pos << 2), &region);
+
+	if (!region)
+		return;
+
+	res->name = pci_name(dev);
+	res->flags = region & ~PCI_BASE_ADDRESS_IO_MASK;
+	res->flags |=
+		(IORESOURCE_IO | IORESOURCE_PCI_FIXED | IORESOURCE_SIZEALIGN);
+	region &= ~(size - 1);
+
+	/* Convert from PCI bus to resource space */
+	bus_region.start = region;
+	bus_region.end = region + size - 1;
+	pcibios_bus_to_resource(dev->bus, res, &bus_region);
+
+	dev_info(&dev->dev, FW_BUG "%s quirk: reg 0x%x: %pR\n",
+		 name, PCI_BASE_ADDRESS_0 + (pos << 2), res);
+}
+
 /*
  * Some CS5536 BIOSes (for example, the Soekris NET5501 board w/ comBIOS
  * ver. 1.33  20070103) don't set the correct ISA PCI region header info.
  * BAR0 should be 8 bytes; instead, it may be set to something like 8k
  * (which conflicts w/ BAR1's memory range).
+ *
+ * CS553x's ISA PCI BARs may also be read-only (ref:
+ * https://bugzilla.kernel.org/show_bug.cgi?id=85991 - Comment #4 forward).
  */
 static void quirk_cs5536_vsa(struct pci_dev *dev)
 {
+	static char *name = "CS5536 ISA bridge";
+
 	if (pci_resource_len(dev, 0) != 8) {
-		struct resource *res = &dev->resource[0];
-		res->end = res->start + 8 - 1;
-		dev_info(&dev->dev, "CS5536 ISA bridge bug detected (incorrect header); workaround applied\n");
+		quirk_io(dev, 0,   8, name);	/* SMB */
+		quirk_io(dev, 1, 256, name);	/* GPIO */
+		quirk_io(dev, 2,  64, name);	/* MFGPT */
+		dev_info(&dev->dev, "%s bug detected (incorrect header); workaround applied\n",
+			 name);
 	}
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CS5536_ISA, quirk_cs5536_vsa);
@@ -3008,6 +3042,20 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_REALTEK, 0x8169,
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MELLANOX, PCI_ANY_ID,
 			 quirk_broken_intx_masking);
 
+static void quirk_no_bus_reset(struct pci_dev *dev)
+{
+	dev->dev_flags |= PCI_DEV_FLAGS_NO_BUS_RESET;
+}
+
+/*
+ * Atheros AR93xx chips do not behave after a bus reset.  The device will
+ * throw a Link Down error on AER-capable systems and regardless of AER,
+ * config space of the device is never accessible again and typically
+ * causes the system to hang or reset when access is attempted.
+ * http://www.spinics.net/lists/linux-pci/msg34797.html
+ */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x0030, quirk_no_bus_reset);
+
 #ifdef CONFIG_ACPI
 /*
  * Apple: Shutdown Cactus Ridge Thunderbolt controller.
diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c
index f955edb9bea..eb0ad530dc4 100644
--- a/drivers/pci/rom.c
+++ b/drivers/pci/rom.c
@@ -71,6 +71,7 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size)
 {
 	void __iomem *image;
 	int last_image;
+	unsigned length;
 
 	image = rom;
 	do {
@@ -93,9 +94,9 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size)
 		if (readb(pds + 3) != 'R')
 			break;
 		last_image = readb(pds + 21) & 0x80;
-		/* this length is reliable */
-		image += readw(pds + 16) * 512;
-	} while (!last_image);
+		length = readw(pds + 16);
+		image += length * 512;
+	} while (length && !last_image);
 
 	/* never return a size larger than the PCI resource window */
 	/* there are known ROMs that get the size wrong */
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 0482235eee9..e3e17f3c0f0 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -530,9 +530,8 @@ EXPORT_SYMBOL(pci_setup_cardbus);
    config space writes, so it's quite possible that an I/O window of
    the bridge will have some undesirable address (e.g. 0) after the
    first write. Ditto 64-bit prefetchable MMIO.  */
-static void pci_setup_bridge_io(struct pci_bus *bus)
+static void pci_setup_bridge_io(struct pci_dev *bridge)
 {
-	struct pci_dev *bridge = bus->self;
 	struct resource *res;
 	struct pci_bus_region region;
 	unsigned long io_mask;
@@ -545,7 +544,7 @@ static void pci_setup_bridge_io(struct pci_bus *bus)
 		io_mask = PCI_IO_1K_RANGE_MASK;
 
 	/* Set up the top and bottom of the PCI I/O segment for this bus. */
-	res = bus->resource[0];
+	res = &bridge->resource[PCI_BRIDGE_RESOURCES + 0];
 	pcibios_resource_to_bus(bridge->bus, &region, res);
 	if (res->flags & IORESOURCE_IO) {
 		pci_read_config_word(bridge, PCI_IO_BASE, &l);
@@ -568,15 +567,14 @@ static void pci_setup_bridge_io(struct pci_bus *bus)
 	pci_write_config_dword(bridge, PCI_IO_BASE_UPPER16, io_upper16);
 }
 
-static void pci_setup_bridge_mmio(struct pci_bus *bus)
+static void pci_setup_bridge_mmio(struct pci_dev *bridge)
 {
-	struct pci_dev *bridge = bus->self;
 	struct resource *res;
 	struct pci_bus_region region;
 	u32 l;
 
 	/* Set up the top and bottom of the PCI Memory segment for this bus. */
-	res = bus->resource[1];
+	res = &bridge->resource[PCI_BRIDGE_RESOURCES + 1];
 	pcibios_resource_to_bus(bridge->bus, &region, res);
 	if (res->flags & IORESOURCE_MEM) {
 		l = (region.start >> 16) & 0xfff0;
@@ -588,9 +586,8 @@ static void pci_setup_bridge_mmio(struct pci_bus *bus)
 	pci_write_config_dword(bridge, PCI_MEMORY_BASE, l);
 }
 
-static void pci_setup_bridge_mmio_pref(struct pci_bus *bus)
+static void pci_setup_bridge_mmio_pref(struct pci_dev *bridge)
 {
-	struct pci_dev *bridge = bus->self;
 	struct resource *res;
 	struct pci_bus_region region;
 	u32 l, bu, lu;
@@ -602,7 +599,7 @@ static void pci_setup_bridge_mmio_pref(struct pci_bus *bus)
 
 	/* Set up PREF base/limit. */
 	bu = lu = 0;
-	res = bus->resource[2];
+	res = &bridge->resource[PCI_BRIDGE_RESOURCES + 2];
 	pcibios_resource_to_bus(bridge->bus, &region, res);
 	if (res->flags & IORESOURCE_PREFETCH) {
 		l = (region.start >> 16) & 0xfff0;
@@ -630,13 +627,13 @@ static void __pci_setup_bridge(struct pci_bus *bus, unsigned long type)
 		 &bus->busn_res);
 
 	if (type & IORESOURCE_IO)
-		pci_setup_bridge_io(bus);
+		pci_setup_bridge_io(bridge);
 
 	if (type & IORESOURCE_MEM)
-		pci_setup_bridge_mmio(bus);
+		pci_setup_bridge_mmio(bridge);
 
 	if (type & IORESOURCE_PREFETCH)
-		pci_setup_bridge_mmio_pref(bus);
+		pci_setup_bridge_mmio_pref(bridge);
 
 	pci_write_config_word(bridge, PCI_BRIDGE_CONTROL, bus->bridge_ctl);
 }
@@ -649,6 +646,41 @@ void pci_setup_bridge(struct pci_bus *bus)
 	__pci_setup_bridge(bus, type);
 }
 
+
+int pci_claim_bridge_resource(struct pci_dev *bridge, int i)
+{
+	if (i < PCI_BRIDGE_RESOURCES || i > PCI_BRIDGE_RESOURCE_END)
+		return 0;
+
+	if (pci_claim_resource(bridge, i) == 0)
+		return 0;	/* claimed the window */
+
+	if ((bridge->class >> 8) != PCI_CLASS_BRIDGE_PCI)
+		return 0;
+
+	if (!pci_bus_clip_resource(bridge, i))
+		return -EINVAL;	/* clipping didn't change anything */
+
+	switch (i - PCI_BRIDGE_RESOURCES) {
+	case 0:
+		pci_setup_bridge_io(bridge);
+		break;
+	case 1:
+		pci_setup_bridge_mmio(bridge);
+		break;
+	case 2:
+		pci_setup_bridge_mmio_pref(bridge);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (pci_claim_resource(bridge, i) == 0)
+		return 0;	/* claimed a smaller window */
+
+	return -EINVAL;
+}
+
 /* Check whether the bridge supports optional I/O and
    prefetchable memory ranges. If not, the respective
    base/limit registers must be read-only and read as 0. */
diff --git a/drivers/pcmcia/topic.h b/drivers/pcmcia/topic.h
index 615a45a8fe8..582688fe750 100644
--- a/drivers/pcmcia/topic.h
+++ b/drivers/pcmcia/topic.h
@@ -104,6 +104,9 @@
 #define TOPIC_EXCA_IF_CONTROL		0x3e	/* 8 bit */
 #define TOPIC_EXCA_IFC_33V_ENA		0x01
 
+#define TOPIC_PCI_CFG_PPBCN		0x3e	/* 16-bit */
+#define TOPIC_PCI_CFG_PPBCN_WBEN	0x0400
+
 static void topic97_zoom_video(struct pcmcia_socket *sock, int onoff)
 {
 	struct yenta_socket *socket = container_of(sock, struct yenta_socket, socket);
@@ -138,6 +141,7 @@ static int topic97_override(struct yenta_socket *socket)
 static int topic95_override(struct yenta_socket *socket)
 {
 	u8 fctrl;
+	u16 ppbcn;
 
 	/* enable 3.3V support for 16bit cards */
 	fctrl = exca_readb(socket, TOPIC_EXCA_IF_CONTROL);
@@ -146,6 +150,18 @@ static int topic95_override(struct yenta_socket *socket)
 	/* tell yenta to use exca registers to power 16bit cards */
 	socket->flags |= YENTA_16BIT_POWER_EXCA | YENTA_16BIT_POWER_DF;
 
+	/* Disable write buffers to prevent lockups under load with numerous
+	   Cardbus cards, observed on Tecra 500CDT and reported elsewhere on the
+	   net.  This is not a power-on default according to the datasheet
+	   but some BIOSes seem to set it. */
+	if (pci_read_config_word(socket->dev, TOPIC_PCI_CFG_PPBCN, &ppbcn) == 0
+	    && socket->dev->revision <= 7
+	    && (ppbcn & TOPIC_PCI_CFG_PPBCN_WBEN)) {
+		ppbcn &= ~TOPIC_PCI_CFG_PPBCN_WBEN;
+		pci_write_config_word(socket->dev, TOPIC_PCI_CFG_PPBCN, ppbcn);
+		dev_info(&socket->dev->dev, "Disabled ToPIC95 Cardbus write buffers.\n");
+	}
+
 	return 0;
 }
 
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index ff5eec5af81..2733112b352 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -51,7 +51,9 @@ static void devm_phy_consume(struct device *dev, void *res)
 
 static int devm_phy_match(struct device *dev, void *res, void *match_data)
 {
-	return res == match_data;
+	struct phy **phy = res;
+
+	return *phy == match_data;
 }
 
 static struct phy *phy_lookup(struct device *device, const char *port)
diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index e4f65510c87..18ee2089df4 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -1110,7 +1110,7 @@ void devm_pinctrl_put(struct pinctrl *p)
 EXPORT_SYMBOL_GPL(devm_pinctrl_put);
 
 int pinctrl_register_map(struct pinctrl_map const *maps, unsigned num_maps,
-			 bool dup, bool locked)
+			 bool dup)
 {
 	int i, ret;
 	struct pinctrl_maps *maps_node;
@@ -1178,11 +1178,9 @@ int pinctrl_register_map(struct pinctrl_map const *maps, unsigned num_maps,
 		maps_node->maps = maps;
 	}
 
-	if (!locked)
-		mutex_lock(&pinctrl_maps_mutex);
+	mutex_lock(&pinctrl_maps_mutex);
 	list_add_tail(&maps_node->node, &pinctrl_maps);
-	if (!locked)
-		mutex_unlock(&pinctrl_maps_mutex);
+	mutex_unlock(&pinctrl_maps_mutex);
 
 	return 0;
 }
@@ -1197,7 +1195,7 @@ int pinctrl_register_map(struct pinctrl_map const *maps, unsigned num_maps,
 int pinctrl_register_mappings(struct pinctrl_map const *maps,
 			      unsigned num_maps)
 {
-	return pinctrl_register_map(maps, num_maps, true, false);
+	return pinctrl_register_map(maps, num_maps, true);
 }
 
 void pinctrl_unregister_map(struct pinctrl_map const *map)
@@ -1801,14 +1799,15 @@ void pinctrl_unregister(struct pinctrl_dev *pctldev)
 	if (pctldev == NULL)
 		return;
 
-	mutex_lock(&pinctrldev_list_mutex);
 	mutex_lock(&pctldev->mutex);
-
 	pinctrl_remove_device_debugfs(pctldev);
+	mutex_unlock(&pctldev->mutex);
 
 	if (!IS_ERR(pctldev->p))
 		pinctrl_put(pctldev->p);
 
+	mutex_lock(&pinctrldev_list_mutex);
+	mutex_lock(&pctldev->mutex);
 	/* TODO: check that no pinmuxes are still active? */
 	list_del(&pctldev->node);
 	/* Destroy descriptor tree */
diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h
index 75476b3d87d..b24ea846c86 100644
--- a/drivers/pinctrl/core.h
+++ b/drivers/pinctrl/core.h
@@ -183,7 +183,7 @@ static inline struct pin_desc *pin_desc_get(struct pinctrl_dev *pctldev,
 }
 
 int pinctrl_register_map(struct pinctrl_map const *maps, unsigned num_maps,
-			 bool dup, bool locked);
+			 bool dup);
 void pinctrl_unregister_map(struct pinctrl_map const *map);
 
 extern int pinctrl_force_sleep(struct pinctrl_dev *pctldev);
diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c
index eda13de2e7c..0bbf7d71b28 100644
--- a/drivers/pinctrl/devicetree.c
+++ b/drivers/pinctrl/devicetree.c
@@ -92,7 +92,7 @@ static int dt_remember_or_free_map(struct pinctrl *p, const char *statename,
 	dt_map->num_maps = num_maps;
 	list_add_tail(&dt_map->node, &p->dt_maps);
 
-	return pinctrl_register_map(map, num_maps, false, true);
+	return pinctrl_register_map(map, num_maps, false);
 }
 
 struct pinctrl_dev *of_pinctrl_get(struct device_node *np)
diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index f2446769247..6f806f93662 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -365,7 +365,7 @@ static void imx_pinconf_dbg_show(struct pinctrl_dev *pctldev,
 	const struct imx_pin_reg *pin_reg = &info->pin_regs[pin_id];
 	unsigned long config;
 
-	if (!pin_reg || !pin_reg->conf_reg) {
+	if (!pin_reg || pin_reg->conf_reg == -1) {
 		seq_printf(s, "N/A");
 		return;
 	}
diff --git a/drivers/pinctrl/freescale/pinctrl-imx25.c b/drivers/pinctrl/freescale/pinctrl-imx25.c
index 550e6d77ac2..b5fabf68463 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx25.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx25.c
@@ -27,150 +27,148 @@
 
 enum imx25_pads {
 	MX25_PAD_RESERVE0 = 1,
-	MX25_PAD_RESERVE1 = 2,
-	MX25_PAD_A10 = 3,
-	MX25_PAD_A13 = 4,
-	MX25_PAD_A14 = 5,
-	MX25_PAD_A15 = 6,
-	MX25_PAD_A16 = 7,
-	MX25_PAD_A17 = 8,
-	MX25_PAD_A18 = 9,
-	MX25_PAD_A19 = 10,
-	MX25_PAD_A20 = 11,
-	MX25_PAD_A21 = 12,
-	MX25_PAD_A22 = 13,
-	MX25_PAD_A23 = 14,
-	MX25_PAD_A24 = 15,
-	MX25_PAD_A25 = 16,
-	MX25_PAD_EB0 = 17,
-	MX25_PAD_EB1 = 18,
-	MX25_PAD_OE = 19,
-	MX25_PAD_CS0 = 20,
-	MX25_PAD_CS1 = 21,
-	MX25_PAD_CS4 = 22,
-	MX25_PAD_CS5 = 23,
-	MX25_PAD_NF_CE0 = 24,
-	MX25_PAD_ECB = 25,
-	MX25_PAD_LBA = 26,
-	MX25_PAD_BCLK = 27,
-	MX25_PAD_RW = 28,
-	MX25_PAD_NFWE_B = 29,
-	MX25_PAD_NFRE_B = 30,
-	MX25_PAD_NFALE = 31,
-	MX25_PAD_NFCLE = 32,
-	MX25_PAD_NFWP_B = 33,
-	MX25_PAD_NFRB = 34,
-	MX25_PAD_D15 = 35,
-	MX25_PAD_D14 = 36,
-	MX25_PAD_D13 = 37,
-	MX25_PAD_D12 = 38,
-	MX25_PAD_D11 = 39,
-	MX25_PAD_D10 = 40,
-	MX25_PAD_D9 = 41,
-	MX25_PAD_D8 = 42,
-	MX25_PAD_D7 = 43,
-	MX25_PAD_D6 = 44,
-	MX25_PAD_D5 = 45,
-	MX25_PAD_D4 = 46,
-	MX25_PAD_D3 = 47,
-	MX25_PAD_D2 = 48,
-	MX25_PAD_D1 = 49,
-	MX25_PAD_D0 = 50,
-	MX25_PAD_LD0 = 51,
-	MX25_PAD_LD1 = 52,
-	MX25_PAD_LD2 = 53,
-	MX25_PAD_LD3 = 54,
-	MX25_PAD_LD4 = 55,
-	MX25_PAD_LD5 = 56,
-	MX25_PAD_LD6 = 57,
-	MX25_PAD_LD7 = 58,
-	MX25_PAD_LD8 = 59,
-	MX25_PAD_LD9 = 60,
-	MX25_PAD_LD10 = 61,
-	MX25_PAD_LD11 = 62,
-	MX25_PAD_LD12 = 63,
-	MX25_PAD_LD13 = 64,
-	MX25_PAD_LD14 = 65,
-	MX25_PAD_LD15 = 66,
-	MX25_PAD_HSYNC = 67,
-	MX25_PAD_VSYNC = 68,
-	MX25_PAD_LSCLK = 69,
-	MX25_PAD_OE_ACD = 70,
-	MX25_PAD_CONTRAST = 71,
-	MX25_PAD_PWM = 72,
-	MX25_PAD_CSI_D2 = 73,
-	MX25_PAD_CSI_D3 = 74,
-	MX25_PAD_CSI_D4 = 75,
-	MX25_PAD_CSI_D5 = 76,
-	MX25_PAD_CSI_D6 = 77,
-	MX25_PAD_CSI_D7 = 78,
-	MX25_PAD_CSI_D8 = 79,
-	MX25_PAD_CSI_D9 = 80,
-	MX25_PAD_CSI_MCLK = 81,
-	MX25_PAD_CSI_VSYNC = 82,
-	MX25_PAD_CSI_HSYNC = 83,
-	MX25_PAD_CSI_PIXCLK = 84,
-	MX25_PAD_I2C1_CLK = 85,
-	MX25_PAD_I2C1_DAT = 86,
-	MX25_PAD_CSPI1_MOSI = 87,
-	MX25_PAD_CSPI1_MISO = 88,
-	MX25_PAD_CSPI1_SS0 = 89,
-	MX25_PAD_CSPI1_SS1 = 90,
-	MX25_PAD_CSPI1_SCLK = 91,
-	MX25_PAD_CSPI1_RDY = 92,
-	MX25_PAD_UART1_RXD = 93,
-	MX25_PAD_UART1_TXD = 94,
-	MX25_PAD_UART1_RTS = 95,
-	MX25_PAD_UART1_CTS = 96,
-	MX25_PAD_UART2_RXD = 97,
-	MX25_PAD_UART2_TXD = 98,
-	MX25_PAD_UART2_RTS = 99,
-	MX25_PAD_UART2_CTS = 100,
-	MX25_PAD_SD1_CMD = 101,
-	MX25_PAD_SD1_CLK = 102,
-	MX25_PAD_SD1_DATA0 = 103,
-	MX25_PAD_SD1_DATA1 = 104,
-	MX25_PAD_SD1_DATA2 = 105,
-	MX25_PAD_SD1_DATA3 = 106,
-	MX25_PAD_KPP_ROW0 = 107,
-	MX25_PAD_KPP_ROW1 = 108,
-	MX25_PAD_KPP_ROW2 = 109,
-	MX25_PAD_KPP_ROW3 = 110,
-	MX25_PAD_KPP_COL0 = 111,
-	MX25_PAD_KPP_COL1 = 112,
-	MX25_PAD_KPP_COL2 = 113,
-	MX25_PAD_KPP_COL3 = 114,
-	MX25_PAD_FEC_MDC = 115,
-	MX25_PAD_FEC_MDIO = 116,
-	MX25_PAD_FEC_TDATA0 = 117,
-	MX25_PAD_FEC_TDATA1 = 118,
-	MX25_PAD_FEC_TX_EN = 119,
-	MX25_PAD_FEC_RDATA0 = 120,
-	MX25_PAD_FEC_RDATA1 = 121,
-	MX25_PAD_FEC_RX_DV = 122,
-	MX25_PAD_FEC_TX_CLK = 123,
-	MX25_PAD_RTCK = 124,
-	MX25_PAD_DE_B = 125,
-	MX25_PAD_GPIO_A = 126,
-	MX25_PAD_GPIO_B = 127,
-	MX25_PAD_GPIO_C = 128,
-	MX25_PAD_GPIO_D = 129,
-	MX25_PAD_GPIO_E = 130,
-	MX25_PAD_GPIO_F = 131,
-	MX25_PAD_EXT_ARMCLK = 132,
-	MX25_PAD_UPLL_BYPCLK = 133,
-	MX25_PAD_VSTBY_REQ = 134,
-	MX25_PAD_VSTBY_ACK = 135,
-	MX25_PAD_POWER_FAIL  = 136,
-	MX25_PAD_CLKO = 137,
-	MX25_PAD_BOOT_MODE0 = 138,
-	MX25_PAD_BOOT_MODE1 = 139,
+	MX25_PAD_A10 = 2,
+	MX25_PAD_A13 = 3,
+	MX25_PAD_A14 = 4,
+	MX25_PAD_A15 = 5,
+	MX25_PAD_A16 = 6,
+	MX25_PAD_A17 = 7,
+	MX25_PAD_A18 = 8,
+	MX25_PAD_A19 = 9,
+	MX25_PAD_A20 = 10,
+	MX25_PAD_A21 = 11,
+	MX25_PAD_A22 = 12,
+	MX25_PAD_A23 = 13,
+	MX25_PAD_A24 = 14,
+	MX25_PAD_A25 = 15,
+	MX25_PAD_EB0 = 16,
+	MX25_PAD_EB1 = 17,
+	MX25_PAD_OE = 18,
+	MX25_PAD_CS0 = 19,
+	MX25_PAD_CS1 = 20,
+	MX25_PAD_CS4 = 21,
+	MX25_PAD_CS5 = 22,
+	MX25_PAD_NF_CE0 = 23,
+	MX25_PAD_ECB = 24,
+	MX25_PAD_LBA = 25,
+	MX25_PAD_BCLK = 26,
+	MX25_PAD_RW = 27,
+	MX25_PAD_NFWE_B = 28,
+	MX25_PAD_NFRE_B = 29,
+	MX25_PAD_NFALE = 30,
+	MX25_PAD_NFCLE = 31,
+	MX25_PAD_NFWP_B = 32,
+	MX25_PAD_NFRB = 33,
+	MX25_PAD_D15 = 34,
+	MX25_PAD_D14 = 35,
+	MX25_PAD_D13 = 36,
+	MX25_PAD_D12 = 37,
+	MX25_PAD_D11 = 38,
+	MX25_PAD_D10 = 39,
+	MX25_PAD_D9 = 40,
+	MX25_PAD_D8 = 41,
+	MX25_PAD_D7 = 42,
+	MX25_PAD_D6 = 43,
+	MX25_PAD_D5 = 44,
+	MX25_PAD_D4 = 45,
+	MX25_PAD_D3 = 46,
+	MX25_PAD_D2 = 47,
+	MX25_PAD_D1 = 48,
+	MX25_PAD_D0 = 49,
+	MX25_PAD_LD0 = 50,
+	MX25_PAD_LD1 = 51,
+	MX25_PAD_LD2 = 52,
+	MX25_PAD_LD3 = 53,
+	MX25_PAD_LD4 = 54,
+	MX25_PAD_LD5 = 55,
+	MX25_PAD_LD6 = 56,
+	MX25_PAD_LD7 = 57,
+	MX25_PAD_LD8 = 58,
+	MX25_PAD_LD9 = 59,
+	MX25_PAD_LD10 = 60,
+	MX25_PAD_LD11 = 61,
+	MX25_PAD_LD12 = 62,
+	MX25_PAD_LD13 = 63,
+	MX25_PAD_LD14 = 64,
+	MX25_PAD_LD15 = 65,
+	MX25_PAD_HSYNC = 66,
+	MX25_PAD_VSYNC = 67,
+	MX25_PAD_LSCLK = 68,
+	MX25_PAD_OE_ACD = 69,
+	MX25_PAD_CONTRAST = 70,
+	MX25_PAD_PWM = 71,
+	MX25_PAD_CSI_D2 = 72,
+	MX25_PAD_CSI_D3 = 73,
+	MX25_PAD_CSI_D4 = 74,
+	MX25_PAD_CSI_D5 = 75,
+	MX25_PAD_CSI_D6 = 76,
+	MX25_PAD_CSI_D7 = 77,
+	MX25_PAD_CSI_D8 = 78,
+	MX25_PAD_CSI_D9 = 79,
+	MX25_PAD_CSI_MCLK = 80,
+	MX25_PAD_CSI_VSYNC = 81,
+	MX25_PAD_CSI_HSYNC = 82,
+	MX25_PAD_CSI_PIXCLK = 83,
+	MX25_PAD_I2C1_CLK = 84,
+	MX25_PAD_I2C1_DAT = 85,
+	MX25_PAD_CSPI1_MOSI = 86,
+	MX25_PAD_CSPI1_MISO = 87,
+	MX25_PAD_CSPI1_SS0 = 88,
+	MX25_PAD_CSPI1_SS1 = 89,
+	MX25_PAD_CSPI1_SCLK = 90,
+	MX25_PAD_CSPI1_RDY = 91,
+	MX25_PAD_UART1_RXD = 92,
+	MX25_PAD_UART1_TXD = 93,
+	MX25_PAD_UART1_RTS = 94,
+	MX25_PAD_UART1_CTS = 95,
+	MX25_PAD_UART2_RXD = 96,
+	MX25_PAD_UART2_TXD = 97,
+	MX25_PAD_UART2_RTS = 98,
+	MX25_PAD_UART2_CTS = 99,
+	MX25_PAD_SD1_CMD = 100,
+	MX25_PAD_SD1_CLK = 101,
+	MX25_PAD_SD1_DATA0 = 102,
+	MX25_PAD_SD1_DATA1 = 103,
+	MX25_PAD_SD1_DATA2 = 104,
+	MX25_PAD_SD1_DATA3 = 105,
+	MX25_PAD_KPP_ROW0 = 106,
+	MX25_PAD_KPP_ROW1 = 107,
+	MX25_PAD_KPP_ROW2 = 108,
+	MX25_PAD_KPP_ROW3 = 109,
+	MX25_PAD_KPP_COL0 = 110,
+	MX25_PAD_KPP_COL1 = 111,
+	MX25_PAD_KPP_COL2 = 112,
+	MX25_PAD_KPP_COL3 = 113,
+	MX25_PAD_FEC_MDC = 114,
+	MX25_PAD_FEC_MDIO = 115,
+	MX25_PAD_FEC_TDATA0 = 116,
+	MX25_PAD_FEC_TDATA1 = 117,
+	MX25_PAD_FEC_TX_EN = 118,
+	MX25_PAD_FEC_RDATA0 = 119,
+	MX25_PAD_FEC_RDATA1 = 120,
+	MX25_PAD_FEC_RX_DV = 121,
+	MX25_PAD_FEC_TX_CLK = 122,
+	MX25_PAD_RTCK = 123,
+	MX25_PAD_DE_B = 124,
+	MX25_PAD_GPIO_A = 125,
+	MX25_PAD_GPIO_B = 126,
+	MX25_PAD_GPIO_C = 127,
+	MX25_PAD_GPIO_D = 128,
+	MX25_PAD_GPIO_E = 129,
+	MX25_PAD_GPIO_F = 130,
+	MX25_PAD_EXT_ARMCLK = 131,
+	MX25_PAD_UPLL_BYPCLK = 132,
+	MX25_PAD_VSTBY_REQ = 133,
+	MX25_PAD_VSTBY_ACK = 134,
+	MX25_PAD_POWER_FAIL  = 135,
+	MX25_PAD_CLKO = 136,
+	MX25_PAD_BOOT_MODE0 = 137,
+	MX25_PAD_BOOT_MODE1 = 138,
 };
 
 /* Pad names for the pinmux subsystem */
 static const struct pinctrl_pin_desc imx25_pinctrl_pads[] = {
 	IMX_PINCTRL_PIN(MX25_PAD_RESERVE0),
-	IMX_PINCTRL_PIN(MX25_PAD_RESERVE1),
 	IMX_PINCTRL_PIN(MX25_PAD_A10),
 	IMX_PINCTRL_PIN(MX25_PAD_A13),
 	IMX_PINCTRL_PIN(MX25_PAD_A14),
diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-370.c b/drivers/pinctrl/mvebu/pinctrl-armada-370.c
index 670e5b01c67..5e423e0b0cb 100644
--- a/drivers/pinctrl/mvebu/pinctrl-armada-370.c
+++ b/drivers/pinctrl/mvebu/pinctrl-armada-370.c
@@ -370,11 +370,11 @@ static struct mvebu_mpp_mode mv88f6710_mpp_modes[] = {
 	MPP_MODE(64,
 	   MPP_FUNCTION(0x0, "gpio", NULL),
 	   MPP_FUNCTION(0x1, "spi0", "miso"),
-	   MPP_FUNCTION(0x2, "spi0-1", "cs1")),
+	   MPP_FUNCTION(0x2, "spi0", "cs1")),
 	MPP_MODE(65,
 	   MPP_FUNCTION(0x0, "gpio", NULL),
 	   MPP_FUNCTION(0x1, "spi0", "mosi"),
-	   MPP_FUNCTION(0x2, "spi0-1", "cs2")),
+	   MPP_FUNCTION(0x2, "spi0", "cs2")),
 };
 
 static struct mvebu_pinctrl_soc_info armada_370_pinctrl_info;
diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-375.c b/drivers/pinctrl/mvebu/pinctrl-armada-375.c
index db078fe7ace..64cc1184ecc 100644
--- a/drivers/pinctrl/mvebu/pinctrl-armada-375.c
+++ b/drivers/pinctrl/mvebu/pinctrl-armada-375.c
@@ -92,19 +92,17 @@ static struct mvebu_mpp_mode mv88f6720_mpp_modes[] = {
 		 MPP_FUNCTION(0x5, "nand", "io1")),
 	MPP_MODE(8,
 		 MPP_FUNCTION(0x0, "gpio", NULL),
-		 MPP_FUNCTION(0x1, "dev ", "bootcs"),
+		 MPP_FUNCTION(0x1, "dev", "bootcs"),
 		 MPP_FUNCTION(0x2, "spi0", "cs0"),
 		 MPP_FUNCTION(0x3, "spi1", "cs0"),
 		 MPP_FUNCTION(0x5, "nand", "ce")),
 	MPP_MODE(9,
 		 MPP_FUNCTION(0x0, "gpio", NULL),
-		 MPP_FUNCTION(0x1, "nf", "wen"),
 		 MPP_FUNCTION(0x2, "spi0", "sck"),
 		 MPP_FUNCTION(0x3, "spi1", "sck"),
 		 MPP_FUNCTION(0x5, "nand", "we")),
 	MPP_MODE(10,
 		 MPP_FUNCTION(0x0, "gpio", NULL),
-		 MPP_FUNCTION(0x1, "nf", "ren"),
 		 MPP_FUNCTION(0x2, "dram", "vttctrl"),
 		 MPP_FUNCTION(0x3, "led", "c1"),
 		 MPP_FUNCTION(0x5, "nand", "re"),
diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-38x.c b/drivers/pinctrl/mvebu/pinctrl-armada-38x.c
index 1049f82fb62..adb6c238f05 100644
--- a/drivers/pinctrl/mvebu/pinctrl-armada-38x.c
+++ b/drivers/pinctrl/mvebu/pinctrl-armada-38x.c
@@ -94,37 +94,39 @@ static struct mvebu_mpp_mode armada_38x_mpp_modes[] = {
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(1, "ge0",   "rxd0",       V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(2, "pcie0", "rstout",     V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(3, "pcie1", "rstout",     V_88F6820_PLUS),
 		 MPP_VAR_FUNCTION(4, "spi0",  "cs1",        V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(5, "dev",   "ad14",       V_88F6810_PLUS)),
+		 MPP_VAR_FUNCTION(5, "dev",   "ad14",       V_88F6810_PLUS),
+		 MPP_VAR_FUNCTION(6, "pcie3", "clkreq",     V_88F6810_PLUS)),
 	MPP_MODE(13,
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(1, "ge0",   "rxd1",       V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(2, "pcie0", "clkreq",     V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(3, "pcie1", "clkreq",     V_88F6820_PLUS),
 		 MPP_VAR_FUNCTION(4, "spi0",  "cs2",        V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(5, "dev",   "ad15",       V_88F6810_PLUS)),
+		 MPP_VAR_FUNCTION(5, "dev",   "ad15",       V_88F6810_PLUS),
+		 MPP_VAR_FUNCTION(6, "pcie2", "clkreq",     V_88F6810_PLUS)),
 	MPP_MODE(14,
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(1, "ge0",   "rxd2",       V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(2, "ptp",   "clk",        V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(3, "m",     "vtt_ctrl",   V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(4, "spi0",  "cs3",        V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(5, "dev",   "wen1",       V_88F6810_PLUS)),
+		 MPP_VAR_FUNCTION(5, "dev",   "wen1",       V_88F6810_PLUS),
+		 MPP_VAR_FUNCTION(6, "pcie3", "clkreq",     V_88F6810_PLUS)),
 	MPP_MODE(15,
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(1, "ge0",   "rxd3",       V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(2, "ge",    "mdc slave",  V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(3, "pcie0", "rstout",     V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(4, "spi0",  "mosi",       V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(5, "pcie1", "rstout",     V_88F6820_PLUS)),
+		 MPP_VAR_FUNCTION(4, "spi0",  "mosi",       V_88F6810_PLUS)),
 	MPP_MODE(16,
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(1, "ge0",   "rxctl",      V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(2, "ge",    "mdio slave", V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(3, "m",     "decc_err",   V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(4, "spi0",  "miso",       V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(5, "pcie0", "clkreq",     V_88F6810_PLUS)),
+		 MPP_VAR_FUNCTION(5, "pcie0", "clkreq",     V_88F6810_PLUS),
+		 MPP_VAR_FUNCTION(6, "pcie1", "clkreq",     V_88F6820_PLUS)),
 	MPP_MODE(17,
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(1, "ge0",   "rxclk",      V_88F6810_PLUS),
@@ -137,20 +139,18 @@ static struct mvebu_mpp_mode armada_38x_mpp_modes[] = {
 		 MPP_VAR_FUNCTION(1, "ge0",   "rxerr",      V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(2, "ptp",   "trig_gen",   V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(3, "ua1",   "txd",        V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(4, "spi0",  "cs0",        V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(5, "pcie1", "rstout",     V_88F6820_PLUS)),
+		 MPP_VAR_FUNCTION(4, "spi0",  "cs0",        V_88F6810_PLUS)),
 	MPP_MODE(19,
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(1, "ge0",   "col",        V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(2, "ptp",   "event_req",  V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(3, "pcie0", "clkreq",     V_88F6810_PLUS),
+		 MPP_VAR_FUNCTION(3, "ge0",   "txerr",      V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(4, "sata1", "prsnt",      V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(5, "ua0",   "cts",        V_88F6810_PLUS)),
 	MPP_MODE(20,
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(1, "ge0",   "txclk",      V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(2, "ptp",   "clk",        V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(3, "pcie1", "rstout",     V_88F6820_PLUS),
 		 MPP_VAR_FUNCTION(4, "sata0", "prsnt",      V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(5, "ua0",   "rts",        V_88F6810_PLUS)),
 	MPP_MODE(21,
@@ -275,35 +275,27 @@ static struct mvebu_mpp_mode armada_38x_mpp_modes[] = {
 		 MPP_VAR_FUNCTION(1, "pcie0", "clkreq",     V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(2, "m",     "vtt_ctrl",   V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(3, "m",     "decc_err",   V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(4, "pcie0", "rstout",     V_88F6810_PLUS),
+		 MPP_VAR_FUNCTION(4, "spi1",  "cs2",        V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(5, "dev",   "clkout",     V_88F6810_PLUS)),
 	MPP_MODE(44,
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(1, "sata0", "prsnt",      V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(2, "sata1", "prsnt",      V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(3, "sata2", "prsnt",      V_88F6828),
-		 MPP_VAR_FUNCTION(4, "sata3", "prsnt",      V_88F6828),
-		 MPP_VAR_FUNCTION(5, "pcie0", "rstout",     V_88F6810_PLUS)),
+		 MPP_VAR_FUNCTION(4, "sata3", "prsnt",      V_88F6828)),
 	MPP_MODE(45,
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(1, "ref",   "clk_out0",   V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(2, "pcie0", "rstout",     V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(3, "pcie1", "rstout",     V_88F6820_PLUS),
-		 MPP_VAR_FUNCTION(4, "pcie2", "rstout",     V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(5, "pcie3", "rstout",     V_88F6810_PLUS)),
+		 MPP_VAR_FUNCTION(2, "pcie0", "rstout",     V_88F6810_PLUS)),
 	MPP_MODE(46,
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(1, "ref",   "clk_out1",   V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(2, "pcie0", "rstout",     V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(3, "pcie1", "rstout",     V_88F6820_PLUS),
-		 MPP_VAR_FUNCTION(4, "pcie2", "rstout",     V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(5, "pcie3", "rstout",     V_88F6810_PLUS)),
+		 MPP_VAR_FUNCTION(2, "pcie0", "rstout",     V_88F6810_PLUS)),
 	MPP_MODE(47,
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(1, "sata0", "prsnt",      V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(2, "sata1", "prsnt",      V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(3, "sata2", "prsnt",      V_88F6828),
-		 MPP_VAR_FUNCTION(4, "spi1",  "cs2",        V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(5, "sata3", "prsnt",      V_88F6828)),
 	MPP_MODE(48,
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
@@ -311,18 +303,19 @@ static struct mvebu_mpp_mode armada_38x_mpp_modes[] = {
 		 MPP_VAR_FUNCTION(2, "m",     "vtt_ctrl",   V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(3, "tdm2c", "pclk",       V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(4, "audio", "mclk",       V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(5, "sd0",   "d4",         V_88F6810_PLUS)),
+		 MPP_VAR_FUNCTION(5, "sd0",   "d4",         V_88F6810_PLUS),
+		 MPP_VAR_FUNCTION(6, "pcie0", "clkreq",     V_88F6810_PLUS)),
 	MPP_MODE(49,
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(1, "sata2", "prsnt",      V_88F6828),
 		 MPP_VAR_FUNCTION(2, "sata3", "prsnt",      V_88F6828),
 		 MPP_VAR_FUNCTION(3, "tdm2c", "fsync",      V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(4, "audio", "lrclk",      V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(5, "sd0",   "d5",         V_88F6810_PLUS)),
+		 MPP_VAR_FUNCTION(5, "sd0",   "d5",         V_88F6810_PLUS),
+		 MPP_VAR_FUNCTION(6, "pcie1", "clkreq",     V_88F6820_PLUS)),
 	MPP_MODE(50,
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(1, "pcie0", "rstout",     V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(2, "pcie1", "rstout",     V_88F6820_PLUS),
 		 MPP_VAR_FUNCTION(3, "tdm2c", "drx",        V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(4, "audio", "extclk",     V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(5, "sd0",   "cmd",        V_88F6810_PLUS)),
@@ -334,7 +327,6 @@ static struct mvebu_mpp_mode armada_38x_mpp_modes[] = {
 	MPP_MODE(52,
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(1, "pcie0", "rstout",     V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(2, "pcie1", "rstout",     V_88F6820_PLUS),
 		 MPP_VAR_FUNCTION(3, "tdm2c", "intn",       V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(4, "audio", "sdi",        V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(5, "sd0",   "d6",         V_88F6810_PLUS)),
@@ -350,7 +342,7 @@ static struct mvebu_mpp_mode armada_38x_mpp_modes[] = {
 		 MPP_VAR_FUNCTION(1, "sata0", "prsnt",      V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(2, "sata1", "prsnt",      V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(3, "pcie0", "rstout",     V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(4, "pcie1", "rstout",     V_88F6820_PLUS),
+		 MPP_VAR_FUNCTION(4, "ge0",   "txerr",      V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(5, "sd0",   "d3",         V_88F6810_PLUS)),
 	MPP_MODE(55,
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
@@ -380,7 +372,6 @@ static struct mvebu_mpp_mode armada_38x_mpp_modes[] = {
 		 MPP_VAR_FUNCTION(0, "gpio",  NULL,         V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(1, "pcie0", "rstout",     V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(2, "i2c1",  "sda",        V_88F6810_PLUS),
-		 MPP_VAR_FUNCTION(3, "pcie1", "rstout",     V_88F6820_PLUS),
 		 MPP_VAR_FUNCTION(4, "spi1",  "cs0",        V_88F6810_PLUS),
 		 MPP_VAR_FUNCTION(5, "sd0",   "d2",         V_88F6810_PLUS)),
 };
@@ -409,7 +400,7 @@ static struct mvebu_mpp_ctrl armada_38x_mpp_controls[] = {
 
 static struct pinctrl_gpio_range armada_38x_mpp_gpio_ranges[] = {
 	MPP_GPIO_RANGE(0,   0,  0, 32),
-	MPP_GPIO_RANGE(1,  32, 32, 27),
+	MPP_GPIO_RANGE(1,  32, 32, 28),
 };
 
 static int armada_38x_pinctrl_probe(struct platform_device *pdev)
diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-xp.c b/drivers/pinctrl/mvebu/pinctrl-armada-xp.c
index de311129f7a..cb06fd293fd 100644
--- a/drivers/pinctrl/mvebu/pinctrl-armada-xp.c
+++ b/drivers/pinctrl/mvebu/pinctrl-armada-xp.c
@@ -14,10 +14,7 @@
  * available: mv78230, mv78260 and mv78460. From a pin muxing
  * perspective, the mv78230 has 49 MPP pins. The mv78260 and mv78460
  * both have 67 MPP pins (more GPIOs and address lines for the memory
- * bus mainly). The only difference between the mv78260 and the
- * mv78460 in terms of pin muxing is the addition of two functions on
- * pins 43 and 56 to access the VDD of the CPU2 and 3 (mv78260 has two
- * cores, mv78460 has four cores).
+ * bus mainly).
  */
 
 #include <linux/err.h>
@@ -171,20 +168,17 @@ static struct mvebu_mpp_mode armada_xp_mpp_modes[] = {
 	MPP_MODE(24,
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x1, "sata1", "prsnt",    V_MV78230_PLUS),
-		 MPP_VAR_FUNCTION(0x2, "nf", "bootcs-re",   V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x3, "tdm", "rst",        V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x4, "lcd", "hsync",      V_MV78230_PLUS)),
 	MPP_MODE(25,
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x1, "sata0", "prsnt",    V_MV78230_PLUS),
-		 MPP_VAR_FUNCTION(0x2, "nf", "bootcs-we",   V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x3, "tdm", "pclk",       V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x4, "lcd", "vsync",      V_MV78230_PLUS)),
 	MPP_MODE(26,
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x3, "tdm", "fsync",      V_MV78230_PLUS),
-		 MPP_VAR_FUNCTION(0x4, "lcd", "clk",        V_MV78230_PLUS),
-		 MPP_VAR_FUNCTION(0x5, "vdd", "cpu1-pd",    V_MV78230_PLUS)),
+		 MPP_VAR_FUNCTION(0x4, "lcd", "clk",        V_MV78230_PLUS)),
 	MPP_MODE(27,
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x1, "ptp", "trig",       V_MV78230_PLUS),
@@ -199,8 +193,7 @@ static struct mvebu_mpp_mode armada_xp_mpp_modes[] = {
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x1, "ptp", "clk",        V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x3, "tdm", "int0",       V_MV78230_PLUS),
-		 MPP_VAR_FUNCTION(0x4, "lcd", "ref-clk",    V_MV78230_PLUS),
-		 MPP_VAR_FUNCTION(0x5, "vdd", "cpu0-pd",    V_MV78230_PLUS)),
+		 MPP_VAR_FUNCTION(0x4, "lcd", "ref-clk",    V_MV78230_PLUS)),
 	MPP_MODE(30,
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x1, "sd0", "clk",        V_MV78230_PLUS),
@@ -208,13 +201,11 @@ static struct mvebu_mpp_mode armada_xp_mpp_modes[] = {
 	MPP_MODE(31,
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x1, "sd0", "cmd",        V_MV78230_PLUS),
-		 MPP_VAR_FUNCTION(0x3, "tdm", "int2",       V_MV78230_PLUS),
-		 MPP_VAR_FUNCTION(0x5, "vdd", "cpu0-pd",    V_MV78230_PLUS)),
+		 MPP_VAR_FUNCTION(0x3, "tdm", "int2",       V_MV78230_PLUS)),
 	MPP_MODE(32,
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x1, "sd0", "d0",         V_MV78230_PLUS),
-		 MPP_VAR_FUNCTION(0x3, "tdm", "int3",       V_MV78230_PLUS),
-		 MPP_VAR_FUNCTION(0x5, "vdd", "cpu1-pd",    V_MV78230_PLUS)),
+		 MPP_VAR_FUNCTION(0x3, "tdm", "int3",       V_MV78230_PLUS)),
 	MPP_MODE(33,
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x1, "sd0", "d1",         V_MV78230_PLUS),
@@ -246,7 +237,6 @@ static struct mvebu_mpp_mode armada_xp_mpp_modes[] = {
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x1, "spi", "cs1",        V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x2, "uart2", "cts",      V_MV78230_PLUS),
-		 MPP_VAR_FUNCTION(0x3, "vdd", "cpu1-pd",    V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x4, "lcd", "vga-hsync",  V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x5, "pcie", "clkreq0",   V_MV78230_PLUS)),
 	MPP_MODE(41,
@@ -261,15 +251,13 @@ static struct mvebu_mpp_mode armada_xp_mpp_modes[] = {
 		 MPP_VAR_FUNCTION(0x1, "uart2", "rxd",      V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x2, "uart0", "cts",      V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x3, "tdm", "int7",       V_MV78230_PLUS),
-		 MPP_VAR_FUNCTION(0x4, "tdm-1", "timer",    V_MV78230_PLUS),
-		 MPP_VAR_FUNCTION(0x5, "vdd", "cpu0-pd",    V_MV78230_PLUS)),
+		 MPP_VAR_FUNCTION(0x4, "tdm-1", "timer",    V_MV78230_PLUS)),
 	MPP_MODE(43,
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x1, "uart2", "txd",      V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x2, "uart0", "rts",      V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x3, "spi", "cs3",        V_MV78230_PLUS),
-		 MPP_VAR_FUNCTION(0x4, "pcie", "rstout",    V_MV78230_PLUS),
-		 MPP_VAR_FUNCTION(0x5, "vdd", "cpu2-3-pd",  V_MV78460)),
+		 MPP_VAR_FUNCTION(0x4, "pcie", "rstout",    V_MV78230_PLUS)),
 	MPP_MODE(44,
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x1, "uart2", "cts",      V_MV78230_PLUS),
@@ -298,7 +286,7 @@ static struct mvebu_mpp_mode armada_xp_mpp_modes[] = {
 		 MPP_VAR_FUNCTION(0x5, "pcie", "clkreq3",   V_MV78230_PLUS)),
 	MPP_MODE(48,
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78230_PLUS),
-		 MPP_VAR_FUNCTION(0x1, "tclk", NULL,        V_MV78230_PLUS),
+		 MPP_VAR_FUNCTION(0x1, "dev", "clkout",     V_MV78230_PLUS),
 		 MPP_VAR_FUNCTION(0x2, "dev", "burst/last", V_MV78230_PLUS)),
 	MPP_MODE(49,
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78260_PLUS),
@@ -320,16 +308,13 @@ static struct mvebu_mpp_mode armada_xp_mpp_modes[] = {
 		 MPP_VAR_FUNCTION(0x1, "dev", "ad19",       V_MV78260_PLUS)),
 	MPP_MODE(55,
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78260_PLUS),
-		 MPP_VAR_FUNCTION(0x1, "dev", "ad20",       V_MV78260_PLUS),
-		 MPP_VAR_FUNCTION(0x2, "vdd", "cpu0-pd",    V_MV78260_PLUS)),
+		 MPP_VAR_FUNCTION(0x1, "dev", "ad20",       V_MV78260_PLUS)),
 	MPP_MODE(56,
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78260_PLUS),
-		 MPP_VAR_FUNCTION(0x1, "dev", "ad21",       V_MV78260_PLUS),
-		 MPP_VAR_FUNCTION(0x2, "vdd", "cpu1-pd",    V_MV78260_PLUS)),
+		 MPP_VAR_FUNCTION(0x1, "dev", "ad21",       V_MV78260_PLUS)),
 	MPP_MODE(57,
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78260_PLUS),
-		 MPP_VAR_FUNCTION(0x1, "dev", "ad22",       V_MV78260_PLUS),
-		 MPP_VAR_FUNCTION(0x2, "vdd", "cpu2-3-pd",  V_MV78460)),
+		 MPP_VAR_FUNCTION(0x1, "dev", "ad22",       V_MV78260_PLUS)),
 	MPP_MODE(58,
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,        V_MV78260_PLUS),
 		 MPP_VAR_FUNCTION(0x1, "dev", "ad23",       V_MV78260_PLUS)),
diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c
index 354a81d4092..d6380c187db 100644
--- a/drivers/pinctrl/pinctrl-at91.c
+++ b/drivers/pinctrl/pinctrl-at91.c
@@ -179,7 +179,7 @@ struct at91_pinctrl {
 	struct device		*dev;
 	struct pinctrl_dev	*pctl;
 
-	int			nbanks;
+	int			nactive_banks;
 
 	uint32_t		*mux_mask;
 	int			nmux;
@@ -655,12 +655,18 @@ static int pin_check_config(struct at91_pinctrl *info, const char *name,
 	int mux;
 
 	/* check if it's a valid config */
-	if (pin->bank >= info->nbanks) {
+	if (pin->bank >= gpio_banks) {
 		dev_err(info->dev, "%s: pin conf %d bank_id %d >= nbanks %d\n",
-			name, index, pin->bank, info->nbanks);
+			name, index, pin->bank, gpio_banks);
 		return -EINVAL;
 	}
 
+	if (!gpio_chips[pin->bank]) {
+		dev_err(info->dev, "%s: pin conf %d bank_id %d not enabled\n",
+			name, index, pin->bank);
+		return -ENXIO;
+	}
+
 	if (pin->pin >= MAX_NB_GPIO_PER_BANK) {
 		dev_err(info->dev, "%s: pin conf %d pin_bank_id %d >= %d\n",
 			name, index, pin->pin, MAX_NB_GPIO_PER_BANK);
@@ -983,7 +989,8 @@ static void at91_pinctrl_child_count(struct at91_pinctrl *info,
 
 	for_each_child_of_node(np, child) {
 		if (of_device_is_compatible(child, gpio_compat)) {
-			info->nbanks++;
+			if (of_device_is_available(child))
+				info->nactive_banks++;
 		} else {
 			info->nfunctions++;
 			info->ngroups += of_get_child_count(child);
@@ -1005,11 +1012,11 @@ static int at91_pinctrl_mux_mask(struct at91_pinctrl *info,
 	}
 
 	size /= sizeof(*list);
-	if (!size || size % info->nbanks) {
-		dev_err(info->dev, "wrong mux mask array should be by %d\n", info->nbanks);
+	if (!size || size % gpio_banks) {
+		dev_err(info->dev, "wrong mux mask array should be by %d\n", gpio_banks);
 		return -EINVAL;
 	}
-	info->nmux = size / info->nbanks;
+	info->nmux = size / gpio_banks;
 
 	info->mux_mask = devm_kzalloc(info->dev, sizeof(u32) * size, GFP_KERNEL);
 	if (!info->mux_mask) {
@@ -1133,7 +1140,7 @@ static int at91_pinctrl_probe_dt(struct platform_device *pdev,
 		of_match_device(at91_pinctrl_of_match, &pdev->dev)->data;
 	at91_pinctrl_child_count(info, np);
 
-	if (info->nbanks < 1) {
+	if (gpio_banks < 1) {
 		dev_err(&pdev->dev, "you need to specify at least one gpio-controller\n");
 		return -EINVAL;
 	}
@@ -1146,7 +1153,7 @@ static int at91_pinctrl_probe_dt(struct platform_device *pdev,
 
 	dev_dbg(&pdev->dev, "mux-mask\n");
 	tmp = info->mux_mask;
-	for (i = 0; i < info->nbanks; i++) {
+	for (i = 0; i < gpio_banks; i++) {
 		for (j = 0; j < info->nmux; j++, tmp++) {
 			dev_dbg(&pdev->dev, "%d:%d\t0x%x\n", i, j, tmp[0]);
 		}
@@ -1164,7 +1171,7 @@ static int at91_pinctrl_probe_dt(struct platform_device *pdev,
 	if (!info->groups)
 		return -ENOMEM;
 
-	dev_dbg(&pdev->dev, "nbanks = %d\n", info->nbanks);
+	dev_dbg(&pdev->dev, "nbanks = %d\n", gpio_banks);
 	dev_dbg(&pdev->dev, "nfunctions = %d\n", info->nfunctions);
 	dev_dbg(&pdev->dev, "ngroups = %d\n", info->ngroups);
 
@@ -1187,7 +1194,7 @@ static int at91_pinctrl_probe(struct platform_device *pdev)
 {
 	struct at91_pinctrl *info;
 	struct pinctrl_pin_desc *pdesc;
-	int ret, i, j, k;
+	int ret, i, j, k, ngpio_chips_enabled = 0;
 
 	info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
 	if (!info)
@@ -1202,23 +1209,27 @@ static int at91_pinctrl_probe(struct platform_device *pdev)
 	 * to obtain references to the struct gpio_chip * for them, and we
 	 * need this to proceed.
 	 */
-	for (i = 0; i < info->nbanks; i++) {
-		if (!gpio_chips[i]) {
-			dev_warn(&pdev->dev, "GPIO chip %d not registered yet\n", i);
-			devm_kfree(&pdev->dev, info);
-			return -EPROBE_DEFER;
-		}
+	for (i = 0; i < gpio_banks; i++)
+		if (gpio_chips[i])
+			ngpio_chips_enabled++;
+
+	if (ngpio_chips_enabled < info->nactive_banks) {
+		dev_warn(&pdev->dev,
+			 "All GPIO chips are not registered yet (%d/%d)\n",
+			 ngpio_chips_enabled, info->nactive_banks);
+		devm_kfree(&pdev->dev, info);
+		return -EPROBE_DEFER;
 	}
 
 	at91_pinctrl_desc.name = dev_name(&pdev->dev);
-	at91_pinctrl_desc.npins = info->nbanks * MAX_NB_GPIO_PER_BANK;
+	at91_pinctrl_desc.npins = gpio_banks * MAX_NB_GPIO_PER_BANK;
 	at91_pinctrl_desc.pins = pdesc =
 		devm_kzalloc(&pdev->dev, sizeof(*pdesc) * at91_pinctrl_desc.npins, GFP_KERNEL);
 
 	if (!at91_pinctrl_desc.pins)
 		return -ENOMEM;
 
-	for (i = 0 , k = 0; i < info->nbanks; i++) {
+	for (i = 0, k = 0; i < gpio_banks; i++) {
 		for (j = 0; j < MAX_NB_GPIO_PER_BANK; j++, k++) {
 			pdesc->number = k;
 			pdesc->name = kasprintf(GFP_KERNEL, "pio%c%d", i + 'A', j);
@@ -1236,8 +1247,9 @@ static int at91_pinctrl_probe(struct platform_device *pdev)
 	}
 
 	/* We will handle a range of GPIO pins */
-	for (i = 0; i < info->nbanks; i++)
-		pinctrl_add_gpio_range(info->pctl, &gpio_chips[i]->range);
+	for (i = 0; i < gpio_banks; i++)
+		if (gpio_chips[i])
+			pinctrl_add_gpio_range(info->pctl, &gpio_chips[i]->range);
 
 	dev_info(&pdev->dev, "initialized AT91 pinctrl driver\n");
 
@@ -1614,9 +1626,10 @@ static void gpio_irq_handler(unsigned irq, struct irq_desc *desc)
 static int at91_gpio_of_irq_setup(struct platform_device *pdev,
 				  struct at91_gpio_chip *at91_gpio)
 {
+	struct gpio_chip	*gpiochip_prev = NULL;
 	struct at91_gpio_chip   *prev = NULL;
 	struct irq_data		*d = irq_get_irq_data(at91_gpio->pioc_virq);
-	int ret;
+	int ret, i;
 
 	at91_gpio->pioc_hwirq = irqd_to_hwirq(d);
 
@@ -1642,24 +1655,33 @@ static int at91_gpio_of_irq_setup(struct platform_device *pdev,
 		return ret;
 	}
 
-	/* Setup chained handler */
-	if (at91_gpio->pioc_idx)
-		prev = gpio_chips[at91_gpio->pioc_idx - 1];
-
 	/* The top level handler handles one bank of GPIOs, except
 	 * on some SoC it can handle up to three...
 	 * We only set up the handler for the first of the list.
 	 */
-	if (prev && prev->next == at91_gpio)
+	gpiochip_prev = irq_get_handler_data(at91_gpio->pioc_virq);
+	if (!gpiochip_prev) {
+		/* Then register the chain on the parent IRQ */
+		gpiochip_set_chained_irqchip(&at91_gpio->chip,
+					     &gpio_irqchip,
+					     at91_gpio->pioc_virq,
+					     gpio_irq_handler);
 		return 0;
+	}
 
-	/* Then register the chain on the parent IRQ */
-	gpiochip_set_chained_irqchip(&at91_gpio->chip,
-				     &gpio_irqchip,
-				     at91_gpio->pioc_virq,
-				     gpio_irq_handler);
+	prev = container_of(gpiochip_prev, struct at91_gpio_chip, chip);
 
-	return 0;
+	/* we can only have 2 banks before */
+	for (i = 0; i < 2; i++) {
+		if (prev->next) {
+			prev = prev->next;
+		} else {
+			prev->next = at91_gpio;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
 }
 
 /* This structure is replicated for each GPIO block allocated at probe time */
@@ -1676,24 +1698,6 @@ static struct gpio_chip at91_gpio_template = {
 	.ngpio			= MAX_NB_GPIO_PER_BANK,
 };
 
-static void at91_gpio_probe_fixup(void)
-{
-	unsigned i;
-	struct at91_gpio_chip *at91_gpio, *last = NULL;
-
-	for (i = 0; i < gpio_banks; i++) {
-		at91_gpio = gpio_chips[i];
-
-		/*
-		 * GPIO controller are grouped on some SoC:
-		 * PIOC, PIOD and PIOE can share the same IRQ line
-		 */
-		if (last && last->pioc_virq == at91_gpio->pioc_virq)
-			last->next = at91_gpio;
-		last = at91_gpio;
-	}
-}
-
 static struct of_device_id at91_gpio_of_match[] = {
 	{ .compatible = "atmel,at91sam9x5-gpio", .data = &at91sam9x5_ops, },
 	{ .compatible = "atmel,at91rm9200-gpio", .data = &at91rm9200_ops },
@@ -1806,8 +1810,6 @@ static int at91_gpio_probe(struct platform_device *pdev)
 	gpio_chips[alias_idx] = at91_chip;
 	gpio_banks = max(gpio_banks, alias_idx + 1);
 
-	at91_gpio_probe_fixup();
-
 	ret = at91_gpio_of_irq_setup(pdev, at91_chip);
 	if (ret)
 		goto irq_setup_err;
diff --git a/drivers/pinctrl/pinctrl-xway.c b/drivers/pinctrl/pinctrl-xway.c
index 37040ab4289..fdff39ff502 100644
--- a/drivers/pinctrl/pinctrl-xway.c
+++ b/drivers/pinctrl/pinctrl-xway.c
@@ -798,10 +798,8 @@ static int pinmux_xway_probe(struct platform_device *pdev)
 
 	/* load the gpio chip */
 	xway_chip.dev = &pdev->dev;
-	of_gpiochip_add(&xway_chip);
 	ret = gpiochip_add(&xway_chip);
 	if (ret) {
-		of_gpiochip_remove(&xway_chip);
 		dev_err(&pdev->dev, "Failed to register gpio chip\n");
 		return ret;
 	}
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index e730935fa45..ed7017df065 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -865,10 +865,10 @@ static int msm_ps_hold_restart(struct notifier_block *nb, unsigned long action,
 
 static void msm_pinctrl_setup_pm_reset(struct msm_pinctrl *pctrl)
 {
-	int i = 0;
+	int i;
 	const struct msm_function *func = pctrl->soc->functions;
 
-	for (; i <= pctrl->soc->nfunctions; i++)
+	for (i = 0; i < pctrl->soc->nfunctions; i++)
 		if (!strcmp(func[i].name, "ps_hold")) {
 			pctrl->restart_nb.notifier_call = msm_ps_hold_restart;
 			pctrl->restart_nb.priority = 128;
diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c
index f94467c0522..7f21f75baa5 100644
--- a/drivers/platform/x86/acerhdf.c
+++ b/drivers/platform/x86/acerhdf.c
@@ -330,7 +330,8 @@ static int acerhdf_bind(struct thermal_zone_device *thermal,
 		return 0;
 
 	if (thermal_zone_bind_cooling_device(thermal, 0, cdev,
-			THERMAL_NO_LIMIT, THERMAL_NO_LIMIT)) {
+			THERMAL_NO_LIMIT, THERMAL_NO_LIMIT,
+			THERMAL_WEIGHT_DEFAULT)) {
 		pr_err("error binding cooling dev\n");
 		return -EINVAL;
 	}
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index c1a6cd66af4..abdaed34c72 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -191,6 +191,15 @@ static const struct dmi_system_id asus_quirks[] = {
 	},
 	{
 		.callback = dmi_matched,
+		.ident = "ASUSTeK COMPUTER INC. X551CA",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X551CA"),
+		},
+		.driver_data = &quirk_asus_wapf4,
+	},
+	{
+		.callback = dmi_matched,
 		.ident = "ASUSTeK COMPUTER INC. X55A",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
diff --git a/drivers/platform/x86/compal-laptop.c b/drivers/platform/x86/compal-laptop.c
index 26bfd7bb5c1..034aa844a1b 100644
--- a/drivers/platform/x86/compal-laptop.c
+++ b/drivers/platform/x86/compal-laptop.c
@@ -1027,9 +1027,9 @@ static int compal_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	hwmon_dev = hwmon_device_register_with_groups(&pdev->dev,
-						      "compal", data,
-						      compal_hwmon_groups);
+	hwmon_dev = devm_hwmon_device_register_with_groups(&pdev->dev,
+							   "compal", data,
+							   compal_hwmon_groups);
 	if (IS_ERR(hwmon_dev)) {
 		err = PTR_ERR(hwmon_dev);
 		goto remove;
@@ -1037,7 +1037,9 @@ static int compal_probe(struct platform_device *pdev)
 
 	/* Power supply */
 	initialize_power_supply_data(data);
-	power_supply_register(&compal_device->dev, &data->psy);
+	err = power_supply_register(&compal_device->dev, &data->psy);
+	if (err < 0)
+		goto remove;
 
 	platform_set_drvdata(pdev, data);
 
diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c
index 233d2ee598a..be945fff61c 100644
--- a/drivers/platform/x86/dell-laptop.c
+++ b/drivers/platform/x86/dell-laptop.c
@@ -272,7 +272,6 @@ static const struct dmi_system_id dell_quirks[] __initconst = {
 };
 
 static struct calling_interface_buffer *buffer;
-static struct page *bufferpage;
 static DEFINE_MUTEX(buffer_mutex);
 
 static int hwswitch_state;
@@ -825,12 +824,11 @@ static int __init dell_init(void)
 	 * Allocate buffer below 4GB for SMI data--only 32-bit physical addr
 	 * is passed to SMI handler.
 	 */
-	bufferpage = alloc_page(GFP_KERNEL | GFP_DMA32);
-	if (!bufferpage) {
+	buffer = (void *)__get_free_page(GFP_KERNEL | GFP_DMA32);
+	if (!buffer) {
 		ret = -ENOMEM;
 		goto fail_buffer;
 	}
-	buffer = page_address(bufferpage);
 
 	ret = dell_setup_rfkill();
 
@@ -892,7 +890,7 @@ fail_backlight:
 	cancel_delayed_work_sync(&dell_rfkill_work);
 	dell_cleanup_rfkill();
 fail_rfkill:
-	free_page((unsigned long)bufferpage);
+	free_page((unsigned long)buffer);
 fail_buffer:
 	platform_device_del(platform_device);
 fail_platform_device2:
diff --git a/drivers/platform/x86/hp_accel.c b/drivers/platform/x86/hp_accel.c
index 6bec745b6b9..10ce6cba445 100644
--- a/drivers/platform/x86/hp_accel.c
+++ b/drivers/platform/x86/hp_accel.c
@@ -246,6 +246,7 @@ static const struct dmi_system_id lis3lv02d_dmi_ids[] = {
 	AXIS_DMI_MATCH("HPB64xx", "HP ProBook 64", xy_swap),
 	AXIS_DMI_MATCH("HPB64xx", "HP EliteBook 84", xy_swap),
 	AXIS_DMI_MATCH("HPB65xx", "HP ProBook 65", x_inverted),
+	AXIS_DMI_MATCH("HPZBook15", "HP ZBook 15", x_inverted),
 	{ NULL, }
 /* Laptop models without axis info (yet):
  * "NC6910" "HP Compaq 6910"
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index ed494f37c40..14ad4c28b0b 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -464,8 +464,9 @@ static const struct ideapad_rfk_data ideapad_rfk_data[] = {
 static int ideapad_rfk_set(void *data, bool blocked)
 {
 	struct ideapad_rfk_priv *priv = data;
+	int opcode = ideapad_rfk_data[priv->dev].opcode;
 
-	return write_ec_cmd(priv->priv->adev->handle, priv->dev, !blocked);
+	return write_ec_cmd(priv->priv->adev->handle, opcode, !blocked);
 }
 
 static struct rfkill_ops ideapad_rfk_ops = {
@@ -831,6 +832,13 @@ static void ideapad_acpi_notify(acpi_handle handle, u32 event, void *data)
  */
 static const struct dmi_system_id no_hw_rfkill_list[] = {
 	{
+		.ident = "Lenovo G50-30",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo G50-30"),
+		},
+	},
+	{
 		.ident = "Lenovo Yoga 2 11 / 13 / Pro",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c
index ff765d8e1a0..ce364a41842 100644
--- a/drivers/platform/x86/samsung-laptop.c
+++ b/drivers/platform/x86/samsung-laptop.c
@@ -353,6 +353,7 @@ struct samsung_quirks {
 	bool broken_acpi_video;
 	bool four_kbd_backlight_levels;
 	bool enable_kbd_backlight;
+	bool use_native_backlight;
 };
 
 static struct samsung_quirks samsung_unknown = {};
@@ -361,6 +362,10 @@ static struct samsung_quirks samsung_broken_acpi_video = {
 	.broken_acpi_video = true,
 };
 
+static struct samsung_quirks samsung_use_native_backlight = {
+	.use_native_backlight = true,
+};
+
 static struct samsung_quirks samsung_np740u3e = {
 	.four_kbd_backlight_levels = true,
 	.enable_kbd_backlight = true,
@@ -1507,7 +1512,7 @@ static struct dmi_system_id __initdata samsung_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "N150P"),
 		DMI_MATCH(DMI_BOARD_NAME, "N150P"),
 		},
-	 .driver_data = &samsung_broken_acpi_video,
+	 .driver_data = &samsung_use_native_backlight,
 	},
 	{
 	 .callback = samsung_dmi_matched,
@@ -1517,7 +1522,7 @@ static struct dmi_system_id __initdata samsung_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "N145P/N250P/N260P"),
 		DMI_MATCH(DMI_BOARD_NAME, "N145P/N250P/N260P"),
 		},
-	 .driver_data = &samsung_broken_acpi_video,
+	 .driver_data = &samsung_use_native_backlight,
 	},
 	{
 	 .callback = samsung_dmi_matched,
@@ -1557,7 +1562,7 @@ static struct dmi_system_id __initdata samsung_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "N250P"),
 		DMI_MATCH(DMI_BOARD_NAME, "N250P"),
 		},
-	 .driver_data = &samsung_broken_acpi_video,
+	 .driver_data = &samsung_use_native_backlight,
 	},
 	{
 	 .callback = samsung_dmi_matched,
@@ -1616,6 +1621,15 @@ static int __init samsung_init(void)
 		pr_info("Disabling ACPI video driver\n");
 		acpi_video_unregister();
 	}
+
+	if (samsung->quirks->use_native_backlight) {
+		pr_info("Using native backlight driver\n");
+		/* Tell acpi-video to not handle the backlight */
+		acpi_video_dmi_promote_vendor();
+		acpi_video_unregister();
+		/* And also do not handle it ourselves */
+		samsung->handle_backlight = false;
+	}
 #endif
 
 	ret = samsung_platform_init(samsung);
diff --git a/drivers/power/88pm860x_charger.c b/drivers/power/88pm860x_charger.c
index de029bbc1cc..5ccca8743ce 100644
--- a/drivers/power/88pm860x_charger.c
+++ b/drivers/power/88pm860x_charger.c
@@ -711,6 +711,7 @@ static int pm860x_charger_probe(struct platform_device *pdev)
 	return 0;
 
 out_irq:
+	power_supply_unregister(&info->usb);
 	while (--i >= 0)
 		free_irq(info->irq[i], info);
 out:
diff --git a/drivers/power/bq24190_charger.c b/drivers/power/bq24190_charger.c
index ad3ff8fbfbb..e4c95e1a673 100644
--- a/drivers/power/bq24190_charger.c
+++ b/drivers/power/bq24190_charger.c
@@ -929,7 +929,7 @@ static void bq24190_charger_init(struct power_supply *charger)
 	charger->properties = bq24190_charger_properties;
 	charger->num_properties = ARRAY_SIZE(bq24190_charger_properties);
 	charger->supplied_to = bq24190_charger_supplied_to;
-	charger->num_supplies = ARRAY_SIZE(bq24190_charger_supplied_to);
+	charger->num_supplicants = ARRAY_SIZE(bq24190_charger_supplied_to);
 	charger->get_property = bq24190_charger_get_property;
 	charger->set_property = bq24190_charger_set_property;
 	charger->property_is_writeable = bq24190_charger_property_is_writeable;
diff --git a/drivers/power/gpio-charger.c b/drivers/power/gpio-charger.c
index 7536933d0ab..e5deb11bf1d 100644
--- a/drivers/power/gpio-charger.c
+++ b/drivers/power/gpio-charger.c
@@ -168,7 +168,7 @@ static int gpio_charger_suspend(struct device *dev)
 
 	if (device_may_wakeup(dev))
 		gpio_charger->wakeup_enabled =
-			enable_irq_wake(gpio_charger->irq);
+			!enable_irq_wake(gpio_charger->irq);
 
 	return 0;
 }
@@ -178,7 +178,7 @@ static int gpio_charger_resume(struct device *dev)
 	struct platform_device *pdev = to_platform_device(dev);
 	struct gpio_charger *gpio_charger = platform_get_drvdata(pdev);
 
-	if (gpio_charger->wakeup_enabled)
+	if (device_may_wakeup(dev) && gpio_charger->wakeup_enabled)
 		disable_irq_wake(gpio_charger->irq);
 	power_supply_changed(&gpio_charger->charger);
 
diff --git a/drivers/power/ipaq_micro_battery.c b/drivers/power/ipaq_micro_battery.c
index 9d694605cdb..96b15e003f3 100644
--- a/drivers/power/ipaq_micro_battery.c
+++ b/drivers/power/ipaq_micro_battery.c
@@ -226,6 +226,7 @@ static struct power_supply micro_ac_power = {
 static int micro_batt_probe(struct platform_device *pdev)
 {
 	struct micro_battery *mb;
+	int ret;
 
 	mb = devm_kzalloc(&pdev->dev, sizeof(*mb), GFP_KERNEL);
 	if (!mb)
@@ -233,14 +234,30 @@ static int micro_batt_probe(struct platform_device *pdev)
 
 	mb->micro = dev_get_drvdata(pdev->dev.parent);
 	mb->wq = create_singlethread_workqueue("ipaq-battery-wq");
+	if (!mb->wq)
+		return -ENOMEM;
+
 	INIT_DELAYED_WORK(&mb->update, micro_battery_work);
 	platform_set_drvdata(pdev, mb);
 	queue_delayed_work(mb->wq, &mb->update, 1);
-	power_supply_register(&pdev->dev, &micro_batt_power);
-	power_supply_register(&pdev->dev, &micro_ac_power);
+
+	ret = power_supply_register(&pdev->dev, &micro_batt_power);
+	if (ret < 0)
+		goto batt_err;
+
+	ret = power_supply_register(&pdev->dev, &micro_ac_power);
+	if (ret < 0)
+		goto ac_err;
 
 	dev_info(&pdev->dev, "iPAQ micro battery driver\n");
 	return 0;
+
+ac_err:
+	power_supply_unregister(&micro_ac_power);
+batt_err:
+	cancel_delayed_work_sync(&mb->update);
+	destroy_workqueue(mb->wq);
+	return ret;
 }
 
 static int micro_batt_remove(struct platform_device *pdev)
@@ -251,6 +268,7 @@ static int micro_batt_remove(struct platform_device *pdev)
 	power_supply_unregister(&micro_ac_power);
 	power_supply_unregister(&micro_batt_power);
 	cancel_delayed_work_sync(&mb->update);
+	destroy_workqueue(mb->wq);
 
 	return 0;
 }
diff --git a/drivers/power/lp8788-charger.c b/drivers/power/lp8788-charger.c
index ed49b50b220..72da2a6c22d 100644
--- a/drivers/power/lp8788-charger.c
+++ b/drivers/power/lp8788-charger.c
@@ -417,8 +417,10 @@ static int lp8788_psy_register(struct platform_device *pdev,
 	pchg->battery.num_properties = ARRAY_SIZE(lp8788_battery_prop);
 	pchg->battery.get_property = lp8788_battery_get_property;
 
-	if (power_supply_register(&pdev->dev, &pchg->battery))
+	if (power_supply_register(&pdev->dev, &pchg->battery)) {
+		power_supply_unregister(&pchg->charger);
 		return -EPERM;
+	}
 
 	return 0;
 }
diff --git a/drivers/power/power_supply_sysfs.c b/drivers/power/power_supply_sysfs.c
index 62653f50a52..87a348cc1e6 100644
--- a/drivers/power/power_supply_sysfs.c
+++ b/drivers/power/power_supply_sysfs.c
@@ -106,7 +106,10 @@ static ssize_t power_supply_show_property(struct device *dev,
 	else if (off >= POWER_SUPPLY_PROP_MODEL_NAME)
 		return sprintf(buf, "%s\n", value.strval);
 
-	return sprintf(buf, "%d\n", value.intval);
+	if (off == POWER_SUPPLY_PROP_CHARGE_COUNTER_EXT)
+		return sprintf(buf, "%lld\n", value.int64val);
+	else
+		return sprintf(buf, "%d\n", value.intval);
 }
 
 static ssize_t power_supply_store_property(struct device *dev,
@@ -197,6 +200,12 @@ static struct device_attribute power_supply_attrs[] = {
 	POWER_SUPPLY_ATTR(scope),
 	POWER_SUPPLY_ATTR(charge_term_current),
 	POWER_SUPPLY_ATTR(calibrate),
+	/* Local extensions */
+	POWER_SUPPLY_ATTR(usb_hc),
+	POWER_SUPPLY_ATTR(usb_otg),
+	POWER_SUPPLY_ATTR(charge_enabled),
+	/* Local extensions of type int64_t */
+	POWER_SUPPLY_ATTR(charge_counter_ext),
 	/* Properties of type `const char *' */
 	POWER_SUPPLY_ATTR(model_name),
 	POWER_SUPPLY_ATTR(manufacturer),
diff --git a/drivers/power/reset/at91-reset.c b/drivers/power/reset/at91-reset.c
index 3cb36693343..80d490da9a4 100644
--- a/drivers/power/reset/at91-reset.c
+++ b/drivers/power/reset/at91-reset.c
@@ -205,9 +205,9 @@ static int at91_reset_platform_probe(struct platform_device *pdev)
 		res = platform_get_resource(pdev, IORESOURCE_MEM, idx + 1 );
 		at91_ramc_base[idx] = devm_ioremap(&pdev->dev, res->start,
 						   resource_size(res));
-		if (IS_ERR(at91_ramc_base[idx])) {
+		if (!at91_ramc_base[idx]) {
 			dev_err(&pdev->dev, "Could not map ram controller address\n");
-			return PTR_ERR(at91_ramc_base[idx]);
+			return -ENOMEM;
 		}
 	}
 
diff --git a/drivers/power/twl4030_madc_battery.c b/drivers/power/twl4030_madc_battery.c
index 7ef445a6cfa..cf907609ec4 100644
--- a/drivers/power/twl4030_madc_battery.c
+++ b/drivers/power/twl4030_madc_battery.c
@@ -192,6 +192,7 @@ static int twl4030_madc_battery_probe(struct platform_device *pdev)
 {
 	struct twl4030_madc_battery *twl4030_madc_bat;
 	struct twl4030_madc_bat_platform_data *pdata = pdev->dev.platform_data;
+	int ret = 0;
 
 	twl4030_madc_bat = kzalloc(sizeof(*twl4030_madc_bat), GFP_KERNEL);
 	if (!twl4030_madc_bat)
@@ -216,9 +217,11 @@ static int twl4030_madc_battery_probe(struct platform_device *pdev)
 
 	twl4030_madc_bat->pdata = pdata;
 	platform_set_drvdata(pdev, twl4030_madc_bat);
-	power_supply_register(&pdev->dev, &twl4030_madc_bat->psy);
+	ret = power_supply_register(&pdev->dev, &twl4030_madc_bat->psy);
+	if (ret < 0)
+		kfree(twl4030_madc_bat);
 
-	return 0;
+	return ret;
 }
 
 static int twl4030_madc_battery_remove(struct platform_device *pdev)
diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c
index 4f730af70e7..30e8d7ad581 100644
--- a/drivers/regulator/anatop-regulator.c
+++ b/drivers/regulator/anatop-regulator.c
@@ -283,6 +283,14 @@ static int anatop_regulator_probe(struct platform_device *pdev)
 			sreg->sel = 0;
 			sreg->bypass = true;
 		}
+
+		/*
+		 * In case vddpu was disabled by the bootloader, we need to set
+		 * a sane default until imx6-cpufreq was probed and changes the
+		 * voltage to the correct value. In this case we set 1.25V.
+		 */
+		if (!sreg->sel && !strcmp(sreg->name, "vddpu"))
+			sreg->sel = 22;
 	} else {
 		rdesc->ops = &anatop_rops;
 	}
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index cd87c0c3703..bc3d80f9d5d 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -774,7 +774,7 @@ static int suspend_prepare(struct regulator_dev *rdev, suspend_state_t state)
 static void print_constraints(struct regulator_dev *rdev)
 {
 	struct regulation_constraints *constraints = rdev->constraints;
-	char buf[80] = "";
+	char buf[160] = "";
 	int count = 0;
 	int ret;
 
@@ -1488,7 +1488,7 @@ struct regulator *regulator_get_optional(struct device *dev, const char *id)
 }
 EXPORT_SYMBOL_GPL(regulator_get_optional);
 
-/* Locks held by regulator_put() */
+/* regulator_list_mutex lock held by regulator_put() */
 static void _regulator_put(struct regulator *regulator)
 {
 	struct regulator_dev *rdev;
@@ -1503,12 +1503,14 @@ static void _regulator_put(struct regulator *regulator)
 	/* remove any sysfs entries */
 	if (regulator->dev)
 		sysfs_remove_link(&rdev->dev.kobj, regulator->supply_name);
+	mutex_lock(&rdev->mutex);
 	kfree(regulator->supply_name);
 	list_del(&regulator->list);
 	kfree(regulator);
 
 	rdev->open_count--;
 	rdev->exclusive = 0;
+	mutex_unlock(&rdev->mutex);
 
 	module_put(rdev->owner);
 }
@@ -1839,10 +1841,12 @@ static int _regulator_do_enable(struct regulator_dev *rdev)
 	}
 
 	if (rdev->ena_pin) {
-		ret = regulator_ena_gpio_ctrl(rdev, true);
-		if (ret < 0)
-			return ret;
-		rdev->ena_gpio_state = 1;
+		if (!rdev->ena_gpio_state) {
+			ret = regulator_ena_gpio_ctrl(rdev, true);
+			if (ret < 0)
+				return ret;
+			rdev->ena_gpio_state = 1;
+		}
 	} else if (rdev->desc->ops->enable) {
 		ret = rdev->desc->ops->enable(rdev);
 		if (ret < 0)
@@ -1939,10 +1943,12 @@ static int _regulator_do_disable(struct regulator_dev *rdev)
 	trace_regulator_disable(rdev_get_name(rdev));
 
 	if (rdev->ena_pin) {
-		ret = regulator_ena_gpio_ctrl(rdev, false);
-		if (ret < 0)
-			return ret;
-		rdev->ena_gpio_state = 0;
+		if (rdev->ena_gpio_state) {
+			ret = regulator_ena_gpio_ctrl(rdev, false);
+			if (ret < 0)
+				return ret;
+			rdev->ena_gpio_state = 0;
+		}
 
 	} else if (rdev->desc->ops->disable) {
 		ret = rdev->desc->ops->disable(rdev);
@@ -3657,12 +3663,6 @@ regulator_register(const struct regulator_desc *regulator_desc,
 				 config->ena_gpio, ret);
 			goto wash;
 		}
-
-		if (config->ena_gpio_flags & GPIOF_OUT_INIT_HIGH)
-			rdev->ena_gpio_state = 1;
-
-		if (config->ena_gpio_invert)
-			rdev->ena_gpio_state = !rdev->ena_gpio_state;
 	}
 
 	/* set regulator constraints */
@@ -3835,9 +3835,11 @@ int regulator_suspend_finish(void)
 	list_for_each_entry(rdev, &regulator_list, list) {
 		mutex_lock(&rdev->mutex);
 		if (rdev->use_count > 0  || rdev->constraints->always_on) {
-			error = _regulator_do_enable(rdev);
-			if (error)
-				ret = error;
+			if (!_regulator_is_enabled(rdev)) {
+				error = _regulator_do_enable(rdev);
+				if (error)
+					ret = error;
+			}
 		} else {
 			if (!have_full_constraints())
 				goto unlock;
diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c
index 1878e5b567e..1a7f5fc1162 100644
--- a/drivers/regulator/palmas-regulator.c
+++ b/drivers/regulator/palmas-regulator.c
@@ -1572,6 +1572,10 @@ static int palmas_regulators_probe(struct platform_device *pdev)
 	if (!pmic)
 		return -ENOMEM;
 
+	if (of_device_is_compatible(node, "ti,tps659038-pmic"))
+		palmas_generic_regs_info[PALMAS_REG_REGEN2].ctrl_addr =
+							TPS659038_REGEN2_CTRL;
+
 	pmic->dev = &pdev->dev;
 	pmic->palmas = palmas;
 	palmas->pmic = pmic;
diff --git a/drivers/regulator/rk808-regulator.c b/drivers/regulator/rk808-regulator.c
index 196a5c8838c..b019956ba5d 100644
--- a/drivers/regulator/rk808-regulator.c
+++ b/drivers/regulator/rk808-regulator.c
@@ -184,6 +184,7 @@ static const struct regulator_desc rk808_reg[] = {
 		.vsel_mask = RK808_LDO_VSEL_MASK,
 		.enable_reg = RK808_LDO_EN_REG,
 		.enable_mask = BIT(0),
+		.enable_time = 400,
 		.owner = THIS_MODULE,
 	}, {
 		.name = "LDO_REG2",
@@ -198,6 +199,7 @@ static const struct regulator_desc rk808_reg[] = {
 		.vsel_mask = RK808_LDO_VSEL_MASK,
 		.enable_reg = RK808_LDO_EN_REG,
 		.enable_mask = BIT(1),
+		.enable_time = 400,
 		.owner = THIS_MODULE,
 	}, {
 		.name = "LDO_REG3",
@@ -212,6 +214,7 @@ static const struct regulator_desc rk808_reg[] = {
 		.vsel_mask = RK808_BUCK4_VSEL_MASK,
 		.enable_reg = RK808_LDO_EN_REG,
 		.enable_mask = BIT(2),
+		.enable_time = 400,
 		.owner = THIS_MODULE,
 	}, {
 		.name = "LDO_REG4",
@@ -226,6 +229,7 @@ static const struct regulator_desc rk808_reg[] = {
 		.vsel_mask = RK808_LDO_VSEL_MASK,
 		.enable_reg = RK808_LDO_EN_REG,
 		.enable_mask = BIT(3),
+		.enable_time = 400,
 		.owner = THIS_MODULE,
 	}, {
 		.name = "LDO_REG5",
@@ -240,6 +244,7 @@ static const struct regulator_desc rk808_reg[] = {
 		.vsel_mask = RK808_LDO_VSEL_MASK,
 		.enable_reg = RK808_LDO_EN_REG,
 		.enable_mask = BIT(4),
+		.enable_time = 400,
 		.owner = THIS_MODULE,
 	}, {
 		.name = "LDO_REG6",
@@ -254,6 +259,7 @@ static const struct regulator_desc rk808_reg[] = {
 		.vsel_mask = RK808_LDO_VSEL_MASK,
 		.enable_reg = RK808_LDO_EN_REG,
 		.enable_mask = BIT(5),
+		.enable_time = 400,
 		.owner = THIS_MODULE,
 	}, {
 		.name = "LDO_REG7",
@@ -268,6 +274,7 @@ static const struct regulator_desc rk808_reg[] = {
 		.vsel_mask = RK808_LDO_VSEL_MASK,
 		.enable_reg = RK808_LDO_EN_REG,
 		.enable_mask = BIT(6),
+		.enable_time = 400,
 		.owner = THIS_MODULE,
 	}, {
 		.name = "LDO_REG8",
@@ -282,6 +289,7 @@ static const struct regulator_desc rk808_reg[] = {
 		.vsel_mask = RK808_LDO_VSEL_MASK,
 		.enable_reg = RK808_LDO_EN_REG,
 		.enable_mask = BIT(7),
+		.enable_time = 400,
 		.owner = THIS_MODULE,
 	}, {
 		.name = "SWITCH_REG1",
diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c
index adab82d5279..697be114e21 100644
--- a/drivers/regulator/s2mps11.c
+++ b/drivers/regulator/s2mps11.c
@@ -479,7 +479,7 @@ static struct regulator_ops s2mps14_reg_ops = {
 	.enable_mask	= S2MPS14_ENABLE_MASK		\
 }
 
-#define regulator_desc_s2mps14_buck(num, min, step) {		\
+#define regulator_desc_s2mps14_buck(num, min, step, min_sel) {	\
 	.name		= "BUCK"#num,				\
 	.id		= S2MPS14_BUCK##num,			\
 	.ops		= &s2mps14_reg_ops,			\
@@ -488,7 +488,7 @@ static struct regulator_ops s2mps14_reg_ops = {
 	.min_uV		= min,					\
 	.uV_step	= step,					\
 	.n_voltages	= S2MPS14_BUCK_N_VOLTAGES,		\
-	.linear_min_sel = S2MPS14_BUCK1235_START_SEL,		\
+	.linear_min_sel = min_sel,				\
 	.ramp_delay	= S2MPS14_BUCK_RAMP_DELAY,		\
 	.vsel_reg	= S2MPS14_REG_B1CTRL2 + (num - 1) * 2,	\
 	.vsel_mask	= S2MPS14_BUCK_VSEL_MASK,		\
@@ -522,11 +522,16 @@ static const struct regulator_desc s2mps14_regulators[] = {
 	regulator_desc_s2mps14_ldo(23, MIN_800_MV, STEP_25_MV),
 	regulator_desc_s2mps14_ldo(24, MIN_1800_MV, STEP_25_MV),
 	regulator_desc_s2mps14_ldo(25, MIN_1800_MV, STEP_25_MV),
-	regulator_desc_s2mps14_buck(1, MIN_600_MV, STEP_6_25_MV),
-	regulator_desc_s2mps14_buck(2, MIN_600_MV, STEP_6_25_MV),
-	regulator_desc_s2mps14_buck(3, MIN_600_MV, STEP_6_25_MV),
-	regulator_desc_s2mps14_buck(4, MIN_1400_MV, STEP_12_5_MV),
-	regulator_desc_s2mps14_buck(5, MIN_600_MV, STEP_6_25_MV),
+	regulator_desc_s2mps14_buck(1, MIN_600_MV, STEP_6_25_MV,
+				    S2MPS14_BUCK1235_START_SEL),
+	regulator_desc_s2mps14_buck(2, MIN_600_MV, STEP_6_25_MV,
+				    S2MPS14_BUCK1235_START_SEL),
+	regulator_desc_s2mps14_buck(3, MIN_600_MV, STEP_6_25_MV,
+				    S2MPS14_BUCK1235_START_SEL),
+	regulator_desc_s2mps14_buck(4, MIN_1400_MV, STEP_12_5_MV,
+				    S2MPS14_BUCK4_START_SEL),
+	regulator_desc_s2mps14_buck(5, MIN_600_MV, STEP_6_25_MV,
+				    S2MPS14_BUCK1235_START_SEL),
 };
 
 static int s2mps14_pmic_enable_ext_control(struct s2mps11_info *s2mps11,
diff --git a/drivers/reset/reset-sunxi.c b/drivers/reset/reset-sunxi.c
index a94e7a7820b..51272b5d755 100644
--- a/drivers/reset/reset-sunxi.c
+++ b/drivers/reset/reset-sunxi.c
@@ -102,6 +102,8 @@ static int sunxi_reset_init(struct device_node *np)
 		goto err_alloc;
 	}
 
+	spin_lock_init(&data->lock);
+
 	data->rcdev.owner = THIS_MODULE;
 	data->rcdev.nr_resets = size * 32;
 	data->rcdev.ops = &sunxi_reset_ops;
@@ -157,6 +159,8 @@ static int sunxi_reset_probe(struct platform_device *pdev)
 	if (IS_ERR(data->membase))
 		return PTR_ERR(data->membase);
 
+	spin_lock_init(&data->lock);
+
 	data->rcdev.owner = THIS_MODULE;
 	data->rcdev.nr_resets = resource_size(res) * 32;
 	data->rcdev.ops = &sunxi_reset_ops;
diff --git a/drivers/rtc/rtc-isl12057.c b/drivers/rtc/rtc-isl12057.c
index 455b601d731..8c3f60737df 100644
--- a/drivers/rtc/rtc-isl12057.c
+++ b/drivers/rtc/rtc-isl12057.c
@@ -88,7 +88,7 @@ static void isl12057_rtc_regs_to_tm(struct rtc_time *tm, u8 *regs)
 	tm->tm_min = bcd2bin(regs[ISL12057_REG_RTC_MN]);
 
 	if (regs[ISL12057_REG_RTC_HR] & ISL12057_REG_RTC_HR_MIL) { /* AM/PM */
-		tm->tm_hour = bcd2bin(regs[ISL12057_REG_RTC_HR] & 0x0f);
+		tm->tm_hour = bcd2bin(regs[ISL12057_REG_RTC_HR] & 0x1f);
 		if (regs[ISL12057_REG_RTC_HR] & ISL12057_REG_RTC_HR_PM)
 			tm->tm_hour += 12;
 	} else {					    /* 24 hour mode */
@@ -97,7 +97,7 @@ static void isl12057_rtc_regs_to_tm(struct rtc_time *tm, u8 *regs)
 
 	tm->tm_mday = bcd2bin(regs[ISL12057_REG_RTC_DT]);
 	tm->tm_wday = bcd2bin(regs[ISL12057_REG_RTC_DW]) - 1; /* starts at 1 */
-	tm->tm_mon  = bcd2bin(regs[ISL12057_REG_RTC_MO]) - 1; /* starts at 1 */
+	tm->tm_mon  = bcd2bin(regs[ISL12057_REG_RTC_MO] & 0x1f) - 1; /* ditto */
 	tm->tm_year = bcd2bin(regs[ISL12057_REG_RTC_YR]) + 100;
 }
 
diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c
index 21142e6574a..828cb9983cc 100644
--- a/drivers/rtc/rtc-omap.c
+++ b/drivers/rtc/rtc-omap.c
@@ -416,6 +416,8 @@ static int __init omap_rtc_probe(struct platform_device *pdev)
 		rtc_writel(KICK1_VALUE, OMAP_RTC_KICK1_REG);
 	}
 
+	device_init_wakeup(&pdev->dev, true);
+
 	rtc = devm_rtc_device_register(&pdev->dev, pdev->name,
 			&omap_rtc_ops, THIS_MODULE);
 	if (IS_ERR(rtc)) {
@@ -431,8 +433,10 @@ static int __init omap_rtc_probe(struct platform_device *pdev)
 	rtc_write(0, OMAP_RTC_INTERRUPTS_REG);
 
 	/* enable RTC functional clock */
-	if (id_entry->driver_data & OMAP_RTC_HAS_32KCLK_EN)
-		rtc_writel(OMAP_RTC_OSC_32KCLK_EN, OMAP_RTC_OSC_REG);
+	if (id_entry->driver_data & OMAP_RTC_HAS_32KCLK_EN) {
+		reg = rtc_read(OMAP_RTC_OSC_REG);
+		rtc_writel(reg | OMAP_RTC_OSC_32KCLK_EN, OMAP_RTC_OSC_REG);
+	}
 
 	/* clear old status */
 	reg = rtc_read(OMAP_RTC_STATUS_REG);
@@ -482,8 +486,6 @@ static int __init omap_rtc_probe(struct platform_device *pdev)
 	 *    is write-only, and always reads as zero...)
 	 */
 
-	device_init_wakeup(&pdev->dev, true);
-
 	if (new_ctrl & (u8) OMAP_RTC_CTRL_SPLIT)
 		pr_info("%s: split power mode\n", pdev->name);
 
@@ -493,6 +495,7 @@ static int __init omap_rtc_probe(struct platform_device *pdev)
 	return 0;
 
 fail0:
+	device_init_wakeup(&pdev->dev, false);
 	if (id_entry->driver_data & OMAP_RTC_HAS_KICKER)
 		rtc_writel(0, OMAP_RTC_KICK0_REG);
 	pm_runtime_put_sync(&pdev->dev);
diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c
index 806072238c0..22a612b0674 100644
--- a/drivers/rtc/rtc-s3c.c
+++ b/drivers/rtc/rtc-s3c.c
@@ -849,6 +849,7 @@ static struct s3c_rtc_data const s3c2443_rtc_data = {
 
 static struct s3c_rtc_data const s3c6410_rtc_data = {
 	.max_user_freq		= 32768,
+	.needs_src_clk		= true,
 	.irq_handler		= s3c6410_rtc_irq,
 	.set_freq		= s3c6410_rtc_setfreq,
 	.enable_tick		= s3c6410_rtc_enable_tick,
diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c
index 8754c33361e..28799d39db8 100644
--- a/drivers/rtc/rtc-s5m.c
+++ b/drivers/rtc/rtc-s5m.c
@@ -832,6 +832,7 @@ static SIMPLE_DEV_PM_OPS(s5m_rtc_pm_ops, s5m_rtc_suspend, s5m_rtc_resume);
 static const struct platform_device_id s5m_rtc_id[] = {
 	{ "s5m-rtc",		S5M8767X },
 	{ "s2mps14-rtc",	S2MPS14X },
+	{ },
 };
 
 static struct platform_driver s5m_rtc_driver = {
diff --git a/drivers/rtc/rtc-sirfsoc.c b/drivers/rtc/rtc-sirfsoc.c
index 76e38007ba9..24ba97d3286 100644
--- a/drivers/rtc/rtc-sirfsoc.c
+++ b/drivers/rtc/rtc-sirfsoc.c
@@ -286,14 +286,6 @@ static int sirfsoc_rtc_probe(struct platform_device *pdev)
 	rtc_div = ((32768 / RTC_HZ) / 2) - 1;
 	sirfsoc_rtc_iobrg_writel(rtc_div, rtcdrv->rtc_base + RTC_DIV);
 
-	rtcdrv->rtc = devm_rtc_device_register(&pdev->dev, pdev->name,
-			&sirfsoc_rtc_ops, THIS_MODULE);
-	if (IS_ERR(rtcdrv->rtc)) {
-		err = PTR_ERR(rtcdrv->rtc);
-		dev_err(&pdev->dev, "can't register RTC device\n");
-		return err;
-	}
-
 	/* 0x3 -> RTC_CLK */
 	sirfsoc_rtc_iobrg_writel(SIRFSOC_RTC_CLK,
 			rtcdrv->rtc_base + RTC_CLOCK_SWITCH);
@@ -308,6 +300,14 @@ static int sirfsoc_rtc_probe(struct platform_device *pdev)
 	rtcdrv->overflow_rtc =
 		sirfsoc_rtc_iobrg_readl(rtcdrv->rtc_base + RTC_SW_VALUE);
 
+	rtcdrv->rtc = devm_rtc_device_register(&pdev->dev, pdev->name,
+			&sirfsoc_rtc_ops, THIS_MODULE);
+	if (IS_ERR(rtcdrv->rtc)) {
+		err = PTR_ERR(rtcdrv->rtc);
+		dev_err(&pdev->dev, "can't register RTC device\n");
+		return err;
+	}
+
 	rtcdrv->irq = platform_get_irq(pdev, 0);
 	err = devm_request_irq(
 			&pdev->dev,
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 99485415dcc..91e97ec0141 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -44,6 +44,7 @@
 #include <linux/hrtimer.h>
 #include <linux/ktime.h>
 #include <asm/facility.h>
+#include <linux/crypto.h>
 
 #include "ap_bus.h"
 
@@ -71,7 +72,7 @@ MODULE_AUTHOR("IBM Corporation");
 MODULE_DESCRIPTION("Adjunct Processor Bus driver, " \
 		   "Copyright IBM Corp. 2006, 2012");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("z90crypt");
+MODULE_ALIAS_CRYPTO("z90crypt");
 
 /*
  * Module parameter
diff --git a/drivers/s390/kvm/virtio_ccw.c b/drivers/s390/kvm/virtio_ccw.c
index bda52f18e96..397e6b8b965 100644
--- a/drivers/s390/kvm/virtio_ccw.c
+++ b/drivers/s390/kvm/virtio_ccw.c
@@ -64,6 +64,7 @@ struct virtio_ccw_device {
 	bool is_thinint;
 	bool going_away;
 	bool device_lost;
+	unsigned int config_ready;
 	void *airq_info;
 };
 
@@ -758,8 +759,11 @@ static void virtio_ccw_get_config(struct virtio_device *vdev,
 	if (ret)
 		goto out_free;
 
-	memcpy(vcdev->config, config_area, sizeof(vcdev->config));
-	memcpy(buf, &vcdev->config[offset], len);
+	memcpy(vcdev->config, config_area, offset + len);
+	if (buf)
+		memcpy(buf, &vcdev->config[offset], len);
+	if (vcdev->config_ready < offset + len)
+		vcdev->config_ready = offset + len;
 
 out_free:
 	kfree(config_area);
@@ -782,6 +786,9 @@ static void virtio_ccw_set_config(struct virtio_device *vdev,
 	if (!config_area)
 		goto out_free;
 
+	/* Make sure we don't overwrite fields. */
+	if (vcdev->config_ready < offset)
+		virtio_ccw_get_config(vdev, 0, NULL, offset);
 	memcpy(&vcdev->config[offset], buf, len);
 	/* Write the config area to the host. */
 	memcpy(config_area, vcdev->config, sizeof(vcdev->config));
diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c
index 0a7325361d2..5f57e3d35e2 100644
--- a/drivers/scsi/3w-9xxx.c
+++ b/drivers/scsi/3w-9xxx.c
@@ -149,7 +149,6 @@ static int twa_reset_sequence(TW_Device_Extension *tw_dev, int soft_reset);
 static int twa_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, char *cdb, int use_sg, TW_SG_Entry *sglistarg);
 static void twa_scsiop_execute_scsi_complete(TW_Device_Extension *tw_dev, int request_id);
 static char *twa_string_lookup(twa_message_type *table, unsigned int aen_code);
-static void twa_unmap_scsi_data(TW_Device_Extension *tw_dev, int request_id);
 
 /* Functions */
 
@@ -1352,11 +1351,11 @@ static irqreturn_t twa_interrupt(int irq, void *dev_instance)
 				}
 
 				/* Now complete the io */
+				scsi_dma_unmap(cmd);
+				cmd->scsi_done(cmd);
 				tw_dev->state[request_id] = TW_S_COMPLETED;
 				twa_free_request_id(tw_dev, request_id);
 				tw_dev->posted_request_count--;
-				tw_dev->srb[request_id]->scsi_done(tw_dev->srb[request_id]);
-				twa_unmap_scsi_data(tw_dev, request_id);
 			}
 
 			/* Check for valid status after each drain */
@@ -1414,26 +1413,6 @@ static void twa_load_sgl(TW_Device_Extension *tw_dev, TW_Command_Full *full_comm
 	}
 } /* End twa_load_sgl() */
 
-/* This function will perform a pci-dma mapping for a scatter gather list */
-static int twa_map_scsi_sg_data(TW_Device_Extension *tw_dev, int request_id)
-{
-	int use_sg;
-	struct scsi_cmnd *cmd = tw_dev->srb[request_id];
-
-	use_sg = scsi_dma_map(cmd);
-	if (!use_sg)
-		return 0;
-	else if (use_sg < 0) {
-		TW_PRINTK(tw_dev->host, TW_DRIVER, 0x1c, "Failed to map scatter gather list");
-		return 0;
-	}
-
-	cmd->SCp.phase = TW_PHASE_SGLIST;
-	cmd->SCp.have_data_in = use_sg;
-
-	return use_sg;
-} /* End twa_map_scsi_sg_data() */
-
 /* This function will poll for a response interrupt of a request */
 static int twa_poll_response(TW_Device_Extension *tw_dev, int request_id, int seconds)
 {
@@ -1612,9 +1591,11 @@ static int twa_reset_device_extension(TW_Device_Extension *tw_dev)
 		    (tw_dev->state[i] != TW_S_INITIAL) &&
 		    (tw_dev->state[i] != TW_S_COMPLETED)) {
 			if (tw_dev->srb[i]) {
-				tw_dev->srb[i]->result = (DID_RESET << 16);
-				tw_dev->srb[i]->scsi_done(tw_dev->srb[i]);
-				twa_unmap_scsi_data(tw_dev, i);
+				struct scsi_cmnd *cmd = tw_dev->srb[i];
+
+				cmd->result = (DID_RESET << 16);
+				scsi_dma_unmap(cmd);
+				cmd->scsi_done(cmd);
 			}
 		}
 	}
@@ -1793,21 +1774,18 @@ static int twa_scsi_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_
 	/* Save the scsi command for use by the ISR */
 	tw_dev->srb[request_id] = SCpnt;
 
-	/* Initialize phase to zero */
-	SCpnt->SCp.phase = TW_PHASE_INITIAL;
-
 	retval = twa_scsiop_execute_scsi(tw_dev, request_id, NULL, 0, NULL);
 	switch (retval) {
 	case SCSI_MLQUEUE_HOST_BUSY:
+		scsi_dma_unmap(SCpnt);
 		twa_free_request_id(tw_dev, request_id);
-		twa_unmap_scsi_data(tw_dev, request_id);
 		break;
 	case 1:
-		tw_dev->state[request_id] = TW_S_COMPLETED;
-		twa_free_request_id(tw_dev, request_id);
-		twa_unmap_scsi_data(tw_dev, request_id);
 		SCpnt->result = (DID_ERROR << 16);
+		scsi_dma_unmap(SCpnt);
 		done(SCpnt);
+		tw_dev->state[request_id] = TW_S_COMPLETED;
+		twa_free_request_id(tw_dev, request_id);
 		retval = 0;
 	}
 out:
@@ -1875,8 +1853,8 @@ static int twa_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id,
 				command_packet->sg_list[0].address = TW_CPU_TO_SGL(tw_dev->generic_buffer_phys[request_id]);
 				command_packet->sg_list[0].length = cpu_to_le32(TW_MIN_SGL_LENGTH);
 			} else {
-				sg_count = twa_map_scsi_sg_data(tw_dev, request_id);
-				if (sg_count == 0)
+				sg_count = scsi_dma_map(srb);
+				if (sg_count < 0)
 					goto out;
 
 				scsi_for_each_sg(srb, sg, sg_count, i) {
@@ -1991,15 +1969,6 @@ static char *twa_string_lookup(twa_message_type *table, unsigned int code)
 	return(table[index].text);
 } /* End twa_string_lookup() */
 
-/* This function will perform a pci-dma unmap */
-static void twa_unmap_scsi_data(TW_Device_Extension *tw_dev, int request_id)
-{
-	struct scsi_cmnd *cmd = tw_dev->srb[request_id];
-
-	if (cmd->SCp.phase == TW_PHASE_SGLIST)
-		scsi_dma_unmap(cmd);
-} /* End twa_unmap_scsi_data() */
-
 /* This function gets called when a disk is coming on-line */
 static int twa_slave_configure(struct scsi_device *sdev)
 {
diff --git a/drivers/scsi/3w-9xxx.h b/drivers/scsi/3w-9xxx.h
index 040f7214e5b..0fdc83cfa0e 100644
--- a/drivers/scsi/3w-9xxx.h
+++ b/drivers/scsi/3w-9xxx.h
@@ -324,11 +324,6 @@ static twa_message_type twa_error_table[] = {
 #define TW_CURRENT_DRIVER_BUILD 0
 #define TW_CURRENT_DRIVER_BRANCH 0
 
-/* Phase defines */
-#define TW_PHASE_INITIAL 0
-#define TW_PHASE_SINGLE  1
-#define TW_PHASE_SGLIST  2
-
 /* Misc defines */
 #define TW_9550SX_DRAIN_COMPLETED	      0xFFFF
 #define TW_SECTOR_SIZE                        512
diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c
index 6da6cec9a65..2ee2e543ab7 100644
--- a/drivers/scsi/3w-sas.c
+++ b/drivers/scsi/3w-sas.c
@@ -303,26 +303,6 @@ static int twl_post_command_packet(TW_Device_Extension *tw_dev, int request_id)
 	return 0;
 } /* End twl_post_command_packet() */
 
-/* This function will perform a pci-dma mapping for a scatter gather list */
-static int twl_map_scsi_sg_data(TW_Device_Extension *tw_dev, int request_id)
-{
-	int use_sg;
-	struct scsi_cmnd *cmd = tw_dev->srb[request_id];
-
-	use_sg = scsi_dma_map(cmd);
-	if (!use_sg)
-		return 0;
-	else if (use_sg < 0) {
-		TW_PRINTK(tw_dev->host, TW_DRIVER, 0x1, "Failed to map scatter gather list");
-		return 0;
-	}
-
-	cmd->SCp.phase = TW_PHASE_SGLIST;
-	cmd->SCp.have_data_in = use_sg;
-
-	return use_sg;
-} /* End twl_map_scsi_sg_data() */
-
 /* This function hands scsi cdb's to the firmware */
 static int twl_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, char *cdb, int use_sg, TW_SG_Entry_ISO *sglistarg)
 {
@@ -370,8 +350,8 @@ static int twl_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id,
 	if (!sglistarg) {
 		/* Map sglist from scsi layer to cmd packet */
 		if (scsi_sg_count(srb)) {
-			sg_count = twl_map_scsi_sg_data(tw_dev, request_id);
-			if (sg_count == 0)
+			sg_count = scsi_dma_map(srb);
+			if (sg_count <= 0)
 				goto out;
 
 			scsi_for_each_sg(srb, sg, sg_count, i) {
@@ -1115,15 +1095,6 @@ out:
 	return retval;
 } /* End twl_initialize_device_extension() */
 
-/* This function will perform a pci-dma unmap */
-static void twl_unmap_scsi_data(TW_Device_Extension *tw_dev, int request_id)
-{
-	struct scsi_cmnd *cmd = tw_dev->srb[request_id];
-
-	if (cmd->SCp.phase == TW_PHASE_SGLIST)
-		scsi_dma_unmap(cmd);
-} /* End twl_unmap_scsi_data() */
-
 /* This function will handle attention interrupts */
 static int twl_handle_attention_interrupt(TW_Device_Extension *tw_dev)
 {
@@ -1264,11 +1235,11 @@ static irqreturn_t twl_interrupt(int irq, void *dev_instance)
 			}
 
 			/* Now complete the io */
+			scsi_dma_unmap(cmd);
+			cmd->scsi_done(cmd);
 			tw_dev->state[request_id] = TW_S_COMPLETED;
 			twl_free_request_id(tw_dev, request_id);
 			tw_dev->posted_request_count--;
-			tw_dev->srb[request_id]->scsi_done(tw_dev->srb[request_id]);
-			twl_unmap_scsi_data(tw_dev, request_id);
 		}
 
 		/* Check for another response interrupt */
@@ -1413,10 +1384,12 @@ static int twl_reset_device_extension(TW_Device_Extension *tw_dev, int ioctl_res
 		if ((tw_dev->state[i] != TW_S_FINISHED) &&
 		    (tw_dev->state[i] != TW_S_INITIAL) &&
 		    (tw_dev->state[i] != TW_S_COMPLETED)) {
-			if (tw_dev->srb[i]) {
-				tw_dev->srb[i]->result = (DID_RESET << 16);
-				tw_dev->srb[i]->scsi_done(tw_dev->srb[i]);
-				twl_unmap_scsi_data(tw_dev, i);
+			struct scsi_cmnd *cmd = tw_dev->srb[i];
+
+			if (cmd) {
+				cmd->result = (DID_RESET << 16);
+				scsi_dma_unmap(cmd);
+				cmd->scsi_done(cmd);
 			}
 		}
 	}
@@ -1520,9 +1493,6 @@ static int twl_scsi_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_
 	/* Save the scsi command for use by the ISR */
 	tw_dev->srb[request_id] = SCpnt;
 
-	/* Initialize phase to zero */
-	SCpnt->SCp.phase = TW_PHASE_INITIAL;
-
 	retval = twl_scsiop_execute_scsi(tw_dev, request_id, NULL, 0, NULL);
 	if (retval) {
 		tw_dev->state[request_id] = TW_S_COMPLETED;
diff --git a/drivers/scsi/3w-sas.h b/drivers/scsi/3w-sas.h
index d474892701d..fec6449c759 100644
--- a/drivers/scsi/3w-sas.h
+++ b/drivers/scsi/3w-sas.h
@@ -103,10 +103,6 @@ static char *twl_aen_severity_table[] =
 #define TW_CURRENT_DRIVER_BUILD 0
 #define TW_CURRENT_DRIVER_BRANCH 0
 
-/* Phase defines */
-#define TW_PHASE_INITIAL 0
-#define TW_PHASE_SGLIST  2
-
 /* Misc defines */
 #define TW_SECTOR_SIZE                        512
 #define TW_MAX_UNITS			      32
diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c
index 752624e6bc0..b327742b95e 100644
--- a/drivers/scsi/3w-xxxx.c
+++ b/drivers/scsi/3w-xxxx.c
@@ -1284,32 +1284,6 @@ static int tw_initialize_device_extension(TW_Device_Extension *tw_dev)
 	return 0;
 } /* End tw_initialize_device_extension() */
 
-static int tw_map_scsi_sg_data(struct pci_dev *pdev, struct scsi_cmnd *cmd)
-{
-	int use_sg;
-
-	dprintk(KERN_WARNING "3w-xxxx: tw_map_scsi_sg_data()\n");
-
-	use_sg = scsi_dma_map(cmd);
-	if (use_sg < 0) {
-		printk(KERN_WARNING "3w-xxxx: tw_map_scsi_sg_data(): pci_map_sg() failed.\n");
-		return 0;
-	}
-
-	cmd->SCp.phase = TW_PHASE_SGLIST;
-	cmd->SCp.have_data_in = use_sg;
-
-	return use_sg;
-} /* End tw_map_scsi_sg_data() */
-
-static void tw_unmap_scsi_data(struct pci_dev *pdev, struct scsi_cmnd *cmd)
-{
-	dprintk(KERN_WARNING "3w-xxxx: tw_unmap_scsi_data()\n");
-
-	if (cmd->SCp.phase == TW_PHASE_SGLIST)
-		scsi_dma_unmap(cmd);
-} /* End tw_unmap_scsi_data() */
-
 /* This function will reset a device extension */
 static int tw_reset_device_extension(TW_Device_Extension *tw_dev)
 {
@@ -1332,8 +1306,8 @@ static int tw_reset_device_extension(TW_Device_Extension *tw_dev)
 			srb = tw_dev->srb[i];
 			if (srb != NULL) {
 				srb->result = (DID_RESET << 16);
-				tw_dev->srb[i]->scsi_done(tw_dev->srb[i]);
-				tw_unmap_scsi_data(tw_dev->tw_pci_dev, tw_dev->srb[i]);
+				scsi_dma_unmap(srb);
+				srb->scsi_done(srb);
 			}
 		}
 	}
@@ -1780,8 +1754,8 @@ static int tw_scsiop_read_write(TW_Device_Extension *tw_dev, int request_id)
 	command_packet->byte8.io.lba = lba;
 	command_packet->byte6.block_count = num_sectors;
 
-	use_sg = tw_map_scsi_sg_data(tw_dev->tw_pci_dev, tw_dev->srb[request_id]);
-	if (!use_sg)
+	use_sg = scsi_dma_map(srb);
+	if (use_sg <= 0)
 		return 1;
 
 	scsi_for_each_sg(tw_dev->srb[request_id], sg, use_sg, i) {
@@ -1968,9 +1942,6 @@ static int tw_scsi_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_c
 	/* Save the scsi command for use by the ISR */
 	tw_dev->srb[request_id] = SCpnt;
 
-	/* Initialize phase to zero */
-	SCpnt->SCp.phase = TW_PHASE_INITIAL;
-
 	switch (*command) {
 		case READ_10:
 		case READ_6:
@@ -2198,12 +2169,11 @@ static irqreturn_t tw_interrupt(int irq, void *dev_instance)
 
 				/* Now complete the io */
 				if ((error != TW_ISR_DONT_COMPLETE)) {
+					scsi_dma_unmap(tw_dev->srb[request_id]);
+					tw_dev->srb[request_id]->scsi_done(tw_dev->srb[request_id]);
 					tw_dev->state[request_id] = TW_S_COMPLETED;
 					tw_state_request_finish(tw_dev, request_id);
 					tw_dev->posted_request_count--;
-					tw_dev->srb[request_id]->scsi_done(tw_dev->srb[request_id]);
-					
-					tw_unmap_scsi_data(tw_dev->tw_pci_dev, tw_dev->srb[request_id]);
 				}
 			}
 				
diff --git a/drivers/scsi/3w-xxxx.h b/drivers/scsi/3w-xxxx.h
index 29b0b84ed69..6f65e663d39 100644
--- a/drivers/scsi/3w-xxxx.h
+++ b/drivers/scsi/3w-xxxx.h
@@ -195,11 +195,6 @@ static unsigned char tw_sense_table[][4] =
 #define TW_AEN_SMART_FAIL        0x000F
 #define TW_AEN_SBUF_FAIL         0x0024
 
-/* Phase defines */
-#define TW_PHASE_INITIAL 0
-#define TW_PHASE_SINGLE 1
-#define TW_PHASE_SGLIST 2
-
 /* Misc defines */
 #define TW_ALIGNMENT_6000		      64 /* 64 bytes */
 #define TW_ALIGNMENT_7000                     4  /* 4 bytes */
diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c
index 45da3c82332..ab1c09eaa5b 100644
--- a/drivers/scsi/NCR5380.c
+++ b/drivers/scsi/NCR5380.c
@@ -2647,14 +2647,14 @@ static void NCR5380_dma_complete(NCR5380_instance * instance) {
  *
  * Purpose : abort a command
  *
- * Inputs : cmd - the Scsi_Cmnd to abort, code - code to set the 
- *      host byte of the result field to, if zero DID_ABORTED is 
+ * Inputs : cmd - the Scsi_Cmnd to abort, code - code to set the
+ *      host byte of the result field to, if zero DID_ABORTED is
  *      used.
  *
- * Returns : 0 - success, -1 on failure.
+ * Returns : SUCCESS - success, FAILED on failure.
  *
- *	XXX - there is no way to abort the command that is currently 
- *	connected, you have to wait for it to complete.  If this is 
+ *	XXX - there is no way to abort the command that is currently
+ *	connected, you have to wait for it to complete.  If this is
  *	a problem, we could implement longjmp() / setjmp(), setjmp()
  *	called where the loop started in NCR5380_main().
  *
@@ -2704,7 +2704,7 @@ static int NCR5380_abort(Scsi_Cmnd * cmd) {
  * aborted flag and get back into our main loop.
  */
 
-		return 0;
+		return SUCCESS;
 	}
 #endif
 
diff --git a/drivers/scsi/aha1740.c b/drivers/scsi/aha1740.c
index 5f3101797c9..31ace4bef8f 100644
--- a/drivers/scsi/aha1740.c
+++ b/drivers/scsi/aha1740.c
@@ -531,7 +531,7 @@ static int aha1740_eh_abort_handler (Scsi_Cmnd *dummy)
  * quiet as possible...
  */
 
-	return 0;
+	return SUCCESS;
 }
 
 static struct scsi_host_template aha1740_template = {
diff --git a/drivers/scsi/atari_NCR5380.c b/drivers/scsi/atari_NCR5380.c
index 79e6f045c2a..e3bbc0a0f9f 100644
--- a/drivers/scsi/atari_NCR5380.c
+++ b/drivers/scsi/atari_NCR5380.c
@@ -2607,7 +2607,7 @@ static void NCR5380_reselect(struct Scsi_Host *instance)
  *	host byte of the result field to, if zero DID_ABORTED is
  *	used.
  *
- * Returns : 0 - success, -1 on failure.
+ * Returns : SUCCESS - success, FAILED on failure.
  *
  * XXX - there is no way to abort the command that is currently
  *	 connected, you have to wait for it to complete.  If this is
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index 30d74a06b99..be4586b788d 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -586,7 +586,6 @@ static struct beiscsi_hba *beiscsi_hba_alloc(struct pci_dev *pcidev)
 			"beiscsi_hba_alloc - iscsi_host_alloc failed\n");
 		return NULL;
 	}
-	shost->dma_boundary = pcidev->dma_mask;
 	shost->max_id = BE2_MAX_SESSIONS;
 	shost->max_channel = 0;
 	shost->max_cmd_len = BEISCSI_MAX_CMD_LEN;
@@ -5736,9 +5735,9 @@ free_port:
 hba_free:
 	if (phba->msix_enabled)
 		pci_disable_msix(phba->pcidev);
-	iscsi_host_remove(phba->shost);
 	pci_dev_put(phba->pcidev);
 	iscsi_host_free(phba->shost);
+	pci_set_drvdata(pcidev, NULL);
 disable_pci:
 	pci_disable_device(pcidev);
 	return ret;
diff --git a/drivers/scsi/esas2r/esas2r_main.c b/drivers/scsi/esas2r/esas2r_main.c
index 6504a195c87..45aa684f8b7 100644
--- a/drivers/scsi/esas2r/esas2r_main.c
+++ b/drivers/scsi/esas2r/esas2r_main.c
@@ -1057,7 +1057,7 @@ int esas2r_eh_abort(struct scsi_cmnd *cmd)
 
 		cmd->scsi_done(cmd);
 
-		return 0;
+		return SUCCESS;
 	}
 
 	spin_lock_irqsave(&a->queue_lock, flags);
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 2a9578c116b..c3bdca7bf1e 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -683,6 +683,7 @@ static void ipr_init_ipr_cmnd(struct ipr_cmnd *ipr_cmd,
 	ipr_reinit_ipr_cmnd(ipr_cmd);
 	ipr_cmd->u.scratch = 0;
 	ipr_cmd->sibling = NULL;
+	ipr_cmd->eh_comp = NULL;
 	ipr_cmd->fast_done = fast_done;
 	init_timer(&ipr_cmd->timer);
 }
@@ -848,6 +849,8 @@ static void ipr_scsi_eh_done(struct ipr_cmnd *ipr_cmd)
 
 	scsi_dma_unmap(ipr_cmd->scsi_cmd);
 	scsi_cmd->scsi_done(scsi_cmd);
+	if (ipr_cmd->eh_comp)
+		complete(ipr_cmd->eh_comp);
 	list_add_tail(&ipr_cmd->queue, &ipr_cmd->hrrq->hrrq_free_q);
 }
 
@@ -4853,6 +4856,84 @@ static int ipr_slave_alloc(struct scsi_device *sdev)
 	return rc;
 }
 
+/**
+ * ipr_match_lun - Match function for specified LUN
+ * @ipr_cmd:	ipr command struct
+ * @device:		device to match (sdev)
+ *
+ * Returns:
+ *	1 if command matches sdev / 0 if command does not match sdev
+ **/
+static int ipr_match_lun(struct ipr_cmnd *ipr_cmd, void *device)
+{
+	if (ipr_cmd->scsi_cmd && ipr_cmd->scsi_cmd->device == device)
+		return 1;
+	return 0;
+}
+
+/**
+ * ipr_wait_for_ops - Wait for matching commands to complete
+ * @ipr_cmd:	ipr command struct
+ * @device:		device to match (sdev)
+ * @match:		match function to use
+ *
+ * Returns:
+ *	SUCCESS / FAILED
+ **/
+static int ipr_wait_for_ops(struct ipr_ioa_cfg *ioa_cfg, void *device,
+			    int (*match)(struct ipr_cmnd *, void *))
+{
+	struct ipr_cmnd *ipr_cmd;
+	int wait;
+	unsigned long flags;
+	struct ipr_hrr_queue *hrrq;
+	signed long timeout = IPR_ABORT_TASK_TIMEOUT;
+	DECLARE_COMPLETION_ONSTACK(comp);
+
+	ENTER;
+	do {
+		wait = 0;
+
+		for_each_hrrq(hrrq, ioa_cfg) {
+			spin_lock_irqsave(hrrq->lock, flags);
+			list_for_each_entry(ipr_cmd, &hrrq->hrrq_pending_q, queue) {
+				if (match(ipr_cmd, device)) {
+					ipr_cmd->eh_comp = &comp;
+					wait++;
+				}
+			}
+			spin_unlock_irqrestore(hrrq->lock, flags);
+		}
+
+		if (wait) {
+			timeout = wait_for_completion_timeout(&comp, timeout);
+
+			if (!timeout) {
+				wait = 0;
+
+				for_each_hrrq(hrrq, ioa_cfg) {
+					spin_lock_irqsave(hrrq->lock, flags);
+					list_for_each_entry(ipr_cmd, &hrrq->hrrq_pending_q, queue) {
+						if (match(ipr_cmd, device)) {
+							ipr_cmd->eh_comp = NULL;
+							wait++;
+						}
+					}
+					spin_unlock_irqrestore(hrrq->lock, flags);
+				}
+
+				if (wait)
+					dev_err(&ioa_cfg->pdev->dev, "Timed out waiting for aborted commands\n");
+				LEAVE;
+				return wait ? FAILED : SUCCESS;
+			}
+		}
+	} while (wait);
+
+	LEAVE;
+	return SUCCESS;
+}
+
 static int ipr_eh_host_reset(struct scsi_cmnd *cmd)
 {
 	struct ipr_ioa_cfg *ioa_cfg;
@@ -5072,11 +5153,17 @@ static int __ipr_eh_dev_reset(struct scsi_cmnd *scsi_cmd)
 static int ipr_eh_dev_reset(struct scsi_cmnd *cmd)
 {
 	int rc;
+	struct ipr_ioa_cfg *ioa_cfg;
+
+	ioa_cfg = (struct ipr_ioa_cfg *) cmd->device->host->hostdata;
 
 	spin_lock_irq(cmd->device->host->host_lock);
 	rc = __ipr_eh_dev_reset(cmd);
 	spin_unlock_irq(cmd->device->host->host_lock);
 
+	if (rc == SUCCESS)
+		rc = ipr_wait_for_ops(ioa_cfg, cmd->device, ipr_match_lun);
+
 	return rc;
 }
 
@@ -5254,13 +5341,18 @@ static int ipr_eh_abort(struct scsi_cmnd *scsi_cmd)
 {
 	unsigned long flags;
 	int rc;
+	struct ipr_ioa_cfg *ioa_cfg;
 
 	ENTER;
 
+	ioa_cfg = (struct ipr_ioa_cfg *) scsi_cmd->device->host->hostdata;
+
 	spin_lock_irqsave(scsi_cmd->device->host->host_lock, flags);
 	rc = ipr_cancel_op(scsi_cmd);
 	spin_unlock_irqrestore(scsi_cmd->device->host->host_lock, flags);
 
+	if (rc == SUCCESS)
+		rc = ipr_wait_for_ops(ioa_cfg, scsi_cmd->device, ipr_match_lun);
 	LEAVE;
 	return rc;
 }
diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h
index d0201ceb4aa..ae4626f6420 100644
--- a/drivers/scsi/ipr.h
+++ b/drivers/scsi/ipr.h
@@ -270,7 +270,7 @@
 #define IPR_RUNTIME_RESET				0x40000000
 
 #define IPR_IPL_INIT_MIN_STAGE_TIME			5
-#define IPR_IPL_INIT_DEFAULT_STAGE_TIME                 15
+#define IPR_IPL_INIT_DEFAULT_STAGE_TIME                 30
 #define IPR_IPL_INIT_STAGE_UNKNOWN			0x0
 #define IPR_IPL_INIT_STAGE_TRANSOP			0xB0000000
 #define IPR_IPL_INIT_STAGE_MASK				0xff000000
@@ -1608,6 +1608,7 @@ struct ipr_cmnd {
 		struct scsi_device *sdev;
 	} u;
 
+	struct completion *eh_comp;
 	struct ipr_hrr_queue *hrrq;
 	struct ipr_ioa_cfg *ioa_cfg;
 };
diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c
index 62b58d38ce2..60de66252fa 100644
--- a/drivers/scsi/libsas/sas_discover.c
+++ b/drivers/scsi/libsas/sas_discover.c
@@ -500,6 +500,7 @@ static void sas_revalidate_domain(struct work_struct *work)
 	struct sas_discovery_event *ev = to_sas_discovery_event(work);
 	struct asd_sas_port *port = ev->port;
 	struct sas_ha_struct *ha = port->ha;
+	struct domain_device *ddev = port->port_dev;
 
 	/* prevent revalidation from finding sata links in recovery */
 	mutex_lock(&ha->disco_mutex);
@@ -514,8 +515,9 @@ static void sas_revalidate_domain(struct work_struct *work)
 	SAS_DPRINTK("REVALIDATING DOMAIN on port %d, pid:%d\n", port->id,
 		    task_pid_nr(current));
 
-	if (port->port_dev)
-		res = sas_ex_revalidate_domain(port->port_dev);
+	if (ddev && (ddev->dev_type == SAS_FANOUT_EXPANDER_DEVICE ||
+		     ddev->dev_type == SAS_EDGE_EXPANDER_DEVICE))
+		res = sas_ex_revalidate_domain(ddev);
 
 	SAS_DPRINTK("done REVALIDATING DOMAIN on port %d, pid:%d, res 0x%x\n",
 		    port->id, task_pid_nr(current), res);
diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
index ac5d94cfd52..2485255f341 100644
--- a/drivers/scsi/megaraid.c
+++ b/drivers/scsi/megaraid.c
@@ -1945,7 +1945,7 @@ megaraid_abort_and_reset(adapter_t *adapter, Scsi_Cmnd *cmd, int aor)
 	     cmd->device->id, (u32)cmd->device->lun);
 
 	if(list_empty(&adapter->pending_list))
-		return FALSE;
+		return FAILED;
 
 	list_for_each_safe(pos, next, &adapter->pending_list) {
 
@@ -1968,7 +1968,7 @@ megaraid_abort_and_reset(adapter_t *adapter, Scsi_Cmnd *cmd, int aor)
 					(aor==SCB_ABORT) ? "ABORTING":"RESET",
 					scb->idx);
 
-				return FALSE;
+				return FAILED;
 			}
 			else {
 
@@ -1993,12 +1993,12 @@ megaraid_abort_and_reset(adapter_t *adapter, Scsi_Cmnd *cmd, int aor)
 				list_add_tail(SCSI_LIST(cmd),
 						&adapter->completed_list);
 
-				return TRUE;
+				return SUCCESS;
 			}
 		}
 	}
 
-	return FALSE;
+	return FAILED;
 }
 
 static inline int
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 5640ad1c821..6e503802947 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -1008,7 +1008,7 @@ megasas_issue_blocked_abort_cmd(struct megasas_instance *instance,
 		cpu_to_le32(upper_32_bits(cmd_to_abort->frame_phys_addr));
 
 	cmd->sync_cmd = 1;
-	cmd->cmd_status = 0xFF;
+	cmd->cmd_status = ENODATA;
 
 	instance->instancet->issue_dcmd(instance, cmd);
 
@@ -3556,7 +3556,6 @@ static int megasas_create_frame_pool(struct megasas_instance *instance)
 	int i;
 	u32 max_cmd;
 	u32 sge_sz;
-	u32 sgl_sz;
 	u32 total_sz;
 	u32 frame_count;
 	struct megasas_cmd *cmd;
@@ -3575,24 +3574,23 @@ static int megasas_create_frame_pool(struct megasas_instance *instance)
 	}
 
 	/*
-	 * Calculated the number of 64byte frames required for SGL
-	 */
-	sgl_sz = sge_sz * instance->max_num_sge;
-	frame_count = (sgl_sz + MEGAMFI_FRAME_SIZE - 1) / MEGAMFI_FRAME_SIZE;
-	frame_count = 15;
-
-	/*
-	 * We need one extra frame for the MFI command
+	 * For MFI controllers.
+	 * max_num_sge = 60
+	 * max_sge_sz  = 16 byte (sizeof megasas_sge_skinny)
+	 * Total 960 byte (15 MFI frame of 64 byte)
+	 *
+	 * Fusion adapter require only 3 extra frame.
+	 * max_num_sge = 16 (defined as MAX_IOCTL_SGE)
+	 * max_sge_sz  = 12 byte (sizeof  megasas_sge64)
+	 * Total 192 byte (3 MFI frame of 64 byte)
 	 */
-	frame_count++;
-
+	frame_count = instance->ctrl_context ? (3 + 1) : (15 + 1);
 	total_sz = MEGAMFI_FRAME_SIZE * frame_count;
 	/*
 	 * Use DMA pool facility provided by PCI layer
 	 */
 	instance->frame_dma_pool = pci_pool_create("megasas frame pool",
-						   instance->pdev, total_sz, 64,
-						   0);
+					instance->pdev, total_sz, 256, 0);
 
 	if (!instance->frame_dma_pool) {
 		printk(KERN_DEBUG "megasas: failed to setup frame pool\n");
diff --git a/drivers/scsi/megaraid/megaraid_sas_fp.c b/drivers/scsi/megaraid/megaraid_sas_fp.c
index 685e6f391fe..7d2d424bc8d 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fp.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fp.c
@@ -170,6 +170,7 @@ void MR_PopulateDrvRaidMap(struct megasas_instance *instance)
 	struct MR_FW_RAID_MAP_ALL     *fw_map_old    = NULL;
 	struct MR_FW_RAID_MAP         *pFwRaidMap    = NULL;
 	int i;
+	u16 ld_count;
 
 
 	struct MR_DRV_RAID_MAP_ALL *drv_map =
@@ -183,14 +184,16 @@ void MR_PopulateDrvRaidMap(struct megasas_instance *instance)
 		/* New Raid map will not set totalSize, so keep expected value
 		 * for legacy code in ValidateMapInfo
 		 */
-		pDrvRaidMap->totalSize = sizeof(struct MR_FW_RAID_MAP_EXT);
+		pDrvRaidMap->totalSize =
+			cpu_to_le32(sizeof(struct MR_FW_RAID_MAP_EXT));
 	} else {
 		fw_map_old = (struct MR_FW_RAID_MAP_ALL *)
 			fusion->ld_map[(instance->map_id & 1)];
 		pFwRaidMap = &fw_map_old->raidMap;
+		ld_count = (u16)le32_to_cpu(pFwRaidMap->ldCount);
 
 #if VD_EXT_DEBUG
-		for (i = 0; i < pFwRaidMap->ldCount; i++) {
+		for (i = 0; i < ld_count; i++) {
 			dev_dbg(&instance->pdev->dev, "(%d) :Index 0x%x "
 				"Target Id 0x%x Seq Num 0x%x Size 0/%llx\n",
 				instance->unique_id, i,
@@ -202,12 +205,15 @@ void MR_PopulateDrvRaidMap(struct megasas_instance *instance)
 
 		memset(drv_map, 0, fusion->drv_map_sz);
 		pDrvRaidMap->totalSize = pFwRaidMap->totalSize;
-		pDrvRaidMap->ldCount = pFwRaidMap->ldCount;
+		pDrvRaidMap->ldCount = (__le16)cpu_to_le16(ld_count);
 		pDrvRaidMap->fpPdIoTimeoutSec = pFwRaidMap->fpPdIoTimeoutSec;
 		for (i = 0; i < MAX_RAIDMAP_LOGICAL_DRIVES + MAX_RAIDMAP_VIEWS; i++)
 			pDrvRaidMap->ldTgtIdToLd[i] =
 				(u8)pFwRaidMap->ldTgtIdToLd[i];
-		for (i = 0; i < pDrvRaidMap->ldCount; i++) {
+		for (i = (MAX_RAIDMAP_LOGICAL_DRIVES + MAX_RAIDMAP_VIEWS);
+			i < MAX_LOGICAL_DRIVES_EXT; i++)
+			pDrvRaidMap->ldTgtIdToLd[i] = 0xff;
+		for (i = 0; i < ld_count; i++) {
 			pDrvRaidMap->ldSpanMap[i] = pFwRaidMap->ldSpanMap[i];
 #if VD_EXT_DEBUG
 			dev_dbg(&instance->pdev->dev,
@@ -249,7 +255,7 @@ u8 MR_ValidateMapInfo(struct megasas_instance *instance)
 	struct LD_LOAD_BALANCE_INFO *lbInfo;
 	PLD_SPAN_INFO ldSpanInfo;
 	struct MR_LD_RAID         *raid;
-	int ldCount, num_lds;
+	u16 ldCount, num_lds;
 	u16 ld;
 	u32 expected_size;
 
@@ -268,7 +274,7 @@ u8 MR_ValidateMapInfo(struct megasas_instance *instance)
 	else
 		expected_size =
 			(sizeof(struct MR_FW_RAID_MAP) - sizeof(struct MR_LD_SPAN_MAP) +
-			(sizeof(struct MR_LD_SPAN_MAP) * le32_to_cpu(pDrvRaidMap->ldCount)));
+			(sizeof(struct MR_LD_SPAN_MAP) * le16_to_cpu(pDrvRaidMap->ldCount)));
 
 	if (le32_to_cpu(pDrvRaidMap->totalSize) != expected_size) {
 		dev_err(&instance->pdev->dev, "map info structure size 0x%x is not matching with ld count\n",
@@ -284,7 +290,7 @@ u8 MR_ValidateMapInfo(struct megasas_instance *instance)
 
 	mr_update_load_balance_params(drv_map, lbInfo);
 
-	num_lds = le32_to_cpu(drv_map->raidMap.ldCount);
+	num_lds = le16_to_cpu(drv_map->raidMap.ldCount);
 
 	/*Convert Raid capability values to CPU arch */
 	for (ldCount = 0; ldCount < num_lds; ldCount++) {
@@ -353,7 +359,7 @@ static int getSpanInfo(struct MR_DRV_RAID_MAP_ALL *map,
 
 	for (ldCount = 0; ldCount < MAX_LOGICAL_DRIVES_EXT; ldCount++) {
 		ld = MR_TargetIdToLdGet(ldCount, map);
-			if (ld >= MAX_LOGICAL_DRIVES_EXT)
+			if (ld >= (MAX_LOGICAL_DRIVES_EXT - 1))
 				continue;
 		raid = MR_LdRaidGet(ld, map);
 		dev_dbg(&instance->pdev->dev, "LD %x: span_depth=%x\n",
@@ -457,7 +463,7 @@ u32 mr_spanset_get_span_block(struct megasas_instance *instance,
 				quad = &map->raidMap.ldSpanMap[ld].
 					spanBlock[span].
 					block_span_info.quad[info];
-				if (le32_to_cpu(quad->diff == 0))
+				if (le32_to_cpu(quad->diff) == 0)
 					return SPAN_INVALID;
 				if (le64_to_cpu(quad->logStart) <= row  &&
 					row <= le64_to_cpu(quad->logEnd)  &&
@@ -520,7 +526,7 @@ static u64  get_row_from_strip(struct megasas_instance *instance,
 				span_set->span_row_data_width) * span_set->diff;
 		for (span = 0, span_offset = 0; span < raid->spanDepth; span++)
 			if (le32_to_cpu(map->raidMap.ldSpanMap[ld].spanBlock[span].
-				block_span_info.noElements >= info+1)) {
+				block_span_info.noElements) >= info+1) {
 				if (strip_offset >=
 					span_set->strip_offset[span])
 					span_offset++;
@@ -1154,7 +1160,7 @@ void mr_update_span_set(struct MR_DRV_RAID_MAP_ALL *map,
 
 	for (ldCount = 0; ldCount < MAX_LOGICAL_DRIVES_EXT; ldCount++) {
 		ld = MR_TargetIdToLdGet(ldCount, map);
-		if (ld >= MAX_LOGICAL_DRIVES_EXT)
+		if (ld >= (MAX_LOGICAL_DRIVES_EXT - 1))
 			continue;
 		raid = MR_LdRaidGet(ld, map);
 		for (element = 0; element < MAX_QUAD_DEPTH; element++) {
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index f37eed682c7..55439563459 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -101,6 +101,8 @@ megasas_enable_intr_fusion(struct megasas_instance *instance)
 {
 	struct megasas_register_set __iomem *regs;
 	regs = instance->reg_set;
+
+	instance->mask_interrupts = 0;
 	/* For Thunderbolt/Invader also clear intr on enable */
 	writel(~0, &regs->outbound_intr_status);
 	readl(&regs->outbound_intr_status);
@@ -109,7 +111,6 @@ megasas_enable_intr_fusion(struct megasas_instance *instance)
 
 	/* Dummy readl to force pci flush */
 	readl(&regs->outbound_intr_mask);
-	instance->mask_interrupts = 0;
 }
 
 /**
@@ -696,12 +697,11 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 		cpu_to_le32(lower_32_bits(ioc_init_handle));
 	init_frame->data_xfer_len = cpu_to_le32(sizeof(struct MPI2_IOC_INIT_REQUEST));
 
-	req_desc.Words = 0;
+	req_desc.u.low = cpu_to_le32(lower_32_bits(cmd->frame_phys_addr));
+	req_desc.u.high = cpu_to_le32(upper_32_bits(cmd->frame_phys_addr));
 	req_desc.MFAIo.RequestFlags =
 		(MEGASAS_REQ_DESCRIPT_FLAGS_MFA <<
-		 MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
-	cpu_to_le32s((u32 *)&req_desc.MFAIo);
-	req_desc.Words |= cpu_to_le64(cmd->frame_phys_addr);
+		MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
 
 	/*
 	 * disable the intr before firing the init frame
@@ -880,7 +880,7 @@ megasas_sync_map_info(struct megasas_instance *instance)
 
 	map = fusion->ld_drv_map[instance->map_id & 1];
 
-	num_lds = le32_to_cpu(map->raidMap.ldCount);
+	num_lds = le16_to_cpu(map->raidMap.ldCount);
 
 	dcmd = &cmd->frame->dcmd;
 
@@ -1173,9 +1173,10 @@ megasas_fire_cmd_fusion(struct megasas_instance *instance,
 			struct megasas_register_set __iomem *regs)
 {
 #if defined(writeq) && defined(CONFIG_64BIT)
-	u64 req_data = (((u64)req_desc_hi << 32) | (u32)req_desc_lo);
+	u64 req_data = (((u64)le32_to_cpu(req_desc_hi) << 32) |
+			le32_to_cpu(req_desc_lo));
 
-	writeq(le64_to_cpu(req_data), &(regs)->inbound_low_queue_port);
+	writeq(req_data, &(regs)->inbound_low_queue_port);
 #else
 	unsigned long flags;
 
@@ -1373,7 +1374,7 @@ megasas_set_pd_lba(struct MPI2_RAID_SCSI_IO_REQUEST *io_request, u8 cdb_len,
 		/* Logical block reference tag */
 		io_request->CDB.EEDP32.PrimaryReferenceTag =
 			cpu_to_be32(ref_tag);
-		io_request->CDB.EEDP32.PrimaryApplicationTagMask = 0xffff;
+		io_request->CDB.EEDP32.PrimaryApplicationTagMask = cpu_to_be16(0xffff);
 		io_request->IoFlags = cpu_to_le16(32); /* Specify 32-byte cdb */
 
 		/* Transfer length */
@@ -1752,9 +1753,19 @@ megasas_build_dcdb_fusion(struct megasas_instance *instance,
 		if (scmd->device->channel < MEGASAS_MAX_PD_CHANNELS)
 			goto NonFastPath;
 
+		/*
+		 * For older firmware, Driver should not access ldTgtIdToLd
+		 * beyond index 127 and for Extended VD firmware, ldTgtIdToLd
+		 * should not go beyond 255.
+		 */
+
+		if ((!fusion->fast_path_io) ||
+			(device_id >= instance->fw_supported_vd_count))
+			goto NonFastPath;
+
 		ld = MR_TargetIdToLdGet(device_id, local_map_ptr);
-		if ((ld >= instance->fw_supported_vd_count) ||
-			(!fusion->fast_path_io))
+
+		if (ld >= instance->fw_supported_vd_count)
 			goto NonFastPath;
 
 		raid = MR_LdRaidGet(ld, local_map_ptr);
@@ -1769,7 +1780,7 @@ megasas_build_dcdb_fusion(struct megasas_instance *instance,
 
 		/* set RAID context values */
 		pRAID_Context->regLockFlags     = REGION_TYPE_SHARED_READ;
-		pRAID_Context->timeoutValue     = raid->fpIoTimeoutForLd;
+		pRAID_Context->timeoutValue     = cpu_to_le16(raid->fpIoTimeoutForLd);
 		pRAID_Context->VirtualDiskTgtId = cpu_to_le16(device_id);
 		pRAID_Context->regLockRowLBA    = 0;
 		pRAID_Context->regLockLength    = 0;
@@ -2254,7 +2265,7 @@ build_mpt_mfi_pass_thru(struct megasas_instance *instance,
 	 * megasas_complete_cmd
 	 */
 
-	if (frame_hdr->flags & MFI_FRAME_DONT_POST_IN_REPLY_QUEUE)
+	if (frame_hdr->flags & cpu_to_le16(MFI_FRAME_DONT_POST_IN_REPLY_QUEUE))
 		cmd->flags = MFI_FRAME_DONT_POST_IN_REPLY_QUEUE;
 
 	fusion = instance->ctrl_context;
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.h b/drivers/scsi/megaraid/megaraid_sas_fusion.h
index 0d183d521bd..a7f216f27ae 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.h
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.h
@@ -304,14 +304,9 @@ struct MPI2_RAID_SCSI_IO_REQUEST {
  * MPT RAID MFA IO Descriptor.
  */
 struct MEGASAS_RAID_MFA_IO_REQUEST_DESCRIPTOR {
-#if   defined(__BIG_ENDIAN_BITFIELD)
-	u32     MessageAddress1:24; /* bits 31:8*/
-	u32     RequestFlags:8;
-#else
 	u32     RequestFlags:8;
-	u32     MessageAddress1:24; /* bits 31:8*/
-#endif
-	u32     MessageAddress2;      /* bits 61:32 */
+	u32     MessageAddress1:24;
+	u32     MessageAddress2;
 };
 
 /* Default Request Descriptor */
diff --git a/drivers/scsi/mpt2sas/mpt2sas_transport.c b/drivers/scsi/mpt2sas/mpt2sas_transport.c
index 0d1d06488a2..e689bf20a3e 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_transport.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_transport.c
@@ -1006,12 +1006,9 @@ mpt2sas_transport_update_links(struct MPT2SAS_ADAPTER *ioc,
 		    &mpt2sas_phy->remote_identify);
 		_transport_add_phy_to_an_existing_port(ioc, sas_node,
 		    mpt2sas_phy, mpt2sas_phy->remote_identify.sas_address);
-	} else {
+	} else
 		memset(&mpt2sas_phy->remote_identify, 0 , sizeof(struct
 		    sas_identify));
-		_transport_del_phy_from_an_existing_port(ioc, sas_node,
-		    mpt2sas_phy);
-	}
 
 	if (mpt2sas_phy->phy)
 		mpt2sas_phy->phy->negotiated_linkrate =
diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c
index d4bafaaebea..3637ae6c017 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_transport.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c
@@ -1003,12 +1003,9 @@ mpt3sas_transport_update_links(struct MPT3SAS_ADAPTER *ioc,
 		    &mpt3sas_phy->remote_identify);
 		_transport_add_phy_to_an_existing_port(ioc, sas_node,
 		    mpt3sas_phy, mpt3sas_phy->remote_identify.sas_address);
-	} else {
+	} else
 		memset(&mpt3sas_phy->remote_identify, 0 , sizeof(struct
 		    sas_identify));
-		_transport_del_phy_from_an_existing_port(ioc, sas_node,
-		    mpt3sas_phy);
-	}
 
 	if (mpt3sas_phy->phy)
 		mpt3sas_phy->phy->negotiated_linkrate =
diff --git a/drivers/scsi/mvsas/mv_sas.c b/drivers/scsi/mvsas/mv_sas.c
index ac52f7c9951..0eb2da8a696 100644
--- a/drivers/scsi/mvsas/mv_sas.c
+++ b/drivers/scsi/mvsas/mv_sas.c
@@ -441,14 +441,11 @@ static u32 mvs_get_ncq_tag(struct sas_task *task, u32 *tag)
 static int mvs_task_prep_ata(struct mvs_info *mvi,
 			     struct mvs_task_exec_info *tei)
 {
-	struct sas_ha_struct *sha = mvi->sas;
 	struct sas_task *task = tei->task;
 	struct domain_device *dev = task->dev;
 	struct mvs_device *mvi_dev = dev->lldd_dev;
 	struct mvs_cmd_hdr *hdr = tei->hdr;
 	struct asd_sas_port *sas_port = dev->port;
-	struct sas_phy *sphy = dev->phy;
-	struct asd_sas_phy *sas_phy = sha->sas_phy[sphy->number];
 	struct mvs_slot_info *slot;
 	void *buf_prd;
 	u32 tag = tei->tag, hdr_tag;
@@ -468,7 +465,7 @@ static int mvs_task_prep_ata(struct mvs_info *mvi,
 	slot->tx = mvi->tx_prod;
 	del_q = TXQ_MODE_I | tag |
 		(TXQ_CMD_STP << TXQ_CMD_SHIFT) |
-		(MVS_PHY_ID << TXQ_PHY_SHIFT) |
+		((sas_port->phy_mask & TXQ_PHY_MASK) << TXQ_PHY_SHIFT) |
 		(mvi_dev->taskfileset << TXQ_SRS_SHIFT);
 	mvi->tx[mvi->tx_prod] = cpu_to_le32(del_q);
 
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 73f9feecda7..272a2646a75 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -1598,7 +1598,7 @@ static int tcm_qla2xxx_check_initiator_node_acl(
 	/*
 	 * Finally register the new FC Nexus with TCM
 	 */
-	__transport_register_session(se_nacl->se_tpg, se_nacl, se_sess, sess);
+	transport_register_session(se_nacl->se_tpg, se_nacl, se_sess, sess);
 
 	return 0;
 }
diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c
index c1d04d4d3c6..9f77d23239a 100644
--- a/drivers/scsi/scsi_devinfo.c
+++ b/drivers/scsi/scsi_devinfo.c
@@ -211,6 +211,7 @@ static struct {
 	{"Medion", "Flash XL  MMC/SD", "2.6D", BLIST_FORCELUN},
 	{"MegaRAID", "LD", NULL, BLIST_FORCELUN},
 	{"MICROP", "4110", NULL, BLIST_NOTQ},
+	{"MSFT", "Virtual HD", NULL, BLIST_NO_RSOC},
 	{"MYLEX", "DACARMRB", "*", BLIST_REPORTLUN2},
 	{"nCipher", "Fastness Crypto", NULL, BLIST_FORCELUN},
 	{"NAKAMICH", "MJ-4.8S", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
@@ -225,6 +226,7 @@ static struct {
 	{"PIONEER", "CD-ROM DRM-624X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
 	{"Promise", "VTrak E610f", NULL, BLIST_SPARSELUN | BLIST_NO_RSOC},
 	{"Promise", "", NULL, BLIST_SPARSELUN},
+	{"QNAP", "iSCSI Storage", NULL, BLIST_MAX_1024},
 	{"QUANTUM", "XP34301", "1071", BLIST_NOTQ},
 	{"REGAL", "CDC-4X", NULL, BLIST_MAX5LUN | BLIST_SINGLELUN},
 	{"SanDisk", "ImageMate CF-SD1", NULL, BLIST_FORCELUN},
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index bc5ff6ff9c7..01a79473350 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1027,7 +1027,7 @@ retry:
 		}
 		/* signal not to enter either branch of the if () below */
 		timeleft = 0;
-		rtn = NEEDS_RETRY;
+		rtn = FAILED;
 	} else {
 		timeleft = wait_for_completion_timeout(&done, timeout);
 		rtn = SUCCESS;
@@ -1067,7 +1067,7 @@ retry:
 			rtn = FAILED;
 			break;
 		}
-	} else if (!rtn) {
+	} else if (rtn != FAILED) {
 		scsi_abort_eh_cmnd(scmd);
 		rtn = FAILED;
 	}
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 50a6e1ac8d9..b1ab509d0e0 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1299,9 +1299,11 @@ scsi_prep_state_check(struct scsi_device *sdev, struct request *req)
 				    "rejecting I/O to dead device\n");
 			ret = BLKPREP_KILL;
 			break;
-		case SDEV_QUIESCE:
 		case SDEV_BLOCK:
 		case SDEV_CREATED_BLOCK:
+			ret = BLKPREP_DEFER;
+			break;
+		case SDEV_QUIESCE:
 			/*
 			 * If the devices is blocked we defer normal commands.
 			 */
@@ -1829,7 +1831,9 @@ static int scsi_mq_prep_fn(struct request *req)
 
 	if (scsi_host_get_prot(shost)) {
 		cmd->prot_sdb = (void *)sg +
-			shost->sg_tablesize * sizeof(struct scatterlist);
+			min_t(unsigned int,
+			      shost->sg_tablesize, SCSI_MAX_SG_SEGMENTS) *
+			sizeof(struct scatterlist);
 		memset(cmd->prot_sdb, 0, sizeof(struct scsi_data_buffer));
 
 		cmd->prot_sdb->table.sgl =
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index ba3f1e8d0d5..f49cb534a82 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -901,6 +901,12 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result,
 	 */
 	if (*bflags & BLIST_MAX_512)
 		blk_queue_max_hw_sectors(sdev->request_queue, 512);
+	/*
+	 * Max 1024 sector transfer length for targets that report incorrect
+	 * max/optimal lengths and relied on the old block layer safe default
+	 */
+	else if (*bflags & BLIST_MAX_1024)
+		blk_queue_max_hw_sectors(sdev->request_queue, 1024);
 
 	/*
 	 * Some devices may not want to have a start command automatically
diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index ae45bd99bae..e05cd7e2d6d 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -396,6 +396,36 @@ static void srp_reconnect_work(struct work_struct *work)
 	}
 }
 
+/**
+ * scsi_request_fn_active() - number of kernel threads inside scsi_request_fn()
+ * @shost: SCSI host for which to count the number of scsi_request_fn() callers.
+ *
+ * To do: add support for scsi-mq in this function.
+ */
+static int scsi_request_fn_active(struct Scsi_Host *shost)
+{
+	struct scsi_device *sdev;
+	struct request_queue *q;
+	int request_fn_active = 0;
+
+	shost_for_each_device(sdev, shost) {
+		q = sdev->request_queue;
+
+		spin_lock_irq(q->queue_lock);
+		request_fn_active += q->request_fn_active;
+		spin_unlock_irq(q->queue_lock);
+	}
+
+	return request_fn_active;
+}
+
+/* Wait until ongoing shost->hostt->queuecommand() calls have finished. */
+static void srp_wait_for_queuecommand(struct Scsi_Host *shost)
+{
+	while (scsi_request_fn_active(shost))
+		msleep(20);
+}
+
 static void __rport_fail_io_fast(struct srp_rport *rport)
 {
 	struct Scsi_Host *shost = rport_to_shost(rport);
@@ -504,27 +534,6 @@ void srp_start_tl_fail_timers(struct srp_rport *rport)
 EXPORT_SYMBOL(srp_start_tl_fail_timers);
 
 /**
- * scsi_request_fn_active() - number of kernel threads inside scsi_request_fn()
- * @shost: SCSI host for which to count the number of scsi_request_fn() callers.
- */
-static int scsi_request_fn_active(struct Scsi_Host *shost)
-{
-	struct scsi_device *sdev;
-	struct request_queue *q;
-	int request_fn_active = 0;
-
-	shost_for_each_device(sdev, shost) {
-		q = sdev->request_queue;
-
-		spin_lock_irq(q->queue_lock);
-		request_fn_active += q->request_fn_active;
-		spin_unlock_irq(q->queue_lock);
-	}
-
-	return request_fn_active;
-}
-
-/**
  * srp_reconnect_rport() - reconnect to an SRP target port
  * @rport: SRP target port.
  *
@@ -559,8 +568,7 @@ int srp_reconnect_rport(struct srp_rport *rport)
 	if (res)
 		goto out;
 	scsi_target_block(&shost->shost_gendev);
-	while (scsi_request_fn_active(shost))
-		msleep(20);
+	srp_wait_for_queuecommand(shost);
 	res = rport->state != SRP_RPORT_LOST ? i->f->reconnect(rport) : -ENODEV;
 	pr_debug("%s (state %d): transport.reconnect() returned %d\n",
 		 dev_name(&shost->shost_gendev), rport->state, res);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index cfba74cd8e8..ce382e85845 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1634,6 +1634,7 @@ static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd)
 {
 	u64 start_lba = blk_rq_pos(scmd->request);
 	u64 end_lba = blk_rq_pos(scmd->request) + (scsi_bufflen(scmd) / 512);
+	u64 factor = scmd->device->sector_size / 512;
 	u64 bad_lba;
 	int info_valid;
 	/*
@@ -1655,16 +1656,9 @@ static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd)
 	if (scsi_bufflen(scmd) <= scmd->device->sector_size)
 		return 0;
 
-	if (scmd->device->sector_size < 512) {
-		/* only legitimate sector_size here is 256 */
-		start_lba <<= 1;
-		end_lba <<= 1;
-	} else {
-		/* be careful ... don't want any overflows */
-		unsigned int factor = scmd->device->sector_size / 512;
-		do_div(start_lba, factor);
-		do_div(end_lba, factor);
-	}
+	/* be careful ... don't want any overflows */
+	do_div(start_lba, factor);
+	do_div(end_lba, factor);
 
 	/* The bad lba was reported incorrectly, we have no idea where
 	 * the error is.
@@ -2231,8 +2225,7 @@ got_data:
 	if (sector_size != 512 &&
 	    sector_size != 1024 &&
 	    sector_size != 2048 &&
-	    sector_size != 4096 &&
-	    sector_size != 256) {
+	    sector_size != 4096) {
 		sd_printk(KERN_NOTICE, sdkp, "Unsupported sector size %d.\n",
 			  sector_size);
 		/*
@@ -2287,8 +2280,6 @@ got_data:
 		sdkp->capacity <<= 2;
 	else if (sector_size == 1024)
 		sdkp->capacity <<= 1;
-	else if (sector_size == 256)
-		sdkp->capacity >>= 1;
 
 	blk_queue_physical_block_size(sdp->request_queue,
 				      sdkp->physical_block_size);
@@ -2818,9 +2809,11 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	 */
 	sd_set_flush_flag(sdkp);
 
-	max_xfer = min_not_zero(queue_max_hw_sectors(sdkp->disk->queue),
-				sdkp->max_xfer_blocks);
+	max_xfer = sdkp->max_xfer_blocks;
 	max_xfer <<= ilog2(sdp->sector_size) - 9;
+
+	max_xfer = min_not_zero(queue_max_hw_sectors(sdkp->disk->queue),
+				max_xfer);
 	blk_queue_max_hw_sectors(sdkp->disk->queue, max_xfer);
 	set_capacity(disk, sdkp->capacity);
 	sd_config_write_same(sdkp);
@@ -3116,6 +3109,7 @@ static void scsi_disk_release(struct device *dev)
 	ida_remove(&sd_index_ida, sdkp->index);
 	spin_unlock(&sd_index_lock);
 
+	blk_integrity_unregister(disk);
 	disk->private_data = NULL;
 	put_disk(disk);
 	put_device(&sdkp->device->sdev_gendev);
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index 14c7d42a11c..5c06d292b94 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -77,7 +77,7 @@ void sd_dif_config_host(struct scsi_disk *sdkp)
 
 		disk->integrity->flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
 
-		if (!sdkp)
+		if (!sdkp->ATO)
 			return;
 
 		if (type == SD_DIF_TYPE3_PROTECTION)
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 60354449d9e..07b2ea1fbf0 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -546,7 +546,7 @@ static ssize_t
 sg_new_read(Sg_fd * sfp, char __user *buf, size_t count, Sg_request * srp)
 {
 	sg_io_hdr_t *hp = &srp->header;
-	int err = 0;
+	int err = 0, err2;
 	int len;
 
 	if (count < SZ_SG_IO_HDR) {
@@ -575,8 +575,8 @@ sg_new_read(Sg_fd * sfp, char __user *buf, size_t count, Sg_request * srp)
 		goto err_out;
 	}
 err_out:
-	err = sg_finish_rem_req(srp);
-	return (0 == err) ? count : err;
+	err2 = sg_finish_rem_req(srp);
+	return err ? : err2 ? : count;
 }
 
 static ssize_t
@@ -1376,6 +1376,17 @@ sg_rq_end_io(struct request *rq, int uptodate)
 	}
 	/* Rely on write phase to clean out srp status values, so no "else" */
 
+	/*
+	 * Free the request as soon as it is complete so that its resources
+	 * can be reused without waiting for userspace to read() the
+	 * result.  But keep the associated bio (if any) around until
+	 * blk_rq_unmap_user() can be called from user context.
+	 */
+	srp->rq = NULL;
+	if (rq->cmd != rq->__cmd)
+		kfree(rq->cmd);
+	__blk_put_request(rq->q, rq);
+
 	write_lock_irqsave(&sfp->rq_list_lock, iflags);
 	if (unlikely(srp->orphan)) {
 		if (sfp->keep_orphan)
@@ -1710,7 +1721,22 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
 			return -ENOMEM;
 	}
 
-	rq = blk_get_request(q, rw, GFP_ATOMIC);
+	/*
+	 * NOTE
+	 *
+	 * With scsi-mq enabled, there are a fixed number of preallocated
+	 * requests equal in number to shost->can_queue.  If all of the
+	 * preallocated requests are already in use, then using GFP_ATOMIC with
+	 * blk_get_request() will return -EWOULDBLOCK, whereas using GFP_KERNEL
+	 * will cause blk_get_request() to sleep until an active command
+	 * completes, freeing up a request.  Neither option is ideal, but
+	 * GFP_KERNEL is the better choice to prevent userspace from getting an
+	 * unexpected EWOULDBLOCK.
+	 *
+	 * With scsi-mq disabled, blk_get_request() with GFP_KERNEL usually
+	 * does not sleep except under memory pressure.
+	 */
+	rq = blk_get_request(q, rw, GFP_KERNEL);
 	if (IS_ERR(rq)) {
 		kfree(long_cmdp);
 		return PTR_ERR(rq);
@@ -1803,10 +1829,10 @@ sg_finish_rem_req(Sg_request *srp)
 	SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp,
 				      "sg_finish_rem_req: res_used=%d\n",
 				      (int) srp->res_used));
-	if (srp->rq) {
-		if (srp->bio)
-			ret = blk_rq_unmap_user(srp->bio);
+	if (srp->bio)
+		ret = blk_rq_unmap_user(srp->bio);
 
+	if (srp->rq) {
 		if (srp->rq->cmd != srp->rq->__cmd)
 			kfree(srp->rq->cmd);
 		blk_put_request(srp->rq);
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 733e5f75951..e511e3406cf 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -741,21 +741,22 @@ static unsigned int copy_to_bounce_buffer(struct scatterlist *orig_sgl,
 			if (bounce_sgl[j].length == PAGE_SIZE) {
 				/* full..move to next entry */
 				sg_kunmap_atomic(bounce_addr);
+				bounce_addr = 0;
 				j++;
+			}
 
-				/* if we need to use another bounce buffer */
-				if (srclen || i != orig_sgl_count - 1)
-					bounce_addr = sg_kmap_atomic(bounce_sgl,j);
+			/* if we need to use another bounce buffer */
+			if (srclen && bounce_addr == 0)
+				bounce_addr = sg_kmap_atomic(bounce_sgl, j);
 
-			} else if (srclen == 0 && i == orig_sgl_count - 1) {
-				/* unmap the last bounce that is < PAGE_SIZE */
-				sg_kunmap_atomic(bounce_addr);
-			}
 		}
 
 		sg_kunmap_atomic(src_addr - orig_sgl[i].offset);
 	}
 
+	if (bounce_addr)
+		sg_kunmap_atomic(bounce_addr);
+
 	local_irq_restore(flags);
 
 	return total_copied;
@@ -1622,8 +1623,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 		break;
 	default:
 		vm_srb->data_in = UNKNOWN_TYPE;
-		vm_srb->win8_extension.srb_flags |= (SRB_FLAGS_DATA_IN |
-						     SRB_FLAGS_DATA_OUT);
+		vm_srb->win8_extension.srb_flags |= SRB_FLAGS_NO_DATA_TRANSFER;
 		break;
 	}
 
@@ -1688,13 +1688,12 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 	if (ret == -EAGAIN) {
 		/* no more space */
 
-		if (cmd_request->bounce_sgl_count) {
+		if (cmd_request->bounce_sgl_count)
 			destroy_bounce_buffer(cmd_request->bounce_sgl,
 					cmd_request->bounce_sgl_count);
 
-			ret = SCSI_MLQUEUE_DEVICE_BUSY;
-			goto queue_error;
-		}
+		ret = SCSI_MLQUEUE_DEVICE_BUSY;
+		goto queue_error;
 	}
 
 	return 0;
diff --git a/drivers/scsi/sun3_NCR5380.c b/drivers/scsi/sun3_NCR5380.c
index 1a2367a1b1f..6d248a299bc 100644
--- a/drivers/scsi/sun3_NCR5380.c
+++ b/drivers/scsi/sun3_NCR5380.c
@@ -2590,15 +2590,15 @@ static void NCR5380_reselect (struct Scsi_Host *instance)
  * Purpose : abort a command
  *
  * Inputs : cmd - the struct scsi_cmnd to abort, code - code to set the
- * 	host byte of the result field to, if zero DID_ABORTED is 
+ *	host byte of the result field to, if zero DID_ABORTED is
  *	used.
  *
- * Returns : 0 - success, -1 on failure.
+ * Returns : SUCCESS - success, FAILED on failure.
  *
- * XXX - there is no way to abort the command that is currently 
- * 	 connected, you have to wait for it to complete.  If this is 
+ * XXX - there is no way to abort the command that is currently
+ *	 connected, you have to wait for it to complete.  If this is
  *	 a problem, we could implement longjmp() / setjmp(), setjmp()
- * 	 called where the loop started in NCR5380_main().
+ *	 called where the loop started in NCR5380_main().
  */
 
 static int NCR5380_abort(struct scsi_cmnd *cmd)
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index 113c83f44b5..4bf337aa4fd 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -775,17 +775,17 @@ static void atmel_spi_pdc_next_xfer(struct spi_master *master,
 			(unsigned long long)xfer->rx_dma);
 	}
 
-	/* REVISIT: We're waiting for ENDRX before we start the next
+	/* REVISIT: We're waiting for RXBUFF before we start the next
 	 * transfer because we need to handle some difficult timing
-	 * issues otherwise. If we wait for ENDTX in one transfer and
-	 * then starts waiting for ENDRX in the next, it's difficult
-	 * to tell the difference between the ENDRX interrupt we're
-	 * actually waiting for and the ENDRX interrupt of the
+	 * issues otherwise. If we wait for TXBUFE in one transfer and
+	 * then starts waiting for RXBUFF in the next, it's difficult
+	 * to tell the difference between the RXBUFF interrupt we're
+	 * actually waiting for and the RXBUFF interrupt of the
 	 * previous transfer.
 	 *
 	 * It should be doable, though. Just not now...
 	 */
-	spi_writel(as, IER, SPI_BIT(ENDRX) | SPI_BIT(OVRES));
+	spi_writel(as, IER, SPI_BIT(RXBUFF) | SPI_BIT(OVRES));
 	spi_writel(as, PTCR, SPI_BIT(TXTEN) | SPI_BIT(RXTEN));
 }
 
diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c
index dc7d2c2d643..fecdda270c5 100644
--- a/drivers/spi/spi-bitbang.c
+++ b/drivers/spi/spi-bitbang.c
@@ -184,7 +184,6 @@ int spi_bitbang_setup(struct spi_device *spi)
 {
 	struct spi_bitbang_cs	*cs = spi->controller_state;
 	struct spi_bitbang	*bitbang;
-	int			retval;
 	unsigned long		flags;
 
 	bitbang = spi_master_get_devdata(spi->master);
@@ -201,9 +200,11 @@ int spi_bitbang_setup(struct spi_device *spi)
 	if (!cs->txrx_word)
 		return -EINVAL;
 
-	retval = bitbang->setup_transfer(spi, NULL);
-	if (retval < 0)
-		return retval;
+	if (bitbang->setup_transfer) {
+		int retval = bitbang->setup_transfer(spi, NULL);
+		if (retval < 0)
+			return retval;
+	}
 
 	dev_dbg(&spi->dev, "%s, %u nsec/bit\n", __func__, 2 * cs->nsecs);
 
@@ -299,9 +300,11 @@ static int spi_bitbang_transfer_one(struct spi_master *master,
 
 		/* init (-1) or override (1) transfer params */
 		if (do_setup != 0) {
-			status = bitbang->setup_transfer(spi, t);
-			if (status < 0)
-				break;
+			if (bitbang->setup_transfer) {
+				status = bitbang->setup_transfer(spi, t);
+				if (status < 0)
+					break;
+			}
 			if (do_setup == -1)
 				do_setup = 0;
 		}
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index 46c6d58e1fd..1417f96546c 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -151,6 +151,9 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change)
 				1,
 				DMA_MEM_TO_DEV,
 				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!txdesc)
+		return NULL;
+
 	txdesc->callback = dw_spi_dma_done;
 	txdesc->callback_param = dws;
 
@@ -173,6 +176,9 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change)
 				1,
 				DMA_DEV_TO_MEM,
 				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!rxdesc)
+		return NULL;
+
 	rxdesc->callback = dw_spi_dma_done;
 	rxdesc->callback_param = dws;
 
@@ -219,7 +225,6 @@ int dw_spi_mid_init(struct dw_spi *dws)
 	iounmap(clk_reg);
 
 	dws->num_cs = 16;
-	dws->fifo_len = 40;	/* FIFO has 40 words buffer */
 
 #ifdef CONFIG_SPI_DW_MID_DMA
 	dws->dma_priv = kzalloc(sizeof(struct mid_dma), GFP_KERNEL);
diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index d0d5542efc0..1a0f266c426 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -621,13 +621,13 @@ static void spi_hw_init(struct dw_spi *dws)
 	if (!dws->fifo_len) {
 		u32 fifo;
 
-		for (fifo = 2; fifo <= 257; fifo++) {
+		for (fifo = 2; fifo <= 256; fifo++) {
 			dw_writew(dws, DW_SPI_TXFLTR, fifo);
 			if (fifo != dw_readw(dws, DW_SPI_TXFLTR))
 				break;
 		}
 
-		dws->fifo_len = (fifo == 257) ? 0 : fifo;
+		dws->fifo_len = (fifo == 2) ? 0 : fifo - 1;
 		dw_writew(dws, DW_SPI_TXFLTR, 0);
 	}
 }
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 831ceb4a91f..276a3cf864d 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -342,8 +342,7 @@ static int dspi_setup_transfer(struct spi_device *spi, struct spi_transfer *t)
 	/* Only alloc on first setup */
 	chip = spi_get_ctldata(spi);
 	if (chip == NULL) {
-		chip = devm_kzalloc(&spi->dev, sizeof(struct chip_data),
-				    GFP_KERNEL);
+		chip = kzalloc(sizeof(struct chip_data), GFP_KERNEL);
 		if (!chip)
 			return -ENOMEM;
 	}
@@ -382,6 +381,16 @@ static int dspi_setup(struct spi_device *spi)
 	return dspi_setup_transfer(spi, NULL);
 }
 
+static void dspi_cleanup(struct spi_device *spi)
+{
+	struct chip_data *chip = spi_get_ctldata((struct spi_device *)spi);
+
+	dev_dbg(&spi->dev, "spi_device %u.%u cleanup\n",
+			spi->master->bus_num, spi->chip_select);
+
+	kfree(chip);
+}
+
 static irqreturn_t dspi_interrupt(int irq, void *dev_id)
 {
 	struct fsl_dspi *dspi = (struct fsl_dspi *)dev_id;
@@ -467,6 +476,7 @@ static int dspi_probe(struct platform_device *pdev)
 	dspi->bitbang.master->setup = dspi_setup;
 	dspi->bitbang.master->dev.of_node = pdev->dev.of_node;
 
+	master->cleanup = dspi_cleanup;
 	master->mode_bits = SPI_CPOL | SPI_CPHA;
 	master->bits_per_word_mask = SPI_BPW_MASK(4) | SPI_BPW_MASK(8) |
 					SPI_BPW_MASK(16);
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 3637847b537..bf0effb8613 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -371,8 +371,6 @@ static int __maybe_unused mx51_ecspi_config(struct spi_imx_data *spi_imx,
 	if (spi_imx->dma_is_inited) {
 		dma = readl(spi_imx->base + MX51_ECSPI_DMA);
 
-		spi_imx->tx_wml = spi_imx_get_fifosize(spi_imx) / 2;
-		spi_imx->rx_wml = spi_imx_get_fifosize(spi_imx) / 2;
 		spi_imx->rxt_wml = spi_imx_get_fifosize(spi_imx) / 2;
 		rx_wml_cfg = spi_imx->rx_wml << MX51_ECSPI_DMA_RX_WML_OFFSET;
 		tx_wml_cfg = spi_imx->tx_wml << MX51_ECSPI_DMA_TX_WML_OFFSET;
@@ -823,6 +821,10 @@ static int spi_imx_sdma_init(struct device *dev, struct spi_imx_data *spi_imx,
 	struct dma_slave_config slave_config = {};
 	int ret;
 
+	/* use pio mode for i.mx6dl chip TKT238285 */
+	if (of_machine_is_compatible("fsl,imx6dl"))
+		return 0;
+
 	/* Prepare for TX DMA: */
 	master->dma_tx = dma_request_slave_channel(dev, "tx");
 	if (!master->dma_tx) {
@@ -865,6 +867,8 @@ static int spi_imx_sdma_init(struct device *dev, struct spi_imx_data *spi_imx,
 	master->max_dma_len = MAX_SDMA_BD_BYTES;
 	spi_imx->bitbang.master->flags = SPI_MASTER_MUST_RX |
 					 SPI_MASTER_MUST_TX;
+	spi_imx->tx_wml = spi_imx_get_fifosize(spi_imx) / 2;
+	spi_imx->rx_wml = spi_imx_get_fifosize(spi_imx) / 2;
 	spi_imx->dma_is_inited = 1;
 
 	return 0;
diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index c76b7d7879d..bd09807b6b0 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -52,6 +52,12 @@ enum orion_spi_type {
 
 struct orion_spi_dev {
 	enum orion_spi_type	typ;
+	/*
+	 * min_divisor and max_hz should be exclusive, the only we can
+	 * have both is for managing the armada-370-spi case with old
+	 * device tree
+	 */
+	unsigned long		max_hz;
 	unsigned int		min_divisor;
 	unsigned int		max_divisor;
 	u32			prescale_mask;
@@ -402,8 +408,9 @@ static const struct orion_spi_dev orion_spi_dev_data = {
 
 static const struct orion_spi_dev armada_spi_dev_data = {
 	.typ = ARMADA_SPI,
-	.min_divisor = 1,
+	.min_divisor = 4,
 	.max_divisor = 1920,
+	.max_hz = 50000000,
 	.prescale_mask = ARMADA_SPI_CLK_PRESCALE_MASK,
 };
 
@@ -468,7 +475,21 @@ static int orion_spi_probe(struct platform_device *pdev)
 		goto out;
 
 	tclk_hz = clk_get_rate(spi->clk);
-	master->max_speed_hz = DIV_ROUND_UP(tclk_hz, devdata->min_divisor);
+
+	/*
+	 * With old device tree, armada-370-spi could be used with
+	 * Armada XP, however for this SoC the maximum frequency is
+	 * 50MHz instead of tclk/4. On Armada 370, tclk cannot be
+	 * higher than 200MHz. So, in order to be able to handle both
+	 * SoCs, we can take the minimum of 50MHz and tclk/4.
+	 */
+	if (of_device_is_compatible(pdev->dev.of_node,
+					"marvell,armada-370-spi"))
+		master->max_speed_hz = min(devdata->max_hz,
+				DIV_ROUND_UP(tclk_hz, devdata->min_divisor));
+	else
+		master->max_speed_hz =
+			DIV_ROUND_UP(tclk_hz, devdata->min_divisor);
 	master->min_speed_hz = DIV_ROUND_UP(tclk_hz, devdata->max_divisor);
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index fc2dd844160..11e18342bc4 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -534,12 +534,12 @@ static void giveback(struct pl022 *pl022)
 	pl022->cur_msg = NULL;
 	pl022->cur_transfer = NULL;
 	pl022->cur_chip = NULL;
-	spi_finalize_current_message(pl022->master);
 
 	/* disable the SPI/SSP operation */
 	writew((readw(SSP_CR1(pl022->virtbase)) &
 		(~SSP_CR1_MASK_SSE)), SSP_CR1(pl022->virtbase));
 
+	spi_finalize_current_message(pl022->master);
 }
 
 /**
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 9e9e0f971e6..d95656d05eb 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -402,8 +402,8 @@ static void giveback(struct driver_data *drv_data)
 			cs_deassert(drv_data);
 	}
 
-	spi_finalize_current_message(drv_data->master);
 	drv_data->cur_chip = NULL;
+	spi_finalize_current_message(drv_data->master);
 }
 
 static void reset_sccr1(struct driver_data *drv_data)
diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c
index 9f83d295074..6976f8aa856 100644
--- a/drivers/spi/spi-qup.c
+++ b/drivers/spi/spi-qup.c
@@ -489,7 +489,7 @@ static int spi_qup_probe(struct platform_device *pdev)
 	struct resource *res;
 	struct device *dev;
 	void __iomem *base;
-	u32 max_freq, iomode;
+	u32 max_freq, iomode, num_cs;
 	int ret, irq, size;
 
 	dev = &pdev->dev;
@@ -541,10 +541,11 @@ static int spi_qup_probe(struct platform_device *pdev)
 	}
 
 	/* use num-cs unless not present or out of range */
-	if (of_property_read_u16(dev->of_node, "num-cs",
-			&master->num_chipselect) ||
-			(master->num_chipselect > SPI_NUM_CHIPSELECTS))
+	if (of_property_read_u32(dev->of_node, "num-cs", &num_cs) ||
+	    num_cs > SPI_NUM_CHIPSELECTS)
 		master->num_chipselect = SPI_NUM_CHIPSELECTS;
+	else
+		master->num_chipselect = num_cs;
 
 	master->bus_num = pdev->id;
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LOOP;
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index 3f365402fcc..14052936b1c 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -480,6 +480,8 @@ static int sh_msiof_spi_setup(struct spi_device *spi)
 	struct device_node	*np = spi->master->dev.of_node;
 	struct sh_msiof_spi_priv *p = spi_master_get_devdata(spi->master);
 
+	pm_runtime_get_sync(&p->pdev->dev);
+
 	if (!np) {
 		/*
 		 * Use spi->controller_data for CS (same strategy as spi_gpio),
@@ -498,6 +500,9 @@ static int sh_msiof_spi_setup(struct spi_device *spi)
 	if (spi->cs_gpio >= 0)
 		gpio_set_value(spi->cs_gpio, !(spi->mode & SPI_CS_HIGH));
 
+
+	pm_runtime_put_sync(&p->pdev->dev);
+
 	return 0;
 }
 
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 50f20f24398..115ad5dbc7c 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1059,9 +1059,6 @@ void spi_finalize_current_message(struct spi_master *master)
 
 	spin_lock_irqsave(&master->queue_lock, flags);
 	mesg = master->cur_msg;
-	master->cur_msg = NULL;
-
-	queue_kthread_work(&master->kworker, &master->pump_messages);
 	spin_unlock_irqrestore(&master->queue_lock, flags);
 
 	spi_unmap_msg(master, mesg);
@@ -1073,13 +1070,18 @@ void spi_finalize_current_message(struct spi_master *master)
 				"failed to unprepare message: %d\n", ret);
 		}
 	}
+
+	spin_lock_irqsave(&master->queue_lock, flags);
+	master->cur_msg = NULL;
 	master->cur_msg_prepared = false;
+	queue_kthread_work(&master->kworker, &master->pump_messages);
+	spin_unlock_irqrestore(&master->queue_lock, flags);
+
+	trace_spi_message_done(mesg);
 
 	mesg->state = NULL;
 	if (mesg->complete)
 		mesg->complete(mesg->context);
-
-	trace_spi_message_done(mesg);
 }
 EXPORT_SYMBOL_GPL(spi_finalize_current_message);
 
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index e50039fb147..409a8c576c7 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -246,7 +246,10 @@ static int spidev_message(struct spidev_data *spidev,
 		k_tmp->len = u_tmp->len;
 
 		total += k_tmp->len;
-		if (total > bufsiz) {
+		/* Check total length of transfers.  Also check each
+		 * transfer length to avoid arithmetic overflow.
+		 */
+		if (total > bufsiz || k_tmp->len > bufsiz) {
 			status = -EMSGSIZE;
 			goto done;
 		}
diff --git a/drivers/ssb/Kconfig b/drivers/ssb/Kconfig
index 75b3603906c..f0d22cdb51c 100644
--- a/drivers/ssb/Kconfig
+++ b/drivers/ssb/Kconfig
@@ -130,6 +130,7 @@ config SSB_DRIVER_MIPS
 	bool "SSB Broadcom MIPS core driver"
 	depends on SSB && MIPS
 	select SSB_SERIAL
+	select SSB_SFLASH
 	help
 	  Driver for the Sonics Silicon Backplane attached
 	  Broadcom MIPS core.
diff --git a/drivers/staging/android/Kconfig b/drivers/staging/android/Kconfig
index 7a0e2885296..21bc8ecbb28 100644
--- a/drivers/staging/android/Kconfig
+++ b/drivers/staging/android/Kconfig
@@ -44,23 +44,6 @@ config ASHMEM
 	  It is, in theory, a good memory allocator for low-memory devices,
 	  because it can discard shared memory units when under memory pressure.
 
-config ANDROID_LOGGER
-	tristate "Android log driver"
-	default n
-	---help---
-	  This adds support for system-wide logging using four log buffers.
-
-	  These are:
-
-	      1: main
-	      2: events
-	      3: radio
-	      4: system
-
-	  Log reading and writing is performed via normal Linux reads and
-	  optimized writes. This optimization avoids logging having too
-	  much overhead in the system.
-
 config ANDROID_TIMED_OUTPUT
 	bool "Timed output class driver"
 	default y
@@ -75,14 +58,14 @@ config ANDROID_LOW_MEMORY_KILLER
 	---help---
 	  Registers processes to be killed when memory is low
 
-config ANDROID_INTF_ALARM_DEV
-	tristate "Android alarm driver"
-	depends on RTC_CLASS
-	default n
+config ANDROID_LOW_MEMORY_KILLER_AUTODETECT_OOM_ADJ_VALUES
+	bool "Android Low Memory Killer: detect oom_adj values"
+	depends on ANDROID_LOW_MEMORY_KILLER
+	default y
 	---help---
-	  Provides non-wakeup and rtc backed wakeup alarms based on rtc or
-	  elapsed realtime, and a non-wakeup alarm on the monotonic clock.
-	  Also exports the alarm interface to user-space.
+	  Detect oom_adj values written to
+	  /sys/module/lowmemorykiller/parameters/adj and convert them
+	  to oom_score_adj values.
 
 config SYNC
 	bool "Synchronization framework"
@@ -114,6 +97,8 @@ config SW_SYNC_USER
 
 source "drivers/staging/android/ion/Kconfig"
 
+source "drivers/staging/android/fiq_debugger/Kconfig"
+
 endif # if ANDROID
 
 endmenu
diff --git a/drivers/staging/android/Makefile b/drivers/staging/android/Makefile
index 517ad5ffa42..b7b9980bea9 100644
--- a/drivers/staging/android/Makefile
+++ b/drivers/staging/android/Makefile
@@ -1,13 +1,12 @@
 ccflags-y += -I$(src)			# needed for trace events
 
 obj-y					+= ion/
+obj-$(CONFIG_FIQ_DEBUGGER)		+= fiq_debugger/
 
 obj-$(CONFIG_ANDROID_BINDER_IPC)	+= binder.o
 obj-$(CONFIG_ASHMEM)			+= ashmem.o
-obj-$(CONFIG_ANDROID_LOGGER)		+= logger.o
 obj-$(CONFIG_ANDROID_TIMED_OUTPUT)	+= timed_output.o
 obj-$(CONFIG_ANDROID_TIMED_GPIO)	+= timed_gpio.o
 obj-$(CONFIG_ANDROID_LOW_MEMORY_KILLER)	+= lowmemorykiller.o
-obj-$(CONFIG_ANDROID_INTF_ALARM_DEV)	+= alarm-dev.o
 obj-$(CONFIG_SYNC)			+= sync.o sync_debug.o
 obj-$(CONFIG_SW_SYNC)			+= sw_sync.o
diff --git a/drivers/staging/android/TODO b/drivers/staging/android/TODO
deleted file mode 100644
index b15fb0d6b15..00000000000
--- a/drivers/staging/android/TODO
+++ /dev/null
@@ -1,10 +0,0 @@
-TODO:
-	- checkpatch.pl cleanups
-	- sparse fixes
-	- rename files to be not so "generic"
-	- make sure things build as modules properly
-	- add proper arch dependencies as needed
-	- audit userspace interfaces to make sure they are sane
-
-Please send patches to Greg Kroah-Hartman <greg@kroah.com> and Cc:
-Brian Swetland <swetland@google.com>
diff --git a/drivers/staging/android/alarm-dev.c b/drivers/staging/android/alarm-dev.c
deleted file mode 100644
index ff4b3e8758a..00000000000
--- a/drivers/staging/android/alarm-dev.c
+++ /dev/null
@@ -1,446 +0,0 @@
-/* drivers/rtc/alarm-dev.c
- *
- * Copyright (C) 2007-2009 Google, Inc.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#include <linux/time.h>
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/miscdevice.h>
-#include <linux/fs.h>
-#include <linux/platform_device.h>
-#include <linux/sched.h>
-#include <linux/spinlock.h>
-#include <linux/uaccess.h>
-#include <linux/alarmtimer.h>
-#include "android_alarm.h"
-
-#define ANDROID_ALARM_PRINT_INFO (1U << 0)
-#define ANDROID_ALARM_PRINT_IO (1U << 1)
-#define ANDROID_ALARM_PRINT_INT (1U << 2)
-
-static int debug_mask = ANDROID_ALARM_PRINT_INFO;
-module_param_named(debug_mask, debug_mask, int, S_IRUGO | S_IWUSR | S_IWGRP);
-
-#define alarm_dbg(debug_level_mask, fmt, ...)				\
-do {									\
-	if (debug_mask & ANDROID_ALARM_PRINT_##debug_level_mask)	\
-		pr_info(fmt, ##__VA_ARGS__);				\
-} while (0)
-
-#define ANDROID_ALARM_WAKEUP_MASK ( \
-	ANDROID_ALARM_RTC_WAKEUP_MASK | \
-	ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP_MASK)
-
-static int alarm_opened;
-static DEFINE_SPINLOCK(alarm_slock);
-static struct wakeup_source alarm_wake_lock;
-static DECLARE_WAIT_QUEUE_HEAD(alarm_wait_queue);
-static uint32_t alarm_pending;
-static uint32_t alarm_enabled;
-static uint32_t wait_pending;
-
-struct devalarm {
-	union {
-		struct hrtimer hrt;
-		struct alarm alrm;
-	} u;
-	enum android_alarm_type type;
-};
-
-static struct devalarm alarms[ANDROID_ALARM_TYPE_COUNT];
-
-/**
- * is_wakeup() - Checks to see if this alarm can wake the device
- * @type:	 The type of alarm being checked
- *
- * Return: 1 if this is a wakeup alarm, otherwise 0
- */
-static int is_wakeup(enum android_alarm_type type)
-{
-	return type == ANDROID_ALARM_RTC_WAKEUP ||
-		type == ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP;
-}
-
-static void devalarm_start(struct devalarm *alrm, ktime_t exp)
-{
-	if (is_wakeup(alrm->type))
-		alarm_start(&alrm->u.alrm, exp);
-	else
-		hrtimer_start(&alrm->u.hrt, exp, HRTIMER_MODE_ABS);
-}
-
-static int devalarm_try_to_cancel(struct devalarm *alrm)
-{
-	if (is_wakeup(alrm->type))
-		return alarm_try_to_cancel(&alrm->u.alrm);
-	return hrtimer_try_to_cancel(&alrm->u.hrt);
-}
-
-static void devalarm_cancel(struct devalarm *alrm)
-{
-	if (is_wakeup(alrm->type))
-		alarm_cancel(&alrm->u.alrm);
-	else
-		hrtimer_cancel(&alrm->u.hrt);
-}
-
-static void alarm_clear(enum android_alarm_type alarm_type)
-{
-	uint32_t alarm_type_mask = 1U << alarm_type;
-	unsigned long flags;
-
-	spin_lock_irqsave(&alarm_slock, flags);
-	alarm_dbg(IO, "alarm %d clear\n", alarm_type);
-	devalarm_try_to_cancel(&alarms[alarm_type]);
-	if (alarm_pending) {
-		alarm_pending &= ~alarm_type_mask;
-		if (!alarm_pending && !wait_pending)
-			__pm_relax(&alarm_wake_lock);
-	}
-	alarm_enabled &= ~alarm_type_mask;
-	spin_unlock_irqrestore(&alarm_slock, flags);
-}
-
-static void alarm_set(enum android_alarm_type alarm_type,
-							struct timespec *ts)
-{
-	uint32_t alarm_type_mask = 1U << alarm_type;
-	unsigned long flags;
-
-	spin_lock_irqsave(&alarm_slock, flags);
-	alarm_dbg(IO, "alarm %d set %ld.%09ld\n",
-			alarm_type, ts->tv_sec, ts->tv_nsec);
-	alarm_enabled |= alarm_type_mask;
-	devalarm_start(&alarms[alarm_type], timespec_to_ktime(*ts));
-	spin_unlock_irqrestore(&alarm_slock, flags);
-}
-
-static int alarm_wait(void)
-{
-	unsigned long flags;
-	int rv = 0;
-
-	spin_lock_irqsave(&alarm_slock, flags);
-	alarm_dbg(IO, "alarm wait\n");
-	if (!alarm_pending && wait_pending) {
-		__pm_relax(&alarm_wake_lock);
-		wait_pending = 0;
-	}
-	spin_unlock_irqrestore(&alarm_slock, flags);
-
-	rv = wait_event_interruptible(alarm_wait_queue, alarm_pending);
-	if (rv)
-		return rv;
-
-	spin_lock_irqsave(&alarm_slock, flags);
-	rv = alarm_pending;
-	wait_pending = 1;
-	alarm_pending = 0;
-	spin_unlock_irqrestore(&alarm_slock, flags);
-
-	return rv;
-}
-
-static int alarm_set_rtc(struct timespec *ts)
-{
-	struct rtc_time new_rtc_tm;
-	struct rtc_device *rtc_dev;
-	unsigned long flags;
-	int rv = 0;
-
-	rtc_time_to_tm(ts->tv_sec, &new_rtc_tm);
-	rtc_dev = alarmtimer_get_rtcdev();
-	rv = do_settimeofday(ts);
-	if (rv < 0)
-		return rv;
-	if (rtc_dev)
-		rv = rtc_set_time(rtc_dev, &new_rtc_tm);
-
-	spin_lock_irqsave(&alarm_slock, flags);
-	alarm_pending |= ANDROID_ALARM_TIME_CHANGE_MASK;
-	wake_up(&alarm_wait_queue);
-	spin_unlock_irqrestore(&alarm_slock, flags);
-
-	return rv;
-}
-
-static int alarm_get_time(enum android_alarm_type alarm_type,
-							struct timespec *ts)
-{
-	int rv = 0;
-
-	switch (alarm_type) {
-	case ANDROID_ALARM_RTC_WAKEUP:
-	case ANDROID_ALARM_RTC:
-		getnstimeofday(ts);
-		break;
-	case ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP:
-	case ANDROID_ALARM_ELAPSED_REALTIME:
-		get_monotonic_boottime(ts);
-		break;
-	case ANDROID_ALARM_SYSTEMTIME:
-		ktime_get_ts(ts);
-		break;
-	default:
-		rv = -EINVAL;
-	}
-	return rv;
-}
-
-static long alarm_do_ioctl(struct file *file, unsigned int cmd,
-							struct timespec *ts)
-{
-	int rv = 0;
-	unsigned long flags;
-	enum android_alarm_type alarm_type = ANDROID_ALARM_IOCTL_TO_TYPE(cmd);
-
-	if (alarm_type >= ANDROID_ALARM_TYPE_COUNT)
-		return -EINVAL;
-
-	if (ANDROID_ALARM_BASE_CMD(cmd) != ANDROID_ALARM_GET_TIME(0)) {
-		if ((file->f_flags & O_ACCMODE) == O_RDONLY)
-			return -EPERM;
-		if (file->private_data == NULL &&
-		    cmd != ANDROID_ALARM_SET_RTC) {
-			spin_lock_irqsave(&alarm_slock, flags);
-			if (alarm_opened) {
-				spin_unlock_irqrestore(&alarm_slock, flags);
-				return -EBUSY;
-			}
-			alarm_opened = 1;
-			file->private_data = (void *)1;
-			spin_unlock_irqrestore(&alarm_slock, flags);
-		}
-	}
-
-	switch (ANDROID_ALARM_BASE_CMD(cmd)) {
-	case ANDROID_ALARM_CLEAR(0):
-		alarm_clear(alarm_type);
-		break;
-	case ANDROID_ALARM_SET(0):
-		alarm_set(alarm_type, ts);
-		break;
-	case ANDROID_ALARM_SET_AND_WAIT(0):
-		alarm_set(alarm_type, ts);
-		/* fall though */
-	case ANDROID_ALARM_WAIT:
-		rv = alarm_wait();
-		break;
-	case ANDROID_ALARM_SET_RTC:
-		rv = alarm_set_rtc(ts);
-		break;
-	case ANDROID_ALARM_GET_TIME(0):
-		rv = alarm_get_time(alarm_type, ts);
-		break;
-
-	default:
-		rv = -EINVAL;
-	}
-	return rv;
-}
-
-static long alarm_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
-
-	struct timespec ts;
-	int rv;
-
-	switch (ANDROID_ALARM_BASE_CMD(cmd)) {
-	case ANDROID_ALARM_SET_AND_WAIT(0):
-	case ANDROID_ALARM_SET(0):
-	case ANDROID_ALARM_SET_RTC:
-		if (copy_from_user(&ts, (void __user *)arg, sizeof(ts)))
-			return -EFAULT;
-		break;
-	}
-
-	rv = alarm_do_ioctl(file, cmd, &ts);
-	if (rv)
-		return rv;
-
-	switch (ANDROID_ALARM_BASE_CMD(cmd)) {
-	case ANDROID_ALARM_GET_TIME(0):
-		if (copy_to_user((void __user *)arg, &ts, sizeof(ts)))
-			return -EFAULT;
-		break;
-	}
-
-	return 0;
-}
-
-#ifdef CONFIG_COMPAT
-static long alarm_compat_ioctl(struct file *file, unsigned int cmd,
-							unsigned long arg)
-{
-
-	struct timespec ts;
-	int rv;
-
-	switch (ANDROID_ALARM_BASE_CMD(cmd)) {
-	case ANDROID_ALARM_SET_AND_WAIT_COMPAT(0):
-	case ANDROID_ALARM_SET_COMPAT(0):
-	case ANDROID_ALARM_SET_RTC_COMPAT:
-		if (compat_get_timespec(&ts, (void __user *)arg))
-			return -EFAULT;
-		/* fall through */
-	case ANDROID_ALARM_GET_TIME_COMPAT(0):
-		cmd = ANDROID_ALARM_COMPAT_TO_NORM(cmd);
-		break;
-	}
-
-	rv = alarm_do_ioctl(file, cmd, &ts);
-	if (rv)
-		return rv;
-
-	switch (ANDROID_ALARM_BASE_CMD(cmd)) {
-	case ANDROID_ALARM_GET_TIME(0): /* NOTE: we modified cmd above */
-		if (compat_put_timespec(&ts, (void __user *)arg))
-			return -EFAULT;
-		break;
-	}
-
-	return 0;
-}
-#endif
-
-static int alarm_open(struct inode *inode, struct file *file)
-{
-	file->private_data = NULL;
-	return 0;
-}
-
-static int alarm_release(struct inode *inode, struct file *file)
-{
-	int i;
-	unsigned long flags;
-
-	spin_lock_irqsave(&alarm_slock, flags);
-	if (file->private_data) {
-		for (i = 0; i < ANDROID_ALARM_TYPE_COUNT; i++) {
-			uint32_t alarm_type_mask = 1U << i;
-
-			if (alarm_enabled & alarm_type_mask) {
-				alarm_dbg(INFO,
-					  "%s: clear alarm, pending %d\n",
-					  __func__,
-					  !!(alarm_pending & alarm_type_mask));
-				alarm_enabled &= ~alarm_type_mask;
-			}
-			spin_unlock_irqrestore(&alarm_slock, flags);
-			devalarm_cancel(&alarms[i]);
-			spin_lock_irqsave(&alarm_slock, flags);
-		}
-		if (alarm_pending | wait_pending) {
-			if (alarm_pending)
-				alarm_dbg(INFO, "%s: clear pending alarms %x\n",
-					  __func__, alarm_pending);
-			__pm_relax(&alarm_wake_lock);
-			wait_pending = 0;
-			alarm_pending = 0;
-		}
-		alarm_opened = 0;
-	}
-	spin_unlock_irqrestore(&alarm_slock, flags);
-	return 0;
-}
-
-static void devalarm_triggered(struct devalarm *alarm)
-{
-	unsigned long flags;
-	uint32_t alarm_type_mask = 1U << alarm->type;
-
-	alarm_dbg(INT, "%s: type %d\n", __func__, alarm->type);
-	spin_lock_irqsave(&alarm_slock, flags);
-	if (alarm_enabled & alarm_type_mask) {
-		__pm_wakeup_event(&alarm_wake_lock, 5000); /* 5secs */
-		alarm_enabled &= ~alarm_type_mask;
-		alarm_pending |= alarm_type_mask;
-		wake_up(&alarm_wait_queue);
-	}
-	spin_unlock_irqrestore(&alarm_slock, flags);
-}
-
-static enum hrtimer_restart devalarm_hrthandler(struct hrtimer *hrt)
-{
-	struct devalarm *devalrm = container_of(hrt, struct devalarm, u.hrt);
-
-	devalarm_triggered(devalrm);
-	return HRTIMER_NORESTART;
-}
-
-static enum alarmtimer_restart devalarm_alarmhandler(struct alarm *alrm,
-							ktime_t now)
-{
-	struct devalarm *devalrm = container_of(alrm, struct devalarm, u.alrm);
-
-	devalarm_triggered(devalrm);
-	return ALARMTIMER_NORESTART;
-}
-
-
-static const struct file_operations alarm_fops = {
-	.owner = THIS_MODULE,
-	.unlocked_ioctl = alarm_ioctl,
-	.open = alarm_open,
-	.release = alarm_release,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl = alarm_compat_ioctl,
-#endif
-};
-
-static struct miscdevice alarm_device = {
-	.minor = MISC_DYNAMIC_MINOR,
-	.name = "alarm",
-	.fops = &alarm_fops,
-};
-
-static int __init alarm_dev_init(void)
-{
-	int err;
-	int i;
-
-	err = misc_register(&alarm_device);
-	if (err)
-		return err;
-
-	alarm_init(&alarms[ANDROID_ALARM_RTC_WAKEUP].u.alrm,
-			ALARM_REALTIME, devalarm_alarmhandler);
-	hrtimer_init(&alarms[ANDROID_ALARM_RTC].u.hrt,
-			CLOCK_REALTIME, HRTIMER_MODE_ABS);
-	alarm_init(&alarms[ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP].u.alrm,
-			ALARM_BOOTTIME, devalarm_alarmhandler);
-	hrtimer_init(&alarms[ANDROID_ALARM_ELAPSED_REALTIME].u.hrt,
-			CLOCK_BOOTTIME, HRTIMER_MODE_ABS);
-	hrtimer_init(&alarms[ANDROID_ALARM_SYSTEMTIME].u.hrt,
-			CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-
-	for (i = 0; i < ANDROID_ALARM_TYPE_COUNT; i++) {
-		alarms[i].type = i;
-		if (!is_wakeup(i))
-			alarms[i].u.hrt.function = devalarm_hrthandler;
-	}
-
-	wakeup_source_init(&alarm_wake_lock, "alarm");
-	return 0;
-}
-
-static void  __exit alarm_dev_exit(void)
-{
-	misc_deregister(&alarm_device);
-	wakeup_source_trash(&alarm_wake_lock);
-}
-
-module_init(alarm_dev_init);
-module_exit(alarm_dev_exit);
-MODULE_LICENSE("GPL");
diff --git a/drivers/staging/android/android_alarm.h b/drivers/staging/android/android_alarm.h
deleted file mode 100644
index 495b20cf3bf..00000000000
--- a/drivers/staging/android/android_alarm.h
+++ /dev/null
@@ -1,41 +0,0 @@
-/* include/linux/android_alarm.h
- *
- * Copyright (C) 2006-2007 Google, Inc.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#ifndef _LINUX_ANDROID_ALARM_H
-#define _LINUX_ANDROID_ALARM_H
-
-#include <linux/compat.h>
-#include <linux/ioctl.h>
-
-#include "uapi/android_alarm.h"
-
-#ifdef CONFIG_COMPAT
-#define ANDROID_ALARM_SET_COMPAT(type)		ALARM_IOW(2, type, \
-							struct compat_timespec)
-#define ANDROID_ALARM_SET_AND_WAIT_COMPAT(type)	ALARM_IOW(3, type, \
-							struct compat_timespec)
-#define ANDROID_ALARM_GET_TIME_COMPAT(type)	ALARM_IOW(4, type, \
-							struct compat_timespec)
-#define ANDROID_ALARM_SET_RTC_COMPAT		_IOW('a', 5, \
-							struct compat_timespec)
-#define ANDROID_ALARM_IOCTL_NR(cmd)		(_IOC_NR(cmd) & ((1<<4)-1))
-#define ANDROID_ALARM_COMPAT_TO_NORM(cmd)  \
-				ALARM_IOW(ANDROID_ALARM_IOCTL_NR(cmd), \
-					ANDROID_ALARM_IOCTL_TO_TYPE(cmd), \
-					struct timespec)
-
-#endif
-
-#endif
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index ad4f5790a76..afee619b7c1 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -396,22 +396,14 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma)
 	}
 	get_file(asma->file);
 
-	/*
-	 * XXX - Reworked to use shmem_zero_setup() instead of
-	 * shmem_set_file while we're in staging. -jstultz
-	 */
-	if (vma->vm_flags & VM_SHARED) {
-		ret = shmem_zero_setup(vma);
-		if (ret) {
-			fput(asma->file);
-			goto out;
-		}
+	if (vma->vm_flags & VM_SHARED)
+		shmem_set_file(vma, asma->file);
+	else {
+		if (vma->vm_file)
+			fput(vma->vm_file);
+		vma->vm_file = asma->file;
 	}
 
-	if (vma->vm_file)
-		fput(vma->vm_file);
-	vma->vm_file = asma->file;
-
 out:
 	mutex_unlock(&ashmem_mutex);
 	return ret;
@@ -441,12 +433,14 @@ ashmem_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 	if (!(sc->gfp_mask & __GFP_FS))
 		return SHRINK_STOP;
 
-	mutex_lock(&ashmem_mutex);
+	if (!mutex_trylock(&ashmem_mutex))
+		return -1;
+
 	list_for_each_entry_safe(range, next, &ashmem_lru_list, lru) {
 		loff_t start = range->pgstart * PAGE_SIZE;
 		loff_t end = (range->pgend + 1) * PAGE_SIZE;
 
-		do_fallocate(range->asma->file,
+		range->asma->file->f_op->fallocate(range->asma->file,
 				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				start, end - start);
 		range->purged = ASHMEM_WAS_PURGED;
diff --git a/drivers/staging/android/binder.c b/drivers/staging/android/binder.c
index c69c40d69d5..710393a72a8 100644
--- a/drivers/staging/android/binder.c
+++ b/drivers/staging/android/binder.c
@@ -26,6 +26,7 @@
 #include <linux/miscdevice.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/rtmutex.h>
 #include <linux/mutex.h>
 #include <linux/nsproxy.h>
 #include <linux/poll.h>
@@ -37,11 +38,12 @@
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/pid_namespace.h>
+#include <linux/security.h>
 
 #include "binder.h"
 #include "binder_trace.h"
 
-static DEFINE_MUTEX(binder_main_lock);
+static DEFINE_RT_MUTEX(binder_main_lock);
 static DEFINE_MUTEX(binder_deferred_lock);
 static DEFINE_MUTEX(binder_mmap_lock);
 
@@ -421,14 +423,14 @@ static long task_close_fd(struct binder_proc *proc, unsigned int fd)
 static inline void binder_lock(const char *tag)
 {
 	trace_binder_lock(tag);
-	mutex_lock(&binder_main_lock);
+	rt_mutex_lock(&binder_main_lock);
 	trace_binder_locked(tag);
 }
 
 static inline void binder_unlock(const char *tag)
 {
 	trace_binder_unlock(tag);
-	mutex_unlock(&binder_main_lock);
+	rt_mutex_unlock(&binder_main_lock);
 }
 
 static void binder_set_nice(long nice)
@@ -1316,6 +1318,7 @@ static void binder_transaction(struct binder_proc *proc,
 	struct binder_transaction *t;
 	struct binder_work *tcomplete;
 	binder_size_t *offp, *off_end;
+	binder_size_t off_min;
 	struct binder_proc *target_proc;
 	struct binder_thread *target_thread = NULL;
 	struct binder_node *target_node = NULL;
@@ -1396,6 +1399,10 @@ static void binder_transaction(struct binder_proc *proc,
 			return_error = BR_DEAD_REPLY;
 			goto err_dead_binder;
 		}
+		if (security_binder_transaction(proc->tsk, target_proc->tsk) < 0) {
+			return_error = BR_FAILED_REPLY;
+			goto err_invalid_target_handle;
+		}
 		if (!(tr->flags & TF_ONE_WAY) && thread->transaction_stack) {
 			struct binder_transaction *tmp;
 
@@ -1512,18 +1519,24 @@ static void binder_transaction(struct binder_proc *proc,
 		goto err_bad_offset;
 	}
 	off_end = (void *)offp + tr->offsets_size;
+	off_min = 0;
 	for (; offp < off_end; offp++) {
 		struct flat_binder_object *fp;
 
 		if (*offp > t->buffer->data_size - sizeof(*fp) ||
+		    *offp < off_min ||
 		    t->buffer->data_size < sizeof(*fp) ||
 		    !IS_ALIGNED(*offp, sizeof(u32))) {
-			binder_user_error("%d:%d got transaction with invalid offset, %lld\n",
-					  proc->pid, thread->pid, (u64)*offp);
+			binder_user_error("%d:%d got transaction with invalid offset, %lld (min %lld, max %lld)\n",
+					  proc->pid, thread->pid, (u64)*offp,
+					  (u64)off_min,
+					  (u64)(t->buffer->data_size -
+					  sizeof(*fp)));
 			return_error = BR_FAILED_REPLY;
 			goto err_bad_offset;
 		}
 		fp = (struct flat_binder_object *)(t->buffer->data + *offp);
+		off_min = *offp + sizeof(struct flat_binder_object);
 		switch (fp->type) {
 		case BINDER_TYPE_BINDER:
 		case BINDER_TYPE_WEAK_BINDER: {
@@ -1547,6 +1560,10 @@ static void binder_transaction(struct binder_proc *proc,
 				return_error = BR_FAILED_REPLY;
 				goto err_binder_get_ref_for_node_failed;
 			}
+	if (security_binder_transfer_binder(proc->tsk, target_proc->tsk)) {
+				return_error = BR_FAILED_REPLY;
+				goto err_binder_get_ref_for_node_failed;
+			}
 			ref = binder_get_ref_for_node(target_proc, node);
 			if (ref == NULL) {
 				return_error = BR_FAILED_REPLY;
@@ -1577,6 +1594,10 @@ static void binder_transaction(struct binder_proc *proc,
 				return_error = BR_FAILED_REPLY;
 				goto err_binder_get_ref_failed;
 			}
+			if (security_binder_transfer_binder(proc->tsk, target_proc->tsk)) {
+				return_error = BR_FAILED_REPLY;
+				goto err_binder_get_ref_failed;
+			}
 			if (ref->node->proc == target_proc) {
 				if (fp->type == BINDER_TYPE_HANDLE)
 					fp->type = BINDER_TYPE_BINDER;
@@ -1634,6 +1655,11 @@ static void binder_transaction(struct binder_proc *proc,
 				return_error = BR_FAILED_REPLY;
 				goto err_fget_failed;
 			}
+			if (security_binder_transfer_file(proc->tsk, target_proc->tsk, file) < 0) {
+				fput(file);
+				return_error = BR_FAILED_REPLY;
+				goto err_get_unused_fd_failed;
+			}
 			target_fd = task_get_unused_fd_flags(target_proc, O_CLOEXEC);
 			if (target_fd < 0) {
 				fput(file);
@@ -2736,6 +2762,9 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		ret = binder_ioctl_set_ctx_mgr(filp);
 		if (ret)
 			goto err;
+		ret = security_binder_set_context_mgr(proc->tsk);
+		if (ret < 0)
+			goto err;
 		break;
 	case BINDER_THREAD_EXIT:
 		binder_debug(BINDER_DEBUG_THREADS, "%d:%d exit\n",
diff --git a/drivers/staging/android/fiq_debugger/Kconfig b/drivers/staging/android/fiq_debugger/Kconfig
new file mode 100644
index 00000000000..56f7f999377
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/Kconfig
@@ -0,0 +1,49 @@
+config FIQ_DEBUGGER
+	bool "FIQ Mode Serial Debugger"
+	default n
+	depends on ARM || ARM64
+	help
+	  The FIQ serial debugger can accept commands even when the
+	  kernel is unresponsive due to being stuck with interrupts
+	  disabled.
+
+config FIQ_DEBUGGER_NO_SLEEP
+	bool "Keep serial debugger active"
+	depends on FIQ_DEBUGGER
+	default n
+	help
+	  Enables the serial debugger at boot. Passing
+	  fiq_debugger.no_sleep on the kernel commandline will
+	  override this config option.
+
+config FIQ_DEBUGGER_WAKEUP_IRQ_ALWAYS_ON
+	bool "Don't disable wakeup IRQ when debugger is active"
+	depends on FIQ_DEBUGGER
+	default n
+	help
+	  Don't disable the wakeup irq when enabling the uart clock.  This will
+	  cause extra interrupts, but it makes the serial debugger usable with
+	  on some MSM radio builds that ignore the uart clock request in power
+	  collapse.
+
+config FIQ_DEBUGGER_CONSOLE
+	bool "Console on FIQ Serial Debugger port"
+	depends on FIQ_DEBUGGER
+	default n
+	help
+	  Enables a console so that printk messages are displayed on
+	  the debugger serial port as the occur.
+
+config FIQ_DEBUGGER_CONSOLE_DEFAULT_ENABLE
+	bool "Put the FIQ debugger into console mode by default"
+	depends on FIQ_DEBUGGER_CONSOLE
+	default n
+	help
+	  If enabled, this puts the fiq debugger into console mode by default.
+	  Otherwise, the fiq debugger will start out in debug mode.
+
+config FIQ_WATCHDOG
+	bool
+	select FIQ_DEBUGGER
+	select PSTORE_RAM
+	default n
diff --git a/drivers/staging/android/fiq_debugger/Makefile b/drivers/staging/android/fiq_debugger/Makefile
new file mode 100644
index 00000000000..a7ca4871cad
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/Makefile
@@ -0,0 +1,4 @@
+obj-y			+= fiq_debugger.o
+obj-$(CONFIG_ARM)	+= fiq_debugger_arm.o
+obj-$(CONFIG_ARM64)	+= fiq_debugger_arm64.o
+obj-$(CONFIG_FIQ_WATCHDOG)	+= fiq_watchdog.o
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger.c b/drivers/staging/android/fiq_debugger/fiq_debugger.c
new file mode 100644
index 00000000000..52f681674c5
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger.c
@@ -0,0 +1,1212 @@
+/*
+ * drivers/staging/android/fiq_debugger.c
+ *
+ * Serial Debugger Interface accessed through an FIQ interrupt.
+ *
+ * Copyright (C) 2008 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <stdarg.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/console.h>
+#include <linux/interrupt.h>
+#include <linux/clk.h>
+#include <linux/platform_device.h>
+#include <linux/kernel_stat.h>
+#include <linux/kmsg_dump.h>
+#include <linux/irq.h>
+#include <linux/delay.h>
+#include <linux/reboot.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/timer.h>
+#include <linux/tty.h>
+#include <linux/tty_flip.h>
+#include <linux/wakelock.h>
+
+#ifdef CONFIG_FIQ_GLUE
+#include <asm/fiq_glue.h>
+#endif
+
+#include <linux/uaccess.h>
+
+#include "fiq_debugger.h"
+#include "fiq_debugger_priv.h"
+#include "fiq_debugger_ringbuf.h"
+
+#define DEBUG_MAX 64
+#define MAX_UNHANDLED_FIQ_COUNT 1000000
+
+#define MAX_FIQ_DEBUGGER_PORTS 4
+
+struct fiq_debugger_state {
+#ifdef CONFIG_FIQ_GLUE
+	struct fiq_glue_handler handler;
+#endif
+	struct fiq_debugger_output output;
+
+	int fiq;
+	int uart_irq;
+	int signal_irq;
+	int wakeup_irq;
+	bool wakeup_irq_no_set_wake;
+	struct clk *clk;
+	struct fiq_debugger_pdata *pdata;
+	struct platform_device *pdev;
+
+	char debug_cmd[DEBUG_MAX];
+	int debug_busy;
+	int debug_abort;
+
+	char debug_buf[DEBUG_MAX];
+	int debug_count;
+
+	bool no_sleep;
+	bool debug_enable;
+	bool ignore_next_wakeup_irq;
+	struct timer_list sleep_timer;
+	spinlock_t sleep_timer_lock;
+	bool uart_enabled;
+	struct wake_lock debugger_wake_lock;
+	bool console_enable;
+	int current_cpu;
+	atomic_t unhandled_fiq_count;
+	bool in_fiq;
+
+	struct work_struct work;
+	spinlock_t work_lock;
+	char work_cmd[DEBUG_MAX];
+
+#ifdef CONFIG_FIQ_DEBUGGER_CONSOLE
+	spinlock_t console_lock;
+	struct console console;
+	struct tty_port tty_port;
+	struct fiq_debugger_ringbuf *tty_rbuf;
+	bool syslog_dumping;
+#endif
+
+	unsigned int last_irqs[NR_IRQS];
+	unsigned int last_local_timer_irqs[NR_CPUS];
+};
+
+#ifdef CONFIG_FIQ_DEBUGGER_CONSOLE
+struct tty_driver *fiq_tty_driver;
+#endif
+
+#ifdef CONFIG_FIQ_DEBUGGER_NO_SLEEP
+static bool initial_no_sleep = true;
+#else
+static bool initial_no_sleep;
+#endif
+
+#ifdef CONFIG_FIQ_DEBUGGER_CONSOLE_DEFAULT_ENABLE
+static bool initial_debug_enable = true;
+static bool initial_console_enable = true;
+#else
+static bool initial_debug_enable;
+static bool initial_console_enable;
+#endif
+
+static bool fiq_kgdb_enable;
+
+module_param_named(no_sleep, initial_no_sleep, bool, 0644);
+module_param_named(debug_enable, initial_debug_enable, bool, 0644);
+module_param_named(console_enable, initial_console_enable, bool, 0644);
+module_param_named(kgdb_enable, fiq_kgdb_enable, bool, 0644);
+
+#ifdef CONFIG_FIQ_DEBUGGER_WAKEUP_IRQ_ALWAYS_ON
+static inline
+void fiq_debugger_enable_wakeup_irq(struct fiq_debugger_state *state) {}
+static inline
+void fiq_debugger_disable_wakeup_irq(struct fiq_debugger_state *state) {}
+#else
+static inline
+void fiq_debugger_enable_wakeup_irq(struct fiq_debugger_state *state)
+{
+	if (state->wakeup_irq < 0)
+		return;
+	enable_irq(state->wakeup_irq);
+	if (!state->wakeup_irq_no_set_wake)
+		enable_irq_wake(state->wakeup_irq);
+}
+static inline
+void fiq_debugger_disable_wakeup_irq(struct fiq_debugger_state *state)
+{
+	if (state->wakeup_irq < 0)
+		return;
+	disable_irq_nosync(state->wakeup_irq);
+	if (!state->wakeup_irq_no_set_wake)
+		disable_irq_wake(state->wakeup_irq);
+}
+#endif
+
+static inline bool fiq_debugger_have_fiq(struct fiq_debugger_state *state)
+{
+	return (state->fiq >= 0);
+}
+
+#ifdef CONFIG_FIQ_GLUE
+static void fiq_debugger_force_irq(struct fiq_debugger_state *state)
+{
+	unsigned int irq = state->signal_irq;
+
+	if (WARN_ON(!fiq_debugger_have_fiq(state)))
+		return;
+	if (state->pdata->force_irq) {
+		state->pdata->force_irq(state->pdev, irq);
+	} else {
+		struct irq_chip *chip = irq_get_chip(irq);
+		if (chip && chip->irq_retrigger)
+			chip->irq_retrigger(irq_get_irq_data(irq));
+	}
+}
+#endif
+
+static void fiq_debugger_uart_enable(struct fiq_debugger_state *state)
+{
+	if (state->clk)
+		clk_enable(state->clk);
+	if (state->pdata->uart_enable)
+		state->pdata->uart_enable(state->pdev);
+}
+
+static void fiq_debugger_uart_disable(struct fiq_debugger_state *state)
+{
+	if (state->pdata->uart_disable)
+		state->pdata->uart_disable(state->pdev);
+	if (state->clk)
+		clk_disable(state->clk);
+}
+
+static void fiq_debugger_uart_flush(struct fiq_debugger_state *state)
+{
+	if (state->pdata->uart_flush)
+		state->pdata->uart_flush(state->pdev);
+}
+
+static void fiq_debugger_putc(struct fiq_debugger_state *state, char c)
+{
+	state->pdata->uart_putc(state->pdev, c);
+}
+
+static void fiq_debugger_puts(struct fiq_debugger_state *state, char *s)
+{
+	unsigned c;
+	while ((c = *s++)) {
+		if (c == '\n')
+			fiq_debugger_putc(state, '\r');
+		fiq_debugger_putc(state, c);
+	}
+}
+
+static void fiq_debugger_prompt(struct fiq_debugger_state *state)
+{
+	fiq_debugger_puts(state, "debug> ");
+}
+
+static void fiq_debugger_dump_kernel_log(struct fiq_debugger_state *state)
+{
+	char buf[512];
+	size_t len;
+	struct kmsg_dumper dumper = { .active = true };
+
+
+	kmsg_dump_rewind_nolock(&dumper);
+	while (kmsg_dump_get_line_nolock(&dumper, true, buf,
+					 sizeof(buf) - 1, &len)) {
+		buf[len] = 0;
+		fiq_debugger_puts(state, buf);
+	}
+}
+
+static void fiq_debugger_printf(struct fiq_debugger_output *output,
+			       const char *fmt, ...)
+{
+	struct fiq_debugger_state *state;
+	char buf[256];
+	va_list ap;
+
+	state = container_of(output, struct fiq_debugger_state, output);
+	va_start(ap, fmt);
+	vsnprintf(buf, sizeof(buf), fmt, ap);
+	va_end(ap);
+
+	fiq_debugger_puts(state, buf);
+}
+
+/* Safe outside fiq context */
+static int fiq_debugger_printf_nfiq(void *cookie, const char *fmt, ...)
+{
+	struct fiq_debugger_state *state = cookie;
+	char buf[256];
+	va_list ap;
+	unsigned long irq_flags;
+
+	va_start(ap, fmt);
+	vsnprintf(buf, 128, fmt, ap);
+	va_end(ap);
+
+	local_irq_save(irq_flags);
+	fiq_debugger_puts(state, buf);
+	fiq_debugger_uart_flush(state);
+	local_irq_restore(irq_flags);
+	return state->debug_abort;
+}
+
+static void fiq_debugger_dump_irqs(struct fiq_debugger_state *state)
+{
+	int n;
+	struct irq_desc *desc;
+
+	fiq_debugger_printf(&state->output,
+			"irqnr       total  since-last   status  name\n");
+	for_each_irq_desc(n, desc) {
+		struct irqaction *act = desc->action;
+		if (!act && !kstat_irqs(n))
+			continue;
+		fiq_debugger_printf(&state->output, "%5d: %10u %11u %8x  %s\n", n,
+			kstat_irqs(n),
+			kstat_irqs(n) - state->last_irqs[n],
+			desc->status_use_accessors,
+			(act && act->name) ? act->name : "???");
+		state->last_irqs[n] = kstat_irqs(n);
+	}
+}
+
+static void fiq_debugger_do_ps(struct fiq_debugger_state *state)
+{
+	struct task_struct *g;
+	struct task_struct *p;
+	unsigned task_state;
+	static const char stat_nam[] = "RSDTtZX";
+
+	fiq_debugger_printf(&state->output, "pid   ppid  prio task            pc\n");
+	read_lock(&tasklist_lock);
+	do_each_thread(g, p) {
+		task_state = p->state ? __ffs(p->state) + 1 : 0;
+		fiq_debugger_printf(&state->output,
+			     "%5d %5d %4d ", p->pid, p->parent->pid, p->prio);
+		fiq_debugger_printf(&state->output, "%-13.13s %c", p->comm,
+			     task_state >= sizeof(stat_nam) ? '?' : stat_nam[task_state]);
+		if (task_state == TASK_RUNNING)
+			fiq_debugger_printf(&state->output, " running\n");
+		else
+			fiq_debugger_printf(&state->output, " %08lx\n",
+					thread_saved_pc(p));
+	} while_each_thread(g, p);
+	read_unlock(&tasklist_lock);
+}
+
+#ifdef CONFIG_FIQ_DEBUGGER_CONSOLE
+static void fiq_debugger_begin_syslog_dump(struct fiq_debugger_state *state)
+{
+	state->syslog_dumping = true;
+}
+
+static void fiq_debugger_end_syslog_dump(struct fiq_debugger_state *state)
+{
+	state->syslog_dumping = false;
+}
+#else
+extern int do_syslog(int type, char __user *bug, int count);
+static void fiq_debugger_begin_syslog_dump(struct fiq_debugger_state *state)
+{
+	do_syslog(5 /* clear */, NULL, 0);
+}
+
+static void fiq_debugger_end_syslog_dump(struct fiq_debugger_state *state)
+{
+	fiq_debugger_dump_kernel_log(state);
+}
+#endif
+
+static void fiq_debugger_do_sysrq(struct fiq_debugger_state *state, char rq)
+{
+	if ((rq == 'g' || rq == 'G') && !fiq_kgdb_enable) {
+		fiq_debugger_printf(&state->output, "sysrq-g blocked\n");
+		return;
+	}
+	fiq_debugger_begin_syslog_dump(state);
+	handle_sysrq(rq);
+	fiq_debugger_end_syslog_dump(state);
+}
+
+#ifdef CONFIG_KGDB
+static void fiq_debugger_do_kgdb(struct fiq_debugger_state *state)
+{
+	if (!fiq_kgdb_enable) {
+		fiq_debugger_printf(&state->output, "kgdb through fiq debugger not enabled\n");
+		return;
+	}
+
+	fiq_debugger_printf(&state->output, "enabling console and triggering kgdb\n");
+	state->console_enable = true;
+	handle_sysrq('g');
+}
+#endif
+
+static void fiq_debugger_schedule_work(struct fiq_debugger_state *state,
+		char *cmd)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&state->work_lock, flags);
+	if (state->work_cmd[0] != '\0') {
+		fiq_debugger_printf(&state->output, "work command processor busy\n");
+		spin_unlock_irqrestore(&state->work_lock, flags);
+		return;
+	}
+
+	strlcpy(state->work_cmd, cmd, sizeof(state->work_cmd));
+	spin_unlock_irqrestore(&state->work_lock, flags);
+
+	schedule_work(&state->work);
+}
+
+static void fiq_debugger_work(struct work_struct *work)
+{
+	struct fiq_debugger_state *state;
+	char work_cmd[DEBUG_MAX];
+	char *cmd;
+	unsigned long flags;
+
+	state = container_of(work, struct fiq_debugger_state, work);
+
+	spin_lock_irqsave(&state->work_lock, flags);
+
+	strlcpy(work_cmd, state->work_cmd, sizeof(work_cmd));
+	state->work_cmd[0] = '\0';
+
+	spin_unlock_irqrestore(&state->work_lock, flags);
+
+	cmd = work_cmd;
+	if (!strncmp(cmd, "reboot", 6)) {
+		cmd += 6;
+		while (*cmd == ' ')
+			cmd++;
+		if (cmd != '\0')
+			kernel_restart(cmd);
+		else
+			kernel_restart(NULL);
+	} else {
+		fiq_debugger_printf(&state->output, "unknown work command '%s'\n",
+				work_cmd);
+	}
+}
+
+/* This function CANNOT be called in FIQ context */
+static void fiq_debugger_irq_exec(struct fiq_debugger_state *state, char *cmd)
+{
+	if (!strcmp(cmd, "ps"))
+		fiq_debugger_do_ps(state);
+	if (!strcmp(cmd, "sysrq"))
+		fiq_debugger_do_sysrq(state, 'h');
+	if (!strncmp(cmd, "sysrq ", 6))
+		fiq_debugger_do_sysrq(state, cmd[6]);
+#ifdef CONFIG_KGDB
+	if (!strcmp(cmd, "kgdb"))
+		fiq_debugger_do_kgdb(state);
+#endif
+	if (!strncmp(cmd, "reboot", 6))
+		fiq_debugger_schedule_work(state, cmd);
+}
+
+static void fiq_debugger_help(struct fiq_debugger_state *state)
+{
+	fiq_debugger_printf(&state->output,
+				"FIQ Debugger commands:\n"
+				" pc            PC status\n"
+				" regs          Register dump\n"
+				" allregs       Extended Register dump\n"
+				" bt            Stack trace\n"
+				" reboot [<c>]  Reboot with command <c>\n"
+				" reset [<c>]   Hard reset with command <c>\n"
+				" irqs          Interupt status\n"
+				" kmsg          Kernel log\n"
+				" version       Kernel version\n");
+	fiq_debugger_printf(&state->output,
+				" sleep         Allow sleep while in FIQ\n"
+				" nosleep       Disable sleep while in FIQ\n"
+				" console       Switch terminal to console\n"
+				" cpu           Current CPU\n"
+				" cpu <number>  Switch to CPU<number>\n");
+	fiq_debugger_printf(&state->output,
+				" ps            Process list\n"
+				" sysrq         sysrq options\n"
+				" sysrq <param> Execute sysrq with <param>\n");
+#ifdef CONFIG_KGDB
+	fiq_debugger_printf(&state->output,
+				" kgdb          Enter kernel debugger\n");
+#endif
+}
+
+static void fiq_debugger_take_affinity(void *info)
+{
+	struct fiq_debugger_state *state = info;
+	struct cpumask cpumask;
+
+	cpumask_clear(&cpumask);
+	cpumask_set_cpu(get_cpu(), &cpumask);
+
+	irq_set_affinity(state->uart_irq, &cpumask);
+}
+
+static void fiq_debugger_switch_cpu(struct fiq_debugger_state *state, int cpu)
+{
+	if (!fiq_debugger_have_fiq(state))
+		smp_call_function_single(cpu, fiq_debugger_take_affinity, state,
+				false);
+	state->current_cpu = cpu;
+}
+
+static bool fiq_debugger_fiq_exec(struct fiq_debugger_state *state,
+			const char *cmd, const struct pt_regs *regs,
+			void *svc_sp)
+{
+	bool signal_helper = false;
+
+	if (!strcmp(cmd, "help") || !strcmp(cmd, "?")) {
+		fiq_debugger_help(state);
+	} else if (!strcmp(cmd, "pc")) {
+		fiq_debugger_dump_pc(&state->output, regs);
+	} else if (!strcmp(cmd, "regs")) {
+		fiq_debugger_dump_regs(&state->output, regs);
+	} else if (!strcmp(cmd, "allregs")) {
+		fiq_debugger_dump_allregs(&state->output, regs);
+	} else if (!strcmp(cmd, "bt")) {
+		fiq_debugger_dump_stacktrace(&state->output, regs, 100, svc_sp);
+	} else if (!strncmp(cmd, "reset", 5)) {
+		cmd += 5;
+		while (*cmd == ' ')
+			cmd++;
+		if (*cmd) {
+			char tmp_cmd[32];
+			strlcpy(tmp_cmd, cmd, sizeof(tmp_cmd));
+			machine_restart(tmp_cmd);
+		} else {
+			machine_restart(NULL);
+		}
+	} else if (!strcmp(cmd, "irqs")) {
+		fiq_debugger_dump_irqs(state);
+	} else if (!strcmp(cmd, "kmsg")) {
+		fiq_debugger_dump_kernel_log(state);
+	} else if (!strcmp(cmd, "version")) {
+		fiq_debugger_printf(&state->output, "%s\n", linux_banner);
+	} else if (!strcmp(cmd, "sleep")) {
+		state->no_sleep = false;
+		fiq_debugger_printf(&state->output, "enabling sleep\n");
+	} else if (!strcmp(cmd, "nosleep")) {
+		state->no_sleep = true;
+		fiq_debugger_printf(&state->output, "disabling sleep\n");
+	} else if (!strcmp(cmd, "console")) {
+		fiq_debugger_printf(&state->output, "console mode\n");
+		fiq_debugger_uart_flush(state);
+		state->console_enable = true;
+	} else if (!strcmp(cmd, "cpu")) {
+		fiq_debugger_printf(&state->output, "cpu %d\n", state->current_cpu);
+	} else if (!strncmp(cmd, "cpu ", 4)) {
+		unsigned long cpu = 0;
+		if (kstrtoul(cmd + 4, 10, &cpu) == 0)
+			fiq_debugger_switch_cpu(state, cpu);
+		else
+			fiq_debugger_printf(&state->output, "invalid cpu\n");
+		fiq_debugger_printf(&state->output, "cpu %d\n", state->current_cpu);
+	} else {
+		if (state->debug_busy) {
+			fiq_debugger_printf(&state->output,
+				"command processor busy. trying to abort.\n");
+			state->debug_abort = -1;
+		} else {
+			strcpy(state->debug_cmd, cmd);
+			state->debug_busy = 1;
+		}
+
+		return true;
+	}
+	if (!state->console_enable)
+		fiq_debugger_prompt(state);
+
+	return signal_helper;
+}
+
+static void fiq_debugger_sleep_timer_expired(unsigned long data)
+{
+	struct fiq_debugger_state *state = (struct fiq_debugger_state *)data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&state->sleep_timer_lock, flags);
+	if (state->uart_enabled && !state->no_sleep) {
+		if (state->debug_enable && !state->console_enable) {
+			state->debug_enable = false;
+			fiq_debugger_printf_nfiq(state,
+					"suspending fiq debugger\n");
+		}
+		state->ignore_next_wakeup_irq = true;
+		fiq_debugger_uart_disable(state);
+		state->uart_enabled = false;
+		fiq_debugger_enable_wakeup_irq(state);
+	}
+	wake_unlock(&state->debugger_wake_lock);
+	spin_unlock_irqrestore(&state->sleep_timer_lock, flags);
+}
+
+static void fiq_debugger_handle_wakeup(struct fiq_debugger_state *state)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&state->sleep_timer_lock, flags);
+	if (state->wakeup_irq >= 0 && state->ignore_next_wakeup_irq) {
+		state->ignore_next_wakeup_irq = false;
+	} else if (!state->uart_enabled) {
+		wake_lock(&state->debugger_wake_lock);
+		fiq_debugger_uart_enable(state);
+		state->uart_enabled = true;
+		fiq_debugger_disable_wakeup_irq(state);
+		mod_timer(&state->sleep_timer, jiffies + HZ / 2);
+	}
+	spin_unlock_irqrestore(&state->sleep_timer_lock, flags);
+}
+
+static irqreturn_t fiq_debugger_wakeup_irq_handler(int irq, void *dev)
+{
+	struct fiq_debugger_state *state = dev;
+
+	if (!state->no_sleep)
+		fiq_debugger_puts(state, "WAKEUP\n");
+	fiq_debugger_handle_wakeup(state);
+
+	return IRQ_HANDLED;
+}
+
+static
+void fiq_debugger_handle_console_irq_context(struct fiq_debugger_state *state)
+{
+#if defined(CONFIG_FIQ_DEBUGGER_CONSOLE)
+	if (state->tty_port.ops) {
+		int i;
+		int count = fiq_debugger_ringbuf_level(state->tty_rbuf);
+		for (i = 0; i < count; i++) {
+			int c = fiq_debugger_ringbuf_peek(state->tty_rbuf, 0);
+			tty_insert_flip_char(&state->tty_port, c, TTY_NORMAL);
+			if (!fiq_debugger_ringbuf_consume(state->tty_rbuf, 1))
+				pr_warn("fiq tty failed to consume byte\n");
+		}
+		tty_flip_buffer_push(&state->tty_port);
+	}
+#endif
+}
+
+static void fiq_debugger_handle_irq_context(struct fiq_debugger_state *state)
+{
+	if (!state->no_sleep) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&state->sleep_timer_lock, flags);
+		wake_lock(&state->debugger_wake_lock);
+		mod_timer(&state->sleep_timer, jiffies + HZ * 5);
+		spin_unlock_irqrestore(&state->sleep_timer_lock, flags);
+	}
+	fiq_debugger_handle_console_irq_context(state);
+	if (state->debug_busy) {
+		fiq_debugger_irq_exec(state, state->debug_cmd);
+		if (!state->console_enable)
+			fiq_debugger_prompt(state);
+		state->debug_busy = 0;
+	}
+}
+
+static int fiq_debugger_getc(struct fiq_debugger_state *state)
+{
+	return state->pdata->uart_getc(state->pdev);
+}
+
+static bool fiq_debugger_handle_uart_interrupt(struct fiq_debugger_state *state,
+			int this_cpu, const struct pt_regs *regs, void *svc_sp)
+{
+	int c;
+	static int last_c;
+	int count = 0;
+	bool signal_helper = false;
+
+	if (this_cpu != state->current_cpu) {
+		if (state->in_fiq)
+			return false;
+
+		if (atomic_inc_return(&state->unhandled_fiq_count) !=
+					MAX_UNHANDLED_FIQ_COUNT)
+			return false;
+
+		fiq_debugger_printf(&state->output,
+			"fiq_debugger: cpu %d not responding, "
+			"reverting to cpu %d\n", state->current_cpu,
+			this_cpu);
+
+		atomic_set(&state->unhandled_fiq_count, 0);
+		fiq_debugger_switch_cpu(state, this_cpu);
+		return false;
+	}
+
+	state->in_fiq = true;
+
+	while ((c = fiq_debugger_getc(state)) != FIQ_DEBUGGER_NO_CHAR) {
+		count++;
+		if (!state->debug_enable) {
+			if ((c == 13) || (c == 10)) {
+				state->debug_enable = true;
+				state->debug_count = 0;
+				fiq_debugger_prompt(state);
+			}
+		} else if (c == FIQ_DEBUGGER_BREAK) {
+			state->console_enable = false;
+			fiq_debugger_puts(state, "fiq debugger mode\n");
+			state->debug_count = 0;
+			fiq_debugger_prompt(state);
+#ifdef CONFIG_FIQ_DEBUGGER_CONSOLE
+		} else if (state->console_enable && state->tty_rbuf) {
+			fiq_debugger_ringbuf_push(state->tty_rbuf, c);
+			signal_helper = true;
+#endif
+		} else if ((c >= ' ') && (c < 127)) {
+			if (state->debug_count < (DEBUG_MAX - 1)) {
+				state->debug_buf[state->debug_count++] = c;
+				fiq_debugger_putc(state, c);
+			}
+		} else if ((c == 8) || (c == 127)) {
+			if (state->debug_count > 0) {
+				state->debug_count--;
+				fiq_debugger_putc(state, 8);
+				fiq_debugger_putc(state, ' ');
+				fiq_debugger_putc(state, 8);
+			}
+		} else if ((c == 13) || (c == 10)) {
+			if (c == '\r' || (c == '\n' && last_c != '\r')) {
+				fiq_debugger_putc(state, '\r');
+				fiq_debugger_putc(state, '\n');
+			}
+			if (state->debug_count) {
+				state->debug_buf[state->debug_count] = 0;
+				state->debug_count = 0;
+				signal_helper |=
+					fiq_debugger_fiq_exec(state,
+							state->debug_buf,
+							regs, svc_sp);
+			} else {
+				fiq_debugger_prompt(state);
+			}
+		}
+		last_c = c;
+	}
+	if (!state->console_enable)
+		fiq_debugger_uart_flush(state);
+	if (state->pdata->fiq_ack)
+		state->pdata->fiq_ack(state->pdev, state->fiq);
+
+	/* poke sleep timer if necessary */
+	if (state->debug_enable && !state->no_sleep)
+		signal_helper = true;
+
+	atomic_set(&state->unhandled_fiq_count, 0);
+	state->in_fiq = false;
+
+	return signal_helper;
+}
+
+#ifdef CONFIG_FIQ_GLUE
+static void fiq_debugger_fiq(struct fiq_glue_handler *h,
+		const struct pt_regs *regs, void *svc_sp)
+{
+	struct fiq_debugger_state *state =
+		container_of(h, struct fiq_debugger_state, handler);
+	unsigned int this_cpu = THREAD_INFO(svc_sp)->cpu;
+	bool need_irq;
+
+	need_irq = fiq_debugger_handle_uart_interrupt(state, this_cpu, regs,
+			svc_sp);
+	if (need_irq)
+		fiq_debugger_force_irq(state);
+}
+#endif
+
+/*
+ * When not using FIQs, we only use this single interrupt as an entry point.
+ * This just effectively takes over the UART interrupt and does all the work
+ * in this context.
+ */
+static irqreturn_t fiq_debugger_uart_irq(int irq, void *dev)
+{
+	struct fiq_debugger_state *state = dev;
+	bool not_done;
+
+	fiq_debugger_handle_wakeup(state);
+
+	/* handle the debugger irq in regular context */
+	not_done = fiq_debugger_handle_uart_interrupt(state, smp_processor_id(),
+					      get_irq_regs(),
+					      current_thread_info());
+	if (not_done)
+		fiq_debugger_handle_irq_context(state);
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * If FIQs are used, not everything can happen in fiq context.
+ * FIQ handler does what it can and then signals this interrupt to finish the
+ * job in irq context.
+ */
+static irqreturn_t fiq_debugger_signal_irq(int irq, void *dev)
+{
+	struct fiq_debugger_state *state = dev;
+
+	if (state->pdata->force_irq_ack)
+		state->pdata->force_irq_ack(state->pdev, state->signal_irq);
+
+	fiq_debugger_handle_irq_context(state);
+
+	return IRQ_HANDLED;
+}
+
+#ifdef CONFIG_FIQ_GLUE
+static void fiq_debugger_resume(struct fiq_glue_handler *h)
+{
+	struct fiq_debugger_state *state =
+		container_of(h, struct fiq_debugger_state, handler);
+	if (state->pdata->uart_resume)
+		state->pdata->uart_resume(state->pdev);
+}
+#endif
+
+#if defined(CONFIG_FIQ_DEBUGGER_CONSOLE)
+struct tty_driver *fiq_debugger_console_device(struct console *co, int *index)
+{
+	*index = co->index;
+	return fiq_tty_driver;
+}
+
+static void fiq_debugger_console_write(struct console *co,
+				const char *s, unsigned int count)
+{
+	struct fiq_debugger_state *state;
+	unsigned long flags;
+
+	state = container_of(co, struct fiq_debugger_state, console);
+
+	if (!state->console_enable && !state->syslog_dumping)
+		return;
+
+	fiq_debugger_uart_enable(state);
+	spin_lock_irqsave(&state->console_lock, flags);
+	while (count--) {
+		if (*s == '\n')
+			fiq_debugger_putc(state, '\r');
+		fiq_debugger_putc(state, *s++);
+	}
+	fiq_debugger_uart_flush(state);
+	spin_unlock_irqrestore(&state->console_lock, flags);
+	fiq_debugger_uart_disable(state);
+}
+
+static struct console fiq_debugger_console = {
+	.name = "ttyFIQ",
+	.device = fiq_debugger_console_device,
+	.write = fiq_debugger_console_write,
+	.flags = CON_PRINTBUFFER | CON_ANYTIME | CON_ENABLED,
+};
+
+int fiq_tty_open(struct tty_struct *tty, struct file *filp)
+{
+	int line = tty->index;
+	struct fiq_debugger_state **states = tty->driver->driver_state;
+	struct fiq_debugger_state *state = states[line];
+
+	return tty_port_open(&state->tty_port, tty, filp);
+}
+
+void fiq_tty_close(struct tty_struct *tty, struct file *filp)
+{
+	tty_port_close(tty->port, tty, filp);
+}
+
+int  fiq_tty_write(struct tty_struct *tty, const unsigned char *buf, int count)
+{
+	int i;
+	int line = tty->index;
+	struct fiq_debugger_state **states = tty->driver->driver_state;
+	struct fiq_debugger_state *state = states[line];
+
+	if (!state->console_enable)
+		return count;
+
+	fiq_debugger_uart_enable(state);
+	spin_lock_irq(&state->console_lock);
+	for (i = 0; i < count; i++)
+		fiq_debugger_putc(state, *buf++);
+	spin_unlock_irq(&state->console_lock);
+	fiq_debugger_uart_disable(state);
+
+	return count;
+}
+
+int  fiq_tty_write_room(struct tty_struct *tty)
+{
+	return 16;
+}
+
+#ifdef CONFIG_CONSOLE_POLL
+static int fiq_tty_poll_init(struct tty_driver *driver, int line, char *options)
+{
+	return 0;
+}
+
+static int fiq_tty_poll_get_char(struct tty_driver *driver, int line)
+{
+	struct fiq_debugger_state **states = driver->driver_state;
+	struct fiq_debugger_state *state = states[line];
+	int c = NO_POLL_CHAR;
+
+	fiq_debugger_uart_enable(state);
+	if (fiq_debugger_have_fiq(state)) {
+		int count = fiq_debugger_ringbuf_level(state->tty_rbuf);
+		if (count > 0) {
+			c = fiq_debugger_ringbuf_peek(state->tty_rbuf, 0);
+			fiq_debugger_ringbuf_consume(state->tty_rbuf, 1);
+		}
+	} else {
+		c = fiq_debugger_getc(state);
+		if (c == FIQ_DEBUGGER_NO_CHAR)
+			c = NO_POLL_CHAR;
+	}
+	fiq_debugger_uart_disable(state);
+
+	return c;
+}
+
+static void fiq_tty_poll_put_char(struct tty_driver *driver, int line, char ch)
+{
+	struct fiq_debugger_state **states = driver->driver_state;
+	struct fiq_debugger_state *state = states[line];
+	fiq_debugger_uart_enable(state);
+	fiq_debugger_putc(state, ch);
+	fiq_debugger_uart_disable(state);
+}
+#endif
+
+static const struct tty_port_operations fiq_tty_port_ops;
+
+static const struct tty_operations fiq_tty_driver_ops = {
+	.write = fiq_tty_write,
+	.write_room = fiq_tty_write_room,
+	.open = fiq_tty_open,
+	.close = fiq_tty_close,
+#ifdef CONFIG_CONSOLE_POLL
+	.poll_init = fiq_tty_poll_init,
+	.poll_get_char = fiq_tty_poll_get_char,
+	.poll_put_char = fiq_tty_poll_put_char,
+#endif
+};
+
+static int fiq_debugger_tty_init(void)
+{
+	int ret;
+	struct fiq_debugger_state **states = NULL;
+
+	states = kzalloc(sizeof(*states) * MAX_FIQ_DEBUGGER_PORTS, GFP_KERNEL);
+	if (!states) {
+		pr_err("Failed to allocate fiq debugger state structres\n");
+		return -ENOMEM;
+	}
+
+	fiq_tty_driver = alloc_tty_driver(MAX_FIQ_DEBUGGER_PORTS);
+	if (!fiq_tty_driver) {
+		pr_err("Failed to allocate fiq debugger tty\n");
+		ret = -ENOMEM;
+		goto err_free_state;
+	}
+
+	fiq_tty_driver->owner		= THIS_MODULE;
+	fiq_tty_driver->driver_name	= "fiq-debugger";
+	fiq_tty_driver->name		= "ttyFIQ";
+	fiq_tty_driver->type		= TTY_DRIVER_TYPE_SERIAL;
+	fiq_tty_driver->subtype		= SERIAL_TYPE_NORMAL;
+	fiq_tty_driver->init_termios	= tty_std_termios;
+	fiq_tty_driver->flags		= TTY_DRIVER_REAL_RAW |
+					  TTY_DRIVER_DYNAMIC_DEV;
+	fiq_tty_driver->driver_state	= states;
+
+	fiq_tty_driver->init_termios.c_cflag =
+					B115200 | CS8 | CREAD | HUPCL | CLOCAL;
+	fiq_tty_driver->init_termios.c_ispeed = 115200;
+	fiq_tty_driver->init_termios.c_ospeed = 115200;
+
+	tty_set_operations(fiq_tty_driver, &fiq_tty_driver_ops);
+
+	ret = tty_register_driver(fiq_tty_driver);
+	if (ret) {
+		pr_err("Failed to register fiq tty: %d\n", ret);
+		goto err_free_tty;
+	}
+
+	pr_info("Registered FIQ tty driver\n");
+	return 0;
+
+err_free_tty:
+	put_tty_driver(fiq_tty_driver);
+	fiq_tty_driver = NULL;
+err_free_state:
+	kfree(states);
+	return ret;
+}
+
+static int fiq_debugger_tty_init_one(struct fiq_debugger_state *state)
+{
+	int ret;
+	struct device *tty_dev;
+	struct fiq_debugger_state **states = fiq_tty_driver->driver_state;
+
+	states[state->pdev->id] = state;
+
+	state->tty_rbuf = fiq_debugger_ringbuf_alloc(1024);
+	if (!state->tty_rbuf) {
+		pr_err("Failed to allocate fiq debugger ringbuf\n");
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	tty_port_init(&state->tty_port);
+	state->tty_port.ops = &fiq_tty_port_ops;
+
+	tty_dev = tty_port_register_device(&state->tty_port, fiq_tty_driver,
+					   state->pdev->id, &state->pdev->dev);
+	if (IS_ERR(tty_dev)) {
+		pr_err("Failed to register fiq debugger tty device\n");
+		ret = PTR_ERR(tty_dev);
+		goto err;
+	}
+
+	device_set_wakeup_capable(tty_dev, 1);
+
+	pr_info("Registered fiq debugger ttyFIQ%d\n", state->pdev->id);
+
+	return 0;
+
+err:
+	fiq_debugger_ringbuf_free(state->tty_rbuf);
+	state->tty_rbuf = NULL;
+	return ret;
+}
+#endif
+
+static int fiq_debugger_dev_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct fiq_debugger_state *state = platform_get_drvdata(pdev);
+
+	if (state->pdata->uart_dev_suspend)
+		return state->pdata->uart_dev_suspend(pdev);
+	return 0;
+}
+
+static int fiq_debugger_dev_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct fiq_debugger_state *state = platform_get_drvdata(pdev);
+
+	if (state->pdata->uart_dev_resume)
+		return state->pdata->uart_dev_resume(pdev);
+	return 0;
+}
+
+static int fiq_debugger_probe(struct platform_device *pdev)
+{
+	int ret;
+	struct fiq_debugger_pdata *pdata = dev_get_platdata(&pdev->dev);
+	struct fiq_debugger_state *state;
+	int fiq;
+	int uart_irq;
+
+	if (pdev->id >= MAX_FIQ_DEBUGGER_PORTS)
+		return -EINVAL;
+
+	if (!pdata->uart_getc || !pdata->uart_putc)
+		return -EINVAL;
+	if ((pdata->uart_enable && !pdata->uart_disable) ||
+	    (!pdata->uart_enable && pdata->uart_disable))
+		return -EINVAL;
+
+	fiq = platform_get_irq_byname(pdev, "fiq");
+	uart_irq = platform_get_irq_byname(pdev, "uart_irq");
+
+	/* uart_irq mode and fiq mode are mutually exclusive, but one of them
+	 * is required */
+	if ((uart_irq < 0 && fiq < 0) || (uart_irq >= 0 && fiq >= 0))
+		return -EINVAL;
+	if (fiq >= 0 && !pdata->fiq_enable)
+		return -EINVAL;
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	state->output.printf = fiq_debugger_printf;
+	setup_timer(&state->sleep_timer, fiq_debugger_sleep_timer_expired,
+		    (unsigned long)state);
+	state->pdata = pdata;
+	state->pdev = pdev;
+	state->no_sleep = initial_no_sleep;
+	state->debug_enable = initial_debug_enable;
+	state->console_enable = initial_console_enable;
+
+	state->fiq = fiq;
+	state->uart_irq = uart_irq;
+	state->signal_irq = platform_get_irq_byname(pdev, "signal");
+	state->wakeup_irq = platform_get_irq_byname(pdev, "wakeup");
+
+	INIT_WORK(&state->work, fiq_debugger_work);
+	spin_lock_init(&state->work_lock);
+
+	platform_set_drvdata(pdev, state);
+
+	spin_lock_init(&state->sleep_timer_lock);
+
+	if (state->wakeup_irq < 0 && fiq_debugger_have_fiq(state))
+		state->no_sleep = true;
+	state->ignore_next_wakeup_irq = !state->no_sleep;
+
+	wake_lock_init(&state->debugger_wake_lock,
+			WAKE_LOCK_SUSPEND, "serial-debug");
+
+	state->clk = clk_get(&pdev->dev, NULL);
+	if (IS_ERR(state->clk))
+		state->clk = NULL;
+
+	/* do not call pdata->uart_enable here since uart_init may still
+	 * need to do some initialization before uart_enable can work.
+	 * So, only try to manage the clock during init.
+	 */
+	if (state->clk)
+		clk_enable(state->clk);
+
+	if (pdata->uart_init) {
+		ret = pdata->uart_init(pdev);
+		if (ret)
+			goto err_uart_init;
+	}
+
+	fiq_debugger_printf_nfiq(state,
+				"<hit enter %sto activate fiq debugger>\n",
+				state->no_sleep ? "" : "twice ");
+
+#ifdef CONFIG_FIQ_GLUE
+	if (fiq_debugger_have_fiq(state)) {
+		state->handler.fiq = fiq_debugger_fiq;
+		state->handler.resume = fiq_debugger_resume;
+		ret = fiq_glue_register_handler(&state->handler);
+		if (ret) {
+			pr_err("%s: could not install fiq handler\n", __func__);
+			goto err_register_irq;
+		}
+
+		pdata->fiq_enable(pdev, state->fiq, 1);
+	} else
+#endif
+	{
+		ret = request_irq(state->uart_irq, fiq_debugger_uart_irq,
+				  IRQF_NO_SUSPEND, "debug", state);
+		if (ret) {
+			pr_err("%s: could not install irq handler\n", __func__);
+			goto err_register_irq;
+		}
+
+		/* for irq-only mode, we want this irq to wake us up, if it
+		 * can.
+		 */
+		enable_irq_wake(state->uart_irq);
+	}
+
+	if (state->clk)
+		clk_disable(state->clk);
+
+	if (state->signal_irq >= 0) {
+		ret = request_irq(state->signal_irq, fiq_debugger_signal_irq,
+			  IRQF_TRIGGER_RISING, "debug-signal", state);
+		if (ret)
+			pr_err("serial_debugger: could not install signal_irq");
+	}
+
+	if (state->wakeup_irq >= 0) {
+		ret = request_irq(state->wakeup_irq,
+				  fiq_debugger_wakeup_irq_handler,
+				  IRQF_TRIGGER_FALLING | IRQF_DISABLED,
+				  "debug-wakeup", state);
+		if (ret) {
+			pr_err("serial_debugger: "
+				"could not install wakeup irq\n");
+			state->wakeup_irq = -1;
+		} else {
+			ret = enable_irq_wake(state->wakeup_irq);
+			if (ret) {
+				pr_err("serial_debugger: "
+					"could not enable wakeup\n");
+				state->wakeup_irq_no_set_wake = true;
+			}
+		}
+	}
+	if (state->no_sleep)
+		fiq_debugger_handle_wakeup(state);
+
+#if defined(CONFIG_FIQ_DEBUGGER_CONSOLE)
+	spin_lock_init(&state->console_lock);
+	state->console = fiq_debugger_console;
+	state->console.index = pdev->id;
+	if (!console_set_on_cmdline)
+		add_preferred_console(state->console.name,
+			state->console.index, NULL);
+	register_console(&state->console);
+	fiq_debugger_tty_init_one(state);
+#endif
+	return 0;
+
+err_register_irq:
+	if (pdata->uart_free)
+		pdata->uart_free(pdev);
+err_uart_init:
+	if (state->clk)
+		clk_disable(state->clk);
+	if (state->clk)
+		clk_put(state->clk);
+	wake_lock_destroy(&state->debugger_wake_lock);
+	platform_set_drvdata(pdev, NULL);
+	kfree(state);
+	return ret;
+}
+
+static const struct dev_pm_ops fiq_debugger_dev_pm_ops = {
+	.suspend	= fiq_debugger_dev_suspend,
+	.resume		= fiq_debugger_dev_resume,
+};
+
+static struct platform_driver fiq_debugger_driver = {
+	.probe	= fiq_debugger_probe,
+	.driver	= {
+		.name	= "fiq_debugger",
+		.pm	= &fiq_debugger_dev_pm_ops,
+	},
+};
+
+static int __init fiq_debugger_init(void)
+{
+#if defined(CONFIG_FIQ_DEBUGGER_CONSOLE)
+	fiq_debugger_tty_init();
+#endif
+	return platform_driver_register(&fiq_debugger_driver);
+}
+
+postcore_initcall(fiq_debugger_init);
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger.h b/drivers/staging/android/fiq_debugger/fiq_debugger.h
new file mode 100644
index 00000000000..c9ec4f8db08
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger.h
@@ -0,0 +1,64 @@
+/*
+ * drivers/staging/android/fiq_debugger/fiq_debugger.h
+ *
+ * Copyright (C) 2010 Google, Inc.
+ * Author: Colin Cross <ccross@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _ARCH_ARM_MACH_TEGRA_FIQ_DEBUGGER_H_
+#define _ARCH_ARM_MACH_TEGRA_FIQ_DEBUGGER_H_
+
+#include <linux/serial_core.h>
+
+#define FIQ_DEBUGGER_NO_CHAR NO_POLL_CHAR
+#define FIQ_DEBUGGER_BREAK 0x00ff0100
+
+#define FIQ_DEBUGGER_FIQ_IRQ_NAME	"fiq"
+#define FIQ_DEBUGGER_SIGNAL_IRQ_NAME	"signal"
+#define FIQ_DEBUGGER_WAKEUP_IRQ_NAME	"wakeup"
+
+/**
+ * struct fiq_debugger_pdata - fiq debugger platform data
+ * @uart_resume:	used to restore uart state right before enabling
+ *			the fiq.
+ * @uart_enable:	Do the work necessary to communicate with the uart
+ *			hw (enable clocks, etc.). This must be ref-counted.
+ * @uart_disable:	Do the work necessary to disable the uart hw
+ *			(disable clocks, etc.). This must be ref-counted.
+ * @uart_dev_suspend:	called during PM suspend, generally not needed
+ *			for real fiq mode debugger.
+ * @uart_dev_resume:	called during PM resume, generally not needed
+ *			for real fiq mode debugger.
+ */
+struct fiq_debugger_pdata {
+	int (*uart_init)(struct platform_device *pdev);
+	void (*uart_free)(struct platform_device *pdev);
+	int (*uart_resume)(struct platform_device *pdev);
+	int (*uart_getc)(struct platform_device *pdev);
+	void (*uart_putc)(struct platform_device *pdev, unsigned int c);
+	void (*uart_flush)(struct platform_device *pdev);
+	void (*uart_enable)(struct platform_device *pdev);
+	void (*uart_disable)(struct platform_device *pdev);
+
+	int (*uart_dev_suspend)(struct platform_device *pdev);
+	int (*uart_dev_resume)(struct platform_device *pdev);
+
+	void (*fiq_enable)(struct platform_device *pdev, unsigned int fiq,
+								bool enable);
+	void (*fiq_ack)(struct platform_device *pdev, unsigned int fiq);
+
+	void (*force_irq)(struct platform_device *pdev, unsigned int irq);
+	void (*force_irq_ack)(struct platform_device *pdev, unsigned int irq);
+};
+
+#endif
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger_arm.c b/drivers/staging/android/fiq_debugger/fiq_debugger_arm.c
new file mode 100644
index 00000000000..8b3e0137be1
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger_arm.c
@@ -0,0 +1,240 @@
+/*
+ * Copyright (C) 2014 Google, Inc.
+ * Author: Colin Cross <ccross@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/ptrace.h>
+#include <linux/uaccess.h>
+
+#include <asm/stacktrace.h>
+
+#include "fiq_debugger_priv.h"
+
+static char *mode_name(unsigned cpsr)
+{
+	switch (cpsr & MODE_MASK) {
+	case USR_MODE: return "USR";
+	case FIQ_MODE: return "FIQ";
+	case IRQ_MODE: return "IRQ";
+	case SVC_MODE: return "SVC";
+	case ABT_MODE: return "ABT";
+	case UND_MODE: return "UND";
+	case SYSTEM_MODE: return "SYS";
+	default: return "???";
+	}
+}
+
+void fiq_debugger_dump_pc(struct fiq_debugger_output *output,
+		const struct pt_regs *regs)
+{
+	output->printf(output, " pc %08x cpsr %08x mode %s\n",
+		regs->ARM_pc, regs->ARM_cpsr, mode_name(regs->ARM_cpsr));
+}
+
+void fiq_debugger_dump_regs(struct fiq_debugger_output *output,
+		const struct pt_regs *regs)
+{
+	output->printf(output,
+			" r0 %08x  r1 %08x  r2 %08x  r3 %08x\n",
+			regs->ARM_r0, regs->ARM_r1, regs->ARM_r2, regs->ARM_r3);
+	output->printf(output,
+			" r4 %08x  r5 %08x  r6 %08x  r7 %08x\n",
+			regs->ARM_r4, regs->ARM_r5, regs->ARM_r6, regs->ARM_r7);
+	output->printf(output,
+			" r8 %08x  r9 %08x r10 %08x r11 %08x  mode %s\n",
+			regs->ARM_r8, regs->ARM_r9, regs->ARM_r10, regs->ARM_fp,
+			mode_name(regs->ARM_cpsr));
+	output->printf(output,
+			" ip %08x  sp %08x  lr %08x  pc %08x cpsr %08x\n",
+			regs->ARM_ip, regs->ARM_sp, regs->ARM_lr, regs->ARM_pc,
+			regs->ARM_cpsr);
+}
+
+struct mode_regs {
+	unsigned long sp_svc;
+	unsigned long lr_svc;
+	unsigned long spsr_svc;
+
+	unsigned long sp_abt;
+	unsigned long lr_abt;
+	unsigned long spsr_abt;
+
+	unsigned long sp_und;
+	unsigned long lr_und;
+	unsigned long spsr_und;
+
+	unsigned long sp_irq;
+	unsigned long lr_irq;
+	unsigned long spsr_irq;
+
+	unsigned long r8_fiq;
+	unsigned long r9_fiq;
+	unsigned long r10_fiq;
+	unsigned long r11_fiq;
+	unsigned long r12_fiq;
+	unsigned long sp_fiq;
+	unsigned long lr_fiq;
+	unsigned long spsr_fiq;
+};
+
+static void __naked get_mode_regs(struct mode_regs *regs)
+{
+	asm volatile (
+	"mrs	r1, cpsr\n"
+	"msr	cpsr_c, #0xd3 @(SVC_MODE | PSR_I_BIT | PSR_F_BIT)\n"
+	"stmia	r0!, {r13 - r14}\n"
+	"mrs	r2, spsr\n"
+	"msr	cpsr_c, #0xd7 @(ABT_MODE | PSR_I_BIT | PSR_F_BIT)\n"
+	"stmia	r0!, {r2, r13 - r14}\n"
+	"mrs	r2, spsr\n"
+	"msr	cpsr_c, #0xdb @(UND_MODE | PSR_I_BIT | PSR_F_BIT)\n"
+	"stmia	r0!, {r2, r13 - r14}\n"
+	"mrs	r2, spsr\n"
+	"msr	cpsr_c, #0xd2 @(IRQ_MODE | PSR_I_BIT | PSR_F_BIT)\n"
+	"stmia	r0!, {r2, r13 - r14}\n"
+	"mrs	r2, spsr\n"
+	"msr	cpsr_c, #0xd1 @(FIQ_MODE | PSR_I_BIT | PSR_F_BIT)\n"
+	"stmia	r0!, {r2, r8 - r14}\n"
+	"mrs	r2, spsr\n"
+	"stmia	r0!, {r2}\n"
+	"msr	cpsr_c, r1\n"
+	"bx	lr\n");
+}
+
+
+void fiq_debugger_dump_allregs(struct fiq_debugger_output *output,
+		const struct pt_regs *regs)
+{
+	struct mode_regs mode_regs;
+	unsigned long mode = regs->ARM_cpsr & MODE_MASK;
+
+	fiq_debugger_dump_regs(output, regs);
+	get_mode_regs(&mode_regs);
+
+	output->printf(output,
+			"%csvc: sp %08x  lr %08x  spsr %08x\n",
+			mode == SVC_MODE ? '*' : ' ',
+			mode_regs.sp_svc, mode_regs.lr_svc, mode_regs.spsr_svc);
+	output->printf(output,
+			"%cabt: sp %08x  lr %08x  spsr %08x\n",
+			mode == ABT_MODE ? '*' : ' ',
+			mode_regs.sp_abt, mode_regs.lr_abt, mode_regs.spsr_abt);
+	output->printf(output,
+			"%cund: sp %08x  lr %08x  spsr %08x\n",
+			mode == UND_MODE ? '*' : ' ',
+			mode_regs.sp_und, mode_regs.lr_und, mode_regs.spsr_und);
+	output->printf(output,
+			"%cirq: sp %08x  lr %08x  spsr %08x\n",
+			mode == IRQ_MODE ? '*' : ' ',
+			mode_regs.sp_irq, mode_regs.lr_irq, mode_regs.spsr_irq);
+	output->printf(output,
+			"%cfiq: r8 %08x  r9 %08x  r10 %08x  r11 %08x  r12 %08x\n",
+			mode == FIQ_MODE ? '*' : ' ',
+			mode_regs.r8_fiq, mode_regs.r9_fiq, mode_regs.r10_fiq,
+			mode_regs.r11_fiq, mode_regs.r12_fiq);
+	output->printf(output,
+			" fiq: sp %08x  lr %08x  spsr %08x\n",
+			mode_regs.sp_fiq, mode_regs.lr_fiq, mode_regs.spsr_fiq);
+}
+
+struct stacktrace_state {
+	struct fiq_debugger_output *output;
+	unsigned int depth;
+};
+
+static int report_trace(struct stackframe *frame, void *d)
+{
+	struct stacktrace_state *sts = d;
+
+	if (sts->depth) {
+		sts->output->printf(sts->output,
+			"  pc: %p (%pF), lr %p (%pF), sp %p, fp %p\n",
+			frame->pc, frame->pc, frame->lr, frame->lr,
+			frame->sp, frame->fp);
+		sts->depth--;
+		return 0;
+	}
+	sts->output->printf(sts->output, "  ...\n");
+
+	return sts->depth == 0;
+}
+
+struct frame_tail {
+	struct frame_tail *fp;
+	unsigned long sp;
+	unsigned long lr;
+} __attribute__((packed));
+
+static struct frame_tail *user_backtrace(struct fiq_debugger_output *output,
+					struct frame_tail *tail)
+{
+	struct frame_tail buftail[2];
+
+	/* Also check accessibility of one struct frame_tail beyond */
+	if (!access_ok(VERIFY_READ, tail, sizeof(buftail))) {
+		output->printf(output, "  invalid frame pointer %p\n",
+				tail);
+		return NULL;
+	}
+	if (__copy_from_user_inatomic(buftail, tail, sizeof(buftail))) {
+		output->printf(output,
+			"  failed to copy frame pointer %p\n", tail);
+		return NULL;
+	}
+
+	output->printf(output, "  %p\n", buftail[0].lr);
+
+	/* frame pointers should strictly progress back up the stack
+	 * (towards higher addresses) */
+	if (tail >= buftail[0].fp)
+		return NULL;
+
+	return buftail[0].fp-1;
+}
+
+void fiq_debugger_dump_stacktrace(struct fiq_debugger_output *output,
+		const struct pt_regs *regs, unsigned int depth, void *ssp)
+{
+	struct frame_tail *tail;
+	struct thread_info *real_thread_info = THREAD_INFO(ssp);
+	struct stacktrace_state sts;
+
+	sts.depth = depth;
+	sts.output = output;
+	*current_thread_info() = *real_thread_info;
+
+	if (!current)
+		output->printf(output, "current NULL\n");
+	else
+		output->printf(output, "pid: %d  comm: %s\n",
+			current->pid, current->comm);
+	fiq_debugger_dump_regs(output, regs);
+
+	if (!user_mode(regs)) {
+		struct stackframe frame;
+		frame.fp = regs->ARM_fp;
+		frame.sp = regs->ARM_sp;
+		frame.lr = regs->ARM_lr;
+		frame.pc = regs->ARM_pc;
+		output->printf(output,
+			"  pc: %p (%pF), lr %p (%pF), sp %p, fp %p\n",
+			regs->ARM_pc, regs->ARM_pc, regs->ARM_lr, regs->ARM_lr,
+			regs->ARM_sp, regs->ARM_fp);
+		walk_stackframe(&frame, report_trace, &sts);
+		return;
+	}
+
+	tail = ((struct frame_tail *) regs->ARM_fp) - 1;
+	while (depth-- && tail && !((unsigned long) tail & 3))
+		tail = user_backtrace(output, tail);
+}
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger_arm64.c b/drivers/staging/android/fiq_debugger/fiq_debugger_arm64.c
new file mode 100644
index 00000000000..99c6584fcfa
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger_arm64.c
@@ -0,0 +1,202 @@
+/*
+ * Copyright (C) 2014 Google, Inc.
+ * Author: Colin Cross <ccross@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/ptrace.h>
+#include <asm/stacktrace.h>
+
+#include "fiq_debugger_priv.h"
+
+static char *mode_name(const struct pt_regs *regs)
+{
+	if (compat_user_mode(regs)) {
+		return "USR";
+	} else {
+		switch (processor_mode(regs)) {
+		case PSR_MODE_EL0t: return "EL0t";
+		case PSR_MODE_EL1t: return "EL1t";
+		case PSR_MODE_EL1h: return "EL1h";
+		case PSR_MODE_EL2t: return "EL2t";
+		case PSR_MODE_EL2h: return "EL2h";
+		default: return "???";
+		}
+	}
+}
+
+void fiq_debugger_dump_pc(struct fiq_debugger_output *output,
+		const struct pt_regs *regs)
+{
+	output->printf(output, " pc %016lx cpsr %08lx mode %s\n",
+		regs->pc, regs->pstate, mode_name(regs));
+}
+
+void fiq_debugger_dump_regs_aarch32(struct fiq_debugger_output *output,
+		const struct pt_regs *regs)
+{
+	output->printf(output, " r0 %08x  r1 %08x  r2 %08x  r3 %08x\n",
+			regs->compat_usr(0), regs->compat_usr(1),
+			regs->compat_usr(2), regs->compat_usr(3));
+	output->printf(output, " r4 %08x  r5 %08x  r6 %08x  r7 %08x\n",
+			regs->compat_usr(4), regs->compat_usr(5),
+			regs->compat_usr(6), regs->compat_usr(7));
+	output->printf(output, " r8 %08x  r9 %08x r10 %08x r11 %08x\n",
+			regs->compat_usr(8), regs->compat_usr(9),
+			regs->compat_usr(10), regs->compat_usr(11));
+	output->printf(output, " ip %08x  sp %08x  lr %08x  pc %08x\n",
+			regs->compat_usr(12), regs->compat_sp,
+			regs->compat_lr, regs->pc);
+	output->printf(output, " cpsr %08x (%s)\n",
+			regs->pstate, mode_name(regs));
+}
+
+void fiq_debugger_dump_regs_aarch64(struct fiq_debugger_output *output,
+		const struct pt_regs *regs)
+{
+
+	output->printf(output, "  x0 %016lx   x1 %016lx\n",
+			regs->regs[0], regs->regs[1]);
+	output->printf(output, "  x2 %016lx   x3 %016lx\n",
+			regs->regs[2], regs->regs[3]);
+	output->printf(output, "  x4 %016lx   x5 %016lx\n",
+			regs->regs[4], regs->regs[5]);
+	output->printf(output, "  x6 %016lx   x7 %016lx\n",
+			regs->regs[6], regs->regs[7]);
+	output->printf(output, "  x8 %016lx   x9 %016lx\n",
+			regs->regs[8], regs->regs[9]);
+	output->printf(output, " x10 %016lx  x11 %016lx\n",
+			regs->regs[10], regs->regs[11]);
+	output->printf(output, " x12 %016lx  x13 %016lx\n",
+			regs->regs[12], regs->regs[13]);
+	output->printf(output, " x14 %016lx  x15 %016lx\n",
+			regs->regs[14], regs->regs[15]);
+	output->printf(output, " x16 %016lx  x17 %016lx\n",
+			regs->regs[16], regs->regs[17]);
+	output->printf(output, " x18 %016lx  x19 %016lx\n",
+			regs->regs[18], regs->regs[19]);
+	output->printf(output, " x20 %016lx  x21 %016lx\n",
+			regs->regs[20], regs->regs[21]);
+	output->printf(output, " x22 %016lx  x23 %016lx\n",
+			regs->regs[22], regs->regs[23]);
+	output->printf(output, " x24 %016lx  x25 %016lx\n",
+			regs->regs[24], regs->regs[25]);
+	output->printf(output, " x26 %016lx  x27 %016lx\n",
+			regs->regs[26], regs->regs[27]);
+	output->printf(output, " x28 %016lx  x29 %016lx\n",
+			regs->regs[28], regs->regs[29]);
+	output->printf(output, " x30 %016lx   sp %016lx\n",
+			regs->regs[30], regs->sp);
+	output->printf(output, "  pc %016lx cpsr %08x (%s)\n",
+			regs->pc, regs->pstate, mode_name(regs));
+}
+
+void fiq_debugger_dump_regs(struct fiq_debugger_output *output,
+		const struct pt_regs *regs)
+{
+	if (compat_user_mode(regs))
+		fiq_debugger_dump_regs_aarch32(output, regs);
+	else
+		fiq_debugger_dump_regs_aarch64(output, regs);
+}
+
+#define READ_SPECIAL_REG(x) ({ \
+	u64 val; \
+	asm volatile ("mrs %0, " # x : "=r"(val)); \
+	val; \
+})
+
+void fiq_debugger_dump_allregs(struct fiq_debugger_output *output,
+		const struct pt_regs *regs)
+{
+	u32 pstate = READ_SPECIAL_REG(CurrentEl);
+	bool in_el2 = (pstate & PSR_MODE_MASK) >= PSR_MODE_EL2t;
+
+	fiq_debugger_dump_regs(output, regs);
+
+	output->printf(output, " sp_el0   %016lx\n",
+			READ_SPECIAL_REG(sp_el0));
+
+	if (in_el2)
+		output->printf(output, " sp_el1   %016lx\n",
+				READ_SPECIAL_REG(sp_el1));
+
+	output->printf(output, " elr_el1  %016lx\n",
+			READ_SPECIAL_REG(elr_el1));
+
+	output->printf(output, " spsr_el1 %08lx\n",
+			READ_SPECIAL_REG(spsr_el1));
+
+	if (in_el2) {
+		output->printf(output, " spsr_irq %08lx\n",
+				READ_SPECIAL_REG(spsr_irq));
+		output->printf(output, " spsr_abt %08lx\n",
+				READ_SPECIAL_REG(spsr_abt));
+		output->printf(output, " spsr_und %08lx\n",
+				READ_SPECIAL_REG(spsr_und));
+		output->printf(output, " spsr_fiq %08lx\n",
+				READ_SPECIAL_REG(spsr_fiq));
+		output->printf(output, " spsr_el2 %08lx\n",
+				READ_SPECIAL_REG(elr_el2));
+		output->printf(output, " spsr_el2 %08lx\n",
+				READ_SPECIAL_REG(spsr_el2));
+	}
+}
+
+struct stacktrace_state {
+	struct fiq_debugger_output *output;
+	unsigned int depth;
+};
+
+static int report_trace(struct stackframe *frame, void *d)
+{
+	struct stacktrace_state *sts = d;
+
+	if (sts->depth) {
+		sts->output->printf(sts->output, "%pF:\n", frame->pc);
+		sts->output->printf(sts->output,
+				"  pc %016lx   sp %016lx   fp %016lx\n",
+				frame->pc, frame->sp, frame->fp);
+		sts->depth--;
+		return 0;
+	}
+	sts->output->printf(sts->output, "  ...\n");
+
+	return sts->depth == 0;
+}
+
+void fiq_debugger_dump_stacktrace(struct fiq_debugger_output *output,
+		const struct pt_regs *regs, unsigned int depth, void *ssp)
+{
+	struct thread_info *real_thread_info = THREAD_INFO(ssp);
+	struct stacktrace_state sts;
+
+	sts.depth = depth;
+	sts.output = output;
+	*current_thread_info() = *real_thread_info;
+
+	if (!current)
+		output->printf(output, "current NULL\n");
+	else
+		output->printf(output, "pid: %d  comm: %s\n",
+			current->pid, current->comm);
+	fiq_debugger_dump_regs(output, regs);
+
+	if (!user_mode(regs)) {
+		struct stackframe frame;
+		frame.fp = regs->regs[29];
+		frame.sp = regs->sp;
+		frame.pc = regs->pc;
+		output->printf(output, "\n");
+		walk_stackframe(&frame, report_trace, &sts);
+	}
+}
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger_priv.h b/drivers/staging/android/fiq_debugger/fiq_debugger_priv.h
new file mode 100644
index 00000000000..d5d051f727a
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger_priv.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2014 Google, Inc.
+ * Author: Colin Cross <ccross@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _FIQ_DEBUGGER_PRIV_H_
+#define _FIQ_DEBUGGER_PRIV_H_
+
+#define THREAD_INFO(sp) ((struct thread_info *) \
+		((unsigned long)(sp) & ~(THREAD_SIZE - 1)))
+
+struct fiq_debugger_output {
+	void (*printf)(struct fiq_debugger_output *output, const char *fmt, ...);
+};
+
+struct pt_regs;
+
+void fiq_debugger_dump_pc(struct fiq_debugger_output *output,
+		const struct pt_regs *regs);
+void fiq_debugger_dump_regs(struct fiq_debugger_output *output,
+		const struct pt_regs *regs);
+void fiq_debugger_dump_allregs(struct fiq_debugger_output *output,
+		const struct pt_regs *regs);
+void fiq_debugger_dump_stacktrace(struct fiq_debugger_output *output,
+		const struct pt_regs *regs, unsigned int depth, void *ssp);
+
+#endif
diff --git a/drivers/staging/android/fiq_debugger/fiq_debugger_ringbuf.h b/drivers/staging/android/fiq_debugger/fiq_debugger_ringbuf.h
new file mode 100644
index 00000000000..10c3c5d0909
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_debugger_ringbuf.h
@@ -0,0 +1,94 @@
+/*
+ * drivers/staging/android/fiq_debugger/fiq_debugger_ringbuf.h
+ *
+ * simple lockless ringbuffer
+ *
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+struct fiq_debugger_ringbuf {
+	int len;
+	int head;
+	int tail;
+	u8 buf[];
+};
+
+
+static inline struct fiq_debugger_ringbuf *fiq_debugger_ringbuf_alloc(int len)
+{
+	struct fiq_debugger_ringbuf *rbuf;
+
+	rbuf = kzalloc(sizeof(*rbuf) + len, GFP_KERNEL);
+	if (rbuf == NULL)
+		return NULL;
+
+	rbuf->len = len;
+	rbuf->head = 0;
+	rbuf->tail = 0;
+	smp_mb();
+
+	return rbuf;
+}
+
+static inline void fiq_debugger_ringbuf_free(struct fiq_debugger_ringbuf *rbuf)
+{
+	kfree(rbuf);
+}
+
+static inline int fiq_debugger_ringbuf_level(struct fiq_debugger_ringbuf *rbuf)
+{
+	int level = rbuf->head - rbuf->tail;
+
+	if (level < 0)
+		level = rbuf->len + level;
+
+	return level;
+}
+
+static inline int fiq_debugger_ringbuf_room(struct fiq_debugger_ringbuf *rbuf)
+{
+	return rbuf->len - fiq_debugger_ringbuf_level(rbuf) - 1;
+}
+
+static inline u8
+fiq_debugger_ringbuf_peek(struct fiq_debugger_ringbuf *rbuf, int i)
+{
+	return rbuf->buf[(rbuf->tail + i) % rbuf->len];
+}
+
+static inline int
+fiq_debugger_ringbuf_consume(struct fiq_debugger_ringbuf *rbuf, int count)
+{
+	count = min(count, fiq_debugger_ringbuf_level(rbuf));
+
+	rbuf->tail = (rbuf->tail + count) % rbuf->len;
+	smp_mb();
+
+	return count;
+}
+
+static inline int
+fiq_debugger_ringbuf_push(struct fiq_debugger_ringbuf *rbuf, u8 datum)
+{
+	if (fiq_debugger_ringbuf_room(rbuf) == 0)
+		return 0;
+
+	rbuf->buf[rbuf->head] = datum;
+	smp_mb();
+	rbuf->head = (rbuf->head + 1) % rbuf->len;
+	smp_mb();
+
+	return 1;
+}
diff --git a/drivers/staging/android/fiq_debugger/fiq_watchdog.c b/drivers/staging/android/fiq_debugger/fiq_watchdog.c
new file mode 100644
index 00000000000..194b5413841
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_watchdog.c
@@ -0,0 +1,56 @@
+/*
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/pstore_ram.h>
+
+#include "fiq_watchdog.h"
+#include "fiq_debugger_priv.h"
+
+static DEFINE_RAW_SPINLOCK(fiq_watchdog_lock);
+
+static void fiq_watchdog_printf(struct fiq_debugger_output *output,
+				const char *fmt, ...)
+{
+	char buf[256];
+	va_list ap;
+	int len;
+
+	va_start(ap, fmt);
+	len = vscnprintf(buf, sizeof(buf), fmt, ap);
+	va_end(ap);
+
+	ramoops_console_write_buf(buf, len);
+}
+
+struct fiq_debugger_output fiq_watchdog_output = {
+	.printf = fiq_watchdog_printf,
+};
+
+void fiq_watchdog_triggered(const struct pt_regs *regs, void *svc_sp)
+{
+	char msg[24];
+	int len;
+
+	raw_spin_lock(&fiq_watchdog_lock);
+
+	len = scnprintf(msg, sizeof(msg), "watchdog fiq cpu %d\n",
+			THREAD_INFO(svc_sp)->cpu);
+	ramoops_console_write_buf(msg, len);
+
+	fiq_debugger_dump_stacktrace(&fiq_watchdog_output, regs, 100, svc_sp);
+
+	raw_spin_unlock(&fiq_watchdog_lock);
+}
diff --git a/drivers/staging/android/fiq_debugger/fiq_watchdog.h b/drivers/staging/android/fiq_debugger/fiq_watchdog.h
new file mode 100644
index 00000000000..c6b507f8d97
--- /dev/null
+++ b/drivers/staging/android/fiq_debugger/fiq_watchdog.h
@@ -0,0 +1,20 @@
+/*
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _FIQ_WATCHDOG_H_
+#define _FIQ_WATCHDOG_H_
+
+void fiq_watchdog_triggered(const struct pt_regs *regs, void *svc_sp);
+
+#endif
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index 56604f41ec4..38352595254 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -250,10 +250,12 @@ static struct ion_buffer *ion_buffer_create(struct ion_heap *heap,
 	   our systems the only dma_address space is physical addresses.
 	   Additionally, we can't afford the overhead of invalidating every
 	   allocation via dma_map_sg. The implicit contract here is that
-	   memory comming from the heaps is ready for dma, ie if it has a
+	   memory coming from the heaps is ready for dma, ie if it has a
 	   cached mapping that mapping has been invalidated */
-	for_each_sg(buffer->sg_table->sgl, sg, buffer->sg_table->nents, i)
+	for_each_sg(buffer->sg_table->sgl, sg, buffer->sg_table->nents, i) {
 		sg_dma_address(sg) = sg_phys(sg);
+		sg_dma_len(sg) = sg->length;
+	}
 	mutex_lock(&dev->buffer_lock);
 	ion_buffer_add(dev, buffer);
 	mutex_unlock(&dev->buffer_lock);
@@ -902,7 +904,7 @@ void ion_pages_sync_for_device(struct device *dev, struct page *page,
 	sg_set_page(&sg, page, size, 0);
 	/*
 	 * This is not correct - sg_dma_address needs a dma_addr_t that is valid
-	 * for the the targeted device, but this works on the currently targeted
+	 * for the targeted device, but this works on the currently targeted
 	 * hardware.
 	 */
 	sg_dma_address(&sg) = page_to_phys(page);
diff --git a/drivers/staging/android/ion/ion.h b/drivers/staging/android/ion/ion.h
index d305bb7e9a7..443db8459a9 100644
--- a/drivers/staging/android/ion/ion.h
+++ b/drivers/staging/android/ion/ion.h
@@ -76,7 +76,7 @@ struct ion_platform_data {
  *		size
  *
  * Calls memblock reserve to set aside memory for heaps that are
- * located at specific memory addresses or of specfic sizes not
+ * located at specific memory addresses or of specific sizes not
  * managed by the kernel
  */
 void ion_reserve(struct ion_platform_data *data);
diff --git a/drivers/staging/android/ion/ion_carveout_heap.c b/drivers/staging/android/ion/ion_carveout_heap.c
index 9156d8238c9..e702ce6461f 100644..100755
--- a/drivers/staging/android/ion/ion_carveout_heap.c
+++ b/drivers/staging/android/ion/ion_carveout_heap.c
@@ -167,7 +167,7 @@ struct ion_heap *ion_carveout_heap_create(struct ion_platform_heap *heap_data)
 	if (!carveout_heap)
 		return ERR_PTR(-ENOMEM);
 
-	carveout_heap->pool = gen_pool_create(12, -1);
+	carveout_heap->pool = gen_pool_create(PAGE_SHIFT, -1);
 	if (!carveout_heap->pool) {
 		kfree(carveout_heap);
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/staging/android/ion/ion_cma_heap.c b/drivers/staging/android/ion/ion_cma_heap.c
index f8cabcbc39e..86b91fd5385 100644
--- a/drivers/staging/android/ion/ion_cma_heap.c
+++ b/drivers/staging/android/ion/ion_cma_heap.c
@@ -39,24 +39,6 @@ struct ion_cma_buffer_info {
 	struct sg_table *table;
 };
 
-/*
- * Create scatter-list for the already allocated DMA buffer.
- * This function could be replaced by dma_common_get_sgtable
- * as soon as it will avalaible.
- */
-static int ion_cma_get_sgtable(struct device *dev, struct sg_table *sgt,
-			       void *cpu_addr, dma_addr_t handle, size_t size)
-{
-	struct page *page = virt_to_page(cpu_addr);
-	int ret;
-
-	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
-	if (unlikely(ret))
-		return ret;
-
-	sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
-	return 0;
-}
 
 /* ION CMA heap operations functions */
 static int ion_cma_allocate(struct ion_heap *heap, struct ion_buffer *buffer,
@@ -91,8 +73,7 @@ static int ion_cma_allocate(struct ion_heap *heap, struct ion_buffer *buffer,
 	if (!info->table)
 		goto free_mem;
 
-	if (ion_cma_get_sgtable
-	    (dev, info->table, info->cpu_addr, info->handle, len))
+	if (dma_get_sgtable(dev, info->table, info->cpu_addr, info->handle, len))
 		goto free_table;
 	/* keep this for memory release */
 	buffer->priv_virt = info;
diff --git a/drivers/staging/android/ion/ion_page_pool.c b/drivers/staging/android/ion/ion_page_pool.c
index 5864f3dfcbc..4b88f11e52d 100644
--- a/drivers/staging/android/ion/ion_page_pool.c
+++ b/drivers/staging/android/ion/ion_page_pool.c
@@ -120,7 +120,7 @@ int ion_page_pool_shrink(struct ion_page_pool *pool, gfp_t gfp_mask,
 	bool high;
 
 	if (current_is_kswapd())
-		high = 1;
+		high = true;
 	else
 		high = !!(gfp_mask & __GFP_HIGHMEM);
 
diff --git a/drivers/staging/android/ion/ion_priv.h b/drivers/staging/android/ion/ion_priv.h
index c8f01757abf..18a5f93e13b 100644
--- a/drivers/staging/android/ion/ion_priv.h
+++ b/drivers/staging/android/ion/ion_priv.h
@@ -345,7 +345,7 @@ void ion_carveout_free(struct ion_heap *heap, ion_phys_addr_t addr,
  * functions for creating and destroying a heap pool -- allows you
  * to keep a pool of pre allocated memory to use from your heap.  Keeping
  * a pool of memory that is ready for dma, ie any cached mapping have been
- * invalidated from the cache, provides a significant peformance benefit on
+ * invalidated from the cache, provides a significant performance benefit on
  * many systems */
 
 /**
@@ -362,7 +362,7 @@ void ion_carveout_free(struct ion_heap *heap, ion_phys_addr_t addr,
  *
  * Allows you to keep a pool of pre allocated pages to use from your heap.
  * Keeping a pool of pages that is ready for dma, ie any cached mapping have
- * been invalidated from the cache, provides a significant peformance benefit
+ * been invalidated from the cache, provides a significant performance benefit
  * on many systems
  */
 struct ion_page_pool {
diff --git a/drivers/staging/android/logger.c b/drivers/staging/android/logger.c
deleted file mode 100644
index a673ffa34aa..00000000000
--- a/drivers/staging/android/logger.c
+++ /dev/null
@@ -1,808 +0,0 @@
-/*
- * drivers/misc/logger.c
- *
- * A Logging Subsystem
- *
- * Copyright (C) 2007-2008 Google, Inc.
- *
- * Robert Love <rlove@google.com>
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#define pr_fmt(fmt) "logger: " fmt
-
-#include <linux/sched.h>
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/miscdevice.h>
-#include <linux/uaccess.h>
-#include <linux/poll.h>
-#include <linux/slab.h>
-#include <linux/time.h>
-#include <linux/vmalloc.h>
-#include <linux/aio.h>
-#include "logger.h"
-
-#include <asm/ioctls.h>
-
-/**
- * struct logger_log - represents a specific log, such as 'main' or 'radio'
- * @buffer:	The actual ring buffer
- * @misc:	The "misc" device representing the log
- * @wq:		The wait queue for @readers
- * @readers:	This log's readers
- * @mutex:	The mutex that protects the @buffer
- * @w_off:	The current write head offset
- * @head:	The head, or location that readers start reading at.
- * @size:	The size of the log
- * @logs:	The list of log channels
- *
- * This structure lives from module insertion until module removal, so it does
- * not need additional reference counting. The structure is protected by the
- * mutex 'mutex'.
- */
-struct logger_log {
-	unsigned char		*buffer;
-	struct miscdevice	misc;
-	wait_queue_head_t	wq;
-	struct list_head	readers;
-	struct mutex		mutex;
-	size_t			w_off;
-	size_t			head;
-	size_t			size;
-	struct list_head	logs;
-};
-
-static LIST_HEAD(log_list);
-
-
-/**
- * struct logger_reader - a logging device open for reading
- * @log:	The associated log
- * @list:	The associated entry in @logger_log's list
- * @r_off:	The current read head offset.
- * @r_all:	Reader can read all entries
- * @r_ver:	Reader ABI version
- *
- * This object lives from open to release, so we don't need additional
- * reference counting. The structure is protected by log->mutex.
- */
-struct logger_reader {
-	struct logger_log	*log;
-	struct list_head	list;
-	size_t			r_off;
-	bool			r_all;
-	int			r_ver;
-};
-
-/* logger_offset - returns index 'n' into the log via (optimized) modulus */
-static size_t logger_offset(struct logger_log *log, size_t n)
-{
-	return n & (log->size - 1);
-}
-
-
-/*
- * file_get_log - Given a file structure, return the associated log
- *
- * This isn't aesthetic. We have several goals:
- *
- *	1) Need to quickly obtain the associated log during an I/O operation
- *	2) Readers need to maintain state (logger_reader)
- *	3) Writers need to be very fast (open() should be a near no-op)
- *
- * In the reader case, we can trivially go file->logger_reader->logger_log.
- * For a writer, we don't want to maintain a logger_reader, so we just go
- * file->logger_log. Thus what file->private_data points at depends on whether
- * or not the file was opened for reading. This function hides that dirtiness.
- */
-static inline struct logger_log *file_get_log(struct file *file)
-{
-	if (file->f_mode & FMODE_READ) {
-		struct logger_reader *reader = file->private_data;
-
-		return reader->log;
-	}
-	return file->private_data;
-}
-
-/*
- * get_entry_header - returns a pointer to the logger_entry header within
- * 'log' starting at offset 'off'. A temporary logger_entry 'scratch' must
- * be provided. Typically the return value will be a pointer within
- * 'logger->buf'.  However, a pointer to 'scratch' may be returned if
- * the log entry spans the end and beginning of the circular buffer.
- */
-static struct logger_entry *get_entry_header(struct logger_log *log,
-		size_t off, struct logger_entry *scratch)
-{
-	size_t len = min(sizeof(struct logger_entry), log->size - off);
-
-	if (len != sizeof(struct logger_entry)) {
-		memcpy(((void *) scratch), log->buffer + off, len);
-		memcpy(((void *) scratch) + len, log->buffer,
-			sizeof(struct logger_entry) - len);
-		return scratch;
-	}
-
-	return (struct logger_entry *) (log->buffer + off);
-}
-
-/*
- * get_entry_msg_len - Grabs the length of the message of the entry
- * starting from from 'off'.
- *
- * An entry length is 2 bytes (16 bits) in host endian order.
- * In the log, the length does not include the size of the log entry structure.
- * This function returns the size including the log entry structure.
- *
- * Caller needs to hold log->mutex.
- */
-static __u32 get_entry_msg_len(struct logger_log *log, size_t off)
-{
-	struct logger_entry scratch;
-	struct logger_entry *entry;
-
-	entry = get_entry_header(log, off, &scratch);
-	return entry->len;
-}
-
-static size_t get_user_hdr_len(int ver)
-{
-	if (ver < 2)
-		return sizeof(struct user_logger_entry_compat);
-	return sizeof(struct logger_entry);
-}
-
-static ssize_t copy_header_to_user(int ver, struct logger_entry *entry,
-					 char __user *buf)
-{
-	void *hdr;
-	size_t hdr_len;
-	struct user_logger_entry_compat v1;
-
-	if (ver < 2) {
-		v1.len      = entry->len;
-		v1.__pad    = 0;
-		v1.pid      = entry->pid;
-		v1.tid      = entry->tid;
-		v1.sec      = entry->sec;
-		v1.nsec     = entry->nsec;
-		hdr         = &v1;
-		hdr_len     = sizeof(struct user_logger_entry_compat);
-	} else {
-		hdr         = entry;
-		hdr_len     = sizeof(struct logger_entry);
-	}
-
-	return copy_to_user(buf, hdr, hdr_len);
-}
-
-/*
- * do_read_log_to_user - reads exactly 'count' bytes from 'log' into the
- * user-space buffer 'buf'. Returns 'count' on success.
- *
- * Caller must hold log->mutex.
- */
-static ssize_t do_read_log_to_user(struct logger_log *log,
-				   struct logger_reader *reader,
-				   char __user *buf,
-				   size_t count)
-{
-	struct logger_entry scratch;
-	struct logger_entry *entry;
-	size_t len;
-	size_t msg_start;
-
-	/*
-	 * First, copy the header to userspace, using the version of
-	 * the header requested
-	 */
-	entry = get_entry_header(log, reader->r_off, &scratch);
-	if (copy_header_to_user(reader->r_ver, entry, buf))
-		return -EFAULT;
-
-	count -= get_user_hdr_len(reader->r_ver);
-	buf += get_user_hdr_len(reader->r_ver);
-	msg_start = logger_offset(log,
-		reader->r_off + sizeof(struct logger_entry));
-
-	/*
-	 * We read from the msg in two disjoint operations. First, we read from
-	 * the current msg head offset up to 'count' bytes or to the end of
-	 * the log, whichever comes first.
-	 */
-	len = min(count, log->size - msg_start);
-	if (copy_to_user(buf, log->buffer + msg_start, len))
-		return -EFAULT;
-
-	/*
-	 * Second, we read any remaining bytes, starting back at the head of
-	 * the log.
-	 */
-	if (count != len)
-		if (copy_to_user(buf + len, log->buffer, count - len))
-			return -EFAULT;
-
-	reader->r_off = logger_offset(log, reader->r_off +
-		sizeof(struct logger_entry) + count);
-
-	return count + get_user_hdr_len(reader->r_ver);
-}
-
-/*
- * get_next_entry_by_uid - Starting at 'off', returns an offset into
- * 'log->buffer' which contains the first entry readable by 'euid'
- */
-static size_t get_next_entry_by_uid(struct logger_log *log,
-		size_t off, kuid_t euid)
-{
-	while (off != log->w_off) {
-		struct logger_entry *entry;
-		struct logger_entry scratch;
-		size_t next_len;
-
-		entry = get_entry_header(log, off, &scratch);
-
-		if (uid_eq(entry->euid, euid))
-			return off;
-
-		next_len = sizeof(struct logger_entry) + entry->len;
-		off = logger_offset(log, off + next_len);
-	}
-
-	return off;
-}
-
-/*
- * logger_read - our log's read() method
- *
- * Behavior:
- *
- *	- O_NONBLOCK works
- *	- If there are no log entries to read, blocks until log is written to
- *	- Atomically reads exactly one log entry
- *
- * Will set errno to EINVAL if read
- * buffer is insufficient to hold next entry.
- */
-static ssize_t logger_read(struct file *file, char __user *buf,
-			   size_t count, loff_t *pos)
-{
-	struct logger_reader *reader = file->private_data;
-	struct logger_log *log = reader->log;
-	ssize_t ret;
-	DEFINE_WAIT(wait);
-
-start:
-	while (1) {
-		mutex_lock(&log->mutex);
-
-		prepare_to_wait(&log->wq, &wait, TASK_INTERRUPTIBLE);
-
-		ret = (log->w_off == reader->r_off);
-		mutex_unlock(&log->mutex);
-		if (!ret)
-			break;
-
-		if (file->f_flags & O_NONBLOCK) {
-			ret = -EAGAIN;
-			break;
-		}
-
-		if (signal_pending(current)) {
-			ret = -EINTR;
-			break;
-		}
-
-		schedule();
-	}
-
-	finish_wait(&log->wq, &wait);
-	if (ret)
-		return ret;
-
-	mutex_lock(&log->mutex);
-
-	if (!reader->r_all)
-		reader->r_off = get_next_entry_by_uid(log,
-			reader->r_off, current_euid());
-
-	/* is there still something to read or did we race? */
-	if (unlikely(log->w_off == reader->r_off)) {
-		mutex_unlock(&log->mutex);
-		goto start;
-	}
-
-	/* get the size of the next entry */
-	ret = get_user_hdr_len(reader->r_ver) +
-		get_entry_msg_len(log, reader->r_off);
-	if (count < ret) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	/* get exactly one entry from the log */
-	ret = do_read_log_to_user(log, reader, buf, ret);
-
-out:
-	mutex_unlock(&log->mutex);
-
-	return ret;
-}
-
-/*
- * get_next_entry - return the offset of the first valid entry at least 'len'
- * bytes after 'off'.
- *
- * Caller must hold log->mutex.
- */
-static size_t get_next_entry(struct logger_log *log, size_t off, size_t len)
-{
-	size_t count = 0;
-
-	do {
-		size_t nr = sizeof(struct logger_entry) +
-			get_entry_msg_len(log, off);
-		off = logger_offset(log, off + nr);
-		count += nr;
-	} while (count < len);
-
-	return off;
-}
-
-/*
- * is_between - is a < c < b, accounting for wrapping of a, b, and c
- *    positions in the buffer
- *
- * That is, if a<b, check for c between a and b
- * and if a>b, check for c outside (not between) a and b
- *
- * |------- a xxxxxxxx b --------|
- *               c^
- *
- * |xxxxx b --------- a xxxxxxxxx|
- *    c^
- *  or                    c^
- */
-static inline int is_between(size_t a, size_t b, size_t c)
-{
-	if (a < b) {
-		/* is c between a and b? */
-		if (a < c && c <= b)
-			return 1;
-	} else {
-		/* is c outside of b through a? */
-		if (c <= b || a < c)
-			return 1;
-	}
-
-	return 0;
-}
-
-/*
- * fix_up_readers - walk the list of all readers and "fix up" any who were
- * lapped by the writer; also do the same for the default "start head".
- * We do this by "pulling forward" the readers and start head to the first
- * entry after the new write head.
- *
- * The caller needs to hold log->mutex.
- */
-static void fix_up_readers(struct logger_log *log, size_t len)
-{
-	size_t old = log->w_off;
-	size_t new = logger_offset(log, old + len);
-	struct logger_reader *reader;
-
-	if (is_between(old, new, log->head))
-		log->head = get_next_entry(log, log->head, len);
-
-	list_for_each_entry(reader, &log->readers, list)
-		if (is_between(old, new, reader->r_off))
-			reader->r_off = get_next_entry(log, reader->r_off, len);
-}
-
-/*
- * logger_write_iter - our write method, implementing support for write(),
- * writev(), and aio_write(). Writes are our fast path, and we try to optimize
- * them above all else.
- */
-static ssize_t logger_write_iter(struct kiocb *iocb, struct iov_iter *from)
-{
-	struct logger_log *log = file_get_log(iocb->ki_filp);
-	struct logger_entry header;
-	struct timespec now;
-	size_t len, count, w_off;
-
-	count = min_t(size_t, iocb->ki_nbytes, LOGGER_ENTRY_MAX_PAYLOAD);
-
-	now = current_kernel_time();
-
-	header.pid = current->tgid;
-	header.tid = current->pid;
-	header.sec = now.tv_sec;
-	header.nsec = now.tv_nsec;
-	header.euid = current_euid();
-	header.len = count;
-	header.hdr_size = sizeof(struct logger_entry);
-
-	/* null writes succeed, return zero */
-	if (unlikely(!header.len))
-		return 0;
-
-	mutex_lock(&log->mutex);
-
-	/*
-	 * Fix up any readers, pulling them forward to the first readable
-	 * entry after (what will be) the new write offset. We do this now
-	 * because if we partially fail, we can end up with clobbered log
-	 * entries that encroach on readable buffer.
-	 */
-	fix_up_readers(log, sizeof(struct logger_entry) + header.len);
-
-	len = min(sizeof(header), log->size - log->w_off);
-	memcpy(log->buffer + log->w_off, &header, len);
-	memcpy(log->buffer, (char *)&header + len, sizeof(header) - len);
-
-	/* Work with a copy until we are ready to commit the whole entry */
-	w_off =  logger_offset(log, log->w_off + sizeof(struct logger_entry));
-
-	len = min(count, log->size - w_off);
-
-	if (copy_from_iter(log->buffer + w_off, len, from) != len) {
-		/*
-		 * Note that by not updating log->w_off, this abandons the
-		 * portion of the new entry that *was* successfully
-		 * copied, just above.  This is intentional to avoid
-		 * message corruption from missing fragments.
-		 */
-		mutex_unlock(&log->mutex);
-		return -EFAULT;
-	}
-
-	if (copy_from_iter(log->buffer, count - len, from) != count - len) {
-		mutex_unlock(&log->mutex);
-		return -EFAULT;
-	}
-
-	log->w_off = logger_offset(log, w_off + count);
-	mutex_unlock(&log->mutex);
-
-	/* wake up any blocked readers */
-	wake_up_interruptible(&log->wq);
-
-	return len;
-}
-
-static struct logger_log *get_log_from_minor(int minor)
-{
-	struct logger_log *log;
-
-	list_for_each_entry(log, &log_list, logs)
-		if (log->misc.minor == minor)
-			return log;
-	return NULL;
-}
-
-/*
- * logger_open - the log's open() file operation
- *
- * Note how near a no-op this is in the write-only case. Keep it that way!
- */
-static int logger_open(struct inode *inode, struct file *file)
-{
-	struct logger_log *log;
-	int ret;
-
-	ret = nonseekable_open(inode, file);
-	if (ret)
-		return ret;
-
-	log = get_log_from_minor(MINOR(inode->i_rdev));
-	if (!log)
-		return -ENODEV;
-
-	if (file->f_mode & FMODE_READ) {
-		struct logger_reader *reader;
-
-		reader = kmalloc(sizeof(struct logger_reader), GFP_KERNEL);
-		if (!reader)
-			return -ENOMEM;
-
-		reader->log = log;
-		reader->r_ver = 1;
-		reader->r_all = in_egroup_p(inode->i_gid) ||
-			capable(CAP_SYSLOG);
-
-		INIT_LIST_HEAD(&reader->list);
-
-		mutex_lock(&log->mutex);
-		reader->r_off = log->head;
-		list_add_tail(&reader->list, &log->readers);
-		mutex_unlock(&log->mutex);
-
-		file->private_data = reader;
-	} else
-		file->private_data = log;
-
-	return 0;
-}
-
-/*
- * logger_release - the log's release file operation
- *
- * Note this is a total no-op in the write-only case. Keep it that way!
- */
-static int logger_release(struct inode *ignored, struct file *file)
-{
-	if (file->f_mode & FMODE_READ) {
-		struct logger_reader *reader = file->private_data;
-		struct logger_log *log = reader->log;
-
-		mutex_lock(&log->mutex);
-		list_del(&reader->list);
-		mutex_unlock(&log->mutex);
-
-		kfree(reader);
-	}
-
-	return 0;
-}
-
-/*
- * logger_poll - the log's poll file operation, for poll/select/epoll
- *
- * Note we always return POLLOUT, because you can always write() to the log.
- * Note also that, strictly speaking, a return value of POLLIN does not
- * guarantee that the log is readable without blocking, as there is a small
- * chance that the writer can lap the reader in the interim between poll()
- * returning and the read() request.
- */
-static unsigned int logger_poll(struct file *file, poll_table *wait)
-{
-	struct logger_reader *reader;
-	struct logger_log *log;
-	unsigned int ret = POLLOUT | POLLWRNORM;
-
-	if (!(file->f_mode & FMODE_READ))
-		return ret;
-
-	reader = file->private_data;
-	log = reader->log;
-
-	poll_wait(file, &log->wq, wait);
-
-	mutex_lock(&log->mutex);
-	if (!reader->r_all)
-		reader->r_off = get_next_entry_by_uid(log,
-			reader->r_off, current_euid());
-
-	if (log->w_off != reader->r_off)
-		ret |= POLLIN | POLLRDNORM;
-	mutex_unlock(&log->mutex);
-
-	return ret;
-}
-
-static long logger_set_version(struct logger_reader *reader, void __user *arg)
-{
-	int version;
-
-	if (copy_from_user(&version, arg, sizeof(int)))
-		return -EFAULT;
-
-	if ((version < 1) || (version > 2))
-		return -EINVAL;
-
-	reader->r_ver = version;
-	return 0;
-}
-
-static long logger_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
-	struct logger_log *log = file_get_log(file);
-	struct logger_reader *reader;
-	long ret = -EINVAL;
-	void __user *argp = (void __user *) arg;
-
-	mutex_lock(&log->mutex);
-
-	switch (cmd) {
-	case LOGGER_GET_LOG_BUF_SIZE:
-		ret = log->size;
-		break;
-	case LOGGER_GET_LOG_LEN:
-		if (!(file->f_mode & FMODE_READ)) {
-			ret = -EBADF;
-			break;
-		}
-		reader = file->private_data;
-		if (log->w_off >= reader->r_off)
-			ret = log->w_off - reader->r_off;
-		else
-			ret = (log->size - reader->r_off) + log->w_off;
-		break;
-	case LOGGER_GET_NEXT_ENTRY_LEN:
-		if (!(file->f_mode & FMODE_READ)) {
-			ret = -EBADF;
-			break;
-		}
-		reader = file->private_data;
-
-		if (!reader->r_all)
-			reader->r_off = get_next_entry_by_uid(log,
-				reader->r_off, current_euid());
-
-		if (log->w_off != reader->r_off)
-			ret = get_user_hdr_len(reader->r_ver) +
-				get_entry_msg_len(log, reader->r_off);
-		else
-			ret = 0;
-		break;
-	case LOGGER_FLUSH_LOG:
-		if (!(file->f_mode & FMODE_WRITE)) {
-			ret = -EBADF;
-			break;
-		}
-		if (!(in_egroup_p(file_inode(file)->i_gid) ||
-				capable(CAP_SYSLOG))) {
-			ret = -EPERM;
-			break;
-		}
-		list_for_each_entry(reader, &log->readers, list)
-			reader->r_off = log->w_off;
-		log->head = log->w_off;
-		ret = 0;
-		break;
-	case LOGGER_GET_VERSION:
-		if (!(file->f_mode & FMODE_READ)) {
-			ret = -EBADF;
-			break;
-		}
-		reader = file->private_data;
-		ret = reader->r_ver;
-		break;
-	case LOGGER_SET_VERSION:
-		if (!(file->f_mode & FMODE_READ)) {
-			ret = -EBADF;
-			break;
-		}
-		reader = file->private_data;
-		ret = logger_set_version(reader, argp);
-		break;
-	}
-
-	mutex_unlock(&log->mutex);
-
-	return ret;
-}
-
-static const struct file_operations logger_fops = {
-	.owner = THIS_MODULE,
-	.read = logger_read,
-	.write_iter = logger_write_iter,
-	.poll = logger_poll,
-	.unlocked_ioctl = logger_ioctl,
-	.compat_ioctl = logger_ioctl,
-	.open = logger_open,
-	.release = logger_release,
-};
-
-/*
- * Log size must must be a power of two, and greater than
- * (LOGGER_ENTRY_MAX_PAYLOAD + sizeof(struct logger_entry)).
- */
-static int __init create_log(char *log_name, int size)
-{
-	int ret = 0;
-	struct logger_log *log;
-	unsigned char *buffer;
-
-	buffer = vmalloc(size);
-	if (buffer == NULL)
-		return -ENOMEM;
-
-	log = kzalloc(sizeof(struct logger_log), GFP_KERNEL);
-	if (log == NULL) {
-		ret = -ENOMEM;
-		goto out_free_buffer;
-	}
-	log->buffer = buffer;
-
-	log->misc.minor = MISC_DYNAMIC_MINOR;
-	log->misc.name = kstrdup(log_name, GFP_KERNEL);
-	if (log->misc.name == NULL) {
-		ret = -ENOMEM;
-		goto out_free_log;
-	}
-
-	log->misc.fops = &logger_fops;
-	log->misc.parent = NULL;
-
-	init_waitqueue_head(&log->wq);
-	INIT_LIST_HEAD(&log->readers);
-	mutex_init(&log->mutex);
-	log->w_off = 0;
-	log->head = 0;
-	log->size = size;
-
-	INIT_LIST_HEAD(&log->logs);
-	list_add_tail(&log->logs, &log_list);
-
-	/* finally, initialize the misc device for this log */
-	ret = misc_register(&log->misc);
-	if (unlikely(ret)) {
-		pr_err("failed to register misc device for log '%s'!\n",
-				log->misc.name);
-		goto out_free_misc_name;
-	}
-
-	pr_info("created %luK log '%s'\n",
-		(unsigned long) log->size >> 10, log->misc.name);
-
-	return 0;
-
-out_free_misc_name:
-	kfree(log->misc.name);
-
-out_free_log:
-	kfree(log);
-
-out_free_buffer:
-	vfree(buffer);
-	return ret;
-}
-
-static int __init logger_init(void)
-{
-	int ret;
-
-	ret = create_log(LOGGER_LOG_MAIN, 256*1024);
-	if (unlikely(ret))
-		goto out;
-
-	ret = create_log(LOGGER_LOG_EVENTS, 256*1024);
-	if (unlikely(ret))
-		goto out;
-
-	ret = create_log(LOGGER_LOG_RADIO, 256*1024);
-	if (unlikely(ret))
-		goto out;
-
-	ret = create_log(LOGGER_LOG_SYSTEM, 256*1024);
-	if (unlikely(ret))
-		goto out;
-
-out:
-	return ret;
-}
-
-static void __exit logger_exit(void)
-{
-	struct logger_log *current_log, *next_log;
-
-	list_for_each_entry_safe(current_log, next_log, &log_list, logs) {
-		/* we have to delete all the entry inside log_list */
-		misc_deregister(&current_log->misc);
-		vfree(current_log->buffer);
-		kfree(current_log->misc.name);
-		list_del(&current_log->logs);
-		kfree(current_log);
-	}
-}
-
-
-device_initcall(logger_init);
-module_exit(logger_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Robert Love, <rlove@google.com>");
-MODULE_DESCRIPTION("Android Logger");
diff --git a/drivers/staging/android/logger.h b/drivers/staging/android/logger.h
deleted file mode 100644
index 70af7d805df..00000000000
--- a/drivers/staging/android/logger.h
+++ /dev/null
@@ -1,89 +0,0 @@
-/* include/linux/logger.h
- *
- * Copyright (C) 2007-2008 Google, Inc.
- * Author: Robert Love <rlove@android.com>
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#ifndef _LINUX_LOGGER_H
-#define _LINUX_LOGGER_H
-
-#include <linux/types.h>
-#include <linux/ioctl.h>
-
-/**
- * struct user_logger_entry_compat - defines a single entry that is given to a logger
- * @len:	The length of the payload
- * @__pad:	Two bytes of padding that appear to be required
- * @pid:	The generating process' process ID
- * @tid:	The generating process' thread ID
- * @sec:	The number of seconds that have elapsed since the Epoch
- * @nsec:	The number of nanoseconds that have elapsed since @sec
- * @msg:	The message that is to be logged
- *
- * The userspace structure for version 1 of the logger_entry ABI.
- * This structure is returned to userspace unless the caller requests
- * an upgrade to a newer ABI version.
- */
-struct user_logger_entry_compat {
-	__u16		len;
-	__u16		__pad;
-	__s32		pid;
-	__s32		tid;
-	__s32		sec;
-	__s32		nsec;
-	char		msg[0];
-};
-
-/**
- * struct logger_entry - defines a single entry that is given to a logger
- * @len:	The length of the payload
- * @hdr_size:	sizeof(struct logger_entry_v2)
- * @pid:	The generating process' process ID
- * @tid:	The generating process' thread ID
- * @sec:	The number of seconds that have elapsed since the Epoch
- * @nsec:	The number of nanoseconds that have elapsed since @sec
- * @euid:	Effective UID of logger
- * @msg:	The message that is to be logged
- *
- * The structure for version 2 of the logger_entry ABI.
- * This structure is returned to userspace if ioctl(LOGGER_SET_VERSION)
- * is called with version >= 2
- */
-struct logger_entry {
-	__u16		len;
-	__u16		hdr_size;
-	__s32		pid;
-	__s32		tid;
-	__s32		sec;
-	__s32		nsec;
-	kuid_t		euid;
-	char		msg[0];
-};
-
-#define LOGGER_LOG_RADIO	"log_radio"	/* radio-related messages */
-#define LOGGER_LOG_EVENTS	"log_events"	/* system/hardware events */
-#define LOGGER_LOG_SYSTEM	"log_system"	/* system/framework messages */
-#define LOGGER_LOG_MAIN		"log_main"	/* everything else */
-
-#define LOGGER_ENTRY_MAX_PAYLOAD	4076
-
-#define __LOGGERIO	0xAE
-
-#define LOGGER_GET_LOG_BUF_SIZE		_IO(__LOGGERIO, 1) /* size of log */
-#define LOGGER_GET_LOG_LEN		_IO(__LOGGERIO, 2) /* used log len */
-#define LOGGER_GET_NEXT_ENTRY_LEN	_IO(__LOGGERIO, 3) /* next entry len */
-#define LOGGER_FLUSH_LOG		_IO(__LOGGERIO, 4) /* flush log */
-#define LOGGER_GET_VERSION		_IO(__LOGGERIO, 5) /* abi version */
-#define LOGGER_SET_VERSION		_IO(__LOGGERIO, 6) /* abi version */
-
-#endif /* _LINUX_LOGGER_H */
diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c
index b545d3d1da3..ca92b605f6a 100644
--- a/drivers/staging/android/lowmemorykiller.c
+++ b/drivers/staging/android/lowmemorykiller.c
@@ -39,7 +39,6 @@
 #include <linux/sched.h>
 #include <linux/swap.h>
 #include <linux/rcupdate.h>
-#include <linux/profile.h>
 #include <linux/notifier.h>
 
 static uint32_t lowmem_debug_level = 1;
@@ -83,6 +82,7 @@ static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
 	int tasksize;
 	int i;
 	short min_score_adj = OOM_SCORE_ADJ_MAX + 1;
+	int minfree = 0;
 	int selected_tasksize = 0;
 	short selected_oom_score_adj;
 	int array_size = ARRAY_SIZE(lowmem_adj);
@@ -96,8 +96,8 @@ static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
 	if (lowmem_minfree_size < array_size)
 		array_size = lowmem_minfree_size;
 	for (i = 0; i < array_size; i++) {
-		if (other_free < lowmem_minfree[i] &&
-		    other_file < lowmem_minfree[i]) {
+		minfree = lowmem_minfree[i];
+		if (other_free < minfree && other_file < minfree) {
 			min_score_adj = lowmem_adj[i];
 			break;
 		}
@@ -152,13 +152,22 @@ static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
 		selected = p;
 		selected_tasksize = tasksize;
 		selected_oom_score_adj = oom_score_adj;
-		lowmem_print(2, "select %d (%s), adj %hd, size %d, to kill\n",
-			     p->pid, p->comm, oom_score_adj, tasksize);
+		lowmem_print(2, "select '%s' (%d), adj %hd, size %d, to kill\n",
+			     p->comm, p->pid, oom_score_adj, tasksize);
 	}
 	if (selected) {
-		lowmem_print(1, "send sigkill to %d (%s), adj %hd, size %d\n",
-			     selected->pid, selected->comm,
-			     selected_oom_score_adj, selected_tasksize);
+		lowmem_print(1, "Killing '%s' (%d), adj %hd,\n" \
+				"   to free %ldkB on behalf of '%s' (%d) because\n" \
+				"   cache %ldkB is below limit %ldkB for oom_score_adj %hd\n" \
+				"   Free memory is %ldkB above reserved\n",
+			     selected->comm, selected->pid,
+			     selected_oom_score_adj,
+			     selected_tasksize * (long)(PAGE_SIZE / 1024),
+			     current->comm, current->pid,
+			     other_file * (long)(PAGE_SIZE / 1024),
+			     minfree * (long)(PAGE_SIZE / 1024),
+			     min_score_adj,
+			     other_free * (long)(PAGE_SIZE / 1024));
 		lowmem_deathpending_timeout = jiffies + HZ;
 		set_tsk_thread_flag(selected, TIF_MEMDIE);
 		send_sig(SIGKILL, selected, 0);
@@ -188,9 +197,92 @@ static void __exit lowmem_exit(void)
 	unregister_shrinker(&lowmem_shrinker);
 }
 
+#ifdef CONFIG_ANDROID_LOW_MEMORY_KILLER_AUTODETECT_OOM_ADJ_VALUES
+static short lowmem_oom_adj_to_oom_score_adj(short oom_adj)
+{
+	if (oom_adj == OOM_ADJUST_MAX)
+		return OOM_SCORE_ADJ_MAX;
+	else
+		return (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE;
+}
+
+static void lowmem_autodetect_oom_adj_values(void)
+{
+	int i;
+	short oom_adj;
+	short oom_score_adj;
+	int array_size = ARRAY_SIZE(lowmem_adj);
+
+	if (lowmem_adj_size < array_size)
+		array_size = lowmem_adj_size;
+
+	if (array_size <= 0)
+		return;
+
+	oom_adj = lowmem_adj[array_size - 1];
+	if (oom_adj > OOM_ADJUST_MAX)
+		return;
+
+	oom_score_adj = lowmem_oom_adj_to_oom_score_adj(oom_adj);
+	if (oom_score_adj <= OOM_ADJUST_MAX)
+		return;
+
+	lowmem_print(1, "lowmem_shrink: convert oom_adj to oom_score_adj:\n");
+	for (i = 0; i < array_size; i++) {
+		oom_adj = lowmem_adj[i];
+		oom_score_adj = lowmem_oom_adj_to_oom_score_adj(oom_adj);
+		lowmem_adj[i] = oom_score_adj;
+		lowmem_print(1, "oom_adj %d => oom_score_adj %d\n",
+			     oom_adj, oom_score_adj);
+	}
+}
+
+static int lowmem_adj_array_set(const char *val, const struct kernel_param *kp)
+{
+	int ret;
+
+	ret = param_array_ops.set(val, kp);
+
+	/* HACK: Autodetect oom_adj values in lowmem_adj array */
+	lowmem_autodetect_oom_adj_values();
+
+	return ret;
+}
+
+static int lowmem_adj_array_get(char *buffer, const struct kernel_param *kp)
+{
+	return param_array_ops.get(buffer, kp);
+}
+
+static void lowmem_adj_array_free(void *arg)
+{
+	param_array_ops.free(arg);
+}
+
+static struct kernel_param_ops lowmem_adj_array_ops = {
+	.set = lowmem_adj_array_set,
+	.get = lowmem_adj_array_get,
+	.free = lowmem_adj_array_free,
+};
+
+static const struct kparam_array __param_arr_adj = {
+	.max = ARRAY_SIZE(lowmem_adj),
+	.num = &lowmem_adj_size,
+	.ops = &param_ops_short,
+	.elemsize = sizeof(lowmem_adj[0]),
+	.elem = lowmem_adj,
+};
+#endif
+
 module_param_named(cost, lowmem_shrinker.seeks, int, S_IRUGO | S_IWUSR);
+#ifdef CONFIG_ANDROID_LOW_MEMORY_KILLER_AUTODETECT_OOM_ADJ_VALUES
+module_param_cb(adj, &lowmem_adj_array_ops,
+		.arr = &__param_arr_adj, S_IRUGO | S_IWUSR);
+__MODULE_PARM_TYPE(adj, "array of short");
+#else
 module_param_array_named(adj, lowmem_adj, short, &lowmem_adj_size,
 			 S_IRUGO | S_IWUSR);
+#endif
 module_param_array_named(minfree, lowmem_minfree, uint, &lowmem_minfree_size,
 			 S_IRUGO | S_IWUSR);
 module_param_named(debug_level, lowmem_debug_level, uint, S_IRUGO | S_IWUSR);
diff --git a/drivers/staging/android/sync.c b/drivers/staging/android/sync.c
index 7bdb62bf6b4..f83e00c7805 100644
--- a/drivers/staging/android/sync.c
+++ b/drivers/staging/android/sync.c
@@ -114,7 +114,7 @@ void sync_timeline_signal(struct sync_timeline *obj)
 	list_for_each_entry_safe(pt, next, &obj->active_list_head,
 				 active_list) {
 		if (fence_is_signaled_locked(&pt->base))
-			list_del(&pt->active_list);
+			list_del_init(&pt->active_list);
 	}
 
 	spin_unlock_irqrestore(&obj->child_list_lock, flags);
diff --git a/drivers/staging/android/uapi/android_alarm.h b/drivers/staging/android/uapi/android_alarm.h
deleted file mode 100644
index aa013f6f5f3..00000000000
--- a/drivers/staging/android/uapi/android_alarm.h
+++ /dev/null
@@ -1,62 +0,0 @@
-/* drivers/staging/android/uapi/android_alarm.h
- *
- * Copyright (C) 2006-2007 Google, Inc.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#ifndef _UAPI_LINUX_ANDROID_ALARM_H
-#define _UAPI_LINUX_ANDROID_ALARM_H
-
-#include <linux/ioctl.h>
-#include <linux/time.h>
-
-enum android_alarm_type {
-	/* return code bit numbers or set alarm arg */
-	ANDROID_ALARM_RTC_WAKEUP,
-	ANDROID_ALARM_RTC,
-	ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP,
-	ANDROID_ALARM_ELAPSED_REALTIME,
-	ANDROID_ALARM_SYSTEMTIME,
-
-	ANDROID_ALARM_TYPE_COUNT,
-
-	/* return code bit numbers */
-	/* ANDROID_ALARM_TIME_CHANGE = 16 */
-};
-
-enum android_alarm_return_flags {
-	ANDROID_ALARM_RTC_WAKEUP_MASK = 1U << ANDROID_ALARM_RTC_WAKEUP,
-	ANDROID_ALARM_RTC_MASK = 1U << ANDROID_ALARM_RTC,
-	ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP_MASK =
-				1U << ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP,
-	ANDROID_ALARM_ELAPSED_REALTIME_MASK =
-				1U << ANDROID_ALARM_ELAPSED_REALTIME,
-	ANDROID_ALARM_SYSTEMTIME_MASK = 1U << ANDROID_ALARM_SYSTEMTIME,
-	ANDROID_ALARM_TIME_CHANGE_MASK = 1U << 16
-};
-
-/* Disable alarm */
-#define ANDROID_ALARM_CLEAR(type)           _IO('a', 0 | ((type) << 4))
-
-/* Ack last alarm and wait for next */
-#define ANDROID_ALARM_WAIT                  _IO('a', 1)
-
-#define ALARM_IOW(c, type, size)            _IOW('a', (c) | ((type) << 4), size)
-/* Set alarm */
-#define ANDROID_ALARM_SET(type)             ALARM_IOW(2, type, struct timespec)
-#define ANDROID_ALARM_SET_AND_WAIT(type)    ALARM_IOW(3, type, struct timespec)
-#define ANDROID_ALARM_GET_TIME(type)        ALARM_IOW(4, type, struct timespec)
-#define ANDROID_ALARM_SET_RTC               _IOW('a', 5, struct timespec)
-#define ANDROID_ALARM_BASE_CMD(cmd)         (cmd & ~(_IOC(0, 0, 0xf0, 0)))
-#define ANDROID_ALARM_IOCTL_TO_TYPE(cmd)    (_IOC_NR(cmd) >> 4)
-
-#endif
diff --git a/drivers/staging/android/uapi/ashmem.h b/drivers/staging/android/uapi/ashmem.h
index ba4743c71d6..13df42d200b 100644
--- a/drivers/staging/android/uapi/ashmem.h
+++ b/drivers/staging/android/uapi/ashmem.h
@@ -13,6 +13,7 @@
 #define _UAPI_LINUX_ASHMEM_H
 
 #include <linux/ioctl.h>
+#include <linux/types.h>
 
 #define ASHMEM_NAME_LEN		256
 
diff --git a/drivers/staging/comedi/comedi_compat32.c b/drivers/staging/comedi/comedi_compat32.c
index 9b6f96f1591..25e0b40881c 100644
--- a/drivers/staging/comedi/comedi_compat32.c
+++ b/drivers/staging/comedi/comedi_compat32.c
@@ -262,7 +262,7 @@ static int compat_cmd(struct file *file, unsigned long arg)
 {
 	struct comedi_cmd __user *cmd;
 	struct comedi32_cmd_struct __user *cmd32;
-	int rc;
+	int rc, err;
 
 	cmd32 = compat_ptr(arg);
 	cmd = compat_alloc_user_space(sizeof(*cmd));
@@ -271,7 +271,15 @@ static int compat_cmd(struct file *file, unsigned long arg)
 	if (rc)
 		return rc;
 
-	return translated_ioctl(file, COMEDI_CMD, (unsigned long)cmd);
+	rc = translated_ioctl(file, COMEDI_CMD, (unsigned long)cmd);
+	if (rc == -EAGAIN) {
+		/* Special case: copy cmd back to user. */
+		err = put_compat_cmd(cmd32, cmd);
+		if (err)
+			rc = err;
+	}
+
+	return rc;
 }
 
 /* Handle 32-bit COMEDI_CMDTEST ioctl. */
diff --git a/drivers/staging/comedi/drivers/adv_pci1710.c b/drivers/staging/comedi/drivers/adv_pci1710.c
index 5539bd29486..a65fa9f68f5 100644
--- a/drivers/staging/comedi/drivers/adv_pci1710.c
+++ b/drivers/staging/comedi/drivers/adv_pci1710.c
@@ -456,7 +456,6 @@ static int pci171x_insn_read_ai(struct comedi_device *dev,
 				struct comedi_insn *insn, unsigned int *data)
 {
 	struct pci1710_private *devpriv = dev->private;
-	unsigned int chan = CR_CHAN(insn->chanspec);
 	int ret = 0;
 	int i;
 
@@ -478,7 +477,7 @@ static int pci171x_insn_read_ai(struct comedi_device *dev,
 			break;
 
 		val = inw(dev->iobase + PCI171x_AD_DATA);
-		ret = pci171x_ai_dropout(dev, s, chan, val);
+		ret = pci171x_ai_dropout(dev, s, 0, val);
 		if (ret)
 			break;
 
diff --git a/drivers/staging/comedi/drivers/cb_pcidas64.c b/drivers/staging/comedi/drivers/cb_pcidas64.c
index 3b6bffc6691..1eb13b134b3 100644
--- a/drivers/staging/comedi/drivers/cb_pcidas64.c
+++ b/drivers/staging/comedi/drivers/cb_pcidas64.c
@@ -439,6 +439,29 @@ static const struct comedi_lrange ai_ranges_64xx = {
 	}
 };
 
+static const uint8_t ai_range_code_64xx[8] = {
+	0x0, 0x1, 0x2, 0x3,	/* bipolar 10, 5, 2,5, 1.25 */
+	0x8, 0x9, 0xa, 0xb	/* unipolar 10, 5, 2.5, 1.25 */
+};
+
+/* analog input ranges for 64-Mx boards */
+static const struct comedi_lrange ai_ranges_64_mx = {
+	7, {
+		BIP_RANGE(5),
+		BIP_RANGE(2.5),
+		BIP_RANGE(1.25),
+		BIP_RANGE(0.625),
+		UNI_RANGE(5),
+		UNI_RANGE(2.5),
+		UNI_RANGE(1.25)
+	}
+};
+
+static const uint8_t ai_range_code_64_mx[7] = {
+	0x0, 0x1, 0x2, 0x3,	/* bipolar 5, 2.5, 1.25, 0.625 */
+	0x9, 0xa, 0xb		/* unipolar 5, 2.5, 1.25 */
+};
+
 /* analog input ranges for 60xx boards */
 static const struct comedi_lrange ai_ranges_60xx = {
 	4, {
@@ -449,6 +472,10 @@ static const struct comedi_lrange ai_ranges_60xx = {
 	}
 };
 
+static const uint8_t ai_range_code_60xx[4] = {
+	0x0, 0x1, 0x4, 0x7	/* bipolar 10, 5, 0.5, 0.05 */
+};
+
 /* analog input ranges for 6030, etc boards */
 static const struct comedi_lrange ai_ranges_6030 = {
 	14, {
@@ -469,6 +496,11 @@ static const struct comedi_lrange ai_ranges_6030 = {
 	}
 };
 
+static const uint8_t ai_range_code_6030[14] = {
+	0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, /* bip 10, 5, 2, 1, 0.5, 0.2, 0.1 */
+	0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf  /* uni 10, 5, 2, 1, 0.5, 0.2, 0.1 */
+};
+
 /* analog input ranges for 6052, etc boards */
 static const struct comedi_lrange ai_ranges_6052 = {
 	15, {
@@ -490,6 +522,11 @@ static const struct comedi_lrange ai_ranges_6052 = {
 	}
 };
 
+static const uint8_t ai_range_code_6052[15] = {
+	0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,	/* bipolar 10 ... 0.05 */
+	0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf	/* unipolar 10 ... 0.1 */
+};
+
 /* analog input ranges for 4020 board */
 static const struct comedi_lrange ai_ranges_4020 = {
 	2, {
@@ -593,6 +630,7 @@ struct pcidas64_board {
 	int ai_bits;		/*  analog input resolution */
 	int ai_speed;		/*  fastest conversion period in ns */
 	const struct comedi_lrange *ai_range_table;
+	const uint8_t *ai_range_code;
 	int ao_nchan;		/*  number of analog out channels */
 	int ao_bits;		/*  analog output resolution */
 	int ao_scan_speed;	/*  analog output scan speed */
@@ -651,6 +689,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_scan_speed	= 10000,
 		.layout		= LAYOUT_64XX,
 		.ai_range_table	= &ai_ranges_64xx,
+		.ai_range_code	= ai_range_code_64xx,
 		.ao_range_table	= &ao_ranges_64xx,
 		.ao_range_code	= ao_range_code_64xx,
 		.ai_fifo	= &ai_fifo_64xx,
@@ -666,6 +705,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_scan_speed	= 10000,
 		.layout		= LAYOUT_64XX,
 		.ai_range_table	= &ai_ranges_64xx,
+		.ai_range_code	= ai_range_code_64xx,
 		.ao_range_table	= &ao_ranges_64xx,
 		.ao_range_code	= ao_range_code_64xx,
 		.ai_fifo	= &ai_fifo_64xx,
@@ -680,7 +720,8 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_bits	= 16,
 		.ao_scan_speed	= 10000,
 		.layout		= LAYOUT_64XX,
-		.ai_range_table	= &ai_ranges_64xx,
+		.ai_range_table	= &ai_ranges_64_mx,
+		.ai_range_code	= ai_range_code_64_mx,
 		.ao_range_table	= &ao_ranges_64xx,
 		.ao_range_code	= ao_range_code_64xx,
 		.ai_fifo	= &ai_fifo_64xx,
@@ -695,7 +736,8 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_bits	= 16,
 		.ao_scan_speed	= 10000,
 		.layout		= LAYOUT_64XX,
-		.ai_range_table	= &ai_ranges_64xx,
+		.ai_range_table	= &ai_ranges_64_mx,
+		.ai_range_code	= ai_range_code_64_mx,
 		.ao_range_table	= &ao_ranges_64xx,
 		.ao_range_code	= ao_range_code_64xx,
 		.ai_fifo	= &ai_fifo_64xx,
@@ -710,7 +752,8 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_bits	= 16,
 		.ao_scan_speed	= 10000,
 		.layout		= LAYOUT_64XX,
-		.ai_range_table	= &ai_ranges_64xx,
+		.ai_range_table	= &ai_ranges_64_mx,
+		.ai_range_code	= ai_range_code_64_mx,
 		.ao_range_table	= &ao_ranges_64xx,
 		.ao_range_code	= ao_range_code_64xx,
 		.ai_fifo	= &ai_fifo_64xx,
@@ -725,6 +768,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_bits	= 16,
 		.layout		= LAYOUT_60XX,
 		.ai_range_table	= &ai_ranges_60xx,
+		.ai_range_code	= ai_range_code_60xx,
 		.ao_range_table	= &range_bipolar10,
 		.ao_range_code	= ao_range_code_60xx,
 		.ai_fifo	= &ai_fifo_60xx,
@@ -740,6 +784,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_scan_speed	= 100000,
 		.layout		= LAYOUT_60XX,
 		.ai_range_table	= &ai_ranges_60xx,
+		.ai_range_code	= ai_range_code_60xx,
 		.ao_range_table	= &range_bipolar10,
 		.ao_range_code	= ao_range_code_60xx,
 		.ai_fifo	= &ai_fifo_60xx,
@@ -754,6 +799,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_scan_speed	= 100000,
 		.layout		= LAYOUT_60XX,
 		.ai_range_table	= &ai_ranges_60xx,
+		.ai_range_code	= ai_range_code_60xx,
 		.ao_range_table	= &range_bipolar10,
 		.ao_range_code	= ao_range_code_60xx,
 		.ai_fifo	= &ai_fifo_60xx,
@@ -769,6 +815,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_scan_speed	= 100000,
 		.layout		= LAYOUT_60XX,
 		.ai_range_table	= &ai_ranges_60xx,
+		.ai_range_code	= ai_range_code_60xx,
 		.ao_range_table	= &range_bipolar10,
 		.ao_range_code	= ao_range_code_60xx,
 		.ai_fifo	= &ai_fifo_60xx,
@@ -784,6 +831,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_scan_speed	= 10000,
 		.layout		= LAYOUT_60XX,
 		.ai_range_table	= &ai_ranges_6030,
+		.ai_range_code	= ai_range_code_6030,
 		.ao_range_table	= &ao_ranges_6030,
 		.ao_range_code	= ao_range_code_6030,
 		.ai_fifo	= &ai_fifo_60xx,
@@ -799,6 +847,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_scan_speed	= 10000,
 		.layout		= LAYOUT_60XX,
 		.ai_range_table	= &ai_ranges_6030,
+		.ai_range_code	= ai_range_code_6030,
 		.ao_range_table	= &ao_ranges_6030,
 		.ao_range_code	= ao_range_code_6030,
 		.ai_fifo	= &ai_fifo_60xx,
@@ -812,6 +861,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_nchan	= 0,
 		.layout		= LAYOUT_60XX,
 		.ai_range_table	= &ai_ranges_6030,
+		.ai_range_code	= ai_range_code_6030,
 		.ai_fifo	= &ai_fifo_60xx,
 		.has_8255	= 0,
 	},
@@ -823,6 +873,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_nchan	= 0,
 		.layout		= LAYOUT_60XX,
 		.ai_range_table	= &ai_ranges_6030,
+		.ai_range_code	= ai_range_code_6030,
 		.ai_fifo	= &ai_fifo_60xx,
 		.has_8255	= 0,
 	},
@@ -835,6 +886,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_scan_speed	= 0,
 		.layout		= LAYOUT_60XX,
 		.ai_range_table	= &ai_ranges_60xx,
+		.ai_range_code	= ai_range_code_60xx,
 		.ai_fifo	= &ai_fifo_60xx,
 		.has_8255	= 0,
 	},
@@ -848,6 +900,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_scan_speed	= 100000,
 		.layout		= LAYOUT_60XX,
 		.ai_range_table	= &ai_ranges_60xx,
+		.ai_range_code	= ai_range_code_60xx,
 		.ao_range_table	= &range_bipolar10,
 		.ao_range_code	= ao_range_code_60xx,
 		.ai_fifo	= &ai_fifo_60xx,
@@ -863,6 +916,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_scan_speed	= 100000,
 		.layout		= LAYOUT_60XX,
 		.ai_range_table	= &ai_ranges_60xx,
+		.ai_range_code	= ai_range_code_60xx,
 		.ao_range_table	= &range_bipolar10,
 		.ao_range_code	= ao_range_code_60xx,
 		.ai_fifo	= &ai_fifo_60xx,
@@ -878,6 +932,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_scan_speed	= 1000,
 		.layout		= LAYOUT_60XX,
 		.ai_range_table	= &ai_ranges_6052,
+		.ai_range_code	= ai_range_code_6052,
 		.ao_range_table	= &ao_ranges_6030,
 		.ao_range_code	= ao_range_code_6030,
 		.ai_fifo	= &ai_fifo_60xx,
@@ -893,6 +948,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_scan_speed	= 3333,
 		.layout		= LAYOUT_60XX,
 		.ai_range_table	= &ai_ranges_6052,
+		.ai_range_code	= ai_range_code_6052,
 		.ao_range_table	= &ao_ranges_6030,
 		.ao_range_code	= ao_range_code_6030,
 		.ai_fifo	= &ai_fifo_60xx,
@@ -908,6 +964,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_scan_speed	= 1000,
 		.layout		= LAYOUT_60XX,
 		.ai_range_table	= &ai_ranges_6052,
+		.ai_range_code	= ai_range_code_6052,
 		.ao_range_table	= &ao_ranges_6030,
 		.ao_range_code	= ao_range_code_6030,
 		.ai_fifo	= &ai_fifo_60xx,
@@ -923,6 +980,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_scan_speed	= 1000,
 		.layout		= LAYOUT_60XX,
 		.ai_range_table	= &ai_ranges_6052,
+		.ai_range_code	= ai_range_code_6052,
 		.ao_range_table	= &ao_ranges_6030,
 		.ao_range_code	= ao_range_code_6030,
 		.ai_fifo	= &ai_fifo_60xx,
@@ -957,6 +1015,7 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_scan_speed	= 10000,
 		.layout		= LAYOUT_64XX,
 		.ai_range_table	= &ai_ranges_64xx,
+		.ai_range_code	= ai_range_code_64xx,
 		.ai_fifo	= ai_fifo_64xx,
 		.has_8255	= 1,
 	},
@@ -968,7 +1027,8 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_nchan	= 0,
 		.ao_scan_speed	= 10000,
 		.layout		= LAYOUT_64XX,
-		.ai_range_table	= &ai_ranges_64xx,
+		.ai_range_table	= &ai_ranges_64_mx,
+		.ai_range_code	= ai_range_code_64_mx,
 		.ai_fifo	= ai_fifo_64xx,
 		.has_8255	= 1,
 	},
@@ -980,7 +1040,8 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_nchan	= 0,
 		.ao_scan_speed	= 10000,
 		.layout		= LAYOUT_64XX,
-		.ai_range_table	= &ai_ranges_64xx,
+		.ai_range_table	= &ai_ranges_64_mx,
+		.ai_range_code	= ai_range_code_64_mx,
 		.ai_fifo	= ai_fifo_64xx,
 		.has_8255	= 1,
 	},
@@ -992,7 +1053,8 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_nchan	= 0,
 		.ao_scan_speed	= 10000,
 		.layout		= LAYOUT_64XX,
-		.ai_range_table	= &ai_ranges_64xx,
+		.ai_range_table	= &ai_ranges_64_mx,
+		.ai_range_code	= ai_range_code_64_mx,
 		.ai_fifo	= ai_fifo_64xx,
 		.has_8255	= 1,
 	},
@@ -1004,7 +1066,8 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_nchan	= 2,
 		.ao_scan_speed	= 10000,
 		.layout		= LAYOUT_64XX,
-		.ai_range_table	= &ai_ranges_64xx,
+		.ai_range_table	= &ai_ranges_64_mx,
+		.ai_range_code	= ai_range_code_64_mx,
 		.ai_fifo	= ai_fifo_64xx,
 		.has_8255	= 1,
 	},
@@ -1016,7 +1079,8 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_nchan	= 2,
 		.ao_scan_speed	= 10000,
 		.layout		= LAYOUT_64XX,
-		.ai_range_table	= &ai_ranges_64xx,
+		.ai_range_table	= &ai_ranges_64_mx,
+		.ai_range_code	= ai_range_code_64_mx,
 		.ai_fifo	= ai_fifo_64xx,
 		.has_8255	= 1,
 	},
@@ -1028,7 +1092,8 @@ static const struct pcidas64_board pcidas64_boards[] = {
 		.ao_nchan	= 2,
 		.ao_scan_speed	= 10000,
 		.layout		= LAYOUT_64XX,
-		.ai_range_table	= &ai_ranges_64xx,
+		.ai_range_table	= &ai_ranges_64_mx,
+		.ai_range_code	= ai_range_code_64_mx,
 		.ai_fifo	= ai_fifo_64xx,
 		.has_8255	= 1,
 	},
@@ -1122,45 +1187,8 @@ static unsigned int ai_range_bits_6xxx(const struct comedi_device *dev,
 				       unsigned int range_index)
 {
 	const struct pcidas64_board *thisboard = dev->board_ptr;
-	const struct comedi_krange *range =
-		&thisboard->ai_range_table->range[range_index];
-	unsigned int bits = 0;
 
-	switch (range->max) {
-	case 10000000:
-		bits = 0x000;
-		break;
-	case 5000000:
-		bits = 0x100;
-		break;
-	case 2000000:
-	case 2500000:
-		bits = 0x200;
-		break;
-	case 1000000:
-	case 1250000:
-		bits = 0x300;
-		break;
-	case 500000:
-		bits = 0x400;
-		break;
-	case 200000:
-	case 250000:
-		bits = 0x500;
-		break;
-	case 100000:
-		bits = 0x600;
-		break;
-	case 50000:
-		bits = 0x700;
-		break;
-	default:
-		dev_err(dev->class_dev, "bug! in %s\n", __func__);
-		break;
-	}
-	if (range->min == 0)
-		bits += 0x900;
-	return bits;
+	return thisboard->ai_range_code[range_index] << 8;
 }
 
 static unsigned int hw_revision(const struct comedi_device *dev,
diff --git a/drivers/staging/gdm724x/gdm_mux.c b/drivers/staging/gdm724x/gdm_mux.c
index b5b063a738f..fe410445a1a 100644
--- a/drivers/staging/gdm724x/gdm_mux.c
+++ b/drivers/staging/gdm724x/gdm_mux.c
@@ -158,7 +158,7 @@ static int up_to_host(struct mux_rx *r)
 	unsigned int start_flag;
 	unsigned int payload_size;
 	unsigned short packet_type;
-	int dummy_cnt;
+	int total_len;
 	u32 packet_size_sum = r->offset;
 	int index;
 	int ret = TO_HOST_INVALID_PACKET;
@@ -176,10 +176,10 @@ static int up_to_host(struct mux_rx *r)
 			break;
 		}
 
-		dummy_cnt = ALIGN(MUX_HEADER_SIZE + payload_size, 4);
+		total_len = ALIGN(MUX_HEADER_SIZE + payload_size, 4);
 
 		if (len - packet_size_sum <
-			MUX_HEADER_SIZE + payload_size + dummy_cnt) {
+			total_len) {
 			pr_err("invalid payload : %d %d %04x\n",
 			       payload_size, len, packet_type);
 			break;
@@ -202,7 +202,7 @@ static int up_to_host(struct mux_rx *r)
 			break;
 		}
 
-		packet_size_sum += MUX_HEADER_SIZE + payload_size + dummy_cnt;
+		packet_size_sum += total_len;
 		if (len - packet_size_sum <= MUX_HEADER_SIZE + 2) {
 			ret = r->callback(NULL,
 					0,
@@ -361,7 +361,6 @@ static int gdm_mux_send(void *priv_dev, void *data, int len, int tty_index,
 	struct mux_pkt_header *mux_header;
 	struct mux_tx *t = NULL;
 	static u32 seq_num = 1;
-	int dummy_cnt;
 	int total_len;
 	int ret;
 	unsigned long flags;
@@ -374,9 +373,7 @@ static int gdm_mux_send(void *priv_dev, void *data, int len, int tty_index,
 
 	spin_lock_irqsave(&mux_dev->write_lock, flags);
 
-	dummy_cnt = ALIGN(MUX_HEADER_SIZE + len, 4);
-
-	total_len = len + MUX_HEADER_SIZE + dummy_cnt;
+	total_len = ALIGN(MUX_HEADER_SIZE + len, 4);
 
 	t = alloc_mux_tx(total_len);
 	if (!t) {
@@ -392,7 +389,8 @@ static int gdm_mux_send(void *priv_dev, void *data, int len, int tty_index,
 	mux_header->packet_type = __cpu_to_le16(packet_type[tty_index]);
 
 	memcpy(t->buf+MUX_HEADER_SIZE, data, len);
-	memset(t->buf+MUX_HEADER_SIZE+len, 0, dummy_cnt);
+	memset(t->buf+MUX_HEADER_SIZE+len, 0, total_len - MUX_HEADER_SIZE -
+	       len);
 
 	t->len = total_len;
 	t->callback = cb;
diff --git a/drivers/staging/iio/adc/mxs-lradc.c b/drivers/staging/iio/adc/mxs-lradc.c
index 2a29b9baec0..ffd42071a12 100644
--- a/drivers/staging/iio/adc/mxs-lradc.c
+++ b/drivers/staging/iio/adc/mxs-lradc.c
@@ -214,11 +214,17 @@ struct mxs_lradc {
 	unsigned long		is_divided;
 
 	/*
-	 * Touchscreen LRADC channels receives a private slot in the CTRL4
-	 * register, the slot #7. Therefore only 7 slots instead of 8 in the
-	 * CTRL4 register can be mapped to LRADC channels when using the
-	 * touchscreen.
-	 *
+	 * When the touchscreen is enabled, we give it two private virtual
+	 * channels: #6 and #7. This means that only 6 virtual channels (instead
+	 * of 8) will be available for buffered capture.
+	 */
+#define TOUCHSCREEN_VCHANNEL1		7
+#define TOUCHSCREEN_VCHANNEL2		6
+#define BUFFER_VCHANS_LIMITED		0x3f
+#define BUFFER_VCHANS_ALL		0xff
+	u8			buffer_vchans;
+
+	/*
 	 * Furthermore, certain LRADC channels are shared between touchscreen
 	 * and/or touch-buttons and generic LRADC block. Therefore when using
 	 * either of these, these channels are not available for the regular
@@ -342,6 +348,9 @@ struct mxs_lradc {
 #define	LRADC_CTRL4				0x140
 #define	LRADC_CTRL4_LRADCSELECT_MASK(n)		(0xf << ((n) * 4))
 #define	LRADC_CTRL4_LRADCSELECT_OFFSET(n)	((n) * 4)
+#define	LRADC_CTRL4_LRADCSELECT(n, x) \
+				(((x) << LRADC_CTRL4_LRADCSELECT_OFFSET(n)) & \
+				LRADC_CTRL4_LRADCSELECT_MASK(n))
 
 #define LRADC_RESOLUTION			12
 #define LRADC_SINGLE_SAMPLE_MASK		((1 << LRADC_RESOLUTION) - 1)
@@ -416,6 +425,14 @@ static bool mxs_lradc_check_touch_event(struct mxs_lradc *lradc)
 					LRADC_STATUS_TOUCH_DETECT_RAW);
 }
 
+static void mxs_lradc_map_channel(struct mxs_lradc *lradc, unsigned vch,
+				  unsigned ch)
+{
+	mxs_lradc_reg_clear(lradc, LRADC_CTRL4_LRADCSELECT_MASK(vch),
+				LRADC_CTRL4);
+	mxs_lradc_reg_set(lradc, LRADC_CTRL4_LRADCSELECT(vch, ch), LRADC_CTRL4);
+}
+
 static void mxs_lradc_setup_ts_channel(struct mxs_lradc *lradc, unsigned ch)
 {
 	/*
@@ -443,12 +460,8 @@ static void mxs_lradc_setup_ts_channel(struct mxs_lradc *lradc, unsigned ch)
 		LRADC_DELAY_DELAY(lradc->over_sample_delay - 1),
 			LRADC_DELAY(3));
 
-	mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ(2) |
-			LRADC_CTRL1_LRADC_IRQ(3) | LRADC_CTRL1_LRADC_IRQ(4) |
-			LRADC_CTRL1_LRADC_IRQ(5), LRADC_CTRL1);
+	mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ(ch), LRADC_CTRL1);
 
-	/* wake us again, when the complete conversion is done */
-	mxs_lradc_reg_set(lradc, LRADC_CTRL1_LRADC_IRQ_EN(ch), LRADC_CTRL1);
 	/*
 	 * after changing the touchscreen plates setting
 	 * the signals need some initial time to settle. Start the
@@ -501,12 +514,8 @@ static void mxs_lradc_setup_ts_pressure(struct mxs_lradc *lradc, unsigned ch1,
 		LRADC_DELAY_DELAY(lradc->over_sample_delay - 1),
 					LRADC_DELAY(3));
 
-	mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ(2) |
-			LRADC_CTRL1_LRADC_IRQ(3) | LRADC_CTRL1_LRADC_IRQ(4) |
-			LRADC_CTRL1_LRADC_IRQ(5), LRADC_CTRL1);
+	mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ(ch2), LRADC_CTRL1);
 
-	/* wake us again, when the conversions are done */
-	mxs_lradc_reg_set(lradc, LRADC_CTRL1_LRADC_IRQ_EN(ch2), LRADC_CTRL1);
 	/*
 	 * after changing the touchscreen plates setting
 	 * the signals need some initial time to settle. Start the
@@ -571,36 +580,6 @@ static unsigned mxs_lradc_read_ts_pressure(struct mxs_lradc *lradc,
 #define TS_CH_XM 4
 #define TS_CH_YM 5
 
-static int mxs_lradc_read_ts_channel(struct mxs_lradc *lradc)
-{
-	u32 reg;
-	int val;
-
-	reg = readl(lradc->base + LRADC_CTRL1);
-
-	/* only channels 3 to 5 are of interest here */
-	if (reg & LRADC_CTRL1_LRADC_IRQ(TS_CH_YP)) {
-		mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ_EN(TS_CH_YP) |
-			LRADC_CTRL1_LRADC_IRQ(TS_CH_YP), LRADC_CTRL1);
-		val = mxs_lradc_read_raw_channel(lradc, TS_CH_YP);
-	} else if (reg & LRADC_CTRL1_LRADC_IRQ(TS_CH_XM)) {
-		mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ_EN(TS_CH_XM) |
-			LRADC_CTRL1_LRADC_IRQ(TS_CH_XM), LRADC_CTRL1);
-		val = mxs_lradc_read_raw_channel(lradc, TS_CH_XM);
-	} else if (reg & LRADC_CTRL1_LRADC_IRQ(TS_CH_YM)) {
-		mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ_EN(TS_CH_YM) |
-			LRADC_CTRL1_LRADC_IRQ(TS_CH_YM), LRADC_CTRL1);
-		val = mxs_lradc_read_raw_channel(lradc, TS_CH_YM);
-	} else {
-		return -EIO;
-	}
-
-	mxs_lradc_reg_wrt(lradc, 0, LRADC_DELAY(2));
-	mxs_lradc_reg_wrt(lradc, 0, LRADC_DELAY(3));
-
-	return val;
-}
-
 /*
  * YP(open)--+-------------+
  *           |             |--+
@@ -644,7 +623,8 @@ static void mxs_lradc_prepare_x_pos(struct mxs_lradc *lradc)
 	mxs_lradc_reg_set(lradc, mxs_lradc_drive_x_plate(lradc), LRADC_CTRL0);
 
 	lradc->cur_plate = LRADC_SAMPLE_X;
-	mxs_lradc_setup_ts_channel(lradc, TS_CH_YP);
+	mxs_lradc_map_channel(lradc, TOUCHSCREEN_VCHANNEL1, TS_CH_YP);
+	mxs_lradc_setup_ts_channel(lradc, TOUCHSCREEN_VCHANNEL1);
 }
 
 /*
@@ -665,7 +645,8 @@ static void mxs_lradc_prepare_y_pos(struct mxs_lradc *lradc)
 	mxs_lradc_reg_set(lradc, mxs_lradc_drive_y_plate(lradc), LRADC_CTRL0);
 
 	lradc->cur_plate = LRADC_SAMPLE_Y;
-	mxs_lradc_setup_ts_channel(lradc, TS_CH_XM);
+	mxs_lradc_map_channel(lradc, TOUCHSCREEN_VCHANNEL1, TS_CH_XM);
+	mxs_lradc_setup_ts_channel(lradc, TOUCHSCREEN_VCHANNEL1);
 }
 
 /*
@@ -686,7 +667,10 @@ static void mxs_lradc_prepare_pressure(struct mxs_lradc *lradc)
 	mxs_lradc_reg_set(lradc, mxs_lradc_drive_pressure(lradc), LRADC_CTRL0);
 
 	lradc->cur_plate = LRADC_SAMPLE_PRESSURE;
-	mxs_lradc_setup_ts_pressure(lradc, TS_CH_XP, TS_CH_YM);
+	mxs_lradc_map_channel(lradc, TOUCHSCREEN_VCHANNEL1, TS_CH_YM);
+	mxs_lradc_map_channel(lradc, TOUCHSCREEN_VCHANNEL2, TS_CH_XP);
+	mxs_lradc_setup_ts_pressure(lradc, TOUCHSCREEN_VCHANNEL2,
+						TOUCHSCREEN_VCHANNEL1);
 }
 
 static void mxs_lradc_enable_touch_detection(struct mxs_lradc *lradc)
@@ -699,6 +683,19 @@ static void mxs_lradc_enable_touch_detection(struct mxs_lradc *lradc)
 	mxs_lradc_reg_set(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ_EN, LRADC_CTRL1);
 }
 
+static void mxs_lradc_start_touch_event(struct mxs_lradc *lradc)
+{
+	mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ_EN,
+				LRADC_CTRL1);
+	mxs_lradc_reg_set(lradc,
+		LRADC_CTRL1_LRADC_IRQ_EN(TOUCHSCREEN_VCHANNEL1), LRADC_CTRL1);
+	/*
+	 * start with the Y-pos, because it uses nearly the same plate
+	 * settings like the touch detection
+	 */
+	mxs_lradc_prepare_y_pos(lradc);
+}
+
 static void mxs_lradc_report_ts_event(struct mxs_lradc *lradc)
 {
 	input_report_abs(lradc->ts_input, ABS_X, lradc->ts_x_pos);
@@ -716,10 +713,12 @@ static void mxs_lradc_complete_touch_event(struct mxs_lradc *lradc)
 	 * start a dummy conversion to burn time to settle the signals
 	 * note: we are not interested in the conversion's value
 	 */
-	mxs_lradc_reg_wrt(lradc, 0, LRADC_CH(5));
-	mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ(5), LRADC_CTRL1);
-	mxs_lradc_reg_set(lradc, LRADC_CTRL1_LRADC_IRQ_EN(5), LRADC_CTRL1);
-	mxs_lradc_reg_wrt(lradc, LRADC_DELAY_TRIGGER(1 << 5) |
+	mxs_lradc_reg_wrt(lradc, 0, LRADC_CH(TOUCHSCREEN_VCHANNEL1));
+	mxs_lradc_reg_clear(lradc,
+		LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL1) |
+		LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL2), LRADC_CTRL1);
+	mxs_lradc_reg_wrt(lradc,
+		LRADC_DELAY_TRIGGER(1 << TOUCHSCREEN_VCHANNEL1) |
 		LRADC_DELAY_KICK | LRADC_DELAY_DELAY(10), /* waste 5 ms */
 			LRADC_DELAY(2));
 }
@@ -751,59 +750,45 @@ static void mxs_lradc_finish_touch_event(struct mxs_lradc *lradc, bool valid)
 
 	/* if it is released, wait for the next touch via IRQ */
 	lradc->cur_plate = LRADC_TOUCH;
-	mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ, LRADC_CTRL1);
+	mxs_lradc_reg_wrt(lradc, 0, LRADC_DELAY(2));
+	mxs_lradc_reg_wrt(lradc, 0, LRADC_DELAY(3));
+	mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ |
+		LRADC_CTRL1_LRADC_IRQ_EN(TOUCHSCREEN_VCHANNEL1) |
+		LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL1), LRADC_CTRL1);
 	mxs_lradc_reg_set(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ_EN, LRADC_CTRL1);
 }
 
 /* touchscreen's state machine */
 static void mxs_lradc_handle_touch(struct mxs_lradc *lradc)
 {
-	int val;
-
 	switch (lradc->cur_plate) {
 	case LRADC_TOUCH:
-		/*
-		 * start with the Y-pos, because it uses nearly the same plate
-		 * settings like the touch detection
-		 */
-		if (mxs_lradc_check_touch_event(lradc)) {
-			mxs_lradc_reg_clear(lradc,
-					LRADC_CTRL1_TOUCH_DETECT_IRQ_EN,
-					LRADC_CTRL1);
-			mxs_lradc_prepare_y_pos(lradc);
-		}
+		if (mxs_lradc_check_touch_event(lradc))
+			mxs_lradc_start_touch_event(lradc);
 		mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ,
 					LRADC_CTRL1);
 		return;
 
 	case LRADC_SAMPLE_Y:
-		val = mxs_lradc_read_ts_channel(lradc);
-		if (val < 0) {
-			mxs_lradc_enable_touch_detection(lradc); /* re-start */
-			return;
-		}
-		lradc->ts_y_pos = val;
+		lradc->ts_y_pos = mxs_lradc_read_raw_channel(lradc,
+							TOUCHSCREEN_VCHANNEL1);
 		mxs_lradc_prepare_x_pos(lradc);
 		return;
 
 	case LRADC_SAMPLE_X:
-		val = mxs_lradc_read_ts_channel(lradc);
-		if (val < 0) {
-			mxs_lradc_enable_touch_detection(lradc); /* re-start */
-			return;
-		}
-		lradc->ts_x_pos = val;
+		lradc->ts_x_pos = mxs_lradc_read_raw_channel(lradc,
+							TOUCHSCREEN_VCHANNEL1);
 		mxs_lradc_prepare_pressure(lradc);
 		return;
 
 	case LRADC_SAMPLE_PRESSURE:
-		lradc->ts_pressure =
-			mxs_lradc_read_ts_pressure(lradc, TS_CH_XP, TS_CH_YM);
+		lradc->ts_pressure = mxs_lradc_read_ts_pressure(lradc,
+							TOUCHSCREEN_VCHANNEL2,
+							TOUCHSCREEN_VCHANNEL1);
 		mxs_lradc_complete_touch_event(lradc);
 		return;
 
 	case LRADC_SAMPLE_VALID:
-		val = mxs_lradc_read_ts_channel(lradc); /* ignore the value */
 		mxs_lradc_finish_touch_event(lradc, 1);
 		break;
 	}
@@ -835,9 +820,9 @@ static int mxs_lradc_read_single(struct iio_dev *iio_dev, int chan, int *val)
 	 * used if doing raw sampling.
 	 */
 	if (lradc->soc == IMX28_LRADC)
-		mxs_lradc_reg_clear(lradc, LRADC_CTRL1_MX28_LRADC_IRQ_EN_MASK,
+		mxs_lradc_reg_clear(lradc, LRADC_CTRL1_LRADC_IRQ_EN(0),
 			LRADC_CTRL1);
-	mxs_lradc_reg_clear(lradc, 0xff, LRADC_CTRL0);
+	mxs_lradc_reg_clear(lradc, 0x1, LRADC_CTRL0);
 
 	/* Enable / disable the divider per requirement */
 	if (test_bit(chan, &lradc->is_divided))
@@ -1081,9 +1066,8 @@ static void mxs_lradc_disable_ts(struct mxs_lradc *lradc)
 {
 	/* stop all interrupts from firing */
 	mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ_EN |
-		LRADC_CTRL1_LRADC_IRQ_EN(2) | LRADC_CTRL1_LRADC_IRQ_EN(3) |
-		LRADC_CTRL1_LRADC_IRQ_EN(4) | LRADC_CTRL1_LRADC_IRQ_EN(5),
-		LRADC_CTRL1);
+		LRADC_CTRL1_LRADC_IRQ_EN(TOUCHSCREEN_VCHANNEL1) |
+		LRADC_CTRL1_LRADC_IRQ_EN(TOUCHSCREEN_VCHANNEL2), LRADC_CTRL1);
 
 	/* Power-down touchscreen touch-detect circuitry. */
 	mxs_lradc_reg_clear(lradc, mxs_lradc_plate_mask(lradc), LRADC_CTRL0);
@@ -1149,26 +1133,31 @@ static irqreturn_t mxs_lradc_handle_irq(int irq, void *data)
 	struct iio_dev *iio = data;
 	struct mxs_lradc *lradc = iio_priv(iio);
 	unsigned long reg = readl(lradc->base + LRADC_CTRL1);
+	uint32_t clr_irq = mxs_lradc_irq_mask(lradc);
 	const uint32_t ts_irq_mask =
 		LRADC_CTRL1_TOUCH_DETECT_IRQ |
-		LRADC_CTRL1_LRADC_IRQ(2) |
-		LRADC_CTRL1_LRADC_IRQ(3) |
-		LRADC_CTRL1_LRADC_IRQ(4) |
-		LRADC_CTRL1_LRADC_IRQ(5);
+		LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL1) |
+		LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL2);
 
 	if (!(reg & mxs_lradc_irq_mask(lradc)))
 		return IRQ_NONE;
 
-	if (lradc->use_touchscreen && (reg & ts_irq_mask))
+	if (lradc->use_touchscreen && (reg & ts_irq_mask)) {
 		mxs_lradc_handle_touch(lradc);
 
-	if (iio_buffer_enabled(iio))
-		iio_trigger_poll(iio->trig);
-	else if (reg & LRADC_CTRL1_LRADC_IRQ(0))
+		/* Make sure we don't clear the next conversion's interrupt. */
+		clr_irq &= ~(LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL1) |
+				LRADC_CTRL1_LRADC_IRQ(TOUCHSCREEN_VCHANNEL2));
+	}
+
+	if (iio_buffer_enabled(iio)) {
+		if (reg & lradc->buffer_vchans)
+			iio_trigger_poll(iio->trig);
+	} else if (reg & LRADC_CTRL1_LRADC_IRQ(0)) {
 		complete(&lradc->completion);
+	}
 
-	mxs_lradc_reg_clear(lradc, reg & mxs_lradc_irq_mask(lradc),
-			LRADC_CTRL1);
+	mxs_lradc_reg_clear(lradc, reg & clr_irq, LRADC_CTRL1);
 
 	return IRQ_HANDLED;
 }
@@ -1280,9 +1269,10 @@ static int mxs_lradc_buffer_preenable(struct iio_dev *iio)
 	}
 
 	if (lradc->soc == IMX28_LRADC)
-		mxs_lradc_reg_clear(lradc, LRADC_CTRL1_MX28_LRADC_IRQ_EN_MASK,
-							LRADC_CTRL1);
-	mxs_lradc_reg_clear(lradc, 0xff, LRADC_CTRL0);
+		mxs_lradc_reg_clear(lradc,
+			lradc->buffer_vchans << LRADC_CTRL1_LRADC_IRQ_EN_OFFSET,
+			LRADC_CTRL1);
+	mxs_lradc_reg_clear(lradc, lradc->buffer_vchans, LRADC_CTRL0);
 
 	for_each_set_bit(chan, iio->active_scan_mask, LRADC_MAX_TOTAL_CHANS) {
 		ctrl4_set |= chan << LRADC_CTRL4_LRADCSELECT_OFFSET(ofs);
@@ -1315,10 +1305,11 @@ static int mxs_lradc_buffer_postdisable(struct iio_dev *iio)
 	mxs_lradc_reg_clear(lradc, LRADC_DELAY_TRIGGER_LRADCS_MASK |
 					LRADC_DELAY_KICK, LRADC_DELAY(0));
 
-	mxs_lradc_reg_clear(lradc, 0xff, LRADC_CTRL0);
+	mxs_lradc_reg_clear(lradc, lradc->buffer_vchans, LRADC_CTRL0);
 	if (lradc->soc == IMX28_LRADC)
-		mxs_lradc_reg_clear(lradc, LRADC_CTRL1_MX28_LRADC_IRQ_EN_MASK,
-					LRADC_CTRL1);
+		mxs_lradc_reg_clear(lradc,
+			lradc->buffer_vchans << LRADC_CTRL1_LRADC_IRQ_EN_OFFSET,
+			LRADC_CTRL1);
 
 	kfree(lradc->buffer);
 	mutex_unlock(&lradc->lock);
@@ -1344,7 +1335,7 @@ static bool mxs_lradc_validate_scan_mask(struct iio_dev *iio,
 	if (lradc->use_touchbutton)
 		rsvd_chans++;
 	if (lradc->use_touchscreen)
-		rsvd_chans++;
+		rsvd_chans += 2;
 
 	/* Test for attempts to map channels with special mode of operation. */
 	if (bitmap_intersects(mask, &rsvd_mask, LRADC_MAX_TOTAL_CHANS))
@@ -1404,6 +1395,13 @@ static const struct iio_chan_spec mxs_lradc_chan_spec[] = {
 		.channel = 8,
 		.scan_type = {.sign = 'u', .realbits = 18, .storagebits = 32,},
 	},
+	/* Hidden channel to keep indexes */
+	{
+		.type = IIO_TEMP,
+		.indexed = 1,
+		.scan_index = -1,
+		.channel = 9,
+	},
 	MXS_ADC_CHAN(10, IIO_VOLTAGE),	/* VDDIO */
 	MXS_ADC_CHAN(11, IIO_VOLTAGE),	/* VTH */
 	MXS_ADC_CHAN(12, IIO_VOLTAGE),	/* VDDA */
@@ -1556,6 +1554,11 @@ static int mxs_lradc_probe(struct platform_device *pdev)
 
 	touch_ret = mxs_lradc_probe_touchscreen(lradc, node);
 
+	if (touch_ret == 0)
+		lradc->buffer_vchans = BUFFER_VCHANS_LIMITED;
+	else
+		lradc->buffer_vchans = BUFFER_VCHANS_ALL;
+
 	/* Grab all IRQ sources */
 	for (i = 0; i < of_cfg->irq_count; i++) {
 		lradc->irq[i] = platform_get_irq(pdev, i);
diff --git a/drivers/staging/lustre/lustre/llite/dcache.c b/drivers/staging/lustre/lustre/llite/dcache.c
index 439e4875b05..311907b762b 100644
--- a/drivers/staging/lustre/lustre/llite/dcache.c
+++ b/drivers/staging/lustre/lustre/llite/dcache.c
@@ -258,7 +258,7 @@ void ll_invalidate_aliases(struct inode *inode)
 	       inode->i_ino, inode->i_generation, inode);
 
 	ll_lock_dcache(inode);
-	ll_d_hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
+	ll_d_hlist_for_each_entry(dentry, p, &inode->i_dentry, d_u.d_alias) {
 		CDEBUG(D_DENTRY, "dentry in drop %.*s (%p) parent %p "
 		       "inode %p flags %d\n", dentry->d_name.len,
 		       dentry->d_name.name, dentry, dentry->d_parent,
diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c
index a8bcc51057f..f4ca7b75302 100644
--- a/drivers/staging/lustre/lustre/llite/llite_lib.c
+++ b/drivers/staging/lustre/lustre/llite/llite_lib.c
@@ -711,7 +711,7 @@ void lustre_dump_dentry(struct dentry *dentry, int recur)
 		return;
 
 	list_for_each(tmp, &dentry->d_subdirs) {
-		struct dentry *d = list_entry(tmp, struct dentry, d_u.d_child);
+		struct dentry *d = list_entry(tmp, struct dentry, d_child);
 		lustre_dump_dentry(d, recur - 1);
 	}
 }
diff --git a/drivers/staging/lustre/lustre/llite/namei.c b/drivers/staging/lustre/lustre/llite/namei.c
index 7a68c1e027e..6dfd9850926 100644
--- a/drivers/staging/lustre/lustre/llite/namei.c
+++ b/drivers/staging/lustre/lustre/llite/namei.c
@@ -167,14 +167,14 @@ static void ll_invalidate_negative_children(struct inode *dir)
 	struct ll_d_hlist_node *p;
 
 	ll_lock_dcache(dir);
-	ll_d_hlist_for_each_entry(dentry, p, &dir->i_dentry, d_alias) {
+	ll_d_hlist_for_each_entry(dentry, p, &dir->i_dentry, d_u.d_alias) {
 		spin_lock(&dentry->d_lock);
 		if (!list_empty(&dentry->d_subdirs)) {
 			struct dentry *child;
 
 			list_for_each_entry_safe(child, tmp_subdir,
 						 &dentry->d_subdirs,
-						 d_u.d_child) {
+						 d_child) {
 				if (child->d_inode == NULL)
 					d_lustre_invalidate(child, 1);
 			}
@@ -362,7 +362,7 @@ static struct dentry *ll_find_alias(struct inode *inode, struct dentry *dentry)
 	discon_alias = invalid_alias = NULL;
 
 	ll_lock_dcache(inode);
-	ll_d_hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) {
+	ll_d_hlist_for_each_entry(alias, p, &inode->i_dentry, d_u.d_alias) {
 		LASSERT(alias != dentry);
 
 		spin_lock(&alias->d_lock);
@@ -953,7 +953,7 @@ static void ll_get_child_fid(struct inode * dir, struct qstr *name,
 {
 	struct dentry *parent, *child;
 
-	parent = ll_d_hlist_entry(dir->i_dentry, struct dentry, d_alias);
+	parent = ll_d_hlist_entry(dir->i_dentry, struct dentry, d_u.d_alias);
 	child = d_lookup(parent, name);
 	if (child) {
 		if (child->d_inode)
diff --git a/drivers/staging/lustre/lustre/llite/vvp_io.c b/drivers/staging/lustre/lustre/llite/vvp_io.c
index d3f967a7813..1f453b275db 100644
--- a/drivers/staging/lustre/lustre/llite/vvp_io.c
+++ b/drivers/staging/lustre/lustre/llite/vvp_io.c
@@ -632,7 +632,7 @@ static int vvp_io_kernel_fault(struct vvp_fault_io *cfio)
 		return 0;
 	}
 
-	if (cfio->fault.ft_flags & VM_FAULT_SIGBUS) {
+	if (cfio->fault.ft_flags & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) {
 		CDEBUG(D_PAGE, "got addr %p - SIGBUS\n", vmf->virtual_address);
 		return -EFAULT;
 	}
diff --git a/drivers/staging/ozwpan/ozusbsvc1.c b/drivers/staging/ozwpan/ozusbsvc1.c
index be7ee01c50a..0c6bea0b311 100644
--- a/drivers/staging/ozwpan/ozusbsvc1.c
+++ b/drivers/staging/ozwpan/ozusbsvc1.c
@@ -326,7 +326,11 @@ static void oz_usb_handle_ep_data(struct oz_usb_ctx *usb_ctx,
 			struct oz_multiple_fixed *body =
 				(struct oz_multiple_fixed *)data_hdr;
 			u8 *data = body->data;
-			int n = (len - sizeof(struct oz_multiple_fixed)+1)
+			unsigned int n;
+			if (!body->unit_size ||
+				len < sizeof(struct oz_multiple_fixed) - 1)
+				break;
+			n = (len - (sizeof(struct oz_multiple_fixed) - 1))
 				/ body->unit_size;
 			while (n--) {
 				oz_hcd_data_ind(usb_ctx->hport, body->endpoint,
@@ -390,10 +394,15 @@ void oz_usb_rx(struct oz_pd *pd, struct oz_elt *elt)
 	case OZ_GET_DESC_RSP: {
 			struct oz_get_desc_rsp *body =
 				(struct oz_get_desc_rsp *)usb_hdr;
-			int data_len = elt->length -
-					sizeof(struct oz_get_desc_rsp) + 1;
-			u16 offs = le16_to_cpu(get_unaligned(&body->offset));
-			u16 total_size =
+			u16 offs, total_size;
+			u8 data_len;
+
+			if (elt->length < sizeof(struct oz_get_desc_rsp) - 1)
+				break;
+			data_len = elt->length -
+					(sizeof(struct oz_get_desc_rsp) - 1);
+			offs = le16_to_cpu(get_unaligned(&body->offset));
+			total_size =
 				le16_to_cpu(get_unaligned(&body->total_size));
 			oz_dbg(ON, "USB_REQ_GET_DESCRIPTOR - cnf\n");
 			oz_hcd_get_desc_cnf(usb_ctx->hport, body->req_id,
diff --git a/drivers/staging/panel/panel.c b/drivers/staging/panel/panel.c
index 6d1a32097d3..2dee1757db7 100644
--- a/drivers/staging/panel/panel.c
+++ b/drivers/staging/panel/panel.c
@@ -275,11 +275,11 @@ static unsigned char lcd_bits[LCD_PORTS][LCD_BITS][BIT_STATES];
  * LCD types
  */
 #define LCD_TYPE_NONE		0
-#define LCD_TYPE_OLD		1
-#define LCD_TYPE_KS0074		2
-#define LCD_TYPE_HANTRONIX	3
-#define LCD_TYPE_NEXCOM		4
-#define LCD_TYPE_CUSTOM		5
+#define LCD_TYPE_CUSTOM		1
+#define LCD_TYPE_OLD		2
+#define LCD_TYPE_KS0074		3
+#define LCD_TYPE_HANTRONIX	4
+#define LCD_TYPE_NEXCOM		5
 
 /*
  * keypad types
diff --git a/drivers/staging/rtl8712/rtl8712_recv.c b/drivers/staging/rtl8712/rtl8712_recv.c
index b2780620926..ff7583d97bf 100644
--- a/drivers/staging/rtl8712/rtl8712_recv.c
+++ b/drivers/staging/rtl8712/rtl8712_recv.c
@@ -1068,7 +1068,8 @@ static int recvbuf2recvframe(struct _adapter *padapter, struct sk_buff *pskb)
 		/* for first fragment packet, driver need allocate 1536 +
 		 * drvinfo_sz + RXDESC_SIZE to defrag packet. */
 		if ((mf == 1) && (frag == 0))
-			alloc_sz = 1658;/*1658+6=1664, 1664 is 128 alignment.*/
+			/*1658+6=1664, 1664 is 128 alignment.*/
+			alloc_sz = max_t(u16, tmp_len, 1658);
 		else
 			alloc_sz = tmp_len;
 		/* 2 is for IP header 4 bytes alignment in QoS packet case.
diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c
index 54e16f40d8e..ea240512cbb 100644
--- a/drivers/staging/vt6655/device_main.c
+++ b/drivers/staging/vt6655/device_main.c
@@ -1340,6 +1340,10 @@ static int device_rx_srv(struct vnt_private *pDevice, unsigned int uIdx)
 	     pRD = pRD->next) {
 		if (works++ > 15)
 			break;
+
+		if (!pRD->pRDInfo->skb)
+			break;
+
 		if (device_receive_frame(pDevice, pRD)) {
 			if (!device_alloc_rx_buf(pDevice, pRD)) {
 				dev_err(&pDevice->pcid->dev,
diff --git a/drivers/staging/vt6655/rf.c b/drivers/staging/vt6655/rf.c
index e505af91bfd..fb62e8dd11b 100644
--- a/drivers/staging/vt6655/rf.c
+++ b/drivers/staging/vt6655/rf.c
@@ -923,6 +923,7 @@ bool RFbSetPower(
 		break;
 	case RATE_6M:
 	case RATE_9M:
+	case RATE_12M:
 	case RATE_18M:
 		byPwr = pDevice->abyOFDMPwrTbl[uCH];
 		if (pDevice->byRFType == RF_UW2452)
diff --git a/drivers/staging/vt6656/rf.c b/drivers/staging/vt6656/rf.c
index c42cde59f59..c4286ccac32 100644
--- a/drivers/staging/vt6656/rf.c
+++ b/drivers/staging/vt6656/rf.c
@@ -640,6 +640,7 @@ int vnt_rf_setpower(struct vnt_private *priv, u32 rate, u32 channel)
 		break;
 	case RATE_6M:
 	case RATE_9M:
+	case RATE_12M:
 	case RATE_18M:
 	case RATE_24M:
 	case RATE_36M:
diff --git a/drivers/staging/vt6656/rxtx.c b/drivers/staging/vt6656/rxtx.c
index ea5140ab2b4..b3500fd3139 100644
--- a/drivers/staging/vt6656/rxtx.c
+++ b/drivers/staging/vt6656/rxtx.c
@@ -800,10 +800,18 @@ int vnt_tx_packet(struct vnt_private *priv, struct sk_buff *skb)
 		vnt_schedule_command(priv, WLAN_CMD_SETPOWER);
 	}
 
-	if (current_rate > RATE_11M)
-		pkt_type = priv->packet_type;
-	else
+	if (current_rate > RATE_11M) {
+		if (info->band == IEEE80211_BAND_5GHZ) {
+			pkt_type = PK_TYPE_11A;
+		} else {
+			if (tx_rate->flags & IEEE80211_TX_RC_USE_CTS_PROTECT)
+				pkt_type = PK_TYPE_11GB;
+			else
+				pkt_type = PK_TYPE_11GA;
+		}
+	} else {
 		pkt_type = PK_TYPE_11B;
+	}
 
 	spin_lock_irqsave(&priv->lock, flags);
 
diff --git a/drivers/switch/Kconfig b/drivers/switch/Kconfig
new file mode 100644
index 00000000000..19404b6f777
--- /dev/null
+++ b/drivers/switch/Kconfig
@@ -0,0 +1,15 @@
+menuconfig SWITCH
+	tristate "Switch class support"
+	help
+	  Say Y here to enable switch class support. This allows
+	  monitoring switches by userspace via sysfs and uevent.
+
+if SWITCH
+
+config SWITCH_GPIO
+	tristate "GPIO Swith support"
+	depends on GPIOLIB
+	help
+	  Say Y here to enable GPIO based switch support.
+
+endif # SWITCH
diff --git a/drivers/switch/Makefile b/drivers/switch/Makefile
new file mode 100644
index 00000000000..f7606ed4a71
--- /dev/null
+++ b/drivers/switch/Makefile
@@ -0,0 +1,4 @@
+# Switch Class Driver
+obj-$(CONFIG_SWITCH)		+= switch_class.o
+obj-$(CONFIG_SWITCH_GPIO)	+= switch_gpio.o
+
diff --git a/drivers/switch/switch_class.c b/drivers/switch/switch_class.c
new file mode 100644
index 00000000000..e373b625806
--- /dev/null
+++ b/drivers/switch/switch_class.c
@@ -0,0 +1,174 @@
+/*
+ *  drivers/switch/switch_class.c
+ *
+ * Copyright (C) 2008 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+*/
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/fs.h>
+#include <linux/err.h>
+#include <linux/switch.h>
+
+struct class *switch_class;
+static atomic_t device_count;
+
+static ssize_t state_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	struct switch_dev *sdev = (struct switch_dev *)
+		dev_get_drvdata(dev);
+
+	if (sdev->print_state) {
+		int ret = sdev->print_state(sdev, buf);
+		if (ret >= 0)
+			return ret;
+	}
+	return sprintf(buf, "%d\n", sdev->state);
+}
+
+static ssize_t name_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	struct switch_dev *sdev = (struct switch_dev *)
+		dev_get_drvdata(dev);
+
+	if (sdev->print_name) {
+		int ret = sdev->print_name(sdev, buf);
+		if (ret >= 0)
+			return ret;
+	}
+	return sprintf(buf, "%s\n", sdev->name);
+}
+
+static DEVICE_ATTR(state, S_IRUGO, state_show, NULL);
+static DEVICE_ATTR(name, S_IRUGO, name_show, NULL);
+
+void switch_set_state(struct switch_dev *sdev, int state)
+{
+	char name_buf[120];
+	char state_buf[120];
+	char *prop_buf;
+	char *envp[3];
+	int env_offset = 0;
+	int length;
+
+	if (sdev->state != state) {
+		sdev->state = state;
+
+		prop_buf = (char *)get_zeroed_page(GFP_KERNEL);
+		if (prop_buf) {
+			length = name_show(sdev->dev, NULL, prop_buf);
+			if (length > 0) {
+				if (prop_buf[length - 1] == '\n')
+					prop_buf[length - 1] = 0;
+				snprintf(name_buf, sizeof(name_buf),
+					"SWITCH_NAME=%s", prop_buf);
+				envp[env_offset++] = name_buf;
+			}
+			length = state_show(sdev->dev, NULL, prop_buf);
+			if (length > 0) {
+				if (prop_buf[length - 1] == '\n')
+					prop_buf[length - 1] = 0;
+				snprintf(state_buf, sizeof(state_buf),
+					"SWITCH_STATE=%s", prop_buf);
+				envp[env_offset++] = state_buf;
+			}
+			envp[env_offset] = NULL;
+			kobject_uevent_env(&sdev->dev->kobj, KOBJ_CHANGE, envp);
+			free_page((unsigned long)prop_buf);
+		} else {
+			printk(KERN_ERR "out of memory in switch_set_state\n");
+			kobject_uevent(&sdev->dev->kobj, KOBJ_CHANGE);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(switch_set_state);
+
+static int create_switch_class(void)
+{
+	if (!switch_class) {
+		switch_class = class_create(THIS_MODULE, "switch");
+		if (IS_ERR(switch_class))
+			return PTR_ERR(switch_class);
+		atomic_set(&device_count, 0);
+	}
+
+	return 0;
+}
+
+int switch_dev_register(struct switch_dev *sdev)
+{
+	int ret;
+
+	if (!switch_class) {
+		ret = create_switch_class();
+		if (ret < 0)
+			return ret;
+	}
+
+	sdev->index = atomic_inc_return(&device_count);
+	sdev->dev = device_create(switch_class, NULL,
+		MKDEV(0, sdev->index), NULL, sdev->name);
+	if (IS_ERR(sdev->dev))
+		return PTR_ERR(sdev->dev);
+
+	ret = device_create_file(sdev->dev, &dev_attr_state);
+	if (ret < 0)
+		goto err_create_file_1;
+	ret = device_create_file(sdev->dev, &dev_attr_name);
+	if (ret < 0)
+		goto err_create_file_2;
+
+	dev_set_drvdata(sdev->dev, sdev);
+	sdev->state = 0;
+	return 0;
+
+err_create_file_2:
+	device_remove_file(sdev->dev, &dev_attr_state);
+err_create_file_1:
+	device_destroy(switch_class, MKDEV(0, sdev->index));
+	printk(KERN_ERR "switch: Failed to register driver %s\n", sdev->name);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(switch_dev_register);
+
+void switch_dev_unregister(struct switch_dev *sdev)
+{
+	device_remove_file(sdev->dev, &dev_attr_name);
+	device_remove_file(sdev->dev, &dev_attr_state);
+	device_destroy(switch_class, MKDEV(0, sdev->index));
+	dev_set_drvdata(sdev->dev, NULL);
+}
+EXPORT_SYMBOL_GPL(switch_dev_unregister);
+
+static int __init switch_class_init(void)
+{
+	return create_switch_class();
+}
+
+static void __exit switch_class_exit(void)
+{
+	class_destroy(switch_class);
+}
+
+module_init(switch_class_init);
+module_exit(switch_class_exit);
+
+MODULE_AUTHOR("Mike Lockwood <lockwood@android.com>");
+MODULE_DESCRIPTION("Switch class driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/switch/switch_gpio.c b/drivers/switch/switch_gpio.c
new file mode 100644
index 00000000000..621d62d20c9
--- /dev/null
+++ b/drivers/switch/switch_gpio.c
@@ -0,0 +1,172 @@
+/*
+ *  drivers/switch/switch_gpio.c
+ *
+ * Copyright (C) 2008 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+*/
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/switch.h>
+#include <linux/workqueue.h>
+#include <linux/gpio.h>
+
+struct gpio_switch_data {
+	struct switch_dev sdev;
+	unsigned gpio;
+	const char *name_on;
+	const char *name_off;
+	const char *state_on;
+	const char *state_off;
+	int irq;
+	struct work_struct work;
+};
+
+static void gpio_switch_work(struct work_struct *work)
+{
+	int state;
+	struct gpio_switch_data	*data =
+		container_of(work, struct gpio_switch_data, work);
+
+	state = gpio_get_value(data->gpio);
+	switch_set_state(&data->sdev, state);
+}
+
+static irqreturn_t gpio_irq_handler(int irq, void *dev_id)
+{
+	struct gpio_switch_data *switch_data =
+	    (struct gpio_switch_data *)dev_id;
+
+	schedule_work(&switch_data->work);
+	return IRQ_HANDLED;
+}
+
+static ssize_t switch_gpio_print_state(struct switch_dev *sdev, char *buf)
+{
+	struct gpio_switch_data	*switch_data =
+		container_of(sdev, struct gpio_switch_data, sdev);
+	const char *state;
+	if (switch_get_state(sdev))
+		state = switch_data->state_on;
+	else
+		state = switch_data->state_off;
+
+	if (state)
+		return sprintf(buf, "%s\n", state);
+	return -1;
+}
+
+static int gpio_switch_probe(struct platform_device *pdev)
+{
+	struct gpio_switch_platform_data *pdata = pdev->dev.platform_data;
+	struct gpio_switch_data *switch_data;
+	int ret = 0;
+
+	if (!pdata)
+		return -EBUSY;
+
+	switch_data = kzalloc(sizeof(struct gpio_switch_data), GFP_KERNEL);
+	if (!switch_data)
+		return -ENOMEM;
+
+	switch_data->sdev.name = pdata->name;
+	switch_data->gpio = pdata->gpio;
+	switch_data->name_on = pdata->name_on;
+	switch_data->name_off = pdata->name_off;
+	switch_data->state_on = pdata->state_on;
+	switch_data->state_off = pdata->state_off;
+	switch_data->sdev.print_state = switch_gpio_print_state;
+
+	ret = switch_dev_register(&switch_data->sdev);
+	if (ret < 0)
+		goto err_switch_dev_register;
+
+	ret = gpio_request(switch_data->gpio, pdev->name);
+	if (ret < 0)
+		goto err_request_gpio;
+
+	ret = gpio_direction_input(switch_data->gpio);
+	if (ret < 0)
+		goto err_set_gpio_input;
+
+	INIT_WORK(&switch_data->work, gpio_switch_work);
+
+	switch_data->irq = gpio_to_irq(switch_data->gpio);
+	if (switch_data->irq < 0) {
+		ret = switch_data->irq;
+		goto err_detect_irq_num_failed;
+	}
+
+	ret = request_irq(switch_data->irq, gpio_irq_handler,
+			  IRQF_TRIGGER_LOW, pdev->name, switch_data);
+	if (ret < 0)
+		goto err_request_irq;
+
+	/* Perform initial detection */
+	gpio_switch_work(&switch_data->work);
+
+	return 0;
+
+err_request_irq:
+err_detect_irq_num_failed:
+err_set_gpio_input:
+	gpio_free(switch_data->gpio);
+err_request_gpio:
+	switch_dev_unregister(&switch_data->sdev);
+err_switch_dev_register:
+	kfree(switch_data);
+
+	return ret;
+}
+
+static int gpio_switch_remove(struct platform_device *pdev)
+{
+	struct gpio_switch_data *switch_data = platform_get_drvdata(pdev);
+
+	cancel_work_sync(&switch_data->work);
+	gpio_free(switch_data->gpio);
+	switch_dev_unregister(&switch_data->sdev);
+	kfree(switch_data);
+
+	return 0;
+}
+
+static struct platform_driver gpio_switch_driver = {
+	.probe		= gpio_switch_probe,
+	.remove		= gpio_switch_remove,
+	.driver		= {
+		.name	= "switch-gpio",
+		.owner	= THIS_MODULE,
+	},
+};
+
+static int __init gpio_switch_init(void)
+{
+	return platform_driver_register(&gpio_switch_driver);
+}
+
+static void __exit gpio_switch_exit(void)
+{
+	platform_driver_unregister(&gpio_switch_driver);
+}
+
+module_init(gpio_switch_init);
+module_exit(gpio_switch_exit);
+
+MODULE_AUTHOR("Mike Lockwood <lockwood@android.com>");
+MODULE_DESCRIPTION("GPIO Switch driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 73e58d22e32..3c5dd976247 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -537,7 +537,7 @@ static struct iscsit_transport iscsi_target_transport = {
 
 static int __init iscsi_target_init_module(void)
 {
-	int ret = 0;
+	int ret = 0, size;
 
 	pr_debug("iSCSI-Target "ISCSIT_VERSION"\n");
 
@@ -546,6 +546,7 @@ static int __init iscsi_target_init_module(void)
 		pr_err("Unable to allocate memory for iscsit_global\n");
 		return -1;
 	}
+	spin_lock_init(&iscsit_global->ts_bitmap_lock);
 	mutex_init(&auth_id_lock);
 	spin_lock_init(&sess_idr_lock);
 	idr_init(&tiqn_idr);
@@ -555,15 +556,11 @@ static int __init iscsi_target_init_module(void)
 	if (ret < 0)
 		goto out;
 
-	ret = iscsi_thread_set_init();
-	if (ret < 0)
+	size = BITS_TO_LONGS(ISCSIT_BITMAP_BITS) * sizeof(long);
+	iscsit_global->ts_bitmap = vzalloc(size);
+	if (!iscsit_global->ts_bitmap) {
+		pr_err("Unable to allocate iscsit_global->ts_bitmap\n");
 		goto configfs_out;
-
-	if (iscsi_allocate_thread_sets(TARGET_THREAD_SET_COUNT) !=
-			TARGET_THREAD_SET_COUNT) {
-		pr_err("iscsi_allocate_thread_sets() returned"
-			" unexpected value!\n");
-		goto ts_out1;
 	}
 
 	lio_qr_cache = kmem_cache_create("lio_qr_cache",
@@ -572,7 +569,7 @@ static int __init iscsi_target_init_module(void)
 	if (!lio_qr_cache) {
 		pr_err("nable to kmem_cache_create() for"
 				" lio_qr_cache\n");
-		goto ts_out2;
+		goto bitmap_out;
 	}
 
 	lio_dr_cache = kmem_cache_create("lio_dr_cache",
@@ -616,10 +613,8 @@ dr_out:
 	kmem_cache_destroy(lio_dr_cache);
 qr_out:
 	kmem_cache_destroy(lio_qr_cache);
-ts_out2:
-	iscsi_deallocate_thread_sets();
-ts_out1:
-	iscsi_thread_set_free();
+bitmap_out:
+	vfree(iscsit_global->ts_bitmap);
 configfs_out:
 	iscsi_target_deregister_configfs();
 out:
@@ -629,8 +624,6 @@ out:
 
 static void __exit iscsi_target_cleanup_module(void)
 {
-	iscsi_deallocate_thread_sets();
-	iscsi_thread_set_free();
 	iscsit_release_discovery_tpg();
 	iscsit_unregister_transport(&iscsi_target_transport);
 	kmem_cache_destroy(lio_qr_cache);
@@ -640,6 +633,7 @@ static void __exit iscsi_target_cleanup_module(void)
 
 	iscsi_target_deregister_configfs();
 
+	vfree(iscsit_global->ts_bitmap);
 	kfree(iscsit_global);
 }
 
@@ -1184,7 +1178,7 @@ iscsit_handle_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	 * traditional iSCSI block I/O.
 	 */
 	if (iscsit_allocate_iovecs(cmd) < 0) {
-		return iscsit_add_reject_cmd(cmd,
+		return iscsit_reject_cmd(cmd,
 				ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf);
 	}
 	immed_data = cmd->immediate_data;
@@ -3680,17 +3674,16 @@ static int iscsit_send_reject(
 
 void iscsit_thread_get_cpumask(struct iscsi_conn *conn)
 {
-	struct iscsi_thread_set *ts = conn->thread_set;
 	int ord, cpu;
 	/*
-	 * thread_id is assigned from iscsit_global->ts_bitmap from
-	 * within iscsi_thread_set.c:iscsi_allocate_thread_sets()
+	 * bitmap_id is assigned from iscsit_global->ts_bitmap from
+	 * within iscsit_start_kthreads()
 	 *
-	 * Here we use thread_id to determine which CPU that this
-	 * iSCSI connection's iscsi_thread_set will be scheduled to
+	 * Here we use bitmap_id to determine which CPU that this
+	 * iSCSI connection's RX/TX threads will be scheduled to
 	 * execute upon.
 	 */
-	ord = ts->thread_id % cpumask_weight(cpu_online_mask);
+	ord = conn->bitmap_id % cpumask_weight(cpu_online_mask);
 	for_each_online_cpu(cpu) {
 		if (ord-- == 0) {
 			cpumask_set_cpu(cpu, conn->conn_cpumask);
@@ -3879,7 +3872,7 @@ check_rsp_state:
 	switch (state) {
 	case ISTATE_SEND_LOGOUTRSP:
 		if (!iscsit_logout_post_handler(cmd, conn))
-			goto restart;
+			return -ECONNRESET;
 		/* fall through */
 	case ISTATE_SEND_STATUS:
 	case ISTATE_SEND_ASYNCMSG:
@@ -3907,8 +3900,6 @@ check_rsp_state:
 
 err:
 	return -1;
-restart:
-	return -EAGAIN;
 }
 
 static int iscsit_handle_response_queue(struct iscsi_conn *conn)
@@ -3935,21 +3926,13 @@ static int iscsit_handle_response_queue(struct iscsi_conn *conn)
 int iscsi_target_tx_thread(void *arg)
 {
 	int ret = 0;
-	struct iscsi_conn *conn;
-	struct iscsi_thread_set *ts = arg;
+	struct iscsi_conn *conn = arg;
 	/*
 	 * Allow ourselves to be interrupted by SIGINT so that a
 	 * connection recovery / failure event can be triggered externally.
 	 */
 	allow_signal(SIGINT);
 
-restart:
-	conn = iscsi_tx_thread_pre_handler(ts);
-	if (!conn)
-		goto out;
-
-	ret = 0;
-
 	while (!kthread_should_stop()) {
 		/*
 		 * Ensure that both TX and RX per connection kthreads
@@ -3958,11 +3941,9 @@ restart:
 		iscsit_thread_check_cpumask(conn, current, 1);
 
 		wait_event_interruptible(conn->queues_wq,
-					 !iscsit_conn_all_queues_empty(conn) ||
-					 ts->status == ISCSI_THREAD_SET_RESET);
+					 !iscsit_conn_all_queues_empty(conn));
 
-		if ((ts->status == ISCSI_THREAD_SET_RESET) ||
-		     signal_pending(current))
+		if (signal_pending(current))
 			goto transport_err;
 
 get_immediate:
@@ -3973,15 +3954,14 @@ get_immediate:
 		ret = iscsit_handle_response_queue(conn);
 		if (ret == 1)
 			goto get_immediate;
-		else if (ret == -EAGAIN)
-			goto restart;
+		else if (ret == -ECONNRESET)
+			goto out;
 		else if (ret < 0)
 			goto transport_err;
 	}
 
 transport_err:
 	iscsit_take_action_for_connection_exit(conn);
-	goto restart;
 out:
 	return 0;
 }
@@ -4070,8 +4050,7 @@ int iscsi_target_rx_thread(void *arg)
 	int ret;
 	u8 buffer[ISCSI_HDR_LEN], opcode;
 	u32 checksum = 0, digest = 0;
-	struct iscsi_conn *conn = NULL;
-	struct iscsi_thread_set *ts = arg;
+	struct iscsi_conn *conn = arg;
 	struct kvec iov;
 	/*
 	 * Allow ourselves to be interrupted by SIGINT so that a
@@ -4079,11 +4058,6 @@ int iscsi_target_rx_thread(void *arg)
 	 */
 	allow_signal(SIGINT);
 
-restart:
-	conn = iscsi_rx_thread_pre_handler(ts);
-	if (!conn)
-		goto out;
-
 	if (conn->conn_transport->transport_type == ISCSI_INFINIBAND) {
 		struct completion comp;
 		int rc;
@@ -4093,7 +4067,7 @@ restart:
 		if (rc < 0)
 			goto transport_err;
 
-		goto out;
+		goto transport_err;
 	}
 
 	while (!kthread_should_stop()) {
@@ -4169,8 +4143,6 @@ transport_err:
 	if (!signal_pending(current))
 		atomic_set(&conn->transport_failed, 1);
 	iscsit_take_action_for_connection_exit(conn);
-	goto restart;
-out:
 	return 0;
 }
 
@@ -4220,13 +4192,36 @@ int iscsit_close_connection(
 	pr_debug("Closing iSCSI connection CID %hu on SID:"
 		" %u\n", conn->cid, sess->sid);
 	/*
-	 * Always up conn_logout_comp just in case the RX Thread is sleeping
-	 * and the logout response never got sent because the connection
-	 * failed.
+	 * Always up conn_logout_comp for the traditional TCP case just in case
+	 * the RX Thread in iscsi_target_rx_opcode() is sleeping and the logout
+	 * response never got sent because the connection failed.
+	 *
+	 * However for iser-target, isert_wait4logout() is using conn_logout_comp
+	 * to signal logout response TX interrupt completion.  Go ahead and skip
+	 * this for iser since isert_rx_opcode() does not wait on logout failure,
+	 * and to avoid iscsi_conn pointer dereference in iser-target code.
 	 */
-	complete(&conn->conn_logout_comp);
+	if (conn->conn_transport->transport_type == ISCSI_TCP)
+		complete(&conn->conn_logout_comp);
+
+	if (!strcmp(current->comm, ISCSI_RX_THREAD_NAME)) {
+		if (conn->tx_thread &&
+		    cmpxchg(&conn->tx_thread_active, true, false)) {
+			send_sig(SIGINT, conn->tx_thread, 1);
+			kthread_stop(conn->tx_thread);
+		}
+	} else if (!strcmp(current->comm, ISCSI_TX_THREAD_NAME)) {
+		if (conn->rx_thread &&
+		    cmpxchg(&conn->rx_thread_active, true, false)) {
+			send_sig(SIGINT, conn->rx_thread, 1);
+			kthread_stop(conn->rx_thread);
+		}
+	}
 
-	iscsi_release_thread_set(conn);
+	spin_lock(&iscsit_global->ts_bitmap_lock);
+	bitmap_release_region(iscsit_global->ts_bitmap, conn->bitmap_id,
+			      get_order(1));
+	spin_unlock(&iscsit_global->ts_bitmap_lock);
 
 	iscsit_stop_timers_for_cmds(conn);
 	iscsit_stop_nopin_response_timer(conn);
@@ -4504,15 +4499,13 @@ static void iscsit_logout_post_handler_closesession(
 	struct iscsi_conn *conn)
 {
 	struct iscsi_session *sess = conn->sess;
-
-	iscsi_set_thread_clear(conn, ISCSI_CLEAR_TX_THREAD);
-	iscsi_set_thread_set_signal(conn, ISCSI_SIGNAL_TX_THREAD);
+	int sleep = cmpxchg(&conn->tx_thread_active, true, false);
 
 	atomic_set(&conn->conn_logout_remove, 0);
 	complete(&conn->conn_logout_comp);
 
 	iscsit_dec_conn_usage_count(conn);
-	iscsit_stop_session(sess, 1, 1);
+	iscsit_stop_session(sess, sleep, sleep);
 	iscsit_dec_session_usage_count(sess);
 	target_put_session(sess->se_sess);
 }
@@ -4520,13 +4513,12 @@ static void iscsit_logout_post_handler_closesession(
 static void iscsit_logout_post_handler_samecid(
 	struct iscsi_conn *conn)
 {
-	iscsi_set_thread_clear(conn, ISCSI_CLEAR_TX_THREAD);
-	iscsi_set_thread_set_signal(conn, ISCSI_SIGNAL_TX_THREAD);
+	int sleep = cmpxchg(&conn->tx_thread_active, true, false);
 
 	atomic_set(&conn->conn_logout_remove, 0);
 	complete(&conn->conn_logout_comp);
 
-	iscsit_cause_connection_reinstatement(conn, 1);
+	iscsit_cause_connection_reinstatement(conn, sleep);
 	iscsit_dec_conn_usage_count(conn);
 }
 
diff --git a/drivers/target/iscsi/iscsi_target_core.h b/drivers/target/iscsi/iscsi_target_core.h
index 302eb3b7871..2423f27e467 100644
--- a/drivers/target/iscsi/iscsi_target_core.h
+++ b/drivers/target/iscsi/iscsi_target_core.h
@@ -602,6 +602,11 @@ struct iscsi_conn {
 	struct iscsi_session	*sess;
 	/* Pointer to thread_set in use for this conn's threads */
 	struct iscsi_thread_set	*thread_set;
+	int			bitmap_id;
+	int			rx_thread_active;
+	struct task_struct	*rx_thread;
+	int			tx_thread_active;
+	struct task_struct	*tx_thread;
 	/* list_head for session connection list */
 	struct list_head	conn_list;
 } ____cacheline_aligned;
@@ -872,10 +877,12 @@ struct iscsit_global {
 	/* Unique identifier used for the authentication daemon */
 	u32			auth_id;
 	u32			inactive_ts;
+#define ISCSIT_BITMAP_BITS	262144
 	/* Thread Set bitmap count */
 	int			ts_bitmap_count;
 	/* Thread Set bitmap pointer */
 	unsigned long		*ts_bitmap;
+	spinlock_t		ts_bitmap_lock;
 	/* Used for iSCSI discovery session authentication */
 	struct iscsi_node_acl	discovery_acl;
 	struct iscsi_portal_group	*discovery_tpg;
diff --git a/drivers/target/iscsi/iscsi_target_erl0.c b/drivers/target/iscsi/iscsi_target_erl0.c
index a0ae5fc0ad7..87f68725872 100644
--- a/drivers/target/iscsi/iscsi_target_erl0.c
+++ b/drivers/target/iscsi/iscsi_target_erl0.c
@@ -860,7 +860,10 @@ void iscsit_connection_reinstatement_rcfr(struct iscsi_conn *conn)
 	}
 	spin_unlock_bh(&conn->state_lock);
 
-	iscsi_thread_set_force_reinstatement(conn);
+	if (conn->tx_thread && conn->tx_thread_active)
+		send_sig(SIGINT, conn->tx_thread, 1);
+	if (conn->rx_thread && conn->rx_thread_active)
+		send_sig(SIGINT, conn->rx_thread, 1);
 
 sleep:
 	wait_for_completion(&conn->conn_wait_rcfr_comp);
@@ -885,10 +888,10 @@ void iscsit_cause_connection_reinstatement(struct iscsi_conn *conn, int sleep)
 		return;
 	}
 
-	if (iscsi_thread_set_force_reinstatement(conn) < 0) {
-		spin_unlock_bh(&conn->state_lock);
-		return;
-	}
+	if (conn->tx_thread && conn->tx_thread_active)
+		send_sig(SIGINT, conn->tx_thread, 1);
+	if (conn->rx_thread && conn->rx_thread_active)
+		send_sig(SIGINT, conn->rx_thread, 1);
 
 	atomic_set(&conn->connection_reinstatement, 1);
 	if (!sleep) {
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 480f2e0ecc1..2d87abc6b38 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -281,7 +281,6 @@ static int iscsi_login_zero_tsih_s1(
 {
 	struct iscsi_session *sess = NULL;
 	struct iscsi_login_req *pdu = (struct iscsi_login_req *)buf;
-	enum target_prot_op sup_pro_ops;
 	int ret;
 
 	sess = kzalloc(sizeof(struct iscsi_session), GFP_KERNEL);
@@ -343,9 +342,8 @@ static int iscsi_login_zero_tsih_s1(
 		kfree(sess);
 		return -ENOMEM;
 	}
-	sup_pro_ops = conn->conn_transport->iscsit_get_sup_prot_ops(conn);
 
-	sess->se_sess = transport_init_session(sup_pro_ops);
+	sess->se_sess = transport_init_session(TARGET_PROT_NORMAL);
 	if (IS_ERR(sess->se_sess)) {
 		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
 				ISCSI_LOGIN_STATUS_NO_RESOURCES);
@@ -701,6 +699,51 @@ static void iscsi_post_login_start_timers(struct iscsi_conn *conn)
 		iscsit_start_nopin_timer(conn);
 }
 
+int iscsit_start_kthreads(struct iscsi_conn *conn)
+{
+	int ret = 0;
+
+	spin_lock(&iscsit_global->ts_bitmap_lock);
+	conn->bitmap_id = bitmap_find_free_region(iscsit_global->ts_bitmap,
+					ISCSIT_BITMAP_BITS, get_order(1));
+	spin_unlock(&iscsit_global->ts_bitmap_lock);
+
+	if (conn->bitmap_id < 0) {
+		pr_err("bitmap_find_free_region() failed for"
+		       " iscsit_start_kthreads()\n");
+		return -ENOMEM;
+	}
+
+	conn->tx_thread = kthread_run(iscsi_target_tx_thread, conn,
+				      "%s", ISCSI_TX_THREAD_NAME);
+	if (IS_ERR(conn->tx_thread)) {
+		pr_err("Unable to start iscsi_target_tx_thread\n");
+		ret = PTR_ERR(conn->tx_thread);
+		goto out_bitmap;
+	}
+	conn->tx_thread_active = true;
+
+	conn->rx_thread = kthread_run(iscsi_target_rx_thread, conn,
+				      "%s", ISCSI_RX_THREAD_NAME);
+	if (IS_ERR(conn->rx_thread)) {
+		pr_err("Unable to start iscsi_target_rx_thread\n");
+		ret = PTR_ERR(conn->rx_thread);
+		goto out_tx;
+	}
+	conn->rx_thread_active = true;
+
+	return 0;
+out_tx:
+	kthread_stop(conn->tx_thread);
+	conn->tx_thread_active = false;
+out_bitmap:
+	spin_lock(&iscsit_global->ts_bitmap_lock);
+	bitmap_release_region(iscsit_global->ts_bitmap, conn->bitmap_id,
+			      get_order(1));
+	spin_unlock(&iscsit_global->ts_bitmap_lock);
+	return ret;
+}
+
 int iscsi_post_login_handler(
 	struct iscsi_np *np,
 	struct iscsi_conn *conn,
@@ -711,7 +754,7 @@ int iscsi_post_login_handler(
 	struct se_session *se_sess = sess->se_sess;
 	struct iscsi_portal_group *tpg = sess->tpg;
 	struct se_portal_group *se_tpg = &tpg->tpg_se_tpg;
-	struct iscsi_thread_set *ts;
+	int rc;
 
 	iscsit_inc_conn_usage_count(conn);
 
@@ -726,7 +769,6 @@ int iscsi_post_login_handler(
 	/*
 	 * SCSI Initiator -> SCSI Target Port Mapping
 	 */
-	ts = iscsi_get_thread_set();
 	if (!zero_tsih) {
 		iscsi_set_session_parameters(sess->sess_ops,
 				conn->param_list, 0);
@@ -753,9 +795,11 @@ int iscsi_post_login_handler(
 			sess->sess_ops->InitiatorName);
 		spin_unlock_bh(&sess->conn_lock);
 
-		iscsi_post_login_start_timers(conn);
+		rc = iscsit_start_kthreads(conn);
+		if (rc)
+			return rc;
 
-		iscsi_activate_thread_set(conn, ts);
+		iscsi_post_login_start_timers(conn);
 		/*
 		 * Determine CPU mask to ensure connection's RX and TX kthreads
 		 * are scheduled on the same CPU.
@@ -812,8 +856,11 @@ int iscsi_post_login_handler(
 		" iSCSI Target Portal Group: %hu\n", tpg->nsessions, tpg->tpgt);
 	spin_unlock_bh(&se_tpg->session_lock);
 
+	rc = iscsit_start_kthreads(conn);
+	if (rc)
+		return rc;
+
 	iscsi_post_login_start_timers(conn);
-	iscsi_activate_thread_set(conn, ts);
 	/*
 	 * Determine CPU mask to ensure connection's RX and TX kthreads
 	 * are scheduled on the same CPU.
@@ -1204,6 +1251,9 @@ old_sess_out:
 		conn->sock = NULL;
 	}
 
+	if (conn->conn_transport->iscsit_wait_conn)
+		conn->conn_transport->iscsit_wait_conn(conn);
+
 	if (conn->conn_transport->iscsit_free_conn)
 		conn->conn_transport->iscsit_free_conn(conn);
 
@@ -1364,6 +1414,9 @@ static int __iscsi_target_login_thread(struct iscsi_np *np)
 	}
 	login->zero_tsih = zero_tsih;
 
+	conn->sess->se_sess->sup_prot_ops =
+		conn->conn_transport->iscsit_get_sup_prot_ops(conn);
+
 	tpg = conn->tpg;
 	if (!tpg) {
 		pr_err("Unable to locate struct iscsi_conn->tpg\n");
diff --git a/drivers/target/iscsi/iscsi_target_tq.c b/drivers/target/iscsi/iscsi_target_tq.c
index 601e9cc61e9..bb2890e79ca 100644
--- a/drivers/target/iscsi/iscsi_target_tq.c
+++ b/drivers/target/iscsi/iscsi_target_tq.c
@@ -24,36 +24,22 @@
 #include "iscsi_target_tq.h"
 #include "iscsi_target.h"
 
-static LIST_HEAD(active_ts_list);
 static LIST_HEAD(inactive_ts_list);
-static DEFINE_SPINLOCK(active_ts_lock);
 static DEFINE_SPINLOCK(inactive_ts_lock);
 static DEFINE_SPINLOCK(ts_bitmap_lock);
 
-static void iscsi_add_ts_to_active_list(struct iscsi_thread_set *ts)
-{
-	spin_lock(&active_ts_lock);
-	list_add_tail(&ts->ts_list, &active_ts_list);
-	iscsit_global->active_ts++;
-	spin_unlock(&active_ts_lock);
-}
-
 static void iscsi_add_ts_to_inactive_list(struct iscsi_thread_set *ts)
 {
+	if (!list_empty(&ts->ts_list)) {
+		WARN_ON(1);
+		return;
+	}
 	spin_lock(&inactive_ts_lock);
 	list_add_tail(&ts->ts_list, &inactive_ts_list);
 	iscsit_global->inactive_ts++;
 	spin_unlock(&inactive_ts_lock);
 }
 
-static void iscsi_del_ts_from_active_list(struct iscsi_thread_set *ts)
-{
-	spin_lock(&active_ts_lock);
-	list_del(&ts->ts_list);
-	iscsit_global->active_ts--;
-	spin_unlock(&active_ts_lock);
-}
-
 static struct iscsi_thread_set *iscsi_get_ts_from_inactive_list(void)
 {
 	struct iscsi_thread_set *ts;
@@ -66,7 +52,7 @@ static struct iscsi_thread_set *iscsi_get_ts_from_inactive_list(void)
 
 	ts = list_first_entry(&inactive_ts_list, struct iscsi_thread_set, ts_list);
 
-	list_del(&ts->ts_list);
+	list_del_init(&ts->ts_list);
 	iscsit_global->inactive_ts--;
 	spin_unlock(&inactive_ts_lock);
 
@@ -204,8 +190,6 @@ static void iscsi_deallocate_extra_thread_sets(void)
 
 void iscsi_activate_thread_set(struct iscsi_conn *conn, struct iscsi_thread_set *ts)
 {
-	iscsi_add_ts_to_active_list(ts);
-
 	spin_lock_bh(&ts->ts_state_lock);
 	conn->thread_set = ts;
 	ts->conn = conn;
@@ -397,7 +381,6 @@ struct iscsi_conn *iscsi_rx_thread_pre_handler(struct iscsi_thread_set *ts)
 
 	if (ts->delay_inactive && (--ts->thread_count == 0)) {
 		spin_unlock_bh(&ts->ts_state_lock);
-		iscsi_del_ts_from_active_list(ts);
 
 		if (!iscsit_global->in_shutdown)
 			iscsi_deallocate_extra_thread_sets();
@@ -452,7 +435,6 @@ struct iscsi_conn *iscsi_tx_thread_pre_handler(struct iscsi_thread_set *ts)
 
 	if (ts->delay_inactive && (--ts->thread_count == 0)) {
 		spin_unlock_bh(&ts->ts_state_lock);
-		iscsi_del_ts_from_active_list(ts);
 
 		if (!iscsit_global->in_shutdown)
 			iscsi_deallocate_extra_thread_sets();
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index ce87ce9bdb9..0b68c2ebce9 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -1358,15 +1358,15 @@ static int iscsit_do_tx_data(
 	struct iscsi_conn *conn,
 	struct iscsi_data_count *count)
 {
-	int data = count->data_length, total_tx = 0, tx_loop = 0, iov_len;
+	int ret, iov_len;
 	struct kvec *iov_p;
 	struct msghdr msg;
 
 	if (!conn || !conn->sock || !conn->conn_ops)
 		return -1;
 
-	if (data <= 0) {
-		pr_err("Data length is: %d\n", data);
+	if (count->data_length <= 0) {
+		pr_err("Data length is: %d\n", count->data_length);
 		return -1;
 	}
 
@@ -1375,20 +1375,16 @@ static int iscsit_do_tx_data(
 	iov_p = count->iov;
 	iov_len = count->iov_count;
 
-	while (total_tx < data) {
-		tx_loop = kernel_sendmsg(conn->sock, &msg, iov_p, iov_len,
-					(data - total_tx));
-		if (tx_loop <= 0) {
-			pr_debug("tx_loop: %d total_tx %d\n",
-				tx_loop, total_tx);
-			return tx_loop;
-		}
-		total_tx += tx_loop;
-		pr_debug("tx_loop: %d, total_tx: %d, data: %d\n",
-					tx_loop, total_tx, data);
+	ret = kernel_sendmsg(conn->sock, &msg, iov_p, iov_len,
+			     count->data_length);
+	if (ret != count->data_length) {
+		pr_err("Unexpected ret: %d send data %d\n",
+		       ret, count->data_length);
+		return -EPIPE;
 	}
+	pr_debug("ret: %d, sent data: %d\n", ret, count->data_length);
 
-	return total_tx;
+	return ret;
 }
 
 int rx_data(
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index ab3ab27d49b..0be83e788df 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -190,7 +190,7 @@ static void tcm_loop_submission_work(struct work_struct *work)
 		set_host_byte(sc, DID_TRANSPORT_DISRUPTED);
 		goto out_done;
 	}
-	tl_nexus = tl_hba->tl_nexus;
+	tl_nexus = tl_tpg->tl_nexus;
 	if (!tl_nexus) {
 		scmd_printk(KERN_ERR, sc, "TCM_Loop I_T Nexus"
 				" does not exist\n");
@@ -270,16 +270,26 @@ static int tcm_loop_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd *sc)
  * to struct scsi_device
  */
 static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg,
-			      struct tcm_loop_nexus *tl_nexus,
 			      int lun, int task, enum tcm_tmreq_table tmr)
 {
 	struct se_cmd *se_cmd = NULL;
 	struct se_session *se_sess;
 	struct se_portal_group *se_tpg;
+	struct tcm_loop_nexus *tl_nexus;
 	struct tcm_loop_cmd *tl_cmd = NULL;
 	struct tcm_loop_tmr *tl_tmr = NULL;
 	int ret = TMR_FUNCTION_FAILED, rc;
 
+	/*
+	 * Locate the tl_nexus and se_sess pointers
+	 */
+	tl_nexus = tl_tpg->tl_nexus;
+	if (!tl_nexus) {
+		pr_err("Unable to perform device reset without"
+				" active I_T Nexus\n");
+		return ret;
+	}
+
 	tl_cmd = kmem_cache_zalloc(tcm_loop_cmd_cache, GFP_KERNEL);
 	if (!tl_cmd) {
 		pr_err("Unable to allocate memory for tl_cmd\n");
@@ -295,7 +305,7 @@ static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg,
 
 	se_cmd = &tl_cmd->tl_se_cmd;
 	se_tpg = &tl_tpg->tl_se_tpg;
-	se_sess = tl_nexus->se_sess;
+	se_sess = tl_tpg->tl_nexus->se_sess;
 	/*
 	 * Initialize struct se_cmd descriptor from target_core_mod infrastructure
 	 */
@@ -340,7 +350,6 @@ release:
 static int tcm_loop_abort_task(struct scsi_cmnd *sc)
 {
 	struct tcm_loop_hba *tl_hba;
-	struct tcm_loop_nexus *tl_nexus;
 	struct tcm_loop_tpg *tl_tpg;
 	int ret = FAILED;
 
@@ -348,21 +357,8 @@ static int tcm_loop_abort_task(struct scsi_cmnd *sc)
 	 * Locate the tcm_loop_hba_t pointer
 	 */
 	tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host);
-	/*
-	 * Locate the tl_nexus and se_sess pointers
-	 */
-	tl_nexus = tl_hba->tl_nexus;
-	if (!tl_nexus) {
-		pr_err("Unable to perform device reset without"
-				" active I_T Nexus\n");
-		return FAILED;
-	}
-
-	/*
-	 * Locate the tl_tpg pointer from TargetID in sc->device->id
-	 */
 	tl_tpg = &tl_hba->tl_hba_tpgs[sc->device->id];
-	ret = tcm_loop_issue_tmr(tl_tpg, tl_nexus, sc->device->lun,
+	ret = tcm_loop_issue_tmr(tl_tpg, sc->device->lun,
 				 sc->request->tag, TMR_ABORT_TASK);
 	return (ret == TMR_FUNCTION_COMPLETE) ? SUCCESS : FAILED;
 }
@@ -374,7 +370,6 @@ static int tcm_loop_abort_task(struct scsi_cmnd *sc)
 static int tcm_loop_device_reset(struct scsi_cmnd *sc)
 {
 	struct tcm_loop_hba *tl_hba;
-	struct tcm_loop_nexus *tl_nexus;
 	struct tcm_loop_tpg *tl_tpg;
 	int ret = FAILED;
 
@@ -382,20 +377,9 @@ static int tcm_loop_device_reset(struct scsi_cmnd *sc)
 	 * Locate the tcm_loop_hba_t pointer
 	 */
 	tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host);
-	/*
-	 * Locate the tl_nexus and se_sess pointers
-	 */
-	tl_nexus = tl_hba->tl_nexus;
-	if (!tl_nexus) {
-		pr_err("Unable to perform device reset without"
-				" active I_T Nexus\n");
-		return FAILED;
-	}
-	/*
-	 * Locate the tl_tpg pointer from TargetID in sc->device->id
-	 */
 	tl_tpg = &tl_hba->tl_hba_tpgs[sc->device->id];
-	ret = tcm_loop_issue_tmr(tl_tpg, tl_nexus, sc->device->lun,
+
+	ret = tcm_loop_issue_tmr(tl_tpg, sc->device->lun,
 				 0, TMR_LUN_RESET);
 	return (ret == TMR_FUNCTION_COMPLETE) ? SUCCESS : FAILED;
 }
@@ -1005,8 +989,8 @@ static int tcm_loop_make_nexus(
 	struct tcm_loop_nexus *tl_nexus;
 	int ret = -ENOMEM;
 
-	if (tl_tpg->tl_hba->tl_nexus) {
-		pr_debug("tl_tpg->tl_hba->tl_nexus already exists\n");
+	if (tl_tpg->tl_nexus) {
+		pr_debug("tl_tpg->tl_nexus already exists\n");
 		return -EEXIST;
 	}
 	se_tpg = &tl_tpg->tl_se_tpg;
@@ -1041,7 +1025,7 @@ static int tcm_loop_make_nexus(
 	 */
 	__transport_register_session(se_tpg, tl_nexus->se_sess->se_node_acl,
 			tl_nexus->se_sess, tl_nexus);
-	tl_tpg->tl_hba->tl_nexus = tl_nexus;
+	tl_tpg->tl_nexus = tl_nexus;
 	pr_debug("TCM_Loop_ConfigFS: Established I_T Nexus to emulated"
 		" %s Initiator Port: %s\n", tcm_loop_dump_proto_id(tl_hba),
 		name);
@@ -1057,12 +1041,8 @@ static int tcm_loop_drop_nexus(
 {
 	struct se_session *se_sess;
 	struct tcm_loop_nexus *tl_nexus;
-	struct tcm_loop_hba *tl_hba = tpg->tl_hba;
 
-	if (!tl_hba)
-		return -ENODEV;
-
-	tl_nexus = tl_hba->tl_nexus;
+	tl_nexus = tpg->tl_nexus;
 	if (!tl_nexus)
 		return -ENODEV;
 
@@ -1078,13 +1058,13 @@ static int tcm_loop_drop_nexus(
 	}
 
 	pr_debug("TCM_Loop_ConfigFS: Removing I_T Nexus to emulated"
-		" %s Initiator Port: %s\n", tcm_loop_dump_proto_id(tl_hba),
+		" %s Initiator Port: %s\n", tcm_loop_dump_proto_id(tpg->tl_hba),
 		tl_nexus->se_sess->se_node_acl->initiatorname);
 	/*
 	 * Release the SCSI I_T Nexus to the emulated SAS Target Port
 	 */
 	transport_deregister_session(tl_nexus->se_sess);
-	tpg->tl_hba->tl_nexus = NULL;
+	tpg->tl_nexus = NULL;
 	kfree(tl_nexus);
 	return 0;
 }
@@ -1100,7 +1080,7 @@ static ssize_t tcm_loop_tpg_show_nexus(
 	struct tcm_loop_nexus *tl_nexus;
 	ssize_t ret;
 
-	tl_nexus = tl_tpg->tl_hba->tl_nexus;
+	tl_nexus = tl_tpg->tl_nexus;
 	if (!tl_nexus)
 		return -ENODEV;
 
diff --git a/drivers/target/loopback/tcm_loop.h b/drivers/target/loopback/tcm_loop.h
index 54c59d0b660..6ae49f272ba 100644
--- a/drivers/target/loopback/tcm_loop.h
+++ b/drivers/target/loopback/tcm_loop.h
@@ -27,11 +27,6 @@ struct tcm_loop_tmr {
 };
 
 struct tcm_loop_nexus {
-	int it_nexus_active;
-	/*
-	 * Pointer to Linux/SCSI HBA from linux/include/scsi_host.h
-	 */
-	struct scsi_host *sh;
 	/*
 	 * Pointer to TCM session for I_T Nexus
 	 */
@@ -51,6 +46,7 @@ struct tcm_loop_tpg {
 	atomic_t tl_tpg_port_count;
 	struct se_portal_group tl_se_tpg;
 	struct tcm_loop_hba *tl_hba;
+	struct tcm_loop_nexus *tl_nexus;
 };
 
 struct tcm_loop_hba {
@@ -59,7 +55,6 @@ struct tcm_loop_hba {
 	struct se_hba_s *se_hba;
 	struct se_lun *tl_hba_lun;
 	struct se_port *tl_hba_lun_sep;
-	struct tcm_loop_nexus *tl_nexus;
 	struct device dev;
 	struct Scsi_Host *sh;
 	struct tcm_loop_tpg tl_hba_tpgs[TL_TPGS_PER_HBA];
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index c45f9e907e4..9e0f5d3b3eb 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -1169,10 +1169,10 @@ int se_dev_set_optimal_sectors(struct se_device *dev, u32 optimal_sectors)
 				" changed for TCM/pSCSI\n", dev);
 		return -EINVAL;
 	}
-	if (optimal_sectors > dev->dev_attrib.fabric_max_sectors) {
+	if (optimal_sectors > dev->dev_attrib.hw_max_sectors) {
 		pr_err("dev[%p]: Passed optimal_sectors %u cannot be"
-			" greater than fabric_max_sectors: %u\n", dev,
-			optimal_sectors, dev->dev_attrib.fabric_max_sectors);
+			" greater than hw_max_sectors: %u\n", dev,
+			optimal_sectors, dev->dev_attrib.hw_max_sectors);
 		return -EINVAL;
 	}
 
@@ -1572,7 +1572,6 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 				DA_UNMAP_GRANULARITY_ALIGNMENT_DEFAULT;
 	dev->dev_attrib.max_write_same_len = DA_MAX_WRITE_SAME_LEN;
 	dev->dev_attrib.fabric_max_sectors = DA_FABRIC_MAX_SECTORS;
-	dev->dev_attrib.optimal_sectors = DA_FABRIC_MAX_SECTORS;
 
 	xcopy_lun = &dev->xcopy_lun;
 	xcopy_lun->lun_se_dev = dev;
@@ -1599,8 +1598,6 @@ int target_configure_device(struct se_device *dev)
 	ret = dev->transport->configure_device(dev);
 	if (ret)
 		goto out;
-	dev->dev_flags |= DF_CONFIGURED;
-
 	/*
 	 * XXX: there is not much point to have two different values here..
 	 */
@@ -1613,6 +1610,7 @@ int target_configure_device(struct se_device *dev)
 	dev->dev_attrib.hw_max_sectors =
 		se_dev_align_max_sectors(dev->dev_attrib.hw_max_sectors,
 					 dev->dev_attrib.hw_block_size);
+	dev->dev_attrib.optimal_sectors = dev->dev_attrib.hw_max_sectors;
 
 	dev->dev_index = scsi_get_new_index(SCSI_DEVICE_INDEX);
 	dev->creation_time = get_jiffies_64();
@@ -1661,6 +1659,8 @@ int target_configure_device(struct se_device *dev)
 	list_add_tail(&dev->g_dev_node, &g_device_list);
 	mutex_unlock(&g_device_mutex);
 
+	dev->dev_flags |= DF_CONFIGURED;
+
 	return 0;
 
 out_free_alua:
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index 72c83d98662..88c9179ab20 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -263,40 +263,32 @@ static int fd_do_prot_rw(struct se_cmd *cmd, struct fd_prot *fd_prot,
 	struct se_device *se_dev = cmd->se_dev;
 	struct fd_dev *dev = FD_DEV(se_dev);
 	struct file *prot_fd = dev->fd_prot_file;
-	struct scatterlist *sg;
 	loff_t pos = (cmd->t_task_lba * se_dev->prot_length);
 	unsigned char *buf;
-	u32 prot_size, len, size;
-	int rc, ret = 1, i;
+	u32 prot_size;
+	int rc, ret = 1;
 
 	prot_size = (cmd->data_length / se_dev->dev_attrib.block_size) *
 		     se_dev->prot_length;
 
 	if (!is_write) {
-		fd_prot->prot_buf = vzalloc(prot_size);
+		fd_prot->prot_buf = kzalloc(prot_size, GFP_KERNEL);
 		if (!fd_prot->prot_buf) {
 			pr_err("Unable to allocate fd_prot->prot_buf\n");
 			return -ENOMEM;
 		}
 		buf = fd_prot->prot_buf;
 
-		fd_prot->prot_sg_nents = cmd->t_prot_nents;
-		fd_prot->prot_sg = kzalloc(sizeof(struct scatterlist) *
-					   fd_prot->prot_sg_nents, GFP_KERNEL);
+		fd_prot->prot_sg_nents = 1;
+		fd_prot->prot_sg = kzalloc(sizeof(struct scatterlist),
+					   GFP_KERNEL);
 		if (!fd_prot->prot_sg) {
 			pr_err("Unable to allocate fd_prot->prot_sg\n");
-			vfree(fd_prot->prot_buf);
+			kfree(fd_prot->prot_buf);
 			return -ENOMEM;
 		}
-		size = prot_size;
-
-		for_each_sg(fd_prot->prot_sg, sg, fd_prot->prot_sg_nents, i) {
-
-			len = min_t(u32, PAGE_SIZE, size);
-			sg_set_buf(sg, buf, len);
-			size -= len;
-			buf += len;
-		}
+		sg_init_table(fd_prot->prot_sg, fd_prot->prot_sg_nents);
+		sg_set_buf(fd_prot->prot_sg, buf, prot_size);
 	}
 
 	if (is_write) {
@@ -317,7 +309,7 @@ static int fd_do_prot_rw(struct se_cmd *cmd, struct fd_prot *fd_prot,
 
 	if (is_write || ret < 0) {
 		kfree(fd_prot->prot_sg);
-		vfree(fd_prot->prot_buf);
+		kfree(fd_prot->prot_buf);
 	}
 
 	return ret;
@@ -543,6 +535,56 @@ fd_execute_write_same(struct se_cmd *cmd)
 	return 0;
 }
 
+static int
+fd_do_prot_fill(struct se_device *se_dev, sector_t lba, sector_t nolb,
+		void *buf, size_t bufsize)
+{
+	struct fd_dev *fd_dev = FD_DEV(se_dev);
+	struct file *prot_fd = fd_dev->fd_prot_file;
+	sector_t prot_length, prot;
+	loff_t pos = lba * se_dev->prot_length;
+
+	if (!prot_fd) {
+		pr_err("Unable to locate fd_dev->fd_prot_file\n");
+		return -ENODEV;
+	}
+
+	prot_length = nolb * se_dev->prot_length;
+
+	for (prot = 0; prot < prot_length;) {
+		sector_t len = min_t(sector_t, bufsize, prot_length - prot);
+		ssize_t ret = kernel_write(prot_fd, buf, len, pos + prot);
+
+		if (ret != len) {
+			pr_err("vfs_write to prot file failed: %zd\n", ret);
+			return ret < 0 ? ret : -ENODEV;
+		}
+		prot += ret;
+	}
+
+	return 0;
+}
+
+static int
+fd_do_prot_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb)
+{
+	void *buf;
+	int rc;
+
+	buf = (void *)__get_free_page(GFP_KERNEL);
+	if (!buf) {
+		pr_err("Unable to allocate FILEIO prot buf\n");
+		return -ENOMEM;
+	}
+	memset(buf, 0xff, PAGE_SIZE);
+
+	rc = fd_do_prot_fill(cmd->se_dev, lba, nolb, buf, PAGE_SIZE);
+
+	free_page((unsigned long)buf);
+
+	return rc;
+}
+
 static sense_reason_t
 fd_do_unmap(struct se_cmd *cmd, void *priv, sector_t lba, sector_t nolb)
 {
@@ -550,6 +592,12 @@ fd_do_unmap(struct se_cmd *cmd, void *priv, sector_t lba, sector_t nolb)
 	struct inode *inode = file->f_mapping->host;
 	int ret;
 
+	if (cmd->se_dev->dev_attrib.pi_prot_type) {
+		ret = fd_do_prot_unmap(cmd, lba, nolb);
+		if (ret)
+			return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+	}
+
 	if (S_ISBLK(inode->i_mode)) {
 		/* The backend is block device, use discard */
 		struct block_device *bdev = inode->i_bdev;
@@ -620,7 +668,16 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	struct fd_prot fd_prot;
 	sense_reason_t rc;
 	int ret = 0;
-
+	/*
+	 * We are currently limited by the number of iovecs (2048) per
+	 * single vfs_[writev,readv] call.
+	 */
+	if (cmd->data_length > FD_MAX_BYTES) {
+		pr_err("FILEIO: Not able to process I/O of %u bytes due to"
+		       "FD_MAX_BYTES: %u iovec count limitiation\n",
+			cmd->data_length, FD_MAX_BYTES);
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+	}
 	/*
 	 * Call vectorized fileio functions to map struct scatterlist
 	 * physical memory addresses to struct iovec virtual memory.
@@ -643,11 +700,11 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 						 0, fd_prot.prot_sg, 0);
 			if (rc) {
 				kfree(fd_prot.prot_sg);
-				vfree(fd_prot.prot_buf);
+				kfree(fd_prot.prot_buf);
 				return rc;
 			}
 			kfree(fd_prot.prot_sg);
-			vfree(fd_prot.prot_buf);
+			kfree(fd_prot.prot_buf);
 		}
 	} else {
 		memset(&fd_prot, 0, sizeof(struct fd_prot));
@@ -663,7 +720,7 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 						  0, fd_prot.prot_sg, 0);
 			if (rc) {
 				kfree(fd_prot.prot_sg);
-				vfree(fd_prot.prot_buf);
+				kfree(fd_prot.prot_buf);
 				return rc;
 			}
 		}
@@ -699,7 +756,7 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 
 	if (ret < 0) {
 		kfree(fd_prot.prot_sg);
-		vfree(fd_prot.prot_buf);
+		kfree(fd_prot.prot_buf);
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 
@@ -863,48 +920,28 @@ static int fd_init_prot(struct se_device *dev)
 
 static int fd_format_prot(struct se_device *dev)
 {
-	struct fd_dev *fd_dev = FD_DEV(dev);
-	struct file *prot_fd = fd_dev->fd_prot_file;
-	sector_t prot_length, prot;
 	unsigned char *buf;
-	loff_t pos = 0;
 	int unit_size = FDBD_FORMAT_UNIT_SIZE * dev->dev_attrib.block_size;
-	int rc, ret = 0, size, len;
+	int ret;
 
 	if (!dev->dev_attrib.pi_prot_type) {
 		pr_err("Unable to format_prot while pi_prot_type == 0\n");
 		return -ENODEV;
 	}
-	if (!prot_fd) {
-		pr_err("Unable to locate fd_dev->fd_prot_file\n");
-		return -ENODEV;
-	}
 
 	buf = vzalloc(unit_size);
 	if (!buf) {
 		pr_err("Unable to allocate FILEIO prot buf\n");
 		return -ENOMEM;
 	}
-	prot_length = (dev->transport->get_blocks(dev) + 1) * dev->prot_length;
-	size = prot_length;
 
 	pr_debug("Using FILEIO prot_length: %llu\n",
-		 (unsigned long long)prot_length);
+		 (unsigned long long)(dev->transport->get_blocks(dev) + 1) *
+					dev->prot_length);
 
 	memset(buf, 0xff, unit_size);
-	for (prot = 0; prot < prot_length; prot += unit_size) {
-		len = min(unit_size, size);
-		rc = kernel_write(prot_fd, buf, len, pos);
-		if (rc != len) {
-			pr_err("vfs_write to prot file failed: %d\n", rc);
-			ret = -ENODEV;
-			goto out;
-		}
-		pos += len;
-		size -= len;
-	}
-
-out:
+	ret = fd_do_prot_fill(dev, 0, dev->transport->get_blocks(dev) + 1,
+			      buf, unit_size);
 	vfree(buf);
 	return ret;
 }
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 7e6b857c6b3..be27773ab82 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -123,7 +123,7 @@ static int iblock_configure_device(struct se_device *dev)
 	q = bdev_get_queue(bd);
 
 	dev->dev_attrib.hw_block_size = bdev_logical_block_size(bd);
-	dev->dev_attrib.hw_max_sectors = UINT_MAX;
+	dev->dev_attrib.hw_max_sectors = queue_max_hw_sectors(q);
 	dev->dev_attrib.hw_queue_depth = q->nr_requests;
 
 	/*
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 9f93b823409..45837a4e950 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -1857,8 +1857,8 @@ static int core_scsi3_update_aptpl_buf(
 		}
 
 		if ((len + strlen(tmp) >= pr_aptpl_buf_len)) {
-			pr_err("Unable to update renaming"
-				" APTPL metadata\n");
+			pr_err("Unable to update renaming APTPL metadata,"
+			       " reallocating larger buffer\n");
 			ret = -EMSGSIZE;
 			goto out;
 		}
@@ -1875,8 +1875,8 @@ static int core_scsi3_update_aptpl_buf(
 			lun->lun_sep->sep_rtpi, lun->unpacked_lun, reg_count);
 
 		if ((len + strlen(tmp) >= pr_aptpl_buf_len)) {
-			pr_err("Unable to update renaming"
-				" APTPL metadata\n");
+			pr_err("Unable to update renaming APTPL metadata,"
+			       " reallocating larger buffer\n");
 			ret = -EMSGSIZE;
 			goto out;
 		}
@@ -1939,7 +1939,7 @@ static int __core_scsi3_write_aptpl_to_file(
 static sense_reason_t core_scsi3_update_and_write_aptpl(struct se_device *dev, bool aptpl)
 {
 	unsigned char *buf;
-	int rc;
+	int rc, len = PR_APTPL_BUF_LEN;
 
 	if (!aptpl) {
 		char *null_buf = "No Registrations or Reservations\n";
@@ -1953,25 +1953,26 @@ static sense_reason_t core_scsi3_update_and_write_aptpl(struct se_device *dev, b
 
 		return 0;
 	}
-
-	buf = kzalloc(PR_APTPL_BUF_LEN, GFP_KERNEL);
+retry:
+	buf = vzalloc(len);
 	if (!buf)
 		return TCM_OUT_OF_RESOURCES;
 
-	rc = core_scsi3_update_aptpl_buf(dev, buf, PR_APTPL_BUF_LEN);
+	rc = core_scsi3_update_aptpl_buf(dev, buf, len);
 	if (rc < 0) {
-		kfree(buf);
-		return TCM_OUT_OF_RESOURCES;
+		vfree(buf);
+		len *= 2;
+		goto retry;
 	}
 
 	rc = __core_scsi3_write_aptpl_to_file(dev, buf);
 	if (rc != 0) {
 		pr_err("SPC-3 PR: Could not update APTPL\n");
-		kfree(buf);
+		vfree(buf);
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	dev->t10_pr.pr_aptpl_active = 1;
-	kfree(buf);
+	vfree(buf);
 	pr_debug("SPC-3 PR: Set APTPL Bit Activated\n");
 	return 0;
 }
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 7c8291f0bbb..3ee77db03cb 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -520,6 +520,7 @@ static int pscsi_configure_device(struct se_device *dev)
 					" pdv_host_id: %d\n", pdv->pdv_host_id);
 				return -EINVAL;
 			}
+			pdv->pdv_lld_host = sh;
 		}
 	} else {
 		if (phv->phv_mode == PHV_VIRTUAL_HOST_ID) {
@@ -602,6 +603,8 @@ static void pscsi_free_device(struct se_device *dev)
 		if ((phv->phv_mode == PHV_LLD_SCSI_HOST_NO) &&
 		    (phv->phv_lld_host != NULL))
 			scsi_host_put(phv->phv_lld_host);
+		else if (pdv->pdv_lld_host)
+			scsi_host_put(pdv->pdv_lld_host);
 
 		if ((sd->type == TYPE_DISK) || (sd->type == TYPE_ROM))
 			scsi_device_put(sd);
@@ -1120,7 +1123,7 @@ static u32 pscsi_get_device_type(struct se_device *dev)
 	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
 	struct scsi_device *sd = pdv->pdv_sd;
 
-	return sd->type;
+	return (sd) ? sd->type : TYPE_NO_LUN;
 }
 
 static sector_t pscsi_get_blocks(struct se_device *dev)
diff --git a/drivers/target/target_core_pscsi.h b/drivers/target/target_core_pscsi.h
index 1bd757dff8e..820d3052b77 100644
--- a/drivers/target/target_core_pscsi.h
+++ b/drivers/target/target_core_pscsi.h
@@ -45,6 +45,7 @@ struct pscsi_dev_virt {
 	int	pdv_lun_id;
 	struct block_device *pdv_bd;
 	struct scsi_device *pdv_sd;
+	struct Scsi_Host *pdv_lld_host;
 } ____cacheline_aligned;
 
 typedef enum phv_modes {
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index ebe62afb957..fa89c2f105e 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -251,6 +251,8 @@ static inline unsigned long long transport_lba_64_ext(unsigned char *cdb)
 static sense_reason_t
 sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *ops)
 {
+	struct se_device *dev = cmd->se_dev;
+	sector_t end_lba = dev->transport->get_blocks(dev) + 1;
 	unsigned int sectors = sbc_get_write_same_sectors(cmd);
 
 	if ((flags[0] & 0x04) || (flags[0] & 0x02)) {
@@ -264,6 +266,16 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o
 			sectors, cmd->se_dev->dev_attrib.max_write_same_len);
 		return TCM_INVALID_CDB_FIELD;
 	}
+	/*
+	 * Sanity check for LBA wrap and request past end of device.
+	 */
+	if (((cmd->t_task_lba + sectors) < cmd->t_task_lba) ||
+	    ((cmd->t_task_lba + sectors) > end_lba)) {
+		pr_err("WRITE_SAME exceeds last lba %llu (lba %llu, sectors %u)\n",
+		       (unsigned long long)end_lba, cmd->t_task_lba, sectors);
+		return TCM_ADDRESS_OUT_OF_RANGE;
+	}
+
 	/* We always have ANC_SUP == 0 so setting ANCHOR is always an error */
 	if (flags[0] & 0x10) {
 		pr_warn("WRITE SAME with ANCHOR not supported\n");
@@ -287,7 +299,7 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o
 	return 0;
 }
 
-static sense_reason_t xdreadwrite_callback(struct se_cmd *cmd)
+static sense_reason_t xdreadwrite_callback(struct se_cmd *cmd, bool success)
 {
 	unsigned char *buf, *addr;
 	struct scatterlist *sg;
@@ -351,7 +363,7 @@ sbc_execute_rw(struct se_cmd *cmd)
 			       cmd->data_direction);
 }
 
-static sense_reason_t compare_and_write_post(struct se_cmd *cmd)
+static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success)
 {
 	struct se_device *dev = cmd->se_dev;
 
@@ -374,7 +386,7 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd)
 	return TCM_NO_SENSE;
 }
 
-static sense_reason_t compare_and_write_callback(struct se_cmd *cmd)
+static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool success)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct scatterlist *write_sg = NULL, *sg;
@@ -389,11 +401,16 @@ static sense_reason_t compare_and_write_callback(struct se_cmd *cmd)
 
 	/*
 	 * Handle early failure in transport_generic_request_failure(),
-	 * which will not have taken ->caw_mutex yet..
+	 * which will not have taken ->caw_sem yet..
 	 */
-	if (!cmd->t_data_sg || !cmd->t_bidi_data_sg)
+	if (!success && (!cmd->t_data_sg || !cmd->t_bidi_data_sg))
 		return TCM_NO_SENSE;
 	/*
+	 * Handle special case for zero-length COMPARE_AND_WRITE
+	 */
+	if (!cmd->data_length)
+		goto out;
+	/*
 	 * Immediately exit + release dev->caw_sem if command has already
 	 * been failed with a non-zero SCSI status.
 	 */
@@ -953,24 +970,10 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 
 	if (cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) {
 		unsigned long long end_lba;
-
-		if (sectors > dev->dev_attrib.fabric_max_sectors) {
-			printk_ratelimited(KERN_ERR "SCSI OP %02xh with too"
-				" big sectors %u exceeds fabric_max_sectors:"
-				" %u\n", cdb[0], sectors,
-				dev->dev_attrib.fabric_max_sectors);
-			return TCM_INVALID_CDB_FIELD;
-		}
-		if (sectors > dev->dev_attrib.hw_max_sectors) {
-			printk_ratelimited(KERN_ERR "SCSI OP %02xh with too"
-				" big sectors %u exceeds backend hw_max_sectors:"
-				" %u\n", cdb[0], sectors,
-				dev->dev_attrib.hw_max_sectors);
-			return TCM_INVALID_CDB_FIELD;
-		}
 check_lba:
 		end_lba = dev->transport->get_blocks(dev) + 1;
-		if (cmd->t_task_lba + sectors > end_lba) {
+		if (((cmd->t_task_lba + sectors) < cmd->t_task_lba) ||
+		    ((cmd->t_task_lba + sectors) > end_lba)) {
 			pr_err("cmd exceeds last lba %llu "
 				"(lba %llu, sectors %u)\n",
 				end_lba, cmd->t_task_lba, sectors);
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index bc286a67af7..614005b6b08 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -505,7 +505,6 @@ static sense_reason_t
 spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
 {
 	struct se_device *dev = cmd->se_dev;
-	u32 max_sectors;
 	int have_tp = 0;
 	int opt, min;
 
@@ -539,9 +538,7 @@ spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
 	/*
 	 * Set MAXIMUM TRANSFER LENGTH
 	 */
-	max_sectors = min(dev->dev_attrib.fabric_max_sectors,
-			  dev->dev_attrib.hw_max_sectors);
-	put_unaligned_be32(max_sectors, &buf[8]);
+	put_unaligned_be32(dev->dev_attrib.hw_max_sectors, &buf[8]);
 
 	/*
 	 * Set OPTIMAL TRANSFER LENGTH
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index be877bf6f73..e786e9104c4 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1615,11 +1615,11 @@ void transport_generic_request_failure(struct se_cmd *cmd,
 	transport_complete_task_attr(cmd);
 	/*
 	 * Handle special case for COMPARE_AND_WRITE failure, where the
-	 * callback is expected to drop the per device ->caw_mutex.
+	 * callback is expected to drop the per device ->caw_sem.
 	 */
 	if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) &&
 	     cmd->transport_complete_callback)
-		cmd->transport_complete_callback(cmd);
+		cmd->transport_complete_callback(cmd, false);
 
 	switch (sense_reason) {
 	case TCM_NON_EXISTENT_LUN:
@@ -1975,8 +1975,12 @@ static void target_complete_ok_work(struct work_struct *work)
 	if (cmd->transport_complete_callback) {
 		sense_reason_t rc;
 
-		rc = cmd->transport_complete_callback(cmd);
+		rc = cmd->transport_complete_callback(cmd, true);
 		if (!rc && !(cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE_POST)) {
+			if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) &&
+			    !cmd->data_length)
+				goto queue_rsp;
+
 			return;
 		} else if (rc) {
 			ret = transport_send_check_condition_and_sense(cmd,
@@ -1990,6 +1994,7 @@ static void target_complete_ok_work(struct work_struct *work)
 		}
 	}
 
+queue_rsp:
 	switch (cmd->data_direction) {
 	case DMA_FROM_DEVICE:
 		spin_lock(&cmd->se_lun->lun_sep_lock);
@@ -2094,6 +2099,16 @@ static inline void transport_reset_sgl_orig(struct se_cmd *cmd)
 static inline void transport_free_pages(struct se_cmd *cmd)
 {
 	if (cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC) {
+		/*
+		 * Release special case READ buffer payload required for
+		 * SG_TO_MEM_NOALLOC to function with COMPARE_AND_WRITE
+		 */
+		if (cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) {
+			transport_free_sgl(cmd->t_bidi_data_sg,
+					   cmd->t_bidi_data_nents);
+			cmd->t_bidi_data_sg = NULL;
+			cmd->t_bidi_data_nents = 0;
+		}
 		transport_reset_sgl_orig(cmd);
 		return;
 	}
@@ -2246,6 +2261,7 @@ sense_reason_t
 transport_generic_new_cmd(struct se_cmd *cmd)
 {
 	int ret = 0;
+	bool zero_flag = !(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB);
 
 	/*
 	 * Determine is the TCM fabric module has already allocated physical
@@ -2254,7 +2270,6 @@ transport_generic_new_cmd(struct se_cmd *cmd)
 	 */
 	if (!(cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC) &&
 	    cmd->data_length) {
-		bool zero_flag = !(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB);
 
 		if ((cmd->se_cmd_flags & SCF_BIDI) ||
 		    (cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE)) {
@@ -2285,6 +2300,20 @@ transport_generic_new_cmd(struct se_cmd *cmd)
 				       cmd->data_length, zero_flag);
 		if (ret < 0)
 			return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+	} else if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) &&
+		    cmd->data_length) {
+		/*
+		 * Special case for COMPARE_AND_WRITE with fabrics
+		 * using SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC.
+		 */
+		u32 caw_length = cmd->t_task_nolb *
+				 cmd->se_dev->dev_attrib.block_size;
+
+		ret = target_alloc_sgl(&cmd->t_bidi_data_sg,
+				       &cmd->t_bidi_data_nents,
+				       caw_length, zero_flag);
+		if (ret < 0)
+			return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	/*
 	 * If this command is not a write we can execute it right here,
@@ -2389,6 +2418,10 @@ int target_get_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd,
 	list_add_tail(&se_cmd->se_cmd_list, &se_sess->sess_cmd_list);
 out:
 	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
+
+	if (ret && ack_kref)
+		target_put_sess_cmd(se_sess, se_cmd);
+
 	return ret;
 }
 EXPORT_SYMBOL(target_get_sess_cmd);
diff --git a/drivers/target/tcm_fc/tfc_io.c b/drivers/target/tcm_fc/tfc_io.c
index 97b486c3dda..583e755d809 100644
--- a/drivers/target/tcm_fc/tfc_io.c
+++ b/drivers/target/tcm_fc/tfc_io.c
@@ -359,7 +359,7 @@ void ft_invl_hw_context(struct ft_cmd *cmd)
 		ep = fc_seq_exch(seq);
 		if (ep) {
 			lport = ep->lp;
-			if (lport && (ep->xid <= lport->lro_xid))
+			if (lport && (ep->xid <= lport->lro_xid)) {
 				/*
 				 * "ddp_done" trigger invalidation of HW
 				 * specific DDP context
@@ -374,6 +374,7 @@ void ft_invl_hw_context(struct ft_cmd *cmd)
 				 * identified using ep->xid)
 				 */
 				cmd->was_ddp_setup = 0;
+			}
 		}
 	}
 }
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index f554d25b439..5b4445842ca 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -42,6 +42,17 @@ config THERMAL_OF
 	  Say 'Y' here if you need to build thermal infrastructure
 	  based on device tree.
 
+config THERMAL_WRITABLE_TRIPS
+	bool "Enable writable trip points"
+	help
+	  This option allows the system integrator to choose whether
+	  trip temperatures can be changed from userspace. The
+	  writable trips need to be specified when setting up the
+	  thermal zone but the choice here takes precedence.
+
+	  Say 'Y' here if you would like to allow userspace tools to
+	  change trip temperatures.
+
 choice
 	prompt "Default Thermal governor"
 	default THERMAL_DEFAULT_GOV_STEP_WISE
@@ -71,6 +82,14 @@ config THERMAL_DEFAULT_GOV_USER_SPACE
 	  Select this if you want to let the user space manage the
 	  platform thermals.
 
+config THERMAL_DEFAULT_GOV_POWER_ALLOCATOR
+	bool "power_allocator"
+	select THERMAL_GOV_POWER_ALLOCATOR
+	help
+	  Select this if you want to control temperature based on
+	  system and device power allocation. This governor can only
+	  operate on cooling devices that implement the power API.
+
 endchoice
 
 config THERMAL_GOV_FAIR_SHARE
@@ -99,6 +118,13 @@ config THERMAL_GOV_USER_SPACE
 	help
 	  Enable this to let the user space manage the platform thermals.
 
+config THERMAL_GOV_POWER_ALLOCATOR
+	bool "Power allocator thermal governor"
+	select THERMAL_POWER_ACTOR
+	help
+	  Enable this to manage platform thermals by dynamically
+	  allocating and limiting power to devices.
+
 config CPU_THERMAL
 	bool "generic cpu cooling support"
 	depends on CPU_FREQ
@@ -112,6 +138,28 @@ config CPU_THERMAL
 
 	  If you want this support, you should say Y here.
 
+config CLOCK_THERMAL
+	bool "Generic clock cooling support"
+	depends on COMMON_CLK
+	depends on PM_OPP
+	help
+	  This entry implements the generic clock cooling mechanism through
+	  frequency clipping. Typically used to cool off co-processors. The
+	  device that is configured to use this cooling mechanism will be
+	  controlled to reduce clock frequency whenever temperature is high.
+
+config DEVFREQ_THERMAL
+	bool "Generic device cooling support"
+	depends on PM_DEVFREQ
+	help
+	  This implements the generic devfreq cooling mechanism through
+	  frequency reduction for devices using devfreq.
+
+	  This will throttle the device by limiting the maximum allowed DVFS
+	  frequency corresponding to the cooling level.
+
+	  If you want this support, you should say Y here.
+
 config THERMAL_EMULATION
 	bool "Thermal emulation mode support"
 	help
@@ -185,6 +233,16 @@ config ARMADA_THERMAL
 	  Enable this option if you want to have support for thermal management
 	  controller present in Armada 370 and Armada XP SoC.
 
+config TEGRA_SOCTHERM
+	tristate "Tegra SOCTHERM thermal management"
+	depends on ARCH_TEGRA
+	help
+	  Enable this option for integrated thermal management support on NVIDIA
+	  Tegra124 systems-on-chip. The driver supports four thermal zones
+	  (CPU, GPU, MEM, PLLX). Cooling devices can be bound to the thermal
+	  zones to manage temperatures. This option is also required for the
+	  emergency thermal reset (thermtrip) feature to function.
+
 config DB8500_CPUFREQ_COOLING
 	tristate "DB8500 cpufreq cooling"
 	depends on ARCH_U8500
@@ -196,6 +254,14 @@ config DB8500_CPUFREQ_COOLING
 	  bound cpufreq cooling device turns active to set CPU frequency low to
 	  cool down the CPU.
 
+config SCPI_THERMAL
+	tristate "Temperature sensor on ARM SoC based on SCPI Firmware interface"
+	depends on ARM_SCPI_PROTOCOL
+	depends on OF
+	help
+	  Support for the SCPI thermal sensor driver in the Linux thermal
+	  framework.
+
 config INTEL_POWERCLAMP
 	tristate "Intel PowerClamp idle injection driver"
 	depends on THERMAL
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index 39c4fe87da2..31e26bd864e 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -14,10 +14,17 @@ thermal_sys-$(CONFIG_THERMAL_GOV_FAIR_SHARE)	+= fair_share.o
 thermal_sys-$(CONFIG_THERMAL_GOV_BANG_BANG)	+= gov_bang_bang.o
 thermal_sys-$(CONFIG_THERMAL_GOV_STEP_WISE)	+= step_wise.o
 thermal_sys-$(CONFIG_THERMAL_GOV_USER_SPACE)	+= user_space.o
+thermal_sys-$(CONFIG_THERMAL_GOV_POWER_ALLOCATOR)	+= power_allocator.o
 
 # cpufreq cooling
 thermal_sys-$(CONFIG_CPU_THERMAL)	+= cpu_cooling.o
 
+# clock cooling
+thermal_sys-$(CONFIG_CLOCK_THERMAL)	+= clock_cooling.o
+
+# devfreq cooling
+thermal_sys-$(CONFIG_DEVFREQ_THERMAL) += devfreq_cooling.o
+
 # platform thermal drivers
 obj-$(CONFIG_SPEAR_THERMAL)	+= spear_thermal.o
 obj-$(CONFIG_RCAR_THERMAL)	+= rcar_thermal.o
@@ -28,9 +35,11 @@ obj-$(CONFIG_DB8500_THERMAL)	+= db8500_thermal.o
 obj-$(CONFIG_ARMADA_THERMAL)	+= armada_thermal.o
 obj-$(CONFIG_IMX_THERMAL)	+= imx_thermal.o
 obj-$(CONFIG_DB8500_CPUFREQ_COOLING)	+= db8500_cpufreq_cooling.o
+obj-$(CONFIG_SCPI_THERMAL)	+= scpi-thermal.o
 obj-$(CONFIG_INTEL_POWERCLAMP)	+= intel_powerclamp.o
 obj-$(CONFIG_X86_PKG_TEMP_THERMAL)	+= x86_pkg_temp_thermal.o
 obj-$(CONFIG_INTEL_SOC_DTS_THERMAL)	+= intel_soc_dts_thermal.o
 obj-$(CONFIG_TI_SOC_THERMAL)	+= ti-soc-thermal/
 obj-$(CONFIG_INT340X_THERMAL)  += int340x_thermal/
 obj-$(CONFIG_ST_THERMAL)	+= st/
+obj-$(CONFIG_TEGRA_SOCTHERM)	+= tegra_soctherm.o
diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 9d1420acb39..e6f1acc7199 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -240,9 +240,9 @@ static const struct armada_thermal_data armada380_data = {
 	.is_valid_shift = 10,
 	.temp_shift = 0,
 	.temp_mask = 0x3ff,
-	.coef_b = 1169498786UL,
-	.coef_m = 2000000UL,
-	.coef_div = 4289,
+	.coef_b = 2931108200UL,
+	.coef_m = 5000000UL,
+	.coef_div = 10502,
 	.inverted = true,
 };
 
diff --git a/drivers/thermal/clock_cooling.c b/drivers/thermal/clock_cooling.c
new file mode 100644
index 00000000000..1b4ff0f4c71
--- /dev/null
+++ b/drivers/thermal/clock_cooling.c
@@ -0,0 +1,485 @@
+/*
+ *  drivers/thermal/clock_cooling.c
+ *
+ *  Copyright (C) 2014 Eduardo Valentin <edubezval@gmail.com>
+ *
+ *  Copyright (C) 2013	Texas Instruments Inc.
+ *  Contact:  Eduardo Valentin <eduardo.valentin@ti.com>
+ *
+ *  Highly based on cpu_cooling.c.
+ *  Copyright (C) 2012	Samsung Electronics Co., Ltd(http://www.samsung.com)
+ *  Copyright (C) 2012  Amit Daniel <amit.kachhap@linaro.org>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ */
+#include <linux/clk.h>
+#include <linux/cpufreq.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/idr.h>
+#include <linux/mutex.h>
+#include <linux/pm_opp.h>
+#include <linux/slab.h>
+#include <linux/thermal.h>
+#include <linux/clock_cooling.h>
+
+/**
+ * struct clock_cooling_device - data for cooling device with clock
+ * @id: unique integer value corresponding to each clock_cooling_device
+ *	registered.
+ * @dev: struct device pointer to the device being used to cool off using
+ *       clock frequencies.
+ * @cdev: thermal_cooling_device pointer to keep track of the
+ *	registered cooling device.
+ * @clk_rate_change_nb: reference to notifier block used to receive clock
+ *                      rate changes.
+ * @freq_table: frequency table used to keep track of available frequencies.
+ * @clock_state: integer value representing the current state of clock
+ *	cooling	devices.
+ * @clock_val: integer value representing the absolute value of the clipped
+ *	frequency.
+ * @clk: struct clk reference used to enforce clock limits.
+ * @lock: mutex lock to protect this struct.
+ *
+ * This structure is required for keeping information of each
+ * clock_cooling_device registered. In order to prevent corruption of this a
+ * mutex @lock is used.
+ */
+struct clock_cooling_device {
+	int id;
+	struct device *dev;
+	struct thermal_cooling_device *cdev;
+	struct notifier_block clk_rate_change_nb;
+	struct cpufreq_frequency_table *freq_table;
+	unsigned long clock_state;
+	unsigned long clock_val;
+	struct clk *clk;
+	struct mutex lock; /* lock to protect the content of this struct */
+};
+#define to_clock_cooling_device(x) \
+		container_of(x, struct clock_cooling_device, clk_rate_change_nb)
+static DEFINE_IDR(clock_idr);
+static DEFINE_MUTEX(cooling_clock_lock);
+
+/**
+ * clock_cooling_get_idr - function to get an unique id.
+ * @id: int * value generated by this function.
+ *
+ * This function will populate @id with an unique
+ * id, using the idr API.
+ *
+ * Return: 0 on success, an error code on failure.
+ */
+static int clock_cooling_get_idr(int *id)
+{
+	int ret;
+
+	mutex_lock(&cooling_clock_lock);
+	ret = idr_alloc(&clock_idr, NULL, 0, 0, GFP_KERNEL);
+	mutex_unlock(&cooling_clock_lock);
+	if (unlikely(ret < 0))
+		return ret;
+	*id = ret;
+
+	return 0;
+}
+
+/**
+ * release_idr - function to free the unique id.
+ * @id: int value representing the unique id.
+ */
+static void release_idr(int id)
+{
+	mutex_lock(&cooling_clock_lock);
+	idr_remove(&clock_idr, id);
+	mutex_unlock(&cooling_clock_lock);
+}
+
+/* Below code defines functions to be used for clock as cooling device */
+
+enum clock_cooling_property {
+	GET_LEVEL,
+	GET_FREQ,
+	GET_MAXL,
+};
+
+/**
+ * clock_cooling_get_property - fetch a property of interest for a give cpu.
+ * @ccdev: clock cooling device reference
+ * @input: query parameter
+ * @output: query return
+ * @property: type of query (frequency, level, max level)
+ *
+ * This is the common function to
+ * 1. get maximum clock cooling states
+ * 2. translate frequency to cooling state
+ * 3. translate cooling state to frequency
+ * Note that the code may be not in good shape
+ * but it is written in this way in order to:
+ * a) reduce duplicate code as most of the code can be shared.
+ * b) make sure the logic is consistent when translating between
+ *    cooling states and frequencies.
+ *
+ * Return: 0 on success, -EINVAL when invalid parameters are passed.
+ */
+static int clock_cooling_get_property(struct clock_cooling_device *ccdev,
+				      unsigned long input,
+				      unsigned long *output,
+				      enum clock_cooling_property property)
+{
+	int i;
+	unsigned long max_level = 0, level = 0;
+	unsigned int freq = CPUFREQ_ENTRY_INVALID;
+	int descend = -1;
+	struct cpufreq_frequency_table *pos, *table = ccdev->freq_table;
+
+	if (!output)
+		return -EINVAL;
+
+	if (!table)
+		return -EINVAL;
+
+	cpufreq_for_each_valid_entry(pos, table) {
+		/* ignore duplicate entry */
+		if (freq == pos->frequency)
+			continue;
+
+		/* get the frequency order */
+		if (freq != CPUFREQ_ENTRY_INVALID && descend == -1)
+			descend = freq > pos->frequency;
+
+		freq = pos->frequency;
+		max_level++;
+	}
+
+	/* No valid cpu frequency entry */
+	if (max_level == 0)
+		return -EINVAL;
+
+	/* max_level is an index, not a counter */
+	max_level--;
+
+	/* get max level */
+	if (property == GET_MAXL) {
+		*output = max_level;
+		return 0;
+	}
+
+	if (property == GET_FREQ)
+		level = descend ? input : (max_level - input);
+
+	i = 0;
+	cpufreq_for_each_valid_entry(pos, table) {
+		/* ignore duplicate entry */
+		if (freq == pos->frequency)
+			continue;
+
+		/* now we have a valid frequency entry */
+		freq = pos->frequency;
+
+		if (property == GET_LEVEL && (unsigned int)input == freq) {
+			/* get level by frequency */
+			*output = descend ? i : (max_level - i);
+			return 0;
+		}
+		if (property == GET_FREQ && level == i) {
+			/* get frequency by level */
+			*output = freq;
+			return 0;
+		}
+		i++;
+	}
+
+	return -EINVAL;
+}
+
+/**
+ * clock_cooling_get_level - return the cooling level of given clock cooling.
+ * @cdev: reference of a thermal cooling device of used as clock cooling device
+ * @freq: the frequency of interest
+ *
+ * This function will match the cooling level corresponding to the
+ * requested @freq and return it.
+ *
+ * Return: The matched cooling level on success or THERMAL_CSTATE_INVALID
+ * otherwise.
+ */
+unsigned long clock_cooling_get_level(struct thermal_cooling_device *cdev,
+				      unsigned long freq)
+{
+	struct clock_cooling_device *ccdev = cdev->devdata;
+	unsigned long val;
+
+	if (clock_cooling_get_property(ccdev, (unsigned long)freq, &val,
+				       GET_LEVEL))
+		return THERMAL_CSTATE_INVALID;
+
+	return val;
+}
+EXPORT_SYMBOL_GPL(clock_cooling_get_level);
+
+/**
+ * clock_cooling_get_frequency - get the absolute value of frequency from level.
+ * @ccdev: clock cooling device reference
+ * @level: cooling level
+ *
+ * This function matches cooling level with frequency. Based on a cooling level
+ * of frequency, equals cooling state of cpu cooling device, it will return
+ * the corresponding frequency.
+ *	e.g level=0 --> 1st MAX FREQ, level=1 ---> 2nd MAX FREQ, .... etc
+ *
+ * Return: 0 on error, the corresponding frequency otherwise.
+ */
+static unsigned long
+clock_cooling_get_frequency(struct clock_cooling_device *ccdev,
+			    unsigned long level)
+{
+	int ret = 0;
+	unsigned long freq;
+
+	ret = clock_cooling_get_property(ccdev, level, &freq, GET_FREQ);
+	if (ret)
+		return 0;
+
+	return freq;
+}
+
+/**
+ * clock_cooling_apply - function to apply frequency clipping.
+ * @ccdev: clock_cooling_device pointer containing frequency clipping data.
+ * @cooling_state: value of the cooling state.
+ *
+ * Function used to make sure the clock layer is aware of current thermal
+ * limits. The limits are applied by updating the clock rate in case it is
+ * higher than the corresponding frequency based on the requested cooling_state.
+ *
+ * Return: 0 on success, an error code otherwise (-EINVAL in case wrong
+ * cooling state).
+ */
+static int clock_cooling_apply(struct clock_cooling_device *ccdev,
+			       unsigned long cooling_state)
+{
+	unsigned long clip_freq, cur_freq;
+	int ret = 0;
+
+	/* Here we write the clipping */
+	/* Check if the old cooling action is same as new cooling action */
+	if (ccdev->clock_state == cooling_state)
+		return 0;
+
+	clip_freq = clock_cooling_get_frequency(ccdev, cooling_state);
+	if (!clip_freq)
+		return -EINVAL;
+
+	cur_freq = clk_get_rate(ccdev->clk);
+
+	mutex_lock(&ccdev->lock);
+	ccdev->clock_state = cooling_state;
+	ccdev->clock_val = clip_freq;
+	/* enforce clock level */
+	if (cur_freq > clip_freq)
+		ret = clk_set_rate(ccdev->clk, clip_freq);
+	mutex_unlock(&ccdev->lock);
+
+	return ret;
+}
+
+/**
+ * clock_cooling_clock_notifier - notifier callback on clock rate changes.
+ * @nb:	struct notifier_block * with callback info.
+ * @event: value showing clock event for which this function invoked.
+ * @data: callback-specific data
+ *
+ * Callback to hijack the notification on clock transition.
+ * Every time there is a clock change, we intercept all pre change events
+ * and block the transition in case the new rate infringes thermal limits.
+ *
+ * Return: NOTIFY_DONE (success) or NOTIFY_BAD (new_rate > thermal limit).
+ */
+static int clock_cooling_clock_notifier(struct notifier_block *nb,
+					unsigned long event, void *data)
+{
+	struct clk_notifier_data *ndata = data;
+	struct clock_cooling_device *ccdev = to_clock_cooling_device(nb);
+
+	switch (event) {
+	case PRE_RATE_CHANGE:
+		/*
+		 * checks on current state
+		 * TODO: current method is not best we can find as it
+		 * allows possibly voltage transitions, in case DVFS
+		 * layer is also hijacking clock pre notifications.
+		 */
+		if (ndata->new_rate > ccdev->clock_val)
+			return NOTIFY_BAD;
+		/* fall through */
+	case POST_RATE_CHANGE:
+	case ABORT_RATE_CHANGE:
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+/* clock cooling device thermal callback functions are defined below */
+
+/**
+ * clock_cooling_get_max_state - callback function to get the max cooling state.
+ * @cdev: thermal cooling device pointer.
+ * @state: fill this variable with the max cooling state.
+ *
+ * Callback for the thermal cooling device to return the clock
+ * max cooling state.
+ *
+ * Return: 0 on success, an error code otherwise.
+ */
+static int clock_cooling_get_max_state(struct thermal_cooling_device *cdev,
+				       unsigned long *state)
+{
+	struct clock_cooling_device *ccdev = cdev->devdata;
+	unsigned long count = 0;
+	int ret;
+
+	ret = clock_cooling_get_property(ccdev, 0, &count, GET_MAXL);
+	if (!ret)
+		*state = count;
+
+	return ret;
+}
+
+/**
+ * clock_cooling_get_cur_state - function to get the current cooling state.
+ * @cdev: thermal cooling device pointer.
+ * @state: fill this variable with the current cooling state.
+ *
+ * Callback for the thermal cooling device to return the clock
+ * current cooling state.
+ *
+ * Return: 0 (success)
+ */
+static int clock_cooling_get_cur_state(struct thermal_cooling_device *cdev,
+				       unsigned long *state)
+{
+	struct clock_cooling_device *ccdev = cdev->devdata;
+
+	*state = ccdev->clock_state;
+
+	return 0;
+}
+
+/**
+ * clock_cooling_set_cur_state - function to set the current cooling state.
+ * @cdev: thermal cooling device pointer.
+ * @state: set this variable to the current cooling state.
+ *
+ * Callback for the thermal cooling device to change the clock cooling
+ * current cooling state.
+ *
+ * Return: 0 on success, an error code otherwise.
+ */
+static int clock_cooling_set_cur_state(struct thermal_cooling_device *cdev,
+				       unsigned long state)
+{
+	struct clock_cooling_device *clock_device = cdev->devdata;
+
+	return clock_cooling_apply(clock_device, state);
+}
+
+/* Bind clock callbacks to thermal cooling device ops */
+static struct thermal_cooling_device_ops const clock_cooling_ops = {
+	.get_max_state = clock_cooling_get_max_state,
+	.get_cur_state = clock_cooling_get_cur_state,
+	.set_cur_state = clock_cooling_set_cur_state,
+};
+
+/**
+ * clock_cooling_register - function to create clock cooling device.
+ * @dev: struct device pointer to the device used as clock cooling device.
+ * @clock_name: string containing the clock used as cooling mechanism.
+ *
+ * This interface function registers the clock cooling device with the name
+ * "thermal-clock-%x". The cooling device is based on clock frequencies.
+ * The struct device is assumed to be capable of DVFS transitions.
+ * The OPP layer is used to fetch and fill the available frequencies for
+ * the referred device. The ordered frequency table is used to control
+ * the clock cooling device cooling states and to limit clock transitions
+ * based on the cooling state requested by the thermal framework.
+ *
+ * Return: a valid struct thermal_cooling_device pointer on success,
+ * on failure, it returns a corresponding ERR_PTR().
+ */
+struct thermal_cooling_device *
+clock_cooling_register(struct device *dev, const char *clock_name)
+{
+	struct thermal_cooling_device *cdev;
+	struct clock_cooling_device *ccdev = NULL;
+	char dev_name[THERMAL_NAME_LENGTH];
+	int ret = 0;
+
+	ccdev = devm_kzalloc(dev, sizeof(*ccdev), GFP_KERNEL);
+	if (!ccdev)
+		return ERR_PTR(-ENOMEM);
+
+	ccdev->dev = dev;
+	ccdev->clk = devm_clk_get(dev, clock_name);
+	if (IS_ERR(ccdev->clk))
+		return ERR_CAST(ccdev->clk);
+
+	ret = clock_cooling_get_idr(&ccdev->id);
+	if (ret)
+		return ERR_PTR(-EINVAL);
+
+	snprintf(dev_name, sizeof(dev_name), "thermal-clock-%d", ccdev->id);
+
+	cdev = thermal_cooling_device_register(dev_name, ccdev,
+					       &clock_cooling_ops);
+	if (IS_ERR(cdev)) {
+		release_idr(ccdev->id);
+		return ERR_PTR(-EINVAL);
+	}
+	ccdev->cdev = cdev;
+	ccdev->clk_rate_change_nb.notifier_call = clock_cooling_clock_notifier;
+
+	/* Assuming someone has already filled the opp table for this device */
+	ret = dev_pm_opp_init_cpufreq_table(dev, &ccdev->freq_table);
+	if (ret) {
+		release_idr(ccdev->id);
+		return ERR_PTR(ret);
+	}
+	ccdev->clock_state = 0;
+	ccdev->clock_val = clock_cooling_get_frequency(ccdev, 0);
+
+	clk_notifier_register(ccdev->clk, &ccdev->clk_rate_change_nb);
+
+	return cdev;
+}
+EXPORT_SYMBOL_GPL(clock_cooling_register);
+
+/**
+ * clock_cooling_unregister - function to remove clock cooling device.
+ * @cdev: thermal cooling device pointer.
+ *
+ * This interface function unregisters the "thermal-clock-%x" cooling device.
+ */
+void clock_cooling_unregister(struct thermal_cooling_device *cdev)
+{
+	struct clock_cooling_device *ccdev;
+
+	if (!cdev)
+		return;
+
+	ccdev = cdev->devdata;
+
+	clk_notifier_unregister(ccdev->clk, &ccdev->clk_rate_change_nb);
+	dev_pm_opp_free_cpufreq_table(ccdev->dev, &ccdev->freq_table);
+
+	thermal_cooling_device_unregister(ccdev->cdev);
+	release_idr(ccdev->id);
+}
+EXPORT_SYMBOL_GPL(clock_cooling_unregister);
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index ad09e51ffae..07a9629edf4 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -4,6 +4,8 @@
  *  Copyright (C) 2012	Samsung Electronics Co., Ltd(http://www.samsung.com)
  *  Copyright (C) 2012  Amit Daniel <amit.kachhap@linaro.org>
  *
+ *  Copyright (C) 2014  Viresh Kumar <viresh.kumar@linaro.org>
+ *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
@@ -24,10 +26,40 @@
 #include <linux/thermal.h>
 #include <linux/cpufreq.h>
 #include <linux/err.h>
+#include <linux/pm_opp.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/cpu_cooling.h>
 
+#include <trace/events/thermal.h>
+
+/*
+ * Cooling state <-> CPUFreq frequency
+ *
+ * Cooling states are translated to frequencies throughout this driver and this
+ * is the relation between them.
+ *
+ * Highest cooling state corresponds to lowest possible frequency.
+ *
+ * i.e.
+ *	level 0 --> 1st Max Freq
+ *	level 1 --> 2nd Max Freq
+ *	...
+ */
+
+/**
+ * struct power_table - frequency to power conversion
+ * @frequency:	frequency in KHz
+ * @power:	power in mW
+ *
+ * This structure is built when the cooling device registers and helps
+ * in translating frequency to power and viceversa.
+ */
+struct power_table {
+	u32 frequency;
+	u32 power;
+};
+
 /**
  * struct cpufreq_cooling_device - data for cooling device with cpufreq
  * @id: unique integer value corresponding to each cpufreq_cooling_device
@@ -38,25 +70,43 @@
  *	cooling	devices.
  * @cpufreq_val: integer value representing the absolute value of the clipped
  *	frequency.
+ * @max_level: maximum cooling level. One less than total number of valid
+ *	cpufreq frequencies.
  * @allowed_cpus: all the cpus involved for this cpufreq_cooling_device.
+ * @node: list_head to link all cpufreq_cooling_device together.
+ * @last_load: load measured by the latest call to cpufreq_get_actual_power()
+ * @time_in_idle: previous reading of the absolute time that this cpu was idle
+ * @time_in_idle_timestamp: wall time of the last invocation of
+ *	get_cpu_idle_time_us()
+ * @dyn_power_table: array of struct power_table for frequency to power
+ *	conversion, sorted in ascending order.
+ * @dyn_power_table_entries: number of entries in the @dyn_power_table array
+ * @cpu_dev: the first cpu_device from @allowed_cpus that has OPPs registered
+ * @plat_get_static_power: callback to calculate the static power
  *
- * This structure is required for keeping information of each
- * cpufreq_cooling_device registered. In order to prevent corruption of this a
- * mutex lock cooling_cpufreq_lock is used.
+ * This structure is required for keeping information of each registered
+ * cpufreq_cooling_device.
  */
 struct cpufreq_cooling_device {
 	int id;
 	struct thermal_cooling_device *cool_dev;
 	unsigned int cpufreq_state;
 	unsigned int cpufreq_val;
+	unsigned int max_level;
+	unsigned int *freq_table;	/* In descending order */
 	struct cpumask allowed_cpus;
 	struct list_head node;
+	u32 last_load;
+	u64 *time_in_idle;
+	u64 *time_in_idle_timestamp;
+	struct power_table *dyn_power_table;
+	int dyn_power_table_entries;
+	struct device *cpu_dev;
+	get_static_t plat_get_static_power;
 };
 static DEFINE_IDR(cpufreq_idr);
 static DEFINE_MUTEX(cooling_cpufreq_lock);
 
-static unsigned int cpufreq_dev_count;
-
 static LIST_HEAD(cpufreq_dev_list);
 
 /**
@@ -98,120 +148,30 @@ static void release_idr(struct idr *idr, int id)
 /* Below code defines functions to be used for cpufreq as cooling device */
 
 /**
- * is_cpufreq_valid - function to check frequency transitioning capability.
- * @cpu: cpu for which check is needed.
+ * get_level: Find the level for a particular frequency
+ * @cpufreq_dev: cpufreq_dev for which the property is required
+ * @freq: Frequency
  *
- * This function will check the current state of the system if
- * it is capable of changing the frequency for a given @cpu.
- *
- * Return: 0 if the system is not currently capable of changing
- * the frequency of given cpu. !0 in case the frequency is changeable.
- */
-static int is_cpufreq_valid(int cpu)
-{
-	struct cpufreq_policy policy;
-
-	return !cpufreq_get_policy(&policy, cpu);
-}
-
-enum cpufreq_cooling_property {
-	GET_LEVEL,
-	GET_FREQ,
-	GET_MAXL,
-};
-
-/**
- * get_property - fetch a property of interest for a give cpu.
- * @cpu: cpu for which the property is required
- * @input: query parameter
- * @output: query return
- * @property: type of query (frequency, level, max level)
- *
- * This is the common function to
- * 1. get maximum cpu cooling states
- * 2. translate frequency to cooling state
- * 3. translate cooling state to frequency
- * Note that the code may be not in good shape
- * but it is written in this way in order to:
- * a) reduce duplicate code as most of the code can be shared.
- * b) make sure the logic is consistent when translating between
- *    cooling states and frequencies.
- *
- * Return: 0 on success, -EINVAL when invalid parameters are passed.
+ * Return: level on success, THERMAL_CSTATE_INVALID on error.
  */
-static int get_property(unsigned int cpu, unsigned long input,
-			unsigned int *output,
-			enum cpufreq_cooling_property property)
+static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_dev,
+			       unsigned int freq)
 {
-	int i;
-	unsigned long max_level = 0, level = 0;
-	unsigned int freq = CPUFREQ_ENTRY_INVALID;
-	int descend = -1;
-	struct cpufreq_frequency_table *pos, *table =
-					cpufreq_frequency_get_table(cpu);
-
-	if (!output)
-		return -EINVAL;
-
-	if (!table)
-		return -EINVAL;
-
-	cpufreq_for_each_valid_entry(pos, table) {
-		/* ignore duplicate entry */
-		if (freq == pos->frequency)
-			continue;
-
-		/* get the frequency order */
-		if (freq != CPUFREQ_ENTRY_INVALID && descend == -1)
-			descend = freq > pos->frequency;
-
-		freq = pos->frequency;
-		max_level++;
-	}
-
-	/* No valid cpu frequency entry */
-	if (max_level == 0)
-		return -EINVAL;
+	unsigned long level;
 
-	/* max_level is an index, not a counter */
-	max_level--;
-
-	/* get max level */
-	if (property == GET_MAXL) {
-		*output = (unsigned int)max_level;
-		return 0;
-	}
-
-	if (property == GET_FREQ)
-		level = descend ? input : (max_level - input);
-
-	i = 0;
-	cpufreq_for_each_valid_entry(pos, table) {
-		/* ignore duplicate entry */
-		if (freq == pos->frequency)
-			continue;
-
-		/* now we have a valid frequency entry */
-		freq = pos->frequency;
+	for (level = 0; level <= cpufreq_dev->max_level; level++) {
+		if (freq == cpufreq_dev->freq_table[level])
+			return level;
 
-		if (property == GET_LEVEL && (unsigned int)input == freq) {
-			/* get level by frequency */
-			*output = descend ? i : (max_level - i);
-			return 0;
-		}
-		if (property == GET_FREQ && level == i) {
-			/* get frequency by level */
-			*output = freq;
-			return 0;
-		}
-		i++;
+		if (freq > cpufreq_dev->freq_table[level])
+			break;
 	}
 
-	return -EINVAL;
+	return THERMAL_CSTATE_INVALID;
 }
 
 /**
- * cpufreq_cooling_get_level - for a give cpu, return the cooling level.
+ * cpufreq_cooling_get_level - for a given cpu, return the cooling level.
  * @cpu: cpu for which the level is required
  * @freq: the frequency of interest
  *
@@ -223,119 +183,268 @@ static int get_property(unsigned int cpu, unsigned long input,
  */
 unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq)
 {
-	unsigned int val;
+	struct cpufreq_cooling_device *cpufreq_dev;
 
-	if (get_property(cpu, (unsigned long)freq, &val, GET_LEVEL))
-		return THERMAL_CSTATE_INVALID;
+	mutex_lock(&cooling_cpufreq_lock);
+	list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
+		if (cpumask_test_cpu(cpu, &cpufreq_dev->allowed_cpus)) {
+			mutex_unlock(&cooling_cpufreq_lock);
+			return get_level(cpufreq_dev, freq);
+		}
+	}
+	mutex_unlock(&cooling_cpufreq_lock);
 
-	return (unsigned long)val;
+	pr_err("%s: cpu:%d not part of any cooling device\n", __func__, cpu);
+	return THERMAL_CSTATE_INVALID;
 }
 EXPORT_SYMBOL_GPL(cpufreq_cooling_get_level);
 
 /**
- * get_cpu_frequency - get the absolute value of frequency from level.
- * @cpu: cpu for which frequency is fetched.
- * @level: cooling level
+ * cpufreq_thermal_notifier - notifier callback for cpufreq policy change.
+ * @nb:	struct notifier_block * with callback info.
+ * @event: value showing cpufreq event for which this function invoked.
+ * @data: callback-specific data
  *
- * This function matches cooling level with frequency. Based on a cooling level
- * of frequency, equals cooling state of cpu cooling device, it will return
- * the corresponding frequency.
- *	e.g level=0 --> 1st MAX FREQ, level=1 ---> 2nd MAX FREQ, .... etc
+ * Callback to hijack the notification on cpufreq policy transition.
+ * Every time there is a change in policy, we will intercept and
+ * update the cpufreq policy with thermal constraints.
  *
- * Return: 0 on error, the corresponding frequency otherwise.
+ * Return: 0 (success)
  */
-static unsigned int get_cpu_frequency(unsigned int cpu, unsigned long level)
+static int cpufreq_thermal_notifier(struct notifier_block *nb,
+				    unsigned long event, void *data)
 {
-	int ret = 0;
-	unsigned int freq;
+	struct cpufreq_policy *policy = data;
+	unsigned long max_freq = 0;
+	struct cpufreq_cooling_device *cpufreq_dev;
 
-	ret = get_property(cpu, level, &freq, GET_FREQ);
-	if (ret)
-		return 0;
+	switch (event) {
+
+	case CPUFREQ_ADJUST:
+		mutex_lock(&cooling_cpufreq_lock);
+		list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
+			if (!cpumask_test_cpu(policy->cpu,
+					      &cpufreq_dev->allowed_cpus))
+				continue;
 
-	return freq;
+			max_freq = cpufreq_dev->cpufreq_val;
+
+			if (policy->max != max_freq)
+				cpufreq_verify_within_limits(policy, 0,
+							     max_freq);
+		}
+		mutex_unlock(&cooling_cpufreq_lock);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
 }
 
 /**
- * cpufreq_apply_cooling - function to apply frequency clipping.
- * @cpufreq_device: cpufreq_cooling_device pointer containing frequency
- *	clipping data.
- * @cooling_state: value of the cooling state.
+ * build_dyn_power_table() - create a dynamic power to frequency table
+ * @cpufreq_device:	the cpufreq cooling device in which to store the table
+ * @capacitance: dynamic power coefficient for these cpus
  *
- * Function used to make sure the cpufreq layer is aware of current thermal
- * limits. The limits are applied by updating the cpufreq policy.
+ * Build a dynamic power to frequency table for this cpu and store it
+ * in @cpufreq_device.  This table will be used in cpu_power_to_freq() and
+ * cpu_freq_to_power() to convert between power and frequency
+ * efficiently.  Power is stored in mW, frequency in KHz.  The
+ * resulting table is in ascending order.
  *
- * Return: 0 on success, an error code otherwise (-EINVAL in case wrong
- * cooling state).
+ * Return: 0 on success, -E* on error.
  */
-static int cpufreq_apply_cooling(struct cpufreq_cooling_device *cpufreq_device,
-				 unsigned long cooling_state)
+static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
+				 u32 capacitance)
 {
-	unsigned int cpuid, clip_freq;
-	struct cpumask *mask = &cpufreq_device->allowed_cpus;
-	unsigned int cpu = cpumask_any(mask);
+	struct power_table *power_table;
+	struct dev_pm_opp *opp;
+	struct device *dev = NULL;
+	int num_opps = 0, cpu, i, ret = 0;
+	unsigned long freq;
+
+	rcu_read_lock();
+
+	for_each_cpu(cpu, &cpufreq_device->allowed_cpus) {
+		dev = get_cpu_device(cpu);
+		if (!dev) {
+			dev_warn(&cpufreq_device->cool_dev->device,
+				 "No cpu device for cpu %d\n", cpu);
+			continue;
+		}
 
+		num_opps = dev_pm_opp_get_opp_count(dev);
+		if (num_opps > 0) {
+			break;
+		} else if (num_opps < 0) {
+			ret = num_opps;
+			goto unlock;
+		}
+	}
 
-	/* Check if the old cooling action is same as new cooling action */
-	if (cpufreq_device->cpufreq_state == cooling_state)
-		return 0;
+	if (num_opps == 0) {
+		ret = -EINVAL;
+		goto unlock;
+	}
 
-	clip_freq = get_cpu_frequency(cpu, cooling_state);
-	if (!clip_freq)
-		return -EINVAL;
+	power_table = kcalloc(num_opps, sizeof(*power_table), GFP_KERNEL);
 
-	cpufreq_device->cpufreq_state = cooling_state;
-	cpufreq_device->cpufreq_val = clip_freq;
+	for (freq = 0, i = 0;
+	     opp = dev_pm_opp_find_freq_ceil(dev, &freq), !IS_ERR(opp);
+	     freq++, i++) {
+		u32 freq_mhz, voltage_mv;
+		u64 power;
+
+		freq_mhz = freq / 1000000;
+		voltage_mv = dev_pm_opp_get_voltage(opp) / 1000;
+
+		/*
+		 * Do the multiplication with MHz and millivolt so as
+		 * to not overflow.
+		 */
+		power = (u64)capacitance * freq_mhz * voltage_mv * voltage_mv;
+		do_div(power, 1000000000);
+
+		/* frequency is stored in power_table in KHz */
+		power_table[i].frequency = freq / 1000;
 
-	for_each_cpu(cpuid, mask) {
-		if (is_cpufreq_valid(cpuid))
-			cpufreq_update_policy(cpuid);
+		/* power is stored in mW */
+		power_table[i].power = power;
 	}
 
-	return 0;
+	if (i == 0) {
+		ret = PTR_ERR(opp);
+		goto unlock;
+	}
+
+	cpufreq_device->cpu_dev = dev;
+	cpufreq_device->dyn_power_table = power_table;
+	cpufreq_device->dyn_power_table_entries = i;
+
+unlock:
+	rcu_read_unlock();
+	return ret;
+}
+
+static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_device,
+			     u32 freq)
+{
+	int i;
+	struct power_table *pt = cpufreq_device->dyn_power_table;
+
+	for (i = 1; i < cpufreq_device->dyn_power_table_entries; i++)
+		if (freq < pt[i].frequency)
+			break;
+
+	return pt[i - 1].power;
+}
+
+static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_device,
+			     u32 power)
+{
+	int i;
+	struct power_table *pt = cpufreq_device->dyn_power_table;
+
+	for (i = 1; i < cpufreq_device->dyn_power_table_entries; i++)
+		if (power < pt[i].power)
+			break;
+
+	return pt[i - 1].frequency;
 }
 
 /**
- * cpufreq_thermal_notifier - notifier callback for cpufreq policy change.
- * @nb:	struct notifier_block * with callback info.
- * @event: value showing cpufreq event for which this function invoked.
- * @data: callback-specific data
+ * get_load() - get load for a cpu since last updated
+ * @cpufreq_device:	&struct cpufreq_cooling_device for this cpu
+ * @cpu:	cpu number
  *
- * Callback to hijack the notification on cpufreq policy transition.
- * Every time there is a change in policy, we will intercept and
- * update the cpufreq policy with thermal constraints.
- *
- * Return: 0 (success)
+ * Return: The average load of cpu @cpu in percentage since this
+ * function was last called.
  */
-static int cpufreq_thermal_notifier(struct notifier_block *nb,
-				    unsigned long event, void *data)
+static u32 get_load(struct cpufreq_cooling_device *cpufreq_device, int cpu)
 {
-	struct cpufreq_policy *policy = data;
-	unsigned long max_freq = 0;
-	struct cpufreq_cooling_device *cpufreq_dev;
+	u32 load;
+	u64 now, now_idle, delta_time, delta_idle;
 
-	if (event != CPUFREQ_ADJUST)
+	now_idle = get_cpu_idle_time(cpu, &now, 0);
+	delta_idle = now_idle - cpufreq_device->time_in_idle[cpu];
+	delta_time = now - cpufreq_device->time_in_idle_timestamp[cpu];
+
+	if (delta_time <= delta_idle)
+		load = 0;
+	else
+		load = div64_u64(100 * (delta_time - delta_idle), delta_time);
+
+	cpufreq_device->time_in_idle[cpu] = now_idle;
+	cpufreq_device->time_in_idle_timestamp[cpu] = now;
+
+	return load;
+}
+
+/**
+ * get_static_power() - calculate the static power consumed by the cpus
+ * @cpufreq_device:	struct &cpufreq_cooling_device for this cpu cdev
+ * @tz:		thermal zone device in which we're operating
+ * @freq:	frequency in KHz
+ * @power:	pointer in which to store the calculated static power
+ *
+ * Calculate the static power consumed by the cpus described by
+ * @cpu_actor running at frequency @freq.  This function relies on a
+ * platform specific function that should have been provided when the
+ * actor was registered.  If it wasn't, the static power is assumed to
+ * be negligible.  The calculated static power is stored in @power.
+ *
+ * Return: 0 on success, -E* on failure.
+ */
+static int get_static_power(struct cpufreq_cooling_device *cpufreq_device,
+			    struct thermal_zone_device *tz, unsigned long freq,
+			    u32 *power)
+{
+	struct dev_pm_opp *opp;
+	unsigned long voltage;
+	struct cpumask *cpumask = &cpufreq_device->allowed_cpus;
+	unsigned long freq_hz = freq * 1000;
+
+	if (!cpufreq_device->plat_get_static_power ||
+	    !cpufreq_device->cpu_dev) {
+		*power = 0;
 		return 0;
+	}
 
-	mutex_lock(&cooling_cpufreq_lock);
-	list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
-		if (!cpumask_test_cpu(policy->cpu,
-					&cpufreq_dev->allowed_cpus))
-			continue;
+	rcu_read_lock();
 
-		if (!cpufreq_dev->cpufreq_val)
-			cpufreq_dev->cpufreq_val = get_cpu_frequency(
-					cpumask_any(&cpufreq_dev->allowed_cpus),
-					cpufreq_dev->cpufreq_state);
+	opp = dev_pm_opp_find_freq_exact(cpufreq_device->cpu_dev, freq_hz,
+					 true);
+	voltage = dev_pm_opp_get_voltage(opp);
 
-		max_freq = cpufreq_dev->cpufreq_val;
+	rcu_read_unlock();
 
-		if (policy->max != max_freq)
-			cpufreq_verify_within_limits(policy, 0, max_freq);
+	if (voltage == 0) {
+		dev_warn_ratelimited(cpufreq_device->cpu_dev,
+				     "Failed to get voltage for frequency %lu: %ld\n",
+				     freq_hz, IS_ERR(opp) ? PTR_ERR(opp) : 0);
+		return -EINVAL;
 	}
-	mutex_unlock(&cooling_cpufreq_lock);
 
-	return 0;
+	return cpufreq_device->plat_get_static_power(cpumask, tz->passive_delay,
+						     voltage, power);
+}
+
+/**
+ * get_dynamic_power() - calculate the dynamic power
+ * @cpufreq_device:	&cpufreq_cooling_device for this cdev
+ * @freq:	current frequency
+ *
+ * Return: the dynamic power consumed by the cpus described by
+ * @cpufreq_device.
+ */
+static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_device,
+			     unsigned long freq)
+{
+	u32 raw_cpu_power;
+
+	raw_cpu_power = cpu_freq_to_power(cpufreq_device, freq);
+	return (raw_cpu_power * cpufreq_device->last_load) / 100;
 }
 
 /* cpufreq cooling device callback functions are defined below */
@@ -354,19 +463,9 @@ static int cpufreq_get_max_state(struct thermal_cooling_device *cdev,
 				 unsigned long *state)
 {
 	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
-	struct cpumask *mask = &cpufreq_device->allowed_cpus;
-	unsigned int cpu;
-	unsigned int count = 0;
-	int ret;
-
-	cpu = cpumask_any(mask);
 
-	ret = get_property(cpu, 0, &count, GET_MAXL);
-
-	if (count > 0)
-		*state = count;
-
-	return ret;
+	*state = cpufreq_device->max_level;
+	return 0;
 }
 
 /**
@@ -403,12 +502,225 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
 				 unsigned long state)
 {
 	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+	unsigned int cpu = cpumask_any(&cpufreq_device->allowed_cpus);
+	unsigned int clip_freq;
+
+	/* Request state should be less than max_level */
+	if (WARN_ON(state > cpufreq_device->max_level))
+		return -EINVAL;
+
+	/* Check if the old cooling action is same as new cooling action */
+	if (cpufreq_device->cpufreq_state == state)
+		return 0;
+
+	clip_freq = cpufreq_device->freq_table[state];
+	cpufreq_device->cpufreq_state = state;
+	cpufreq_device->cpufreq_val = clip_freq;
+
+	cpufreq_update_policy(cpu);
+
+	return 0;
+}
+
+/**
+ * cpufreq_get_requested_power() - get the current power
+ * @cdev:	&thermal_cooling_device pointer
+ * @tz:		a valid thermal zone device pointer
+ * @power:	pointer in which to store the resulting power
+ *
+ * Calculate the current power consumption of the cpus in milliwatts
+ * and store it in @power.  This function should actually calculate
+ * the requested power, but it's hard to get the frequency that
+ * cpufreq would have assigned if there were no thermal limits.
+ * Instead, we calculate the current power on the assumption that the
+ * immediate future will look like the immediate past.
+ *
+ * We use the current frequency and the average load since this
+ * function was last called.  In reality, there could have been
+ * multiple opps since this function was last called and that affects
+ * the load calculation.  While it's not perfectly accurate, this
+ * simplification is good enough and works.  REVISIT this, as more
+ * complex code may be needed if experiments show that it's not
+ * accurate enough.
+ *
+ * Return: 0 on success, -E* if getting the static power failed.
+ */
+static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
+				       struct thermal_zone_device *tz,
+				       u32 *power)
+{
+	unsigned long freq;
+	int i = 0, cpu, ret;
+	u32 static_power, dynamic_power, total_load = 0;
+	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+	u32 *load_cpu = NULL;
+
+	cpu = cpumask_any_and(&cpufreq_device->allowed_cpus, cpu_online_mask);
+
+	/*
+	 * All the CPUs are offline, thus the requested power by
+	 * the cdev is 0
+	 */
+	if (cpu >= nr_cpu_ids) {
+		*power = 0;
+		return 0;
+	}
+
+	freq = cpufreq_quick_get(cpu);
+
+	if (trace_thermal_power_cpu_get_power_enabled()) {
+		u32 ncpus = cpumask_weight(&cpufreq_device->allowed_cpus);
+
+		load_cpu = devm_kcalloc(&cdev->device, ncpus, sizeof(*load_cpu),
+					GFP_KERNEL);
+	}
+
+	for_each_cpu(cpu, &cpufreq_device->allowed_cpus) {
+		u32 load;
+
+		if (cpu_online(cpu))
+			load = get_load(cpufreq_device, cpu);
+		else
+			load = 0;
+
+		total_load += load;
+		if (trace_thermal_power_cpu_limit_enabled() && load_cpu)
+			load_cpu[i] = load;
+
+		i++;
+	}
+
+	cpufreq_device->last_load = total_load;
+
+	dynamic_power = get_dynamic_power(cpufreq_device, freq);
+	ret = get_static_power(cpufreq_device, tz, freq, &static_power);
+	if (ret) {
+		if (load_cpu)
+			devm_kfree(&cdev->device, load_cpu);
+		return ret;
+	}
+
+	if (load_cpu) {
+		trace_thermal_power_cpu_get_power(
+			&cpufreq_device->allowed_cpus,
+			freq, load_cpu, i, dynamic_power, static_power);
+
+		devm_kfree(&cdev->device, load_cpu);
+	}
+
+	*power = static_power + dynamic_power;
+	return 0;
+}
+
+/**
+ * cpufreq_state2power() - convert a cpu cdev state to power consumed
+ * @cdev:	&thermal_cooling_device pointer
+ * @tz:		a valid thermal zone device pointer
+ * @state:	cooling device state to be converted
+ * @power:	pointer in which to store the resulting power
+ *
+ * Convert cooling device state @state into power consumption in
+ * milliwatts assuming 100% load.  Store the calculated power in
+ * @power.
+ *
+ * Return: 0 on success, -EINVAL if the cooling device state could not
+ * be converted into a frequency or other -E* if there was an error
+ * when calculating the static power.
+ */
+static int cpufreq_state2power(struct thermal_cooling_device *cdev,
+			       struct thermal_zone_device *tz,
+			       unsigned long state, u32 *power)
+{
+	unsigned int freq, num_cpus;
+	cpumask_t cpumask;
+	u32 static_power, dynamic_power;
+	int ret;
+	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+
+	cpumask_and(&cpumask, &cpufreq_device->allowed_cpus, cpu_online_mask);
+	num_cpus = cpumask_weight(&cpumask);
+
+	/* None of our cpus are online, so no power */
+	if (num_cpus == 0) {
+		*power = 0;
+		return 0;
+	}
+
+	freq = cpufreq_device->freq_table[state];
+	if (!freq)
+		return -EINVAL;
+
+	dynamic_power = cpu_freq_to_power(cpufreq_device, freq) * num_cpus;
+	ret = get_static_power(cpufreq_device, tz, freq, &static_power);
+	if (ret)
+		return ret;
+
+	*power = static_power + dynamic_power;
+	return 0;
+}
+
+/**
+ * cpufreq_power2state() - convert power to a cooling device state
+ * @cdev:	&thermal_cooling_device pointer
+ * @tz:		a valid thermal zone device pointer
+ * @power:	power in milliwatts to be converted
+ * @state:	pointer in which to store the resulting state
+ *
+ * Calculate a cooling device state for the cpus described by @cdev
+ * that would allow them to consume at most @power mW and store it in
+ * @state.  Note that this calculation depends on external factors
+ * such as the cpu load or the current static power.  Calling this
+ * function with the same power as input can yield different cooling
+ * device states depending on those external factors.
+ *
+ * Return: 0 on success, -ENODEV if no cpus are online or -EINVAL if
+ * the calculated frequency could not be converted to a valid state.
+ * The latter should not happen unless the frequencies available to
+ * cpufreq have changed since the initialization of the cpu cooling
+ * device.
+ */
+static int cpufreq_power2state(struct thermal_cooling_device *cdev,
+			       struct thermal_zone_device *tz, u32 power,
+			       unsigned long *state)
+{
+	unsigned int cpu, cur_freq, target_freq;
+	int ret;
+	s32 dyn_power;
+	u32 last_load, normalised_power, static_power;
+	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+
+	cpu = cpumask_any_and(&cpufreq_device->allowed_cpus, cpu_online_mask);
+
+	/* None of our cpus are online */
+	if (cpu >= nr_cpu_ids)
+		return -ENODEV;
+
+	cur_freq = cpufreq_quick_get(cpu);
+	ret = get_static_power(cpufreq_device, tz, cur_freq, &static_power);
+	if (ret)
+		return ret;
 
-	return cpufreq_apply_cooling(cpufreq_device, state);
+	dyn_power = power - static_power;
+	dyn_power = dyn_power > 0 ? dyn_power : 0;
+	last_load = cpufreq_device->last_load ?: 1;
+	normalised_power = (dyn_power * 100) / last_load;
+	target_freq = cpu_power_to_freq(cpufreq_device, normalised_power);
+
+	*state = cpufreq_cooling_get_level(cpu, target_freq);
+	if (*state == THERMAL_CSTATE_INVALID) {
+		dev_warn_ratelimited(&cdev->device,
+				     "Failed to convert %dKHz for cpu %d into a cdev state\n",
+				     target_freq, cpu);
+		return -EINVAL;
+	}
+
+	trace_thermal_power_cpu_limit(&cpufreq_device->allowed_cpus,
+				      target_freq, *state, power);
+	return 0;
 }
 
 /* Bind cpufreq callbacks to thermal cooling device ops */
-static struct thermal_cooling_device_ops const cpufreq_cooling_ops = {
+static struct thermal_cooling_device_ops cpufreq_cooling_ops = {
 	.get_max_state = cpufreq_get_max_state,
 	.get_cur_state = cpufreq_get_cur_state,
 	.set_cur_state = cpufreq_set_cur_state,
@@ -419,10 +731,28 @@ static struct notifier_block thermal_cpufreq_notifier_block = {
 	.notifier_call = cpufreq_thermal_notifier,
 };
 
+static unsigned int find_next_max(struct cpufreq_frequency_table *table,
+				  unsigned int prev_max)
+{
+	struct cpufreq_frequency_table *pos;
+	unsigned int max = 0;
+
+	cpufreq_for_each_valid_entry(pos, table) {
+		if (pos->frequency > max && pos->frequency < prev_max)
+			max = pos->frequency;
+	}
+
+	return max;
+}
+
 /**
  * __cpufreq_cooling_register - helper function to create cpufreq cooling device
  * @np: a valid struct device_node to the cooling device device tree node
  * @clip_cpus: cpumask of cpus where the frequency constraints will happen.
+ * Normally this should be same as cpufreq policy->related_cpus.
+ * @capacitance: dynamic power coefficient for these cpus
+ * @plat_static_func: function to calculate the static power consumed by these
+ *                    cpus (optional)
  *
  * This interface function registers the cpufreq cooling device with the name
  * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
@@ -434,40 +764,77 @@ static struct notifier_block thermal_cpufreq_notifier_block = {
  */
 static struct thermal_cooling_device *
 __cpufreq_cooling_register(struct device_node *np,
-			   const struct cpumask *clip_cpus)
+			const struct cpumask *clip_cpus, u32 capacitance,
+			get_static_t plat_static_func)
 {
 	struct thermal_cooling_device *cool_dev;
-	struct cpufreq_cooling_device *cpufreq_dev = NULL;
-	unsigned int min = 0, max = 0;
+	struct cpufreq_cooling_device *cpufreq_dev;
 	char dev_name[THERMAL_NAME_LENGTH];
-	int ret = 0, i;
-	struct cpufreq_policy policy;
+	struct cpufreq_frequency_table *pos, *table;
+	unsigned int freq, i, num_cpus;
+	int ret;
 
-	/* Verify that all the clip cpus have same freq_min, freq_max limit */
-	for_each_cpu(i, clip_cpus) {
-		/* continue if cpufreq policy not found and not return error */
-		if (!cpufreq_get_policy(&policy, i))
-			continue;
-		if (min == 0 && max == 0) {
-			min = policy.cpuinfo.min_freq;
-			max = policy.cpuinfo.max_freq;
-		} else {
-			if (min != policy.cpuinfo.min_freq ||
-			    max != policy.cpuinfo.max_freq)
-				return ERR_PTR(-EINVAL);
-		}
+	table = cpufreq_frequency_get_table(cpumask_first(clip_cpus));
+	if (!table) {
+		pr_debug("%s: CPUFreq table not found\n", __func__);
+		return ERR_PTR(-EPROBE_DEFER);
 	}
-	cpufreq_dev = kzalloc(sizeof(struct cpufreq_cooling_device),
-			      GFP_KERNEL);
+
+	cpufreq_dev = kzalloc(sizeof(*cpufreq_dev), GFP_KERNEL);
 	if (!cpufreq_dev)
 		return ERR_PTR(-ENOMEM);
 
+	num_cpus = cpumask_weight(clip_cpus);
+	cpufreq_dev->time_in_idle = kcalloc(num_cpus,
+					    sizeof(*cpufreq_dev->time_in_idle),
+					    GFP_KERNEL);
+	if (!cpufreq_dev->time_in_idle) {
+		cool_dev = ERR_PTR(-ENOMEM);
+		goto free_cdev;
+	}
+
+	cpufreq_dev->time_in_idle_timestamp =
+		kcalloc(num_cpus, sizeof(*cpufreq_dev->time_in_idle_timestamp),
+			GFP_KERNEL);
+	if (!cpufreq_dev->time_in_idle_timestamp) {
+		cool_dev = ERR_PTR(-ENOMEM);
+		goto free_time_in_idle;
+	}
+
+	/* Find max levels */
+	cpufreq_for_each_valid_entry(pos, table)
+		cpufreq_dev->max_level++;
+
+	cpufreq_dev->freq_table = kmalloc(sizeof(*cpufreq_dev->freq_table) *
+					  cpufreq_dev->max_level, GFP_KERNEL);
+	if (!cpufreq_dev->freq_table) {
+		cool_dev = ERR_PTR(-ENOMEM);
+		goto free_time_in_idle_timestamp;
+	}
+
+	/* max_level is an index, not a counter */
+	cpufreq_dev->max_level--;
+
 	cpumask_copy(&cpufreq_dev->allowed_cpus, clip_cpus);
 
+	if (capacitance) {
+		cpufreq_cooling_ops.get_requested_power =
+			cpufreq_get_requested_power;
+		cpufreq_cooling_ops.state2power = cpufreq_state2power;
+		cpufreq_cooling_ops.power2state = cpufreq_power2state;
+		cpufreq_dev->plat_get_static_power = plat_static_func;
+
+		ret = build_dyn_power_table(cpufreq_dev, capacitance);
+		if (ret) {
+			cool_dev = ERR_PTR(ret);
+			goto free_table;
+		}
+	}
+
 	ret = get_idr(&cpufreq_idr, &cpufreq_dev->id);
 	if (ret) {
-		kfree(cpufreq_dev);
-		return ERR_PTR(-EINVAL);
+		cool_dev = ERR_PTR(ret);
+		goto free_table;
 	}
 
 	snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d",
@@ -475,25 +842,48 @@ __cpufreq_cooling_register(struct device_node *np,
 
 	cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev,
 						      &cpufreq_cooling_ops);
-	if (IS_ERR(cool_dev)) {
-		release_idr(&cpufreq_idr, cpufreq_dev->id);
-		kfree(cpufreq_dev);
-		return cool_dev;
+	if (IS_ERR(cool_dev))
+		goto remove_idr;
+
+	/* Fill freq-table in descending order of frequencies */
+	for (i = 0, freq = -1; i <= cpufreq_dev->max_level; i++) {
+		freq = find_next_max(table, freq);
+		cpufreq_dev->freq_table[i] = freq;
+
+		/* Warn for duplicate entries */
+		if (!freq)
+			pr_warn("%s: table has duplicate entries\n", __func__);
+		else
+			pr_debug("%s: freq:%u KHz\n", __func__, freq);
 	}
+
+	cpufreq_dev->cpufreq_val = cpufreq_dev->freq_table[0];
 	cpufreq_dev->cool_dev = cool_dev;
-	cpufreq_dev->cpufreq_state = 0;
+
 	mutex_lock(&cooling_cpufreq_lock);
 
 	/* Register the notifier for first cpufreq cooling device */
-	if (cpufreq_dev_count == 0)
+	if (list_empty(&cpufreq_dev_list))
 		cpufreq_register_notifier(&thermal_cpufreq_notifier_block,
 					  CPUFREQ_POLICY_NOTIFIER);
-	cpufreq_dev_count++;
 	list_add(&cpufreq_dev->node, &cpufreq_dev_list);
 
 	mutex_unlock(&cooling_cpufreq_lock);
 
 	return cool_dev;
+
+remove_idr:
+	release_idr(&cpufreq_idr, cpufreq_dev->id);
+free_table:
+	kfree(cpufreq_dev->freq_table);
+free_time_in_idle_timestamp:
+	kfree(cpufreq_dev->time_in_idle_timestamp);
+free_time_in_idle:
+	kfree(cpufreq_dev->time_in_idle);
+free_cdev:
+	kfree(cpufreq_dev);
+
+	return cool_dev;
 }
 
 /**
@@ -510,7 +900,7 @@ __cpufreq_cooling_register(struct device_node *np,
 struct thermal_cooling_device *
 cpufreq_cooling_register(const struct cpumask *clip_cpus)
 {
-	return __cpufreq_cooling_register(NULL, clip_cpus);
+	return __cpufreq_cooling_register(NULL, clip_cpus, 0, NULL);
 }
 EXPORT_SYMBOL_GPL(cpufreq_cooling_register);
 
@@ -534,11 +924,78 @@ of_cpufreq_cooling_register(struct device_node *np,
 	if (!np)
 		return ERR_PTR(-EINVAL);
 
-	return __cpufreq_cooling_register(np, clip_cpus);
+	return __cpufreq_cooling_register(np, clip_cpus, 0, NULL);
 }
 EXPORT_SYMBOL_GPL(of_cpufreq_cooling_register);
 
 /**
+ * cpufreq_power_cooling_register() - create cpufreq cooling device with power extensions
+ * @clip_cpus:	cpumask of cpus where the frequency constraints will happen
+ * @capacitance:	dynamic power coefficient for these cpus
+ * @plat_static_func:	function to calculate the static power consumed by these
+ *			cpus (optional)
+ *
+ * This interface function registers the cpufreq cooling device with
+ * the name "thermal-cpufreq-%x".  This api can support multiple
+ * instances of cpufreq cooling devices.  Using this function, the
+ * cooling device will implement the power extensions by using a
+ * simple cpu power model.  The cpus must have registered their OPPs
+ * using the OPP library.
+ *
+ * An optional @plat_static_func may be provided to calculate the
+ * static power consumed by these cpus.  If the platform's static
+ * power consumption is unknown or negligible, make it NULL.
+ *
+ * Return: a valid struct thermal_cooling_device pointer on success,
+ * on failure, it returns a corresponding ERR_PTR().
+ */
+struct thermal_cooling_device *
+cpufreq_power_cooling_register(const struct cpumask *clip_cpus, u32 capacitance,
+			       get_static_t plat_static_func)
+{
+	return __cpufreq_cooling_register(NULL, clip_cpus, capacitance,
+				plat_static_func);
+}
+EXPORT_SYMBOL(cpufreq_power_cooling_register);
+
+/**
+ * of_cpufreq_power_cooling_register() - create cpufreq cooling device with power extensions
+ * @np:	a valid struct device_node to the cooling device device tree node
+ * @clip_cpus:	cpumask of cpus where the frequency constraints will happen
+ * @capacitance:	dynamic power coefficient for these cpus
+ * @plat_static_func:	function to calculate the static power consumed by these
+ *			cpus (optional)
+ *
+ * This interface function registers the cpufreq cooling device with
+ * the name "thermal-cpufreq-%x".  This api can support multiple
+ * instances of cpufreq cooling devices.  Using this API, the cpufreq
+ * cooling device will be linked to the device tree node provided.
+ * Using this function, the cooling device will implement the power
+ * extensions by using a simple cpu power model.  The cpus must have
+ * registered their OPPs using the OPP library.
+ *
+ * An optional @plat_static_func may be provided to calculate the
+ * static power consumed by these cpus.  If the platform's static
+ * power consumption is unknown or negligible, make it NULL.
+ *
+ * Return: a valid struct thermal_cooling_device pointer on success,
+ * on failure, it returns a corresponding ERR_PTR().
+ */
+struct thermal_cooling_device *
+of_cpufreq_power_cooling_register(struct device_node *np,
+				  const struct cpumask *clip_cpus,
+				  u32 capacitance,
+				  get_static_t plat_static_func)
+{
+	if (!np)
+		return ERR_PTR(-EINVAL);
+
+	return __cpufreq_cooling_register(np, clip_cpus, capacitance,
+				plat_static_func);
+}
+EXPORT_SYMBOL(of_cpufreq_power_cooling_register);
+
+/**
  * cpufreq_cooling_unregister - function to remove cpufreq cooling device.
  * @cdev: thermal cooling device pointer.
  *
@@ -554,16 +1011,18 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 	cpufreq_dev = cdev->devdata;
 	mutex_lock(&cooling_cpufreq_lock);
 	list_del(&cpufreq_dev->node);
-	cpufreq_dev_count--;
 
 	/* Unregister the notifier for the last cpufreq cooling device */
-	if (cpufreq_dev_count == 0)
+	if (list_empty(&cpufreq_dev_list))
 		cpufreq_unregister_notifier(&thermal_cpufreq_notifier_block,
 					    CPUFREQ_POLICY_NOTIFIER);
 	mutex_unlock(&cooling_cpufreq_lock);
 
 	thermal_cooling_device_unregister(cpufreq_dev->cool_dev);
 	release_idr(&cpufreq_idr, cpufreq_dev->id);
+	kfree(cpufreq_dev->time_in_idle_timestamp);
+	kfree(cpufreq_dev->time_in_idle);
+	kfree(cpufreq_dev->freq_table);
 	kfree(cpufreq_dev);
 }
 EXPORT_SYMBOL_GPL(cpufreq_cooling_unregister);
diff --git a/drivers/thermal/db8500_cpufreq_cooling.c b/drivers/thermal/db8500_cpufreq_cooling.c
index 786d19263ab..1ac7ec651c3 100644
--- a/drivers/thermal/db8500_cpufreq_cooling.c
+++ b/drivers/thermal/db8500_cpufreq_cooling.c
@@ -18,7 +18,6 @@
  */
 
 #include <linux/cpu_cooling.h>
-#include <linux/cpufreq.h>
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -30,10 +29,6 @@ static int db8500_cpufreq_cooling_probe(struct platform_device *pdev)
 	struct thermal_cooling_device *cdev;
 	struct cpumask mask_val;
 
-	/* make sure cpufreq driver has been initialized */
-	if (!cpufreq_frequency_get_table(0))
-		return -EPROBE_DEFER;
-
 	cpumask_set_cpu(0, &mask_val);
 	cdev = cpufreq_cooling_register(&mask_val);
 
diff --git a/drivers/thermal/db8500_thermal.c b/drivers/thermal/db8500_thermal.c
index 1e3b3bf9f99..e3ccc2218eb 100644
--- a/drivers/thermal/db8500_thermal.c
+++ b/drivers/thermal/db8500_thermal.c
@@ -76,7 +76,7 @@ static int db8500_cdev_bind(struct thermal_zone_device *thermal,
 		upper = lower = i > max_state ? max_state : i;
 
 		ret = thermal_zone_bind_cooling_device(thermal, i, cdev,
-			upper, lower);
+			upper, lower, THERMAL_WEIGHT_DEFAULT);
 
 		dev_info(&cdev->device, "%s bind to %d: %d-%s\n", cdev->type,
 			i, ret, ret ? "fail" : "succeed");
diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c
new file mode 100644
index 00000000000..58da2a8d08d
--- /dev/null
+++ b/drivers/thermal/devfreq_cooling.c
@@ -0,0 +1,477 @@
+/*
+ * devfreq_cooling: Thermal cooling device implementation for devices using
+ *                  devfreq
+ *
+ * Copyright (C) 2014-2015 ARM Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/devfreq.h>
+#include <linux/devfreq_cooling.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/pm_opp.h>
+#include <linux/thermal.h>
+
+#include <trace/events/thermal.h>
+
+static DEFINE_MUTEX(devfreq_lock);
+static DEFINE_IDR(devfreq_idr);
+
+/**
+ * get_idr - function to get a unique id.
+ * @idr: struct idr * handle used to create a id.
+ * @id: int * value generated by this function.
+ *
+ * This function will populate @id with an unique
+ * id, using the idr API.
+ *
+ * Return: 0 on success, an error code on failure.
+ */
+static int get_idr(struct idr *idr, int *id)
+{
+	int ret;
+
+	mutex_lock(&devfreq_lock);
+	ret = idr_alloc(idr, NULL, 0, 0, GFP_KERNEL);
+	mutex_unlock(&devfreq_lock);
+	if (unlikely(ret < 0))
+		return ret;
+	*id = ret;
+
+	return 0;
+}
+
+/**
+ * release_idr - function to free the unique id.
+ * @idr: struct idr * handle used for creating the id.
+ * @id: int value representing the unique id.
+ */
+static void release_idr(struct idr *idr, int id)
+{
+	mutex_lock(&devfreq_lock);
+	idr_remove(idr, id);
+	mutex_unlock(&devfreq_lock);
+}
+
+static int enable_disable_opps(struct devfreq *df, int max_enabled_state)
+{
+	int i;
+	struct device *dev = df->dev.parent;
+
+	for (i = 0; i < df->profile->max_state; i++) {
+		struct dev_pm_opp *opp;
+		unsigned int freq = df->profile->freq_table[i];
+		bool want_enable = i <= max_enabled_state ? true : false;
+
+		rcu_read_lock();
+		opp = dev_pm_opp_find_freq_exact(dev, freq, !want_enable);
+		rcu_read_unlock();
+
+		if (PTR_ERR(opp) == -ERANGE)
+			continue;
+		else if (IS_ERR(opp))
+			return PTR_ERR(opp);
+
+		if (want_enable)
+			dev_pm_opp_enable(dev, freq);
+		else
+			dev_pm_opp_disable(dev, freq);
+	}
+
+	return 0;
+}
+
+static int devfreq_cooling_get_max_state(struct thermal_cooling_device *cdev,
+					 unsigned long *state)
+{
+	struct devfreq_cooling_device *dfc = cdev->devdata;
+	struct devfreq *df = dfc->devfreq;
+
+	*state = df->profile->max_state - 1;
+
+	return 0;
+}
+
+static int devfreq_cooling_get_cur_state(struct thermal_cooling_device *cdev,
+					 unsigned long *state)
+{
+	struct devfreq_cooling_device *dfc = cdev->devdata;
+
+	*state = dfc->cooling_state;
+
+	return 0;
+}
+
+static int devfreq_cooling_set_cur_state(struct thermal_cooling_device *cdev,
+					 unsigned long state)
+{
+	struct devfreq_cooling_device *dfc = cdev->devdata;
+	struct devfreq *df = dfc->devfreq;
+	struct device *dev = df->dev.parent;
+	unsigned long index;
+	unsigned long max_state = df->profile->max_state;
+	int ret;
+
+	if (state == dfc->cooling_state)
+		return 0;
+
+	dev_dbg(dev, "Setting cooling state %lu\n", state);
+
+	if (state >= max_state)
+		return -EINVAL;
+
+	index = (max_state - 1) - state;
+
+	ret = enable_disable_opps(df, index);
+	if (ret)
+		return ret;
+
+	dfc->cooling_state = state;
+
+	return 0;
+}
+
+static unsigned long
+freq_get_state(struct devfreq *df, unsigned long freq)
+{
+	unsigned long state = THERMAL_CSTATE_INVALID;
+	int i;
+
+	for (i = 0; i < df->profile->max_state; i++) {
+		if (df->profile->freq_table[i] == freq)
+			state = (df->profile->max_state - 1) - i;
+	}
+
+	return state;
+}
+
+static unsigned long
+state_get_freq(struct devfreq *df, unsigned long state)
+{
+	unsigned long index = (df->profile->max_state - 1) - state;
+
+	if (index >= df->profile->max_state)
+		return 0;
+
+	return df->profile->freq_table[index];
+}
+
+static unsigned long
+get_static_power(struct devfreq_cooling_device *dfc, unsigned long freq)
+{
+	struct devfreq *df = dfc->devfreq;
+	struct device *dev = df->dev.parent;
+	unsigned long voltage;
+	struct dev_pm_opp *opp;
+
+	rcu_read_lock();
+
+	opp = dev_pm_opp_find_freq_exact(dev, freq, true);
+	if (IS_ERR(opp) && (PTR_ERR(opp) == -ERANGE))
+		opp = dev_pm_opp_find_freq_exact(dev, freq, false);
+
+	voltage = dev_pm_opp_get_voltage_always(opp) / 1000; /* mV */
+
+	rcu_read_unlock();
+
+	if (voltage == 0) {
+		dev_warn_ratelimited(dev,
+				     "Failed to get voltage for frequency %lu: %ld\n",
+				     freq, IS_ERR(opp) ? PTR_ERR(opp) : 0);
+		return 0;
+	}
+
+	return dfc->power_ops->get_static_power(voltage);
+}
+
+static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cdev,
+					       struct thermal_zone_device *tz,
+					       u32 *power)
+{
+	struct devfreq_cooling_device *dfc = cdev->devdata;
+	struct devfreq *df = dfc->devfreq;
+	struct devfreq_dev_status *status = &df->last_status;
+	unsigned long state;
+	unsigned long freq = status->current_frequency;
+	u32 dyn_power, static_power;
+
+	/* Get dynamic power for state */
+	state = freq_get_state(df, freq);
+	if (state == THERMAL_CSTATE_INVALID)
+		return -EAGAIN;
+
+	dyn_power = dfc->power_table[state];
+
+	/* Scale dynamic power for utilization */
+	dyn_power = (dyn_power * status->busy_time) / status->total_time;
+
+	/* Get static power */
+	static_power = get_static_power(dfc, freq);
+
+	trace_thermal_power_devfreq_get_power(cdev, status, freq, dyn_power,
+					      static_power);
+
+	*power = dyn_power + static_power;
+
+	return 0;
+}
+
+static int devfreq_cooling_state2power(struct thermal_cooling_device *cdev,
+				       struct thermal_zone_device *tz,
+				       unsigned long state,
+				       u32 *power)
+{
+	struct devfreq_cooling_device *dfc = cdev->devdata;
+	struct devfreq *df = dfc->devfreq;
+	unsigned long freq;
+	u32 static_power;
+
+	freq = state_get_freq(df, state);
+	static_power = get_static_power(dfc, freq);
+
+	*power = dfc->power_table[state] + static_power;
+	return 0;
+}
+
+static int devfreq_cooling_power2state(struct thermal_cooling_device *cdev,
+				       struct thermal_zone_device *tz,
+				       u32 power, unsigned long *state)
+{
+	struct devfreq_cooling_device *dfc = cdev->devdata;
+	struct devfreq *df = dfc->devfreq;
+	struct devfreq_dev_status *status = &df->last_status;
+	unsigned long freq = status->current_frequency;
+	unsigned long busy_time;
+	s32 dyn_power;
+	u32 static_power;
+	int i;
+
+	static_power = get_static_power(dfc, freq);
+
+	dyn_power = power - static_power;
+	dyn_power = dyn_power > 0 ? dyn_power : 0;
+
+	/* Scale dynamic power for utilization */
+	busy_time = status->busy_time ?: 1;
+	dyn_power = (dyn_power * status->total_time) / busy_time;
+
+	/*
+	 * Find the first cooling state that is within the power
+	 * budget for dynamic power.
+	 */
+	for (i = 0; i < df->profile->max_state - 1; i++)
+		if (dyn_power >= dfc->power_table[i])
+			break;
+
+	*state = i;
+	trace_thermal_power_devfreq_limit(cdev, freq, *state, power);
+	return 0;
+}
+
+static struct thermal_cooling_device_ops devfreq_cooling_ops = {
+	.get_max_state = devfreq_cooling_get_max_state,
+	.get_cur_state = devfreq_cooling_get_cur_state,
+	.set_cur_state = devfreq_cooling_set_cur_state,
+};
+
+/**
+ * devfreq_cooling_gen_power_table(): - Generate power table.
+ * @dfc: Pointer to devfreq cooling device.
+ *
+ * Generate a table with the device's maximum power usage at each cooling
+ * state (OPP). The static and dynamic powerm using the appropriate voltage and
+ * frequency for the state, is acquired from the struct devfreq_cooling_ops, and
+ * summed to make the maximum power draw.
+ *
+ * The table is malloced, and a pointer put in dfc->power_table. This must be
+ * freed when unregistering the devfreq cooling device.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+static int devfreq_cooling_gen_power_table(struct devfreq_cooling_device *dfc)
+{
+	struct devfreq *df = dfc->devfreq;
+	struct device *dev = df->dev.parent;
+	int num_opps;
+	struct devfreq_cooling_ops *callbacks = dfc->power_ops;
+	unsigned long freq;
+	u32 *table;
+	int i;
+
+	if (!IS_ENABLED(CONFIG_PM_OPP)) {
+		dev_warn(dev, "Can't use power extensions of the devfreq cooling device without CONFIG_PM_OPP\n");
+		return -EINVAL;
+	}
+
+	rcu_read_lock();
+	num_opps = dev_pm_opp_get_opp_count(dev);
+
+	if (num_opps != dfc->devfreq->profile->max_state) {
+		rcu_read_unlock();
+		return -ERANGE;
+	}
+
+	table = devm_kcalloc(dev, num_opps, sizeof(*table), GFP_KERNEL);
+	if (!table) {
+		rcu_read_unlock();
+		return -ENOMEM;
+	}
+
+	for (i = 0, freq = ULONG_MAX; i < num_opps; i++, freq--) {
+		unsigned long power_dyn, voltage;
+		struct dev_pm_opp *opp;
+
+		opp = dev_pm_opp_find_freq_floor(dev, &freq);
+		if (IS_ERR(opp))
+			break;
+
+		voltage = dev_pm_opp_get_voltage(opp) / 1000; /* mV */
+
+		power_dyn = callbacks->get_dynamic_power(freq, voltage);
+
+		dev_info(dev, "Dynamic power table: %lu MHz @ %lu mV: %lu = %lu mW\n",
+			 freq / 1000000, voltage, power_dyn, power_dyn);
+
+		table[i] = power_dyn;
+	}
+	rcu_read_unlock();
+
+	if (i != num_opps) {
+		devm_kfree(dev, table);
+		return -EFAULT;
+	}
+
+	dfc->power_table = table;
+
+	return 0;
+}
+
+/**
+ * of_devfreq_cooling_register_power(): - Register devfreq cooling device,
+ *                                      with OF and power information.
+ * @np: Pointer to OF device_node.
+ * @df: Pointer to devfreq device.
+ * @ops: Pointer to power ops.
+ */
+struct devfreq_cooling_device *
+of_devfreq_cooling_register_power(struct device_node *np, struct devfreq *df,
+				  struct devfreq_cooling_ops *ops)
+{
+	struct thermal_cooling_device *cdev;
+	struct devfreq_cooling_device *dfc;
+	struct device *dev = df->dev.parent;
+	char dev_name[THERMAL_NAME_LENGTH];
+	int err;
+
+	/* freq_table is required to look map state index to frequency. */
+	if (!df->profile->max_state || !df->profile->freq_table)
+		return ERR_PTR(-EINVAL);
+
+	dfc = devm_kzalloc(dev, sizeof(*dfc), GFP_KERNEL);
+	if (!dfc)
+		return ERR_PTR(-ENOMEM);
+
+	dfc->devfreq = df;
+
+	if (ops) {
+		if (!ops->get_static_power || !ops->get_dynamic_power) {
+			err = -EINVAL;
+			goto free_dfc;
+		}
+		dfc->power_ops = ops;
+
+		err = devfreq_cooling_gen_power_table(dfc);
+		if (err)
+			goto free_dfc;
+
+		devfreq_cooling_ops.get_requested_power =
+			devfreq_cooling_get_requested_power;
+		devfreq_cooling_ops.state2power = devfreq_cooling_state2power;
+		devfreq_cooling_ops.power2state = devfreq_cooling_power2state;
+	}
+
+	err = get_idr(&devfreq_idr, &dfc->id);
+	if (err)
+		goto free_power_table;
+
+	snprintf(dev_name, sizeof(dev_name), "devfreq-%d", dfc->id);
+
+	cdev = thermal_of_cooling_device_register(np, dev_name, dfc,
+						  &devfreq_cooling_ops);
+	if (IS_ERR(cdev)) {
+		err = PTR_ERR(cdev);
+		dev_err(df->dev.parent,
+			"Failed to register devfreq cooling device (%d)\n",
+			err);
+		goto release_idr;
+	}
+
+	dfc->cdev = cdev;
+
+	return dfc;
+
+release_idr:
+	release_idr(&devfreq_idr, dfc->id);
+free_power_table:
+	if (dfc->power_table)
+		devm_kfree(dev, dfc->power_table);
+free_dfc:
+	devm_kfree(dev, dfc);
+
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL(of_devfreq_cooling_register_power);
+
+/**
+ * of_devfreq_cooling_register(): - Register devfreq cooling device,
+ *                                with OF information.
+ * @np: Pointer to OF device_node.
+ * @df: Pointer to devfreq device.
+ */
+struct devfreq_cooling_device *
+of_devfreq_cooling_register(struct device_node *np, struct devfreq *df)
+{
+	return of_devfreq_cooling_register_power(np, df, NULL);
+}
+EXPORT_SYMBOL(of_devfreq_cooling_register);
+
+/**
+ * devfreq_cooling_register(): - Register devfreq cooling device.
+ * @df: Pointer to devfreq device.
+ */
+struct devfreq_cooling_device *devfreq_cooling_register(struct devfreq *df)
+{
+	return of_devfreq_cooling_register(NULL, df);
+}
+EXPORT_SYMBOL(devfreq_cooling_register);
+
+/**
+ * devfreq_cooling_unregister(): - Unregister devfreq cooling device.
+ * @dfc: Pointer to devfreq cooling device to unregister.
+ */
+void devfreq_cooling_unregister(struct devfreq_cooling_device *dfc)
+{
+	struct device *dev;
+
+	if (!dfc)
+		return;
+
+	dev = dfc->devfreq->dev.parent;
+
+	thermal_cooling_device_unregister(dfc->cdev);
+
+	release_idr(&devfreq_idr, dfc->id);
+	if (dfc->power_table)
+		devm_kfree(dev, dfc->power_table);
+	devm_kfree(dev, dfc);
+}
+EXPORT_SYMBOL(devfreq_cooling_unregister);
diff --git a/drivers/thermal/fair_share.c b/drivers/thermal/fair_share.c
index 6e0a3fbfae8..8c50b8d6afb 100644
--- a/drivers/thermal/fair_share.c
+++ b/drivers/thermal/fair_share.c
@@ -59,13 +59,13 @@ static int get_trip_level(struct thermal_zone_device *tz)
 }
 
 static long get_target_state(struct thermal_zone_device *tz,
-		struct thermal_cooling_device *cdev, int weight, int level)
+		struct thermal_cooling_device *cdev, int percentage, int level)
 {
 	unsigned long max_state;
 
 	cdev->ops->get_max_state(cdev, &max_state);
 
-	return (long)(weight * level * max_state) / (100 * tz->trips);
+	return (long)(percentage * level * max_state) / (100 * tz->trips);
 }
 
 /**
@@ -77,7 +77,7 @@ static long get_target_state(struct thermal_zone_device *tz,
  *
  * Parameters used for Throttling:
  * P1. max_state: Maximum throttle state exposed by the cooling device.
- * P2. weight[i]/100:
+ * P2. percentage[i]/100:
  *	How 'effective' the 'i'th device is, in cooling the given zone.
  * P3. cur_trip_level/max_no_of_trips:
  *	This describes the extent to which the devices should be throttled.
@@ -88,28 +88,33 @@ static long get_target_state(struct thermal_zone_device *tz,
  */
 static int fair_share_throttle(struct thermal_zone_device *tz, int trip)
 {
-	const struct thermal_zone_params *tzp;
-	struct thermal_cooling_device *cdev;
 	struct thermal_instance *instance;
-	int i;
+	int total_weight = 0;
+	int total_instance = 0;
 	int cur_trip_level = get_trip_level(tz);
 
-	if (!tz->tzp || !tz->tzp->tbp)
-		return -EINVAL;
+	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+		if (instance->trip != trip)
+			continue;
+
+		total_weight += instance->weight;
+		total_instance++;
+	}
 
-	tzp = tz->tzp;
+	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+		int percentage;
+		struct thermal_cooling_device *cdev = instance->cdev;
 
-	for (i = 0; i < tzp->num_tbps; i++) {
-		if (!tzp->tbp[i].cdev)
+		if (instance->trip != trip)
 			continue;
 
-		cdev = tzp->tbp[i].cdev;
-		instance = get_thermal_instance(tz, cdev, trip);
-		if (!instance)
-			continue;
+		if (!total_weight)
+			percentage = 100 / total_instance;
+		else
+			percentage = (instance->weight * 100) / total_weight;
 
-		instance->target = get_target_state(tz, cdev,
-					tzp->tbp[i].weight, cur_trip_level);
+		instance->target = get_target_state(tz, cdev, percentage,
+						    cur_trip_level);
 
 		instance->cdev->updated = false;
 		thermal_cdev_update(cdev);
diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c
index 5a1f1070b70..31ada06c7dc 100644
--- a/drivers/thermal/imx_thermal.c
+++ b/drivers/thermal/imx_thermal.c
@@ -9,7 +9,6 @@
 
 #include <linux/clk.h>
 #include <linux/cpu_cooling.h>
-#include <linux/cpufreq.h>
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/init.h>
@@ -307,7 +306,8 @@ static int imx_bind(struct thermal_zone_device *tz,
 
 	ret = thermal_zone_bind_cooling_device(tz, IMX_TRIP_PASSIVE, cdev,
 					       THERMAL_NO_LIMIT,
-					       THERMAL_NO_LIMIT);
+					       THERMAL_NO_LIMIT,
+					       THERMAL_WEIGHT_DEFAULT);
 	if (ret) {
 		dev_err(&tz->device,
 			"binding zone %s with cdev %s failed:%d\n",
@@ -459,10 +459,6 @@ static int imx_thermal_probe(struct platform_device *pdev)
 	int measure_freq;
 	int ret;
 
-	if (!cpufreq_get_current_driver()) {
-		dev_dbg(&pdev->dev, "no cpufreq driver!");
-		return -EPROBE_DEFER;
-	}
 	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
diff --git a/drivers/thermal/int340x_thermal/int3403_thermal.c b/drivers/thermal/int340x_thermal/int3403_thermal.c
index 6e9fb62eb81..76910d35eec 100644
--- a/drivers/thermal/int340x_thermal/int3403_thermal.c
+++ b/drivers/thermal/int340x_thermal/int3403_thermal.c
@@ -471,7 +471,6 @@ static struct platform_driver int3403_driver = {
 	.remove = int3403_remove,
 	.driver = {
 		.name = "int3403 thermal",
-		.owner  = THIS_MODULE,
 		.acpi_match_table = int3403_device_ids,
 	},
 };
diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c
index 95cb7fc20e1..6cb78497076 100644
--- a/drivers/thermal/intel_powerclamp.c
+++ b/drivers/thermal/intel_powerclamp.c
@@ -435,7 +435,6 @@ static int clamp_thread(void *arg)
 		 * allowed. thus jiffies are updated properly.
 		 */
 		preempt_disable();
-		tick_nohz_idle_enter();
 		/* mwait until target jiffies is reached */
 		while (time_before(jiffies, target_jiffies)) {
 			unsigned long ecx = 1;
@@ -451,7 +450,6 @@ static int clamp_thread(void *arg)
 			start_critical_timings();
 			atomic_inc(&idle_wakeup_counter);
 		}
-		tick_nohz_idle_exit();
 		preempt_enable();
 	}
 	del_timer_sync(&wakeup_timer);
diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c
index 62143ba3100..b295b2b6c19 100644
--- a/drivers/thermal/of-thermal.c
+++ b/drivers/thermal/of-thermal.c
@@ -30,27 +30,13 @@
 #include <linux/err.h>
 #include <linux/export.h>
 #include <linux/string.h>
+#include <linux/thermal.h>
 
 #include "thermal_core.h"
 
 /***   Private data structures to represent thermal device tree data ***/
 
 /**
- * struct __thermal_trip - representation of a point in temperature domain
- * @np: pointer to struct device_node that this trip point was created from
- * @temperature: temperature value in miliCelsius
- * @hysteresis: relative hysteresis in miliCelsius
- * @type: trip point type
- */
-
-struct __thermal_trip {
-	struct device_node *np;
-	unsigned long int temperature;
-	unsigned long int hysteresis;
-	enum thermal_trip_type type;
-};
-
-/**
  * struct __thermal_bind_param - a match between trip and cooling device
  * @cooling_device: a pointer to identify the referred cooling device
  * @trip_id: the trip point index
@@ -72,23 +58,26 @@ struct __thermal_bind_params {
  * @mode: current thermal zone device mode (enabled/disabled)
  * @passive_delay: polling interval while passive cooling is activated
  * @polling_delay: zone polling interval
+ * @slope: slope of the temperature adjustment curve
+ * @offset: offset of the temperature adjustment curve
  * @ntrips: number of trip points
  * @trips: an array of trip points (0..ntrips - 1)
  * @num_tbps: number of thermal bind params
  * @tbps: an array of thermal bind params (0..num_tbps - 1)
  * @sensor_data: sensor private data used while reading temperature and trend
- * @get_temp: sensor callback to read temperature
- * @get_trend: sensor callback to read temperature trend
+ * @ops: set of callbacks to handle the thermal zone based on DT
  */
 
 struct __thermal_zone {
 	enum thermal_device_mode mode;
 	int passive_delay;
 	int polling_delay;
+	int slope;
+	int offset;
 
 	/* trip data */
 	int ntrips;
-	struct __thermal_trip *trips;
+	struct thermal_trip *trips;
 
 	/* cooling binding data */
 	int num_tbps;
@@ -96,8 +85,7 @@ struct __thermal_zone {
 
 	/* sensor interface */
 	void *sensor_data;
-	int (*get_temp)(void *, long *);
-	int (*get_trend)(void *, long *);
+	const struct thermal_zone_of_device_ops *ops;
 };
 
 /***   DT thermal zone device callbacks   ***/
@@ -107,10 +95,96 @@ static int of_thermal_get_temp(struct thermal_zone_device *tz,
 {
 	struct __thermal_zone *data = tz->devdata;
 
-	if (!data->get_temp)
+	if (!data->ops->get_temp)
 		return -EINVAL;
 
-	return data->get_temp(data->sensor_data, temp);
+	return data->ops->get_temp(data->sensor_data, temp);
+}
+
+/**
+ * of_thermal_get_ntrips - function to export number of available trip
+ *			   points.
+ * @tz: pointer to a thermal zone
+ *
+ * This function is a globally visible wrapper to get number of trip points
+ * stored in the local struct __thermal_zone
+ *
+ * Return: number of available trip points, -ENODEV when data not available
+ */
+int of_thermal_get_ntrips(struct thermal_zone_device *tz)
+{
+	struct __thermal_zone *data = tz->devdata;
+
+	if (!data || IS_ERR(data))
+		return -ENODEV;
+
+	return data->ntrips;
+}
+EXPORT_SYMBOL_GPL(of_thermal_get_ntrips);
+
+/**
+ * of_thermal_is_trip_valid - function to check if trip point is valid
+ *
+ * @tz:	pointer to a thermal zone
+ * @trip:	trip point to evaluate
+ *
+ * This function is responsible for checking if passed trip point is valid
+ *
+ * Return: true if trip point is valid, false otherwise
+ */
+bool of_thermal_is_trip_valid(struct thermal_zone_device *tz, int trip)
+{
+	struct __thermal_zone *data = tz->devdata;
+
+	if (!data || trip >= data->ntrips || trip < 0)
+		return false;
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(of_thermal_is_trip_valid);
+
+/**
+ * of_thermal_get_trip_points - function to get access to a globally exported
+ *				trip points
+ *
+ * @tz:	pointer to a thermal zone
+ *
+ * This function provides a pointer to trip points table
+ *
+ * Return: pointer to trip points table, NULL otherwise
+ */
+const struct thermal_trip *
+of_thermal_get_trip_points(struct thermal_zone_device *tz)
+{
+	struct __thermal_zone *data = tz->devdata;
+
+	if (!data)
+		return NULL;
+
+	return data->trips;
+}
+EXPORT_SYMBOL_GPL(of_thermal_get_trip_points);
+
+/**
+ * of_thermal_set_emul_temp - function to set emulated temperature
+ *
+ * @tz:	pointer to a thermal zone
+ * @temp:	temperature to set
+ *
+ * This function gives the ability to set emulated value of temperature,
+ * which is handy for debugging
+ *
+ * Return: zero on success, error code otherwise
+ */
+static int of_thermal_set_emul_temp(struct thermal_zone_device *tz,
+				    unsigned long temp)
+{
+	struct __thermal_zone *data = tz->devdata;
+
+	if (!data->ops || !data->ops->set_emul_temp)
+		return -EINVAL;
+
+	return data->ops->set_emul_temp(data->sensor_data, temp);
 }
 
 static int of_thermal_get_trend(struct thermal_zone_device *tz, int trip,
@@ -120,10 +194,10 @@ static int of_thermal_get_trend(struct thermal_zone_device *tz, int trip,
 	long dev_trend;
 	int r;
 
-	if (!data->get_trend)
+	if (!data->ops->get_trend)
 		return -EINVAL;
 
-	r = data->get_trend(data->sensor_data, &dev_trend);
+	r = data->ops->get_trend(data->sensor_data, &dev_trend);
 	if (r)
 		return r;
 
@@ -157,7 +231,8 @@ static int of_thermal_bind(struct thermal_zone_device *thermal,
 			ret = thermal_zone_bind_cooling_device(thermal,
 						tbp->trip_id, cdev,
 						tbp->max,
-						tbp->min);
+						tbp->min,
+						tbp->usage);
 			if (ret)
 				return ret;
 		}
@@ -324,8 +399,7 @@ static struct thermal_zone_device_ops of_thermal_ops = {
 static struct thermal_zone_device *
 thermal_zone_of_add_sensor(struct device_node *zone,
 			   struct device_node *sensor, void *data,
-			   int (*get_temp)(void *, long *),
-			   int (*get_trend)(void *, long *))
+			   const struct thermal_zone_of_device_ops *ops)
 {
 	struct thermal_zone_device *tzd;
 	struct __thermal_zone *tz;
@@ -336,13 +410,16 @@ thermal_zone_of_add_sensor(struct device_node *zone,
 
 	tz = tzd->devdata;
 
+	if (!ops)
+		return ERR_PTR(-EINVAL);
+
 	mutex_lock(&tzd->lock);
-	tz->get_temp = get_temp;
-	tz->get_trend = get_trend;
+	tz->ops = ops;
 	tz->sensor_data = data;
 
 	tzd->ops->get_temp = of_thermal_get_temp;
 	tzd->ops->get_trend = of_thermal_get_trend;
+	tzd->ops->set_emul_temp = of_thermal_set_emul_temp;
 	mutex_unlock(&tzd->lock);
 
 	return tzd;
@@ -356,8 +433,7 @@ thermal_zone_of_add_sensor(struct device_node *zone,
  *             than one sensors
  * @data: a private pointer (owned by the caller) that will be passed
  *        back, when a temperature reading is needed.
- * @get_temp: a pointer to a function that reads the sensor temperature.
- * @get_trend: a pointer to a function that reads the sensor temperature trend.
+ * @ops: struct thermal_zone_of_device_ops *. Must contain at least .get_temp.
  *
  * This function will search the list of thermal zones described in device
  * tree and look for the zone that refer to the sensor device pointed by
@@ -382,9 +458,8 @@ thermal_zone_of_add_sensor(struct device_node *zone,
  * check the return value with help of IS_ERR() helper.
  */
 struct thermal_zone_device *
-thermal_zone_of_sensor_register(struct device *dev, int sensor_id,
-				void *data, int (*get_temp)(void *, long *),
-				int (*get_trend)(void *, long *))
+thermal_zone_of_sensor_register(struct device *dev, int sensor_id, void *data,
+				const struct thermal_zone_of_device_ops *ops)
 {
 	struct device_node *np, *child, *sensor_np;
 	struct thermal_zone_device *tzd = ERR_PTR(-ENODEV);
@@ -426,9 +501,10 @@ thermal_zone_of_sensor_register(struct device *dev, int sensor_id,
 
 		if (sensor_specs.np == sensor_np && id == sensor_id) {
 			tzd = thermal_zone_of_add_sensor(child, sensor_np,
-							 data,
-							 get_temp,
-							 get_trend);
+							 data, ops);
+			if (!IS_ERR(tzd))
+				tzd->ops->set_mode(tzd, THERMAL_DEVICE_ENABLED);
+
 			of_node_put(sensor_specs.np);
 			of_node_put(child);
 			goto exit;
@@ -475,9 +551,9 @@ void thermal_zone_of_sensor_unregister(struct device *dev,
 	mutex_lock(&tzd->lock);
 	tzd->ops->get_temp = NULL;
 	tzd->ops->get_trend = NULL;
+	tzd->ops->set_emul_temp = NULL;
 
-	tz->get_temp = NULL;
-	tz->get_trend = NULL;
+	tz->ops = NULL;
 	tz->sensor_data = NULL;
 	mutex_unlock(&tzd->lock);
 }
@@ -501,7 +577,7 @@ EXPORT_SYMBOL_GPL(thermal_zone_of_sensor_unregister);
  */
 static int thermal_of_populate_bind_params(struct device_node *np,
 					   struct __thermal_bind_params *__tbp,
-					   struct __thermal_trip *trips,
+					   struct thermal_trip *trips,
 					   int ntrips)
 {
 	struct of_phandle_args cooling_spec;
@@ -510,7 +586,7 @@ static int thermal_of_populate_bind_params(struct device_node *np,
 	u32 prop;
 
 	/* Default weight. Usage is optional */
-	__tbp->usage = 0;
+	__tbp->usage = THERMAL_WEIGHT_DEFAULT;
 	ret = of_property_read_u32(np, "contribution", &prop);
 	if (ret == 0)
 		__tbp->usage = prop;
@@ -604,7 +680,7 @@ static int thermal_of_get_trip_type(struct device_node *np,
  * Return: 0 on success, proper error code otherwise
  */
 static int thermal_of_populate_trip(struct device_node *np,
-				    struct __thermal_trip *trip)
+				    struct thermal_trip *trip)
 {
 	int prop;
 	int ret;
@@ -644,7 +720,7 @@ static int thermal_of_populate_trip(struct device_node *np,
  * @np parameter and fills the read data into a __thermal_zone data structure
  * and return this pointer.
  *
- * TODO: Missing properties to parse: thermal-sensor-names and coefficients
+ * TODO: Missing properties to parse: thermal-sensor-names
  *
  * Return: On success returns a valid struct __thermal_zone,
  * otherwise, it returns a corresponding ERR_PTR(). Caller must
@@ -656,7 +732,7 @@ thermal_of_build_thermal_zone(struct device_node *np)
 	struct device_node *child = NULL, *gchild;
 	struct __thermal_zone *tz;
 	int ret, i;
-	u32 prop;
+	u32 prop, coef[2];
 
 	if (!np) {
 		pr_err("no thermal zone np\n");
@@ -681,6 +757,20 @@ thermal_of_build_thermal_zone(struct device_node *np)
 	}
 	tz->polling_delay = prop;
 
+	/*
+	 * REVIST: for now, the thermal framework supports only
+	 * one sensor per thermal zone. Thus, we are considering
+	 * only the first two values as slope and offset.
+	 */
+	ret = of_property_read_u32_array(np, "coefficients", coef, 2);
+	if (ret == 0) {
+		tz->slope = coef[0];
+		tz->offset = coef[1];
+	} else {
+		tz->slope = 1;
+		tz->offset = 0;
+	}
+
 	/* trips */
 	child = of_get_child_by_name(np, "trips");
 
@@ -794,6 +884,8 @@ int __init of_parse_thermal_zones(void)
 	for_each_child_of_node(np, child) {
 		struct thermal_zone_device *zone;
 		struct thermal_zone_params *tzp;
+		int i, mask = 0;
+		u32 prop;
 
 		/* Check whether child is enabled or not */
 		if (!of_device_is_available(child))
@@ -820,8 +912,18 @@ int __init of_parse_thermal_zones(void)
 		/* No hwmon because there might be hwmon drivers registering */
 		tzp->no_hwmon = true;
 
+		if (!of_property_read_u32(child, "sustainable-power", &prop))
+			tzp->sustainable_power = prop;
+
+		for (i = 0; i < tz->ntrips; i++)
+			mask |= 1 << i;
+
+		/* these two are left for temperature drivers to use */
+		tzp->slope = tz->slope;
+		tzp->offset = tz->offset;
+
 		zone = thermal_zone_device_register(child->name, tz->ntrips,
-						    0, tz,
+						    mask, tz,
 						    ops, tzp,
 						    tz->passive_delay,
 						    tz->polling_delay);
diff --git a/drivers/thermal/power_allocator.c b/drivers/thermal/power_allocator.c
new file mode 100644
index 00000000000..63a448f9d93
--- /dev/null
+++ b/drivers/thermal/power_allocator.c
@@ -0,0 +1,545 @@
+/*
+ * A power allocator to manage temperature
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) "Power allocator: " fmt
+
+#include <linux/rculist.h>
+#include <linux/slab.h>
+#include <linux/thermal.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/thermal_power_allocator.h>
+
+#include "thermal_core.h"
+
+#define FRAC_BITS 10
+#define int_to_frac(x) ((x) << FRAC_BITS)
+#define frac_to_int(x) ((x) >> FRAC_BITS)
+
+/**
+ * mul_frac() - multiply two fixed-point numbers
+ * @x:	first multiplicand
+ * @y:	second multiplicand
+ *
+ * Return: the result of multiplying two fixed-point numbers.  The
+ * result is also a fixed-point number.
+ */
+static inline s64 mul_frac(s64 x, s64 y)
+{
+	return (x * y) >> FRAC_BITS;
+}
+
+/**
+ * div_frac() - divide two fixed-point numbers
+ * @x:	the dividend
+ * @y:	the divisor
+ *
+ * Return: the result of dividing two fixed-point numbers.  The
+ * result is also a fixed-point number.
+ */
+static inline s64 div_frac(s64 x, s64 y)
+{
+	return div_s64(x << FRAC_BITS, y);
+}
+
+/**
+ * struct power_allocator_params - parameters for the power allocator governor
+ * @err_integral:	accumulated error in the PID controller.
+ * @prev_err:	error in the previous iteration of the PID controller.
+ *		Used to calculate the derivative term.
+ * @trip_switch_on:	first passive trip point of the thermal zone.  The
+ *			governor switches on when this trip point is crossed.
+ * @trip_max_desired_temperature:	last passive trip point of the thermal
+ *					zone.  The temperature we are
+ *					controlling for.
+ */
+struct power_allocator_params {
+	s64 err_integral;
+	s32 prev_err;
+	int trip_switch_on;
+	int trip_max_desired_temperature;
+};
+
+/**
+ * pid_controller() - PID controller
+ * @tz:	thermal zone we are operating in
+ * @current_temp:	the current temperature in millicelsius
+ * @control_temp:	the target temperature in millicelsius
+ * @max_allocatable_power:	maximum allocatable power for this thermal zone
+ *
+ * This PID controller increases the available power budget so that the
+ * temperature of the thermal zone gets as close as possible to
+ * @control_temp and limits the power if it exceeds it.  k_po is the
+ * proportional term when we are overshooting, k_pu is the
+ * proportional term when we are undershooting.  integral_cutoff is a
+ * threshold below which we stop accumulating the error.  The
+ * accumulated error is only valid if the requested power will make
+ * the system warmer.  If the system is mostly idle, there's no point
+ * in accumulating positive error.
+ *
+ * Return: The power budget for the next period.
+ */
+static u32 pid_controller(struct thermal_zone_device *tz,
+			  unsigned long current_temp,
+			  unsigned long control_temp,
+			  u32 max_allocatable_power)
+{
+	s64 p, i, d, power_range;
+	s32 err, max_power_frac;
+	struct power_allocator_params *params = tz->governor_data;
+
+	max_power_frac = int_to_frac(max_allocatable_power);
+
+	err = ((s32)control_temp - (s32)current_temp);
+	err = int_to_frac(err);
+
+	/* Calculate the proportional term */
+	p = mul_frac(err < 0 ? tz->tzp->k_po : tz->tzp->k_pu, err);
+
+	/*
+	 * Calculate the integral term
+	 *
+	 * if the error is less than cut off allow integration (but
+	 * the integral is limited to max power)
+	 */
+	i = mul_frac(tz->tzp->k_i, params->err_integral);
+
+	if (err < int_to_frac(tz->tzp->integral_cutoff)) {
+		s64 i_next = i + mul_frac(tz->tzp->k_i, err);
+
+		if (abs64(i_next) < max_power_frac) {
+			i = i_next;
+			params->err_integral += err;
+		}
+	}
+
+	/*
+	 * Calculate the derivative term
+	 *
+	 * We do err - prev_err, so with a positive k_d, a decreasing
+	 * error (i.e. driving closer to the line) results in less
+	 * power being applied, slowing down the controller)
+	 */
+	d = mul_frac(tz->tzp->k_d, err - params->prev_err);
+	d = div_frac(d, tz->passive_delay);
+	params->prev_err = err;
+
+	power_range = p + i + d;
+
+	/* feed-forward the known sustainable dissipatable power */
+	power_range = tz->tzp->sustainable_power + frac_to_int(power_range);
+
+	power_range = clamp(power_range, (s64)0, (s64)max_allocatable_power);
+
+	trace_thermal_power_allocator_pid(tz, frac_to_int(err),
+					  frac_to_int(params->err_integral),
+					  frac_to_int(p), frac_to_int(i),
+					  frac_to_int(d), power_range);
+
+	return power_range;
+}
+
+/**
+ * divvy_up_power() - divvy the allocated power between the actors
+ * @req_power:	each actor's requested power
+ * @max_power:	each actor's maximum available power
+ * @num_actors:	size of the @req_power, @max_power and @granted_power's array
+ * @total_req_power: sum of @req_power
+ * @power_range:	total allocated power
+ * @granted_power:	output array: each actor's granted power
+ * @extra_actor_power:	an appropriately sized array to be used in the
+ *			function as temporary storage of the extra power given
+ *			to the actors
+ *
+ * This function divides the total allocated power (@power_range)
+ * fairly between the actors.  It first tries to give each actor a
+ * share of the @power_range according to how much power it requested
+ * compared to the rest of the actors.  For example, if only one actor
+ * requests power, then it receives all the @power_range.  If
+ * three actors each requests 1mW, each receives a third of the
+ * @power_range.
+ *
+ * If any actor received more than their maximum power, then that
+ * surplus is re-divvied among the actors based on how far they are
+ * from their respective maximums.
+ *
+ * Granted power for each actor is written to @granted_power, which
+ * should've been allocated by the calling function.
+ */
+static void divvy_up_power(u32 *req_power, u32 *max_power, int num_actors,
+			   u32 total_req_power, u32 power_range,
+			   u32 *granted_power, u32 *extra_actor_power)
+{
+	u32 extra_power, capped_extra_power;
+	int i;
+
+	/*
+	 * Prevent division by 0 if none of the actors request power.
+	 */
+	if (!total_req_power)
+		total_req_power = 1;
+
+	capped_extra_power = 0;
+	extra_power = 0;
+	for (i = 0; i < num_actors; i++) {
+		u64 req_range = req_power[i] * power_range;
+
+		granted_power[i] = DIV_ROUND_CLOSEST_ULL(req_range,
+							 total_req_power);
+
+		if (granted_power[i] > max_power[i]) {
+			extra_power += granted_power[i] - max_power[i];
+			granted_power[i] = max_power[i];
+		}
+
+		extra_actor_power[i] = max_power[i] - granted_power[i];
+		capped_extra_power += extra_actor_power[i];
+	}
+
+	if (!extra_power)
+		return;
+
+	/*
+	 * Re-divvy the reclaimed extra among actors based on
+	 * how far they are from the max
+	 */
+	extra_power = min(extra_power, capped_extra_power);
+	if (capped_extra_power > 0)
+		for (i = 0; i < num_actors; i++)
+			granted_power[i] += (extra_actor_power[i] *
+					extra_power) / capped_extra_power;
+}
+
+static int allocate_power(struct thermal_zone_device *tz,
+			  unsigned long current_temp,
+			  unsigned long control_temp)
+{
+	struct thermal_instance *instance;
+	struct power_allocator_params *params = tz->governor_data;
+	u32 *req_power, *max_power, *granted_power, *extra_actor_power;
+	u32 *weighted_req_power;
+	u32 total_req_power, max_allocatable_power, total_weighted_req_power;
+	u32 total_granted_power, power_range;
+	int i, num_actors, total_weight, ret = 0;
+	int trip_max_desired_temperature = params->trip_max_desired_temperature;
+
+	mutex_lock(&tz->lock);
+
+	num_actors = 0;
+	total_weight = 0;
+	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+		if ((instance->trip == trip_max_desired_temperature) &&
+		    cdev_is_power_actor(instance->cdev)) {
+			num_actors++;
+			total_weight += instance->weight;
+		}
+	}
+
+	/*
+	 * We need to allocate five arrays of the same size:
+	 * req_power, max_power, granted_power, extra_actor_power and
+	 * weighted_req_power.  They are going to be needed until this
+	 * function returns.  Allocate them all in one go to simplify
+	 * the allocation and deallocation logic.
+	 */
+	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*max_power));
+	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*granted_power));
+	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*extra_actor_power));
+	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*weighted_req_power));
+	req_power = devm_kcalloc(&tz->device, num_actors * 5,
+				 sizeof(*req_power), GFP_KERNEL);
+	if (!req_power) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	max_power = &req_power[num_actors];
+	granted_power = &req_power[2 * num_actors];
+	extra_actor_power = &req_power[3 * num_actors];
+	weighted_req_power = &req_power[4 * num_actors];
+
+	i = 0;
+	total_weighted_req_power = 0;
+	total_req_power = 0;
+	max_allocatable_power = 0;
+
+	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+		int weight;
+		struct thermal_cooling_device *cdev = instance->cdev;
+
+		if (instance->trip != trip_max_desired_temperature)
+			continue;
+
+		if (!cdev_is_power_actor(cdev))
+			continue;
+
+		if (cdev->ops->get_requested_power(cdev, tz, &req_power[i]))
+			continue;
+
+		if (!total_weight)
+			weight = 1 << FRAC_BITS;
+		else
+			weight = instance->weight;
+
+		weighted_req_power[i] = frac_to_int(weight * req_power[i]);
+
+		if (power_actor_get_max_power(cdev, tz, &max_power[i]))
+			continue;
+
+		total_req_power += req_power[i];
+		max_allocatable_power += max_power[i];
+		total_weighted_req_power += weighted_req_power[i];
+
+		i++;
+	}
+
+	power_range = pid_controller(tz, current_temp, control_temp,
+				     max_allocatable_power);
+
+	divvy_up_power(weighted_req_power, max_power, num_actors,
+		       total_weighted_req_power, power_range, granted_power,
+		       extra_actor_power);
+
+	total_granted_power = 0;
+	i = 0;
+	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+		if (instance->trip != trip_max_desired_temperature)
+			continue;
+
+		if (!cdev_is_power_actor(instance->cdev))
+			continue;
+
+		power_actor_set_power(instance->cdev, instance,
+				      granted_power[i]);
+		total_granted_power += granted_power[i];
+
+		i++;
+	}
+
+	trace_thermal_power_allocator(tz, req_power, total_req_power,
+				      granted_power, total_granted_power,
+				      num_actors, power_range,
+				      max_allocatable_power, current_temp,
+				      (s32)control_temp - (s32)current_temp);
+
+	devm_kfree(&tz->device, req_power);
+unlock:
+	mutex_unlock(&tz->lock);
+
+	return ret;
+}
+
+static int get_governor_trips(struct thermal_zone_device *tz,
+			      struct power_allocator_params *params)
+{
+	int i, ret, last_passive;
+	bool found_first_passive;
+
+	found_first_passive = false;
+	last_passive = -1;
+	ret = -EINVAL;
+
+	for (i = 0; i < tz->trips; i++) {
+		enum thermal_trip_type type;
+
+		ret = tz->ops->get_trip_type(tz, i, &type);
+		if (ret)
+			return ret;
+
+		if (!found_first_passive) {
+			if (type == THERMAL_TRIP_PASSIVE) {
+				params->trip_switch_on = i;
+				found_first_passive = true;
+			}
+		} else if (type == THERMAL_TRIP_PASSIVE) {
+			last_passive = i;
+		} else {
+			break;
+		}
+	}
+
+	if (last_passive != -1) {
+		params->trip_max_desired_temperature = last_passive;
+		ret = 0;
+	} else {
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static void reset_pid_controller(struct power_allocator_params *params)
+{
+	params->err_integral = 0;
+	params->prev_err = 0;
+}
+
+static void allow_maximum_power(struct thermal_zone_device *tz)
+{
+	struct thermal_instance *instance;
+	struct power_allocator_params *params = tz->governor_data;
+
+	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+		if ((instance->trip != params->trip_max_desired_temperature) ||
+		    (!cdev_is_power_actor(instance->cdev)))
+			continue;
+
+		instance->target = 0;
+		instance->cdev->updated = false;
+		thermal_cdev_update(instance->cdev);
+	}
+}
+
+/**
+ * power_allocator_bind() - bind the power_allocator governor to a thermal zone
+ * @tz:	thermal zone to bind it to
+ *
+ * Check that the thermal zone is valid for this governor, that is, it
+ * has two thermal trips.  If so, initialize the PID controller
+ * parameters and bind it to the thermal zone.
+ *
+ * Return: 0 on success, -EINVAL if the trips were invalid or -ENOMEM
+ * if we ran out of memory.
+ */
+static int power_allocator_bind(struct thermal_zone_device *tz)
+{
+	int ret;
+	struct power_allocator_params *params;
+	unsigned long switch_on_temp, control_temp;
+	u32 temperature_threshold;
+
+	if (!tz->tzp || !tz->tzp->sustainable_power) {
+		dev_err(&tz->device,
+			"power_allocator: missing sustainable_power\n");
+		return -EINVAL;
+	}
+
+	params = devm_kzalloc(&tz->device, sizeof(*params), GFP_KERNEL);
+	if (!params)
+		return -ENOMEM;
+
+	ret = get_governor_trips(tz, params);
+	if (ret) {
+		dev_err(&tz->device,
+			"thermal zone %s has wrong trip setup for power allocator\n",
+			tz->type);
+		goto free;
+	}
+
+	ret = tz->ops->get_trip_temp(tz, params->trip_switch_on,
+				     &switch_on_temp);
+	if (ret)
+		goto free;
+
+	ret = tz->ops->get_trip_temp(tz, params->trip_max_desired_temperature,
+				     &control_temp);
+	if (ret)
+		goto free;
+
+	temperature_threshold = control_temp - switch_on_temp;
+
+	tz->tzp->k_po = tz->tzp->k_po ?:
+		int_to_frac(tz->tzp->sustainable_power) / temperature_threshold;
+	tz->tzp->k_pu = tz->tzp->k_pu ?:
+		int_to_frac(2 * tz->tzp->sustainable_power) /
+		temperature_threshold;
+	tz->tzp->k_i = tz->tzp->k_i ?: int_to_frac(10) / 1000;
+	/*
+	 * The default for k_d and integral_cutoff is 0, so we can
+	 * leave them as they are.
+	 */
+
+	reset_pid_controller(params);
+
+	tz->governor_data = params;
+
+	return 0;
+
+free:
+	devm_kfree(&tz->device, params);
+	return ret;
+}
+
+static void power_allocator_unbind(struct thermal_zone_device *tz)
+{
+	dev_dbg(&tz->device, "Unbinding from thermal zone %d\n", tz->id);
+	devm_kfree(&tz->device, tz->governor_data);
+	tz->governor_data = NULL;
+}
+
+static int power_allocator_throttle(struct thermal_zone_device *tz, int trip)
+{
+	int ret;
+	unsigned long switch_on_temp, control_temp, current_temp;
+	struct power_allocator_params *params = tz->governor_data;
+
+	/*
+	 * We get called for every trip point but we only need to do
+	 * our calculations once
+	 */
+	if (trip != params->trip_max_desired_temperature)
+		return 0;
+
+	ret = thermal_zone_get_temp(tz, &current_temp);
+	if (ret) {
+		dev_warn(&tz->device, "Failed to get temperature: %d\n", ret);
+		return ret;
+	}
+
+	ret = tz->ops->get_trip_temp(tz, params->trip_switch_on,
+				     &switch_on_temp);
+	if (ret) {
+		dev_warn(&tz->device,
+			 "Failed to get switch on temperature: %d\n", ret);
+		return ret;
+	}
+
+	if (current_temp < switch_on_temp) {
+		tz->passive = 0;
+		reset_pid_controller(params);
+		allow_maximum_power(tz);
+		return 0;
+	}
+
+	tz->passive = 1;
+
+	ret = tz->ops->get_trip_temp(tz, params->trip_max_desired_temperature,
+				&control_temp);
+	if (ret) {
+		dev_warn(&tz->device,
+			 "Failed to get the maximum desired temperature: %d\n",
+			 ret);
+		return ret;
+	}
+
+	return allocate_power(tz, current_temp, control_temp);
+}
+
+static struct thermal_governor thermal_gov_power_allocator = {
+	.name		= "power_allocator",
+	.bind_to_tz	= power_allocator_bind,
+	.unbind_from_tz	= power_allocator_unbind,
+	.throttle	= power_allocator_throttle,
+};
+
+int thermal_gov_power_allocator_register(void)
+{
+	return thermal_register_governor(&thermal_gov_power_allocator);
+}
+
+void thermal_gov_power_allocator_unregister(void)
+{
+	thermal_unregister_governor(&thermal_gov_power_allocator);
+}
diff --git a/drivers/thermal/samsung/Kconfig b/drivers/thermal/samsung/Kconfig
index f760389a204..c43306ecc0a 100644
--- a/drivers/thermal/samsung/Kconfig
+++ b/drivers/thermal/samsung/Kconfig
@@ -1,6 +1,6 @@
 config EXYNOS_THERMAL
 	tristate "Exynos thermal management unit driver"
-	depends on ARCH_HAS_BANDGAP && OF
+	depends on OF
 	help
 	  If you say yes here you get support for the TMU (Thermal Management
 	  Unit) driver for SAMSUNG EXYNOS series of SoCs. This driver initialises
diff --git a/drivers/thermal/samsung/exynos_thermal_common.c b/drivers/thermal/samsung/exynos_thermal_common.c
index b6be572704a..7c97db1cf82 100644
--- a/drivers/thermal/samsung/exynos_thermal_common.c
+++ b/drivers/thermal/samsung/exynos_thermal_common.c
@@ -163,7 +163,7 @@ static int exynos_bind(struct thermal_zone_device *thermal,
 		case MONITOR_ZONE:
 		case WARN_ZONE:
 			if (thermal_zone_bind_cooling_device(thermal, i, cdev,
-								level, 0)) {
+							     level, 0, THERMAL_WEIGHT_DEFAULT)) {
 				dev_err(data->dev,
 					"error unbinding cdev inst=%d\n", i);
 				ret = -EINVAL;
@@ -371,9 +371,11 @@ int exynos_register_thermal(struct thermal_sensor_conf *sensor_conf)
 		th_zone->cool_dev[th_zone->cool_dev_size] =
 					cpufreq_cooling_register(&mask_val);
 		if (IS_ERR(th_zone->cool_dev[th_zone->cool_dev_size])) {
-			dev_err(sensor_conf->dev,
-				"Failed to register cpufreq cooling device\n");
-			ret = -EINVAL;
+			ret = PTR_ERR(th_zone->cool_dev[th_zone->cool_dev_size]);
+			if (ret != -EPROBE_DEFER)
+				dev_err(sensor_conf->dev,
+					"Failed to register cpufreq cooling device: %d\n",
+					ret);
 			goto err_unregister;
 		}
 		th_zone->cool_dev_size++;
diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c
index 49c09243fd3..2afca9bf40d 100644
--- a/drivers/thermal/samsung/exynos_tmu.c
+++ b/drivers/thermal/samsung/exynos_tmu.c
@@ -683,7 +683,10 @@ static int exynos_tmu_probe(struct platform_device *pdev)
 	/* Register the sensor with thermal management interface */
 	ret = exynos_register_thermal(sensor_conf);
 	if (ret) {
-		dev_err(&pdev->dev, "Failed to register thermal interface\n");
+		if (ret != -EPROBE_DEFER)
+			dev_err(&pdev->dev,
+				"Failed to register thermal interface: %d\n",
+				ret);
 		goto err_clk;
 	}
 	data->reg_conf = sensor_conf;
diff --git a/drivers/thermal/scpi-thermal.c b/drivers/thermal/scpi-thermal.c
new file mode 100644
index 00000000000..cc630cabc21
--- /dev/null
+++ b/drivers/thermal/scpi-thermal.c
@@ -0,0 +1,309 @@
+#include <linux/cpu_cooling.h>
+#include <linux/cpufreq.h>
+#include <linux/cpumask.h>
+#include <linux/debugfs.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/scpi_protocol.h>
+#include <linux/thermal.h>
+#include <linux/topology.h>
+
+#define SOC_SENSOR "SENSOR_TEMP_SOC"
+
+enum cluster_type {
+	CLUSTER_BIG = 0,
+	CLUSTER_LITTLE,
+	NUM_CLUSTERS
+};
+
+struct cluster_power_coefficients {
+	int dyn_coeff;
+	int static_coeff;
+	int cache_static_coeff;
+};
+
+struct cluster_power_coefficients cluster_data[] = {
+	[CLUSTER_BIG] = {
+		.dyn_coeff = 530,
+		.static_coeff = 103,		/* 75 mW @ 85C/0.9V */
+		.cache_static_coeff = 88,	/* 64 mW @ 85C/0.9V */
+	},
+	[CLUSTER_LITTLE] = {
+		.dyn_coeff = 140,
+		.static_coeff = 36,		/* 26 mW @ 85C/0.9V */
+		.cache_static_coeff = 73,	/* 53 mW @ 85C/0.9V */
+	},
+};
+
+struct scpi_sensor {
+	u16 sensor_id;
+	unsigned long prev_temp;
+	u32 alpha;
+	struct thermal_zone_device *tzd;
+	struct thermal_zone_device *gpu_tzd;
+	struct cpumask cluster[NUM_CLUSTERS];
+	struct thermal_cooling_device *cdevs[NUM_CLUSTERS];
+};
+static struct scpi_sensor scpi_temp_sensor;
+
+static struct scpi_ops *scpi_ops;
+
+#define FRAC_BITS 10
+#define int_to_frac(x) ((x) << FRAC_BITS)
+#define frac_to_int(x) ((x) >> FRAC_BITS)
+
+/**
+ * mul_frac() - multiply two fixed-point numbers
+ * @x:	first multiplicand
+ * @y:	second multiplicand
+ *
+ * Return: the result of multiplying two fixed-point numbers.  The
+ * result is also a fixed-point number.
+ */
+static inline s64 mul_frac(s64 x, s64 y)
+{
+	return (x * y) >> FRAC_BITS;
+}
+
+static unsigned long get_temperature_scale(unsigned long temp)
+{
+	int i, t_exp = 1, t_scale = 0;
+	int coeff[] = { 32000, 4700, -80, 2 }; // * 1E6
+
+	for (i = 0; i < 4; i++) {
+		t_scale += coeff[i] * t_exp;
+		t_exp *= temp;
+	}
+
+	return t_scale / 1000; // the value returned needs to be /1E3
+}
+
+static unsigned long get_voltage_scale(unsigned long u_volt)
+{
+	unsigned long m_volt = u_volt / 1000;
+	unsigned long v_scale;
+
+	v_scale = m_volt * m_volt * m_volt; // = (m_V^3) / (900 ^ 3) =
+
+	return v_scale / 1000000; // the value returned needs to be /(1E3)
+}
+
+/* voltage in uV and temperature in mC */
+static int get_static_power(cpumask_t *cpumask, int interval,
+		unsigned long u_volt, u32 *power)
+{
+	struct thermal_zone_device *tzd = scpi_temp_sensor.tzd;
+	unsigned long t_scale, v_scale, milli_temp = 0;
+	u32 cpu_coeff;
+	int nr_cpus = cpumask_weight(cpumask);
+	enum cluster_type cluster =
+		topology_physical_package_id(cpumask_any(cpumask));
+
+	cpu_coeff = cluster_data[cluster].static_coeff;
+
+	if (tzd)
+		milli_temp = tzd->temperature;
+
+	t_scale = get_temperature_scale(milli_temp / 1000);
+	v_scale = get_voltage_scale(u_volt);
+
+	*power = nr_cpus * (cpu_coeff * t_scale * v_scale) / 1000000;
+
+	if (nr_cpus) {
+		u32 cache_coeff = cluster_data[cluster].cache_static_coeff;
+		*power += (cache_coeff * v_scale * t_scale) / 1000000; /* cache leakage */
+	}
+
+	return 0;
+}
+
+static int get_temp_value(void *data, long *temp)
+{
+	struct scpi_sensor *sensor = (struct scpi_sensor *)data;
+	u32 val;
+	int ret;
+	unsigned long est_temp;
+
+	ret = scpi_ops->sensor_get_value(sensor->sensor_id, &val);
+	if (ret)
+		return ret;
+
+	if (!sensor->prev_temp)
+		sensor->prev_temp = val;
+
+	est_temp = mul_frac(sensor->alpha, val) +
+		mul_frac((int_to_frac(1) - sensor->alpha), sensor->prev_temp);
+
+	sensor->prev_temp = est_temp;
+	*temp = est_temp;
+
+	return 0;
+}
+
+static int get_temp_for_gpu(struct thermal_zone_device *tz, unsigned long *temp)
+{
+	struct scpi_sensor *sensor = (struct scpi_sensor *)tz->devdata;
+
+	*temp = sensor->tzd->temperature;
+
+	return 0;
+}
+
+static void update_debugfs(struct scpi_sensor *sensor_data)
+{
+	struct dentry *dentry_f, *filter_d;
+
+	filter_d = debugfs_create_dir("thermal_lpf_filter", NULL);
+	if (IS_ERR_OR_NULL(filter_d)) {
+		pr_warning("unable to create debugfs directory for the LPF filter\n");
+		return;
+	}
+
+	dentry_f = debugfs_create_u32("alpha", S_IWUSR | S_IRUGO, filter_d,
+				      &sensor_data->alpha);
+	if (IS_ERR_OR_NULL(dentry_f)) {
+		pr_warn("Unable to create debugfsfile: alpha\n");
+		return;
+	}
+}
+
+static struct thermal_zone_of_device_ops scpi_of_ops = {
+	.get_temp = get_temp_value,
+};
+
+static struct thermal_zone_device_ops gpu_dummy_tz_ops = {
+	.get_temp = get_temp_for_gpu,
+};
+
+static struct thermal_zone_params gpu_dummy_tzp = {
+	.governor_name = "user_space",
+};
+
+static int scpi_thermal_probe(struct platform_device *pdev)
+{
+	struct scpi_sensor *sensor_data = &scpi_temp_sensor;
+	struct device_node *np;
+	int sensor, cpu;
+	int i, j;
+
+	scpi_ops = get_scpi_ops();
+	if (!scpi_ops)
+		return -EPROBE_DEFER;
+
+	if (!cpufreq_frequency_get_table(0))
+		return -EPROBE_DEFER;
+
+	platform_set_drvdata(pdev, sensor_data);
+
+	for_each_possible_cpu(cpu) {
+		int cluster_id = topology_physical_package_id(cpu);
+		if (cluster_id > NUM_CLUSTERS) {
+			dev_warn(&pdev->dev, "Cluster id: %d > %d\n",
+				 cluster_id, NUM_CLUSTERS);
+			goto error;
+		}
+
+		cpumask_set_cpu(cpu, &sensor_data->cluster[cluster_id]);
+	}
+
+	for (i = 0, j = 0; i < NUM_CLUSTERS; i++) {
+		char node[16];
+
+		snprintf(node, 16, "cluster%d", i);
+		np = of_find_node_by_name(NULL, node);
+
+		if (!np) {
+			dev_info(&pdev->dev, "Node not found: %s\n", node);
+			continue;
+		}
+
+		sensor_data->cdevs[j] =
+			of_cpufreq_power_cooling_register(np,
+							  &sensor_data->cluster[i],
+							  cluster_data[i].dyn_coeff,
+							  get_static_power);
+
+		if (IS_ERR(sensor_data->cdevs[i])) {
+			dev_warn(&pdev->dev,
+				"Error registering cooling device: %s\n", node);
+			continue;
+		}
+		j++;
+	}
+
+	if ((sensor = scpi_ops->sensor_get_id(SOC_SENSOR)) < 0) {
+		dev_warn(&pdev->dev, "%s not found. ret=%d\n", SOC_SENSOR, sensor);
+		goto error;
+	}
+
+	sensor_data->sensor_id = (u16)sensor;
+	dev_info(&pdev->dev, "Probed %s sensor. Id=%hu\n", SOC_SENSOR, sensor_data->sensor_id);
+
+	/*
+	 * alpha ~= 2 / (N + 1) with N the window of a rolling mean We
+	 * use 8-bit fixed point arithmetic.  For a rolling average of
+	 * window 20, alpha = 2 / (20 + 1) ~= 0.09523809523809523 .
+	 * In 8-bit fixed point arigthmetic, 0.09523809523809523 * 256
+	 * ~= 24
+	 */
+	sensor_data->alpha = 24;
+
+	sensor_data->tzd = thermal_zone_of_sensor_register(&pdev->dev,
+							sensor_data->sensor_id,
+							sensor_data,
+							&scpi_of_ops);
+
+	if (IS_ERR(sensor_data->tzd)) {
+		dev_warn(&pdev->dev, "Error registering sensor: %ld\n", PTR_ERR(sensor_data->tzd));
+		return PTR_ERR(sensor_data->tzd);
+	}
+
+	sensor_data->gpu_tzd = thermal_zone_device_register("gpu", 0, 0,
+							    sensor_data,
+							    &gpu_dummy_tz_ops,
+							    &gpu_dummy_tzp,
+							    0, 0);
+	if (IS_ERR(sensor_data->gpu_tzd)) {
+		int ret = PTR_ERR(sensor_data->gpu_tzd);
+
+		dev_warn(&pdev->dev, "Error register gpu thermal zone: %d\n",
+			 ret);
+		return ret;
+	}
+
+	update_debugfs(sensor_data);
+
+	return 0;
+
+error:
+	return -ENODEV;
+}
+
+static int scpi_thermal_remove(struct platform_device *pdev)
+{
+	struct scpi_sensor *sensor = platform_get_drvdata(pdev);
+
+	thermal_zone_device_unregister(sensor->tzd);
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+static struct of_device_id scpi_thermal_of_match[] = {
+	{ .compatible = "arm,scpi-thermal" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, scpi_thermal_of_match);
+
+static struct platform_driver scpi_thermal_platdrv = {
+	.driver = {
+		.name		= "scpi-thermal",
+		.owner		= THIS_MODULE,
+		.of_match_table = scpi_thermal_of_match,
+	},
+	.probe	= scpi_thermal_probe,
+	.remove	= scpi_thermal_remove,
+};
+module_platform_driver(scpi_thermal_platdrv);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/thermal/tegra_soctherm.c b/drivers/thermal/tegra_soctherm.c
new file mode 100644
index 00000000000..9197fc05c5c
--- /dev/null
+++ b/drivers/thermal/tegra_soctherm.c
@@ -0,0 +1,476 @@
+/*
+ * Copyright (c) 2014, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * Author:
+ *	Mikko Perttunen <mperttunen@nvidia.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+#include <linux/thermal.h>
+
+#include <soc/tegra/fuse.h>
+
+#define SENSOR_CONFIG0				0
+#define SENSOR_CONFIG0_STOP			BIT(0)
+#define SENSOR_CONFIG0_TALL_SHIFT		8
+#define SENSOR_CONFIG0_TCALC_OVER		BIT(4)
+#define SENSOR_CONFIG0_OVER			BIT(3)
+#define SENSOR_CONFIG0_CPTR_OVER		BIT(2)
+
+#define SENSOR_CONFIG1				4
+#define SENSOR_CONFIG1_TSAMPLE_SHIFT		0
+#define SENSOR_CONFIG1_TIDDQ_EN_SHIFT		15
+#define SENSOR_CONFIG1_TEN_COUNT_SHIFT		24
+#define SENSOR_CONFIG1_TEMP_ENABLE		BIT(31)
+
+#define SENSOR_CONFIG2				8
+#define SENSOR_CONFIG2_THERMA_SHIFT		16
+#define SENSOR_CONFIG2_THERMB_SHIFT		0
+
+#define SENSOR_PDIV				0x1c0
+#define SENSOR_PDIV_T124			0x8888
+#define SENSOR_HOTSPOT_OFF			0x1c4
+#define SENSOR_HOTSPOT_OFF_T124			0x00060600
+#define SENSOR_TEMP1				0x1c8
+#define SENSOR_TEMP2				0x1cc
+
+#define SENSOR_TEMP_MASK			0xffff
+#define READBACK_VALUE_MASK			0xff00
+#define READBACK_VALUE_SHIFT			8
+#define READBACK_ADD_HALF			BIT(7)
+#define READBACK_NEGATE				BIT(1)
+
+#define FUSE_TSENSOR8_CALIB			0x180
+#define FUSE_SPARE_REALIGNMENT_REG_0		0x1fc
+
+#define FUSE_TSENSOR_CALIB_CP_TS_BASE_MASK	0x1fff
+#define FUSE_TSENSOR_CALIB_FT_TS_BASE_MASK	(0x1fff << 13)
+#define FUSE_TSENSOR_CALIB_FT_TS_BASE_SHIFT	13
+
+#define FUSE_TSENSOR8_CALIB_CP_TS_BASE_MASK	0x3ff
+#define FUSE_TSENSOR8_CALIB_FT_TS_BASE_MASK	(0x7ff << 10)
+#define FUSE_TSENSOR8_CALIB_FT_TS_BASE_SHIFT	10
+
+#define FUSE_SPARE_REALIGNMENT_REG_SHIFT_CP_MASK 0x3f
+#define FUSE_SPARE_REALIGNMENT_REG_SHIFT_FT_MASK (0x1f << 21)
+#define FUSE_SPARE_REALIGNMENT_REG_SHIFT_FT_SHIFT 21
+
+#define NOMINAL_CALIB_FT_T124			105
+#define NOMINAL_CALIB_CP_T124			25
+
+struct tegra_tsensor_configuration {
+	u32 tall, tsample, tiddq_en, ten_count, pdiv, tsample_ate, pdiv_ate;
+};
+
+struct tegra_tsensor {
+	const struct tegra_tsensor_configuration *config;
+	u32 base, calib_fuse_offset;
+	/* Correction values used to modify values read from calibration fuses */
+	s32 fuse_corr_alpha, fuse_corr_beta;
+};
+
+struct tegra_thermctl_zone {
+	void __iomem *reg;
+	unsigned int shift;
+};
+
+static const struct tegra_tsensor_configuration t124_tsensor_config = {
+	.tall = 16300,
+	.tsample = 120,
+	.tiddq_en = 1,
+	.ten_count = 1,
+	.pdiv = 8,
+	.tsample_ate = 480,
+	.pdiv_ate = 8
+};
+
+static const struct tegra_tsensor t124_tsensors[] = {
+	{
+		.config = &t124_tsensor_config,
+		.base = 0xc0,
+		.calib_fuse_offset = 0x098,
+		.fuse_corr_alpha = 1135400,
+		.fuse_corr_beta = -6266900,
+	},
+	{
+		.config = &t124_tsensor_config,
+		.base = 0xe0,
+		.calib_fuse_offset = 0x084,
+		.fuse_corr_alpha = 1122220,
+		.fuse_corr_beta = -5700700,
+	},
+	{
+		.config = &t124_tsensor_config,
+		.base = 0x100,
+		.calib_fuse_offset = 0x088,
+		.fuse_corr_alpha = 1127000,
+		.fuse_corr_beta = -6768200,
+	},
+	{
+		.config = &t124_tsensor_config,
+		.base = 0x120,
+		.calib_fuse_offset = 0x12c,
+		.fuse_corr_alpha = 1110900,
+		.fuse_corr_beta = -6232000,
+	},
+	{
+		.config = &t124_tsensor_config,
+		.base = 0x140,
+		.calib_fuse_offset = 0x158,
+		.fuse_corr_alpha = 1122300,
+		.fuse_corr_beta = -5936400,
+	},
+	{
+		.config = &t124_tsensor_config,
+		.base = 0x160,
+		.calib_fuse_offset = 0x15c,
+		.fuse_corr_alpha = 1145700,
+		.fuse_corr_beta = -7124600,
+	},
+	{
+		.config = &t124_tsensor_config,
+		.base = 0x180,
+		.calib_fuse_offset = 0x154,
+		.fuse_corr_alpha = 1120100,
+		.fuse_corr_beta = -6000500,
+	},
+	{
+		.config = &t124_tsensor_config,
+		.base = 0x1a0,
+		.calib_fuse_offset = 0x160,
+		.fuse_corr_alpha = 1106500,
+		.fuse_corr_beta = -6729300,
+	},
+};
+
+struct tegra_soctherm {
+	struct reset_control *reset;
+	struct clk *clock_tsensor;
+	struct clk *clock_soctherm;
+	void __iomem *regs;
+
+	struct thermal_zone_device *thermctl_tzs[4];
+};
+
+struct tsensor_shared_calibration {
+	u32 base_cp, base_ft;
+	u32 actual_temp_cp, actual_temp_ft;
+};
+
+static int calculate_shared_calibration(struct tsensor_shared_calibration *r)
+{
+	u32 val, shifted_cp, shifted_ft;
+	int err;
+
+	err = tegra_fuse_readl(FUSE_TSENSOR8_CALIB, &val);
+	if (err)
+		return err;
+	r->base_cp = val & FUSE_TSENSOR8_CALIB_CP_TS_BASE_MASK;
+	r->base_ft = (val & FUSE_TSENSOR8_CALIB_FT_TS_BASE_MASK)
+		>> FUSE_TSENSOR8_CALIB_FT_TS_BASE_SHIFT;
+	val = ((val & FUSE_SPARE_REALIGNMENT_REG_SHIFT_FT_MASK)
+		>> FUSE_SPARE_REALIGNMENT_REG_SHIFT_FT_SHIFT);
+	shifted_ft = sign_extend32(val, 4);
+
+	err = tegra_fuse_readl(FUSE_SPARE_REALIGNMENT_REG_0, &val);
+	if (err)
+		return err;
+	shifted_cp = sign_extend32(val, 5);
+
+	r->actual_temp_cp = 2 * NOMINAL_CALIB_CP_T124 + shifted_cp;
+	r->actual_temp_ft = 2 * NOMINAL_CALIB_FT_T124 + shifted_ft;
+
+	return 0;
+}
+
+static s64 div64_s64_precise(s64 a, s64 b)
+{
+	s64 r, al;
+
+	/* Scale up for increased precision division */
+	al = a << 16;
+
+	r = div64_s64(al * 2 + 1, 2 * b);
+	return r >> 16;
+}
+
+static int
+calculate_tsensor_calibration(const struct tegra_tsensor *sensor,
+			      const struct tsensor_shared_calibration *shared,
+			      u32 *calib)
+{
+	u32 val;
+	s32 actual_tsensor_ft, actual_tsensor_cp, delta_sens, delta_temp,
+	    mult, div;
+	s16 therma, thermb;
+	s64 tmp;
+	int err;
+
+	err = tegra_fuse_readl(sensor->calib_fuse_offset, &val);
+	if (err)
+		return err;
+
+	actual_tsensor_cp = (shared->base_cp * 64) + sign_extend32(val, 12);
+	val = (val & FUSE_TSENSOR_CALIB_FT_TS_BASE_MASK)
+		>> FUSE_TSENSOR_CALIB_FT_TS_BASE_SHIFT;
+	actual_tsensor_ft = (shared->base_ft * 32) + sign_extend32(val, 12);
+
+	delta_sens = actual_tsensor_ft - actual_tsensor_cp;
+	delta_temp = shared->actual_temp_ft - shared->actual_temp_cp;
+
+	mult = sensor->config->pdiv * sensor->config->tsample_ate;
+	div = sensor->config->tsample * sensor->config->pdiv_ate;
+
+	therma = div64_s64_precise((s64) delta_temp * (1LL << 13) * mult,
+				   (s64) delta_sens * div);
+
+	tmp = (s64)actual_tsensor_ft * shared->actual_temp_cp -
+	      (s64)actual_tsensor_cp * shared->actual_temp_ft;
+	thermb = div64_s64_precise(tmp, (s64)delta_sens);
+
+	therma = div64_s64_precise((s64)therma * sensor->fuse_corr_alpha,
+				   (s64)1000000LL);
+	thermb = div64_s64_precise((s64)thermb * sensor->fuse_corr_alpha +
+				   sensor->fuse_corr_beta, (s64)1000000LL);
+
+	*calib = ((u16)therma << SENSOR_CONFIG2_THERMA_SHIFT) |
+		 ((u16)thermb << SENSOR_CONFIG2_THERMB_SHIFT);
+
+	return 0;
+}
+
+static int enable_tsensor(struct tegra_soctherm *tegra,
+			  const struct tegra_tsensor *sensor,
+			  const struct tsensor_shared_calibration *shared)
+{
+	void __iomem *base = tegra->regs + sensor->base;
+	unsigned int val;
+	u32 calib;
+	int err;
+
+	err = calculate_tsensor_calibration(sensor, shared, &calib);
+	if (err)
+		return err;
+
+	val = sensor->config->tall << SENSOR_CONFIG0_TALL_SHIFT;
+	writel(val, base + SENSOR_CONFIG0);
+
+	val  = (sensor->config->tsample - 1) << SENSOR_CONFIG1_TSAMPLE_SHIFT;
+	val |= sensor->config->tiddq_en << SENSOR_CONFIG1_TIDDQ_EN_SHIFT;
+	val |= sensor->config->ten_count << SENSOR_CONFIG1_TEN_COUNT_SHIFT;
+	val |= SENSOR_CONFIG1_TEMP_ENABLE;
+	writel(val, base + SENSOR_CONFIG1);
+
+	writel(calib, base + SENSOR_CONFIG2);
+
+	return 0;
+}
+
+/*
+ * Translate from soctherm readback format to millicelsius.
+ * The soctherm readback format in bits is as follows:
+ *   TTTTTTTT H______N
+ * where T's contain the temperature in Celsius,
+ * H denotes an addition of 0.5 Celsius and N denotes negation
+ * of the final value.
+ */
+static long translate_temp(u16 val)
+{
+	long t;
+
+	t = ((val & READBACK_VALUE_MASK) >> READBACK_VALUE_SHIFT) * 1000;
+	if (val & READBACK_ADD_HALF)
+		t += 500;
+	if (val & READBACK_NEGATE)
+		t *= -1;
+
+	return t;
+}
+
+static int tegra_thermctl_get_temp(void *data, long *out_temp)
+{
+	struct tegra_thermctl_zone *zone = data;
+	u32 val;
+
+	val = (readl(zone->reg) >> zone->shift) & SENSOR_TEMP_MASK;
+	*out_temp = translate_temp(val);
+
+	return 0;
+}
+
+static const struct thermal_zone_of_device_ops tegra_of_thermal_ops = {
+	.get_temp = tegra_thermctl_get_temp,
+};
+
+static const struct of_device_id tegra_soctherm_of_match[] = {
+	{ .compatible = "nvidia,tegra124-soctherm" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, tegra_soctherm_of_match);
+
+struct thermctl_zone_desc {
+	unsigned int offset;
+	unsigned int shift;
+};
+
+static const struct thermctl_zone_desc t124_thermctl_temp_zones[] = {
+	{ SENSOR_TEMP1, 16 },
+	{ SENSOR_TEMP2, 16 },
+	{ SENSOR_TEMP1, 0 },
+	{ SENSOR_TEMP2, 0 }
+};
+
+static int tegra_soctherm_probe(struct platform_device *pdev)
+{
+	struct tegra_soctherm *tegra;
+	struct thermal_zone_device *tz;
+	struct tsensor_shared_calibration shared_calib;
+	struct resource *res;
+	unsigned int i;
+	int err;
+
+	const struct tegra_tsensor *tsensors = t124_tsensors;
+
+	tegra = devm_kzalloc(&pdev->dev, sizeof(*tegra), GFP_KERNEL);
+	if (!tegra)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	tegra->regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(tegra->regs))
+		return PTR_ERR(tegra->regs);
+
+	tegra->reset = devm_reset_control_get(&pdev->dev, "soctherm");
+	if (IS_ERR(tegra->reset)) {
+		dev_err(&pdev->dev, "can't get soctherm reset\n");
+		return PTR_ERR(tegra->reset);
+	}
+
+	tegra->clock_tsensor = devm_clk_get(&pdev->dev, "tsensor");
+	if (IS_ERR(tegra->clock_tsensor)) {
+		dev_err(&pdev->dev, "can't get tsensor clock\n");
+		return PTR_ERR(tegra->clock_tsensor);
+	}
+
+	tegra->clock_soctherm = devm_clk_get(&pdev->dev, "soctherm");
+	if (IS_ERR(tegra->clock_soctherm)) {
+		dev_err(&pdev->dev, "can't get soctherm clock\n");
+		return PTR_ERR(tegra->clock_soctherm);
+	}
+
+	reset_control_assert(tegra->reset);
+
+	err = clk_prepare_enable(tegra->clock_soctherm);
+	if (err)
+		return err;
+
+	err = clk_prepare_enable(tegra->clock_tsensor);
+	if (err) {
+		clk_disable_unprepare(tegra->clock_soctherm);
+		return err;
+	}
+
+	reset_control_deassert(tegra->reset);
+
+	/* Initialize raw sensors */
+
+	err = calculate_shared_calibration(&shared_calib);
+	if (err)
+		goto disable_clocks;
+
+	for (i = 0; i < ARRAY_SIZE(t124_tsensors); ++i) {
+		err = enable_tsensor(tegra, tsensors + i, &shared_calib);
+		if (err)
+			goto disable_clocks;
+	}
+
+	writel(SENSOR_PDIV_T124, tegra->regs + SENSOR_PDIV);
+	writel(SENSOR_HOTSPOT_OFF_T124, tegra->regs + SENSOR_HOTSPOT_OFF);
+
+	/* Initialize thermctl sensors */
+
+	for (i = 0; i < ARRAY_SIZE(tegra->thermctl_tzs); ++i) {
+		struct tegra_thermctl_zone *zone =
+			devm_kzalloc(&pdev->dev, sizeof(*zone), GFP_KERNEL);
+		if (!zone) {
+			err = -ENOMEM;
+			goto unregister_tzs;
+		}
+
+		zone->reg = tegra->regs + t124_thermctl_temp_zones[i].offset;
+		zone->shift = t124_thermctl_temp_zones[i].shift;
+
+		tz = thermal_zone_of_sensor_register(&pdev->dev, i, zone,
+						     &tegra_of_thermal_ops);
+		if (IS_ERR(tz)) {
+			err = PTR_ERR(tz);
+			dev_err(&pdev->dev, "failed to register sensor: %d\n",
+				err);
+			goto unregister_tzs;
+		}
+
+		tegra->thermctl_tzs[i] = tz;
+	}
+
+	return 0;
+
+unregister_tzs:
+	while (i--)
+		thermal_zone_of_sensor_unregister(&pdev->dev,
+						  tegra->thermctl_tzs[i]);
+
+disable_clocks:
+	clk_disable_unprepare(tegra->clock_tsensor);
+	clk_disable_unprepare(tegra->clock_soctherm);
+
+	return err;
+}
+
+static int tegra_soctherm_remove(struct platform_device *pdev)
+{
+	struct tegra_soctherm *tegra = platform_get_drvdata(pdev);
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(tegra->thermctl_tzs); ++i) {
+		thermal_zone_of_sensor_unregister(&pdev->dev,
+						  tegra->thermctl_tzs[i]);
+	}
+
+	clk_disable_unprepare(tegra->clock_tsensor);
+	clk_disable_unprepare(tegra->clock_soctherm);
+
+	return 0;
+}
+
+static struct platform_driver tegra_soctherm_driver = {
+	.probe = tegra_soctherm_probe,
+	.remove = tegra_soctherm_remove,
+	.driver = {
+		.name = "tegra-soctherm",
+		.of_match_table = tegra_soctherm_of_match,
+	},
+};
+module_platform_driver(tegra_soctherm_driver);
+
+MODULE_AUTHOR("Mikko Perttunen <mperttunen@nvidia.com>");
+MODULE_DESCRIPTION("NVIDIA Tegra SOCTHERM thermal management driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 43b90709585..249b6123d65 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -75,6 +75,58 @@ static struct thermal_governor *__find_governor(const char *name)
 	return NULL;
 }
 
+/**
+ * bind_previous_governor() - bind the previous governor of the thermal zone
+ * @tz:		a valid pointer to a struct thermal_zone_device
+ * @failed_gov_name:	the name of the governor that failed to register
+ *
+ * Register the previous governor of the thermal zone after a new
+ * governor has failed to be bound.
+ */
+static void bind_previous_governor(struct thermal_zone_device *tz,
+				   const char *failed_gov_name)
+{
+	if (tz->governor && tz->governor->bind_to_tz) {
+		if (tz->governor->bind_to_tz(tz)) {
+			dev_err(&tz->device,
+				"governor %s failed to bind and the previous one (%s) failed to bind again, thermal zone %s has no governor\n",
+				failed_gov_name, tz->governor->name, tz->type);
+			tz->governor = NULL;
+		}
+	}
+}
+
+/**
+ * thermal_set_governor() - Switch to another governor
+ * @tz:		a valid pointer to a struct thermal_zone_device
+ * @new_gov:	pointer to the new governor
+ *
+ * Change the governor of thermal zone @tz.
+ *
+ * Return: 0 on success, an error if the new governor's bind_to_tz() failed.
+ */
+static int thermal_set_governor(struct thermal_zone_device *tz,
+				struct thermal_governor *new_gov)
+{
+	int ret = 0;
+
+	if (tz->governor && tz->governor->unbind_from_tz)
+		tz->governor->unbind_from_tz(tz);
+
+	if (new_gov && new_gov->bind_to_tz) {
+		ret = new_gov->bind_to_tz(tz);
+		if (ret) {
+			bind_previous_governor(tz, new_gov->name);
+
+			return ret;
+		}
+	}
+
+	tz->governor = new_gov;
+
+	return ret;
+}
+
 int thermal_register_governor(struct thermal_governor *governor)
 {
 	int err;
@@ -107,8 +159,15 @@ int thermal_register_governor(struct thermal_governor *governor)
 
 		name = pos->tzp->governor_name;
 
-		if (!strncasecmp(name, governor->name, THERMAL_NAME_LENGTH))
-			pos->governor = governor;
+		if (!strncasecmp(name, governor->name, THERMAL_NAME_LENGTH)) {
+			int ret;
+
+			ret = thermal_set_governor(pos, governor);
+			if (ret)
+				dev_err(&pos->device,
+					"Failed to set governor %s for thermal zone %s: %d\n",
+					governor->name, pos->type, ret);
+		}
 	}
 
 	mutex_unlock(&thermal_list_lock);
@@ -134,7 +193,7 @@ void thermal_unregister_governor(struct thermal_governor *governor)
 	list_for_each_entry(pos, &thermal_tz_list, node) {
 		if (!strncasecmp(pos->governor->name, governor->name,
 						THERMAL_NAME_LENGTH))
-			pos->governor = NULL;
+			thermal_set_governor(pos, NULL);
 	}
 
 	mutex_unlock(&thermal_list_lock);
@@ -218,7 +277,8 @@ static void print_bind_err_msg(struct thermal_zone_device *tz,
 
 static void __bind(struct thermal_zone_device *tz, int mask,
 			struct thermal_cooling_device *cdev,
-			unsigned long *limits)
+			unsigned long *limits,
+			unsigned int weight)
 {
 	int i, ret;
 
@@ -233,7 +293,8 @@ static void __bind(struct thermal_zone_device *tz, int mask,
 				upper = limits[i * 2 + 1];
 			}
 			ret = thermal_zone_bind_cooling_device(tz, i, cdev,
-							       upper, lower);
+							       upper, lower,
+							       weight);
 			if (ret)
 				print_bind_err_msg(tz, cdev, ret);
 		}
@@ -280,7 +341,8 @@ static void bind_cdev(struct thermal_cooling_device *cdev)
 				continue;
 			tzp->tbp[i].cdev = cdev;
 			__bind(pos, tzp->tbp[i].trip_mask, cdev,
-			       tzp->tbp[i].binding_limits);
+			       tzp->tbp[i].binding_limits,
+			       tzp->tbp[i].weight);
 		}
 	}
 
@@ -319,7 +381,8 @@ static void bind_tz(struct thermal_zone_device *tz)
 				continue;
 			tzp->tbp[i].cdev = pos;
 			__bind(tz, tzp->tbp[i].trip_mask, pos,
-			       tzp->tbp[i].binding_limits);
+			       tzp->tbp[i].binding_limits,
+			       tzp->tbp[i].weight);
 		}
 	}
 exit:
@@ -368,7 +431,7 @@ static void handle_critical_trips(struct thermal_zone_device *tz,
 	tz->ops->get_trip_temp(tz, trip, &trip_temp);
 
 	/* If we have not crossed the trip_temp, we do not care. */
-	if (tz->temperature < trip_temp)
+	if (trip_temp <= 0 || tz->temperature < trip_temp)
 		return;
 
 	trace_thermal_zone_trip(tz, trip, trip_type);
@@ -711,7 +774,8 @@ passive_store(struct device *dev, struct device_attribute *attr,
 				thermal_zone_bind_cooling_device(tz,
 						THERMAL_TRIPS_NONE, cdev,
 						THERMAL_NO_LIMIT,
-						THERMAL_NO_LIMIT);
+						THERMAL_NO_LIMIT,
+						THERMAL_WEIGHT_DEFAULT);
 		}
 		mutex_unlock(&thermal_list_lock);
 		if (!tz->passive_delay)
@@ -757,15 +821,18 @@ policy_store(struct device *dev, struct device_attribute *attr,
 	snprintf(name, sizeof(name), "%s", buf);
 
 	mutex_lock(&thermal_governor_lock);
+	mutex_lock(&tz->lock);
 
 	gov = __find_governor(strim(name));
 	if (!gov)
 		goto exit;
 
-	tz->governor = gov;
-	ret = count;
+	ret = thermal_set_governor(tz, gov);
+	if (!ret)
+		ret = count;
 
 exit:
+	mutex_unlock(&tz->lock);
 	mutex_unlock(&thermal_governor_lock);
 	return ret;
 }
@@ -806,6 +873,158 @@ emul_temp_store(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR(emul_temp, S_IWUSR, NULL, emul_temp_store);
 #endif/*CONFIG_THERMAL_EMULATION*/
 
+static ssize_t
+sustainable_power_show(struct device *dev, struct device_attribute *devattr,
+		       char *buf)
+{
+	struct thermal_zone_device *tz = to_thermal_zone(dev);
+
+	if (tz->tzp)
+		return sprintf(buf, "%u\n", tz->tzp->sustainable_power);
+	else
+		return -EIO;
+}
+
+static ssize_t
+sustainable_power_store(struct device *dev, struct device_attribute *devattr,
+			const char *buf, size_t count)
+{
+	struct thermal_zone_device *tz = to_thermal_zone(dev);
+	u32 sustainable_power;
+
+	if (!tz->tzp)
+		return -EIO;
+
+	if (kstrtou32(buf, 10, &sustainable_power))
+		return -EINVAL;
+
+	tz->tzp->sustainable_power = sustainable_power;
+
+	return count;
+}
+static DEVICE_ATTR(sustainable_power, S_IWUSR | S_IRUGO, sustainable_power_show,
+		sustainable_power_store);
+
+#define create_s32_tzp_attr(name)					\
+	static ssize_t							\
+	name##_show(struct device *dev, struct device_attribute *devattr, \
+		char *buf)						\
+	{								\
+	struct thermal_zone_device *tz = to_thermal_zone(dev);		\
+									\
+	if (tz->tzp)							\
+		return sprintf(buf, "%u\n", tz->tzp->name);		\
+	else								\
+		return -EIO;						\
+	}								\
+									\
+	static ssize_t							\
+	name##_store(struct device *dev, struct device_attribute *devattr, \
+		const char *buf, size_t count)				\
+	{								\
+		struct thermal_zone_device *tz = to_thermal_zone(dev);	\
+		s32 value;						\
+									\
+		if (!tz->tzp)						\
+			return -EIO;					\
+									\
+		if (kstrtos32(buf, 10, &value))				\
+			return -EINVAL;					\
+									\
+		tz->tzp->name = value;					\
+									\
+		return count;						\
+	}								\
+	static DEVICE_ATTR(name, S_IWUSR | S_IRUGO, name##_show, name##_store)
+
+create_s32_tzp_attr(k_po);
+create_s32_tzp_attr(k_pu);
+create_s32_tzp_attr(k_i);
+create_s32_tzp_attr(k_d);
+create_s32_tzp_attr(integral_cutoff);
+create_s32_tzp_attr(slope);
+create_s32_tzp_attr(offset);
+#undef create_s32_tzp_attr
+
+static struct device_attribute *dev_tzp_attrs[] = {
+	&dev_attr_sustainable_power,
+	&dev_attr_k_po,
+	&dev_attr_k_pu,
+	&dev_attr_k_i,
+	&dev_attr_k_d,
+	&dev_attr_integral_cutoff,
+	&dev_attr_slope,
+	&dev_attr_offset,
+};
+
+static int create_tzp_attrs(struct device *dev)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dev_tzp_attrs); i++) {
+		int ret;
+		struct device_attribute *dev_attr = dev_tzp_attrs[i];
+
+		ret = device_create_file(dev, dev_attr);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * power_actor_get_max_power() - get the maximum power that a cdev can consume
+ * @cdev:	pointer to &thermal_cooling_device
+ * @tz:		a valid thermal zone device pointer
+ * @max_power:	pointer in which to store the maximum power
+ *
+ * Calculate the maximum power consumption in milliwats that the
+ * cooling device can currently consume and store it in @max_power.
+ *
+ * Return: 0 on success, -EINVAL if @cdev doesn't support the
+ * power_actor API or -E* on other error.
+ */
+int power_actor_get_max_power(struct thermal_cooling_device *cdev,
+			      struct thermal_zone_device *tz, u32 *max_power)
+{
+	if (!cdev_is_power_actor(cdev))
+		return -EINVAL;
+
+	return cdev->ops->state2power(cdev, tz, 0, max_power);
+}
+
+/**
+ * power_actor_set_power() - limit the maximum power that a cooling device can consume
+ * @cdev:	pointer to &thermal_cooling_device
+ * @instance:	thermal instance to update
+ * @power:	the power in milliwatts
+ *
+ * Set the cooling device to consume at most @power milliwatts.
+ *
+ * Return: 0 on success, -EINVAL if the cooling device does not
+ * implement the power actor API or -E* for other failures.
+ */
+int power_actor_set_power(struct thermal_cooling_device *cdev,
+			  struct thermal_instance *instance, u32 power)
+{
+	unsigned long state;
+	int ret;
+
+	if (!cdev_is_power_actor(cdev))
+		return -EINVAL;
+
+	ret = cdev->ops->power2state(cdev, instance->tz, power, &state);
+	if (ret)
+		return ret;
+
+	instance->target = state;
+	cdev->updated = false;
+	thermal_cdev_update(cdev);
+
+	return 0;
+}
+
 static DEVICE_ATTR(type, 0444, type_show, NULL);
 static DEVICE_ATTR(temp, 0444, temp_show, NULL);
 static DEVICE_ATTR(mode, 0644, mode_show, mode_store);
@@ -897,6 +1116,50 @@ thermal_cooling_device_trip_point_show(struct device *dev,
 		return sprintf(buf, "%d\n", instance->trip);
 }
 
+static struct attribute *cooling_device_attrs[] = {
+	&dev_attr_cdev_type.attr,
+	&dev_attr_max_state.attr,
+	&dev_attr_cur_state.attr,
+	NULL,
+};
+
+static const struct attribute_group cooling_device_attr_group = {
+	.attrs = cooling_device_attrs,
+};
+
+static const struct attribute_group *cooling_device_attr_groups[] = {
+	&cooling_device_attr_group,
+	NULL,
+};
+
+static ssize_t
+thermal_cooling_device_weight_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct thermal_instance *instance;
+
+	instance = container_of(attr, struct thermal_instance, weight_attr);
+
+	return sprintf(buf, "%d\n", instance->weight);
+}
+
+static ssize_t
+thermal_cooling_device_weight_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t count)
+{
+	struct thermal_instance *instance;
+	int ret, weight;
+
+	ret = kstrtoint(buf, 0, &weight);
+	if (ret)
+		return ret;
+
+	instance = container_of(attr, struct thermal_instance, weight_attr);
+	instance->weight = weight;
+
+	return count;
+}
 /* Device management */
 
 /**
@@ -911,6 +1174,9 @@ thermal_cooling_device_trip_point_show(struct device *dev,
  * @lower:	the Minimum cooling state can be used for this trip point.
  *		THERMAL_NO_LIMIT means no lower limit,
  *		and the cooling device can be in cooling state 0.
+ * @weight:	The weight of the cooling device to be bound to the
+ *		thermal zone. Use THERMAL_WEIGHT_DEFAULT for the
+ *		default value
  *
  * This interface function bind a thermal cooling device to the certain trip
  * point of a thermal zone device.
@@ -921,7 +1187,8 @@ thermal_cooling_device_trip_point_show(struct device *dev,
 int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz,
 				     int trip,
 				     struct thermal_cooling_device *cdev,
-				     unsigned long upper, unsigned long lower)
+				     unsigned long upper, unsigned long lower,
+				     unsigned int weight)
 {
 	struct thermal_instance *dev;
 	struct thermal_instance *pos;
@@ -964,6 +1231,7 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz,
 	dev->upper = upper;
 	dev->lower = lower;
 	dev->target = THERMAL_NO_TARGET;
+	dev->weight = weight;
 
 	result = get_idr(&tz->idr, &tz->lock, &dev->id);
 	if (result)
@@ -984,6 +1252,16 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz,
 	if (result)
 		goto remove_symbol_link;
 
+	sprintf(dev->weight_attr_name, "cdev%d_weight", dev->id);
+	sysfs_attr_init(&dev->weight_attr.attr);
+	dev->weight_attr.attr.name = dev->weight_attr_name;
+	dev->weight_attr.attr.mode = S_IWUSR | S_IRUGO;
+	dev->weight_attr.show = thermal_cooling_device_weight_show;
+	dev->weight_attr.store = thermal_cooling_device_weight_store;
+	result = device_create_file(&tz->device, &dev->weight_attr);
+	if (result)
+		goto remove_trip_file;
+
 	mutex_lock(&tz->lock);
 	mutex_lock(&cdev->lock);
 	list_for_each_entry(pos, &tz->thermal_instances, tz_node)
@@ -1001,6 +1279,8 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz,
 	if (!result)
 		return 0;
 
+	device_remove_file(&tz->device, &dev->weight_attr);
+remove_trip_file:
 	device_remove_file(&tz->device, &dev->attr);
 remove_symbol_link:
 	sysfs_remove_link(&tz->device.kobj, dev->name);
@@ -1126,6 +1406,7 @@ __thermal_cooling_device_register(struct device_node *np,
 	cdev->ops = ops;
 	cdev->updated = false;
 	cdev->device.class = &thermal_class;
+	cdev->device.groups = cooling_device_attr_groups;
 	cdev->devdata = devdata;
 	dev_set_name(&cdev->device, "cooling_device%d", cdev->id);
 	result = device_register(&cdev->device);
@@ -1135,21 +1416,6 @@ __thermal_cooling_device_register(struct device_node *np,
 		return ERR_PTR(result);
 	}
 
-	/* sys I/F */
-	if (type) {
-		result = device_create_file(&cdev->device, &dev_attr_cdev_type);
-		if (result)
-			goto unregister;
-	}
-
-	result = device_create_file(&cdev->device, &dev_attr_max_state);
-	if (result)
-		goto unregister;
-
-	result = device_create_file(&cdev->device, &dev_attr_cur_state);
-	if (result)
-		goto unregister;
-
 	/* Add 'this' new cdev to the global cdev list */
 	mutex_lock(&thermal_list_lock);
 	list_add(&cdev->node, &thermal_cdev_list);
@@ -1159,11 +1425,6 @@ __thermal_cooling_device_register(struct device_node *np,
 	bind_cdev(cdev);
 
 	return cdev;
-
-unregister:
-	release_idr(&thermal_cdev_idr, &thermal_idr_lock, cdev->id);
-	device_unregister(&cdev->device);
-	return ERR_PTR(result);
 }
 
 /**
@@ -1374,7 +1635,8 @@ static int create_trip_attrs(struct thermal_zone_device *tz, int mask)
 						tz->trip_temp_attrs[indx].name;
 		tz->trip_temp_attrs[indx].attr.attr.mode = S_IRUGO;
 		tz->trip_temp_attrs[indx].attr.show = trip_point_temp_show;
-		if (mask & (1 << indx)) {
+		if (IS_ENABLED(CONFIG_THERMAL_WRITABLE_TRIPS) &&
+		    mask & (1 << indx)) {
 			tz->trip_temp_attrs[indx].attr.attr.mode |= S_IWUSR;
 			tz->trip_temp_attrs[indx].attr.store =
 							trip_point_temp_store;
@@ -1451,7 +1713,7 @@ static void remove_trip_attrs(struct thermal_zone_device *tz)
 struct thermal_zone_device *thermal_zone_device_register(const char *type,
 	int trips, int mask, void *devdata,
 	struct thermal_zone_device_ops *ops,
-	const struct thermal_zone_params *tzp,
+	struct thermal_zone_params *tzp,
 	int passive_delay, int polling_delay)
 {
 	struct thermal_zone_device *tz;
@@ -1459,6 +1721,7 @@ struct thermal_zone_device *thermal_zone_device_register(const char *type,
 	int result;
 	int count;
 	int passive = 0;
+	struct thermal_governor *governor;
 
 	if (type && strlen(type) >= THERMAL_NAME_LENGTH)
 		return ERR_PTR(-EINVAL);
@@ -1545,13 +1808,24 @@ struct thermal_zone_device *thermal_zone_device_register(const char *type,
 	if (result)
 		goto unregister;
 
+	/* Add thermal zone params */
+	result = create_tzp_attrs(&tz->device);
+	if (result)
+		goto unregister;
+
 	/* Update 'this' zone's governor information */
 	mutex_lock(&thermal_governor_lock);
 
 	if (tz->tzp)
-		tz->governor = __find_governor(tz->tzp->governor_name);
+		governor = __find_governor(tz->tzp->governor_name);
 	else
-		tz->governor = def_governor;
+		governor = def_governor;
+
+	result = thermal_set_governor(tz, governor);
+	if (result) {
+		mutex_unlock(&thermal_governor_lock);
+		goto unregister;
+	}
 
 	mutex_unlock(&thermal_governor_lock);
 
@@ -1640,7 +1914,7 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 		device_remove_file(&tz->device, &dev_attr_mode);
 	device_remove_file(&tz->device, &dev_attr_policy);
 	remove_trip_attrs(tz);
-	tz->governor = NULL;
+	thermal_set_governor(tz, NULL);
 
 	thermal_remove_hwmon_sysfs(tz);
 	release_idr(&thermal_tz_idr, &thermal_idr_lock, tz->id);
@@ -1800,7 +2074,11 @@ static int __init thermal_register_governors(void)
 	if (result)
 		return result;
 
-	return thermal_gov_user_space_register();
+	result = thermal_gov_user_space_register();
+	if (result)
+		return result;
+
+	return thermal_gov_power_allocator_register();
 }
 
 static void thermal_unregister_governors(void)
@@ -1809,6 +2087,7 @@ static void thermal_unregister_governors(void)
 	thermal_gov_fair_share_unregister();
 	thermal_gov_bang_bang_unregister();
 	thermal_gov_user_space_unregister();
+	thermal_gov_power_allocator_unregister();
 }
 
 static int __init thermal_init(void)
@@ -1835,10 +2114,10 @@ static int __init thermal_init(void)
 
 exit_netlink:
 	genetlink_exit();
-unregister_governors:
-	thermal_unregister_governors();
 unregister_class:
 	class_unregister(&thermal_class);
+unregister_governors:
+	thermal_unregister_governors();
 error:
 	idr_destroy(&thermal_tz_idr);
 	idr_destroy(&thermal_cdev_idr);
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index d15d243de27..8a6624488cc 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -46,8 +46,11 @@ struct thermal_instance {
 	unsigned long target;	/* expected cooling state */
 	char attr_name[THERMAL_NAME_LENGTH];
 	struct device_attribute attr;
+	char weight_attr_name[THERMAL_NAME_LENGTH];
+	struct device_attribute weight_attr;
 	struct list_head tz_node; /* node in tz->thermal_instances */
 	struct list_head cdev_node; /* node in cdev->thermal_instances */
+	unsigned int weight; /* The weight of the cooling device */
 };
 
 int thermal_register_governor(struct thermal_governor *);
@@ -85,13 +88,39 @@ static inline int thermal_gov_user_space_register(void) { return 0; }
 static inline void thermal_gov_user_space_unregister(void) {}
 #endif /* CONFIG_THERMAL_GOV_USER_SPACE */
 
+#ifdef CONFIG_THERMAL_GOV_POWER_ALLOCATOR
+int thermal_gov_power_allocator_register(void);
+void thermal_gov_power_allocator_unregister(void);
+#else
+static inline int thermal_gov_power_allocator_register(void) { return 0; }
+static inline void thermal_gov_power_allocator_unregister(void) {}
+#endif /* CONFIG_THERMAL_GOV_POWER_ALLOCATOR */
+
 /* device tree support */
 #ifdef CONFIG_THERMAL_OF
 int of_parse_thermal_zones(void);
 void of_thermal_destroy_zones(void);
+int of_thermal_get_ntrips(struct thermal_zone_device *);
+bool of_thermal_is_trip_valid(struct thermal_zone_device *, int);
+const struct thermal_trip *
+of_thermal_get_trip_points(struct thermal_zone_device *);
 #else
 static inline int of_parse_thermal_zones(void) { return 0; }
 static inline void of_thermal_destroy_zones(void) { }
+static inline int of_thermal_get_ntrips(struct thermal_zone_device *tz)
+{
+	return 0;
+}
+static inline bool of_thermal_is_trip_valid(struct thermal_zone_device *tz,
+					    int trip)
+{
+	return 0;
+}
+static inline const struct thermal_trip *
+of_thermal_get_trip_points(struct thermal_zone_device *tz)
+{
+	return NULL;
+}
 #endif
 
 #endif /* __THERMAL_CORE_H__ */
diff --git a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
index 9eec26dc044..68f53fcb8fb 100644
--- a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
+++ b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
@@ -28,7 +28,6 @@
 #include <linux/kernel.h>
 #include <linux/workqueue.h>
 #include <linux/thermal.h>
-#include <linux/cpufreq.h>
 #include <linux/cpumask.h>
 #include <linux/cpu_cooling.h>
 #include <linux/of.h>
@@ -147,7 +146,8 @@ static int ti_thermal_bind(struct thermal_zone_device *thermal,
 	return thermal_zone_bind_cooling_device(thermal, 0, cdev,
 	/* bind with min and max states defined by cpu_cooling */
 						THERMAL_NO_LIMIT,
-						THERMAL_NO_LIMIT);
+						THERMAL_NO_LIMIT,
+						THERMAL_WEIGHT_DEFAULT);
 }
 
 /* Unbind callback functions for thermal zone */
@@ -286,6 +286,11 @@ static int ti_thermal_get_crit_temp(struct thermal_zone_device *thermal,
 	return ti_thermal_get_trip_temp(thermal, OMAP_TRIP_NUMBER - 1, temp);
 }
 
+static const struct thermal_zone_of_device_ops ti_of_thermal_ops = {
+	.get_temp = __ti_thermal_get_temp,
+	.get_trend = __ti_thermal_get_trend,
+};
+
 static struct thermal_zone_device_ops ti_thermal_ops = {
 	.get_temp = ti_thermal_get_temp,
 	.get_trend = ti_thermal_get_trend,
@@ -333,8 +338,7 @@ int ti_thermal_expose_sensor(struct ti_bandgap *bgp, int id,
 
 	/* in case this is specified by DT */
 	data->ti_thermal = thermal_zone_of_sensor_register(bgp->dev, id,
-					data, __ti_thermal_get_temp,
-					__ti_thermal_get_trend);
+					data, &ti_of_thermal_ops);
 	if (IS_ERR(data->ti_thermal)) {
 		/* Create thermal zone */
 		data->ti_thermal = thermal_zone_device_register(domain,
@@ -403,11 +407,6 @@ int ti_thermal_register_cpu_cooling(struct ti_bandgap *bgp, int id)
 	if (!data)
 		return -EINVAL;
 
-	if (!cpufreq_get_current_driver()) {
-		dev_dbg(bgp->dev, "no cpufreq driver yet\n");
-		return -EPROBE_DEFER;
-	}
-
 	/* Register cooling device */
 	data->cool_dev = cpufreq_cooling_register(cpu_present_mask);
 	if (IS_ERR(data->cool_dev)) {
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index f1e57425e39..7a3d146a5f0 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -289,7 +289,7 @@ static int xen_initial_domain_console_init(void)
 			return -ENOMEM;
 	}
 
-	info->irq = bind_virq_to_irq(VIRQ_CONSOLE, 0);
+	info->irq = bind_virq_to_irq(VIRQ_CONSOLE, 0, false);
 	info->vtermno = HVC_COOKIE;
 
 	spin_lock(&xencons_lock);
@@ -299,11 +299,27 @@ static int xen_initial_domain_console_init(void)
 	return 0;
 }
 
+static void xen_console_update_evtchn(struct xencons_info *info)
+{
+	if (xen_hvm_domain()) {
+		uint64_t v;
+		int err;
+
+		err = hvm_get_parameter(HVM_PARAM_CONSOLE_EVTCHN, &v);
+		if (!err && v)
+			info->evtchn = v;
+	} else
+		info->evtchn = xen_start_info->console.domU.evtchn;
+}
+
 void xen_console_resume(void)
 {
 	struct xencons_info *info = vtermno_to_xencons(HVC_COOKIE);
-	if (info != NULL && info->irq)
+	if (info != NULL && info->irq) {
+		if (!xen_initial_domain())
+			xen_console_update_evtchn(info);
 		rebind_evtchn_irq(info->evtchn, info->irq);
+	}
 }
 
 static void xencons_disconnect_backend(struct xencons_info *info)
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index c4343764cc5..bce16e405d5 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -3170,7 +3170,7 @@ static int gsmtty_break_ctl(struct tty_struct *tty, int state)
 	return gsmtty_modem_update(dlci, encode);
 }
 
-static void gsmtty_remove(struct tty_driver *driver, struct tty_struct *tty)
+static void gsmtty_cleanup(struct tty_struct *tty)
 {
 	struct gsm_dlci *dlci = tty->driver_data;
 	struct gsm_mux *gsm = dlci->gsm;
@@ -3178,7 +3178,6 @@ static void gsmtty_remove(struct tty_driver *driver, struct tty_struct *tty)
 	dlci_put(dlci);
 	dlci_put(gsm->dlci[0]);
 	mux_put(gsm);
-	driver->ttys[tty->index] = NULL;
 }
 
 /* Virtual ttys for the demux */
@@ -3199,7 +3198,7 @@ static const struct tty_operations gsmtty_ops = {
 	.tiocmget		= gsmtty_tiocmget,
 	.tiocmset		= gsmtty_tiocmset,
 	.break_ctl		= gsmtty_break_ctl,
-	.remove			= gsmtty_remove,
+	.cleanup		= gsmtty_cleanup,
 };
 
 
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index 2e900a98c3e..e3ebb674a69 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -186,6 +186,17 @@ static int receive_room(struct tty_struct *tty)
 	return left;
 }
 
+static inline int tty_copy_to_user(struct tty_struct *tty,
+					void __user *to,
+					const void *from,
+					unsigned long n)
+{
+	struct n_tty_data *ldata = tty->disc_data;
+
+	tty_audit_add_data(tty, to, n, ldata->icanon);
+	return copy_to_user(to, from, n);
+}
+
 /**
  *	n_tty_set_room	-	receive space
  *	@tty: terminal
@@ -247,8 +258,6 @@ static void n_tty_write_wakeup(struct tty_struct *tty)
 
 static void n_tty_check_throttle(struct tty_struct *tty)
 {
-	if (tty->driver->type == TTY_DRIVER_TYPE_PTY)
-		return;
 	/*
 	 * Check the remaining room for the input canonicalization
 	 * mode.  We don't want to throttle the driver if we're in
@@ -321,7 +330,8 @@ static void n_tty_check_unthrottle(struct tty_struct *tty)
 
 static inline void put_tty_queue(unsigned char c, struct n_tty_data *ldata)
 {
-	*read_buf_addr(ldata, ldata->read_head++) = c;
+	*read_buf_addr(ldata, ldata->read_head) = c;
+	ldata->read_head++;
 }
 
 /**
@@ -1511,23 +1521,6 @@ n_tty_receive_char_lnext(struct tty_struct *tty, unsigned char c, char flag)
 		n_tty_receive_char_flagged(tty, c, flag);
 }
 
-/**
- *	n_tty_receive_buf	-	data receive
- *	@tty: terminal device
- *	@cp: buffer
- *	@fp: flag buffer
- *	@count: characters
- *
- *	Called by the terminal driver when a block of characters has
- *	been received. This function must be called from soft contexts
- *	not from interrupt context. The driver is responsible for making
- *	calls one at a time and in order (or using flush_to_ldisc)
- *
- *	n_tty_receive_buf()/producer path:
- *		claims non-exclusive termios_rwsem
- *		publishes read_head and canon_head
- */
-
 static void
 n_tty_receive_buf_real_raw(struct tty_struct *tty, const unsigned char *cp,
 			   char *fp, int count)
@@ -1683,24 +1676,85 @@ static void __receive_buf(struct tty_struct *tty, const unsigned char *cp,
 	}
 }
 
+/**
+ *	n_tty_receive_buf_common	-	process input
+ *	@tty: device to receive input
+ *	@cp: input chars
+ *	@fp: flags for each char (if NULL, all chars are TTY_NORMAL)
+ *	@count: number of input chars in @cp
+ *
+ *	Called by the terminal driver when a block of characters has
+ *	been received. This function must be called from soft contexts
+ *	not from interrupt context. The driver is responsible for making
+ *	calls one at a time and in order (or using flush_to_ldisc)
+ *
+ *	Returns the # of input chars from @cp which were processed.
+ *
+ *	In canonical mode, the maximum line length is 4096 chars (including
+ *	the line termination char); lines longer than 4096 chars are
+ *	truncated. After 4095 chars, input data is still processed but
+ *	not stored. Overflow processing ensures the tty can always
+ *	receive more input until at least one line can be read.
+ *
+ *	In non-canonical mode, the read buffer will only accept 4095 chars;
+ *	this provides the necessary space for a newline char if the input
+ *	mode is switched to canonical.
+ *
+ *	Note it is possible for the read buffer to _contain_ 4096 chars
+ *	in non-canonical mode: the read buffer could already contain the
+ *	maximum canon line of 4096 chars when the mode is switched to
+ *	non-canonical.
+ *
+ *	n_tty_receive_buf()/producer path:
+ *		claims non-exclusive termios_rwsem
+ *		publishes commit_head or canon_head
+ */
 static int
 n_tty_receive_buf_common(struct tty_struct *tty, const unsigned char *cp,
 			 char *fp, int count, int flow)
 {
 	struct n_tty_data *ldata = tty->disc_data;
-	int room, n, rcvd = 0;
+	int room, n, rcvd = 0, overflow;
 
 	down_read(&tty->termios_rwsem);
 
 	while (1) {
-		room = receive_room(tty);
+		/*
+		 * When PARMRK is set, each input char may take up to 3 chars
+		 * in the read buf; reduce the buffer space avail by 3x
+		 *
+		 * If we are doing input canonicalization, and there are no
+		 * pending newlines, let characters through without limit, so
+		 * that erase characters will be handled.  Other excess
+		 * characters will be beeped.
+		 *
+		 * paired with store in *_copy_from_read_buf() -- guarantees
+		 * the consumer has loaded the data in read_buf up to the new
+		 * read_tail (so this producer will not overwrite unread data)
+		 */
+		size_t tail = ldata->read_tail;
+
+		room = N_TTY_BUF_SIZE - (ldata->read_head - tail);
+		if (I_PARMRK(tty))
+			room = (room + 2) / 3;
+		room--;
+		if (room <= 0) {
+			overflow = ldata->icanon && ldata->canon_head == tail;
+			if (overflow && room < 0)
+				ldata->read_head--;
+			room = overflow;
+			ldata->no_room = flow && !room;
+		} else
+			overflow = 0;
+
 		n = min(count, room);
-		if (!n) {
-			if (flow && !room)
-				ldata->no_room = 1;
+		if (!n)
 			break;
-		}
-		__receive_buf(tty, cp, fp, n);
+
+		/* ignore parity errors if handling overflow */
+		if (!overflow || !fp || *fp != TTY_PARITY)
+			__receive_buf(tty, cp, fp, n);
+
 		cp += n;
 		if (fp)
 			fp += n;
@@ -1709,7 +1763,17 @@ n_tty_receive_buf_common(struct tty_struct *tty, const unsigned char *cp,
 	}
 
 	tty->receive_room = room;
-	n_tty_check_throttle(tty);
+
+	/* Unthrottle if handling overflow on pty */
+	if (tty->driver->type == TTY_DRIVER_TYPE_PTY) {
+		if (overflow) {
+			tty_set_flow_change(tty, TTY_UNTHROTTLE_SAFE);
+			tty_unthrottle_safe(tty);
+			__tty_set_flow_change(tty, 0);
+		}
+	} else
+		n_tty_check_throttle(tty);
+
 	up_read(&tty->termios_rwsem);
 
 	return rcvd;
@@ -2028,12 +2092,12 @@ static int canon_copy_from_read_buf(struct tty_struct *tty,
 		    __func__, eol, found, n, c, size, more);
 
 	if (n > size) {
-		ret = copy_to_user(*b, read_buf_addr(ldata, tail), size);
+		ret = tty_copy_to_user(tty, *b, read_buf_addr(ldata, tail), size);
 		if (ret)
 			return -EFAULT;
-		ret = copy_to_user(*b + size, ldata->read_buf, n - size);
+		ret = tty_copy_to_user(tty, *b + size, ldata->read_buf, n - size);
 	} else
-		ret = copy_to_user(*b, read_buf_addr(ldata, tail), n);
+		ret = tty_copy_to_user(tty, *b, read_buf_addr(ldata, tail), n);
 
 	if (ret)
 		return -EFAULT;
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index 7c4447a5c0f..082304dcbe8 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -210,6 +210,9 @@ static int pty_signal(struct tty_struct *tty, int sig)
 	unsigned long flags;
 	struct pid *pgrp;
 
+	if (sig != SIGINT && sig != SIGQUIT && sig != SIGTSTP)
+		return -EINVAL;
+
 	if (tty->link) {
 		spin_lock_irqsave(&tty->link->ctrl_lock, flags);
 		pgrp = get_pid(tty->link->pgrp);
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index ca5cfdc1459..e5c31eadb0a 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -2088,8 +2088,8 @@ int serial8250_do_startup(struct uart_port *port)
 	/*
 	 * Clear the interrupt registers.
 	 */
-	if (serial_port_in(port, UART_LSR) & UART_LSR_DR)
-		serial_port_in(port, UART_RX);
+	serial_port_in(port, UART_LSR);
+	serial_port_in(port, UART_RX);
 	serial_port_in(port, UART_IIR);
 	serial_port_in(port, UART_MSR);
 
@@ -2250,8 +2250,8 @@ dont_test_tx_en:
 	 * saved flags to avoid getting false values from polling
 	 * routines or the previous session.
 	 */
-	if (serial_port_in(port, UART_LSR) & UART_LSR_DR)
-		serial_port_in(port, UART_RX);
+	serial_port_in(port, UART_LSR);
+	serial_port_in(port, UART_RX);
 	serial_port_in(port, UART_IIR);
 	serial_port_in(port, UART_MSR);
 	up->lsr_saved_flags = 0;
@@ -2344,8 +2344,7 @@ void serial8250_do_shutdown(struct uart_port *port)
 	 * Read data port to reset things, and then unlink from
 	 * the IRQ chain.
 	 */
-	if (serial_port_in(port, UART_LSR) & UART_LSR_DR)
-		serial_port_in(port, UART_RX);
+	serial_port_in(port, UART_RX);
 	serial8250_rpm_put(up);
 
 	del_timer_sync(&up->timer);
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index beea6ca73ee..5c247d7943a 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -111,7 +111,10 @@ static void dw8250_serial_out(struct uart_port *p, int offset, int value)
 			dw8250_force_idle(p);
 			writeb(value, p->membase + (UART_LCR << p->regshift));
 		}
-		dev_err(p->dev, "Couldn't set LCR to %d\n", value);
+		/*
+		 * FIXME: this deadlocks if port->lock is already held
+		 * dev_err(p->dev, "Couldn't set LCR to %d\n", value);
+		 */
 	}
 }
 
@@ -148,7 +151,10 @@ static void dw8250_serial_out32(struct uart_port *p, int offset, int value)
 			dw8250_force_idle(p);
 			writel(value, p->membase + (UART_LCR << p->regshift));
 		}
-		dev_err(p->dev, "Couldn't set LCR to %d\n", value);
+		/*
+		 * FIXME: this deadlocks if port->lock is already held
+		 * dev_err(p->dev, "Couldn't set LCR to %d\n", value);
+		 */
 	}
 }
 
@@ -310,10 +316,20 @@ static int dw8250_probe_of(struct uart_port *p,
 static int dw8250_probe_acpi(struct uart_8250_port *up,
 			     struct dw8250_data *data)
 {
+	const struct acpi_device_id *id;
 	struct uart_port *p = &up->port;
 
 	dw8250_setup_port(up);
 
+	id = acpi_match_device(p->dev->driver->acpi_match_table, p->dev);
+	if (!id)
+		return -ENODEV;
+
+	if (!p->uartclk)
+		if (device_property_read_u32(p->dev, "clock-frequency",
+					     &p->uartclk))
+			return -EINVAL;
+
 	p->iotype = UPIO_MEM32;
 	p->serial_in = dw8250_serial_in32;
 	p->serial_out = dw8250_serial_out32;
@@ -536,6 +552,8 @@ static const struct acpi_device_id dw8250_acpi_match[] = {
 	{ "INT3435", 0 },
 	{ "80860F0A", 0 },
 	{ "8086228A", 0 },
+	{ "APMC0D08", 0},
+	{ "AMD0020", 0 },
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, dw8250_acpi_match);
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index beb9d71cd47..439bd1a5d00 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -69,7 +69,7 @@ static void moan_device(const char *str, struct pci_dev *dev)
 	       "Please send the output of lspci -vv, this\n"
 	       "message (0x%04x,0x%04x,0x%04x,0x%04x), the\n"
 	       "manufacturer and name of serial board or\n"
-	       "modem board to rmk+serial@arm.linux.org.uk.\n",
+	       "modem board to <linux-serial@vger.kernel.org>.\n",
 	       pci_name(dev), str, dev->vendor, dev->device,
 	       dev->subsystem_vendor, dev->subsystem_device);
 }
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index edde3eca055..daaed7c79e4 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -311,8 +311,7 @@ void atmel_config_rs485(struct uart_port *port, struct serial_rs485 *rs485conf)
 	if (rs485conf->flags & SER_RS485_ENABLED) {
 		dev_dbg(port->dev, "Setting UART to RS485\n");
 		atmel_port->tx_done_mask = ATMEL_US_TXEMPTY;
-		if ((rs485conf->delay_rts_after_send) > 0)
-			UART_PUT_TTGR(port, rs485conf->delay_rts_after_send);
+		UART_PUT_TTGR(port, rs485conf->delay_rts_after_send);
 		mode |= ATMEL_US_USMODE_RS485;
 	} else {
 		dev_dbg(port->dev, "Setting UART to RS232\n");
@@ -861,6 +860,7 @@ static int atmel_prepare_tx_dma(struct uart_port *port)
 	config.direction = DMA_MEM_TO_DEV;
 	config.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
 	config.dst_addr = port->mapbase + ATMEL_US_THR;
+	config.dst_maxburst = 1;
 
 	ret = dmaengine_device_control(atmel_port->chan_tx,
 					DMA_SLAVE_CONFIG,
@@ -1025,6 +1025,7 @@ static int atmel_prepare_rx_dma(struct uart_port *port)
 	config.direction = DMA_DEV_TO_MEM;
 	config.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
 	config.src_addr = port->mapbase + ATMEL_US_RHR;
+	config.src_maxburst = 1;
 
 	ret = dmaengine_device_control(atmel_port->chan_rx,
 					DMA_SLAVE_CONFIG,
@@ -2014,9 +2015,7 @@ static void atmel_set_termios(struct uart_port *port, struct ktermios *termios,
 	mode &= ~ATMEL_US_USMODE;
 
 	if (atmel_port->rs485.flags & SER_RS485_ENABLED) {
-		if ((atmel_port->rs485.delay_rts_after_send) > 0)
-			UART_PUT_TTGR(port,
-					atmel_port->rs485.delay_rts_after_send);
+		UART_PUT_TTGR(port, atmel_port->rs485.delay_rts_after_send);
 		mode |= ATMEL_US_USMODE_RS485;
 	}
 
@@ -2577,7 +2576,7 @@ static int atmel_serial_probe(struct platform_device *pdev)
 
 	ret = atmel_init_port(port, pdev);
 	if (ret)
-		goto err;
+		goto err_clear_bit;
 
 	if (!atmel_use_pdc_rx(&port->uart)) {
 		ret = -ENOMEM;
@@ -2626,6 +2625,8 @@ err_alloc_ring:
 		clk_put(port->clk);
 		port->clk = NULL;
 	}
+err_clear_bit:
+	clear_bit(port->uart.line, atmel_ports_in_use);
 err:
 	return ret;
 }
diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index 6dd53af546a..1883478d6a8 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -506,9 +506,6 @@ static inline void lpuart_prepare_rx(struct lpuart_port *sport)
 
 	spin_lock_irqsave(&sport->port.lock, flags);
 
-	init_timer(&sport->lpuart_timer);
-	sport->lpuart_timer.function = lpuart_timer_func;
-	sport->lpuart_timer.data = (unsigned long)sport;
 	sport->lpuart_timer.expires = jiffies + sport->dma_rx_timeout;
 	add_timer(&sport->lpuart_timer);
 
@@ -758,18 +755,18 @@ out:
 static irqreturn_t lpuart_int(int irq, void *dev_id)
 {
 	struct lpuart_port *sport = dev_id;
-	unsigned char sts;
+	unsigned char sts, crdma;
 
 	sts = readb(sport->port.membase + UARTSR1);
+	crdma = readb(sport->port.membase + UARTCR5);
 
-	if (sts & UARTSR1_RDRF) {
+	if (sts & UARTSR1_RDRF && !(crdma & UARTCR5_RDMAS)) {
 		if (sport->lpuart_dma_use)
 			lpuart_prepare_rx(sport);
 		else
 			lpuart_rxint(irq, dev_id);
 	}
-	if (sts & UARTSR1_TDRE &&
-		!(readb(sport->port.membase + UARTCR5) & UARTCR5_TDMAS)) {
+	if (sts & UARTSR1_TDRE && !(crdma & UARTCR5_TDMAS)) {
 		if (sport->lpuart_dma_use)
 			lpuart_pio_tx(sport);
 		else
@@ -913,6 +910,9 @@ static void lpuart_setup_watermark(struct lpuart_port *sport)
 	writeb(val | UARTPFIFO_TXFE | UARTPFIFO_RXFE,
 			sport->port.membase + UARTPFIFO);
 
+	/* explicitly clear RDRF */
+	readb(sport->port.membase + UARTSR1);
+
 	/* flush Tx and Rx FIFO */
 	writeb(UARTCFIFO_TXFLUSH | UARTCFIFO_RXFLUSH,
 			sport->port.membase + UARTCFIFO);
@@ -1098,6 +1098,8 @@ static int lpuart_startup(struct uart_port *port)
 	sport->txfifo_size = 0x1 << (((temp >> UARTPFIFO_TXSIZE_OFF) &
 		UARTPFIFO_FIFOSIZE_MASK) + 1);
 
+	sport->port.fifosize = sport->txfifo_size;
+
 	sport->rxfifo_size = 0x1 << (((temp >> UARTPFIFO_RXSIZE_OFF) &
 		UARTPFIFO_FIFOSIZE_MASK) + 1);
 
@@ -1106,7 +1108,10 @@ static int lpuart_startup(struct uart_port *port)
 		sport->lpuart_dma_use = false;
 	} else {
 		sport->lpuart_dma_use = true;
+		setup_timer(&sport->lpuart_timer, lpuart_timer_func,
+			    (unsigned long)sport);
 		temp = readb(port->membase + UARTCR5);
+		temp &= ~UARTCR5_RDMAS;
 		writeb(temp | UARTCR5_TDMAS, port->membase + UARTCR5);
 	}
 
@@ -1180,6 +1185,8 @@ static void lpuart_shutdown(struct uart_port *port)
 	devm_free_irq(port->dev, port->irq, sport);
 
 	if (sport->lpuart_dma_use) {
+		del_timer_sync(&sport->lpuart_timer);
+
 		lpuart_dma_tx_free(port);
 		lpuart_dma_rx_free(port);
 	}
diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 8f62a3cec23..696d4b5af29 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -590,13 +590,6 @@ static void imx_start_tx(struct uart_port *port)
 		temp &= ~(UCR1_RRDYEN);
 		writel(temp, sport->port.membase + UCR1);
 	}
-	/* Clear any pending ORE flag before enabling interrupt */
-	temp = readl(sport->port.membase + USR2);
-	writel(temp | USR2_ORE, sport->port.membase + USR2);
-
-	temp = readl(sport->port.membase + UCR4);
-	temp |= UCR4_OREN;
-	writel(temp, sport->port.membase + UCR4);
 
 	if (!sport->dma_is_enabled) {
 		temp = readl(sport->port.membase + UCR1);
@@ -771,7 +764,7 @@ static irqreturn_t imx_int(int irq, void *dev_id)
 	if (sts2 & USR2_ORE) {
 		dev_err(sport->port.dev, "Rx FIFO overrun\n");
 		sport->port.icount.overrun++;
-		writel(sts2 | USR2_ORE, sport->port.membase + USR2);
+		writel(USR2_ORE, sport->port.membase + USR2);
 	}
 
 	return IRQ_HANDLED;
@@ -907,6 +900,14 @@ static void dma_rx_callback(void *data)
 
 	status = dmaengine_tx_status(chan, (dma_cookie_t)0, &state);
 	count = RX_BUF_SIZE - state.residue;
+
+	if (readl(sport->port.membase + USR2) & USR2_IDLE) {
+		/* In condition [3] the SDMA counted up too early */
+		count--;
+
+		writel(USR2_IDLE, sport->port.membase + USR2);
+	}
+
 	dev_dbg(sport->port.dev, "We get %d bytes.\n", count);
 
 	if (count) {
@@ -1141,10 +1142,12 @@ static int imx_startup(struct uart_port *port)
 	}
 
 	spin_lock_irqsave(&sport->port.lock, flags);
+
 	/*
 	 * Finally, clear and enable interrupts
 	 */
 	writel(USR1_RTSD, sport->port.membase + USR1);
+	writel(USR2_ORE, sport->port.membase + USR2);
 
 	temp = readl(sport->port.membase + UCR1);
 	temp |= UCR1_RRDYEN | UCR1_RTSDEN | UCR1_UARTEN;
@@ -1156,6 +1159,10 @@ static int imx_startup(struct uart_port *port)
 
 	writel(temp, sport->port.membase + UCR1);
 
+	temp = readl(sport->port.membase + UCR4);
+	temp |= UCR4_OREN;
+	writel(temp, sport->port.membase + UCR4);
+
 	temp = readl(sport->port.membase + UCR2);
 	temp |= (UCR2_RXEN | UCR2_TXEN);
 	if (!sport->have_rtscts)
diff --git a/drivers/tty/serial/men_z135_uart.c b/drivers/tty/serial/men_z135_uart.c
index 30e9e60bc5c..517cd073dc0 100644
--- a/drivers/tty/serial/men_z135_uart.c
+++ b/drivers/tty/serial/men_z135_uart.c
@@ -809,6 +809,7 @@ static void men_z135_remove(struct mcb_device *mdev)
 
 static const struct mcb_device_id men_z135_ids[] = {
 	{ .device = 0x87 },
+	{ }
 };
 MODULE_DEVICE_TABLE(mcb, men_z135_ids);
 
diff --git a/drivers/tty/serial/of_serial.c b/drivers/tty/serial/of_serial.c
index bf355050eab..2e4b545f182 100644
--- a/drivers/tty/serial/of_serial.c
+++ b/drivers/tty/serial/of_serial.c
@@ -262,7 +262,6 @@ static struct of_device_id of_platform_serial_table[] = {
 	{ .compatible = "ibm,qpace-nwp-serial",
 		.data = (void *)PORT_NWPSERIAL, },
 #endif
-	{ .type = "serial",         .data = (void *)PORT_UNKNOWN, },
 	{ /* end of list */ },
 };
 
diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c
index c78f43a481c..587d63bcbd0 100644
--- a/drivers/tty/serial/samsung.c
+++ b/drivers/tty/serial/samsung.c
@@ -559,11 +559,15 @@ static void s3c24xx_serial_pm(struct uart_port *port, unsigned int level,
 			      unsigned int old)
 {
 	struct s3c24xx_uart_port *ourport = to_ourport(port);
+	int timeout = 10000;
 
 	ourport->pm_level = level;
 
 	switch (level) {
 	case 3:
+		while (--timeout && !s3c24xx_serial_txempty_nofifo(port))
+			udelay(100);
+
 		if (!IS_ERR(ourport->baudclk))
 			clk_disable_unprepare(ourport->baudclk);
 
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index eaeb9a02c7f..ec40c5983aa 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -95,6 +95,9 @@ static void __uart_start(struct tty_struct *tty)
 	struct uart_state *state = tty->driver_data;
 	struct uart_port *port = state->uart_port;
 
+	if (port->ops->wake_peer)
+		port->ops->wake_peer(port);
+
 	if (!uart_tx_stopped(port))
 		port->ops->start_tx(port);
 }
@@ -2102,7 +2105,9 @@ uart_report_port(struct uart_driver *drv, struct uart_port *port)
 		break;
 	}
 
-	dev_info(port->dev, "%s%d at %s (irq = %d, base_baud = %d) is a %s\n",
+	printk(KERN_INFO "%s%s%s%d at %s (irq = %d, base_baud = %d) is a %s\n",
+	       port->dev ? dev_name(port->dev) : "",
+	       port->dev ? ": " : "",
 	       drv->dev_name,
 	       drv->tty_driver->name_base + port->line,
 	       address, port->irq, port->uartclk / 16, uart_type(port));
diff --git a/drivers/tty/serial/uartlite.c b/drivers/tty/serial/uartlite.c
index 189f52e3111..a0099a7f60d 100644
--- a/drivers/tty/serial/uartlite.c
+++ b/drivers/tty/serial/uartlite.c
@@ -632,7 +632,8 @@ MODULE_DEVICE_TABLE(of, ulite_of_match);
 
 static int ulite_probe(struct platform_device *pdev)
 {
-	struct resource *res, *res2;
+	struct resource *res;
+	int irq;
 	int id = pdev->id;
 #ifdef CONFIG_OF
 	const __be32 *prop;
@@ -646,11 +647,11 @@ static int ulite_probe(struct platform_device *pdev)
 	if (!res)
 		return -ENODEV;
 
-	res2 = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (!res2)
-		return -ENODEV;
+	irq = platform_get_irq(pdev, 0);
+	if (irq <= 0)
+		return -ENXIO;
 
-	return ulite_assign(&pdev->dev, id, res->start, res2->start);
+	return ulite_assign(&pdev->dev, id, res->start, irq);
 }
 
 static int ulite_remove(struct platform_device *pdev)
diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index 200c1af2141..fabde0e878e 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -1303,9 +1303,9 @@ static SIMPLE_DEV_PM_OPS(cdns_uart_dev_pm_ops, cdns_uart_suspend,
  */
 static int cdns_uart_probe(struct platform_device *pdev)
 {
-	int rc, id;
+	int rc, id, irq;
 	struct uart_port *port;
-	struct resource *res, *res2;
+	struct resource *res;
 	struct cdns_uart *cdns_uart_data;
 
 	cdns_uart_data = devm_kzalloc(&pdev->dev, sizeof(*cdns_uart_data),
@@ -1352,9 +1352,9 @@ static int cdns_uart_probe(struct platform_device *pdev)
 		goto err_out_clk_disable;
 	}
 
-	res2 = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (!res2) {
-		rc = -ENODEV;
+	irq = platform_get_irq(pdev, 0);
+	if (irq <= 0) {
+		rc = -ENXIO;
 		goto err_out_clk_disable;
 	}
 
@@ -1383,7 +1383,7 @@ static int cdns_uart_probe(struct platform_device *pdev)
 		 * and triggers invocation of the config_port() entry point.
 		 */
 		port->mapbase = res->start;
-		port->irq = res2->start;
+		port->irq = irq;
 		port->dev = &pdev->dev;
 		port->uartclk = clk_get_rate(cdns_uart_data->uartclk);
 		port->private_data = cdns_uart_data;
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 0508a1d8e4c..0a0a6305c51 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -975,8 +975,8 @@ EXPORT_SYMBOL(start_tty);
 /* We limit tty time update visibility to every 8 seconds or so. */
 static void tty_update_time(struct timespec *time)
 {
-	unsigned long sec = get_seconds() & ~7;
-	if ((long)(sec - time->tv_sec) > 0)
+	unsigned long sec = get_seconds();
+	if (abs(sec - time->tv_sec) & ~7)
 		time->tv_sec = sec;
 }
 
diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c
index 62380ccf70f..e43b6e559b3 100644
--- a/drivers/tty/tty_ioctl.c
+++ b/drivers/tty/tty_ioctl.c
@@ -217,11 +217,17 @@ void tty_wait_until_sent(struct tty_struct *tty, long timeout)
 #endif
 	if (!timeout)
 		timeout = MAX_SCHEDULE_TIMEOUT;
+
 	if (wait_event_interruptible_timeout(tty->write_wait,
-			!tty_chars_in_buffer(tty), timeout) >= 0) {
-		if (tty->ops->wait_until_sent)
-			tty->ops->wait_until_sent(tty, timeout);
+			!tty_chars_in_buffer(tty), timeout) < 0) {
+		return;
 	}
+
+	if (timeout == MAX_SCHEDULE_TIMEOUT)
+		timeout = 0;
+
+	if (tty->ops->wait_until_sent)
+		tty->ops->wait_until_sent(tty, timeout);
 }
 EXPORT_SYMBOL(tty_wait_until_sent);
 
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index b33b00b386d..53c25bca7d0 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -498,6 +498,7 @@ void invert_screen(struct vc_data *vc, int offset, int count, int viewed)
 #endif
 	if (DO_UPDATE(vc))
 		do_update_region(vc, (unsigned long) p, count);
+	notify_update(vc);
 }
 
 /* used by selection: complement pointer position */
@@ -514,6 +515,7 @@ void complement_pos(struct vc_data *vc, int offset)
 		scr_writew(old, screenpos(vc, old_offset, 1));
 		if (DO_UPDATE(vc))
 			vc->vc_sw->con_putc(vc, old, oldy, oldx);
+		notify_update(vc);
 	}
 
 	old_offset = offset;
@@ -531,8 +533,8 @@ void complement_pos(struct vc_data *vc, int offset)
 			oldy = (offset >> 1) / vc->vc_cols;
 			vc->vc_sw->con_putc(vc, new, oldy, oldx);
 		}
+		notify_update(vc);
 	}
-
 }
 
 static void insert_char(struct vc_data *vc, unsigned int nr)
diff --git a/drivers/usb/chipidea/otg_fsm.c b/drivers/usb/chipidea/otg_fsm.c
index caaabc58021..34a52cd7bfb 100644
--- a/drivers/usb/chipidea/otg_fsm.c
+++ b/drivers/usb/chipidea/otg_fsm.c
@@ -537,7 +537,6 @@ static int ci_otg_start_host(struct otg_fsm *fsm, int on)
 {
 	struct ci_hdrc	*ci = container_of(fsm, struct ci_hdrc, fsm);
 
-	mutex_unlock(&fsm->lock);
 	if (on) {
 		ci_role_stop(ci);
 		ci_role_start(ci, CI_ROLE_HOST);
@@ -546,7 +545,6 @@ static int ci_otg_start_host(struct otg_fsm *fsm, int on)
 		hw_device_reset(ci, USBMODE_CM_DC);
 		ci_role_start(ci, CI_ROLE_GADGET);
 	}
-	mutex_lock(&fsm->lock);
 	return 0;
 }
 
@@ -554,12 +552,10 @@ static int ci_otg_start_gadget(struct otg_fsm *fsm, int on)
 {
 	struct ci_hdrc	*ci = container_of(fsm, struct ci_hdrc, fsm);
 
-	mutex_unlock(&fsm->lock);
 	if (on)
 		usb_gadget_vbus_connect(&ci->gadget);
 	else
 		usb_gadget_vbus_disconnect(&ci->gadget);
-	mutex_lock(&fsm->lock);
 
 	return 0;
 }
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index 0444d3f8971..c42bf8da56d 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -933,6 +933,13 @@ __acquires(hwep->lock)
 	return retval;
 }
 
+static int otg_a_alt_hnp_support(struct ci_hdrc *ci)
+{
+	dev_warn(&ci->gadget.dev,
+		"connect the device to an alternate port if you want HNP\n");
+	return isr_setup_status_phase(ci);
+}
+
 /**
  * isr_setup_packet_handler: setup packet handler
  * @ci: UDC descriptor
@@ -1065,6 +1072,10 @@ __acquires(ci->lock)
 							ci);
 				}
 				break;
+			case USB_DEVICE_A_ALT_HNP_SUPPORT:
+				if (ci_otg_is_fsm_mode(ci))
+					err = otg_a_alt_hnp_support(ci);
+				break;
 			default:
 				goto delegate;
 			}
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 077d58ac3dc..7d8c3d4ede2 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1091,6 +1091,7 @@ static int acm_probe(struct usb_interface *intf,
 	unsigned long quirks;
 	int num_rx_buf;
 	int i;
+	unsigned int elength = 0;
 	int combined_interfaces = 0;
 	struct device *tty_dev;
 	int rv = -ENOMEM;
@@ -1132,13 +1133,22 @@ static int acm_probe(struct usb_interface *intf,
 	}
 
 	while (buflen > 0) {
+		elength = buffer[0];
+		if (!elength) {
+			dev_err(&intf->dev, "skipping garbage byte\n");
+			elength = 1;
+			goto next_desc;
+		}
 		if (buffer[1] != USB_DT_CS_INTERFACE) {
 			dev_err(&intf->dev, "skipping garbage\n");
 			goto next_desc;
 		}
+		elength = buffer[0];
 
 		switch (buffer[2]) {
 		case USB_CDC_UNION_TYPE: /* we've found it */
+			if (elength < sizeof(struct usb_cdc_union_desc))
+				goto next_desc;
 			if (union_header) {
 				dev_err(&intf->dev, "More than one "
 					"union descriptor, skipping ...\n");
@@ -1147,31 +1157,38 @@ static int acm_probe(struct usb_interface *intf,
 			union_header = (struct usb_cdc_union_desc *)buffer;
 			break;
 		case USB_CDC_COUNTRY_TYPE: /* export through sysfs*/
+			if (elength < sizeof(struct usb_cdc_country_functional_desc))
+				goto next_desc;
 			cfd = (struct usb_cdc_country_functional_desc *)buffer;
 			break;
 		case USB_CDC_HEADER_TYPE: /* maybe check version */
 			break; /* for now we ignore it */
 		case USB_CDC_ACM_TYPE:
+			if (elength < 4)
+				goto next_desc;
 			ac_management_function = buffer[3];
 			break;
 		case USB_CDC_CALL_MANAGEMENT_TYPE:
+			if (elength < 5)
+				goto next_desc;
 			call_management_function = buffer[3];
 			call_interface_num = buffer[4];
 			if ((quirks & NOT_A_MODEM) == 0 && (call_management_function & 3) != 3)
 				dev_err(&intf->dev, "This device cannot do calls on its own. It is not a modem.\n");
 			break;
 		default:
-			/* there are LOTS more CDC descriptors that
+			/*
+			 * there are LOTS more CDC descriptors that
 			 * could legitimately be found here.
 			 */
 			dev_dbg(&intf->dev, "Ignoring descriptor: "
-					"type %02x, length %d\n",
-					buffer[2], buffer[0]);
+					"type %02x, length %ud\n",
+					buffer[2], elength);
 			break;
 		}
 next_desc:
-		buflen -= buffer[0];
-		buffer += buffer[0];
+		buflen -= elength;
+		buffer += elength;
 	}
 
 	if (!union_header) {
@@ -1197,10 +1214,11 @@ next_desc:
 	} else {
 		control_interface = usb_ifnum_to_if(usb_dev, union_header->bMasterInterface0);
 		data_interface = usb_ifnum_to_if(usb_dev, (data_interface_num = union_header->bSlaveInterface0));
-		if (!control_interface || !data_interface) {
-			dev_dbg(&intf->dev, "no interfaces\n");
-			return -ENODEV;
-		}
+	}
+
+	if (!control_interface || !data_interface) {
+		dev_dbg(&intf->dev, "no interfaces\n");
+		return -ENODEV;
 	}
 
 	if (data_interface_num != call_interface_num)
@@ -1468,6 +1486,11 @@ skip_countries:
 		goto alloc_fail8;
 	}
 
+	if (quirks & CLEAR_HALT_CONDITIONS) {
+		usb_clear_halt(usb_dev, usb_rcvbulkpipe(usb_dev, epread->bEndpointAddress));
+		usb_clear_halt(usb_dev, usb_sndbulkpipe(usb_dev, epwrite->bEndpointAddress));
+	}
+
 	return 0;
 alloc_fail8:
 	if (acm->country_codes) {
@@ -1475,6 +1498,7 @@ alloc_fail8:
 				&dev_attr_wCountryCodes);
 		device_remove_file(&acm->control->dev,
 				&dev_attr_iCountryCodeRelDate);
+		kfree(acm->country_codes);
 	}
 	device_remove_file(&acm->control->dev, &dev_attr_bmCapabilities);
 alloc_fail7:
@@ -1744,6 +1768,10 @@ static const struct usb_device_id acm_ids[] = {
 	.driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */
 	},
 
+	{ USB_DEVICE(0x2912, 0x0001), /* ATOL FPrint */
+	.driver_info = CLEAR_HALT_CONDITIONS,
+	},
+
 	/* Nokia S60 phones expose two ACM channels. The first is
 	 * a modem and is picked up by the standard AT-command
 	 * information below. The second is 'vendor-specific' but
diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h
index d3251ebd09e..9cca2e7280b 100644
--- a/drivers/usb/class/cdc-acm.h
+++ b/drivers/usb/class/cdc-acm.h
@@ -134,3 +134,4 @@ struct acm {
 #define NO_DATA_INTERFACE		BIT(4)
 #define IGNORE_DEVICE			BIT(5)
 #define QUIRK_CONTROL_LINE_STATE	BIT(6)
+#define CLEAR_HALT_CONDITIONS		BIT(7)
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index a051a7a2b1b..a81f9dd7ee9 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -245,7 +245,7 @@ static void wdm_int_callback(struct urb *urb)
 	case USB_CDC_NOTIFY_RESPONSE_AVAILABLE:
 		dev_dbg(&desc->intf->dev,
 			"NOTIFY_RESPONSE_AVAILABLE received: index %d len %d",
-			dr->wIndex, dr->wLength);
+			le16_to_cpu(dr->wIndex), le16_to_cpu(dr->wLength));
 		break;
 
 	case USB_CDC_NOTIFY_NETWORK_CONNECTION:
@@ -262,7 +262,9 @@ static void wdm_int_callback(struct urb *urb)
 		clear_bit(WDM_POLL_RUNNING, &desc->flags);
 		dev_err(&desc->intf->dev,
 			"unknown notification %d received: index %d len %d\n",
-			dr->bNotificationType, dr->wIndex, dr->wLength);
+			dr->bNotificationType,
+			le16_to_cpu(dr->wIndex),
+			le16_to_cpu(dr->wLength));
 		goto exit;
 	}
 
@@ -408,7 +410,7 @@ static ssize_t wdm_write
 			     USB_RECIP_INTERFACE);
 	req->bRequest = USB_CDC_SEND_ENCAPSULATED_COMMAND;
 	req->wValue = 0;
-	req->wIndex = desc->inum;
+	req->wIndex = desc->inum; /* already converted */
 	req->wLength = cpu_to_le16(count);
 	set_bit(WDM_IN_USE, &desc->flags);
 	desc->outbuf = buf;
@@ -422,7 +424,7 @@ static ssize_t wdm_write
 		rv = usb_translate_errors(rv);
 	} else {
 		dev_dbg(&desc->intf->dev, "Tx URB has been submitted index=%d",
-			req->wIndex);
+			le16_to_cpu(req->wIndex));
 	}
 out:
 	usb_autopm_put_interface(desc->intf);
@@ -820,7 +822,7 @@ static int wdm_create(struct usb_interface *intf, struct usb_endpoint_descriptor
 	desc->irq->bRequestType = (USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE);
 	desc->irq->bRequest = USB_CDC_GET_ENCAPSULATED_RESPONSE;
 	desc->irq->wValue = 0;
-	desc->irq->wIndex = desc->inum;
+	desc->irq->wIndex = desc->inum; /* already converted */
 	desc->irq->wLength = cpu_to_le16(desc->wMaxCommand);
 
 	usb_fill_control_urb(
diff --git a/drivers/usb/common/usb-otg-fsm.c b/drivers/usb/common/usb-otg-fsm.c
index 98e8340a5bb..c812fefe0e5 100644
--- a/drivers/usb/common/usb-otg-fsm.c
+++ b/drivers/usb/common/usb-otg-fsm.c
@@ -150,9 +150,9 @@ static int otg_set_state(struct otg_fsm *fsm, enum usb_otg_state new_state)
 		break;
 	case OTG_STATE_B_PERIPHERAL:
 		otg_chrg_vbus(fsm, 0);
-		otg_loc_conn(fsm, 1);
 		otg_loc_sof(fsm, 0);
 		otg_set_protocol(fsm, PROTO_GADGET);
+		otg_loc_conn(fsm, 1);
 		break;
 	case OTG_STATE_B_WAIT_ACON:
 		otg_chrg_vbus(fsm, 0);
@@ -213,10 +213,10 @@ static int otg_set_state(struct otg_fsm *fsm, enum usb_otg_state new_state)
 
 		break;
 	case OTG_STATE_A_PERIPHERAL:
-		otg_loc_conn(fsm, 1);
 		otg_loc_sof(fsm, 0);
 		otg_set_protocol(fsm, PROTO_GADGET);
 		otg_drv_vbus(fsm, 1);
+		otg_loc_conn(fsm, 1);
 		otg_add_timer(fsm, A_BIDL_ADIS);
 		break;
 	case OTG_STATE_A_WAIT_VFALL:
diff --git a/drivers/usb/core/buffer.c b/drivers/usb/core/buffer.c
index 684ef70dc09..506b969ea7f 100644
--- a/drivers/usb/core/buffer.c
+++ b/drivers/usb/core/buffer.c
@@ -22,17 +22,25 @@
  */
 
 /* FIXME tune these based on pool statistics ... */
-static const size_t	pool_max[HCD_BUFFER_POOLS] = {
-	/* platforms without dma-friendly caches might need to
-	 * prevent cacheline sharing...
-	 */
-	32,
-	128,
-	512,
-	PAGE_SIZE / 2
-	/* bigger --> allocate pages */
+static size_t pool_max[HCD_BUFFER_POOLS] = {
+	32, 128, 512, 2048,
 };
 
+void __init usb_init_pool_max(void)
+{
+	/*
+	 * The pool_max values must never be smaller than
+	 * ARCH_KMALLOC_MINALIGN.
+	 */
+	if (ARCH_KMALLOC_MINALIGN <= 32)
+		;			/* Original value is okay */
+	else if (ARCH_KMALLOC_MINALIGN <= 64)
+		pool_max[0] = 64;
+	else if (ARCH_KMALLOC_MINALIGN <= 128)
+		pool_max[0] = 0;	/* Don't use this pool */
+	else
+		BUILD_BUG();		/* We don't allow this */
+}
 
 /* SETUP primitives */
 
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index 0b59731c302..a85eadff6be 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -501,6 +501,7 @@ static void async_completed(struct urb *urb)
 	as->status = urb->status;
 	signr = as->signr;
 	if (signr) {
+		memset(&sinfo, 0, sizeof(sinfo));
 		sinfo.si_signo = as->signr;
 		sinfo.si_errno = as->status;
 		sinfo.si_code = SI_ASYNCIO;
@@ -512,7 +513,7 @@ static void async_completed(struct urb *urb)
 	snoop(&urb->dev->dev, "urb complete\n");
 	snoop_urb(urb->dev, as->userurb, urb->pipe, urb->actual_length,
 			as->status, COMPLETE, NULL, 0);
-	if ((urb->transfer_flags & URB_DIR_MASK) == USB_DIR_IN)
+	if ((urb->transfer_flags & URB_DIR_MASK) == URB_DIR_IN)
 		snoop_urb_data(urb, urb->actual_length);
 
 	if (as->status < 0 && as->bulk_addr && as->status != -ECONNRESET &&
@@ -1689,7 +1690,7 @@ static struct async *reap_as(struct usb_dev_state *ps)
 	for (;;) {
 		__set_current_state(TASK_INTERRUPTIBLE);
 		as = async_getcompleted(ps);
-		if (as)
+		if (as || !connected(ps))
 			break;
 		if (signal_pending(current))
 			break;
@@ -1712,7 +1713,7 @@ static int proc_reapurb(struct usb_dev_state *ps, void __user *arg)
 	}
 	if (signal_pending(current))
 		return -EINTR;
-	return -EIO;
+	return -ENODEV;
 }
 
 static int proc_reapurbnonblock(struct usb_dev_state *ps, void __user *arg)
@@ -1721,10 +1722,11 @@ static int proc_reapurbnonblock(struct usb_dev_state *ps, void __user *arg)
 	struct async *as;
 
 	as = async_getcompleted(ps);
-	retval = -EAGAIN;
 	if (as) {
 		retval = processcompl(as, (void __user * __user *)arg);
 		free_async(as);
+	} else {
+		retval = (connected(ps) ? -EAGAIN : -ENODEV);
 	}
 	return retval;
 }
@@ -1854,7 +1856,7 @@ static int proc_reapurb_compat(struct usb_dev_state *ps, void __user *arg)
 	}
 	if (signal_pending(current))
 		return -EINTR;
-	return -EIO;
+	return -ENODEV;
 }
 
 static int proc_reapurbnonblock_compat(struct usb_dev_state *ps, void __user *arg)
@@ -1862,11 +1864,12 @@ static int proc_reapurbnonblock_compat(struct usb_dev_state *ps, void __user *ar
 	int retval;
 	struct async *as;
 
-	retval = -EAGAIN;
 	as = async_getcompleted(ps);
 	if (as) {
 		retval = processcompl_compat(as, (void __user * __user *)arg);
 		free_async(as);
+	} else {
+		retval = (connected(ps) ? -EAGAIN : -ENODEV);
 	}
 	return retval;
 }
@@ -2038,7 +2041,8 @@ static int proc_get_capabilities(struct usb_dev_state *ps, void __user *arg)
 {
 	__u32 caps;
 
-	caps = USBDEVFS_CAP_ZERO_PACKET | USBDEVFS_CAP_NO_PACKET_SIZE_LIM;
+	caps = USBDEVFS_CAP_ZERO_PACKET | USBDEVFS_CAP_NO_PACKET_SIZE_LIM |
+			USBDEVFS_CAP_REAP_AFTER_DISCONNECT;
 	if (!ps->dev->bus->no_stop_on_short)
 		caps |= USBDEVFS_CAP_BULK_CONTINUATION;
 	if (ps->dev->bus->sg_tablesize)
@@ -2138,6 +2142,32 @@ static long usbdev_do_ioctl(struct file *file, unsigned int cmd,
 		return -EPERM;
 
 	usb_lock_device(dev);
+
+	/* Reap operations are allowed even after disconnection */
+	switch (cmd) {
+	case USBDEVFS_REAPURB:
+		snoop(&dev->dev, "%s: REAPURB\n", __func__);
+		ret = proc_reapurb(ps, p);
+		goto done;
+
+	case USBDEVFS_REAPURBNDELAY:
+		snoop(&dev->dev, "%s: REAPURBNDELAY\n", __func__);
+		ret = proc_reapurbnonblock(ps, p);
+		goto done;
+
+#ifdef CONFIG_COMPAT
+	case USBDEVFS_REAPURB32:
+		snoop(&dev->dev, "%s: REAPURB32\n", __func__);
+		ret = proc_reapurb_compat(ps, p);
+		goto done;
+
+	case USBDEVFS_REAPURBNDELAY32:
+		snoop(&dev->dev, "%s: REAPURBNDELAY32\n", __func__);
+		ret = proc_reapurbnonblock_compat(ps, p);
+		goto done;
+#endif
+	}
+
 	if (!connected(ps)) {
 		usb_unlock_device(dev);
 		return -ENODEV;
@@ -2231,16 +2261,6 @@ static long usbdev_do_ioctl(struct file *file, unsigned int cmd,
 			inode->i_mtime = CURRENT_TIME;
 		break;
 
-	case USBDEVFS_REAPURB32:
-		snoop(&dev->dev, "%s: REAPURB32\n", __func__);
-		ret = proc_reapurb_compat(ps, p);
-		break;
-
-	case USBDEVFS_REAPURBNDELAY32:
-		snoop(&dev->dev, "%s: REAPURBNDELAY32\n", __func__);
-		ret = proc_reapurbnonblock_compat(ps, p);
-		break;
-
 	case USBDEVFS_IOCTL32:
 		snoop(&dev->dev, "%s: IOCTL32\n", __func__);
 		ret = proc_ioctl_compat(ps, ptr_to_compat(p));
@@ -2252,16 +2272,6 @@ static long usbdev_do_ioctl(struct file *file, unsigned int cmd,
 		ret = proc_unlinkurb(ps, p);
 		break;
 
-	case USBDEVFS_REAPURB:
-		snoop(&dev->dev, "%s: REAPURB\n", __func__);
-		ret = proc_reapurb(ps, p);
-		break;
-
-	case USBDEVFS_REAPURBNDELAY:
-		snoop(&dev->dev, "%s: REAPURBNDELAY\n", __func__);
-		ret = proc_reapurbnonblock(ps, p);
-		break;
-
 	case USBDEVFS_DISCSIGNAL:
 		snoop(&dev->dev, "%s: DISCSIGNAL\n", __func__);
 		ret = proc_disconnectsignal(ps, p);
@@ -2304,6 +2314,8 @@ static long usbdev_do_ioctl(struct file *file, unsigned int cmd,
 		ret = proc_free_streams(ps, p);
 		break;
 	}
+
+ done:
 	usb_unlock_device(dev);
 	if (ret >= 0)
 		inode->i_atime = CURRENT_TIME;
@@ -2371,6 +2383,7 @@ static void usbdev_remove(struct usb_device *udev)
 		wake_up_all(&ps->wait);
 		list_del_init(&ps->list);
 		if (ps->discsignr) {
+			memset(&sinfo, 0, sizeof(sinfo));
 			sinfo.si_signo = ps->discsignr;
 			sinfo.si_errno = EPIPE;
 			sinfo.si_code = SI_ASYNCIO;
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 9bffd26cea0..d7a6d8bc510 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -275,21 +275,6 @@ static int usb_unbind_device(struct device *dev)
 	return 0;
 }
 
-/*
- * Cancel any pending scheduled resets
- *
- * [see usb_queue_reset_device()]
- *
- * Called after unconfiguring / when releasing interfaces. See
- * comments in __usb_queue_reset_device() regarding
- * udev->reset_running.
- */
-static void usb_cancel_queued_reset(struct usb_interface *iface)
-{
-	if (iface->reset_running == 0)
-		cancel_work_sync(&iface->reset_ws);
-}
-
 /* called from driver core with dev locked */
 static int usb_probe_interface(struct device *dev)
 {
@@ -380,7 +365,6 @@ static int usb_probe_interface(struct device *dev)
 	usb_set_intfdata(intf, NULL);
 	intf->needs_remote_wakeup = 0;
 	intf->condition = USB_INTERFACE_UNBOUND;
-	usb_cancel_queued_reset(intf);
 
 	/* If the LPM disable succeeded, balance the ref counts. */
 	if (!lpm_disable_error)
@@ -425,7 +409,6 @@ static int usb_unbind_interface(struct device *dev)
 		usb_disable_interface(udev, intf, false);
 
 	driver->disconnect(intf);
-	usb_cancel_queued_reset(intf);
 
 	/* Free streams */
 	for (i = 0, j = 0; i < intf->cur_altsetting->desc.bNumEndpoints; i++) {
@@ -1801,6 +1784,18 @@ static int autosuspend_check(struct usb_device *udev)
 		dev_dbg(&udev->dev, "remote wakeup needed for autosuspend\n");
 		return -EOPNOTSUPP;
 	}
+
+	/*
+	 * If the device is a direct child of the root hub and the HCD
+	 * doesn't handle wakeup requests, don't allow autosuspend when
+	 * wakeup is needed.
+	 */
+	if (w && udev->parent == udev->bus->root_hub &&
+			bus_to_hcd(udev->bus)->cant_recv_wakeups) {
+		dev_dbg(&udev->dev, "HCD doesn't handle wakeup requests\n");
+		return -EOPNOTSUPP;
+	}
+
 	udev->do_remote_wakeup = w;
 	return 0;
 }
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index a6efb4184f2..0009fc847ee 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1618,6 +1618,7 @@ static int unlink1(struct usb_hcd *hcd, struct urb *urb, int status)
 int usb_hcd_unlink_urb (struct urb *urb, int status)
 {
 	struct usb_hcd		*hcd;
+	struct usb_device	*udev = urb->dev;
 	int			retval = -EIDRM;
 	unsigned long		flags;
 
@@ -1629,20 +1630,19 @@ int usb_hcd_unlink_urb (struct urb *urb, int status)
 	spin_lock_irqsave(&hcd_urb_unlink_lock, flags);
 	if (atomic_read(&urb->use_count) > 0) {
 		retval = 0;
-		usb_get_dev(urb->dev);
+		usb_get_dev(udev);
 	}
 	spin_unlock_irqrestore(&hcd_urb_unlink_lock, flags);
 	if (retval == 0) {
 		hcd = bus_to_hcd(urb->dev->bus);
 		retval = unlink1(hcd, urb, status);
-		usb_put_dev(urb->dev);
+		if (retval == 0)
+			retval = -EINPROGRESS;
+		else if (retval != -EIDRM && retval != -EBUSY)
+			dev_dbg(&udev->dev, "hcd_unlink_urb %p fail %d\n",
+					urb, retval);
+		usb_put_dev(udev);
 	}
-
-	if (retval == 0)
-		retval = -EINPROGRESS;
-	else if (retval != -EIDRM && retval != -EBUSY)
-		dev_dbg(&urb->dev->dev, "hcd_unlink_urb %p fail %d\n",
-				urb, retval);
 	return retval;
 }
 
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index b649fef2e35..2222899c4b6 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -2613,9 +2613,6 @@ static bool use_new_scheme(struct usb_device *udev, int retry)
 	return USE_NEW_SCHEME(retry);
 }
 
-static int hub_port_reset(struct usb_hub *hub, int port1,
-			struct usb_device *udev, unsigned int delay, bool warm);
-
 /* Is a USB 3.0 port in the Inactive or Compliance Mode state?
  * Port worm reset is required to recover
  */
@@ -2703,44 +2700,6 @@ static int hub_port_wait_reset(struct usb_hub *hub, int port1,
 	return 0;
 }
 
-static void hub_port_finish_reset(struct usb_hub *hub, int port1,
-			struct usb_device *udev, int *status)
-{
-	switch (*status) {
-	case 0:
-		/* TRSTRCY = 10 ms; plus some extra */
-		msleep(10 + 40);
-		if (udev) {
-			struct usb_hcd *hcd = bus_to_hcd(udev->bus);
-
-			update_devnum(udev, 0);
-			/* The xHC may think the device is already reset,
-			 * so ignore the status.
-			 */
-			if (hcd->driver->reset_device)
-				hcd->driver->reset_device(hcd, udev);
-		}
-		/* FALL THROUGH */
-	case -ENOTCONN:
-	case -ENODEV:
-		usb_clear_port_feature(hub->hdev,
-				port1, USB_PORT_FEAT_C_RESET);
-		if (hub_is_superspeed(hub->hdev)) {
-			usb_clear_port_feature(hub->hdev, port1,
-					USB_PORT_FEAT_C_BH_PORT_RESET);
-			usb_clear_port_feature(hub->hdev, port1,
-					USB_PORT_FEAT_C_PORT_LINK_STATE);
-			usb_clear_port_feature(hub->hdev, port1,
-					USB_PORT_FEAT_C_CONNECTION);
-		}
-		if (udev)
-			usb_set_device_state(udev, *status
-					? USB_STATE_NOTATTACHED
-					: USB_STATE_DEFAULT);
-		break;
-	}
-}
-
 /* Handle port reset and port warm(BH) reset (for USB3 protocol ports) */
 static int hub_port_reset(struct usb_hub *hub, int port1,
 			struct usb_device *udev, unsigned int delay, bool warm)
@@ -2764,13 +2723,10 @@ static int hub_port_reset(struct usb_hub *hub, int port1,
 		 * If the caller hasn't explicitly requested a warm reset,
 		 * double check and see if one is needed.
 		 */
-		status = hub_port_status(hub, port1,
-					&portstatus, &portchange);
-		if (status < 0)
-			goto done;
-
-		if (hub_port_warm_reset_required(hub, port1, portstatus))
-			warm = true;
+		if (hub_port_status(hub, port1, &portstatus, &portchange) == 0)
+			if (hub_port_warm_reset_required(hub, port1,
+							portstatus))
+				warm = true;
 	}
 	clear_bit(port1, hub->warm_reset_bits);
 
@@ -2796,11 +2752,19 @@ static int hub_port_reset(struct usb_hub *hub, int port1,
 
 		/* Check for disconnect or reset */
 		if (status == 0 || status == -ENOTCONN || status == -ENODEV) {
-			hub_port_finish_reset(hub, port1, udev, &status);
+			usb_clear_port_feature(hub->hdev, port1,
+					USB_PORT_FEAT_C_RESET);
 
 			if (!hub_is_superspeed(hub->hdev))
 				goto done;
 
+			usb_clear_port_feature(hub->hdev, port1,
+					USB_PORT_FEAT_C_BH_PORT_RESET);
+			usb_clear_port_feature(hub->hdev, port1,
+					USB_PORT_FEAT_C_PORT_LINK_STATE);
+			usb_clear_port_feature(hub->hdev, port1,
+					USB_PORT_FEAT_C_CONNECTION);
+
 			/*
 			 * If a USB 3.0 device migrates from reset to an error
 			 * state, re-issue the warm reset.
@@ -2833,6 +2797,26 @@ static int hub_port_reset(struct usb_hub *hub, int port1,
 	dev_err(&port_dev->dev, "Cannot enable. Maybe the USB cable is bad?\n");
 
 done:
+	if (status == 0) {
+		/* TRSTRCY = 10 ms; plus some extra */
+		msleep(10 + 40);
+		if (udev) {
+			struct usb_hcd *hcd = bus_to_hcd(udev->bus);
+
+			update_devnum(udev, 0);
+			/* The xHC may think the device is already reset,
+			 * so ignore the status.
+			 */
+			if (hcd->driver->reset_device)
+				hcd->driver->reset_device(hcd, udev);
+
+			usb_set_device_state(udev, USB_STATE_DEFAULT);
+		}
+	} else {
+		if (udev)
+			usb_set_device_state(udev, USB_STATE_NOTATTACHED);
+	}
+
 	if (!hub_is_superspeed(hub->hdev))
 		up_read(&ehci_cf_port_reset_rwsem);
 
@@ -3394,10 +3378,10 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg)
 	if (status) {
 		dev_dbg(&port_dev->dev, "can't resume, status %d\n", status);
 	} else {
-		/* drive resume for at least 20 msec */
+		/* drive resume for USB_RESUME_TIMEOUT msec */
 		dev_dbg(&udev->dev, "usb %sresume\n",
 				(PMSG_IS_AUTO(msg) ? "auto-" : ""));
-		msleep(25);
+		msleep(USB_RESUME_TIMEOUT);
 
 		/* Virtual root hubs can trigger on GET_PORT_STATUS to
 		 * stop resume signaling.  Then finish the resume
@@ -5591,26 +5575,19 @@ EXPORT_SYMBOL_GPL(usb_reset_device);
  *   possible; depending on how the driver attached to each interface
  *   handles ->pre_reset(), the second reset might happen or not.
  *
- * - If a driver is unbound and it had a pending reset, the reset will
- *   be cancelled.
- *
- * - This function can be called during .probe() or .disconnect()
- *   times. On return from .disconnect(), any pending resets will be
- *   cancelled.
- *
- * There is no no need to lock/unlock the @reset_ws as schedule_work()
- * does its own.
+ * - If the reset is delayed so long that the interface is unbound from
+ *   its driver, the reset will be skipped.
  *
- * NOTE: We don't do any reference count tracking because it is not
- *     needed. The lifecycle of the work_struct is tied to the
- *     usb_interface. Before destroying the interface we cancel the
- *     work_struct, so the fact that work_struct is queued and or
- *     running means the interface (and thus, the device) exist and
- *     are referenced.
+ * - This function can be called during .probe().  It can also be called
+ *   during .disconnect(), but doing so is pointless because the reset
+ *   will not occur.  If you really want to reset the device during
+ *   .disconnect(), call usb_reset_device() directly -- but watch out
+ *   for nested unbinding issues!
  */
 void usb_queue_reset_device(struct usb_interface *iface)
 {
-	schedule_work(&iface->reset_ws);
+	if (schedule_work(&iface->reset_ws))
+		usb_get_intf(iface);
 }
 EXPORT_SYMBOL_GPL(usb_queue_reset_device);
 
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index f7b7713cfb2..f368d2053da 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -1551,6 +1551,7 @@ static void usb_release_interface(struct device *dev)
 			altsetting_to_usb_interface_cache(intf->altsetting);
 
 	kref_put(&intfc->ref, usb_release_interface_cache);
+	usb_put_dev(interface_to_usbdev(intf));
 	kfree(intf);
 }
 
@@ -1626,24 +1627,6 @@ static struct usb_interface_assoc_descriptor *find_iad(struct usb_device *dev,
 
 /*
  * Internal function to queue a device reset
- *
- * This is initialized into the workstruct in 'struct
- * usb_device->reset_ws' that is launched by
- * message.c:usb_set_configuration() when initializing each 'struct
- * usb_interface'.
- *
- * It is safe to get the USB device without reference counts because
- * the life cycle of @iface is bound to the life cycle of @udev. Then,
- * this function will be ran only if @iface is alive (and before
- * freeing it any scheduled instances of it will have been cancelled).
- *
- * We need to set a flag (usb_dev->reset_running) because when we call
- * the reset, the interfaces might be unbound. The current interface
- * cannot try to remove the queued work as it would cause a deadlock
- * (you cannot remove your work from within your executing
- * workqueue). This flag lets it know, so that
- * usb_cancel_queued_reset() doesn't try to do it.
- *
  * See usb_queue_reset_device() for more details
  */
 static void __usb_queue_reset_device(struct work_struct *ws)
@@ -1655,11 +1638,10 @@ static void __usb_queue_reset_device(struct work_struct *ws)
 
 	rc = usb_lock_device_for_reset(udev, iface);
 	if (rc >= 0) {
-		iface->reset_running = 1;
 		usb_reset_device(udev);
-		iface->reset_running = 0;
 		usb_unlock_device(udev);
 	}
+	usb_put_intf(iface);	/* Undo _get_ in usb_queue_reset_device() */
 }
 
 
@@ -1854,6 +1836,7 @@ free_interfaces:
 		dev_set_name(&intf->dev, "%d-%s:%d.%d",
 			dev->bus->busnum, dev->devpath,
 			configuration, alt->desc.bInterfaceNumber);
+		usb_get_dev(dev);
 	}
 	kfree(new_interfaces);
 
diff --git a/drivers/usb/core/otg_whitelist.h b/drivers/usb/core/otg_whitelist.h
index de0c9c9d709..a6315abe7b7 100644
--- a/drivers/usb/core/otg_whitelist.h
+++ b/drivers/usb/core/otg_whitelist.h
@@ -55,6 +55,11 @@ static int is_targeted(struct usb_device *dev)
 	     le16_to_cpu(dev->descriptor.idProduct) == 0xbadd))
 		return 0;
 
+	/* OTG PET device is always targeted (see OTG 2.0 ECN 6.4.2) */
+	if ((le16_to_cpu(dev->descriptor.idVendor) == 0x1a0a &&
+	     le16_to_cpu(dev->descriptor.idProduct) == 0x0200))
+		return 1;
+
 	/* NOTE: can't use usb_match_id() since interface caches
 	 * aren't set up yet. this is cut/paste from that code.
 	 */
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 96fafed92b7..41e510ae8c8 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -103,6 +103,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x04f3, 0x009b), .driver_info =
 			USB_QUIRK_DEVICE_QUALIFIER },
 
+	{ USB_DEVICE(0x04f3, 0x010c), .driver_info =
+			USB_QUIRK_DEVICE_QUALIFIER },
+
 	{ USB_DEVICE(0x04f3, 0x016f), .driver_info =
 			USB_QUIRK_DEVICE_QUALIFIER },
 
@@ -176,6 +179,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x0b05, 0x17e0), .driver_info =
 			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
 
+	/* Protocol and OTG Electrical Test Device */
+	{ USB_DEVICE(0x1a0a, 0x0200), .driver_info =
+			USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL },
+
 	{ }  /* terminating entry must be last */
 };
 
diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c
index 2dd2362198d..29ee9363faa 100644
--- a/drivers/usb/core/usb.c
+++ b/drivers/usb/core/usb.c
@@ -1051,6 +1051,7 @@ static int __init usb_init(void)
 		pr_info("%s: USB support disabled\n", usbcore_name);
 		return 0;
 	}
+	usb_init_pool_max();
 
 	retval = usb_debugfs_init();
 	if (retval)
diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c
index 0a0e6f0ad15..e749631d6a9 100644
--- a/drivers/usb/dwc2/hcd.c
+++ b/drivers/usb/dwc2/hcd.c
@@ -1517,7 +1517,7 @@ static int dwc2_hcd_hub_control(struct dwc2_hsotg *hsotg, u16 typereq,
 			dev_dbg(hsotg->dev,
 				"ClearPortFeature USB_PORT_FEAT_SUSPEND\n");
 			writel(0, hsotg->regs + PCGCTL);
-			usleep_range(20000, 40000);
+			msleep(USB_RESUME_TIMEOUT);
 
 			hprt0 = dwc2_read_hprt0(hsotg);
 			hprt0 |= HPRT0_RES;
diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
index a0aa9f3da44..3eb0f5eace7 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -205,6 +205,18 @@ static void dwc3_omap_write_irq0_set(struct dwc3_omap *omap, u32 value)
 						omap->irq0_offset, value);
 }
 
+static void dwc3_omap_write_irqmisc_clr(struct dwc3_omap *omap, u32 value)
+{
+	dwc3_omap_writel(omap->base, USBOTGSS_IRQENABLE_CLR_MISC +
+						omap->irqmisc_offset, value);
+}
+
+static void dwc3_omap_write_irq0_clr(struct dwc3_omap *omap, u32 value)
+{
+	dwc3_omap_writel(omap->base, USBOTGSS_IRQENABLE_CLR_0 -
+						omap->irq0_offset, value);
+}
+
 static void dwc3_omap_set_mailbox(struct dwc3_omap *omap,
 	enum omap_dwc3_vbus_id_status status)
 {
@@ -345,9 +357,23 @@ static void dwc3_omap_enable_irqs(struct dwc3_omap *omap)
 
 static void dwc3_omap_disable_irqs(struct dwc3_omap *omap)
 {
+	u32			reg;
+
 	/* disable all IRQs */
-	dwc3_omap_write_irqmisc_set(omap, 0x00);
-	dwc3_omap_write_irq0_set(omap, 0x00);
+	reg = USBOTGSS_IRQO_COREIRQ_ST;
+	dwc3_omap_write_irq0_clr(omap, reg);
+
+	reg = (USBOTGSS_IRQMISC_OEVT |
+			USBOTGSS_IRQMISC_DRVVBUS_RISE |
+			USBOTGSS_IRQMISC_CHRGVBUS_RISE |
+			USBOTGSS_IRQMISC_DISCHRGVBUS_RISE |
+			USBOTGSS_IRQMISC_IDPULLUP_RISE |
+			USBOTGSS_IRQMISC_DRVVBUS_FALL |
+			USBOTGSS_IRQMISC_CHRGVBUS_FALL |
+			USBOTGSS_IRQMISC_DISCHRGVBUS_FALL |
+			USBOTGSS_IRQMISC_IDPULLUP_FALL);
+
+	dwc3_omap_write_irqmisc_clr(omap, reg);
 }
 
 static u64 dwc3_omap_dma_mask = DMA_BIT_MASK(32);
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index df38e7ef497..bdc995da342 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -727,6 +727,10 @@ static int dwc3_ep0_std_request(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl)
 		dwc3_trace(trace_dwc3_ep0, "USB_REQ_SET_ISOCH_DELAY\n");
 		ret = dwc3_ep0_set_isoch_delay(dwc, ctrl);
 		break;
+	case USB_REQ_SET_INTERFACE:
+		dev_vdbg(dwc->dev, "USB_REQ_SET_INTERFACE\n");
+		dwc->start_config_issued = false;
+		/* Fall through */
 	default:
 		dwc3_trace(trace_dwc3_ep0, "Forwarding to gadget driver\n");
 		ret = dwc3_ep0_delegate_req(dwc, ctrl);
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 546ea5431b8..d98faf73d6b 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -289,6 +289,8 @@ int dwc3_send_gadget_generic_command(struct dwc3 *dwc, unsigned cmd, u32 param)
 		if (!(reg & DWC3_DGCMD_CMDACT)) {
 			dev_vdbg(dwc->dev, "Command Complete --> %d\n",
 					DWC3_DGCMD_STATUS(reg));
+			if (DWC3_DGCMD_STATUS(reg))
+				return -EINVAL;
 			return 0;
 		}
 
@@ -322,6 +324,8 @@ int dwc3_send_gadget_ep_cmd(struct dwc3 *dwc, unsigned ep,
 		if (!(reg & DWC3_DEPCMD_CMDACT)) {
 			dev_vdbg(dwc->dev, "Command Complete --> %d\n",
 					DWC3_DEPCMD_STATUS(reg));
+			if (DWC3_DEPCMD_STATUS(reg))
+				return -EINVAL;
 			return 0;
 		}
 
@@ -882,8 +886,7 @@ static void dwc3_prepare_trbs(struct dwc3_ep *dep, bool starting)
 
 				if (i == (request->num_mapped_sgs - 1) ||
 						sg_is_last(s)) {
-					if (list_is_last(&req->list,
-							&dep->request_list))
+					if (list_empty(&dep->request_list))
 						last_one = true;
 					chain = false;
 				}
@@ -901,6 +904,9 @@ static void dwc3_prepare_trbs(struct dwc3_ep *dep, bool starting)
 				if (last_one)
 					break;
 			}
+
+			if (last_one)
+				break;
 		} else {
 			dma = req->request.dma;
 			length = req->request.length;
@@ -1897,12 +1903,16 @@ static void dwc3_endpoint_transfer_complete(struct dwc3 *dwc,
 {
 	unsigned		status = 0;
 	int			clean_busy;
+	u32			is_xfer_complete;
+
+	is_xfer_complete = (event->endpoint_event == DWC3_DEPEVT_XFERCOMPLETE);
 
 	if (event->status & DEPEVT_STATUS_BUSERR)
 		status = -ECONNRESET;
 
 	clean_busy = dwc3_cleanup_done_reqs(dwc, dep, event, status);
-	if (clean_busy)
+	if (clean_busy && (is_xfer_complete ||
+				usb_endpoint_xfer_isoc(dep->endpoint.desc)))
 		dep->flags &= ~DWC3_EP_BUSY;
 
 	/*
diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig
index c4880fc0d86..e4115768039 100644
--- a/drivers/usb/gadget/Kconfig
+++ b/drivers/usb/gadget/Kconfig
@@ -183,13 +183,25 @@ config USB_F_FS
 
 config USB_F_UAC1
 	tristate
-
+ 
 config USB_F_UAC2
 	tristate
 
 config USB_F_UVC
 	tristate
 
+config USB_F_MTP
+	tristate
+
+config USB_F_PTP
+        tristate
+
+config USB_F_AUDIO_SRC
+	tristate
+
+config USB_F_ACC
+	tristate
+
 choice
 	tristate "USB Gadget Drivers"
 	default USB_ETH
@@ -362,6 +374,43 @@ config USB_CONFIGFS_F_FS
 	  implemented in kernel space (for instance Ethernet, serial or
 	  mass storage) and other are implemented in user space.
 
+config USB_CONFIGFS_F_MTP
+        boolean "MTP gadget"
+        depends on USB_CONFIGFS
+        select USB_F_MTP
+        help
+          USB gadget MTP support
+
+config USB_CONFIGFS_F_PTP
+        boolean "PTP gadget"
+        depends on USB_CONFIGFS && USB_CONFIGFS_F_MTP
+        select USB_F_PTP
+        help
+          USB gadget PTP support
+
+config USB_CONFIGFS_F_ACC
+	boolean "Accessory gadget"
+	depends on USB_CONFIGFS
+	select USB_F_ACC
+	help
+	  USB gadget Accessory support
+
+config USB_CONFIGFS_F_AUDIO_SRC
+	boolean "Audio Source gadget"
+	depends on USB_CONFIGFS && USB_CONFIGFS_F_ACC
+	depends on SND_PCM
+	select USB_F_AUDIO_SRC
+	help
+	  USB gadget Audio Source support
+
+config USB_CONFIGFS_UEVENT
+	boolean "Uevent notification of Gadget state"
+	depends on USB_CONFIGFS
+	help
+	  Enable uevent notifications to userspace when the gadget
+	  state changes. The gadget can be in any of the following
+	  three states: "CONNECTED/DISCONNECTED/CONFIGURED"
+
 source "drivers/usb/gadget/legacy/Kconfig"
 
 endchoice
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index f6a51fddd5b..815126ae386 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -845,7 +845,7 @@ done:
 }
 EXPORT_SYMBOL_GPL(usb_add_config);
 
-static void remove_config(struct usb_composite_dev *cdev,
+static void unbind_config(struct usb_composite_dev *cdev,
 			      struct usb_configuration *config)
 {
 	while (!list_empty(&config->functions)) {
@@ -860,7 +860,6 @@ static void remove_config(struct usb_composite_dev *cdev,
 			/* may free memory for "f" */
 		}
 	}
-	list_del(&config->list);
 	if (config->unbind) {
 		DBG(cdev, "unbind config '%s'/%p\n", config->label, config);
 		config->unbind(config);
@@ -887,9 +886,11 @@ void usb_remove_config(struct usb_composite_dev *cdev,
 	if (cdev->config == config)
 		reset_config(cdev);
 
+	list_del(&config->list);
+
 	spin_unlock_irqrestore(&cdev->lock, flags);
 
-	remove_config(cdev, config);
+	unbind_config(cdev, config);
 }
 
 /*-------------------------------------------------------------------------*/
@@ -1780,6 +1781,12 @@ void composite_disconnect(struct usb_gadget *gadget)
 	struct usb_composite_dev	*cdev = get_gadget_data(gadget);
 	unsigned long			flags;
 
+	if (cdev == NULL) {
+		WARN(1, "%s: Calling disconnect on a Gadget that is \
+			 not connected\n", __func__);
+		return;
+	}
+
 	/* REVISIT:  should we have config and device level
 	 * disconnect callbacks?
 	 */
@@ -1818,7 +1825,8 @@ static void __composite_unbind(struct usb_gadget *gadget, bool unbind_driver)
 		struct usb_configuration	*c;
 		c = list_first_entry(&cdev->configs,
 				struct usb_configuration, list);
-		remove_config(cdev, c);
+		list_del(&c->list);
+		unbind_config(cdev, c);
 	}
 	if (cdev->driver->unbind && unbind_driver)
 		cdev->driver->unbind(cdev);
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index 34034333f7f..c73103d6215 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -9,6 +9,31 @@
 #include "u_f.h"
 #include "u_os_desc.h"
 
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+#include <linux/platform_device.h>
+#include <linux/kdev_t.h>
+#include <linux/usb/ch9.h>
+
+#ifdef CONFIG_USB_CONFIGFS_F_ACC
+extern int acc_ctrlrequest(struct usb_composite_dev *cdev,
+				const struct usb_ctrlrequest *ctrl);
+void acc_disconnect(void);
+#endif
+static struct class *android_class;
+static struct device *android_device;
+static int index;
+
+struct device *create_function_device(char *name)
+{
+	if (android_device && !IS_ERR(android_device))
+		return device_create(android_class, android_device,
+			MKDEV(0, index++), NULL, name);
+	else
+		return ERR_PTR(-EINVAL);
+}
+EXPORT_SYMBOL_GPL(create_function_device);
+#endif
+
 int check_user_usb_string(const char *name,
 		struct usb_gadget_strings *stringtab_dev)
 {
@@ -63,6 +88,12 @@ struct gadget_info {
 	bool use_os_desc;
 	char b_vendor_code;
 	char qw_sign[OS_STRING_QW_SIGN_LEN];
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+	bool connected;
+	bool sw_connected;
+	struct work_struct work;
+	struct device *dev;
+#endif
 };
 
 struct config_usb_cfg {
@@ -262,7 +293,7 @@ static ssize_t gadget_dev_desc_UDC_store(struct gadget_info *gi,
 
 	mutex_lock(&gi->lock);
 
-	if (!strlen(name)) {
+	if (!strlen(name) || strcmp(name, "none") == 0) {
 		ret = unregister_gadget(gi);
 		if (ret)
 			goto err;
@@ -405,6 +436,11 @@ static int config_usb_cfg_link(
 	}
 
 	f = usb_get_function(fi);
+	if (f == NULL) {
+		/* Are we trying to symlink PTP without MTP function? */
+		ret = -EINVAL; /* Invalid Configuration */
+		goto out;
+	}
 	if (IS_ERR(f)) {
 		ret = PTR_ERR(f);
 		goto out;
@@ -1161,7 +1197,6 @@ static ssize_t interf_grp_compatible_id_store(struct usb_os_desc *desc,
 	if (desc->opts_mutex)
 		mutex_lock(desc->opts_mutex);
 	memcpy(desc->ext_compat_id, page, l);
-	desc->ext_compat_id[l] = '\0';
 
 	if (desc->opts_mutex)
 		mutex_unlock(desc->opts_mutex);
@@ -1192,7 +1227,6 @@ static ssize_t interf_grp_sub_compatible_id_store(struct usb_os_desc *desc,
 	if (desc->opts_mutex)
 		mutex_lock(desc->opts_mutex);
 	memcpy(desc->ext_compat_id + 8, page, l);
-	desc->ext_compat_id[l + 8] = '\0';
 
 	if (desc->opts_mutex)
 		mutex_unlock(desc->opts_mutex);
@@ -1297,6 +1331,7 @@ static void purge_configs_funcs(struct gadget_info *gi)
 			}
 		}
 		c->next_interface_id = 0;
+		memset(c->interface, 0, sizeof(c->interface));
 		c->superspeed = 0;
 		c->highspeed = 0;
 		c->fullspeed = 0;
@@ -1428,6 +1463,60 @@ err_comp_cleanup:
 	return ret;
 }
 
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+static void android_work(struct work_struct *data)
+{
+	struct gadget_info *gi = container_of(data, struct gadget_info, work);
+	struct usb_composite_dev *cdev = &gi->cdev;
+	char *disconnected[2] = { "USB_STATE=DISCONNECTED", NULL };
+	char *connected[2]    = { "USB_STATE=CONNECTED", NULL };
+	char *configured[2]   = { "USB_STATE=CONFIGURED", NULL };
+	/* 0-connected 1-configured 2-disconnected*/
+	bool status[3] = { false, false, false };
+	unsigned long flags;
+	bool uevent_sent = false;
+
+	spin_lock_irqsave(&cdev->lock, flags);
+	if (cdev->config)
+		status[1] = true;
+
+	if (gi->connected != gi->sw_connected) {
+		if (gi->connected)
+			status[0] = true;
+		else
+			status[2] = true;
+		gi->sw_connected = gi->connected;
+	}
+	spin_unlock_irqrestore(&cdev->lock, flags);
+
+	if (status[0]) {
+		kobject_uevent_env(&android_device->kobj,
+					KOBJ_CHANGE, connected);
+		pr_info("%s: sent uevent %s\n", __func__, connected[0]);
+		uevent_sent = true;
+	}
+
+	if (status[1]) {
+		kobject_uevent_env(&android_device->kobj,
+					KOBJ_CHANGE, configured);
+		pr_info("%s: sent uevent %s\n", __func__, configured[0]);
+		uevent_sent = true;
+	}
+
+	if (status[2]) {
+		kobject_uevent_env(&android_device->kobj,
+					KOBJ_CHANGE, disconnected);
+		pr_info("%s: sent uevent %s\n", __func__, disconnected[0]);
+		uevent_sent = true;
+	}
+
+	if (!uevent_sent) {
+		pr_info("%s: did not send uevent (%d %d %p)\n", __func__,
+			gi->connected, gi->sw_connected, cdev->config);
+	}
+}
+#endif
+
 static void configfs_composite_unbind(struct usb_gadget *gadget)
 {
 	struct usb_composite_dev	*cdev;
@@ -1445,14 +1534,78 @@ static void configfs_composite_unbind(struct usb_gadget *gadget)
 	set_gadget_data(gadget, NULL);
 }
 
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+static int android_setup(struct usb_gadget *gadget,
+			const struct usb_ctrlrequest *c)
+{
+	struct usb_composite_dev *cdev = get_gadget_data(gadget);
+	unsigned long flags;
+	struct gadget_info *gi = container_of(cdev, struct gadget_info, cdev);
+	int value = -EOPNOTSUPP;
+	struct usb_function_instance *fi;
+
+	spin_lock_irqsave(&cdev->lock, flags);
+	if (!gi->connected) {
+		gi->connected = 1;
+		schedule_work(&gi->work);
+	}
+	spin_unlock_irqrestore(&cdev->lock, flags);
+	list_for_each_entry(fi, &gi->available_func, cfs_list) {
+		if (fi != NULL && fi->f != NULL && fi->f->setup != NULL) {
+			value = fi->f->setup(fi->f, c);
+			if (value >= 0)
+				break;
+		}
+	}
+
+#ifdef CONFIG_USB_CONFIGFS_F_ACC
+	if (value < 0)
+		value = acc_ctrlrequest(cdev, c);
+#endif
+
+	if (value < 0)
+		value = composite_setup(gadget, c);
+
+	spin_lock_irqsave(&cdev->lock, flags);
+	if (c->bRequest == USB_REQ_SET_CONFIGURATION &&
+						cdev->config) {
+		schedule_work(&gi->work);
+	}
+	spin_unlock_irqrestore(&cdev->lock, flags);
+
+	return value;
+}
+
+static void android_disconnect(struct usb_gadget *gadget)
+{
+	struct usb_composite_dev        *cdev = get_gadget_data(gadget);
+	struct gadget_info *gi = container_of(cdev, struct gadget_info, cdev);
+
+	/* accessory HID support can be active while the
+		accessory function is not actually enabled,
+		so we need to inform it when we are disconnected.
+	*/
+
+#ifdef CONFIG_USB_CONFIGFS_F_ACC
+	acc_disconnect();
+#endif
+	gi->connected = 0;
+	schedule_work(&gi->work);
+	composite_disconnect(gadget);
+}
+#endif
+
 static const struct usb_gadget_driver configfs_driver_template = {
 	.bind           = configfs_composite_bind,
 	.unbind         = configfs_composite_unbind,
-
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+	.setup          = android_setup,
+	.disconnect     = android_disconnect,
+#else
 	.setup          = composite_setup,
 	.reset          = composite_disconnect,
 	.disconnect     = composite_disconnect,
-
+#endif
 	.max_speed	= USB_SPEED_SUPER,
 	.driver = {
 		.owner          = THIS_MODULE,
@@ -1460,16 +1613,55 @@ static const struct usb_gadget_driver configfs_driver_template = {
 	},
 };
 
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+static ssize_t state_show(struct device *pdev, struct device_attribute *attr,
+			char *buf)
+{
+	struct gadget_info *dev = dev_get_drvdata(pdev);
+	struct usb_composite_dev *cdev;
+	char *state = "DISCONNECTED";
+	unsigned long flags;
+
+	if (!dev)
+		goto out;
+
+	cdev = &dev->cdev;
+
+	if (!cdev)
+		goto out;
+
+	spin_lock_irqsave(&cdev->lock, flags);
+	if (cdev->config)
+		state = "CONFIGURED";
+	else if (dev->connected)
+		state = "CONNECTED";
+	spin_unlock_irqrestore(&cdev->lock, flags);
+out:
+	return sprintf(buf, "%s\n", state);
+}
+
+static DEVICE_ATTR(state, S_IRUGO, state_show, NULL);
+
+static struct device_attribute *android_usb_attributes[] = {
+	&dev_attr_state,
+	NULL
+};
+#endif
+
 static struct config_group *gadgets_make(
 		struct config_group *group,
 		const char *name)
 {
 	struct gadget_info *gi;
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+	struct device_attribute **attrs;
+	struct device_attribute *attr;
+	int err;
+#endif
 
 	gi = kzalloc(sizeof(*gi), GFP_KERNEL);
 	if (!gi)
 		return ERR_PTR(-ENOMEM);
-
 	gi->group.default_groups = gi->default_groups;
 	gi->group.default_groups[0] = &gi->functions_group;
 	gi->group.default_groups[1] = &gi->configs_group;
@@ -1505,9 +1697,26 @@ static struct config_group *gadgets_make(
 	gi->composite.gadget_driver.function = kstrdup(name, GFP_KERNEL);
 	gi->composite.name = gi->composite.gadget_driver.function;
 
-	if (!gi->composite.gadget_driver.function)
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+	INIT_WORK(&gi->work, android_work);
+	android_device = device_create(android_class, NULL,
+				MKDEV(0, 0), NULL, "android0");
+	if (IS_ERR(android_device))
 		goto err;
 
+	dev_set_drvdata(android_device, gi);
+
+	attrs = android_usb_attributes;
+	while ((attr = *attrs++)) {
+		err = device_create_file(android_device, attr);
+		if (err)
+			goto err1;
+	}
+#endif
+
+	if (!gi->composite.gadget_driver.function)
+		goto err1;
+
 #ifdef CONFIG_USB_OTG
 	gi->otg.bLength = sizeof(struct usb_otg_descriptor);
 	gi->otg.bDescriptorType = USB_DT_OTG;
@@ -1517,13 +1726,33 @@ static struct config_group *gadgets_make(
 	config_group_init_type_name(&gi->group, name,
 				&gadget_root_type);
 	return &gi->group;
+
+err1:
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+	attrs = android_usb_attributes;
+	while ((attr = *attrs++))
+		device_remove_file(android_device, attr);
+
+	device_destroy(android_device->class,
+				android_device->devt);
 err:
+#endif
 	kfree(gi);
 	return ERR_PTR(-ENOMEM);
 }
 
 static void gadgets_drop(struct config_group *group, struct config_item *item)
 {
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+	struct device_attribute **attrs;
+	struct device_attribute *attr;
+
+	attrs = android_usb_attributes;
+	while ((attr = *attrs++))
+		device_remove_file(android_device, attr);
+	device_destroy(android_device->class, android_device->devt);
+#endif
+
 	config_item_put(item);
 }
 
@@ -1562,6 +1791,13 @@ static int __init gadget_cfs_init(void)
 	config_group_init(&gadget_subsys.su_group);
 
 	ret = configfs_register_subsystem(&gadget_subsys);
+
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+	android_class = class_create(THIS_MODULE, "android_usb");
+	if (IS_ERR(android_class))
+		return PTR_ERR(android_class);
+#endif
+
 	return ret;
 }
 module_init(gadget_cfs_init);
@@ -1569,5 +1805,10 @@ module_init(gadget_cfs_init);
 static void __exit gadget_cfs_exit(void)
 {
 	configfs_unregister_subsystem(&gadget_subsys);
+#ifdef CONFIG_USB_CONFIGFS_UEVENT
+	if (!IS_ERR(android_class))
+		class_destroy(android_class);
+#endif
+
 }
 module_exit(gadget_cfs_exit);
diff --git a/drivers/usb/gadget/function/Makefile b/drivers/usb/gadget/function/Makefile
index 90701aa5a82..cc428c4d2b9 100644
--- a/drivers/usb/gadget/function/Makefile
+++ b/drivers/usb/gadget/function/Makefile
@@ -38,3 +38,13 @@ usb_f_uac2-y			:= f_uac2.o
 obj-$(CONFIG_USB_F_UAC2)	+= usb_f_uac2.o
 usb_f_uvc-y			:= f_uvc.o uvc_queue.o uvc_v4l2.o uvc_video.o
 obj-$(CONFIG_USB_F_UVC)		+= usb_f_uvc.o
+usb_f_mtp-y                     := f_mtp.o
+obj-$(CONFIG_USB_F_MTP)         += usb_f_mtp.o
+usb_f_ptp-y                     := f_ptp.o
+obj-$(CONFIG_USB_F_PTP)         += usb_f_ptp.o
+usb_f_audio_source-y            := f_audio_source.o
+obj-$(CONFIG_USB_F_AUDIO_SRC)   += usb_f_audio_source.o
+usb_f_accessory-y               := f_accessory.o
+obj-$(CONFIG_USB_F_ACC)         += usb_f_accessory.o
+
+
diff --git a/drivers/usb/gadget/function/f_accessory.c b/drivers/usb/gadget/function/f_accessory.c
new file mode 100644
index 00000000000..95a7bbb69fc
--- /dev/null
+++ b/drivers/usb/gadget/function/f_accessory.c
@@ -0,0 +1,1362 @@
+/*
+ * Gadget Function Driver for Android USB accessories
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+/* #define DEBUG */
+/* #define VERBOSE_DEBUG */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/poll.h>
+#include <linux/delay.h>
+#include <linux/wait.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+
+#include <linux/types.h>
+#include <linux/file.h>
+#include <linux/device.h>
+#include <linux/miscdevice.h>
+
+#include <linux/hid.h>
+#include <linux/hiddev.h>
+#include <linux/usb.h>
+#include <linux/usb/ch9.h>
+#include <linux/usb/f_accessory.h>
+
+#include <linux/configfs.h>
+#include <linux/usb/composite.h>
+
+#define MAX_INST_NAME_LEN        40
+#define BULK_BUFFER_SIZE    16384
+#define ACC_STRING_SIZE     256
+
+#define PROTOCOL_VERSION    2
+
+/* String IDs */
+#define INTERFACE_STRING_INDEX	0
+
+/* number of tx and rx requests to allocate */
+#define TX_REQ_MAX 4
+#define RX_REQ_MAX 2
+
+struct acc_hid_dev {
+	struct list_head	list;
+	struct hid_device *hid;
+	struct acc_dev *dev;
+	/* accessory defined ID */
+	int id;
+	/* HID report descriptor */
+	u8 *report_desc;
+	/* length of HID report descriptor */
+	int report_desc_len;
+	/* number of bytes of report_desc we have received so far */
+	int report_desc_offset;
+};
+
+struct acc_dev {
+	struct usb_function function;
+	struct usb_composite_dev *cdev;
+	spinlock_t lock;
+
+	struct usb_ep *ep_in;
+	struct usb_ep *ep_out;
+
+	/* set to 1 when we connect */
+	int online:1;
+	/* Set to 1 when we disconnect.
+	 * Not cleared until our file is closed.
+	 */
+	int disconnected:1;
+
+	/* strings sent by the host */
+	char manufacturer[ACC_STRING_SIZE];
+	char model[ACC_STRING_SIZE];
+	char description[ACC_STRING_SIZE];
+	char version[ACC_STRING_SIZE];
+	char uri[ACC_STRING_SIZE];
+	char serial[ACC_STRING_SIZE];
+
+	/* for acc_complete_set_string */
+	int string_index;
+
+	/* set to 1 if we have a pending start request */
+	int start_requested;
+
+	int audio_mode;
+
+	/* synchronize access to our device file */
+	atomic_t open_excl;
+
+	struct list_head tx_idle;
+
+	wait_queue_head_t read_wq;
+	wait_queue_head_t write_wq;
+	struct usb_request *rx_req[RX_REQ_MAX];
+	int rx_done;
+
+	/* delayed work for handling ACCESSORY_START */
+	struct delayed_work start_work;
+
+	/* worker for registering and unregistering hid devices */
+	struct work_struct hid_work;
+
+	/* list of active HID devices */
+	struct list_head	hid_list;
+
+	/* list of new HID devices to register */
+	struct list_head	new_hid_list;
+
+	/* list of dead HID devices to unregister */
+	struct list_head	dead_hid_list;
+};
+
+static struct usb_interface_descriptor acc_interface_desc = {
+	.bLength                = USB_DT_INTERFACE_SIZE,
+	.bDescriptorType        = USB_DT_INTERFACE,
+	.bInterfaceNumber       = 0,
+	.bNumEndpoints          = 2,
+	.bInterfaceClass        = USB_CLASS_VENDOR_SPEC,
+	.bInterfaceSubClass     = USB_SUBCLASS_VENDOR_SPEC,
+	.bInterfaceProtocol     = 0,
+};
+
+static struct usb_endpoint_descriptor acc_highspeed_in_desc = {
+	.bLength                = USB_DT_ENDPOINT_SIZE,
+	.bDescriptorType        = USB_DT_ENDPOINT,
+	.bEndpointAddress       = USB_DIR_IN,
+	.bmAttributes           = USB_ENDPOINT_XFER_BULK,
+	.wMaxPacketSize         = __constant_cpu_to_le16(512),
+};
+
+static struct usb_endpoint_descriptor acc_highspeed_out_desc = {
+	.bLength                = USB_DT_ENDPOINT_SIZE,
+	.bDescriptorType        = USB_DT_ENDPOINT,
+	.bEndpointAddress       = USB_DIR_OUT,
+	.bmAttributes           = USB_ENDPOINT_XFER_BULK,
+	.wMaxPacketSize         = __constant_cpu_to_le16(512),
+};
+
+static struct usb_endpoint_descriptor acc_fullspeed_in_desc = {
+	.bLength                = USB_DT_ENDPOINT_SIZE,
+	.bDescriptorType        = USB_DT_ENDPOINT,
+	.bEndpointAddress       = USB_DIR_IN,
+	.bmAttributes           = USB_ENDPOINT_XFER_BULK,
+};
+
+static struct usb_endpoint_descriptor acc_fullspeed_out_desc = {
+	.bLength                = USB_DT_ENDPOINT_SIZE,
+	.bDescriptorType        = USB_DT_ENDPOINT,
+	.bEndpointAddress       = USB_DIR_OUT,
+	.bmAttributes           = USB_ENDPOINT_XFER_BULK,
+};
+
+static struct usb_descriptor_header *fs_acc_descs[] = {
+	(struct usb_descriptor_header *) &acc_interface_desc,
+	(struct usb_descriptor_header *) &acc_fullspeed_in_desc,
+	(struct usb_descriptor_header *) &acc_fullspeed_out_desc,
+	NULL,
+};
+
+static struct usb_descriptor_header *hs_acc_descs[] = {
+	(struct usb_descriptor_header *) &acc_interface_desc,
+	(struct usb_descriptor_header *) &acc_highspeed_in_desc,
+	(struct usb_descriptor_header *) &acc_highspeed_out_desc,
+	NULL,
+};
+
+static struct usb_string acc_string_defs[] = {
+	[INTERFACE_STRING_INDEX].s	= "Android Accessory Interface",
+	{  },	/* end of list */
+};
+
+static struct usb_gadget_strings acc_string_table = {
+	.language		= 0x0409,	/* en-US */
+	.strings		= acc_string_defs,
+};
+
+static struct usb_gadget_strings *acc_strings[] = {
+	&acc_string_table,
+	NULL,
+};
+
+/* temporary variable used between acc_open() and acc_gadget_bind() */
+static struct acc_dev *_acc_dev;
+
+struct acc_instance {
+	struct usb_function_instance func_inst;
+	const char *name;
+};
+
+static inline struct acc_dev *func_to_dev(struct usb_function *f)
+{
+	return container_of(f, struct acc_dev, function);
+}
+
+static struct usb_request *acc_request_new(struct usb_ep *ep, int buffer_size)
+{
+	struct usb_request *req = usb_ep_alloc_request(ep, GFP_KERNEL);
+	if (!req)
+		return NULL;
+
+	/* now allocate buffers for the requests */
+	req->buf = kmalloc(buffer_size, GFP_KERNEL);
+	if (!req->buf) {
+		usb_ep_free_request(ep, req);
+		return NULL;
+	}
+
+	return req;
+}
+
+static void acc_request_free(struct usb_request *req, struct usb_ep *ep)
+{
+	if (req) {
+		kfree(req->buf);
+		usb_ep_free_request(ep, req);
+	}
+}
+
+/* add a request to the tail of a list */
+static void req_put(struct acc_dev *dev, struct list_head *head,
+		struct usb_request *req)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->lock, flags);
+	list_add_tail(&req->list, head);
+	spin_unlock_irqrestore(&dev->lock, flags);
+}
+
+/* remove a request from the head of a list */
+static struct usb_request *req_get(struct acc_dev *dev, struct list_head *head)
+{
+	unsigned long flags;
+	struct usb_request *req;
+
+	spin_lock_irqsave(&dev->lock, flags);
+	if (list_empty(head)) {
+		req = 0;
+	} else {
+		req = list_first_entry(head, struct usb_request, list);
+		list_del(&req->list);
+	}
+	spin_unlock_irqrestore(&dev->lock, flags);
+	return req;
+}
+
+static void acc_set_disconnected(struct acc_dev *dev)
+{
+	dev->online = 0;
+	dev->disconnected = 1;
+}
+
+static void acc_complete_in(struct usb_ep *ep, struct usb_request *req)
+{
+	struct acc_dev *dev = _acc_dev;
+
+	if (req->status == -ESHUTDOWN) {
+		pr_debug("acc_complete_in set disconnected");
+		acc_set_disconnected(dev);
+	}
+
+	req_put(dev, &dev->tx_idle, req);
+
+	wake_up(&dev->write_wq);
+}
+
+static void acc_complete_out(struct usb_ep *ep, struct usb_request *req)
+{
+	struct acc_dev *dev = _acc_dev;
+
+	dev->rx_done = 1;
+	if (req->status == -ESHUTDOWN) {
+		pr_debug("acc_complete_out set disconnected");
+		acc_set_disconnected(dev);
+	}
+
+	wake_up(&dev->read_wq);
+}
+
+static void acc_complete_set_string(struct usb_ep *ep, struct usb_request *req)
+{
+	struct acc_dev	*dev = ep->driver_data;
+	char *string_dest = NULL;
+	int length = req->actual;
+
+	if (req->status != 0) {
+		pr_err("acc_complete_set_string, err %d\n", req->status);
+		return;
+	}
+
+	switch (dev->string_index) {
+	case ACCESSORY_STRING_MANUFACTURER:
+		string_dest = dev->manufacturer;
+		break;
+	case ACCESSORY_STRING_MODEL:
+		string_dest = dev->model;
+		break;
+	case ACCESSORY_STRING_DESCRIPTION:
+		string_dest = dev->description;
+		break;
+	case ACCESSORY_STRING_VERSION:
+		string_dest = dev->version;
+		break;
+	case ACCESSORY_STRING_URI:
+		string_dest = dev->uri;
+		break;
+	case ACCESSORY_STRING_SERIAL:
+		string_dest = dev->serial;
+		break;
+	}
+	if (string_dest) {
+		unsigned long flags;
+
+		if (length >= ACC_STRING_SIZE)
+			length = ACC_STRING_SIZE - 1;
+
+		spin_lock_irqsave(&dev->lock, flags);
+		memcpy(string_dest, req->buf, length);
+		/* ensure zero termination */
+		string_dest[length] = 0;
+		spin_unlock_irqrestore(&dev->lock, flags);
+	} else {
+		pr_err("unknown accessory string index %d\n",
+			dev->string_index);
+	}
+}
+
+static void acc_complete_set_hid_report_desc(struct usb_ep *ep,
+		struct usb_request *req)
+{
+	struct acc_hid_dev *hid = req->context;
+	struct acc_dev *dev = hid->dev;
+	int length = req->actual;
+
+	if (req->status != 0) {
+		pr_err("acc_complete_set_hid_report_desc, err %d\n",
+			req->status);
+		return;
+	}
+
+	memcpy(hid->report_desc + hid->report_desc_offset, req->buf, length);
+	hid->report_desc_offset += length;
+	if (hid->report_desc_offset == hid->report_desc_len) {
+		/* After we have received the entire report descriptor
+		 * we schedule work to initialize the HID device
+		 */
+		schedule_work(&dev->hid_work);
+	}
+}
+
+static void acc_complete_send_hid_event(struct usb_ep *ep,
+		struct usb_request *req)
+{
+	struct acc_hid_dev *hid = req->context;
+	int length = req->actual;
+
+	if (req->status != 0) {
+		pr_err("acc_complete_send_hid_event, err %d\n", req->status);
+		return;
+	}
+
+	hid_report_raw_event(hid->hid, HID_INPUT_REPORT, req->buf, length, 1);
+}
+
+static int acc_hid_parse(struct hid_device *hid)
+{
+	struct acc_hid_dev *hdev = hid->driver_data;
+
+	hid_parse_report(hid, hdev->report_desc, hdev->report_desc_len);
+	return 0;
+}
+
+static int acc_hid_start(struct hid_device *hid)
+{
+	return 0;
+}
+
+static void acc_hid_stop(struct hid_device *hid)
+{
+}
+
+static int acc_hid_open(struct hid_device *hid)
+{
+	return 0;
+}
+
+static void acc_hid_close(struct hid_device *hid)
+{
+}
+
+static struct hid_ll_driver acc_hid_ll_driver = {
+	.parse = acc_hid_parse,
+	.start = acc_hid_start,
+	.stop = acc_hid_stop,
+	.open = acc_hid_open,
+	.close = acc_hid_close,
+};
+
+static struct acc_hid_dev *acc_hid_new(struct acc_dev *dev,
+		int id, int desc_len)
+{
+	struct acc_hid_dev *hdev;
+
+	hdev = kzalloc(sizeof(*hdev), GFP_ATOMIC);
+	if (!hdev)
+		return NULL;
+	hdev->report_desc = kzalloc(desc_len, GFP_ATOMIC);
+	if (!hdev->report_desc) {
+		kfree(hdev);
+		return NULL;
+	}
+	hdev->dev = dev;
+	hdev->id = id;
+	hdev->report_desc_len = desc_len;
+
+	return hdev;
+}
+
+static struct acc_hid_dev *acc_hid_get(struct list_head *list, int id)
+{
+	struct acc_hid_dev *hid;
+
+	list_for_each_entry(hid, list, list) {
+		if (hid->id == id)
+			return hid;
+	}
+	return NULL;
+}
+
+static int acc_register_hid(struct acc_dev *dev, int id, int desc_length)
+{
+	struct acc_hid_dev *hid;
+	unsigned long flags;
+
+	/* report descriptor length must be > 0 */
+	if (desc_length <= 0)
+		return -EINVAL;
+
+	spin_lock_irqsave(&dev->lock, flags);
+	/* replace HID if one already exists with this ID */
+	hid = acc_hid_get(&dev->hid_list, id);
+	if (!hid)
+		hid = acc_hid_get(&dev->new_hid_list, id);
+	if (hid)
+		list_move(&hid->list, &dev->dead_hid_list);
+
+	hid = acc_hid_new(dev, id, desc_length);
+	if (!hid) {
+		spin_unlock_irqrestore(&dev->lock, flags);
+		return -ENOMEM;
+	}
+
+	list_add(&hid->list, &dev->new_hid_list);
+	spin_unlock_irqrestore(&dev->lock, flags);
+
+	/* schedule work to register the HID device */
+	schedule_work(&dev->hid_work);
+	return 0;
+}
+
+static int acc_unregister_hid(struct acc_dev *dev, int id)
+{
+	struct acc_hid_dev *hid;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->lock, flags);
+	hid = acc_hid_get(&dev->hid_list, id);
+	if (!hid)
+		hid = acc_hid_get(&dev->new_hid_list, id);
+	if (!hid) {
+		spin_unlock_irqrestore(&dev->lock, flags);
+		return -EINVAL;
+	}
+
+	list_move(&hid->list, &dev->dead_hid_list);
+	spin_unlock_irqrestore(&dev->lock, flags);
+
+	schedule_work(&dev->hid_work);
+	return 0;
+}
+
+static int create_bulk_endpoints(struct acc_dev *dev,
+				struct usb_endpoint_descriptor *in_desc,
+				struct usb_endpoint_descriptor *out_desc)
+{
+	struct usb_composite_dev *cdev = dev->cdev;
+	struct usb_request *req;
+	struct usb_ep *ep;
+	int i;
+
+	DBG(cdev, "create_bulk_endpoints dev: %p\n", dev);
+
+	ep = usb_ep_autoconfig(cdev->gadget, in_desc);
+	if (!ep) {
+		DBG(cdev, "usb_ep_autoconfig for ep_in failed\n");
+		return -ENODEV;
+	}
+	DBG(cdev, "usb_ep_autoconfig for ep_in got %s\n", ep->name);
+	ep->driver_data = dev;		/* claim the endpoint */
+	dev->ep_in = ep;
+
+	ep = usb_ep_autoconfig(cdev->gadget, out_desc);
+	if (!ep) {
+		DBG(cdev, "usb_ep_autoconfig for ep_out failed\n");
+		return -ENODEV;
+	}
+	DBG(cdev, "usb_ep_autoconfig for ep_out got %s\n", ep->name);
+	ep->driver_data = dev;		/* claim the endpoint */
+	dev->ep_out = ep;
+
+	ep = usb_ep_autoconfig(cdev->gadget, out_desc);
+	if (!ep) {
+		DBG(cdev, "usb_ep_autoconfig for ep_out failed\n");
+		return -ENODEV;
+	}
+	DBG(cdev, "usb_ep_autoconfig for ep_out got %s\n", ep->name);
+	ep->driver_data = dev;		/* claim the endpoint */
+	dev->ep_out = ep;
+
+	/* now allocate requests for our endpoints */
+	for (i = 0; i < TX_REQ_MAX; i++) {
+		req = acc_request_new(dev->ep_in, BULK_BUFFER_SIZE);
+		if (!req)
+			goto fail;
+		req->complete = acc_complete_in;
+		req_put(dev, &dev->tx_idle, req);
+	}
+	for (i = 0; i < RX_REQ_MAX; i++) {
+		req = acc_request_new(dev->ep_out, BULK_BUFFER_SIZE);
+		if (!req)
+			goto fail;
+		req->complete = acc_complete_out;
+		dev->rx_req[i] = req;
+	}
+
+	return 0;
+
+fail:
+	pr_err("acc_bind() could not allocate requests\n");
+	while ((req = req_get(dev, &dev->tx_idle)))
+		acc_request_free(req, dev->ep_in);
+	for (i = 0; i < RX_REQ_MAX; i++)
+		acc_request_free(dev->rx_req[i], dev->ep_out);
+	return -1;
+}
+
+static ssize_t acc_read(struct file *fp, char __user *buf,
+	size_t count, loff_t *pos)
+{
+	struct acc_dev *dev = fp->private_data;
+	struct usb_request *req;
+	ssize_t r = count;
+	unsigned xfer;
+	int ret = 0;
+
+	pr_debug("acc_read(%zu)\n", count);
+
+	if (dev->disconnected) {
+		pr_debug("acc_read disconnected");
+		return -ENODEV;
+	}
+
+	if (count > BULK_BUFFER_SIZE)
+		count = BULK_BUFFER_SIZE;
+
+	/* we will block until we're online */
+	pr_debug("acc_read: waiting for online\n");
+	ret = wait_event_interruptible(dev->read_wq, dev->online);
+	if (ret < 0) {
+		r = ret;
+		goto done;
+	}
+
+	if (dev->rx_done) {
+		// last req cancelled. try to get it.
+		req = dev->rx_req[0];
+		goto copy_data;
+	}
+
+requeue_req:
+	/* queue a request */
+	req = dev->rx_req[0];
+	req->length = count;
+	dev->rx_done = 0;
+	ret = usb_ep_queue(dev->ep_out, req, GFP_KERNEL);
+	if (ret < 0) {
+		r = -EIO;
+		goto done;
+	} else {
+		pr_debug("rx %p queue\n", req);
+	}
+
+	/* wait for a request to complete */
+	ret = wait_event_interruptible(dev->read_wq, dev->rx_done);
+	if (ret < 0) {
+		r = ret;
+		ret = usb_ep_dequeue(dev->ep_out, req);
+		if (ret != 0) {
+			// cancel failed. There can be a data already received.
+			// it will be retrieved in the next read.
+			pr_debug("acc_read: cancelling failed %d", ret);
+		}
+		goto done;
+	}
+
+copy_data:
+	dev->rx_done = 0;
+	if (dev->online) {
+		/* If we got a 0-len packet, throw it back and try again. */
+		if (req->actual == 0)
+			goto requeue_req;
+
+		pr_debug("rx %p %u\n", req, req->actual);
+		xfer = (req->actual < count) ? req->actual : count;
+		r = xfer;
+		if (copy_to_user(buf, req->buf, xfer))
+			r = -EFAULT;
+	} else
+		r = -EIO;
+
+done:
+	pr_debug("acc_read returning %zd\n", r);
+	return r;
+}
+
+static ssize_t acc_write(struct file *fp, const char __user *buf,
+	size_t count, loff_t *pos)
+{
+	struct acc_dev *dev = fp->private_data;
+	struct usb_request *req = 0;
+	ssize_t r = count;
+	unsigned xfer;
+	int ret;
+
+	pr_debug("acc_write(%zu)\n", count);
+
+	if (!dev->online || dev->disconnected) {
+		pr_debug("acc_write disconnected or not online");
+		return -ENODEV;
+	}
+
+	while (count > 0) {
+		if (!dev->online) {
+			pr_debug("acc_write dev->error\n");
+			r = -EIO;
+			break;
+		}
+
+		/* get an idle tx request to use */
+		req = 0;
+		ret = wait_event_interruptible(dev->write_wq,
+			((req = req_get(dev, &dev->tx_idle)) || !dev->online));
+		if (!req) {
+			r = ret;
+			break;
+		}
+
+		if (count > BULK_BUFFER_SIZE) {
+			xfer = BULK_BUFFER_SIZE;
+			/* ZLP, They will be more TX requests so not yet. */
+			req->zero = 0;
+		} else {
+			xfer = count;
+			/* If the data length is a multple of the
+			 * maxpacket size then send a zero length packet(ZLP).
+			*/
+			req->zero = ((xfer % dev->ep_in->maxpacket) == 0);
+		}
+		if (copy_from_user(req->buf, buf, xfer)) {
+			r = -EFAULT;
+			break;
+		}
+
+		req->length = xfer;
+		ret = usb_ep_queue(dev->ep_in, req, GFP_KERNEL);
+		if (ret < 0) {
+			pr_debug("acc_write: xfer error %d\n", ret);
+			r = -EIO;
+			break;
+		}
+
+		buf += xfer;
+		count -= xfer;
+
+		/* zero this so we don't try to free it on error exit */
+		req = 0;
+	}
+
+	if (req)
+		req_put(dev, &dev->tx_idle, req);
+
+	pr_debug("acc_write returning %zd\n", r);
+	return r;
+}
+
+static long acc_ioctl(struct file *fp, unsigned code, unsigned long value)
+{
+	struct acc_dev *dev = fp->private_data;
+	char *src = NULL;
+	int ret;
+
+	switch (code) {
+	case ACCESSORY_GET_STRING_MANUFACTURER:
+		src = dev->manufacturer;
+		break;
+	case ACCESSORY_GET_STRING_MODEL:
+		src = dev->model;
+		break;
+	case ACCESSORY_GET_STRING_DESCRIPTION:
+		src = dev->description;
+		break;
+	case ACCESSORY_GET_STRING_VERSION:
+		src = dev->version;
+		break;
+	case ACCESSORY_GET_STRING_URI:
+		src = dev->uri;
+		break;
+	case ACCESSORY_GET_STRING_SERIAL:
+		src = dev->serial;
+		break;
+	case ACCESSORY_IS_START_REQUESTED:
+		return dev->start_requested;
+	case ACCESSORY_GET_AUDIO_MODE:
+		return dev->audio_mode;
+	}
+	if (!src)
+		return -EINVAL;
+
+	ret = strlen(src) + 1;
+	if (copy_to_user((void __user *)value, src, ret))
+		ret = -EFAULT;
+	return ret;
+}
+
+static int acc_open(struct inode *ip, struct file *fp)
+{
+	printk(KERN_INFO "acc_open\n");
+	if (atomic_xchg(&_acc_dev->open_excl, 1))
+		return -EBUSY;
+
+	_acc_dev->disconnected = 0;
+	fp->private_data = _acc_dev;
+	return 0;
+}
+
+static int acc_release(struct inode *ip, struct file *fp)
+{
+	printk(KERN_INFO "acc_release\n");
+
+	WARN_ON(!atomic_xchg(&_acc_dev->open_excl, 0));
+	_acc_dev->disconnected = 0;
+	return 0;
+}
+
+/* file operations for /dev/usb_accessory */
+static const struct file_operations acc_fops = {
+	.owner = THIS_MODULE,
+	.read = acc_read,
+	.write = acc_write,
+	.unlocked_ioctl = acc_ioctl,
+	.open = acc_open,
+	.release = acc_release,
+};
+
+static int acc_hid_probe(struct hid_device *hdev,
+		const struct hid_device_id *id)
+{
+	int ret;
+
+	ret = hid_parse(hdev);
+	if (ret)
+		return ret;
+	return hid_hw_start(hdev, HID_CONNECT_DEFAULT);
+}
+
+static struct miscdevice acc_device = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "usb_accessory",
+	.fops = &acc_fops,
+};
+
+static const struct hid_device_id acc_hid_table[] = {
+	{ HID_USB_DEVICE(HID_ANY_ID, HID_ANY_ID) },
+	{ }
+};
+
+static struct hid_driver acc_hid_driver = {
+	.name = "USB accessory",
+	.id_table = acc_hid_table,
+	.probe = acc_hid_probe,
+};
+
+int acc_ctrlrequest(struct usb_composite_dev *cdev,
+				const struct usb_ctrlrequest *ctrl)
+{
+	struct acc_dev	*dev = _acc_dev;
+	int	value = -EOPNOTSUPP;
+	struct acc_hid_dev *hid;
+	int offset;
+	u8 b_requestType = ctrl->bRequestType;
+	u8 b_request = ctrl->bRequest;
+	u16	w_index = le16_to_cpu(ctrl->wIndex);
+	u16	w_value = le16_to_cpu(ctrl->wValue);
+	u16	w_length = le16_to_cpu(ctrl->wLength);
+	unsigned long flags;
+
+/*
+	printk(KERN_INFO "acc_ctrlrequest "
+			"%02x.%02x v%04x i%04x l%u\n",
+			b_requestType, b_request,
+			w_value, w_index, w_length);
+*/
+
+	if (b_requestType == (USB_DIR_OUT | USB_TYPE_VENDOR)) {
+		if (b_request == ACCESSORY_START) {
+			dev->start_requested = 1;
+			schedule_delayed_work(
+				&dev->start_work, msecs_to_jiffies(10));
+			value = 0;
+		} else if (b_request == ACCESSORY_SEND_STRING) {
+			dev->string_index = w_index;
+			cdev->gadget->ep0->driver_data = dev;
+			cdev->req->complete = acc_complete_set_string;
+			value = w_length;
+		} else if (b_request == ACCESSORY_SET_AUDIO_MODE &&
+				w_index == 0 && w_length == 0) {
+			dev->audio_mode = w_value;
+			value = 0;
+		} else if (b_request == ACCESSORY_REGISTER_HID) {
+			value = acc_register_hid(dev, w_value, w_index);
+		} else if (b_request == ACCESSORY_UNREGISTER_HID) {
+			value = acc_unregister_hid(dev, w_value);
+		} else if (b_request == ACCESSORY_SET_HID_REPORT_DESC) {
+			spin_lock_irqsave(&dev->lock, flags);
+			hid = acc_hid_get(&dev->new_hid_list, w_value);
+			spin_unlock_irqrestore(&dev->lock, flags);
+			if (!hid) {
+				value = -EINVAL;
+				goto err;
+			}
+			offset = w_index;
+			if (offset != hid->report_desc_offset
+				|| offset + w_length > hid->report_desc_len) {
+				value = -EINVAL;
+				goto err;
+			}
+			cdev->req->context = hid;
+			cdev->req->complete = acc_complete_set_hid_report_desc;
+			value = w_length;
+		} else if (b_request == ACCESSORY_SEND_HID_EVENT) {
+			spin_lock_irqsave(&dev->lock, flags);
+			hid = acc_hid_get(&dev->hid_list, w_value);
+			spin_unlock_irqrestore(&dev->lock, flags);
+			if (!hid) {
+				value = -EINVAL;
+				goto err;
+			}
+			cdev->req->context = hid;
+			cdev->req->complete = acc_complete_send_hid_event;
+			value = w_length;
+		}
+	} else if (b_requestType == (USB_DIR_IN | USB_TYPE_VENDOR)) {
+		if (b_request == ACCESSORY_GET_PROTOCOL) {
+			*((u16 *)cdev->req->buf) = PROTOCOL_VERSION;
+			value = sizeof(u16);
+
+			/* clear any string left over from a previous session */
+			memset(dev->manufacturer, 0, sizeof(dev->manufacturer));
+			memset(dev->model, 0, sizeof(dev->model));
+			memset(dev->description, 0, sizeof(dev->description));
+			memset(dev->version, 0, sizeof(dev->version));
+			memset(dev->uri, 0, sizeof(dev->uri));
+			memset(dev->serial, 0, sizeof(dev->serial));
+			dev->start_requested = 0;
+			dev->audio_mode = 0;
+		}
+	}
+
+	if (value >= 0) {
+		cdev->req->zero = 0;
+		cdev->req->length = value;
+		value = usb_ep_queue(cdev->gadget->ep0, cdev->req, GFP_ATOMIC);
+		if (value < 0)
+			ERROR(cdev, "%s setup response queue error\n",
+				__func__);
+	}
+
+err:
+	if (value == -EOPNOTSUPP)
+		VDBG(cdev,
+			"unknown class-specific control req "
+			"%02x.%02x v%04x i%04x l%u\n",
+			ctrl->bRequestType, ctrl->bRequest,
+			w_value, w_index, w_length);
+	return value;
+}
+EXPORT_SYMBOL_GPL(acc_ctrlrequest);
+
+static int
+__acc_function_bind(struct usb_configuration *c,
+			struct usb_function *f, bool configfs)
+{
+	struct usb_composite_dev *cdev = c->cdev;
+	struct acc_dev	*dev = func_to_dev(f);
+	int			id;
+	int			ret;
+
+	DBG(cdev, "acc_function_bind dev: %p\n", dev);
+
+	if (configfs) {
+		if (acc_string_defs[INTERFACE_STRING_INDEX].id == 0) {
+			ret = usb_string_id(c->cdev);
+			if (ret < 0)
+				return ret;
+			acc_string_defs[INTERFACE_STRING_INDEX].id = ret;
+			acc_interface_desc.iInterface = ret;
+		}
+		dev->cdev = c->cdev;
+	}
+	ret = hid_register_driver(&acc_hid_driver);
+	if (ret)
+		return ret;
+
+	dev->start_requested = 0;
+
+	/* allocate interface ID(s) */
+	id = usb_interface_id(c, f);
+	if (id < 0)
+		return id;
+	acc_interface_desc.bInterfaceNumber = id;
+
+	/* allocate endpoints */
+	ret = create_bulk_endpoints(dev, &acc_fullspeed_in_desc,
+			&acc_fullspeed_out_desc);
+	if (ret)
+		return ret;
+
+	/* support high speed hardware */
+	if (gadget_is_dualspeed(c->cdev->gadget)) {
+		acc_highspeed_in_desc.bEndpointAddress =
+			acc_fullspeed_in_desc.bEndpointAddress;
+		acc_highspeed_out_desc.bEndpointAddress =
+			acc_fullspeed_out_desc.bEndpointAddress;
+	}
+
+	DBG(cdev, "%s speed %s: IN/%s, OUT/%s\n",
+			gadget_is_dualspeed(c->cdev->gadget) ? "dual" : "full",
+			f->name, dev->ep_in->name, dev->ep_out->name);
+	return 0;
+}
+
+static int
+acc_function_bind(struct usb_configuration *c, struct usb_function *f) {
+	return __acc_function_bind(c, f, false);
+}
+
+static int
+acc_function_bind_configfs(struct usb_configuration *c,
+			struct usb_function *f) {
+	return __acc_function_bind(c, f, true);
+}
+
+static void
+kill_all_hid_devices(struct acc_dev *dev)
+{
+	struct acc_hid_dev *hid;
+	struct list_head *entry, *temp;
+	unsigned long flags;
+
+	/* do nothing if usb accessory device doesn't exist */
+	if (!dev)
+		return;
+
+	spin_lock_irqsave(&dev->lock, flags);
+	list_for_each_safe(entry, temp, &dev->hid_list) {
+		hid = list_entry(entry, struct acc_hid_dev, list);
+		list_del(&hid->list);
+		list_add(&hid->list, &dev->dead_hid_list);
+	}
+	list_for_each_safe(entry, temp, &dev->new_hid_list) {
+		hid = list_entry(entry, struct acc_hid_dev, list);
+		list_del(&hid->list);
+		list_add(&hid->list, &dev->dead_hid_list);
+	}
+	spin_unlock_irqrestore(&dev->lock, flags);
+
+	schedule_work(&dev->hid_work);
+}
+
+static void
+acc_hid_unbind(struct acc_dev *dev)
+{
+	hid_unregister_driver(&acc_hid_driver);
+	kill_all_hid_devices(dev);
+}
+
+static void
+acc_function_unbind(struct usb_configuration *c, struct usb_function *f)
+{
+	struct acc_dev	*dev = func_to_dev(f);
+	struct usb_request *req;
+	int i;
+
+	while ((req = req_get(dev, &dev->tx_idle)))
+		acc_request_free(req, dev->ep_in);
+	for (i = 0; i < RX_REQ_MAX; i++)
+		acc_request_free(dev->rx_req[i], dev->ep_out);
+
+	acc_hid_unbind(dev);
+}
+
+static void acc_start_work(struct work_struct *data)
+{
+	char *envp[2] = { "ACCESSORY=START", NULL };
+	kobject_uevent_env(&acc_device.this_device->kobj, KOBJ_CHANGE, envp);
+}
+
+static int acc_hid_init(struct acc_hid_dev *hdev)
+{
+	struct hid_device *hid;
+	int ret;
+
+	hid = hid_allocate_device();
+	if (IS_ERR(hid))
+		return PTR_ERR(hid);
+
+	hid->ll_driver = &acc_hid_ll_driver;
+	hid->dev.parent = acc_device.this_device;
+
+	hid->bus = BUS_USB;
+	hid->vendor = HID_ANY_ID;
+	hid->product = HID_ANY_ID;
+	hid->driver_data = hdev;
+	ret = hid_add_device(hid);
+	if (ret) {
+		pr_err("can't add hid device: %d\n", ret);
+		hid_destroy_device(hid);
+		return ret;
+	}
+
+	hdev->hid = hid;
+	return 0;
+}
+
+static void acc_hid_delete(struct acc_hid_dev *hid)
+{
+	kfree(hid->report_desc);
+	kfree(hid);
+}
+
+static void acc_hid_work(struct work_struct *data)
+{
+	struct acc_dev *dev = _acc_dev;
+	struct list_head	*entry, *temp;
+	struct acc_hid_dev *hid;
+	struct list_head	new_list, dead_list;
+	unsigned long flags;
+
+	INIT_LIST_HEAD(&new_list);
+
+	spin_lock_irqsave(&dev->lock, flags);
+
+	/* copy hids that are ready for initialization to new_list */
+	list_for_each_safe(entry, temp, &dev->new_hid_list) {
+		hid = list_entry(entry, struct acc_hid_dev, list);
+		if (hid->report_desc_offset == hid->report_desc_len)
+			list_move(&hid->list, &new_list);
+	}
+
+	if (list_empty(&dev->dead_hid_list)) {
+		INIT_LIST_HEAD(&dead_list);
+	} else {
+		/* move all of dev->dead_hid_list to dead_list */
+		dead_list.prev = dev->dead_hid_list.prev;
+		dead_list.next = dev->dead_hid_list.next;
+		dead_list.next->prev = &dead_list;
+		dead_list.prev->next = &dead_list;
+		INIT_LIST_HEAD(&dev->dead_hid_list);
+	}
+
+	spin_unlock_irqrestore(&dev->lock, flags);
+
+	/* register new HID devices */
+	list_for_each_safe(entry, temp, &new_list) {
+		hid = list_entry(entry, struct acc_hid_dev, list);
+		if (acc_hid_init(hid)) {
+			pr_err("can't add HID device %p\n", hid);
+			acc_hid_delete(hid);
+		} else {
+			spin_lock_irqsave(&dev->lock, flags);
+			list_move(&hid->list, &dev->hid_list);
+			spin_unlock_irqrestore(&dev->lock, flags);
+		}
+	}
+
+	/* remove dead HID devices */
+	list_for_each_safe(entry, temp, &dead_list) {
+		hid = list_entry(entry, struct acc_hid_dev, list);
+		list_del(&hid->list);
+		if (hid->hid)
+			hid_destroy_device(hid->hid);
+		acc_hid_delete(hid);
+	}
+}
+
+static int acc_function_set_alt(struct usb_function *f,
+		unsigned intf, unsigned alt)
+{
+	struct acc_dev	*dev = func_to_dev(f);
+	struct usb_composite_dev *cdev = f->config->cdev;
+	int ret;
+
+	DBG(cdev, "acc_function_set_alt intf: %d alt: %d\n", intf, alt);
+
+	ret = config_ep_by_speed(cdev->gadget, f, dev->ep_in);
+	if (ret)
+		return ret;
+
+	ret = usb_ep_enable(dev->ep_in);
+	if (ret)
+		return ret;
+
+	ret = config_ep_by_speed(cdev->gadget, f, dev->ep_out);
+	if (ret)
+		return ret;
+
+	ret = usb_ep_enable(dev->ep_out);
+	if (ret) {
+		usb_ep_disable(dev->ep_in);
+		return ret;
+	}
+
+	dev->online = 1;
+
+	/* readers may be blocked waiting for us to go online */
+	wake_up(&dev->read_wq);
+	return 0;
+}
+
+static void acc_function_disable(struct usb_function *f)
+{
+	struct acc_dev	*dev = func_to_dev(f);
+	struct usb_composite_dev	*cdev = dev->cdev;
+
+	DBG(cdev, "acc_function_disable\n");
+	acc_set_disconnected(dev);
+	usb_ep_disable(dev->ep_in);
+	usb_ep_disable(dev->ep_out);
+
+	/* readers may be blocked waiting for us to go online */
+	wake_up(&dev->read_wq);
+
+	VDBG(cdev, "%s disabled\n", dev->function.name);
+}
+
+static int __maybe_unused acc_bind_config(struct usb_configuration *c)
+{
+	struct acc_dev *dev = _acc_dev;
+	int ret;
+
+	printk(KERN_INFO "acc_bind_config\n");
+
+	/* allocate a string ID for our interface */
+	if (acc_string_defs[INTERFACE_STRING_INDEX].id == 0) {
+		ret = usb_string_id(c->cdev);
+		if (ret < 0)
+			return ret;
+		acc_string_defs[INTERFACE_STRING_INDEX].id = ret;
+		acc_interface_desc.iInterface = ret;
+	}
+
+	dev->cdev = c->cdev;
+	dev->function.name = "accessory";
+	dev->function.strings = acc_strings,
+	dev->function.fs_descriptors = fs_acc_descs;
+	dev->function.hs_descriptors = hs_acc_descs;
+	dev->function.bind = acc_function_bind;
+	dev->function.unbind = acc_function_unbind;
+	dev->function.set_alt = acc_function_set_alt;
+	dev->function.disable = acc_function_disable;
+
+	return usb_add_function(c, &dev->function);
+}
+
+static int acc_setup(void)
+{
+	struct acc_dev *dev;
+	int ret;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	spin_lock_init(&dev->lock);
+	init_waitqueue_head(&dev->read_wq);
+	init_waitqueue_head(&dev->write_wq);
+	atomic_set(&dev->open_excl, 0);
+	INIT_LIST_HEAD(&dev->tx_idle);
+	INIT_LIST_HEAD(&dev->hid_list);
+	INIT_LIST_HEAD(&dev->new_hid_list);
+	INIT_LIST_HEAD(&dev->dead_hid_list);
+	INIT_DELAYED_WORK(&dev->start_work, acc_start_work);
+	INIT_WORK(&dev->hid_work, acc_hid_work);
+
+	/* _acc_dev must be set before calling usb_gadget_register_driver */
+	_acc_dev = dev;
+
+	ret = misc_register(&acc_device);
+	if (ret)
+		goto err;
+
+	return 0;
+
+err:
+	kfree(dev);
+	pr_err("USB accessory gadget driver failed to initialize\n");
+	return ret;
+}
+
+void acc_disconnect(void)
+{
+	/* unregister all HID devices if USB is disconnected */
+	kill_all_hid_devices(_acc_dev);
+}
+EXPORT_SYMBOL_GPL(acc_disconnect);
+
+static void acc_cleanup(void)
+{
+	misc_deregister(&acc_device);
+	kfree(_acc_dev);
+	_acc_dev = NULL;
+}
+static struct acc_instance *to_acc_instance(struct config_item *item)
+{
+	return container_of(to_config_group(item), struct acc_instance,
+		func_inst.group);
+}
+
+static void acc_attr_release(struct config_item *item)
+{
+	struct acc_instance *fi_acc = to_acc_instance(item);
+
+	usb_put_function_instance(&fi_acc->func_inst);
+}
+
+static struct configfs_item_operations acc_item_ops = {
+	.release        = acc_attr_release,
+};
+
+static struct config_item_type acc_func_type = {
+	.ct_item_ops    = &acc_item_ops,
+	.ct_owner       = THIS_MODULE,
+};
+
+static struct acc_instance *to_fi_acc(struct usb_function_instance *fi)
+{
+	return container_of(fi, struct acc_instance, func_inst);
+}
+
+static int acc_set_inst_name(struct usb_function_instance *fi, const char *name)
+{
+	struct acc_instance *fi_acc;
+	char *ptr;
+	int name_len;
+
+	name_len = strlen(name) + 1;
+	if (name_len > MAX_INST_NAME_LEN)
+		return -ENAMETOOLONG;
+
+	ptr = kstrndup(name, name_len, GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	fi_acc = to_fi_acc(fi);
+	fi_acc->name = ptr;
+	return 0;
+}
+
+static void acc_free_inst(struct usb_function_instance *fi)
+{
+	struct acc_instance *fi_acc;
+
+	fi_acc = to_fi_acc(fi);
+	kfree(fi_acc->name);
+	acc_cleanup();
+}
+
+static struct usb_function_instance *acc_alloc_inst(void)
+{
+	struct acc_instance *fi_acc;
+	struct acc_dev *dev;
+	int err;
+
+	fi_acc = kzalloc(sizeof(*fi_acc), GFP_KERNEL);
+	if (!fi_acc)
+		return ERR_PTR(-ENOMEM);
+	fi_acc->func_inst.set_inst_name = acc_set_inst_name;
+	fi_acc->func_inst.free_func_inst = acc_free_inst;
+
+	err = acc_setup();
+	if (err) {
+		kfree(fi_acc);
+		pr_err("Error setting ACCESSORY\n");
+		return ERR_PTR(err);
+	}
+
+	config_group_init_type_name(&fi_acc->func_inst.group,
+					"", &acc_func_type);
+	dev = _acc_dev;
+	return  &fi_acc->func_inst;
+}
+
+static void acc_free(struct usb_function *f)
+{
+/*NO-OP: no function specific resource allocation in mtp_alloc*/
+}
+
+int acc_ctrlrequest_configfs(struct usb_function *f,
+			const struct usb_ctrlrequest *ctrl) {
+	if (f->config != NULL && f->config->cdev != NULL)
+		return acc_ctrlrequest(f->config->cdev, ctrl);
+	else
+		return -1;
+}
+
+static struct usb_function *acc_alloc(struct usb_function_instance *fi)
+{
+	struct acc_dev *dev = _acc_dev;
+
+	pr_info("acc_alloc\n");
+
+	dev->function.name = "accessory";
+	dev->function.strings = acc_strings,
+	dev->function.fs_descriptors = fs_acc_descs;
+	dev->function.hs_descriptors = hs_acc_descs;
+	dev->function.bind = acc_function_bind_configfs;
+	dev->function.unbind = acc_function_unbind;
+	dev->function.set_alt = acc_function_set_alt;
+	dev->function.disable = acc_function_disable;
+	dev->function.free_func = acc_free;
+	dev->function.setup = acc_ctrlrequest_configfs;
+
+	return &dev->function;
+}
+DECLARE_USB_FUNCTION_INIT(accessory, acc_alloc_inst, acc_alloc);
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/gadget/function/f_audio_source.c b/drivers/usb/gadget/function/f_audio_source.c
new file mode 100644
index 00000000000..39645be9350
--- /dev/null
+++ b/drivers/usb/gadget/function/f_audio_source.c
@@ -0,0 +1,1054 @@
+/*
+ * Gadget Function Driver for USB audio source device
+ *
+ * Copyright (C) 2012 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/device.h>
+#include <linux/usb/audio.h>
+#include <linux/wait.h>
+#include <sound/core.h>
+#include <sound/initval.h>
+#include <sound/pcm.h>
+
+#include <linux/usb.h>
+#include <linux/usb_usual.h>
+#include <linux/usb/ch9.h>
+#include <linux/configfs.h>
+#include <linux/usb/composite.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#define SAMPLE_RATE 44100
+#define FRAMES_PER_MSEC (SAMPLE_RATE / 1000)
+
+#define IN_EP_MAX_PACKET_SIZE 256
+
+/* Number of requests to allocate */
+#define IN_EP_REQ_COUNT 4
+
+#define AUDIO_AC_INTERFACE	0
+#define AUDIO_AS_INTERFACE	1
+#define AUDIO_NUM_INTERFACES	2
+#define MAX_INST_NAME_LEN     40
+
+/* B.3.1  Standard AC Interface Descriptor */
+static struct usb_interface_descriptor ac_interface_desc = {
+	.bLength =		USB_DT_INTERFACE_SIZE,
+	.bDescriptorType =	USB_DT_INTERFACE,
+	.bNumEndpoints =	0,
+	.bInterfaceClass =	USB_CLASS_AUDIO,
+	.bInterfaceSubClass =	USB_SUBCLASS_AUDIOCONTROL,
+};
+
+DECLARE_UAC_AC_HEADER_DESCRIPTOR(2);
+
+#define UAC_DT_AC_HEADER_LENGTH	UAC_DT_AC_HEADER_SIZE(AUDIO_NUM_INTERFACES)
+/* 1 input terminal, 1 output terminal and 1 feature unit */
+#define UAC_DT_TOTAL_LENGTH (UAC_DT_AC_HEADER_LENGTH \
+	+ UAC_DT_INPUT_TERMINAL_SIZE + UAC_DT_OUTPUT_TERMINAL_SIZE \
+	+ UAC_DT_FEATURE_UNIT_SIZE(0))
+/* B.3.2  Class-Specific AC Interface Descriptor */
+static struct uac1_ac_header_descriptor_2 ac_header_desc = {
+	.bLength =		UAC_DT_AC_HEADER_LENGTH,
+	.bDescriptorType =	USB_DT_CS_INTERFACE,
+	.bDescriptorSubtype =	UAC_HEADER,
+	.bcdADC =		__constant_cpu_to_le16(0x0100),
+	.wTotalLength =		__constant_cpu_to_le16(UAC_DT_TOTAL_LENGTH),
+	.bInCollection =	AUDIO_NUM_INTERFACES,
+	.baInterfaceNr = {
+		[0] =		AUDIO_AC_INTERFACE,
+		[1] =		AUDIO_AS_INTERFACE,
+	}
+};
+
+#define INPUT_TERMINAL_ID	1
+static struct uac_input_terminal_descriptor input_terminal_desc = {
+	.bLength =		UAC_DT_INPUT_TERMINAL_SIZE,
+	.bDescriptorType =	USB_DT_CS_INTERFACE,
+	.bDescriptorSubtype =	UAC_INPUT_TERMINAL,
+	.bTerminalID =		INPUT_TERMINAL_ID,
+	.wTerminalType =	UAC_INPUT_TERMINAL_MICROPHONE,
+	.bAssocTerminal =	0,
+	.wChannelConfig =	0x3,
+};
+
+DECLARE_UAC_FEATURE_UNIT_DESCRIPTOR(0);
+
+#define FEATURE_UNIT_ID		2
+static struct uac_feature_unit_descriptor_0 feature_unit_desc = {
+	.bLength		= UAC_DT_FEATURE_UNIT_SIZE(0),
+	.bDescriptorType	= USB_DT_CS_INTERFACE,
+	.bDescriptorSubtype	= UAC_FEATURE_UNIT,
+	.bUnitID		= FEATURE_UNIT_ID,
+	.bSourceID		= INPUT_TERMINAL_ID,
+	.bControlSize		= 2,
+};
+
+#define OUTPUT_TERMINAL_ID	3
+static struct uac1_output_terminal_descriptor output_terminal_desc = {
+	.bLength		= UAC_DT_OUTPUT_TERMINAL_SIZE,
+	.bDescriptorType	= USB_DT_CS_INTERFACE,
+	.bDescriptorSubtype	= UAC_OUTPUT_TERMINAL,
+	.bTerminalID		= OUTPUT_TERMINAL_ID,
+	.wTerminalType		= UAC_TERMINAL_STREAMING,
+	.bAssocTerminal		= FEATURE_UNIT_ID,
+	.bSourceID		= FEATURE_UNIT_ID,
+};
+
+/* B.4.1  Standard AS Interface Descriptor */
+static struct usb_interface_descriptor as_interface_alt_0_desc = {
+	.bLength =		USB_DT_INTERFACE_SIZE,
+	.bDescriptorType =	USB_DT_INTERFACE,
+	.bAlternateSetting =	0,
+	.bNumEndpoints =	0,
+	.bInterfaceClass =	USB_CLASS_AUDIO,
+	.bInterfaceSubClass =	USB_SUBCLASS_AUDIOSTREAMING,
+};
+
+static struct usb_interface_descriptor as_interface_alt_1_desc = {
+	.bLength =		USB_DT_INTERFACE_SIZE,
+	.bDescriptorType =	USB_DT_INTERFACE,
+	.bAlternateSetting =	1,
+	.bNumEndpoints =	1,
+	.bInterfaceClass =	USB_CLASS_AUDIO,
+	.bInterfaceSubClass =	USB_SUBCLASS_AUDIOSTREAMING,
+};
+
+/* B.4.2  Class-Specific AS Interface Descriptor */
+static struct uac1_as_header_descriptor as_header_desc = {
+	.bLength =		UAC_DT_AS_HEADER_SIZE,
+	.bDescriptorType =	USB_DT_CS_INTERFACE,
+	.bDescriptorSubtype =	UAC_AS_GENERAL,
+	.bTerminalLink =	INPUT_TERMINAL_ID,
+	.bDelay =		1,
+	.wFormatTag =		UAC_FORMAT_TYPE_I_PCM,
+};
+
+DECLARE_UAC_FORMAT_TYPE_I_DISCRETE_DESC(1);
+
+static struct uac_format_type_i_discrete_descriptor_1 as_type_i_desc = {
+	.bLength =		UAC_FORMAT_TYPE_I_DISCRETE_DESC_SIZE(1),
+	.bDescriptorType =	USB_DT_CS_INTERFACE,
+	.bDescriptorSubtype =	UAC_FORMAT_TYPE,
+	.bFormatType =		UAC_FORMAT_TYPE_I,
+	.bSubframeSize =	2,
+	.bBitResolution =	16,
+	.bSamFreqType =		1,
+};
+
+/* Standard ISO IN Endpoint Descriptor for highspeed */
+static struct usb_endpoint_descriptor hs_as_in_ep_desc  = {
+	.bLength =		USB_DT_ENDPOINT_AUDIO_SIZE,
+	.bDescriptorType =	USB_DT_ENDPOINT,
+	.bEndpointAddress =	USB_DIR_IN,
+	.bmAttributes =		USB_ENDPOINT_SYNC_SYNC
+				| USB_ENDPOINT_XFER_ISOC,
+	.wMaxPacketSize =	__constant_cpu_to_le16(IN_EP_MAX_PACKET_SIZE),
+	.bInterval =		4, /* poll 1 per millisecond */
+};
+
+/* Standard ISO IN Endpoint Descriptor for highspeed */
+static struct usb_endpoint_descriptor fs_as_in_ep_desc  = {
+	.bLength =		USB_DT_ENDPOINT_AUDIO_SIZE,
+	.bDescriptorType =	USB_DT_ENDPOINT,
+	.bEndpointAddress =	USB_DIR_IN,
+	.bmAttributes =		USB_ENDPOINT_SYNC_SYNC
+				| USB_ENDPOINT_XFER_ISOC,
+	.wMaxPacketSize =	__constant_cpu_to_le16(IN_EP_MAX_PACKET_SIZE),
+	.bInterval =		1, /* poll 1 per millisecond */
+};
+
+/* Class-specific AS ISO OUT Endpoint Descriptor */
+static struct uac_iso_endpoint_descriptor as_iso_in_desc = {
+	.bLength =		UAC_ISO_ENDPOINT_DESC_SIZE,
+	.bDescriptorType =	USB_DT_CS_ENDPOINT,
+	.bDescriptorSubtype =	UAC_EP_GENERAL,
+	.bmAttributes =		1,
+	.bLockDelayUnits =	1,
+	.wLockDelay =		__constant_cpu_to_le16(1),
+};
+
+static struct usb_descriptor_header *hs_audio_desc[] = {
+	(struct usb_descriptor_header *)&ac_interface_desc,
+	(struct usb_descriptor_header *)&ac_header_desc,
+
+	(struct usb_descriptor_header *)&input_terminal_desc,
+	(struct usb_descriptor_header *)&output_terminal_desc,
+	(struct usb_descriptor_header *)&feature_unit_desc,
+
+	(struct usb_descriptor_header *)&as_interface_alt_0_desc,
+	(struct usb_descriptor_header *)&as_interface_alt_1_desc,
+	(struct usb_descriptor_header *)&as_header_desc,
+
+	(struct usb_descriptor_header *)&as_type_i_desc,
+
+	(struct usb_descriptor_header *)&hs_as_in_ep_desc,
+	(struct usb_descriptor_header *)&as_iso_in_desc,
+	NULL,
+};
+
+static struct usb_descriptor_header *fs_audio_desc[] = {
+	(struct usb_descriptor_header *)&ac_interface_desc,
+	(struct usb_descriptor_header *)&ac_header_desc,
+
+	(struct usb_descriptor_header *)&input_terminal_desc,
+	(struct usb_descriptor_header *)&output_terminal_desc,
+	(struct usb_descriptor_header *)&feature_unit_desc,
+
+	(struct usb_descriptor_header *)&as_interface_alt_0_desc,
+	(struct usb_descriptor_header *)&as_interface_alt_1_desc,
+	(struct usb_descriptor_header *)&as_header_desc,
+
+	(struct usb_descriptor_header *)&as_type_i_desc,
+
+	(struct usb_descriptor_header *)&fs_as_in_ep_desc,
+	(struct usb_descriptor_header *)&as_iso_in_desc,
+	NULL,
+};
+
+static struct snd_pcm_hardware audio_hw_info = {
+	.info =			SNDRV_PCM_INFO_MMAP |
+				SNDRV_PCM_INFO_MMAP_VALID |
+				SNDRV_PCM_INFO_BATCH |
+				SNDRV_PCM_INFO_INTERLEAVED |
+				SNDRV_PCM_INFO_BLOCK_TRANSFER,
+
+	.formats		= SNDRV_PCM_FMTBIT_S16_LE,
+	.channels_min		= 2,
+	.channels_max		= 2,
+	.rate_min		= SAMPLE_RATE,
+	.rate_max		= SAMPLE_RATE,
+
+	.buffer_bytes_max =	1024 * 1024,
+	.period_bytes_min =	64,
+	.period_bytes_max =	512 * 1024,
+	.periods_min =		2,
+	.periods_max =		1024,
+};
+
+/*-------------------------------------------------------------------------*/
+
+struct audio_source_config {
+	int	card;
+	int	device;
+};
+
+struct audio_dev {
+	struct usb_function		func;
+	struct snd_card			*card;
+	struct snd_pcm			*pcm;
+	struct snd_pcm_substream *substream;
+
+	struct list_head		idle_reqs;
+	struct usb_ep			*in_ep;
+
+	spinlock_t			lock;
+
+	/* beginning, end and current position in our buffer */
+	void				*buffer_start;
+	void				*buffer_end;
+	void				*buffer_pos;
+
+	/* byte size of a "period" */
+	unsigned int			period;
+	/* bytes sent since last call to snd_pcm_period_elapsed */
+	unsigned int			period_offset;
+	/* time we started playing */
+	ktime_t				start_time;
+	/* number of frames sent since start_time */
+	s64				frames_sent;
+	struct audio_source_config	*config;
+};
+
+static inline struct audio_dev *func_to_audio(struct usb_function *f)
+{
+	return container_of(f, struct audio_dev, func);
+}
+
+/*-------------------------------------------------------------------------*/
+
+struct audio_source_instance {
+	struct usb_function_instance func_inst;
+	const char *name;
+	struct audio_source_config *config;
+	struct device *audio_device;
+};
+
+static void audio_source_attr_release(struct config_item *item);
+
+static struct configfs_item_operations audio_source_item_ops = {
+	.release        = audio_source_attr_release,
+};
+
+static struct config_item_type audio_source_func_type = {
+	.ct_item_ops    = &audio_source_item_ops,
+	.ct_owner       = THIS_MODULE,
+};
+
+static ssize_t audio_source_pcm_show(struct device *dev,
+		struct device_attribute *attr, char *buf);
+
+static DEVICE_ATTR(pcm, S_IRUGO, audio_source_pcm_show, NULL);
+
+static struct device_attribute *audio_source_function_attributes[] = {
+	&dev_attr_pcm,
+	NULL
+};
+
+/*--------------------------------------------------------------------------*/
+
+static struct usb_request *audio_request_new(struct usb_ep *ep, int buffer_size)
+{
+	struct usb_request *req = usb_ep_alloc_request(ep, GFP_KERNEL);
+	if (!req)
+		return NULL;
+
+	req->buf = kmalloc(buffer_size, GFP_KERNEL);
+	if (!req->buf) {
+		usb_ep_free_request(ep, req);
+		return NULL;
+	}
+	req->length = buffer_size;
+	return req;
+}
+
+static void audio_request_free(struct usb_request *req, struct usb_ep *ep)
+{
+	if (req) {
+		kfree(req->buf);
+		usb_ep_free_request(ep, req);
+	}
+}
+
+static void audio_req_put(struct audio_dev *audio, struct usb_request *req)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&audio->lock, flags);
+	list_add_tail(&req->list, &audio->idle_reqs);
+	spin_unlock_irqrestore(&audio->lock, flags);
+}
+
+static struct usb_request *audio_req_get(struct audio_dev *audio)
+{
+	unsigned long flags;
+	struct usb_request *req;
+
+	spin_lock_irqsave(&audio->lock, flags);
+	if (list_empty(&audio->idle_reqs)) {
+		req = 0;
+	} else {
+		req = list_first_entry(&audio->idle_reqs, struct usb_request,
+				list);
+		list_del(&req->list);
+	}
+	spin_unlock_irqrestore(&audio->lock, flags);
+	return req;
+}
+
+/* send the appropriate number of packets to match our bitrate */
+static void audio_send(struct audio_dev *audio)
+{
+	struct snd_pcm_runtime *runtime;
+	struct usb_request *req;
+	int length, length1, length2, ret;
+	s64 msecs;
+	s64 frames;
+	ktime_t now;
+
+	/* audio->substream will be null if we have been closed */
+	if (!audio->substream)
+		return;
+	/* audio->buffer_pos will be null if we have been stopped */
+	if (!audio->buffer_pos)
+		return;
+
+	runtime = audio->substream->runtime;
+
+	/* compute number of frames to send */
+	now = ktime_get();
+	msecs = ktime_to_ns(now) - ktime_to_ns(audio->start_time);
+	do_div(msecs, 1000000);
+	frames = msecs * SAMPLE_RATE;
+	do_div(frames, 1000);
+
+	/* Readjust our frames_sent if we fall too far behind.
+	 * If we get too far behind it is better to drop some frames than
+	 * to keep sending data too fast in an attempt to catch up.
+	 */
+	if (frames - audio->frames_sent > 10 * FRAMES_PER_MSEC)
+		audio->frames_sent = frames - FRAMES_PER_MSEC;
+
+	frames -= audio->frames_sent;
+
+	/* We need to send something to keep the pipeline going */
+	if (frames <= 0)
+		frames = FRAMES_PER_MSEC;
+
+	while (frames > 0) {
+		req = audio_req_get(audio);
+		if (!req)
+			break;
+
+		length = frames_to_bytes(runtime, frames);
+		if (length > IN_EP_MAX_PACKET_SIZE)
+			length = IN_EP_MAX_PACKET_SIZE;
+
+		if (audio->buffer_pos + length > audio->buffer_end)
+			length1 = audio->buffer_end - audio->buffer_pos;
+		else
+			length1 = length;
+		memcpy(req->buf, audio->buffer_pos, length1);
+		if (length1 < length) {
+			/* Wrap around and copy remaining length
+			 * at beginning of buffer.
+			 */
+			length2 = length - length1;
+			memcpy(req->buf + length1, audio->buffer_start,
+					length2);
+			audio->buffer_pos = audio->buffer_start + length2;
+		} else {
+			audio->buffer_pos += length1;
+			if (audio->buffer_pos >= audio->buffer_end)
+				audio->buffer_pos = audio->buffer_start;
+		}
+
+		req->length = length;
+		ret = usb_ep_queue(audio->in_ep, req, GFP_ATOMIC);
+		if (ret < 0) {
+			pr_err("usb_ep_queue failed ret: %d\n", ret);
+			audio_req_put(audio, req);
+			break;
+		}
+
+		frames -= bytes_to_frames(runtime, length);
+		audio->frames_sent += bytes_to_frames(runtime, length);
+	}
+}
+
+static void audio_control_complete(struct usb_ep *ep, struct usb_request *req)
+{
+	/* nothing to do here */
+}
+
+static void audio_data_complete(struct usb_ep *ep, struct usb_request *req)
+{
+	struct audio_dev *audio = req->context;
+
+	pr_debug("audio_data_complete req->status %d req->actual %d\n",
+		req->status, req->actual);
+
+	audio_req_put(audio, req);
+
+	if (!audio->buffer_start || req->status)
+		return;
+
+	audio->period_offset += req->actual;
+	if (audio->period_offset >= audio->period) {
+		snd_pcm_period_elapsed(audio->substream);
+		audio->period_offset = 0;
+	}
+	audio_send(audio);
+}
+
+static int audio_set_endpoint_req(struct usb_function *f,
+		const struct usb_ctrlrequest *ctrl)
+{
+	int value = -EOPNOTSUPP;
+	u16 ep = le16_to_cpu(ctrl->wIndex);
+	u16 len = le16_to_cpu(ctrl->wLength);
+	u16 w_value = le16_to_cpu(ctrl->wValue);
+
+	pr_debug("bRequest 0x%x, w_value 0x%04x, len %d, endpoint %d\n",
+			ctrl->bRequest, w_value, len, ep);
+
+	switch (ctrl->bRequest) {
+	case UAC_SET_CUR:
+	case UAC_SET_MIN:
+	case UAC_SET_MAX:
+	case UAC_SET_RES:
+		value = len;
+		break;
+	default:
+		break;
+	}
+
+	return value;
+}
+
+static int audio_get_endpoint_req(struct usb_function *f,
+		const struct usb_ctrlrequest *ctrl)
+{
+	struct usb_composite_dev *cdev = f->config->cdev;
+	int value = -EOPNOTSUPP;
+	u8 ep = ((le16_to_cpu(ctrl->wIndex) >> 8) & 0xFF);
+	u16 len = le16_to_cpu(ctrl->wLength);
+	u16 w_value = le16_to_cpu(ctrl->wValue);
+	u8 *buf = cdev->req->buf;
+
+	pr_debug("bRequest 0x%x, w_value 0x%04x, len %d, endpoint %d\n",
+			ctrl->bRequest, w_value, len, ep);
+
+	if (w_value == UAC_EP_CS_ATTR_SAMPLE_RATE << 8) {
+		switch (ctrl->bRequest) {
+		case UAC_GET_CUR:
+		case UAC_GET_MIN:
+		case UAC_GET_MAX:
+		case UAC_GET_RES:
+			/* return our sample rate */
+			buf[0] = (u8)SAMPLE_RATE;
+			buf[1] = (u8)(SAMPLE_RATE >> 8);
+			buf[2] = (u8)(SAMPLE_RATE >> 16);
+			value = 3;
+			break;
+		default:
+			break;
+		}
+	}
+
+	return value;
+}
+
+static int
+audio_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl)
+{
+	struct usb_composite_dev *cdev = f->config->cdev;
+	struct usb_request *req = cdev->req;
+	int value = -EOPNOTSUPP;
+	u16 w_index = le16_to_cpu(ctrl->wIndex);
+	u16 w_value = le16_to_cpu(ctrl->wValue);
+	u16 w_length = le16_to_cpu(ctrl->wLength);
+
+	/* composite driver infrastructure handles everything; interface
+	 * activation uses set_alt().
+	 */
+	switch (ctrl->bRequestType) {
+	case USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_ENDPOINT:
+		value = audio_set_endpoint_req(f, ctrl);
+		break;
+
+	case USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_ENDPOINT:
+		value = audio_get_endpoint_req(f, ctrl);
+		break;
+	}
+
+	/* respond with data transfer or status phase? */
+	if (value >= 0) {
+		pr_debug("audio req%02x.%02x v%04x i%04x l%d\n",
+			ctrl->bRequestType, ctrl->bRequest,
+			w_value, w_index, w_length);
+		req->zero = 0;
+		req->length = value;
+		req->complete = audio_control_complete;
+		value = usb_ep_queue(cdev->gadget->ep0, req, GFP_ATOMIC);
+		if (value < 0)
+			pr_err("audio response on err %d\n", value);
+	}
+
+	/* device either stalls (value < 0) or reports success */
+	return value;
+}
+
+static int audio_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
+{
+	struct audio_dev *audio = func_to_audio(f);
+	struct usb_composite_dev *cdev = f->config->cdev;
+	int ret;
+
+	pr_debug("audio_set_alt intf %d, alt %d\n", intf, alt);
+
+	ret = config_ep_by_speed(cdev->gadget, f, audio->in_ep);
+	if (ret)
+		return ret;
+
+	usb_ep_enable(audio->in_ep);
+	return 0;
+}
+
+static void audio_disable(struct usb_function *f)
+{
+	struct audio_dev	*audio = func_to_audio(f);
+
+	pr_debug("audio_disable\n");
+	usb_ep_disable(audio->in_ep);
+}
+
+/*-------------------------------------------------------------------------*/
+
+static void audio_build_desc(struct audio_dev *audio)
+{
+	u8 *sam_freq;
+	int rate;
+
+	/* Set channel numbers */
+	input_terminal_desc.bNrChannels = 2;
+	as_type_i_desc.bNrChannels = 2;
+
+	/* Set sample rates */
+	rate = SAMPLE_RATE;
+	sam_freq = as_type_i_desc.tSamFreq[0];
+	memcpy(sam_freq, &rate, 3);
+}
+
+
+static int snd_card_setup(struct usb_configuration *c,
+	struct audio_source_config *config);
+static struct audio_source_instance *to_fi_audio_source(
+	const struct usb_function_instance *fi);
+
+
+/* audio function driver setup/binding */
+static int
+audio_bind(struct usb_configuration *c, struct usb_function *f)
+{
+	struct usb_composite_dev *cdev = c->cdev;
+	struct audio_dev *audio = func_to_audio(f);
+	int status;
+	struct usb_ep *ep;
+	struct usb_request *req;
+	int i;
+	int err;
+
+	if (IS_ENABLED(CONFIG_USB_CONFIGFS)) {
+		struct audio_source_instance *fi_audio =
+				to_fi_audio_source(f->fi);
+		struct audio_source_config *config =
+				fi_audio->config;
+
+		err = snd_card_setup(c, config);
+		if (err)
+			return err;
+	}
+
+	audio_build_desc(audio);
+
+	/* allocate instance-specific interface IDs, and patch descriptors */
+	status = usb_interface_id(c, f);
+	if (status < 0)
+		goto fail;
+	ac_interface_desc.bInterfaceNumber = status;
+
+	/* AUDIO_AC_INTERFACE */
+	ac_header_desc.baInterfaceNr[0] = status;
+
+	status = usb_interface_id(c, f);
+	if (status < 0)
+		goto fail;
+	as_interface_alt_0_desc.bInterfaceNumber = status;
+	as_interface_alt_1_desc.bInterfaceNumber = status;
+
+	/* AUDIO_AS_INTERFACE */
+	ac_header_desc.baInterfaceNr[1] = status;
+
+	status = -ENODEV;
+
+	/* allocate our endpoint */
+	ep = usb_ep_autoconfig(cdev->gadget, &fs_as_in_ep_desc);
+	if (!ep)
+		goto fail;
+	audio->in_ep = ep;
+	ep->driver_data = audio; /* claim */
+
+	if (gadget_is_dualspeed(c->cdev->gadget))
+		hs_as_in_ep_desc.bEndpointAddress =
+			fs_as_in_ep_desc.bEndpointAddress;
+
+	f->fs_descriptors = fs_audio_desc;
+	f->hs_descriptors = hs_audio_desc;
+
+	for (i = 0, status = 0; i < IN_EP_REQ_COUNT && status == 0; i++) {
+		req = audio_request_new(ep, IN_EP_MAX_PACKET_SIZE);
+		if (req) {
+			req->context = audio;
+			req->complete = audio_data_complete;
+			audio_req_put(audio, req);
+		} else
+			status = -ENOMEM;
+	}
+
+fail:
+	return status;
+}
+
+static void
+audio_unbind(struct usb_configuration *c, struct usb_function *f)
+{
+	struct audio_dev *audio = func_to_audio(f);
+	struct usb_request *req;
+
+	while ((req = audio_req_get(audio)))
+		audio_request_free(req, audio->in_ep);
+
+	snd_card_free_when_closed(audio->card);
+	audio->card = NULL;
+	audio->pcm = NULL;
+	audio->substream = NULL;
+	audio->in_ep = NULL;
+
+	if (IS_ENABLED(CONFIG_USB_CONFIGFS)) {
+		struct audio_source_instance *fi_audio =
+				to_fi_audio_source(f->fi);
+		struct audio_source_config *config =
+				fi_audio->config;
+
+		config->card = -1;
+		config->device = -1;
+	}
+}
+
+static void audio_pcm_playback_start(struct audio_dev *audio)
+{
+	audio->start_time = ktime_get();
+	audio->frames_sent = 0;
+	audio_send(audio);
+}
+
+static void audio_pcm_playback_stop(struct audio_dev *audio)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&audio->lock, flags);
+	audio->buffer_start = 0;
+	audio->buffer_end = 0;
+	audio->buffer_pos = 0;
+	spin_unlock_irqrestore(&audio->lock, flags);
+}
+
+static int audio_pcm_open(struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct audio_dev *audio = substream->private_data;
+
+	runtime->private_data = audio;
+	runtime->hw = audio_hw_info;
+	snd_pcm_limit_hw_rates(runtime);
+	runtime->hw.channels_max = 2;
+
+	audio->substream = substream;
+	return 0;
+}
+
+static int audio_pcm_close(struct snd_pcm_substream *substream)
+{
+	struct audio_dev *audio = substream->private_data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&audio->lock, flags);
+	audio->substream = NULL;
+	spin_unlock_irqrestore(&audio->lock, flags);
+
+	return 0;
+}
+
+static int audio_pcm_hw_params(struct snd_pcm_substream *substream,
+				struct snd_pcm_hw_params *params)
+{
+	unsigned int channels = params_channels(params);
+	unsigned int rate = params_rate(params);
+
+	if (rate != SAMPLE_RATE)
+		return -EINVAL;
+	if (channels != 2)
+		return -EINVAL;
+
+	return snd_pcm_lib_alloc_vmalloc_buffer(substream,
+		params_buffer_bytes(params));
+}
+
+static int audio_pcm_hw_free(struct snd_pcm_substream *substream)
+{
+	return snd_pcm_lib_free_vmalloc_buffer(substream);
+}
+
+static int audio_pcm_prepare(struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct audio_dev *audio = runtime->private_data;
+
+	audio->period = snd_pcm_lib_period_bytes(substream);
+	audio->period_offset = 0;
+	audio->buffer_start = runtime->dma_area;
+	audio->buffer_end = audio->buffer_start
+		+ snd_pcm_lib_buffer_bytes(substream);
+	audio->buffer_pos = audio->buffer_start;
+
+	return 0;
+}
+
+static snd_pcm_uframes_t audio_pcm_pointer(struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct audio_dev *audio = runtime->private_data;
+	ssize_t bytes = audio->buffer_pos - audio->buffer_start;
+
+	/* return offset of next frame to fill in our buffer */
+	return bytes_to_frames(runtime, bytes);
+}
+
+static int audio_pcm_playback_trigger(struct snd_pcm_substream *substream,
+					int cmd)
+{
+	struct audio_dev *audio = substream->runtime->private_data;
+	int ret = 0;
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_RESUME:
+		audio_pcm_playback_start(audio);
+		break;
+
+	case SNDRV_PCM_TRIGGER_STOP:
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+		audio_pcm_playback_stop(audio);
+		break;
+
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static struct audio_dev _audio_dev = {
+	.func = {
+		.name = "audio_source",
+		.bind = audio_bind,
+		.unbind = audio_unbind,
+		.set_alt = audio_set_alt,
+		.setup = audio_setup,
+		.disable = audio_disable,
+	},
+	.lock = __SPIN_LOCK_UNLOCKED(_audio_dev.lock),
+	.idle_reqs = LIST_HEAD_INIT(_audio_dev.idle_reqs),
+};
+
+static struct snd_pcm_ops audio_playback_ops = {
+	.open		= audio_pcm_open,
+	.close		= audio_pcm_close,
+	.ioctl		= snd_pcm_lib_ioctl,
+	.hw_params	= audio_pcm_hw_params,
+	.hw_free	= audio_pcm_hw_free,
+	.prepare	= audio_pcm_prepare,
+	.trigger	= audio_pcm_playback_trigger,
+	.pointer	= audio_pcm_pointer,
+};
+
+int audio_source_bind_config(struct usb_configuration *c,
+		struct audio_source_config *config)
+{
+	struct audio_dev *audio;
+	int err;
+
+	config->card = -1;
+	config->device = -1;
+
+	audio = &_audio_dev;
+
+	err = snd_card_setup(c, config);
+	if (err)
+		return err;
+
+	err = usb_add_function(c, &audio->func);
+	if (err)
+		goto add_fail;
+
+	return 0;
+
+add_fail:
+	snd_card_free(audio->card);
+	return err;
+}
+
+static int snd_card_setup(struct usb_configuration *c,
+		struct audio_source_config *config)
+{
+	struct audio_dev *audio;
+	struct snd_card *card;
+	struct snd_pcm *pcm;
+	int err;
+
+	audio = &_audio_dev;
+
+	err = snd_card_new(&c->cdev->gadget->dev,
+			SNDRV_DEFAULT_IDX1, SNDRV_DEFAULT_STR1,
+			THIS_MODULE, 0, &card);
+	if (err)
+		return err;
+
+	err = snd_pcm_new(card, "USB audio source", 0, 1, 0, &pcm);
+	if (err)
+		goto pcm_fail;
+
+	pcm->private_data = audio;
+	pcm->info_flags = 0;
+	audio->pcm = pcm;
+
+	strlcpy(pcm->name, "USB gadget audio", sizeof(pcm->name));
+
+	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &audio_playback_ops);
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
+				NULL, 0, 64 * 1024);
+
+	strlcpy(card->driver, "audio_source", sizeof(card->driver));
+	strlcpy(card->shortname, card->driver, sizeof(card->shortname));
+	strlcpy(card->longname, "USB accessory audio source",
+		sizeof(card->longname));
+
+	err = snd_card_register(card);
+	if (err)
+		goto register_fail;
+
+	config->card = pcm->card->number;
+	config->device = pcm->device;
+	audio->card = card;
+	return 0;
+
+register_fail:
+pcm_fail:
+	snd_card_free(audio->card);
+	return err;
+}
+
+static struct audio_source_instance *to_audio_source_instance(
+					struct config_item *item)
+{
+	return container_of(to_config_group(item), struct audio_source_instance,
+		func_inst.group);
+}
+
+static struct audio_source_instance *to_fi_audio_source(
+					const struct usb_function_instance *fi)
+{
+	return container_of(fi, struct audio_source_instance, func_inst);
+}
+
+static void audio_source_attr_release(struct config_item *item)
+{
+	struct audio_source_instance *fi_audio = to_audio_source_instance(item);
+
+	usb_put_function_instance(&fi_audio->func_inst);
+}
+
+static int audio_source_set_inst_name(struct usb_function_instance *fi,
+					const char *name)
+{
+	struct audio_source_instance *fi_audio;
+	char *ptr;
+	int name_len;
+
+	name_len = strlen(name) + 1;
+	if (name_len > MAX_INST_NAME_LEN)
+		return -ENAMETOOLONG;
+
+	ptr = kstrndup(name, name_len, GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	fi_audio = to_fi_audio_source(fi);
+	fi_audio->name = ptr;
+
+	return 0;
+}
+
+static void audio_source_free_inst(struct usb_function_instance *fi)
+{
+	struct audio_source_instance *fi_audio;
+
+	fi_audio = to_fi_audio_source(fi);
+	device_destroy(fi_audio->audio_device->class,
+			fi_audio->audio_device->devt);
+	kfree(fi_audio->name);
+	kfree(fi_audio->config);
+}
+
+static ssize_t audio_source_pcm_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct audio_source_instance *fi_audio = dev_get_drvdata(dev);
+	struct audio_source_config *config = fi_audio->config;
+
+	/* print PCM card and device numbers */
+	return sprintf(buf, "%d %d\n", config->card, config->device);
+}
+
+struct device *create_function_device(char *name);
+
+static struct usb_function_instance *audio_source_alloc_inst(void)
+{
+	struct audio_source_instance *fi_audio;
+	struct device_attribute **attrs;
+	struct device_attribute *attr;
+	struct device *dev;
+	void *err_ptr;
+	int err = 0;
+
+	fi_audio = kzalloc(sizeof(*fi_audio), GFP_KERNEL);
+	if (!fi_audio)
+		return ERR_PTR(-ENOMEM);
+
+	fi_audio->func_inst.set_inst_name = audio_source_set_inst_name;
+	fi_audio->func_inst.free_func_inst = audio_source_free_inst;
+
+	fi_audio->config = kzalloc(sizeof(struct audio_source_config),
+							GFP_KERNEL);
+	if (!fi_audio->config) {
+		err_ptr = ERR_PTR(-ENOMEM);
+		goto fail_audio;
+	}
+
+	config_group_init_type_name(&fi_audio->func_inst.group, "",
+						&audio_source_func_type);
+	dev = create_function_device("f_audio_source");
+
+	if (IS_ERR(dev)) {
+		err_ptr = dev;
+		goto fail_audio_config;
+	}
+
+	fi_audio->config->card = -1;
+	fi_audio->config->device = -1;
+	fi_audio->audio_device = dev;
+
+	attrs = audio_source_function_attributes;
+	if (attrs) {
+		while ((attr = *attrs++) && !err)
+			err = device_create_file(dev, attr);
+		if (err) {
+			err_ptr = ERR_PTR(-EINVAL);
+			goto fail_device;
+		}
+	}
+
+	dev_set_drvdata(dev, fi_audio);
+	_audio_dev.config = fi_audio->config;
+
+	return  &fi_audio->func_inst;
+
+fail_device:
+	device_destroy(dev->class, dev->devt);
+fail_audio_config:
+	kfree(fi_audio->config);
+fail_audio:
+	kfree(fi_audio);
+	return err_ptr;
+
+}
+
+static struct usb_function *audio_source_alloc(struct usb_function_instance *fi)
+{
+	return &_audio_dev.func;
+}
+
+DECLARE_USB_FUNCTION_INIT(audio_source, audio_source_alloc_inst,
+			audio_source_alloc);
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 63314ede7ba..45207e2246c 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -86,12 +86,15 @@ ffs_setup_state_clear_cancelled(struct ffs_data *ffs)
 		cmpxchg(&ffs->setup_state, FFS_SETUP_CANCELLED, FFS_NO_SETUP);
 }
 
+static void ffs_func_free(struct ffs_function *func);
 
 static void ffs_func_eps_disable(struct ffs_function *func);
 static int __must_check ffs_func_eps_enable(struct ffs_function *func);
 
 static int ffs_func_bind(struct usb_configuration *,
 			 struct usb_function *);
+static void old_ffs_func_unbind(struct usb_configuration *,
+				struct usb_function *);
 static int ffs_func_set_alt(struct usb_function *, unsigned, unsigned);
 static void ffs_func_disable(struct usb_function *);
 static int ffs_func_setup(struct usb_function *,
@@ -1616,6 +1619,71 @@ static void ffs_epfiles_destroy(struct ffs_epfile *epfiles, unsigned count)
 	kfree(epfiles);
 }
 
+static int functionfs_bind_config(struct usb_composite_dev *cdev,
+				   struct usb_configuration *c,
+				   struct ffs_data *ffs)
+{
+	struct ffs_function *func;
+	int ret;
+
+	ENTER();
+
+	func = kzalloc(sizeof *func, GFP_KERNEL);
+	if (unlikely(!func))
+		return -ENOMEM;
+
+	func->function.name    = "Function FS Gadget";
+	func->function.strings = ffs->stringtabs;
+
+	func->function.bind    = ffs_func_bind;
+	func->function.unbind  = old_ffs_func_unbind;
+	func->function.set_alt = ffs_func_set_alt;
+	func->function.disable = ffs_func_disable;
+	func->function.setup   = ffs_func_setup;
+	func->function.suspend = ffs_func_suspend;
+	func->function.resume  = ffs_func_resume;
+
+	func->conf   = c;
+	func->gadget = cdev->gadget;
+	func->ffs = ffs;
+	ffs_data_get(ffs);
+
+	ret = usb_add_function(c, &func->function);
+	if (unlikely(ret))
+		ffs_func_free(func);
+
+	return ret;
+}
+
+static void ffs_func_free(struct ffs_function *func)
+{
+	struct ffs_ep *ep         = func->eps;
+	unsigned count            = func->ffs->eps_count;
+	unsigned long flags;
+
+	ENTER();
+
+	/* cleanup after autoconfig */
+	spin_lock_irqsave(&func->ffs->eps_lock, flags);
+	do {
+		if (ep->ep && ep->req)
+			usb_ep_free_request(ep->ep, ep->req);
+		ep->req = NULL;
+		++ep;
+	} while (--count);
+	spin_unlock_irqrestore(&func->ffs->eps_lock, flags);
+
+	ffs_data_put(func->ffs);
+
+	kfree(func->eps);
+	/*
+	 * eps and interfaces_nums are allocated in the same chunk so
+	 * only one free is required.  Descriptors are also allocated
+	 * in the same chunk.
+	 */
+
+	kfree(func);
+}
 
 static void ffs_func_eps_disable(struct ffs_function *func)
 {
@@ -2888,6 +2956,24 @@ static int ffs_func_bind(struct usb_configuration *c,
 
 /* Other USB function hooks *************************************************/
 
+static void old_ffs_func_unbind(struct usb_configuration *c,
+				struct usb_function *f)
+{
+	struct ffs_function *func = ffs_func_from_usb(f);
+	struct ffs_data *ffs = func->ffs;
+
+	ENTER();
+
+	if (ffs->func == func) {
+		ffs_func_eps_disable(func);
+		ffs->func = NULL;
+	}
+
+	ffs_event_add(ffs, FUNCTIONFS_UNBIND);
+
+	ffs_func_free(func);
+}
+
 static int ffs_func_set_alt(struct usb_function *f,
 			    unsigned interface, unsigned alt)
 {
@@ -3400,6 +3486,7 @@ done:
 static void ffs_closed(struct ffs_data *ffs)
 {
 	struct ffs_dev *ffs_obj;
+	struct f_fs_opts *opts;
 
 	ENTER();
 	ffs_dev_lock();
@@ -3413,8 +3500,13 @@ static void ffs_closed(struct ffs_data *ffs)
 	if (ffs_obj->ffs_closed_callback)
 		ffs_obj->ffs_closed_callback(ffs);
 
-	if (!ffs_obj->opts || ffs_obj->opts->no_configfs
-	    || !ffs_obj->opts->func_inst.group.cg_item.ci_parent)
+	if (ffs_obj->opts)
+		opts = ffs_obj->opts;
+	else
+		goto done;
+
+	if (opts->no_configfs || !opts->func_inst.group.cg_item.ci_parent
+	    || !atomic_read(&opts->func_inst.group.cg_item.ci_kref.refcount))
 		goto done;
 
 	unregister_gadget_item(ffs_obj->opts->
diff --git a/drivers/usb/gadget/function/f_mtp.c b/drivers/usb/gadget/function/f_mtp.c
new file mode 100644
index 00000000000..79053fda286
--- /dev/null
+++ b/drivers/usb/gadget/function/f_mtp.c
@@ -0,0 +1,1473 @@
+/*
+ * Gadget Function Driver for MTP
+ *
+ * Copyright (C) 2010 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+/* #define DEBUG */
+/* #define VERBOSE_DEBUG */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/poll.h>
+#include <linux/delay.h>
+#include <linux/wait.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+
+#include <linux/types.h>
+#include <linux/file.h>
+#include <linux/device.h>
+#include <linux/miscdevice.h>
+
+#include <linux/usb.h>
+#include <linux/usb_usual.h>
+#include <linux/usb/ch9.h>
+#include <linux/usb/f_mtp.h>
+#include <linux/configfs.h>
+#include <linux/usb/composite.h>
+
+#include "configfs.h"
+
+#define MTP_BULK_BUFFER_SIZE       16384
+#define INTR_BUFFER_SIZE           28
+#define MAX_INST_NAME_LEN          40
+
+/* String IDs */
+#define INTERFACE_STRING_INDEX	0
+
+/* values for mtp_dev.state */
+#define STATE_OFFLINE               0   /* initial state, disconnected */
+#define STATE_READY                 1   /* ready for userspace calls */
+#define STATE_BUSY                  2   /* processing userspace calls */
+#define STATE_CANCELED              3   /* transaction canceled by host */
+#define STATE_ERROR                 4   /* error from completion routine */
+
+/* number of tx and rx requests to allocate */
+#define TX_REQ_MAX 4
+#define RX_REQ_MAX 2
+#define INTR_REQ_MAX 5
+
+/* ID for Microsoft MTP OS String */
+#define MTP_OS_STRING_ID   0xEE
+
+/* MTP class reqeusts */
+#define MTP_REQ_CANCEL              0x64
+#define MTP_REQ_GET_EXT_EVENT_DATA  0x65
+#define MTP_REQ_RESET               0x66
+#define MTP_REQ_GET_DEVICE_STATUS   0x67
+
+/* constants for device status */
+#define MTP_RESPONSE_OK             0x2001
+#define MTP_RESPONSE_DEVICE_BUSY    0x2019
+#define DRIVER_NAME "mtp"
+
+static const char mtp_shortname[] = DRIVER_NAME "_usb";
+
+struct mtp_dev {
+	struct usb_function function;
+	struct usb_composite_dev *cdev;
+	spinlock_t lock;
+
+	struct usb_ep *ep_in;
+	struct usb_ep *ep_out;
+	struct usb_ep *ep_intr;
+
+	int state;
+
+	/* synchronize access to our device file */
+	atomic_t open_excl;
+	/* to enforce only one ioctl at a time */
+	atomic_t ioctl_excl;
+
+	struct list_head tx_idle;
+	struct list_head intr_idle;
+
+	wait_queue_head_t read_wq;
+	wait_queue_head_t write_wq;
+	wait_queue_head_t intr_wq;
+	struct usb_request *rx_req[RX_REQ_MAX];
+	int rx_done;
+
+	/* for processing MTP_SEND_FILE, MTP_RECEIVE_FILE and
+	 * MTP_SEND_FILE_WITH_HEADER ioctls on a work queue
+	 */
+	struct workqueue_struct *wq;
+	struct work_struct send_file_work;
+	struct work_struct receive_file_work;
+	struct file *xfer_file;
+	loff_t xfer_file_offset;
+	int64_t xfer_file_length;
+	unsigned xfer_send_header;
+	uint16_t xfer_command;
+	uint32_t xfer_transaction_id;
+	int xfer_result;
+};
+
+static struct usb_interface_descriptor mtp_interface_desc = {
+	.bLength                = USB_DT_INTERFACE_SIZE,
+	.bDescriptorType        = USB_DT_INTERFACE,
+	.bInterfaceNumber       = 0,
+	.bNumEndpoints          = 3,
+	.bInterfaceClass        = USB_CLASS_VENDOR_SPEC,
+	.bInterfaceSubClass     = USB_SUBCLASS_VENDOR_SPEC,
+	.bInterfaceProtocol     = 0,
+};
+
+static struct usb_interface_descriptor ptp_interface_desc = {
+	.bLength                = USB_DT_INTERFACE_SIZE,
+	.bDescriptorType        = USB_DT_INTERFACE,
+	.bInterfaceNumber       = 0,
+	.bNumEndpoints          = 3,
+	.bInterfaceClass        = USB_CLASS_STILL_IMAGE,
+	.bInterfaceSubClass     = 1,
+	.bInterfaceProtocol     = 1,
+};
+
+static struct usb_endpoint_descriptor mtp_highspeed_in_desc = {
+	.bLength                = USB_DT_ENDPOINT_SIZE,
+	.bDescriptorType        = USB_DT_ENDPOINT,
+	.bEndpointAddress       = USB_DIR_IN,
+	.bmAttributes           = USB_ENDPOINT_XFER_BULK,
+	.wMaxPacketSize         = __constant_cpu_to_le16(512),
+};
+
+static struct usb_endpoint_descriptor mtp_highspeed_out_desc = {
+	.bLength                = USB_DT_ENDPOINT_SIZE,
+	.bDescriptorType        = USB_DT_ENDPOINT,
+	.bEndpointAddress       = USB_DIR_OUT,
+	.bmAttributes           = USB_ENDPOINT_XFER_BULK,
+	.wMaxPacketSize         = __constant_cpu_to_le16(512),
+};
+
+static struct usb_endpoint_descriptor mtp_fullspeed_in_desc = {
+	.bLength                = USB_DT_ENDPOINT_SIZE,
+	.bDescriptorType        = USB_DT_ENDPOINT,
+	.bEndpointAddress       = USB_DIR_IN,
+	.bmAttributes           = USB_ENDPOINT_XFER_BULK,
+};
+
+static struct usb_endpoint_descriptor mtp_fullspeed_out_desc = {
+	.bLength                = USB_DT_ENDPOINT_SIZE,
+	.bDescriptorType        = USB_DT_ENDPOINT,
+	.bEndpointAddress       = USB_DIR_OUT,
+	.bmAttributes           = USB_ENDPOINT_XFER_BULK,
+};
+
+static struct usb_endpoint_descriptor mtp_intr_desc = {
+	.bLength                = USB_DT_ENDPOINT_SIZE,
+	.bDescriptorType        = USB_DT_ENDPOINT,
+	.bEndpointAddress       = USB_DIR_IN,
+	.bmAttributes           = USB_ENDPOINT_XFER_INT,
+	.wMaxPacketSize         = __constant_cpu_to_le16(INTR_BUFFER_SIZE),
+	.bInterval              = 6,
+};
+
+static struct usb_descriptor_header *fs_mtp_descs[] = {
+	(struct usb_descriptor_header *) &mtp_interface_desc,
+	(struct usb_descriptor_header *) &mtp_fullspeed_in_desc,
+	(struct usb_descriptor_header *) &mtp_fullspeed_out_desc,
+	(struct usb_descriptor_header *) &mtp_intr_desc,
+	NULL,
+};
+
+static struct usb_descriptor_header *hs_mtp_descs[] = {
+	(struct usb_descriptor_header *) &mtp_interface_desc,
+	(struct usb_descriptor_header *) &mtp_highspeed_in_desc,
+	(struct usb_descriptor_header *) &mtp_highspeed_out_desc,
+	(struct usb_descriptor_header *) &mtp_intr_desc,
+	NULL,
+};
+
+static struct usb_descriptor_header *fs_ptp_descs[] = {
+	(struct usb_descriptor_header *) &ptp_interface_desc,
+	(struct usb_descriptor_header *) &mtp_fullspeed_in_desc,
+	(struct usb_descriptor_header *) &mtp_fullspeed_out_desc,
+	(struct usb_descriptor_header *) &mtp_intr_desc,
+	NULL,
+};
+
+static struct usb_descriptor_header *hs_ptp_descs[] = {
+	(struct usb_descriptor_header *) &ptp_interface_desc,
+	(struct usb_descriptor_header *) &mtp_highspeed_in_desc,
+	(struct usb_descriptor_header *) &mtp_highspeed_out_desc,
+	(struct usb_descriptor_header *) &mtp_intr_desc,
+	NULL,
+};
+
+static struct usb_string mtp_string_defs[] = {
+	/* Naming interface "MTP" so libmtp will recognize us */
+	[INTERFACE_STRING_INDEX].s	= "MTP",
+	{  },	/* end of list */
+};
+
+static struct usb_gadget_strings mtp_string_table = {
+	.language		= 0x0409,	/* en-US */
+	.strings		= mtp_string_defs,
+};
+
+static struct usb_gadget_strings *mtp_strings[] = {
+	&mtp_string_table,
+	NULL,
+};
+
+/* Microsoft MTP OS String */
+static u8 mtp_os_string[] = {
+	18, /* sizeof(mtp_os_string) */
+	USB_DT_STRING,
+	/* Signature field: "MSFT100" */
+	'M', 0, 'S', 0, 'F', 0, 'T', 0, '1', 0, '0', 0, '0', 0,
+	/* vendor code */
+	1,
+	/* padding */
+	0
+};
+
+/* Microsoft Extended Configuration Descriptor Header Section */
+struct mtp_ext_config_desc_header {
+	__le32	dwLength;
+	__u16	bcdVersion;
+	__le16	wIndex;
+	__u8	bCount;
+	__u8	reserved[7];
+};
+
+/* Microsoft Extended Configuration Descriptor Function Section */
+struct mtp_ext_config_desc_function {
+	__u8	bFirstInterfaceNumber;
+	__u8	bInterfaceCount;
+	__u8	compatibleID[8];
+	__u8	subCompatibleID[8];
+	__u8	reserved[6];
+};
+
+/* MTP Extended Configuration Descriptor */
+struct {
+	struct mtp_ext_config_desc_header	header;
+	struct mtp_ext_config_desc_function    function;
+} mtp_ext_config_desc = {
+	.header = {
+		.dwLength = __constant_cpu_to_le32(sizeof(mtp_ext_config_desc)),
+		.bcdVersion = __constant_cpu_to_le16(0x0100),
+		.wIndex = __constant_cpu_to_le16(4),
+		.bCount = __constant_cpu_to_le16(1),
+	},
+	.function = {
+		.bFirstInterfaceNumber = 0,
+		.bInterfaceCount = 1,
+		.compatibleID = { 'M', 'T', 'P' },
+	},
+};
+
+struct mtp_device_status {
+	__le16	wLength;
+	__le16	wCode;
+};
+
+struct mtp_data_header {
+	/* length of packet, including this header */
+	__le32	length;
+	/* container type (2 for data packet) */
+	__le16	type;
+	/* MTP command code */
+	__le16	command;
+	/* MTP transaction ID */
+	__le32	transaction_id;
+};
+
+struct mtp_instance {
+	struct usb_function_instance func_inst;
+	const char *name;
+	struct mtp_dev *dev;
+};
+
+/* temporary variable used between mtp_open() and mtp_gadget_bind() */
+static struct mtp_dev *_mtp_dev;
+
+static inline struct mtp_dev *func_to_mtp(struct usb_function *f)
+{
+	return container_of(f, struct mtp_dev, function);
+}
+
+static struct usb_request *mtp_request_new(struct usb_ep *ep, int buffer_size)
+{
+	struct usb_request *req = usb_ep_alloc_request(ep, GFP_KERNEL);
+	if (!req)
+		return NULL;
+
+	/* now allocate buffers for the requests */
+	req->buf = kmalloc(buffer_size, GFP_KERNEL);
+	if (!req->buf) {
+		usb_ep_free_request(ep, req);
+		return NULL;
+	}
+
+	return req;
+}
+
+static void mtp_request_free(struct usb_request *req, struct usb_ep *ep)
+{
+	if (req) {
+		kfree(req->buf);
+		usb_ep_free_request(ep, req);
+	}
+}
+
+static inline int mtp_lock(atomic_t *excl)
+{
+	if (atomic_inc_return(excl) == 1) {
+		return 0;
+	} else {
+		atomic_dec(excl);
+		return -1;
+	}
+}
+
+static inline void mtp_unlock(atomic_t *excl)
+{
+	atomic_dec(excl);
+}
+
+/* add a request to the tail of a list */
+static void mtp_req_put(struct mtp_dev *dev, struct list_head *head,
+		struct usb_request *req)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->lock, flags);
+	list_add_tail(&req->list, head);
+	spin_unlock_irqrestore(&dev->lock, flags);
+}
+
+/* remove a request from the head of a list */
+static struct usb_request
+*mtp_req_get(struct mtp_dev *dev, struct list_head *head)
+{
+	unsigned long flags;
+	struct usb_request *req;
+
+	spin_lock_irqsave(&dev->lock, flags);
+	if (list_empty(head)) {
+		req = 0;
+	} else {
+		req = list_first_entry(head, struct usb_request, list);
+		list_del(&req->list);
+	}
+	spin_unlock_irqrestore(&dev->lock, flags);
+	return req;
+}
+
+static void mtp_complete_in(struct usb_ep *ep, struct usb_request *req)
+{
+	struct mtp_dev *dev = _mtp_dev;
+
+	if (req->status != 0)
+		dev->state = STATE_ERROR;
+
+	mtp_req_put(dev, &dev->tx_idle, req);
+
+	wake_up(&dev->write_wq);
+}
+
+static void mtp_complete_out(struct usb_ep *ep, struct usb_request *req)
+{
+	struct mtp_dev *dev = _mtp_dev;
+
+	dev->rx_done = 1;
+	if (req->status != 0)
+		dev->state = STATE_ERROR;
+
+	wake_up(&dev->read_wq);
+}
+
+static void mtp_complete_intr(struct usb_ep *ep, struct usb_request *req)
+{
+	struct mtp_dev *dev = _mtp_dev;
+
+	if (req->status != 0)
+		dev->state = STATE_ERROR;
+
+	mtp_req_put(dev, &dev->intr_idle, req);
+
+	wake_up(&dev->intr_wq);
+}
+
+static int mtp_create_bulk_endpoints(struct mtp_dev *dev,
+				struct usb_endpoint_descriptor *in_desc,
+				struct usb_endpoint_descriptor *out_desc,
+				struct usb_endpoint_descriptor *intr_desc)
+{
+	struct usb_composite_dev *cdev = dev->cdev;
+	struct usb_request *req;
+	struct usb_ep *ep;
+	int i;
+
+	DBG(cdev, "create_bulk_endpoints dev: %p\n", dev);
+
+	ep = usb_ep_autoconfig(cdev->gadget, in_desc);
+	if (!ep) {
+		DBG(cdev, "usb_ep_autoconfig for ep_in failed\n");
+		return -ENODEV;
+	}
+	DBG(cdev, "usb_ep_autoconfig for ep_in got %s\n", ep->name);
+	ep->driver_data = dev;		/* claim the endpoint */
+	dev->ep_in = ep;
+
+	ep = usb_ep_autoconfig(cdev->gadget, out_desc);
+	if (!ep) {
+		DBG(cdev, "usb_ep_autoconfig for ep_out failed\n");
+		return -ENODEV;
+	}
+	DBG(cdev, "usb_ep_autoconfig for mtp ep_out got %s\n", ep->name);
+	ep->driver_data = dev;		/* claim the endpoint */
+	dev->ep_out = ep;
+
+	ep = usb_ep_autoconfig(cdev->gadget, intr_desc);
+	if (!ep) {
+		DBG(cdev, "usb_ep_autoconfig for ep_intr failed\n");
+		return -ENODEV;
+	}
+	DBG(cdev, "usb_ep_autoconfig for mtp ep_intr got %s\n", ep->name);
+	ep->driver_data = dev;		/* claim the endpoint */
+	dev->ep_intr = ep;
+
+	/* now allocate requests for our endpoints */
+	for (i = 0; i < TX_REQ_MAX; i++) {
+		req = mtp_request_new(dev->ep_in, MTP_BULK_BUFFER_SIZE);
+		if (!req)
+			goto fail;
+		req->complete = mtp_complete_in;
+		mtp_req_put(dev, &dev->tx_idle, req);
+	}
+	for (i = 0; i < RX_REQ_MAX; i++) {
+		req = mtp_request_new(dev->ep_out, MTP_BULK_BUFFER_SIZE);
+		if (!req)
+			goto fail;
+		req->complete = mtp_complete_out;
+		dev->rx_req[i] = req;
+	}
+	for (i = 0; i < INTR_REQ_MAX; i++) {
+		req = mtp_request_new(dev->ep_intr, INTR_BUFFER_SIZE);
+		if (!req)
+			goto fail;
+		req->complete = mtp_complete_intr;
+		mtp_req_put(dev, &dev->intr_idle, req);
+	}
+
+	return 0;
+
+fail:
+	pr_err("mtp_bind() could not allocate requests\n");
+	return -1;
+}
+
+static ssize_t mtp_read(struct file *fp, char __user *buf,
+	size_t count, loff_t *pos)
+{
+	struct mtp_dev *dev = fp->private_data;
+	struct usb_composite_dev *cdev = dev->cdev;
+	struct usb_request *req;
+	ssize_t r = count;
+	unsigned xfer;
+	int ret = 0;
+
+	DBG(cdev, "mtp_read(%zu)\n", count);
+
+	if (count > MTP_BULK_BUFFER_SIZE)
+		return -EINVAL;
+
+	/* we will block until we're online */
+	DBG(cdev, "mtp_read: waiting for online state\n");
+	ret = wait_event_interruptible(dev->read_wq,
+		dev->state != STATE_OFFLINE);
+	if (ret < 0) {
+		r = ret;
+		goto done;
+	}
+	spin_lock_irq(&dev->lock);
+	if (dev->state == STATE_CANCELED) {
+		/* report cancelation to userspace */
+		dev->state = STATE_READY;
+		spin_unlock_irq(&dev->lock);
+		return -ECANCELED;
+	}
+	dev->state = STATE_BUSY;
+	spin_unlock_irq(&dev->lock);
+
+requeue_req:
+	/* queue a request */
+	req = dev->rx_req[0];
+	req->length = count;
+	dev->rx_done = 0;
+	ret = usb_ep_queue(dev->ep_out, req, GFP_KERNEL);
+	if (ret < 0) {
+		r = -EIO;
+		goto done;
+	} else {
+		DBG(cdev, "rx %p queue\n", req);
+	}
+
+	/* wait for a request to complete */
+	ret = wait_event_interruptible(dev->read_wq, dev->rx_done);
+	if (ret < 0) {
+		r = ret;
+		usb_ep_dequeue(dev->ep_out, req);
+		goto done;
+	}
+	if (dev->state == STATE_BUSY) {
+		/* If we got a 0-len packet, throw it back and try again. */
+		if (req->actual == 0)
+			goto requeue_req;
+
+		DBG(cdev, "rx %p %d\n", req, req->actual);
+		xfer = (req->actual < count) ? req->actual : count;
+		r = xfer;
+		if (copy_to_user(buf, req->buf, xfer))
+			r = -EFAULT;
+	} else
+		r = -EIO;
+
+done:
+	spin_lock_irq(&dev->lock);
+	if (dev->state == STATE_CANCELED)
+		r = -ECANCELED;
+	else if (dev->state != STATE_OFFLINE)
+		dev->state = STATE_READY;
+	spin_unlock_irq(&dev->lock);
+
+	DBG(cdev, "mtp_read returning %zd\n", r);
+	return r;
+}
+
+static ssize_t mtp_write(struct file *fp, const char __user *buf,
+	size_t count, loff_t *pos)
+{
+	struct mtp_dev *dev = fp->private_data;
+	struct usb_composite_dev *cdev = dev->cdev;
+	struct usb_request *req = 0;
+	ssize_t r = count;
+	unsigned xfer;
+	int sendZLP = 0;
+	int ret;
+
+	DBG(cdev, "mtp_write(%zu)\n", count);
+
+	spin_lock_irq(&dev->lock);
+	if (dev->state == STATE_CANCELED) {
+		/* report cancelation to userspace */
+		dev->state = STATE_READY;
+		spin_unlock_irq(&dev->lock);
+		return -ECANCELED;
+	}
+	if (dev->state == STATE_OFFLINE) {
+		spin_unlock_irq(&dev->lock);
+		return -ENODEV;
+	}
+	dev->state = STATE_BUSY;
+	spin_unlock_irq(&dev->lock);
+
+	/* we need to send a zero length packet to signal the end of transfer
+	 * if the transfer size is aligned to a packet boundary.
+	 */
+	if ((count & (dev->ep_in->maxpacket - 1)) == 0)
+		sendZLP = 1;
+
+	while (count > 0 || sendZLP) {
+		/* so we exit after sending ZLP */
+		if (count == 0)
+			sendZLP = 0;
+
+		if (dev->state != STATE_BUSY) {
+			DBG(cdev, "mtp_write dev->error\n");
+			r = -EIO;
+			break;
+		}
+
+		/* get an idle tx request to use */
+		req = 0;
+		ret = wait_event_interruptible(dev->write_wq,
+			((req = mtp_req_get(dev, &dev->tx_idle))
+				|| dev->state != STATE_BUSY));
+		if (!req) {
+			r = ret;
+			break;
+		}
+
+		if (count > MTP_BULK_BUFFER_SIZE)
+			xfer = MTP_BULK_BUFFER_SIZE;
+		else
+			xfer = count;
+		if (xfer && copy_from_user(req->buf, buf, xfer)) {
+			r = -EFAULT;
+			break;
+		}
+
+		req->length = xfer;
+		ret = usb_ep_queue(dev->ep_in, req, GFP_KERNEL);
+		if (ret < 0) {
+			DBG(cdev, "mtp_write: xfer error %d\n", ret);
+			r = -EIO;
+			break;
+		}
+
+		buf += xfer;
+		count -= xfer;
+
+		/* zero this so we don't try to free it on error exit */
+		req = 0;
+	}
+
+	if (req)
+		mtp_req_put(dev, &dev->tx_idle, req);
+
+	spin_lock_irq(&dev->lock);
+	if (dev->state == STATE_CANCELED)
+		r = -ECANCELED;
+	else if (dev->state != STATE_OFFLINE)
+		dev->state = STATE_READY;
+	spin_unlock_irq(&dev->lock);
+
+	DBG(cdev, "mtp_write returning %zd\n", r);
+	return r;
+}
+
+/* read from a local file and write to USB */
+static void send_file_work(struct work_struct *data)
+{
+	struct mtp_dev *dev = container_of(data, struct mtp_dev,
+						send_file_work);
+	struct usb_composite_dev *cdev = dev->cdev;
+	struct usb_request *req = 0;
+	struct mtp_data_header *header;
+	struct file *filp;
+	loff_t offset;
+	int64_t count;
+	int xfer, ret, hdr_size;
+	int r = 0;
+	int sendZLP = 0;
+
+	/* read our parameters */
+	smp_rmb();
+	filp = dev->xfer_file;
+	offset = dev->xfer_file_offset;
+	count = dev->xfer_file_length;
+
+	DBG(cdev, "send_file_work(%lld %lld)\n", offset, count);
+
+	if (dev->xfer_send_header) {
+		hdr_size = sizeof(struct mtp_data_header);
+		count += hdr_size;
+	} else {
+		hdr_size = 0;
+	}
+
+	/* we need to send a zero length packet to signal the end of transfer
+	 * if the transfer size is aligned to a packet boundary.
+	 */
+	if ((count & (dev->ep_in->maxpacket - 1)) == 0)
+		sendZLP = 1;
+
+	while (count > 0 || sendZLP) {
+		/* so we exit after sending ZLP */
+		if (count == 0)
+			sendZLP = 0;
+
+		/* get an idle tx request to use */
+		req = 0;
+		ret = wait_event_interruptible(dev->write_wq,
+			(req = mtp_req_get(dev, &dev->tx_idle))
+			|| dev->state != STATE_BUSY);
+		if (dev->state == STATE_CANCELED) {
+			r = -ECANCELED;
+			break;
+		}
+		if (!req) {
+			r = ret;
+			break;
+		}
+
+		if (count > MTP_BULK_BUFFER_SIZE)
+			xfer = MTP_BULK_BUFFER_SIZE;
+		else
+			xfer = count;
+
+		if (hdr_size) {
+			/* prepend MTP data header */
+			header = (struct mtp_data_header *)req->buf;
+			header->length = __cpu_to_le32(count);
+			header->type = __cpu_to_le16(2); /* data packet */
+			header->command = __cpu_to_le16(dev->xfer_command);
+			header->transaction_id =
+					__cpu_to_le32(dev->xfer_transaction_id);
+		}
+
+		ret = vfs_read(filp, req->buf + hdr_size, xfer - hdr_size,
+								&offset);
+		if (ret < 0) {
+			r = ret;
+			break;
+		}
+		xfer = ret + hdr_size;
+		hdr_size = 0;
+
+		req->length = xfer;
+		ret = usb_ep_queue(dev->ep_in, req, GFP_KERNEL);
+		if (ret < 0) {
+			DBG(cdev, "send_file_work: xfer error %d\n", ret);
+			dev->state = STATE_ERROR;
+			r = -EIO;
+			break;
+		}
+
+		count -= xfer;
+
+		/* zero this so we don't try to free it on error exit */
+		req = 0;
+	}
+
+	if (req)
+		mtp_req_put(dev, &dev->tx_idle, req);
+
+	DBG(cdev, "send_file_work returning %d\n", r);
+	/* write the result */
+	dev->xfer_result = r;
+	smp_wmb();
+}
+
+/* read from USB and write to a local file */
+static void receive_file_work(struct work_struct *data)
+{
+	struct mtp_dev *dev = container_of(data, struct mtp_dev,
+						receive_file_work);
+	struct usb_composite_dev *cdev = dev->cdev;
+	struct usb_request *read_req = NULL, *write_req = NULL;
+	struct file *filp;
+	loff_t offset;
+	int64_t count;
+	int ret, cur_buf = 0;
+	int r = 0;
+
+	/* read our parameters */
+	smp_rmb();
+	filp = dev->xfer_file;
+	offset = dev->xfer_file_offset;
+	count = dev->xfer_file_length;
+
+	DBG(cdev, "receive_file_work(%lld)\n", count);
+
+	while (count > 0 || write_req) {
+		if (count > 0) {
+			/* queue a request */
+			read_req = dev->rx_req[cur_buf];
+			cur_buf = (cur_buf + 1) % RX_REQ_MAX;
+
+			read_req->length = (count > MTP_BULK_BUFFER_SIZE
+					? MTP_BULK_BUFFER_SIZE : count);
+			dev->rx_done = 0;
+			ret = usb_ep_queue(dev->ep_out, read_req, GFP_KERNEL);
+			if (ret < 0) {
+				r = -EIO;
+				dev->state = STATE_ERROR;
+				break;
+			}
+		}
+
+		if (write_req) {
+			DBG(cdev, "rx %p %d\n", write_req, write_req->actual);
+			ret = vfs_write(filp, write_req->buf, write_req->actual,
+				&offset);
+			DBG(cdev, "vfs_write %d\n", ret);
+			if (ret != write_req->actual) {
+				r = -EIO;
+				dev->state = STATE_ERROR;
+				break;
+			}
+			write_req = NULL;
+		}
+
+		if (read_req) {
+			/* wait for our last read to complete */
+			ret = wait_event_interruptible(dev->read_wq,
+				dev->rx_done || dev->state != STATE_BUSY);
+			if (dev->state == STATE_CANCELED) {
+				r = -ECANCELED;
+				if (!dev->rx_done)
+					usb_ep_dequeue(dev->ep_out, read_req);
+				break;
+			}
+			/* if xfer_file_length is 0xFFFFFFFF, then we read until
+			 * we get a zero length packet
+			 */
+			if (count != 0xFFFFFFFF)
+				count -= read_req->actual;
+			if (read_req->actual < read_req->length) {
+				/*
+				 * short packet is used to signal EOF for
+				 * sizes > 4 gig
+				 */
+				DBG(cdev, "got short packet\n");
+				count = 0;
+			}
+
+			write_req = read_req;
+			read_req = NULL;
+		}
+	}
+
+	DBG(cdev, "receive_file_work returning %d\n", r);
+	/* write the result */
+	dev->xfer_result = r;
+	smp_wmb();
+}
+
+static int mtp_send_event(struct mtp_dev *dev, struct mtp_event *event)
+{
+	struct usb_request *req = NULL;
+	int ret;
+	int length = event->length;
+
+	DBG(dev->cdev, "mtp_send_event(%zu)\n", event->length);
+
+	if (length < 0 || length > INTR_BUFFER_SIZE)
+		return -EINVAL;
+	if (dev->state == STATE_OFFLINE)
+		return -ENODEV;
+
+	ret = wait_event_interruptible_timeout(dev->intr_wq,
+			(req = mtp_req_get(dev, &dev->intr_idle)),
+			msecs_to_jiffies(1000));
+	if (!req)
+		return -ETIME;
+
+	if (copy_from_user(req->buf, (void __user *)event->data, length)) {
+		mtp_req_put(dev, &dev->intr_idle, req);
+		return -EFAULT;
+	}
+	req->length = length;
+	ret = usb_ep_queue(dev->ep_intr, req, GFP_KERNEL);
+	if (ret)
+		mtp_req_put(dev, &dev->intr_idle, req);
+
+	return ret;
+}
+
+static long mtp_ioctl(struct file *fp, unsigned code, unsigned long value)
+{
+	struct mtp_dev *dev = fp->private_data;
+	struct file *filp = NULL;
+	int ret = -EINVAL;
+
+	if (mtp_lock(&dev->ioctl_excl))
+		return -EBUSY;
+
+	switch (code) {
+	case MTP_SEND_FILE:
+	case MTP_RECEIVE_FILE:
+	case MTP_SEND_FILE_WITH_HEADER:
+	{
+		struct mtp_file_range	mfr;
+		struct work_struct *work;
+
+		spin_lock_irq(&dev->lock);
+		if (dev->state == STATE_CANCELED) {
+			/* report cancelation to userspace */
+			dev->state = STATE_READY;
+			spin_unlock_irq(&dev->lock);
+			ret = -ECANCELED;
+			goto out;
+		}
+		if (dev->state == STATE_OFFLINE) {
+			spin_unlock_irq(&dev->lock);
+			ret = -ENODEV;
+			goto out;
+		}
+		dev->state = STATE_BUSY;
+		spin_unlock_irq(&dev->lock);
+
+		if (copy_from_user(&mfr, (void __user *)value, sizeof(mfr))) {
+			ret = -EFAULT;
+			goto fail;
+		}
+		/* hold a reference to the file while we are working with it */
+		filp = fget(mfr.fd);
+		if (!filp) {
+			ret = -EBADF;
+			goto fail;
+		}
+
+		/* write the parameters */
+		dev->xfer_file = filp;
+		dev->xfer_file_offset = mfr.offset;
+		dev->xfer_file_length = mfr.length;
+		smp_wmb();
+
+		if (code == MTP_SEND_FILE_WITH_HEADER) {
+			work = &dev->send_file_work;
+			dev->xfer_send_header = 1;
+			dev->xfer_command = mfr.command;
+			dev->xfer_transaction_id = mfr.transaction_id;
+		} else if (code == MTP_SEND_FILE) {
+			work = &dev->send_file_work;
+			dev->xfer_send_header = 0;
+		} else {
+			work = &dev->receive_file_work;
+		}
+
+		/* We do the file transfer on a work queue so it will run
+		 * in kernel context, which is necessary for vfs_read and
+		 * vfs_write to use our buffers in the kernel address space.
+		 */
+		queue_work(dev->wq, work);
+		/* wait for operation to complete */
+		flush_workqueue(dev->wq);
+		fput(filp);
+
+		/* read the result */
+		smp_rmb();
+		ret = dev->xfer_result;
+		break;
+	}
+	case MTP_SEND_EVENT:
+	{
+		struct mtp_event	event;
+		/* return here so we don't change dev->state below,
+		 * which would interfere with bulk transfer state.
+		 */
+		if (copy_from_user(&event, (void __user *)value, sizeof(event)))
+			ret = -EFAULT;
+		else
+			ret = mtp_send_event(dev, &event);
+		goto out;
+	}
+	}
+
+fail:
+	spin_lock_irq(&dev->lock);
+	if (dev->state == STATE_CANCELED)
+		ret = -ECANCELED;
+	else if (dev->state != STATE_OFFLINE)
+		dev->state = STATE_READY;
+	spin_unlock_irq(&dev->lock);
+out:
+	mtp_unlock(&dev->ioctl_excl);
+	DBG(dev->cdev, "ioctl returning %d\n", ret);
+	return ret;
+}
+
+static int mtp_open(struct inode *ip, struct file *fp)
+{
+	printk(KERN_INFO "mtp_open\n");
+	if (mtp_lock(&_mtp_dev->open_excl))
+		return -EBUSY;
+
+	/* clear any error condition */
+	if (_mtp_dev->state != STATE_OFFLINE)
+		_mtp_dev->state = STATE_READY;
+
+	fp->private_data = _mtp_dev;
+	return 0;
+}
+
+static int mtp_release(struct inode *ip, struct file *fp)
+{
+	printk(KERN_INFO "mtp_release\n");
+
+	mtp_unlock(&_mtp_dev->open_excl);
+	return 0;
+}
+
+/* file operations for /dev/mtp_usb */
+static const struct file_operations mtp_fops = {
+	.owner = THIS_MODULE,
+	.read = mtp_read,
+	.write = mtp_write,
+	.unlocked_ioctl = mtp_ioctl,
+	.open = mtp_open,
+	.release = mtp_release,
+};
+
+static struct miscdevice mtp_device = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = mtp_shortname,
+	.fops = &mtp_fops,
+};
+
+static int mtp_ctrlrequest(struct usb_composite_dev *cdev,
+				const struct usb_ctrlrequest *ctrl)
+{
+	struct mtp_dev *dev = _mtp_dev;
+	int	value = -EOPNOTSUPP;
+	u16	w_index = le16_to_cpu(ctrl->wIndex);
+	u16	w_value = le16_to_cpu(ctrl->wValue);
+	u16	w_length = le16_to_cpu(ctrl->wLength);
+	unsigned long	flags;
+
+	VDBG(cdev, "mtp_ctrlrequest "
+			"%02x.%02x v%04x i%04x l%u\n",
+			ctrl->bRequestType, ctrl->bRequest,
+			w_value, w_index, w_length);
+
+	/* Handle MTP OS string */
+	if (ctrl->bRequestType ==
+			(USB_DIR_IN | USB_TYPE_STANDARD | USB_RECIP_DEVICE)
+			&& ctrl->bRequest == USB_REQ_GET_DESCRIPTOR
+			&& (w_value >> 8) == USB_DT_STRING
+			&& (w_value & 0xFF) == MTP_OS_STRING_ID) {
+		value = (w_length < sizeof(mtp_os_string)
+				? w_length : sizeof(mtp_os_string));
+		memcpy(cdev->req->buf, mtp_os_string, value);
+	} else if ((ctrl->bRequestType & USB_TYPE_MASK) == USB_TYPE_VENDOR) {
+		/* Handle MTP OS descriptor */
+		DBG(cdev, "vendor request: %d index: %d value: %d length: %d\n",
+			ctrl->bRequest, w_index, w_value, w_length);
+
+		if (ctrl->bRequest == 1
+				&& (ctrl->bRequestType & USB_DIR_IN)
+				&& (w_index == 4 || w_index == 5)) {
+			value = (w_length < sizeof(mtp_ext_config_desc) ?
+					w_length : sizeof(mtp_ext_config_desc));
+			memcpy(cdev->req->buf, &mtp_ext_config_desc, value);
+		}
+	} else if ((ctrl->bRequestType & USB_TYPE_MASK) == USB_TYPE_CLASS) {
+		DBG(cdev, "class request: %d index: %d value: %d length: %d\n",
+			ctrl->bRequest, w_index, w_value, w_length);
+
+		if (ctrl->bRequest == MTP_REQ_CANCEL && w_index == 0
+				&& w_value == 0) {
+			DBG(cdev, "MTP_REQ_CANCEL\n");
+
+			spin_lock_irqsave(&dev->lock, flags);
+			if (dev->state == STATE_BUSY) {
+				dev->state = STATE_CANCELED;
+				wake_up(&dev->read_wq);
+				wake_up(&dev->write_wq);
+			}
+			spin_unlock_irqrestore(&dev->lock, flags);
+
+			/* We need to queue a request to read the remaining
+			 *  bytes, but we don't actually need to look at
+			 * the contents.
+			 */
+			value = w_length;
+		} else if (ctrl->bRequest == MTP_REQ_GET_DEVICE_STATUS
+				&& w_index == 0 && w_value == 0) {
+			struct mtp_device_status *status = cdev->req->buf;
+			status->wLength =
+				__constant_cpu_to_le16(sizeof(*status));
+
+			DBG(cdev, "MTP_REQ_GET_DEVICE_STATUS\n");
+			spin_lock_irqsave(&dev->lock, flags);
+			/* device status is "busy" until we report
+			 * the cancelation to userspace
+			 */
+			if (dev->state == STATE_CANCELED)
+				status->wCode =
+					__cpu_to_le16(MTP_RESPONSE_DEVICE_BUSY);
+			else
+				status->wCode =
+					__cpu_to_le16(MTP_RESPONSE_OK);
+			spin_unlock_irqrestore(&dev->lock, flags);
+			value = sizeof(*status);
+		}
+	}
+
+	/* respond with data transfer or status phase? */
+	if (value >= 0) {
+		int rc;
+		cdev->req->zero = value < w_length;
+		cdev->req->length = value;
+		rc = usb_ep_queue(cdev->gadget->ep0, cdev->req, GFP_ATOMIC);
+		if (rc < 0)
+			ERROR(cdev, "%s: response queue error\n", __func__);
+	}
+	return value;
+}
+
+static int
+mtp_function_bind(struct usb_configuration *c, struct usb_function *f)
+{
+	struct usb_composite_dev *cdev = c->cdev;
+	struct mtp_dev	*dev = func_to_mtp(f);
+	int			id;
+	int			ret;
+
+	dev->cdev = cdev;
+	DBG(cdev, "mtp_function_bind dev: %p\n", dev);
+
+	/* allocate interface ID(s) */
+	id = usb_interface_id(c, f);
+	if (id < 0)
+		return id;
+	mtp_interface_desc.bInterfaceNumber = id;
+
+	if (mtp_string_defs[INTERFACE_STRING_INDEX].id == 0) {
+		ret = usb_string_id(c->cdev);
+		if (ret < 0)
+			return ret;
+		mtp_string_defs[INTERFACE_STRING_INDEX].id = ret;
+		mtp_interface_desc.iInterface = ret;
+	}
+	/* allocate endpoints */
+	ret = mtp_create_bulk_endpoints(dev, &mtp_fullspeed_in_desc,
+			&mtp_fullspeed_out_desc, &mtp_intr_desc);
+	if (ret)
+		return ret;
+
+	/* support high speed hardware */
+	if (gadget_is_dualspeed(c->cdev->gadget)) {
+		mtp_highspeed_in_desc.bEndpointAddress =
+			mtp_fullspeed_in_desc.bEndpointAddress;
+		mtp_highspeed_out_desc.bEndpointAddress =
+			mtp_fullspeed_out_desc.bEndpointAddress;
+	}
+
+	DBG(cdev, "%s speed %s: IN/%s, OUT/%s\n",
+			gadget_is_dualspeed(c->cdev->gadget) ? "dual" : "full",
+			f->name, dev->ep_in->name, dev->ep_out->name);
+	return 0;
+}
+
+static void
+mtp_function_unbind(struct usb_configuration *c, struct usb_function *f)
+{
+	struct mtp_dev	*dev = func_to_mtp(f);
+	struct usb_request *req;
+	int i;
+
+	mtp_string_defs[INTERFACE_STRING_INDEX].id = 0;
+	while ((req = mtp_req_get(dev, &dev->tx_idle)))
+		mtp_request_free(req, dev->ep_in);
+	for (i = 0; i < RX_REQ_MAX; i++)
+		mtp_request_free(dev->rx_req[i], dev->ep_out);
+	while ((req = mtp_req_get(dev, &dev->intr_idle)))
+		mtp_request_free(req, dev->ep_intr);
+	dev->state = STATE_OFFLINE;
+}
+
+static int mtp_function_set_alt(struct usb_function *f,
+		unsigned intf, unsigned alt)
+{
+	struct mtp_dev	*dev = func_to_mtp(f);
+	struct usb_composite_dev *cdev = f->config->cdev;
+	int ret;
+
+	DBG(cdev, "mtp_function_set_alt intf: %d alt: %d\n", intf, alt);
+
+	ret = config_ep_by_speed(cdev->gadget, f, dev->ep_in);
+	if (ret)
+		return ret;
+
+	ret = usb_ep_enable(dev->ep_in);
+	if (ret)
+		return ret;
+
+	ret = config_ep_by_speed(cdev->gadget, f, dev->ep_out);
+	if (ret)
+		return ret;
+
+	ret = usb_ep_enable(dev->ep_out);
+	if (ret) {
+		usb_ep_disable(dev->ep_in);
+		return ret;
+	}
+
+	ret = config_ep_by_speed(cdev->gadget, f, dev->ep_intr);
+	if (ret)
+		return ret;
+
+	ret = usb_ep_enable(dev->ep_intr);
+	if (ret) {
+		usb_ep_disable(dev->ep_out);
+		usb_ep_disable(dev->ep_in);
+		return ret;
+	}
+	dev->state = STATE_READY;
+
+	/* readers may be blocked waiting for us to go online */
+	wake_up(&dev->read_wq);
+	return 0;
+}
+
+static void mtp_function_disable(struct usb_function *f)
+{
+	struct mtp_dev	*dev = func_to_mtp(f);
+	struct usb_composite_dev	*cdev = dev->cdev;
+
+	DBG(cdev, "mtp_function_disable\n");
+	dev->state = STATE_OFFLINE;
+	usb_ep_disable(dev->ep_in);
+	usb_ep_disable(dev->ep_out);
+	usb_ep_disable(dev->ep_intr);
+
+	/* readers may be blocked waiting for us to go online */
+	wake_up(&dev->read_wq);
+
+	VDBG(cdev, "%s disabled\n", dev->function.name);
+}
+
+static int __maybe_unused mtp_bind_config(struct usb_configuration *c, bool ptp_config)
+{
+	struct mtp_dev *dev = _mtp_dev;
+	int ret = 0;
+
+	printk(KERN_INFO "mtp_bind_config\n");
+
+	/* allocate a string ID for our interface */
+	if (mtp_string_defs[INTERFACE_STRING_INDEX].id == 0) {
+		ret = usb_string_id(c->cdev);
+		if (ret < 0)
+			return ret;
+		mtp_string_defs[INTERFACE_STRING_INDEX].id = ret;
+		mtp_interface_desc.iInterface = ret;
+	}
+
+	dev->cdev = c->cdev;
+	dev->function.name = DRIVER_NAME;
+	dev->function.strings = mtp_strings;
+	if (ptp_config) {
+		dev->function.fs_descriptors = fs_ptp_descs;
+		dev->function.hs_descriptors = hs_ptp_descs;
+	} else {
+		dev->function.fs_descriptors = fs_mtp_descs;
+		dev->function.hs_descriptors = hs_mtp_descs;
+	}
+	dev->function.bind = mtp_function_bind;
+	dev->function.unbind = mtp_function_unbind;
+	dev->function.set_alt = mtp_function_set_alt;
+	dev->function.disable = mtp_function_disable;
+
+	return usb_add_function(c, &dev->function);
+}
+
+static int __mtp_setup(struct mtp_instance *fi_mtp)
+{
+	struct mtp_dev *dev;
+	int ret;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+
+	if (fi_mtp != NULL)
+		fi_mtp->dev = dev;
+
+	if (!dev)
+		return -ENOMEM;
+
+	spin_lock_init(&dev->lock);
+	init_waitqueue_head(&dev->read_wq);
+	init_waitqueue_head(&dev->write_wq);
+	init_waitqueue_head(&dev->intr_wq);
+	atomic_set(&dev->open_excl, 0);
+	atomic_set(&dev->ioctl_excl, 0);
+	INIT_LIST_HEAD(&dev->tx_idle);
+	INIT_LIST_HEAD(&dev->intr_idle);
+
+	dev->wq = create_singlethread_workqueue("f_mtp");
+	if (!dev->wq) {
+		ret = -ENOMEM;
+		goto err1;
+	}
+	INIT_WORK(&dev->send_file_work, send_file_work);
+	INIT_WORK(&dev->receive_file_work, receive_file_work);
+
+	_mtp_dev = dev;
+
+	ret = misc_register(&mtp_device);
+	if (ret)
+		goto err2;
+
+	return 0;
+
+err2:
+	destroy_workqueue(dev->wq);
+err1:
+	_mtp_dev = NULL;
+	kfree(dev);
+	printk(KERN_ERR "mtp gadget driver failed to initialize\n");
+	return ret;
+}
+
+static int __maybe_unused mtp_setup(void)
+{
+	return __mtp_setup(NULL);
+}
+
+static int mtp_setup_configfs(struct mtp_instance *fi_mtp)
+{
+	return __mtp_setup(fi_mtp);
+}
+
+
+static void mtp_cleanup(void)
+{
+	struct mtp_dev *dev = _mtp_dev;
+
+	if (!dev)
+		return;
+
+	misc_deregister(&mtp_device);
+	destroy_workqueue(dev->wq);
+	_mtp_dev = NULL;
+	kfree(dev);
+}
+
+static struct mtp_instance *to_mtp_instance(struct config_item *item)
+{
+	return container_of(to_config_group(item), struct mtp_instance,
+		func_inst.group);
+}
+
+static void mtp_attr_release(struct config_item *item)
+{
+	struct mtp_instance *fi_mtp = to_mtp_instance(item);
+	usb_put_function_instance(&fi_mtp->func_inst);
+}
+
+static struct configfs_item_operations mtp_item_ops = {
+	.release        = mtp_attr_release,
+};
+
+static struct config_item_type mtp_func_type = {
+	.ct_item_ops    = &mtp_item_ops,
+	.ct_owner       = THIS_MODULE,
+};
+
+
+static struct mtp_instance *to_fi_mtp(struct usb_function_instance *fi)
+{
+	return container_of(fi, struct mtp_instance, func_inst);
+}
+
+static int mtp_set_inst_name(struct usb_function_instance *fi, const char *name)
+{
+	struct mtp_instance *fi_mtp;
+	char *ptr;
+	int name_len;
+
+	name_len = strlen(name) + 1;
+	if (name_len > MAX_INST_NAME_LEN)
+		return -ENAMETOOLONG;
+
+	ptr = kstrndup(name, name_len, GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	fi_mtp = to_fi_mtp(fi);
+	fi_mtp->name = ptr;
+
+	return 0;
+}
+
+static void mtp_free_inst(struct usb_function_instance *fi)
+{
+	struct mtp_instance *fi_mtp;
+
+	fi_mtp = to_fi_mtp(fi);
+	kfree(fi_mtp->name);
+	mtp_cleanup();
+	kfree(fi_mtp);
+}
+
+struct usb_function_instance *alloc_inst_mtp_ptp(bool mtp_config)
+{
+	struct mtp_instance *fi_mtp;
+	int ret = 0;
+
+	fi_mtp = kzalloc(sizeof(*fi_mtp), GFP_KERNEL);
+	if (!fi_mtp)
+		return ERR_PTR(-ENOMEM);
+	fi_mtp->func_inst.set_inst_name = mtp_set_inst_name;
+	fi_mtp->func_inst.free_func_inst = mtp_free_inst;
+
+	if (mtp_config) {
+		ret = mtp_setup_configfs(fi_mtp);
+		if (ret) {
+			kfree(fi_mtp);
+			pr_err("Error setting MTP\n");
+			return ERR_PTR(ret);
+		}
+	} else
+		fi_mtp->dev = _mtp_dev;
+
+	config_group_init_type_name(&fi_mtp->func_inst.group,
+					"", &mtp_func_type);
+
+	return  &fi_mtp->func_inst;
+}
+EXPORT_SYMBOL_GPL(alloc_inst_mtp_ptp);
+
+static struct usb_function_instance *mtp_alloc_inst(void)
+{
+		return alloc_inst_mtp_ptp(true);
+}
+
+static int mtp_ctrlreq_configfs(struct usb_function *f,
+				const struct usb_ctrlrequest *ctrl)
+{
+	return mtp_ctrlrequest(f->config->cdev, ctrl);
+}
+
+static void mtp_free(struct usb_function *f)
+{
+	/*NO-OP: no function specific resource allocation in mtp_alloc*/
+}
+
+struct usb_function *function_alloc_mtp_ptp(struct usb_function_instance *fi,
+					bool mtp_config)
+{
+	struct mtp_instance *fi_mtp = to_fi_mtp(fi);
+	struct mtp_dev *dev;
+
+	/*
+	 * PTP piggybacks on MTP function so make sure we have
+	 * created MTP function before we associate this PTP
+	 * function with a gadget configuration.
+	 */
+	if (fi_mtp->dev == NULL) {
+		pr_err("Error: Create MTP function before linking"
+				" PTP function with a gadget configuration\n");
+		pr_err("\t1: Delete existing PTP function if any\n");
+		pr_err("\t2: Create MTP function\n");
+		pr_err("\t3: Create and symlink PTP function"
+				" with a gadget configuration\n");
+		return NULL;
+	}
+
+	dev = fi_mtp->dev;
+	dev->function.name = DRIVER_NAME;
+	dev->function.strings = mtp_strings;
+	if (mtp_config) {
+		dev->function.fs_descriptors = fs_mtp_descs;
+		dev->function.hs_descriptors = hs_mtp_descs;
+	} else {
+		dev->function.fs_descriptors = fs_ptp_descs;
+		dev->function.hs_descriptors = hs_ptp_descs;
+	}
+	dev->function.bind = mtp_function_bind;
+	dev->function.unbind = mtp_function_unbind;
+	dev->function.set_alt = mtp_function_set_alt;
+	dev->function.disable = mtp_function_disable;
+	dev->function.setup = mtp_ctrlreq_configfs;
+	dev->function.free_func = mtp_free;
+
+	return &dev->function;
+}
+EXPORT_SYMBOL_GPL(function_alloc_mtp_ptp);
+
+static struct usb_function *mtp_alloc(struct usb_function_instance *fi)
+{
+	return function_alloc_mtp_ptp(fi, true);
+}
+
+DECLARE_USB_FUNCTION_INIT(mtp, mtp_alloc_inst, mtp_alloc);
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/gadget/function/f_mtp.h b/drivers/usb/gadget/function/f_mtp.h
new file mode 100644
index 00000000000..7adb1ff08ef
--- /dev/null
+++ b/drivers/usb/gadget/function/f_mtp.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) 2014 Google, Inc.
+ * Author: Badhri Jagan Sridharan <badhri@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+extern struct usb_function_instance *alloc_inst_mtp_ptp(bool mtp_config);
+extern struct usb_function *function_alloc_mtp_ptp(
+			struct usb_function_instance *fi, bool mtp_config);
diff --git a/drivers/usb/gadget/function/f_ptp.c b/drivers/usb/gadget/function/f_ptp.c
new file mode 100644
index 00000000000..da3e4d53e08
--- /dev/null
+++ b/drivers/usb/gadget/function/f_ptp.c
@@ -0,0 +1,38 @@
+/*
+ * Gadget Function Driver for PTP
+ *
+ * Copyright (C) 2014 Google, Inc.
+ * Author: Badhri Jagan Sridharan <badhri@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+
+#include <linux/configfs.h>
+#include <linux/usb/composite.h>
+
+#include "f_mtp.h"
+
+static struct usb_function_instance *ptp_alloc_inst(void)
+{
+	return alloc_inst_mtp_ptp(false);
+}
+
+static struct usb_function *ptp_alloc(struct usb_function_instance *fi)
+{
+	return function_alloc_mtp_ptp(fi, false);
+}
+
+DECLARE_USB_FUNCTION_INIT(ptp, ptp_alloc_inst, ptp_alloc);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Badhri Jagan Sridharan");
diff --git a/drivers/usb/gadget/function/f_rndis.c b/drivers/usb/gadget/function/f_rndis.c
index f13fc6a5856..f60ec148d70 100644
--- a/drivers/usb/gadget/function/f_rndis.c
+++ b/drivers/usb/gadget/function/f_rndis.c
@@ -70,6 +70,16 @@
  *   - MS-Windows drivers sometimes emit undocumented requests.
  */
 
+static unsigned int rndis_dl_max_pkt_per_xfer = 3;
+module_param(rndis_dl_max_pkt_per_xfer, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(rndis_dl_max_pkt_per_xfer,
+	"Maximum packets per transfer for DL aggregation");
+
+static unsigned int rndis_ul_max_pkt_per_xfer = 3;
+module_param(rndis_ul_max_pkt_per_xfer, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(rndis_ul_max_pkt_per_xfer,
+       "Maximum packets per transfer for UL aggregation");
+
 struct f_rndis {
 	struct gether			port;
 	u8				ctrl_id, data_id;
@@ -451,6 +461,7 @@ static void rndis_command_complete(struct usb_ep *ep, struct usb_request *req)
 {
 	struct f_rndis			*rndis = req->context;
 	int				status;
+	rndis_init_msg_type		*buf;
 
 	/* received RNDIS command from USB_CDC_SEND_ENCAPSULATED_COMMAND */
 //	spin_lock(&dev->lock);
@@ -458,6 +469,21 @@ static void rndis_command_complete(struct usb_ep *ep, struct usb_request *req)
 	if (status < 0)
 		pr_err("RNDIS command error %d, %d/%d\n",
 			status, req->actual, req->length);
+
+	buf = (rndis_init_msg_type *)req->buf;
+
+	if (buf->MessageType == RNDIS_MSG_INIT) {
+		if (buf->MaxTransferSize > 2048)
+			rndis->port.multi_pkt_xfer = 1;
+		else
+			rndis->port.multi_pkt_xfer = 0;
+		pr_info("%s: MaxTransferSize: %d : Multi_pkt_txr: %s\n",
+				__func__, buf->MaxTransferSize,
+				rndis->port.multi_pkt_xfer ? "enabled" :
+							    "disabled");
+		if (rndis_dl_max_pkt_per_xfer <= 1)
+			rndis->port.multi_pkt_xfer = 0;
+	}
 //	spin_unlock(&dev->lock);
 }
 
@@ -799,6 +825,7 @@ rndis_bind(struct usb_configuration *c, struct usb_function *f)
 
 	rndis_set_param_medium(rndis->config, RNDIS_MEDIUM_802_3, 0);
 	rndis_set_host_mac(rndis->config, rndis->ethaddr);
+	rndis_set_max_pkt_xfer(rndis->config, rndis_ul_max_pkt_per_xfer);
 
 	if (rndis->manufacturer && rndis->vendorID &&
 			rndis_set_param_vendor(rndis->config, rndis->vendorID,
@@ -843,6 +870,62 @@ fail:
 	return status;
 }
 
+static void
+rndis_old_unbind(struct usb_configuration *c, struct usb_function *f)
+{
+	struct f_rndis          *rndis = func_to_rndis(f);
+
+	rndis_deregister(rndis->config);
+
+	usb_free_all_descriptors(f);
+
+	kfree(rndis->notify_req->buf);
+	usb_ep_free_request(rndis->notify, rndis->notify_req);
+
+	kfree(rndis);
+}
+
+int
+rndis_bind_config_vendor(struct usb_configuration *c, u8 ethaddr[ETH_ALEN],
+		u32 vendorID, const char *manufacturer, struct eth_dev *dev)
+{
+	struct f_rndis  *rndis;
+	int             status;
+
+	/* allocate and initialize one new instance */
+	status = -ENOMEM;
+	rndis = kzalloc(sizeof *rndis, GFP_KERNEL);
+	if (!rndis)
+		goto fail;
+
+	memcpy(rndis->ethaddr, ethaddr, ETH_ALEN);
+	rndis->vendorID = vendorID;
+	rndis->manufacturer = manufacturer;
+
+	rndis->port.ioport = dev;
+	/* RNDIS activates when the host changes this filter */
+	rndis->port.cdc_filter = 0;
+
+	/* RNDIS has special (and complex) framing */
+	rndis->port.header_len = sizeof(struct rndis_packet_msg_type);
+	rndis->port.wrap = rndis_add_header;
+	rndis->port.unwrap = rndis_rm_hdr;
+
+	rndis->port.func.name = "rndis";
+	/* descriptors are per-instance copies */
+	rndis->port.func.bind = rndis_bind;
+	rndis->port.func.unbind = rndis_old_unbind;
+	rndis->port.func.set_alt = rndis_set_alt;
+	rndis->port.func.setup = rndis_setup;
+	rndis->port.func.disable = rndis_disable;
+
+	status = usb_add_function(c, &rndis->port.func);
+	if (status)
+		kfree(rndis);
+fail:
+	return status;
+}
+
 void rndis_borrow_net(struct usb_function_instance *f, struct net_device *net)
 {
 	struct f_rndis_opts *opts;
@@ -993,6 +1076,8 @@ static struct usb_function *rndis_alloc(struct usb_function_instance *fi)
 	rndis->port.header_len = sizeof(struct rndis_packet_msg_type);
 	rndis->port.wrap = rndis_add_header;
 	rndis->port.unwrap = rndis_rm_hdr;
+	rndis->port.ul_max_pkts_per_xfer = rndis_ul_max_pkt_per_xfer;
+	rndis->port.dl_max_pkts_per_xfer = rndis_dl_max_pkt_per_xfer;
 
 	rndis->port.func.name = "rndis";
 	/* descriptors are per-instance copies */
diff --git a/drivers/usb/gadget/function/rndis.c b/drivers/usb/gadget/function/rndis.c
index 95d2324f697..1b468a8297b 100644
--- a/drivers/usb/gadget/function/rndis.c
+++ b/drivers/usb/gadget/function/rndis.c
@@ -59,6 +59,16 @@ MODULE_PARM_DESC (rndis_debug, "enable debugging");
 
 #define RNDIS_MAX_CONFIGS	1
 
+int rndis_ul_max_pkt_per_xfer_rcvd;
+module_param(rndis_ul_max_pkt_per_xfer_rcvd, int, S_IRUGO);
+MODULE_PARM_DESC(rndis_ul_max_pkt_per_xfer_rcvd,
+		"Max num of REMOTE_NDIS_PACKET_MSGs received in a single transfer");
+
+int rndis_ul_max_xfer_size_rcvd;
+module_param(rndis_ul_max_xfer_size_rcvd, int, S_IRUGO);
+MODULE_PARM_DESC(rndis_ul_max_xfer_size_rcvd,
+		"Max size of bus transfer received");
+
 
 static rndis_params rndis_per_dev_params[RNDIS_MAX_CONFIGS];
 
@@ -585,12 +595,12 @@ static int rndis_init_response(int configNr, rndis_init_msg_type *buf)
 	resp->MinorVersion = cpu_to_le32(RNDIS_MINOR_VERSION);
 	resp->DeviceFlags = cpu_to_le32(RNDIS_DF_CONNECTIONLESS);
 	resp->Medium = cpu_to_le32(RNDIS_MEDIUM_802_3);
-	resp->MaxPacketsPerTransfer = cpu_to_le32(1);
-	resp->MaxTransferSize = cpu_to_le32(
-		  params->dev->mtu
+	resp->MaxPacketsPerTransfer = cpu_to_le32(params->max_pkt_per_xfer);
+	resp->MaxTransferSize = cpu_to_le32(params->max_pkt_per_xfer *
+		(params->dev->mtu
 		+ sizeof(struct ethhdr)
 		+ sizeof(struct rndis_packet_msg_type)
-		+ 22);
+		+ 22));
 	resp->PacketAlignmentFactor = cpu_to_le32(0);
 	resp->AFListOffset = cpu_to_le32(0);
 	resp->AFListSize = cpu_to_le32(0);
@@ -686,6 +696,12 @@ static int rndis_reset_response(int configNr, rndis_reset_msg_type *buf)
 	rndis_reset_cmplt_type *resp;
 	rndis_resp_t *r;
 	struct rndis_params *params = rndis_per_dev_params + configNr;
+	u32 length;
+	u8 *xbuf;
+
+	/* drain the response queue */
+	while ((xbuf = rndis_get_next_response(configNr, &length)))
+		rndis_free_response(configNr, xbuf);
 
 	r = rndis_add_response(configNr, sizeof(rndis_reset_cmplt_type));
 	if (!r)
@@ -917,6 +933,8 @@ int rndis_set_param_dev(u8 configNr, struct net_device *dev, u16 *cdc_filter)
 	rndis_per_dev_params[configNr].dev = dev;
 	rndis_per_dev_params[configNr].filter = cdc_filter;
 
+	rndis_ul_max_xfer_size_rcvd = 0;
+	rndis_ul_max_pkt_per_xfer_rcvd = 0;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(rndis_set_param_dev);
@@ -946,6 +964,13 @@ int rndis_set_param_medium(u8 configNr, u32 medium, u32 speed)
 }
 EXPORT_SYMBOL_GPL(rndis_set_param_medium);
 
+void rndis_set_max_pkt_xfer(u8 configNr, u8 max_pkt_per_xfer)
+{
+	pr_debug("%s:\n", __func__);
+
+	rndis_per_dev_params[configNr].max_pkt_per_xfer = max_pkt_per_xfer;
+}
+
 void rndis_add_hdr(struct sk_buff *skb)
 {
 	struct rndis_packet_msg_type *header;
@@ -1021,23 +1046,73 @@ int rndis_rm_hdr(struct gether *port,
 			struct sk_buff *skb,
 			struct sk_buff_head *list)
 {
-	/* tmp points to a struct rndis_packet_msg_type */
-	__le32 *tmp = (void *)skb->data;
+	int num_pkts = 1;
 
-	/* MessageType, MessageLength */
-	if (cpu_to_le32(RNDIS_MSG_PACKET)
-			!= get_unaligned(tmp++)) {
-		dev_kfree_skb_any(skb);
-		return -EINVAL;
-	}
-	tmp++;
+	if (skb->len > rndis_ul_max_xfer_size_rcvd)
+		rndis_ul_max_xfer_size_rcvd = skb->len;
+
+	while (skb->len) {
+		struct rndis_packet_msg_type *hdr;
+		struct sk_buff          *skb2;
+		u32             msg_len, data_offset, data_len;
+
+		/* some rndis hosts send extra byte to avoid zlp, ignore it */
+		if (skb->len == 1) {
+			dev_kfree_skb_any(skb);
+			return 0;
+		}
+
+		if (skb->len < sizeof *hdr) {
+			pr_err("invalid rndis pkt: skblen:%u hdr_len:%u",
+					skb->len, sizeof *hdr);
+			dev_kfree_skb_any(skb);
+			return -EINVAL;
+		}
+
+		hdr = (void *)skb->data;
+		msg_len = le32_to_cpu(hdr->MessageLength);
+		data_offset = le32_to_cpu(hdr->DataOffset);
+		data_len = le32_to_cpu(hdr->DataLength);
+
+		if (skb->len < msg_len ||
+				((data_offset + data_len + 8) > msg_len)) {
+			pr_err("invalid rndis message: %d/%d/%d/%d, len:%d\n",
+					le32_to_cpu(hdr->MessageType),
+					msg_len, data_offset, data_len, skb->len);
+			dev_kfree_skb_any(skb);
+			return -EOVERFLOW;
+		}
+		if (le32_to_cpu(hdr->MessageType) != RNDIS_MSG_PACKET) {
+			pr_err("invalid rndis message: %d/%d/%d/%d, len:%d\n",
+					le32_to_cpu(hdr->MessageType),
+					msg_len, data_offset, data_len, skb->len);
+			dev_kfree_skb_any(skb);
+			return -EINVAL;
+		}
+
+		skb_pull(skb, data_offset + 8);
 
-	/* DataOffset, DataLength */
-	if (!skb_pull(skb, get_unaligned_le32(tmp++) + 8)) {
-		dev_kfree_skb_any(skb);
-		return -EOVERFLOW;
+		if (msg_len == skb->len) {
+			skb_trim(skb, data_len);
+			break;
+		}
+
+		skb2 = skb_clone(skb, GFP_ATOMIC);
+		if (!skb2) {
+			pr_err("%s:skb clone failed\n", __func__);
+			dev_kfree_skb_any(skb);
+			return -ENOMEM;
+		}
+
+		skb_pull(skb, msg_len - sizeof *hdr);
+		skb_trim(skb2, data_len);
+		skb_queue_tail(list, skb2);
+
+		num_pkts++;
 	}
-	skb_trim(skb, get_unaligned_le32(tmp++));
+
+	if (num_pkts > rndis_ul_max_pkt_per_xfer_rcvd)
+		rndis_ul_max_pkt_per_xfer_rcvd = num_pkts;
 
 	skb_queue_tail(list, skb);
 	return 0;
diff --git a/drivers/usb/gadget/function/rndis.h b/drivers/usb/gadget/function/rndis.h
index 0f4abb4c377..145f01b1819 100644
--- a/drivers/usb/gadget/function/rndis.h
+++ b/drivers/usb/gadget/function/rndis.h
@@ -190,6 +190,7 @@ typedef struct rndis_params
 	struct net_device	*dev;
 
 	u32			vendorID;
+	u8			max_pkt_per_xfer;
 	const char		*vendorDescr;
 	void			(*resp_avail)(void *v);
 	void			*v;
@@ -205,6 +206,7 @@ int  rndis_set_param_dev (u8 configNr, struct net_device *dev,
 int  rndis_set_param_vendor (u8 configNr, u32 vendorID,
 			    const char *vendorDescr);
 int  rndis_set_param_medium (u8 configNr, u32 medium, u32 speed);
+void rndis_set_max_pkt_xfer(u8 configNr, u8 max_pkt_per_xfer);
 void rndis_add_hdr (struct sk_buff *skb);
 int rndis_rm_hdr(struct gether *port, struct sk_buff *skb,
 			struct sk_buff_head *list);
diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 6e6f87656e7..ac43a0cf07e 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -48,6 +48,8 @@
 
 #define UETH__VERSION	"29-May-2008"
 
+static struct workqueue_struct	*uether_wq;
+
 struct eth_dev {
 	/* lock is held while accessing port_usb
 	 */
@@ -59,19 +61,27 @@ struct eth_dev {
 
 	spinlock_t		req_lock;	/* guard {rx,tx}_reqs */
 	struct list_head	tx_reqs, rx_reqs;
-	atomic_t		tx_qlen;
+	unsigned		tx_qlen;
+/* Minimum number of TX USB request queued to UDC */
+#define TX_REQ_THRESHOLD	5
+	int			no_tx_req_used;
+	int			tx_skb_hold_count;
+	u32			tx_req_bufsize;
 
 	struct sk_buff_head	rx_frames;
 
 	unsigned		qmult;
 
 	unsigned		header_len;
+	unsigned		ul_max_pkts_per_xfer;
+	unsigned		dl_max_pkts_per_xfer;
 	struct sk_buff		*(*wrap)(struct gether *, struct sk_buff *skb);
 	int			(*unwrap)(struct gether *,
 						struct sk_buff *skb,
 						struct sk_buff_head *list);
 
 	struct work_struct	work;
+	struct work_struct	rx_work;
 
 	unsigned long		todo;
 #define	WORK_RX_MEMORY		0
@@ -225,9 +235,13 @@ rx_submit(struct eth_dev *dev, struct usb_request *req, gfp_t gfp_flags)
 	size += out->maxpacket - 1;
 	size -= size % out->maxpacket;
 
+	if (dev->ul_max_pkts_per_xfer)
+		size *= dev->ul_max_pkts_per_xfer;
+
 	if (dev->port_usb->is_fixed)
 		size = max_t(size_t, size, dev->port_usb->fixed_out_len);
 
+	DBG(dev, "%s: size: %d\n", __func__, size);
 	skb = alloc_skb(size + NET_IP_ALIGN, gfp_flags);
 	if (skb == NULL) {
 		DBG(dev, "no rx skb\n");
@@ -253,18 +267,16 @@ enomem:
 		DBG(dev, "rx submit --> %d\n", retval);
 		if (skb)
 			dev_kfree_skb_any(skb);
-		spin_lock_irqsave(&dev->req_lock, flags);
-		list_add(&req->list, &dev->rx_reqs);
-		spin_unlock_irqrestore(&dev->req_lock, flags);
 	}
 	return retval;
 }
 
 static void rx_complete(struct usb_ep *ep, struct usb_request *req)
 {
-	struct sk_buff	*skb = req->context, *skb2;
+	struct sk_buff	*skb = req->context;
 	struct eth_dev	*dev = ep->driver_data;
 	int		status = req->status;
+	bool		queue = 0;
 
 	switch (status) {
 
@@ -280,6 +292,10 @@ static void rx_complete(struct usb_ep *ep, struct usb_request *req)
 				status = dev->unwrap(dev->port_usb,
 							skb,
 							&dev->rx_frames);
+				if (status == -EINVAL)
+					dev->net->stats.rx_errors++;
+				else if (status == -EOVERFLOW)
+					dev->net->stats.rx_over_errors++;
 			} else {
 				dev_kfree_skb_any(skb);
 				status = -ENOTCONN;
@@ -288,30 +304,9 @@ static void rx_complete(struct usb_ep *ep, struct usb_request *req)
 		} else {
 			skb_queue_tail(&dev->rx_frames, skb);
 		}
-		skb = NULL;
-
-		skb2 = skb_dequeue(&dev->rx_frames);
-		while (skb2) {
-			if (status < 0
-					|| ETH_HLEN > skb2->len
-					|| skb2->len > VLAN_ETH_FRAME_LEN) {
-				dev->net->stats.rx_errors++;
-				dev->net->stats.rx_length_errors++;
-				DBG(dev, "rx length %d\n", skb2->len);
-				dev_kfree_skb_any(skb2);
-				goto next_frame;
-			}
-			skb2->protocol = eth_type_trans(skb2, dev->net);
-			dev->net->stats.rx_packets++;
-			dev->net->stats.rx_bytes += skb2->len;
 
-			/* no buffer copies needed, unless hardware can't
-			 * use skb buffers.
-			 */
-			status = netif_rx(skb2);
-next_frame:
-			skb2 = skb_dequeue(&dev->rx_frames);
-		}
+		if (!status)
+			queue = 1;
 		break;
 
 	/* software-driven interface shutdown */
@@ -334,22 +329,20 @@ quiesce:
 		/* FALLTHROUGH */
 
 	default:
+		queue = 1;
+		dev_kfree_skb_any(skb);
 		dev->net->stats.rx_errors++;
 		DBG(dev, "rx status %d\n", status);
 		break;
 	}
 
-	if (skb)
-		dev_kfree_skb_any(skb);
-	if (!netif_running(dev->net)) {
 clean:
-		spin_lock(&dev->req_lock);
-		list_add(&req->list, &dev->rx_reqs);
-		spin_unlock(&dev->req_lock);
-		req = NULL;
-	}
-	if (req)
-		rx_submit(dev, req, GFP_ATOMIC);
+	spin_lock(&dev->req_lock);
+	list_add(&req->list, &dev->rx_reqs);
+	spin_unlock(&dev->req_lock);
+
+	if (queue)
+		queue_work(uether_wq, &dev->rx_work);
 }
 
 static int prealloc(struct list_head *list, struct usb_ep *ep, unsigned n)
@@ -414,16 +407,24 @@ static void rx_fill(struct eth_dev *dev, gfp_t gfp_flags)
 {
 	struct usb_request	*req;
 	unsigned long		flags;
+	int			req_cnt = 0;
 
 	/* fill unused rxq slots with some skb */
 	spin_lock_irqsave(&dev->req_lock, flags);
 	while (!list_empty(&dev->rx_reqs)) {
+		/* break the nexus of continuous completion and re-submission*/
+		if (++req_cnt > qlen(dev->gadget, dev->qmult))
+			break;
+
 		req = container_of(dev->rx_reqs.next,
 				struct usb_request, list);
 		list_del_init(&req->list);
 		spin_unlock_irqrestore(&dev->req_lock, flags);
 
 		if (rx_submit(dev, req, gfp_flags) < 0) {
+			spin_lock_irqsave(&dev->req_lock, flags);
+			list_add(&req->list, &dev->rx_reqs);
+			spin_unlock_irqrestore(&dev->req_lock, flags);
 			defer_kevent(dev, WORK_RX_MEMORY);
 			return;
 		}
@@ -433,6 +434,36 @@ static void rx_fill(struct eth_dev *dev, gfp_t gfp_flags)
 	spin_unlock_irqrestore(&dev->req_lock, flags);
 }
 
+static void process_rx_w(struct work_struct *work)
+{
+	struct eth_dev	*dev = container_of(work, struct eth_dev, rx_work);
+	struct sk_buff	*skb;
+	int		status = 0;
+
+	if (!dev->port_usb)
+		return;
+
+	while ((skb = skb_dequeue(&dev->rx_frames))) {
+		if (status < 0
+				|| ETH_HLEN > skb->len
+				|| skb->len > ETH_FRAME_LEN) {
+			dev->net->stats.rx_errors++;
+			dev->net->stats.rx_length_errors++;
+			DBG(dev, "rx length %d\n", skb->len);
+			dev_kfree_skb_any(skb);
+			continue;
+		}
+		skb->protocol = eth_type_trans(skb, dev->net);
+		dev->net->stats.rx_packets++;
+		dev->net->stats.rx_bytes += skb->len;
+
+		status = netif_rx_ni(skb);
+	}
+
+	if (netif_running(dev->net))
+		rx_fill(dev, GFP_KERNEL);
+}
+
 static void eth_work(struct work_struct *work)
 {
 	struct eth_dev	*dev = container_of(work, struct eth_dev, work);
@@ -450,6 +481,11 @@ static void tx_complete(struct usb_ep *ep, struct usb_request *req)
 {
 	struct sk_buff	*skb = req->context;
 	struct eth_dev	*dev = ep->driver_data;
+	struct net_device *net = dev->net;
+	struct usb_request *new_req;
+	struct usb_ep *in;
+	int length;
+	int retval;
 
 	switch (req->status) {
 	default:
@@ -460,16 +496,74 @@ static void tx_complete(struct usb_ep *ep, struct usb_request *req)
 	case -ESHUTDOWN:		/* disconnect etc */
 		break;
 	case 0:
-		dev->net->stats.tx_bytes += skb->len;
+		if (!req->zero)
+			dev->net->stats.tx_bytes += req->length-1;
+		else
+			dev->net->stats.tx_bytes += req->length;
 	}
 	dev->net->stats.tx_packets++;
 
 	spin_lock(&dev->req_lock);
-	list_add(&req->list, &dev->tx_reqs);
-	spin_unlock(&dev->req_lock);
-	dev_kfree_skb_any(skb);
+	list_add_tail(&req->list, &dev->tx_reqs);
+
+	if (dev->port_usb->multi_pkt_xfer) {
+		dev->no_tx_req_used--;
+		req->length = 0;
+		in = dev->port_usb->in_ep;
+
+		if (!list_empty(&dev->tx_reqs)) {
+			new_req = container_of(dev->tx_reqs.next,
+					struct usb_request, list);
+			list_del(&new_req->list);
+			spin_unlock(&dev->req_lock);
+			if (new_req->length > 0) {
+				length = new_req->length;
+
+				/* NCM requires no zlp if transfer is
+				 * dwNtbInMaxSize */
+				if (dev->port_usb->is_fixed &&
+					length == dev->port_usb->fixed_in_len &&
+					(length % in->maxpacket) == 0)
+					new_req->zero = 0;
+				else
+					new_req->zero = 1;
+
+				/* use zlp framing on tx for strict CDC-Ether
+				 * conformance, though any robust network rx
+				 * path ignores extra padding. and some hardware
+				 * doesn't like to write zlps.
+				 */
+				if (new_req->zero && !dev->zlp &&
+						(length % in->maxpacket) == 0) {
+					new_req->zero = 0;
+					length++;
+				}
+
+				new_req->length = length;
+				retval = usb_ep_queue(in, new_req, GFP_ATOMIC);
+				switch (retval) {
+				default:
+					DBG(dev, "tx queue err %d\n", retval);
+					break;
+				case 0:
+					spin_lock(&dev->req_lock);
+					dev->no_tx_req_used++;
+					spin_unlock(&dev->req_lock);
+					net->trans_start = jiffies;
+				}
+			} else {
+				spin_lock(&dev->req_lock);
+				list_add(&new_req->list, &dev->tx_reqs);
+				spin_unlock(&dev->req_lock);
+			}
+		} else {
+			spin_unlock(&dev->req_lock);
+		}
+	} else {
+		spin_unlock(&dev->req_lock);
+		dev_kfree_skb_any(skb);
+	}
 
-	atomic_dec(&dev->tx_qlen);
 	if (netif_carrier_ok(dev->net))
 		netif_wake_queue(dev->net);
 }
@@ -479,6 +573,26 @@ static inline int is_promisc(u16 cdc_filter)
 	return cdc_filter & USB_CDC_PACKET_TYPE_PROMISCUOUS;
 }
 
+static void alloc_tx_buffer(struct eth_dev *dev)
+{
+	struct list_head	*act;
+	struct usb_request	*req;
+
+	dev->tx_req_bufsize = (dev->dl_max_pkts_per_xfer *
+				(dev->net->mtu
+				+ sizeof(struct ethhdr)
+				/* size of rndis_packet_msg_type */
+				+ 44
+				+ 22));
+
+	list_for_each(act, &dev->tx_reqs) {
+		req = container_of(act, struct usb_request, list);
+		if (!req->buf)
+			req->buf = kmalloc(dev->tx_req_bufsize,
+						GFP_ATOMIC);
+	}
+}
+
 static netdev_tx_t eth_start_xmit(struct sk_buff *skb,
 					struct net_device *net)
 {
@@ -505,6 +619,10 @@ static netdev_tx_t eth_start_xmit(struct sk_buff *skb,
 		return NETDEV_TX_OK;
 	}
 
+	/* Allocate memory for tx_reqs to support multi packet transfer */
+	if (dev->port_usb->multi_pkt_xfer && !dev->tx_req_bufsize)
+		alloc_tx_buffer(dev);
+
 	/* apply outgoing CDC or RNDIS filters */
 	if (skb && !is_promisc(cdc_filter)) {
 		u8		*dest = skb->data;
@@ -567,9 +685,37 @@ static netdev_tx_t eth_start_xmit(struct sk_buff *skb,
 		}
 	}
 
-	length = skb->len;
-	req->buf = skb->data;
-	req->context = skb;
+	spin_lock_irqsave(&dev->req_lock, flags);
+	dev->tx_skb_hold_count++;
+	spin_unlock_irqrestore(&dev->req_lock, flags);
+
+	if (dev->port_usb->multi_pkt_xfer) {
+		memcpy(req->buf + req->length, skb->data, skb->len);
+		req->length = req->length + skb->len;
+		length = req->length;
+		dev_kfree_skb_any(skb);
+
+		spin_lock_irqsave(&dev->req_lock, flags);
+		if (dev->tx_skb_hold_count < dev->dl_max_pkts_per_xfer) {
+			if (dev->no_tx_req_used > TX_REQ_THRESHOLD) {
+				list_add(&req->list, &dev->tx_reqs);
+				spin_unlock_irqrestore(&dev->req_lock, flags);
+				goto success;
+			}
+		}
+
+		dev->no_tx_req_used++;
+		spin_unlock_irqrestore(&dev->req_lock, flags);
+
+		spin_lock_irqsave(&dev->lock, flags);
+		dev->tx_skb_hold_count = 0;
+		spin_unlock_irqrestore(&dev->lock, flags);
+	} else {
+		length = skb->len;
+		req->buf = skb->data;
+		req->context = skb;
+	}
+
 	req->complete = tx_complete;
 
 	/* NCM requires no zlp if transfer is dwNtbInMaxSize */
@@ -584,17 +730,26 @@ static netdev_tx_t eth_start_xmit(struct sk_buff *skb,
 	 * though any robust network rx path ignores extra padding.
 	 * and some hardware doesn't like to write zlps.
 	 */
-	if (req->zero && !dev->zlp && (length % in->maxpacket) == 0)
+	if (req->zero && !dev->zlp && (length % in->maxpacket) == 0) {
+		req->zero = 0;
 		length++;
+	}
 
 	req->length = length;
 
-	/* throttle high/super speed IRQ rate back slightly */
-	if (gadget_is_dualspeed(dev->gadget))
-		req->no_interrupt = (dev->gadget->speed == USB_SPEED_HIGH ||
-				     dev->gadget->speed == USB_SPEED_SUPER)
-			? ((atomic_read(&dev->tx_qlen) % dev->qmult) != 0)
-			: 0;
+	/* throttle highspeed IRQ rate back slightly */
+	if (gadget_is_dualspeed(dev->gadget) &&
+			 (dev->gadget->speed == USB_SPEED_HIGH)) {
+		dev->tx_qlen++;
+		if (dev->tx_qlen == (dev->qmult/2)) {
+			req->no_interrupt = 0;
+			dev->tx_qlen = 0;
+		} else {
+			req->no_interrupt = 1;
+		}
+	} else {
+		req->no_interrupt = 0;
+	}
 
 	retval = usb_ep_queue(in, req, GFP_ATOMIC);
 	switch (retval) {
@@ -603,11 +758,11 @@ static netdev_tx_t eth_start_xmit(struct sk_buff *skb,
 		break;
 	case 0:
 		net->trans_start = jiffies;
-		atomic_inc(&dev->tx_qlen);
 	}
 
 	if (retval) {
-		dev_kfree_skb_any(skb);
+		if (!dev->port_usb->multi_pkt_xfer)
+			dev_kfree_skb_any(skb);
 drop:
 		dev->net->stats.tx_dropped++;
 multiframe:
@@ -617,6 +772,7 @@ multiframe:
 		list_add(&req->list, &dev->tx_reqs);
 		spin_unlock_irqrestore(&dev->req_lock, flags);
 	}
+success:
 	return NETDEV_TX_OK;
 }
 
@@ -630,7 +786,7 @@ static void eth_start(struct eth_dev *dev, gfp_t gfp_flags)
 	rx_fill(dev, gfp_flags);
 
 	/* and open the tx floodgates */
-	atomic_set(&dev->tx_qlen, 0);
+	dev->tx_qlen = 0;
 	netif_wake_queue(dev->net);
 }
 
@@ -703,6 +859,8 @@ static int eth_stop(struct net_device *net)
 
 /*-------------------------------------------------------------------------*/
 
+static u8 host_ethaddr[ETH_ALEN];
+
 static int get_ether_addr(const char *str, u8 *dev_addr)
 {
 	if (str) {
@@ -735,6 +893,17 @@ static int get_ether_addr_str(u8 dev_addr[ETH_ALEN], char *str, int len)
 	return 18;
 }
 
+static int get_host_ether_addr(u8 *str, u8 *dev_addr)
+{
+	memcpy(dev_addr, str, ETH_ALEN);
+	if (is_valid_ether_addr(dev_addr))
+		return 0;
+
+	random_ether_addr(dev_addr);
+	memcpy(str, dev_addr, ETH_ALEN);
+	return 1;
+}
+
 static const struct net_device_ops eth_netdev_ops = {
 	.ndo_open		= eth_open,
 	.ndo_stop		= eth_stop,
@@ -778,6 +947,7 @@ struct eth_dev *gether_setup_name(struct usb_gadget *g,
 	spin_lock_init(&dev->lock);
 	spin_lock_init(&dev->req_lock);
 	INIT_WORK(&dev->work, eth_work);
+	INIT_WORK(&dev->rx_work, process_rx_w);
 	INIT_LIST_HEAD(&dev->tx_reqs);
 	INIT_LIST_HEAD(&dev->rx_reqs);
 
@@ -791,9 +961,11 @@ struct eth_dev *gether_setup_name(struct usb_gadget *g,
 	if (get_ether_addr(dev_addr, net->dev_addr))
 		dev_warn(&g->dev,
 			"using random %s ethernet address\n", "self");
-	if (get_ether_addr(host_addr, dev->host_mac))
-		dev_warn(&g->dev,
-			"using random %s ethernet address\n", "host");
+
+	if (get_host_ether_addr(host_ethaddr, dev->host_mac))
+		dev_warn(&g->dev, "using random %s ethernet address\n", "host");
+	else
+		dev_warn(&g->dev, "using previous %s ethernet address\n", "host");
 
 	if (ethaddr)
 		memcpy(ethaddr, dev->host_mac, ETH_ALEN);
@@ -1074,8 +1246,13 @@ struct net_device *gether_connect(struct gether *link)
 		dev->header_len = link->header_len;
 		dev->unwrap = link->unwrap;
 		dev->wrap = link->wrap;
+		dev->ul_max_pkts_per_xfer = link->ul_max_pkts_per_xfer;
+		dev->dl_max_pkts_per_xfer = link->dl_max_pkts_per_xfer;
 
 		spin_lock(&dev->lock);
+		dev->tx_skb_hold_count = 0;
+		dev->no_tx_req_used = 0;
+		dev->tx_req_bufsize = 0;
 		dev->port_usb = link;
 		if (netif_running(dev->net)) {
 			if (link->open)
@@ -1120,6 +1297,7 @@ void gether_disconnect(struct gether *link)
 {
 	struct eth_dev		*dev = link->ioport;
 	struct usb_request	*req;
+	struct sk_buff		*skb;
 
 	WARN_ON(!dev);
 	if (!dev)
@@ -1142,6 +1320,8 @@ void gether_disconnect(struct gether *link)
 		list_del(&req->list);
 
 		spin_unlock(&dev->req_lock);
+		if (link->multi_pkt_xfer)
+			kfree(req->buf);
 		usb_ep_free_request(link->in_ep, req);
 		spin_lock(&dev->req_lock);
 	}
@@ -1161,6 +1341,12 @@ void gether_disconnect(struct gether *link)
 		spin_lock(&dev->req_lock);
 	}
 	spin_unlock(&dev->req_lock);
+
+	spin_lock(&dev->rx_frames.lock);
+	while ((skb = __skb_dequeue(&dev->rx_frames)))
+		dev_kfree_skb_any(skb);
+	spin_unlock(&dev->rx_frames.lock);
+
 	link->out_ep->driver_data = NULL;
 	link->out_ep->desc = NULL;
 
@@ -1175,5 +1361,23 @@ void gether_disconnect(struct gether *link)
 }
 EXPORT_SYMBOL_GPL(gether_disconnect);
 
-MODULE_LICENSE("GPL");
+static int __init gether_init(void)
+{
+	uether_wq  = create_singlethread_workqueue("uether");
+	if (!uether_wq) {
+		pr_err("%s: Unable to create workqueue: uether\n", __func__);
+		return -ENOMEM;
+	}
+	return 0;
+}
+module_init(gether_init);
+
+static void __exit gether_exit(void)
+{
+	destroy_workqueue(uether_wq);
+
+}
+module_exit(gether_exit);
 MODULE_AUTHOR("David Brownell");
+MODULE_DESCRIPTION("ethernet over USB driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/usb/gadget/function/u_ether.h b/drivers/usb/gadget/function/u_ether.h
index 334b3894791..f591f74d270 100644
--- a/drivers/usb/gadget/function/u_ether.h
+++ b/drivers/usb/gadget/function/u_ether.h
@@ -75,6 +75,9 @@ struct gether {
 	bool				is_fixed;
 	u32				fixed_out_len;
 	u32				fixed_in_len;
+	unsigned		ul_max_pkts_per_xfer;
+	unsigned		dl_max_pkts_per_xfer;
+	bool				multi_pkt_xfer;
 	bool				supports_multi_frame;
 	struct sk_buff			*(*wrap)(struct gether *port,
 						struct sk_buff *skb);
diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c
index 491082aaf10..d9b867a4f98 100644
--- a/drivers/usb/gadget/function/u_serial.c
+++ b/drivers/usb/gadget/function/u_serial.c
@@ -1122,6 +1122,7 @@ int gserial_alloc_line(unsigned char *line_num)
 
 	tty_dev = tty_port_register_device(&ports[port_num].port->port,
 			gs_tty_driver, port_num, NULL);
+
 	if (IS_ERR(tty_dev)) {
 		struct gs_port	*port;
 		pr_err("%s: failed to register tty for port %d, err %ld\n",
diff --git a/drivers/usb/gadget/functions.c b/drivers/usb/gadget/functions.c
index b13f839e736..389c1f3d0fe 100644
--- a/drivers/usb/gadget/functions.c
+++ b/drivers/usb/gadget/functions.c
@@ -58,7 +58,7 @@ struct usb_function *usb_get_function(struct usb_function_instance *fi)
 	struct usb_function *f;
 
 	f = fi->fd->alloc_func(fi);
-	if (IS_ERR(f))
+	if ((f == NULL) || IS_ERR(f))
 		return f;
 	f->fi = fi;
 	return f;
diff --git a/drivers/usb/gadget/legacy/Kconfig b/drivers/usb/gadget/legacy/Kconfig
index 24392d26970..664625f57bd 100644
--- a/drivers/usb/gadget/legacy/Kconfig
+++ b/drivers/usb/gadget/legacy/Kconfig
@@ -313,6 +313,26 @@ config USB_G_PRINTER
 	  For more information, see Documentation/usb/gadget_printer.txt
 	  which includes sample code for accessing the device file.
 
+config USB_G_ANDROID
+	boolean "Android Composite Gadget"
+	select USB_F_ACM
+	select USB_LIBCOMPOSITE
+	select USB_U_SERIAL
+	select USB_F_MASS_STORAGE
+	select SND_PCM
+	help
+	  The Android Composite Gadget supports multiple USB
+	  functions: adb, acm, mass storage, mtp, accessory
+	  and rndis.
+	  Each function can be configured and enabled/disabled
+	  dynamically from userspace through a sysfs interface.
+
+config USB_ANDROID_RNDIS_DWORD_ALIGNED
+	boolean "Use double word aligned"
+	depends on USB_G_ANDROID
+	help
+		Provides dword aligned for DMA controller.
+
 if TTY
 
 config USB_CDC_COMPOSITE
diff --git a/drivers/usb/gadget/legacy/Makefile b/drivers/usb/gadget/legacy/Makefile
index 7f485f25705..f7c7a59d205 100644
--- a/drivers/usb/gadget/legacy/Makefile
+++ b/drivers/usb/gadget/legacy/Makefile
@@ -22,6 +22,7 @@ g_nokia-y			:= nokia.o
 g_webcam-y			:= webcam.o
 g_ncm-y				:= ncm.o
 g_acm_ms-y			:= acm_ms.o
+g_android-y			:= android.o
 g_tcm_usb_gadget-y		:= tcm_usb_gadget.o
 
 obj-$(CONFIG_USB_ZERO)		+= g_zero.o
@@ -41,4 +42,5 @@ obj-$(CONFIG_USB_G_NOKIA)	+= g_nokia.o
 obj-$(CONFIG_USB_G_WEBCAM)	+= g_webcam.o
 obj-$(CONFIG_USB_G_NCM)		+= g_ncm.o
 obj-$(CONFIG_USB_G_ACM_MS)	+= g_acm_ms.o
+obj-$(CONFIG_USB_G_ANDROID)	+= g_android.o
 obj-$(CONFIG_USB_GADGET_TARGET)	+= tcm_usb_gadget.o
diff --git a/drivers/usb/gadget/legacy/android.c b/drivers/usb/gadget/legacy/android.c
new file mode 100644
index 00000000000..1d38c8da914
--- /dev/null
+++ b/drivers/usb/gadget/legacy/android.c
@@ -0,0 +1,1568 @@
+/*
+ * Gadget Driver for Android
+ *
+ * Copyright (C) 2008 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *         Benoit Goby <benoit@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/delay.h>
+#include <linux/kernel.h>
+#include <linux/utsname.h>
+#include <linux/platform_device.h>
+
+#include <linux/usb/ch9.h>
+#include <linux/usb/composite.h>
+#include <linux/usb/gadget.h>
+
+#include "gadget_chips.h"
+
+#include "f_fs.c"
+#include "f_audio_source.c"
+#include "f_mtp.c"
+#include "f_accessory.c"
+#define USB_ETH_RNDIS y
+#include "f_rndis.c"
+#include "rndis.c"
+#include "u_ether.c"
+
+USB_ETHERNET_MODULE_PARAMETERS();
+
+MODULE_AUTHOR("Mike Lockwood");
+MODULE_DESCRIPTION("Android Composite USB Driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1.0");
+
+static const char longname[] = "Gadget Android";
+
+/* Default vendor and product IDs, overridden by userspace */
+#define VENDOR_ID		0x18D1
+#define PRODUCT_ID		0x0001
+
+struct android_usb_function {
+	char *name;
+	void *config;
+
+	struct device *dev;
+	char *dev_name;
+	struct device_attribute **attributes;
+
+	/* for android_dev.enabled_functions */
+	struct list_head enabled_list;
+
+	/* Optional: initialization during gadget bind */
+	int (*init)(struct android_usb_function *, struct usb_composite_dev *);
+	/* Optional: cleanup during gadget unbind */
+	void (*cleanup)(struct android_usb_function *);
+	/* Optional: called when the function is added the list of
+	 *		enabled functions */
+	void (*enable)(struct android_usb_function *);
+	/* Optional: called when it is removed */
+	void (*disable)(struct android_usb_function *);
+
+	int (*bind_config)(struct android_usb_function *,
+			   struct usb_configuration *);
+
+	/* Optional: called when the configuration is removed */
+	void (*unbind_config)(struct android_usb_function *,
+			      struct usb_configuration *);
+	/* Optional: handle ctrl requests before the device is configured */
+	int (*ctrlrequest)(struct android_usb_function *,
+					struct usb_composite_dev *,
+					const struct usb_ctrlrequest *);
+};
+
+struct android_dev {
+	struct android_usb_function **functions;
+	struct list_head enabled_functions;
+	struct usb_composite_dev *cdev;
+	struct device *dev;
+
+	void (*setup_complete)(struct usb_ep *ep,
+				struct usb_request *req);
+
+	bool enabled;
+	int disable_depth;
+	struct mutex mutex;
+	bool connected;
+	bool sw_connected;
+	struct work_struct work;
+	char ffs_aliases[256];
+};
+
+static struct class *android_class;
+static struct android_dev *_android_dev;
+static int android_bind_config(struct usb_configuration *c);
+static void android_unbind_config(struct usb_configuration *c);
+
+/* string IDs are assigned dynamically */
+#define STRING_MANUFACTURER_IDX		0
+#define STRING_PRODUCT_IDX		1
+#define STRING_SERIAL_IDX		2
+
+static char manufacturer_string[256];
+static char product_string[256];
+static char serial_string[256];
+
+/*---Copied from configfs.c to let this composite driver build---*/
+static struct class *android_class;
+static struct device *android_device;
+static int index;
+
+struct device *create_function_device(char *name)
+{
+        if (android_device && !IS_ERR(android_device))
+                return device_create(android_class, android_device,
+                        MKDEV(0, index++), NULL, name);
+        else
+                return ERR_PTR(-EINVAL);
+}
+EXPORT_SYMBOL_GPL(create_function_device);
+/*---------------------------------------------------------------*/
+
+/* String Table */
+static struct usb_string strings_dev[] = {
+	[STRING_MANUFACTURER_IDX].s = manufacturer_string,
+	[STRING_PRODUCT_IDX].s = product_string,
+	[STRING_SERIAL_IDX].s = serial_string,
+	{  }			/* end of list */
+};
+
+static struct usb_gadget_strings stringtab_dev = {
+	.language	= 0x0409,	/* en-us */
+	.strings	= strings_dev,
+};
+
+static struct usb_gadget_strings *dev_strings[] = {
+	&stringtab_dev,
+	NULL,
+};
+
+static struct usb_device_descriptor device_desc = {
+	.bLength              = sizeof(device_desc),
+	.bDescriptorType      = USB_DT_DEVICE,
+	.bcdUSB               = __constant_cpu_to_le16(0x0200),
+	.bDeviceClass         = USB_CLASS_PER_INTERFACE,
+	.idVendor             = __constant_cpu_to_le16(VENDOR_ID),
+	.idProduct            = __constant_cpu_to_le16(PRODUCT_ID),
+	.bcdDevice            = __constant_cpu_to_le16(0xffff),
+	.bNumConfigurations   = 1,
+};
+
+static struct usb_configuration android_config_driver = {
+	.label		= "android",
+	.unbind		= android_unbind_config,
+	.bConfigurationValue = 1,
+	.bmAttributes	= USB_CONFIG_ATT_ONE | USB_CONFIG_ATT_SELFPOWER,
+	.MaxPower	= 500, /* 500ma */
+};
+
+static void android_work(struct work_struct *data)
+{
+	struct android_dev *dev = container_of(data, struct android_dev, work);
+	struct usb_composite_dev *cdev = dev->cdev;
+	char *disconnected[2] = { "USB_STATE=DISCONNECTED", NULL };
+	char *connected[2]    = { "USB_STATE=CONNECTED", NULL };
+	char *configured[2]   = { "USB_STATE=CONFIGURED", NULL };
+	char **uevent_envp = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cdev->lock, flags);
+	if (cdev->config)
+		uevent_envp = configured;
+	else if (dev->connected != dev->sw_connected)
+		uevent_envp = dev->connected ? connected : disconnected;
+	dev->sw_connected = dev->connected;
+	spin_unlock_irqrestore(&cdev->lock, flags);
+
+	if (uevent_envp) {
+		kobject_uevent_env(&dev->dev->kobj, KOBJ_CHANGE, uevent_envp);
+		pr_info("%s: sent uevent %s\n", __func__, uevent_envp[0]);
+	} else {
+		pr_info("%s: did not send uevent (%d %d %p)\n", __func__,
+			 dev->connected, dev->sw_connected, cdev->config);
+	}
+}
+
+static void android_enable(struct android_dev *dev)
+{
+	struct usb_composite_dev *cdev = dev->cdev;
+
+	if (WARN_ON(!dev->disable_depth))
+		return;
+
+	if (--dev->disable_depth == 0) {
+		usb_add_config(cdev, &android_config_driver,
+					android_bind_config);
+		usb_gadget_connect(cdev->gadget);
+	}
+}
+
+static void android_disable(struct android_dev *dev)
+{
+	struct usb_composite_dev *cdev = dev->cdev;
+
+	if (dev->disable_depth++ == 0) {
+		usb_gadget_disconnect(cdev->gadget);
+		/* Cancel pending control requests */
+		usb_ep_dequeue(cdev->gadget->ep0, cdev->req);
+		usb_remove_config(cdev, &android_config_driver);
+	}
+}
+
+/*-------------------------------------------------------------------------*/
+/* Supported functions initialization */
+
+struct functionfs_config {
+	bool opened;
+	bool enabled;
+	struct ffs_data *data;
+};
+
+static int ffs_function_init(struct android_usb_function *f,
+			     struct usb_composite_dev *cdev)
+{
+	f->config = kzalloc(sizeof(struct functionfs_config), GFP_KERNEL);
+	if (!f->config)
+		return -ENOMEM;
+
+	return functionfs_init();
+}
+
+static void ffs_function_cleanup(struct android_usb_function *f)
+{
+	functionfs_cleanup();
+	kfree(f->config);
+}
+
+static void ffs_function_enable(struct android_usb_function *f)
+{
+	struct android_dev *dev = _android_dev;
+	struct functionfs_config *config = f->config;
+
+	config->enabled = true;
+
+	/* Disable the gadget until the function is ready */
+	if (!config->opened)
+		android_disable(dev);
+}
+
+static void ffs_function_disable(struct android_usb_function *f)
+{
+	struct android_dev *dev = _android_dev;
+	struct functionfs_config *config = f->config;
+
+	config->enabled = false;
+
+	/* Balance the disable that was called in closed_callback */
+	if (!config->opened)
+		android_enable(dev);
+}
+
+static int ffs_function_bind_config(struct android_usb_function *f,
+				    struct usb_configuration *c)
+{
+	struct functionfs_config *config = f->config;
+	return functionfs_bind_config(c->cdev, c, config->data);
+}
+
+static ssize_t
+ffs_aliases_show(struct device *pdev, struct device_attribute *attr, char *buf)
+{
+	struct android_dev *dev = _android_dev;
+	int ret;
+
+	mutex_lock(&dev->mutex);
+	ret = sprintf(buf, "%s\n", dev->ffs_aliases);
+	mutex_unlock(&dev->mutex);
+
+	return ret;
+}
+
+static ssize_t
+ffs_aliases_store(struct device *pdev, struct device_attribute *attr,
+					const char *buf, size_t size)
+{
+	struct android_dev *dev = _android_dev;
+	char buff[256];
+
+	mutex_lock(&dev->mutex);
+
+	if (dev->enabled) {
+		mutex_unlock(&dev->mutex);
+		return -EBUSY;
+	}
+
+	strlcpy(buff, buf, sizeof(buff));
+	strlcpy(dev->ffs_aliases, strim(buff), sizeof(dev->ffs_aliases));
+
+	mutex_unlock(&dev->mutex);
+
+	return size;
+}
+
+static DEVICE_ATTR(aliases, S_IRUGO | S_IWUSR, ffs_aliases_show,
+					       ffs_aliases_store);
+static struct device_attribute *ffs_function_attributes[] = {
+	&dev_attr_aliases,
+	NULL
+};
+
+static struct android_usb_function ffs_function = {
+	.name		= "ffs",
+	.init		= ffs_function_init,
+	.enable		= ffs_function_enable,
+	.disable	= ffs_function_disable,
+	.cleanup	= ffs_function_cleanup,
+	.bind_config	= ffs_function_bind_config,
+	.attributes	= ffs_function_attributes,
+};
+
+static int functionfs_ready_callback(struct ffs_data *ffs)
+{
+	struct android_dev *dev = _android_dev;
+	struct functionfs_config *config = ffs_function.config;
+	int ret = 0;
+
+	mutex_lock(&dev->mutex);
+
+	ret = functionfs_bind(ffs, dev->cdev);
+	if (ret)
+		goto err;
+
+	config->data = ffs;
+	config->opened = true;
+
+	if (config->enabled)
+		android_enable(dev);
+
+err:
+	mutex_unlock(&dev->mutex);
+	return ret;
+}
+
+static void functionfs_closed_callback(struct ffs_data *ffs)
+{
+	struct android_dev *dev = _android_dev;
+	struct functionfs_config *config = ffs_function.config;
+
+	mutex_lock(&dev->mutex);
+
+	if (config->enabled)
+		android_disable(dev);
+
+	config->opened = false;
+	config->data = NULL;
+
+	functionfs_unbind(ffs);
+
+	mutex_unlock(&dev->mutex);
+}
+
+static void *functionfs_acquire_dev_callback(const char *dev_name)
+{
+	return 0;
+}
+
+static void functionfs_release_dev_callback(struct ffs_data *ffs_data)
+{
+}
+
+#define MAX_ACM_INSTANCES 4
+struct acm_function_config {
+	int instances;
+	int instances_on;
+	struct usb_function *f_acm[MAX_ACM_INSTANCES];
+	struct usb_function_instance *f_acm_inst[MAX_ACM_INSTANCES];
+};
+
+static int
+acm_function_init(struct android_usb_function *f,
+		struct usb_composite_dev *cdev)
+{
+	int i;
+	int ret;
+	struct acm_function_config *config;
+
+	config = kzalloc(sizeof(struct acm_function_config), GFP_KERNEL);
+	if (!config)
+		return -ENOMEM;
+	f->config = config;
+
+	for (i = 0; i < MAX_ACM_INSTANCES; i++) {
+		config->f_acm_inst[i] = usb_get_function_instance("acm");
+		if (IS_ERR(config->f_acm_inst[i])) {
+			ret = PTR_ERR(config->f_acm_inst[i]);
+			goto err_usb_get_function_instance;
+		}
+		config->f_acm[i] = usb_get_function(config->f_acm_inst[i]);
+		if (IS_ERR(config->f_acm[i])) {
+			ret = PTR_ERR(config->f_acm[i]);
+			goto err_usb_get_function;
+		}
+	}
+	return 0;
+err_usb_get_function_instance:
+	while (i-- > 0) {
+		usb_put_function(config->f_acm[i]);
+err_usb_get_function:
+		usb_put_function_instance(config->f_acm_inst[i]);
+	}
+	return ret;
+}
+
+static void acm_function_cleanup(struct android_usb_function *f)
+{
+	int i;
+	struct acm_function_config *config = f->config;
+
+	for (i = 0; i < MAX_ACM_INSTANCES; i++) {
+		usb_put_function(config->f_acm[i]);
+		usb_put_function_instance(config->f_acm_inst[i]);
+	}
+	kfree(f->config);
+	f->config = NULL;
+}
+
+static int
+acm_function_bind_config(struct android_usb_function *f,
+		struct usb_configuration *c)
+{
+	int i;
+	int ret = 0;
+	struct acm_function_config *config = f->config;
+
+	config->instances_on = config->instances;
+	for (i = 0; i < config->instances_on; i++) {
+		ret = usb_add_function(c, config->f_acm[i]);
+		if (ret) {
+			pr_err("Could not bind acm%u config\n", i);
+			goto err_usb_add_function;
+		}
+	}
+
+	return 0;
+
+err_usb_add_function:
+	while (i-- > 0)
+		usb_remove_function(c, config->f_acm[i]);
+	return ret;
+}
+
+static void acm_function_unbind_config(struct android_usb_function *f,
+				       struct usb_configuration *c)
+{
+	int i;
+	struct acm_function_config *config = f->config;
+
+	for (i = 0; i < config->instances_on; i++)
+		usb_remove_function(c, config->f_acm[i]);
+}
+
+static ssize_t acm_instances_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct android_usb_function *f = dev_get_drvdata(dev);
+	struct acm_function_config *config = f->config;
+	return sprintf(buf, "%d\n", config->instances);
+}
+
+static ssize_t acm_instances_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t size)
+{
+	struct android_usb_function *f = dev_get_drvdata(dev);
+	struct acm_function_config *config = f->config;
+	int value;
+
+	sscanf(buf, "%d", &value);
+	if (value > MAX_ACM_INSTANCES)
+		value = MAX_ACM_INSTANCES;
+	config->instances = value;
+	return size;
+}
+
+static DEVICE_ATTR(instances, S_IRUGO | S_IWUSR, acm_instances_show,
+						 acm_instances_store);
+static struct device_attribute *acm_function_attributes[] = {
+	&dev_attr_instances,
+	NULL
+};
+
+static struct android_usb_function acm_function = {
+	.name		= "acm",
+	.init		= acm_function_init,
+	.cleanup	= acm_function_cleanup,
+	.bind_config	= acm_function_bind_config,
+	.unbind_config	= acm_function_unbind_config,
+	.attributes	= acm_function_attributes,
+};
+
+
+static int
+mtp_function_init(struct android_usb_function *f,
+		struct usb_composite_dev *cdev)
+{
+	return mtp_setup();
+}
+
+static void mtp_function_cleanup(struct android_usb_function *f)
+{
+	mtp_cleanup();
+}
+
+static int
+mtp_function_bind_config(struct android_usb_function *f,
+		struct usb_configuration *c)
+{
+	return mtp_bind_config(c, false);
+}
+
+static int
+ptp_function_init(struct android_usb_function *f,
+		struct usb_composite_dev *cdev)
+{
+	/* nothing to do - initialization is handled by mtp_function_init */
+	return 0;
+}
+
+static void ptp_function_cleanup(struct android_usb_function *f)
+{
+	/* nothing to do - cleanup is handled by mtp_function_cleanup */
+}
+
+static int
+ptp_function_bind_config(struct android_usb_function *f,
+		struct usb_configuration *c)
+{
+	return mtp_bind_config(c, true);
+}
+
+static int mtp_function_ctrlrequest(struct android_usb_function *f,
+					struct usb_composite_dev *cdev,
+					const struct usb_ctrlrequest *c)
+{
+	return mtp_ctrlrequest(cdev, c);
+}
+
+static struct android_usb_function mtp_function = {
+	.name		= "mtp",
+	.init		= mtp_function_init,
+	.cleanup	= mtp_function_cleanup,
+	.bind_config	= mtp_function_bind_config,
+	.ctrlrequest	= mtp_function_ctrlrequest,
+};
+
+/* PTP function is same as MTP with slightly different interface descriptor */
+static struct android_usb_function ptp_function = {
+	.name		= "ptp",
+	.init		= ptp_function_init,
+	.cleanup	= ptp_function_cleanup,
+	.bind_config	= ptp_function_bind_config,
+};
+
+
+struct rndis_function_config {
+	u8      ethaddr[ETH_ALEN];
+	u32     vendorID;
+	char	manufacturer[256];
+	/* "Wireless" RNDIS; auto-detected by Windows */
+	bool	wceis;
+	struct eth_dev *dev;
+};
+
+static int
+rndis_function_init(struct android_usb_function *f,
+		struct usb_composite_dev *cdev)
+{
+	f->config = kzalloc(sizeof(struct rndis_function_config), GFP_KERNEL);
+	if (!f->config)
+		return -ENOMEM;
+	return 0;
+}
+
+static void rndis_function_cleanup(struct android_usb_function *f)
+{
+	kfree(f->config);
+	f->config = NULL;
+}
+
+static int
+rndis_function_bind_config(struct android_usb_function *f,
+		struct usb_configuration *c)
+{
+	int ret;
+	struct eth_dev *dev;
+	struct rndis_function_config *rndis = f->config;
+
+	if (!rndis) {
+		pr_err("%s: rndis_pdata\n", __func__);
+		return -1;
+	}
+
+	pr_info("%s MAC: %02X:%02X:%02X:%02X:%02X:%02X\n", __func__,
+		rndis->ethaddr[0], rndis->ethaddr[1], rndis->ethaddr[2],
+		rndis->ethaddr[3], rndis->ethaddr[4], rndis->ethaddr[5]);
+
+	dev = gether_setup_name(c->cdev->gadget,dev_addr, host_addr, rndis->ethaddr, qmult, "rndis");
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		pr_err("%s: gether_setup failed\n", __func__);
+		return ret;
+	}
+	rndis->dev = dev;
+
+	if (rndis->wceis) {
+		/* "Wireless" RNDIS; auto-detected by Windows */
+		rndis_iad_descriptor.bFunctionClass =
+						USB_CLASS_WIRELESS_CONTROLLER;
+		rndis_iad_descriptor.bFunctionSubClass = 0x01;
+		rndis_iad_descriptor.bFunctionProtocol = 0x03;
+		rndis_control_intf.bInterfaceClass =
+						USB_CLASS_WIRELESS_CONTROLLER;
+		rndis_control_intf.bInterfaceSubClass =	 0x01;
+		rndis_control_intf.bInterfaceProtocol =	 0x03;
+	}
+
+	return rndis_bind_config_vendor(c, rndis->ethaddr, rndis->vendorID,
+					   rndis->manufacturer, rndis->dev);
+}
+
+static void rndis_function_unbind_config(struct android_usb_function *f,
+						struct usb_configuration *c)
+{
+	struct rndis_function_config *rndis = f->config;
+	gether_cleanup(rndis->dev);
+}
+
+static ssize_t rndis_manufacturer_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct android_usb_function *f = dev_get_drvdata(dev);
+	struct rndis_function_config *config = f->config;
+	return sprintf(buf, "%s\n", config->manufacturer);
+}
+
+static ssize_t rndis_manufacturer_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t size)
+{
+	struct android_usb_function *f = dev_get_drvdata(dev);
+	struct rndis_function_config *config = f->config;
+
+	if (size >= sizeof(config->manufacturer))
+		return -EINVAL;
+	if (sscanf(buf, "%s", config->manufacturer) == 1)
+		return size;
+	return -1;
+}
+
+static DEVICE_ATTR(manufacturer, S_IRUGO | S_IWUSR, rndis_manufacturer_show,
+						    rndis_manufacturer_store);
+
+static ssize_t rndis_wceis_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct android_usb_function *f = dev_get_drvdata(dev);
+	struct rndis_function_config *config = f->config;
+	return sprintf(buf, "%d\n", config->wceis);
+}
+
+static ssize_t rndis_wceis_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t size)
+{
+	struct android_usb_function *f = dev_get_drvdata(dev);
+	struct rndis_function_config *config = f->config;
+	int value;
+
+	if (sscanf(buf, "%d", &value) == 1) {
+		config->wceis = value;
+		return size;
+	}
+	return -EINVAL;
+}
+
+static DEVICE_ATTR(wceis, S_IRUGO | S_IWUSR, rndis_wceis_show,
+					     rndis_wceis_store);
+
+static ssize_t rndis_ethaddr_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct android_usb_function *f = dev_get_drvdata(dev);
+	struct rndis_function_config *rndis = f->config;
+	return sprintf(buf, "%02x:%02x:%02x:%02x:%02x:%02x\n",
+		rndis->ethaddr[0], rndis->ethaddr[1], rndis->ethaddr[2],
+		rndis->ethaddr[3], rndis->ethaddr[4], rndis->ethaddr[5]);
+}
+
+static ssize_t rndis_ethaddr_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t size)
+{
+	struct android_usb_function *f = dev_get_drvdata(dev);
+	struct rndis_function_config *rndis = f->config;
+
+	if (sscanf(buf, "%02x:%02x:%02x:%02x:%02x:%02x\n",
+		    (int *)&rndis->ethaddr[0], (int *)&rndis->ethaddr[1],
+		    (int *)&rndis->ethaddr[2], (int *)&rndis->ethaddr[3],
+		    (int *)&rndis->ethaddr[4], (int *)&rndis->ethaddr[5]) == 6)
+		return size;
+	return -EINVAL;
+}
+
+static DEVICE_ATTR(ethaddr, S_IRUGO | S_IWUSR, rndis_ethaddr_show,
+					       rndis_ethaddr_store);
+
+static ssize_t rndis_vendorID_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct android_usb_function *f = dev_get_drvdata(dev);
+	struct rndis_function_config *config = f->config;
+	return sprintf(buf, "%04x\n", config->vendorID);
+}
+
+static ssize_t rndis_vendorID_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t size)
+{
+	struct android_usb_function *f = dev_get_drvdata(dev);
+	struct rndis_function_config *config = f->config;
+	int value;
+
+	if (sscanf(buf, "%04x", &value) == 1) {
+		config->vendorID = value;
+		return size;
+	}
+	return -EINVAL;
+}
+
+static DEVICE_ATTR(vendorID, S_IRUGO | S_IWUSR, rndis_vendorID_show,
+						rndis_vendorID_store);
+
+static struct device_attribute *rndis_function_attributes[] = {
+	&dev_attr_manufacturer,
+	&dev_attr_wceis,
+	&dev_attr_ethaddr,
+	&dev_attr_vendorID,
+	NULL
+};
+
+static struct android_usb_function rndis_function = {
+	.name		= "rndis",
+	.init		= rndis_function_init,
+	.cleanup	= rndis_function_cleanup,
+	.bind_config	= rndis_function_bind_config,
+	.unbind_config	= rndis_function_unbind_config,
+	.attributes	= rndis_function_attributes,
+};
+
+
+#define MAX_MS_INSTANCES 1
+struct mass_storage_function_config {
+	int instances;
+	int instances_on;
+	struct usb_function *f_ms[MAX_MS_INSTANCES];
+	struct usb_function_instance *f_ms_inst[MAX_MS_INSTANCES];
+};
+
+static int mass_storage_function_init(struct android_usb_function *f,
+					struct usb_composite_dev *cdev)
+{
+	struct mass_storage_function_config *config;
+	int i;
+	int ret;
+
+	config = kzalloc(sizeof(struct mass_storage_function_config),
+								GFP_KERNEL);
+	if (!config)
+		return -ENOMEM;
+	f->config = config;
+
+	for (i = 0; i < MAX_MS_INSTANCES; i++) {
+		config->f_ms_inst[i] = usb_get_function_instance("mass_storage");
+		if (IS_ERR(config->f_ms_inst[i])) {
+			ret = PTR_ERR(config->f_ms_inst[i]);
+			goto err_usb_get_function_instance;
+		}
+		config->f_ms[i] = usb_get_function(config->f_ms_inst[i]);
+		if (IS_ERR(config->f_ms[i])) {
+			ret = PTR_ERR(config->f_ms[i]);
+			goto err_usb_get_function;
+		}
+	}
+
+	return 0;
+err_usb_get_function_instance:
+	while (i-- > 0) {
+		usb_put_function(config->f_ms[i]);
+err_usb_get_function:
+		usb_put_function_instance(config->f_ms_inst[i]);
+	}
+	return ret;
+}
+
+static void mass_storage_function_cleanup(struct android_usb_function *f)
+{
+	struct mass_storage_function_config *config = f->config;
+	int i;
+
+	for (i = 0; i < MAX_MS_INSTANCES; i++) {
+		usb_put_function(config->f_ms[i]);
+		usb_put_function_instance(config->f_ms_inst[i]);
+	}
+	kfree(f->config);
+	f->config = NULL;
+}
+
+static int mass_storage_function_bind_config(struct android_usb_function *f,
+					   struct usb_configuration *c)
+{
+	struct mass_storage_function_config *config = f->config;
+	int ret = 0;
+	int i;
+
+	config->instances_on = config->instances;
+	for (i = 0; i < config->instances_on; i++) {
+		ret = usb_add_function(c, config->f_ms[i]);
+		if (ret) {
+			pr_err("Could not bind ms%u config\n", i);
+			goto err_usb_add_function;
+		}
+	}
+
+	return 0;
+
+err_usb_add_function:
+	while (i-- > 0)
+		usb_remove_function(c, config->f_ms[i]);
+	return ret;
+}
+
+static void mass_storage_function_unbind_config(struct android_usb_function *f,
+				struct usb_configuration *c)
+{
+	int i;
+	struct mass_storage_function_config *config = f->config;
+
+	for (i = 0; i < config->instances_on; i++)
+		usb_remove_function(c, config->f_ms[i]);
+}
+
+static ssize_t mass_storage_inquiry_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct android_usb_function *f = dev_get_drvdata(dev);
+	struct mass_storage_function_config *config = f->config;
+	return sprintf(buf, "%d\n", config->instances);
+}
+
+static ssize_t mass_storage_inquiry_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t size)
+{
+	struct android_usb_function *f = dev_get_drvdata(dev);
+	struct mass_storage_function_config *config = f->config;
+	int value;
+
+	sscanf(buf, "%d", &value);
+	if (value > MAX_MS_INSTANCES)
+		value = MAX_MS_INSTANCES;
+	config->instances = value;
+	return size;
+}
+
+static DEVICE_ATTR(inquiry_string, S_IRUGO | S_IWUSR,
+					mass_storage_inquiry_show,
+					mass_storage_inquiry_store);
+
+static struct device_attribute *mass_storage_function_attributes[] = {
+	&dev_attr_inquiry_string,
+	NULL
+};
+
+static struct android_usb_function mass_storage_function = {
+	.name		= "mass_storage",
+	.init		= mass_storage_function_init,
+	.cleanup	= mass_storage_function_cleanup,
+	.bind_config	= mass_storage_function_bind_config,
+	.attributes	= mass_storage_function_attributes,
+};
+
+
+static int accessory_function_init(struct android_usb_function *f,
+					struct usb_composite_dev *cdev)
+{
+	return acc_setup();
+}
+
+static void accessory_function_cleanup(struct android_usb_function *f)
+{
+	acc_cleanup();
+}
+
+static int accessory_function_bind_config(struct android_usb_function *f,
+						struct usb_configuration *c)
+{
+	return acc_bind_config(c);
+}
+
+static int accessory_function_ctrlrequest(struct android_usb_function *f,
+						struct usb_composite_dev *cdev,
+						const struct usb_ctrlrequest *c)
+{
+	return acc_ctrlrequest(cdev, c);
+}
+
+static struct android_usb_function accessory_function = {
+	.name		= "accessory",
+	.init		= accessory_function_init,
+	.cleanup	= accessory_function_cleanup,
+	.bind_config	= accessory_function_bind_config,
+	.ctrlrequest	= accessory_function_ctrlrequest,
+};
+
+static int audio_source_function_init(struct android_usb_function *f,
+			struct usb_composite_dev *cdev)
+{
+	struct audio_source_config *config;
+
+	config = kzalloc(sizeof(struct audio_source_config), GFP_KERNEL);
+	if (!config)
+		return -ENOMEM;
+	config->card = -1;
+	config->device = -1;
+	f->config = config;
+	return 0;
+}
+
+static void audio_source_function_cleanup(struct android_usb_function *f)
+{
+	kfree(f->config);
+}
+
+static int audio_source_function_bind_config(struct android_usb_function *f,
+						struct usb_configuration *c)
+{
+	struct audio_source_config *config = f->config;
+
+	return audio_source_bind_config(c, config);
+}
+
+static void audio_source_function_unbind_config(struct android_usb_function *f,
+						struct usb_configuration *c)
+{
+	struct audio_source_config *config = f->config;
+
+	config->card = -1;
+	config->device = -1;
+}
+
+static struct android_usb_function audio_source_function = {
+	.name		= "audio_source",
+	.init		= audio_source_function_init,
+	.cleanup	= audio_source_function_cleanup,
+	.bind_config	= audio_source_function_bind_config,
+	.unbind_config	= audio_source_function_unbind_config,
+	.attributes	= audio_source_function_attributes,
+};
+
+static struct android_usb_function *supported_functions[] = {
+	&ffs_function,
+	&acm_function,
+	&mtp_function,
+	&ptp_function,
+	&rndis_function,
+	&mass_storage_function,
+	&accessory_function,
+	&audio_source_function,
+	NULL
+};
+
+
+static int android_init_functions(struct android_usb_function **functions,
+				  struct usb_composite_dev *cdev)
+{
+	struct android_dev *dev = _android_dev;
+	struct android_usb_function *f;
+	struct device_attribute **attrs;
+	struct device_attribute *attr;
+	int err;
+	int index = 0;
+
+	for (; (f = *functions++); index++) {
+		f->dev_name = kasprintf(GFP_KERNEL, "f_%s", f->name);
+		f->dev = device_create(android_class, dev->dev,
+				MKDEV(0, index), f, f->dev_name);
+		if (IS_ERR(f->dev)) {
+			pr_err("%s: Failed to create dev %s", __func__,
+							f->dev_name);
+			err = PTR_ERR(f->dev);
+			goto err_create;
+		}
+
+		if (f->init) {
+			err = f->init(f, cdev);
+			if (err) {
+				pr_err("%s: Failed to init %s", __func__,
+								f->name);
+				goto err_out;
+			}
+		}
+
+		attrs = f->attributes;
+		if (attrs) {
+			while ((attr = *attrs++) && !err)
+				err = device_create_file(f->dev, attr);
+		}
+		if (err) {
+			pr_err("%s: Failed to create function %s attributes",
+					__func__, f->name);
+			goto err_out;
+		}
+	}
+	return 0;
+
+err_out:
+	device_destroy(android_class, f->dev->devt);
+err_create:
+	kfree(f->dev_name);
+	return err;
+}
+
+static void android_cleanup_functions(struct android_usb_function **functions)
+{
+	struct android_usb_function *f;
+
+	while (*functions) {
+		f = *functions++;
+
+		if (f->dev) {
+			device_destroy(android_class, f->dev->devt);
+			kfree(f->dev_name);
+		}
+
+		if (f->cleanup)
+			f->cleanup(f);
+	}
+}
+
+static int
+android_bind_enabled_functions(struct android_dev *dev,
+			       struct usb_configuration *c)
+{
+	struct android_usb_function *f;
+	int ret;
+
+	list_for_each_entry(f, &dev->enabled_functions, enabled_list) {
+		ret = f->bind_config(f, c);
+		if (ret) {
+			pr_err("%s: %s failed", __func__, f->name);
+			return ret;
+		}
+	}
+	return 0;
+}
+
+static void
+android_unbind_enabled_functions(struct android_dev *dev,
+			       struct usb_configuration *c)
+{
+	struct android_usb_function *f;
+
+	list_for_each_entry(f, &dev->enabled_functions, enabled_list) {
+		if (f->unbind_config)
+			f->unbind_config(f, c);
+	}
+}
+
+static int android_enable_function(struct android_dev *dev, char *name)
+{
+	struct android_usb_function **functions = dev->functions;
+	struct android_usb_function *f;
+	while ((f = *functions++)) {
+		if (!strcmp(name, f->name)) {
+			list_add_tail(&f->enabled_list,
+						&dev->enabled_functions);
+			return 0;
+		}
+	}
+	return -EINVAL;
+}
+
+/*-------------------------------------------------------------------------*/
+/* /sys/class/android_usb/android%d/ interface */
+
+static ssize_t
+functions_show(struct device *pdev, struct device_attribute *attr, char *buf)
+{
+	struct android_dev *dev = dev_get_drvdata(pdev);
+	struct android_usb_function *f;
+	char *buff = buf;
+
+	mutex_lock(&dev->mutex);
+
+	list_for_each_entry(f, &dev->enabled_functions, enabled_list)
+		buff += sprintf(buff, "%s,", f->name);
+
+	mutex_unlock(&dev->mutex);
+
+	if (buff != buf)
+		*(buff-1) = '\n';
+	return buff - buf;
+}
+
+static ssize_t
+functions_store(struct device *pdev, struct device_attribute *attr,
+			       const char *buff, size_t size)
+{
+	struct android_dev *dev = dev_get_drvdata(pdev);
+	char *name;
+	char buf[256], *b;
+	char aliases[256], *a;
+	int err;
+	int is_ffs;
+	int ffs_enabled = 0;
+
+	mutex_lock(&dev->mutex);
+
+	if (dev->enabled) {
+		mutex_unlock(&dev->mutex);
+		return -EBUSY;
+	}
+
+	INIT_LIST_HEAD(&dev->enabled_functions);
+
+	strlcpy(buf, buff, sizeof(buf));
+	b = strim(buf);
+
+	while (b) {
+		name = strsep(&b, ",");
+		if (!name)
+			continue;
+
+		is_ffs = 0;
+		strlcpy(aliases, dev->ffs_aliases, sizeof(aliases));
+		a = aliases;
+
+		while (a) {
+			char *alias = strsep(&a, ",");
+			if (alias && !strcmp(name, alias)) {
+				is_ffs = 1;
+				break;
+			}
+		}
+
+		if (is_ffs) {
+			if (ffs_enabled)
+				continue;
+			err = android_enable_function(dev, "ffs");
+			if (err)
+				pr_err("android_usb: Cannot enable ffs (%d)",
+									err);
+			else
+				ffs_enabled = 1;
+			continue;
+		}
+
+		err = android_enable_function(dev, name);
+		if (err)
+			pr_err("android_usb: Cannot enable '%s' (%d)",
+							   name, err);
+	}
+
+	mutex_unlock(&dev->mutex);
+
+	return size;
+}
+
+static ssize_t enable_show(struct device *pdev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct android_dev *dev = dev_get_drvdata(pdev);
+	return sprintf(buf, "%d\n", dev->enabled);
+}
+
+static ssize_t enable_store(struct device *pdev, struct device_attribute *attr,
+			    const char *buff, size_t size)
+{
+	struct android_dev *dev = dev_get_drvdata(pdev);
+	struct usb_composite_dev *cdev = dev->cdev;
+	struct android_usb_function *f;
+	int enabled = 0;
+
+
+	if (!cdev)
+		return -ENODEV;
+
+	mutex_lock(&dev->mutex);
+
+	sscanf(buff, "%d", &enabled);
+	if (enabled && !dev->enabled) {
+		cdev->next_string_id = 0;
+		/*
+		 * Update values in composite driver's copy of
+		 * device descriptor.
+		 */
+		cdev->desc.idVendor = device_desc.idVendor;
+		cdev->desc.idProduct = device_desc.idProduct;
+		cdev->desc.bcdDevice = device_desc.bcdDevice;
+		cdev->desc.bDeviceClass = device_desc.bDeviceClass;
+		cdev->desc.bDeviceSubClass = device_desc.bDeviceSubClass;
+		cdev->desc.bDeviceProtocol = device_desc.bDeviceProtocol;
+		list_for_each_entry(f, &dev->enabled_functions, enabled_list) {
+			if (f->enable)
+				f->enable(f);
+		}
+		android_enable(dev);
+		dev->enabled = true;
+	} else if (!enabled && dev->enabled) {
+		android_disable(dev);
+		list_for_each_entry(f, &dev->enabled_functions, enabled_list) {
+			if (f->disable)
+				f->disable(f);
+		}
+		dev->enabled = false;
+	} else {
+		pr_err("android_usb: already %s\n",
+				dev->enabled ? "enabled" : "disabled");
+	}
+
+	mutex_unlock(&dev->mutex);
+	return size;
+}
+
+static ssize_t state_show(struct device *pdev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct android_dev *dev = dev_get_drvdata(pdev);
+	struct usb_composite_dev *cdev = dev->cdev;
+	char *state = "DISCONNECTED";
+	unsigned long flags;
+
+	if (!cdev)
+		goto out;
+
+	spin_lock_irqsave(&cdev->lock, flags);
+	if (cdev->config)
+		state = "CONFIGURED";
+	else if (dev->connected)
+		state = "CONNECTED";
+	spin_unlock_irqrestore(&cdev->lock, flags);
+out:
+	return sprintf(buf, "%s\n", state);
+}
+
+#define DESCRIPTOR_ATTR(field, format_string)				\
+static ssize_t								\
+field ## _show(struct device *dev, struct device_attribute *attr,	\
+		char *buf)						\
+{									\
+	return sprintf(buf, format_string, device_desc.field);		\
+}									\
+static ssize_t								\
+field ## _store(struct device *dev, struct device_attribute *attr,	\
+		const char *buf, size_t size)				\
+{									\
+	int value;							\
+	if (sscanf(buf, format_string, &value) == 1) {			\
+		device_desc.field = value;				\
+		return size;						\
+	}								\
+	return -1;							\
+}									\
+static DEVICE_ATTR(field, S_IRUGO | S_IWUSR, field ## _show, field ## _store);
+
+#define DESCRIPTOR_STRING_ATTR(field, buffer)				\
+static ssize_t								\
+field ## _show(struct device *dev, struct device_attribute *attr,	\
+		char *buf)						\
+{									\
+	return sprintf(buf, "%s", buffer);				\
+}									\
+static ssize_t								\
+field ## _store(struct device *dev, struct device_attribute *attr,	\
+		const char *buf, size_t size)				\
+{									\
+	if (size >= sizeof(buffer))					\
+		return -EINVAL;						\
+	return strlcpy(buffer, buf, sizeof(buffer));			\
+}									\
+static DEVICE_ATTR(field, S_IRUGO | S_IWUSR, field ## _show, field ## _store);
+
+
+DESCRIPTOR_ATTR(idVendor, "%04x\n")
+DESCRIPTOR_ATTR(idProduct, "%04x\n")
+DESCRIPTOR_ATTR(bcdDevice, "%04x\n")
+DESCRIPTOR_ATTR(bDeviceClass, "%d\n")
+DESCRIPTOR_ATTR(bDeviceSubClass, "%d\n")
+DESCRIPTOR_ATTR(bDeviceProtocol, "%d\n")
+DESCRIPTOR_STRING_ATTR(iManufacturer, manufacturer_string)
+DESCRIPTOR_STRING_ATTR(iProduct, product_string)
+DESCRIPTOR_STRING_ATTR(iSerial, serial_string)
+
+static DEVICE_ATTR(functions, S_IRUGO | S_IWUSR, functions_show,
+						 functions_store);
+static DEVICE_ATTR(enable, S_IRUGO | S_IWUSR, enable_show, enable_store);
+static DEVICE_ATTR(state, S_IRUGO, state_show, NULL);
+
+static struct device_attribute *android_usb_attributes[] = {
+	&dev_attr_idVendor,
+	&dev_attr_idProduct,
+	&dev_attr_bcdDevice,
+	&dev_attr_bDeviceClass,
+	&dev_attr_bDeviceSubClass,
+	&dev_attr_bDeviceProtocol,
+	&dev_attr_iManufacturer,
+	&dev_attr_iProduct,
+	&dev_attr_iSerial,
+	&dev_attr_functions,
+	&dev_attr_enable,
+	&dev_attr_state,
+	NULL
+};
+
+/*-------------------------------------------------------------------------*/
+/* Composite driver */
+
+static int android_bind_config(struct usb_configuration *c)
+{
+	struct android_dev *dev = _android_dev;
+	int ret = 0;
+
+	ret = android_bind_enabled_functions(dev, c);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static void android_unbind_config(struct usb_configuration *c)
+{
+	struct android_dev *dev = _android_dev;
+
+	android_unbind_enabled_functions(dev, c);
+}
+
+static int android_bind(struct usb_composite_dev *cdev)
+{
+	struct android_dev *dev = _android_dev;
+	struct usb_gadget	*gadget = cdev->gadget;
+	int			id, ret;
+
+	/* Save the default handler */
+	dev->setup_complete = cdev->req->complete;
+
+	/*
+	 * Start disconnected. Userspace will connect the gadget once
+	 * it is done configuring the functions.
+	 */
+	usb_gadget_disconnect(gadget);
+
+	ret = android_init_functions(dev->functions, cdev);
+	if (ret)
+		return ret;
+
+	/* Allocate string descriptor numbers ... note that string
+	 * contents can be overridden by the composite_dev glue.
+	 */
+	id = usb_string_id(cdev);
+	if (id < 0)
+		return id;
+	strings_dev[STRING_MANUFACTURER_IDX].id = id;
+	device_desc.iManufacturer = id;
+
+	id = usb_string_id(cdev);
+	if (id < 0)
+		return id;
+	strings_dev[STRING_PRODUCT_IDX].id = id;
+	device_desc.iProduct = id;
+
+	/* Default strings - should be updated by userspace */
+	strncpy(manufacturer_string, "Android", sizeof(manufacturer_string)-1);
+	strncpy(product_string, "Android", sizeof(product_string) - 1);
+	strncpy(serial_string, "0123456789ABCDEF", sizeof(serial_string) - 1);
+
+	id = usb_string_id(cdev);
+	if (id < 0)
+		return id;
+	strings_dev[STRING_SERIAL_IDX].id = id;
+	device_desc.iSerialNumber = id;
+
+	usb_gadget_set_selfpowered(gadget);
+	dev->cdev = cdev;
+
+	return 0;
+}
+
+static int android_usb_unbind(struct usb_composite_dev *cdev)
+{
+	struct android_dev *dev = _android_dev;
+
+	cancel_work_sync(&dev->work);
+	android_cleanup_functions(dev->functions);
+	return 0;
+}
+
+/* HACK: android needs to override setup for accessory to work */
+static int (*composite_setup_func)(struct usb_gadget *gadget, const struct usb_ctrlrequest *c);
+
+static int
+android_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *c)
+{
+	struct android_dev		*dev = _android_dev;
+	struct usb_composite_dev	*cdev = get_gadget_data(gadget);
+	struct usb_request		*req = cdev->req;
+	struct android_usb_function	*f;
+	int value = -EOPNOTSUPP;
+	unsigned long flags;
+
+	req->zero = 0;
+	req->length = 0;
+	req->complete = dev->setup_complete;
+	gadget->ep0->driver_data = cdev;
+
+	list_for_each_entry(f, &dev->enabled_functions, enabled_list) {
+		if (f->ctrlrequest) {
+			value = f->ctrlrequest(f, cdev, c);
+			if (value >= 0)
+				break;
+		}
+	}
+
+	/* Special case the accessory function.
+	 * It needs to handle control requests before it is enabled.
+	 */
+	if (value < 0)
+		value = acc_ctrlrequest(cdev, c);
+
+	if (value < 0)
+		value = composite_setup_func(gadget, c);
+
+	spin_lock_irqsave(&cdev->lock, flags);
+	if (!dev->connected) {
+		dev->connected = 1;
+		schedule_work(&dev->work);
+	} else if (c->bRequest == USB_REQ_SET_CONFIGURATION &&
+						cdev->config) {
+		schedule_work(&dev->work);
+	}
+	spin_unlock_irqrestore(&cdev->lock, flags);
+
+	return value;
+}
+
+static void android_disconnect(struct usb_composite_dev *cdev)
+{
+	struct android_dev *dev = _android_dev;
+
+	/* accessory HID support can be active while the
+	   accessory function is not actually enabled,
+	   so we need to inform it when we are disconnected.
+	 */
+	acc_disconnect();
+
+	dev->connected = 0;
+	schedule_work(&dev->work);
+}
+
+static struct usb_composite_driver android_usb_driver = {
+	.name		= "android_usb",
+	.dev		= &device_desc,
+	.strings	= dev_strings,
+	.bind		= android_bind,
+	.unbind		= android_usb_unbind,
+	.disconnect	= android_disconnect,
+	.max_speed	= USB_SPEED_HIGH,
+};
+
+static int android_create_device(struct android_dev *dev)
+{
+	struct device_attribute **attrs = android_usb_attributes;
+	struct device_attribute *attr;
+	int err;
+
+	dev->dev = device_create(android_class, NULL,
+					MKDEV(0, 0), NULL, "android0");
+	if (IS_ERR(dev->dev))
+		return PTR_ERR(dev->dev);
+
+	dev_set_drvdata(dev->dev, dev);
+
+	while ((attr = *attrs++)) {
+		err = device_create_file(dev->dev, attr);
+		if (err) {
+			device_destroy(android_class, dev->dev->devt);
+			return err;
+		}
+	}
+	return 0;
+}
+
+
+static int __init init(void)
+{
+	struct android_dev *dev;
+	int err;
+
+	android_class = class_create(THIS_MODULE, "android_usb");
+	if (IS_ERR(android_class))
+		return PTR_ERR(android_class);
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev) {
+		err = -ENOMEM;
+		goto err_dev;
+	}
+
+	dev->disable_depth = 1;
+	dev->functions = supported_functions;
+	INIT_LIST_HEAD(&dev->enabled_functions);
+	INIT_WORK(&dev->work, android_work);
+	mutex_init(&dev->mutex);
+
+	err = android_create_device(dev);
+	if (err) {
+		pr_err("%s: failed to create android device %d", __func__, err);
+		goto err_create;
+	}
+
+	_android_dev = dev;
+
+	err = usb_composite_probe(&android_usb_driver);
+	if (err) {
+		pr_err("%s: failed to probe driver %d", __func__, err);
+		goto err_probe;
+	}
+
+	/* HACK: exchange composite's setup with ours */
+	composite_setup_func = android_usb_driver.gadget_driver.setup;
+	android_usb_driver.gadget_driver.setup = android_setup;
+
+	return 0;
+
+err_probe:
+	device_destroy(android_class, dev->dev->devt);
+err_create:
+	kfree(dev);
+err_dev:
+	class_destroy(android_class);
+	return err;
+}
+late_initcall(init);
+
+static void __exit cleanup(void)
+{
+	usb_composite_unregister(&android_usb_driver);
+	class_destroy(android_class);
+	kfree(_android_dev);
+	_android_dev = NULL;
+}
+module_exit(cleanup);
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index c744e4975d7..db2becd31a5 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -449,6 +449,7 @@ ep_write (struct file *fd, const char __user *buf, size_t len, loff_t *ptr)
 		data->name, len, (int) value);
 free1:
 	mutex_unlock(&data->lock);
+	kfree (kbuf);
 	return value;
 }
 
@@ -564,7 +565,6 @@ static ssize_t ep_copy_to_user(struct kiocb_priv *priv)
 		if (total == 0)
 			break;
 	}
-
 	return len;
 }
 
@@ -583,6 +583,7 @@ static void ep_user_copy_worker(struct work_struct *work)
 	aio_complete(iocb, ret, ret);
 
 	kfree(priv->buf);
+	kfree(priv->iv);
 	kfree(priv);
 }
 
@@ -603,6 +604,7 @@ static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req)
 	 */
 	if (priv->iv == NULL || unlikely(req->actual == 0)) {
 		kfree(req->buf);
+		kfree(priv->iv);
 		kfree(priv);
 		iocb->private = NULL;
 		/* aio_complete() reports bytes-transferred _and_ faults */
@@ -638,7 +640,7 @@ ep_aio_rwtail(
 	struct usb_request	*req;
 	ssize_t			value;
 
-	priv = kmalloc(sizeof *priv, GFP_KERNEL);
+	priv = kzalloc(sizeof *priv, GFP_KERNEL);
 	if (!priv) {
 		value = -ENOMEM;
 fail:
@@ -647,7 +649,14 @@ fail:
 	}
 	iocb->private = priv;
 	priv->iocb = iocb;
-	priv->iv = iv;
+	if (iv) {
+		priv->iv = kmemdup(iv, nr_segs * sizeof(struct iovec),
+				   GFP_KERNEL);
+		if (!priv->iv) {
+			kfree(priv);
+			goto fail;
+		}
+	}
 	priv->nr_segs = nr_segs;
 	INIT_WORK(&priv->work, ep_user_copy_worker);
 
@@ -687,6 +696,7 @@ fail:
 	mutex_unlock(&epdata->lock);
 
 	if (unlikely(value)) {
+		kfree(priv->iv);
 		kfree(priv);
 		put_ep(epdata);
 	} else
diff --git a/drivers/usb/gadget/legacy/printer.c b/drivers/usb/gadget/legacy/printer.c
index 6474081dcba..c9c6dae75c1 100644
--- a/drivers/usb/gadget/legacy/printer.c
+++ b/drivers/usb/gadget/legacy/printer.c
@@ -980,6 +980,15 @@ unknown:
 		break;
 	}
 	/* host either stalls (value < 0) or reports success */
+	if (value >= 0) {
+		req->length = value;
+		req->zero = value < wLength;
+		value = usb_ep_queue(cdev->gadget->ep0, req, GFP_ATOMIC);
+		if (value < 0) {
+			ERROR(dev, "%s:%d Error!\n", __func__, __LINE__);
+			req->status = 0;
+		}
+	}
 	return value;
 }
 
diff --git a/drivers/usb/gadget/udc/at91_udc.c b/drivers/usb/gadget/udc/at91_udc.c
index 9968f5331fe..0716c1994e2 100644
--- a/drivers/usb/gadget/udc/at91_udc.c
+++ b/drivers/usb/gadget/udc/at91_udc.c
@@ -870,12 +870,10 @@ static void clk_on(struct at91_udc *udc)
 		return;
 	udc->clocked = 1;
 
-	if (IS_ENABLED(CONFIG_COMMON_CLK)) {
-		clk_set_rate(udc->uclk, 48000000);
-		clk_prepare_enable(udc->uclk);
-	}
-	clk_prepare_enable(udc->iclk);
-	clk_prepare_enable(udc->fclk);
+	if (IS_ENABLED(CONFIG_COMMON_CLK))
+		clk_enable(udc->uclk);
+	clk_enable(udc->iclk);
+	clk_enable(udc->fclk);
 }
 
 static void clk_off(struct at91_udc *udc)
@@ -884,10 +882,10 @@ static void clk_off(struct at91_udc *udc)
 		return;
 	udc->clocked = 0;
 	udc->gadget.speed = USB_SPEED_UNKNOWN;
-	clk_disable_unprepare(udc->fclk);
-	clk_disable_unprepare(udc->iclk);
+	clk_disable(udc->fclk);
+	clk_disable(udc->iclk);
 	if (IS_ENABLED(CONFIG_COMMON_CLK))
-		clk_disable_unprepare(udc->uclk);
+		clk_disable(udc->uclk);
 }
 
 /*
@@ -1780,14 +1778,24 @@ static int at91udc_probe(struct platform_device *pdev)
 	}
 
 	/* don't do anything until we have both gadget driver and VBUS */
+	if (IS_ENABLED(CONFIG_COMMON_CLK)) {
+		clk_set_rate(udc->uclk, 48000000);
+		retval = clk_prepare(udc->uclk);
+		if (retval)
+			goto fail1;
+	}
+	retval = clk_prepare(udc->fclk);
+	if (retval)
+		goto fail1a;
+
 	retval = clk_prepare_enable(udc->iclk);
 	if (retval)
-		goto fail1;
+		goto fail1b;
 	at91_udp_write(udc, AT91_UDP_TXVC, AT91_UDP_TXVC_TXVDIS);
 	at91_udp_write(udc, AT91_UDP_IDR, 0xffffffff);
 	/* Clear all pending interrupts - UDP may be used by bootloader. */
 	at91_udp_write(udc, AT91_UDP_ICR, 0xffffffff);
-	clk_disable_unprepare(udc->iclk);
+	clk_disable(udc->iclk);
 
 	/* request UDC and maybe VBUS irqs */
 	udc->udp_irq = platform_get_irq(pdev, 0);
@@ -1795,7 +1803,7 @@ static int at91udc_probe(struct platform_device *pdev)
 			0, driver_name, udc);
 	if (retval < 0) {
 		DBG("request irq %d failed\n", udc->udp_irq);
-		goto fail1;
+		goto fail1c;
 	}
 	if (gpio_is_valid(udc->board.vbus_pin)) {
 		retval = gpio_request(udc->board.vbus_pin, "udc_vbus");
@@ -1848,6 +1856,13 @@ fail3:
 		gpio_free(udc->board.vbus_pin);
 fail2:
 	free_irq(udc->udp_irq, udc);
+fail1c:
+	clk_unprepare(udc->iclk);
+fail1b:
+	clk_unprepare(udc->fclk);
+fail1a:
+	if (IS_ENABLED(CONFIG_COMMON_CLK))
+		clk_unprepare(udc->uclk);
 fail1:
 	if (IS_ENABLED(CONFIG_COMMON_CLK) && !IS_ERR(udc->uclk))
 		clk_put(udc->uclk);
@@ -1896,6 +1911,11 @@ static int __exit at91udc_remove(struct platform_device *pdev)
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	release_mem_region(res->start, resource_size(res));
 
+	if (IS_ENABLED(CONFIG_COMMON_CLK))
+		clk_unprepare(udc->uclk);
+	clk_unprepare(udc->fclk);
+	clk_unprepare(udc->iclk);
+
 	clk_put(udc->iclk);
 	clk_put(udc->fclk);
 	if (IS_ENABLED(CONFIG_COMMON_CLK))
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index 1529926e20a..840856ca3e6 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -716,10 +716,10 @@ static int queue_dma(struct usba_udc *udc, struct usba_ep *ep,
 	req->using_dma = 1;
 	req->ctrl = USBA_BF(DMA_BUF_LEN, req->req.length)
 			| USBA_DMA_CH_EN | USBA_DMA_END_BUF_IE
-			| USBA_DMA_END_TR_EN | USBA_DMA_END_TR_IE;
+			| USBA_DMA_END_BUF_EN;
 
-	if (ep->is_in)
-		req->ctrl |= USBA_DMA_END_BUF_EN;
+	if (!ep->is_in)
+		req->ctrl |= USBA_DMA_END_TR_EN | USBA_DMA_END_TR_IE;
 
 	/*
 	 * Add this request to the queue and submit for DMA if
@@ -828,7 +828,7 @@ static int usba_ep_dequeue(struct usb_ep *_ep, struct usb_request *_req)
 {
 	struct usba_ep *ep = to_usba_ep(_ep);
 	struct usba_udc *udc = ep->udc;
-	struct usba_request *req = to_usba_req(_req);
+	struct usba_request *req;
 	unsigned long flags;
 	u32 status;
 
@@ -837,6 +837,16 @@ static int usba_ep_dequeue(struct usb_ep *_ep, struct usb_request *_req)
 
 	spin_lock_irqsave(&udc->lock, flags);
 
+	list_for_each_entry(req, &ep->queue, queue) {
+		if (&req->req == _req)
+			break;
+	}
+
+	if (&req->req != _req) {
+		spin_unlock_irqrestore(&udc->lock, flags);
+		return -EINVAL;
+	}
+
 	if (req->using_dma) {
 		/*
 		 * If this request is currently being transferred,
@@ -1572,7 +1582,6 @@ static void usba_ep_irq(struct usba_udc *udc, struct usba_ep *ep)
 	if ((epstatus & epctrl) & USBA_RX_BK_RDY) {
 		DBG(DBG_BUS, "%s: RX data ready\n", ep->ep.name);
 		receive_data(ep);
-		usba_ep_writel(ep, CLR_STA, USBA_RX_BK_RDY);
 	}
 }
 
diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c
index f2054659f25..382d8b6bfd2 100644
--- a/drivers/usb/gadget/udc/udc-core.c
+++ b/drivers/usb/gadget/udc/udc-core.c
@@ -400,7 +400,15 @@ static int udc_bind_to_driver(struct usb_udc *udc, struct usb_gadget_driver *dri
 		driver->unbind(udc->gadget);
 		goto err1;
 	}
-	usb_gadget_connect(udc->gadget);
+	/*
+	 * HACK: The Android gadget driver disconnects the gadget
+	 * on bind and expects the gadget to stay disconnected until
+	 * it calls usb_gadget_connect when userspace is ready. Remove
+	 * the call to usb_gadget_connect bellow to avoid enabling the
+	 * pullup before userspace is ready.
+	 *
+	 * usb_gadget_connect(udc->gadget);
+	 */
 
 	kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE);
 	return 0;
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 15feaf924b7..3df32fa8c8a 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -787,12 +787,12 @@ static irqreturn_t ehci_irq (struct usb_hcd *hcd)
 					ehci->reset_done[i] == 0))
 				continue;
 
-			/* start 20 msec resume signaling from this port,
-			 * and make hub_wq collect PORT_STAT_C_SUSPEND to
-			 * stop that signaling.  Use 5 ms extra for safety,
-			 * like usb_port_resume() does.
+			/* start USB_RESUME_TIMEOUT msec resume signaling from
+			 * this port, and make hub_wq collect
+			 * PORT_STAT_C_SUSPEND to stop that signaling.
 			 */
-			ehci->reset_done[i] = jiffies + msecs_to_jiffies(25);
+			ehci->reset_done[i] = jiffies +
+				msecs_to_jiffies(USB_RESUME_TIMEOUT);
 			set_bit(i, &ehci->resuming_ports);
 			ehci_dbg (ehci, "port %d remote wakeup\n", i + 1);
 			usb_hcd_start_port_resume(&hcd->self, i);
diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c
index 5728829cf6e..ecd5d6a55ca 100644
--- a/drivers/usb/host/ehci-hub.c
+++ b/drivers/usb/host/ehci-hub.c
@@ -473,10 +473,13 @@ static int ehci_bus_resume (struct usb_hcd *hcd)
 		ehci_writel(ehci, temp, &ehci->regs->port_status [i]);
 	}
 
-	/* msleep for 20ms only if code is trying to resume port */
+	/*
+	 * msleep for USB_RESUME_TIMEOUT ms only if code is trying to resume
+	 * port
+	 */
 	if (resume_needed) {
 		spin_unlock_irq(&ehci->lock);
-		msleep(20);
+		msleep(USB_RESUME_TIMEOUT);
 		spin_lock_irq(&ehci->lock);
 		if (ehci->shutdown)
 			goto shutdown;
@@ -944,7 +947,7 @@ int ehci_hub_control(
 			temp &= ~PORT_WAKE_BITS;
 			ehci_writel(ehci, temp | PORT_RESUME, status_reg);
 			ehci->reset_done[wIndex] = jiffies
-					+ msecs_to_jiffies(20);
+					+ msecs_to_jiffies(USB_RESUME_TIMEOUT);
 			set_bit(wIndex, &ehci->resuming_ports);
 			usb_hcd_start_port_resume(&hcd->self, wIndex);
 			break;
diff --git a/drivers/usb/host/ehci-sched.c b/drivers/usb/host/ehci-sched.c
index e113fd73aea..c399606f154 100644
--- a/drivers/usb/host/ehci-sched.c
+++ b/drivers/usb/host/ehci-sched.c
@@ -1581,6 +1581,10 @@ iso_stream_schedule (
 	else
 		next = (now + 2 + 7) & ~0x07;	/* full frame cache */
 
+	/* If needed, initialize last_iso_frame so that this URB will be seen */
+	if (ehci->isoc_count == 0)
+		ehci->last_iso_frame = now >> 3;
+
 	/*
 	 * Use ehci->last_iso_frame as the base.  There can't be any
 	 * TDs scheduled for earlier than that.
@@ -1671,10 +1675,6 @@ iso_stream_schedule (
 	urb->start_frame = start & (mod - 1);
 	if (!stream->highspeed)
 		urb->start_frame >>= 3;
-
-	/* Make sure scan_isoc() sees these */
-	if (ehci->isoc_count == 0)
-		ehci->last_iso_frame = now >> 3;
 	return status;
 
  fail:
diff --git a/drivers/usb/host/fotg210-hcd.c b/drivers/usb/host/fotg210-hcd.c
index 3de1278677d..a2fbb0b3db3 100644
--- a/drivers/usb/host/fotg210-hcd.c
+++ b/drivers/usb/host/fotg210-hcd.c
@@ -1595,7 +1595,7 @@ static int fotg210_hub_control(
 			/* resume signaling for 20 msec */
 			fotg210_writel(fotg210, temp | PORT_RESUME, status_reg);
 			fotg210->reset_done[wIndex] = jiffies
-					+ msecs_to_jiffies(20);
+					+ msecs_to_jiffies(USB_RESUME_TIMEOUT);
 			break;
 		case USB_PORT_FEAT_C_SUSPEND:
 			clear_bit(wIndex, &fotg210->port_c_suspend);
diff --git a/drivers/usb/host/fusbh200-hcd.c b/drivers/usb/host/fusbh200-hcd.c
index abe42f31559..50fa8f2eabe 100644
--- a/drivers/usb/host/fusbh200-hcd.c
+++ b/drivers/usb/host/fusbh200-hcd.c
@@ -1550,10 +1550,9 @@ static int fusbh200_hub_control (
 			if ((temp & PORT_PE) == 0)
 				goto error;
 
-			/* resume signaling for 20 msec */
 			fusbh200_writel(fusbh200, temp | PORT_RESUME, status_reg);
 			fusbh200->reset_done[wIndex] = jiffies
-					+ msecs_to_jiffies(20);
+					+ msecs_to_jiffies(USB_RESUME_TIMEOUT);
 			break;
 		case USB_PORT_FEAT_C_SUSPEND:
 			clear_bit(wIndex, &fusbh200->port_c_suspend);
diff --git a/drivers/usb/host/isp116x-hcd.c b/drivers/usb/host/isp116x-hcd.c
index 240e792c81a..b62298fe0be 100644
--- a/drivers/usb/host/isp116x-hcd.c
+++ b/drivers/usb/host/isp116x-hcd.c
@@ -1487,7 +1487,7 @@ static int isp116x_bus_resume(struct usb_hcd *hcd)
 	spin_unlock_irq(&isp116x->lock);
 
 	hcd->state = HC_STATE_RESUMING;
-	msleep(20);
+	msleep(USB_RESUME_TIMEOUT);
 
 	/* Go operational */
 	spin_lock_irq(&isp116x->lock);
diff --git a/drivers/usb/host/isp1760-hcd.c b/drivers/usb/host/isp1760-hcd.c
index e752c3098f3..d2a85652847 100644
--- a/drivers/usb/host/isp1760-hcd.c
+++ b/drivers/usb/host/isp1760-hcd.c
@@ -2247,6 +2247,9 @@ struct usb_hcd *isp1760_register(phys_addr_t res_start, resource_size_t res_len,
 	hcd->rsrc_start = res_start;
 	hcd->rsrc_len = res_len;
 
+	/* This driver doesn't support wakeup requests */
+	hcd->cant_recv_wakeups = 1;
+
 	ret = usb_add_hcd(hcd, irq, irqflags);
 	if (ret)
 		goto err_unmap;
diff --git a/drivers/usb/host/oxu210hp-hcd.c b/drivers/usb/host/oxu210hp-hcd.c
index 4fe79a2d71a..c3d4074309f 100644
--- a/drivers/usb/host/oxu210hp-hcd.c
+++ b/drivers/usb/host/oxu210hp-hcd.c
@@ -2500,11 +2500,12 @@ static irqreturn_t oxu210_hcd_irq(struct usb_hcd *hcd)
 					|| oxu->reset_done[i] != 0)
 				continue;
 
-			/* start 20 msec resume signaling from this port,
-			 * and make hub_wq collect PORT_STAT_C_SUSPEND to
+			/* start USB_RESUME_TIMEOUT resume signaling from this
+			 * port, and make hub_wq collect PORT_STAT_C_SUSPEND to
 			 * stop that signaling.
 			 */
-			oxu->reset_done[i] = jiffies + msecs_to_jiffies(20);
+			oxu->reset_done[i] = jiffies +
+				msecs_to_jiffies(USB_RESUME_TIMEOUT);
 			oxu_dbg(oxu, "port %d remote wakeup\n", i + 1);
 			mod_timer(&hcd->rh_timer, oxu->reset_done[i]);
 		}
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index 2f3acebb577..f4e6b945136 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -571,7 +571,8 @@ static void quirk_usb_handoff_ohci(struct pci_dev *pdev)
 {
 	void __iomem *base;
 	u32 control;
-	u32 fminterval;
+	u32 fminterval = 0;
+	bool no_fminterval = false;
 	int cnt;
 
 	if (!mmio_resource_enabled(pdev, 0))
@@ -581,6 +582,13 @@ static void quirk_usb_handoff_ohci(struct pci_dev *pdev)
 	if (base == NULL)
 		return;
 
+	/*
+	 * ULi M5237 OHCI controller locks the whole system when accessing
+	 * the OHCI_FMINTERVAL offset.
+	 */
+	if (pdev->vendor == PCI_VENDOR_ID_AL && pdev->device == 0x5237)
+		no_fminterval = true;
+
 	control = readl(base + OHCI_CONTROL);
 
 /* On PA-RISC, PDC can leave IR set incorrectly; ignore it there. */
@@ -619,7 +627,9 @@ static void quirk_usb_handoff_ohci(struct pci_dev *pdev)
 	}
 
 	/* software reset of the controller, preserving HcFmInterval */
-	fminterval = readl(base + OHCI_FMINTERVAL);
+	if (!no_fminterval)
+		fminterval = readl(base + OHCI_FMINTERVAL);
+
 	writel(OHCI_HCR, base + OHCI_CMDSTATUS);
 
 	/* reset requires max 10 us delay */
@@ -628,7 +638,9 @@ static void quirk_usb_handoff_ohci(struct pci_dev *pdev)
 			break;
 		udelay(1);
 	}
-	writel(fminterval, base + OHCI_FMINTERVAL);
+
+	if (!no_fminterval)
+		writel(fminterval, base + OHCI_FMINTERVAL);
 
 	/* Now the controller is safely in SUSPEND and nothing can wake it up */
 	iounmap(base);
diff --git a/drivers/usb/host/r8a66597-hcd.c b/drivers/usb/host/r8a66597-hcd.c
index 110b4b9ebea..f130bb2f7bb 100644
--- a/drivers/usb/host/r8a66597-hcd.c
+++ b/drivers/usb/host/r8a66597-hcd.c
@@ -2300,7 +2300,7 @@ static int r8a66597_bus_resume(struct usb_hcd *hcd)
 		rh->port &= ~USB_PORT_STAT_SUSPEND;
 		rh->port |= USB_PORT_STAT_C_SUSPEND << 16;
 		r8a66597_mdfy(r8a66597, RESUME, RESUME | UACT, dvstctr_reg);
-		msleep(50);
+		msleep(USB_RESUME_TIMEOUT);
 		r8a66597_mdfy(r8a66597, UACT, RESUME | UACT, dvstctr_reg);
 	}
 
diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c
index ad0c348e68e..17f97f999c3 100644
--- a/drivers/usb/host/sl811-hcd.c
+++ b/drivers/usb/host/sl811-hcd.c
@@ -1259,7 +1259,7 @@ sl811h_hub_control(
 			sl811_write(sl811, SL11H_CTLREG1, sl811->ctrl1);
 
 			mod_timer(&sl811->timer, jiffies
-					+ msecs_to_jiffies(20));
+					+ msecs_to_jiffies(USB_RESUME_TIMEOUT));
 			break;
 		case USB_PORT_FEAT_POWER:
 			port_power(sl811, 0);
diff --git a/drivers/usb/host/uhci-hub.c b/drivers/usb/host/uhci-hub.c
index 93e17b12fb3..98c66d88ebd 100644
--- a/drivers/usb/host/uhci-hub.c
+++ b/drivers/usb/host/uhci-hub.c
@@ -165,7 +165,7 @@ static void uhci_check_ports(struct uhci_hcd *uhci)
 				/* Port received a wakeup request */
 				set_bit(port, &uhci->resuming_ports);
 				uhci->ports_timeout = jiffies +
-						msecs_to_jiffies(25);
+					msecs_to_jiffies(USB_RESUME_TIMEOUT);
 				usb_hcd_start_port_resume(
 						&uhci_to_hcd(uhci)->self, port);
 
@@ -337,7 +337,8 @@ static int uhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 			uhci_finish_suspend(uhci, port, port_addr);
 
 			/* USB v2.0 7.1.7.5 */
-			uhci->ports_timeout = jiffies + msecs_to_jiffies(50);
+			uhci->ports_timeout = jiffies +
+				msecs_to_jiffies(USB_RESUME_TIMEOUT);
 			break;
 		case USB_PORT_FEAT_POWER:
 			/* UHCI has no power switching */
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 388cfd83b6b..7ff97c39c8b 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -387,6 +387,10 @@ static void xhci_clear_port_change_bit(struct xhci_hcd *xhci, u16 wValue,
 		status = PORT_PLC;
 		port_change_bit = "link state";
 		break;
+	case USB_PORT_FEAT_C_PORT_CONFIG_ERROR:
+		status = PORT_CEC;
+		port_change_bit = "config error";
+		break;
 	default:
 		/* Should never happen */
 		return;
@@ -588,6 +592,8 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd,
 			status |= USB_PORT_STAT_C_LINK_STATE << 16;
 		if ((raw_port_status & PORT_WRC))
 			status |= USB_PORT_STAT_C_BH_RESET << 16;
+		if ((raw_port_status & PORT_CEC))
+			status |= USB_PORT_STAT_C_CONFIG_ERROR << 16;
 	}
 
 	if (hcd->speed != HCD_USB3) {
@@ -1005,6 +1011,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 		case USB_PORT_FEAT_C_OVER_CURRENT:
 		case USB_PORT_FEAT_C_ENABLE:
 		case USB_PORT_FEAT_C_PORT_LINK_STATE:
+		case USB_PORT_FEAT_C_PORT_CONFIG_ERROR:
 			xhci_clear_port_change_bit(xhci, wValue, wIndex,
 					port_array[wIndex], temp);
 			break;
@@ -1069,7 +1076,7 @@ int xhci_hub_status_data(struct usb_hcd *hcd, char *buf)
 	 */
 	status = bus_state->resuming_ports;
 
-	mask = PORT_CSC | PORT_PEC | PORT_OCC | PORT_PLC | PORT_WRC;
+	mask = PORT_CSC | PORT_PEC | PORT_OCC | PORT_PLC | PORT_WRC | PORT_CEC;
 
 	spin_lock_irqsave(&xhci->lock, flags);
 	/* For each port, did anything change?  If so, set that bit in buf. */
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 5cb3d7a1001..a67018eddf4 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1431,10 +1431,10 @@ int xhci_endpoint_init(struct xhci_hcd *xhci,
 		/* Attempt to use the ring cache */
 		if (virt_dev->num_rings_cached == 0)
 			return -ENOMEM;
+		virt_dev->num_rings_cached--;
 		virt_dev->eps[ep_index].new_ring =
 			virt_dev->ring_cache[virt_dev->num_rings_cached];
 		virt_dev->ring_cache[virt_dev->num_rings_cached] = NULL;
-		virt_dev->num_rings_cached--;
 		xhci_reinit_cached_ring(xhci, virt_dev->eps[ep_index].new_ring,
 					1, type);
 	}
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 142b601f956..2af32e26faf 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -37,6 +37,9 @@
 
 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_XHCI	0x8c31
 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI	0x9c31
+#define PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI		0x22b5
+#define PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_XHCI		0xa12f
+#define PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_XHCI	0x9d2f
 
 static const char hcd_name[] = "xhci_hcd";
 
@@ -82,6 +85,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 				"must be suspended extra slowly",
 				pdev->revision);
 		}
+		if (pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_PDK)
+			xhci->quirks |= XHCI_BROKEN_STREAMS;
 		/* Fresco Logic confirms: all revisions of this chip do not
 		 * support MSI, even though some of them claim to in their PCI
 		 * capabilities.
@@ -110,6 +115,7 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL) {
 		xhci->quirks |= XHCI_LPM_SUPPORT;
 		xhci->quirks |= XHCI_INTEL_HOST;
+		xhci->quirks |= XHCI_AVOID_BEI;
 	}
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
 			pdev->device == PCI_DEVICE_ID_INTEL_PANTHERPOINT_XHCI) {
@@ -125,12 +131,17 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		 * PPT chipsets.
 		 */
 		xhci->quirks |= XHCI_SPURIOUS_REBOOT;
-		xhci->quirks |= XHCI_AVOID_BEI;
 	}
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
 		pdev->device == PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI) {
 		xhci->quirks |= XHCI_SPURIOUS_REBOOT;
 	}
+	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
+		(pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_XHCI ||
+		 pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_XHCI ||
+		 pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI)) {
+		xhci->quirks |= XHCI_PME_STUCK_QUIRK;
+	}
 	if (pdev->vendor == PCI_VENDOR_ID_ETRON &&
 			pdev->device == PCI_DEVICE_ID_EJ168) {
 		xhci->quirks |= XHCI_RESET_ON_RESUME;
@@ -157,6 +168,21 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 				"QUIRK: Resetting on resume");
 }
 
+/*
+ * Make sure PME works on some Intel xHCI controllers by writing 1 to clear
+ * the Internal PME flag bit in vendor specific PMCTRL register at offset 0x80a4
+ */
+static void xhci_pme_quirk(struct xhci_hcd *xhci)
+{
+	u32 val;
+	void __iomem *reg;
+
+	reg = (void __iomem *) xhci->cap_regs + 0x80a4;
+	val = readl(reg);
+	writel(val | BIT(28), reg);
+	readl(reg);
+}
+
 /* called during probe() after chip reset completes */
 static int xhci_pci_setup(struct usb_hcd *hcd)
 {
@@ -281,6 +307,9 @@ static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup)
 	if (xhci->quirks & XHCI_COMP_MODE_QUIRK)
 		pdev->no_d3cold = true;
 
+	if (xhci->quirks & XHCI_PME_STUCK_QUIRK)
+		xhci_pme_quirk(xhci);
+
 	return xhci_suspend(xhci, do_wakeup);
 }
 
@@ -311,6 +340,9 @@ static int xhci_pci_resume(struct usb_hcd *hcd, bool hibernated)
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL)
 		usb_enable_intel_xhci_ports(pdev);
 
+	if (xhci->quirks & XHCI_PME_STUCK_QUIRK)
+		xhci_pme_quirk(xhci);
+
 	retval = xhci_resume(xhci, hibernated);
 	return retval;
 }
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 646300cbe5f..22516f41c6f 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -87,15 +87,6 @@ static int xhci_plat_probe(struct platform_device *pdev)
 	if (!res)
 		return -ENODEV;
 
-	if (of_device_is_compatible(pdev->dev.of_node,
-				    "marvell,armada-375-xhci") ||
-	    of_device_is_compatible(pdev->dev.of_node,
-				    "marvell,armada-380-xhci")) {
-		ret = xhci_mvebu_mbus_init_quirk(pdev);
-		if (ret)
-			return ret;
-	}
-
 	/* Initialize dma_mask and coherent_dma_mask to 32-bits */
 	ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
 	if (ret)
@@ -129,6 +120,15 @@ static int xhci_plat_probe(struct platform_device *pdev)
 			goto put_hcd;
 	}
 
+	if (of_device_is_compatible(pdev->dev.of_node,
+				    "marvell,armada-375-xhci") ||
+	    of_device_is_compatible(pdev->dev.of_node,
+				    "marvell,armada-380-xhci")) {
+		ret = xhci_mvebu_mbus_init_quirk(pdev);
+		if (ret)
+			goto disable_clk;
+	}
+
 	ret = usb_add_hcd(hcd, irq, IRQF_SHARED);
 	if (ret)
 		goto disable_clk;
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 06433aec81d..9848a67ddbb 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -1576,7 +1576,7 @@ static void handle_port_status(struct xhci_hcd *xhci,
 		} else {
 			xhci_dbg(xhci, "resume HS port %d\n", port_id);
 			bus_state->resume_done[faked_port_index] = jiffies +
-				msecs_to_jiffies(20);
+				msecs_to_jiffies(USB_RESUME_TIMEOUT);
 			set_bit(faked_port_index, &bus_state->resuming_ports);
 			mod_timer(&hcd->rh_timer,
 				  bus_state->resume_done[faked_port_index]);
@@ -1957,7 +1957,7 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td,
 	if (event_trb != ep_ring->dequeue) {
 		/* The event was for the status stage */
 		if (event_trb == td->last_trb) {
-			if (td->urb->actual_length != 0) {
+			if (td->urb_length_set) {
 				/* Don't overwrite a previously set error code
 				 */
 				if ((*status == -EINPROGRESS || *status == 0) &&
@@ -1971,7 +1971,13 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td,
 					td->urb->transfer_buffer_length;
 			}
 		} else {
-		/* Maybe the event was for the data stage? */
+			/*
+			 * Maybe the event was for the data stage? If so, update
+			 * already the actual_length of the URB and flag it as
+			 * set, so that it is not overwritten in the event for
+			 * the last TRB.
+			 */
+			td->urb_length_set = true;
 			td->urb->actual_length =
 				td->urb->transfer_buffer_length -
 				EVENT_TRB_LEN(le32_to_cpu(event->transfer_len));
@@ -2031,8 +2037,13 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td,
 		break;
 	case COMP_DEV_ERR:
 	case COMP_STALL:
+		frame->status = -EPROTO;
+		skip_td = true;
+		break;
 	case COMP_TX_ERR:
 		frame->status = -EPROTO;
+		if (event_trb != td->last_trb)
+			return 0;
 		skip_td = true;
 		break;
 	case COMP_STOP:
@@ -2645,7 +2656,7 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd)
 		xhci_halt(xhci);
 hw_died:
 		spin_unlock(&xhci->lock);
-		return -ESHUTDOWN;
+		return IRQ_HANDLED;
 	}
 
 	/*
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 033b46c470b..3bceabe109f 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -3803,6 +3803,15 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev,
 		return -EINVAL;
 	}
 
+	if (setup == SETUP_CONTEXT_ONLY) {
+		slot_ctx = xhci_get_slot_ctx(xhci, virt_dev->out_ctx);
+		if (GET_SLOT_STATE(le32_to_cpu(slot_ctx->dev_state)) ==
+		    SLOT_STATE_DEFAULT) {
+			xhci_dbg(xhci, "Slot already in default state\n");
+			return 0;
+		}
+	}
+
 	command = xhci_alloc_command(xhci, false, false, GFP_KERNEL);
 	if (!command)
 		return -ENOMEM;
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index d745715a1e2..54f386f8097 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1,3 +1,4 @@
+
 /*
  * xHCI host controller driver
  *
@@ -88,9 +89,10 @@ struct xhci_cap_regs {
 #define HCS_IST(p)		(((p) >> 0) & 0xf)
 /* bits 4:7, max number of Event Ring segments */
 #define HCS_ERST_MAX(p)		(((p) >> 4) & 0xf)
+/* bits 21:25 Hi 5 bits of Scratchpad buffers SW must allocate for the HW */
 /* bit 26 Scratchpad restore - for save/restore HW state - not used yet */
-/* bits 27:31 number of Scratchpad buffers SW must allocate for the HW */
-#define HCS_MAX_SCRATCHPAD(p)   (((p) >> 27) & 0x1f)
+/* bits 27:31 Lo 5 bits of Scratchpad buffers SW must allocate for the HW */
+#define HCS_MAX_SCRATCHPAD(p)   ((((p) >> 16) & 0x3e0) | (((p) >> 27) & 0x1f))
 
 /* HCSPARAMS3 - hcs_params3 - bitmasks */
 /* bits 0:7, Max U1 to U0 latency for the roothub ports */
@@ -1265,7 +1267,7 @@ union xhci_trb {
  * since the command ring is 64-byte aligned.
  * It must also be greater than 16.
  */
-#define TRBS_PER_SEGMENT	64
+#define TRBS_PER_SEGMENT	256
 /* Allow two commands + a link TRB, along with any reserved command TRBs */
 #define MAX_RSVD_CMD_TRBS	(TRBS_PER_SEGMENT - 3)
 #define TRB_SEGMENT_SIZE	(TRBS_PER_SEGMENT*16)
@@ -1288,6 +1290,8 @@ struct xhci_td {
 	struct xhci_segment	*start_seg;
 	union xhci_trb		*first_trb;
 	union xhci_trb		*last_trb;
+	/* actual_length of the URB has already been set */
+	bool			urb_length_set;
 };
 
 /* xHCI command default timeout value */
@@ -1560,6 +1564,7 @@ struct xhci_hcd {
 #define XHCI_SPURIOUS_WAKEUP	(1 << 18)
 /* For controllers with a broken beyond repair streams implementation */
 #define XHCI_BROKEN_STREAMS	(1 << 19)
+#define XHCI_PME_STUCK_QUIRK	(1 << 20)
 	unsigned int		num_active_eps;
 	unsigned int		limit_active_eps;
 	/* There are two roothubs to keep track of bus suspend info for */
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index b841ee0bff0..6d63efce370 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -99,6 +99,7 @@
 #include <linux/platform_device.h>
 #include <linux/io.h>
 #include <linux/dma-mapping.h>
+#include <linux/usb.h>
 
 #include "musb_core.h"
 
@@ -480,7 +481,7 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 						 + msecs_to_jiffies(20);
 				schedule_delayed_work(
 					&musb->finish_resume_work,
-					msecs_to_jiffies(20));
+					msecs_to_jiffies(USB_RESUME_TIMEOUT));
 
 				musb->xceiv->state = OTG_STATE_A_HOST;
 				musb->is_active = 1;
@@ -1521,16 +1522,30 @@ irqreturn_t musb_interrupt(struct musb *musb)
 		is_host_active(musb) ? "host" : "peripheral",
 		musb->int_usb, musb->int_tx, musb->int_rx);
 
-	/* the core can interrupt us for multiple reasons; docs have
-	 * a generic interrupt flowchart to follow
+	/**
+	 * According to Mentor Graphics' documentation, flowchart on page 98,
+	 * IRQ should be handled as follows:
+	 *
+	 * . Resume IRQ
+	 * . Session Request IRQ
+	 * . VBUS Error IRQ
+	 * . Suspend IRQ
+	 * . Connect IRQ
+	 * . Disconnect IRQ
+	 * . Reset/Babble IRQ
+	 * . SOF IRQ (we're not using this one)
+	 * . Endpoint 0 IRQ
+	 * . TX Endpoints
+	 * . RX Endpoints
+	 *
+	 * We will be following that flowchart in order to avoid any problems
+	 * that might arise with internal Finite State Machine.
 	 */
+
 	if (musb->int_usb)
 		retval |= musb_stage0_irq(musb, musb->int_usb,
 				devctl);
 
-	/* "stage 1" is handling endpoint irqs */
-
-	/* handle endpoint 0 first */
 	if (musb->int_tx & 1) {
 		if (is_host_active(musb))
 			retval |= musb_h_ep0_irq(musb);
@@ -1538,37 +1553,31 @@ irqreturn_t musb_interrupt(struct musb *musb)
 			retval |= musb_g_ep0_irq(musb);
 	}
 
-	/* RX on endpoints 1-15 */
-	reg = musb->int_rx >> 1;
+	reg = musb->int_tx >> 1;
 	ep_num = 1;
 	while (reg) {
 		if (reg & 1) {
-			/* musb_ep_select(musb->mregs, ep_num); */
-			/* REVISIT just retval = ep->rx_irq(...) */
 			retval = IRQ_HANDLED;
 			if (is_host_active(musb))
-				musb_host_rx(musb, ep_num);
+				musb_host_tx(musb, ep_num);
 			else
-				musb_g_rx(musb, ep_num);
+				musb_g_tx(musb, ep_num);
 		}
-
 		reg >>= 1;
 		ep_num++;
 	}
 
-	/* TX on endpoints 1-15 */
-	reg = musb->int_tx >> 1;
+	reg = musb->int_rx >> 1;
 	ep_num = 1;
 	while (reg) {
 		if (reg & 1) {
-			/* musb_ep_select(musb->mregs, ep_num); */
-			/* REVISIT just retval |= ep->tx_irq(...) */
 			retval = IRQ_HANDLED;
 			if (is_host_active(musb))
-				musb_host_tx(musb, ep_num);
+				musb_host_rx(musb, ep_num);
 			else
-				musb_g_tx(musb, ep_num);
+				musb_g_rx(musb, ep_num);
 		}
+
 		reg >>= 1;
 		ep_num++;
 	}
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index 855793d701b..4500610356f 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -2663,7 +2663,6 @@ void musb_host_cleanup(struct musb *musb)
 	if (musb->port_mode == MUSB_PORT_MODE_GADGET)
 		return;
 	usb_remove_hcd(musb->hcd);
-	musb->hcd = NULL;
 }
 
 void musb_host_free(struct musb *musb)
diff --git a/drivers/usb/musb/musb_virthub.c b/drivers/usb/musb/musb_virthub.c
index e2d2d8c9891..1e9bde4fe78 100644
--- a/drivers/usb/musb/musb_virthub.c
+++ b/drivers/usb/musb/musb_virthub.c
@@ -136,7 +136,7 @@ void musb_port_suspend(struct musb *musb, bool do_suspend)
 		/* later, GetPortStatus will stop RESUME signaling */
 		musb->port1_status |= MUSB_PORT_STAT_RESUME;
 		schedule_delayed_work(&musb->finish_resume_work,
-				      msecs_to_jiffies(20));
+				      msecs_to_jiffies(USB_RESUME_TIMEOUT));
 	}
 }
 
@@ -273,9 +273,7 @@ static int musb_has_gadget(struct musb *musb)
 #ifdef CONFIG_USB_MUSB_HOST
 	return 1;
 #else
-	if (musb->port_mode == MUSB_PORT_MODE_HOST)
-		return 1;
-	return musb->g.dev.driver != NULL;
+	return musb->port_mode == MUSB_PORT_MODE_HOST;
 #endif
 }
 
diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig
index 0cd1f44f0ee..77ef4bb73d4 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -6,6 +6,14 @@ menu "USB Physical Layer drivers"
 config USB_PHY
 	def_bool n
 
+config USB_OTG_WAKELOCK
+	bool "Hold a wakelock when USB connected"
+	depends on WAKELOCK
+	select USB_OTG_UTILS
+	help
+	  Select this to automatically hold a wakelock when USB is
+	  connected, preventing suspend.
+
 #
 # USB Transceiver Drivers
 #
@@ -213,4 +221,13 @@ config USB_ULPI_VIEWPORT
 	  Provides read/write operations to the ULPI phy register set for
 	  controllers with a viewport register (e.g. Chipidea/ARC controllers).
 
+config DUAL_ROLE_USB_INTF
+	bool "Generic DUAL ROLE sysfs interface"
+	depends on SYSFS && USB_PHY
+	help
+	  A generic sysfs interface to track and change the state of
+	  dual role usb phys. The usb phy drivers can register to
+	  this interface to expose it capabilities to the userspace
+	  and thereby allowing userspace to change the port mode.
+
 endmenu
diff --git a/drivers/usb/phy/Makefile b/drivers/usb/phy/Makefile
index 75f2bba58c8..5cd78717b13 100644
--- a/drivers/usb/phy/Makefile
+++ b/drivers/usb/phy/Makefile
@@ -3,6 +3,8 @@
 #
 obj-$(CONFIG_USB_PHY)			+= phy.o
 obj-$(CONFIG_OF)			+= of.o
+obj-$(CONFIG_USB_OTG_WAKELOCK)		+= otg-wakelock.o
+obj-$(CONFIG_DUAL_ROLE_USB_INTF)	+= class-dual-role.o
 
 # transceiver drivers, keep the list sorted
 
diff --git a/drivers/usb/phy/class-dual-role.c b/drivers/usb/phy/class-dual-role.c
new file mode 100644
index 00000000000..51fcb545a9d
--- /dev/null
+++ b/drivers/usb/phy/class-dual-role.c
@@ -0,0 +1,529 @@
+/*
+ * class-dual-role.c
+ *
+ * Copyright (C) 2015 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/ctype.h>
+#include <linux/device.h>
+#include <linux/usb/class-dual-role.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/types.h>
+
+#define DUAL_ROLE_NOTIFICATION_TIMEOUT 2000
+
+static ssize_t dual_role_store_property(struct device *dev,
+					struct device_attribute *attr,
+					const char *buf, size_t count);
+static ssize_t dual_role_show_property(struct device *dev,
+				       struct device_attribute *attr,
+				       char *buf);
+
+#define DUAL_ROLE_ATTR(_name)				\
+{							\
+	.attr = { .name = #_name },			\
+	.show = dual_role_show_property,		\
+	.store = dual_role_store_property,		\
+}
+
+static struct device_attribute dual_role_attrs[] = {
+	DUAL_ROLE_ATTR(supported_modes),
+	DUAL_ROLE_ATTR(mode),
+	DUAL_ROLE_ATTR(power_role),
+	DUAL_ROLE_ATTR(data_role),
+	DUAL_ROLE_ATTR(powers_vconn),
+};
+
+struct class *dual_role_class;
+EXPORT_SYMBOL_GPL(dual_role_class);
+
+static struct device_type dual_role_dev_type;
+
+static char *kstrdupcase(const char *str, gfp_t gfp, bool to_upper)
+{
+	char *ret, *ustr;
+
+	ustr = ret = kmalloc(strlen(str) + 1, gfp);
+
+	if (!ret)
+		return NULL;
+
+	while (*str)
+		*ustr++ = to_upper ? toupper(*str++) : tolower(*str++);
+
+	*ustr = 0;
+
+	return ret;
+}
+
+static void dual_role_changed_work(struct work_struct *work)
+{
+	struct dual_role_phy_instance *dual_role =
+	    container_of(work, struct dual_role_phy_instance,
+			 changed_work);
+
+	dev_dbg(&dual_role->dev, "%s\n", __func__);
+	kobject_uevent(&dual_role->dev.kobj, KOBJ_CHANGE);
+}
+
+void dual_role_instance_changed(struct dual_role_phy_instance *dual_role)
+{
+	dev_dbg(&dual_role->dev, "%s\n", __func__);
+	pm_wakeup_event(&dual_role->dev, DUAL_ROLE_NOTIFICATION_TIMEOUT);
+	schedule_work(&dual_role->changed_work);
+}
+EXPORT_SYMBOL_GPL(dual_role_instance_changed);
+
+int dual_role_get_property(struct dual_role_phy_instance *dual_role,
+			   enum dual_role_property prop,
+			   unsigned int *val)
+{
+	return dual_role->desc->get_property(dual_role, prop, val);
+}
+EXPORT_SYMBOL_GPL(dual_role_get_property);
+
+int dual_role_set_property(struct dual_role_phy_instance *dual_role,
+			   enum dual_role_property prop,
+			   const unsigned int *val)
+{
+	if (!dual_role->desc->set_property)
+		return -ENODEV;
+
+	return dual_role->desc->set_property(dual_role, prop, val);
+}
+EXPORT_SYMBOL_GPL(dual_role_set_property);
+
+int dual_role_property_is_writeable(struct dual_role_phy_instance *dual_role,
+				    enum dual_role_property prop)
+{
+	if (!dual_role->desc->property_is_writeable)
+		return -ENODEV;
+
+	return dual_role->desc->property_is_writeable(dual_role, prop);
+}
+EXPORT_SYMBOL_GPL(dual_role_property_is_writeable);
+
+static void dual_role_dev_release(struct device *dev)
+{
+	struct dual_role_phy_instance *dual_role =
+	    container_of(dev, struct dual_role_phy_instance, dev);
+	pr_debug("device: '%s': %s\n", dev_name(dev), __func__);
+	kfree(dual_role);
+}
+
+static struct dual_role_phy_instance *__must_check
+__dual_role_register(struct device *parent,
+		     const struct dual_role_phy_desc *desc)
+{
+	struct device *dev;
+	struct dual_role_phy_instance *dual_role;
+	int rc;
+
+	dual_role = kzalloc(sizeof(*dual_role), GFP_KERNEL);
+	if (!dual_role)
+		return ERR_PTR(-ENOMEM);
+
+	dev = &dual_role->dev;
+
+	device_initialize(dev);
+
+	dev->class = dual_role_class;
+	dev->type = &dual_role_dev_type;
+	dev->parent = parent;
+	dev->release = dual_role_dev_release;
+	dev_set_drvdata(dev, dual_role);
+	dual_role->desc = desc;
+
+	rc = dev_set_name(dev, "%s", desc->name);
+	if (rc)
+		goto dev_set_name_failed;
+
+	INIT_WORK(&dual_role->changed_work, dual_role_changed_work);
+
+	rc = device_init_wakeup(dev, true);
+	if (rc)
+		goto wakeup_init_failed;
+
+	rc = device_add(dev);
+	if (rc)
+		goto device_add_failed;
+
+	dual_role_instance_changed(dual_role);
+
+	return dual_role;
+
+device_add_failed:
+	device_init_wakeup(dev, false);
+wakeup_init_failed:
+dev_set_name_failed:
+	put_device(dev);
+	kfree(dual_role);
+
+	return ERR_PTR(rc);
+}
+
+static void dual_role_instance_unregister(struct dual_role_phy_instance
+					  *dual_role)
+{
+	cancel_work_sync(&dual_role->changed_work);
+	device_init_wakeup(&dual_role->dev, false);
+	device_unregister(&dual_role->dev);
+}
+
+static void devm_dual_role_release(struct device *dev, void *res)
+{
+	struct dual_role_phy_instance **dual_role = res;
+
+	dual_role_instance_unregister(*dual_role);
+}
+
+struct dual_role_phy_instance *__must_check
+devm_dual_role_instance_register(struct device *parent,
+				 const struct dual_role_phy_desc *desc)
+{
+	struct dual_role_phy_instance **ptr, *dual_role;
+
+	ptr = devres_alloc(devm_dual_role_release, sizeof(*ptr), GFP_KERNEL);
+
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+	dual_role = __dual_role_register(parent, desc);
+	if (IS_ERR(dual_role)) {
+		devres_free(ptr);
+	} else {
+		*ptr = dual_role;
+		devres_add(parent, ptr);
+	}
+	return dual_role;
+}
+EXPORT_SYMBOL_GPL(devm_dual_role_instance_register);
+
+static int devm_dual_role_match(struct device *dev, void *res, void *data)
+{
+	struct dual_role_phy_instance **r = res;
+
+	if (WARN_ON(!r || !*r))
+		return 0;
+
+	return *r == data;
+}
+
+void devm_dual_role_instance_unregister(struct device *dev,
+					struct dual_role_phy_instance
+					*dual_role)
+{
+	int rc;
+
+	rc = devres_release(dev, devm_dual_role_release,
+			    devm_dual_role_match, dual_role);
+	WARN_ON(rc);
+}
+EXPORT_SYMBOL_GPL(devm_dual_role_instance_unregister);
+
+void *dual_role_get_drvdata(struct dual_role_phy_instance *dual_role)
+{
+	return dual_role->drv_data;
+}
+EXPORT_SYMBOL_GPL(dual_role_get_drvdata);
+
+/***************** Device attribute functions **************************/
+
+/* port type */
+static char *supported_modes_text[] = {
+	"ufp dfp", "dfp", "ufp"
+};
+
+/* current mode */
+static char *mode_text[] = {
+	"ufp", "dfp", "none"
+};
+
+/* Power role */
+static char *pr_text[] = {
+	"source", "sink", "none"
+};
+
+/* Data role */
+static char *dr_text[] = {
+	"host", "device", "none"
+};
+
+/* Vconn supply */
+static char *vconn_supply_text[] = {
+	"n", "y"
+};
+
+static ssize_t dual_role_show_property(struct device *dev,
+				       struct device_attribute *attr, char *buf)
+{
+	ssize_t ret = 0;
+	struct dual_role_phy_instance *dual_role = dev_get_drvdata(dev);
+	const ptrdiff_t off = attr - dual_role_attrs;
+	unsigned int value;
+
+	if (off == DUAL_ROLE_PROP_SUPPORTED_MODES) {
+		value = dual_role->desc->supported_modes;
+	} else {
+		ret = dual_role_get_property(dual_role, off, &value);
+
+		if (ret < 0) {
+			if (ret == -ENODATA)
+				dev_dbg(dev,
+					"driver has no data for `%s' property\n",
+					attr->attr.name);
+			else if (ret != -ENODEV)
+				dev_err(dev,
+					"driver failed to report `%s' property: %zd\n",
+					attr->attr.name, ret);
+			return ret;
+		}
+	}
+
+	if (off == DUAL_ROLE_PROP_SUPPORTED_MODES) {
+		BUILD_BUG_ON(DUAL_ROLE_PROP_SUPPORTED_MODES_TOTAL !=
+			ARRAY_SIZE(supported_modes_text));
+		if (value < DUAL_ROLE_PROP_SUPPORTED_MODES_TOTAL)
+			return snprintf(buf, PAGE_SIZE, "%s\n",
+					supported_modes_text[value]);
+		else
+			return -EIO;
+	} else if (off == DUAL_ROLE_PROP_MODE) {
+		BUILD_BUG_ON(DUAL_ROLE_PROP_MODE_TOTAL !=
+			ARRAY_SIZE(mode_text));
+		if (value < DUAL_ROLE_PROP_MODE_TOTAL)
+			return snprintf(buf, PAGE_SIZE, "%s\n",
+					mode_text[value]);
+		else
+			return -EIO;
+	} else if (off == DUAL_ROLE_PROP_PR) {
+		BUILD_BUG_ON(DUAL_ROLE_PROP_PR_TOTAL != ARRAY_SIZE(pr_text));
+		if (value < DUAL_ROLE_PROP_PR_TOTAL)
+			return snprintf(buf, PAGE_SIZE, "%s\n",
+					pr_text[value]);
+		else
+			return -EIO;
+	} else if (off == DUAL_ROLE_PROP_DR) {
+		BUILD_BUG_ON(DUAL_ROLE_PROP_DR_TOTAL != ARRAY_SIZE(dr_text));
+		if (value < DUAL_ROLE_PROP_DR_TOTAL)
+			return snprintf(buf, PAGE_SIZE, "%s\n",
+					dr_text[value]);
+		else
+			return -EIO;
+	} else if (off == DUAL_ROLE_PROP_VCONN_SUPPLY) {
+		BUILD_BUG_ON(DUAL_ROLE_PROP_VCONN_SUPPLY_TOTAL !=
+				ARRAY_SIZE(vconn_supply_text));
+		if (value < DUAL_ROLE_PROP_VCONN_SUPPLY_TOTAL)
+			return snprintf(buf, PAGE_SIZE, "%s\n",
+					vconn_supply_text[value]);
+		else
+			return -EIO;
+	} else
+		return -EIO;
+}
+
+static ssize_t dual_role_store_property(struct device *dev,
+					struct device_attribute *attr,
+					const char *buf, size_t count)
+{
+	ssize_t ret;
+	struct dual_role_phy_instance *dual_role = dev_get_drvdata(dev);
+	const ptrdiff_t off = attr - dual_role_attrs;
+	unsigned int value;
+	int total, i;
+	char *dup_buf, **text_array;
+	bool result = false;
+
+	dup_buf = kstrdupcase(buf, GFP_KERNEL, false);
+	switch (off) {
+	case DUAL_ROLE_PROP_MODE:
+		total = DUAL_ROLE_PROP_MODE_TOTAL;
+		text_array = mode_text;
+		break;
+	case DUAL_ROLE_PROP_PR:
+		total = DUAL_ROLE_PROP_PR_TOTAL;
+		text_array = pr_text;
+		break;
+	case DUAL_ROLE_PROP_DR:
+		total = DUAL_ROLE_PROP_DR_TOTAL;
+		text_array = dr_text;
+		break;
+	case DUAL_ROLE_PROP_VCONN_SUPPLY:
+		ret = strtobool(dup_buf, &result);
+		value = result;
+		if (!ret)
+			goto setprop;
+	default:
+		ret = -EINVAL;
+		goto error;
+	}
+
+	for (i = 0; i <= total; i++) {
+		if (i == total) {
+			ret = -ENOTSUPP;
+			goto error;
+		}
+		if (!strncmp(*(text_array + i), dup_buf,
+			     strlen(*(text_array + i)))) {
+			value = i;
+			break;
+		}
+	}
+
+setprop:
+	ret = dual_role->desc->set_property(dual_role, off, &value);
+
+error:
+	kfree(dup_buf);
+
+	if (ret < 0)
+		return ret;
+
+	return count;
+}
+
+static umode_t dual_role_attr_is_visible(struct kobject *kobj,
+					 struct attribute *attr, int attrno)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct dual_role_phy_instance *dual_role = dev_get_drvdata(dev);
+	umode_t mode = S_IRUSR | S_IRGRP | S_IROTH;
+	int i;
+
+	if (attrno == DUAL_ROLE_PROP_SUPPORTED_MODES)
+		return mode;
+
+	for (i = 0; i < dual_role->desc->num_properties; i++) {
+		int property = dual_role->desc->properties[i];
+
+		if (property == attrno) {
+			if (dual_role->desc->property_is_writeable &&
+			    dual_role_property_is_writeable(dual_role, property)
+			    > 0)
+				mode |= S_IWUSR;
+
+			return mode;
+		}
+	}
+
+	return 0;
+}
+
+static struct attribute *__dual_role_attrs[ARRAY_SIZE(dual_role_attrs) + 1];
+
+static struct attribute_group dual_role_attr_group = {
+	.attrs = __dual_role_attrs,
+	.is_visible = dual_role_attr_is_visible,
+};
+
+static const struct attribute_group *dual_role_attr_groups[] = {
+	&dual_role_attr_group,
+	NULL,
+};
+
+void dual_role_init_attrs(struct device_type *dev_type)
+{
+	int i;
+
+	dev_type->groups = dual_role_attr_groups;
+
+	for (i = 0; i < ARRAY_SIZE(dual_role_attrs); i++)
+		__dual_role_attrs[i] = &dual_role_attrs[i].attr;
+}
+
+int dual_role_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	struct dual_role_phy_instance *dual_role = dev_get_drvdata(dev);
+	int ret = 0, j;
+	char *prop_buf;
+	char *attrname;
+
+	dev_dbg(dev, "uevent\n");
+
+	if (!dual_role || !dual_role->desc) {
+		dev_dbg(dev, "No dual_role phy yet\n");
+		return ret;
+	}
+
+	dev_dbg(dev, "DUAL_ROLE_NAME=%s\n", dual_role->desc->name);
+
+	ret = add_uevent_var(env, "DUAL_ROLE_NAME=%s", dual_role->desc->name);
+	if (ret)
+		return ret;
+
+	prop_buf = (char *)get_zeroed_page(GFP_KERNEL);
+	if (!prop_buf)
+		return -ENOMEM;
+
+	for (j = 0; j < dual_role->desc->num_properties; j++) {
+		struct device_attribute *attr;
+		char *line;
+
+		attr = &dual_role_attrs[dual_role->desc->properties[j]];
+
+		ret = dual_role_show_property(dev, attr, prop_buf);
+		if (ret == -ENODEV || ret == -ENODATA) {
+			ret = 0;
+			continue;
+		}
+
+		if (ret < 0)
+			goto out;
+		line = strnchr(prop_buf, PAGE_SIZE, '\n');
+		if (line)
+			*line = 0;
+
+		attrname = kstrdupcase(attr->attr.name, GFP_KERNEL, true);
+		if (!attrname)
+			ret = -ENOMEM;
+
+		dev_dbg(dev, "prop %s=%s\n", attrname, prop_buf);
+
+		ret = add_uevent_var(env, "DUAL_ROLE_%s=%s", attrname,
+				     prop_buf);
+		kfree(attrname);
+		if (ret)
+			goto out;
+	}
+
+out:
+	free_page((unsigned long)prop_buf);
+
+	return ret;
+}
+
+/******************* Module Init ***********************************/
+
+static int __init dual_role_class_init(void)
+{
+	dual_role_class = class_create(THIS_MODULE, "dual_role_usb");
+
+	if (IS_ERR(dual_role_class))
+		return PTR_ERR(dual_role_class);
+
+	dual_role_class->dev_uevent = dual_role_uevent;
+	dual_role_init_attrs(&dual_role_dev_type);
+
+	return 0;
+}
+
+static void __exit dual_role_class_exit(void)
+{
+	class_destroy(dual_role_class);
+}
+
+subsys_initcall(dual_role_class_init);
+module_exit(dual_role_class_exit);
diff --git a/drivers/usb/phy/otg-wakelock.c b/drivers/usb/phy/otg-wakelock.c
new file mode 100644
index 00000000000..479376bfa48
--- /dev/null
+++ b/drivers/usb/phy/otg-wakelock.c
@@ -0,0 +1,173 @@
+/*
+ * otg-wakelock.c
+ *
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/wakelock.h>
+#include <linux/spinlock.h>
+#include <linux/usb/otg.h>
+
+#define TEMPORARY_HOLD_TIME	2000
+
+static bool enabled = true;
+static struct usb_phy *otgwl_xceiv;
+static struct notifier_block otgwl_nb;
+
+/*
+ * otgwl_spinlock is held while the VBUS lock is grabbed or dropped and the
+ * held field is updated to match.
+ */
+
+static DEFINE_SPINLOCK(otgwl_spinlock);
+
+/*
+ * Only one lock, but since these 3 fields are associated with each other...
+ */
+
+struct otgwl_lock {
+	char name[40];
+	struct wake_lock wakelock;
+	bool held;
+};
+
+/*
+ * VBUS present lock.  Also used as a timed lock on charger
+ * connect/disconnect and USB host disconnect, to allow the system
+ * to react to the change in power.
+ */
+
+static struct otgwl_lock vbus_lock;
+
+static void otgwl_hold(struct otgwl_lock *lock)
+{
+	if (!lock->held) {
+		wake_lock(&lock->wakelock);
+		lock->held = true;
+	}
+}
+
+static void otgwl_temporary_hold(struct otgwl_lock *lock)
+{
+	wake_lock_timeout(&lock->wakelock,
+			  msecs_to_jiffies(TEMPORARY_HOLD_TIME));
+	lock->held = false;
+}
+
+static void otgwl_drop(struct otgwl_lock *lock)
+{
+	if (lock->held) {
+		wake_unlock(&lock->wakelock);
+		lock->held = false;
+	}
+}
+
+static void otgwl_handle_event(unsigned long event)
+{
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&otgwl_spinlock, irqflags);
+
+	if (!enabled) {
+		otgwl_drop(&vbus_lock);
+		spin_unlock_irqrestore(&otgwl_spinlock, irqflags);
+		return;
+	}
+
+	switch (event) {
+	case USB_EVENT_VBUS:
+	case USB_EVENT_ENUMERATED:
+		otgwl_hold(&vbus_lock);
+		break;
+
+	case USB_EVENT_NONE:
+	case USB_EVENT_ID:
+	case USB_EVENT_CHARGER:
+		otgwl_temporary_hold(&vbus_lock);
+		break;
+
+	default:
+		break;
+	}
+
+	spin_unlock_irqrestore(&otgwl_spinlock, irqflags);
+}
+
+static int otgwl_otg_notifications(struct notifier_block *nb,
+				   unsigned long event, void *unused)
+{
+	otgwl_handle_event(event);
+	return NOTIFY_OK;
+}
+
+static int set_enabled(const char *val, const struct kernel_param *kp)
+{
+	int rv = param_set_bool(val, kp);
+
+	if (rv)
+		return rv;
+
+	if (otgwl_xceiv)
+		otgwl_handle_event(otgwl_xceiv->last_event);
+
+	return 0;
+}
+
+static struct kernel_param_ops enabled_param_ops = {
+	.set = set_enabled,
+	.get = param_get_bool,
+};
+
+module_param_cb(enabled, &enabled_param_ops, &enabled, 0644);
+MODULE_PARM_DESC(enabled, "enable wakelock when VBUS present");
+
+static int __init otg_wakelock_init(void)
+{
+	int ret;
+	struct usb_phy *phy;
+
+	phy = usb_get_phy(USB_PHY_TYPE_USB2);
+
+	if (IS_ERR(phy)) {
+		pr_err("%s: No USB transceiver found\n", __func__);
+		return PTR_ERR(phy);
+	}
+	otgwl_xceiv = phy;
+
+	snprintf(vbus_lock.name, sizeof(vbus_lock.name), "vbus-%s",
+		 dev_name(otgwl_xceiv->dev));
+	wake_lock_init(&vbus_lock.wakelock, WAKE_LOCK_SUSPEND,
+		       vbus_lock.name);
+
+	otgwl_nb.notifier_call = otgwl_otg_notifications;
+	ret = usb_register_notifier(otgwl_xceiv, &otgwl_nb);
+
+	if (ret) {
+		pr_err("%s: usb_register_notifier on transceiver %s"
+		       " failed\n", __func__,
+		       dev_name(otgwl_xceiv->dev));
+		otgwl_xceiv = NULL;
+		wake_lock_destroy(&vbus_lock.wakelock);
+		return ret;
+	}
+
+	otgwl_handle_event(otgwl_xceiv->last_event);
+	return ret;
+}
+
+late_initcall(otg_wakelock_init);
diff --git a/drivers/usb/phy/phy-am335x-control.c b/drivers/usb/phy/phy-am335x-control.c
index 35b6083b799..d5eca7b9c55 100644
--- a/drivers/usb/phy/phy-am335x-control.c
+++ b/drivers/usb/phy/phy-am335x-control.c
@@ -126,6 +126,9 @@ struct phy_control *am335x_get_phy_control(struct device *dev)
 		return NULL;
 
 	dev = bus_find_device(&platform_bus_type, NULL, node, match);
+	if (!dev)
+		return NULL;
+
 	ctrl_usb = dev_get_drvdata(dev);
 	if (!ctrl_usb)
 		return NULL;
diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c
index 045cd309367..7e8898d61dc 100644
--- a/drivers/usb/phy/phy.c
+++ b/drivers/usb/phy/phy.c
@@ -78,7 +78,9 @@ static void devm_usb_phy_release(struct device *dev, void *res)
 
 static int devm_usb_phy_match(struct device *dev, void *res, void *match_data)
 {
-	return res == match_data;
+	struct usb_phy **phy = res;
+
+	return *phy == match_data;
 }
 
 /**
diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c
index 2d17c10a042..294d43c387b 100644
--- a/drivers/usb/renesas_usbhs/mod_gadget.c
+++ b/drivers/usb/renesas_usbhs/mod_gadget.c
@@ -602,6 +602,9 @@ static int usbhsg_ep_disable(struct usb_ep *ep)
 	struct usbhsg_uep *uep = usbhsg_ep_to_uep(ep);
 	struct usbhs_pipe *pipe = usbhsg_uep_to_pipe(uep);
 
+	if (!pipe)
+		return -EINVAL;
+
 	usbhsg_pipe_disable(uep);
 	usbhs_pipe_free(pipe);
 
diff --git a/drivers/usb/serial/bus.c b/drivers/usb/serial/bus.c
index 9374bd2aba2..6f91eb9ae81 100644
--- a/drivers/usb/serial/bus.c
+++ b/drivers/usb/serial/bus.c
@@ -51,6 +51,7 @@ static int usb_serial_device_probe(struct device *dev)
 {
 	struct usb_serial_driver *driver;
 	struct usb_serial_port *port;
+	struct device *tty_dev;
 	int retval = 0;
 	int minor;
 
@@ -75,12 +76,20 @@ static int usb_serial_device_probe(struct device *dev)
 	retval = device_create_file(dev, &dev_attr_port_number);
 	if (retval) {
 		if (driver->port_remove)
-			retval = driver->port_remove(port);
+			driver->port_remove(port);
 		goto exit_with_autopm;
 	}
 
 	minor = port->minor;
-	tty_register_device(usb_serial_tty_driver, minor, dev);
+	tty_dev = tty_register_device(usb_serial_tty_driver, minor, dev);
+	if (IS_ERR(tty_dev)) {
+		retval = PTR_ERR(tty_dev);
+		device_remove_file(dev, &dev_attr_port_number);
+		if (driver->port_remove)
+			driver->port_remove(port);
+		goto exit_with_autopm;
+	}
+
 	dev_info(&port->serial->dev->dev,
 		 "%s converter now attached to ttyUSB%d\n",
 		 driver->description, minor);
diff --git a/drivers/usb/serial/console.c b/drivers/usb/serial/console.c
index 8d7fc48b1f3..29fa1c3d008 100644
--- a/drivers/usb/serial/console.c
+++ b/drivers/usb/serial/console.c
@@ -46,6 +46,8 @@ static struct console usbcons;
  * ------------------------------------------------------------
  */
 
+static const struct tty_operations usb_console_fake_tty_ops = {
+};
 
 /*
  * The parsing of the command line works exactly like the
@@ -137,13 +139,17 @@ static int usb_console_setup(struct console *co, char *options)
 				goto reset_open_count;
 			}
 			kref_init(&tty->kref);
-			tty_port_tty_set(&port->port, tty);
 			tty->driver = usb_serial_tty_driver;
 			tty->index = co->index;
+			init_ldsem(&tty->ldisc_sem);
+			INIT_LIST_HEAD(&tty->tty_files);
+			kref_get(&tty->driver->kref);
+			tty->ops = &usb_console_fake_tty_ops;
 			if (tty_init_termios(tty)) {
 				retval = -ENOMEM;
-				goto free_tty;
+				goto put_tty;
 			}
+			tty_port_tty_set(&port->port, tty);
 		}
 
 		/* only call the device specific open if this
@@ -161,7 +167,7 @@ static int usb_console_setup(struct console *co, char *options)
 			serial->type->set_termios(tty, port, &dummy);
 
 			tty_port_tty_set(&port->port, NULL);
-			kfree(tty);
+			tty_kref_put(tty);
 		}
 		set_bit(ASYNCB_INITIALIZED, &port->port.flags);
 	}
@@ -177,8 +183,8 @@ static int usb_console_setup(struct console *co, char *options)
 
  fail:
 	tty_port_tty_set(&port->port, NULL);
- free_tty:
-	kfree(tty);
+ put_tty:
+	tty_kref_put(tty);
  reset_open_count:
 	port->port.count = 0;
 	usb_autopm_put_interface(serial->interface);
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 6c4eb3cf5ef..eac7ccaa3c8 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -56,6 +56,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x0846, 0x1100) }, /* NetGear Managed Switch M4100 series, M5300 series, M7100 series */
 	{ USB_DEVICE(0x08e6, 0x5501) }, /* Gemalto Prox-PU/CU contactless smartcard reader */
 	{ USB_DEVICE(0x08FD, 0x000A) }, /* Digianswer A/S , ZigBee/802.15.4 MAC Device */
+	{ USB_DEVICE(0x0908, 0x01FF) }, /* Siemens RUGGEDCOM USB Serial Console */
 	{ USB_DEVICE(0x0BED, 0x1100) }, /* MEI (TM) Cashflow-SC Bill/Voucher Acceptor */
 	{ USB_DEVICE(0x0BED, 0x1101) }, /* MEI series 2000 Combo Acceptor */
 	{ USB_DEVICE(0x0FCF, 0x1003) }, /* Dynastream ANT development board */
@@ -120,10 +121,14 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */
 	{ USB_DEVICE(0x10C4, 0x8664) }, /* AC-Services CAN-IF */
 	{ USB_DEVICE(0x10C4, 0x8665) }, /* AC-Services OBD-IF */
-	{ USB_DEVICE(0x10C4, 0x8875) }, /* CEL MeshConnect USB Stick */
+	{ USB_DEVICE(0x10C4, 0x8856) },	/* CEL EM357 ZigBee USB Stick - LR */
+	{ USB_DEVICE(0x10C4, 0x8857) },	/* CEL EM357 ZigBee USB Stick */
 	{ USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */
 	{ USB_DEVICE(0x10C4, 0x88A5) }, /* Planet Innovation Ingeni ZigBee USB Device */
 	{ USB_DEVICE(0x10C4, 0x8946) }, /* Ketra N1 Wireless Interface */
+	{ USB_DEVICE(0x10C4, 0x8977) },	/* CEL MeshWorks DevKit Device */
+	{ USB_DEVICE(0x10C4, 0x8998) }, /* KCF Technologies PRN */
+	{ USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */
 	{ USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */
 	{ USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */
 	{ USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */
@@ -144,6 +149,8 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x166A, 0x0305) }, /* Clipsal C-5000CT2 C-Bus Spectrum Colour Touchscreen */
 	{ USB_DEVICE(0x166A, 0x0401) }, /* Clipsal L51xx C-Bus Architectural Dimmer */
 	{ USB_DEVICE(0x166A, 0x0101) }, /* Clipsal 5560884 C-Bus Multi-room Audio Matrix Switcher */
+	{ USB_DEVICE(0x16C0, 0x09B0) }, /* Lunatico Seletek */
+	{ USB_DEVICE(0x16C0, 0x09B1) }, /* Lunatico Seletek */
 	{ USB_DEVICE(0x16D6, 0x0001) }, /* Jablotron serial interface */
 	{ USB_DEVICE(0x16DC, 0x0010) }, /* W-IE-NE-R Plein & Baus GmbH PL512 Power Supply */
 	{ USB_DEVICE(0x16DC, 0x0011) }, /* W-IE-NE-R Plein & Baus GmbH RCM Remote Control for MARATON Power Supply */
@@ -180,6 +187,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x1FB9, 0x0602) }, /* Lake Shore Model 648 Magnet Power Supply */
 	{ USB_DEVICE(0x1FB9, 0x0700) }, /* Lake Shore Model 737 VSM Controller */
 	{ USB_DEVICE(0x1FB9, 0x0701) }, /* Lake Shore Model 776 Hall Matrix */
+	{ USB_DEVICE(0x2626, 0xEA60) }, /* Aruba Networks 7xxx USB Serial Console */
 	{ USB_DEVICE(0x3195, 0xF190) }, /* Link Instruments MSO-19 */
 	{ USB_DEVICE(0x3195, 0xF280) }, /* Link Instruments MSO-28 */
 	{ USB_DEVICE(0x3195, 0xF281) }, /* Link Instruments MSO-28 */
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 1ebb351b9e9..4c8b3b82103 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -604,6 +604,7 @@ static const struct usb_device_id id_table_combined[] = {
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	{ USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLXM_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+	{ USB_DEVICE(FTDI_VID, FTDI_SYNAPSE_SS200_PID) },
 	/*
 	 * ELV devices:
 	 */
@@ -698,6 +699,7 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(XSENS_VID, XSENS_AWINDA_DONGLE_PID) },
 	{ USB_DEVICE(XSENS_VID, XSENS_AWINDA_STATION_PID) },
 	{ USB_DEVICE(XSENS_VID, XSENS_CONVERTER_PID) },
+	{ USB_DEVICE(XSENS_VID, XSENS_MTDEVBOARD_PID) },
 	{ USB_DEVICE(XSENS_VID, XSENS_MTW_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_OMNI1509) },
 	{ USB_DEVICE(MOBILITY_VID, MOBILITY_USB_SERIAL_PID) },
@@ -799,6 +801,8 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_ELSTER_UNICOM_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_PROPOX_JTAGCABLEII_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_PROPOX_ISPCABLEIII_PID) },
+	{ USB_DEVICE(FTDI_VID, CYBER_CORTEX_AV_PID),
+		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	{ USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	{ USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_H_PID),
@@ -978,6 +982,23 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_PID, 1) },
 	/* GE Healthcare devices */
 	{ USB_DEVICE(GE_HEALTHCARE_VID, GE_HEALTHCARE_NEMO_TRACKER_PID) },
+	/* Active Research (Actisense) devices */
+	{ USB_DEVICE(FTDI_VID, ACTISENSE_NDC_PID) },
+	{ USB_DEVICE(FTDI_VID, ACTISENSE_USG_PID) },
+	{ USB_DEVICE(FTDI_VID, ACTISENSE_NGT_PID) },
+	{ USB_DEVICE(FTDI_VID, ACTISENSE_NGW_PID) },
+	{ USB_DEVICE(FTDI_VID, ACTISENSE_D9AC_PID) },
+	{ USB_DEVICE(FTDI_VID, ACTISENSE_D9AD_PID) },
+	{ USB_DEVICE(FTDI_VID, ACTISENSE_D9AE_PID) },
+	{ USB_DEVICE(FTDI_VID, ACTISENSE_D9AF_PID) },
+	{ USB_DEVICE(FTDI_VID, CHETCO_SEAGAUGE_PID) },
+	{ USB_DEVICE(FTDI_VID, CHETCO_SEASWITCH_PID) },
+	{ USB_DEVICE(FTDI_VID, CHETCO_SEASMART_NMEA2000_PID) },
+	{ USB_DEVICE(FTDI_VID, CHETCO_SEASMART_ETHERNET_PID) },
+	{ USB_DEVICE(FTDI_VID, CHETCO_SEASMART_WIFI_PID) },
+	{ USB_DEVICE(FTDI_VID, CHETCO_SEASMART_DISPLAY_PID) },
+	{ USB_DEVICE(FTDI_VID, CHETCO_SEASMART_LITE_PID) },
+	{ USB_DEVICE(FTDI_VID, CHETCO_SEASMART_ANALOG_PID) },
 	{ }					/* Terminating entry */
 };
 
@@ -1864,8 +1885,12 @@ static int ftdi_8u2232c_probe(struct usb_serial *serial)
 {
 	struct usb_device *udev = serial->dev;
 
-	if ((udev->manufacturer && !strcmp(udev->manufacturer, "CALAO Systems")) ||
-	    (udev->product && !strcmp(udev->product, "BeagleBone/XDS100V2")))
+	if (udev->manufacturer && !strcmp(udev->manufacturer, "CALAO Systems"))
+		return ftdi_jtag_probe(serial);
+
+	if (udev->product &&
+		(!strcmp(udev->product, "BeagleBone/XDS100V2") ||
+		 !strcmp(udev->product, "SNAP Connect E10")))
 		return ftdi_jtag_probe(serial);
 
 	return 0;
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index e52409c9be9..792e054126d 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -38,6 +38,9 @@
 
 #define FTDI_LUMEL_PD12_PID	0x6002
 
+/* Cyber Cortex AV by Fabulous Silicon (http://fabuloussilicon.com) */
+#define CYBER_CORTEX_AV_PID	0x8698
+
 /*
  * Marvell OpenRD Base, Client
  * http://www.open-rd.org
@@ -152,6 +155,7 @@
 #define XSENS_AWINDA_STATION_PID 0x0101
 #define XSENS_AWINDA_DONGLE_PID 0x0102
 #define XSENS_MTW_PID		0x0200	/* Xsens MTw */
+#define XSENS_MTDEVBOARD_PID	0x0300	/* Motion Tracker Development Board */
 #define XSENS_CONVERTER_PID	0xD00D	/* Xsens USB-serial converter */
 
 /* Xsens devices using FTDI VID */
@@ -558,6 +562,12 @@
  */
 #define FTDI_NT_ORIONLXM_PID	0x7c90	/* OrionLXm Substation Automation Platform */
 
+/*
+ * Synapse Wireless product ids (FTDI_VID)
+ * http://www.synapse-wireless.com
+ */
+#define FTDI_SYNAPSE_SS200_PID 0x9090 /* SS200 - SNAP Stick 200 */
+
 
 /********************************/
 /** third-party VID/PID combos **/
@@ -1438,3 +1448,23 @@
  */
 #define GE_HEALTHCARE_VID		0x1901
 #define GE_HEALTHCARE_NEMO_TRACKER_PID	0x0015
+
+/*
+ * Active Research (Actisense) devices
+ */
+#define ACTISENSE_NDC_PID		0xD9A8 /* NDC USB Serial Adapter */
+#define ACTISENSE_USG_PID		0xD9A9 /* USG USB Serial Adapter */
+#define ACTISENSE_NGT_PID		0xD9AA /* NGT NMEA2000 Interface */
+#define ACTISENSE_NGW_PID		0xD9AB /* NGW NMEA2000 Gateway */
+#define ACTISENSE_D9AC_PID		0xD9AC /* Actisense Reserved */
+#define ACTISENSE_D9AD_PID		0xD9AD /* Actisense Reserved */
+#define ACTISENSE_D9AE_PID		0xD9AE /* Actisense Reserved */
+#define ACTISENSE_D9AF_PID		0xD9AF /* Actisense Reserved */
+#define CHETCO_SEAGAUGE_PID		0xA548 /* SeaGauge USB Adapter */
+#define CHETCO_SEASWITCH_PID		0xA549 /* SeaSwitch USB Adapter */
+#define CHETCO_SEASMART_NMEA2000_PID	0xA54A /* SeaSmart NMEA2000 Gateway */
+#define CHETCO_SEASMART_ETHERNET_PID	0xA54B /* SeaSmart Ethernet Gateway */
+#define CHETCO_SEASMART_WIFI_PID	0xA5AC /* SeaSmart Wifi Gateway */
+#define CHETCO_SEASMART_DISPLAY_PID	0xA5AD /* SeaSmart NMEA2000 Display */
+#define CHETCO_SEASMART_LITE_PID	0xA5AE /* SeaSmart Lite USB Adapter */
+#define CHETCO_SEASMART_ANALOG_PID	0xA5AF /* SeaSmart Analog Adapter */
diff --git a/drivers/usb/serial/generic.c b/drivers/usb/serial/generic.c
index 1bd192290b0..c44b911937e 100644
--- a/drivers/usb/serial/generic.c
+++ b/drivers/usb/serial/generic.c
@@ -258,7 +258,8 @@ void usb_serial_generic_wait_until_sent(struct tty_struct *tty, long timeout)
 	 * character or at least one jiffy.
 	 */
 	period = max_t(unsigned long, (10 * HZ / bps), 1);
-	period = min_t(unsigned long, period, timeout);
+	if (timeout)
+		period = min_t(unsigned long, period, timeout);
 
 	dev_dbg(&port->dev, "%s - timeout = %u ms, period = %u ms\n",
 					__func__, jiffies_to_msecs(timeout),
@@ -268,7 +269,7 @@ void usb_serial_generic_wait_until_sent(struct tty_struct *tty, long timeout)
 		schedule_timeout_interruptible(period);
 		if (signal_pending(current))
 			break;
-		if (time_after(jiffies, expire))
+		if (timeout && time_after(jiffies, expire))
 			break;
 	}
 }
@@ -373,7 +374,7 @@ void usb_serial_generic_read_bulk_callback(struct urb *urb)
 							__func__, urb->status);
 		return;
 	default:
-		dev_err(&port->dev, "%s - nonzero urb status: %d\n",
+		dev_dbg(&port->dev, "%s - nonzero urb status: %d\n",
 							__func__, urb->status);
 		goto resubmit;
 	}
diff --git a/drivers/usb/serial/keyspan.c b/drivers/usb/serial/keyspan.c
index 077c714f128..e07b15ed581 100644
--- a/drivers/usb/serial/keyspan.c
+++ b/drivers/usb/serial/keyspan.c
@@ -410,6 +410,8 @@ static void	usa26_instat_callback(struct urb *urb)
 	}
 	port = serial->port[msg->port];
 	p_priv = usb_get_serial_port_data(port);
+	if (!p_priv)
+		goto resubmit;
 
 	/* Update handshaking pin state information */
 	old_dcd_state = p_priv->dcd_state;
@@ -420,7 +422,7 @@ static void	usa26_instat_callback(struct urb *urb)
 
 	if (old_dcd_state != p_priv->dcd_state)
 		tty_port_tty_hangup(&port->port, true);
-
+resubmit:
 	/* Resubmit urb so we continue receiving */
 	err = usb_submit_urb(urb, GFP_ATOMIC);
 	if (err != 0)
@@ -527,6 +529,8 @@ static void	usa28_instat_callback(struct urb *urb)
 	}
 	port = serial->port[msg->port];
 	p_priv = usb_get_serial_port_data(port);
+	if (!p_priv)
+		goto resubmit;
 
 	/* Update handshaking pin state information */
 	old_dcd_state = p_priv->dcd_state;
@@ -537,7 +541,7 @@ static void	usa28_instat_callback(struct urb *urb)
 
 	if (old_dcd_state != p_priv->dcd_state && old_dcd_state)
 		tty_port_tty_hangup(&port->port, true);
-
+resubmit:
 		/* Resubmit urb so we continue receiving */
 	err = usb_submit_urb(urb, GFP_ATOMIC);
 	if (err != 0)
@@ -607,6 +611,8 @@ static void	usa49_instat_callback(struct urb *urb)
 	}
 	port = serial->port[msg->portNumber];
 	p_priv = usb_get_serial_port_data(port);
+	if (!p_priv)
+		goto resubmit;
 
 	/* Update handshaking pin state information */
 	old_dcd_state = p_priv->dcd_state;
@@ -617,7 +623,7 @@ static void	usa49_instat_callback(struct urb *urb)
 
 	if (old_dcd_state != p_priv->dcd_state && old_dcd_state)
 		tty_port_tty_hangup(&port->port, true);
-
+resubmit:
 	/* Resubmit urb so we continue receiving */
 	err = usb_submit_urb(urb, GFP_ATOMIC);
 	if (err != 0)
@@ -855,6 +861,8 @@ static void	usa90_instat_callback(struct urb *urb)
 
 	port = serial->port[0];
 	p_priv = usb_get_serial_port_data(port);
+	if (!p_priv)
+		goto resubmit;
 
 	/* Update handshaking pin state information */
 	old_dcd_state = p_priv->dcd_state;
@@ -865,7 +873,7 @@ static void	usa90_instat_callback(struct urb *urb)
 
 	if (old_dcd_state != p_priv->dcd_state && old_dcd_state)
 		tty_port_tty_hangup(&port->port, true);
-
+resubmit:
 	/* Resubmit urb so we continue receiving */
 	err = usb_submit_urb(urb, GFP_ATOMIC);
 	if (err != 0)
@@ -926,6 +934,8 @@ static void	usa67_instat_callback(struct urb *urb)
 
 	port = serial->port[msg->port];
 	p_priv = usb_get_serial_port_data(port);
+	if (!p_priv)
+		goto resubmit;
 
 	/* Update handshaking pin state information */
 	old_dcd_state = p_priv->dcd_state;
@@ -934,7 +944,7 @@ static void	usa67_instat_callback(struct urb *urb)
 
 	if (old_dcd_state != p_priv->dcd_state && old_dcd_state)
 		tty_port_tty_hangup(&port->port, true);
-
+resubmit:
 	/* Resubmit urb so we continue receiving */
 	err = usb_submit_urb(urb, GFP_ATOMIC);
 	if (err != 0)
diff --git a/drivers/usb/serial/keyspan_pda.c b/drivers/usb/serial/keyspan_pda.c
index 742d827f876..04a217af29b 100644
--- a/drivers/usb/serial/keyspan_pda.c
+++ b/drivers/usb/serial/keyspan_pda.c
@@ -61,6 +61,7 @@ struct keyspan_pda_private {
 /* For Xircom PGSDB9 and older Entregra version of the same device */
 #define XIRCOM_VENDOR_ID		0x085a
 #define XIRCOM_FAKE_ID			0x8027
+#define XIRCOM_FAKE_ID_2                0x8025 /* "PGMFHUB" serial */
 #define ENTREGRA_VENDOR_ID		0x1645
 #define ENTREGRA_FAKE_ID		0x8093
 
@@ -70,6 +71,7 @@ static const struct usb_device_id id_table_combined[] = {
 #endif
 #ifdef XIRCOM
 	{ USB_DEVICE(XIRCOM_VENDOR_ID, XIRCOM_FAKE_ID) },
+	{ USB_DEVICE(XIRCOM_VENDOR_ID, XIRCOM_FAKE_ID_2) },
 	{ USB_DEVICE(ENTREGRA_VENDOR_ID, ENTREGRA_FAKE_ID) },
 #endif
 	{ USB_DEVICE(KEYSPAN_VENDOR_ID, KEYSPAN_PDA_ID) },
@@ -93,6 +95,7 @@ static const struct usb_device_id id_table_fake[] = {
 #ifdef XIRCOM
 static const struct usb_device_id id_table_fake_xircom[] = {
 	{ USB_DEVICE(XIRCOM_VENDOR_ID, XIRCOM_FAKE_ID) },
+	{ USB_DEVICE(XIRCOM_VENDOR_ID, XIRCOM_FAKE_ID_2) },
 	{ USB_DEVICE(ENTREGRA_VENDOR_ID, ENTREGRA_FAKE_ID) },
 	{ }
 };
diff --git a/drivers/usb/serial/mxuport.c b/drivers/usb/serial/mxuport.c
index ab1d690274a..460a4066996 100644
--- a/drivers/usb/serial/mxuport.c
+++ b/drivers/usb/serial/mxuport.c
@@ -1284,7 +1284,8 @@ static int mxuport_open(struct tty_struct *tty, struct usb_serial_port *port)
 	}
 
 	/* Initial port termios */
-	mxuport_set_termios(tty, port, NULL);
+	if (tty)
+		mxuport_set_termios(tty, port, NULL);
 
 	/*
 	 * TODO: use RQ_VENDOR_GET_MSR, once we know what it
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 7a4c21b4f67..c8c4e50ffee 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -234,6 +234,8 @@ static void option_instat_callback(struct urb *urb);
 
 #define QUALCOMM_VENDOR_ID			0x05C6
 
+#define SIERRA_VENDOR_ID			0x1199
+
 #define CMOTECH_VENDOR_ID			0x16d8
 #define CMOTECH_PRODUCT_6001			0x6001
 #define CMOTECH_PRODUCT_CMU_300			0x6002
@@ -512,7 +514,7 @@ enum option_blacklist_reason {
 		OPTION_BLACKLIST_RESERVED_IF = 2
 };
 
-#define MAX_BL_NUM  8
+#define MAX_BL_NUM  11
 struct option_blacklist_info {
 	/* bitfield of interface numbers for OPTION_BLACKLIST_SENDSETUP */
 	const unsigned long sendsetup;
@@ -601,6 +603,11 @@ static const struct option_blacklist_info telit_le920_blacklist = {
 	.reserved = BIT(1) | BIT(5),
 };
 
+static const struct option_blacklist_info sierra_mc73xx_blacklist = {
+	.sendsetup = BIT(0) | BIT(2),
+	.reserved = BIT(8) | BIT(10) | BIT(11),
+};
+
 static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) },
 	{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) },
@@ -1098,6 +1105,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */
+	{ USB_DEVICE_INTERFACE_CLASS(SIERRA_VENDOR_ID, 0x68c0, 0xff),
+	  .driver_info = (kernel_ulong_t)&sierra_mc73xx_blacklist }, /* MC73xx */
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003),
@@ -1764,6 +1773,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x00, 0x00) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */
+	{ USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) },                /* OLICARD300 - MT6225 */
 	{ USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) },
 	{ USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) },
 	{ } /* Terminating entry */
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index 0f872e6b2c8..534c308c6b3 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -61,7 +61,6 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(DCU10_VENDOR_ID, DCU10_PRODUCT_ID) },
 	{ USB_DEVICE(SITECOM_VENDOR_ID, SITECOM_PRODUCT_ID) },
 	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_ID) },
-	{ USB_DEVICE(SAMSUNG_VENDOR_ID, SAMSUNG_PRODUCT_ID) },
 	{ USB_DEVICE(SIEMENS_VENDOR_ID, SIEMENS_PRODUCT_ID_SX1),
 		.driver_info = PL2303_QUIRK_UART_STATE_IDX0 },
 	{ USB_DEVICE(SIEMENS_VENDOR_ID, SIEMENS_PRODUCT_ID_X65),
diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h
index 71fd9da1d6e..e3b7af8adfb 100644
--- a/drivers/usb/serial/pl2303.h
+++ b/drivers/usb/serial/pl2303.h
@@ -62,10 +62,6 @@
 #define ALCATEL_VENDOR_ID	0x11f7
 #define ALCATEL_PRODUCT_ID	0x02df
 
-/* Samsung I330 phone cradle */
-#define SAMSUNG_VENDOR_ID	0x04e8
-#define SAMSUNG_PRODUCT_ID	0x8001
-
 #define SIEMENS_VENDOR_ID	0x11f5
 #define SIEMENS_PRODUCT_ID_SX1	0x0001
 #define SIEMENS_PRODUCT_ID_X65	0x0003
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index b2aa003bf41..9c63897b3a5 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -27,12 +27,15 @@ enum qcserial_layouts {
 	QCSERIAL_G2K = 0,	/* Gobi 2000 */
 	QCSERIAL_G1K = 1,	/* Gobi 1000 */
 	QCSERIAL_SWI = 2,	/* Sierra Wireless */
+	QCSERIAL_HWI = 3,	/* Huawei */
 };
 
 #define DEVICE_G1K(v, p) \
 	USB_DEVICE(v, p), .driver_info = QCSERIAL_G1K
 #define DEVICE_SWI(v, p) \
 	USB_DEVICE(v, p), .driver_info = QCSERIAL_SWI
+#define DEVICE_HWI(v, p) \
+	USB_DEVICE(v, p), .driver_info = QCSERIAL_HWI
 
 static const struct usb_device_id id_table[] = {
 	/* Gobi 1000 devices */
@@ -139,7 +142,6 @@ static const struct usb_device_id id_table[] = {
 	{DEVICE_SWI(0x0f3d, 0x68a2)},	/* Sierra Wireless MC7700 */
 	{DEVICE_SWI(0x114f, 0x68a2)},	/* Sierra Wireless MC7750 */
 	{DEVICE_SWI(0x1199, 0x68a2)},	/* Sierra Wireless MC7710 */
-	{DEVICE_SWI(0x1199, 0x68c0)},	/* Sierra Wireless MC73xx */
 	{DEVICE_SWI(0x1199, 0x901c)},	/* Sierra Wireless EM7700 */
 	{DEVICE_SWI(0x1199, 0x901f)},	/* Sierra Wireless EM7355 */
 	{DEVICE_SWI(0x1199, 0x9040)},	/* Sierra Wireless Modem */
@@ -157,6 +159,9 @@ static const struct usb_device_id id_table[] = {
 	{DEVICE_SWI(0x413c, 0x81a8)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81a9)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
 
+	/* Huawei devices */
+	{DEVICE_HWI(0x03f0, 0x581d)},	/* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */
+
 	{ }				/* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, id_table);
@@ -287,6 +292,33 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id)
 			break;
 		}
 		break;
+	case QCSERIAL_HWI:
+		/*
+		 * Huawei layout:
+		 * 0: AT-capable modem port
+		 * 1: DM/DIAG
+		 * 2: AT-capable modem port
+		 * 3: CCID-compatible PCSC interface
+		 * 4: QMI/net
+		 * 5: NMEA
+		 */
+		switch (ifnum) {
+		case 0:
+		case 2:
+			dev_dbg(dev, "Modem port found\n");
+			break;
+		case 1:
+			dev_dbg(dev, "DM/DIAG interface found\n");
+			break;
+		case 5:
+			dev_dbg(dev, "NMEA GPS interface found\n");
+			break;
+		default:
+			/* don't claim any unsupported interface */
+			altsetting = -1;
+			break;
+		}
+		break;
 	default:
 		dev_err(dev, "unsupported device layout type: %lu\n",
 			id->driver_info);
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 475723c006f..6fbfc8fc2f5 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -940,8 +940,9 @@ static int usb_serial_probe(struct usb_interface *interface,
 		port = serial->port[i];
 		if (kfifo_alloc(&port->write_fifo, PAGE_SIZE, GFP_KERNEL))
 			goto probe_error;
-		buffer_size = max_t(int, serial->type->bulk_out_size,
-						usb_endpoint_maxp(endpoint));
+		buffer_size = serial->type->bulk_out_size;
+		if (!buffer_size)
+			buffer_size = usb_endpoint_maxp(endpoint);
 		port->bulk_out_size = buffer_size;
 		port->bulk_out_endpointAddress = endpoint->bEndpointAddress;
 
@@ -1289,6 +1290,7 @@ static void __exit usb_serial_exit(void)
 	tty_unregister_driver(usb_serial_tty_driver);
 	put_tty_driver(usb_serial_tty_driver);
 	bus_unregister(&usb_serial_bus_type);
+	idr_destroy(&serial_minors);
 }
 
 
diff --git a/drivers/usb/serial/visor.c b/drivers/usb/serial/visor.c
index bf2bd40e5f2..60afb39eb73 100644
--- a/drivers/usb/serial/visor.c
+++ b/drivers/usb/serial/visor.c
@@ -95,7 +95,7 @@ static const struct usb_device_id id_table[] = {
 		.driver_info = (kernel_ulong_t)&palm_os_4_probe },
 	{ USB_DEVICE(ACER_VENDOR_ID, ACER_S10_ID),
 		.driver_info = (kernel_ulong_t)&palm_os_4_probe },
-	{ USB_DEVICE(SAMSUNG_VENDOR_ID, SAMSUNG_SCH_I330_ID),
+	{ USB_DEVICE_INTERFACE_CLASS(SAMSUNG_VENDOR_ID, SAMSUNG_SCH_I330_ID, 0xff),
 		.driver_info = (kernel_ulong_t)&palm_os_4_probe },
 	{ USB_DEVICE(SAMSUNG_VENDOR_ID, SAMSUNG_SPH_I500_ID),
 		.driver_info = (kernel_ulong_t)&palm_os_4_probe },
diff --git a/drivers/usb/storage/uas-detect.h b/drivers/usb/storage/uas-detect.h
index 8a6f371ed6e..a451903a685 100644
--- a/drivers/usb/storage/uas-detect.h
+++ b/drivers/usb/storage/uas-detect.h
@@ -51,7 +51,8 @@ static int uas_find_endpoints(struct usb_host_interface *alt,
 }
 
 static int uas_use_uas_driver(struct usb_interface *intf,
-			      const struct usb_device_id *id)
+			      const struct usb_device_id *id,
+			      unsigned long *flags_ret)
 {
 	struct usb_host_endpoint *eps[4] = { };
 	struct usb_device *udev = interface_to_usbdev(intf);
@@ -80,6 +81,9 @@ static int uas_use_uas_driver(struct usb_interface *intf,
 			flags |= US_FL_IGNORE_UAS;
 		} else if (usb_ss_max_streams(&eps[1]->ss_ep_comp) == 32) {
 			flags |= US_FL_IGNORE_UAS;
+		} else {
+			/* ASM1053, these have issues with large transfers */
+			flags |= US_FL_MAX_SECTORS_240;
 		}
 	}
 
@@ -109,5 +113,8 @@ static int uas_use_uas_driver(struct usb_interface *intf,
 		return 0;
 	}
 
+	if (flags_ret)
+		*flags_ret = flags;
+
 	return 1;
 }
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 89b24349269..2ef0f0abe24 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -770,7 +770,10 @@ static int uas_eh_bus_reset_handler(struct scsi_cmnd *cmnd)
 
 static int uas_slave_alloc(struct scsi_device *sdev)
 {
-	sdev->hostdata = (void *)sdev->host->hostdata;
+	struct uas_dev_info *devinfo =
+		(struct uas_dev_info *)sdev->host->hostdata;
+
+	sdev->hostdata = devinfo;
 
 	/* USB has unusual DMA-alignment requirements: Although the
 	 * starting address of each scatter-gather element doesn't matter,
@@ -789,6 +792,11 @@ static int uas_slave_alloc(struct scsi_device *sdev)
 	 */
 	blk_queue_update_dma_alignment(sdev->request_queue, (512 - 1));
 
+	if (devinfo->flags & US_FL_MAX_SECTORS_64)
+		blk_queue_max_hw_sectors(sdev->request_queue, 64);
+	else if (devinfo->flags & US_FL_MAX_SECTORS_240)
+		blk_queue_max_hw_sectors(sdev->request_queue, 240);
+
 	return 0;
 }
 
@@ -906,8 +914,9 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	struct Scsi_Host *shost = NULL;
 	struct uas_dev_info *devinfo;
 	struct usb_device *udev = interface_to_usbdev(intf);
+	unsigned long dev_flags;
 
-	if (!uas_use_uas_driver(intf, id))
+	if (!uas_use_uas_driver(intf, id, &dev_flags))
 		return -ENODEV;
 
 	if (uas_switch_interface(udev, intf))
@@ -929,8 +938,7 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	devinfo->udev = udev;
 	devinfo->resetting = 0;
 	devinfo->shutdown = 0;
-	devinfo->flags = id->driver_info;
-	usb_stor_adjust_quirks(udev, &devinfo->flags);
+	devinfo->flags = dev_flags;
 	init_usb_anchor(&devinfo->cmd_urbs);
 	init_usb_anchor(&devinfo->sense_urbs);
 	init_usb_anchor(&devinfo->data_urbs);
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 11c7a967644..300ef9b817e 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -766,6 +766,13 @@ UNUSUAL_DEV(  0x059f, 0x0643, 0x0000, 0x0000,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_GO_SLOW ),
 
+/* Reported by Christian Schaller <cschalle@redhat.com> */
+UNUSUAL_DEV(  0x059f, 0x0651, 0x0000, 0x0000,
+		"LaCie",
+		"External HDD",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_WP_DETECT ),
+
 /* Submitted by Joel Bourquard <numlock@freesurf.ch>
  * Some versions of this device need the SubClass and Protocol overrides
  * while others don't.
@@ -1995,6 +2002,13 @@ UNUSUAL_DEV(  0x152d, 0x2329, 0x0100, 0x0100,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_IGNORE_RESIDUE | US_FL_SANE_SENSE ),
 
+/* Reported by Dmitry Nezhevenko <dion@dion.org.ua> */
+UNUSUAL_DEV(  0x152d, 0x2566, 0x0114, 0x0114,
+		"JMicron",
+		"USB to ATA/ATAPI Bridge",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_BROKEN_FUA ),
+
 /* Entrega Technologies U1-SC25 (later Xircom PortGear PGSCSI)
  * and Mac USB Dock USB-SCSI */
 UNUSUAL_DEV(  0x1645, 0x0007, 0x0100, 0x0133,
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 18a283d6de1..cd4ba61330c 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -68,6 +68,20 @@ UNUSUAL_DEV(0x0bc2, 0xa003, 0x0000, 0x9999,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_ATA_1X),
 
+/* Reported-by: Marcin Zajączkowski <mszpak@wp.pl> */
+UNUSUAL_DEV(0x0bc2, 0xa013, 0x0000, 0x9999,
+		"Seagate",
+		"Backup Plus",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_ATA_1X),
+
+/* Reported-by: Hans de Goede <hdegoede@redhat.com> */
+UNUSUAL_DEV(0x0bc2, 0xa0a4, 0x0000, 0x9999,
+		"Seagate",
+		"Backup Plus Desk",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_ATA_1X),
+
 /* https://bbs.archlinux.org/viewtopic.php?id=183190 */
 UNUSUAL_DEV(0x0bc2, 0xab20, 0x0000, 0x9999,
 		"Seagate",
@@ -82,6 +96,27 @@ UNUSUAL_DEV(0x0bc2, 0xab21, 0x0000, 0x9999,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_ATA_1X),
 
+/* Reported-by: G. Richard Bellamy <rbellamy@pteradigm.com> */
+UNUSUAL_DEV(0x0bc2, 0xab2a, 0x0000, 0x9999,
+		"Seagate",
+		"BUP Fast HDD",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_ATA_1X),
+
+/* Reported-by: Benjamin Tissoires <benjamin.tissoires@redhat.com> */
+UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999,
+		"Initio Corporation",
+		"",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_ATA_1X),
+
+/* Reported-by: Tom Arild Naess <tanaess@gmail.com> */
+UNUSUAL_DEV(0x152d, 0x0539, 0x0000, 0x9999,
+		"JMicron",
+		"JMS539",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_REPORT_OPCODES),
+
 /* Reported-by: Claudio Bizzarri <claudio.bizzarri@gmail.com> */
 UNUSUAL_DEV(0x152d, 0x0567, 0x0000, 0x9999,
 		"JMicron",
@@ -104,9 +139,23 @@ UNUSUAL_DEV(0x2109, 0x0711, 0x0000, 0x9999,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_ATA_1X),
 
+/* Reported-by: Takeo Nakayama <javhera@gmx.com> */
+UNUSUAL_DEV(0x357d, 0x7788, 0x0000, 0x9999,
+		"JMicron",
+		"JMS566",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_REPORT_OPCODES),
+
 /* Reported-by: Hans de Goede <hdegoede@redhat.com> */
 UNUSUAL_DEV(0x4971, 0x1012, 0x0000, 0x9999,
 		"Hitachi",
 		"External HDD",
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_IGNORE_UAS),
+
+/* Reported-by: Richard Henderson <rth@redhat.com> */
+UNUSUAL_DEV(0x4971, 0x8017, 0x0000, 0x9999,
+		"SimpleTech",
+		"External HDD",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_REPORT_OPCODES),
diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c
index 9d66ce62542..cda42cf779a 100644
--- a/drivers/usb/storage/usb.c
+++ b/drivers/usb/storage/usb.c
@@ -479,7 +479,8 @@ void usb_stor_adjust_quirks(struct usb_device *udev, unsigned long *fflags)
 			US_FL_SINGLE_LUN | US_FL_NO_WP_DETECT |
 			US_FL_NO_READ_DISC_INFO | US_FL_NO_READ_CAPACITY_16 |
 			US_FL_INITIAL_READ10 | US_FL_WRITE_CACHE |
-			US_FL_NO_ATA_1X | US_FL_NO_REPORT_OPCODES);
+			US_FL_NO_ATA_1X | US_FL_NO_REPORT_OPCODES |
+			US_FL_MAX_SECTORS_240);
 
 	p = quirks;
 	while (*p) {
@@ -520,6 +521,9 @@ void usb_stor_adjust_quirks(struct usb_device *udev, unsigned long *fflags)
 		case 'f':
 			f |= US_FL_NO_REPORT_OPCODES;
 			break;
+		case 'g':
+			f |= US_FL_MAX_SECTORS_240;
+			break;
 		case 'h':
 			f |= US_FL_CAPACITY_HEURISTICS;
 			break;
@@ -1062,7 +1066,7 @@ static int storage_probe(struct usb_interface *intf,
 
 	/* If uas is enabled and this device can do uas then ignore it. */
 #if IS_ENABLED(CONFIG_USB_UAS)
-	if (uas_use_uas_driver(intf, id))
+	if (uas_use_uas_driver(intf, id, NULL))
 		return -ENXIO;
 #endif
 
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 9558da3f06a..2f8a0552d02 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -839,13 +839,11 @@ static const struct vfio_device_ops vfio_pci_ops = {
 
 static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
-	u8 type;
 	struct vfio_pci_device *vdev;
 	struct iommu_group *group;
 	int ret;
 
-	pci_read_config_byte(pdev, PCI_HEADER_TYPE, &type);
-	if ((type & PCI_HEADER_TYPE) != PCI_HEADER_TYPE_NORMAL)
+	if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
 		return -EINVAL;
 
 	group = iommu_group_get(&pdev->dev);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index a17f1185066..cb84f69f76a 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -909,6 +909,23 @@ vhost_scsi_map_iov_to_prot(struct tcm_vhost_cmd *cmd,
 	return 0;
 }
 
+static int vhost_scsi_to_tcm_attr(int attr)
+{
+	switch (attr) {
+	case VIRTIO_SCSI_S_SIMPLE:
+		return MSG_SIMPLE_TAG;
+	case VIRTIO_SCSI_S_ORDERED:
+		return MSG_ORDERED_TAG;
+	case VIRTIO_SCSI_S_HEAD:
+		return MSG_HEAD_TAG;
+	case VIRTIO_SCSI_S_ACA:
+		return MSG_ACA_TAG;
+	default:
+		break;
+	}
+	return MSG_SIMPLE_TAG;
+}
+
 static void tcm_vhost_submission_work(struct work_struct *work)
 {
 	struct tcm_vhost_cmd *cmd =
@@ -934,9 +951,10 @@ static void tcm_vhost_submission_work(struct work_struct *work)
 	rc = target_submit_cmd_map_sgls(se_cmd, tv_nexus->tvn_se_sess,
 			cmd->tvc_cdb, &cmd->tvc_sense_buf[0],
 			cmd->tvc_lun, cmd->tvc_exp_data_len,
-			cmd->tvc_task_attr, cmd->tvc_data_direction,
-			TARGET_SCF_ACK_KREF, sg_ptr, cmd->tvc_sgl_count,
-			NULL, 0, sg_prot_ptr, cmd->tvc_prot_sgl_count);
+			vhost_scsi_to_tcm_attr(cmd->tvc_task_attr),
+			cmd->tvc_data_direction, TARGET_SCF_ACK_KREF,
+			sg_ptr, cmd->tvc_sgl_count, NULL, 0,
+			sg_prot_ptr, cmd->tvc_prot_sgl_count);
 	if (rc < 0) {
 		transport_send_check_condition_and_sense(se_cmd,
 				TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE, 0);
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index 8bf495ffb02..49fcbb1632a 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -31,6 +31,7 @@ source "drivers/video/fbdev/Kconfig"
 endmenu
 
 source "drivers/video/backlight/Kconfig"
+source "drivers/video/adf/Kconfig"
 
 config VGASTATE
        tristate
diff --git a/drivers/video/Makefile b/drivers/video/Makefile
index 9ad3c17d645..1a8c4ced39b 100644
--- a/drivers/video/Makefile
+++ b/drivers/video/Makefile
@@ -1,6 +1,7 @@
 obj-$(CONFIG_VGASTATE)            += vgastate.o
 obj-$(CONFIG_HDMI)                += hdmi.o
 
+obj-$(CONFIG_ADF)		  += adf/
 obj-$(CONFIG_VT)		  += console/
 obj-$(CONFIG_LOGO)		  += logo/
 obj-y				  += backlight/
diff --git a/drivers/video/adf/Kconfig b/drivers/video/adf/Kconfig
new file mode 100644
index 00000000000..33858b73d8b
--- /dev/null
+++ b/drivers/video/adf/Kconfig
@@ -0,0 +1,14 @@
+menuconfig ADF
+	depends on SYNC
+	depends on DMA_SHARED_BUFFER
+	tristate "Atomic Display Framework"
+
+menuconfig ADF_FBDEV
+	depends on ADF
+	depends on FB
+	tristate "Helper for implementing the fbdev API in ADF drivers"
+
+menuconfig ADF_MEMBLOCK
+	depends on ADF
+	depends on HAVE_MEMBLOCK
+	tristate "Helper for using memblocks as buffers in ADF drivers"
diff --git a/drivers/video/adf/Makefile b/drivers/video/adf/Makefile
new file mode 100644
index 00000000000..78d0915122f
--- /dev/null
+++ b/drivers/video/adf/Makefile
@@ -0,0 +1,15 @@
+ccflags-y := -Idrivers/staging/android
+
+CFLAGS_adf.o := -I$(src)
+
+obj-$(CONFIG_ADF) += adf.o \
+	adf_client.o \
+	adf_fops.o \
+	adf_format.o \
+	adf_sysfs.o
+
+obj-$(CONFIG_COMPAT) += adf_fops32.o
+
+obj-$(CONFIG_ADF_FBDEV) += adf_fbdev.o
+
+obj-$(CONFIG_ADF_MEMBLOCK) += adf_memblock.o
diff --git a/drivers/video/adf/adf.c b/drivers/video/adf/adf.c
new file mode 100644
index 00000000000..42c30c05826
--- /dev/null
+++ b/drivers/video/adf/adf.c
@@ -0,0 +1,1188 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ * adf_modeinfo_{set_name,set_vrefresh} modified from
+ * drivers/gpu/drm/drm_modes.c
+ * adf_format_validate_yuv modified from framebuffer_check in
+ * drivers/gpu/drm/drm_crtc.c
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/device.h>
+#include <linux/idr.h>
+#include <linux/highmem.h>
+#include <linux/memblock.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include <video/adf_format.h>
+
+#include "sw_sync.h"
+#include "sync.h"
+
+#include "adf.h"
+#include "adf_fops.h"
+#include "adf_sysfs.h"
+
+#define CREATE_TRACE_POINTS
+#include "adf_trace.h"
+
+#define ADF_SHORT_FENCE_TIMEOUT (1 * MSEC_PER_SEC)
+#define ADF_LONG_FENCE_TIMEOUT (10 * MSEC_PER_SEC)
+
+static DEFINE_IDR(adf_devices);
+
+static void adf_fence_wait(struct adf_device *dev, struct sync_fence *fence)
+{
+	/* sync_fence_wait() dumps debug information on timeout.  Experience
+	   has shown that if the pipeline gets stuck, a short timeout followed
+	   by a longer one provides useful information for debugging. */
+	int err = sync_fence_wait(fence, ADF_SHORT_FENCE_TIMEOUT);
+	if (err >= 0)
+		return;
+
+	if (err == -ETIME)
+		err = sync_fence_wait(fence, ADF_LONG_FENCE_TIMEOUT);
+
+	if (err < 0)
+		dev_warn(&dev->base.dev, "error waiting on fence: %d\n", err);
+}
+
+void adf_buffer_cleanup(struct adf_buffer *buf)
+{
+	size_t i;
+	for (i = 0; i < ARRAY_SIZE(buf->dma_bufs); i++)
+		if (buf->dma_bufs[i])
+			dma_buf_put(buf->dma_bufs[i]);
+
+	if (buf->acquire_fence)
+		sync_fence_put(buf->acquire_fence);
+}
+
+void adf_buffer_mapping_cleanup(struct adf_buffer_mapping *mapping,
+		struct adf_buffer *buf)
+{
+	/* calling adf_buffer_mapping_cleanup() is safe even if mapping is
+	   uninitialized or partially-initialized, as long as it was
+	   zeroed on allocation */
+	size_t i;
+	for (i = 0; i < ARRAY_SIZE(mapping->sg_tables); i++) {
+		if (mapping->sg_tables[i])
+			dma_buf_unmap_attachment(mapping->attachments[i],
+					mapping->sg_tables[i], DMA_TO_DEVICE);
+		if (mapping->attachments[i])
+			dma_buf_detach(buf->dma_bufs[i],
+					mapping->attachments[i]);
+	}
+}
+
+void adf_post_cleanup(struct adf_device *dev, struct adf_pending_post *post)
+{
+	size_t i;
+
+	if (post->state)
+		dev->ops->state_free(dev, post->state);
+
+	for (i = 0; i < post->config.n_bufs; i++) {
+		adf_buffer_mapping_cleanup(&post->config.mappings[i],
+				&post->config.bufs[i]);
+		adf_buffer_cleanup(&post->config.bufs[i]);
+	}
+
+	kfree(post->config.custom_data);
+	kfree(post->config.mappings);
+	kfree(post->config.bufs);
+	kfree(post);
+}
+
+static void adf_sw_advance_timeline(struct adf_device *dev)
+{
+#ifdef CONFIG_SW_SYNC
+	sw_sync_timeline_inc(dev->timeline, 1);
+#else
+	BUG();
+#endif
+}
+
+static void adf_post_work_func(struct kthread_work *work)
+{
+	struct adf_device *dev =
+			container_of(work, struct adf_device, post_work);
+	struct adf_pending_post *post, *next;
+	struct list_head saved_list;
+
+	mutex_lock(&dev->post_lock);
+	memcpy(&saved_list, &dev->post_list, sizeof(saved_list));
+	list_replace_init(&dev->post_list, &saved_list);
+	mutex_unlock(&dev->post_lock);
+
+	list_for_each_entry_safe(post, next, &saved_list, head) {
+		int i;
+
+		for (i = 0; i < post->config.n_bufs; i++) {
+			struct sync_fence *fence =
+					post->config.bufs[i].acquire_fence;
+			if (fence)
+				adf_fence_wait(dev, fence);
+		}
+
+		dev->ops->post(dev, &post->config, post->state);
+
+		if (dev->ops->advance_timeline)
+			dev->ops->advance_timeline(dev, &post->config,
+					post->state);
+		else
+			adf_sw_advance_timeline(dev);
+
+		list_del(&post->head);
+		if (dev->onscreen)
+			adf_post_cleanup(dev, dev->onscreen);
+		dev->onscreen = post;
+	}
+}
+
+void adf_attachment_free(struct adf_attachment_list *attachment)
+{
+	list_del(&attachment->head);
+	kfree(attachment);
+}
+
+struct adf_event_refcount *adf_obj_find_event_refcount(struct adf_obj *obj,
+		enum adf_event_type type)
+{
+	struct rb_root *root = &obj->event_refcount;
+	struct rb_node **new = &(root->rb_node);
+	struct rb_node *parent = NULL;
+	struct adf_event_refcount *refcount;
+
+	while (*new) {
+		refcount = container_of(*new, struct adf_event_refcount, node);
+		parent = *new;
+
+		if (refcount->type > type)
+			new = &(*new)->rb_left;
+		else if (refcount->type < type)
+			new = &(*new)->rb_right;
+		else
+			return refcount;
+	}
+
+	refcount = kzalloc(sizeof(*refcount), GFP_KERNEL);
+	if (!refcount)
+		return NULL;
+	refcount->type = type;
+
+	rb_link_node(&refcount->node, parent, new);
+	rb_insert_color(&refcount->node, root);
+	return refcount;
+}
+
+/**
+ * adf_event_get - increase the refcount for an event
+ *
+ * @obj: the object that produces the event
+ * @type: the event type
+ *
+ * ADF will call the object's set_event() op if needed.  ops are allowed
+ * to sleep, so adf_event_get() must NOT be called from an atomic context.
+ *
+ * Returns 0 if successful, or -%EINVAL if the object does not support the
+ * requested event type.
+ */
+int adf_event_get(struct adf_obj *obj, enum adf_event_type type)
+{
+	struct adf_event_refcount *refcount;
+	int old_refcount;
+	int ret;
+
+	ret = adf_obj_check_supports_event(obj, type);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&obj->event_lock);
+
+	refcount = adf_obj_find_event_refcount(obj, type);
+	if (!refcount) {
+		ret = -ENOMEM;
+		goto done;
+	}
+
+	old_refcount = refcount->refcount++;
+
+	if (old_refcount == 0) {
+		obj->ops->set_event(obj, type, true);
+		trace_adf_event_enable(obj, type);
+	}
+
+done:
+	mutex_unlock(&obj->event_lock);
+	return ret;
+}
+EXPORT_SYMBOL(adf_event_get);
+
+/**
+ * adf_event_put - decrease the refcount for an event
+ *
+ * @obj: the object that produces the event
+ * @type: the event type
+ *
+ * ADF will call the object's set_event() op if needed.  ops are allowed
+ * to sleep, so adf_event_put() must NOT be called from an atomic context.
+ *
+ * Returns 0 if successful, -%EINVAL if the object does not support the
+ * requested event type, or -%EALREADY if the refcount is already 0.
+ */
+int adf_event_put(struct adf_obj *obj, enum adf_event_type type)
+{
+	struct adf_event_refcount *refcount;
+	int old_refcount;
+	int ret;
+
+	ret = adf_obj_check_supports_event(obj, type);
+	if (ret < 0)
+		return ret;
+
+
+	mutex_lock(&obj->event_lock);
+
+	refcount = adf_obj_find_event_refcount(obj, type);
+	if (!refcount) {
+		ret = -ENOMEM;
+		goto done;
+	}
+
+	old_refcount = refcount->refcount--;
+
+	if (WARN_ON(old_refcount == 0)) {
+		refcount->refcount++;
+		ret = -EALREADY;
+	} else if (old_refcount == 1) {
+		obj->ops->set_event(obj, type, false);
+		trace_adf_event_disable(obj, type);
+	}
+
+done:
+	mutex_unlock(&obj->event_lock);
+	return ret;
+}
+EXPORT_SYMBOL(adf_event_put);
+
+/**
+ * adf_vsync_wait - wait for a vsync event on a display interface
+ *
+ * @intf: the display interface
+ * @timeout: timeout in jiffies (0 = wait indefinitely)
+ *
+ * adf_vsync_wait() may sleep, so it must NOT be called from an atomic context.
+ *
+ * This function returns -%ERESTARTSYS if it is interrupted by a signal.
+ * If @timeout == 0 then this function returns 0 on vsync. If @timeout > 0 then
+ * this function returns the number of remaining jiffies or -%ETIMEDOUT on
+ * timeout.
+ */
+int adf_vsync_wait(struct adf_interface *intf, long timeout)
+{
+	ktime_t timestamp;
+	int ret;
+	unsigned long flags;
+
+	read_lock_irqsave(&intf->vsync_lock, flags);
+	timestamp = intf->vsync_timestamp;
+	read_unlock_irqrestore(&intf->vsync_lock, flags);
+
+	adf_vsync_get(intf);
+	if (timeout) {
+		ret = wait_event_interruptible_timeout(intf->vsync_wait,
+				!ktime_equal(timestamp,
+						intf->vsync_timestamp),
+				msecs_to_jiffies(timeout));
+		if (ret == 0 && ktime_equal(timestamp, intf->vsync_timestamp))
+			ret = -ETIMEDOUT;
+	} else {
+		ret = wait_event_interruptible(intf->vsync_wait,
+				!ktime_equal(timestamp,
+						intf->vsync_timestamp));
+	}
+	adf_vsync_put(intf);
+
+	return ret;
+}
+EXPORT_SYMBOL(adf_vsync_wait);
+
+static void adf_event_queue(struct adf_obj *obj, struct adf_event *event)
+{
+	struct adf_file *file;
+	unsigned long flags;
+
+	trace_adf_event(obj, event->type);
+
+	spin_lock_irqsave(&obj->file_lock, flags);
+
+	list_for_each_entry(file, &obj->file_list, head)
+		if (test_bit(event->type, file->event_subscriptions))
+			adf_file_queue_event(file, event);
+
+	spin_unlock_irqrestore(&obj->file_lock, flags);
+}
+
+/**
+ * adf_event_notify - notify userspace of a driver-private event
+ *
+ * @obj: the ADF object that produced the event
+ * @event: the event
+ *
+ * adf_event_notify() may be called safely from an atomic context.  It will
+ * copy @event if needed, so @event may point to a variable on the stack.
+ *
+ * Drivers must NOT call adf_event_notify() for vsync and hotplug events.
+ * ADF provides adf_vsync_notify() and
+ * adf_hotplug_notify_{connected,disconnected}() for these events.
+ */
+int adf_event_notify(struct adf_obj *obj, struct adf_event *event)
+{
+	if (WARN_ON(event->type == ADF_EVENT_VSYNC ||
+			event->type == ADF_EVENT_HOTPLUG))
+		return -EINVAL;
+
+	adf_event_queue(obj, event);
+	return 0;
+}
+EXPORT_SYMBOL(adf_event_notify);
+
+/**
+ * adf_vsync_notify - notify ADF of a display interface's vsync event
+ *
+ * @intf: the display interface
+ * @timestamp: the time the vsync occurred
+ *
+ * adf_vsync_notify() may be called safely from an atomic context.
+ */
+void adf_vsync_notify(struct adf_interface *intf, ktime_t timestamp)
+{
+	unsigned long flags;
+	struct adf_vsync_event event;
+
+	write_lock_irqsave(&intf->vsync_lock, flags);
+	intf->vsync_timestamp = timestamp;
+	write_unlock_irqrestore(&intf->vsync_lock, flags);
+
+	wake_up_interruptible_all(&intf->vsync_wait);
+
+	event.base.type = ADF_EVENT_VSYNC;
+	event.base.length = sizeof(event);
+	event.timestamp = ktime_to_ns(timestamp);
+	adf_event_queue(&intf->base, &event.base);
+}
+EXPORT_SYMBOL(adf_vsync_notify);
+
+void adf_hotplug_notify(struct adf_interface *intf, bool connected,
+		struct drm_mode_modeinfo *modelist, size_t n_modes)
+{
+	unsigned long flags;
+	struct adf_hotplug_event event;
+	struct drm_mode_modeinfo *old_modelist;
+
+	write_lock_irqsave(&intf->hotplug_modelist_lock, flags);
+	old_modelist = intf->modelist;
+	intf->hotplug_detect = connected;
+	intf->modelist = modelist;
+	intf->n_modes = n_modes;
+	write_unlock_irqrestore(&intf->hotplug_modelist_lock, flags);
+
+	kfree(old_modelist);
+
+	event.base.length = sizeof(event);
+	event.base.type = ADF_EVENT_HOTPLUG;
+	event.connected = connected;
+	adf_event_queue(&intf->base, &event.base);
+}
+
+/**
+ * adf_hotplug_notify_connected - notify ADF of a display interface being
+ * connected to a display
+ *
+ * @intf: the display interface
+ * @modelist: hardware modes supported by display
+ * @n_modes: length of modelist
+ *
+ * @modelist is copied as needed, so it may point to a variable on the stack.
+ *
+ * adf_hotplug_notify_connected() may NOT be called safely from an atomic
+ * context.
+ *
+ * Returns 0 on success or error code (<0) on error.
+ */
+int adf_hotplug_notify_connected(struct adf_interface *intf,
+		struct drm_mode_modeinfo *modelist, size_t n_modes)
+{
+	struct drm_mode_modeinfo *modelist_copy;
+
+	if (n_modes > ADF_MAX_MODES)
+		return -ENOMEM;
+
+	modelist_copy = kzalloc(sizeof(modelist_copy[0]) * n_modes,
+			GFP_KERNEL);
+	if (!modelist_copy)
+		return -ENOMEM;
+	memcpy(modelist_copy, modelist, sizeof(modelist_copy[0]) * n_modes);
+
+	adf_hotplug_notify(intf, true, modelist_copy, n_modes);
+	return 0;
+}
+EXPORT_SYMBOL(adf_hotplug_notify_connected);
+
+/**
+ * adf_hotplug_notify_disconnected - notify ADF of a display interface being
+ * disconnected from a display
+ *
+ * @intf: the display interface
+ *
+ * adf_hotplug_notify_disconnected() may be called safely from an atomic
+ * context.
+ */
+void adf_hotplug_notify_disconnected(struct adf_interface *intf)
+{
+	adf_hotplug_notify(intf, false, NULL, 0);
+}
+EXPORT_SYMBOL(adf_hotplug_notify_disconnected);
+
+static int adf_obj_init(struct adf_obj *obj, enum adf_obj_type type,
+		struct idr *idr, struct adf_device *parent,
+		const struct adf_obj_ops *ops, const char *fmt, va_list args)
+{
+	int ret;
+
+	if (ops && ops->supports_event && !ops->set_event) {
+		pr_err("%s: %s implements supports_event but not set_event\n",
+				__func__, adf_obj_type_str(type));
+		return -EINVAL;
+	}
+
+	ret = idr_alloc(idr, obj, 0, 0, GFP_KERNEL);
+	if (ret < 0) {
+		pr_err("%s: allocating object id failed: %d\n", __func__, ret);
+		return ret;
+	}
+	obj->id = ret;
+
+	vscnprintf(obj->name, sizeof(obj->name), fmt, args);
+
+	obj->type = type;
+	obj->ops = ops;
+	obj->parent = parent;
+	mutex_init(&obj->event_lock);
+	obj->event_refcount = RB_ROOT;
+	spin_lock_init(&obj->file_lock);
+	INIT_LIST_HEAD(&obj->file_list);
+	return 0;
+}
+
+static void adf_obj_destroy(struct adf_obj *obj, struct idr *idr)
+{
+	struct rb_node *node = rb_first(&obj->event_refcount);
+
+	while (node) {
+		struct adf_event_refcount *refcount =
+				container_of(node, struct adf_event_refcount,
+						node);
+		rb_erase(&refcount->node, &obj->event_refcount);
+		kfree(refcount);
+		node = rb_first(&obj->event_refcount);
+	}
+
+	mutex_destroy(&obj->event_lock);
+	idr_remove(idr, obj->id);
+}
+
+/**
+ * adf_device_init - initialize ADF-internal data for a display device
+ * and create sysfs entries
+ *
+ * @dev: the display device
+ * @parent: the device's parent device
+ * @ops: the device's associated ops
+ * @fmt: formatting string for the display device's name
+ *
+ * @fmt specifies the device's sysfs filename and the name returned to
+ * userspace through the %ADF_GET_DEVICE_DATA ioctl.
+ *
+ * Returns 0 on success or error code (<0) on failure.
+ */
+int adf_device_init(struct adf_device *dev, struct device *parent,
+		const struct adf_device_ops *ops, const char *fmt, ...)
+{
+	int ret;
+	va_list args;
+
+	if (!ops->validate || !ops->post) {
+		pr_err("%s: device must implement validate and post\n",
+				__func__);
+		return -EINVAL;
+	}
+
+	if (!ops->complete_fence && !ops->advance_timeline) {
+		if (!IS_ENABLED(CONFIG_SW_SYNC)) {
+			pr_err("%s: device requires sw_sync but it is not enabled in the kernel\n",
+					__func__);
+			return -EINVAL;
+		}
+	} else if (!(ops->complete_fence && ops->advance_timeline)) {
+		pr_err("%s: device must implement both complete_fence and advance_timeline, or implement neither\n",
+				__func__);
+		return -EINVAL;
+	}
+
+	memset(dev, 0, sizeof(*dev));
+
+	va_start(args, fmt);
+	ret = adf_obj_init(&dev->base, ADF_OBJ_DEVICE, &adf_devices, dev,
+			&ops->base, fmt, args);
+	va_end(args);
+	if (ret < 0)
+		return ret;
+
+	dev->dev = parent;
+	dev->ops = ops;
+	idr_init(&dev->overlay_engines);
+	idr_init(&dev->interfaces);
+	mutex_init(&dev->client_lock);
+	INIT_LIST_HEAD(&dev->post_list);
+	mutex_init(&dev->post_lock);
+	init_kthread_worker(&dev->post_worker);
+	INIT_LIST_HEAD(&dev->attached);
+	INIT_LIST_HEAD(&dev->attach_allowed);
+
+	dev->post_thread = kthread_run(kthread_worker_fn,
+			&dev->post_worker, dev->base.name);
+	if (IS_ERR(dev->post_thread)) {
+		ret = PTR_ERR(dev->post_thread);
+		dev->post_thread = NULL;
+
+		pr_err("%s: failed to run config posting thread: %d\n",
+				__func__, ret);
+		goto err;
+	}
+	init_kthread_work(&dev->post_work, adf_post_work_func);
+
+	ret = adf_device_sysfs_init(dev);
+	if (ret < 0)
+		goto err;
+
+	return 0;
+
+err:
+	adf_device_destroy(dev);
+	return ret;
+}
+EXPORT_SYMBOL(adf_device_init);
+
+/**
+ * adf_device_destroy - clean up ADF-internal data for a display device
+ *
+ * @dev: the display device
+ */
+void adf_device_destroy(struct adf_device *dev)
+{
+	struct adf_attachment_list *entry, *next;
+
+	idr_destroy(&dev->interfaces);
+	idr_destroy(&dev->overlay_engines);
+
+	if (dev->post_thread) {
+		flush_kthread_worker(&dev->post_worker);
+		kthread_stop(dev->post_thread);
+	}
+
+	if (dev->onscreen)
+		adf_post_cleanup(dev, dev->onscreen);
+	adf_device_sysfs_destroy(dev);
+	list_for_each_entry_safe(entry, next, &dev->attach_allowed, head) {
+		adf_attachment_free(entry);
+	}
+	list_for_each_entry_safe(entry, next, &dev->attached, head) {
+		adf_attachment_free(entry);
+	}
+	mutex_destroy(&dev->post_lock);
+	mutex_destroy(&dev->client_lock);
+
+	if (dev->timeline)
+		sync_timeline_destroy(&dev->timeline->obj);
+
+	adf_obj_destroy(&dev->base, &adf_devices);
+}
+EXPORT_SYMBOL(adf_device_destroy);
+
+/**
+ * adf_interface_init - initialize ADF-internal data for a display interface
+ * and create sysfs entries
+ *
+ * @intf: the display interface
+ * @dev: the interface's "parent" display device
+ * @type: interface type (see enum @adf_interface_type)
+ * @idx: which interface of type @type;
+ *	e.g. interface DSI.1 -> @type=%ADF_INTF_TYPE_DSI, @idx=1
+ * @flags: informational flags (bitmask of %ADF_INTF_FLAG_* values)
+ * @ops: the interface's associated ops
+ * @fmt: formatting string for the display interface's name
+ *
+ * @dev must have previously been initialized with adf_device_init().
+ *
+ * @fmt affects the name returned to userspace through the
+ * %ADF_GET_INTERFACE_DATA ioctl.  It does not affect the sysfs filename,
+ * which is derived from @dev's name.
+ *
+ * Returns 0 on success or error code (<0) on failure.
+ */
+int adf_interface_init(struct adf_interface *intf, struct adf_device *dev,
+		enum adf_interface_type type, u32 idx, u32 flags,
+		const struct adf_interface_ops *ops, const char *fmt, ...)
+{
+	int ret;
+	va_list args;
+	const u32 allowed_flags = ADF_INTF_FLAG_PRIMARY |
+			ADF_INTF_FLAG_EXTERNAL;
+
+	if (dev->n_interfaces == ADF_MAX_INTERFACES) {
+		pr_err("%s: parent device %s has too many interfaces\n",
+				__func__, dev->base.name);
+		return -ENOMEM;
+	}
+
+	if (type >= ADF_INTF_MEMORY && type <= ADF_INTF_TYPE_DEVICE_CUSTOM) {
+		pr_err("%s: invalid interface type %u\n", __func__, type);
+		return -EINVAL;
+	}
+
+	if (flags & ~allowed_flags) {
+		pr_err("%s: invalid interface flags 0x%X\n", __func__,
+				flags & ~allowed_flags);
+		return -EINVAL;
+	}
+
+	memset(intf, 0, sizeof(*intf));
+
+	va_start(args, fmt);
+	ret = adf_obj_init(&intf->base, ADF_OBJ_INTERFACE, &dev->interfaces,
+			dev, ops ? &ops->base : NULL, fmt, args);
+	va_end(args);
+	if (ret < 0)
+		return ret;
+
+	intf->type = type;
+	intf->idx = idx;
+	intf->flags = flags;
+	intf->ops = ops;
+	intf->dpms_state = DRM_MODE_DPMS_OFF;
+	init_waitqueue_head(&intf->vsync_wait);
+	rwlock_init(&intf->vsync_lock);
+	rwlock_init(&intf->hotplug_modelist_lock);
+
+	ret = adf_interface_sysfs_init(intf);
+	if (ret < 0)
+		goto err;
+	dev->n_interfaces++;
+
+	return 0;
+
+err:
+	adf_obj_destroy(&intf->base, &dev->interfaces);
+	return ret;
+}
+EXPORT_SYMBOL(adf_interface_init);
+
+/**
+ * adf_interface_destroy - clean up ADF-internal data for a display interface
+ *
+ * @intf: the display interface
+ */
+void adf_interface_destroy(struct adf_interface *intf)
+{
+	struct adf_device *dev = adf_interface_parent(intf);
+	struct adf_attachment_list *entry, *next;
+
+	mutex_lock(&dev->client_lock);
+	list_for_each_entry_safe(entry, next, &dev->attach_allowed, head) {
+		if (entry->attachment.interface == intf) {
+			adf_attachment_free(entry);
+			dev->n_attach_allowed--;
+		}
+	}
+	list_for_each_entry_safe(entry, next, &dev->attached, head) {
+		if (entry->attachment.interface == intf) {
+			adf_device_detach_op(dev,
+					entry->attachment.overlay_engine, intf);
+			adf_attachment_free(entry);
+			dev->n_attached--;
+		}
+	}
+	kfree(intf->modelist);
+	adf_interface_sysfs_destroy(intf);
+	adf_obj_destroy(&intf->base, &dev->interfaces);
+	dev->n_interfaces--;
+	mutex_unlock(&dev->client_lock);
+}
+EXPORT_SYMBOL(adf_interface_destroy);
+
+static bool adf_overlay_engine_has_custom_formats(
+		const struct adf_overlay_engine_ops *ops)
+{
+	size_t i;
+	for (i = 0; i < ops->n_supported_formats; i++)
+		if (!adf_format_is_standard(ops->supported_formats[i]))
+			return true;
+	return false;
+}
+
+/**
+ * adf_overlay_engine_init - initialize ADF-internal data for an
+ * overlay engine and create sysfs entries
+ *
+ * @eng: the overlay engine
+ * @dev: the overlay engine's "parent" display device
+ * @ops: the overlay engine's associated ops
+ * @fmt: formatting string for the overlay engine's name
+ *
+ * @dev must have previously been initialized with adf_device_init().
+ *
+ * @fmt affects the name returned to userspace through the
+ * %ADF_GET_OVERLAY_ENGINE_DATA ioctl.  It does not affect the sysfs filename,
+ * which is derived from @dev's name.
+ *
+ * Returns 0 on success or error code (<0) on failure.
+ */
+int adf_overlay_engine_init(struct adf_overlay_engine *eng,
+		struct adf_device *dev,
+		const struct adf_overlay_engine_ops *ops, const char *fmt, ...)
+{
+	int ret;
+	va_list args;
+
+	if (!ops->supported_formats) {
+		pr_err("%s: overlay engine must support at least one format\n",
+				__func__);
+		return -EINVAL;
+	}
+
+	if (ops->n_supported_formats > ADF_MAX_SUPPORTED_FORMATS) {
+		pr_err("%s: overlay engine supports too many formats\n",
+				__func__);
+		return -EINVAL;
+	}
+
+	if (adf_overlay_engine_has_custom_formats(ops) &&
+			!dev->ops->validate_custom_format) {
+		pr_err("%s: overlay engine has custom formats but parent device %s does not implement validate_custom_format\n",
+				__func__, dev->base.name);
+		return -EINVAL;
+	}
+
+	memset(eng, 0, sizeof(*eng));
+
+	va_start(args, fmt);
+	ret = adf_obj_init(&eng->base, ADF_OBJ_OVERLAY_ENGINE,
+			&dev->overlay_engines, dev, &ops->base, fmt, args);
+	va_end(args);
+	if (ret < 0)
+		return ret;
+
+	eng->ops = ops;
+
+	ret = adf_overlay_engine_sysfs_init(eng);
+	if (ret < 0)
+		goto err;
+
+	return 0;
+
+err:
+	adf_obj_destroy(&eng->base, &dev->overlay_engines);
+	return ret;
+}
+EXPORT_SYMBOL(adf_overlay_engine_init);
+
+/**
+ * adf_interface_destroy - clean up ADF-internal data for an overlay engine
+ *
+ * @eng: the overlay engine
+ */
+void adf_overlay_engine_destroy(struct adf_overlay_engine *eng)
+{
+	struct adf_device *dev = adf_overlay_engine_parent(eng);
+	struct adf_attachment_list *entry, *next;
+
+	mutex_lock(&dev->client_lock);
+	list_for_each_entry_safe(entry, next, &dev->attach_allowed, head) {
+		if (entry->attachment.overlay_engine == eng) {
+			adf_attachment_free(entry);
+			dev->n_attach_allowed--;
+		}
+	}
+	list_for_each_entry_safe(entry, next, &dev->attached, head) {
+		if (entry->attachment.overlay_engine == eng) {
+			adf_device_detach_op(dev, eng,
+					entry->attachment.interface);
+			adf_attachment_free(entry);
+			dev->n_attached--;
+		}
+	}
+	adf_overlay_engine_sysfs_destroy(eng);
+	adf_obj_destroy(&eng->base, &dev->overlay_engines);
+	mutex_unlock(&dev->client_lock);
+}
+EXPORT_SYMBOL(adf_overlay_engine_destroy);
+
+struct adf_attachment_list *adf_attachment_find(struct list_head *list,
+		struct adf_overlay_engine *eng, struct adf_interface *intf)
+{
+	struct adf_attachment_list *entry;
+	list_for_each_entry(entry, list, head) {
+		if (entry->attachment.interface == intf &&
+				entry->attachment.overlay_engine == eng)
+			return entry;
+	}
+	return NULL;
+}
+
+int adf_attachment_validate(struct adf_device *dev,
+		struct adf_overlay_engine *eng, struct adf_interface *intf)
+{
+	struct adf_device *intf_dev = adf_interface_parent(intf);
+	struct adf_device *eng_dev = adf_overlay_engine_parent(eng);
+
+	if (intf_dev != dev) {
+		dev_err(&dev->base.dev, "can't attach interface %s belonging to device %s\n",
+				intf->base.name, intf_dev->base.name);
+		return -EINVAL;
+	}
+
+	if (eng_dev != dev) {
+		dev_err(&dev->base.dev, "can't attach overlay engine %s belonging to device %s\n",
+				eng->base.name, eng_dev->base.name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * adf_attachment_allow - add a new entry to the list of allowed
+ * attachments
+ *
+ * @dev: the parent device
+ * @eng: the overlay engine
+ * @intf: the interface
+ *
+ * adf_attachment_allow() indicates that the underlying display hardware allows
+ * @intf to scan out @eng's output.  It is intended to be called at
+ * driver initialization for each supported overlay engine + interface pair.
+ *
+ * Returns 0 on success, -%EALREADY if the entry already exists, or -errno on
+ * any other failure.
+ */
+int adf_attachment_allow(struct adf_device *dev,
+		struct adf_overlay_engine *eng, struct adf_interface *intf)
+{
+	int ret;
+	struct adf_attachment_list *entry = NULL;
+
+	ret = adf_attachment_validate(dev, eng, intf);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&dev->client_lock);
+
+	if (dev->n_attach_allowed == ADF_MAX_ATTACHMENTS) {
+		ret = -ENOMEM;
+		goto done;
+	}
+
+	if (adf_attachment_find(&dev->attach_allowed, eng, intf)) {
+		ret = -EALREADY;
+		goto done;
+	}
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry) {
+		ret = -ENOMEM;
+		goto done;
+	}
+
+	entry->attachment.interface = intf;
+	entry->attachment.overlay_engine = eng;
+	list_add_tail(&entry->head, &dev->attach_allowed);
+	dev->n_attach_allowed++;
+
+done:
+	mutex_unlock(&dev->client_lock);
+	if (ret < 0)
+		kfree(entry);
+
+	return ret;
+}
+EXPORT_SYMBOL(adf_attachment_allow);
+
+/**
+ * adf_obj_type_str - string representation of an adf_obj_type
+ *
+ * @type: the object type
+ */
+const char *adf_obj_type_str(enum adf_obj_type type)
+{
+	switch (type) {
+	case ADF_OBJ_OVERLAY_ENGINE:
+		return "overlay engine";
+
+	case ADF_OBJ_INTERFACE:
+		return "interface";
+
+	case ADF_OBJ_DEVICE:
+		return "device";
+
+	default:
+		return "unknown";
+	}
+}
+EXPORT_SYMBOL(adf_obj_type_str);
+
+/**
+ * adf_interface_type_str - string representation of an adf_interface's type
+ *
+ * @intf: the interface
+ */
+const char *adf_interface_type_str(struct adf_interface *intf)
+{
+	switch (intf->type) {
+	case ADF_INTF_DSI:
+		return "DSI";
+
+	case ADF_INTF_eDP:
+		return "eDP";
+
+	case ADF_INTF_DPI:
+		return "DPI";
+
+	case ADF_INTF_VGA:
+		return "VGA";
+
+	case ADF_INTF_DVI:
+		return "DVI";
+
+	case ADF_INTF_HDMI:
+		return "HDMI";
+
+	case ADF_INTF_MEMORY:
+		return "memory";
+
+	default:
+		if (intf->type >= ADF_INTF_TYPE_DEVICE_CUSTOM) {
+			if (intf->ops && intf->ops->type_str)
+				return intf->ops->type_str(intf);
+			return "custom";
+		}
+		return "unknown";
+	}
+}
+EXPORT_SYMBOL(adf_interface_type_str);
+
+/**
+ * adf_event_type_str - string representation of an adf_event_type
+ *
+ * @obj: ADF object that produced the event
+ * @type: event type
+ */
+const char *adf_event_type_str(struct adf_obj *obj, enum adf_event_type type)
+{
+	switch (type) {
+	case ADF_EVENT_VSYNC:
+		return "vsync";
+
+	case ADF_EVENT_HOTPLUG:
+		return "hotplug";
+
+	default:
+		if (type >= ADF_EVENT_DEVICE_CUSTOM) {
+			if (obj->ops && obj->ops->event_type_str)
+				return obj->ops->event_type_str(obj, type);
+			return "custom";
+		}
+		return "unknown";
+	}
+}
+EXPORT_SYMBOL(adf_event_type_str);
+
+/**
+ * adf_format_str - string representation of an ADF/DRM fourcc format
+ *
+ * @format: format fourcc
+ * @buf: target buffer for the format's string representation
+ */
+void adf_format_str(u32 format, char buf[ADF_FORMAT_STR_SIZE])
+{
+	buf[0] = format & 0xFF;
+	buf[1] = (format >> 8) & 0xFF;
+	buf[2] = (format >> 16) & 0xFF;
+	buf[3] = (format >> 24) & 0xFF;
+	buf[4] = '\0';
+}
+EXPORT_SYMBOL(adf_format_str);
+
+/**
+ * adf_format_validate_yuv - validate the number and size of planes in buffers
+ * with a custom YUV format.
+ *
+ * @dev: ADF device performing the validation
+ * @buf: buffer to validate
+ * @num_planes: expected number of planes
+ * @hsub: expected horizontal chroma subsampling factor, in pixels
+ * @vsub: expected vertical chroma subsampling factor, in pixels
+ * @cpp: expected bytes per pixel for each plane (length @num_planes)
+ *
+ * adf_format_validate_yuv() is intended to be called as a helper from @dev's
+ * validate_custom_format() op.
+ *
+ * Returns 0 if @buf has the expected number of planes and each plane
+ * has sufficient size, or -EINVAL otherwise.
+ */
+int adf_format_validate_yuv(struct adf_device *dev, struct adf_buffer *buf,
+		u8 num_planes, u8 hsub, u8 vsub, u8 cpp[])
+{
+	u8 i;
+
+	if (num_planes != buf->n_planes) {
+		char format_str[ADF_FORMAT_STR_SIZE];
+		adf_format_str(buf->format, format_str);
+		dev_err(&dev->base.dev, "%u planes expected for format %s but %u planes provided\n",
+				num_planes, format_str, buf->n_planes);
+		return -EINVAL;
+	}
+
+	if (buf->w == 0 || buf->w % hsub) {
+		dev_err(&dev->base.dev, "bad buffer width %u\n", buf->w);
+		return -EINVAL;
+	}
+
+	if (buf->h == 0 || buf->h % vsub) {
+		dev_err(&dev->base.dev, "bad buffer height %u\n", buf->h);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < num_planes; i++) {
+		u32 width = buf->w / (i != 0 ? hsub : 1);
+		u32 height = buf->h / (i != 0 ? vsub : 1);
+		u8 cpp = adf_format_plane_cpp(buf->format, i);
+		u32 last_line_size;
+
+		if (buf->pitch[i] < (u64) width * cpp) {
+			dev_err(&dev->base.dev, "plane %u pitch is shorter than buffer width (pitch = %u, width = %u, bpp = %u)\n",
+					i, buf->pitch[i], width, cpp * 8);
+			return -EINVAL;
+		}
+
+		switch (dev->ops->quirks.buffer_padding) {
+		case ADF_BUFFER_PADDED_TO_PITCH:
+			last_line_size = buf->pitch[i];
+			break;
+
+		case ADF_BUFFER_UNPADDED:
+			last_line_size = width * cpp;
+			break;
+
+		default:
+			BUG();
+		}
+
+		if ((u64) (height - 1) * buf->pitch[i] + last_line_size +
+				buf->offset[i] > buf->dma_bufs[i]->size) {
+			dev_err(&dev->base.dev, "plane %u buffer too small (height = %u, pitch = %u, offset = %u, size = %zu)\n",
+					i, height, buf->pitch[i],
+					buf->offset[i], buf->dma_bufs[i]->size);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(adf_format_validate_yuv);
+
+/**
+ * adf_modeinfo_set_name - sets the name of a mode from its display resolution
+ *
+ * @mode: mode
+ *
+ * adf_modeinfo_set_name() fills in @mode->name in the format
+ * "[hdisplay]x[vdisplay](i)".  It is intended to help drivers create
+ * ADF/DRM-style modelists from other mode formats.
+ */
+void adf_modeinfo_set_name(struct drm_mode_modeinfo *mode)
+{
+	bool interlaced = mode->flags & DRM_MODE_FLAG_INTERLACE;
+
+	snprintf(mode->name, DRM_DISPLAY_MODE_LEN, "%dx%d%s",
+		 mode->hdisplay, mode->vdisplay,
+		 interlaced ? "i" : "");
+}
+EXPORT_SYMBOL(adf_modeinfo_set_name);
+
+/**
+ * adf_modeinfo_set_vrefresh - sets the vrefresh of a mode from its other
+ * timing data
+ *
+ * @mode: mode
+ *
+ * adf_modeinfo_set_vrefresh() calculates @mode->vrefresh from
+ * @mode->{h,v}display and @mode->flags.  It is intended to help drivers
+ * create ADF/DRM-style modelists from other mode formats.
+ */
+void adf_modeinfo_set_vrefresh(struct drm_mode_modeinfo *mode)
+{
+	int refresh = 0;
+	unsigned int calc_val;
+
+	if (mode->vrefresh > 0)
+		return;
+
+	if (mode->htotal <= 0 || mode->vtotal <= 0)
+		return;
+
+	/* work out vrefresh the value will be x1000 */
+	calc_val = (mode->clock * 1000);
+	calc_val /= mode->htotal;
+	refresh = (calc_val + mode->vtotal / 2) / mode->vtotal;
+
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+		refresh *= 2;
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		refresh /= 2;
+	if (mode->vscan > 1)
+		refresh /= mode->vscan;
+
+	mode->vrefresh = refresh;
+}
+EXPORT_SYMBOL(adf_modeinfo_set_vrefresh);
+
+static int __init adf_init(void)
+{
+	int err;
+
+	err = adf_sysfs_init();
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static void __exit adf_exit(void)
+{
+	adf_sysfs_destroy();
+}
+
+module_init(adf_init);
+module_exit(adf_exit);
diff --git a/drivers/video/adf/adf.h b/drivers/video/adf/adf.h
new file mode 100644
index 00000000000..3bcf1fabc23
--- /dev/null
+++ b/drivers/video/adf/adf.h
@@ -0,0 +1,71 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __VIDEO_ADF_ADF_H
+#define __VIDEO_ADF_ADF_H
+
+#include <linux/idr.h>
+#include <linux/list.h>
+#include <video/adf.h>
+#include "sync.h"
+
+struct adf_event_refcount {
+	struct rb_node node;
+	enum adf_event_type type;
+	int refcount;
+};
+
+void adf_buffer_cleanup(struct adf_buffer *buf);
+void adf_buffer_mapping_cleanup(struct adf_buffer_mapping *mapping,
+		struct adf_buffer *buf);
+void adf_post_cleanup(struct adf_device *dev, struct adf_pending_post *post);
+
+struct adf_attachment_list *adf_attachment_find(struct list_head *list,
+		struct adf_overlay_engine *eng, struct adf_interface *intf);
+int adf_attachment_validate(struct adf_device *dev,
+		struct adf_overlay_engine *eng, struct adf_interface *intf);
+void adf_attachment_free(struct adf_attachment_list *attachment);
+
+struct adf_event_refcount *adf_obj_find_event_refcount(struct adf_obj *obj,
+		enum adf_event_type type);
+
+static inline int adf_obj_check_supports_event(struct adf_obj *obj,
+		enum adf_event_type type)
+{
+	if (!obj->ops || !obj->ops->supports_event)
+		return -EOPNOTSUPP;
+	if (!obj->ops->supports_event(obj, type))
+		return -EINVAL;
+	return 0;
+}
+
+static inline int adf_device_attach_op(struct adf_device *dev,
+		struct adf_overlay_engine *eng, struct adf_interface *intf)
+{
+	if (!dev->ops->attach)
+		return 0;
+
+	return dev->ops->attach(dev, eng, intf);
+}
+
+static inline int adf_device_detach_op(struct adf_device *dev,
+		struct adf_overlay_engine *eng, struct adf_interface *intf)
+{
+	if (!dev->ops->detach)
+		return 0;
+
+	return dev->ops->detach(dev, eng, intf);
+}
+
+#endif /* __VIDEO_ADF_ADF_H */
diff --git a/drivers/video/adf/adf_client.c b/drivers/video/adf/adf_client.c
new file mode 100644
index 00000000000..8061d8e6b9f
--- /dev/null
+++ b/drivers/video/adf/adf_client.c
@@ -0,0 +1,811 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kthread.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+
+#include "sw_sync.h"
+
+#include <video/adf.h>
+#include <video/adf_client.h>
+#include <video/adf_format.h>
+
+#include "adf.h"
+
+static inline bool vsync_active(u8 state)
+{
+	return state == DRM_MODE_DPMS_ON || state == DRM_MODE_DPMS_STANDBY;
+}
+
+/**
+ * adf_interface_blank - set interface's DPMS state
+ *
+ * @intf: the interface
+ * @state: one of %DRM_MODE_DPMS_*
+ *
+ * Returns 0 on success or -errno on failure.
+ */
+int adf_interface_blank(struct adf_interface *intf, u8 state)
+{
+	struct adf_device *dev = adf_interface_parent(intf);
+	u8 prev_state;
+	bool disable_vsync;
+	bool enable_vsync;
+	int ret = 0;
+	struct adf_event_refcount *vsync_refcount;
+
+	if (!intf->ops || !intf->ops->blank)
+		return -EOPNOTSUPP;
+
+	if (state > DRM_MODE_DPMS_OFF)
+		return -EINVAL;
+
+	mutex_lock(&dev->client_lock);
+	if (state != DRM_MODE_DPMS_ON)
+		flush_kthread_worker(&dev->post_worker);
+	mutex_lock(&intf->base.event_lock);
+
+	vsync_refcount = adf_obj_find_event_refcount(&intf->base,
+			ADF_EVENT_VSYNC);
+	if (!vsync_refcount) {
+		ret = -ENOMEM;
+		goto done;
+	}
+
+	prev_state = intf->dpms_state;
+	if (prev_state == state) {
+		ret = -EBUSY;
+		goto done;
+	}
+
+	disable_vsync = vsync_active(prev_state) &&
+			!vsync_active(state) &&
+			vsync_refcount->refcount;
+	enable_vsync = !vsync_active(prev_state) &&
+			vsync_active(state) &&
+			vsync_refcount->refcount;
+
+	if (disable_vsync)
+		intf->base.ops->set_event(&intf->base, ADF_EVENT_VSYNC,
+				false);
+
+	ret = intf->ops->blank(intf, state);
+	if (ret < 0) {
+		if (disable_vsync)
+			intf->base.ops->set_event(&intf->base, ADF_EVENT_VSYNC,
+					true);
+		goto done;
+	}
+
+	if (enable_vsync)
+		intf->base.ops->set_event(&intf->base, ADF_EVENT_VSYNC,
+				true);
+
+	intf->dpms_state = state;
+done:
+	mutex_unlock(&intf->base.event_lock);
+	mutex_unlock(&dev->client_lock);
+	return ret;
+}
+EXPORT_SYMBOL(adf_interface_blank);
+
+/**
+ * adf_interface_blank - get interface's current DPMS state
+ *
+ * @intf: the interface
+ *
+ * Returns one of %DRM_MODE_DPMS_*.
+ */
+u8 adf_interface_dpms_state(struct adf_interface *intf)
+{
+	struct adf_device *dev = adf_interface_parent(intf);
+	u8 dpms_state;
+
+	mutex_lock(&dev->client_lock);
+	dpms_state = intf->dpms_state;
+	mutex_unlock(&dev->client_lock);
+
+	return dpms_state;
+}
+EXPORT_SYMBOL(adf_interface_dpms_state);
+
+/**
+ * adf_interface_current_mode - get interface's current display mode
+ *
+ * @intf: the interface
+ * @mode: returns the current mode
+ */
+void adf_interface_current_mode(struct adf_interface *intf,
+		struct drm_mode_modeinfo *mode)
+{
+	struct adf_device *dev = adf_interface_parent(intf);
+
+	mutex_lock(&dev->client_lock);
+	memcpy(mode, &intf->current_mode, sizeof(*mode));
+	mutex_unlock(&dev->client_lock);
+}
+EXPORT_SYMBOL(adf_interface_current_mode);
+
+/**
+ * adf_interface_modelist - get interface's modelist
+ *
+ * @intf: the interface
+ * @modelist: storage for the modelist (optional)
+ * @n_modes: length of @modelist
+ *
+ * If @modelist is not NULL, adf_interface_modelist() will copy up to @n_modes
+ * modelist entries into @modelist.
+ *
+ * Returns the length of the modelist.
+ */
+size_t adf_interface_modelist(struct adf_interface *intf,
+		struct drm_mode_modeinfo *modelist, size_t n_modes)
+{
+	unsigned long flags;
+	size_t retval;
+
+	read_lock_irqsave(&intf->hotplug_modelist_lock, flags);
+	if (modelist)
+		memcpy(modelist, intf->modelist, sizeof(modelist[0]) *
+				min(n_modes, intf->n_modes));
+	retval = intf->n_modes;
+	read_unlock_irqrestore(&intf->hotplug_modelist_lock, flags);
+
+	return retval;
+}
+EXPORT_SYMBOL(adf_interface_modelist);
+
+/**
+ * adf_interface_set_mode - set interface's display mode
+ *
+ * @intf: the interface
+ * @mode: the new mode
+ *
+ * Returns 0 on success or -errno on failure.
+ */
+int adf_interface_set_mode(struct adf_interface *intf,
+		struct drm_mode_modeinfo *mode)
+{
+	struct adf_device *dev = adf_interface_parent(intf);
+	int ret = 0;
+
+	if (!intf->ops || !intf->ops->modeset)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&dev->client_lock);
+	flush_kthread_worker(&dev->post_worker);
+
+	ret = intf->ops->modeset(intf, mode);
+	if (ret < 0)
+		goto done;
+
+	memcpy(&intf->current_mode, mode, sizeof(*mode));
+done:
+	mutex_unlock(&dev->client_lock);
+	return ret;
+}
+EXPORT_SYMBOL(adf_interface_set_mode);
+
+/**
+ * adf_interface_screen_size - get size of screen connected to interface
+ *
+ * @intf: the interface
+ * @width_mm: returns the screen width in mm
+ * @height_mm: returns the screen width in mm
+ *
+ * Returns 0 on success or -errno on failure.
+ */
+int adf_interface_get_screen_size(struct adf_interface *intf, u16 *width_mm,
+		u16 *height_mm)
+{
+	struct adf_device *dev = adf_interface_parent(intf);
+	int ret;
+
+	if (!intf->ops || !intf->ops->screen_size)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&dev->client_lock);
+	ret = intf->ops->screen_size(intf, width_mm, height_mm);
+	mutex_unlock(&dev->client_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL(adf_interface_get_screen_size);
+
+/**
+ * adf_overlay_engine_supports_format - returns whether a format is in an
+ * overlay engine's supported list
+ *
+ * @eng: the overlay engine
+ * @format: format fourcc
+ */
+bool adf_overlay_engine_supports_format(struct adf_overlay_engine *eng,
+		u32 format)
+{
+	size_t i;
+	for (i = 0; i < eng->ops->n_supported_formats; i++)
+		if (format == eng->ops->supported_formats[i])
+			return true;
+
+	return false;
+}
+EXPORT_SYMBOL(adf_overlay_engine_supports_format);
+
+static int adf_buffer_validate(struct adf_buffer *buf)
+{
+	struct adf_overlay_engine *eng = buf->overlay_engine;
+	struct device *dev = &eng->base.dev;
+	struct adf_device *parent = adf_overlay_engine_parent(eng);
+	u8 hsub, vsub, num_planes, cpp[ADF_MAX_PLANES], i;
+
+	if (!adf_overlay_engine_supports_format(eng, buf->format)) {
+		char format_str[ADF_FORMAT_STR_SIZE];
+		adf_format_str(buf->format, format_str);
+		dev_err(dev, "unsupported format %s\n", format_str);
+		return -EINVAL;
+	}
+
+	if (!adf_format_is_standard(buf->format))
+		return parent->ops->validate_custom_format(parent, buf);
+
+	hsub = adf_format_horz_chroma_subsampling(buf->format);
+	vsub = adf_format_vert_chroma_subsampling(buf->format);
+	num_planes = adf_format_num_planes(buf->format);
+	for (i = 0; i < num_planes; i++)
+		cpp[i] = adf_format_plane_cpp(buf->format, i);
+
+	return adf_format_validate_yuv(parent, buf, num_planes, hsub, vsub,
+			cpp);
+}
+
+static int adf_buffer_map(struct adf_device *dev, struct adf_buffer *buf,
+		struct adf_buffer_mapping *mapping)
+{
+	int ret = 0;
+	size_t i;
+
+	for (i = 0; i < buf->n_planes; i++) {
+		struct dma_buf_attachment *attachment;
+		struct sg_table *sg_table;
+
+		attachment = dma_buf_attach(buf->dma_bufs[i], dev->dev);
+		if (IS_ERR(attachment)) {
+			ret = PTR_ERR(attachment);
+			dev_err(&dev->base.dev, "attaching plane %zu failed: %d\n",
+					i, ret);
+			goto done;
+		}
+		mapping->attachments[i] = attachment;
+
+		sg_table = dma_buf_map_attachment(attachment, DMA_TO_DEVICE);
+		if (IS_ERR(sg_table)) {
+			ret = PTR_ERR(sg_table);
+			dev_err(&dev->base.dev, "mapping plane %zu failed: %d",
+					i, ret);
+			goto done;
+		} else if (!sg_table) {
+			ret = -ENOMEM;
+			dev_err(&dev->base.dev, "mapping plane %zu failed\n",
+					i);
+			goto done;
+		}
+		mapping->sg_tables[i] = sg_table;
+	}
+
+done:
+	if (ret < 0)
+		adf_buffer_mapping_cleanup(mapping, buf);
+
+	return ret;
+}
+
+static struct sync_fence *adf_sw_complete_fence(struct adf_device *dev)
+{
+	struct sync_pt *pt;
+	struct sync_fence *complete_fence;
+
+	if (!dev->timeline) {
+		dev->timeline = sw_sync_timeline_create(dev->base.name);
+		if (!dev->timeline)
+			return ERR_PTR(-ENOMEM);
+		dev->timeline_max = 1;
+	}
+
+	dev->timeline_max++;
+	pt = sw_sync_pt_create(dev->timeline, dev->timeline_max);
+	if (!pt)
+		goto err_pt_create;
+	complete_fence = sync_fence_create(dev->base.name, pt);
+	if (!complete_fence)
+		goto err_fence_create;
+
+	return complete_fence;
+
+err_fence_create:
+	sync_pt_free(pt);
+err_pt_create:
+	dev->timeline_max--;
+	return ERR_PTR(-ENOSYS);
+}
+
+/**
+ * adf_device_post - flip to a new set of buffers
+ *
+ * @dev: device targeted by the flip
+ * @intfs: interfaces targeted by the flip
+ * @n_intfs: number of targeted interfaces
+ * @bufs: description of buffers displayed
+ * @n_bufs: number of buffers displayed
+ * @custom_data: driver-private data
+ * @custom_data_size: size of driver-private data
+ *
+ * adf_device_post() will copy @intfs, @bufs, and @custom_data, so they may
+ * point to variables on the stack.  adf_device_post() also takes its own
+ * reference on each of the dma-bufs in @bufs.  The adf_device_post_nocopy()
+ * variant transfers ownership of these resources to ADF instead.
+ *
+ * On success, returns a sync fence which signals when the buffers are removed
+ * from the screen.  On failure, returns ERR_PTR(-errno).
+ */
+struct sync_fence *adf_device_post(struct adf_device *dev,
+		struct adf_interface **intfs, size_t n_intfs,
+		struct adf_buffer *bufs, size_t n_bufs, void *custom_data,
+		size_t custom_data_size)
+{
+	struct adf_interface **intfs_copy = NULL;
+	struct adf_buffer *bufs_copy = NULL;
+	void *custom_data_copy = NULL;
+	struct sync_fence *ret;
+	size_t i;
+
+	intfs_copy = kzalloc(sizeof(intfs_copy[0]) * n_intfs, GFP_KERNEL);
+	if (!intfs_copy)
+		return ERR_PTR(-ENOMEM);
+
+	bufs_copy = kzalloc(sizeof(bufs_copy[0]) * n_bufs, GFP_KERNEL);
+	if (!bufs_copy) {
+		ret = ERR_PTR(-ENOMEM);
+		goto err_alloc;
+	}
+
+	custom_data_copy = kzalloc(custom_data_size, GFP_KERNEL);
+	if (!custom_data_copy) {
+		ret = ERR_PTR(-ENOMEM);
+		goto err_alloc;
+	}
+
+	for (i = 0; i < n_bufs; i++) {
+		size_t j;
+		for (j = 0; j < bufs[i].n_planes; j++)
+			get_dma_buf(bufs[i].dma_bufs[j]);
+	}
+
+	memcpy(intfs_copy, intfs, sizeof(intfs_copy[0]) * n_intfs);
+	memcpy(bufs_copy, bufs, sizeof(bufs_copy[0]) * n_bufs);
+	memcpy(custom_data_copy, custom_data, custom_data_size);
+
+	ret = adf_device_post_nocopy(dev, intfs_copy, n_intfs, bufs_copy,
+			n_bufs, custom_data_copy, custom_data_size);
+	if (IS_ERR(ret))
+		goto err_post;
+
+	return ret;
+
+err_post:
+	for (i = 0; i < n_bufs; i++) {
+		size_t j;
+		for (j = 0; j < bufs[i].n_planes; j++)
+			dma_buf_put(bufs[i].dma_bufs[j]);
+	}
+err_alloc:
+	kfree(custom_data_copy);
+	kfree(bufs_copy);
+	kfree(intfs_copy);
+	return ret;
+}
+EXPORT_SYMBOL(adf_device_post);
+
+/**
+ * adf_device_post_nocopy - flip to a new set of buffers
+ *
+ * adf_device_post_nocopy() has the same behavior as adf_device_post(),
+ * except ADF does not copy @intfs, @bufs, or @custom_data, and it does
+ * not take an extra reference on the dma-bufs in @bufs.
+ *
+ * @intfs, @bufs, and @custom_data must point to buffers allocated by
+ * kmalloc().  On success, ADF takes ownership of these buffers and the dma-bufs
+ * in @bufs, and will kfree()/dma_buf_put() them when they are no longer needed.
+ * On failure, adf_device_post_nocopy() does NOT take ownership of these
+ * buffers or the dma-bufs, and the caller must clean them up.
+ *
+ * adf_device_post_nocopy() is mainly intended for implementing ADF's ioctls.
+ * Clients may find the nocopy variant useful in limited cases, but most should
+ * call adf_device_post() instead.
+ */
+struct sync_fence *adf_device_post_nocopy(struct adf_device *dev,
+		struct adf_interface **intfs, size_t n_intfs,
+		struct adf_buffer *bufs, size_t n_bufs,
+		void *custom_data, size_t custom_data_size)
+{
+	struct adf_pending_post *cfg;
+	struct adf_buffer_mapping *mappings;
+	struct sync_fence *ret;
+	size_t i;
+	int err;
+
+	cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+	if (!cfg)
+		return ERR_PTR(-ENOMEM);
+
+	mappings = kzalloc(sizeof(mappings[0]) * n_bufs, GFP_KERNEL);
+	if (!mappings) {
+		ret = ERR_PTR(-ENOMEM);
+		goto err_alloc;
+	}
+
+	mutex_lock(&dev->client_lock);
+
+	for (i = 0; i < n_bufs; i++) {
+		err = adf_buffer_validate(&bufs[i]);
+		if (err < 0) {
+			ret = ERR_PTR(err);
+			goto err_buf;
+		}
+
+		err = adf_buffer_map(dev, &bufs[i], &mappings[i]);
+		if (err < 0) {
+			ret = ERR_PTR(err);
+			goto err_buf;
+		}
+	}
+
+	INIT_LIST_HEAD(&cfg->head);
+	cfg->config.n_bufs = n_bufs;
+	cfg->config.bufs = bufs;
+	cfg->config.mappings = mappings;
+	cfg->config.custom_data = custom_data;
+	cfg->config.custom_data_size = custom_data_size;
+
+	err = dev->ops->validate(dev, &cfg->config, &cfg->state);
+	if (err < 0) {
+		ret = ERR_PTR(err);
+		goto err_buf;
+	}
+
+	mutex_lock(&dev->post_lock);
+
+	if (dev->ops->complete_fence)
+		ret = dev->ops->complete_fence(dev, &cfg->config,
+				cfg->state);
+	else
+		ret = adf_sw_complete_fence(dev);
+
+	if (IS_ERR(ret))
+		goto err_fence;
+
+	list_add_tail(&cfg->head, &dev->post_list);
+	queue_kthread_work(&dev->post_worker, &dev->post_work);
+	mutex_unlock(&dev->post_lock);
+	mutex_unlock(&dev->client_lock);
+	kfree(intfs);
+	return ret;
+
+err_fence:
+	mutex_unlock(&dev->post_lock);
+
+err_buf:
+	for (i = 0; i < n_bufs; i++)
+		adf_buffer_mapping_cleanup(&mappings[i], &bufs[i]);
+
+	mutex_unlock(&dev->client_lock);
+	kfree(mappings);
+
+err_alloc:
+	kfree(cfg);
+	return ret;
+}
+EXPORT_SYMBOL(adf_device_post_nocopy);
+
+static void adf_attachment_list_to_array(struct adf_device *dev,
+		struct list_head *src, struct adf_attachment *dst, size_t size)
+{
+	struct adf_attachment_list *entry;
+	size_t i = 0;
+
+	if (!dst)
+		return;
+
+	list_for_each_entry(entry, src, head) {
+		if (i == size)
+			return;
+		dst[i] = entry->attachment;
+		i++;
+	}
+}
+
+/**
+ * adf_device_attachments - get device's list of active attachments
+ *
+ * @dev: the device
+ * @attachments: storage for the attachment list (optional)
+ * @n_attachments: length of @attachments
+ *
+ * If @attachments is not NULL, adf_device_attachments() will copy up to
+ * @n_attachments entries into @attachments.
+ *
+ * Returns the length of the active attachment list.
+ */
+size_t adf_device_attachments(struct adf_device *dev,
+		struct adf_attachment *attachments, size_t n_attachments)
+{
+	size_t retval;
+
+	mutex_lock(&dev->client_lock);
+	adf_attachment_list_to_array(dev, &dev->attached, attachments,
+			n_attachments);
+	retval = dev->n_attached;
+	mutex_unlock(&dev->client_lock);
+
+	return retval;
+}
+EXPORT_SYMBOL(adf_device_attachments);
+
+/**
+ * adf_device_attachments_allowed - get device's list of allowed attachments
+ *
+ * @dev: the device
+ * @attachments: storage for the attachment list (optional)
+ * @n_attachments: length of @attachments
+ *
+ * If @attachments is not NULL, adf_device_attachments_allowed() will copy up to
+ * @n_attachments entries into @attachments.
+ *
+ * Returns the length of the allowed attachment list.
+ */
+size_t adf_device_attachments_allowed(struct adf_device *dev,
+		struct adf_attachment *attachments, size_t n_attachments)
+{
+	size_t retval;
+
+	mutex_lock(&dev->client_lock);
+	adf_attachment_list_to_array(dev, &dev->attach_allowed, attachments,
+			n_attachments);
+	retval = dev->n_attach_allowed;
+	mutex_unlock(&dev->client_lock);
+
+	return retval;
+}
+EXPORT_SYMBOL(adf_device_attachments_allowed);
+
+/**
+ * adf_device_attached - return whether an overlay engine and interface are
+ * attached
+ *
+ * @dev: the parent device
+ * @eng: the overlay engine
+ * @intf: the interface
+ */
+bool adf_device_attached(struct adf_device *dev, struct adf_overlay_engine *eng,
+		struct adf_interface *intf)
+{
+	struct adf_attachment_list *attachment;
+
+	mutex_lock(&dev->client_lock);
+	attachment = adf_attachment_find(&dev->attached, eng, intf);
+	mutex_unlock(&dev->client_lock);
+
+	return attachment != NULL;
+}
+EXPORT_SYMBOL(adf_device_attached);
+
+/**
+ * adf_device_attach_allowed - return whether the ADF device supports attaching
+ * an overlay engine and interface
+ *
+ * @dev: the parent device
+ * @eng: the overlay engine
+ * @intf: the interface
+ */
+bool adf_device_attach_allowed(struct adf_device *dev,
+		struct adf_overlay_engine *eng, struct adf_interface *intf)
+{
+	struct adf_attachment_list *attachment;
+
+	mutex_lock(&dev->client_lock);
+	attachment = adf_attachment_find(&dev->attach_allowed, eng, intf);
+	mutex_unlock(&dev->client_lock);
+
+	return attachment != NULL;
+}
+EXPORT_SYMBOL(adf_device_attach_allowed);
+/**
+ * adf_device_attach - attach an overlay engine to an interface
+ *
+ * @dev: the parent device
+ * @eng: the overlay engine
+ * @intf: the interface
+ *
+ * Returns 0 on success, -%EINVAL if attaching @intf and @eng is not allowed,
+ * -%EALREADY if @intf and @eng are already attached, or -errno on any other
+ * failure.
+ */
+int adf_device_attach(struct adf_device *dev, struct adf_overlay_engine *eng,
+		struct adf_interface *intf)
+{
+	int ret;
+	struct adf_attachment_list *attachment = NULL;
+
+	ret = adf_attachment_validate(dev, eng, intf);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&dev->client_lock);
+
+	if (dev->n_attached == ADF_MAX_ATTACHMENTS) {
+		ret = -ENOMEM;
+		goto done;
+	}
+
+	if (!adf_attachment_find(&dev->attach_allowed, eng, intf)) {
+		ret = -EINVAL;
+		goto done;
+	}
+
+	if (adf_attachment_find(&dev->attached, eng, intf)) {
+		ret = -EALREADY;
+		goto done;
+	}
+
+	ret = adf_device_attach_op(dev, eng, intf);
+	if (ret < 0)
+		goto done;
+
+	attachment = kzalloc(sizeof(*attachment), GFP_KERNEL);
+	if (!attachment) {
+		ret = -ENOMEM;
+		goto done;
+	}
+
+	attachment->attachment.interface = intf;
+	attachment->attachment.overlay_engine = eng;
+	list_add_tail(&attachment->head, &dev->attached);
+	dev->n_attached++;
+
+done:
+	mutex_unlock(&dev->client_lock);
+	if (ret < 0)
+		kfree(attachment);
+
+	return ret;
+}
+EXPORT_SYMBOL(adf_device_attach);
+
+/**
+ * adf_device_detach - detach an overlay engine from an interface
+ *
+ * @dev: the parent device
+ * @eng: the overlay engine
+ * @intf: the interface
+ *
+ * Returns 0 on success, -%EINVAL if @intf and @eng are not attached,
+ * or -errno on any other failure.
+ */
+int adf_device_detach(struct adf_device *dev, struct adf_overlay_engine *eng,
+		struct adf_interface *intf)
+{
+	int ret;
+	struct adf_attachment_list *attachment;
+
+	ret = adf_attachment_validate(dev, eng, intf);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&dev->client_lock);
+
+	attachment = adf_attachment_find(&dev->attached, eng, intf);
+	if (!attachment) {
+		ret = -EINVAL;
+		goto done;
+	}
+
+	ret = adf_device_detach_op(dev, eng, intf);
+	if (ret < 0)
+		goto done;
+
+	adf_attachment_free(attachment);
+	dev->n_attached--;
+done:
+	mutex_unlock(&dev->client_lock);
+	return ret;
+}
+EXPORT_SYMBOL(adf_device_detach);
+
+/**
+ * adf_interface_simple_buffer_alloc - allocate a simple buffer
+ *
+ * @intf: target interface
+ * @w: width in pixels
+ * @h: height in pixels
+ * @format: format fourcc
+ * @dma_buf: returns the allocated buffer
+ * @offset: returns the byte offset of the allocated buffer's first pixel
+ * @pitch: returns the allocated buffer's pitch
+ *
+ * See &struct adf_simple_buffer_alloc for a description of simple buffers and
+ * their limitations.
+ *
+ * Returns 0 on success or -errno on failure.
+ */
+int adf_interface_simple_buffer_alloc(struct adf_interface *intf, u16 w, u16 h,
+		u32 format, struct dma_buf **dma_buf, u32 *offset, u32 *pitch)
+{
+	if (!intf->ops || !intf->ops->alloc_simple_buffer)
+		return -EOPNOTSUPP;
+
+	if (!adf_format_is_rgb(format))
+		return -EINVAL;
+
+	return intf->ops->alloc_simple_buffer(intf, w, h, format, dma_buf,
+			offset, pitch);
+}
+EXPORT_SYMBOL(adf_interface_simple_buffer_alloc);
+
+/**
+ * adf_interface_simple_post - flip to a single buffer
+ *
+ * @intf: interface targeted by the flip
+ * @buf: buffer to display
+ *
+ * adf_interface_simple_post() can be used generically for simple display
+ * configurations, since the client does not need to provide any driver-private
+ * configuration data.
+ *
+ * adf_interface_simple_post() has the same copying semantics as
+ * adf_device_post().
+ *
+ * On success, returns a sync fence which signals when the buffer is removed
+ * from the screen.  On failure, returns ERR_PTR(-errno).
+ */
+struct sync_fence *adf_interface_simple_post(struct adf_interface *intf,
+		struct adf_buffer *buf)
+{
+	size_t custom_data_size = 0;
+	void *custom_data = NULL;
+	struct sync_fence *ret;
+
+	if (intf->ops && intf->ops->describe_simple_post) {
+		int err;
+
+		custom_data = kzalloc(ADF_MAX_CUSTOM_DATA_SIZE, GFP_KERNEL);
+		if (!custom_data) {
+			ret = ERR_PTR(-ENOMEM);
+			goto done;
+		}
+
+		err = intf->ops->describe_simple_post(intf, buf, custom_data,
+				&custom_data_size);
+		if (err < 0) {
+			ret = ERR_PTR(err);
+			goto done;
+		}
+	}
+
+	ret = adf_device_post(adf_interface_parent(intf), &intf, 1, buf, 1,
+			custom_data, custom_data_size);
+done:
+	kfree(custom_data);
+	return ret;
+}
+EXPORT_SYMBOL(adf_interface_simple_post);
diff --git a/drivers/video/adf/adf_fbdev.c b/drivers/video/adf/adf_fbdev.c
new file mode 100644
index 00000000000..a5b53bc08c3
--- /dev/null
+++ b/drivers/video/adf/adf_fbdev.c
@@ -0,0 +1,665 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/vmalloc.h>
+
+#include <video/adf.h>
+#include <video/adf_client.h>
+#include <video/adf_fbdev.h>
+#include <video/adf_format.h>
+
+#include "adf.h"
+
+struct adf_fbdev_format {
+	u32 fourcc;
+	u32 bpp;
+	u32 r_length;
+	u32 g_length;
+	u32 b_length;
+	u32 a_length;
+	u32 r_offset;
+	u32 g_offset;
+	u32 b_offset;
+	u32 a_offset;
+};
+
+static const struct adf_fbdev_format format_table[] = {
+	{DRM_FORMAT_RGB332, 8, 3, 3, 2, 0, 5, 2, 0, 0},
+	{DRM_FORMAT_BGR233, 8, 3, 3, 2, 0, 0, 3, 5, 0},
+
+	{DRM_FORMAT_XRGB4444, 16, 4, 4, 4, 0, 8, 4, 0, 0},
+	{DRM_FORMAT_XBGR4444, 16, 4, 4, 4, 0, 0, 4, 8, 0},
+	{DRM_FORMAT_RGBX4444, 16, 4, 4, 4, 0, 12, 8, 4, 0},
+	{DRM_FORMAT_BGRX4444, 16, 4, 4, 4, 0, 0, 4, 8, 0},
+
+	{DRM_FORMAT_ARGB4444, 16, 4, 4, 4, 4, 8, 4, 0, 12},
+	{DRM_FORMAT_ABGR4444, 16, 4, 4, 4, 4, 0, 4, 8, 12},
+	{DRM_FORMAT_RGBA4444, 16, 4, 4, 4, 4, 12, 8, 4, 0},
+	{DRM_FORMAT_BGRA4444, 16, 4, 4, 4, 4, 0, 4, 8, 0},
+
+	{DRM_FORMAT_XRGB1555, 16, 5, 5, 5, 0, 10, 5, 0, 0},
+	{DRM_FORMAT_XBGR1555, 16, 5, 5, 5, 0, 0, 5, 10, 0},
+	{DRM_FORMAT_RGBX5551, 16, 5, 5, 5, 0, 11, 6, 1, 0},
+	{DRM_FORMAT_BGRX5551, 16, 5, 5, 5, 0, 1, 6, 11, 0},
+
+	{DRM_FORMAT_ARGB1555, 16, 5, 5, 5, 1, 10, 5, 0, 15},
+	{DRM_FORMAT_ABGR1555, 16, 5, 5, 5, 1, 0, 5, 10, 15},
+	{DRM_FORMAT_RGBA5551, 16, 5, 5, 5, 1, 11, 6, 1, 0},
+	{DRM_FORMAT_BGRA5551, 16, 5, 5, 5, 1, 1, 6, 11, 0},
+
+	{DRM_FORMAT_RGB565, 16, 5, 6, 5, 0, 11, 5, 0, 0},
+	{DRM_FORMAT_BGR565, 16, 5, 6, 5, 0, 0, 5, 11, 0},
+
+	{DRM_FORMAT_RGB888, 24, 8, 8, 8, 0, 16, 8, 0, 0},
+	{DRM_FORMAT_BGR888, 24, 8, 8, 8, 0, 0, 8, 16, 0},
+
+	{DRM_FORMAT_XRGB8888, 32, 8, 8, 8, 0, 16, 8, 0, 0},
+	{DRM_FORMAT_XBGR8888, 32, 8, 8, 8, 0, 0, 8, 16, 0},
+	{DRM_FORMAT_RGBX8888, 32, 8, 8, 8, 0, 24, 16, 8, 0},
+	{DRM_FORMAT_BGRX8888, 32, 8, 8, 8, 0, 8, 16, 24, 0},
+
+	{DRM_FORMAT_ARGB8888, 32, 8, 8, 8, 8, 16, 8, 0, 24},
+	{DRM_FORMAT_ABGR8888, 32, 8, 8, 8, 8, 0, 8, 16, 24},
+	{DRM_FORMAT_RGBA8888, 32, 8, 8, 8, 8, 24, 16, 8, 0},
+	{DRM_FORMAT_BGRA8888, 32, 8, 8, 8, 8, 8, 16, 24, 0},
+
+	{DRM_FORMAT_XRGB2101010, 32, 10, 10, 10, 0, 20, 10, 0, 0},
+	{DRM_FORMAT_XBGR2101010, 32, 10, 10, 10, 0, 0, 10, 20, 0},
+	{DRM_FORMAT_RGBX1010102, 32, 10, 10, 10, 0, 22, 12, 2, 0},
+	{DRM_FORMAT_BGRX1010102, 32, 10, 10, 10, 0, 2, 12, 22, 0},
+
+	{DRM_FORMAT_ARGB2101010, 32, 10, 10, 10, 2, 20, 10, 0, 30},
+	{DRM_FORMAT_ABGR2101010, 32, 10, 10, 10, 2, 0, 10, 20, 30},
+	{DRM_FORMAT_RGBA1010102, 32, 10, 10, 10, 2, 22, 12, 2, 0},
+	{DRM_FORMAT_BGRA1010102, 32, 10, 10, 10, 2, 2, 12, 22, 0},
+};
+
+static u32 drm_fourcc_from_fb_var(struct fb_var_screeninfo *var)
+{
+	size_t i;
+	for (i = 0; i < ARRAY_SIZE(format_table); i++) {
+		const struct adf_fbdev_format *f = &format_table[i];
+		if (var->red.length == f->r_length &&
+			var->red.offset == f->r_offset &&
+			var->green.length == f->g_length &&
+			var->green.offset == f->g_offset &&
+			var->blue.length == f->b_length &&
+			var->blue.offset == f->b_offset &&
+			var->transp.length == f->a_length &&
+			(var->transp.length == 0 ||
+					var->transp.offset == f->a_offset))
+			return f->fourcc;
+	}
+
+	return 0;
+}
+
+static const struct adf_fbdev_format *fbdev_format_info(u32 format)
+{
+	size_t i;
+	for (i = 0; i < ARRAY_SIZE(format_table); i++) {
+		const struct adf_fbdev_format *f = &format_table[i];
+		if (f->fourcc == format)
+			return f;
+	}
+
+	BUG();
+}
+
+void adf_modeinfo_to_fb_videomode(const struct drm_mode_modeinfo *mode,
+		struct fb_videomode *vmode)
+{
+	memset(vmode, 0, sizeof(*vmode));
+
+	vmode->refresh = mode->vrefresh;
+
+	vmode->xres = mode->hdisplay;
+	vmode->yres = mode->vdisplay;
+
+	vmode->pixclock = mode->clock ? KHZ2PICOS(mode->clock) : 0;
+	vmode->left_margin = mode->htotal - mode->hsync_end;
+	vmode->right_margin = mode->hsync_start - mode->hdisplay;
+	vmode->upper_margin = mode->vtotal - mode->vsync_end;
+	vmode->lower_margin = mode->vsync_start - mode->vdisplay;
+	vmode->hsync_len = mode->hsync_end - mode->hsync_start;
+	vmode->vsync_len = mode->vsync_end - mode->vsync_start;
+
+	vmode->sync = 0;
+	if (mode->flags & DRM_MODE_FLAG_PHSYNC)
+		vmode->sync |= FB_SYNC_HOR_HIGH_ACT;
+	if (mode->flags & DRM_MODE_FLAG_PVSYNC)
+		vmode->sync |= FB_SYNC_VERT_HIGH_ACT;
+	if (mode->flags & DRM_MODE_FLAG_PCSYNC)
+		vmode->sync |= FB_SYNC_COMP_HIGH_ACT;
+	if (mode->flags & DRM_MODE_FLAG_BCAST)
+		vmode->sync |= FB_SYNC_BROADCAST;
+
+	vmode->vmode = 0;
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+		vmode->vmode |= FB_VMODE_INTERLACED;
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		vmode->vmode |= FB_VMODE_DOUBLE;
+}
+EXPORT_SYMBOL(adf_modeinfo_to_fb_videomode);
+
+void adf_modeinfo_from_fb_videomode(const struct fb_videomode *vmode,
+		struct drm_mode_modeinfo *mode)
+{
+	memset(mode, 0, sizeof(*mode));
+
+	mode->hdisplay = vmode->xres;
+	mode->hsync_start = mode->hdisplay + vmode->right_margin;
+	mode->hsync_end = mode->hsync_start + vmode->hsync_len;
+	mode->htotal = mode->hsync_end + vmode->left_margin;
+
+	mode->vdisplay = vmode->yres;
+	mode->vsync_start = mode->vdisplay + vmode->lower_margin;
+	mode->vsync_end = mode->vsync_start + vmode->vsync_len;
+	mode->vtotal = mode->vsync_end + vmode->upper_margin;
+
+	mode->clock = vmode->pixclock ? PICOS2KHZ(vmode->pixclock) : 0;
+
+	mode->flags = 0;
+	if (vmode->sync & FB_SYNC_HOR_HIGH_ACT)
+		mode->flags |= DRM_MODE_FLAG_PHSYNC;
+	if (vmode->sync & FB_SYNC_VERT_HIGH_ACT)
+		mode->flags |= DRM_MODE_FLAG_PVSYNC;
+	if (vmode->sync & FB_SYNC_COMP_HIGH_ACT)
+		mode->flags |= DRM_MODE_FLAG_PCSYNC;
+	if (vmode->sync & FB_SYNC_BROADCAST)
+		mode->flags |= DRM_MODE_FLAG_BCAST;
+	if (vmode->vmode & FB_VMODE_INTERLACED)
+		mode->flags |= DRM_MODE_FLAG_INTERLACE;
+	if (vmode->vmode & FB_VMODE_DOUBLE)
+		mode->flags |= DRM_MODE_FLAG_DBLSCAN;
+
+	if (vmode->refresh)
+		mode->vrefresh = vmode->refresh;
+	else
+		adf_modeinfo_set_vrefresh(mode);
+
+	if (vmode->name)
+		strlcpy(mode->name, vmode->name, sizeof(mode->name));
+	else
+		adf_modeinfo_set_name(mode);
+}
+EXPORT_SYMBOL(adf_modeinfo_from_fb_videomode);
+
+static int adf_fbdev_post(struct adf_fbdev *fbdev)
+{
+	struct adf_buffer buf;
+	struct sync_fence *complete_fence;
+	int ret = 0;
+
+	memset(&buf, 0, sizeof(buf));
+	buf.overlay_engine = fbdev->eng;
+	buf.w = fbdev->info->var.xres;
+	buf.h = fbdev->info->var.yres;
+	buf.format = fbdev->format;
+	buf.dma_bufs[0] = fbdev->dma_buf;
+	buf.offset[0] = fbdev->offset +
+			fbdev->info->var.yoffset * fbdev->pitch +
+			fbdev->info->var.xoffset *
+			(fbdev->info->var.bits_per_pixel / 8);
+	buf.pitch[0] = fbdev->pitch;
+	buf.n_planes = 1;
+
+	complete_fence = adf_interface_simple_post(fbdev->intf, &buf);
+	if (IS_ERR(complete_fence)) {
+		ret = PTR_ERR(complete_fence);
+		goto done;
+	}
+
+	sync_fence_put(complete_fence);
+done:
+	return ret;
+}
+
+static const u16 vga_palette[][3] = {
+	{0x0000, 0x0000, 0x0000},
+	{0x0000, 0x0000, 0xAAAA},
+	{0x0000, 0xAAAA, 0x0000},
+	{0x0000, 0xAAAA, 0xAAAA},
+	{0xAAAA, 0x0000, 0x0000},
+	{0xAAAA, 0x0000, 0xAAAA},
+	{0xAAAA, 0x5555, 0x0000},
+	{0xAAAA, 0xAAAA, 0xAAAA},
+	{0x5555, 0x5555, 0x5555},
+	{0x5555, 0x5555, 0xFFFF},
+	{0x5555, 0xFFFF, 0x5555},
+	{0x5555, 0xFFFF, 0xFFFF},
+	{0xFFFF, 0x5555, 0x5555},
+	{0xFFFF, 0x5555, 0xFFFF},
+	{0xFFFF, 0xFFFF, 0x5555},
+	{0xFFFF, 0xFFFF, 0xFFFF},
+};
+
+static int adf_fb_alloc(struct adf_fbdev *fbdev)
+{
+	int ret;
+
+	ret = adf_interface_simple_buffer_alloc(fbdev->intf,
+			fbdev->default_xres_virtual,
+			fbdev->default_yres_virtual,
+			fbdev->default_format,
+			&fbdev->dma_buf, &fbdev->offset, &fbdev->pitch);
+	if (ret < 0) {
+		dev_err(fbdev->info->dev, "allocating fb failed: %d\n", ret);
+		return ret;
+	}
+
+	fbdev->vaddr = dma_buf_vmap(fbdev->dma_buf);
+	if (!fbdev->vaddr) {
+		ret = -ENOMEM;
+		dev_err(fbdev->info->dev, "vmapping fb failed\n");
+		goto err_vmap;
+	}
+	fbdev->info->fix.line_length = fbdev->pitch;
+	fbdev->info->var.xres_virtual = fbdev->default_xres_virtual;
+	fbdev->info->var.yres_virtual = fbdev->default_yres_virtual;
+	fbdev->info->fix.smem_len = fbdev->dma_buf->size;
+	fbdev->info->screen_base = fbdev->vaddr;
+
+	return 0;
+
+err_vmap:
+	dma_buf_put(fbdev->dma_buf);
+	return ret;
+}
+
+static void adf_fb_destroy(struct adf_fbdev *fbdev)
+{
+	dma_buf_vunmap(fbdev->dma_buf, fbdev->vaddr);
+	dma_buf_put(fbdev->dma_buf);
+}
+
+static void adf_fbdev_set_format(struct adf_fbdev *fbdev, u32 format)
+{
+	size_t i;
+	const struct adf_fbdev_format *info = fbdev_format_info(format);
+	for (i = 0; i < ARRAY_SIZE(vga_palette); i++) {
+		u16 r = vga_palette[i][0];
+		u16 g = vga_palette[i][1];
+		u16 b = vga_palette[i][2];
+
+		r >>= (16 - info->r_length);
+		g >>= (16 - info->g_length);
+		b >>= (16 - info->b_length);
+
+		fbdev->pseudo_palette[i] =
+			(r << info->r_offset) |
+			(g << info->g_offset) |
+			(b << info->b_offset);
+
+		if (info->a_length) {
+			u16 a = BIT(info->a_length) - 1;
+			fbdev->pseudo_palette[i] |= (a << info->a_offset);
+		}
+	}
+
+	fbdev->info->var.bits_per_pixel = adf_format_bpp(format);
+	fbdev->info->var.red.length = info->r_length;
+	fbdev->info->var.red.offset = info->r_offset;
+	fbdev->info->var.green.length = info->g_length;
+	fbdev->info->var.green.offset = info->g_offset;
+	fbdev->info->var.blue.length = info->b_length;
+	fbdev->info->var.blue.offset = info->b_offset;
+	fbdev->info->var.transp.length = info->a_length;
+	fbdev->info->var.transp.offset = info->a_offset;
+	fbdev->format = format;
+}
+
+static void adf_fbdev_fill_modelist(struct adf_fbdev *fbdev)
+{
+	struct drm_mode_modeinfo *modelist;
+	struct fb_videomode fbmode;
+	size_t n_modes, i;
+	int ret = 0;
+
+	n_modes = adf_interface_modelist(fbdev->intf, NULL, 0);
+	modelist = kzalloc(sizeof(modelist[0]) * n_modes, GFP_KERNEL);
+	if (!modelist) {
+		dev_warn(fbdev->info->dev, "allocating new modelist failed; keeping old modelist\n");
+		return;
+	}
+	adf_interface_modelist(fbdev->intf, modelist, n_modes);
+
+	fb_destroy_modelist(&fbdev->info->modelist);
+
+	for (i = 0; i < n_modes; i++) {
+		adf_modeinfo_to_fb_videomode(&modelist[i], &fbmode);
+		ret = fb_add_videomode(&fbmode, &fbdev->info->modelist);
+		if (ret < 0)
+			dev_warn(fbdev->info->dev, "adding mode %s to modelist failed: %d\n",
+					modelist[i].name, ret);
+	}
+
+	kfree(modelist);
+}
+
+/**
+ * adf_fbdev_open - default implementation of fbdev open op
+ */
+int adf_fbdev_open(struct fb_info *info, int user)
+{
+	struct adf_fbdev *fbdev = info->par;
+	int ret;
+
+	mutex_lock(&fbdev->refcount_lock);
+
+	if (unlikely(fbdev->refcount == UINT_MAX)) {
+		ret = -EMFILE;
+		goto done;
+	}
+
+	if (!fbdev->refcount) {
+		struct drm_mode_modeinfo mode;
+		struct fb_videomode fbmode;
+		struct adf_device *dev = adf_interface_parent(fbdev->intf);
+
+		ret = adf_device_attach(dev, fbdev->eng, fbdev->intf);
+		if (ret < 0 && ret != -EALREADY)
+			goto done;
+
+		ret = adf_fb_alloc(fbdev);
+		if (ret < 0)
+			goto done;
+
+		adf_interface_current_mode(fbdev->intf, &mode);
+		adf_modeinfo_to_fb_videomode(&mode, &fbmode);
+		fb_videomode_to_var(&fbdev->info->var, &fbmode);
+
+		adf_fbdev_set_format(fbdev, fbdev->default_format);
+		adf_fbdev_fill_modelist(fbdev);
+	}
+
+	ret = adf_fbdev_post(fbdev);
+	if (ret < 0) {
+		if (!fbdev->refcount)
+			adf_fb_destroy(fbdev);
+		goto done;
+	}
+
+	fbdev->refcount++;
+done:
+	mutex_unlock(&fbdev->refcount_lock);
+	return ret;
+}
+EXPORT_SYMBOL(adf_fbdev_open);
+
+/**
+ * adf_fbdev_release - default implementation of fbdev release op
+ */
+int adf_fbdev_release(struct fb_info *info, int user)
+{
+	struct adf_fbdev *fbdev = info->par;
+	mutex_lock(&fbdev->refcount_lock);
+	BUG_ON(!fbdev->refcount);
+	fbdev->refcount--;
+	if (!fbdev->refcount)
+		adf_fb_destroy(fbdev);
+	mutex_unlock(&fbdev->refcount_lock);
+	return 0;
+}
+EXPORT_SYMBOL(adf_fbdev_release);
+
+/**
+ * adf_fbdev_check_var - default implementation of fbdev check_var op
+ */
+int adf_fbdev_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
+{
+	struct adf_fbdev *fbdev = info->par;
+	bool valid_format = true;
+	u32 format = drm_fourcc_from_fb_var(var);
+	u32 pitch = var->xres_virtual * var->bits_per_pixel / 8;
+
+	if (!format) {
+		dev_dbg(info->dev, "%s: unrecognized format\n", __func__);
+		valid_format = false;
+	}
+
+	if (valid_format && var->grayscale) {
+		dev_dbg(info->dev, "%s: grayscale modes not supported\n",
+				__func__);
+		valid_format = false;
+	}
+
+	if (valid_format && var->nonstd) {
+		dev_dbg(info->dev, "%s: nonstandard formats not supported\n",
+				__func__);
+		valid_format = false;
+	}
+
+	if (valid_format && !adf_overlay_engine_supports_format(fbdev->eng,
+			format)) {
+		char format_str[ADF_FORMAT_STR_SIZE];
+		adf_format_str(format, format_str);
+		dev_dbg(info->dev, "%s: format %s not supported by overlay engine %s\n",
+				__func__, format_str, fbdev->eng->base.name);
+		valid_format = false;
+	}
+
+	if (valid_format && pitch > fbdev->pitch) {
+		dev_dbg(info->dev, "%s: fb pitch too small for var (pitch = %u, xres_virtual = %u, bits_per_pixel = %u)\n",
+				__func__, fbdev->pitch, var->xres_virtual,
+				var->bits_per_pixel);
+		valid_format = false;
+	}
+
+	if (valid_format && var->yres_virtual > fbdev->default_yres_virtual) {
+		dev_dbg(info->dev, "%s: fb height too small for var (h = %u, yres_virtual = %u)\n",
+				__func__, fbdev->default_yres_virtual,
+				var->yres_virtual);
+		valid_format = false;
+	}
+
+	if (valid_format) {
+		var->activate = info->var.activate;
+		var->height = info->var.height;
+		var->width = info->var.width;
+		var->accel_flags = info->var.accel_flags;
+		var->rotate = info->var.rotate;
+		var->colorspace = info->var.colorspace;
+		/* userspace can't change these */
+	} else {
+		/* if any part of the format is invalid then fixing it up is
+		   impractical, so save just the modesetting bits and
+		   overwrite everything else */
+		struct fb_videomode mode;
+		fb_var_to_videomode(&mode, var);
+		memcpy(var, &info->var, sizeof(*var));
+		fb_videomode_to_var(var, &mode);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(adf_fbdev_check_var);
+
+/**
+ * adf_fbdev_set_par - default implementation of fbdev set_par op
+ */
+int adf_fbdev_set_par(struct fb_info *info)
+{
+	struct adf_fbdev *fbdev = info->par;
+	struct adf_interface *intf = fbdev->intf;
+	struct fb_videomode vmode;
+	struct drm_mode_modeinfo mode;
+	int ret;
+	u32 format = drm_fourcc_from_fb_var(&info->var);
+
+	fb_var_to_videomode(&vmode, &info->var);
+	adf_modeinfo_from_fb_videomode(&vmode, &mode);
+	ret = adf_interface_set_mode(intf, &mode);
+	if (ret < 0)
+		return ret;
+
+	ret = adf_fbdev_post(fbdev);
+	if (ret < 0)
+		return ret;
+
+	if (format != fbdev->format)
+		adf_fbdev_set_format(fbdev, format);
+
+	return 0;
+}
+EXPORT_SYMBOL(adf_fbdev_set_par);
+
+/**
+ * adf_fbdev_blank - default implementation of fbdev blank op
+ */
+int adf_fbdev_blank(int blank, struct fb_info *info)
+{
+	struct adf_fbdev *fbdev = info->par;
+	struct adf_interface *intf = fbdev->intf;
+	u8 dpms_state;
+
+	switch (blank) {
+	case FB_BLANK_UNBLANK:
+		dpms_state = DRM_MODE_DPMS_ON;
+		break;
+	case FB_BLANK_NORMAL:
+		dpms_state = DRM_MODE_DPMS_STANDBY;
+		break;
+	case FB_BLANK_VSYNC_SUSPEND:
+		dpms_state = DRM_MODE_DPMS_SUSPEND;
+		break;
+	case FB_BLANK_HSYNC_SUSPEND:
+		dpms_state = DRM_MODE_DPMS_STANDBY;
+		break;
+	case FB_BLANK_POWERDOWN:
+		dpms_state = DRM_MODE_DPMS_OFF;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return adf_interface_blank(intf, dpms_state);
+}
+EXPORT_SYMBOL(adf_fbdev_blank);
+
+/**
+ * adf_fbdev_pan_display - default implementation of fbdev pan_display op
+ */
+int adf_fbdev_pan_display(struct fb_var_screeninfo *var, struct fb_info *info)
+{
+	struct adf_fbdev *fbdev = info->par;
+	return adf_fbdev_post(fbdev);
+}
+EXPORT_SYMBOL(adf_fbdev_pan_display);
+
+/**
+ * adf_fbdev_mmap - default implementation of fbdev mmap op
+ */
+int adf_fbdev_mmap(struct fb_info *info, struct vm_area_struct *vma)
+{
+	struct adf_fbdev *fbdev = info->par;
+
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	return dma_buf_mmap(fbdev->dma_buf, vma, 0);
+}
+EXPORT_SYMBOL(adf_fbdev_mmap);
+
+/**
+ * adf_fbdev_init - initialize helper to wrap ADF device in fbdev API
+ *
+ * @fbdev: the fbdev helper
+ * @interface: the ADF interface that will display the framebuffer
+ * @eng: the ADF overlay engine that will scan out the framebuffer
+ * @xres_virtual: the virtual width of the framebuffer
+ * @yres_virtual: the virtual height of the framebuffer
+ * @format: the format of the framebuffer
+ * @fbops: the device's fbdev ops
+ * @fmt: formatting for the framebuffer identification string
+ * @...: variable arguments
+ *
+ * @format must be a standard, non-indexed RGB format, i.e.,
+ * adf_format_is_rgb(@format) && @format != @DRM_FORMAT_C8.
+ *
+ * Returns 0 on success or -errno on failure.
+ */
+int adf_fbdev_init(struct adf_fbdev *fbdev, struct adf_interface *interface,
+		struct adf_overlay_engine *eng,
+		u16 xres_virtual, u16 yres_virtual, u32 format,
+		struct fb_ops *fbops, const char *fmt, ...)
+{
+	struct adf_device *parent = adf_interface_parent(interface);
+	struct device *dev = &parent->base.dev;
+	u16 width_mm, height_mm;
+	va_list args;
+	int ret;
+
+	if (!adf_format_is_rgb(format) ||
+			format == DRM_FORMAT_C8) {
+		dev_err(dev, "fbdev helper does not support format %u\n",
+				format);
+		return -EINVAL;
+	}
+
+	memset(fbdev, 0, sizeof(*fbdev));
+	fbdev->intf = interface;
+	fbdev->eng = eng;
+	fbdev->info = framebuffer_alloc(0, dev);
+	if (!fbdev->info) {
+		dev_err(dev, "allocating framebuffer device failed\n");
+		return -ENOMEM;
+	}
+	mutex_init(&fbdev->refcount_lock);
+	fbdev->default_xres_virtual = xres_virtual;
+	fbdev->default_yres_virtual = yres_virtual;
+	fbdev->default_format = format;
+
+	fbdev->info->flags = FBINFO_FLAG_DEFAULT;
+	ret = adf_interface_get_screen_size(interface, &width_mm, &height_mm);
+	if (ret < 0) {
+		width_mm = 0;
+		height_mm = 0;
+	}
+	fbdev->info->var.width = width_mm;
+	fbdev->info->var.height = height_mm;
+	fbdev->info->var.activate = FB_ACTIVATE_VBL;
+	va_start(args, fmt);
+	vsnprintf(fbdev->info->fix.id, sizeof(fbdev->info->fix.id), fmt, args);
+	va_end(args);
+	fbdev->info->fix.type = FB_TYPE_PACKED_PIXELS;
+	fbdev->info->fix.visual = FB_VISUAL_TRUECOLOR;
+	fbdev->info->fix.xpanstep = 1;
+	fbdev->info->fix.ypanstep = 1;
+	INIT_LIST_HEAD(&fbdev->info->modelist);
+	fbdev->info->fbops = fbops;
+	fbdev->info->pseudo_palette = fbdev->pseudo_palette;
+	fbdev->info->par = fbdev;
+
+	ret = register_framebuffer(fbdev->info);
+	if (ret < 0) {
+		dev_err(dev, "registering framebuffer failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(adf_fbdev_init);
+
+/**
+ * adf_fbdev_destroy - destroy helper to wrap ADF device in fbdev API
+ *
+ * @fbdev: the fbdev helper
+ */
+void adf_fbdev_destroy(struct adf_fbdev *fbdev)
+{
+	unregister_framebuffer(fbdev->info);
+	BUG_ON(fbdev->refcount);
+	mutex_destroy(&fbdev->refcount_lock);
+	framebuffer_release(fbdev->info);
+}
+EXPORT_SYMBOL(adf_fbdev_destroy);
diff --git a/drivers/video/adf/adf_fops.c b/drivers/video/adf/adf_fops.c
new file mode 100644
index 00000000000..7fbf33e1cb3
--- /dev/null
+++ b/drivers/video/adf/adf_fops.c
@@ -0,0 +1,957 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/bitops.h>
+#include <linux/circ_buf.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/poll.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+#include <video/adf_client.h>
+#include <video/adf_format.h>
+
+#include "sw_sync.h"
+#include "sync.h"
+
+#include "adf.h"
+#include "adf_fops.h"
+#include "adf_sysfs.h"
+
+#ifdef CONFIG_COMPAT
+#include "adf_fops32.h"
+#endif
+
+static int adf_obj_set_event(struct adf_obj *obj, struct adf_file *file,
+		struct adf_set_event __user *arg)
+{
+	struct adf_set_event data;
+	bool enabled;
+	unsigned long flags;
+	int err;
+
+	if (copy_from_user(&data, arg, sizeof(data)))
+		return -EFAULT;
+
+	err = adf_obj_check_supports_event(obj, data.type);
+	if (err < 0)
+		return err;
+
+	spin_lock_irqsave(&obj->file_lock, flags);
+	if (data.enabled)
+		enabled = test_and_set_bit(data.type,
+				file->event_subscriptions);
+	else
+		enabled = test_and_clear_bit(data.type,
+				file->event_subscriptions);
+	spin_unlock_irqrestore(&obj->file_lock, flags);
+
+	if (data.enabled == enabled)
+		return -EALREADY;
+
+	if (data.enabled)
+		adf_event_get(obj, data.type);
+	else
+		adf_event_put(obj, data.type);
+
+	return 0;
+}
+
+static int adf_obj_copy_custom_data_to_user(struct adf_obj *obj,
+		void __user *dst, size_t *dst_size)
+{
+	void *custom_data;
+	size_t custom_data_size;
+	int ret;
+
+	if (!obj->ops || !obj->ops->custom_data) {
+		dev_dbg(&obj->dev, "%s: no custom_data op\n", __func__);
+		return 0;
+	}
+
+	custom_data = kzalloc(ADF_MAX_CUSTOM_DATA_SIZE, GFP_KERNEL);
+	if (!custom_data)
+		return -ENOMEM;
+
+	ret = obj->ops->custom_data(obj, custom_data, &custom_data_size);
+	if (ret < 0)
+		goto done;
+
+	if (copy_to_user(dst, custom_data, min(*dst_size, custom_data_size))) {
+		ret = -EFAULT;
+		goto done;
+	}
+	*dst_size = custom_data_size;
+
+done:
+	kfree(custom_data);
+	return ret;
+}
+
+static int adf_eng_get_data(struct adf_overlay_engine *eng,
+		struct adf_overlay_engine_data __user *arg)
+{
+	struct adf_device *dev = adf_overlay_engine_parent(eng);
+	struct adf_overlay_engine_data data;
+	size_t n_supported_formats;
+	u32 *supported_formats = NULL;
+	int ret = 0;
+
+	if (copy_from_user(&data, arg, sizeof(data)))
+		return -EFAULT;
+
+	strlcpy(data.name, eng->base.name, sizeof(data.name));
+
+	if (data.n_supported_formats > ADF_MAX_SUPPORTED_FORMATS)
+		return -EINVAL;
+
+	n_supported_formats = data.n_supported_formats;
+	data.n_supported_formats = eng->ops->n_supported_formats;
+
+	if (n_supported_formats) {
+		supported_formats = kzalloc(n_supported_formats *
+				sizeof(supported_formats[0]), GFP_KERNEL);
+		if (!supported_formats)
+			return -ENOMEM;
+	}
+
+	memcpy(supported_formats, eng->ops->supported_formats,
+			sizeof(u32) * min(n_supported_formats,
+					eng->ops->n_supported_formats));
+
+	mutex_lock(&dev->client_lock);
+	ret = adf_obj_copy_custom_data_to_user(&eng->base, arg->custom_data,
+			&data.custom_data_size);
+	mutex_unlock(&dev->client_lock);
+
+	if (ret < 0)
+		goto done;
+
+	if (copy_to_user(arg, &data, sizeof(data))) {
+		ret = -EFAULT;
+		goto done;
+	}
+
+	if (supported_formats && copy_to_user(arg->supported_formats,
+			supported_formats,
+			n_supported_formats * sizeof(supported_formats[0])))
+		ret = -EFAULT;
+
+done:
+	kfree(supported_formats);
+	return ret;
+}
+
+static int adf_buffer_import(struct adf_device *dev,
+		struct adf_buffer_config __user *cfg, struct adf_buffer *buf)
+{
+	struct adf_buffer_config user_buf;
+	size_t i;
+	int ret = 0;
+
+	if (copy_from_user(&user_buf, cfg, sizeof(user_buf)))
+		return -EFAULT;
+
+	memset(buf, 0, sizeof(*buf));
+
+	if (user_buf.n_planes > ADF_MAX_PLANES) {
+		dev_err(&dev->base.dev, "invalid plane count %u\n",
+				user_buf.n_planes);
+		return -EINVAL;
+	}
+
+	buf->overlay_engine = idr_find(&dev->overlay_engines,
+			user_buf.overlay_engine);
+	if (!buf->overlay_engine) {
+		dev_err(&dev->base.dev, "invalid overlay engine id %u\n",
+				user_buf.overlay_engine);
+		return -ENOENT;
+	}
+
+	buf->w = user_buf.w;
+	buf->h = user_buf.h;
+	buf->format = user_buf.format;
+	for (i = 0; i < user_buf.n_planes; i++) {
+		buf->dma_bufs[i] = dma_buf_get(user_buf.fd[i]);
+		if (IS_ERR(buf->dma_bufs[i])) {
+			ret = PTR_ERR(buf->dma_bufs[i]);
+			dev_err(&dev->base.dev, "importing dma_buf fd %d failed: %d\n",
+					user_buf.fd[i], ret);
+			buf->dma_bufs[i] = NULL;
+			goto done;
+		}
+		buf->offset[i] = user_buf.offset[i];
+		buf->pitch[i] = user_buf.pitch[i];
+	}
+	buf->n_planes = user_buf.n_planes;
+
+	if (user_buf.acquire_fence >= 0) {
+		buf->acquire_fence = sync_fence_fdget(user_buf.acquire_fence);
+		if (!buf->acquire_fence) {
+			dev_err(&dev->base.dev, "getting fence fd %d failed\n",
+					user_buf.acquire_fence);
+			ret = -EINVAL;
+			goto done;
+		}
+	}
+
+done:
+	if (ret < 0)
+		adf_buffer_cleanup(buf);
+	return ret;
+}
+
+static int adf_device_post_config(struct adf_device *dev,
+		struct adf_post_config __user *arg)
+{
+	struct sync_fence *complete_fence;
+	int complete_fence_fd;
+	struct adf_buffer *bufs = NULL;
+	struct adf_interface **intfs = NULL;
+	size_t n_intfs, n_bufs, i;
+	void *custom_data = NULL;
+	size_t custom_data_size;
+	int ret = 0;
+
+	complete_fence_fd = get_unused_fd();
+	if (complete_fence_fd < 0)
+		return complete_fence_fd;
+
+	if (get_user(n_intfs, &arg->n_interfaces)) {
+		ret = -EFAULT;
+		goto err_get_user;
+	}
+
+	if (n_intfs > ADF_MAX_INTERFACES) {
+		ret = -EINVAL;
+		goto err_get_user;
+	}
+
+	if (get_user(n_bufs, &arg->n_bufs)) {
+		ret = -EFAULT;
+		goto err_get_user;
+	}
+
+	if (n_bufs > ADF_MAX_BUFFERS) {
+		ret = -EINVAL;
+		goto err_get_user;
+	}
+
+	if (get_user(custom_data_size, &arg->custom_data_size)) {
+		ret = -EFAULT;
+		goto err_get_user;
+	}
+
+	if (custom_data_size > ADF_MAX_CUSTOM_DATA_SIZE) {
+		ret = -EINVAL;
+		goto err_get_user;
+	}
+
+	if (n_intfs) {
+		intfs = kmalloc(sizeof(intfs[0]) * n_intfs, GFP_KERNEL);
+		if (!intfs) {
+			ret = -ENOMEM;
+			goto err_get_user;
+		}
+	}
+
+	for (i = 0; i < n_intfs; i++) {
+		u32 intf_id;
+		if (get_user(intf_id, &arg->interfaces[i])) {
+			ret = -EFAULT;
+			goto err_get_user;
+		}
+
+		intfs[i] = idr_find(&dev->interfaces, intf_id);
+		if (!intfs[i]) {
+			ret = -EINVAL;
+			goto err_get_user;
+		}
+	}
+
+	if (n_bufs) {
+		bufs = kzalloc(sizeof(bufs[0]) * n_bufs, GFP_KERNEL);
+		if (!bufs) {
+			ret = -ENOMEM;
+			goto err_get_user;
+		}
+	}
+
+	for (i = 0; i < n_bufs; i++) {
+		ret = adf_buffer_import(dev, &arg->bufs[i], &bufs[i]);
+		if (ret < 0) {
+			memset(&bufs[i], 0, sizeof(bufs[i]));
+			goto err_import;
+		}
+	}
+
+	if (custom_data_size) {
+		custom_data = kzalloc(custom_data_size, GFP_KERNEL);
+		if (!custom_data) {
+			ret = -ENOMEM;
+			goto err_import;
+		}
+
+		if (copy_from_user(custom_data, arg->custom_data,
+				custom_data_size)) {
+			ret = -EFAULT;
+			goto err_import;
+		}
+	}
+
+	if (put_user(complete_fence_fd, &arg->complete_fence)) {
+		ret = -EFAULT;
+		goto err_import;
+	}
+
+	complete_fence = adf_device_post_nocopy(dev, intfs, n_intfs, bufs,
+			n_bufs, custom_data, custom_data_size);
+	if (IS_ERR(complete_fence)) {
+		ret = PTR_ERR(complete_fence);
+		goto err_import;
+	}
+
+	sync_fence_install(complete_fence, complete_fence_fd);
+	return 0;
+
+err_import:
+	for (i = 0; i < n_bufs; i++)
+		adf_buffer_cleanup(&bufs[i]);
+
+err_get_user:
+	kfree(custom_data);
+	kfree(bufs);
+	kfree(intfs);
+	put_unused_fd(complete_fence_fd);
+	return ret;
+}
+
+static int adf_intf_simple_post_config(struct adf_interface *intf,
+		struct adf_simple_post_config __user *arg)
+{
+	struct adf_device *dev = intf->base.parent;
+	struct sync_fence *complete_fence;
+	int complete_fence_fd;
+	struct adf_buffer buf;
+	int ret = 0;
+
+	complete_fence_fd = get_unused_fd();
+	if (complete_fence_fd < 0)
+		return complete_fence_fd;
+
+	ret = adf_buffer_import(dev, &arg->buf, &buf);
+	if (ret < 0)
+		goto err_import;
+
+	if (put_user(complete_fence_fd, &arg->complete_fence)) {
+		ret = -EFAULT;
+		goto err_put_user;
+	}
+
+	complete_fence = adf_interface_simple_post(intf, &buf);
+	if (IS_ERR(complete_fence)) {
+		ret = PTR_ERR(complete_fence);
+		goto err_put_user;
+	}
+
+	sync_fence_install(complete_fence, complete_fence_fd);
+	return 0;
+
+err_put_user:
+	adf_buffer_cleanup(&buf);
+err_import:
+	put_unused_fd(complete_fence_fd);
+	return ret;
+}
+
+static int adf_intf_simple_buffer_alloc(struct adf_interface *intf,
+		struct adf_simple_buffer_alloc __user *arg)
+{
+	struct adf_simple_buffer_alloc data;
+	struct dma_buf *dma_buf;
+	int ret = 0;
+
+	if (copy_from_user(&data, arg, sizeof(data)))
+		return -EFAULT;
+
+	data.fd = get_unused_fd_flags(O_CLOEXEC);
+	if (data.fd < 0)
+		return data.fd;
+
+	ret = adf_interface_simple_buffer_alloc(intf, data.w, data.h,
+			data.format, &dma_buf, &data.offset, &data.pitch);
+	if (ret < 0)
+		goto err_alloc;
+
+	if (copy_to_user(arg, &data, sizeof(*arg))) {
+		ret = -EFAULT;
+		goto err_copy;
+	}
+
+	fd_install(data.fd, dma_buf->file);
+	return 0;
+
+err_copy:
+	dma_buf_put(dma_buf);
+
+err_alloc:
+	put_unused_fd(data.fd);
+	return ret;
+}
+
+static int adf_copy_attachment_list_to_user(
+		struct adf_attachment_config __user *to, size_t n_to,
+		struct adf_attachment *from, size_t n_from)
+{
+	struct adf_attachment_config *temp;
+	size_t n = min(n_to, n_from);
+	size_t i;
+	int ret = 0;
+
+	if (!n)
+		return 0;
+
+	temp = kzalloc(n * sizeof(temp[0]), GFP_KERNEL);
+	if (!temp)
+		return -ENOMEM;
+
+	for (i = 0; i < n; i++) {
+		temp[i].interface = from[i].interface->base.id;
+		temp[i].overlay_engine = from[i].overlay_engine->base.id;
+	}
+
+	if (copy_to_user(to, temp, n * sizeof(to[0]))) {
+		ret = -EFAULT;
+		goto done;
+	}
+
+done:
+	kfree(temp);
+	return ret;
+}
+
+static int adf_device_get_data(struct adf_device *dev,
+		struct adf_device_data __user *arg)
+{
+	struct adf_device_data data;
+	size_t n_attach;
+	struct adf_attachment *attach = NULL;
+	size_t n_allowed_attach;
+	struct adf_attachment *allowed_attach = NULL;
+	int ret = 0;
+
+	if (copy_from_user(&data, arg, sizeof(data)))
+		return -EFAULT;
+
+	if (data.n_attachments > ADF_MAX_ATTACHMENTS ||
+			data.n_allowed_attachments > ADF_MAX_ATTACHMENTS)
+		return -EINVAL;
+
+	strlcpy(data.name, dev->base.name, sizeof(data.name));
+
+	if (data.n_attachments) {
+		attach = kzalloc(data.n_attachments * sizeof(attach[0]),
+				GFP_KERNEL);
+		if (!attach)
+			return -ENOMEM;
+	}
+	n_attach = adf_device_attachments(dev, attach, data.n_attachments);
+
+	if (data.n_allowed_attachments) {
+		allowed_attach = kzalloc(data.n_allowed_attachments *
+				sizeof(allowed_attach[0]), GFP_KERNEL);
+		if (!allowed_attach) {
+			ret = -ENOMEM;
+			goto done;
+		}
+	}
+	n_allowed_attach = adf_device_attachments_allowed(dev, allowed_attach,
+			data.n_allowed_attachments);
+
+	mutex_lock(&dev->client_lock);
+	ret = adf_obj_copy_custom_data_to_user(&dev->base, arg->custom_data,
+			&data.custom_data_size);
+	mutex_unlock(&dev->client_lock);
+
+	if (ret < 0)
+		goto done;
+
+	ret = adf_copy_attachment_list_to_user(arg->attachments,
+			data.n_attachments, attach, n_attach);
+	if (ret < 0)
+		goto done;
+
+	ret = adf_copy_attachment_list_to_user(arg->allowed_attachments,
+			data.n_allowed_attachments, allowed_attach,
+			n_allowed_attach);
+	if (ret < 0)
+		goto done;
+
+	data.n_attachments = n_attach;
+	data.n_allowed_attachments = n_allowed_attach;
+
+	if (copy_to_user(arg, &data, sizeof(data)))
+		ret = -EFAULT;
+
+done:
+	kfree(allowed_attach);
+	kfree(attach);
+	return ret;
+}
+
+static int adf_device_handle_attachment(struct adf_device *dev,
+		struct adf_attachment_config __user *arg, bool attach)
+{
+	struct adf_attachment_config data;
+	struct adf_overlay_engine *eng;
+	struct adf_interface *intf;
+
+	if (copy_from_user(&data, arg, sizeof(data)))
+		return -EFAULT;
+
+	eng = idr_find(&dev->overlay_engines, data.overlay_engine);
+	if (!eng) {
+		dev_err(&dev->base.dev, "invalid overlay engine id %u\n",
+				data.overlay_engine);
+		return -EINVAL;
+	}
+
+	intf = idr_find(&dev->interfaces, data.interface);
+	if (!intf) {
+		dev_err(&dev->base.dev, "invalid interface id %u\n",
+				data.interface);
+		return -EINVAL;
+	}
+
+	if (attach)
+		return adf_device_attach(dev, eng, intf);
+	else
+		return adf_device_detach(dev, eng, intf);
+}
+
+static int adf_intf_set_mode(struct adf_interface *intf,
+		struct drm_mode_modeinfo __user *arg)
+{
+	struct drm_mode_modeinfo mode;
+
+	if (copy_from_user(&mode, arg, sizeof(mode)))
+		return -EFAULT;
+
+	return adf_interface_set_mode(intf, &mode);
+}
+
+static int adf_intf_get_data(struct adf_interface *intf,
+		struct adf_interface_data __user *arg)
+{
+	struct adf_device *dev = adf_interface_parent(intf);
+	struct adf_interface_data data;
+	struct drm_mode_modeinfo *modelist;
+	size_t modelist_size;
+	int err;
+	int ret = 0;
+	unsigned long flags;
+
+	if (copy_from_user(&data, arg, sizeof(data)))
+		return -EFAULT;
+
+	strlcpy(data.name, intf->base.name, sizeof(data.name));
+
+	data.type = intf->type;
+	data.id = intf->idx;
+	data.flags = intf->flags;
+
+	err = adf_interface_get_screen_size(intf, &data.width_mm,
+			&data.height_mm);
+	if (err < 0) {
+		data.width_mm = 0;
+		data.height_mm = 0;
+	}
+
+	modelist = kmalloc(sizeof(modelist[0]) * ADF_MAX_MODES, GFP_KERNEL);
+	if (!modelist)
+		return -ENOMEM;
+
+	mutex_lock(&dev->client_lock);
+	read_lock_irqsave(&intf->hotplug_modelist_lock, flags);
+	data.hotplug_detect = intf->hotplug_detect;
+	modelist_size = min(data.n_available_modes, intf->n_modes) *
+			sizeof(intf->modelist[0]);
+	memcpy(modelist, intf->modelist, modelist_size);
+	data.n_available_modes = intf->n_modes;
+	read_unlock_irqrestore(&intf->hotplug_modelist_lock, flags);
+
+	if (copy_to_user(arg->available_modes, modelist, modelist_size)) {
+		ret = -EFAULT;
+		goto done;
+	}
+
+	data.dpms_state = intf->dpms_state;
+	memcpy(&data.current_mode, &intf->current_mode,
+			sizeof(intf->current_mode));
+
+	ret = adf_obj_copy_custom_data_to_user(&intf->base, arg->custom_data,
+			&data.custom_data_size);
+done:
+	mutex_unlock(&dev->client_lock);
+	kfree(modelist);
+
+	if (ret < 0)
+		return ret;
+
+	if (copy_to_user(arg, &data, sizeof(data)))
+		ret = -EFAULT;
+
+	return ret;
+}
+
+static inline long adf_obj_custom_ioctl(struct adf_obj *obj, unsigned int cmd,
+		unsigned long arg)
+{
+	if (obj->ops && obj->ops->ioctl)
+		return obj->ops->ioctl(obj, cmd, arg);
+	return -ENOTTY;
+}
+
+static long adf_overlay_engine_ioctl(struct adf_overlay_engine *eng,
+		struct adf_file *file, unsigned int cmd, unsigned long arg)
+{
+	switch (cmd) {
+	case ADF_SET_EVENT:
+		return adf_obj_set_event(&eng->base, file,
+				(struct adf_set_event __user *)arg);
+
+	case ADF_GET_OVERLAY_ENGINE_DATA:
+		return adf_eng_get_data(eng,
+			(struct adf_overlay_engine_data __user *)arg);
+
+	case ADF_BLANK:
+	case ADF_POST_CONFIG:
+	case ADF_SET_MODE:
+	case ADF_GET_DEVICE_DATA:
+	case ADF_GET_INTERFACE_DATA:
+	case ADF_SIMPLE_POST_CONFIG:
+	case ADF_SIMPLE_BUFFER_ALLOC:
+	case ADF_ATTACH:
+	case ADF_DETACH:
+		return -EINVAL;
+
+	default:
+		return adf_obj_custom_ioctl(&eng->base, cmd, arg);
+	}
+}
+
+static long adf_interface_ioctl(struct adf_interface *intf,
+		struct adf_file *file, unsigned int cmd, unsigned long arg)
+{
+	switch (cmd) {
+	case ADF_SET_EVENT:
+		return adf_obj_set_event(&intf->base, file,
+				(struct adf_set_event __user *)arg);
+
+	case ADF_BLANK:
+		return adf_interface_blank(intf, arg);
+
+	case ADF_SET_MODE:
+		return adf_intf_set_mode(intf,
+				(struct drm_mode_modeinfo __user *)arg);
+
+	case ADF_GET_INTERFACE_DATA:
+		return adf_intf_get_data(intf,
+				(struct adf_interface_data __user *)arg);
+
+	case ADF_SIMPLE_POST_CONFIG:
+		return adf_intf_simple_post_config(intf,
+				(struct adf_simple_post_config __user *)arg);
+
+	case ADF_SIMPLE_BUFFER_ALLOC:
+		return adf_intf_simple_buffer_alloc(intf,
+				(struct adf_simple_buffer_alloc __user *)arg);
+
+	case ADF_POST_CONFIG:
+	case ADF_GET_DEVICE_DATA:
+	case ADF_GET_OVERLAY_ENGINE_DATA:
+	case ADF_ATTACH:
+	case ADF_DETACH:
+		return -EINVAL;
+
+	default:
+		return adf_obj_custom_ioctl(&intf->base, cmd, arg);
+	}
+}
+
+static long adf_device_ioctl(struct adf_device *dev, struct adf_file *file,
+		unsigned int cmd, unsigned long arg)
+{
+	switch (cmd) {
+	case ADF_SET_EVENT:
+		return adf_obj_set_event(&dev->base, file,
+				(struct adf_set_event __user *)arg);
+
+	case ADF_POST_CONFIG:
+		return adf_device_post_config(dev,
+				(struct adf_post_config __user *)arg);
+
+	case ADF_GET_DEVICE_DATA:
+		return adf_device_get_data(dev,
+				(struct adf_device_data __user *)arg);
+
+	case ADF_ATTACH:
+		return adf_device_handle_attachment(dev,
+				(struct adf_attachment_config __user *)arg,
+				true);
+
+	case ADF_DETACH:
+		return adf_device_handle_attachment(dev,
+				(struct adf_attachment_config __user *)arg,
+				false);
+
+	case ADF_BLANK:
+	case ADF_SET_MODE:
+	case ADF_GET_INTERFACE_DATA:
+	case ADF_GET_OVERLAY_ENGINE_DATA:
+	case ADF_SIMPLE_POST_CONFIG:
+	case ADF_SIMPLE_BUFFER_ALLOC:
+		return -EINVAL;
+
+	default:
+		return adf_obj_custom_ioctl(&dev->base, cmd, arg);
+	}
+}
+
+static int adf_file_open(struct inode *inode, struct file *file)
+{
+	struct adf_obj *obj;
+	struct adf_file *fpriv = NULL;
+	unsigned long flags;
+	int ret = 0;
+
+	obj = adf_obj_sysfs_find(iminor(inode));
+	if (!obj)
+		return -ENODEV;
+
+	dev_dbg(&obj->dev, "opening %s\n", dev_name(&obj->dev));
+
+	if (!try_module_get(obj->parent->ops->owner)) {
+		dev_err(&obj->dev, "getting owner module failed\n");
+		return -ENODEV;
+	}
+
+	fpriv = kzalloc(sizeof(*fpriv), GFP_KERNEL);
+	if (!fpriv) {
+		ret = -ENOMEM;
+		goto done;
+	}
+
+	INIT_LIST_HEAD(&fpriv->head);
+	fpriv->obj = obj;
+	init_waitqueue_head(&fpriv->event_wait);
+
+	file->private_data = fpriv;
+
+	if (obj->ops && obj->ops->open) {
+		ret = obj->ops->open(obj, inode, file);
+		if (ret < 0)
+			goto done;
+	}
+
+	spin_lock_irqsave(&obj->file_lock, flags);
+	list_add_tail(&fpriv->head, &obj->file_list);
+	spin_unlock_irqrestore(&obj->file_lock, flags);
+
+done:
+	if (ret < 0) {
+		kfree(fpriv);
+		module_put(obj->parent->ops->owner);
+	}
+	return ret;
+}
+
+static int adf_file_release(struct inode *inode, struct file *file)
+{
+	struct adf_file *fpriv = file->private_data;
+	struct adf_obj *obj = fpriv->obj;
+	enum adf_event_type event_type;
+	unsigned long flags;
+
+	if (obj->ops && obj->ops->release)
+		obj->ops->release(obj, inode, file);
+
+	spin_lock_irqsave(&obj->file_lock, flags);
+	list_del(&fpriv->head);
+	spin_unlock_irqrestore(&obj->file_lock, flags);
+
+	for_each_set_bit(event_type, fpriv->event_subscriptions,
+			ADF_EVENT_TYPE_MAX) {
+		adf_event_put(obj, event_type);
+	}
+
+	kfree(fpriv);
+	module_put(obj->parent->ops->owner);
+
+	dev_dbg(&obj->dev, "released %s\n", dev_name(&obj->dev));
+	return 0;
+}
+
+long adf_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct adf_file *fpriv = file->private_data;
+	struct adf_obj *obj = fpriv->obj;
+	long ret = -EINVAL;
+
+	dev_dbg(&obj->dev, "%s ioctl %u\n", dev_name(&obj->dev), _IOC_NR(cmd));
+
+	switch (obj->type) {
+	case ADF_OBJ_OVERLAY_ENGINE:
+		ret = adf_overlay_engine_ioctl(adf_obj_to_overlay_engine(obj),
+				fpriv, cmd, arg);
+		break;
+
+	case ADF_OBJ_INTERFACE:
+		ret = adf_interface_ioctl(adf_obj_to_interface(obj), fpriv, cmd,
+				arg);
+		break;
+
+	case ADF_OBJ_DEVICE:
+		ret = adf_device_ioctl(adf_obj_to_device(obj), fpriv, cmd, arg);
+		break;
+	}
+
+	return ret;
+}
+
+static inline bool adf_file_event_available(struct adf_file *fpriv)
+{
+	int head = fpriv->event_head;
+	int tail = fpriv->event_tail;
+	return CIRC_CNT(head, tail, sizeof(fpriv->event_buf)) != 0;
+}
+
+void adf_file_queue_event(struct adf_file *fpriv, struct adf_event *event)
+{
+	int head = fpriv->event_head;
+	int tail = fpriv->event_tail;
+	size_t space = CIRC_SPACE(head, tail, sizeof(fpriv->event_buf));
+	size_t space_to_end =
+			CIRC_SPACE_TO_END(head, tail, sizeof(fpriv->event_buf));
+
+	if (space < event->length) {
+		dev_dbg(&fpriv->obj->dev,
+				"insufficient buffer space for event %u\n",
+				event->type);
+		return;
+	}
+
+	if (space_to_end >= event->length) {
+		memcpy(fpriv->event_buf + head, event, event->length);
+	} else {
+		memcpy(fpriv->event_buf + head, event, space_to_end);
+		memcpy(fpriv->event_buf, (u8 *)event + space_to_end,
+				event->length - space_to_end);
+	}
+
+	smp_wmb();
+	fpriv->event_head = (fpriv->event_head + event->length) &
+			(sizeof(fpriv->event_buf) - 1);
+	wake_up_interruptible_all(&fpriv->event_wait);
+}
+
+static ssize_t adf_file_copy_to_user(struct adf_file *fpriv,
+		char __user *buffer, size_t buffer_size)
+{
+	int head, tail;
+	u8 *event_buf;
+	size_t cnt, cnt_to_end, copy_size = 0;
+	ssize_t ret = 0;
+	unsigned long flags;
+
+	event_buf = kmalloc(min(buffer_size, sizeof(fpriv->event_buf)),
+			GFP_KERNEL);
+	if (!event_buf)
+		return -ENOMEM;
+
+	spin_lock_irqsave(&fpriv->obj->file_lock, flags);
+
+	if (!adf_file_event_available(fpriv))
+		goto out;
+
+	head = fpriv->event_head;
+	tail = fpriv->event_tail;
+
+	cnt = CIRC_CNT(head, tail, sizeof(fpriv->event_buf));
+	cnt_to_end = CIRC_CNT_TO_END(head, tail, sizeof(fpriv->event_buf));
+	copy_size = min(buffer_size, cnt);
+
+	if (cnt_to_end >= copy_size) {
+		memcpy(event_buf, fpriv->event_buf + tail, copy_size);
+	} else {
+		memcpy(event_buf, fpriv->event_buf + tail, cnt_to_end);
+		memcpy(event_buf + cnt_to_end, fpriv->event_buf,
+				copy_size - cnt_to_end);
+	}
+
+	fpriv->event_tail = (fpriv->event_tail + copy_size) &
+			(sizeof(fpriv->event_buf) - 1);
+
+out:
+	spin_unlock_irqrestore(&fpriv->obj->file_lock, flags);
+	if (copy_size) {
+		if (copy_to_user(buffer, event_buf, copy_size))
+			ret = -EFAULT;
+		else
+			ret = copy_size;
+	}
+	kfree(event_buf);
+	return ret;
+}
+
+ssize_t adf_file_read(struct file *filp, char __user *buffer,
+		 size_t count, loff_t *offset)
+{
+	struct adf_file *fpriv = filp->private_data;
+	int err;
+
+	err = wait_event_interruptible(fpriv->event_wait,
+			adf_file_event_available(fpriv));
+	if (err < 0)
+		return err;
+
+	return adf_file_copy_to_user(fpriv, buffer, count);
+}
+
+unsigned int adf_file_poll(struct file *filp, struct poll_table_struct *wait)
+{
+	struct adf_file *fpriv = filp->private_data;
+	unsigned int mask = 0;
+
+	poll_wait(filp, &fpriv->event_wait, wait);
+
+	if (adf_file_event_available(fpriv))
+		mask |= POLLIN | POLLRDNORM;
+
+	return mask;
+}
+
+const struct file_operations adf_fops = {
+	.owner = THIS_MODULE,
+	.unlocked_ioctl = adf_file_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = adf_file_compat_ioctl,
+#endif
+	.open = adf_file_open,
+	.release = adf_file_release,
+	.llseek = default_llseek,
+	.read = adf_file_read,
+	.poll = adf_file_poll,
+};
diff --git a/drivers/video/adf/adf_fops.h b/drivers/video/adf/adf_fops.h
new file mode 100644
index 00000000000..90a3a74796d
--- /dev/null
+++ b/drivers/video/adf/adf_fops.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __VIDEO_ADF_ADF_FOPS_H
+#define __VIDEO_ADF_ADF_FOPS_H
+
+#include <linux/bitmap.h>
+#include <linux/fs.h>
+
+extern const struct file_operations adf_fops;
+
+struct adf_file {
+	struct list_head head;
+	struct adf_obj *obj;
+
+	DECLARE_BITMAP(event_subscriptions, ADF_EVENT_TYPE_MAX);
+	u8 event_buf[4096];
+	int event_head;
+	int event_tail;
+	wait_queue_head_t event_wait;
+};
+
+void adf_file_queue_event(struct adf_file *file, struct adf_event *event);
+long adf_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+
+#endif /* __VIDEO_ADF_ADF_FOPS_H */
diff --git a/drivers/video/adf/adf_fops32.c b/drivers/video/adf/adf_fops32.c
new file mode 100644
index 00000000000..d299a816149
--- /dev/null
+++ b/drivers/video/adf/adf_fops32.c
@@ -0,0 +1,217 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/uaccess.h>
+#include <video/adf.h>
+
+#include "adf_fops.h"
+#include "adf_fops32.h"
+
+long adf_compat_post_config(struct file *file,
+		struct adf_post_config32 __user *arg)
+{
+	struct adf_post_config32 cfg32;
+	struct adf_post_config __user *cfg;
+	int ret;
+
+	if (copy_from_user(&cfg32, arg, sizeof(cfg32)))
+		return -EFAULT;
+
+	cfg = compat_alloc_user_space(sizeof(*cfg));
+	if (!access_ok(VERIFY_WRITE, cfg, sizeof(*cfg)))
+		return -EFAULT;
+
+	if (put_user(cfg32.n_interfaces, &cfg->n_interfaces) ||
+			put_user(compat_ptr(cfg32.interfaces),
+					&cfg->interfaces) ||
+			put_user(cfg32.n_bufs, &cfg->n_bufs) ||
+			put_user(compat_ptr(cfg32.bufs), &cfg->bufs) ||
+			put_user(cfg32.custom_data_size,
+					&cfg->custom_data_size) ||
+			put_user(compat_ptr(cfg32.custom_data),
+					&cfg->custom_data))
+		return -EFAULT;
+
+	ret = adf_file_ioctl(file, ADF_POST_CONFIG, (unsigned long)cfg);
+	if (ret < 0)
+		return ret;
+
+	if (copy_in_user(&arg->complete_fence, &cfg->complete_fence,
+			sizeof(cfg->complete_fence)))
+		return -EFAULT;
+
+	return 0;
+}
+
+long adf_compat_get_device_data(struct file *file,
+		struct adf_device_data32 __user *arg)
+{
+	struct adf_device_data32 data32;
+	struct adf_device_data __user *data;
+	int ret;
+
+	if (copy_from_user(&data32, arg, sizeof(data32)))
+		return -EFAULT;
+
+	data = compat_alloc_user_space(sizeof(*data));
+	if (!access_ok(VERIFY_WRITE, data, sizeof(*data)))
+		return -EFAULT;
+
+	if (put_user(data32.n_attachments, &data->n_attachments) ||
+			put_user(compat_ptr(data32.attachments),
+					&data->attachments) ||
+			put_user(data32.n_allowed_attachments,
+					&data->n_allowed_attachments) ||
+			put_user(compat_ptr(data32.allowed_attachments),
+					&data->allowed_attachments) ||
+			put_user(data32.custom_data_size,
+					&data->custom_data_size) ||
+			put_user(compat_ptr(data32.custom_data),
+					&data->custom_data))
+		return -EFAULT;
+
+	ret = adf_file_ioctl(file, ADF_GET_DEVICE_DATA, (unsigned long)data);
+	if (ret < 0)
+		return ret;
+
+	if (copy_in_user(arg->name, data->name, sizeof(arg->name)) ||
+			copy_in_user(&arg->n_attachments, &data->n_attachments,
+					sizeof(arg->n_attachments)) ||
+			copy_in_user(&arg->n_allowed_attachments,
+					&data->n_allowed_attachments,
+					sizeof(arg->n_allowed_attachments)) ||
+			copy_in_user(&arg->custom_data_size,
+					&data->custom_data_size,
+					sizeof(arg->custom_data_size)))
+		return -EFAULT;
+
+	return 0;
+}
+
+long adf_compat_get_interface_data(struct file *file,
+		struct adf_interface_data32 __user *arg)
+{
+	struct adf_interface_data32 data32;
+	struct adf_interface_data __user *data;
+	int ret;
+
+	if (copy_from_user(&data32, arg, sizeof(data32)))
+		return -EFAULT;
+
+	data = compat_alloc_user_space(sizeof(*data));
+	if (!access_ok(VERIFY_WRITE, data, sizeof(*data)))
+		return -EFAULT;
+
+	if (put_user(data32.n_available_modes, &data->n_available_modes) ||
+			put_user(compat_ptr(data32.available_modes),
+					&data->available_modes) ||
+			put_user(data32.custom_data_size,
+					&data->custom_data_size) ||
+			put_user(compat_ptr(data32.custom_data),
+					&data->custom_data))
+		return -EFAULT;
+
+	ret = adf_file_ioctl(file, ADF_GET_INTERFACE_DATA, (unsigned long)data);
+	if (ret < 0)
+		return ret;
+
+	if (copy_in_user(arg->name, data->name, sizeof(arg->name)) ||
+			copy_in_user(&arg->type, &data->type,
+					sizeof(arg->type)) ||
+			copy_in_user(&arg->id, &data->id, sizeof(arg->id)) ||
+			copy_in_user(&arg->flags, &data->flags,
+					sizeof(arg->flags)) ||
+			copy_in_user(&arg->dpms_state, &data->dpms_state,
+					sizeof(arg->dpms_state)) ||
+			copy_in_user(&arg->hotplug_detect,
+					&data->hotplug_detect,
+					sizeof(arg->hotplug_detect)) ||
+			copy_in_user(&arg->width_mm, &data->width_mm,
+					sizeof(arg->width_mm)) ||
+			copy_in_user(&arg->height_mm, &data->height_mm,
+					sizeof(arg->height_mm)) ||
+			copy_in_user(&arg->current_mode, &data->current_mode,
+					sizeof(arg->current_mode)) ||
+			copy_in_user(&arg->n_available_modes,
+					&data->n_available_modes,
+					sizeof(arg->n_available_modes)) ||
+			copy_in_user(&arg->custom_data_size,
+					&data->custom_data_size,
+					sizeof(arg->custom_data_size)))
+		return -EFAULT;
+
+	return 0;
+}
+
+long adf_compat_get_overlay_engine_data(struct file *file,
+		struct adf_overlay_engine_data32 __user *arg)
+{
+	struct adf_overlay_engine_data32 data32;
+	struct adf_overlay_engine_data __user *data;
+	int ret;
+
+	if (copy_from_user(&data32, arg, sizeof(data32)))
+		return -EFAULT;
+
+	data = compat_alloc_user_space(sizeof(*data));
+	if (!access_ok(VERIFY_WRITE, data, sizeof(*data)))
+		return -EFAULT;
+
+	if (put_user(data32.n_supported_formats, &data->n_supported_formats) ||
+			put_user(compat_ptr(data32.supported_formats),
+					&data->supported_formats) ||
+			put_user(data32.custom_data_size,
+					&data->custom_data_size) ||
+			put_user(compat_ptr(data32.custom_data),
+					&data->custom_data))
+		return -EFAULT;
+
+	ret = adf_file_ioctl(file, ADF_GET_OVERLAY_ENGINE_DATA,
+			(unsigned long)data);
+	if (ret < 0)
+		return ret;
+
+	if (copy_in_user(arg->name, data->name, sizeof(arg->name)) ||
+			copy_in_user(&arg->n_supported_formats,
+					&data->n_supported_formats,
+					sizeof(arg->n_supported_formats)) ||
+			copy_in_user(&arg->custom_data_size,
+					&data->custom_data_size,
+					sizeof(arg->custom_data_size)))
+		return -EFAULT;
+
+	return 0;
+}
+
+long adf_file_compat_ioctl(struct file *file, unsigned int cmd,
+		unsigned long arg)
+{
+	switch (cmd) {
+	case ADF_POST_CONFIG32:
+		return adf_compat_post_config(file, compat_ptr(arg));
+
+	case ADF_GET_DEVICE_DATA32:
+		return adf_compat_get_device_data(file, compat_ptr(arg));
+
+	case ADF_GET_INTERFACE_DATA32:
+		return adf_compat_get_interface_data(file, compat_ptr(arg));
+
+	case ADF_GET_OVERLAY_ENGINE_DATA32:
+		return adf_compat_get_overlay_engine_data(file,
+				compat_ptr(arg));
+
+	default:
+		return adf_file_ioctl(file, cmd, arg);
+	}
+}
diff --git a/drivers/video/adf/adf_fops32.h b/drivers/video/adf/adf_fops32.h
new file mode 100644
index 00000000000..64034ce33a6
--- /dev/null
+++ b/drivers/video/adf/adf_fops32.h
@@ -0,0 +1,78 @@
+#ifndef __VIDEO_ADF_ADF_FOPS32_H
+#define __VIDEO_ADF_ADF_FOPS32_H
+
+#include <linux/compat.h>
+#include <linux/ioctl.h>
+
+#include <video/adf.h>
+
+#define ADF_POST_CONFIG32 \
+		_IOW(ADF_IOCTL_TYPE, 2, struct adf_post_config32)
+#define ADF_GET_DEVICE_DATA32 \
+		_IOR(ADF_IOCTL_TYPE, 4, struct adf_device_data32)
+#define ADF_GET_INTERFACE_DATA32 \
+		_IOR(ADF_IOCTL_TYPE, 5, struct adf_interface_data32)
+#define ADF_GET_OVERLAY_ENGINE_DATA32 \
+		_IOR(ADF_IOCTL_TYPE, 6, struct adf_overlay_engine_data32)
+
+struct adf_post_config32 {
+	compat_size_t n_interfaces;
+	compat_uptr_t interfaces;
+
+	compat_size_t n_bufs;
+	compat_uptr_t bufs;
+
+	compat_size_t custom_data_size;
+	compat_uptr_t custom_data;
+
+	__s32 complete_fence;
+};
+
+struct adf_device_data32 {
+	char name[ADF_NAME_LEN];
+
+	compat_size_t n_attachments;
+	compat_uptr_t attachments;
+
+	compat_size_t n_allowed_attachments;
+	compat_uptr_t allowed_attachments;
+
+	compat_size_t custom_data_size;
+	compat_uptr_t custom_data;
+};
+
+struct adf_interface_data32 {
+	char name[ADF_NAME_LEN];
+
+	__u8 type;
+	__u32 id;
+	/* e.g. type=ADF_INTF_TYPE_DSI, id=1 => DSI.1 */
+	__u32 flags;
+
+	__u8 dpms_state;
+	__u8 hotplug_detect;
+	__u16 width_mm;
+	__u16 height_mm;
+
+	struct drm_mode_modeinfo current_mode;
+	compat_size_t n_available_modes;
+	compat_uptr_t available_modes;
+
+	compat_size_t custom_data_size;
+	compat_uptr_t custom_data;
+};
+
+struct adf_overlay_engine_data32 {
+	char name[ADF_NAME_LEN];
+
+	compat_size_t n_supported_formats;
+	compat_uptr_t supported_formats;
+
+	compat_size_t custom_data_size;
+	compat_uptr_t custom_data;
+};
+
+long adf_file_compat_ioctl(struct file *file, unsigned int cmd,
+		unsigned long arg);
+
+#endif /* __VIDEO_ADF_ADF_FOPS32_H */
diff --git a/drivers/video/adf/adf_format.c b/drivers/video/adf/adf_format.c
new file mode 100644
index 00000000000..e3f22c7c85d
--- /dev/null
+++ b/drivers/video/adf/adf_format.c
@@ -0,0 +1,280 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ * modified from drivers/gpu/drm/drm_crtc.c
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <drm/drm_fourcc.h>
+#include <video/adf_format.h>
+
+bool adf_format_is_standard(u32 format)
+{
+	switch (format) {
+	case DRM_FORMAT_C8:
+	case DRM_FORMAT_RGB332:
+	case DRM_FORMAT_BGR233:
+	case DRM_FORMAT_XRGB4444:
+	case DRM_FORMAT_XBGR4444:
+	case DRM_FORMAT_RGBX4444:
+	case DRM_FORMAT_BGRX4444:
+	case DRM_FORMAT_ARGB4444:
+	case DRM_FORMAT_ABGR4444:
+	case DRM_FORMAT_RGBA4444:
+	case DRM_FORMAT_BGRA4444:
+	case DRM_FORMAT_XRGB1555:
+	case DRM_FORMAT_XBGR1555:
+	case DRM_FORMAT_RGBX5551:
+	case DRM_FORMAT_BGRX5551:
+	case DRM_FORMAT_ARGB1555:
+	case DRM_FORMAT_ABGR1555:
+	case DRM_FORMAT_RGBA5551:
+	case DRM_FORMAT_BGRA5551:
+	case DRM_FORMAT_RGB565:
+	case DRM_FORMAT_BGR565:
+	case DRM_FORMAT_RGB888:
+	case DRM_FORMAT_BGR888:
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_RGBX8888:
+	case DRM_FORMAT_BGRX8888:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_ABGR8888:
+	case DRM_FORMAT_RGBA8888:
+	case DRM_FORMAT_BGRA8888:
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_RGBX1010102:
+	case DRM_FORMAT_BGRX1010102:
+	case DRM_FORMAT_ARGB2101010:
+	case DRM_FORMAT_ABGR2101010:
+	case DRM_FORMAT_RGBA1010102:
+	case DRM_FORMAT_BGRA1010102:
+	case DRM_FORMAT_YUYV:
+	case DRM_FORMAT_YVYU:
+	case DRM_FORMAT_UYVY:
+	case DRM_FORMAT_VYUY:
+	case DRM_FORMAT_AYUV:
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV21:
+	case DRM_FORMAT_NV16:
+	case DRM_FORMAT_NV61:
+	case DRM_FORMAT_YUV410:
+	case DRM_FORMAT_YVU410:
+	case DRM_FORMAT_YUV411:
+	case DRM_FORMAT_YVU411:
+	case DRM_FORMAT_YUV420:
+	case DRM_FORMAT_YVU420:
+	case DRM_FORMAT_YUV422:
+	case DRM_FORMAT_YVU422:
+	case DRM_FORMAT_YUV444:
+	case DRM_FORMAT_YVU444:
+		return true;
+	default:
+		return false;
+	}
+}
+EXPORT_SYMBOL(adf_format_is_standard);
+
+bool adf_format_is_rgb(u32 format)
+{
+	switch (format) {
+	case DRM_FORMAT_C8:
+	case DRM_FORMAT_RGB332:
+	case DRM_FORMAT_BGR233:
+	case DRM_FORMAT_XRGB1555:
+	case DRM_FORMAT_XBGR1555:
+	case DRM_FORMAT_RGBX5551:
+	case DRM_FORMAT_BGRX5551:
+	case DRM_FORMAT_ARGB1555:
+	case DRM_FORMAT_ABGR1555:
+	case DRM_FORMAT_RGBA5551:
+	case DRM_FORMAT_BGRA5551:
+	case DRM_FORMAT_RGB565:
+	case DRM_FORMAT_BGR565:
+	case DRM_FORMAT_RGB888:
+	case DRM_FORMAT_BGR888:
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_RGBX8888:
+	case DRM_FORMAT_BGRX8888:
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_RGBX1010102:
+	case DRM_FORMAT_BGRX1010102:
+	case DRM_FORMAT_ARGB2101010:
+	case DRM_FORMAT_ABGR2101010:
+	case DRM_FORMAT_RGBA1010102:
+	case DRM_FORMAT_BGRA1010102:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_ABGR8888:
+	case DRM_FORMAT_RGBA8888:
+	case DRM_FORMAT_BGRA8888:
+		return true;
+
+	default:
+		return false;
+	}
+}
+EXPORT_SYMBOL(adf_format_is_rgb);
+
+u8 adf_format_num_planes(u32 format)
+{
+	switch (format) {
+	case DRM_FORMAT_YUV410:
+	case DRM_FORMAT_YVU410:
+	case DRM_FORMAT_YUV411:
+	case DRM_FORMAT_YVU411:
+	case DRM_FORMAT_YUV420:
+	case DRM_FORMAT_YVU420:
+	case DRM_FORMAT_YUV422:
+	case DRM_FORMAT_YVU422:
+	case DRM_FORMAT_YUV444:
+	case DRM_FORMAT_YVU444:
+		return 3;
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV21:
+	case DRM_FORMAT_NV16:
+	case DRM_FORMAT_NV61:
+		return 2;
+	default:
+		return 1;
+	}
+}
+EXPORT_SYMBOL(adf_format_num_planes);
+
+u8 adf_format_bpp(u32 format)
+{
+	switch (format) {
+	case DRM_FORMAT_C8:
+	case DRM_FORMAT_RGB332:
+	case DRM_FORMAT_BGR233:
+		return 8;
+
+	case DRM_FORMAT_XRGB1555:
+	case DRM_FORMAT_XBGR1555:
+	case DRM_FORMAT_RGBX5551:
+	case DRM_FORMAT_BGRX5551:
+	case DRM_FORMAT_ARGB1555:
+	case DRM_FORMAT_ABGR1555:
+	case DRM_FORMAT_RGBA5551:
+	case DRM_FORMAT_BGRA5551:
+	case DRM_FORMAT_RGB565:
+	case DRM_FORMAT_BGR565:
+		return 16;
+
+	case DRM_FORMAT_RGB888:
+	case DRM_FORMAT_BGR888:
+		return 24;
+
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_RGBX8888:
+	case DRM_FORMAT_BGRX8888:
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_RGBX1010102:
+	case DRM_FORMAT_BGRX1010102:
+	case DRM_FORMAT_ARGB2101010:
+	case DRM_FORMAT_ABGR2101010:
+	case DRM_FORMAT_RGBA1010102:
+	case DRM_FORMAT_BGRA1010102:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_ABGR8888:
+	case DRM_FORMAT_RGBA8888:
+	case DRM_FORMAT_BGRA8888:
+		return 32;
+
+	default:
+		pr_debug("%s: unsupported pixel format %u\n", __func__, format);
+		return 0;
+	}
+}
+EXPORT_SYMBOL(adf_format_bpp);
+
+u8 adf_format_plane_cpp(u32 format, int plane)
+{
+	if (plane >= adf_format_num_planes(format))
+		return 0;
+
+	switch (format) {
+	case DRM_FORMAT_YUYV:
+	case DRM_FORMAT_YVYU:
+	case DRM_FORMAT_UYVY:
+	case DRM_FORMAT_VYUY:
+		return 2;
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV21:
+	case DRM_FORMAT_NV16:
+	case DRM_FORMAT_NV61:
+		return plane ? 2 : 1;
+	case DRM_FORMAT_YUV410:
+	case DRM_FORMAT_YVU410:
+	case DRM_FORMAT_YUV411:
+	case DRM_FORMAT_YVU411:
+	case DRM_FORMAT_YUV420:
+	case DRM_FORMAT_YVU420:
+	case DRM_FORMAT_YUV422:
+	case DRM_FORMAT_YVU422:
+	case DRM_FORMAT_YUV444:
+	case DRM_FORMAT_YVU444:
+		return 1;
+	default:
+		return adf_format_bpp(format) / 8;
+	}
+}
+EXPORT_SYMBOL(adf_format_plane_cpp);
+
+u8 adf_format_horz_chroma_subsampling(u32 format)
+{
+	switch (format) {
+	case DRM_FORMAT_YUV411:
+	case DRM_FORMAT_YVU411:
+	case DRM_FORMAT_YUV410:
+	case DRM_FORMAT_YVU410:
+		return 4;
+	case DRM_FORMAT_YUYV:
+	case DRM_FORMAT_YVYU:
+	case DRM_FORMAT_UYVY:
+	case DRM_FORMAT_VYUY:
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV21:
+	case DRM_FORMAT_NV16:
+	case DRM_FORMAT_NV61:
+	case DRM_FORMAT_YUV422:
+	case DRM_FORMAT_YVU422:
+	case DRM_FORMAT_YUV420:
+	case DRM_FORMAT_YVU420:
+		return 2;
+	default:
+		return 1;
+	}
+}
+EXPORT_SYMBOL(adf_format_horz_chroma_subsampling);
+
+u8 adf_format_vert_chroma_subsampling(u32 format)
+{
+	switch (format) {
+	case DRM_FORMAT_YUV410:
+	case DRM_FORMAT_YVU410:
+		return 4;
+	case DRM_FORMAT_YUV420:
+	case DRM_FORMAT_YVU420:
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV21:
+		return 2;
+	default:
+		return 1;
+	}
+}
+EXPORT_SYMBOL(adf_format_vert_chroma_subsampling);
diff --git a/drivers/video/adf/adf_memblock.c b/drivers/video/adf/adf_memblock.c
new file mode 100644
index 00000000000..ab583f838db
--- /dev/null
+++ b/drivers/video/adf/adf_memblock.c
@@ -0,0 +1,160 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/dma-buf.h>
+#include <linux/highmem.h>
+#include <linux/memblock.h>
+#include <linux/slab.h>
+
+struct adf_memblock_pdata {
+	phys_addr_t base;
+};
+
+static struct sg_table *adf_memblock_map(struct dma_buf_attachment *attach,
+		enum dma_data_direction direction)
+{
+	struct adf_memblock_pdata *pdata = attach->dmabuf->priv;
+	unsigned long pfn = PFN_DOWN(pdata->base);
+	struct page *page = pfn_to_page(pfn);
+	struct sg_table *table;
+	int nents, ret;
+
+	table = kzalloc(sizeof(*table), GFP_KERNEL);
+	if (!table)
+		return ERR_PTR(-ENOMEM);
+
+	ret = sg_alloc_table(table, 1, GFP_KERNEL);
+	if (ret < 0)
+		goto err_alloc;
+
+	sg_set_page(table->sgl, page, attach->dmabuf->size, 0);
+
+	nents = dma_map_sg(attach->dev, table->sgl, 1, direction);
+	if (!nents) {
+		ret = -EINVAL;
+		goto err_map;
+	}
+
+	return table;
+
+err_map:
+	sg_free_table(table);
+err_alloc:
+	kfree(table);
+	return ERR_PTR(ret);
+}
+
+static void adf_memblock_unmap(struct dma_buf_attachment *attach,
+		struct sg_table *table, enum dma_data_direction direction)
+{
+	dma_unmap_sg(attach->dev, table->sgl, 1, direction);
+	sg_free_table(table);
+}
+
+static void __init_memblock adf_memblock_release(struct dma_buf *buf)
+{
+	struct adf_memblock_pdata *pdata = buf->priv;
+	int err = memblock_free(pdata->base, buf->size);
+
+	if (err < 0)
+		pr_warn("%s: freeing memblock failed: %d\n", __func__, err);
+	kfree(pdata);
+}
+
+static void *adf_memblock_do_kmap(struct dma_buf *buf, unsigned long pgoffset,
+		bool atomic)
+{
+	struct adf_memblock_pdata *pdata = buf->priv;
+	unsigned long pfn = PFN_DOWN(pdata->base) + pgoffset;
+	struct page *page = pfn_to_page(pfn);
+
+	if (atomic)
+		return kmap_atomic(page);
+	else
+		return kmap(page);
+}
+
+static void *adf_memblock_kmap_atomic(struct dma_buf *buf,
+		unsigned long pgoffset)
+{
+	return adf_memblock_do_kmap(buf, pgoffset, true);
+}
+
+static void adf_memblock_kunmap_atomic(struct dma_buf *buf,
+		unsigned long pgoffset, void *vaddr)
+{
+	kunmap_atomic(vaddr);
+}
+
+static void *adf_memblock_kmap(struct dma_buf *buf, unsigned long pgoffset)
+{
+	return adf_memblock_do_kmap(buf, pgoffset, false);
+}
+
+static void adf_memblock_kunmap(struct dma_buf *buf, unsigned long pgoffset,
+		void *vaddr)
+{
+	kunmap(vaddr);
+}
+
+static int adf_memblock_mmap(struct dma_buf *buf, struct vm_area_struct *vma)
+{
+	struct adf_memblock_pdata *pdata = buf->priv;
+
+	return remap_pfn_range(vma, vma->vm_start, PFN_DOWN(pdata->base),
+			vma->vm_end - vma->vm_start, vma->vm_page_prot);
+}
+
+struct dma_buf_ops adf_memblock_ops = {
+	.map_dma_buf = adf_memblock_map,
+	.unmap_dma_buf = adf_memblock_unmap,
+	.release = adf_memblock_release,
+	.kmap_atomic = adf_memblock_kmap_atomic,
+	.kunmap_atomic = adf_memblock_kunmap_atomic,
+	.kmap = adf_memblock_kmap,
+	.kunmap = adf_memblock_kunmap,
+	.mmap = adf_memblock_mmap,
+};
+
+/**
+ * adf_memblock_export - export a memblock reserved area as a dma-buf
+ *
+ * @base: base physical address
+ * @size: memblock size
+ * @flags: mode flags for the dma-buf's file
+ *
+ * @base and @size must be page-aligned.
+ *
+ * Returns a dma-buf on success or ERR_PTR(-errno) on failure.
+ */
+struct dma_buf *adf_memblock_export(phys_addr_t base, size_t size, int flags)
+{
+	struct adf_memblock_pdata *pdata;
+	struct dma_buf *buf;
+
+	if (PAGE_ALIGN(base) != base || PAGE_ALIGN(size) != size)
+		return ERR_PTR(-EINVAL);
+
+	pdata = kzalloc(sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return ERR_PTR(-ENOMEM);
+
+	pdata->base = base;
+	buf = dma_buf_export(pdata, &adf_memblock_ops, size, flags, NULL);
+	if (IS_ERR(buf))
+		kfree(pdata);
+
+	return buf;
+}
+EXPORT_SYMBOL(adf_memblock_export);
diff --git a/drivers/video/adf/adf_sysfs.c b/drivers/video/adf/adf_sysfs.c
new file mode 100644
index 00000000000..8c659c71ffa
--- /dev/null
+++ b/drivers/video/adf/adf_sysfs.c
@@ -0,0 +1,296 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <video/adf_client.h>
+
+#include "adf.h"
+#include "adf_fops.h"
+#include "adf_sysfs.h"
+
+static struct class *adf_class;
+static int adf_major;
+static DEFINE_IDR(adf_minors);
+
+#define dev_to_adf_interface(p) \
+	adf_obj_to_interface(container_of(p, struct adf_obj, dev))
+
+static ssize_t dpms_state_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct adf_interface *intf = dev_to_adf_interface(dev);
+	return scnprintf(buf, PAGE_SIZE, "%u\n",
+			adf_interface_dpms_state(intf));
+}
+
+static ssize_t dpms_state_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct adf_interface *intf = dev_to_adf_interface(dev);
+	u8 dpms_state;
+	int err;
+
+	err = kstrtou8(buf, 0, &dpms_state);
+	if (err < 0)
+		return err;
+
+	err = adf_interface_blank(intf, dpms_state);
+	if (err < 0)
+		return err;
+
+	return count;
+}
+
+static ssize_t current_mode_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct adf_interface *intf = dev_to_adf_interface(dev);
+	struct drm_mode_modeinfo mode;
+
+	adf_interface_current_mode(intf, &mode);
+
+	if (mode.name[0]) {
+		return scnprintf(buf, PAGE_SIZE, "%s\n", mode.name);
+	} else {
+		bool interlaced = !!(mode.flags & DRM_MODE_FLAG_INTERLACE);
+		return scnprintf(buf, PAGE_SIZE, "%ux%u%s\n", mode.hdisplay,
+				mode.vdisplay, interlaced ? "i" : "");
+	}
+}
+
+static ssize_t type_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
+{
+	struct adf_interface *intf = dev_to_adf_interface(dev);
+	return scnprintf(buf, PAGE_SIZE, "%s\n",
+			adf_interface_type_str(intf));
+}
+
+static ssize_t vsync_timestamp_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct adf_interface *intf = dev_to_adf_interface(dev);
+	ktime_t timestamp;
+	unsigned long flags;
+
+	read_lock_irqsave(&intf->vsync_lock, flags);
+	memcpy(&timestamp, &intf->vsync_timestamp, sizeof(timestamp));
+	read_unlock_irqrestore(&intf->vsync_lock, flags);
+
+	return scnprintf(buf, PAGE_SIZE, "%llu\n", ktime_to_ns(timestamp));
+}
+
+static ssize_t hotplug_detect_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct adf_interface *intf = dev_to_adf_interface(dev);
+	return scnprintf(buf, PAGE_SIZE, "%u\n", intf->hotplug_detect);
+}
+
+static struct device_attribute adf_interface_attrs[] = {
+	__ATTR(dpms_state, S_IRUGO|S_IWUSR, dpms_state_show, dpms_state_store),
+	__ATTR_RO(current_mode),
+	__ATTR_RO(hotplug_detect),
+	__ATTR_RO(type),
+	__ATTR_RO(vsync_timestamp),
+};
+
+int adf_obj_sysfs_init(struct adf_obj *obj, struct device *parent)
+{
+	int ret = idr_alloc(&adf_minors, obj, 0, 0, GFP_KERNEL);
+	if (ret < 0) {
+		pr_err("%s: allocating adf minor failed: %d\n", __func__,
+				ret);
+		return ret;
+	}
+
+	obj->minor = ret;
+	obj->dev.parent = parent;
+	obj->dev.class = adf_class;
+	obj->dev.devt = MKDEV(adf_major, obj->minor);
+
+	ret = device_register(&obj->dev);
+	if (ret < 0) {
+		pr_err("%s: registering adf object failed: %d\n", __func__,
+				ret);
+		goto err_device_register;
+	}
+
+	return 0;
+
+err_device_register:
+	idr_remove(&adf_minors, obj->minor);
+	return ret;
+}
+
+static char *adf_device_devnode(struct device *dev, umode_t *mode,
+		kuid_t *uid, kgid_t *gid)
+{
+	struct adf_obj *obj = container_of(dev, struct adf_obj, dev);
+	return kasprintf(GFP_KERNEL, "adf%d", obj->id);
+}
+
+static char *adf_interface_devnode(struct device *dev, umode_t *mode,
+		kuid_t *uid, kgid_t *gid)
+{
+	struct adf_obj *obj = container_of(dev, struct adf_obj, dev);
+	struct adf_interface *intf = adf_obj_to_interface(obj);
+	struct adf_device *parent = adf_interface_parent(intf);
+	return kasprintf(GFP_KERNEL, "adf-interface%d.%d",
+			parent->base.id, intf->base.id);
+}
+
+static char *adf_overlay_engine_devnode(struct device *dev, umode_t *mode,
+		kuid_t *uid, kgid_t *gid)
+{
+	struct adf_obj *obj = container_of(dev, struct adf_obj, dev);
+	struct adf_overlay_engine *eng = adf_obj_to_overlay_engine(obj);
+	struct adf_device *parent = adf_overlay_engine_parent(eng);
+	return kasprintf(GFP_KERNEL, "adf-overlay-engine%d.%d",
+			parent->base.id, eng->base.id);
+}
+
+static void adf_noop_release(struct device *dev)
+{
+}
+
+static struct device_type adf_device_type = {
+	.name = "adf_device",
+	.devnode = adf_device_devnode,
+	.release = adf_noop_release,
+};
+
+static struct device_type adf_interface_type = {
+	.name = "adf_interface",
+	.devnode = adf_interface_devnode,
+	.release = adf_noop_release,
+};
+
+static struct device_type adf_overlay_engine_type = {
+	.name = "adf_overlay_engine",
+	.devnode = adf_overlay_engine_devnode,
+	.release = adf_noop_release,
+};
+
+int adf_device_sysfs_init(struct adf_device *dev)
+{
+	dev->base.dev.type = &adf_device_type;
+	dev_set_name(&dev->base.dev, "%s", dev->base.name);
+	return adf_obj_sysfs_init(&dev->base, dev->dev);
+}
+
+int adf_interface_sysfs_init(struct adf_interface *intf)
+{
+	struct adf_device *parent = adf_interface_parent(intf);
+	size_t i, j;
+	int ret;
+
+	intf->base.dev.type = &adf_interface_type;
+	dev_set_name(&intf->base.dev, "%s-interface%d", parent->base.name,
+			intf->base.id);
+
+	ret = adf_obj_sysfs_init(&intf->base, &parent->base.dev);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < ARRAY_SIZE(adf_interface_attrs); i++) {
+		ret = device_create_file(&intf->base.dev,
+				&adf_interface_attrs[i]);
+		if (ret < 0) {
+			dev_err(&intf->base.dev, "creating sysfs attribute %s failed: %d\n",
+					adf_interface_attrs[i].attr.name, ret);
+			goto err;
+		}
+	}
+
+	return 0;
+
+err:
+	for (j = 0; j < i; j++)
+		device_remove_file(&intf->base.dev, &adf_interface_attrs[j]);
+	return ret;
+}
+
+int adf_overlay_engine_sysfs_init(struct adf_overlay_engine *eng)
+{
+	struct adf_device *parent = adf_overlay_engine_parent(eng);
+
+	eng->base.dev.type = &adf_overlay_engine_type;
+	dev_set_name(&eng->base.dev, "%s-overlay-engine%d", parent->base.name,
+			eng->base.id);
+
+	return adf_obj_sysfs_init(&eng->base, &parent->base.dev);
+}
+
+struct adf_obj *adf_obj_sysfs_find(int minor)
+{
+	return idr_find(&adf_minors, minor);
+}
+
+void adf_obj_sysfs_destroy(struct adf_obj *obj)
+{
+	idr_remove(&adf_minors, obj->minor);
+	device_unregister(&obj->dev);
+}
+
+void adf_device_sysfs_destroy(struct adf_device *dev)
+{
+	adf_obj_sysfs_destroy(&dev->base);
+}
+
+void adf_interface_sysfs_destroy(struct adf_interface *intf)
+{
+	size_t i;
+
+	for (i = 0; i < ARRAY_SIZE(adf_interface_attrs); i++)
+		device_remove_file(&intf->base.dev, &adf_interface_attrs[i]);
+	adf_obj_sysfs_destroy(&intf->base);
+}
+
+void adf_overlay_engine_sysfs_destroy(struct adf_overlay_engine *eng)
+{
+	adf_obj_sysfs_destroy(&eng->base);
+}
+
+int adf_sysfs_init(void)
+{
+	struct class *class;
+	int ret;
+
+	class = class_create(THIS_MODULE, "adf");
+	if (IS_ERR(class)) {
+		ret = PTR_ERR(class);
+		pr_err("%s: creating class failed: %d\n", __func__, ret);
+		return ret;
+	}
+
+	ret = register_chrdev(0, "adf", &adf_fops);
+	if (ret < 0) {
+		pr_err("%s: registering device failed: %d\n", __func__, ret);
+		goto err_chrdev;
+	}
+
+	adf_class = class;
+	adf_major = ret;
+	return 0;
+
+err_chrdev:
+	class_destroy(adf_class);
+	return ret;
+}
+
+void adf_sysfs_destroy(void)
+{
+	idr_destroy(&adf_minors);
+	class_destroy(adf_class);
+}
diff --git a/drivers/video/adf/adf_sysfs.h b/drivers/video/adf/adf_sysfs.h
new file mode 100644
index 00000000000..0613ac364f8
--- /dev/null
+++ b/drivers/video/adf/adf_sysfs.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __VIDEO_ADF_ADF_SYSFS_H
+#define __VIDEO_ADF_ADF_SYSFS_H
+
+struct adf_device;
+struct adf_interface;
+struct adf_overlay_engine;
+
+int adf_device_sysfs_init(struct adf_device *dev);
+void adf_device_sysfs_destroy(struct adf_device *dev);
+int adf_interface_sysfs_init(struct adf_interface *intf);
+void adf_interface_sysfs_destroy(struct adf_interface *intf);
+int adf_overlay_engine_sysfs_init(struct adf_overlay_engine *eng);
+void adf_overlay_engine_sysfs_destroy(struct adf_overlay_engine *eng);
+struct adf_obj *adf_obj_sysfs_find(int minor);
+
+int adf_sysfs_init(void);
+void adf_sysfs_destroy(void);
+
+#endif /* __VIDEO_ADF_ADF_SYSFS_H */
diff --git a/drivers/video/adf/adf_trace.h b/drivers/video/adf/adf_trace.h
new file mode 100644
index 00000000000..3cb2a84d728
--- /dev/null
+++ b/drivers/video/adf/adf_trace.h
@@ -0,0 +1,93 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM adf
+
+#if !defined(__VIDEO_ADF_ADF_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __VIDEO_ADF_ADF_TRACE_H
+
+#include <linux/tracepoint.h>
+#include <video/adf.h>
+
+TRACE_EVENT(adf_event,
+	TP_PROTO(struct adf_obj *obj, enum adf_event_type type),
+	TP_ARGS(obj, type),
+
+	TP_STRUCT__entry(
+		__string(name, obj->name)
+		__field(enum adf_event_type, type)
+		__array(char, type_str, 32)
+	),
+	TP_fast_assign(
+		__assign_str(name, obj->name);
+		__entry->type = type;
+		strlcpy(__entry->type_str, adf_event_type_str(obj, type),
+				sizeof(__entry->type_str));
+	),
+	TP_printk("obj=%s type=%u (%s)",
+			__get_str(name),
+			__entry->type,
+			__entry->type_str)
+);
+
+TRACE_EVENT(adf_event_enable,
+	TP_PROTO(struct adf_obj *obj, enum adf_event_type type),
+	TP_ARGS(obj, type),
+
+	TP_STRUCT__entry(
+		__string(name, obj->name)
+		__field(enum adf_event_type, type)
+		__array(char, type_str, 32)
+	),
+	TP_fast_assign(
+		__assign_str(name, obj->name);
+		__entry->type = type;
+		strlcpy(__entry->type_str, adf_event_type_str(obj, type),
+				sizeof(__entry->type_str));
+	),
+	TP_printk("obj=%s type=%u (%s)",
+			__get_str(name),
+			__entry->type,
+			__entry->type_str)
+);
+
+TRACE_EVENT(adf_event_disable,
+	TP_PROTO(struct adf_obj *obj, enum adf_event_type type),
+	TP_ARGS(obj, type),
+
+	TP_STRUCT__entry(
+		__string(name, obj->name)
+		__field(enum adf_event_type, type)
+		__array(char, type_str, 32)
+	),
+	TP_fast_assign(
+		__assign_str(name, obj->name);
+		__entry->type = type;
+		strlcpy(__entry->type_str, adf_event_type_str(obj, type),
+				sizeof(__entry->type_str));
+	),
+	TP_printk("obj=%s type=%u (%s)",
+			__get_str(name),
+			__entry->type,
+			__entry->type_str)
+);
+
+#endif /* __VIDEO_ADF_ADF_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE adf_trace
+#include <trace/define_trace.h>
diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c
index 900aa4ecd61..d6cab1fd9a4 100644
--- a/drivers/video/fbdev/core/fb_defio.c
+++ b/drivers/video/fbdev/core/fb_defio.c
@@ -83,9 +83,10 @@ int fb_deferred_io_fsync(struct file *file, loff_t start, loff_t end, int datasy
 	cancel_delayed_work_sync(&info->deferred_work);
 
 	/* Run it immediately */
-	err = schedule_delayed_work(&info->deferred_work, 0);
+	schedule_delayed_work(&info->deferred_work, 0);
 	mutex_unlock(&inode->i_mutex);
-	return err;
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(fb_deferred_io_fsync);
 
diff --git a/drivers/video/logo/logo.c b/drivers/video/logo/logo.c
index 940cd196eef..10fbfd8ab96 100644
--- a/drivers/video/logo/logo.c
+++ b/drivers/video/logo/logo.c
@@ -21,6 +21,21 @@ static bool nologo;
 module_param(nologo, bool, 0);
 MODULE_PARM_DESC(nologo, "Disables startup logo");
 
+/*
+ * Logos are located in the initdata, and will be freed in kernel_init.
+ * Use late_init to mark the logos as freed to prevent any further use.
+ */
+
+static bool logos_freed;
+
+static int __init fb_logo_late_init(void)
+{
+	logos_freed = true;
+	return 0;
+}
+
+late_initcall(fb_logo_late_init);
+
 /* logo's are marked __initdata. Use __init_refok to tell
  * modpost that it is intended that this function uses data
  * marked __initdata.
@@ -29,7 +44,7 @@ const struct linux_logo * __init_refok fb_find_logo(int depth)
 {
 	const struct linux_logo *logo = NULL;
 
-	if (nologo)
+	if (nologo || logos_freed)
 		return NULL;
 
 	if (depth >= 1) {
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index c9703d4d6f6..440d78f39c0 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/balloon_compaction.h>
+#include <linux/wait.h>
 
 /*
  * Balloon device works in 4K page units.  So each page is pointed to by
@@ -290,17 +291,25 @@ static void update_balloon_size(struct virtio_balloon *vb)
 static int balloon(void *_vballoon)
 {
 	struct virtio_balloon *vb = _vballoon;
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
 	set_freezable();
 	while (!kthread_should_stop()) {
 		s64 diff;
 
 		try_to_freeze();
-		wait_event_interruptible(vb->config_change,
-					 (diff = towards_target(vb)) != 0
-					 || vb->need_stats_update
-					 || kthread_should_stop()
-					 || freezing(current));
+
+		add_wait_queue(&vb->config_change, &wait);
+		for (;;) {
+			if ((diff = towards_target(vb)) != 0 ||
+			    vb->need_stats_update ||
+			    kthread_should_stop() ||
+			    freezing(current))
+				break;
+			wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+		}
+		remove_wait_queue(&vb->config_change, &wait);
+
 		if (vb->need_stats_update)
 			stats_handle_request(vb);
 		if (diff > 0)
@@ -443,6 +452,8 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	if (err)
 		goto out_free_vb;
 
+	virtio_device_ready(vdev);
+
 	vb->thread = kthread_run(balloon, vb, "vballoon");
 	if (IS_ERR(vb->thread)) {
 		err = PTR_ERR(vb->thread);
diff --git a/drivers/w1/masters/ds2482.c b/drivers/w1/masters/ds2482.c
index e76a9b39abb..5e505d496f9 100644
--- a/drivers/w1/masters/ds2482.c
+++ b/drivers/w1/masters/ds2482.c
@@ -18,6 +18,8 @@
 #include <linux/slab.h>
 #include <linux/i2c.h>
 #include <linux/delay.h>
+#include <linux/gpio.h>
+#include <linux/platform_data/ds2482.h>
 #include <asm/delay.h>
 
 #include "../w1.h"
@@ -84,7 +86,8 @@ static const u8 ds2482_chan_rd[8] =
 static int ds2482_probe(struct i2c_client *client,
 			const struct i2c_device_id *id);
 static int ds2482_remove(struct i2c_client *client);
-
+static int ds2482_suspend(struct device *dev);
+static int ds2482_resume(struct device *dev);
 
 /**
  * Driver data (common to all clients)
@@ -94,10 +97,16 @@ static const struct i2c_device_id ds2482_id[] = {
 	{ }
 };
 
+static const struct dev_pm_ops ds2482_pm_ops = {
+	.suspend = ds2482_suspend,
+	.resume = ds2482_resume,
+};
+
 static struct i2c_driver ds2482_driver = {
 	.driver = {
 		.owner	= THIS_MODULE,
 		.name	= "ds2482",
+		.pm = &ds2482_pm_ops,
 	},
 	.probe		= ds2482_probe,
 	.remove		= ds2482_remove,
@@ -119,6 +128,7 @@ struct ds2482_w1_chan {
 struct ds2482_data {
 	struct i2c_client	*client;
 	struct mutex		access_lock;
+	int			slpz_gpio;
 
 	/* 1-wire interface(s) */
 	int			w1_count;	/* 1 or 8 */
@@ -444,11 +454,31 @@ static u8 ds2482_w1_set_pullup(void *data, int delay)
 	return retval;
 }
 
+static int ds2482_suspend(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct ds2482_data *data = i2c_get_clientdata(client);
+
+	if (data->slpz_gpio >= 0)
+		gpio_set_value(data->slpz_gpio, 0);
+	return 0;
+}
+
+static int ds2482_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct ds2482_data *data = i2c_get_clientdata(client);
+
+	if (data->slpz_gpio >= 0)
+		gpio_set_value(data->slpz_gpio, 1);
+	return 0;
+}
 
 static int ds2482_probe(struct i2c_client *client,
 			const struct i2c_device_id *id)
 {
 	struct ds2482_data *data;
+	struct ds2482_platform_data *pdata;
 	int err = -ENODEV;
 	int temp1;
 	int idx;
@@ -515,6 +545,16 @@ static int ds2482_probe(struct i2c_client *client,
 		}
 	}
 
+	pdata = client->dev.platform_data;
+	data->slpz_gpio = pdata ? pdata->slpz_gpio : -1;
+
+	if (data->slpz_gpio >= 0) {
+		err = gpio_request_one(data->slpz_gpio, GPIOF_OUT_INIT_HIGH,
+				       "ds2482.slpz");
+		if (err < 0)
+			goto exit_w1_remove;
+	}
+
 	return 0;
 
 exit_w1_remove:
@@ -539,6 +579,11 @@ static int ds2482_remove(struct i2c_client *client)
 			w1_remove_master_device(&data->w1_ch[idx].w1_bm);
 	}
 
+	if (data->slpz_gpio >= 0) {
+		gpio_set_value(data->slpz_gpio, 0);
+		gpio_free(data->slpz_gpio);
+	}
+
 	/* Free the memory */
 	kfree(data);
 	return 0;
diff --git a/drivers/w1/slaves/w1_therm.c b/drivers/w1/slaves/w1_therm.c
index 1f11a20a8ab..55eb86c9e21 100644
--- a/drivers/w1/slaves/w1_therm.c
+++ b/drivers/w1/slaves/w1_therm.c
@@ -59,16 +59,32 @@ MODULE_ALIAS("w1-family-" __stringify(W1_THERM_DS28EA00));
 static int w1_strong_pullup = 1;
 module_param_named(strong_pullup, w1_strong_pullup, int, 0);
 
+struct w1_therm_family_data {
+	uint8_t rom[9];
+	atomic_t refcnt;
+};
+
+/* return the address of the refcnt in the family data */
+#define THERM_REFCNT(family_data) \
+	(&((struct w1_therm_family_data*)family_data)->refcnt)
+
 static int w1_therm_add_slave(struct w1_slave *sl)
 {
-	sl->family_data = kzalloc(9, GFP_KERNEL);
+	sl->family_data = kzalloc(sizeof(struct w1_therm_family_data),
+		GFP_KERNEL);
 	if (!sl->family_data)
 		return -ENOMEM;
+	atomic_set(THERM_REFCNT(sl->family_data), 1);
 	return 0;
 }
 
 static void w1_therm_remove_slave(struct w1_slave *sl)
 {
+	int refcnt = atomic_sub_return(1, THERM_REFCNT(sl->family_data));
+	while(refcnt) {
+		msleep(1000);
+		refcnt = atomic_read(THERM_REFCNT(sl->family_data));
+	}
 	kfree(sl->family_data);
 	sl->family_data = NULL;
 }
@@ -194,13 +210,22 @@ static ssize_t w1_slave_show(struct device *device,
 	struct w1_slave *sl = dev_to_w1_slave(device);
 	struct w1_master *dev = sl->master;
 	u8 rom[9], crc, verdict, external_power;
-	int i, max_trying = 10;
+	int i, ret, max_trying = 10;
 	ssize_t c = PAGE_SIZE;
+	u8 *family_data = sl->family_data;
+
+	ret = mutex_lock_interruptible(&dev->bus_mutex);
+	if (ret != 0)
+		goto post_unlock;
 
-	i = mutex_lock_interruptible(&dev->bus_mutex);
-	if (i != 0)
-		return i;
+	if(!sl->family_data)
+	{
+		ret = -ENODEV;
+		goto pre_unlock;
+	}
 
+	/* prevent the slave from going away in sleep */
+	atomic_inc(THERM_REFCNT(family_data));
 	memset(rom, 0, sizeof(rom));
 
 	while (max_trying--) {
@@ -230,17 +255,19 @@ static ssize_t w1_slave_show(struct device *device,
 				mutex_unlock(&dev->bus_mutex);
 
 				sleep_rem = msleep_interruptible(tm);
-				if (sleep_rem != 0)
-					return -EINTR;
+				if (sleep_rem != 0) {
+					ret = -EINTR;
+					goto post_unlock;
+				}
 
-				i = mutex_lock_interruptible(&dev->bus_mutex);
-				if (i != 0)
-					return i;
+				ret = mutex_lock_interruptible(&dev->bus_mutex);
+				if (ret != 0)
+					goto post_unlock;
 			} else if (!w1_strong_pullup) {
 				sleep_rem = msleep_interruptible(tm);
 				if (sleep_rem != 0) {
-					mutex_unlock(&dev->bus_mutex);
-					return -EINTR;
+					ret = -EINTR;
+					goto pre_unlock;
 				}
 			}
 
@@ -269,19 +296,24 @@ static ssize_t w1_slave_show(struct device *device,
 	c -= snprintf(buf + PAGE_SIZE - c, c, ": crc=%02x %s\n",
 			   crc, (verdict) ? "YES" : "NO");
 	if (verdict)
-		memcpy(sl->family_data, rom, sizeof(rom));
+		memcpy(family_data, rom, sizeof(rom));
 	else
 		dev_warn(device, "Read failed CRC check\n");
 
 	for (i = 0; i < 9; ++i)
 		c -= snprintf(buf + PAGE_SIZE - c, c, "%02x ",
-			      ((u8 *)sl->family_data)[i]);
+			      ((u8 *)family_data)[i]);
 
 	c -= snprintf(buf + PAGE_SIZE - c, c, "t=%d\n",
 		w1_convert_temp(rom, sl->family->fid));
+	ret = PAGE_SIZE - c;
+
+pre_unlock:
 	mutex_unlock(&dev->bus_mutex);
 
-	return PAGE_SIZE - c;
+post_unlock:
+	atomic_dec(THERM_REFCNT(family_data));
+	return ret;
 }
 
 static int __init w1_therm_init(void)
diff --git a/drivers/watchdog/omap_wdt.c b/drivers/watchdog/omap_wdt.c
index 3691b157516..0c8868eceb4 100644
--- a/drivers/watchdog/omap_wdt.c
+++ b/drivers/watchdog/omap_wdt.c
@@ -132,6 +132,13 @@ static int omap_wdt_start(struct watchdog_device *wdog)
 
 	pm_runtime_get_sync(wdev->dev);
 
+	/*
+	 * Make sure the watchdog is disabled. This is unfortunately required
+	 * because writing to various registers with the watchdog running has no
+	 * effect.
+	 */
+	omap_wdt_disable(wdev);
+
 	/* initialize prescaler */
 	while (readl_relaxed(base + OMAP_WATCHDOG_WPS) & 0x01)
 		cpu_relax();
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 2140398a2a8..2ccd3592d41 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -2,7 +2,7 @@ ifeq ($(filter y, $(CONFIG_ARM) $(CONFIG_ARM64)),)
 obj-$(CONFIG_HOTPLUG_CPU)		+= cpu_hotplug.o
 endif
 obj-$(CONFIG_X86)			+= fallback.o
-obj-y	+= grant-table.o features.o balloon.o manage.o
+obj-y	+= grant-table.o features.o balloon.o manage.o preempt.o
 obj-y	+= events/
 obj-y	+= xenbus/
 
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 3860d02729d..a325814341b 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -230,6 +230,29 @@ static enum bp_state reserve_additional_memory(long credit)
 	balloon_hotplug = round_up(balloon_hotplug, PAGES_PER_SECTION);
 	nid = memory_add_physaddr_to_nid(hotplug_start_paddr);
 
+#ifdef CONFIG_XEN_HAVE_PVMMU
+        /*
+         * add_memory() will build page tables for the new memory so
+         * the p2m must contain invalid entries so the correct
+         * non-present PTEs will be written.
+         *
+         * If a failure occurs, the original (identity) p2m entries
+         * are not restored since this region is now known not to
+         * conflict with any devices.
+         */
+	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+		unsigned long pfn, i;
+
+		pfn = PFN_DOWN(hotplug_start_paddr);
+		for (i = 0; i < balloon_hotplug; i++) {
+			if (!set_phys_to_machine(pfn + i, INVALID_P2M_ENTRY)) {
+				pr_warn("set_phys_to_machine() failed, no memory added\n");
+				return BP_ECANCELED;
+			}
+                }
+	}
+#endif
+
 	rc = add_memory(nid, hotplug_start_paddr, balloon_hotplug << PAGE_SHIFT);
 
 	if (rc) {
diff --git a/drivers/xen/events/events_2l.c b/drivers/xen/events/events_2l.c
index 5db43fc100a..7dd46312c18 100644
--- a/drivers/xen/events/events_2l.c
+++ b/drivers/xen/events/events_2l.c
@@ -345,6 +345,15 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static void evtchn_2l_resume(void)
+{
+	int i;
+
+	for_each_online_cpu(i)
+		memset(per_cpu(cpu_evtchn_mask, i), 0, sizeof(xen_ulong_t) *
+				EVTCHN_2L_NR_CHANNELS/BITS_PER_EVTCHN_WORD);
+}
+
 static const struct evtchn_ops evtchn_ops_2l = {
 	.max_channels      = evtchn_2l_max_channels,
 	.nr_channels       = evtchn_2l_max_channels,
@@ -356,6 +365,7 @@ static const struct evtchn_ops evtchn_ops_2l = {
 	.mask              = evtchn_2l_mask,
 	.unmask            = evtchn_2l_unmask,
 	.handle_events     = evtchn_2l_handle_events,
+	.resume	           = evtchn_2l_resume,
 };
 
 void __init xen_evtchn_2l_init(void)
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index b4bca2d4a7e..38387950490 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -526,20 +526,26 @@ static unsigned int __startup_pirq(unsigned int irq)
 	pirq_query_unmask(irq);
 
 	rc = set_evtchn_to_irq(evtchn, irq);
-	if (rc != 0) {
-		pr_err("irq%d: Failed to set port to irq mapping (%d)\n",
-		       irq, rc);
-		xen_evtchn_close(evtchn);
-		return 0;
-	}
-	bind_evtchn_to_cpu(evtchn, 0);
+	if (rc)
+		goto err;
+
 	info->evtchn = evtchn;
+	bind_evtchn_to_cpu(evtchn, 0);
+
+	rc = xen_evtchn_port_setup(info);
+	if (rc)
+		goto err;
 
 out:
 	unmask_evtchn(evtchn);
 	eoi_pirq(irq_get_irq_data(irq));
 
 	return 0;
+
+err:
+	pr_err("irq%d: Failed to set port to irq mapping (%d)\n", irq, rc);
+	xen_evtchn_close(evtchn);
+	return 0;
 }
 
 static unsigned int startup_pirq(struct irq_data *data)
@@ -951,7 +957,7 @@ unsigned xen_evtchn_nr_channels(void)
 }
 EXPORT_SYMBOL_GPL(xen_evtchn_nr_channels);
 
-int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
+int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu)
 {
 	struct evtchn_bind_virq bind_virq;
 	int evtchn, irq, ret;
@@ -965,8 +971,12 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
 		if (irq < 0)
 			goto out;
 
-		irq_set_chip_and_handler_name(irq, &xen_percpu_chip,
-					      handle_percpu_irq, "virq");
+		if (percpu)
+			irq_set_chip_and_handler_name(irq, &xen_percpu_chip,
+						      handle_percpu_irq, "virq");
+		else
+			irq_set_chip_and_handler_name(irq, &xen_dynamic_chip,
+						      handle_edge_irq, "virq");
 
 		bind_virq.virq = virq;
 		bind_virq.vcpu = cpu;
@@ -1056,7 +1066,7 @@ int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu,
 {
 	int irq, retval;
 
-	irq = bind_virq_to_irq(virq, cpu);
+	irq = bind_virq_to_irq(virq, cpu, irqflags & IRQF_PERCPU);
 	if (irq < 0)
 		return irq;
 	retval = request_irq(irq, handler, irqflags, devname, dev_id);
@@ -1273,8 +1283,9 @@ void rebind_evtchn_irq(int evtchn, int irq)
 
 	mutex_unlock(&irq_mapping_update_lock);
 
-	/* new event channels are always bound to cpu 0 */
-	irq_set_affinity(irq, cpumask_of(0));
+        bind_evtchn_to_cpu(evtchn, info->cpu);
+	/* This will be deferred until interrupt is processed */
+	irq_set_affinity(irq, cpumask_of(info->cpu));
 
 	/* Unmask the event channel. */
 	enable_irq(irq);
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index f8bb36f9d9c..bf194070642 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -105,10 +105,16 @@ static void do_suspend(void)
 
 	err = freeze_processes();
 	if (err) {
-		pr_err("%s: freeze failed %d\n", __func__, err);
+		pr_err("%s: freeze processes failed %d\n", __func__, err);
 		goto out;
 	}
 
+	err = freeze_kernel_threads();
+	if (err) {
+		pr_err("%s: freeze kernel threads failed %d\n", __func__, err);
+		goto out_thaw;
+	}
+
 	err = dpm_suspend_start(PMSG_FREEZE);
 	if (err) {
 		pr_err("%s: dpm_suspend_start %d\n", __func__, err);
diff --git a/drivers/xen/preempt.c b/drivers/xen/preempt.c
new file mode 100644
index 00000000000..a1800c15083
--- /dev/null
+++ b/drivers/xen/preempt.c
@@ -0,0 +1,44 @@
+/*
+ * Preemptible hypercalls
+ *
+ * Copyright (C) 2014 Citrix Systems R&D ltd.
+ *
+ * This source code is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ */
+
+#include <linux/sched.h>
+#include <xen/xen-ops.h>
+
+#ifndef CONFIG_PREEMPT
+
+/*
+ * Some hypercalls issued by the toolstack can take many 10s of
+ * seconds. Allow tasks running hypercalls via the privcmd driver to
+ * be voluntarily preempted even if full kernel preemption is
+ * disabled.
+ *
+ * Such preemptible hypercalls are bracketed by
+ * xen_preemptible_hcall_begin() and xen_preemptible_hcall_end()
+ * calls.
+ */
+
+DEFINE_PER_CPU(bool, xen_in_preemptible_hcall);
+EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall);
+
+asmlinkage __visible void xen_maybe_preempt_hcall(void)
+{
+	if (unlikely(__this_cpu_read(xen_in_preemptible_hcall)
+		     && should_resched())) {
+		/*
+		 * Clear flag as we may be rescheduled on a different
+		 * cpu.
+		 */
+		__this_cpu_write(xen_in_preemptible_hcall, false);
+		_cond_resched();
+		__this_cpu_write(xen_in_preemptible_hcall, true);
+	}
+}
+#endif /* CONFIG_PREEMPT */
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 569a13b9e85..59ac71c4a04 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -56,10 +56,12 @@ static long privcmd_ioctl_hypercall(void __user *udata)
 	if (copy_from_user(&hypercall, udata, sizeof(hypercall)))
 		return -EFAULT;
 
+	xen_preemptible_hcall_begin();
 	ret = privcmd_call(hypercall.op,
 			   hypercall.arg[0], hypercall.arg[1],
 			   hypercall.arg[2], hypercall.arg[3],
 			   hypercall.arg[4]);
+	xen_preemptible_hcall_end();
 
 	return ret;
 }
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index ebd8f218a78..c9d0d5a0e66 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -96,8 +96,6 @@ static inline phys_addr_t xen_bus_to_phys(dma_addr_t baddr)
 	dma_addr_t dma = (dma_addr_t)pfn << PAGE_SHIFT;
 	phys_addr_t paddr = dma;
 
-	BUG_ON(paddr != dma); /* truncation has occurred, should never happen */
-
 	paddr |= baddr & ~PAGE_MASK;
 
 	return paddr;
@@ -399,7 +397,9 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 * buffering it.
 	 */
 	if (dma_capable(dev, dev_addr, size) &&
-	    !range_straddles_page_boundary(phys, size) && !swiotlb_force) {
+	    !range_straddles_page_boundary(phys, size) &&
+		!xen_arch_need_swiotlb(dev, PFN_DOWN(phys), PFN_DOWN(dev_addr)) &&
+		!swiotlb_force) {
 		/* we are not interested in the dma_addr returned by
 		 * xen_dma_map_page, only in the potential cache flushes executed
 		 * by the function. */
@@ -447,7 +447,7 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
 
 	BUG_ON(dir == DMA_NONE);
 
-	xen_dma_unmap_page(hwdev, paddr, size, dir, attrs);
+	xen_dma_unmap_page(hwdev, dev_addr, size, dir, attrs);
 
 	/* NOTE: We use dev_addr here, not paddr! */
 	if (is_xen_swiotlb_buffer(dev_addr)) {
@@ -495,14 +495,14 @@ xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 	BUG_ON(dir == DMA_NONE);
 
 	if (target == SYNC_FOR_CPU)
-		xen_dma_sync_single_for_cpu(hwdev, paddr, size, dir);
+		xen_dma_sync_single_for_cpu(hwdev, dev_addr, size, dir);
 
 	/* NOTE: We use dev_addr here, not paddr! */
 	if (is_xen_swiotlb_buffer(dev_addr))
 		swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
 
 	if (target == SYNC_FOR_DEVICE)
-		xen_dma_sync_single_for_cpu(hwdev, paddr, size, dir);
+		xen_dma_sync_single_for_device(hwdev, dev_addr, size, dir);
 
 	if (dir != DMA_FROM_DEVICE)
 		return;
@@ -557,6 +557,7 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 		dma_addr_t dev_addr = xen_phys_to_bus(paddr);
 
 		if (swiotlb_force ||
+		    xen_arch_need_swiotlb(hwdev, PFN_DOWN(paddr), PFN_DOWN(dev_addr)) ||
 		    !dma_capable(hwdev, dev_addr, sg->length) ||
 		    range_straddles_page_boundary(paddr, sg->length)) {
 			phys_addr_t map = swiotlb_tbl_map_single(hwdev,
diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c
index 46ae0f9f02a..9c234209d8b 100644
--- a/drivers/xen/xen-pciback/conf_space.c
+++ b/drivers/xen/xen-pciback/conf_space.c
@@ -16,8 +16,8 @@
 #include "conf_space.h"
 #include "conf_space_quirks.h"
 
-static bool permissive;
-module_param(permissive, bool, 0644);
+bool xen_pcibk_permissive;
+module_param_named(permissive, xen_pcibk_permissive, bool, 0644);
 
 /* This is where xen_pcibk_read_config_byte, xen_pcibk_read_config_word,
  * xen_pcibk_write_config_word, and xen_pcibk_write_config_byte are created. */
@@ -262,7 +262,7 @@ int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value)
 		 * This means that some fields may still be read-only because
 		 * they have entries in the config_field list that intercept
 		 * the write and do nothing. */
-		if (dev_data->permissive || permissive) {
+		if (dev_data->permissive || xen_pcibk_permissive) {
 			switch (size) {
 			case 1:
 				err = pci_write_config_byte(dev, offset,
diff --git a/drivers/xen/xen-pciback/conf_space.h b/drivers/xen/xen-pciback/conf_space.h
index e56c934ad13..62461a8ba1d 100644
--- a/drivers/xen/xen-pciback/conf_space.h
+++ b/drivers/xen/xen-pciback/conf_space.h
@@ -64,6 +64,8 @@ struct config_field_entry {
 	void *data;
 };
 
+extern bool xen_pcibk_permissive;
+
 #define OFFSET(cfg_entry) ((cfg_entry)->base_offset+(cfg_entry)->field->offset)
 
 /* Add fields to a device - the add_fields macro expects to get a pointer to
diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c
index c5ee82587e8..f8baf463dd3 100644
--- a/drivers/xen/xen-pciback/conf_space_header.c
+++ b/drivers/xen/xen-pciback/conf_space_header.c
@@ -11,6 +11,10 @@
 #include "pciback.h"
 #include "conf_space.h"
 
+struct pci_cmd_info {
+	u16 val;
+};
+
 struct pci_bar_info {
 	u32 val;
 	u32 len_val;
@@ -20,22 +24,36 @@ struct pci_bar_info {
 #define is_enable_cmd(value) ((value)&(PCI_COMMAND_MEMORY|PCI_COMMAND_IO))
 #define is_master_cmd(value) ((value)&PCI_COMMAND_MASTER)
 
-static int command_read(struct pci_dev *dev, int offset, u16 *value, void *data)
+/* Bits guests are allowed to control in permissive mode. */
+#define PCI_COMMAND_GUEST (PCI_COMMAND_MASTER|PCI_COMMAND_SPECIAL| \
+			   PCI_COMMAND_INVALIDATE|PCI_COMMAND_VGA_PALETTE| \
+			   PCI_COMMAND_WAIT|PCI_COMMAND_FAST_BACK)
+
+static void *command_init(struct pci_dev *dev, int offset)
 {
-	int i;
-	int ret;
-
-	ret = xen_pcibk_read_config_word(dev, offset, value, data);
-	if (!pci_is_enabled(dev))
-		return ret;
-
-	for (i = 0; i < PCI_ROM_RESOURCE; i++) {
-		if (dev->resource[i].flags & IORESOURCE_IO)
-			*value |= PCI_COMMAND_IO;
-		if (dev->resource[i].flags & IORESOURCE_MEM)
-			*value |= PCI_COMMAND_MEMORY;
+	struct pci_cmd_info *cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
+	int err;
+
+	if (!cmd)
+		return ERR_PTR(-ENOMEM);
+
+	err = pci_read_config_word(dev, PCI_COMMAND, &cmd->val);
+	if (err) {
+		kfree(cmd);
+		return ERR_PTR(err);
 	}
 
+	return cmd;
+}
+
+static int command_read(struct pci_dev *dev, int offset, u16 *value, void *data)
+{
+	int ret = pci_read_config_word(dev, offset, value);
+	const struct pci_cmd_info *cmd = data;
+
+	*value &= PCI_COMMAND_GUEST;
+	*value |= cmd->val & ~PCI_COMMAND_GUEST;
+
 	return ret;
 }
 
@@ -43,6 +61,8 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data)
 {
 	struct xen_pcibk_dev_data *dev_data;
 	int err;
+	u16 val;
+	struct pci_cmd_info *cmd = data;
 
 	dev_data = pci_get_drvdata(dev);
 	if (!pci_is_enabled(dev) && is_enable_cmd(value)) {
@@ -83,6 +103,19 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data)
 		}
 	}
 
+	cmd->val = value;
+
+	if (!xen_pcibk_permissive && (!dev_data || !dev_data->permissive))
+		return 0;
+
+	/* Only allow the guest to control certain bits. */
+	err = pci_read_config_word(dev, offset, &val);
+	if (err || val == value)
+		return err;
+
+	value &= PCI_COMMAND_GUEST;
+	value |= val & ~PCI_COMMAND_GUEST;
+
 	return pci_write_config_word(dev, offset, value);
 }
 
@@ -282,6 +315,8 @@ static const struct config_field header_common[] = {
 	{
 	 .offset    = PCI_COMMAND,
 	 .size      = 2,
+	 .init      = command_init,
+	 .release   = bar_release,
 	 .u.w.read  = command_read,
 	 .u.w.write = command_write,
 	},
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index 3e32146472a..d30c6b24634 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -712,12 +712,11 @@ static int prepare_pending_reqs(struct vscsibk_info *info,
 static int scsiback_do_cmd_fn(struct vscsibk_info *info)
 {
 	struct vscsiif_back_ring *ring = &info->ring;
-	struct vscsiif_request *ring_req;
+	struct vscsiif_request ring_req;
 	struct vscsibk_pend *pending_req;
 	RING_IDX rc, rp;
 	int err, more_to_do;
 	uint32_t result;
-	uint8_t act;
 
 	rc = ring->req_cons;
 	rp = ring->sring->req_prod;
@@ -738,11 +737,10 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info)
 		if (!pending_req)
 			return 1;
 
-		ring_req = RING_GET_REQUEST(ring, rc);
+		ring_req = *RING_GET_REQUEST(ring, rc);
 		ring->req_cons = ++rc;
 
-		act = ring_req->act;
-		err = prepare_pending_reqs(info, ring_req, pending_req);
+		err = prepare_pending_reqs(info, &ring_req, pending_req);
 		if (err) {
 			switch (err) {
 			case -ENODEV:
@@ -758,9 +756,9 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info)
 			return 1;
 		}
 
-		switch (act) {
+		switch (ring_req.act) {
 		case VSCSIIF_ACT_SCSI_CDB:
-			if (scsiback_gnttab_data_map(ring_req, pending_req)) {
+			if (scsiback_gnttab_data_map(&ring_req, pending_req)) {
 				scsiback_fast_flush_area(pending_req);
 				scsiback_do_resp_with_sense(NULL,
 					DRIVER_ERROR << 24, 0, pending_req);
@@ -771,7 +769,7 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info)
 			break;
 		case VSCSIIF_ACT_SCSI_ABORT:
 			scsiback_device_action(pending_req, TMR_ABORT_TASK,
-				ring_req->ref_rqid);
+				ring_req.ref_rqid);
 			break;
 		case VSCSIIF_ACT_SCSI_RESET:
 			scsiback_device_action(pending_req, TMR_LUN_RESET, 0);
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 564b3158486..5390a674b5e 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -57,6 +57,7 @@
 #include <xen/xen.h>
 #include <xen/xenbus.h>
 #include <xen/events.h>
+#include <xen/xen-ops.h>
 #include <xen/page.h>
 
 #include <xen/hvm.h>
@@ -735,6 +736,30 @@ static int __init xenstored_local_init(void)
 	return err;
 }
 
+static int xenbus_resume_cb(struct notifier_block *nb,
+			    unsigned long action, void *data)
+{
+	int err = 0;
+
+	if (xen_hvm_domain()) {
+		uint64_t v;
+
+		err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v);
+		if (!err && v)
+			xen_store_evtchn = v;
+		else
+			pr_warn("Cannot update xenstore event channel: %d\n",
+				err);
+	} else
+		xen_store_evtchn = xen_start_info->store_evtchn;
+
+	return err;
+}
+
+static struct notifier_block xenbus_resume_nb = {
+	.notifier_call = xenbus_resume_cb,
+};
+
 static int __init xenbus_init(void)
 {
 	int err = 0;
@@ -793,6 +818,10 @@ static int __init xenbus_init(void)
 		goto out_error;
 	}
 
+	if ((xen_store_domain_type != XS_LOCAL) &&
+	    (xen_store_domain_type != XS_UNKNOWN))
+		xen_resume_notifier_register(&xenbus_resume_nb);
+
 #ifdef CONFIG_XEN_COMPAT_XENFS
 	/*
 	 * Create xenfs mountpoint in /proc for compatibility with
diff --git a/firmware/ihex2fw.c b/firmware/ihex2fw.c
index cf38e159131..08d90e25abf 100644
--- a/firmware/ihex2fw.c
+++ b/firmware/ihex2fw.c
@@ -86,6 +86,7 @@ int main(int argc, char **argv)
 		case 'j':
 			include_jump = 1;
 			break;
+		default:
 			return usage();
 		}
 	}
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 296482fc77a..a2f6e9ae1a9 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -540,8 +540,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb,
 	unlock_new_inode(inode);
 	return inode;
 error:
-	unlock_new_inode(inode);
-	iput(inode);
+	iget_failed(inode);
 	return ERR_PTR(retval);
 
 }
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 02b64f4e576..092d20c643e 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -149,8 +149,7 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb,
 	unlock_new_inode(inode);
 	return inode;
 error:
-	unlock_new_inode(inode);
-	iput(inode);
+	iget_failed(inode);
 	return ERR_PTR(retval);
 
 }
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index abc853968fe..937ce8754b2 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -125,7 +125,7 @@ affs_fix_dcache(struct inode *inode, u32 entry_ino)
 {
 	struct dentry *dentry;
 	spin_lock(&inode->i_lock);
-	hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
 		if (entry_ino == (u32)(long)dentry->d_fsdata) {
 			dentry->d_fsdata = (void *)inode->i_ino;
 			break;
diff --git a/fs/aio.c b/fs/aio.c
index 14b93159ef8..58caa7e5d81 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -715,6 +715,9 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 err_cleanup:
 	aio_nr_sub(ctx->max_reqs);
 err_ctx:
+	atomic_set(&ctx->dead, 1);
+	if (ctx->mmap_size)
+		vm_munmap(ctx->mmap_base, ctx->mmap_size);
 	aio_free_ring(ctx);
 err:
 	mutex_unlock(&ctx->ring_lock);
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index aaf96cb2545..ac7d921ed98 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -95,7 +95,7 @@ static int check_dev_ioctl_version(int cmd, struct autofs_dev_ioctl *param)
  */
 static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *in)
 {
-	struct autofs_dev_ioctl tmp;
+	struct autofs_dev_ioctl tmp, *res;
 
 	if (copy_from_user(&tmp, in, sizeof(tmp)))
 		return ERR_PTR(-EFAULT);
@@ -106,7 +106,11 @@ static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *i
 	if (tmp.size > (PATH_MAX + sizeof(tmp)))
 		return ERR_PTR(-ENAMETOOLONG);
 
-	return memdup_user(in, tmp.size);
+	res = memdup_user(in, tmp.size);
+	if (!IS_ERR(res))
+		res->size = tmp.size;
+
+	return res;
 }
 
 static inline void free_dev_ioctl(struct autofs_dev_ioctl *param)
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 683a5b9ce22..dcdec6fd33c 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -85,7 +85,7 @@ static struct dentry *get_next_positive_subdir(struct dentry *prev,
 	spin_lock(&root->d_lock);
 
 	if (prev)
-		next = prev->d_u.d_child.next;
+		next = prev->d_child.next;
 	else {
 		prev = dget_dlock(root);
 		next = prev->d_subdirs.next;
@@ -99,13 +99,13 @@ cont:
 		return NULL;
 	}
 
-	q = list_entry(next, struct dentry, d_u.d_child);
+	q = list_entry(next, struct dentry, d_child);
 
 	spin_lock_nested(&q->d_lock, DENTRY_D_LOCK_NESTED);
 	/* Already gone or negative dentry (under construction) - try next */
 	if (!d_count(q) || !simple_positive(q)) {
 		spin_unlock(&q->d_lock);
-		next = q->d_u.d_child.next;
+		next = q->d_child.next;
 		goto cont;
 	}
 	dget_dlock(q);
@@ -155,13 +155,13 @@ again:
 				goto relock;
 			}
 			spin_unlock(&p->d_lock);
-			next = p->d_u.d_child.next;
+			next = p->d_child.next;
 			p = parent;
 			if (next != &parent->d_subdirs)
 				break;
 		}
 	}
-	ret = list_entry(next, struct dentry, d_u.d_child);
+	ret = list_entry(next, struct dentry, d_child);
 
 	spin_lock_nested(&ret->d_lock, DENTRY_D_LOCK_NESTED);
 	/* Negative dentry - try next */
@@ -489,7 +489,7 @@ found:
 	spin_lock(&sbi->lookup_lock);
 	spin_lock(&expired->d_parent->d_lock);
 	spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED);
-	list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child);
+	list_move(&expired->d_parent->d_subdirs, &expired->d_child);
 	spin_unlock(&expired->d_lock);
 	spin_unlock(&expired->d_parent->d_lock);
 	spin_unlock(&sbi->lookup_lock);
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index d76d083f2f0..0822c9eacc5 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -687,7 +687,7 @@ static void autofs_clear_leaf_automount_flags(struct dentry *dentry)
 	/* only consider parents below dentrys in the root */
 	if (IS_ROOT(parent->d_parent))
 		return;
-	d_child = &dentry->d_u.d_child;
+	d_child = &dentry->d_child;
 	/* Set parent managed if it's becoming empty */
 	if (d_child->next == &parent->d_subdirs &&
 	    d_child->prev == &parent->d_subdirs)
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index d8fc0605b9d..e39fe28f1ea 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -554,11 +554,12 @@ out:
 
 static unsigned long randomize_stack_top(unsigned long stack_top)
 {
-	unsigned int random_variable = 0;
+	unsigned long random_variable = 0;
 
 	if ((current->flags & PF_RANDOMIZE) &&
 		!(current->personality & ADDR_NO_RANDOMIZE)) {
-		random_variable = get_random_int() & STACK_RND_MASK;
+		random_variable = (unsigned long) get_random_int();
+		random_variable &= STACK_RND_MASK;
 		random_variable <<= PAGE_SHIFT;
 	}
 #ifdef CONFIG_STACK_GROWSUP
@@ -749,6 +750,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	    i < loc->elf_ex.e_phnum; i++, elf_ppnt++) {
 		int elf_prot = 0, elf_flags;
 		unsigned long k, vaddr;
+		unsigned long total_size = 0;
 
 		if (elf_ppnt->p_type != PT_LOAD)
 			continue;
@@ -811,10 +813,16 @@ static int load_elf_binary(struct linux_binprm *bprm)
 #else
 			load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
 #endif
+			total_size = total_mapping_size(elf_phdata,
+							loc->elf_ex.e_phnum);
+			if (!total_size) {
+				retval = -EINVAL;
+				goto out_free_dentry;
+			}
 		}
 
 		error = elf_map(bprm->file, load_bias + vaddr, elf_ppnt,
-				elf_prot, elf_flags, 0);
+				elf_prot, elf_flags, total_size);
 		if (BAD_ADDR(error)) {
 			retval = IS_ERR((void *)error) ?
 				PTR_ERR((void*)error) : -EINVAL;
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 150822ee0a0..f54511dd287 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -2609,32 +2609,23 @@ static int key_search(struct extent_buffer *b, struct btrfs_key *key,
 	return 0;
 }
 
-int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *found_path,
+int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path,
 		u64 iobjectid, u64 ioff, u8 key_type,
 		struct btrfs_key *found_key)
 {
 	int ret;
 	struct btrfs_key key;
 	struct extent_buffer *eb;
-	struct btrfs_path *path;
+
+	ASSERT(path);
 
 	key.type = key_type;
 	key.objectid = iobjectid;
 	key.offset = ioff;
 
-	if (found_path == NULL) {
-		path = btrfs_alloc_path();
-		if (!path)
-			return -ENOMEM;
-	} else
-		path = found_path;
-
 	ret = btrfs_search_slot(NULL, fs_root, &key, path, 0, 0);
-	if ((ret < 0) || (found_key == NULL)) {
-		if (path != found_path)
-			btrfs_free_path(path);
+	if ((ret < 0) || (found_key == NULL))
 		return ret;
-	}
 
 	eb = path->nodes[0];
 	if (ret && path->slots[0] >= btrfs_header_nritems(eb)) {
@@ -2929,7 +2920,7 @@ done:
 	 */
 	if (!p->leave_spinning)
 		btrfs_set_path_blocking(p);
-	if (ret < 0)
+	if (ret < 0 && !p->skip_release_on_error)
 		btrfs_release_path(p);
 	return ret;
 }
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index fe69edda11f..ba5aec76e6f 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -607,6 +607,7 @@ struct btrfs_path {
 	unsigned int leave_spinning:1;
 	unsigned int search_commit_root:1;
 	unsigned int need_commit_sem:1;
+	unsigned int skip_release_on_error:1;
 };
 
 /*
@@ -3686,6 +3687,10 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans,
 int verify_dir_item(struct btrfs_root *root,
 		    struct extent_buffer *leaf,
 		    struct btrfs_dir_item *dir_item);
+struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root,
+						 struct btrfs_path *path,
+						 const char *name,
+						 int name_len);
 
 /* orphan.c */
 int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 054577bddaf..de4e70fb3cb 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1857,6 +1857,14 @@ int btrfs_delayed_delete_inode_ref(struct inode *inode)
 {
 	struct btrfs_delayed_node *delayed_node;
 
+	/*
+	 * we don't do delayed inode updates during log recovery because it
+	 * leads to enospc problems.  This means we also can't do
+	 * delayed inode refs
+	 */
+	if (BTRFS_I(inode)->root->fs_info->log_root_recovering)
+		return -EAGAIN;
+
 	delayed_node = btrfs_get_or_create_delayed_node(inode);
 	if (IS_ERR(delayed_node))
 		return PTR_ERR(delayed_node);
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index fc8df866e91..1752625fb4d 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -21,10 +21,6 @@
 #include "hash.h"
 #include "transaction.h"
 
-static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root,
-			      struct btrfs_path *path,
-			      const char *name, int name_len);
-
 /*
  * insert a name into a directory, doing overflow properly if there is a hash
  * collision.  data_size indicates how big the item inserted should be.  On
@@ -383,9 +379,9 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans,
  * this walks through all the entries in a dir item and finds one
  * for a specific name.
  */
-static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root,
-			      struct btrfs_path *path,
-			      const char *name, int name_len)
+struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root,
+						 struct btrfs_path *path,
+						 const char *name, int name_len)
 {
 	struct btrfs_dir_item *dir_item;
 	unsigned long name_ptr;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1bf9f897065..b1709831b1a 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1630,6 +1630,7 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
 				     bool check_ref)
 {
 	struct btrfs_root *root;
+	struct btrfs_path *path;
 	int ret;
 
 	if (location->objectid == BTRFS_ROOT_TREE_OBJECTID)
@@ -1669,8 +1670,14 @@ again:
 	if (ret)
 		goto fail;
 
-	ret = btrfs_find_item(fs_info->tree_root, NULL, BTRFS_ORPHAN_OBJECTID,
+	path = btrfs_alloc_path();
+	if (!path) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+	ret = btrfs_find_item(fs_info->tree_root, path, BTRFS_ORPHAN_OBJECTID,
 			location->objectid, BTRFS_ORPHAN_ITEM_KEY, NULL);
+	btrfs_free_path(path);
 	if (ret < 0)
 		goto fail;
 	if (ret == 0)
@@ -2496,7 +2503,7 @@ int open_ctree(struct super_block *sb,
 		features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
 
 	if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
-		printk(KERN_ERR "BTRFS: has skinny extents\n");
+		printk(KERN_INFO "BTRFS: has skinny extents\n");
 
 	/*
 	 * flag our filesystem as having big metadata blocks if
@@ -4106,12 +4113,6 @@ again:
 		if (ret)
 			break;
 
-		/* opt_discard */
-		if (btrfs_test_opt(root, DISCARD))
-			ret = btrfs_error_discard_extent(root, start,
-							 end + 1 - start,
-							 NULL);
-
 		clear_extent_dirty(unpin, start, end, GFP_NOFS);
 		btrfs_error_unpin_extent_range(root, start, end);
 		cond_resched();
@@ -4129,6 +4130,25 @@ again:
 	return 0;
 }
 
+static void btrfs_free_pending_ordered(struct btrfs_transaction *cur_trans,
+				       struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_ordered_extent *ordered;
+
+	spin_lock(&fs_info->trans_lock);
+	while (!list_empty(&cur_trans->pending_ordered)) {
+		ordered = list_first_entry(&cur_trans->pending_ordered,
+					   struct btrfs_ordered_extent,
+					   trans_list);
+		list_del_init(&ordered->trans_list);
+		spin_unlock(&fs_info->trans_lock);
+
+		btrfs_put_ordered_extent(ordered);
+		spin_lock(&fs_info->trans_lock);
+	}
+	spin_unlock(&fs_info->trans_lock);
+}
+
 void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 				   struct btrfs_root *root)
 {
@@ -4140,6 +4160,7 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 	cur_trans->state = TRANS_STATE_UNBLOCKED;
 	wake_up(&root->fs_info->transaction_wait);
 
+	btrfs_free_pending_ordered(cur_trans, root->fs_info);
 	btrfs_destroy_delayed_inodes(root);
 	btrfs_assert_delayed_root_empty(root);
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 47c1ba14108..950479f2d33 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5715,7 +5715,8 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
 	update_global_block_rsv(fs_info);
 }
 
-static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
+static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end,
+			      const bool return_free_space)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_block_group_cache *cache = NULL;
@@ -5739,7 +5740,8 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
 
 		if (start < cache->last_byte_to_unpin) {
 			len = min(len, cache->last_byte_to_unpin - start);
-			btrfs_add_free_space(cache, start, len);
+			if (return_free_space)
+				btrfs_add_free_space(cache, start, len);
 		}
 
 		start += len;
@@ -5803,7 +5805,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 						   end + 1 - start, NULL);
 
 		clear_extent_dirty(unpin, start, end, GFP_NOFS);
-		unpin_extent_range(root, start, end);
+		unpin_extent_range(root, start, end, true);
 		cond_resched();
 	}
 
@@ -6953,12 +6955,11 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root,
 		return -ENOSPC;
 	}
 
-	if (btrfs_test_opt(root, DISCARD))
-		ret = btrfs_discard_extent(root, start, len, NULL);
-
 	if (pin)
 		pin_down_extent(root, cache, start, len, 1);
 	else {
+		if (btrfs_test_opt(root, DISCARD))
+			ret = btrfs_discard_extent(root, start, len, NULL);
 		btrfs_add_free_space(cache, start, len);
 		btrfs_update_reserved_bytes(cache, len, RESERVE_FREE, delalloc);
 	}
@@ -9585,7 +9586,7 @@ out:
 
 int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
 {
-	return unpin_extent_range(root, start, end);
+	return unpin_extent_range(root, start, end, false);
 }
 
 int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 225302b39af..6a98bddd8f3 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -287,8 +287,6 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len,
 	if (!em)
 		goto out;
 
-	if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags))
-		list_move(&em->list, &tree->modified_extents);
 	em->generation = gen;
 	clear_bit(EXTENT_FLAG_PINNED, &em->flags);
 	em->mod_start = em->start;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index a18ceabd99a..5193c784431 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1803,22 +1803,10 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	mutex_unlock(&inode->i_mutex);
 
 	/*
-	 * we want to make sure fsync finds this change
-	 * but we haven't joined a transaction running right now.
-	 *
-	 * Later on, someone is sure to update the inode and get the
-	 * real transid recorded.
-	 *
-	 * We set last_trans now to the fs_info generation + 1,
-	 * this will either be one more than the running transaction
-	 * or the generation used for the next transaction if there isn't
-	 * one running right now.
-	 *
 	 * We also have to set last_sub_trans to the current log transid,
 	 * otherwise subsequent syncs to a file that's been synced in this
 	 * transaction will appear to have already occured.
 	 */
-	BTRFS_I(inode)->last_trans = root->fs_info->generation + 1;
 	BTRFS_I(inode)->last_sub_trans = root->log_transid;
 	if (num_written > 0) {
 		err = generic_write_sync(file, pos, num_written);
@@ -1954,25 +1942,37 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	atomic_inc(&root->log_batch);
 
 	/*
-	 * check the transaction that last modified this inode
-	 * and see if its already been committed
-	 */
-	if (!BTRFS_I(inode)->last_trans) {
-		mutex_unlock(&inode->i_mutex);
-		goto out;
-	}
-
-	/*
-	 * if the last transaction that changed this file was before
-	 * the current transaction, we can bail out now without any
-	 * syncing
+	 * If the last transaction that changed this file was before the current
+	 * transaction and we have the full sync flag set in our inode, we can
+	 * bail out now without any syncing.
+	 *
+	 * Note that we can't bail out if the full sync flag isn't set. This is
+	 * because when the full sync flag is set we start all ordered extents
+	 * and wait for them to fully complete - when they complete they update
+	 * the inode's last_trans field through:
+	 *
+	 *     btrfs_finish_ordered_io() ->
+	 *         btrfs_update_inode_fallback() ->
+	 *             btrfs_update_inode() ->
+	 *                 btrfs_set_inode_last_trans()
+	 *
+	 * So we are sure that last_trans is up to date and can do this check to
+	 * bail out safely. For the fast path, when the full sync flag is not
+	 * set in our inode, we can not do it because we start only our ordered
+	 * extents and don't wait for them to complete (that is when
+	 * btrfs_finish_ordered_io runs), so here at this point their last_trans
+	 * value might be less than or equals to fs_info->last_trans_committed,
+	 * and setting a speculative last_trans for an inode when a buffered
+	 * write is made (such as fs_info->generation + 1 for example) would not
+	 * be reliable since after setting the value and before fsync is called
+	 * any number of transactions can start and commit (transaction kthread
+	 * commits the current transaction periodically), and a transaction
+	 * commit does not start nor waits for ordered extents to complete.
 	 */
 	smp_mb();
 	if (btrfs_inode_in_log(inode, root->fs_info->generation) ||
-	    BTRFS_I(inode)->last_trans <=
-	    root->fs_info->last_trans_committed) {
-		BTRFS_I(inode)->last_trans = 0;
-
+	    (full_sync && BTRFS_I(inode)->last_trans <=
+	     root->fs_info->last_trans_committed)) {
 		/*
 		 * We'v had everything committed since the last time we were
 		 * modified so clear this flag in case it was set for whatever
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 83d646bd2e4..ed2de833dd1 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -271,7 +271,7 @@ void btrfs_unpin_free_ino(struct btrfs_root *root)
 		__btrfs_add_free_space(ctl, info->offset, count);
 free:
 		rb_erase(&info->offset_index, rbroot);
-		kfree(info);
+		kmem_cache_free(btrfs_free_space_cachep, info);
 	}
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d23362f4464..edaa6178b4e 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7151,7 +7151,6 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	    ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
 	     em->block_start != EXTENT_MAP_HOLE)) {
 		int type;
-		int ret;
 		u64 block_start, orig_start, orig_block_len, ram_bytes;
 
 		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 4399f0c3a4c..3d50f1ee51b 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2431,11 +2431,9 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 			"Attempt to delete subvolume %llu during send",
 			dest->root_key.objectid);
 		err = -EPERM;
-		goto out_dput;
+		goto out_unlock_inode;
 	}
 
-	d_invalidate(dentry);
-
 	down_write(&root->fs_info->subvol_sem);
 
 	err = may_destroy_subvol(dest);
@@ -2526,9 +2524,10 @@ out_up_write:
 				root_flags & ~BTRFS_ROOT_SUBVOL_DEAD);
 		spin_unlock(&dest->root_item_lock);
 	}
+out_unlock_inode:
 	mutex_unlock(&inode->i_mutex);
 	if (!err) {
-		shrink_dcache_sb(root->fs_info->sb);
+		d_invalidate(dentry);
 		btrfs_invalidate_inodes(dest);
 		d_delete(dentry);
 		ASSERT(dest->send_in_progress == 0);
@@ -2925,6 +2924,9 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 len,
 	if (src == dst)
 		return -EINVAL;
 
+	if (len == 0)
+		return 0;
+
 	btrfs_double_lock(src, loff, dst, dst_loff, len);
 
 	ret = extent_same_check_offsets(src, loff, len);
@@ -2957,7 +2959,7 @@ out_unlock:
 static long btrfs_ioctl_file_extent_same(struct file *file,
 			struct btrfs_ioctl_same_args __user *argp)
 {
-	struct btrfs_ioctl_same_args *same;
+	struct btrfs_ioctl_same_args *same = NULL;
 	struct btrfs_ioctl_same_extent_info *info;
 	struct inode *src = file_inode(file);
 	u64 off;
@@ -2987,6 +2989,7 @@ static long btrfs_ioctl_file_extent_same(struct file *file,
 
 	if (IS_ERR(same)) {
 		ret = PTR_ERR(same);
+		same = NULL;
 		goto out;
 	}
 
@@ -3057,6 +3060,7 @@ static long btrfs_ioctl_file_extent_same(struct file *file,
 
 out:
 	mnt_drop_write_file(file);
+	kfree(same);
 	return ret;
 }
 
@@ -3654,6 +3658,11 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 	if (off + len == src->i_size)
 		len = ALIGN(src->i_size, bs) - off;
 
+	if (len == 0) {
+		ret = 0;
+		goto out_unlock;
+	}
+
 	/* verify the end result is block aligned */
 	if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs) ||
 	    !IS_ALIGNED(destoff, bs))
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index ac734ec4cc2..b23d024c023 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -220,6 +220,7 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 	INIT_LIST_HEAD(&entry->work_list);
 	init_completion(&entry->completion);
 	INIT_LIST_HEAD(&entry->log_list);
+	INIT_LIST_HEAD(&entry->trans_list);
 
 	trace_btrfs_ordered_extent_add(inode, entry);
 
@@ -441,7 +442,7 @@ void btrfs_get_logged_extents(struct inode *inode,
 	spin_lock_irq(&tree->lock);
 	for (n = rb_first(&tree->tree); n; n = rb_next(n)) {
 		ordered = rb_entry(n, struct btrfs_ordered_extent, rb_node);
-		if (!list_empty(&ordered->log_list))
+		if (test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
 			continue;
 		list_add_tail(&ordered->log_list, logged_list);
 		atomic_inc(&ordered->refs);
@@ -472,7 +473,8 @@ void btrfs_submit_logged_extents(struct list_head *logged_list,
 	spin_unlock_irq(&log->log_extents_lock[index]);
 }
 
-void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid)
+void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *log, u64 transid)
 {
 	struct btrfs_ordered_extent *ordered;
 	int index = transid % 2;
@@ -497,7 +499,7 @@ void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid)
 		wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
 						   &ordered->flags));
 
-		btrfs_put_ordered_extent(ordered);
+		list_add_tail(&ordered->trans_list, &trans->ordered);
 		spin_lock_irq(&log->log_extents_lock[index]);
 	}
 	spin_unlock_irq(&log->log_extents_lock[index]);
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index d81a274d621..0124bffc775 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -71,6 +71,8 @@ struct btrfs_ordered_sum {
 				       ordered extent */
 #define BTRFS_ORDERED_TRUNCATED 9 /* Set when we have to truncate an extent */
 
+#define BTRFS_ORDERED_LOGGED 10 /* Set when we've waited on this ordered extent
+				 * in the logging code. */
 struct btrfs_ordered_extent {
 	/* logical offset in the file */
 	u64 file_offset;
@@ -121,6 +123,9 @@ struct btrfs_ordered_extent {
 	/* If we need to wait on this to be done */
 	struct list_head log_list;
 
+	/* If the transaction needs to wait on this ordered extent */
+	struct list_head trans_list;
+
 	/* used to wait for the BTRFS_ORDERED_COMPLETE bit */
 	wait_queue_head_t wait;
 
@@ -197,7 +202,8 @@ void btrfs_get_logged_extents(struct inode *inode,
 void btrfs_put_logged_extents(struct list_head *logged_list);
 void btrfs_submit_logged_extents(struct list_head *logged_list,
 				 struct btrfs_root *log);
-void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid);
+void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *log, u64 transid);
 void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid);
 int __init ordered_data_init(void);
 void ordered_data_exit(void);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 54bd91ece35..cde9c03e391 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1824,7 +1824,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bfree -= block_rsv->size >> bits;
 	spin_unlock(&block_rsv->lock);
 
-	buf->f_bavail = total_free_data;
+	buf->f_bavail = div_u64(total_free_data, factor);
 	ret = btrfs_calc_avail_data_space(fs_info->tree_root, &total_free_data);
 	if (ret) {
 		mutex_unlock(&fs_info->chunk_mutex);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index dcaae361672..63c6d05950f 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -220,6 +220,7 @@ loop:
 	INIT_LIST_HEAD(&cur_trans->pending_snapshots);
 	INIT_LIST_HEAD(&cur_trans->pending_chunks);
 	INIT_LIST_HEAD(&cur_trans->switch_commits);
+	INIT_LIST_HEAD(&cur_trans->pending_ordered);
 	list_add_tail(&cur_trans->list, &fs_info->trans_list);
 	extent_io_tree_init(&cur_trans->dirty_pages,
 			     fs_info->btree_inode->i_mapping);
@@ -488,6 +489,7 @@ again:
 	h->sync = false;
 	INIT_LIST_HEAD(&h->qgroup_ref_list);
 	INIT_LIST_HEAD(&h->new_bgs);
+	INIT_LIST_HEAD(&h->ordered);
 
 	smp_mb();
 	if (cur_trans->state >= TRANS_STATE_BLOCKED &&
@@ -719,6 +721,12 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 	if (!list_empty(&trans->new_bgs))
 		btrfs_create_pending_block_groups(trans, root);
 
+	if (!list_empty(&trans->ordered)) {
+		spin_lock(&info->trans_lock);
+		list_splice(&trans->ordered, &cur_trans->pending_ordered);
+		spin_unlock(&info->trans_lock);
+	}
+
 	trans->delayed_ref_updates = 0;
 	if (!trans->sync) {
 		must_run_delayed_refs =
@@ -1652,6 +1660,28 @@ static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info)
 		btrfs_wait_ordered_roots(fs_info, -1);
 }
 
+static inline void
+btrfs_wait_pending_ordered(struct btrfs_transaction *cur_trans,
+			   struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_ordered_extent *ordered;
+
+	spin_lock(&fs_info->trans_lock);
+	while (!list_empty(&cur_trans->pending_ordered)) {
+		ordered = list_first_entry(&cur_trans->pending_ordered,
+					   struct btrfs_ordered_extent,
+					   trans_list);
+		list_del_init(&ordered->trans_list);
+		spin_unlock(&fs_info->trans_lock);
+
+		wait_event(ordered->wait, test_bit(BTRFS_ORDERED_COMPLETE,
+						   &ordered->flags));
+		btrfs_put_ordered_extent(ordered);
+		spin_lock(&fs_info->trans_lock);
+	}
+	spin_unlock(&fs_info->trans_lock);
+}
+
 int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root)
 {
@@ -1702,6 +1732,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	}
 
 	spin_lock(&root->fs_info->trans_lock);
+	list_splice(&trans->ordered, &cur_trans->pending_ordered);
 	if (cur_trans->state >= TRANS_STATE_COMMIT_START) {
 		spin_unlock(&root->fs_info->trans_lock);
 		atomic_inc(&cur_trans->use_count);
@@ -1754,6 +1785,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
 	btrfs_wait_delalloc_flush(root->fs_info);
 
+	btrfs_wait_pending_ordered(cur_trans, root->fs_info);
+
 	btrfs_scrub_pause(root);
 	/*
 	 * Ok now we need to make sure to block out any other joins while we
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index d8f40e1a5d2..1ba9c3e0419 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -56,6 +56,7 @@ struct btrfs_transaction {
 	wait_queue_head_t commit_wait;
 	struct list_head pending_snapshots;
 	struct list_head pending_chunks;
+	struct list_head pending_ordered;
 	struct list_head switch_commits;
 	struct btrfs_delayed_ref_root delayed_refs;
 	int aborted;
@@ -105,6 +106,7 @@ struct btrfs_trans_handle {
 	 */
 	struct btrfs_root *root;
 	struct seq_list delayed_ref_elem;
+	struct list_head ordered;
 	struct list_head qgroup_ref_list;
 	struct list_head new_bgs;
 };
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 286213cec86..3b68c75ecce 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -488,8 +488,20 @@ insert:
 		src_item = (struct btrfs_inode_item *)src_ptr;
 		dst_item = (struct btrfs_inode_item *)dst_ptr;
 
-		if (btrfs_inode_generation(eb, src_item) == 0)
+		if (btrfs_inode_generation(eb, src_item) == 0) {
+			struct extent_buffer *dst_eb = path->nodes[0];
+
+			if (S_ISREG(btrfs_inode_mode(eb, src_item)) &&
+			    S_ISREG(btrfs_inode_mode(dst_eb, dst_item))) {
+				struct btrfs_map_token token;
+				u64 ino_size = btrfs_inode_size(eb, src_item);
+
+				btrfs_init_map_token(&token);
+				btrfs_set_token_inode_size(dst_eb, dst_item,
+							   ino_size, &token);
+			}
 			goto no_copy;
+		}
 
 		if (overwrite_root &&
 		    S_ISDIR(btrfs_inode_mode(eb, src_item)) &&
@@ -998,7 +1010,7 @@ again:
 		base = btrfs_item_ptr_offset(leaf, path->slots[0]);
 
 		while (cur_offset < item_size) {
-			extref = (struct btrfs_inode_extref *)base + cur_offset;
+			extref = (struct btrfs_inode_extref *)(base + cur_offset);
 
 			victim_name_len = btrfs_inode_extref_name_len(leaf, extref);
 
@@ -1254,13 +1266,14 @@ out:
 }
 
 static int insert_orphan_item(struct btrfs_trans_handle *trans,
-			      struct btrfs_root *root, u64 offset)
+			      struct btrfs_root *root, u64 ino)
 {
 	int ret;
-	ret = btrfs_find_item(root, NULL, BTRFS_ORPHAN_OBJECTID,
-			offset, BTRFS_ORPHAN_ITEM_KEY, NULL);
-	if (ret > 0)
-		ret = btrfs_insert_orphan_item(trans, root, offset);
+
+	ret = btrfs_insert_orphan_item(trans, root, ino);
+	if (ret == -EEXIST)
+		ret = 0;
+
 	return ret;
 }
 
@@ -2600,9 +2613,9 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	if (atomic_read(&log_root_tree->log_commit[index2])) {
 		blk_finish_plug(&plug);
 		btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
+		btrfs_wait_logged_extents(trans, log, log_transid);
 		wait_log_commit(trans, log_root_tree,
 				root_log_ctx.log_transid);
-		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
 		ret = root_log_ctx.log_ret;
 		goto out;
@@ -2645,7 +2658,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	btrfs_wait_marked_extents(log_root_tree,
 				  &log_root_tree->dirty_log_pages,
 				  EXTENT_NEW | EXTENT_DIRTY);
-	btrfs_wait_logged_extents(log, log_transid);
+	btrfs_wait_logged_extents(trans, log, log_transid);
 
 	btrfs_set_super_log_root(root->fs_info->super_for_commit,
 				log_root_tree->node->start);
@@ -3209,7 +3222,8 @@ static int drop_objectid_items(struct btrfs_trans_handle *trans,
 static void fill_inode_item(struct btrfs_trans_handle *trans,
 			    struct extent_buffer *leaf,
 			    struct btrfs_inode_item *item,
-			    struct inode *inode, int log_inode_only)
+			    struct inode *inode, int log_inode_only,
+			    u64 logged_isize)
 {
 	struct btrfs_map_token token;
 
@@ -3222,7 +3236,7 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
 		 * to say 'update this inode with these values'
 		 */
 		btrfs_set_token_inode_generation(leaf, item, 0, &token);
-		btrfs_set_token_inode_size(leaf, item, 0, &token);
+		btrfs_set_token_inode_size(leaf, item, logged_isize, &token);
 	} else {
 		btrfs_set_token_inode_generation(leaf, item,
 						 BTRFS_I(inode)->generation,
@@ -3274,7 +3288,7 @@ static int log_inode_item(struct btrfs_trans_handle *trans,
 		return ret;
 	inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				    struct btrfs_inode_item);
-	fill_inode_item(trans, path->nodes[0], inode_item, inode, 0);
+	fill_inode_item(trans, path->nodes[0], inode_item, inode, 0, 0);
 	btrfs_release_path(path);
 	return 0;
 }
@@ -3283,7 +3297,8 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 			       struct inode *inode,
 			       struct btrfs_path *dst_path,
 			       struct btrfs_path *src_path, u64 *last_extent,
-			       int start_slot, int nr, int inode_only)
+			       int start_slot, int nr, int inode_only,
+			       u64 logged_isize)
 {
 	unsigned long src_offset;
 	unsigned long dst_offset;
@@ -3340,7 +3355,8 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 						    dst_path->slots[0],
 						    struct btrfs_inode_item);
 			fill_inode_item(trans, dst_path->nodes[0], inode_item,
-					inode, inode_only == LOG_INODE_EXISTS);
+					inode, inode_only == LOG_INODE_EXISTS,
+					logged_isize);
 		} else {
 			copy_extent_buffer(dst_path->nodes[0], src, dst_offset,
 					   src_offset, ins_sizes[i]);
@@ -3766,7 +3782,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	fi = btrfs_item_ptr(leaf, path->slots[0],
 			    struct btrfs_file_extent_item);
 
-	btrfs_set_token_file_extent_generation(leaf, fi, em->generation,
+	btrfs_set_token_file_extent_generation(leaf, fi, trans->transid,
 					       &token);
 	if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
 		btrfs_set_token_file_extent_type(leaf, fi,
@@ -3886,6 +3902,33 @@ process:
 	return ret;
 }
 
+static int logged_inode_size(struct btrfs_root *log, struct inode *inode,
+			     struct btrfs_path *path, u64 *size_ret)
+{
+	struct btrfs_key key;
+	int ret;
+
+	key.objectid = btrfs_ino(inode);
+	key.type = BTRFS_INODE_ITEM_KEY;
+	key.offset = 0;
+
+	ret = btrfs_search_slot(NULL, log, &key, path, 0, 0);
+	if (ret < 0) {
+		return ret;
+	} else if (ret > 0) {
+		*size_ret = i_size_read(inode);
+	} else {
+		struct btrfs_inode_item *item;
+
+		item = btrfs_item_ptr(path->nodes[0], path->slots[0],
+				      struct btrfs_inode_item);
+		*size_ret = btrfs_inode_size(path->nodes[0], item);
+	}
+
+	btrfs_release_path(path);
+	return 0;
+}
+
 /* log a single inode in the tree log.
  * At least one parent directory for this inode must exist in the tree
  * or be logged already.
@@ -3923,6 +3966,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	bool fast_search = false;
 	u64 ino = btrfs_ino(inode);
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+	u64 logged_isize = 0;
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -3976,6 +4020,25 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 			max_key_type = BTRFS_XATTR_ITEM_KEY;
 		ret = drop_objectid_items(trans, log, path, ino, max_key_type);
 	} else {
+		if (inode_only == LOG_INODE_EXISTS) {
+			/*
+			 * Make sure the new inode item we write to the log has
+			 * the same isize as the current one (if it exists).
+			 * This is necessary to prevent data loss after log
+			 * replay, and also to prevent doing a wrong expanding
+			 * truncate - for e.g. create file, write 4K into offset
+			 * 0, fsync, write 4K into offset 4096, add hard link,
+			 * fsync some other file (to sync log), power fail - if
+			 * we use the inode's current i_size, after log replay
+			 * we get a 8Kb file, with the last 4Kb extent as a hole
+			 * (zeroes), as if an expanding truncate happened,
+			 * instead of getting a file of 4Kb only.
+			 */
+			err = logged_inode_size(log, inode, path,
+						&logged_isize);
+			if (err)
+				goto out_unlock;
+		}
 		if (test_and_clear_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
 				       &BTRFS_I(inode)->runtime_flags)) {
 			clear_bit(BTRFS_INODE_COPY_EVERYTHING,
@@ -4031,7 +4094,8 @@ again:
 		}
 
 		ret = copy_items(trans, inode, dst_path, path, &last_extent,
-				 ins_start_slot, ins_nr, inode_only);
+				 ins_start_slot, ins_nr, inode_only,
+				 logged_isize);
 		if (ret < 0) {
 			err = ret;
 			goto out_unlock;
@@ -4055,7 +4119,7 @@ next_slot:
 		if (ins_nr) {
 			ret = copy_items(trans, inode, dst_path, path,
 					 &last_extent, ins_start_slot,
-					 ins_nr, inode_only);
+					 ins_nr, inode_only, logged_isize);
 			if (ret < 0) {
 				err = ret;
 				goto out_unlock;
@@ -4076,7 +4140,8 @@ next_slot:
 	}
 	if (ins_nr) {
 		ret = copy_items(trans, inode, dst_path, path, &last_extent,
-				 ins_start_slot, ins_nr, inode_only);
+				 ins_start_slot, ins_nr, inode_only,
+				 logged_isize);
 		if (ret < 0) {
 			err = ret;
 			goto out_unlock;
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index dcf20131fbe..01bad724b5f 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -29,6 +29,7 @@
 #include "xattr.h"
 #include "disk-io.h"
 #include "props.h"
+#include "locking.h"
 
 
 ssize_t __btrfs_getxattr(struct inode *inode, const char *name,
@@ -91,7 +92,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 		       struct inode *inode, const char *name,
 		       const void *value, size_t size, int flags)
 {
-	struct btrfs_dir_item *di;
+	struct btrfs_dir_item *di = NULL;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_path *path;
 	size_t name_len = strlen(name);
@@ -103,84 +104,119 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
+	path->skip_release_on_error = 1;
+
+	if (!value) {
+		di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode),
+					name, name_len, -1);
+		if (!di && (flags & XATTR_REPLACE))
+			ret = -ENODATA;
+		else if (di)
+			ret = btrfs_delete_one_dir_name(trans, root, path, di);
+		goto out;
+	}
 
+	/*
+	 * For a replace we can't just do the insert blindly.
+	 * Do a lookup first (read-only btrfs_search_slot), and return if xattr
+	 * doesn't exist. If it exists, fall down below to the insert/replace
+	 * path - we can't race with a concurrent xattr delete, because the VFS
+	 * locks the inode's i_mutex before calling setxattr or removexattr.
+	 */
 	if (flags & XATTR_REPLACE) {
-		di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), name,
-					name_len, -1);
-		if (IS_ERR(di)) {
-			ret = PTR_ERR(di);
-			goto out;
-		} else if (!di) {
+		ASSERT(mutex_is_locked(&inode->i_mutex));
+		di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode),
+					name, name_len, 0);
+		if (!di) {
 			ret = -ENODATA;
 			goto out;
 		}
-		ret = btrfs_delete_one_dir_name(trans, root, path, di);
-		if (ret)
-			goto out;
 		btrfs_release_path(path);
+		di = NULL;
+	}
 
+	ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode),
+				      name, name_len, value, size);
+	if (ret == -EOVERFLOW) {
 		/*
-		 * remove the attribute
+		 * We have an existing item in a leaf, split_leaf couldn't
+		 * expand it. That item might have or not a dir_item that
+		 * matches our target xattr, so lets check.
 		 */
-		if (!value)
-			goto out;
-	} else {
-		di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode),
-					name, name_len, 0);
-		if (IS_ERR(di)) {
-			ret = PTR_ERR(di);
+		ret = 0;
+		btrfs_assert_tree_locked(path->nodes[0]);
+		di = btrfs_match_dir_item_name(root, path, name, name_len);
+		if (!di && !(flags & XATTR_REPLACE)) {
+			ret = -ENOSPC;
 			goto out;
 		}
-		if (!di && !value)
-			goto out;
-		btrfs_release_path(path);
+	} else if (ret == -EEXIST) {
+		ret = 0;
+		di = btrfs_match_dir_item_name(root, path, name, name_len);
+		ASSERT(di); /* logic error */
+	} else if (ret) {
+		goto out;
 	}
 
-again:
-	ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode),
-				      name, name_len, value, size);
-	/*
-	 * If we're setting an xattr to a new value but the new value is say
-	 * exactly BTRFS_MAX_XATTR_SIZE, we could end up with EOVERFLOW getting
-	 * back from split_leaf.  This is because it thinks we'll be extending
-	 * the existing item size, but we're asking for enough space to add the
-	 * item itself.  So if we get EOVERFLOW just set ret to EEXIST and let
-	 * the rest of the function figure it out.
-	 */
-	if (ret == -EOVERFLOW)
+	if (di && (flags & XATTR_CREATE)) {
 		ret = -EEXIST;
+		goto out;
+	}
 
-	if (ret == -EEXIST) {
-		if (flags & XATTR_CREATE)
-			goto out;
+	if (di) {
 		/*
-		 * We can't use the path we already have since we won't have the
-		 * proper locking for a delete, so release the path and
-		 * re-lookup to delete the thing.
+		 * We're doing a replace, and it must be atomic, that is, at
+		 * any point in time we have either the old or the new xattr
+		 * value in the tree. We don't want readers (getxattr and
+		 * listxattrs) to miss a value, this is specially important
+		 * for ACLs.
 		 */
-		btrfs_release_path(path);
-		di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode),
-					name, name_len, -1);
-		if (IS_ERR(di)) {
-			ret = PTR_ERR(di);
-			goto out;
-		} else if (!di) {
-			/* Shouldn't happen but just in case... */
-			btrfs_release_path(path);
-			goto again;
+		const int slot = path->slots[0];
+		struct extent_buffer *leaf = path->nodes[0];
+		const u16 old_data_len = btrfs_dir_data_len(leaf, di);
+		const u32 item_size = btrfs_item_size_nr(leaf, slot);
+		const u32 data_size = sizeof(*di) + name_len + size;
+		struct btrfs_item *item;
+		unsigned long data_ptr;
+		char *ptr;
+
+		if (size > old_data_len) {
+			if (btrfs_leaf_free_space(root, leaf) <
+			    (size - old_data_len)) {
+				ret = -ENOSPC;
+				goto out;
+			}
 		}
 
-		ret = btrfs_delete_one_dir_name(trans, root, path, di);
-		if (ret)
-			goto out;
+		if (old_data_len + name_len + sizeof(*di) == item_size) {
+			/* No other xattrs packed in the same leaf item. */
+			if (size > old_data_len)
+				btrfs_extend_item(root, path,
+						  size - old_data_len);
+			else if (size < old_data_len)
+				btrfs_truncate_item(root, path, data_size, 1);
+		} else {
+			/* There are other xattrs packed in the same item. */
+			ret = btrfs_delete_one_dir_name(trans, root, path, di);
+			if (ret)
+				goto out;
+			btrfs_extend_item(root, path, data_size);
+		}
 
+		item = btrfs_item_nr(slot);
+		ptr = btrfs_item_ptr(leaf, slot, char);
+		ptr += btrfs_item_size(leaf, item) - data_size;
+		di = (struct btrfs_dir_item *)ptr;
+		btrfs_set_dir_data_len(leaf, di, size);
+		data_ptr = ((unsigned long)(di + 1)) + name_len;
+		write_extent_buffer(leaf, value, data_ptr, size);
+		btrfs_mark_buffer_dirty(leaf);
+	} else {
 		/*
-		 * We have a value to set, so go back and try to insert it now.
+		 * Insert, and we had space for the xattr, so path->slots[0] is
+		 * where our xattr dir_item is and btrfs_insert_xattr_item()
+		 * filled it.
 		 */
-		if (value) {
-			btrfs_release_path(path);
-			goto again;
-		}
 	}
 out:
 	btrfs_free_path(path);
@@ -324,22 +360,42 @@ const struct xattr_handler *btrfs_xattr_handlers[] = {
 /*
  * Check if the attribute is in a supported namespace.
  *
- * This applied after the check for the synthetic attributes in the system
+ * This is applied after the check for the synthetic attributes in the system
  * namespace.
  */
-static bool btrfs_is_valid_xattr(const char *name)
+static int btrfs_is_valid_xattr(const char *name)
 {
-	return !strncmp(name, XATTR_SECURITY_PREFIX,
-			XATTR_SECURITY_PREFIX_LEN) ||
-	       !strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) ||
-	       !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) ||
-	       !strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) ||
-		!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN);
+	int len = strlen(name);
+	int prefixlen = 0;
+
+	if (!strncmp(name, XATTR_SECURITY_PREFIX,
+			XATTR_SECURITY_PREFIX_LEN))
+		prefixlen = XATTR_SECURITY_PREFIX_LEN;
+	else if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
+		prefixlen = XATTR_SYSTEM_PREFIX_LEN;
+	else if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN))
+		prefixlen = XATTR_TRUSTED_PREFIX_LEN;
+	else if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN))
+		prefixlen = XATTR_USER_PREFIX_LEN;
+	else if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN))
+		prefixlen = XATTR_BTRFS_PREFIX_LEN;
+	else
+		return -EOPNOTSUPP;
+
+	/*
+	 * The name cannot consist of just prefix
+	 */
+	if (len <= prefixlen)
+		return -EINVAL;
+
+	return 0;
 }
 
 ssize_t btrfs_getxattr(struct dentry *dentry, const char *name,
 		       void *buffer, size_t size)
 {
+	int ret;
+
 	/*
 	 * If this is a request for a synthetic attribute in the system.*
 	 * namespace use the generic infrastructure to resolve a handler
@@ -348,8 +404,9 @@ ssize_t btrfs_getxattr(struct dentry *dentry, const char *name,
 	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
 		return generic_getxattr(dentry, name, buffer, size);
 
-	if (!btrfs_is_valid_xattr(name))
-		return -EOPNOTSUPP;
+	ret = btrfs_is_valid_xattr(name);
+	if (ret)
+		return ret;
 	return __btrfs_getxattr(dentry->d_inode, name, buffer, size);
 }
 
@@ -357,6 +414,7 @@ int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 		   size_t size, int flags)
 {
 	struct btrfs_root *root = BTRFS_I(dentry->d_inode)->root;
+	int ret;
 
 	/*
 	 * The permission on security.* and system.* is not checked
@@ -373,8 +431,9 @@ int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
 		return generic_setxattr(dentry, name, value, size, flags);
 
-	if (!btrfs_is_valid_xattr(name))
-		return -EOPNOTSUPP;
+	ret = btrfs_is_valid_xattr(name);
+	if (ret)
+		return ret;
 
 	if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN))
 		return btrfs_set_prop(dentry->d_inode, name,
@@ -390,6 +449,7 @@ int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 int btrfs_removexattr(struct dentry *dentry, const char *name)
 {
 	struct btrfs_root *root = BTRFS_I(dentry->d_inode)->root;
+	int ret;
 
 	/*
 	 * The permission on security.* and system.* is not checked
@@ -406,8 +466,9 @@ int btrfs_removexattr(struct dentry *dentry, const char *name)
 	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
 		return generic_removexattr(dentry, name);
 
-	if (!btrfs_is_valid_xattr(name))
-		return -EOPNOTSUPP;
+	ret = btrfs_is_valid_xattr(name);
+	if (ret)
+		return ret;
 
 	if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN))
 		return btrfs_set_prop(dentry->d_inode, name,
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 18c06bbaf13..481529b879f 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -673,7 +673,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 	int rc = 0;
 	unsigned wsize = 1 << inode->i_blkbits;
 	struct ceph_osd_request *req = NULL;
-	int do_sync;
+	int do_sync = 0;
 	u64 truncate_size, snap_size;
 	u32 truncate_seq;
 
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index e6d63f8f98c..695e7888fef 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -111,7 +111,7 @@ static int fpos_cmp(loff_t l, loff_t r)
 /*
  * When possible, we try to satisfy a readdir by peeking at the
  * dcache.  We make this work by carefully ordering dentries on
- * d_u.d_child when we initially get results back from the MDS, and
+ * d_child when we initially get results back from the MDS, and
  * falling back to a "normal" sync readdir if any dentries in the dir
  * are dropped.
  *
@@ -147,11 +147,11 @@ static int __dcache_readdir(struct file *file,  struct dir_context *ctx,
 		p = parent->d_subdirs.prev;
 		dout(" initial p %p/%p\n", p->prev, p->next);
 	} else {
-		p = last->d_u.d_child.prev;
+		p = last->d_child.prev;
 	}
 
 more:
-	dentry = list_entry(p, struct dentry, d_u.d_child);
+	dentry = list_entry(p, struct dentry, d_child);
 	di = ceph_dentry(dentry);
 	while (1) {
 		dout(" p %p/%p %s d_subdirs %p/%p\n", p->prev, p->next,
@@ -174,7 +174,7 @@ more:
 		     !dentry->d_inode ? " null" : "");
 		spin_unlock(&dentry->d_lock);
 		p = p->prev;
-		dentry = list_entry(p, struct dentry, d_u.d_child);
+		dentry = list_entry(p, struct dentry, d_child);
 		di = ceph_dentry(dentry);
 	}
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 7b613900440..7a1df90c777 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1399,7 +1399,7 @@ retry_lookup:
 			/* reorder parent's d_subdirs */
 			spin_lock(&parent->d_lock);
 			spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED);
-			list_move(&dn->d_u.d_child, &parent->d_subdirs);
+			list_move(&dn->d_child, &parent->d_subdirs);
 			spin_unlock(&dn->d_lock);
 			spin_unlock(&parent->d_lock);
 		}
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 3e4d00a06c4..9431449a73a 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -366,6 +366,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
 	struct cifsLockInfo *li, *tmp;
 	struct cifs_fid fid;
 	struct cifs_pending_open open;
+	bool oplock_break_cancelled;
 
 	spin_lock(&cifs_file_list_lock);
 	if (--cifs_file->count > 0) {
@@ -397,7 +398,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
 	}
 	spin_unlock(&cifs_file_list_lock);
 
-	cancel_work_sync(&cifs_file->oplock_break);
+	oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break);
 
 	if (!tcon->need_reconnect && !cifs_file->invalidHandle) {
 		struct TCP_Server_Info *server = tcon->ses->server;
@@ -409,6 +410,9 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
 		_free_xid(xid);
 	}
 
+	if (oplock_break_cancelled)
+		cifs_done_oplock_break(cifsi);
+
 	cifs_del_pending_open(&open);
 
 	/*
@@ -1825,6 +1829,7 @@ refind_writable:
 			cifsFileInfo_put(inv_file);
 			spin_lock(&cifs_file_list_lock);
 			++refind;
+			inv_file = NULL;
 			goto refind_writable;
 		}
 	}
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 197cb503d52..0c3ce464cae 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -895,7 +895,7 @@ inode_has_hashed_dentries(struct inode *inode)
 	struct dentry *dentry;
 
 	spin_lock(&inode->i_lock);
-	hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
 		if (!d_unhashed(dentry) || IS_ROOT(dentry)) {
 			spin_unlock(&inode->i_lock);
 			return true;
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index 45cb59bcc79..8b7898b7670 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -86,21 +86,16 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
 	}
 
 	src_inode = file_inode(src_file.file);
+	rc = -EINVAL;
+	if (S_ISDIR(src_inode->i_mode))
+		goto out_fput;
 
 	/*
 	 * Note: cifs case is easier than btrfs since server responsible for
 	 * checks for proper open modes and file type and if it wants
 	 * server could even support copy of range where source = target
 	 */
-
-	/* so we do not deadlock racing two ioctls on same files */
-	if (target_inode < src_inode) {
-		mutex_lock_nested(&target_inode->i_mutex, I_MUTEX_PARENT);
-		mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_CHILD);
-	} else {
-		mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_PARENT);
-		mutex_lock_nested(&target_inode->i_mutex, I_MUTEX_CHILD);
-	}
+	lock_two_nondirectories(target_inode, src_inode);
 
 	/* determine range to clone */
 	rc = -EINVAL;
@@ -124,13 +119,7 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
 out_unlock:
 	/* although unlocking in the reverse order from locking is not
 	   strictly necessary here it is a little cleaner to be consistent */
-	if (target_inode < src_inode) {
-		mutex_unlock(&src_inode->i_mutex);
-		mutex_unlock(&target_inode->i_mutex);
-	} else {
-		mutex_unlock(&target_inode->i_mutex);
-		mutex_unlock(&src_inode->i_mutex);
-	}
+	unlock_two_nondirectories(src_inode, target_inode);
 out_fput:
 	fdput(src_file);
 out_drop_write:
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index c5f521bcdee..cc93a7ffe8e 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -683,7 +683,8 @@ smb2_clone_range(const unsigned int xid,
 
 			/* No need to change MaxChunks since already set to 1 */
 			chunk_sizes_updated = true;
-		}
+		} else
+			goto cchunk_out;
 	}
 
 cchunk_out:
diff --git a/fs/coda/cache.c b/fs/coda/cache.c
index 278f8fdeb9e..46ee6f23898 100644
--- a/fs/coda/cache.c
+++ b/fs/coda/cache.c
@@ -92,7 +92,7 @@ static void coda_flag_children(struct dentry *parent, int flag)
 	struct dentry *de;
 
 	spin_lock(&parent->d_lock);
-	list_for_each_entry(de, &parent->d_subdirs, d_u.d_child) {
+	list_for_each_entry(de, &parent->d_subdirs, d_child) {
 		/* don't know what to do with negative dentries */
 		if (de->d_inode ) 
 			coda_flag_inode(de->d_inode, flag);
diff --git a/fs/coredump.c b/fs/coredump.c
index b5c86ffd503..4c5866b948e 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -657,7 +657,7 @@ void do_coredump(const siginfo_t *siginfo)
 		 */
 		if (!uid_eq(inode->i_uid, current_fsuid()))
 			goto close_fail;
-		if (!cprm.file->f_op->write)
+		if (!(cprm.file->f_mode & FMODE_CAN_WRITE))
 			goto close_fail;
 		if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file))
 			goto close_fail;
diff --git a/fs/dcache.c b/fs/dcache.c
index 5bc72b07fde..d0539a4a1ab 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -44,7 +44,7 @@
 /*
  * Usage:
  * dcache->d_inode->i_lock protects:
- *   - i_dentry, d_alias, d_inode of aliases
+ *   - i_dentry, d_u.d_alias, d_inode of aliases
  * dcache_hash_bucket lock protects:
  *   - the dcache hash table
  * s_anon bl list spinlock protects:
@@ -59,7 +59,7 @@
  *   - d_unhashed()
  *   - d_parent and d_subdirs
  *   - childrens' d_child and d_parent
- *   - d_alias, d_inode
+ *   - d_u.d_alias, d_inode
  *
  * Ordering:
  * dentry->d_inode->i_lock
@@ -252,14 +252,12 @@ static void __d_free(struct rcu_head *head)
 {
 	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
 
-	WARN_ON(!hlist_unhashed(&dentry->d_alias));
 	kmem_cache_free(dentry_cache, dentry); 
 }
 
 static void __d_free_external(struct rcu_head *head)
 {
 	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
-	WARN_ON(!hlist_unhashed(&dentry->d_alias));
 	kfree(external_name(dentry));
 	kmem_cache_free(dentry_cache, dentry); 
 }
@@ -271,6 +269,7 @@ static inline int dname_external(const struct dentry *dentry)
 
 static void dentry_free(struct dentry *dentry)
 {
+	WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias));
 	if (unlikely(dname_external(dentry))) {
 		struct external_name *p = external_name(dentry);
 		if (likely(atomic_dec_and_test(&p->u.count))) {
@@ -311,7 +310,7 @@ static void dentry_iput(struct dentry * dentry)
 	struct inode *inode = dentry->d_inode;
 	if (inode) {
 		dentry->d_inode = NULL;
-		hlist_del_init(&dentry->d_alias);
+		hlist_del_init(&dentry->d_u.d_alias);
 		spin_unlock(&dentry->d_lock);
 		spin_unlock(&inode->i_lock);
 		if (!inode->i_nlink)
@@ -336,7 +335,7 @@ static void dentry_unlink_inode(struct dentry * dentry)
 	struct inode *inode = dentry->d_inode;
 	__d_clear_type(dentry);
 	dentry->d_inode = NULL;
-	hlist_del_init(&dentry->d_alias);
+	hlist_del_init(&dentry->d_u.d_alias);
 	dentry_rcuwalk_barrier(dentry);
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&inode->i_lock);
@@ -496,7 +495,7 @@ static void __dentry_kill(struct dentry *dentry)
 	}
 	/* if it was on the hash then remove it */
 	__d_drop(dentry);
-	list_del(&dentry->d_u.d_child);
+	__list_del_entry(&dentry->d_child);
 	/*
 	 * Inform d_walk() that we are no longer attached to the
 	 * dentry tree
@@ -722,7 +721,7 @@ static struct dentry *__d_find_alias(struct inode *inode)
 
 again:
 	discon_alias = NULL;
-	hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
 		spin_lock(&alias->d_lock);
  		if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
 			if (IS_ROOT(alias) &&
@@ -772,7 +771,7 @@ void d_prune_aliases(struct inode *inode)
 	struct dentry *dentry;
 restart:
 	spin_lock(&inode->i_lock);
-	hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
 		spin_lock(&dentry->d_lock);
 		if (!dentry->d_lockref.count) {
 			struct dentry *parent = lock_parent(dentry);
@@ -1051,7 +1050,7 @@ repeat:
 resume:
 	while (next != &this_parent->d_subdirs) {
 		struct list_head *tmp = next;
-		struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
+		struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
 		next = tmp->next;
 
 		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
@@ -1083,33 +1082,31 @@ resume:
 	/*
 	 * All done at this level ... ascend and resume the search.
 	 */
+	rcu_read_lock();
+ascend:
 	if (this_parent != parent) {
 		struct dentry *child = this_parent;
 		this_parent = child->d_parent;
 
-		rcu_read_lock();
 		spin_unlock(&child->d_lock);
 		spin_lock(&this_parent->d_lock);
 
-		/*
-		 * might go back up the wrong parent if we have had a rename
-		 * or deletion
-		 */
-		if (this_parent != child->d_parent ||
-			 (child->d_flags & DCACHE_DENTRY_KILLED) ||
-			 need_seqretry(&rename_lock, seq)) {
-			spin_unlock(&this_parent->d_lock);
-			rcu_read_unlock();
+		/* might go back up the wrong parent if we have had a rename. */
+		if (need_seqretry(&rename_lock, seq))
 			goto rename_retry;
-		}
+		/* go into the first sibling still alive */
+		do {
+			next = child->d_child.next;
+			if (next == &this_parent->d_subdirs)
+				goto ascend;
+			child = list_entry(next, struct dentry, d_child);
+		} while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
 		rcu_read_unlock();
-		next = child->d_u.d_child.next;
 		goto resume;
 	}
-	if (need_seqretry(&rename_lock, seq)) {
-		spin_unlock(&this_parent->d_lock);
+	if (need_seqretry(&rename_lock, seq))
 		goto rename_retry;
-	}
+	rcu_read_unlock();
 	if (finish)
 		finish(data);
 
@@ -1119,6 +1116,9 @@ out_unlock:
 	return;
 
 rename_retry:
+	spin_unlock(&this_parent->d_lock);
+	rcu_read_unlock();
+	BUG_ON(seq & 1);
 	if (!retry)
 		return;
 	seq = 1;
@@ -1455,8 +1455,8 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	INIT_HLIST_BL_NODE(&dentry->d_hash);
 	INIT_LIST_HEAD(&dentry->d_lru);
 	INIT_LIST_HEAD(&dentry->d_subdirs);
-	INIT_HLIST_NODE(&dentry->d_alias);
-	INIT_LIST_HEAD(&dentry->d_u.d_child);
+	INIT_HLIST_NODE(&dentry->d_u.d_alias);
+	INIT_LIST_HEAD(&dentry->d_child);
 	d_set_d_op(dentry, dentry->d_sb->s_d_op);
 
 	this_cpu_inc(nr_dentry);
@@ -1486,7 +1486,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
 	 */
 	__dget_dlock(parent);
 	dentry->d_parent = parent;
-	list_add(&dentry->d_u.d_child, &parent->d_subdirs);
+	list_add(&dentry->d_child, &parent->d_subdirs);
 	spin_unlock(&parent->d_lock);
 
 	return dentry;
@@ -1579,7 +1579,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 	spin_lock(&dentry->d_lock);
 	__d_set_type(dentry, add_flags);
 	if (inode)
-		hlist_add_head(&dentry->d_alias, &inode->i_dentry);
+		hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
 	dentry->d_inode = inode;
 	dentry_rcuwalk_barrier(dentry);
 	spin_unlock(&dentry->d_lock);
@@ -1603,7 +1603,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
  
 void d_instantiate(struct dentry *entry, struct inode * inode)
 {
-	BUG_ON(!hlist_unhashed(&entry->d_alias));
+	BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
 	if (inode)
 		spin_lock(&inode->i_lock);
 	__d_instantiate(entry, inode);
@@ -1642,7 +1642,7 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry,
 		return NULL;
 	}
 
-	hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
 		/*
 		 * Don't need alias->d_lock here, because aliases with
 		 * d_parent == entry->d_parent are not subject to name or
@@ -1668,7 +1668,7 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
 {
 	struct dentry *result;
 
-	BUG_ON(!hlist_unhashed(&entry->d_alias));
+	BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
 
 	if (inode)
 		spin_lock(&inode->i_lock);
@@ -1699,7 +1699,7 @@ EXPORT_SYMBOL(d_instantiate_unique);
  */
 int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode)
 {
-	BUG_ON(!hlist_unhashed(&entry->d_alias));
+	BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
 
 	spin_lock(&inode->i_lock);
 	if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) {
@@ -1738,7 +1738,7 @@ static struct dentry * __d_find_any_alias(struct inode *inode)
 
 	if (hlist_empty(&inode->i_dentry))
 		return NULL;
-	alias = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
+	alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
 	__dget(alias);
 	return alias;
 }
@@ -1800,7 +1800,7 @@ static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected)
 	spin_lock(&tmp->d_lock);
 	tmp->d_inode = inode;
 	tmp->d_flags |= add_flags;
-	hlist_add_head(&tmp->d_alias, &inode->i_dentry);
+	hlist_add_head(&tmp->d_u.d_alias, &inode->i_dentry);
 	hlist_bl_lock(&tmp->d_sb->s_anon);
 	hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon);
 	hlist_bl_unlock(&tmp->d_sb->s_anon);
@@ -2235,7 +2235,7 @@ int d_validate(struct dentry *dentry, struct dentry *dparent)
 	struct dentry *child;
 
 	spin_lock(&dparent->d_lock);
-	list_for_each_entry(child, &dparent->d_subdirs, d_u.d_child) {
+	list_for_each_entry(child, &dparent->d_subdirs, d_child) {
 		if (dentry == child) {
 			spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
 			__dget_dlock(dentry);
@@ -2393,6 +2393,8 @@ static void swap_names(struct dentry *dentry, struct dentry *target)
 			 */
 			unsigned int i;
 			BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long)));
+			kmemcheck_mark_initialized(dentry->d_iname, DNAME_INLINE_LEN);
+			kmemcheck_mark_initialized(target->d_iname, DNAME_INLINE_LEN);
 			for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) {
 				swap(((long *) &dentry->d_iname)[i],
 				     ((long *) &target->d_iname)[i]);
@@ -2526,13 +2528,13 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
 		/* splicing a tree */
 		dentry->d_parent = target->d_parent;
 		target->d_parent = target;
-		list_del_init(&target->d_u.d_child);
-		list_move(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
+		list_del_init(&target->d_child);
+		list_move(&dentry->d_child, &dentry->d_parent->d_subdirs);
 	} else {
 		/* swapping two dentries */
 		swap(dentry->d_parent, target->d_parent);
-		list_move(&target->d_u.d_child, &target->d_parent->d_subdirs);
-		list_move(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
+		list_move(&target->d_child, &target->d_parent->d_subdirs);
+		list_move(&dentry->d_child, &dentry->d_parent->d_subdirs);
 		if (exchange)
 			fsnotify_d_move(target);
 		fsnotify_d_move(dentry);
@@ -2891,17 +2893,6 @@ restart:
 				vfsmnt = &mnt->mnt;
 				continue;
 			}
-			/*
-			 * Filesystems needing to implement special "root names"
-			 * should do so with ->d_dname()
-			 */
-			if (IS_ROOT(dentry) &&
-			   (dentry->d_name.len != 1 ||
-			    dentry->d_name.name[0] != '/')) {
-				WARN(1, "Root dentry has weird name <%.*s>\n",
-				     (int) dentry->d_name.len,
-				     dentry->d_name.name);
-			}
 			if (!error)
 				error = is_mounted(vfsmnt) ? 1 : 2;
 			break;
@@ -3321,7 +3312,7 @@ void d_tmpfile(struct dentry *dentry, struct inode *inode)
 {
 	inode_dec_link_count(inode);
 	BUG_ON(dentry->d_name.name != dentry->d_iname ||
-		!hlist_unhashed(&dentry->d_alias) ||
+		!hlist_unhashed(&dentry->d_u.d_alias) ||
 		!d_unlinked(dentry));
 	spin_lock(&dentry->d_parent->d_lock);
 	spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 1e3b99d3db0..6f0ce531e22 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -246,10 +246,19 @@ static int debugfs_show_options(struct seq_file *m, struct dentry *root)
 	return 0;
 }
 
+static void debugfs_evict_inode(struct inode *inode)
+{
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
+	if (S_ISLNK(inode->i_mode))
+		kfree(inode->i_private);
+}
+
 static const struct super_operations debugfs_super_operations = {
 	.statfs		= simple_statfs,
 	.remount_fs	= debugfs_remount,
 	.show_options	= debugfs_show_options,
+	.evict_inode	= debugfs_evict_inode,
 };
 
 static int debug_fill_super(struct super_block *sb, void *data, int silent)
@@ -466,23 +475,14 @@ static int __debugfs_remove(struct dentry *dentry, struct dentry *parent)
 	int ret = 0;
 
 	if (debugfs_positive(dentry)) {
-		if (dentry->d_inode) {
-			dget(dentry);
-			switch (dentry->d_inode->i_mode & S_IFMT) {
-			case S_IFDIR:
-				ret = simple_rmdir(parent->d_inode, dentry);
-				break;
-			case S_IFLNK:
-				kfree(dentry->d_inode->i_private);
-				/* fall through */
-			default:
-				simple_unlink(parent->d_inode, dentry);
-				break;
-			}
-			if (!ret)
-				d_delete(dentry);
-			dput(dentry);
-		}
+		dget(dentry);
+		if (S_ISDIR(dentry->d_inode->i_mode))
+			ret = simple_rmdir(parent->d_inode, dentry);
+		else
+			simple_unlink(parent->d_inode, dentry);
+		if (!ret)
+			d_delete(dentry);
+		dput(dentry);
 	}
 	return ret;
 }
@@ -553,7 +553,7 @@ void debugfs_remove_recursive(struct dentry *dentry)
 	 * use the d_u.d_child as the rcu head and corrupt this list.
 	 */
 	spin_lock(&parent->d_lock);
-	list_for_each_entry(child, &parent->d_subdirs, d_u.d_child) {
+	list_for_each_entry(child, &parent->d_subdirs, d_child) {
 		if (!debugfs_positive(child))
 			continue;
 
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 2f6735dbf1a..31b148f3e77 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1917,7 +1917,6 @@ ecryptfs_decode_from_filename(unsigned char *dst, size_t *dst_size,
 			break;
 		case 2:
 			dst[dst_byte_offset++] |= (src_byte);
-			dst[dst_byte_offset] = 0;
 			current_bit_offset = 0;
 			break;
 		}
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index f5bce909655..77a3db3791c 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -190,23 +190,11 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 {
 	int rc = 0;
 	struct ecryptfs_crypt_stat *crypt_stat = NULL;
-	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
 	struct dentry *ecryptfs_dentry = file->f_path.dentry;
 	/* Private value of ecryptfs_dentry allocated in
 	 * ecryptfs_lookup() */
 	struct ecryptfs_file_info *file_info;
 
-	mount_crypt_stat = &ecryptfs_superblock_to_private(
-		ecryptfs_dentry->d_sb)->mount_crypt_stat;
-	if ((mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
-	    && ((file->f_flags & O_WRONLY) || (file->f_flags & O_RDWR)
-		|| (file->f_flags & O_CREAT) || (file->f_flags & O_TRUNC)
-		|| (file->f_flags & O_APPEND))) {
-		printk(KERN_WARNING "Mount has encrypted view enabled; "
-		       "files may only be read\n");
-		rc = -EPERM;
-		goto out;
-	}
 	/* Released in ecryptfs_release or end of function if failure */
 	file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL);
 	ecryptfs_set_file_private(file, file_info);
@@ -315,9 +303,22 @@ ecryptfs_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	struct file *lower_file = ecryptfs_file_to_lower(file);
 	long rc = -ENOTTY;
 
-	if (lower_file->f_op->unlocked_ioctl)
+	if (!lower_file->f_op->unlocked_ioctl)
+		return rc;
+
+	switch (cmd) {
+	case FITRIM:
+	case FS_IOC_GETFLAGS:
+	case FS_IOC_SETFLAGS:
+	case FS_IOC_GETVERSION:
+	case FS_IOC_SETVERSION:
 		rc = lower_file->f_op->unlocked_ioctl(lower_file, cmd, arg);
-	return rc;
+		fsstack_copy_attr_all(file_inode(file), file_inode(lower_file));
+
+		return rc;
+	default:
+		return rc;
+	}
 }
 
 #ifdef CONFIG_COMPAT
@@ -327,9 +328,22 @@ ecryptfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	struct file *lower_file = ecryptfs_file_to_lower(file);
 	long rc = -ENOIOCTLCMD;
 
-	if (lower_file->f_op->compat_ioctl)
+	if (!lower_file->f_op->compat_ioctl)
+		return rc;
+
+	switch (cmd) {
+	case FITRIM:
+	case FS_IOC32_GETFLAGS:
+	case FS_IOC32_SETFLAGS:
+	case FS_IOC32_GETVERSION:
+	case FS_IOC32_SETVERSION:
 		rc = lower_file->f_op->compat_ioctl(lower_file, cmd, arg);
-	return rc;
+		fsstack_copy_attr_all(file_inode(file), file_inode(lower_file));
+
+		return rc;
+	default:
+		return rc;
+	}
 }
 #endif
 
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index c4cd1fd86cc..d9eb84bda55 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -493,6 +493,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 {
 	struct super_block *s;
 	struct ecryptfs_sb_info *sbi;
+	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
 	struct ecryptfs_dentry_info *root_info;
 	const char *err = "Getting sb failed";
 	struct inode *inode;
@@ -511,6 +512,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 		err = "Error parsing options";
 		goto out;
 	}
+	mount_crypt_stat = &sbi->mount_crypt_stat;
 
 	s = sget(fs_type, NULL, set_anon_super, flags, NULL);
 	if (IS_ERR(s)) {
@@ -557,11 +559,19 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 
 	/**
 	 * Set the POSIX ACL flag based on whether they're enabled in the lower
-	 * mount. Force a read-only eCryptfs mount if the lower mount is ro.
-	 * Allow a ro eCryptfs mount even when the lower mount is rw.
+	 * mount.
 	 */
 	s->s_flags = flags & ~MS_POSIXACL;
-	s->s_flags |= path.dentry->d_sb->s_flags & (MS_RDONLY | MS_POSIXACL);
+	s->s_flags |= path.dentry->d_sb->s_flags & MS_POSIXACL;
+
+	/**
+	 * Force a read-only eCryptfs mount when:
+	 *   1) The lower mount is ro
+	 *   2) The ecryptfs_encrypted_view mount option is specified
+	 */
+	if (path.dentry->d_sb->s_flags & MS_RDONLY ||
+	    mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
+		s->s_flags |= MS_RDONLY;
 
 	s->s_maxbytes = path.dentry->d_sb->s_maxbytes;
 	s->s_blocksize = path.dentry->d_sb->s_blocksize;
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 0a48886e069..c2f421c30cc 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -121,7 +121,7 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 	int len, i;
 	int err = -ENOMEM;
 
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
 		return err;
 
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 7bcfff900f0..1c6bba7e6aa 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -34,6 +34,7 @@
 #include <linux/mutex.h>
 #include <linux/anon_inodes.h>
 #include <linux/device.h>
+#include <linux/freezer.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/mman.h>
@@ -1637,7 +1638,8 @@ fetch_events:
 			}
 
 			spin_unlock_irqrestore(&ep->lock, flags);
-			if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS))
+			if (!freezable_schedule_hrtimeout_range(to, slack,
+								HRTIMER_MODE_ABS))
 				timed_out = 1;
 
 			spin_lock_irqsave(&ep->lock, flags);
diff --git a/fs/exec.c b/fs/exec.c
index 7302b75a982..b7a5f46181b 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -658,6 +658,9 @@ int setup_arg_pages(struct linux_binprm *bprm,
 	if (stack_base > STACK_SIZE_MAX)
 		stack_base = STACK_SIZE_MAX;
 
+	/* Add space for stack randomization. */
+	stack_base += (STACK_RND_MASK << PAGE_SHIFT);
+
 	/* Make sure we didn't let the argument array grow too large. */
 	if (vma->vm_end - vma->vm_start > stack_base)
 		return -ENOMEM;
@@ -1250,6 +1253,53 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 	spin_unlock(&p->fs->lock);
 }
 
+static void bprm_fill_uid(struct linux_binprm *bprm)
+{
+	struct inode *inode;
+	unsigned int mode;
+	kuid_t uid;
+	kgid_t gid;
+
+	/* clear any previous set[ug]id data from a previous binary */
+	bprm->cred->euid = current_euid();
+	bprm->cred->egid = current_egid();
+
+	if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)
+		return;
+
+	if (task_no_new_privs(current))
+		return;
+
+	inode = file_inode(bprm->file);
+	mode = READ_ONCE(inode->i_mode);
+	if (!(mode & (S_ISUID|S_ISGID)))
+		return;
+
+	/* Be careful if suid/sgid is set */
+	mutex_lock(&inode->i_mutex);
+
+	/* reload atomically mode/uid/gid now that lock held */
+	mode = inode->i_mode;
+	uid = inode->i_uid;
+	gid = inode->i_gid;
+	mutex_unlock(&inode->i_mutex);
+
+	/* We ignore suid/sgid if there are no mappings for them in the ns */
+	if (!kuid_has_mapping(bprm->cred->user_ns, uid) ||
+		 !kgid_has_mapping(bprm->cred->user_ns, gid))
+		return;
+
+	if (mode & S_ISUID) {
+		bprm->per_clear |= PER_CLEAR_ON_SETID;
+		bprm->cred->euid = uid;
+	}
+
+	if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
+		bprm->per_clear |= PER_CLEAR_ON_SETID;
+		bprm->cred->egid = gid;
+	}
+}
+
 /*
  * Fill the binprm structure from the inode.
  * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes
@@ -1258,36 +1308,9 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
  */
 int prepare_binprm(struct linux_binprm *bprm)
 {
-	struct inode *inode = file_inode(bprm->file);
-	umode_t mode = inode->i_mode;
 	int retval;
 
-
-	/* clear any previous set[ug]id data from a previous binary */
-	bprm->cred->euid = current_euid();
-	bprm->cred->egid = current_egid();
-
-	if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) &&
-	    !task_no_new_privs(current) &&
-	    kuid_has_mapping(bprm->cred->user_ns, inode->i_uid) &&
-	    kgid_has_mapping(bprm->cred->user_ns, inode->i_gid)) {
-		/* Set-uid? */
-		if (mode & S_ISUID) {
-			bprm->per_clear |= PER_CLEAR_ON_SETID;
-			bprm->cred->euid = inode->i_uid;
-		}
-
-		/* Set-gid? */
-		/*
-		 * If setgid is set but no group execute bit then this
-		 * is a candidate for mandatory locking, not a setgid
-		 * executable.
-		 */
-		if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
-			bprm->per_clear |= PER_CLEAR_ON_SETID;
-			bprm->cred->egid = inode->i_gid;
-		}
-	}
+	bprm_fill_uid(bprm);
 
 	/* fill in binprm security blob */
 	retval = security_bprm_set_creds(bprm);
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index b01fbfb51f4..a3aa6baad1a 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -50,7 +50,7 @@ find_acceptable_alias(struct dentry *result,
 
 	inode = result->d_inode;
 	spin_lock(&inode->i_lock);
-	hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
 		dget(dentry);
 		spin_unlock(&inode->i_lock);
 		if (toput)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index c55a1faaed5..a2f44223d34 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2085,7 +2085,8 @@ extern int ext4_mb_add_groupinfo(struct super_block *sb,
 		ext4_group_t i, struct ext4_group_desc *desc);
 extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 				ext4_fsblk_t block, unsigned long count);
-extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
+extern int ext4_trim_fs(struct super_block *, struct fstrim_range *,
+				unsigned long blkdev_flags);
 
 /* inode.c */
 struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 3445035c7e0..d4184318181 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -87,6 +87,12 @@ int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
 		ext4_put_nojournal(handle);
 		return 0;
 	}
+
+	if (!handle->h_transaction) {
+		err = jbd2_journal_stop(handle);
+		return handle->h_err ? handle->h_err : err;
+	}
+
 	sb = handle->h_transaction->t_journal->j_private;
 	err = handle->h_err;
 	rc = jbd2_journal_stop(handle);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 0b16fb4c06d..b5fcb1ac0dd 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -377,7 +377,7 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
 	ext4_lblk_t lblock = le32_to_cpu(ext->ee_block);
 	ext4_lblk_t last = lblock + len - 1;
 
-	if (lblock > last)
+	if (len == 0 || lblock > last)
 		return 0;
 	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
 }
@@ -4923,13 +4923,6 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (ret)
 		return ret;
 
-	/*
-	 * currently supporting (pre)allocate mode for extent-based
-	 * files _only_
-	 */
-	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
-		return -EOPNOTSUPP;
-
 	if (mode & FALLOC_FL_COLLAPSE_RANGE)
 		return ext4_collapse_range(inode, offset, len);
 
@@ -4951,6 +4944,14 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 
 	mutex_lock(&inode->i_mutex);
 
+	/*
+	 * We only support preallocation for extent-based files only
+	 */
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
 	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
 	     offset + len > i_size_read(inode)) {
 		new_size = offset + len;
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 94e7855ae71..b860603dac3 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -670,6 +670,14 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 
 	BUG_ON(end < lblk);
 
+	if ((status & EXTENT_STATUS_DELAYED) &&
+	    (status & EXTENT_STATUS_WRITTEN)) {
+		ext4_warning(inode->i_sb, "Inserting extent [%u/%u] as "
+				" delayed and written which can potentially "
+				" cause data loss.\n", lblk, len);
+		WARN_ON(1);
+	}
+
 	newes.es_lblk = lblk;
 	newes.es_len = len;
 	ext4_es_store_pblock_status(&newes, pblk, status);
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 36b369697a1..11368881477 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -565,7 +565,7 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 				       EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
 		EXT4_ERROR_INODE(inode, "Can't allocate blocks for "
 				 "non-extent mapped inodes with bigalloc");
-		return -ENOSPC;
+		return -EUCLEAN;
 	}
 
 	/* Set up for the direct block allocation */
@@ -1393,10 +1393,7 @@ end_range:
 				 * to free. Everything was covered by the start
 				 * of the range.
 				 */
-				return 0;
-			} else {
-				/* Shared branch grows from an indirect block */
-				partial2--;
+				goto do_indirects;
 			}
 		} else {
 			/*
@@ -1427,56 +1424,96 @@ end_range:
 	/* Punch happened within the same level (n == n2) */
 	partial = ext4_find_shared(inode, n, offsets, chain, &nr);
 	partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);
-	/*
-	 * ext4_find_shared returns Indirect structure which
-	 * points to the last element which should not be
-	 * removed by truncate. But this is end of the range
-	 * in punch_hole so we need to point to the next element
-	 */
-	partial2->p++;
-	while ((partial > chain) || (partial2 > chain2)) {
-		/* We're at the same block, so we're almost finished */
-		if ((partial->bh && partial2->bh) &&
-		    (partial->bh->b_blocknr == partial2->bh->b_blocknr)) {
-			if ((partial > chain) && (partial2 > chain2)) {
+
+	/* Free top, but only if partial2 isn't its subtree. */
+	if (nr) {
+		int level = min(partial - chain, partial2 - chain2);
+		int i;
+		int subtree = 1;
+
+		for (i = 0; i <= level; i++) {
+			if (offsets[i] != offsets2[i]) {
+				subtree = 0;
+				break;
+			}
+		}
+
+		if (!subtree) {
+			if (partial == chain) {
+				/* Shared branch grows from the inode */
+				ext4_free_branches(handle, inode, NULL,
+						   &nr, &nr+1,
+						   (chain+n-1) - partial);
+				*partial->p = 0;
+			} else {
+				/* Shared branch grows from an indirect block */
+				BUFFER_TRACE(partial->bh, "get_write_access");
 				ext4_free_branches(handle, inode, partial->bh,
-						   partial->p + 1,
-						   partial2->p,
+						   partial->p,
+						   partial->p+1,
 						   (chain+n-1) - partial);
-				BUFFER_TRACE(partial->bh, "call brelse");
-				brelse(partial->bh);
-				BUFFER_TRACE(partial2->bh, "call brelse");
-				brelse(partial2->bh);
 			}
-			return 0;
 		}
+	}
+
+	if (!nr2) {
 		/*
-		 * Clear the ends of indirect blocks on the shared branch
-		 * at the start of the range
+		 * ext4_find_shared returns Indirect structure which
+		 * points to the last element which should not be
+		 * removed by truncate. But this is end of the range
+		 * in punch_hole so we need to point to the next element
 		 */
-		if (partial > chain) {
+		partial2->p++;
+	}
+
+	while (partial > chain || partial2 > chain2) {
+		int depth = (chain+n-1) - partial;
+		int depth2 = (chain2+n2-1) - partial2;
+
+		if (partial > chain && partial2 > chain2 &&
+		    partial->bh->b_blocknr == partial2->bh->b_blocknr) {
+			/*
+			 * We've converged on the same block. Clear the range,
+			 * then we're done.
+			 */
 			ext4_free_branches(handle, inode, partial->bh,
-				   partial->p + 1,
-				   (__le32 *)partial->bh->b_data+addr_per_block,
-				   (chain+n-1) - partial);
+					   partial->p + 1,
+					   partial2->p,
+					   (chain+n-1) - partial);
 			BUFFER_TRACE(partial->bh, "call brelse");
 			brelse(partial->bh);
-			partial--;
+			BUFFER_TRACE(partial2->bh, "call brelse");
+			brelse(partial2->bh);
+			return 0;
 		}
+
 		/*
-		 * Clear the ends of indirect blocks on the shared branch
-		 * at the end of the range
+		 * The start and end partial branches may not be at the same
+		 * level even though the punch happened within one level. So, we
+		 * give them a chance to arrive at the same level, then walk
+		 * them in step with each other until we converge on the same
+		 * block.
 		 */
-		if (partial2 > chain2) {
+		if (partial > chain && depth <= depth2) {
+			ext4_free_branches(handle, inode, partial->bh,
+					   partial->p + 1,
+					   (__le32 *)partial->bh->b_data+addr_per_block,
+					   (chain+n-1) - partial);
+			BUFFER_TRACE(partial->bh, "call brelse");
+			brelse(partial->bh);
+			partial--;
+		}
+		if (partial2 > chain2 && depth2 <= depth) {
 			ext4_free_branches(handle, inode, partial2->bh,
 					   (__le32 *)partial2->bh->b_data,
 					   partial2->p,
-					   (chain2+n-1) - partial2);
+					   (chain2+n2-1) - partial2);
 			BUFFER_TRACE(partial2->bh, "call brelse");
 			brelse(partial2->bh);
 			partial2--;
 		}
 	}
+	return 0;
 
 do_indirects:
 	/* Kill the remaining (whole) subtrees */
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 3356ab5395f..777f7437014 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -540,6 +540,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		status = map->m_flags & EXT4_MAP_UNWRITTEN ?
 				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
 		if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
+		    !(status & EXTENT_STATUS_WRITTEN) &&
 		    ext4_find_delalloc_range(inode, map->m_lblk,
 					     map->m_lblk + map->m_len - 1))
 			status |= EXTENT_STATUS_DELAYED;
@@ -644,6 +645,7 @@ found:
 		status = map->m_flags & EXT4_MAP_UNWRITTEN ?
 				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
 		if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
+		    !(status & EXTENT_STATUS_WRITTEN) &&
 		    ext4_find_delalloc_range(inode, map->m_lblk,
 					     map->m_lblk + map->m_len - 1))
 			status |= EXTENT_STATUS_DELAYED;
@@ -1228,7 +1230,7 @@ static void ext4_da_page_release_reservation(struct page *page,
 					     unsigned int offset,
 					     unsigned int length)
 {
-	int to_release = 0;
+	int to_release = 0, contiguous_blks = 0;
 	struct buffer_head *head, *bh;
 	unsigned int curr_off = 0;
 	struct inode *inode = page->mapping->host;
@@ -1249,14 +1251,23 @@ static void ext4_da_page_release_reservation(struct page *page,
 
 		if ((offset <= curr_off) && (buffer_delay(bh))) {
 			to_release++;
+			contiguous_blks++;
 			clear_buffer_delay(bh);
+		} else if (contiguous_blks) {
+			lblk = page->index <<
+			       (PAGE_CACHE_SHIFT - inode->i_blkbits);
+			lblk += (curr_off >> inode->i_blkbits) -
+				contiguous_blks;
+			ext4_es_remove_extent(inode, lblk, contiguous_blks);
+			contiguous_blks = 0;
 		}
 		curr_off = next_off;
 	} while ((bh = bh->b_this_page) != head);
 
-	if (to_release) {
+	if (contiguous_blks) {
 		lblk = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
-		ext4_es_remove_extent(inode, lblk, to_release);
+		lblk += (curr_off >> inode->i_blkbits) - contiguous_blks;
+		ext4_es_remove_extent(inode, lblk, contiguous_blks);
 	}
 
 	/* If we have released all the blocks belonging to a cluster, then we
@@ -1604,19 +1615,32 @@ static int __ext4_journalled_writepage(struct page *page,
 		ext4_walk_page_buffers(handle, page_bufs, 0, len,
 				       NULL, bget_one);
 	}
-	/* As soon as we unlock the page, it can go away, but we have
-	 * references to buffers so we are safe */
+	/*
+	 * We need to release the page lock before we start the
+	 * journal, so grab a reference so the page won't disappear
+	 * out from under us.
+	 */
+	get_page(page);
 	unlock_page(page);
 
 	handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
 				    ext4_writepage_trans_blocks(inode));
 	if (IS_ERR(handle)) {
 		ret = PTR_ERR(handle);
-		goto out;
+		put_page(page);
+		goto out_no_pagelock;
 	}
-
 	BUG_ON(!ext4_handle_valid(handle));
 
+	lock_page(page);
+	put_page(page);
+	if (page->mapping != mapping) {
+		/* The page got truncated from under us */
+		ext4_journal_stop(handle);
+		ret = 0;
+		goto out;
+	}
+
 	if (inline_data) {
 		BUFFER_TRACE(inode_bh, "get write access");
 		ret = ext4_journal_get_write_access(handle, inode_bh);
@@ -1642,6 +1666,8 @@ static int __ext4_journalled_writepage(struct page *page,
 				       NULL, bput_one);
 	ext4_set_inode_state(inode, EXT4_STATE_JDATA);
 out:
+	unlock_page(page);
+out_no_pagelock:
 	brelse(inode_bh);
 	return ret;
 }
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index bfda18a1559..e75462a41d1 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -587,11 +587,13 @@ resizefs_out:
 		return err;
 	}
 
+	case FIDTRIM:
 	case FITRIM:
 	{
 		struct request_queue *q = bdev_get_queue(sb->s_bdev);
 		struct fstrim_range range;
 		int ret = 0;
+		int flags  = cmd == FIDTRIM ? BLKDEV_DISCARD_SECURE : 0;
 
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
@@ -599,13 +601,15 @@ resizefs_out:
 		if (!blk_queue_discard(q))
 			return -EOPNOTSUPP;
 
+		if ((flags & BLKDEV_DISCARD_SECURE) && !blk_queue_secdiscard(q))
+			return -EOPNOTSUPP;
 		if (copy_from_user(&range, (struct fstrim_range __user *)arg,
 		    sizeof(range)))
 			return -EFAULT;
 
 		range.minlen = max((unsigned int)range.minlen,
 				   q->limits.discard_granularity);
-		ret = ext4_trim_fs(sb, &range);
+		ret = ext4_trim_fs(sb, &range, flags);
 		if (ret < 0)
 			return ret;
 
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index dbfe15c2533..07b13c1eece 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2744,7 +2744,8 @@ int ext4_mb_release(struct super_block *sb)
 }
 
 static inline int ext4_issue_discard(struct super_block *sb,
-		ext4_group_t block_group, ext4_grpblk_t cluster, int count)
+		ext4_group_t block_group, ext4_grpblk_t cluster, int count,
+		unsigned long flags)
 {
 	ext4_fsblk_t discard_block;
 
@@ -2753,7 +2754,7 @@ static inline int ext4_issue_discard(struct super_block *sb,
 	count = EXT4_C2B(EXT4_SB(sb), count);
 	trace_ext4_discard_blocks(sb,
 			(unsigned long long) discard_block, count);
-	return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0);
+	return sb_issue_discard(sb, discard_block, count, GFP_NOFS, flags);
 }
 
 /*
@@ -2775,7 +2776,7 @@ static void ext4_free_data_callback(struct super_block *sb,
 	if (test_opt(sb, DISCARD)) {
 		err = ext4_issue_discard(sb, entry->efd_group,
 					 entry->efd_start_cluster,
-					 entry->efd_count);
+					 entry->efd_count, 0);
 		if (err && err != -EOPNOTSUPP)
 			ext4_msg(sb, KERN_WARNING, "discard request in"
 				 " group:%d block:%d count:%d failed"
@@ -4801,18 +4802,12 @@ do_more:
 		/*
 		 * blocks being freed are metadata. these blocks shouldn't
 		 * be used until this transaction is committed
+		 *
+		 * We use __GFP_NOFAIL because ext4_free_blocks() is not allowed
+		 * to fail.
 		 */
-	retry:
-		new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS);
-		if (!new_entry) {
-			/*
-			 * We use a retry loop because
-			 * ext4_free_blocks() is not allowed to fail.
-			 */
-			cond_resched();
-			congestion_wait(BLK_RW_ASYNC, HZ/50);
-			goto retry;
-		}
+		new_entry = kmem_cache_alloc(ext4_free_data_cachep,
+				GFP_NOFS|__GFP_NOFAIL);
 		new_entry->efd_start_cluster = bit;
 		new_entry->efd_group = block_group;
 		new_entry->efd_count = count_clusters;
@@ -4827,7 +4822,8 @@ do_more:
 		 * them with group lock_held
 		 */
 		if (test_opt(sb, DISCARD)) {
-			err = ext4_issue_discard(sb, block_group, bit, count);
+			err = ext4_issue_discard(sb, block_group, bit, count,
+						 0);
 			if (err && err != -EOPNOTSUPP)
 				ext4_msg(sb, KERN_WARNING, "discard request in"
 					 " group:%d block:%d count:%lu failed"
@@ -5022,13 +5018,15 @@ error_return:
  * @count:	number of blocks to TRIM
  * @group:	alloc. group we are working with
  * @e4b:	ext4 buddy for the group
+ * @blkdev_flags: flags for the block device
  *
  * Trim "count" blocks starting at "start" in the "group". To assure that no
  * one will allocate those blocks, mark it as used in buddy bitmap. This must
  * be called with under the group lock.
  */
 static int ext4_trim_extent(struct super_block *sb, int start, int count,
-			     ext4_group_t group, struct ext4_buddy *e4b)
+			    ext4_group_t group, struct ext4_buddy *e4b,
+			    unsigned long blkdev_flags)
 __releases(bitlock)
 __acquires(bitlock)
 {
@@ -5049,7 +5047,7 @@ __acquires(bitlock)
 	 */
 	mb_mark_used(e4b, &ex);
 	ext4_unlock_group(sb, group);
-	ret = ext4_issue_discard(sb, group, start, count);
+	ret = ext4_issue_discard(sb, group, start, count, blkdev_flags);
 	ext4_lock_group(sb, group);
 	mb_free_blocks(NULL, e4b, start, ex.fe_len);
 	return ret;
@@ -5062,6 +5060,7 @@ __acquires(bitlock)
  * @start:		first group block to examine
  * @max:		last group block to examine
  * @minblocks:		minimum extent block count
+ * @blkdev_flags:	flags for the block device
  *
  * ext4_trim_all_free walks through group's buddy bitmap searching for free
  * extents. When the free block is found, ext4_trim_extent is called to TRIM
@@ -5076,7 +5075,7 @@ __acquires(bitlock)
 static ext4_grpblk_t
 ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
 		   ext4_grpblk_t start, ext4_grpblk_t max,
-		   ext4_grpblk_t minblocks)
+		   ext4_grpblk_t minblocks, unsigned long blkdev_flags)
 {
 	void *bitmap;
 	ext4_grpblk_t next, count = 0, free_count = 0;
@@ -5109,7 +5108,8 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
 
 		if ((next - start) >= minblocks) {
 			ret = ext4_trim_extent(sb, start,
-					       next - start, group, &e4b);
+					       next - start, group, &e4b,
+					       blkdev_flags);
 			if (ret && ret != -EOPNOTSUPP)
 				break;
 			ret = 0;
@@ -5151,6 +5151,7 @@ out:
  * ext4_trim_fs() -- trim ioctl handle function
  * @sb:			superblock for filesystem
  * @range:		fstrim_range structure
+ * @blkdev_flags:	flags for the block device
  *
  * start:	First Byte to trim
  * len:		number of Bytes to trim from start
@@ -5159,7 +5160,8 @@ out:
  * start to start+len. For each such a group ext4_trim_all_free function
  * is invoked to trim all free space.
  */
-int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
+int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range,
+			unsigned long blkdev_flags)
 {
 	struct ext4_group_info *grp;
 	ext4_group_t group, first_group, last_group;
@@ -5215,7 +5217,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 
 		if (grp->bb_free >= minlen) {
 			cnt = ext4_trim_all_free(sb, group, first_cluster,
-						end, minlen);
+						end, minlen, blkdev_flags);
 			if (cnt < 0) {
 				ret = cnt;
 				break;
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index a432634f2e6..876b984f1a7 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -620,6 +620,7 @@ int ext4_ind_migrate(struct inode *inode)
 	struct ext4_inode_info		*ei = EXT4_I(inode);
 	struct ext4_extent		*ex;
 	unsigned int			i, len;
+	ext4_lblk_t			start, end;
 	ext4_fsblk_t			blk;
 	handle_t			*handle;
 	int				ret;
@@ -633,6 +634,14 @@ int ext4_ind_migrate(struct inode *inode)
 				       EXT4_FEATURE_RO_COMPAT_BIGALLOC))
 		return -EOPNOTSUPP;
 
+	/*
+	 * In order to get correct extent info, force all delayed allocation
+	 * blocks to be allocated, otherwise delayed allocation blocks may not
+	 * be reflected and bypass the checks on extent header.
+	 */
+	if (test_opt(inode->i_sb, DELALLOC))
+		ext4_alloc_da_blocks(inode);
+
 	handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
@@ -650,11 +659,13 @@ int ext4_ind_migrate(struct inode *inode)
 		goto errout;
 	}
 	if (eh->eh_entries == 0)
-		blk = len = 0;
+		blk = len = start = end = 0;
 	else {
 		len = le16_to_cpu(ex->ee_len);
 		blk = ext4_ext_pblock(ex);
-		if (len > EXT4_NDIR_BLOCKS) {
+		start = le32_to_cpu(ex->ee_block);
+		end = start + len - 1;
+		if (end >= EXT4_NDIR_BLOCKS) {
 			ret = -EOPNOTSUPP;
 			goto errout;
 		}
@@ -662,7 +673,7 @@ int ext4_ind_migrate(struct inode *inode)
 
 	ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
 	memset(ei->i_data, 0, sizeof(ei->i_data));
-	for (i=0; i < len; i++)
+	for (i = start; i <= end; i++)
 		ei->i_data[i] = cpu_to_le32(blk++);
 	ext4_mark_inode_dirty(handle, inode);
 errout:
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 426211882f7..447486425b8 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1865,7 +1865,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 			  struct inode *inode)
 {
 	struct inode *dir = dentry->d_parent->d_inode;
-	struct buffer_head *bh;
+	struct buffer_head *bh = NULL;
 	struct ext4_dir_entry_2 *de;
 	struct ext4_dir_entry_tail *t;
 	struct super_block *sb;
@@ -1889,14 +1889,14 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 			return retval;
 		if (retval == 1) {
 			retval = 0;
-			return retval;
+			goto out;
 		}
 	}
 
 	if (is_dx(dir)) {
 		retval = ext4_dx_add_entry(handle, dentry, inode);
 		if (!retval || (retval != ERR_BAD_DX_DIR))
-			return retval;
+			goto out;
 		ext4_clear_inode_flag(dir, EXT4_INODE_INDEX);
 		dx_fallback++;
 		ext4_mark_inode_dirty(handle, dir);
@@ -1908,14 +1908,15 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 			return PTR_ERR(bh);
 
 		retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
-		if (retval != -ENOSPC) {
-			brelse(bh);
-			return retval;
-		}
+		if (retval != -ENOSPC)
+			goto out;
 
 		if (blocks == 1 && !dx_fallback &&
-		    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX))
-			return make_indexed_dir(handle, dentry, inode, bh);
+		    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) {
+			retval = make_indexed_dir(handle, dentry, inode, bh);
+			bh = NULL; /* make_indexed_dir releases bh */
+			goto out;
+		}
 		brelse(bh);
 	}
 	bh = ext4_append(handle, dir, &block);
@@ -1931,6 +1932,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 	}
 
 	retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
+out:
 	brelse(bh);
 	if (retval == 0)
 		ext4_set_inode_state(inode, EXT4_STATE_NEWENTRY);
@@ -3259,12 +3261,18 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		   EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2);
 	if (!(flags & RENAME_WHITEOUT)) {
 		handle = ext4_journal_start(old.dir, EXT4_HT_DIR, credits);
-		if (IS_ERR(handle))
-			return PTR_ERR(handle);
+		if (IS_ERR(handle)) {
+			retval = PTR_ERR(handle);
+			handle = NULL;
+			goto end_rename;
+		}
 	} else {
 		whiteout = ext4_whiteout_for_rename(&old, credits, &handle);
-		if (IS_ERR(whiteout))
-			return PTR_ERR(whiteout);
+		if (IS_ERR(whiteout)) {
+			retval = PTR_ERR(whiteout);
+			whiteout = NULL;
+			goto end_rename;
+		}
 	}
 
 	if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir))
@@ -3428,8 +3436,11 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	handle = ext4_journal_start(old.dir, EXT4_HT_DIR,
 		(2 * EXT4_DATA_TRANS_BLOCKS(old.dir->i_sb) +
 		 2 * EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2));
-	if (IS_ERR(handle))
-		return PTR_ERR(handle);
+	if (IS_ERR(handle)) {
+		retval = PTR_ERR(handle);
+		handle = NULL;
+		goto end_rename;
+	}
 
 	if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir))
 		ext4_handle_sync(handle);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 2c9e6864abd..86dc22690ad 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -304,6 +304,8 @@ static void __save_error_info(struct super_block *sb, const char *func,
 	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
 
 	EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+	if (bdev_read_only(sb->s_bdev))
+		return;
 	es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
 	es->s_last_error_time = cpu_to_le32(get_seconds());
 	strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
@@ -831,6 +833,7 @@ static void ext4_put_super(struct super_block *sb)
 		dump_orphan_list(sb, sbi);
 	J_ASSERT(list_empty(&sbi->s_orphan));
 
+	sync_blockdev(sb->s_bdev);
 	invalidate_bdev(sb->s_bdev);
 	if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) {
 		/*
@@ -4849,9 +4852,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^
 	    test_opt(sb, JOURNAL_CHECKSUM)) {
 		ext4_msg(sb, KERN_ERR, "changing journal_checksum "
-			 "during remount not supported");
-		err = -EINVAL;
-		goto restore_opts;
+			 "during remount not supported; ignoring");
+		sbi->s_mount_opt ^= EXT4_MOUNT_JOURNAL_CHECKSUM;
 	}
 
 	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 8e58c4cc2cb..f988b01b6f8 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1007,21 +1007,19 @@ inline_data:
 		goto out;
 	}
 
-	if (dn.data_blkaddr == NEW_ADDR) {
+	if (f2fs_has_inline_data(inode)) {
+		err = f2fs_read_inline_data(inode, page);
+		if (err) {
+			page_cache_release(page);
+			goto fail;
+		}
+	} else if (dn.data_blkaddr == NEW_ADDR) {
 		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
 	} else {
-		if (f2fs_has_inline_data(inode)) {
-			err = f2fs_read_inline_data(inode, page);
-			if (err) {
-				page_cache_release(page);
-				goto fail;
-			}
-		} else {
-			err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr,
-							READ_SYNC);
-			if (err)
-				goto fail;
-		}
+		err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr,
+					   READ_SYNC);
+		if (err)
+			goto fail;
 
 		lock_page(page);
 		if (unlikely(!PageUptodate(page))) {
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 923cb76fdc4..3c31221affe 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1004,6 +1004,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 						range->len < sbi->blocksize)
 		return -EINVAL;
 
+	cpc.trimmed = 0;
 	if (end <= MAIN_BLKADDR(sbi))
 		goto out;
 
@@ -1015,7 +1016,6 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	cpc.trim_start = start_segno;
 	cpc.trim_end = end_segno;
 	cpc.trim_minlen = range->minlen >> sbi->log_blocksize;
-	cpc.trimmed = 0;
 
 	/* do checkpoint to issue discard commands safely */
 	write_checkpoint(sbi, &cpc);
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 999ff5c3cab..d59712dfa3e 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -195,8 +195,9 @@ static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
 		goto out_err;
 	}
 	/* copy the full handle */
-	if (copy_from_user(handle, ufh,
-			   sizeof(struct file_handle) +
+	*handle = f_handle;
+	if (copy_from_user(&handle->f_handle,
+			   &ufh->f_handle,
 			   f_handle.handle_bytes)) {
 		retval = -EFAULT;
 		goto out_handle;
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index ef9bef11834..4bc7cbe88ad 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -479,12 +479,28 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	 * write_inode()
 	 */
 	spin_lock(&inode->i_lock);
-	/* Clear I_DIRTY_PAGES if we've written out all dirty pages */
-	if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
-		inode->i_state &= ~I_DIRTY_PAGES;
+
 	dirty = inode->i_state & I_DIRTY;
-	inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC);
+	inode->i_state &= ~I_DIRTY;
+
+	/*
+	 * Paired with smp_mb() in __mark_inode_dirty().  This allows
+	 * __mark_inode_dirty() to test i_state without grabbing i_lock -
+	 * either they see the I_DIRTY bits cleared or we see the dirtied
+	 * inode.
+	 *
+	 * I_DIRTY_PAGES is always cleared together above even if @mapping
+	 * still has dirty pages.  The flag is reinstated after smp_mb() if
+	 * necessary.  This guarantees that either __mark_inode_dirty()
+	 * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY.
+	 */
+	smp_mb();
+
+	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
+		inode->i_state |= I_DIRTY_PAGES;
+
 	spin_unlock(&inode->i_lock);
+
 	/* Don't write the inode if only I_DIRTY_PAGES was set */
 	if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
 		int err = write_inode(inode, wbc);
@@ -1148,16 +1164,15 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 	}
 
 	/*
-	 * make sure that changes are seen by all cpus before we test i_state
-	 * -- mikulas
+	 * Paired with smp_mb() in __writeback_single_inode() for the
+	 * following lockless i_state test.  See there for details.
 	 */
 	smp_mb();
 
-	/* avoid the locking if we can */
 	if ((inode->i_state & flags) == flags)
 		return;
 
-	if (unlikely(block_dump))
+	if (unlikely(block_dump > 1))
 		block_dump___mark_inode_dirty(inode);
 
 	spin_lock(&inode->i_lock);
diff --git a/fs/fs_pin.c b/fs/fs_pin.c
index 9368236ca10..569bbd10e37 100644
--- a/fs/fs_pin.c
+++ b/fs/fs_pin.c
@@ -20,8 +20,8 @@ void pin_put(struct fs_pin *p)
 void pin_remove(struct fs_pin *pin)
 {
 	spin_lock(&pin_lock);
-	hlist_del(&pin->m_list);
-	hlist_del(&pin->s_list);
+	hlist_del_init(&pin->m_list);
+	hlist_del_init(&pin->s_list);
 	spin_unlock(&pin_lock);
 }
 
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index ca887314aba..3f00d676bf8 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -20,6 +20,7 @@
 #include <linux/swap.h>
 #include <linux/splice.h>
 #include <linux/aio.h>
+#include <linux/freezer.h>
 
 MODULE_ALIAS_MISCDEV(FUSE_MINOR);
 MODULE_ALIAS("devname:fuse");
@@ -464,7 +465,10 @@ __acquires(fc->lock)
 	 * Wait it out.
 	 */
 	spin_unlock(&fc->lock);
-	wait_event(req->waitq, req->state == FUSE_REQ_FINISHED);
+
+	while (req->state != FUSE_REQ_FINISHED)
+		wait_event_freezable(req->waitq,
+				     req->state == FUSE_REQ_FINISHED);
 	spin_lock(&fc->lock);
 
 	if (!req->aborted)
@@ -814,8 +818,8 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 
 	newpage = buf->page;
 
-	if (WARN_ON(!PageUptodate(newpage)))
-		return -EIO;
+	if (!PageUptodate(newpage))
+		SetPageUptodate(newpage);
 
 	ClearPageMappedToDisk(newpage);
 
@@ -1721,6 +1725,9 @@ copy_finish:
 static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
 		       unsigned int size, struct fuse_copy_state *cs)
 {
+	/* Don't try to move pages (yet) */
+	cs->move_pages = 0;
+
 	switch (code) {
 	case FUSE_NOTIFY_POLL:
 		return fuse_notify_poll(fc, size, cs);
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 03246cd9d47..9e3f6cfee2f 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1049,6 +1049,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 		goto err_fput;
 
 	fuse_conn_init(fc);
+	fc->release = fuse_free_conn;
 
 	fc->dev = sb->s_dev;
 	fc->sb = sb;
@@ -1063,7 +1064,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 		fc->dont_mask = 1;
 	sb->s_flags |= MS_POSIXACL;
 
-	fc->release = fuse_free_conn;
 	fc->flags = d.flags;
 	fc->user_id = d.user_id;
 	fc->group_id = d.group_id;
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index 3088e2a38e3..7b3143064af 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -73,7 +73,7 @@ int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 
 	BUG_ON(name == NULL);
 
-	if (acl->a_count > GFS2_ACL_MAX_ENTRIES(GFS2_SB(inode)))
+	if (acl && acl->a_count > GFS2_ACL_MAX_ENTRIES(GFS2_SB(inode)))
 		return -E2BIG;
 
 	if (type == ACL_TYPE_ACCESS) {
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 64b29f7f6b4..dc482ffff65 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -667,7 +667,7 @@ static void do_qc(struct gfs2_quota_data *qd, s64 change)
 
 static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
 			     s64 change, struct gfs2_quota_data *qd,
-			     struct fs_disk_quota *fdq)
+			     struct qc_dqblk *fdq)
 {
 	struct inode *inode = &ip->i_inode;
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
@@ -697,16 +697,16 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
 	be64_add_cpu(&q.qu_value, change);
 	qd->qd_qb.qb_value = q.qu_value;
 	if (fdq) {
-		if (fdq->d_fieldmask & FS_DQ_BSOFT) {
-			q.qu_warn = cpu_to_be64(fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift);
+		if (fdq->d_fieldmask & QC_SPC_SOFT) {
+			q.qu_warn = cpu_to_be64(fdq->d_spc_softlimit >> sdp->sd_sb.sb_bsize_shift);
 			qd->qd_qb.qb_warn = q.qu_warn;
 		}
-		if (fdq->d_fieldmask & FS_DQ_BHARD) {
-			q.qu_limit = cpu_to_be64(fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift);
+		if (fdq->d_fieldmask & QC_SPC_HARD) {
+			q.qu_limit = cpu_to_be64(fdq->d_spc_hardlimit >> sdp->sd_sb.sb_bsize_shift);
 			qd->qd_qb.qb_limit = q.qu_limit;
 		}
-		if (fdq->d_fieldmask & FS_DQ_BCOUNT) {
-			q.qu_value = cpu_to_be64(fdq->d_bcount >> sdp->sd_fsb2bb_shift);
+		if (fdq->d_fieldmask & QC_SPACE) {
+			q.qu_value = cpu_to_be64(fdq->d_space >> sdp->sd_sb.sb_bsize_shift);
 			qd->qd_qb.qb_value = q.qu_value;
 		}
 	}
@@ -1502,7 +1502,7 @@ static int gfs2_quota_get_xstate(struct super_block *sb,
 }
 
 static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid,
-			  struct fs_disk_quota *fdq)
+			  struct qc_dqblk *fdq)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct gfs2_quota_lvb *qlvb;
@@ -1510,7 +1510,7 @@ static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid,
 	struct gfs2_holder q_gh;
 	int error;
 
-	memset(fdq, 0, sizeof(struct fs_disk_quota));
+	memset(fdq, 0, sizeof(*fdq));
 
 	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
 		return -ESRCH; /* Crazy XFS error code */
@@ -1527,12 +1527,9 @@ static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid,
 		goto out;
 
 	qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr;
-	fdq->d_version = FS_DQUOT_VERSION;
-	fdq->d_flags = (qid.type == USRQUOTA) ? FS_USER_QUOTA : FS_GROUP_QUOTA;
-	fdq->d_id = from_kqid_munged(current_user_ns(), qid);
-	fdq->d_blk_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_fsb2bb_shift;
-	fdq->d_blk_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_fsb2bb_shift;
-	fdq->d_bcount = be64_to_cpu(qlvb->qb_value) << sdp->sd_fsb2bb_shift;
+	fdq->d_spc_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_sb.sb_bsize_shift;
+	fdq->d_spc_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_sb.sb_bsize_shift;
+	fdq->d_space = be64_to_cpu(qlvb->qb_value) << sdp->sd_sb.sb_bsize_shift;
 
 	gfs2_glock_dq_uninit(&q_gh);
 out:
@@ -1541,10 +1538,10 @@ out:
 }
 
 /* GFS2 only supports a subset of the XFS fields */
-#define GFS2_FIELDMASK (FS_DQ_BSOFT|FS_DQ_BHARD|FS_DQ_BCOUNT)
+#define GFS2_FIELDMASK (QC_SPC_SOFT|QC_SPC_HARD|QC_SPACE)
 
 static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid,
-			  struct fs_disk_quota *fdq)
+			  struct qc_dqblk *fdq)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
@@ -1588,17 +1585,17 @@ static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid,
 		goto out_i;
 
 	/* If nothing has changed, this is a no-op */
-	if ((fdq->d_fieldmask & FS_DQ_BSOFT) &&
-	    ((fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_warn)))
-		fdq->d_fieldmask ^= FS_DQ_BSOFT;
+	if ((fdq->d_fieldmask & QC_SPC_SOFT) &&
+	    ((fdq->d_spc_softlimit >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_warn)))
+		fdq->d_fieldmask ^= QC_SPC_SOFT;
 
-	if ((fdq->d_fieldmask & FS_DQ_BHARD) &&
-	    ((fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_limit)))
-		fdq->d_fieldmask ^= FS_DQ_BHARD;
+	if ((fdq->d_fieldmask & QC_SPC_HARD) &&
+	    ((fdq->d_spc_hardlimit >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_limit)))
+		fdq->d_fieldmask ^= QC_SPC_HARD;
 
-	if ((fdq->d_fieldmask & FS_DQ_BCOUNT) &&
-	    ((fdq->d_bcount >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_value)))
-		fdq->d_fieldmask ^= FS_DQ_BCOUNT;
+	if ((fdq->d_fieldmask & QC_SPACE) &&
+	    ((fdq->d_space >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_value)))
+		fdq->d_fieldmask ^= QC_SPACE;
 
 	if (fdq->d_fieldmask == 0)
 		goto out_i;
diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c
index 6e560d56094..754fdf8c635 100644
--- a/fs/hfsplus/brec.c
+++ b/fs/hfsplus/brec.c
@@ -131,13 +131,16 @@ skip:
 	hfs_bnode_write(node, entry, data_off + key_len, entry_len);
 	hfs_bnode_dump(node);
 
-	if (new_node) {
-		/* update parent key if we inserted a key
-		 * at the start of the first node
-		 */
-		if (!rec && new_node != node)
-			hfs_brec_update_parent(fd);
+	/*
+	 * update parent key if we inserted a key
+	 * at the start of the node and it is not the new node
+	 */
+	if (!rec && new_node != node) {
+		hfs_bnode_read_key(node, fd->search_key, data_off + size);
+		hfs_brec_update_parent(fd);
+	}
 
+	if (new_node) {
 		hfs_bnode_put(fd->bnode);
 		if (!new_node->parent) {
 			hfs_btree_inc_height(tree);
@@ -168,9 +171,6 @@ skip:
 		goto again;
 	}
 
-	if (!rec)
-		hfs_brec_update_parent(fd);
-
 	return 0;
 }
 
@@ -370,6 +370,8 @@ again:
 	if (IS_ERR(parent))
 		return PTR_ERR(parent);
 	__hfs_brec_find(parent, fd, hfs_find_rec_by_key);
+	if (fd->record < 0)
+		return -ENOENT;
 	hfs_bnode_dump(parent);
 	rec = fd->record;
 
diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c
index d98094a9f47..ff10f3decbc 100644
--- a/fs/hfsplus/xattr.c
+++ b/fs/hfsplus/xattr.c
@@ -806,9 +806,6 @@ end_removexattr:
 static int hfsplus_osx_getxattr(struct dentry *dentry, const char *name,
 					void *buffer, size_t size, int type)
 {
-	char *xattr_name;
-	int res;
-
 	if (!strcmp(name, ""))
 		return -EINVAL;
 
@@ -818,24 +815,19 @@ static int hfsplus_osx_getxattr(struct dentry *dentry, const char *name,
 	 */
 	if (is_known_namespace(name))
 		return -EOPNOTSUPP;
-	xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN
-		+ XATTR_MAC_OSX_PREFIX_LEN + 1, GFP_KERNEL);
-	if (!xattr_name)
-		return -ENOMEM;
-	strcpy(xattr_name, XATTR_MAC_OSX_PREFIX);
-	strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name);
 
-	res = hfsplus_getxattr(dentry, xattr_name, buffer, size);
-	kfree(xattr_name);
-	return res;
+	/*
+	 * osx is the namespace we use to indicate an unprefixed
+	 * attribute on the filesystem (like the ones that OS X
+	 * creates), so we pass the name through unmodified (after
+	 * ensuring it doesn't conflict with another namespace).
+	 */
+	return hfsplus_getxattr(dentry, name, buffer, size);
 }
 
 static int hfsplus_osx_setxattr(struct dentry *dentry, const char *name,
 		const void *buffer, size_t size, int flags, int type)
 {
-	char *xattr_name;
-	int res;
-
 	if (!strcmp(name, ""))
 		return -EINVAL;
 
@@ -845,16 +837,14 @@ static int hfsplus_osx_setxattr(struct dentry *dentry, const char *name,
 	 */
 	if (is_known_namespace(name))
 		return -EOPNOTSUPP;
-	xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN
-		+ XATTR_MAC_OSX_PREFIX_LEN + 1, GFP_KERNEL);
-	if (!xattr_name)
-		return -ENOMEM;
-	strcpy(xattr_name, XATTR_MAC_OSX_PREFIX);
-	strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name);
 
-	res = hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
-	kfree(xattr_name);
-	return res;
+	/*
+	 * osx is the namespace we use to indicate an unprefixed
+	 * attribute on the filesystem (like the ones that OS X
+	 * creates), so we pass the name through unmodified (after
+	 * ensuring it doesn't conflict with another namespace).
+	 */
+	return hfsplus_setxattr(dentry, name, buffer, size, flags);
 }
 
 static size_t hfsplus_osx_listxattr(struct dentry *dentry, char *list,
diff --git a/fs/inode.c b/fs/inode.c
index 26753ba7b6d..56d1d2b4bf3 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1631,8 +1631,8 @@ int file_remove_suid(struct file *file)
 		error = security_inode_killpriv(dentry);
 	if (!error && killsuid)
 		error = __remove_suid(dentry, killsuid);
-	if (!error && (inode->i_sb->s_flags & MS_NOSEC))
-		inode->i_flags |= S_NOSEC;
+	if (!error)
+		inode_has_no_xattr(inode);
 
 	return error;
 }
diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c
index f488bbae541..735d7522a3a 100644
--- a/fs/isofs/rock.c
+++ b/fs/isofs/rock.c
@@ -30,6 +30,7 @@ struct rock_state {
 	int cont_size;
 	int cont_extent;
 	int cont_offset;
+	int cont_loops;
 	struct inode *inode;
 };
 
@@ -73,6 +74,9 @@ static void init_rock_state(struct rock_state *rs, struct inode *inode)
 	rs->inode = inode;
 }
 
+/* Maximum number of Rock Ridge continuation entries */
+#define RR_MAX_CE_ENTRIES 32
+
 /*
  * Returns 0 if the caller should continue scanning, 1 if the scan must end
  * and -ve on error.
@@ -105,6 +109,8 @@ static int rock_continue(struct rock_state *rs)
 			goto out;
 		}
 		ret = -EIO;
+		if (++rs->cont_loops >= RR_MAX_CE_ENTRIES)
+			goto out;
 		bh = sb_bread(rs->inode->i_sb, rs->cont_extent);
 		if (bh) {
 			memcpy(rs->buffer, bh->b_data + rs->cont_offset,
@@ -356,6 +362,9 @@ repeat:
 			rs.cont_size = isonum_733(rr->u.CE.size);
 			break;
 		case SIG('E', 'R'):
+			/* Invalid length of ER tag id? */
+			if (rr->u.ER.len_id + offsetof(struct rock_ridge, u.ER.data) > rr->len)
+				goto out;
 			ISOFS_SB(inode->i_sb)->s_rock = 1;
 			printk(KERN_DEBUG "ISO 9660 Extensions: ");
 			{
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 988b32ed4c8..4227dc4f743 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -390,7 +390,7 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
 	unsigned long	blocknr;
 
 	if (is_journal_aborted(journal))
-		return 1;
+		return -EIO;
 
 	if (!jbd2_journal_get_log_tail(journal, &first_tid, &blocknr))
 		return 1;
@@ -405,10 +405,9 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
 	 * jbd2_cleanup_journal_tail() doesn't get called all that often.
 	 */
 	if (journal->j_flags & JBD2_BARRIER)
-		blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
+		blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS, NULL);
 
-	__jbd2_update_log_tail(journal, first_tid, blocknr);
-	return 0;
+	return __jbd2_update_log_tail(journal, first_tid, blocknr);
 }
 
 
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 1df94fabe4e..be6f7178d23 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -885,9 +885,10 @@ int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid,
  *
  * Requires j_checkpoint_mutex
  */
-void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
+int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
 {
 	unsigned long freed;
+	int ret;
 
 	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
 
@@ -897,7 +898,10 @@ void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
 	 * space and if we lose sb update during power failure we'd replay
 	 * old transaction with possibly newly overwritten data.
 	 */
-	jbd2_journal_update_sb_log_tail(journal, tid, block, WRITE_FUA);
+	ret = jbd2_journal_update_sb_log_tail(journal, tid, block, WRITE_FUA);
+	if (ret)
+		goto out;
+
 	write_lock(&journal->j_state_lock);
 	freed = block - journal->j_tail;
 	if (block < journal->j_tail)
@@ -913,6 +917,9 @@ void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
 	journal->j_tail_sequence = tid;
 	journal->j_tail = block;
 	write_unlock(&journal->j_state_lock);
+
+out:
+	return ret;
 }
 
 /*
@@ -1331,7 +1338,7 @@ static int journal_reset(journal_t *journal)
 	return jbd2_journal_start_thread(journal);
 }
 
-static void jbd2_write_superblock(journal_t *journal, int write_op)
+static int jbd2_write_superblock(journal_t *journal, int write_op)
 {
 	struct buffer_head *bh = journal->j_sb_buffer;
 	journal_superblock_t *sb = journal->j_superblock;
@@ -1370,7 +1377,10 @@ static void jbd2_write_superblock(journal_t *journal, int write_op)
 		printk(KERN_ERR "JBD2: Error %d detected when updating "
 		       "journal superblock for %s.\n", ret,
 		       journal->j_devname);
+		jbd2_journal_abort(journal, ret);
 	}
+
+	return ret;
 }
 
 /**
@@ -1383,10 +1393,11 @@ static void jbd2_write_superblock(journal_t *journal, int write_op)
  * Update a journal's superblock information about log tail and write it to
  * disk, waiting for the IO to complete.
  */
-void jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
+int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
 				     unsigned long tail_block, int write_op)
 {
 	journal_superblock_t *sb = journal->j_superblock;
+	int ret;
 
 	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
 	jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n",
@@ -1395,13 +1406,18 @@ void jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
 	sb->s_sequence = cpu_to_be32(tail_tid);
 	sb->s_start    = cpu_to_be32(tail_block);
 
-	jbd2_write_superblock(journal, write_op);
+	ret = jbd2_write_superblock(journal, write_op);
+	if (ret)
+		goto out;
 
 	/* Log is no longer empty */
 	write_lock(&journal->j_state_lock);
 	WARN_ON(!sb->s_sequence);
 	journal->j_flags &= ~JBD2_FLUSHED;
 	write_unlock(&journal->j_state_lock);
+
+out:
+	return ret;
 }
 
 /**
@@ -1951,7 +1967,14 @@ int jbd2_journal_flush(journal_t *journal)
 		return -EIO;
 
 	mutex_lock(&journal->j_checkpoint_mutex);
-	jbd2_cleanup_journal_tail(journal);
+	if (!err) {
+		err = jbd2_cleanup_journal_tail(journal);
+		if (err < 0) {
+			mutex_unlock(&journal->j_checkpoint_mutex);
+			goto out;
+		}
+		err = 0;
+	}
 
 	/* Finally, mark the journal as really needing no recovery.
 	 * This sets s_start==0 in the underlying superblock, which is
@@ -1967,7 +1990,8 @@ int jbd2_journal_flush(journal_t *journal)
 	J_ASSERT(journal->j_head == journal->j_tail);
 	J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence);
 	write_unlock(&journal->j_state_lock);
-	return 0;
+out:
+	return err;
 }
 
 /**
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index bcbef08a4d8..a5f72a36c6c 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -839,15 +839,23 @@ static int scan_revoke_records(journal_t *journal, struct buffer_head *bh,
 {
 	jbd2_journal_revoke_header_t *header;
 	int offset, max;
+	int csum_size = 0;
+	__u32 rcount;
 	int record_len = 4;
 
 	header = (jbd2_journal_revoke_header_t *) bh->b_data;
 	offset = sizeof(jbd2_journal_revoke_header_t);
-	max = be32_to_cpu(header->r_count);
+	rcount = be32_to_cpu(header->r_count);
 
 	if (!jbd2_revoke_block_csum_verify(journal, header))
 		return -EINVAL;
 
+	if (jbd2_journal_has_csum_v2or3(journal))
+		csum_size = sizeof(struct jbd2_journal_revoke_tail);
+	if (rcount > journal->j_blocksize - csum_size)
+		return -EINVAL;
+	max = rcount;
+
 	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
 		record_len = 8;
 
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index c6cbaef2bda..14214da80eb 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -577,7 +577,7 @@ static void write_one_revoke_record(journal_t *journal,
 {
 	int csum_size = 0;
 	struct buffer_head *descriptor;
-	int offset;
+	int sz, offset;
 	journal_header_t *header;
 
 	/* If we are already aborting, this all becomes a noop.  We
@@ -594,9 +594,14 @@ static void write_one_revoke_record(journal_t *journal,
 	if (jbd2_journal_has_csum_v2or3(journal))
 		csum_size = sizeof(struct jbd2_journal_revoke_tail);
 
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
+		sz = 8;
+	else
+		sz = 4;
+
 	/* Make sure we have a descriptor with space left for the record */
 	if (descriptor) {
-		if (offset >= journal->j_blocksize - csum_size) {
+		if (offset + sz > journal->j_blocksize - csum_size) {
 			flush_descriptor(journal, descriptor, offset, write_op);
 			descriptor = NULL;
 		}
@@ -619,16 +624,13 @@ static void write_one_revoke_record(journal_t *journal,
 		*descriptorp = descriptor;
 	}
 
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) {
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
 		* ((__be64 *)(&descriptor->b_data[offset])) =
 			cpu_to_be64(record->blocknr);
-		offset += 8;
-
-	} else {
+	else
 		* ((__be32 *)(&descriptor->b_data[offset])) =
 			cpu_to_be32(record->blocknr);
-		offset += 4;
-	}
+	offset += sz;
 
 	*offsetp = offset;
 }
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 5f09370c90a..ff2f2e6ad31 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -551,7 +551,6 @@ int jbd2_journal_extend(handle_t *handle, int nblocks)
 	int result;
 	int wanted;
 
-	WARN_ON(!transaction);
 	if (is_handle_aborted(handle))
 		return -EROFS;
 	journal = transaction->t_journal;
@@ -627,7 +626,6 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask)
 	tid_t		tid;
 	int		need_to_start, ret;
 
-	WARN_ON(!transaction);
 	/* If we've had an abort of any type, don't even think about
 	 * actually doing the restart! */
 	if (is_handle_aborted(handle))
@@ -785,7 +783,6 @@ do_get_write_access(handle_t *handle, struct journal_head *jh,
 	int need_copy = 0;
 	unsigned long start_lock, time_lock;
 
-	WARN_ON(!transaction);
 	if (is_handle_aborted(handle))
 		return -EROFS;
 	journal = transaction->t_journal;
@@ -1051,7 +1048,6 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
 	int err;
 
 	jbd_debug(5, "journal_head %p\n", jh);
-	WARN_ON(!transaction);
 	err = -EROFS;
 	if (is_handle_aborted(handle))
 		goto out;
@@ -1266,7 +1262,6 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 	struct journal_head *jh;
 	int ret = 0;
 
-	WARN_ON(!transaction);
 	if (is_handle_aborted(handle))
 		return -EROFS;
 	journal = transaction->t_journal;
@@ -1397,7 +1392,6 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
 	int err = 0;
 	int was_modified = 0;
 
-	WARN_ON(!transaction);
 	if (is_handle_aborted(handle))
 		return -EROFS;
 	journal = transaction->t_journal;
@@ -1530,8 +1524,22 @@ int jbd2_journal_stop(handle_t *handle)
 	tid_t tid;
 	pid_t pid;
 
-	if (!transaction)
-		goto free_and_exit;
+	if (!transaction) {
+		/*
+		 * Handle is already detached from the transaction so
+		 * there is nothing to do other than decrease a refcount,
+		 * or free the handle if refcount drops to zero
+		 */
+		if (--handle->h_ref > 0) {
+			jbd_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1,
+							 handle->h_ref);
+			return err;
+		} else {
+			if (handle->h_rsv_handle)
+				jbd2_free_handle(handle->h_rsv_handle);
+			goto free_and_exit;
+		}
+	}
 	journal = transaction->t_journal;
 
 	J_ASSERT(journal_current_handle() == handle);
@@ -2373,7 +2381,6 @@ int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode)
 	transaction_t *transaction = handle->h_transaction;
 	journal_t *journal;
 
-	WARN_ON(!transaction);
 	if (is_handle_aborted(handle))
 		return -EROFS;
 	journal = transaction->t_journal;
diff --git a/fs/jffs2/scan.c b/fs/jffs2/scan.c
index 7654e87b042..9ad5ba4b299 100644
--- a/fs/jffs2/scan.c
+++ b/fs/jffs2/scan.c
@@ -510,6 +510,10 @@ static int jffs2_scan_eraseblock (struct jffs2_sb_info *c, struct jffs2_eraseblo
 				sumlen = c->sector_size - je32_to_cpu(sm->offset);
 				sumptr = buf + buf_size - sumlen;
 
+				/* sm->offset maybe wrong but MAGIC maybe right */
+				if (sumlen > c->sector_size)
+					goto full_scan;
+
 				/* Now, make sure the summary itself is available */
 				if (sumlen > buf_size) {
 					/* Need to kmalloc for this. */
@@ -544,6 +548,7 @@ static int jffs2_scan_eraseblock (struct jffs2_sb_info *c, struct jffs2_eraseblo
 		}
 	}
 
+full_scan:
 	buf_ofs = jeb->offset;
 
 	if (!buf_size) {
diff --git a/fs/libfs.c b/fs/libfs.c
index 171d2846f2a..005843ce5db 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -114,18 +114,18 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 
 			spin_lock(&dentry->d_lock);
 			/* d_lock not required for cursor */
-			list_del(&cursor->d_u.d_child);
+			list_del(&cursor->d_child);
 			p = dentry->d_subdirs.next;
 			while (n && p != &dentry->d_subdirs) {
 				struct dentry *next;
-				next = list_entry(p, struct dentry, d_u.d_child);
+				next = list_entry(p, struct dentry, d_child);
 				spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
 				if (simple_positive(next))
 					n--;
 				spin_unlock(&next->d_lock);
 				p = p->next;
 			}
-			list_add_tail(&cursor->d_u.d_child, p);
+			list_add_tail(&cursor->d_child, p);
 			spin_unlock(&dentry->d_lock);
 		}
 	}
@@ -150,7 +150,7 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	struct dentry *cursor = file->private_data;
-	struct list_head *p, *q = &cursor->d_u.d_child;
+	struct list_head *p, *q = &cursor->d_child;
 
 	if (!dir_emit_dots(file, ctx))
 		return 0;
@@ -159,7 +159,7 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
 		list_move(q, &dentry->d_subdirs);
 
 	for (p = q->next; p != &dentry->d_subdirs; p = p->next) {
-		struct dentry *next = list_entry(p, struct dentry, d_u.d_child);
+		struct dentry *next = list_entry(p, struct dentry, d_child);
 		spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
 		if (!simple_positive(next)) {
 			spin_unlock(&next->d_lock);
@@ -287,7 +287,7 @@ int simple_empty(struct dentry *dentry)
 	int ret = 0;
 
 	spin_lock(&dentry->d_lock);
-	list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child) {
+	list_for_each_entry(child, &dentry->d_subdirs, d_child) {
 		spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
 		if (simple_positive(child)) {
 			spin_unlock(&child->d_lock);
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 9106f42c472..67bdc0bb9ae 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -65,7 +65,7 @@ static inline struct sockaddr *nsm_addr(const struct nsm_handle *nsm)
 	return (struct sockaddr *)&nsm->sm_addr;
 }
 
-static struct rpc_clnt *nsm_create(struct net *net)
+static struct rpc_clnt *nsm_create(struct net *net, const char *nodename)
 {
 	struct sockaddr_in sin = {
 		.sin_family		= AF_INET,
@@ -77,6 +77,7 @@ static struct rpc_clnt *nsm_create(struct net *net)
 		.address		= (struct sockaddr *)&sin,
 		.addrsize		= sizeof(sin),
 		.servername		= "rpc.statd",
+		.nodename		= nodename,
 		.program		= &nsm_program,
 		.version		= NSM_VERSION,
 		.authflavor		= RPC_AUTH_NULL,
@@ -102,7 +103,7 @@ out:
 	return clnt;
 }
 
-static struct rpc_clnt *nsm_client_get(struct net *net)
+static struct rpc_clnt *nsm_client_get(struct net *net, const char *nodename)
 {
 	struct rpc_clnt	*clnt, *new;
 	struct lockd_net *ln = net_generic(net, lockd_net_id);
@@ -111,7 +112,7 @@ static struct rpc_clnt *nsm_client_get(struct net *net)
 	if (clnt != NULL)
 		goto out;
 
-	clnt = new = nsm_create(net);
+	clnt = new = nsm_create(net, nodename);
 	if (IS_ERR(clnt))
 		goto out;
 
@@ -190,19 +191,23 @@ int nsm_monitor(const struct nlm_host *host)
 	struct nsm_res	res;
 	int		status;
 	struct rpc_clnt *clnt;
+	const char *nodename = NULL;
 
 	dprintk("lockd: nsm_monitor(%s)\n", nsm->sm_name);
 
 	if (nsm->sm_monitored)
 		return 0;
 
+	if (host->h_rpcclnt)
+		nodename = host->h_rpcclnt->cl_nodename;
+
 	/*
 	 * Choose whether to record the caller_name or IP address of
 	 * this peer in the local rpc.statd's database.
 	 */
 	nsm->sm_mon_name = nsm_use_hostnames ? nsm->sm_name : nsm->sm_addrbuf;
 
-	clnt = nsm_client_get(host->net);
+	clnt = nsm_client_get(host->net, nodename);
 	if (IS_ERR(clnt)) {
 		status = PTR_ERR(clnt);
 		dprintk("lockd: failed to create NSM upcall transport, "
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index d1bb7ecfd20..61024987f97 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -138,10 +138,6 @@ lockd(void *vrqstp)
 
 	dprintk("NFS locking service started (ver " LOCKD_VERSION ").\n");
 
-	if (!nlm_timeout)
-		nlm_timeout = LOCKD_DFLT_TIMEO;
-	nlmsvc_timeout = nlm_timeout * HZ;
-
 	/*
 	 * The main request loop. We don't terminate until the last
 	 * NFS mount or NFS daemon has gone away.
@@ -350,6 +346,10 @@ static struct svc_serv *lockd_create_svc(void)
 		printk(KERN_WARNING
 			"lockd_up: no pid, %d users??\n", nlmsvc_users);
 
+	if (!nlm_timeout)
+		nlm_timeout = LOCKD_DFLT_TIMEO;
+	nlmsvc_timeout = nlm_timeout * HZ;
+
 	serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, NULL);
 	if (!serv) {
 		printk(KERN_WARNING "lockd_up: create service failed\n");
diff --git a/fs/locks.c b/fs/locks.c
index 735b8d3fa78..59e2f905e4f 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1702,7 +1702,7 @@ static int generic_delete_lease(struct file *filp)
 			break;
 	}
 	trace_generic_delete_lease(inode, fl);
-	if (fl)
+	if (fl && IS_LEASE(fl))
 		error = fl->fl_lmops->lm_change(before, F_UNLCK, &dispose);
 	spin_unlock(&inode->i_lock);
 	locks_dispose_list(&dispose);
diff --git a/fs/namei.c b/fs/namei.c
index db5fe86319e..d20f061cddd 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1560,7 +1560,8 @@ static inline int walk_component(struct nameidata *nd, struct path *path,
 
 	if (should_follow_link(path->dentry, follow)) {
 		if (nd->flags & LOOKUP_RCU) {
-			if (unlikely(unlazy_walk(nd, path->dentry))) {
+			if (unlikely(nd->path.mnt != path->mnt ||
+				     unlazy_walk(nd, path->dentry))) {
 				err = -ECHILD;
 				goto out_err;
 			}
@@ -3015,7 +3016,8 @@ finish_lookup:
 
 	if (should_follow_link(path->dentry, !symlink_ok)) {
 		if (nd->flags & LOOKUP_RCU) {
-			if (unlikely(unlazy_walk(nd, path->dentry))) {
+			if (unlikely(nd->path.mnt != path->mnt ||
+				     unlazy_walk(nd, path->dentry))) {
 				error = -ECHILD;
 				goto out;
 			}
@@ -3195,7 +3197,7 @@ static struct file *path_openat(int dfd, struct filename *pathname,
 
 	if (unlikely(file->f_flags & __O_TMPFILE)) {
 		error = do_tmpfile(dfd, pathname, nd, flags, op, file, &opened);
-		goto out;
+		goto out2;
 	}
 
 	error = path_init(dfd, pathname->name, flags | LOOKUP_PARENT, nd, &base);
@@ -3233,6 +3235,7 @@ out:
 		path_put(&nd->root);
 	if (base)
 		fput(base);
+out2:
 	if (!(opened & FILE_OPENED)) {
 		BUG_ON(!error);
 		put_filp(file);
diff --git a/fs/namespace.c b/fs/namespace.c
index 5b66b2b3624..da23ad8a2c8 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1322,14 +1322,15 @@ static inline void namespace_lock(void)
 	down_write(&namespace_sem);
 }
 
+enum umount_tree_flags {
+	UMOUNT_SYNC = 1,
+	UMOUNT_PROPAGATE = 2,
+};
 /*
  * mount_lock must be held
  * namespace_sem must be held for write
- * how = 0 => just this tree, don't propagate
- * how = 1 => propagate; we know that nobody else has reference to any victims
- * how = 2 => lazy umount
  */
-void umount_tree(struct mount *mnt, int how)
+static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 {
 	HLIST_HEAD(tmp_list);
 	struct mount *p;
@@ -1343,7 +1344,7 @@ void umount_tree(struct mount *mnt, int how)
 	hlist_for_each_entry(p, &tmp_list, mnt_hash)
 		list_del_init(&p->mnt_child);
 
-	if (how)
+	if (how & UMOUNT_PROPAGATE)
 		propagate_umount(&tmp_list);
 
 	hlist_for_each_entry(p, &tmp_list, mnt_hash) {
@@ -1351,7 +1352,7 @@ void umount_tree(struct mount *mnt, int how)
 		list_del_init(&p->mnt_list);
 		__touch_mnt_namespace(p->mnt_ns);
 		p->mnt_ns = NULL;
-		if (how < 2)
+		if (how & UMOUNT_SYNC)
 			p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
 		if (mnt_has_parent(p)) {
 			hlist_del_init(&p->mnt_mp_list);
@@ -1369,6 +1370,8 @@ void umount_tree(struct mount *mnt, int how)
 	}
 	if (last) {
 		last->mnt_hash.next = unmounted.first;
+		if (unmounted.first)
+			unmounted.first->pprev = &last->mnt_hash.next;
 		unmounted.first = tmp_list.first;
 		unmounted.first->pprev = &unmounted.first;
 	}
@@ -1454,14 +1457,14 @@ static int do_umount(struct mount *mnt, int flags)
 
 	if (flags & MNT_DETACH) {
 		if (!list_empty(&mnt->mnt_list))
-			umount_tree(mnt, 2);
+			umount_tree(mnt, UMOUNT_PROPAGATE);
 		retval = 0;
 	} else {
 		shrink_submounts(mnt);
 		retval = -EBUSY;
 		if (!propagate_mount_busy(mnt, 2)) {
 			if (!list_empty(&mnt->mnt_list))
-				umount_tree(mnt, 1);
+				umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC);
 			retval = 0;
 		}
 	}
@@ -1487,13 +1490,13 @@ void __detach_mounts(struct dentry *dentry)
 
 	namespace_lock();
 	mp = lookup_mountpoint(dentry);
-	if (!mp)
+	if (IS_ERR_OR_NULL(mp))
 		goto out_unlock;
 
 	lock_mount_hash();
 	while (!hlist_empty(&mp->m_list)) {
 		mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
-		umount_tree(mnt, 2);
+		umount_tree(mnt, 0);
 	}
 	unlock_mount_hash();
 	put_mountpoint(mp);
@@ -1544,6 +1547,9 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
 		goto dput_and_out;
 	if (mnt->mnt.mnt_flags & MNT_LOCKED)
 		goto dput_and_out;
+	retval = -EPERM;
+	if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN))
+		goto dput_and_out;
 
 	retval = do_umount(mnt, flags);
 dput_and_out:
@@ -1657,7 +1663,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 out:
 	if (res) {
 		lock_mount_hash();
-		umount_tree(res, 0);
+		umount_tree(res, UMOUNT_SYNC);
 		unlock_mount_hash();
 	}
 	return q;
@@ -1669,8 +1675,11 @@ struct vfsmount *collect_mounts(struct path *path)
 {
 	struct mount *tree;
 	namespace_lock();
-	tree = copy_tree(real_mount(path->mnt), path->dentry,
-			 CL_COPY_ALL | CL_PRIVATE);
+	if (!check_mnt(real_mount(path->mnt)))
+		tree = ERR_PTR(-EINVAL);
+	else
+		tree = copy_tree(real_mount(path->mnt), path->dentry,
+				 CL_COPY_ALL | CL_PRIVATE);
 	namespace_unlock();
 	if (IS_ERR(tree))
 		return ERR_CAST(tree);
@@ -1681,7 +1690,7 @@ void drop_collected_mounts(struct vfsmount *mnt)
 {
 	namespace_lock();
 	lock_mount_hash();
-	umount_tree(real_mount(mnt), 0);
+	umount_tree(real_mount(mnt), UMOUNT_SYNC);
 	unlock_mount_hash();
 	namespace_unlock();
 }
@@ -1864,7 +1873,7 @@ static int attach_recursive_mnt(struct mount *source_mnt,
  out_cleanup_ids:
 	while (!hlist_empty(&tree_list)) {
 		child = hlist_entry(tree_list.first, struct mount, mnt_hash);
-		umount_tree(child, 0);
+		umount_tree(child, UMOUNT_SYNC);
 	}
 	unlock_mount_hash();
 	cleanup_group_ids(source_mnt, NULL);
@@ -2041,7 +2050,7 @@ static int do_loopback(struct path *path, const char *old_name,
 	err = graft_tree(mnt, parent, mp);
 	if (err) {
 		lock_mount_hash();
-		umount_tree(mnt, 0);
+		umount_tree(mnt, UMOUNT_SYNC);
 		unlock_mount_hash();
 	}
 out2:
@@ -2098,7 +2107,13 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
 	}
 	if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) &&
 	    !(mnt_flags & MNT_NODEV)) {
-		return -EPERM;
+		/* Was the nodev implicitly added in mount? */
+		if ((mnt->mnt_ns->user_ns != &init_user_ns) &&
+		    !(sb->s_type->fs_flags & FS_USERNS_DEV_MOUNT)) {
+			mnt_flags |= MNT_NODEV;
+		} else {
+			return -EPERM;
+		}
 	}
 	if ((mnt->mnt.mnt_flags & MNT_LOCK_NOSUID) &&
 	    !(mnt_flags & MNT_NOSUID)) {
@@ -2282,6 +2297,8 @@ unlock:
 	return err;
 }
 
+static bool fs_fully_visible(struct file_system_type *fs_type, int *new_mnt_flags);
+
 /*
  * create a new mount for userspace and request it to be added into the
  * namespace's tree
@@ -2313,6 +2330,10 @@ static int do_new_mount(struct path *path, const char *fstype, int flags,
 			flags |= MS_NODEV;
 			mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV;
 		}
+		if (type->fs_flags & FS_USERNS_VISIBLE) {
+			if (!fs_fully_visible(type, &mnt_flags))
+				return -EPERM;
+		}
 	}
 
 	mnt = vfs_kern_mount(type, flags, name, data);
@@ -2406,7 +2427,7 @@ void mark_mounts_for_expiry(struct list_head *mounts)
 	while (!list_empty(&graveyard)) {
 		mnt = list_first_entry(&graveyard, struct mount, mnt_expire);
 		touch_mnt_namespace(mnt->mnt_ns);
-		umount_tree(mnt, 1);
+		umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC);
 	}
 	unlock_mount_hash();
 	namespace_unlock();
@@ -2477,7 +2498,7 @@ static void shrink_submounts(struct mount *mnt)
 			m = list_first_entry(&graveyard, struct mount,
 						mnt_expire);
 			touch_mnt_namespace(m->mnt_ns);
-			umount_tree(m, 1);
+			umount_tree(m, UMOUNT_PROPAGATE|UMOUNT_SYNC);
 		}
 	}
 }
@@ -3110,9 +3131,10 @@ bool current_chrooted(void)
 	return chrooted;
 }
 
-bool fs_fully_visible(struct file_system_type *type)
+static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags)
 {
 	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
+	int new_flags = *new_mnt_flags;
 	struct mount *mnt;
 	bool visible = false;
 
@@ -3125,16 +3147,43 @@ bool fs_fully_visible(struct file_system_type *type)
 		if (mnt->mnt.mnt_sb->s_type != type)
 			continue;
 
-		/* This mount is not fully visible if there are any child mounts
-		 * that cover anything except for empty directories.
+		/* This mount is not fully visible if it's root directory
+		 * is not the root directory of the filesystem.
+		 */
+		if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root)
+			continue;
+
+		/* Verify the mount flags are equal to or more permissive
+		 * than the proposed new mount.
+		 */
+		if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) &&
+		    !(new_flags & MNT_READONLY))
+			continue;
+		if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) &&
+		    !(new_flags & MNT_NODEV))
+			continue;
+		if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) &&
+		    ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK)))
+			continue;
+
+		/* This mount is not fully visible if there are any
+		 * locked child mounts that cover anything except for
+		 * empty directories.
 		 */
 		list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
 			struct inode *inode = child->mnt_mountpoint->d_inode;
+			/* Only worry about locked mounts */
+			if (!(mnt->mnt.mnt_flags & MNT_LOCKED))
+				continue;
 			if (!S_ISDIR(inode->i_mode))
 				goto next;
 			if (inode->i_nlink > 2)
 				goto next;
 		}
+		/* Preserve the locked attributes */
+		*new_mnt_flags |= mnt->mnt.mnt_flags & (MNT_LOCK_READONLY | \
+							MNT_LOCK_NODEV    | \
+							MNT_LOCK_ATIME);
 		visible = true;
 		goto found;
 	next:	;
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index 7cb751dfbee..75424d692fd 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -403,7 +403,7 @@ ncp_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos)
 
 	/* If a pointer is invalid, we search the dentry. */
 	spin_lock(&parent->d_lock);
-	list_for_each_entry(dent, &parent->d_subdirs, d_u.d_child) {
+	list_for_each_entry(dent, &parent->d_subdirs, d_child) {
 		if ((unsigned long)dent->d_fsdata == fpos) {
 			if (dent->d_inode)
 				dget(dent);
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index d5659d96ee7..cf7e043a944 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -447,7 +447,6 @@ static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg
 						result = -EIO;
 					}
 				}
-				result = 0;
 			}
 			mutex_unlock(&server->root_setup_lock);
 
diff --git a/fs/ncpfs/ncplib_kernel.h b/fs/ncpfs/ncplib_kernel.h
index 52cb19d66ec..b785f74bfe3 100644
--- a/fs/ncpfs/ncplib_kernel.h
+++ b/fs/ncpfs/ncplib_kernel.h
@@ -191,7 +191,7 @@ ncp_renew_dentries(struct dentry *parent)
 	struct dentry *dentry;
 
 	spin_lock(&parent->d_lock);
-	list_for_each_entry(dentry, &parent->d_subdirs, d_u.d_child) {
+	list_for_each_entry(dentry, &parent->d_subdirs, d_child) {
 		if (dentry->d_fsdata == NULL)
 			ncp_age_dentry(server, dentry);
 		else
@@ -207,7 +207,7 @@ ncp_invalidate_dircache_entries(struct dentry *parent)
 	struct dentry *dentry;
 
 	spin_lock(&parent->d_lock);
-	list_for_each_entry(dentry, &parent->d_subdirs, d_u.d_child) {
+	list_for_each_entry(dentry, &parent->d_subdirs, d_child) {
 		dentry->d_fsdata = NULL;
 		ncp_age_dentry(server, dentry);
 	}
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index b8fb3a4ef64..351be9205bf 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -128,22 +128,24 @@ nfs41_callback_svc(void *vrqstp)
 		if (try_to_freeze())
 			continue;
 
-		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE);
+		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_UNINTERRUPTIBLE);
 		spin_lock_bh(&serv->sv_cb_lock);
 		if (!list_empty(&serv->sv_cb_list)) {
 			req = list_first_entry(&serv->sv_cb_list,
 					struct rpc_rqst, rq_bc_list);
 			list_del(&req->rq_bc_list);
 			spin_unlock_bh(&serv->sv_cb_lock);
+			finish_wait(&serv->sv_cb_waitq, &wq);
 			dprintk("Invoking bc_svc_process()\n");
 			error = bc_svc_process(serv, req, rqstp);
 			dprintk("bc_svc_process() returned w/ error code= %d\n",
 				error);
 		} else {
 			spin_unlock_bh(&serv->sv_cb_lock);
-			schedule();
+			/* schedule_timeout to game the hung task watchdog */
+			schedule_timeout(60 * HZ);
+			finish_wait(&serv->sv_cb_waitq, &wq);
 		}
-		finish_wait(&serv->sv_cb_waitq, &wq);
 	}
 	return 0;
 }
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index f4ccfe6521e..02f8d09e119 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -464,8 +464,10 @@ static __be32 decode_cb_sequence_args(struct svc_rqst *rqstp,
 
 		for (i = 0; i < args->csa_nrclists; i++) {
 			status = decode_rc_list(xdr, &args->csa_rclists[i]);
-			if (status)
+			if (status) {
+				args->csa_nrclists = i;
 				goto out_free;
+			}
 		}
 	}
 	status = 0;
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 7f3f6064134..4030b558b07 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -177,8 +177,8 @@ void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred,
 				  &delegation->flags);
 			NFS_I(inode)->delegation_state = delegation->type;
 			spin_unlock(&delegation->lock);
-			put_rpccred(oldcred);
 			rcu_read_unlock();
+			put_rpccred(oldcred);
 			trace_nfs4_reclaim_delegation(inode, res->delegation_type);
 		} else {
 			/* We appear to have raced with a delegation return. */
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 6e62155abf2..7a8d67cd823 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -469,6 +469,8 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 	struct inode *inode;
 	int status;
 
+	if (!(entry->fattr->valid & NFS_ATTR_FATTR_FSID))
+		return;
 	if (filename.name[0] == '.') {
 		if (filename.len == 1)
 			return;
@@ -479,6 +481,10 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 
 	dentry = d_lookup(parent, &filename);
 	if (dentry != NULL) {
+		/* Is there a mountpoint here? If so, just exit */
+		if (!nfs_fsid_equal(&NFS_SB(dentry->d_sb)->fsid,
+					&entry->fattr->fsid))
+			goto out;
 		if (nfs_same_file(dentry, entry)) {
 			nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 			status = nfs_refresh_inode(dentry->d_inode, entry->fattr);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 10bf07280f4..a094b0c34ac 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -212,6 +212,12 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq,
  */
 ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
 {
+	struct inode *inode = iocb->ki_filp->f_mapping->host;
+
+	/* we only support swap file calling nfs_direct_IO */
+	if (!IS_SWAPFILE(inode))
+		return 0;
+
 #ifndef CONFIG_NFS_SWAP
 	dprintk("NFS: nfs_direct_IO (%pD) off/no(%Ld/%lu) EINVAL\n",
 			iocb->ki_filp, (long long) pos, iter->nr_segs);
@@ -236,7 +242,7 @@ static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
 void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
 			      struct nfs_direct_req *dreq)
 {
-	cinfo->lock = &dreq->lock;
+	cinfo->lock = &dreq->inode->i_lock;
 	cinfo->mds = &dreq->mds_cinfo;
 	cinfo->ds = &dreq->ds_cinfo;
 	cinfo->dreq = dreq;
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 880618a8b04..ebc6a0add5a 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -58,7 +58,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i
 		 */
 		spin_lock(&sb->s_root->d_inode->i_lock);
 		spin_lock(&sb->s_root->d_lock);
-		hlist_del_init(&sb->s_root->d_alias);
+		hlist_del_init(&sb->s_root->d_u.d_alias);
 		spin_unlock(&sb->s_root->d_lock);
 		spin_unlock(&sb->s_root->d_inode->i_lock);
 	}
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index efaa31c70fb..e1acc1c4ce6 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -377,7 +377,7 @@ extern struct rpc_stat nfs_rpcstat;
 
 extern int __init register_nfs_fs(void);
 extern void __exit unregister_nfs_fs(void);
-extern void nfs_sb_active(struct super_block *sb);
+extern bool nfs_sb_active(struct super_block *sb);
 extern void nfs_sb_deactive(struct super_block *sb);
 
 /* namespace.c */
@@ -495,6 +495,26 @@ extern int nfs41_walk_client_list(struct nfs_client *clp,
 				struct nfs_client **result,
 				struct rpc_cred *cred);
 
+static inline struct inode *nfs_igrab_and_active(struct inode *inode)
+{
+	inode = igrab(inode);
+	if (inode != NULL && !nfs_sb_active(inode->i_sb)) {
+		iput(inode);
+		inode = NULL;
+	}
+	return inode;
+}
+
+static inline void nfs_iput_and_deactive(struct inode *inode)
+{
+	if (inode != NULL) {
+		struct super_block *sb = inode->i_sb;
+
+		iput(inode);
+		nfs_sb_deactive(sb);
+	}
+}
+
 /*
  * Determine the device name as a string
  */
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 8f4cbe7f4aa..53853ca134e 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -1342,7 +1342,7 @@ static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req,
 	if (args->npages != 0)
 		xdr_write_pages(xdr, args->pages, 0, args->len);
 	else
-		xdr_reserve_space(xdr, NFS_ACL_INLINE_BUFSIZE);
+		xdr_reserve_space(xdr, args->len);
 
 	error = nfsacl_encode(xdr->buf, base, args->inode,
 			    (args->mask & NFS_ACL) ?
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index ffdb28d86cf..368a6b72290 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -572,20 +572,14 @@ static bool nfs4_match_clientids(struct nfs_client *a, struct nfs_client *b)
 }
 
 /*
- * Returns true if the server owners match
+ * Returns true if the server major ids match
  */
 static bool
-nfs4_match_serverowners(struct nfs_client *a, struct nfs_client *b)
+nfs4_check_clientid_trunking(struct nfs_client *a, struct nfs_client *b)
 {
 	struct nfs41_server_owner *o1 = a->cl_serverowner;
 	struct nfs41_server_owner *o2 = b->cl_serverowner;
 
-	if (o1->minor_id != o2->minor_id) {
-		dprintk("NFS: --> %s server owner minor IDs do not match\n",
-			__func__);
-		return false;
-	}
-
 	if (o1->major_id_sz != o2->major_id_sz)
 		goto out_major_mismatch;
 	if (memcmp(o1->major_id, o2->major_id, o1->major_id_sz) != 0)
@@ -646,7 +640,7 @@ int nfs41_walk_client_list(struct nfs_client *new,
 			prev = pos;
 
 			status = nfs_wait_client_init_complete(pos);
-			if (status == 0) {
+			if (pos->cl_cons_state == NFS_CS_SESSION_INITING) {
 				nfs4_schedule_lease_recovery(pos);
 				status = nfs4_wait_clnt_recover(pos);
 			}
@@ -661,7 +655,12 @@ int nfs41_walk_client_list(struct nfs_client *new,
 		if (!nfs4_match_clientids(pos, new))
 			continue;
 
-		if (!nfs4_match_serverowners(pos, new))
+		/*
+		 * Note that session trunking is just a special subcase of
+		 * client id trunking. In either case, we want to fall back
+		 * to using the existing nfs_client.
+		 */
+		if (!nfs4_check_clientid_trunking(pos, new))
 			continue;
 
 		atomic_inc(&pos->cl_count);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 69dc20a743f..c9ff4a176a2 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -38,6 +38,7 @@
 #include <linux/mm.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
+#include <linux/file.h>
 #include <linux/string.h>
 #include <linux/ratelimit.h>
 #include <linux/printk.h>
@@ -5130,9 +5131,13 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 static void nfs4_delegreturn_release(void *calldata)
 {
 	struct nfs4_delegreturndata *data = calldata;
+	struct inode *inode = data->inode;
 
-	if (data->roc)
-		pnfs_roc_release(data->inode);
+	if (inode) {
+		if (data->roc)
+			pnfs_roc_release(inode);
+		nfs_iput_and_deactive(inode);
+	}
 	kfree(calldata);
 }
 
@@ -5189,9 +5194,9 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co
 	nfs_fattr_init(data->res.fattr);
 	data->timestamp = jiffies;
 	data->rpc_status = 0;
-	data->inode = inode;
-	data->roc = list_empty(&NFS_I(inode)->open_files) ?
-		    pnfs_roc(inode) : false;
+	data->inode = nfs_igrab_and_active(inode);
+	if (data->inode)
+		data->roc = nfs4_roc(inode);
 
 	task_setup_data.callback_data = data;
 	msg.rpc_argp = &data->args;
@@ -5546,6 +5551,7 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl,
 	p->server = server;
 	atomic_inc(&lsp->ls_count);
 	p->ctx = get_nfs_open_context(ctx);
+	get_file(fl->fl_file);
 	memcpy(&p->fl, fl, sizeof(p->fl));
 	return p;
 out_free_seqid:
@@ -5635,6 +5641,7 @@ static void nfs4_lock_release(void *calldata)
 		nfs_free_seqid(data->arg.lock_seqid);
 	nfs4_put_lock_state(data->lsp);
 	put_nfs_open_context(data->ctx);
+	fput(data->fl.fl_file);
 	kfree(data);
 	dprintk("%s: done!\n", __func__);
 }
@@ -7704,6 +7711,9 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 
 	dprintk("--> %s\n", __func__);
 
+	/* nfs4_layoutget_release calls pnfs_put_layout_hdr */
+	pnfs_get_layout_hdr(NFS_I(inode)->layout);
+
 	lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags);
 	if (!lgp->args.layout.pages) {
 		nfs4_layoutget_release(lgp);
@@ -7716,9 +7726,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 	lgp->res.seq_res.sr_slot = NULL;
 	nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0);
 
-	/* nfs4_layoutget_release calls pnfs_put_layout_hdr */
-	pnfs_get_layout_hdr(NFS_I(inode)->layout);
-
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return ERR_CAST(task);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 5194933ed41..1f9d57ab8df 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1455,6 +1455,8 @@ restart:
 					spin_unlock(&state->state_lock);
 				}
 				nfs4_put_open_state(state);
+				clear_bit(NFS4CLNT_RECLAIM_NOGRACE,
+					&state->flags);
 				spin_lock(&sp->so_lock);
 				goto restart;
 			}
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 206c08a60c7..22bd1d61270 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7336,6 +7336,11 @@ nfs4_stat_to_errno(int stat)
 	.p_name   = #proc,					\
 }
 
+#define STUB(proc)		\
+[NFSPROC4_CLNT_##proc] = {	\
+	.p_name = #proc,	\
+}
+
 struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(READ,		enc_read,		dec_read),
 	PROC(WRITE,		enc_write,		dec_write),
@@ -7388,6 +7393,7 @@ struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(SECINFO_NO_NAME,	enc_secinfo_no_name,	dec_secinfo_no_name),
 	PROC(TEST_STATEID,	enc_test_stateid,	dec_test_stateid),
 	PROC(FREE_STATEID,	enc_free_stateid,	dec_free_stateid),
+	STUB(GETDEVICELIST),
 	PROC(BIND_CONN_TO_SESSION,
 			enc_bind_conn_to_session, dec_bind_conn_to_session),
 	PROC(DESTROY_CLIENTID,	enc_destroy_clientid,	dec_destroy_clientid),
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 0a5dda4d85c..354f6660931 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1445,19 +1445,19 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r
 {
 	u64 rd_size = req->wb_bytes;
 
-	WARN_ON_ONCE(pgio->pg_lseg != NULL);
-
-	if (pgio->pg_dreq == NULL)
-		rd_size = i_size_read(pgio->pg_inode) - req_offset(req);
-	else
-		rd_size = nfs_dreq_bytes_left(pgio->pg_dreq);
-
-	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
-					   req->wb_context,
-					   req_offset(req),
-					   rd_size,
-					   IOMODE_READ,
-					   GFP_KERNEL);
+	if (pgio->pg_lseg == NULL) {
+		if (pgio->pg_dreq == NULL)
+			rd_size = i_size_read(pgio->pg_inode) - req_offset(req);
+		else
+			rd_size = nfs_dreq_bytes_left(pgio->pg_dreq);
+
+		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
+						   req->wb_context,
+						   req_offset(req),
+						   rd_size,
+						   IOMODE_READ,
+						   GFP_KERNEL);
+	}
 	/* If no lseg, fall back to read through mds */
 	if (pgio->pg_lseg == NULL)
 		nfs_pageio_reset_read_mds(pgio);
@@ -1469,14 +1469,13 @@ void
 pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
 			   struct nfs_page *req, u64 wb_size)
 {
-	WARN_ON_ONCE(pgio->pg_lseg != NULL);
-
-	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
-					   req->wb_context,
-					   req_offset(req),
-					   wb_size,
-					   IOMODE_RW,
-					   GFP_NOFS);
+	if (pgio->pg_lseg == NULL)
+		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
+						   req->wb_context,
+						   req_offset(req),
+						   wb_size,
+						   IOMODE_RW,
+						   GFP_NOFS);
 	/* If no lseg, fall back to write through mds */
 	if (pgio->pg_lseg == NULL)
 		nfs_pageio_reset_write_mds(pgio);
@@ -1536,6 +1535,7 @@ int pnfs_write_done_resend_to_mds(struct nfs_pgio_header *hdr)
 	/* Resend all requests through the MDS */
 	nfs_pageio_init_write(&pgio, hdr->inode, FLUSH_STABLE, true,
 			      hdr->completion_ops);
+	set_bit(NFS_CONTEXT_RESEND_WRITES, &hdr->args.context->flags);
 	return nfs_pageio_resend(&pgio, hdr);
 }
 EXPORT_SYMBOL_GPL(pnfs_write_done_resend_to_mds);
@@ -1577,6 +1577,7 @@ pnfs_write_through_mds(struct nfs_pageio_descriptor *desc,
 		desc->pg_recoalesce = 1;
 	}
 	nfs_pgio_data_destroy(hdr);
+	hdr->release(hdr);
 }
 
 static enum pnfs_try_status
@@ -1693,6 +1694,7 @@ pnfs_read_through_mds(struct nfs_pageio_descriptor *desc,
 		desc->pg_recoalesce = 1;
 	}
 	nfs_pgio_data_destroy(hdr);
+	hdr->release(hdr);
 }
 
 /*
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 31a11b0e885..368d9395d2e 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -405,12 +405,15 @@ void __exit unregister_nfs_fs(void)
 	unregister_filesystem(&nfs_fs_type);
 }
 
-void nfs_sb_active(struct super_block *sb)
+bool nfs_sb_active(struct super_block *sb)
 {
 	struct nfs_server *server = NFS_SB(sb);
 
-	if (atomic_inc_return(&server->active) == 1)
-		atomic_inc(&sb->s_active);
+	if (!atomic_inc_not_zero(&sb->s_active))
+		return false;
+	if (atomic_inc_return(&server->active) != 1)
+		atomic_dec(&sb->s_active);
+	return true;
 }
 EXPORT_SYMBOL_GPL(nfs_sb_active);
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index f83b02dc916..6067f2a0b49 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1252,6 +1252,7 @@ static void nfs_initiate_write(struct nfs_pgio_header *hdr,
 static void nfs_redirty_request(struct nfs_page *req)
 {
 	nfs_mark_request_dirty(req);
+	set_bit(NFS_CONTEXT_RESEND_WRITES, &req->wb_context->flags);
 	nfs_unlock_request(req);
 	nfs_end_page_writeback(req);
 	nfs_release_request(req);
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 0beb023f25a..6ed585935d5 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1028,6 +1028,8 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n");
 		return status;
 	}
+	if (!file)
+		return nfserr_bad_stateid;
 
 	switch (seek->seek_whence) {
 	case NFS4_CONTENT_DATA:
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index e9c3afe4b5d..58f98ad9382 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1650,7 +1650,7 @@ __destroy_client(struct nfs4_client *clp)
 		nfs4_put_stid(&dp->dl_stid);
 	}
 	while (!list_empty(&clp->cl_revoked)) {
-		dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru);
+		dp = list_entry(clp->cl_revoked.next, struct nfs4_delegation, dl_recall_lru);
 		list_del_init(&dp->dl_recall_lru);
 		nfs4_put_stid(&dp->dl_stid);
 	}
@@ -1711,15 +1711,14 @@ static int copy_cred(struct svc_cred *target, struct svc_cred *source)
 	return 0;
 }
 
-static long long
+static int
 compare_blob(const struct xdr_netobj *o1, const struct xdr_netobj *o2)
 {
-	long long res;
-
-	res = o1->len - o2->len;
-	if (res)
-		return res;
-	return (long long)memcmp(o1->data, o2->data, o1->len);
+	if (o1->len < o2->len)
+		return -1;
+	if (o1->len > o2->len)
+		return 1;
+	return memcmp(o1->data, o2->data, o1->len);
 }
 
 static int same_name(const char *n1, const char *n2)
@@ -1907,7 +1906,7 @@ add_clp_to_name_tree(struct nfs4_client *new_clp, struct rb_root *root)
 static struct nfs4_client *
 find_clp_in_name_tree(struct xdr_netobj *name, struct rb_root *root)
 {
-	long long cmp;
+	int cmp;
 	struct rb_node *node = root->rb_node;
 	struct nfs4_client *clp;
 
@@ -3227,7 +3226,7 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
 	} else
 		nfs4_free_openowner(&oo->oo_owner);
 	spin_unlock(&clp->cl_lock);
-	return oo;
+	return ret;
 }
 
 static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *open) {
@@ -3891,11 +3890,11 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 		status = nfs4_setlease(dp);
 		goto out;
 	}
-	atomic_inc(&fp->fi_delegees);
 	if (fp->fi_had_conflict) {
 		status = -EAGAIN;
 		goto out_unlock;
 	}
+	atomic_inc(&fp->fi_delegees);
 	hash_delegation_locked(dp, fp);
 	status = 0;
 out_unlock:
@@ -4386,10 +4385,17 @@ static __be32 check_stateid_generation(stateid_t *in, stateid_t *ref, bool has_s
 	return nfserr_old_stateid;
 }
 
+static __be32 nfsd4_check_openowner_confirmed(struct nfs4_ol_stateid *ols)
+{
+	if (ols->st_stateowner->so_is_open_owner &&
+	    !(openowner(ols->st_stateowner)->oo_flags & NFS4_OO_CONFIRMED))
+		return nfserr_bad_stateid;
+	return nfs_ok;
+}
+
 static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 {
 	struct nfs4_stid *s;
-	struct nfs4_ol_stateid *ols;
 	__be32 status = nfserr_bad_stateid;
 
 	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
@@ -4419,13 +4425,7 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 		break;
 	case NFS4_OPEN_STID:
 	case NFS4_LOCK_STID:
-		ols = openlockstateid(s);
-		if (ols->st_stateowner->so_is_open_owner
-	    			&& !(openowner(ols->st_stateowner)->oo_flags
-						& NFS4_OO_CONFIRMED))
-			status = nfserr_bad_stateid;
-		else
-			status = nfs_ok;
+		status = nfsd4_check_openowner_confirmed(openlockstateid(s));
 		break;
 	default:
 		printk("unknown stateid type %x\n", s->sc_type);
@@ -4517,8 +4517,8 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
 		status = nfs4_check_fh(current_fh, stp);
 		if (status)
 			goto out;
-		if (stp->st_stateowner->so_is_open_owner
-		    && !(openowner(stp->st_stateowner)->oo_flags & NFS4_OO_CONFIRMED))
+		status = nfsd4_check_openowner_confirmed(stp);
+		if (status)
 			goto out;
 		status = nfs4_check_openmode(stp, flags);
 		if (status)
@@ -5059,7 +5059,7 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp,
 	} else
 		nfs4_free_lockowner(&lo->lo_owner);
 	spin_unlock(&clp->cl_lock);
-	return lo;
+	return ret;
 }
 
 static void
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index eeea7a90eb8..6abe9659322 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1795,9 +1795,12 @@ static __be32 nfsd4_encode_components_esc(struct xdr_stream *xdr, char sep,
 		}
 		else
 			end++;
+		if (found_esc)
+			end = next;
+
 		str = end;
 	}
-	pathlen = htonl(xdr->buf->len - pathlen_offset);
+	pathlen = htonl(count);
 	write_bytes_to_xdr_buf(xdr->buf, pathlen_offset, &pathlen, 4);
 	return 0;
 }
@@ -3226,6 +3229,7 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
 	unsigned long maxcount;
 	struct xdr_stream *xdr = &resp->xdr;
 	struct file *file = read->rd_filp;
+	struct svc_fh *fhp = read->rd_fhp;
 	int starting_len = xdr->buf->len;
 	struct raparms *ra;
 	__be32 *p;
@@ -3249,12 +3253,15 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
 	maxcount = min_t(unsigned long, maxcount, (xdr->buf->buflen - xdr->buf->len));
 	maxcount = min_t(unsigned long, maxcount, read->rd_length);
 
-	if (!read->rd_filp) {
+	if (read->rd_filp)
+		err = nfsd_permission(resp->rqstp, fhp->fh_export,
+				fhp->fh_dentry,
+				NFSD_MAY_READ|NFSD_MAY_OWNER_OVERRIDE);
+	else
 		err = nfsd_get_tmp_read_open(resp->rqstp, read->rd_fhp,
 						&file, &ra);
-		if (err)
-			goto err_truncate;
-	}
+	if (err)
+		goto err_truncate;
 
 	if (file->f_op->splice_read && resp->rqstp->rq_splice_ok)
 		err = nfsd4_encode_splice_read(resp, read, file, maxcount);
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index b2e3ff34762..090d8ce25bd 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -31,6 +31,8 @@
 #include "alloc.h"
 #include "dat.h"
 
+static void __nilfs_btree_init(struct nilfs_bmap *bmap);
+
 static struct nilfs_btree_path *nilfs_btree_alloc_path(void)
 {
 	struct nilfs_btree_path *path;
@@ -368,6 +370,34 @@ static int nilfs_btree_node_broken(const struct nilfs_btree_node *node,
 	return ret;
 }
 
+/**
+ * nilfs_btree_root_broken - verify consistency of btree root node
+ * @node: btree root node to be examined
+ * @ino: inode number
+ *
+ * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned.
+ */
+static int nilfs_btree_root_broken(const struct nilfs_btree_node *node,
+				   unsigned long ino)
+{
+	int level, flags, nchildren;
+	int ret = 0;
+
+	level = nilfs_btree_node_get_level(node);
+	flags = nilfs_btree_node_get_flags(node);
+	nchildren = nilfs_btree_node_get_nchildren(node);
+
+	if (unlikely(level < NILFS_BTREE_LEVEL_NODE_MIN ||
+		     level >= NILFS_BTREE_LEVEL_MAX ||
+		     nchildren < 0 ||
+		     nchildren > NILFS_BTREE_ROOT_NCHILDREN_MAX)) {
+		pr_crit("NILFS: bad btree root (inode number=%lu): level = %d, flags = 0x%x, nchildren = %d\n",
+			ino, level, flags, nchildren);
+		ret = 1;
+	}
+	return ret;
+}
+
 int nilfs_btree_broken_node_block(struct buffer_head *bh)
 {
 	int ret;
@@ -1713,7 +1743,7 @@ nilfs_btree_commit_convert_and_insert(struct nilfs_bmap *btree,
 
 	/* convert and insert */
 	dat = NILFS_BMAP_USE_VBN(btree) ? nilfs_bmap_get_dat(btree) : NULL;
-	nilfs_btree_init(btree);
+	__nilfs_btree_init(btree);
 	if (nreq != NULL) {
 		nilfs_bmap_commit_alloc_ptr(btree, dreq, dat);
 		nilfs_bmap_commit_alloc_ptr(btree, nreq, dat);
@@ -2294,12 +2324,23 @@ static const struct nilfs_bmap_operations nilfs_btree_ops_gc = {
 	.bop_gather_data	=	NULL,
 };
 
-int nilfs_btree_init(struct nilfs_bmap *bmap)
+static void __nilfs_btree_init(struct nilfs_bmap *bmap)
 {
 	bmap->b_ops = &nilfs_btree_ops;
 	bmap->b_nchildren_per_block =
 		NILFS_BTREE_NODE_NCHILDREN_MAX(nilfs_btree_node_size(bmap));
-	return 0;
+}
+
+int nilfs_btree_init(struct nilfs_bmap *bmap)
+{
+	int ret = 0;
+
+	__nilfs_btree_init(bmap);
+
+	if (nilfs_btree_root_broken(nilfs_btree_get_root(bmap),
+				    bmap->b_inode->i_ino))
+		ret = -EIO;
+	return ret;
 }
 
 void nilfs_btree_init_gc(struct nilfs_bmap *bmap)
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index e1fa69b341b..8b5969538f3 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -49,6 +49,8 @@ struct nilfs_iget_args {
 	int for_gc;
 };
 
+static int nilfs_iget_test(struct inode *inode, void *opaque);
+
 void nilfs_inode_add_blocks(struct inode *inode, int n)
 {
 	struct nilfs_root *root = NILFS_I(inode)->i_root;
@@ -348,6 +350,17 @@ const struct address_space_operations nilfs_aops = {
 	.is_partially_uptodate  = block_is_partially_uptodate,
 };
 
+static int nilfs_insert_inode_locked(struct inode *inode,
+				     struct nilfs_root *root,
+				     unsigned long ino)
+{
+	struct nilfs_iget_args args = {
+		.ino = ino, .root = root, .cno = 0, .for_gc = 0
+	};
+
+	return insert_inode_locked4(inode, ino, nilfs_iget_test, &args);
+}
+
 struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 {
 	struct super_block *sb = dir->i_sb;
@@ -383,7 +396,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
 		err = nilfs_bmap_read(ii->i_bmap, NULL);
 		if (err < 0)
-			goto failed_bmap;
+			goto failed_after_creation;
 
 		set_bit(NILFS_I_BMAP, &ii->i_state);
 		/* No lock is needed; iget() ensures it. */
@@ -399,21 +412,24 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 	spin_lock(&nilfs->ns_next_gen_lock);
 	inode->i_generation = nilfs->ns_next_generation++;
 	spin_unlock(&nilfs->ns_next_gen_lock);
-	insert_inode_hash(inode);
+	if (nilfs_insert_inode_locked(inode, root, ino) < 0) {
+		err = -EIO;
+		goto failed_after_creation;
+	}
 
 	err = nilfs_init_acl(inode, dir);
 	if (unlikely(err))
-		goto failed_acl; /* never occur. When supporting
+		goto failed_after_creation; /* never occur. When supporting
 				    nilfs_init_acl(), proper cancellation of
 				    above jobs should be considered */
 
 	return inode;
 
- failed_acl:
- failed_bmap:
+ failed_after_creation:
 	clear_nlink(inode);
+	unlock_new_inode(inode);
 	iput(inode);  /* raw_inode will be deleted through
-			 generic_delete_inode() */
+			 nilfs_evict_inode() */
 	goto failed;
 
  failed_ifile_create_inode:
@@ -461,8 +477,8 @@ int nilfs_read_inode_common(struct inode *inode,
 	inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
 	inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec);
 	inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
-	if (inode->i_nlink == 0 && inode->i_mode == 0)
-		return -EINVAL; /* this inode is deleted */
+	if (inode->i_nlink == 0)
+		return -ESTALE; /* this inode is deleted */
 
 	inode->i_blocks = le64_to_cpu(raw_inode->i_blocks);
 	ii->i_flags = le32_to_cpu(raw_inode->i_flags);
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 9de78f08989..0f84b257932 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -51,9 +51,11 @@ static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode)
 	int err = nilfs_add_link(dentry, inode);
 	if (!err) {
 		d_instantiate(dentry, inode);
+		unlock_new_inode(inode);
 		return 0;
 	}
 	inode_dec_link_count(inode);
+	unlock_new_inode(inode);
 	iput(inode);
 	return err;
 }
@@ -182,6 +184,7 @@ out:
 out_fail:
 	drop_nlink(inode);
 	nilfs_mark_inode_dirty(inode);
+	unlock_new_inode(inode);
 	iput(inode);
 	goto out;
 }
@@ -201,11 +204,15 @@ static int nilfs_link(struct dentry *old_dentry, struct inode *dir,
 	inode_inc_link_count(inode);
 	ihold(inode);
 
-	err = nilfs_add_nondir(dentry, inode);
-	if (!err)
+	err = nilfs_add_link(dentry, inode);
+	if (!err) {
+		d_instantiate(dentry, inode);
 		err = nilfs_transaction_commit(dir->i_sb);
-	else
+	} else {
+		inode_dec_link_count(inode);
+		iput(inode);
 		nilfs_transaction_abort(dir->i_sb);
+	}
 
 	return err;
 }
@@ -243,6 +250,7 @@ static int nilfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	nilfs_mark_inode_dirty(inode);
 	d_instantiate(dentry, inode);
+	unlock_new_inode(inode);
 out:
 	if (!err)
 		err = nilfs_transaction_commit(dir->i_sb);
@@ -255,6 +263,7 @@ out_fail:
 	drop_nlink(inode);
 	drop_nlink(inode);
 	nilfs_mark_inode_dirty(inode);
+	unlock_new_inode(inode);
 	iput(inode);
 out_dir:
 	drop_nlink(dir);
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 91093cd74f0..38570402757 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -141,7 +141,6 @@ enum {
  * @ti_save: Backup of journal_info field of task_struct
  * @ti_flags: Flags
  * @ti_count: Nest level
- * @ti_garbage:	List of inode to be put when releasing semaphore
  */
 struct nilfs_transaction_info {
 	u32			ti_magic;
@@ -150,7 +149,6 @@ struct nilfs_transaction_info {
 				   one of other filesystems has a bug. */
 	unsigned short		ti_flags;
 	unsigned short		ti_count;
-	struct list_head	ti_garbage;
 };
 
 /* ti_magic */
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 7ef18fc656c..0c3f303baf3 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -305,7 +305,6 @@ static void nilfs_transaction_lock(struct super_block *sb,
 	ti->ti_count = 0;
 	ti->ti_save = cur_ti;
 	ti->ti_magic = NILFS_TI_MAGIC;
-	INIT_LIST_HEAD(&ti->ti_garbage);
 	current->journal_info = ti;
 
 	for (;;) {
@@ -332,8 +331,6 @@ static void nilfs_transaction_unlock(struct super_block *sb)
 
 	up_write(&nilfs->ns_segctor_sem);
 	current->journal_info = ti->ti_save;
-	if (!list_empty(&ti->ti_garbage))
-		nilfs_dispose_list(nilfs, &ti->ti_garbage, 0);
 }
 
 static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci,
@@ -746,6 +743,15 @@ static void nilfs_dispose_list(struct the_nilfs *nilfs,
 	}
 }
 
+static void nilfs_iput_work_func(struct work_struct *work)
+{
+	struct nilfs_sc_info *sci = container_of(work, struct nilfs_sc_info,
+						 sc_iput_work);
+	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
+
+	nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 0);
+}
+
 static int nilfs_test_metadata_dirty(struct the_nilfs *nilfs,
 				     struct nilfs_root *root)
 {
@@ -1900,8 +1906,9 @@ static int nilfs_segctor_collect_dirty_files(struct nilfs_sc_info *sci,
 static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci,
 					     struct the_nilfs *nilfs)
 {
-	struct nilfs_transaction_info *ti = current->journal_info;
 	struct nilfs_inode_info *ii, *n;
+	int during_mount = !(sci->sc_super->s_flags & MS_ACTIVE);
+	int defer_iput = false;
 
 	spin_lock(&nilfs->ns_inode_lock);
 	list_for_each_entry_safe(ii, n, &sci->sc_dirty_files, i_dirty) {
@@ -1912,9 +1919,24 @@ static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci,
 		clear_bit(NILFS_I_BUSY, &ii->i_state);
 		brelse(ii->i_bh);
 		ii->i_bh = NULL;
-		list_move_tail(&ii->i_dirty, &ti->ti_garbage);
+		list_del_init(&ii->i_dirty);
+		if (!ii->vfs_inode.i_nlink || during_mount) {
+			/*
+			 * Defer calling iput() to avoid deadlocks if
+			 * i_nlink == 0 or mount is not yet finished.
+			 */
+			list_add_tail(&ii->i_dirty, &sci->sc_iput_queue);
+			defer_iput = true;
+		} else {
+			spin_unlock(&nilfs->ns_inode_lock);
+			iput(&ii->vfs_inode);
+			spin_lock(&nilfs->ns_inode_lock);
+		}
 	}
 	spin_unlock(&nilfs->ns_inode_lock);
+
+	if (defer_iput)
+		schedule_work(&sci->sc_iput_work);
 }
 
 /*
@@ -2583,6 +2605,8 @@ static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb,
 	INIT_LIST_HEAD(&sci->sc_segbufs);
 	INIT_LIST_HEAD(&sci->sc_write_logs);
 	INIT_LIST_HEAD(&sci->sc_gc_inodes);
+	INIT_LIST_HEAD(&sci->sc_iput_queue);
+	INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func);
 	init_timer(&sci->sc_timer);
 
 	sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT;
@@ -2609,6 +2633,8 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci)
 		ret = nilfs_segctor_construct(sci, SC_LSEG_SR);
 		nilfs_transaction_unlock(sci->sc_super);
 
+		flush_work(&sci->sc_iput_work);
+
 	} while (ret && retrycount-- > 0);
 }
 
@@ -2633,6 +2659,9 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
 		|| sci->sc_seq_request != sci->sc_seq_done);
 	spin_unlock(&sci->sc_state_lock);
 
+	if (flush_work(&sci->sc_iput_work))
+		flag = true;
+
 	if (flag || !nilfs_segctor_confirm(sci))
 		nilfs_segctor_write_out(sci);
 
@@ -2642,6 +2671,12 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
 		nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1);
 	}
 
+	if (!list_empty(&sci->sc_iput_queue)) {
+		nilfs_warning(sci->sc_super, __func__,
+			      "iput queue is not empty\n");
+		nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1);
+	}
+
 	WARN_ON(!list_empty(&sci->sc_segbufs));
 	WARN_ON(!list_empty(&sci->sc_write_logs));
 
diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h
index 38a1d001331..a48d6de1e02 100644
--- a/fs/nilfs2/segment.h
+++ b/fs/nilfs2/segment.h
@@ -26,6 +26,7 @@
 #include <linux/types.h>
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
+#include <linux/workqueue.h>
 #include <linux/nilfs2_fs.h>
 #include "nilfs.h"
 
@@ -92,6 +93,8 @@ struct nilfs_segsum_pointer {
  * @sc_nblk_inc: Block count of current generation
  * @sc_dirty_files: List of files to be written
  * @sc_gc_inodes: List of GC inodes having blocks to be written
+ * @sc_iput_queue: list of inodes for which iput should be done
+ * @sc_iput_work: work struct to defer iput call
  * @sc_freesegs: array of segment numbers to be freed
  * @sc_nfreesegs: number of segments on @sc_freesegs
  * @sc_dsync_inode: inode whose data pages are written for a sync operation
@@ -135,6 +138,8 @@ struct nilfs_sc_info {
 
 	struct list_head	sc_dirty_files;
 	struct list_head	sc_gc_inodes;
+	struct list_head	sc_iput_queue;
+	struct work_struct	sc_iput_work;
 
 	__u64		       *sc_freesegs;
 	size_t			sc_nfreesegs;
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 89326acd456..41e39102743 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -63,14 +63,14 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
 	spin_lock(&inode->i_lock);
 	/* run all of the dentries associated with this inode.  Since this is a
 	 * directory, there damn well better only be one item on this list */
-	hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
 		struct dentry *child;
 
 		/* run all of the children of the original inode and fix their
 		 * d_flags to indicate parental interest (their parent is the
 		 * original inode) */
 		spin_lock(&alias->d_lock);
-		list_for_each_entry(child, &alias->d_subdirs, d_u.d_child) {
+		list_for_each_entry(child, &alias->d_subdirs, d_child) {
 			if (!child->d_inode)
 				continue;
 
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 1ef547e4937..c71174a0b1b 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -894,7 +894,7 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
 	}
 }
 
-static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc)
 {
 	int i;
 
@@ -915,7 +915,11 @@ static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
 		page_cache_release(wc->w_target_page);
 	}
 	ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
+}
 
+static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+{
+	ocfs2_unlock_pages(wc);
 	brelse(wc->w_di_bh);
 	kfree(wc);
 }
@@ -2042,11 +2046,19 @@ out_write_size:
 	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 	ocfs2_journal_dirty(handle, wc->w_di_bh);
 
+	/* unlock pages before dealloc since it needs acquiring j_trans_barrier
+	 * lock, or it will cause a deadlock since journal commit threads holds
+	 * this lock and will ask for the page lock when flushing the data.
+	 * put it here to preserve the unlock order.
+	 */
+	ocfs2_unlock_pages(wc);
+
 	ocfs2_commit_trans(osb, handle);
 
 	ocfs2_run_deallocs(osb, &wc->w_dealloc);
 
-	ocfs2_free_write_ctxt(wc);
+	brelse(wc->w_di_bh);
+	kfree(wc);
 
 	return copied;
 }
diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index e2e05a106be..92edcfc23c1 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -172,7 +172,7 @@ struct dentry *ocfs2_find_local_alias(struct inode *inode,
 	struct dentry *dentry;
 
 	spin_lock(&inode->i_lock);
-	hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
 		spin_lock(&dentry->d_lock);
 		if (ocfs2_match_dentry(dentry, parent_blkno, skip_unhashed)) {
 			trace_ocfs2_find_local_alias(dentry->d_name.len,
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 215e41abf10..9ec1eea7c3a 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -765,6 +765,19 @@ lookup:
 	if (tmpres) {
 		spin_unlock(&dlm->spinlock);
 		spin_lock(&tmpres->spinlock);
+
+		/*
+		 * Right after dlm spinlock was released, dlm_thread could have
+		 * purged the lockres. Check if lockres got unhashed. If so
+		 * start over.
+		 */
+		if (hlist_unhashed(&tmpres->hash_node)) {
+			spin_unlock(&tmpres->spinlock);
+			dlm_lockres_put(tmpres);
+			tmpres = NULL;
+			goto lookup;
+		}
+
 		/* Wait on the thread that is mastering the resource */
 		if (tmpres->owner == DLM_LOCK_RES_OWNER_UNKNOWN) {
 			__dlm_wait_on_lockres(tmpres);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 324dc93ac89..e6e8d6449b4 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2374,10 +2374,14 @@ out_dio:
 	/* buffered aio wouldn't have proper lock coverage today */
 	BUG_ON(ret == -EIOCBQUEUED && !(file->f_flags & O_DIRECT));
 
+	if (unlikely(written <= 0))
+		goto no_sync;
+
 	if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) ||
 	    ((file->f_flags & O_DIRECT) && !direct_io)) {
-		ret = filemap_fdatawrite_range(file->f_mapping, *ppos,
-					       *ppos + count - 1);
+		ret = filemap_fdatawrite_range(file->f_mapping,
+					       iocb->ki_pos - written,
+					       iocb->ki_pos - 1);
 		if (ret < 0)
 			written = ret;
 
@@ -2390,10 +2394,12 @@ out_dio:
 		}
 
 		if (!ret)
-			ret = filemap_fdatawait_range(file->f_mapping, *ppos,
-						      *ppos + count - 1);
+			ret = filemap_fdatawait_range(file->f_mapping,
+						      iocb->ki_pos - written,
+						      iocb->ki_pos - 1);
 	}
 
+no_sync:
 	/*
 	 * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io
 	 * function pointer which is called when o_direct io completes so that
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index b931e04e338..914c121ec89 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -94,6 +94,14 @@ static int ocfs2_create_symlink_data(struct ocfs2_super *osb,
 				     struct inode *inode,
 				     const char *symname);
 
+static int ocfs2_double_lock(struct ocfs2_super *osb,
+			     struct buffer_head **bh1,
+			     struct inode *inode1,
+			     struct buffer_head **bh2,
+			     struct inode *inode2,
+			     int rename);
+
+static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2);
 /* An orphan dir name is an 8 byte value, printed as a hex string */
 #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64)))
 
@@ -678,8 +686,10 @@ static int ocfs2_link(struct dentry *old_dentry,
 {
 	handle_t *handle;
 	struct inode *inode = old_dentry->d_inode;
+	struct inode *old_dir = old_dentry->d_parent->d_inode;
 	int err;
 	struct buffer_head *fe_bh = NULL;
+	struct buffer_head *old_dir_bh = NULL;
 	struct buffer_head *parent_fe_bh = NULL;
 	struct ocfs2_dinode *fe = NULL;
 	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
@@ -696,19 +706,33 @@ static int ocfs2_link(struct dentry *old_dentry,
 
 	dquot_initialize(dir);
 
-	err = ocfs2_inode_lock_nested(dir, &parent_fe_bh, 1, OI_LS_PARENT);
+	err = ocfs2_double_lock(osb, &old_dir_bh, old_dir,
+			&parent_fe_bh, dir, 0);
 	if (err < 0) {
 		if (err != -ENOENT)
 			mlog_errno(err);
 		return err;
 	}
 
+	/* make sure both dirs have bhs
+	 * get an extra ref on old_dir_bh if old==new */
+	if (!parent_fe_bh) {
+		if (old_dir_bh) {
+			parent_fe_bh = old_dir_bh;
+			get_bh(parent_fe_bh);
+		} else {
+			mlog(ML_ERROR, "%s: no old_dir_bh!\n", osb->uuid_str);
+			err = -EIO;
+			goto out;
+		}
+	}
+
 	if (!dir->i_nlink) {
 		err = -ENOENT;
 		goto out;
 	}
 
-	err = ocfs2_lookup_ino_from_name(dir, old_dentry->d_name.name,
+	err = ocfs2_lookup_ino_from_name(old_dir, old_dentry->d_name.name,
 			old_dentry->d_name.len, &old_de_ino);
 	if (err) {
 		err = -ENOENT;
@@ -801,10 +825,11 @@ out_unlock_inode:
 	ocfs2_inode_unlock(inode, 1);
 
 out:
-	ocfs2_inode_unlock(dir, 1);
+	ocfs2_double_unlock(old_dir, dir);
 
 	brelse(fe_bh);
 	brelse(parent_fe_bh);
+	brelse(old_dir_bh);
 
 	ocfs2_free_dir_lookup_result(&lookup);
 
@@ -1072,14 +1097,15 @@ static int ocfs2_check_if_ancestor(struct ocfs2_super *osb,
 }
 
 /*
- * The only place this should be used is rename!
+ * The only place this should be used is rename and link!
  * if they have the same id, then the 1st one is the only one locked.
  */
 static int ocfs2_double_lock(struct ocfs2_super *osb,
 			     struct buffer_head **bh1,
 			     struct inode *inode1,
 			     struct buffer_head **bh2,
-			     struct inode *inode2)
+			     struct inode *inode2,
+			     int rename)
 {
 	int status;
 	int inode1_is_ancestor, inode2_is_ancestor;
@@ -1127,7 +1153,7 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 		}
 		/* lock id2 */
 		status = ocfs2_inode_lock_nested(inode2, bh2, 1,
-						 OI_LS_RENAME1);
+				rename == 1 ? OI_LS_RENAME1 : OI_LS_PARENT);
 		if (status < 0) {
 			if (status != -ENOENT)
 				mlog_errno(status);
@@ -1136,7 +1162,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 	}
 
 	/* lock id1 */
-	status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_RENAME2);
+	status = ocfs2_inode_lock_nested(inode1, bh1, 1,
+			rename == 1 ?  OI_LS_RENAME2 : OI_LS_PARENT);
 	if (status < 0) {
 		/*
 		 * An error return must mean that no cluster locks
@@ -1252,7 +1279,7 @@ static int ocfs2_rename(struct inode *old_dir,
 
 	/* if old and new are the same, this'll just do one lock. */
 	status = ocfs2_double_lock(osb, &old_dir_bh, old_dir,
-				   &new_dir_bh, new_dir);
+				   &new_dir_bh, new_dir, 1);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 10b653930ee..465223b7592 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -701,8 +701,8 @@ static int ocfs2_local_read_info(struct super_block *sb, int type)
 	/* We don't need the lock and we have to acquire quota file locks
 	 * which will later depend on this lock */
 	mutex_unlock(&sb_dqopt(sb)->dqio_mutex);
-	info->dqi_maxblimit = 0x7fffffffffffffffLL;
-	info->dqi_maxilimit = 0x7fffffffffffffffLL;
+	info->dqi_max_spc_limit = 0x7fffffffffffffffLL;
+	info->dqi_max_ino_limit = 0x7fffffffffffffffLL;
 	oinfo = kmalloc(sizeof(struct ocfs2_mem_dqinfo), GFP_NOFS);
 	if (!oinfo) {
 		mlog(ML_ERROR, "failed to allocate memory for ocfs2 quota"
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index 138321b0c6c..454111a3308 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -306,7 +306,8 @@ static const struct super_operations omfs_sops = {
  */
 static int omfs_get_imap(struct super_block *sb)
 {
-	unsigned int bitmap_size, count, array_size;
+	unsigned int bitmap_size, array_size;
+	int count;
 	struct omfs_sb_info *sbi = OMFS_SB(sb);
 	struct buffer_head *bh;
 	unsigned long **ptr;
@@ -359,7 +360,7 @@ nomem:
 }
 
 enum {
-	Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask
+	Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask, Opt_err
 };
 
 static const match_table_t tokens = {
@@ -368,6 +369,7 @@ static const match_table_t tokens = {
 	{Opt_umask, "umask=%o"},
 	{Opt_dmask, "dmask=%o"},
 	{Opt_fmask, "fmask=%o"},
+	{Opt_err, NULL},
 };
 
 static int parse_options(char *options, struct omfs_sb_info *sbi)
diff --git a/fs/open.c b/fs/open.c
index de92c13b58b..4a8a355ffab 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -558,6 +558,7 @@ static int chown_common(struct path *path, uid_t user, gid_t group)
 	uid = make_kuid(current_user_ns(), user);
 	gid = make_kgid(current_user_ns(), group);
 
+retry_deleg:
 	newattrs.ia_valid =  ATTR_CTIME;
 	if (user != (uid_t) -1) {
 		if (!uid_valid(uid))
@@ -574,7 +575,6 @@ static int chown_common(struct path *path, uid_t user, gid_t group)
 	if (!S_ISDIR(inode->i_mode))
 		newattrs.ia_valid |=
 			ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
-retry_deleg:
 	mutex_lock(&inode->i_mutex);
 	error = security_path_chown(path, uid, gid);
 	if (!error)
diff --git a/fs/pnode.h b/fs/pnode.h
index 4a246358b03..16afc3d6d2f 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -47,7 +47,6 @@ int get_dominating_id(struct mount *mnt, const struct path *root);
 unsigned int mnt_get_count(struct mount *mnt);
 void mnt_set_mountpoint(struct mount *, struct mountpoint *,
 			struct mount *);
-void umount_tree(struct mount *, int);
 struct mount *copy_tree(struct mount *, struct dentry *, int);
 bool is_path_reachable(struct mount *, struct dentry *,
 			 const struct path *root);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 772efa45a45..e1b04048108 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2464,6 +2464,57 @@ static const struct file_operations proc_projid_map_operations = {
 	.llseek		= seq_lseek,
 	.release	= proc_id_map_release,
 };
+
+static int proc_setgroups_open(struct inode *inode, struct file *file)
+{
+	struct user_namespace *ns = NULL;
+	struct task_struct *task;
+	int ret;
+
+	ret = -ESRCH;
+	task = get_proc_task(inode);
+	if (task) {
+		rcu_read_lock();
+		ns = get_user_ns(task_cred_xxx(task, user_ns));
+		rcu_read_unlock();
+		put_task_struct(task);
+	}
+	if (!ns)
+		goto err;
+
+	if (file->f_mode & FMODE_WRITE) {
+		ret = -EACCES;
+		if (!ns_capable(ns, CAP_SYS_ADMIN))
+			goto err_put_ns;
+	}
+
+	ret = single_open(file, &proc_setgroups_show, ns);
+	if (ret)
+		goto err_put_ns;
+
+	return 0;
+err_put_ns:
+	put_user_ns(ns);
+err:
+	return ret;
+}
+
+static int proc_setgroups_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct user_namespace *ns = seq->private;
+	int ret = single_release(inode, file);
+	put_user_ns(ns);
+	return ret;
+}
+
+static const struct file_operations proc_setgroups_operations = {
+	.open		= proc_setgroups_open,
+	.write		= proc_setgroups_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_setgroups_release,
+};
 #endif /* CONFIG_USER_NS */
 
 static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
@@ -2550,8 +2601,8 @@ static const struct pid_entry tgid_base_stuff[] = {
 	ONE("cgroup",  S_IRUGO, proc_cgroup_show),
 #endif
 	ONE("oom_score",  S_IRUGO, proc_oom_score),
-	REG("oom_adj",    S_IRUGO|S_IWUSR, proc_oom_adj_operations),
-	REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
+	REG("oom_adj",    S_IRUSR, proc_oom_adj_operations),
+	REG("oom_score_adj", S_IRUSR, proc_oom_score_adj_operations),
 #ifdef CONFIG_AUDITSYSCALL
 	REG("loginuid",   S_IWUSR|S_IRUGO, proc_loginuid_operations),
 	REG("sessionid",  S_IRUGO, proc_sessionid_operations),
@@ -2572,6 +2623,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("uid_map",    S_IRUGO|S_IWUSR, proc_uid_map_operations),
 	REG("gid_map",    S_IRUGO|S_IWUSR, proc_gid_map_operations),
 	REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
+	REG("setgroups",  S_IRUGO|S_IWUSR, proc_setgroups_operations),
 #endif
 #ifdef CONFIG_CHECKPOINT_RESTORE
 	REG("timers",	  S_IRUGO, proc_timers_operations),
@@ -2894,8 +2946,8 @@ static const struct pid_entry tid_base_stuff[] = {
 	ONE("cgroup",  S_IRUGO, proc_cgroup_show),
 #endif
 	ONE("oom_score", S_IRUGO, proc_oom_score),
-	REG("oom_adj",   S_IRUGO|S_IWUSR, proc_oom_adj_operations),
-	REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
+	REG("oom_adj",   S_IRUSR, proc_oom_adj_operations),
+	REG("oom_score_adj", S_IRUSR, proc_oom_score_adj_operations),
 #ifdef CONFIG_AUDITSYSCALL
 	REG("loginuid",  S_IWUSR|S_IRUGO, proc_loginuid_operations),
 	REG("sessionid",  S_IRUGO, proc_sessionid_operations),
@@ -2913,6 +2965,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	REG("uid_map",    S_IRUGO|S_IWUSR, proc_uid_map_operations),
 	REG("gid_map",    S_IRUGO|S_IWUSR, proc_gid_map_operations),
 	REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
+	REG("setgroups",  S_IRUGO|S_IWUSR, proc_setgroups_operations),
 #endif
 };
 
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 317b72641eb..228cc4eeeb4 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -19,7 +19,6 @@
 #include <linux/mount.h>
 #include <linux/init.h>
 #include <linux/idr.h>
-#include <linux/namei.h>
 #include <linux/bitops.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
@@ -162,17 +161,6 @@ void proc_free_inum(unsigned int inum)
 	spin_unlock_irqrestore(&proc_inum_lock, flags);
 }
 
-static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	nd_set_link(nd, __PDE_DATA(dentry->d_inode));
-	return NULL;
-}
-
-static const struct inode_operations proc_link_inode_operations = {
-	.readlink	= generic_readlink,
-	.follow_link	= proc_follow_link,
-};
-
 /*
  * Don't create negative dentries here, return -ENOENT by hand
  * instead.
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 333080d7a67..54ed31cfb39 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/mount.h>
 #include <linux/magic.h>
+#include <linux/namei.h>
 
 #include <asm/uaccess.h>
 
@@ -401,6 +402,26 @@ static const struct file_operations proc_reg_file_ops_no_compat = {
 };
 #endif
 
+static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	struct proc_dir_entry *pde = PDE(dentry->d_inode);
+	if (unlikely(!use_pde(pde)))
+		return ERR_PTR(-EINVAL);
+	nd_set_link(nd, pde->data);
+	return pde;
+}
+
+static void proc_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
+{
+	unuse_pde(p);
+}
+
+const struct inode_operations proc_link_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= proc_follow_link,
+	.put_link	= proc_put_link,
+};
+
 struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 {
 	struct inode *inode = new_inode_pseudo(sb);
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index aa7a0ee182e..73f8190de79 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -199,6 +199,7 @@ struct pde_opener {
 	int closing;
 	struct completion *c;
 };
+extern const struct inode_operations proc_link_inode_operations;
 
 extern const struct inode_operations proc_pid_link_inode_operations;
 
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 094e44d4a6b..9e772f1a538 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -112,9 +112,6 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
 		ns = task_active_pid_ns(current);
 		options = data;
 
-		if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
-			return ERR_PTR(-EPERM);
-
 		/* Does the mounter have privilege over the pid namespace? */
 		if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
 			return ERR_PTR(-EPERM);
@@ -159,7 +156,7 @@ static struct file_system_type proc_fs_type = {
 	.name		= "proc",
 	.mount		= proc_mount,
 	.kill_sb	= proc_kill_sb,
-	.fs_flags	= FS_USERNS_MOUNT,
+	.fs_flags	= FS_USERNS_VISIBLE | FS_USERNS_MOUNT,
 };
 
 void __init proc_root_init(void)
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index bf2d03f8fd3..510413eb25b 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -159,7 +159,7 @@ static int show_stat(struct seq_file *p, void *v)
 
 	/* sum again ? it could be updated? */
 	for_each_irq_nr(j)
-		seq_put_decimal_ull(p, ' ', kstat_irqs(j));
+		seq_put_decimal_ull(p, ' ', kstat_irqs_usr(j));
 
 	seq_printf(p,
 		"\nctxt %llu\n"
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 4e0388cffe3..23c697ed974 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -111,6 +111,56 @@ static void release_task_mempolicy(struct proc_maps_private *priv)
 }
 #endif
 
+static void seq_print_vma_name(struct seq_file *m, struct vm_area_struct *vma)
+{
+	const char __user *name = vma_get_anon_name(vma);
+	struct mm_struct *mm = vma->vm_mm;
+
+	unsigned long page_start_vaddr;
+	unsigned long page_offset;
+	unsigned long num_pages;
+	unsigned long max_len = NAME_MAX;
+	int i;
+
+	page_start_vaddr = (unsigned long)name & PAGE_MASK;
+	page_offset = (unsigned long)name - page_start_vaddr;
+	num_pages = DIV_ROUND_UP(page_offset + max_len, PAGE_SIZE);
+
+	seq_puts(m, "[anon:");
+
+	for (i = 0; i < num_pages; i++) {
+		int len;
+		int write_len;
+		const char *kaddr;
+		long pages_pinned;
+		struct page *page;
+
+		pages_pinned = get_user_pages(current, mm, page_start_vaddr,
+				1, 0, 0, &page, NULL);
+		if (pages_pinned < 1) {
+			seq_puts(m, "<fault>]");
+			return;
+		}
+
+		kaddr = (const char *)kmap(page);
+		len = min(max_len, PAGE_SIZE - page_offset);
+		write_len = strnlen(kaddr + page_offset, len);
+		seq_write(m, kaddr + page_offset, write_len);
+		kunmap(page);
+		put_page(page);
+
+		/* if strnlen hit a null terminator then we're done */
+		if (write_len != len)
+			break;
+
+		max_len -= len;
+		page_offset = 0;
+		page_start_vaddr += PAGE_SIZE;
+	}
+
+	seq_putc(m, ']');
+}
+
 static void vma_stop(struct proc_maps_private *priv)
 {
 	struct mm_struct *mm = priv->mm;
@@ -346,6 +396,12 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 				seq_pad(m, ' ');
 				seq_printf(m, "[stack:%d]", tid);
 			}
+			goto done;
+		}
+
+		if (vma_get_anon_name(vma)) {
+			seq_pad(m, ' ');
+			seq_print_vma_name(m, vma);
 		}
 	}
 
@@ -602,6 +658,12 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 
 	show_map_vma(m, vma, is_pid);
 
+	if (vma_get_anon_name(vma)) {
+		seq_puts(m, "Name:           ");
+		seq_print_vma_name(m, vma);
+		seq_putc(m, '\n');
+	}
+
 	seq_printf(m,
 		   "Size:           %8lu kB\n"
 		   "Rss:            %8lu kB\n"
@@ -712,6 +774,7 @@ enum clear_refs_types {
 	CLEAR_REFS_ANON,
 	CLEAR_REFS_MAPPED,
 	CLEAR_REFS_SOFT_DIRTY,
+	CLEAR_REFS_MM_HIWATER_RSS,
 	CLEAR_REFS_LAST,
 };
 
@@ -826,6 +889,18 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 			.mm = mm,
 			.private = &cp,
 		};
+
+		if (type == CLEAR_REFS_MM_HIWATER_RSS) {
+			/*
+			 * Writing 5 to /proc/pid/clear_refs resets the peak
+			 * resident set size to this mm's current rss value.
+			 */
+			down_write(&mm->mmap_sem);
+			reset_mm_hiwater_rss(mm);
+			up_write(&mm->mmap_sem);
+			goto out_mm;
+		}
+
 		down_read(&mm->mmap_sem);
 		if (type == CLEAR_REFS_SOFT_DIRTY) {
 			for (vma = mm->mmap; vma; vma = vma->vm_next) {
@@ -868,6 +943,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 			mmu_notifier_invalidate_range_end(mm, 0, -1);
 		flush_tlb_mm(mm);
 		up_read(&mm->mmap_sem);
+out_mm:
 		mmput(mm);
 	}
 	put_task_struct(task);
@@ -1034,7 +1110,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	struct vm_area_struct *vma;
 	struct pagemapread *pm = walk->private;
 	spinlock_t *ptl;
-	pte_t *pte;
+	pte_t *pte, *orig_pte;
 	int err = 0;
 
 	/* find the first VMA at or above 'addr' */
@@ -1095,15 +1171,19 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		BUG_ON(is_vm_hugetlb_page(vma));
 
 		/* Addresses in the VMA. */
-		for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) {
+		orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+		for (; addr < min(end, vma->vm_end); pte++, addr += PAGE_SIZE) {
 			pagemap_entry_t pme;
-			pte = pte_offset_map(pmd, addr);
+
 			pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
-			pte_unmap(pte);
 			err = add_to_pagemap(addr, &pme, pm);
 			if (err)
-				return err;
+				break;
 		}
+		pte_unmap_unlock(orig_pte, ptl);
+
+		if (err)
+			return err;
 
 		if (addr == end)
 			break;
@@ -1287,6 +1367,9 @@ out:
 
 static int pagemap_open(struct inode *inode, struct file *file)
 {
+	/* do not disclose physical addresses: attack vector */
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
 	pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about "
 			"to stop being page-shift some time soon. See the "
 			"linux/Documentation/vm/pagemap.txt for details.\n");
diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig
index 983d9510bec..916b8e23d96 100644
--- a/fs/pstore/Kconfig
+++ b/fs/pstore/Kconfig
@@ -21,6 +21,16 @@ config PSTORE_CONSOLE
 	  When the option is enabled, pstore will log all kernel
 	  messages, even if no oops or panic happened.
 
+config PSTORE_PMSG
+	bool "Log user space messages"
+	depends on PSTORE
+	help
+	  When the option is enabled, pstore will export a character
+	  interface /dev/pmsg0 to log user space messages. On reboot
+	  data can be retrieved from /sys/fs/pstore/pmsg-ramoops-[ID].
+
+	  If unsure, say N.
+
 config PSTORE_FTRACE
 	bool "Persistent function tracer"
 	depends on PSTORE
diff --git a/fs/pstore/Makefile b/fs/pstore/Makefile
index 4c9095c2781..e647d8e8171 100644
--- a/fs/pstore/Makefile
+++ b/fs/pstore/Makefile
@@ -7,5 +7,7 @@ obj-y += pstore.o
 pstore-objs += inode.o platform.o
 obj-$(CONFIG_PSTORE_FTRACE)	+= ftrace.o
 
+obj-$(CONFIG_PSTORE_PMSG)	+= pmsg.o
+
 ramoops-objs += ram.o ram_core.o
 obj-$(CONFIG_PSTORE_RAM)	+= ramoops.o
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index fafb7a02a5d..6dce93c8ac2 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -316,32 +316,38 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
 
 	switch (type) {
 	case PSTORE_TYPE_DMESG:
-		sprintf(name, "dmesg-%s-%lld%s", psname, id,
-						compressed ? ".enc.z" : "");
+		scnprintf(name, sizeof(name), "dmesg-%s-%lld%s",
+			  psname, id, compressed ? ".enc.z" : "");
 		break;
 	case PSTORE_TYPE_CONSOLE:
-		sprintf(name, "console-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "console-%s", psname);
 		break;
 	case PSTORE_TYPE_FTRACE:
-		sprintf(name, "ftrace-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "ftrace-%s", psname);
 		break;
 	case PSTORE_TYPE_MCE:
-		sprintf(name, "mce-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "mce-%s-%lld", psname, id);
 		break;
 	case PSTORE_TYPE_PPC_RTAS:
-		sprintf(name, "rtas-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "rtas-%s-%lld", psname, id);
 		break;
 	case PSTORE_TYPE_PPC_OF:
-		sprintf(name, "powerpc-ofw-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "powerpc-ofw-%s-%lld",
+			  psname, id);
 		break;
 	case PSTORE_TYPE_PPC_COMMON:
-		sprintf(name, "powerpc-common-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "powerpc-common-%s-%lld",
+			  psname, id);
+		break;
+	case PSTORE_TYPE_PMSG:
+		scnprintf(name, sizeof(name), "pmsg-%s-%lld", psname, id);
 		break;
 	case PSTORE_TYPE_UNKNOWN:
-		sprintf(name, "unknown-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "unknown-%s-%lld", psname, id);
 		break;
 	default:
-		sprintf(name, "type%d-%s-%lld", type, psname, id);
+		scnprintf(name, sizeof(name), "type%d-%s-%lld",
+			  type, psname, id);
 		break;
 	}
 
diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h
index 3b3d305277c..c36ba2cd0b5 100644
--- a/fs/pstore/internal.h
+++ b/fs/pstore/internal.h
@@ -45,6 +45,12 @@ extern void pstore_register_ftrace(void);
 static inline void pstore_register_ftrace(void) {}
 #endif
 
+#ifdef CONFIG_PSTORE_PMSG
+extern void pstore_register_pmsg(void);
+#else
+static inline void pstore_register_pmsg(void) {}
+#endif
+
 extern struct pstore_info *psinfo;
 
 extern void	pstore_set_kmsg_bytes(int);
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 0a9b72cdfec..15ee78c5020 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -447,6 +447,7 @@ int pstore_register(struct pstore_info *psi)
 	if ((psi->flags & PSTORE_FLAGS_FRAGILE) == 0) {
 		pstore_register_console();
 		pstore_register_ftrace();
+		pstore_register_pmsg();
 	}
 
 	if (pstore_update_ms >= 0) {
diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c
new file mode 100644
index 00000000000..5a2f05a16c1
--- /dev/null
+++ b/fs/pstore/pmsg.c
@@ -0,0 +1,116 @@
+/*
+ * Copyright 2014  Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/cdev.h>
+#include <linux/device.h>
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include "internal.h"
+
+static DEFINE_MUTEX(pmsg_lock);
+#define PMSG_MAX_BOUNCE_BUFFER_SIZE (2*PAGE_SIZE)
+
+static ssize_t write_pmsg(struct file *file, const char __user *buf,
+			  size_t count, loff_t *ppos)
+{
+	size_t i, buffer_size;
+	char *buffer;
+
+	if (!count)
+		return 0;
+
+	if (!access_ok(VERIFY_READ, buf, count))
+		return -EFAULT;
+
+	buffer_size = count;
+	if (buffer_size > PMSG_MAX_BOUNCE_BUFFER_SIZE)
+		buffer_size = PMSG_MAX_BOUNCE_BUFFER_SIZE;
+	buffer = vmalloc(buffer_size);
+	if (!buffer)
+		return -ENOMEM;
+
+	mutex_lock(&pmsg_lock);
+	for (i = 0; i < count; ) {
+		size_t c = min(count - i, buffer_size);
+		u64 id;
+		long ret;
+
+		ret = __copy_from_user(buffer, buf + i, c);
+		if (unlikely(ret != 0)) {
+			mutex_unlock(&pmsg_lock);
+			vfree(buffer);
+			return -EFAULT;
+		}
+		psinfo->write_buf(PSTORE_TYPE_PMSG, 0, &id, 0, buffer, 0, c,
+				  psinfo);
+
+		i += c;
+	}
+
+	mutex_unlock(&pmsg_lock);
+	vfree(buffer);
+	return count;
+}
+
+static const struct file_operations pmsg_fops = {
+	.owner		= THIS_MODULE,
+	.llseek		= noop_llseek,
+	.write		= write_pmsg,
+};
+
+static struct class *pmsg_class;
+static int pmsg_major;
+#define PMSG_NAME "pmsg"
+#undef pr_fmt
+#define pr_fmt(fmt) PMSG_NAME ": " fmt
+
+static char *pmsg_devnode(struct device *dev, umode_t *mode)
+{
+	if (mode)
+		*mode = 0220;
+	return NULL;
+}
+
+void pstore_register_pmsg(void)
+{
+	struct device *pmsg_device;
+
+	pmsg_major = register_chrdev(0, PMSG_NAME, &pmsg_fops);
+	if (pmsg_major < 0) {
+		pr_err("register_chrdev failed\n");
+		goto err;
+	}
+
+	pmsg_class = class_create(THIS_MODULE, PMSG_NAME);
+	if (IS_ERR(pmsg_class)) {
+		pr_err("device class file already in use\n");
+		goto err_class;
+	}
+	pmsg_class->devnode = pmsg_devnode;
+
+	pmsg_device = device_create(pmsg_class, NULL, MKDEV(pmsg_major, 0),
+					NULL, "%s%d", PMSG_NAME, 0);
+	if (IS_ERR(pmsg_device)) {
+		pr_err("failed to create device\n");
+		goto err_device;
+	}
+	return;
+
+err_device:
+	class_destroy(pmsg_class);
+err_class:
+	unregister_chrdev(pmsg_major, PMSG_NAME);
+err:
+	return;
+}
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 3b5744306ed..c28dc6802cf 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -51,6 +51,10 @@ static ulong ramoops_ftrace_size = MIN_MEM_SIZE;
 module_param_named(ftrace_size, ramoops_ftrace_size, ulong, 0400);
 MODULE_PARM_DESC(ftrace_size, "size of ftrace log");
 
+static ulong ramoops_pmsg_size = MIN_MEM_SIZE;
+module_param_named(pmsg_size, ramoops_pmsg_size, ulong, 0400);
+MODULE_PARM_DESC(pmsg_size, "size of user space message log");
+
 static ulong mem_address;
 module_param(mem_address, ulong, 0400);
 MODULE_PARM_DESC(mem_address,
@@ -61,6 +65,11 @@ module_param(mem_size, ulong, 0400);
 MODULE_PARM_DESC(mem_size,
 		"size of reserved RAM used to store oops/panic logs");
 
+static unsigned int mem_type;
+module_param(mem_type, uint, 0600);
+MODULE_PARM_DESC(mem_type,
+		"set to 1 to try to use unbuffered memory (default 0)");
+
 static int dump_oops = 1;
 module_param(dump_oops, int, 0600);
 MODULE_PARM_DESC(dump_oops,
@@ -77,11 +86,14 @@ struct ramoops_context {
 	struct persistent_ram_zone **przs;
 	struct persistent_ram_zone *cprz;
 	struct persistent_ram_zone *fprz;
+	struct persistent_ram_zone *mprz;
 	phys_addr_t phys_addr;
 	unsigned long size;
+	unsigned int memtype;
 	size_t record_size;
 	size_t console_size;
 	size_t ftrace_size;
+	size_t pmsg_size;
 	int dump_oops;
 	struct persistent_ram_ecc_info ecc_info;
 	unsigned int max_dump_cnt;
@@ -90,6 +102,7 @@ struct ramoops_context {
 	unsigned int dump_read_cnt;
 	unsigned int console_read_cnt;
 	unsigned int ftrace_read_cnt;
+	unsigned int pmsg_read_cnt;
 	struct pstore_info pstore;
 };
 
@@ -103,6 +116,7 @@ static int ramoops_pstore_open(struct pstore_info *psi)
 	cxt->dump_read_cnt = 0;
 	cxt->console_read_cnt = 0;
 	cxt->ftrace_read_cnt = 0;
+	cxt->pmsg_read_cnt = 0;
 	return 0;
 }
 
@@ -156,6 +170,12 @@ static void ramoops_read_kmsg_hdr(char *buffer, struct timespec *time,
 	}
 }
 
+static bool prz_ok(struct persistent_ram_zone *prz)
+{
+	return !!prz && !!(persistent_ram_old_size(prz) +
+			   persistent_ram_ecc_string(prz, NULL, 0));
+}
+
 static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
 				   int *count, struct timespec *time,
 				   char **buf, bool *compressed,
@@ -169,13 +189,16 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
 	prz = ramoops_get_next_prz(cxt->przs, &cxt->dump_read_cnt,
 				   cxt->max_dump_cnt, id, type,
 				   PSTORE_TYPE_DMESG, 1);
-	if (!prz)
+	if (!prz_ok(prz))
 		prz = ramoops_get_next_prz(&cxt->cprz, &cxt->console_read_cnt,
 					   1, id, type, PSTORE_TYPE_CONSOLE, 0);
-	if (!prz)
+	if (!prz_ok(prz))
 		prz = ramoops_get_next_prz(&cxt->fprz, &cxt->ftrace_read_cnt,
 					   1, id, type, PSTORE_TYPE_FTRACE, 0);
-	if (!prz)
+	if (!prz_ok(prz))
+		prz = ramoops_get_next_prz(&cxt->mprz, &cxt->pmsg_read_cnt,
+					   1, id, type, PSTORE_TYPE_PMSG, 0);
+	if (!prz_ok(prz))
 		return 0;
 
 	size = persistent_ram_old_size(prz);
@@ -238,6 +261,11 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type,
 			return -ENOMEM;
 		persistent_ram_write(cxt->fprz, buf, size);
 		return 0;
+	} else if (type == PSTORE_TYPE_PMSG) {
+		if (!cxt->mprz)
+			return -ENOMEM;
+		persistent_ram_write(cxt->mprz, buf, size);
+		return 0;
 	}
 
 	if (type != PSTORE_TYPE_DMESG)
@@ -295,6 +323,9 @@ static int ramoops_pstore_erase(enum pstore_type_id type, u64 id, int count,
 	case PSTORE_TYPE_FTRACE:
 		prz = cxt->fprz;
 		break;
+	case PSTORE_TYPE_PMSG:
+		prz = cxt->mprz;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -358,7 +389,8 @@ static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt,
 		size_t sz = cxt->record_size;
 
 		cxt->przs[i] = persistent_ram_new(*paddr, sz, 0,
-						  &cxt->ecc_info);
+						  &cxt->ecc_info,
+						  cxt->memtype);
 		if (IS_ERR(cxt->przs[i])) {
 			err = PTR_ERR(cxt->przs[i]);
 			dev_err(dev, "failed to request mem region (0x%zx@0x%llx): %d\n",
@@ -388,7 +420,7 @@ static int ramoops_init_prz(struct device *dev, struct ramoops_context *cxt,
 		return -ENOMEM;
 	}
 
-	*prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info);
+	*prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info, cxt->memtype);
 	if (IS_ERR(*prz)) {
 		int err = PTR_ERR(*prz);
 
@@ -404,6 +436,12 @@ static int ramoops_init_prz(struct device *dev, struct ramoops_context *cxt,
 	return 0;
 }
 
+void notrace ramoops_console_write_buf(const char *buf, size_t size)
+{
+	struct ramoops_context *cxt = &oops_cxt;
+	persistent_ram_write(cxt->cprz, buf, size);
+}
+
 static int ramoops_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -420,7 +458,7 @@ static int ramoops_probe(struct platform_device *pdev)
 		goto fail_out;
 
 	if (!pdata->mem_size || (!pdata->record_size && !pdata->console_size &&
-			!pdata->ftrace_size)) {
+			!pdata->ftrace_size && !pdata->pmsg_size)) {
 		pr_err("The memory size and the record/console size must be "
 			"non-zero\n");
 		goto fail_out;
@@ -432,18 +470,23 @@ static int ramoops_probe(struct platform_device *pdev)
 		pdata->console_size = rounddown_pow_of_two(pdata->console_size);
 	if (pdata->ftrace_size && !is_power_of_2(pdata->ftrace_size))
 		pdata->ftrace_size = rounddown_pow_of_two(pdata->ftrace_size);
+	if (pdata->pmsg_size && !is_power_of_2(pdata->pmsg_size))
+		pdata->pmsg_size = rounddown_pow_of_two(pdata->pmsg_size);
 
 	cxt->size = pdata->mem_size;
 	cxt->phys_addr = pdata->mem_address;
+	cxt->memtype = pdata->mem_type;
 	cxt->record_size = pdata->record_size;
 	cxt->console_size = pdata->console_size;
 	cxt->ftrace_size = pdata->ftrace_size;
+	cxt->pmsg_size = pdata->pmsg_size;
 	cxt->dump_oops = pdata->dump_oops;
 	cxt->ecc_info = pdata->ecc_info;
 
 	paddr = cxt->phys_addr;
 
-	dump_mem_sz = cxt->size - cxt->console_size - cxt->ftrace_size;
+	dump_mem_sz = cxt->size - cxt->console_size - cxt->ftrace_size
+			- cxt->pmsg_size;
 	err = ramoops_init_przs(dev, cxt, &paddr, dump_mem_sz);
 	if (err)
 		goto fail_out;
@@ -458,13 +501,9 @@ static int ramoops_probe(struct platform_device *pdev)
 	if (err)
 		goto fail_init_fprz;
 
-	if (!cxt->przs && !cxt->cprz && !cxt->fprz) {
-		pr_err("memory size too small, minimum is %zu\n",
-			cxt->console_size + cxt->record_size +
-			cxt->ftrace_size);
-		err = -EINVAL;
-		goto fail_cnt;
-	}
+	err = ramoops_init_prz(dev, cxt, &cxt->mprz, &paddr, cxt->pmsg_size, 0);
+	if (err)
+		goto fail_init_mprz;
 
 	cxt->pstore.data = cxt;
 	/*
@@ -509,7 +548,9 @@ fail_buf:
 	kfree(cxt->pstore.buf);
 fail_clear:
 	cxt->pstore.bufsize = 0;
-fail_cnt:
+	cxt->max_dump_cnt = 0;
+	kfree(cxt->mprz);
+fail_init_mprz:
 	kfree(cxt->fprz);
 fail_init_fprz:
 	kfree(cxt->cprz);
@@ -564,9 +605,11 @@ static void ramoops_register_dummy(void)
 
 	dummy_data->mem_size = mem_size;
 	dummy_data->mem_address = mem_address;
+	dummy_data->mem_type = 0;
 	dummy_data->record_size = record_size;
 	dummy_data->console_size = ramoops_console_size;
 	dummy_data->ftrace_size = ramoops_ftrace_size;
+	dummy_data->pmsg_size = ramoops_pmsg_size;
 	dummy_data->dump_oops = dump_oops;
 	/*
 	 * For backwards compatibility ramoops.ecc=1 means 16 bytes ECC
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index 9d7b9a83699..76c3f80efdf 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -380,7 +380,8 @@ void persistent_ram_zap(struct persistent_ram_zone *prz)
 	persistent_ram_update_header_ecc(prz);
 }
 
-static void *persistent_ram_vmap(phys_addr_t start, size_t size)
+static void *persistent_ram_vmap(phys_addr_t start, size_t size,
+		unsigned int memtype)
 {
 	struct page **pages;
 	phys_addr_t page_start;
@@ -392,7 +393,10 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size)
 	page_start = start - offset_in_page(start);
 	page_count = DIV_ROUND_UP(size + offset_in_page(start), PAGE_SIZE);
 
-	prot = pgprot_noncached(PAGE_KERNEL);
+	if (memtype)
+		prot = pgprot_noncached(PAGE_KERNEL);
+	else
+		prot = pgprot_writecombine(PAGE_KERNEL);
 
 	pages = kmalloc_array(page_count, sizeof(struct page *), GFP_KERNEL);
 	if (!pages) {
@@ -411,8 +415,11 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size)
 	return vaddr;
 }
 
-static void *persistent_ram_iomap(phys_addr_t start, size_t size)
+static void *persistent_ram_iomap(phys_addr_t start, size_t size,
+		unsigned int memtype)
 {
+	void *va;
+
 	if (!request_mem_region(start, size, "persistent_ram")) {
 		pr_err("request mem region (0x%llx@0x%llx) failed\n",
 			(unsigned long long)size, (unsigned long long)start);
@@ -422,19 +429,24 @@ static void *persistent_ram_iomap(phys_addr_t start, size_t size)
 	buffer_start_add = buffer_start_add_locked;
 	buffer_size_add = buffer_size_add_locked;
 
-	return ioremap(start, size);
+	if (memtype)
+		va = ioremap(start, size);
+	else
+		va = ioremap_wc(start, size);
+
+	return va;
 }
 
 static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size,
-		struct persistent_ram_zone *prz)
+		struct persistent_ram_zone *prz, int memtype)
 {
 	prz->paddr = start;
 	prz->size = size;
 
 	if (pfn_valid(start >> PAGE_SHIFT))
-		prz->vaddr = persistent_ram_vmap(start, size);
+		prz->vaddr = persistent_ram_vmap(start, size, memtype);
 	else
-		prz->vaddr = persistent_ram_iomap(start, size);
+		prz->vaddr = persistent_ram_iomap(start, size, memtype);
 
 	if (!prz->vaddr) {
 		pr_err("%s: Failed to map 0x%llx pages at 0x%llx\n", __func__,
@@ -500,7 +512,8 @@ void persistent_ram_free(struct persistent_ram_zone *prz)
 }
 
 struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
-			u32 sig, struct persistent_ram_ecc_info *ecc_info)
+			u32 sig, struct persistent_ram_ecc_info *ecc_info,
+			unsigned int memtype)
 {
 	struct persistent_ram_zone *prz;
 	int ret = -ENOMEM;
@@ -511,7 +524,7 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
 		goto err;
 	}
 
-	ret = persistent_ram_buffer_map(start, size, prz);
+	ret = persistent_ram_buffer_map(start, size, prz, memtype);
 	if (ret)
 		goto err;
 
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 6b4527216a7..05fea2ac116 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2380,41 +2380,26 @@ out:
 }
 EXPORT_SYMBOL(dquot_quota_on_mount);
 
-static inline qsize_t qbtos(qsize_t blocks)
-{
-	return blocks << QIF_DQBLKSIZE_BITS;
-}
-
-static inline qsize_t stoqb(qsize_t space)
-{
-	return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS;
-}
-
 /* Generic routine for getting common part of quota structure */
-static void do_get_dqblk(struct dquot *dquot, struct fs_disk_quota *di)
+static void do_get_dqblk(struct dquot *dquot, struct qc_dqblk *di)
 {
 	struct mem_dqblk *dm = &dquot->dq_dqb;
 
 	memset(di, 0, sizeof(*di));
-	di->d_version = FS_DQUOT_VERSION;
-	di->d_flags = dquot->dq_id.type == USRQUOTA ?
-			FS_USER_QUOTA : FS_GROUP_QUOTA;
-	di->d_id = from_kqid_munged(current_user_ns(), dquot->dq_id);
-
 	spin_lock(&dq_data_lock);
-	di->d_blk_hardlimit = stoqb(dm->dqb_bhardlimit);
-	di->d_blk_softlimit = stoqb(dm->dqb_bsoftlimit);
+	di->d_spc_hardlimit = dm->dqb_bhardlimit;
+	di->d_spc_softlimit = dm->dqb_bsoftlimit;
 	di->d_ino_hardlimit = dm->dqb_ihardlimit;
 	di->d_ino_softlimit = dm->dqb_isoftlimit;
-	di->d_bcount = dm->dqb_curspace + dm->dqb_rsvspace;
-	di->d_icount = dm->dqb_curinodes;
-	di->d_btimer = dm->dqb_btime;
-	di->d_itimer = dm->dqb_itime;
+	di->d_space = dm->dqb_curspace + dm->dqb_rsvspace;
+	di->d_ino_count = dm->dqb_curinodes;
+	di->d_spc_timer = dm->dqb_btime;
+	di->d_ino_timer = dm->dqb_itime;
 	spin_unlock(&dq_data_lock);
 }
 
 int dquot_get_dqblk(struct super_block *sb, struct kqid qid,
-		    struct fs_disk_quota *di)
+		    struct qc_dqblk *di)
 {
 	struct dquot *dquot;
 
@@ -2428,70 +2413,70 @@ int dquot_get_dqblk(struct super_block *sb, struct kqid qid,
 }
 EXPORT_SYMBOL(dquot_get_dqblk);
 
-#define VFS_FS_DQ_MASK \
-	(FS_DQ_BCOUNT | FS_DQ_BSOFT | FS_DQ_BHARD | \
-	 FS_DQ_ICOUNT | FS_DQ_ISOFT | FS_DQ_IHARD | \
-	 FS_DQ_BTIMER | FS_DQ_ITIMER)
+#define VFS_QC_MASK \
+	(QC_SPACE | QC_SPC_SOFT | QC_SPC_HARD | \
+	 QC_INO_COUNT | QC_INO_SOFT | QC_INO_HARD | \
+	 QC_SPC_TIMER | QC_INO_TIMER)
 
 /* Generic routine for setting common part of quota structure */
-static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di)
+static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di)
 {
 	struct mem_dqblk *dm = &dquot->dq_dqb;
 	int check_blim = 0, check_ilim = 0;
 	struct mem_dqinfo *dqi = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type];
 
-	if (di->d_fieldmask & ~VFS_FS_DQ_MASK)
+	if (di->d_fieldmask & ~VFS_QC_MASK)
 		return -EINVAL;
 
-	if (((di->d_fieldmask & FS_DQ_BSOFT) &&
-	     (di->d_blk_softlimit > dqi->dqi_maxblimit)) ||
-	    ((di->d_fieldmask & FS_DQ_BHARD) &&
-	     (di->d_blk_hardlimit > dqi->dqi_maxblimit)) ||
-	    ((di->d_fieldmask & FS_DQ_ISOFT) &&
-	     (di->d_ino_softlimit > dqi->dqi_maxilimit)) ||
-	    ((di->d_fieldmask & FS_DQ_IHARD) &&
-	     (di->d_ino_hardlimit > dqi->dqi_maxilimit)))
+	if (((di->d_fieldmask & QC_SPC_SOFT) &&
+	     di->d_spc_softlimit > dqi->dqi_max_spc_limit) ||
+	    ((di->d_fieldmask & QC_SPC_HARD) &&
+	     di->d_spc_hardlimit > dqi->dqi_max_spc_limit) ||
+	    ((di->d_fieldmask & QC_INO_SOFT) &&
+	     (di->d_ino_softlimit > dqi->dqi_max_ino_limit)) ||
+	    ((di->d_fieldmask & QC_INO_HARD) &&
+	     (di->d_ino_hardlimit > dqi->dqi_max_ino_limit)))
 		return -ERANGE;
 
 	spin_lock(&dq_data_lock);
-	if (di->d_fieldmask & FS_DQ_BCOUNT) {
-		dm->dqb_curspace = di->d_bcount - dm->dqb_rsvspace;
+	if (di->d_fieldmask & QC_SPACE) {
+		dm->dqb_curspace = di->d_space - dm->dqb_rsvspace;
 		check_blim = 1;
 		set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags);
 	}
 
-	if (di->d_fieldmask & FS_DQ_BSOFT)
-		dm->dqb_bsoftlimit = qbtos(di->d_blk_softlimit);
-	if (di->d_fieldmask & FS_DQ_BHARD)
-		dm->dqb_bhardlimit = qbtos(di->d_blk_hardlimit);
-	if (di->d_fieldmask & (FS_DQ_BSOFT | FS_DQ_BHARD)) {
+	if (di->d_fieldmask & QC_SPC_SOFT)
+		dm->dqb_bsoftlimit = di->d_spc_softlimit;
+	if (di->d_fieldmask & QC_SPC_HARD)
+		dm->dqb_bhardlimit = di->d_spc_hardlimit;
+	if (di->d_fieldmask & (QC_SPC_SOFT | QC_SPC_HARD)) {
 		check_blim = 1;
 		set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags);
 	}
 
-	if (di->d_fieldmask & FS_DQ_ICOUNT) {
-		dm->dqb_curinodes = di->d_icount;
+	if (di->d_fieldmask & QC_INO_COUNT) {
+		dm->dqb_curinodes = di->d_ino_count;
 		check_ilim = 1;
 		set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags);
 	}
 
-	if (di->d_fieldmask & FS_DQ_ISOFT)
+	if (di->d_fieldmask & QC_INO_SOFT)
 		dm->dqb_isoftlimit = di->d_ino_softlimit;
-	if (di->d_fieldmask & FS_DQ_IHARD)
+	if (di->d_fieldmask & QC_INO_HARD)
 		dm->dqb_ihardlimit = di->d_ino_hardlimit;
-	if (di->d_fieldmask & (FS_DQ_ISOFT | FS_DQ_IHARD)) {
+	if (di->d_fieldmask & (QC_INO_SOFT | QC_INO_HARD)) {
 		check_ilim = 1;
 		set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags);
 	}
 
-	if (di->d_fieldmask & FS_DQ_BTIMER) {
-		dm->dqb_btime = di->d_btimer;
+	if (di->d_fieldmask & QC_SPC_TIMER) {
+		dm->dqb_btime = di->d_spc_timer;
 		check_blim = 1;
 		set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags);
 	}
 
-	if (di->d_fieldmask & FS_DQ_ITIMER) {
-		dm->dqb_itime = di->d_itimer;
+	if (di->d_fieldmask & QC_INO_TIMER) {
+		dm->dqb_itime = di->d_ino_timer;
 		check_ilim = 1;
 		set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags);
 	}
@@ -2501,7 +2486,7 @@ static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di)
 		    dm->dqb_curspace < dm->dqb_bsoftlimit) {
 			dm->dqb_btime = 0;
 			clear_bit(DQ_BLKS_B, &dquot->dq_flags);
-		} else if (!(di->d_fieldmask & FS_DQ_BTIMER))
+		} else if (!(di->d_fieldmask & QC_SPC_TIMER))
 			/* Set grace only if user hasn't provided his own... */
 			dm->dqb_btime = get_seconds() + dqi->dqi_bgrace;
 	}
@@ -2510,7 +2495,7 @@ static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di)
 		    dm->dqb_curinodes < dm->dqb_isoftlimit) {
 			dm->dqb_itime = 0;
 			clear_bit(DQ_INODES_B, &dquot->dq_flags);
-		} else if (!(di->d_fieldmask & FS_DQ_ITIMER))
+		} else if (!(di->d_fieldmask & QC_INO_TIMER))
 			/* Set grace only if user hasn't provided his own... */
 			dm->dqb_itime = get_seconds() + dqi->dqi_igrace;
 	}
@@ -2526,7 +2511,7 @@ static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di)
 }
 
 int dquot_set_dqblk(struct super_block *sb, struct kqid qid,
-		  struct fs_disk_quota *di)
+		  struct qc_dqblk *di)
 {
 	struct dquot *dquot;
 	int rc;
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 75621649dbd..2ce66201c36 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -115,17 +115,27 @@ static int quota_setinfo(struct super_block *sb, int type, void __user *addr)
 	return sb->s_qcop->set_info(sb, type, &info);
 }
 
-static void copy_to_if_dqblk(struct if_dqblk *dst, struct fs_disk_quota *src)
+static inline qsize_t qbtos(qsize_t blocks)
+{
+	return blocks << QIF_DQBLKSIZE_BITS;
+}
+
+static inline qsize_t stoqb(qsize_t space)
+{
+	return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS;
+}
+
+static void copy_to_if_dqblk(struct if_dqblk *dst, struct qc_dqblk *src)
 {
 	memset(dst, 0, sizeof(*dst));
-	dst->dqb_bhardlimit = src->d_blk_hardlimit;
-	dst->dqb_bsoftlimit = src->d_blk_softlimit;
-	dst->dqb_curspace = src->d_bcount;
+	dst->dqb_bhardlimit = stoqb(src->d_spc_hardlimit);
+	dst->dqb_bsoftlimit = stoqb(src->d_spc_softlimit);
+	dst->dqb_curspace = src->d_space;
 	dst->dqb_ihardlimit = src->d_ino_hardlimit;
 	dst->dqb_isoftlimit = src->d_ino_softlimit;
-	dst->dqb_curinodes = src->d_icount;
-	dst->dqb_btime = src->d_btimer;
-	dst->dqb_itime = src->d_itimer;
+	dst->dqb_curinodes = src->d_ino_count;
+	dst->dqb_btime = src->d_spc_timer;
+	dst->dqb_itime = src->d_ino_timer;
 	dst->dqb_valid = QIF_ALL;
 }
 
@@ -133,7 +143,7 @@ static int quota_getquota(struct super_block *sb, int type, qid_t id,
 			  void __user *addr)
 {
 	struct kqid qid;
-	struct fs_disk_quota fdq;
+	struct qc_dqblk fdq;
 	struct if_dqblk idq;
 	int ret;
 
@@ -151,36 +161,36 @@ static int quota_getquota(struct super_block *sb, int type, qid_t id,
 	return 0;
 }
 
-static void copy_from_if_dqblk(struct fs_disk_quota *dst, struct if_dqblk *src)
+static void copy_from_if_dqblk(struct qc_dqblk *dst, struct if_dqblk *src)
 {
-	dst->d_blk_hardlimit = src->dqb_bhardlimit;
-	dst->d_blk_softlimit  = src->dqb_bsoftlimit;
-	dst->d_bcount = src->dqb_curspace;
+	dst->d_spc_hardlimit = qbtos(src->dqb_bhardlimit);
+	dst->d_spc_softlimit = qbtos(src->dqb_bsoftlimit);
+	dst->d_space = src->dqb_curspace;
 	dst->d_ino_hardlimit = src->dqb_ihardlimit;
 	dst->d_ino_softlimit = src->dqb_isoftlimit;
-	dst->d_icount = src->dqb_curinodes;
-	dst->d_btimer = src->dqb_btime;
-	dst->d_itimer = src->dqb_itime;
+	dst->d_ino_count = src->dqb_curinodes;
+	dst->d_spc_timer = src->dqb_btime;
+	dst->d_ino_timer = src->dqb_itime;
 
 	dst->d_fieldmask = 0;
 	if (src->dqb_valid & QIF_BLIMITS)
-		dst->d_fieldmask |= FS_DQ_BSOFT | FS_DQ_BHARD;
+		dst->d_fieldmask |= QC_SPC_SOFT | QC_SPC_HARD;
 	if (src->dqb_valid & QIF_SPACE)
-		dst->d_fieldmask |= FS_DQ_BCOUNT;
+		dst->d_fieldmask |= QC_SPACE;
 	if (src->dqb_valid & QIF_ILIMITS)
-		dst->d_fieldmask |= FS_DQ_ISOFT | FS_DQ_IHARD;
+		dst->d_fieldmask |= QC_INO_SOFT | QC_INO_HARD;
 	if (src->dqb_valid & QIF_INODES)
-		dst->d_fieldmask |= FS_DQ_ICOUNT;
+		dst->d_fieldmask |= QC_INO_COUNT;
 	if (src->dqb_valid & QIF_BTIME)
-		dst->d_fieldmask |= FS_DQ_BTIMER;
+		dst->d_fieldmask |= QC_SPC_TIMER;
 	if (src->dqb_valid & QIF_ITIME)
-		dst->d_fieldmask |= FS_DQ_ITIMER;
+		dst->d_fieldmask |= QC_INO_TIMER;
 }
 
 static int quota_setquota(struct super_block *sb, int type, qid_t id,
 			  void __user *addr)
 {
-	struct fs_disk_quota fdq;
+	struct qc_dqblk fdq;
 	struct if_dqblk idq;
 	struct kqid qid;
 
@@ -244,10 +254,78 @@ static int quota_getxstatev(struct super_block *sb, void __user *addr)
 	return ret;
 }
 
+/*
+ * XFS defines BBTOB and BTOBB macros inside fs/xfs/ and we cannot move them
+ * out of there as xfsprogs rely on definitions being in that header file. So
+ * just define same functions here for quota purposes.
+ */
+#define XFS_BB_SHIFT 9
+
+static inline u64 quota_bbtob(u64 blocks)
+{
+	return blocks << XFS_BB_SHIFT;
+}
+
+static inline u64 quota_btobb(u64 bytes)
+{
+	return (bytes + (1 << XFS_BB_SHIFT) - 1) >> XFS_BB_SHIFT;
+}
+
+static void copy_from_xfs_dqblk(struct qc_dqblk *dst, struct fs_disk_quota *src)
+{
+	dst->d_spc_hardlimit = quota_bbtob(src->d_blk_hardlimit);
+	dst->d_spc_softlimit = quota_bbtob(src->d_blk_softlimit);
+	dst->d_ino_hardlimit = src->d_ino_hardlimit;
+	dst->d_ino_softlimit = src->d_ino_softlimit;
+	dst->d_space = quota_bbtob(src->d_bcount);
+	dst->d_ino_count = src->d_icount;
+	dst->d_ino_timer = src->d_itimer;
+	dst->d_spc_timer = src->d_btimer;
+	dst->d_ino_warns = src->d_iwarns;
+	dst->d_spc_warns = src->d_bwarns;
+	dst->d_rt_spc_hardlimit = quota_bbtob(src->d_rtb_hardlimit);
+	dst->d_rt_spc_softlimit = quota_bbtob(src->d_rtb_softlimit);
+	dst->d_rt_space = quota_bbtob(src->d_rtbcount);
+	dst->d_rt_spc_timer = src->d_rtbtimer;
+	dst->d_rt_spc_warns = src->d_rtbwarns;
+	dst->d_fieldmask = 0;
+	if (src->d_fieldmask & FS_DQ_ISOFT)
+		dst->d_fieldmask |= QC_INO_SOFT;
+	if (src->d_fieldmask & FS_DQ_IHARD)
+		dst->d_fieldmask |= QC_INO_HARD;
+	if (src->d_fieldmask & FS_DQ_BSOFT)
+		dst->d_fieldmask |= QC_SPC_SOFT;
+	if (src->d_fieldmask & FS_DQ_BHARD)
+		dst->d_fieldmask |= QC_SPC_HARD;
+	if (src->d_fieldmask & FS_DQ_RTBSOFT)
+		dst->d_fieldmask |= QC_RT_SPC_SOFT;
+	if (src->d_fieldmask & FS_DQ_RTBHARD)
+		dst->d_fieldmask |= QC_RT_SPC_HARD;
+	if (src->d_fieldmask & FS_DQ_BTIMER)
+		dst->d_fieldmask |= QC_SPC_TIMER;
+	if (src->d_fieldmask & FS_DQ_ITIMER)
+		dst->d_fieldmask |= QC_INO_TIMER;
+	if (src->d_fieldmask & FS_DQ_RTBTIMER)
+		dst->d_fieldmask |= QC_RT_SPC_TIMER;
+	if (src->d_fieldmask & FS_DQ_BWARNS)
+		dst->d_fieldmask |= QC_SPC_WARNS;
+	if (src->d_fieldmask & FS_DQ_IWARNS)
+		dst->d_fieldmask |= QC_INO_WARNS;
+	if (src->d_fieldmask & FS_DQ_RTBWARNS)
+		dst->d_fieldmask |= QC_RT_SPC_WARNS;
+	if (src->d_fieldmask & FS_DQ_BCOUNT)
+		dst->d_fieldmask |= QC_SPACE;
+	if (src->d_fieldmask & FS_DQ_ICOUNT)
+		dst->d_fieldmask |= QC_INO_COUNT;
+	if (src->d_fieldmask & FS_DQ_RTBCOUNT)
+		dst->d_fieldmask |= QC_RT_SPACE;
+}
+
 static int quota_setxquota(struct super_block *sb, int type, qid_t id,
 			   void __user *addr)
 {
 	struct fs_disk_quota fdq;
+	struct qc_dqblk qdq;
 	struct kqid qid;
 
 	if (copy_from_user(&fdq, addr, sizeof(fdq)))
@@ -257,13 +335,44 @@ static int quota_setxquota(struct super_block *sb, int type, qid_t id,
 	qid = make_kqid(current_user_ns(), type, id);
 	if (!qid_valid(qid))
 		return -EINVAL;
-	return sb->s_qcop->set_dqblk(sb, qid, &fdq);
+	copy_from_xfs_dqblk(&qdq, &fdq);
+	return sb->s_qcop->set_dqblk(sb, qid, &qdq);
+}
+
+static void copy_to_xfs_dqblk(struct fs_disk_quota *dst, struct qc_dqblk *src,
+			      int type, qid_t id)
+{
+	memset(dst, 0, sizeof(*dst));
+	dst->d_version = FS_DQUOT_VERSION;
+	dst->d_id = id;
+	if (type == USRQUOTA)
+		dst->d_flags = FS_USER_QUOTA;
+	else if (type == PRJQUOTA)
+		dst->d_flags = FS_PROJ_QUOTA;
+	else
+		dst->d_flags = FS_GROUP_QUOTA;
+	dst->d_blk_hardlimit = quota_btobb(src->d_spc_hardlimit);
+	dst->d_blk_softlimit = quota_btobb(src->d_spc_softlimit);
+	dst->d_ino_hardlimit = src->d_ino_hardlimit;
+	dst->d_ino_softlimit = src->d_ino_softlimit;
+	dst->d_bcount = quota_btobb(src->d_space);
+	dst->d_icount = src->d_ino_count;
+	dst->d_itimer = src->d_ino_timer;
+	dst->d_btimer = src->d_spc_timer;
+	dst->d_iwarns = src->d_ino_warns;
+	dst->d_bwarns = src->d_spc_warns;
+	dst->d_rtb_hardlimit = quota_btobb(src->d_rt_spc_hardlimit);
+	dst->d_rtb_softlimit = quota_btobb(src->d_rt_spc_softlimit);
+	dst->d_rtbcount = quota_btobb(src->d_rt_space);
+	dst->d_rtbtimer = src->d_rt_spc_timer;
+	dst->d_rtbwarns = src->d_rt_spc_warns;
 }
 
 static int quota_getxquota(struct super_block *sb, int type, qid_t id,
 			   void __user *addr)
 {
 	struct fs_disk_quota fdq;
+	struct qc_dqblk qdq;
 	struct kqid qid;
 	int ret;
 
@@ -272,8 +381,11 @@ static int quota_getxquota(struct super_block *sb, int type, qid_t id,
 	qid = make_kqid(current_user_ns(), type, id);
 	if (!qid_valid(qid))
 		return -EINVAL;
-	ret = sb->s_qcop->get_dqblk(sb, qid, &fdq);
-	if (!ret && copy_to_user(addr, &fdq, sizeof(fdq)))
+	ret = sb->s_qcop->get_dqblk(sb, qid, &qdq);
+	if (ret)
+		return ret;
+	copy_to_xfs_dqblk(&fdq, &qdq, type, id);
+	if (copy_to_user(addr, &fdq, sizeof(fdq)))
 		return -EFAULT;
 	return ret;
 }
diff --git a/fs/quota/quota_v1.c b/fs/quota/quota_v1.c
index 469c6848b32..8fe79beced5 100644
--- a/fs/quota/quota_v1.c
+++ b/fs/quota/quota_v1.c
@@ -169,8 +169,8 @@ static int v1_read_file_info(struct super_block *sb, int type)
 	}
 	ret = 0;
 	/* limits are stored as unsigned 32-bit data */
-	dqopt->info[type].dqi_maxblimit = 0xffffffff;
-	dqopt->info[type].dqi_maxilimit = 0xffffffff;
+	dqopt->info[type].dqi_max_spc_limit = 0xffffffffULL << QUOTABLOCK_BITS;
+	dqopt->info[type].dqi_max_ino_limit = 0xffffffff;
 	dqopt->info[type].dqi_igrace =
 			dqblk.dqb_itime ? dqblk.dqb_itime : MAX_IQ_TIME;
 	dqopt->info[type].dqi_bgrace =
diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c
index 02751ec695c..d1a8054bba9 100644
--- a/fs/quota/quota_v2.c
+++ b/fs/quota/quota_v2.c
@@ -117,12 +117,12 @@ static int v2_read_file_info(struct super_block *sb, int type)
 	qinfo = info->dqi_priv;
 	if (version == 0) {
 		/* limits are stored as unsigned 32-bit data */
-		info->dqi_maxblimit = 0xffffffff;
-		info->dqi_maxilimit = 0xffffffff;
+		info->dqi_max_spc_limit = 0xffffffffULL << QUOTABLOCK_BITS;
+		info->dqi_max_ino_limit = 0xffffffff;
 	} else {
-		/* used space is stored as unsigned 64-bit value */
-		info->dqi_maxblimit = 0xffffffffffffffffULL;	/* 2^64-1 */
-		info->dqi_maxilimit = 0xffffffffffffffffULL;
+		/* used space is stored as unsigned 64-bit value in bytes */
+		info->dqi_max_spc_limit = 0xffffffffffffffffULL; /* 2^64-1 */
+		info->dqi_max_ino_limit = 0xffffffffffffffffULL;
 	}
 	info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace);
 	info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace);
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index f1376c92cf7..b27ef354149 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -2161,6 +2161,9 @@ error_unlocked:
 		reiserfs_write_unlock(s);
 	}
 
+	if (sbi->commit_wq)
+		destroy_workqueue(sbi->commit_wq);
+
 	cancel_delayed_work_sync(&REISERFS_SB(s)->old_work);
 
 	reiserfs_free_bitmap_cache(s);
diff --git a/fs/super.c b/fs/super.c
index eae088f6aaa..cdf6dec2654 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -769,7 +769,7 @@ static void do_emergency_remount(struct work_struct *work)
 	struct super_block *sb, *p = NULL;
 
 	spin_lock(&sb_lock);
-	list_for_each_entry(sb, &super_blocks, s_list) {
+	list_for_each_entry_reverse(sb, &super_blocks, s_list) {
 		if (hlist_unhashed(&sb->s_instances))
 			continue;
 		sb->s_count++;
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 8a49486bf30..1c6ac6fcee9 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -31,9 +31,6 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
 	bool new_sb;
 
 	if (!(flags & MS_KERNMOUNT)) {
-		if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
-			return ERR_PTR(-EPERM);
-
 		if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET))
 			return ERR_PTR(-EPERM);
 	}
@@ -58,7 +55,7 @@ static struct file_system_type sysfs_fs_type = {
 	.name		= "sysfs",
 	.mount		= sysfs_mount,
 	.kill_sb	= sysfs_kill_sb,
-	.fs_flags	= FS_USERNS_MOUNT,
+	.fs_flags	= FS_USERNS_VISIBLE | FS_USERNS_MOUNT,
 };
 
 int __init sysfs_init(void)
diff --git a/fs/udf/dir.c b/fs/udf/dir.c
index a012c51caff..a7690b46ce0 100644
--- a/fs/udf/dir.c
+++ b/fs/udf/dir.c
@@ -167,7 +167,8 @@ static int udf_readdir(struct file *file, struct dir_context *ctx)
 			continue;
 		}
 
-		flen = udf_get_filename(dir->i_sb, nameptr, fname, lfi);
+		flen = udf_get_filename(dir->i_sb, nameptr, lfi, fname,
+					UDF_NAME_LEN);
 		if (!flen)
 			continue;
 
diff --git a/fs/udf/file.c b/fs/udf/file.c
index bb15771b92a..08f3555fbea 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -224,7 +224,7 @@ out:
 static int udf_release_file(struct inode *inode, struct file *filp)
 {
 	if (filp->f_mode & FMODE_WRITE &&
-	    atomic_read(&inode->i_writecount) > 1) {
+	    atomic_read(&inode->i_writecount) == 1) {
 		/*
 		 * Grab i_mutex to avoid races with writes changing i_size
 		 * while we are running.
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index c9b4df5810d..7b72b7dd890 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1288,6 +1288,7 @@ static int udf_read_inode(struct inode *inode, bool hidden_inode)
 	struct kernel_lb_addr *iloc = &iinfo->i_location;
 	unsigned int link_count;
 	unsigned int indirections = 0;
+	int bs = inode->i_sb->s_blocksize;
 	int ret = -EIO;
 
 reread:
@@ -1374,38 +1375,35 @@ reread:
 	if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_EFE)) {
 		iinfo->i_efe = 1;
 		iinfo->i_use = 0;
-		ret = udf_alloc_i_data(inode, inode->i_sb->s_blocksize -
+		ret = udf_alloc_i_data(inode, bs -
 					sizeof(struct extendedFileEntry));
 		if (ret)
 			goto out;
 		memcpy(iinfo->i_ext.i_data,
 		       bh->b_data + sizeof(struct extendedFileEntry),
-		       inode->i_sb->s_blocksize -
-					sizeof(struct extendedFileEntry));
+		       bs - sizeof(struct extendedFileEntry));
 	} else if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_FE)) {
 		iinfo->i_efe = 0;
 		iinfo->i_use = 0;
-		ret = udf_alloc_i_data(inode, inode->i_sb->s_blocksize -
-						sizeof(struct fileEntry));
+		ret = udf_alloc_i_data(inode, bs - sizeof(struct fileEntry));
 		if (ret)
 			goto out;
 		memcpy(iinfo->i_ext.i_data,
 		       bh->b_data + sizeof(struct fileEntry),
-		       inode->i_sb->s_blocksize - sizeof(struct fileEntry));
+		       bs - sizeof(struct fileEntry));
 	} else if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_USE)) {
 		iinfo->i_efe = 0;
 		iinfo->i_use = 1;
 		iinfo->i_lenAlloc = le32_to_cpu(
 				((struct unallocSpaceEntry *)bh->b_data)->
 				 lengthAllocDescs);
-		ret = udf_alloc_i_data(inode, inode->i_sb->s_blocksize -
+		ret = udf_alloc_i_data(inode, bs -
 					sizeof(struct unallocSpaceEntry));
 		if (ret)
 			goto out;
 		memcpy(iinfo->i_ext.i_data,
 		       bh->b_data + sizeof(struct unallocSpaceEntry),
-		       inode->i_sb->s_blocksize -
-					sizeof(struct unallocSpaceEntry));
+		       bs - sizeof(struct unallocSpaceEntry));
 		return 0;
 	}
 
@@ -1489,6 +1487,28 @@ reread:
 	}
 	inode->i_generation = iinfo->i_unique;
 
+	/*
+	 * Sanity check length of allocation descriptors and extended attrs to
+	 * avoid integer overflows
+	 */
+	if (iinfo->i_lenEAttr > bs || iinfo->i_lenAlloc > bs)
+		goto out;
+	/* Now do exact checks */
+	if (udf_file_entry_alloc_offset(inode) + iinfo->i_lenAlloc > bs)
+		goto out;
+	/* Sanity checks for files in ICB so that we don't get confused later */
+	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) {
+		/*
+		 * For file in ICB data is stored in allocation descriptor
+		 * so sizes should match
+		 */
+		if (iinfo->i_lenAlloc != inode->i_size)
+			goto out;
+		/* File in ICB has to fit in there... */
+		if (inode->i_size > bs - udf_file_entry_alloc_offset(inode))
+			goto out;
+	}
+
 	switch (fe->icbTag.fileType) {
 	case ICBTAG_FILE_TYPE_DIRECTORY:
 		inode->i_op = &udf_dir_inode_operations;
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index c12e260fd6c..6ff19b54b51 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -233,7 +233,8 @@ static struct fileIdentDesc *udf_find_entry(struct inode *dir,
 		if (!lfi)
 			continue;
 
-		flen = udf_get_filename(dir->i_sb, nameptr, fname, lfi);
+		flen = udf_get_filename(dir->i_sb, nameptr, lfi, fname,
+					UDF_NAME_LEN);
 		if (flen && udf_match(flen, fname, child->len, child->name))
 			goto out_ok;
 	}
diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c
index 6fb7945c1e6..ac10ca939f2 100644
--- a/fs/udf/symlink.c
+++ b/fs/udf/symlink.c
@@ -30,49 +30,73 @@
 #include <linux/buffer_head.h>
 #include "udf_i.h"
 
-static void udf_pc_to_char(struct super_block *sb, unsigned char *from,
-			   int fromlen, unsigned char *to)
+static int udf_pc_to_char(struct super_block *sb, unsigned char *from,
+			  int fromlen, unsigned char *to, int tolen)
 {
 	struct pathComponent *pc;
 	int elen = 0;
+	int comp_len;
 	unsigned char *p = to;
 
+	/* Reserve one byte for terminating \0 */
+	tolen--;
 	while (elen < fromlen) {
 		pc = (struct pathComponent *)(from + elen);
+		elen += sizeof(struct pathComponent);
 		switch (pc->componentType) {
 		case 1:
 			/*
 			 * Symlink points to some place which should be agreed
  			 * upon between originator and receiver of the media. Ignore.
 			 */
-			if (pc->lengthComponentIdent > 0)
+			if (pc->lengthComponentIdent > 0) {
+				elen += pc->lengthComponentIdent;
 				break;
+			}
 			/* Fall through */
 		case 2:
+			if (tolen == 0)
+				return -ENAMETOOLONG;
 			p = to;
 			*p++ = '/';
+			tolen--;
 			break;
 		case 3:
+			if (tolen < 3)
+				return -ENAMETOOLONG;
 			memcpy(p, "../", 3);
 			p += 3;
+			tolen -= 3;
 			break;
 		case 4:
+			if (tolen < 2)
+				return -ENAMETOOLONG;
 			memcpy(p, "./", 2);
 			p += 2;
+			tolen -= 2;
 			/* that would be . - just ignore */
 			break;
 		case 5:
-			p += udf_get_filename(sb, pc->componentIdent, p,
-					      pc->lengthComponentIdent);
+			elen += pc->lengthComponentIdent;
+			if (elen > fromlen)
+				return -EIO;
+			comp_len = udf_get_filename(sb, pc->componentIdent,
+						    pc->lengthComponentIdent,
+						    p, tolen);
+			p += comp_len;
+			tolen -= comp_len;
+			if (tolen == 0)
+				return -ENAMETOOLONG;
 			*p++ = '/';
+			tolen--;
 			break;
 		}
-		elen += sizeof(struct pathComponent) + pc->lengthComponentIdent;
 	}
 	if (p > to + 1)
 		p[-1] = '\0';
 	else
 		p[0] = '\0';
+	return 0;
 }
 
 static int udf_symlink_filler(struct file *file, struct page *page)
@@ -80,11 +104,17 @@ static int udf_symlink_filler(struct file *file, struct page *page)
 	struct inode *inode = page->mapping->host;
 	struct buffer_head *bh = NULL;
 	unsigned char *symlink;
-	int err = -EIO;
+	int err;
 	unsigned char *p = kmap(page);
 	struct udf_inode_info *iinfo;
 	uint32_t pos;
 
+	/* We don't support symlinks longer than one block */
+	if (inode->i_size > inode->i_sb->s_blocksize) {
+		err = -ENAMETOOLONG;
+		goto out_unmap;
+	}
+
 	iinfo = UDF_I(inode);
 	pos = udf_block_map(inode, 0);
 
@@ -94,14 +124,18 @@ static int udf_symlink_filler(struct file *file, struct page *page)
 	} else {
 		bh = sb_bread(inode->i_sb, pos);
 
-		if (!bh)
-			goto out;
+		if (!bh) {
+			err = -EIO;
+			goto out_unlock_inode;
+		}
 
 		symlink = bh->b_data;
 	}
 
-	udf_pc_to_char(inode->i_sb, symlink, inode->i_size, p);
+	err = udf_pc_to_char(inode->i_sb, symlink, inode->i_size, p, PAGE_SIZE);
 	brelse(bh);
+	if (err)
+		goto out_unlock_inode;
 
 	up_read(&iinfo->i_data_sem);
 	SetPageUptodate(page);
@@ -109,9 +143,10 @@ static int udf_symlink_filler(struct file *file, struct page *page)
 	unlock_page(page);
 	return 0;
 
-out:
+out_unlock_inode:
 	up_read(&iinfo->i_data_sem);
 	SetPageError(page);
+out_unmap:
 	kunmap(page);
 	unlock_page(page);
 	return err;
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index 1cc3c993ebd..47bb3f5ca36 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -211,7 +211,8 @@ udf_get_lb_pblock(struct super_block *sb, struct kernel_lb_addr *loc,
 }
 
 /* unicode.c */
-extern int udf_get_filename(struct super_block *, uint8_t *, uint8_t *, int);
+extern int udf_get_filename(struct super_block *, uint8_t *, int, uint8_t *,
+			    int);
 extern int udf_put_filename(struct super_block *, const uint8_t *, uint8_t *,
 			    int);
 extern int udf_build_ustr(struct ustr *, dstring *, int);
diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c
index afd470e588f..b84fee37273 100644
--- a/fs/udf/unicode.c
+++ b/fs/udf/unicode.c
@@ -28,7 +28,8 @@
 
 #include "udf_sb.h"
 
-static int udf_translate_to_linux(uint8_t *, uint8_t *, int, uint8_t *, int);
+static int udf_translate_to_linux(uint8_t *, int, uint8_t *, int, uint8_t *,
+				  int);
 
 static int udf_char_to_ustr(struct ustr *dest, const uint8_t *src, int strlen)
 {
@@ -333,8 +334,8 @@ try_again:
 	return u_len + 1;
 }
 
-int udf_get_filename(struct super_block *sb, uint8_t *sname, uint8_t *dname,
-		     int flen)
+int udf_get_filename(struct super_block *sb, uint8_t *sname, int slen,
+		     uint8_t *dname, int dlen)
 {
 	struct ustr *filename, *unifilename;
 	int len = 0;
@@ -347,7 +348,7 @@ int udf_get_filename(struct super_block *sb, uint8_t *sname, uint8_t *dname,
 	if (!unifilename)
 		goto out1;
 
-	if (udf_build_ustr_exact(unifilename, sname, flen))
+	if (udf_build_ustr_exact(unifilename, sname, slen))
 		goto out2;
 
 	if (UDF_QUERY_FLAG(sb, UDF_FLAG_UTF8)) {
@@ -366,7 +367,8 @@ int udf_get_filename(struct super_block *sb, uint8_t *sname, uint8_t *dname,
 	} else
 		goto out2;
 
-	len = udf_translate_to_linux(dname, filename->u_name, filename->u_len,
+	len = udf_translate_to_linux(dname, dlen,
+				     filename->u_name, filename->u_len,
 				     unifilename->u_name, unifilename->u_len);
 out2:
 	kfree(unifilename);
@@ -403,10 +405,12 @@ int udf_put_filename(struct super_block *sb, const uint8_t *sname,
 #define EXT_MARK		'.'
 #define CRC_MARK		'#'
 #define EXT_SIZE 		5
+/* Number of chars we need to store generated CRC to make filename unique */
+#define CRC_LEN			5
 
-static int udf_translate_to_linux(uint8_t *newName, uint8_t *udfName,
-				  int udfLen, uint8_t *fidName,
-				  int fidNameLen)
+static int udf_translate_to_linux(uint8_t *newName, int newLen,
+				  uint8_t *udfName, int udfLen,
+				  uint8_t *fidName, int fidNameLen)
 {
 	int index, newIndex = 0, needsCRC = 0;
 	int extIndex = 0, newExtIndex = 0, hasExt = 0;
@@ -439,7 +443,7 @@ static int udf_translate_to_linux(uint8_t *newName, uint8_t *udfName,
 					newExtIndex = newIndex;
 				}
 			}
-			if (newIndex < 256)
+			if (newIndex < newLen)
 				newName[newIndex++] = curr;
 			else
 				needsCRC = 1;
@@ -467,13 +471,13 @@ static int udf_translate_to_linux(uint8_t *newName, uint8_t *udfName,
 				}
 				ext[localExtIndex++] = curr;
 			}
-			maxFilenameLen = 250 - localExtIndex;
+			maxFilenameLen = newLen - CRC_LEN - localExtIndex;
 			if (newIndex > maxFilenameLen)
 				newIndex = maxFilenameLen;
 			else
 				newIndex = newExtIndex;
-		} else if (newIndex > 250)
-			newIndex = 250;
+		} else if (newIndex > newLen - CRC_LEN)
+			newIndex = newLen - CRC_LEN;
 		newName[newIndex++] = CRC_MARK;
 		valueCRC = crc_itu_t(0, fidName, fidNameLen);
 		newName[newIndex++] = hex_asc_upper_hi(valueCRC >> 8);
diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index 2c1036080d5..a7106eda502 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -51,8 +51,8 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count)
 	
 	if (ufs_fragnum(fragment) + count > uspi->s_fpg)
 		ufs_error (sb, "ufs_free_fragments", "internal error");
-	
-	lock_ufs(sb);
+
+	mutex_lock(&UFS_SB(sb)->s_lock);
 	
 	cgno = ufs_dtog(uspi, fragment);
 	bit = ufs_dtogd(uspi, fragment);
@@ -115,13 +115,13 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count)
 	if (sb->s_flags & MS_SYNCHRONOUS)
 		ubh_sync_block(UCPI_UBH(ucpi));
 	ufs_mark_sb_dirty(sb);
-	
-	unlock_ufs(sb);
+
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT\n");
 	return;
 
 failed:
-	unlock_ufs(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT (FAILED)\n");
 	return;
 }
@@ -151,7 +151,7 @@ void ufs_free_blocks(struct inode *inode, u64 fragment, unsigned count)
 		goto failed;
 	}
 
-	lock_ufs(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 	
 do_more:
 	overflow = 0;
@@ -211,12 +211,12 @@ do_more:
 	}
 
 	ufs_mark_sb_dirty(sb);
-	unlock_ufs(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT\n");
 	return;
 
 failed_unlock:
-	unlock_ufs(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 failed:
 	UFSD("EXIT (FAILED)\n");
 	return;
@@ -357,7 +357,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 	usb1 = ubh_get_usb_first(uspi);
 	*err = -ENOSPC;
 
-	lock_ufs(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 	tmp = ufs_data_ptr_to_cpu(sb, p);
 
 	if (count + ufs_fragnum(fragment) > uspi->s_fpb) {
@@ -378,19 +378,19 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 				  "fragment %llu, tmp %llu\n",
 				  (unsigned long long)fragment,
 				  (unsigned long long)tmp);
-			unlock_ufs(sb);
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			return INVBLOCK;
 		}
 		if (fragment < UFS_I(inode)->i_lastfrag) {
 			UFSD("EXIT (ALREADY ALLOCATED)\n");
-			unlock_ufs(sb);
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			return 0;
 		}
 	}
 	else {
 		if (tmp) {
 			UFSD("EXIT (ALREADY ALLOCATED)\n");
-			unlock_ufs(sb);
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			return 0;
 		}
 	}
@@ -399,7 +399,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 	 * There is not enough space for user on the device
 	 */
 	if (!capable(CAP_SYS_RESOURCE) && ufs_freespace(uspi, UFS_MINFREE) <= 0) {
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		UFSD("EXIT (FAILED)\n");
 		return 0;
 	}
@@ -424,7 +424,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 			ufs_clear_frags(inode, result + oldcount,
 					newcount - oldcount, locked_page != NULL);
 		}
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		UFSD("EXIT, result %llu\n", (unsigned long long)result);
 		return result;
 	}
@@ -439,7 +439,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 						fragment + count);
 		ufs_clear_frags(inode, result + oldcount, newcount - oldcount,
 				locked_page != NULL);
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		UFSD("EXIT, result %llu\n", (unsigned long long)result);
 		return result;
 	}
@@ -477,7 +477,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 		*err = 0;
 		UFS_I(inode)->i_lastfrag = max(UFS_I(inode)->i_lastfrag,
 						fragment + count);
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		if (newcount < request)
 			ufs_free_fragments (inode, result + newcount, request - newcount);
 		ufs_free_fragments (inode, tmp, oldcount);
@@ -485,7 +485,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 		return result;
 	}
 
-	unlock_ufs(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT (FAILED)\n");
 	return 0;
 }		
diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c
index 7caa0165288..fd0203ce1f7 100644
--- a/fs/ufs/ialloc.c
+++ b/fs/ufs/ialloc.c
@@ -69,11 +69,11 @@ void ufs_free_inode (struct inode * inode)
 	
 	ino = inode->i_ino;
 
-	lock_ufs(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 
 	if (!((ino > 1) && (ino < (uspi->s_ncg * uspi->s_ipg )))) {
 		ufs_warning(sb, "ufs_free_inode", "reserved inode or nonexistent inode %u\n", ino);
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		return;
 	}
 	
@@ -81,7 +81,7 @@ void ufs_free_inode (struct inode * inode)
 	bit = ufs_inotocgoff (ino);
 	ucpi = ufs_load_cylinder (sb, cg);
 	if (!ucpi) {
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		return;
 	}
 	ucg = ubh_get_ucg(UCPI_UBH(ucpi));
@@ -115,7 +115,7 @@ void ufs_free_inode (struct inode * inode)
 		ubh_sync_block(UCPI_UBH(ucpi));
 	
 	ufs_mark_sb_dirty(sb);
-	unlock_ufs(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT\n");
 }
 
@@ -193,7 +193,7 @@ struct inode *ufs_new_inode(struct inode *dir, umode_t mode)
 	sbi = UFS_SB(sb);
 	uspi = sbi->s_uspi;
 
-	lock_ufs(sb);
+	mutex_lock(&sbi->s_lock);
 
 	/*
 	 * Try to place the inode in its parent directory
@@ -331,21 +331,21 @@ cg_found:
 			sync_dirty_buffer(bh);
 		brelse(bh);
 	}
-	unlock_ufs(sb);
+	mutex_unlock(&sbi->s_lock);
 
 	UFSD("allocating inode %lu\n", inode->i_ino);
 	UFSD("EXIT\n");
 	return inode;
 
 fail_remove_inode:
-	unlock_ufs(sb);
+	mutex_unlock(&sbi->s_lock);
 	clear_nlink(inode);
 	unlock_new_inode(inode);
 	iput(inode);
 	UFSD("EXIT (FAILED): err %d\n", err);
 	return ERR_PTR(err);
 failed:
-	unlock_ufs(sb);
+	mutex_unlock(&sbi->s_lock);
 	make_bad_inode(inode);
 	iput (inode);
 	UFSD("EXIT (FAILED): err %d\n", err);
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index be7d42c7d93..2d93ab07da8 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -902,6 +902,9 @@ void ufs_evict_inode(struct inode * inode)
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
 
-	if (want_delete)
+	if (want_delete) {
+		lock_ufs(inode->i_sb);
 		ufs_free_inode(inode);
+		unlock_ufs(inode->i_sb);
+	}
 }
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index fd65deb4b5f..e8ee2985b06 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -128,12 +128,12 @@ static int ufs_symlink (struct inode * dir, struct dentry * dentry,
 	if (l > sb->s_blocksize)
 		goto out_notlocked;
 
+	lock_ufs(dir->i_sb);
 	inode = ufs_new_inode(dir, S_IFLNK | S_IRWXUGO);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
-		goto out_notlocked;
+		goto out;
 
-	lock_ufs(dir->i_sb);
 	if (l > UFS_SB(sb)->s_uspi->s_maxsymlinklen) {
 		/* slow symlink */
 		inode->i_op = &ufs_symlink_inode_operations;
@@ -174,7 +174,12 @@ static int ufs_link (struct dentry * old_dentry, struct inode * dir,
 	inode_inc_link_count(inode);
 	ihold(inode);
 
-	error = ufs_add_nondir(dentry, inode);
+	error = ufs_add_link(dentry, inode);
+	if (error) {
+		inode_dec_link_count(inode);
+		iput(inode);
+	} else
+		d_instantiate(dentry, inode);
 	unlock_ufs(dir->i_sb);
 	return error;
 }
@@ -184,9 +189,13 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
 	struct inode * inode;
 	int err;
 
+	lock_ufs(dir->i_sb);
+	inode_inc_link_count(dir);
+
 	inode = ufs_new_inode(dir, S_IFDIR|mode);
+	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
-		return PTR_ERR(inode);
+		goto out_dir;
 
 	inode->i_op = &ufs_dir_inode_operations;
 	inode->i_fop = &ufs_dir_operations;
@@ -194,9 +203,6 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
 
 	inode_inc_link_count(inode);
 
-	lock_ufs(dir->i_sb);
-	inode_inc_link_count(dir);
-
 	err = ufs_make_empty(inode, dir);
 	if (err)
 		goto out_fail;
@@ -206,6 +212,7 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
 		goto out_fail;
 	unlock_ufs(dir->i_sb);
 
+	unlock_new_inode(inode);
 	d_instantiate(dentry, inode);
 out:
 	return err;
@@ -215,6 +222,7 @@ out_fail:
 	inode_dec_link_count(inode);
 	unlock_new_inode(inode);
 	iput (inode);
+out_dir:
 	inode_dec_link_count(dir);
 	unlock_ufs(dir->i_sb);
 	goto out;
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index da73801301d..ce02dff5572 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -698,6 +698,7 @@ static int ufs_sync_fs(struct super_block *sb, int wait)
 	unsigned flags;
 
 	lock_ufs(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 
 	UFSD("ENTER\n");
 
@@ -715,6 +716,7 @@ static int ufs_sync_fs(struct super_block *sb, int wait)
 	ufs_put_cstotal(sb);
 
 	UFSD("EXIT\n");
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	unlock_ufs(sb);
 
 	return 0;
@@ -803,6 +805,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 	UFSD("flag %u\n", (int)(sb->s_flags & MS_RDONLY));
 	
 	mutex_init(&sbi->mutex);
+	mutex_init(&sbi->s_lock);
 	spin_lock_init(&sbi->work_lock);
 	INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs);
 	/*
@@ -1281,6 +1284,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 
 	sync_filesystem(sb);
 	lock_ufs(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 	uspi = UFS_SB(sb)->s_uspi;
 	flags = UFS_SB(sb)->s_flags;
 	usb1 = ubh_get_usb_first(uspi);
@@ -1294,6 +1298,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 	new_mount_opt = 0;
 	ufs_set_opt (new_mount_opt, ONERROR_LOCK);
 	if (!ufs_parse_options (data, &new_mount_opt)) {
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		unlock_ufs(sb);
 		return -EINVAL;
 	}
@@ -1301,12 +1306,14 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 		new_mount_opt |= ufstype;
 	} else if ((new_mount_opt & UFS_MOUNT_UFSTYPE) != ufstype) {
 		pr_err("ufstype can't be changed during remount\n");
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		unlock_ufs(sb);
 		return -EINVAL;
 	}
 
 	if ((*mount_flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
 		UFS_SB(sb)->s_mount_opt = new_mount_opt;
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		unlock_ufs(sb);
 		return 0;
 	}
@@ -1330,6 +1337,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 	 */
 #ifndef CONFIG_UFS_FS_WRITE
 		pr_err("ufs was compiled with read-only support, can't be mounted as read-write\n");
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		unlock_ufs(sb);
 		return -EINVAL;
 #else
@@ -1339,11 +1347,13 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 		    ufstype != UFS_MOUNT_UFSTYPE_SUNx86 &&
 		    ufstype != UFS_MOUNT_UFSTYPE_UFS2) {
 			pr_err("this ufstype is read-only supported\n");
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			unlock_ufs(sb);
 			return -EINVAL;
 		}
 		if (!ufs_read_cylinder_structures(sb)) {
 			pr_err("failed during remounting\n");
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			unlock_ufs(sb);
 			return -EPERM;
 		}
@@ -1351,6 +1361,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 #endif
 	}
 	UFS_SB(sb)->s_mount_opt = new_mount_opt;
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	unlock_ufs(sb);
 	return 0;
 }
diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h
index 2a07396d5f9..cf6368d42d4 100644
--- a/fs/ufs/ufs.h
+++ b/fs/ufs/ufs.h
@@ -30,6 +30,7 @@ struct ufs_sb_info {
 	int work_queued; /* non-zero if the delayed work is queued */
 	struct delayed_work sync_work; /* FS sync delayed work */
 	spinlock_t work_lock; /* protects sync_work and work_queued */
+	struct mutex s_lock;
 };
 
 struct ufs_inode_info {
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index b1f73dbbf3d..b7cd0a0541a 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -500,8 +500,8 @@ xfs_attr_shortform_add(xfs_da_args_t *args, int forkoff)
  * After the last attribute is removed revert to original inode format,
  * making all literal area available to the data fork once more.
  */
-STATIC void
-xfs_attr_fork_reset(
+void
+xfs_attr_fork_remove(
 	struct xfs_inode	*ip,
 	struct xfs_trans	*tp)
 {
@@ -567,7 +567,7 @@ xfs_attr_shortform_remove(xfs_da_args_t *args)
 	    (mp->m_flags & XFS_MOUNT_ATTR2) &&
 	    (dp->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
 	    !(args->op_flags & XFS_DA_OP_ADDNAME)) {
-		xfs_attr_fork_reset(dp, args->trans);
+		xfs_attr_fork_remove(dp, args->trans);
 	} else {
 		xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
 		dp->i_d.di_forkoff = xfs_attr_shortform_bytesfit(dp, totsize);
@@ -830,7 +830,7 @@ xfs_attr3_leaf_to_shortform(
 	if (forkoff == -1) {
 		ASSERT(dp->i_mount->m_flags & XFS_MOUNT_ATTR2);
 		ASSERT(dp->i_d.di_format != XFS_DINODE_FMT_BTREE);
-		xfs_attr_fork_reset(dp, args->trans);
+		xfs_attr_fork_remove(dp, args->trans);
 		goto out;
 	}
 
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index e2929da7c3b..4f3a60aa93d 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -53,7 +53,7 @@ int	xfs_attr_shortform_remove(struct xfs_da_args *args);
 int	xfs_attr_shortform_list(struct xfs_attr_list_context *context);
 int	xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
 int	xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes);
-
+void	xfs_attr_fork_remove(struct xfs_inode *ip, struct xfs_trans *tp);
 
 /*
  * Internal routines when attribute fork size == XFS_LBSIZE(mp).
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 79c981984dc..661666ecac2 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -976,7 +976,11 @@ xfs_bmap_local_to_extents(
 	*firstblock = args.fsbno;
 	bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0);
 
-	/* initialise the block and copy the data */
+	/*
+	 * Initialise the block and copy the data
+	 *
+	 * Note: init_fn must set the buffer log item type correctly!
+	 */
 	init_fn(tp, bp, ip, ifp);
 
 	/* account for the change in fork size and log everything */
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index 5782f037eab..a7dce9aea5b 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -180,6 +180,8 @@ xfs_symlink_local_to_remote(
 	struct xfs_mount	*mp = ip->i_mount;
 	char			*buf;
 
+	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SYMLINK_BUF);
+
 	if (!xfs_sb_version_hascrc(&mp->m_sb)) {
 		bp->b_ops = NULL;
 		memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes);
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index aa2a8b1838a..0687b67741b 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -382,23 +382,31 @@ xfs_attr3_root_inactive(
 	return error;
 }
 
+/*
+ * xfs_attr_inactive kills all traces of an attribute fork on an inode. It
+ * removes both the on-disk and in-memory inode fork. Note that this also has to
+ * handle the condition of inodes without attributes but with an attribute fork
+ * configured, so we can't use xfs_inode_hasattr() here.
+ *
+ * The in-memory attribute fork is removed even on error.
+ */
 int
-xfs_attr_inactive(xfs_inode_t *dp)
+xfs_attr_inactive(
+	struct xfs_inode	*dp)
 {
-	xfs_trans_t *trans;
-	xfs_mount_t *mp;
-	int error;
+	struct xfs_trans	*trans;
+	struct xfs_mount	*mp;
+	int			cancel_flags = 0;
+	int			lock_mode = XFS_ILOCK_SHARED;
+	int			error = 0;
 
 	mp = dp->i_mount;
 	ASSERT(! XFS_NOT_DQATTACHED(mp, dp));
 
-	xfs_ilock(dp, XFS_ILOCK_SHARED);
-	if (!xfs_inode_hasattr(dp) ||
-	    dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
-		xfs_iunlock(dp, XFS_ILOCK_SHARED);
-		return 0;
-	}
-	xfs_iunlock(dp, XFS_ILOCK_SHARED);
+	xfs_ilock(dp, lock_mode);
+	if (!XFS_IFORK_Q(dp))
+		goto out_destroy_fork;
+	xfs_iunlock(dp, lock_mode);
 
 	/*
 	 * Start our first transaction of the day.
@@ -410,13 +418,18 @@ xfs_attr_inactive(xfs_inode_t *dp)
 	 * the inode in every transaction to let it float upward through
 	 * the log.
 	 */
+	lock_mode = 0;
 	trans = xfs_trans_alloc(mp, XFS_TRANS_ATTRINVAL);
 	error = xfs_trans_reserve(trans, &M_RES(mp)->tr_attrinval, 0, 0);
-	if (error) {
-		xfs_trans_cancel(trans, 0);
-		return error;
-	}
-	xfs_ilock(dp, XFS_ILOCK_EXCL);
+	if (error)
+		goto out_cancel;
+
+	lock_mode = XFS_ILOCK_EXCL;
+	cancel_flags = XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT;
+	xfs_ilock(dp, lock_mode);
+
+	if (!XFS_IFORK_Q(dp))
+		goto out_cancel;
 
 	/*
 	 * No need to make quota reservations here. We expect to release some
@@ -424,29 +437,31 @@ xfs_attr_inactive(xfs_inode_t *dp)
 	 */
 	xfs_trans_ijoin(trans, dp, 0);
 
-	/*
-	 * Decide on what work routines to call based on the inode size.
-	 */
-	if (!xfs_inode_hasattr(dp) ||
-	    dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
-		error = 0;
-		goto out;
+	/* invalidate and truncate the attribute fork extents */
+	if (dp->i_d.di_aformat != XFS_DINODE_FMT_LOCAL) {
+		error = xfs_attr3_root_inactive(&trans, dp);
+		if (error)
+			goto out_cancel;
+
+		error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
+		if (error)
+			goto out_cancel;
 	}
-	error = xfs_attr3_root_inactive(&trans, dp);
-	if (error)
-		goto out;
 
-	error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
-	if (error)
-		goto out;
+	/* Reset the attribute fork - this also destroys the in-core fork */
+	xfs_attr_fork_remove(dp, trans);
 
 	error = xfs_trans_commit(trans, XFS_TRANS_RELEASE_LOG_RES);
-	xfs_iunlock(dp, XFS_ILOCK_EXCL);
-
+	xfs_iunlock(dp, lock_mode);
 	return error;
 
-out:
-	xfs_trans_cancel(trans, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
-	xfs_iunlock(dp, XFS_ILOCK_EXCL);
+out_cancel:
+	xfs_trans_cancel(trans, cancel_flags);
+out_destroy_fork:
+	/* kill the in-core attr fork before we drop the inode lock */
+	if (dp->i_afp)
+		xfs_idestroy_fork(dp, XFS_ATTR_FORK);
+	if (lock_mode)
+		xfs_iunlock(dp, lock_mode);
 	return error;
 }
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index f1596954332..1a6c9b93678 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -319,6 +319,10 @@ xfs_buf_item_format(
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
 	ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
 	       (bip->bli_flags & XFS_BLI_STALE));
+	ASSERT((bip->bli_flags & XFS_BLI_STALE) ||
+	       (xfs_blft_from_flags(&bip->__bli_format) > XFS_BLFT_UNKNOWN_BUF
+	        && xfs_blft_from_flags(&bip->__bli_format) < XFS_BLFT_MAX_BUF));
+
 
 	/*
 	 * If it is an inode buffer, transfer the in-memory state to the
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index eb596b41994..ba8b158a618 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -127,7 +127,7 @@ xfs_iozero(
 		status = 0;
 	} while (count);
 
-	return (-status);
+	return status;
 }
 
 /*
@@ -363,7 +363,8 @@ STATIC int				/* error (positive) */
 xfs_zero_last_block(
 	struct xfs_inode	*ip,
 	xfs_fsize_t		offset,
-	xfs_fsize_t		isize)
+	xfs_fsize_t		isize,
+	bool			*did_zeroing)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		last_fsb = XFS_B_TO_FSBT(mp, isize);
@@ -391,6 +392,7 @@ xfs_zero_last_block(
 	zero_len = mp->m_sb.sb_blocksize - zero_offset;
 	if (isize + zero_len > offset)
 		zero_len = offset - isize;
+	*did_zeroing = true;
 	return xfs_iozero(ip, isize, zero_len);
 }
 
@@ -409,7 +411,8 @@ int					/* error (positive) */
 xfs_zero_eof(
 	struct xfs_inode	*ip,
 	xfs_off_t		offset,		/* starting I/O offset */
-	xfs_fsize_t		isize)		/* current inode size */
+	xfs_fsize_t		isize,		/* current inode size */
+	bool			*did_zeroing)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		start_zero_fsb;
@@ -431,7 +434,7 @@ xfs_zero_eof(
 	 * We only zero a part of that block so it is handled specially.
 	 */
 	if (XFS_B_FSB_OFFSET(mp, isize) != 0) {
-		error = xfs_zero_last_block(ip, offset, isize);
+		error = xfs_zero_last_block(ip, offset, isize, did_zeroing);
 		if (error)
 			return error;
 	}
@@ -491,6 +494,7 @@ xfs_zero_eof(
 		if (error)
 			return error;
 
+		*did_zeroing = true;
 		start_zero_fsb = imap.br_startoff + imap.br_blockcount;
 		ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
 	}
@@ -529,13 +533,15 @@ restart:
 	 * having to redo all checks before.
 	 */
 	if (*pos > i_size_read(inode)) {
+		bool	zero = false;
+
 		if (*iolock == XFS_IOLOCK_SHARED) {
 			xfs_rw_iunlock(ip, *iolock);
 			*iolock = XFS_IOLOCK_EXCL;
 			xfs_rw_ilock(ip, *iolock);
 			goto restart;
 		}
-		error = xfs_zero_eof(ip, *pos, i_size_read(inode));
+		error = xfs_zero_eof(ip, *pos, i_size_read(inode), &zero);
 		if (error)
 			return error;
 	}
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 8ed049d1e33..32e95c76cbd 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1894,21 +1894,17 @@ xfs_inactive(
 	/*
 	 * If there are attributes associated with the file then blow them away
 	 * now.  The code calls a routine that recursively deconstructs the
-	 * attribute fork.  We need to just commit the current transaction
-	 * because we can't use it for xfs_attr_inactive().
+	 * attribute fork. If also blows away the in-core attribute fork.
 	 */
-	if (ip->i_d.di_anextents > 0) {
-		ASSERT(ip->i_d.di_forkoff != 0);
-
+	if (XFS_IFORK_Q(ip)) {
 		error = xfs_attr_inactive(ip);
 		if (error)
 			return;
 	}
 
-	if (ip->i_afp)
-		xfs_idestroy_fork(ip, XFS_ATTR_FORK);
-
+	ASSERT(!ip->i_afp);
 	ASSERT(ip->i_d.di_anextents == 0);
+	ASSERT(ip->i_d.di_forkoff == 0);
 
 	/*
 	 * Free the inode.
@@ -2000,6 +1996,7 @@ xfs_iunlink(
 	agi->agi_unlinked[bucket_index] = cpu_to_be32(agino);
 	offset = offsetof(xfs_agi_t, agi_unlinked) +
 		(sizeof(xfs_agino_t) * bucket_index);
+	xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF);
 	xfs_trans_log_buf(tp, agibp, offset,
 			  (offset + sizeof(xfs_agino_t) - 1));
 	return 0;
@@ -2091,6 +2088,7 @@ xfs_iunlink_remove(
 		agi->agi_unlinked[bucket_index] = cpu_to_be32(next_agino);
 		offset = offsetof(xfs_agi_t, agi_unlinked) +
 			(sizeof(xfs_agino_t) * bucket_index);
+		xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF);
 		xfs_trans_log_buf(tp, agibp, offset,
 				  (offset + sizeof(xfs_agino_t) - 1));
 	} else {
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 9af2882e1f4..cb6ab0ad91a 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -379,8 +379,9 @@ int		xfs_droplink(struct xfs_trans *, struct xfs_inode *);
 int		xfs_bumplink(struct xfs_trans *, struct xfs_inode *);
 
 /* from xfs_file.c */
-int		xfs_zero_eof(struct xfs_inode *, xfs_off_t, xfs_fsize_t);
-int		xfs_iozero(struct xfs_inode *, loff_t, size_t);
+int	xfs_zero_eof(struct xfs_inode *ip, xfs_off_t offset,
+		     xfs_fsize_t isize, bool *did_zeroing);
+int	xfs_iozero(struct xfs_inode *ip, loff_t pos, size_t count);
 
 
 #define IHOLD(ip) \
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index ec6dcdc181e..d2273d24399 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -744,6 +744,7 @@ xfs_setattr_size(
 	int			error;
 	uint			lock_flags = 0;
 	uint			commit_flags = 0;
+	bool			did_zeroing = false;
 
 	trace_xfs_setattr(ip);
 
@@ -787,20 +788,16 @@ xfs_setattr_size(
 		return error;
 
 	/*
-	 * Now we can make the changes.  Before we join the inode to the
-	 * transaction, take care of the part of the truncation that must be
-	 * done without the inode lock.  This needs to be done before joining
-	 * the inode to the transaction, because the inode cannot be unlocked
-	 * once it is a part of the transaction.
+	 * File data changes must be complete before we start the transaction to
+	 * modify the inode.  This needs to be done before joining the inode to
+	 * the transaction because the inode cannot be unlocked once it is a
+	 * part of the transaction.
+	 *
+	 * Start with zeroing any data block beyond EOF that we may expose on
+	 * file extension.
 	 */
 	if (newsize > oldsize) {
-		/*
-		 * Do the first part of growing a file: zero any data in the
-		 * last block that is beyond the old EOF.  We need to do this
-		 * before the inode is joined to the transaction to modify
-		 * i_size.
-		 */
-		error = xfs_zero_eof(ip, newsize, oldsize);
+		error = xfs_zero_eof(ip, newsize, oldsize, &did_zeroing);
 		if (error)
 			return error;
 	}
@@ -810,23 +807,18 @@ xfs_setattr_size(
 	 * any previous writes that are beyond the on disk EOF and the new
 	 * EOF that have not been written out need to be written here.  If we
 	 * do not write the data out, we expose ourselves to the null files
-	 * problem.
-	 *
-	 * Only flush from the on disk size to the smaller of the in memory
-	 * file size or the new size as that's the range we really care about
-	 * here and prevents waiting for other data not within the range we
-	 * care about here.
+	 * problem. Note that this includes any block zeroing we did above;
+	 * otherwise those blocks may not be zeroed after a crash.
 	 */
-	if (oldsize != ip->i_d.di_size && newsize > ip->i_d.di_size) {
+	if (newsize > ip->i_d.di_size &&
+	    (oldsize != ip->i_d.di_size || did_zeroing)) {
 		error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
 						      ip->i_d.di_size, newsize);
 		if (error)
 			return error;
 	}
 
-	/*
-	 * Wait for all direct I/O to complete.
-	 */
+	/* Now wait for all direct I/O to complete. */
 	inode_dio_wait(inode);
 
 	/*
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index d68f23021af..cf2bc2dd702 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -844,6 +844,11 @@ xfs_qm_reset_dqcounts(
 		 */
 		xfs_dqcheck(mp, ddq, id+j, type, XFS_QMOPT_DQREPAIR,
 			    "xfs_quotacheck");
+		/*
+		 * Reset type in case we are reusing group quota file for
+		 * project quotas or vice versa
+		 */
+		ddq->d_flags = type;
 		ddq->d_bcount = 0;
 		ddq->d_icount = 0;
 		ddq->d_rtbcount = 0;
diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h
index 3a07a937e23..41f6c0b9d51 100644
--- a/fs/xfs/xfs_qm.h
+++ b/fs/xfs/xfs_qm.h
@@ -166,9 +166,9 @@ extern void		xfs_qm_dqrele_all_inodes(struct xfs_mount *, uint);
 /* quota ops */
 extern int		xfs_qm_scall_trunc_qfiles(struct xfs_mount *, uint);
 extern int		xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t,
-					uint, struct fs_disk_quota *);
+					uint, struct qc_dqblk *);
 extern int		xfs_qm_scall_setqlim(struct xfs_mount *, xfs_dqid_t, uint,
-					struct fs_disk_quota *);
+					struct qc_dqblk *);
 extern int		xfs_qm_scall_getqstat(struct xfs_mount *,
 					struct fs_quota_stat *);
 extern int		xfs_qm_scall_getqstatv(struct xfs_mount *,
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 80f2d77d929..327f85abbea 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -40,7 +40,6 @@ STATIC int	xfs_qm_log_quotaoff(xfs_mount_t *, xfs_qoff_logitem_t **, uint);
 STATIC int	xfs_qm_log_quotaoff_end(xfs_mount_t *, xfs_qoff_logitem_t *,
 					uint);
 STATIC uint	xfs_qm_export_flags(uint);
-STATIC uint	xfs_qm_export_qtype_flags(uint);
 
 /*
  * Turn off quota accounting and/or enforcement for all udquots and/or
@@ -574,8 +573,8 @@ xfs_qm_scall_getqstatv(
 	return 0;
 }
 
-#define XFS_DQ_MASK \
-	(FS_DQ_LIMIT_MASK | FS_DQ_TIMER_MASK | FS_DQ_WARNS_MASK)
+#define XFS_QC_MASK \
+	(QC_LIMIT_MASK | QC_TIMER_MASK | QC_WARNS_MASK)
 
 /*
  * Adjust quota limits, and start/stop timers accordingly.
@@ -585,7 +584,7 @@ xfs_qm_scall_setqlim(
 	struct xfs_mount	*mp,
 	xfs_dqid_t		id,
 	uint			type,
-	fs_disk_quota_t		*newlim)
+	struct qc_dqblk		*newlim)
 {
 	struct xfs_quotainfo	*q = mp->m_quotainfo;
 	struct xfs_disk_dquot	*ddq;
@@ -594,9 +593,9 @@ xfs_qm_scall_setqlim(
 	int			error;
 	xfs_qcnt_t		hard, soft;
 
-	if (newlim->d_fieldmask & ~XFS_DQ_MASK)
+	if (newlim->d_fieldmask & ~XFS_QC_MASK)
 		return -EINVAL;
-	if ((newlim->d_fieldmask & XFS_DQ_MASK) == 0)
+	if ((newlim->d_fieldmask & XFS_QC_MASK) == 0)
 		return 0;
 
 	/*
@@ -634,11 +633,11 @@ xfs_qm_scall_setqlim(
 	/*
 	 * Make sure that hardlimits are >= soft limits before changing.
 	 */
-	hard = (newlim->d_fieldmask & FS_DQ_BHARD) ?
-		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_hardlimit) :
+	hard = (newlim->d_fieldmask & QC_SPC_HARD) ?
+		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_hardlimit) :
 			be64_to_cpu(ddq->d_blk_hardlimit);
-	soft = (newlim->d_fieldmask & FS_DQ_BSOFT) ?
-		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_softlimit) :
+	soft = (newlim->d_fieldmask & QC_SPC_SOFT) ?
+		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_softlimit) :
 			be64_to_cpu(ddq->d_blk_softlimit);
 	if (hard == 0 || hard >= soft) {
 		ddq->d_blk_hardlimit = cpu_to_be64(hard);
@@ -651,11 +650,11 @@ xfs_qm_scall_setqlim(
 	} else {
 		xfs_debug(mp, "blkhard %Ld < blksoft %Ld", hard, soft);
 	}
-	hard = (newlim->d_fieldmask & FS_DQ_RTBHARD) ?
-		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_hardlimit) :
+	hard = (newlim->d_fieldmask & QC_RT_SPC_HARD) ?
+		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_hardlimit) :
 			be64_to_cpu(ddq->d_rtb_hardlimit);
-	soft = (newlim->d_fieldmask & FS_DQ_RTBSOFT) ?
-		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_softlimit) :
+	soft = (newlim->d_fieldmask & QC_RT_SPC_SOFT) ?
+		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_softlimit) :
 			be64_to_cpu(ddq->d_rtb_softlimit);
 	if (hard == 0 || hard >= soft) {
 		ddq->d_rtb_hardlimit = cpu_to_be64(hard);
@@ -668,10 +667,10 @@ xfs_qm_scall_setqlim(
 		xfs_debug(mp, "rtbhard %Ld < rtbsoft %Ld", hard, soft);
 	}
 
-	hard = (newlim->d_fieldmask & FS_DQ_IHARD) ?
+	hard = (newlim->d_fieldmask & QC_INO_HARD) ?
 		(xfs_qcnt_t) newlim->d_ino_hardlimit :
 			be64_to_cpu(ddq->d_ino_hardlimit);
-	soft = (newlim->d_fieldmask & FS_DQ_ISOFT) ?
+	soft = (newlim->d_fieldmask & QC_INO_SOFT) ?
 		(xfs_qcnt_t) newlim->d_ino_softlimit :
 			be64_to_cpu(ddq->d_ino_softlimit);
 	if (hard == 0 || hard >= soft) {
@@ -688,12 +687,12 @@ xfs_qm_scall_setqlim(
 	/*
 	 * Update warnings counter(s) if requested
 	 */
-	if (newlim->d_fieldmask & FS_DQ_BWARNS)
-		ddq->d_bwarns = cpu_to_be16(newlim->d_bwarns);
-	if (newlim->d_fieldmask & FS_DQ_IWARNS)
-		ddq->d_iwarns = cpu_to_be16(newlim->d_iwarns);
-	if (newlim->d_fieldmask & FS_DQ_RTBWARNS)
-		ddq->d_rtbwarns = cpu_to_be16(newlim->d_rtbwarns);
+	if (newlim->d_fieldmask & QC_SPC_WARNS)
+		ddq->d_bwarns = cpu_to_be16(newlim->d_spc_warns);
+	if (newlim->d_fieldmask & QC_INO_WARNS)
+		ddq->d_iwarns = cpu_to_be16(newlim->d_ino_warns);
+	if (newlim->d_fieldmask & QC_RT_SPC_WARNS)
+		ddq->d_rtbwarns = cpu_to_be16(newlim->d_rt_spc_warns);
 
 	if (id == 0) {
 		/*
@@ -703,24 +702,24 @@ xfs_qm_scall_setqlim(
 		 * soft and hard limit values (already done, above), and
 		 * for warnings.
 		 */
-		if (newlim->d_fieldmask & FS_DQ_BTIMER) {
-			q->qi_btimelimit = newlim->d_btimer;
-			ddq->d_btimer = cpu_to_be32(newlim->d_btimer);
+		if (newlim->d_fieldmask & QC_SPC_TIMER) {
+			q->qi_btimelimit = newlim->d_spc_timer;
+			ddq->d_btimer = cpu_to_be32(newlim->d_spc_timer);
 		}
-		if (newlim->d_fieldmask & FS_DQ_ITIMER) {
-			q->qi_itimelimit = newlim->d_itimer;
-			ddq->d_itimer = cpu_to_be32(newlim->d_itimer);
+		if (newlim->d_fieldmask & QC_INO_TIMER) {
+			q->qi_itimelimit = newlim->d_ino_timer;
+			ddq->d_itimer = cpu_to_be32(newlim->d_ino_timer);
 		}
-		if (newlim->d_fieldmask & FS_DQ_RTBTIMER) {
-			q->qi_rtbtimelimit = newlim->d_rtbtimer;
-			ddq->d_rtbtimer = cpu_to_be32(newlim->d_rtbtimer);
+		if (newlim->d_fieldmask & QC_RT_SPC_TIMER) {
+			q->qi_rtbtimelimit = newlim->d_rt_spc_timer;
+			ddq->d_rtbtimer = cpu_to_be32(newlim->d_rt_spc_timer);
 		}
-		if (newlim->d_fieldmask & FS_DQ_BWARNS)
-			q->qi_bwarnlimit = newlim->d_bwarns;
-		if (newlim->d_fieldmask & FS_DQ_IWARNS)
-			q->qi_iwarnlimit = newlim->d_iwarns;
-		if (newlim->d_fieldmask & FS_DQ_RTBWARNS)
-			q->qi_rtbwarnlimit = newlim->d_rtbwarns;
+		if (newlim->d_fieldmask & QC_SPC_WARNS)
+			q->qi_bwarnlimit = newlim->d_spc_warns;
+		if (newlim->d_fieldmask & QC_INO_WARNS)
+			q->qi_iwarnlimit = newlim->d_ino_warns;
+		if (newlim->d_fieldmask & QC_RT_SPC_WARNS)
+			q->qi_rtbwarnlimit = newlim->d_rt_spc_warns;
 	} else {
 		/*
 		 * If the user is now over quota, start the timelimit.
@@ -831,7 +830,7 @@ xfs_qm_scall_getquota(
 	struct xfs_mount	*mp,
 	xfs_dqid_t		id,
 	uint			type,
-	struct fs_disk_quota	*dst)
+	struct qc_dqblk		*dst)
 {
 	struct xfs_dquot	*dqp;
 	int			error;
@@ -855,28 +854,25 @@ xfs_qm_scall_getquota(
 	}
 
 	memset(dst, 0, sizeof(*dst));
-	dst->d_version = FS_DQUOT_VERSION;
-	dst->d_flags = xfs_qm_export_qtype_flags(dqp->q_core.d_flags);
-	dst->d_id = be32_to_cpu(dqp->q_core.d_id);
-	dst->d_blk_hardlimit =
-		XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit));
-	dst->d_blk_softlimit =
-		XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_blk_softlimit));
+	dst->d_spc_hardlimit =
+		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit));
+	dst->d_spc_softlimit =
+		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_softlimit));
 	dst->d_ino_hardlimit = be64_to_cpu(dqp->q_core.d_ino_hardlimit);
 	dst->d_ino_softlimit = be64_to_cpu(dqp->q_core.d_ino_softlimit);
-	dst->d_bcount = XFS_FSB_TO_BB(mp, dqp->q_res_bcount);
-	dst->d_icount = dqp->q_res_icount;
-	dst->d_btimer = be32_to_cpu(dqp->q_core.d_btimer);
-	dst->d_itimer = be32_to_cpu(dqp->q_core.d_itimer);
-	dst->d_iwarns = be16_to_cpu(dqp->q_core.d_iwarns);
-	dst->d_bwarns = be16_to_cpu(dqp->q_core.d_bwarns);
-	dst->d_rtb_hardlimit =
-		XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_rtb_hardlimit));
-	dst->d_rtb_softlimit =
-		XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_rtb_softlimit));
-	dst->d_rtbcount = XFS_FSB_TO_BB(mp, dqp->q_res_rtbcount);
-	dst->d_rtbtimer = be32_to_cpu(dqp->q_core.d_rtbtimer);
-	dst->d_rtbwarns = be16_to_cpu(dqp->q_core.d_rtbwarns);
+	dst->d_space = XFS_FSB_TO_B(mp, dqp->q_res_bcount);
+	dst->d_ino_count = dqp->q_res_icount;
+	dst->d_spc_timer = be32_to_cpu(dqp->q_core.d_btimer);
+	dst->d_ino_timer = be32_to_cpu(dqp->q_core.d_itimer);
+	dst->d_ino_warns = be16_to_cpu(dqp->q_core.d_iwarns);
+	dst->d_spc_warns = be16_to_cpu(dqp->q_core.d_bwarns);
+	dst->d_rt_spc_hardlimit =
+		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_rtb_hardlimit));
+	dst->d_rt_spc_softlimit =
+		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_rtb_softlimit));
+	dst->d_rt_space = XFS_FSB_TO_B(mp, dqp->q_res_rtbcount);
+	dst->d_rt_spc_timer = be32_to_cpu(dqp->q_core.d_rtbtimer);
+	dst->d_rt_spc_warns = be16_to_cpu(dqp->q_core.d_rtbwarns);
 
 	/*
 	 * Internally, we don't reset all the timers when quota enforcement
@@ -889,23 +885,23 @@ xfs_qm_scall_getquota(
 	     dqp->q_core.d_flags == XFS_DQ_GROUP) ||
 	    (!XFS_IS_PQUOTA_ENFORCED(mp) &&
 	     dqp->q_core.d_flags == XFS_DQ_PROJ)) {
-		dst->d_btimer = 0;
-		dst->d_itimer = 0;
-		dst->d_rtbtimer = 0;
+		dst->d_spc_timer = 0;
+		dst->d_ino_timer = 0;
+		dst->d_rt_spc_timer = 0;
 	}
 
 #ifdef DEBUG
-	if (((XFS_IS_UQUOTA_ENFORCED(mp) && dst->d_flags == FS_USER_QUOTA) ||
-	     (XFS_IS_GQUOTA_ENFORCED(mp) && dst->d_flags == FS_GROUP_QUOTA) ||
-	     (XFS_IS_PQUOTA_ENFORCED(mp) && dst->d_flags == FS_PROJ_QUOTA)) &&
-	    dst->d_id != 0) {
-		if ((dst->d_bcount > dst->d_blk_softlimit) &&
-		    (dst->d_blk_softlimit > 0)) {
-			ASSERT(dst->d_btimer != 0);
+	if (((XFS_IS_UQUOTA_ENFORCED(mp) && type == XFS_DQ_USER) ||
+	     (XFS_IS_GQUOTA_ENFORCED(mp) && type == XFS_DQ_GROUP) ||
+	     (XFS_IS_PQUOTA_ENFORCED(mp) && type == XFS_DQ_PROJ)) &&
+	    id != 0) {
+		if ((dst->d_space > dst->d_spc_softlimit) &&
+		    (dst->d_spc_softlimit > 0)) {
+			ASSERT(dst->d_spc_timer != 0);
 		}
-		if ((dst->d_icount > dst->d_ino_softlimit) &&
+		if ((dst->d_ino_count > dst->d_ino_softlimit) &&
 		    (dst->d_ino_softlimit > 0)) {
-			ASSERT(dst->d_itimer != 0);
+			ASSERT(dst->d_ino_timer != 0);
 		}
 	}
 #endif
@@ -915,26 +911,6 @@ out_put:
 }
 
 STATIC uint
-xfs_qm_export_qtype_flags(
-	uint flags)
-{
-	/*
-	 * Can't be more than one, or none.
-	 */
-	ASSERT((flags & (FS_PROJ_QUOTA | FS_USER_QUOTA)) !=
-		(FS_PROJ_QUOTA | FS_USER_QUOTA));
-	ASSERT((flags & (FS_PROJ_QUOTA | FS_GROUP_QUOTA)) !=
-		(FS_PROJ_QUOTA | FS_GROUP_QUOTA));
-	ASSERT((flags & (FS_USER_QUOTA | FS_GROUP_QUOTA)) !=
-		(FS_USER_QUOTA | FS_GROUP_QUOTA));
-	ASSERT((flags & (FS_PROJ_QUOTA|FS_USER_QUOTA|FS_GROUP_QUOTA)) != 0);
-
-	return (flags & XFS_DQ_USER) ?
-		FS_USER_QUOTA : (flags & XFS_DQ_PROJ) ?
-			FS_PROJ_QUOTA : FS_GROUP_QUOTA;
-}
-
-STATIC uint
 xfs_qm_export_flags(
 	uint flags)
 {
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index b238027df98..320c814bb9a 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -133,7 +133,7 @@ STATIC int
 xfs_fs_get_dqblk(
 	struct super_block	*sb,
 	struct kqid		qid,
-	struct fs_disk_quota	*fdq)
+	struct qc_dqblk		*qdq)
 {
 	struct xfs_mount	*mp = XFS_M(sb);
 
@@ -143,14 +143,14 @@ xfs_fs_get_dqblk(
 		return -ESRCH;
 
 	return xfs_qm_scall_getquota(mp, from_kqid(&init_user_ns, qid),
-				      xfs_quota_type(qid.type), fdq);
+				      xfs_quota_type(qid.type), qdq);
 }
 
 STATIC int
 xfs_fs_set_dqblk(
 	struct super_block	*sb,
 	struct kqid		qid,
-	struct fs_disk_quota	*fdq)
+	struct qc_dqblk		*qdq)
 {
 	struct xfs_mount	*mp = XFS_M(sb);
 
@@ -162,7 +162,7 @@ xfs_fs_set_dqblk(
 		return -ESRCH;
 
 	return xfs_qm_scall_setqlim(mp, from_kqid(&init_user_ns, qid),
-				     xfs_quota_type(qid.type), fdq);
+				     xfs_quota_type(qid.type), qdq);
 }
 
 const struct quotactl_ops xfs_quotactl_operations = {
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 02ae62a998e..6a93fd583ec 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -107,7 +107,7 @@ xfs_readlink_bmap(
 			cur_chunk += sizeof(struct xfs_dsymlink_hdr);
 		}
 
-		memcpy(link + offset, bp->b_addr, byte_cnt);
+		memcpy(link + offset, cur_chunk, byte_cnt);
 
 		pathlen -= byte_cnt;
 		offset += byte_cnt;
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 30e8e341095..32dfdb5d3e6 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -474,6 +474,7 @@ xfs_trans_apply_sb_deltas(
 		whole = 1;
 	}
 
+	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);
 	if (whole)
 		/*
 		 * Log the whole thing, the fields are noncontiguous.
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index f34a0835aa4..20c757cdd39 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -312,6 +312,7 @@ struct acpi_device_wakeup_flags {
 	u8 valid:1;		/* Can successfully enable wakeup? */
 	u8 run_wake:1;		/* Run-Wake GPE devices */
 	u8 notifier_present:1;  /* Wake-up notify handler has been installed */
+	u8 enabled:1;		/* Enabled for wakeup */
 };
 
 struct acpi_device_wakeup_context {
@@ -337,6 +338,12 @@ struct acpi_device_physical_node {
 	bool put_online:1;
 };
 
+/* ACPI Device Specific Data (_DSD) */
+struct acpi_device_data {
+	const union acpi_object *pointer;
+	const union acpi_object *properties;
+};
+
 /* Device */
 struct acpi_device {
 	int device_type;
@@ -353,6 +360,7 @@ struct acpi_device {
 	struct acpi_device_wakeup wakeup;
 	struct acpi_device_perf performance;
 	struct acpi_device_dir dir;
+	struct acpi_device_data data;
 	struct acpi_scan_handler *handler;
 	struct acpi_hotplug_context *hp;
 	struct acpi_driver *driver;
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index ab2acf629a6..0747006ba2b 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -431,13 +431,13 @@ ACPI_EXTERNAL_RETURN_STATUS(acpi_status __init acpi_load_tables(void))
 ACPI_EXTERNAL_RETURN_STATUS(acpi_status __init acpi_reallocate_root_table(void))
 
 ACPI_EXTERNAL_RETURN_STATUS(acpi_status __init
-			    acpi_find_root_pointer(acpi_size * rsdp_address))
-
+			    acpi_find_root_pointer(acpi_physical_address *
+						   rsdp_address))
 ACPI_EXTERNAL_RETURN_STATUS(acpi_status
-			    acpi_get_table_header(acpi_string signature,
-						  u32 instance,
-						  struct acpi_table_header
-						  *out_table_header))
+			     acpi_get_table_header(acpi_string signature,
+						   u32 instance,
+						   struct acpi_table_header
+						   *out_table_header))
 ACPI_EXTERNAL_RETURN_STATUS(acpi_status
 			     acpi_get_table(acpi_string signature, u32 instance,
 					    struct acpi_table_header
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 7000e66f768..f6406e70ea4 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -199,9 +199,29 @@ typedef int s32;
 typedef s32 acpi_native_int;
 
 typedef u32 acpi_size;
+
+#ifdef ACPI_32BIT_PHYSICAL_ADDRESS
+
+/*
+ * OSPMs can define this to shrink the size of the structures for 32-bit
+ * none PAE environment. ASL compiler may always define this to generate
+ * 32-bit OSPM compliant tables.
+ */
 typedef u32 acpi_io_address;
 typedef u32 acpi_physical_address;
 
+#else				/* ACPI_32BIT_PHYSICAL_ADDRESS */
+
+/*
+ * It is reported that, after some calculations, the physical addresses can
+ * wrap over the 32-bit boundary on 32-bit PAE environment.
+ * https://bugzilla.kernel.org/show_bug.cgi?id=87971
+ */
+typedef u64 acpi_io_address;
+typedef u64 acpi_physical_address;
+
+#endif				/* ACPI_32BIT_PHYSICAL_ADDRESS */
+
 #define ACPI_MAX_PTR                    ACPI_UINT32_MAX
 #define ACPI_SIZE_MAX                   ACPI_UINT32_MAX
 
@@ -553,6 +573,7 @@ typedef u64 acpi_integer;
 #define ACPI_NO_ACPI_ENABLE             0x10
 #define ACPI_NO_DEVICE_INIT             0x20
 #define ACPI_NO_OBJECT_INIT             0x40
+#define ACPI_NO_FACS_INIT               0x80
 
 /*
  * Initialization state
diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h
index 5f8cc1fa327..9e1ed2e380b 100644
--- a/include/acpi/platform/acenv.h
+++ b/include/acpi/platform/acenv.h
@@ -76,6 +76,7 @@
 #define ACPI_LARGE_NAMESPACE_NODE
 #define ACPI_DATA_TABLE_DISASSEMBLY
 #define ACPI_SINGLE_THREADED
+#define ACPI_32BIT_PHYSICAL_ADDRESS
 #endif
 
 /* acpi_exec configuration. Multithreaded with full AML debugger */
diff --git a/include/asm-generic/seccomp.h b/include/asm-generic/seccomp.h
new file mode 100644
index 00000000000..9fa1f653ed3
--- /dev/null
+++ b/include/asm-generic/seccomp.h
@@ -0,0 +1,30 @@
+/*
+ * include/asm-generic/seccomp.h
+ *
+ * Copyright (C) 2014 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef _ASM_GENERIC_SECCOMP_H
+#define _ASM_GENERIC_SECCOMP_H
+
+#include <linux/unistd.h>
+
+#if defined(CONFIG_COMPAT) && !defined(__NR_seccomp_read_32)
+#define __NR_seccomp_read_32		__NR_read
+#define __NR_seccomp_write_32		__NR_write
+#define __NR_seccomp_exit_32		__NR_exit
+#define __NR_seccomp_sigreturn_32	__NR_rt_sigreturn
+#endif /* CONFIG_COMPAT && ! already defined */
+
+#define __NR_seccomp_read		__NR_read
+#define __NR_seccomp_write		__NR_write
+#define __NR_seccomp_exit		__NR_exit
+#ifndef __NR_seccomp_sigreturn
+#define __NR_seccomp_sigreturn		__NR_rt_sigreturn
+#endif
+
+#endif /* _ASM_GENERIC_SECCOMP_H */
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 5672d7ea1fa..08848050922 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -96,10 +96,9 @@ struct mmu_gather {
 #endif
 	unsigned long		start;
 	unsigned long		end;
-	unsigned int		need_flush : 1,	/* Did free PTEs */
 	/* we are in the middle of an operation to clear
 	 * a full mm and can make some optimizations */
-				fullmm : 1,
+	unsigned int		fullmm : 1,
 	/* we have performed an operation which
 	 * requires a complete flush of the tlb */
 				need_flush_all : 1;
@@ -128,16 +127,54 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 		tlb_flush_mmu(tlb);
 }
 
+static inline void __tlb_adjust_range(struct mmu_gather *tlb,
+				      unsigned long address)
+{
+	tlb->start = min(tlb->start, address);
+	tlb->end = max(tlb->end, address + PAGE_SIZE);
+}
+
+static inline void __tlb_reset_range(struct mmu_gather *tlb)
+{
+	tlb->start = TASK_SIZE;
+	tlb->end = 0;
+}
+
+/*
+ * In the case of tlb vma handling, we can optimise these away in the
+ * case where we're doing a full MM flush.  When we're doing a munmap,
+ * the vmas are adjusted to only cover the region to be torn down.
+ */
+#ifndef tlb_start_vma
+#define tlb_start_vma(tlb, vma) do { } while (0)
+#endif
+
+#define __tlb_end_vma(tlb, vma)					\
+	do {							\
+		if (!tlb->fullmm && tlb->end) {			\
+			tlb_flush(tlb);				\
+			__tlb_reset_range(tlb);			\
+		}						\
+	} while (0)
+
+#ifndef tlb_end_vma
+#define tlb_end_vma	__tlb_end_vma
+#endif
+
+#ifndef __tlb_remove_tlb_entry
+#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
+#endif
+
 /**
  * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
  *
- * Record the fact that pte's were really umapped in ->need_flush, so we can
- * later optimise away the tlb invalidate.   This helps when userspace is
- * unmapping already-unmapped pages, which happens quite a lot.
+ * Record the fact that pte's were really unmapped by updating the range,
+ * so we can later optimise away the tlb invalidate.   This helps when
+ * userspace is unmapping already-unmapped pages, which happens quite a lot.
  */
 #define tlb_remove_tlb_entry(tlb, ptep, address)		\
 	do {							\
-		tlb->need_flush = 1;				\
+		__tlb_adjust_range(tlb, address);		\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
@@ -151,27 +188,27 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 
 #define tlb_remove_pmd_tlb_entry(tlb, pmdp, address)		\
 	do {							\
-		tlb->need_flush = 1;				\
+		__tlb_adjust_range(tlb, address);		\
 		__tlb_remove_pmd_tlb_entry(tlb, pmdp, address);	\
 	} while (0)
 
 #define pte_free_tlb(tlb, ptep, address)			\
 	do {							\
-		tlb->need_flush = 1;				\
+		__tlb_adjust_range(tlb, address);		\
 		__pte_free_tlb(tlb, ptep, address);		\
 	} while (0)
 
 #ifndef __ARCH_HAS_4LEVEL_HACK
 #define pud_free_tlb(tlb, pudp, address)			\
 	do {							\
-		tlb->need_flush = 1;				\
+		__tlb_adjust_range(tlb, address);		\
 		__pud_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
 
 #define pmd_free_tlb(tlb, pmdp, address)			\
 	do {							\
-		tlb->need_flush = 1;				\
+		__tlb_adjust_range(tlb, address);		\
 		__pmd_free_tlb(tlb, pmdp, address);		\
 	} while (0)
 
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 2dd405c9be7..45c39a37f92 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -186,6 +186,7 @@
 	{0x1002, 0x6658, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x665c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x665d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x665f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6660, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6663, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6664, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index a70d4564789..47116c87ab1 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -214,9 +214,9 @@
 	INTEL_VGA_DEVICE((((gt) - 1) << 4) | (id), info)
 
 #define _INTEL_BDW_M_IDS(gt, info) \
-	_INTEL_BDW_M(gt, 0x1602, info), /* ULT */ \
+	_INTEL_BDW_M(gt, 0x1602, info), /* Halo */ \
 	_INTEL_BDW_M(gt, 0x1606, info), /* ULT */ \
-	_INTEL_BDW_M(gt, 0x160B, info), /* Iris */ \
+	_INTEL_BDW_M(gt, 0x160B, info), /* ULT */ \
 	_INTEL_BDW_M(gt, 0x160E, info) /* ULX */
 
 #define _INTEL_BDW_D_IDS(gt, info) \
diff --git a/include/dt-bindings/thermal/thermal.h b/include/dt-bindings/thermal/thermal.h
index 59822a99585..b5e6b0069ac 100644
--- a/include/dt-bindings/thermal/thermal.h
+++ b/include/dt-bindings/thermal/thermal.h
@@ -11,7 +11,7 @@
 #define _DT_BINDINGS_THERMAL_THERMAL_H
 
 /* On cooling devices upper and lower limits */
-#define THERMAL_NO_LIMIT		(-1UL)
+#define THERMAL_NO_LIMIT		(~0)
 
 #endif
 
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index ad9db6045b2..b3f45a57834 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -60,7 +60,8 @@ struct arch_timer_cpu {
 
 #ifdef CONFIG_KVM_ARM_TIMER
 int kvm_timer_hyp_init(void);
-int kvm_timer_init(struct kvm *kvm);
+void kvm_timer_enable(struct kvm *kvm);
+void kvm_timer_init(struct kvm *kvm);
 void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
 			  const struct kvm_irq_level *irq);
 void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
@@ -77,11 +78,8 @@ static inline int kvm_timer_hyp_init(void)
 	return 0;
 };
 
-static inline int kvm_timer_init(struct kvm *kvm)
-{
-	return 0;
-}
-
+static inline void kvm_timer_enable(struct kvm *kvm) {}
+static inline void kvm_timer_init(struct kvm *kvm) {}
 static inline void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
 					const struct kvm_irq_level *irq) {}
 static inline void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) {}
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 206dcc3b3f7..3f73f6c48ad 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -113,6 +113,7 @@ struct vgic_ops {
 	void	(*sync_lr_elrsr)(struct kvm_vcpu *, int, struct vgic_lr);
 	u64	(*get_elrsr)(const struct kvm_vcpu *vcpu);
 	u64	(*get_eisr)(const struct kvm_vcpu *vcpu);
+	void	(*clear_eisr)(struct kvm_vcpu *vcpu);
 	u32	(*get_interrupt_status)(const struct kvm_vcpu *vcpu);
 	void	(*enable_underflow)(struct kvm_vcpu *vcpu);
 	void	(*disable_underflow)(struct kvm_vcpu *vcpu);
@@ -274,7 +275,7 @@ struct kvm_exit_mmio;
 #ifdef CONFIG_KVM_ARM_VGIC
 int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
 int kvm_vgic_hyp_init(void);
-int kvm_vgic_init(struct kvm *kvm);
+int kvm_vgic_map_resources(struct kvm *kvm);
 int kvm_vgic_create(struct kvm *kvm);
 void kvm_vgic_destroy(struct kvm *kvm);
 void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
@@ -321,7 +322,7 @@ static inline int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr,
 	return -ENXIO;
 }
 
-static inline int kvm_vgic_init(struct kvm *kvm)
+static inline int kvm_vgic_map_resources(struct kvm *kvm)
 {
 	return 0;
 }
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
new file mode 100644
index 00000000000..a4608897a5f
--- /dev/null
+++ b/include/linux/Kbuild
@@ -0,0 +1,2 @@
+header-y += if_pppolac.h
+header-y += if_pppopns.h
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 407a12f663e..76d64d6a903 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -28,6 +28,7 @@
 #include <linux/errno.h>
 #include <linux/ioport.h>	/* for struct resource */
 #include <linux/device.h>
+#include <linux/property.h>
 
 #ifndef _LINUX
 #define _LINUX
@@ -659,4 +660,75 @@ do {									\
 #endif
 #endif
 
+/* Device properties */
+
+#define MAX_ACPI_REFERENCE_ARGS	8
+struct acpi_reference_args {
+	struct acpi_device *adev;
+	size_t nargs;
+	u64 args[MAX_ACPI_REFERENCE_ARGS];
+};
+
+#ifdef CONFIG_ACPI
+int acpi_dev_get_property(struct acpi_device *adev, const char *name,
+			  acpi_object_type type, const union acpi_object **obj);
+int acpi_dev_get_property_array(struct acpi_device *adev, const char *name,
+				acpi_object_type type,
+				const union acpi_object **obj);
+int acpi_dev_get_property_reference(struct acpi_device *adev, const char *name,
+				    const char *cells_name, size_t index,
+				    struct acpi_reference_args *args);
+
+int acpi_dev_prop_get(struct acpi_device *adev, const char *propname,
+		      void **valptr);
+int acpi_dev_prop_read_single(struct acpi_device *adev, const char *propname,
+			      enum dev_prop_type proptype, void *val);
+int acpi_dev_prop_read(struct acpi_device *adev, const char *propname,
+		       enum dev_prop_type proptype, void *val, size_t nval);
+#else
+static inline int acpi_dev_get_property(struct acpi_device *adev,
+					const char *name, acpi_object_type type,
+					const union acpi_object **obj)
+{
+	return -ENXIO;
+}
+static inline int acpi_dev_get_property_array(struct acpi_device *adev,
+					      const char *name,
+					      acpi_object_type type,
+					      const union acpi_object **obj)
+{
+	return -ENXIO;
+}
+static inline int acpi_dev_get_property_reference(struct acpi_device *adev,
+				const char *name, const char *cells_name,
+				size_t index, struct acpi_reference_args *args)
+{
+	return -ENXIO;
+}
+
+static inline int acpi_dev_prop_get(struct acpi_device *adev,
+				    const char *propname,
+				    void **valptr)
+{
+	return -ENXIO;
+}
+
+static inline int acpi_dev_prop_read_single(struct acpi_device *adev,
+					    const char *propname,
+					    enum dev_prop_type proptype,
+					    void *val)
+{
+	return -ENXIO;
+}
+
+static inline int acpi_dev_prop_read(struct acpi_device *adev,
+				     const char *propname,
+				     enum dev_prop_type proptype,
+				     void *val, size_t nval)
+{
+	return -ENXIO;
+}
+
+#endif
+
 #endif	/*_LINUX_ACPI_H*/
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index c324f5700d1..d024bd9c9d9 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -23,6 +23,7 @@
 
 #define AMBA_NR_IRQS	9
 #define AMBA_CID	0xb105f00d
+#define CORESIGHT_CID	0xb105900d
 
 struct clk;
 
diff --git a/include/linux/amba/mmci.h b/include/linux/amba/mmci.h
index 8c98113069c..8bfd21c13d5 100644
--- a/include/linux/amba/mmci.h
+++ b/include/linux/amba/mmci.h
@@ -5,6 +5,15 @@
 #define AMBA_MMCI_H
 
 #include <linux/mmc/host.h>
+#include <linux/mmc/card.h>
+#include <linux/mmc/sdio_func.h>
+
+struct embedded_sdio_data {
+        struct sdio_cis cis;
+        struct sdio_cccr cccr;
+        struct sdio_embedded_func *funcs;
+        int num_funcs;
+};
 
 /**
  * struct mmci_platform_data - platform configuration for the MMCI
@@ -31,6 +40,10 @@ struct mmci_platform_data {
 	int	gpio_wp;
 	int	gpio_cd;
 	bool	cd_invert;
+	unsigned int status_irq;
+	struct embedded_sdio_data *embedded_sdio;
+	int (*register_status_notify)(void (*callback)(int card_present, void *dev_id), void *dev_id);
+
 };
 
 #endif
diff --git a/include/linux/android_aid.h b/include/linux/android_aid.h
new file mode 100644
index 00000000000..6f1fa1792df
--- /dev/null
+++ b/include/linux/android_aid.h
@@ -0,0 +1,28 @@
+/* include/linux/android_aid.h
+ *
+ * Copyright (C) 2008 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_ANDROID_AID_H
+#define _LINUX_ANDROID_AID_H
+
+/* AIDs that the kernel treats differently */
+#define AID_OBSOLETE_000 KGIDT_INIT(3001)  /* was NET_BT_ADMIN */
+#define AID_OBSOLETE_001 KGIDT_INIT(3002)  /* was NET_BT */
+#define AID_INET         KGIDT_INIT(3003)
+#define AID_NET_RAW      KGIDT_INIT(3004)
+#define AID_NET_ADMIN    KGIDT_INIT(3005)
+#define AID_NET_BW_STATS KGIDT_INIT(3006)  /* read bandwidth statistics */
+#define AID_NET_BW_ACCT  KGIDT_INIT(3007)  /* change bandwidth statistics accounting */
+
+#endif
diff --git a/include/linux/audit.h b/include/linux/audit.h
index e58fe7df8b9..10f155b7daf 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -47,6 +47,7 @@ struct sk_buff;
 
 struct audit_krule {
 	int			vers_ops;
+	u32			pflags;
 	u32			flags;
 	u32			listnr;
 	u32			action;
@@ -64,6 +65,9 @@ struct audit_krule {
 	u64			prio;
 };
 
+/* Flag to indicate legacy AUDIT_LOGINUID unset usage */
+#define AUDIT_LOGINUID_LEGACY		0x1
+
 struct audit_field {
 	u32				type;
 	union {
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 445d59231bc..c50182a4a94 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -181,7 +181,9 @@ enum rq_flag_bits {
 	__REQ_ELVPRIV,		/* elevator private data attached */
 	__REQ_FAILED,		/* set if the request failed */
 	__REQ_QUIET,		/* don't worry about errors */
-	__REQ_PREEMPT,		/* set for "ide_preempt" requests */
+	__REQ_PREEMPT,		/* set for "ide_preempt" requests and also
+				   for requests for which the SCSI "quiesce"
+				   state must be ignored. */
 	__REQ_ALLOCED,		/* request came from our alloc pool */
 	__REQ_COPY_USER,	/* contains copies of user pages */
 	__REQ_FLUSH_SEQ,	/* request for flush sequence */
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3cf91754a95..cb4156a2c6b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -48,7 +48,7 @@ struct bpf_map *bpf_map_get(struct fd f);
 
 /* function argument constraints */
 enum bpf_arg_type {
-	ARG_ANYTHING = 0,	/* any argument is ok */
+	ARG_DONTCARE = 0,	/* unused argument in helper function */
 
 	/* the following constraints used to prototype
 	 * bpf_map_lookup/update/delete_elem() functions
@@ -62,6 +62,8 @@ enum bpf_arg_type {
 	 */
 	ARG_PTR_TO_STACK,	/* any pointer to eBPF program stack */
 	ARG_CONST_STACK_SIZE,	/* number of bytes accessed from stack */
+
+	ARG_ANYTHING,		/* any (initialized) argument is ok */
 };
 
 /* type of values returned from helper functions */
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 1d519688904..cbc8db1c1c0 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -615,6 +615,8 @@ struct cgroup_subsys {
 	void (*css_free)(struct cgroup_subsys_state *css);
 	void (*css_reset)(struct cgroup_subsys_state *css);
 
+	int (*allow_attach)(struct cgroup_subsys_state *css,
+			    struct cgroup_taskset *tset);
 	int (*can_attach)(struct cgroup_subsys_state *css,
 			  struct cgroup_taskset *tset);
 	void (*cancel_attach)(struct cgroup_subsys_state *css,
@@ -911,6 +913,17 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
 struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
 						       struct cgroup_subsys *ss);
 
+/*
+ * Default Android check for whether the current process is allowed to move a
+ * task across cgroups, either because CAP_SYS_NICE is set or because the uid
+ * of the calling process is the same as the moved task or because we are
+ * running as root.
+ * Returns 0 if this is allowed, or -EACCES otherwise.
+ */
+int subsys_cgroup_allow_attach(struct cgroup_subsys_state *css,
+			       struct cgroup_taskset *tset);
+
+
 #else /* !CONFIG_CGROUPS */
 
 static inline int cgroup_init_early(void) { return 0; }
@@ -932,6 +945,11 @@ static inline int cgroup_attach_task_all(struct task_struct *from,
 	return 0;
 }
 
+static inline int subsys_cgroup_allow_attach(struct cgroup_subsys_state *css,
+					     void *tset)
+{
+	return -EINVAL;
+}
 #endif /* !CONFIG_CGROUPS */
 
 #endif /* _LINUX_CGROUP_H */
diff --git a/include/linux/clk-private.h b/include/linux/clk-private.h
index 0ca5f604692..228a98724b1 100644
--- a/include/linux/clk-private.h
+++ b/include/linux/clk-private.h
@@ -13,7 +13,9 @@
 
 #include <linux/clk-provider.h>
 #include <linux/kref.h>
+#include <linux/ktime.h>
 #include <linux/list.h>
+#include <linux/rbtree.h>
 
 /*
  * WARNING: Do not include clk-private.h from any file that implements struct
@@ -28,6 +30,14 @@
 
 struct module;
 
+#ifdef CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING
+struct freq_stats {
+	ktime_t time_spent;
+	unsigned long rate;
+	struct rb_node node;
+};
+#endif /*CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING*/
+
 struct clk {
 	const char		*name;
 	const struct clk_ops	*ops;
@@ -53,6 +63,13 @@ struct clk {
 	unsigned int		notifier_count;
 #ifdef CONFIG_DEBUG_FS
 	struct dentry		*dentry;
+#ifdef CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING
+	struct rb_root freq_stats_table;
+	struct freq_stats *current_freq_stats;
+	ktime_t default_freq_time;
+	ktime_t start_time;
+#endif /* CONFIG_COMMON_CLK_FREQ_STATS_ACCOUNTING*/
+
 #endif
 	struct kref		ref;
 };
diff --git a/include/linux/clock_cooling.h b/include/linux/clock_cooling.h
new file mode 100644
index 00000000000..4d1019d56f7
--- /dev/null
+++ b/include/linux/clock_cooling.h
@@ -0,0 +1,65 @@
+/*
+ *  linux/include/linux/clock_cooling.h
+ *
+ *  Copyright (C) 2014 Eduardo Valentin <edubezval@gmail.com>
+ *
+ *  Copyright (C) 2013	Texas Instruments Inc.
+ *  Contact:  Eduardo Valentin <eduardo.valentin@ti.com>
+ *
+ *  Highly based on cpu_cooling.c.
+ *  Copyright (C) 2012	Samsung Electronics Co., Ltd(http://www.samsung.com)
+ *  Copyright (C) 2012  Amit Daniel <amit.kachhap@linaro.org>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ */
+
+#ifndef __CPU_COOLING_H__
+#define __CPU_COOLING_H__
+
+#include <linux/of.h>
+#include <linux/thermal.h>
+#include <linux/cpumask.h>
+
+#ifdef CONFIG_CLOCK_THERMAL
+/**
+ * clock_cooling_register - function to create clock cooling device.
+ * @dev: struct device pointer to the device used as clock cooling device.
+ * @clock_name: string containing the clock used as cooling mechanism.
+ */
+struct thermal_cooling_device *
+clock_cooling_register(struct device *dev, const char *clock_name);
+
+/**
+ * clock_cooling_unregister - function to remove clock cooling device.
+ * @cdev: thermal cooling device pointer.
+ */
+void clock_cooling_unregister(struct thermal_cooling_device *cdev);
+
+unsigned long clock_cooling_get_level(struct thermal_cooling_device *cdev,
+				      unsigned long freq);
+#else /* !CONFIG_CLOCK_THERMAL */
+static inline struct thermal_cooling_device *
+clock_cooling_register(struct device *dev, const char *clock_name)
+{
+	return NULL;
+}
+static inline
+void clock_cooling_unregister(struct thermal_cooling_device *cdev)
+{
+}
+static inline
+unsigned long clock_cooling_get_level(struct thermal_cooling_device *cdev,
+				      unsigned long freq)
+{
+	return THERMAL_CSTATE_INVALID;
+}
+#endif	/* CONFIG_CLOCK_THERMAL */
+
+#endif /* __CPU_COOLING_H__ */
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index d5ad7b1118f..000c5f90f08 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -186,6 +186,80 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 # define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__)
 #endif
 
+#include <uapi/linux/types.h>
+
+static __always_inline void data_access_exceeds_word_size(void)
+#ifdef __compiletime_warning
+__compiletime_warning("data access exceeds word size and won't be atomic")
+#endif
+;
+
+static __always_inline void data_access_exceeds_word_size(void)
+{
+}
+
+static __always_inline void __read_once_size(const volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(__u8 *)res = *(volatile __u8 *)p; break;
+	case 2: *(__u16 *)res = *(volatile __u16 *)p; break;
+	case 4: *(__u32 *)res = *(volatile __u32 *)p; break;
+#ifdef CONFIG_64BIT
+	case 8: *(__u64 *)res = *(volatile __u64 *)p; break;
+#endif
+	default:
+		barrier();
+		__builtin_memcpy((void *)res, (const void *)p, size);
+		data_access_exceeds_word_size();
+		barrier();
+	}
+}
+
+static __always_inline void __write_once_size(volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(volatile __u8 *)p = *(__u8 *)res; break;
+	case 2: *(volatile __u16 *)p = *(__u16 *)res; break;
+	case 4: *(volatile __u32 *)p = *(__u32 *)res; break;
+#ifdef CONFIG_64BIT
+	case 8: *(volatile __u64 *)p = *(__u64 *)res; break;
+#endif
+	default:
+		barrier();
+		__builtin_memcpy((void *)p, (const void *)res, size);
+		data_access_exceeds_word_size();
+		barrier();
+	}
+}
+
+/*
+ * Prevent the compiler from merging or refetching reads or writes. The
+ * compiler is also forbidden from reordering successive instances of
+ * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the
+ * compiler is aware of some particular ordering.  One way to make the
+ * compiler aware of ordering is to put the two invocations of READ_ONCE,
+ * WRITE_ONCE or ACCESS_ONCE() in different C statements.
+ *
+ * In contrast to ACCESS_ONCE these two macros will also work on aggregate
+ * data types like structs or unions. If the size of the accessed data
+ * type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
+ * READ_ONCE() and WRITE_ONCE()  will fall back to memcpy and print a
+ * compile-time warning.
+ *
+ * Their two major use cases are: (1) Mediating communication between
+ * process-level code and irq/NMI handlers, all running on the same CPU,
+ * and (2) Ensuring that the compiler does not  fold, spindle, or otherwise
+ * mutilate accesses that either do not require ordering or that interact
+ * with an explicit memory barrier or atomic instruction that provides the
+ * required ordering.
+ */
+
+#define READ_ONCE(x) \
+	({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+
+#define WRITE_ONCE(x, val) \
+	({ typeof(x) __val = (val); __write_once_size(&(x), &__val, sizeof(__val)); __val; })
+
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
new file mode 100644
index 00000000000..44c1597a738
--- /dev/null
+++ b/include/linux/coresight.h
@@ -0,0 +1,251 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _LINUX_CORESIGHT_H
+#define _LINUX_CORESIGHT_H
+
+#include <linux/device.h>
+
+/* Peripheral id registers (0xFD0-0xFEC) */
+#define CORESIGHT_PERIPHIDR4	0xfd0
+#define CORESIGHT_PERIPHIDR5	0xfd4
+#define CORESIGHT_PERIPHIDR6	0xfd8
+#define CORESIGHT_PERIPHIDR7	0xfdC
+#define CORESIGHT_PERIPHIDR0	0xfe0
+#define CORESIGHT_PERIPHIDR1	0xfe4
+#define CORESIGHT_PERIPHIDR2	0xfe8
+#define CORESIGHT_PERIPHIDR3	0xfeC
+/* Component id registers (0xFF0-0xFFC) */
+#define CORESIGHT_COMPIDR0	0xff0
+#define CORESIGHT_COMPIDR1	0xff4
+#define CORESIGHT_COMPIDR2	0xff8
+#define CORESIGHT_COMPIDR3	0xffC
+
+#define ETM_ARCH_V3_3		0x23
+#define ETM_ARCH_V3_5		0x25
+#define PFT_ARCH_V1_0		0x30
+#define PFT_ARCH_V1_1		0x31
+
+#define CORESIGHT_UNLOCK	0xc5acce55
+
+extern struct bus_type coresight_bustype;
+
+enum coresight_dev_type {
+	CORESIGHT_DEV_TYPE_NONE,
+	CORESIGHT_DEV_TYPE_SINK,
+	CORESIGHT_DEV_TYPE_LINK,
+	CORESIGHT_DEV_TYPE_LINKSINK,
+	CORESIGHT_DEV_TYPE_SOURCE,
+};
+
+enum coresight_dev_subtype_sink {
+	CORESIGHT_DEV_SUBTYPE_SINK_NONE,
+	CORESIGHT_DEV_SUBTYPE_SINK_PORT,
+	CORESIGHT_DEV_SUBTYPE_SINK_BUFFER,
+};
+
+enum coresight_dev_subtype_link {
+	CORESIGHT_DEV_SUBTYPE_LINK_NONE,
+	CORESIGHT_DEV_SUBTYPE_LINK_MERG,
+	CORESIGHT_DEV_SUBTYPE_LINK_SPLIT,
+	CORESIGHT_DEV_SUBTYPE_LINK_FIFO,
+};
+
+enum coresight_dev_subtype_source {
+	CORESIGHT_DEV_SUBTYPE_SOURCE_NONE,
+	CORESIGHT_DEV_SUBTYPE_SOURCE_PROC,
+	CORESIGHT_DEV_SUBTYPE_SOURCE_BUS,
+	CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE,
+};
+
+/**
+ * struct coresight_dev_subtype - further characterisation of a type
+ * @sink_subtype:	type of sink this component is, as defined
+			by @coresight_dev_subtype_sink.
+ * @link_subtype:	type of link this component is, as defined
+			by @coresight_dev_subtype_link.
+ * @source_subtype:	type of source this component is, as defined
+			by @coresight_dev_subtype_source.
+ */
+struct coresight_dev_subtype {
+	enum coresight_dev_subtype_sink sink_subtype;
+	enum coresight_dev_subtype_link link_subtype;
+	enum coresight_dev_subtype_source source_subtype;
+};
+
+/**
+ * struct coresight_platform_data - data harvested from the DT specification
+ * @cpu:	the CPU a source belongs to. Only applicable for ETM/PTMs.
+ * @name:	name of the component as shown under sysfs.
+ * @nr_inport:	number of input ports for this component.
+ * @outports:	list of remote enpoint port number.
+ * @child_names:name of all child components connected to this device.
+ * @child_ports:child component port number the current component is
+		connected  to.
+ * @nr_outport:	number of output ports for this component.
+ * @clk:	The clock this component is associated to.
+ */
+struct coresight_platform_data {
+	int cpu;
+	const char *name;
+	int nr_inport;
+	int *outports;
+	const char **child_names;
+	int *child_ports;
+	int nr_outport;
+	struct clk *clk;
+};
+
+/**
+ * struct coresight_desc - description of a component required from drivers
+ * @type:	as defined by @coresight_dev_type.
+ * @subtype:	as defined by @coresight_dev_subtype.
+ * @ops:	generic operations for this component, as defined
+		by @coresight_ops.
+ * @pdata:	platform data collected from DT.
+ * @dev:	The device entity associated to this component.
+ * @groups	:operations specific to this component. These will end up
+		in the component's sysfs sub-directory.
+ */
+struct coresight_desc {
+	enum coresight_dev_type type;
+	struct coresight_dev_subtype subtype;
+	const struct coresight_ops *ops;
+	struct coresight_platform_data *pdata;
+	struct device *dev;
+	const struct attribute_group **groups;
+};
+
+/**
+ * struct coresight_connection - representation of a single connection
+ * @ref_count:	keeping count a port' references.
+ * @outport:	a connection's output port number.
+ * @chid_name:	remote component's name.
+ * @child_port:	remote component's port number @output is connected to.
+ * @child_dev:	a @coresight_device representation of the component
+		connected to @outport.
+ */
+struct coresight_connection {
+	int outport;
+	const char *child_name;
+	int child_port;
+	struct coresight_device *child_dev;
+};
+
+/**
+ * struct coresight_device - representation of a device as used by the framework
+ * @nr_inport:	number of input port associated to this component.
+ * @nr_outport:	number of output port associated to this component.
+ * @type:	as defined by @coresight_dev_type.
+ * @subtype:	as defined by @coresight_dev_subtype.
+ * @ops:	generic operations for this component, as defined
+		by @coresight_ops.
+ * @dev:	The device entity associated to this component.
+ * @refcnt:	keep track of what is in use.
+ * @path_link:	link of current component into the path being enabled.
+ * @orphan:	true if the component has connections that haven't been linked.
+ * @enable:	'true' if component is currently part of an active path.
+ * @activated:	'true' only if a _sink_ has been activated.  A sink can be
+		activated but not yet enabled.  Enabling for a _sink_
+		happens when a source has been selected for that it.
+ */
+struct coresight_device {
+	struct coresight_connection *conns;
+	int nr_inport;
+	int nr_outport;
+	enum coresight_dev_type type;
+	struct coresight_dev_subtype subtype;
+	const struct coresight_ops *ops;
+	struct device dev;
+	atomic_t *refcnt;
+	struct list_head path_link;
+	bool orphan;
+	bool enable;	/* true only if configured as part of a path */
+	bool activated;	/* true only if a sink is part of a path */
+};
+
+#define to_coresight_device(d) container_of(d, struct coresight_device, dev)
+
+#define source_ops(csdev)	csdev->ops->source_ops
+#define sink_ops(csdev)		csdev->ops->sink_ops
+#define link_ops(csdev)		csdev->ops->link_ops
+
+/**
+ * struct coresight_ops_sink - basic operations for a sink
+ * Operations available for sinks
+ * @enable:	enables the sink.
+ * @disable:	disables the sink.
+ */
+struct coresight_ops_sink {
+	int (*enable)(struct coresight_device *csdev);
+	void (*disable)(struct coresight_device *csdev);
+};
+
+/**
+ * struct coresight_ops_link - basic operations for a link
+ * Operations available for links.
+ * @enable:	enables flow between iport and oport.
+ * @disable:	disables flow between iport and oport.
+ */
+struct coresight_ops_link {
+	int (*enable)(struct coresight_device *csdev, int iport, int oport);
+	void (*disable)(struct coresight_device *csdev, int iport, int oport);
+};
+
+/**
+ * struct coresight_ops_source - basic operations for a source
+ * Operations available for sources.
+ * @trace_id:	returns the value of the component's trace ID as known
+		to the HW.
+ * @enable:	enables tracing from a source.
+ * @disable:	disables tracing for a source.
+ */
+struct coresight_ops_source {
+	int (*trace_id)(struct coresight_device *csdev);
+	int (*enable)(struct coresight_device *csdev);
+	void (*disable)(struct coresight_device *csdev);
+};
+
+struct coresight_ops {
+	const struct coresight_ops_sink *sink_ops;
+	const struct coresight_ops_link *link_ops;
+	const struct coresight_ops_source *source_ops;
+};
+
+#ifdef CONFIG_CORESIGHT
+extern struct coresight_device *
+coresight_register(struct coresight_desc *desc);
+extern void coresight_unregister(struct coresight_device *csdev);
+extern int coresight_enable(struct coresight_device *csdev);
+extern void coresight_disable(struct coresight_device *csdev);
+extern int coresight_timeout(void __iomem *addr, u32 offset,
+			     int position, int value);
+#else
+static inline struct coresight_device *
+coresight_register(struct coresight_desc *desc) { return NULL; }
+static inline void coresight_unregister(struct coresight_device *csdev) {}
+static inline int
+coresight_enable(struct coresight_device *csdev) { return -ENOSYS; }
+static inline void coresight_disable(struct coresight_device *csdev) {}
+static inline int coresight_timeout(void __iomem *addr, u32 offset,
+				     int position, int value) { return 1; }
+#endif
+
+#ifdef CONFIG_OF
+extern struct coresight_platform_data *of_get_coresight_platform_data(
+				struct device *dev, struct device_node *node);
+#else
+static inline struct coresight_platform_data *of_get_coresight_platform_data(
+	struct device *dev, struct device_node *node) { return NULL; }
+#endif
+
+#endif
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index b2d9a43012b..10d981a245d 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -267,4 +267,11 @@ void arch_cpu_idle_enter(void);
 void arch_cpu_idle_exit(void);
 void arch_cpu_idle_dead(void);
 
+#define IDLE_START 1
+#define IDLE_END 2
+
+void idle_notifier_register(struct notifier_block *n);
+void idle_notifier_unregister(struct notifier_block *n);
+void idle_notifier_call_chain(unsigned long val);
+
 #endif /* _LINUX_CPU_H_ */
diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h
index c303d383def..8ac03318241 100644
--- a/include/linux/cpu_cooling.h
+++ b/include/linux/cpu_cooling.h
@@ -28,6 +28,9 @@
 #include <linux/thermal.h>
 #include <linux/cpumask.h>
 
+typedef int (*get_static_t)(cpumask_t *cpumask, int interval,
+			    unsigned long voltage, u32 *power);
+
 #ifdef CONFIG_CPU_THERMAL
 /**
  * cpufreq_cooling_register - function to create cpufreq cooling device.
@@ -36,6 +39,10 @@
 struct thermal_cooling_device *
 cpufreq_cooling_register(const struct cpumask *clip_cpus);
 
+struct thermal_cooling_device *
+cpufreq_power_cooling_register(const struct cpumask *clip_cpus,
+			       u32 capacitance, get_static_t plat_static_func);
+
 /**
  * of_cpufreq_cooling_register - create cpufreq cooling device based on DT.
  * @np: a valid struct device_node to the cooling device device tree node.
@@ -45,6 +52,12 @@ cpufreq_cooling_register(const struct cpumask *clip_cpus);
 struct thermal_cooling_device *
 of_cpufreq_cooling_register(struct device_node *np,
 			    const struct cpumask *clip_cpus);
+
+struct thermal_cooling_device *
+of_cpufreq_power_cooling_register(struct device_node *np,
+				  const struct cpumask *clip_cpus,
+				  u32 capacitance,
+				  get_static_t plat_static_func);
 #else
 static inline struct thermal_cooling_device *
 of_cpufreq_cooling_register(struct device_node *np,
@@ -52,6 +65,15 @@ of_cpufreq_cooling_register(struct device_node *np,
 {
 	return NULL;
 }
+
+static inline struct thermal_cooling_device *
+of_cpufreq_power_cooling_register(struct device_node *np,
+				  const struct cpumask *clip_cpus,
+				  u32 capacitance,
+				  get_static_t plat_static_func)
+{
+	return NULL;
+}
 #endif
 
 /**
@@ -68,11 +90,28 @@ cpufreq_cooling_register(const struct cpumask *clip_cpus)
 	return NULL;
 }
 static inline struct thermal_cooling_device *
+cpufreq_power_cooling_register(const struct cpumask *clip_cpus,
+			       u32 capacitance, get_static_t plat_static_func)
+{
+	return NULL;
+}
+
+static inline struct thermal_cooling_device *
 of_cpufreq_cooling_register(struct device_node *np,
 			    const struct cpumask *clip_cpus)
 {
 	return NULL;
 }
+
+static inline struct thermal_cooling_device *
+of_cpufreq_power_cooling_register(struct device_node *np,
+				  const struct cpumask *clip_cpus,
+				  u32 capacitance,
+				  get_static_t plat_static_func)
+{
+	return NULL;
+}
+
 static inline
 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 {
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 503b085b783..56ea8a33601 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -18,6 +18,8 @@
 #include <linux/notifier.h>
 #include <linux/spinlock.h>
 #include <linux/sysfs.h>
+#include <asm/cputime.h>
+
 
 /*********************************************************************
  *                        CPUFREQ INTERFACE                          *
@@ -481,6 +483,9 @@ extern struct cpufreq_governor cpufreq_gov_ondemand;
 #elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE)
 extern struct cpufreq_governor cpufreq_gov_conservative;
 #define CPUFREQ_DEFAULT_GOVERNOR	(&cpufreq_gov_conservative)
+#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE)
+extern struct cpufreq_governor cpufreq_gov_interactive;
+#define CPUFREQ_DEFAULT_GOVERNOR	(&cpufreq_gov_interactive)
 #endif
 
 /*********************************************************************
@@ -597,4 +602,11 @@ unsigned int cpufreq_generic_get(unsigned int cpu);
 int cpufreq_generic_init(struct cpufreq_policy *policy,
 		struct cpufreq_frequency_table *table,
 		unsigned int transition_latency);
+
+/*********************************************************************
+ *                         CPUFREQ STATS                             *
+ *********************************************************************/
+
+void acct_update_power(struct task_struct *p, cputime_t cputime);
+
 #endif /* _LINUX_CPUFREQ_H */
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 25e0df6155a..575b7166cb0 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -69,7 +69,6 @@ struct cpuidle_device {
 	unsigned int		cpu;
 
 	int			last_residency;
-	int			state_count;
 	struct cpuidle_state_usage	states_usage[CPUIDLE_STATE_MAX];
 	struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX];
 	struct cpuidle_driver_kobj *kobj_driver;
diff --git a/include/linux/cred.h b/include/linux/cred.h
index b2d0820837c..2fb2ca2127e 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -68,6 +68,7 @@ extern void groups_free(struct group_info *);
 extern int set_current_groups(struct group_info *);
 extern void set_groups(struct cred *, struct group_info *);
 extern int groups_search(const struct group_info *, kgid_t);
+extern bool may_setgroups(void);
 
 /* access the groups "array" with this macro */
 #define GROUP_AT(gi, i) \
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index d45e949699e..dc34dfc766b 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -26,6 +26,19 @@
 #include <linux/uaccess.h>
 
 /*
+ * Autoloaded crypto modules should only use a prefixed name to avoid allowing
+ * arbitrary modules to be loaded. Loading from userspace may still need the
+ * unprefixed names, so retains those aliases as well.
+ * This uses __MODULE_INFO directly instead of MODULE_ALIAS because pre-4.3
+ * gcc (e.g. avr32 toolchain) uses __LINE__ for uniqueness, and this macro
+ * expands twice on the same line. Instead, use a separate base name for the
+ * alias.
+ */
+#define MODULE_ALIAS_CRYPTO(name)	\
+		__MODULE_INFO(alias, alias_userspace, name);	\
+		__MODULE_INFO(alias, alias_crypto, "crypto-" name)
+
+/*
  * Algorithm masks and types.
  */
 #define CRYPTO_ALG_TYPE_MASK		0x0000000f
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index b2a2a08523b..1c2f1b84468 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -124,15 +124,15 @@ struct dentry {
 	void *d_fsdata;			/* fs-specific data */
 
 	struct list_head d_lru;		/* LRU list */
+	struct list_head d_child;	/* child of parent list */
+	struct list_head d_subdirs;	/* our children */
 	/*
-	 * d_child and d_rcu can share memory
+	 * d_alias and d_rcu can share memory
 	 */
 	union {
-		struct list_head d_child;	/* child of parent list */
+		struct hlist_node d_alias;	/* inode alias list */
 	 	struct rcu_head d_rcu;
 	} d_u;
-	struct list_head d_subdirs;	/* our children */
-	struct hlist_node d_alias;	/* inode alias list */
 };
 
 /*
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index f1863dcd83e..a2f4a834b88 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -161,6 +161,7 @@ struct devfreq {
 	struct delayed_work work;
 
 	unsigned long previous_freq;
+	struct devfreq_dev_status last_status;
 
 	void *data; /* private data for governors */
 
@@ -204,6 +205,8 @@ extern int devm_devfreq_register_opp_notifier(struct device *dev,
 extern void devm_devfreq_unregister_opp_notifier(struct device *dev,
 						struct devfreq *devfreq);
 
+int devfreq_update_stats(struct devfreq *df);
+
 #if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND)
 /**
  * struct devfreq_simple_ondemand_data - void *data fed to struct devfreq
@@ -289,6 +292,11 @@ static inline void devm_devfreq_unregister_opp_notifier(struct device *dev,
 							struct devfreq *devfreq)
 {
 }
+
+static inline int devfreq_update_stats(struct devfreq *df)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_PM_DEVFREQ */
 
 #endif /* __LINUX_DEVFREQ_H__ */
diff --git a/include/linux/devfreq_cooling.h b/include/linux/devfreq_cooling.h
new file mode 100644
index 00000000000..8e7346ebbeb
--- /dev/null
+++ b/include/linux/devfreq_cooling.h
@@ -0,0 +1,93 @@
+/*
+ * devfreq_cooling: Thermal cooling device implementation for devices using
+ *                  devfreq
+ *
+ * Copyright (C) 2014 ARM Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DEVFREQ_COOLING_H__
+#define __DEVFREQ_COOLING_H__
+
+#include <linux/devfreq.h>
+#include <linux/thermal.h>
+
+#ifdef CONFIG_DEVFREQ_THERMAL
+
+/**
+ * struct devfreq_cooling_ops - Devfreq cooling power ops
+ * @get_static_power: Take voltage, in mV, and return the static power in mW.
+ * @get_dynamic_power: Take voltage, in mV, and frequency, in HZ, and return
+ * the dynamic power draw in mW.
+ */
+struct devfreq_cooling_ops {
+	unsigned long (*get_static_power)(unsigned long voltage);
+	unsigned long (*get_dynamic_power)(unsigned long freq,
+					   unsigned long voltage);
+};
+
+/**
+ * struct devfreq_cooling_device - Devfreq cooling device
+ * @id:            unique integer value corresponding to each
+ *                 devfreq_cooling_device registered.
+ * @cdev:          Pointer to associated thermal cooling device.
+ * @devfreq:       Pointer to associated devfreq device.
+ * @cooling_state: Current cooling state.
+ * @power_table:   Pointer to table with maximum power draw for each cooling
+ *                 state. State is the index into the table, and the power is
+ *                 stated in mW.
+ * @power_ops:     Pointer to power operations, used to generate @power_table.
+ */
+struct devfreq_cooling_device {
+	int id;
+	struct thermal_cooling_device *cdev;
+	struct devfreq *devfreq;
+	unsigned long cooling_state;
+	u32 *power_table;
+	struct devfreq_cooling_ops *power_ops;
+};
+
+struct devfreq_cooling_device *
+of_devfreq_cooling_register_power(struct device_node *np, struct devfreq *df,
+				  struct devfreq_cooling_ops *ops);
+struct devfreq_cooling_device *
+of_devfreq_cooling_register(struct device_node *np, struct devfreq *df);
+struct devfreq_cooling_device *devfreq_cooling_register(struct devfreq *df);
+void devfreq_cooling_unregister(struct devfreq_cooling_device *dfc);
+
+#else /* !CONFIG_DEVFREQ_THERMAL */
+
+struct devfreq_cooling_device *
+of_devfreq_cooling_register_power(struct device_node *np, struct devfreq *df,
+				  struct devfreq_cooling_ops *ops)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline struct devfreq_cooling_device *
+of_devfreq_cooling_register(struct device_node *np, struct devfreq *df)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline struct devfreq_cooling_device *
+devfreq_cooling_register(struct devfreq *df)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline void
+devfreq_cooling_unregister(struct devfreq_cooling_device *dfc)
+{
+}
+
+#endif /* CONFIG_DEVFREQ_THERMAL */
+#endif /* __DEVFREQ_COOLING_H__ */
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index e1707de043a..c51706b7a36 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -366,6 +366,7 @@ int dm_create(int minor, struct mapped_device **md);
  */
 struct mapped_device *dm_get_md(dev_t dev);
 void dm_get(struct mapped_device *md);
+int dm_hold(struct mapped_device *md);
 void dm_put(struct mapped_device *md);
 
 /*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9ab779e8a63..84d672914bd 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1791,6 +1791,7 @@ struct file_system_type {
 #define FS_HAS_SUBTYPE		4
 #define FS_USERNS_MOUNT		8	/* Can be mounted by userns root */
 #define FS_USERNS_DEV_MOUNT	16 /* A userns mount does not imply MNT_NODEV */
+#define FS_USERNS_VISIBLE	32	/* FS must already be visible */
 #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
 	struct dentry *(*mount) (struct file_system_type *, int,
 		       const char *, void *);
@@ -1878,7 +1879,6 @@ extern int vfs_ustat(dev_t, struct kstatfs *);
 extern int freeze_super(struct super_block *super);
 extern int thaw_super(struct super_block *super);
 extern bool our_mnt(struct vfsmount *mnt);
-extern bool fs_fully_visible(struct file_system_type *);
 
 extern int current_umask(void);
 
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 1c804b057fb..7ee1774edee 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -101,8 +101,10 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
 		new_dir_mask |= FS_ISDIR;
 	}
 
-	fsnotify(old_dir, old_dir_mask, old_dir, FSNOTIFY_EVENT_INODE, old_name, fs_cookie);
-	fsnotify(new_dir, new_dir_mask, new_dir, FSNOTIFY_EVENT_INODE, new_name, fs_cookie);
+	fsnotify(old_dir, old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_name,
+		 fs_cookie);
+	fsnotify(new_dir, new_dir_mask, source, FSNOTIFY_EVENT_INODE, new_name,
+		 fs_cookie);
 
 	if (target)
 		fsnotify_link_count(target);
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 28672e87e91..cac1e8069fa 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -44,6 +44,10 @@ const char *ftrace_print_bitmask_seq(struct trace_seq *p, void *bitmask_ptr,
 const char *ftrace_print_hex_seq(struct trace_seq *p,
 				 const unsigned char *buf, int len);
 
+const char *ftrace_print_array_seq(struct trace_seq *p,
+				   const void *buf, int buf_len,
+				   size_t el_size);
+
 struct trace_iterator;
 struct trace_event;
 
diff --git a/include/linux/gpio_event.h b/include/linux/gpio_event.h
new file mode 100644
index 00000000000..2613fc5e4a9
--- /dev/null
+++ b/include/linux/gpio_event.h
@@ -0,0 +1,170 @@
+/* include/linux/gpio_event.h
+ *
+ * Copyright (C) 2007 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_GPIO_EVENT_H
+#define _LINUX_GPIO_EVENT_H
+
+#include <linux/input.h>
+
+struct gpio_event_input_devs {
+	int count;
+	struct input_dev *dev[];
+};
+enum {
+	GPIO_EVENT_FUNC_UNINIT  = 0x0,
+	GPIO_EVENT_FUNC_INIT    = 0x1,
+	GPIO_EVENT_FUNC_SUSPEND = 0x2,
+	GPIO_EVENT_FUNC_RESUME  = 0x3,
+};
+struct gpio_event_info {
+	int (*func)(struct gpio_event_input_devs *input_devs,
+		    struct gpio_event_info *info,
+		    void **data, int func);
+	int (*event)(struct gpio_event_input_devs *input_devs,
+		     struct gpio_event_info *info,
+		     void **data, unsigned int dev, unsigned int type,
+		     unsigned int code, int value); /* out events */
+	bool no_suspend;
+};
+
+struct gpio_event_platform_data {
+	const char *name;
+	struct gpio_event_info **info;
+	size_t info_count;
+	int (*power)(const struct gpio_event_platform_data *pdata, bool on);
+	const char *names[]; /* If name is NULL, names contain a NULL */
+			     /* terminated list of input devices to create */
+};
+
+#define GPIO_EVENT_DEV_NAME "gpio-event"
+
+/* Key matrix */
+
+enum gpio_event_matrix_flags {
+	/* unset: drive active output low, set: drive active output high */
+	GPIOKPF_ACTIVE_HIGH              = 1U << 0,
+	GPIOKPF_DEBOUNCE                 = 1U << 1,
+	GPIOKPF_REMOVE_SOME_PHANTOM_KEYS = 1U << 2,
+	GPIOKPF_REMOVE_PHANTOM_KEYS      = GPIOKPF_REMOVE_SOME_PHANTOM_KEYS |
+					   GPIOKPF_DEBOUNCE,
+	GPIOKPF_DRIVE_INACTIVE           = 1U << 3,
+	GPIOKPF_LEVEL_TRIGGERED_IRQ      = 1U << 4,
+	GPIOKPF_PRINT_UNMAPPED_KEYS      = 1U << 16,
+	GPIOKPF_PRINT_MAPPED_KEYS        = 1U << 17,
+	GPIOKPF_PRINT_PHANTOM_KEYS       = 1U << 18,
+};
+
+#define MATRIX_CODE_BITS (10)
+#define MATRIX_KEY_MASK ((1U << MATRIX_CODE_BITS) - 1)
+#define MATRIX_KEY(dev, code) \
+	(((dev) << MATRIX_CODE_BITS) | (code & MATRIX_KEY_MASK))
+
+extern int gpio_event_matrix_func(struct gpio_event_input_devs *input_devs,
+			struct gpio_event_info *info, void **data, int func);
+struct gpio_event_matrix_info {
+	/* initialize to gpio_event_matrix_func */
+	struct gpio_event_info info;
+	/* size must be ninputs * noutputs */
+	const unsigned short *keymap;
+	unsigned int *input_gpios;
+	unsigned int *output_gpios;
+	unsigned int ninputs;
+	unsigned int noutputs;
+	/* time to wait before reading inputs after driving each output */
+	ktime_t settle_time;
+	/* time to wait before scanning the keypad a second time */
+	ktime_t debounce_delay;
+	ktime_t poll_time;
+	unsigned flags;
+};
+
+/* Directly connected inputs and outputs */
+
+enum gpio_event_direct_flags {
+	GPIOEDF_ACTIVE_HIGH         = 1U << 0,
+/*	GPIOEDF_USE_DOWN_IRQ        = 1U << 1, */
+/*	GPIOEDF_USE_IRQ             = (1U << 2) | GPIOIDF_USE_DOWN_IRQ, */
+	GPIOEDF_PRINT_KEYS          = 1U << 8,
+	GPIOEDF_PRINT_KEY_DEBOUNCE  = 1U << 9,
+	GPIOEDF_PRINT_KEY_UNSTABLE  = 1U << 10,
+};
+
+struct gpio_event_direct_entry {
+	uint32_t gpio:16;
+	uint32_t code:10;
+	uint32_t dev:6;
+};
+
+/* inputs */
+extern int gpio_event_input_func(struct gpio_event_input_devs *input_devs,
+			struct gpio_event_info *info, void **data, int func);
+struct gpio_event_input_info {
+	/* initialize to gpio_event_input_func */
+	struct gpio_event_info info;
+	ktime_t debounce_time;
+	ktime_t poll_time;
+	uint16_t flags;
+	uint16_t type;
+	const struct gpio_event_direct_entry *keymap;
+	size_t keymap_size;
+};
+
+/* outputs */
+extern int gpio_event_output_func(struct gpio_event_input_devs *input_devs,
+			struct gpio_event_info *info, void **data, int func);
+extern int gpio_event_output_event(struct gpio_event_input_devs *input_devs,
+			struct gpio_event_info *info, void **data,
+			unsigned int dev, unsigned int type,
+			unsigned int code, int value);
+struct gpio_event_output_info {
+	/* initialize to gpio_event_output_func and gpio_event_output_event */
+	struct gpio_event_info info;
+	uint16_t flags;
+	uint16_t type;
+	const struct gpio_event_direct_entry *keymap;
+	size_t keymap_size;
+};
+
+
+/* axes */
+
+enum gpio_event_axis_flags {
+	GPIOEAF_PRINT_UNKNOWN_DIRECTION  = 1U << 16,
+	GPIOEAF_PRINT_RAW                = 1U << 17,
+	GPIOEAF_PRINT_EVENT              = 1U << 18,
+};
+
+extern int gpio_event_axis_func(struct gpio_event_input_devs *input_devs,
+			struct gpio_event_info *info, void **data, int func);
+struct gpio_event_axis_info {
+	/* initialize to gpio_event_axis_func */
+	struct gpio_event_info info;
+	uint8_t  count; /* number of gpios for this axis */
+	uint8_t  dev; /* device index when using multiple input devices */
+	uint8_t  type; /* EV_REL or EV_ABS */
+	uint16_t code;
+	uint16_t decoded_size;
+	uint16_t (*map)(struct gpio_event_axis_info *info, uint16_t in);
+	uint32_t *gpio;
+	uint32_t flags;
+};
+#define gpio_axis_2bit_gray_map gpio_axis_4bit_gray_map
+#define gpio_axis_3bit_gray_map gpio_axis_4bit_gray_map
+uint16_t gpio_axis_4bit_gray_map(
+			struct gpio_event_axis_info *info, uint16_t in);
+uint16_t gpio_axis_5bit_singletrack_map(
+			struct gpio_event_axis_info *info, uint16_t in);
+
+#endif
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 78ea9bf941c..15680809d34 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -670,8 +670,8 @@ struct hid_driver {
 	int (*input_mapped)(struct hid_device *hdev,
 			struct hid_input *hidinput, struct hid_field *field,
 			struct hid_usage *usage, unsigned long **bit, int *max);
-	void (*input_configured)(struct hid_device *hdev,
-				 struct hid_input *hidinput);
+	int (*input_configured)(struct hid_device *hdev,
+				struct hid_input *hidinput);
 	void (*feature_mapping)(struct hid_device *hdev,
 			struct hid_field *field,
 			struct hid_usage *usage);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 6e6d338641f..14020c7796a 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -99,9 +99,9 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep);
 struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
 			      int write);
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-				pmd_t *pmd, int write);
+				pmd_t *pmd, int flags);
 struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
-				pud_t *pud, int write);
+				pud_t *pud, int flags);
 int pmd_huge(pmd_t pmd);
 int pud_huge(pud_t pmd);
 unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
@@ -133,8 +133,8 @@ static inline void hugetlb_report_meminfo(struct seq_file *m)
 static inline void hugetlb_show_meminfo(void)
 {
 }
-#define follow_huge_pmd(mm, addr, pmd, write)	NULL
-#define follow_huge_pud(mm, addr, pud, write)	NULL
+#define follow_huge_pmd(mm, addr, pmd, flags)	NULL
+#define follow_huge_pud(mm, addr, pud, flags)	NULL
 #define prepare_hugepage_range(file, addr, len)	(-EINVAL)
 #define pmd_huge(x)	0
 #define pud_huge(x)	0
diff --git a/include/linux/if_pppolac.h b/include/linux/if_pppolac.h
new file mode 100644
index 00000000000..e40aa1075a3
--- /dev/null
+++ b/include/linux/if_pppolac.h
@@ -0,0 +1,23 @@
+/* include/linux/if_pppolac.h
+ *
+ * Header for PPP on L2TP Access Concentrator / PPPoLAC Socket (RFC 2661)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ * Author: Chia-chi Yeh <chiachi@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __LINUX_IF_PPPOLAC_H
+#define __LINUX_IF_PPPOLAC_H
+
+#include <uapi/linux/if_pppolac.h>
+
+#endif /* __LINUX_IF_PPPOLAC_H */
diff --git a/include/linux/if_pppopns.h b/include/linux/if_pppopns.h
new file mode 100644
index 00000000000..4ac621a9ce7
--- /dev/null
+++ b/include/linux/if_pppopns.h
@@ -0,0 +1,23 @@
+/* include/linux/if_pppopns.h
+ *
+ * Header for PPP on PPTP Network Server / PPPoPNS Socket (RFC 2637)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ * Author: Chia-chi Yeh <chiachi@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __LINUX_IF_PPPOPNS_H
+#define __LINUX_IF_PPPOPNS_H
+
+#include <uapi/linux/if_pppopns.h>
+
+#endif /* __LINUX_IF_PPPOPNS_H */
diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h
index aff7ad8a4ea..070ec7d0df4 100644
--- a/include/linux/if_pppox.h
+++ b/include/linux/if_pppox.h
@@ -41,6 +41,25 @@ struct pptp_opt {
 	u32 seq_sent, seq_recv;
 	int ppp_flags;
 };
+
+struct pppolac_opt {
+	__u32		local;
+	__u32		remote;
+	__u32		recv_sequence;
+	__u32		xmit_sequence;
+	atomic_t	sequencing;
+	int		(*backlog_rcv)(struct sock *sk_udp, struct sk_buff *skb);
+};
+
+struct pppopns_opt {
+	__u16		local;
+	__u16		remote;
+	__u32		recv_sequence;
+	__u32		xmit_sequence;
+	void		(*data_ready)(struct sock *sk_raw);
+	int		(*backlog_rcv)(struct sock *sk_raw, struct sk_buff *skb);
+};
+
 #include <net/sock.h>
 
 struct pppox_sock {
@@ -51,6 +70,8 @@ struct pppox_sock {
 	union {
 		struct pppoe_opt pppoe;
 		struct pptp_opt  pptp;
+		struct pppolac_opt lac;
+		struct pppopns_opt pns;
 	} proto;
 	__be16			num;
 };
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index d69f0577a31..3a3c4fadcc6 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -320,8 +320,9 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
 }
 
 /**
- * __vlan_put_tag - regular VLAN tag inserting
+ * vlan_insert_tag_set_proto - regular VLAN tag inserting
  * @skb: skbuff to tag
+ * @vlan_proto: VLAN encapsulation protocol
  * @vlan_tci: VLAN TCI to insert
  *
  * Inserts the VLAN tag into @skb as part of the payload
@@ -330,8 +331,9 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
  * Following the skb_unshare() example, in case of error, the calling function
  * doesn't have to worry about freeing the original skb.
  */
-static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb,
-					     __be16 vlan_proto, u16 vlan_tci)
+static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb,
+							__be16 vlan_proto,
+							u16 vlan_tci)
 {
 	skb = vlan_insert_tag(skb, vlan_proto, vlan_tci);
 	if (skb)
@@ -339,6 +341,40 @@ static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb,
 	return skb;
 }
 
+/*
+ * __vlan_hwaccel_push_inside - pushes vlan tag to the payload
+ * @skb: skbuff to tag
+ *
+ * Pushes the VLAN tag from @skb->vlan_tci inside to the payload.
+ *
+ * Following the skb_unshare() example, in case of error, the calling function
+ * doesn't have to worry about freeing the original skb.
+ */
+static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb)
+{
+	skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
+					vlan_tx_tag_get(skb));
+	if (likely(skb))
+		skb->vlan_tci = 0;
+	return skb;
+}
+/*
+ * vlan_hwaccel_push_inside - pushes vlan tag to the payload
+ * @skb: skbuff to tag
+ *
+ * Checks is tag is present in @skb->vlan_tci and if it is, it pushes the
+ * VLAN tag from @skb->vlan_tci inside to the payload.
+ *
+ * Following the skb_unshare() example, in case of error, the calling function
+ * doesn't have to worry about freeing the original skb.
+ */
+static inline struct sk_buff *vlan_hwaccel_push_inside(struct sk_buff *skb)
+{
+	if (vlan_tx_tag_present(skb))
+		skb = __vlan_hwaccel_push_inside(skb);
+	return skb;
+}
+
 /**
  * __vlan_hwaccel_put_tag - hardware accelerated VLAN inserting
  * @skb: skbuff to tag
@@ -357,24 +393,6 @@ static inline struct sk_buff *__vlan_hwaccel_put_tag(struct sk_buff *skb,
 }
 
 /**
- * vlan_put_tag - inserts VLAN tag according to device features
- * @skb: skbuff to tag
- * @vlan_tci: VLAN TCI to insert
- *
- * Assumes skb->dev is the target that will xmit this frame.
- * Returns a VLAN tagged skb.
- */
-static inline struct sk_buff *vlan_put_tag(struct sk_buff *skb,
-					   __be16 vlan_proto, u16 vlan_tci)
-{
-	if (vlan_hw_offload_capable(skb->dev->features, vlan_proto)) {
-		return __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
-	} else {
-		return __vlan_put_tag(skb, vlan_proto, vlan_tci);
-	}
-}
-
-/**
  * __vlan_get_tag - get the VLAN ID that is part of the payload
  * @skb: skbuff to query
  * @vlan_tci: buffer to store vlaue
diff --git a/include/linux/initramfs.h b/include/linux/initramfs.h
new file mode 100644
index 00000000000..fc7da63b125
--- /dev/null
+++ b/include/linux/initramfs.h
@@ -0,0 +1,32 @@
+/*
+ * include/linux/initramfs.h
+ *
+ * Copyright (C) 2015, Google
+ * Rom Lemarchand <romlem@android.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef _LINUX_INITRAMFS_H
+#define _LINUX_INITRAMFS_H
+
+#include <linux/kconfig.h>
+
+#if IS_BUILTIN(CONFIG_BLK_DEV_INITRD)
+
+int __init default_rootfs(void);
+
+#endif
+
+#endif /* _LINUX_INITRAMFS_H */
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index e6a7c9ff72f..e438b30f062 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -27,7 +27,7 @@
 #define IOMMU_READ	(1 << 0)
 #define IOMMU_WRITE	(1 << 1)
 #define IOMMU_CACHE	(1 << 2) /* DMA cache coherency */
-#define IOMMU_EXEC	(1 << 3)
+#define IOMMU_NOEXEC	(1 << 3)
 
 struct iommu_ops;
 struct iommu_group;
@@ -61,6 +61,7 @@ enum iommu_cap {
 	IOMMU_CAP_CACHE_COHERENCY,	/* IOMMU can enforce cache coherent DMA
 					   transactions */
 	IOMMU_CAP_INTR_REMAP,		/* IOMMU supports interrupt isolation */
+	IOMMU_CAP_NOEXEC,		/* IOMMU_NOEXEC flag */
 };
 
 /*
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index ff560537dd6..b8476f01635 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -37,11 +37,13 @@ struct ipv6_devconf {
 	__s32		accept_ra_rt_info_max_plen;
 #endif
 #endif
+	__s32		accept_ra_rt_table;
 	__s32		proxy_ndp;
 	__s32		accept_source_route;
 	__s32		accept_ra_from_local;
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
 	__s32		optimistic_dad;
+	__s32		use_optimistic;
 #endif
 #ifdef CONFIG_IPV6_MROUTE
 	__s32		mc_forwarding;
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 704b9a599b2..dadb42109de 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1035,7 +1035,7 @@ struct buffer_head *jbd2_journal_get_descriptor_buffer(journal_t *journal);
 int jbd2_journal_next_log_block(journal_t *, unsigned long long *);
 int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid,
 			      unsigned long *block);
-void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block);
+int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block);
 void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block);
 
 /* Commit management */
@@ -1157,7 +1157,7 @@ extern int	   jbd2_journal_recover    (journal_t *journal);
 extern int	   jbd2_journal_wipe       (journal_t *, int);
 extern int	   jbd2_journal_skip_recovery	(journal_t *);
 extern void	   jbd2_journal_update_sb_errno(journal_t *);
-extern void	   jbd2_journal_update_sb_log_tail	(journal_t *, tid_t,
+extern int	   jbd2_journal_update_sb_log_tail	(journal_t *, tid_t,
 				unsigned long, int);
 extern void	   __jbd2_journal_abort_hard	(journal_t *);
 extern void	   jbd2_journal_abort      (journal_t *, int);
diff --git a/include/linux/jhash.h b/include/linux/jhash.h
index 47cb09edec1..348c6f47e4c 100644
--- a/include/linux/jhash.h
+++ b/include/linux/jhash.h
@@ -145,11 +145,11 @@ static inline u32 jhash2(const u32 *k, u32 length, u32 initval)
 }
 
 
-/* jhash_3words - hash exactly 3, 2 or 1 word(s) */
-static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval)
+/* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */
+static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
 {
-	a += JHASH_INITVAL;
-	b += JHASH_INITVAL;
+	a += initval;
+	b += initval;
 	c += initval;
 
 	__jhash_final(a, b, c);
@@ -157,14 +157,19 @@ static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval)
 	return c;
 }
 
+static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval)
+{
+	return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2));
+}
+
 static inline u32 jhash_2words(u32 a, u32 b, u32 initval)
 {
-	return jhash_3words(a, b, 0, initval);
+	return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
 }
 
 static inline u32 jhash_1word(u32 a, u32 initval)
 {
-	return jhash_3words(a, 0, 0, initval);
+	return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2));
 }
 
 #endif /* _LINUX_JHASH_H */
diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h
index be342b94c64..16cfb344856 100644
--- a/include/linux/kconfig.h
+++ b/include/linux/kconfig.h
@@ -43,4 +43,13 @@
  */
 #define IS_MODULE(option) config_enabled(option##_MODULE)
 
+/*
+ * IS_REACHABLE(CONFIG_FOO) evaluates to 1 if the currently compiled
+ * code can call a function defined in code compiled based on CONFIG_FOO.
+ * This is similar to IS_ENABLED(), but returns false when invoked from
+ * built-in code when CONFIG_FOO is set to 'm'.
+ */
+#define IS_REACHABLE(option) (config_enabled(option) || \
+		 (config_enabled(option##_MODULE) && config_enabled(MODULE)))
+
 #endif /* __LINUX_KCONFIG_H */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 3d770f5564b..54c20a457d3 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -103,6 +103,18 @@
 		(((__x) - ((__d) / 2)) / (__d));	\
 }							\
 )
+/*
+ * Same as above but for u64 dividends. divisor must be a 32-bit
+ * number.
+ */
+#define DIV_ROUND_CLOSEST_ULL(x, divisor)(		\
+{							\
+	typeof(divisor) __d = divisor;			\
+	unsigned long long _tmp = (x) + (__d) / 2;	\
+	do_div(_tmp, __d);				\
+	_tmp;						\
+}							\
+)
 
 /*
  * Multiplies an integer by a fraction, while avoiding unnecessary
@@ -814,4 +826,8 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 	 /* Other writable?  Generally considered a bad idea. */	\
 	 BUILD_BUG_ON_ZERO((perms) & 2) +				\
 	 (perms))
+
+/* To identify board information in panic logs, set this */
+extern char *mach_panic_string;
+
 #endif
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index b9376cd5a18..25a822f6f00 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -68,6 +68,7 @@ static inline unsigned int kstat_softirqs_cpu(unsigned int irq, int cpu)
  * Number of interrupts per specific IRQ source, since bootup
  */
 extern unsigned int kstat_irqs(unsigned int irq);
+extern unsigned int kstat_irqs_usr(unsigned int irq);
 
 /*
  * Number of interrupts per cpu, since bootup
diff --git a/include/linux/keychord.h b/include/linux/keychord.h
new file mode 100644
index 00000000000..08cf5402102
--- /dev/null
+++ b/include/linux/keychord.h
@@ -0,0 +1,23 @@
+/*
+ *  Key chord input driver
+ *
+ * Copyright (C) 2008 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+*/
+
+#ifndef __LINUX_KEYCHORD_H_
+#define __LINUX_KEYCHORD_H_
+
+#include <uapi/linux/keychord.h>
+
+#endif	/* __LINUX_KEYCHORD_H_ */
diff --git a/include/linux/keycombo.h b/include/linux/keycombo.h
new file mode 100644
index 00000000000..c6db2626b0d
--- /dev/null
+++ b/include/linux/keycombo.h
@@ -0,0 +1,36 @@
+/*
+ * include/linux/keycombo.h - platform data structure for keycombo driver
+ *
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_KEYCOMBO_H
+#define _LINUX_KEYCOMBO_H
+
+#define KEYCOMBO_NAME "keycombo"
+
+/*
+ * if key_down_fn and key_up_fn are both present, you are guaranteed that
+ * key_down_fn will return before key_up_fn is called, and that key_up_fn
+ * is called iff key_down_fn is called.
+ */
+struct keycombo_platform_data {
+	void (*key_down_fn)(void *);
+	void (*key_up_fn)(void *);
+	void *priv;
+	int key_down_delay; /* Time in ms */
+	int *keys_up;
+	int keys_down[]; /* 0 terminated */
+};
+
+#endif /* _LINUX_KEYCOMBO_H */
diff --git a/include/linux/keyreset.h b/include/linux/keyreset.h
new file mode 100644
index 00000000000..2e34afab65e
--- /dev/null
+++ b/include/linux/keyreset.h
@@ -0,0 +1,29 @@
+/*
+ * include/linux/keyreset.h - platform data structure for resetkeys driver
+ *
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_KEYRESET_H
+#define _LINUX_KEYRESET_H
+
+#define KEYRESET_NAME "keyreset"
+
+struct keyreset_platform_data {
+	int (*reset_fn)(void);
+	int key_down_delay;
+	int *keys_up;
+	int keys_down[]; /* 0 terminated */
+};
+
+#endif /* _LINUX_KEYRESET_H */
diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h
index 057e9597101..19acfdc3828 100644
--- a/include/linux/kmemleak.h
+++ b/include/linux/kmemleak.h
@@ -26,7 +26,8 @@
 extern void kmemleak_init(void) __ref;
 extern void kmemleak_alloc(const void *ptr, size_t size, int min_count,
 			   gfp_t gfp) __ref;
-extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size) __ref;
+extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size,
+				  gfp_t gfp) __ref;
 extern void kmemleak_free(const void *ptr) __ref;
 extern void kmemleak_free_part(const void *ptr, size_t size) __ref;
 extern void kmemleak_free_percpu(const void __percpu *ptr) __ref;
@@ -69,7 +70,8 @@ static inline void kmemleak_alloc_recursive(const void *ptr, size_t size,
 					    gfp_t gfp)
 {
 }
-static inline void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size)
+static inline void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size,
+					 gfp_t gfp)
 {
 }
 static inline void kmemleak_free(const void *ptr)
diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index c9d645ad98f..039bbe5f59d 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -166,9 +166,34 @@ static inline bool ktime_before(const ktime_t cmp1, const ktime_t cmp2)
 }
 
 #if BITS_PER_LONG < 64
-extern u64 ktime_divns(const ktime_t kt, s64 div);
+extern s64 __ktime_divns(const ktime_t kt, s64 div);
+static inline s64 ktime_divns(const ktime_t kt, s64 div)
+{
+	/*
+	 * Negative divisors could cause an inf loop,
+	 * so bug out here.
+	 */
+	BUG_ON(div < 0);
+	if (__builtin_constant_p(div) && !(div >> 32)) {
+		s64 ns = kt.tv64;
+		u64 tmp = ns < 0 ? -ns : ns;
+
+		do_div(tmp, div);
+		return ns < 0 ? -tmp : tmp;
+	} else {
+		return __ktime_divns(kt, div);
+	}
+}
 #else /* BITS_PER_LONG < 64 */
-# define ktime_divns(kt, div)		(u64)((kt).tv64 / (div))
+static inline s64 ktime_divns(const ktime_t kt, s64 div)
+{
+	/*
+	 * 32-bit implementation cannot handle negative divisors,
+	 * so catch them on 64bit as well.
+	 */
+	WARN_ON(div < 0);
+	return kt.tv64 / div;
+}
 #endif
 
 static inline s64 ktime_to_us(const ktime_t kt)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index a6059bdf7b0..e4d8f705fec 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -43,6 +43,7 @@
  * include/linux/kvm_h.
  */
 #define KVM_MEMSLOT_INVALID	(1UL << 16)
+#define KVM_MEMSLOT_INCOHERENT	(1UL << 17)
 
 /* Two fragments for cross MMIO pages. */
 #define KVM_MAX_MMIO_FRAGMENTS	2
diff --git a/include/linux/libata.h b/include/linux/libata.h
index bd5fefeaf54..8f6a07441b8 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -204,6 +204,7 @@ enum {
 	ATA_LFLAG_SW_ACTIVITY	= (1 << 7), /* keep activity stats */
 	ATA_LFLAG_NO_LPM	= (1 << 8), /* disable LPM on this link */
 	ATA_LFLAG_RST_ONCE	= (1 << 9), /* limit recovery to one reset */
+	ATA_LFLAG_CHANGED	= (1 << 10), /* LPM state changed on this link */
 
 	/* struct ata_port flags */
 	ATA_FLAG_SLAVE_POSS	= (1 << 0), /* host supports slave dev */
@@ -230,6 +231,7 @@ enum {
 	ATA_FLAG_SW_ACTIVITY	= (1 << 22), /* driver supports sw activity
 					      * led */
 	ATA_FLAG_NO_DIPM	= (1 << 23), /* host not happy with DIPM */
+	ATA_FLAG_LOWTAG		= (1 << 24), /* host wants lowest available tag */
 
 	/* bits 24:31 of ap->flags are reserved for LLD specific flags */
 
@@ -307,6 +309,12 @@ enum {
 	 */
 	ATA_TMOUT_PMP_SRST_WAIT	= 5000,
 
+	/* When the LPM policy is set to ATA_LPM_MAX_POWER, there might
+	 * be a spurious PHY event, so ignore the first PHY event that
+	 * occurs within 10s after the policy change.
+	 */
+	ATA_TMOUT_SPURIOUS_PHY	= 10000,
+
 	/* ATA bus states */
 	BUS_UNKNOWN		= 0,
 	BUS_DMA			= 1,
@@ -421,6 +429,7 @@ enum {
 	ATA_HORKAGE_NO_NCQ_TRIM	= (1 << 19),	/* don't use queued TRIM */
 	ATA_HORKAGE_NOLPM	= (1 << 20),	/* don't use LPM */
 	ATA_HORKAGE_WD_BROKEN_LPM = (1 << 21),	/* some WDs have broken LPM */
+	ATA_HORKAGE_NOTRIM = (1 << 24),		/* don't use TRIM */
 
 	 /* DMA mask for user DMA control: User visible values; DO NOT
 	    renumber */
@@ -785,6 +794,8 @@ struct ata_link {
 	struct ata_eh_context	eh_context;
 
 	struct ata_device	device[ATA_MAX_DEVICES];
+
+	unsigned long		last_lpm_change; /* when last LPM change happened */
 };
 #define ATA_LINK_CLEAR_BEGIN		offsetof(struct ata_link, active_tag)
 #define ATA_LINK_CLEAR_END		offsetof(struct ata_link, device[0])
@@ -1198,6 +1209,7 @@ extern struct ata_device *ata_dev_pair(struct ata_device *adev);
 extern int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev);
 extern void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap);
 extern void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, struct list_head *eh_q);
+extern bool sata_lpm_ignore_phy_events(struct ata_link *link);
 
 extern int ata_cable_40wire(struct ata_port *ap);
 extern int ata_cable_80wire(struct ata_port *ap);
diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h
index 1cc89e9df48..ffb9c9da4f3 100644
--- a/include/linux/lsm_audit.h
+++ b/include/linux/lsm_audit.h
@@ -40,6 +40,11 @@ struct lsm_network_audit {
 	} fam;
 };
 
+struct lsm_ioctlop_audit {
+	struct path path;
+	u16 cmd;
+};
+
 /* Auxiliary data to use in generating the audit record. */
 struct common_audit_data {
 	char type;
@@ -53,6 +58,7 @@ struct common_audit_data {
 #define LSM_AUDIT_DATA_KMOD	8
 #define LSM_AUDIT_DATA_INODE	9
 #define LSM_AUDIT_DATA_DENTRY	10
+#define LSM_AUDIT_DATA_IOCTL_OP	11
 	union 	{
 		struct path path;
 		struct dentry *dentry;
@@ -68,6 +74,7 @@ struct common_audit_data {
 		} key_struct;
 #endif
 		char *kmod_name;
+		struct lsm_ioctlop_audit *op;
 	} u;
 	/* this union contains LSM specific data */
 	union {
diff --git a/include/linux/mailbox_client.h b/include/linux/mailbox_client.h
index 307d9cab202..1726ccbd800 100644
--- a/include/linux/mailbox_client.h
+++ b/include/linux/mailbox_client.h
@@ -25,6 +25,8 @@ struct mbox_chan;
  *			if the client receives some ACK packet for transmission.
  *			Unused if the controller already has TX_Done/RTR IRQ.
  * @rx_callback:	Atomic callback to provide client the data received
+ * @tx_prepare: 	Atomic callback to ask client to prepare the payload
+ *			before initiating the transmission if required.
  * @tx_done:		Atomic callback to tell client of data transmission
  */
 struct mbox_client {
@@ -34,6 +36,7 @@ struct mbox_client {
 	bool knows_txdone;
 
 	void (*rx_callback)(struct mbox_client *cl, void *mssg);
+	void (*tx_prepare)(struct mbox_client *cl, void *mssg);
 	void (*tx_done)(struct mbox_client *cl, void *mssg, int r);
 };
 
diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h
index fb0390a1a49..ee7b1ce7a6f 100644
--- a/include/linux/mfd/palmas.h
+++ b/include/linux/mfd/palmas.h
@@ -2999,6 +2999,9 @@ enum usb_irq_events {
 #define PALMAS_GPADC_TRIM15					0x0E
 #define PALMAS_GPADC_TRIM16					0x0F
 
+/* TPS659038 regen2_ctrl offset iss different from palmas */
+#define TPS659038_REGEN2_CTRL					0x12
+
 /* TPS65917 Interrupt registers */
 
 /* Registers for function INTERRUPT */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b46461116cd..8fae7d6e9a1 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1054,6 +1054,7 @@ static inline int page_mapped(struct page *page)
 #define VM_FAULT_WRITE	0x0008	/* Special case for get_user_pages */
 #define VM_FAULT_HWPOISON 0x0010	/* Hit poisoned small page */
 #define VM_FAULT_HWPOISON_LARGE 0x0020  /* Hit poisoned large page. Index encoded in upper bits */
+#define VM_FAULT_SIGSEGV 0x0040
 
 #define VM_FAULT_NOPAGE	0x0100	/* ->fault installed the pte, not return page */
 #define VM_FAULT_LOCKED	0x0200	/* ->fault locked the returned page */
@@ -1062,8 +1063,9 @@ static inline int page_mapped(struct page *page)
 
 #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
 
-#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \
-			 VM_FAULT_FALLBACK | VM_FAULT_HWPOISON_LARGE)
+#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | \
+			 VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE | \
+			 VM_FAULT_FALLBACK)
 
 /* Encode hstate index for a hwpoisoned large page */
 #define VM_FAULT_SET_HINDEX(x) ((x) << 12)
@@ -1085,6 +1087,7 @@ extern void pagefault_out_of_memory(void);
 extern void show_free_areas(unsigned int flags);
 extern bool skip_free_areas_node(unsigned int flags, int nid);
 
+void shmem_set_file(struct vm_area_struct *vma, struct file *file);
 int shmem_zero_setup(struct vm_area_struct *);
 #ifdef CONFIG_SHMEM
 bool shmem_mapping(struct address_space *mapping);
@@ -1350,6 +1353,11 @@ static inline void update_hiwater_vm(struct mm_struct *mm)
 		mm->hiwater_vm = mm->total_vm;
 }
 
+static inline void reset_mm_hiwater_rss(struct mm_struct *mm)
+{
+	mm->hiwater_rss = get_mm_rss(mm);
+}
+
 static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
 					 struct mm_struct *mm)
 {
@@ -1788,7 +1796,7 @@ extern int vma_adjust(struct vm_area_struct *vma, unsigned long start,
 extern struct vm_area_struct *vma_merge(struct mm_struct *,
 	struct vm_area_struct *prev, unsigned long addr, unsigned long end,
 	unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t,
-	struct mempolicy *);
+	struct mempolicy *, const char __user *);
 extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *);
 extern int split_vma(struct mm_struct *,
 	struct vm_area_struct *, unsigned long addr, int new_below);
@@ -1936,7 +1944,7 @@ extern int expand_downwards(struct vm_area_struct *vma,
 #if VM_GROWSUP
 extern int expand_upwards(struct vm_area_struct *vma, unsigned long address);
 #else
-  #define expand_upwards(vma, address) do { } while (0)
+  #define expand_upwards(vma, address) (0)
 #endif
 
 /* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6e0b286649f..6c44170c4ac 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -274,6 +274,10 @@ struct vm_area_struct {
 	 * For areas with an address space and backing store,
 	 * linkage into the address_space->i_mmap interval tree, or
 	 * linkage of vma in the address_space->i_mmap_nonlinear list.
+	 *
+	 * For private anonymous mappings, a pointer to a null terminated string
+	 * in the user process containing the name given to the vma, or NULL
+	 * if unnamed.
 	 */
 	union {
 		struct {
@@ -281,6 +285,7 @@ struct vm_area_struct {
 			unsigned long rb_subtree_last;
 		} linear;
 		struct list_head nonlinear;
+		const char __user *anon_name;
 	} shared;
 
 	/*
@@ -525,4 +530,13 @@ enum tlb_flush_reason {
 	NR_TLB_FLUSH_REASONS,
 };
 
+/* Return the name for an anonymous mapping or NULL for a file-backed mapping */
+static inline const char __user *vma_get_anon_name(struct vm_area_struct *vma)
+{
+	if (vma->vm_file)
+		return NULL;
+
+	return vma->shared.anon_name;
+}
+
 #endif /* _LINUX_MM_TYPES_H */
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index df0c15396bb..bf2252a6fe3 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -375,6 +375,15 @@ struct mmc_host {
 	int			dsr_req;	/* DSR value is valid */
 	u32			dsr;	/* optional driver stage (DSR) value */
 
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+	struct {
+		struct sdio_cis			*cis;
+		struct sdio_cccr		*cccr;
+		struct sdio_embedded_func	*funcs;
+		int				num_funcs;
+	} embedded_sdio_data;
+#endif
+
 	unsigned long		private[0] ____cacheline_aligned;
 };
 
@@ -384,6 +393,14 @@ void mmc_remove_host(struct mmc_host *);
 void mmc_free_host(struct mmc_host *);
 int mmc_of_parse(struct mmc_host *host);
 
+#ifdef CONFIG_MMC_EMBEDDED_SDIO
+extern void mmc_set_embedded_sdio_data(struct mmc_host *host,
+				       struct sdio_cis *cis,
+				       struct sdio_cccr *cccr,
+				       struct sdio_embedded_func *funcs,
+				       int num_funcs);
+#endif
+
 static inline void *mmc_priv(struct mmc_host *host)
 {
 	return (void *)host->private;
diff --git a/include/linux/mmc/pm.h b/include/linux/mmc/pm.h
index 4a139204c20..6e2d6a135c7 100644
--- a/include/linux/mmc/pm.h
+++ b/include/linux/mmc/pm.h
@@ -26,5 +26,6 @@ typedef unsigned int mmc_pm_flag_t;
 
 #define MMC_PM_KEEP_POWER	(1 << 0)	/* preserve card power during suspend */
 #define MMC_PM_WAKE_SDIO_IRQ	(1 << 1)	/* wake up host system on SDIO IRQ assertion */
+#define MMC_PM_IGNORE_PM_NOTIFY	(1 << 2)	/* ignore mmc pm notify */
 
 #endif /* LINUX_MMC_PM_H */
diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h
index 50f0bc95232..dc680c4b50d 100644..100755
--- a/include/linux/mmc/sdio_func.h
+++ b/include/linux/mmc/sdio_func.h
@@ -23,6 +23,14 @@ struct sdio_func;
 typedef void (sdio_irq_handler_t)(struct sdio_func *);
 
 /*
+ * Structure used to hold embedded SDIO device data from platform layer
+ */
+struct sdio_embedded_func {
+	uint8_t f_class;
+	uint32_t f_maxblksize;
+};
+
+/*
  * SDIO function CIS tuple (unknown to the core)
  */
 struct sdio_func_tuple {
@@ -130,6 +138,8 @@ extern int sdio_release_irq(struct sdio_func *func);
 extern unsigned int sdio_align_size(struct sdio_func *func, unsigned int sz);
 
 extern u8 sdio_readb(struct sdio_func *func, unsigned int addr, int *err_ret);
+extern u8 sdio_readb_ext(struct sdio_func *func, unsigned int addr, int *err_ret,
+	unsigned in);
 extern u16 sdio_readw(struct sdio_func *func, unsigned int addr, int *err_ret);
 extern u32 sdio_readl(struct sdio_func *func, unsigned int addr, int *err_ret);
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 74fd5d37f15..c3fd34da6c0 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -998,12 +998,15 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  *	Callback to use for xmit over the accelerated station. This
  *	is used in place of ndo_start_xmit on accelerated net
  *	devices.
- * bool	(*ndo_gso_check) (struct sk_buff *skb,
- *			  struct net_device *dev);
+ * netdev_features_t (*ndo_features_check) (struct sk_buff *skb,
+ *					    struct net_device *dev
+ *					    netdev_features_t features);
  *	Called by core transmit path to determine if device is capable of
- *	performing GSO on a packet. The device returns true if it is
- *	able to GSO the packet, false otherwise. If the return value is
- *	false the stack will do software GSO.
+ *	performing offload operations on a given packet. This is to give
+ *	the device an opportunity to implement any restrictions that cannot
+ *	be otherwise expressed by feature flags. The check is called with
+ *	the set of features that the stack has calculated and it returns
+ *	those the driver believes to be appropriate.
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -1153,8 +1156,9 @@ struct net_device_ops {
 							struct net_device *dev,
 							void *priv);
 	int			(*ndo_get_lock_subclass)(struct net_device *dev);
-	bool			(*ndo_gso_check) (struct sk_buff *skb,
-						  struct net_device *dev);
+	netdev_features_t	(*ndo_features_check) (struct sk_buff *skb,
+						       struct net_device *dev,
+						       netdev_features_t features);
 };
 
 /**
@@ -2118,6 +2122,12 @@ void netdev_freemem(struct net_device *dev);
 void synchronize_net(void);
 int init_dummy_netdev(struct net_device *dev);
 
+DECLARE_PER_CPU(int, xmit_recursion);
+static inline int dev_recursion_level(void)
+{
+	return this_cpu_read(xmit_recursion);
+}
+
 struct net_device *dev_get_by_index(struct net *net, int ifindex);
 struct net_device *__dev_get_by_index(struct net *net, int ifindex);
 struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
@@ -3584,8 +3594,6 @@ static inline bool netif_needs_gso(struct net_device *dev, struct sk_buff *skb,
 				   netdev_features_t features)
 {
 	return skb_is_gso(skb) && (!skb_gso_ok(skb, features) ||
-		(dev->netdev_ops->ndo_gso_check &&
-		 !dev->netdev_ops->ndo_gso_check(skb, dev)) ||
 		unlikely((skb->ip_summed != CHECKSUM_PARTIAL) &&
 			 (skb->ip_summed != CHECKSUM_UNNECESSARY)));
 }
diff --git a/include/linux/netfilter/xt_qtaguid.h b/include/linux/netfilter/xt_qtaguid.h
new file mode 100644
index 00000000000..ca60fbdec2f
--- /dev/null
+++ b/include/linux/netfilter/xt_qtaguid.h
@@ -0,0 +1,13 @@
+#ifndef _XT_QTAGUID_MATCH_H
+#define _XT_QTAGUID_MATCH_H
+
+/* For now we just replace the xt_owner.
+ * FIXME: make iptables aware of qtaguid. */
+#include <linux/netfilter/xt_owner.h>
+
+#define XT_QTAGUID_UID    XT_OWNER_UID
+#define XT_QTAGUID_GID    XT_OWNER_GID
+#define XT_QTAGUID_SOCKET XT_OWNER_SOCKET
+#define xt_qtaguid_match_info xt_owner_match_info
+
+#endif /* _XT_QTAGUID_MATCH_H */
diff --git a/include/linux/netfilter/xt_quota2.h b/include/linux/netfilter/xt_quota2.h
new file mode 100644
index 00000000000..eadc6903314
--- /dev/null
+++ b/include/linux/netfilter/xt_quota2.h
@@ -0,0 +1,25 @@
+#ifndef _XT_QUOTA_H
+#define _XT_QUOTA_H
+
+enum xt_quota_flags {
+	XT_QUOTA_INVERT    = 1 << 0,
+	XT_QUOTA_GROW      = 1 << 1,
+	XT_QUOTA_PACKET    = 1 << 2,
+	XT_QUOTA_NO_CHANGE = 1 << 3,
+	XT_QUOTA_MASK      = 0x0F,
+};
+
+struct xt_quota_counter;
+
+struct xt_quota_mtinfo2 {
+	char name[15];
+	u_int8_t flags;
+
+	/* Comparison-invariant */
+	aligned_u64 quota;
+
+	/* Used internally by the kernel */
+	struct xt_quota_counter *master __attribute__((aligned(8)));
+};
+
+#endif /* _XT_QUOTA_H */
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 47ebb4fafd8..d71682435f4 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1132,7 +1132,7 @@ struct nfs41_state_protection {
 	struct nfs4_op_map allow;
 };
 
-#define NFS4_EXCHANGE_ID_LEN	(48)
+#define NFS4_EXCHANGE_ID_LEN	(127)
 struct nfs41_exchange_id_args {
 	struct nfs_client		*client;
 	nfs4_verifier			*verifier;
@@ -1328,7 +1328,7 @@ struct nfs_commit_completion_ops {
 };
 
 struct nfs_commit_info {
-	spinlock_t			*lock;
+	spinlock_t			*lock;	/* inode->i_lock */
 	struct nfs_mds_commit_info	*mds;
 	struct pnfs_ds_commit_info	*ds;
 	struct nfs_direct_req		*dreq;	/* O_DIRECT request */
diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h
index ff3fea3194c..9abb763e4b8 100644
--- a/include/linux/nilfs2_fs.h
+++ b/include/linux/nilfs2_fs.h
@@ -460,7 +460,7 @@ struct nilfs_btree_node {
 /* level */
 #define NILFS_BTREE_LEVEL_DATA          0
 #define NILFS_BTREE_LEVEL_NODE_MIN      (NILFS_BTREE_LEVEL_DATA + 1)
-#define NILFS_BTREE_LEVEL_MAX           14
+#define NILFS_BTREE_LEVEL_MAX           14	/* Max level (exclusive) */
 
 /**
  * struct nilfs_palloc_group_desc - block group descriptor
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 9b2022ab4d8..eeb54ae381b 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -14,8 +14,11 @@
  * may be used to reset the timeout - for code which intentionally
  * disables interrupts for a long time. This call is stateless.
  */
-#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
+#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR_NMI)
 #include <asm/nmi.h>
+#endif
+
+#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
 extern void touch_nmi_watchdog(void);
 #else
 static inline void touch_nmi_watchdog(void)
@@ -45,13 +48,23 @@ static inline bool watchdog_hardlockup_detector_is_enabled(void)
 #ifdef arch_trigger_all_cpu_backtrace
 static inline bool trigger_all_cpu_backtrace(void)
 {
+	#if defined(CONFIG_ARM)
+	arch_trigger_all_cpu_backtrace();
+	#else
 	arch_trigger_all_cpu_backtrace(true);
+	#endif
 
 	return true;
 }
 static inline bool trigger_allbutself_cpu_backtrace(void)
 {
+	#if defined(CONFIG_ARM)
+	arch_trigger_all_cpu_backtrace();
+	#else
 	arch_trigger_all_cpu_backtrace(false);
+	#endif
+
+
 	return true;
 }
 #else
diff --git a/include/linux/of.h b/include/linux/of.h
index 29f0adc5f3e..4a6a489a750 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -23,6 +23,7 @@
 #include <linux/spinlock.h>
 #include <linux/topology.h>
 #include <linux/notifier.h>
+#include <linux/property.h>
 
 #include <asm/byteorder.h>
 #include <asm/errno.h>
@@ -263,6 +264,10 @@ extern int of_property_read_u32_array(const struct device_node *np,
 				      size_t sz);
 extern int of_property_read_u64(const struct device_node *np,
 				const char *propname, u64 *out_value);
+extern int of_property_read_u64_array(const struct device_node *np,
+				      const char *propname,
+				      u64 *out_values,
+				      size_t sz);
 
 extern int of_property_read_string(struct device_node *np,
 				   const char *propname,
@@ -477,6 +482,13 @@ static inline int of_property_read_u32_array(const struct device_node *np,
 	return -ENOSYS;
 }
 
+static inline int of_property_read_u64_array(const struct device_node *np,
+					     const char *propname,
+					     u64 *out_values, size_t sz)
+{
+	return -ENOSYS;
+}
+
 static inline int of_property_read_string(struct device_node *np,
 					  const char *propname,
 					  const char **out_string)
@@ -581,7 +593,10 @@ static inline const char *of_prop_next_string(struct property *prop,
 #if defined(CONFIG_OF) && defined(CONFIG_NUMA)
 extern int of_node_to_nid(struct device_node *np);
 #else
-static inline int of_node_to_nid(struct device_node *device) { return 0; }
+static inline int of_node_to_nid(struct device_node *device)
+{
+	return NUMA_NO_NODE;
+}
 #endif
 
 static inline struct device_node *of_find_matching_node(
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index 0ff360d5b3b..35feeca7bf2 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -57,6 +57,27 @@ extern int of_flat_dt_match(unsigned long node, const char *const *matches);
 extern unsigned long of_get_flat_dt_root(void);
 extern int of_get_flat_dt_size(void);
 
+/*
+ * early_init_dt_scan_chosen - scan the device tree for ramdisk and bootargs
+ *
+ * The boot arguments will be placed into the memory pointed to by @data.
+ * That memory should be COMMAND_LINE_SIZE big and initialized to be a valid
+ * (possibly empty) string.  Logic for what will be in @data after this
+ * function finishes:
+ *
+ * - CONFIG_CMDLINE_FORCE=true
+ *     CONFIG_CMDLINE
+ * - CONFIG_CMDLINE_EXTEND=true, @data is non-empty string
+ *     @data + dt bootargs (even if dt bootargs are empty)
+ * - CONFIG_CMDLINE_EXTEND=true, @data is empty string
+ *     CONFIG_CMDLINE + dt bootargs (even if dt bootargs are empty)
+ * - CMDLINE_FROM_BOOTLOADER=true, dt bootargs=non-empty:
+ *     dt bootargs
+ * - CMDLINE_FROM_BOOTLOADER=true, dt bootargs=empty, @data is non-empty string
+ *     @data is left unchanged
+ * - CMDLINE_FROM_BOOTLOADER=true, dt bootargs=empty, @data is empty string
+ *     CONFIG_CMDLINE (or "" if that's not defined)
+ */
 extern int early_init_dt_scan_chosen(unsigned long node, const char *uname,
 				     int depth, void *data);
 extern int early_init_dt_scan_memory(unsigned long node, const char *uname,
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 7ea069cd325..4b3736f7065 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -251,7 +251,7 @@ pgoff_t page_cache_prev_hole(struct address_space *mapping,
 #define FGP_NOWAIT		0x00000020
 
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
-		int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask);
+		int fgp_flags, gfp_t cache_gfp_mask);
 
 /**
  * find_get_page - find and get a page reference
@@ -266,13 +266,13 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
 static inline struct page *find_get_page(struct address_space *mapping,
 					pgoff_t offset)
 {
-	return pagecache_get_page(mapping, offset, 0, 0, 0);
+	return pagecache_get_page(mapping, offset, 0, 0);
 }
 
 static inline struct page *find_get_page_flags(struct address_space *mapping,
 					pgoff_t offset, int fgp_flags)
 {
-	return pagecache_get_page(mapping, offset, fgp_flags, 0, 0);
+	return pagecache_get_page(mapping, offset, fgp_flags, 0);
 }
 
 /**
@@ -292,7 +292,7 @@ static inline struct page *find_get_page_flags(struct address_space *mapping,
 static inline struct page *find_lock_page(struct address_space *mapping,
 					pgoff_t offset)
 {
-	return pagecache_get_page(mapping, offset, FGP_LOCK, 0, 0);
+	return pagecache_get_page(mapping, offset, FGP_LOCK, 0);
 }
 
 /**
@@ -319,7 +319,7 @@ static inline struct page *find_or_create_page(struct address_space *mapping,
 {
 	return pagecache_get_page(mapping, offset,
 					FGP_LOCK|FGP_ACCESSED|FGP_CREAT,
-					gfp_mask, gfp_mask & GFP_RECLAIM_MASK);
+					gfp_mask);
 }
 
 /**
@@ -340,8 +340,7 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping,
 {
 	return pagecache_get_page(mapping, index,
 			FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT,
-			mapping_gfp_mask(mapping),
-			GFP_NOFS);
+			mapping_gfp_mask(mapping));
 }
 
 struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 4c8ac5fcc22..e92cdad3240 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -175,6 +175,8 @@ enum pci_dev_flags {
 	PCI_DEV_FLAGS_DMA_ALIAS_DEVFN = (__force pci_dev_flags_t) (1 << 4),
 	/* Use a PCIe-to-PCI bridge alias even if !pci_is_pcie */
 	PCI_DEV_FLAG_PCIE_BRIDGE_ALIAS = (__force pci_dev_flags_t) (1 << 5),
+	/* Do not use bus resets for device */
+	PCI_DEV_FLAGS_NO_BUS_RESET = (__force pci_dev_flags_t) (1 << 6),
 };
 
 enum pci_irq_reroute_variant {
@@ -991,6 +993,7 @@ int __must_check pci_assign_resource(struct pci_dev *dev, int i);
 int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align);
 int pci_select_bars(struct pci_dev *dev, unsigned long flags);
 bool pci_device_is_present(struct pci_dev *pdev);
+void pci_ignore_hotplug(struct pci_dev *dev);
 
 /* ROM control related routines */
 int pci_enable_rom(struct pci_dev *pdev);
@@ -1026,11 +1029,6 @@ bool pci_dev_run_wake(struct pci_dev *dev);
 bool pci_check_pme_status(struct pci_dev *dev);
 void pci_pme_wakeup_bus(struct pci_bus *bus);
 
-static inline void pci_ignore_hotplug(struct pci_dev *dev)
-{
-	dev->ignore_hotplug = 1;
-}
-
 static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state,
 				  bool enable)
 {
@@ -1062,6 +1060,7 @@ resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx);
 void pci_bus_assign_resources(const struct pci_bus *bus);
 void pci_bus_size_bridges(struct pci_bus *bus);
 int pci_claim_resource(struct pci_dev *, int);
+int pci_claim_bridge_resource(struct pci_dev *bridge, int i);
 void pci_assign_unassigned_resources(void);
 void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge);
 void pci_assign_unassigned_bus_resources(struct pci_bus *bus);
diff --git a/include/linux/platform_data/ds2482.h b/include/linux/platform_data/ds2482.h
new file mode 100644
index 00000000000..5a6879e2a09
--- /dev/null
+++ b/include/linux/platform_data/ds2482.h
@@ -0,0 +1,21 @@
+/*
+ * Copyright (C) 2012 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __PLATFORM_DATA_DS2482__
+#define __PLATFORM_DATA_DS2482__
+
+struct ds2482_platform_data {
+	int		slpz_gpio;
+};
+
+#endif /* __PLATFORM_DATA_DS2482__ */
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 0330217abfa..1c93411b2ac 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -28,6 +28,8 @@ enum dev_pm_opp_event {
 
 unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp);
 
+unsigned long dev_pm_opp_get_voltage_always(struct dev_pm_opp *opp);
+
 unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp);
 
 int dev_pm_opp_get_opp_count(struct device *dev);
@@ -56,6 +58,11 @@ static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 	return 0;
 }
 
+static inline unsigned long dev_pm_opp_get_voltage_always(struct dev_pm_opp *opp)
+{
+	return 0;
+}
+
 static inline unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 {
 	return 0;
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index 096dbced02a..ec509ed0860 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -17,6 +17,7 @@
 #include <linux/leds.h>
 #include <linux/spinlock.h>
 #include <linux/notifier.h>
+#include <linux/types.h>
 
 /*
  * All voltages, currents, charges, energies, time and temperatures in uV,
@@ -147,6 +148,12 @@ enum power_supply_property {
 	POWER_SUPPLY_PROP_SCOPE,
 	POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT,
 	POWER_SUPPLY_PROP_CALIBRATE,
+	/* Local extensions */
+	POWER_SUPPLY_PROP_USB_HC,
+	POWER_SUPPLY_PROP_USB_OTG,
+	POWER_SUPPLY_PROP_CHARGE_ENABLED,
+	/* Local extensions of type int64_t */
+	POWER_SUPPLY_PROP_CHARGE_COUNTER_EXT,
 	/* Properties of type `const char *' */
 	POWER_SUPPLY_PROP_MODEL_NAME,
 	POWER_SUPPLY_PROP_MANUFACTURER,
@@ -171,6 +178,7 @@ enum power_supply_notifier_events {
 union power_supply_propval {
 	int intval;
 	const char *strval;
+	int64_t int64val;
 };
 
 struct device;
diff --git a/include/linux/property.h b/include/linux/property.h
new file mode 100644
index 00000000000..9242fb0221b
--- /dev/null
+++ b/include/linux/property.h
@@ -0,0 +1,73 @@
+/*
+ * property.h - Unified device property interface.
+ *
+ * Copyright (C) 2014, Intel Corporation
+ * Authors: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *          Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _LINUX_PROPERTY_H_
+#define _LINUX_PROPERTY_H_
+
+#include <linux/types.h>
+
+struct device;
+
+enum dev_prop_type {
+	DEV_PROP_U8,
+	DEV_PROP_U16,
+	DEV_PROP_U32,
+	DEV_PROP_U64,
+	DEV_PROP_STRING,
+	DEV_PROP_MAX,
+};
+
+bool device_property_present(struct device *dev, const char *propname);
+int device_property_read_u8_array(struct device *dev, const char *propname,
+				  u8 *val, size_t nval);
+int device_property_read_u16_array(struct device *dev, const char *propname,
+				   u16 *val, size_t nval);
+int device_property_read_u32_array(struct device *dev, const char *propname,
+				   u32 *val, size_t nval);
+int device_property_read_u64_array(struct device *dev, const char *propname,
+				   u64 *val, size_t nval);
+int device_property_read_string_array(struct device *dev, const char *propname,
+				      const char **val, size_t nval);
+int device_property_read_string(struct device *dev, const char *propname,
+				const char **val);
+
+static inline bool device_property_read_bool(struct device *dev,
+					     const char *propname)
+{
+	return device_property_present(dev, propname);
+}
+
+static inline int device_property_read_u8(struct device *dev,
+					  const char *propname, u8 *val)
+{
+	return device_property_read_u8_array(dev, propname, val, 1);
+}
+
+static inline int device_property_read_u16(struct device *dev,
+					   const char *propname, u16 *val)
+{
+	return device_property_read_u16_array(dev, propname, val, 1);
+}
+
+static inline int device_property_read_u32(struct device *dev,
+					   const char *propname, u32 *val)
+{
+	return device_property_read_u32_array(dev, propname, val, 1);
+}
+
+static inline int device_property_read_u64(struct device *dev,
+					   const char *propname, u64 *val)
+{
+	return device_property_read_u64_array(dev, propname, val, 1);
+}
+
+#endif /* _LINUX_PROPERTY_H_ */
diff --git a/include/linux/pstore.h b/include/linux/pstore.h
index ece0c6bbfcc..8884f6e507f 100644
--- a/include/linux/pstore.h
+++ b/include/linux/pstore.h
@@ -39,6 +39,7 @@ enum pstore_type_id {
 	PSTORE_TYPE_PPC_RTAS	= 4,
 	PSTORE_TYPE_PPC_OF	= 5,
 	PSTORE_TYPE_PPC_COMMON	= 6,
+	PSTORE_TYPE_PMSG	= 7,
 	PSTORE_TYPE_UNKNOWN	= 255
 };
 
diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h
index 9974975d40d..712757f320a 100644
--- a/include/linux/pstore_ram.h
+++ b/include/linux/pstore_ram.h
@@ -53,7 +53,8 @@ struct persistent_ram_zone {
 };
 
 struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
-			u32 sig, struct persistent_ram_ecc_info *ecc_info);
+			u32 sig, struct persistent_ram_ecc_info *ecc_info,
+			unsigned int memtype);
 void persistent_ram_free(struct persistent_ram_zone *prz);
 void persistent_ram_zap(struct persistent_ram_zone *prz);
 
@@ -67,6 +68,8 @@ void persistent_ram_free_old(struct persistent_ram_zone *prz);
 ssize_t persistent_ram_ecc_string(struct persistent_ram_zone *prz,
 	char *str, size_t len);
 
+void ramoops_console_write_buf(const char *buf, size_t size);
+
 /*
  * Ramoops platform data
  * @mem_size	memory size for ramoops
@@ -76,9 +79,11 @@ ssize_t persistent_ram_ecc_string(struct persistent_ram_zone *prz,
 struct ramoops_platform_data {
 	unsigned long	mem_size;
 	unsigned long	mem_address;
+	unsigned int	mem_type;
 	unsigned long	record_size;
 	unsigned long	console_size;
 	unsigned long	ftrace_size;
+	unsigned long	pmsg_size;
 	int		dump_oops;
 	struct persistent_ram_ecc_info ecc_info;
 };
diff --git a/include/linux/quota.h b/include/linux/quota.h
index 80d345a3524..8b0877faa7f 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -211,8 +211,8 @@ struct mem_dqinfo {
 	unsigned long dqi_flags;
 	unsigned int dqi_bgrace;
 	unsigned int dqi_igrace;
-	qsize_t dqi_maxblimit;
-	qsize_t dqi_maxilimit;
+	qsize_t dqi_max_spc_limit;
+	qsize_t dqi_max_ino_limit;
 	void *dqi_priv;
 };
 
@@ -316,6 +316,49 @@ struct dquot_operations {
 
 struct path;
 
+/* Structure for communicating via ->get_dqblk() & ->set_dqblk() */
+struct qc_dqblk {
+	int d_fieldmask;	/* mask of fields to change in ->set_dqblk() */
+	u64 d_spc_hardlimit;	/* absolute limit on used space */
+	u64 d_spc_softlimit;	/* preferred limit on used space */
+	u64 d_ino_hardlimit;	/* maximum # allocated inodes */
+	u64 d_ino_softlimit;	/* preferred inode limit */
+	u64 d_space;		/* Space owned by the user */
+	u64 d_ino_count;	/* # inodes owned by the user */
+	s64 d_ino_timer;	/* zero if within inode limits */
+				/* if not, we refuse service */
+	s64 d_spc_timer;	/* similar to above; for space */
+	int d_ino_warns;	/* # warnings issued wrt num inodes */
+	int d_spc_warns;	/* # warnings issued wrt used space */
+	u64 d_rt_spc_hardlimit;	/* absolute limit on realtime space */
+	u64 d_rt_spc_softlimit;	/* preferred limit on RT space */
+	u64 d_rt_space;		/* realtime space owned */
+	s64 d_rt_spc_timer;	/* similar to above; for RT space */
+	int d_rt_spc_warns;	/* # warnings issued wrt RT space */
+};
+
+/* Field specifiers for ->set_dqblk() in struct qc_dqblk */
+#define	QC_INO_SOFT	(1<<0)
+#define	QC_INO_HARD	(1<<1)
+#define	QC_SPC_SOFT	(1<<2)
+#define	QC_SPC_HARD	(1<<3)
+#define	QC_RT_SPC_SOFT	(1<<4)
+#define	QC_RT_SPC_HARD	(1<<5)
+#define QC_LIMIT_MASK (QC_INO_SOFT | QC_INO_HARD | QC_SPC_SOFT | QC_SPC_HARD | \
+		       QC_RT_SPC_SOFT | QC_RT_SPC_HARD)
+#define	QC_SPC_TIMER	(1<<6)
+#define	QC_INO_TIMER	(1<<7)
+#define	QC_RT_SPC_TIMER	(1<<8)
+#define QC_TIMER_MASK (QC_SPC_TIMER | QC_INO_TIMER | QC_RT_SPC_TIMER)
+#define	QC_SPC_WARNS	(1<<9)
+#define	QC_INO_WARNS	(1<<10)
+#define	QC_RT_SPC_WARNS	(1<<11)
+#define QC_WARNS_MASK (QC_SPC_WARNS | QC_INO_WARNS | QC_RT_SPC_WARNS)
+#define	QC_SPACE	(1<<12)
+#define	QC_INO_COUNT	(1<<13)
+#define	QC_RT_SPACE	(1<<14)
+#define QC_ACCT_MASK (QC_SPACE | QC_INO_COUNT | QC_RT_SPACE)
+
 /* Operations handling requests from userspace */
 struct quotactl_ops {
 	int (*quota_on)(struct super_block *, int, int, struct path *);
@@ -324,8 +367,8 @@ struct quotactl_ops {
 	int (*quota_sync)(struct super_block *, int);
 	int (*get_info)(struct super_block *, int, struct if_dqinfo *);
 	int (*set_info)(struct super_block *, int, struct if_dqinfo *);
-	int (*get_dqblk)(struct super_block *, struct kqid, struct fs_disk_quota *);
-	int (*set_dqblk)(struct super_block *, struct kqid, struct fs_disk_quota *);
+	int (*get_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *);
+	int (*set_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *);
 	int (*get_xstate)(struct super_block *, struct fs_quota_stat *);
 	int (*set_xstate)(struct super_block *, unsigned int, int);
 	int (*get_xstatev)(struct super_block *, struct fs_quota_statv *);
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 1d3eee594cd..bfaf7138d5e 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -98,9 +98,9 @@ int dquot_quota_sync(struct super_block *sb, int type);
 int dquot_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii);
 int dquot_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii);
 int dquot_get_dqblk(struct super_block *sb, struct kqid id,
-		struct fs_disk_quota *di);
+		struct qc_dqblk *di);
 int dquot_set_dqblk(struct super_block *sb, struct kqid id,
-		struct fs_disk_quota *di);
+		struct qc_dqblk *di);
 
 int __dquot_transfer(struct inode *inode, struct dquot **transfer_to);
 int dquot_transfer(struct inode *inode, struct iattr *iattr);
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index fb298e9d6d3..84056743780 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -108,7 +108,7 @@ int rhashtable_expand(struct rhashtable *ht, gfp_t flags);
 int rhashtable_shrink(struct rhashtable *ht, gfp_t flags);
 
 void *rhashtable_lookup(const struct rhashtable *ht, const void *key);
-void *rhashtable_lookup_compare(const struct rhashtable *ht, u32 hash,
+void *rhashtable_lookup_compare(const struct rhashtable *ht, void *key,
 				bool (*compare)(void *, void *), void *arg);
 
 void rhashtable_destroy(const struct rhashtable *ht);
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index c0c2bce6b0b..d9d7e7e5635 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -37,6 +37,16 @@ struct anon_vma {
 	atomic_t refcount;
 
 	/*
+	 * Count of child anon_vmas and VMAs which points to this anon_vma.
+	 *
+	 * This counter is used for making decision about reusing anon_vma
+	 * instead of forking new one. See comments in function anon_vma_clone.
+	 */
+	unsigned degree;
+
+	struct anon_vma *parent;	/* Parent of this anon_vma */
+
+	/*
 	 * NOTE: the LSB of the rb_root.rb_node is set by
 	 * mm_take_all_locks() _after_ taking the above lock. So the
 	 * rb_root must only be read/written after taking the above lock
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5e344bbe63e..41e9b0e7c36 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1034,6 +1034,14 @@ extern void wake_up_if_idle(int cpu);
 # define SD_INIT_NAME(type)
 #endif
 
+#ifdef CONFIG_SCHED_HMP
+struct hmp_domain {
+	struct cpumask cpus;
+	struct cpumask possible_cpus;
+	struct list_head hmp_domains;
+};
+#endif /* CONFIG_SCHED_HMP */
+
 #else /* CONFIG_SMP */
 
 struct sched_domain_attr;
@@ -1081,8 +1089,33 @@ struct sched_avg {
 	u64 last_runnable_update;
 	s64 decay_count;
 	unsigned long load_avg_contrib;
+	unsigned long load_avg_ratio;
+#ifdef CONFIG_SCHED_HMP
+	u64 hmp_last_up_migration;
+	u64 hmp_last_down_migration;
+#endif
+	u32 usage_avg_sum;
 };
 
+#ifdef CONFIG_SCHED_HMP
+/*
+ * We want to avoid boosting any processes forked from init (PID 1)
+ * and kthreadd (assumed to be PID 2).
+ *
+ * System services are generally started by init, whilst kernel threads are
+ * started by kthreadd. We do not want to give those tasks a head start, as
+ * this costs power for very little benefit. We do however wish to do that for
+ * tasks which the user launches.
+ *
+ * Further, some tasks allocate per-cpu timers directly after launch which can
+ * lead to those tasks being always scheduled on a big CPU when there is no
+ * computational need to do so. Not promoting services to big CPUs on launch
+ * will prevent that unless a service allocates their per-cpu resources after
+ * a period of intense computation, which is not a common pattern.
+ */
+#define hmp_task_should_forkboost(task) ((task->parent && task->parent->pid > 2))
+#endif
+
 #ifdef CONFIG_SCHEDSTATS
 struct sched_statistics {
 	u64			wait_start;
@@ -1367,6 +1400,7 @@ struct task_struct {
 
 	cputime_t utime, stime, utimescaled, stimescaled;
 	cputime_t gtime;
+	unsigned long long cpu_power;
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	struct cputime prev_cputime;
 #endif
@@ -1895,6 +1929,9 @@ static inline cputime_t task_gtime(struct task_struct *t)
 extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
 extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
 
+extern int task_free_register(struct notifier_block *n);
+extern int task_free_unregister(struct notifier_block *n);
+
 /*
  * Per process flags
  */
diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
index 6341f5be6e2..a30b172df6e 100644
--- a/include/linux/sched/rt.h
+++ b/include/linux/sched/rt.h
@@ -18,7 +18,7 @@ static inline int rt_task(struct task_struct *p)
 #ifdef CONFIG_RT_MUTEXES
 extern int rt_mutex_getprio(struct task_struct *p);
 extern void rt_mutex_setprio(struct task_struct *p, int prio);
-extern int rt_mutex_check_prio(struct task_struct *task, int newprio);
+extern int rt_mutex_get_effective_prio(struct task_struct *task, int newprio);
 extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task);
 extern void rt_mutex_adjust_pi(struct task_struct *p);
 static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
@@ -31,9 +31,10 @@ static inline int rt_mutex_getprio(struct task_struct *p)
 	return p->normal_prio;
 }
 
-static inline int rt_mutex_check_prio(struct task_struct *task, int newprio)
+static inline int rt_mutex_get_effective_prio(struct task_struct *task,
+					      int newprio)
 {
-	return 0;
+	return newprio;
 }
 
 static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
diff --git a/include/linux/scpi_protocol.h b/include/linux/scpi_protocol.h
new file mode 100644
index 00000000000..9ac852801b1
--- /dev/null
+++ b/include/linux/scpi_protocol.h
@@ -0,0 +1,63 @@
+/*
+ * SCPI Message Protocol driver header
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/types.h>
+
+struct scpi_opp {
+	u32 freq;
+	u32 m_volt;
+} __packed;
+
+struct scpi_dvfs_info {
+	unsigned int count;
+	unsigned int latency; /* in nanoseconds */
+	struct scpi_opp *opps;
+};
+
+/**
+ * struct scpi_ops - represents the various operations provided
+ *	by SCP through SCPI message protocol
+ * @get_version: returns the major and minor revision on the SCPI
+ *	message protocol
+ * @clk_get_range: gets clock range limit(min - max in Hz)
+ * @clk_get_val: gets clock value(in Hz)
+ * @clk_set_val: sets the clock value, setting to 0 will disable the
+ *	clock (if supported)
+ * @dvfs_get_idx: gets the Operating Point of the given power domain.
+ *	OPP is an index to the list return by @dvfs_get_info
+ * @dvfs_set_idx: sets the Operating Point of the given power domain.
+ *	OPP is an index to the list return by @dvfs_get_info
+ * @dvfs_get_info: returns the DVFS capabilities of the given power
+ *	domain. It includes the OPP list and the latency information
+ */
+struct scpi_ops {
+	u32 (*get_version)(void);
+	int (*clk_get_range)(u16, unsigned long *, unsigned long *);
+	unsigned long (*clk_get_val)(u16);
+	int (*clk_set_val)(u16, unsigned long);
+	int (*dvfs_get_idx)(u8);
+	int (*dvfs_set_idx)(u8, u8);
+	struct scpi_dvfs_info *(*dvfs_get_info)(u8);
+	int (*sensor_get_id)(char *);
+	int (*sensor_get_value)(u16, u32 *);
+};
+
+#if IS_ENABLED(CONFIG_ARM_SCPI_PROTOCOL)
+struct scpi_ops *get_scpi_ops(void);
+#else
+static inline struct scpi_ops *get_scpi_ops(void) { return NULL; }
+#endif
diff --git a/include/linux/security.h b/include/linux/security.h
index ba96471c11b..d3c02ee9611 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1441,6 +1441,11 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
 struct security_operations {
 	char name[SECURITY_NAME_MAX + 1];
 
+	int (*binder_set_context_mgr) (struct task_struct *mgr);
+	int (*binder_transaction) (struct task_struct *from, struct task_struct *to);
+	int (*binder_transfer_binder) (struct task_struct *from, struct task_struct *to);
+	int (*binder_transfer_file) (struct task_struct *from, struct task_struct *to, struct file *file);
+
 	int (*ptrace_access_check) (struct task_struct *child, unsigned int mode);
 	int (*ptrace_traceme) (struct task_struct *parent);
 	int (*capget) (struct task_struct *target,
@@ -1739,6 +1744,10 @@ extern void __init security_fixup_ops(struct security_operations *ops);
 
 
 /* Security operations */
+int security_binder_set_context_mgr(struct task_struct *mgr);
+int security_binder_transaction(struct task_struct *from, struct task_struct *to);
+int security_binder_transfer_binder(struct task_struct *from, struct task_struct *to);
+int security_binder_transfer_file(struct task_struct *from, struct task_struct *to, struct file *file);
 int security_ptrace_access_check(struct task_struct *child, unsigned int mode);
 int security_ptrace_traceme(struct task_struct *parent);
 int security_capget(struct task_struct *target,
@@ -1927,6 +1936,26 @@ static inline int security_init(void)
 	return 0;
 }
 
+static inline int security_binder_set_context_mgr(struct task_struct *mgr)
+{
+	return 0;
+}
+
+static inline int security_binder_transaction(struct task_struct *from, struct task_struct *to)
+{
+	return 0;
+}
+
+static inline int security_binder_transfer_binder(struct task_struct *from, struct task_struct *to)
+{
+	return 0;
+}
+
+static inline int security_binder_transfer_file(struct task_struct *from, struct task_struct *to, struct file *file)
+{
+	return 0;
+}
+
 static inline int security_ptrace_access_check(struct task_struct *child,
 					     unsigned int mode)
 {
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 21c2e05c1bc..219b6a30d47 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -66,6 +66,7 @@ struct uart_ops {
 	void		(*set_ldisc)(struct uart_port *, int new);
 	void		(*pm)(struct uart_port *, unsigned int state,
 			      unsigned int oldstate);
+	void		(*wake_peer)(struct uart_port *);
 
 	/*
 	 * Return a string describing the type of the port
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6c8b6f604e7..522d8373170 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -772,6 +772,7 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 
 struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags,
 			    int node);
+struct sk_buff *__build_skb(void *data, unsigned int frag_size);
 struct sk_buff *build_skb(void *data, unsigned int frag_size);
 static inline struct sk_buff *alloc_skb(unsigned int size,
 					gfp_t priority)
@@ -2958,6 +2959,18 @@ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb,
  */
 #define CHECKSUM_BREAK 76
 
+/* Unset checksum-complete
+ *
+ * Unset checksum complete can be done when packet is being modified
+ * (uncompressed for instance) and checksum-complete value is
+ * invalidated.
+ */
+static inline void skb_checksum_complete_unset(struct sk_buff *skb)
+{
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->ip_summed = CHECKSUM_NONE;
+}
+
 /* Validate (init) checksum based on checksum complete.
  *
  * Return values:
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 70736b98c72..b363a0f6dfe 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -57,7 +57,7 @@ struct rpc_clnt {
 	const struct rpc_timeout *cl_timeout;	/* Timeout strategy */
 
 	int			cl_nodelen;	/* nodename length */
-	char 			cl_nodename[UNX_MAXNODENAME];
+	char 			cl_nodename[UNX_MAXNODENAME+1];
 	struct rpc_pipe_dir_head cl_pipedir_objects;
 	struct rpc_clnt *	cl_parent;	/* Points to parent of clones */
 	struct rpc_rtt		cl_rtt_default;
@@ -109,6 +109,7 @@ struct rpc_create_args {
 	struct sockaddr		*saddress;
 	const struct rpc_timeout *timeout;
 	const char		*servername;
+	const char		*nodename;
 	const struct rpc_program *program;
 	u32			prognumber;	/* overrides program->number */
 	u32			version;
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 3388c1b6f7d..16f208f40ee 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -379,6 +379,7 @@ extern bool pm_get_wakeup_count(unsigned int *count, bool block);
 extern bool pm_save_wakeup_count(unsigned int count);
 extern void pm_wakep_autosleep_enabled(bool set);
 extern void pm_print_active_wakeup_sources(void);
+extern void pm_get_active_wakeup_sources(char *pending_sources, size_t max);
 
 static inline void lock_system_sleep(void)
 {
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 6adfb7bfbf4..e288d5c016a 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -137,6 +137,8 @@ static inline void make_migration_entry_read(swp_entry_t *entry)
 	*entry = swp_entry(SWP_MIGRATION_READ, swp_offset(*entry));
 }
 
+extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
+					spinlock_t *ptl);
 extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					unsigned long address);
 extern void migration_entry_wait_huge(struct vm_area_struct *vma,
@@ -150,6 +152,8 @@ static inline int is_migration_entry(swp_entry_t swp)
 }
 #define migration_entry_to_page(swp) NULL
 static inline void make_migration_entry_read(swp_entry_t *entryp) { }
+static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
+					spinlock_t *ptl) { }
 static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					 unsigned long address) { }
 static inline void migration_entry_wait_huge(struct vm_area_struct *vma,
diff --git a/include/linux/switch.h b/include/linux/switch.h
new file mode 100644
index 00000000000..3e4c748e343
--- /dev/null
+++ b/include/linux/switch.h
@@ -0,0 +1,53 @@
+/*
+ *  Switch class driver
+ *
+ * Copyright (C) 2008 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+*/
+
+#ifndef __LINUX_SWITCH_H__
+#define __LINUX_SWITCH_H__
+
+struct switch_dev {
+	const char	*name;
+	struct device	*dev;
+	int		index;
+	int		state;
+
+	ssize_t	(*print_name)(struct switch_dev *sdev, char *buf);
+	ssize_t	(*print_state)(struct switch_dev *sdev, char *buf);
+};
+
+struct gpio_switch_platform_data {
+	const char *name;
+	unsigned 	gpio;
+
+	/* if NULL, switch_dev.name will be printed */
+	const char *name_on;
+	const char *name_off;
+	/* if NULL, "0" or "1" will be printed */
+	const char *state_on;
+	const char *state_off;
+};
+
+extern int switch_dev_register(struct switch_dev *sdev);
+extern void switch_dev_unregister(struct switch_dev *sdev);
+
+static inline int switch_get_state(struct switch_dev *sdev)
+{
+	return sdev->state;
+}
+
+extern void switch_set_state(struct switch_dev *sdev, int state);
+
+#endif /* __LINUX_SWITCH_H__ */
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index ef90838b36a..037e9df2f61 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -29,16 +29,19 @@
 #include <linux/idr.h>
 #include <linux/device.h>
 #include <linux/workqueue.h>
+#include <uapi/linux/thermal.h>
 
 #define THERMAL_TRIPS_NONE	-1
 #define THERMAL_MAX_TRIPS	12
-#define THERMAL_NAME_LENGTH	20
 
 /* invalid cooling state */
 #define THERMAL_CSTATE_INVALID -1UL
 
 /* No upper/lower limit requirement */
-#define THERMAL_NO_LIMIT	THERMAL_CSTATE_INVALID
+#define THERMAL_NO_LIMIT	((u32)~0)
+
+/* Default weight of a bound cooling device */
+#define THERMAL_WEIGHT_DEFAULT 0
 
 /* Unit conversion macros */
 #define KELVIN_TO_CELSIUS(t)	(long)(((long)t-2732 >= 0) ?	\
@@ -49,11 +52,6 @@
 #define MILLICELSIUS_TO_DECI_KELVIN_WITH_OFFSET(t, off) (((t) / 100) + (off))
 #define MILLICELSIUS_TO_DECI_KELVIN(t) MILLICELSIUS_TO_DECI_KELVIN_WITH_OFFSET(t, 2732)
 
-/* Adding event notification support elements */
-#define THERMAL_GENL_FAMILY_NAME                "thermal_event"
-#define THERMAL_GENL_VERSION                    0x01
-#define THERMAL_GENL_MCAST_GROUP_NAME           "thermal_mc_grp"
-
 /* Default Thermal Governor */
 #if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE)
 #define DEFAULT_THERMAL_GOVERNOR       "step_wise"
@@ -61,10 +59,13 @@
 #define DEFAULT_THERMAL_GOVERNOR       "fair_share"
 #elif defined(CONFIG_THERMAL_DEFAULT_GOV_USER_SPACE)
 #define DEFAULT_THERMAL_GOVERNOR       "user_space"
+#elif defined(CONFIG_THERMAL_DEFAULT_GOV_POWER_ALLOCATOR)
+#define DEFAULT_THERMAL_GOVERNOR       "power_allocator"
 #endif
 
 struct thermal_zone_device;
 struct thermal_cooling_device;
+struct thermal_instance;
 
 enum thermal_device_mode {
 	THERMAL_DEVICE_DISABLED = 0,
@@ -86,30 +87,6 @@ enum thermal_trend {
 	THERMAL_TREND_DROP_FULL, /* apply lowest cooling action */
 };
 
-/* Events supported by Thermal Netlink */
-enum events {
-	THERMAL_AUX0,
-	THERMAL_AUX1,
-	THERMAL_CRITICAL,
-	THERMAL_DEV_FAULT,
-};
-
-/* attributes of thermal_genl_family */
-enum {
-	THERMAL_GENL_ATTR_UNSPEC,
-	THERMAL_GENL_ATTR_EVENT,
-	__THERMAL_GENL_ATTR_MAX,
-};
-#define THERMAL_GENL_ATTR_MAX (__THERMAL_GENL_ATTR_MAX - 1)
-
-/* commands supported by the thermal_genl_family */
-enum {
-	THERMAL_GENL_CMD_UNSPEC,
-	THERMAL_GENL_CMD_EVENT,
-	__THERMAL_GENL_CMD_MAX,
-};
-#define THERMAL_GENL_CMD_MAX (__THERMAL_GENL_CMD_MAX - 1)
-
 struct thermal_zone_device_ops {
 	int (*bind) (struct thermal_zone_device *,
 		     struct thermal_cooling_device *);
@@ -142,6 +119,12 @@ struct thermal_cooling_device_ops {
 	int (*get_max_state) (struct thermal_cooling_device *, unsigned long *);
 	int (*get_cur_state) (struct thermal_cooling_device *, unsigned long *);
 	int (*set_cur_state) (struct thermal_cooling_device *, unsigned long);
+	int (*get_requested_power)(struct thermal_cooling_device *,
+				   struct thermal_zone_device *, u32 *);
+	int (*state2power)(struct thermal_cooling_device *,
+			   struct thermal_zone_device *, unsigned long, u32 *);
+	int (*power2state)(struct thermal_cooling_device *,
+			   struct thermal_zone_device *, u32, unsigned long *);
 };
 
 struct thermal_cooling_device {
@@ -173,8 +156,7 @@ struct thermal_attr {
  * @devdata:	private pointer for device private data
  * @trips:	number of trip points the thermal zone supports
  * @passive_delay:	number of milliseconds to wait between polls when
- *			performing passive cooling.  Currenty only used by the
- *			step-wise governor
+ *			performing passive cooling.
  * @polling_delay:	number of milliseconds to wait between polls when
  *			checking whether trip points have been crossed (0 for
  *			interrupt driven systems)
@@ -184,13 +166,13 @@ struct thermal_attr {
  * @last_temperature:	previous temperature read
  * @emul_temperature:	emulated temperature when using CONFIG_THERMAL_EMULATION
  * @passive:		1 if you've crossed a passive trip point, 0 otherwise.
- *			Currenty only used by the step-wise governor.
  * @forced_passive:	If > 0, temperature at which to switch on all ACPI
  *			processor cooling devices.  Currently only used by the
  *			step-wise governor.
  * @ops:	operations this &thermal_zone_device supports
  * @tzp:	thermal zone parameters
  * @governor:	pointer to the governor for this thermal zone
+ * @governor_data:	private pointer for governor data
  * @thermal_instances:	list of &struct thermal_instance of this thermal zone
  * @idr:	&struct idr to generate unique id for this zone's cooling
  *		devices
@@ -215,8 +197,9 @@ struct thermal_zone_device {
 	int passive;
 	unsigned int forced_passive;
 	struct thermal_zone_device_ops *ops;
-	const struct thermal_zone_params *tzp;
+	struct thermal_zone_params *tzp;
 	struct thermal_governor *governor;
+	void *governor_data;
 	struct list_head thermal_instances;
 	struct idr idr;
 	struct mutex lock;
@@ -227,12 +210,19 @@ struct thermal_zone_device {
 /**
  * struct thermal_governor - structure that holds thermal governor information
  * @name:	name of the governor
+ * @bind_to_tz: callback called when binding to a thermal zone.  If it
+ *		returns 0, the governor is bound to the thermal zone,
+ *		otherwise it fails.
+ * @unbind_from_tz:	callback called when a governor is unbound from a
+ *			thermal zone.
  * @throttle:	callback called for every trip point even if temperature is
  *		below the trip point temperature
  * @governor_list:	node in thermal_governor_list (in thermal_core.c)
  */
 struct thermal_governor {
 	char name[THERMAL_NAME_LENGTH];
+	int (*bind_to_tz)(struct thermal_zone_device *tz);
+	void (*unbind_from_tz)(struct thermal_zone_device *tz);
 	int (*throttle)(struct thermal_zone_device *tz, int trip);
 	struct list_head	governor_list;
 };
@@ -243,9 +233,12 @@ struct thermal_bind_params {
 
 	/*
 	 * This is a measure of 'how effectively these devices can
-	 * cool 'this' thermal zone. The shall be determined by platform
-	 * characterization. This is on a 'percentage' scale.
-	 * See Documentation/thermal/sysfs-api.txt for more information.
+	 * cool 'this' thermal zone. It shall be determined by
+	 * platform characterization. This value is relative to the
+	 * rest of the weights so a cooling device whose weight is
+	 * double that of another cooling device is twice as
+	 * effective. See Documentation/thermal/sysfs-api.txt for more
+	 * information.
 	 */
 	int weight;
 
@@ -282,6 +275,44 @@ struct thermal_zone_params {
 
 	int num_tbps;	/* Number of tbp entries */
 	struct thermal_bind_params *tbp;
+
+	/*
+	 * Sustainable power (heat) that this thermal zone can dissipate in
+	 * mW
+	 */
+	u32 sustainable_power;
+
+	/*
+	 * Proportional parameter of the PID controller when
+	 * overshooting (i.e., when temperature is below the target)
+	 */
+	s32 k_po;
+
+	/*
+	 * Proportional parameter of the PID controller when
+	 * undershooting
+	 */
+	s32 k_pu;
+
+	/* Integral parameter of the PID controller */
+	s32 k_i;
+
+	/* Derivative parameter of the PID controller */
+	s32 k_d;
+
+	/* threshold below which the error is no longer accumulated */
+	s32 integral_cutoff;
+
+	/*
+	 * @slope:	slope of a linear temperature adjustment curve.
+	 * 		Used by thermal zone drivers.
+	 */
+	int slope;
+	/*
+	 * @offset:	offset of a linear temperature adjustment curve.
+	 * 		Used by thermal zone drivers (default 0).
+	 */
+	int offset;
 };
 
 struct thermal_genl_event {
@@ -289,19 +320,49 @@ struct thermal_genl_event {
 	enum events event;
 };
 
+/**
+ * struct thermal_zone_of_device_ops - scallbacks for handling DT based zones
+ *
+ * Mandatory:
+ * @get_temp: a pointer to a function that reads the sensor temperature.
+ *
+ * Optional:
+ * @get_trend: a pointer to a function that reads the sensor temperature trend.
+ * @set_emul_temp: a pointer to a function that sets sensor emulated
+ *		   temperature.
+ */
+struct thermal_zone_of_device_ops {
+	int (*get_temp)(void *, long *);
+	int (*get_trend)(void *, long *);
+	int (*set_emul_temp)(void *, unsigned long);
+};
+
+/**
+ * struct thermal_trip - representation of a point in temperature domain
+ * @np: pointer to struct device_node that this trip point was created from
+ * @temperature: temperature value in miliCelsius
+ * @hysteresis: relative hysteresis in miliCelsius
+ * @type: trip point type
+ */
+
+struct thermal_trip {
+	struct device_node *np;
+	unsigned long int temperature;
+	unsigned long int hysteresis;
+	enum thermal_trip_type type;
+};
+
 /* Function declarations */
 #ifdef CONFIG_THERMAL_OF
 struct thermal_zone_device *
-thermal_zone_of_sensor_register(struct device *dev, int id,
-				void *data, int (*get_temp)(void *, long *),
-				int (*get_trend)(void *, long *));
+thermal_zone_of_sensor_register(struct device *dev, int id, void *data,
+				const struct thermal_zone_of_device_ops *ops);
 void thermal_zone_of_sensor_unregister(struct device *dev,
 				       struct thermal_zone_device *tz);
 #else
 static inline struct thermal_zone_device *
-thermal_zone_of_sensor_register(struct device *dev, int id,
-				void *data, int (*get_temp)(void *, long *),
-				int (*get_trend)(void *, long *))
+thermal_zone_of_sensor_register(struct device *dev, int id, void *data,
+				const struct thermal_zone_of_device_ops *ops)
 {
 	return NULL;
 }
@@ -313,14 +374,27 @@ void thermal_zone_of_sensor_unregister(struct device *dev,
 }
 
 #endif
+
+#if IS_ENABLED(CONFIG_THERMAL)
+static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev)
+{
+	return cdev->ops->get_requested_power && cdev->ops->state2power &&
+		cdev->ops->power2state;
+}
+
+int power_actor_get_max_power(struct thermal_cooling_device *,
+			      struct thermal_zone_device *tz, u32 *max_power);
+int power_actor_set_power(struct thermal_cooling_device *,
+			  struct thermal_instance *, u32);
 struct thermal_zone_device *thermal_zone_device_register(const char *, int, int,
 		void *, struct thermal_zone_device_ops *,
-		const struct thermal_zone_params *, int, int);
+		struct thermal_zone_params *, int, int);
 void thermal_zone_device_unregister(struct thermal_zone_device *);
 
 int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int,
 				     struct thermal_cooling_device *,
-				     unsigned long, unsigned long);
+				     unsigned long, unsigned long,
+				     unsigned int);
 int thermal_zone_unbind_cooling_device(struct thermal_zone_device *, int,
 				       struct thermal_cooling_device *);
 void thermal_zone_device_update(struct thermal_zone_device *);
@@ -339,8 +413,66 @@ struct thermal_instance *get_thermal_instance(struct thermal_zone_device *,
 		struct thermal_cooling_device *, int);
 void thermal_cdev_update(struct thermal_cooling_device *);
 void thermal_notify_framework(struct thermal_zone_device *, int);
-
-#ifdef CONFIG_NET
+#else
+static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev)
+{ return false; }
+static inline int power_actor_get_max_power(struct thermal_cooling_device *cdev,
+			      struct thermal_zone_device *tz, u32 *max_power)
+{ return 0; }
+static inline int power_actor_set_power(struct thermal_cooling_device *cdev,
+			  struct thermal_instance *tz, u32 power)
+{ return 0; }
+static inline struct thermal_zone_device *thermal_zone_device_register(
+	const char *type, int trips, int mask, void *devdata,
+	struct thermal_zone_device_ops *ops,
+	const struct thermal_zone_params *tzp,
+	int passive_delay, int polling_delay)
+{ return ERR_PTR(-ENODEV); }
+static inline void thermal_zone_device_unregister(
+	struct thermal_zone_device *tz)
+{ }
+static inline int thermal_zone_bind_cooling_device(
+	struct thermal_zone_device *tz, int trip,
+	struct thermal_cooling_device *cdev,
+	unsigned long upper, unsigned long lower)
+{ return -ENODEV; }
+static inline int thermal_zone_unbind_cooling_device(
+	struct thermal_zone_device *tz, int trip,
+	struct thermal_cooling_device *cdev)
+{ return -ENODEV; }
+static inline void thermal_zone_device_update(struct thermal_zone_device *tz)
+{ }
+static inline struct thermal_cooling_device *
+thermal_cooling_device_register(char *type, void *devdata,
+	const struct thermal_cooling_device_ops *ops)
+{ return ERR_PTR(-ENODEV); }
+static inline struct thermal_cooling_device *
+thermal_of_cooling_device_register(struct device_node *np,
+	char *type, void *devdata, const struct thermal_cooling_device_ops *ops)
+{ return ERR_PTR(-ENODEV); }
+static inline void thermal_cooling_device_unregister(
+	struct thermal_cooling_device *cdev)
+{ }
+static inline struct thermal_zone_device *thermal_zone_get_zone_by_name(
+		const char *name)
+{ return ERR_PTR(-ENODEV); }
+static inline int thermal_zone_get_temp(
+		struct thermal_zone_device *tz, unsigned long *temp)
+{ return -ENODEV; }
+static inline int get_tz_trend(struct thermal_zone_device *tz, int trip)
+{ return -ENODEV; }
+static inline struct thermal_instance *
+get_thermal_instance(struct thermal_zone_device *tz,
+	struct thermal_cooling_device *cdev, int trip)
+{ return ERR_PTR(-ENODEV); }
+static inline void thermal_cdev_update(struct thermal_cooling_device *cdev)
+{ }
+static inline void thermal_notify_framework(struct thermal_zone_device *tz,
+	int trip)
+{ }
+#endif /* CONFIG_THERMAL */
+
+#if defined(CONFIG_NET) && IS_ENABLED(CONFIG_THERMAL)
 extern int thermal_generate_netlink_event(struct thermal_zone_device *tz,
 						enum events event);
 #else
diff --git a/include/linux/time.h b/include/linux/time.h
index 8c42cf8d244..5989b0ead1e 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -99,6 +99,19 @@ static inline bool timespec_valid_strict(const struct timespec *ts)
 	return true;
 }
 
+static inline bool timeval_valid(const struct timeval *tv)
+{
+	/* Dates before 1970 are bogus */
+	if (tv->tv_sec < 0)
+		return false;
+
+	/* Can't have more microseconds then a second */
+	if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC)
+		return false;
+
+	return true;
+}
+
 extern struct timespec timespec_trunc(struct timespec t, unsigned gran);
 
 #define CURRENT_TIME		(current_kernel_time())
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index e08e21e5f60..c72851328ca 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -173,7 +173,7 @@ extern void syscall_unregfunc(void);
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
 				TP_CONDITION(cond),,);			\
-		if (IS_ENABLED(CONFIG_LOCKDEP)) {			\
+		if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) {		\
 			rcu_read_lock_sched_notrace();			\
 			rcu_dereference_sched(__tracepoint_##name.funcs);\
 			rcu_read_unlock_sched_notrace();		\
diff --git a/include/linux/uid_stat.h b/include/linux/uid_stat.h
new file mode 100644
index 00000000000..6bd6c4e52d1
--- /dev/null
+++ b/include/linux/uid_stat.h
@@ -0,0 +1,29 @@
+/* include/linux/uid_stat.h
+ *
+ * Copyright (C) 2008-2009 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __uid_stat_h
+#define __uid_stat_h
+
+/* Contains definitions for resource tracking per uid. */
+
+#ifdef CONFIG_UID_STAT
+int uid_stat_tcp_snd(uid_t uid, int size);
+int uid_stat_tcp_rcv(uid_t uid, int size);
+#else
+#define uid_stat_tcp_snd(uid, size) do {} while (0);
+#define uid_stat_tcp_rcv(uid, size) do {} while (0);
+#endif
+
+#endif /* _LINUX_UID_STAT_H */
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 447a7e2fc19..bdbd19fb1ff 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -127,10 +127,6 @@ enum usb_interface_condition {
  *	to the sysfs representation for that device.
  * @pm_usage_cnt: PM usage counter for this interface
  * @reset_ws: Used for scheduling resets from atomic context.
- * @reset_running: set to 1 if the interface is currently running a
- *      queued reset so that usb_cancel_queued_reset() doesn't try to
- *      remove from the workqueue when running inside the worker
- *      thread. See __usb_queue_reset_device().
  * @resetting_device: USB core reset the device, so use alt setting 0 as
  *	current; needs bandwidth alloc after reset.
  *
@@ -181,7 +177,6 @@ struct usb_interface {
 	unsigned needs_remote_wakeup:1;	/* driver requires remote wakeup */
 	unsigned needs_altsetting0:1;	/* switch to altsetting 0 is pending */
 	unsigned needs_binding:1;	/* needs delayed unbind/rebind */
-	unsigned reset_running:1;
 	unsigned resetting_device:1;	/* true: bandwidth alloc after reset */
 
 	struct device dev;		/* interface specific device info */
@@ -210,6 +205,32 @@ void usb_put_intf(struct usb_interface *intf);
 #define USB_MAXINTERFACES	32
 #define USB_MAXIADS		(USB_MAXINTERFACES/2)
 
+/*
+ * USB Resume Timer: Every Host controller driver should drive the resume
+ * signalling on the bus for the amount of time defined by this macro.
+ *
+ * That way we will have a 'stable' behavior among all HCDs supported by Linux.
+ *
+ * Note that the USB Specification states we should drive resume for *at least*
+ * 20 ms, but it doesn't give an upper bound. This creates two possible
+ * situations which we want to avoid:
+ *
+ * (a) sometimes an msleep(20) might expire slightly before 20 ms, which causes
+ * us to fail USB Electrical Tests, thus failing Certification
+ *
+ * (b) Some (many) devices actually need more than 20 ms of resume signalling,
+ * and while we can argue that's against the USB Specification, we don't have
+ * control over which devices a certification laboratory will be using for
+ * certification. If CertLab uses a device which was tested against Windows and
+ * that happens to have relaxed resume signalling rules, we might fall into
+ * situations where we fail interoperability and electrical tests.
+ *
+ * In order to avoid both conditions, we're using a 40 ms resume timeout, which
+ * should cope with both LPJ calibration errors and devices not following every
+ * detail of the USB Specification.
+ */
+#define USB_RESUME_TIMEOUT	40 /* ms */
+
 /**
  * struct usb_interface_cache - long-term representation of a device interface
  * @num_altsetting: number of altsettings defined.
diff --git a/include/linux/usb/class-dual-role.h b/include/linux/usb/class-dual-role.h
new file mode 100644
index 00000000000..af42ed34944
--- /dev/null
+++ b/include/linux/usb/class-dual-role.h
@@ -0,0 +1,128 @@
+#ifndef __LINUX_CLASS_DUAL_ROLE_H__
+#define __LINUX_CLASS_DUAL_ROLE_H__
+
+#include <linux/workqueue.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+
+struct device;
+
+enum dual_role_supported_modes {
+	DUAL_ROLE_SUPPORTED_MODES_DFP_AND_UFP = 0,
+	DUAL_ROLE_SUPPORTED_MODES_DFP,
+	DUAL_ROLE_SUPPORTED_MODES_UFP,
+/*The following should be the last element*/
+	DUAL_ROLE_PROP_SUPPORTED_MODES_TOTAL,
+};
+
+enum {
+	DUAL_ROLE_PROP_MODE_UFP = 0,
+	DUAL_ROLE_PROP_MODE_DFP,
+	DUAL_ROLE_PROP_MODE_NONE,
+/*The following should be the last element*/
+	DUAL_ROLE_PROP_MODE_TOTAL,
+};
+
+enum {
+	DUAL_ROLE_PROP_PR_SRC = 0,
+	DUAL_ROLE_PROP_PR_SNK,
+	DUAL_ROLE_PROP_PR_NONE,
+/*The following should be the last element*/
+	DUAL_ROLE_PROP_PR_TOTAL,
+
+};
+
+enum {
+	DUAL_ROLE_PROP_DR_HOST = 0,
+	DUAL_ROLE_PROP_DR_DEVICE,
+	DUAL_ROLE_PROP_DR_NONE,
+/*The following should be the last element*/
+	DUAL_ROLE_PROP_DR_TOTAL,
+};
+
+enum {
+	DUAL_ROLE_PROP_VCONN_SUPPLY_NO = 0,
+	DUAL_ROLE_PROP_VCONN_SUPPLY_YES,
+/*The following should be the last element*/
+	DUAL_ROLE_PROP_VCONN_SUPPLY_TOTAL,
+};
+
+enum dual_role_property {
+	DUAL_ROLE_PROP_SUPPORTED_MODES = 0,
+	DUAL_ROLE_PROP_MODE,
+	DUAL_ROLE_PROP_PR,
+	DUAL_ROLE_PROP_DR,
+	DUAL_ROLE_PROP_VCONN_SUPPLY,
+};
+
+struct dual_role_phy_instance;
+
+/* Description of typec port */
+struct dual_role_phy_desc {
+	/* /sys/class/dual_role_usb/<name>/ */
+	const char *name;
+	enum dual_role_supported_modes supported_modes;
+	enum dual_role_property *properties;
+	size_t num_properties;
+
+	/* Callback for "cat /sys/class/dual_role_usb/<name>/<property>" */
+	int (*get_property)(struct dual_role_phy_instance *dual_role,
+			     enum dual_role_property prop,
+			     unsigned int *val);
+	/* Callback for "echo <value> >
+	 *                      /sys/class/dual_role_usb/<name>/<property>" */
+	int (*set_property)(struct dual_role_phy_instance *dual_role,
+			     enum dual_role_property prop,
+			     const unsigned int *val);
+	/* Decides whether userspace can change a specific property */
+	int (*property_is_writeable)(struct dual_role_phy_instance *dual_role,
+				      enum dual_role_property prop);
+};
+
+struct dual_role_phy_instance {
+	const struct dual_role_phy_desc *desc;
+
+	/* Driver private data */
+	void *drv_data;
+
+	struct device dev;
+	struct work_struct changed_work;
+};
+
+#if IS_ENABLED(CONFIG_DUAL_ROLE_USB_INTF)
+extern void dual_role_instance_changed(struct dual_role_phy_instance
+				       *dual_role);
+extern struct dual_role_phy_instance *__must_check
+devm_dual_role_instance_register(struct device *parent,
+				 const struct dual_role_phy_desc *desc);
+extern void devm_dual_role_instance_unregister(struct device *dev,
+					       struct dual_role_phy_instance
+					       *dual_role);
+extern int dual_role_get_property(struct dual_role_phy_instance *dual_role,
+				  enum dual_role_property prop,
+				  unsigned int *val);
+extern int dual_role_set_property(struct dual_role_phy_instance *dual_role,
+				  enum dual_role_property prop,
+				  const unsigned int *val);
+extern int dual_role_property_is_writeable(struct dual_role_phy_instance
+					   *dual_role,
+					   enum dual_role_property prop);
+extern void *dual_role_get_drvdata(struct dual_role_phy_instance *dual_role);
+#else /* CONFIG_DUAL_ROLE_USB_INTF */
+static void dual_role_instance_changed(struct dual_role_phy_instance
+				       *dual_role){}
+static struct dual_role_phy_instance *__must_check
+devm_dual_role_instance_register(struct device *parent,
+				 const struct dual_role_phy_desc *desc)
+{
+	return ERR_PTR(-ENOSYS);
+}
+static void devm_dual_role_instance_unregister(struct device *dev,
+					       struct dual_role_phy_instance
+					       *dual_role){}
+static void *dual_role_get_drvdata(struct dual_role_phy_instance *dual_role)
+{
+	return ERR_PTR(-ENOSYS);
+}
+#endif /* CONFIG_DUAL_ROLE_USB_INTF */
+#endif /* __LINUX_CLASS_DUAL_ROLE_H__ */
diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h
index c330f5ef42c..6380a0e4001 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -562,6 +562,7 @@ struct usb_function_instance {
 	struct config_group group;
 	struct list_head cfs_list;
 	struct usb_function_driver *fd;
+	struct usb_function *f;
 	int (*set_inst_name)(struct usb_function_instance *inst,
 			      const char *name);
 	void (*free_func_inst)(struct usb_function_instance *inst);
diff --git a/include/linux/usb/f_accessory.h b/include/linux/usb/f_accessory.h
new file mode 100644
index 00000000000..ebe3c4d5930
--- /dev/null
+++ b/include/linux/usb/f_accessory.h
@@ -0,0 +1,23 @@
+/*
+ * Gadget Function Driver for Android USB accessories
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __LINUX_USB_F_ACCESSORY_H
+#define __LINUX_USB_F_ACCESSORY_H
+
+#include <uapi/linux/usb/f_accessory.h>
+
+#endif /* __LINUX_USB_F_ACCESSORY_H */
diff --git a/include/linux/usb/f_mtp.h b/include/linux/usb/f_mtp.h
new file mode 100644
index 00000000000..4e8417791be
--- /dev/null
+++ b/include/linux/usb/f_mtp.h
@@ -0,0 +1,23 @@
+/*
+ * Gadget Function Driver for MTP
+ *
+ * Copyright (C) 2010 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __LINUX_USB_F_MTP_H
+#define __LINUX_USB_F_MTP_H
+
+#include <uapi/linux/usb/f_mtp.h>
+
+#endif /* __LINUX_USB_F_MTP_H */
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index cd96a2bc338..2f48e1756cb 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -146,6 +146,8 @@ struct usb_hcd {
 	unsigned		amd_resume_bug:1; /* AMD remote wakeup quirk */
 	unsigned		can_do_streams:1; /* HC supports streams */
 	unsigned		tpl_support:1; /* OTG & EH TPL support */
+	unsigned		cant_recv_wakeups:1;
+			/* wakeup requests from downstream aren't received */
 
 	unsigned int		irq;		/* irq allocated */
 	void __iomem		*regs;		/* device memory/io */
@@ -450,6 +452,7 @@ extern const struct dev_pm_ops usb_hcd_pci_pm_ops;
 #endif /* CONFIG_PCI */
 
 /* pci-ish (pdev null is ok) buffer alloc/mapping support */
+void usb_init_pool_max(void);
 int hcd_buffer_create(struct usb_hcd *hcd);
 void hcd_buffer_destroy(struct usb_hcd *hcd);
 
diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index 9bb547c7bce..704a1ab8240 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -190,8 +190,7 @@ static inline void usb_set_serial_data(struct usb_serial *serial, void *data)
  * @num_ports: the number of different ports this device will have.
  * @bulk_in_size: minimum number of bytes to allocate for bulk-in buffer
  *	(0 = end-point size)
- * @bulk_out_size: minimum number of bytes to allocate for bulk-out buffer
- *	(0 = end-point size)
+ * @bulk_out_size: bytes to allocate for bulk-out buffer (0 = end-point size)
  * @calc_num_ports: pointer to a function to determine how many ports this
  *	device has dynamically.  It will be called after the probe()
  *	callback is called, but before attach()
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index d9a4905e01d..6e0ce8c7b8c 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -227,9 +227,23 @@ struct skb_data {	/* skb->cb is one of these */
 	struct urb		*urb;
 	struct usbnet		*dev;
 	enum skb_state		state;
-	size_t			length;
+	long			length;
+	unsigned long		packets;
 };
 
+/* Drivers that set FLAG_MULTI_PACKET must call this in their
+ * tx_fixup method before returning an skb.
+ */
+static inline void
+usbnet_set_skb_tx_stats(struct sk_buff *skb,
+			unsigned long packets, long bytes_delta)
+{
+	struct skb_data *entry = (struct skb_data *) skb->cb;
+
+	entry->packets = packets;
+	entry->length = bytes_delta;
+}
+
 extern int usbnet_open(struct net_device *net);
 extern int usbnet_stop(struct net_device *net);
 extern netdev_tx_t usbnet_start_xmit(struct sk_buff *skb,
diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h
index a7f2604c5f2..7f5f78bd15a 100644
--- a/include/linux/usb_usual.h
+++ b/include/linux/usb_usual.h
@@ -77,6 +77,8 @@
 		/* Cannot handle ATA_12 or ATA_16 CDBs */	\
 	US_FLAG(NO_REPORT_OPCODES,	0x04000000)		\
 		/* Cannot handle MI_REPORT_SUPPORTED_OPERATION_CODES */	\
+	US_FLAG(MAX_SECTORS_240,	0x08000000)		\
+		/* Sets max_sectors to 240 */			\
 
 #define US_FLAG(name, value)	US_FL_##name = value ,
 enum { US_DO_ALL_FLAGS };
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index e95372654f0..9f3579ff543 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -17,6 +17,10 @@ struct uid_gid_map {	/* 64 bytes -- 1 cache line */
 	} extent[UID_GID_MAP_MAX_EXTENTS];
 };
 
+#define USERNS_SETGROUPS_ALLOWED 1UL
+
+#define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED
+
 struct user_namespace {
 	struct uid_gid_map	uid_map;
 	struct uid_gid_map	gid_map;
@@ -27,6 +31,7 @@ struct user_namespace {
 	kuid_t			owner;
 	kgid_t			group;
 	unsigned int		proc_inum;
+	unsigned long		flags;
 
 	/* Register of per-UID persistent keyrings for this namespace */
 #ifdef CONFIG_PERSISTENT_KEYRINGS
@@ -63,6 +68,9 @@ extern const struct seq_operations proc_projid_seq_operations;
 extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *);
+extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *);
+extern int proc_setgroups_show(struct seq_file *m, void *v);
+extern bool userns_may_setgroups(const struct user_namespace *ns);
 #else
 
 static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
@@ -87,6 +95,10 @@ static inline void put_user_ns(struct user_namespace *ns)
 {
 }
 
+static inline bool userns_may_setgroups(const struct user_namespace *ns)
+{
+	return true;
+}
 #endif
 
 #endif /* _LINUX_USER_H */
diff --git a/include/linux/wait.h b/include/linux/wait.h
index e4a8eb9312e..fc0e99395fb 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -13,9 +13,12 @@ typedef struct __wait_queue wait_queue_t;
 typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key);
 int default_wake_function(wait_queue_t *wait, unsigned mode, int flags, void *key);
 
+/* __wait_queue::flags */
+#define WQ_FLAG_EXCLUSIVE	0x01
+#define WQ_FLAG_WOKEN		0x02
+
 struct __wait_queue {
 	unsigned int		flags;
-#define WQ_FLAG_EXCLUSIVE	0x01
 	void			*private;
 	wait_queue_func_t	func;
 	struct list_head	task_list;
@@ -830,6 +833,8 @@ void prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int sta
 long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state);
 void finish_wait(wait_queue_head_t *q, wait_queue_t *wait);
 void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, unsigned int mode, void *key);
+long wait_woken(wait_queue_t *wait, unsigned mode, long timeout);
+int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 
diff --git a/include/linux/wakelock.h b/include/linux/wakelock.h
new file mode 100644
index 00000000000..f4a698a2288
--- /dev/null
+++ b/include/linux/wakelock.h
@@ -0,0 +1,67 @@
+/* include/linux/wakelock.h
+ *
+ * Copyright (C) 2007-2012 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_WAKELOCK_H
+#define _LINUX_WAKELOCK_H
+
+#include <linux/ktime.h>
+#include <linux/device.h>
+
+/* A wake_lock prevents the system from entering suspend or other low power
+ * states when active. If the type is set to WAKE_LOCK_SUSPEND, the wake_lock
+ * prevents a full system suspend.
+ */
+
+enum {
+	WAKE_LOCK_SUSPEND, /* Prevent suspend */
+	WAKE_LOCK_TYPE_COUNT
+};
+
+struct wake_lock {
+	struct wakeup_source ws;
+};
+
+static inline void wake_lock_init(struct wake_lock *lock, int type,
+				  const char *name)
+{
+	wakeup_source_init(&lock->ws, name);
+}
+
+static inline void wake_lock_destroy(struct wake_lock *lock)
+{
+	wakeup_source_trash(&lock->ws);
+}
+
+static inline void wake_lock(struct wake_lock *lock)
+{
+	__pm_stay_awake(&lock->ws);
+}
+
+static inline void wake_lock_timeout(struct wake_lock *lock, long timeout)
+{
+	__pm_wakeup_event(&lock->ws, jiffies_to_msecs(timeout));
+}
+
+static inline void wake_unlock(struct wake_lock *lock)
+{
+	__pm_relax(&lock->ws);
+}
+
+static inline int wake_lock_active(struct wake_lock *lock)
+{
+	return lock->ws.active;
+}
+
+#endif
diff --git a/include/linux/wakeup_reason.h b/include/linux/wakeup_reason.h
new file mode 100644
index 00000000000..ad8b76936c7
--- /dev/null
+++ b/include/linux/wakeup_reason.h
@@ -0,0 +1,27 @@
+/*
+ * include/linux/wakeup_reason.h
+ *
+ * Logs the reason which caused the kernel to resume
+ * from the suspend mode.
+ *
+ * Copyright (C) 2014 Google, Inc.
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _LINUX_WAKEUP_REASON_H
+#define _LINUX_WAKEUP_REASON_H
+
+#define MAX_SUSPEND_ABORT_LEN 256
+
+void log_wakeup_reason(int irq);
+void log_suspend_abort_reason(const char *fmt, ...);
+int check_wakeup_reason(int irq);
+
+#endif /* _LINUX_WAKEUP_REASON_H */
diff --git a/include/linux/wifi_tiwlan.h b/include/linux/wifi_tiwlan.h
new file mode 100644
index 00000000000..f07e0679fb8
--- /dev/null
+++ b/include/linux/wifi_tiwlan.h
@@ -0,0 +1,27 @@
+/* include/linux/wifi_tiwlan.h
+ *
+ * Copyright (C) 2008 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+#ifndef _LINUX_WIFI_TIWLAN_H_
+#define _LINUX_WIFI_TIWLAN_H_
+
+#include <linux/wlan_plat.h>
+
+#define WMPA_NUMBER_OF_SECTIONS	3
+#define WMPA_NUMBER_OF_BUFFERS	160
+#define WMPA_SECTION_HEADER	24
+#define WMPA_SECTION_SIZE_0	(WMPA_NUMBER_OF_BUFFERS * 64)
+#define WMPA_SECTION_SIZE_1	(WMPA_NUMBER_OF_BUFFERS * 256)
+#define WMPA_SECTION_SIZE_2	(WMPA_NUMBER_OF_BUFFERS * 2048)
+
+#endif
diff --git a/include/linux/wlan_plat.h b/include/linux/wlan_plat.h
new file mode 100644
index 00000000000..8e8b06f1ba4
--- /dev/null
+++ b/include/linux/wlan_plat.h
@@ -0,0 +1,30 @@
+/* include/linux/wlan_plat.h
+ *
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+#ifndef _LINUX_WLAN_PLAT_H_
+#define _LINUX_WLAN_PLAT_H_
+
+#define WLAN_PLAT_NODFS_FLAG	0x01
+
+struct wifi_platform_data {
+	int (*set_power)(int val);
+	int (*set_reset)(int val);
+	int (*set_carddetect)(int val);
+	void *(*mem_prealloc)(int section, unsigned long size);
+	int (*get_mac_addr)(unsigned char *buf);
+	int (*get_wake_irq)(void);
+	void *(*get_country_code)(char *ccode, u32 flags);
+};
+
+#endif
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index b996e6cde6b..9eb54f41623 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -70,7 +70,8 @@ enum {
 	/* data contains off-queue information when !WORK_STRUCT_PWQ */
 	WORK_OFFQ_FLAG_BASE	= WORK_STRUCT_COLOR_SHIFT,
 
-	WORK_OFFQ_CANCELING	= (1 << WORK_OFFQ_FLAG_BASE),
+	__WORK_OFFQ_CANCELING	= WORK_OFFQ_FLAG_BASE,
+	WORK_OFFQ_CANCELING	= (1 << __WORK_OFFQ_CANCELING),
 
 	/*
 	 * When a work item is off queue, its high bits point to the last
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index a219be961c0..00048339c23 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -177,7 +177,6 @@ int write_cache_pages(struct address_space *mapping,
 		      struct writeback_control *wbc, writepage_t writepage,
 		      void *data);
 int do_writepages(struct address_space *mapping, struct writeback_control *wbc);
-void set_page_dirty_balance(struct page *page);
 void writeback_set_ratelimit(void);
 void tag_pages_for_writeback(struct address_space *mapping,
 			     pgoff_t start, pgoff_t end);
diff --git a/include/net/activity_stats.h b/include/net/activity_stats.h
new file mode 100644
index 00000000000..10e4c1506ee
--- /dev/null
+++ b/include/net/activity_stats.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Author: Mike Chan (mike@android.com)
+ */
+
+#ifndef __activity_stats_h
+#define __activity_stats_h
+
+#ifdef CONFIG_NET_ACTIVITY_STATS
+void activity_stats_update(void);
+#else
+#define activity_stats_update(void) {}
+#endif
+
+#endif /* _NET_ACTIVITY_STATS_H */
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index d13573bb879..9828539ae70 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -193,6 +193,8 @@ static inline bool ipv6_is_mld(struct sk_buff *skb, int nexthdr, int offset)
 void addrconf_prefix_rcv(struct net_device *dev,
 			 u8 *opt, int len, bool sllao);
 
+u32 addrconf_rt_table(const struct net_device *dev, u32 default_table);
+
 /*
  *	anycast prototypes (anycast.c)
  */
diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h
index a6fd939f202..3ebb168b9af 100644
--- a/include/net/cipso_ipv4.h
+++ b/include/net/cipso_ipv4.h
@@ -121,13 +121,6 @@ extern int cipso_v4_rbm_strictvalid;
 #endif
 
 /*
- * Helper Functions
- */
-
-#define CIPSO_V4_OPTEXIST(x) (IPCB(x)->opt.cipso != 0)
-#define CIPSO_V4_OPTPTR(x) (skb_network_header(x) + IPCB(x)->opt.cipso)
-
-/*
  * DOI List Functions
  */
 
@@ -190,7 +183,7 @@ static inline int cipso_v4_doi_domhsh_remove(struct cipso_v4_doi *doi_def,
 
 #ifdef CONFIG_NETLABEL
 void cipso_v4_cache_invalidate(void);
-int cipso_v4_cache_add(const struct sk_buff *skb,
+int cipso_v4_cache_add(const unsigned char *cipso_ptr,
 		       const struct netlbl_lsm_secattr *secattr);
 #else
 static inline void cipso_v4_cache_invalidate(void)
@@ -198,7 +191,7 @@ static inline void cipso_v4_cache_invalidate(void)
 	return;
 }
 
-static inline int cipso_v4_cache_add(const struct sk_buff *skb,
+static inline int cipso_v4_cache_add(const unsigned char *cipso_ptr,
 				     const struct netlbl_lsm_secattr *secattr)
 {
 	return 0;
@@ -211,6 +204,8 @@ static inline int cipso_v4_cache_add(const struct sk_buff *skb,
 
 #ifdef CONFIG_NETLABEL
 void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway);
+int cipso_v4_getattr(const unsigned char *cipso,
+		     struct netlbl_lsm_secattr *secattr);
 int cipso_v4_sock_setattr(struct sock *sk,
 			  const struct cipso_v4_doi *doi_def,
 			  const struct netlbl_lsm_secattr *secattr);
@@ -226,6 +221,7 @@ int cipso_v4_skbuff_setattr(struct sk_buff *skb,
 int cipso_v4_skbuff_delattr(struct sk_buff *skb);
 int cipso_v4_skbuff_getattr(const struct sk_buff *skb,
 			    struct netlbl_lsm_secattr *secattr);
+unsigned char *cipso_v4_optptr(const struct sk_buff *skb);
 int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option);
 #else
 static inline void cipso_v4_error(struct sk_buff *skb,
@@ -235,6 +231,12 @@ static inline void cipso_v4_error(struct sk_buff *skb,
 	return;
 }
 
+static inline int cipso_v4_getattr(const unsigned char *cipso,
+				   struct netlbl_lsm_secattr *secattr)
+{
+	return -ENOSYS;
+}
+
 static inline int cipso_v4_sock_setattr(struct sock *sk,
 				      const struct cipso_v4_doi *doi_def,
 				      const struct netlbl_lsm_secattr *secattr)
@@ -282,6 +284,11 @@ static inline int cipso_v4_skbuff_getattr(const struct sk_buff *skb,
 	return -ENOSYS;
 }
 
+static inline unsigned char *cipso_v4_optptr(const struct sk_buff *skb)
+{
+	return NULL;
+}
+
 static inline int cipso_v4_validate(const struct sk_buff *skb,
 				    unsigned char **option)
 {
diff --git a/include/net/dst.h b/include/net/dst.h
index a8ae4e76077..0fb99a26e97 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -481,6 +481,7 @@ void dst_init(void);
 enum {
 	XFRM_LOOKUP_ICMP = 1 << 0,
 	XFRM_LOOKUP_QUEUE = 1 << 1,
+	XFRM_LOOKUP_KEEP_DST_REF = 1 << 2,
 };
 
 struct flowi;
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index e584de16e4c..c10c06f8e59 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -28,6 +28,8 @@ struct fib_rule {
 	int			suppress_prefixlen;
 	char			iifname[IFNAMSIZ];
 	char			oifname[IFNAMSIZ];
+	kuid_t			uid_start;
+	kuid_t			uid_end;
 	struct rcu_head		rcu;
 };
 
@@ -86,9 +88,13 @@ struct fib_rules_ops {
 	[FRA_FWMARK]	= { .type = NLA_U32 }, \
 	[FRA_FWMASK]	= { .type = NLA_U32 }, \
 	[FRA_TABLE]     = { .type = NLA_U32 }, \
+	[FRA_GOTO]	= { .type = NLA_U32 }, \
+	[FRA_UID_START]	= { .type = NLA_U32 }, \
+	[FRA_UID_END]	= { .type = NLA_U32 }, \
 	[FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \
 	[FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \
 	[FRA_GOTO]	= { .type = NLA_U32 }
+	
 
 static inline void fib_rule_get(struct fib_rule *rule)
 {
diff --git a/include/net/flow.h b/include/net/flow.h
index 8109a159d1b..da7743eea60 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -10,6 +10,7 @@
 #include <linux/socket.h>
 #include <linux/in6.h>
 #include <linux/atomic.h>
+#include <linux/uidgid.h>
 
 /*
  * ifindex generation is per-net namespace, and loopback is
@@ -30,6 +31,7 @@ struct flowi_common {
 #define FLOWI_FLAG_ANYSRC		0x01
 #define FLOWI_FLAG_KNOWN_NH		0x02
 	__u32	flowic_secid;
+	kuid_t	flowic_uid;
 };
 
 union flowi_uli {
@@ -66,6 +68,7 @@ struct flowi4 {
 #define flowi4_proto		__fl_common.flowic_proto
 #define flowi4_flags		__fl_common.flowic_flags
 #define flowi4_secid		__fl_common.flowic_secid
+#define flowi4_uid		__fl_common.flowic_uid
 
 	/* (saddr,daddr) must be grouped, same order as in IP header */
 	__be32			saddr;
@@ -85,7 +88,8 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
 				      __u32 mark, __u8 tos, __u8 scope,
 				      __u8 proto, __u8 flags,
 				      __be32 daddr, __be32 saddr,
-				      __be16 dport, __be16 sport)
+				      __be16 dport, __be16 sport,
+				      kuid_t uid)
 {
 	fl4->flowi4_oif = oif;
 	fl4->flowi4_iif = LOOPBACK_IFINDEX;
@@ -95,6 +99,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
 	fl4->flowi4_proto = proto;
 	fl4->flowi4_flags = flags;
 	fl4->flowi4_secid = 0;
+	fl4->flowi4_uid = uid;
 	fl4->daddr = daddr;
 	fl4->saddr = saddr;
 	fl4->fl4_dport = dport;
@@ -122,6 +127,7 @@ struct flowi6 {
 #define flowi6_proto		__fl_common.flowic_proto
 #define flowi6_flags		__fl_common.flowic_flags
 #define flowi6_secid		__fl_common.flowic_secid
+#define flowi6_uid		__fl_common.flowic_uid
 	struct in6_addr		daddr;
 	struct in6_addr		saddr;
 	__be32			flowlabel;
@@ -165,6 +171,7 @@ struct flowi {
 #define flowi_proto	u.__fl_common.flowic_proto
 #define flowi_flags	u.__fl_common.flowic_flags
 #define flowi_secid	u.__fl_common.flowic_secid
+#define flowi_uid	u.__fl_common.flowic_uid
 } __attribute__((__aligned__(BITS_PER_LONG/8)));
 
 static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 848e85cb5c6..24d5c099d3a 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -98,7 +98,8 @@ struct inet_connection_sock {
 	const struct tcp_congestion_ops *icsk_ca_ops;
 	const struct inet_connection_sock_af_ops *icsk_af_ops;
 	unsigned int		  (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
-	__u8			  icsk_ca_state;
+	__u8			  icsk_ca_state:7,
+				  icsk_ca_setsockopt:1;
 	__u8			  icsk_retransmits;
 	__u8			  icsk_pending;
 	__u8			  icsk_backoff;
diff --git a/include/net/ip.h b/include/net/ip.h
index 0bb62070292..3fce700850e 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -39,11 +39,12 @@ struct inet_skb_parm {
 	struct ip_options	opt;		/* Compiled IP options		*/
 	unsigned char		flags;
 
-#define IPSKB_FORWARDED		1
-#define IPSKB_XFRM_TUNNEL_SIZE	2
-#define IPSKB_XFRM_TRANSFORMED	4
-#define IPSKB_FRAG_COMPLETE	8
-#define IPSKB_REROUTED		16
+#define IPSKB_FORWARDED		BIT(0)
+#define IPSKB_XFRM_TUNNEL_SIZE	BIT(1)
+#define IPSKB_XFRM_TRANSFORMED	BIT(2)
+#define IPSKB_FRAG_COMPLETE	BIT(3)
+#define IPSKB_REROUTED		BIT(4)
+#define IPSKB_DOREDIRECT	BIT(5)
 
 	u16			frag_max_size;
 };
@@ -171,6 +172,7 @@ struct ip_reply_arg {
 				/* -1 if not needed */ 
 	int	    bound_dev_if;
 	u8  	    tos;
+	kuid_t	    uid;
 }; 
 
 #define IP_REPLY_ARG_NOSRCCHECK 1
@@ -180,7 +182,7 @@ static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg)
 	return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0;
 }
 
-void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
+void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			   const struct ip_options *sopt,
 			   __be32 daddr, __be32 saddr,
 			   const struct ip_reply_arg *arg,
@@ -452,22 +454,6 @@ static __inline__ void inet_reset_saddr(struct sock *sk)
 
 #endif
 
-static inline int sk_mc_loop(struct sock *sk)
-{
-	if (!sk)
-		return 1;
-	switch (sk->sk_family) {
-	case AF_INET:
-		return inet_sk(sk)->mc_loop;
-#if IS_ENABLED(CONFIG_IPV6)
-	case AF_INET6:
-		return inet6_sk(sk)->mc_loop;
-#endif
-	}
-	WARN_ON(1);
-	return 1;
-}
-
 bool ip_call_ra_chain(struct sk_buff *skb);
 
 /*
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 1d09b46c1e4..d513308ddc3 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -108,7 +108,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 		  const struct in6_addr *gwaddr);
 
 void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif,
-		     u32 mark);
+		     u32 mark, kuid_t uid);
 void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu);
 void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark);
 void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
@@ -174,7 +174,8 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));
 
 static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
 {
-	struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
+	struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
+				inet6_sk(skb->sk) : NULL;
 
 	return (np && np->pmtudisc >= IPV6_PMTUDISC_PROBE) ?
 	       skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 0ad1f47d2dc..a9de1da73c0 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1227,8 +1227,7 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev);
  *
  * @IEEE80211_KEY_FLAG_GENERATE_IV: This flag should be set by the
  *	driver to indicate that it requires IV generation for this
- *	particular key. Setting this flag does not necessarily mean that SKBs
- *	will have sufficient tailroom for ICV or MIC.
+ *	particular key.
  * @IEEE80211_KEY_FLAG_GENERATE_MMIC: This flag should be set by
  *	the driver for a TKIP key if it requires Michael MIC
  *	generation in software.
@@ -1240,9 +1239,7 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev);
  * @IEEE80211_KEY_FLAG_PUT_IV_SPACE: This flag should be set by the driver
  *	if space should be prepared for the IV, but the IV
  *	itself should not be generated. Do not set together with
- *	@IEEE80211_KEY_FLAG_GENERATE_IV on the same key. Setting this flag does
- *	not necessarily mean that SKBs will have sufficient tailroom for ICV or
- *	MIC.
+ *	@IEEE80211_KEY_FLAG_GENERATE_IV on the same key.
  * @IEEE80211_KEY_FLAG_RX_MGMT: This key will be used to decrypt received
  *	management frames. The flag can help drivers that have a hardware
  *	crypto implementation that doesn't deal with management frames
diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h
index 84a53d78030..1a91f979160 100644
--- a/include/net/netfilter/nf_queue.h
+++ b/include/net/netfilter/nf_queue.h
@@ -28,6 +28,8 @@ struct nf_queue_entry {
 struct nf_queue_handler {
 	int			(*outfn)(struct nf_queue_entry *entry,
 					 unsigned int queuenum);
+	void			(*nf_hook_drop)(struct net *net,
+						struct nf_hook_ops *ops);
 };
 
 void nf_register_queue_handler(const struct nf_queue_handler *qh);
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 24945cefc4f..0ffef1a38ef 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -52,6 +52,7 @@ struct netns_ipv4 {
 	struct inet_peer_base	*peers;
 	struct tcpm_hash_bucket	*tcp_metrics_hash;
 	unsigned int		tcp_metrics_hash_log;
+	struct sock  * __percpu	*tcp_sk;
 	struct netns_frags	frags;
 #ifdef CONFIG_NETFILTER
 	struct xt_table		*iptable_filter;
diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h
index 3573a81815a..8ba379f9e46 100644
--- a/include/net/netns/sctp.h
+++ b/include/net/netns/sctp.h
@@ -31,6 +31,7 @@ struct netns_sctp {
 	struct list_head addr_waitq;
 	struct timer_list addr_wq_timer;
 	struct list_head auto_asconf_splist;
+	/* Lock that protects both addr_waitq and auto_asconf_splist */
 	spinlock_t addr_wq_lock;
 
 	/* Lock that protects the local_addr_list writers */
diff --git a/include/net/route.h b/include/net/route.h
index b17cf28f996..41288e35689 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -140,7 +140,7 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi
 	flowi4_init_output(fl4, oif, sk ? sk->sk_mark : 0, tos,
 			   RT_SCOPE_UNIVERSE, proto,
 			   sk ? inet_sk_flowi_flags(sk) : 0,
-			   daddr, saddr, dport, sport);
+			   daddr, saddr, dport, sport, sk ? sock_i_uid(sk) : GLOBAL_ROOT_UID);
 	if (sk)
 		security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
 	return ip_route_output_flow(net, fl4, sk);
@@ -249,7 +249,8 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32
 		flow_flags |= FLOWI_FLAG_ANYSRC;
 
 	flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE,
-			   protocol, flow_flags, dst, src, dport, sport);
+			   protocol, flow_flags, dst, src, dport, sport,
+			   sock_i_uid(sk));
 }
 
 static inline struct rtable *ip_route_connect(struct flowi4 *fl4,
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d17ed6fb2f7..5ccfe161f35 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -79,6 +79,9 @@ struct Qdisc {
 	struct netdev_queue	*dev_queue;
 
 	struct gnet_stats_rate_est64	rate_est;
+	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+	struct gnet_stats_queue	__percpu *cpu_qstats;
+
 	struct Qdisc		*next_sched;
 	struct sk_buff		*gso_skb;
 	/*
@@ -86,15 +89,9 @@ struct Qdisc {
 	 */
 	unsigned long		state;
 	struct sk_buff_head	q;
-	union {
-		struct gnet_stats_basic_packed bstats;
-		struct gnet_stats_basic_cpu __percpu *cpu_bstats;
-	} __packed;
+	struct gnet_stats_basic_packed bstats;
 	unsigned int		__state;
-	union {
-		struct gnet_stats_queue	qstats;
-		struct gnet_stats_queue	__percpu *cpu_qstats;
-	} __packed;
+	struct gnet_stats_queue	qstats;
 	struct rcu_head		rcu_head;
 	int			padded;
 	atomic_t		refcnt;
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 856f01cb51d..230775f5952 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -571,11 +571,14 @@ static inline void sctp_v6_map_v4(union sctp_addr *addr)
 /* Map v4 address to v4-mapped v6 address */
 static inline void sctp_v4_map_v6(union sctp_addr *addr)
 {
+	__be16 port;
+
+	port = addr->v4.sin_port;
+	addr->v6.sin6_addr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
+	addr->v6.sin6_port = port;
 	addr->v6.sin6_family = AF_INET6;
 	addr->v6.sin6_flowinfo = 0;
 	addr->v6.sin6_scope_id = 0;
-	addr->v6.sin6_port = addr->v4.sin_port;
-	addr->v6.sin6_addr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
 	addr->v6.sin6_addr.s6_addr32[0] = 0;
 	addr->v6.sin6_addr.s6_addr32[1] = 0;
 	addr->v6.sin6_addr.s6_addr32[2] = htonl(0x0000ffff);
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 4ff3f67be62..2ad3a7bc838 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -223,6 +223,10 @@ struct sctp_sock {
 	atomic_t pd_mode;
 	/* Receive to here while partial delivery is in effect. */
 	struct sk_buff_head pd_lobby;
+
+	/* These must be the last fields, as they will skipped on copies,
+	 * like on accept and peeloff operations
+	 */
 	struct list_head auto_asconf_list;
 	int do_auto_asconf;
 };
diff --git a/include/net/sock.h b/include/net/sock.h
index 7db3db112ba..4406dbe491f 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -67,6 +67,7 @@
 #include <linux/atomic.h>
 #include <net/dst.h>
 #include <net/checksum.h>
+#include <net/tcp_states.h>
 #include <linux/net_tstamp.h>
 
 struct cgroup;
@@ -1806,6 +1807,8 @@ struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
 
 struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie);
 
+bool sk_mc_loop(struct sock *sk);
+
 static inline bool sk_can_gso(const struct sock *sk)
 {
 	return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type);
@@ -2265,6 +2268,14 @@ static inline struct sock *skb_steal_sock(struct sk_buff *skb)
 	return NULL;
 }
 
+/* This helper checks if a socket is a full socket,
+ * ie _not_ a timewait or request socket.
+ */
+static inline bool sk_fullsock(const struct sock *sk)
+{
+	return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV);
+}
+
 void sock_enable_timestamp(struct sock *sk, int flag);
 int sock_get_timestamp(struct sock *, struct timeval __user *);
 int sock_get_timestampns(struct sock *, struct timespec __user *);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 4062b4f0d12..e6ec66a5fed 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -276,6 +276,7 @@ extern int sysctl_tcp_challenge_ack_limit;
 extern unsigned int sysctl_tcp_notsent_lowat;
 extern int sysctl_tcp_min_tso_segs;
 extern int sysctl_tcp_autocorking;
+extern int sysctl_tcp_default_init_rwnd;
 
 extern atomic_long_t tcp_memory_allocated;
 extern struct percpu_counter tcp_sockets_allocated;
@@ -1601,6 +1602,8 @@ static inline bool tcp_stream_memory_free(const struct sock *sk)
 	return notsent_bytes < tcp_notsent_lowat(tp);
 }
 
+extern int tcp_nuke_addr(struct net *net, struct sockaddr *addr);
+
 #ifdef CONFIG_PROC_FS
 int tcp4_proc_init(void);
 void tcp4_proc_exit(void);
diff --git a/include/net/tcp_states.h b/include/net/tcp_states.h
index b0b645988bd..50e78a74d0d 100644
--- a/include/net/tcp_states.h
+++ b/include/net/tcp_states.h
@@ -25,6 +25,7 @@ enum {
 	TCP_LAST_ACK,
 	TCP_LISTEN,
 	TCP_CLOSING,	/* Now a valid state */
+	TCP_NEW_SYN_RECV,
 
 	TCP_MAX_STATES	/* Leave at the end! */
 };
@@ -44,7 +45,8 @@ enum {
 	TCPF_CLOSE_WAIT	 = (1 << 8),
 	TCPF_LAST_ACK	 = (1 << 9),
 	TCPF_LISTEN	 = (1 << 10),
-	TCPF_CLOSING	 = (1 << 11) 
+	TCPF_CLOSING	 = (1 << 11),
+	TCPF_NEW_SYN_RECV = (1 << 12),
 };
 
 #endif	/* _LINUX_TCP_STATES_H */
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 57cccd0052e..903461aa564 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -1,6 +1,9 @@
 #ifndef __NET_VXLAN_H
 #define __NET_VXLAN_H 1
 
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/if_vlan.h>
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include <linux/udp.h>
@@ -51,16 +54,33 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 		   __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
 		   __be16 src_port, __be16 dst_port, __be32 vni, bool xnet);
 
-static inline bool vxlan_gso_check(struct sk_buff *skb)
+static inline netdev_features_t vxlan_features_check(struct sk_buff *skb,
+						     netdev_features_t features)
 {
-	if ((skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL) &&
+	u8 l4_hdr = 0;
+
+	if (!skb->encapsulation)
+		return features;
+
+	switch (vlan_get_protocol(skb)) {
+	case htons(ETH_P_IP):
+		l4_hdr = ip_hdr(skb)->protocol;
+		break;
+	case htons(ETH_P_IPV6):
+		l4_hdr = ipv6_hdr(skb)->nexthdr;
+		break;
+	default:
+		return features;;
+	}
+
+	if ((l4_hdr == IPPROTO_UDP) &&
 	    (skb->inner_protocol_type != ENCAP_TYPE_ETHER ||
 	     skb->inner_protocol != htons(ETH_P_TEB) ||
 	     (skb_inner_mac_header(skb) - skb_transport_header(skb) !=
 	      sizeof(struct udphdr) + sizeof(struct vxlanhdr))))
-		return false;
+		return features & ~(NETIF_F_ALL_CSUM | NETIF_F_GSO_MASK);
 
-	return true;
+	return features;
 }
 
 /* IP header + UDP + VXLAN + Ethernet header */
diff --git a/include/scsi/scsi_devinfo.h b/include/scsi/scsi_devinfo.h
index 183eaab7c38..96e3f56519e 100644
--- a/include/scsi/scsi_devinfo.h
+++ b/include/scsi/scsi_devinfo.h
@@ -36,5 +36,6 @@
 					     for sequential scan */
 #define BLIST_TRY_VPD_PAGES	0x10000000 /* Attempt to read VPD pages */
 #define BLIST_NO_RSOC		0x20000000 /* don't try to issue RSOC */
+#define BLIST_MAX_1024		0x40000000 /* maximum 1024 sector cdb length */
 
 #endif
diff --git a/include/sound/ak4113.h b/include/sound/ak4113.h
index 2609048c1d4..3a34f6edc2d 100644
--- a/include/sound/ak4113.h
+++ b/include/sound/ak4113.h
@@ -286,7 +286,7 @@ struct ak4113 {
 	ak4113_write_t *write;
 	ak4113_read_t *read;
 	void *private_data;
-	unsigned int init:1;
+	atomic_t wq_processing;
 	spinlock_t lock;
 	unsigned char regmap[AK4113_WRITABLE_REGS];
 	struct snd_kcontrol *kctls[AK4113_CONTROLS];
diff --git a/include/sound/ak4114.h b/include/sound/ak4114.h
index 52f02a60dba..069299a8891 100644
--- a/include/sound/ak4114.h
+++ b/include/sound/ak4114.h
@@ -168,7 +168,7 @@ struct ak4114 {
 	ak4114_write_t * write;
 	ak4114_read_t * read;
 	void * private_data;
-	unsigned int init: 1;
+	atomic_t wq_processing;
 	spinlock_t lock;
 	unsigned char regmap[6];
 	unsigned char txcsb[5];
diff --git a/include/sound/emu10k1.h b/include/sound/emu10k1.h
index c46908c1bb3..8af2fff0eb0 100644
--- a/include/sound/emu10k1.h
+++ b/include/sound/emu10k1.h
@@ -41,7 +41,8 @@
 
 #define EMUPAGESIZE     4096
 #define MAXREQVOICES    8
-#define MAXPAGES        8192
+#define MAXPAGES0       4096	/* 32 bit mode */
+#define MAXPAGES1       8192	/* 31 bit mode */
 #define RESERVED        0
 #define NUM_MIDI        16
 #define NUM_G           64              /* use all channels */
@@ -50,8 +51,7 @@
 
 /* FIXME? - according to the OSS driver the EMU10K1 needs a 29 bit DMA mask */
 #define EMU10K1_DMA_MASK	0x7fffffffUL	/* 31bit */
-#define AUDIGY_DMA_MASK		0x7fffffffUL	/* 31bit FIXME - 32 should work? */
-						/* See ALSA bug #1276 - rlrevell */
+#define AUDIGY_DMA_MASK		0xffffffffUL	/* 32bit mode */
 
 #define TMEMSIZE        256*1024
 #define TMEMSIZEREG     4
@@ -466,8 +466,11 @@
 
 #define MAPB			0x0d		/* Cache map B						*/
 
-#define MAP_PTE_MASK		0xffffe000	/* The 19 MSBs of the PTE indexed by the PTI		*/
-#define MAP_PTI_MASK		0x00001fff	/* The 13 bit index to one of the 8192 PTE dwords      	*/
+#define MAP_PTE_MASK0		0xfffff000	/* The 20 MSBs of the PTE indexed by the PTI		*/
+#define MAP_PTI_MASK0		0x00000fff	/* The 12 bit index to one of the 4096 PTE dwords      	*/
+
+#define MAP_PTE_MASK1		0xffffe000	/* The 19 MSBs of the PTE indexed by the PTI		*/
+#define MAP_PTI_MASK1		0x00001fff	/* The 13 bit index to one of the 8192 PTE dwords      	*/
 
 /* 0x0e, 0x0f: Not used */
 
@@ -1704,6 +1707,7 @@ struct snd_emu10k1 {
 	unsigned short model;			/* subsystem id */
 	unsigned int card_type;			/* EMU10K1_CARD_* */
 	unsigned int ecard_ctrl;		/* ecard control bits */
+	unsigned int address_mode;		/* address mode */
 	unsigned long dma_mask;			/* PCI DMA mask */
 	unsigned int delay_pcm_irq;		/* in samples */
 	int max_cache_pages;			/* max memory size / PAGE_SIZE */
diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index 3a4d7da67b8..525f313f9f4 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -287,7 +287,7 @@ struct device;
 	.access = SNDRV_CTL_ELEM_ACCESS_TLV_READ | SNDRV_CTL_ELEM_ACCESS_READWRITE,\
 	.tlv.p = (tlv_array), \
 	.get = snd_soc_dapm_get_volsw, .put = snd_soc_dapm_put_volsw, \
-	.private_value = SOC_SINGLE_VALUE(reg, shift, max, invert, 0) }
+	.private_value = SOC_SINGLE_VALUE(reg, shift, max, invert, 1) }
 #define SOC_DAPM_SINGLE_TLV_VIRT(xname, max, tlv_array) \
 	SOC_DAPM_SINGLE(xname, SND_SOC_NOPM, 0, max, 0, tlv_array)
 #define SOC_DAPM_ENUM(xname, xenum) \
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 23c518a0340..c4b85a5889b 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -409,7 +409,7 @@ struct t10_reservation {
 	/* Activate Persistence across Target Power Loss enabled
 	 * for SCSI device */
 	int pr_aptpl_active;
-#define PR_APTPL_BUF_LEN			8192
+#define PR_APTPL_BUF_LEN			262144
 	u32 pr_generation;
 	spinlock_t registration_lock;
 	spinlock_t aptpl_reg_lock;
@@ -520,7 +520,7 @@ struct se_cmd {
 	sense_reason_t		(*execute_cmd)(struct se_cmd *);
 	sense_reason_t		(*execute_rw)(struct se_cmd *, struct scatterlist *,
 					      u32, enum dma_data_direction);
-	sense_reason_t (*transport_complete_callback)(struct se_cmd *);
+	sense_reason_t (*transport_complete_callback)(struct se_cmd *, bool);
 
 	unsigned char		*t_task_cdb;
 	unsigned char		__t_task_cdb[TCM_MAX_COMMAND_SIZE];
diff --git a/include/trace/events/cpufreq_interactive.h b/include/trace/events/cpufreq_interactive.h
new file mode 100644
index 00000000000..951e6ca12da
--- /dev/null
+++ b/include/trace/events/cpufreq_interactive.h
@@ -0,0 +1,112 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM cpufreq_interactive
+
+#if !defined(_TRACE_CPUFREQ_INTERACTIVE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_CPUFREQ_INTERACTIVE_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(set,
+	TP_PROTO(u32 cpu_id, unsigned long targfreq,
+	         unsigned long actualfreq),
+	TP_ARGS(cpu_id, targfreq, actualfreq),
+
+	TP_STRUCT__entry(
+	    __field(          u32, cpu_id    )
+	    __field(unsigned long, targfreq   )
+	    __field(unsigned long, actualfreq )
+	   ),
+
+	TP_fast_assign(
+	    __entry->cpu_id = (u32) cpu_id;
+	    __entry->targfreq = targfreq;
+	    __entry->actualfreq = actualfreq;
+	),
+
+	TP_printk("cpu=%u targ=%lu actual=%lu",
+	      __entry->cpu_id, __entry->targfreq,
+	      __entry->actualfreq)
+);
+
+DEFINE_EVENT(set, cpufreq_interactive_setspeed,
+	TP_PROTO(u32 cpu_id, unsigned long targfreq,
+	     unsigned long actualfreq),
+	TP_ARGS(cpu_id, targfreq, actualfreq)
+);
+
+DECLARE_EVENT_CLASS(loadeval,
+	    TP_PROTO(unsigned long cpu_id, unsigned long load,
+		     unsigned long curtarg, unsigned long curactual,
+		     unsigned long newtarg),
+		    TP_ARGS(cpu_id, load, curtarg, curactual, newtarg),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned long, cpu_id    )
+		    __field(unsigned long, load      )
+		    __field(unsigned long, curtarg   )
+		    __field(unsigned long, curactual )
+		    __field(unsigned long, newtarg   )
+	    ),
+
+	    TP_fast_assign(
+		    __entry->cpu_id = cpu_id;
+		    __entry->load = load;
+		    __entry->curtarg = curtarg;
+		    __entry->curactual = curactual;
+		    __entry->newtarg = newtarg;
+	    ),
+
+	    TP_printk("cpu=%lu load=%lu cur=%lu actual=%lu targ=%lu",
+		      __entry->cpu_id, __entry->load, __entry->curtarg,
+		      __entry->curactual, __entry->newtarg)
+);
+
+DEFINE_EVENT(loadeval, cpufreq_interactive_target,
+	    TP_PROTO(unsigned long cpu_id, unsigned long load,
+		     unsigned long curtarg, unsigned long curactual,
+		     unsigned long newtarg),
+	    TP_ARGS(cpu_id, load, curtarg, curactual, newtarg)
+);
+
+DEFINE_EVENT(loadeval, cpufreq_interactive_already,
+	    TP_PROTO(unsigned long cpu_id, unsigned long load,
+		     unsigned long curtarg, unsigned long curactual,
+		     unsigned long newtarg),
+	    TP_ARGS(cpu_id, load, curtarg, curactual, newtarg)
+);
+
+DEFINE_EVENT(loadeval, cpufreq_interactive_notyet,
+	    TP_PROTO(unsigned long cpu_id, unsigned long load,
+		     unsigned long curtarg, unsigned long curactual,
+		     unsigned long newtarg),
+	    TP_ARGS(cpu_id, load, curtarg, curactual, newtarg)
+);
+
+TRACE_EVENT(cpufreq_interactive_boost,
+	    TP_PROTO(const char *s),
+	    TP_ARGS(s),
+	    TP_STRUCT__entry(
+		    __string(s, s)
+	    ),
+	    TP_fast_assign(
+		    __assign_str(s, s);
+	    ),
+	    TP_printk("%s", __get_str(s))
+);
+
+TRACE_EVENT(cpufreq_interactive_unboost,
+	    TP_PROTO(const char *s),
+	    TP_ARGS(s),
+	    TP_STRUCT__entry(
+		    __string(s, s)
+	    ),
+	    TP_fast_assign(
+		    __assign_str(s, s);
+	    ),
+	    TP_printk("%s", __get_str(s))
+);
+
+#endif /* _TRACE_CPUFREQ_INTERACTIVE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/gpu.h b/include/trace/events/gpu.h
new file mode 100644
index 00000000000..7e15cdfafe5
--- /dev/null
+++ b/include/trace/events/gpu.h
@@ -0,0 +1,143 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM gpu
+
+#if !defined(_TRACE_GPU_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_GPU_H
+
+#include <linux/tracepoint.h>
+#include <linux/time.h>
+
+#define show_secs_from_ns(ns) \
+	({ \
+		u64 t = ns + (NSEC_PER_USEC / 2); \
+		do_div(t, NSEC_PER_SEC); \
+		t; \
+	})
+
+#define show_usecs_from_ns(ns) \
+	({ \
+		u64 t = ns + (NSEC_PER_USEC / 2) ; \
+		u32 rem; \
+		do_div(t, NSEC_PER_USEC); \
+		rem = do_div(t, USEC_PER_SEC); \
+	})
+
+/*
+ * The gpu_sched_switch event indicates that a switch from one GPU context to
+ * another occurred on one of the GPU hardware blocks.
+ *
+ * The gpu_name argument identifies the GPU hardware block.  Each independently
+ * scheduled GPU hardware block should have a different name.  This may be used
+ * in different ways for different GPUs.  For example, if a GPU includes
+ * multiple processing cores it may use names "GPU 0", "GPU 1", etc.  If a GPU
+ * includes a separately scheduled 2D and 3D hardware block, it might use the
+ * names "2D" and "3D".
+ *
+ * The timestamp argument is the timestamp at which the switch occurred on the
+ * GPU. These timestamps are in units of nanoseconds and must use
+ * approximately the same time as sched_clock, though they need not come from
+ * any CPU clock. The timestamps for a single hardware block must be
+ * monotonically nondecreasing.  This means that if a variable compensation
+ * offset is used to translate from some other clock to the sched_clock, then
+ * care must be taken when increasing that offset, and doing so may result in
+ * multiple events with the same timestamp.
+ *
+ * The next_ctx_id argument identifies the next context that was running on
+ * the GPU hardware block.  A value of 0 indicates that the hardware block
+ * will be idle.
+ *
+ * The next_prio argument indicates the priority of the next context at the
+ * time of the event.  The exact numeric values may mean different things for
+ * different GPUs, but they should follow the rule that lower values indicate a
+ * higher priority.
+ *
+ * The next_job_id argument identifies the batch of work that the GPU will be
+ * working on.  This should correspond to a job_id that was previously traced
+ * as a gpu_job_enqueue event when the batch of work was created.
+ */
+TRACE_EVENT(gpu_sched_switch,
+
+	TP_PROTO(const char *gpu_name, u64 timestamp,
+		u32 next_ctx_id, s32 next_prio, u32 next_job_id),
+
+	TP_ARGS(gpu_name, timestamp, next_ctx_id, next_prio, next_job_id),
+
+	TP_STRUCT__entry(
+		__string(       gpu_name,       gpu_name        )
+		__field(        u64,            timestamp       )
+		__field(        u32,            next_ctx_id     )
+		__field(        s32,            next_prio       )
+		__field(        u32,            next_job_id     )
+	),
+
+	TP_fast_assign(
+		__assign_str(gpu_name, gpu_name);
+		__entry->timestamp = timestamp;
+		__entry->next_ctx_id = next_ctx_id;
+		__entry->next_prio = next_prio;
+		__entry->next_job_id = next_job_id;
+	),
+
+	TP_printk("gpu_name=%s ts=%llu.%06lu next_ctx_id=%lu next_prio=%ld "
+		"next_job_id=%lu",
+		__get_str(gpu_name),
+		(unsigned long long)show_secs_from_ns(__entry->timestamp),
+		(unsigned long)show_usecs_from_ns(__entry->timestamp),
+		(unsigned long)__entry->next_ctx_id,
+		(long)__entry->next_prio,
+		(unsigned long)__entry->next_job_id)
+);
+
+/*
+ * The gpu_job_enqueue event indicates that a batch of work has been queued up
+ * to be processed by the GPU.  This event is not intended to indicate that
+ * the batch of work has been submitted to the GPU hardware, but rather that
+ * it has been submitted to the GPU kernel driver.
+ *
+ * This event should be traced on the thread that initiated the work being
+ * queued.  For example, if a batch of work is submitted to the kernel by a
+ * userland thread, the event should be traced on that thread.
+ *
+ * The ctx_id field identifies the GPU context in which the batch of work
+ * being queued is to be run.
+ *
+ * The job_id field identifies the batch of work being queued within the given
+ * GPU context.  The first batch of work submitted for a given GPU context
+ * should have a job_id of 0, and each subsequent batch of work should
+ * increment the job_id by 1.
+ *
+ * The type field identifies the type of the job being enqueued.  The job
+ * types may be different for different GPU hardware.  For example, a GPU may
+ * differentiate between "2D", "3D", and "compute" jobs.
+ */
+TRACE_EVENT(gpu_job_enqueue,
+
+	TP_PROTO(u32 ctx_id, u32 job_id, const char *type),
+
+	TP_ARGS(ctx_id, job_id, type),
+
+	TP_STRUCT__entry(
+		__field(        u32,            ctx_id          )
+		__field(        u32,            job_id          )
+		__string(       type,           type            )
+	),
+
+	TP_fast_assign(
+		__entry->ctx_id = ctx_id;
+		__entry->job_id = job_id;
+		__assign_str(type, type);
+	),
+
+	TP_printk("ctx_id=%lu job_id=%lu type=%s",
+		(unsigned long)__entry->ctx_id,
+		(unsigned long)__entry->job_id,
+		__get_str(type))
+);
+
+#undef show_secs_from_ns
+#undef show_usecs_from_ns
+
+#endif /* _TRACE_GPU_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index aece1346ceb..4ad10baecd4 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -268,11 +268,11 @@ TRACE_EVENT(mm_page_alloc_extfrag,
 
 	TP_PROTO(struct page *page,
 		int alloc_order, int fallback_order,
-		int alloc_migratetype, int fallback_migratetype, int new_migratetype),
+		int alloc_migratetype, int fallback_migratetype),
 
 	TP_ARGS(page,
 		alloc_order, fallback_order,
-		alloc_migratetype, fallback_migratetype, new_migratetype),
+		alloc_migratetype, fallback_migratetype),
 
 	TP_STRUCT__entry(
 		__field(	struct page *,	page			)
@@ -289,7 +289,8 @@ TRACE_EVENT(mm_page_alloc_extfrag,
 		__entry->fallback_order		= fallback_order;
 		__entry->alloc_migratetype	= alloc_migratetype;
 		__entry->fallback_migratetype	= fallback_migratetype;
-		__entry->change_ownership	= (new_migratetype == alloc_migratetype);
+		__entry->change_ownership	= (alloc_migratetype ==
+					get_pageblock_migratetype(page));
 	),
 
 	TP_printk("page=%p pfn=%lu alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d",
diff --git a/include/trace/events/mmc.h b/include/trace/events/mmc.h
new file mode 100644
index 00000000000..82b368dbcef
--- /dev/null
+++ b/include/trace/events/mmc.h
@@ -0,0 +1,91 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mmc
+
+#if !defined(_TRACE_MMC_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MMC_H
+
+#include <linux/tracepoint.h>
+#include <linux/mmc/mmc.h>
+#include <linux/mmc/core.h>
+
+/*
+ * Unconditional logging of mmc block erase operations,
+ * including cmd, address, size
+ */
+DECLARE_EVENT_CLASS(mmc_blk_erase_class,
+	TP_PROTO(unsigned int cmd, unsigned int addr, unsigned int size),
+	TP_ARGS(cmd, addr, size),
+	TP_STRUCT__entry(
+		__field(unsigned int, cmd)
+		__field(unsigned int, addr)
+		__field(unsigned int, size)
+	),
+	TP_fast_assign(
+		__entry->cmd = cmd;
+		__entry->addr = addr;
+		__entry->size = size;
+	),
+	TP_printk("cmd=%u,addr=0x%08x,size=0x%08x",
+		  __entry->cmd, __entry->addr, __entry->size)
+);
+
+DEFINE_EVENT(mmc_blk_erase_class, mmc_blk_erase_start,
+	TP_PROTO(unsigned int cmd, unsigned int addr, unsigned int size),
+	TP_ARGS(cmd, addr, size));
+
+DEFINE_EVENT(mmc_blk_erase_class, mmc_blk_erase_end,
+	TP_PROTO(unsigned int cmd, unsigned int addr, unsigned int size),
+	TP_ARGS(cmd, addr, size));
+
+/*
+ * Logging of start of read or write mmc block operation,
+ * including cmd, address, size
+ */
+DECLARE_EVENT_CLASS(mmc_blk_rw_class,
+	TP_PROTO(unsigned int cmd, unsigned int addr, struct mmc_data *data),
+	TP_ARGS(cmd, addr, data),
+	TP_STRUCT__entry(
+		__field(unsigned int, cmd)
+		__field(unsigned int, addr)
+		__field(unsigned int, size)
+	),
+	TP_fast_assign(
+		__entry->cmd = cmd;
+		__entry->addr = addr;
+		__entry->size = data->blocks;
+	),
+	TP_printk("cmd=%u,addr=0x%08x,size=0x%08x",
+		  __entry->cmd, __entry->addr, __entry->size)
+);
+
+DEFINE_EVENT_CONDITION(mmc_blk_rw_class, mmc_blk_rw_start,
+	TP_PROTO(unsigned int cmd, unsigned int addr, struct mmc_data *data),
+	TP_ARGS(cmd, addr, data),
+	TP_CONDITION(((cmd == MMC_READ_MULTIPLE_BLOCK) ||
+		      (cmd == MMC_WRITE_MULTIPLE_BLOCK)) &&
+		      data));
+
+DEFINE_EVENT_CONDITION(mmc_blk_rw_class, mmc_blk_rw_end,
+	TP_PROTO(unsigned int cmd, unsigned int addr, struct mmc_data *data),
+	TP_ARGS(cmd, addr, data),
+	TP_CONDITION(((cmd == MMC_READ_MULTIPLE_BLOCK) ||
+		      (cmd == MMC_WRITE_MULTIPLE_BLOCK)) &&
+		      data));
+#endif /* _TRACE_MMC_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index d19840b0cac..274021214b4 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -264,6 +264,25 @@ DEFINE_EVENT(clock, clock_set_rate,
 	TP_ARGS(name, state, cpu_id)
 );
 
+TRACE_EVENT(clock_set_parent,
+
+	TP_PROTO(const char *name, const char *parent_name),
+
+	TP_ARGS(name, parent_name),
+
+	TP_STRUCT__entry(
+		__string(       name,           name            )
+		__string(       parent_name,    parent_name     )
+	),
+
+	TP_fast_assign(
+		__assign_str(name, name);
+		__assign_str(parent_name, parent_name);
+	),
+
+	TP_printk("%s parent=%s", __get_str(name), __get_str(parent_name))
+);
+
 /*
  * The power domain events are used for power domains transitions
  */
diff --git a/include/trace/events/regmap.h b/include/trace/events/regmap.h
index 23d561512f6..22317d2b52a 100644
--- a/include/trace/events/regmap.h
+++ b/include/trace/events/regmap.h
@@ -7,27 +7,26 @@
 #include <linux/ktime.h>
 #include <linux/tracepoint.h>
 
-struct device;
-struct regmap;
+#include "../../../drivers/base/regmap/internal.h"
 
 /*
  * Log register events
  */
 DECLARE_EVENT_CLASS(regmap_reg,
 
-	TP_PROTO(struct device *dev, unsigned int reg,
+	TP_PROTO(struct regmap *map, unsigned int reg,
 		 unsigned int val),
 
-	TP_ARGS(dev, reg, val),
+	TP_ARGS(map, reg, val),
 
 	TP_STRUCT__entry(
-		__string(	name,		dev_name(dev)	)
-		__field(	unsigned int,	reg		)
-		__field(	unsigned int,	val		)
+		__string(	name,		regmap_name(map)	)
+		__field(	unsigned int,	reg			)
+		__field(	unsigned int,	val			)
 	),
 
 	TP_fast_assign(
-		__assign_str(name, dev_name(dev));
+		__assign_str(name, regmap_name(map));
 		__entry->reg = reg;
 		__entry->val = val;
 	),
@@ -39,45 +38,45 @@ DECLARE_EVENT_CLASS(regmap_reg,
 
 DEFINE_EVENT(regmap_reg, regmap_reg_write,
 
-	TP_PROTO(struct device *dev, unsigned int reg,
+	TP_PROTO(struct regmap *map, unsigned int reg,
 		 unsigned int val),
 
-	TP_ARGS(dev, reg, val)
+	TP_ARGS(map, reg, val)
 
 );
 
 DEFINE_EVENT(regmap_reg, regmap_reg_read,
 
-	TP_PROTO(struct device *dev, unsigned int reg,
+	TP_PROTO(struct regmap *map, unsigned int reg,
 		 unsigned int val),
 
-	TP_ARGS(dev, reg, val)
+	TP_ARGS(map, reg, val)
 
 );
 
 DEFINE_EVENT(regmap_reg, regmap_reg_read_cache,
 
-	TP_PROTO(struct device *dev, unsigned int reg,
+	TP_PROTO(struct regmap *map, unsigned int reg,
 		 unsigned int val),
 
-	TP_ARGS(dev, reg, val)
+	TP_ARGS(map, reg, val)
 
 );
 
 DECLARE_EVENT_CLASS(regmap_block,
 
-	TP_PROTO(struct device *dev, unsigned int reg, int count),
+	TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-	TP_ARGS(dev, reg, count),
+	TP_ARGS(map, reg, count),
 
 	TP_STRUCT__entry(
-		__string(	name,		dev_name(dev)	)
-		__field(	unsigned int,	reg		)
-		__field(	int,		count		)
+		__string(	name,		regmap_name(map)	)
+		__field(	unsigned int,	reg			)
+		__field(	int,		count			)
 	),
 
 	TP_fast_assign(
-		__assign_str(name, dev_name(dev));
+		__assign_str(name, regmap_name(map));
 		__entry->reg = reg;
 		__entry->count = count;
 	),
@@ -89,48 +88,48 @@ DECLARE_EVENT_CLASS(regmap_block,
 
 DEFINE_EVENT(regmap_block, regmap_hw_read_start,
 
-	TP_PROTO(struct device *dev, unsigned int reg, int count),
+	TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-	TP_ARGS(dev, reg, count)
+	TP_ARGS(map, reg, count)
 );
 
 DEFINE_EVENT(regmap_block, regmap_hw_read_done,
 
-	TP_PROTO(struct device *dev, unsigned int reg, int count),
+	TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-	TP_ARGS(dev, reg, count)
+	TP_ARGS(map, reg, count)
 );
 
 DEFINE_EVENT(regmap_block, regmap_hw_write_start,
 
-	TP_PROTO(struct device *dev, unsigned int reg, int count),
+	TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-	TP_ARGS(dev, reg, count)
+	TP_ARGS(map, reg, count)
 );
 
 DEFINE_EVENT(regmap_block, regmap_hw_write_done,
 
-	TP_PROTO(struct device *dev, unsigned int reg, int count),
+	TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-	TP_ARGS(dev, reg, count)
+	TP_ARGS(map, reg, count)
 );
 
 TRACE_EVENT(regcache_sync,
 
-	TP_PROTO(struct device *dev, const char *type,
+	TP_PROTO(struct regmap *map, const char *type,
 		 const char *status),
 
-	TP_ARGS(dev, type, status),
+	TP_ARGS(map, type, status),
 
 	TP_STRUCT__entry(
-		__string(       name,           dev_name(dev)   )
-		__string(	status,		status		)
-		__string(	type,		type		)
-		__field(	int,		type		)
+		__string(       name,           regmap_name(map)	)
+		__string(	status,		status			)
+		__string(	type,		type			)
+		__field(	int,		type			)
 	),
 
 	TP_fast_assign(
-		__assign_str(name, dev_name(dev));
+		__assign_str(name, regmap_name(map));
 		__assign_str(status, status);
 		__assign_str(type, type);
 	),
@@ -141,17 +140,17 @@ TRACE_EVENT(regcache_sync,
 
 DECLARE_EVENT_CLASS(regmap_bool,
 
-	TP_PROTO(struct device *dev, bool flag),
+	TP_PROTO(struct regmap *map, bool flag),
 
-	TP_ARGS(dev, flag),
+	TP_ARGS(map, flag),
 
 	TP_STRUCT__entry(
-		__string(	name,		dev_name(dev)	)
-		__field(	int,		flag		)
+		__string(	name,		regmap_name(map)	)
+		__field(	int,		flag			)
 	),
 
 	TP_fast_assign(
-		__assign_str(name, dev_name(dev));
+		__assign_str(name, regmap_name(map));
 		__entry->flag = flag;
 	),
 
@@ -161,32 +160,32 @@ DECLARE_EVENT_CLASS(regmap_bool,
 
 DEFINE_EVENT(regmap_bool, regmap_cache_only,
 
-	TP_PROTO(struct device *dev, bool flag),
+	TP_PROTO(struct regmap *map, bool flag),
 
-	TP_ARGS(dev, flag)
+	TP_ARGS(map, flag)
 
 );
 
 DEFINE_EVENT(regmap_bool, regmap_cache_bypass,
 
-	TP_PROTO(struct device *dev, bool flag),
+	TP_PROTO(struct regmap *map, bool flag),
 
-	TP_ARGS(dev, flag)
+	TP_ARGS(map, flag)
 
 );
 
 DECLARE_EVENT_CLASS(regmap_async,
 
-	TP_PROTO(struct device *dev),
+	TP_PROTO(struct regmap *map),
 
-	TP_ARGS(dev),
+	TP_ARGS(map),
 
 	TP_STRUCT__entry(
-		__string(	name,		dev_name(dev)	)
+		__string(	name,		regmap_name(map)	)
 	),
 
 	TP_fast_assign(
-		__assign_str(name, dev_name(dev));
+		__assign_str(name, regmap_name(map));
 	),
 
 	TP_printk("%s", __get_str(name))
@@ -194,50 +193,50 @@ DECLARE_EVENT_CLASS(regmap_async,
 
 DEFINE_EVENT(regmap_block, regmap_async_write_start,
 
-	TP_PROTO(struct device *dev, unsigned int reg, int count),
+	TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-	TP_ARGS(dev, reg, count)
+	TP_ARGS(map, reg, count)
 );
 
 DEFINE_EVENT(regmap_async, regmap_async_io_complete,
 
-	TP_PROTO(struct device *dev),
+	TP_PROTO(struct regmap *map),
 
-	TP_ARGS(dev)
+	TP_ARGS(map)
 
 );
 
 DEFINE_EVENT(regmap_async, regmap_async_complete_start,
 
-	TP_PROTO(struct device *dev),
+	TP_PROTO(struct regmap *map),
 
-	TP_ARGS(dev)
+	TP_ARGS(map)
 
 );
 
 DEFINE_EVENT(regmap_async, regmap_async_complete_done,
 
-	TP_PROTO(struct device *dev),
+	TP_PROTO(struct regmap *map),
 
-	TP_ARGS(dev)
+	TP_ARGS(map)
 
 );
 
 TRACE_EVENT(regcache_drop_region,
 
-	TP_PROTO(struct device *dev, unsigned int from,
+	TP_PROTO(struct regmap *map, unsigned int from,
 		 unsigned int to),
 
-	TP_ARGS(dev, from, to),
+	TP_ARGS(map, from, to),
 
 	TP_STRUCT__entry(
-		__string(       name,           dev_name(dev)   )
-		__field(	unsigned int,	from		)
-		__field(	unsigned int,	to		)
+		__string(       name,           regmap_name(map)	)
+		__field(	unsigned int,	from			)
+		__field(	unsigned int,	to			)
 	),
 
 	TP_fast_assign(
-		__assign_str(name, dev_name(dev));
+		__assign_str(name, regmap_name(map));
 		__entry->from = from;
 		__entry->to = to;
 	),
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 0a68d5ae584..13086c3f2a5 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -100,7 +100,7 @@ static inline long __trace_sched_switch_state(struct task_struct *p)
 	/*
 	 * For all intents and purposes a preempted task is a running task.
 	 */
-	if (task_preempt_count(p) & PREEMPT_ACTIVE)
+	if (preempt_count() & PREEMPT_ACTIVE)
 		state = TASK_RUNNING | TASK_STATE_MAX;
 #endif
 
@@ -550,6 +550,282 @@ TRACE_EVENT(sched_wake_idle_without_ipi,
 
 	TP_printk("cpu=%d", __entry->cpu)
 );
+
+/*
+ * Tracepoint for showing tracked load contribution.
+ */
+TRACE_EVENT(sched_task_load_contrib,
+
+       TP_PROTO(struct task_struct *tsk, unsigned long load_contrib),
+
+       TP_ARGS(tsk, load_contrib),
+
+       TP_STRUCT__entry(
+               __array(char, comm, TASK_COMM_LEN)
+               __field(pid_t, pid)
+               __field(unsigned long, load_contrib)
+       ),
+
+       TP_fast_assign(
+               memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+               __entry->pid            = tsk->pid;
+               __entry->load_contrib   = load_contrib;
+       ),
+
+       TP_printk("comm=%s pid=%d load_contrib=%lu",
+                       __entry->comm, __entry->pid,
+                       __entry->load_contrib)
+);
+
+/*
+ * Tracepoint for showing tracked task runnable ratio [0..1023].
+ */
+TRACE_EVENT(sched_task_runnable_ratio,
+
+       TP_PROTO(struct task_struct *tsk, unsigned long ratio),
+
+       TP_ARGS(tsk, ratio),
+
+       TP_STRUCT__entry(
+               __array(char, comm, TASK_COMM_LEN)
+               __field(pid_t, pid)
+               __field(unsigned long, ratio)
+       ),
+
+       TP_fast_assign(
+       memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+               __entry->pid   = tsk->pid;
+               __entry->ratio = ratio;
+       ),
+
+       TP_printk("comm=%s pid=%d ratio=%lu",
+                       __entry->comm, __entry->pid,
+                       __entry->ratio)
+);
+
+/*
+ * Tracepoint for showing tracked rq runnable ratio [0..1023].
+ */
+TRACE_EVENT(sched_rq_runnable_ratio,
+
+       TP_PROTO(int cpu, unsigned long ratio),
+
+       TP_ARGS(cpu, ratio),
+
+       TP_STRUCT__entry(
+               __field(int, cpu)
+               __field(unsigned long, ratio)
+       ),
+
+       TP_fast_assign(
+               __entry->cpu   = cpu;
+               __entry->ratio = ratio;
+       ),
+
+       TP_printk("cpu=%d ratio=%lu",
+                       __entry->cpu,
+                       __entry->ratio)
+);
+
+/*
+ * Tracepoint for showing tracked rq runnable load.
+ */
+TRACE_EVENT(sched_rq_runnable_load,
+
+       TP_PROTO(int cpu, u64 load),
+
+       TP_ARGS(cpu, load),
+
+       TP_STRUCT__entry(
+               __field(int, cpu)
+               __field(u64, load)
+       ),
+
+       TP_fast_assign(
+               __entry->cpu  = cpu;
+               __entry->load = load;
+       ),
+
+       TP_printk("cpu=%d load=%llu",
+                       __entry->cpu,
+                       __entry->load)
+);
+
+TRACE_EVENT(sched_rq_nr_running,
+
+       TP_PROTO(int cpu, unsigned int nr_running, int nr_iowait),
+
+       TP_ARGS(cpu, nr_running, nr_iowait),
+
+       TP_STRUCT__entry(
+               __field(int, cpu)
+               __field(unsigned int, nr_running)
+               __field(int, nr_iowait)
+       ),
+
+       TP_fast_assign(
+               __entry->cpu  = cpu;
+               __entry->nr_running = nr_running;
+               __entry->nr_iowait = nr_iowait;
+       ),
+
+       TP_printk("cpu=%d nr_running=%u nr_iowait=%d",
+                       __entry->cpu,
+                       __entry->nr_running, __entry->nr_iowait)
+);
+
+/*
+ * Tracepoint for showing tracked task cpu usage ratio [0..1023].
+ */
+TRACE_EVENT(sched_task_usage_ratio,
+
+       TP_PROTO(struct task_struct *tsk, unsigned long ratio),
+
+       TP_ARGS(tsk, ratio),
+
+       TP_STRUCT__entry(
+               __array(char, comm, TASK_COMM_LEN)
+               __field(pid_t, pid)
+               __field(unsigned long, ratio)
+       ),
+
+       TP_fast_assign(
+       memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+               __entry->pid   = tsk->pid;
+               __entry->ratio = ratio;
+       ),
+
+       TP_printk("comm=%s pid=%d ratio=%lu",
+                       __entry->comm, __entry->pid,
+                       __entry->ratio)
+);
+
+/*
+ * Tracepoint for HMP (CONFIG_SCHED_HMP) task migrations,
+ * marking the forced transition of runnable or running tasks.
+ */
+TRACE_EVENT(sched_hmp_migrate_force_running,
+
+	TP_PROTO(struct task_struct *tsk, int running),
+
+	TP_ARGS(tsk, running),
+
+	TP_STRUCT__entry(
+		__array(char, comm, TASK_COMM_LEN)
+		__field(int, running)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->running = running;
+	),
+
+	TP_printk("running=%d comm=%s",
+		__entry->running, __entry->comm)
+);
+
+/*
+ * Tracepoint for HMP (CONFIG_SCHED_HMP) task migrations,
+ * marking the forced transition of runnable or running
+ * tasks when a task is about to go idle.
+ */
+TRACE_EVENT(sched_hmp_migrate_idle_running,
+
+	TP_PROTO(struct task_struct *tsk, int running),
+
+	TP_ARGS(tsk, running),
+
+	TP_STRUCT__entry(
+		__array(char, comm, TASK_COMM_LEN)
+		__field(int, running)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->running = running;
+	),
+
+	TP_printk("running=%d comm=%s",
+		__entry->running, __entry->comm)
+);
+
+/*
+ * Tracepoint for HMP (CONFIG_SCHED_HMP) task migrations.
+ */
+#define HMP_MIGRATE_WAKEUP 0
+#define HMP_MIGRATE_FORCE  1
+#define HMP_MIGRATE_OFFLOAD 2
+#define HMP_MIGRATE_IDLE_PULL 3
+#define HMP_MIGRATE_FORCED_IDLE_PULL 4
+TRACE_EVENT(sched_hmp_migrate,
+
+	TP_PROTO(struct task_struct *tsk, int dest, int force),
+
+	TP_ARGS(tsk, dest, force),
+
+	TP_STRUCT__entry(
+		__array(char, comm, TASK_COMM_LEN)
+		__field(pid_t, pid)
+		__field(int,  dest)
+		__field(int,  force)
+	),
+
+	TP_fast_assign(
+	memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid   = tsk->pid;
+		__entry->dest  = dest;
+		__entry->force = force;
+	),
+
+	TP_printk("comm=%s pid=%d dest=%d force=%d",
+			__entry->comm, __entry->pid,
+			__entry->dest, __entry->force)
+);
+
+TRACE_EVENT(sched_hmp_offload_abort,
+
+	TP_PROTO(int cpu, int data, char *label),
+
+	TP_ARGS(cpu,data,label),
+
+	TP_STRUCT__entry(
+		__array(char, label, 64)
+		__field(int, cpu)
+		__field(int, data)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->label, label, 64);
+		__entry->cpu   = cpu;
+		__entry->data = data;
+	),
+
+	TP_printk("cpu=%d data=%d label=%63s",
+			__entry->cpu, __entry->data,
+			__entry->label)
+);
+
+TRACE_EVENT(sched_hmp_offload_succeed,
+
+	TP_PROTO(int cpu, int dest_cpu),
+
+	TP_ARGS(cpu,dest_cpu),
+
+	TP_STRUCT__entry(
+		__field(int, cpu)
+		__field(int, dest_cpu)
+	),
+
+	TP_fast_assign(
+		__entry->cpu   = cpu;
+		__entry->dest_cpu = dest_cpu;
+	),
+
+	TP_printk("cpu=%d dest=%d",
+			__entry->cpu,
+			__entry->dest_cpu)
+);
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/smp.h b/include/trace/events/smp.h
new file mode 100644
index 00000000000..da0baf27a39
--- /dev/null
+++ b/include/trace/events/smp.h
@@ -0,0 +1,90 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM smp
+
+#if !defined(_TRACE_SMP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SMP_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(smp_call_class,
+
+	TP_PROTO(void * fnc),
+
+	TP_ARGS(fnc),
+
+	TP_STRUCT__entry(
+		__field( void *, func )
+	),
+
+	TP_fast_assign(
+		__entry->func = fnc;
+	),
+
+	TP_printk("func=%pf", __entry->func)
+);
+
+/**
+ * smp_call_func_entry - called in the generic smp-cross-call-handler
+ * 						 immediately before calling the destination
+ * 						 function
+ * @func:  function pointer
+ *
+ * When used in combination with the smp_call_func_exit tracepoint
+ * we can determine the cross-call runtime.
+ */
+DEFINE_EVENT(smp_call_class, smp_call_func_entry,
+
+	TP_PROTO(void * fnc),
+
+	TP_ARGS(fnc)
+);
+
+/**
+ * smp_call_func_exit - called in the generic smp-cross-call-handler
+ * 						immediately after the destination function
+ * 						returns
+ * @func:  function pointer
+ *
+ * When used in combination with the smp_call_entry tracepoint
+ * we can determine the cross-call runtime.
+ */
+DEFINE_EVENT(smp_call_class, smp_call_func_exit,
+
+	TP_PROTO(void * fnc),
+
+	TP_ARGS(fnc)
+);
+
+/**
+ * smp_call_func_send - called as destination function is set
+ * 						in the per-cpu storage
+ * @func:  function pointer
+ * @dest:  cpu to send to
+ *
+ * When used in combination with the smp_cross_call_entry tracepoint
+ * we can determine the call-to-run latency.
+ */
+TRACE_EVENT(smp_call_func_send,
+
+	TP_PROTO(void * func, int dest),
+
+	TP_ARGS(func, dest),
+
+	TP_STRUCT__entry(
+		__field(	void * 	,	func )
+		__field(	int		,	dest )
+	),
+
+	TP_fast_assign(
+		__entry->func = func;
+		__entry->dest = dest;
+	),
+
+	TP_printk("dest=%d func=%pf", __entry->dest,
+			__entry->func)
+);
+
+#endif /*  _TRACE_SMP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/thermal.h b/include/trace/events/thermal.h
index 0f4f95d63c0..5738bb3e234 100644
--- a/include/trace/events/thermal.h
+++ b/include/trace/events/thermal.h
@@ -4,6 +4,7 @@
 #if !defined(_TRACE_THERMAL_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_THERMAL_H
 
+#include <linux/devfreq.h>
 #include <linux/thermal.h>
 #include <linux/tracepoint.h>
 
@@ -77,6 +78,116 @@ TRACE_EVENT(thermal_zone_trip,
 		__entry->trip_type)
 );
 
+TRACE_EVENT(thermal_power_cpu_get_power,
+	TP_PROTO(const struct cpumask *cpus, unsigned long freq, u32 *load,
+		size_t load_len, u32 dynamic_power, u32 static_power),
+
+	TP_ARGS(cpus, freq, load, load_len, dynamic_power, static_power),
+
+	TP_STRUCT__entry(
+		__bitmask(cpumask, num_possible_cpus())
+		__field(unsigned long, freq          )
+		__dynamic_array(u32,   load, load_len)
+		__field(size_t,        load_len      )
+		__field(u32,           dynamic_power )
+		__field(u32,           static_power  )
+	),
+
+	TP_fast_assign(
+		__assign_bitmask(cpumask, cpumask_bits(cpus),
+				num_possible_cpus());
+		__entry->freq = freq;
+		memcpy(__get_dynamic_array(load), load,
+			load_len * sizeof(*load));
+		__entry->load_len = load_len;
+		__entry->dynamic_power = dynamic_power;
+		__entry->static_power = static_power;
+	),
+
+	TP_printk("cpus=%s freq=%lu load={%s} dynamic_power=%d static_power=%d",
+		__get_bitmask(cpumask), __entry->freq,
+		__print_array(__get_dynamic_array(load), __entry->load_len, 4),
+		__entry->dynamic_power, __entry->static_power)
+);
+
+TRACE_EVENT(thermal_power_cpu_limit,
+	TP_PROTO(const struct cpumask *cpus, unsigned int freq,
+		unsigned long cdev_state, u32 power),
+
+	TP_ARGS(cpus, freq, cdev_state, power),
+
+	TP_STRUCT__entry(
+		__bitmask(cpumask, num_possible_cpus())
+		__field(unsigned int,  freq      )
+		__field(unsigned long, cdev_state)
+		__field(u32,           power     )
+	),
+
+	TP_fast_assign(
+		__assign_bitmask(cpumask, cpumask_bits(cpus),
+				num_possible_cpus());
+		__entry->freq = freq;
+		__entry->cdev_state = cdev_state;
+		__entry->power = power;
+	),
+
+	TP_printk("cpus=%s freq=%u cdev_state=%lu power=%u",
+		__get_bitmask(cpumask), __entry->freq, __entry->cdev_state,
+		__entry->power)
+);
+
+TRACE_EVENT(thermal_power_devfreq_get_power,
+	TP_PROTO(struct thermal_cooling_device *cdev,
+		 struct devfreq_dev_status *status, unsigned long freq,
+		u32 dynamic_power, u32 static_power),
+
+	TP_ARGS(cdev, status,  freq, dynamic_power, static_power),
+
+	TP_STRUCT__entry(
+		__string(type,         cdev->type    )
+		__field(unsigned long, freq          )
+		__field(u32,           load          )
+		__field(u32,           dynamic_power )
+		__field(u32,           static_power  )
+	),
+
+	TP_fast_assign(
+		__assign_str(type, cdev->type);
+		__entry->freq = freq;
+		__entry->load = (100 * status->busy_time) / status->total_time;
+		__entry->dynamic_power = dynamic_power;
+		__entry->static_power = static_power;
+	),
+
+	TP_printk("type=%s freq=%lu load=%u dynamic_power=%u static_power=%u",
+		__get_str(type), __entry->freq,
+		__entry->load, __entry->dynamic_power, __entry->static_power)
+);
+
+TRACE_EVENT(thermal_power_devfreq_limit,
+	TP_PROTO(struct thermal_cooling_device *cdev, unsigned long freq,
+		unsigned long cdev_state, u32 power),
+
+	TP_ARGS(cdev, freq, cdev_state, power),
+
+	TP_STRUCT__entry(
+		__string(type,         cdev->type)
+		__field(unsigned int,  freq      )
+		__field(unsigned long, cdev_state)
+		__field(u32,           power     )
+	),
+
+	TP_fast_assign(
+		__assign_str(type, cdev->type);
+		__entry->freq = freq;
+		__entry->cdev_state = cdev_state;
+		__entry->power = power;
+	),
+
+	TP_printk("type=%s freq=%u cdev_state=%lu power=%u",
+		__get_str(type), __entry->freq, __entry->cdev_state,
+		__entry->power)
+);
 #endif /* _TRACE_THERMAL_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/thermal_power_allocator.h b/include/trace/events/thermal_power_allocator.h
new file mode 100644
index 00000000000..12e1321c4e0
--- /dev/null
+++ b/include/trace/events/thermal_power_allocator.h
@@ -0,0 +1,87 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM thermal_power_allocator
+
+#if !defined(_TRACE_THERMAL_POWER_ALLOCATOR_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_THERMAL_POWER_ALLOCATOR_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(thermal_power_allocator,
+	TP_PROTO(struct thermal_zone_device *tz, u32 *req_power,
+		 u32 total_req_power, u32 *granted_power,
+		 u32 total_granted_power, size_t num_actors,
+		 u32 power_range, u32 max_allocatable_power,
+		 unsigned long current_temp, s32 delta_temp),
+	TP_ARGS(tz, req_power, total_req_power, granted_power,
+		total_granted_power, num_actors, power_range,
+		max_allocatable_power, current_temp, delta_temp),
+	TP_STRUCT__entry(
+		__field(int,           tz_id          )
+		__dynamic_array(u32,   req_power, num_actors    )
+		__field(u32,           total_req_power          )
+		__dynamic_array(u32,   granted_power, num_actors)
+		__field(u32,           total_granted_power      )
+		__field(size_t,        num_actors               )
+		__field(u32,           power_range              )
+		__field(u32,           max_allocatable_power    )
+		__field(unsigned long, current_temp             )
+		__field(s32,           delta_temp               )
+	),
+	TP_fast_assign(
+		__entry->tz_id = tz->id;
+		memcpy(__get_dynamic_array(req_power), req_power,
+			num_actors * sizeof(*req_power));
+		__entry->total_req_power = total_req_power;
+		memcpy(__get_dynamic_array(granted_power), granted_power,
+			num_actors * sizeof(*granted_power));
+		__entry->total_granted_power = total_granted_power;
+		__entry->num_actors = num_actors;
+		__entry->power_range = power_range;
+		__entry->max_allocatable_power = max_allocatable_power;
+		__entry->current_temp = current_temp;
+		__entry->delta_temp = delta_temp;
+	),
+
+	TP_printk("thermal_zone_id=%d req_power={%s} total_req_power=%u granted_power={%s} total_granted_power=%u power_range=%u max_allocatable_power=%u current_temperature=%lu delta_temperature=%d",
+		__entry->tz_id,
+		__print_array(__get_dynamic_array(req_power),
+                              __entry->num_actors, 4),
+		__entry->total_req_power,
+		__print_array(__get_dynamic_array(granted_power),
+                              __entry->num_actors, 4),
+		__entry->total_granted_power, __entry->power_range,
+		__entry->max_allocatable_power, __entry->current_temp,
+		__entry->delta_temp)
+);
+
+TRACE_EVENT(thermal_power_allocator_pid,
+	TP_PROTO(struct thermal_zone_device *tz, s32 err, s32 err_integral,
+		 s64 p, s64 i, s64 d, s32 output),
+	TP_ARGS(tz, err, err_integral, p, i, d, output),
+	TP_STRUCT__entry(
+		__field(int, tz_id       )
+		__field(s32, err         )
+		__field(s32, err_integral)
+		__field(s64, p           )
+		__field(s64, i           )
+		__field(s64, d           )
+		__field(s32, output      )
+	),
+	TP_fast_assign(
+		__entry->tz_id = tz->id;
+		__entry->err = err;
+		__entry->err_integral = err_integral;
+		__entry->p = p;
+		__entry->i = i;
+		__entry->d = d;
+		__entry->output = output;
+	),
+
+	TP_printk("thermal_zone_id=%d err=%d err_integral=%d p=%lld i=%lld d=%lld output=%d",
+		  __entry->tz_id, __entry->err, __entry->err_integral,
+		  __entry->p, __entry->i, __entry->d, __entry->output)
+);
+#endif /* _TRACE_THERMAL_POWER_ALLOCATOR_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/tlb.h b/include/trace/events/tlb.h
index 13391d28810..0e763576515 100644
--- a/include/trace/events/tlb.h
+++ b/include/trace/events/tlb.h
@@ -13,11 +13,13 @@
 	{ TLB_LOCAL_SHOOTDOWN,		"local shootdown" },		\
 	{ TLB_LOCAL_MM_SHOOTDOWN,	"local mm shootdown" }
 
-TRACE_EVENT(tlb_flush,
+TRACE_EVENT_CONDITION(tlb_flush,
 
 	TP_PROTO(int reason, unsigned long pages),
 	TP_ARGS(reason, pages),
 
+	TP_CONDITION(cpu_online(smp_processor_id())),
+
 	TP_STRUCT__entry(
 		__field(	  int, reason)
 		__field(unsigned long,  pages)
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 26b4f2e1327..f5d9371fbdf 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -263,6 +263,14 @@
 #undef __print_hex
 #define __print_hex(buf, buf_len) ftrace_print_hex_seq(p, buf, buf_len)
 
+#undef __print_array
+#define __print_array(array, count, el_size)				\
+	({								\
+		BUILD_BUG_ON(el_size != 1 && el_size != 2 &&		\
+			     el_size != 4 && el_size != 8);		\
+		ftrace_print_array_seq(p, array, count, el_size);	\
+	})
+
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 static notrace enum print_line_t					\
@@ -676,6 +684,7 @@ static inline void ftrace_test_probe_##call(void)			\
 #undef __get_dynamic_array_len
 #undef __get_str
 #undef __get_bitmask
+#undef __print_array
 
 #undef TP_printk
 #define TP_printk(fmt, args...) "\"" fmt "\", "  __stringify(args)
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 50d0fb41a3b..76d2edea5bd 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -1034,6 +1034,7 @@ struct drm_radeon_cs {
 #define RADEON_INFO_VRAM_USAGE		0x1e
 #define RADEON_INFO_GTT_USAGE		0x1f
 #define RADEON_INFO_ACTIVE_CU_COUNT	0x20
+#define RADEON_INFO_VA_UNMAP_WORKING	0x25
 
 struct drm_radeon_info {
 	uint32_t		request;
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 8523f9bb72f..fe473953116 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -383,6 +383,7 @@ header-y += tcp.h
 header-y += tcp_metrics.h
 header-y += telephony.h
 header-y += termios.h
+header-y += thermal.h
 header-y += time.h
 header-y += times.h
 header-y += timex.h
diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index d4dbef14d4d..584bb0113e2 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -365,7 +365,9 @@ enum {
 #define AUDIT_ARCH_PARISC	(EM_PARISC)
 #define AUDIT_ARCH_PARISC64	(EM_PARISC|__AUDIT_ARCH_64BIT)
 #define AUDIT_ARCH_PPC		(EM_PPC)
+/* do not define AUDIT_ARCH_PPCLE since it is not supported by audit */
 #define AUDIT_ARCH_PPC64	(EM_PPC64|__AUDIT_ARCH_64BIT)
+#define AUDIT_ARCH_PPC64LE	(EM_PPC64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
 #define AUDIT_ARCH_S390		(EM_S390)
 #define AUDIT_ARCH_S390X	(EM_S390|__AUDIT_ARCH_64BIT)
 #define AUDIT_ARCH_SH		(EM_SH)
diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h
index 3e4323a3918..94ffe0c83ce 100644
--- a/include/uapi/linux/can/netlink.h
+++ b/include/uapi/linux/can/netlink.h
@@ -98,6 +98,7 @@ struct can_ctrlmode {
 #define CAN_CTRLMODE_BERR_REPORTING	0x10	/* Bus-error reporting */
 #define CAN_CTRLMODE_FD			0x20	/* CAN FD mode */
 #define CAN_CTRLMODE_PRESUME_ACK	0x40	/* Ignore missing CAN ACKs */
+#define CAN_CTRLMODE_FD_NON_ISO		0x80	/* CAN FD in non-ISO mode */
 
 /*
  * CAN device statistics
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index ea9bf2561b9..71e1d0ed92f 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -397,6 +397,7 @@ typedef struct elf64_shdr {
 #define NT_ARM_TLS	0x401		/* ARM TLS register */
 #define NT_ARM_HW_BREAK	0x402		/* ARM hardware breakpoint registers */
 #define NT_ARM_HW_WATCH	0x403		/* ARM hardware watchpoint registers */
+#define NT_ARM_SYSTEM_CALL	0x404	/* ARM system call number */
 #define NT_METAG_CBUF	0x500		/* Metag catch buffer registers */
 #define NT_METAG_RPIPE	0x501		/* Metag read pipeline state */
 #define NT_METAG_TLS	0x502		/* Metag TLS pointer */
diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
index 2b82d7e3097..743e3008df6 100644
--- a/include/uapi/linux/fib_rules.h
+++ b/include/uapi/linux/fib_rules.h
@@ -49,6 +49,8 @@ enum {
 	FRA_TABLE,	/* Extended table id */
 	FRA_FWMASK,	/* mask for netfilter mark */
 	FRA_OIFNAME,
+	FRA_UID_START,	/* UID range */
+	FRA_UID_END,
 	__FRA_MAX
 };
 
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 3735fa0a678..48e59f948ea 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -158,6 +158,8 @@ struct inodes_stat_t {
 #define FITHAW		_IOWR('X', 120, int)	/* Thaw */
 #define FITRIM		_IOWR('X', 121, struct fstrim_range)	/* Trim */
 
+#define FIDTRIM	_IOWR('f', 128, struct fstrim_range)	/* Deep discard trim */
+
 #define	FS_IOC_GETFLAGS			_IOR('f', 1, long)
 #define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
 #define	FS_IOC_GETVERSION		_IOR('v', 1, long)
diff --git a/include/uapi/linux/hyperv.h b/include/uapi/linux/hyperv.h
index 0a8e6badb29..bb1cb73c927 100644
--- a/include/uapi/linux/hyperv.h
+++ b/include/uapi/linux/hyperv.h
@@ -134,6 +134,7 @@ struct hv_start_fcopy {
 
 struct hv_do_fcopy {
 	struct hv_fcopy_hdr hdr;
+	__u32   pad;
 	__u64	offset;
 	__u32	size;
 	__u8	data[DATA_FRAGMENT];
diff --git a/include/uapi/linux/if_pppolac.h b/include/uapi/linux/if_pppolac.h
new file mode 100644
index 00000000000..b7eb8153ef6
--- /dev/null
+++ b/include/uapi/linux/if_pppolac.h
@@ -0,0 +1,33 @@
+/* include/uapi/linux/if_pppolac.h
+ *
+ * Header for PPP on L2TP Access Concentrator / PPPoLAC Socket (RFC 2661)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ * Author: Chia-chi Yeh <chiachi@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _UAPI_LINUX_IF_PPPOLAC_H
+#define _UAPI_LINUX_IF_PPPOLAC_H
+
+#include <linux/socket.h>
+#include <linux/types.h>
+
+struct sockaddr_pppolac {
+	sa_family_t	sa_family;	/* AF_PPPOX */
+	unsigned int	sa_protocol;	/* PX_PROTO_OLAC */
+	int		udp_socket;
+	struct __attribute__((packed)) {
+		__u16	tunnel, session;
+	} local, remote;
+} __attribute__((packed));
+
+#endif /* _UAPI_LINUX_IF_PPPOLAC_H */
diff --git a/include/uapi/linux/if_pppopns.h b/include/uapi/linux/if_pppopns.h
new file mode 100644
index 00000000000..a392b52ea6e
--- /dev/null
+++ b/include/uapi/linux/if_pppopns.h
@@ -0,0 +1,32 @@
+/* include/uapi/linux/if_pppopns.h
+ *
+ * Header for PPP on PPTP Network Server / PPPoPNS Socket (RFC 2637)
+ *
+ * Copyright (C) 2009 Google, Inc.
+ * Author: Chia-chi Yeh <chiachi@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _UAPI_LINUX_IF_PPPOPNS_H
+#define _UAPI_LINUX_IF_PPPOPNS_H
+
+#include <linux/socket.h>
+#include <linux/types.h>
+
+struct sockaddr_pppopns {
+	sa_family_t	sa_family;	/* AF_PPPOX */
+	unsigned int	sa_protocol;	/* PX_PROTO_OPNS */
+	int		tcp_socket;
+	__u16		local;
+	__u16		remote;
+} __attribute__((packed));
+
+#endif /* _UAPI_LINUX_IF_PPPOPNS_H */
diff --git a/include/uapi/linux/if_pppox.h b/include/uapi/linux/if_pppox.h
index e128769331b..5861d45bc51 100644
--- a/include/uapi/linux/if_pppox.h
+++ b/include/uapi/linux/if_pppox.h
@@ -23,6 +23,8 @@
 #include <linux/socket.h>
 #include <linux/if_ether.h>
 #include <linux/if_pppol2tp.h>
+#include <linux/if_pppolac.h>
+#include <linux/if_pppopns.h>
 
 /* For user-space programs to pick up these definitions
  * which they wouldn't get otherwise without defining __KERNEL__
@@ -56,7 +58,9 @@ struct pptp_addr {
 #define PX_PROTO_OE    0 /* Currently just PPPoE */
 #define PX_PROTO_OL2TP 1 /* Now L2TP also */
 #define PX_PROTO_PPTP  2
-#define PX_MAX_PROTO   3
+#define PX_PROTO_OLAC  3
+#define PX_PROTO_OPNS  4
+#define PX_MAX_PROTO   5
 
 struct sockaddr_pppox {
 	__kernel_sa_family_t sa_family;       /* address family, AF_PPPOX */
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index 74a2a177349..79b12b004ad 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -149,7 +149,7 @@ struct in6_flowlabel_req {
 /*
  *	IPV6 socket options
  */
-
+#if __UAPI_DEF_IPV6_OPTIONS
 #define IPV6_ADDRFORM		1
 #define IPV6_2292PKTINFO	2
 #define IPV6_2292HOPOPTS	3
@@ -196,6 +196,7 @@ struct in6_flowlabel_req {
 
 #define IPV6_IPSEC_POLICY	34
 #define IPV6_XFRM_POLICY	35
+#endif
 
 /*
  * Multicast:
diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h
index a1d7e931ab7..cc75b7bed6c 100644
--- a/include/uapi/linux/input.h
+++ b/include/uapi/linux/input.h
@@ -152,7 +152,12 @@ struct input_keymap_entry {
 #define EVIOCGEFFECTS		_IOR('E', 0x84, int)			/* Report number of effects playable at the same time */
 
 #define EVIOCGRAB		_IOW('E', 0x90, int)			/* Grab/Release device */
-#define EVIOCREVOKE		_IOW('E', 0x91, int)			/* Revoke device access */
+
+/* HACK: disable conflicting EVIOCREVOKE until Android userspace stops using EVIOCSSUSPENDBLOCK */
+/*#define EVIOCREVOKE		_IOW('E', 0x91, int)*/			/* Revoke device access */
+
+#define EVIOCGSUSPENDBLOCK	_IOR('E', 0x91, int)			/* get suspend block enable */
+#define EVIOCSSUSPENDBLOCK	_IOW('E', 0x91, int)			/* set suspend block enable */
 
 #define EVIOCSCLOCKID		_IOW('E', 0xa0, int)			/* Set clockid to be used for timestamps */
 
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index efa2666f4b8..187d9f6ccb0 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -160,10 +160,12 @@ enum {
 	DEVCONF_ACCEPT_DAD,
 	DEVCONF_FORCE_TLLAO,
 	DEVCONF_NDISC_NOTIFY,
+	DEVCONF_ACCEPT_RA_RT_TABLE,
 	DEVCONF_MLDV1_UNSOLICITED_REPORT_INTERVAL,
 	DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL,
 	DEVCONF_SUPPRESS_FRAG_NDISC,
 	DEVCONF_ACCEPT_RA_FROM_LOCAL,
+	DEVCONF_USE_OPTIMISTIC,
 	DEVCONF_MAX
 };
 
diff --git a/include/uapi/linux/keychord.h b/include/uapi/linux/keychord.h
new file mode 100644
index 00000000000..ea7cf4d27bb
--- /dev/null
+++ b/include/uapi/linux/keychord.h
@@ -0,0 +1,52 @@
+/*
+ *  Key chord input driver
+ *
+ * Copyright (C) 2008 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+*/
+
+#ifndef _UAPI_LINUX_KEYCHORD_H_
+#define _UAPI_LINUX_KEYCHORD_H_
+
+#include <linux/input.h>
+
+#define KEYCHORD_VERSION		1
+
+/*
+ * One or more input_keychord structs are written to /dev/keychord
+ * at once to specify the list of keychords to monitor.
+ * Reading /dev/keychord returns the id of a keychord when the
+ * keychord combination is pressed.  A keychord is signalled when
+ * all of the keys in the keycode list are in the pressed state.
+ * The order in which the keys are pressed does not matter.
+ * The keychord will not be signalled if keys not in the keycode
+ * list are pressed.
+ * Keychords will not be signalled on key release events.
+ */
+struct input_keychord {
+	/* should be KEYCHORD_VERSION */
+	__u16 version;
+	/*
+	 * client specified ID, returned from read()
+	 * when this keychord is pressed.
+	 */
+	__u16 id;
+
+	/* number of keycodes in this keychord */
+	__u16 count;
+
+	/* variable length array of keycodes */
+	__u16 keycodes[];
+};
+
+#endif	/* _UAPI_LINUX_KEYCHORD_H_ */
diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h
index c140620dad9..e28807ad17f 100644
--- a/include/uapi/linux/libc-compat.h
+++ b/include/uapi/linux/libc-compat.h
@@ -69,6 +69,7 @@
 #define __UAPI_DEF_SOCKADDR_IN6		0
 #define __UAPI_DEF_IPV6_MREQ		0
 #define __UAPI_DEF_IPPROTO_V6		0
+#define __UAPI_DEF_IPV6_OPTIONS		0
 
 #else
 
@@ -82,6 +83,7 @@
 #define __UAPI_DEF_SOCKADDR_IN6		1
 #define __UAPI_DEF_IPV6_MREQ		1
 #define __UAPI_DEF_IPPROTO_V6		1
+#define __UAPI_DEF_IPV6_OPTIONS		1
 
 #endif /* _NETINET_IN_H */
 
@@ -103,6 +105,7 @@
 #define __UAPI_DEF_SOCKADDR_IN6		1
 #define __UAPI_DEF_IPV6_MREQ		1
 #define __UAPI_DEF_IPPROTO_V6		1
+#define __UAPI_DEF_IPV6_OPTIONS		1
 
 /* Definitions for xattr.h */
 #define __UAPI_DEF_XATTR		1
diff --git a/include/uapi/linux/netfilter/xt_IDLETIMER.h b/include/uapi/linux/netfilter/xt_IDLETIMER.h
index 208ae938733..faaa28b3d06 100644
--- a/include/uapi/linux/netfilter/xt_IDLETIMER.h
+++ b/include/uapi/linux/netfilter/xt_IDLETIMER.h
@@ -4,6 +4,7 @@
  * Header file for Xtables timer target module.
  *
  * Copyright (C) 2004, 2010 Nokia Corporation
+ *
  * Written by Timo Teras <ext-timo.teras@nokia.com>
  *
  * Converted to x_tables and forward-ported to 2.6.34
@@ -32,12 +33,19 @@
 #include <linux/types.h>
 
 #define MAX_IDLETIMER_LABEL_SIZE 28
+#define NLMSG_MAX_SIZE 64
+
+#define NL_EVENT_TYPE_INACTIVE 0
+#define NL_EVENT_TYPE_ACTIVE 1
 
 struct idletimer_tg_info {
 	__u32 timeout;
 
 	char label[MAX_IDLETIMER_LABEL_SIZE];
 
+	/* Use netlink messages for notification in addition to sysfs */
+	__u8 send_nl_msg;
+
 	/* for kernel module internal use only */
 	struct idletimer_tg *timer __attribute__((aligned(8)));
 };
diff --git a/include/uapi/linux/netfilter/xt_socket.h b/include/uapi/linux/netfilter/xt_socket.h
index 6315e2ac347..55076a32bdf 100644
--- a/include/uapi/linux/netfilter/xt_socket.h
+++ b/include/uapi/linux/netfilter/xt_socket.h
@@ -18,4 +18,9 @@ struct xt_socket_mtinfo2 {
 };
 #define XT_SOCKET_FLAGS_V2 (XT_SOCKET_TRANSPARENT | XT_SOCKET_NOWILDCARD)
 
+struct sock *xt_socket_get4_sk(const struct sk_buff *skb,
+			       struct xt_action_param *par);
+struct sock *xt_socket_get6_sk(const struct sk_buff *skb,
+			       struct xt_action_param *par);
+
 #endif /* _XT_SOCKET_H */
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 513df75d0fc..933ff2a9a03 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -179,4 +179,13 @@ struct prctl_mm_map {
 #define PR_SET_THP_DISABLE	41
 #define PR_GET_THP_DISABLE	42
 
+/* Sets the timerslack for arbitrary threads
+ * arg2 slack value, 0 means "use default"
+ * arg3 pid of the thread whose timer slack needs to be set
+ */
+#define PR_SET_TIMERSLACK_PID 43
+
+#define PR_SET_VMA		0x53564d41
+# define PR_SET_VMA_ANON_NAME		0
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index eb0f1a554d7..01757b79db6 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -297,6 +297,7 @@ enum rtattr_type_t {
 	RTA_TABLE,
 	RTA_MARK,
 	RTA_MFC_STATS,
+	RTA_UID,
 	__RTA_MAX
 };
 
diff --git a/include/uapi/linux/sockios.h b/include/uapi/linux/sockios.h
index e888b1aed69..623e9aab645 100644
--- a/include/uapi/linux/sockios.h
+++ b/include/uapi/linux/sockios.h
@@ -65,6 +65,7 @@
 #define SIOCDIFADDR	0x8936		/* delete PA address		*/
 #define	SIOCSIFHWBROADCAST	0x8937	/* set hardware broadcast addr	*/
 #define SIOCGIFCOUNT	0x8938		/* get number of devices */
+#define SIOCKILLADDR	0x8939		/* kill sockets with this local addr */
 
 #define SIOCGIFBR	0x8940		/* Bridging support		*/
 #define SIOCSIFBR	0x8941		/* Set bridging options 	*/
diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h
index 7dcfbe6771b..b483d1909d3 100644
--- a/include/uapi/linux/target_core_user.h
+++ b/include/uapi/linux/target_core_user.h
@@ -6,10 +6,6 @@
 #include <linux/types.h>
 #include <linux/uio.h>
 
-#ifndef __packed
-#define __packed                        __attribute__((packed))
-#endif
-
 #define TCMU_VERSION "1.0"
 
 /*
diff --git a/include/uapi/linux/thermal.h b/include/uapi/linux/thermal.h
new file mode 100644
index 00000000000..ac553585598
--- /dev/null
+++ b/include/uapi/linux/thermal.h
@@ -0,0 +1,35 @@
+#ifndef _UAPI_LINUX_THERMAL_H
+#define _UAPI_LINUX_THERMAL_H
+
+#define THERMAL_NAME_LENGTH	20
+
+/* Adding event notification support elements */
+#define THERMAL_GENL_FAMILY_NAME                "thermal_event"
+#define THERMAL_GENL_VERSION                    0x01
+#define THERMAL_GENL_MCAST_GROUP_NAME           "thermal_mc_grp"
+
+/* Events supported by Thermal Netlink */
+enum events {
+	THERMAL_AUX0,
+	THERMAL_AUX1,
+	THERMAL_CRITICAL,
+	THERMAL_DEV_FAULT,
+};
+
+/* attributes of thermal_genl_family */
+enum {
+	THERMAL_GENL_ATTR_UNSPEC,
+	THERMAL_GENL_ATTR_EVENT,
+	__THERMAL_GENL_ATTR_MAX,
+};
+#define THERMAL_GENL_ATTR_MAX (__THERMAL_GENL_ATTR_MAX - 1)
+
+/* commands supported by the thermal_genl_family */
+enum {
+	THERMAL_GENL_CMD_UNSPEC,
+	THERMAL_GENL_CMD_EVENT,
+	__THERMAL_GENL_CMD_MAX,
+};
+#define THERMAL_GENL_CMD_MAX (__THERMAL_GENL_CMD_MAX - 1)
+
+#endif /* _UAPI_LINUX_THERMAL_H */
diff --git a/include/uapi/linux/usb/f_accessory.h b/include/uapi/linux/usb/f_accessory.h
new file mode 100644
index 00000000000..0baeb7d0d74
--- /dev/null
+++ b/include/uapi/linux/usb/f_accessory.h
@@ -0,0 +1,146 @@
+/*
+ * Gadget Function Driver for Android USB accessories
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _UAPI_LINUX_USB_F_ACCESSORY_H
+#define _UAPI_LINUX_USB_F_ACCESSORY_H
+
+/* Use Google Vendor ID when in accessory mode */
+#define USB_ACCESSORY_VENDOR_ID 0x18D1
+
+
+/* Product ID to use when in accessory mode */
+#define USB_ACCESSORY_PRODUCT_ID 0x2D00
+
+/* Product ID to use when in accessory mode and adb is enabled */
+#define USB_ACCESSORY_ADB_PRODUCT_ID 0x2D01
+
+/* Indexes for strings sent by the host via ACCESSORY_SEND_STRING */
+#define ACCESSORY_STRING_MANUFACTURER   0
+#define ACCESSORY_STRING_MODEL          1
+#define ACCESSORY_STRING_DESCRIPTION    2
+#define ACCESSORY_STRING_VERSION        3
+#define ACCESSORY_STRING_URI            4
+#define ACCESSORY_STRING_SERIAL         5
+
+/* Control request for retrieving device's protocol version
+ *
+ *	requestType:    USB_DIR_IN | USB_TYPE_VENDOR
+ *	request:        ACCESSORY_GET_PROTOCOL
+ *	value:          0
+ *	index:          0
+ *	data            version number (16 bits little endian)
+ *                     1 for original accessory support
+ *                     2 adds HID and device to host audio support
+ */
+#define ACCESSORY_GET_PROTOCOL  51
+
+/* Control request for host to send a string to the device
+ *
+ *	requestType:    USB_DIR_OUT | USB_TYPE_VENDOR
+ *	request:        ACCESSORY_SEND_STRING
+ *	value:          0
+ *	index:          string ID
+ *	data            zero terminated UTF8 string
+ *
+ *  The device can later retrieve these strings via the
+ *  ACCESSORY_GET_STRING_* ioctls
+ */
+#define ACCESSORY_SEND_STRING   52
+
+/* Control request for starting device in accessory mode.
+ * The host sends this after setting all its strings to the device.
+ *
+ *	requestType:    USB_DIR_OUT | USB_TYPE_VENDOR
+ *	request:        ACCESSORY_START
+ *	value:          0
+ *	index:          0
+ *	data            none
+ */
+#define ACCESSORY_START         53
+
+/* Control request for registering a HID device.
+ * Upon registering, a unique ID is sent by the accessory in the
+ * value parameter. This ID will be used for future commands for
+ * the device
+ *
+ *	requestType:    USB_DIR_OUT | USB_TYPE_VENDOR
+ *	request:        ACCESSORY_REGISTER_HID_DEVICE
+ *	value:          Accessory assigned ID for the HID device
+ *	index:          total length of the HID report descriptor
+ *	data            none
+ */
+#define ACCESSORY_REGISTER_HID         54
+
+/* Control request for unregistering a HID device.
+ *
+ *	requestType:    USB_DIR_OUT | USB_TYPE_VENDOR
+ *	request:        ACCESSORY_REGISTER_HID
+ *	value:          Accessory assigned ID for the HID device
+ *	index:          0
+ *	data            none
+ */
+#define ACCESSORY_UNREGISTER_HID         55
+
+/* Control request for sending the HID report descriptor.
+ * If the HID descriptor is longer than the endpoint zero max packet size,
+ * the descriptor will be sent in multiple ACCESSORY_SET_HID_REPORT_DESC
+ * commands. The data for the descriptor must be sent sequentially
+ * if multiple packets are needed.
+ *
+ *	requestType:    USB_DIR_OUT | USB_TYPE_VENDOR
+ *	request:        ACCESSORY_SET_HID_REPORT_DESC
+ *	value:          Accessory assigned ID for the HID device
+ *	index:          offset of data in descriptor
+ *                      (needed when HID descriptor is too big for one packet)
+ *	data            the HID report descriptor
+ */
+#define ACCESSORY_SET_HID_REPORT_DESC         56
+
+/* Control request for sending HID events.
+ *
+ *	requestType:    USB_DIR_OUT | USB_TYPE_VENDOR
+ *	request:        ACCESSORY_SEND_HID_EVENT
+ *	value:          Accessory assigned ID for the HID device
+ *	index:          0
+ *	data            the HID report for the event
+ */
+#define ACCESSORY_SEND_HID_EVENT         57
+
+/* Control request for setting the audio mode.
+ *
+ *	requestType:	USB_DIR_OUT | USB_TYPE_VENDOR
+ *	request:        ACCESSORY_SET_AUDIO_MODE
+ *	value:          0 - no audio
+ *                     1 - device to host, 44100 16-bit stereo PCM
+ *	index:          0
+ *	data            none
+ */
+#define ACCESSORY_SET_AUDIO_MODE         58
+
+/* ioctls for retrieving strings set by the host */
+#define ACCESSORY_GET_STRING_MANUFACTURER   _IOW('M', 1, char[256])
+#define ACCESSORY_GET_STRING_MODEL          _IOW('M', 2, char[256])
+#define ACCESSORY_GET_STRING_DESCRIPTION    _IOW('M', 3, char[256])
+#define ACCESSORY_GET_STRING_VERSION        _IOW('M', 4, char[256])
+#define ACCESSORY_GET_STRING_URI            _IOW('M', 5, char[256])
+#define ACCESSORY_GET_STRING_SERIAL         _IOW('M', 6, char[256])
+/* returns 1 if there is a start request pending */
+#define ACCESSORY_IS_START_REQUESTED        _IO('M', 7)
+/* returns audio mode (set via the ACCESSORY_SET_AUDIO_MODE control request) */
+#define ACCESSORY_GET_AUDIO_MODE            _IO('M', 8)
+
+#endif /* _UAPI_LINUX_USB_F_ACCESSORY_H */
diff --git a/include/uapi/linux/usb/f_mtp.h b/include/uapi/linux/usb/f_mtp.h
new file mode 100644
index 00000000000..503291855ab
--- /dev/null
+++ b/include/uapi/linux/usb/f_mtp.h
@@ -0,0 +1,61 @@
+/*
+ * Gadget Function Driver for MTP
+ *
+ * Copyright (C) 2010 Google, Inc.
+ * Author: Mike Lockwood <lockwood@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _UAPI_LINUX_USB_F_MTP_H
+#define _UAPI_LINUX_USB_F_MTP_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+struct mtp_file_range {
+	/* file descriptor for file to transfer */
+	int			fd;
+	/* offset in file for start of transfer */
+	loff_t		offset;
+	/* number of bytes to transfer */
+	int64_t		length;
+	/* MTP command ID for data header,
+	 * used only for MTP_SEND_FILE_WITH_HEADER
+	 */
+	uint16_t	command;
+	/* MTP transaction ID for data header,
+	 * used only for MTP_SEND_FILE_WITH_HEADER
+	 */
+	uint32_t	transaction_id;
+};
+
+struct mtp_event {
+	/* size of the event */
+	size_t		length;
+	/* event data to send */
+	void		*data;
+};
+
+/* Sends the specified file range to the host */
+#define MTP_SEND_FILE              _IOW('M', 0, struct mtp_file_range)
+/* Receives data from the host and writes it to a file.
+ * The file is created if it does not exist.
+ */
+#define MTP_RECEIVE_FILE           _IOW('M', 1, struct mtp_file_range)
+/* Sends an event to the host via the interrupt endpoint */
+#define MTP_SEND_EVENT             _IOW('M', 3, struct mtp_event)
+/* Sends the specified file range to the host,
+ * with a 12 byte MTP data packet header at the beginning.
+ */
+#define MTP_SEND_FILE_WITH_HEADER  _IOW('M', 4, struct mtp_file_range)
+
+#endif /* _UAPI_LINUX_USB_F_MTP_H */
diff --git a/include/uapi/linux/usbdevice_fs.h b/include/uapi/linux/usbdevice_fs.h
index abe5f4bd4d8..019ba1e0799 100644
--- a/include/uapi/linux/usbdevice_fs.h
+++ b/include/uapi/linux/usbdevice_fs.h
@@ -128,11 +128,12 @@ struct usbdevfs_hub_portinfo {
 	char port [127];	/* e.g. port 3 connects to device 27 */
 };
 
-/* Device capability flags */
+/* System and bus capability flags */
 #define USBDEVFS_CAP_ZERO_PACKET		0x01
 #define USBDEVFS_CAP_BULK_CONTINUATION		0x02
 #define USBDEVFS_CAP_NO_PACKET_SIZE_LIM		0x04
 #define USBDEVFS_CAP_BULK_SCATTER_GATHER	0x08
+#define USBDEVFS_CAP_REAP_AFTER_DISCONNECT	0x10
 
 /* USBDEVFS_DISCONNECT_CLAIM flags & struct */
 
diff --git a/include/uapi/video/adf.h b/include/uapi/video/adf.h
new file mode 100644
index 00000000000..c5d2e62cdb9
--- /dev/null
+++ b/include/uapi/video/adf.h
@@ -0,0 +1,321 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _UAPI_VIDEO_ADF_H_
+#define _UAPI_VIDEO_ADF_H_
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+#include <drm/drm_fourcc.h>
+#include <drm/drm_mode.h>
+
+#define ADF_NAME_LEN 32
+#define ADF_MAX_CUSTOM_DATA_SIZE 4096
+
+enum adf_interface_type {
+	ADF_INTF_DSI = 0,
+	ADF_INTF_eDP = 1,
+	ADF_INTF_DPI = 2,
+	ADF_INTF_VGA = 3,
+	ADF_INTF_DVI = 4,
+	ADF_INTF_HDMI = 5,
+	ADF_INTF_MEMORY = 6,
+	ADF_INTF_TYPE_DEVICE_CUSTOM = 128,
+	ADF_INTF_TYPE_MAX = (~(__u32)0),
+};
+
+#define ADF_INTF_FLAG_PRIMARY (1 << 0)
+#define ADF_INTF_FLAG_EXTERNAL (1 << 1)
+
+enum adf_event_type {
+	ADF_EVENT_VSYNC = 0,
+	ADF_EVENT_HOTPLUG = 1,
+	ADF_EVENT_DEVICE_CUSTOM = 128,
+	ADF_EVENT_TYPE_MAX = 255,
+};
+
+/**
+ * struct adf_set_event - start or stop subscribing to ADF events
+ *
+ * @type: the type of event to (un)subscribe
+ * @enabled: subscribe or unsubscribe
+ *
+ * After subscribing to an event, userspace may poll() the ADF object's fd
+ * to wait for events or read() to consume the event's data.
+ *
+ * ADF reserves event types 0 to %ADF_EVENT_DEVICE_CUSTOM-1 for its own events.
+ * Devices may use event types %ADF_EVENT_DEVICE_CUSTOM to %ADF_EVENT_TYPE_MAX-1
+ * for driver-private events.
+ */
+struct adf_set_event {
+	__u8 type;
+	__u8 enabled;
+};
+
+/**
+ * struct adf_event - common header for ADF event data
+ *
+ * @type: event type
+ * @length: total size of event data, header inclusive
+ */
+struct adf_event {
+	__u8 type;
+	__u32 length;
+};
+
+/**
+ * struct adf_vsync_event - ADF vsync event
+ *
+ * @base: event header (see &struct adf_event)
+ * @timestamp: time of vsync event, in nanoseconds
+ */
+struct adf_vsync_event {
+	struct adf_event base;
+	__aligned_u64 timestamp;
+};
+
+/**
+ * struct adf_vsync_event - ADF display hotplug event
+ *
+ * @base: event header (see &struct adf_event)
+ * @connected: whether a display is now connected to the interface
+ */
+struct adf_hotplug_event {
+	struct adf_event base;
+	__u8 connected;
+};
+
+#define ADF_MAX_PLANES 4
+/**
+ * struct adf_buffer_config - description of buffer displayed by adf_post_config
+ *
+ * @overlay_engine: id of the target overlay engine
+ * @w: width of display region in pixels
+ * @h: height of display region in pixels
+ * @format: DRM-style fourcc, see drm_fourcc.h for standard formats
+ * @fd: dma_buf fd for each plane
+ * @offset: location of first pixel to scan out, in bytes
+ * @pitch: stride (i.e. length of a scanline including padding) in bytes
+ * @n_planes: number of planes in buffer
+ * @acquire_fence: sync_fence fd which will clear when the buffer is
+ *	ready for display, or <0 if the buffer is already ready
+ */
+struct adf_buffer_config {
+	__u32 overlay_engine;
+
+	__u32 w;
+	__u32 h;
+	__u32 format;
+
+	__s32 fd[ADF_MAX_PLANES];
+	__u32 offset[ADF_MAX_PLANES];
+	__u32 pitch[ADF_MAX_PLANES];
+	__u8 n_planes;
+
+	__s32 acquire_fence;
+};
+#define ADF_MAX_BUFFERS (4096 / sizeof(struct adf_buffer_config))
+
+/**
+ * struct adf_post_config - request to flip to a new set of buffers
+ *
+ * @n_interfaces: number of interfaces targeted by the flip (input)
+ * @interfaces: ids of interfaces targeted by the flip (input)
+ * @n_bufs: number of buffers displayed (input)
+ * @bufs: description of buffers displayed (input)
+ * @custom_data_size: size of driver-private data (input)
+ * @custom_data: driver-private data (input)
+ * @complete_fence: sync_fence fd which will clear when this
+ *	configuration has left the screen (output)
+ */
+struct adf_post_config {
+	size_t n_interfaces;
+	__u32 __user *interfaces;
+
+	size_t n_bufs;
+	struct adf_buffer_config __user *bufs;
+
+	size_t custom_data_size;
+	void __user *custom_data;
+
+	__s32 complete_fence;
+};
+#define ADF_MAX_INTERFACES (4096 / sizeof(__u32))
+
+/**
+ * struct adf_simple_buffer_allocate - request to allocate a "simple" buffer
+ *
+ * @w: width of buffer in pixels (input)
+ * @h: height of buffer in pixels (input)
+ * @format: DRM-style fourcc (input)
+ *
+ * @fd: dma_buf fd (output)
+ * @offset: location of first pixel, in bytes (output)
+ * @pitch: length of a scanline including padding, in bytes (output)
+ *
+ * Simple buffers are analogous to DRM's "dumb" buffers.  They have a single
+ * plane of linear RGB data which can be allocated and scanned out without
+ * any driver-private ioctls or data.
+ *
+ * @format must be a standard RGB format defined in drm_fourcc.h.
+ *
+ * ADF clients must NOT assume that an interface can scan out a simple buffer
+ * allocated by a different ADF interface, even if the two interfaces belong to
+ * the same ADF device.
+ */
+struct adf_simple_buffer_alloc {
+	__u16 w;
+	__u16 h;
+	__u32 format;
+
+	__s32 fd;
+	__u32 offset;
+	__u32 pitch;
+};
+
+/**
+ * struct adf_simple_post_config - request to flip to a single buffer without
+ * driver-private data
+ *
+ * @buf: description of buffer displayed (input)
+ * @complete_fence: sync_fence fd which will clear when this buffer has left the
+ * screen (output)
+ */
+struct adf_simple_post_config {
+	struct adf_buffer_config buf;
+	__s32 complete_fence;
+};
+
+/**
+ * struct adf_attachment_config - description of attachment between an overlay
+ * engine and an interface
+ *
+ * @overlay_engine: id of the overlay engine
+ * @interface: id of the interface
+ */
+struct adf_attachment_config {
+	__u32 overlay_engine;
+	__u32 interface;
+};
+
+/**
+ * struct adf_device_data - describes a display device
+ *
+ * @name: display device's name
+ * @n_attachments: the number of current attachments
+ * @attachments: list of current attachments
+ * @n_allowed_attachments: the number of allowed attachments
+ * @allowed_attachments: list of allowed attachments
+ * @custom_data_size: size of driver-private data
+ * @custom_data: driver-private data
+ */
+struct adf_device_data {
+	char name[ADF_NAME_LEN];
+
+	size_t n_attachments;
+	struct adf_attachment_config __user *attachments;
+
+	size_t n_allowed_attachments;
+	struct adf_attachment_config __user *allowed_attachments;
+
+	size_t custom_data_size;
+	void __user *custom_data;
+};
+#define ADF_MAX_ATTACHMENTS (4096 / sizeof(struct adf_attachment_config))
+
+/**
+ * struct adf_device_data - describes a display interface
+ *
+ * @name: display interface's name
+ * @type: interface type (see enum @adf_interface_type)
+ * @id: which interface of type @type;
+ *	e.g. interface DSI.1 -> @type=@ADF_INTF_TYPE_DSI, @id=1
+ * @flags: informational flags (bitmask of %ADF_INTF_FLAG_* values)
+ * @dpms_state: DPMS state (one of @DRM_MODE_DPMS_* defined in drm_mode.h)
+ * @hotplug_detect: whether a display is plugged in
+ * @width_mm: screen width in millimeters, or 0 if unknown
+ * @height_mm: screen height in millimeters, or 0 if unknown
+ * @current_mode: current display mode
+ * @n_available_modes: the number of hardware display modes
+ * @available_modes: list of hardware display modes
+ * @custom_data_size: size of driver-private data
+ * @custom_data: driver-private data
+ */
+struct adf_interface_data {
+	char name[ADF_NAME_LEN];
+
+	__u32 type;
+	__u32 id;
+	/* e.g. type=ADF_INTF_TYPE_DSI, id=1 => DSI.1 */
+	__u32 flags;
+
+	__u8 dpms_state;
+	__u8 hotplug_detect;
+	__u16 width_mm;
+	__u16 height_mm;
+
+	struct drm_mode_modeinfo current_mode;
+	size_t n_available_modes;
+	struct drm_mode_modeinfo __user *available_modes;
+
+	size_t custom_data_size;
+	void __user *custom_data;
+};
+#define ADF_MAX_MODES (4096 / sizeof(struct drm_mode_modeinfo))
+
+/**
+ * struct adf_overlay_engine_data - describes an overlay engine
+ *
+ * @name: overlay engine's name
+ * @n_supported_formats: number of supported formats
+ * @supported_formats: list of supported formats
+ * @custom_data_size: size of driver-private data
+ * @custom_data: driver-private data
+ */
+struct adf_overlay_engine_data {
+	char name[ADF_NAME_LEN];
+
+	size_t n_supported_formats;
+	__u32 __user *supported_formats;
+
+	size_t custom_data_size;
+	void __user *custom_data;
+};
+#define ADF_MAX_SUPPORTED_FORMATS (4096 / sizeof(__u32))
+
+#define ADF_IOCTL_TYPE		'D'
+#define ADF_IOCTL_NR_CUSTOM	128
+
+#define ADF_SET_EVENT		_IOW(ADF_IOCTL_TYPE, 0, struct adf_set_event)
+#define ADF_BLANK		_IOW(ADF_IOCTL_TYPE, 1, __u8)
+#define ADF_POST_CONFIG		_IOW(ADF_IOCTL_TYPE, 2, struct adf_post_config)
+#define ADF_SET_MODE		_IOW(ADF_IOCTL_TYPE, 3, \
+					struct drm_mode_modeinfo)
+#define ADF_GET_DEVICE_DATA	_IOR(ADF_IOCTL_TYPE, 4, struct adf_device_data)
+#define ADF_GET_INTERFACE_DATA	_IOR(ADF_IOCTL_TYPE, 5, \
+					struct adf_interface_data)
+#define ADF_GET_OVERLAY_ENGINE_DATA \
+				_IOR(ADF_IOCTL_TYPE, 6, \
+					struct adf_overlay_engine_data)
+#define ADF_SIMPLE_POST_CONFIG	_IOW(ADF_IOCTL_TYPE, 7, \
+					struct adf_simple_post_config)
+#define ADF_SIMPLE_BUFFER_ALLOC	_IOW(ADF_IOCTL_TYPE, 8, \
+					struct adf_simple_buffer_alloc)
+#define ADF_ATTACH		_IOW(ADF_IOCTL_TYPE, 9, \
+					struct adf_attachment_config)
+#define ADF_DETACH		_IOW(ADF_IOCTL_TYPE, 10, \
+					struct adf_attachment_config)
+
+#endif /* _UAPI_VIDEO_ADF_H_ */
diff --git a/include/video/adf.h b/include/video/adf.h
new file mode 100644
index 00000000000..34f10e538f9
--- /dev/null
+++ b/include/video/adf.h
@@ -0,0 +1,502 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _VIDEO_ADF_H
+#define _VIDEO_ADF_H
+
+#include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/idr.h>
+#include <linux/kref.h>
+#include <linux/kthread.h>
+#include <linux/ktime.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/scatterlist.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
+#include <uapi/video/adf.h>
+#include "sync.h"
+
+struct adf_obj;
+struct adf_obj_ops;
+struct adf_device;
+struct adf_device_ops;
+struct adf_interface;
+struct adf_interface_ops;
+struct adf_overlay_engine;
+struct adf_overlay_engine_ops;
+
+/**
+ * struct adf_buffer - buffer displayed by adf_post
+ *
+ * @overlay_engine: target overlay engine
+ * @w: width of display region in pixels
+ * @h: height of display region in pixels
+ * @format: DRM-style fourcc, see drm_fourcc.h for standard formats
+ * @dma_bufs: dma_buf for each plane
+ * @offset: location of first pixel to scan out, in bytes
+ * @pitch: length of a scanline including padding, in bytes
+ * @n_planes: number of planes in buffer
+ * @acquire_fence: sync_fence which will clear when the buffer is
+ *	ready for display
+ *
+ * &struct adf_buffer is the in-kernel counterpart to the userspace-facing
+ * &struct adf_buffer_config.
+ */
+struct adf_buffer {
+	struct adf_overlay_engine *overlay_engine;
+
+	u32 w;
+	u32 h;
+	u32 format;
+
+	struct dma_buf *dma_bufs[ADF_MAX_PLANES];
+	u32 offset[ADF_MAX_PLANES];
+	u32 pitch[ADF_MAX_PLANES];
+	u8 n_planes;
+
+	struct sync_fence *acquire_fence;
+};
+
+/**
+ * struct adf_buffer_mapping - state for mapping a &struct adf_buffer into the
+ * display device
+ *
+ * @attachments: dma-buf attachment for each plane
+ * @sg_tables: SG tables for each plane
+ */
+struct adf_buffer_mapping {
+	struct dma_buf_attachment *attachments[ADF_MAX_PLANES];
+	struct sg_table *sg_tables[ADF_MAX_PLANES];
+};
+
+/**
+ * struct adf_post - request to flip to a new set of buffers
+ *
+ * @n_bufs: number of buffers displayed
+ * @bufs: buffers displayed
+ * @mappings: in-device mapping state for each buffer
+ * @custom_data_size: size of driver-private data
+ * @custom_data: driver-private data
+ *
+ * &struct adf_post is the in-kernel counterpart to the userspace-facing
+ * &struct adf_post_config.
+ */
+struct adf_post {
+	size_t n_bufs;
+	struct adf_buffer *bufs;
+	struct adf_buffer_mapping *mappings;
+
+	size_t custom_data_size;
+	void *custom_data;
+};
+
+/**
+ * struct adf_attachment - description of attachment between an overlay engine
+ * and an interface
+ *
+ * @overlay_engine: the overlay engine
+ * @interface: the interface
+ *
+ * &struct adf_attachment is the in-kernel counterpart to the userspace-facing
+ * &struct adf_attachment_config.
+ */
+struct adf_attachment {
+	struct adf_overlay_engine *overlay_engine;
+	struct adf_interface *interface;
+};
+
+struct adf_pending_post {
+	struct list_head head;
+	struct adf_post config;
+	void *state;
+};
+
+enum adf_obj_type {
+	ADF_OBJ_OVERLAY_ENGINE = 0,
+	ADF_OBJ_INTERFACE = 1,
+	ADF_OBJ_DEVICE = 2,
+};
+
+/**
+ * struct adf_obj_ops - common ADF object implementation ops
+ *
+ * @open: handle opening the object's device node
+ * @release: handle releasing an open file
+ * @ioctl: handle custom ioctls
+ *
+ * @supports_event: return whether the object supports generating events of type
+ *	@type
+ * @set_event: enable or disable events of type @type
+ * @event_type_str: return a string representation of custom event @type
+ *	(@type >= %ADF_EVENT_DEVICE_CUSTOM).
+ *
+ * @custom_data: copy up to %ADF_MAX_CUSTOM_DATA_SIZE bytes of driver-private
+ *	data into @data (allocated by ADF) and return the number of copied bytes
+ *	in @size.  Return 0 on success or an error code (<0) on failure.
+ */
+struct adf_obj_ops {
+	/* optional */
+	int (*open)(struct adf_obj *obj, struct inode *inode,
+			struct file *file);
+	/* optional */
+	void (*release)(struct adf_obj *obj, struct inode *inode,
+			struct file *file);
+	/* optional */
+	long (*ioctl)(struct adf_obj *obj, unsigned int cmd, unsigned long arg);
+
+	/* optional */
+	bool (*supports_event)(struct adf_obj *obj, enum adf_event_type type);
+	/* required if supports_event is implemented */
+	void (*set_event)(struct adf_obj *obj, enum adf_event_type type,
+			bool enabled);
+	/* optional */
+	const char *(*event_type_str)(struct adf_obj *obj,
+			enum adf_event_type type);
+
+	/* optional */
+	int (*custom_data)(struct adf_obj *obj, void *data, size_t *size);
+};
+
+struct adf_obj {
+	enum adf_obj_type type;
+	char name[ADF_NAME_LEN];
+	struct adf_device *parent;
+
+	const struct adf_obj_ops *ops;
+
+	struct device dev;
+
+	struct spinlock file_lock;
+	struct list_head file_list;
+
+	struct mutex event_lock;
+	struct rb_root event_refcount;
+
+	int id;
+	int minor;
+};
+
+/**
+ * struct adf_device_quirks - common display device quirks
+ *
+ * @buffer_padding: whether the last scanline of a buffer extends to the
+ * 	buffer's pitch (@ADF_BUFFER_PADDED_TO_PITCH) or just to the visible
+ * 	width (@ADF_BUFFER_UNPADDED)
+ */
+struct adf_device_quirks {
+	/* optional, defaults to ADF_BUFFER_PADDED_TO_PITCH */
+	enum {
+		ADF_BUFFER_PADDED_TO_PITCH = 0,
+		ADF_BUFFER_UNPADDED = 1,
+	} buffer_padding;
+};
+
+/**
+ * struct adf_device_ops - display device implementation ops
+ *
+ * @owner: device's module
+ * @base: common operations (see &struct adf_obj_ops)
+ * @quirks: device's quirks (see &struct adf_device_quirks)
+ *
+ * @attach: attach overlay engine @eng to interface @intf.  Return 0 on success
+ *	or error code (<0) on failure.
+ * @detach: detach overlay engine @eng from interface @intf.  Return 0 on
+ *	success or error code (<0) on failure.
+ *
+ * @validate_custom_format: validate the number and size of planes
+ *	in buffers with a custom format (i.e., not one of the @DRM_FORMAT_*
+ *	types defined in drm/drm_fourcc.h).  Return 0 if the buffer is valid or
+ *	an error code (<0) otherwise.
+ *
+ * @validate: validate that the proposed configuration @cfg is legal.  The
+ *	driver may optionally allocate and return some driver-private state in
+ *	@driver_state, which will be passed to the corresponding post().  The
+ *	driver may NOT commit any changes to hardware.  Return 0 if @cfg is
+ *	valid or an error code (<0) otherwise.
+ * @complete_fence: create a hardware-backed sync fence to be signaled when
+ *	@cfg is removed from the screen.  If unimplemented, ADF automatically
+ *	creates an sw_sync fence.  Return the sync fence on success or a
+ *	PTR_ERR() on failure.
+ * @post: flip @cfg onto the screen.  Wait for the display to begin scanning out
+ *	@cfg before returning.
+ * @advance_timeline: signal the sync fence for the last configuration to leave
+ *	the display.  If unimplemented, ADF automatically advances an sw_sync
+ *	timeline.
+ * @state_free: free driver-private state allocated during validate()
+ */
+struct adf_device_ops {
+	/* required */
+	struct module *owner;
+	const struct adf_obj_ops base;
+	/* optional */
+	const struct adf_device_quirks quirks;
+
+	/* optional */
+	int (*attach)(struct adf_device *dev, struct adf_overlay_engine *eng,
+			struct adf_interface *intf);
+	/* optional */
+	int (*detach)(struct adf_device *dev, struct adf_overlay_engine *eng,
+			struct adf_interface *intf);
+
+	/* required if any of the device's overlay engines supports at least one
+	   custom format */
+	int (*validate_custom_format)(struct adf_device *dev,
+			struct adf_buffer *buf);
+
+	/* required */
+	int (*validate)(struct adf_device *dev, struct adf_post *cfg,
+			void **driver_state);
+	/* optional */
+	struct sync_fence *(*complete_fence)(struct adf_device *dev,
+			struct adf_post *cfg, void *driver_state);
+	/* required */
+	void (*post)(struct adf_device *dev, struct adf_post *cfg,
+			void *driver_state);
+	/* required if complete_fence is implemented */
+	void (*advance_timeline)(struct adf_device *dev,
+			struct adf_post *cfg, void *driver_state);
+	/* required if validate allocates driver state */
+	void (*state_free)(struct adf_device *dev, void *driver_state);
+};
+
+struct adf_attachment_list {
+	struct adf_attachment attachment;
+	struct list_head head;
+};
+
+struct adf_device {
+	struct adf_obj base;
+	struct device *dev;
+
+	const struct adf_device_ops *ops;
+
+	struct mutex client_lock;
+
+	struct idr interfaces;
+	size_t n_interfaces;
+	struct idr overlay_engines;
+
+	struct list_head post_list;
+	struct mutex post_lock;
+	struct kthread_worker post_worker;
+	struct task_struct *post_thread;
+	struct kthread_work post_work;
+
+	struct list_head attached;
+	size_t n_attached;
+	struct list_head attach_allowed;
+	size_t n_attach_allowed;
+
+	struct adf_pending_post *onscreen;
+
+	struct sw_sync_timeline *timeline;
+	int timeline_max;
+};
+
+/**
+ * struct adf_interface_ops - display interface implementation ops
+ *
+ * @base: common operations (see &struct adf_obj_ops)
+ *
+ * @blank: change the display's DPMS state.  Return 0 on success or error
+ *	code (<0) on failure.
+ *
+ * @alloc_simple_buffer: allocate a buffer with the specified @w, @h, and
+ *	@format.  @format will be a standard RGB format (i.e.,
+ *	adf_format_is_rgb(@format) == true).  Return 0 on success or error code
+ *	(<0) on failure.  On success, return the buffer, offset, and pitch in
+ *	@dma_buf, @offset, and @pitch respectively.
+ * @describe_simple_post: provide driver-private data needed to post a single
+ *	buffer @buf.  Copy up to ADF_MAX_CUSTOM_DATA_SIZE bytes into @data
+ *	(allocated by ADF) and return the number of bytes in @size.  Return 0 on
+ *	success or error code (<0) on failure.
+ *
+ * @modeset: change the interface's mode.  @mode is not necessarily part of the
+ *	modelist passed to adf_hotplug_notify_connected(); the driver may
+ *	accept or reject custom modes at its discretion.  Return 0 on success or
+ *	error code (<0) if the mode could not be set.
+ *
+ * @screen_size: copy the screen dimensions in millimeters into @width_mm
+ *	and @height_mm.  Return 0 on success or error code (<0) if the display
+ *	dimensions are unknown.
+ *
+ * @type_str: return a string representation of custom @intf->type
+ *	(@intf->type >= @ADF_INTF_TYPE_DEVICE_CUSTOM).
+ */
+struct adf_interface_ops {
+	const struct adf_obj_ops base;
+
+	/* optional */
+	int (*blank)(struct adf_interface *intf, u8 state);
+
+	/* optional */
+	int (*alloc_simple_buffer)(struct adf_interface *intf,
+			u16 w, u16 h, u32 format,
+			struct dma_buf **dma_buf, u32 *offset, u32 *pitch);
+	/* optional */
+	int (*describe_simple_post)(struct adf_interface *intf,
+			struct adf_buffer *fb, void *data, size_t *size);
+
+	/* optional */
+	int (*modeset)(struct adf_interface *intf,
+			struct drm_mode_modeinfo *mode);
+
+	/* optional */
+	int (*screen_size)(struct adf_interface *intf, u16 *width_mm,
+			u16 *height_mm);
+
+	/* optional */
+	const char *(*type_str)(struct adf_interface *intf);
+};
+
+struct adf_interface {
+	struct adf_obj base;
+	const struct adf_interface_ops *ops;
+
+	struct drm_mode_modeinfo current_mode;
+
+	enum adf_interface_type type;
+	u32 idx;
+	u32 flags;
+
+	wait_queue_head_t vsync_wait;
+	ktime_t vsync_timestamp;
+	rwlock_t vsync_lock;
+
+	u8 dpms_state;
+
+	bool hotplug_detect;
+	struct drm_mode_modeinfo *modelist;
+	size_t n_modes;
+	rwlock_t hotplug_modelist_lock;
+};
+
+/**
+ * struct adf_interface_ops - overlay engine implementation ops
+ *
+ * @base: common operations (see &struct adf_obj_ops)
+ *
+ * @supported_formats: list of fourccs the overlay engine can scan out
+ * @n_supported_formats: length of supported_formats, up to
+ *	ADF_MAX_SUPPORTED_FORMATS
+ */
+struct adf_overlay_engine_ops {
+	const struct adf_obj_ops base;
+
+	/* required */
+	const u32 *supported_formats;
+	/* required */
+	const size_t n_supported_formats;
+};
+
+struct adf_overlay_engine {
+	struct adf_obj base;
+
+	const struct adf_overlay_engine_ops *ops;
+};
+
+#define adf_obj_to_device(ptr) \
+	container_of((ptr), struct adf_device, base)
+
+#define adf_obj_to_interface(ptr) \
+	container_of((ptr), struct adf_interface, base)
+
+#define adf_obj_to_overlay_engine(ptr) \
+	container_of((ptr), struct adf_overlay_engine, base)
+
+int __printf(4, 5) adf_device_init(struct adf_device *dev,
+		struct device *parent, const struct adf_device_ops *ops,
+		const char *fmt, ...);
+void adf_device_destroy(struct adf_device *dev);
+int __printf(7, 8) adf_interface_init(struct adf_interface *intf,
+		struct adf_device *dev, enum adf_interface_type type, u32 idx,
+		u32 flags, const struct adf_interface_ops *ops, const char *fmt,
+		...);
+void adf_interface_destroy(struct adf_interface *intf);
+static inline struct adf_device *adf_interface_parent(
+		struct adf_interface *intf)
+{
+	return intf->base.parent;
+}
+int __printf(4, 5) adf_overlay_engine_init(struct adf_overlay_engine *eng,
+		struct adf_device *dev,
+		const struct adf_overlay_engine_ops *ops, const char *fmt, ...);
+void adf_overlay_engine_destroy(struct adf_overlay_engine *eng);
+static inline struct adf_device *adf_overlay_engine_parent(
+		struct adf_overlay_engine *eng)
+{
+	return eng->base.parent;
+}
+
+int adf_attachment_allow(struct adf_device *dev, struct adf_overlay_engine *eng,
+		struct adf_interface *intf);
+
+const char *adf_obj_type_str(enum adf_obj_type type);
+const char *adf_interface_type_str(struct adf_interface *intf);
+const char *adf_event_type_str(struct adf_obj *obj, enum adf_event_type type);
+
+#define ADF_FORMAT_STR_SIZE 5
+void adf_format_str(u32 format, char buf[ADF_FORMAT_STR_SIZE]);
+int adf_format_validate_yuv(struct adf_device *dev, struct adf_buffer *buf,
+		u8 num_planes, u8 hsub, u8 vsub, u8 cpp[]);
+/**
+ * adf_format_validate_rgb - validate the number and size of planes in buffers
+ * with a custom RGB format.
+ *
+ * @dev: ADF device performing the validation
+ * @buf: buffer to validate
+ * @cpp: expected bytes per pixel
+ *
+ * adf_format_validate_rgb() is intended to be called as a helper from @dev's
+ * validate_custom_format() op.  @buf must have a single RGB plane.
+ *
+ * Returns 0 if @buf has a single plane with sufficient size, or -EINVAL
+ * otherwise.
+ */
+static inline int adf_format_validate_rgb(struct adf_device *dev,
+		struct adf_buffer *buf, u8 cpp)
+{
+	return adf_format_validate_yuv(dev, buf, 1, 1, 1, &cpp);
+}
+
+int adf_event_get(struct adf_obj *obj, enum adf_event_type type);
+int adf_event_put(struct adf_obj *obj, enum adf_event_type type);
+int adf_event_notify(struct adf_obj *obj, struct adf_event *event);
+
+static inline void adf_vsync_get(struct adf_interface *intf)
+{
+	adf_event_get(&intf->base, ADF_EVENT_VSYNC);
+}
+
+static inline void adf_vsync_put(struct adf_interface *intf)
+{
+	adf_event_put(&intf->base, ADF_EVENT_VSYNC);
+}
+
+int adf_vsync_wait(struct adf_interface *intf, long timeout);
+void adf_vsync_notify(struct adf_interface *intf, ktime_t timestamp);
+
+int adf_hotplug_notify_connected(struct adf_interface *intf,
+		struct drm_mode_modeinfo *modelist, size_t n_modes);
+void adf_hotplug_notify_disconnected(struct adf_interface *intf);
+
+void adf_modeinfo_set_name(struct drm_mode_modeinfo *mode);
+void adf_modeinfo_set_vrefresh(struct drm_mode_modeinfo *mode);
+
+#endif /* _VIDEO_ADF_H */
diff --git a/include/video/adf_client.h b/include/video/adf_client.h
new file mode 100644
index 00000000000..983f2b6a589
--- /dev/null
+++ b/include/video/adf_client.h
@@ -0,0 +1,61 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _VIDEO_ADF_CLIENT_H_
+#define _VIDEO_ADF_CLIENT_H_
+
+#include <video/adf.h>
+
+int adf_interface_blank(struct adf_interface *intf, u8 state);
+u8 adf_interface_dpms_state(struct adf_interface *intf);
+
+void adf_interface_current_mode(struct adf_interface *intf,
+		struct drm_mode_modeinfo *mode);
+size_t adf_interface_modelist(struct adf_interface *intf,
+		struct drm_mode_modeinfo *modelist, size_t n_modes);
+int adf_interface_set_mode(struct adf_interface *intf,
+		struct drm_mode_modeinfo *mode);
+int adf_interface_get_screen_size(struct adf_interface *intf, u16 *width,
+		u16 *height);
+int adf_interface_simple_buffer_alloc(struct adf_interface *intf, u16 w, u16 h,
+		u32 format, struct dma_buf **dma_buf, u32 *offset, u32 *pitch);
+struct sync_fence *adf_interface_simple_post(struct adf_interface *intf,
+		struct adf_buffer *buf);
+
+bool adf_overlay_engine_supports_format(struct adf_overlay_engine *eng,
+		u32 format);
+
+size_t adf_device_attachments(struct adf_device *dev,
+		struct adf_attachment *attachments, size_t n_attachments);
+size_t adf_device_attachments_allowed(struct adf_device *dev,
+		struct adf_attachment *attachments, size_t n_attachments);
+bool adf_device_attached(struct adf_device *dev, struct adf_overlay_engine *eng,
+		struct adf_interface *intf);
+bool adf_device_attach_allowed(struct adf_device *dev,
+		struct adf_overlay_engine *eng, struct adf_interface *intf);
+int adf_device_attach(struct adf_device *dev, struct adf_overlay_engine *eng,
+		struct adf_interface *intf);
+int adf_device_detach(struct adf_device *dev, struct adf_overlay_engine *eng,
+		struct adf_interface *intf);
+
+struct sync_fence *adf_device_post(struct adf_device *dev,
+		struct adf_interface **intfs, size_t n_intfs,
+		struct adf_buffer *bufs, size_t n_bufs, void *custom_data,
+		size_t custom_data_size);
+struct sync_fence *adf_device_post_nocopy(struct adf_device *dev,
+		struct adf_interface **intfs, size_t n_intfs,
+		struct adf_buffer *bufs, size_t n_bufs, void *custom_data,
+		size_t custom_data_size);
+
+#endif /* _VIDEO_ADF_CLIENT_H_ */
diff --git a/include/video/adf_fbdev.h b/include/video/adf_fbdev.h
new file mode 100644
index 00000000000..b722c6b3ab0
--- /dev/null
+++ b/include/video/adf_fbdev.h
@@ -0,0 +1,124 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _VIDEO_ADF_FBDEV_H_
+#define _VIDEO_ADF_FBDEV_H_
+
+#include <linux/fb.h>
+#include <linux/mutex.h>
+#include <video/adf.h>
+
+struct adf_fbdev {
+	struct adf_interface *intf;
+	struct adf_overlay_engine *eng;
+	struct fb_info *info;
+	u32 pseudo_palette[16];
+
+	unsigned int refcount;
+	struct mutex refcount_lock;
+
+	struct dma_buf *dma_buf;
+	u32 offset;
+	u32 pitch;
+	void *vaddr;
+	u32 format;
+
+	u16 default_xres_virtual;
+	u16 default_yres_virtual;
+	u32 default_format;
+};
+
+#if IS_ENABLED(CONFIG_ADF_FBDEV)
+void adf_modeinfo_to_fb_videomode(const struct drm_mode_modeinfo *mode,
+		struct fb_videomode *vmode);
+void adf_modeinfo_from_fb_videomode(const struct fb_videomode *vmode,
+		struct drm_mode_modeinfo *mode);
+
+int adf_fbdev_init(struct adf_fbdev *fbdev, struct adf_interface *interface,
+		struct adf_overlay_engine *eng,
+		u16 xres_virtual, u16 yres_virtual, u32 format,
+		struct fb_ops *fbops, const char *fmt, ...);
+void adf_fbdev_destroy(struct adf_fbdev *fbdev);
+
+int adf_fbdev_open(struct fb_info *info, int user);
+int adf_fbdev_release(struct fb_info *info, int user);
+int adf_fbdev_check_var(struct fb_var_screeninfo *var, struct fb_info *info);
+int adf_fbdev_set_par(struct fb_info *info);
+int adf_fbdev_blank(int blank, struct fb_info *info);
+int adf_fbdev_pan_display(struct fb_var_screeninfo *var, struct fb_info *info);
+int adf_fbdev_mmap(struct fb_info *info, struct vm_area_struct *vma);
+#else
+static inline void adf_modeinfo_to_fb_videomode(const struct drm_mode_modeinfo *mode,
+		struct fb_videomode *vmode)
+{
+	WARN_ONCE(1, "%s: CONFIG_ADF_FBDEV is disabled\n", __func__);
+}
+
+static inline void adf_modeinfo_from_fb_videomode(const struct fb_videomode *vmode,
+		struct drm_mode_modeinfo *mode)
+{
+	WARN_ONCE(1, "%s: CONFIG_ADF_FBDEV is disabled\n", __func__);
+}
+
+static inline int adf_fbdev_init(struct adf_fbdev *fbdev,
+		struct adf_interface *interface,
+		struct adf_overlay_engine *eng,
+		u16 xres_virtual, u16 yres_virtual, u32 format,
+		struct fb_ops *fbops, const char *fmt, ...)
+{
+	return -ENODEV;
+}
+
+static inline void adf_fbdev_destroy(struct adf_fbdev *fbdev) { }
+
+static inline int adf_fbdev_open(struct fb_info *info, int user)
+{
+	return -ENODEV;
+}
+
+static inline int adf_fbdev_release(struct fb_info *info, int user)
+{
+	return -ENODEV;
+}
+
+static inline int adf_fbdev_check_var(struct fb_var_screeninfo *var,
+		struct fb_info *info)
+{
+	return -ENODEV;
+}
+
+static inline int adf_fbdev_set_par(struct fb_info *info)
+{
+	return -ENODEV;
+}
+
+static inline int adf_fbdev_blank(int blank, struct fb_info *info)
+{
+	return -ENODEV;
+}
+
+static inline int adf_fbdev_pan_display(struct fb_var_screeninfo *var,
+		struct fb_info *info)
+{
+	return -ENODEV;
+}
+
+static inline int adf_fbdev_mmap(struct fb_info *info,
+		struct vm_area_struct *vma)
+{
+	return -ENODEV;
+}
+#endif
+
+#endif /* _VIDEO_ADF_FBDEV_H_ */
diff --git a/include/video/adf_format.h b/include/video/adf_format.h
new file mode 100644
index 00000000000..e03182cdcb0
--- /dev/null
+++ b/include/video/adf_format.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _VIDEO_ADF_FORMAT_H
+#define _VIDEO_ADF_FORMAT_H
+
+bool adf_format_is_standard(u32 format);
+bool adf_format_is_rgb(u32 format);
+u8 adf_format_num_planes(u32 format);
+u8 adf_format_bpp(u32 format);
+u8 adf_format_plane_cpp(u32 format, int plane);
+u8 adf_format_horz_chroma_subsampling(u32 format);
+u8 adf_format_vert_chroma_subsampling(u32 format);
+
+#endif /* _VIDEO_ADF_FORMAT_H */
diff --git a/include/video/adf_memblock.h b/include/video/adf_memblock.h
new file mode 100644
index 00000000000..6256e0eebcc
--- /dev/null
+++ b/include/video/adf_memblock.h
@@ -0,0 +1,20 @@
+/*
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _VIDEO_ADF_MEMBLOCK_H_
+#define _VIDEO_ADF_MEMBLOCK_H_
+
+struct dma_buf *adf_memblock_export(phys_addr_t base, size_t size, int flags);
+
+#endif /* _VIDEO_ADF_MEMBLOCK_H_ */
diff --git a/include/xen/events.h b/include/xen/events.h
index 5321cd9636e..7d95fdf9cf3 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -17,7 +17,7 @@ int bind_evtchn_to_irqhandler(unsigned int evtchn,
 			      irq_handler_t handler,
 			      unsigned long irqflags, const char *devname,
 			      void *dev_id);
-int bind_virq_to_irq(unsigned int virq, unsigned int cpu);
+int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu);
 int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu,
 			    irq_handler_t handler,
 			    unsigned long irqflags, const char *devname,
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 7491ee5d816..83338210ee0 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -46,4 +46,30 @@ static inline efi_system_table_t __init *xen_efi_probe(void)
 }
 #endif
 
+#ifdef CONFIG_PREEMPT
+
+static inline void xen_preemptible_hcall_begin(void)
+{
+}
+
+static inline void xen_preemptible_hcall_end(void)
+{
+}
+
+#else
+
+DECLARE_PER_CPU(bool, xen_in_preemptible_hcall);
+
+static inline void xen_preemptible_hcall_begin(void)
+{
+	__this_cpu_write(xen_in_preemptible_hcall, true);
+}
+
+static inline void xen_preemptible_hcall_end(void)
+{
+	__this_cpu_write(xen_in_preemptible_hcall, false);
+}
+
+#endif /* CONFIG_PREEMPT */
+
 #endif /* INCLUDE_XEN_OPS_H */
diff --git a/init/Makefile b/init/Makefile
index 7bc47ee31c3..692b91f1c1d 100644
--- a/init/Makefile
+++ b/init/Makefile
@@ -3,11 +3,8 @@
 #
 
 obj-y                          := main.o version.o mounts.o
-ifneq ($(CONFIG_BLK_DEV_INITRD),y)
 obj-y                          += noinitramfs.o
-else
 obj-$(CONFIG_BLK_DEV_INITRD)   += initramfs.o
-endif
 obj-$(CONFIG_GENERIC_CALIBRATE_DELAY) += calibrate.o
 
 ifneq ($(CONFIG_ARCH_INIT_TASK),y)
diff --git a/init/initramfs.c b/init/initramfs.c
index ad1bd7787bb..d39079e690f 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -18,6 +18,7 @@
 #include <linux/dirent.h>
 #include <linux/syscalls.h>
 #include <linux/utime.h>
+#include <linux/initramfs.h>
 
 static ssize_t __init xwrite(int fd, const char *p, size_t count)
 {
@@ -605,9 +606,25 @@ static void __init clean_rootfs(void)
 }
 #endif
 
+static int __initdata do_skip_initramfs;
+
+static int __init skip_initramfs_param(char *str)
+{
+	if (*str)
+		return 0;
+	do_skip_initramfs = 1;
+	return 1;
+}
+__setup("skip_initramfs", skip_initramfs_param);
+
 static int __init populate_rootfs(void)
 {
-	char *err = unpack_to_rootfs(__initramfs_start, __initramfs_size);
+	char *err;
+
+	if (do_skip_initramfs)
+		return default_rootfs();
+
+	err = unpack_to_rootfs(__initramfs_start, __initramfs_size);
 	if (err)
 		panic("%s", err); /* Failed to decompress INTERNAL initramfs */
 	if (initrd_start) {
diff --git a/init/noinitramfs.c b/init/noinitramfs.c
index 267739d8517..bcc8bcb053e 100644
--- a/init/noinitramfs.c
+++ b/init/noinitramfs.c
@@ -21,11 +21,16 @@
 #include <linux/stat.h>
 #include <linux/kdev_t.h>
 #include <linux/syscalls.h>
+#include <linux/kconfig.h>
+#include <linux/initramfs.h>
 
 /*
  * Create a simple rootfs that is similar to the default initramfs
  */
-static int __init default_rootfs(void)
+#if !IS_BUILTIN(CONFIG_BLK_DEV_INITRD)
+static
+#endif
+int __init default_rootfs(void)
 {
 	int err;
 
@@ -49,4 +54,6 @@ out:
 	printk(KERN_WARNING "Failed to create a rootfs\n");
 	return err;
 }
+#if !IS_BUILTIN(CONFIG_BLK_DEV_INITRD)
 rootfs_initcall(default_rootfs);
+#endif
diff --git a/kernel/audit.c b/kernel/audit.c
index cebb11db4d3..c6df9905f1c 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -429,7 +429,7 @@ static void kauditd_send_skb(struct sk_buff *skb)
  * This function doesn't consume an skb as might be expected since it has to
  * copy it anyways.
  */
-static void kauditd_send_multicast_skb(struct sk_buff *skb)
+static void kauditd_send_multicast_skb(struct sk_buff *skb, gfp_t gfp_mask)
 {
 	struct sk_buff		*copy;
 	struct audit_net	*aunet = net_generic(&init_net, audit_net_id);
@@ -448,11 +448,11 @@ static void kauditd_send_multicast_skb(struct sk_buff *skb)
 	 * no reason for new multicast clients to continue with this
 	 * non-compliance.
 	 */
-	copy = skb_copy(skb, GFP_KERNEL);
+	copy = skb_copy(skb, gfp_mask);
 	if (!copy)
 		return;
 
-	nlmsg_multicast(sock, copy, 0, AUDIT_NLGRP_READLOG, GFP_KERNEL);
+	nlmsg_multicast(sock, copy, 0, AUDIT_NLGRP_READLOG, gfp_mask);
 }
 
 /*
@@ -1949,7 +1949,7 @@ void audit_log_end(struct audit_buffer *ab)
 		struct nlmsghdr *nlh = nlmsg_hdr(ab->skb);
 
 		nlh->nlmsg_len = ab->skb->len;
-		kauditd_send_multicast_skb(ab->skb);
+		kauditd_send_multicast_skb(ab->skb, ab->gfp_mask);
 
 		/*
 		 * The original kaudit unicast socket sends up messages with
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 3598e13f2a6..4f68a326d92 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -442,19 +442,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 		if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) {
 			f->type = AUDIT_LOGINUID_SET;
 			f->val = 0;
-		}
-
-		if ((f->type == AUDIT_PID) || (f->type == AUDIT_PPID)) {
-			struct pid *pid;
-			rcu_read_lock();
-			pid = find_vpid(f->val);
-			if (!pid) {
-				rcu_read_unlock();
-				err = -ESRCH;
-				goto exit_free;
-			}
-			f->val = pid_nr(pid);
-			rcu_read_unlock();
+			entry->rule.pflags |= AUDIT_LOGINUID_LEGACY;
 		}
 
 		err = audit_field_valid(entry, f);
@@ -630,6 +618,13 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule)
 			data->buflen += data->values[i] =
 				audit_pack_string(&bufp, krule->filterkey);
 			break;
+		case AUDIT_LOGINUID_SET:
+			if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) {
+				data->fields[i] = AUDIT_LOGINUID;
+				data->values[i] = AUDIT_UID_UNSET;
+				break;
+			}
+			/* fallthrough if set */
 		default:
 			data->values[i] = f->val;
 		}
@@ -646,6 +641,7 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b)
 	int i;
 
 	if (a->flags != b->flags ||
+	    a->pflags != b->pflags ||
 	    a->listnr != b->listnr ||
 	    a->action != b->action ||
 	    a->field_count != b->field_count)
@@ -764,6 +760,7 @@ struct audit_entry *audit_dupe_rule(struct audit_krule *old)
 	new = &entry->rule;
 	new->vers_ops = old->vers_ops;
 	new->flags = old->flags;
+	new->pflags = old->pflags;
 	new->listnr = old->listnr;
 	new->action = old->action;
 	for (i = 0; i < AUDIT_BITMASK_SIZE; i++)
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index d6594e457a2..71a9e5be659 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -357,8 +357,8 @@ select_insn:
 	ALU64_MOD_X:
 		if (unlikely(SRC == 0))
 			return 0;
-		tmp = DST;
-		DST = do_div(tmp, SRC);
+		div64_u64_rem(DST, SRC, &tmp);
+		DST = tmp;
 		CONT;
 	ALU_MOD_X:
 		if (unlikely(SRC == 0))
@@ -367,8 +367,8 @@ select_insn:
 		DST = do_div(tmp, (u32) SRC);
 		CONT;
 	ALU64_MOD_K:
-		tmp = DST;
-		DST = do_div(tmp, IMM);
+		div64_u64_rem(DST, IMM, &tmp);
+		DST = tmp;
 		CONT;
 	ALU_MOD_K:
 		tmp = (u32) DST;
@@ -377,7 +377,7 @@ select_insn:
 	ALU64_DIV_X:
 		if (unlikely(SRC == 0))
 			return 0;
-		do_div(DST, SRC);
+		DST = div64_u64(DST, SRC);
 		CONT;
 	ALU_DIV_X:
 		if (unlikely(SRC == 0))
@@ -387,7 +387,7 @@ select_insn:
 		DST = (u32) tmp;
 		CONT;
 	ALU64_DIV_K:
-		do_div(DST, IMM);
+		DST = div64_u64(DST, IMM);
 		CONT;
 	ALU_DIV_K:
 		tmp = (u32) DST;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9f81818f294..055ae6ac028 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -763,7 +763,7 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 	enum bpf_reg_type expected_type;
 	int err = 0;
 
-	if (arg_type == ARG_ANYTHING)
+	if (arg_type == ARG_DONTCARE)
 		return 0;
 
 	if (reg->type == NOT_INIT) {
@@ -771,6 +771,9 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 		return -EACCES;
 	}
 
+	if (arg_type == ARG_ANYTHING)
+		return 0;
+
 	if (arg_type == ARG_PTR_TO_STACK || arg_type == ARG_PTR_TO_MAP_KEY ||
 	    arg_type == ARG_PTR_TO_MAP_VALUE) {
 		expected_type = PTR_TO_STACK;
@@ -1324,7 +1327,8 @@ peek_stack:
 			/* tell verifier to check for equivalent states
 			 * after every call and jump
 			 */
-			env->explored_states[t + 1] = STATE_LIST_MARK;
+			if (t + 1 < insn_cnt)
+				env->explored_states[t + 1] = STATE_LIST_MARK;
 		} else {
 			/* conditional jump with two edges */
 			ret = push_insn(t, t + 1, FALLTHROUGH, env);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 136eceadeed..30f18011292 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2327,6 +2327,44 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp,
 	return ret;
 }
 
+int subsys_cgroup_allow_attach(struct cgroup_subsys_state *css, struct cgroup_taskset *tset)
+{
+	const struct cred *cred = current_cred(), *tcred;
+	struct task_struct *task;
+
+	if (capable(CAP_SYS_NICE))
+		return 0;
+
+	cgroup_taskset_for_each(task, tset) {
+		tcred = __task_cred(task);
+
+		if (current != task && !uid_eq(cred->euid, tcred->uid) &&
+		    !uid_eq(cred->euid, tcred->suid))
+			return -EACCES;
+	}
+
+	return 0;
+}
+
+static int cgroup_allow_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
+{
+	struct cgroup_subsys_state *css;
+	int i;
+	int ret;
+
+	for_each_css(css, i, cgrp) {
+		if (css->ss->allow_attach) {
+			ret = css->ss->allow_attach(css, tset);
+			if (ret)
+				return ret;
+		} else {
+			return -EACCES;
+		}
+	}
+
+	return 0;
+}
+
 /*
  * Find the task_struct of the task to attach by vpid and pass it along to the
  * function to attach either it or all tasks in its threadgroup. Will lock
@@ -2365,9 +2403,24 @@ retry_find_task:
 		if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
 		    !uid_eq(cred->euid, tcred->uid) &&
 		    !uid_eq(cred->euid, tcred->suid)) {
-			rcu_read_unlock();
-			ret = -EACCES;
-			goto out_unlock_cgroup;
+			/*
+			 * if the default permission check fails, give each
+			 * cgroup a chance to extend the permission check
+			 */
+			struct cgroup_taskset tset = {
+				.src_csets = LIST_HEAD_INIT(tset.src_csets),
+				.dst_csets = LIST_HEAD_INIT(tset.dst_csets),
+				.csets = &tset.src_csets,
+			};
+			struct css_set *cset;
+			cset = task_css_set(tsk);
+			list_add(&cset->mg_node, &tset.src_csets);
+			ret = cgroup_allow_attach(cgrp, &tset);
+			list_del(&tset.src_csets);
+			if (ret) {
+				rcu_read_unlock();
+				goto out_unlock_cgroup;
+			}
 		}
 	} else
 		tsk = current;
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 90a3d017b90..2fb146ba6dc 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -791,3 +791,23 @@ void init_cpu_online(const struct cpumask *src)
 {
 	cpumask_copy(to_cpumask(cpu_online_bits), src);
 }
+
+static ATOMIC_NOTIFIER_HEAD(idle_notifier);
+
+void idle_notifier_register(struct notifier_block *n)
+{
+	atomic_notifier_chain_register(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_register);
+
+void idle_notifier_unregister(struct notifier_block *n)
+{
+	atomic_notifier_chain_unregister(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_unregister);
+
+void idle_notifier_call_chain(unsigned long val)
+{
+	atomic_notifier_call_chain(&idle_notifier, val, NULL);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_call_chain);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 1f107c74087..672310e1597 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -538,9 +538,6 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr,
 
 	rcu_read_lock();
 	cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
-		if (cp == root_cs)
-			continue;
-
 		/* skip the whole subtree if @cp doesn't have any CPU */
 		if (cpumask_empty(cp->cpus_allowed)) {
 			pos_css = css_rightmost_descendant(pos_css);
@@ -863,7 +860,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
 		 * If it becomes empty, inherit the effective mask of the
 		 * parent, which is guaranteed to have some CPUs.
 		 */
-		if (cpumask_empty(new_cpus))
+		if (cgroup_on_dfl(cp->css.cgroup) && cpumask_empty(new_cpus))
 			cpumask_copy(new_cpus, parent->effective_cpus);
 
 		/* Skip the whole subtree if the cpumask remains the same. */
@@ -1119,7 +1116,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
 		 * If it becomes empty, inherit the effective mask of the
 		 * parent, which is guaranteed to have some MEMs.
 		 */
-		if (nodes_empty(*new_mems))
+		if (cgroup_on_dfl(cp->css.cgroup) && nodes_empty(*new_mems))
 			*new_mems = parent->effective_mems;
 
 		/* Skip the whole subtree if the nodemask remains the same. */
@@ -1991,7 +1988,9 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 
 	mutex_lock(&callback_mutex);
 	cs->mems_allowed = parent->mems_allowed;
+	cs->effective_mems = parent->mems_allowed;
 	cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
+	cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
 	mutex_unlock(&callback_mutex);
 out_unlock:
 	mutex_unlock(&cpuset_mutex);
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 1adf62b39b9..af061221681 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -87,6 +87,10 @@ static int kgdb_use_con;
 bool dbg_is_early = true;
 /* Next cpu to become the master debug core */
 int dbg_switch_cpu;
+/* Flag for entering kdb when a panic occurs */
+static bool break_on_panic = true;
+/* Flag for entering kdb when an exception occurs */
+static bool break_on_exception = true;
 
 /* Use kdb or gdbserver mode */
 int dbg_kdb_mode = 1;
@@ -101,6 +105,8 @@ early_param("kgdbcon", opt_kgdb_con);
 
 module_param(kgdb_use_con, int, 0644);
 module_param(kgdbreboot, int, 0644);
+module_param(break_on_panic, bool, 0644);
+module_param(break_on_exception, bool, 0644);
 
 /*
  * Holds information about breakpoints in a kernel. These breakpoints are
@@ -690,6 +696,9 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
 	if (arch_kgdb_ops.enable_nmi)
 		arch_kgdb_ops.enable_nmi(0);
 
+	if (unlikely(signo != SIGTRAP && !break_on_exception))
+		return 1;
+
 	memset(ks, 0, sizeof(struct kgdb_state));
 	ks->cpu			= raw_smp_processor_id();
 	ks->ex_vector		= evector;
@@ -821,6 +830,9 @@ static int kgdb_panic_event(struct notifier_block *self,
 			    unsigned long val,
 			    void *data)
 {
+	if (!break_on_panic)
+		return NOTIFY_DONE;
+
 	if (dbg_kdb_mode)
 		kdb_printf("PANIC: %s\n", (char *)data);
 	kgdb_breakpoint();
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index 7c70812caea..13a1e6b5c40 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -216,7 +216,7 @@ static char *kdb_read(char *buffer, size_t bufsize)
 	int i;
 	int diag, dtab_count;
 	int key;
-
+	static int last_crlf;
 
 	diag = kdbgetintenv("DTABCOUNT", &dtab_count);
 	if (diag)
@@ -237,6 +237,9 @@ poll_again:
 		return buffer;
 	if (key != 9)
 		tab = 0;
+	if (key != 10 && key != 13)
+		last_crlf = 0;
+
 	switch (key) {
 	case 8: /* backspace */
 		if (cp > buffer) {
@@ -254,7 +257,12 @@ poll_again:
 			*cp = tmp;
 		}
 		break;
-	case 13: /* enter */
+	case 10: /* new line */
+	case 13: /* carriage return */
+		/* handle \n after \r */
+		if (last_crlf && last_crlf != key)
+			break;
+		last_crlf = key;
 		*lastchar++ = '\n';
 		*lastchar++ = '\0';
 		if (!KDB_STATE(KGDB_TRANS)) {
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 379650b984f..6ffdc96059a 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -2535,7 +2535,7 @@ static int kdb_summary(int argc, const char **argv)
 #define K(x) ((x) << (PAGE_SHIFT - 10))
 	kdb_printf("\nMemTotal:       %8lu kB\nMemFree:        %8lu kB\n"
 		   "Buffers:        %8lu kB\n",
-		   val.totalram, val.freeram, val.bufferram);
+		   K(val.totalram), K(val.freeram), K(val.bufferram));
 	return 0;
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1cd5eef1fcd..cb86038cad4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4057,20 +4057,20 @@ static void ring_buffer_attach(struct perf_event *event,
 		WARN_ON_ONCE(event->rcu_pending);
 
 		old_rb = event->rb;
-		event->rcu_batches = get_state_synchronize_rcu();
-		event->rcu_pending = 1;
-
 		spin_lock_irqsave(&old_rb->event_lock, flags);
 		list_del_rcu(&event->rb_entry);
 		spin_unlock_irqrestore(&old_rb->event_lock, flags);
-	}
 
-	if (event->rcu_pending && rb) {
-		cond_synchronize_rcu(event->rcu_batches);
-		event->rcu_pending = 0;
+		event->rcu_batches = get_state_synchronize_rcu();
+		event->rcu_pending = 1;
 	}
 
 	if (rb) {
+		if (event->rcu_pending) {
+			cond_synchronize_rcu(event->rcu_batches);
+			event->rcu_pending = 0;
+		}
+
 		spin_lock_irqsave(&rb->event_lock, flags);
 		list_add_rcu(&event->rb_entry, &rb->event_list);
 		spin_unlock_irqrestore(&rb->event_lock, flags);
@@ -4412,6 +4412,13 @@ static void perf_pending_event(struct irq_work *entry)
 {
 	struct perf_event *event = container_of(entry,
 			struct perf_event, pending);
+	int rctx;
+
+	rctx = perf_swevent_get_recursion_context();
+	/*
+	 * If we 'fail' here, that's OK, it means recursion is already disabled
+	 * and we won't recurse 'further'.
+	 */
 
 	if (event->pending_disable) {
 		event->pending_disable = 0;
@@ -4422,6 +4429,9 @@ static void perf_pending_event(struct irq_work *entry)
 		event->pending_wakeup = 0;
 		perf_event_wakeup(event);
 	}
+
+	if (rctx >= 0)
+		perf_swevent_put_recursion_context(rctx);
 }
 
 /*
@@ -7435,11 +7445,11 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	if (move_group) {
 		synchronize_rcu();
-		perf_install_in_context(ctx, group_leader, event->cpu);
+		perf_install_in_context(ctx, group_leader, group_leader->cpu);
 		get_ctx(ctx);
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
-			perf_install_in_context(ctx, sibling, event->cpu);
+			perf_install_in_context(ctx, sibling, sibling->cpu);
 			get_ctx(ctx);
 		}
 	}
diff --git a/kernel/exit.c b/kernel/exit.c
index 5d30019ff95..2116aace6c8 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1302,9 +1302,15 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
 static int wait_consider_task(struct wait_opts *wo, int ptrace,
 				struct task_struct *p)
 {
+	/*
+	 * We can race with wait_task_zombie() from another thread.
+	 * Ensure that EXIT_ZOMBIE -> EXIT_DEAD/EXIT_TRACE transition
+	 * can't confuse the checks below.
+	 */
+	int exit_state = ACCESS_ONCE(p->exit_state);
 	int ret;
 
-	if (unlikely(p->exit_state == EXIT_DEAD))
+	if (unlikely(exit_state == EXIT_DEAD))
 		return 0;
 
 	ret = eligible_child(wo, p);
@@ -1325,7 +1331,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 		return 0;
 	}
 
-	if (unlikely(p->exit_state == EXIT_TRACE)) {
+	if (unlikely(exit_state == EXIT_TRACE)) {
 		/*
 		 * ptrace == 0 means we are the natural parent. In this case
 		 * we should clear notask_error, debugger will notify us.
@@ -1352,7 +1358,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 	}
 
 	/* slay zombie? */
-	if (p->exit_state == EXIT_ZOMBIE) {
+	if (exit_state == EXIT_ZOMBIE) {
 		/* we don't reap group leaders with subthreads */
 		if (!delay_group_leader(p)) {
 			/*
diff --git a/kernel/fork.c b/kernel/fork.c
index 9b7d746d6d6..d3a81415925 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -201,6 +201,9 @@ struct kmem_cache *vm_area_cachep;
 /* SLAB cache for mm_struct structures (tsk->mm) */
 static struct kmem_cache *mm_cachep;
 
+/* Notifier list called when a task struct is freed */
+static ATOMIC_NOTIFIER_HEAD(task_free_notifier);
+
 static void account_kernel_stack(struct thread_info *ti, int account)
 {
 	struct zone *zone = page_zone(virt_to_page(ti));
@@ -234,6 +237,18 @@ static inline void put_signal_struct(struct signal_struct *sig)
 		free_signal_struct(sig);
 }
 
+int task_free_register(struct notifier_block *n)
+{
+	return atomic_notifier_chain_register(&task_free_notifier, n);
+}
+EXPORT_SYMBOL(task_free_register);
+
+int task_free_unregister(struct notifier_block *n)
+{
+	return atomic_notifier_chain_unregister(&task_free_notifier, n);
+}
+EXPORT_SYMBOL(task_free_unregister);
+
 void __put_task_struct(struct task_struct *tsk)
 {
 	WARN_ON(!tsk->exit_state);
@@ -246,6 +261,7 @@ void __put_task_struct(struct task_struct *tsk)
 	delayacct_tsk_free(tsk);
 	put_signal_struct(tsk->signal);
 
+	atomic_notifier_call_chain(&task_free_notifier, 0, tsk);
 	if (!profile_handoff_task(tsk))
 		free_task(tsk);
 }
@@ -735,7 +751,8 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 
 	mm = get_task_mm(task);
 	if (mm && mm != current->mm &&
-			!ptrace_may_access(task, mode)) {
+			!ptrace_may_access(task, mode) &&
+			!capable(CAP_SYS_RESOURCE)) {
 		mmput(mm);
 		mm = ERR_PTR(-EACCES);
 	}
@@ -1287,6 +1304,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	p->utime = p->stime = p->gtime = 0;
 	p->utimescaled = p->stimescaled = 0;
+	p->cpu_power = 0;
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	p->prev_cputime.utime = p->prev_cputime.stime = 0;
 #endif
diff --git a/kernel/groups.c b/kernel/groups.c
index 451698f86cf..664411f171b 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -6,6 +6,7 @@
 #include <linux/slab.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
+#include <linux/user_namespace.h>
 #include <asm/uaccess.h>
 
 /* init to 2 - one for init_task, one to ensure it is never freed */
@@ -213,6 +214,14 @@ out:
 	return i;
 }
 
+bool may_setgroups(void)
+{
+	struct user_namespace *user_ns = current_user_ns();
+
+	return ns_capable(user_ns, CAP_SETGID) &&
+		userns_may_setgroups(user_ns);
+}
+
 /*
  *	SMP: Our groups are copy-on-write. We can set them safely
  *	without another task interfering.
@@ -223,7 +232,7 @@ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
 	struct group_info *group_info;
 	int retval;
 
-	if (!ns_capable(current_user_ns(), CAP_SETGID))
+	if (!may_setgroups())
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index d5d0f7345c5..74d90a75426 100644
--- a/kernel/irq/devres.c
+++ b/kernel/irq/devres.c
@@ -104,7 +104,7 @@ int devm_request_any_context_irq(struct device *dev, unsigned int irq,
 		return -ENOMEM;
 
 	rc = request_any_context_irq(irq, handler, irqflags, devname, dev_id);
-	if (rc) {
+	if (rc < 0) {
 		devres_free(dr);
 		return rc;
 	}
@@ -113,7 +113,7 @@ int devm_request_any_context_irq(struct device *dev, unsigned int irq,
 	dr->dev_id = dev_id;
 	devres_add(dev, dr);
 
-	return 0;
+	return rc;
 }
 EXPORT_SYMBOL(devm_request_any_context_irq);
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 4332d766619..df553b0af93 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -78,8 +78,12 @@ extern void unmask_threaded_irq(struct irq_desc *desc);
 
 #ifdef CONFIG_SPARSE_IRQ
 static inline void irq_mark_irq(unsigned int irq) { }
+extern void irq_lock_sparse(void);
+extern void irq_unlock_sparse(void);
 #else
 extern void irq_mark_irq(unsigned int irq);
+static inline void irq_lock_sparse(void) { }
+static inline void irq_unlock_sparse(void) { }
 #endif
 
 extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index a1782f88f0a..fec632d8ef9 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -24,10 +24,35 @@
 static struct lock_class_key irq_desc_lock_class;
 
 #if defined(CONFIG_SMP)
+static int __init irq_affinity_setup(char *str)
+{
+	zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
+	cpulist_parse(str, irq_default_affinity);
+	/*
+	 * Set at least the boot cpu. We don't want to end up with
+	 * bugreports caused by random comandline masks
+	 */
+	cpumask_set_cpu(smp_processor_id(), irq_default_affinity);
+	return 1;
+}
+__setup("irqaffinity=", irq_affinity_setup);
+
+extern struct cpumask hmp_slow_cpu_mask;
+
 static void __init init_irq_default_affinity(void)
 {
-	alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
-	cpumask_setall(irq_default_affinity);
+#ifdef CONFIG_CPUMASK_OFFSTACK
+	if (!irq_default_affinity)
+		zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
+#endif
+#ifdef CONFIG_SCHED_HMP
+	if (!cpumask_empty(&hmp_slow_cpu_mask)) {
+		cpumask_copy(irq_default_affinity, &hmp_slow_cpu_mask);
+		return;
+	}
+#endif
+	if (cpumask_empty(irq_default_affinity))
+		cpumask_setall(irq_default_affinity);
 }
 #else
 static void __init init_irq_default_affinity(void)
@@ -132,6 +157,16 @@ static void free_masks(struct irq_desc *desc)
 static inline void free_masks(struct irq_desc *desc) { }
 #endif
 
+void irq_lock_sparse(void)
+{
+	mutex_lock(&sparse_irq_lock);
+}
+
+void irq_unlock_sparse(void)
+{
+	mutex_unlock(&sparse_irq_lock);
+}
+
 static struct irq_desc *alloc_desc(int irq, int node, struct module *owner)
 {
 	struct irq_desc *desc;
@@ -168,6 +203,12 @@ static void free_desc(unsigned int irq)
 
 	unregister_irq_proc(irq, desc);
 
+	/*
+	 * sparse_irq_lock protects also show_interrupts() and
+	 * kstat_irq_usr(). Once we deleted the descriptor from the
+	 * sparse tree we can free it. Access in proc will fail to
+	 * lookup the descriptor.
+	 */
 	mutex_lock(&sparse_irq_lock);
 	delete_irq_desc(irq);
 	mutex_unlock(&sparse_irq_lock);
@@ -574,6 +615,15 @@ void kstat_incr_irq_this_cpu(unsigned int irq)
 	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
 }
 
+/**
+ * kstat_irqs_cpu - Get the statistics for an interrupt on a cpu
+ * @irq:	The interrupt number
+ * @cpu:	The cpu number
+ *
+ * Returns the sum of interrupt counts on @cpu since boot for
+ * @irq. The caller must ensure that the interrupt is not removed
+ * concurrently.
+ */
 unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
@@ -582,6 +632,14 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 			*per_cpu_ptr(desc->kstat_irqs, cpu) : 0;
 }
 
+/**
+ * kstat_irqs - Get the statistics for an interrupt
+ * @irq:	The interrupt number
+ *
+ * Returns the sum of interrupt counts on all cpus since boot for
+ * @irq. The caller must ensure that the interrupt is not removed
+ * concurrently.
+ */
 unsigned int kstat_irqs(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
@@ -594,3 +652,22 @@ unsigned int kstat_irqs(unsigned int irq)
 		sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
 	return sum;
 }
+
+/**
+ * kstat_irqs_usr - Get the statistics for an interrupt
+ * @irq:	The interrupt number
+ *
+ * Returns the sum of interrupt counts on all cpus since boot for
+ * @irq. Contrary to kstat_irqs() this can be called from any
+ * preemptible context. It's protected against concurrent removal of
+ * an interrupt descriptor when sparse irqs are enabled.
+ */
+unsigned int kstat_irqs_usr(unsigned int irq)
+{
+	int sum;
+
+	irq_lock_sparse();
+	sum = kstat_irqs(irq);
+	irq_unlock_sparse();
+	return sum;
+}
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index ac1ba2f1103..9dc9bfd8a67 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -15,6 +15,23 @@
 
 #include "internals.h"
 
+/*
+ * Access rules:
+ *
+ * procfs protects read/write of /proc/irq/N/ files against a
+ * concurrent free of the interrupt descriptor. remove_proc_entry()
+ * immediately prevents new read/writes to happen and waits for
+ * already running read/write functions to complete.
+ *
+ * We remove the proc entries first and then delete the interrupt
+ * descriptor from the radix tree and free it. So it is guaranteed
+ * that irq_to_desc(N) is valid as long as the read/writes are
+ * permitted by procfs.
+ *
+ * The read from /proc/interrupts is a different problem because there
+ * is no protection. So the lookup and the access to irqdesc
+ * information must be protected by sparse_irq_lock.
+ */
 static struct proc_dir_entry *root_irq_dir;
 
 #ifdef CONFIG_SMP
@@ -437,9 +454,10 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 	}
 
+	irq_lock_sparse();
 	desc = irq_to_desc(i);
 	if (!desc)
-		return 0;
+		goto outsparse;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	for_each_online_cpu(j)
@@ -479,6 +497,8 @@ int show_interrupts(struct seq_file *p, void *v)
 	seq_putc(p, '\n');
 out:
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
+outsparse:
+	irq_unlock_sparse();
 	return 0;
 }
 #endif
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 7c98873a307..1929ee2291f 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -265,15 +265,17 @@ struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
 }
 
 /*
- * Called by sched_setscheduler() to check whether the priority change
- * is overruled by a possible priority boosting.
+ * Called by sched_setscheduler() to get the priority which will be
+ * effective after the change.
  */
-int rt_mutex_check_prio(struct task_struct *task, int newprio)
+int rt_mutex_get_effective_prio(struct task_struct *task, int newprio)
 {
 	if (!task_has_pi_waiters(task))
-		return 0;
+		return newprio;
 
-	return task_top_pi_waiter(task)->task->prio <= newprio;
+	if (task_top_pi_waiter(task)->task->prio <= newprio)
+		return task_top_pi_waiter(task)->task->prio;
+	return newprio;
 }
 
 /*
@@ -1193,7 +1195,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	set_current_state(TASK_RUNNING);
 
 	if (unlikely(ret)) {
-		remove_waiter(lock, &waiter);
+		if (rt_mutex_has_waiters(lock))
+			remove_waiter(lock, &waiter);
 		rt_mutex_handle_deadlock(ret, chwalk, &waiter);
 	}
 
diff --git a/kernel/module.c b/kernel/module.c
index 88cec1ddb1e..c353707bbbd 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3307,6 +3307,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	module_bug_cleanup(mod);
 	mutex_unlock(&module_mutex);
 
+	blocking_notifier_call_chain(&module_notify_list,
+				     MODULE_STATE_GOING, mod);
+
 	/* we can't deallocate the module until we clear memory protection */
 	unset_module_init_ro_nx(mod);
 	unset_module_core_ro_nx(mod);
diff --git a/kernel/panic.c b/kernel/panic.c
index cf80672b792..bad337c3d66 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -27,6 +27,9 @@
 #define PANIC_TIMER_STEP 100
 #define PANIC_BLINK_SPD 18
 
+/* Machine specific panic information string */
+char *mach_panic_string;
+
 int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE;
 static unsigned long tainted_mask;
 static int pause_on_oops;
@@ -396,6 +399,11 @@ late_initcall(init_oops_id);
 void print_oops_end_marker(void)
 {
 	init_oops_id();
+
+	if (mach_panic_string)
+		printk(KERN_WARNING "Board Information: %s\n",
+		       mach_panic_string);
+
 	pr_warn("---[ end trace %016llx ]---\n", (unsigned long long)oops_id);
 }
 
diff --git a/kernel/pid.c b/kernel/pid.c
index 9b9a2669814..82430c858d6 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -341,6 +341,8 @@ out:
 
 out_unlock:
 	spin_unlock_irq(&pidmap_lock);
+	put_pid_ns(ns);
+
 out_free:
 	while (++i <= ns->level)
 		free_pidmap(pid->numbers + i);
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index bbef57f5bdf..67ecc6b59e1 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -18,6 +18,15 @@ config SUSPEND_FREEZER
 
 	  Turning OFF this setting is NOT recommended! If in doubt, say Y.
 
+config WAKELOCK
+	bool "Android's method of preventing suspend"
+	default y
+	---help---
+	  This allows applications to prevent the CPU from suspending while
+	  they need it.
+
+	  Say Y if you are running an android userspace.
+
 config HIBERNATE_CALLBACKS
 	bool
 
@@ -191,7 +200,7 @@ config DPM_WATCHDOG
 config DPM_WATCHDOG_TIMEOUT
 	int "Watchdog timeout in seconds"
 	range 1 120
-	default 12
+	default 60
 	depends on DPM_WATCHDOG
 
 config PM_TRACE
@@ -309,3 +318,10 @@ config PM_GENERIC_DOMAINS_OF
 config CPU_PM
 	bool
 	depends on SUSPEND || CPU_IDLE
+
+config SUSPEND_TIME
+	bool "Log time spent in suspend"
+	---help---
+	  Prints the time spent in suspend in the kernel log, and
+	  keeps statistics on the time spent in suspend in
+	  /sys/kernel/debug/suspend_time
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index 29472bff11e..74c713ba61b 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -11,5 +11,8 @@ obj-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o user.o \
 				   block_io.o
 obj-$(CONFIG_PM_AUTOSLEEP)	+= autosleep.o
 obj-$(CONFIG_PM_WAKELOCKS)	+= wakelock.o
+obj-$(CONFIG_SUSPEND_TIME)	+= suspend_time.o
 
 obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o
+
+obj-$(CONFIG_SUSPEND)	+= wakeup_reason.o
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 5a6ec8678b9..7456dcb1624 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -18,6 +18,7 @@
 #include <linux/workqueue.h>
 #include <linux/kmod.h>
 #include <trace/events/power.h>
+#include <linux/wakeup_reason.h>
 
 /* 
  * Timeout for stopping processes
@@ -35,6 +36,9 @@ static int try_to_freeze_tasks(bool user_only)
 	unsigned int elapsed_msecs;
 	bool wakeup = false;
 	int sleep_usecs = USEC_PER_MSEC;
+#ifdef CONFIG_PM_SLEEP
+	char suspend_abort[MAX_SUSPEND_ABORT_LEN];
+#endif
 
 	do_gettimeofday(&start);
 
@@ -64,6 +68,11 @@ static int try_to_freeze_tasks(bool user_only)
 			break;
 
 		if (pm_wakeup_pending()) {
+#ifdef CONFIG_PM_SLEEP
+			pm_get_active_wakeup_sources(suspend_abort,
+				MAX_SUSPEND_ABORT_LEN);
+			log_suspend_abort_reason(suspend_abort);
+#endif
 			wakeup = true;
 			break;
 		}
@@ -83,15 +92,17 @@ static int try_to_freeze_tasks(bool user_only)
 	do_div(elapsed_msecs64, NSEC_PER_MSEC);
 	elapsed_msecs = elapsed_msecs64;
 
-	if (todo) {
+	if (wakeup) {
 		printk("\n");
-		printk(KERN_ERR "Freezing of tasks %s after %d.%03d seconds "
-		       "(%d tasks refusing to freeze, wq_busy=%d):\n",
-		       wakeup ? "aborted" : "failed",
+		printk(KERN_ERR "Freezing of tasks aborted after %d.%03d seconds",
+		       elapsed_msecs / 1000, elapsed_msecs % 1000);
+	} else if (todo) {
+		printk("\n");
+		printk(KERN_ERR "Freezing of tasks failed after %d.%03d seconds"
+		       " (%d tasks refusing to freeze, wq_busy=%d):\n",
 		       elapsed_msecs / 1000, elapsed_msecs % 1000,
 		       todo - wq_busy, wq_busy);
 
-		if (!wakeup) {
 			read_lock(&tasklist_lock);
 			for_each_process_thread(g, p) {
 				if (p != current && !freezer_should_skip(p)
@@ -99,7 +110,6 @@ static int try_to_freeze_tasks(bool user_only)
 					sched_show_task(p);
 			}
 			read_unlock(&tasklist_lock);
-		}
 	} else {
 		printk("(elapsed %d.%03d seconds) ", elapsed_msecs / 1000,
 			elapsed_msecs % 1000);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 791a61892bb..7325e35403c 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -954,25 +954,6 @@ static void mark_nosave_pages(struct memory_bitmap *bm)
 	}
 }
 
-static bool is_nosave_page(unsigned long pfn)
-{
-	struct nosave_region *region;
-
-	list_for_each_entry(region, &nosave_regions, list) {
-		if (pfn >= region->start_pfn && pfn < region->end_pfn) {
-			pr_err("PM: %#010llx in e820 nosave region: "
-			       "[mem %#010llx-%#010llx]\n",
-			       (unsigned long long) pfn << PAGE_SHIFT,
-			       (unsigned long long) region->start_pfn << PAGE_SHIFT,
-			       ((unsigned long long) region->end_pfn << PAGE_SHIFT)
-					- 1);
-			return true;
-		}
-	}
-
-	return false;
-}
-
 /**
  *	create_basic_memory_bitmaps - create bitmaps needed for marking page
  *	frames that should not be saved and free page frames.  The pointers
@@ -2038,7 +2019,7 @@ static int mark_unsafe_pages(struct memory_bitmap *bm)
 	do {
 		pfn = memory_bm_next_pfn(bm);
 		if (likely(pfn != BM_END_OF_MAP)) {
-			if (likely(pfn_valid(pfn)) && !is_nosave_page(pfn))
+			if (likely(pfn_valid(pfn)))
 				swsusp_set_page_free(pfn_to_page(pfn));
 			else
 				return -EFAULT;
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index c347e3ce3a5..a212348cbfb 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -26,8 +26,10 @@
 #include <linux/suspend.h>
 #include <linux/syscore_ops.h>
 #include <linux/ftrace.h>
+#include <linux/rtc.h>
 #include <trace/events/power.h>
 #include <linux/compiler.h>
+#include <linux/wakeup_reason.h>
 
 #include "power.h"
 
@@ -271,7 +273,8 @@ void __weak arch_suspend_enable_irqs(void)
  */
 static int suspend_enter(suspend_state_t state, bool *wakeup)
 {
-	int error;
+	char suspend_abort[MAX_SUSPEND_ABORT_LEN];
+	int error, last_dev;
 
 	error = platform_suspend_prepare(state);
 	if (error)
@@ -279,7 +282,11 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 
 	error = dpm_suspend_late(PMSG_SUSPEND);
 	if (error) {
+		last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1;
+		last_dev %= REC_FAILED_NUM;
 		printk(KERN_ERR "PM: late suspend of devices failed\n");
+		log_suspend_abort_reason("%s device failed to power down",
+			suspend_stats.failed_devs[last_dev]);
 		goto Platform_finish;
 	}
 	error = platform_suspend_prepare_late(state);
@@ -288,7 +295,11 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 
 	error = dpm_suspend_noirq(PMSG_SUSPEND);
 	if (error) {
+		last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1;
+		last_dev %= REC_FAILED_NUM;
 		printk(KERN_ERR "PM: noirq suspend of devices failed\n");
+		log_suspend_abort_reason("noirq suspend of %s device failed",
+			suspend_stats.failed_devs[last_dev]);
 		goto Platform_early_resume;
 	}
 	error = platform_suspend_prepare_noirq(state);
@@ -312,8 +323,10 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	}
 
 	error = disable_nonboot_cpus();
-	if (error || suspend_test(TEST_CPUS))
+	if (error || suspend_test(TEST_CPUS)) {
+		log_suspend_abort_reason("Disabling non-boot cpus failed");
 		goto Enable_cpus;
+	}
 
 	arch_suspend_disable_irqs();
 	BUG_ON(!irqs_disabled());
@@ -328,6 +341,11 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 			trace_suspend_resume(TPS("machine_suspend"),
 				state, false);
 			events_check_enabled = false;
+		} else if (*wakeup) {
+			pm_get_active_wakeup_sources(suspend_abort,
+				MAX_SUSPEND_ABORT_LEN);
+			log_suspend_abort_reason(suspend_abort);
+			error = -EBUSY;
 		}
 		syscore_resume();
 	}
@@ -374,6 +392,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 	error = dpm_suspend_start(PMSG_SUSPEND);
 	if (error) {
 		pr_err("PM: Some devices failed to suspend, or early wake event detected\n");
+		log_suspend_abort_reason("Some devices failed to suspend, or early wake event detected");
 		goto Recover_platform;
 	}
 	suspend_test_finish("suspend devices");
@@ -472,6 +491,18 @@ static int enter_state(suspend_state_t state)
 	return error;
 }
 
+static void pm_suspend_marker(char *annotation)
+{
+	struct timespec ts;
+	struct rtc_time tm;
+
+	getnstimeofday(&ts);
+	rtc_time_to_tm(ts.tv_sec, &tm);
+	pr_info("PM: suspend %s %d-%02d-%02d %02d:%02d:%02d.%09lu UTC\n",
+		annotation, tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
+		tm.tm_hour, tm.tm_min, tm.tm_sec, ts.tv_nsec);
+}
+
 /**
  * pm_suspend - Externally visible function for suspending the system.
  * @state: System sleep state to enter.
@@ -486,6 +517,7 @@ int pm_suspend(suspend_state_t state)
 	if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX)
 		return -EINVAL;
 
+	pm_suspend_marker("entry");
 	error = enter_state(state);
 	if (error) {
 		suspend_stats.fail++;
@@ -493,6 +525,7 @@ int pm_suspend(suspend_state_t state)
 	} else {
 		suspend_stats.success++;
 	}
+	pm_suspend_marker("exit");
 	return error;
 }
 EXPORT_SYMBOL(pm_suspend);
diff --git a/kernel/power/suspend_time.c b/kernel/power/suspend_time.c
new file mode 100644
index 00000000000..d2a65da9f22
--- /dev/null
+++ b/kernel/power/suspend_time.c
@@ -0,0 +1,111 @@
+/*
+ * debugfs file to track time spent in suspend
+ *
+ * Copyright (c) 2011, Google, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/seq_file.h>
+#include <linux/syscore_ops.h>
+#include <linux/time.h>
+
+static struct timespec suspend_time_before;
+static unsigned int time_in_suspend_bins[32];
+
+#ifdef CONFIG_DEBUG_FS
+static int suspend_time_debug_show(struct seq_file *s, void *data)
+{
+	int bin;
+	seq_printf(s, "time (secs)  count\n");
+	seq_printf(s, "------------------\n");
+	for (bin = 0; bin < 32; bin++) {
+		if (time_in_suspend_bins[bin] == 0)
+			continue;
+		seq_printf(s, "%4d - %4d %4u\n",
+			bin ? 1 << (bin - 1) : 0, 1 << bin,
+				time_in_suspend_bins[bin]);
+	}
+	return 0;
+}
+
+static int suspend_time_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, suspend_time_debug_show, NULL);
+}
+
+static const struct file_operations suspend_time_debug_fops = {
+	.open		= suspend_time_debug_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init suspend_time_debug_init(void)
+{
+	struct dentry *d;
+
+	d = debugfs_create_file("suspend_time", 0755, NULL, NULL,
+		&suspend_time_debug_fops);
+	if (!d) {
+		pr_err("Failed to create suspend_time debug file\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+late_initcall(suspend_time_debug_init);
+#endif
+
+static int suspend_time_syscore_suspend(void)
+{
+	read_persistent_clock(&suspend_time_before);
+
+	return 0;
+}
+
+static void suspend_time_syscore_resume(void)
+{
+	struct timespec after;
+
+	read_persistent_clock(&after);
+
+	after = timespec_sub(after, suspend_time_before);
+
+	time_in_suspend_bins[fls(after.tv_sec)]++;
+
+	pr_info("Suspended for %lu.%03lu seconds\n", after.tv_sec,
+		after.tv_nsec / NSEC_PER_MSEC);
+}
+
+static struct syscore_ops suspend_time_syscore_ops = {
+	.suspend = suspend_time_syscore_suspend,
+	.resume = suspend_time_syscore_resume,
+};
+
+static int suspend_time_syscore_init(void)
+{
+	register_syscore_ops(&suspend_time_syscore_ops);
+
+	return 0;
+}
+
+static void suspend_time_syscore_exit(void)
+{
+	unregister_syscore_ops(&suspend_time_syscore_ops);
+}
+module_init(suspend_time_syscore_init);
+module_exit(suspend_time_syscore_exit);
diff --git a/kernel/power/wakeup_reason.c b/kernel/power/wakeup_reason.c
new file mode 100644
index 00000000000..252611fad2f
--- /dev/null
+++ b/kernel/power/wakeup_reason.c
@@ -0,0 +1,225 @@
+/*
+ * kernel/power/wakeup_reason.c
+ *
+ * Logs the reasons which caused the kernel to resume from
+ * the suspend mode.
+ *
+ * Copyright (C) 2014 Google, Inc.
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/wakeup_reason.h>
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/notifier.h>
+#include <linux/suspend.h>
+
+
+#define MAX_WAKEUP_REASON_IRQS 32
+static int irq_list[MAX_WAKEUP_REASON_IRQS];
+static int irqcount;
+static bool suspend_abort;
+static char abort_reason[MAX_SUSPEND_ABORT_LEN];
+static struct kobject *wakeup_reason;
+static DEFINE_SPINLOCK(resume_reason_lock);
+
+static ktime_t last_monotime; /* monotonic time before last suspend */
+static ktime_t curr_monotime; /* monotonic time after last suspend */
+static ktime_t last_stime; /* monotonic boottime offset before last suspend */
+static ktime_t curr_stime; /* monotonic boottime offset after last suspend */
+
+static ssize_t last_resume_reason_show(struct kobject *kobj, struct kobj_attribute *attr,
+		char *buf)
+{
+	int irq_no, buf_offset = 0;
+	struct irq_desc *desc;
+	spin_lock(&resume_reason_lock);
+	if (suspend_abort) {
+		buf_offset = sprintf(buf, "Abort: %s", abort_reason);
+	} else {
+		for (irq_no = 0; irq_no < irqcount; irq_no++) {
+			desc = irq_to_desc(irq_list[irq_no]);
+			if (desc && desc->action && desc->action->name)
+				buf_offset += sprintf(buf + buf_offset, "%d %s\n",
+						irq_list[irq_no], desc->action->name);
+			else
+				buf_offset += sprintf(buf + buf_offset, "%d\n",
+						irq_list[irq_no]);
+		}
+	}
+	spin_unlock(&resume_reason_lock);
+	return buf_offset;
+}
+
+static ssize_t last_suspend_time_show(struct kobject *kobj,
+			struct kobj_attribute *attr, char *buf)
+{
+	struct timespec sleep_time;
+	struct timespec total_time;
+	struct timespec suspend_resume_time;
+
+	/*
+	 * total_time is calculated from monotonic bootoffsets because
+	 * unlike CLOCK_MONOTONIC it include the time spent in suspend state.
+	 */
+	total_time = ktime_to_timespec(ktime_sub(curr_stime, last_stime));
+
+	/*
+	 * suspend_resume_time is calculated as monotonic (CLOCK_MONOTONIC)
+	 * time interval before entering suspend and post suspend.
+	 */
+	suspend_resume_time = ktime_to_timespec(ktime_sub(curr_monotime, last_monotime));
+
+	/* sleep_time = total_time - suspend_resume_time */
+	sleep_time = timespec_sub(total_time, suspend_resume_time);
+
+	/* Export suspend_resume_time and sleep_time in pair here. */
+	return sprintf(buf, "%lu.%09lu %lu.%09lu\n",
+				suspend_resume_time.tv_sec, suspend_resume_time.tv_nsec,
+				sleep_time.tv_sec, sleep_time.tv_nsec);
+}
+
+static struct kobj_attribute resume_reason = __ATTR_RO(last_resume_reason);
+static struct kobj_attribute suspend_time = __ATTR_RO(last_suspend_time);
+
+static struct attribute *attrs[] = {
+	&resume_reason.attr,
+	&suspend_time.attr,
+	NULL,
+};
+static struct attribute_group attr_group = {
+	.attrs = attrs,
+};
+
+/*
+ * logs all the wake up reasons to the kernel
+ * stores the irqs to expose them to the userspace via sysfs
+ */
+void log_wakeup_reason(int irq)
+{
+	struct irq_desc *desc;
+	desc = irq_to_desc(irq);
+	if (desc && desc->action && desc->action->name)
+		printk(KERN_INFO "Resume caused by IRQ %d, %s\n", irq,
+				desc->action->name);
+	else
+		printk(KERN_INFO "Resume caused by IRQ %d\n", irq);
+
+	spin_lock(&resume_reason_lock);
+	if (irqcount == MAX_WAKEUP_REASON_IRQS) {
+		spin_unlock(&resume_reason_lock);
+		printk(KERN_WARNING "Resume caused by more than %d IRQs\n",
+				MAX_WAKEUP_REASON_IRQS);
+		return;
+	}
+
+	irq_list[irqcount++] = irq;
+	spin_unlock(&resume_reason_lock);
+}
+
+int check_wakeup_reason(int irq)
+{
+	int irq_no;
+	int ret = false;
+
+	spin_lock(&resume_reason_lock);
+	for (irq_no = 0; irq_no < irqcount; irq_no++)
+		if (irq_list[irq_no] == irq) {
+			ret = true;
+			break;
+	}
+	spin_unlock(&resume_reason_lock);
+	return ret;
+}
+
+void log_suspend_abort_reason(const char *fmt, ...)
+{
+	va_list args;
+
+	spin_lock(&resume_reason_lock);
+
+	//Suspend abort reason has already been logged.
+	if (suspend_abort) {
+		spin_unlock(&resume_reason_lock);
+		return;
+	}
+
+	suspend_abort = true;
+	va_start(args, fmt);
+	vsnprintf(abort_reason, MAX_SUSPEND_ABORT_LEN, fmt, args);
+	va_end(args);
+	spin_unlock(&resume_reason_lock);
+}
+
+/* Detects a suspend and clears all the previous wake up reasons*/
+static int wakeup_reason_pm_event(struct notifier_block *notifier,
+		unsigned long pm_event, void *unused)
+{
+	switch (pm_event) {
+	case PM_SUSPEND_PREPARE:
+		spin_lock(&resume_reason_lock);
+		irqcount = 0;
+		suspend_abort = false;
+		spin_unlock(&resume_reason_lock);
+		/* monotonic time since boot */
+		last_monotime = ktime_get();
+		/* monotonic time since boot including the time spent in suspend */
+		last_stime = ktime_get_boottime();
+		break;
+	case PM_POST_SUSPEND:
+		/* monotonic time since boot */
+		curr_monotime = ktime_get();
+		/* monotonic time since boot including the time spent in suspend */
+		curr_stime = ktime_get_boottime();
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block wakeup_reason_pm_notifier_block = {
+	.notifier_call = wakeup_reason_pm_event,
+};
+
+/* Initializes the sysfs parameter
+ * registers the pm_event notifier
+ */
+int __init wakeup_reason_init(void)
+{
+	int retval;
+
+	retval = register_pm_notifier(&wakeup_reason_pm_notifier_block);
+	if (retval)
+		printk(KERN_WARNING "[%s] failed to register PM notifier %d\n",
+				__func__, retval);
+
+	wakeup_reason = kobject_create_and_add("wakeup_reasons", kernel_kobj);
+	if (!wakeup_reason) {
+		printk(KERN_WARNING "[%s] failed to create a sysfs kobject\n",
+				__func__);
+		return 1;
+	}
+	retval = sysfs_create_group(wakeup_reason, &attr_group);
+	if (retval) {
+		kobject_put(wakeup_reason);
+		printk(KERN_WARNING "[%s] failed to create a sysfs group %d\n",
+				__func__, retval);
+	}
+	return 0;
+}
+
+late_initcall(wakeup_reason_init);
diff --git a/kernel/printk/console_cmdline.h b/kernel/printk/console_cmdline.h
index cbd69d84234..2ca4a8b5fe5 100644
--- a/kernel/printk/console_cmdline.h
+++ b/kernel/printk/console_cmdline.h
@@ -3,7 +3,7 @@
 
 struct console_cmdline
 {
-	char	name[8];			/* Name of the driver	    */
+	char	name[16];			/* Name of the driver	    */
 	int	index;				/* Minor dev. to use	    */
 	char	*options;			/* Options for the driver   */
 #ifdef CONFIG_A11Y_BRAILLE_CONSOLE
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index ced2b84b1cb..ac42553b7d3 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -55,6 +55,10 @@
 #include "console_cmdline.h"
 #include "braille.h"
 
+#ifdef CONFIG_EARLY_PRINTK_DIRECT
+extern void printascii(char *);
+#endif
+
 int console_printk[4] = {
 	CONSOLE_LOGLEVEL_DEFAULT,	/* console_loglevel */
 	MESSAGE_LOGLEVEL_DEFAULT,	/* default_message_loglevel */
@@ -487,11 +491,11 @@ static int check_syslog_permissions(int type, bool from_file)
 	 * already done the capabilities checks at open time.
 	 */
 	if (from_file && type != SYSLOG_ACTION_OPEN)
-		return 0;
+		goto ok;
 
 	if (syslog_action_restricted(type)) {
 		if (capable(CAP_SYSLOG))
-			return 0;
+			goto ok;
 		/*
 		 * For historical reasons, accept CAP_SYS_ADMIN too, with
 		 * a warning.
@@ -501,10 +505,11 @@ static int check_syslog_permissions(int type, bool from_file)
 				     "CAP_SYS_ADMIN but no CAP_SYSLOG "
 				     "(deprecated).\n",
 				 current->comm, task_pid_nr(current));
-			return 0;
+			goto ok;
 		}
 		return -EPERM;
 	}
+ok:
 	return security_syslog(type);
 }
 
@@ -1266,10 +1271,6 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
 	if (error)
 		goto out;
 
-	error = security_syslog(type);
-	if (error)
-		return error;
-
 	switch (type) {
 	case SYSLOG_ACTION_CLOSE:	/* Close log */
 		break;
@@ -1710,6 +1711,10 @@ asmlinkage int vprintk_emit(int facility, int level,
 		}
 	}
 
+#ifdef CONFIG_EARLY_PRINTK_DIRECT
+	printascii(text);
+#endif
+
 	if (level == -1)
 		level = default_message_loglevel;
 
@@ -2440,6 +2445,7 @@ void register_console(struct console *newcon)
 	for (i = 0, c = console_cmdline;
 	     i < MAX_CMDLINECONSOLES && c->name[0];
 	     i++, c++) {
+		BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name));
 		if (strcmp(c->name, newcon->name) != 0)
 			continue;
 		if (newcon->index >= 0 &&
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 54e75226c2c..dcd968232d4 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -714,6 +714,8 @@ static int ptrace_peek_siginfo(struct task_struct *child,
 static int ptrace_resume(struct task_struct *child, long request,
 			 unsigned long data)
 {
+	bool need_siglock;
+
 	if (!valid_signal(data))
 		return -EIO;
 
@@ -741,8 +743,26 @@ static int ptrace_resume(struct task_struct *child, long request,
 		user_disable_single_step(child);
 	}
 
+	/*
+	 * Change ->exit_code and ->state under siglock to avoid the race
+	 * with wait_task_stopped() in between; a non-zero ->exit_code will
+	 * wrongly look like another report from tracee.
+	 *
+	 * Note that we need siglock even if ->exit_code == data and/or this
+	 * status was not reported yet, the new status must not be cleared by
+	 * wait_task_stopped() after resume.
+	 *
+	 * If data == 0 we do not care if wait_task_stopped() reports the old
+	 * status and clears the code too; this can't race with the tracee, it
+	 * takes siglock after resume.
+	 */
+	need_siglock = data && !thread_group_empty(current);
+	if (need_siglock)
+		spin_lock_irq(&child->sighand->siglock);
 	child->exit_code = data;
 	wake_up_state(child, __TASK_TRACED);
+	if (need_siglock)
+		spin_unlock_irq(&child->sighand->siglock);
 
 	return 0;
 }
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index c0623fc4712..da80f2f73b5 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -282,6 +282,11 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 
 	/* Move the ready-to-invoke callbacks to a local list. */
 	local_irq_save(flags);
+	if (rcp->donetail == &rcp->rcucblist) {
+		/* No callbacks ready, so just leave. */
+		local_irq_restore(flags);
+		return;
+	}
 	RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1));
 	list = rcp->rcucblist;
 	rcp->rcucblist = *rcp->donetail;
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index 8a2e230fb86..eae160dd669 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -87,8 +87,7 @@ static inline struct autogroup *autogroup_create(void)
 	 * so we don't have to move tasks around upon policy change,
 	 * or flail around trying to allocate bandwidth on the fly.
 	 * A bandwidth exception in __sched_setscheduler() allows
-	 * the policy change to proceed.  Thereafter, task_group()
-	 * returns &root_task_group, so zero bandwidth is required.
+	 * the policy change to proceed.
 	 */
 	free_rt_sched_group(tg);
 	tg->rt_se = root_task_group.rt_se;
@@ -115,9 +114,6 @@ bool task_wants_autogroup(struct task_struct *p, struct task_group *tg)
 	if (tg != &root_task_group)
 		return false;
 
-	if (p->sched_class != &fair_sched_class)
-		return false;
-
 	/*
 	 * We can only assume the task group can't go away on us if
 	 * autogroup_move_group() can see us on ->thread_group list.
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 89e7283015a..b254d0c395b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -490,6 +490,11 @@ static __init void init_hrtick(void)
  */
 void hrtick_start(struct rq *rq, u64 delay)
 {
+	/*
+	 * Don't schedule slices shorter than 10000ns, that just
+	 * doesn't make sense. Rely on vruntime for fairness.
+	 */
+	delay = max_t(u64, delay, 10000LL);
 	__hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
 			HRTIMER_MODE_REL_PINNED, 0);
 }
@@ -1577,7 +1582,12 @@ void scheduler_ipi(void)
 	 */
 	preempt_fold_need_resched();
 
-	if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick())
+	if (llist_empty(&this_rq()->wake_list)
+			&& !got_nohz_idle_kick()
+#ifdef CONFIG_SCHED_HMP
+			&& !this_rq()->wake_for_idle_pull
+#endif
+			)
 		return;
 
 	/*
@@ -1603,6 +1613,11 @@ void scheduler_ipi(void)
 		this_rq()->idle_balance = 1;
 		raise_softirq_irqoff(SCHED_SOFTIRQ);
 	}
+#ifdef CONFIG_SCHED_HMP
+	else if (unlikely(this_rq()->wake_for_idle_pull))
+		raise_softirq_irqoff(SCHED_SOFTIRQ);
+#endif
+
 	irq_exit();
 }
 
@@ -1623,8 +1638,10 @@ void wake_up_if_idle(int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
 
-	if (!is_idle_task(rq->curr))
-		return;
+	rcu_read_lock();
+
+	if (!is_idle_task(rcu_dereference(rq->curr)))
+		goto out;
 
 	if (set_nr_if_polling(rq->idle)) {
 		trace_sched_wake_idle_without_ipi(cpu);
@@ -1635,6 +1652,9 @@ void wake_up_if_idle(int cpu)
 		/* Else cpu is not in idle, do nothing here */
 		raw_spin_unlock_irqrestore(&rq->lock, flags);
 	}
+
+out:
+	rcu_read_unlock();
 }
 
 bool cpus_share_cache(int this_cpu, int that_cpu)
@@ -1824,6 +1844,20 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->se.vruntime			= 0;
 	INIT_LIST_HEAD(&p->se.group_node);
 
+#ifdef CONFIG_SCHED_HMP
+	/* keep LOAD_AVG_MAX in sync with fair.c if load avg series is changed */
+#define LOAD_AVG_MAX 47742
+	p->se.avg.hmp_last_up_migration = 0;
+	p->se.avg.hmp_last_down_migration = 0;
+	if (hmp_task_should_forkboost(p)) {
+		p->se.avg.load_avg_ratio = 1023;
+		p->se.avg.load_avg_contrib =
+				(1023 * scale_load_down(p->se.load.weight));
+		p->se.avg.runnable_avg_period = LOAD_AVG_MAX;
+		p->se.avg.runnable_avg_sum = LOAD_AVG_MAX;
+		p->se.avg.usage_avg_sum = LOAD_AVG_MAX;
+	}
+#endif
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
@@ -3087,6 +3121,8 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	} else {
 		if (dl_prio(oldprio))
 			p->dl.dl_boosted = 0;
+		if (rt_prio(oldprio))
+			p->rt.timeout = 0;
 		p->sched_class = &fair_sched_class;
 	}
 
@@ -3313,22 +3349,36 @@ static void __setscheduler_params(struct task_struct *p,
 	set_load_weight(p);
 }
 
+extern struct cpumask hmp_slow_cpu_mask;
+
 /* Actually do priority change: must hold pi & rq lock. */
 static void __setscheduler(struct rq *rq, struct task_struct *p,
-			   const struct sched_attr *attr)
+			   const struct sched_attr *attr, bool keep_boost)
 {
 	__setscheduler_params(p, attr);
 
 	/*
-	 * If we get here, there was no pi waiters boosting the
-	 * task. It is safe to use the normal prio.
+	 * Keep a potential priority boosting if called from
+	 * sched_setscheduler().
 	 */
-	p->prio = normal_prio(p);
+	if (keep_boost)
+		p->prio = rt_mutex_get_effective_prio(p, normal_prio(p));
+	else
+		p->prio = normal_prio(p);
 
 	if (dl_prio(p->prio))
 		p->sched_class = &dl_sched_class;
-	else if (rt_prio(p->prio))
+	else if (rt_prio(p->prio)) {
 		p->sched_class = &rt_sched_class;
+#ifdef CONFIG_SCHED_HMP
+		if (!cpumask_empty(&hmp_slow_cpu_mask))
+			if (cpumask_equal(&p->cpus_allowed, cpu_all_mask)) {
+				p->nr_cpus_allowed =
+					cpumask_weight(&hmp_slow_cpu_mask);
+				do_set_cpus_allowed(p, &hmp_slow_cpu_mask);
+			}
+#endif
+	}
 	else
 		p->sched_class = &fair_sched_class;
 }
@@ -3409,7 +3459,7 @@ static int __sched_setscheduler(struct task_struct *p,
 	int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 :
 		      MAX_RT_PRIO - 1 - attr->sched_priority;
 	int retval, oldprio, oldpolicy = -1, queued, running;
-	int policy = attr->sched_policy;
+	int new_effective_prio, policy = attr->sched_policy;
 	unsigned long flags;
 	const struct sched_class *prev_class;
 	struct rq *rq;
@@ -3591,15 +3641,14 @@ change:
 	oldprio = p->prio;
 
 	/*
-	 * Special case for priority boosted tasks.
-	 *
-	 * If the new priority is lower or equal (user space view)
-	 * than the current (boosted) priority, we just store the new
+	 * Take priority boosted tasks into account. If the new
+	 * effective priority is unchanged, we just store the new
 	 * normal parameters and do not touch the scheduler class and
 	 * the runqueue. This will be done when the task deboost
 	 * itself.
 	 */
-	if (rt_mutex_check_prio(p, newprio)) {
+	new_effective_prio = rt_mutex_get_effective_prio(p, newprio);
+	if (new_effective_prio == oldprio) {
 		__setscheduler_params(p, attr);
 		task_rq_unlock(rq, p, &flags);
 		return 0;
@@ -3613,7 +3662,7 @@ change:
 		put_prev_task(rq, p);
 
 	prev_class = p->sched_class;
-	__setscheduler(rq, p, attr);
+	__setscheduler(rq, p, attr, true);
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
@@ -6213,6 +6262,10 @@ sd_init(struct sched_domain_topology_level *tl, int cpu)
 #endif
 	} else {
 		sd->flags |= SD_PREFER_SIBLING;
+#ifdef CONFIG_SCHED_HMP
+		/* Disable load balance on DIE level */
+		sd->flags &= ~SD_LOAD_BALANCE;
+#endif
 		sd->cache_nice_tries = 1;
 		sd->busy_idx = 2;
 		sd->idle_idx = 1;
@@ -7176,14 +7229,24 @@ static inline int preempt_count_equals(int preempt_offset)
 	return (nested == preempt_offset);
 }
 
+static int __might_sleep_init_called;
+int __init __might_sleep_init(void)
+{
+	__might_sleep_init_called = 1;
+	return 0;
+}
+early_initcall(__might_sleep_init);
+
 void __might_sleep(const char *file, int line, int preempt_offset)
 {
 	static unsigned long prev_jiffy;	/* ratelimiting */
 
 	rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
 	if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
-	     !is_idle_task(current)) ||
-	    system_state != SYSTEM_RUNNING || oops_in_progress)
+	     !is_idle_task(current)) || oops_in_progress)
+		return;
+	if (system_state != SYSTEM_RUNNING &&
+	    (!__might_sleep_init_called || system_state != SYSTEM_BOOTING))
 		return;
 	if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
 		return;
@@ -7225,7 +7288,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
 	queued = task_on_rq_queued(p);
 	if (queued)
 		dequeue_task(rq, p, 0);
-	__setscheduler(rq, p, &attr);
+	__setscheduler(rq, p, &attr, false);
 	if (queued) {
 		enqueue_task(rq, p, 0);
 		resched_curr(rq);
@@ -7460,6 +7523,12 @@ static inline int tg_has_rt_tasks(struct task_group *tg)
 {
 	struct task_struct *g, *p;
 
+	/*
+	 * Autogroups do not have RT tasks; see autogroup_create().
+	 */
+	if (task_group_is_autogroup(tg))
+		return 0;
+
 	for_each_process_thread(g, p) {
 		if (rt_task(p) && task_group(p) == tg)
 			return 1;
@@ -8237,6 +8306,7 @@ struct cgroup_subsys cpu_cgrp_subsys = {
 	.fork		= cpu_cgroup_fork,
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
+	.allow_attach   = subsys_cgroup_allow_attach,
 	.exit		= cpu_cgroup_exit,
 	.legacy_cftypes	= cpu_files,
 	.early_init	= 1,
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 8394b1ee600..b293203ff25 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -1,3 +1,4 @@
+#include <linux/cpufreq.h>
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/tsacct_kern.h>
@@ -149,6 +150,11 @@ void account_user_time(struct task_struct *p, cputime_t cputime,
 
 	/* Account for user time used */
 	acct_account_cputime(p);
+
+#ifdef CONFIG_CPU_FREQ_STAT
+	/* Account power usage for user time */
+	acct_update_power(p, cputime);
+#endif
 }
 
 /*
@@ -199,6 +205,11 @@ void __account_system_time(struct task_struct *p, cputime_t cputime,
 
 	/* Account for system time used */
 	acct_account_cputime(p);
+
+#ifdef CONFIG_CPU_FREQ_STAT
+	/* Account power usage for system time */
+	acct_update_power(p, cputime);
+#endif
 }
 
 /*
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 28fa9d9e920..40a97c3d8ab 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -575,24 +575,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
 static
 int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
 {
-	int dmiss = dl_time_before(dl_se->deadline, rq_clock(rq));
-	int rorun = dl_se->runtime <= 0;
-
-	if (!rorun && !dmiss)
-		return 0;
-
-	/*
-	 * If we are beyond our current deadline and we are still
-	 * executing, then we have already used some of the runtime of
-	 * the next instance. Thus, if we do not account that, we are
-	 * stealing bandwidth from the system at each deadline miss!
-	 */
-	if (dmiss) {
-		dl_se->runtime = rorun ? dl_se->runtime : 0;
-		dl_se->runtime -= rq_clock(rq) - dl_se->deadline;
-	}
-
-	return 1;
+	return (dl_se->runtime <= 0);
 }
 
 extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
@@ -831,10 +814,10 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se,
 	 * parameters of the task might need updating. Otherwise,
 	 * we want a replenishment of its runtime.
 	 */
-	if (!dl_se->dl_new && flags & ENQUEUE_REPLENISH)
-		replenish_dl_entity(dl_se, pi_se);
-	else
+	if (dl_se->dl_new || flags & ENQUEUE_WAKEUP)
 		update_dl_entity(dl_se, pi_se);
+	else if (flags & ENQUEUE_REPLENISH)
+		replenish_dl_entity(dl_se, pi_se);
 
 	__enqueue_dl_entity(dl_se);
 }
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index ce33780d8f2..c5c876442f5 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -95,6 +95,7 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 #ifdef CONFIG_SMP
 	P(se->avg.runnable_avg_sum);
 	P(se->avg.runnable_avg_period);
+	P(se->avg.usage_avg_sum);
 	P(se->avg.load_avg_contrib);
 	P(se->avg.decay_count);
 #endif
@@ -223,6 +224,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			atomic_long_read(&cfs_rq->tg->load_avg));
 	SEQ_printf(m, "  .%-30s: %d\n", "tg->runnable_avg",
 			atomic_read(&cfs_rq->tg->runnable_avg));
+	SEQ_printf(m, "  .%-30s: %d\n", "tg->usage_avg",
+			atomic_read(&cfs_rq->tg->usage_avg));
 #endif
 #endif
 #ifdef CONFIG_CFS_BANDWIDTH
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ef2b104b254..72179312b72 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -32,6 +32,17 @@
 #include <linux/task_work.h>
 
 #include <trace/events/sched.h>
+#include <linux/sysfs.h>
+#include <linux/vmalloc.h>
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+/* Include cpufreq header to add a notifier so that cpu frequency
+ * scaling can track the current CPU frequency
+ */
+#include <linux/cpufreq.h>
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
+#ifdef CONFIG_SCHED_HMP
+#include <linux/cpuidle.h>
+#endif
 
 #include "sched.h"
 
@@ -1979,8 +1990,10 @@ void task_numa_work(struct callback_head *work)
 		vma = mm->mmap;
 	}
 	for (; vma; vma = vma->vm_next) {
-		if (!vma_migratable(vma) || !vma_policy_mof(vma))
+		if (!vma_migratable(vma) || !vma_policy_mof(vma) ||
+		    is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) {
 			continue;
+		}
 
 		/*
 		 * Shared library pages mapped by multiple processes are not
@@ -2287,6 +2300,93 @@ static u32 __compute_runnable_contrib(u64 n)
 	return contrib + runnable_avg_yN_sum[n];
 }
 
+#ifdef CONFIG_SCHED_HMP
+#define HMP_VARIABLE_SCALE_SHIFT 16ULL
+struct hmp_global_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct kobject *kobj,
+			struct attribute *attr, char *buf);
+	ssize_t (*store)(struct kobject *a, struct attribute *b,
+			const char *c, size_t count);
+	int *value;
+	int (*to_sysfs)(int);
+	int (*from_sysfs)(int);
+	ssize_t (*to_sysfs_text)(char *buf, int buf_size);
+};
+
+#define HMP_DATA_SYSFS_MAX 8
+
+struct hmp_data_struct {
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+	int freqinvar_load_scale_enabled;
+#endif
+	int multiplier; /* used to scale the time delta */
+	struct attribute_group attr_group;
+	struct attribute *attributes[HMP_DATA_SYSFS_MAX + 1];
+	struct hmp_global_attr attr[HMP_DATA_SYSFS_MAX];
+} hmp_data;
+
+static u64 hmp_variable_scale_convert(u64 delta);
+
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+/* Frequency-Invariant Load Modification:
+ * Loads are calculated as in PJT's patch however we also scale the current
+ * contribution in line with the frequency of the CPU that the task was
+ * executed on.
+ * In this version, we use a simple linear scale derived from the maximum
+ * frequency reported by CPUFreq. As an example:
+ *
+ * Consider that we ran a task for 100% of the previous interval.
+ *
+ * Our CPU was under asynchronous frequency control through one of the
+ * CPUFreq governors.
+ *
+ * The CPUFreq governor reports that it is able to scale the CPU between
+ * 500MHz and 1GHz.
+ *
+ * During the period, the CPU was running at 1GHz.
+ *
+ * In this case, our load contribution for that period is calculated as
+ * 1 * (number_of_active_microseconds)
+ *
+ * This results in our task being able to accumulate maximum load as normal.
+ *
+ *
+ * Consider now that our CPU was executing at 500MHz.
+ *
+ * We now scale the load contribution such that it is calculated as
+ * 0.5 * (number_of_active_microseconds)
+ *
+ * Our task can only record 50% maximum load during this period.
+ *
+ * This represents the task consuming 50% of the CPU's *possible* compute
+ * capacity. However the task did consume 100% of the CPU's *available*
+ * compute capacity which is the value seen by the CPUFreq governor and
+ * user-side CPU Utilization tools.
+ *
+ * Restricting tracked load to be scaled by the CPU's frequency accurately
+ * represents the consumption of possible compute capacity and allows the
+ * HMP migration's simple threshold migration strategy to interact more
+ * predictably with CPUFreq's asynchronous compute capacity changes.
+ */
+#define SCHED_FREQSCALE_SHIFT 10
+struct cpufreq_extents {
+	u32 curr_scale;
+	u32 min;
+	u32 max;
+	u32 flags;
+};
+
+/* Flag set when the governor in use only allows one frequency.
+ * Disables scaling.
+ */
+#define SCHED_LOAD_FREQINVAR_SINGLEFREQ 0x01
+
+static struct cpufreq_extents freq_scale[CONFIG_NR_CPUS];
+
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
+#endif /* CONFIG_SCHED_HMP */
+
 /*
  * We can represent the historical contribution to runnable average as the
  * coefficients of a geometric series.  To do this we sub-divide our runnable
@@ -2317,13 +2417,24 @@ static u32 __compute_runnable_contrib(u64 n)
  */
 static __always_inline int __update_entity_runnable_avg(u64 now,
 							struct sched_avg *sa,
-							int runnable)
+							int runnable,
+							int running,
+							int cpu)
 {
 	u64 delta, periods;
 	u32 runnable_contrib;
 	int delta_w, decayed = 0;
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+	u64 scaled_delta;
+	u32 scaled_runnable_contrib;
+	int scaled_delta_w;
+	u32 curr_scale = 1024;
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
 
 	delta = now - sa->last_runnable_update;
+#ifdef CONFIG_SCHED_HMP
+	delta = hmp_variable_scale_convert(delta);
+#endif
 	/*
 	 * This should only happen when time goes backwards, which it
 	 * unfortunately does during sched clock init when we swap over to TSC.
@@ -2342,6 +2453,12 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 		return 0;
 	sa->last_runnable_update = now;
 
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+	/* retrieve scale factor for load */
+	if (hmp_data.freqinvar_load_scale_enabled)
+		curr_scale = freq_scale[cpu].curr_scale;
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
+
 	/* delta_w is the amount already accumulated against our next period */
 	delta_w = sa->runnable_avg_period % 1024;
 	if (delta + delta_w >= 1024) {
@@ -2354,8 +2471,20 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 		 * period and accrue it.
 		 */
 		delta_w = 1024 - delta_w;
+		/* scale runnable time if necessary */
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+		scaled_delta_w = (delta_w * curr_scale)
+				>> SCHED_FREQSCALE_SHIFT;
+		if (runnable)
+			sa->runnable_avg_sum += scaled_delta_w;
+		if (running)
+			sa->usage_avg_sum += scaled_delta_w;
+#else
 		if (runnable)
 			sa->runnable_avg_sum += delta_w;
+		if (running)
+			sa->usage_avg_sum += delta_w;
+#endif /* #ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
 		sa->runnable_avg_period += delta_w;
 
 		delta -= delta_w;
@@ -2363,22 +2492,51 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 		/* Figure out how many additional periods this update spans */
 		periods = delta / 1024;
 		delta %= 1024;
+		/* decay the load we have accumulated so far */
 
 		sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum,
 						  periods + 1);
 		sa->runnable_avg_period = decay_load(sa->runnable_avg_period,
 						     periods + 1);
+		sa->usage_avg_sum = decay_load(sa->usage_avg_sum, periods + 1);
+		/* add the contribution from this period */
 
 		/* Efficiently calculate \sum (1..n_period) 1024*y^i */
 		runnable_contrib = __compute_runnable_contrib(periods);
+		/* Apply load scaling if necessary.
+		 * Note that multiplying the whole series is same as
+		 * multiplying all terms
+		 */
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+		scaled_runnable_contrib = (runnable_contrib * curr_scale)
+				>> SCHED_FREQSCALE_SHIFT;
+		if (runnable)
+			sa->runnable_avg_sum += scaled_runnable_contrib;
+		if (running)
+			sa->usage_avg_sum += scaled_runnable_contrib;
+#else
 		if (runnable)
 			sa->runnable_avg_sum += runnable_contrib;
+		if (running)
+			sa->usage_avg_sum += runnable_contrib;
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
 		sa->runnable_avg_period += runnable_contrib;
 	}
 
 	/* Remainder of delta accrued against u_0` */
+	/* scale if necessary */
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+	scaled_delta = ((delta * curr_scale) >> SCHED_FREQSCALE_SHIFT);
+	if (runnable)
+		sa->runnable_avg_sum += scaled_delta;
+	if (running)
+		sa->usage_avg_sum += scaled_delta;
+#else
 	if (runnable)
 		sa->runnable_avg_sum += delta;
+	if (running)
+		sa->usage_avg_sum += delta;
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
 	sa->runnable_avg_period += delta;
 
 	return decayed;
@@ -2391,10 +2549,8 @@ static inline u64 __synchronize_entity_decay(struct sched_entity *se)
 	u64 decays = atomic64_read(&cfs_rq->decay_counter);
 
 	decays -= se->avg.decay_count;
-	if (!decays)
-		return 0;
-
-	se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays);
+	if (decays)
+		se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays);
 	se->avg.decay_count = 0;
 
 	return decays;
@@ -2427,16 +2583,28 @@ static inline void __update_tg_runnable_avg(struct sched_avg *sa,
 						  struct cfs_rq *cfs_rq)
 {
 	struct task_group *tg = cfs_rq->tg;
-	long contrib;
+	long contrib, usage_contrib;
 
 	/* The fraction of a cpu used by this cfs_rq */
 	contrib = div_u64((u64)sa->runnable_avg_sum << NICE_0_SHIFT,
 			  sa->runnable_avg_period + 1);
 	contrib -= cfs_rq->tg_runnable_contrib;
 
-	if (abs(contrib) > cfs_rq->tg_runnable_contrib / 64) {
+	usage_contrib = div_u64(sa->usage_avg_sum << NICE_0_SHIFT,
+			        sa->runnable_avg_period + 1);
+	usage_contrib -= cfs_rq->tg_usage_contrib;
+
+	/*
+	 * contrib/usage at this point represent deltas, only update if they
+	 * are substantive.
+	 */
+	if ((abs(contrib) > cfs_rq->tg_runnable_contrib / 64) ||
+	    (abs(usage_contrib) > cfs_rq->tg_usage_contrib / 64)) {
 		atomic_add(contrib, &tg->runnable_avg);
 		cfs_rq->tg_runnable_contrib += contrib;
+
+		atomic_add(usage_contrib, &tg->usage_avg);
+		cfs_rq->tg_usage_contrib += usage_contrib;
 	}
 }
 
@@ -2484,8 +2652,17 @@ static inline void __update_group_entity_contrib(struct sched_entity *se)
 
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
 {
-	__update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable);
+	int cpu = -1;	/* not used in normal case */
+
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+	cpu = rq->cpu;
+#endif
+	__update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable,
+				     runnable, cpu);
 	__update_tg_runnable_avg(&rq->avg, &rq->cfs);
+	trace_sched_rq_runnable_ratio(cpu_of(rq), rq->avg.load_avg_ratio);
+	trace_sched_rq_runnable_load(cpu_of(rq), rq->cfs.runnable_load_avg);
+	trace_sched_rq_nr_running(cpu_of(rq), rq->nr_running, rq->nr_iowait.counter);
 }
 #else /* CONFIG_FAIR_GROUP_SCHED */
 static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq,
@@ -2504,12 +2681,18 @@ static inline void __update_task_entity_contrib(struct sched_entity *se)
 	contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight);
 	contrib /= (se->avg.runnable_avg_period + 1);
 	se->avg.load_avg_contrib = scale_load(contrib);
+	trace_sched_task_load_contrib(task_of(se), se->avg.load_avg_contrib);
+	contrib = se->avg.runnable_avg_sum * scale_load_down(NICE_0_LOAD);
+	contrib /= (se->avg.runnable_avg_period + 1);
+	se->avg.load_avg_ratio = scale_load(contrib);
+	trace_sched_task_runnable_ratio(task_of(se), se->avg.load_avg_ratio);
 }
 
 /* Compute the current contribution to load_avg by se, return any delta */
-static long __update_entity_load_avg_contrib(struct sched_entity *se)
+static long __update_entity_load_avg_contrib(struct sched_entity *se, long *ratio)
 {
 	long old_contrib = se->avg.load_avg_contrib;
+	long old_ratio   = se->avg.load_avg_ratio;
 
 	if (entity_is_task(se)) {
 		__update_task_entity_contrib(se);
@@ -2518,6 +2701,8 @@ static long __update_entity_load_avg_contrib(struct sched_entity *se)
 		__update_group_entity_contrib(se);
 	}
 
+	if (ratio)
+		*ratio = se->avg.load_avg_ratio - old_ratio;
 	return se->avg.load_avg_contrib - old_contrib;
 }
 
@@ -2537,9 +2722,13 @@ static inline void update_entity_load_avg(struct sched_entity *se,
 					  int update_cfs_rq)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
-	long contrib_delta;
+	long contrib_delta, ratio_delta;
 	u64 now;
+	int cpu = -1;   /* not used in normal case */
 
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+	cpu = cfs_rq->rq->cpu;
+#endif
 	/*
 	 * For a group entity we need to use their owned cfs_rq_clock_task() in
 	 * case they are the parent of a throttled hierarchy.
@@ -2549,18 +2738,23 @@ static inline void update_entity_load_avg(struct sched_entity *se,
 	else
 		now = cfs_rq_clock_task(group_cfs_rq(se));
 
-	if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq))
+	if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq,
+			cfs_rq->curr == se, cpu))
 		return;
 
-	contrib_delta = __update_entity_load_avg_contrib(se);
+	contrib_delta = __update_entity_load_avg_contrib(se, &ratio_delta);
 
 	if (!update_cfs_rq)
 		return;
 
-	if (se->on_rq)
+	if (se->on_rq) {
 		cfs_rq->runnable_load_avg += contrib_delta;
-	else
+#ifdef CONFIG_SCHED_HMP
+		rq_of(cfs_rq)->avg.load_avg_ratio += ratio_delta;
+#endif /* CONFIG_SCHED_HMP */
+	} else {
 		subtract_blocked_load_contrib(cfs_rq, -contrib_delta);
+	}
 }
 
 /*
@@ -2635,6 +2829,10 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
 	}
 
 	cfs_rq->runnable_load_avg += se->avg.load_avg_contrib;
+#ifdef CONFIG_SCHED_HMP
+	rq_of(cfs_rq)->avg.load_avg_ratio += se->avg.load_avg_ratio;
+#endif /* CONFIG_SCHED_HMP */
+
 	/* we force update consideration on load-balancer moves */
 	update_cfs_rq_blocked_load(cfs_rq, !wakeup);
 }
@@ -2653,6 +2851,10 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
 	update_cfs_rq_blocked_load(cfs_rq, !sleep);
 
 	cfs_rq->runnable_load_avg -= se->avg.load_avg_contrib;
+#ifdef CONFIG_SCHED_HMP
+	rq_of(cfs_rq)->avg.load_avg_ratio -= se->avg.load_avg_ratio;
+#endif /* CONFIG_SCHED_HMP */
+
 	if (sleep) {
 		cfs_rq->blocked_load_avg += se->avg.load_avg_contrib;
 		se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
@@ -2990,6 +3192,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		 */
 		update_stats_wait_end(cfs_rq, se);
 		__dequeue_entity(cfs_rq, se);
+		update_entity_load_avg(se, 1);
 	}
 
 	update_stats_curr_start(cfs_rq, se);
@@ -4526,6 +4729,844 @@ done:
 	return target;
 }
 
+#ifdef CONFIG_SCHED_HMP
+/*
+ * Heterogenous multiprocessor (HMP) optimizations
+ *
+ * The cpu types are distinguished using a list of hmp_domains
+ * which each represent one cpu type using a cpumask.
+ * The list is assumed ordered by compute capacity with the
+ * fastest domain first.
+ */
+DEFINE_PER_CPU(struct hmp_domain *, hmp_cpu_domain);
+static const int hmp_max_tasks = 5;
+
+extern void __init arch_get_hmp_domains(struct list_head *hmp_domains_list);
+
+#ifdef CONFIG_CPU_IDLE
+/*
+ * hmp_idle_pull:
+ *
+ * In this version we have stopped using forced up migrations when we
+ * detect that a task running on a little CPU should be moved to a bigger
+ * CPU. In most cases, the bigger CPU is in a deep sleep state and a forced
+ * migration means we stop the task immediately but need to wait for the
+ * target CPU to wake up before we can restart the task which is being
+ * moved. Instead, we now wake a big CPU with an IPI and ask it to pull
+ * a task when ready. This allows the task to continue executing on its
+ * current CPU, reducing the amount of time that the task is stalled for.
+ *
+ * keepalive timers:
+ *
+ * The keepalive timer is used as a way to keep a CPU engaged in an
+ * idle pull operation out of idle while waiting for the source
+ * CPU to stop and move the task. Ideally this would not be necessary
+ * and we could impose a temporary zero-latency requirement on the
+ * current CPU, but in the current QoS framework this will result in
+ * all CPUs in the system being unable to enter idle states which is
+ * not desirable. The timer does not perform any work when it expires.
+ */
+struct hmp_keepalive {
+	bool init;
+	ktime_t delay;	/* if zero, no need for timer */
+	struct hrtimer timer;
+};
+DEFINE_PER_CPU(struct hmp_keepalive, hmp_cpu_keepalive);
+
+/* setup per-cpu keepalive timers */
+static enum hrtimer_restart hmp_cpu_keepalive_notify(struct hrtimer *hrtimer)
+{
+	return HRTIMER_NORESTART;
+}
+
+/*
+ * Work out if any of the idle states have an exit latency too high for us.
+ * ns_delay is passed in containing the max we are willing to tolerate.
+ * If there are none, set ns_delay to zero.
+ * If there are any, set ns_delay to
+ * ('target_residency of state with shortest too-big latency' - 1) * 1000.
+ */
+static void hmp_keepalive_delay(int cpu, unsigned int *ns_delay)
+{
+	struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
+	struct cpuidle_driver *drv;
+
+	drv = cpuidle_get_cpu_driver(dev);
+	if (drv) {
+		unsigned int us_delay = UINT_MAX;
+		unsigned int us_max_delay = *ns_delay / 1000;
+		int idx;
+		/* if cpuidle states are guaranteed to be sorted we
+		 * could stop at the first match.
+		 */
+		for (idx = 0; idx < drv->state_count; idx++) {
+			if (drv->states[idx].exit_latency > us_max_delay &&
+				drv->states[idx].target_residency < us_delay) {
+				us_delay = drv->states[idx].target_residency;
+			}
+		}
+		if (us_delay == UINT_MAX)
+			*ns_delay = 0; /* no timer required */
+		else
+			*ns_delay = 1000 * (us_delay - 1);
+	}
+}
+
+static void hmp_cpu_keepalive_trigger(void)
+{
+	int cpu = smp_processor_id();
+	struct hmp_keepalive *keepalive = &per_cpu(hmp_cpu_keepalive, cpu);
+	if (!keepalive->init) {
+		unsigned int ns_delay = 100000; /* tolerate 100usec delay */
+
+		hrtimer_init(&keepalive->timer,
+				CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
+		keepalive->timer.function = hmp_cpu_keepalive_notify;
+
+		hmp_keepalive_delay(cpu, &ns_delay);
+		keepalive->delay = ns_to_ktime(ns_delay);
+		keepalive->init = true;
+	}
+	if (ktime_to_ns(keepalive->delay))
+		__hrtimer_start_range_ns(&keepalive->timer,
+			keepalive->delay, 0, HRTIMER_MODE_REL_PINNED, 0);
+}
+
+static void hmp_cpu_keepalive_cancel(int cpu)
+{
+	struct hmp_keepalive *keepalive = &per_cpu(hmp_cpu_keepalive, cpu);
+	if (keepalive->init)
+		hrtimer_cancel(&keepalive->timer);
+}
+#else /* !CONFIG_CPU_IDLE */
+static void hmp_cpu_keepalive_trigger(void)
+{
+}
+
+static void hmp_cpu_keepalive_cancel(int cpu)
+{
+}
+#endif
+
+/* Setup hmp_domains */
+static int __init hmp_cpu_mask_setup(void)
+{
+	char buf[64];
+	struct hmp_domain *domain;
+	struct list_head *pos;
+	int dc, cpu;
+
+	pr_debug("Initializing HMP scheduler:\n");
+
+	/* Initialize hmp_domains using platform code */
+	arch_get_hmp_domains(&hmp_domains);
+	if (list_empty(&hmp_domains)) {
+		pr_debug("HMP domain list is empty!\n");
+		return 0;
+	}
+
+	/* Print hmp_domains */
+	dc = 0;
+	list_for_each(pos, &hmp_domains) {
+		domain = list_entry(pos, struct hmp_domain, hmp_domains);
+		cpulist_scnprintf(buf, 64, &domain->possible_cpus);
+		pr_debug("  HMP domain %d: %s\n", dc, buf);
+
+		for_each_cpu_mask(cpu, domain->possible_cpus) {
+			per_cpu(hmp_cpu_domain, cpu) = domain;
+		}
+		dc++;
+	}
+
+	return 1;
+}
+
+static struct hmp_domain *hmp_get_hmp_domain_for_cpu(int cpu)
+{
+	struct hmp_domain *domain;
+	struct list_head *pos;
+
+	list_for_each(pos, &hmp_domains) {
+		domain = list_entry(pos, struct hmp_domain, hmp_domains);
+		if(cpumask_test_cpu(cpu, &domain->possible_cpus))
+			return domain;
+	}
+	return NULL;
+}
+
+static void hmp_online_cpu(int cpu)
+{
+	struct hmp_domain *domain = hmp_get_hmp_domain_for_cpu(cpu);
+
+	if(domain)
+		cpumask_set_cpu(cpu, &domain->cpus);
+}
+
+static void hmp_offline_cpu(int cpu)
+{
+	struct hmp_domain *domain = hmp_get_hmp_domain_for_cpu(cpu);
+
+	if(domain)
+		cpumask_clear_cpu(cpu, &domain->cpus);
+
+	hmp_cpu_keepalive_cancel(cpu);
+}
+
+/*
+ * Needed to determine heaviest tasks etc.
+ */
+static inline unsigned int hmp_cpu_is_fastest(int cpu);
+static inline unsigned int hmp_cpu_is_slowest(int cpu);
+static inline struct hmp_domain *hmp_slower_domain(int cpu);
+static inline struct hmp_domain *hmp_faster_domain(int cpu);
+
+/* must hold runqueue lock for queue se is currently on */
+static struct sched_entity *hmp_get_heaviest_task(
+				struct sched_entity *se, int target_cpu)
+{
+	int num_tasks = hmp_max_tasks;
+	struct sched_entity *max_se = se;
+	unsigned long int max_ratio = se->avg.load_avg_ratio;
+	const struct cpumask *hmp_target_mask = NULL;
+	struct hmp_domain *hmp;
+
+	if (hmp_cpu_is_fastest(cpu_of(se->cfs_rq->rq)))
+		return max_se;
+
+	hmp = hmp_faster_domain(cpu_of(se->cfs_rq->rq));
+	hmp_target_mask = &hmp->cpus;
+	if (target_cpu >= 0) {
+		/* idle_balance gets run on a CPU while
+		 * it is in the middle of being hotplugged
+		 * out. Bail early in that case.
+		 */
+		if(!cpumask_test_cpu(target_cpu, hmp_target_mask))
+			return NULL;
+		hmp_target_mask = cpumask_of(target_cpu);
+	}
+	/* The currently running task is not on the runqueue */
+	se = __pick_first_entity(cfs_rq_of(se));
+
+	while (num_tasks && se) {
+		if (entity_is_task(se) &&
+			se->avg.load_avg_ratio > max_ratio &&
+			cpumask_intersects(hmp_target_mask,
+				tsk_cpus_allowed(task_of(se)))) {
+			max_se = se;
+			max_ratio = se->avg.load_avg_ratio;
+		}
+		se = __pick_next_entity(se);
+		num_tasks--;
+	}
+	return max_se;
+}
+
+static struct sched_entity *hmp_get_lightest_task(
+				struct sched_entity *se, int migrate_down)
+{
+	int num_tasks = hmp_max_tasks;
+	struct sched_entity *min_se = se;
+	unsigned long int min_ratio = se->avg.load_avg_ratio;
+	const struct cpumask *hmp_target_mask = NULL;
+
+	if (migrate_down) {
+		struct hmp_domain *hmp;
+		if (hmp_cpu_is_slowest(cpu_of(se->cfs_rq->rq)))
+			return min_se;
+		hmp = hmp_slower_domain(cpu_of(se->cfs_rq->rq));
+		hmp_target_mask = &hmp->cpus;
+	}
+	/* The currently running task is not on the runqueue */
+	se = __pick_first_entity(cfs_rq_of(se));
+
+	while (num_tasks && se) {
+		if (entity_is_task(se) &&
+			(se->avg.load_avg_ratio < min_ratio &&
+			hmp_target_mask &&
+				cpumask_intersects(hmp_target_mask,
+				tsk_cpus_allowed(task_of(se))))) {
+			min_se = se;
+			min_ratio = se->avg.load_avg_ratio;
+		}
+		se = __pick_next_entity(se);
+		num_tasks--;
+	}
+	return min_se;
+}
+
+/*
+ * Migration thresholds should be in the range [0..1023]
+ * hmp_up_threshold: min. load required for migrating tasks to a faster cpu
+ * hmp_down_threshold: max. load allowed for tasks migrating to a slower cpu
+ *
+ * hmp_up_prio: Only up migrate task with high priority (<hmp_up_prio)
+ * hmp_next_up_threshold: Delay before next up migration (1024 ~= 1 ms)
+ * hmp_next_down_threshold: Delay before next down migration (1024 ~= 1 ms)
+ *
+ * Small Task Packing:
+ * We can choose to fill the littlest CPUs in an HMP system rather than
+ * the typical spreading mechanic. This behavior is controllable using
+ * two variables.
+ * hmp_packing_enabled: runtime control over pack/spread
+ * hmp_full_threshold: Consider a CPU with this much unweighted load full
+ */
+unsigned int hmp_up_threshold = 700;
+unsigned int hmp_down_threshold = 512;
+#ifdef CONFIG_SCHED_HMP_PRIO_FILTER
+unsigned int hmp_up_prio = NICE_TO_PRIO(CONFIG_SCHED_HMP_PRIO_FILTER_VAL);
+#endif
+unsigned int hmp_next_up_threshold = 4096;
+unsigned int hmp_next_down_threshold = 4096;
+
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+/*
+ * Set the default packing threshold to try to keep little
+ * CPUs at no more than 80% of their maximum frequency if only
+ * packing a small number of small tasks. Bigger tasks will
+ * raise frequency as normal.
+ * In order to pack a task onto a CPU, the sum of the
+ * unweighted runnable_avg load of existing tasks plus the
+ * load of the new task must be less than hmp_full_threshold.
+ *
+ * This works in conjunction with frequency-invariant load
+ * and DVFS governors. Since most DVFS governors aim for 80%
+ * utilisation, we arrive at (0.8*0.8*(max_load=1024))=655
+ * and use a value slightly lower to give a little headroom
+ * in the decision.
+ * Note that the most efficient frequency is different for
+ * each system so /sys/kernel/hmp/packing_limit should be
+ * configured at runtime for any given platform to achieve
+ * optimal energy usage. Some systems may not benefit from
+ * packing, so this feature can also be disabled at runtime
+ * with /sys/kernel/hmp/packing_enable
+ */
+unsigned int hmp_packing_enabled = 1;
+unsigned int hmp_full_threshold = 650;
+#endif
+
+static unsigned int hmp_up_migration(int cpu, int *target_cpu, struct sched_entity *se);
+static unsigned int hmp_down_migration(int cpu, struct sched_entity *se);
+static inline unsigned int hmp_domain_min_load(struct hmp_domain *hmpd,
+						int *min_cpu, struct cpumask *affinity);
+
+static inline struct hmp_domain *hmp_smallest_domain(void)
+{
+	return list_entry(hmp_domains.prev, struct hmp_domain, hmp_domains);
+}
+
+/* Check if cpu is in fastest hmp_domain */
+static inline unsigned int hmp_cpu_is_fastest(int cpu)
+{
+	struct list_head *pos;
+
+	pos = &hmp_cpu_domain(cpu)->hmp_domains;
+	return pos == hmp_domains.next;
+}
+
+/* Check if cpu is in slowest hmp_domain */
+static inline unsigned int hmp_cpu_is_slowest(int cpu)
+{
+	struct list_head *pos;
+
+	pos = &hmp_cpu_domain(cpu)->hmp_domains;
+	return list_is_last(pos, &hmp_domains);
+}
+
+/* Next (slower) hmp_domain relative to cpu */
+static inline struct hmp_domain *hmp_slower_domain(int cpu)
+{
+	struct list_head *pos;
+
+	pos = &hmp_cpu_domain(cpu)->hmp_domains;
+	return list_entry(pos->next, struct hmp_domain, hmp_domains);
+}
+
+/* Previous (faster) hmp_domain relative to cpu */
+static inline struct hmp_domain *hmp_faster_domain(int cpu)
+{
+	struct list_head *pos;
+
+	pos = &hmp_cpu_domain(cpu)->hmp_domains;
+	return list_entry(pos->prev, struct hmp_domain, hmp_domains);
+}
+
+/*
+ * Selects a cpu in previous (faster) hmp_domain
+ */
+static inline unsigned int hmp_select_faster_cpu(struct task_struct *tsk,
+							int cpu)
+{
+	int lowest_cpu=NR_CPUS;
+	__always_unused int lowest_ratio;
+	struct hmp_domain *hmp;
+
+	if (hmp_cpu_is_fastest(cpu))
+		hmp = hmp_cpu_domain(cpu);
+	else
+		hmp = hmp_faster_domain(cpu);
+
+	lowest_ratio = hmp_domain_min_load(hmp, &lowest_cpu,
+			tsk_cpus_allowed(tsk));
+
+	return lowest_cpu;
+}
+
+/*
+ * Selects a cpu in next (slower) hmp_domain
+ * Note that cpumask_any_and() returns the first cpu in the cpumask
+ */
+static inline unsigned int hmp_select_slower_cpu(struct task_struct *tsk,
+							int cpu)
+{
+	int lowest_cpu=NR_CPUS;
+	struct hmp_domain *hmp;
+	__always_unused int lowest_ratio;
+
+	if (hmp_cpu_is_slowest(cpu))
+		hmp = hmp_cpu_domain(cpu);
+	else
+		hmp = hmp_slower_domain(cpu);
+
+	lowest_ratio = hmp_domain_min_load(hmp, &lowest_cpu,
+			tsk_cpus_allowed(tsk));
+
+	return lowest_cpu;
+}
+
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+/*
+ * Select the 'best' candidate little CPU to wake up on.
+ * Implements a packing strategy which examines CPU in
+ * logical CPU order, and selects the first which will
+ * be loaded less than hmp_full_threshold according to
+ * the sum of the tracked load of the runqueue and the task.
+ */
+static inline unsigned int hmp_best_little_cpu(struct task_struct *tsk,
+		int cpu) {
+	int tmp_cpu;
+	unsigned long estimated_load;
+	struct hmp_domain *hmp;
+	struct sched_avg *avg;
+	struct cpumask allowed_hmp_cpus;
+
+	if(!hmp_packing_enabled ||
+			tsk->se.avg.load_avg_ratio > ((NICE_0_LOAD * 90)/100))
+		return hmp_select_slower_cpu(tsk, cpu);
+
+	if (hmp_cpu_is_slowest(cpu))
+		hmp = hmp_cpu_domain(cpu);
+	else
+		hmp = hmp_slower_domain(cpu);
+
+	/* respect affinity */
+	cpumask_and(&allowed_hmp_cpus, &hmp->cpus,
+			tsk_cpus_allowed(tsk));
+
+	for_each_cpu_mask(tmp_cpu, allowed_hmp_cpus) {
+		avg = &cpu_rq(tmp_cpu)->avg;
+		/* estimate new rq load if we add this task */
+		estimated_load = avg->load_avg_ratio +
+				tsk->se.avg.load_avg_ratio;
+		if (estimated_load <= hmp_full_threshold) {
+			cpu = tmp_cpu;
+			break;
+		}
+	}
+	/* if no match was found, the task uses the initial value */
+	return cpu;
+}
+#endif
+
+static inline void hmp_next_up_delay(struct sched_entity *se, int cpu)
+{
+	/* hack - always use clock from first online CPU */
+	u64 now = cpu_rq(cpumask_first(cpu_online_mask))->clock_task;
+	se->avg.hmp_last_up_migration = now;
+	se->avg.hmp_last_down_migration = 0;
+	cpu_rq(cpu)->avg.hmp_last_up_migration = now;
+	cpu_rq(cpu)->avg.hmp_last_down_migration = 0;
+}
+
+static inline void hmp_next_down_delay(struct sched_entity *se, int cpu)
+{
+	/* hack - always use clock from first online CPU */
+	u64 now = cpu_rq(cpumask_first(cpu_online_mask))->clock_task;
+	se->avg.hmp_last_down_migration = now;
+	se->avg.hmp_last_up_migration = 0;
+	cpu_rq(cpu)->avg.hmp_last_down_migration = now;
+	cpu_rq(cpu)->avg.hmp_last_up_migration = 0;
+}
+
+/*
+ * Heterogenous multiprocessor (HMP) optimizations
+ *
+ * These functions allow to change the growing speed of the load_avg_ratio
+ * by default it goes from 0 to 0.5 in LOAD_AVG_PERIOD = 32ms
+ * This can now be changed with /sys/kernel/hmp/load_avg_period_ms.
+ *
+ * These functions also allow to change the up and down threshold of HMP
+ * using /sys/kernel/hmp/{up,down}_threshold.
+ * Both must be between 0 and 1023. The threshold that is compared
+ * to the load_avg_ratio is up_threshold/1024 and down_threshold/1024.
+ *
+ * For instance, if load_avg_period = 64 and up_threshold = 512, an idle
+ * task with a load of 0 will reach the threshold after 64ms of busy loop.
+ *
+ * Changing load_avg_periods_ms has the same effect than changing the
+ * default scaling factor Y=1002/1024 in the load_avg_ratio computation to
+ * (1002/1024.0)^(LOAD_AVG_PERIOD/load_avg_period_ms), but the last one
+ * could trigger overflows.
+ * For instance, with Y = 1023/1024 in __update_task_entity_contrib()
+ * "contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight);"
+ * could be overflowed for a weight > 2^12 even is the load_avg_contrib
+ * should still be a 32bits result. This would not happen by multiplicating
+ * delta time by 1/22 and setting load_avg_period_ms = 706.
+ */
+
+/*
+ * By scaling the delta time it end-up increasing or decrease the
+ * growing speed of the per entity load_avg_ratio
+ * The scale factor hmp_data.multiplier is a fixed point
+ * number: (32-HMP_VARIABLE_SCALE_SHIFT).HMP_VARIABLE_SCALE_SHIFT
+ */
+static inline u64 hmp_variable_scale_convert(u64 delta)
+{
+#ifdef CONFIG_HMP_VARIABLE_SCALE
+	u64 high = delta >> 32ULL;
+	u64 low = delta & 0xffffffffULL;
+	low *= hmp_data.multiplier;
+	high *= hmp_data.multiplier;
+	return (low >> HMP_VARIABLE_SCALE_SHIFT)
+			+ (high << (32ULL - HMP_VARIABLE_SCALE_SHIFT));
+#else
+	return delta;
+#endif
+}
+
+static ssize_t hmp_show(struct kobject *kobj,
+				struct attribute *attr, char *buf)
+{
+	struct hmp_global_attr *hmp_attr =
+		container_of(attr, struct hmp_global_attr, attr);
+	int temp;
+
+	if (hmp_attr->to_sysfs_text != NULL)
+		return hmp_attr->to_sysfs_text(buf, PAGE_SIZE);
+
+	temp = *(hmp_attr->value);
+	if (hmp_attr->to_sysfs != NULL)
+		temp = hmp_attr->to_sysfs(temp);
+
+	return (ssize_t)sprintf(buf, "%d\n", temp);
+}
+
+static ssize_t hmp_store(struct kobject *a, struct attribute *attr,
+				const char *buf, size_t count)
+{
+	int temp;
+	ssize_t ret = count;
+	struct hmp_global_attr *hmp_attr =
+		container_of(attr, struct hmp_global_attr, attr);
+	char *str = vmalloc(count + 1);
+	if (str == NULL)
+		return -ENOMEM;
+	memcpy(str, buf, count);
+	str[count] = 0;
+	if (sscanf(str, "%d", &temp) < 1)
+		ret = -EINVAL;
+	else {
+		if (hmp_attr->from_sysfs != NULL)
+			temp = hmp_attr->from_sysfs(temp);
+		if (temp < 0)
+			ret = -EINVAL;
+		else
+			*(hmp_attr->value) = temp;
+	}
+	vfree(str);
+	return ret;
+}
+
+static ssize_t hmp_print_domains(char *outbuf, int outbufsize)
+{
+	char buf[64];
+	const char nospace[] = "%s", space[] = " %s";
+	const char *fmt = nospace;
+	struct hmp_domain *domain;
+	struct list_head *pos;
+	int outpos = 0;
+	list_for_each(pos, &hmp_domains) {
+		domain = list_entry(pos, struct hmp_domain, hmp_domains);
+		if (cpumask_scnprintf(buf, 64, &domain->possible_cpus)) {
+			outpos += sprintf(outbuf+outpos, fmt, buf);
+			fmt = space;
+		}
+	}
+	strcat(outbuf, "\n");
+	return outpos+1;
+}
+
+#ifdef CONFIG_HMP_VARIABLE_SCALE
+static int hmp_period_tofrom_sysfs(int value)
+{
+	return (LOAD_AVG_PERIOD << HMP_VARIABLE_SCALE_SHIFT) / value;
+}
+#endif
+
+/* max value for threshold is 1024 */
+static int hmp_theshold_from_sysfs(int value)
+{
+	if (value > 1024)
+		return -1;
+	return value;
+}
+
+#if defined(CONFIG_SCHED_HMP_LITTLE_PACKING) || \
+		defined(CONFIG_HMP_FREQUENCY_INVARIANT_SCALE)
+/* toggle control is only 0,1 off/on */
+static int hmp_toggle_from_sysfs(int value)
+{
+	if (value < 0 || value > 1)
+		return -1;
+	return value;
+}
+#endif
+
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+/* packing value must be non-negative */
+static int hmp_packing_from_sysfs(int value)
+{
+	if (value < 0)
+		return -1;
+	return value;
+}
+#endif
+
+static void hmp_attr_add(
+	const char *name,
+	int *value,
+	int (*to_sysfs)(int),
+	int (*from_sysfs)(int),
+	ssize_t (*to_sysfs_text)(char *, int),
+	umode_t mode)
+{
+	int i = 0;
+	while (hmp_data.attributes[i] != NULL) {
+		i++;
+		if (i >= HMP_DATA_SYSFS_MAX)
+			return;
+	}
+	if (mode)
+		hmp_data.attr[i].attr.mode = mode;
+	else
+		hmp_data.attr[i].attr.mode = 0644;
+	hmp_data.attr[i].show = hmp_show;
+	hmp_data.attr[i].store = hmp_store;
+	hmp_data.attr[i].attr.name = name;
+	hmp_data.attr[i].value = value;
+	hmp_data.attr[i].to_sysfs = to_sysfs;
+	hmp_data.attr[i].from_sysfs = from_sysfs;
+	hmp_data.attr[i].to_sysfs_text = to_sysfs_text;
+	hmp_data.attributes[i] = &hmp_data.attr[i].attr;
+	hmp_data.attributes[i + 1] = NULL;
+}
+
+static int hmp_attr_init(void)
+{
+	int ret;
+	memset(&hmp_data, 0, sizeof(hmp_data));
+	hmp_attr_add("hmp_domains",
+		NULL,
+		NULL,
+		NULL,
+		hmp_print_domains,
+		0444);
+	hmp_attr_add("up_threshold",
+		&hmp_up_threshold,
+		NULL,
+		hmp_theshold_from_sysfs,
+		NULL,
+		0);
+	hmp_attr_add("down_threshold",
+		&hmp_down_threshold,
+		NULL,
+		hmp_theshold_from_sysfs,
+		NULL,
+		0);
+#ifdef CONFIG_HMP_VARIABLE_SCALE
+	/* by default load_avg_period_ms == LOAD_AVG_PERIOD
+	 * meaning no change
+	 */
+	hmp_data.multiplier = hmp_period_tofrom_sysfs(LOAD_AVG_PERIOD);
+	hmp_attr_add("load_avg_period_ms",
+		&hmp_data.multiplier,
+		hmp_period_tofrom_sysfs,
+		hmp_period_tofrom_sysfs,
+		NULL,
+		0);
+#endif
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+	/* default frequency-invariant scaling ON */
+	hmp_data.freqinvar_load_scale_enabled = 1;
+	hmp_attr_add("frequency_invariant_load_scale",
+		&hmp_data.freqinvar_load_scale_enabled,
+		NULL,
+		hmp_toggle_from_sysfs,
+		NULL,
+		0);
+#endif
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+	hmp_attr_add("packing_enable",
+		&hmp_packing_enabled,
+		NULL,
+		hmp_toggle_from_sysfs,
+		NULL,
+		0);
+	hmp_attr_add("packing_limit",
+		&hmp_full_threshold,
+		NULL,
+		hmp_packing_from_sysfs,
+		NULL,
+		0);
+#endif
+	hmp_data.attr_group.name = "hmp";
+	hmp_data.attr_group.attrs = hmp_data.attributes;
+	ret = sysfs_create_group(kernel_kobj,
+		&hmp_data.attr_group);
+	return 0;
+}
+late_initcall(hmp_attr_init);
+
+/*
+ * return the load of the lowest-loaded CPU in a given HMP domain
+ * min_cpu optionally points to an int to receive the CPU.
+ * affinity optionally points to a cpumask containing the
+ * CPUs to be considered. note:
+ *   + min_cpu = NR_CPUS only if no CPUs are in the set of
+ *     affinity && hmp_domain cpus
+ *   + min_cpu will always otherwise equal one of the CPUs in
+ *     the hmp domain
+ *   + when more than one CPU has the same load, the one which
+ *     is least-recently-disturbed by an HMP migration will be
+ *     selected
+ *   + if all CPUs are equally loaded or idle and the times are
+ *     all the same, the first in the set will be used
+ *   + if affinity is not set, cpu_online_mask is used
+ */
+static inline unsigned int hmp_domain_min_load(struct hmp_domain *hmpd,
+						int *min_cpu, struct cpumask *affinity)
+{
+	int cpu;
+	int min_cpu_runnable_temp = NR_CPUS;
+	u64 min_target_last_migration = ULLONG_MAX;
+	u64 curr_last_migration;
+	unsigned long min_runnable_load = INT_MAX;
+	unsigned long contrib;
+	struct sched_avg *avg;
+	struct cpumask temp_cpumask;
+	/*
+	 * only look at CPUs allowed if specified,
+	 * otherwise look at all online CPUs in the
+	 * right HMP domain
+	 */
+	cpumask_and(&temp_cpumask, &hmpd->cpus, affinity ? affinity : cpu_online_mask);
+
+	for_each_cpu_mask(cpu, temp_cpumask) {
+		avg = &cpu_rq(cpu)->avg;
+		/* used for both up and down migration */
+		curr_last_migration = avg->hmp_last_up_migration ?
+			avg->hmp_last_up_migration : avg->hmp_last_down_migration;
+
+		contrib = avg->load_avg_ratio;
+		/*
+		 * Consider a runqueue completely busy if there is any load
+		 * on it. Definitely not the best for overall fairness, but
+		 * does well in typical Android use cases.
+		 */
+		if (contrib)
+			contrib = 1023;
+
+		if ((contrib < min_runnable_load) ||
+			(contrib == min_runnable_load &&
+			 curr_last_migration < min_target_last_migration)) {
+			/*
+			 * if the load is the same target the CPU with
+			 * the longest time since a migration.
+			 * This is to spread migration load between
+			 * members of a domain more evenly when the
+			 * domain is fully loaded
+			 */
+			min_runnable_load = contrib;
+			min_cpu_runnable_temp = cpu;
+			min_target_last_migration = curr_last_migration;
+		}
+	}
+
+	if (min_cpu)
+		*min_cpu = min_cpu_runnable_temp;
+
+	return min_runnable_load;
+}
+
+/*
+ * Calculate the task starvation
+ * This is the ratio of actually running time vs. runnable time.
+ * If the two are equal the task is getting the cpu time it needs or
+ * it is alone on the cpu and the cpu is fully utilized.
+ */
+static inline unsigned int hmp_task_starvation(struct sched_entity *se)
+{
+	u32 starvation;
+
+	starvation = se->avg.usage_avg_sum * scale_load_down(NICE_0_LOAD);
+	starvation /= (se->avg.runnable_avg_sum + 1);
+
+	return scale_load(starvation);
+}
+
+static inline unsigned int hmp_offload_down(int cpu, struct sched_entity *se)
+{
+	int min_usage;
+	int dest_cpu = NR_CPUS;
+
+	if (hmp_cpu_is_slowest(cpu))
+		return NR_CPUS;
+
+	/* Is there an idle CPU in the current domain */
+	min_usage = hmp_domain_min_load(hmp_cpu_domain(cpu), NULL, NULL);
+	if (min_usage == 0) {
+		trace_sched_hmp_offload_abort(cpu, min_usage, "load");
+		return NR_CPUS;
+	}
+
+	/* Is the task alone on the cpu? */
+	if (cpu_rq(cpu)->cfs.h_nr_running < 2) {
+		trace_sched_hmp_offload_abort(cpu,
+			cpu_rq(cpu)->cfs.h_nr_running, "nr_running");
+		return NR_CPUS;
+	}
+
+	/* Is the task actually starving? */
+	/* >=25% ratio running/runnable = starving */
+	if (hmp_task_starvation(se) > 768) {
+		trace_sched_hmp_offload_abort(cpu, hmp_task_starvation(se),
+			"starvation");
+		return NR_CPUS;
+	}
+
+	/* Does the slower domain have any idle CPUs? */
+	min_usage = hmp_domain_min_load(hmp_slower_domain(cpu), &dest_cpu,
+			tsk_cpus_allowed(task_of(se)));
+
+	if (min_usage == 0) {
+		trace_sched_hmp_offload_succeed(cpu, dest_cpu);
+		return dest_cpu;
+	} else
+		trace_sched_hmp_offload_abort(cpu,min_usage,"slowdomain");
+
+	return NR_CPUS;
+}
+#endif /* CONFIG_SCHED_HMP */
+
 /*
  * select_task_rq_fair: Select target runqueue for the waking task in domains
  * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
@@ -4550,6 +5591,19 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 	if (p->nr_cpus_allowed == 1)
 		return prev_cpu;
 
+#ifdef CONFIG_SCHED_HMP
+	/* always put non-kernel forking tasks on a big domain */
+	if (unlikely(sd_flag & SD_BALANCE_FORK) && hmp_task_should_forkboost(p)) {
+		new_cpu = hmp_select_faster_cpu(p, prev_cpu);
+		if (new_cpu != NR_CPUS) {
+			hmp_next_up_delay(&p->se, new_cpu);
+			return new_cpu;
+		}
+		/* failed to perform HMP fork balance, use normal balance */
+		new_cpu = cpu;
+	}
+#endif
+
 	if (sd_flag & SD_BALANCE_WAKE)
 		want_affine = cpumask_test_cpu(cpu, tsk_cpus_allowed(p));
 
@@ -4617,9 +5671,49 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 unlock:
 	rcu_read_unlock();
 
+#ifdef CONFIG_SCHED_HMP
+	prev_cpu = task_cpu(p);
+
+	if (hmp_up_migration(prev_cpu, &new_cpu, &p->se)) {
+		hmp_next_up_delay(&p->se, new_cpu);
+		trace_sched_hmp_migrate(p, new_cpu, HMP_MIGRATE_WAKEUP);
+		return new_cpu;
+	}
+	if (hmp_down_migration(prev_cpu, &p->se)) {
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+		new_cpu = hmp_best_little_cpu(p, prev_cpu);
+#else
+		new_cpu = hmp_select_slower_cpu(p, prev_cpu);
+#endif
+		/*
+		 * we might have no suitable CPU
+		 * in which case new_cpu == NR_CPUS
+		 */
+		if (new_cpu < NR_CPUS && new_cpu != prev_cpu) {
+			hmp_next_down_delay(&p->se, new_cpu);
+			trace_sched_hmp_migrate(p, new_cpu, HMP_MIGRATE_WAKEUP);
+			return new_cpu;
+		}
+	}
+	/* Make sure that the task stays in its previous hmp domain */
+	if (!cpumask_test_cpu(new_cpu, &hmp_cpu_domain(prev_cpu)->cpus))
+		return prev_cpu;
+#endif
+
 	return new_cpu;
 }
 
+#ifdef CONFIG_SCHED_HMP
+#ifdef CONFIG_NO_HZ_COMMON
+static int nohz_test_cpu(int cpu);
+#else
+static inline int nohz_test_cpu(int cpu)
+{
+	return 0;
+}
+#endif
+#endif
+
 /*
  * Called immediately before a task is migrated to a new cpu; task_cpu(p) and
  * cfs_rq_of(p) references at time of call are still valid and identify the
@@ -4639,6 +5733,27 @@ migrate_task_rq_fair(struct task_struct *p, int next_cpu)
 	 * be negative here since on-rq tasks have decay-count == 0.
 	 */
 	if (se->avg.decay_count) {
+#ifdef CONFIG_SCHED_HMP
+		/*
+		 * If we migrate a sleeping task away from a CPU
+		 * which has the tick stopped, then both the clock_task
+		 * and decay_counter will be out of date for that CPU
+		 * and we will not decay load correctly.
+		 */
+		if (!se->on_rq && nohz_test_cpu(task_cpu(p))) {
+			struct rq *rq = cpu_rq(task_cpu(p));
+			unsigned long flags;
+			/*
+			 * Current CPU cannot be holding rq->lock in this
+			 * circumstance, but another might be. We must hold
+			 * rq->lock before we go poking around in its clocks
+			 */
+			raw_spin_lock_irqsave(&rq->lock, flags);
+			update_rq_clock(rq);
+			update_cfs_rq_blocked_load(cfs_rq, 0);
+			raw_spin_unlock_irqrestore(&rq->lock, flags);
+		}
+#endif /* CONFIG_SCHED_HMP */
 		se->avg.decay_count = -__synchronize_entity_decay(se);
 		atomic_long_add(se->avg.load_avg_contrib,
 						&cfs_rq->removed_load);
@@ -6918,6 +8033,10 @@ update_next_balance(struct sched_domain *sd, int cpu_busy, unsigned long *next_b
 		*next_balance = next;
 }
 
+#ifdef CONFIG_SCHED_HMP
+static unsigned int hmp_idle_pull(int this_cpu);
+#endif
+
 /*
  * idle_balance is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
@@ -6992,7 +8111,10 @@ static int idle_balance(struct rq *this_rq)
 			break;
 	}
 	rcu_read_unlock();
-
+#ifdef CONFIG_SCHED_HMP
+	if (!pulled_task)
+		pulled_task = hmp_idle_pull(this_cpu);
+#endif
 	raw_spin_lock(&this_rq->lock);
 
 	if (curr_cost > this_rq->max_idle_balance_cost)
@@ -7023,24 +8145,128 @@ out:
 	return pulled_task;
 }
 
-/*
- * active_load_balance_cpu_stop is run by cpu stopper. It pushes
- * running tasks off the busiest CPU onto idle CPUs. It requires at
- * least 1 task to be running on each physical CPU where possible, and
- * avoids physical / logical imbalances.
- */
-static int active_load_balance_cpu_stop(void *data)
+static int active_load_balance_fair(void *data)
+{
+	struct rq *busiest_rq = data;
+	int busiest_cpu = cpu_of(busiest_rq);
+	int target_cpu = busiest_rq->push_cpu;
+	struct rq *target_rq = cpu_rq(target_cpu);
+	struct task_struct *tsk = NULL;
+	struct lb_env env = {
+		.dst_cpu	= target_cpu,
+		.dst_rq		= target_rq,
+		.src_cpu	= busiest_rq->cpu,
+		.src_rq		= busiest_rq,
+		.idle		= CPU_IDLE,
+	};
+
+	/* Search for an sd spanning us and the target CPU. */
+	rcu_read_lock();
+	for_each_domain(target_cpu, env.sd)
+		if ((env.sd->flags & SD_LOAD_BALANCE) &&
+			cpumask_test_cpu(busiest_cpu, sched_domain_span(env.sd)))
+				break;
+
+	/* Task could not be migrated between these two CPUs */
+	if (unlikely(env.sd == NULL))
+		goto out_done;
+
+	/* FAIR active balance */
+	schedstat_inc(env.sd, alb_count);
+
+	tsk = detach_one_task(&env);
+	if (tsk)
+		schedstat_inc(env.sd, alb_pushed);
+	else
+		schedstat_inc(env.sd, alb_failed);
+
+out_done:
+
+	rcu_read_unlock();
+
+	busiest_rq->active_balance = 0;
+	raw_spin_unlock(&busiest_rq->lock);
+
+	if (tsk)
+		attach_one_task(target_rq, tsk);
+
+	local_irq_enable();
+
+	return 0;
+}
+
+#ifdef CONFIG_SCHED_HMP
+static int move_specific_task(struct lb_env *env, struct task_struct *pm);
+static int active_load_balance_hmp(void *data)
+{
+	struct rq *busiest_rq = data;
+	int busiest_cpu = cpu_of(busiest_rq);
+	int target_cpu = busiest_rq->push_cpu;
+	struct rq *target_rq = cpu_rq(target_cpu);
+	struct task_struct *tsk = busiest_rq->migrate_task;
+	struct lb_env env = {
+		.dst_cpu        = target_cpu,
+		.dst_rq         = target_rq,
+		.src_cpu        = busiest_rq->cpu,
+		.src_rq         = busiest_rq,
+		.idle           = CPU_IDLE,
+	};
+
+	/* move a task from busiest_rq to target_rq */
+	double_lock_balance(busiest_rq, target_rq);
+
+	/* Search for an sd spanning us and the target CPU. */
+	rcu_read_lock();
+	for_each_domain(target_cpu, env.sd)
+		if (cpumask_test_cpu(busiest_cpu, sched_domain_span(env.sd)))
+				break;
+
+	/* Task could not be migrated between these two CPUs */
+	if (unlikely(env.sd == NULL))
+		goto out_done;
+
+	schedstat_inc(env.sd, alb_count);
+
+	if (move_specific_task(&env, tsk))
+		schedstat_inc(env.sd, alb_pushed);
+	else
+		schedstat_inc(env.sd, alb_failed);
+
+out_done:
+
+	rcu_read_unlock();
+	double_unlock_balance(busiest_rq, target_rq);
+
+	busiest_rq->active_balance = 0;
+	raw_spin_unlock(&busiest_rq->lock);
+
+	/*
+	 * Reset active balance request and release the task
+	 *
+	 * NOTE: The put_task_struct() is done while the runqueue spinlock is
+	 * held, but put_task_struct() can also cause a reschedule causing the
+	 * runqueue lock to be acquired recursively.
+	 * To avoid this race condition, we keep the put_task_struct() outside
+	 * the runqueue spinlock.
+	 */
+	put_task_struct(tsk);
+
+	local_irq_enable();
+
+	return 0;
+}
+#endif
+
+static int __do_active_load_balance_cpu_stop(void *data, bool hmp_active_balance)
 {
 	struct rq *busiest_rq = data;
 	int busiest_cpu = cpu_of(busiest_rq);
 	int target_cpu = busiest_rq->push_cpu;
 	struct rq *target_rq = cpu_rq(target_cpu);
-	struct sched_domain *sd;
-	struct task_struct *p = NULL;
 
 	raw_spin_lock_irq(&busiest_rq->lock);
 
-	/* make sure the requested cpu hasn't gone down in the meantime */
+	/* Make sure the requested cpu hasn't gone down in the meantime */
 	if (unlikely(busiest_cpu != smp_processor_id() ||
 		     !busiest_rq->active_balance))
 		goto out_unlock;
@@ -7056,43 +8282,41 @@ static int active_load_balance_cpu_stop(void *data)
 	 */
 	BUG_ON(busiest_rq == target_rq);
 
-	/* Search for an sd spanning us and the target CPU. */
-	rcu_read_lock();
-	for_each_domain(target_cpu, sd) {
-		if ((sd->flags & SD_LOAD_BALANCE) &&
-		    cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
-				break;
-	}
-
-	if (likely(sd)) {
-		struct lb_env env = {
-			.sd		= sd,
-			.dst_cpu	= target_cpu,
-			.dst_rq		= target_rq,
-			.src_cpu	= busiest_rq->cpu,
-			.src_rq		= busiest_rq,
-			.idle		= CPU_IDLE,
-		};
+#ifdef CONFIG_SCHED_HMP
+	/* HMP active balance (using double locking) */
+	if (hmp_active_balance)
+		return active_load_balance_hmp(data);
+#endif
 
-		schedstat_inc(sd, alb_count);
+	/* FAIR active balance (using attach/detach) */
+	return active_load_balance_fair(data);
 
-		p = detach_one_task(&env);
-		if (p)
-			schedstat_inc(sd, alb_pushed);
-		else
-			schedstat_inc(sd, alb_failed);
-	}
-	rcu_read_unlock();
 out_unlock:
+
 	busiest_rq->active_balance = 0;
+
 	raw_spin_unlock(&busiest_rq->lock);
 
-	if (p)
-		attach_one_task(target_rq, p);
+#ifdef CONFIG_SCHED_HMP
+	if (hmp_active_balance)
+		put_task_struct(busiest_rq->migrate_task);
+#endif
 
 	local_irq_enable();
 
 	return 0;
+
+}
+
+/*
+ * active_load_balance_cpu_stop is run by cpu stopper. It pushes
+ * running tasks off the busiest CPU onto idle CPUs. It requires at
+ * least 1 task to be running on each physical CPU where possible, and
+ * avoids physical / logical imbalances.
+ */
+static int active_load_balance_cpu_stop(void *data)
+{
+	return __do_active_load_balance_cpu_stop(data, false);
 }
 
 static inline int on_null_domain(struct rq *rq)
@@ -7113,12 +8337,79 @@ static struct {
 	unsigned long next_balance;     /* in jiffy units */
 } nohz ____cacheline_aligned;
 
-static inline int find_new_ilb(void)
+#ifdef CONFIG_SCHED_HMP
+static int nohz_test_cpu(int cpu)
+{
+	return cpumask_test_cpu(cpu, nohz.idle_cpus_mask);
+}
+#endif
+
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+/*
+ * Decide if the tasks on the busy CPUs in the littlest domain would benefit
+ * from an idle balance
+ *
+ * When packing is enabled, only enforce this behaviour when we are not in the
+ * smallest domain - there we idle balance whenever a CPU is over the
+ * up_threshold regardless of tasks in case one needs to be moved.
+ */
+static int hmp_packing_ilb_needed(int cpu, int ilb_needed)
+{
+	struct hmp_domain *hmp;
+	/* allow previous decision on non-slowest domain */
+	if (!hmp_cpu_is_slowest(cpu))
+		return ilb_needed;
+
+	/* if disabled, use normal ILB behaviour */
+	if (!hmp_packing_enabled)
+		return ilb_needed;
+
+	hmp = hmp_cpu_domain(cpu);
+	for_each_cpu_and(cpu, &hmp->cpus, nohz.idle_cpus_mask) {
+		/* only idle balance if a CPU is loaded over threshold */
+		if (cpu_rq(cpu)->avg.load_avg_ratio > hmp_full_threshold)
+			return 1;
+	}
+	return 0;
+}
+#endif
+
+DEFINE_PER_CPU(cpumask_var_t, ilb_tmpmask);
+
+static inline int find_new_ilb(int call_cpu)
 {
 	int ilb = cpumask_first(nohz.idle_cpus_mask);
+#ifdef CONFIG_SCHED_HMP
+	int ilb_needed = 0;
+	int cpu;
+	struct cpumask* tmp = per_cpu(ilb_tmpmask, smp_processor_id());
+
+	/* restrict nohz balancing to occur in the same hmp domain */
+	ilb = cpumask_first_and(nohz.idle_cpus_mask,
+			&((struct hmp_domain *)hmp_cpu_domain(call_cpu))->cpus);
+
+	/* check to see if it's necessary within this domain */
+	cpumask_andnot(tmp,
+			&((struct hmp_domain *)hmp_cpu_domain(call_cpu))->cpus,
+			nohz.idle_cpus_mask);
+	for_each_cpu(cpu, tmp) {
+		if (cpu_rq(cpu)->nr_running > 1) {
+			ilb_needed = 1;
+			break;
+		}
+	}
 
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+	if (ilb < nr_cpu_ids)
+		ilb_needed = hmp_packing_ilb_needed(ilb, ilb_needed);
+#endif
+
+	if (ilb_needed && ilb < nr_cpu_ids && idle_cpu(ilb))
+		return ilb;
+#else
 	if (ilb < nr_cpu_ids && idle_cpu(ilb))
 		return ilb;
+#endif
 
 	return nr_cpu_ids;
 }
@@ -7128,13 +8419,13 @@ static inline int find_new_ilb(void)
  * nohz_load_balancer CPU (if there is one) otherwise fallback to any idle
  * CPU (if there is one).
  */
-static void nohz_balancer_kick(void)
+static void nohz_balancer_kick(int cpu)
 {
 	int ilb_cpu;
 
 	nohz.next_balance++;
 
-	ilb_cpu = find_new_ilb();
+	ilb_cpu = find_new_ilb(cpu);
 
 	if (ilb_cpu >= nr_cpu_ids)
 		return;
@@ -7429,6 +8720,18 @@ static inline int nohz_kick_needed(struct rq *rq)
 	if (time_before(now, nohz.next_balance))
 		return 0;
 
+#ifdef CONFIG_SCHED_HMP
+	/*
+	 * Bail out if there are no nohz CPUs in our
+	 * HMP domain, since we will move tasks between
+	 * domains through wakeup and force balancing
+	 * as necessary based upon task load.
+	 */
+	if (cpumask_first_and(nohz.idle_cpus_mask,
+			&((struct hmp_domain *)hmp_cpu_domain(cpu))->cpus) >= nr_cpu_ids)
+		return 0;
+#endif
+
 	if (rq->nr_running >= 2)
 		goto need_kick;
 
@@ -7461,6 +8764,456 @@ need_kick:
 static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { }
 #endif
 
+#ifdef CONFIG_SCHED_HMP
+static unsigned int hmp_task_eligible_for_up_migration(struct sched_entity *se)
+{
+	/* below hmp_up_threshold, never eligible */
+	if (se->avg.load_avg_ratio < hmp_up_threshold)
+		return 0;
+	return 1;
+}
+
+/* Check if task should migrate to a faster cpu */
+static unsigned int hmp_up_migration(int cpu, int *target_cpu, struct sched_entity *se)
+{
+	struct task_struct *p = task_of(se);
+	int temp_target_cpu;
+	u64 now;
+
+	if (hmp_cpu_is_fastest(cpu))
+		return 0;
+
+#ifdef CONFIG_SCHED_HMP_PRIO_FILTER
+	/* Filter by task priority */
+	if (p->prio >= hmp_up_prio)
+		return 0;
+#endif
+	if (!hmp_task_eligible_for_up_migration(se))
+		return 0;
+
+	/* Let the task load settle before doing another up migration */
+	/* hack - always use clock from first online CPU */
+	now = cpu_rq(cpumask_first(cpu_online_mask))->clock_task;
+	if (((now - se->avg.hmp_last_up_migration) >> 10)
+					< hmp_next_up_threshold)
+		return 0;
+
+	/* hmp_domain_min_load only returns 0 for an
+	 * idle CPU or 1023 for any partly-busy one.
+	 * Be explicit about requirement for an idle CPU.
+	 */
+	if (hmp_domain_min_load(hmp_faster_domain(cpu), &temp_target_cpu,
+			tsk_cpus_allowed(p)) == 0 && temp_target_cpu != NR_CPUS) {
+		if(target_cpu)
+			*target_cpu = temp_target_cpu;
+		return 1;
+	}
+	return 0;
+}
+
+/* Check if task should migrate to a slower cpu */
+static unsigned int hmp_down_migration(int cpu, struct sched_entity *se)
+{
+	struct task_struct *p = task_of(se);
+	u64 now;
+
+	if (hmp_cpu_is_slowest(cpu)) {
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+		if(hmp_packing_enabled)
+			return 1;
+		else
+#endif
+		return 0;
+	}
+
+#ifdef CONFIG_SCHED_HMP_PRIO_FILTER
+	/* Filter by task priority */
+	if ((p->prio >= hmp_up_prio) &&
+		cpumask_intersects(&hmp_slower_domain(cpu)->cpus,
+					tsk_cpus_allowed(p))) {
+		return 1;
+	}
+#endif
+
+	/* Let the task load settle before doing another down migration */
+	/* hack - always use clock from first online CPU */
+	now = cpu_rq(cpumask_first(cpu_online_mask))->clock_task;
+	if (((now - se->avg.hmp_last_down_migration) >> 10)
+					< hmp_next_down_threshold)
+		return 0;
+
+	if (cpumask_intersects(&hmp_slower_domain(cpu)->cpus,
+					tsk_cpus_allowed(p))
+		&& se->avg.load_avg_ratio < hmp_down_threshold) {
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * hmp_can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
+ * Ideally this function should be merged with can_migrate_task() to avoid
+ * redundant code.
+ */
+static int hmp_can_migrate_task(struct task_struct *p, struct lb_env *env)
+{
+	int tsk_cache_hot = 0;
+
+	/*
+	 * We do not migrate tasks that are:
+	 * 1) running (obviously), or
+	 * 2) cannot be migrated to this CPU due to cpus_allowed
+	 */
+	if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) {
+		schedstat_inc(p, se.statistics.nr_failed_migrations_affine);
+		return 0;
+	}
+	env->flags &= ~LBF_ALL_PINNED;
+
+	if (task_running(env->src_rq, p)) {
+		schedstat_inc(p, se.statistics.nr_failed_migrations_running);
+		return 0;
+	}
+
+	/*
+	 * Aggressive migration if:
+	 * 1) task is cache cold, or
+	 * 2) too many balance attempts have failed.
+	 */
+
+	tsk_cache_hot = task_hot(p, env);
+	if (!tsk_cache_hot ||
+		env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
+#ifdef CONFIG_SCHEDSTATS
+		if (tsk_cache_hot) {
+			schedstat_inc(env->sd, lb_hot_gained[env->idle]);
+			schedstat_inc(p, se.statistics.nr_forced_migrations);
+		}
+#endif
+		return 1;
+	}
+
+	return 1;
+}
+
+/*
+ * move_task - move a task from one runqueue to another runqueue.
+ * Both runqueues must be locked.
+ */
+static void move_task(struct task_struct *p, struct lb_env *env)
+{
+        deactivate_task(env->src_rq, p, 0);
+        set_task_cpu(p, env->dst_cpu);
+        activate_task(env->dst_rq, p, 0);
+        check_preempt_curr(env->dst_rq, p, 0);
+}
+
+/*
+ * move_specific_task tries to move a specific task.
+ * Returns 1 if successful and 0 otherwise.
+ * Called with both runqueues locked.
+ */
+static int move_specific_task(struct lb_env *env, struct task_struct *pm)
+{
+	struct task_struct *p, *n;
+
+	list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) {
+		if (throttled_lb_pair(task_group(p),
+				env->src_rq->cpu, env->dst_cpu))
+			continue;
+
+		if (!hmp_can_migrate_task(p, env))
+			continue;
+		/* Check if we found the right task */
+		if (p != pm)
+			continue;
+
+		move_task(p, env);
+		/*
+		 * Right now, this is only the third place move_task()
+		 * is called, so we can safely collect move_task()
+		 * stats here rather than inside move_task().
+		 */
+		schedstat_inc(env->sd, lb_gained[env->idle]);
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * hmp_active_task_migration_cpu_stop is run by cpu stopper and used to
+ * migrate a specific task from one runqueue to another.
+ * hmp_force_up_migration uses this to push a currently running task
+ * off a runqueue. hmp_idle_pull uses this to pull a currently
+ * running task to an idle runqueue.
+ * Reuses __do_active_load_balance_cpu_stop to actually do the work.
+ */
+static int hmp_active_task_migration_cpu_stop(void *data)
+{
+	return __do_active_load_balance_cpu_stop(data, true);
+}
+
+/*
+ * Move task in a runnable state to another CPU.
+ *
+ * Tailored on 'active_load_balance_cpu_stop' with slight
+ * modification to locking and pre-transfer checks.  Note
+ * rq->lock must be held before calling.
+ */
+static void hmp_migrate_runnable_task(struct rq *rq)
+{
+	struct sched_domain *sd;
+	int src_cpu = cpu_of(rq);
+	struct rq *src_rq = rq;
+	int dst_cpu = rq->push_cpu;
+	struct rq *dst_rq = cpu_rq(dst_cpu);
+	struct task_struct *p = rq->migrate_task;
+	/*
+	 * One last check to make sure nobody else is playing
+	 * with the source rq.
+	 */
+	if (src_rq->active_balance)
+		goto out;
+
+	if (src_rq->nr_running <= 1)
+		goto out;
+
+	if (task_rq(p) != src_rq)
+		goto out;
+	/*
+	 * Not sure if this applies here but one can never
+	 * be too cautious
+	 */
+	BUG_ON(src_rq == dst_rq);
+
+	double_lock_balance(src_rq, dst_rq);
+
+	rcu_read_lock();
+	for_each_domain(dst_cpu, sd) {
+		if (cpumask_test_cpu(src_cpu, sched_domain_span(sd)))
+			break;
+	}
+
+	if (likely(sd)) {
+		struct lb_env env = {
+			.sd             = sd,
+			.dst_cpu        = dst_cpu,
+			.dst_rq         = dst_rq,
+			.src_cpu        = src_cpu,
+			.src_rq         = src_rq,
+			.idle           = CPU_IDLE,
+		};
+
+		schedstat_inc(sd, alb_count);
+
+		if (move_specific_task(&env, p))
+			schedstat_inc(sd, alb_pushed);
+		else
+			schedstat_inc(sd, alb_failed);
+	}
+
+	rcu_read_unlock();
+	double_unlock_balance(src_rq, dst_rq);
+out:
+	put_task_struct(p);
+}
+
+static DEFINE_SPINLOCK(hmp_force_migration);
+
+/*
+ * hmp_force_up_migration checks runqueues for tasks that need to
+ * be actively migrated to a faster cpu.
+ */
+static void hmp_force_up_migration(int this_cpu)
+{
+	int cpu, target_cpu;
+	struct sched_entity *curr, *orig;
+	struct rq *target;
+	unsigned long flags;
+	unsigned int force, got_target;
+	struct task_struct *p;
+
+	if (!spin_trylock(&hmp_force_migration))
+		return;
+	for_each_online_cpu(cpu) {
+		force = 0;
+		got_target = 0;
+		target = cpu_rq(cpu);
+		raw_spin_lock_irqsave(&target->lock, flags);
+		curr = target->cfs.curr;
+		if (!curr || target->active_balance) {
+			raw_spin_unlock_irqrestore(&target->lock, flags);
+			continue;
+		}
+		if (!entity_is_task(curr)) {
+			struct cfs_rq *cfs_rq;
+
+			cfs_rq = group_cfs_rq(curr);
+			while (cfs_rq) {
+				curr = cfs_rq->curr;
+				cfs_rq = group_cfs_rq(curr);
+			}
+		}
+		orig = curr;
+		curr = hmp_get_heaviest_task(curr, -1);
+		if (!curr) {
+			raw_spin_unlock_irqrestore(&target->lock, flags);
+			continue;
+		}
+		p = task_of(curr);
+		if (hmp_up_migration(cpu, &target_cpu, curr)) {
+			cpu_rq(target_cpu)->wake_for_idle_pull = 1;
+			raw_spin_unlock_irqrestore(&target->lock, flags);
+			spin_unlock(&hmp_force_migration);
+			smp_send_reschedule(target_cpu);
+			return;
+		}
+		if (!got_target) {
+			/*
+			 * For now we just check the currently running task.
+			 * Selecting the lightest task for offloading will
+			 * require extensive book keeping.
+			 */
+			curr = hmp_get_lightest_task(orig, 1);
+			p = task_of(curr);
+			target->push_cpu = hmp_offload_down(cpu, curr);
+			if (target->push_cpu < NR_CPUS) {
+				get_task_struct(p);
+				target->migrate_task = p;
+				got_target = 1;
+				trace_sched_hmp_migrate(p, target->push_cpu, HMP_MIGRATE_OFFLOAD);
+				hmp_next_down_delay(&p->se, target->push_cpu);
+			}
+		}
+		/*
+		 * We have a target with no active_balance.  If the task
+		 * is not currently running move it, otherwise let the
+		 * CPU stopper take care of it.
+		 */
+		if (got_target) {
+			if (!task_running(target, p)) {
+				trace_sched_hmp_migrate_force_running(p, 0);
+				hmp_migrate_runnable_task(target);
+			} else {
+				target->active_balance = 1;
+				force = 1;
+			}
+		}
+
+		raw_spin_unlock_irqrestore(&target->lock, flags);
+
+		if (force)
+			stop_one_cpu_nowait(cpu_of(target),
+				hmp_active_task_migration_cpu_stop,
+				target, &target->active_balance_work);
+	}
+	spin_unlock(&hmp_force_migration);
+}
+
+/*
+ * hmp_idle_pull looks at little domain runqueues to see
+ * if a task should be pulled.
+ *
+ * Reuses hmp_force_migration spinlock.
+ *
+ */
+static unsigned int hmp_idle_pull(int this_cpu)
+{
+	int cpu;
+	struct sched_entity *curr, *orig;
+	struct hmp_domain *hmp_domain = NULL;
+	struct rq *target = NULL, *rq;
+	unsigned long flags, ratio = 0;
+	unsigned int force = 0;
+	struct task_struct *p = NULL;
+
+	if (!hmp_cpu_is_slowest(this_cpu))
+		hmp_domain = hmp_slower_domain(this_cpu);
+	if (!hmp_domain)
+		return 0;
+
+	if (!spin_trylock(&hmp_force_migration))
+		return 0;
+
+	/* first select a task */
+	for_each_cpu(cpu, &hmp_domain->cpus) {
+		rq = cpu_rq(cpu);
+		raw_spin_lock_irqsave(&rq->lock, flags);
+		curr = rq->cfs.curr;
+		if (!curr) {
+			raw_spin_unlock_irqrestore(&rq->lock, flags);
+			continue;
+		}
+		if (!entity_is_task(curr)) {
+			struct cfs_rq *cfs_rq;
+
+			cfs_rq = group_cfs_rq(curr);
+			while (cfs_rq) {
+				curr = cfs_rq->curr;
+				if (!entity_is_task(curr))
+					cfs_rq = group_cfs_rq(curr);
+				else
+					cfs_rq = NULL;
+			}
+		}
+		orig = curr;
+		curr = hmp_get_heaviest_task(curr, this_cpu);
+		/* check if heaviest eligible task on this
+		 * CPU is heavier than previous task
+		 */
+		if (curr && hmp_task_eligible_for_up_migration(curr) &&
+			curr->avg.load_avg_ratio > ratio &&
+			cpumask_test_cpu(this_cpu,
+					tsk_cpus_allowed(task_of(curr)))) {
+			p = task_of(curr);
+			target = rq;
+			ratio = curr->avg.load_avg_ratio;
+		}
+		raw_spin_unlock_irqrestore(&rq->lock, flags);
+	}
+
+	if (!p)
+		goto done;
+
+	/* now we have a candidate */
+	raw_spin_lock_irqsave(&target->lock, flags);
+	if (!target->active_balance && task_rq(p) == target) {
+		get_task_struct(p);
+		target->push_cpu = this_cpu;
+		target->migrate_task = p;
+		trace_sched_hmp_migrate(p, target->push_cpu, HMP_MIGRATE_IDLE_PULL);
+		hmp_next_up_delay(&p->se, target->push_cpu);
+		/*
+		 * if the task isn't running move it right away.
+		 * Otherwise setup the active_balance mechanic and let
+		 * the CPU stopper do its job.
+		 */
+		if (!task_running(target, p)) {
+			trace_sched_hmp_migrate_idle_running(p, 0);
+			hmp_migrate_runnable_task(target);
+		} else {
+			target->active_balance = 1;
+			force = 1;
+		}
+	}
+	raw_spin_unlock_irqrestore(&target->lock, flags);
+
+	if (force) {
+		/* start timer to keep us awake */
+		hmp_cpu_keepalive_trigger();
+		stop_one_cpu_nowait(cpu_of(target),
+			hmp_active_task_migration_cpu_stop,
+			target, &target->active_balance_work);
+	}
+done:
+	spin_unlock(&hmp_force_migration);
+	return force;
+}
+
+#else
+static void hmp_force_up_migration(int this_cpu) { }
+#endif /* CONFIG_SCHED_HMP */
+
 /*
  * run_rebalance_domains is triggered when needed from the scheduler tick.
  * Also triggered for nohz idle balancing (with nohz_balancing_kick set).
@@ -7471,6 +9224,20 @@ static void run_rebalance_domains(struct softirq_action *h)
 	enum cpu_idle_type idle = this_rq->idle_balance ?
 						CPU_IDLE : CPU_NOT_IDLE;
 
+#ifdef CONFIG_SCHED_HMP
+	/* shortcut for hmp idle pull wakeups */
+	if (unlikely(this_rq->wake_for_idle_pull)) {
+		this_rq->wake_for_idle_pull = 0;
+		if (hmp_idle_pull(cpu_of(this_rq))) {
+			/* break out unless running nohz idle as well */
+			if (idle != CPU_IDLE)
+				return;
+		}
+	}
+#endif
+
+	hmp_force_up_migration(cpu_of(this_rq));
+
 	rebalance_domains(this_rq, idle);
 
 	/*
@@ -7494,12 +9261,15 @@ void trigger_load_balance(struct rq *rq)
 		raise_softirq(SCHED_SOFTIRQ);
 #ifdef CONFIG_NO_HZ_COMMON
 	if (nohz_kick_needed(rq))
-		nohz_balancer_kick();
+		nohz_balancer_kick(cpu_of(rq));
 #endif
 }
 
 static void rq_online_fair(struct rq *rq)
 {
+#ifdef CONFIG_SCHED_HMP
+	hmp_online_cpu(rq->cpu);
+#endif
 	update_sysctl();
 
 	update_runtime_enabled(rq);
@@ -7507,6 +9277,9 @@ static void rq_online_fair(struct rq *rq)
 
 static void rq_offline_fair(struct rq *rq)
 {
+#ifdef CONFIG_SCHED_HMP
+	hmp_offline_cpu(rq->cpu);
+#endif
 	update_sysctl();
 
 	/* Ensure any throttled groups are reachable by pick_next_task */
@@ -7990,6 +9763,139 @@ __init void init_sched_fair_class(void)
 	zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
 	cpu_notifier(sched_ilb_notifier, 0);
 #endif
+
+#ifdef CONFIG_SCHED_HMP
+	hmp_cpu_mask_setup();
+#endif
 #endif /* SMP */
 
 }
+
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+static u32 cpufreq_calc_scale(u32 min, u32 max, u32 curr)
+{
+	u32 result = curr / max;
+	return result;
+}
+
+/* Called when the CPU Frequency is changed.
+ * Once for each CPU.
+ */
+static int cpufreq_callback(struct notifier_block *nb,
+					unsigned long val, void *data)
+{
+	struct cpufreq_freqs *freq = data;
+	int cpu = freq->cpu;
+	struct cpufreq_extents *extents;
+
+	if (freq->flags & CPUFREQ_CONST_LOOPS)
+		return NOTIFY_OK;
+
+	if (val != CPUFREQ_POSTCHANGE)
+		return NOTIFY_OK;
+
+	/* if dynamic load scale is disabled, set the load scale to 1.0 */
+	if (!hmp_data.freqinvar_load_scale_enabled) {
+		freq_scale[cpu].curr_scale = 1024;
+		return NOTIFY_OK;
+	}
+
+	extents = &freq_scale[cpu];
+	if (extents->flags & SCHED_LOAD_FREQINVAR_SINGLEFREQ) {
+		/* If our governor was recognised as a single-freq governor,
+		 * use 1.0
+		 */
+		extents->curr_scale = 1024;
+	} else {
+		extents->curr_scale = cpufreq_calc_scale(extents->min,
+				extents->max, freq->new);
+	}
+
+	return NOTIFY_OK;
+}
+
+/* Called when the CPUFreq governor is changed.
+ * Only called for the CPUs which are actually changed by the
+ * userspace.
+ */
+static int cpufreq_policy_callback(struct notifier_block *nb,
+				       unsigned long event, void *data)
+{
+	struct cpufreq_policy *policy = data;
+	struct cpufreq_extents *extents;
+	int cpu, singleFreq = 0;
+	static const char performance_governor[] = "performance";
+	static const char powersave_governor[] = "powersave";
+
+	if (event == CPUFREQ_START)
+		return 0;
+
+	if (event != CPUFREQ_INCOMPATIBLE)
+		return 0;
+
+	/* CPUFreq governors do not accurately report the range of
+	 * CPU Frequencies they will choose from.
+	 * We recognise performance and powersave governors as
+	 * single-frequency only.
+	 */
+	if (!strncmp(policy->governor->name, performance_governor,
+			strlen(performance_governor)) ||
+		!strncmp(policy->governor->name, powersave_governor,
+				strlen(powersave_governor)))
+		singleFreq = 1;
+
+	/* Make sure that all CPUs impacted by this policy are
+	 * updated since we will only get a notification when the
+	 * user explicitly changes the policy on a CPU.
+	 */
+	for_each_cpu(cpu, policy->cpus) {
+		extents = &freq_scale[cpu];
+		extents->max = policy->max >> SCHED_FREQSCALE_SHIFT;
+		extents->min = policy->min >> SCHED_FREQSCALE_SHIFT;
+		if (!hmp_data.freqinvar_load_scale_enabled) {
+			extents->curr_scale = 1024;
+		} else if (singleFreq) {
+			extents->flags |= SCHED_LOAD_FREQINVAR_SINGLEFREQ;
+			extents->curr_scale = 1024;
+		} else {
+			extents->flags &= ~SCHED_LOAD_FREQINVAR_SINGLEFREQ;
+			extents->curr_scale = cpufreq_calc_scale(extents->min,
+					extents->max, policy->cur);
+		}
+	}
+
+	return 0;
+}
+
+static struct notifier_block cpufreq_notifier = {
+	.notifier_call  = cpufreq_callback,
+};
+static struct notifier_block cpufreq_policy_notifier = {
+	.notifier_call  = cpufreq_policy_callback,
+};
+
+static int __init register_sched_cpufreq_notifier(void)
+{
+	int ret = 0;
+
+	/* init safe defaults since there are no policies at registration */
+	for (ret = 0; ret < CONFIG_NR_CPUS; ret++) {
+		/* safe defaults */
+		freq_scale[ret].max = 1024;
+		freq_scale[ret].min = 1024;
+		freq_scale[ret].curr_scale = 1024;
+	}
+
+	pr_info("sched: registering cpufreq notifiers for scale-invariant loads\n");
+	ret = cpufreq_register_notifier(&cpufreq_policy_notifier,
+			CPUFREQ_POLICY_NOTIFIER);
+
+	if (ret != -EINVAL)
+		ret = cpufreq_register_notifier(&cpufreq_notifier,
+			CPUFREQ_TRANSITION_NOTIFIER);
+
+	return ret;
+}
+
+core_initcall(register_sched_cpufreq_notifier);
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 2df8ef067cc..7b34840b827 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -219,6 +219,7 @@ struct task_group {
 #ifdef	CONFIG_SMP
 	atomic_long_t load_avg;
 	atomic_t runnable_avg;
+	atomic_t usage_avg;
 #endif
 #endif
 
@@ -352,6 +353,7 @@ struct cfs_rq {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* Required to track per-cpu representation of a task_group */
 	u32 tg_runnable_contrib;
+	u32 tg_usage_contrib;
 	unsigned long tg_load_contrib;
 
 	/*
@@ -586,6 +588,10 @@ struct rq {
 	int active_balance;
 	int push_cpu;
 	struct cpu_stop_work active_balance_work;
+#ifdef CONFIG_SCHED_HMP
+	struct task_struct *migrate_task;
+	int wake_for_idle_pull;
+#endif
 	/* cpu of this runqueue: */
 	int cpu;
 	int online;
@@ -805,6 +811,12 @@ static inline unsigned int group_first_cpu(struct sched_group *group)
 
 extern int group_balance_cpu(struct sched_group *sg);
 
+#ifdef CONFIG_SCHED_HMP
+static LIST_HEAD(hmp_domains);
+DECLARE_PER_CPU(struct hmp_domain *, hmp_cpu_domain);
+#define hmp_cpu_domain(cpu)	(per_cpu(hmp_cpu_domain, (cpu)))
+#endif /* CONFIG_SCHED_HMP */
+
 #else
 
 static inline void sched_ttwu_pending(void) { }
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 5a62915f47a..4dae1885db6 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -297,6 +297,67 @@ int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *
 }
 EXPORT_SYMBOL(autoremove_wake_function);
 
+
+/*
+ * DEFINE_WAIT_FUNC(wait, woken_wake_func);
+ *
+ * add_wait_queue(&wq, &wait);
+ * for (;;) {
+ *     if (condition)
+ *         break;
+ *
+ *     p->state = mode;				condition = true;
+ *     smp_mb(); // A				smp_wmb(); // C
+ *     if (!wait->flags & WQ_FLAG_WOKEN)	wait->flags |= WQ_FLAG_WOKEN;
+ *         schedule()				try_to_wake_up();
+ *     p->state = TASK_RUNNING;		    ~~~~~~~~~~~~~~~~~~
+ *     wait->flags &= ~WQ_FLAG_WOKEN;		condition = true;
+ *     smp_mb() // B				smp_wmb(); // C
+ *						wait->flags |= WQ_FLAG_WOKEN;
+ * }
+ * remove_wait_queue(&wq, &wait);
+ *
+ */
+long wait_woken(wait_queue_t *wait, unsigned mode, long timeout)
+{
+	set_current_state(mode); /* A */
+	/*
+	 * The above implies an smp_mb(), which matches with the smp_wmb() from
+	 * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must
+	 * also observe all state before the wakeup.
+	 */
+	if (!(wait->flags & WQ_FLAG_WOKEN))
+		timeout = schedule_timeout(timeout);
+	__set_current_state(TASK_RUNNING);
+
+	/*
+	 * The below implies an smp_mb(), it too pairs with the smp_wmb() from
+	 * woken_wake_function() such that we must either observe the wait
+	 * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss
+	 * an event.
+	 */
+	set_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */
+
+	return timeout;
+}
+EXPORT_SYMBOL(wait_woken);
+
+int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
+{
+	/*
+	 * Although this function is called under waitqueue lock, LOCK
+	 * doesn't imply write barrier and the users expects write
+	 * barrier semantics on wakeup functions.  The following
+	 * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
+	 * and is paired with set_mb() in wait_woken().
+	 */
+	smp_wmb(); /* C */
+	wait->flags |= WQ_FLAG_WOKEN;
+
+	return default_wake_function(wait, mode, sync, key);
+}
+EXPORT_SYMBOL(woken_wake_function);
+
 int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *arg)
 {
 	struct wait_bit_key *key = arg;
diff --git a/kernel/smp.c b/kernel/smp.c
index f38a1e69225..ca0789f1755 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -14,6 +14,8 @@
 #include <linux/smp.h>
 #include <linux/cpu.h>
 #include <linux/sched.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/smp.h>
 
 #include "smpboot.h"
 
@@ -152,7 +154,9 @@ static int generic_exec_single(int cpu, struct call_single_data *csd,
 
 	if (cpu == smp_processor_id()) {
 		local_irq_save(flags);
+		trace_smp_call_func_entry(func);
 		func(info);
+		trace_smp_call_func_exit(func);
 		local_irq_restore(flags);
 		return 0;
 	}
@@ -187,8 +191,10 @@ static int generic_exec_single(int cpu, struct call_single_data *csd,
 	 * locking and barrier primitives. Generic code isn't really
 	 * equipped to do the right thing...
 	 */
-	if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
+	if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu))) {
+		trace_smp_call_func_send(csd->func, cpu);
 		arch_send_call_function_single_ipi(cpu);
+	}
 
 	if (wait)
 		csd_lock_wait(csd);
@@ -250,7 +256,9 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
 	}
 
 	llist_for_each_entry_safe(csd, csd_next, entry, llist) {
+		trace_smp_call_func_entry(csd->func);
 		csd->func(csd->info);
+		trace_smp_call_func_exit(csd->func);
 		csd_unlock(csd);
 	}
 
@@ -277,6 +285,7 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 	int this_cpu;
 	int err;
 
+	trace_smp_call_func_send(func, cpu);
 	/*
 	 * prevent preemption and reschedule on another processor,
 	 * as well as CPU removal
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index eb89e180740..60d35ac5d3f 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -279,6 +279,7 @@ int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
 	unsigned int cpu;
 	int ret = 0;
 
+	get_online_cpus();
 	mutex_lock(&smpboot_threads_lock);
 	for_each_online_cpu(cpu) {
 		ret = __smpboot_create_thread(plug_thread, cpu);
@@ -291,6 +292,7 @@ int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
 	list_add(&plug_thread->list, &hotplug_threads);
 out:
 	mutex_unlock(&smpboot_threads_lock);
+	put_online_cpus();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 0699add1916..9e787d8311b 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -656,9 +656,13 @@ static void run_ksoftirqd(unsigned int cpu)
 		 * in the task stack here.
 		 */
 		__do_softirq();
-		rcu_note_context_switch(cpu);
 		local_irq_enable();
 		cond_resched();
+
+		preempt_disable();
+		rcu_note_context_switch(cpu);
+		preempt_enable();
+
 		return;
 	}
 	local_irq_enable();
diff --git a/kernel/sys.c b/kernel/sys.c
index 1eaa2f0b024..38a20992feb 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -41,6 +41,9 @@
 #include <linux/syscore_ops.h>
 #include <linux/version.h>
 #include <linux/ctype.h>
+#include <linux/mm.h>
+#include <linux/mempolicy.h>
+#include <linux/sched.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
@@ -2025,10 +2028,158 @@ static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
 }
 #endif
 
+#ifdef CONFIG_MMU
+static int prctl_update_vma_anon_name(struct vm_area_struct *vma,
+		struct vm_area_struct **prev,
+		unsigned long start, unsigned long end,
+		const char __user *name_addr)
+{
+	struct mm_struct * mm = vma->vm_mm;
+	int error = 0;
+	pgoff_t pgoff;
+
+	if (name_addr == vma_get_anon_name(vma)) {
+		*prev = vma;
+		goto out;
+	}
+
+	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
+	*prev = vma_merge(mm, *prev, start, end, vma->vm_flags, vma->anon_vma,
+				vma->vm_file, pgoff, vma_policy(vma),
+				name_addr);
+	if (*prev) {
+		vma = *prev;
+		goto success;
+	}
+
+	*prev = vma;
+
+	if (start != vma->vm_start) {
+		error = split_vma(mm, vma, start, 1);
+		if (error)
+			goto out;
+	}
+
+	if (end != vma->vm_end) {
+		error = split_vma(mm, vma, end, 0);
+		if (error)
+			goto out;
+	}
+
+success:
+	if (!vma->vm_file)
+		vma->shared.anon_name = name_addr;
+
+out:
+	if (error == -ENOMEM)
+		error = -EAGAIN;
+	return error;
+}
+
+static int prctl_set_vma_anon_name(unsigned long start, unsigned long end,
+			unsigned long arg)
+{
+	unsigned long tmp;
+	struct vm_area_struct * vma, *prev;
+	int unmapped_error = 0;
+	int error = -EINVAL;
+
+	/*
+	 * If the interval [start,end) covers some unmapped address
+	 * ranges, just ignore them, but return -ENOMEM at the end.
+	 * - this matches the handling in madvise.
+	 */
+	vma = find_vma_prev(current->mm, start, &prev);
+	if (vma && start > vma->vm_start)
+		prev = vma;
+
+	for (;;) {
+		/* Still start < end. */
+		error = -ENOMEM;
+		if (!vma)
+			return error;
+
+		/* Here start < (end|vma->vm_end). */
+		if (start < vma->vm_start) {
+			unmapped_error = -ENOMEM;
+			start = vma->vm_start;
+			if (start >= end)
+				return error;
+		}
+
+		/* Here vma->vm_start <= start < (end|vma->vm_end) */
+		tmp = vma->vm_end;
+		if (end < tmp)
+			tmp = end;
+
+		/* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
+		error = prctl_update_vma_anon_name(vma, &prev, start, tmp,
+				(const char __user *)arg);
+		if (error)
+			return error;
+		start = tmp;
+		if (prev && start < prev->vm_end)
+			start = prev->vm_end;
+		error = unmapped_error;
+		if (start >= end)
+			return error;
+		if (prev)
+			vma = prev->vm_next;
+		else	/* madvise_remove dropped mmap_sem */
+			vma = find_vma(current->mm, start);
+	}
+}
+
+static int prctl_set_vma(unsigned long opt, unsigned long start,
+		unsigned long len_in, unsigned long arg)
+{
+	struct mm_struct *mm = current->mm;
+	int error;
+	unsigned long len;
+	unsigned long end;
+
+	if (start & ~PAGE_MASK)
+		return -EINVAL;
+	len = (len_in + ~PAGE_MASK) & PAGE_MASK;
+
+	/* Check to see whether len was rounded up from small -ve to zero */
+	if (len_in && !len)
+		return -EINVAL;
+
+	end = start + len;
+	if (end < start)
+		return -EINVAL;
+
+	if (end == start)
+		return 0;
+
+	down_write(&mm->mmap_sem);
+
+	switch (opt) {
+	case PR_SET_VMA_ANON_NAME:
+		error = prctl_set_vma_anon_name(start, end, arg);
+		break;
+	default:
+		error = -EINVAL;
+	}
+
+	up_write(&mm->mmap_sem);
+
+	return error;
+}
+#else /* CONFIG_MMU */
+static int prctl_set_vma(unsigned long opt, unsigned long start,
+		unsigned long len_in, unsigned long arg)
+{
+	return -EINVAL;
+}
+#endif
+
 SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		unsigned long, arg4, unsigned long, arg5)
 {
 	struct task_struct *me = current;
+	struct task_struct *tsk;
 	unsigned char comm[sizeof(me->comm)];
 	long error;
 
@@ -2171,6 +2322,26 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_GET_TID_ADDRESS:
 		error = prctl_get_tid_address(me, (int __user **)arg2);
 		break;
+	case PR_SET_TIMERSLACK_PID:
+		if (task_pid_vnr(current) != (pid_t)arg3 &&
+				!capable(CAP_SYS_NICE))
+			return -EPERM;
+		rcu_read_lock();
+		tsk = find_task_by_vpid((pid_t)arg3);
+		if (tsk == NULL) {
+			rcu_read_unlock();
+			return -EINVAL;
+		}
+		get_task_struct(tsk);
+		rcu_read_unlock();
+		if (arg2 <= 0)
+			tsk->timer_slack_ns =
+				tsk->default_timer_slack_ns;
+		else
+			tsk->timer_slack_ns = arg2;
+		put_task_struct(tsk);
+		error = 0;
+		break;
 	case PR_SET_CHILD_SUBREAPER:
 		me->signal->is_child_subreaper = !!arg2;
 		break;
@@ -2203,6 +2374,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			me->mm->def_flags &= ~VM_NOHUGEPAGE;
 		up_write(&me->mm->mmap_sem);
 		break;
+	case PR_SET_VMA:
+		error = prctl_set_vma(arg2, arg3, arg4, arg5);
+		break;
 	default:
 		error = -EINVAL;
 		break;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 15f2511a1b7..8479c4567ad 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -104,6 +104,8 @@ extern char core_pattern[];
 extern unsigned int core_pipe_limit;
 #endif
 extern int pid_max;
+extern int extra_free_kbytes;
+extern int min_free_order_shift;
 extern int pid_max_min, pid_max_max;
 extern int percpu_pagelist_fraction;
 extern int compat_log;
@@ -1232,7 +1234,6 @@ static struct ctl_table vm_table[] = {
 		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
 		.proc_handler	= hugetlb_sysctl_handler,
-		.extra1		= &zero,
 	},
 #ifdef CONFIG_NUMA
 	{
@@ -1241,7 +1242,6 @@ static struct ctl_table vm_table[] = {
 		.maxlen         = sizeof(unsigned long),
 		.mode           = 0644,
 		.proc_handler   = &hugetlb_mempolicy_sysctl_handler,
-		.extra1		= &zero,
 	},
 #endif
 	 {
@@ -1264,7 +1264,6 @@ static struct ctl_table vm_table[] = {
 		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
 		.proc_handler	= hugetlb_overcommit_handler,
-		.extra1		= &zero,
 	},
 #endif
 	{
@@ -1311,6 +1310,21 @@ static struct ctl_table vm_table[] = {
 		.extra1		= &zero,
 	},
 	{
+		.procname	= "extra_free_kbytes",
+		.data		= &extra_free_kbytes,
+		.maxlen		= sizeof(extra_free_kbytes),
+		.mode		= 0644,
+		.proc_handler	= min_free_kbytes_sysctl_handler,
+		.extra1		= &zero,
+	},
+	{
+		.procname	= "min_free_order_shift",
+		.data		= &min_free_order_shift,
+		.maxlen		= sizeof(min_free_order_shift),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{
 		.procname	= "percpu_pagelist_fraction",
 		.data		= &percpu_pagelist_fraction,
 		.maxlen		= sizeof(percpu_pagelist_fraction),
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 37e50aadd47..210b8488293 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -122,7 +122,7 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 	mono = ktime_get_update_offsets_tick(&off_real, &off_boot, &off_tai);
 	boot = ktime_add(mono, off_boot);
 	xtim = ktime_add(mono, off_real);
-	tai = ktime_add(xtim, off_tai);
+	tai = ktime_add(mono, off_tai);
 
 	base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
 	base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono;
@@ -266,23 +266,25 @@ lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
 /*
  * Divide a ktime value by a nanosecond value
  */
-u64 ktime_divns(const ktime_t kt, s64 div)
+s64 __ktime_divns(const ktime_t kt, s64 div)
 {
-	u64 dclc;
 	int sft = 0;
+	s64 dclc;
+	u64 tmp;
 
 	dclc = ktime_to_ns(kt);
+	tmp = dclc < 0 ? -dclc : dclc;
+
 	/* Make sure the divisor is less than 2^32: */
 	while (div >> 32) {
 		sft++;
 		div >>= 1;
 	}
-	dclc >>= sft;
-	do_div(dclc, (unsigned long) div);
-
-	return dclc;
+	tmp >>= sft;
+	do_div(tmp, (unsigned long) div);
+	return dclc < 0 ? -tmp : tmp;
 }
-EXPORT_SYMBOL_GPL(ktime_divns);
+EXPORT_SYMBOL_GPL(__ktime_divns);
 #endif /* BITS_PER_LONG >= 64 */
 
 /*
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 87a346fd6d6..85fb3d632bd 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -633,6 +633,17 @@ int ntp_validate_timex(struct timex *txc)
 	if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME)))
 		return -EPERM;
 
+	/*
+	 * Check for potential multiplication overflows that can
+	 * only happen on 64-bit systems:
+	 */
+	if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) {
+		if (LLONG_MIN / PPM_SCALE > txc->freq)
+			return -EINVAL;
+		if (LLONG_MAX / PPM_SCALE < txc->freq)
+			return -EINVAL;
+	}
+
 	return 0;
 }
 
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index eb682d5c697..6aac4beedbb 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -49,6 +49,7 @@ static void bc_set_mode(enum clock_event_mode mode,
  */
 static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
 {
+	int bc_moved;
 	/*
 	 * We try to cancel the timer first. If the callback is on
 	 * flight on some other cpu then we let it handle it. If we
@@ -60,9 +61,15 @@ static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
 	 * restart the timer because we are in the callback, but we
 	 * can set the expiry time and let the callback return
 	 * HRTIMER_RESTART.
+	 *
+	 * Since we are in the idle loop at this point and because
+	 * hrtimer_{start/cancel} functions call into tracing,
+	 * calls to these functions must be bound within RCU_NONIDLE.
 	 */
-	if (hrtimer_try_to_cancel(&bctimer) >= 0) {
-		hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED);
+	RCU_NONIDLE(bc_moved = (hrtimer_try_to_cancel(&bctimer) >= 0) ?
+		!hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED) :
+			0);
+	if (bc_moved) {
 		/* Bind the "device" to the cpu */
 		bc->bound_on = smp_processor_id();
 	} else if (bc->bound_on == smp_processor_id()) {
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 7b5741fc411..8c30ef7a2b7 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -847,7 +847,6 @@ void tick_nohz_idle_enter(void)
 
 	local_irq_enable();
 }
-EXPORT_SYMBOL_GPL(tick_nohz_idle_enter);
 
 /**
  * tick_nohz_irq_exit - update next tick event from interrupt exit
@@ -974,7 +973,6 @@ void tick_nohz_idle_exit(void)
 
 	local_irq_enable();
 }
-EXPORT_SYMBOL_GPL(tick_nohz_idle_exit);
 
 static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now)
 {
diff --git a/kernel/time/time.c b/kernel/time/time.c
index a9ae20fb0b1..22d5d3b7397 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -196,6 +196,10 @@ SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv,
 	if (tv) {
 		if (copy_from_user(&user_tv, tv, sizeof(*tv)))
 			return -EFAULT;
+
+		if (!timeval_valid(&user_tv))
+			return -EINVAL;
+
 		new_ts.tv_sec = user_tv.tv_sec;
 		new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC;
 	}
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index a5da09c899d..37e1fb831d9 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -77,6 +77,9 @@ config EVENT_TRACING
 	select CONTEXT_SWITCH_TRACER
 	bool
 
+config GPU_TRACEPOINTS
+	bool
+
 config CONTEXT_SWITCH_TRACER
 	bool
 
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 67d6369ddf8..5da3cfb1bb8 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -63,6 +63,7 @@ obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
 endif
 obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
 obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o
+obj-$(CONFIG_GPU_TRACEPOINTS) += gpu-traces.o
 
 obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 31c90fec415..d1eff3dd8a0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1053,6 +1053,12 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
 
 static struct pid * const ftrace_swapper_pid = &init_struct_pid;
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int ftrace_graph_active;
+#else
+# define ftrace_graph_active 0
+#endif
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 static struct ftrace_ops *removed_ops;
@@ -1849,8 +1855,12 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update)
 		if (!ftrace_rec_count(rec))
 			rec->flags = 0;
 		else
-			/* Just disable the record (keep REGS state) */
-			rec->flags &= ~FTRACE_FL_ENABLED;
+			/*
+			 * Just disable the record, but keep the ops TRAMP
+			 * and REGS states. The _EN flags must be disabled though.
+			 */
+			rec->flags &= ~(FTRACE_FL_ENABLED | FTRACE_FL_TRAMP_EN |
+					FTRACE_FL_REGS_EN);
 	}
 
 	return FTRACE_UPDATE_MAKE_NOP;
@@ -2308,12 +2318,14 @@ static void ftrace_run_update_code(int command)
 }
 
 static void ftrace_run_modify_code(struct ftrace_ops *ops, int command,
-				   struct ftrace_hash *old_hash)
+				   struct ftrace_ops_hash *old_hash)
 {
 	ops->flags |= FTRACE_OPS_FL_MODIFYING;
-	ops->old_hash.filter_hash = old_hash;
+	ops->old_hash.filter_hash = old_hash->filter_hash;
+	ops->old_hash.notrace_hash = old_hash->notrace_hash;
 	ftrace_run_update_code(command);
 	ops->old_hash.filter_hash = NULL;
+	ops->old_hash.notrace_hash = NULL;
 	ops->flags &= ~FTRACE_OPS_FL_MODIFYING;
 }
 
@@ -2480,24 +2492,36 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 
 static void ftrace_startup_sysctl(void)
 {
+	int command;
+
 	if (unlikely(ftrace_disabled))
 		return;
 
 	/* Force update next time */
 	saved_ftrace_func = NULL;
 	/* ftrace_start_up is true if we want ftrace running */
-	if (ftrace_start_up)
-		ftrace_run_update_code(FTRACE_UPDATE_CALLS);
+	if (ftrace_start_up) {
+		command = FTRACE_UPDATE_CALLS;
+		if (ftrace_graph_active)
+			command |= FTRACE_START_FUNC_RET;
+		ftrace_startup_enable(command);
+	}
 }
 
 static void ftrace_shutdown_sysctl(void)
 {
+	int command;
+
 	if (unlikely(ftrace_disabled))
 		return;
 
 	/* ftrace_start_up is true if ftrace is running */
-	if (ftrace_start_up)
-		ftrace_run_update_code(FTRACE_DISABLE_CALLS);
+	if (ftrace_start_up) {
+		command = FTRACE_DISABLE_CALLS;
+		if (ftrace_graph_active)
+			command |= FTRACE_STOP_FUNC_RET;
+		ftrace_run_update_code(command);
+	}
 }
 
 static cycle_t		ftrace_update_time;
@@ -3357,7 +3381,7 @@ static struct ftrace_ops trace_probe_ops __read_mostly =
 
 static int ftrace_probe_registered;
 
-static void __enable_ftrace_function_probe(struct ftrace_hash *old_hash)
+static void __enable_ftrace_function_probe(struct ftrace_ops_hash *old_hash)
 {
 	int ret;
 	int i;
@@ -3415,6 +3439,7 @@ int
 register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 			      void *data)
 {
+	struct ftrace_ops_hash old_hash_ops;
 	struct ftrace_func_probe *entry;
 	struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash;
 	struct ftrace_hash *old_hash = *orig_hash;
@@ -3436,6 +3461,10 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 
 	mutex_lock(&trace_probe_ops.func_hash->regex_lock);
 
+	old_hash_ops.filter_hash = old_hash;
+	/* Probes only have filters */
+	old_hash_ops.notrace_hash = NULL;
+
 	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, old_hash);
 	if (!hash) {
 		count = -ENOMEM;
@@ -3496,7 +3525,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 
 	ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
 
-	__enable_ftrace_function_probe(old_hash);
+	__enable_ftrace_function_probe(&old_hash_ops);
 
 	if (!ret)
 		free_ftrace_hash_rcu(old_hash);
@@ -3784,10 +3813,34 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
 }
 
 static void ftrace_ops_update_code(struct ftrace_ops *ops,
-				   struct ftrace_hash *old_hash)
+				   struct ftrace_ops_hash *old_hash)
 {
-	if (ops->flags & FTRACE_OPS_FL_ENABLED && ftrace_enabled)
+	struct ftrace_ops *op;
+
+	if (!ftrace_enabled)
+		return;
+
+	if (ops->flags & FTRACE_OPS_FL_ENABLED) {
 		ftrace_run_modify_code(ops, FTRACE_UPDATE_CALLS, old_hash);
+		return;
+	}
+
+	/*
+	 * If this is the shared global_ops filter, then we need to
+	 * check if there is another ops that shares it, is enabled.
+	 * If so, we still need to run the modify code.
+	 */
+	if (ops->func_hash != &global_ops.local_hash)
+		return;
+
+	do_for_each_ftrace_op(op, ftrace_ops_list) {
+		if (op->func_hash == &global_ops.local_hash &&
+		    op->flags & FTRACE_OPS_FL_ENABLED) {
+			ftrace_run_modify_code(op, FTRACE_UPDATE_CALLS, old_hash);
+			/* Only need to do this once */
+			return;
+		}
+	} while_for_each_ftrace_op(op);
 }
 
 static int
@@ -3795,6 +3848,7 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 		unsigned long ip, int remove, int reset, int enable)
 {
 	struct ftrace_hash **orig_hash;
+	struct ftrace_ops_hash old_hash_ops;
 	struct ftrace_hash *old_hash;
 	struct ftrace_hash *hash;
 	int ret;
@@ -3831,9 +3885,11 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 
 	mutex_lock(&ftrace_lock);
 	old_hash = *orig_hash;
+	old_hash_ops.filter_hash = ops->func_hash->filter_hash;
+	old_hash_ops.notrace_hash = ops->func_hash->notrace_hash;
 	ret = ftrace_hash_move(ops, enable, orig_hash, hash);
 	if (!ret) {
-		ftrace_ops_update_code(ops, old_hash);
+		ftrace_ops_update_code(ops, &old_hash_ops);
 		free_ftrace_hash_rcu(old_hash);
 	}
 	mutex_unlock(&ftrace_lock);
@@ -4042,6 +4098,7 @@ static void __init set_ftrace_early_filters(void)
 int ftrace_regex_release(struct inode *inode, struct file *file)
 {
 	struct seq_file *m = (struct seq_file *)file->private_data;
+	struct ftrace_ops_hash old_hash_ops;
 	struct ftrace_iterator *iter;
 	struct ftrace_hash **orig_hash;
 	struct ftrace_hash *old_hash;
@@ -4075,10 +4132,12 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
 
 		mutex_lock(&ftrace_lock);
 		old_hash = *orig_hash;
+		old_hash_ops.filter_hash = iter->ops->func_hash->filter_hash;
+		old_hash_ops.notrace_hash = iter->ops->func_hash->notrace_hash;
 		ret = ftrace_hash_move(iter->ops, filter_hash,
 				       orig_hash, iter->hash);
 		if (!ret) {
-			ftrace_ops_update_code(iter->ops, old_hash);
+			ftrace_ops_update_code(iter->ops, &old_hash_ops);
 			free_ftrace_hash_rcu(old_hash);
 		}
 		mutex_unlock(&ftrace_lock);
@@ -5266,12 +5325,12 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 	if (ftrace_enabled) {
 
-		ftrace_startup_sysctl();
-
 		/* we are starting ftrace again */
 		if (ftrace_ops_list != &ftrace_list_end)
 			update_ftrace_function();
 
+		ftrace_startup_sysctl();
+
 	} else {
 		/* stopping ftrace calls (just send to ftrace_stub) */
 		ftrace_trace_function = ftrace_stub;
@@ -5297,8 +5356,6 @@ static struct ftrace_ops graph_ops = {
 	ASSIGN_OPS_HASH(graph_ops, &global_ops.local_hash)
 };
 
-static int ftrace_graph_active;
-
 int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
 {
 	return 0;
diff --git a/kernel/trace/gpu-traces.c b/kernel/trace/gpu-traces.c
new file mode 100644
index 00000000000..a4b3f00faee
--- /dev/null
+++ b/kernel/trace/gpu-traces.c
@@ -0,0 +1,23 @@
+/*
+ * GPU tracepoints
+ *
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/gpu.h>
+
+EXPORT_TRACEPOINT_SYMBOL(gpu_sched_switch);
+EXPORT_TRACEPOINT_SYMBOL(gpu_job_enqueue);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index a56e07c8d15..0fc5cfedcc8 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -450,7 +450,10 @@ int ring_buffer_print_page_header(struct trace_seq *s)
 struct rb_irq_work {
 	struct irq_work			work;
 	wait_queue_head_t		waiters;
+	wait_queue_head_t		full_waiters;
 	bool				waiters_pending;
+	bool				full_waiters_pending;
+	bool				wakeup_full;
 };
 
 /*
@@ -532,6 +535,10 @@ static void rb_wake_up_waiters(struct irq_work *work)
 	struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work);
 
 	wake_up_all(&rbwork->waiters);
+	if (rbwork->wakeup_full) {
+		rbwork->wakeup_full = false;
+		wake_up_all(&rbwork->full_waiters);
+	}
 }
 
 /**
@@ -556,9 +563,11 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full)
 	 * data in any cpu buffer, or a specific buffer, put the
 	 * caller on the appropriate wait queue.
 	 */
-	if (cpu == RING_BUFFER_ALL_CPUS)
+	if (cpu == RING_BUFFER_ALL_CPUS) {
 		work = &buffer->irq_work;
-	else {
+		/* Full only makes sense on per cpu reads */
+		full = false;
+	} else {
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
 			return -ENODEV;
 		cpu_buffer = buffer->buffers[cpu];
@@ -567,7 +576,10 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full)
 
 
 	while (true) {
-		prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
+		if (full)
+			prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE);
+		else
+			prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
 
 		/*
 		 * The events can happen in critical sections where
@@ -589,7 +601,10 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full)
 		 * that is necessary is that the wake up happens after
 		 * a task has been queued. It's OK for spurious wake ups.
 		 */
-		work->waiters_pending = true;
+		if (full)
+			work->full_waiters_pending = true;
+		else
+			work->waiters_pending = true;
 
 		if (signal_pending(current)) {
 			ret = -EINTR;
@@ -618,7 +633,10 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full)
 		schedule();
 	}
 
-	finish_wait(&work->waiters, &wait);
+	if (full)
+		finish_wait(&work->full_waiters, &wait);
+	else
+		finish_wait(&work->waiters, &wait);
 
 	return ret;
 }
@@ -1233,6 +1251,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu)
 	init_completion(&cpu_buffer->update_done);
 	init_irq_work(&cpu_buffer->irq_work.work, rb_wake_up_waiters);
 	init_waitqueue_head(&cpu_buffer->irq_work.waiters);
+	init_waitqueue_head(&cpu_buffer->irq_work.full_waiters);
 
 	bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
 			    GFP_KERNEL, cpu_to_node(cpu));
@@ -2665,7 +2684,7 @@ static DEFINE_PER_CPU(unsigned int, current_context);
 
 static __always_inline int trace_recursive_lock(void)
 {
-	unsigned int val = this_cpu_read(current_context);
+	unsigned int val = __this_cpu_read(current_context);
 	int bit;
 
 	if (in_interrupt()) {
@@ -2682,18 +2701,17 @@ static __always_inline int trace_recursive_lock(void)
 		return 1;
 
 	val |= (1 << bit);
-	this_cpu_write(current_context, val);
+	__this_cpu_write(current_context, val);
 
 	return 0;
 }
 
 static __always_inline void trace_recursive_unlock(void)
 {
-	unsigned int val = this_cpu_read(current_context);
+	unsigned int val = __this_cpu_read(current_context);
 
-	val--;
-	val &= this_cpu_read(current_context);
-	this_cpu_write(current_context, val);
+	val &= val & (val - 1);
+	__this_cpu_write(current_context, val);
 }
 
 #else
@@ -2804,6 +2822,8 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
 static __always_inline void
 rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
 {
+	bool pagebusy;
+
 	if (buffer->irq_work.waiters_pending) {
 		buffer->irq_work.waiters_pending = false;
 		/* irq_work_queue() supplies it's own memory barriers */
@@ -2815,6 +2835,15 @@ rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
 		/* irq_work_queue() supplies it's own memory barriers */
 		irq_work_queue(&cpu_buffer->irq_work.work);
 	}
+
+	pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
+
+	if (!pagebusy && cpu_buffer->irq_work.full_waiters_pending) {
+		cpu_buffer->irq_work.wakeup_full = true;
+		cpu_buffer->irq_work.full_waiters_pending = false;
+		/* irq_work_queue() supplies it's own memory barriers */
+		irq_work_queue(&cpu_buffer->irq_work.work);
+	}
 }
 
 /**
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 3f9e328c30b..728f99b4533 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -452,7 +452,7 @@ static int __init ring_buffer_benchmark_init(void)
 
 	if (producer_fifo >= 0) {
 		struct sched_param param = {
-			.sched_priority = consumer_fifo
+			.sched_priority = producer_fifo
 		};
 		sched_setscheduler(producer, SCHED_FIFO, &param);
 	} else
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 92f4a6cee17..637f572b643 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -812,6 +812,7 @@ static const char *trace_options[] = {
 	"irq-info",
 	"markers",
 	"function-trace",
+	"print-tgid",
 	NULL
 };
 
@@ -1279,6 +1280,7 @@ void tracing_reset_all_online_cpus(void)
 
 #define SAVED_CMDLINES_DEFAULT 128
 #define NO_CMDLINE_MAP UINT_MAX
+static unsigned saved_tgids[SAVED_CMDLINES_DEFAULT];
 static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
 struct saved_cmdlines_buffer {
 	unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
@@ -1517,7 +1519,7 @@ static int trace_save_cmdline(struct task_struct *tsk)
 	}
 
 	set_cmdline(idx, tsk->comm);
-
+	saved_tgids[idx] = tsk->tgid;
 	arch_spin_unlock(&trace_cmdline_lock);
 
 	return 1;
@@ -1560,6 +1562,25 @@ void trace_find_cmdline(int pid, char comm[])
 	preempt_enable();
 }
 
+int trace_find_tgid(int pid)
+{
+	unsigned map;
+	int tgid;
+
+	preempt_disable();
+	arch_spin_lock(&trace_cmdline_lock);
+	map = savedcmd->map_pid_to_cmdline[pid];
+	if (map != NO_CMDLINE_MAP)
+		tgid = saved_tgids[map];
+	else
+		tgid = -1;
+
+	arch_spin_unlock(&trace_cmdline_lock);
+	preempt_enable();
+
+	return tgid;
+}
+
 void tracing_record_cmdline(struct task_struct *tsk)
 {
 	if (atomic_read(&trace_record_cmdline_disabled) || !tracing_is_on())
@@ -2537,6 +2558,13 @@ static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m)
 	seq_puts(m, "#              | |       |          |         |\n");
 }
 
+static void print_func_help_header_tgid(struct trace_buffer *buf, struct seq_file *m)
+{
+	print_event_info(buf, m);
+	seq_puts(m, "#           TASK-PID    TGID   CPU#      TIMESTAMP  FUNCTION\n");
+	seq_puts(m, "#              | |        |      |          |         |\n");
+}
+
 static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m)
 {
 	print_event_info(buf, m);
@@ -2549,6 +2577,18 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file
 	seq_puts(m, "#              | |       |   ||||       |         |\n");
 }
 
+static void print_func_help_header_irq_tgid(struct trace_buffer *buf, struct seq_file *m)
+{
+	print_event_info(buf, m);
+	seq_puts(m, "#                                      _-----=> irqs-off\n");
+	seq_puts(m, "#                                     / _----=> need-resched\n");
+	seq_puts(m, "#                                    | / _---=> hardirq/softirq\n");
+	seq_puts(m, "#                                    || / _--=> preempt-depth\n");
+	seq_puts(m, "#                                    ||| /     delay\n");
+	seq_puts(m, "#           TASK-PID    TGID   CPU#  ||||    TIMESTAMP  FUNCTION\n");
+	seq_puts(m, "#              | |        |      |   ||||       |         |\n");
+}
+
 void
 print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 {
@@ -2849,9 +2889,15 @@ void trace_default_header(struct seq_file *m)
 	} else {
 		if (!(trace_flags & TRACE_ITER_VERBOSE)) {
 			if (trace_flags & TRACE_ITER_IRQ_INFO)
-				print_func_help_header_irq(iter->trace_buffer, m);
+				if (trace_flags & TRACE_ITER_TGID)
+					print_func_help_header_irq_tgid(iter->trace_buffer, m);
+				else
+					print_func_help_header_irq(iter->trace_buffer, m);
 			else
-				print_func_help_header(iter->trace_buffer, m);
+				if (trace_flags & TRACE_ITER_TGID)
+					print_func_help_header_tgid(iter->trace_buffer, m);
+				else
+					print_func_help_header(iter->trace_buffer, m);
 		}
 	}
 }
@@ -3897,6 +3943,50 @@ static const struct file_operations tracing_saved_cmdlines_size_fops = {
 };
 
 static ssize_t
+tracing_saved_tgids_read(struct file *file, char __user *ubuf,
+				size_t cnt, loff_t *ppos)
+{
+	char *file_buf;
+	char *buf;
+	int len = 0;
+	int pid;
+	int i;
+
+	file_buf = kmalloc(SAVED_CMDLINES_DEFAULT*(16+1+16), GFP_KERNEL);
+	if (!file_buf)
+		return -ENOMEM;
+
+	buf = file_buf;
+
+	for (i = 0; i < SAVED_CMDLINES_DEFAULT; i++) {
+		int tgid;
+		int r;
+
+		pid = savedcmd->map_cmdline_to_pid[i];
+		if (pid == -1 || pid == NO_CMDLINE_MAP)
+			continue;
+
+		tgid = trace_find_tgid(pid);
+		r = sprintf(buf, "%d %d\n", pid, tgid);
+		buf += r;
+		len += r;
+	}
+
+	len = simple_read_from_buffer(ubuf, cnt, ppos,
+				      file_buf, len);
+
+	kfree(file_buf);
+
+	return len;
+}
+
+static const struct file_operations tracing_saved_tgids_fops = {
+	.open	= tracing_open_generic,
+	.read	= tracing_saved_tgids_read,
+	.llseek	= generic_file_llseek,
+};
+
+static ssize_t
 tracing_set_trace_read(struct file *filp, char __user *ubuf,
 		       size_t cnt, loff_t *ppos)
 {
@@ -4916,7 +5006,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	*fpos += written;
 
  out_unlock:
-	for (i = 0; i < nr_pages; i++){
+	for (i = nr_pages - 1; i >= 0; i--) {
 		kunmap_atomic(map_page[i]);
 		put_page(pages[i]);
 	}
@@ -6417,7 +6507,7 @@ static int instance_mkdir (struct inode *inode, struct dentry *dentry, umode_t m
 	int ret;
 
 	/* Paranoid: Make sure the parent is the "instances" directory */
-	parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
+	parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
 	if (WARN_ON_ONCE(parent != trace_instance_dir))
 		return -ENOENT;
 
@@ -6444,7 +6534,7 @@ static int instance_rmdir(struct inode *inode, struct dentry *dentry)
 	int ret;
 
 	/* Paranoid: Make sure the parent is the "instances" directory */
-	parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
+	parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
 	if (WARN_ON_ONCE(parent != trace_instance_dir))
 		return -ENOENT;
 
@@ -6520,6 +6610,9 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
 	trace_create_file("trace_marker", 0220, d_tracer,
 			  tr, &tracing_mark_fops);
 
+	trace_create_file("saved_tgids", 0444, d_tracer,
+			  tr, &tracing_saved_tgids_fops);
+
 	trace_create_file("trace_clock", 0644, d_tracer, tr,
 			  &trace_clock_fops);
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 385391fb1d3..0d2f5875c99 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -442,6 +442,7 @@ enum {
 
 	TRACE_CONTROL_BIT,
 
+	TRACE_BRANCH_BIT,
 /*
  * Abuse of the trace_recursion.
  * As we need a way to maintain state if we are tracing the function
@@ -658,6 +659,7 @@ static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
 extern cycle_t ftrace_now(int cpu);
 
 extern void trace_find_cmdline(int pid, char comm[]);
+extern int trace_find_tgid(int pid);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 extern unsigned long ftrace_update_tot_cnt;
@@ -938,6 +940,7 @@ enum trace_iterator_flags {
 	TRACE_ITER_IRQ_INFO		= 0x800000,
 	TRACE_ITER_MARKERS		= 0x1000000,
 	TRACE_ITER_FUNCTION		= 0x2000000,
+	TRACE_ITER_TGID 		= 0x4000000,
 };
 
 /*
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index 697fb9bac8f..60850b4fcb0 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -37,9 +37,12 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 	struct trace_branch *entry;
 	struct ring_buffer *buffer;
 	unsigned long flags;
-	int cpu, pc;
+	int pc;
 	const char *p;
 
+	if (current->trace_recursion & TRACE_BRANCH_BIT)
+		return;
+
 	/*
 	 * I would love to save just the ftrace_likely_data pointer, but
 	 * this code can also be used by modules. Ugly things can happen
@@ -50,10 +53,10 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 	if (unlikely(!tr))
 		return;
 
-	local_irq_save(flags);
-	cpu = raw_smp_processor_id();
-	data = per_cpu_ptr(tr->trace_buffer.data, cpu);
-	if (atomic_inc_return(&data->disabled) != 1)
+	raw_local_irq_save(flags);
+	current->trace_recursion |= TRACE_BRANCH_BIT;
+	data = this_cpu_ptr(tr->trace_buffer.data);
+	if (atomic_read(&data->disabled))
 		goto out;
 
 	pc = preempt_count();
@@ -82,8 +85,8 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 		__buffer_unlock_commit(buffer, event);
 
  out:
-	atomic_dec(&data->disabled);
-	local_irq_restore(flags);
+	current->trace_recursion &= ~TRACE_BRANCH_BIT;
+	raw_local_irq_restore(flags);
 }
 
 static inline
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 0cc51edde3a..1b0df1e504f 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -461,7 +461,7 @@ static void remove_event_file_dir(struct ftrace_event_file *file)
 
 	if (dir) {
 		spin_lock(&dir->d_lock);	/* probably unneeded */
-		list_for_each_entry(child, &dir->d_subdirs, d_u.d_child) {
+		list_for_each_entry(child, &dir->d_subdirs, d_child) {
 			if (child->d_inode)	/* probably unneeded */
 				child->d_inode->i_private = NULL;
 		}
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 7a8c1528e14..357b1ddf088 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1050,6 +1050,9 @@ static void parse_init(struct filter_parse_state *ps,
 
 static char infix_next(struct filter_parse_state *ps)
 {
+	if (!ps->infix.cnt)
+		return 0;
+
 	ps->infix.cnt--;
 
 	return ps->infix.string[ps->infix.tail++];
@@ -1065,6 +1068,9 @@ static char infix_peek(struct filter_parse_state *ps)
 
 static void infix_advance(struct filter_parse_state *ps)
 {
+	if (!ps->infix.cnt)
+		return;
+
 	ps->infix.cnt--;
 	ps->infix.tail++;
 }
@@ -1363,19 +1369,26 @@ static int check_preds(struct filter_parse_state *ps)
 {
 	int n_normal_preds = 0, n_logical_preds = 0;
 	struct postfix_elt *elt;
+	int cnt = 0;
 
 	list_for_each_entry(elt, &ps->postfix, list) {
-		if (elt->op == OP_NONE)
+		if (elt->op == OP_NONE) {
+			cnt++;
 			continue;
+		}
 
+		cnt--;
 		if (elt->op == OP_AND || elt->op == OP_OR) {
 			n_logical_preds++;
 			continue;
 		}
 		n_normal_preds++;
+		/* all ops should have operands */
+		if (cnt < 0)
+			break;
 	}
 
-	if (!n_normal_preds || n_logical_preds >= n_normal_preds) {
+	if (cnt != 1 || !n_normal_preds || n_logical_preds >= n_normal_preds) {
 		parse_error(ps, FILT_ERR_INVALID_FILTER, 0);
 		return -EINVAL;
 	}
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index f0a0c982cde..70c2f41bec1 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -65,6 +65,9 @@ struct fgraph_data {
 
 #define TRACE_GRAPH_INDENT	2
 
+/* Flag options */
+#define TRACE_GRAPH_PRINT_FLAT		0x80
+
 static unsigned int max_depth;
 
 static struct tracer_opt trace_opts[] = {
@@ -84,6 +87,8 @@ static struct tracer_opt trace_opts[] = {
 	{ TRACER_OPT(funcgraph-irqs, TRACE_GRAPH_PRINT_IRQS) },
 	/* Display function name after trailing } */
 	{ TRACER_OPT(funcgraph-tail, TRACE_GRAPH_PRINT_TAIL) },
+	/* Use standard trace formatting rather than hierarchical */
+	{ TRACER_OPT(funcgraph-flat, TRACE_GRAPH_PRINT_FLAT) },
 	{ } /* Empty entry */
 };
 
@@ -1314,6 +1319,9 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 	int cpu = iter->cpu;
 	int ret;
 
+	if (flags & TRACE_GRAPH_PRINT_FLAT)
+		return TRACE_TYPE_UNHANDLED;
+
 	if (data && per_cpu_ptr(data->cpu_data, cpu)->ignore) {
 		per_cpu_ptr(data->cpu_data, cpu)->ignore = 0;
 		return TRACE_TYPE_HANDLED;
@@ -1371,13 +1379,6 @@ print_graph_function(struct trace_iterator *iter)
 	return print_graph_function_flags(iter, tracer_flags.val);
 }
 
-static enum print_line_t
-print_graph_function_event(struct trace_iterator *iter, int flags,
-			   struct trace_event *event)
-{
-	return print_graph_function(iter);
-}
-
 static void print_lat_header(struct seq_file *s, u32 flags)
 {
 	static const char spaces[] = "                "	/* 16 spaces */
@@ -1444,6 +1445,11 @@ void print_graph_headers_flags(struct seq_file *s, u32 flags)
 {
 	struct trace_iterator *iter = s->private;
 
+	if (flags & TRACE_GRAPH_PRINT_FLAT) {
+		trace_default_header(s);
+		return;
+	}
+
 	if (!(trace_flags & TRACE_ITER_CONTEXT_INFO))
 		return;
 
@@ -1462,15 +1468,19 @@ void graph_trace_open(struct trace_iterator *iter)
 {
 	/* pid and depth on the last trace processed */
 	struct fgraph_data *data;
+	gfp_t gfpflags;
 	int cpu;
 
 	iter->private = NULL;
 
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	/* We can be called in atomic context via ftrace_dump() */
+	gfpflags = (in_atomic() || irqs_disabled()) ? GFP_ATOMIC : GFP_KERNEL;
+
+	data = kzalloc(sizeof(*data), gfpflags);
 	if (!data)
 		goto out_err;
 
-	data->cpu_data = alloc_percpu(struct fgraph_cpu_data);
+	data->cpu_data = alloc_percpu_gfp(struct fgraph_cpu_data, gfpflags);
 	if (!data->cpu_data)
 		goto out_err_free;
 
@@ -1515,19 +1525,6 @@ func_graph_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 	return 0;
 }
 
-static struct trace_event_functions graph_functions = {
-	.trace		= print_graph_function_event,
-};
-
-static struct trace_event graph_trace_entry_event = {
-	.type		= TRACE_GRAPH_ENT,
-	.funcs		= &graph_functions,
-};
-
-static struct trace_event graph_trace_ret_event = {
-	.type		= TRACE_GRAPH_RET,
-	.funcs		= &graph_functions
-};
 
 static struct tracer graph_trace __tracer_data = {
 	.name		= "function_graph",
@@ -1604,16 +1601,6 @@ static __init int init_graph_trace(void)
 {
 	max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1);
 
-	if (!register_ftrace_event(&graph_trace_entry_event)) {
-		pr_warning("Warning: could not register graph trace events\n");
-		return 1;
-	}
-
-	if (!register_ftrace_event(&graph_trace_ret_event)) {
-		pr_warning("Warning: could not register graph trace events\n");
-		return 1;
-	}
-
 	return register_tracer(&graph_trace);
 }
 
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index c6977d5a9b1..a2b8202d858 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -186,6 +186,50 @@ ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len)
 }
 EXPORT_SYMBOL(ftrace_print_hex_seq);
 
+const char *
+ftrace_print_array_seq(struct trace_seq *p, const void *buf, int buf_len,
+		       size_t el_size)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+	const char *prefix = "";
+	void *ptr = (void *)buf;
+
+	trace_seq_putc(p, '{');
+
+	while (ptr < buf + buf_len) {
+		switch (el_size) {
+		case 1:
+			trace_seq_printf(p, "%s0x%x", prefix,
+					 *(u8 *)ptr);
+			break;
+		case 2:
+			trace_seq_printf(p, "%s0x%x", prefix,
+					 *(u16 *)ptr);
+			break;
+		case 4:
+			trace_seq_printf(p, "%s0x%x", prefix,
+					 *(u32 *)ptr);
+			break;
+		case 8:
+			trace_seq_printf(p, "%s0x%llx", prefix,
+					 *(u64 *)ptr);
+			break;
+		default:
+			trace_seq_printf(p, "BAD SIZE:%zu 0x%x", el_size,
+					 *(u8 *)ptr);
+			el_size = 1;
+		}
+		prefix = ",";
+		ptr += el_size;
+	}
+
+	trace_seq_putc(p, '}');
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+EXPORT_SYMBOL(ftrace_print_array_seq);
+
 int ftrace_raw_output_prep(struct trace_iterator *iter,
 			   struct trace_event *trace_event)
 {
@@ -521,11 +565,25 @@ int trace_print_context(struct trace_iterator *iter)
 	unsigned long secs, usec_rem;
 	char comm[TASK_COMM_LEN];
 	int ret;
+	int tgid;
 
 	trace_find_cmdline(entry->pid, comm);
 
-	ret = trace_seq_printf(s, "%16s-%-5d [%03d] ",
-			       comm, entry->pid, iter->cpu);
+	ret = trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
+	if (!ret)
+		return 0;
+
+	if (trace_flags & TRACE_ITER_TGID) {
+		tgid = trace_find_tgid(entry->pid);
+		if (tgid < 0)
+			ret = trace_seq_puts(s, "(-----) ");
+		else
+			ret = trace_seq_printf(s, "(%5d) ", tgid);
+		if (!ret)
+			return 0;
+	}
+
+	ret = trace_seq_printf(s, "[%03d] ", iter->cpu);
 	if (!ret)
 		return 0;
 
@@ -854,6 +912,168 @@ static struct trace_event trace_fn_event = {
 	.funcs		= &trace_fn_funcs,
 };
 
+/* TRACE_GRAPH_ENT */
+static enum print_line_t trace_graph_ent_trace(struct trace_iterator *iter, int flags,
+					struct trace_event *event)
+{
+	struct trace_seq *s = &iter->seq;
+	struct ftrace_graph_ent_entry *field;
+
+	trace_assign_type(field, iter->ent);
+
+	if (!trace_seq_puts(s, "graph_ent: func="))
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	if (!seq_print_ip_sym(s, field->graph_ent.func, flags))
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	if (!trace_seq_puts(s, "\n"))
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ent_raw(struct trace_iterator *iter, int flags,
+				      struct trace_event *event)
+{
+	struct ftrace_graph_ent_entry *field;
+
+	trace_assign_type(field, iter->ent);
+
+	if (!trace_seq_printf(&iter->seq, "%lx %d\n",
+			      field->graph_ent.func,
+			      field->graph_ent.depth))
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ent_hex(struct trace_iterator *iter, int flags,
+				      struct trace_event *event)
+{
+	struct ftrace_graph_ent_entry *field;
+	struct trace_seq *s = &iter->seq;
+
+	trace_assign_type(field, iter->ent);
+
+	SEQ_PUT_HEX_FIELD_RET(s, field->graph_ent.func);
+	SEQ_PUT_HEX_FIELD_RET(s, field->graph_ent.depth);
+
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ent_bin(struct trace_iterator *iter, int flags,
+				      struct trace_event *event)
+{
+	struct ftrace_graph_ent_entry *field;
+	struct trace_seq *s = &iter->seq;
+
+	trace_assign_type(field, iter->ent);
+
+	SEQ_PUT_FIELD_RET(s, field->graph_ent.func);
+	SEQ_PUT_FIELD_RET(s, field->graph_ent.depth);
+
+	return TRACE_TYPE_HANDLED;
+}
+
+static struct trace_event_functions trace_graph_ent_funcs = {
+	.trace		= trace_graph_ent_trace,
+	.raw		= trace_graph_ent_raw,
+	.hex		= trace_graph_ent_hex,
+	.binary		= trace_graph_ent_bin,
+};
+
+static struct trace_event trace_graph_ent_event = {
+	.type		= TRACE_GRAPH_ENT,
+	.funcs		= &trace_graph_ent_funcs,
+};
+
+/* TRACE_GRAPH_RET */
+static enum print_line_t trace_graph_ret_trace(struct trace_iterator *iter, int flags,
+					struct trace_event *event)
+{
+	struct trace_seq *s = &iter->seq;
+	struct trace_entry *entry = iter->ent;
+	struct ftrace_graph_ret_entry *field;
+
+	trace_assign_type(field, entry);
+
+	if (!trace_seq_puts(s, "graph_ret: func="))
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	if (!seq_print_ip_sym(s, field->ret.func, flags))
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	if (!trace_seq_puts(s, "\n"))
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ret_raw(struct trace_iterator *iter, int flags,
+				      struct trace_event *event)
+{
+	struct ftrace_graph_ret_entry *field;
+
+	trace_assign_type(field, iter->ent);
+
+	if (!trace_seq_printf(&iter->seq, "%lx %lld %lld %ld %d\n",
+			      field->ret.func,
+			      field->ret.calltime,
+			      field->ret.rettime,
+			      field->ret.overrun,
+			      field->ret.depth));
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ret_hex(struct trace_iterator *iter, int flags,
+				      struct trace_event *event)
+{
+	struct ftrace_graph_ret_entry *field;
+	struct trace_seq *s = &iter->seq;
+
+	trace_assign_type(field, iter->ent);
+
+	SEQ_PUT_HEX_FIELD_RET(s, field->ret.func);
+	SEQ_PUT_HEX_FIELD_RET(s, field->ret.calltime);
+	SEQ_PUT_HEX_FIELD_RET(s, field->ret.rettime);
+	SEQ_PUT_HEX_FIELD_RET(s, field->ret.overrun);
+	SEQ_PUT_HEX_FIELD_RET(s, field->ret.depth);
+
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ret_bin(struct trace_iterator *iter, int flags,
+				      struct trace_event *event)
+{
+	struct ftrace_graph_ret_entry *field;
+	struct trace_seq *s = &iter->seq;
+
+	trace_assign_type(field, iter->ent);
+
+	SEQ_PUT_FIELD_RET(s, field->ret.func);
+	SEQ_PUT_FIELD_RET(s, field->ret.calltime);
+	SEQ_PUT_FIELD_RET(s, field->ret.rettime);
+	SEQ_PUT_FIELD_RET(s, field->ret.overrun);
+	SEQ_PUT_FIELD_RET(s, field->ret.depth);
+
+	return TRACE_TYPE_HANDLED;
+}
+
+static struct trace_event_functions trace_graph_ret_funcs = {
+	.trace		= trace_graph_ret_trace,
+	.raw		= trace_graph_ret_raw,
+	.hex		= trace_graph_ret_hex,
+	.binary		= trace_graph_ret_bin,
+};
+
+static struct trace_event trace_graph_ret_event = {
+	.type		= TRACE_GRAPH_RET,
+	.funcs		= &trace_graph_ret_funcs,
+};
+
 /* TRACE_CTX an TRACE_WAKE */
 static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
 					     char *delim)
@@ -1244,6 +1464,8 @@ static struct trace_event trace_print_event = {
 
 static struct trace_event *events[] __initdata = {
 	&trace_fn_event,
+	&trace_graph_ent_event,
+	&trace_graph_ret_event,
 	&trace_ctx_event,
 	&trace_wake_event,
 	&trace_stack_event,
diff --git a/kernel/uid16.c b/kernel/uid16.c
index 602e5bbbcef..d58cc4d8f0d 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -176,7 +176,7 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist)
 	struct group_info *group_info;
 	int retval;
 
-	if (!ns_capable(current_user_ns(), CAP_SETGID))
+	if (!may_setgroups())
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;
diff --git a/kernel/user.c b/kernel/user.c
index 4efa39350e4..2d09940c963 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,6 +51,7 @@ struct user_namespace init_user_ns = {
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.proc_inum = PROC_USER_INIT_INO,
+	.flags = USERNS_INIT_FLAGS,
 #ifdef CONFIG_PERSISTENT_KEYRINGS
 	.persistent_keyring_register_sem =
 	__RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem),
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index aa312b0dc3e..a2e37c5d2f6 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -24,6 +24,7 @@
 #include <linux/fs_struct.h>
 
 static struct kmem_cache *user_ns_cachep __read_mostly;
+static DEFINE_MUTEX(userns_state_mutex);
 
 static bool new_idmap_permitted(const struct file *file,
 				struct user_namespace *ns, int cap_setid,
@@ -99,6 +100,11 @@ int create_user_ns(struct cred *new)
 	ns->owner = owner;
 	ns->group = group;
 
+	/* Inherit USERNS_SETGROUPS_ALLOWED from our parent */
+	mutex_lock(&userns_state_mutex);
+	ns->flags = parent_ns->flags;
+	mutex_unlock(&userns_state_mutex);
+
 	set_cred_user_ns(new, ns);
 
 #ifdef CONFIG_PERSISTENT_KEYRINGS
@@ -583,9 +589,6 @@ static bool mappings_overlap(struct uid_gid_map *new_map,
 	return false;
 }
 
-
-static DEFINE_MUTEX(id_map_mutex);
-
 static ssize_t map_write(struct file *file, const char __user *buf,
 			 size_t count, loff_t *ppos,
 			 int cap_setid,
@@ -602,7 +605,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 	ssize_t ret = -EINVAL;
 
 	/*
-	 * The id_map_mutex serializes all writes to any given map.
+	 * The userns_state_mutex serializes all writes to any given map.
 	 *
 	 * Any map is only ever written once.
 	 *
@@ -620,7 +623,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 	 * order and smp_rmb() is guaranteed that we don't have crazy
 	 * architectures returning stale data.
 	 */
-	mutex_lock(&id_map_mutex);
+	mutex_lock(&userns_state_mutex);
 
 	ret = -EPERM;
 	/* Only allow one successful write to the map */
@@ -750,7 +753,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 	*ppos = count;
 	ret = count;
 out:
-	mutex_unlock(&id_map_mutex);
+	mutex_unlock(&userns_state_mutex);
 	if (page)
 		free_page(page);
 	return ret;
@@ -812,16 +815,21 @@ static bool new_idmap_permitted(const struct file *file,
 				struct user_namespace *ns, int cap_setid,
 				struct uid_gid_map *new_map)
 {
-	/* Allow mapping to your own filesystem ids */
-	if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1)) {
+	const struct cred *cred = file->f_cred;
+	/* Don't allow mappings that would allow anything that wouldn't
+	 * be allowed without the establishment of unprivileged mappings.
+	 */
+	if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) &&
+	    uid_eq(ns->owner, cred->euid)) {
 		u32 id = new_map->extent[0].lower_first;
 		if (cap_setid == CAP_SETUID) {
 			kuid_t uid = make_kuid(ns->parent, id);
-			if (uid_eq(uid, file->f_cred->fsuid))
+			if (uid_eq(uid, cred->euid))
 				return true;
 		} else if (cap_setid == CAP_SETGID) {
 			kgid_t gid = make_kgid(ns->parent, id);
-			if (gid_eq(gid, file->f_cred->fsgid))
+			if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) &&
+			    gid_eq(gid, cred->egid))
 				return true;
 		}
 	}
@@ -841,6 +849,100 @@ static bool new_idmap_permitted(const struct file *file,
 	return false;
 }
 
+int proc_setgroups_show(struct seq_file *seq, void *v)
+{
+	struct user_namespace *ns = seq->private;
+	unsigned long userns_flags = ACCESS_ONCE(ns->flags);
+
+	seq_printf(seq, "%s\n",
+		   (userns_flags & USERNS_SETGROUPS_ALLOWED) ?
+		   "allow" : "deny");
+	return 0;
+}
+
+ssize_t proc_setgroups_write(struct file *file, const char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	struct seq_file *seq = file->private_data;
+	struct user_namespace *ns = seq->private;
+	char kbuf[8], *pos;
+	bool setgroups_allowed;
+	ssize_t ret;
+
+	/* Only allow a very narrow range of strings to be written */
+	ret = -EINVAL;
+	if ((*ppos != 0) || (count >= sizeof(kbuf)))
+		goto out;
+
+	/* What was written? */
+	ret = -EFAULT;
+	if (copy_from_user(kbuf, buf, count))
+		goto out;
+	kbuf[count] = '\0';
+	pos = kbuf;
+
+	/* What is being requested? */
+	ret = -EINVAL;
+	if (strncmp(pos, "allow", 5) == 0) {
+		pos += 5;
+		setgroups_allowed = true;
+	}
+	else if (strncmp(pos, "deny", 4) == 0) {
+		pos += 4;
+		setgroups_allowed = false;
+	}
+	else
+		goto out;
+
+	/* Verify there is not trailing junk on the line */
+	pos = skip_spaces(pos);
+	if (*pos != '\0')
+		goto out;
+
+	ret = -EPERM;
+	mutex_lock(&userns_state_mutex);
+	if (setgroups_allowed) {
+		/* Enabling setgroups after setgroups has been disabled
+		 * is not allowed.
+		 */
+		if (!(ns->flags & USERNS_SETGROUPS_ALLOWED))
+			goto out_unlock;
+	} else {
+		/* Permanently disabling setgroups after setgroups has
+		 * been enabled by writing the gid_map is not allowed.
+		 */
+		if (ns->gid_map.nr_extents != 0)
+			goto out_unlock;
+		ns->flags &= ~USERNS_SETGROUPS_ALLOWED;
+	}
+	mutex_unlock(&userns_state_mutex);
+
+	/* Report a successful write */
+	*ppos = count;
+	ret = count;
+out:
+	return ret;
+out_unlock:
+	mutex_unlock(&userns_state_mutex);
+	goto out;
+}
+
+bool userns_may_setgroups(const struct user_namespace *ns)
+{
+	bool allowed;
+
+	mutex_lock(&userns_state_mutex);
+	/* It is not safe to use setgroups until a gid mapping in
+	 * the user namespace has been established.
+	 */
+	allowed = ns->gid_map.nr_extents != 0;
+	/* Is setgroups allowed? */
+	allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED);
+	mutex_unlock(&userns_state_mutex);
+
+	return allowed;
+}
+
 static void *userns_get(struct task_struct *task)
 {
 	struct user_namespace *user_ns;
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 70bf11815f8..7eccf9b6d8b 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -47,6 +47,11 @@ static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved);
 static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
+#endif
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU
+static cpumask_t __read_mostly watchdog_cpus;
+#endif
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
 #endif
 static unsigned long soft_lockup_nmi_warn;
@@ -221,7 +226,7 @@ void touch_softlockup_watchdog_sync(void)
 	__this_cpu_write(watchdog_touch_ts, 0);
 }
 
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI
 /* watchdog detector functions */
 static int is_hardlockup(void)
 {
@@ -235,6 +240,76 @@ static int is_hardlockup(void)
 }
 #endif
 
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU
+static unsigned int watchdog_next_cpu(unsigned int cpu)
+{
+	cpumask_t cpus = watchdog_cpus;
+	unsigned int next_cpu;
+
+	next_cpu = cpumask_next(cpu, &cpus);
+	if (next_cpu >= nr_cpu_ids)
+		next_cpu = cpumask_first(&cpus);
+
+	if (next_cpu == cpu)
+		return nr_cpu_ids;
+
+	return next_cpu;
+}
+
+static int is_hardlockup_other_cpu(unsigned int cpu)
+{
+	unsigned long hrint = per_cpu(hrtimer_interrupts, cpu);
+
+	if (per_cpu(hrtimer_interrupts_saved, cpu) == hrint)
+		return 1;
+
+	per_cpu(hrtimer_interrupts_saved, cpu) = hrint;
+	return 0;
+}
+
+static void watchdog_check_hardlockup_other_cpu(void)
+{
+	unsigned int next_cpu;
+
+	/*
+	 * Test for hardlockups every 3 samples.  The sample period is
+	 *  watchdog_thresh * 2 / 5, so 3 samples gets us back to slightly over
+	 *  watchdog_thresh (over by 20%).
+	 */
+	if (__this_cpu_read(hrtimer_interrupts) % 3 != 0)
+		return;
+
+	/* check for a hardlockup on the next cpu */
+	next_cpu = watchdog_next_cpu(smp_processor_id());
+	if (next_cpu >= nr_cpu_ids)
+		return;
+
+	smp_rmb();
+
+	if (per_cpu(watchdog_nmi_touch, next_cpu) == true) {
+		per_cpu(watchdog_nmi_touch, next_cpu) = false;
+		return;
+	}
+
+	if (is_hardlockup_other_cpu(next_cpu)) {
+		/* only warn once */
+		if (per_cpu(hard_watchdog_warn, next_cpu) == true)
+			return;
+
+		if (hardlockup_panic)
+			panic("Watchdog detected hard LOCKUP on cpu %u", next_cpu);
+		else
+			WARN(1, "Watchdog detected hard LOCKUP on cpu %u", next_cpu);
+
+		per_cpu(hard_watchdog_warn, next_cpu) = true;
+	} else {
+		per_cpu(hard_watchdog_warn, next_cpu) = false;
+	}
+}
+#else
+static inline void watchdog_check_hardlockup_other_cpu(void) { return; }
+#endif
+
 static int is_softlockup(unsigned long touch_ts)
 {
 	unsigned long now = get_timestamp();
@@ -246,7 +321,7 @@ static int is_softlockup(unsigned long touch_ts)
 	return 0;
 }
 
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI
 
 static struct perf_event_attr wd_hw_attr = {
 	.type		= PERF_TYPE_HARDWARE,
@@ -296,7 +371,7 @@ static void watchdog_overflow_callback(struct perf_event *event,
 	__this_cpu_write(hard_watchdog_warn, false);
 	return;
 }
-#endif /* CONFIG_HARDLOCKUP_DETECTOR */
+#endif /* CONFIG_HARDLOCKUP_DETECTOR_NMI */
 
 static void watchdog_interrupt_count(void)
 {
@@ -317,6 +392,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	/* kick the hardlockup detector */
 	watchdog_interrupt_count();
 
+	/* test for hardlockups on the next cpu */
+	watchdog_check_hardlockup_other_cpu();
+
 	/* kick the softlockup detector */
 	wake_up_process(__this_cpu_read(softlockup_watchdog));
 
@@ -479,7 +557,7 @@ static void watchdog(unsigned int cpu)
 	__touch_watchdog();
 }
 
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI
 /*
  * People like the simple clean cpu node info on boot.
  * Reduce the watchdog noise by only printing messages
@@ -568,9 +646,44 @@ static void watchdog_nmi_disable(unsigned int cpu)
 	}
 }
 #else
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU
+static int watchdog_nmi_enable(unsigned int cpu)
+{
+	/*
+	 * The new cpu will be marked online before the first hrtimer interrupt
+	 * runs on it.  If another cpu tests for a hardlockup on the new cpu
+	 * before it has run its first hrtimer, it will get a false positive.
+	 * Touch the watchdog on the new cpu to delay the first check for at
+	 * least 3 sampling periods to guarantee one hrtimer has run on the new
+	 * cpu.
+	 */
+	per_cpu(watchdog_nmi_touch, cpu) = true;
+	smp_wmb();
+	cpumask_set_cpu(cpu, &watchdog_cpus);
+	return 0;
+}
+
+static void watchdog_nmi_disable(unsigned int cpu)
+{
+	unsigned int next_cpu = watchdog_next_cpu(cpu);
+
+	/*
+	 * Offlining this cpu will cause the cpu before this one to start
+	 * checking the one after this one.  If this cpu just finished checking
+	 * the next cpu and updating hrtimer_interrupts_saved, and then the
+	 * previous cpu checks it within one sample period, it will trigger a
+	 * false positive.  Touch the watchdog on the next cpu to prevent it.
+	 */
+	if (next_cpu < nr_cpu_ids)
+		per_cpu(watchdog_nmi_touch, next_cpu) = true;
+	smp_wmb();
+	cpumask_clear_cpu(cpu, &watchdog_cpus);
+}
+#else
 static int watchdog_nmi_enable(unsigned int cpu) { return 0; }
 static void watchdog_nmi_disable(unsigned int cpu) { return; }
-#endif /* CONFIG_HARDLOCKUP_DETECTOR */
+#endif /* CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU */
+#endif /* CONFIG_HARDLOCKUP_DETECTOR_NMI */
 
 static struct smp_hotplug_thread watchdog_threads = {
 	.store			= &softlockup_watchdog,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 09b685daee3..2273f534b01 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1841,17 +1841,11 @@ static void pool_mayday_timeout(unsigned long __pool)
  * spin_lock_irq(pool->lock) which may be released and regrabbed
  * multiple times.  Does GFP_KERNEL allocations.  Called only from
  * manager.
- *
- * Return:
- * %false if no action was taken and pool->lock stayed locked, %true
- * otherwise.
  */
-static bool maybe_create_worker(struct worker_pool *pool)
+static void maybe_create_worker(struct worker_pool *pool)
 __releases(&pool->lock)
 __acquires(&pool->lock)
 {
-	if (!need_to_create_worker(pool))
-		return false;
 restart:
 	spin_unlock_irq(&pool->lock);
 
@@ -1877,7 +1871,6 @@ restart:
 	 */
 	if (need_to_create_worker(pool))
 		goto restart;
-	return true;
 }
 
 /**
@@ -1897,16 +1890,14 @@ restart:
  * multiple times.  Does GFP_KERNEL allocations.
  *
  * Return:
- * %false if the pool don't need management and the caller can safely start
- * processing works, %true indicates that the function released pool->lock
- * and reacquired it to perform some management function and that the
- * conditions that the caller verified while holding the lock before
- * calling the function might no longer be true.
+ * %false if the pool doesn't need management and the caller can safely
+ * start processing works, %true if management function was performed and
+ * the conditions that the caller verified before calling the function may
+ * no longer be true.
  */
 static bool manage_workers(struct worker *worker)
 {
 	struct worker_pool *pool = worker->pool;
-	bool ret = false;
 
 	/*
 	 * Anyone who successfully grabs manager_arb wins the arbitration
@@ -1919,12 +1910,12 @@ static bool manage_workers(struct worker *worker)
 	 * actual management, the pool may stall indefinitely.
 	 */
 	if (!mutex_trylock(&pool->manager_arb))
-		return ret;
+		return false;
 
-	ret |= maybe_create_worker(pool);
+	maybe_create_worker(pool);
 
 	mutex_unlock(&pool->manager_arb);
-	return ret;
+	return true;
 }
 
 /**
@@ -2719,19 +2710,57 @@ bool flush_work(struct work_struct *work)
 }
 EXPORT_SYMBOL_GPL(flush_work);
 
+struct cwt_wait {
+	wait_queue_t		wait;
+	struct work_struct	*work;
+};
+
+static int cwt_wakefn(wait_queue_t *wait, unsigned mode, int sync, void *key)
+{
+	struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait);
+
+	if (cwait->work != key)
+		return 0;
+	return autoremove_wake_function(wait, mode, sync, key);
+}
+
 static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
 {
+	static DECLARE_WAIT_QUEUE_HEAD(cancel_waitq);
 	unsigned long flags;
 	int ret;
 
 	do {
 		ret = try_to_grab_pending(work, is_dwork, &flags);
 		/*
-		 * If someone else is canceling, wait for the same event it
-		 * would be waiting for before retrying.
+		 * If someone else is already canceling, wait for it to
+		 * finish.  flush_work() doesn't work for PREEMPT_NONE
+		 * because we may get scheduled between @work's completion
+		 * and the other canceling task resuming and clearing
+		 * CANCELING - flush_work() will return false immediately
+		 * as @work is no longer busy, try_to_grab_pending() will
+		 * return -ENOENT as @work is still being canceled and the
+		 * other canceling task won't be able to clear CANCELING as
+		 * we're hogging the CPU.
+		 *
+		 * Let's wait for completion using a waitqueue.  As this
+		 * may lead to the thundering herd problem, use a custom
+		 * wake function which matches @work along with exclusive
+		 * wait and wakeup.
 		 */
-		if (unlikely(ret == -ENOENT))
-			flush_work(work);
+		if (unlikely(ret == -ENOENT)) {
+			struct cwt_wait cwait;
+
+			init_wait(&cwait.wait);
+			cwait.wait.func = cwt_wakefn;
+			cwait.work = work;
+
+			prepare_to_wait_exclusive(&cancel_waitq, &cwait.wait,
+						  TASK_UNINTERRUPTIBLE);
+			if (work_is_canceling(work))
+				schedule();
+			finish_wait(&cancel_waitq, &cwait.wait);
+		}
 	} while (unlikely(ret < 0));
 
 	/* tell other tasks trying to grab @work to back off */
@@ -2740,6 +2769,16 @@ static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
 
 	flush_work(work);
 	clear_work_data(work);
+
+	/*
+	 * Paired with prepare_to_wait() above so that either
+	 * waitqueue_active() is visible here or !work_is_canceling() is
+	 * visible there.
+	 */
+	smp_mb();
+	if (waitqueue_active(&cancel_waitq))
+		__wake_up(&cancel_waitq, TASK_NORMAL, 1, work);
+
 	return ret;
 }
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 4e35a5d767e..95e5931cd05 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -668,15 +668,27 @@ config LOCKUP_DETECTOR
 	  The overhead should be minimal.  A periodic hrtimer runs to
 	  generate interrupts and kick the watchdog task every 4 seconds.
 	  An NMI is generated every 10 seconds or so to check for hardlockups.
+	  If NMIs are not available on the platform, every 12 seconds the
+	  hrtimer interrupt on one cpu will be used to check for hardlockups
+	  on the next cpu.
 
 	  The frequency of hrtimer and NMI events and the soft and hard lockup
 	  thresholds can be controlled through the sysctl watchdog_thresh.
 
-config HARDLOCKUP_DETECTOR
+config HARDLOCKUP_DETECTOR_NMI
 	def_bool y
 	depends on LOCKUP_DETECTOR && !HAVE_NMI_WATCHDOG
 	depends on PERF_EVENTS && HAVE_PERF_EVENTS_NMI
 
+config HARDLOCKUP_DETECTOR_OTHER_CPU
+	def_bool y
+	depends on LOCKUP_DETECTOR && SMP
+	depends on !HARDLOCKUP_DETECTOR_NMI && !HAVE_NMI_WATCHDOG
+
+config HARDLOCKUP_DETECTOR
+	def_bool y
+	depends on HARDLOCKUP_DETECTOR_NMI || HARDLOCKUP_DETECTOR_OTHER_CPU
+
 config BOOTPARAM_HARDLOCKUP_PANIC
 	bool "Panic (Reboot) On Hard Lockups"
 	depends on HARDLOCKUP_DETECTOR
diff --git a/lib/bitmap.c b/lib/bitmap.c
index b499ab6ada2..2ed91904e80 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -610,12 +610,12 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen,
 	unsigned a, b;
 	int c, old_c, totaldigits;
 	const char __user __force *ubuf = (const char __user __force *)buf;
-	int exp_digit, in_range;
+	int at_start, in_range;
 
 	totaldigits = c = 0;
 	bitmap_zero(maskp, nmaskbits);
 	do {
-		exp_digit = 1;
+		at_start = 1;
 		in_range = 0;
 		a = b = 0;
 
@@ -644,11 +644,10 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen,
 				break;
 
 			if (c == '-') {
-				if (exp_digit || in_range)
+				if (at_start || in_range)
 					return -EINVAL;
 				b = 0;
 				in_range = 1;
-				exp_digit = 1;
 				continue;
 			}
 
@@ -658,16 +657,18 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen,
 			b = b * 10 + (c - '0');
 			if (!in_range)
 				a = b;
-			exp_digit = 0;
+			at_start = 0;
 			totaldigits++;
 		}
 		if (!(a <= b))
 			return -EINVAL;
 		if (b >= nmaskbits)
 			return -ERANGE;
-		while (a <= b) {
-			set_bit(a, maskp);
-			a++;
+		if (!at_start) {
+			while (a <= b) {
+				set_bit(a, maskp);
+				a++;
+			}
 		}
 	} while (buflen && c == ',');
 	return 0;
diff --git a/lib/checksum.c b/lib/checksum.c
index 129775eb6de..8b39e86dbab 100644
--- a/lib/checksum.c
+++ b/lib/checksum.c
@@ -181,6 +181,15 @@ csum_partial_copy(const void *src, void *dst, int len, __wsum sum)
 EXPORT_SYMBOL(csum_partial_copy);
 
 #ifndef csum_tcpudp_nofold
+static inline u32 from64to32(u64 x)
+{
+	/* add up 32-bit and 32-bit for 32+c bit */
+	x = (x & 0xffffffff) + (x >> 32);
+	/* add up carry.. */
+	x = (x & 0xffffffff) + (x >> 32);
+	return (u32)x;
+}
+
 __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 			unsigned short len,
 			unsigned short proto,
@@ -195,8 +204,7 @@ __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 #else
 	s += (proto + len) << 8;
 #endif
-	s += (s >> 32);
-	return (__force __wsum)s;
+	return (__force __wsum)from64to32(s);
 }
 EXPORT_SYMBOL(csum_tcpudp_nofold);
 #endif
diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c
index 8290e0bef7e..6dd0335ea61 100644
--- a/lib/decompress_bunzip2.c
+++ b/lib/decompress_bunzip2.c
@@ -184,7 +184,7 @@ static int INIT get_next_block(struct bunzip_data *bd)
 	if (get_bits(bd, 1))
 		return RETVAL_OBSOLETE_INPUT;
 	origPtr = get_bits(bd, 24);
-	if (origPtr > dbufSize)
+	if (origPtr >= dbufSize)
 		return RETVAL_DATA_ERROR;
 	/* mapping table: if some byte values are never used (encoding things
 	   like ascii text), the compression code removes the gaps to have fewer
diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
index 7a85967060a..f0f5c5c3de1 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -139,6 +139,9 @@ static int lz4_uncompress(const char *source, char *dest, int osize)
 			/* Error: request to write beyond destination buffer */
 			if (cpy > oend)
 				goto _output_error;
+			if ((ref + COPYLENGTH) > oend ||
+					(op + COPYLENGTH) > oend)
+				goto _output_error;
 			LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH));
 			while (op < cpy)
 				*op++ = *ref++;
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 624a0b7c05e..cb22073fe68 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -61,6 +61,8 @@ static u32 __hashfn(const struct rhashtable *ht, const void *key,
  * Computes the hash value using the hash function provided in the 'hashfn'
  * of struct rhashtable_params. The returned value is guaranteed to be
  * smaller than the number of buckets in the hash table.
+ *
+ * The caller must ensure that no concurrent table mutations occur.
  */
 u32 rhashtable_hashfn(const struct rhashtable *ht, const void *key, u32 len)
 {
@@ -92,6 +94,8 @@ static u32 obj_hashfn(const struct rhashtable *ht, const void *ptr, u32 hsize)
  * 'obj_hashfn' depending on whether the hash table is set up to work with
  * a fixed length key. The returned value is guaranteed to be smaller than
  * the number of buckets in the hash table.
+ *
+ * The caller must ensure that no concurrent table mutations occur.
  */
 u32 rhashtable_obj_hashfn(const struct rhashtable *ht, void *ptr)
 {
@@ -474,7 +478,7 @@ EXPORT_SYMBOL_GPL(rhashtable_lookup);
 /**
  * rhashtable_lookup_compare - search hash table with compare function
  * @ht:		hash table
- * @hash:	hash value of desired entry
+ * @key:	pointer to key
  * @compare:	compare function, must return true on match
  * @arg:	argument passed on to compare function
  *
@@ -486,14 +490,14 @@ EXPORT_SYMBOL_GPL(rhashtable_lookup);
  *
  * Returns the first entry on which the compare function returned true.
  */
-void *rhashtable_lookup_compare(const struct rhashtable *ht, u32 hash,
+void *rhashtable_lookup_compare(const struct rhashtable *ht, void *key,
 				bool (*compare)(void *, void *), void *arg)
 {
 	const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
 	struct rhash_head *he;
+	u32 hash;
 
-	if (unlikely(hash >= tbl->size))
-		return NULL;
+	hash = __hashfn(ht, key, ht->p.key_len, tbl->size);
 
 	rht_for_each_rcu(he, tbl->buckets[hash], ht) {
 		if (!compare(rht_obj(ht, he), arg))
diff --git a/lib/string.c b/lib/string.c
index 10063300b83..643b0a90802 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -610,7 +610,7 @@ EXPORT_SYMBOL(memset);
 void memzero_explicit(void *s, size_t count)
 {
 	memset(s, 0, count);
-	OPTIMIZER_HIDE_VAR(s);
+	barrier();
 }
 EXPORT_SYMBOL(memzero_explicit);
 
diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c
index a28df5206d9..11649615c50 100644
--- a/lib/strnlen_user.c
+++ b/lib/strnlen_user.c
@@ -57,7 +57,8 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count,
 			return res + find_zero(data) + 1 - align;
 		}
 		res += sizeof(unsigned long);
-		if (unlikely(max < sizeof(unsigned long)))
+		/* We already handled 'unsigned long' bytes. Did we do it all ? */
+		if (unlikely(max <= sizeof(unsigned long)))
 			break;
 		max -= sizeof(unsigned long);
 		if (unlikely(__get_user(c,(unsigned long __user *)(src+res))))
diff --git a/linaro/configs/android.conf b/linaro/configs/android.conf
new file mode 100644
index 00000000000..06c0af0f85d
--- /dev/null
+++ b/linaro/configs/android.conf
@@ -0,0 +1,194 @@
+CONFIG_IPV6=y
+# CONFIG_IPV6_SIT is not set
+CONFIG_PANIC_TIMEOUT=0
+CONFIG_HAS_WAKELOCK=y
+CONFIG_WAKELOCK=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_DM_CRYPT=y
+CONFIG_POWER_SUPPLY=y
+CONFIG_ANDROID_PARANOID_NETWORK=y
+CONFIG_NET_ACTIVITY_STATS=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_UINPUT=y
+CONFIG_INPUT_GPIO=y
+CONFIG_USB_G_ANDROID=y
+CONFIG_SWITCH=y
+CONFIG_STAGING=y
+CONFIG_ANDROID=y
+CONFIG_ANDROID_BINDER_IPC=y
+CONFIG_ASHMEM=y
+CONFIG_ANDROID_LOGGER=y
+CONFIG_ANDROID_TIMED_OUTPUT=y
+CONFIG_ANDROID_TIMED_GPIO=y
+CONFIG_ANDROID_LOW_MEMORY_KILLER=y
+CONFIG_ANDROID_INTF_ALARM_DEV=y
+CONFIG_CRYPTO_TWOFISH=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_COUNT=16
+CONFIG_BLK_DEV_RAM_SIZE=16384
+CONFIG_FUSE_FS=y
+CONFIG_CPU_FREQ_GOV_INTERACTIVE=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE=y
+CONFIG_ION=y
+CONFIG_SYNC=y
+CONFIG_SW_SYNC=y
+CONFIG_SW_SYNC_USER=y
+CONFIG_ION_TEST=y
+CONFIG_ION_DUMMY=y
+CONFIG_ADF=y
+CONFIG_ADF_FBDEV=y
+CONFIG_ADF_MEMBLOCK=y
+CONFIG_DMA_SHARED_BUFFER=y
+CONFIG_TUN=y
+CONFIG_NETFILTER_NETLINK=y
+CONFIG_NETFILTER_NETLINK_QUEUE=y
+CONFIG_NETFILTER_NETLINK_LOG=y
+CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_MARK=y
+CONFIG_NF_CONNTRACK_PROCFS=y
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_GRE=y
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
+CONFIG_NF_CONNTRACK_AMANDA=y
+CONFIG_NF_CONNTRACK_FTP=y
+CONFIG_NF_CONNTRACK_H323=y
+CONFIG_NF_CONNTRACK_IRC=y
+CONFIG_NF_CONNTRACK_BROADCAST=y
+CONFIG_NF_CONNTRACK_NETBIOS_NS=y
+CONFIG_NF_CONNTRACK_PPTP=y
+CONFIG_NF_CONNTRACK_SANE=y
+CONFIG_NF_CONNTRACK_TFTP=y
+CONFIG_NF_CT_NETLINK=y
+CONFIG_NF_NAT=y
+CONFIG_NF_NAT_NEEDED=y
+CONFIG_NF_NAT_PROTO_DCCP=y
+CONFIG_NF_NAT_PROTO_UDPLITE=y
+CONFIG_NF_NAT_PROTO_SCTP=y
+CONFIG_NF_NAT_AMANDA=y
+CONFIG_NF_NAT_FTP=y
+CONFIG_NF_NAT_IRC=y
+CONFIG_NF_NAT_TFTP=y
+CONFIG_NETFILTER_TPROXY=y
+CONFIG_NETFILTER_XTABLES=y
+CONFIG_NETFILTER_XT_MARK=y
+CONFIG_NETFILTER_XT_CONNMARK=y
+CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y
+CONFIG_NETFILTER_XT_TARGET_CONNMARK=y
+CONFIG_NETFILTER_XT_TARGET_MARK=y
+CONFIG_NETFILTER_XT_TARGET_NETMAP=y
+CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y
+CONFIG_NETFILTER_XT_TARGET_REDIRECT=y
+CONFIG_NETFILTER_XT_TARGET_TPROXY=y
+CONFIG_NETFILTER_XT_TARGET_TRACE=y
+CONFIG_NETFILTER_XT_MATCH_COMMENT=y
+CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_CONNMARK=y
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
+CONFIG_NETFILTER_XT_MATCH_ECN=y
+CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_HELPER=y
+CONFIG_NETFILTER_XT_MATCH_HL=y
+CONFIG_NETFILTER_XT_MATCH_IPRANGE=y
+CONFIG_NETFILTER_XT_MATCH_LENGTH=y
+CONFIG_NETFILTER_XT_MATCH_LIMIT=y
+CONFIG_NETFILTER_XT_MATCH_MAC=y
+CONFIG_NETFILTER_XT_MATCH_MARK=y
+CONFIG_NETFILTER_XT_MATCH_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
+CONFIG_NETFILTER_XT_MATCH_QTAGUID=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA2=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG=y
+CONFIG_NETFILTER_XT_MATCH_SOCKET=y
+CONFIG_NETFILTER_XT_MATCH_STATE=y
+CONFIG_NETFILTER_XT_MATCH_STATISTIC=y
+CONFIG_NETFILTER_XT_MATCH_STRING=y
+CONFIG_NETFILTER_XT_MATCH_TIME=y
+CONFIG_NETFILTER_XT_MATCH_U32=y
+CONFIG_NF_DEFRAG_IPV4=y
+CONFIG_NF_CONNTRACK_IPV4=y
+CONFIG_NF_CONNTRACK_PROC_COMPAT=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_MATCH_AH=y
+CONFIG_IP_NF_MATCH_ECN=y
+CONFIG_IP_NF_MATCH_TTL=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_IP_NF_TARGET_REJECT_SKERR=y
+CONFIG_NF_NAT_IPV4=y
+CONFIG_IP_NF_TARGET_MASQUERADE=y
+CONFIG_IP_NF_TARGET_NETMAP=y
+CONFIG_IP_NF_TARGET_REDIRECT=y
+CONFIG_NF_NAT_PROTO_GRE=y
+CONFIG_NF_NAT_PPTP=y
+CONFIG_NF_NAT_H323=y
+CONFIG_IP_NF_MANGLE=y
+CONFIG_IP_NF_RAW=y
+CONFIG_IP_NF_ARPTABLES=y
+CONFIG_IP_NF_ARPFILTER=y
+CONFIG_IP_NF_ARP_MANGLE=y
+CONFIG_NF_DEFRAG_IPV6=y
+CONFIG_NF_CONNTRACK_IPV6=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_TARGET_REJECT=y
+CONFIG_IP6_NF_TARGET_REJECT_SKERR=y
+CONFIG_IP6_NF_MANGLE=y
+CONFIG_IP6_NF_RAW=y
+CONFIG_TEXTSEARCH=y
+CONFIG_TEXTSEARCH_KMP=y
+CONFIG_TEXTSEARCH_BM=y
+CONFIG_TEXTSEARCH_FSM=y
+CONFIG_SWP_EMULATE=y
+CONFIG_ARMV7_COMPAT=y
+CONFIG_ARMV7_COMPAT_CPUINFO=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_DEBUG=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_RESOURCE_COUNTERS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_PREEMPT=y
+CONFIG_PM_AUTOSLEEP=y
+CONFIG_PM_WAKELOCKS=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_INET_ESP=y
+CONFIG_IPV6_PRIVACY=y
+CONFIG_IPV6_ROUTER_PREF=y
+CONFIG_IPV6_OPTIMISTIC_DAD=y
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
+CONFIG_INET6_IPCOMP=y
+CONFIG_IPV6_MIP6=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_NETFILTER_XT_TARGET_NFLOG=y
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_HTB=y
+CONFIG_NET_CLS_U32=y
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_U32=y
+CONFIG_NET_CLS_ACT=y
+CONFIG_PPP=y
+CONFIG_PPP_BSDCOMP=y
+CONFIG_PPP_DEFLATE=y
+CONFIG_PPP_MPPE=y
+CONFIG_PPPOLAC=y
+CONFIG_PPPOPNS=y
+CONFIG_KALLSYMS_ALL=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_PM_WAKELOCKS_LIMIT=0
+# CONFIG_PM_WAKELOCKS_GC is not set
+CONFIG_PM_RUNTIME=y
+CONFIG_PM_DEBUG=y
+CONFIG_SUSPEND_TIME=y
+CONFIG_UID_STAT=y
+CONFIG_DM_UEVENT=y
+# CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_MEDIA_SUPPORT=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_SCHED_TRACER=y
diff --git a/linaro/configs/arndale.conf b/linaro/configs/arndale.conf
new file mode 100644
index 00000000000..109052f2f6e
--- /dev/null
+++ b/linaro/configs/arndale.conf
@@ -0,0 +1,66 @@
+CONFIG_KALLSYMS_ALL=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_ARCH_EXYNOS=y
+CONFIG_S3C_LOWLEVEL_UART_PORT=2
+CONFIG_ARCH_EXYNOS5=y
+# CONFIG_EXYNOS_ATAGS is not set
+CONFIG_MACH_EXYNOS4_DT=y
+CONFIG_VMSPLIT_2G=y
+CONFIG_NR_CPUS=2
+CONFIG_HIGHMEM=y
+# CONFIG_COMPACTION is not set
+CONFIG_ARM_APPENDED_DTB=y
+CONFIG_ARM_ATAG_DTB_COMPAT=y
+CONFIG_CMDLINE="root=/dev/ram0 rw ramdisk=8192 initrd=0x41000000,8M console=ttySAC1,115200 init= mem=256M"
+CONFIG_CPU_FREQ_GOV_USERSPACE=y
+CONFIG_VFP=y
+CONFIG_NEON=y
+CONFIG_PM_RUNTIME=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_CHR_DEV_SG=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_SATA_EXYNOS=y
+CONFIG_AX88796=y
+CONFIG_AX88796_93CX6=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_KEYBOARD_GPIO=y
+CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_SAMSUNG=y
+CONFIG_SERIAL_SAMSUNG_CONSOLE=y
+CONFIG_HW_RANDOM=y
+CONFIG_I2C=y
+CONFIG_I2C_S3C2410=y
+CONFIG_THERMAL=y
+CONFIG_CPU_THERMAL=y
+CONFIG_EXYNOS_THERMAL=y
+CONFIG_MFD_SEC_CORE=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_REGULATOR_S5M8767=y
+CONFIG_DRM=y
+CONFIG_DRM_LOAD_EDID_FIRMWARE=y
+CONFIG_DRM_EXYNOS=y
+CONFIG_DRM_EXYNOS_DMABUF=y
+CONFIG_DRM_EXYNOS_HDMI=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_LOGO=y
+CONFIG_MMC=y
+CONFIG_MMC_UNSAFE_RESUME=y
+CONFIG_MMC_DW=y
+CONFIG_MMC_DW_IDMAC=y
+CONFIG_MMC_DW_EXYNOS=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_S3C=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_DEBUG_RT_MUTEXES=y
+CONFIG_DEBUG_SPINLOCK=y
+CONFIG_DEBUG_INFO=y
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
+CONFIG_DEBUG_USER=y
+CONFIG_TUN=y
diff --git a/linaro/configs/big-LITTLE-IKS.conf b/linaro/configs/big-LITTLE-IKS.conf
new file mode 100644
index 00000000000..b067fde86ea
--- /dev/null
+++ b/linaro/configs/big-LITTLE-IKS.conf
@@ -0,0 +1,5 @@
+CONFIG_BIG_LITTLE=y
+CONFIG_BL_SWITCHER=y
+CONFIG_ARM_DT_BL_CPUFREQ=y
+CONFIG_ARM_VEXPRESS_BL_CPUFREQ=y
+CONFIG_CPU_FREQ_GOV_USERSPACE=y
diff --git a/linaro/configs/big-LITTLE-MP.conf b/linaro/configs/big-LITTLE-MP.conf
new file mode 100644
index 00000000000..fc1b64f8b09
--- /dev/null
+++ b/linaro/configs/big-LITTLE-MP.conf
@@ -0,0 +1,11 @@
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_FAIR_GROUP_SCHED=y
+CONFIG_NO_HZ=y
+CONFIG_SCHED_MC=y
+CONFIG_SCHED_HMP=y
+CONFIG_HMP_FAST_CPU_MASK=""
+CONFIG_HMP_SLOW_CPU_MASK=""
+CONFIG_HMP_VARIABLE_SCALE=y
+CONFIG_HMP_FREQUENCY_INVARIANT_SCALE=y
+CONFIG_SCHED_HMP_LITTLE_PACKING=y
diff --git a/linaro/configs/bigendian.conf b/linaro/configs/bigendian.conf
new file mode 100644
index 00000000000..6a1020299e8
--- /dev/null
+++ b/linaro/configs/bigendian.conf
@@ -0,0 +1,4 @@
+CONFIG_CPU_BIG_ENDIAN=y
+CONFIG_CPU_ENDIAN_BE8=y
+# CONFIG_VIRTUALIZATION is not set
+# CONFIG_MMC_DW_IDMAC is not set
diff --git a/linaro/configs/distribution.conf b/linaro/configs/distribution.conf
new file mode 100644
index 00000000000..b1d96acfb15
--- /dev/null
+++ b/linaro/configs/distribution.conf
@@ -0,0 +1,62 @@
+CONFIG_CGROUPS=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_DEFAULT_MMAP_MIN_ADDR=32768
+CONFIG_SECCOMP=y
+CONFIG_CC_STACKPROTECTOR_REGULAR=y
+CONFIG_SYN_COOKIES=y
+CONFIG_IPV6=m
+CONFIG_NETLABEL=y
+CONFIG_BRIDGE_NETFILTER=y
+CONFIG_NF_CONNTRACK=m
+CONFIG_NF_CT_NETLINK=m
+CONFIG_NETFILTER_NETLINK=m
+CONFIG_NETFILTER_NETLINK_LOG=m
+CONFIG_NETFILTER_XT_CONNMARK=m
+CONFIG_NETFILTER_XT_MARK=m
+CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
+CONFIG_NETFILTER_XT_MATCH_LIMIT=m
+CONFIG_NETFILTER_XT_MATCH_MAC=m
+CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
+CONFIG_NETFILTER_XT_MATCH_STATE=m
+CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
+CONFIG_NETFILTER_XT_TARGET_LOG=m
+CONFIG_NETFILTER_XT_TARGET_REDIRECT=m
+CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_NAT_IPV4=m
+CONFIG_IP_NF_TARGET_MASQUERADE=m
+CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_MANGLE=m
+CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_NAT_IPV6=m
+CONFIG_IP6_NF_TARGET_MASQUERADE=m
+CONFIG_IP6_NF_IPTABLES=m
+CONFIG_IP6_NF_FILTER=m
+CONFIG_IP6_NF_MANGLE=m
+CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_BRIDGE_NF_EBTABLES=m
+CONFIG_BRIDGE_EBT_T_FILTER=m
+CONFIG_BRIDGE_EBT_T_NAT=m
+CONFIG_BRIDGE_EBT_MARK_T=m
+CONFIG_BRIDGE=m
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=65536
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_UINPUT=y
+# CONFIG_DEVKMEM is not set
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_STRICT_DEVMEM=y
+CONFIG_SECURITY=y
+CONFIG_LSM_MMAP_MIN_ADDR=0
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SECURITY_SMACK=y
+CONFIG_SECURITY_APPARMOR=y
+CONFIG_DEFAULT_SECURITY_APPARMOR=y
+CONFIG_OF_SELFTEST=y
diff --git a/linaro/configs/kvm-guest.conf b/linaro/configs/kvm-guest.conf
new file mode 100644
index 00000000000..00e84a3ba1e
--- /dev/null
+++ b/linaro/configs/kvm-guest.conf
@@ -0,0 +1,11 @@
+CONFIG_BALLOON_COMPACTION=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_NET=y
+CONFIG_HVC_DRIVER=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_VIRTIO=y
+CONFIG_VIRTIO_BALLOON=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
+CONFIG_VIRTUALIZATION=y
+# CONFIG_THUMB2_KERNEL is not set
diff --git a/linaro/configs/kvm-host.conf b/linaro/configs/kvm-host.conf
new file mode 100644
index 00000000000..21a40e03137
--- /dev/null
+++ b/linaro/configs/kvm-host.conf
@@ -0,0 +1,11 @@
+CONFIG_VIRTUALIZATION=y
+CONFIG_ARM_LPAE=y
+CONFIG_ARM_VIRT_EXT=y
+CONFIG_HAVE_KVM_IRQCHIP=y
+CONFIG_KVM_ARM_HOST=y
+CONFIG_KVM_ARM_MAX_VCPUS=4
+CONFIG_KVM_ARM_TIMER=y
+CONFIG_KVM_ARM_VGIC=y
+CONFIG_KVM_MMIO=y
+CONFIG_KVM=y
+CONFIG_BLK_DEV_NBD=m
diff --git a/linaro/configs/linaro-base.conf b/linaro/configs/linaro-base.conf
new file mode 100644
index 00000000000..0a1d7bcd63a
--- /dev/null
+++ b/linaro/configs/linaro-base.conf
@@ -0,0 +1,129 @@
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=16
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EMBEDDED=y
+CONFIG_HOTPLUG=y
+CONFIG_PERF_EVENTS=y
+CONFIG_SLAB=y
+CONFIG_PROFILING=y
+CONFIG_OPROFILE=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_SMP=y
+CONFIG_SCHED_MC=y
+CONFIG_SCHED_SMT=y
+CONFIG_THUMB2_KERNEL=y
+CONFIG_AEABI=y
+# CONFIG_OABI_COMPAT is not set
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
+CONFIG_CPU_IDLE=y
+CONFIG_BINFMT_MISC=y
+CONFIG_MD=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=y
+CONFIG_NET_KEY=y
+CONFIG_NET_KEY_MIGRATE=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+# CONFIG_INET_LRO is not set
+CONFIG_NETFILTER=y
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_CONNECTOR=y
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_OOPS=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_CFI_INTELEXT=y
+CONFIG_MTD_NAND=y
+CONFIG_NETDEVICES=y
+CONFIG_EXT2_FS=y
+CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
+CONFIG_BTRFS_FS=y
+CONFIG_QUOTA=y
+CONFIG_QFMT_V2=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_ECRYPT_FS=y
+CONFIG_JFFS2_FS=y
+CONFIG_JFFS2_SUMMARY=y
+CONFIG_JFFS2_FS_XATTR=y
+CONFIG_JFFS2_COMPRESSION_OPTIONS=y
+CONFIG_JFFS2_LZO=y
+CONFIG_JFFS2_RUBIN=y
+CONFIG_CRAMFS=y
+CONFIG_NETWORK_FILESYSTEMS=y
+CONFIG_NFS_FS=y
+# CONFIG_NFS_V2 is not set
+CONFIG_NFS_V3=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_PRINTK_TIME=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_FS=y
+CONFIG_SCHEDSTATS=y
+CONFIG_TIMER_STATS=y
+CONFIG_KEYS=y
+CONFIG_CRYPTO_MICHAEL_MIC=y
+CONFIG_CRC_CCITT=y
+CONFIG_CRC_T10DIF=y
+CONFIG_CRC_ITU_T=y
+CONFIG_CRC7=y
+CONFIG_HW_PERF_EVENTS=y
+CONFIG_FUNCTION_TRACER=y
+CONFIG_ENABLE_DEFAULT_TRACERS=y
+CONFIG_PROC_DEVICETREE=y
+CONFIG_JUMP_LABEL=y
+CONFIG_STRICT_DEVMEM=y
+CONFIG_KGDB=y
+CONFIG_KGDB_TESTS=y
+CONFIG_OF_IDLE_STATES=y
+CONFIG_FTRACE=y
+CONFIG_FUNCTION_TRACER=y
+CONFIG_FTRACE_SYSCALLS=y
+CONFIG_STACK_TRACER=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_MAILBOX=y
+CONFIG_AUDIT=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_IP_NF_SECURITY=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_LSM_MMAP_MIN_ADDR=4096
+CONFIG_SECURITY_SELINUX=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_DEBUG_INFO=y
+CONFIG_FANOTIFY=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_RCU_TORTURE_TEST_RUNNABLE=n
+CONFIG_CORESIGHT=y
+CONFIG_CORESIGHT_LINKS_AND_SINKS=y
+CONFIG_CORESIGHT_SOURCE_ETM=y
+
+# enable ZRAM features
+CONFIG_ZPOOL=y
+CONFIG_ZSMALLOC=y
+CONFIG_ZRAM=y
+CONFIG_ZRAM_LZ4_COMPRESS=y
diff --git a/linaro/configs/omap4.conf b/linaro/configs/omap4.conf
new file mode 100644
index 00000000000..d0a2b808ff1
--- /dev/null
+++ b/linaro/configs/omap4.conf
@@ -0,0 +1,196 @@
+CONFIG_EXPERT=y
+CONFIG_KPROBES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+CONFIG_MODULE_SRCVERSION_ALL=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_GPIO_PCA953X=y
+CONFIG_OMAP_RESET_CLOCKS=y
+CONFIG_OMAP_MUX_DEBUG=y
+CONFIG_ARCH_OMAP3=y
+CONFIG_ARCH_OMAP4=y
+CONFIG_ARCH_OMAP2PLUS=y
+CONFIG_SOC_OMAP5=y
+# CONFIG_ARCH_OMAP2 is not set
+CONFIG_ARCH_VEXPRESS_CA9X4=y
+CONFIG_ARM_THUMBEE=y
+CONFIG_ARM_ERRATA_411920=y
+CONFIG_NR_CPUS=2
+CONFIG_ZBOOT_ROM_TEXT=0x0
+CONFIG_ZBOOT_ROM_BSS=0x0
+CONFIG_CMDLINE="root=/dev/mmcblk0p2 rootwait console=ttyO2,115200"
+CONFIG_KEXEC=y
+CONFIG_PM_DEBUG=y
+CONFIG_CAN=m
+CONFIG_CAN_C_CAN=m
+CONFIG_CAN_C_CAN_PLATFORM=m
+CONFIG_BT=m
+CONFIG_BT_HCIUART=m
+CONFIG_BT_HCIUART_H4=y
+CONFIG_BT_HCIUART_BCSP=y
+CONFIG_BT_HCIUART_LL=y
+CONFIG_BT_HCIBCM203X=m
+CONFIG_BT_HCIBPA10X=m
+CONFIG_CFG80211=m
+CONFIG_MAC80211=m
+CONFIG_MAC80211_RC_PID=y
+CONFIG_MAC80211_RC_DEFAULT_PID=y
+CONFIG_CMA=y
+CONFIG_MTD_NAND_OMAP2=y
+CONFIG_MTD_ONENAND=y
+CONFIG_MTD_ONENAND_VERIFY_WRITE=y
+CONFIG_MTD_ONENAND_OMAP2=y
+CONFIG_MTD_UBI=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM_SIZE=16384
+CONFIG_SENSORS_TSL2550=m
+CONFIG_SENSORS_LIS3_I2C=m
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_SCSI_MULTI_LUN=y
+CONFIG_SCSI_SCAN_ASYNC=y
+CONFIG_KS8851=y
+CONFIG_KS8851_MLL=y
+CONFIG_SMC91X=y
+CONFIG_SMSC911X=y
+CONFIG_TI_CPSW=y
+CONFIG_SMSC_PHY=y
+CONFIG_USB_USBNET=y
+CONFIG_USB_NET_SMSC95XX=y
+CONFIG_USB_ALI_M5632=y
+CONFIG_USB_AN2720=y
+CONFIG_USB_EPSON2888=y
+CONFIG_USB_KC2190=y
+CONFIG_LIBERTAS=m
+CONFIG_LIBERTAS_USB=m
+CONFIG_LIBERTAS_SDIO=m
+CONFIG_LIBERTAS_DEBUG=y
+CONFIG_INPUT_JOYDEV=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_KEYBOARD_GPIO=y
+CONFIG_KEYBOARD_MATRIX=m
+CONFIG_KEYBOARD_TWL4030=y
+CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_TOUCHSCREEN_ADS7846=y
+CONFIG_INPUT_TWL4030_PWRBUTTON=y
+CONFIG_VT_HW_CONSOLE_BINDING=y
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=32
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_SHARE_IRQ=y
+CONFIG_SERIAL_8250_DETECT_IRQ=y
+CONFIG_SERIAL_8250_RSA=y
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_SERIAL_OMAP=y
+CONFIG_SERIAL_OMAP_CONSOLE=y
+CONFIG_HW_RANDOM=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_SPI=y
+CONFIG_SPI_OMAP24XX=y
+CONFIG_PINCTRL_SINGLE=y
+CONFIG_DEBUG_GPIO=y
+CONFIG_GPIO_SYSFS=y
+CONFIG_GPIO_TWL4030=y
+CONFIG_W1=y
+CONFIG_SENSORS_LM75=m
+CONFIG_WATCHDOG=y
+CONFIG_OMAP_WATCHDOG=y
+CONFIG_TWL4030_WATCHDOG=y
+CONFIG_MFD_TPS65217=y
+CONFIG_MFD_TPS65910=y
+CONFIG_TWL6040_CORE=y
+CONFIG_REGULATOR_TPS65023=y
+CONFIG_REGULATOR_TPS6507X=y
+CONFIG_REGULATOR_TPS65217=y
+CONFIG_REGULATOR_TPS65910=y
+CONFIG_REGULATOR_TWL4030=y
+CONFIG_FB=y
+CONFIG_FIRMWARE_EDID=y
+CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB_TILEBLITTING=y
+CONFIG_OMAP2_DSS=m
+CONFIG_OMAP2_DSS_RFBI=y
+CONFIG_OMAP2_DSS_SDI=y
+CONFIG_OMAP2_DSS_DSI=y
+CONFIG_FB_OMAP2=m
+CONFIG_PANEL_GENERIC_DPI=m
+CONFIG_PANEL_TFP410=m
+CONFIG_PANEL_SHARP_LS037V7DW01=m
+CONFIG_PANEL_NEC_NL8048HL11_01B=m
+CONFIG_PANEL_TAAL=m
+CONFIG_PANEL_TPO_TD043MTEA1=m
+CONFIG_PANEL_ACX565AKM=m
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+CONFIG_LCD_CLASS_DEVICE=y
+CONFIG_LCD_PLATFORM=y
+CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
+CONFIG_FONTS=y
+CONFIG_FONT_8x8=y
+CONFIG_FONT_8x16=y
+CONFIG_LOGO=y
+CONFIG_SOUND=m
+CONFIG_SND=m
+CONFIG_SND_VERBOSE_PRINTK=y
+CONFIG_SND_DEBUG=y
+CONFIG_SND_USB_AUDIO=m
+CONFIG_SND_SOC=m
+CONFIG_SND_OMAP_SOC=m
+CONFIG_SND_OMAP_SOC_OMAP_TWL4030=m
+CONFIG_SND_OMAP_SOC_OMAP_ABE_TWL6040=m
+CONFIG_SND_OMAP_SOC_OMAP3_PANDORA=m
+CONFIG_USB=y
+CONFIG_USB_DEBUG=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_MON=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_WDM=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_TEST=y
+CONFIG_USB_PHY=y
+CONFIG_NOP_USB_XCEIV=y
+CONFIG_USB_GADGET=y
+CONFIG_USB_GADGET_DEBUG=y
+CONFIG_USB_GADGET_DEBUG_FILES=y
+CONFIG_USB_GADGET_DEBUG_FS=y
+CONFIG_USB_ZERO=m
+CONFIG_MMC=y
+CONFIG_MMC_UNSAFE_RESUME=y
+CONFIG_SDIO_UART=y
+CONFIG_MMC_ARMMMCI=y
+CONFIG_MMC_OMAP=y
+CONFIG_MMC_OMAP_HS=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_TIMER=y
+CONFIG_LEDS_TRIGGER_ONESHOT=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_LEDS_TRIGGER_BACKLIGHT=y
+CONFIG_LEDS_TRIGGER_CPU=y
+CONFIG_LEDS_TRIGGER_GPIO=y
+CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_TWL92330=y
+CONFIG_RTC_DRV_TWL4030=y
+CONFIG_RTC_DRV_OMAP=y
+CONFIG_DMADEVICES=y
+CONFIG_DMA_OMAP=y
+# CONFIG_EXT3_FS_XATTR is not set
+CONFIG_UBIFS_FS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+# CONFIG_DEBUG_BUGVERBOSE is not set
+CONFIG_DEBUG_INFO=y
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+CONFIG_LIBCRC32C=y
+# CONFIG_CPU_FREQ is not set
diff --git a/linaro/configs/preempt-rt.conf b/linaro/configs/preempt-rt.conf
new file mode 100644
index 00000000000..7c6594f3a01
--- /dev/null
+++ b/linaro/configs/preempt-rt.conf
@@ -0,0 +1,3 @@
+CONFIG_PREEMPT=y
+CONFIG_PREEMPT_RT_FULL=y
+# CONFIG_CPU_FREQ is not set
diff --git a/linaro/configs/selinux.conf b/linaro/configs/selinux.conf
new file mode 100644
index 00000000000..6a38da1fb2f
--- /dev/null
+++ b/linaro/configs/selinux.conf
@@ -0,0 +1,12 @@
+CONFIG_AUDIT=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SECURITY=y
+
+CONFIG_SECURITY_SELINUX_BOOTPARAM=y
+CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=1
+CONFIG_SECURITY_SELINUX_DISABLE=y
+
+CONFIG_IKCONFIG_PROC=n
diff --git a/linaro/configs/vexpress.conf b/linaro/configs/vexpress.conf
new file mode 100644
index 00000000000..b40f4c4f8f1
--- /dev/null
+++ b/linaro/configs/vexpress.conf
@@ -0,0 +1,66 @@
+CONFIG_ARCH_VEXPRESS=y
+CONFIG_ARCH_VEXPRESS_CA9X4=y
+CONFIG_HAVE_ARM_ARCH_TIMER=y
+CONFIG_NR_CPUS=8
+CONFIG_HIGHMEM=y
+CONFIG_HIGHPTE=y
+CONFIG_ARM_PSCI=y
+CONFIG_MCPM=y
+CONFIG_ARCH_VEXPRESS_DCSCB=y
+CONFIG_ARCH_VEXPRESS_TC2_PM=y
+CONFIG_ARM_BIG_LITTLE_CPUIDLE=y
+CONFIG_BIG_LITTLE=y
+CONFIG_ARM_BIG_LITTLE_CPUFREQ=y
+CONFIG_ARM_VEXPRESS_SPC_CPUFREQ=y
+CONFIG_PM_OPP=y
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_GOV_ONDEMAND=y
+CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
+CONFIG_CPU_FREQ_GOV_INTERACTIVE=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
+CONFIG_CMDLINE="console=ttyAMA0,38400n8 root=/dev/mmcblk0p2 rootwait mmci.fmax=4000000"
+CONFIG_VFP=y
+CONFIG_NEON=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_SMSC911X=y
+CONFIG_SMC91X=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_SERIO_AMBAKMI=y
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_FB=y
+CONFIG_FB_ARMCLCD=y
+CONFIG_FB_ARMHDLCD=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_SND_ARMAACI=y
+CONFIG_USB=y
+CONFIG_USB_ISP1760_HCD=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_ARMMMCI=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_PL031=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_VEXPRESS_CONFIG=y
+CONFIG_SENSORS_VEXPRESS=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_VEXPRESS=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_LEDS_TRIGGER_CPU=y
+CONFIG_VIRTIO=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
diff --git a/linaro/configs/vexpress64.conf b/linaro/configs/vexpress64.conf
new file mode 100644
index 00000000000..85c4f3e67a1
--- /dev/null
+++ b/linaro/configs/vexpress64.conf
@@ -0,0 +1,71 @@
+CONFIG_ARCH_VEXPRESS=y
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT=y
+CONFIG_CMDLINE="console=ttyAMA0"
+CONFIG_COMPAT=y
+CONFIG_SMC91X=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_SERIO_AMBAKMI=y
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+# CONFIG_SERIO_I8042 is not set
+CONFIG_FB=y
+CONFIG_FB_ARMCLCD=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_MMC=y
+CONFIG_MMC_ARMMMCI=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_PL031=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_VIRTIO=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
+# CONFIG_DEBUG_PREEMPT is not set
+CONFIG_SMSC911X=y
+CONFIG_I2C=y
+CONFIG_I2C_DESIGNWARE_PLATFORM=y
+CONFIG_USB_HIDDEV=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB=y
+CONFIG_USB_ULPI=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_NOP_USB_XCEIV=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_ARM64_CPUIDLE=y
+CONFIG_MAILBOX=y
+CONFIG_ARM_MHU=y
+CONFIG_ARM_SCPI_PROTOCOL=y
+CONFIG_COMMON_CLK_SCPI=y
+CONFIG_ARM_SCPI_CPUFREQ=y
+CONFIG_ARM_BIG_LITTLE_CPUFREQ=y
+CONFIG_ARM_DT_BL_CPUFREQ=y
+CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
+CONFIG_CPU_FREQ_GOV_USERSPACE=y
+CONFIG_CPU_FREQ_GOV_ONDEMAND=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
+CONFIG_THERMAL=y
+CONFIG_THERMAL_DEFAULT_GOV_POWER_ALLOCATOR=y
+CONFIG_THERMAL_GOV_USER_SPACE=y
+CONFIG_CPU_THERMAL=y
+CONFIG_SCPI_THERMAL=y
+CONFIG_THERMAL_WRITABLE_TRIPS=y
+CONFIG_PM_DEVFREQ=y
+CONFIG_DEVFREQ_THERMAL=y
+CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y
+CONFIG_DEVFREQ_GOV_PERFORMANCE=y
+CONFIG_MALI_DEVFREQ=y
diff --git a/mm/cma.c b/mm/cma.c
index fde706e1284..8e9ec13d31d 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -215,9 +215,21 @@ int __init cma_declare_contiguous(phys_addr_t base,
 			bool fixed, struct cma **res_cma)
 {
 	phys_addr_t memblock_end = memblock_end_of_DRAM();
-	phys_addr_t highmem_start = __pa(high_memory);
+	phys_addr_t highmem_start;
 	int ret = 0;
 
+#ifdef CONFIG_X86
+	/*
+	 * high_memory isn't direct mapped memory so retrieving its physical
+	 * address isn't appropriate.  But it would be useful to check the
+	 * physical address of the highmem boundary so it's justfiable to get
+	 * the physical address from it.  On x86 there is a validation check for
+	 * this case, so the following workaround is needed to avoid it.
+	 */
+	highmem_start = __pa_nodebug(high_memory);
+#else
+	highmem_start = __pa(high_memory);
+#endif
 	pr_debug("%s(size %pa, base %pa, limit %pa alignment %pa)\n",
 		__func__, &size, &base, &limit, &alignment);
 
diff --git a/mm/compaction.c b/mm/compaction.c
index f9792ba3537..b47f08e159d 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1027,8 +1027,10 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 		low_pfn = isolate_migratepages_block(cc, low_pfn, end_pfn,
 								isolate_mode);
 
-		if (!low_pfn || cc->contended)
+		if (!low_pfn || cc->contended) {
+			acct_isolated(zone, cc);
 			return ISOLATE_ABORT;
+		}
 
 		/*
 		 * Either we isolated something and proceed with migration. Or
@@ -1100,7 +1102,7 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
 			return COMPACT_PARTIAL;
 
 		/* Job done if allocation would set block type */
-		if (cc->order >= pageblock_order && area->nr_free)
+		if (order >= pageblock_order && area->nr_free)
 			return COMPACT_PARTIAL;
 	}
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 14b4642279f..37beab98b41 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1046,8 +1046,7 @@ EXPORT_SYMBOL(find_lock_entry);
  * @mapping: the address_space to search
  * @offset: the page index
  * @fgp_flags: PCG flags
- * @cache_gfp_mask: gfp mask to use for the page cache data page allocation
- * @radix_gfp_mask: gfp mask to use for radix tree node allocation
+ * @gfp_mask: gfp mask to use for the page cache data page allocation
  *
  * Looks up the page cache slot at @mapping & @offset.
  *
@@ -1056,11 +1055,9 @@ EXPORT_SYMBOL(find_lock_entry);
  * FGP_ACCESSED: the page will be marked accessed
  * FGP_LOCK: Page is return locked
  * FGP_CREAT: If page is not present then a new page is allocated using
- *		@cache_gfp_mask and added to the page cache and the VM's LRU
- *		list. If radix tree nodes are allocated during page cache
- *		insertion then @radix_gfp_mask is used. The page is returned
- *		locked and with an increased refcount. Otherwise, %NULL is
- *		returned.
+ *		@gfp_mask and added to the page cache and the VM's LRU
+ *		list. The page is returned locked and with an increased
+ *		refcount. Otherwise, %NULL is returned.
  *
  * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even
  * if the GFP flags specified for FGP_CREAT are atomic.
@@ -1068,7 +1065,7 @@ EXPORT_SYMBOL(find_lock_entry);
  * If there is a page cache page, it is returned with an increased refcount.
  */
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
-	int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask)
+	int fgp_flags, gfp_t gfp_mask)
 {
 	struct page *page;
 
@@ -1105,13 +1102,11 @@ no_page:
 	if (!page && (fgp_flags & FGP_CREAT)) {
 		int err;
 		if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping))
-			cache_gfp_mask |= __GFP_WRITE;
-		if (fgp_flags & FGP_NOFS) {
-			cache_gfp_mask &= ~__GFP_FS;
-			radix_gfp_mask &= ~__GFP_FS;
-		}
+			gfp_mask |= __GFP_WRITE;
+		if (fgp_flags & FGP_NOFS)
+			gfp_mask &= ~__GFP_FS;
 
-		page = __page_cache_alloc(cache_gfp_mask);
+		page = __page_cache_alloc(gfp_mask);
 		if (!page)
 			return NULL;
 
@@ -1122,7 +1117,8 @@ no_page:
 		if (fgp_flags & FGP_ACCESSED)
 			__SetPageReferenced(page);
 
-		err = add_to_page_cache_lru(page, mapping, offset, radix_gfp_mask);
+		err = add_to_page_cache_lru(page, mapping, offset,
+				gfp_mask & GFP_RECLAIM_MASK);
 		if (unlikely(err)) {
 			page_cache_release(page);
 			page = NULL;
@@ -2443,8 +2439,7 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping,
 		fgp_flags |= FGP_NOFS;
 
 	page = pagecache_get_page(mapping, index, fgp_flags,
-			mapping_gfp_mask(mapping),
-			GFP_KERNEL);
+			mapping_gfp_mask(mapping));
 	if (page)
 		wait_for_stable_page(page);
 
diff --git a/mm/gup.c b/mm/gup.c
index cd62c8c90d4..377a5a79624 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -167,10 +167,10 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 	if (pud_none(*pud))
 		return no_page_table(vma, flags);
 	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
-		if (flags & FOLL_GET)
-			return NULL;
-		page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
-		return page;
+		page = follow_huge_pud(mm, address, pud, flags);
+		if (page)
+			return page;
+		return no_page_table(vma, flags);
 	}
 	if (unlikely(pud_bad(*pud)))
 		return no_page_table(vma, flags);
@@ -179,19 +179,10 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 	if (pmd_none(*pmd))
 		return no_page_table(vma, flags);
 	if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
-		page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
-		if (flags & FOLL_GET) {
-			/*
-			 * Refcount on tail pages are not well-defined and
-			 * shouldn't be taken. The caller should handle a NULL
-			 * return when trying to follow tail pages.
-			 */
-			if (PageHead(page))
-				get_page(page);
-			else
-				page = NULL;
-		}
-		return page;
+		page = follow_huge_pmd(mm, address, pmd, flags);
+		if (page)
+			return page;
+		return no_page_table(vma, flags);
 	}
 	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
 		return no_page_table(vma, flags);
@@ -296,7 +287,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 			return -ENOMEM;
 		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
 			return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT;
-		if (ret & VM_FAULT_SIGBUS)
+		if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
 			return -EFAULT;
 		BUG();
 	}
@@ -571,7 +562,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 			return -ENOMEM;
 		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
 			return -EHWPOISON;
-		if (ret & VM_FAULT_SIGBUS)
+		if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
 			return -EFAULT;
 		BUG();
 	}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9fd72276992..da8fa4e4237 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2653,9 +2653,10 @@ again:
 			goto unlock;
 
 		/*
-		 * HWPoisoned hugepage is already unmapped and dropped reference
+		 * Migrating hugepage or HWPoisoned hugepage is already
+		 * unmapped and its refcount is dropped, so just clear pte here.
 		 */
-		if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) {
+		if (unlikely(!pte_present(pte))) {
 			huge_pte_clear(mm, address, ptep);
 			goto unlock;
 		}
@@ -3128,6 +3129,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *pagecache_page = NULL;
 	struct hstate *h = hstate_vma(vma);
 	struct address_space *mapping;
+	int need_wait_lock = 0;
 
 	address &= huge_page_mask(h);
 
@@ -3166,6 +3168,16 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	ret = 0;
 
 	/*
+	 * entry could be a migration/hwpoison entry at this point, so this
+	 * check prevents the kernel from going below assuming that we have
+	 * a active hugepage in pagecache. This goto expects the 2nd page fault,
+	 * and is_hugetlb_entry_(migration|hwpoisoned) check will properly
+	 * handle it.
+	 */
+	if (!pte_present(entry))
+		goto out_mutex;
+
+	/*
 	 * If we are going to COW the mapping later, we examine the pending
 	 * reservations for this page now. This will ensure that any
 	 * allocations necessary to record that reservation occur outside the
@@ -3184,30 +3196,31 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 								vma, address);
 	}
 
+	ptl = huge_pte_lock(h, mm, ptep);
+
+	/* Check for a racing update before calling hugetlb_cow */
+	if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
+		goto out_ptl;
+
 	/*
 	 * hugetlb_cow() requires page locks of pte_page(entry) and
 	 * pagecache_page, so here we need take the former one
 	 * when page != pagecache_page or !pagecache_page.
-	 * Note that locking order is always pagecache_page -> page,
-	 * so no worry about deadlock.
 	 */
 	page = pte_page(entry);
-	get_page(page);
 	if (page != pagecache_page)
-		lock_page(page);
-
-	ptl = huge_pte_lockptr(h, mm, ptep);
-	spin_lock(ptl);
-	/* Check for a racing update before calling hugetlb_cow */
-	if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
-		goto out_ptl;
+		if (!trylock_page(page)) {
+			need_wait_lock = 1;
+			goto out_ptl;
+		}
 
+	get_page(page);
 
 	if (flags & FAULT_FLAG_WRITE) {
 		if (!huge_pte_write(entry)) {
 			ret = hugetlb_cow(mm, vma, address, ptep, entry,
 					pagecache_page, ptl);
-			goto out_ptl;
+			goto out_put_page;
 		}
 		entry = huge_pte_mkdirty(entry);
 	}
@@ -3215,7 +3228,10 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (huge_ptep_set_access_flags(vma, address, ptep, entry,
 						flags & FAULT_FLAG_WRITE))
 		update_mmu_cache(vma, address, ptep);
-
+out_put_page:
+	if (page != pagecache_page)
+		unlock_page(page);
+	put_page(page);
 out_ptl:
 	spin_unlock(ptl);
 
@@ -3223,12 +3239,17 @@ out_ptl:
 		unlock_page(pagecache_page);
 		put_page(pagecache_page);
 	}
-	if (page != pagecache_page)
-		unlock_page(page);
-	put_page(page);
-
 out_mutex:
 	mutex_unlock(&htlb_fault_mutex_table[hash]);
+	/*
+	 * Generally it's safe to hold refcount during waiting page lock. But
+	 * here we just wait to defer the next page fault to avoid busy loop and
+	 * the page is not used after unlocked before returning from the current
+	 * page fault. So we are safe from accessing freed page, even if we wait
+	 * here without taking refcount.
+	 */
+	if (need_wait_lock)
+		wait_on_page_locked(page);
 	return ret;
 }
 
@@ -3358,7 +3379,26 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 			spin_unlock(ptl);
 			continue;
 		}
-		if (!huge_pte_none(huge_ptep_get(ptep))) {
+		pte = huge_ptep_get(ptep);
+		if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) {
+			spin_unlock(ptl);
+			continue;
+		}
+		if (unlikely(is_hugetlb_entry_migration(pte))) {
+			swp_entry_t entry = pte_to_swp_entry(pte);
+
+			if (is_write_migration_entry(entry)) {
+				pte_t newpte;
+
+				make_migration_entry_read(&entry);
+				newpte = swp_entry_to_pte(entry);
+				set_huge_pte_at(mm, address, ptep, newpte);
+				pages++;
+			}
+			spin_unlock(ptl);
+			continue;
+		}
+		if (!huge_pte_none(pte)) {
 			pte = huge_ptep_get_and_clear(mm, address, ptep);
 			pte = pte_mkhuge(huge_pte_modify(pte, newprot));
 			pte = arch_make_huge_pte(pte, vma, NULL, 0);
@@ -3653,42 +3693,64 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	return (pte_t *) pmd;
 }
 
-struct page *
-follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-		pmd_t *pmd, int write)
-{
-	struct page *page;
+#endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */
 
-	page = pte_page(*(pte_t *)pmd);
-	if (page)
-		page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
-	return page;
+/*
+ * These functions are overwritable if your architecture needs its own
+ * behavior.
+ */
+struct page * __weak
+follow_huge_addr(struct mm_struct *mm, unsigned long address,
+			      int write)
+{
+	return ERR_PTR(-EINVAL);
 }
 
-struct page *
-follow_huge_pud(struct mm_struct *mm, unsigned long address,
-		pud_t *pud, int write)
+struct page * __weak
+follow_huge_pmd(struct mm_struct *mm, unsigned long address,
+		pmd_t *pmd, int flags)
 {
-	struct page *page;
-
-	page = pte_page(*(pte_t *)pud);
-	if (page)
-		page += ((address & ~PUD_MASK) >> PAGE_SHIFT);
+	struct page *page = NULL;
+	spinlock_t *ptl;
+retry:
+	ptl = pmd_lockptr(mm, pmd);
+	spin_lock(ptl);
+	/*
+	 * make sure that the address range covered by this pmd is not
+	 * unmapped from other threads.
+	 */
+	if (!pmd_huge(*pmd))
+		goto out;
+	if (pmd_present(*pmd)) {
+		page = pte_page(*(pte_t *)pmd) +
+			((address & ~PMD_MASK) >> PAGE_SHIFT);
+		if (flags & FOLL_GET)
+			get_page(page);
+	} else {
+		if (is_hugetlb_entry_migration(huge_ptep_get((pte_t *)pmd))) {
+			spin_unlock(ptl);
+			__migration_entry_wait(mm, (pte_t *)pmd, ptl);
+			goto retry;
+		}
+		/*
+		 * hwpoisoned entry is treated as no_page_table in
+		 * follow_page_mask().
+		 */
+	}
+out:
+	spin_unlock(ptl);
 	return page;
 }
 
-#else /* !CONFIG_ARCH_WANT_GENERAL_HUGETLB */
-
-/* Can be overriden by architectures */
 struct page * __weak
 follow_huge_pud(struct mm_struct *mm, unsigned long address,
-	       pud_t *pud, int write)
+		pud_t *pud, int flags)
 {
-	BUG();
-	return NULL;
-}
+	if (flags & FOLL_GET)
+		return NULL;
 
-#endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */
+	return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
+}
 
 #ifdef CONFIG_MEMORY_FAILURE
 
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 3cda50c1e39..1f14ef68a5c 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -193,6 +193,8 @@ static struct kmem_cache *scan_area_cache;
 
 /* set if tracing memory operations is enabled */
 static int kmemleak_enabled;
+/* same as above but only for the kmemleak_free() callback */
+static int kmemleak_free_enabled;
 /* set in the late_initcall if there were no errors */
 static int kmemleak_initialized;
 /* enables or disables early logging of the memory operations */
@@ -905,12 +907,13 @@ EXPORT_SYMBOL_GPL(kmemleak_alloc);
  * kmemleak_alloc_percpu - register a newly allocated __percpu object
  * @ptr:	__percpu pointer to beginning of the object
  * @size:	size of the object
+ * @gfp:	flags used for kmemleak internal memory allocations
  *
  * This function is called from the kernel percpu allocator when a new object
- * (memory block) is allocated (alloc_percpu). It assumes GFP_KERNEL
- * allocation.
+ * (memory block) is allocated (alloc_percpu).
  */
-void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size)
+void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size,
+				 gfp_t gfp)
 {
 	unsigned int cpu;
 
@@ -923,7 +926,7 @@ void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size)
 	if (kmemleak_enabled && ptr && !IS_ERR(ptr))
 		for_each_possible_cpu(cpu)
 			create_object((unsigned long)per_cpu_ptr(ptr, cpu),
-				      size, 0, GFP_KERNEL);
+				      size, 0, gfp);
 	else if (kmemleak_early_log)
 		log_early(KMEMLEAK_ALLOC_PERCPU, ptr, size, 0);
 }
@@ -940,7 +943,7 @@ void __ref kmemleak_free(const void *ptr)
 {
 	pr_debug("%s(0x%p)\n", __func__, ptr);
 
-	if (kmemleak_enabled && ptr && !IS_ERR(ptr))
+	if (kmemleak_free_enabled && ptr && !IS_ERR(ptr))
 		delete_object_full((unsigned long)ptr);
 	else if (kmemleak_early_log)
 		log_early(KMEMLEAK_FREE, ptr, 0, 0);
@@ -980,7 +983,7 @@ void __ref kmemleak_free_percpu(const void __percpu *ptr)
 
 	pr_debug("%s(0x%p)\n", __func__, ptr);
 
-	if (kmemleak_enabled && ptr && !IS_ERR(ptr))
+	if (kmemleak_free_enabled && ptr && !IS_ERR(ptr))
 		for_each_possible_cpu(cpu)
 			delete_object_full((unsigned long)per_cpu_ptr(ptr,
 								      cpu));
@@ -1743,6 +1746,13 @@ static void kmemleak_do_cleanup(struct work_struct *work)
 	mutex_lock(&scan_mutex);
 	stop_scan_thread();
 
+	/*
+	 * Once the scan thread has stopped, it is safe to no longer track
+	 * object freeing. Ordering of the scan thread stopping and the memory
+	 * accesses below is guaranteed by the kthread_stop() function.
+	 */
+	kmemleak_free_enabled = 0;
+
 	if (!kmemleak_found_leaks)
 		__kmemleak_do_cleanup();
 	else
@@ -1769,6 +1779,8 @@ static void kmemleak_disable(void)
 	/* check whether it is too early for a kernel thread */
 	if (kmemleak_initialized)
 		schedule_work(&cleanup_work);
+	else
+		kmemleak_free_enabled = 0;
 
 	pr_info("Kernel memory leak detector disabled\n");
 }
@@ -1833,8 +1845,10 @@ void __init kmemleak_init(void)
 	if (kmemleak_error) {
 		local_irq_restore(flags);
 		return;
-	} else
+	} else {
 		kmemleak_enabled = 1;
+		kmemleak_free_enabled = 1;
+	}
 	local_irq_restore(flags);
 
 	/*
diff --git a/mm/ksm.c b/mm/ksm.c
index 6b2e337bc03..a0ed043a109 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -376,7 +376,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
 		else
 			ret = VM_FAULT_WRITE;
 		put_page(page);
-	} while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_OOM)));
+	} while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM)));
 	/*
 	 * We must loop because handle_mm_fault() may back out if there's
 	 * any difficulty e.g. if pte accessed bit gets updated concurrently.
diff --git a/mm/madvise.c b/mm/madvise.c
index 0938b30da4a..dd7d354c5bf 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -102,7 +102,8 @@ static long madvise_behavior(struct vm_area_struct *vma,
 
 	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
 	*prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma,
-				vma->vm_file, pgoff, vma_policy(vma));
+				vma->vm_file, pgoff, vma_policy(vma),
+				vma_get_anon_name(vma));
 	if (*prev) {
 		vma = *prev;
 		goto success;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d6ac0e33e15..ee15ae6e698 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1638,9 +1638,9 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 
 	pr_info("Task in ");
 	pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id));
-	pr_info(" killed as a result of limit of ");
+	pr_cont(" killed as a result of limit of ");
 	pr_cont_cgroup_path(memcg->css.cgroup);
-	pr_info("\n");
+	pr_cont("\n");
 
 	rcu_read_unlock();
 
@@ -6001,6 +6001,12 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
 	return ret;
 }
 
+static int mem_cgroup_allow_attach(struct cgroup_subsys_state *css,
+				   struct cgroup_taskset *tset)
+{
+	return subsys_cgroup_allow_attach(css, tset);
+}
+
 static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css,
 				     struct cgroup_taskset *tset)
 {
@@ -6169,6 +6175,11 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
 {
 	return 0;
 }
+static int mem_cgroup_allow_attach(struct cgroup_subsys_state *css,
+				   struct cgroup_taskset *tset)
+{
+	return 0;
+}
 static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css,
 				     struct cgroup_taskset *tset)
 {
@@ -6204,6 +6215,7 @@ struct cgroup_subsys memory_cgrp_subsys = {
 	.can_attach = mem_cgroup_can_attach,
 	.cancel_attach = mem_cgroup_cancel_attach,
 	.attach = mem_cgroup_move_task,
+	.allow_attach = mem_cgroup_allow_attach,
 	.bind = mem_cgroup_bind,
 	.legacy_cftypes = mem_cgroup_files,
 	.early_init = 0,
@@ -6589,7 +6601,7 @@ void mem_cgroup_uncharge_list(struct list_head *page_list)
  * mem_cgroup_migrate - migrate a charge to another page
  * @oldpage: currently charged page
  * @newpage: page to transfer the charge to
- * @lrucare: both pages might be on the LRU already
+ * @lrucare: either or both pages might be on the LRU already
  *
  * Migrate the charge from @oldpage to @newpage.
  *
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 8639f6b2874..22f047fbaa3 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1153,10 +1153,10 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	 * The check (unnecessarily) ignores LRU pages being isolated and
 	 * walked by the page reclaim code, however that's not a big loss.
 	 */
-	if (!PageHuge(p) && !PageTransTail(p)) {
-		if (!PageLRU(p))
-			shake_page(p, 0);
-		if (!PageLRU(p)) {
+	if (!PageHuge(p)) {
+		if (!PageLRU(hpage))
+			shake_page(hpage, 0);
+		if (!PageLRU(hpage)) {
 			/*
 			 * shake_page could have turned it free.
 			 */
@@ -1659,8 +1659,6 @@ static int __soft_offline_page(struct page *page, int flags)
 			 * setting PG_hwpoison.
 			 */
 			if (!is_free_buddy_page(page))
-				lru_add_drain_all();
-			if (!is_free_buddy_page(page))
 				drain_all_pages();
 			SetPageHWPoison(page);
 			if (!is_free_buddy_page(page))
@@ -1735,12 +1733,12 @@ int soft_offline_page(struct page *page, int flags)
 	} else if (ret == 0) { /* for free pages */
 		if (PageHuge(page)) {
 			set_page_hwpoison_huge_page(hpage);
-			dequeue_hwpoisoned_huge_page(hpage);
-			atomic_long_add(1 << compound_order(hpage),
+			if (!dequeue_hwpoisoned_huge_page(hpage))
+				atomic_long_add(1 << compound_order(hpage),
 					&num_poisoned_pages);
 		} else {
-			SetPageHWPoison(page);
-			atomic_long_inc(&num_poisoned_pages);
+			if (!TestSetPageHWPoison(page))
+				atomic_long_inc(&num_poisoned_pages);
 		}
 	}
 	unset_migratetype_isolate(page, MIGRATE_MOVABLE);
diff --git a/mm/memory.c b/mm/memory.c
index d5f2ae9c4a2..90fb265b32b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -220,9 +220,6 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long
 	/* Is it from 0 to ~0? */
 	tlb->fullmm     = !(start | (end+1));
 	tlb->need_flush_all = 0;
-	tlb->start	= start;
-	tlb->end	= end;
-	tlb->need_flush = 0;
 	tlb->local.next = NULL;
 	tlb->local.nr   = 0;
 	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
@@ -232,15 +229,20 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb->batch = NULL;
 #endif
+
+	__tlb_reset_range(tlb);
 }
 
 static void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
-	tlb->need_flush = 0;
+	if (!tlb->end)
+		return;
+
 	tlb_flush(tlb);
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb_table_flush(tlb);
 #endif
+	__tlb_reset_range(tlb);
 }
 
 static void tlb_flush_mmu_free(struct mmu_gather *tlb)
@@ -256,8 +258,6 @@ static void tlb_flush_mmu_free(struct mmu_gather *tlb)
 
 void tlb_flush_mmu(struct mmu_gather *tlb)
 {
-	if (!tlb->need_flush)
-		return;
 	tlb_flush_mmu_tlbonly(tlb);
 	tlb_flush_mmu_free(tlb);
 }
@@ -292,7 +292,7 @@ int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
 	struct mmu_gather_batch *batch;
 
-	VM_BUG_ON(!tlb->need_flush);
+	VM_BUG_ON(!tlb->end);
 
 	batch = tlb->active;
 	batch->pages[batch->nr++] = page;
@@ -359,8 +359,6 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 {
 	struct mmu_table_batch **batch = &tlb->batch;
 
-	tlb->need_flush = 1;
-
 	/*
 	 * When there's less then two users of this mm there cannot be a
 	 * concurrent page-table walk.
@@ -1186,20 +1184,8 @@ again:
 	arch_leave_lazy_mmu_mode();
 
 	/* Do the actual TLB flush before dropping ptl */
-	if (force_flush) {
-		unsigned long old_end;
-
-		/*
-		 * Flush the TLB just for the previous segment,
-		 * then update the range to be the remaining
-		 * TLB range.
-		 */
-		old_end = tlb->end;
-		tlb->end = addr;
+	if (force_flush)
 		tlb_flush_mmu_tlbonly(tlb);
-		tlb->start = addr;
-		tlb->end = old_end;
-	}
 	pte_unmap_unlock(start_pte, ptl);
 
 	/*
@@ -2150,17 +2136,24 @@ reuse:
 		if (!dirty_page)
 			return ret;
 
-		/*
-		 * Yes, Virginia, this is actually required to prevent a race
-		 * with clear_page_dirty_for_io() from clearing the page dirty
-		 * bit after it clear all dirty ptes, but before a racing
-		 * do_wp_page installs a dirty pte.
-		 *
-		 * do_shared_fault is protected similarly.
-		 */
 		if (!page_mkwrite) {
-			wait_on_page_locked(dirty_page);
-			set_page_dirty_balance(dirty_page);
+			struct address_space *mapping;
+			int dirtied;
+
+			lock_page(dirty_page);
+			dirtied = set_page_dirty(dirty_page);
+			VM_BUG_ON_PAGE(PageAnon(dirty_page), dirty_page);
+			mapping = dirty_page->mapping;
+			unlock_page(dirty_page);
+
+			if (dirtied && mapping) {
+				/*
+				 * Some device drivers do not set page.mapping
+				 * but still dirty their pages
+				 */
+				balance_dirty_pages_ratelimited(mapping);
+			}
+
 			/* file_update_time outside page_lock */
 			if (vma->vm_file)
 				file_update_time(vma->vm_file);
@@ -2606,7 +2599,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo
 		if (prev && prev->vm_end == address)
 			return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
 
-		expand_downwards(vma, address - PAGE_SIZE);
+		return expand_downwards(vma, address - PAGE_SIZE);
 	}
 	if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
 		struct vm_area_struct *next = vma->vm_next;
@@ -2615,7 +2608,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo
 		if (next && next->vm_start == address + PAGE_SIZE)
 			return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM;
 
-		expand_upwards(vma, address + PAGE_SIZE);
+		return expand_upwards(vma, address + PAGE_SIZE);
 	}
 	return 0;
 }
@@ -2638,7 +2631,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	/* Check if we need to add a guard page to the stack */
 	if (check_stack_guard_page(vma, address) < 0)
-		return VM_FAULT_SIGBUS;
+		return VM_FAULT_SIGSEGV;
 
 	/* Use the zero-page for reads */
 	if (!(flags & FAULT_FLAG_WRITE)) {
@@ -3551,7 +3544,7 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
 	if (follow_phys(vma, addr, write, &prot, &phys_addr))
 		return -EINVAL;
 
-	maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot);
+	maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot);
 	if (write)
 		memcpy_toio(maddr + offset, buf, len);
 	else
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1bf4807cb21..05014e89efa 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1092,6 +1092,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 			return NULL;
 
 		arch_refresh_nodedata(nid, pgdat);
+	} else {
+		/* Reset the nr_zones and classzone_idx to 0 before reuse */
+		pgdat->nr_zones = 0;
+		pgdat->classzone_idx = 0;
 	}
 
 	/* we can use NODE_DATA(nid) from here */
@@ -1974,18 +1978,11 @@ void try_offline_node(int nid)
 		 * wait_table may be allocated from boot memory,
 		 * here only free if it's allocated by vmalloc.
 		 */
-		if (is_vmalloc_addr(zone->wait_table))
+		if (is_vmalloc_addr(zone->wait_table)) {
 			vfree(zone->wait_table);
+			zone->wait_table = NULL;
+		}
 	}
-
-	/*
-	 * Since there is no way to guarentee the address of pgdat/zone is not
-	 * on stack of any kernel threads or used by other kernel objects
-	 * without reference counting or other symchronizing method, do not
-	 * reset node_data and free pgdat here. Just reset it to 0 and reuse
-	 * the memory when the node is online again.
-	 */
-	memset(pgdat, 0, sizeof(*pgdat));
 }
 EXPORT_SYMBOL(try_offline_node);
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e58725aff7e..30d683e54ab 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -770,7 +770,7 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
 			((vmstart - vma->vm_start) >> PAGE_SHIFT);
 		prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags,
 				  vma->anon_vma, vma->vm_file, pgoff,
-				  new_pol);
+				  new_pol, vma_get_anon_name(vma));
 		if (prev) {
 			vma = prev;
 			next = vma->vm_next;
@@ -2548,7 +2548,7 @@ static void __init check_numabalancing_enable(void)
 	if (numabalancing_override)
 		set_numabalancing_state(numabalancing_override == 1);
 
-	if (nr_node_ids > 1 && !numabalancing_override) {
+	if (num_online_nodes() > 1 && !numabalancing_override) {
 		pr_info("%s automatic NUMA balancing. "
 			"Configure with numa_balancing= or the "
 			"kernel.numa_balancing sysctl",
diff --git a/mm/migrate.c b/mm/migrate.c
index 01439953abf..cd4fd10c4ec 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -229,7 +229,7 @@ static void remove_migration_ptes(struct page *old, struct page *new)
  * get to the page and wait until migration is finished.
  * When we return from this function the fault will be retried.
  */
-static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
+void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
 				spinlock_t *ptl)
 {
 	pte_t pte;
@@ -1260,7 +1260,8 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
 			goto put_and_set;
 
 		if (PageHuge(page)) {
-			isolate_huge_page(page, &pagelist);
+			if (PageHead(page))
+				isolate_huge_page(page, &pagelist);
 			goto put_and_set;
 		}
 
diff --git a/mm/mlock.c b/mm/mlock.c
index 73cf0987088..1d0d2392ffa 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -566,7 +566,8 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
 
 	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
 	*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
-			  vma->vm_file, pgoff, vma_policy(vma));
+			  vma->vm_file, pgoff, vma_policy(vma),
+			  vma_get_anon_name(vma));
 	if (*prev) {
 		vma = *prev;
 		goto success;
diff --git a/mm/mmap.c b/mm/mmap.c
index ae919891a08..f73ff5b2282 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -152,7 +152,7 @@ EXPORT_SYMBOL_GPL(vm_memory_committed);
  */
 int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 {
-	unsigned long free, allowed, reserve;
+	long free, allowed, reserve;
 
 	VM_WARN_ONCE(percpu_counter_read(&vm_committed_as) <
 			-(s64)vm_committed_as_batch * num_online_cpus(),
@@ -220,7 +220,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 	 */
 	if (mm) {
 		reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10);
-		allowed -= min(mm->total_vm / 32, reserve);
+		allowed -= min_t(long, mm->total_vm / 32, reserve);
 	}
 
 	if (percpu_counter_read_positive(&vm_committed_as) < allowed)
@@ -778,10 +778,10 @@ again:			remove_next = 1 + (end > next->vm_end);
 		if (exporter && exporter->anon_vma && !importer->anon_vma) {
 			int error;
 
+			importer->anon_vma = exporter->anon_vma;
 			error = anon_vma_clone(importer, exporter);
 			if (error)
 				return error;
-			importer->anon_vma = exporter->anon_vma;
 		}
 	}
 
@@ -928,7 +928,8 @@ again:			remove_next = 1 + (end > next->vm_end);
  * per-vma resources, so we don't attempt to merge those.
  */
 static inline int is_mergeable_vma(struct vm_area_struct *vma,
-			struct file *file, unsigned long vm_flags)
+			struct file *file, unsigned long vm_flags,
+			const char __user *anon_name)
 {
 	/*
 	 * VM_SOFTDIRTY should not prevent from VMA merging, if we
@@ -944,6 +945,8 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma,
 		return 0;
 	if (vma->vm_ops && vma->vm_ops->close)
 		return 0;
+	if (vma_get_anon_name(vma) != anon_name)
+		return 0;
 	return 1;
 }
 
@@ -974,9 +977,10 @@ static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1,
  */
 static int
 can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
-	struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
+	struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff,
+	const char __user *anon_name)
 {
-	if (is_mergeable_vma(vma, file, vm_flags) &&
+	if (is_mergeable_vma(vma, file, vm_flags, anon_name) &&
 	    is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
 		if (vma->vm_pgoff == vm_pgoff)
 			return 1;
@@ -993,9 +997,10 @@ can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
  */
 static int
 can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
-	struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
+	struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff,
+	const char __user *anon_name)
 {
-	if (is_mergeable_vma(vma, file, vm_flags) &&
+	if (is_mergeable_vma(vma, file, vm_flags, anon_name) &&
 	    is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
 		pgoff_t vm_pglen;
 		vm_pglen = vma_pages(vma);
@@ -1006,9 +1011,9 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
 }
 
 /*
- * Given a mapping request (addr,end,vm_flags,file,pgoff), figure out
- * whether that can be merged with its predecessor or its successor.
- * Or both (it neatly fills a hole).
+ * Given a mapping request (addr,end,vm_flags,file,pgoff,anon_name),
+ * figure out whether that can be merged with its predecessor or its
+ * successor.  Or both (it neatly fills a hole).
  *
  * In most cases - when called for mmap, brk or mremap - [addr,end) is
  * certain not to be mapped by the time vma_merge is called; but when
@@ -1037,8 +1042,9 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
 struct vm_area_struct *vma_merge(struct mm_struct *mm,
 			struct vm_area_struct *prev, unsigned long addr,
 			unsigned long end, unsigned long vm_flags,
-			struct anon_vma *anon_vma, struct file *file,
-			pgoff_t pgoff, struct mempolicy *policy)
+		    struct anon_vma *anon_vma, struct file *file,
+			pgoff_t pgoff, struct mempolicy *policy,
+			const char __user *anon_name)
 {
 	pgoff_t pglen = (end - addr) >> PAGE_SHIFT;
 	struct vm_area_struct *area, *next;
@@ -1063,16 +1069,16 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 	 * Can it merge with the predecessor?
 	 */
 	if (prev && prev->vm_end == addr &&
-			mpol_equal(vma_policy(prev), policy) &&
-			can_vma_merge_after(prev, vm_flags,
-						anon_vma, file, pgoff)) {
+  			mpol_equal(vma_policy(prev), policy) &&
+			can_vma_merge_after(prev, vm_flags, anon_vma,
+						file, pgoff, anon_name)) {
 		/*
 		 * OK, it can.  Can we now merge in the successor as well?
 		 */
 		if (next && end == next->vm_start &&
 				mpol_equal(policy, vma_policy(next)) &&
-				can_vma_merge_before(next, vm_flags,
-					anon_vma, file, pgoff+pglen) &&
+				can_vma_merge_before(next, vm_flags, anon_vma,
+						file, pgoff+pglen, anon_name) &&
 				is_mergeable_anon_vma(prev->anon_vma,
 						      next->anon_vma, NULL)) {
 							/* cases 1, 6 */
@@ -1091,9 +1097,9 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 	 * Can this new request be merged in front of next?
 	 */
 	if (next && end == next->vm_start &&
-			mpol_equal(policy, vma_policy(next)) &&
-			can_vma_merge_before(next, vm_flags,
-					anon_vma, file, pgoff+pglen)) {
+ 			mpol_equal(policy, vma_policy(next)) &&
+			can_vma_merge_before(next, vm_flags, anon_vma,
+					file, pgoff+pglen, anon_name)) {
 		if (prev && addr < prev->vm_end)	/* case 4 */
 			err = vma_adjust(prev, prev->vm_start,
 				addr, prev->vm_pgoff, NULL);
@@ -1580,7 +1586,8 @@ munmap_back:
 	/*
 	 * Can we just expand an old mapping?
 	 */
-	vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL);
+	vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff,
+			NULL, NULL);
 	if (vma)
 		goto out;
 
@@ -2099,14 +2106,17 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct rlimit *rlim = current->signal->rlim;
-	unsigned long new_start;
+	unsigned long new_start, actual_size;
 
 	/* address space limit tests */
 	if (!may_expand_vm(mm, grow))
 		return -ENOMEM;
 
 	/* Stack limit test */
-	if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur))
+	actual_size = size;
+	if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN)))
+		actual_size -= PAGE_SIZE;
+	if (actual_size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur))
 		return -ENOMEM;
 
 	/* mlock limit tests */
@@ -2691,7 +2701,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len)
 
 	/* Can we just expand an old private anonymous mapping? */
 	vma = vma_merge(mm, prev, addr, addr + len, flags,
-					NULL, NULL, pgoff, NULL);
+					NULL, NULL, pgoff, NULL, NULL);
 	if (vma)
 		goto out;
 
@@ -2850,7 +2860,8 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 	if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent))
 		return NULL;	/* should never get here */
 	new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags,
-			vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma));
+			vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
+			vma_get_anon_name(vma));
 	if (new_vma) {
 		/*
 		 * Source vma may have been merged into new_vma
diff --git a/mm/mprotect.c b/mm/mprotect.c
index ace93454ce8..5911e603269 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -289,7 +289,8 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	 */
 	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
 	*pprev = vma_merge(mm, *pprev, start, end, newflags,
-			vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma));
+			vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
+			vma_get_anon_name(vma));
 	if (*pprev) {
 		vma = *pprev;
 		goto success;
diff --git a/mm/nommu.c b/mm/nommu.c
index bd1808e194a..b5ba5bc02e4 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1905,7 +1905,7 @@ EXPORT_SYMBOL(unmap_mapping_range);
  */
 int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 {
-	unsigned long free, allowed, reserve;
+	long free, allowed, reserve;
 
 	vm_acct_memory(pages);
 
@@ -1969,7 +1969,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 	 */
 	if (mm) {
 		reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10);
-		allowed -= min(mm->total_vm / 32, reserve);
+		allowed -= min_t(long, mm->total_vm / 32, reserve);
 	}
 
 	if (percpu_counter_read_positive(&vm_committed_as) < allowed)
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 19ceae87522..b9aaa16dcf8 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -580,7 +580,7 @@ static long long pos_ratio_polynom(unsigned long setpoint,
 	long x;
 
 	x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT,
-		    limit - setpoint + 1);
+		      (limit - setpoint) | 1);
 	pos_ratio = x;
 	pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
 	pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
@@ -807,7 +807,7 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi,
 	 * scale global setpoint to bdi's:
 	 *	bdi_setpoint = setpoint * bdi_thresh / thresh
 	 */
-	x = div_u64((u64)bdi_thresh << 16, thresh + 1);
+	x = div_u64((u64)bdi_thresh << 16, thresh | 1);
 	bdi_setpoint = setpoint * (u64)x >> 16;
 	/*
 	 * Use span=(8*write_bw) in single bdi case as indicated by
@@ -822,7 +822,7 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi,
 
 	if (bdi_dirty < x_intercept - span / 4) {
 		pos_ratio = div64_u64(pos_ratio * (x_intercept - bdi_dirty),
-				    x_intercept - bdi_setpoint + 1);
+				      (x_intercept - bdi_setpoint) | 1);
 	} else
 		pos_ratio /= 4;
 
@@ -857,8 +857,11 @@ static void bdi_update_write_bandwidth(struct backing_dev_info *bdi,
 	 *                   bw * elapsed + write_bandwidth * (period - elapsed)
 	 * write_bandwidth = ---------------------------------------------------
 	 *                                          period
+	 *
+	 * @written may have decreased due to account_page_redirty().
+	 * Avoid underflowing @bw calculation.
 	 */
-	bw = written - bdi->written_stamp;
+	bw = written - min(written, bdi->written_stamp);
 	bw *= HZ;
 	if (unlikely(elapsed > period)) {
 		do_div(bw, elapsed);
@@ -922,7 +925,7 @@ static void global_update_bandwidth(unsigned long thresh,
 				    unsigned long now)
 {
 	static DEFINE_SPINLOCK(dirty_lock);
-	static unsigned long update_time;
+	static unsigned long update_time = INITIAL_JIFFIES;
 
 	/*
 	 * check locklessly first to optimize away locking for the most time
@@ -1541,16 +1544,6 @@ pause:
 		bdi_start_background_writeback(bdi);
 }
 
-void set_page_dirty_balance(struct page *page)
-{
-	if (set_page_dirty(page)) {
-		struct address_space *mapping = page_mapping(page);
-
-		if (mapping)
-			balance_dirty_pages_ratelimited(mapping);
-	}
-}
-
 static DEFINE_PER_CPU(int, bdp_ratelimits);
 
 /*
@@ -2123,32 +2116,25 @@ EXPORT_SYMBOL(account_page_dirtied);
  * page dirty in that case, but not all the buffers.  This is a "bottom-up"
  * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
  *
- * Most callers have locked the page, which pins the address_space in memory.
- * But zap_pte_range() does not lock the page, however in that case the
- * mapping is pinned by the vma's ->vm_file reference.
- *
- * We take care to handle the case where the page was truncated from the
- * mapping by re-checking page_mapping() inside tree_lock.
+ * The caller must ensure this doesn't race with truncation.  Most will simply
+ * hold the page lock, but e.g. zap_pte_range() calls with the page mapped and
+ * the pte lock held, which also locks out truncation.
  */
 int __set_page_dirty_nobuffers(struct page *page)
 {
 	if (!TestSetPageDirty(page)) {
 		struct address_space *mapping = page_mapping(page);
-		struct address_space *mapping2;
 		unsigned long flags;
 
 		if (!mapping)
 			return 1;
 
 		spin_lock_irqsave(&mapping->tree_lock, flags);
-		mapping2 = page_mapping(page);
-		if (mapping2) { /* Race with truncate? */
-			BUG_ON(mapping2 != mapping);
-			WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
-			account_page_dirtied(page, mapping);
-			radix_tree_tag_set(&mapping->page_tree,
-				page_index(page), PAGECACHE_TAG_DIRTY);
-		}
+		BUG_ON(page_mapping(page) != mapping);
+		WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
+		account_page_dirtied(page, mapping);
+		radix_tree_tag_set(&mapping->page_tree, page_index(page),
+				   PAGECACHE_TAG_DIRTY);
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 		if (mapping->host) {
 			/* !PageAnon && !swapper_space */
@@ -2305,12 +2291,10 @@ int clear_page_dirty_for_io(struct page *page)
 		/*
 		 * We carefully synchronise fault handlers against
 		 * installing a dirty pte and marking the page dirty
-		 * at this point. We do this by having them hold the
-		 * page lock at some point after installing their
-		 * pte, but before marking the page dirty.
-		 * Pages are always locked coming in here, so we get
-		 * the desired exclusion. See mm/memory.c:do_wp_page()
-		 * for more comments.
+		 * at this point.  We do this by having them hold the
+		 * page lock while dirtying the page, and pages are
+		 * always locked coming in here, so we get the desired
+		 * exclusion.
 		 */
 		if (TestClearPageDirty(page)) {
 			dec_zone_page_state(page, NR_FILE_DIRTY);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 616a2c956b4..d45203779b5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -204,8 +204,21 @@ static char * const zone_names[MAX_NR_ZONES] = {
 	 "Movable",
 };
 
+/*
+ * Try to keep at least this much lowmem free.  Do not allow normal
+ * allocations below this point, only high priority ones. Automatically
+ * tuned according to the amount of memory in the system.
+ */
 int min_free_kbytes = 1024;
 int user_min_free_kbytes = -1;
+int min_free_order_shift = 1;
+
+/*
+ * Extra memory for the system to try freeing. Used to temporarily
+ * free memory, to make space for new workloads. Anyone can allocate
+ * down to the min watermarks controlled by min_free_kbytes above.
+ */
+int extra_free_kbytes = 0;
 
 static unsigned long __meminitdata nr_kernel_pages;
 static unsigned long __meminitdata nr_all_pages;
@@ -1073,8 +1086,8 @@ static void change_pageblock_range(struct page *pageblock_page,
  * nor move CMA pages to different free lists. We don't want unmovable pages
  * to be allocated from MIGRATE_CMA areas.
  *
- * Returns the new migratetype of the pageblock (or the same old migratetype
- * if it was unchanged).
+ * Returns the allocation migratetype if free pages were stolen, or the
+ * fallback migratetype if it was decided not to steal.
  */
 static int try_to_steal_freepages(struct zone *zone, struct page *page,
 				  int start_type, int fallback_type)
@@ -1105,12 +1118,10 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page,
 
 		/* Claim the whole block if over half of it is free */
 		if (pages >= (1 << (pageblock_order-1)) ||
-				page_group_by_mobility_disabled) {
-
+				page_group_by_mobility_disabled)
 			set_pageblock_migratetype(page, start_type);
-			return start_type;
-		}
 
+		return start_type;
 	}
 
 	return fallback_type;
@@ -1162,7 +1173,7 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype)
 			set_freepage_migratetype(page, new_type);
 
 			trace_mm_page_alloc_extfrag(page, order, current_order,
-				start_migratetype, migratetype, new_type);
+				start_migratetype, migratetype);
 
 			return page;
 		}
@@ -1728,7 +1739,7 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
 		free_pages -= z->free_area[o].nr_free << o;
 
 		/* Require fewer higher order pages to be free */
-		min >>= 1;
+		min >>= min_free_order_shift;
 
 		if (free_pages <= min)
 			return false;
@@ -5654,6 +5665,7 @@ static void setup_per_zone_lowmem_reserve(void)
 static void __setup_per_zone_wmarks(void)
 {
 	unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
+	unsigned long pages_low = extra_free_kbytes >> (PAGE_SHIFT - 10);
 	unsigned long lowmem_pages = 0;
 	struct zone *zone;
 	unsigned long flags;
@@ -5665,11 +5677,14 @@ static void __setup_per_zone_wmarks(void)
 	}
 
 	for_each_zone(zone) {
-		u64 tmp;
+		u64 min, low;
 
 		spin_lock_irqsave(&zone->lock, flags);
-		tmp = (u64)pages_min * zone->managed_pages;
-		do_div(tmp, lowmem_pages);
+		min = (u64)pages_min * zone->managed_pages;
+		do_div(min, lowmem_pages);
+		low = (u64)pages_low * zone->managed_pages;
+		do_div(low, vm_total_pages);
+
 		if (is_highmem(zone)) {
 			/*
 			 * __GFP_HIGH and PF_MEMALLOC allocations usually don't
@@ -5690,11 +5705,13 @@ static void __setup_per_zone_wmarks(void)
 			 * If it's a lowmem zone, reserve a number of pages
 			 * proportionate to the zone's size.
 			 */
-			zone->watermark[WMARK_MIN] = tmp;
+			zone->watermark[WMARK_MIN] = min;
 		}
 
-		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) + (tmp >> 2);
-		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
+		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) +
+					low + (min >> 2);
+		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) +
+					low + (min >> 1);
 
 		__mod_zone_page_state(zone, NR_ALLOC_BATCH,
 			high_wmark_pages(zone) - low_wmark_pages(zone) -
@@ -5818,7 +5835,7 @@ module_init(init_per_zone_wmark_min)
 /*
  * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
  *	that we can call two helper functions whenever min_free_kbytes
- *	changes.
+ *	or extra_free_kbytes changes.
  */
 int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index c8778f7e208..ec66134fb2a 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -103,6 +103,7 @@ void unset_migratetype_isolate(struct page *page, unsigned migratetype)
 
 			if (!is_migrate_isolate_page(buddy)) {
 				__isolate_free_page(page, order);
+				kernel_map_pages(page, (1 << order), 1);
 				set_page_refcounted(page);
 				isolated_page = page;
 			}
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index ad83195521f..b264bda46e1 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -199,7 +199,10 @@ int walk_page_range(unsigned long addr, unsigned long end,
 			 */
 			if ((vma->vm_start <= addr) &&
 			    (vma->vm_flags & VM_PFNMAP)) {
-				next = vma->vm_end;
+				if (walk->pte_hole)
+					err = walk->pte_hole(addr, next, walk);
+				if (err)
+					break;
 				pgd = pgd_offset(walk->mm, next);
 				continue;
 			}
diff --git a/mm/percpu.c b/mm/percpu.c
index 014bab65e0f..88bb6c92d83 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1030,7 +1030,7 @@ area_found:
 		memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
 
 	ptr = __addr_to_pcpu_ptr(chunk->base_addr + off);
-	kmemleak_alloc_percpu(ptr, size);
+	kmemleak_alloc_percpu(ptr, size, gfp);
 	return ptr;
 
 fail_unlock:
diff --git a/mm/rmap.c b/mm/rmap.c
index 3e4c7213210..5fc824b7311 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -72,6 +72,8 @@ static inline struct anon_vma *anon_vma_alloc(void)
 	anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
 	if (anon_vma) {
 		atomic_set(&anon_vma->refcount, 1);
+		anon_vma->degree = 1;	/* Reference for first vma */
+		anon_vma->parent = anon_vma;
 		/*
 		 * Initialise the anon_vma root to point to itself. If called
 		 * from fork, the root will be reset to the parents anon_vma.
@@ -188,6 +190,8 @@ int anon_vma_prepare(struct vm_area_struct *vma)
 		if (likely(!vma->anon_vma)) {
 			vma->anon_vma = anon_vma;
 			anon_vma_chain_link(vma, avc, anon_vma);
+			/* vma reference or self-parent link for new root */
+			anon_vma->degree++;
 			allocated = NULL;
 			avc = NULL;
 		}
@@ -236,6 +240,14 @@ static inline void unlock_anon_vma_root(struct anon_vma *root)
 /*
  * Attach the anon_vmas from src to dst.
  * Returns 0 on success, -ENOMEM on failure.
+ *
+ * If dst->anon_vma is NULL this function tries to find and reuse existing
+ * anon_vma which has no vmas and only one child anon_vma. This prevents
+ * degradation of anon_vma hierarchy to endless linear chain in case of
+ * constantly forking task. On the other hand, an anon_vma with more than one
+ * child isn't reused even if there was no alive vma, thus rmap walker has a
+ * good chance of avoiding scanning the whole hierarchy when it searches where
+ * page is mapped.
  */
 int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
 {
@@ -256,11 +268,32 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
 		anon_vma = pavc->anon_vma;
 		root = lock_anon_vma_root(root, anon_vma);
 		anon_vma_chain_link(dst, avc, anon_vma);
+
+		/*
+		 * Reuse existing anon_vma if its degree lower than two,
+		 * that means it has no vma and only one anon_vma child.
+		 *
+		 * Do not chose parent anon_vma, otherwise first child
+		 * will always reuse it. Root anon_vma is never reused:
+		 * it has self-parent reference and at least one child.
+		 */
+		if (!dst->anon_vma && anon_vma != src->anon_vma &&
+				anon_vma->degree < 2)
+			dst->anon_vma = anon_vma;
 	}
+	if (dst->anon_vma)
+		dst->anon_vma->degree++;
 	unlock_anon_vma_root(root);
 	return 0;
 
  enomem_failure:
+	/*
+	 * dst->anon_vma is dropped here otherwise its degree can be incorrectly
+	 * decremented in unlink_anon_vmas().
+	 * We can safely do this because callers of anon_vma_clone() don't care
+	 * about dst->anon_vma if anon_vma_clone() failed.
+	 */
+	dst->anon_vma = NULL;
 	unlink_anon_vmas(dst);
 	return -ENOMEM;
 }
@@ -280,6 +313,9 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	if (!pvma->anon_vma)
 		return 0;
 
+	/* Drop inherited anon_vma, we'll reuse existing or allocate new. */
+	vma->anon_vma = NULL;
+
 	/*
 	 * First, attach the new VMA to the parent VMA's anon_vmas,
 	 * so rmap can find non-COWed pages in child processes.
@@ -288,6 +324,10 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	if (error)
 		return error;
 
+	/* An existing anon_vma has been reused, all done then. */
+	if (vma->anon_vma)
+		return 0;
+
 	/* Then add our own anon_vma. */
 	anon_vma = anon_vma_alloc();
 	if (!anon_vma)
@@ -301,6 +341,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	 * lock any of the anon_vmas in this anon_vma tree.
 	 */
 	anon_vma->root = pvma->anon_vma->root;
+	anon_vma->parent = pvma->anon_vma;
 	/*
 	 * With refcounts, an anon_vma can stay around longer than the
 	 * process it belongs to. The root anon_vma needs to be pinned until
@@ -311,6 +352,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	vma->anon_vma = anon_vma;
 	anon_vma_lock_write(anon_vma);
 	anon_vma_chain_link(vma, avc, anon_vma);
+	anon_vma->parent->degree++;
 	anon_vma_unlock_write(anon_vma);
 
 	return 0;
@@ -341,12 +383,16 @@ void unlink_anon_vmas(struct vm_area_struct *vma)
 		 * Leave empty anon_vmas on the list - we'll need
 		 * to free them outside the lock.
 		 */
-		if (RB_EMPTY_ROOT(&anon_vma->rb_root))
+		if (RB_EMPTY_ROOT(&anon_vma->rb_root)) {
+			anon_vma->parent->degree--;
 			continue;
+		}
 
 		list_del(&avc->same_vma);
 		anon_vma_chain_free(avc);
 	}
+	if (vma->anon_vma)
+		vma->anon_vma->degree--;
 	unlock_anon_vma_root(root);
 
 	/*
@@ -357,6 +403,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma)
 	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
 		struct anon_vma *anon_vma = avc->anon_vma;
 
+		BUG_ON(anon_vma->degree);
 		put_anon_vma(anon_vma);
 
 		list_del(&avc->same_vma);
diff --git a/mm/shmem.c b/mm/shmem.c
index 185836ba53e..26472ff651b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1013,7 +1013,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 		 */
 		oldpage = newpage;
 	} else {
-		mem_cgroup_migrate(oldpage, newpage, false);
+		mem_cgroup_migrate(oldpage, newpage, true);
 		lru_cache_add_anon(newpage);
 		*pagep = newpage;
 	}
@@ -3404,6 +3404,14 @@ struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags
 }
 EXPORT_SYMBOL_GPL(shmem_file_setup);
 
+void shmem_set_file(struct vm_area_struct *vma, struct file *file)
+{
+	if (vma->vm_file)
+		fput(vma->vm_file);
+	vma->vm_file = file;
+	vma->vm_ops = &shmem_vm_ops;
+}
+
 /**
  * shmem_zero_setup - setup a shared anonymous mapping
  * @vma: the vma to be mmapped is prepared by do_mmap_pgoff
@@ -3417,10 +3425,7 @@ int shmem_zero_setup(struct vm_area_struct *vma)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	if (vma->vm_file)
-		fput(vma->vm_file);
-	vma->vm_file = file;
-	vma->vm_ops = &shmem_vm_ops;
+	shmem_set_file(vma, file);
 	return 0;
 }
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index dcb47074ae0..bae2b954029 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -46,6 +46,7 @@
 #include <linux/oom.h>
 #include <linux/prefetch.h>
 #include <linux/printk.h>
+#include <linux/debugfs.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -186,6 +187,39 @@ static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru)
 	return zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru);
 }
 
+struct dentry *debug_file;
+
+static int debug_shrinker_show(struct seq_file *s, void *unused)
+{
+	struct shrinker *shrinker;
+	struct shrink_control sc;
+
+	sc.gfp_mask = -1;
+	sc.nr_to_scan = 0;
+
+	down_read(&shrinker_rwsem);
+	list_for_each_entry(shrinker, &shrinker_list, list) {
+		int num_objs;
+
+		num_objs = shrinker->count_objects(shrinker, &sc);
+		seq_printf(s, "%pf %d\n", shrinker->scan_objects, num_objs);
+	}
+	up_read(&shrinker_rwsem);
+	return 0;
+}
+
+static int debug_shrinker_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, debug_shrinker_show, inode->i_private);
+}
+
+static const struct file_operations debug_shrinker_fops = {
+        .open = debug_shrinker_open,
+        .read = seq_read,
+        .llseek = seq_lseek,
+        .release = single_release,
+};
+
 /*
  * Add a shrinker callback to be called from the vm.
  */
@@ -215,6 +249,15 @@ int register_shrinker(struct shrinker *shrinker)
 }
 EXPORT_SYMBOL(register_shrinker);
 
+static int __init add_shrinker_debug(void)
+{
+	debugfs_create_file("shrinker", 0644, NULL, NULL,
+			    &debug_shrinker_fops);
+	return 0;
+}
+
+late_initcall(add_shrinker_debug);
+
 /*
  * Remove one
  */
@@ -2904,18 +2947,20 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
 		return false;
 
 	/*
-	 * There is a potential race between when kswapd checks its watermarks
-	 * and a process gets throttled. There is also a potential race if
-	 * processes get throttled, kswapd wakes, a large process exits therby
-	 * balancing the zones that causes kswapd to miss a wakeup. If kswapd
-	 * is going to sleep, no process should be sleeping on pfmemalloc_wait
-	 * so wake them now if necessary. If necessary, processes will wake
-	 * kswapd and get throttled again
+	 * The throttled processes are normally woken up in balance_pgdat() as
+	 * soon as pfmemalloc_watermark_ok() is true. But there is a potential
+	 * race between when kswapd checks the watermarks and a process gets
+	 * throttled. There is also a potential race if processes get
+	 * throttled, kswapd wakes, a large process exits thereby balancing the
+	 * zones, which causes kswapd to exit balance_pgdat() before reaching
+	 * the wake up checks. If kswapd is going to sleep, no process should
+	 * be sleeping on pfmemalloc_wait, so wake them now if necessary. If
+	 * the wake up is premature, processes will wake kswapd and get
+	 * throttled again. The difference from wake ups in balance_pgdat() is
+	 * that here we are under prepare_to_wait().
 	 */
-	if (waitqueue_active(&pgdat->pfmemalloc_wait)) {
-		wake_up(&pgdat->pfmemalloc_wait);
-		return false;
-	}
+	if (waitqueue_active(&pgdat->pfmemalloc_wait))
+		wake_up_all(&pgdat->pfmemalloc_wait);
 
 	return pgdat_balanced(pgdat, order, classzone_idx);
 }
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 1b12d390dc6..4590aa42b6c 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1348,7 +1348,7 @@ static void __init start_shepherd_timer(void)
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu),
+		INIT_DELAYED_WORK(per_cpu_ptr(&vmstat_work, cpu),
 			vmstat_update);
 
 	if (!alloc_cpumask_var(&cpu_stat_off, GFP_KERNEL))
diff --git a/net/9p/client.c b/net/9p/client.c
index e86a9bea1d1..53fe98ee8a5 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -850,7 +850,8 @@ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type,
 	if (err < 0) {
 		if (err == -EIO)
 			c->status = Disconnected;
-		goto reterr;
+		if (err != -ERESTARTSYS)
+			goto reterr;
 	}
 	if (req->status == REQ_STATUS_ERROR) {
 		p9_debug(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err);
diff --git a/net/Kconfig b/net/Kconfig
index 99815b5454b..15a2d76703b 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -83,6 +83,20 @@ source "net/netlabel/Kconfig"
 
 endif # if INET
 
+config ANDROID_PARANOID_NETWORK
+	bool "Only allow certain groups to create sockets"
+	default ANDROID
+	help
+		none
+
+config NET_ACTIVITY_STATS
+	bool "Network activity statistics tracking"
+	default y
+	help
+	 Network activity statistics are useful for tracking wireless
+	 modem activity on 2G, 3G, 4G wireless networks. Counts number of
+	 transmissions and groups them in specified time buckets.
+
 config NETWORK_SECMARK
 	bool "Security Marking"
 	help
@@ -230,7 +244,7 @@ source "net/mpls/Kconfig"
 source "net/hsr/Kconfig"
 
 config RPS
-	boolean
+	boolean "RPS"
 	depends on SMP && SYSFS
 	default y
 
diff --git a/net/Makefile b/net/Makefile
index 7ed1970074b..550c1123047 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -73,3 +73,4 @@ obj-$(CONFIG_OPENVSWITCH)	+= openvswitch/
 obj-$(CONFIG_VSOCKETS)	+= vmw_vsock/
 obj-$(CONFIG_NET_MPLS_GSO)	+= mpls/
 obj-$(CONFIG_HSR)		+= hsr/
+obj-$(CONFIG_NET_ACTIVITY_STATS)		+= activity_stats.o
diff --git a/net/activity_stats.c b/net/activity_stats.c
new file mode 100644
index 00000000000..4609ce2043e
--- /dev/null
+++ b/net/activity_stats.c
@@ -0,0 +1,119 @@
+/* net/activity_stats.c
+ *
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Author: Mike Chan (mike@android.com)
+ */
+
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/suspend.h>
+#include <net/net_namespace.h>
+
+/*
+ * Track transmission rates in buckets (power of 2).
+ * 1,2,4,8...512 seconds.
+ *
+ * Buckets represent the count of network transmissions at least
+ * N seconds apart, where N is 1 << bucket index.
+ */
+#define BUCKET_MAX 10
+
+/* Track network activity frequency */
+static unsigned long activity_stats[BUCKET_MAX];
+static ktime_t last_transmit;
+static ktime_t suspend_time;
+static DEFINE_SPINLOCK(activity_lock);
+
+void activity_stats_update(void)
+{
+	int i;
+	unsigned long flags;
+	ktime_t now;
+	s64 delta;
+
+	spin_lock_irqsave(&activity_lock, flags);
+	now = ktime_get();
+	delta = ktime_to_ns(ktime_sub(now, last_transmit));
+
+	for (i = BUCKET_MAX - 1; i >= 0; i--) {
+		/*
+		 * Check if the time delta between network activity is within the
+		 * minimum bucket range.
+		 */
+		if (delta < (1000000000ULL << i))
+			continue;
+
+		activity_stats[i]++;
+		last_transmit = now;
+		break;
+	}
+	spin_unlock_irqrestore(&activity_lock, flags);
+}
+
+static int activity_stats_show(struct seq_file *m, void *v)
+{
+	int i;
+	int ret;
+
+	seq_printf(m, "Min Bucket(sec) Count\n");
+
+	for (i = 0; i < BUCKET_MAX; i++) {
+		ret = seq_printf(m, "%15d %lu\n", 1 << i, activity_stats[i]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int activity_stats_notifier(struct notifier_block *nb,
+					unsigned long event, void *dummy)
+{
+	switch (event) {
+		case PM_SUSPEND_PREPARE:
+			suspend_time = ktime_get_real();
+			break;
+
+		case PM_POST_SUSPEND:
+			suspend_time = ktime_sub(ktime_get_real(), suspend_time);
+			last_transmit = ktime_sub(last_transmit, suspend_time);
+	}
+
+	return 0;
+}
+
+static int activity_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, activity_stats_show, PDE_DATA(inode));
+}
+
+static const struct file_operations activity_stats_fops = {
+	.open		= activity_stats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static struct notifier_block activity_stats_notifier_block = {
+	.notifier_call = activity_stats_notifier,
+};
+
+static int  __init activity_stats_init(void)
+{
+	proc_create("activity", S_IRUGO,
+		    init_net.proc_net_stat, &activity_stats_fops);
+	return register_pm_notifier(&activity_stats_notifier_block);
+}
+
+subsys_initcall(activity_stats_init);
+
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index fc1835c6bb4..00f9e144cc9 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -251,7 +251,7 @@ batadv_frag_merge_packets(struct hlist_head *chain, struct sk_buff *skb)
 	kfree(entry);
 
 	/* Make room for the rest of the fragments. */
-	if (pskb_expand_head(skb_out, 0, size - skb->len, GFP_ATOMIC) < 0) {
+	if (pskb_expand_head(skb_out, 0, size - skb_out->len, GFP_ATOMIC) < 0) {
 		kfree_skb(skb_out);
 		skb_out = NULL;
 		goto free;
@@ -434,7 +434,7 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
 	 * fragments larger than BATADV_FRAG_MAX_FRAG_SIZE
 	 */
 	mtu = min_t(unsigned, mtu, BATADV_FRAG_MAX_FRAG_SIZE);
-	max_fragment_size = (mtu - header_size - ETH_HLEN);
+	max_fragment_size = mtu - header_size;
 	max_packet_size = max_fragment_size * BATADV_FRAG_MAX_FRAGMENTS;
 
 	/* Don't even try to fragment, if we need more than 16 fragments */
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index 90cff585b37..e0bcf9e8427 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -810,7 +810,7 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv,
 		goto out;
 
 	gw_node = batadv_gw_node_get(bat_priv, orig_dst_node);
-	if (!gw_node->bandwidth_down == 0)
+	if (!gw_node)
 		goto out;
 
 	switch (atomic_read(&bat_priv->gw_mode)) {
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index c2e0d14433d..cfbb39e6fdf 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -591,17 +591,13 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev)
 	int err = 0;
 	bdaddr_t addr;
 	u8 addr_type;
-	struct sk_buff *tmpskb;
 
 	/* We must take a copy of the skb before we modify/replace the ipv6
 	 * header as the header could be used elsewhere
 	 */
-	tmpskb = skb_unshare(skb, GFP_ATOMIC);
-	if (!tmpskb) {
-		kfree_skb(skb);
+	skb = skb_unshare(skb, GFP_ATOMIC);
+	if (!skb)
 		return NET_XMIT_DROP;
-	}
-	skb = tmpskb;
 
 	/* Return values from setup_header()
 	 *  <0 - error, packet is dropped
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 339c74ad455..6ad34688a20 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -104,11 +104,40 @@ void bt_sock_unregister(int proto)
 }
 EXPORT_SYMBOL(bt_sock_unregister);
 
+#ifdef CONFIG_PARANOID_NETWORK
+static inline int current_has_bt_admin(void)
+{
+	return !current_euid();
+}
+
+static inline int current_has_bt(void)
+{
+	return current_has_bt_admin();
+}
+# else
+static inline int current_has_bt_admin(void)
+{
+	return 1;
+}
+
+static inline int current_has_bt(void)
+{
+	return 1;
+}
+#endif
+
 static int bt_sock_create(struct net *net, struct socket *sock, int proto,
 			  int kern)
 {
 	int err;
 
+	if (proto == BTPROTO_RFCOMM || proto == BTPROTO_SCO ||
+			proto == BTPROTO_L2CAP) {
+		if (!current_has_bt())
+			return -EPERM;
+	} else if (!current_has_bt_admin())
+		return -EPERM;
+
 	if (net != &init_net)
 		return -EAFNOSUPPORT;
 
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index b9517bd1719..b45eb243a5e 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -415,7 +415,7 @@ static void le_conn_timeout(struct work_struct *work)
 	 * happen with broken hardware or if low duty cycle was used
 	 * (which doesn't have a timeout of its own).
 	 */
-	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) {
+	if (conn->role == HCI_ROLE_SLAVE) {
 		u8 enable = 0x00;
 		hci_send_cmd(hdev, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable),
 			     &enable);
@@ -517,7 +517,7 @@ int hci_conn_del(struct hci_conn *conn)
 		/* Unacked frames */
 		hdev->acl_cnt += conn->sent;
 	} else if (conn->type == LE_LINK) {
-		cancel_delayed_work_sync(&conn->le_conn_timeout);
+		cancel_delayed_work(&conn->le_conn_timeout);
 
 		if (hdev->le_pkts)
 			hdev->le_cnt += conn->sent;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 8b0a2a6de41..e5124a9ea6f 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -205,6 +205,8 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb)
 	hdev->le_scan_type = LE_SCAN_PASSIVE;
 
 	hdev->ssp_debug_mode = 0;
+
+	hci_bdaddr_list_clear(&hdev->le_white_list);
 }
 
 static void hci_cc_write_local_name(struct hci_dev *hdev, struct sk_buff *skb)
@@ -237,7 +239,8 @@ static void hci_cc_read_local_name(struct hci_dev *hdev, struct sk_buff *skb)
 	if (rp->status)
 		return;
 
-	if (test_bit(HCI_SETUP, &hdev->dev_flags))
+	if (test_bit(HCI_SETUP, &hdev->dev_flags) ||
+	    test_bit(HCI_CONFIG, &hdev->dev_flags))
 		memcpy(hdev->dev_name, rp->name, HCI_MAX_NAME_LENGTH);
 }
 
@@ -492,7 +495,8 @@ static void hci_cc_read_local_version(struct hci_dev *hdev, struct sk_buff *skb)
 	if (rp->status)
 		return;
 
-	if (test_bit(HCI_SETUP, &hdev->dev_flags)) {
+	if (test_bit(HCI_SETUP, &hdev->dev_flags) ||
+	    test_bit(HCI_CONFIG, &hdev->dev_flags)) {
 		hdev->hci_ver = rp->hci_ver;
 		hdev->hci_rev = __le16_to_cpu(rp->hci_rev);
 		hdev->lmp_ver = rp->lmp_ver;
@@ -511,7 +515,8 @@ static void hci_cc_read_local_commands(struct hci_dev *hdev,
 	if (rp->status)
 		return;
 
-	if (test_bit(HCI_SETUP, &hdev->dev_flags))
+	if (test_bit(HCI_SETUP, &hdev->dev_flags) ||
+	    test_bit(HCI_CONFIG, &hdev->dev_flags))
 		memcpy(hdev->commands, rp->commands, sizeof(hdev->commands));
 }
 
@@ -2139,7 +2144,12 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		return;
 	}
 
-	if (!test_bit(HCI_CONNECTABLE, &hdev->dev_flags) &&
+	/* Require HCI_CONNECTABLE or a whitelist entry to accept the
+	 * connection. These features are only touched through mgmt so
+	 * only do the checks if HCI_MGMT is set.
+	 */
+	if (test_bit(HCI_MGMT, &hdev->dev_flags) &&
+	    !test_bit(HCI_CONNECTABLE, &hdev->dev_flags) &&
 	    !hci_bdaddr_list_lookup(&hdev->whitelist, &ev->bdaddr,
 				    BDADDR_BREDR)) {
 		    hci_reject_conn(hdev, &ev->bdaddr);
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index f09b6b65cf6..9ebc394ea5e 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -1392,8 +1392,12 @@ static int smp_cmd_ident_addr_info(struct l2cap_conn *conn,
 	 * implementations are not known of and in order to not over
 	 * complicate our implementation, simply pretend that we never
 	 * received an IRK for such a device.
+	 *
+	 * The Identity Address must also be a Static Random or Public
+	 * Address, which hci_is_identity_address() checks for.
 	 */
-	if (!bacmp(&info->bdaddr, BDADDR_ANY)) {
+	if (!bacmp(&info->bdaddr, BDADDR_ANY) ||
+	    !hci_is_identity_address(&info->bdaddr, info->addr_type)) {
 		BT_ERR("Ignoring IRK with no identity address");
 		goto distribute;
 	}
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index ffd379db593..b8919d01f0f 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -44,16 +44,17 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 #endif
 
-	u64_stats_update_begin(&brstats->syncp);
-	brstats->tx_packets++;
-	brstats->tx_bytes += skb->len;
-	u64_stats_update_end(&brstats->syncp);
-
 	BR_INPUT_SKB_CB(skb)->brdev = dev;
 
 	skb_reset_mac_header(skb);
 	skb_pull(skb, ETH_HLEN);
 
+	u64_stats_update_begin(&brstats->syncp);
+	brstats->tx_packets++;
+	/* Exclude ETH_HLEN from byte stats for consistency with Rx chain */
+	brstats->tx_bytes += skb->len;
+	u64_stats_update_end(&brstats->syncp);
+
 	if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid))
 		goto out;
 
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 6f6c95cfe8f..eab8862d9f8 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -789,9 +789,11 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p,
 	int err = 0;
 
 	if (ndm->ndm_flags & NTF_USE) {
+		local_bh_disable();
 		rcu_read_lock();
 		br_fdb_update(p->br, p, addr, vid, true);
 		rcu_read_unlock();
+		local_bh_enable();
 	} else {
 		spin_lock_bh(&p->br->hash_lock);
 		err = fdb_add_entry(p, addr, ndm->ndm_state,
diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index a9a4a1b7863..8d423bc649b 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -247,9 +247,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
 
-		spin_lock_bh(&br->lock);
 		br_stp_set_bridge_priority(br, args[1]);
-		spin_unlock_bh(&br->lock);
 		return 0;
 
 	case BRCTL_SET_PORT_PRIORITY:
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index c465876c786..c08f510fce3 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1071,7 +1071,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 
 		err = br_ip6_multicast_add_group(br, port, &grec->grec_mca,
 						 vid);
-		if (!err)
+		if (err)
 			break;
 	}
 
@@ -1166,6 +1166,9 @@ static void br_multicast_add_router(struct net_bridge *br,
 	struct net_bridge_port *p;
 	struct hlist_node *slot = NULL;
 
+	if (!hlist_unhashed(&port->rlist))
+		return;
+
 	hlist_for_each_entry(p, &br->router_list, rlist) {
 		if ((unsigned long) port >= (unsigned long) p)
 			break;
@@ -1193,12 +1196,8 @@ static void br_multicast_mark_router(struct net_bridge *br,
 	if (port->multicast_router != 1)
 		return;
 
-	if (!hlist_unhashed(&port->rlist))
-		goto timer;
-
 	br_multicast_add_router(br, port);
 
-timer:
 	mod_timer(&port->multicast_router_timer,
 		  now + br->multicast_querier_interval);
 }
@@ -1821,7 +1820,7 @@ static void br_multicast_query_expired(struct net_bridge *br,
 	if (query->startup_sent < br->multicast_startup_query_count)
 		query->startup_sent++;
 
-	RCU_INIT_POINTER(querier, NULL);
+	RCU_INIT_POINTER(querier->port, NULL);
 	br_multicast_send_query(br, NULL, query);
 	spin_unlock(&br->multicast_lock);
 }
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 1a4f32c09ad..f076a8ede00 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -650,6 +650,13 @@ static int br_nf_forward_finish(struct sk_buff *skb)
 	struct net_device *in;
 
 	if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) {
+		int frag_max_size;
+
+		if (skb->protocol == htons(ETH_P_IP)) {
+			frag_max_size = IPCB(skb)->frag_max_size;
+			BR_INPUT_SKB_CB(skb)->frag_max_size = frag_max_size;
+		}
+
 		in = nf_bridge->physindev;
 		if (nf_bridge->mask & BRNF_PKT_TYPE) {
 			skb->pkt_type = PACKET_OTHERHOST;
@@ -709,8 +716,14 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops,
 		nf_bridge->mask |= BRNF_PKT_TYPE;
 	}
 
-	if (pf == NFPROTO_IPV4 && br_parse_ip_options(skb))
-		return NF_DROP;
+	if (pf == NFPROTO_IPV4) {
+		int frag_max = BR_INPUT_SKB_CB(skb)->frag_max_size;
+
+		if (br_parse_ip_options(skb))
+			return NF_DROP;
+
+		IPCB(skb)->frag_max_size = frag_max;
+	}
 
 	/* The physdev module checks on this */
 	nf_bridge->mask |= BRNF_BRIDGED;
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 41146872c1b..7832d07f48f 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -243,12 +243,13 @@ bool br_stp_recalculate_bridge_id(struct net_bridge *br)
 	return true;
 }
 
-/* called under bridge lock */
+/* Acquires and releases bridge lock */
 void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio)
 {
 	struct net_bridge_port *p;
 	int wasroot;
 
+	spin_lock_bh(&br->lock);
 	wasroot = br_is_root_bridge(br);
 
 	list_for_each_entry(p, &br->port_list, list) {
@@ -266,6 +267,7 @@ void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio)
 	br_port_state_selection(br);
 	if (br_is_root_bridge(br) && !wasroot)
 		br_become_root_bridge(br);
+	spin_unlock_bh(&br->lock);
 }
 
 /* called under bridge lock */
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 150048fb99b..97b8ddf5736 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -199,8 +199,8 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 		if (skb->vlan_proto != proto) {
 			/* Protocol-mismatch, empty out vlan_tci for new tag */
 			skb_push(skb, ETH_HLEN);
-			skb = __vlan_put_tag(skb, skb->vlan_proto,
-					     vlan_tx_tag_get(skb));
+			skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
+							vlan_tx_tag_get(skb));
 			if (unlikely(!skb))
 				return false;
 
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 43f750e88e1..5e10ee0efff 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -281,7 +281,7 @@ static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock,
 	int copylen;
 
 	ret = -EOPNOTSUPP;
-	if (m->msg_flags&MSG_OOB)
+	if (flags & MSG_OOB)
 		goto read_error;
 
 	skb = skb_recv_datagram(sk, flags, 0 , &ret);
@@ -330,6 +330,10 @@ static long caif_stream_data_wait(struct sock *sk, long timeo)
 		release_sock(sk);
 		timeo = schedule_timeout(timeo);
 		lock_sock(sk);
+
+		if (sock_flag(sk, SOCK_DEAD))
+			break;
+
 		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
 	}
 
@@ -374,6 +378,10 @@ static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		struct sk_buff *skb;
 
 		lock_sock(sk);
+		if (sock_flag(sk, SOCK_DEAD)) {
+			err = -ECONNRESET;
+			goto unlock;
+		}
 		skb = skb_dequeue(&sk->sk_receive_queue);
 		caif_check_flow_release(sk);
 
diff --git a/net/can/af_can.c b/net/can/af_can.c
index ce82337521f..d6030d6949d 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -262,6 +262,9 @@ int can_send(struct sk_buff *skb, int loop)
 		goto inval_skb;
 	}
 
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+	skb_reset_mac_header(skb);
 	skb_reset_network_header(skb);
 	skb_reset_transport_header(skb);
 
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index a1ef53c0441..b1f2d1f44d3 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -290,6 +290,7 @@ static int is_out(const struct crush_map *map,
  * @type: the type of item to choose
  * @out: pointer to output vector
  * @outpos: our position in that vector
+ * @out_size: size of the out vector
  * @tries: number of attempts to make
  * @recurse_tries: number of attempts to have recursive chooseleaf make
  * @local_retries: localized retries
@@ -304,6 +305,7 @@ static int crush_choose_firstn(const struct crush_map *map,
 			       const __u32 *weight, int weight_max,
 			       int x, int numrep, int type,
 			       int *out, int outpos,
+			       int out_size,
 			       unsigned int tries,
 			       unsigned int recurse_tries,
 			       unsigned int local_retries,
@@ -322,6 +324,7 @@ static int crush_choose_firstn(const struct crush_map *map,
 	int item = 0;
 	int itemtype;
 	int collide, reject;
+	int count = out_size;
 
 	dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d tries %d recurse_tries %d local_retries %d local_fallback_retries %d parent_r %d\n",
 		recurse_to_leaf ? "_LEAF" : "",
@@ -329,7 +332,7 @@ static int crush_choose_firstn(const struct crush_map *map,
 		tries, recurse_tries, local_retries, local_fallback_retries,
 		parent_r);
 
-	for (rep = outpos; rep < numrep; rep++) {
+	for (rep = outpos; rep < numrep && count > 0 ; rep++) {
 		/* keep trying until we get a non-out, non-colliding item */
 		ftotal = 0;
 		skip_rep = 0;
@@ -403,7 +406,7 @@ static int crush_choose_firstn(const struct crush_map *map,
 							 map->buckets[-1-item],
 							 weight, weight_max,
 							 x, outpos+1, 0,
-							 out2, outpos,
+							 out2, outpos, count,
 							 recurse_tries, 0,
 							 local_retries,
 							 local_fallback_retries,
@@ -463,6 +466,7 @@ reject:
 		dprintk("CHOOSE got %d\n", item);
 		out[outpos] = item;
 		outpos++;
+		count--;
 	}
 
 	dprintk("CHOOSE returns %d\n", outpos);
@@ -654,6 +658,7 @@ int crush_do_rule(const struct crush_map *map,
 	__u32 step;
 	int i, j;
 	int numrep;
+	int out_size;
 	/*
 	 * the original choose_total_tries value was off by one (it
 	 * counted "retries" and not "tries").  add one.
@@ -761,6 +766,7 @@ int crush_do_rule(const struct crush_map *map,
 						x, numrep,
 						curstep->arg2,
 						o+osize, j,
+						result_max-osize,
 						choose_tries,
 						recurse_tries,
 						choose_local_retries,
@@ -770,11 +776,13 @@ int crush_do_rule(const struct crush_map *map,
 						c+osize,
 						0);
 				} else {
+					out_size = ((numrep < (result_max-osize)) ?
+                                                    numrep : (result_max-osize));
 					crush_choose_indep(
 						map,
 						map->buckets[-1-w[i]],
 						weight, weight_max,
-						x, numrep, numrep,
+						x, out_size, numrep,
 						curstep->arg2,
 						o+osize, j,
 						choose_tries,
@@ -783,7 +791,7 @@ int crush_do_rule(const struct crush_map *map,
 						recurse_to_leaf,
 						c+osize,
 						0);
-					osize += numrep;
+					osize += out_size;
 				}
 			}
 
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 8d1653caffd..56a65536c8f 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -484,7 +484,7 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 			       IPPROTO_TCP, &sock);
 	if (ret)
 		return ret;
-	sock->sk->sk_allocation = GFP_NOFS | __GFP_MEMALLOC;
+	sock->sk->sk_allocation = GFP_NOFS;
 
 #ifdef CONFIG_LOCKDEP
 	lockdep_set_class(&sock->sk->sk_lock, &socket_class);
@@ -510,8 +510,6 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 		return ret;
 	}
 
-	sk_set_memalloc(sock->sk);
-
 	con->sock = sock;
 	return 0;
 }
@@ -2772,11 +2770,8 @@ static void con_work(struct work_struct *work)
 {
 	struct ceph_connection *con = container_of(work, struct ceph_connection,
 						   work.work);
-	unsigned long pflags = current->flags;
 	bool fault;
 
-	current->flags |= PF_MEMALLOC;
-
 	mutex_lock(&con->mutex);
 	while (true) {
 		int ret;
@@ -2830,8 +2825,6 @@ static void con_work(struct work_struct *work)
 		con_fault_finish(con);
 
 	con->ops->put(con);
-
-	tsk_restore_flags(current, pflags, PF_MEMALLOC);
 }
 
 /*
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 6f164289bde..e242f96550b 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1006,14 +1006,24 @@ static void put_osd(struct ceph_osd *osd)
  */
 static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
 {
-	dout("__remove_osd %p\n", osd);
+	dout("%s %p osd%d\n", __func__, osd, osd->o_osd);
 	WARN_ON(!list_empty(&osd->o_requests));
 	WARN_ON(!list_empty(&osd->o_linger_requests));
 
-	rb_erase(&osd->o_node, &osdc->osds);
 	list_del_init(&osd->o_osd_lru);
-	ceph_con_close(&osd->o_con);
-	put_osd(osd);
+	rb_erase(&osd->o_node, &osdc->osds);
+	RB_CLEAR_NODE(&osd->o_node);
+}
+
+static void remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
+{
+	dout("%s %p osd%d\n", __func__, osd, osd->o_osd);
+
+	if (!RB_EMPTY_NODE(&osd->o_node)) {
+		ceph_con_close(&osd->o_con);
+		__remove_osd(osdc, osd);
+		put_osd(osd);
+	}
 }
 
 static void remove_all_osds(struct ceph_osd_client *osdc)
@@ -1023,7 +1033,7 @@ static void remove_all_osds(struct ceph_osd_client *osdc)
 	while (!RB_EMPTY_ROOT(&osdc->osds)) {
 		struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds),
 						struct ceph_osd, o_node);
-		__remove_osd(osdc, osd);
+		remove_osd(osdc, osd);
 	}
 	mutex_unlock(&osdc->request_mutex);
 }
@@ -1064,7 +1074,7 @@ static void remove_old_osds(struct ceph_osd_client *osdc)
 	list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) {
 		if (time_before(jiffies, osd->lru_ttl))
 			break;
-		__remove_osd(osdc, osd);
+		remove_osd(osdc, osd);
 	}
 	mutex_unlock(&osdc->request_mutex);
 }
@@ -1079,8 +1089,7 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
 	dout("__reset_osd %p osd%d\n", osd, osd->o_osd);
 	if (list_empty(&osd->o_requests) &&
 	    list_empty(&osd->o_linger_requests)) {
-		__remove_osd(osdc, osd);
-
+		remove_osd(osdc, osd);
 		return -ENODEV;
 	}
 
@@ -1254,8 +1263,6 @@ static void __unregister_linger_request(struct ceph_osd_client *osdc,
 		if (list_empty(&req->r_osd_item))
 			req->r_osd = NULL;
 	}
-
-	list_del_init(&req->r_req_lru_item); /* can be on notarget */
 	ceph_osdc_put_request(req);
 }
 
@@ -1884,6 +1891,7 @@ static void reset_changed_osds(struct ceph_osd_client *osdc)
 {
 	struct rb_node *p, *n;
 
+	dout("%s %p\n", __func__, osdc);
 	for (p = rb_first(&osdc->osds); p; p = n) {
 		struct ceph_osd *osd = rb_entry(p, struct ceph_osd, o_node);
 
@@ -1964,20 +1972,29 @@ static void kick_requests(struct ceph_osd_client *osdc, bool force_resend,
 		err = __map_request(osdc, req,
 				    force_resend || force_resend_writes);
 		dout("__map_request returned %d\n", err);
-		if (err == 0)
-			continue;  /* no change and no osd was specified */
 		if (err < 0)
 			continue;  /* hrm! */
-		if (req->r_osd == NULL) {
-			dout("tid %llu maps to no valid osd\n", req->r_tid);
-			needmap++;  /* request a newer map */
-			continue;
-		}
+		if (req->r_osd == NULL || err > 0) {
+			if (req->r_osd == NULL) {
+				dout("lingering %p tid %llu maps to no osd\n",
+				     req, req->r_tid);
+				/*
+				 * A homeless lingering request makes
+				 * no sense, as it's job is to keep
+				 * a particular OSD connection open.
+				 * Request a newer map and kick the
+				 * request, knowing that it won't be
+				 * resent until we actually get a map
+				 * that can tell us where to send it.
+				 */
+				needmap++;
+			}
 
-		dout("kicking lingering %p tid %llu osd%d\n", req, req->r_tid,
-		     req->r_osd ? req->r_osd->o_osd : -1);
-		__register_request(osdc, req);
-		__unregister_linger_request(osdc, req);
+			dout("kicking lingering %p tid %llu osd%d\n", req,
+			     req->r_tid, req->r_osd ? req->r_osd->o_osd : -1);
+			__register_request(osdc, req);
+			__unregister_linger_request(osdc, req);
+		}
 	}
 	reset_changed_osds(osdc);
 	mutex_unlock(&osdc->request_mutex);
diff --git a/net/compat.c b/net/compat.c
index bc8aeefddf3..53e933eb78b 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -71,6 +71,13 @@ int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg)
 	    __get_user(kmsg->msg_controllen, &umsg->msg_controllen) ||
 	    __get_user(kmsg->msg_flags, &umsg->msg_flags))
 		return -EFAULT;
+
+	if (!tmp1)
+		kmsg->msg_namelen = 0;
+
+	if (kmsg->msg_namelen < 0)
+		return -EINVAL;
+
 	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
 		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
 	kmsg->msg_name = compat_ptr(tmp1);
@@ -738,24 +745,18 @@ static unsigned char nas[21] = {
 
 COMPAT_SYSCALL_DEFINE3(sendmsg, int, fd, struct compat_msghdr __user *, msg, unsigned int, flags)
 {
-	if (flags & MSG_CMSG_COMPAT)
-		return -EINVAL;
 	return __sys_sendmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
 }
 
 COMPAT_SYSCALL_DEFINE4(sendmmsg, int, fd, struct compat_mmsghdr __user *, mmsg,
 		       unsigned int, vlen, unsigned int, flags)
 {
-	if (flags & MSG_CMSG_COMPAT)
-		return -EINVAL;
 	return __sys_sendmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
 			      flags | MSG_CMSG_COMPAT);
 }
 
 COMPAT_SYSCALL_DEFINE3(recvmsg, int, fd, struct compat_msghdr __user *, msg, unsigned int, flags)
 {
-	if (flags & MSG_CMSG_COMPAT)
-		return -EINVAL;
 	return __sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
 }
 
@@ -778,9 +779,6 @@ COMPAT_SYSCALL_DEFINE5(recvmmsg, int, fd, struct compat_mmsghdr __user *, mmsg,
 	int datagrams;
 	struct timespec ktspec;
 
-	if (flags & MSG_CMSG_COMPAT)
-		return -EINVAL;
-
 	if (timeout == NULL)
 		return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
 				      flags | MSG_CMSG_COMPAT, NULL);
diff --git a/net/core/dev.c b/net/core/dev.c
index 945bbd00135..fb9625874b3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -943,7 +943,7 @@ bool dev_valid_name(const char *name)
 		return false;
 
 	while (*name) {
-		if (*name == '/' || isspace(*name))
+		if (*name == '/' || *name == ':' || isspace(*name))
 			return false;
 		name++;
 	}
@@ -1697,6 +1697,7 @@ int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 
 	skb_scrub_packet(skb, true);
 	skb->protocol = eth_type_trans(skb, dev);
+	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
 
 	return 0;
 }
@@ -2565,7 +2566,7 @@ static netdev_features_t harmonize_features(struct sk_buff *skb,
 
 netdev_features_t netif_skb_features(struct sk_buff *skb)
 {
-	const struct net_device *dev = skb->dev;
+	struct net_device *dev = skb->dev;
 	netdev_features_t features = dev->features;
 	u16 gso_segs = skb_shinfo(skb)->gso_segs;
 	__be16 protocol = skb->protocol;
@@ -2573,11 +2574,21 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
 	if (gso_segs > dev->gso_max_segs || gso_segs < dev->gso_min_segs)
 		features &= ~NETIF_F_GSO_MASK;
 
-	if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) {
-		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
-		protocol = veh->h_vlan_encapsulated_proto;
-	} else if (!vlan_tx_tag_present(skb)) {
-		return harmonize_features(skb, features);
+	/* If encapsulation offload request, verify we are testing
+	 * hardware encapsulation features instead of standard
+	 * features for the netdev
+	 */
+	if (skb->encapsulation)
+		features &= dev->hw_enc_features;
+
+	if (!vlan_tx_tag_present(skb)) {
+		if (unlikely(protocol == htons(ETH_P_8021Q) ||
+			     protocol == htons(ETH_P_8021AD))) {
+			struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
+			protocol = veh->h_vlan_encapsulated_proto;
+		} else {
+			goto finalize;
+		}
 	}
 
 	features = netdev_intersect_features(features,
@@ -2594,6 +2605,11 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
 						     NETIF_F_HW_VLAN_CTAG_TX |
 						     NETIF_F_HW_VLAN_STAG_TX);
 
+finalize:
+	if (dev->netdev_ops->ndo_features_check)
+		features &= dev->netdev_ops->ndo_features_check(skb, dev,
+								features);
+
 	return harmonize_features(skb, features);
 }
 EXPORT_SYMBOL(netif_skb_features);
@@ -2647,12 +2663,8 @@ static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb,
 					  netdev_features_t features)
 {
 	if (vlan_tx_tag_present(skb) &&
-	    !vlan_hw_offload_capable(features, skb->vlan_proto)) {
-		skb = __vlan_put_tag(skb, skb->vlan_proto,
-				     vlan_tx_tag_get(skb));
-		if (skb)
-			skb->vlan_tci = 0;
-	}
+	    !vlan_hw_offload_capable(features, skb->vlan_proto))
+		skb = __vlan_hwaccel_push_inside(skb);
 	return skb;
 }
 
@@ -2668,19 +2680,12 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
 	if (unlikely(!skb))
 		goto out_null;
 
-	/* If encapsulation offload request, verify we are testing
-	 * hardware encapsulation features instead of standard
-	 * features for the netdev
-	 */
-	if (skb->encapsulation)
-		features &= dev->hw_enc_features;
-
 	if (netif_needs_gso(dev, skb, features)) {
 		struct sk_buff *segs;
 
 		segs = skb_gso_segment(skb, features);
 		if (IS_ERR(segs)) {
-			segs = NULL;
+			goto out_kfree_skb;
 		} else if (segs) {
 			consume_skb(skb);
 			skb = segs;
@@ -2848,7 +2853,9 @@ static void skb_update_prio(struct sk_buff *skb)
 #define skb_update_prio(skb)
 #endif
 
-static DEFINE_PER_CPU(int, xmit_recursion);
+DEFINE_PER_CPU(int, xmit_recursion);
+EXPORT_SYMBOL(xmit_recursion);
+
 #define RECURSION_LIMIT 10
 
 /**
@@ -5073,7 +5080,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper))
 		return -EBUSY;
 
-	if (__netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper))
+	if (__netdev_find_adj(dev, upper_dev, &dev->adj_list.upper))
 		return -EEXIST;
 
 	if (master && netdev_master_upper_dev_get(dev))
@@ -6981,10 +6988,20 @@ static int dev_cpu_callback(struct notifier_block *nfb,
 		oldsd->output_queue = NULL;
 		oldsd->output_queue_tailp = &oldsd->output_queue;
 	}
-	/* Append NAPI poll list from offline CPU. */
-	if (!list_empty(&oldsd->poll_list)) {
-		list_splice_init(&oldsd->poll_list, &sd->poll_list);
-		raise_softirq_irqoff(NET_RX_SOFTIRQ);
+	/* Append NAPI poll list from offline CPU, with one exception :
+	 * process_backlog() must be called by cpu owning percpu backlog.
+	 * We properly handle process_queue & input_pkt_queue later.
+	 */
+	while (!list_empty(&oldsd->poll_list)) {
+		struct napi_struct *napi = list_first_entry(&oldsd->poll_list,
+							    struct napi_struct,
+							    poll_list);
+
+		list_del_init(&napi->poll_list);
+		if (napi->poll == process_backlog)
+			napi->state = 0;
+		else
+			____napi_schedule(sd, napi);
 	}
 
 	raise_softirq_irqoff(NET_TX_SOFTIRQ);
@@ -6995,7 +7012,7 @@ static int dev_cpu_callback(struct notifier_block *nfb,
 		netif_rx_internal(skb);
 		input_queue_head_incr(oldsd);
 	}
-	while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
+	while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) {
 		netif_rx_internal(skb);
 		input_queue_head_incr(oldsd);
 	}
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 185c341fafb..5cbcdfd89f3 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -31,6 +31,8 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
 	r->pref = pref;
 	r->table = table;
 	r->flags = flags;
+	r->uid_start = INVALID_UID;
+	r->uid_end = INVALID_UID;
 	r->fr_net = hold_net(ops->fro_net);
 
 	r->suppress_prefixlen = -1;
@@ -182,6 +184,23 @@ void fib_rules_unregister(struct fib_rules_ops *ops)
 }
 EXPORT_SYMBOL_GPL(fib_rules_unregister);
 
+static inline kuid_t fib_nl_uid(struct nlattr *nla)
+{
+	return make_kuid(current_user_ns(), nla_get_u32(nla));
+}
+
+static int nla_put_uid(struct sk_buff *skb, int idx, kuid_t uid)
+{
+	return nla_put_u32(skb, idx, from_kuid_munged(current_user_ns(), uid));
+}
+
+static int fib_uid_range_match(struct flowi *fl, struct fib_rule *rule)
+{
+	return (!uid_valid(rule->uid_start) && !uid_valid(rule->uid_end)) ||
+	       (uid_gte(fl->flowi_uid, rule->uid_start) &&
+		uid_lte(fl->flowi_uid, rule->uid_end));
+}
+
 static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
 			  struct flowi *fl, int flags)
 {
@@ -196,6 +215,9 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
 	if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask)
 		goto out;
 
+	if (!fib_uid_range_match(fl, rule))
+		goto out;
+
 	ret = ops->match(rule, fl, flags);
 out:
 	return (rule->flags & FIB_RULE_INVERT) ? !ret : ret;
@@ -378,6 +400,19 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 	} else if (rule->action == FR_ACT_GOTO)
 		goto errout_free;
 
+	/* UID start and end must either both be valid or both unspecified. */
+	rule->uid_start = rule->uid_end = INVALID_UID;
+	if (tb[FRA_UID_START] || tb[FRA_UID_END]) {
+		if (tb[FRA_UID_START] && tb[FRA_UID_END]) {
+			rule->uid_start = fib_nl_uid(tb[FRA_UID_START]);
+			rule->uid_end = fib_nl_uid(tb[FRA_UID_END]);
+		}
+		if (!uid_valid(rule->uid_start) ||
+		    !uid_valid(rule->uid_end) ||
+		    !uid_lte(rule->uid_start, rule->uid_end))
+		goto errout_free;
+	}
+
 	err = ops->configure(rule, skb, frh, tb);
 	if (err < 0)
 		goto errout_free;
@@ -484,6 +519,14 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 		    (rule->mark_mask != nla_get_u32(tb[FRA_FWMASK])))
 			continue;
 
+		if (tb[FRA_UID_START] &&
+		    !uid_eq(rule->uid_start, fib_nl_uid(tb[FRA_UID_START])))
+			continue;
+
+		if (tb[FRA_UID_END] &&
+		    !uid_eq(rule->uid_end, fib_nl_uid(tb[FRA_UID_END])))
+			continue;
+
 		if (!ops->compare(rule, frh, tb))
 			continue;
 
@@ -542,7 +585,9 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
 			 + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */
 			 + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */
 			 + nla_total_size(4) /* FRA_FWMARK */
-			 + nla_total_size(4); /* FRA_FWMASK */
+			 + nla_total_size(4) /* FRA_FWMASK */
+			 + nla_total_size(4) /* FRA_UID_START */
+			 + nla_total_size(4); /* FRA_UID_END */
 
 	if (ops->nlmsg_payload)
 		payload += ops->nlmsg_payload(rule);
@@ -598,7 +643,11 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 	    ((rule->mark_mask || rule->mark) &&
 	     nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) ||
 	    (rule->target &&
-	     nla_put_u32(skb, FRA_GOTO, rule->target)))
+	     nla_put_u32(skb, FRA_GOTO, rule->target)) ||
+	    (uid_valid(rule->uid_start) &&
+	     nla_put_uid(skb, FRA_UID_START, rule->uid_start)) ||
+	    (uid_valid(rule->uid_end) &&
+	     nla_put_uid(skb, FRA_UID_END, rule->uid_end)))
 		goto nla_put_failure;
 
 	if (rule->suppress_ifgroup != -1) {
diff --git a/net/core/flow.c b/net/core/flow.c
index a0348fde1fd..1033725be40 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -379,7 +379,7 @@ done:
 static void flow_cache_flush_task(struct work_struct *work)
 {
 	struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
-						flow_cache_gc_work);
+						flow_cache_flush_work);
 	struct net *net = container_of(xfrm, struct net, xfrm);
 
 	flow_cache_flush(net);
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 0c08062d179..1e2f46a69d5 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -32,6 +32,9 @@ gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size)
 	return 0;
 
 nla_put_failure:
+	kfree(d->xstats);
+	d->xstats = NULL;
+	d->xstats_len = 0;
 	spin_unlock_bh(d->lock);
 	return -1;
 }
@@ -305,7 +308,9 @@ int
 gnet_stats_copy_app(struct gnet_dump *d, void *st, int len)
 {
 	if (d->compat_xstats) {
-		d->xstats = st;
+		d->xstats = kmemdup(st, len, GFP_ATOMIC);
+		if (!d->xstats)
+			goto err_out;
 		d->xstats_len = len;
 	}
 
@@ -313,6 +318,11 @@ gnet_stats_copy_app(struct gnet_dump *d, void *st, int len)
 		return gnet_stats_copy(d, TCA_STATS_APP, st, len);
 
 	return 0;
+
+err_out:
+	d->xstats_len = 0;
+	spin_unlock_bh(d->lock);
+	return -1;
 }
 EXPORT_SYMBOL(gnet_stats_copy_app);
 
@@ -345,6 +355,9 @@ gnet_stats_finish_copy(struct gnet_dump *d)
 			return -1;
 	}
 
+	kfree(d->xstats);
+	d->xstats = NULL;
+	d->xstats_len = 0;
 	spin_unlock_bh(d->lock);
 	return 0;
 }
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index ef31fef25e5..2b0d99dad8b 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -977,6 +977,8 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 	rc = 0;
 	if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))
 		goto out_unlock_bh;
+	if (neigh->dead)
+		goto out_dead;
 
 	if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) {
 		if (NEIGH_VAR(neigh->parms, MCAST_PROBES) +
@@ -1033,6 +1035,13 @@ out_unlock_bh:
 		write_unlock(&neigh->lock);
 	local_bh_enable();
 	return rc;
+
+out_dead:
+	if (neigh->nud_state & NUD_STALE)
+		goto out_unlock_bh;
+	write_unlock_bh(&neigh->lock);
+	kfree_skb(skb);
+	return 1;
 }
 EXPORT_SYMBOL(__neigh_event_send);
 
@@ -1096,6 +1105,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 	if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
 	    (old & (NUD_NOARP | NUD_PERMANENT)))
 		goto out;
+	if (neigh->dead)
+		goto out;
 
 	if (!(new & NUD_VALID)) {
 		neigh_del_timer(neigh);
@@ -1245,6 +1256,8 @@ EXPORT_SYMBOL(neigh_update);
  */
 void __neigh_set_probe_once(struct neighbour *neigh)
 {
+	if (neigh->dead)
+		return;
 	neigh->updated = jiffies;
 	if (!(neigh->nud_state & NUD_FAILED))
 		return;
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index e6645b4f330..e0ad5d16c9c 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -79,8 +79,7 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	if (vlan_tx_tag_present(skb) &&
 	    !vlan_hw_offload_capable(features, skb->vlan_proto)) {
-		skb = __vlan_put_tag(skb, skb->vlan_proto,
-				     vlan_tx_tag_get(skb));
+		skb = __vlan_hwaccel_push_inside(skb);
 		if (unlikely(!skb)) {
 			/* This is actually a packet drop, but we
 			 * don't want the code that calls this
@@ -88,7 +87,6 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			 */
 			goto out;
 		}
-		skb->vlan_tci = 0;
 	}
 
 	status = netdev_start_xmit(skb, dev, txq, false);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 443256bdcdd..0b320d93fb5 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -1134,6 +1134,9 @@ static ssize_t pktgen_if_write(struct file *file,
 			return len;
 
 		i += len;
+		if ((value > 1) &&
+		    (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING)))
+			return -ENOTSUPP;
 		pkt_dev->burst = value < 1 ? 1 : value;
 		sprintf(pg_result, "OK: burst=%d", pkt_dev->burst);
 		return count;
@@ -2842,25 +2845,25 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
 	skb->dev = odev;
 	skb->pkt_type = PACKET_HOST;
 
+	pktgen_finalize_skb(pkt_dev, skb, datalen);
+
 	if (!(pkt_dev->flags & F_UDPCSUM)) {
 		skb->ip_summed = CHECKSUM_NONE;
 	} else if (odev->features & NETIF_F_V4_CSUM) {
 		skb->ip_summed = CHECKSUM_PARTIAL;
 		skb->csum = 0;
-		udp4_hwcsum(skb, udph->source, udph->dest);
+		udp4_hwcsum(skb, iph->saddr, iph->daddr);
 	} else {
-		__wsum csum = udp_csum(skb);
+		__wsum csum = skb_checksum(skb, skb_transport_offset(skb), datalen + 8, 0);
 
 		/* add protocol-dependent pseudo-header */
-		udph->check = csum_tcpudp_magic(udph->source, udph->dest,
+		udph->check = csum_tcpudp_magic(iph->saddr, iph->daddr,
 						datalen + 8, IPPROTO_UDP, csum);
 
 		if (udph->check == 0)
 			udph->check = CSUM_MANGLED_0;
 	}
 
-	pktgen_finalize_skb(pkt_dev, skb, datalen);
-
 #ifdef CONFIG_XFRM
 	if (!process_ipsec(pkt_dev, skb, protocol))
 		return NULL;
@@ -2976,6 +2979,8 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
 	skb->dev = odev;
 	skb->pkt_type = PACKET_HOST;
 
+	pktgen_finalize_skb(pkt_dev, skb, datalen);
+
 	if (!(pkt_dev->flags & F_UDPCSUM)) {
 		skb->ip_summed = CHECKSUM_NONE;
 	} else if (odev->features & NETIF_F_V6_CSUM) {
@@ -2984,7 +2989,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
 		skb->csum_offset = offsetof(struct udphdr, check);
 		udph->check = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, 0);
 	} else {
-		__wsum csum = udp_csum(skb);
+		__wsum csum = skb_checksum(skb, skb_transport_offset(skb), udplen, 0);
 
 		/* add protocol-dependent pseudo-header */
 		udph->check = csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, csum);
@@ -2993,8 +2998,6 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
 			udph->check = CSUM_MANGLED_0;
 	}
 
-	pktgen_finalize_skb(pkt_dev, skb, datalen);
-
 	return skb;
 }
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 76321ea442c..c522f7a00ea 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1212,18 +1212,12 @@ static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = {
 };
 
 static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
-	[IFLA_VF_MAC]		= { .type = NLA_BINARY,
-				    .len = sizeof(struct ifla_vf_mac) },
-	[IFLA_VF_VLAN]		= { .type = NLA_BINARY,
-				    .len = sizeof(struct ifla_vf_vlan) },
-	[IFLA_VF_TX_RATE]	= { .type = NLA_BINARY,
-				    .len = sizeof(struct ifla_vf_tx_rate) },
-	[IFLA_VF_SPOOFCHK]	= { .type = NLA_BINARY,
-				    .len = sizeof(struct ifla_vf_spoofchk) },
-	[IFLA_VF_RATE]		= { .type = NLA_BINARY,
-				    .len = sizeof(struct ifla_vf_rate) },
-	[IFLA_VF_LINK_STATE]	= { .type = NLA_BINARY,
-				    .len = sizeof(struct ifla_vf_link_state) },
+	[IFLA_VF_MAC]		= { .len = sizeof(struct ifla_vf_mac) },
+	[IFLA_VF_VLAN]		= { .len = sizeof(struct ifla_vf_vlan) },
+	[IFLA_VF_TX_RATE]	= { .len = sizeof(struct ifla_vf_tx_rate) },
+	[IFLA_VF_SPOOFCHK]	= { .len = sizeof(struct ifla_vf_spoofchk) },
+	[IFLA_VF_RATE]		= { .len = sizeof(struct ifla_vf_rate) },
+	[IFLA_VF_LINK_STATE]	= { .len = sizeof(struct ifla_vf_link_state) },
 };
 
 static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
@@ -1255,7 +1249,6 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	s_h = cb->args[0];
 	s_idx = cb->args[1];
 
-	rcu_read_lock();
 	cb->seq = net->dev_base_seq;
 
 	/* A hack to preserve kernel<->userspace interface.
@@ -1277,7 +1270,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
 		idx = 0;
 		head = &net->dev_index_head[h];
-		hlist_for_each_entry_rcu(dev, head, index_hlist) {
+		hlist_for_each_entry(dev, head, index_hlist) {
 			if (idx < s_idx)
 				goto cont;
 			err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
@@ -1299,7 +1292,6 @@ cont:
 		}
 	}
 out:
-	rcu_read_unlock();
 	cb->args[1] = idx;
 	cb->args[0] = h;
 
@@ -2105,8 +2097,16 @@ replay:
 			}
 		}
 		err = rtnl_configure_link(dev, ifm);
-		if (err < 0)
-			unregister_netdevice(dev);
+		if (err < 0) {
+			if (ops->newlink) {
+				LIST_HEAD(list_kill);
+
+				ops->dellink(dev, &list_kill);
+				unregister_netdevice_many(&list_kill);
+			} else {
+				unregister_netdevice(dev);
+			}
+		}
 out:
 		put_net(dest_net);
 		return err;
@@ -2770,12 +2770,16 @@ static int rtnl_bridge_notify(struct net_device *dev, u16 flags)
 			goto errout;
 	}
 
+	if (!skb->len)
+		goto errout;
+
 	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC);
 	return 0;
 errout:
 	WARN_ON(err == -EMSGSIZE);
 	kfree_skb(skb);
-	rtnl_set_sk_err(net, RTNLGRP_LINK, err);
+	if (err)
+		rtnl_set_sk_err(net, RTNLGRP_LINK, err);
 	return err;
 }
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 32e31c29963..72400a1bb43 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -278,13 +278,14 @@ nodata:
 EXPORT_SYMBOL(__alloc_skb);
 
 /**
- * build_skb - build a network buffer
+ * __build_skb - build a network buffer
  * @data: data buffer provided by caller
- * @frag_size: size of fragment, or 0 if head was kmalloced
+ * @frag_size: size of data, or 0 if head was kmalloced
  *
  * Allocate a new &sk_buff. Caller provides space holding head and
  * skb_shared_info. @data must have been allocated by kmalloc() only if
- * @frag_size is 0, otherwise data should come from the page allocator.
+ * @frag_size is 0, otherwise data should come from the page allocator
+ *  or vmalloc()
  * The return is the new skb buffer.
  * On a failure the return is %NULL, and @data is not freed.
  * Notes :
@@ -295,7 +296,7 @@ EXPORT_SYMBOL(__alloc_skb);
  *  before giving packet to stack.
  *  RX rings only contains data buffers, not full skbs.
  */
-struct sk_buff *build_skb(void *data, unsigned int frag_size)
+struct sk_buff *__build_skb(void *data, unsigned int frag_size)
 {
 	struct skb_shared_info *shinfo;
 	struct sk_buff *skb;
@@ -309,7 +310,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	memset(skb, 0, offsetof(struct sk_buff, tail));
 	skb->truesize = SKB_TRUESIZE(size);
-	skb->head_frag = frag_size != 0;
 	atomic_set(&skb->users, 1);
 	skb->head = data;
 	skb->data = data;
@@ -326,6 +326,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	return skb;
 }
+
+/* build_skb() is wrapper over __build_skb(), that specifically
+ * takes care of skb->head and skb->pfmemalloc
+ * This means that if @frag_size is not zero, then @data must be backed
+ * by a page fragment, not kmalloc() or vmalloc()
+ */
+struct sk_buff *build_skb(void *data, unsigned int frag_size)
+{
+	struct sk_buff *skb = __build_skb(data, frag_size);
+
+	if (skb && frag_size) {
+		skb->head_frag = 1;
+		if (virt_to_head_page(data)->pfmemalloc)
+			skb->pfmemalloc = 1;
+	}
+	return skb;
+}
 EXPORT_SYMBOL(build_skb);
 
 struct netdev_alloc_cache {
@@ -352,7 +369,8 @@ refill:
 			gfp_t gfp = gfp_mask;
 
 			if (order)
-				gfp |= __GFP_COMP | __GFP_NOWARN;
+				gfp |= __GFP_COMP | __GFP_NOWARN |
+				       __GFP_NOMEMALLOC;
 			nc->frag.page = alloc_pages(gfp, order);
 			if (likely(nc->frag.page))
 				break;
@@ -3515,13 +3533,14 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk)
 {
 	struct sk_buff_head *q = &sk->sk_error_queue;
 	struct sk_buff *skb, *skb_next;
+	unsigned long flags;
 	int err = 0;
 
-	spin_lock_bh(&q->lock);
+	spin_lock_irqsave(&q->lock, flags);
 	skb = __skb_dequeue(q);
 	if (skb && (skb_next = skb_peek(q)))
 		err = SKB_EXT_ERR(skb_next)->ee.ee_errno;
-	spin_unlock_bh(&q->lock);
+	spin_unlock_irqrestore(&q->lock, flags);
 
 	sk->sk_err = err;
 	if (err)
@@ -4032,17 +4051,20 @@ EXPORT_SYMBOL(skb_try_coalesce);
  */
 void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 {
-	if (xnet)
-		skb_orphan(skb);
 	skb->tstamp.tv64 = 0;
 	skb->pkt_type = PACKET_HOST;
 	skb->skb_iif = 0;
 	skb->ignore_df = 0;
 	skb_dst_drop(skb);
-	skb->mark = 0;
 	secpath_reset(skb);
 	nf_reset(skb);
 	nf_reset_trace(skb);
+
+	if (!xnet)
+		return;
+
+	skb_orphan(skb);
+	skb->mark = 0;
 }
 EXPORT_SYMBOL_GPL(skb_scrub_packet);
 
@@ -4177,7 +4199,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 
 		while (order) {
 			if (npages >= 1 << order) {
-				page = alloc_pages(gfp_mask |
+				page = alloc_pages((gfp_mask & ~__GFP_WAIT) |
 						   __GFP_COMP |
 						   __GFP_NOWARN |
 						   __GFP_NORETRY,
diff --git a/net/core/sock.c b/net/core/sock.c
index 15e0c67b106..1e5130de31b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -651,6 +651,25 @@ static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool)
 		sock_reset_flag(sk, bit);
 }
 
+bool sk_mc_loop(struct sock *sk)
+{
+	if (dev_recursion_level())
+		return false;
+	if (!sk)
+		return true;
+	switch (sk->sk_family) {
+	case AF_INET:
+		return inet_sk(sk)->mc_loop;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		return inet6_sk(sk)->mc_loop;
+#endif
+	}
+	WARN_ON(1);
+	return true;
+}
+EXPORT_SYMBOL(sk_mc_loop);
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
@@ -1835,7 +1854,7 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp)
 
 	pfrag->offset = 0;
 	if (SKB_FRAG_PAGE_ORDER) {
-		pfrag->page = alloc_pages(gfp | __GFP_COMP |
+		pfrag->page = alloc_pages((gfp & ~__GFP_WAIT) | __GFP_COMP |
 					  __GFP_NOWARN | __GFP_NORETRY,
 					  SKB_FRAG_PAGE_ORDER);
 		if (likely(pfrag->page)) {
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index cf9cd13509a..8725b91120f 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -23,8 +23,9 @@
 #include <net/pkt_sched.h>
 
 static int zero = 0;
-static int one = 1;
 static int ushort_max = USHRT_MAX;
+static int min_sndbuf = SOCK_MIN_SNDBUF;
+static int min_rcvbuf = SOCK_MIN_RCVBUF;
 
 #ifdef CONFIG_RPS
 static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
@@ -223,7 +224,7 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= &min_sndbuf,
 	},
 	{
 		.procname	= "rmem_max",
@@ -231,7 +232,7 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= &min_rcvbuf,
 	},
 	{
 		.procname	= "wmem_default",
@@ -239,7 +240,7 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= &min_sndbuf,
 	},
 	{
 		.procname	= "rmem_default",
@@ -247,7 +248,7 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= &min_rcvbuf,
 	},
 	{
 		.procname	= "dev_weight",
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 518c04ed666..591745df6d5 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -15,6 +15,7 @@ obj-y     := route.o inetpeer.o protocol.o \
 
 obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
 obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
+obj-$(CONFIG_SYSFS) += sysfs_net_ipv4.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o
 obj-$(CONFIG_IP_MROUTE) += ipmr.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e67da4e6c32..401e41e339e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -119,6 +119,19 @@
 #include <linux/mroute.h>
 #endif
 
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+#include <linux/android_aid.h>
+
+static inline int current_has_network(void)
+{
+	return in_egroup_p(AID_INET) || capable(CAP_NET_RAW);
+}
+#else
+static inline int current_has_network(void)
+{
+	return 1;
+}
+#endif
 
 /* The inetsw table contains everything that inet_create needs to
  * build a new socket.
@@ -228,6 +241,8 @@ int inet_listen(struct socket *sock, int backlog)
 				err = 0;
 			if (err)
 				goto out;
+
+			tcp_fastopen_init_key_once(true);
 		}
 		err = inet_csk_listen_start(sk, backlog);
 		if (err)
@@ -257,6 +272,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
 	int try_loading_module = 0;
 	int err;
 
+	if (!current_has_network())
+		return -EACCES;
+
 	sock->state = SS_UNCONNECTED;
 
 	/* Look for the requested type/protocol pair. */
@@ -305,8 +323,7 @@ lookup_protocol:
 	}
 
 	err = -EPERM;
-	if (sock->type == SOCK_RAW && !kern &&
-	    !ns_capable(net->user_ns, CAP_NET_RAW))
+	if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
 		goto out_rcu_unlock;
 
 	sock->ops = answer->ops;
@@ -868,6 +885,7 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	case SIOCSIFPFLAGS:
 	case SIOCGIFPFLAGS:
 	case SIOCSIFFLAGS:
+	case SIOCKILLADDR:
 		err = devinet_ioctl(net, cmd, (void __user *)arg);
 		break;
 	default:
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 4715f25dfe0..bc7c9662a90 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -376,20 +376,18 @@ static int cipso_v4_cache_check(const unsigned char *key,
  * negative values on failure.
  *
  */
-int cipso_v4_cache_add(const struct sk_buff *skb,
+int cipso_v4_cache_add(const unsigned char *cipso_ptr,
 		       const struct netlbl_lsm_secattr *secattr)
 {
 	int ret_val = -EPERM;
 	u32 bkt;
 	struct cipso_v4_map_cache_entry *entry = NULL;
 	struct cipso_v4_map_cache_entry *old_entry = NULL;
-	unsigned char *cipso_ptr;
 	u32 cipso_ptr_len;
 
 	if (!cipso_v4_cache_enabled || cipso_v4_cache_bucketsize <= 0)
 		return 0;
 
-	cipso_ptr = CIPSO_V4_OPTPTR(skb);
 	cipso_ptr_len = cipso_ptr[1];
 
 	entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
@@ -1577,6 +1575,33 @@ static int cipso_v4_parsetag_loc(const struct cipso_v4_doi *doi_def,
 }
 
 /**
+ * cipso_v4_optptr - Find the CIPSO option in the packet
+ * @skb: the packet
+ *
+ * Description:
+ * Parse the packet's IP header looking for a CIPSO option.  Returns a pointer
+ * to the start of the CIPSO option on success, NULL if one if not found.
+ *
+ */
+unsigned char *cipso_v4_optptr(const struct sk_buff *skb)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	unsigned char *optptr = (unsigned char *)&(ip_hdr(skb)[1]);
+	int optlen;
+	int taglen;
+
+	for (optlen = iph->ihl*4 - sizeof(struct iphdr); optlen > 0; ) {
+		if (optptr[0] == IPOPT_CIPSO)
+			return optptr;
+		taglen = optptr[1];
+		optlen -= taglen;
+		optptr += taglen;
+	}
+
+	return NULL;
+}
+
+/**
  * cipso_v4_validate - Validate a CIPSO option
  * @option: the start of the option, on error it is set to point to the error
  *
@@ -2117,8 +2142,8 @@ void cipso_v4_req_delattr(struct request_sock *req)
  * on success and negative values on failure.
  *
  */
-static int cipso_v4_getattr(const unsigned char *cipso,
-			    struct netlbl_lsm_secattr *secattr)
+int cipso_v4_getattr(const unsigned char *cipso,
+		     struct netlbl_lsm_secattr *secattr)
 {
 	int ret_val = -ENOMSG;
 	u32 doi;
@@ -2303,22 +2328,6 @@ int cipso_v4_skbuff_delattr(struct sk_buff *skb)
 	return 0;
 }
 
-/**
- * cipso_v4_skbuff_getattr - Get the security attributes from the CIPSO option
- * @skb: the packet
- * @secattr: the security attributes
- *
- * Description:
- * Parse the given packet's CIPSO option and return the security attributes.
- * Returns zero on success and negative values on failure.
- *
- */
-int cipso_v4_skbuff_getattr(const struct sk_buff *skb,
-			    struct netlbl_lsm_secattr *secattr)
-{
-	return cipso_v4_getattr(CIPSO_V4_OPTPTR(skb), secattr);
-}
-
 /*
  * Setup Functions
  */
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 214882e7d6d..629ee7b96bb 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -59,6 +59,7 @@
 
 #include <net/arp.h>
 #include <net/ip.h>
+#include <net/tcp.h>
 #include <net/route.h>
 #include <net/ip_fib.h>
 #include <net/rtnetlink.h>
@@ -934,6 +935,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 	case SIOCSIFBRDADDR:	/* Set the broadcast address */
 	case SIOCSIFDSTADDR:	/* Set the destination address */
 	case SIOCSIFNETMASK: 	/* Set the netmask for the interface */
+	case SIOCKILLADDR:	/* Nuke all sockets on this address */
 		ret = -EPERM;
 		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			goto out;
@@ -985,7 +987,8 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 	}
 
 	ret = -EADDRNOTAVAIL;
-	if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS)
+	if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS
+	    && cmd != SIOCKILLADDR)
 		goto done;
 
 	switch (cmd) {
@@ -1112,6 +1115,9 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 			inet_insert_ifa(ifa);
 		}
 		break;
+	case SIOCKILLADDR:	/* Nuke all connections on this address */
+		ret = tcp_nuke_addr(net, (struct sockaddr *) sin);
+		break;
 	}
 done:
 	rtnl_unlock();
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 23104a3f292..69facd48893 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -533,6 +533,7 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
 	[RTA_METRICS]		= { .type = NLA_NESTED },
 	[RTA_MULTIPATH]		= { .len = sizeof(struct rtnexthop) },
 	[RTA_FLOW]		= { .type = NLA_U32 },
+	[RTA_UID]		= { .type = NLA_U32 },
 };
 
 static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c
index dedb21e9991..d5423e33d32 100644
--- a/net/ipv4/geneve.c
+++ b/net/ipv4/geneve.c
@@ -121,8 +121,6 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
 	int min_headroom;
 	int err;
 
-	skb = udp_tunnel_handle_offloads(skb, !gs->sock->sk->sk_no_check_tx);
-
 	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
 			+ GENEVE_BASE_HLEN + opt_len + sizeof(struct iphdr)
 			+ (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
@@ -131,15 +129,13 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
 	if (unlikely(err))
 		return err;
 
-	if (vlan_tx_tag_present(skb)) {
-		if (unlikely(!__vlan_put_tag(skb,
-					     skb->vlan_proto,
-					     vlan_tx_tag_get(skb)))) {
-			err = -ENOMEM;
-			return err;
-		}
-		skb->vlan_tci = 0;
-	}
+	skb = vlan_hwaccel_push_inside(skb);
+	if (unlikely(!skb))
+		return -ENOMEM;
+
+	skb = udp_tunnel_handle_offloads(skb, !gs->sock->sk->sk_no_check_tx);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
 
 	gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len);
 	geneve_build_header(gnvh, tun_flags, vni, opt_len, opt);
@@ -165,6 +161,15 @@ static void geneve_notify_add_rx_port(struct geneve_sock *gs)
 	}
 }
 
+static void geneve_notify_del_rx_port(struct geneve_sock *gs)
+{
+	struct sock *sk = gs->sock->sk;
+	sa_family_t sa_family = sk->sk_family;
+
+	if (sa_family == AF_INET)
+		udp_del_offload(&gs->udp_offloads);
+}
+
 /* Callback from net/ipv4/udp.c to receive packets */
 static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 {
@@ -293,6 +298,7 @@ struct geneve_sock *geneve_sock_add(struct net *net, __be16 port,
 				    geneve_rcv_t *rcv, void *data,
 				    bool no_share, bool ipv6)
 {
+	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_sock *gs;
 
 	gs = geneve_socket_create(net, port, rcv, data, ipv6);
@@ -302,15 +308,15 @@ struct geneve_sock *geneve_sock_add(struct net *net, __be16 port,
 	if (no_share)	/* Return error if sharing is not allowed. */
 		return ERR_PTR(-EINVAL);
 
+	spin_lock(&gn->sock_lock);
 	gs = geneve_find_sock(net, port);
-	if (gs) {
-		if (gs->rcv == rcv)
-			atomic_inc(&gs->refcnt);
-		else
+	if (gs && ((gs->rcv != rcv) ||
+		   !atomic_add_unless(&gs->refcnt, 1, 0)))
 			gs = ERR_PTR(-EBUSY);
-	} else {
+	spin_unlock(&gn->sock_lock);
+
+	if (!gs)
 		gs = ERR_PTR(-EINVAL);
-	}
 
 	return gs;
 }
@@ -318,9 +324,17 @@ EXPORT_SYMBOL_GPL(geneve_sock_add);
 
 void geneve_sock_release(struct geneve_sock *gs)
 {
+	struct net *net = sock_net(gs->sock->sk);
+	struct geneve_net *gn = net_generic(net, geneve_net_id);
+
 	if (!atomic_dec_and_test(&gs->refcnt))
 		return;
 
+	spin_lock(&gn->sock_lock);
+	hlist_del_rcu(&gs->hlist);
+	geneve_notify_del_rx_port(gs);
+	spin_unlock(&gn->sock_lock);
+
 	queue_work(geneve_wq, &gs->del_work);
 }
 EXPORT_SYMBOL_GPL(geneve_sock_release);
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index bb5947b0ce2..51973ddc05a 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -247,6 +247,9 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff)
 		err = ptype->callbacks.gro_complete(skb, nhoff + grehlen);
 
 	rcu_read_unlock();
+
+	skb_set_inner_mac_header(skb, nhoff + grehlen);
+
 	return err;
 }
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 14d02ea905b..1756f5643f2 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -410,7 +410,8 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 			   sk->sk_protocol,
 			   flags,
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
-			   ireq->ir_loc_addr, ireq->ir_rmt_port, inet_sk(sk)->inet_sport);
+			   ireq->ir_loc_addr, ireq->ir_rmt_port, inet_sk(sk)->inet_sport,
+			   sock_i_uid(sk));
 	security_req_classify_flow(req, flowi4_to_flowi(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
@@ -446,7 +447,8 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
-			   ireq->ir_loc_addr, ireq->ir_rmt_port, inet_sk(sk)->inet_sport);
+			   ireq->ir_loc_addr, ireq->ir_rmt_port, inet_sk(sk)->inet_sport,
+			   sock_i_uid(sk));
 	security_req_classify_flow(req, flowi4_to_flowi(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index e34dccbc4d7..4eeba4e497a 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -71,6 +71,20 @@ static inline void inet_diag_unlock_handler(
 	mutex_unlock(&inet_diag_table_mutex);
 }
 
+static size_t inet_sk_attr_size(void)
+{
+	return	  nla_total_size(sizeof(struct tcp_info))
+		+ nla_total_size(1) /* INET_DIAG_SHUTDOWN */
+		+ nla_total_size(1) /* INET_DIAG_TOS */
+		+ nla_total_size(1) /* INET_DIAG_TCLASS */
+		+ nla_total_size(sizeof(struct inet_diag_meminfo))
+		+ nla_total_size(sizeof(struct inet_diag_msg))
+		+ nla_total_size(SK_MEMINFO_VARS * sizeof(u32))
+		+ nla_total_size(TCP_CA_NAME_MAX)
+		+ nla_total_size(sizeof(struct tcpvegas_info))
+		+ 64;
+}
+
 int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 			      struct sk_buff *skb, struct inet_diag_req_v2 *req,
 			      struct user_namespace *user_ns,		      	
@@ -324,9 +338,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_s
 	if (err)
 		goto out;
 
-	rep = nlmsg_new(sizeof(struct inet_diag_msg) +
-			sizeof(struct inet_diag_meminfo) +
-			sizeof(struct tcp_info) + 64, GFP_KERNEL);
+	rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL);
 	if (!rep) {
 		err = -ENOMEM;
 		goto out;
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 3a83ce5efa8..d5410b57da1 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -81,6 +81,9 @@ int ip_forward(struct sk_buff *skb)
 	if (skb->pkt_type != PACKET_HOST)
 		goto drop;
 
+	if (unlikely(skb->sk))
+		goto drop;
+
 	if (skb_warn_if_lro(skb))
 		goto drop;
 
@@ -129,7 +132,8 @@ int ip_forward(struct sk_buff *skb)
 	 *	We now generate an ICMP HOST REDIRECT giving the route
 	 *	we calculated.
 	 */
-	if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb))
+	if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr &&
+	    !skb_sec_path(skb))
 		ip_rt_send_redirect(skb);
 
 	skb->priority = rt_tos2priority(iph->tos);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 2811cc18701..b48e03cd665 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -660,27 +660,30 @@ EXPORT_SYMBOL(ip_defrag);
 struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
 {
 	struct iphdr iph;
+	int netoff;
 	u32 len;
 
 	if (skb->protocol != htons(ETH_P_IP))
 		return skb;
 
-	if (!skb_copy_bits(skb, 0, &iph, sizeof(iph)))
+	netoff = skb_network_offset(skb);
+
+	if (skb_copy_bits(skb, netoff, &iph, sizeof(iph)) < 0)
 		return skb;
 
 	if (iph.ihl < 5 || iph.version != 4)
 		return skb;
 
 	len = ntohs(iph.tot_len);
-	if (skb->len < len || len < (iph.ihl * 4))
+	if (skb->len < netoff + len || len < (iph.ihl * 4))
 		return skb;
 
 	if (ip_is_fragment(&iph)) {
 		skb = skb_share_check(skb, GFP_ATOMIC);
 		if (skb) {
-			if (!pskb_may_pull(skb, iph.ihl*4))
+			if (!pskb_may_pull(skb, netoff + iph.ihl * 4))
 				return skb;
-			if (pskb_trim_rcsum(skb, len))
+			if (pskb_trim_rcsum(skb, netoff + len))
 				return skb;
 			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
 			if (ip_defrag(skb, user))
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 12055fdbe71..69aaf0a2c42 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -252,10 +252,6 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	const struct iphdr *tnl_params;
 
-	skb = gre_handle_offloads(skb, !!(tunnel->parms.o_flags&TUNNEL_CSUM));
-	if (IS_ERR(skb))
-		goto out;
-
 	if (dev->header_ops) {
 		/* Need space for new headers */
 		if (skb_cow_head(skb, dev->needed_headroom -
@@ -268,6 +264,7 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
 		 * to gre header.
 		 */
 		skb_pull(skb, tunnel->hlen + sizeof(struct iphdr));
+		skb_reset_mac_header(skb);
 	} else {
 		if (skb_cow_head(skb, dev->needed_headroom))
 			goto free_skb;
@@ -275,6 +272,10 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
 		tnl_params = &tunnel->parms.iph;
 	}
 
+	skb = gre_handle_offloads(skb, !!(tunnel->parms.o_flags&TUNNEL_CSUM));
+	if (IS_ERR(skb))
+		goto out;
+
 	__gre_xmit(skb, dev, tnl_params, skb->protocol);
 
 	return NETDEV_TX_OK;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index bc6471d4abc..edf54b04448 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -890,7 +890,8 @@ static int __ip_append_data(struct sock *sk,
 	cork->length += length;
 	if (((length > mtu) || (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
-	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) {
+	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
+	    (sk->sk_type == SOCK_DGRAM)) {
 		err = ip_ufo_append_data(sk, queue, getfrag, from, length,
 					 hh_len, fragheaderlen, transhdrlen,
 					 maxfraglen, flags);
@@ -1506,23 +1507,8 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset,
 /*
  *	Generic function to send a packet as reply to another packet.
  *	Used to send some TCP resets/acks so far.
- *
- *	Use a fake percpu inet socket to avoid false sharing and contention.
  */
-static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = {
-	.sk = {
-		.__sk_common = {
-			.skc_refcnt = ATOMIC_INIT(1),
-		},
-		.sk_wmem_alloc	= ATOMIC_INIT(1),
-		.sk_allocation	= GFP_ATOMIC,
-		.sk_flags	= (1UL << SOCK_USE_WRITE_QUEUE),
-	},
-	.pmtudisc	= IP_PMTUDISC_WANT,
-	.uc_ttl		= -1,
-};
-
-void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
+void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			   const struct ip_options *sopt,
 			   __be32 daddr, __be32 saddr,
 			   const struct ip_reply_arg *arg,
@@ -1532,9 +1518,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
 	struct ipcm_cookie ipc;
 	struct flowi4 fl4;
 	struct rtable *rt = skb_rtable(skb);
+	struct net *net = sock_net(sk);
 	struct sk_buff *nskb;
-	struct sock *sk;
-	struct inet_sock *inet;
 	int err;
 
 	if (__ip_options_echo(&replyopts.opt.opt, skb, sopt))
@@ -1559,21 +1544,18 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
 			   RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol,
 			   ip_reply_arg_flowi_flags(arg),
 			   daddr, saddr,
-			   tcp_hdr(skb)->source, tcp_hdr(skb)->dest);
+			   tcp_hdr(skb)->source, tcp_hdr(skb)->dest,
+			   arg->uid);
 	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_key(net, &fl4);
 	if (IS_ERR(rt))
 		return;
 
-	inet = &get_cpu_var(unicast_sock);
+	inet_sk(sk)->tos = arg->tos;
 
-	inet->tos = arg->tos;
-	sk = &inet->sk;
 	sk->sk_priority = skb->priority;
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
-	sock_net_set(sk, net);
-	__skb_queue_head_init(&sk->sk_write_queue);
 	sk->sk_sndbuf = sysctl_wmem_default;
 	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
 			     len, 0, &ipc, &rt, MSG_DONTWAIT);
@@ -1589,13 +1571,10 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
 			  arg->csumoffset) = csum_fold(csum_add(nskb->csum,
 								arg->csum));
 		nskb->ip_summed = CHECKSUM_NONE;
-		skb_orphan(nskb);
 		skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb));
 		ip_push_pending_frames(sk, &fl4);
 	}
 out:
-	put_cpu_var(unicast_sock);
-
 	ip_rt_put(rt);
 }
 
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 9daf2177dc0..046fce012da 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -443,15 +443,11 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
 	sin = &errhdr.offender;
-	sin->sin_family = AF_UNSPEC;
+	memset(sin, 0, sizeof(*sin));
 	if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) {
-		struct inet_sock *inet = inet_sk(sk);
-
 		sin->sin_family = AF_INET;
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
-		sin->sin_port = 0;
-		memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
-		if (inet->cmsg_flags)
+		if (inet_sk(sk)->cmsg_flags)
 			ip_cmsg_recv(msg, skb);
 	}
 
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 5d740cccf69..ca95839a90c 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -158,6 +158,7 @@ void ping_unhash(struct sock *sk)
 	if (sk_hashed(sk)) {
 		write_lock_bh(&ping_table.lock);
 		hlist_nulls_del(&sk->sk_nulls_node);
+		sk_nulls_node_init(&sk->sk_nulls_node);
 		sock_put(sk);
 		isk->inet_num = 0;
 		isk->inet_sport = 0;
@@ -259,6 +260,9 @@ int ping_init_sock(struct sock *sk)
 	kgid_t low, high;
 	int ret = 0;
 
+	if (sk->sk_family == AF_INET6)
+		sk->sk_ipv6only = 1;
+
 	inet_get_ping_group_range_net(net, &low, &high);
 	if (gid_lte(low, group) && gid_lte(group, high))
 		return 0;
@@ -305,6 +309,11 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
 		if (addr_len < sizeof(*addr))
 			return -EINVAL;
 
+		if (addr->sin_family != AF_INET &&
+		    !(addr->sin_family == AF_UNSPEC &&
+		      addr->sin_addr.s_addr == htonl(INADDR_ANY)))
+			return -EAFNOSUPPORT;
+
 		pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n",
 			 sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port));
 
@@ -330,7 +339,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
 			return -EINVAL;
 
 		if (addr->sin6_family != AF_INET6)
-			return -EINVAL;
+			return -EAFNOSUPPORT;
 
 		pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n",
 			 sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port));
@@ -716,7 +725,7 @@ static int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 		if (msg->msg_namelen < sizeof(*usin))
 			return -EINVAL;
 		if (usin->sin_family != AF_INET)
-			return -EINVAL;
+			return -EAFNOSUPPORT;
 		daddr = usin->sin_addr.s_addr;
 		/* no remote port */
 	} else {
@@ -780,7 +789,8 @@ static int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 
 	flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
 			   RT_SCOPE_UNIVERSE, sk->sk_protocol,
-			   inet_sk_flowi_flags(sk), faddr, saddr, 0, 0);
+			   inet_sk_flowi_flags(sk), faddr, saddr, 0, 0,
+			   sock_i_uid(sk));
 
 	security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_flow(net, &fl4, sk);
@@ -965,8 +975,11 @@ void ping_rcv(struct sk_buff *skb)
 
 	sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
 	if (sk != NULL) {
+		struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
+
 		pr_debug("rcv on socket %p\n", sk);
-		ping_queue_rcv_skb(sk, skb_get(skb));
+		if (skb2)
+			ping_queue_rcv_skb(sk, skb2);
 		sock_put(sk);
 		return;
 	}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 739db3100c2..6167b55fa06 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -582,7 +582,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			   inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
 			   inet_sk_flowi_flags(sk) |
 			    (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
-			   daddr, saddr, 0, 0);
+			   daddr, saddr, 0, 0,
+			   sock_i_uid(sk));
 
 	if (!inet->hdrincl) {
 		err = raw_probe_proto_opt(&fl4, msg);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6a2155b0260..f5174c8fe0c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -499,7 +499,7 @@ void __ip_select_ident(struct iphdr *iph, int segs)
 }
 EXPORT_SYMBOL(__ip_select_ident);
 
-static void __build_flow_key(struct flowi4 *fl4, const struct sock *sk,
+static void __build_flow_key(struct flowi4 *fl4, struct sock *sk,
 			     const struct iphdr *iph,
 			     int oif, u8 tos,
 			     u8 prot, u32 mark, int flow_flags)
@@ -515,11 +515,12 @@ static void __build_flow_key(struct flowi4 *fl4, const struct sock *sk,
 	flowi4_init_output(fl4, oif, mark, tos,
 			   RT_SCOPE_UNIVERSE, prot,
 			   flow_flags,
-			   iph->daddr, iph->saddr, 0, 0);
+			   iph->daddr, iph->saddr, 0, 0,
+			   sk ? sock_i_uid(sk) : GLOBAL_ROOT_UID);
 }
 
 static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb,
-			       const struct sock *sk)
+			       struct sock *sk)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	int oif = skb->dev->ifindex;
@@ -530,7 +531,7 @@ static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb,
 	__build_flow_key(fl4, sk, iph, oif, tos, prot, mark, 0);
 }
 
-static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
+static void build_sk_flow_key(struct flowi4 *fl4, struct sock *sk)
 {
 	const struct inet_sock *inet = inet_sk(sk);
 	const struct ip_options_rcu *inet_opt;
@@ -544,11 +545,12 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
 			   inet_sk_flowi_flags(sk),
-			   daddr, inet->inet_saddr, 0, 0);
+			   daddr, inet->inet_saddr, 0, 0,
+			   sock_i_uid(sk));
 	rcu_read_unlock();
 }
 
-static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk,
+static void ip_rt_build_flow_key(struct flowi4 *fl4, struct sock *sk,
 				 const struct sk_buff *skb)
 {
 	if (skb)
@@ -903,6 +905,10 @@ static int ip_error(struct sk_buff *skb)
 	bool send;
 	int code;
 
+	/* IP on this device is disabled. */
+	if (!in_dev)
+		goto out;
+
 	net = dev_net(rt->dst.dev);
 	if (!IN_DEV_FORWARD(in_dev)) {
 		switch (rt->dst.error) {
@@ -1554,11 +1560,10 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	do_cache = res->fi && !itag;
 	if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) &&
+	    skb->protocol == htons(ETH_P_IP) &&
 	    (IN_DEV_SHARED_MEDIA(out_dev) ||
-	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) {
-		flags |= RTCF_DOREDIRECT;
-		do_cache = false;
-	}
+	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
+		IPCB(skb)->flags |= IPSKB_DOREDIRECT;
 
 	if (skb->protocol != htons(ETH_P_IP)) {
 		/* Not IP (i.e. ARP). Do not create route, if it is
@@ -2303,6 +2308,8 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 	r->rtm_flags	= (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED;
 	if (rt->rt_flags & RTCF_NOTIFY)
 		r->rtm_flags |= RTM_F_NOTIFY;
+	if (IPCB(skb)->flags & IPSKB_DOREDIRECT)
+		r->rtm_flags |= RTCF_DOREDIRECT;
 
 	if (nla_put_be32(skb, RTA_DST, dst))
 		goto nla_put_failure;
@@ -2348,6 +2355,11 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 	    nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark))
 		goto nla_put_failure;
 
+	if (!uid_eq(fl4->flowi4_uid, INVALID_UID) &&
+	    nla_put_u32(skb, RTA_UID,
+			from_kuid_munged(current_user_ns(), fl4->flowi4_uid)))
+		goto nla_put_failure;
+
 	error = rt->dst.error;
 
 	if (rt_is_input_route(rt)) {
@@ -2397,6 +2409,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	int err;
 	int mark;
 	struct sk_buff *skb;
+	kuid_t uid;
 
 	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
 	if (err < 0)
@@ -2424,6 +2437,10 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	dst = tb[RTA_DST] ? nla_get_be32(tb[RTA_DST]) : 0;
 	iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
 	mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0;
+	if (tb[RTA_UID])
+		uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID]));
+	else
+		uid = (iif ? INVALID_UID : current_uid());
 
 	memset(&fl4, 0, sizeof(fl4));
 	fl4.daddr = dst;
@@ -2431,6 +2448,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	fl4.flowi4_tos = rtm->rtm_tos;
 	fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
 	fl4.flowi4_mark = mark;
+	fl4.flowi4_uid = uid;
 
 	if (iif) {
 		struct net_device *dev;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 32b98d0207b..088b6ab40ca 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -336,8 +336,9 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	flowi4_init_output(&fl4, sk->sk_bound_dev_if, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
 			   inet_sk_flowi_flags(sk),
-			   opt->srr ? opt->faddr : ireq->ir_rmt_addr,
-			   ireq->ir_loc_addr, th->source, th->dest);
+			   (opt && opt->srr) ? opt->faddr : ireq->ir_rmt_addr,
+			   ireq->ir_loc_addr, th->source, th->dest,
+			   sock_i_uid(sk));
 	security_req_classify_flow(req, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_key(sock_net(sk), &fl4);
 	if (IS_ERR(rt)) {
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index b3c53c8b331..6aae73fa818 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -145,6 +145,21 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write,
 	return ret;
 }
 
+/* Validate changes from /proc interface. */
+static int proc_tcp_default_init_rwnd(struct ctl_table *ctl, int write,
+				      void __user *buffer,
+				      size_t *lenp, loff_t *ppos)
+{
+	int old_value = *(int *)ctl->data;
+	int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+	int new_value = *(int *)ctl->data;
+
+	if (write && ret == 0 && (new_value < 3 || new_value > 100))
+		*(int *)ctl->data = old_value;
+
+	return ret;
+}
+
 static int proc_tcp_congestion_control(struct ctl_table *ctl, int write,
 				       void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -722,6 +737,13 @@ static struct ctl_table ipv4_table[] = {
 		.extra2		= &one,
 	},
 	{
+		.procname       = "tcp_default_init_rwnd",
+		.data           = &sysctl_tcp_default_init_rwnd,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_tcp_default_init_rwnd
+	},
+	{
 		.procname	= "icmp_msgs_per_sec",
 		.data		= &sysctl_icmp_msgs_per_sec,
 		.maxlen		= sizeof(int),
diff --git a/net/ipv4/sysfs_net_ipv4.c b/net/ipv4/sysfs_net_ipv4.c
new file mode 100644
index 00000000000..0cbbf10026a
--- /dev/null
+++ b/net/ipv4/sysfs_net_ipv4.c
@@ -0,0 +1,88 @@
+/*
+ * net/ipv4/sysfs_net_ipv4.c
+ *
+ * sysfs-based networking knobs (so we can, unlike with sysctl, control perms)
+ *
+ * Copyright (C) 2008 Google, Inc.
+ *
+ * Robert Love <rlove@google.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kobject.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/init.h>
+#include <net/tcp.h>
+
+#define CREATE_IPV4_FILE(_name, _var) \
+static ssize_t _name##_show(struct kobject *kobj, \
+			    struct kobj_attribute *attr, char *buf) \
+{ \
+	return sprintf(buf, "%d\n", _var); \
+} \
+static ssize_t _name##_store(struct kobject *kobj, \
+			     struct kobj_attribute *attr, \
+			     const char *buf, size_t count) \
+{ \
+	int val, ret; \
+	ret = sscanf(buf, "%d", &val); \
+	if (ret != 1) \
+		return -EINVAL; \
+	if (val < 0) \
+		return -EINVAL; \
+	_var = val; \
+	return count; \
+} \
+static struct kobj_attribute _name##_attr = \
+	__ATTR(_name, 0644, _name##_show, _name##_store)
+
+CREATE_IPV4_FILE(tcp_wmem_min, sysctl_tcp_wmem[0]);
+CREATE_IPV4_FILE(tcp_wmem_def, sysctl_tcp_wmem[1]);
+CREATE_IPV4_FILE(tcp_wmem_max, sysctl_tcp_wmem[2]);
+
+CREATE_IPV4_FILE(tcp_rmem_min, sysctl_tcp_rmem[0]);
+CREATE_IPV4_FILE(tcp_rmem_def, sysctl_tcp_rmem[1]);
+CREATE_IPV4_FILE(tcp_rmem_max, sysctl_tcp_rmem[2]);
+
+static struct attribute *ipv4_attrs[] = {
+	&tcp_wmem_min_attr.attr,
+	&tcp_wmem_def_attr.attr,
+	&tcp_wmem_max_attr.attr,
+	&tcp_rmem_min_attr.attr,
+	&tcp_rmem_def_attr.attr,
+	&tcp_rmem_max_attr.attr,
+	NULL
+};
+
+static struct attribute_group ipv4_attr_group = {
+	.attrs = ipv4_attrs,
+};
+
+static __init int sysfs_ipv4_init(void)
+{
+	struct kobject *ipv4_kobject;
+	int ret;
+
+	ipv4_kobject = kobject_create_and_add("ipv4", kernel_kobj);
+	if (!ipv4_kobject)
+		return -ENOMEM;
+
+	ret = sysfs_create_group(ipv4_kobject, &ipv4_attr_group);
+	if (ret) {
+		kobject_put(ipv4_kobject);
+		return ret;
+	}
+
+	return 0;
+}
+
+subsys_initcall(sysfs_ipv4_init);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 38c2bcb8dd5..cba58d88039 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -268,12 +268,16 @@
 #include <linux/crypto.h>
 #include <linux/time.h>
 #include <linux/slab.h>
+#include <linux/uid_stat.h>
 
 #include <net/icmp.h>
 #include <net/inet_common.h>
 #include <net/tcp.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
+#include <net/ip6_route.h>
+#include <net/ipv6.h>
+#include <net/transp_v6.h>
 #include <net/sock.h>
 
 #include <asm/uaccess.h>
@@ -1298,6 +1302,10 @@ out:
 		tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
 out_nopush:
 	release_sock(sk);
+
+	if (copied + copied_syn)
+		uid_stat_tcp_snd(from_kuid(&init_user_ns, current_uid()),
+				 copied + copied_syn);
 	return copied + copied_syn;
 
 do_fault:
@@ -1569,6 +1577,8 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 	if (copied > 0) {
 		tcp_recv_skb(sk, seq, &offset);
 		tcp_cleanup_rbuf(sk, copied);
+		uid_stat_tcp_rcv(from_kuid(&init_user_ns, current_uid()),
+				 copied);
 	}
 	return copied;
 }
@@ -1898,6 +1908,10 @@ skip_copy:
 	tcp_cleanup_rbuf(sk, copied);
 
 	release_sock(sk);
+
+	if (copied > 0)
+		uid_stat_tcp_rcv(from_kuid(&init_user_ns, current_uid()),
+				 copied);
 	return copied;
 
 out:
@@ -1906,6 +1920,9 @@ out:
 
 recv_urg:
 	err = tcp_recv_urg(sk, msg, len, flags);
+	if (err > 0)
+		uid_stat_tcp_rcv(from_kuid(&init_user_ns, current_uid()),
+				 err);
 	goto out;
 
 recv_sndq:
@@ -2585,10 +2602,13 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 
 	case TCP_FASTOPEN:
 		if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
-		    TCPF_LISTEN)))
+		    TCPF_LISTEN))) {
+			tcp_fastopen_init_key_once(true);
+
 			err = fastopen_init_queue(sk, val);
-		else
+		} else {
 			err = -EINVAL;
+		}
 		break;
 	case TCP_TIMESTAMP:
 		if (!tp->repair)
@@ -2639,6 +2659,7 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
 	const struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 now = tcp_time_stamp;
+	u32 rate;
 
 	memset(info, 0, sizeof(*info));
 
@@ -2699,10 +2720,11 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
 
 	info->tcpi_total_retrans = tp->total_retrans;
 
-	info->tcpi_pacing_rate = sk->sk_pacing_rate != ~0U ?
-					sk->sk_pacing_rate : ~0ULL;
-	info->tcpi_max_pacing_rate = sk->sk_max_pacing_rate != ~0U ?
-					sk->sk_max_pacing_rate : ~0ULL;
+	rate = READ_ONCE(sk->sk_pacing_rate);
+	info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL;
+
+	rate = READ_ONCE(sk->sk_max_pacing_rate);
+	info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL;
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
 
@@ -3123,3 +3145,108 @@ void __init tcp_init(void)
 	BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0);
 	tcp_tasklet_init();
 }
+
+static int tcp_is_local(struct net *net, __be32 addr) {
+	struct rtable *rt;
+	struct flowi4 fl4 = { .daddr = addr };
+	rt = ip_route_output_key(net, &fl4);
+	if (IS_ERR_OR_NULL(rt))
+		return 0;
+	return rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK);
+}
+
+#if defined(CONFIG_IPV6)
+static int tcp_is_local6(struct net *net, struct in6_addr *addr) {
+	struct rt6_info *rt6 = rt6_lookup(net, addr, addr, 0, 0);
+	return rt6 && rt6->dst.dev && (rt6->dst.dev->flags & IFF_LOOPBACK);
+}
+#endif
+
+/*
+ * tcp_nuke_addr - destroy all sockets on the given local address
+ * if local address is the unspecified address (0.0.0.0 or ::), destroy all
+ * sockets with local addresses that are not configured.
+ */
+int tcp_nuke_addr(struct net *net, struct sockaddr *addr)
+{
+	int family = addr->sa_family;
+	unsigned int bucket;
+
+	struct in_addr *in = NULL;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+	struct in6_addr *in6 = NULL;
+#endif
+	if (family == AF_INET) {
+		in = &((struct sockaddr_in *)addr)->sin_addr;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+	} else if (family == AF_INET6) {
+		in6 = &((struct sockaddr_in6 *)addr)->sin6_addr;
+#endif
+	} else {
+		return -EAFNOSUPPORT;
+	}
+
+	for (bucket = 0; bucket < tcp_hashinfo.ehash_mask; bucket++) {
+		struct hlist_nulls_node *node;
+		struct sock *sk;
+		spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, bucket);
+
+restart:
+		spin_lock_bh(lock);
+		sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[bucket].chain) {
+			struct inet_sock *inet = inet_sk(sk);
+
+			if (sysctl_ip_dynaddr && sk->sk_state == TCP_SYN_SENT)
+				continue;
+			if (sk->sk_state == TCP_TIME_WAIT)
+				continue;
+			if (sock_flag(sk, SOCK_DEAD))
+				continue;
+
+			if (family == AF_INET) {
+				__be32 s4 = inet->inet_rcv_saddr;
+				if (s4 == LOOPBACK4_IPV6)
+					continue;
+
+				if (in->s_addr != s4 &&
+				    !(in->s_addr == INADDR_ANY &&
+				      !tcp_is_local(net, s4)))
+					continue;
+			}
+
+#if defined(CONFIG_IPV6)
+			if (family == AF_INET6) {
+				struct in6_addr *s6;
+
+				s6 = &sk->sk_v6_rcv_saddr;
+				if (ipv6_addr_type(s6) == IPV6_ADDR_MAPPED)
+					continue;
+
+				if (!ipv6_addr_equal(in6, s6) &&
+				    !(ipv6_addr_equal(in6, &in6addr_any) &&
+				      !tcp_is_local6(net, s6)))
+				continue;
+			}
+#endif
+
+			sock_hold(sk);
+			spin_unlock_bh(lock);
+
+			local_bh_disable();
+			bh_lock_sock(sk);
+			sk->sk_err = ETIMEDOUT;
+			sk->sk_error_report(sk);
+
+			tcp_done(sk);
+			bh_unlock_sock(sk);
+			local_bh_enable();
+			sock_put(sk);
+
+			goto restart;
+		}
+		spin_unlock_bh(lock);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(tcp_nuke_addr);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index b1c5970d47a..b3316c8279a 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -248,9 +248,10 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
 	ca = tcp_ca_find(name);
 
 	/* no change asking for existing value */
-	if (ca == icsk->icsk_ca_ops)
+	if (ca == icsk->icsk_ca_ops) {
+		icsk->icsk_ca_setsockopt = 1;
 		goto out;
-
+	}
 #ifdef CONFIG_MODULES
 	/* not found attempt to autoload module */
 	if (!ca && capable(CAP_NET_ADMIN)) {
@@ -273,6 +274,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
 	else {
 		tcp_cleanup_congestion_control(sk);
 		icsk->icsk_ca_ops = ca;
+		icsk->icsk_ca_setsockopt = 1;
 
 		if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init)
 			icsk->icsk_ca_ops->init(sk);
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 815c85e3b1e..b01d5bd6d6c 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -78,8 +78,6 @@ static bool __tcp_fastopen_cookie_gen(const void *path,
 	struct tcp_fastopen_context *ctx;
 	bool ok = false;
 
-	tcp_fastopen_init_key_once(true);
-
 	rcu_read_lock();
 	ctx = rcu_dereference(tcp_fastopen_ctx);
 	if (ctx) {
@@ -134,6 +132,7 @@ static bool tcp_fastopen_create_child(struct sock *sk,
 	struct tcp_sock *tp;
 	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
 	struct sock *child;
+	u32 end_seq;
 
 	req->num_retrans = 0;
 	req->num_timeout = 0;
@@ -185,20 +184,35 @@ static bool tcp_fastopen_create_child(struct sock *sk,
 
 	/* Queue the data carried in the SYN packet. We need to first
 	 * bump skb's refcnt because the caller will attempt to free it.
+	 * Note that IPv6 might also have used skb_get() trick
+	 * in tcp_v6_conn_request() to keep this SYN around (treq->pktopts)
+	 * So we need to eventually get a clone of the packet,
+	 * before inserting it in sk_receive_queue.
 	 *
 	 * XXX (TFO) - we honor a zero-payload TFO request for now,
 	 * (any reason not to?) but no need to queue the skb since
 	 * there is no data. How about SYN+FIN?
 	 */
-	if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1) {
-		skb = skb_get(skb);
-		skb_dst_drop(skb);
-		__skb_pull(skb, tcp_hdr(skb)->doff * 4);
-		skb_set_owner_r(skb, child);
-		__skb_queue_tail(&child->sk_receive_queue, skb);
-		tp->syn_data_acked = 1;
+	end_seq = TCP_SKB_CB(skb)->end_seq;
+	if (end_seq != TCP_SKB_CB(skb)->seq + 1) {
+		struct sk_buff *skb2;
+
+		if (unlikely(skb_shared(skb)))
+			skb2 = skb_clone(skb, GFP_ATOMIC);
+		else
+			skb2 = skb_get(skb);
+
+		if (likely(skb2)) {
+			skb_dst_drop(skb2);
+			__skb_pull(skb2, tcp_hdrlen(skb));
+			skb_set_owner_r(skb2, child);
+			__skb_queue_tail(&child->sk_receive_queue, skb2);
+			tp->syn_data_acked = 1;
+		} else {
+			end_seq = TCP_SKB_CB(skb)->seq + 1;
+		}
 	}
-	tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+	tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = end_seq;
 	sk->sk_data_ready(sk);
 	bh_unlock_sock(child);
 	sock_put(child);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d107ee246a1..bbeaf7bb623 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -99,6 +99,7 @@ int sysctl_tcp_thin_dupack __read_mostly;
 
 int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
 int sysctl_tcp_early_retrans __read_mostly = 3;
+int sysctl_tcp_default_init_rwnd __read_mostly = TCP_INIT_CWND * 2;
 
 #define FLAG_DATA		0x01 /* Incoming frame contained data.		*/
 #define FLAG_WIN_UPDATE		0x02 /* Incoming ACK was a window update.	*/
@@ -3103,10 +3104,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 			if (!first_ackt.v64)
 				first_ackt = last_ackt;
 
-			if (!(sacked & TCPCB_SACKED_ACKED))
+			if (!(sacked & TCPCB_SACKED_ACKED)) {
 				reord = min(pkts_acked, reord);
-			if (!after(scb->end_seq, tp->high_seq))
-				flag |= FLAG_ORIG_SACK_ACKED;
+				if (!after(scb->end_seq, tp->high_seq))
+					flag |= FLAG_ORIG_SACK_ACKED;
+			}
 		}
 
 		if (sacked & TCPCB_SACKED_ACKED)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 147be202429..a5fdfe9fa54 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -623,6 +623,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 	arg.iov[0].iov_base = (unsigned char *)&rep;
 	arg.iov[0].iov_len  = sizeof(rep.th);
 
+	net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
 #ifdef CONFIG_TCP_MD5SIG
 	hash_location = tcp_parse_md5sig_option(th);
 	if (!sk && hash_location) {
@@ -633,7 +634,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 		 * Incoming packet is checked with md5 hash with finding key,
 		 * no RST generated if md5 hash doesn't match.
 		 */
-		sk1 = __inet_lookup_listener(dev_net(skb_dst(skb)->dev),
+		sk1 = __inet_lookup_listener(net,
 					     &tcp_hashinfo, ip_hdr(skb)->saddr,
 					     th->source, ip_hdr(skb)->daddr,
 					     ntohs(th->source), inet_iif(skb));
@@ -681,9 +682,9 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 	if (sk)
 		arg.bound_dev_if = sk->sk_bound_dev_if;
 
-	net = dev_net(skb_dst(skb)->dev);
 	arg.tos = ip_hdr(skb)->tos;
-	ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
 			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
 			      &arg, arg.iov[0].iov_len);
 
@@ -767,7 +768,8 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 	if (oif)
 		arg.bound_dev_if = oif;
 	arg.tos = tos;
-	ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
 			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
 			      &arg, arg.iov[0].iov_len);
 
@@ -1512,7 +1514,7 @@ void tcp_v4_early_demux(struct sk_buff *skb)
 		skb->sk = sk;
 		skb->destructor = sock_edemux;
 		if (sk->sk_state != TCP_TIME_WAIT) {
-			struct dst_entry *dst = sk->sk_rx_dst;
+			struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst);
 
 			if (dst)
 				dst = dst_check(dst, 0);
@@ -2426,14 +2428,39 @@ struct proto tcp_prot = {
 };
 EXPORT_SYMBOL(tcp_prot);
 
+static void __net_exit tcp_sk_exit(struct net *net)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
+	free_percpu(net->ipv4.tcp_sk);
+}
+
 static int __net_init tcp_sk_init(struct net *net)
 {
+	int res, cpu;
+
+	net->ipv4.tcp_sk = alloc_percpu(struct sock *);
+	if (!net->ipv4.tcp_sk)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu) {
+		struct sock *sk;
+
+		res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW,
+					   IPPROTO_TCP, net);
+		if (res)
+			goto fail;
+		*per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
+	}
 	net->ipv4.sysctl_tcp_ecn = 2;
 	return 0;
-}
 
-static void __net_exit tcp_sk_exit(struct net *net)
-{
+fail:
+	tcp_sk_exit(net);
+
+	return res;
 }
 
 static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 63d2680b65d..2f6667116e8 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -297,7 +297,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 			tw->tw_v6_daddr = sk->sk_v6_daddr;
 			tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
 			tw->tw_tclass = np->tclass;
-			tw->tw_flowlabel = np->flow_label >> 12;
+			tw->tw_flowlabel = be32_to_cpu(np->flow_label & IPV6_FLOWLABEL_MASK);
 			tw->tw_ipv6only = sk->sk_ipv6only;
 		}
 #endif
@@ -451,7 +451,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 		newtp->snd_cwnd = TCP_INIT_CWND;
 		newtp->snd_cwnd_cnt = 0;
 
-		if (!try_module_get(newicsk->icsk_ca_ops->owner))
+		if (!newicsk->icsk_ca_setsockopt ||
+		    !try_module_get(newicsk->icsk_ca_ops->owner))
 			tcp_assign_congestion_control(newsk);
 
 		tcp_set_ca_state(newsk, TCP_CA_Open);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a3d453b9474..c07062b7517 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -197,7 +197,7 @@ u32 tcp_default_init_rwnd(u32 mss)
 	 * (RFC 3517, Section 4, NextSeg() rule (2)). Further place a
 	 * limit when mss is larger than 1460.
 	 */
-	u32 init_rwnd = TCP_INIT_CWND * 2;
+	u32 init_rwnd = sysctl_tcp_default_init_rwnd;
 
 	if (mss > 1460)
 		init_rwnd = max((1460 * init_rwnd) / mss, 2U);
@@ -1984,7 +1984,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now)))
 			break;
 
-		if (tso_segs == 1) {
+		if (tso_segs == 1 || !sk->sk_gso_max_segs) {
 			if (unlikely(!tcp_nagle_test(tp, skb, mss_now,
 						     (tcp_skb_is_last(sk, skb) ?
 						      nonagle : TCP_NAGLE_PUSH))))
@@ -2020,7 +2020,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		}
 
 		limit = mss_now;
-		if (tso_segs > 1 && !tcp_urg_mode(tp))
+		if (tso_segs > 1 && sk->sk_gso_max_segs && !tcp_urg_mode(tp))
 			limit = tcp_mss_split_point(sk, skb, mss_now,
 						    min_t(unsigned int,
 							  cwnd_quota,
@@ -2717,43 +2717,65 @@ begin_fwd:
 	}
 }
 
-/* Send a fin.  The caller locks the socket for us.  This cannot be
- * allowed to fail queueing a FIN frame under any circumstances.
+/* We allow to exceed memory limits for FIN packets to expedite
+ * connection tear down and (memory) recovery.
+ * Otherwise tcp_send_fin() could be tempted to either delay FIN
+ * or even be forced to close flow without any FIN.
+ */
+static void sk_forced_wmem_schedule(struct sock *sk, int size)
+{
+	int amt, status;
+
+	if (size <= sk->sk_forward_alloc)
+		return;
+	amt = sk_mem_pages(size);
+	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
+	sk_memory_allocated_add(sk, amt, &status);
+}
+
+/* Send a FIN. The caller locks the socket for us.
+ * We should try to send a FIN packet really hard, but eventually give up.
  */
 void tcp_send_fin(struct sock *sk)
 {
+	struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb = tcp_write_queue_tail(sk);
-	int mss_now;
 
-	/* Optimization, tack on the FIN if we have a queue of
-	 * unsent frames.  But be careful about outgoing SACKS
-	 * and IP options.
+	/* Optimization, tack on the FIN if we have one skb in write queue and
+	 * this skb was not yet sent, or we are under memory pressure.
+	 * Note: in the latter case, FIN packet will be sent after a timeout,
+	 * as TCP stack thinks it has already been transmitted.
 	 */
-	mss_now = tcp_current_mss(sk);
-
-	if (tcp_send_head(sk) != NULL) {
-		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN;
-		TCP_SKB_CB(skb)->end_seq++;
+	if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) {
+coalesce:
+		TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
+		TCP_SKB_CB(tskb)->end_seq++;
 		tp->write_seq++;
+		if (!tcp_send_head(sk)) {
+			/* This means tskb was already sent.
+			 * Pretend we included the FIN on previous transmit.
+			 * We need to set tp->snd_nxt to the value it would have
+			 * if FIN had been sent. This is because retransmit path
+			 * does not change tp->snd_nxt.
+			 */
+			tp->snd_nxt++;
+			return;
+		}
 	} else {
-		/* Socket is locked, keep trying until memory is available. */
-		for (;;) {
-			skb = alloc_skb_fclone(MAX_TCP_HEADER,
-					       sk->sk_allocation);
-			if (skb)
-				break;
-			yield();
+		skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
+		if (unlikely(!skb)) {
+			if (tskb)
+				goto coalesce;
+			return;
 		}
-
-		/* Reserve space for headers and prepare control bits. */
 		skb_reserve(skb, MAX_TCP_HEADER);
+		sk_forced_wmem_schedule(sk, skb->truesize);
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
 		tcp_init_nondata_skb(skb, tp->write_seq,
 				     TCPHDR_ACK | TCPHDR_FIN);
 		tcp_queue_skb(sk, skb);
 	}
-	__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
+	__tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF);
 }
 
 /* We get here when a process closes a file descriptor (either due to
@@ -2899,6 +2921,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	}
 #endif
 
+	/* Do not fool tcpdump (if any), clean our debris */
+	skb->tstamp.tv64 = 0;
 	return skb;
 }
 EXPORT_SYMBOL(tcp_make_synack);
@@ -2998,9 +3022,9 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_fastopen_request *fo = tp->fastopen_req;
-	int syn_loss = 0, space, i, err = 0, iovlen = fo->data->msg_iovlen;
-	struct sk_buff *syn_data = NULL, *data;
+	int syn_loss = 0, space, err = 0;
 	unsigned long last_syn_loss = 0;
+	struct sk_buff *syn_data;
 
 	tp->rx_opt.mss_clamp = tp->advmss;  /* If MSS is not cached */
 	tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie,
@@ -3031,48 +3055,40 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	/* limit to order-0 allocations */
 	space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER));
 
-	syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space,
-				   sk->sk_allocation);
-	if (syn_data == NULL)
+	syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation);
+	if (!syn_data)
+		goto fallback;
+	syn_data->ip_summed = CHECKSUM_PARTIAL;
+	memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
+	if (unlikely(memcpy_fromiovecend(skb_put(syn_data, space),
+					 fo->data->msg_iov, 0, space))) {
+		kfree_skb(syn_data);
 		goto fallback;
+	}
 
-	for (i = 0; i < iovlen && syn_data->len < space; ++i) {
-		struct iovec *iov = &fo->data->msg_iov[i];
-		unsigned char __user *from = iov->iov_base;
-		int len = iov->iov_len;
+	/* No more data pending in inet_wait_for_connect() */
+	if (space == fo->size)
+		fo->data = NULL;
+	fo->copied = space;
 
-		if (syn_data->len + len > space)
-			len = space - syn_data->len;
-		else if (i + 1 == iovlen)
-			/* No more data pending in inet_wait_for_connect() */
-			fo->data = NULL;
+	tcp_connect_queue_skb(sk, syn_data);
 
-		if (skb_add_data(syn_data, from, len))
-			goto fallback;
-	}
+	err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation);
 
-	/* Queue a data-only packet after the regular SYN for retransmission */
-	data = pskb_copy(syn_data, sk->sk_allocation);
-	if (data == NULL)
-		goto fallback;
-	TCP_SKB_CB(data)->seq++;
-	TCP_SKB_CB(data)->tcp_flags &= ~TCPHDR_SYN;
-	TCP_SKB_CB(data)->tcp_flags = (TCPHDR_ACK|TCPHDR_PSH);
-	tcp_connect_queue_skb(sk, data);
-	fo->copied = data->len;
-
-	/* syn_data is about to be sent, we need to take current time stamps
-	 * for the packets that are in write queue : SYN packet and DATA
-	 */
-	skb_mstamp_get(&syn->skb_mstamp);
-	data->skb_mstamp = syn->skb_mstamp;
+	syn->skb_mstamp = syn_data->skb_mstamp;
 
-	if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) {
+	/* Now full SYN+DATA was cloned and sent (or not),
+	 * remove the SYN from the original skb (syn_data)
+	 * we keep in write queue in case of a retransmit, as we
+	 * also have the SYN packet (with no data) in the same queue.
+	 */
+	TCP_SKB_CB(syn_data)->seq++;
+	TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH;
+	if (!err) {
 		tp->syn_data = (fo->copied > 0);
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT);
 		goto done;
 	}
-	syn_data = NULL;
 
 fallback:
 	/* Send a regular SYN with Fast Open cookie request option */
@@ -3081,7 +3097,6 @@ fallback:
 	err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation);
 	if (err)
 		tp->syn_fastopen = 0;
-	kfree_skb(syn_data);
 done:
 	fo->cookie.len = -1;  /* Exclude Fast Open option for SYN retries */
 	return err;
@@ -3101,13 +3116,10 @@ int tcp_connect(struct sock *sk)
 		return 0;
 	}
 
-	buff = alloc_skb_fclone(MAX_TCP_HEADER + 15, sk->sk_allocation);
-	if (unlikely(buff == NULL))
+	buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
+	if (unlikely(!buff))
 		return -ENOBUFS;
 
-	/* Reserve space for headers. */
-	skb_reserve(buff, MAX_TCP_HEADER);
-
 	tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);
 	tp->retrans_stamp = tcp_time_stamp;
 	tcp_connect_queue_skb(sk, buff);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index cd0db5471bb..e9277f69956 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -90,6 +90,7 @@
 #include <linux/socket.h>
 #include <linux/sockios.h>
 #include <linux/igmp.h>
+#include <linux/inetdevice.h>
 #include <linux/in.h>
 #include <linux/errno.h>
 #include <linux/timer.h>
@@ -1006,7 +1007,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos,
 				   RT_SCOPE_UNIVERSE, sk->sk_protocol,
 				   inet_sk_flowi_flags(sk),
-				   faddr, saddr, dport, inet->inet_sport);
+				   faddr, saddr, dport, inet->inet_sport,
+				   sock_i_uid(sk));
 
 		security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
 		rt = ip_route_output_flow(net, fl4, sk);
@@ -1336,10 +1338,8 @@ csum_copy_err:
 	}
 	unlock_sock_fast(sk, slow);
 
-	if (noblock)
-		return -EAGAIN;
-
-	/* starting over for a new packet */
+	/* starting over for a new packet, but check if we need to yield */
+	cond_resched();
 	msg->msg_flags &= ~MSG_TRUNC;
 	goto try_again;
 }
@@ -1950,6 +1950,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
 	struct sock *sk;
 	struct dst_entry *dst;
 	int dif = skb->dev->ifindex;
+	int ours;
 
 	/* validate the packet */
 	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
@@ -1959,14 +1960,24 @@ void udp_v4_early_demux(struct sk_buff *skb)
 	uh = udp_hdr(skb);
 
 	if (skb->pkt_type == PACKET_BROADCAST ||
-	    skb->pkt_type == PACKET_MULTICAST)
+	    skb->pkt_type == PACKET_MULTICAST) {
+		struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+
+		if (!in_dev)
+			return;
+
+		ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
+				       iph->protocol);
+		if (!ours)
+			return;
 		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
 						   uh->source, iph->saddr, dif);
-	else if (skb->pkt_type == PACKET_HOST)
+	} else if (skb->pkt_type == PACKET_HOST) {
 		sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
 					     uh->source, iph->saddr, dif);
-	else
+	} else {
 		return;
+	}
 
 	if (!sk)
 		return;
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 7927db0a927..4a000f1dd75 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -99,11 +99,13 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlin
 	s_slot = cb->args[0];
 	num = s_num = cb->args[1];
 
-	for (slot = s_slot; slot <= table->mask; num = s_num = 0, slot++) {
+	for (slot = s_slot; slot <= table->mask; s_num = 0, slot++) {
 		struct sock *sk;
 		struct hlist_nulls_node *node;
 		struct udp_hslot *hslot = &table->hash[slot];
 
+		num = 0;
+
 		if (hlist_nulls_empty(&hslot->head))
 			continue;
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 0169ccf5aa4..89a9a1e4bbf 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -196,6 +196,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.accept_ra_rt_info_max_plen = 0,
 #endif
 #endif
+	.accept_ra_rt_table	= 0,
 	.proxy_ndp		= 0,
 	.accept_source_route	= 0,	/* we do not accept RH0 by default. */
 	.disable_ipv6		= 0,
@@ -233,6 +234,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.accept_ra_rt_info_max_plen = 0,
 #endif
 #endif
+	.accept_ra_rt_table	= 0,
 	.proxy_ndp		= 0,
 	.accept_source_route	= 0,	/* we do not accept RH0 by default. */
 	.disable_ipv6		= 0,
@@ -1170,6 +1172,9 @@ enum {
 	IPV6_SADDR_RULE_PRIVACY,
 	IPV6_SADDR_RULE_ORCHID,
 	IPV6_SADDR_RULE_PREFIX,
+#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
+	IPV6_SADDR_RULE_NOT_OPTIMISTIC,
+#endif
 	IPV6_SADDR_RULE_MAX
 };
 
@@ -1197,6 +1202,15 @@ static inline int ipv6_saddr_preferred(int type)
 	return 0;
 }
 
+static inline bool ipv6_use_optimistic_addr(struct inet6_dev *idev)
+{
+#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
+	return idev && idev->cnf.optimistic_dad && idev->cnf.use_optimistic;
+#else
+	return false;
+#endif
+}
+
 static int ipv6_get_saddr_eval(struct net *net,
 			       struct ipv6_saddr_score *score,
 			       struct ipv6_saddr_dst *dst,
@@ -1257,10 +1271,16 @@ static int ipv6_get_saddr_eval(struct net *net,
 		score->scopedist = ret;
 		break;
 	case IPV6_SADDR_RULE_PREFERRED:
+	    {
 		/* Rule 3: Avoid deprecated and optimistic addresses */
+		u8 avoid = IFA_F_DEPRECATED;
+
+		if (!ipv6_use_optimistic_addr(score->ifa->idev))
+			avoid |= IFA_F_OPTIMISTIC;
 		ret = ipv6_saddr_preferred(score->addr_type) ||
-		      !(score->ifa->flags & (IFA_F_DEPRECATED|IFA_F_OPTIMISTIC));
+		      !(score->ifa->flags & avoid);
 		break;
+	    }
 #ifdef CONFIG_IPV6_MIP6
 	case IPV6_SADDR_RULE_HOA:
 	    {
@@ -1306,6 +1326,14 @@ static int ipv6_get_saddr_eval(struct net *net,
 			ret = score->ifa->prefix_len;
 		score->matchlen = ret;
 		break;
+#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
+	case IPV6_SADDR_RULE_NOT_OPTIMISTIC:
+		/* Optimistic addresses still have lower precedence than other
+		 * preferred addresses.
+		 */
+		ret = !(score->ifa->flags & IFA_F_OPTIMISTIC);
+		break;
+#endif
 	default:
 		ret = 0;
 	}
@@ -1503,7 +1531,9 @@ int ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
 		if (!net_eq(dev_net(ifp->idev->dev), net))
 			continue;
 		if (ipv6_addr_equal(&ifp->addr, addr) &&
-		    !(ifp->flags&IFA_F_TENTATIVE) &&
+		    (!(ifp->flags&IFA_F_TENTATIVE) ||
+		     (ipv6_use_optimistic_addr(ifp->idev) &&
+		      ifp->flags&IFA_F_OPTIMISTIC)) &&
 		    (dev == NULL || ifp->idev->dev == dev ||
 		     !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) {
 			rcu_read_unlock_bh();
@@ -1966,6 +1996,31 @@ static void  __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmp
 		__ipv6_regen_rndid(idev);
 }
 
+u32 addrconf_rt_table(const struct net_device *dev, u32 default_table) {
+	/* Determines into what table to put autoconf PIO/RIO/default routes
+	 * learned on this device.
+	 *
+	 * - If 0, use the same table for every device. This puts routes into
+	 *   one of RT_TABLE_{PREFIX,INFO,DFLT} depending on the type of route
+	 *   (but note that these three are currently all equal to
+	 *   RT6_TABLE_MAIN).
+	 * - If > 0, use the specified table.
+	 * - If < 0, put routes into table dev->ifindex + (-rt_table).
+	 */
+	struct inet6_dev *idev = in6_dev_get(dev);
+	u32 table;
+	int sysctl = idev->cnf.accept_ra_rt_table;
+	if (sysctl == 0) {
+		table = default_table;
+	} else if (sysctl > 0) {
+		table = (u32) sysctl;
+	} else {
+		table = (unsigned) dev->ifindex + (-sysctl);
+	}
+	in6_dev_put(idev);
+	return table;
+}
+
 /*
  *	Add prefix route.
  */
@@ -1975,7 +2030,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
 		      unsigned long expires, u32 flags)
 {
 	struct fib6_config cfg = {
-		.fc_table = RT6_TABLE_PREFIX,
+		.fc_table = addrconf_rt_table(dev, RT6_TABLE_PREFIX),
 		.fc_metric = IP6_RT_PRIO_ADDRCONF,
 		.fc_ifindex = dev->ifindex,
 		.fc_expires = expires,
@@ -2009,7 +2064,8 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 	struct rt6_info *rt = NULL;
 	struct fib6_table *table;
 
-	table = fib6_get_table(dev_net(dev), RT6_TABLE_PREFIX);
+	table = fib6_get_table(dev_net(dev),
+			       addrconf_rt_table(dev, RT6_TABLE_PREFIX));
 	if (table == NULL)
 		return NULL;
 
@@ -3222,8 +3278,15 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 	 * Optimistic nodes can start receiving
 	 * Frames right away
 	 */
-	if (ifp->flags & IFA_F_OPTIMISTIC)
+	if (ifp->flags & IFA_F_OPTIMISTIC) {
 		ip6_ins_rt(ifp->rt);
+		if (ipv6_use_optimistic_addr(idev)) {
+			/* Because optimistic nodes can use this address,
+			 * notify listeners. If DAD fails, RTM_DELADDR is sent.
+			 */
+			ipv6_ifa_notify(RTM_NEWADDR, ifp);
+		}
+	}
 
 	addrconf_dad_kick(ifp);
 out:
@@ -4326,10 +4389,12 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen;
 #endif
 #endif
+	array[DEVCONF_ACCEPT_RA_RT_TABLE] = cnf->accept_ra_rt_table;
 	array[DEVCONF_PROXY_NDP] = cnf->proxy_ndp;
 	array[DEVCONF_ACCEPT_SOURCE_ROUTE] = cnf->accept_source_route;
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
 	array[DEVCONF_OPTIMISTIC_DAD] = cnf->optimistic_dad;
+	array[DEVCONF_USE_OPTIMISTIC] = cnf->use_optimistic;
 #endif
 #ifdef CONFIG_IPV6_MROUTE
 	array[DEVCONF_MC_FORWARDING] = cnf->mc_forwarding;
@@ -4536,6 +4601,22 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
 	return 0;
 }
 
+static const struct nla_policy inet6_af_policy[IFLA_INET6_MAX + 1] = {
+	[IFLA_INET6_ADDR_GEN_MODE]	= { .type = NLA_U8 },
+	[IFLA_INET6_TOKEN]		= { .len = sizeof(struct in6_addr) },
+};
+
+static int inet6_validate_link_af(const struct net_device *dev,
+				  const struct nlattr *nla)
+{
+	struct nlattr *tb[IFLA_INET6_MAX + 1];
+
+	if (dev && !__in6_dev_get(dev))
+		return -EAFNOSUPPORT;
+
+	return nla_parse_nested(tb, IFLA_INET6_MAX, nla, inet6_af_policy);
+}
+
 static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla)
 {
 	int err = -EINVAL;
@@ -5134,6 +5215,13 @@ static struct addrconf_sysctl_table
 #endif
 #endif
 		{
+			.procname	= "accept_ra_rt_table",
+			.data		= &ipv6_devconf.accept_ra_rt_table,
+			.maxlen		= sizeof(int),
+			.mode		= 0644,
+			.proc_handler	= proc_dointvec,
+		},
+		{
 			.procname	= "proxy_ndp",
 			.data		= &ipv6_devconf.proxy_ndp,
 			.maxlen		= sizeof(int),
@@ -5156,6 +5244,14 @@ static struct addrconf_sysctl_table
 			.proc_handler   = proc_dointvec,
 
 		},
+		{
+			.procname       = "use_optimistic",
+			.data           = &ipv6_devconf.use_optimistic,
+			.maxlen         = sizeof(int),
+			.mode           = 0644,
+			.proc_handler   = proc_dointvec,
+
+		},
 #endif
 #ifdef CONFIG_IPV6_MROUTE
 		{
@@ -5351,6 +5447,7 @@ static struct rtnl_af_ops inet6_ops = {
 	.family		  = AF_INET6,
 	.fill_link_af	  = inet6_fill_link_af,
 	.get_link_af_size = inet6_get_link_af_size,
+	.validate_link_af = inet6_validate_link_af,
 	.set_link_af	  = inet6_set_link_af,
 };
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index e8c4400f23e..4c591c0aa3e 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -64,6 +64,20 @@
 #include <asm/uaccess.h>
 #include <linux/mroute6.h>
 
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+#include <linux/android_aid.h>
+
+static inline int current_has_network(void)
+{
+	return in_egroup_p(AID_INET) || capable(CAP_NET_RAW);
+}
+#else
+static inline int current_has_network(void)
+{
+	return 1;
+}
+#endif
+
 MODULE_AUTHOR("Cast of dozens");
 MODULE_DESCRIPTION("IPv6 protocol stack for Linux");
 MODULE_LICENSE("GPL");
@@ -109,6 +123,9 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
 	int try_loading_module = 0;
 	int err;
 
+	if (!current_has_network())
+		return -EACCES;
+
 	/* Look for the requested type/protocol pair. */
 lookup_protocol:
 	err = -ESOCKTNOSUPPORT;
@@ -155,8 +172,7 @@ lookup_protocol:
 	}
 
 	err = -EPERM;
-	if (sock->type == SOCK_RAW && !kern &&
-	    !ns_capable(net->user_ns, CAP_NET_RAW))
+	if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
 		goto out_rcu_unlock;
 
 	sock->ops = answer->ops;
@@ -471,6 +487,21 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
 }
 EXPORT_SYMBOL(inet6_getname);
 
+int inet6_killaddr_ioctl(struct net *net, void __user *arg) {
+	struct in6_ifreq ireq;
+	struct sockaddr_in6 sin6;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EACCES;
+
+	if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq)))
+		return -EFAULT;
+
+	sin6.sin6_family = AF_INET6;
+	sin6.sin6_addr = ireq.ifr6_addr;
+	return tcp_nuke_addr(net, (struct sockaddr *) &sin6);
+}
+
 int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 {
 	struct sock *sk = sock->sk;
@@ -494,6 +525,8 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		return addrconf_del_ifaddr(net, (void __user *) arg);
 	case SIOCSIFDSTADDR:
 		return addrconf_set_dstaddr(net, (void __user *) arg);
+	case SIOCKILLADDR:
+		return inet6_killaddr_ioctl(net, (void __user *) arg);
 	default:
 		if (!sk->sk_prot->ioctl)
 			return -ENOIOCTLCMD;
@@ -654,6 +687,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
 		fl6.flowi6_mark = sk->sk_mark;
 		fl6.fl6_dport = inet->inet_dport;
 		fl6.fl6_sport = inet->inet_sport;
+		fl6.flowi6_uid = sock_i_uid(sk);
 		security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
 		final_p = fl6_update_dst(&fl6, np->opt, &final);
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 6d16eb0e0c7..bb93d3b979a 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -662,7 +662,7 @@ static int ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (type == NDISC_REDIRECT)
 		ip6_redirect(skb, net, skb->dev->ifindex, 0);
 	else
-		ip6_update_pmtu(skb, net, info, 0, 0);
+		ip6_update_pmtu(skb, net, info, 0, 0, INVALID_UID);
 	xfrm_state_put(x);
 
 	return 0;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 2cdc38338be..696641f9b22 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -161,6 +161,7 @@ ipv4_connected:
 	fl6.flowi6_mark = sk->sk_mark;
 	fl6.fl6_dport = inet->inet_dport;
 	fl6.fl6_sport = inet->inet_sport;
+	fl6.flowi6_uid = sock_i_uid(sk);
 
 	if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST))
 		fl6.flowi6_oif = np->mcast_oif;
@@ -383,11 +384,10 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
 	sin = &errhdr.offender;
-	sin->sin6_family = AF_UNSPEC;
+	memset(sin, 0, sizeof(*sin));
+
 	if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) {
 		sin->sin6_family = AF_INET6;
-		sin->sin6_flowinfo = 0;
-		sin->sin6_port = 0;
 		if (np->rxopt.all)
 			ip6_datagram_recv_common_ctl(sk, msg, skb);
 		if (skb->protocol == htons(ETH_P_IPV6)) {
@@ -398,12 +398,9 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 				ipv6_iface_scope_id(&sin->sin6_addr,
 						    IP6CB(skb)->iif);
 		} else {
-			struct inet_sock *inet = inet_sk(sk);
-
 			ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr,
 					       &sin->sin6_addr);
-			sin->sin6_scope_id = 0;
-			if (inet->cmsg_flags)
+			if (inet_sk(sk)->cmsg_flags)
 				ip_cmsg_recv(msg, skb);
 		}
 	}
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 83fc3a385a2..09583542f28 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -441,7 +441,7 @@ static int esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (type == NDISC_REDIRECT)
 		ip6_redirect(skb, net, skb->dev->ifindex, 0);
 	else
-		ip6_update_pmtu(skb, net, info, 0, 0);
+		ip6_update_pmtu(skb, net, info, 0, 0, INVALID_UID);
 	xfrm_state_put(x);
 
 	return 0;
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 8af3eb57f43..958a187a3cc 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -166,15 +166,15 @@ EXPORT_SYMBOL_GPL(ipv6_find_tlv);
  * to explore inner IPv6 header, eg. ICMPv6 error messages.
  *
  * If target header is found, its offset is set in *offset and return protocol
- * number. Otherwise, return -1.
+ * number. Otherwise, return -ENOENT or -EBADMSG.
  *
  * If the first fragment doesn't contain the final protocol header or
  * NEXTHDR_NONE it is considered invalid.
  *
  * Note that non-1st fragment is special case that "the protocol number
  * of last header" is "next header" field in Fragment header. In this case,
- * *offset is meaningless and fragment offset is stored in *fragoff if fragoff
- * isn't NULL.
+ * *offset is meaningless. If fragoff is not NULL, the fragment offset is
+ * stored in *fragoff; if it is NULL, return -EINVAL.
  *
  * if flags is not NULL and it's a fragment, then the frag flag
  * IP6_FH_F_FRAG will be set. If it's an AH header, the
@@ -253,9 +253,12 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 				if (target < 0 &&
 				    ((!ipv6_ext_hdr(hp->nexthdr)) ||
 				     hp->nexthdr == NEXTHDR_NONE)) {
-					if (fragoff)
+					if (fragoff) {
 						*fragoff = _frag_off;
-					return hp->nexthdr;
+						return hp->nexthdr;
+					} else {
+						return -EINVAL;
+					}
 				}
 				return -ENOENT;
 			}
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index b4d5e1d97c1..27ca79682ef 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -104,6 +104,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 				goto again;
 			flp6->saddr = saddr;
 		}
+		err = rt->dst.error;
 		goto out;
 	}
 again:
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 97ae70077a4..070d591332c 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -91,7 +91,7 @@ static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	struct net *net = dev_net(skb->dev);
 
 	if (type == ICMPV6_PKT_TOOBIG)
-		ip6_update_pmtu(skb, net, info, 0, 0);
+		ip6_update_pmtu(skb, net, info, 0, 0, INVALID_UID);
 	else if (type == NDISC_REDIRECT)
 		ip6_redirect(skb, net, skb->dev->ifindex, 0);
 
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 29b32206e49..c8f730266b7 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -83,6 +83,7 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
 	fl6->flowi6_mark = ireq->ir_mark;
 	fl6->fl6_dport = ireq->ir_rmt_port;
 	fl6->fl6_sport = htons(ireq->ir_num);
+	fl6->flowi6_uid = sock_i_uid(sk);
 	security_req_classify_flow(req, flowi6_to_flowi(fl6));
 
 	dst = ip6_dst_lookup_flow(sk, fl6, final_p);
@@ -206,6 +207,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
 	fl6->flowi6_mark = sk->sk_mark;
 	fl6->fl6_sport = inet->inet_sport;
 	fl6->fl6_dport = inet->inet_dport;
+	fl6->flowi6_uid = sock_i_uid(sk);
 	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
 
 	final_p = fl6_update_dst(fl6, np->opt, &final);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index b2d1838897c..f1c6d5e9832 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -659,6 +659,29 @@ static int fib6_commit_metrics(struct dst_entry *dst,
 	return 0;
 }
 
+static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
+			  struct net *net)
+{
+	if (atomic_read(&rt->rt6i_ref) != 1) {
+		/* This route is used as dummy address holder in some split
+		 * nodes. It is not leaked, but it still holds other resources,
+		 * which must be released in time. So, scan ascendant nodes
+		 * and replace dummy references to this route with references
+		 * to still alive ones.
+		 */
+		while (fn) {
+			if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) {
+				fn->leaf = fib6_find_prefix(net, fn);
+				atomic_inc(&fn->leaf->rt6i_ref);
+				rt6_release(rt);
+			}
+			fn = fn->parent;
+		}
+		/* No more references are possible at this point. */
+		BUG_ON(atomic_read(&rt->rt6i_ref) != 1);
+	}
+}
+
 /*
  *	Insert routing information in a node.
  */
@@ -807,11 +830,12 @@ add:
 		rt->dst.rt6_next = iter->dst.rt6_next;
 		atomic_inc(&rt->rt6i_ref);
 		inet6_rt_notify(RTM_NEWROUTE, rt, info);
-		rt6_release(iter);
 		if (!(fn->fn_flags & RTN_RTINFO)) {
 			info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
 			fn->fn_flags |= RTN_RTINFO;
 		}
+		fib6_purge_rt(iter, fn, info->nl_net);
+		rt6_release(iter);
 	}
 
 	return 0;
@@ -1322,24 +1346,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
 		fn = fib6_repair_tree(net, fn);
 	}
 
-	if (atomic_read(&rt->rt6i_ref) != 1) {
-		/* This route is used as dummy address holder in some split
-		 * nodes. It is not leaked, but it still holds other resources,
-		 * which must be released in time. So, scan ascendant nodes
-		 * and replace dummy references to this route with references
-		 * to still alive ones.
-		 */
-		while (fn) {
-			if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) {
-				fn->leaf = fib6_find_prefix(net, fn);
-				atomic_inc(&fn->leaf->rt6i_ref);
-				rt6_release(rt);
-			}
-			fn = fn->parent;
-		}
-		/* No more references are possible at this point. */
-		BUG_ON(atomic_read(&rt->rt6i_ref) != 1);
-	}
+	fib6_purge_rt(rt, fn, net);
 
 	inet6_rt_notify(RTM_DELROUTE, rt, info);
 	rt6_release(rt);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 8e950c250ad..7b5cb003ee2 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -555,7 +555,8 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 {
 	struct sk_buff *frag;
 	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
-	struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
+	struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
+				inet6_sk(skb->sk) : NULL;
 	struct ipv6hdr *tmp_hdr;
 	struct frag_hdr *fh;
 	unsigned int mtu, hlen, left, len;
@@ -1296,7 +1297,8 @@ emsgsize:
 	if (((length > mtu) ||
 	     (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
-	    (rt->dst.dev->features & NETIF_F_UFO)) {
+	    (rt->dst.dev->features & NETIF_F_UFO) &&
+	    (sk->sk_type == SOCK_DGRAM)) {
 		err = ip6_ufo_append_data(sk, getfrag, from, length,
 					  hh_len, fragheaderlen,
 					  transhdrlen, mtu, flags, rt);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index bcda14de7f8..8d12faa6200 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -271,8 +271,7 @@ static struct ip6_tnl *vti6_locate(struct net *net, struct __ip6_tnl_parm *p,
 static void vti6_dev_uninit(struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
-	struct net *net = dev_net(dev);
-	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
+	struct vti6_net *ip6n = net_generic(t->net, vti6_net_id);
 
 	if (dev == ip6n->fb_tnl_dev)
 		RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL);
@@ -556,7 +555,7 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (type == NDISC_REDIRECT)
 		ip6_redirect(skb, net, skb->dev->ifindex, 0);
 	else
-		ip6_update_pmtu(skb, net, info, 0, 0);
+		ip6_update_pmtu(skb, net, info, 0, 0, INVALID_UID);
 	xfrm_state_put(x);
 
 	return 0;
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index 1b9316e1386..b247baceb79 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -76,7 +76,7 @@ static int ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (type == NDISC_REDIRECT)
 		ip6_redirect(skb, net, skb->dev->ifindex, 0);
 	else
-		ip6_update_pmtu(skb, net, info, 0, 0);
+		ip6_update_pmtu(skb, net, info, 0, 0, INVALID_UID);
 	xfrm_state_put(x);
 
 	return 0;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 4cb45c1079a..a46c50423ae 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1215,7 +1215,14 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 	if (rt)
 		rt6_set_expires(rt, jiffies + (HZ * lifetime));
 	if (ra_msg->icmph.icmp6_hop_limit) {
-		in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
+		/* Only set hop_limit on the interface if it is higher than
+		 * the current hop_limit.
+		 */
+		if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) {
+			in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
+		} else {
+			ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n");
+		}
 		if (rt)
 			dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
 				       ra_msg->icmph.icmp6_hop_limit);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 5b7a1ed2aba..75aa8c1c403 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -102,9 +102,10 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	if (msg->msg_name) {
 		DECLARE_SOCKADDR(struct sockaddr_in6 *, u, msg->msg_name);
-		if (msg->msg_namelen < sizeof(struct sockaddr_in6) ||
-		    u->sin6_family != AF_INET6) {
+		if (msg->msg_namelen < sizeof(*u))
 			return -EINVAL;
+		if (u->sin6_family != AF_INET6) {
+			return -EAFNOSUPPORT;
 		}
 		if (sk->sk_bound_dev_if &&
 		    sk->sk_bound_dev_if != u->sin6_scope_id) {
@@ -135,6 +136,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	fl6.saddr = np->saddr;
 	fl6.daddr = *daddr;
 	fl6.flowi6_mark = sk->sk_mark;
+	fl6.flowi6_uid = sock_i_uid(sk);
 	fl6.fl6_icmp_type = user_icmph.icmp6_type;
 	fl6.fl6_icmp_code = user_icmph.icmp6_code;
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 896af880797..e332cf1e8b4 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -768,6 +768,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	memset(&fl6, 0, sizeof(fl6));
 
 	fl6.flowi6_mark = sk->sk_mark;
+	fl6.flowi6_uid = sock_i_uid(sk);
 
 	if (sin6) {
 		if (addr_len < SIN6_LEN_RFC2133)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a318dd89b6d..babc601a895 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -95,13 +95,12 @@ static void		rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
 static int rt6_score_route(struct rt6_info *rt, int oif, int strict);
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
-static struct rt6_info *rt6_add_route_info(struct net *net,
+static struct rt6_info *rt6_add_route_info(struct net_device *dev,
 					   const struct in6_addr *prefix, int prefixlen,
-					   const struct in6_addr *gwaddr, int ifindex,
-					   unsigned int pref);
-static struct rt6_info *rt6_get_route_info(struct net *net,
+					   const struct in6_addr *gwaddr, unsigned int pref);
+static struct rt6_info *rt6_get_route_info(struct net_device *dev,
 					   const struct in6_addr *prefix, int prefixlen,
-					   const struct in6_addr *gwaddr, int ifindex);
+					   const struct in6_addr *gwaddr);
 #endif
 
 static void rt6_bind_peer(struct rt6_info *rt, int create)
@@ -141,7 +140,7 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
 	u32 *p = NULL;
 
 	if (!(rt->dst.flags & DST_HOST))
-		return NULL;
+		return dst_cow_metrics_generic(dst, old);
 
 	peer = rt6_get_peer_create(rt);
 	if (peer) {
@@ -700,7 +699,6 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
 int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 		  const struct in6_addr *gwaddr)
 {
-	struct net *net = dev_net(dev);
 	struct route_info *rinfo = (struct route_info *) opt;
 	struct in6_addr prefix_buf, *prefix;
 	unsigned int pref;
@@ -745,8 +743,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 	if (rinfo->prefix_len == 0)
 		rt = rt6_get_dflt_router(gwaddr, dev);
 	else
-		rt = rt6_get_route_info(net, prefix, rinfo->prefix_len,
-					gwaddr, dev->ifindex);
+		rt = rt6_get_route_info(dev, prefix, rinfo->prefix_len,	gwaddr);
 
 	if (rt && !lifetime) {
 		ip6_del_rt(rt);
@@ -754,8 +751,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 	}
 
 	if (!rt && lifetime)
-		rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev->ifindex,
-					pref);
+		rt = rt6_add_route_info(dev, prefix, rinfo->prefix_len, gwaddr, pref);
 	else if (rt)
 		rt->rt6i_flags = RTF_ROUTEINFO |
 				 (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
@@ -1150,19 +1146,16 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 		struct net *net = dev_net(dst->dev);
 
 		rt6->rt6i_flags |= RTF_MODIFIED;
-		if (mtu < IPV6_MIN_MTU) {
-			u32 features = dst_metric(dst, RTAX_FEATURES);
+		if (mtu < IPV6_MIN_MTU)
 			mtu = IPV6_MIN_MTU;
-			features |= RTAX_FEATURE_ALLFRAG;
-			dst_metric_set(dst, RTAX_FEATURES, features);
-		}
+
 		dst_metric_set(dst, RTAX_MTU, mtu);
 		rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires);
 	}
 }
 
 void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
-		     int oif, u32 mark)
+		     int oif, u32 mark, kuid_t uid)
 {
 	const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
 	struct dst_entry *dst;
@@ -1174,6 +1167,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
 	fl6.daddr = iph->daddr;
 	fl6.saddr = iph->saddr;
 	fl6.flowlabel = ip6_flowinfo(iph);
+	fl6.flowi6_uid = uid;
 
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (!dst->error)
@@ -1185,7 +1179,7 @@ EXPORT_SYMBOL_GPL(ip6_update_pmtu);
 void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
 {
 	ip6_update_pmtu(skb, sock_net(sk), mtu,
-			sk->sk_bound_dev_if, sk->sk_mark);
+			sk->sk_bound_dev_if, sk->sk_mark, sock_i_uid(sk));
 }
 EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);
 
@@ -1905,15 +1899,16 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
 }
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
-static struct rt6_info *rt6_get_route_info(struct net *net,
+static struct rt6_info *rt6_get_route_info(struct net_device *dev,
 					   const struct in6_addr *prefix, int prefixlen,
-					   const struct in6_addr *gwaddr, int ifindex)
+					   const struct in6_addr *gwaddr)
 {
 	struct fib6_node *fn;
 	struct rt6_info *rt = NULL;
 	struct fib6_table *table;
 
-	table = fib6_get_table(net, RT6_TABLE_INFO);
+	table = fib6_get_table(dev_net(dev),
+			       addrconf_rt_table(dev, RT6_TABLE_INFO));
 	if (!table)
 		return NULL;
 
@@ -1923,7 +1918,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
 		goto out;
 
 	for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
-		if (rt->dst.dev->ifindex != ifindex)
+		if (rt->dst.dev->ifindex != dev->ifindex)
 			continue;
 		if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY))
 			continue;
@@ -1937,21 +1932,20 @@ out:
 	return rt;
 }
 
-static struct rt6_info *rt6_add_route_info(struct net *net,
+static struct rt6_info *rt6_add_route_info(struct net_device *dev,
 					   const struct in6_addr *prefix, int prefixlen,
-					   const struct in6_addr *gwaddr, int ifindex,
-					   unsigned int pref)
+					   const struct in6_addr *gwaddr, unsigned int pref)
 {
 	struct fib6_config cfg = {
-		.fc_table	= RT6_TABLE_INFO,
+		.fc_table	= addrconf_rt_table(dev, RT6_TABLE_INFO),
 		.fc_metric	= IP6_RT_PRIO_USER,
-		.fc_ifindex	= ifindex,
+		.fc_ifindex	= dev->ifindex,
 		.fc_dst_len	= prefixlen,
 		.fc_flags	= RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO |
 				  RTF_UP | RTF_PREF(pref),
 		.fc_nlinfo.portid = 0,
 		.fc_nlinfo.nlh = NULL,
-		.fc_nlinfo.nl_net = net,
+		.fc_nlinfo.nl_net = dev_net(dev),
 	};
 
 	cfg.fc_dst = *prefix;
@@ -1963,7 +1957,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
 
 	ip6_route_add(&cfg);
 
-	return rt6_get_route_info(net, prefix, prefixlen, gwaddr, ifindex);
+	return rt6_get_route_info(dev, prefix, prefixlen, gwaddr);
 }
 #endif
 
@@ -1972,7 +1966,8 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev
 	struct rt6_info *rt;
 	struct fib6_table *table;
 
-	table = fib6_get_table(dev_net(dev), RT6_TABLE_DFLT);
+	table = fib6_get_table(dev_net(dev),
+			       addrconf_rt_table(dev, RT6_TABLE_MAIN));
 	if (!table)
 		return NULL;
 
@@ -1994,7 +1989,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
 				     unsigned int pref)
 {
 	struct fib6_config cfg = {
-		.fc_table	= RT6_TABLE_DFLT,
+		.fc_table	= addrconf_rt_table(dev, RT6_TABLE_DFLT),
 		.fc_metric	= IP6_RT_PRIO_USER,
 		.fc_ifindex	= dev->ifindex,
 		.fc_flags	= RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
@@ -2011,28 +2006,17 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
 	return rt6_get_dflt_router(gwaddr, dev);
 }
 
-void rt6_purge_dflt_routers(struct net *net)
-{
-	struct rt6_info *rt;
-	struct fib6_table *table;
 
-	/* NOTE: Keep consistent with rt6_get_dflt_router */
-	table = fib6_get_table(net, RT6_TABLE_DFLT);
-	if (!table)
-		return;
+int rt6_addrconf_purge(struct rt6_info *rt, void *arg) {
+	if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
+	    (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2))
+		return -1;
+	return 0;
+}
 
-restart:
-	read_lock_bh(&table->tb6_lock);
-	for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) {
-		if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
-		    (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) {
-			dst_hold(&rt->dst);
-			read_unlock_bh(&table->tb6_lock);
-			ip6_del_rt(rt);
-			goto restart;
-		}
-	}
-	read_unlock_bh(&table->tb6_lock);
+void rt6_purge_dflt_routers(struct net *net)
+{
+	fib6_clean_all(net, rt6_addrconf_purge, NULL);
 }
 
 static void rtmsg_to_fib6_config(struct net *net,
@@ -2338,6 +2322,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_PRIORITY]          = { .type = NLA_U32 },
 	[RTA_METRICS]           = { .type = NLA_NESTED },
 	[RTA_MULTIPATH]		= { .len = sizeof(struct rtnexthop) },
+	[RTA_UID]		= { .type = NLA_U32 },
 };
 
 static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -2727,6 +2712,11 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	if (tb[RTA_MARK])
 		fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]);
 
+	if (tb[RTA_UID])
+		fl6.flowi6_uid = make_kuid(current_user_ns(),
+					   nla_get_u32(tb[RTA_UID]));
+	else
+		fl6.flowi6_uid = iif ? INVALID_UID : current_uid();
 	if (iif) {
 		struct net_device *dev;
 		int flags = 0;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 2f25cb6347c..088a6b840dc 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -247,6 +247,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		fl6.flowi6_mark = ireq->ir_mark;
 		fl6.fl6_dport = ireq->ir_rmt_port;
 		fl6.fl6_sport = inet_sk(sk)->inet_sport;
+		fl6.flowi6_uid = sock_i_uid(sk);
 		security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
 		dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index dc495ae2ead..b36d1eb8fee 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -252,6 +252,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.flowi6_mark = sk->sk_mark;
 	fl6.fl6_dport = usin->sin6_port;
 	fl6.fl6_sport = inet->inet_sport;
+	fl6.flowi6_uid = sock_i_uid(sk);
 
 	final_p = fl6_update_dst(&fl6, np->opt, &final);
 
@@ -787,16 +788,16 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
 	.queue_hash_add =	inet6_csk_reqsk_queue_hash_add,
 };
 
-static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
-				 u32 tsval, u32 tsecr, int oif,
-				 struct tcp_md5sig_key *key, int rst, u8 tclass,
-				 u32 label)
+static void tcp_v6_send_response(struct sock *sk, struct sk_buff *skb, u32 seq,
+				 u32 ack, u32 win, u32 tsval, u32 tsecr,
+				 int oif, struct tcp_md5sig_key *key, int rst,
+				 u8 tclass, u32 label)
 {
 	const struct tcphdr *th = tcp_hdr(skb);
 	struct tcphdr *t1;
 	struct sk_buff *buff;
 	struct flowi6 fl6;
-	struct net *net = dev_net(skb_dst(skb)->dev);
+	struct net *net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
 	struct sock *ctl_sk = net->ipv6.tcp_sk;
 	unsigned int tot_len = sizeof(struct tcphdr);
 	struct dst_entry *dst;
@@ -946,7 +947,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
 			  (th->doff << 2);
 
 	oif = sk ? sk->sk_bound_dev_if : 0;
-	tcp_v6_send_response(skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0);
+	tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0);
 
 #ifdef CONFIG_TCP_MD5SIG
 release_sk1:
@@ -957,13 +958,13 @@ release_sk1:
 #endif
 }
 
-static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
-			    u32 win, u32 tsval, u32 tsecr, int oif,
+static void tcp_v6_send_ack(struct sock *sk, struct sk_buff *skb, u32 seq,
+			    u32 ack, u32 win, u32 tsval, u32 tsecr, int oif,
 			    struct tcp_md5sig_key *key, u8 tclass,
 			    u32 label)
 {
-	tcp_v6_send_response(skb, seq, ack, win, tsval, tsecr, oif, key, 0, tclass,
-			     label);
+	tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, key, 0,
+			     tclass, label);
 }
 
 static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
@@ -971,11 +972,11 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
 	struct inet_timewait_sock *tw = inet_twsk(sk);
 	struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
 
-	tcp_v6_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+	tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_time_stamp + tcptw->tw_ts_offset,
 			tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw),
-			tw->tw_tclass, (tw->tw_flowlabel << 12));
+			tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel));
 
 	inet_twsk_put(tw);
 }
@@ -986,10 +987,10 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
 	 * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
 	 */
-	tcp_v6_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
+	tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ?
 			tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
-			tcp_rsk(req)->rcv_nxt,
-			req->rcv_wnd, tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
+			tcp_rsk(req)->rcv_nxt, req->rcv_wnd,
+			tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
 			tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
 			0, 0);
 }
@@ -1385,6 +1386,37 @@ ipv6_pktoptions:
 	return 0;
 }
 
+static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
+			   const struct tcphdr *th)
+{
+	/* This is tricky: we move IP6CB at its correct location into
+	 * TCP_SKB_CB(). It must be done after xfrm6_policy_check(), because
+	 * _decode_session6() uses IP6CB().
+	 * barrier() makes sure compiler won't play aliasing games.
+	 */
+	memmove(&TCP_SKB_CB(skb)->header.h6, IP6CB(skb),
+		sizeof(struct inet6_skb_parm));
+	barrier();
+
+	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
+	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
+				    skb->len - th->doff*4);
+	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
+	TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
+	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
+	TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
+	TCP_SKB_CB(skb)->sacked = 0;
+}
+
+static void tcp_v6_restore_cb(struct sk_buff *skb)
+{
+	/* We need to move header back to the beginning if xfrm6_policy_check()
+	 * and tcp_v6_fill_cb() are going to be called again.
+	 */
+	memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
+		sizeof(struct inet6_skb_parm));
+}
+
 static int tcp_v6_rcv(struct sk_buff *skb)
 {
 	const struct tcphdr *th;
@@ -1416,24 +1448,9 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 
 	th = tcp_hdr(skb);
 	hdr = ipv6_hdr(skb);
-	/* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
-	 * barrier() makes sure compiler wont play fool^Waliasing games.
-	 */
-	memmove(&TCP_SKB_CB(skb)->header.h6, IP6CB(skb),
-		sizeof(struct inet6_skb_parm));
-	barrier();
-
-	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
-	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
-				    skb->len - th->doff*4);
-	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
-	TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
-	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
-	TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
-	TCP_SKB_CB(skb)->sacked = 0;
 
 	sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest,
-				tcp_v6_iif(skb));
+				inet6_iif(skb));
 	if (!sk)
 		goto no_tcp_socket;
 
@@ -1449,6 +1466,8 @@ process:
 	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_and_relse;
 
+	tcp_v6_fill_cb(skb, hdr, th);
+
 #ifdef CONFIG_TCP_MD5SIG
 	if (tcp_v6_inbound_md5_hash(sk, skb))
 		goto discard_and_relse;
@@ -1480,6 +1499,8 @@ no_tcp_socket:
 	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
 		goto discard_it;
 
+	tcp_v6_fill_cb(skb, hdr, th);
+
 	if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) {
 csum_error:
 		TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS);
@@ -1503,6 +1524,8 @@ do_time_wait:
 		goto discard_it;
 	}
 
+	tcp_v6_fill_cb(skb, hdr, th);
+
 	if (skb->len < (th->doff<<2)) {
 		inet_twsk_put(inet_twsk(sk));
 		goto bad_packet;
@@ -1526,6 +1549,7 @@ do_time_wait:
 			inet_twsk_deschedule(tw, &tcp_death_row);
 			inet_twsk_put(tw);
 			sk = sk2;
+			tcp_v6_restore_cb(skb);
 			goto process;
 		}
 		/* Fall through to ACK */
@@ -1534,6 +1558,7 @@ do_time_wait:
 		tcp_v6_timewait_ack(sk, skb);
 		break;
 	case TCP_TW_RST:
+		tcp_v6_restore_cb(skb);
 		goto no_tcp_socket;
 	case TCP_TW_SUCCESS:
 		;
@@ -1568,7 +1593,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb)
 		skb->sk = sk;
 		skb->destructor = sock_edemux;
 		if (sk->sk_state != TCP_TIME_WAIT) {
-			struct dst_entry *dst = sk->sk_rx_dst;
+			struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst);
 
 			if (dst)
 				dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index f6ba535b6fe..79a080de4d4 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -514,10 +514,8 @@ csum_copy_err:
 	}
 	unlock_sock_fast(sk, slow);
 
-	if (noblock)
-		return -EAGAIN;
-
-	/* starting over for a new packet */
+	/* starting over for a new packet, but check if we need to yield */
+	cond_resched();
 	msg->msg_flags &= ~MSG_TRUNC;
 	goto try_again;
 }
@@ -721,7 +719,9 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
 	    (inet->inet_dport && inet->inet_dport != rmt_port) ||
 	    (!ipv6_addr_any(&sk->sk_v6_daddr) &&
 		    !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) ||
-	    (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
+	    (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) ||
+	    (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
+		    !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)))
 		return false;
 	if (!inet6_mc_check(sk, loc_addr, rmt_addr))
 		return false;
@@ -1213,6 +1213,7 @@ do_udp_sendmsg:
 		fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
 
 	fl6.flowi6_mark = sk->sk_mark;
+	fl6.flowi6_uid = sock_i_uid(sk);
 
 	if (msg->msg_controllen) {
 		opt = &opt_space;
diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c
index 61ceb4cdb4a..23ad419361f 100644
--- a/net/irda/ircomm/ircomm_tty.c
+++ b/net/irda/ircomm/ircomm_tty.c
@@ -816,7 +816,9 @@ static void ircomm_tty_wait_until_sent(struct tty_struct *tty, int timeout)
 	orig_jiffies = jiffies;
 
 	/* Set poll time to 200 ms */
-	poll_time = IRDA_MIN(timeout, msecs_to_jiffies(200));
+	poll_time = msecs_to_jiffies(200);
+	if (timeout)
+		poll_time = min_t(unsigned long, timeout, poll_time);
 
 	spin_lock_irqsave(&self->spinlock, flags);
 	while (self->tx_skb && self->tx_skb->len) {
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index a48bad46888..7702978a4c9 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -49,8 +49,6 @@ static void ieee80211_free_tid_rx(struct rcu_head *h)
 		container_of(h, struct tid_ampdu_rx, rcu_head);
 	int i;
 
-	del_timer_sync(&tid_rx->reorder_timer);
-
 	for (i = 0; i < tid_rx->buf_size; i++)
 		__skb_queue_purge(&tid_rx->reorder_buf[i]);
 	kfree(tid_rx->reorder_buf);
@@ -93,6 +91,12 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid,
 
 	del_timer_sync(&tid_rx->session_timer);
 
+	/* make sure ieee80211_sta_reorder_release() doesn't re-arm the timer */
+	spin_lock_bh(&tid_rx->reorder_lock);
+	tid_rx->removed = true;
+	spin_unlock_bh(&tid_rx->reorder_lock);
+	del_timer_sync(&tid_rx->reorder_timer);
+
 	call_rcu(&tid_rx->rcu_head, ieee80211_free_tid_rx);
 }
 
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index 4c74e8da64b..5ce13a76d0f 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -929,6 +929,21 @@ ieee80211_vif_chanctx_reservation_complete(struct ieee80211_sub_if_data *sdata)
 	}
 }
 
+static void
+ieee80211_vif_update_chandef(struct ieee80211_sub_if_data *sdata,
+			     const struct cfg80211_chan_def *chandef)
+{
+	struct ieee80211_sub_if_data *vlan;
+
+	sdata->vif.bss_conf.chandef = *chandef;
+
+	if (sdata->vif.type != NL80211_IFTYPE_AP)
+		return;
+
+	list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
+		vlan->vif.bss_conf.chandef = *chandef;
+}
+
 static int
 ieee80211_vif_use_reserved_reassign(struct ieee80211_sub_if_data *sdata)
 {
@@ -991,7 +1006,7 @@ ieee80211_vif_use_reserved_reassign(struct ieee80211_sub_if_data *sdata)
 	if (sdata->vif.bss_conf.chandef.width != sdata->reserved_chandef.width)
 		changed = BSS_CHANGED_BANDWIDTH;
 
-	sdata->vif.bss_conf.chandef = sdata->reserved_chandef;
+	ieee80211_vif_update_chandef(sdata, &sdata->reserved_chandef);
 
 	if (changed)
 		ieee80211_bss_info_change_notify(sdata, changed);
@@ -1333,7 +1348,7 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local)
 			    sdata->reserved_chandef.width)
 				changed = BSS_CHANGED_BANDWIDTH;
 
-			sdata->vif.bss_conf.chandef = sdata->reserved_chandef;
+			ieee80211_vif_update_chandef(sdata, &sdata->reserved_chandef);
 			if (changed)
 				ieee80211_bss_info_change_notify(sdata,
 								 changed);
@@ -1504,7 +1519,7 @@ int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
 		goto out;
 	}
 
-	sdata->vif.bss_conf.chandef = *chandef;
+	ieee80211_vif_update_chandef(sdata, chandef);
 
 	ret = ieee80211_assign_vif_chanctx(sdata, ctx);
 	if (ret) {
@@ -1646,7 +1661,7 @@ int ieee80211_vif_change_bandwidth(struct ieee80211_sub_if_data *sdata,
 		break;
 	}
 
-	sdata->vif.bss_conf.chandef = *chandef;
+	ieee80211_vif_update_chandef(sdata, chandef);
 
 	ieee80211_recalc_chanctx_chantype(local, ctx);
 
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 8c68da30595..aed656d18b2 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -58,13 +58,24 @@ struct ieee80211_local;
 #define IEEE80211_UNSET_POWER_LEVEL	INT_MIN
 
 /*
- * Some APs experience problems when working with U-APSD. Decrease the
- * probability of that happening by using legacy mode for all ACs but VO.
- * The AP that caused us trouble was a Cisco 4410N. It ignores our
- * setting, and always treats non-VO ACs as legacy.
+ * Some APs experience problems when working with U-APSD. Decreasing the
+ * probability of that happening by using legacy mode for all ACs but VO isn't
+ * enough.
+ *
+ * Cisco 4410N originally forced us to enable VO by default only because it
+ * treated non-VO ACs as legacy.
+ *
+ * However some APs (notably Netgear R7000) silently reclassify packets to
+ * different ACs. Since u-APSD ACs require trigger frames for frame retrieval
+ * clients would never see some frames (e.g. ARP responses) or would fetch them
+ * accidentally after a long time.
+ *
+ * It makes little sense to enable u-APSD queues by default because it needs
+ * userspace applications to be aware of it to actually take advantage of the
+ * possible additional powersavings. Implicitly depending on driver autotrigger
+ * frame support doesn't make much sense.
  */
-#define IEEE80211_DEFAULT_UAPSD_QUEUES \
-	IEEE80211_WMM_IE_STA_QOSINFO_AC_VO
+#define IEEE80211_DEFAULT_UAPSD_QUEUES 0
 
 #define IEEE80211_DEFAULT_MAX_SP_LEN		\
 	IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL
@@ -193,6 +204,8 @@ enum ieee80211_packet_rx_flags {
  * @IEEE80211_RX_CMNTR: received on cooked monitor already
  * @IEEE80211_RX_BEACON_REPORTED: This frame was already reported
  *	to cfg80211_report_obss_beacon().
+ * @IEEE80211_RX_REORDER_TIMER: this frame is released by the
+ *	reorder buffer timeout timer, not the normal RX path
  *
  * These flags are used across handling multiple interfaces
  * for a single frame.
@@ -200,6 +213,7 @@ enum ieee80211_packet_rx_flags {
 enum ieee80211_rx_flags {
 	IEEE80211_RX_CMNTR		= BIT(0),
 	IEEE80211_RX_BEACON_REPORTED	= BIT(1),
+	IEEE80211_RX_REORDER_TIMER	= BIT(2),
 };
 
 struct ieee80211_rx_data {
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 653f5eb07a2..eeae0abd01d 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -511,6 +511,7 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 		sdata->vif.cab_queue = master->vif.cab_queue;
 		memcpy(sdata->vif.hw_queue, master->vif.hw_queue,
 		       sizeof(sdata->vif.hw_queue));
+		sdata->vif.bss_conf.chandef = master->vif.bss_conf.chandef;
 		break;
 		}
 	case NL80211_IFTYPE_AP:
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 4712150dc21..94368404744 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -131,7 +131,9 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 	if (!ret) {
 		key->flags |= KEY_FLAG_UPLOADED_TO_HARDWARE;
 
-		if (!(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC))
+		if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
+		      (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV) ||
+		      (key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)))
 			sdata->crypto_tx_tailroom_needed_cnt--;
 
 		WARN_ON((key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) &&
@@ -179,7 +181,9 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key)
 	sta = key->sta;
 	sdata = key->sdata;
 
-	if (!(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC))
+	if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
+	      (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV) ||
+	      (key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)))
 		increment_tailroom_need_count(sdata);
 
 	ret = drv_set_key(key->local, DISABLE_KEY, sdata,
@@ -647,7 +651,7 @@ void ieee80211_free_sta_keys(struct ieee80211_local *local,
 	int i;
 
 	mutex_lock(&local->key_mtx);
-	for (i = 0; i < NUM_DEFAULT_KEYS; i++) {
+	for (i = 0; i < ARRAY_SIZE(sta->gtk); i++) {
 		key = key_mtx_dereference(local, sta->gtk[i]);
 		if (!key)
 			continue;
@@ -875,7 +879,9 @@ void ieee80211_remove_key(struct ieee80211_key_conf *keyconf)
 	if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) {
 		key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE;
 
-		if (!(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC))
+		if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
+		      (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV) ||
+		      (key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)))
 			increment_tailroom_need_count(key->sdata);
 	}
 
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 0de7c93bf62..67943cb5df8 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -249,6 +249,7 @@ static void ieee80211_restart_work(struct work_struct *work)
 {
 	struct ieee80211_local *local =
 		container_of(work, struct ieee80211_local, restart_work);
+	struct ieee80211_sub_if_data *sdata;
 
 	/* wait for scan work complete */
 	flush_workqueue(local->workqueue);
@@ -257,6 +258,8 @@ static void ieee80211_restart_work(struct work_struct *work)
 	     "%s called with hardware scan in progress\n", __func__);
 
 	rtnl_lock();
+	list_for_each_entry(sdata, &local->interfaces, list)
+		flush_delayed_work(&sdata->dec_tailroom_needed_wk);
 	ieee80211_scan_cancel(local);
 	ieee80211_reconfig(local);
 	rtnl_unlock();
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 93af0f1c9d9..da1f639ecfb 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -174,6 +174,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 	if (!(ht_cap->cap_info &
 	      cpu_to_le16(IEEE80211_HT_CAP_SUP_WIDTH_20_40))) {
 		ret = IEEE80211_STA_DISABLE_40MHZ;
+		vht_chandef = *chandef;
 		goto out;
 	}
 
diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index 4c5192e0d66..4a95fe3cffb 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -86,20 +86,6 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 		}
 	}
 
-	/* tear down aggregation sessions and remove STAs */
-	mutex_lock(&local->sta_mtx);
-	list_for_each_entry(sta, &local->sta_list, list) {
-		if (sta->uploaded) {
-			enum ieee80211_sta_state state;
-
-			state = sta->sta_state;
-			for (; state > IEEE80211_STA_NOTEXIST; state--)
-				WARN_ON(drv_sta_state(local, sta->sdata, sta,
-						      state, state - 1));
-		}
-	}
-	mutex_unlock(&local->sta_mtx);
-
 	/* remove all interfaces that were created in the driver */
 	list_for_each_entry(sdata, &local->interfaces, list) {
 		if (!ieee80211_sdata_running(sdata))
@@ -111,6 +97,21 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 		case NL80211_IFTYPE_STATION:
 			ieee80211_mgd_quiesce(sdata);
 			break;
+		case NL80211_IFTYPE_WDS:
+			/* tear down aggregation sessions and remove STAs */
+			mutex_lock(&local->sta_mtx);
+			sta = sdata->u.wds.sta;
+			if (sta && sta->uploaded) {
+				enum ieee80211_sta_state state;
+
+				state = sta->sta_state;
+				for (; state > IEEE80211_STA_NOTEXIST; state--)
+					WARN_ON(drv_sta_state(local, sta->sdata,
+							      sta, state,
+							      state - 1));
+			}
+			mutex_unlock(&local->sta_mtx);
+			break;
 		default:
 			break;
 		}
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index a37f9af634c..a578c571711 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -235,7 +235,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	else if (rate && rate->flags & IEEE80211_RATE_ERP_G)
 		channel_flags |= IEEE80211_CHAN_OFDM | IEEE80211_CHAN_2GHZ;
 	else if (rate)
-		channel_flags |= IEEE80211_CHAN_OFDM | IEEE80211_CHAN_2GHZ;
+		channel_flags |= IEEE80211_CHAN_CCK | IEEE80211_CHAN_2GHZ;
 	else
 		channel_flags |= IEEE80211_CHAN_2GHZ;
 	put_unaligned_le16(channel_flags, pos);
@@ -808,9 +808,10 @@ static void ieee80211_sta_reorder_release(struct ieee80211_sub_if_data *sdata,
 
  set_release_timer:
 
-		mod_timer(&tid_agg_rx->reorder_timer,
-			  tid_agg_rx->reorder_time[j] + 1 +
-			  HT_RX_REORDER_BUF_TIMEOUT);
+		if (!tid_agg_rx->removed)
+			mod_timer(&tid_agg_rx->reorder_timer,
+				  tid_agg_rx->reorder_time[j] + 1 +
+				  HT_RX_REORDER_BUF_TIMEOUT);
 	} else {
 		del_timer(&tid_agg_rx->reorder_timer);
 	}
@@ -1678,14 +1679,14 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 	sc = le16_to_cpu(hdr->seq_ctrl);
 	frag = sc & IEEE80211_SCTL_FRAG;
 
-	if (likely(!ieee80211_has_morefrags(fc) && frag == 0))
-		goto out;
-
 	if (is_multicast_ether_addr(hdr->addr1)) {
 		rx->local->dot11MulticastReceivedFrameCount++;
-		goto out;
+		goto out_no_led;
 	}
 
+	if (likely(!ieee80211_has_morefrags(fc) && frag == 0))
+		goto out;
+
 	I802_DEBUG_INC(rx->local->rx_handlers_fragments);
 
 	if (skb_linearize(rx->skb))
@@ -1776,9 +1777,10 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 	status->rx_flags |= IEEE80211_RX_FRAGMENTED;
 
  out:
+	ieee80211_led_rx(rx->local);
+ out_no_led:
 	if (rx->sta)
 		rx->sta->rx_packets++;
-	ieee80211_led_rx(rx->local);
 	return RX_CONTINUE;
 }
 
@@ -1998,7 +2000,8 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx)
 		/* deliver to local stack */
 		skb->protocol = eth_type_trans(skb, dev);
 		memset(skb->cb, 0, sizeof(skb->cb));
-		if (rx->local->napi)
+		if (!(rx->flags & IEEE80211_RX_REORDER_TIMER) &&
+		    rx->local->napi)
 			napi_gro_receive(rx->local->napi, skb);
 		else
 			netif_receive_skb(skb);
@@ -2107,6 +2110,9 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
 	hdr = (struct ieee80211_hdr *) skb->data;
 	mesh_hdr = (struct ieee80211s_hdr *) (skb->data + hdrlen);
 
+	if (ieee80211_drop_unencrypted(rx, hdr->frame_control))
+		return RX_DROP_MONITOR;
+
 	/* frame is in RMC, don't forward */
 	if (ieee80211_is_data(hdr->frame_control) &&
 	    is_multicast_ether_addr(hdr->addr1) &&
@@ -3065,7 +3071,7 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid)
 		/* This is OK -- must be QoS data frame */
 		.security_idx = tid,
 		.seqno_idx = tid,
-		.flags = 0,
+		.flags = IEEE80211_RX_REORDER_TIMER,
 	};
 	struct tid_ampdu_rx *tid_agg_rx;
 
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index bcda2ac7d84..bdba4ca5e76 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -170,6 +170,7 @@ struct tid_ampdu_tx {
  * @reorder_lock: serializes access to reorder buffer, see below.
  * @auto_seq: used for offloaded BA sessions to automatically pick head_seq_and
  *	and ssn.
+ * @removed: this session is removed (but might have been found due to RCU)
  *
  * This structure's lifetime is managed by RCU, assignments to
  * the array holding it must hold the aggregation mutex.
@@ -194,6 +195,7 @@ struct tid_ampdu_rx {
 	u16 timeout;
 	u8 dialog_token;
 	bool auto_seq;
+	bool removed;
 };
 
 /**
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 900632a250e..80ce44f6693 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -563,6 +563,7 @@ ieee80211_tx_h_check_control_port_protocol(struct ieee80211_tx_data *tx)
 		if (tx->sdata->control_port_no_encrypt)
 			info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT;
 		info->control.flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO;
+		info->flags |= IEEE80211_TX_CTL_USE_MINRATE;
 	}
 
 	return TX_CONTINUE;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 3c61060a4d2..0043256df48 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -3050,7 +3050,7 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata,
 		wdev_iter = &sdata_iter->wdev;
 
 		if (sdata_iter == sdata ||
-		    rcu_access_pointer(sdata_iter->vif.chanctx_conf) == NULL ||
+		    !ieee80211_sdata_running(sdata_iter) ||
 		    local->hw.wiphy->software_iftypes & BIT(wdev_iter->iftype))
 			continue;
 
diff --git a/net/mac80211/wep.c b/net/mac80211/wep.c
index 9181fb6d643..837b7b1bb31 100644
--- a/net/mac80211/wep.c
+++ b/net/mac80211/wep.c
@@ -98,8 +98,7 @@ static u8 *ieee80211_wep_add_iv(struct ieee80211_local *local,
 
 	hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_PROTECTED);
 
-	if (WARN_ON(skb_tailroom(skb) < IEEE80211_WEP_ICV_LEN ||
-		    skb_headroom(skb) < IEEE80211_WEP_IV_LEN))
+	if (WARN_ON(skb_headroom(skb) < IEEE80211_WEP_IV_LEN))
 		return NULL;
 
 	hdrlen = ieee80211_hdrlen(hdr->frame_control);
@@ -169,6 +168,9 @@ int ieee80211_wep_encrypt(struct ieee80211_local *local,
 	size_t len;
 	u8 rc4key[3 + WLAN_KEY_LEN_WEP104];
 
+	if (WARN_ON(skb_tailroom(skb) < IEEE80211_WEP_ICV_LEN))
+		return -1;
+
 	iv = ieee80211_wep_add_iv(local, skb, keylen, keyidx);
 	if (!iv)
 		return -1;
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index ae5096ab65e..6b099d15585 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -1255,6 +1255,8 @@ config NETFILTER_XT_MATCH_OWNER
 	based on who created the socket: the user or group. It is also
 	possible to check whether a socket actually exists.
 
+	Conflicts with '"quota, tag, uid" match'
+
 config NETFILTER_XT_MATCH_POLICY
 	tristate 'IPsec "policy" match support'
 	depends on XFRM
@@ -1288,6 +1290,22 @@ config NETFILTER_XT_MATCH_PKTTYPE
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config NETFILTER_XT_MATCH_QTAGUID
+	bool '"quota, tag, owner" match and stats support'
+        depends on NETFILTER_XT_MATCH_SOCKET
+	depends on NETFILTER_XT_MATCH_OWNER=n
+	help
+	  This option replaces the `owner' match. In addition to matching
+	  on uid, it keeps stats based on a tag assigned to a socket.
+	  The full tag is comprised of a UID and an accounting tag.
+	  The tags are assignable to sockets from user space (e.g. a download
+	  manager can assign the socket to another UID for accounting).
+	  Stats and control are done via /proc/net/xt_qtaguid/.
+	  It replaces owner as it takes the same arguments, but should
+	  really be recognized by the iptables tool.
+
+	  If unsure, say `N'.
+
 config NETFILTER_XT_MATCH_QUOTA
 	tristate '"quota" match support'
 	depends on NETFILTER_ADVANCED
@@ -1298,6 +1316,30 @@ config NETFILTER_XT_MATCH_QUOTA
 	  If you want to compile it as a module, say M here and read
 	  <file:Documentation/kbuild/modules.txt>.  If unsure, say `N'.
 
+config NETFILTER_XT_MATCH_QUOTA2
+	tristate '"quota2" match support'
+	depends on NETFILTER_ADVANCED
+	help
+	  This option adds a `quota2' match, which allows to match on a
+	  byte counter correctly and not per CPU.
+	  It allows naming the quotas.
+	  This is based on http://xtables-addons.git.sourceforge.net
+
+	  If you want to compile it as a module, say M here and read
+	  <file:Documentation/kbuild/modules.txt>.  If unsure, say `N'.
+
+config NETFILTER_XT_MATCH_QUOTA2_LOG
+	bool '"quota2" Netfilter LOG support'
+	depends on NETFILTER_XT_MATCH_QUOTA2
+	depends on IP_NF_TARGET_ULOG=n    # not yes, not module, just no
+	default n
+	help
+	  This option allows `quota2' to log ONCE when a quota limit
+	  is passed. It logs via NETLINK using the NETLINK_NFLOG family.
+	  It logs similarly to how ipt_ULOG would without data.
+
+	  If unsure, say `N'.
+
 config NETFILTER_XT_MATCH_RATEEST
 	tristate '"rateest" match support'
 	depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index a9571be3f79..c07bfc8c77c 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -155,7 +155,9 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_CGROUP) += xt_cgroup.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_PHYSDEV) += xt_physdev.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_PKTTYPE) += xt_pkttype.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_POLICY) += xt_policy.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_QTAGUID) += xt_qtaguid_print.o xt_qtaguid.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_QUOTA) += xt_quota.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_QUOTA2) += xt_quota2.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_RATEEST) += xt_rateest.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_REALM) += xt_realm.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_RECENT) += xt_recent.o
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 024a2e25c8a..d047a6679ff 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -88,6 +88,7 @@ void nf_unregister_hook(struct nf_hook_ops *reg)
 	static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]);
 #endif
 	synchronize_net();
+	nf_queue_nf_hook_drop(reg);
 }
 EXPORT_SYMBOL(nf_unregister_hook);
 
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 1d5341f3761..5d3daae98bf 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -183,6 +183,8 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	struct nf_conn *ct;
 	struct net *net;
 
+	*diff = 0;
+
 #ifdef CONFIG_IP_VS_IPV6
 	/* This application helper doesn't work with IPv6 yet,
 	 * so turn this into a no-op for IPv6 packets
@@ -191,8 +193,6 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		return 1;
 #endif
 
-	*diff = 0;
-
 	/* Only useful for established sessions */
 	if (cp->state != IP_VS_TCP_S_ESTABLISHED)
 		return 1;
@@ -322,6 +322,9 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	struct ip_vs_conn *n_cp;
 	struct net *net;
 
+	/* no diff required for incoming packets */
+	*diff = 0;
+
 #ifdef CONFIG_IP_VS_IPV6
 	/* This application helper doesn't work with IPv6 yet,
 	 * so turn this into a no-op for IPv6 packets
@@ -330,9 +333,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		return 1;
 #endif
 
-	/* no diff required for incoming packets */
-	*diff = 0;
-
 	/* Only useful for established sessions */
 	if (cp->state != IP_VS_TCP_S_ESTABLISHED)
 		return 1;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 5016a692908..c5880124ec0 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -611,16 +611,15 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	 */
 	NF_CT_ASSERT(!nf_ct_is_confirmed(ct));
 	pr_debug("Confirming conntrack %p\n", ct);
-	/* We have to check the DYING flag inside the lock to prevent
-	   a race against nf_ct_get_next_corpse() possibly called from
-	   user context, else we insert an already 'dead' hash, blocking
-	   further use of that particular connection -JM */
+	/* We have to check the DYING flag after unlink to prevent
+	 * a race against nf_ct_get_next_corpse() possibly called from
+	 * user context, else we insert an already 'dead' hash, blocking
+	 * further use of that particular connection -JM.
+	 */
+	nf_ct_del_from_dying_or_unconfirmed_list(ct);
 
-	if (unlikely(nf_ct_is_dying(ct))) {
-		nf_conntrack_double_unlock(hash, reply_hash);
-		local_bh_enable();
-		return NF_ACCEPT;
-	}
+	if (unlikely(nf_ct_is_dying(ct)))
+		goto out;
 
 	/* See if there's one in the list already, including reverse:
 	   NAT could have grabbed it without realizing, since we're
@@ -636,8 +635,6 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 		    zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
 			goto out;
 
-	nf_ct_del_from_dying_or_unconfirmed_list(ct);
-
 	/* Timer relative to confirmation time, not original
 	   setting time, otherwise we'd get timer wrap in
 	   weird delay cases. */
@@ -673,6 +670,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	return NF_ACCEPT;
 
 out:
+	nf_ct_add_to_dying_list(ct);
 	nf_conntrack_double_unlock(hash, reply_hash);
 	NF_CT_STAT_INC(net, insert_failed);
 	local_bh_enable();
diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h
index 61a3c927e63..aba1d7dac17 100644
--- a/net/netfilter/nf_internals.h
+++ b/net/netfilter/nf_internals.h
@@ -24,6 +24,7 @@ int nf_queue(struct sk_buff *skb, struct nf_hook_ops *elem, u_int8_t pf,
 	     unsigned int hook, struct net_device *indev,
 	     struct net_device *outdev, int (*okfn)(struct sk_buff *),
 	     unsigned int queuenum);
+void nf_queue_nf_hook_drop(struct nf_hook_ops *ops);
 int __init netfilter_queue_init(void);
 
 /* nf_log.c */
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 4c8b68e5fa1..77ee2d4d504 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -95,6 +95,23 @@ bool nf_queue_entry_get_refs(struct nf_queue_entry *entry)
 }
 EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs);
 
+void nf_queue_nf_hook_drop(struct nf_hook_ops *ops)
+{
+	const struct nf_queue_handler *qh;
+	struct net *net;
+
+	rtnl_lock();
+	rcu_read_lock();
+	qh = rcu_dereference(queue_handler);
+	if (qh) {
+		for_each_net(net) {
+			qh->nf_hook_drop(net, ops);
+		}
+	}
+	rcu_read_unlock();
+	rtnl_unlock();
+}
+
 /*
  * Any packet that leaves via this function must come back
  * through nf_reinject().
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 66e8425dbfe..9fe2baa01fb 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -713,16 +713,12 @@ static int nft_flush_table(struct nft_ctx *ctx)
 	struct nft_chain *chain, *nc;
 	struct nft_set *set, *ns;
 
-	list_for_each_entry_safe(chain, nc, &ctx->table->chains, list) {
+	list_for_each_entry(chain, &ctx->table->chains, list) {
 		ctx->chain = chain;
 
 		err = nft_delrule_by_chain(ctx);
 		if (err < 0)
 			goto out;
-
-		err = nft_delchain(ctx);
-		if (err < 0)
-			goto out;
 	}
 
 	list_for_each_entry_safe(set, ns, &ctx->table->sets, list) {
@@ -735,6 +731,14 @@ static int nft_flush_table(struct nft_ctx *ctx)
 			goto out;
 	}
 
+	list_for_each_entry_safe(chain, nc, &ctx->table->chains, list) {
+		ctx->chain = chain;
+
+		err = nft_delchain(ctx);
+		if (err < 0)
+			goto out;
+	}
+
 	err = nft_deltable(ctx);
 out:
 	return err;
@@ -1217,7 +1221,10 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 
 	if (nla[NFTA_CHAIN_POLICY]) {
 		if ((chain != NULL &&
-		    !(chain->flags & NFT_BASE_CHAIN)) ||
+		    !(chain->flags & NFT_BASE_CHAIN)))
+			return -EOPNOTSUPP;
+
+		if (chain == NULL &&
 		    nla[NFTA_CHAIN_HOOK] == NULL)
 			return -EOPNOTSUPP;
 
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 13c2e17bbe2..1aa7049c93f 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -321,7 +321,8 @@ replay:
 		nlh = nlmsg_hdr(skb);
 		err = 0;
 
-		if (nlh->nlmsg_len < NLMSG_HDRLEN) {
+		if (nlmsg_len(nlh) < sizeof(struct nfgenmsg) ||
+		    skb->len < nlh->nlmsg_len) {
 			err = -EINVAL;
 			goto ack;
 		}
@@ -469,7 +470,7 @@ static int nfnetlink_bind(int group)
 	int type;
 
 	if (group <= NFNLGRP_NONE || group > NFNLGRP_MAX)
-		return -EINVAL;
+		return 0;
 
 	type = nfnl_group2type[group];
 
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 9e287cb56a0..54330fb5efa 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -77,6 +77,9 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple,
 	if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM])
 		return -EINVAL;
 
+	/* Not all fields are initialized so first zero the tuple */
+	memset(tuple, 0, sizeof(struct nf_conntrack_tuple));
+
 	tuple->src.l3num = ntohs(nla_get_be16(tb[NFCTH_TUPLE_L3PROTONUM]));
 	tuple->dst.protonum = nla_get_u8(tb[NFCTH_TUPLE_L4PROTONUM]);
 
@@ -86,7 +89,7 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple,
 static int
 nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
 {
-	const struct nf_conn_help *help = nfct_help(ct);
+	struct nf_conn_help *help = nfct_help(ct);
 
 	if (attr == NULL)
 		return -EINVAL;
@@ -94,7 +97,7 @@ nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
 	if (help->helper->data_len == 0)
 		return -EINVAL;
 
-	memcpy(&help->data, nla_data(attr), help->helper->data_len);
+	memcpy(help->data, nla_data(attr), help->helper->data_len);
 	return 0;
 }
 
diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c
index 7c60ccd61a3..8add272654f 100644
--- a/net/netfilter/nfnetlink_queue_core.c
+++ b/net/netfilter/nfnetlink_queue_core.c
@@ -815,6 +815,27 @@ static struct notifier_block nfqnl_dev_notifier = {
 	.notifier_call	= nfqnl_rcv_dev_event,
 };
 
+static int nf_hook_cmp(struct nf_queue_entry *entry, unsigned long ops_ptr)
+{
+	return entry->elem == (struct nf_hook_ops *)ops_ptr;
+}
+
+static void nfqnl_nf_hook_drop(struct net *net, struct nf_hook_ops *hook)
+{
+	struct nfnl_queue_net *q = nfnl_queue_pernet(net);
+	int i;
+
+	rcu_read_lock();
+	for (i = 0; i < INSTANCE_BUCKETS; i++) {
+		struct nfqnl_instance *inst;
+		struct hlist_head *head = &q->instance_table[i];
+
+		hlist_for_each_entry_rcu(inst, head, hlist)
+			nfqnl_flush(inst, nf_hook_cmp, (unsigned long)hook);
+	}
+	rcu_read_unlock();
+}
+
 static int
 nfqnl_rcv_nl_event(struct notifier_block *this,
 		   unsigned long event, void *ptr)
@@ -1022,7 +1043,8 @@ static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = {
 };
 
 static const struct nf_queue_handler nfqh = {
-	.outfn	= &nfqnl_enqueue_packet,
+	.outfn		= &nfqnl_enqueue_packet,
+	.nf_hook_drop	= &nfqnl_nf_hook_drop,
 };
 
 static int
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 265e190f221..e22a2961cc3 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -97,6 +97,9 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par,
 		entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0;
 		break;
 	case AF_INET6:
+		if (proto)
+			entry->e6.ipv6.flags |= IP6T_F_PROTO;
+
 		entry->e6.ipv6.proto = proto;
 		entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0;
 		break;
@@ -304,6 +307,9 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx,
 		entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0;
 		break;
 	case AF_INET6:
+		if (proto)
+			entry->e6.ipv6.flags |= IP6T_F_PROTO;
+
 		entry->e6.ipv6.proto = proto;
 		entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0;
 		break;
diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index f407ebc1348..31f76cd19d3 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -5,6 +5,7 @@
  * After timer expires a kevent will be sent.
  *
  * Copyright (C) 2004, 2010 Nokia Corporation
+ *
  * Written by Timo Teras <ext-timo.teras@nokia.com>
  *
  * Converted to x_tables and reworked for upstream inclusion
@@ -38,8 +39,16 @@
 #include <linux/netfilter/xt_IDLETIMER.h>
 #include <linux/kdev_t.h>
 #include <linux/kobject.h>
+#include <linux/skbuff.h>
 #include <linux/workqueue.h>
 #include <linux/sysfs.h>
+#include <linux/rtc.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+#include <linux/suspend.h>
+#include <linux/notifier.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
 
 struct idletimer_tg_attr {
 	struct attribute attr;
@@ -55,14 +64,110 @@ struct idletimer_tg {
 	struct kobject *kobj;
 	struct idletimer_tg_attr attr;
 
+	struct timespec delayed_timer_trigger;
+	struct timespec last_modified_timer;
+	struct timespec last_suspend_time;
+	struct notifier_block pm_nb;
+
+	int timeout;
 	unsigned int refcnt;
+	bool work_pending;
+	bool send_nl_msg;
+	bool active;
+	uid_t uid;
 };
 
 static LIST_HEAD(idletimer_tg_list);
 static DEFINE_MUTEX(list_mutex);
+static DEFINE_SPINLOCK(timestamp_lock);
 
 static struct kobject *idletimer_tg_kobj;
 
+static bool check_for_delayed_trigger(struct idletimer_tg *timer,
+		struct timespec *ts)
+{
+	bool state;
+	struct timespec temp;
+	spin_lock_bh(&timestamp_lock);
+	timer->work_pending = false;
+	if ((ts->tv_sec - timer->last_modified_timer.tv_sec) > timer->timeout ||
+			timer->delayed_timer_trigger.tv_sec != 0) {
+		state = false;
+		temp.tv_sec = timer->timeout;
+		temp.tv_nsec = 0;
+		if (timer->delayed_timer_trigger.tv_sec != 0) {
+			temp = timespec_add(timer->delayed_timer_trigger, temp);
+			ts->tv_sec = temp.tv_sec;
+			ts->tv_nsec = temp.tv_nsec;
+			timer->delayed_timer_trigger.tv_sec = 0;
+			timer->work_pending = true;
+			schedule_work(&timer->work);
+		} else {
+			temp = timespec_add(timer->last_modified_timer, temp);
+			ts->tv_sec = temp.tv_sec;
+			ts->tv_nsec = temp.tv_nsec;
+		}
+	} else {
+		state = timer->active;
+	}
+	spin_unlock_bh(&timestamp_lock);
+	return state;
+}
+
+static void notify_netlink_uevent(const char *iface, struct idletimer_tg *timer)
+{
+	char iface_msg[NLMSG_MAX_SIZE];
+	char state_msg[NLMSG_MAX_SIZE];
+	char timestamp_msg[NLMSG_MAX_SIZE];
+	char uid_msg[NLMSG_MAX_SIZE];
+	char *envp[] = { iface_msg, state_msg, timestamp_msg, uid_msg, NULL };
+	int res;
+	struct timespec ts;
+	uint64_t time_ns;
+	bool state;
+
+	res = snprintf(iface_msg, NLMSG_MAX_SIZE, "INTERFACE=%s",
+		       iface);
+	if (NLMSG_MAX_SIZE <= res) {
+		pr_err("message too long (%d)", res);
+		return;
+	}
+
+	get_monotonic_boottime(&ts);
+	state = check_for_delayed_trigger(timer, &ts);
+	res = snprintf(state_msg, NLMSG_MAX_SIZE, "STATE=%s",
+			state ? "active" : "inactive");
+
+	if (NLMSG_MAX_SIZE <= res) {
+		pr_err("message too long (%d)", res);
+		return;
+	}
+
+	if (state) {
+		res = snprintf(uid_msg, NLMSG_MAX_SIZE, "UID=%u", timer->uid);
+		if (NLMSG_MAX_SIZE <= res)
+			pr_err("message too long (%d)", res);
+	} else {
+		res = snprintf(uid_msg, NLMSG_MAX_SIZE, "UID=");
+		if (NLMSG_MAX_SIZE <= res)
+			pr_err("message too long (%d)", res);
+	}
+
+	time_ns = timespec_to_ns(&ts);
+	res = snprintf(timestamp_msg, NLMSG_MAX_SIZE, "TIME_NS=%llu", time_ns);
+	if (NLMSG_MAX_SIZE <= res) {
+		timestamp_msg[0] = '\0';
+		pr_err("message too long (%d)", res);
+	}
+
+	pr_debug("putting nlmsg: <%s> <%s> <%s> <%s>\n", iface_msg, state_msg,
+		 timestamp_msg, uid_msg);
+	kobject_uevent_env(idletimer_tg_kobj, KOBJ_CHANGE, envp);
+	return;
+
+
+}
+
 static
 struct idletimer_tg *__idletimer_tg_find_by_label(const char *label)
 {
@@ -83,6 +188,7 @@ static ssize_t idletimer_tg_show(struct kobject *kobj, struct attribute *attr,
 {
 	struct idletimer_tg *timer;
 	unsigned long expires = 0;
+	unsigned long now = jiffies;
 
 	mutex_lock(&list_mutex);
 
@@ -92,11 +198,15 @@ static ssize_t idletimer_tg_show(struct kobject *kobj, struct attribute *attr,
 
 	mutex_unlock(&list_mutex);
 
-	if (time_after(expires, jiffies))
+	if (time_after(expires, now))
 		return sprintf(buf, "%u\n",
-			       jiffies_to_msecs(expires - jiffies) / 1000);
+			       jiffies_to_msecs(expires - now) / 1000);
 
-	return sprintf(buf, "0\n");
+	if (timer->send_nl_msg)
+		return sprintf(buf, "0 %d\n",
+			jiffies_to_msecs(now - expires) / 1000);
+	else
+		return sprintf(buf, "0\n");
 }
 
 static void idletimer_tg_work(struct work_struct *work)
@@ -105,6 +215,9 @@ static void idletimer_tg_work(struct work_struct *work)
 						  work);
 
 	sysfs_notify(idletimer_tg_kobj, NULL, timer->attr.attr.name);
+
+	if (timer->send_nl_msg)
+		notify_netlink_uevent(timer->attr.attr.name, timer);
 }
 
 static void idletimer_tg_expired(unsigned long data)
@@ -112,8 +225,55 @@ static void idletimer_tg_expired(unsigned long data)
 	struct idletimer_tg *timer = (struct idletimer_tg *) data;
 
 	pr_debug("timer %s expired\n", timer->attr.attr.name);
-
+	spin_lock_bh(&timestamp_lock);
+	timer->active = false;
+	timer->work_pending = true;
 	schedule_work(&timer->work);
+	spin_unlock_bh(&timestamp_lock);
+}
+
+static int idletimer_resume(struct notifier_block *notifier,
+		unsigned long pm_event, void *unused)
+{
+	struct timespec ts;
+	unsigned long time_diff, now = jiffies;
+	struct idletimer_tg *timer = container_of(notifier,
+			struct idletimer_tg, pm_nb);
+	if (!timer)
+		return NOTIFY_DONE;
+	switch (pm_event) {
+	case PM_SUSPEND_PREPARE:
+		get_monotonic_boottime(&timer->last_suspend_time);
+		break;
+	case PM_POST_SUSPEND:
+		spin_lock_bh(&timestamp_lock);
+		if (!timer->active) {
+			spin_unlock_bh(&timestamp_lock);
+			break;
+		}
+		/* since jiffies are not updated when suspended now represents
+		 * the time it would have suspended */
+		if (time_after(timer->timer.expires, now)) {
+			get_monotonic_boottime(&ts);
+			ts = timespec_sub(ts, timer->last_suspend_time);
+			time_diff = timespec_to_jiffies(&ts);
+			if (timer->timer.expires > (time_diff + now)) {
+				mod_timer_pending(&timer->timer,
+						(timer->timer.expires - time_diff));
+			} else {
+				del_timer(&timer->timer);
+				timer->timer.expires = 0;
+				timer->active = false;
+				timer->work_pending = true;
+				schedule_work(&timer->work);
+			}
+		}
+		spin_unlock_bh(&timestamp_lock);
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_DONE;
 }
 
 static int idletimer_tg_create(struct idletimer_tg_info *info)
@@ -145,6 +305,21 @@ static int idletimer_tg_create(struct idletimer_tg_info *info)
 	setup_timer(&info->timer->timer, idletimer_tg_expired,
 		    (unsigned long) info->timer);
 	info->timer->refcnt = 1;
+	info->timer->send_nl_msg = (info->send_nl_msg == 0) ? false : true;
+	info->timer->active = true;
+	info->timer->timeout = info->timeout;
+
+	info->timer->delayed_timer_trigger.tv_sec = 0;
+	info->timer->delayed_timer_trigger.tv_nsec = 0;
+	info->timer->work_pending = false;
+	info->timer->uid = 0;
+	get_monotonic_boottime(&info->timer->last_modified_timer);
+
+	info->timer->pm_nb.notifier_call = idletimer_resume;
+	ret = register_pm_notifier(&info->timer->pm_nb);
+	if (ret)
+		printk(KERN_WARNING "[%s] Failed to register pm notifier %d\n",
+				__func__, ret);
 
 	mod_timer(&info->timer->timer,
 		  msecs_to_jiffies(info->timeout * 1000) + jiffies);
@@ -161,6 +336,42 @@ out:
 	return ret;
 }
 
+static void reset_timer(const struct idletimer_tg_info *info,
+			struct sk_buff *skb)
+{
+	unsigned long now = jiffies;
+	struct idletimer_tg *timer = info->timer;
+	bool timer_prev;
+
+	spin_lock_bh(&timestamp_lock);
+	timer_prev = timer->active;
+	timer->active = true;
+	/* timer_prev is used to guard overflow problem in time_before*/
+	if (!timer_prev || time_before(timer->timer.expires, now)) {
+		pr_debug("Starting Checkentry timer (Expired, Jiffies): %lu, %lu\n",
+				timer->timer.expires, now);
+
+		/* Stores the uid resposible for waking up the radio */
+		if (skb && (skb->sk)) {
+			timer->uid = from_kuid_munged(current_user_ns(),
+						sock_i_uid(skb->sk));
+		}
+
+		/* checks if there is a pending inactive notification*/
+		if (timer->work_pending)
+			timer->delayed_timer_trigger = timer->last_modified_timer;
+		else {
+			timer->work_pending = true;
+			schedule_work(&timer->work);
+		}
+	}
+
+	get_monotonic_boottime(&timer->last_modified_timer);
+	mod_timer(&timer->timer,
+			msecs_to_jiffies(info->timeout * 1000) + now);
+	spin_unlock_bh(&timestamp_lock);
+}
+
 /*
  * The actual xt_tables plugin.
  */
@@ -168,15 +379,23 @@ static unsigned int idletimer_tg_target(struct sk_buff *skb,
 					 const struct xt_action_param *par)
 {
 	const struct idletimer_tg_info *info = par->targinfo;
+	unsigned long now = jiffies;
 
 	pr_debug("resetting timer %s, timeout period %u\n",
 		 info->label, info->timeout);
 
 	BUG_ON(!info->timer);
 
-	mod_timer(&info->timer->timer,
-		  msecs_to_jiffies(info->timeout * 1000) + jiffies);
+	info->timer->active = true;
 
+	if (time_before(info->timer->timer.expires, now)) {
+		schedule_work(&info->timer->work);
+		pr_debug("Starting timer %s (Expired, Jiffies): %lu, %lu\n",
+			 info->label, info->timer->timer.expires, now);
+	}
+
+	/* TODO: Avoid modifying timers on each packet */
+	reset_timer(info, skb);
 	return XT_CONTINUE;
 }
 
@@ -185,7 +404,7 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par)
 	struct idletimer_tg_info *info = par->targinfo;
 	int ret;
 
-	pr_debug("checkentry targinfo%s\n", info->label);
+	pr_debug("checkentry targinfo %s\n", info->label);
 
 	if (info->timeout == 0) {
 		pr_debug("timeout value is zero\n");
@@ -204,9 +423,7 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par)
 	info->timer = __idletimer_tg_find_by_label(info->label);
 	if (info->timer) {
 		info->timer->refcnt++;
-		mod_timer(&info->timer->timer,
-			  msecs_to_jiffies(info->timeout * 1000) + jiffies);
-
+		reset_timer(info, NULL);
 		pr_debug("increased refcnt of timer %s to %u\n",
 			 info->label, info->timer->refcnt);
 	} else {
@@ -219,6 +436,7 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par)
 	}
 
 	mutex_unlock(&list_mutex);
+
 	return 0;
 }
 
@@ -236,11 +454,12 @@ static void idletimer_tg_destroy(const struct xt_tgdtor_param *par)
 		list_del(&info->timer->entry);
 		del_timer_sync(&info->timer->timer);
 		sysfs_remove_file(idletimer_tg_kobj, &info->timer->attr.attr);
+		unregister_pm_notifier(&info->timer->pm_nb);
 		kfree(info->timer->attr.attr.name);
 		kfree(info->timer);
 	} else {
 		pr_debug("decreased refcnt of timer %s to %u\n",
-			 info->label, info->timer->refcnt);
+		info->label, info->timer->refcnt);
 	}
 
 	mutex_unlock(&list_mutex);
@@ -248,6 +467,7 @@ static void idletimer_tg_destroy(const struct xt_tgdtor_param *par)
 
 static struct xt_target idletimer_tg __read_mostly = {
 	.name		= "IDLETIMER",
+	.revision	= 1,
 	.family		= NFPROTO_UNSPEC,
 	.target		= idletimer_tg_target,
 	.targetsize     = sizeof(struct idletimer_tg_info),
@@ -313,3 +533,4 @@ MODULE_DESCRIPTION("Xtables: idle time monitor");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("ipt_IDLETIMER");
 MODULE_ALIAS("ip6t_IDLETIMER");
+MODULE_ALIAS("arpt_IDLETIMER");
diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c
index 7198d660b4d..a1d126f2946 100644
--- a/net/netfilter/xt_cgroup.c
+++ b/net/netfilter/xt_cgroup.c
@@ -39,7 +39,7 @@ cgroup_mt(const struct sk_buff *skb, struct xt_action_param *par)
 {
 	const struct xt_cgroup_info *info = par->matchinfo;
 
-	if (skb->sk == NULL)
+	if (skb->sk == NULL || !sk_fullsock(skb->sk))
 		return false;
 
 	return (info->id == skb->sk->sk_classid) ^ info->invert;
diff --git a/net/netfilter/xt_qtaguid.c b/net/netfilter/xt_qtaguid.c
new file mode 100644
index 00000000000..87603f69eab
--- /dev/null
+++ b/net/netfilter/xt_qtaguid.c
@@ -0,0 +1,3033 @@
+/*
+ * Kernel iptables module to track stats for packets based on user tags.
+ *
+ * (C) 2011 Google, Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * There are run-time debug flags enabled via the debug_mask module param, or
+ * via the DEFAULT_DEBUG_MASK. See xt_qtaguid_internal.h.
+ */
+#define DEBUG
+
+#include <linux/file.h>
+#include <linux/inetdevice.h>
+#include <linux/module.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_qtaguid.h>
+#include <linux/ratelimit.h>
+#include <linux/seq_file.h>
+#include <linux/skbuff.h>
+#include <linux/workqueue.h>
+#include <net/addrconf.h>
+#include <net/sock.h>
+#include <net/tcp.h>
+#include <net/udp.h>
+
+#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#endif
+
+#include <linux/netfilter/xt_socket.h>
+#include "xt_qtaguid_internal.h"
+#include "xt_qtaguid_print.h"
+#include "../../fs/proc/internal.h"
+
+/*
+ * We only use the xt_socket funcs within a similar context to avoid unexpected
+ * return values.
+ */
+#define XT_SOCKET_SUPPORTED_HOOKS \
+	((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN))
+
+
+static const char *module_procdirname = "xt_qtaguid";
+static struct proc_dir_entry *xt_qtaguid_procdir;
+
+static unsigned int proc_iface_perms = S_IRUGO;
+module_param_named(iface_perms, proc_iface_perms, uint, S_IRUGO | S_IWUSR);
+
+static struct proc_dir_entry *xt_qtaguid_stats_file;
+static unsigned int proc_stats_perms = S_IRUGO;
+module_param_named(stats_perms, proc_stats_perms, uint, S_IRUGO | S_IWUSR);
+
+static struct proc_dir_entry *xt_qtaguid_ctrl_file;
+
+/* Everybody can write. But proc_ctrl_write_limited is true by default which
+ * limits what can be controlled. See the can_*() functions.
+ */
+static unsigned int proc_ctrl_perms = S_IRUGO | S_IWUGO;
+module_param_named(ctrl_perms, proc_ctrl_perms, uint, S_IRUGO | S_IWUSR);
+
+/* Limited by default, so the gid of the ctrl and stats proc entries
+ * will limit what can be done. See the can_*() functions.
+ */
+static bool proc_stats_readall_limited = true;
+static bool proc_ctrl_write_limited = true;
+
+module_param_named(stats_readall_limited, proc_stats_readall_limited, bool,
+		   S_IRUGO | S_IWUSR);
+module_param_named(ctrl_write_limited, proc_ctrl_write_limited, bool,
+		   S_IRUGO | S_IWUSR);
+
+/*
+ * Limit the number of active tags (via socket tags) for a given UID.
+ * Multiple processes could share the UID.
+ */
+static int max_sock_tags = DEFAULT_MAX_SOCK_TAGS;
+module_param(max_sock_tags, int, S_IRUGO | S_IWUSR);
+
+/*
+ * After the kernel has initiallized this module, it is still possible
+ * to make it passive.
+ * Setting passive to Y:
+ *  - the iface stats handling will not act on notifications.
+ *  - iptables matches will never match.
+ *  - ctrl commands silently succeed.
+ *  - stats are always empty.
+ * This is mostly usefull when a bug is suspected.
+ */
+static bool module_passive;
+module_param_named(passive, module_passive, bool, S_IRUGO | S_IWUSR);
+
+/*
+ * Control how qtaguid data is tracked per proc/uid.
+ * Setting tag_tracking_passive to Y:
+ *  - don't create proc specific structs to track tags
+ *  - don't check that active tag stats exceed some limits.
+ *  - don't clean up socket tags on process exits.
+ * This is mostly usefull when a bug is suspected.
+ */
+static bool qtu_proc_handling_passive;
+module_param_named(tag_tracking_passive, qtu_proc_handling_passive, bool,
+		   S_IRUGO | S_IWUSR);
+
+#define QTU_DEV_NAME "xt_qtaguid"
+
+uint qtaguid_debug_mask = DEFAULT_DEBUG_MASK;
+module_param_named(debug_mask, qtaguid_debug_mask, uint, S_IRUGO | S_IWUSR);
+
+/*---------------------------------------------------------------------------*/
+static const char *iface_stat_procdirname = "iface_stat";
+static struct proc_dir_entry *iface_stat_procdir;
+/*
+ * The iface_stat_all* will go away once userspace gets use to the new fields
+ * that have a format line.
+ */
+static const char *iface_stat_all_procfilename = "iface_stat_all";
+static struct proc_dir_entry *iface_stat_all_procfile;
+static const char *iface_stat_fmt_procfilename = "iface_stat_fmt";
+static struct proc_dir_entry *iface_stat_fmt_procfile;
+
+
+static LIST_HEAD(iface_stat_list);
+static DEFINE_SPINLOCK(iface_stat_list_lock);
+
+static struct rb_root sock_tag_tree = RB_ROOT;
+static DEFINE_SPINLOCK(sock_tag_list_lock);
+
+static struct rb_root tag_counter_set_tree = RB_ROOT;
+static DEFINE_SPINLOCK(tag_counter_set_list_lock);
+
+static struct rb_root uid_tag_data_tree = RB_ROOT;
+static DEFINE_SPINLOCK(uid_tag_data_tree_lock);
+
+static struct rb_root proc_qtu_data_tree = RB_ROOT;
+/* No proc_qtu_data_tree_lock; use uid_tag_data_tree_lock */
+
+static struct qtaguid_event_counts qtu_events;
+/*----------------------------------------------*/
+static bool can_manipulate_uids(void)
+{
+	/* root pwnd */
+	return in_egroup_p(xt_qtaguid_ctrl_file->gid)
+		|| unlikely(!from_kuid(&init_user_ns, current_fsuid())) || unlikely(!proc_ctrl_write_limited)
+		|| unlikely(uid_eq(current_fsuid(), xt_qtaguid_ctrl_file->uid));
+}
+
+static bool can_impersonate_uid(kuid_t uid)
+{
+	return uid_eq(uid, current_fsuid()) || can_manipulate_uids();
+}
+
+static bool can_read_other_uid_stats(kuid_t uid)
+{
+	/* root pwnd */
+	return in_egroup_p(xt_qtaguid_stats_file->gid)
+		|| unlikely(!from_kuid(&init_user_ns, current_fsuid())) || uid_eq(uid, current_fsuid())
+		|| unlikely(!proc_stats_readall_limited)
+		|| unlikely(uid_eq(current_fsuid(), xt_qtaguid_ctrl_file->uid));
+}
+
+static inline void dc_add_byte_packets(struct data_counters *counters, int set,
+				  enum ifs_tx_rx direction,
+				  enum ifs_proto ifs_proto,
+				  int bytes,
+				  int packets)
+{
+	counters->bpc[set][direction][ifs_proto].bytes += bytes;
+	counters->bpc[set][direction][ifs_proto].packets += packets;
+}
+
+static struct tag_node *tag_node_tree_search(struct rb_root *root, tag_t tag)
+{
+	struct rb_node *node = root->rb_node;
+
+	while (node) {
+		struct tag_node *data = rb_entry(node, struct tag_node, node);
+		int result;
+		RB_DEBUG("qtaguid: tag_node_tree_search(0x%llx): "
+			 " node=%p data=%p\n", tag, node, data);
+		result = tag_compare(tag, data->tag);
+		RB_DEBUG("qtaguid: tag_node_tree_search(0x%llx): "
+			 " data.tag=0x%llx (uid=%u) res=%d\n",
+			 tag, data->tag, get_uid_from_tag(data->tag), result);
+		if (result < 0)
+			node = node->rb_left;
+		else if (result > 0)
+			node = node->rb_right;
+		else
+			return data;
+	}
+	return NULL;
+}
+
+static void tag_node_tree_insert(struct tag_node *data, struct rb_root *root)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+	/* Figure out where to put new node */
+	while (*new) {
+		struct tag_node *this = rb_entry(*new, struct tag_node,
+						 node);
+		int result = tag_compare(data->tag, this->tag);
+		RB_DEBUG("qtaguid: %s(): tag=0x%llx"
+			 " (uid=%u)\n", __func__,
+			 this->tag,
+			 get_uid_from_tag(this->tag));
+		parent = *new;
+		if (result < 0)
+			new = &((*new)->rb_left);
+		else if (result > 0)
+			new = &((*new)->rb_right);
+		else
+			BUG();
+	}
+
+	/* Add new node and rebalance tree. */
+	rb_link_node(&data->node, parent, new);
+	rb_insert_color(&data->node, root);
+}
+
+static void tag_stat_tree_insert(struct tag_stat *data, struct rb_root *root)
+{
+	tag_node_tree_insert(&data->tn, root);
+}
+
+static struct tag_stat *tag_stat_tree_search(struct rb_root *root, tag_t tag)
+{
+	struct tag_node *node = tag_node_tree_search(root, tag);
+	if (!node)
+		return NULL;
+	return rb_entry(&node->node, struct tag_stat, tn.node);
+}
+
+static void tag_counter_set_tree_insert(struct tag_counter_set *data,
+					struct rb_root *root)
+{
+	tag_node_tree_insert(&data->tn, root);
+}
+
+static struct tag_counter_set *tag_counter_set_tree_search(struct rb_root *root,
+							   tag_t tag)
+{
+	struct tag_node *node = tag_node_tree_search(root, tag);
+	if (!node)
+		return NULL;
+	return rb_entry(&node->node, struct tag_counter_set, tn.node);
+
+}
+
+static void tag_ref_tree_insert(struct tag_ref *data, struct rb_root *root)
+{
+	tag_node_tree_insert(&data->tn, root);
+}
+
+static struct tag_ref *tag_ref_tree_search(struct rb_root *root, tag_t tag)
+{
+	struct tag_node *node = tag_node_tree_search(root, tag);
+	if (!node)
+		return NULL;
+	return rb_entry(&node->node, struct tag_ref, tn.node);
+}
+
+static struct sock_tag *sock_tag_tree_search(struct rb_root *root,
+					     const struct sock *sk)
+{
+	struct rb_node *node = root->rb_node;
+
+	while (node) {
+		struct sock_tag *data = rb_entry(node, struct sock_tag,
+						 sock_node);
+		if (sk < data->sk)
+			node = node->rb_left;
+		else if (sk > data->sk)
+			node = node->rb_right;
+		else
+			return data;
+	}
+	return NULL;
+}
+
+static void sock_tag_tree_insert(struct sock_tag *data, struct rb_root *root)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+	/* Figure out where to put new node */
+	while (*new) {
+		struct sock_tag *this = rb_entry(*new, struct sock_tag,
+						 sock_node);
+		parent = *new;
+		if (data->sk < this->sk)
+			new = &((*new)->rb_left);
+		else if (data->sk > this->sk)
+			new = &((*new)->rb_right);
+		else
+			BUG();
+	}
+
+	/* Add new node and rebalance tree. */
+	rb_link_node(&data->sock_node, parent, new);
+	rb_insert_color(&data->sock_node, root);
+}
+
+static void sock_tag_tree_erase(struct rb_root *st_to_free_tree)
+{
+	struct rb_node *node;
+	struct sock_tag *st_entry;
+
+	node = rb_first(st_to_free_tree);
+	while (node) {
+		st_entry = rb_entry(node, struct sock_tag, sock_node);
+		node = rb_next(node);
+		CT_DEBUG("qtaguid: %s(): "
+			 "erase st: sk=%p tag=0x%llx (uid=%u)\n", __func__,
+			 st_entry->sk,
+			 st_entry->tag,
+			 get_uid_from_tag(st_entry->tag));
+		rb_erase(&st_entry->sock_node, st_to_free_tree);
+		sockfd_put(st_entry->socket);
+		kfree(st_entry);
+	}
+}
+
+static struct proc_qtu_data *proc_qtu_data_tree_search(struct rb_root *root,
+						       const pid_t pid)
+{
+	struct rb_node *node = root->rb_node;
+
+	while (node) {
+		struct proc_qtu_data *data = rb_entry(node,
+						      struct proc_qtu_data,
+						      node);
+		if (pid < data->pid)
+			node = node->rb_left;
+		else if (pid > data->pid)
+			node = node->rb_right;
+		else
+			return data;
+	}
+	return NULL;
+}
+
+static void proc_qtu_data_tree_insert(struct proc_qtu_data *data,
+				      struct rb_root *root)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+	/* Figure out where to put new node */
+	while (*new) {
+		struct proc_qtu_data *this = rb_entry(*new,
+						      struct proc_qtu_data,
+						      node);
+		parent = *new;
+		if (data->pid < this->pid)
+			new = &((*new)->rb_left);
+		else if (data->pid > this->pid)
+			new = &((*new)->rb_right);
+		else
+			BUG();
+	}
+
+	/* Add new node and rebalance tree. */
+	rb_link_node(&data->node, parent, new);
+	rb_insert_color(&data->node, root);
+}
+
+static void uid_tag_data_tree_insert(struct uid_tag_data *data,
+				     struct rb_root *root)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+	/* Figure out where to put new node */
+	while (*new) {
+		struct uid_tag_data *this = rb_entry(*new,
+						     struct uid_tag_data,
+						     node);
+		parent = *new;
+		if (data->uid < this->uid)
+			new = &((*new)->rb_left);
+		else if (data->uid > this->uid)
+			new = &((*new)->rb_right);
+		else
+			BUG();
+	}
+
+	/* Add new node and rebalance tree. */
+	rb_link_node(&data->node, parent, new);
+	rb_insert_color(&data->node, root);
+}
+
+static struct uid_tag_data *uid_tag_data_tree_search(struct rb_root *root,
+						     uid_t uid)
+{
+	struct rb_node *node = root->rb_node;
+
+	while (node) {
+		struct uid_tag_data *data = rb_entry(node,
+						     struct uid_tag_data,
+						     node);
+		if (uid < data->uid)
+			node = node->rb_left;
+		else if (uid > data->uid)
+			node = node->rb_right;
+		else
+			return data;
+	}
+	return NULL;
+}
+
+/*
+ * Allocates a new uid_tag_data struct if needed.
+ * Returns a pointer to the found or allocated uid_tag_data.
+ * Returns a PTR_ERR on failures, and lock is not held.
+ * If found is not NULL:
+ *   sets *found to true if not allocated.
+ *   sets *found to false if allocated.
+ */
+struct uid_tag_data *get_uid_data(uid_t uid, bool *found_res)
+{
+	struct uid_tag_data *utd_entry;
+
+	/* Look for top level uid_tag_data for the UID */
+	utd_entry = uid_tag_data_tree_search(&uid_tag_data_tree, uid);
+	DR_DEBUG("qtaguid: get_uid_data(%u) utd=%p\n", uid, utd_entry);
+
+	if (found_res)
+		*found_res = utd_entry;
+	if (utd_entry)
+		return utd_entry;
+
+	utd_entry = kzalloc(sizeof(*utd_entry), GFP_ATOMIC);
+	if (!utd_entry) {
+		pr_err("qtaguid: get_uid_data(%u): "
+		       "tag data alloc failed\n", uid);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	utd_entry->uid = uid;
+	utd_entry->tag_ref_tree = RB_ROOT;
+	uid_tag_data_tree_insert(utd_entry, &uid_tag_data_tree);
+	DR_DEBUG("qtaguid: get_uid_data(%u) new utd=%p\n", uid, utd_entry);
+	return utd_entry;
+}
+
+/* Never returns NULL. Either PTR_ERR or a valid ptr. */
+static struct tag_ref *new_tag_ref(tag_t new_tag,
+				   struct uid_tag_data *utd_entry)
+{
+	struct tag_ref *tr_entry;
+	int res;
+
+	if (utd_entry->num_active_tags + 1 > max_sock_tags) {
+		pr_info("qtaguid: new_tag_ref(0x%llx): "
+			"tag ref alloc quota exceeded. max=%d\n",
+			new_tag, max_sock_tags);
+		res = -EMFILE;
+		goto err_res;
+
+	}
+
+	tr_entry = kzalloc(sizeof(*tr_entry), GFP_ATOMIC);
+	if (!tr_entry) {
+		pr_err("qtaguid: new_tag_ref(0x%llx): "
+		       "tag ref alloc failed\n",
+		       new_tag);
+		res = -ENOMEM;
+		goto err_res;
+	}
+	tr_entry->tn.tag = new_tag;
+	/* tr_entry->num_sock_tags  handled by caller */
+	utd_entry->num_active_tags++;
+	tag_ref_tree_insert(tr_entry, &utd_entry->tag_ref_tree);
+	DR_DEBUG("qtaguid: new_tag_ref(0x%llx): "
+		 " inserted new tag ref %p\n",
+		 new_tag, tr_entry);
+	return tr_entry;
+
+err_res:
+	return ERR_PTR(res);
+}
+
+static struct tag_ref *lookup_tag_ref(tag_t full_tag,
+				      struct uid_tag_data **utd_res)
+{
+	struct uid_tag_data *utd_entry;
+	struct tag_ref *tr_entry;
+	bool found_utd;
+	uid_t uid = get_uid_from_tag(full_tag);
+
+	DR_DEBUG("qtaguid: lookup_tag_ref(tag=0x%llx (uid=%u))\n",
+		 full_tag, uid);
+
+	utd_entry = get_uid_data(uid, &found_utd);
+	if (IS_ERR_OR_NULL(utd_entry)) {
+		if (utd_res)
+			*utd_res = utd_entry;
+		return NULL;
+	}
+
+	tr_entry = tag_ref_tree_search(&utd_entry->tag_ref_tree, full_tag);
+	if (utd_res)
+		*utd_res = utd_entry;
+	DR_DEBUG("qtaguid: lookup_tag_ref(0x%llx) utd_entry=%p tr_entry=%p\n",
+		 full_tag, utd_entry, tr_entry);
+	return tr_entry;
+}
+
+/* Never returns NULL. Either PTR_ERR or a valid ptr. */
+static struct tag_ref *get_tag_ref(tag_t full_tag,
+				   struct uid_tag_data **utd_res)
+{
+	struct uid_tag_data *utd_entry;
+	struct tag_ref *tr_entry;
+
+	DR_DEBUG("qtaguid: get_tag_ref(0x%llx)\n",
+		 full_tag);
+	spin_lock_bh(&uid_tag_data_tree_lock);
+	tr_entry = lookup_tag_ref(full_tag, &utd_entry);
+	BUG_ON(IS_ERR_OR_NULL(utd_entry));
+	if (!tr_entry)
+		tr_entry = new_tag_ref(full_tag, utd_entry);
+
+	spin_unlock_bh(&uid_tag_data_tree_lock);
+	if (utd_res)
+		*utd_res = utd_entry;
+	DR_DEBUG("qtaguid: get_tag_ref(0x%llx) utd=%p tr=%p\n",
+		 full_tag, utd_entry, tr_entry);
+	return tr_entry;
+}
+
+/* Checks and maybe frees the UID Tag Data entry */
+static void put_utd_entry(struct uid_tag_data *utd_entry)
+{
+	/* Are we done with the UID tag data entry? */
+	if (RB_EMPTY_ROOT(&utd_entry->tag_ref_tree) &&
+		!utd_entry->num_pqd) {
+		DR_DEBUG("qtaguid: %s(): "
+			 "erase utd_entry=%p uid=%u "
+			 "by pid=%u tgid=%u uid=%u\n", __func__,
+			 utd_entry, utd_entry->uid,
+			 current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+		BUG_ON(utd_entry->num_active_tags);
+		rb_erase(&utd_entry->node, &uid_tag_data_tree);
+		kfree(utd_entry);
+	} else {
+		DR_DEBUG("qtaguid: %s(): "
+			 "utd_entry=%p still has %d tags %d proc_qtu_data\n",
+			 __func__, utd_entry, utd_entry->num_active_tags,
+			 utd_entry->num_pqd);
+		BUG_ON(!(utd_entry->num_active_tags ||
+			 utd_entry->num_pqd));
+	}
+}
+
+/*
+ * If no sock_tags are using this tag_ref,
+ * decrements refcount of utd_entry, removes tr_entry
+ * from utd_entry->tag_ref_tree and frees.
+ */
+static void free_tag_ref_from_utd_entry(struct tag_ref *tr_entry,
+					struct uid_tag_data *utd_entry)
+{
+	DR_DEBUG("qtaguid: %s(): %p tag=0x%llx (uid=%u)\n", __func__,
+		 tr_entry, tr_entry->tn.tag,
+		 get_uid_from_tag(tr_entry->tn.tag));
+	if (!tr_entry->num_sock_tags) {
+		BUG_ON(!utd_entry->num_active_tags);
+		utd_entry->num_active_tags--;
+		rb_erase(&tr_entry->tn.node, &utd_entry->tag_ref_tree);
+		DR_DEBUG("qtaguid: %s(): erased %p\n", __func__, tr_entry);
+		kfree(tr_entry);
+	}
+}
+
+static void put_tag_ref_tree(tag_t full_tag, struct uid_tag_data *utd_entry)
+{
+	struct rb_node *node;
+	struct tag_ref *tr_entry;
+	tag_t acct_tag;
+
+	DR_DEBUG("qtaguid: %s(tag=0x%llx (uid=%u))\n", __func__,
+		 full_tag, get_uid_from_tag(full_tag));
+	acct_tag = get_atag_from_tag(full_tag);
+	node = rb_first(&utd_entry->tag_ref_tree);
+	while (node) {
+		tr_entry = rb_entry(node, struct tag_ref, tn.node);
+		node = rb_next(node);
+		if (!acct_tag || tr_entry->tn.tag == full_tag)
+			free_tag_ref_from_utd_entry(tr_entry, utd_entry);
+	}
+}
+
+static ssize_t read_proc_u64(struct file *file, char __user *buf,
+			 size_t size, loff_t *ppos)
+{
+	uint64_t *valuep = PDE_DATA(file_inode(file));
+	char tmp[24];
+	size_t tmp_size;
+
+	tmp_size = scnprintf(tmp, sizeof(tmp), "%llu\n", *valuep);
+	return simple_read_from_buffer(buf, size, ppos, tmp, tmp_size);
+}
+
+static ssize_t read_proc_bool(struct file *file, char __user *buf,
+			  size_t size, loff_t *ppos)
+{
+	bool *valuep = PDE_DATA(file_inode(file));
+	char tmp[24];
+	size_t tmp_size;
+
+	tmp_size = scnprintf(tmp, sizeof(tmp), "%u\n", *valuep);
+	return simple_read_from_buffer(buf, size, ppos, tmp, tmp_size);
+}
+
+static int get_active_counter_set(tag_t tag)
+{
+	int active_set = 0;
+	struct tag_counter_set *tcs;
+
+	MT_DEBUG("qtaguid: get_active_counter_set(tag=0x%llx)"
+		 " (uid=%u)\n",
+		 tag, get_uid_from_tag(tag));
+	/* For now we only handle UID tags for active sets */
+	tag = get_utag_from_tag(tag);
+	spin_lock_bh(&tag_counter_set_list_lock);
+	tcs = tag_counter_set_tree_search(&tag_counter_set_tree, tag);
+	if (tcs)
+		active_set = tcs->active_set;
+	spin_unlock_bh(&tag_counter_set_list_lock);
+	return active_set;
+}
+
+/*
+ * Find the entry for tracking the specified interface.
+ * Caller must hold iface_stat_list_lock
+ */
+static struct iface_stat *get_iface_entry(const char *ifname)
+{
+	struct iface_stat *iface_entry;
+
+	/* Find the entry for tracking the specified tag within the interface */
+	if (ifname == NULL) {
+		pr_info("qtaguid: iface_stat: get() NULL device name\n");
+		return NULL;
+	}
+
+	/* Iterate over interfaces */
+	list_for_each_entry(iface_entry, &iface_stat_list, list) {
+		if (!strcmp(ifname, iface_entry->ifname))
+			goto done;
+	}
+	iface_entry = NULL;
+done:
+	return iface_entry;
+}
+
+/* This is for fmt2 only */
+static void pp_iface_stat_header(struct seq_file *m)
+{
+	seq_puts(m,
+		 "ifname "
+		 "total_skb_rx_bytes total_skb_rx_packets "
+		 "total_skb_tx_bytes total_skb_tx_packets "
+		 "rx_tcp_bytes rx_tcp_packets "
+		 "rx_udp_bytes rx_udp_packets "
+		 "rx_other_bytes rx_other_packets "
+		 "tx_tcp_bytes tx_tcp_packets "
+		 "tx_udp_bytes tx_udp_packets "
+		 "tx_other_bytes tx_other_packets\n"
+	);
+}
+
+static void pp_iface_stat_line(struct seq_file *m,
+			       struct iface_stat *iface_entry)
+{
+	struct data_counters *cnts;
+	int cnt_set = 0;   /* We only use one set for the device */
+	cnts = &iface_entry->totals_via_skb;
+	seq_printf(m, "%s %llu %llu %llu %llu %llu %llu %llu %llu "
+		   "%llu %llu %llu %llu %llu %llu %llu %llu\n",
+		   iface_entry->ifname,
+		   dc_sum_bytes(cnts, cnt_set, IFS_RX),
+		   dc_sum_packets(cnts, cnt_set, IFS_RX),
+		   dc_sum_bytes(cnts, cnt_set, IFS_TX),
+		   dc_sum_packets(cnts, cnt_set, IFS_TX),
+		   cnts->bpc[cnt_set][IFS_RX][IFS_TCP].bytes,
+		   cnts->bpc[cnt_set][IFS_RX][IFS_TCP].packets,
+		   cnts->bpc[cnt_set][IFS_RX][IFS_UDP].bytes,
+		   cnts->bpc[cnt_set][IFS_RX][IFS_UDP].packets,
+		   cnts->bpc[cnt_set][IFS_RX][IFS_PROTO_OTHER].bytes,
+		   cnts->bpc[cnt_set][IFS_RX][IFS_PROTO_OTHER].packets,
+		   cnts->bpc[cnt_set][IFS_TX][IFS_TCP].bytes,
+		   cnts->bpc[cnt_set][IFS_TX][IFS_TCP].packets,
+		   cnts->bpc[cnt_set][IFS_TX][IFS_UDP].bytes,
+		   cnts->bpc[cnt_set][IFS_TX][IFS_UDP].packets,
+		   cnts->bpc[cnt_set][IFS_TX][IFS_PROTO_OTHER].bytes,
+		   cnts->bpc[cnt_set][IFS_TX][IFS_PROTO_OTHER].packets);
+}
+
+struct proc_iface_stat_fmt_info {
+	int fmt;
+};
+
+static void *iface_stat_fmt_proc_start(struct seq_file *m, loff_t *pos)
+{
+	struct proc_iface_stat_fmt_info *p = m->private;
+	loff_t n = *pos;
+
+	/*
+	 * This lock will prevent iface_stat_update() from changing active,
+	 * and in turn prevent an interface from unregistering itself.
+	 */
+	spin_lock_bh(&iface_stat_list_lock);
+
+	if (unlikely(module_passive))
+		return NULL;
+
+	if (!n && p->fmt == 2)
+		pp_iface_stat_header(m);
+
+	return seq_list_start(&iface_stat_list, n);
+}
+
+static void *iface_stat_fmt_proc_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	return seq_list_next(p, &iface_stat_list, pos);
+}
+
+static void iface_stat_fmt_proc_stop(struct seq_file *m, void *p)
+{
+	spin_unlock_bh(&iface_stat_list_lock);
+}
+
+static int iface_stat_fmt_proc_show(struct seq_file *m, void *v)
+{
+	struct proc_iface_stat_fmt_info *p = m->private;
+	struct iface_stat *iface_entry;
+	struct rtnl_link_stats64 dev_stats, *stats;
+	struct rtnl_link_stats64 no_dev_stats = {0};
+
+
+	CT_DEBUG("qtaguid:proc iface_stat_fmt pid=%u tgid=%u uid=%u\n",
+		 current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+
+	iface_entry = list_entry(v, struct iface_stat, list);
+
+	if (iface_entry->active) {
+		stats = dev_get_stats(iface_entry->net_dev,
+				      &dev_stats);
+	} else {
+		stats = &no_dev_stats;
+	}
+	/*
+	 * If the meaning of the data changes, then update the fmtX
+	 * string.
+	 */
+	if (p->fmt == 1) {
+		seq_printf(m, "%s %d %llu %llu %llu %llu %llu %llu %llu %llu\n",
+			   iface_entry->ifname,
+			   iface_entry->active,
+			   iface_entry->totals_via_dev[IFS_RX].bytes,
+			   iface_entry->totals_via_dev[IFS_RX].packets,
+			   iface_entry->totals_via_dev[IFS_TX].bytes,
+			   iface_entry->totals_via_dev[IFS_TX].packets,
+			   stats->rx_bytes, stats->rx_packets,
+			   stats->tx_bytes, stats->tx_packets
+			   );
+	} else {
+		pp_iface_stat_line(m, iface_entry);
+	}
+	return 0;
+}
+
+static const struct file_operations read_u64_fops = {
+	.read		= read_proc_u64,
+	.llseek		= default_llseek,
+};
+
+static const struct file_operations read_bool_fops = {
+	.read		= read_proc_bool,
+	.llseek		= default_llseek,
+};
+
+static void iface_create_proc_worker(struct work_struct *work)
+{
+	struct proc_dir_entry *proc_entry;
+	struct iface_stat_work *isw = container_of(work, struct iface_stat_work,
+						   iface_work);
+	struct iface_stat *new_iface  = isw->iface_entry;
+
+	/* iface_entries are not deleted, so safe to manipulate. */
+	proc_entry = proc_mkdir(new_iface->ifname, iface_stat_procdir);
+	if (IS_ERR_OR_NULL(proc_entry)) {
+		pr_err("qtaguid: iface_stat: create_proc(): alloc failed.\n");
+		kfree(isw);
+		return;
+	}
+
+	new_iface->proc_ptr = proc_entry;
+
+	proc_create_data("tx_bytes", proc_iface_perms, proc_entry,
+			 &read_u64_fops,
+			 &new_iface->totals_via_dev[IFS_TX].bytes);
+	proc_create_data("rx_bytes", proc_iface_perms, proc_entry,
+			 &read_u64_fops,
+			 &new_iface->totals_via_dev[IFS_RX].bytes);
+	proc_create_data("tx_packets", proc_iface_perms, proc_entry,
+			 &read_u64_fops,
+			 &new_iface->totals_via_dev[IFS_TX].packets);
+	proc_create_data("rx_packets", proc_iface_perms, proc_entry,
+			 &read_u64_fops,
+			 &new_iface->totals_via_dev[IFS_RX].packets);
+	proc_create_data("active", proc_iface_perms, proc_entry,
+			 &read_bool_fops, &new_iface->active);
+
+	IF_DEBUG("qtaguid: iface_stat: create_proc(): done "
+		 "entry=%p dev=%s\n", new_iface, new_iface->ifname);
+	kfree(isw);
+}
+
+/*
+ * Will set the entry's active state, and
+ * update the net_dev accordingly also.
+ */
+static void _iface_stat_set_active(struct iface_stat *entry,
+				   struct net_device *net_dev,
+				   bool activate)
+{
+	if (activate) {
+		entry->net_dev = net_dev;
+		entry->active = true;
+		IF_DEBUG("qtaguid: %s(%s): "
+			 "enable tracking. rfcnt=%d\n", __func__,
+			 entry->ifname,
+			 __this_cpu_read(*net_dev->pcpu_refcnt));
+	} else {
+		entry->active = false;
+		entry->net_dev = NULL;
+		IF_DEBUG("qtaguid: %s(%s): "
+			 "disable tracking. rfcnt=%d\n", __func__,
+			 entry->ifname,
+			 __this_cpu_read(*net_dev->pcpu_refcnt));
+
+	}
+}
+
+/* Caller must hold iface_stat_list_lock */
+static struct iface_stat *iface_alloc(struct net_device *net_dev)
+{
+	struct iface_stat *new_iface;
+	struct iface_stat_work *isw;
+
+	new_iface = kzalloc(sizeof(*new_iface), GFP_ATOMIC);
+	if (new_iface == NULL) {
+		pr_err("qtaguid: iface_stat: create(%s): "
+		       "iface_stat alloc failed\n", net_dev->name);
+		return NULL;
+	}
+	new_iface->ifname = kstrdup(net_dev->name, GFP_ATOMIC);
+	if (new_iface->ifname == NULL) {
+		pr_err("qtaguid: iface_stat: create(%s): "
+		       "ifname alloc failed\n", net_dev->name);
+		kfree(new_iface);
+		return NULL;
+	}
+	spin_lock_init(&new_iface->tag_stat_list_lock);
+	new_iface->tag_stat_tree = RB_ROOT;
+	_iface_stat_set_active(new_iface, net_dev, true);
+
+	/*
+	 * ipv6 notifier chains are atomic :(
+	 * No create_proc_read_entry() for you!
+	 */
+	isw = kmalloc(sizeof(*isw), GFP_ATOMIC);
+	if (!isw) {
+		pr_err("qtaguid: iface_stat: create(%s): "
+		       "work alloc failed\n", new_iface->ifname);
+		_iface_stat_set_active(new_iface, net_dev, false);
+		kfree(new_iface->ifname);
+		kfree(new_iface);
+		return NULL;
+	}
+	isw->iface_entry = new_iface;
+	INIT_WORK(&isw->iface_work, iface_create_proc_worker);
+	schedule_work(&isw->iface_work);
+	list_add(&new_iface->list, &iface_stat_list);
+	return new_iface;
+}
+
+static void iface_check_stats_reset_and_adjust(struct net_device *net_dev,
+					       struct iface_stat *iface)
+{
+	struct rtnl_link_stats64 dev_stats, *stats;
+	bool stats_rewound;
+
+	stats = dev_get_stats(net_dev, &dev_stats);
+	/* No empty packets */
+	stats_rewound =
+		(stats->rx_bytes < iface->last_known[IFS_RX].bytes)
+		|| (stats->tx_bytes < iface->last_known[IFS_TX].bytes);
+
+	IF_DEBUG("qtaguid: %s(%s): iface=%p netdev=%p "
+		 "bytes rx/tx=%llu/%llu "
+		 "active=%d last_known=%d "
+		 "stats_rewound=%d\n", __func__,
+		 net_dev ? net_dev->name : "?",
+		 iface, net_dev,
+		 stats->rx_bytes, stats->tx_bytes,
+		 iface->active, iface->last_known_valid, stats_rewound);
+
+	if (iface->active && iface->last_known_valid && stats_rewound) {
+		pr_warn_once("qtaguid: iface_stat: %s(%s): "
+			     "iface reset its stats unexpectedly\n", __func__,
+			     net_dev->name);
+
+		iface->totals_via_dev[IFS_TX].bytes +=
+			iface->last_known[IFS_TX].bytes;
+		iface->totals_via_dev[IFS_TX].packets +=
+			iface->last_known[IFS_TX].packets;
+		iface->totals_via_dev[IFS_RX].bytes +=
+			iface->last_known[IFS_RX].bytes;
+		iface->totals_via_dev[IFS_RX].packets +=
+			iface->last_known[IFS_RX].packets;
+		iface->last_known_valid = false;
+		IF_DEBUG("qtaguid: %s(%s): iface=%p "
+			 "used last known bytes rx/tx=%llu/%llu\n", __func__,
+			 iface->ifname, iface, iface->last_known[IFS_RX].bytes,
+			 iface->last_known[IFS_TX].bytes);
+	}
+}
+
+/*
+ * Create a new entry for tracking the specified interface.
+ * Do nothing if the entry already exists.
+ * Called when an interface is configured with a valid IP address.
+ */
+static void iface_stat_create(struct net_device *net_dev,
+			      struct in_ifaddr *ifa)
+{
+	struct in_device *in_dev = NULL;
+	const char *ifname;
+	struct iface_stat *entry;
+	__be32 ipaddr = 0;
+	struct iface_stat *new_iface;
+
+	IF_DEBUG("qtaguid: iface_stat: create(%s): ifa=%p netdev=%p\n",
+		 net_dev ? net_dev->name : "?",
+		 ifa, net_dev);
+	if (!net_dev) {
+		pr_err("qtaguid: iface_stat: create(): no net dev\n");
+		return;
+	}
+
+	ifname = net_dev->name;
+	if (!ifa) {
+		in_dev = in_dev_get(net_dev);
+		if (!in_dev) {
+			pr_err("qtaguid: iface_stat: create(%s): no inet dev\n",
+			       ifname);
+			return;
+		}
+		IF_DEBUG("qtaguid: iface_stat: create(%s): in_dev=%p\n",
+			 ifname, in_dev);
+		for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
+			IF_DEBUG("qtaguid: iface_stat: create(%s): "
+				 "ifa=%p ifa_label=%s\n",
+				 ifname, ifa,
+				 ifa->ifa_label ? ifa->ifa_label : "(null)");
+			if (ifa->ifa_label && !strcmp(ifname, ifa->ifa_label))
+				break;
+		}
+	}
+
+	if (!ifa) {
+		IF_DEBUG("qtaguid: iface_stat: create(%s): no matching IP\n",
+			 ifname);
+		goto done_put;
+	}
+	ipaddr = ifa->ifa_local;
+
+	spin_lock_bh(&iface_stat_list_lock);
+	entry = get_iface_entry(ifname);
+	if (entry != NULL) {
+		IF_DEBUG("qtaguid: iface_stat: create(%s): entry=%p\n",
+			 ifname, entry);
+		iface_check_stats_reset_and_adjust(net_dev, entry);
+		_iface_stat_set_active(entry, net_dev, true);
+		IF_DEBUG("qtaguid: %s(%s): "
+			 "tracking now %d on ip=%pI4\n", __func__,
+			 entry->ifname, true, &ipaddr);
+		goto done_unlock_put;
+	}
+
+	new_iface = iface_alloc(net_dev);
+	IF_DEBUG("qtaguid: iface_stat: create(%s): done "
+		 "entry=%p ip=%pI4\n", ifname, new_iface, &ipaddr);
+done_unlock_put:
+	spin_unlock_bh(&iface_stat_list_lock);
+done_put:
+	if (in_dev)
+		in_dev_put(in_dev);
+}
+
+static void iface_stat_create_ipv6(struct net_device *net_dev,
+				   struct inet6_ifaddr *ifa)
+{
+	struct in_device *in_dev;
+	const char *ifname;
+	struct iface_stat *entry;
+	struct iface_stat *new_iface;
+	int addr_type;
+
+	IF_DEBUG("qtaguid: iface_stat: create6(): ifa=%p netdev=%p->name=%s\n",
+		 ifa, net_dev, net_dev ? net_dev->name : "");
+	if (!net_dev) {
+		pr_err("qtaguid: iface_stat: create6(): no net dev!\n");
+		return;
+	}
+	ifname = net_dev->name;
+
+	in_dev = in_dev_get(net_dev);
+	if (!in_dev) {
+		pr_err("qtaguid: iface_stat: create6(%s): no inet dev\n",
+		       ifname);
+		return;
+	}
+
+	IF_DEBUG("qtaguid: iface_stat: create6(%s): in_dev=%p\n",
+		 ifname, in_dev);
+
+	if (!ifa) {
+		IF_DEBUG("qtaguid: iface_stat: create6(%s): no matching IP\n",
+			 ifname);
+		goto done_put;
+	}
+	addr_type = ipv6_addr_type(&ifa->addr);
+
+	spin_lock_bh(&iface_stat_list_lock);
+	entry = get_iface_entry(ifname);
+	if (entry != NULL) {
+		IF_DEBUG("qtaguid: %s(%s): entry=%p\n", __func__,
+			 ifname, entry);
+		iface_check_stats_reset_and_adjust(net_dev, entry);
+		_iface_stat_set_active(entry, net_dev, true);
+		IF_DEBUG("qtaguid: %s(%s): "
+			 "tracking now %d on ip=%pI6c\n", __func__,
+			 entry->ifname, true, &ifa->addr);
+		goto done_unlock_put;
+	}
+
+	new_iface = iface_alloc(net_dev);
+	IF_DEBUG("qtaguid: iface_stat: create6(%s): done "
+		 "entry=%p ip=%pI6c\n", ifname, new_iface, &ifa->addr);
+
+done_unlock_put:
+	spin_unlock_bh(&iface_stat_list_lock);
+done_put:
+	in_dev_put(in_dev);
+}
+
+static struct sock_tag *get_sock_stat_nl(const struct sock *sk)
+{
+	MT_DEBUG("qtaguid: get_sock_stat_nl(sk=%p)\n", sk);
+	return sock_tag_tree_search(&sock_tag_tree, sk);
+}
+
+static struct sock_tag *get_sock_stat(const struct sock *sk)
+{
+	struct sock_tag *sock_tag_entry;
+	MT_DEBUG("qtaguid: get_sock_stat(sk=%p)\n", sk);
+	if (!sk)
+		return NULL;
+	spin_lock_bh(&sock_tag_list_lock);
+	sock_tag_entry = get_sock_stat_nl(sk);
+	spin_unlock_bh(&sock_tag_list_lock);
+	return sock_tag_entry;
+}
+
+static int ipx_proto(const struct sk_buff *skb,
+		     struct xt_action_param *par)
+{
+	int thoff = 0, tproto;
+
+	switch (par->family) {
+	case NFPROTO_IPV6:
+		tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
+		if (tproto < 0)
+			MT_DEBUG("%s(): transport header not found in ipv6"
+				 " skb=%p\n", __func__, skb);
+		break;
+	case NFPROTO_IPV4:
+		tproto = ip_hdr(skb)->protocol;
+		break;
+	default:
+		tproto = IPPROTO_RAW;
+	}
+	return tproto;
+}
+
+static void
+data_counters_update(struct data_counters *dc, int set,
+		     enum ifs_tx_rx direction, int proto, int bytes)
+{
+	switch (proto) {
+	case IPPROTO_TCP:
+		dc_add_byte_packets(dc, set, direction, IFS_TCP, bytes, 1);
+		break;
+	case IPPROTO_UDP:
+		dc_add_byte_packets(dc, set, direction, IFS_UDP, bytes, 1);
+		break;
+	case IPPROTO_IP:
+	default:
+		dc_add_byte_packets(dc, set, direction, IFS_PROTO_OTHER, bytes,
+				    1);
+		break;
+	}
+}
+
+/*
+ * Update stats for the specified interface. Do nothing if the entry
+ * does not exist (when a device was never configured with an IP address).
+ * Called when an device is being unregistered.
+ */
+static void iface_stat_update(struct net_device *net_dev, bool stash_only)
+{
+	struct rtnl_link_stats64 dev_stats, *stats;
+	struct iface_stat *entry;
+
+	stats = dev_get_stats(net_dev, &dev_stats);
+	spin_lock_bh(&iface_stat_list_lock);
+	entry = get_iface_entry(net_dev->name);
+	if (entry == NULL) {
+		IF_DEBUG("qtaguid: iface_stat: update(%s): not tracked\n",
+			 net_dev->name);
+		spin_unlock_bh(&iface_stat_list_lock);
+		return;
+	}
+
+	IF_DEBUG("qtaguid: %s(%s): entry=%p\n", __func__,
+		 net_dev->name, entry);
+	if (!entry->active) {
+		IF_DEBUG("qtaguid: %s(%s): already disabled\n", __func__,
+			 net_dev->name);
+		spin_unlock_bh(&iface_stat_list_lock);
+		return;
+	}
+
+	if (stash_only) {
+		entry->last_known[IFS_TX].bytes = stats->tx_bytes;
+		entry->last_known[IFS_TX].packets = stats->tx_packets;
+		entry->last_known[IFS_RX].bytes = stats->rx_bytes;
+		entry->last_known[IFS_RX].packets = stats->rx_packets;
+		entry->last_known_valid = true;
+		IF_DEBUG("qtaguid: %s(%s): "
+			 "dev stats stashed rx/tx=%llu/%llu\n", __func__,
+			 net_dev->name, stats->rx_bytes, stats->tx_bytes);
+		spin_unlock_bh(&iface_stat_list_lock);
+		return;
+	}
+	entry->totals_via_dev[IFS_TX].bytes += stats->tx_bytes;
+	entry->totals_via_dev[IFS_TX].packets += stats->tx_packets;
+	entry->totals_via_dev[IFS_RX].bytes += stats->rx_bytes;
+	entry->totals_via_dev[IFS_RX].packets += stats->rx_packets;
+	/* We don't need the last_known[] anymore */
+	entry->last_known_valid = false;
+	_iface_stat_set_active(entry, net_dev, false);
+	IF_DEBUG("qtaguid: %s(%s): "
+		 "disable tracking. rx/tx=%llu/%llu\n", __func__,
+		 net_dev->name, stats->rx_bytes, stats->tx_bytes);
+	spin_unlock_bh(&iface_stat_list_lock);
+}
+
+/*
+ * Update stats for the specified interface from the skb.
+ * Do nothing if the entry
+ * does not exist (when a device was never configured with an IP address).
+ * Called on each sk.
+ */
+static void iface_stat_update_from_skb(const struct sk_buff *skb,
+				       struct xt_action_param *par)
+{
+	struct iface_stat *entry;
+	const struct net_device *el_dev;
+	enum ifs_tx_rx direction = par->in ? IFS_RX : IFS_TX;
+	int bytes = skb->len;
+	int proto;
+
+	if (!skb->dev) {
+		MT_DEBUG("qtaguid[%d]: no skb->dev\n", par->hooknum);
+		el_dev = par->in ? : par->out;
+	} else {
+		const struct net_device *other_dev;
+		el_dev = skb->dev;
+		other_dev = par->in ? : par->out;
+		if (el_dev != other_dev) {
+			MT_DEBUG("qtaguid[%d]: skb->dev=%p %s vs "
+				 "par->(in/out)=%p %s\n",
+				 par->hooknum, el_dev, el_dev->name, other_dev,
+				 other_dev->name);
+		}
+	}
+
+	if (unlikely(!el_dev)) {
+		pr_err_ratelimited("qtaguid[%d]: %s(): no par->in/out?!!\n",
+				   par->hooknum, __func__);
+		BUG();
+	} else if (unlikely(!el_dev->name)) {
+		pr_err_ratelimited("qtaguid[%d]: %s(): no dev->name?!!\n",
+				   par->hooknum, __func__);
+		BUG();
+	} else {
+		proto = ipx_proto(skb, par);
+		MT_DEBUG("qtaguid[%d]: dev name=%s type=%d fam=%d proto=%d\n",
+			 par->hooknum, el_dev->name, el_dev->type,
+			 par->family, proto);
+	}
+
+	spin_lock_bh(&iface_stat_list_lock);
+	entry = get_iface_entry(el_dev->name);
+	if (entry == NULL) {
+		IF_DEBUG("qtaguid: iface_stat: %s(%s): not tracked\n",
+			 __func__, el_dev->name);
+		spin_unlock_bh(&iface_stat_list_lock);
+		return;
+	}
+
+	IF_DEBUG("qtaguid: %s(%s): entry=%p\n", __func__,
+		 el_dev->name, entry);
+
+	data_counters_update(&entry->totals_via_skb, 0, direction, proto,
+			     bytes);
+	spin_unlock_bh(&iface_stat_list_lock);
+}
+
+static void tag_stat_update(struct tag_stat *tag_entry,
+			enum ifs_tx_rx direction, int proto, int bytes)
+{
+	int active_set;
+	active_set = get_active_counter_set(tag_entry->tn.tag);
+	MT_DEBUG("qtaguid: tag_stat_update(tag=0x%llx (uid=%u) set=%d "
+		 "dir=%d proto=%d bytes=%d)\n",
+		 tag_entry->tn.tag, get_uid_from_tag(tag_entry->tn.tag),
+		 active_set, direction, proto, bytes);
+	data_counters_update(&tag_entry->counters, active_set, direction,
+			     proto, bytes);
+	if (tag_entry->parent_counters)
+		data_counters_update(tag_entry->parent_counters, active_set,
+				     direction, proto, bytes);
+}
+
+/*
+ * Create a new entry for tracking the specified {acct_tag,uid_tag} within
+ * the interface.
+ * iface_entry->tag_stat_list_lock should be held.
+ */
+static struct tag_stat *create_if_tag_stat(struct iface_stat *iface_entry,
+					   tag_t tag)
+{
+	struct tag_stat *new_tag_stat_entry = NULL;
+	IF_DEBUG("qtaguid: iface_stat: %s(): ife=%p tag=0x%llx"
+		 " (uid=%u)\n", __func__,
+		 iface_entry, tag, get_uid_from_tag(tag));
+	new_tag_stat_entry = kzalloc(sizeof(*new_tag_stat_entry), GFP_ATOMIC);
+	if (!new_tag_stat_entry) {
+		pr_err("qtaguid: iface_stat: tag stat alloc failed\n");
+		goto done;
+	}
+	new_tag_stat_entry->tn.tag = tag;
+	tag_stat_tree_insert(new_tag_stat_entry, &iface_entry->tag_stat_tree);
+done:
+	return new_tag_stat_entry;
+}
+
+static void if_tag_stat_update(const char *ifname, uid_t uid,
+			       const struct sock *sk, enum ifs_tx_rx direction,
+			       int proto, int bytes)
+{
+	struct tag_stat *tag_stat_entry;
+	tag_t tag, acct_tag;
+	tag_t uid_tag;
+	struct data_counters *uid_tag_counters;
+	struct sock_tag *sock_tag_entry;
+	struct iface_stat *iface_entry;
+	struct tag_stat *new_tag_stat = NULL;
+	MT_DEBUG("qtaguid: if_tag_stat_update(ifname=%s "
+		"uid=%u sk=%p dir=%d proto=%d bytes=%d)\n",
+		 ifname, uid, sk, direction, proto, bytes);
+
+
+	iface_entry = get_iface_entry(ifname);
+	if (!iface_entry) {
+		pr_err_ratelimited("qtaguid: iface_stat: stat_update() "
+				   "%s not found\n", ifname);
+		return;
+	}
+	/* It is ok to process data when an iface_entry is inactive */
+
+	MT_DEBUG("qtaguid: iface_stat: stat_update() dev=%s entry=%p\n",
+		 ifname, iface_entry);
+
+	/*
+	 * Look for a tagged sock.
+	 * It will have an acct_uid.
+	 */
+	sock_tag_entry = get_sock_stat(sk);
+	if (sock_tag_entry) {
+		tag = sock_tag_entry->tag;
+		acct_tag = get_atag_from_tag(tag);
+		uid_tag = get_utag_from_tag(tag);
+	} else {
+		acct_tag = make_atag_from_value(0);
+		tag = combine_atag_with_uid(acct_tag, uid);
+		uid_tag = make_tag_from_uid(uid);
+	}
+	MT_DEBUG("qtaguid: iface_stat: stat_update(): "
+		 " looking for tag=0x%llx (uid=%u) in ife=%p\n",
+		 tag, get_uid_from_tag(tag), iface_entry);
+	/* Loop over tag list under this interface for {acct_tag,uid_tag} */
+	spin_lock_bh(&iface_entry->tag_stat_list_lock);
+
+	tag_stat_entry = tag_stat_tree_search(&iface_entry->tag_stat_tree,
+					      tag);
+	if (tag_stat_entry) {
+		/*
+		 * Updating the {acct_tag, uid_tag} entry handles both stats:
+		 * {0, uid_tag} will also get updated.
+		 */
+		tag_stat_update(tag_stat_entry, direction, proto, bytes);
+		spin_unlock_bh(&iface_entry->tag_stat_list_lock);
+		return;
+	}
+
+	/* Loop over tag list under this interface for {0,uid_tag} */
+	tag_stat_entry = tag_stat_tree_search(&iface_entry->tag_stat_tree,
+					      uid_tag);
+	if (!tag_stat_entry) {
+		/* Here: the base uid_tag did not exist */
+		/*
+		 * No parent counters. So
+		 *  - No {0, uid_tag} stats and no {acc_tag, uid_tag} stats.
+		 */
+		new_tag_stat = create_if_tag_stat(iface_entry, uid_tag);
+		if (!new_tag_stat)
+			goto unlock;
+		uid_tag_counters = &new_tag_stat->counters;
+	} else {
+		uid_tag_counters = &tag_stat_entry->counters;
+	}
+
+	if (acct_tag) {
+		/* Create the child {acct_tag, uid_tag} and hook up parent. */
+		new_tag_stat = create_if_tag_stat(iface_entry, tag);
+		if (!new_tag_stat)
+			goto unlock;
+		new_tag_stat->parent_counters = uid_tag_counters;
+	} else {
+		/*
+		 * For new_tag_stat to be still NULL here would require:
+		 *  {0, uid_tag} exists
+		 *  and {acct_tag, uid_tag} doesn't exist
+		 *  AND acct_tag == 0.
+		 * Impossible. This reassures us that new_tag_stat
+		 * below will always be assigned.
+		 */
+		BUG_ON(!new_tag_stat);
+	}
+	tag_stat_update(new_tag_stat, direction, proto, bytes);
+unlock:
+	spin_unlock_bh(&iface_entry->tag_stat_list_lock);
+}
+
+static int iface_netdev_event_handler(struct notifier_block *nb,
+				      unsigned long event, void *ptr) {
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+	if (unlikely(module_passive))
+		return NOTIFY_DONE;
+
+	IF_DEBUG("qtaguid: iface_stat: netdev_event(): "
+		 "ev=0x%lx/%s netdev=%p->name=%s\n",
+		 event, netdev_evt_str(event), dev, dev ? dev->name : "");
+
+	switch (event) {
+	case NETDEV_UP:
+		iface_stat_create(dev, NULL);
+		atomic64_inc(&qtu_events.iface_events);
+		break;
+	case NETDEV_DOWN:
+	case NETDEV_UNREGISTER:
+		iface_stat_update(dev, event == NETDEV_DOWN);
+		atomic64_inc(&qtu_events.iface_events);
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+static int iface_inet6addr_event_handler(struct notifier_block *nb,
+					 unsigned long event, void *ptr)
+{
+	struct inet6_ifaddr *ifa = ptr;
+	struct net_device *dev;
+
+	if (unlikely(module_passive))
+		return NOTIFY_DONE;
+
+	IF_DEBUG("qtaguid: iface_stat: inet6addr_event(): "
+		 "ev=0x%lx/%s ifa=%p\n",
+		 event, netdev_evt_str(event), ifa);
+
+	switch (event) {
+	case NETDEV_UP:
+		BUG_ON(!ifa || !ifa->idev);
+		dev = (struct net_device *)ifa->idev->dev;
+		iface_stat_create_ipv6(dev, ifa);
+		atomic64_inc(&qtu_events.iface_events);
+		break;
+	case NETDEV_DOWN:
+	case NETDEV_UNREGISTER:
+		BUG_ON(!ifa || !ifa->idev);
+		dev = (struct net_device *)ifa->idev->dev;
+		iface_stat_update(dev, event == NETDEV_DOWN);
+		atomic64_inc(&qtu_events.iface_events);
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+static int iface_inetaddr_event_handler(struct notifier_block *nb,
+					unsigned long event, void *ptr)
+{
+	struct in_ifaddr *ifa = ptr;
+	struct net_device *dev;
+
+	if (unlikely(module_passive))
+		return NOTIFY_DONE;
+
+	IF_DEBUG("qtaguid: iface_stat: inetaddr_event(): "
+		 "ev=0x%lx/%s ifa=%p\n",
+		 event, netdev_evt_str(event), ifa);
+
+	switch (event) {
+	case NETDEV_UP:
+		BUG_ON(!ifa || !ifa->ifa_dev);
+		dev = ifa->ifa_dev->dev;
+		iface_stat_create(dev, ifa);
+		atomic64_inc(&qtu_events.iface_events);
+		break;
+	case NETDEV_DOWN:
+	case NETDEV_UNREGISTER:
+		BUG_ON(!ifa || !ifa->ifa_dev);
+		dev = ifa->ifa_dev->dev;
+		iface_stat_update(dev, event == NETDEV_DOWN);
+		atomic64_inc(&qtu_events.iface_events);
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block iface_netdev_notifier_blk = {
+	.notifier_call = iface_netdev_event_handler,
+};
+
+static struct notifier_block iface_inetaddr_notifier_blk = {
+	.notifier_call = iface_inetaddr_event_handler,
+};
+
+static struct notifier_block iface_inet6addr_notifier_blk = {
+	.notifier_call = iface_inet6addr_event_handler,
+};
+
+static const struct seq_operations iface_stat_fmt_proc_seq_ops = {
+	.start	= iface_stat_fmt_proc_start,
+	.next	= iface_stat_fmt_proc_next,
+	.stop	= iface_stat_fmt_proc_stop,
+	.show	= iface_stat_fmt_proc_show,
+};
+
+static int proc_iface_stat_fmt_open(struct inode *inode, struct file *file)
+{
+	struct proc_iface_stat_fmt_info *s;
+
+	s = __seq_open_private(file, &iface_stat_fmt_proc_seq_ops,
+			sizeof(struct proc_iface_stat_fmt_info));
+	if (!s)
+		return -ENOMEM;
+
+	s->fmt = (uintptr_t)PDE_DATA(inode);
+	return 0;
+}
+
+static const struct file_operations proc_iface_stat_fmt_fops = {
+	.open		= proc_iface_stat_fmt_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+static int __init iface_stat_init(struct proc_dir_entry *parent_procdir)
+{
+	int err;
+
+	iface_stat_procdir = proc_mkdir(iface_stat_procdirname, parent_procdir);
+	if (!iface_stat_procdir) {
+		pr_err("qtaguid: iface_stat: init failed to create proc entry\n");
+		err = -1;
+		goto err;
+	}
+
+	iface_stat_all_procfile = proc_create_data(iface_stat_all_procfilename,
+						   proc_iface_perms,
+						   parent_procdir,
+						   &proc_iface_stat_fmt_fops,
+						   (void *)1 /* fmt1 */);
+	if (!iface_stat_all_procfile) {
+		pr_err("qtaguid: iface_stat: init "
+		       " failed to create stat_old proc entry\n");
+		err = -1;
+		goto err_zap_entry;
+	}
+
+	iface_stat_fmt_procfile = proc_create_data(iface_stat_fmt_procfilename,
+						   proc_iface_perms,
+						   parent_procdir,
+						   &proc_iface_stat_fmt_fops,
+						   (void *)2 /* fmt2 */);
+	if (!iface_stat_fmt_procfile) {
+		pr_err("qtaguid: iface_stat: init "
+		       " failed to create stat_all proc entry\n");
+		err = -1;
+		goto err_zap_all_stats_entry;
+	}
+
+
+	err = register_netdevice_notifier(&iface_netdev_notifier_blk);
+	if (err) {
+		pr_err("qtaguid: iface_stat: init "
+		       "failed to register dev event handler\n");
+		goto err_zap_all_stats_entries;
+	}
+	err = register_inetaddr_notifier(&iface_inetaddr_notifier_blk);
+	if (err) {
+		pr_err("qtaguid: iface_stat: init "
+		       "failed to register ipv4 dev event handler\n");
+		goto err_unreg_nd;
+	}
+
+	err = register_inet6addr_notifier(&iface_inet6addr_notifier_blk);
+	if (err) {
+		pr_err("qtaguid: iface_stat: init "
+		       "failed to register ipv6 dev event handler\n");
+		goto err_unreg_ip4_addr;
+	}
+	return 0;
+
+err_unreg_ip4_addr:
+	unregister_inetaddr_notifier(&iface_inetaddr_notifier_blk);
+err_unreg_nd:
+	unregister_netdevice_notifier(&iface_netdev_notifier_blk);
+err_zap_all_stats_entries:
+	remove_proc_entry(iface_stat_fmt_procfilename, parent_procdir);
+err_zap_all_stats_entry:
+	remove_proc_entry(iface_stat_all_procfilename, parent_procdir);
+err_zap_entry:
+	remove_proc_entry(iface_stat_procdirname, parent_procdir);
+err:
+	return err;
+}
+
+static struct sock *qtaguid_find_sk(const struct sk_buff *skb,
+				    struct xt_action_param *par)
+{
+	struct sock *sk;
+	unsigned int hook_mask = (1 << par->hooknum);
+
+	MT_DEBUG("qtaguid: find_sk(skb=%p) hooknum=%d family=%d\n", skb,
+		 par->hooknum, par->family);
+
+	/*
+	 * Let's not abuse the the xt_socket_get*_sk(), or else it will
+	 * return garbage SKs.
+	 */
+	if (!(hook_mask & XT_SOCKET_SUPPORTED_HOOKS))
+		return NULL;
+
+	switch (par->family) {
+	case NFPROTO_IPV6:
+		sk = xt_socket_get6_sk(skb, par);
+		break;
+	case NFPROTO_IPV4:
+		sk = xt_socket_get4_sk(skb, par);
+		break;
+	default:
+		return NULL;
+	}
+
+	if (sk) {
+		MT_DEBUG("qtaguid: %p->sk_proto=%u "
+			 "->sk_state=%d\n", sk, sk->sk_protocol, sk->sk_state);
+		/*
+		 * When in TCP_TIME_WAIT the sk is not a "struct sock" but
+		 * "struct inet_timewait_sock" which is missing fields.
+		 */
+		if (sk->sk_state  == TCP_TIME_WAIT) {
+			if (sk != skb->sk)
+				sock_gen_put(sk);
+			sk = NULL;
+		}
+	}
+	return sk;
+}
+
+static void account_for_uid(const struct sk_buff *skb,
+			    const struct sock *alternate_sk, uid_t uid,
+			    struct xt_action_param *par)
+{
+	const struct net_device *el_dev;
+
+	if (!skb->dev) {
+		MT_DEBUG("qtaguid[%d]: no skb->dev\n", par->hooknum);
+		el_dev = par->in ? : par->out;
+	} else {
+		const struct net_device *other_dev;
+		el_dev = skb->dev;
+		other_dev = par->in ? : par->out;
+		if (el_dev != other_dev) {
+			MT_DEBUG("qtaguid[%d]: skb->dev=%p %s vs "
+				"par->(in/out)=%p %s\n",
+				par->hooknum, el_dev, el_dev->name, other_dev,
+				other_dev->name);
+		}
+	}
+
+	if (unlikely(!el_dev)) {
+		pr_info("qtaguid[%d]: no par->in/out?!!\n", par->hooknum);
+	} else if (unlikely(!el_dev->name)) {
+		pr_info("qtaguid[%d]: no dev->name?!!\n", par->hooknum);
+	} else {
+		int proto = ipx_proto(skb, par);
+		MT_DEBUG("qtaguid[%d]: dev name=%s type=%d fam=%d proto=%d\n",
+			 par->hooknum, el_dev->name, el_dev->type,
+			 par->family, proto);
+
+		if_tag_stat_update(el_dev->name, uid,
+				skb->sk ? skb->sk : alternate_sk,
+				par->in ? IFS_RX : IFS_TX,
+				proto, skb->len);
+	}
+}
+
+static bool qtaguid_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct xt_qtaguid_match_info *info = par->matchinfo;
+	const struct file *filp;
+	bool got_sock = false;
+	struct sock *sk;
+	kuid_t sock_uid;
+	bool res;
+	bool set_sk_callback_lock = false;
+
+	if (unlikely(module_passive))
+		return (info->match ^ info->invert) == 0;
+
+	MT_DEBUG("qtaguid[%d]: entered skb=%p par->in=%p/out=%p fam=%d\n",
+		 par->hooknum, skb, par->in, par->out, par->family);
+
+	atomic64_inc(&qtu_events.match_calls);
+	if (skb == NULL) {
+		res = (info->match ^ info->invert) == 0;
+		goto ret_res;
+	}
+
+	switch (par->hooknum) {
+	case NF_INET_PRE_ROUTING:
+	case NF_INET_POST_ROUTING:
+		atomic64_inc(&qtu_events.match_calls_prepost);
+		iface_stat_update_from_skb(skb, par);
+		/*
+		 * We are done in pre/post. The skb will get processed
+		 * further alter.
+		 */
+		res = (info->match ^ info->invert);
+		goto ret_res;
+		break;
+	/* default: Fall through and do UID releated work */
+	}
+
+	sk = skb->sk;
+	/*
+	 * When in TCP_TIME_WAIT the sk is not a "struct sock" but
+	 * "struct inet_timewait_sock" which is missing fields.
+	 * So we ignore it.
+	 */
+	if (sk && sk->sk_state == TCP_TIME_WAIT)
+		sk = NULL;
+	if (sk == NULL) {
+		/*
+		 * A missing sk->sk_socket happens when packets are in-flight
+		 * and the matching socket is already closed and gone.
+		 */
+		sk = qtaguid_find_sk(skb, par);
+		/*
+		 * If we got the socket from the find_sk(), we will need to put
+		 * it back, as nf_tproxy_get_sock_v4() got it.
+		 */
+		got_sock = sk;
+		if (sk)
+			atomic64_inc(&qtu_events.match_found_sk_in_ct);
+		else
+			atomic64_inc(&qtu_events.match_found_no_sk_in_ct);
+	} else {
+		atomic64_inc(&qtu_events.match_found_sk);
+	}
+	MT_DEBUG("qtaguid[%d]: sk=%p got_sock=%d fam=%d proto=%d\n",
+		 par->hooknum, sk, got_sock, par->family, ipx_proto(skb, par));
+	if (sk != NULL) {
+		set_sk_callback_lock = true;
+		read_lock_bh(&sk->sk_callback_lock);
+		MT_DEBUG("qtaguid[%d]: sk=%p->sk_socket=%p->file=%p\n",
+			par->hooknum, sk, sk->sk_socket,
+			sk->sk_socket ? sk->sk_socket->file : (void *)-1LL);
+		filp = sk->sk_socket ? sk->sk_socket->file : NULL;
+		MT_DEBUG("qtaguid[%d]: filp...uid=%u\n",
+			par->hooknum, filp ? from_kuid(&init_user_ns, filp->f_cred->fsuid) : -1);
+	}
+
+	if (sk == NULL || sk->sk_socket == NULL) {
+		/*
+		 * Here, the qtaguid_find_sk() using connection tracking
+		 * couldn't find the owner, so for now we just count them
+		 * against the system.
+		 */
+		/*
+		 * TODO: unhack how to force just accounting.
+		 * For now we only do iface stats when the uid-owner is not
+		 * requested.
+		 */
+		if (!(info->match & XT_QTAGUID_UID))
+			account_for_uid(skb, sk, 0, par);
+		MT_DEBUG("qtaguid[%d]: leaving (sk?sk->sk_socket)=%p\n",
+			par->hooknum,
+			sk ? sk->sk_socket : NULL);
+		res = (info->match ^ info->invert) == 0;
+		atomic64_inc(&qtu_events.match_no_sk);
+		goto put_sock_ret_res;
+	} else if (info->match & info->invert & XT_QTAGUID_SOCKET) {
+		res = false;
+		goto put_sock_ret_res;
+	}
+	filp = sk->sk_socket->file;
+	if (filp == NULL) {
+		MT_DEBUG("qtaguid[%d]: leaving filp=NULL\n", par->hooknum);
+		account_for_uid(skb, sk, 0, par);
+		res = ((info->match ^ info->invert) &
+			(XT_QTAGUID_UID | XT_QTAGUID_GID)) == 0;
+		atomic64_inc(&qtu_events.match_no_sk_file);
+		goto put_sock_ret_res;
+	}
+	sock_uid = filp->f_cred->fsuid;
+	/*
+	 * TODO: unhack how to force just accounting.
+	 * For now we only do iface stats when the uid-owner is not requested
+	 */
+	if (!(info->match & XT_QTAGUID_UID))
+		account_for_uid(skb, sk, from_kuid(&init_user_ns, sock_uid), par);
+
+	/*
+	 * The following two tests fail the match when:
+	 *    id not in range AND no inverted condition requested
+	 * or id     in range AND    inverted condition requested
+	 * Thus (!a && b) || (a && !b) == a ^ b
+	 */
+	if (info->match & XT_QTAGUID_UID) {
+		kuid_t uid_min = make_kuid(&init_user_ns, info->uid_min);
+		kuid_t uid_max = make_kuid(&init_user_ns, info->uid_max);
+
+		if ((uid_gte(filp->f_cred->fsuid, uid_min) &&
+		     uid_lte(filp->f_cred->fsuid, uid_max)) ^
+		    !(info->invert & XT_QTAGUID_UID)) {
+			MT_DEBUG("qtaguid[%d]: leaving uid not matching\n",
+				 par->hooknum);
+			res = false;
+			goto put_sock_ret_res;
+		}
+	}
+	if (info->match & XT_QTAGUID_GID) {
+		kgid_t gid_min = make_kgid(&init_user_ns, info->gid_min);
+		kgid_t gid_max = make_kgid(&init_user_ns, info->gid_max);
+
+		if ((gid_gte(filp->f_cred->fsgid, gid_min) &&
+				gid_lte(filp->f_cred->fsgid, gid_max)) ^
+			!(info->invert & XT_QTAGUID_GID)) {
+			MT_DEBUG("qtaguid[%d]: leaving gid not matching\n",
+				par->hooknum);
+			res = false;
+			goto put_sock_ret_res;
+		}
+	}
+	MT_DEBUG("qtaguid[%d]: leaving matched\n", par->hooknum);
+	res = true;
+
+put_sock_ret_res:
+	if (got_sock)
+		sock_gen_put(sk);
+	if (set_sk_callback_lock)
+		read_unlock_bh(&sk->sk_callback_lock);
+ret_res:
+	MT_DEBUG("qtaguid[%d]: left %d\n", par->hooknum, res);
+	return res;
+}
+
+#ifdef DDEBUG
+/* This function is not in xt_qtaguid_print.c because of locks visibility */
+static void prdebug_full_state(int indent_level, const char *fmt, ...)
+{
+	va_list args;
+	char *fmt_buff;
+	char *buff;
+
+	if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+		return;
+
+	fmt_buff = kasprintf(GFP_ATOMIC,
+			     "qtaguid: %s(): %s {\n", __func__, fmt);
+	BUG_ON(!fmt_buff);
+	va_start(args, fmt);
+	buff = kvasprintf(GFP_ATOMIC,
+			  fmt_buff, args);
+	BUG_ON(!buff);
+	pr_debug("%s", buff);
+	kfree(fmt_buff);
+	kfree(buff);
+	va_end(args);
+
+	spin_lock_bh(&sock_tag_list_lock);
+	prdebug_sock_tag_tree(indent_level, &sock_tag_tree);
+	spin_unlock_bh(&sock_tag_list_lock);
+
+	spin_lock_bh(&sock_tag_list_lock);
+	spin_lock_bh(&uid_tag_data_tree_lock);
+	prdebug_uid_tag_data_tree(indent_level, &uid_tag_data_tree);
+	prdebug_proc_qtu_data_tree(indent_level, &proc_qtu_data_tree);
+	spin_unlock_bh(&uid_tag_data_tree_lock);
+	spin_unlock_bh(&sock_tag_list_lock);
+
+	spin_lock_bh(&iface_stat_list_lock);
+	prdebug_iface_stat_list(indent_level, &iface_stat_list);
+	spin_unlock_bh(&iface_stat_list_lock);
+
+	pr_debug("qtaguid: %s(): }\n", __func__);
+}
+#else
+static void prdebug_full_state(int indent_level, const char *fmt, ...) {}
+#endif
+
+struct proc_ctrl_print_info {
+	struct sock *sk; /* socket found by reading to sk_pos */
+	loff_t sk_pos;
+};
+
+static void *qtaguid_ctrl_proc_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct proc_ctrl_print_info *pcpi = m->private;
+	struct sock_tag *sock_tag_entry = v;
+	struct rb_node *node;
+
+	(*pos)++;
+
+	if (!v || v  == SEQ_START_TOKEN)
+		return NULL;
+
+	node = rb_next(&sock_tag_entry->sock_node);
+	if (!node) {
+		pcpi->sk = NULL;
+		sock_tag_entry = SEQ_START_TOKEN;
+	} else {
+		sock_tag_entry = rb_entry(node, struct sock_tag, sock_node);
+		pcpi->sk = sock_tag_entry->sk;
+	}
+	pcpi->sk_pos = *pos;
+	return sock_tag_entry;
+}
+
+static void *qtaguid_ctrl_proc_start(struct seq_file *m, loff_t *pos)
+{
+	struct proc_ctrl_print_info *pcpi = m->private;
+	struct sock_tag *sock_tag_entry;
+	struct rb_node *node;
+
+	spin_lock_bh(&sock_tag_list_lock);
+
+	if (unlikely(module_passive))
+		return NULL;
+
+	if (*pos == 0) {
+		pcpi->sk_pos = 0;
+		node = rb_first(&sock_tag_tree);
+		if (!node) {
+			pcpi->sk = NULL;
+			return SEQ_START_TOKEN;
+		}
+		sock_tag_entry = rb_entry(node, struct sock_tag, sock_node);
+		pcpi->sk = sock_tag_entry->sk;
+	} else {
+		sock_tag_entry = (pcpi->sk ? get_sock_stat_nl(pcpi->sk) :
+						NULL) ?: SEQ_START_TOKEN;
+		if (*pos != pcpi->sk_pos) {
+			/* seq_read skipped a next call */
+			*pos = pcpi->sk_pos;
+			return qtaguid_ctrl_proc_next(m, sock_tag_entry, pos);
+		}
+	}
+	return sock_tag_entry;
+}
+
+static void qtaguid_ctrl_proc_stop(struct seq_file *m, void *v)
+{
+	spin_unlock_bh(&sock_tag_list_lock);
+}
+
+/*
+ * Procfs reader to get all active socket tags using style "1)" as described in
+ * fs/proc/generic.c
+ */
+static int qtaguid_ctrl_proc_show(struct seq_file *m, void *v)
+{
+	struct sock_tag *sock_tag_entry = v;
+	uid_t uid;
+	long f_count;
+
+	CT_DEBUG("qtaguid: proc ctrl pid=%u tgid=%u uid=%u\n",
+		 current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+
+	if (sock_tag_entry != SEQ_START_TOKEN) {
+		uid = get_uid_from_tag(sock_tag_entry->tag);
+		CT_DEBUG("qtaguid: proc_read(): sk=%p tag=0x%llx (uid=%u) "
+			 "pid=%u\n",
+			 sock_tag_entry->sk,
+			 sock_tag_entry->tag,
+			 uid,
+			 sock_tag_entry->pid
+			);
+		f_count = atomic_long_read(
+			&sock_tag_entry->socket->file->f_count);
+		seq_printf(m, "sock=%p tag=0x%llx (uid=%u) pid=%u "
+			   "f_count=%lu\n",
+			   sock_tag_entry->sk,
+			   sock_tag_entry->tag, uid,
+			   sock_tag_entry->pid, f_count);
+	} else {
+		seq_printf(m, "events: sockets_tagged=%llu "
+			   "sockets_untagged=%llu "
+			   "counter_set_changes=%llu "
+			   "delete_cmds=%llu "
+			   "iface_events=%llu "
+			   "match_calls=%llu "
+			   "match_calls_prepost=%llu "
+			   "match_found_sk=%llu "
+			   "match_found_sk_in_ct=%llu "
+			   "match_found_no_sk_in_ct=%llu "
+			   "match_no_sk=%llu "
+			   "match_no_sk_file=%llu\n",
+			   (u64)atomic64_read(&qtu_events.sockets_tagged),
+			   (u64)atomic64_read(&qtu_events.sockets_untagged),
+			   (u64)atomic64_read(&qtu_events.counter_set_changes),
+			   (u64)atomic64_read(&qtu_events.delete_cmds),
+			   (u64)atomic64_read(&qtu_events.iface_events),
+			   (u64)atomic64_read(&qtu_events.match_calls),
+			   (u64)atomic64_read(&qtu_events.match_calls_prepost),
+			   (u64)atomic64_read(&qtu_events.match_found_sk),
+			   (u64)atomic64_read(&qtu_events.match_found_sk_in_ct),
+			   (u64)atomic64_read(&qtu_events.match_found_no_sk_in_ct),
+			   (u64)atomic64_read(&qtu_events.match_no_sk),
+			   (u64)atomic64_read(&qtu_events.match_no_sk_file));
+
+		/* Count the following as part of the last item_index */
+		prdebug_full_state(0, "proc ctrl");
+	}
+
+	return 0;
+}
+
+/*
+ * Delete socket tags, and stat tags associated with a given
+ * accouting tag and uid.
+ */
+static int ctrl_cmd_delete(const char *input)
+{
+	char cmd;
+	int uid_int;
+	kuid_t uid;
+	uid_t entry_uid;
+	tag_t acct_tag;
+	tag_t tag;
+	int res, argc;
+	struct iface_stat *iface_entry;
+	struct rb_node *node;
+	struct sock_tag *st_entry;
+	struct rb_root st_to_free_tree = RB_ROOT;
+	struct tag_stat *ts_entry;
+	struct tag_counter_set *tcs_entry;
+	struct tag_ref *tr_entry;
+	struct uid_tag_data *utd_entry;
+
+	argc = sscanf(input, "%c %llu %u", &cmd, &acct_tag, &uid_int);
+	uid = make_kuid(&init_user_ns, uid_int);
+	CT_DEBUG("qtaguid: ctrl_delete(%s): argc=%d cmd=%c "
+		 "user_tag=0x%llx uid=%u\n", input, argc, cmd,
+		 acct_tag, uid_int);
+	if (argc < 2) {
+		res = -EINVAL;
+		goto err;
+	}
+	if (!valid_atag(acct_tag)) {
+		pr_info("qtaguid: ctrl_delete(%s): invalid tag\n", input);
+		res = -EINVAL;
+		goto err;
+	}
+	if (argc < 3) {
+		uid = current_fsuid();
+		uid_int = from_kuid(&init_user_ns, uid);
+	} else if (!can_impersonate_uid(uid)) {
+		pr_info("qtaguid: ctrl_delete(%s): "
+			"insufficient priv from pid=%u tgid=%u uid=%u\n",
+			input, current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+		res = -EPERM;
+		goto err;
+	}
+
+	tag = combine_atag_with_uid(acct_tag, uid_int);
+	CT_DEBUG("qtaguid: ctrl_delete(%s): "
+		 "looking for tag=0x%llx (uid=%u)\n",
+		 input, tag, uid_int);
+
+	/* Delete socket tags */
+	spin_lock_bh(&sock_tag_list_lock);
+	node = rb_first(&sock_tag_tree);
+	while (node) {
+		st_entry = rb_entry(node, struct sock_tag, sock_node);
+		entry_uid = get_uid_from_tag(st_entry->tag);
+		node = rb_next(node);
+		if (entry_uid != uid_int)
+			continue;
+
+		CT_DEBUG("qtaguid: ctrl_delete(%s): st tag=0x%llx (uid=%u)\n",
+			 input, st_entry->tag, entry_uid);
+
+		if (!acct_tag || st_entry->tag == tag) {
+			rb_erase(&st_entry->sock_node, &sock_tag_tree);
+			/* Can't sockfd_put() within spinlock, do it later. */
+			sock_tag_tree_insert(st_entry, &st_to_free_tree);
+			tr_entry = lookup_tag_ref(st_entry->tag, NULL);
+			BUG_ON(tr_entry->num_sock_tags <= 0);
+			tr_entry->num_sock_tags--;
+			/*
+			 * TODO: remove if, and start failing.
+			 * This is a hack to work around the fact that in some
+			 * places we have "if (IS_ERR_OR_NULL(pqd_entry))"
+			 * and are trying to work around apps
+			 * that didn't open the /dev/xt_qtaguid.
+			 */
+			if (st_entry->list.next && st_entry->list.prev)
+				list_del(&st_entry->list);
+		}
+	}
+	spin_unlock_bh(&sock_tag_list_lock);
+
+	sock_tag_tree_erase(&st_to_free_tree);
+
+	/* Delete tag counter-sets */
+	spin_lock_bh(&tag_counter_set_list_lock);
+	/* Counter sets are only on the uid tag, not full tag */
+	tcs_entry = tag_counter_set_tree_search(&tag_counter_set_tree, tag);
+	if (tcs_entry) {
+		CT_DEBUG("qtaguid: ctrl_delete(%s): "
+			 "erase tcs: tag=0x%llx (uid=%u) set=%d\n",
+			 input,
+			 tcs_entry->tn.tag,
+			 get_uid_from_tag(tcs_entry->tn.tag),
+			 tcs_entry->active_set);
+		rb_erase(&tcs_entry->tn.node, &tag_counter_set_tree);
+		kfree(tcs_entry);
+	}
+	spin_unlock_bh(&tag_counter_set_list_lock);
+
+	/*
+	 * If acct_tag is 0, then all entries belonging to uid are
+	 * erased.
+	 */
+	spin_lock_bh(&iface_stat_list_lock);
+	list_for_each_entry(iface_entry, &iface_stat_list, list) {
+		spin_lock_bh(&iface_entry->tag_stat_list_lock);
+		node = rb_first(&iface_entry->tag_stat_tree);
+		while (node) {
+			ts_entry = rb_entry(node, struct tag_stat, tn.node);
+			entry_uid = get_uid_from_tag(ts_entry->tn.tag);
+			node = rb_next(node);
+
+			CT_DEBUG("qtaguid: ctrl_delete(%s): "
+				 "ts tag=0x%llx (uid=%u)\n",
+				 input, ts_entry->tn.tag, entry_uid);
+
+			if (entry_uid != uid_int)
+				continue;
+			if (!acct_tag || ts_entry->tn.tag == tag) {
+				CT_DEBUG("qtaguid: ctrl_delete(%s): "
+					 "erase ts: %s 0x%llx %u\n",
+					 input, iface_entry->ifname,
+					 get_atag_from_tag(ts_entry->tn.tag),
+					 entry_uid);
+				rb_erase(&ts_entry->tn.node,
+					 &iface_entry->tag_stat_tree);
+				kfree(ts_entry);
+			}
+		}
+		spin_unlock_bh(&iface_entry->tag_stat_list_lock);
+	}
+	spin_unlock_bh(&iface_stat_list_lock);
+
+	/* Cleanup the uid_tag_data */
+	spin_lock_bh(&uid_tag_data_tree_lock);
+	node = rb_first(&uid_tag_data_tree);
+	while (node) {
+		utd_entry = rb_entry(node, struct uid_tag_data, node);
+		entry_uid = utd_entry->uid;
+		node = rb_next(node);
+
+		CT_DEBUG("qtaguid: ctrl_delete(%s): "
+			 "utd uid=%u\n",
+			 input, entry_uid);
+
+		if (entry_uid != uid_int)
+			continue;
+		/*
+		 * Go over the tag_refs, and those that don't have
+		 * sock_tags using them are freed.
+		 */
+		put_tag_ref_tree(tag, utd_entry);
+		put_utd_entry(utd_entry);
+	}
+	spin_unlock_bh(&uid_tag_data_tree_lock);
+
+	atomic64_inc(&qtu_events.delete_cmds);
+	res = 0;
+
+err:
+	return res;
+}
+
+static int ctrl_cmd_counter_set(const char *input)
+{
+	char cmd;
+	uid_t uid = 0;
+	tag_t tag;
+	int res, argc;
+	struct tag_counter_set *tcs;
+	int counter_set;
+
+	argc = sscanf(input, "%c %d %u", &cmd, &counter_set, &uid);
+	CT_DEBUG("qtaguid: ctrl_counterset(%s): argc=%d cmd=%c "
+		 "set=%d uid=%u\n", input, argc, cmd,
+		 counter_set, uid);
+	if (argc != 3) {
+		res = -EINVAL;
+		goto err;
+	}
+	if (counter_set < 0 || counter_set >= IFS_MAX_COUNTER_SETS) {
+		pr_info("qtaguid: ctrl_counterset(%s): invalid counter_set range\n",
+			input);
+		res = -EINVAL;
+		goto err;
+	}
+	if (!can_manipulate_uids()) {
+		pr_info("qtaguid: ctrl_counterset(%s): "
+			"insufficient priv from pid=%u tgid=%u uid=%u\n",
+			input, current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+		res = -EPERM;
+		goto err;
+	}
+
+	tag = make_tag_from_uid(uid);
+	spin_lock_bh(&tag_counter_set_list_lock);
+	tcs = tag_counter_set_tree_search(&tag_counter_set_tree, tag);
+	if (!tcs) {
+		tcs = kzalloc(sizeof(*tcs), GFP_ATOMIC);
+		if (!tcs) {
+			spin_unlock_bh(&tag_counter_set_list_lock);
+			pr_err("qtaguid: ctrl_counterset(%s): "
+			       "failed to alloc counter set\n",
+			       input);
+			res = -ENOMEM;
+			goto err;
+		}
+		tcs->tn.tag = tag;
+		tag_counter_set_tree_insert(tcs, &tag_counter_set_tree);
+		CT_DEBUG("qtaguid: ctrl_counterset(%s): added tcs tag=0x%llx "
+			 "(uid=%u) set=%d\n",
+			 input, tag, get_uid_from_tag(tag), counter_set);
+	}
+	tcs->active_set = counter_set;
+	spin_unlock_bh(&tag_counter_set_list_lock);
+	atomic64_inc(&qtu_events.counter_set_changes);
+	res = 0;
+
+err:
+	return res;
+}
+
+static int ctrl_cmd_tag(const char *input)
+{
+	char cmd;
+	int sock_fd = 0;
+	kuid_t uid;
+	unsigned int uid_int = 0;
+	tag_t acct_tag = make_atag_from_value(0);
+	tag_t full_tag;
+	struct socket *el_socket;
+	int res, argc;
+	struct sock_tag *sock_tag_entry;
+	struct tag_ref *tag_ref_entry;
+	struct uid_tag_data *uid_tag_data_entry;
+	struct proc_qtu_data *pqd_entry;
+
+	/* Unassigned args will get defaulted later. */
+	argc = sscanf(input, "%c %d %llu %u", &cmd, &sock_fd, &acct_tag, &uid_int);
+	uid = make_kuid(&init_user_ns, uid_int);
+	CT_DEBUG("qtaguid: ctrl_tag(%s): argc=%d cmd=%c sock_fd=%d "
+		 "acct_tag=0x%llx uid=%u\n", input, argc, cmd, sock_fd,
+		 acct_tag, uid_int);
+	if (argc < 2) {
+		res = -EINVAL;
+		goto err;
+	}
+	el_socket = sockfd_lookup(sock_fd, &res);  /* This locks the file */
+	if (!el_socket) {
+		pr_info("qtaguid: ctrl_tag(%s): failed to lookup"
+			" sock_fd=%d err=%d pid=%u tgid=%u uid=%u\n",
+			input, sock_fd, res, current->pid, current->tgid,
+			from_kuid(&init_user_ns, current_fsuid()));
+		goto err;
+	}
+	CT_DEBUG("qtaguid: ctrl_tag(%s): socket->...->f_count=%ld ->sk=%p\n",
+		 input, atomic_long_read(&el_socket->file->f_count),
+		 el_socket->sk);
+	if (argc < 3) {
+		acct_tag = make_atag_from_value(0);
+	} else if (!valid_atag(acct_tag)) {
+		pr_info("qtaguid: ctrl_tag(%s): invalid tag\n", input);
+		res = -EINVAL;
+		goto err_put;
+	}
+	CT_DEBUG("qtaguid: ctrl_tag(%s): "
+		 "pid=%u tgid=%u uid=%u euid=%u fsuid=%u "
+		 "ctrl.gid=%u in_group()=%d in_egroup()=%d\n",
+		 input, current->pid, current->tgid,
+		 from_kuid(&init_user_ns, current_uid()),
+		 from_kuid(&init_user_ns, current_euid()),
+		 from_kuid(&init_user_ns, current_fsuid()),
+		 from_kgid(&init_user_ns, xt_qtaguid_ctrl_file->gid),
+		 in_group_p(xt_qtaguid_ctrl_file->gid),
+		 in_egroup_p(xt_qtaguid_ctrl_file->gid));
+	if (argc < 4) {
+		uid = current_fsuid();
+		uid_int = from_kuid(&init_user_ns, uid);
+	} else if (!can_impersonate_uid(uid)) {
+		pr_info("qtaguid: ctrl_tag(%s): "
+			"insufficient priv from pid=%u tgid=%u uid=%u\n",
+			input, current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+		res = -EPERM;
+		goto err_put;
+	}
+	full_tag = combine_atag_with_uid(acct_tag, uid_int);
+
+	spin_lock_bh(&sock_tag_list_lock);
+	sock_tag_entry = get_sock_stat_nl(el_socket->sk);
+	tag_ref_entry = get_tag_ref(full_tag, &uid_tag_data_entry);
+	if (IS_ERR(tag_ref_entry)) {
+		res = PTR_ERR(tag_ref_entry);
+		spin_unlock_bh(&sock_tag_list_lock);
+		goto err_put;
+	}
+	tag_ref_entry->num_sock_tags++;
+	if (sock_tag_entry) {
+		struct tag_ref *prev_tag_ref_entry;
+
+		CT_DEBUG("qtaguid: ctrl_tag(%s): retag for sk=%p "
+			 "st@%p ...->f_count=%ld\n",
+			 input, el_socket->sk, sock_tag_entry,
+			 atomic_long_read(&el_socket->file->f_count));
+		/*
+		 * This is a re-tagging, so release the sock_fd that was
+		 * locked at the time of the 1st tagging.
+		 * There is still the ref from this call's sockfd_lookup() so
+		 * it can be done within the spinlock.
+		 */
+		sockfd_put(sock_tag_entry->socket);
+		prev_tag_ref_entry = lookup_tag_ref(sock_tag_entry->tag,
+						    &uid_tag_data_entry);
+		BUG_ON(IS_ERR_OR_NULL(prev_tag_ref_entry));
+		BUG_ON(prev_tag_ref_entry->num_sock_tags <= 0);
+		prev_tag_ref_entry->num_sock_tags--;
+		sock_tag_entry->tag = full_tag;
+	} else {
+		CT_DEBUG("qtaguid: ctrl_tag(%s): newtag for sk=%p\n",
+			 input, el_socket->sk);
+		sock_tag_entry = kzalloc(sizeof(*sock_tag_entry),
+					 GFP_ATOMIC);
+		if (!sock_tag_entry) {
+			pr_err("qtaguid: ctrl_tag(%s): "
+			       "socket tag alloc failed\n",
+			       input);
+			spin_unlock_bh(&sock_tag_list_lock);
+			res = -ENOMEM;
+			goto err_tag_unref_put;
+		}
+		sock_tag_entry->sk = el_socket->sk;
+		sock_tag_entry->socket = el_socket;
+		sock_tag_entry->pid = current->tgid;
+		sock_tag_entry->tag = combine_atag_with_uid(acct_tag, uid_int);
+		spin_lock_bh(&uid_tag_data_tree_lock);
+		pqd_entry = proc_qtu_data_tree_search(
+			&proc_qtu_data_tree, current->tgid);
+		/*
+		 * TODO: remove if, and start failing.
+		 * At first, we want to catch user-space code that is not
+		 * opening the /dev/xt_qtaguid.
+		 */
+		if (IS_ERR_OR_NULL(pqd_entry))
+			pr_warn_once(
+				"qtaguid: %s(): "
+				"User space forgot to open /dev/xt_qtaguid? "
+				"pid=%u tgid=%u uid=%u\n", __func__,
+				current->pid, current->tgid,
+				from_kuid(&init_user_ns, current_fsuid()));
+		else
+			list_add(&sock_tag_entry->list,
+				 &pqd_entry->sock_tag_list);
+		spin_unlock_bh(&uid_tag_data_tree_lock);
+
+		sock_tag_tree_insert(sock_tag_entry, &sock_tag_tree);
+		atomic64_inc(&qtu_events.sockets_tagged);
+	}
+	spin_unlock_bh(&sock_tag_list_lock);
+	/* We keep the ref to the socket (file) until it is untagged */
+	CT_DEBUG("qtaguid: ctrl_tag(%s): done st@%p ...->f_count=%ld\n",
+		 input, sock_tag_entry,
+		 atomic_long_read(&el_socket->file->f_count));
+	return 0;
+
+err_tag_unref_put:
+	BUG_ON(tag_ref_entry->num_sock_tags <= 0);
+	tag_ref_entry->num_sock_tags--;
+	free_tag_ref_from_utd_entry(tag_ref_entry, uid_tag_data_entry);
+err_put:
+	CT_DEBUG("qtaguid: ctrl_tag(%s): done. ...->f_count=%ld\n",
+		 input, atomic_long_read(&el_socket->file->f_count) - 1);
+	/* Release the sock_fd that was grabbed by sockfd_lookup(). */
+	sockfd_put(el_socket);
+	return res;
+
+err:
+	CT_DEBUG("qtaguid: ctrl_tag(%s): done.\n", input);
+	return res;
+}
+
+static int ctrl_cmd_untag(const char *input)
+{
+	char cmd;
+	int sock_fd = 0;
+	struct socket *el_socket;
+	int res, argc;
+	struct sock_tag *sock_tag_entry;
+	struct tag_ref *tag_ref_entry;
+	struct uid_tag_data *utd_entry;
+	struct proc_qtu_data *pqd_entry;
+
+	argc = sscanf(input, "%c %d", &cmd, &sock_fd);
+	CT_DEBUG("qtaguid: ctrl_untag(%s): argc=%d cmd=%c sock_fd=%d\n",
+		 input, argc, cmd, sock_fd);
+	if (argc < 2) {
+		res = -EINVAL;
+		goto err;
+	}
+	el_socket = sockfd_lookup(sock_fd, &res);  /* This locks the file */
+	if (!el_socket) {
+		pr_info("qtaguid: ctrl_untag(%s): failed to lookup"
+			" sock_fd=%d err=%d pid=%u tgid=%u uid=%u\n",
+			input, sock_fd, res, current->pid, current->tgid,
+			from_kuid(&init_user_ns, current_fsuid()));
+		goto err;
+	}
+	CT_DEBUG("qtaguid: ctrl_untag(%s): socket->...->f_count=%ld ->sk=%p\n",
+		 input, atomic_long_read(&el_socket->file->f_count),
+		 el_socket->sk);
+	spin_lock_bh(&sock_tag_list_lock);
+	sock_tag_entry = get_sock_stat_nl(el_socket->sk);
+	if (!sock_tag_entry) {
+		spin_unlock_bh(&sock_tag_list_lock);
+		res = -EINVAL;
+		goto err_put;
+	}
+	/*
+	 * The socket already belongs to the current process
+	 * so it can do whatever it wants to it.
+	 */
+	rb_erase(&sock_tag_entry->sock_node, &sock_tag_tree);
+
+	tag_ref_entry = lookup_tag_ref(sock_tag_entry->tag, &utd_entry);
+	BUG_ON(!tag_ref_entry);
+	BUG_ON(tag_ref_entry->num_sock_tags <= 0);
+	spin_lock_bh(&uid_tag_data_tree_lock);
+	pqd_entry = proc_qtu_data_tree_search(
+		&proc_qtu_data_tree, current->tgid);
+	/*
+	 * TODO: remove if, and start failing.
+	 * At first, we want to catch user-space code that is not
+	 * opening the /dev/xt_qtaguid.
+	 */
+	if (IS_ERR_OR_NULL(pqd_entry))
+		pr_warn_once("qtaguid: %s(): "
+			     "User space forgot to open /dev/xt_qtaguid? "
+			     "pid=%u tgid=%u uid=%u\n", __func__,
+			     current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+	else
+		list_del(&sock_tag_entry->list);
+	spin_unlock_bh(&uid_tag_data_tree_lock);
+	/*
+	 * We don't free tag_ref from the utd_entry here,
+	 * only during a cmd_delete().
+	 */
+	tag_ref_entry->num_sock_tags--;
+	spin_unlock_bh(&sock_tag_list_lock);
+	/*
+	 * Release the sock_fd that was grabbed at tag time,
+	 * and once more for the sockfd_lookup() here.
+	 */
+	sockfd_put(sock_tag_entry->socket);
+	CT_DEBUG("qtaguid: ctrl_untag(%s): done. st@%p ...->f_count=%ld\n",
+		 input, sock_tag_entry,
+		 atomic_long_read(&el_socket->file->f_count) - 1);
+	sockfd_put(el_socket);
+
+	kfree(sock_tag_entry);
+	atomic64_inc(&qtu_events.sockets_untagged);
+
+	return 0;
+
+err_put:
+	CT_DEBUG("qtaguid: ctrl_untag(%s): done. socket->...->f_count=%ld\n",
+		 input, atomic_long_read(&el_socket->file->f_count) - 1);
+	/* Release the sock_fd that was grabbed by sockfd_lookup(). */
+	sockfd_put(el_socket);
+	return res;
+
+err:
+	CT_DEBUG("qtaguid: ctrl_untag(%s): done.\n", input);
+	return res;
+}
+
+static ssize_t qtaguid_ctrl_parse(const char *input, size_t count)
+{
+	char cmd;
+	ssize_t res;
+
+	CT_DEBUG("qtaguid: ctrl(%s): pid=%u tgid=%u uid=%u\n",
+		 input, current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+
+	cmd = input[0];
+	/* Collect params for commands */
+	switch (cmd) {
+	case 'd':
+		res = ctrl_cmd_delete(input);
+		break;
+
+	case 's':
+		res = ctrl_cmd_counter_set(input);
+		break;
+
+	case 't':
+		res = ctrl_cmd_tag(input);
+		break;
+
+	case 'u':
+		res = ctrl_cmd_untag(input);
+		break;
+
+	default:
+		res = -EINVAL;
+		goto err;
+	}
+	if (!res)
+		res = count;
+err:
+	CT_DEBUG("qtaguid: ctrl(%s): res=%zd\n", input, res);
+	return res;
+}
+
+#define MAX_QTAGUID_CTRL_INPUT_LEN 255
+static ssize_t qtaguid_ctrl_proc_write(struct file *file, const char __user *buffer,
+				   size_t count, loff_t *offp)
+{
+	char input_buf[MAX_QTAGUID_CTRL_INPUT_LEN];
+
+	if (unlikely(module_passive))
+		return count;
+
+	if (count >= MAX_QTAGUID_CTRL_INPUT_LEN)
+		return -EINVAL;
+
+	if (copy_from_user(input_buf, buffer, count))
+		return -EFAULT;
+
+	input_buf[count] = '\0';
+	return qtaguid_ctrl_parse(input_buf, count);
+}
+
+struct proc_print_info {
+	struct iface_stat *iface_entry;
+	int item_index;
+	tag_t tag; /* tag found by reading to tag_pos */
+	off_t tag_pos;
+	int tag_item_index;
+};
+
+static void pp_stats_header(struct seq_file *m)
+{
+	seq_puts(m,
+		 "idx iface acct_tag_hex uid_tag_int cnt_set "
+		 "rx_bytes rx_packets "
+		 "tx_bytes tx_packets "
+		 "rx_tcp_bytes rx_tcp_packets "
+		 "rx_udp_bytes rx_udp_packets "
+		 "rx_other_bytes rx_other_packets "
+		 "tx_tcp_bytes tx_tcp_packets "
+		 "tx_udp_bytes tx_udp_packets "
+		 "tx_other_bytes tx_other_packets\n");
+}
+
+static int pp_stats_line(struct seq_file *m, struct tag_stat *ts_entry,
+			 int cnt_set)
+{
+	int ret;
+	struct data_counters *cnts;
+	tag_t tag = ts_entry->tn.tag;
+	uid_t stat_uid = get_uid_from_tag(tag);
+	struct proc_print_info *ppi = m->private;
+	/* Detailed tags are not available to everybody */
+	if (get_atag_from_tag(tag) && !can_read_other_uid_stats(
+						make_kuid(&init_user_ns,stat_uid))) {
+		CT_DEBUG("qtaguid: stats line: "
+			 "%s 0x%llx %u: insufficient priv "
+			 "from pid=%u tgid=%u uid=%u stats.gid=%u\n",
+			 ppi->iface_entry->ifname,
+			 get_atag_from_tag(tag), stat_uid,
+			 current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()),
+			 from_kgid(&init_user_ns,xt_qtaguid_stats_file->gid));
+		return 0;
+	}
+	ppi->item_index++;
+	cnts = &ts_entry->counters;
+	ret = seq_printf(m, "%d %s 0x%llx %u %u "
+		"%llu %llu "
+		"%llu %llu "
+		"%llu %llu "
+		"%llu %llu "
+		"%llu %llu "
+		"%llu %llu "
+		"%llu %llu "
+		"%llu %llu\n",
+		ppi->item_index,
+		ppi->iface_entry->ifname,
+		get_atag_from_tag(tag),
+		stat_uid,
+		cnt_set,
+		dc_sum_bytes(cnts, cnt_set, IFS_RX),
+		dc_sum_packets(cnts, cnt_set, IFS_RX),
+		dc_sum_bytes(cnts, cnt_set, IFS_TX),
+		dc_sum_packets(cnts, cnt_set, IFS_TX),
+		cnts->bpc[cnt_set][IFS_RX][IFS_TCP].bytes,
+		cnts->bpc[cnt_set][IFS_RX][IFS_TCP].packets,
+		cnts->bpc[cnt_set][IFS_RX][IFS_UDP].bytes,
+		cnts->bpc[cnt_set][IFS_RX][IFS_UDP].packets,
+		cnts->bpc[cnt_set][IFS_RX][IFS_PROTO_OTHER].bytes,
+		cnts->bpc[cnt_set][IFS_RX][IFS_PROTO_OTHER].packets,
+		cnts->bpc[cnt_set][IFS_TX][IFS_TCP].bytes,
+		cnts->bpc[cnt_set][IFS_TX][IFS_TCP].packets,
+		cnts->bpc[cnt_set][IFS_TX][IFS_UDP].bytes,
+		cnts->bpc[cnt_set][IFS_TX][IFS_UDP].packets,
+		cnts->bpc[cnt_set][IFS_TX][IFS_PROTO_OTHER].bytes,
+		cnts->bpc[cnt_set][IFS_TX][IFS_PROTO_OTHER].packets);
+	return ret ?: 1;
+}
+
+static bool pp_sets(struct seq_file *m, struct tag_stat *ts_entry)
+{
+	int ret;
+	int counter_set;
+	for (counter_set = 0; counter_set < IFS_MAX_COUNTER_SETS;
+	     counter_set++) {
+		ret = pp_stats_line(m, ts_entry, counter_set);
+		if (ret < 0)
+			return false;
+	}
+	return true;
+}
+
+static int qtaguid_stats_proc_iface_stat_ptr_valid(struct iface_stat *ptr)
+{
+	struct iface_stat *iface_entry;
+
+	if (!ptr)
+		return false;
+
+	list_for_each_entry(iface_entry, &iface_stat_list, list)
+		if (iface_entry == ptr)
+			return true;
+	return false;
+}
+
+static void qtaguid_stats_proc_next_iface_entry(struct proc_print_info *ppi)
+{
+	spin_unlock_bh(&ppi->iface_entry->tag_stat_list_lock);
+	list_for_each_entry_continue(ppi->iface_entry, &iface_stat_list, list) {
+		spin_lock_bh(&ppi->iface_entry->tag_stat_list_lock);
+		return;
+	}
+	ppi->iface_entry = NULL;
+}
+
+static void *qtaguid_stats_proc_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct proc_print_info *ppi = m->private;
+	struct tag_stat *ts_entry;
+	struct rb_node *node;
+
+	if (!v) {
+		pr_err("qtaguid: %s(): unexpected v: NULL\n", __func__);
+		return NULL;
+	}
+
+	(*pos)++;
+
+	if (!ppi->iface_entry || unlikely(module_passive))
+		return NULL;
+
+	if (v == SEQ_START_TOKEN)
+		node = rb_first(&ppi->iface_entry->tag_stat_tree);
+	else
+		node = rb_next(&((struct tag_stat *)v)->tn.node);
+
+	while (!node) {
+		qtaguid_stats_proc_next_iface_entry(ppi);
+		if (!ppi->iface_entry)
+			return NULL;
+		node = rb_first(&ppi->iface_entry->tag_stat_tree);
+	}
+
+	ts_entry = rb_entry(node, struct tag_stat, tn.node);
+	ppi->tag = ts_entry->tn.tag;
+	ppi->tag_pos = *pos;
+	ppi->tag_item_index = ppi->item_index;
+	return ts_entry;
+}
+
+static void *qtaguid_stats_proc_start(struct seq_file *m, loff_t *pos)
+{
+	struct proc_print_info *ppi = m->private;
+	struct tag_stat *ts_entry = NULL;
+
+	spin_lock_bh(&iface_stat_list_lock);
+
+	if (*pos == 0) {
+		ppi->item_index = 1;
+		ppi->tag_pos = 0;
+		if (list_empty(&iface_stat_list)) {
+			ppi->iface_entry = NULL;
+		} else {
+			ppi->iface_entry = list_first_entry(&iface_stat_list,
+							    struct iface_stat,
+							    list);
+			spin_lock_bh(&ppi->iface_entry->tag_stat_list_lock);
+		}
+		return SEQ_START_TOKEN;
+	}
+	if (!qtaguid_stats_proc_iface_stat_ptr_valid(ppi->iface_entry)) {
+		if (ppi->iface_entry) {
+			pr_err("qtaguid: %s(): iface_entry %p not found\n",
+			       __func__, ppi->iface_entry);
+			ppi->iface_entry = NULL;
+		}
+		return NULL;
+	}
+
+	spin_lock_bh(&ppi->iface_entry->tag_stat_list_lock);
+
+	if (!ppi->tag_pos) {
+		/* seq_read skipped first next call */
+		ts_entry = SEQ_START_TOKEN;
+	} else {
+		ts_entry = tag_stat_tree_search(
+				&ppi->iface_entry->tag_stat_tree, ppi->tag);
+		if (!ts_entry) {
+			pr_info("qtaguid: %s(): tag_stat.tag 0x%llx not found. Abort.\n",
+				__func__, ppi->tag);
+			return NULL;
+		}
+	}
+
+	if (*pos == ppi->tag_pos) { /* normal resume */
+		ppi->item_index = ppi->tag_item_index;
+	} else {
+		/* seq_read skipped a next call */
+		*pos = ppi->tag_pos;
+		ts_entry = qtaguid_stats_proc_next(m, ts_entry, pos);
+	}
+
+	return ts_entry;
+}
+
+static void qtaguid_stats_proc_stop(struct seq_file *m, void *v)
+{
+	struct proc_print_info *ppi = m->private;
+	if (ppi->iface_entry)
+		spin_unlock_bh(&ppi->iface_entry->tag_stat_list_lock);
+	spin_unlock_bh(&iface_stat_list_lock);
+}
+
+/*
+ * Procfs reader to get all tag stats using style "1)" as described in
+ * fs/proc/generic.c
+ * Groups all protocols tx/rx bytes.
+ */
+static int qtaguid_stats_proc_show(struct seq_file *m, void *v)
+{
+	struct tag_stat *ts_entry = v;
+
+	if (v == SEQ_START_TOKEN)
+		pp_stats_header(m);
+	else
+		pp_sets(m, ts_entry);
+
+	return 0;
+}
+
+/*------------------------------------------*/
+static int qtudev_open(struct inode *inode, struct file *file)
+{
+	struct uid_tag_data *utd_entry;
+	struct proc_qtu_data  *pqd_entry;
+	struct proc_qtu_data  *new_pqd_entry;
+	int res;
+	bool utd_entry_found;
+
+	if (unlikely(qtu_proc_handling_passive))
+		return 0;
+
+	DR_DEBUG("qtaguid: qtudev_open(): pid=%u tgid=%u uid=%u\n",
+		 current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+
+	spin_lock_bh(&uid_tag_data_tree_lock);
+
+	/* Look for existing uid data, or alloc one. */
+	utd_entry = get_uid_data(from_kuid(&init_user_ns, current_fsuid()), &utd_entry_found);
+	if (IS_ERR_OR_NULL(utd_entry)) {
+		res = PTR_ERR(utd_entry);
+		goto err_unlock;
+	}
+
+	/* Look for existing PID based proc_data */
+	pqd_entry = proc_qtu_data_tree_search(&proc_qtu_data_tree,
+					      current->tgid);
+	if (pqd_entry) {
+		pr_err("qtaguid: qtudev_open(): %u/%u %u "
+		       "%s already opened\n",
+		       current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()),
+		       QTU_DEV_NAME);
+		res = -EBUSY;
+		goto err_unlock_free_utd;
+	}
+
+	new_pqd_entry = kzalloc(sizeof(*new_pqd_entry), GFP_ATOMIC);
+	if (!new_pqd_entry) {
+		pr_err("qtaguid: qtudev_open(): %u/%u %u: "
+		       "proc data alloc failed\n",
+		       current->pid, current->tgid, from_kuid(&init_user_ns, current_fsuid()));
+		res = -ENOMEM;
+		goto err_unlock_free_utd;
+	}
+	new_pqd_entry->pid = current->tgid;
+	INIT_LIST_HEAD(&new_pqd_entry->sock_tag_list);
+	new_pqd_entry->parent_tag_data = utd_entry;
+	utd_entry->num_pqd++;
+
+	proc_qtu_data_tree_insert(new_pqd_entry,
+				  &proc_qtu_data_tree);
+
+	spin_unlock_bh(&uid_tag_data_tree_lock);
+	DR_DEBUG("qtaguid: tracking data for uid=%u in pqd=%p\n",
+		 from_kuid(&init_user_ns, current_fsuid()), new_pqd_entry);
+	file->private_data = new_pqd_entry;
+	return 0;
+
+err_unlock_free_utd:
+	if (!utd_entry_found) {
+		rb_erase(&utd_entry->node, &uid_tag_data_tree);
+		kfree(utd_entry);
+	}
+err_unlock:
+	spin_unlock_bh(&uid_tag_data_tree_lock);
+	return res;
+}
+
+static int qtudev_release(struct inode *inode, struct file *file)
+{
+	struct proc_qtu_data  *pqd_entry = file->private_data;
+	struct uid_tag_data  *utd_entry = pqd_entry->parent_tag_data;
+	struct sock_tag *st_entry;
+	struct rb_root st_to_free_tree = RB_ROOT;
+	struct list_head *entry, *next;
+	struct tag_ref *tr;
+
+	if (unlikely(qtu_proc_handling_passive))
+		return 0;
+
+	/*
+	 * Do not trust the current->pid, it might just be a kworker cleaning
+	 * up after a dead proc.
+	 */
+	DR_DEBUG("qtaguid: qtudev_release(): "
+		 "pid=%u tgid=%u uid=%u "
+		 "pqd_entry=%p->pid=%u utd_entry=%p->active_tags=%d\n",
+		 current->pid, current->tgid, pqd_entry->parent_tag_data->uid,
+		 pqd_entry, pqd_entry->pid, utd_entry,
+		 utd_entry->num_active_tags);
+
+	spin_lock_bh(&sock_tag_list_lock);
+	spin_lock_bh(&uid_tag_data_tree_lock);
+
+	list_for_each_safe(entry, next, &pqd_entry->sock_tag_list) {
+		st_entry = list_entry(entry, struct sock_tag, list);
+		DR_DEBUG("qtaguid: %s(): "
+			 "erase sock_tag=%p->sk=%p pid=%u tgid=%u uid=%u\n",
+			 __func__,
+			 st_entry, st_entry->sk,
+			 current->pid, current->tgid,
+			 pqd_entry->parent_tag_data->uid);
+
+		utd_entry = uid_tag_data_tree_search(
+			&uid_tag_data_tree,
+			get_uid_from_tag(st_entry->tag));
+		BUG_ON(IS_ERR_OR_NULL(utd_entry));
+		DR_DEBUG("qtaguid: %s(): "
+			 "looking for tag=0x%llx in utd_entry=%p\n", __func__,
+			 st_entry->tag, utd_entry);
+		tr = tag_ref_tree_search(&utd_entry->tag_ref_tree,
+					 st_entry->tag);
+		BUG_ON(!tr);
+		BUG_ON(tr->num_sock_tags <= 0);
+		tr->num_sock_tags--;
+		free_tag_ref_from_utd_entry(tr, utd_entry);
+
+		rb_erase(&st_entry->sock_node, &sock_tag_tree);
+		list_del(&st_entry->list);
+		/* Can't sockfd_put() within spinlock, do it later. */
+		sock_tag_tree_insert(st_entry, &st_to_free_tree);
+
+		/*
+		 * Try to free the utd_entry if no other proc_qtu_data is
+		 * using it (num_pqd is 0) and it doesn't have active tags
+		 * (num_active_tags is 0).
+		 */
+		put_utd_entry(utd_entry);
+	}
+
+	rb_erase(&pqd_entry->node, &proc_qtu_data_tree);
+	BUG_ON(pqd_entry->parent_tag_data->num_pqd < 1);
+	pqd_entry->parent_tag_data->num_pqd--;
+	put_utd_entry(pqd_entry->parent_tag_data);
+	kfree(pqd_entry);
+	file->private_data = NULL;
+
+	spin_unlock_bh(&uid_tag_data_tree_lock);
+	spin_unlock_bh(&sock_tag_list_lock);
+
+
+	sock_tag_tree_erase(&st_to_free_tree);
+
+	prdebug_full_state(0, "%s(): pid=%u tgid=%u", __func__,
+			   current->pid, current->tgid);
+	return 0;
+}
+
+/*------------------------------------------*/
+static const struct file_operations qtudev_fops = {
+	.owner = THIS_MODULE,
+	.open = qtudev_open,
+	.release = qtudev_release,
+};
+
+static struct miscdevice qtu_device = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = QTU_DEV_NAME,
+	.fops = &qtudev_fops,
+	/* How sad it doesn't allow for defaults: .mode = S_IRUGO | S_IWUSR */
+};
+
+static const struct seq_operations proc_qtaguid_ctrl_seqops = {
+	.start = qtaguid_ctrl_proc_start,
+	.next = qtaguid_ctrl_proc_next,
+	.stop = qtaguid_ctrl_proc_stop,
+	.show = qtaguid_ctrl_proc_show,
+};
+
+static int proc_qtaguid_ctrl_open(struct inode *inode, struct file *file)
+{
+	return seq_open_private(file, &proc_qtaguid_ctrl_seqops,
+				sizeof(struct proc_ctrl_print_info));
+}
+
+static const struct file_operations proc_qtaguid_ctrl_fops = {
+	.open		= proc_qtaguid_ctrl_open,
+	.read		= seq_read,
+	.write		= qtaguid_ctrl_proc_write,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+static const struct seq_operations proc_qtaguid_stats_seqops = {
+	.start = qtaguid_stats_proc_start,
+	.next = qtaguid_stats_proc_next,
+	.stop = qtaguid_stats_proc_stop,
+	.show = qtaguid_stats_proc_show,
+};
+
+static int proc_qtaguid_stats_open(struct inode *inode, struct file *file)
+{
+	return seq_open_private(file, &proc_qtaguid_stats_seqops,
+				sizeof(struct proc_print_info));
+}
+
+static const struct file_operations proc_qtaguid_stats_fops = {
+	.open		= proc_qtaguid_stats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+/*------------------------------------------*/
+static int __init qtaguid_proc_register(struct proc_dir_entry **res_procdir)
+{
+	int ret;
+	*res_procdir = proc_mkdir(module_procdirname, init_net.proc_net);
+	if (!*res_procdir) {
+		pr_err("qtaguid: failed to create proc/.../xt_qtaguid\n");
+		ret = -ENOMEM;
+		goto no_dir;
+	}
+
+	xt_qtaguid_ctrl_file = proc_create_data("ctrl", proc_ctrl_perms,
+						*res_procdir,
+						&proc_qtaguid_ctrl_fops,
+						NULL);
+	if (!xt_qtaguid_ctrl_file) {
+		pr_err("qtaguid: failed to create xt_qtaguid/ctrl "
+			" file\n");
+		ret = -ENOMEM;
+		goto no_ctrl_entry;
+	}
+
+	xt_qtaguid_stats_file = proc_create_data("stats", proc_stats_perms,
+						 *res_procdir,
+						 &proc_qtaguid_stats_fops,
+						 NULL);
+	if (!xt_qtaguid_stats_file) {
+		pr_err("qtaguid: failed to create xt_qtaguid/stats "
+			"file\n");
+		ret = -ENOMEM;
+		goto no_stats_entry;
+	}
+	/*
+	 * TODO: add support counter hacking
+	 * xt_qtaguid_stats_file->write_proc = qtaguid_stats_proc_write;
+	 */
+	return 0;
+
+no_stats_entry:
+	remove_proc_entry("ctrl", *res_procdir);
+no_ctrl_entry:
+	remove_proc_entry("xt_qtaguid", NULL);
+no_dir:
+	return ret;
+}
+
+static struct xt_match qtaguid_mt_reg __read_mostly = {
+	/*
+	 * This module masquerades as the "owner" module so that iptables
+	 * tools can deal with it.
+	 */
+	.name       = "owner",
+	.revision   = 1,
+	.family     = NFPROTO_UNSPEC,
+	.match      = qtaguid_mt,
+	.matchsize  = sizeof(struct xt_qtaguid_match_info),
+	.me         = THIS_MODULE,
+};
+
+static int __init qtaguid_mt_init(void)
+{
+	if (qtaguid_proc_register(&xt_qtaguid_procdir)
+	    || iface_stat_init(xt_qtaguid_procdir)
+	    || xt_register_match(&qtaguid_mt_reg)
+	    || misc_register(&qtu_device))
+		return -1;
+	return 0;
+}
+
+/*
+ * TODO: allow unloading of the module.
+ * For now stats are permanent.
+ * Kconfig forces'y/n' and never an 'm'.
+ */
+
+module_init(qtaguid_mt_init);
+MODULE_AUTHOR("jpa <jpa@google.com>");
+MODULE_DESCRIPTION("Xtables: socket owner+tag matching and associated stats");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("ipt_owner");
+MODULE_ALIAS("ip6t_owner");
+MODULE_ALIAS("ipt_qtaguid");
+MODULE_ALIAS("ip6t_qtaguid");
diff --git a/net/netfilter/xt_qtaguid_internal.h b/net/netfilter/xt_qtaguid_internal.h
new file mode 100644
index 00000000000..6dc14a9c688
--- /dev/null
+++ b/net/netfilter/xt_qtaguid_internal.h
@@ -0,0 +1,352 @@
+/*
+ * Kernel iptables module to track stats for packets based on user tags.
+ *
+ * (C) 2011 Google, Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __XT_QTAGUID_INTERNAL_H__
+#define __XT_QTAGUID_INTERNAL_H__
+
+#include <linux/types.h>
+#include <linux/rbtree.h>
+#include <linux/spinlock_types.h>
+#include <linux/workqueue.h>
+
+/* Iface handling */
+#define IDEBUG_MASK (1<<0)
+/* Iptable Matching. Per packet. */
+#define MDEBUG_MASK (1<<1)
+/* Red-black tree handling. Per packet. */
+#define RDEBUG_MASK (1<<2)
+/* procfs ctrl/stats handling */
+#define CDEBUG_MASK (1<<3)
+/* dev and resource tracking */
+#define DDEBUG_MASK (1<<4)
+
+/* E.g (IDEBUG_MASK | CDEBUG_MASK | DDEBUG_MASK) */
+#define DEFAULT_DEBUG_MASK 0
+
+/*
+ * (Un)Define these *DEBUG to compile out/in the pr_debug calls.
+ * All undef: text size ~ 0x3030; all def: ~ 0x4404.
+ */
+#define IDEBUG
+#define MDEBUG
+#define RDEBUG
+#define CDEBUG
+#define DDEBUG
+
+#define MSK_DEBUG(mask, ...) do {                           \
+		if (unlikely(qtaguid_debug_mask & (mask)))  \
+			pr_debug(__VA_ARGS__);              \
+	} while (0)
+#ifdef IDEBUG
+#define IF_DEBUG(...) MSK_DEBUG(IDEBUG_MASK, __VA_ARGS__)
+#else
+#define IF_DEBUG(...) no_printk(__VA_ARGS__)
+#endif
+#ifdef MDEBUG
+#define MT_DEBUG(...) MSK_DEBUG(MDEBUG_MASK, __VA_ARGS__)
+#else
+#define MT_DEBUG(...) no_printk(__VA_ARGS__)
+#endif
+#ifdef RDEBUG
+#define RB_DEBUG(...) MSK_DEBUG(RDEBUG_MASK, __VA_ARGS__)
+#else
+#define RB_DEBUG(...) no_printk(__VA_ARGS__)
+#endif
+#ifdef CDEBUG
+#define CT_DEBUG(...) MSK_DEBUG(CDEBUG_MASK, __VA_ARGS__)
+#else
+#define CT_DEBUG(...) no_printk(__VA_ARGS__)
+#endif
+#ifdef DDEBUG
+#define DR_DEBUG(...) MSK_DEBUG(DDEBUG_MASK, __VA_ARGS__)
+#else
+#define DR_DEBUG(...) no_printk(__VA_ARGS__)
+#endif
+
+extern uint qtaguid_debug_mask;
+
+/*---------------------------------------------------------------------------*/
+/*
+ * Tags:
+ *
+ * They represent what the data usage counters will be tracked against.
+ * By default a tag is just based on the UID.
+ * The UID is used as the base for policing, and can not be ignored.
+ * So a tag will always at least represent a UID (uid_tag).
+ *
+ * A tag can be augmented with an "accounting tag" which is associated
+ * with a UID.
+ * User space can set the acct_tag portion of the tag which is then used
+ * with sockets: all data belonging to that socket will be counted against the
+ * tag. The policing is then based on the tag's uid_tag portion,
+ * and stats are collected for the acct_tag portion separately.
+ *
+ * There could be
+ * a:  {acct_tag=1, uid_tag=10003}
+ * b:  {acct_tag=2, uid_tag=10003}
+ * c:  {acct_tag=3, uid_tag=10003}
+ * d:  {acct_tag=0, uid_tag=10003}
+ * a, b, and c represent tags associated with specific sockets.
+ * d is for the totals for that uid, including all untagged traffic.
+ * Typically d is used with policing/quota rules.
+ *
+ * We want tag_t big enough to distinguish uid_t and acct_tag.
+ * It might become a struct if needed.
+ * Nothing should be using it as an int.
+ */
+typedef uint64_t tag_t;  /* Only used via accessors */
+
+#define TAG_UID_MASK 0xFFFFFFFFULL
+#define TAG_ACCT_MASK (~0xFFFFFFFFULL)
+
+static inline int tag_compare(tag_t t1, tag_t t2)
+{
+	return t1 < t2 ? -1 : t1 == t2 ? 0 : 1;
+}
+
+static inline tag_t combine_atag_with_uid(tag_t acct_tag, uid_t uid)
+{
+	return acct_tag | uid;
+}
+static inline tag_t make_tag_from_uid(uid_t uid)
+{
+	return uid;
+}
+static inline uid_t get_uid_from_tag(tag_t tag)
+{
+	return tag & TAG_UID_MASK;
+}
+static inline tag_t get_utag_from_tag(tag_t tag)
+{
+	return tag & TAG_UID_MASK;
+}
+static inline tag_t get_atag_from_tag(tag_t tag)
+{
+	return tag & TAG_ACCT_MASK;
+}
+
+static inline bool valid_atag(tag_t tag)
+{
+	return !(tag & TAG_UID_MASK);
+}
+static inline tag_t make_atag_from_value(uint32_t value)
+{
+	return (uint64_t)value << 32;
+}
+/*---------------------------------------------------------------------------*/
+
+/*
+ * Maximum number of socket tags that a UID is allowed to have active.
+ * Multiple processes belonging to the same UID contribute towards this limit.
+ * Special UIDs that can impersonate a UID also contribute (e.g. download
+ * manager, ...)
+ */
+#define DEFAULT_MAX_SOCK_TAGS 1024
+
+/*
+ * For now we only track 2 sets of counters.
+ * The default set is 0.
+ * Userspace can activate another set for a given uid being tracked.
+ */
+#define IFS_MAX_COUNTER_SETS 2
+
+enum ifs_tx_rx {
+	IFS_TX,
+	IFS_RX,
+	IFS_MAX_DIRECTIONS
+};
+
+/* For now, TCP, UDP, the rest */
+enum ifs_proto {
+	IFS_TCP,
+	IFS_UDP,
+	IFS_PROTO_OTHER,
+	IFS_MAX_PROTOS
+};
+
+struct byte_packet_counters {
+	uint64_t bytes;
+	uint64_t packets;
+};
+
+struct data_counters {
+	struct byte_packet_counters bpc[IFS_MAX_COUNTER_SETS][IFS_MAX_DIRECTIONS][IFS_MAX_PROTOS];
+};
+
+static inline uint64_t dc_sum_bytes(struct data_counters *counters,
+				    int set,
+				    enum ifs_tx_rx direction)
+{
+	return counters->bpc[set][direction][IFS_TCP].bytes
+		+ counters->bpc[set][direction][IFS_UDP].bytes
+		+ counters->bpc[set][direction][IFS_PROTO_OTHER].bytes;
+}
+
+static inline uint64_t dc_sum_packets(struct data_counters *counters,
+				      int set,
+				      enum ifs_tx_rx direction)
+{
+	return counters->bpc[set][direction][IFS_TCP].packets
+		+ counters->bpc[set][direction][IFS_UDP].packets
+		+ counters->bpc[set][direction][IFS_PROTO_OTHER].packets;
+}
+
+
+/* Generic X based nodes used as a base for rb_tree ops */
+struct tag_node {
+	struct rb_node node;
+	tag_t tag;
+};
+
+struct tag_stat {
+	struct tag_node tn;
+	struct data_counters counters;
+	/*
+	 * If this tag is acct_tag based, we need to count against the
+	 * matching parent uid_tag.
+	 */
+	struct data_counters *parent_counters;
+};
+
+struct iface_stat {
+	struct list_head list;  /* in iface_stat_list */
+	char *ifname;
+	bool active;
+	/* net_dev is only valid for active iface_stat */
+	struct net_device *net_dev;
+
+	struct byte_packet_counters totals_via_dev[IFS_MAX_DIRECTIONS];
+	struct data_counters totals_via_skb;
+	/*
+	 * We keep the last_known, because some devices reset their counters
+	 * just before NETDEV_UP, while some will reset just before
+	 * NETDEV_REGISTER (which is more normal).
+	 * So now, if the device didn't do a NETDEV_UNREGISTER and we see
+	 * its current dev stats smaller that what was previously known, we
+	 * assume an UNREGISTER and just use the last_known.
+	 */
+	struct byte_packet_counters last_known[IFS_MAX_DIRECTIONS];
+	/* last_known is usable when last_known_valid is true */
+	bool last_known_valid;
+
+	struct proc_dir_entry *proc_ptr;
+
+	struct rb_root tag_stat_tree;
+	spinlock_t tag_stat_list_lock;
+};
+
+/* This is needed to create proc_dir_entries from atomic context. */
+struct iface_stat_work {
+	struct work_struct iface_work;
+	struct iface_stat *iface_entry;
+};
+
+/*
+ * Track tag that this socket is transferring data for, and not necessarily
+ * the uid that owns the socket.
+ * This is the tag against which tag_stat.counters will be billed.
+ * These structs need to be looked up by sock and pid.
+ */
+struct sock_tag {
+	struct rb_node sock_node;
+	struct sock *sk;  /* Only used as a number, never dereferenced */
+	/* The socket is needed for sockfd_put() */
+	struct socket *socket;
+	/* Used to associate with a given pid */
+	struct list_head list;   /* in proc_qtu_data.sock_tag_list */
+	pid_t pid;
+
+	tag_t tag;
+};
+
+struct qtaguid_event_counts {
+	/* Various successful events */
+	atomic64_t sockets_tagged;
+	atomic64_t sockets_untagged;
+	atomic64_t counter_set_changes;
+	atomic64_t delete_cmds;
+	atomic64_t iface_events;  /* Number of NETDEV_* events handled */
+
+	atomic64_t match_calls;   /* Number of times iptables called mt */
+	/* Number of times iptables called mt from pre or post routing hooks */
+	atomic64_t match_calls_prepost;
+	/*
+	 * match_found_sk_*: numbers related to the netfilter matching
+	 * function finding a sock for the sk_buff.
+	 * Total skbs processed is sum(match_found*).
+	 */
+	atomic64_t match_found_sk;   /* An sk was already in the sk_buff. */
+	/* The connection tracker had or didn't have the sk. */
+	atomic64_t match_found_sk_in_ct;
+	atomic64_t match_found_no_sk_in_ct;
+	/*
+	 * No sk could be found. No apparent owner. Could happen with
+	 * unsolicited traffic.
+	 */
+	atomic64_t match_no_sk;
+	/*
+	 * The file ptr in the sk_socket wasn't there.
+	 * This might happen for traffic while the socket is being closed.
+	 */
+	atomic64_t match_no_sk_file;
+};
+
+/* Track the set active_set for the given tag. */
+struct tag_counter_set {
+	struct tag_node tn;
+	int active_set;
+};
+
+/*----------------------------------------------*/
+/*
+ * The qtu uid data is used to track resources that are created directly or
+ * indirectly by processes (uid tracked).
+ * It is shared by the processes with the same uid.
+ * Some of the resource will be counted to prevent further rogue allocations,
+ * some will need freeing once the owner process (uid) exits.
+ */
+struct uid_tag_data {
+	struct rb_node node;
+	uid_t uid;
+
+	/*
+	 * For the uid, how many accounting tags have been set.
+	 */
+	int num_active_tags;
+	/* Track the number of proc_qtu_data that reference it */
+	int num_pqd;
+	struct rb_root tag_ref_tree;
+	/* No tag_node_tree_lock; use uid_tag_data_tree_lock */
+};
+
+struct tag_ref {
+	struct tag_node tn;
+
+	/*
+	 * This tracks the number of active sockets that have a tag on them
+	 * which matches this tag_ref.tn.tag.
+	 * A tag ref can live on after the sockets are untagged.
+	 * A tag ref can only be removed during a tag delete command.
+	 */
+	int num_sock_tags;
+};
+
+struct proc_qtu_data {
+	struct rb_node node;
+	pid_t pid;
+
+	struct uid_tag_data *parent_tag_data;
+
+	/* Tracks the sock_tags that need freeing upon this proc's death */
+	struct list_head sock_tag_list;
+	/* No spinlock_t sock_tag_list_lock; use the global one. */
+};
+
+/*----------------------------------------------*/
+#endif  /* ifndef __XT_QTAGUID_INTERNAL_H__ */
diff --git a/net/netfilter/xt_qtaguid_print.c b/net/netfilter/xt_qtaguid_print.c
new file mode 100644
index 00000000000..f6a00a3520e
--- /dev/null
+++ b/net/netfilter/xt_qtaguid_print.c
@@ -0,0 +1,566 @@
+/*
+ * Pretty printing Support for iptables xt_qtaguid module.
+ *
+ * (C) 2011 Google, Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Most of the functions in this file just waste time if DEBUG is not defined.
+ * The matching xt_qtaguid_print.h will static inline empty funcs if the needed
+ * debug flags ore not defined.
+ * Those funcs that fail to allocate memory will panic as there is no need to
+ * hobble allong just pretending to do the requested work.
+ */
+
+#define DEBUG
+
+#include <linux/fs.h>
+#include <linux/gfp.h>
+#include <linux/net.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+#include <linux/spinlock_types.h>
+
+
+#include "xt_qtaguid_internal.h"
+#include "xt_qtaguid_print.h"
+
+#ifdef DDEBUG
+
+static void _bug_on_err_or_null(void *ptr)
+{
+	if (IS_ERR_OR_NULL(ptr)) {
+		pr_err("qtaguid: kmalloc failed\n");
+		BUG();
+	}
+}
+
+char *pp_tag_t(tag_t *tag)
+{
+	char *res;
+
+	if (!tag)
+		res = kasprintf(GFP_ATOMIC, "tag_t@null{}");
+	else
+		res = kasprintf(GFP_ATOMIC,
+				"tag_t@%p{tag=0x%llx, uid=%u}",
+				tag, *tag, get_uid_from_tag(*tag));
+	_bug_on_err_or_null(res);
+	return res;
+}
+
+char *pp_data_counters(struct data_counters *dc, bool showValues)
+{
+	char *res;
+
+	if (!dc)
+		res = kasprintf(GFP_ATOMIC, "data_counters@null{}");
+	else if (showValues)
+		res = kasprintf(
+			GFP_ATOMIC, "data_counters@%p{"
+			"set0{"
+			"rx{"
+			"tcp{b=%llu, p=%llu}, "
+			"udp{b=%llu, p=%llu},"
+			"other{b=%llu, p=%llu}}, "
+			"tx{"
+			"tcp{b=%llu, p=%llu}, "
+			"udp{b=%llu, p=%llu},"
+			"other{b=%llu, p=%llu}}}, "
+			"set1{"
+			"rx{"
+			"tcp{b=%llu, p=%llu}, "
+			"udp{b=%llu, p=%llu},"
+			"other{b=%llu, p=%llu}}, "
+			"tx{"
+			"tcp{b=%llu, p=%llu}, "
+			"udp{b=%llu, p=%llu},"
+			"other{b=%llu, p=%llu}}}}",
+			dc,
+			dc->bpc[0][IFS_RX][IFS_TCP].bytes,
+			dc->bpc[0][IFS_RX][IFS_TCP].packets,
+			dc->bpc[0][IFS_RX][IFS_UDP].bytes,
+			dc->bpc[0][IFS_RX][IFS_UDP].packets,
+			dc->bpc[0][IFS_RX][IFS_PROTO_OTHER].bytes,
+			dc->bpc[0][IFS_RX][IFS_PROTO_OTHER].packets,
+			dc->bpc[0][IFS_TX][IFS_TCP].bytes,
+			dc->bpc[0][IFS_TX][IFS_TCP].packets,
+			dc->bpc[0][IFS_TX][IFS_UDP].bytes,
+			dc->bpc[0][IFS_TX][IFS_UDP].packets,
+			dc->bpc[0][IFS_TX][IFS_PROTO_OTHER].bytes,
+			dc->bpc[0][IFS_TX][IFS_PROTO_OTHER].packets,
+			dc->bpc[1][IFS_RX][IFS_TCP].bytes,
+			dc->bpc[1][IFS_RX][IFS_TCP].packets,
+			dc->bpc[1][IFS_RX][IFS_UDP].bytes,
+			dc->bpc[1][IFS_RX][IFS_UDP].packets,
+			dc->bpc[1][IFS_RX][IFS_PROTO_OTHER].bytes,
+			dc->bpc[1][IFS_RX][IFS_PROTO_OTHER].packets,
+			dc->bpc[1][IFS_TX][IFS_TCP].bytes,
+			dc->bpc[1][IFS_TX][IFS_TCP].packets,
+			dc->bpc[1][IFS_TX][IFS_UDP].bytes,
+			dc->bpc[1][IFS_TX][IFS_UDP].packets,
+			dc->bpc[1][IFS_TX][IFS_PROTO_OTHER].bytes,
+			dc->bpc[1][IFS_TX][IFS_PROTO_OTHER].packets);
+	else
+		res = kasprintf(GFP_ATOMIC, "data_counters@%p{...}", dc);
+	_bug_on_err_or_null(res);
+	return res;
+}
+
+char *pp_tag_node(struct tag_node *tn)
+{
+	char *tag_str;
+	char *res;
+
+	if (!tn) {
+		res = kasprintf(GFP_ATOMIC, "tag_node@null{}");
+		_bug_on_err_or_null(res);
+		return res;
+	}
+	tag_str = pp_tag_t(&tn->tag);
+	res = kasprintf(GFP_ATOMIC,
+			"tag_node@%p{tag=%s}",
+			tn, tag_str);
+	_bug_on_err_or_null(res);
+	kfree(tag_str);
+	return res;
+}
+
+char *pp_tag_ref(struct tag_ref *tr)
+{
+	char *tn_str;
+	char *res;
+
+	if (!tr) {
+		res = kasprintf(GFP_ATOMIC, "tag_ref@null{}");
+		_bug_on_err_or_null(res);
+		return res;
+	}
+	tn_str = pp_tag_node(&tr->tn);
+	res = kasprintf(GFP_ATOMIC,
+			"tag_ref@%p{%s, num_sock_tags=%d}",
+			tr, tn_str, tr->num_sock_tags);
+	_bug_on_err_or_null(res);
+	kfree(tn_str);
+	return res;
+}
+
+char *pp_tag_stat(struct tag_stat *ts)
+{
+	char *tn_str;
+	char *counters_str;
+	char *parent_counters_str;
+	char *res;
+
+	if (!ts) {
+		res = kasprintf(GFP_ATOMIC, "tag_stat@null{}");
+		_bug_on_err_or_null(res);
+		return res;
+	}
+	tn_str = pp_tag_node(&ts->tn);
+	counters_str = pp_data_counters(&ts->counters, true);
+	parent_counters_str = pp_data_counters(ts->parent_counters, false);
+	res = kasprintf(GFP_ATOMIC,
+			"tag_stat@%p{%s, counters=%s, parent_counters=%s}",
+			ts, tn_str, counters_str, parent_counters_str);
+	_bug_on_err_or_null(res);
+	kfree(tn_str);
+	kfree(counters_str);
+	kfree(parent_counters_str);
+	return res;
+}
+
+char *pp_iface_stat(struct iface_stat *is)
+{
+	char *res;
+	if (!is) {
+		res = kasprintf(GFP_ATOMIC, "iface_stat@null{}");
+	} else {
+		struct data_counters *cnts = &is->totals_via_skb;
+		res = kasprintf(GFP_ATOMIC, "iface_stat@%p{"
+				"list=list_head{...}, "
+				"ifname=%s, "
+				"total_dev={rx={bytes=%llu, "
+				"packets=%llu}, "
+				"tx={bytes=%llu, "
+				"packets=%llu}}, "
+				"total_skb={rx={bytes=%llu, "
+				"packets=%llu}, "
+				"tx={bytes=%llu, "
+				"packets=%llu}}, "
+				"last_known_valid=%d, "
+				"last_known={rx={bytes=%llu, "
+				"packets=%llu}, "
+				"tx={bytes=%llu, "
+				"packets=%llu}}, "
+				"active=%d, "
+				"net_dev=%p, "
+				"proc_ptr=%p, "
+				"tag_stat_tree=rb_root{...}}",
+				is,
+				is->ifname,
+				is->totals_via_dev[IFS_RX].bytes,
+				is->totals_via_dev[IFS_RX].packets,
+				is->totals_via_dev[IFS_TX].bytes,
+				is->totals_via_dev[IFS_TX].packets,
+				dc_sum_bytes(cnts, 0, IFS_RX),
+				dc_sum_packets(cnts, 0, IFS_RX),
+				dc_sum_bytes(cnts, 0, IFS_TX),
+				dc_sum_packets(cnts, 0, IFS_TX),
+				is->last_known_valid,
+				is->last_known[IFS_RX].bytes,
+				is->last_known[IFS_RX].packets,
+				is->last_known[IFS_TX].bytes,
+				is->last_known[IFS_TX].packets,
+				is->active,
+				is->net_dev,
+				is->proc_ptr);
+	}
+	_bug_on_err_or_null(res);
+	return res;
+}
+
+char *pp_sock_tag(struct sock_tag *st)
+{
+	char *tag_str;
+	char *res;
+
+	if (!st) {
+		res = kasprintf(GFP_ATOMIC, "sock_tag@null{}");
+		_bug_on_err_or_null(res);
+		return res;
+	}
+	tag_str = pp_tag_t(&st->tag);
+	res = kasprintf(GFP_ATOMIC, "sock_tag@%p{"
+			"sock_node=rb_node{...}, "
+			"sk=%p socket=%p (f_count=%lu), list=list_head{...}, "
+			"pid=%u, tag=%s}",
+			st, st->sk, st->socket, atomic_long_read(
+				&st->socket->file->f_count),
+			st->pid, tag_str);
+	_bug_on_err_or_null(res);
+	kfree(tag_str);
+	return res;
+}
+
+char *pp_uid_tag_data(struct uid_tag_data *utd)
+{
+	char *res;
+
+	if (!utd)
+		res = kasprintf(GFP_ATOMIC, "uid_tag_data@null{}");
+	else
+		res = kasprintf(GFP_ATOMIC, "uid_tag_data@%p{"
+				"uid=%u, num_active_acct_tags=%d, "
+				"num_pqd=%d, "
+				"tag_node_tree=rb_root{...}, "
+				"proc_qtu_data_tree=rb_root{...}}",
+				utd, utd->uid,
+				utd->num_active_tags, utd->num_pqd);
+	_bug_on_err_or_null(res);
+	return res;
+}
+
+char *pp_proc_qtu_data(struct proc_qtu_data *pqd)
+{
+	char *parent_tag_data_str;
+	char *res;
+
+	if (!pqd) {
+		res = kasprintf(GFP_ATOMIC, "proc_qtu_data@null{}");
+		_bug_on_err_or_null(res);
+		return res;
+	}
+	parent_tag_data_str = pp_uid_tag_data(pqd->parent_tag_data);
+	res = kasprintf(GFP_ATOMIC, "proc_qtu_data@%p{"
+			"node=rb_node{...}, pid=%u, "
+			"parent_tag_data=%s, "
+			"sock_tag_list=list_head{...}}",
+			pqd, pqd->pid, parent_tag_data_str
+		);
+	_bug_on_err_or_null(res);
+	kfree(parent_tag_data_str);
+	return res;
+}
+
+/*------------------------------------------*/
+void prdebug_sock_tag_tree(int indent_level,
+			   struct rb_root *sock_tag_tree)
+{
+	struct rb_node *node;
+	struct sock_tag *sock_tag_entry;
+	char *str;
+
+	if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+		return;
+
+	if (RB_EMPTY_ROOT(sock_tag_tree)) {
+		str = "sock_tag_tree=rb_root{}";
+		pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+		return;
+	}
+
+	str = "sock_tag_tree=rb_root{";
+	pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+	indent_level++;
+	for (node = rb_first(sock_tag_tree);
+	     node;
+	     node = rb_next(node)) {
+		sock_tag_entry = rb_entry(node, struct sock_tag, sock_node);
+		str = pp_sock_tag(sock_tag_entry);
+		pr_debug("%*d: %s,\n", indent_level*2, indent_level, str);
+		kfree(str);
+	}
+	indent_level--;
+	str = "}";
+	pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_sock_tag_list(int indent_level,
+			   struct list_head *sock_tag_list)
+{
+	struct sock_tag *sock_tag_entry;
+	char *str;
+
+	if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+		return;
+
+	if (list_empty(sock_tag_list)) {
+		str = "sock_tag_list=list_head{}";
+		pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+		return;
+	}
+
+	str = "sock_tag_list=list_head{";
+	pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+	indent_level++;
+	list_for_each_entry(sock_tag_entry, sock_tag_list, list) {
+		str = pp_sock_tag(sock_tag_entry);
+		pr_debug("%*d: %s,\n", indent_level*2, indent_level, str);
+		kfree(str);
+	}
+	indent_level--;
+	str = "}";
+	pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_proc_qtu_data_tree(int indent_level,
+				struct rb_root *proc_qtu_data_tree)
+{
+	char *str;
+	struct rb_node *node;
+	struct proc_qtu_data *proc_qtu_data_entry;
+
+	if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+		return;
+
+	if (RB_EMPTY_ROOT(proc_qtu_data_tree)) {
+		str = "proc_qtu_data_tree=rb_root{}";
+		pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+		return;
+	}
+
+	str = "proc_qtu_data_tree=rb_root{";
+	pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+	indent_level++;
+	for (node = rb_first(proc_qtu_data_tree);
+	     node;
+	     node = rb_next(node)) {
+		proc_qtu_data_entry = rb_entry(node,
+					       struct proc_qtu_data,
+					       node);
+		str = pp_proc_qtu_data(proc_qtu_data_entry);
+		pr_debug("%*d: %s,\n", indent_level*2, indent_level,
+			 str);
+		kfree(str);
+		indent_level++;
+		prdebug_sock_tag_list(indent_level,
+				      &proc_qtu_data_entry->sock_tag_list);
+		indent_level--;
+
+	}
+	indent_level--;
+	str = "}";
+	pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_tag_ref_tree(int indent_level, struct rb_root *tag_ref_tree)
+{
+	char *str;
+	struct rb_node *node;
+	struct tag_ref *tag_ref_entry;
+
+	if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+		return;
+
+	if (RB_EMPTY_ROOT(tag_ref_tree)) {
+		str = "tag_ref_tree{}";
+		pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+		return;
+	}
+
+	str = "tag_ref_tree{";
+	pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+	indent_level++;
+	for (node = rb_first(tag_ref_tree);
+	     node;
+	     node = rb_next(node)) {
+		tag_ref_entry = rb_entry(node,
+					 struct tag_ref,
+					 tn.node);
+		str = pp_tag_ref(tag_ref_entry);
+		pr_debug("%*d: %s,\n", indent_level*2, indent_level,
+			 str);
+		kfree(str);
+	}
+	indent_level--;
+	str = "}";
+	pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_uid_tag_data_tree(int indent_level,
+			       struct rb_root *uid_tag_data_tree)
+{
+	char *str;
+	struct rb_node *node;
+	struct uid_tag_data *uid_tag_data_entry;
+
+	if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+		return;
+
+	if (RB_EMPTY_ROOT(uid_tag_data_tree)) {
+		str = "uid_tag_data_tree=rb_root{}";
+		pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+		return;
+	}
+
+	str = "uid_tag_data_tree=rb_root{";
+	pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+	indent_level++;
+	for (node = rb_first(uid_tag_data_tree);
+	     node;
+	     node = rb_next(node)) {
+		uid_tag_data_entry = rb_entry(node, struct uid_tag_data,
+					      node);
+		str = pp_uid_tag_data(uid_tag_data_entry);
+		pr_debug("%*d: %s,\n", indent_level*2, indent_level, str);
+		kfree(str);
+		if (!RB_EMPTY_ROOT(&uid_tag_data_entry->tag_ref_tree)) {
+			indent_level++;
+			prdebug_tag_ref_tree(indent_level,
+					     &uid_tag_data_entry->tag_ref_tree);
+			indent_level--;
+		}
+	}
+	indent_level--;
+	str = "}";
+	pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_tag_stat_tree(int indent_level,
+				  struct rb_root *tag_stat_tree)
+{
+	char *str;
+	struct rb_node *node;
+	struct tag_stat *ts_entry;
+
+	if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+		return;
+
+	if (RB_EMPTY_ROOT(tag_stat_tree)) {
+		str = "tag_stat_tree{}";
+		pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+		return;
+	}
+
+	str = "tag_stat_tree{";
+	pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+	indent_level++;
+	for (node = rb_first(tag_stat_tree);
+	     node;
+	     node = rb_next(node)) {
+		ts_entry = rb_entry(node, struct tag_stat, tn.node);
+		str = pp_tag_stat(ts_entry);
+		pr_debug("%*d: %s\n", indent_level*2, indent_level,
+			 str);
+		kfree(str);
+	}
+	indent_level--;
+	str = "}";
+	pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+void prdebug_iface_stat_list(int indent_level,
+			     struct list_head *iface_stat_list)
+{
+	char *str;
+	struct iface_stat *iface_entry;
+
+	if (!unlikely(qtaguid_debug_mask & DDEBUG_MASK))
+		return;
+
+	if (list_empty(iface_stat_list)) {
+		str = "iface_stat_list=list_head{}";
+		pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+		return;
+	}
+
+	str = "iface_stat_list=list_head{";
+	pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+	indent_level++;
+	list_for_each_entry(iface_entry, iface_stat_list, list) {
+		str = pp_iface_stat(iface_entry);
+		pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+		kfree(str);
+
+		spin_lock_bh(&iface_entry->tag_stat_list_lock);
+		if (!RB_EMPTY_ROOT(&iface_entry->tag_stat_tree)) {
+			indent_level++;
+			prdebug_tag_stat_tree(indent_level,
+					      &iface_entry->tag_stat_tree);
+			indent_level--;
+		}
+		spin_unlock_bh(&iface_entry->tag_stat_list_lock);
+	}
+	indent_level--;
+	str = "}";
+	pr_debug("%*d: %s\n", indent_level*2, indent_level, str);
+}
+
+#endif  /* ifdef DDEBUG */
+/*------------------------------------------*/
+static const char * const netdev_event_strings[] = {
+	"netdev_unknown",
+	"NETDEV_UP",
+	"NETDEV_DOWN",
+	"NETDEV_REBOOT",
+	"NETDEV_CHANGE",
+	"NETDEV_REGISTER",
+	"NETDEV_UNREGISTER",
+	"NETDEV_CHANGEMTU",
+	"NETDEV_CHANGEADDR",
+	"NETDEV_GOING_DOWN",
+	"NETDEV_CHANGENAME",
+	"NETDEV_FEAT_CHANGE",
+	"NETDEV_BONDING_FAILOVER",
+	"NETDEV_PRE_UP",
+	"NETDEV_PRE_TYPE_CHANGE",
+	"NETDEV_POST_TYPE_CHANGE",
+	"NETDEV_POST_INIT",
+	"NETDEV_UNREGISTER_BATCH",
+	"NETDEV_RELEASE",
+	"NETDEV_NOTIFY_PEERS",
+	"NETDEV_JOIN",
+};
+
+const char *netdev_evt_str(int netdev_event)
+{
+	if (netdev_event < 0
+	    || netdev_event >= ARRAY_SIZE(netdev_event_strings))
+		return "bad event num";
+	return netdev_event_strings[netdev_event];
+}
diff --git a/net/netfilter/xt_qtaguid_print.h b/net/netfilter/xt_qtaguid_print.h
new file mode 100644
index 00000000000..b63871a0be5
--- /dev/null
+++ b/net/netfilter/xt_qtaguid_print.h
@@ -0,0 +1,120 @@
+/*
+ * Pretty printing Support for iptables xt_qtaguid module.
+ *
+ * (C) 2011 Google, Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __XT_QTAGUID_PRINT_H__
+#define __XT_QTAGUID_PRINT_H__
+
+#include "xt_qtaguid_internal.h"
+
+#ifdef DDEBUG
+
+char *pp_tag_t(tag_t *tag);
+char *pp_data_counters(struct data_counters *dc, bool showValues);
+char *pp_tag_node(struct tag_node *tn);
+char *pp_tag_ref(struct tag_ref *tr);
+char *pp_tag_stat(struct tag_stat *ts);
+char *pp_iface_stat(struct iface_stat *is);
+char *pp_sock_tag(struct sock_tag *st);
+char *pp_uid_tag_data(struct uid_tag_data *qtd);
+char *pp_proc_qtu_data(struct proc_qtu_data *pqd);
+
+/*------------------------------------------*/
+void prdebug_sock_tag_list(int indent_level,
+			   struct list_head *sock_tag_list);
+void prdebug_sock_tag_tree(int indent_level,
+			   struct rb_root *sock_tag_tree);
+void prdebug_proc_qtu_data_tree(int indent_level,
+				struct rb_root *proc_qtu_data_tree);
+void prdebug_tag_ref_tree(int indent_level, struct rb_root *tag_ref_tree);
+void prdebug_uid_tag_data_tree(int indent_level,
+			       struct rb_root *uid_tag_data_tree);
+void prdebug_tag_stat_tree(int indent_level,
+			   struct rb_root *tag_stat_tree);
+void prdebug_iface_stat_list(int indent_level,
+			     struct list_head *iface_stat_list);
+
+#else
+
+/*------------------------------------------*/
+static inline char *pp_tag_t(tag_t *tag)
+{
+	return NULL;
+}
+static inline char *pp_data_counters(struct data_counters *dc, bool showValues)
+{
+	return NULL;
+}
+static inline char *pp_tag_node(struct tag_node *tn)
+{
+	return NULL;
+}
+static inline char *pp_tag_ref(struct tag_ref *tr)
+{
+	return NULL;
+}
+static inline char *pp_tag_stat(struct tag_stat *ts)
+{
+	return NULL;
+}
+static inline char *pp_iface_stat(struct iface_stat *is)
+{
+	return NULL;
+}
+static inline char *pp_sock_tag(struct sock_tag *st)
+{
+	return NULL;
+}
+static inline char *pp_uid_tag_data(struct uid_tag_data *qtd)
+{
+	return NULL;
+}
+static inline char *pp_proc_qtu_data(struct proc_qtu_data *pqd)
+{
+	return NULL;
+}
+
+/*------------------------------------------*/
+static inline
+void prdebug_sock_tag_list(int indent_level,
+			   struct list_head *sock_tag_list)
+{
+}
+static inline
+void prdebug_sock_tag_tree(int indent_level,
+			   struct rb_root *sock_tag_tree)
+{
+}
+static inline
+void prdebug_proc_qtu_data_tree(int indent_level,
+				struct rb_root *proc_qtu_data_tree)
+{
+}
+static inline
+void prdebug_tag_ref_tree(int indent_level, struct rb_root *tag_ref_tree)
+{
+}
+static inline
+void prdebug_uid_tag_data_tree(int indent_level,
+			       struct rb_root *uid_tag_data_tree)
+{
+}
+static inline
+void prdebug_tag_stat_tree(int indent_level,
+			   struct rb_root *tag_stat_tree)
+{
+}
+static inline
+void prdebug_iface_stat_list(int indent_level,
+			     struct list_head *iface_stat_list)
+{
+}
+#endif
+/*------------------------------------------*/
+const char *netdev_evt_str(int netdev_event);
+#endif  /* ifndef __XT_QTAGUID_PRINT_H__ */
diff --git a/net/netfilter/xt_quota2.c b/net/netfilter/xt_quota2.c
new file mode 100644
index 00000000000..99592ae56d9
--- /dev/null
+++ b/net/netfilter/xt_quota2.c
@@ -0,0 +1,382 @@
+/*
+ * xt_quota2 - enhanced xt_quota that can count upwards and in packets
+ * as a minimal accounting match.
+ * by Jan Engelhardt <jengelh@medozas.de>, 2008
+ *
+ * Originally based on xt_quota.c:
+ * 	netfilter module to enforce network quotas
+ * 	Sam Johnston <samj@samj.net>
+ *
+ *	This program is free software; you can redistribute it and/or modify
+ *	it under the terms of the GNU General Public License; either
+ *	version 2 of the License, as published by the Free Software Foundation.
+ */
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/skbuff.h>
+#include <linux/spinlock.h>
+#include <asm/atomic.h>
+#include <net/netlink.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_quota2.h>
+#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG
+#include <linux/netfilter_ipv4/ipt_ULOG.h>
+#endif
+
+/**
+ * @lock:	lock to protect quota writers from each other
+ */
+struct xt_quota_counter {
+	u_int64_t quota;
+	spinlock_t lock;
+	struct list_head list;
+	atomic_t ref;
+	char name[sizeof(((struct xt_quota_mtinfo2 *)NULL)->name)];
+	struct proc_dir_entry *procfs_entry;
+};
+
+#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG
+/* Harald's favorite number +1 :D From ipt_ULOG.C */
+static int qlog_nl_event = 112;
+module_param_named(event_num, qlog_nl_event, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(event_num,
+		 "Event number for NETLINK_NFLOG message. 0 disables log."
+		 "111 is what ipt_ULOG uses.");
+static struct sock *nflognl;
+#endif
+
+static LIST_HEAD(counter_list);
+static DEFINE_SPINLOCK(counter_list_lock);
+
+static struct proc_dir_entry *proc_xt_quota;
+static unsigned int quota_list_perms = S_IRUGO | S_IWUSR;
+static kuid_t quota_list_uid = KUIDT_INIT(0);
+static kgid_t quota_list_gid = KGIDT_INIT(0);
+module_param_named(perms, quota_list_perms, uint, S_IRUGO | S_IWUSR);
+
+#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG
+static void quota2_log(unsigned int hooknum,
+		       const struct sk_buff *skb,
+		       const struct net_device *in,
+		       const struct net_device *out,
+		       const char *prefix)
+{
+	ulog_packet_msg_t *pm;
+	struct sk_buff *log_skb;
+	size_t size;
+	struct nlmsghdr *nlh;
+
+	if (!qlog_nl_event)
+		return;
+
+	size = NLMSG_SPACE(sizeof(*pm));
+	size = max(size, (size_t)NLMSG_GOODSIZE);
+	log_skb = alloc_skb(size, GFP_ATOMIC);
+	if (!log_skb) {
+		pr_err("xt_quota2: cannot alloc skb for logging\n");
+		return;
+	}
+
+	nlh = nlmsg_put(log_skb, /*pid*/0, /*seq*/0, qlog_nl_event,
+			sizeof(*pm), 0);
+	if (!nlh) {
+		pr_err("xt_quota2: nlmsg_put failed\n");
+		kfree_skb(log_skb);
+		return;
+	}
+	pm = nlmsg_data(nlh);
+	if (skb->tstamp.tv64 == 0)
+		__net_timestamp((struct sk_buff *)skb);
+	pm->data_len = 0;
+	pm->hook = hooknum;
+	if (prefix != NULL)
+		strlcpy(pm->prefix, prefix, sizeof(pm->prefix));
+	else
+		*(pm->prefix) = '\0';
+	if (in)
+		strlcpy(pm->indev_name, in->name, sizeof(pm->indev_name));
+	else
+		pm->indev_name[0] = '\0';
+
+	if (out)
+		strlcpy(pm->outdev_name, out->name, sizeof(pm->outdev_name));
+	else
+		pm->outdev_name[0] = '\0';
+
+	NETLINK_CB(log_skb).dst_group = 1;
+	pr_debug("throwing 1 packets to netlink group 1\n");
+	netlink_broadcast(nflognl, log_skb, 0, 1, GFP_ATOMIC);
+}
+#else
+static void quota2_log(unsigned int hooknum,
+		       const struct sk_buff *skb,
+		       const struct net_device *in,
+		       const struct net_device *out,
+		       const char *prefix)
+{
+}
+#endif  /* if+else CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG */
+
+static ssize_t quota_proc_read(struct file *file, char __user *buf,
+			   size_t size, loff_t *ppos)
+{
+	struct xt_quota_counter *e = PDE_DATA(file_inode(file));
+	char tmp[24];
+	size_t tmp_size;
+
+	spin_lock_bh(&e->lock);
+	tmp_size = scnprintf(tmp, sizeof(tmp), "%llu\n", e->quota);
+	spin_unlock_bh(&e->lock);
+	return simple_read_from_buffer(buf, size, ppos, tmp, tmp_size);
+}
+
+static ssize_t quota_proc_write(struct file *file, const char __user *input,
+                            size_t size, loff_t *ppos)
+{
+	struct xt_quota_counter *e = PDE_DATA(file_inode(file));
+	char buf[sizeof("18446744073709551616")];
+
+	if (size > sizeof(buf))
+		size = sizeof(buf);
+	if (copy_from_user(buf, input, size) != 0)
+		return -EFAULT;
+	buf[sizeof(buf)-1] = '\0';
+
+	spin_lock_bh(&e->lock);
+	e->quota = simple_strtoull(buf, NULL, 0);
+	spin_unlock_bh(&e->lock);
+	return size;
+}
+
+static const struct file_operations q2_counter_fops = {
+	.read		= quota_proc_read,
+	.write		= quota_proc_write,
+	.llseek		= default_llseek,
+};
+
+static struct xt_quota_counter *
+q2_new_counter(const struct xt_quota_mtinfo2 *q, bool anon)
+{
+	struct xt_quota_counter *e;
+	unsigned int size;
+
+	/* Do not need all the procfs things for anonymous counters. */
+	size = anon ? offsetof(typeof(*e), list) : sizeof(*e);
+	e = kmalloc(size, GFP_KERNEL);
+	if (e == NULL)
+		return NULL;
+
+	e->quota = q->quota;
+	spin_lock_init(&e->lock);
+	if (!anon) {
+		INIT_LIST_HEAD(&e->list);
+		atomic_set(&e->ref, 1);
+		strlcpy(e->name, q->name, sizeof(e->name));
+	}
+	return e;
+}
+
+/**
+ * q2_get_counter - get ref to counter or create new
+ * @name:	name of counter
+ */
+static struct xt_quota_counter *
+q2_get_counter(const struct xt_quota_mtinfo2 *q)
+{
+	struct proc_dir_entry *p;
+	struct xt_quota_counter *e = NULL;
+	struct xt_quota_counter *new_e;
+
+	if (*q->name == '\0')
+		return q2_new_counter(q, true);
+
+	/* No need to hold a lock while getting a new counter */
+	new_e = q2_new_counter(q, false);
+	if (new_e == NULL)
+		goto out;
+
+	spin_lock_bh(&counter_list_lock);
+	list_for_each_entry(e, &counter_list, list)
+		if (strcmp(e->name, q->name) == 0) {
+			atomic_inc(&e->ref);
+			spin_unlock_bh(&counter_list_lock);
+			kfree(new_e);
+			pr_debug("xt_quota2: old counter name=%s", e->name);
+			return e;
+		}
+	e = new_e;
+	pr_debug("xt_quota2: new_counter name=%s", e->name);
+	list_add_tail(&e->list, &counter_list);
+	/* The entry having a refcount of 1 is not directly destructible.
+	 * This func has not yet returned the new entry, thus iptables
+	 * has not references for destroying this entry.
+	 * For another rule to try to destroy it, it would 1st need for this
+	 * func* to be re-invoked, acquire a new ref for the same named quota.
+	 * Nobody will access the e->procfs_entry either.
+	 * So release the lock. */
+	spin_unlock_bh(&counter_list_lock);
+
+	/* create_proc_entry() is not spin_lock happy */
+	p = e->procfs_entry = proc_create_data(e->name, quota_list_perms,
+	                      proc_xt_quota, &q2_counter_fops, e);
+
+	if (IS_ERR_OR_NULL(p)) {
+		spin_lock_bh(&counter_list_lock);
+		list_del(&e->list);
+		spin_unlock_bh(&counter_list_lock);
+		goto out;
+	}
+	proc_set_user(p, quota_list_uid, quota_list_gid);
+	return e;
+
+ out:
+	kfree(e);
+	return NULL;
+}
+
+static int quota_mt2_check(const struct xt_mtchk_param *par)
+{
+	struct xt_quota_mtinfo2 *q = par->matchinfo;
+
+	pr_debug("xt_quota2: check() flags=0x%04x", q->flags);
+
+	if (q->flags & ~XT_QUOTA_MASK)
+		return -EINVAL;
+
+	q->name[sizeof(q->name)-1] = '\0';
+	if (*q->name == '.' || strchr(q->name, '/') != NULL) {
+		printk(KERN_ERR "xt_quota.3: illegal name\n");
+		return -EINVAL;
+	}
+
+	q->master = q2_get_counter(q);
+	if (q->master == NULL) {
+		printk(KERN_ERR "xt_quota.3: memory alloc failure\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void quota_mt2_destroy(const struct xt_mtdtor_param *par)
+{
+	struct xt_quota_mtinfo2 *q = par->matchinfo;
+	struct xt_quota_counter *e = q->master;
+
+	if (*q->name == '\0') {
+		kfree(e);
+		return;
+	}
+
+	spin_lock_bh(&counter_list_lock);
+	if (!atomic_dec_and_test(&e->ref)) {
+		spin_unlock_bh(&counter_list_lock);
+		return;
+	}
+
+	list_del(&e->list);
+	remove_proc_entry(e->name, proc_xt_quota);
+	spin_unlock_bh(&counter_list_lock);
+	kfree(e);
+}
+
+static bool
+quota_mt2(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	struct xt_quota_mtinfo2 *q = (void *)par->matchinfo;
+	struct xt_quota_counter *e = q->master;
+	bool ret = q->flags & XT_QUOTA_INVERT;
+
+	spin_lock_bh(&e->lock);
+	if (q->flags & XT_QUOTA_GROW) {
+		/*
+		 * While no_change is pointless in "grow" mode, we will
+		 * implement it here simply to have a consistent behavior.
+		 */
+		if (!(q->flags & XT_QUOTA_NO_CHANGE)) {
+			e->quota += (q->flags & XT_QUOTA_PACKET) ? 1 : skb->len;
+		}
+		ret = true;
+	} else {
+		if (e->quota >= skb->len) {
+			if (!(q->flags & XT_QUOTA_NO_CHANGE))
+				e->quota -= (q->flags & XT_QUOTA_PACKET) ? 1 : skb->len;
+			ret = !ret;
+		} else {
+			/* We are transitioning, log that fact. */
+			if (e->quota) {
+				quota2_log(par->hooknum,
+					   skb,
+					   par->in,
+					   par->out,
+					   q->name);
+			}
+			/* we do not allow even small packets from now on */
+			e->quota = 0;
+		}
+	}
+	spin_unlock_bh(&e->lock);
+	return ret;
+}
+
+static struct xt_match quota_mt2_reg[] __read_mostly = {
+	{
+		.name       = "quota2",
+		.revision   = 3,
+		.family     = NFPROTO_IPV4,
+		.checkentry = quota_mt2_check,
+		.match      = quota_mt2,
+		.destroy    = quota_mt2_destroy,
+		.matchsize  = sizeof(struct xt_quota_mtinfo2),
+		.me         = THIS_MODULE,
+	},
+	{
+		.name       = "quota2",
+		.revision   = 3,
+		.family     = NFPROTO_IPV6,
+		.checkentry = quota_mt2_check,
+		.match      = quota_mt2,
+		.destroy    = quota_mt2_destroy,
+		.matchsize  = sizeof(struct xt_quota_mtinfo2),
+		.me         = THIS_MODULE,
+	},
+};
+
+static int __init quota_mt2_init(void)
+{
+	int ret;
+	pr_debug("xt_quota2: init()");
+
+#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG
+	nflognl = netlink_kernel_create(&init_net, NETLINK_NFLOG, NULL);
+	if (!nflognl)
+		return -ENOMEM;
+#endif
+
+	proc_xt_quota = proc_mkdir("xt_quota", init_net.proc_net);
+	if (proc_xt_quota == NULL)
+		return -EACCES;
+
+	ret = xt_register_matches(quota_mt2_reg, ARRAY_SIZE(quota_mt2_reg));
+	if (ret < 0)
+		remove_proc_entry("xt_quota", init_net.proc_net);
+	pr_debug("xt_quota2: init() %d", ret);
+	return ret;
+}
+
+static void __exit quota_mt2_exit(void)
+{
+	xt_unregister_matches(quota_mt2_reg, ARRAY_SIZE(quota_mt2_reg));
+	remove_proc_entry("xt_quota", init_net.proc_net);
+}
+
+module_init(quota_mt2_init);
+module_exit(quota_mt2_exit);
+MODULE_DESCRIPTION("Xtables: countdown quota match; up counter");
+MODULE_AUTHOR("Sam Johnston <samj@samj.net>");
+MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("ipt_quota2");
+MODULE_ALIAS("ip6t_quota2");
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 1ba67931eb1..7eb9d7d534d 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -129,9 +129,10 @@ xt_socket_get_sock_v4(struct net *net, const u8 protocol,
 	return NULL;
 }
 
-static bool
-socket_match(const struct sk_buff *skb, struct xt_action_param *par,
-	     const struct xt_socket_mtinfo1 *info)
+
+
+struct sock*
+xt_socket_get4_sk(const struct sk_buff *skb, struct xt_action_param *par)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct udphdr _hdr, *hp = NULL;
@@ -148,7 +149,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
 		hp = skb_header_pointer(skb, ip_hdrlen(skb),
 					sizeof(_hdr), &_hdr);
 		if (hp == NULL)
-			return false;
+			return NULL;
 
 		protocol = iph->protocol;
 		saddr = iph->saddr;
@@ -159,9 +160,9 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
 	} else if (iph->protocol == IPPROTO_ICMP) {
 		if (extract_icmp4_fields(skb, &protocol, &saddr, &daddr,
 					&sport, &dport))
-			return false;
+			return NULL;
 	} else {
-		return false;
+		return NULL;
 	}
 
 #ifdef XT_SOCKET_HAVE_CONNTRACK
@@ -187,6 +188,24 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
 		sk = xt_socket_get_sock_v4(dev_net(skb->dev), protocol,
 					   saddr, daddr, sport, dport,
 					   par->in);
+
+	pr_debug("proto %hhu %pI4:%hu -> %pI4:%hu (orig %pI4:%hu) sock %p\n",
+		 protocol, &saddr, ntohs(sport),
+		 &daddr, ntohs(dport),
+		 &iph->daddr, hp ? ntohs(hp->dest) : 0, sk);
+
+	return sk;
+}
+EXPORT_SYMBOL(xt_socket_get4_sk);
+
+static bool
+socket_match(const struct sk_buff *skb, struct xt_action_param *par,
+	     const struct xt_socket_mtinfo1 *info)
+{
+	struct sock *sk;
+
+	sk = xt_socket_get4_sk(skb, par);
+
 	if (sk) {
 		bool wildcard;
 		bool transparent = true;
@@ -213,11 +232,6 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
 			sk = NULL;
 	}
 
-	pr_debug("proto %hhu %pI4:%hu -> %pI4:%hu (orig %pI4:%hu) sock %p\n",
-		 protocol, &saddr, ntohs(sport),
-		 &daddr, ntohs(dport),
-		 &iph->daddr, hp ? ntohs(hp->dest) : 0, sk);
-
 	return (sk != NULL);
 }
 
@@ -312,8 +326,8 @@ xt_socket_get_sock_v6(struct net *net, const u8 protocol,
 	return NULL;
 }
 
-static bool
-socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
+struct sock*
+xt_socket_get6_sk(const struct sk_buff *skb, struct xt_action_param *par)
 {
 	struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct udphdr _hdr, *hp = NULL;
@@ -321,7 +335,6 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
 	struct in6_addr *daddr = NULL, *saddr = NULL;
 	__be16 uninitialized_var(dport), uninitialized_var(sport);
 	int thoff = 0, uninitialized_var(tproto);
-	const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo;
 
 	tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
 	if (tproto < 0) {
@@ -333,7 +346,7 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
 		hp = skb_header_pointer(skb, thoff,
 					sizeof(_hdr), &_hdr);
 		if (hp == NULL)
-			return false;
+			return NULL;
 
 		saddr = &iph->saddr;
 		sport = hp->source;
@@ -343,15 +356,35 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
 	} else if (tproto == IPPROTO_ICMPV6) {
 		if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr,
 					 &sport, &dport))
-			return false;
+			return NULL;
 	} else {
-		return false;
+		return NULL;
 	}
 
 	if (!sk)
 		sk = xt_socket_get_sock_v6(dev_net(skb->dev), tproto,
 					   saddr, daddr, sport, dport,
 					   par->in);
+
+	pr_debug("proto %hhd %pI6:%hu -> %pI6:%hu "
+		 "(orig %pI6:%hu) sock %p\n",
+		 tproto, saddr, ntohs(sport),
+		 daddr, ntohs(dport),
+		 &iph->daddr, hp ? ntohs(hp->dest) : 0, sk);
+	return sk;
+}
+EXPORT_SYMBOL(xt_socket_get6_sk);
+
+static bool
+socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	struct sock *sk;
+	const struct xt_socket_mtinfo1 *info;
+
+	info = (struct xt_socket_mtinfo1 *) par->matchinfo;
+
+	sk = xt_socket_get6_sk(skb, par);
+
 	if (sk) {
 		bool wildcard;
 		bool transparent = true;
@@ -378,12 +411,6 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
 			sk = NULL;
 	}
 
-	pr_debug("proto %hhd %pI6:%hu -> %pI6:%hu "
-		 "(orig %pI6:%hu) sock %p\n",
-		 tproto, saddr, ntohs(sport),
-		 daddr, ntohs(dport),
-		 &iph->daddr, hp ? ntohs(hp->dest) : 0, sk);
-
 	return (sk != NULL);
 }
 #endif
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index a845cd4cf21..28cddc85b70 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -1065,10 +1065,12 @@ int netlbl_skbuff_getattr(const struct sk_buff *skb,
 			  u16 family,
 			  struct netlbl_lsm_secattr *secattr)
 {
+	unsigned char *ptr;
+
 	switch (family) {
 	case AF_INET:
-		if (CIPSO_V4_OPTEXIST(skb) &&
-		    cipso_v4_skbuff_getattr(skb, secattr) == 0)
+		ptr = cipso_v4_optptr(skb);
+		if (ptr && cipso_v4_getattr(ptr, secattr) == 0)
 			return 0;
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
@@ -1094,7 +1096,7 @@ int netlbl_skbuff_getattr(const struct sk_buff *skb,
  */
 void netlbl_skbuff_err(struct sk_buff *skb, int error, int gateway)
 {
-	if (CIPSO_V4_OPTEXIST(skb))
+	if (cipso_v4_optptr(skb))
 		cipso_v4_error(skb, error, gateway);
 }
 
@@ -1126,11 +1128,14 @@ void netlbl_cache_invalidate(void)
 int netlbl_cache_add(const struct sk_buff *skb,
 		     const struct netlbl_lsm_secattr *secattr)
 {
+	unsigned char *ptr;
+
 	if ((secattr->flags & NETLBL_SECATTR_CACHE) == 0)
 		return -ENOMSG;
 
-	if (CIPSO_V4_OPTEXIST(skb))
-		return cipso_v4_cache_add(skb, secattr);
+	ptr = cipso_v4_optptr(skb);
+	if (ptr)
+		return cipso_v4_cache_add(ptr, secattr);
 
 	return -ENOMSG;
 }
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 0007b818039..c82b2e37e65 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -526,14 +526,14 @@ out:
 	return err;
 }
 
-static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr)
+static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr, unsigned int nm_len)
 {
 #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1
 	struct page *p_start, *p_end;
 
 	/* First page is flushed through netlink_{get,set}_status */
 	p_start = pgvec_to_page(hdr + PAGE_SIZE);
-	p_end   = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + hdr->nm_len - 1);
+	p_end   = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + nm_len - 1);
 	while (p_start <= p_end) {
 		flush_dcache_page(p_start);
 		p_start++;
@@ -551,9 +551,9 @@ static enum nl_mmap_status netlink_get_status(const struct nl_mmap_hdr *hdr)
 static void netlink_set_status(struct nl_mmap_hdr *hdr,
 			       enum nl_mmap_status status)
 {
+	smp_mb();
 	hdr->nm_status = status;
 	flush_dcache_page(pgvec_to_page(hdr));
-	smp_wmb();
 }
 
 static struct nl_mmap_hdr *
@@ -715,24 +715,16 @@ static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg,
 	struct nl_mmap_hdr *hdr;
 	struct sk_buff *skb;
 	unsigned int maxlen;
-	bool excl = true;
 	int err = 0, len = 0;
 
-	/* Netlink messages are validated by the receiver before processing.
-	 * In order to avoid userspace changing the contents of the message
-	 * after validation, the socket and the ring may only be used by a
-	 * single process, otherwise we fall back to copying.
-	 */
-	if (atomic_long_read(&sk->sk_socket->file->f_count) > 1 ||
-	    atomic_read(&nlk->mapped) > 1)
-		excl = false;
-
 	mutex_lock(&nlk->pg_vec_lock);
 
 	ring   = &nlk->tx_ring;
 	maxlen = ring->frame_size - NL_MMAP_HDRLEN;
 
 	do {
+		unsigned int nm_len;
+
 		hdr = netlink_current_frame(ring, NL_MMAP_STATUS_VALID);
 		if (hdr == NULL) {
 			if (!(msg->msg_flags & MSG_DONTWAIT) &&
@@ -740,35 +732,23 @@ static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg,
 				schedule();
 			continue;
 		}
-		if (hdr->nm_len > maxlen) {
+
+		nm_len = ACCESS_ONCE(hdr->nm_len);
+		if (nm_len > maxlen) {
 			err = -EINVAL;
 			goto out;
 		}
 
-		netlink_frame_flush_dcache(hdr);
+		netlink_frame_flush_dcache(hdr, nm_len);
 
-		if (likely(dst_portid == 0 && dst_group == 0 && excl)) {
-			skb = alloc_skb_head(GFP_KERNEL);
-			if (skb == NULL) {
-				err = -ENOBUFS;
-				goto out;
-			}
-			sock_hold(sk);
-			netlink_ring_setup_skb(skb, sk, ring, hdr);
-			NETLINK_CB(skb).flags |= NETLINK_SKB_TX;
-			__skb_put(skb, hdr->nm_len);
-			netlink_set_status(hdr, NL_MMAP_STATUS_RESERVED);
-			atomic_inc(&ring->pending);
-		} else {
-			skb = alloc_skb(hdr->nm_len, GFP_KERNEL);
-			if (skb == NULL) {
-				err = -ENOBUFS;
-				goto out;
-			}
-			__skb_put(skb, hdr->nm_len);
-			memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, hdr->nm_len);
-			netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED);
+		skb = alloc_skb(nm_len, GFP_KERNEL);
+		if (skb == NULL) {
+			err = -ENOBUFS;
+			goto out;
 		}
+		__skb_put(skb, nm_len);
+		memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, nm_len);
+		netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED);
 
 		netlink_increment_head(ring);
 
@@ -814,7 +794,7 @@ static void netlink_queue_mmaped_skb(struct sock *sk, struct sk_buff *skb)
 	hdr->nm_pid	= NETLINK_CB(skb).creds.pid;
 	hdr->nm_uid	= from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid);
 	hdr->nm_gid	= from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid);
-	netlink_frame_flush_dcache(hdr);
+	netlink_frame_flush_dcache(hdr, hdr->nm_len);
 	netlink_set_status(hdr, NL_MMAP_STATUS_VALID);
 
 	NETLINK_CB(skb).flags |= NETLINK_SKB_DELIVERED;
@@ -1023,11 +1003,8 @@ static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid,
 		.net = net,
 		.portid = portid,
 	};
-	u32 hash;
 
-	hash = rhashtable_hashfn(&table->hash, &portid, sizeof(portid));
-
-	return rhashtable_lookup_compare(&table->hash, hash,
+	return rhashtable_lookup_compare(&table->hash, &portid,
 					 &netlink_compare, &arg);
 }
 
@@ -1619,13 +1596,11 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size,
 	if (data == NULL)
 		return NULL;
 
-	skb = build_skb(data, size);
+	skb = __build_skb(data, size);
 	if (skb == NULL)
 		vfree(data);
-	else {
-		skb->head_frag = 0;
+	else
 		skb->destructor = netlink_skb_destructor;
-	}
 
 	return skb;
 }
@@ -3130,7 +3105,7 @@ static int __init netlink_proto_init(void)
 		.head_offset = offsetof(struct netlink_sock, node),
 		.key_offset = offsetof(struct netlink_sock, portid),
 		.key_len = sizeof(u32), /* portid */
-		.hashfn = arch_fast_hash,
+		.hashfn = jhash,
 		.max_shift = 16, /* 64K */
 		.grow_decision = rht_grow_above_75,
 		.shrink_decision = rht_shrink_below_30,
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 8c4229b11c3..4107eae4f45 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -184,7 +184,9 @@ static int push_vlan(struct sk_buff *skb, const struct ovs_action_push_vlan *vla
 		/* push down current VLAN tag */
 		current_tag = vlan_tx_tag_get(skb);
 
-		if (!__vlan_put_tag(skb, skb->vlan_proto, current_tag))
+		skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
+						current_tag);
+		if (!skb)
 			return -ENOMEM;
 
 		if (skb->ip_summed == CHECKSUM_COMPLETE)
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index f9e556b5608..28213dff723 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -423,11 +423,10 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 		if (!nskb)
 			return -ENOMEM;
 
-		nskb = __vlan_put_tag(nskb, nskb->vlan_proto, vlan_tx_tag_get(nskb));
+		nskb = __vlan_hwaccel_push_inside(nskb);
 		if (!nskb)
 			return -ENOMEM;
 
-		nskb->vlan_tci = 0;
 		skb = nskb;
 	}
 
@@ -2060,14 +2059,55 @@ static int __net_init ovs_init_net(struct net *net)
 	return 0;
 }
 
-static void __net_exit ovs_exit_net(struct net *net)
+static void __net_exit list_vports_from_net(struct net *net, struct net *dnet,
+					    struct list_head *head)
 {
-	struct datapath *dp, *dp_next;
 	struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
+	struct datapath *dp;
+
+	list_for_each_entry(dp, &ovs_net->dps, list_node) {
+		int i;
+
+		for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) {
+			struct vport *vport;
+
+			hlist_for_each_entry(vport, &dp->ports[i], dp_hash_node) {
+				struct netdev_vport *netdev_vport;
+
+				if (vport->ops->type != OVS_VPORT_TYPE_INTERNAL)
+					continue;
+
+				netdev_vport = netdev_vport_priv(vport);
+				if (dev_net(netdev_vport->dev) == dnet)
+					list_add(&vport->detach_list, head);
+			}
+		}
+	}
+}
+
+static void __net_exit ovs_exit_net(struct net *dnet)
+{
+	struct datapath *dp, *dp_next;
+	struct ovs_net *ovs_net = net_generic(dnet, ovs_net_id);
+	struct vport *vport, *vport_next;
+	struct net *net;
+	LIST_HEAD(head);
 
 	ovs_lock();
 	list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node)
 		__dp_destroy(dp);
+
+	rtnl_lock();
+	for_each_net(net)
+		list_vports_from_net(net, dnet, &head);
+	rtnl_unlock();
+
+	/* Detach all vports from given namespace. */
+	list_for_each_entry_safe(vport, vport_next, &head, detach_list) {
+		list_del(&vport->detach_list);
+		ovs_dp_detach_port(vport);
+	}
+
 	ovs_unlock();
 
 	cancel_work_sync(&ovs_net->dp_notify_work);
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 089b195c064..918e96645b0 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -145,7 +145,7 @@ static bool match_validate(const struct sw_flow_match *match,
 	if (match->key->eth.type == htons(ETH_P_ARP)
 			|| match->key->eth.type == htons(ETH_P_RARP)) {
 		key_expected |= 1 << OVS_KEY_ATTR_ARP;
-		if (match->mask && (match->mask->key.tp.src == htons(0xff)))
+		if (match->mask && (match->mask->key.eth.type == htons(0xffff)))
 			mask_allowed |= 1 << OVS_KEY_ATTR_ARP;
 	}
 
@@ -220,7 +220,7 @@ static bool match_validate(const struct sw_flow_match *match,
 						htons(NDISC_NEIGHBOUR_SOLICITATION) ||
 				    match->key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
 					key_expected |= 1 << OVS_KEY_ATTR_ND;
-					if (match->mask && (match->mask->key.tp.src == htons(0xffff)))
+					if (match->mask && (match->mask->key.tp.src == htons(0xff)))
 						mask_allowed |= 1 << OVS_KEY_ATTR_ND;
 				}
 			}
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index 108b82da2fd..e88fa34b004 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -172,14 +172,10 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
 			goto err_free_rt;
 	}
 
-	if (vlan_tx_tag_present(skb)) {
-		if (unlikely(!__vlan_put_tag(skb,
-					     skb->vlan_proto,
-					     vlan_tx_tag_get(skb)))) {
-			err = -ENOMEM;
-			goto err_free_rt;
-		}
-		skb->vlan_tci = 0;
+	skb = vlan_hwaccel_push_inside(skb);
+	if (unlikely(!skb)) {
+		err = -ENOMEM;
+		goto err_free_rt;
 	}
 
 	/* Push Tunnel header. */
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index 8942125de3a..ab01c65fb3d 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -93,6 +93,7 @@ struct vport_portids {
  * @ops: Class structure.
  * @percpu_stats: Points to per-CPU statistics used and maintained by vport
  * @err_stats: Points to error statistics used and maintained by vport
+ * @detach_list: list used for detaching vport in net-exit call.
  */
 struct vport {
 	struct rcu_head rcu;
@@ -107,6 +108,7 @@ struct vport {
 	struct pcpu_sw_netstats __percpu *percpu_stats;
 
 	struct vport_err_stats err_stats;
+	struct list_head detach_list;
 };
 
 /**
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 07c04a841ba..5dcfe05ea23 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1255,16 +1255,6 @@ static void packet_sock_destruct(struct sock *sk)
 	sk_refcnt_debug_dec(sk);
 }
 
-static int fanout_rr_next(struct packet_fanout *f, unsigned int num)
-{
-	int x = atomic_read(&f->rr_cur) + 1;
-
-	if (x >= num)
-		x = 0;
-
-	return x;
-}
-
 static unsigned int fanout_demux_hash(struct packet_fanout *f,
 				      struct sk_buff *skb,
 				      unsigned int num)
@@ -1276,13 +1266,9 @@ static unsigned int fanout_demux_lb(struct packet_fanout *f,
 				    struct sk_buff *skb,
 				    unsigned int num)
 {
-	int cur, old;
+	unsigned int val = atomic_inc_return(&f->rr_cur);
 
-	cur = atomic_read(&f->rr_cur);
-	while ((old = atomic_cmpxchg(&f->rr_cur, cur,
-				     fanout_rr_next(f, num))) != cur)
-		cur = old;
-	return cur;
+	return val % num;
 }
 
 static unsigned int fanout_demux_cpu(struct packet_fanout *f,
@@ -1336,7 +1322,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 			     struct packet_type *pt, struct net_device *orig_dev)
 {
 	struct packet_fanout *f = pt->af_packet_priv;
-	unsigned int num = f->num_members;
+	unsigned int num = READ_ONCE(f->num_members);
 	struct packet_sock *po;
 	unsigned int idx;
 
diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c
index a817705ce2d..dba8d0864f1 100644
--- a/net/rds/iw_rdma.c
+++ b/net/rds/iw_rdma.c
@@ -88,7 +88,9 @@ static unsigned int rds_iw_unmap_fastreg_list(struct rds_iw_mr_pool *pool,
 			int *unpinned);
 static void rds_iw_destroy_fastreg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr);
 
-static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwdev, struct rdma_cm_id **cm_id)
+static int rds_iw_get_device(struct sockaddr_in *src, struct sockaddr_in *dst,
+			     struct rds_iw_device **rds_iwdev,
+			     struct rdma_cm_id **cm_id)
 {
 	struct rds_iw_device *iwdev;
 	struct rds_iw_cm_id *i_cm_id;
@@ -112,15 +114,15 @@ static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwd
 				src_addr->sin_port,
 				dst_addr->sin_addr.s_addr,
 				dst_addr->sin_port,
-				rs->rs_bound_addr,
-				rs->rs_bound_port,
-				rs->rs_conn_addr,
-				rs->rs_conn_port);
+				src->sin_addr.s_addr,
+				src->sin_port,
+				dst->sin_addr.s_addr,
+				dst->sin_port);
 #ifdef WORKING_TUPLE_DETECTION
-			if (src_addr->sin_addr.s_addr == rs->rs_bound_addr &&
-			    src_addr->sin_port == rs->rs_bound_port &&
-			    dst_addr->sin_addr.s_addr == rs->rs_conn_addr &&
-			    dst_addr->sin_port == rs->rs_conn_port) {
+			if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr &&
+			    src_addr->sin_port == src->sin_port &&
+			    dst_addr->sin_addr.s_addr == dst->sin_addr.s_addr &&
+			    dst_addr->sin_port == dst->sin_port) {
 #else
 			/* FIXME - needs to compare the local and remote
 			 * ipaddr/port tuple, but the ipaddr is the only
@@ -128,7 +130,7 @@ static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwd
 			 * zero'ed.  It doesn't appear to be properly populated
 			 * during connection setup...
 			 */
-			if (src_addr->sin_addr.s_addr == rs->rs_bound_addr) {
+			if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr) {
 #endif
 				spin_unlock_irq(&iwdev->spinlock);
 				*rds_iwdev = iwdev;
@@ -180,19 +182,13 @@ int rds_iw_update_cm_id(struct rds_iw_device *rds_iwdev, struct rdma_cm_id *cm_i
 {
 	struct sockaddr_in *src_addr, *dst_addr;
 	struct rds_iw_device *rds_iwdev_old;
-	struct rds_sock rs;
 	struct rdma_cm_id *pcm_id;
 	int rc;
 
 	src_addr = (struct sockaddr_in *)&cm_id->route.addr.src_addr;
 	dst_addr = (struct sockaddr_in *)&cm_id->route.addr.dst_addr;
 
-	rs.rs_bound_addr = src_addr->sin_addr.s_addr;
-	rs.rs_bound_port = src_addr->sin_port;
-	rs.rs_conn_addr = dst_addr->sin_addr.s_addr;
-	rs.rs_conn_port = dst_addr->sin_port;
-
-	rc = rds_iw_get_device(&rs, &rds_iwdev_old, &pcm_id);
+	rc = rds_iw_get_device(src_addr, dst_addr, &rds_iwdev_old, &pcm_id);
 	if (rc)
 		rds_iw_remove_cm_id(rds_iwdev, cm_id);
 
@@ -598,9 +594,17 @@ void *rds_iw_get_mr(struct scatterlist *sg, unsigned long nents,
 	struct rds_iw_device *rds_iwdev;
 	struct rds_iw_mr *ibmr = NULL;
 	struct rdma_cm_id *cm_id;
+	struct sockaddr_in src = {
+		.sin_addr.s_addr = rs->rs_bound_addr,
+		.sin_port = rs->rs_bound_port,
+	};
+	struct sockaddr_in dst = {
+		.sin_addr.s_addr = rs->rs_conn_addr,
+		.sin_port = rs->rs_conn_port,
+	};
 	int ret;
 
-	ret = rds_iw_get_device(rs, &rds_iwdev, &cm_id);
+	ret = rds_iw_get_device(&src, &dst, &rds_iwdev, &cm_id);
 	if (ret || !cm_id) {
 		ret = -ENODEV;
 		goto out;
diff --git a/net/rfkill/Kconfig b/net/rfkill/Kconfig
index 4c10e7e6c9f..77aa1dfc3f8 100644
--- a/net/rfkill/Kconfig
+++ b/net/rfkill/Kconfig
@@ -10,6 +10,11 @@ menuconfig RFKILL
 	  To compile this driver as a module, choose M here: the
 	  module will be called rfkill.
 
+config RFKILL_PM
+	bool "Power off on suspend"
+	depends on RFKILL && PM
+	default y
+
 # LED trigger support
 config RFKILL_LEDS
 	bool
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index fa7cd792791..c22df40fe46 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -782,6 +782,7 @@ void rfkill_pause_polling(struct rfkill *rfkill)
 }
 EXPORT_SYMBOL(rfkill_pause_polling);
 
+#ifdef CONFIG_RFKILL_PM
 void rfkill_resume_polling(struct rfkill *rfkill)
 {
 	BUG_ON(!rfkill);
@@ -817,14 +818,17 @@ static int rfkill_resume(struct device *dev)
 
 	return 0;
 }
+#endif
 
 static struct class rfkill_class = {
 	.name		= "rfkill",
 	.dev_release	= rfkill_release,
 	.dev_groups	= rfkill_dev_groups,
 	.dev_uevent	= rfkill_dev_uevent,
+#ifdef CONFIG_RFKILL_PM
 	.suspend	= rfkill_suspend,
 	.resume		= rfkill_resume,
+#endif
 };
 
 bool rfkill_blocked(struct rfkill *rfkill)
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index a85c1a086ae..67984fb42f1 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -192,7 +192,8 @@ static void rose_kill_by_device(struct net_device *dev)
 
 		if (rose->device == dev) {
 			rose_disconnect(s, ENETUNREACH, ROSE_OUT_OF_ORDER, 0);
-			rose->neighbour->use--;
+			if (rose->neighbour)
+				rose->neighbour->use--;
 			rose->device = NULL;
 		}
 	}
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c
index e9aaa65c077..0df95463c65 100644
--- a/net/rxrpc/ar-recvmsg.c
+++ b/net/rxrpc/ar-recvmsg.c
@@ -87,7 +87,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock,
 		if (!skb) {
 			/* nothing remains on the queue */
 			if (copied &&
-			    (msg->msg_flags & MSG_PEEK || timeo == 0))
+			    (flags & MSG_PEEK || timeo == 0))
 				goto out;
 
 			/* wait for a message to turn up */
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index aad6a679fb1..fae88709aaa 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -81,6 +81,11 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops)
 	struct tcf_proto_ops *t;
 	int rc = -ENOENT;
 
+	/* Wait for outstanding call_rcu()s, if any, from a
+	 * tcf_proto_ops's destroy() handler.
+	 */
+	rcu_barrier();
+
 	write_lock(&cls_mod_lock);
 	list_for_each_entry(t, &tcf_proto_base, head) {
 		if (t == ops) {
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 0472909bb01..b78d81f5ffd 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -78,8 +78,11 @@ struct tc_u_hnode {
 	struct tc_u_common	*tp_c;
 	int			refcnt;
 	unsigned int		divisor;
-	struct tc_u_knode __rcu	*ht[1];
 	struct rcu_head		rcu;
+	/* The 'ht' field MUST be the last field in structure to allow for
+	 * more entries allocated at end of structure.
+	 */
+	struct tc_u_knode __rcu	*ht[1];
 };
 
 struct tc_u_common {
diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index 6742200b130..fbb7ebfc58c 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -228,6 +228,7 @@ static int tcf_em_validate(struct tcf_proto *tp,
 				 * to replay the request.
 				 */
 				module_put(em->ops->owner);
+				em->ops = NULL;
 				err = -EAGAIN;
 			}
 #endif
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 76f402e05bd..a25fae3c8ad 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -815,10 +815,8 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 		if (dev->flags & IFF_UP)
 			dev_deactivate(dev);
 
-		if (new && new->ops->attach) {
-			new->ops->attach(new);
-			num_q = 0;
-		}
+		if (new && new->ops->attach)
+			goto skip;
 
 		for (i = 0; i < num_q; i++) {
 			struct netdev_queue *dev_queue = dev_ingress_queue(dev);
@@ -834,12 +832,16 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 				qdisc_destroy(old);
 		}
 
+skip:
 		if (!ingress) {
 			notify_and_destroy(net, skb, n, classid,
 					   dev->qdisc, new);
 			if (new && !new->ops->attach)
 				atomic_inc(&new->refcnt);
 			dev->qdisc = new ? : &noop_qdisc;
+
+			if (new && new->ops->attach)
+				new->ops->attach(new);
 		} else {
 			notify_and_destroy(net, skb, n, classid, old, new);
 		}
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index b9ca32ebc1d..1e52decb7b5 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -94,7 +94,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch,
 	    TC_H_MIN(skb->priority) <= q->flows_cnt)
 		return TC_H_MIN(skb->priority);
 
-	filter = rcu_dereference(q->filter_list);
+	filter = rcu_dereference_bh(q->filter_list);
 	if (!filter)
 		return fq_codel_hash(q, skb) + 1;
 
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index f791edd64d6..26d06dbcc1c 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1182,7 +1182,6 @@ void sctp_assoc_update(struct sctp_association *asoc,
 	asoc->peer.peer_hmacs = new->peer.peer_hmacs;
 	new->peer.peer_hmacs = NULL;
 
-	sctp_auth_key_put(asoc->asoc_shared_key);
 	sctp_auth_asoc_init_active_key(asoc, GFP_ATOMIC);
 }
 
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 42dffd42838..abe7c2db241 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -401,12 +401,12 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 	sk = chunk->skb->sk;
 
 	/* Allocate the new skb.  */
-	nskb = alloc_skb(packet->size + LL_MAX_HEADER, GFP_ATOMIC);
+	nskb = alloc_skb(packet->size + MAX_HEADER, GFP_ATOMIC);
 	if (!nskb)
 		goto nomem;
 
 	/* Make sure the outbound skb has enough header room reserved. */
-	skb_reserve(nskb, packet->overhead + LL_MAX_HEADER);
+	skb_reserve(nskb, packet->overhead + MAX_HEADER);
 
 	/* Set the owning socket so that we know where to get the
 	 * destination IP address.
@@ -599,7 +599,9 @@ out:
 	return err;
 no_route:
 	kfree_skb(nskb);
-	IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
+
+	if (asoc)
+		IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
 
 	/* FIXME: Returning the 'err' will effect all the associations
 	 * associated with a socket, although only one of the paths of the
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 9f32741abb1..371a152d975 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2608,7 +2608,7 @@ do_addr_param:
 
 		addr_param = param.v + sizeof(sctp_addip_param_t);
 
-		af = sctp_get_af_specific(param_type2af(param.p->type));
+		af = sctp_get_af_specific(param_type2af(addr_param->p.type));
 		if (af == NULL)
 			break;
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 634a2abb5f3..99e640c46ab 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1533,8 +1533,10 @@ static void sctp_close(struct sock *sk, long timeout)
 
 	/* Supposedly, no process has access to the socket, but
 	 * the net layers still may.
+	 * Also, sctp_destroy_sock() needs to be called with addr_wq_lock
+	 * held and that should be grabbed before socket lock.
 	 */
-	local_bh_disable();
+	spin_lock_bh(&net->sctp.addr_wq_lock);
 	bh_lock_sock(sk);
 
 	/* Hold the sock, since sk_common_release() will put sock_put()
@@ -1544,7 +1546,7 @@ static void sctp_close(struct sock *sk, long timeout)
 	sk_common_release(sk);
 
 	bh_unlock_sock(sk);
-	local_bh_enable();
+	spin_unlock_bh(&net->sctp.addr_wq_lock);
 
 	sock_put(sk);
 
@@ -3581,6 +3583,7 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
 	if ((val && sp->do_auto_asconf) || (!val && !sp->do_auto_asconf))
 		return 0;
 
+	spin_lock_bh(&sock_net(sk)->sctp.addr_wq_lock);
 	if (val == 0 && sp->do_auto_asconf) {
 		list_del(&sp->auto_asconf_list);
 		sp->do_auto_asconf = 0;
@@ -3589,6 +3592,7 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
 		    &sock_net(sk)->sctp.auto_asconf_splist);
 		sp->do_auto_asconf = 1;
 	}
+	spin_unlock_bh(&sock_net(sk)->sctp.addr_wq_lock);
 	return 0;
 }
 
@@ -4122,18 +4126,28 @@ static int sctp_init_sock(struct sock *sk)
 	local_bh_disable();
 	percpu_counter_inc(&sctp_sockets_allocated);
 	sock_prot_inuse_add(net, sk->sk_prot, 1);
+
+	/* Nothing can fail after this block, otherwise
+	 * sctp_destroy_sock() will be called without addr_wq_lock held
+	 */
 	if (net->sctp.default_auto_asconf) {
+		spin_lock(&sock_net(sk)->sctp.addr_wq_lock);
 		list_add_tail(&sp->auto_asconf_list,
 		    &net->sctp.auto_asconf_splist);
 		sp->do_auto_asconf = 1;
-	} else
+		spin_unlock(&sock_net(sk)->sctp.addr_wq_lock);
+	} else {
 		sp->do_auto_asconf = 0;
+	}
+
 	local_bh_enable();
 
 	return 0;
 }
 
-/* Cleanup any SCTP per socket resources.  */
+/* Cleanup any SCTP per socket resources. Must be called with
+ * sock_net(sk)->sctp.addr_wq_lock held if sp->do_auto_asconf is true
+ */
 static void sctp_destroy_sock(struct sock *sk)
 {
 	struct sctp_sock *sp;
@@ -7201,6 +7215,19 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newinet->mc_list = NULL;
 }
 
+static inline void sctp_copy_descendant(struct sock *sk_to,
+					const struct sock *sk_from)
+{
+	int ancestor_size = sizeof(struct inet_sock) +
+			    sizeof(struct sctp_sock) -
+			    offsetof(struct sctp_sock, auto_asconf_list);
+
+	if (sk_from->sk_family == PF_INET6)
+		ancestor_size += sizeof(struct ipv6_pinfo);
+
+	__inet_sk_copy_descendant(sk_to, sk_from, ancestor_size);
+}
+
 /* Populate the fields of the newsk from the oldsk and migrate the assoc
  * and its messages to the newsk.
  */
@@ -7215,7 +7242,6 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	struct sk_buff *skb, *tmp;
 	struct sctp_ulpevent *event;
 	struct sctp_bind_hashbucket *head;
-	struct list_head tmplist;
 
 	/* Migrate socket buffer sizes and all the socket level options to the
 	 * new socket.
@@ -7223,12 +7249,7 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	newsk->sk_sndbuf = oldsk->sk_sndbuf;
 	newsk->sk_rcvbuf = oldsk->sk_rcvbuf;
 	/* Brute force copy old sctp opt. */
-	if (oldsp->do_auto_asconf) {
-		memcpy(&tmplist, &newsp->auto_asconf_list, sizeof(tmplist));
-		inet_sk_copy_descendant(newsk, oldsk);
-		memcpy(&newsp->auto_asconf_list, &tmplist, sizeof(tmplist));
-	} else
-		inet_sk_copy_descendant(newsk, oldsk);
+	sctp_copy_descendant(newsk, oldsk);
 
 	/* Restore the ep value that was overwritten with the above structure
 	 * copy.
diff --git a/net/socket.c b/net/socket.c
index fe20c319a0b..02fc7c8ea9e 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -892,9 +892,6 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
 static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb,
 					 struct sock_iocb *siocb)
 {
-	if (!is_sync_kiocb(iocb))
-		BUG();
-
 	siocb->kiocb = iocb;
 	iocb->private = siocb;
 	return siocb;
@@ -2020,14 +2017,12 @@ static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg,
 	int err, ctl_len, total_len;
 
 	err = -EFAULT;
-	if (MSG_CMSG_COMPAT & flags) {
-		if (get_compat_msghdr(msg_sys, msg_compat))
-			return -EFAULT;
-	} else {
+	if (MSG_CMSG_COMPAT & flags)
+		err = get_compat_msghdr(msg_sys, msg_compat);
+	else
 		err = copy_msghdr_from_user(msg_sys, msg);
-		if (err)
-			return err;
-	}
+	if (err)
+		return err;
 
 	if (msg_sys->msg_iovlen > UIO_FASTIOV) {
 		err = -EMSGSIZE;
@@ -2232,14 +2227,12 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
 	struct sockaddr __user *uaddr;
 	int __user *uaddr_len;
 
-	if (MSG_CMSG_COMPAT & flags) {
-		if (get_compat_msghdr(msg_sys, msg_compat))
-			return -EFAULT;
-	} else {
+	if (MSG_CMSG_COMPAT & flags)
+		err = get_compat_msghdr(msg_sys, msg_compat);
+	else
 		err = copy_msghdr_from_user(msg_sys, msg);
-		if (err)
-			return err;
-	}
+	if (err)
+		return err;
 
 	if (msg_sys->msg_iovlen > UIO_FASTIOV) {
 		err = -EMSGSIZE;
diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c
index 1ec19f6f0c2..eeeba5adee6 100644
--- a/net/sunrpc/auth_gss/gss_rpc_xdr.c
+++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c
@@ -793,20 +793,26 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp,
 {
 	u32 value_follows;
 	int err;
+	struct page *scratch;
+
+	scratch = alloc_page(GFP_KERNEL);
+	if (!scratch)
+		return -ENOMEM;
+	xdr_set_scratch_buffer(xdr, page_address(scratch), PAGE_SIZE);
 
 	/* res->status */
 	err = gssx_dec_status(xdr, &res->status);
 	if (err)
-		return err;
+		goto out_free;
 
 	/* res->context_handle */
 	err = gssx_dec_bool(xdr, &value_follows);
 	if (err)
-		return err;
+		goto out_free;
 	if (value_follows) {
 		err = gssx_dec_ctx(xdr, res->context_handle);
 		if (err)
-			return err;
+			goto out_free;
 	} else {
 		res->context_handle = NULL;
 	}
@@ -814,11 +820,11 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp,
 	/* res->output_token */
 	err = gssx_dec_bool(xdr, &value_follows);
 	if (err)
-		return err;
+		goto out_free;
 	if (value_follows) {
 		err = gssx_dec_buffer(xdr, res->output_token);
 		if (err)
-			return err;
+			goto out_free;
 	} else {
 		res->output_token = NULL;
 	}
@@ -826,14 +832,17 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp,
 	/* res->delegated_cred_handle */
 	err = gssx_dec_bool(xdr, &value_follows);
 	if (err)
-		return err;
+		goto out_free;
 	if (value_follows) {
 		/* we do not support upcall servers sending this data. */
-		return -EINVAL;
+		err = -EINVAL;
+		goto out_free;
 	}
 
 	/* res->options */
 	err = gssx_dec_option_array(xdr, &res->options);
 
+out_free:
+	__free_page(scratch);
 	return err;
 }
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index 9761a0da964..ca9ff71134f 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -60,7 +60,7 @@ static void xprt_free_allocation(struct rpc_rqst *req)
 
 	dprintk("RPC:        free allocations for req= %p\n", req);
 	WARN_ON_ONCE(test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state));
-	xbufp = &req->rq_private_buf;
+	xbufp = &req->rq_rcv_buf;
 	free_page((unsigned long)xbufp->head[0].iov_base);
 	xbufp = &req->rq_snd_buf;
 	free_page((unsigned long)xbufp->head[0].iov_base);
@@ -309,12 +309,15 @@ void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied)
 	struct rpc_xprt *xprt = req->rq_xprt;
 	struct svc_serv *bc_serv = xprt->bc_serv;
 
+	spin_lock(&xprt->bc_pa_lock);
+	list_del(&req->rq_bc_pa_list);
+	spin_unlock(&xprt->bc_pa_lock);
+
 	req->rq_private_buf.len = copied;
 	set_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
 
 	dprintk("RPC:       add callback request to list\n");
 	spin_lock(&bc_serv->sv_cb_lock);
-	list_del(&req->rq_bc_pa_list);
 	list_add(&req->rq_bc_list, &bc_serv->sv_cb_list);
 	wake_up(&bc_serv->sv_cb_waitq);
 	spin_unlock(&bc_serv->sv_cb_lock);
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 06636214113..48f14003af1 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -920,7 +920,7 @@ static unsigned int cache_poll(struct file *filp, poll_table *wait,
 	poll_wait(filp, &queue_wait, wait);
 
 	/* alway allow write */
-	mask = POLL_OUT | POLLWRNORM;
+	mask = POLLOUT | POLLWRNORM;
 
 	if (!rp)
 		return mask;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 9acd6ce88db..ae46f019860 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -286,10 +286,8 @@ static struct rpc_xprt *rpc_clnt_set_transport(struct rpc_clnt *clnt,
 
 static void rpc_clnt_set_nodename(struct rpc_clnt *clnt, const char *nodename)
 {
-	clnt->cl_nodelen = strlen(nodename);
-	if (clnt->cl_nodelen > UNX_MAXNODENAME)
-		clnt->cl_nodelen = UNX_MAXNODENAME;
-	memcpy(clnt->cl_nodename, nodename, clnt->cl_nodelen);
+	clnt->cl_nodelen = strlcpy(clnt->cl_nodename,
+			nodename, sizeof(clnt->cl_nodename));
 }
 
 static int rpc_client_register(struct rpc_clnt *clnt,
@@ -360,6 +358,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args,
 	const struct rpc_version *version;
 	struct rpc_clnt *clnt = NULL;
 	const struct rpc_timeout *timeout;
+	const char *nodename = args->nodename;
 	int err;
 
 	/* sanity check the name before trying to print it */
@@ -415,8 +414,10 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args,
 
 	atomic_set(&clnt->cl_count, 1);
 
+	if (nodename == NULL)
+		nodename = utsname()->nodename;
 	/* save the nodename */
-	rpc_clnt_set_nodename(clnt, utsname()->nodename);
+	rpc_clnt_set_nodename(clnt, nodename);
 
 	err = rpc_client_register(clnt, args->authflavor, args->client_name);
 	if (err)
@@ -571,6 +572,7 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args,
 	if (xprt == NULL)
 		goto out_err;
 	args->servername = xprt->servername;
+	args->nodename = clnt->cl_nodename;
 
 	new = rpc_new_client(args, xprt, clnt);
 	if (IS_ERR(new)) {
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 1891a1022c1..74b75c3ce39 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -355,7 +355,8 @@ out:
 	return result;
 }
 
-static struct rpc_clnt *rpcb_create(struct net *net, const char *hostname,
+static struct rpc_clnt *rpcb_create(struct net *net, const char *nodename,
+				    const char *hostname,
 				    struct sockaddr *srvaddr, size_t salen,
 				    int proto, u32 version)
 {
@@ -365,6 +366,7 @@ static struct rpc_clnt *rpcb_create(struct net *net, const char *hostname,
 		.address	= srvaddr,
 		.addrsize	= salen,
 		.servername	= hostname,
+		.nodename	= nodename,
 		.program	= &rpcb_program,
 		.version	= version,
 		.authflavor	= RPC_AUTH_UNIX,
@@ -740,7 +742,9 @@ void rpcb_getport_async(struct rpc_task *task)
 	dprintk("RPC: %5u %s: trying rpcbind version %u\n",
 		task->tk_pid, __func__, bind_version);
 
-	rpcb_clnt = rpcb_create(xprt->xprt_net, xprt->servername, sap, salen,
+	rpcb_clnt = rpcb_create(xprt->xprt_net,
+				clnt->cl_nodename,
+				xprt->servername, sap, salen,
 				xprt->prot, bind_version);
 	if (IS_ERR(rpcb_clnt)) {
 		status = PTR_ERR(rpcb_clnt);
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 290af97bf6f..2a81e77c447 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -606,7 +606,7 @@ void xdr_truncate_encode(struct xdr_stream *xdr, size_t len)
 	struct kvec *head = buf->head;
 	struct kvec *tail = buf->tail;
 	int fraglen;
-	int new, old;
+	int new;
 
 	if (len > buf->len) {
 		WARN_ON_ONCE(1);
@@ -628,8 +628,8 @@ void xdr_truncate_encode(struct xdr_stream *xdr, size_t len)
 	buf->len -= fraglen;
 
 	new = buf->page_base + buf->page_len;
-	old = new + fraglen;
-	xdr->page_ptr -= (old >> PAGE_SHIFT) - (new >> PAGE_SHIFT);
+
+	xdr->page_ptr = buf->pages + (new >> PAGE_SHIFT);
 
 	if (buf->page_len && buf->len == len) {
 		xdr->p = page_address(*xdr->page_ptr);
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 61c41298b4e..6e5d5034b0f 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -511,8 +511,8 @@ int
 rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
 {
 	int rc, mem_priv;
-	struct ib_device_attr devattr;
 	struct rpcrdma_ia *ia = &xprt->rx_ia;
+	struct ib_device_attr *devattr = &ia->ri_devattr;
 
 	ia->ri_id = rpcrdma_create_id(xprt, ia, addr);
 	if (IS_ERR(ia->ri_id)) {
@@ -528,28 +528,24 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
 		goto out2;
 	}
 
-	/*
-	 * Query the device to determine if the requested memory
-	 * registration strategy is supported. If it isn't, set the
-	 * strategy to a globally supported model.
-	 */
-	rc = ib_query_device(ia->ri_id->device, &devattr);
+	rc = ib_query_device(ia->ri_id->device, devattr);
 	if (rc) {
 		dprintk("RPC:       %s: ib_query_device failed %d\n",
 			__func__, rc);
 		goto out2;
 	}
 
-	if (devattr.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) {
+	if (devattr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) {
 		ia->ri_have_dma_lkey = 1;
 		ia->ri_dma_lkey = ia->ri_id->device->local_dma_lkey;
 	}
 
 	if (memreg == RPCRDMA_FRMR) {
 		/* Requires both frmr reg and local dma lkey */
-		if ((devattr.device_cap_flags &
+		if (((devattr->device_cap_flags &
 		     (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) !=
-		    (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) {
+		    (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) ||
+		      (devattr->max_fast_reg_page_list_len == 0)) {
 			dprintk("RPC:       %s: FRMR registration "
 				"not supported by HCA\n", __func__);
 			memreg = RPCRDMA_MTHCAFMR;
@@ -557,7 +553,7 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
 			/* Mind the ia limit on FRMR page list depth */
 			ia->ri_max_frmr_depth = min_t(unsigned int,
 				RPCRDMA_MAX_DATA_SEGS,
-				devattr.max_fast_reg_page_list_len);
+				devattr->max_fast_reg_page_list_len);
 		}
 	}
 	if (memreg == RPCRDMA_MTHCAFMR) {
@@ -655,20 +651,13 @@ int
 rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 				struct rpcrdma_create_data_internal *cdata)
 {
-	struct ib_device_attr devattr;
+	struct ib_device_attr *devattr = &ia->ri_devattr;
 	struct ib_cq *sendcq, *recvcq;
 	int rc, err;
 
-	rc = ib_query_device(ia->ri_id->device, &devattr);
-	if (rc) {
-		dprintk("RPC:       %s: ib_query_device failed %d\n",
-			__func__, rc);
-		return rc;
-	}
-
 	/* check provider's send/recv wr limits */
-	if (cdata->max_requests > devattr.max_qp_wr)
-		cdata->max_requests = devattr.max_qp_wr;
+	if (cdata->max_requests > devattr->max_qp_wr)
+		cdata->max_requests = devattr->max_qp_wr;
 
 	ep->rep_attr.event_handler = rpcrdma_qp_async_error_upcall;
 	ep->rep_attr.qp_context = ep;
@@ -703,8 +692,8 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 
 		}
 		ep->rep_attr.cap.max_send_wr *= depth;
-		if (ep->rep_attr.cap.max_send_wr > devattr.max_qp_wr) {
-			cdata->max_requests = devattr.max_qp_wr / depth;
+		if (ep->rep_attr.cap.max_send_wr > devattr->max_qp_wr) {
+			cdata->max_requests = devattr->max_qp_wr / depth;
 			if (!cdata->max_requests)
 				return -EINVAL;
 			ep->rep_attr.cap.max_send_wr = cdata->max_requests *
@@ -786,10 +775,11 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 
 	/* Client offers RDMA Read but does not initiate */
 	ep->rep_remote_cma.initiator_depth = 0;
-	if (devattr.max_qp_rd_atom > 32)	/* arbitrary but <= 255 */
+	if (devattr->max_qp_rd_atom > 32)	/* arbitrary but <= 255 */
 		ep->rep_remote_cma.responder_resources = 32;
 	else
-		ep->rep_remote_cma.responder_resources = devattr.max_qp_rd_atom;
+		ep->rep_remote_cma.responder_resources =
+						devattr->max_qp_rd_atom;
 
 	ep->rep_remote_cma.retry_count = 7;
 	ep->rep_remote_cma.flow_control = 0;
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index ac7fc9a3134..11f0e06f662 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -70,6 +70,7 @@ struct rpcrdma_ia {
 	int			ri_async_rc;
 	enum rpcrdma_memreg	ri_memreg_strategy;
 	unsigned int		ri_max_frmr_depth;
+	struct ib_device_attr	ri_devattr;
 };
 
 /*
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index e9688438073..8232118b3f8 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1899,6 +1899,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
 		unix_state_unlock(sk);
 		timeo = freezable_schedule_timeout(timeo);
 		unix_state_lock(sk);
+
+		if (sock_flag(sk, SOCK_DEAD))
+			break;
+
 		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
 	}
 
@@ -1963,6 +1967,10 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		struct sk_buff *skb, *last;
 
 		unix_state_lock(sk);
+		if (sock_flag(sk, SOCK_DEAD)) {
+			err = -ECONNRESET;
+			goto unlock;
+		}
 		last = skb = skb_peek(&sk->sk_receive_queue);
 again:
 		if (skb == NULL) {
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 72d81e2154d..92ae263ebbf 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -602,7 +602,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
 {
 	struct ieee80211_sta_ht_cap *ht_cap;
 	struct ieee80211_sta_vht_cap *vht_cap;
-	u32 width, control_freq;
+	u32 width, control_freq, cap;
 
 	if (WARN_ON(!cfg80211_chandef_valid(chandef)))
 		return false;
@@ -642,7 +642,8 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
 			return false;
 		break;
 	case NL80211_CHAN_WIDTH_80P80:
-		if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ))
+		cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK;
+		if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ)
 			return false;
 	case NL80211_CHAN_WIDTH_80:
 		if (!vht_cap->vht_supported)
@@ -653,7 +654,9 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
 	case NL80211_CHAN_WIDTH_160:
 		if (!vht_cap->vht_supported)
 			return false;
-		if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ))
+		cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK;
+		if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ &&
+		    cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ)
 			return false;
 		prohibited_flags |= IEEE80211_CHAN_NO_160MHZ;
 		width = 160;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 5839c85075f..5fed79cfe45 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -2805,6 +2805,9 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info)
 	if (!rdev->ops->get_key)
 		return -EOPNOTSUPP;
 
+	if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN))
+		return -ENOENT;
+
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
 		return -ENOMEM;
@@ -2824,10 +2827,6 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info)
 	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr))
 		goto nla_put_failure;
 
-	if (pairwise && mac_addr &&
-	    !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN))
-		return -ENOENT;
-
 	err = rdev_get_key(rdev, dev, key_idx, pairwise, mac_addr, &cookie,
 			   get_key_callback);
 
@@ -2998,7 +2997,7 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info)
 	wdev_lock(dev->ieee80211_ptr);
 	err = nl80211_key_allowed(dev->ieee80211_ptr);
 
-	if (key.type == NL80211_KEYTYPE_PAIRWISE && mac_addr &&
+	if (key.type == NL80211_KEYTYPE_GROUP && mac_addr &&
 	    !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN))
 		err = -ENOENT;
 
@@ -4312,6 +4311,16 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info)
 	if (parse_station_flags(info, dev->ieee80211_ptr->iftype, &params))
 		return -EINVAL;
 
+	/* HT/VHT requires QoS, but if we don't have that just ignore HT/VHT
+	 * as userspace might just pass through the capabilities from the IEs
+	 * directly, rather than enforcing this restriction and returning an
+	 * error in this case.
+	 */
+	if (!(params.sta_flags_set & BIT(NL80211_STA_FLAG_WME))) {
+		params.ht_capa = NULL;
+		params.vht_capa = NULL;
+	}
+
 	/* When you run into this, adjust the code below for the new flag */
 	BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 7);
 
@@ -5799,7 +5808,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 		}
 
 		/* there was no other matchset, so the RSSI one is alone */
-		if (i == 0)
+		if (i == 0 && n_match_sets)
 			request->match_sets[0].rssi_thold = default_match_rssi;
 
 		request->min_rssi_thold = INT_MAX;
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index b725a31a475..6fd53ea3019 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -1760,7 +1760,7 @@ static enum reg_request_treatment
 reg_process_hint_driver(struct wiphy *wiphy,
 			struct regulatory_request *driver_request)
 {
-	const struct ieee80211_regdomain *regd;
+	const struct ieee80211_regdomain *regd, *tmp;
 	enum reg_request_treatment treatment;
 
 	treatment = __reg_process_hint_driver(driver_request);
@@ -1780,7 +1780,10 @@ reg_process_hint_driver(struct wiphy *wiphy,
 			reg_free_request(driver_request);
 			return REG_REQ_IGNORE;
 		}
+
+		tmp = get_wiphy_regdom(wiphy);
 		rcu_assign_pointer(wiphy->regd, regd);
+		rcu_free_regdom(tmp);
 	}
 
 
@@ -1839,11 +1842,8 @@ __reg_process_hint_country_ie(struct wiphy *wiphy,
 			return REG_REQ_IGNORE;
 		return REG_REQ_ALREADY_SET;
 	}
-	/*
-	 * Two consecutive Country IE hints on the same wiphy.
-	 * This should be picked up early by the driver/stack
-	 */
-	if (WARN_ON(regdom_changes(country_ie_request->alpha2)))
+
+	if (regdom_changes(country_ie_request->alpha2))
 		return REG_REQ_OK;
 	return REG_REQ_ALREADY_SET;
 }
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index bda39f14981..9e62e9cd714 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -56,7 +56,7 @@
  * also linked into the probe response struct.
  */
 
-#define IEEE80211_SCAN_RESULT_EXPIRE	(30 * HZ)
+#define IEEE80211_SCAN_RESULT_EXPIRE	(7 * HZ)
 
 static void bss_free(struct cfg80211_internal_bss *bss)
 {
diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index 0f47948c572..d2c77d5707b 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -1333,6 +1333,8 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev)
 	memcpy(bssid, wdev->current_bss->pub.bssid, ETH_ALEN);
 	wdev_unlock(wdev);
 
+	memset(&sinfo, 0, sizeof(sinfo));
+
 	if (rdev_get_station(rdev, dev, bssid, &sinfo))
 		return NULL;
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 88bf289abdc..f62fd2c5d83 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2264,11 +2264,9 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 		 * have the xfrm_state's. We need to wait for KM to
 		 * negotiate new SA's or bail out with error.*/
 		if (net->xfrm.sysctl_larval_drop) {
-			dst_release(dst);
-			xfrm_pols_put(pols, drop_pols);
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
-
-			return ERR_PTR(-EREMOTE);
+			err = -EREMOTE;
+			goto error;
 		}
 
 		err = -EAGAIN;
@@ -2319,7 +2317,8 @@ nopol:
 error:
 	dst_release(dst);
 dropdst:
-	dst_release(dst_orig);
+	if (!(flags & XFRM_LOOKUP_KEEP_DST_REF))
+		dst_release(dst_orig);
 	xfrm_pols_put(pols, drop_pols);
 	return ERR_PTR(err);
 }
@@ -2333,7 +2332,8 @@ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig,
 				    struct sock *sk, int flags)
 {
 	struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk,
-					    flags | XFRM_LOOKUP_QUEUE);
+					    flags | XFRM_LOOKUP_QUEUE |
+					    XFRM_LOOKUP_KEEP_DST_REF);
 
 	if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE)
 		return make_blackhole(net, dst_orig->ops->family, dst_orig);
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index 65e7b08bb2c..5374b1bdf02 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -179,6 +179,12 @@ build := -f $(srctree)/scripts/Makefile.build obj
 # $(Q)$(MAKE) $(modbuiltin)=dir
 modbuiltin := -f $(srctree)/scripts/Makefile.modbuiltin obj
 
+###
+# Shorthand for $(Q)$(MAKE) -f scripts/Makefile.dtbinst obj=
+# Usage:
+# $(Q)$(MAKE) $(dtbinst)=dir
+dtbinst := -f $(if $(KBUILD_SRC),$(srctree)/)scripts/Makefile.dtbinst obj
+
 # Prefix -I with $(srctree) if it is not an absolute path.
 # skip if -I has no parameter
 addtree = $(if $(patsubst -I%,%,$(1)), \
diff --git a/scripts/Makefile.clean b/scripts/Makefile.clean
index b1c668dc681..a609552a86d 100644
--- a/scripts/Makefile.clean
+++ b/scripts/Makefile.clean
@@ -45,19 +45,19 @@ __clean-files	:= $(extra-y) $(extra-m) $(extra-)       \
 
 __clean-files   := $(filter-out $(no-clean-files), $(__clean-files))
 
-# as clean-files is given relative to the current directory, this adds
-# a $(obj) prefix, except for absolute paths
+# clean-files is given relative to the current directory, unless it
+# starts with $(objtree)/ (which means "./", so do not add "./" unless
+# you want to delete a file from the toplevel object directory).
 
 __clean-files   := $(wildcard                                               \
-                   $(addprefix $(obj)/, $(filter-out /%, $(__clean-files))) \
-		   $(filter /%, $(__clean-files)))
+		   $(addprefix $(obj)/, $(filter-out $(objtree)/%, $(__clean-files))) \
+		   $(filter $(objtree)/%, $(__clean-files)))
 
-# as clean-dirs is given relative to the current directory, this adds
-# a $(obj) prefix, except for absolute paths
+# same as clean-files
 
 __clean-dirs    := $(wildcard                                               \
-                   $(addprefix $(obj)/, $(filter-out /%, $(clean-dirs)))    \
-		   $(filter /%, $(clean-dirs)))
+		   $(addprefix $(obj)/, $(filter-out $(objtree)/%, $(clean-dirs)))    \
+		   $(filter $(objtree)/%, $(clean-dirs)))
 
 # ==========================================================================
 
diff --git a/scripts/Makefile.dtbinst b/scripts/Makefile.dtbinst
new file mode 100644
index 00000000000..909ed7a2ac6
--- /dev/null
+++ b/scripts/Makefile.dtbinst
@@ -0,0 +1,51 @@
+# ==========================================================================
+# Installing dtb files
+#
+# Installs all dtb files listed in $(dtb-y) either in the
+# INSTALL_DTBS_PATH directory or the default location:
+#
+#   $INSTALL_PATH/dtbs/$KERNELRELEASE
+#
+# Traverse through subdirectories listed in $(dts-dirs).
+# ==========================================================================
+
+src := $(obj)
+
+PHONY := __dtbs_install
+__dtbs_install:
+
+export dtbinst-root ?= $(obj)
+
+include include/config/auto.conf
+include scripts/Kbuild.include
+include $(srctree)/$(obj)/Makefile
+
+PHONY += __dtbs_install_prep
+__dtbs_install_prep:
+ifeq ("$(dtbinst-root)", "$(obj)")
+	$(Q)if [ -d $(INSTALL_DTBS_PATH).old ]; then rm -rf $(INSTALL_DTBS_PATH).old; fi
+	$(Q)if [ -d $(INSTALL_DTBS_PATH) ]; then mv $(INSTALL_DTBS_PATH) $(INSTALL_DTBS_PATH).old; fi
+	$(Q)mkdir -p $(INSTALL_DTBS_PATH)
+endif
+
+dtbinst-files	:= $(dtb-y)
+dtbinst-dirs	:= $(dts-dirs)
+
+# Helper targets for Installing DTBs into the boot directory
+quiet_cmd_dtb_install =	INSTALL $<
+      cmd_dtb_install =	mkdir -p $(2); cp $< $(2)
+
+install-dir = $(patsubst $(dtbinst-root)%,$(INSTALL_DTBS_PATH)%,$(obj))
+
+$(dtbinst-files) $(dtbinst-dirs): | __dtbs_install_prep
+
+$(dtbinst-files): %.dtb: $(obj)/%.dtb
+	$(call cmd,dtb_install,$(install-dir))
+
+$(dtbinst-dirs):
+	$(Q)$(MAKE) $(dtbinst)=$(obj)/$@
+
+PHONY += $(dtbinst-files) $(dtbinst-dirs)
+__dtbs_install: $(dtbinst-files) $(dtbinst-dirs)
+
+.PHONY: $(PHONY)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 54be19a0fa5..bb65833aeb8 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -283,17 +283,11 @@ $(obj)/%.dtb: $(src)/%.dts FORCE
 
 dtc-tmp = $(subst $(comma),_,$(dot-target).dts.tmp)
 
-# Helper targets for Installing DTBs into the boot directory
-quiet_cmd_dtb_install =	INSTALL $<
-      cmd_dtb_install =	cp $< $(2)
-
-_dtbinst_pre_:
-	$(Q)if [ -d $(INSTALL_DTBS_PATH).old ]; then rm -rf $(INSTALL_DTBS_PATH).old; fi
-	$(Q)if [ -d $(INSTALL_DTBS_PATH) ]; then mv $(INSTALL_DTBS_PATH) $(INSTALL_DTBS_PATH).old; fi
-	$(Q)mkdir -p $(INSTALL_DTBS_PATH)
-
-%.dtb_dtbinst_: $(obj)/%.dtb _dtbinst_pre_
-	$(call cmd,dtb_install,$(INSTALL_DTBS_PATH))
+# cat
+# ---------------------------------------------------------------------------
+# Concatentate multiple files together
+quiet_cmd_cat = CAT     $@
+cmd_cat = (cat $(filter-out FORCE,$^) > $@) || (rm -f $@; false)
 
 # Bzip2
 # ---------------------------------------------------------------------------
diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst
index e48a4e9d886..9b7b2804e50 100644
--- a/scripts/Makefile.modinst
+++ b/scripts/Makefile.modinst
@@ -29,7 +29,7 @@ quiet_cmd_modules_install = INSTALL $@
 INSTALL_MOD_DIR ?= extra
 ext-mod-dir = $(INSTALL_MOD_DIR)$(subst $(patsubst %/,%,$(KBUILD_EXTMOD)),,$(@D))
 
-modinst_dir = $(if $(KBUILD_EXTMOD),$(ext-mod-dir),kernel/$(@D))
+modinst_dir ?= $(if $(KBUILD_EXTMOD),$(ext-mod-dir),kernel/$(@D))
 
 $(modules):
 	$(call cmd,modules_install,$(MODLIB)/$(modinst_dir))
diff --git a/scripts/coccinelle/misc/bugon.cocci b/scripts/coccinelle/misc/bugon.cocci
index 556456ca761..3b7eec24fb5 100644
--- a/scripts/coccinelle/misc/bugon.cocci
+++ b/scripts/coccinelle/misc/bugon.cocci
@@ -8,7 +8,7 @@
 // Confidence: High
 // Copyright: (C) 2014 Himangi Saraogi.  GPLv2.
 // Comments:
-// Options: --no-includes, --include-headers
+// Options: --no-includes --include-headers
 
 virtual patch
 virtual context
diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c
index a26cc5d2a9b..72c9dba84c5 100644
--- a/scripts/kconfig/menu.c
+++ b/scripts/kconfig/menu.c
@@ -548,7 +548,7 @@ static void get_prompt_str(struct gstr *r, struct property *prop,
 {
 	int i, j;
 	struct menu *submenu[8], *menu, *location = NULL;
-	struct jump_key *jump;
+	struct jump_key *jump = NULL;
 
 	str_printf(r, _("Prompt: %s\n"), _(prop->text));
 	menu = prop->menu->parent;
@@ -586,7 +586,7 @@ static void get_prompt_str(struct gstr *r, struct property *prop,
 		str_printf(r, _("  Location:\n"));
 		for (j = 4; --i >= 0; j += 2) {
 			menu = submenu[i];
-			if (head && location && menu == location)
+			if (jump && menu == location)
 				jump->offset = strlen(r->s);
 			str_printf(r, "%*c-> %s", j, ' ',
 				   _(menu_get_prompt(menu)));
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index 70bea942b41..9922e66883a 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -1753,7 +1753,7 @@ sub dump_struct($$) {
 	# strip kmemcheck_bitfield_{begin,end}.*;
 	$members =~ s/kmemcheck_bitfield_.*?;//gos;
 	# strip attributes
-	$members =~ s/__aligned\s*\(.+\)//gos;
+	$members =~ s/__aligned\s*\([^;]*\)//gos;
 
 	create_parameterlist($members, ';', $file);
 	check_sections($file, $declaration_name, "struct", $sectcheck, $struct_actual, $nested);
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index d4b665610d6..1f9f08ae60c 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -255,7 +255,6 @@ if ($arch eq "x86_64") {
     # force flags for this arch
     $ld .= " -m shlelf_linux";
     $objcopy .= " -O elf32-sh-linux";
-    $cc .= " -m32";
 
 } elsif ($arch eq "powerpc") {
     $local_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\.?\\S+)";
diff --git a/security/capability.c b/security/capability.c
index d68c57a62bc..ef951b00414 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -12,6 +12,26 @@
 
 #include <linux/security.h>
 
+static int cap_binder_set_context_mgr(struct task_struct *mgr)
+{
+	return 0;
+}
+
+static int cap_binder_transaction(struct task_struct *from, struct task_struct *to)
+{
+	return 0;
+}
+
+static int cap_binder_transfer_binder(struct task_struct *from, struct task_struct *to)
+{
+	return 0;
+}
+
+static int cap_binder_transfer_file(struct task_struct *from, struct task_struct *to, struct file *file)
+{
+	return 0;
+}
+
 static int cap_syslog(int type)
 {
 	return 0;
@@ -930,6 +950,10 @@ static void cap_audit_rule_free(void *lsmrule)
 
 void __init security_fixup_ops(struct security_operations *ops)
 {
+	set_to_cap_if_null(ops, binder_set_context_mgr);
+	set_to_cap_if_null(ops, binder_transaction);
+	set_to_cap_if_null(ops, binder_transfer_binder);
+	set_to_cap_if_null(ops, binder_transfer_file);
 	set_to_cap_if_null(ops, ptrace_access_check);
 	set_to_cap_if_null(ops, ptrace_traceme);
 	set_to_cap_if_null(ops, capget);
diff --git a/security/commoncap.c b/security/commoncap.c
index bab0611afc1..7ae25198d8e 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -31,6 +31,10 @@
 #include <linux/binfmts.h>
 #include <linux/personality.h>
 
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+#include <linux/android_aid.h>
+#endif
+
 /*
  * If a non-root user executes a setuid-root binary in
  * !secure(SECURE_NOROOT) mode, then we raise capabilities.
@@ -78,6 +82,13 @@ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns,
 {
 	struct user_namespace *ns = targ_ns;
 
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+	if (cap == CAP_NET_RAW && in_egroup_p(AID_NET_RAW))
+		return 0;
+	if (cap == CAP_NET_ADMIN && in_egroup_p(AID_NET_ADMIN))
+		return 0;
+#endif
+
 	/* See if cred has the capability in the target user namespace
 	 * by examining the target user namespace and all of the target
 	 * user namespace's parents.
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index c5ee1a7c5e8..4ada1a97a60 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -22,6 +22,7 @@
 #include <linux/xattr.h>
 #include <linux/integrity.h>
 #include <linux/evm.h>
+#include <linux/magic.h>
 #include <crypto/hash.h>
 #include "evm.h"
 
@@ -291,6 +292,17 @@ static int evm_protect_xattr(struct dentry *dentry, const char *xattr_name,
 		iint = integrity_iint_find(dentry->d_inode);
 		if (iint && (iint->flags & IMA_NEW_FILE))
 			return 0;
+
+		/* exception for pseudo filesystems */
+		if (dentry->d_inode->i_sb->s_magic == TMPFS_MAGIC
+		    || dentry->d_inode->i_sb->s_magic == SYSFS_MAGIC)
+			return 0;
+
+		integrity_audit_msg(AUDIT_INTEGRITY_METADATA,
+				    dentry->d_inode, dentry->d_name.name,
+				    "update_metadata",
+				    integrity_status_msg[evm_status],
+				    -EPERM, 0);
 	}
 out:
 	if (evm_status != INTEGRITY_PASS)
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index 8ee997dff13..fc56d4dfa95 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -106,7 +106,7 @@ void ima_add_violation(struct file *file, const unsigned char *filename,
 		       const char *op, const char *cause);
 int ima_init_crypto(void);
 void ima_putc(struct seq_file *m, void *data, int datalen);
-void ima_print_digest(struct seq_file *m, u8 *digest, int size);
+void ima_print_digest(struct seq_file *m, u8 *digest, u32 size);
 struct ima_template_desc *ima_template_desc_current(void);
 int ima_init_template(void);
 
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index da92fcc08d1..d30afe46107 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -186,9 +186,9 @@ static const struct file_operations ima_measurements_ops = {
 	.release = seq_release,
 };
 
-void ima_print_digest(struct seq_file *m, u8 *digest, int size)
+void ima_print_digest(struct seq_file *m, u8 *digest, u32 size)
 {
-	int i;
+	u32 i;
 
 	for (i = 0; i < size; i++)
 		seq_printf(m, "%02x", *(digest + i));
diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c
index 1506f024857..1eb173ddefd 100644
--- a/security/integrity/ima/ima_template_lib.c
+++ b/security/integrity/ima/ima_template_lib.c
@@ -70,7 +70,8 @@ static void ima_show_template_data_ascii(struct seq_file *m,
 					 enum data_formats datafmt,
 					 struct ima_field_data *field_data)
 {
-	u8 *buf_ptr = field_data->data, buflen = field_data->len;
+	u8 *buf_ptr = field_data->data;
+	u32 buflen = field_data->len;
 
 	switch (datafmt) {
 	case DATA_FMT_DIGEST_WITH_ALGO:
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index db9675db102..7bed4ad7cd7 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -1017,10 +1017,13 @@ static int __init init_encrypted(void)
 	ret = encrypted_shash_alloc();
 	if (ret < 0)
 		return ret;
+	ret = aes_get_sizes();
+	if (ret < 0)
+		goto out;
 	ret = register_key_type(&key_type_encrypted);
 	if (ret < 0)
 		goto out;
-	return aes_get_sizes();
+	return 0;
 out:
 	encrypted_shash_release();
 	return ret;
diff --git a/security/keys/gc.c b/security/keys/gc.c
index 9609a7f0fae..c7952375ac5 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -148,12 +148,12 @@ static noinline void key_gc_unused_keys(struct list_head *keys)
 		if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags))
 			atomic_dec(&key->user->nikeys);
 
-		key_user_put(key->user);
-
 		/* now throw away the key memory */
 		if (key->type->destroy)
 			key->type->destroy(key);
 
+		key_user_put(key->user);
+
 		kfree(key->description);
 
 #ifdef KEY_DEBUGGING
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index e72548b5897..d33437007ad 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -1181,9 +1181,11 @@ void __key_link_end(struct key *keyring,
 	if (index_key->type == &key_type_keyring)
 		up_write(&keyring_serialise_link_sem);
 
-	if (edit && !edit->dead_leaf) {
-		key_payload_reserve(keyring,
-				    keyring->datalen - KEYQUOTA_LINK_BYTES);
+	if (edit) {
+		if (!edit->dead_leaf) {
+			key_payload_reserve(keyring,
+				keyring->datalen - KEYQUOTA_LINK_BYTES);
+		}
 		assoc_array_cancel_edit(edit);
 	}
 	up_write(&keyring->sem);
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 69fdf3bc765..7147c17fce7 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -245,6 +245,21 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 		}
 		break;
 	}
+	case LSM_AUDIT_DATA_IOCTL_OP: {
+		struct inode *inode;
+
+		audit_log_d_path(ab, " path=", &a->u.op->path);
+
+		inode = a->u.op->path.dentry->d_inode;
+		if (inode) {
+			audit_log_format(ab, " dev=");
+			audit_log_untrustedstring(ab, inode->i_sb->s_id);
+			audit_log_format(ab, " ino=%lu", inode->i_ino);
+		}
+
+		audit_log_format(ab, " ioctlcmd=%hx", a->u.op->cmd);
+		break;
+	}
 	case LSM_AUDIT_DATA_DENTRY: {
 		struct inode *inode;
 
diff --git a/security/security.c b/security/security.c
index 18b35c63fc0..6ad484c7930 100644
--- a/security/security.c
+++ b/security/security.c
@@ -135,6 +135,26 @@ int __init register_security(struct security_operations *ops)
 
 /* Security operations */
 
+int security_binder_set_context_mgr(struct task_struct *mgr)
+{
+	return security_ops->binder_set_context_mgr(mgr);
+}
+
+int security_binder_transaction(struct task_struct *from, struct task_struct *to)
+{
+	return security_ops->binder_transaction(from, to);
+}
+
+int security_binder_transfer_binder(struct task_struct *from, struct task_struct *to)
+{
+	return security_ops->binder_transfer_binder(from, to);
+}
+
+int security_binder_transfer_file(struct task_struct *from, struct task_struct *to, struct file *file)
+{
+	return security_ops->binder_transfer_file(from, to, file);
+}
+
 int security_ptrace_access_check(struct task_struct *child, unsigned int mode)
 {
 #ifdef CONFIG_SECURITY_YAMA_STACKED
diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index a18f1fa6440..21a34153df1 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/skbuff.h>
 #include <linux/percpu.h>
+#include <linux/list.h>
 #include <net/sock.h>
 #include <linux/un.h>
 #include <net/af_unix.h>
@@ -48,6 +49,7 @@ struct avc_entry {
 	u32			tsid;
 	u16			tclass;
 	struct av_decision	avd;
+	struct avc_operation_node *ops_node;
 };
 
 struct avc_node {
@@ -64,6 +66,16 @@ struct avc_cache {
 	u32			latest_notif;	/* latest revocation notification */
 };
 
+struct avc_operation_decision_node {
+	struct operation_decision od;
+	struct list_head od_list;
+};
+
+struct avc_operation_node {
+	struct operation ops;
+	struct list_head od_head; /* list of operation_decision_node */
+};
+
 struct avc_callback_node {
 	int (*callback) (u32 event);
 	u32 events;
@@ -80,6 +92,9 @@ DEFINE_PER_CPU(struct avc_cache_stats, avc_cache_stats) = { 0 };
 static struct avc_cache avc_cache;
 static struct avc_callback_node *avc_callbacks;
 static struct kmem_cache *avc_node_cachep;
+static struct kmem_cache *avc_operation_decision_node_cachep;
+static struct kmem_cache *avc_operation_node_cachep;
+static struct kmem_cache *avc_operation_perm_cachep;
 
 static inline int avc_hash(u32 ssid, u32 tsid, u16 tclass)
 {
@@ -171,6 +186,16 @@ void __init avc_init(void)
 
 	avc_node_cachep = kmem_cache_create("avc_node", sizeof(struct avc_node),
 					     0, SLAB_PANIC, NULL);
+	avc_operation_node_cachep = kmem_cache_create("avc_operation_node",
+				sizeof(struct avc_operation_node),
+				0, SLAB_PANIC, NULL);
+	avc_operation_decision_node_cachep = kmem_cache_create(
+				"avc_operation_decision_node",
+				sizeof(struct avc_operation_decision_node),
+				0, SLAB_PANIC, NULL);
+	avc_operation_perm_cachep = kmem_cache_create("avc_operation_perm",
+				sizeof(struct operation_perm),
+				0, SLAB_PANIC, NULL);
 
 	audit_log(current->audit_context, GFP_KERNEL, AUDIT_KERNEL, "AVC INITIALIZED\n");
 }
@@ -205,9 +230,271 @@ int avc_get_hash_stats(char *page)
 			 slots_used, AVC_CACHE_SLOTS, max_chain_len);
 }
 
+/*
+ * using a linked list for operation_decision lookup because the list is
+ * always small. i.e. less than 5, typically 1
+ */
+static struct operation_decision *avc_operation_lookup(u8 type,
+					struct avc_operation_node *ops_node)
+{
+	struct avc_operation_decision_node *od_node;
+	struct operation_decision *od = NULL;
+
+	list_for_each_entry(od_node, &ops_node->od_head, od_list) {
+		if (od_node->od.type != type)
+			continue;
+		od = &od_node->od;
+		break;
+	}
+	return od;
+}
+
+static inline unsigned int avc_operation_has_perm(struct operation_decision *od,
+						u16 cmd, u8 specified)
+{
+	unsigned int rc = 0;
+	u8 num = cmd & 0xff;
+
+	if ((specified == OPERATION_ALLOWED) &&
+			(od->specified & OPERATION_ALLOWED))
+		rc = security_operation_test(od->allowed->perms, num);
+	else if ((specified == OPERATION_AUDITALLOW) &&
+			(od->specified & OPERATION_AUDITALLOW))
+		rc = security_operation_test(od->auditallow->perms, num);
+	else if ((specified == OPERATION_DONTAUDIT) &&
+			(od->specified & OPERATION_DONTAUDIT))
+		rc = security_operation_test(od->dontaudit->perms, num);
+	return rc;
+}
+
+static void avc_operation_allow_perm(struct avc_operation_node *node, u16 cmd)
+{
+	struct operation_decision *od;
+	u8 type;
+	u8 num;
+
+	type = cmd >> 8;
+	num = cmd & 0xff;
+	security_operation_set(node->ops.type, type);
+	od = avc_operation_lookup(type, node);
+	if (od && od->allowed)
+		security_operation_set(od->allowed->perms, num);
+}
+
+static void avc_operation_decision_free(
+				struct avc_operation_decision_node *od_node)
+{
+	struct operation_decision *od;
+
+	od = &od_node->od;
+	if (od->allowed)
+		kmem_cache_free(avc_operation_perm_cachep, od->allowed);
+	if (od->auditallow)
+		kmem_cache_free(avc_operation_perm_cachep, od->auditallow);
+	if (od->dontaudit)
+		kmem_cache_free(avc_operation_perm_cachep, od->dontaudit);
+	kmem_cache_free(avc_operation_decision_node_cachep, od_node);
+}
+
+static void avc_operation_free(struct avc_operation_node *ops_node)
+{
+	struct avc_operation_decision_node *od_node, *tmp;
+
+	if (!ops_node)
+		return;
+
+	list_for_each_entry_safe(od_node, tmp, &ops_node->od_head, od_list) {
+		list_del(&od_node->od_list);
+		avc_operation_decision_free(od_node);
+	}
+	kmem_cache_free(avc_operation_node_cachep, ops_node);
+}
+
+static void avc_copy_operation_decision(struct operation_decision *dest,
+					struct operation_decision *src)
+{
+	dest->type = src->type;
+	dest->specified = src->specified;
+	if (dest->specified & OPERATION_ALLOWED)
+		memcpy(dest->allowed->perms, src->allowed->perms,
+				sizeof(src->allowed->perms));
+	if (dest->specified & OPERATION_AUDITALLOW)
+		memcpy(dest->auditallow->perms, src->auditallow->perms,
+				sizeof(src->auditallow->perms));
+	if (dest->specified & OPERATION_DONTAUDIT)
+		memcpy(dest->dontaudit->perms, src->dontaudit->perms,
+				sizeof(src->dontaudit->perms));
+}
+
+/*
+ * similar to avc_copy_operation_decision, but only copy decision
+ * information relevant to this command
+ */
+static inline void avc_quick_copy_operation_decision(u16 cmd,
+			struct operation_decision *dest,
+			struct operation_decision *src)
+{
+	/*
+	 * compute index of the u32 of the 256 bits (8 u32s) that contain this
+	 * command permission
+	 */
+	u8 i = (0xff & cmd) >> 5;
+
+	dest->specified = src->specified;
+	if (dest->specified & OPERATION_ALLOWED)
+		dest->allowed->perms[i] = src->allowed->perms[i];
+	if (dest->specified & OPERATION_AUDITALLOW)
+		dest->auditallow->perms[i] = src->auditallow->perms[i];
+	if (dest->specified & OPERATION_DONTAUDIT)
+		dest->dontaudit->perms[i] = src->dontaudit->perms[i];
+}
+
+static struct avc_operation_decision_node
+		*avc_operation_decision_alloc(u8 specified)
+{
+	struct avc_operation_decision_node *node;
+	struct operation_decision *od;
+
+	node = kmem_cache_zalloc(avc_operation_decision_node_cachep,
+				GFP_ATOMIC | __GFP_NOMEMALLOC);
+	if (!node)
+		return NULL;
+
+	od = &node->od;
+	if (specified & OPERATION_ALLOWED) {
+		od->allowed = kmem_cache_zalloc(avc_operation_perm_cachep,
+						GFP_ATOMIC | __GFP_NOMEMALLOC);
+		if (!od->allowed)
+			goto error;
+	}
+	if (specified & OPERATION_AUDITALLOW) {
+		od->auditallow = kmem_cache_zalloc(avc_operation_perm_cachep,
+						GFP_ATOMIC | __GFP_NOMEMALLOC);
+		if (!od->auditallow)
+			goto error;
+	}
+	if (specified & OPERATION_DONTAUDIT) {
+		od->dontaudit = kmem_cache_zalloc(avc_operation_perm_cachep,
+						GFP_ATOMIC | __GFP_NOMEMALLOC);
+		if (!od->dontaudit)
+			goto error;
+	}
+	return node;
+error:
+	avc_operation_decision_free(node);
+	return NULL;
+}
+
+static int avc_add_operation(struct avc_node *node,
+			struct operation_decision *od)
+{
+	struct avc_operation_decision_node *dest_od;
+
+	node->ae.ops_node->ops.len++;
+	dest_od = avc_operation_decision_alloc(od->specified);
+	if (!dest_od)
+		return -ENOMEM;
+	avc_copy_operation_decision(&dest_od->od, od);
+	list_add(&dest_od->od_list, &node->ae.ops_node->od_head);
+	return 0;
+}
+
+static struct avc_operation_node *avc_operation_alloc(void)
+{
+	struct avc_operation_node *ops;
+
+	ops = kmem_cache_zalloc(avc_operation_node_cachep,
+				GFP_ATOMIC|__GFP_NOMEMALLOC);
+	if (!ops)
+		return ops;
+	INIT_LIST_HEAD(&ops->od_head);
+	return ops;
+}
+
+static int avc_operation_populate(struct avc_node *node,
+				struct avc_operation_node *src)
+{
+	struct avc_operation_node *dest;
+	struct avc_operation_decision_node *dest_od;
+	struct avc_operation_decision_node *src_od;
+
+	if (src->ops.len == 0)
+		return 0;
+	dest = avc_operation_alloc();
+	if (!dest)
+		return -ENOMEM;
+
+	memcpy(dest->ops.type, &src->ops.type, sizeof(dest->ops.type));
+	dest->ops.len = src->ops.len;
+
+	/* for each source od allocate a destination od and copy */
+	list_for_each_entry(src_od, &src->od_head, od_list) {
+		dest_od = avc_operation_decision_alloc(src_od->od.specified);
+		if (!dest_od)
+			goto error;
+		avc_copy_operation_decision(&dest_od->od, &src_od->od);
+		list_add(&dest_od->od_list, &dest->od_head);
+	}
+	node->ae.ops_node = dest;
+	return 0;
+error:
+	avc_operation_free(dest);
+	return -ENOMEM;
+
+}
+
+static inline u32 avc_operation_audit_required(u32 requested,
+					struct av_decision *avd,
+					struct operation_decision *od,
+					u16 cmd,
+					int result,
+					u32 *deniedp)
+{
+	u32 denied, audited;
+
+	denied = requested & ~avd->allowed;
+	if (unlikely(denied)) {
+		audited = denied & avd->auditdeny;
+		if (audited && od) {
+			if (avc_operation_has_perm(od, cmd,
+						OPERATION_DONTAUDIT))
+				audited &= ~requested;
+		}
+	} else if (result) {
+		audited = denied = requested;
+	} else {
+		audited = requested & avd->auditallow;
+		if (audited && od) {
+			if (!avc_operation_has_perm(od, cmd,
+						OPERATION_AUDITALLOW))
+				audited &= ~requested;
+		}
+	}
+
+	*deniedp = denied;
+	return audited;
+}
+
+static inline int avc_operation_audit(u32 ssid, u32 tsid, u16 tclass,
+				u32 requested, struct av_decision *avd,
+				struct operation_decision *od,
+				u16 cmd, int result,
+				struct common_audit_data *ad)
+{
+	u32 audited, denied;
+
+	audited = avc_operation_audit_required(
+			requested, avd, od, cmd, result, &denied);
+	if (likely(!audited))
+		return 0;
+	return slow_avc_audit(ssid, tsid, tclass, requested,
+			audited, denied, result, ad, 0);
+}
+
 static void avc_node_free(struct rcu_head *rhead)
 {
 	struct avc_node *node = container_of(rhead, struct avc_node, rhead);
+	avc_operation_free(node->ae.ops_node);
 	kmem_cache_free(avc_node_cachep, node);
 	avc_cache_stats_incr(frees);
 }
@@ -221,6 +508,7 @@ static void avc_node_delete(struct avc_node *node)
 
 static void avc_node_kill(struct avc_node *node)
 {
+	avc_operation_free(node->ae.ops_node);
 	kmem_cache_free(avc_node_cachep, node);
 	avc_cache_stats_incr(frees);
 	atomic_dec(&avc_cache.active_nodes);
@@ -367,6 +655,7 @@ static int avc_latest_notif_update(int seqno, int is_insert)
  * @tsid: target security identifier
  * @tclass: target security class
  * @avd: resulting av decision
+ * @ops: resulting operation decisions
  *
  * Insert an AVC entry for the SID pair
  * (@ssid, @tsid) and class @tclass.
@@ -378,7 +667,9 @@ static int avc_latest_notif_update(int seqno, int is_insert)
  * the access vectors into a cache entry, returns
  * avc_node inserted. Otherwise, this function returns NULL.
  */
-static struct avc_node *avc_insert(u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd)
+static struct avc_node *avc_insert(u32 ssid, u32 tsid, u16 tclass,
+				struct av_decision *avd,
+				struct avc_operation_node *ops_node)
 {
 	struct avc_node *pos, *node = NULL;
 	int hvalue;
@@ -391,10 +682,15 @@ static struct avc_node *avc_insert(u32 ssid, u32 tsid, u16 tclass, struct av_dec
 	if (node) {
 		struct hlist_head *head;
 		spinlock_t *lock;
+		int rc = 0;
 
 		hvalue = avc_hash(ssid, tsid, tclass);
 		avc_node_populate(node, ssid, tsid, tclass, avd);
-
+		rc = avc_operation_populate(node, ops_node);
+		if (rc) {
+			kmem_cache_free(avc_node_cachep, node);
+			return NULL;
+		}
 		head = &avc_cache.slots[hvalue];
 		lock = &avc_cache.slots_lock[hvalue];
 
@@ -528,14 +824,17 @@ static inline int avc_sidcmp(u32 x, u32 y)
  * @perms : Permission mask bits
  * @ssid,@tsid,@tclass : identifier of an AVC entry
  * @seqno : sequence number when decision was made
+ * @od: operation_decision to be added to the node
  *
  * if a valid AVC entry doesn't exist,this function returns -ENOENT.
  * if kmalloc() called internal returns NULL, this function returns -ENOMEM.
  * otherwise, this function updates the AVC entry. The original AVC-entry object
  * will release later by RCU.
  */
-static int avc_update_node(u32 event, u32 perms, u32 ssid, u32 tsid, u16 tclass,
-			   u32 seqno)
+static int avc_update_node(u32 event, u32 perms, u16 cmd, u32 ssid, u32 tsid,
+			u16 tclass, u32 seqno,
+			struct operation_decision *od,
+			u32 flags)
 {
 	int hvalue, rc = 0;
 	unsigned long flag;
@@ -579,9 +878,19 @@ static int avc_update_node(u32 event, u32 perms, u32 ssid, u32 tsid, u16 tclass,
 
 	avc_node_populate(node, ssid, tsid, tclass, &orig->ae.avd);
 
+	if (orig->ae.ops_node) {
+		rc = avc_operation_populate(node, orig->ae.ops_node);
+		if (rc) {
+			kmem_cache_free(avc_node_cachep, node);
+			goto out_unlock;
+		}
+	}
+
 	switch (event) {
 	case AVC_CALLBACK_GRANT:
 		node->ae.avd.allowed |= perms;
+		if (node->ae.ops_node && (flags & AVC_OPERATION_CMD))
+			avc_operation_allow_perm(node->ae.ops_node, cmd);
 		break;
 	case AVC_CALLBACK_TRY_REVOKE:
 	case AVC_CALLBACK_REVOKE:
@@ -599,6 +908,9 @@ static int avc_update_node(u32 event, u32 perms, u32 ssid, u32 tsid, u16 tclass,
 	case AVC_CALLBACK_AUDITDENY_DISABLE:
 		node->ae.avd.auditdeny &= ~perms;
 		break;
+	case AVC_CALLBACK_ADD_OPERATION:
+		avc_add_operation(node, od);
+		break;
 	}
 	avc_node_replace(node, orig);
 out_unlock:
@@ -670,18 +982,20 @@ int avc_ss_reset(u32 seqno)
  * results in a bigger stack frame.
  */
 static noinline struct avc_node *avc_compute_av(u32 ssid, u32 tsid,
-			 u16 tclass, struct av_decision *avd)
+			 u16 tclass, struct av_decision *avd,
+			 struct avc_operation_node *ops_node)
 {
 	rcu_read_unlock();
-	security_compute_av(ssid, tsid, tclass, avd);
+	INIT_LIST_HEAD(&ops_node->od_head);
+	security_compute_av(ssid, tsid, tclass, avd, &ops_node->ops);
 	rcu_read_lock();
-	return avc_insert(ssid, tsid, tclass, avd);
+	return avc_insert(ssid, tsid, tclass, avd, ops_node);
 }
 
 static noinline int avc_denied(u32 ssid, u32 tsid,
-			 u16 tclass, u32 requested,
-			 unsigned flags,
-			 struct av_decision *avd)
+				u16 tclass, u32 requested,
+				u16 cmd, unsigned flags,
+				struct av_decision *avd)
 {
 	if (flags & AVC_STRICT)
 		return -EACCES;
@@ -689,11 +1003,92 @@ static noinline int avc_denied(u32 ssid, u32 tsid,
 	if (selinux_enforcing && !(avd->flags & AVD_FLAGS_PERMISSIVE))
 		return -EACCES;
 
-	avc_update_node(AVC_CALLBACK_GRANT, requested, ssid,
-				tsid, tclass, avd->seqno);
+	avc_update_node(AVC_CALLBACK_GRANT, requested, cmd, ssid,
+				tsid, tclass, avd->seqno, NULL, flags);
 	return 0;
 }
 
+/*
+ * ioctl commands are comprised of four fields, direction, size, type, and
+ * number. The avc operation logic filters based on two of them:
+ *
+ * type: or code, typically unique to each driver
+ * number: or function
+ *
+ * For example, 0x89 is a socket type, and number 0x27 is the get hardware
+ * address function.
+ */
+int avc_has_operation(u32 ssid, u32 tsid, u16 tclass, u32 requested,
+			u16 cmd, struct common_audit_data *ad)
+{
+	struct avc_node *node;
+	struct av_decision avd;
+	u32 denied;
+	struct operation_decision *od = NULL;
+	struct operation_decision od_local;
+	struct operation_perm allowed;
+	struct operation_perm auditallow;
+	struct operation_perm dontaudit;
+	struct avc_operation_node local_ops_node;
+	struct avc_operation_node *ops_node;
+	u8 type = cmd >> 8;
+	int rc = 0, rc2;
+
+	ops_node = &local_ops_node;
+	BUG_ON(!requested);
+
+	rcu_read_lock();
+
+	node = avc_lookup(ssid, tsid, tclass);
+	if (unlikely(!node)) {
+		node = avc_compute_av(ssid, tsid, tclass, &avd, ops_node);
+	} else {
+		memcpy(&avd, &node->ae.avd, sizeof(avd));
+		ops_node = node->ae.ops_node;
+	}
+	/* if operations are not defined, only consider av_decision */
+	if (!ops_node || !ops_node->ops.len)
+		goto decision;
+
+	od_local.allowed = &allowed;
+	od_local.auditallow = &auditallow;
+	od_local.dontaudit = &dontaudit;
+
+	/* lookup operation decision */
+	od = avc_operation_lookup(type, ops_node);
+	if (unlikely(!od)) {
+		/* Compute operation decision if type is flagged */
+		if (!security_operation_test(ops_node->ops.type, type)) {
+			avd.allowed &= ~requested;
+			goto decision;
+		}
+		rcu_read_unlock();
+		security_compute_operation(ssid, tsid, tclass, type, &od_local);
+		rcu_read_lock();
+		avc_update_node(AVC_CALLBACK_ADD_OPERATION, requested, cmd,
+				ssid, tsid, tclass, avd.seqno, &od_local, 0);
+	} else {
+		avc_quick_copy_operation_decision(cmd, &od_local, od);
+	}
+	od = &od_local;
+
+	if (!avc_operation_has_perm(od, cmd, OPERATION_ALLOWED))
+		avd.allowed &= ~requested;
+
+decision:
+	denied = requested & ~(avd.allowed);
+	if (unlikely(denied))
+		rc = avc_denied(ssid, tsid, tclass, requested, cmd,
+				AVC_OPERATION_CMD, &avd);
+
+	rcu_read_unlock();
+
+	rc2 = avc_operation_audit(ssid, tsid, tclass, requested,
+			&avd, od, cmd, rc, ad);
+	if (rc2)
+		return rc2;
+	return rc;
+}
 
 /**
  * avc_has_perm_noaudit - Check permissions but perform no auditing.
@@ -721,6 +1116,7 @@ inline int avc_has_perm_noaudit(u32 ssid, u32 tsid,
 			 struct av_decision *avd)
 {
 	struct avc_node *node;
+	struct avc_operation_node ops_node;
 	int rc = 0;
 	u32 denied;
 
@@ -729,16 +1125,14 @@ inline int avc_has_perm_noaudit(u32 ssid, u32 tsid,
 	rcu_read_lock();
 
 	node = avc_lookup(ssid, tsid, tclass);
-	if (unlikely(!node)) {
-		node = avc_compute_av(ssid, tsid, tclass, avd);
-	} else {
+	if (unlikely(!node))
+		node = avc_compute_av(ssid, tsid, tclass, avd, &ops_node);
+	else
 		memcpy(avd, &node->ae.avd, sizeof(*avd));
-		avd = &node->ae.avd;
-	}
 
 	denied = requested & ~(avd->allowed);
 	if (unlikely(denied))
-		rc = avc_denied(ssid, tsid, tclass, requested, flags, avd);
+		rc = avc_denied(ssid, tsid, tclass, requested, 0, flags, avd);
 
 	rcu_read_unlock();
 	return rc;
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index c603b20356a..cdce4947ebd 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -403,23 +403,15 @@ static int selinux_is_sblabel_mnt(struct super_block *sb)
 {
 	struct superblock_security_struct *sbsec = sb->s_security;
 
-	if (sbsec->behavior == SECURITY_FS_USE_XATTR ||
-	    sbsec->behavior == SECURITY_FS_USE_TRANS ||
-	    sbsec->behavior == SECURITY_FS_USE_TASK)
-		return 1;
-
-	/* Special handling for sysfs. Is genfs but also has setxattr handler*/
-	if (strncmp(sb->s_type->name, "sysfs", sizeof("sysfs")) == 0)
-		return 1;
-
-	/*
-	 * Special handling for rootfs. Is genfs but supports
-	 * setting SELinux context on in-core inodes.
-	 */
-	if (strncmp(sb->s_type->name, "rootfs", sizeof("rootfs")) == 0)
-		return 1;
-
-	return 0;
+	return sbsec->behavior == SECURITY_FS_USE_XATTR ||
+		sbsec->behavior == SECURITY_FS_USE_TRANS ||
+		sbsec->behavior == SECURITY_FS_USE_TASK ||
+		sbsec->behavior == SECURITY_FS_USE_NATIVE ||
+		/* Special handling. Genfs but also in-core setxattr handler */
+		!strcmp(sb->s_type->name, "sysfs") ||
+		!strcmp(sb->s_type->name, "pstore") ||
+		!strcmp(sb->s_type->name, "debugfs") ||
+		!strcmp(sb->s_type->name, "rootfs");
 }
 
 static int sb_finish_set_opts(struct super_block *sb)
@@ -740,7 +732,12 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 	}
 
 	if (strcmp(sb->s_type->name, "proc") == 0)
-		sbsec->flags |= SE_SBPROC;
+		sbsec->flags |= SE_SBPROC | SE_SBGENFS;
+
+	if (!strcmp(sb->s_type->name, "debugfs") ||
+	    !strcmp(sb->s_type->name, "sysfs") ||
+	    !strcmp(sb->s_type->name, "pstore"))
+		sbsec->flags |= SE_SBGENFS;
 
 	if (!sbsec->behavior) {
 		/*
@@ -1236,12 +1233,13 @@ static inline u16 socket_type_to_security_class(int family, int type, int protoc
 	return SECCLASS_SOCKET;
 }
 
-#ifdef CONFIG_PROC_FS
-static int selinux_proc_get_sid(struct dentry *dentry,
-				u16 tclass,
-				u32 *sid)
+static int selinux_genfs_get_sid(struct dentry *dentry,
+				 u16 tclass,
+				 u16 flags,
+				 u32 *sid)
 {
 	int rc;
+	struct super_block *sb = dentry->d_inode->i_sb;
 	char *buffer, *path;
 
 	buffer = (char *)__get_free_page(GFP_KERNEL);
@@ -1252,26 +1250,20 @@ static int selinux_proc_get_sid(struct dentry *dentry,
 	if (IS_ERR(path))
 		rc = PTR_ERR(path);
 	else {
-		/* each process gets a /proc/PID/ entry. Strip off the
-		 * PID part to get a valid selinux labeling.
-		 * e.g. /proc/1/net/rpc/nfs -> /net/rpc/nfs */
-		while (path[1] >= '0' && path[1] <= '9') {
-			path[1] = '/';
-			path++;
+		if (flags & SE_SBPROC) {
+			/* each process gets a /proc/PID/ entry. Strip off the
+			 * PID part to get a valid selinux labeling.
+			 * e.g. /proc/1/net/rpc/nfs -> /net/rpc/nfs */
+			while (path[1] >= '0' && path[1] <= '9') {
+				path[1] = '/';
+				path++;
+			}
 		}
-		rc = security_genfs_sid("proc", path, tclass, sid);
+		rc = security_genfs_sid(sb->s_type->name, path, tclass, sid);
 	}
 	free_page((unsigned long)buffer);
 	return rc;
 }
-#else
-static int selinux_proc_get_sid(struct dentry *dentry,
-				u16 tclass,
-				u32 *sid)
-{
-	return -EINVAL;
-}
-#endif
 
 /* The inode's security attributes must be initialized before first use. */
 static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry)
@@ -1428,7 +1420,7 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent
 		/* Default to the fs superblock SID. */
 		isec->sid = sbsec->sid;
 
-		if ((sbsec->flags & SE_SBPROC) && !S_ISLNK(inode->i_mode)) {
+		if ((sbsec->flags & SE_SBGENFS) && !S_ISLNK(inode->i_mode)) {
 			/* We must have a dentry to determine the label on
 			 * procfs inodes */
 			if (opt_dentry)
@@ -1451,7 +1443,8 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent
 			if (!dentry)
 				goto out_unlock;
 			isec->sclass = inode_mode_to_security_class(inode->i_mode);
-			rc = selinux_proc_get_sid(dentry, isec->sclass, &sid);
+			rc = selinux_genfs_get_sid(dentry, isec->sclass,
+						   sbsec->flags, &sid);
 			dput(dentry);
 			if (rc)
 				goto out_unlock;
@@ -1935,6 +1928,65 @@ static inline u32 open_file_to_av(struct file *file)
 
 /* Hook functions begin here. */
 
+static int selinux_binder_set_context_mgr(struct task_struct *mgr)
+{
+	u32 mysid = current_sid();
+	u32 mgrsid = task_sid(mgr);
+
+	return avc_has_perm(mysid, mgrsid, SECCLASS_BINDER, BINDER__SET_CONTEXT_MGR, NULL);
+}
+
+static int selinux_binder_transaction(struct task_struct *from, struct task_struct *to)
+{
+	u32 mysid = current_sid();
+	u32 fromsid = task_sid(from);
+	u32 tosid = task_sid(to);
+	int rc;
+
+	if (mysid != fromsid) {
+		rc = avc_has_perm(mysid, fromsid, SECCLASS_BINDER, BINDER__IMPERSONATE, NULL);
+		if (rc)
+			return rc;
+	}
+
+	return avc_has_perm(fromsid, tosid, SECCLASS_BINDER, BINDER__CALL, NULL);
+}
+
+static int selinux_binder_transfer_binder(struct task_struct *from, struct task_struct *to)
+{
+	u32 fromsid = task_sid(from);
+	u32 tosid = task_sid(to);
+	return avc_has_perm(fromsid, tosid, SECCLASS_BINDER, BINDER__TRANSFER, NULL);
+}
+
+static int selinux_binder_transfer_file(struct task_struct *from, struct task_struct *to, struct file *file)
+{
+	u32 sid = task_sid(to);
+	struct file_security_struct *fsec = file->f_security;
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct inode_security_struct *isec = inode->i_security;
+	struct common_audit_data ad;
+	int rc;
+
+	ad.type = LSM_AUDIT_DATA_PATH;
+	ad.u.path = file->f_path;
+
+	if (sid != fsec->sid) {
+		rc = avc_has_perm(sid, fsec->sid,
+				  SECCLASS_FD,
+				  FD__USE,
+				  &ad);
+		if (rc)
+			return rc;
+	}
+
+	if (unlikely(IS_PRIVATE(inode)))
+		return 0;
+
+	return avc_has_perm(sid, isec->sid, isec->sclass, file_to_av(file),
+			    &ad);
+}
+
 static int selinux_ptrace_access_check(struct task_struct *child,
 				     unsigned int mode)
 {
@@ -3186,6 +3238,44 @@ static void selinux_file_free_security(struct file *file)
 	file_free_security(file);
 }
 
+/*
+ * Check whether a task has the ioctl permission and cmd
+ * operation to an inode.
+ */
+int ioctl_has_perm(const struct cred *cred, struct file *file,
+		u32 requested, u16 cmd)
+{
+	struct common_audit_data ad;
+	struct file_security_struct *fsec = file->f_security;
+	struct inode *inode = file_inode(file);
+	struct inode_security_struct *isec = inode->i_security;
+	struct lsm_ioctlop_audit ioctl;
+	u32 ssid = cred_sid(cred);
+	int rc;
+
+	ad.type = LSM_AUDIT_DATA_IOCTL_OP;
+	ad.u.op = &ioctl;
+	ad.u.op->cmd = cmd;
+	ad.u.op->path = file->f_path;
+
+	if (ssid != fsec->sid) {
+		rc = avc_has_perm(ssid, fsec->sid,
+				SECCLASS_FD,
+				FD__USE,
+				&ad);
+		if (rc)
+			goto out;
+	}
+
+	if (unlikely(IS_PRIVATE(inode)))
+		return 0;
+
+	rc = avc_has_operation(ssid, isec->sid, isec->sclass,
+			requested, cmd, &ad);
+out:
+	return rc;
+}
+
 static int selinux_file_ioctl(struct file *file, unsigned int cmd,
 			      unsigned long arg)
 {
@@ -3228,7 +3318,7 @@ static int selinux_file_ioctl(struct file *file, unsigned int cmd,
 	 * to the file's ioctl() function.
 	 */
 	default:
-		error = file_has_perm(cred, file, FILE__IOCTL);
+		error = ioctl_has_perm(cred, file, FILE__IOCTL, (u16) cmd);
 	}
 	return error;
 }
@@ -5812,6 +5902,11 @@ static int selinux_key_getsecurity(struct key *key, char **_buffer)
 static struct security_operations selinux_ops = {
 	.name =				"selinux",
 
+	.binder_set_context_mgr =	selinux_binder_set_context_mgr,
+	.binder_transaction =		selinux_binder_transaction,
+	.binder_transfer_binder =	selinux_binder_transfer_binder,
+	.binder_transfer_file =		selinux_binder_transfer_file,
+
 	.ptrace_access_check =		selinux_ptrace_access_check,
 	.ptrace_traceme =		selinux_ptrace_traceme,
 	.capget =			selinux_capget,
diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h
index ddf8eec03f2..3165d4ed837 100644
--- a/security/selinux/include/avc.h
+++ b/security/selinux/include/avc.h
@@ -142,6 +142,7 @@ static inline int avc_audit(u32 ssid, u32 tsid,
 }
 
 #define AVC_STRICT 1 /* Ignore permissive mode. */
+#define AVC_OPERATION_CMD 2	/* ignore command when updating operations */
 int avc_has_perm_noaudit(u32 ssid, u32 tsid,
 			 u16 tclass, u32 requested,
 			 unsigned flags,
@@ -151,6 +152,9 @@ int avc_has_perm(u32 ssid, u32 tsid,
 		 u16 tclass, u32 requested,
 		 struct common_audit_data *auditdata);
 
+int avc_has_operation(u32 ssid, u32 tsid, u16 tclass, u32 requested,
+		u16 cmd, struct common_audit_data *ad);
+
 u32 avc_policy_seqno(void);
 
 #define AVC_CALLBACK_GRANT		1
@@ -161,6 +165,7 @@ u32 avc_policy_seqno(void);
 #define AVC_CALLBACK_AUDITALLOW_DISABLE	32
 #define AVC_CALLBACK_AUDITDENY_ENABLE	64
 #define AVC_CALLBACK_AUDITDENY_DISABLE	128
+#define AVC_CALLBACK_ADD_OPERATION	256
 
 int avc_add_callback(int (*callback)(u32 event), u32 events);
 
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index be491a74c1e..bdc9325a465 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -151,5 +151,6 @@ struct security_class_mapping secclass_map[] = {
 	{ "kernel_service", { "use_as_override", "create_files_as", NULL } },
 	{ "tun_socket",
 	  { COMMON_SOCK_PERMS, "attach_queue", NULL } },
+	{ "binder", { "impersonate", "call", "set_context_mgr", "transfer", NULL } },
 	{ NULL }
   };
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index d1e0b239b60..8d506832927 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -35,13 +35,14 @@
 #define POLICYDB_VERSION_NEW_OBJECT_DEFAULTS	27
 #define POLICYDB_VERSION_DEFAULT_TYPE	28
 #define POLICYDB_VERSION_CONSTRAINT_NAMES	29
+#define POLICYDB_VERSION_IOCTL_OPERATIONS	30
 
 /* Range of policy versions we understand*/
 #define POLICYDB_VERSION_MIN   POLICYDB_VERSION_BASE
 #ifdef CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX
 #define POLICYDB_VERSION_MAX	CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX_VALUE
 #else
-#define POLICYDB_VERSION_MAX	POLICYDB_VERSION_CONSTRAINT_NAMES
+#define POLICYDB_VERSION_MAX	POLICYDB_VERSION_IOCTL_OPERATIONS
 #endif
 
 /* Mask for just the mount related flags */
@@ -56,6 +57,7 @@
 /* Non-mount related flags */
 #define SE_SBINITIALIZED	0x0100
 #define SE_SBPROC		0x0200
+#define SE_SBGENFS		0x0400
 
 #define CONTEXT_STR	"context="
 #define FSCONTEXT_STR	"fscontext="
@@ -108,11 +110,40 @@ struct av_decision {
 	u32 flags;
 };
 
+#define security_operation_set(perms, x) (perms[x >> 5] |= 1 << (x & 0x1f))
+#define security_operation_test(perms, x) (1 & (perms[x >> 5] >> (x & 0x1f)))
+
+struct operation_perm {
+	u32 perms[8];
+};
+
+struct operation_decision {
+	u8 type;
+	u8 specified;
+	struct operation_perm *allowed;
+	struct operation_perm *auditallow;
+	struct operation_perm *dontaudit;
+};
+
+#define OPERATION_ALLOWED 1
+#define OPERATION_AUDITALLOW 2
+#define OPERATION_DONTAUDIT 4
+#define OPERATION_ALL (OPERATION_ALLOWED | OPERATION_AUDITALLOW |\
+			OPERATION_DONTAUDIT)
+struct operation {
+	u16 len;	/* length of operation decision chain */
+	u32 type[8];	/* 256 types */
+};
+
 /* definitions of av_decision.flags */
 #define AVD_FLAGS_PERMISSIVE	0x0001
 
 void security_compute_av(u32 ssid, u32 tsid,
-			 u16 tclass, struct av_decision *avd);
+			 u16 tclass, struct av_decision *avd,
+			 struct operation *ops);
+
+void security_compute_operation(u32 ssid, u32 tsid, u16 tclass,
+			 u8 type, struct operation_decision *od);
 
 void security_compute_av_user(u32 ssid, u32 tsid,
 			     u16 tclass, struct av_decision *avd);
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
index 2df7b900e25..902b5e9cec7 100644
--- a/security/selinux/nlmsgtab.c
+++ b/security/selinux/nlmsgtab.c
@@ -100,6 +100,13 @@ static struct nlmsg_perm nlmsg_xfrm_perms[] =
 	{ XFRM_MSG_FLUSHPOLICY,	NETLINK_XFRM_SOCKET__NLMSG_WRITE },
 	{ XFRM_MSG_NEWAE,	NETLINK_XFRM_SOCKET__NLMSG_WRITE },
 	{ XFRM_MSG_GETAE,	NETLINK_XFRM_SOCKET__NLMSG_READ  },
+	{ XFRM_MSG_REPORT,	NETLINK_XFRM_SOCKET__NLMSG_READ  },
+	{ XFRM_MSG_MIGRATE,	NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_NEWSADINFO,	NETLINK_XFRM_SOCKET__NLMSG_READ  },
+	{ XFRM_MSG_GETSADINFO,	NETLINK_XFRM_SOCKET__NLMSG_READ  },
+	{ XFRM_MSG_NEWSPDINFO,	NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_GETSPDINFO,	NETLINK_XFRM_SOCKET__NLMSG_READ  },
+	{ XFRM_MSG_MAPPING,	NETLINK_XFRM_SOCKET__NLMSG_READ  },
 };
 
 static struct nlmsg_perm nlmsg_audit_perms[] =
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index c71737f6d1c..138949a31ea 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -152,7 +152,7 @@ static ssize_t sel_write_enforce(struct file *file, const char __user *buf,
 		goto out;
 
 	/* No partial writes. */
-	length = EINVAL;
+	length = -EINVAL;
 	if (*ppos != 0)
 		goto out;
 
@@ -1200,7 +1200,7 @@ static void sel_remove_entries(struct dentry *de)
 	spin_lock(&de->d_lock);
 	node = de->d_subdirs.next;
 	while (node != &de->d_subdirs) {
-		struct dentry *d = list_entry(node, struct dentry, d_u.d_child);
+		struct dentry *d = list_entry(node, struct dentry, d_child);
 
 		spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
 		list_del_init(node);
@@ -1674,12 +1674,12 @@ static void sel_remove_classes(void)
 
 	list_for_each(class_node, &class_dir->d_subdirs) {
 		struct dentry *class_subdir = list_entry(class_node,
-					struct dentry, d_u.d_child);
+					struct dentry, d_child);
 		struct list_head *class_subdir_node;
 
 		list_for_each(class_subdir_node, &class_subdir->d_subdirs) {
 			struct dentry *d = list_entry(class_subdir_node,
-						struct dentry, d_u.d_child);
+						struct dentry, d_child);
 
 			if (d->d_inode)
 				if (d->d_inode->i_mode & S_IFDIR)
diff --git a/security/selinux/ss/avtab.c b/security/selinux/ss/avtab.c
index a3dd9faa19c..dd7466cb202 100644
--- a/security/selinux/ss/avtab.c
+++ b/security/selinux/ss/avtab.c
@@ -24,6 +24,7 @@
 #include "policydb.h"
 
 static struct kmem_cache *avtab_node_cachep;
+static struct kmem_cache *avtab_operation_cachep;
 
 static inline int avtab_hash(struct avtab_key *keyp, u16 mask)
 {
@@ -37,11 +38,24 @@ avtab_insert_node(struct avtab *h, int hvalue,
 		  struct avtab_key *key, struct avtab_datum *datum)
 {
 	struct avtab_node *newnode;
+	struct avtab_operation *ops;
 	newnode = kmem_cache_zalloc(avtab_node_cachep, GFP_KERNEL);
 	if (newnode == NULL)
 		return NULL;
 	newnode->key = *key;
-	newnode->datum = *datum;
+
+	if (key->specified & AVTAB_OP) {
+		ops = kmem_cache_zalloc(avtab_operation_cachep, GFP_KERNEL);
+		if (ops == NULL) {
+			kmem_cache_free(avtab_node_cachep, newnode);
+			return NULL;
+		}
+		*ops = *(datum->u.ops);
+		newnode->datum.u.ops = ops;
+	} else {
+		newnode->datum.u.data = datum->u.data;
+	}
+
 	if (prev) {
 		newnode->next = prev->next;
 		prev->next = newnode;
@@ -70,8 +84,11 @@ static int avtab_insert(struct avtab *h, struct avtab_key *key, struct avtab_dat
 		if (key->source_type == cur->key.source_type &&
 		    key->target_type == cur->key.target_type &&
 		    key->target_class == cur->key.target_class &&
-		    (specified & cur->key.specified))
+		    (specified & cur->key.specified)) {
+			if (specified & AVTAB_OPNUM)
+				break;
 			return -EEXIST;
+		}
 		if (key->source_type < cur->key.source_type)
 			break;
 		if (key->source_type == cur->key.source_type &&
@@ -232,6 +249,9 @@ void avtab_destroy(struct avtab *h)
 		while (cur) {
 			temp = cur;
 			cur = cur->next;
+			if (temp->key.specified & AVTAB_OP)
+				kmem_cache_free(avtab_operation_cachep,
+							temp->datum.u.ops);
 			kmem_cache_free(avtab_node_cachep, temp);
 		}
 		h->htable[i] = NULL;
@@ -320,7 +340,13 @@ static uint16_t spec_order[] = {
 	AVTAB_AUDITALLOW,
 	AVTAB_TRANSITION,
 	AVTAB_CHANGE,
-	AVTAB_MEMBER
+	AVTAB_MEMBER,
+	AVTAB_OPNUM_ALLOWED,
+	AVTAB_OPNUM_AUDITALLOW,
+	AVTAB_OPNUM_DONTAUDIT,
+	AVTAB_OPTYPE_ALLOWED,
+	AVTAB_OPTYPE_AUDITALLOW,
+	AVTAB_OPTYPE_DONTAUDIT
 };
 
 int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
@@ -330,10 +356,11 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
 {
 	__le16 buf16[4];
 	u16 enabled;
-	__le32 buf32[7];
 	u32 items, items2, val, vers = pol->policyvers;
 	struct avtab_key key;
 	struct avtab_datum datum;
+	struct avtab_operation ops;
+	__le32 buf32[ARRAY_SIZE(ops.op.perms)];
 	int i, rc;
 	unsigned set;
 
@@ -390,11 +417,15 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
 			printk(KERN_ERR "SELinux: avtab: entry has both access vectors and types\n");
 			return -EINVAL;
 		}
+		if (val & AVTAB_OP) {
+			printk(KERN_ERR "SELinux: avtab: entry has operations\n");
+			return -EINVAL;
+		}
 
 		for (i = 0; i < ARRAY_SIZE(spec_order); i++) {
 			if (val & spec_order[i]) {
 				key.specified = spec_order[i] | enabled;
-				datum.data = le32_to_cpu(buf32[items++]);
+				datum.u.data = le32_to_cpu(buf32[items++]);
 				rc = insertf(a, &key, &datum, p);
 				if (rc)
 					return rc;
@@ -413,7 +444,6 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
 		printk(KERN_ERR "SELinux: avtab: truncated entry\n");
 		return rc;
 	}
-
 	items = 0;
 	key.source_type = le16_to_cpu(buf16[items++]);
 	key.target_type = le16_to_cpu(buf16[items++]);
@@ -437,14 +467,32 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
 		return -EINVAL;
 	}
 
-	rc = next_entry(buf32, fp, sizeof(u32));
-	if (rc) {
-		printk(KERN_ERR "SELinux: avtab: truncated entry\n");
-		return rc;
+	if ((vers < POLICYDB_VERSION_IOCTL_OPERATIONS)
+			|| !(key.specified & AVTAB_OP)) {
+		rc = next_entry(buf32, fp, sizeof(u32));
+		if (rc) {
+			printk(KERN_ERR "SELinux: avtab: truncated entry\n");
+			return rc;
+		}
+		datum.u.data = le32_to_cpu(*buf32);
+	} else {
+		memset(&ops, 0, sizeof(struct avtab_operation));
+		rc = next_entry(&ops.type, fp, sizeof(u8));
+		if (rc) {
+			printk(KERN_ERR "SELinux: avtab: truncated entry\n");
+			return rc;
+		}
+		rc = next_entry(buf32, fp, sizeof(u32)*ARRAY_SIZE(ops.op.perms));
+		if (rc) {
+			printk(KERN_ERR "SELinux: avtab: truncated entry\n");
+			return rc;
+		}
+		for (i = 0; i < ARRAY_SIZE(ops.op.perms); i++)
+			ops.op.perms[i] = le32_to_cpu(buf32[i]);
+		datum.u.ops = &ops;
 	}
-	datum.data = le32_to_cpu(*buf32);
 	if ((key.specified & AVTAB_TYPE) &&
-	    !policydb_type_isvalid(pol, datum.data)) {
+	    !policydb_type_isvalid(pol, datum.u.data)) {
 		printk(KERN_ERR "SELinux: avtab: invalid type\n");
 		return -EINVAL;
 	}
@@ -504,8 +552,9 @@ bad:
 int avtab_write_item(struct policydb *p, struct avtab_node *cur, void *fp)
 {
 	__le16 buf16[4];
-	__le32 buf32[1];
+	__le32 buf32[ARRAY_SIZE(cur->datum.u.ops->op.perms)];
 	int rc;
+	unsigned int i;
 
 	buf16[0] = cpu_to_le16(cur->key.source_type);
 	buf16[1] = cpu_to_le16(cur->key.target_type);
@@ -514,8 +563,19 @@ int avtab_write_item(struct policydb *p, struct avtab_node *cur, void *fp)
 	rc = put_entry(buf16, sizeof(u16), 4, fp);
 	if (rc)
 		return rc;
-	buf32[0] = cpu_to_le32(cur->datum.data);
-	rc = put_entry(buf32, sizeof(u32), 1, fp);
+
+	if (cur->key.specified & AVTAB_OP) {
+		rc = put_entry(&cur->datum.u.ops->type, sizeof(u8), 1, fp);
+		if (rc)
+			return rc;
+		for (i = 0; i < ARRAY_SIZE(cur->datum.u.ops->op.perms); i++)
+			buf32[i] = cpu_to_le32(cur->datum.u.ops->op.perms[i]);
+		rc = put_entry(buf32, sizeof(u32),
+				ARRAY_SIZE(cur->datum.u.ops->op.perms), fp);
+	} else {
+		buf32[0] = cpu_to_le32(cur->datum.u.data);
+		rc = put_entry(buf32, sizeof(u32), 1, fp);
+	}
 	if (rc)
 		return rc;
 	return 0;
@@ -548,9 +608,13 @@ void avtab_cache_init(void)
 	avtab_node_cachep = kmem_cache_create("avtab_node",
 					      sizeof(struct avtab_node),
 					      0, SLAB_PANIC, NULL);
+	avtab_operation_cachep = kmem_cache_create("avtab_operation",
+					      sizeof(struct avtab_operation),
+					      0, SLAB_PANIC, NULL);
 }
 
 void avtab_cache_destroy(void)
 {
 	kmem_cache_destroy(avtab_node_cachep);
+	kmem_cache_destroy(avtab_operation_cachep);
 }
diff --git a/security/selinux/ss/avtab.h b/security/selinux/ss/avtab.h
index 63ce2f9e441..97acd6fa705 100644
--- a/security/selinux/ss/avtab.h
+++ b/security/selinux/ss/avtab.h
@@ -23,6 +23,8 @@
 #ifndef _SS_AVTAB_H_
 #define _SS_AVTAB_H_
 
+#include "security.h"
+
 struct avtab_key {
 	u16 source_type;	/* source type */
 	u16 target_type;	/* target type */
@@ -35,13 +37,34 @@ struct avtab_key {
 #define AVTAB_MEMBER		0x0020
 #define AVTAB_CHANGE		0x0040
 #define AVTAB_TYPE		(AVTAB_TRANSITION | AVTAB_MEMBER | AVTAB_CHANGE)
+#define AVTAB_OPNUM_ALLOWED	0x0100
+#define AVTAB_OPNUM_AUDITALLOW	0x0200
+#define AVTAB_OPNUM_DONTAUDIT	0x0400
+#define AVTAB_OPNUM		(AVTAB_OPNUM_ALLOWED | \
+				AVTAB_OPNUM_AUDITALLOW | \
+				AVTAB_OPNUM_DONTAUDIT)
+#define AVTAB_OPTYPE_ALLOWED	0x1000
+#define AVTAB_OPTYPE_AUDITALLOW	0x2000
+#define AVTAB_OPTYPE_DONTAUDIT	0x4000
+#define AVTAB_OPTYPE		(AVTAB_OPTYPE_ALLOWED | \
+				AVTAB_OPTYPE_AUDITALLOW | \
+				AVTAB_OPTYPE_DONTAUDIT)
+#define AVTAB_OP		(AVTAB_OPNUM | AVTAB_OPTYPE)
 #define AVTAB_ENABLED_OLD   0x80000000 /* reserved for used in cond_avtab */
 #define AVTAB_ENABLED		0x8000 /* reserved for used in cond_avtab */
 	u16 specified;	/* what field is specified */
 };
 
+struct avtab_operation {
+	u8 type;
+	struct operation_perm op;
+};
+
 struct avtab_datum {
-	u32 data; /* access vector or type value */
+	union {
+		u32 data; /* access vector or type value */
+		struct avtab_operation *ops; /* ioctl operations */
+	} u;
 };
 
 struct avtab_node {
diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c
index 62c6773be0b..c4cd20a2d5b 100644
--- a/security/selinux/ss/conditional.c
+++ b/security/selinux/ss/conditional.c
@@ -15,6 +15,7 @@
 
 #include "security.h"
 #include "conditional.h"
+#include "services.h"
 
 /*
  * cond_evaluate_expr evaluates a conditional expr
@@ -612,21 +613,39 @@ int cond_write_list(struct policydb *p, struct cond_node *list, void *fp)
 
 	return 0;
 }
+
+void cond_compute_operation(struct avtab *ctab, struct avtab_key *key,
+		struct operation_decision *od)
+{
+	struct avtab_node *node;
+
+	if (!ctab || !key || !od)
+		return;
+
+	for (node = avtab_search_node(ctab, key); node;
+			node = avtab_search_node_next(node, key->specified)) {
+		if (node->key.specified & AVTAB_ENABLED)
+			services_compute_operation_num(od, node);
+	}
+	return;
+
+}
 /* Determine whether additional permissions are granted by the conditional
  * av table, and if so, add them to the result
  */
-void cond_compute_av(struct avtab *ctab, struct avtab_key *key, struct av_decision *avd)
+void cond_compute_av(struct avtab *ctab, struct avtab_key *key,
+		struct av_decision *avd, struct operation *ops)
 {
 	struct avtab_node *node;
 
-	if (!ctab || !key || !avd)
+	if (!ctab || !key || !avd || !ops)
 		return;
 
 	for (node = avtab_search_node(ctab, key); node;
 				node = avtab_search_node_next(node, key->specified)) {
 		if ((u16)(AVTAB_ALLOWED|AVTAB_ENABLED) ==
 		    (node->key.specified & (AVTAB_ALLOWED|AVTAB_ENABLED)))
-			avd->allowed |= node->datum.data;
+			avd->allowed |= node->datum.u.data;
 		if ((u16)(AVTAB_AUDITDENY|AVTAB_ENABLED) ==
 		    (node->key.specified & (AVTAB_AUDITDENY|AVTAB_ENABLED)))
 			/* Since a '0' in an auditdeny mask represents a
@@ -634,10 +653,13 @@ void cond_compute_av(struct avtab *ctab, struct avtab_key *key, struct av_decisi
 			 * the '&' operand to ensure that all '0's in the mask
 			 * are retained (much unlike the allow and auditallow cases).
 			 */
-			avd->auditdeny &= node->datum.data;
+			avd->auditdeny &= node->datum.u.data;
 		if ((u16)(AVTAB_AUDITALLOW|AVTAB_ENABLED) ==
 		    (node->key.specified & (AVTAB_AUDITALLOW|AVTAB_ENABLED)))
-			avd->auditallow |= node->datum.data;
+			avd->auditallow |= node->datum.u.data;
+		if ((node->key.specified & AVTAB_ENABLED) &&
+				(node->key.specified & AVTAB_OP))
+			services_compute_operation_type(ops, node);
 	}
 	return;
 }
diff --git a/security/selinux/ss/conditional.h b/security/selinux/ss/conditional.h
index 4d1f8746650..80ee2bb20ee 100644
--- a/security/selinux/ss/conditional.h
+++ b/security/selinux/ss/conditional.h
@@ -73,8 +73,10 @@ int cond_read_list(struct policydb *p, void *fp);
 int cond_write_bool(void *key, void *datum, void *ptr);
 int cond_write_list(struct policydb *p, struct cond_node *list, void *fp);
 
-void cond_compute_av(struct avtab *ctab, struct avtab_key *key, struct av_decision *avd);
-
+void cond_compute_av(struct avtab *ctab, struct avtab_key *key,
+		struct av_decision *avd, struct operation *ops);
+void cond_compute_operation(struct avtab *ctab, struct avtab_key *key,
+		struct operation_decision *od);
 int evaluate_cond_node(struct policydb *p, struct cond_node *node);
 
 #endif /* _CONDITIONAL_H_ */
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index bc2a586f095..1c7daf20a2d 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -148,6 +148,11 @@ static struct policydb_compat_info policydb_compat[] = {
 		.sym_num	= SYM_NUM,
 		.ocon_num	= OCON_NUM,
 	},
+	{
+		.version	= POLICYDB_VERSION_IOCTL_OPERATIONS,
+		.sym_num	= SYM_NUM,
+		.ocon_num	= OCON_NUM,
+	},
 };
 
 static struct policydb_compat_info *policydb_lookup_compat(int version)
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index a1d3944751b..4eba19fd912 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -93,9 +93,10 @@ static int context_struct_to_string(struct context *context, char **scontext,
 				    u32 *scontext_len);
 
 static void context_struct_compute_av(struct context *scontext,
-				      struct context *tcontext,
-				      u16 tclass,
-				      struct av_decision *avd);
+					struct context *tcontext,
+					u16 tclass,
+					struct av_decision *avd,
+					struct operation *ops);
 
 struct selinux_mapping {
 	u16 value; /* policy value */
@@ -565,7 +566,8 @@ static void type_attribute_bounds_av(struct context *scontext,
 		context_struct_compute_av(&lo_scontext,
 					  tcontext,
 					  tclass,
-					  &lo_avd);
+					  &lo_avd,
+					  NULL);
 		if ((lo_avd.allowed & avd->allowed) == avd->allowed)
 			return;		/* no masked permission */
 		masked = ~lo_avd.allowed & avd->allowed;
@@ -580,7 +582,8 @@ static void type_attribute_bounds_av(struct context *scontext,
 		context_struct_compute_av(scontext,
 					  &lo_tcontext,
 					  tclass,
-					  &lo_avd);
+					  &lo_avd,
+					  NULL);
 		if ((lo_avd.allowed & avd->allowed) == avd->allowed)
 			return;		/* no masked permission */
 		masked = ~lo_avd.allowed & avd->allowed;
@@ -596,7 +599,8 @@ static void type_attribute_bounds_av(struct context *scontext,
 		context_struct_compute_av(&lo_scontext,
 					  &lo_tcontext,
 					  tclass,
-					  &lo_avd);
+					  &lo_avd,
+					  NULL);
 		if ((lo_avd.allowed & avd->allowed) == avd->allowed)
 			return;		/* no masked permission */
 		masked = ~lo_avd.allowed & avd->allowed;
@@ -612,14 +616,39 @@ static void type_attribute_bounds_av(struct context *scontext,
 	}
 }
 
+/* flag ioctl types that have operation permissions */
+void services_compute_operation_type(
+		struct operation *ops,
+		struct avtab_node *node)
+{
+	u8 type;
+	unsigned int i;
+
+	if (node->key.specified & AVTAB_OPTYPE) {
+		/* if allowing one or more complete types */
+		for (i = 0; i < ARRAY_SIZE(ops->type); i++)
+			ops->type[i] |= node->datum.u.ops->op.perms[i];
+	} else {
+		/* if allowing operations within a type */
+		type = node->datum.u.ops->type;
+		security_operation_set(ops->type, type);
+	}
+
+	/* If no ioctl commands are allowed, ignore auditallow and auditdeny */
+	if (node->key.specified & AVTAB_OPTYPE_ALLOWED ||
+			node->key.specified & AVTAB_OPNUM_ALLOWED)
+		ops->len = 1;
+}
+
 /*
- * Compute access vectors based on a context structure pair for
- * the permissions in a particular class.
+ * Compute access vectors and operations ranges based on a context
+ * structure pair for the permissions in a particular class.
  */
 static void context_struct_compute_av(struct context *scontext,
-				      struct context *tcontext,
-				      u16 tclass,
-				      struct av_decision *avd)
+					struct context *tcontext,
+					u16 tclass,
+					struct av_decision *avd,
+					struct operation *ops)
 {
 	struct constraint_node *constraint;
 	struct role_allow *ra;
@@ -633,6 +662,10 @@ static void context_struct_compute_av(struct context *scontext,
 	avd->allowed = 0;
 	avd->auditallow = 0;
 	avd->auditdeny = 0xffffffff;
+	if (ops) {
+		memset(&ops->type, 0, sizeof(ops->type));
+		ops->len = 0;
+	}
 
 	if (unlikely(!tclass || tclass > policydb.p_classes.nprim)) {
 		if (printk_ratelimit())
@@ -647,7 +680,7 @@ static void context_struct_compute_av(struct context *scontext,
 	 * this permission check, then use it.
 	 */
 	avkey.target_class = tclass;
-	avkey.specified = AVTAB_AV;
+	avkey.specified = AVTAB_AV | AVTAB_OP;
 	sattr = flex_array_get(policydb.type_attr_map_array, scontext->type - 1);
 	BUG_ON(!sattr);
 	tattr = flex_array_get(policydb.type_attr_map_array, tcontext->type - 1);
@@ -660,15 +693,17 @@ static void context_struct_compute_av(struct context *scontext,
 			     node;
 			     node = avtab_search_node_next(node, avkey.specified)) {
 				if (node->key.specified == AVTAB_ALLOWED)
-					avd->allowed |= node->datum.data;
+					avd->allowed |= node->datum.u.data;
 				else if (node->key.specified == AVTAB_AUDITALLOW)
-					avd->auditallow |= node->datum.data;
+					avd->auditallow |= node->datum.u.data;
 				else if (node->key.specified == AVTAB_AUDITDENY)
-					avd->auditdeny &= node->datum.data;
+					avd->auditdeny &= node->datum.u.data;
+				else if (ops && (node->key.specified & AVTAB_OP))
+					services_compute_operation_type(ops, node);
 			}
 
 			/* Check conditional av table for additional permissions */
-			cond_compute_av(&policydb.te_cond_avtab, &avkey, avd);
+			cond_compute_av(&policydb.te_cond_avtab, &avkey, avd, ops);
 
 		}
 	}
@@ -899,13 +934,138 @@ static void avd_init(struct av_decision *avd)
 	avd->flags = 0;
 }
 
+void services_compute_operation_num(struct operation_decision *od,
+					struct avtab_node *node)
+{
+	unsigned int i;
 
+	if (node->key.specified & AVTAB_OPNUM) {
+		if (od->type != node->datum.u.ops->type)
+			return;
+	} else {
+		if (!security_operation_test(node->datum.u.ops->op.perms,
+					od->type))
+			return;
+	}
+
+	if (node->key.specified == AVTAB_OPTYPE_ALLOWED) {
+		od->specified |= OPERATION_ALLOWED;
+		memset(od->allowed->perms, 0xff,
+				sizeof(od->allowed->perms));
+	} else if (node->key.specified == AVTAB_OPTYPE_AUDITALLOW) {
+		od->specified |= OPERATION_AUDITALLOW;
+		memset(od->auditallow->perms, 0xff,
+				sizeof(od->auditallow->perms));
+	} else if (node->key.specified == AVTAB_OPTYPE_DONTAUDIT) {
+		od->specified |= OPERATION_DONTAUDIT;
+		memset(od->dontaudit->perms, 0xff,
+				sizeof(od->dontaudit->perms));
+	} else if (node->key.specified == AVTAB_OPNUM_ALLOWED) {
+		od->specified |= OPERATION_ALLOWED;
+		for (i = 0; i < ARRAY_SIZE(od->allowed->perms); i++)
+			od->allowed->perms[i] |=
+					node->datum.u.ops->op.perms[i];
+	} else if (node->key.specified == AVTAB_OPNUM_AUDITALLOW) {
+		od->specified |= OPERATION_AUDITALLOW;
+		for (i = 0; i < ARRAY_SIZE(od->auditallow->perms); i++)
+			od->auditallow->perms[i] |=
+					node->datum.u.ops->op.perms[i];
+	} else if (node->key.specified == AVTAB_OPNUM_DONTAUDIT) {
+		od->specified |= OPERATION_DONTAUDIT;
+		for (i = 0; i < ARRAY_SIZE(od->dontaudit->perms); i++)
+			od->dontaudit->perms[i] |=
+					node->datum.u.ops->op.perms[i];
+	} else {
+		BUG();
+	}
+}
+
+void security_compute_operation(u32 ssid,
+				u32 tsid,
+				u16 orig_tclass,
+				u8 type,
+				struct operation_decision *od)
+{
+	u16 tclass;
+	struct context *scontext, *tcontext;
+	struct avtab_key avkey;
+	struct avtab_node *node;
+	struct ebitmap *sattr, *tattr;
+	struct ebitmap_node *snode, *tnode;
+	unsigned int i, j;
+
+	od->type = type;
+	od->specified = 0;
+	memset(od->allowed->perms, 0, sizeof(od->allowed->perms));
+	memset(od->auditallow->perms, 0, sizeof(od->auditallow->perms));
+	memset(od->dontaudit->perms, 0, sizeof(od->dontaudit->perms));
+
+	read_lock(&policy_rwlock);
+	if (!ss_initialized)
+		goto allow;
+
+	scontext = sidtab_search(&sidtab, ssid);
+	if (!scontext) {
+		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		       __func__, ssid);
+		goto out;
+	}
+
+	tcontext = sidtab_search(&sidtab, tsid);
+	if (!tcontext) {
+		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		       __func__, tsid);
+		goto out;
+	}
+
+	tclass = unmap_class(orig_tclass);
+	if (unlikely(orig_tclass && !tclass)) {
+		if (policydb.allow_unknown)
+			goto allow;
+		goto out;
+	}
+
+
+	if (unlikely(!tclass || tclass > policydb.p_classes.nprim)) {
+		pr_warn_ratelimited("SELinux:  Invalid class %hu\n", tclass);
+		goto out;
+	}
+
+	avkey.target_class = tclass;
+	avkey.specified = AVTAB_OP;
+	sattr = flex_array_get(policydb.type_attr_map_array,
+				scontext->type - 1);
+	BUG_ON(!sattr);
+	tattr = flex_array_get(policydb.type_attr_map_array,
+				tcontext->type - 1);
+	BUG_ON(!tattr);
+	ebitmap_for_each_positive_bit(sattr, snode, i) {
+		ebitmap_for_each_positive_bit(tattr, tnode, j) {
+			avkey.source_type = i + 1;
+			avkey.target_type = j + 1;
+			for (node = avtab_search_node(&policydb.te_avtab, &avkey);
+			     node;
+			     node = avtab_search_node_next(node, avkey.specified))
+				services_compute_operation_num(od, node);
+
+			cond_compute_operation(&policydb.te_cond_avtab,
+						&avkey, od);
+		}
+	}
+out:
+	read_unlock(&policy_rwlock);
+	return;
+allow:
+	memset(od->allowed->perms, 0xff, sizeof(od->allowed->perms));
+	goto out;
+}
 /**
  * security_compute_av - Compute access vector decisions.
  * @ssid: source security identifier
  * @tsid: target security identifier
  * @tclass: target security class
  * @avd: access vector decisions
+ * @od: operation decisions
  *
  * Compute a set of access vector decisions based on the
  * SID pair (@ssid, @tsid) for the permissions in @tclass.
@@ -913,13 +1073,15 @@ static void avd_init(struct av_decision *avd)
 void security_compute_av(u32 ssid,
 			 u32 tsid,
 			 u16 orig_tclass,
-			 struct av_decision *avd)
+			 struct av_decision *avd,
+			 struct operation *ops)
 {
 	u16 tclass;
 	struct context *scontext = NULL, *tcontext = NULL;
 
 	read_lock(&policy_rwlock);
 	avd_init(avd);
+	ops->len = 0;
 	if (!ss_initialized)
 		goto allow;
 
@@ -947,7 +1109,7 @@ void security_compute_av(u32 ssid,
 			goto allow;
 		goto out;
 	}
-	context_struct_compute_av(scontext, tcontext, tclass, avd);
+	context_struct_compute_av(scontext, tcontext, tclass, avd, ops);
 	map_decision(orig_tclass, avd, policydb.allow_unknown);
 out:
 	read_unlock(&policy_rwlock);
@@ -993,7 +1155,7 @@ void security_compute_av_user(u32 ssid,
 		goto out;
 	}
 
-	context_struct_compute_av(scontext, tcontext, tclass, avd);
+	context_struct_compute_av(scontext, tcontext, tclass, avd, NULL);
  out:
 	read_unlock(&policy_rwlock);
 	return;
@@ -1515,7 +1677,7 @@ static int security_compute_sid(u32 ssid,
 
 	if (avdatum) {
 		/* Use the type from the type transition/member/change rule. */
-		newcontext.type = avdatum->data;
+		newcontext.type = avdatum->u.data;
 	}
 
 	/* if we have a objname this is a file trans check so check those rules */
diff --git a/security/selinux/ss/services.h b/security/selinux/ss/services.h
index e8d907e903c..569757484d0 100644
--- a/security/selinux/ss/services.h
+++ b/security/selinux/ss/services.h
@@ -11,5 +11,11 @@
 
 extern struct policydb policydb;
 
+void services_compute_operation_type(struct operation *ops,
+				struct avtab_node *node);
+
+void services_compute_operation_num(struct operation_decision *od,
+					struct avtab_node *node);
+
 #endif	/* _SS_SERVICES_H_ */
 
diff --git a/security/smack/smack.h b/security/smack/smack.h
index b828a379377..b48359c0da3 100644
--- a/security/smack/smack.h
+++ b/security/smack/smack.h
@@ -298,6 +298,16 @@ static inline struct smack_known *smk_of_task(const struct task_smack *tsp)
 	return tsp->smk_task;
 }
 
+static inline struct smack_known *smk_of_task_struct(const struct task_struct *t)
+{
+	struct smack_known *skp;
+
+	rcu_read_lock();
+	skp = smk_of_task(__task_cred(t)->security);
+	rcu_read_unlock();
+	return skp;
+}
+
 /*
  * Present a pointer to the forked smack label entry in an task blob.
  */
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index d515ec25ae9..9d3c64af1ca 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -43,8 +43,6 @@
 #include <linux/binfmts.h>
 #include "smack.h"
 
-#define task_security(task)	(task_cred_xxx((task), security))
-
 #define TRANS_TRUE	"TRUE"
 #define TRANS_TRUE_SIZE	4
 
@@ -119,7 +117,7 @@ static int smk_bu_current(char *note, struct smack_known *oskp,
 static int smk_bu_task(struct task_struct *otp, int mode, int rc)
 {
 	struct task_smack *tsp = current_security();
-	struct task_smack *otsp = task_security(otp);
+	struct smack_known *smk_task = smk_of_task_struct(otp);
 	char acc[SMK_NUM_ACCESS_TYPE + 1];
 
 	if (rc <= 0)
@@ -127,7 +125,7 @@ static int smk_bu_task(struct task_struct *otp, int mode, int rc)
 
 	smk_bu_mode(mode, acc);
 	pr_info("Smack Bringup: (%s %s %s) %s to %s\n",
-		tsp->smk_task->smk_known, otsp->smk_task->smk_known, acc,
+		tsp->smk_task->smk_known, smk_task->smk_known, acc,
 		current->comm, otp->comm);
 	return 0;
 }
@@ -344,7 +342,8 @@ static int smk_ptrace_rule_check(struct task_struct *tracer,
 		saip = &ad;
 	}
 
-	tsp = task_security(tracer);
+	rcu_read_lock();
+	tsp = __task_cred(tracer)->security;
 	tracer_known = smk_of_task(tsp);
 
 	if ((mode & PTRACE_MODE_ATTACH) &&
@@ -364,11 +363,14 @@ static int smk_ptrace_rule_check(struct task_struct *tracer,
 				  tracee_known->smk_known,
 				  0, rc, saip);
 
+		rcu_read_unlock();
 		return rc;
 	}
 
 	/* In case of rule==SMACK_PTRACE_DEFAULT or mode==PTRACE_MODE_READ */
 	rc = smk_tskacc(tsp, tracee_known, smk_ptrace_mode(mode), saip);
+
+	rcu_read_unlock();
 	return rc;
 }
 
@@ -395,7 +397,7 @@ static int smack_ptrace_access_check(struct task_struct *ctp, unsigned int mode)
 	if (rc != 0)
 		return rc;
 
-	skp = smk_of_task(task_security(ctp));
+	skp = smk_of_task_struct(ctp);
 
 	rc = smk_ptrace_rule_check(current, skp, mode, __func__);
 	return rc;
@@ -1825,7 +1827,7 @@ static int smk_curacc_on_task(struct task_struct *p, int access,
 				const char *caller)
 {
 	struct smk_audit_info ad;
-	struct smack_known *skp = smk_of_task(task_security(p));
+	struct smack_known *skp = smk_of_task_struct(p);
 	int rc;
 
 	smk_ad_init(&ad, caller, LSM_AUDIT_DATA_TASK);
@@ -1878,7 +1880,7 @@ static int smack_task_getsid(struct task_struct *p)
  */
 static void smack_task_getsecid(struct task_struct *p, u32 *secid)
 {
-	struct smack_known *skp = smk_of_task(task_security(p));
+	struct smack_known *skp = smk_of_task_struct(p);
 
 	*secid = skp->smk_secid;
 }
@@ -1985,7 +1987,7 @@ static int smack_task_kill(struct task_struct *p, struct siginfo *info,
 {
 	struct smk_audit_info ad;
 	struct smack_known *skp;
-	struct smack_known *tkp = smk_of_task(task_security(p));
+	struct smack_known *tkp = smk_of_task_struct(p);
 	int rc;
 
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
@@ -2039,7 +2041,7 @@ static int smack_task_wait(struct task_struct *p)
 static void smack_task_to_inode(struct task_struct *p, struct inode *inode)
 {
 	struct inode_smack *isp = inode->i_security;
-	struct smack_known *skp = smk_of_task(task_security(p));
+	struct smack_known *skp = smk_of_task_struct(p);
 
 	isp->smk_inode = skp;
 }
@@ -3199,7 +3201,7 @@ unlockandout:
  */
 static int smack_getprocattr(struct task_struct *p, char *name, char **value)
 {
-	struct smack_known *skp = smk_of_task(task_security(p));
+	struct smack_known *skp = smk_of_task_struct(p);
 	char *cp;
 	int slen;
 
diff --git a/sound/core/control.c b/sound/core/control.c
index b9611344ff9..82a638a01b2 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -1167,6 +1167,10 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file,
 
 	if (info->count < 1)
 		return -EINVAL;
+	if (!*info->id.name)
+		return -EINVAL;
+	if (strnlen(info->id.name, sizeof(info->id.name)) >= sizeof(info->id.name))
+		return -EINVAL;
 	access = info->access == 0 ? SNDRV_CTL_ELEM_ACCESS_READWRITE :
 		(info->access & (SNDRV_CTL_ELEM_ACCESS_READWRITE|
 				 SNDRV_CTL_ELEM_ACCESS_INACTIVE|
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 166d59cdc86..9c823cfdfff 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -1523,6 +1523,8 @@ static int snd_pcm_do_drain_init(struct snd_pcm_substream *substream, int state)
 			if (! snd_pcm_playback_empty(substream)) {
 				snd_pcm_do_start(substream, SNDRV_PCM_STATE_DRAINING);
 				snd_pcm_post_start(substream, SNDRV_PCM_STATE_DRAINING);
+			} else {
+				runtime->status->state = SNDRV_PCM_STATE_SETUP;
 			}
 			break;
 		case SNDRV_PCM_STATE_RUNNING:
diff --git a/sound/core/seq/seq_dummy.c b/sound/core/seq/seq_dummy.c
index ec667f158f1..5d905d90d50 100644
--- a/sound/core/seq/seq_dummy.c
+++ b/sound/core/seq/seq_dummy.c
@@ -82,36 +82,6 @@ struct snd_seq_dummy_port {
 static int my_client = -1;
 
 /*
- * unuse callback - send ALL_SOUNDS_OFF and RESET_CONTROLLERS events
- * to subscribers.
- * Note: this callback is called only after all subscribers are removed.
- */
-static int
-dummy_unuse(void *private_data, struct snd_seq_port_subscribe *info)
-{
-	struct snd_seq_dummy_port *p;
-	int i;
-	struct snd_seq_event ev;
-
-	p = private_data;
-	memset(&ev, 0, sizeof(ev));
-	if (p->duplex)
-		ev.source.port = p->connect;
-	else
-		ev.source.port = p->port;
-	ev.dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS;
-	ev.type = SNDRV_SEQ_EVENT_CONTROLLER;
-	for (i = 0; i < 16; i++) {
-		ev.data.control.channel = i;
-		ev.data.control.param = MIDI_CTL_ALL_SOUNDS_OFF;
-		snd_seq_kernel_client_dispatch(p->client, &ev, 0, 0);
-		ev.data.control.param = MIDI_CTL_RESET_CONTROLLERS;
-		snd_seq_kernel_client_dispatch(p->client, &ev, 0, 0);
-	}
-	return 0;
-}
-
-/*
  * event input callback - just redirect events to subscribers
  */
 static int
@@ -175,7 +145,6 @@ create_port(int idx, int type)
 		| SNDRV_SEQ_PORT_TYPE_PORT;
 	memset(&pcb, 0, sizeof(pcb));
 	pcb.owner = THIS_MODULE;
-	pcb.unuse = dummy_unuse;
 	pcb.event_input = dummy_input;
 	pcb.private_free = dummy_free;
 	pcb.private_data = rec;
diff --git a/sound/firewire/bebob/bebob_maudio.c b/sound/firewire/bebob/bebob_maudio.c
index 70faa3a3252..0215a9194d8 100644
--- a/sound/firewire/bebob/bebob_maudio.c
+++ b/sound/firewire/bebob/bebob_maudio.c
@@ -96,10 +96,10 @@ int snd_bebob_maudio_load_firmware(struct fw_unit *unit)
 	struct fw_device *device = fw_parent_device(unit);
 	int err, rcode;
 	u64 date;
-	__be32 cues[3] = {
-		MAUDIO_BOOTLOADER_CUE1,
-		MAUDIO_BOOTLOADER_CUE2,
-		MAUDIO_BOOTLOADER_CUE3
+	__le32 cues[3] = {
+		cpu_to_le32(MAUDIO_BOOTLOADER_CUE1),
+		cpu_to_le32(MAUDIO_BOOTLOADER_CUE2),
+		cpu_to_le32(MAUDIO_BOOTLOADER_CUE3)
 	};
 
 	/* check date of software used to build */
diff --git a/sound/firewire/fireworks/fireworks_transaction.c b/sound/firewire/fireworks/fireworks_transaction.c
index 255dabc6fc3..2a85e4209f0 100644
--- a/sound/firewire/fireworks/fireworks_transaction.c
+++ b/sound/firewire/fireworks/fireworks_transaction.c
@@ -124,7 +124,7 @@ copy_resp_to_buf(struct snd_efw *efw, void *data, size_t length, int *rcode)
 	spin_lock_irq(&efw->lock);
 
 	t = (struct snd_efw_transaction *)data;
-	length = min_t(size_t, t->length * sizeof(t->length), length);
+	length = min_t(size_t, be32_to_cpu(t->length) * sizeof(u32), length);
 
 	if (efw->push_ptr < efw->pull_ptr)
 		capacity = (unsigned int)(efw->pull_ptr - efw->push_ptr);
diff --git a/sound/i2c/other/ak4113.c b/sound/i2c/other/ak4113.c
index 1a3a6fa2715..c6bba99a90b 100644
--- a/sound/i2c/other/ak4113.c
+++ b/sound/i2c/other/ak4113.c
@@ -56,8 +56,7 @@ static inline unsigned char reg_read(struct ak4113 *ak4113, unsigned char reg)
 
 static void snd_ak4113_free(struct ak4113 *chip)
 {
-	chip->init = 1;	/* don't schedule new work */
-	mb();
+	atomic_inc(&chip->wq_processing);	/* don't schedule new work */
 	cancel_delayed_work_sync(&chip->work);
 	kfree(chip);
 }
@@ -89,6 +88,7 @@ int snd_ak4113_create(struct snd_card *card, ak4113_read_t *read,
 	chip->write = write;
 	chip->private_data = private_data;
 	INIT_DELAYED_WORK(&chip->work, ak4113_stats);
+	atomic_set(&chip->wq_processing, 0);
 
 	for (reg = 0; reg < AK4113_WRITABLE_REGS ; reg++)
 		chip->regmap[reg] = pgm[reg];
@@ -139,13 +139,11 @@ static void ak4113_init_regs(struct ak4113 *chip)
 
 void snd_ak4113_reinit(struct ak4113 *chip)
 {
-	chip->init = 1;
-	mb();
-	flush_delayed_work(&chip->work);
+	if (atomic_inc_return(&chip->wq_processing) == 1)
+		cancel_delayed_work_sync(&chip->work);
 	ak4113_init_regs(chip);
 	/* bring up statistics / event queing */
-	chip->init = 0;
-	if (chip->kctls[0])
+	if (atomic_dec_and_test(&chip->wq_processing))
 		schedule_delayed_work(&chip->work, HZ / 10);
 }
 EXPORT_SYMBOL_GPL(snd_ak4113_reinit);
@@ -632,8 +630,9 @@ static void ak4113_stats(struct work_struct *work)
 {
 	struct ak4113 *chip = container_of(work, struct ak4113, work.work);
 
-	if (!chip->init)
+	if (atomic_inc_return(&chip->wq_processing) == 1)
 		snd_ak4113_check_rate_and_errors(chip, chip->check_flags);
 
-	schedule_delayed_work(&chip->work, HZ / 10);
+	if (atomic_dec_and_test(&chip->wq_processing))
+		schedule_delayed_work(&chip->work, HZ / 10);
 }
diff --git a/sound/i2c/other/ak4114.c b/sound/i2c/other/ak4114.c
index c7f56339415..b70e6eccbd0 100644
--- a/sound/i2c/other/ak4114.c
+++ b/sound/i2c/other/ak4114.c
@@ -66,8 +66,7 @@ static void reg_dump(struct ak4114 *ak4114)
 
 static void snd_ak4114_free(struct ak4114 *chip)
 {
-	chip->init = 1;	/* don't schedule new work */
-	mb();
+	atomic_inc(&chip->wq_processing);	/* don't schedule new work */
 	cancel_delayed_work_sync(&chip->work);
 	kfree(chip);
 }
@@ -100,6 +99,7 @@ int snd_ak4114_create(struct snd_card *card,
 	chip->write = write;
 	chip->private_data = private_data;
 	INIT_DELAYED_WORK(&chip->work, ak4114_stats);
+	atomic_set(&chip->wq_processing, 0);
 
 	for (reg = 0; reg < 6; reg++)
 		chip->regmap[reg] = pgm[reg];
@@ -152,13 +152,11 @@ static void ak4114_init_regs(struct ak4114 *chip)
 
 void snd_ak4114_reinit(struct ak4114 *chip)
 {
-	chip->init = 1;
-	mb();
-	flush_delayed_work(&chip->work);
+	if (atomic_inc_return(&chip->wq_processing) == 1)
+		cancel_delayed_work_sync(&chip->work);
 	ak4114_init_regs(chip);
 	/* bring up statistics / event queing */
-	chip->init = 0;
-	if (chip->kctls[0])
+	if (atomic_dec_and_test(&chip->wq_processing))
 		schedule_delayed_work(&chip->work, HZ / 10);
 }
 
@@ -612,10 +610,10 @@ static void ak4114_stats(struct work_struct *work)
 {
 	struct ak4114 *chip = container_of(work, struct ak4114, work.work);
 
-	if (!chip->init)
+	if (atomic_inc_return(&chip->wq_processing) == 1)
 		snd_ak4114_check_rate_and_errors(chip, chip->check_flags);
-
-	schedule_delayed_work(&chip->work, HZ / 10);
+	if (atomic_dec_and_test(&chip->wq_processing))
+		schedule_delayed_work(&chip->work, HZ / 10);
 }
 
 EXPORT_SYMBOL(snd_ak4114_create);
diff --git a/sound/oss/sequencer.c b/sound/oss/sequencer.c
index c0eea1dfe90..f19da4b47c1 100644
--- a/sound/oss/sequencer.c
+++ b/sound/oss/sequencer.c
@@ -681,13 +681,8 @@ static int seq_timing_event(unsigned char *event_rec)
 			break;
 
 		case TMR_ECHO:
-			if (seq_mode == SEQ_2)
-				seq_copy_to_input(event_rec, 8);
-			else
-			{
-				parm = (parm << 8 | SEQ_ECHO);
-				seq_copy_to_input((unsigned char *) &parm, 4);
-			}
+			parm = (parm << 8 | SEQ_ECHO);
+			seq_copy_to_input((unsigned char *) &parm, 4);
 			break;
 
 		default:;
@@ -1324,7 +1319,6 @@ int sequencer_ioctl(int dev, struct file *file, unsigned int cmd, void __user *a
 	int mode = translate_mode(file);
 	struct synth_info inf;
 	struct seq_event_rec event_rec;
-	unsigned long flags;
 	int __user *p = arg;
 
 	orig_dev = dev = dev >> 4;
@@ -1479,9 +1473,7 @@ int sequencer_ioctl(int dev, struct file *file, unsigned int cmd, void __user *a
 		case SNDCTL_SEQ_OUTOFBAND:
 			if (copy_from_user(&event_rec, arg, sizeof(event_rec)))
 				return -EFAULT;
-			spin_lock_irqsave(&lock,flags);
 			play_event(event_rec.arr);
-			spin_unlock_irqrestore(&lock,flags);
 			return 0;
 
 		case SNDCTL_MIDI_INFO:
diff --git a/sound/pci/emu10k1/emu10k1.c b/sound/pci/emu10k1/emu10k1.c
index 4c171636efc..a432b4c7869 100644
--- a/sound/pci/emu10k1/emu10k1.c
+++ b/sound/pci/emu10k1/emu10k1.c
@@ -183,8 +183,10 @@ static int snd_card_emu10k1_probe(struct pci_dev *pci,
 	}
 #endif
  
-	strcpy(card->driver, emu->card_capabilities->driver);
-	strcpy(card->shortname, emu->card_capabilities->name);
+	strlcpy(card->driver, emu->card_capabilities->driver,
+		sizeof(card->driver));
+	strlcpy(card->shortname, emu->card_capabilities->name,
+		sizeof(card->shortname));
 	snprintf(card->longname, sizeof(card->longname),
 		 "%s (rev.%d, serial:0x%x) at 0x%lx, irq %i",
 		 card->shortname, emu->revision, emu->serial, emu->port, emu->irq);
diff --git a/sound/pci/emu10k1/emu10k1_callback.c b/sound/pci/emu10k1/emu10k1_callback.c
index 874cd76c7b7..d2c7ea3a761 100644
--- a/sound/pci/emu10k1/emu10k1_callback.c
+++ b/sound/pci/emu10k1/emu10k1_callback.c
@@ -415,7 +415,7 @@ start_voice(struct snd_emux_voice *vp)
 	snd_emu10k1_ptr_write(hw, Z2, ch, 0);
 
 	/* invalidate maps */
-	temp = (hw->silent_page.addr << 1) | MAP_PTI_MASK;
+	temp = (hw->silent_page.addr << hw->address_mode) | (hw->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0);
 	snd_emu10k1_ptr_write(hw, MAPA, ch, temp);
 	snd_emu10k1_ptr_write(hw, MAPB, ch, temp);
 #if 0
@@ -436,7 +436,7 @@ start_voice(struct snd_emux_voice *vp)
 		snd_emu10k1_ptr_write(hw, CDF, ch, sample);
 
 		/* invalidate maps */
-		temp = ((unsigned int)hw->silent_page.addr << 1) | MAP_PTI_MASK;
+		temp = ((unsigned int)hw->silent_page.addr << hw_address_mode) | (hw->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0);
 		snd_emu10k1_ptr_write(hw, MAPA, ch, temp);
 		snd_emu10k1_ptr_write(hw, MAPB, ch, temp);
 		
diff --git a/sound/pci/emu10k1/emu10k1_main.c b/sound/pci/emu10k1/emu10k1_main.c
index 22926978802..92f2371791a 100644
--- a/sound/pci/emu10k1/emu10k1_main.c
+++ b/sound/pci/emu10k1/emu10k1_main.c
@@ -282,7 +282,7 @@ static int snd_emu10k1_init(struct snd_emu10k1 *emu, int enable_ir, int resume)
 	snd_emu10k1_ptr_write(emu, TCB, 0, 0);	/* taken from original driver */
 	snd_emu10k1_ptr_write(emu, TCBS, 0, 4);	/* taken from original driver */
 
-	silent_page = (emu->silent_page.addr << 1) | MAP_PTI_MASK;
+	silent_page = (emu->silent_page.addr << emu->address_mode) | (emu->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0);
 	for (ch = 0; ch < NUM_G; ch++) {
 		snd_emu10k1_ptr_write(emu, MAPA, ch, silent_page);
 		snd_emu10k1_ptr_write(emu, MAPB, ch, silent_page);
@@ -348,6 +348,11 @@ static int snd_emu10k1_init(struct snd_emu10k1 *emu, int enable_ir, int resume)
 		outl(reg | A_IOCFG_GPOUT0, emu->port + A_IOCFG);
 	}
 
+	if (emu->address_mode == 0) {
+		/* use 16M in 4G */
+		outl(inl(emu->port + HCFG) | HCFG_EXPANDED_MEM, emu->port + HCFG);
+	}
+
 	return 0;
 }
 
@@ -1424,7 +1429,7 @@ static struct snd_emu_chip_details emu_chip_details[] = {
 	 *
 	 */
 	{.vendor = 0x1102, .device = 0x0008, .subsystem = 0x20011102,
-	 .driver = "Audigy2", .name = "SB Audigy 2 ZS Notebook [SB0530]",
+	 .driver = "Audigy2", .name = "Audigy 2 ZS Notebook [SB0530]",
 	 .id = "Audigy2",
 	 .emu10k2_chip = 1,
 	 .ca0108_chip = 1,
@@ -1574,7 +1579,7 @@ static struct snd_emu_chip_details emu_chip_details[] = {
 	 .adc_1361t = 1,  /* 24 bit capture instead of 16bit */
 	 .ac97_chip = 1} ,
 	{.vendor = 0x1102, .device = 0x0004, .subsystem = 0x10051102,
-	 .driver = "Audigy2", .name = "SB Audigy 2 Platinum EX [SB0280]",
+	 .driver = "Audigy2", .name = "Audigy 2 Platinum EX [SB0280]",
 	 .id = "Audigy2",
 	 .emu10k2_chip = 1,
 	 .ca0102_chip = 1,
@@ -1880,8 +1885,10 @@ int snd_emu10k1_create(struct snd_card *card,
 
 	is_audigy = emu->audigy = c->emu10k2_chip;
 
+	/* set addressing mode */
+	emu->address_mode = is_audigy ? 0 : 1;
 	/* set the DMA transfer mask */
-	emu->dma_mask = is_audigy ? AUDIGY_DMA_MASK : EMU10K1_DMA_MASK;
+	emu->dma_mask = emu->address_mode ? EMU10K1_DMA_MASK : AUDIGY_DMA_MASK;
 	if (pci_set_dma_mask(pci, emu->dma_mask) < 0 ||
 	    pci_set_consistent_dma_mask(pci, emu->dma_mask) < 0) {
 		dev_err(card->dev,
@@ -1906,7 +1913,7 @@ int snd_emu10k1_create(struct snd_card *card,
 
 	emu->max_cache_pages = max_cache_bytes >> PAGE_SHIFT;
 	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci),
-				32 * 1024, &emu->ptb_pages) < 0) {
+				(emu->address_mode ? 32 : 16) * 1024, &emu->ptb_pages) < 0) {
 		err = -ENOMEM;
 		goto error;
 	}
@@ -2005,8 +2012,8 @@ int snd_emu10k1_create(struct snd_card *card,
 
 	/* Clear silent pages and set up pointers */
 	memset(emu->silent_page.area, 0, PAGE_SIZE);
-	silent_page = emu->silent_page.addr << 1;
-	for (idx = 0; idx < MAXPAGES; idx++)
+	silent_page = emu->silent_page.addr << emu->address_mode;
+	for (idx = 0; idx < (emu->address_mode ? MAXPAGES1 : MAXPAGES0); idx++)
 		((u32 *)emu->ptb_pages.area)[idx] = cpu_to_le32(silent_page | idx);
 
 	/* set up voice indices */
diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c
index f82481bd254..36f0b864641 100644
--- a/sound/pci/emu10k1/emupcm.c
+++ b/sound/pci/emu10k1/emupcm.c
@@ -380,7 +380,7 @@ static void snd_emu10k1_pcm_init_voice(struct snd_emu10k1 *emu,
 	snd_emu10k1_ptr_write(emu, Z1, voice, 0);
 	snd_emu10k1_ptr_write(emu, Z2, voice, 0);
 	/* invalidate maps */
-	silent_page = ((unsigned int)emu->silent_page.addr << 1) | MAP_PTI_MASK;
+	silent_page = ((unsigned int)emu->silent_page.addr << emu->address_mode) | (emu->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0);
 	snd_emu10k1_ptr_write(emu, MAPA, voice, silent_page);
 	snd_emu10k1_ptr_write(emu, MAPB, voice, silent_page);
 	/* modulation envelope */
diff --git a/sound/pci/emu10k1/emuproc.c b/sound/pci/emu10k1/emuproc.c
index 2ca9f2e9313..53745f4c2bf 100644
--- a/sound/pci/emu10k1/emuproc.c
+++ b/sound/pci/emu10k1/emuproc.c
@@ -241,31 +241,22 @@ static void snd_emu10k1_proc_spdif_read(struct snd_info_entry *entry,
 	struct snd_emu10k1 *emu = entry->private_data;
 	u32 value;
 	u32 value2;
-	unsigned long flags;
 	u32 rate;
 
 	if (emu->card_capabilities->emu_model) {
-		spin_lock_irqsave(&emu->emu_lock, flags);
 		snd_emu1010_fpga_read(emu, 0x38, &value);
-		spin_unlock_irqrestore(&emu->emu_lock, flags);
 		if ((value & 0x1) == 0) {
-			spin_lock_irqsave(&emu->emu_lock, flags);
 			snd_emu1010_fpga_read(emu, 0x2a, &value);
 			snd_emu1010_fpga_read(emu, 0x2b, &value2);
-			spin_unlock_irqrestore(&emu->emu_lock, flags);
 			rate = 0x1770000 / (((value << 5) | value2)+1);	
 			snd_iprintf(buffer, "ADAT Locked : %u\n", rate);
 		} else {
 			snd_iprintf(buffer, "ADAT Unlocked\n");
 		}
-		spin_lock_irqsave(&emu->emu_lock, flags);
 		snd_emu1010_fpga_read(emu, 0x20, &value);
-		spin_unlock_irqrestore(&emu->emu_lock, flags);
 		if ((value & 0x4) == 0) {
-			spin_lock_irqsave(&emu->emu_lock, flags);
 			snd_emu1010_fpga_read(emu, 0x28, &value);
 			snd_emu1010_fpga_read(emu, 0x29, &value2);
-			spin_unlock_irqrestore(&emu->emu_lock, flags);
 			rate = 0x1770000 / (((value << 5) | value2)+1);	
 			snd_iprintf(buffer, "SPDIF Locked : %d\n", rate);
 		} else {
@@ -410,14 +401,11 @@ static void snd_emu_proc_emu1010_reg_read(struct snd_info_entry *entry,
 {
 	struct snd_emu10k1 *emu = entry->private_data;
 	u32 value;
-	unsigned long flags;
 	int i;
 	snd_iprintf(buffer, "EMU1010 Registers:\n\n");
 
 	for(i = 0; i < 0x40; i+=1) {
-		spin_lock_irqsave(&emu->emu_lock, flags);
 		snd_emu1010_fpga_read(emu, i, &value);
-		spin_unlock_irqrestore(&emu->emu_lock, flags);
 		snd_iprintf(buffer, "%02X: %08X, %02X\n", i, value, (value >> 8) & 0x7f);
 	}
 }
diff --git a/sound/pci/emu10k1/memory.c b/sound/pci/emu10k1/memory.c
index c68e6dd2fa6..4f1f69be186 100644
--- a/sound/pci/emu10k1/memory.c
+++ b/sound/pci/emu10k1/memory.c
@@ -34,10 +34,11 @@
  * aligned pages in others
  */
 #define __set_ptb_entry(emu,page,addr) \
-	(((u32 *)(emu)->ptb_pages.area)[page] = cpu_to_le32(((addr) << 1) | (page)))
+	(((u32 *)(emu)->ptb_pages.area)[page] = cpu_to_le32(((addr) << (emu->address_mode)) | (page)))
 
 #define UNIT_PAGES		(PAGE_SIZE / EMUPAGESIZE)
-#define MAX_ALIGN_PAGES		(MAXPAGES / UNIT_PAGES)
+#define MAX_ALIGN_PAGES0		(MAXPAGES0 / UNIT_PAGES)
+#define MAX_ALIGN_PAGES1		(MAXPAGES1 / UNIT_PAGES)
 /* get aligned page from offset address */
 #define get_aligned_page(offset)	((offset) >> PAGE_SHIFT)
 /* get offset address from aligned page */
@@ -124,7 +125,7 @@ static int search_empty_map_area(struct snd_emu10k1 *emu, int npages, struct lis
 		}
 		page = blk->mapped_page + blk->pages;
 	}
-	size = MAX_ALIGN_PAGES - page;
+	size = (emu->address_mode ? MAX_ALIGN_PAGES1 : MAX_ALIGN_PAGES0) - page;
 	if (size >= max_size) {
 		*nextp = pos;
 		return page;
@@ -181,7 +182,7 @@ static int unmap_memblk(struct snd_emu10k1 *emu, struct snd_emu10k1_memblk *blk)
 		q = get_emu10k1_memblk(p, mapped_link);
 		end_page = q->mapped_page;
 	} else
-		end_page = MAX_ALIGN_PAGES;
+		end_page = (emu->address_mode ? MAX_ALIGN_PAGES1 : MAX_ALIGN_PAGES0);
 
 	/* remove links */
 	list_del(&blk->mapped_link);
@@ -307,7 +308,7 @@ snd_emu10k1_alloc_pages(struct snd_emu10k1 *emu, struct snd_pcm_substream *subst
 	if (snd_BUG_ON(!emu))
 		return NULL;
 	if (snd_BUG_ON(runtime->dma_bytes <= 0 ||
-		       runtime->dma_bytes >= MAXPAGES * EMUPAGESIZE))
+		       runtime->dma_bytes >= (emu->address_mode ? MAXPAGES1 : MAXPAGES0) * EMUPAGESIZE))
 		return NULL;
 	hdr = emu->memhdr;
 	if (snd_BUG_ON(!hdr))
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index 15e0089492f..6bd95f95e48 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -338,8 +338,10 @@ int snd_hda_get_sub_nodes(struct hda_codec *codec, hda_nid_t nid,
 	unsigned int parm;
 
 	parm = snd_hda_param_read(codec, nid, AC_PAR_NODE_COUNT);
-	if (parm == -1)
+	if (parm == -1) {
+		*start_id = 0;
 		return 0;
+	}
 	*start_id = (parm >> 16) & 0x7fff;
 	return (int)(parm & 0x7fff);
 }
@@ -2138,6 +2140,16 @@ static void put_vol_mute(struct hda_codec *codec, unsigned int amp_caps,
 	snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_AMP_GAIN_MUTE, parm);
 }
 
+/* meta hook to call each driver's vmaster hook */
+static void vmaster_hook(void *private_data, int enabled)
+{
+	struct hda_vmaster_mute_hook *hook = private_data;
+
+	if (hook->mute_mode != HDA_VMUTE_FOLLOW_MASTER)
+		enabled = hook->mute_mode;
+	hook->hook(hook->codec, enabled);
+}
+
 /**
  * snd_hda_codec_amp_read - Read AMP value
  * @codec: HD-audio codec
@@ -2983,9 +2995,9 @@ int snd_hda_add_vmaster_hook(struct hda_codec *codec,
 
 	if (!hook->hook || !hook->sw_kctl)
 		return 0;
-	snd_ctl_add_vmaster_hook(hook->sw_kctl, hook->hook, codec);
 	hook->codec = codec;
 	hook->mute_mode = HDA_VMUTE_FOLLOW_MASTER;
+	snd_ctl_add_vmaster_hook(hook->sw_kctl, vmaster_hook, hook);
 	if (!expose_enum_ctl)
 		return 0;
 	kctl = snd_ctl_new1(&vmaster_mute_mode, hook);
@@ -3008,14 +3020,7 @@ void snd_hda_sync_vmaster_hook(struct hda_vmaster_mute_hook *hook)
 	 */
 	if (hook->codec->bus->shutdown)
 		return;
-	switch (hook->mute_mode) {
-	case HDA_VMUTE_FOLLOW_MASTER:
-		snd_ctl_sync_vmaster_hook(hook->sw_kctl);
-		break;
-	default:
-		hook->hook(hook->codec, hook->mute_mode);
-		break;
-	}
+	snd_ctl_sync_vmaster_hook(hook->sw_kctl);
 }
 EXPORT_SYMBOL_GPL(snd_hda_sync_vmaster_hook);
 
diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c
index 8337645aa7a..20aa52b14b8 100644
--- a/sound/pci/hda/hda_controller.c
+++ b/sound/pci/hda/hda_controller.c
@@ -957,7 +957,6 @@ static int azx_alloc_cmd_io(struct azx *chip)
 		dev_err(chip->card->dev, "cannot allocate CORB/RIRB\n");
 	return err;
 }
-EXPORT_SYMBOL_GPL(azx_alloc_cmd_io);
 
 static void azx_init_cmd_io(struct azx *chip)
 {
@@ -1022,7 +1021,6 @@ static void azx_init_cmd_io(struct azx *chip)
 	azx_writeb(chip, RIRBCTL, AZX_RBCTL_DMA_EN | AZX_RBCTL_IRQ_EN);
 	spin_unlock_irq(&chip->reg_lock);
 }
-EXPORT_SYMBOL_GPL(azx_init_cmd_io);
 
 static void azx_free_cmd_io(struct azx *chip)
 {
@@ -1032,7 +1030,6 @@ static void azx_free_cmd_io(struct azx *chip)
 	azx_writeb(chip, CORBCTL, 0);
 	spin_unlock_irq(&chip->reg_lock);
 }
-EXPORT_SYMBOL_GPL(azx_free_cmd_io);
 
 static unsigned int azx_command_addr(u32 cmd)
 {
@@ -1163,7 +1160,7 @@ static unsigned int azx_rirb_get_response(struct hda_bus *bus,
 		}
 	}
 
-	if (!bus->no_response_fallback)
+	if (bus->no_response_fallback)
 		return -1;
 
 	if (!chip->polling_mode && chip->poll_count < 2) {
@@ -1312,7 +1309,6 @@ static int azx_send_cmd(struct hda_bus *bus, unsigned int val)
 	else
 		return azx_corb_send_cmd(bus, val);
 }
-EXPORT_SYMBOL_GPL(azx_send_cmd);
 
 /* get a response */
 static unsigned int azx_get_response(struct hda_bus *bus,
@@ -1326,7 +1322,6 @@ static unsigned int azx_get_response(struct hda_bus *bus,
 	else
 		return azx_rirb_get_response(bus, addr);
 }
-EXPORT_SYMBOL_GPL(azx_get_response);
 
 #ifdef CONFIG_SND_HDA_DSP_LOADER
 /*
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 64220c08bd9..6c6e35aba98 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -637,12 +637,45 @@ static int get_amp_val_to_activate(struct hda_codec *codec, hda_nid_t nid,
 	return val;
 }
 
+/* is this a stereo widget or a stereo-to-mono mix? */
+static bool is_stereo_amps(struct hda_codec *codec, hda_nid_t nid, int dir)
+{
+	unsigned int wcaps = get_wcaps(codec, nid);
+	hda_nid_t conn;
+
+	if (wcaps & AC_WCAP_STEREO)
+		return true;
+	if (dir != HDA_INPUT || get_wcaps_type(wcaps) != AC_WID_AUD_MIX)
+		return false;
+	if (snd_hda_get_num_conns(codec, nid) != 1)
+		return false;
+	if (snd_hda_get_connections(codec, nid, &conn, 1) < 0)
+		return false;
+	return !!(get_wcaps(codec, conn) & AC_WCAP_STEREO);
+}
+
 /* initialize the amp value (only at the first time) */
 static void init_amp(struct hda_codec *codec, hda_nid_t nid, int dir, int idx)
 {
 	unsigned int caps = query_amp_caps(codec, nid, dir);
 	int val = get_amp_val_to_activate(codec, nid, dir, caps, false);
-	snd_hda_codec_amp_init_stereo(codec, nid, dir, idx, 0xff, val);
+
+	if (is_stereo_amps(codec, nid, dir))
+		snd_hda_codec_amp_init_stereo(codec, nid, dir, idx, 0xff, val);
+	else
+		snd_hda_codec_amp_init(codec, nid, 0, dir, idx, 0xff, val);
+}
+
+/* update the amp, doing in stereo or mono depending on NID */
+static int update_amp(struct hda_codec *codec, hda_nid_t nid, int dir, int idx,
+		      unsigned int mask, unsigned int val)
+{
+	if (is_stereo_amps(codec, nid, dir))
+		return snd_hda_codec_amp_stereo(codec, nid, dir, idx,
+						mask, val);
+	else
+		return snd_hda_codec_amp_update(codec, nid, 0, dir, idx,
+						mask, val);
 }
 
 /* calculate amp value mask we can modify;
@@ -682,7 +715,7 @@ static void activate_amp(struct hda_codec *codec, hda_nid_t nid, int dir,
 		return;
 
 	val &= mask;
-	snd_hda_codec_amp_stereo(codec, nid, dir, idx, mask, val);
+	update_amp(codec, nid, dir, idx, mask, val);
 }
 
 static void activate_amp_out(struct hda_codec *codec, struct nid_path *path,
@@ -4331,13 +4364,11 @@ static void mute_all_mixer_nid(struct hda_codec *codec, hda_nid_t mix)
 	has_amp = nid_has_mute(codec, mix, HDA_INPUT);
 	for (i = 0; i < nums; i++) {
 		if (has_amp)
-			snd_hda_codec_amp_stereo(codec, mix,
-						 HDA_INPUT, i,
-						 0xff, HDA_AMP_MUTE);
+			update_amp(codec, mix, HDA_INPUT, i,
+				   0xff, HDA_AMP_MUTE);
 		else if (nid_has_volume(codec, conn[i], HDA_OUTPUT))
-			snd_hda_codec_amp_stereo(codec, conn[i],
-						 HDA_OUTPUT, 0,
-						 0xff, HDA_AMP_MUTE);
+			update_amp(codec, conn[i], HDA_OUTPUT, 0,
+				   0xff, HDA_AMP_MUTE);
 	}
 }
 
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 48b6c5a3884..58f82733c89 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -272,43 +272,52 @@ enum {
 	AZX_NUM_DRIVERS, /* keep this as last entry */
 };
 
+#define azx_get_snoop_type(chip) \
+	(((chip)->driver_caps & AZX_DCAPS_SNOOP_MASK) >> 10)
+#define AZX_DCAPS_SNOOP_TYPE(type) ((AZX_SNOOP_TYPE_ ## type) << 10)
+
 /* quirks for Intel PCH */
 #define AZX_DCAPS_INTEL_PCH_NOPM \
-	(AZX_DCAPS_SCH_SNOOP | AZX_DCAPS_BUFSIZE | \
-	 AZX_DCAPS_COUNT_LPIB_DELAY | AZX_DCAPS_REVERSE_ASSIGN)
+	(AZX_DCAPS_BUFSIZE | AZX_DCAPS_COUNT_LPIB_DELAY |\
+	 AZX_DCAPS_REVERSE_ASSIGN | AZX_DCAPS_SNOOP_TYPE(SCH))
 
 #define AZX_DCAPS_INTEL_PCH \
 	(AZX_DCAPS_INTEL_PCH_NOPM | AZX_DCAPS_PM_RUNTIME)
 
 #define AZX_DCAPS_INTEL_HASWELL \
-	(AZX_DCAPS_SCH_SNOOP | AZX_DCAPS_ALIGN_BUFSIZE | \
-	 AZX_DCAPS_COUNT_LPIB_DELAY | AZX_DCAPS_PM_RUNTIME | \
-	 AZX_DCAPS_I915_POWERWELL)
+	(AZX_DCAPS_ALIGN_BUFSIZE | AZX_DCAPS_COUNT_LPIB_DELAY |\
+	 AZX_DCAPS_PM_RUNTIME | AZX_DCAPS_I915_POWERWELL |\
+	 AZX_DCAPS_SNOOP_TYPE(SCH))
 
 /* Broadwell HDMI can't use position buffer reliably, force to use LPIB */
 #define AZX_DCAPS_INTEL_BROADWELL \
-	(AZX_DCAPS_SCH_SNOOP | AZX_DCAPS_ALIGN_BUFSIZE | \
-	 AZX_DCAPS_POSFIX_LPIB | AZX_DCAPS_PM_RUNTIME | \
-	 AZX_DCAPS_I915_POWERWELL)
+	(AZX_DCAPS_ALIGN_BUFSIZE | AZX_DCAPS_POSFIX_LPIB |\
+	 AZX_DCAPS_PM_RUNTIME | AZX_DCAPS_I915_POWERWELL |\
+	 AZX_DCAPS_SNOOP_TYPE(SCH))
 
 /* quirks for ATI SB / AMD Hudson */
 #define AZX_DCAPS_PRESET_ATI_SB \
-	(AZX_DCAPS_ATI_SNOOP | AZX_DCAPS_NO_TCSEL | \
-	 AZX_DCAPS_SYNC_WRITE | AZX_DCAPS_POSFIX_LPIB)
+	(AZX_DCAPS_NO_TCSEL | AZX_DCAPS_SYNC_WRITE | AZX_DCAPS_POSFIX_LPIB |\
+	 AZX_DCAPS_SNOOP_TYPE(ATI))
 
 /* quirks for ATI/AMD HDMI */
 #define AZX_DCAPS_PRESET_ATI_HDMI \
 	(AZX_DCAPS_NO_TCSEL | AZX_DCAPS_SYNC_WRITE | AZX_DCAPS_POSFIX_LPIB|\
 	 AZX_DCAPS_NO_MSI64)
 
+/* quirks for ATI HDMI with snoop off */
+#define AZX_DCAPS_PRESET_ATI_HDMI_NS \
+	(AZX_DCAPS_PRESET_ATI_HDMI | AZX_DCAPS_SNOOP_OFF)
+
 /* quirks for Nvidia */
 #define AZX_DCAPS_PRESET_NVIDIA \
-	(AZX_DCAPS_NVIDIA_SNOOP | AZX_DCAPS_RIRB_DELAY | AZX_DCAPS_NO_MSI |\
-	 AZX_DCAPS_ALIGN_BUFSIZE | AZX_DCAPS_NO_64BIT |\
-	 AZX_DCAPS_CORBRP_SELF_CLEAR)
+	(AZX_DCAPS_RIRB_DELAY | AZX_DCAPS_NO_MSI | AZX_DCAPS_ALIGN_BUFSIZE |\
+	 AZX_DCAPS_NO_64BIT | AZX_DCAPS_CORBRP_SELF_CLEAR |\
+	 AZX_DCAPS_SNOOP_TYPE(NVIDIA))
 
 #define AZX_DCAPS_PRESET_CTHDA \
-	(AZX_DCAPS_NO_MSI | AZX_DCAPS_POSFIX_LPIB | AZX_DCAPS_4K_BDLE_BOUNDARY)
+	(AZX_DCAPS_NO_MSI | AZX_DCAPS_POSFIX_LPIB |\
+	 AZX_DCAPS_4K_BDLE_BOUNDARY | AZX_DCAPS_SNOOP_OFF)
 
 /*
  * VGA-switcher support
@@ -437,6 +446,8 @@ static void update_pci_byte(struct pci_dev *pci, unsigned int reg,
 
 static void azx_init_pci(struct azx *chip)
 {
+	int snoop_type = azx_get_snoop_type(chip);
+
 	/* Clear bits 0-2 of PCI register TCSEL (at offset 0x44)
 	 * TCSEL == Traffic Class Select Register, which sets PCI express QOS
 	 * Ensuring these bits are 0 clears playback static on some HD Audio
@@ -451,7 +462,7 @@ static void azx_init_pci(struct azx *chip)
 	/* For ATI SB450/600/700/800/900 and AMD Hudson azalia HD audio,
 	 * we need to enable snoop.
 	 */
-	if (chip->driver_caps & AZX_DCAPS_ATI_SNOOP) {
+	if (snoop_type == AZX_SNOOP_TYPE_ATI) {
 		dev_dbg(chip->card->dev, "Setting ATI snoop: %d\n",
 			azx_snoop(chip));
 		update_pci_byte(chip->pci,
@@ -460,7 +471,7 @@ static void azx_init_pci(struct azx *chip)
 	}
 
 	/* For NVIDIA HDA, enable snoop */
-	if (chip->driver_caps & AZX_DCAPS_NVIDIA_SNOOP) {
+	if (snoop_type == AZX_SNOOP_TYPE_NVIDIA) {
 		dev_dbg(chip->card->dev, "Setting Nvidia snoop: %d\n",
 			azx_snoop(chip));
 		update_pci_byte(chip->pci,
@@ -475,7 +486,7 @@ static void azx_init_pci(struct azx *chip)
 	}
 
 	/* Enable SCH/PCH snoop if needed */
-	if (chip->driver_caps & AZX_DCAPS_SCH_SNOOP) {
+	if (snoop_type == AZX_SNOOP_TYPE_SCH) {
 		unsigned short snoop;
 		pci_read_config_word(chip->pci, INTEL_SCH_HDA_DEVC, &snoop);
 		if ((!azx_snoop(chip) && !(snoop & INTEL_SCH_HDA_DEVC_NOSNOOP)) ||
@@ -1363,8 +1374,8 @@ static void azx_check_snoop_available(struct azx *chip)
 {
 	bool snoop = chip->snoop;
 
-	switch (chip->driver_type) {
-	case AZX_DRIVER_VIA:
+	if (azx_get_snoop_type(chip) == AZX_SNOOP_TYPE_NONE &&
+	    chip->driver_type == AZX_DRIVER_VIA) {
 		/* force to non-snoop mode for a new VIA controller
 		 * when BIOS is set
 		 */
@@ -1374,17 +1385,11 @@ static void azx_check_snoop_available(struct azx *chip)
 			if (!(val & 0x80) && chip->pci->revision == 0x30)
 				snoop = false;
 		}
-		break;
-	case AZX_DRIVER_ATIHDMI_NS:
-		/* new ATI HDMI requires non-snoop */
-		snoop = false;
-		break;
-	case AZX_DRIVER_CTHDA:
-	case AZX_DRIVER_CMEDIA:
-		snoop = false;
-		break;
 	}
 
+	if (chip->driver_caps & AZX_DCAPS_SNOOP_OFF)
+		snoop = false;
+
 	if (snoop != chip->snoop) {
 		dev_info(chip->card->dev, "Force to %s mode\n",
 			 snoop ? "snoop" : "non-snoop");
@@ -1995,7 +2000,7 @@ static const struct pci_device_id azx_ids[] = {
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH_NOPM },
 	/* Panther Point */
 	{ PCI_DEVICE(0x8086, 0x1e20),
-	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH_NOPM },
 	/* Lynx Point */
 	{ PCI_DEVICE(0x8086, 0x8c20),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
@@ -2086,6 +2091,8 @@ static const struct pci_device_id azx_ids[] = {
 	{ PCI_DEVICE(0x1022, 0x780d),
 	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_SB },
 	/* ATI HDMI */
+	{ PCI_DEVICE(0x1002, 0x1308),
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0x793b),
 	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
 	{ PCI_DEVICE(0x1002, 0x7919),
@@ -2094,6 +2101,8 @@ static const struct pci_device_id azx_ids[] = {
 	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
 	{ PCI_DEVICE(0x1002, 0x970f),
 	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
+	{ PCI_DEVICE(0x1002, 0x9840),
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0xaa00),
 	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
 	{ PCI_DEVICE(0x1002, 0xaa08),
@@ -2131,13 +2140,15 @@ static const struct pci_device_id azx_ids[] = {
 	{ PCI_DEVICE(0x1002, 0xaa98),
 	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
 	{ PCI_DEVICE(0x1002, 0x9902),
-	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI },
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0xaaa0),
-	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI },
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0xaaa8),
-	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI },
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0xaab0),
-	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI },
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+	{ PCI_DEVICE(0x1002, 0xaac8),
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	/* VIA VT8251/VT8237A */
 	{ PCI_DEVICE(0x1106, 0x3288),
 	  .driver_data = AZX_DRIVER_VIA | AZX_DCAPS_POSFIX_VIA },
@@ -2184,7 +2195,7 @@ static const struct pci_device_id azx_ids[] = {
 	/* CM8888 */
 	{ PCI_DEVICE(0x13f6, 0x5011),
 	  .driver_data = AZX_DRIVER_CMEDIA |
-	  AZX_DCAPS_NO_MSI | AZX_DCAPS_POSFIX_LPIB },
+	  AZX_DCAPS_NO_MSI | AZX_DCAPS_POSFIX_LPIB | AZX_DCAPS_SNOOP_OFF },
 	/* Vortex86MX */
 	{ PCI_DEVICE(0x17f3, 0x3010), .driver_data = AZX_DRIVER_GENERIC },
 	/* VMware HDAudio */
diff --git a/sound/pci/hda/hda_priv.h b/sound/pci/hda/hda_priv.h
index 5016014e57f..a09703a2b2c 100644
--- a/sound/pci/hda/hda_priv.h
+++ b/sound/pci/hda/hda_priv.h
@@ -152,9 +152,8 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 };
 /* bits 0-7 are used for indicating driver type */
 #define AZX_DCAPS_NO_TCSEL	(1 << 8)	/* No Intel TCSEL bit */
 #define AZX_DCAPS_NO_MSI	(1 << 9)	/* No MSI support */
-#define AZX_DCAPS_ATI_SNOOP	(1 << 10)	/* ATI snoop enable */
-#define AZX_DCAPS_NVIDIA_SNOOP	(1 << 11)	/* Nvidia snoop enable */
-#define AZX_DCAPS_SCH_SNOOP	(1 << 12)	/* SCH/PCH snoop enable */
+#define AZX_DCAPS_SNOOP_MASK	(3 << 10)	/* snoop type mask */
+#define AZX_DCAPS_SNOOP_OFF	(1 << 12)	/* snoop default off */
 #define AZX_DCAPS_RIRB_DELAY	(1 << 13)	/* Long delay in read loop */
 #define AZX_DCAPS_RIRB_PRE_DELAY (1 << 14)	/* Put a delay before read */
 #define AZX_DCAPS_CTX_WORKAROUND (1 << 15)	/* X-Fi workaround */
@@ -173,6 +172,13 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 };
 #define AZX_DCAPS_CORBRP_SELF_CLEAR (1 << 28)	/* CORBRP clears itself after reset */
 #define AZX_DCAPS_NO_MSI64      (1 << 29)	/* Stick to 32-bit MSIs */
 
+enum {
+	AZX_SNOOP_TYPE_NONE ,
+	AZX_SNOOP_TYPE_SCH,
+	AZX_SNOOP_TYPE_ATI,
+	AZX_SNOOP_TYPE_NVIDIA,
+};
+
 /* HD Audio class code */
 #define PCI_CLASS_MULTIMEDIA_HD_AUDIO	0x0403
 
diff --git a/sound/pci/hda/hda_proc.c b/sound/pci/hda/hda_proc.c
index ce5a6da8341..05e19f78b4c 100644
--- a/sound/pci/hda/hda_proc.c
+++ b/sound/pci/hda/hda_proc.c
@@ -134,13 +134,38 @@ static void print_amp_caps(struct snd_info_buffer *buffer,
 		    (caps & AC_AMPCAP_MUTE) >> AC_AMPCAP_MUTE_SHIFT);
 }
 
+/* is this a stereo widget or a stereo-to-mono mix? */
+static bool is_stereo_amps(struct hda_codec *codec, hda_nid_t nid,
+			   int dir, unsigned int wcaps, int indices)
+{
+	hda_nid_t conn;
+
+	if (wcaps & AC_WCAP_STEREO)
+		return true;
+	/* check for a stereo-to-mono mix; it must be:
+	 * only a single connection, only for input, and only a mixer widget
+	 */
+	if (indices != 1 || dir != HDA_INPUT ||
+	    get_wcaps_type(wcaps) != AC_WID_AUD_MIX)
+		return false;
+
+	if (snd_hda_get_raw_connections(codec, nid, &conn, 1) < 0)
+		return false;
+	/* the connection source is a stereo? */
+	wcaps = snd_hda_param_read(codec, conn, AC_PAR_AUDIO_WIDGET_CAP);
+	return !!(wcaps & AC_WCAP_STEREO);
+}
+
 static void print_amp_vals(struct snd_info_buffer *buffer,
 			   struct hda_codec *codec, hda_nid_t nid,
-			   int dir, int stereo, int indices)
+			   int dir, unsigned int wcaps, int indices)
 {
 	unsigned int val;
+	bool stereo;
 	int i;
 
+	stereo = is_stereo_amps(codec, nid, dir, wcaps, indices);
+
 	dir = dir == HDA_OUTPUT ? AC_AMP_GET_OUTPUT : AC_AMP_GET_INPUT;
 	for (i = 0; i < indices; i++) {
 		snd_iprintf(buffer, " [");
@@ -757,12 +782,10 @@ static void print_codec_info(struct snd_info_entry *entry,
 			    (codec->single_adc_amp &&
 			     wid_type == AC_WID_AUD_IN))
 				print_amp_vals(buffer, codec, nid, HDA_INPUT,
-					       wid_caps & AC_WCAP_STEREO,
-					       1);
+					       wid_caps, 1);
 			else
 				print_amp_vals(buffer, codec, nid, HDA_INPUT,
-					       wid_caps & AC_WCAP_STEREO,
-					       conn_len);
+					       wid_caps, conn_len);
 		}
 		if (wid_caps & AC_WCAP_OUT_AMP) {
 			snd_iprintf(buffer, "  Amp-Out caps: ");
@@ -771,11 +794,10 @@ static void print_codec_info(struct snd_info_entry *entry,
 			if (wid_type == AC_WID_PIN &&
 			    codec->pin_amp_workaround)
 				print_amp_vals(buffer, codec, nid, HDA_OUTPUT,
-					       wid_caps & AC_WCAP_STEREO,
-					       conn_len);
+					       wid_caps, conn_len);
 			else
 				print_amp_vals(buffer, codec, nid, HDA_OUTPUT,
-					       wid_caps & AC_WCAP_STEREO, 1);
+					       wid_caps, 1);
 		}
 
 		switch (wid_type) {
diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c
index 06275f8807a..4714ff92f15 100644
--- a/sound/pci/hda/patch_analog.c
+++ b/sound/pci/hda/patch_analog.c
@@ -332,6 +332,7 @@ static const struct hda_fixup ad1986a_fixups[] = {
 
 static const struct snd_pci_quirk ad1986a_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x30af, "HP B2800", AD1986A_FIXUP_LAPTOP_IMIC),
+	SND_PCI_QUIRK(0x1043, 0x1443, "ASUS Z99He", AD1986A_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x1043, 0x1447, "ASUS A8JN", AD1986A_FIXUP_EAPD),
 	SND_PCI_QUIRK_MASK(0x1043, 0xff00, 0x8100, "ASUS P5", AD1986A_FIXUP_3STACK),
 	SND_PCI_QUIRK_MASK(0x1043, 0xff00, 0x8200, "ASUS M2", AD1986A_FIXUP_3STACK),
diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index 1589c9bcce3..dd2b3d92071 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -393,6 +393,7 @@ static const struct snd_pci_quirk cs420x_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x106b, 0x1c00, "MacBookPro 8,1", CS420X_MBP81),
 	SND_PCI_QUIRK(0x106b, 0x2000, "iMac 12,2", CS420X_IMAC27_122),
 	SND_PCI_QUIRK(0x106b, 0x2800, "MacBookPro 10,1", CS420X_MBP101),
+	SND_PCI_QUIRK(0x106b, 0x5600, "MacBookAir 5,2", CS420X_MBP81),
 	SND_PCI_QUIRK(0x106b, 0x5b00, "MacBookAir 4,2", CS420X_MBA42),
 	SND_PCI_QUIRK_VENDOR(0x106b, "Apple", CS420X_APPLE),
 	{} /* terminator */
@@ -584,6 +585,7 @@ static int patch_cs420x(struct hda_codec *codec)
 		return -ENOMEM;
 
 	spec->gen.automute_hook = cs_automute;
+	codec->single_adc_amp = 1;
 
 	snd_hda_pick_fixup(codec, cs420x_models, cs420x_fixup_tbl,
 			   cs420x_fixups);
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index e9ebc7bd752..69c9d377e51 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -223,6 +223,7 @@ enum {
 	CXT_PINCFG_LENOVO_TP410,
 	CXT_PINCFG_LEMOTE_A1004,
 	CXT_PINCFG_LEMOTE_A1205,
+	CXT_PINCFG_COMPAQ_CQ60,
 	CXT_FIXUP_STEREO_DMIC,
 	CXT_FIXUP_INC_MIC_BOOST,
 	CXT_FIXUP_HEADPHONE_MIC_PIN,
@@ -660,6 +661,15 @@ static const struct hda_fixup cxt_fixups[] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = cxt_pincfg_lemote,
 	},
+	[CXT_PINCFG_COMPAQ_CQ60] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			/* 0x17 was falsely set up as a mic, it should 0x1d */
+			{ 0x17, 0x400001f0 },
+			{ 0x1d, 0x97a70120 },
+			{ }
+		}
+	},
 	[CXT_FIXUP_STEREO_DMIC] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = cxt_fixup_stereo_dmic,
@@ -769,6 +779,7 @@ static const struct hda_model_fixup cxt5047_fixup_models[] = {
 };
 
 static const struct snd_pci_quirk cxt5051_fixups[] = {
+	SND_PCI_QUIRK(0x103c, 0x360b, "Compaq CQ60", CXT_PINCFG_COMPAQ_CQ60),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo X200", CXT_PINCFG_LENOVO_X200),
 	{}
 };
@@ -962,6 +973,14 @@ static const struct hda_codec_preset snd_hda_preset_conexant[] = {
 	  .patch = patch_conexant_auto },
 	{ .id = 0x14f150b9, .name = "CX20665",
 	  .patch = patch_conexant_auto },
+	{ .id = 0x14f150f1, .name = "CX20721",
+	  .patch = patch_conexant_auto },
+	{ .id = 0x14f150f2, .name = "CX20722",
+	  .patch = patch_conexant_auto },
+	{ .id = 0x14f150f3, .name = "CX20723",
+	  .patch = patch_conexant_auto },
+	{ .id = 0x14f150f4, .name = "CX20724",
+	  .patch = patch_conexant_auto },
 	{ .id = 0x14f1510f, .name = "CX20751/2",
 	  .patch = patch_conexant_auto },
 	{ .id = 0x14f15110, .name = "CX20751/2",
@@ -996,6 +1015,10 @@ MODULE_ALIAS("snd-hda-codec-id:14f150ab");
 MODULE_ALIAS("snd-hda-codec-id:14f150ac");
 MODULE_ALIAS("snd-hda-codec-id:14f150b8");
 MODULE_ALIAS("snd-hda-codec-id:14f150b9");
+MODULE_ALIAS("snd-hda-codec-id:14f150f1");
+MODULE_ALIAS("snd-hda-codec-id:14f150f2");
+MODULE_ALIAS("snd-hda-codec-id:14f150f3");
+MODULE_ALIAS("snd-hda-codec-id:14f150f4");
 MODULE_ALIAS("snd-hda-codec-id:14f1510f");
 MODULE_ALIAS("snd-hda-codec-id:14f15110");
 MODULE_ALIAS("snd-hda-codec-id:14f15111");
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 9dc9cf8c90e..edb6e6124a2 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -3351,6 +3351,7 @@ static const struct hda_codec_preset snd_hda_preset_hdmi[] = {
 { .id = 0x10de0067, .name = "MCP67 HDMI",	.patch = patch_nvhdmi_2ch },
 { .id = 0x10de0070, .name = "GPU 70 HDMI/DP",	.patch = patch_nvhdmi },
 { .id = 0x10de0071, .name = "GPU 71 HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de0072, .name = "GPU 72 HDMI/DP",	.patch = patch_nvhdmi },
 { .id = 0x10de8001, .name = "MCP73 HDMI",	.patch = patch_nvhdmi_2ch },
 { .id = 0x11069f80, .name = "VX900 HDMI/DP",	.patch = patch_via_hdmi },
 { .id = 0x11069f81, .name = "VX900 HDMI/DP",	.patch = patch_via_hdmi },
@@ -3410,6 +3411,7 @@ MODULE_ALIAS("snd-hda-codec-id:10de0060");
 MODULE_ALIAS("snd-hda-codec-id:10de0067");
 MODULE_ALIAS("snd-hda-codec-id:10de0070");
 MODULE_ALIAS("snd-hda-codec-id:10de0071");
+MODULE_ALIAS("snd-hda-codec-id:10de0072");
 MODULE_ALIAS("snd-hda-codec-id:10de8001");
 MODULE_ALIAS("snd-hda-codec-id:11069f80");
 MODULE_ALIAS("snd-hda-codec-id:11069f81");
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index b118a5be18d..24cec17db1a 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -319,10 +319,12 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 		break;
 	case 0x10ec0233:
 	case 0x10ec0255:
+	case 0x10ec0256:
 	case 0x10ec0282:
 	case 0x10ec0283:
 	case 0x10ec0286:
 	case 0x10ec0288:
+	case 0x10ec0298:
 		alc_update_coef_idx(codec, 0x10, 1<<9, 0);
 		break;
 	case 0x10ec0285:
@@ -390,7 +392,7 @@ static void alc_auto_setup_eapd(struct hda_codec *codec, bool on)
 {
 	/* We currently only handle front, HP */
 	static hda_nid_t pins[] = {
-		0x0f, 0x10, 0x14, 0x15, 0
+		0x0f, 0x10, 0x14, 0x15, 0x17, 0
 	};
 	hda_nid_t *p;
 	for (p = pins; *p; p++)
@@ -878,6 +880,8 @@ static struct alc_codec_rename_pci_table rename_pci_tbl[] = {
 	{ 0x10ec0668, 0x1028, 0, "ALC3661" },
 	{ 0x10ec0275, 0x1028, 0, "ALC3260" },
 	{ 0x10ec0899, 0x1028, 0, "ALC3861" },
+	{ 0x10ec0298, 0x1028, 0, "ALC3266" },
+	{ 0x10ec0256, 0x1028, 0, "ALC3246" },
 	{ 0x10ec0670, 0x1025, 0, "ALC669X" },
 	{ 0x10ec0676, 0x1025, 0, "ALC679X" },
 	{ 0x10ec0282, 0x1043, 0, "ALC3229" },
@@ -2161,6 +2165,7 @@ static const struct hda_fixup alc882_fixups[] = {
 static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x006c, "Acer Aspire 9810", ALC883_FIXUP_ACER_EAPD),
 	SND_PCI_QUIRK(0x1025, 0x0090, "Acer Aspire", ALC883_FIXUP_ACER_EAPD),
+	SND_PCI_QUIRK(0x1025, 0x0107, "Acer Aspire", ALC883_FIXUP_ACER_EAPD),
 	SND_PCI_QUIRK(0x1025, 0x010a, "Acer Ferrari 5000", ALC883_FIXUP_ACER_EAPD),
 	SND_PCI_QUIRK(0x1025, 0x0110, "Acer Aspire", ALC883_FIXUP_ACER_EAPD),
 	SND_PCI_QUIRK(0x1025, 0x0112, "Acer Aspire 9303", ALC883_FIXUP_ACER_EAPD),
@@ -2657,7 +2662,9 @@ enum {
 	ALC269_TYPE_ALC284,
 	ALC269_TYPE_ALC285,
 	ALC269_TYPE_ALC286,
+	ALC269_TYPE_ALC298,
 	ALC269_TYPE_ALC255,
+	ALC269_TYPE_ALC256,
 };
 
 /*
@@ -2684,7 +2691,9 @@ static int alc269_parse_auto_config(struct hda_codec *codec)
 	case ALC269_TYPE_ALC282:
 	case ALC269_TYPE_ALC283:
 	case ALC269_TYPE_ALC286:
+	case ALC269_TYPE_ALC298:
 	case ALC269_TYPE_ALC255:
+	case ALC269_TYPE_ALC256:
 		ssids = alc269_ssids;
 		break;
 	default:
@@ -2902,6 +2911,8 @@ static void alc283_init(struct hda_codec *codec)
 
 	if (!hp_pin)
 		return;
+
+	msleep(30);
 	hp_pin_sense = snd_hda_jack_detect(codec, hp_pin);
 
 	/* Index 0x43 Direct Drive HP AMP LPM Control 1 */
@@ -3468,6 +3479,14 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
 		WRITE_COEF(0x32, 0x42a3),
 		{}
 	};
+	static struct coef_fw coef0288[] = {
+		UPDATE_COEF(0x4f, 0xfcc0, 0xc400),
+		UPDATE_COEF(0x50, 0x2000, 0x2000),
+		UPDATE_COEF(0x56, 0x0006, 0x0006),
+		UPDATE_COEF(0x66, 0x0008, 0),
+		UPDATE_COEF(0x67, 0x2000, 0),
+		{}
+	};
 	static struct coef_fw coef0292[] = {
 		WRITE_COEF(0x76, 0x000e),
 		WRITE_COEF(0x6c, 0x2400),
@@ -3492,12 +3511,18 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
 
 	switch (codec->vendor_id) {
 	case 0x10ec0255:
+	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0255);
 		break;
 	case 0x10ec0233:
 	case 0x10ec0283:
 		alc_process_coef_fw(codec, coef0233);
 		break;
+	case 0x10ec0286:
+	case 0x10ec0288:
+	case 0x10ec0298:
+		alc_process_coef_fw(codec, coef0288);
+		break;
 	case 0x10ec0292:
 		alc_process_coef_fw(codec, coef0292);
 		break;
@@ -3527,6 +3552,14 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin,
 		WRITE_COEF(0x26, 0x008c),
 		{}
 	};
+	static struct coef_fw coef0288[] = {
+		UPDATE_COEF(0x50, 0x2000, 0),
+		UPDATE_COEF(0x56, 0x0006, 0),
+		UPDATE_COEF(0x4f, 0xfcc0, 0xc400),
+		UPDATE_COEF(0x66, 0x0008, 0x0008),
+		UPDATE_COEF(0x67, 0x2000, 0x2000),
+		{}
+	};
 	static struct coef_fw coef0292[] = {
 		WRITE_COEF(0x19, 0xa208),
 		WRITE_COEF(0x2e, 0xacf0),
@@ -3547,6 +3580,7 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin,
 
 	switch (codec->vendor_id) {
 	case 0x10ec0255:
+	case 0x10ec0256:
 		alc_write_coef_idx(codec, 0x45, 0xc489);
 		snd_hda_set_pin_ctl_cache(codec, hp_pin, 0);
 		alc_process_coef_fw(codec, coef0255);
@@ -3559,6 +3593,14 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin,
 		alc_process_coef_fw(codec, coef0233);
 		snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50);
 		break;
+	case 0x10ec0286:
+	case 0x10ec0288:
+	case 0x10ec0298:
+		alc_update_coef_idx(codec, 0x4f, 0x000c, 0);
+		snd_hda_set_pin_ctl_cache(codec, hp_pin, 0);
+		alc_process_coef_fw(codec, coef0288);
+		snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50);
+		break;
 	case 0x10ec0292:
 		snd_hda_set_pin_ctl_cache(codec, hp_pin, 0);
 		alc_process_coef_fw(codec, coef0292);
@@ -3570,6 +3612,10 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin,
 		alc_process_coef_fw(codec, coef0293);
 		snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50);
 		break;
+	case 0x10ec0662:
+		snd_hda_set_pin_ctl_cache(codec, hp_pin, 0);
+		snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50);
+		break;
 	case 0x10ec0668:
 		alc_write_coef_idx(codec, 0x11, 0x0001);
 		snd_hda_set_pin_ctl_cache(codec, hp_pin, 0);
@@ -3594,6 +3640,14 @@ static void alc_headset_mode_default(struct hda_codec *codec)
 		WRITE_COEF(0x32, 0x4ea3),
 		{}
 	};
+	static struct coef_fw coef0288[] = {
+		UPDATE_COEF(0x4f, 0xfcc0, 0xc400), /* Set to TRS type */
+		UPDATE_COEF(0x50, 0x2000, 0x2000),
+		UPDATE_COEF(0x56, 0x0006, 0x0006),
+		UPDATE_COEF(0x66, 0x0008, 0),
+		UPDATE_COEF(0x67, 0x2000, 0),
+		{}
+	};
 	static struct coef_fw coef0292[] = {
 		WRITE_COEF(0x76, 0x000e),
 		WRITE_COEF(0x6c, 0x2400),
@@ -3616,12 +3670,18 @@ static void alc_headset_mode_default(struct hda_codec *codec)
 
 	switch (codec->vendor_id) {
 	case 0x10ec0255:
+	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0255);
 		break;
 	case 0x10ec0233:
 	case 0x10ec0283:
 		alc_process_coef_fw(codec, coef0233);
 		break;
+	case 0x10ec0286:
+	case 0x10ec0288:
+	case 0x10ec0298:
+		alc_process_coef_fw(codec, coef0288);
+		break;
 	case 0x10ec0292:
 		alc_process_coef_fw(codec, coef0292);
 		break;
@@ -3650,6 +3710,13 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
 		WRITE_COEF(0x32, 0x4ea3),
 		{}
 	};
+	static struct coef_fw coef0288[] = {
+		UPDATE_COEF(0x50, 0x2000, 0x2000),
+		UPDATE_COEF(0x56, 0x0006, 0x0006),
+		UPDATE_COEF(0x66, 0x0008, 0),
+		UPDATE_COEF(0x67, 0x2000, 0),
+		{}
+	};
 	static struct coef_fw coef0292[] = {
 		WRITE_COEF(0x6b, 0xd429),
 		WRITE_COEF(0x76, 0x0008),
@@ -3670,12 +3737,22 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
 
 	switch (codec->vendor_id) {
 	case 0x10ec0255:
+	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0255);
 		break;
 	case 0x10ec0233:
 	case 0x10ec0283:
 		alc_process_coef_fw(codec, coef0233);
 		break;
+	case 0x10ec0298:
+		alc_update_coef_idx(codec, 0x8e, 0x0070, 0x0020);/* Headset output enable */
+		/* ALC298 jack type setting is the same with ALC286/ALC288 */
+	case 0x10ec0286:
+	case 0x10ec0288:
+		alc_update_coef_idx(codec, 0x4f, 0xfcc0, 0xd400);
+		msleep(300);
+		alc_process_coef_fw(codec, coef0288);
+		break;
 	case 0x10ec0292:
 		alc_process_coef_fw(codec, coef0292);
 		break;
@@ -3704,6 +3781,13 @@ static void alc_headset_mode_omtp(struct hda_codec *codec)
 		WRITE_COEF(0x32, 0x4ea3),
 		{}
 	};
+	static struct coef_fw coef0288[] = {
+		UPDATE_COEF(0x50, 0x2000, 0x2000),
+		UPDATE_COEF(0x56, 0x0006, 0x0006),
+		UPDATE_COEF(0x66, 0x0008, 0),
+		UPDATE_COEF(0x67, 0x2000, 0),
+		{}
+	};
 	static struct coef_fw coef0292[] = {
 		WRITE_COEF(0x6b, 0xe429),
 		WRITE_COEF(0x76, 0x0008),
@@ -3724,12 +3808,22 @@ static void alc_headset_mode_omtp(struct hda_codec *codec)
 
 	switch (codec->vendor_id) {
 	case 0x10ec0255:
+	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0255);
 		break;
 	case 0x10ec0233:
 	case 0x10ec0283:
 		alc_process_coef_fw(codec, coef0233);
 		break;
+	case 0x10ec0298:
+		alc_update_coef_idx(codec, 0x8e, 0x0070, 0x0010);/* Headset output enable */
+		/* ALC298 jack type setting is the same with ALC286/ALC288 */
+	case 0x10ec0286:
+	case 0x10ec0288:
+		alc_update_coef_idx(codec, 0x4f, 0xfcc0, 0xe400);
+		msleep(300);
+		alc_process_coef_fw(codec, coef0288);
+		break;
 	case 0x10ec0292:
 		alc_process_coef_fw(codec, coef0292);
 		break;
@@ -3754,6 +3848,10 @@ static void alc_determine_headset_type(struct hda_codec *codec)
  conteol) */
 		{}
 	};
+	static struct coef_fw coef0288[] = {
+		UPDATE_COEF(0x4f, 0xfcc0, 0xd400), /* Check Type */
+		{}
+	};
 	static struct coef_fw coef0293[] = {
 		UPDATE_COEF(0x4a, 0x000f, 0x0008), /* Combo Jack auto detect */
 		WRITE_COEF(0x45, 0xD429), /* Set to ctia type */
@@ -3769,6 +3867,7 @@ static void alc_determine_headset_type(struct hda_codec *codec)
 
 	switch (codec->vendor_id) {
 	case 0x10ec0255:
+	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0255);
 		msleep(300);
 		val = alc_read_coef_idx(codec, 0x46);
@@ -3781,6 +3880,16 @@ static void alc_determine_headset_type(struct hda_codec *codec)
 		val = alc_read_coef_idx(codec, 0x46);
 		is_ctia = (val & 0x0070) == 0x0070;
 		break;
+	case 0x10ec0298:
+		alc_update_coef_idx(codec, 0x8e, 0x0070, 0x0020); /* Headset output enable */
+		/* ALC298 check jack type is the same with ALC286/ALC288 */
+	case 0x10ec0286:
+	case 0x10ec0288:
+		alc_process_coef_fw(codec, coef0288);
+		msleep(350);
+		val = alc_read_coef_idx(codec, 0x50);
+		is_ctia = (val & 0x0070) == 0x0070;
+		break;
 	case 0x10ec0292:
 		alc_write_coef_idx(codec, 0x6b, 0xd429);
 		msleep(300);
@@ -3855,7 +3964,7 @@ static void alc_update_headset_mode(struct hda_codec *codec)
 	if (new_headset_mode != ALC_HEADSET_MODE_MIC) {
 		snd_hda_set_pin_ctl_cache(codec, hp_pin,
 					  AC_PINCTL_OUT_EN | AC_PINCTL_HP_EN);
-		if (spec->headphone_mic_pin)
+		if (spec->headphone_mic_pin && spec->headphone_mic_pin != hp_pin)
 			snd_hda_set_pin_ctl_cache(codec, spec->headphone_mic_pin,
 						  PIN_VREFHIZ);
 	}
@@ -4030,6 +4139,23 @@ static void alc_fixup_dell_xps13(struct hda_codec *codec,
 	}
 }
 
+static void alc_fixup_headset_mode_alc662(struct hda_codec *codec,
+				const struct hda_fixup *fix, int action)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->parse_flags |= HDA_PINCFG_HEADSET_MIC;
+		spec->gen.hp_mic = 1; /* Mic-in is same pin as headphone */
+
+		/* Disable boost for mic-in permanently. (This code is only called
+		   from quirks that guarantee that the headphone is at NID 0x1b.) */
+		snd_hda_codec_write(codec, 0x1b, 0, AC_VERB_SET_AMP_GAIN_MUTE, 0x7000);
+		snd_hda_override_wcaps(codec, 0x1b, get_wcaps(codec, 0x1b) & ~AC_WCAP_IN_AMP);
+	} else
+		alc_fixup_headset_mode(codec, fix, action);
+}
+
 static void alc_fixup_headset_mode_alc668(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)
 {
@@ -4249,6 +4375,8 @@ enum {
 	ALC269_FIXUP_QUANTA_MUTE,
 	ALC269_FIXUP_LIFEBOOK,
 	ALC269_FIXUP_LIFEBOOK_EXTMIC,
+	ALC269_FIXUP_LIFEBOOK_HP_PIN,
+	ALC269_FIXUP_LIFEBOOK_NO_HP_TO_LINEOUT,
 	ALC269_FIXUP_AMIC,
 	ALC269_FIXUP_DMIC,
 	ALC269VB_FIXUP_AMIC,
@@ -4269,6 +4397,7 @@ enum {
 	ALC269_FIXUP_DELL3_MIC_NO_PRESENCE,
 	ALC269_FIXUP_HEADSET_MODE,
 	ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC,
+	ALC269_FIXUP_ASPIRE_HEADSET_MIC,
 	ALC269_FIXUP_ASUS_X101_FUNC,
 	ALC269_FIXUP_ASUS_X101_VERB,
 	ALC269_FIXUP_ASUS_X101,
@@ -4296,6 +4425,7 @@ enum {
 	ALC255_FIXUP_HEADSET_MODE_NO_HP_MIC,
 	ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
 	ALC292_FIXUP_TPT440_DOCK,
+	ALC292_FIXUP_TPT440_DOCK2,
 	ALC283_FIXUP_BXBT2807_MIC,
 	ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED,
 	ALC282_FIXUP_ASPIRE_V5_PINS,
@@ -4399,6 +4529,17 @@ static const struct hda_fixup alc269_fixups[] = {
 			{ }
 		},
 	},
+	[ALC269_FIXUP_LIFEBOOK_HP_PIN] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x21, 0x0221102f }, /* HP out */
+			{ }
+		},
+	},
+	[ALC269_FIXUP_LIFEBOOK_NO_HP_TO_LINEOUT] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc269_fixup_pincfg_no_hp_to_lineout,
+	},
 	[ALC269_FIXUP_AMIC] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -4527,6 +4668,15 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_headset_mode_no_hp_mic,
 	},
+	[ALC269_FIXUP_ASPIRE_HEADSET_MIC] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x01a1913c }, /* headset mic w/o jack detect */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MODE,
+	},
 	[ALC286_FIXUP_SONY_MIC_NO_PRESENCE] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -4729,6 +4879,12 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chain_id = ALC269_FIXUP_HEADSET_MODE
 	},
 	[ALC292_FIXUP_TPT440_DOCK] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc269_fixup_pincfg_no_hp_to_lineout,
+		.chained = true,
+		.chain_id = ALC292_FIXUP_TPT440_DOCK2
+	},
+	[ALC292_FIXUP_TPT440_DOCK2] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
 			{ 0x16, 0x21211010 }, /* dock headphone */
@@ -4776,6 +4932,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x029b, "Acer 1810TZ", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x0349, "Acer AOD260", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x047c, "Acer AC700", ALC269_FIXUP_ACER_AC700),
+	SND_PCI_QUIRK(0x1025, 0x072d, "Acer Aspire V5-571G", ALC269_FIXUP_ASPIRE_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1025, 0x080d, "Acer Aspire V5-122P", ALC269_FIXUP_ASPIRE_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x0740, "Acer AO725", ALC271_FIXUP_HP_GATE_MIC_JACK),
 	SND_PCI_QUIRK(0x1025, 0x0742, "Acer AO756", ALC271_FIXUP_HP_GATE_MIC_JACK),
 	SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
@@ -4790,6 +4948,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0638, "Dell Inspiron 5439", ALC290_FIXUP_MONO_SPEAKERS_HSJACK),
 	SND_PCI_QUIRK(0x1028, 0x064a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x064b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x06c7, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x06d9, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x06da, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
@@ -4798,6 +4957,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x18e6, "HP", ALC269_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x218b, "HP", ALC269_FIXUP_LIMIT_INT_MIC_BOOST_MUTE_LED),
 	/* ALC282 */
+	SND_PCI_QUIRK(0x103c, 0x21f9, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2210, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2214, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2236, "HP", ALC269_FIXUP_HP_LINE1_MIC1_LED),
@@ -4867,6 +5027,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x104d, 0x9084, "Sony VAIO", ALC275_FIXUP_SONY_HWEQ),
 	SND_PCI_QUIRK(0x104d, 0x9099, "Sony VAIO S13", ALC275_FIXUP_SONY_DISABLE_AAMIX),
 	SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK),
+	SND_PCI_QUIRK(0x10cf, 0x159f, "Lifebook E780", ALC269_FIXUP_LIFEBOOK_NO_HP_TO_LINEOUT),
+	SND_PCI_QUIRK(0x10cf, 0x15dc, "Lifebook T731", ALC269_FIXUP_LIFEBOOK_HP_PIN),
+	SND_PCI_QUIRK(0x10cf, 0x1757, "Lifebook E752", ALC269_FIXUP_LIFEBOOK_HP_PIN),
 	SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
 	SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_BXBT2807_MIC),
@@ -4887,11 +5050,16 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x2212, "Thinkpad T440", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad X240", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x17aa, 0x2226, "ThinkPad X250", ALC292_FIXUP_TPT440_DOCK),
+	SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP),
 	SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC283_FIXUP_INT_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x501e, "Thinkpad L440", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x5026, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x17aa, 0x5034, "Thinkpad T450", ALC292_FIXUP_TPT440_DOCK),
+	SND_PCI_QUIRK(0x17aa, 0x5036, "Thinkpad T450s", ALC292_FIXUP_TPT440_DOCK),
+	SND_PCI_QUIRK(0x17aa, 0x503c, "Thinkpad L450", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K),
 	SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD),
@@ -4980,6 +5148,16 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{0x1b, 0x411111f0}, \
 	{0x1e, 0x411111f0}
 
+#define ALC256_STANDARD_PINS \
+	{0x12, 0x90a60140}, \
+	{0x14, 0x90170110}, \
+	{0x19, 0x411111f0}, \
+	{0x1a, 0x411111f0}, \
+	{0x1b, 0x411111f0}, \
+	{0x1d, 0x40700001}, \
+	{0x1e, 0x411111f0}, \
+	{0x21, 0x02211020}
+
 #define ALC282_STANDARD_PINS \
 	{0x14, 0x90170110}, \
 	{0x18, 0x411111f0}, \
@@ -5065,6 +5243,26 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x17, 0x40000000},
 		{0x1d, 0x40700001},
 		{0x21, 0x02211040}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC255_STANDARD_PINS,
+		{0x12, 0x90a60170},
+		{0x14, 0x90170140},
+		{0x17, 0x40000000},
+		{0x1d, 0x40700001},
+		{0x21, 0x02211050}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell Inspiron 5548", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC255_STANDARD_PINS,
+		{0x12, 0x90a60180},
+		{0x14, 0x90170130},
+		{0x17, 0x40000000},
+		{0x1d, 0x40700001},
+		{0x21, 0x02211040}),
+	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC256_STANDARD_PINS,
+		{0x13, 0x40000000}),
+	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC256_STANDARD_PINS,
+		{0x13, 0x411111f0}),
 	SND_HDA_PIN_QUIRK(0x10ec0280, 0x103c, "HP", ALC280_FIXUP_HP_GPIO4,
 		{0x12, 0x90a60130},
 		{0x13, 0x40000000},
@@ -5376,9 +5574,17 @@ static int patch_alc269(struct hda_codec *codec)
 		spec->codec_variant = ALC269_TYPE_ALC286;
 		spec->shutup = alc286_shutup;
 		break;
+	case 0x10ec0298:
+		spec->codec_variant = ALC269_TYPE_ALC298;
+		break;
 	case 0x10ec0255:
 		spec->codec_variant = ALC269_TYPE_ALC255;
 		break;
+	case 0x10ec0256:
+		spec->codec_variant = ALC269_TYPE_ALC256;
+		spec->gen.mixer_nid = 0; /* ALC256 does not have any loopback mixer path */
+		alc_update_coef_idx(codec, 0x36, 1 << 13, 1 << 5); /* Switch pcbeep path to Line in path*/
+		break;
 	}
 
 	if (snd_hda_codec_read(codec, 0x51, 0, AC_VERB_PARAMETERS, 0) == 0x10ec5505) {
@@ -5391,8 +5597,8 @@ static int patch_alc269(struct hda_codec *codec)
 	if (err < 0)
 		goto error;
 
-	if (!spec->gen.no_analog && spec->gen.beep_nid)
-		set_beep_amp(spec, 0x0b, 0x04, HDA_INPUT);
+	if (!spec->gen.no_analog && spec->gen.beep_nid && spec->gen.mixer_nid)
+		set_beep_amp(spec, spec->gen.mixer_nid, 0x04, HDA_INPUT);
 
 	codec->patch_ops = alc_patch_ops;
 #ifdef CONFIG_PM
@@ -5790,7 +5996,9 @@ enum {
 	ALC662_FIXUP_NO_JACK_DETECT,
 	ALC662_FIXUP_ZOTAC_Z68,
 	ALC662_FIXUP_INV_DMIC,
+	ALC662_FIXUP_DELL_MIC_NO_PRESENCE,
 	ALC668_FIXUP_DELL_MIC_NO_PRESENCE,
+	ALC662_FIXUP_HEADSET_MODE,
 	ALC668_FIXUP_HEADSET_MODE,
 	ALC662_FIXUP_BASS_MODE4_CHMAP,
 	ALC662_FIXUP_BASS_16,
@@ -5983,6 +6191,20 @@ static const struct hda_fixup alc662_fixups[] = {
 		.chained = true,
 		.chain_id = ALC668_FIXUP_DELL_MIC_NO_PRESENCE
 	},
+	[ALC662_FIXUP_DELL_MIC_NO_PRESENCE] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x03a1113c }, /* use as headset mic, without its own jack detect */
+			/* headphone mic by setting pin control of 0x1b (headphone out) to in + vref_50 */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC662_FIXUP_HEADSET_MODE
+	},
+	[ALC662_FIXUP_HEADSET_MODE] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_headset_mode_alc662,
+	},
 	[ALC668_FIXUP_DELL_MIC_NO_PRESENCE] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -6134,6 +6356,18 @@ static const struct hda_model_fixup alc662_fixup_models[] = {
 };
 
 static const struct snd_hda_pin_quirk alc662_pin_fixup_tbl[] = {
+	SND_HDA_PIN_QUIRK(0x10ec0662, 0x1028, "Dell", ALC662_FIXUP_DELL_MIC_NO_PRESENCE,
+		{0x12, 0x4004c000},
+		{0x14, 0x01014010},
+		{0x15, 0x411111f0},
+		{0x16, 0x411111f0},
+		{0x18, 0x01a19020},
+		{0x19, 0x411111f0},
+		{0x1a, 0x0181302f},
+		{0x1b, 0x0221401f},
+		{0x1c, 0x411111f0},
+		{0x1d, 0x4054c601},
+		{0x1e, 0x411111f0}),
 	SND_HDA_PIN_QUIRK(0x10ec0668, 0x1028, "Dell", ALC668_FIXUP_AUTO_MUTE,
 		{0x12, 0x99a30130},
 		{0x14, 0x90170110},
@@ -6314,6 +6548,7 @@ static const struct hda_codec_preset snd_hda_preset_realtek[] = {
 	{ .id = 0x10ec0233, .name = "ALC233", .patch = patch_alc269 },
 	{ .id = 0x10ec0235, .name = "ALC233", .patch = patch_alc269 },
 	{ .id = 0x10ec0255, .name = "ALC255", .patch = patch_alc269 },
+	{ .id = 0x10ec0256, .name = "ALC256", .patch = patch_alc269 },
 	{ .id = 0x10ec0260, .name = "ALC260", .patch = patch_alc260 },
 	{ .id = 0x10ec0262, .name = "ALC262", .patch = patch_alc262 },
 	{ .id = 0x10ec0267, .name = "ALC267", .patch = patch_alc268 },
@@ -6333,6 +6568,7 @@ static const struct hda_codec_preset snd_hda_preset_realtek[] = {
 	{ .id = 0x10ec0290, .name = "ALC290", .patch = patch_alc269 },
 	{ .id = 0x10ec0292, .name = "ALC292", .patch = patch_alc269 },
 	{ .id = 0x10ec0293, .name = "ALC293", .patch = patch_alc269 },
+	{ .id = 0x10ec0298, .name = "ALC298", .patch = patch_alc269 },
 	{ .id = 0x10ec0861, .rev = 0x100340, .name = "ALC660",
 	  .patch = patch_alc861 },
 	{ .id = 0x10ec0660, .name = "ALC660-VD", .patch = patch_alc861vd },
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 4f6413e01c1..60b3100a212 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -79,6 +79,7 @@ enum {
 	STAC_ALIENWARE_M17X,
 	STAC_92HD89XX_HP_FRONT_JACK,
 	STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK,
+	STAC_92HD73XX_ASUS_MOBO,
 	STAC_92HD73XX_MODELS
 };
 
@@ -99,6 +100,8 @@ enum {
 	STAC_HP_ENVY_BASS,
 	STAC_HP_BNB13_EQ,
 	STAC_HP_ENVY_TS_BASS,
+	STAC_HP_ENVY_TS_DAC_BIND,
+	STAC_92HD83XXX_GPIO10_EAPD,
 	STAC_92HD83XXX_MODELS
 };
 
@@ -568,9 +571,9 @@ static void stac_store_hints(struct hda_codec *codec)
 			spec->gpio_mask;
 	}
 	if (get_int_hint(codec, "gpio_dir", &spec->gpio_dir))
-		spec->gpio_mask &= spec->gpio_mask;
-	if (get_int_hint(codec, "gpio_data", &spec->gpio_data))
 		spec->gpio_dir &= spec->gpio_mask;
+	if (get_int_hint(codec, "gpio_data", &spec->gpio_data))
+		spec->gpio_data &= spec->gpio_mask;
 	if (get_int_hint(codec, "eapd_mask", &spec->eapd_mask))
 		spec->eapd_mask &= spec->gpio_mask;
 	if (get_int_hint(codec, "gpio_mute", &spec->gpio_mute))
@@ -1910,7 +1913,18 @@ static const struct hda_fixup stac92hd73xx_fixups[] = {
 	[STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = stac92hd89xx_hp_z1_g2_right_mic_jack_pin_configs,
-	}
+	},
+	[STAC_92HD73XX_ASUS_MOBO] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			/* enable 5.1 and SPDIF out */
+			{ 0x0c, 0x01014411 },
+			{ 0x0d, 0x01014410 },
+			{ 0x0e, 0x01014412 },
+			{ 0x22, 0x014b1180 },
+			{ }
+		}
+	},
 };
 
 static const struct hda_model_fixup stac92hd73xx_models[] = {
@@ -1922,6 +1936,7 @@ static const struct hda_model_fixup stac92hd73xx_models[] = {
 	{ .id = STAC_DELL_M6_BOTH, .name = "dell-m6" },
 	{ .id = STAC_DELL_EQ, .name = "dell-eq" },
 	{ .id = STAC_ALIENWARE_M17X, .name = "alienware" },
+	{ .id = STAC_92HD73XX_ASUS_MOBO, .name = "asus-mobo" },
 	{}
 };
 
@@ -1974,6 +1989,8 @@ static const struct snd_pci_quirk stac92hd73xx_fixup_tbl[] = {
 				"HP Z1 G2", STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x2b17,
 				"unknown HP", STAC_92HD89XX_HP_FRONT_JACK),
+	SND_PCI_QUIRK(PCI_VENDOR_ID_ASUSTEK, 0x83f8, "ASUS AT4NM10",
+		      STAC_92HD73XX_ASUS_MOBO),
 	{} /* terminator */
 };
 
@@ -2141,6 +2158,35 @@ static void stac92hd83xxx_fixup_headset_jack(struct hda_codec *codec,
 		spec->headset_jack = 1;
 }
 
+static void stac92hd83xxx_fixup_gpio10_eapd(struct hda_codec *codec,
+					    const struct hda_fixup *fix,
+					    int action)
+{
+	struct sigmatel_spec *spec = codec->spec;
+
+	if (action != HDA_FIXUP_ACT_PRE_PROBE)
+		return;
+	spec->eapd_mask = spec->gpio_mask = spec->gpio_dir =
+		spec->gpio_data = 0x10;
+	spec->eapd_switch = 0;
+}
+
+static void hp_envy_ts_fixup_dac_bind(struct hda_codec *codec,
+					    const struct hda_fixup *fix,
+					    int action)
+{
+	struct sigmatel_spec *spec = codec->spec;
+	static hda_nid_t preferred_pairs[] = {
+		0xd, 0x13,
+		0
+	};
+
+	if (action != HDA_FIXUP_ACT_PRE_PROBE)
+		return;
+
+	spec->gen.preferred_dacs = preferred_pairs;
+}
+
 static const struct hda_verb hp_bnb13_eq_verbs[] = {
 	/* 44.1KHz base */
 	{ 0x22, 0x7A6, 0x3E },
@@ -2656,6 +2702,16 @@ static const struct hda_fixup stac92hd83xxx_fixups[] = {
 			{}
 		},
 	},
+	[STAC_HP_ENVY_TS_DAC_BIND] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = hp_envy_ts_fixup_dac_bind,
+		.chained = true,
+		.chain_id = STAC_HP_ENVY_TS_BASS,
+	},
+	[STAC_92HD83XXX_GPIO10_EAPD] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = stac92hd83xxx_fixup_gpio10_eapd,
+	},
 };
 
 static const struct hda_model_fixup stac92hd83xxx_models[] = {
@@ -2730,6 +2786,8 @@ static const struct snd_pci_quirk stac92hd83xxx_fixup_tbl[] = {
 			  "HP bNB13", STAC_HP_BNB13_EQ),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x190e,
 			  "HP ENVY TS", STAC_HP_ENVY_TS_BASS),
+	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1967,
+			  "HP ENVY TS", STAC_HP_ENVY_TS_DAC_BIND),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1940,
 			  "HP bNB13", STAC_HP_BNB13_EQ),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1941,
@@ -2861,6 +2919,8 @@ static const struct snd_pci_quirk stac92hd83xxx_fixup_tbl[] = {
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x148a,
 		      "HP Mini", STAC_92HD83XXX_HP_LED),
 	SND_PCI_QUIRK_VENDOR(PCI_VENDOR_ID_HP, "HP", STAC_92HD83XXX_HP),
+	SND_PCI_QUIRK(PCI_VENDOR_ID_TOSHIBA, 0xfa91,
+		      "Toshiba Satellite S50D", STAC_92HD83XXX_GPIO10_EAPD),
 	{} /* terminator */
 };
 
diff --git a/sound/pci/riptide/riptide.c b/sound/pci/riptide/riptide.c
index 6abc2ac8fff..e7685727769 100644
--- a/sound/pci/riptide/riptide.c
+++ b/sound/pci/riptide/riptide.c
@@ -2030,32 +2030,43 @@ snd_riptide_joystick_probe(struct pci_dev *pci, const struct pci_device_id *id)
 {
 	static int dev;
 	struct gameport *gameport;
+	int ret;
 
 	if (dev >= SNDRV_CARDS)
 		return -ENODEV;
+
 	if (!enable[dev]) {
-		dev++;
-		return -ENOENT;
+		ret = -ENOENT;
+		goto inc_dev;
 	}
 
-	if (!joystick_port[dev++])
-		return 0;
+	if (!joystick_port[dev]) {
+		ret = 0;
+		goto inc_dev;
+	}
 
 	gameport = gameport_allocate_port();
-	if (!gameport)
-		return -ENOMEM;
+	if (!gameport) {
+		ret = -ENOMEM;
+		goto inc_dev;
+	}
 	if (!request_region(joystick_port[dev], 8, "Riptide gameport")) {
 		snd_printk(KERN_WARNING
 			   "Riptide: cannot grab gameport 0x%x\n",
 			   joystick_port[dev]);
 		gameport_free_port(gameport);
-		return -EBUSY;
+		ret = -EBUSY;
+		goto inc_dev;
 	}
 
 	gameport->io = joystick_port[dev];
 	gameport_register_port(gameport);
 	pci_set_drvdata(pci, gameport);
-	return 0;
+
+	ret = 0;
+inc_dev:
+	dev++;
+	return ret;
 }
 
 static void snd_riptide_joystick_remove(struct pci_dev *pci)
diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c
index 52d86af3ef2..fcf91ee0328 100644
--- a/sound/pci/rme9652/hdspm.c
+++ b/sound/pci/rme9652/hdspm.c
@@ -6114,6 +6114,9 @@ static int snd_hdspm_playback_open(struct snd_pcm_substream *substream)
 		snd_pcm_hw_constraint_minmax(runtime,
 					     SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
 					     64, 8192);
+		snd_pcm_hw_constraint_minmax(runtime,
+					     SNDRV_PCM_HW_PARAM_PERIODS,
+					     2, 2);
 		break;
 	}
 
@@ -6188,6 +6191,9 @@ static int snd_hdspm_capture_open(struct snd_pcm_substream *substream)
 		snd_pcm_hw_constraint_minmax(runtime,
 					     SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
 					     64, 8192);
+		snd_pcm_hw_constraint_minmax(runtime,
+					     SNDRV_PCM_HW_PARAM_PERIODS,
+					     2, 2);
 		break;
 	}
 
diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c
index f403f399808..51413e239cc 100644
--- a/sound/soc/atmel/atmel_ssc_dai.c
+++ b/sound/soc/atmel/atmel_ssc_dai.c
@@ -345,7 +345,6 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream,
 	struct atmel_pcm_dma_params *dma_params;
 	int dir, channels, bits;
 	u32 tfmr, rfmr, tcmr, rcmr;
-	int start_event;
 	int ret;
 	int fslen, fslen_ext;
 
@@ -454,19 +453,10 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream,
 		 * The SSC transmit clock is obtained from the BCLK signal on
 		 * on the TK line, and the SSC receive clock is
 		 * generated from the transmit clock.
-		 *
-		 *  For single channel data, one sample is transferred
-		 * on the falling edge of the LRC clock.
-		 * For two channel data, one sample is
-		 * transferred on both edges of the LRC clock.
 		 */
-		start_event = ((channels == 1)
-				? SSC_START_FALLING_RF
-				: SSC_START_EDGE_RF);
-
 		rcmr =	  SSC_BF(RCMR_PERIOD, 0)
 			| SSC_BF(RCMR_STTDLY, START_DELAY)
-			| SSC_BF(RCMR_START, start_event)
+			| SSC_BF(RCMR_START, SSC_START_FALLING_RF)
 			| SSC_BF(RCMR_CKI, SSC_CKI_RISING)
 			| SSC_BF(RCMR_CKO, SSC_CKO_NONE)
 			| SSC_BF(RCMR_CKS, ssc->clk_from_rk_pin ?
@@ -475,14 +465,14 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream,
 		rfmr =	  SSC_BF(RFMR_FSEDGE, SSC_FSEDGE_POSITIVE)
 			| SSC_BF(RFMR_FSOS, SSC_FSOS_NONE)
 			| SSC_BF(RFMR_FSLEN, 0)
-			| SSC_BF(RFMR_DATNB, 0)
+			| SSC_BF(RFMR_DATNB, (channels - 1))
 			| SSC_BIT(RFMR_MSBF)
 			| SSC_BF(RFMR_LOOP, 0)
 			| SSC_BF(RFMR_DATLEN, (bits - 1));
 
 		tcmr =	  SSC_BF(TCMR_PERIOD, 0)
 			| SSC_BF(TCMR_STTDLY, START_DELAY)
-			| SSC_BF(TCMR_START, start_event)
+			| SSC_BF(TCMR_START, SSC_START_FALLING_RF)
 			| SSC_BF(TCMR_CKI, SSC_CKI_FALLING)
 			| SSC_BF(TCMR_CKO, SSC_CKO_NONE)
 			| SSC_BF(TCMR_CKS, ssc->clk_from_rk_pin ?
@@ -492,7 +482,7 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream,
 			| SSC_BF(TFMR_FSDEN, 0)
 			| SSC_BF(TFMR_FSOS, SSC_FSOS_NONE)
 			| SSC_BF(TFMR_FSLEN, 0)
-			| SSC_BF(TFMR_DATNB, 0)
+			| SSC_BF(TFMR_DATNB, (channels - 1))
 			| SSC_BIT(TFMR_MSBF)
 			| SSC_BF(TFMR_DATDEF, 0)
 			| SSC_BF(TFMR_DATLEN, (bits - 1));
diff --git a/sound/soc/codecs/adav80x.c b/sound/soc/codecs/adav80x.c
index ce3cdca9fc6..01ab70a7f59 100644
--- a/sound/soc/codecs/adav80x.c
+++ b/sound/soc/codecs/adav80x.c
@@ -317,7 +317,7 @@ static int adav80x_put_deemph(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct adav80x *adav80x = snd_soc_codec_get_drvdata(codec);
-	unsigned int deemph = ucontrol->value.enumerated.item[0];
+	unsigned int deemph = ucontrol->value.integer.value[0];
 
 	if (deemph > 1)
 		return -EINVAL;
@@ -333,7 +333,7 @@ static int adav80x_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct adav80x *adav80x = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = adav80x->deemph;
+	ucontrol->value.integer.value[0] = adav80x->deemph;
 	return 0;
 };
 
diff --git a/sound/soc/codecs/ak4641.c b/sound/soc/codecs/ak4641.c
index 7afe8f48208..570ec04fe41 100644
--- a/sound/soc/codecs/ak4641.c
+++ b/sound/soc/codecs/ak4641.c
@@ -76,7 +76,7 @@ static int ak4641_put_deemph(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct ak4641_priv *ak4641 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 
 	if (deemph > 1)
 		return -EINVAL;
@@ -92,7 +92,7 @@ static int ak4641_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct ak4641_priv *ak4641 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = ak4641->deemph;
+	ucontrol->value.integer.value[0] = ak4641->deemph;
 	return 0;
 };
 
diff --git a/sound/soc/codecs/ak4671.c b/sound/soc/codecs/ak4671.c
index 998fa0c5a0b..61a31802cf7 100644
--- a/sound/soc/codecs/ak4671.c
+++ b/sound/soc/codecs/ak4671.c
@@ -343,25 +343,25 @@ static const struct snd_soc_dapm_widget ak4671_dapm_widgets[] = {
 };
 
 static const struct snd_soc_dapm_route ak4671_intercon[] = {
-	{"DAC Left", "NULL", "PMPLL"},
-	{"DAC Right", "NULL", "PMPLL"},
-	{"ADC Left", "NULL", "PMPLL"},
-	{"ADC Right", "NULL", "PMPLL"},
+	{"DAC Left", NULL, "PMPLL"},
+	{"DAC Right", NULL, "PMPLL"},
+	{"ADC Left", NULL, "PMPLL"},
+	{"ADC Right", NULL, "PMPLL"},
 
 	/* Outputs */
-	{"LOUT1", "NULL", "LOUT1 Mixer"},
-	{"ROUT1", "NULL", "ROUT1 Mixer"},
-	{"LOUT2", "NULL", "LOUT2 Mix Amp"},
-	{"ROUT2", "NULL", "ROUT2 Mix Amp"},
-	{"LOUT3", "NULL", "LOUT3 Mixer"},
-	{"ROUT3", "NULL", "ROUT3 Mixer"},
+	{"LOUT1", NULL, "LOUT1 Mixer"},
+	{"ROUT1", NULL, "ROUT1 Mixer"},
+	{"LOUT2", NULL, "LOUT2 Mix Amp"},
+	{"ROUT2", NULL, "ROUT2 Mix Amp"},
+	{"LOUT3", NULL, "LOUT3 Mixer"},
+	{"ROUT3", NULL, "ROUT3 Mixer"},
 
 	{"LOUT1 Mixer", "DACL", "DAC Left"},
 	{"ROUT1 Mixer", "DACR", "DAC Right"},
 	{"LOUT2 Mixer", "DACHL", "DAC Left"},
 	{"ROUT2 Mixer", "DACHR", "DAC Right"},
-	{"LOUT2 Mix Amp", "NULL", "LOUT2 Mixer"},
-	{"ROUT2 Mix Amp", "NULL", "ROUT2 Mixer"},
+	{"LOUT2 Mix Amp", NULL, "LOUT2 Mixer"},
+	{"ROUT2 Mix Amp", NULL, "ROUT2 Mixer"},
 	{"LOUT3 Mixer", "DACSL", "DAC Left"},
 	{"ROUT3 Mixer", "DACSR", "DAC Right"},
 
@@ -381,18 +381,18 @@ static const struct snd_soc_dapm_route ak4671_intercon[] = {
 	{"LIN2", NULL, "Mic Bias"},
 	{"RIN2", NULL, "Mic Bias"},
 
-	{"ADC Left", "NULL", "LIN MUX"},
-	{"ADC Right", "NULL", "RIN MUX"},
+	{"ADC Left", NULL, "LIN MUX"},
+	{"ADC Right", NULL, "RIN MUX"},
 
 	/* Analog Loops */
-	{"LIN1 Mixing Circuit", "NULL", "LIN1"},
-	{"RIN1 Mixing Circuit", "NULL", "RIN1"},
-	{"LIN2 Mixing Circuit", "NULL", "LIN2"},
-	{"RIN2 Mixing Circuit", "NULL", "RIN2"},
-	{"LIN3 Mixing Circuit", "NULL", "LIN3"},
-	{"RIN3 Mixing Circuit", "NULL", "RIN3"},
-	{"LIN4 Mixing Circuit", "NULL", "LIN4"},
-	{"RIN4 Mixing Circuit", "NULL", "RIN4"},
+	{"LIN1 Mixing Circuit", NULL, "LIN1"},
+	{"RIN1 Mixing Circuit", NULL, "RIN1"},
+	{"LIN2 Mixing Circuit", NULL, "LIN2"},
+	{"RIN2 Mixing Circuit", NULL, "RIN2"},
+	{"LIN3 Mixing Circuit", NULL, "LIN3"},
+	{"RIN3 Mixing Circuit", NULL, "RIN3"},
+	{"LIN4 Mixing Circuit", NULL, "LIN4"},
+	{"RIN4 Mixing Circuit", NULL, "RIN4"},
 
 	{"LOUT1 Mixer", "LINL1", "LIN1 Mixing Circuit"},
 	{"ROUT1 Mixer", "RINR1", "RIN1 Mixing Circuit"},
diff --git a/sound/soc/codecs/cs4271.c b/sound/soc/codecs/cs4271.c
index 93cec52f473..38c2adc9977 100644
--- a/sound/soc/codecs/cs4271.c
+++ b/sound/soc/codecs/cs4271.c
@@ -287,7 +287,7 @@ static int cs4271_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct cs4271_private *cs4271 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = cs4271->deemph;
+	ucontrol->value.integer.value[0] = cs4271->deemph;
 	return 0;
 }
 
@@ -297,7 +297,7 @@ static int cs4271_put_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct cs4271_private *cs4271 = snd_soc_codec_get_drvdata(codec);
 
-	cs4271->deemph = ucontrol->value.enumerated.item[0];
+	cs4271->deemph = ucontrol->value.integer.value[0];
 	return cs4271_set_deemph(codec);
 }
 
@@ -561,10 +561,10 @@ static int cs4271_probe(struct snd_soc_codec *codec)
 	if (gpio_is_valid(cs4271->gpio_nreset)) {
 		/* Reset codec */
 		gpio_direction_output(cs4271->gpio_nreset, 0);
-		udelay(1);
+		mdelay(1);
 		gpio_set_value(cs4271->gpio_nreset, 1);
 		/* Give the codec time to wake up */
-		udelay(1);
+		mdelay(1);
 	}
 
 	ret = regmap_update_bits(cs4271->regmap, CS4271_MODE2,
diff --git a/sound/soc/codecs/da732x.c b/sound/soc/codecs/da732x.c
index 61b2f9a2eef..e3110c67f3b 100644
--- a/sound/soc/codecs/da732x.c
+++ b/sound/soc/codecs/da732x.c
@@ -876,11 +876,11 @@ static const struct snd_soc_dapm_widget da732x_dapm_widgets[] = {
 
 static const struct snd_soc_dapm_route da732x_dapm_routes[] = {
 	/* Inputs */
-	{"AUX1L PGA", "NULL", "AUX1L"},
-	{"AUX1R PGA", "NULL", "AUX1R"},
+	{"AUX1L PGA", NULL, "AUX1L"},
+	{"AUX1R PGA", NULL, "AUX1R"},
 	{"MIC1 PGA", NULL, "MIC1"},
-	{"MIC2 PGA", "NULL", "MIC2"},
-	{"MIC3 PGA", "NULL", "MIC3"},
+	{"MIC2 PGA", NULL, "MIC2"},
+	{"MIC3 PGA", NULL, "MIC3"},
 
 	/* Capture Path */
 	{"ADC1 Left MUX", "MIC1", "MIC1 PGA"},
diff --git a/sound/soc/codecs/es8328.c b/sound/soc/codecs/es8328.c
index f27325155ac..c5f35a07e8e 100644
--- a/sound/soc/codecs/es8328.c
+++ b/sound/soc/codecs/es8328.c
@@ -120,7 +120,7 @@ static int es8328_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct es8328_priv *es8328 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = es8328->deemph;
+	ucontrol->value.integer.value[0] = es8328->deemph;
 	return 0;
 }
 
@@ -129,7 +129,7 @@ static int es8328_put_deemph(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct es8328_priv *es8328 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 	int ret;
 
 	if (deemph > 1)
diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c
index 1229554f146..d492d6ea656 100644
--- a/sound/soc/codecs/max98090.c
+++ b/sound/soc/codecs/max98090.c
@@ -1395,8 +1395,8 @@ static const struct snd_soc_dapm_route max98090_dapm_routes[] = {
 	{"STENL Mux", "Sidetone Left", "DMICL"},
 	{"STENR Mux", "Sidetone Right", "ADCR"},
 	{"STENR Mux", "Sidetone Right", "DMICR"},
-	{"DACL", "NULL", "STENL Mux"},
-	{"DACR", "NULL", "STENL Mux"},
+	{"DACL", NULL, "STENL Mux"},
+	{"DACR", NULL, "STENL Mux"},
 
 	{"AIFINL", NULL, "SHDN"},
 	{"AIFINR", NULL, "SHDN"},
diff --git a/sound/soc/codecs/mc13783.c b/sound/soc/codecs/mc13783.c
index 71f775aad7c..2f98417b16b 100644
--- a/sound/soc/codecs/mc13783.c
+++ b/sound/soc/codecs/mc13783.c
@@ -623,14 +623,14 @@ static int mc13783_probe(struct snd_soc_codec *codec)
 				AUDIO_SSI_SEL, 0);
 	else
 		mc13xxx_reg_rmw(priv->mc13xxx, MC13783_AUDIO_CODEC,
-				0, AUDIO_SSI_SEL);
+				AUDIO_SSI_SEL, AUDIO_SSI_SEL);
 
 	if (priv->dac_ssi_port == MC13783_SSI1_PORT)
 		mc13xxx_reg_rmw(priv->mc13xxx, MC13783_AUDIO_DAC,
 				AUDIO_SSI_SEL, 0);
 	else
 		mc13xxx_reg_rmw(priv->mc13xxx, MC13783_AUDIO_DAC,
-				0, AUDIO_SSI_SEL);
+				AUDIO_SSI_SEL, AUDIO_SSI_SEL);
 
 	return 0;
 }
diff --git a/sound/soc/codecs/pcm1681.c b/sound/soc/codecs/pcm1681.c
index a722a023c26..477e13d3097 100644
--- a/sound/soc/codecs/pcm1681.c
+++ b/sound/soc/codecs/pcm1681.c
@@ -118,7 +118,7 @@ static int pcm1681_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct pcm1681_private *priv = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = priv->deemph;
+	ucontrol->value.integer.value[0] = priv->deemph;
 
 	return 0;
 }
@@ -129,7 +129,7 @@ static int pcm1681_put_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct pcm1681_private *priv = snd_soc_codec_get_drvdata(codec);
 
-	priv->deemph = ucontrol->value.enumerated.item[0];
+	priv->deemph = ucontrol->value.integer.value[0];
 
 	return pcm1681_set_deemph(codec);
 }
diff --git a/sound/soc/codecs/pcm512x-i2c.c b/sound/soc/codecs/pcm512x-i2c.c
index 4d62230bd37..d0547fa275f 100644
--- a/sound/soc/codecs/pcm512x-i2c.c
+++ b/sound/soc/codecs/pcm512x-i2c.c
@@ -24,8 +24,13 @@ static int pcm512x_i2c_probe(struct i2c_client *i2c,
 			     const struct i2c_device_id *id)
 {
 	struct regmap *regmap;
+	struct regmap_config config = pcm512x_regmap;
 
-	regmap = devm_regmap_init_i2c(i2c, &pcm512x_regmap);
+	/* msb needs to be set to enable auto-increment of addresses */
+	config.read_flag_mask = 0x80;
+	config.write_flag_mask = 0x80;
+
+	regmap = devm_regmap_init_i2c(i2c, &config);
 	if (IS_ERR(regmap))
 		return PTR_ERR(regmap);
 
diff --git a/sound/soc/codecs/pcm512x.c b/sound/soc/codecs/pcm512x.c
index 0c8aefab404..28b77214d82 100644
--- a/sound/soc/codecs/pcm512x.c
+++ b/sound/soc/codecs/pcm512x.c
@@ -188,8 +188,8 @@ static const DECLARE_TLV_DB_SCALE(boost_tlv, 0, 80, 0);
 static const char * const pcm512x_dsp_program_texts[] = {
 	"FIR interpolation with de-emphasis",
 	"Low latency IIR with de-emphasis",
-	"Fixed process flow",
 	"High attenuation with de-emphasis",
+	"Fixed process flow",
 	"Ringing-less low latency FIR",
 };
 
@@ -261,9 +261,9 @@ static const struct soc_enum pcm512x_veds =
 static const struct snd_kcontrol_new pcm512x_controls[] = {
 SOC_DOUBLE_R_TLV("Digital Playback Volume", PCM512x_DIGITAL_VOLUME_2,
 		 PCM512x_DIGITAL_VOLUME_3, 0, 255, 1, digital_tlv),
-SOC_DOUBLE_TLV("Playback Volume", PCM512x_ANALOG_GAIN_CTRL,
+SOC_DOUBLE_TLV("Analogue Playback Volume", PCM512x_ANALOG_GAIN_CTRL,
 	       PCM512x_LAGN_SHIFT, PCM512x_RAGN_SHIFT, 1, 1, analog_tlv),
-SOC_DOUBLE_TLV("Playback Boost Volume", PCM512x_ANALOG_GAIN_BOOST,
+SOC_DOUBLE_TLV("Analogue Playback Boost Volume", PCM512x_ANALOG_GAIN_BOOST,
 	       PCM512x_AGBL_SHIFT, PCM512x_AGBR_SHIFT, 1, 0, boost_tlv),
 SOC_DOUBLE("Digital Playback Switch", PCM512x_MUTE, PCM512x_RQML_SHIFT,
 	   PCM512x_RQMR_SHIFT, 1, 1),
diff --git a/sound/soc/codecs/rt5670.c b/sound/soc/codecs/rt5670.c
index 9bd8b4f6330..a8a9c1f36b2 100644
--- a/sound/soc/codecs/rt5670.c
+++ b/sound/soc/codecs/rt5670.c
@@ -222,7 +222,6 @@ static bool rt5670_volatile_register(struct device *dev, unsigned int reg)
 	case RT5670_ADC_EQ_CTRL1:
 	case RT5670_EQ_CTRL1:
 	case RT5670_ALC_CTRL_1:
-	case RT5670_IRQ_CTRL1:
 	case RT5670_IRQ_CTRL2:
 	case RT5670_INT_IRQ_ST:
 	case RT5670_IL_CMD:
@@ -2439,6 +2438,7 @@ static struct snd_soc_codec_driver soc_codec_dev_rt5670 = {
 static const struct regmap_config rt5670_regmap = {
 	.reg_bits = 8,
 	.val_bits = 16,
+	.use_single_rw = true,
 	.max_register = RT5670_VENDOR_ID2 + 1 + (ARRAY_SIZE(rt5670_ranges) *
 					       RT5670_PR_SPACING),
 	.volatile_reg = rt5670_volatile_register,
diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c
index 16aa4d99a71..691237a3ab5 100644
--- a/sound/soc/codecs/rt5677.c
+++ b/sound/soc/codecs/rt5677.c
@@ -644,7 +644,7 @@ static int set_dmic_clk(struct snd_soc_dapm_widget *w,
 {
 	struct snd_soc_codec *codec = w->codec;
 	struct rt5677_priv *rt5677 = snd_soc_codec_get_drvdata(codec);
-	int idx = rl6231_calc_dmic_clk(rt5677->sysclk);
+	int idx = rl6231_calc_dmic_clk(rt5677->lrck[RT5677_AIF1] << 8);
 
 	if (idx < 0)
 		dev_err(codec->dev, "Failed to set DMIC clock\n");
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index dab9b15304a..7de7431efcb 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -1136,13 +1136,7 @@ static int sgtl5000_set_power_regs(struct snd_soc_codec *codec)
 		/* Enable VDDC charge pump */
 		ana_pwr |= SGTL5000_VDDC_CHRGPMP_POWERUP;
 	} else if (vddio >= 3100 && vdda >= 3100) {
-		/*
-		 * if vddio and vddd > 3.1v,
-		 * charge pump should be clean before set ana_pwr
-		 */
-		snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER,
-				SGTL5000_VDDC_CHRGPMP_POWERUP, 0);
-
+		ana_pwr &= ~SGTL5000_VDDC_CHRGPMP_POWERUP;
 		/* VDDC use VDDIO rail */
 		lreg_ctrl |= SGTL5000_VDDC_ASSN_OVRD;
 		lreg_ctrl |= SGTL5000_VDDC_MAN_ASSN_VDDIO <<
@@ -1452,6 +1446,9 @@ static int sgtl5000_i2c_probe(struct i2c_client *client,
 	if (ret)
 		return ret;
 
+	/* Need 8 clocks before I2C accesses */
+	udelay(1);
+
 	/* read chip information */
 	ret = regmap_read(sgtl5000->regmap, SGTL5000_CHIP_ID, &reg);
 	if (ret)
diff --git a/sound/soc/codecs/sigmadsp.c b/sound/soc/codecs/sigmadsp.c
index f2de7e049bc..81a38dd9af1 100644
--- a/sound/soc/codecs/sigmadsp.c
+++ b/sound/soc/codecs/sigmadsp.c
@@ -159,6 +159,13 @@ int _process_sigma_firmware(struct device *dev,
 		goto done;
 	}
 
+	if (ssfw_head->version != 1) {
+		dev_err(dev,
+			"Failed to load firmware: Invalid version %d. Supported firmware versions: 1\n",
+			ssfw_head->version);
+		goto done;
+	}
+
 	crc = crc32(0, fw->data + sizeof(*ssfw_head),
 			fw->size - sizeof(*ssfw_head));
 	pr_debug("%s: crc=%x\n", __func__, crc);
diff --git a/sound/soc/codecs/sn95031.c b/sound/soc/codecs/sn95031.c
index cf8fa40662f..01af0517245 100644
--- a/sound/soc/codecs/sn95031.c
+++ b/sound/soc/codecs/sn95031.c
@@ -531,8 +531,8 @@ static const struct snd_soc_dapm_route sn95031_audio_map[] = {
 	/* speaker map */
 	{ "IHFOUTL", NULL, "Speaker Rail"},
 	{ "IHFOUTR", NULL, "Speaker Rail"},
-	{ "IHFOUTL", "NULL", "Speaker Left Playback"},
-	{ "IHFOUTR", "NULL", "Speaker Right Playback"},
+	{ "IHFOUTL", NULL, "Speaker Left Playback"},
+	{ "IHFOUTR", NULL, "Speaker Right Playback"},
 	{ "Speaker Left Playback", NULL, "Speaker Left Filter"},
 	{ "Speaker Right Playback", NULL, "Speaker Right Filter"},
 	{ "Speaker Left Filter", NULL, "IHFDAC Left"},
diff --git a/sound/soc/codecs/tas2552.c b/sound/soc/codecs/tas2552.c
index f039dc82597..6dbfc4703a3 100644
--- a/sound/soc/codecs/tas2552.c
+++ b/sound/soc/codecs/tas2552.c
@@ -120,6 +120,9 @@ static void tas2552_sw_shutdown(struct tas2552_data *tas_data, int sw_shutdown)
 {
 	u8 cfg1_reg;
 
+	if (!tas_data->codec)
+		return;
+
 	if (sw_shutdown)
 		cfg1_reg = 0;
 	else
@@ -335,7 +338,6 @@ static DECLARE_TLV_DB_SCALE(dac_tlv, -7, 100, 24);
 static const struct snd_kcontrol_new tas2552_snd_controls[] = {
 	SOC_SINGLE_TLV("Speaker Driver Playback Volume",
 			 TAS2552_PGA_GAIN, 0, 0x1f, 1, dac_tlv),
-	SOC_DAPM_SINGLE("Playback AMP", SND_SOC_NOPM, 0, 1, 0),
 };
 
 static const struct reg_default tas2552_init_regs[] = {
diff --git a/sound/soc/codecs/tas5086.c b/sound/soc/codecs/tas5086.c
index 249ef5c4c76..32942bed34b 100644
--- a/sound/soc/codecs/tas5086.c
+++ b/sound/soc/codecs/tas5086.c
@@ -281,7 +281,7 @@ static int tas5086_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct tas5086_private *priv = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = priv->deemph;
+	ucontrol->value.integer.value[0] = priv->deemph;
 
 	return 0;
 }
@@ -292,7 +292,7 @@ static int tas5086_put_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct tas5086_private *priv = snd_soc_codec_get_drvdata(codec);
 
-	priv->deemph = ucontrol->value.enumerated.item[0];
+	priv->deemph = ucontrol->value.integer.value[0];
 
 	return tas5086_set_deemph(codec);
 }
diff --git a/sound/soc/codecs/tlv320aic31xx.c b/sound/soc/codecs/tlv320aic31xx.c
index 145fe5b253d..93de5dd0a7b 100644
--- a/sound/soc/codecs/tlv320aic31xx.c
+++ b/sound/soc/codecs/tlv320aic31xx.c
@@ -911,12 +911,13 @@ static int aic31xx_set_dai_sysclk(struct snd_soc_dai *codec_dai,
 	}
 	aic31xx->p_div = i;
 
-	for (i = 0; aic31xx_divs[i].mclk_p != freq/aic31xx->p_div; i++) {
-		if (i == ARRAY_SIZE(aic31xx_divs)) {
-			dev_err(aic31xx->dev, "%s: Unsupported frequency %d\n",
-				__func__, freq);
-			return -EINVAL;
-		}
+	for (i = 0; i < ARRAY_SIZE(aic31xx_divs) &&
+		     aic31xx_divs[i].mclk_p != freq/aic31xx->p_div; i++)
+		;
+	if (i == ARRAY_SIZE(aic31xx_divs)) {
+		dev_err(aic31xx->dev, "%s: Unsupported frequency %d\n",
+			__func__, freq);
+		return -EINVAL;
 	}
 
 	/* set clock on MCLK, BCLK, or GPIO1 as PLL input */
diff --git a/sound/soc/codecs/wm2000.c b/sound/soc/codecs/wm2000.c
index 34ef65c52a7..8eeab47a423 100644
--- a/sound/soc/codecs/wm2000.c
+++ b/sound/soc/codecs/wm2000.c
@@ -610,7 +610,7 @@ static int wm2000_anc_mode_get(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev);
 
-	ucontrol->value.enumerated.item[0] = wm2000->anc_active;
+	ucontrol->value.integer.value[0] = wm2000->anc_active;
 
 	return 0;
 }
@@ -620,7 +620,7 @@ static int wm2000_anc_mode_put(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev);
-	int anc_active = ucontrol->value.enumerated.item[0];
+	int anc_active = ucontrol->value.integer.value[0];
 	int ret;
 
 	if (anc_active > 1)
@@ -643,7 +643,7 @@ static int wm2000_speaker_get(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev);
 
-	ucontrol->value.enumerated.item[0] = wm2000->spk_ena;
+	ucontrol->value.integer.value[0] = wm2000->spk_ena;
 
 	return 0;
 }
@@ -653,7 +653,7 @@ static int wm2000_speaker_put(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev);
-	int val = ucontrol->value.enumerated.item[0];
+	int val = ucontrol->value.integer.value[0];
 	int ret;
 
 	if (val > 1)
diff --git a/sound/soc/codecs/wm5102.c b/sound/soc/codecs/wm5102.c
index f6023496252..8fafff5fad4 100644
--- a/sound/soc/codecs/wm5102.c
+++ b/sound/soc/codecs/wm5102.c
@@ -41,7 +41,7 @@ struct wm5102_priv {
 static DECLARE_TLV_DB_SCALE(ana_tlv, 0, 100, 0);
 static DECLARE_TLV_DB_SCALE(eq_tlv, -1200, 100, 0);
 static DECLARE_TLV_DB_SCALE(digital_tlv, -6400, 50, 0);
-static DECLARE_TLV_DB_SCALE(noise_tlv, 0, 600, 0);
+static DECLARE_TLV_DB_SCALE(noise_tlv, -13200, 600, 0);
 static DECLARE_TLV_DB_SCALE(ng_tlv, -10200, 600, 0);
 
 static const struct wm_adsp_region wm5102_dsp1_regions[] = {
diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c
index 2f2ec26d831..4cab08b43a5 100644
--- a/sound/soc/codecs/wm5110.c
+++ b/sound/soc/codecs/wm5110.c
@@ -167,7 +167,7 @@ static int wm5110_sysclk_ev(struct snd_soc_dapm_widget *w,
 static DECLARE_TLV_DB_SCALE(ana_tlv, 0, 100, 0);
 static DECLARE_TLV_DB_SCALE(eq_tlv, -1200, 100, 0);
 static DECLARE_TLV_DB_SCALE(digital_tlv, -6400, 50, 0);
-static DECLARE_TLV_DB_SCALE(noise_tlv, 0, 600, 0);
+static DECLARE_TLV_DB_SCALE(noise_tlv, -13200, 600, 0);
 static DECLARE_TLV_DB_SCALE(ng_tlv, -10200, 600, 0);
 
 #define WM5110_NG_SRC(name, base) \
diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c
index eebb3280bfa..19a53dca343 100644
--- a/sound/soc/codecs/wm8731.c
+++ b/sound/soc/codecs/wm8731.c
@@ -122,7 +122,7 @@ static int wm8731_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8731_priv *wm8731 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = wm8731->deemph;
+	ucontrol->value.integer.value[0] = wm8731->deemph;
 
 	return 0;
 }
@@ -132,7 +132,7 @@ static int wm8731_put_deemph(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8731_priv *wm8731 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 	int ret = 0;
 
 	if (deemph > 1)
diff --git a/sound/soc/codecs/wm8737.c b/sound/soc/codecs/wm8737.c
index 744a422ecb0..4be874c9dc9 100644
--- a/sound/soc/codecs/wm8737.c
+++ b/sound/soc/codecs/wm8737.c
@@ -494,7 +494,8 @@ static int wm8737_set_bias_level(struct snd_soc_codec *codec,
 
 			/* Fast VMID ramp at 2*2.5k */
 			snd_soc_update_bits(codec, WM8737_MISC_BIAS_CONTROL,
-					    WM8737_VMIDSEL_MASK, 0x4);
+					    WM8737_VMIDSEL_MASK,
+					    2 << WM8737_VMIDSEL_SHIFT);
 
 			/* Bring VMID up */
 			snd_soc_update_bits(codec, WM8737_POWER_MANAGEMENT,
@@ -508,7 +509,8 @@ static int wm8737_set_bias_level(struct snd_soc_codec *codec,
 
 		/* VMID at 2*300k */
 		snd_soc_update_bits(codec, WM8737_MISC_BIAS_CONTROL,
-				    WM8737_VMIDSEL_MASK, 2);
+				    WM8737_VMIDSEL_MASK,
+				    1 << WM8737_VMIDSEL_SHIFT);
 
 		break;
 
diff --git a/sound/soc/codecs/wm8741.c b/sound/soc/codecs/wm8741.c
index 31bb4801a00..9e71c768966 100644
--- a/sound/soc/codecs/wm8741.c
+++ b/sound/soc/codecs/wm8741.c
@@ -123,7 +123,7 @@ static struct {
 };
 
 static const unsigned int rates_11289[] = {
-	44100, 88235,
+	44100, 88200,
 };
 
 static const struct snd_pcm_hw_constraint_list constraints_11289 = {
@@ -150,7 +150,7 @@ static const struct snd_pcm_hw_constraint_list constraints_16384 = {
 };
 
 static const unsigned int rates_16934[] = {
-	44100, 88235,
+	44100, 88200,
 };
 
 static const struct snd_pcm_hw_constraint_list constraints_16934 = {
@@ -168,7 +168,7 @@ static const struct snd_pcm_hw_constraint_list constraints_18432 = {
 };
 
 static const unsigned int rates_22579[] = {
-	44100, 88235, 1764000
+	44100, 88200, 176400
 };
 
 static const struct snd_pcm_hw_constraint_list constraints_22579 = {
@@ -186,7 +186,7 @@ static const struct snd_pcm_hw_constraint_list constraints_24576 = {
 };
 
 static const unsigned int rates_36864[] = {
-	48000, 96000, 19200
+	48000, 96000, 192000
 };
 
 static const struct snd_pcm_hw_constraint_list constraints_36864 = {
diff --git a/sound/soc/codecs/wm8903.c b/sound/soc/codecs/wm8903.c
index c038b3e0439..5b758756dd8 100644
--- a/sound/soc/codecs/wm8903.c
+++ b/sound/soc/codecs/wm8903.c
@@ -441,7 +441,7 @@ static int wm8903_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8903_priv *wm8903 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = wm8903->deemph;
+	ucontrol->value.integer.value[0] = wm8903->deemph;
 
 	return 0;
 }
@@ -451,7 +451,7 @@ static int wm8903_put_deemph(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8903_priv *wm8903 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 	int ret = 0;
 
 	if (deemph > 1)
diff --git a/sound/soc/codecs/wm8903.h b/sound/soc/codecs/wm8903.h
index db949311c0f..0bb4a647755 100644
--- a/sound/soc/codecs/wm8903.h
+++ b/sound/soc/codecs/wm8903.h
@@ -172,7 +172,7 @@ extern int wm8903_mic_detect(struct snd_soc_codec *codec,
 #define WM8903_VMID_BUF_ENA_WIDTH                    1  /* VMID_BUF_ENA */
 
 #define WM8903_VMID_RES_50K                          2
-#define WM8903_VMID_RES_250K                         3
+#define WM8903_VMID_RES_250K                         4
 #define WM8903_VMID_RES_5K                           6
 
 /*
diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c
index 4d2d2b1380d..af2446f16cd 100644
--- a/sound/soc/codecs/wm8904.c
+++ b/sound/soc/codecs/wm8904.c
@@ -525,7 +525,7 @@ static int wm8904_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = wm8904->deemph;
+	ucontrol->value.integer.value[0] = wm8904->deemph;
 	return 0;
 }
 
@@ -534,7 +534,7 @@ static int wm8904_put_deemph(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 
 	if (deemph > 1)
 		return -EINVAL;
diff --git a/sound/soc/codecs/wm8955.c b/sound/soc/codecs/wm8955.c
index 09d91d9dc4e..d48ac712f62 100644
--- a/sound/soc/codecs/wm8955.c
+++ b/sound/soc/codecs/wm8955.c
@@ -298,7 +298,7 @@ static int wm8955_configure_clocking(struct snd_soc_codec *codec)
 		snd_soc_update_bits(codec, WM8955_PLL_CONTROL_2,
 				    WM8955_K_17_9_MASK,
 				    (pll.k >> 9) & WM8955_K_17_9_MASK);
-		snd_soc_update_bits(codec, WM8955_PLL_CONTROL_2,
+		snd_soc_update_bits(codec, WM8955_PLL_CONTROL_3,
 				    WM8955_K_8_0_MASK,
 				    pll.k & WM8955_K_8_0_MASK);
 		if (pll.k)
@@ -393,7 +393,7 @@ static int wm8955_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8955_priv *wm8955 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = wm8955->deemph;
+	ucontrol->value.integer.value[0] = wm8955->deemph;
 	return 0;
 }
 
@@ -402,7 +402,7 @@ static int wm8955_put_deemph(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8955_priv *wm8955 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 
 	if (deemph > 1)
 		return -EINVAL;
diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c
index 4dc4e85116c..ab7fa7c9fa8 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -181,7 +181,7 @@ static int wm8960_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8960_priv *wm8960 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = wm8960->deemph;
+	ucontrol->value.integer.value[0] = wm8960->deemph;
 	return 0;
 }
 
@@ -190,7 +190,7 @@ static int wm8960_put_deemph(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8960_priv *wm8960 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 
 	if (deemph > 1)
 		return -EINVAL;
@@ -242,7 +242,7 @@ SOC_SINGLE("PCM Playback -6dB Switch", WM8960_DACCTL1, 7, 1, 0),
 SOC_ENUM("ADC Polarity", wm8960_enum[0]),
 SOC_SINGLE("ADC High Pass Filter Switch", WM8960_DACCTL1, 0, 1, 0),
 
-SOC_ENUM("DAC Polarity", wm8960_enum[2]),
+SOC_ENUM("DAC Polarity", wm8960_enum[1]),
 SOC_SINGLE_BOOL_EXT("DAC Deemphasis Switch", 0,
 		    wm8960_get_deemph, wm8960_put_deemph),
 
@@ -392,7 +392,7 @@ static const struct snd_soc_dapm_route audio_paths[] = {
 	{ "Right Input Mixer", "Boost Switch", "Right Boost Mixer", },
 	{ "Right Input Mixer", NULL, "RINPUT1", },  /* Really Boost Switch */
 	{ "Right Input Mixer", NULL, "RINPUT2" },
-	{ "Right Input Mixer", NULL, "LINPUT3" },
+	{ "Right Input Mixer", NULL, "RINPUT3" },
 
 	{ "Left ADC", NULL, "Left Input Mixer" },
 	{ "Right ADC", NULL, "Right Input Mixer" },
@@ -555,7 +555,7 @@ static struct {
 	{ 22050, 2 },
 	{ 24000, 2 },
 	{ 16000, 3 },
-	{ 11250, 4 },
+	{ 11025, 4 },
 	{ 12000, 4 },
 	{  8000, 5 },
 };
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index 1fcb9f3f309..e5f14c87863 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -2753,7 +2753,7 @@ static struct {
 };
 
 static int fs_ratios[] = {
-	64, 128, 192, 256, 348, 512, 768, 1024, 1408, 1536
+	64, 128, 192, 256, 384, 512, 768, 1024, 1408, 1536
 };
 
 static int bclk_divs[] = {
diff --git a/sound/soc/codecs/wm8997.c b/sound/soc/codecs/wm8997.c
index ab33fe59651..dd1842527b3 100644
--- a/sound/soc/codecs/wm8997.c
+++ b/sound/soc/codecs/wm8997.c
@@ -40,7 +40,7 @@ struct wm8997_priv {
 static DECLARE_TLV_DB_SCALE(ana_tlv, 0, 100, 0);
 static DECLARE_TLV_DB_SCALE(eq_tlv, -1200, 100, 0);
 static DECLARE_TLV_DB_SCALE(digital_tlv, -6400, 50, 0);
-static DECLARE_TLV_DB_SCALE(noise_tlv, 0, 600, 0);
+static DECLARE_TLV_DB_SCALE(noise_tlv, -13200, 600, 0);
 static DECLARE_TLV_DB_SCALE(ng_tlv, -10200, 600, 0);
 
 static const struct reg_default wm8997_sysclk_reva_patch[] = {
diff --git a/sound/soc/davinci/Kconfig b/sound/soc/davinci/Kconfig
index 8e948c63f3d..2b81ca418d2 100644
--- a/sound/soc/davinci/Kconfig
+++ b/sound/soc/davinci/Kconfig
@@ -58,13 +58,12 @@ choice
 	depends on MACH_DAVINCI_DM365_EVM
 
 config SND_DM365_AIC3X_CODEC
-	bool "Audio Codec - AIC3101"
+	tristate "Audio Codec - AIC3101"
 	help
 	  Say Y if you want to add support for AIC3101 audio codec
 
 config SND_DM365_VOICE_CODEC
 	tristate "Voice Codec - CQ93VC"
-	depends on SND_DAVINCI_SOC
 	select MFD_DAVINCI_VOICECODEC
 	select SND_DAVINCI_SOC_VCIF
 	select SND_SOC_CQ0093VC
diff --git a/sound/soc/davinci/davinci-evm.c b/sound/soc/davinci/davinci-evm.c
index a50010e2891..82837e5e96a 100644
--- a/sound/soc/davinci/davinci-evm.c
+++ b/sound/soc/davinci/davinci-evm.c
@@ -431,18 +431,8 @@ static int davinci_evm_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int davinci_evm_remove(struct platform_device *pdev)
-{
-	struct snd_soc_card *card = platform_get_drvdata(pdev);
-
-	snd_soc_unregister_card(card);
-
-	return 0;
-}
-
 static struct platform_driver davinci_evm_driver = {
 	.probe		= davinci_evm_probe,
-	.remove		= davinci_evm_remove,
 	.driver		= {
 		.name	= "davinci_evm",
 		.owner	= THIS_MODULE,
diff --git a/sound/soc/dwc/designware_i2s.c b/sound/soc/dwc/designware_i2s.c
index e961388e6e9..10e1b8ca42e 100644
--- a/sound/soc/dwc/designware_i2s.c
+++ b/sound/soc/dwc/designware_i2s.c
@@ -263,6 +263,19 @@ static void dw_i2s_shutdown(struct snd_pcm_substream *substream,
 	snd_soc_dai_set_dma_data(dai, substream, NULL);
 }
 
+static int dw_i2s_prepare(struct snd_pcm_substream *substream,
+			  struct snd_soc_dai *dai)
+{
+	struct dw_i2s_dev *dev = snd_soc_dai_get_drvdata(dai);
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		i2s_write_reg(dev->i2s_base, TXFFR, 1);
+	else
+		i2s_write_reg(dev->i2s_base, RXFFR, 1);
+
+	return 0;
+}
+
 static int dw_i2s_trigger(struct snd_pcm_substream *substream,
 		int cmd, struct snd_soc_dai *dai)
 {
@@ -294,6 +307,7 @@ static struct snd_soc_dai_ops dw_i2s_dai_ops = {
 	.startup	= dw_i2s_startup,
 	.shutdown	= dw_i2s_shutdown,
 	.hw_params	= dw_i2s_hw_params,
+	.prepare	= dw_i2s_prepare,
 	.trigger	= dw_i2s_trigger,
 };
 
diff --git a/sound/soc/fsl/eukrea-tlv320.c b/sound/soc/fsl/eukrea-tlv320.c
index eb093d5b85c..54790461f39 100644
--- a/sound/soc/fsl/eukrea-tlv320.c
+++ b/sound/soc/fsl/eukrea-tlv320.c
@@ -105,7 +105,7 @@ static int eukrea_tlv320_probe(struct platform_device *pdev)
 	int ret;
 	int int_port = 0, ext_port;
 	struct device_node *np = pdev->dev.of_node;
-	struct device_node *ssi_np, *codec_np;
+	struct device_node *ssi_np = NULL, *codec_np = NULL;
 
 	eukrea_tlv320.dev = &pdev->dev;
 	if (np) {
diff --git a/sound/soc/fsl/fsl_esai.h b/sound/soc/fsl/fsl_esai.h
index 91a550f4a10..5e793bbb6b0 100644
--- a/sound/soc/fsl/fsl_esai.h
+++ b/sound/soc/fsl/fsl_esai.h
@@ -302,7 +302,7 @@
 #define ESAI_xCCR_xFP_MASK	(((1 << ESAI_xCCR_xFP_WIDTH) - 1) << ESAI_xCCR_xFP_SHIFT)
 #define ESAI_xCCR_xFP(v)	((((v) - 1) << ESAI_xCCR_xFP_SHIFT) & ESAI_xCCR_xFP_MASK)
 #define ESAI_xCCR_xDC_SHIFT     9
-#define ESAI_xCCR_xDC_WIDTH	4
+#define ESAI_xCCR_xDC_WIDTH	5
 #define ESAI_xCCR_xDC_MASK	(((1 << ESAI_xCCR_xDC_WIDTH) - 1) << ESAI_xCCR_xDC_SHIFT)
 #define ESAI_xCCR_xDC(v)	((((v) - 1) << ESAI_xCCR_xDC_SHIFT) & ESAI_xCCR_xDC_MASK)
 #define ESAI_xCCR_xPSR_SHIFT	8
diff --git a/sound/soc/fsl/imx-wm8962.c b/sound/soc/fsl/imx-wm8962.c
index 3a3d17ce6ba..66445259949 100644
--- a/sound/soc/fsl/imx-wm8962.c
+++ b/sound/soc/fsl/imx-wm8962.c
@@ -190,7 +190,7 @@ static int imx_wm8962_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "audmux internal port setup failed\n");
 		return ret;
 	}
-	imx_audmux_v2_configure_port(ext_port,
+	ret = imx_audmux_v2_configure_port(ext_port,
 			IMX_AUDMUX_V2_PTCR_SYN,
 			IMX_AUDMUX_V2_PDCR_RXDSEL(int_port));
 	if (ret) {
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index d1b7293c133..c6a6693bbfc 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -453,9 +453,8 @@ static int asoc_simple_card_parse_of(struct device_node *node,
 }
 
 /* Decrease the reference count of the device nodes */
-static int asoc_simple_card_unref(struct platform_device *pdev)
+static int asoc_simple_card_unref(struct snd_soc_card *card)
 {
-	struct snd_soc_card *card = platform_get_drvdata(pdev);
 	struct snd_soc_dai_link *dai_link;
 	struct device_node *np;
 	int num_links;
@@ -562,7 +561,7 @@ static int asoc_simple_card_probe(struct platform_device *pdev)
 		return ret;
 
 err:
-	asoc_simple_card_unref(pdev);
+	asoc_simple_card_unref(&priv->snd_card);
 	return ret;
 }
 
@@ -578,7 +577,7 @@ static int asoc_simple_card_remove(struct platform_device *pdev)
 		snd_soc_jack_free_gpios(&simple_card_mic_jack, 1,
 					&simple_card_mic_jack_gpio);
 
-	return asoc_simple_card_unref(pdev);
+	return asoc_simple_card_unref(card);
 }
 
 static const struct of_device_id asoc_simple_of_match[] = {
diff --git a/sound/soc/omap/omap-mcbsp.c b/sound/soc/omap/omap-mcbsp.c
index bd3ef2a88be..aafc0686ab2 100644
--- a/sound/soc/omap/omap-mcbsp.c
+++ b/sound/soc/omap/omap-mcbsp.c
@@ -434,7 +434,7 @@ static int omap_mcbsp_dai_set_dai_fmt(struct snd_soc_dai *cpu_dai,
 	case SND_SOC_DAIFMT_CBM_CFS:
 		/* McBSP slave. FS clock as output */
 		regs->srgr2	|= FSGM;
-		regs->pcr0	|= FSXM;
+		regs->pcr0	|= FSXM | FSRM;
 		break;
 	case SND_SOC_DAIFMT_CBM_CFM:
 		/* McBSP slave */
diff --git a/sound/soc/omap/omap-pcm.c b/sound/soc/omap/omap-pcm.c
index f4b05bc23e4..1343ecbf0bd 100644
--- a/sound/soc/omap/omap-pcm.c
+++ b/sound/soc/omap/omap-pcm.c
@@ -201,7 +201,7 @@ static int omap_pcm_new(struct snd_soc_pcm_runtime *rtd)
 	struct snd_pcm *pcm = rtd->pcm;
 	int ret;
 
-	ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(64));
+	ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32));
 	if (ret)
 		return ret;
 
diff --git a/sound/soc/pxa/mioa701_wm9713.c b/sound/soc/pxa/mioa701_wm9713.c
index 595eee341e9..a08a877fc10 100644
--- a/sound/soc/pxa/mioa701_wm9713.c
+++ b/sound/soc/pxa/mioa701_wm9713.c
@@ -81,7 +81,7 @@ static int rear_amp_power(struct snd_soc_codec *codec, int power)
 static int rear_amp_event(struct snd_soc_dapm_widget *widget,
 			  struct snd_kcontrol *kctl, int event)
 {
-	struct snd_soc_codec *codec = widget->codec;
+	struct snd_soc_codec *codec = widget->dapm->card->rtd[0].codec;
 
 	return rear_amp_power(codec, SND_SOC_DAPM_EVENT_ON(event));
 }
diff --git a/sound/soc/samsung/s3c24xx-i2s.c b/sound/soc/samsung/s3c24xx-i2s.c
index e87d9a2053b..fb1d39324a6 100644
--- a/sound/soc/samsung/s3c24xx-i2s.c
+++ b/sound/soc/samsung/s3c24xx-i2s.c
@@ -461,8 +461,8 @@ static int s3c24xx_iis_dev_probe(struct platform_device *pdev)
 		return -ENOENT;
 	}
 	s3c24xx_i2s.regs = devm_ioremap_resource(&pdev->dev, res);
-	if (s3c24xx_i2s.regs == NULL)
-		return -ENXIO;
+	if (IS_ERR(s3c24xx_i2s.regs))
+		return PTR_ERR(s3c24xx_i2s.regs);
 
 	s3c24xx_i2s_pcm_stereo_out.dma_addr = res->start + S3C2410_IISFIFO;
 	s3c24xx_i2s_pcm_stereo_in.dma_addr = res->start + S3C2410_IISFIFO;
diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c
index cecfab3cc94..08e430d664c 100644
--- a/sound/soc/soc-compress.c
+++ b/sound/soc/soc-compress.c
@@ -666,7 +666,8 @@ int soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num)
 			rtd->dai_link->stream_name);
 
 		ret = snd_pcm_new_internal(rtd->card->snd_card, new_name, num,
-				1, 0, &be_pcm);
+				rtd->dai_link->dpcm_playback,
+				rtd->dai_link->dpcm_capture, &be_pcm);
 		if (ret < 0) {
 			dev_err(rtd->card->dev, "ASoC: can't create compressed for %s\n",
 				rtd->dai_link->name);
@@ -675,8 +676,10 @@ int soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num)
 
 		rtd->pcm = be_pcm;
 		rtd->fe_compr = 1;
-		be_pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream->private_data = rtd;
-		be_pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream->private_data = rtd;
+		if (rtd->dai_link->dpcm_playback)
+			be_pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream->private_data = rtd;
+		else if (rtd->dai_link->dpcm_capture)
+			be_pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream->private_data = rtd;
 		memcpy(compr->ops, &soc_compr_dyn_ops, sizeof(soc_compr_dyn_ops));
 	} else
 		memcpy(compr->ops, &soc_compr_ops, sizeof(soc_compr_ops));
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index c61cb9cedbc..943e6a9a631 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -3076,11 +3076,16 @@ snd_soc_dapm_new_control(struct snd_soc_dapm_context *dapm,
 	}
 
 	prefix = soc_dapm_prefix(dapm);
-	if (prefix)
+	if (prefix) {
 		w->name = kasprintf(GFP_KERNEL, "%s %s", prefix, widget->name);
-	else
+		if (widget->sname)
+			w->sname = kasprintf(GFP_KERNEL, "%s %s", prefix,
+					     widget->sname);
+	} else {
 		w->name = kasprintf(GFP_KERNEL, "%s", widget->name);
-
+		if (widget->sname)
+			w->sname = kasprintf(GFP_KERNEL, "%s", widget->sname);
+	}
 	if (w->name == NULL) {
 		kfree(w);
 		return NULL;
diff --git a/sound/synth/emux/emux_oss.c b/sound/synth/emux/emux_oss.c
index 319754cf620..daf61abc367 100644
--- a/sound/synth/emux/emux_oss.c
+++ b/sound/synth/emux/emux_oss.c
@@ -118,12 +118,8 @@ snd_emux_open_seq_oss(struct snd_seq_oss_arg *arg, void *closure)
 	if (snd_BUG_ON(!arg || !emu))
 		return -ENXIO;
 
-	mutex_lock(&emu->register_mutex);
-
-	if (!snd_emux_inc_count(emu)) {
-		mutex_unlock(&emu->register_mutex);
+	if (!snd_emux_inc_count(emu))
 		return -EFAULT;
-	}
 
 	memset(&callback, 0, sizeof(callback));
 	callback.owner = THIS_MODULE;
@@ -135,7 +131,6 @@ snd_emux_open_seq_oss(struct snd_seq_oss_arg *arg, void *closure)
 	if (p == NULL) {
 		snd_printk(KERN_ERR "can't create port\n");
 		snd_emux_dec_count(emu);
-		mutex_unlock(&emu->register_mutex);
 		return -ENOMEM;
 	}
 
@@ -148,8 +143,6 @@ snd_emux_open_seq_oss(struct snd_seq_oss_arg *arg, void *closure)
 	reset_port_mode(p, arg->seq_mode);
 
 	snd_emux_reset_port(p);
-
-	mutex_unlock(&emu->register_mutex);
 	return 0;
 }
 
@@ -195,13 +188,11 @@ snd_emux_close_seq_oss(struct snd_seq_oss_arg *arg)
 	if (snd_BUG_ON(!emu))
 		return -ENXIO;
 
-	mutex_lock(&emu->register_mutex);
 	snd_emux_sounds_off_all(p);
 	snd_soundfont_close_check(emu->sflist, SF_CLIENT_NO(p->chset.port));
 	snd_seq_event_port_detach(p->chset.client, p->chset.port);
 	snd_emux_dec_count(emu);
 
-	mutex_unlock(&emu->register_mutex);
 	return 0;
 }
 
diff --git a/sound/synth/emux/emux_seq.c b/sound/synth/emux/emux_seq.c
index 7778b8e1978..a0209204ae4 100644
--- a/sound/synth/emux/emux_seq.c
+++ b/sound/synth/emux/emux_seq.c
@@ -124,12 +124,10 @@ snd_emux_detach_seq(struct snd_emux *emu)
 	if (emu->voices)
 		snd_emux_terminate_all(emu);
 		
-	mutex_lock(&emu->register_mutex);
 	if (emu->client >= 0) {
 		snd_seq_delete_kernel_client(emu->client);
 		emu->client = -1;
 	}
-	mutex_unlock(&emu->register_mutex);
 }
 
 
@@ -269,8 +267,8 @@ snd_emux_event_input(struct snd_seq_event *ev, int direct, void *private_data,
 /*
  * increment usage count
  */
-int
-snd_emux_inc_count(struct snd_emux *emu)
+static int
+__snd_emux_inc_count(struct snd_emux *emu)
 {
 	emu->used++;
 	if (!try_module_get(emu->ops.owner))
@@ -284,12 +282,21 @@ snd_emux_inc_count(struct snd_emux *emu)
 	return 1;
 }
 
+int snd_emux_inc_count(struct snd_emux *emu)
+{
+	int ret;
+
+	mutex_lock(&emu->register_mutex);
+	ret = __snd_emux_inc_count(emu);
+	mutex_unlock(&emu->register_mutex);
+	return ret;
+}
 
 /*
  * decrease usage count
  */
-void
-snd_emux_dec_count(struct snd_emux *emu)
+static void
+__snd_emux_dec_count(struct snd_emux *emu)
 {
 	module_put(emu->card->module);
 	emu->used--;
@@ -298,6 +305,12 @@ snd_emux_dec_count(struct snd_emux *emu)
 	module_put(emu->ops.owner);
 }
 
+void snd_emux_dec_count(struct snd_emux *emu)
+{
+	mutex_lock(&emu->register_mutex);
+	__snd_emux_dec_count(emu);
+	mutex_unlock(&emu->register_mutex);
+}
 
 /*
  * Routine that is called upon a first use of a particular port
@@ -317,7 +330,7 @@ snd_emux_use(void *private_data, struct snd_seq_port_subscribe *info)
 
 	mutex_lock(&emu->register_mutex);
 	snd_emux_init_port(p);
-	snd_emux_inc_count(emu);
+	__snd_emux_inc_count(emu);
 	mutex_unlock(&emu->register_mutex);
 	return 0;
 }
@@ -340,7 +353,7 @@ snd_emux_unuse(void *private_data, struct snd_seq_port_subscribe *info)
 
 	mutex_lock(&emu->register_mutex);
 	snd_emux_sounds_off_all(p);
-	snd_emux_dec_count(emu);
+	__snd_emux_dec_count(emu);
 	mutex_unlock(&emu->register_mutex);
 	return 0;
 }
diff --git a/sound/usb/caiaq/audio.c b/sound/usb/caiaq/audio.c
index 27284474613..327f8642ca8 100644
--- a/sound/usb/caiaq/audio.c
+++ b/sound/usb/caiaq/audio.c
@@ -816,7 +816,7 @@ int snd_usb_caiaq_audio_init(struct snd_usb_caiaqdev *cdev)
 		return -EINVAL;
 	}
 
-	if (cdev->n_streams < 2) {
+	if (cdev->n_streams < 1) {
 		dev_err(dev, "bogus number of streams: %d\n", cdev->n_streams);
 		return -EINVAL;
 	}
diff --git a/sound/usb/clock.c b/sound/usb/clock.c
index 03fed6611d9..2ed260b10f6 100644
--- a/sound/usb/clock.c
+++ b/sound/usb/clock.c
@@ -303,6 +303,11 @@ static int set_sample_rate_v1(struct snd_usb_audio *chip, int iface,
 		return err;
 	}
 
+	/* Don't check the sample rate for devices which we know don't
+	 * support reading */
+	if (snd_usb_get_sample_rate_quirk(chip))
+		return 0;
+
 	if ((err = snd_usb_ctl_msg(dev, usb_rcvctrlpipe(dev, 0), UAC_GET_CUR,
 				   USB_TYPE_CLASS | USB_RECIP_ENDPOINT | USB_DIR_IN,
 				   UAC_EP_CS_ATTR_SAMPLE_RATE << 8, ep,
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index d3d49525a16..5bfb695547f 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -365,6 +365,8 @@ static void snd_usbmidi_error_timer(unsigned long data)
 		if (in && in->error_resubmit) {
 			in->error_resubmit = 0;
 			for (j = 0; j < INPUT_URBS; ++j) {
+				if (atomic_read(&in->urbs[j]->use_count))
+					continue;
 				in->urbs[j]->dev = umidi->dev;
 				snd_usbmidi_submit_urb(in->urbs[j], GFP_ATOMIC);
 			}
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 6e354d32685..b4edae1d4f5 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -909,10 +909,12 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval,
 	case USB_ID(0x046d, 0x0807): /* Logitech Webcam C500 */
 	case USB_ID(0x046d, 0x0808):
 	case USB_ID(0x046d, 0x0809):
+	case USB_ID(0x046d, 0x0819): /* Logitech Webcam C210 */
 	case USB_ID(0x046d, 0x081b): /* HD Webcam c310 */
 	case USB_ID(0x046d, 0x081d): /* HD Webcam c510 */
 	case USB_ID(0x046d, 0x0825): /* HD Webcam c270 */
 	case USB_ID(0x046d, 0x0826): /* HD Webcam c525 */
+	case USB_ID(0x046d, 0x08ca): /* Logitech Quickcam Fusion */
 	case USB_ID(0x046d, 0x0991):
 	/* Most audio usb devices lie about volume resolution.
 	 * Most Logitech webcams have res = 384.
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index d1d72ff5034..b16be394421 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -328,8 +328,11 @@ static struct usbmix_name_map gamecom780_map[] = {
 	{}
 };
 
-static const struct usbmix_name_map kef_x300a_map[] = {
-	{ 10, NULL }, /* firmware locks up (?) when we try to access this FU */
+/* some (all?) SCMS USB3318 devices are affected by a firmware lock up
+ * when anything attempts to access FU 10 (control)
+ */
+static const struct usbmix_name_map scms_usb3318_map[] = {
+	{ 10, NULL },
 	{ 0 }
 };
 
@@ -425,8 +428,19 @@ static struct usbmix_ctl_map usbmix_ctl_maps[] = {
 		.map = ebox44_map,
 	},
 	{
+		/* MAYA44 USB+ */
+		.id = USB_ID(0x2573, 0x0008),
+		.map = maya44_map,
+	},
+	{
+		/* KEF X300A */
 		.id = USB_ID(0x27ac, 0x1000),
-		.map = kef_x300a_map,
+		.map = scms_usb3318_map,
+	},
+	{
+		/* Arcam rPAC */
+		.id = USB_ID(0x25c4, 0x0003),
+		.map = scms_usb3318_map,
 	},
 	{ 0 } /* terminator */
 };
diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index 8c9bf4b7aaf..524366f9d32 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -178,6 +178,7 @@ static const struct rc_config {
 	{ USB_ID(0x041e, 0x3040), 2, 2, 6, 6,  2,  0x6e91 }, /* Live! 24-bit */
 	{ USB_ID(0x041e, 0x3042), 0, 1, 1, 1,  1,  0x000d }, /* Usb X-Fi S51 */
 	{ USB_ID(0x041e, 0x30df), 0, 1, 1, 1,  1,  0x000d }, /* Usb X-Fi S51 Pro */
+	{ USB_ID(0x041e, 0x3237), 0, 1, 1, 1,  1,  0x000d }, /* Usb X-Fi S51 Pro */
 	{ USB_ID(0x041e, 0x3048), 2, 2, 6, 6,  2,  0x6e91 }, /* Toshiba SB0500 */
 };
 
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index c62a1659106..0d8aba5fe1a 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -482,6 +482,11 @@ static int set_format(struct snd_usb_substream *subs, struct audioformat *fmt)
 	/* set interface */
 	if (subs->interface != fmt->iface ||
 	    subs->altset_idx != fmt->altset_idx) {
+
+		err = snd_usb_select_mode_quirk(subs, fmt);
+		if (err < 0)
+			return -EIO;
+
 		err = usb_set_interface(dev, fmt->iface, fmt->altsetting);
 		if (err < 0) {
 			dev_err(&dev->dev,
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index c657752a420..fde5b6e3c8e 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -1773,6 +1773,36 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 		}
 	}
 },
+{
+	USB_DEVICE(0x0582, 0x0159),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		/* .vendor_name = "Roland", */
+		/* .product_name = "UA-22", */
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = (const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 1,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 2,
+				.type = QUIRK_MIDI_FIXED_ENDPOINT,
+				.data = & (const struct snd_usb_midi_endpoint_info) {
+					.out_cables = 0x0001,
+					.in_cables = 0x0001
+				}
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
 /* this catches most recent vendor-specific Roland devices */
 {
 	.match_flags = USB_DEVICE_ID_MATCH_VENDOR |
@@ -2804,133 +2834,45 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 	}
 },
 
-/* Hauppauge HVR-950Q and HVR-850 */
-{
-	USB_DEVICE_VENDOR_SPEC(0x2040, 0x7200),
-	.match_flags = USB_DEVICE_ID_MATCH_DEVICE |
-		       USB_DEVICE_ID_MATCH_INT_CLASS |
-		       USB_DEVICE_ID_MATCH_INT_SUBCLASS,
-	.bInterfaceClass = USB_CLASS_AUDIO,
-	.bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL,
-	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
-		.vendor_name = "Hauppauge",
-		.product_name = "HVR-950Q",
-		.ifnum = QUIRK_ANY_INTERFACE,
-		.type = QUIRK_AUDIO_ALIGN_TRANSFER,
-	}
-},
-{
-	USB_DEVICE_VENDOR_SPEC(0x2040, 0x7210),
-	.match_flags = USB_DEVICE_ID_MATCH_DEVICE |
-		       USB_DEVICE_ID_MATCH_INT_CLASS |
-		       USB_DEVICE_ID_MATCH_INT_SUBCLASS,
-	.bInterfaceClass = USB_CLASS_AUDIO,
-	.bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL,
-	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
-		.vendor_name = "Hauppauge",
-		.product_name = "HVR-950Q",
-		.ifnum = QUIRK_ANY_INTERFACE,
-		.type = QUIRK_AUDIO_ALIGN_TRANSFER,
-	}
-},
-{
-	USB_DEVICE_VENDOR_SPEC(0x2040, 0x7217),
-	.match_flags = USB_DEVICE_ID_MATCH_DEVICE |
-		       USB_DEVICE_ID_MATCH_INT_CLASS |
-		       USB_DEVICE_ID_MATCH_INT_SUBCLASS,
-	.bInterfaceClass = USB_CLASS_AUDIO,
-	.bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL,
-	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
-		.vendor_name = "Hauppauge",
-		.product_name = "HVR-950Q",
-		.ifnum = QUIRK_ANY_INTERFACE,
-		.type = QUIRK_AUDIO_ALIGN_TRANSFER,
-	}
-},
-{
-	USB_DEVICE_VENDOR_SPEC(0x2040, 0x721b),
-	.match_flags = USB_DEVICE_ID_MATCH_DEVICE |
-		       USB_DEVICE_ID_MATCH_INT_CLASS |
-		       USB_DEVICE_ID_MATCH_INT_SUBCLASS,
-	.bInterfaceClass = USB_CLASS_AUDIO,
-	.bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL,
-	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
-		.vendor_name = "Hauppauge",
-		.product_name = "HVR-950Q",
-		.ifnum = QUIRK_ANY_INTERFACE,
-		.type = QUIRK_AUDIO_ALIGN_TRANSFER,
-	}
-},
-{
-	USB_DEVICE_VENDOR_SPEC(0x2040, 0x721e),
-	.match_flags = USB_DEVICE_ID_MATCH_DEVICE |
-		       USB_DEVICE_ID_MATCH_INT_CLASS |
-		       USB_DEVICE_ID_MATCH_INT_SUBCLASS,
-	.bInterfaceClass = USB_CLASS_AUDIO,
-	.bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL,
-	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
-		.vendor_name = "Hauppauge",
-		.product_name = "HVR-950Q",
-		.ifnum = QUIRK_ANY_INTERFACE,
-		.type = QUIRK_AUDIO_ALIGN_TRANSFER,
-	}
-},
-{
-	USB_DEVICE_VENDOR_SPEC(0x2040, 0x721f),
-	.match_flags = USB_DEVICE_ID_MATCH_DEVICE |
-		       USB_DEVICE_ID_MATCH_INT_CLASS |
-		       USB_DEVICE_ID_MATCH_INT_SUBCLASS,
-	.bInterfaceClass = USB_CLASS_AUDIO,
-	.bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL,
-	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
-		.vendor_name = "Hauppauge",
-		.product_name = "HVR-950Q",
-		.ifnum = QUIRK_ANY_INTERFACE,
-		.type = QUIRK_AUDIO_ALIGN_TRANSFER,
-	}
-},
-{
-	USB_DEVICE_VENDOR_SPEC(0x2040, 0x7240),
-	.match_flags = USB_DEVICE_ID_MATCH_DEVICE |
-		       USB_DEVICE_ID_MATCH_INT_CLASS |
-		       USB_DEVICE_ID_MATCH_INT_SUBCLASS,
-	.bInterfaceClass = USB_CLASS_AUDIO,
-	.bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL,
-	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
-		.vendor_name = "Hauppauge",
-		.product_name = "HVR-850",
-		.ifnum = QUIRK_ANY_INTERFACE,
-		.type = QUIRK_AUDIO_ALIGN_TRANSFER,
-	}
-},
-{
-	USB_DEVICE_VENDOR_SPEC(0x2040, 0x7280),
-	.match_flags = USB_DEVICE_ID_MATCH_DEVICE |
-		       USB_DEVICE_ID_MATCH_INT_CLASS |
-		       USB_DEVICE_ID_MATCH_INT_SUBCLASS,
-	.bInterfaceClass = USB_CLASS_AUDIO,
-	.bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL,
-	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
-		.vendor_name = "Hauppauge",
-		.product_name = "HVR-950Q",
-		.ifnum = QUIRK_ANY_INTERFACE,
-		.type = QUIRK_AUDIO_ALIGN_TRANSFER,
-	}
-},
-{
-	USB_DEVICE_VENDOR_SPEC(0x0fd9, 0x0008),
-	.match_flags = USB_DEVICE_ID_MATCH_DEVICE |
-		       USB_DEVICE_ID_MATCH_INT_CLASS |
-		       USB_DEVICE_ID_MATCH_INT_SUBCLASS,
-	.bInterfaceClass = USB_CLASS_AUDIO,
-	.bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL,
-	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
-		.vendor_name = "Hauppauge",
-		.product_name = "HVR-950Q",
-		.ifnum = QUIRK_ANY_INTERFACE,
-		.type = QUIRK_AUDIO_ALIGN_TRANSFER,
-	}
-},
+/*
+ * Auvitek au0828 devices with audio interface.
+ * This should be kept in sync with drivers/media/usb/au0828/au0828-cards.c
+ * Please notice that some drivers are DVB only, and don't need to be
+ * here. That's the case, for example, of DVICO_FUSIONHDTV7.
+ */
+
+#define AU0828_DEVICE(vid, pid, vname, pname) { \
+	USB_DEVICE_VENDOR_SPEC(vid, pid), \
+	.match_flags = USB_DEVICE_ID_MATCH_DEVICE | \
+		       USB_DEVICE_ID_MATCH_INT_CLASS | \
+		       USB_DEVICE_ID_MATCH_INT_SUBCLASS, \
+	.bInterfaceClass = USB_CLASS_AUDIO, \
+	.bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, \
+	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { \
+		.vendor_name = vname, \
+		.product_name = pname, \
+		.ifnum = QUIRK_ANY_INTERFACE, \
+		.type = QUIRK_AUDIO_ALIGN_TRANSFER, \
+	} \
+}
+
+AU0828_DEVICE(0x2040, 0x7200, "Hauppauge", "HVR-950Q"),
+AU0828_DEVICE(0x2040, 0x7240, "Hauppauge", "HVR-850"),
+AU0828_DEVICE(0x2040, 0x7210, "Hauppauge", "HVR-950Q"),
+AU0828_DEVICE(0x2040, 0x7217, "Hauppauge", "HVR-950Q"),
+AU0828_DEVICE(0x2040, 0x721b, "Hauppauge", "HVR-950Q"),
+AU0828_DEVICE(0x2040, 0x721e, "Hauppauge", "HVR-950Q"),
+AU0828_DEVICE(0x2040, 0x721f, "Hauppauge", "HVR-950Q"),
+AU0828_DEVICE(0x2040, 0x7280, "Hauppauge", "HVR-950Q"),
+AU0828_DEVICE(0x0fd9, 0x0008, "Hauppauge", "HVR-950Q"),
+AU0828_DEVICE(0x2040, 0x7201, "Hauppauge", "HVR-950Q-MXL"),
+AU0828_DEVICE(0x2040, 0x7211, "Hauppauge", "HVR-950Q-MXL"),
+AU0828_DEVICE(0x2040, 0x7281, "Hauppauge", "HVR-950Q-MXL"),
+AU0828_DEVICE(0x05e1, 0x0480, "Hauppauge", "Woodbury"),
+AU0828_DEVICE(0x2040, 0x8200, "Hauppauge", "Woodbury"),
+AU0828_DEVICE(0x2040, 0x7260, "Hauppauge", "HVR-950Q"),
+AU0828_DEVICE(0x2040, 0x7213, "Hauppauge", "HVR-950Q"),
+AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
 
 /* Digidesign Mbox */
 {
@@ -3203,6 +3145,46 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 
 {
 	/*
+	 * ZOOM R16/24 in audio interface mode.
+	 * Mixer descriptors are garbage, further quirks will be needed
+	 * to make any of it functional, thus disabled for now.
+	 * Playback stream appears to start and run fine but no sound
+	 * is produced, so also disabled for now.
+	 */
+	USB_DEVICE(0x1686, 0x00dd),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = (const struct snd_usb_audio_quirk[]) {
+			{
+				/* Mixer */
+				.ifnum = 0,
+				.type = QUIRK_IGNORE_INTERFACE,
+			},
+			{
+				/* Playback  */
+				.ifnum = 1,
+				.type = QUIRK_IGNORE_INTERFACE,
+			},
+			{
+				/* Capture */
+				.ifnum = 2,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE,
+			},
+			{
+				/* Midi */
+				.ifnum = 3,
+				.type = QUIRK_MIDI_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = -1
+			},
+		}
+	}
+},
+
+{
+	/*
 	 * Some USB MIDI devices don't have an audio control interface,
 	 * so we have to grab MIDI streaming interfaces here.
 	 */
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 60dfe0d2877..9ff5050d513 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1102,6 +1102,65 @@ void snd_usb_set_format_quirk(struct snd_usb_substream *subs,
 	}
 }
 
+bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip)
+{
+	/* devices which do not support reading the sample rate. */
+	switch (chip->usb_id) {
+	case USB_ID(0x045E, 0x075D): /* MS Lifecam Cinema  */
+	case USB_ID(0x045E, 0x076D): /* MS Lifecam HD-5000 */
+	case USB_ID(0x045E, 0x0772): /* MS Lifecam Studio */
+	case USB_ID(0x045E, 0x0779): /* MS Lifecam HD-3000 */
+	case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */
+		return true;
+	}
+	return false;
+}
+
+/* Marantz/Denon USB DACs need a vendor cmd to switch
+ * between PCM and native DSD mode
+ */
+static bool is_marantz_denon_dac(unsigned int id)
+{
+	switch (id) {
+	case USB_ID(0x154e, 0x1003): /* Denon DA-300USB */
+	case USB_ID(0x154e, 0x3005): /* Marantz HD-DAC1 */
+	case USB_ID(0x154e, 0x3006): /* Marantz SA-14S1 */
+		return true;
+	}
+	return false;
+}
+
+int snd_usb_select_mode_quirk(struct snd_usb_substream *subs,
+			      struct audioformat *fmt)
+{
+	struct usb_device *dev = subs->dev;
+	int err;
+
+	if (is_marantz_denon_dac(subs->stream->chip->usb_id)) {
+		/* First switch to alt set 0, otherwise the mode switch cmd
+		 * will not be accepted by the DAC
+		 */
+		err = usb_set_interface(dev, fmt->iface, 0);
+		if (err < 0)
+			return err;
+
+		mdelay(20); /* Delay needed after setting the interface */
+
+		switch (fmt->altsetting) {
+		case 2: /* DSD mode requested */
+		case 1: /* PCM mode requested */
+			err = snd_usb_ctl_msg(dev, usb_sndctrlpipe(dev, 0), 0,
+					      USB_DIR_OUT|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
+					      fmt->altsetting - 1, 1, NULL, 0);
+			if (err < 0)
+				return err;
+			break;
+		}
+		mdelay(20);
+	}
+	return 0;
+}
+
 void snd_usb_endpoint_start_quirk(struct snd_usb_endpoint *ep)
 {
 	/*
@@ -1150,16 +1209,18 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe,
 	/* Marantz/Denon devices with USB DAC functionality need a delay
 	 * after each class compliant request
 	 */
-	if ((le16_to_cpu(dev->descriptor.idVendor) == 0x154e) &&
-	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) {
+	if (is_marantz_denon_dac(USB_ID(le16_to_cpu(dev->descriptor.idVendor),
+					le16_to_cpu(dev->descriptor.idProduct)))
+	    && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
+		mdelay(20);
 
-		switch (le16_to_cpu(dev->descriptor.idProduct)) {
-		case 0x3005: /* Marantz HD-DAC1 */
-		case 0x3006: /* Marantz SA-14S1 */
-			mdelay(20);
-			break;
-		}
-	}
+	/* Zoom R16/24 needs a tiny delay here, otherwise requests like
+	 * get/set frequency return as failed despite actually succeeding.
+	 */
+	if ((le16_to_cpu(dev->descriptor.idVendor) == 0x1686) &&
+	    (le16_to_cpu(dev->descriptor.idProduct) == 0x00dd) &&
+	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
+		mdelay(1);
 }
 
 /*
@@ -1190,13 +1251,15 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip,
 
 	/* XMOS based USB DACs */
 	switch (chip->usb_id) {
-	/* iFi Audio micro/nano iDSD */
-	case USB_ID(0x20b1, 0x3008):
+	case USB_ID(0x20b1, 0x3008): /* iFi Audio micro/nano iDSD */
+	case USB_ID(0x20b1, 0x2008): /* Matrix Audio X-Sabre */
+	case USB_ID(0x20b1, 0x300a): /* Matrix Audio Mini-i Pro */
 		if (fp->altsetting == 2)
 			return SNDRV_PCM_FMTBIT_DSD_U32_BE;
 		break;
-	/* DIYINHK DSD DXD 384kHz USB to I2S/DSD */
-	case USB_ID(0x20b1, 0x2009):
+
+	case USB_ID(0x20b1, 0x2009): /* DIYINHK DSD DXD 384kHz USB to I2S/DSD */
+	case USB_ID(0x20b1, 0x2023): /* JLsounds I2SoverUSB */
 		if (fp->altsetting == 3)
 			return SNDRV_PCM_FMTBIT_DSD_U32_BE;
 		break;
@@ -1204,5 +1267,11 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip,
 		break;
 	}
 
+	/* Denon/Marantz devices with USB DAC functionality */
+	if (is_marantz_denon_dac(chip->usb_id)) {
+		if (fp->altsetting == 2)
+			return SNDRV_PCM_FMTBIT_DSD_U32_BE;
+	}
+
 	return 0;
 }
diff --git a/sound/usb/quirks.h b/sound/usb/quirks.h
index 665e972a1b4..2cd71ed1201 100644
--- a/sound/usb/quirks.h
+++ b/sound/usb/quirks.h
@@ -21,6 +21,8 @@ int snd_usb_apply_boot_quirk(struct usb_device *dev,
 void snd_usb_set_format_quirk(struct snd_usb_substream *subs,
 			      struct audioformat *fmt);
 
+bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip);
+
 int snd_usb_is_big_endian_format(struct snd_usb_audio *chip,
 				 struct audioformat *fp);
 
@@ -31,6 +33,9 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe,
 			   __u8 request, __u8 requesttype, __u16 value,
 			   __u16 index, void *data, __u16 size);
 
+int snd_usb_select_mode_quirk(struct snd_usb_substream *subs,
+			      struct audioformat *fmt);
+
 u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip,
 					struct audioformat *fp,
 					unsigned int sample_bytes);
diff --git a/tools/gator/daemon/Android.mk b/tools/gator/daemon/Android.mk
new file mode 100644
index 00000000000..99342115424
--- /dev/null
+++ b/tools/gator/daemon/Android.mk
@@ -0,0 +1,83 @@
+LOCAL_PATH := $(call my-dir)
+
+# Don't use this file if GATOR_DAEMON_PATH is set and we're not under that path
+ifneq ($(and $(GATOR_DAEMON_PATH),$(filter $(patsubst %/,%,$(GATOR_DAEMON_PATH))/%,$(LOCAL_PATH)/)),)
+
+include $(CLEAR_VARS)
+
+XML_H := $(shell cd $(LOCAL_PATH) && make events_xml.h defaults_xml.h SrcMd5.cpp)
+
+LOCAL_SRC_FILES := \
+	AnnotateListener.cpp \
+	AtraceDriver.cpp \
+	Buffer.cpp \
+	CCNDriver.cpp \
+	CapturedXML.cpp \
+	Child.cpp \
+	Command.cpp \
+	ConfigurationXML.cpp \
+	DiskIODriver.cpp \
+	Driver.cpp \
+	DriverSource.cpp \
+	DynBuf.cpp \
+	EventsXML.cpp \
+	ExternalDriver.cpp \
+	ExternalSource.cpp \
+	FSDriver.cpp \
+	Fifo.cpp \
+	FtraceDriver.cpp \
+	HwmonDriver.cpp \
+	KMod.cpp \
+	LocalCapture.cpp \
+	Logging.cpp \
+	main.cpp \
+	MaliVideoDriver.cpp \
+	MemInfoDriver.cpp\
+	Monitor.cpp \
+	NetDriver.cpp \
+	OlySocket.cpp \
+	OlyUtility.cpp \
+	PerfBuffer.cpp \
+	PerfDriver.cpp \
+	PerfGroup.cpp \
+	PerfSource.cpp \
+	Proc.cpp \
+	Sender.cpp \
+	SessionData.cpp \
+	SessionXML.cpp \
+	Setup.cpp \
+	Source.cpp \
+	SrcMd5.cpp \
+	StreamlineSetup.cpp \
+	UEvent.cpp \
+	UserSpaceSource.cpp \
+	libsensors/access.c \
+	libsensors/conf-lex.c \
+	libsensors/conf-parse.c \
+	libsensors/data.c \
+	libsensors/error.c \
+	libsensors/general.c \
+	libsensors/init.c \
+	libsensors/sysfs.c \
+	mxml/mxml-attr.c \
+	mxml/mxml-entity.c \
+	mxml/mxml-file.c \
+	mxml/mxml-get.c \
+	mxml/mxml-index.c \
+	mxml/mxml-node.c \
+	mxml/mxml-private.c \
+	mxml/mxml-search.c \
+	mxml/mxml-set.c \
+	mxml/mxml-string.c
+
+LOCAL_CFLAGS += -Wall -O3 -fno-exceptions -pthread -DETCDIR=\"/etc\" -Ilibsensors -fPIE
+LOCAL_LDFLAGS += -fPIE -pie
+
+LOCAL_C_INCLUDES := $(LOCAL_PATH)
+
+LOCAL_MODULE := gatord
+LOCAL_MODULE_TAGS := optional
+
+include $(BUILD_EXECUTABLE)
+
+endif
diff --git a/tools/gator/daemon/AnnotateListener.cpp b/tools/gator/daemon/AnnotateListener.cpp
new file mode 100644
index 00000000000..5966cbea8d1
--- /dev/null
+++ b/tools/gator/daemon/AnnotateListener.cpp
@@ -0,0 +1,89 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "AnnotateListener.h"
+
+#include <unistd.h>
+
+#include "OlySocket.h"
+
+static const char STREAMLINE_ANNOTATE_PARENT[] = "\0streamline-annotate-parent";
+
+struct AnnotateClient {
+	AnnotateClient *next;
+	int fd;
+};
+
+AnnotateListener::AnnotateListener() : mClients(NULL), mSock(NULL), mUds(NULL) {
+}
+
+AnnotateListener::~AnnotateListener() {
+	close();
+	delete mUds;
+	delete mSock;
+}
+
+void AnnotateListener::setup() {
+	mSock = new OlyServerSocket(8082);
+	mUds = new OlyServerSocket(STREAMLINE_ANNOTATE_PARENT, sizeof(STREAMLINE_ANNOTATE_PARENT), true);
+}
+
+int AnnotateListener::getSockFd() {
+	return mSock->getFd();
+}
+
+void AnnotateListener::handleSock() {
+	AnnotateClient *const client = new AnnotateClient();
+	client->fd = mSock->acceptConnection();
+	client->next = mClients;
+	mClients = client;
+}
+
+int AnnotateListener::getUdsFd() {
+	return mUds->getFd();
+}
+
+void AnnotateListener::handleUds() {
+	AnnotateClient *const client = new AnnotateClient();
+	client->fd = mUds->acceptConnection();
+	client->next = mClients;
+	mClients = client;
+}
+
+void AnnotateListener::close() {
+	if (mUds != NULL) {
+		mUds->closeServerSocket();
+	}
+	if (mSock != NULL) {
+		mSock->closeServerSocket();
+	}
+	while (mClients != NULL) {
+		::close(mClients->fd);
+		AnnotateClient *next = mClients->next;
+		delete mClients;
+		mClients = next;
+	}
+}
+
+void AnnotateListener::signal() {
+	const char ch = 0;
+	AnnotateClient **ptr = &mClients;
+	AnnotateClient *client = mClients;
+	while (client != NULL) {
+		if (write(client->fd, &ch, sizeof(ch)) != 1) {
+			::close(client->fd);
+			AnnotateClient *next = client->next;
+			delete client;
+			*ptr = next;
+			client = next;
+			continue;
+		}
+		ptr = &client->next;
+		client = client->next;
+	}
+}
diff --git a/tools/gator/daemon/AnnotateListener.h b/tools/gator/daemon/AnnotateListener.h
new file mode 100644
index 00000000000..6bc747d42d1
--- /dev/null
+++ b/tools/gator/daemon/AnnotateListener.h
@@ -0,0 +1,39 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef ANNOTATELISTENER_H
+#define ANNOTATELISTENER_H
+
+struct AnnotateClient;
+class OlyServerSocket;
+
+class AnnotateListener {
+public:
+	AnnotateListener();
+	~AnnotateListener();
+
+	void setup();
+	int getSockFd();
+	int getUdsFd();
+
+	void handleSock();
+	void handleUds();
+	void close();
+	void signal();
+
+private:
+	AnnotateClient *mClients;
+	OlyServerSocket *mSock;
+	OlyServerSocket *mUds;
+
+	// Intentionally unimplemented
+	AnnotateListener(const AnnotateListener &);
+	AnnotateListener &operator=(const AnnotateListener &);
+};
+
+#endif // ANNOTATELISTENER_H
diff --git a/tools/gator/daemon/Application.mk b/tools/gator/daemon/Application.mk
new file mode 100644
index 00000000000..8b0a7882e93
--- /dev/null
+++ b/tools/gator/daemon/Application.mk
@@ -0,0 +1,3 @@
+APP_PLATFORM := android-9
+# Replace armeabi-v7a with arm64-v8a to build an arm64 gatord or with armeabi to build an ARM11 gatord
+APP_ABI := armeabi-v7a
diff --git a/tools/gator/daemon/AtraceDriver.cpp b/tools/gator/daemon/AtraceDriver.cpp
new file mode 100644
index 00000000000..78fe58a5c46
--- /dev/null
+++ b/tools/gator/daemon/AtraceDriver.cpp
@@ -0,0 +1,136 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "AtraceDriver.h"
+
+#include <unistd.h>
+
+/*
+#include <regex.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+
+#include "DriverSource.h"
+#include "Setup.h"
+*/
+
+#include "Logging.h"
+#include "OlyUtility.h"
+#include "SessionData.h"
+
+class AtraceCounter : public DriverCounter {
+public:
+	AtraceCounter(DriverCounter *next, char *name, int flag);
+	~AtraceCounter();
+
+	int getFlag() const { return mFlag; }
+
+private:
+	const int mFlag;
+
+	// Intentionally unimplemented
+	AtraceCounter(const AtraceCounter &);
+	AtraceCounter &operator=(const AtraceCounter &);
+};
+
+AtraceCounter::AtraceCounter(DriverCounter *next, char *name, int flag) : DriverCounter(next, name), mFlag(flag) {
+}
+
+AtraceCounter::~AtraceCounter() {
+}
+
+AtraceDriver::AtraceDriver() : mSupported(false), mNotifyPath() {
+}
+
+AtraceDriver::~AtraceDriver() {
+}
+
+void AtraceDriver::readEvents(mxml_node_t *const xml) {
+	if (!gSessionData->mFtraceDriver.isSupported()) {
+		logg->logMessage("Atrace support disabled, ftrace support is required");
+		return;
+	}
+	if (access("/system/bin/setprop", X_OK) != 0) {
+		logg->logMessage("Atrace support disabled, setprop is not found, this is not an Android target");
+		return;
+	}
+
+	if (util->getApplicationFullPath(mNotifyPath, sizeof(mNotifyPath)) != 0) {
+		logg->logMessage("Unable to determine the full path of gatord, the cwd will be used");
+	}
+	strncat(mNotifyPath, "notify.dex", sizeof(mNotifyPath) - strlen(mNotifyPath) - 1);
+	if (access(mNotifyPath, W_OK) != 0) {
+		logg->logMessage("Atrace support disabled, unable to locate notify.dex");
+		return;
+	}
+
+	mSupported = true;
+
+	mxml_node_t *node = xml;
+	while (true) {
+		node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND);
+		if (node == NULL) {
+			break;
+		}
+		const char *counter = mxmlElementGetAttr(node, "counter");
+		if (counter == NULL) {
+			continue;
+		}
+
+		if (strncmp(counter, "atrace_", 7) != 0) {
+			continue;
+		}
+
+		const char *flag = mxmlElementGetAttr(node, "flag");
+		if (flag == NULL) {
+			logg->logError("The atrace counter %s is missing the required flag attribute", counter);
+			handleException();
+		}
+		setCounters(new AtraceCounter(getCounters(), strdup(counter), strtol(flag, NULL, 16)));
+	}
+}
+
+void AtraceDriver::setAtrace(const int flags) {
+	logg->logMessage("Setting atrace flags to %i\n", flags);
+	pid_t pid = fork();
+	if (pid < 0) {
+		logg->logError("fork failed");
+		handleException();
+	} else if (pid == 0) {
+		char buf[1<<10];
+		snprintf(buf, sizeof(buf), "setprop debug.atrace.tags.enableflags %i; "
+			 "dalvikvm -cp %s com.android.internal.util.WithFramework Notify", flags, mNotifyPath);
+		execlp("sh", "sh", "-c", buf, NULL);
+		exit(0);
+	}
+}
+
+void AtraceDriver::start() {
+	if (!mSupported) {
+		return;
+	}
+
+	int flags = 0;
+	for (AtraceCounter *counter = static_cast<AtraceCounter *>(getCounters()); counter != NULL; counter = static_cast<AtraceCounter *>(counter->getNext())) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		flags |= counter->getFlag();
+	}
+
+	setAtrace(flags);
+}
+
+void AtraceDriver::stop() {
+	if (!mSupported) {
+		return;
+	}
+
+	setAtrace(0);
+}
diff --git a/tools/gator/daemon/AtraceDriver.h b/tools/gator/daemon/AtraceDriver.h
new file mode 100644
index 00000000000..0a068580caf
--- /dev/null
+++ b/tools/gator/daemon/AtraceDriver.h
@@ -0,0 +1,39 @@
+/**
+ * Copyright (C) ARM Limited 2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef ATRACEDRIVER_H
+#define ATRACEDRIVER_H
+
+#include "mxml/mxml.h"
+
+#include "Driver.h"
+
+class AtraceDriver : public SimpleDriver {
+public:
+	AtraceDriver();
+	~AtraceDriver();
+
+	void readEvents(mxml_node_t *const xml);
+
+	void start();
+	void stop();
+
+	bool isSupported() const { return mSupported; }
+
+private:
+	void setAtrace(const int flags);
+
+	bool mSupported;
+	char mNotifyPath[256];
+
+	// Intentionally unimplemented
+	AtraceDriver(const AtraceDriver &);
+	AtraceDriver &operator=(const AtraceDriver &);
+};
+
+#endif // ATRACEDRIVER_H
diff --git a/tools/gator/daemon/Buffer.cpp b/tools/gator/daemon/Buffer.cpp
new file mode 100644
index 00000000000..26deb2e4372
--- /dev/null
+++ b/tools/gator/daemon/Buffer.cpp
@@ -0,0 +1,473 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Buffer.h"
+
+#include "Logging.h"
+#include "Sender.h"
+#include "SessionData.h"
+
+#define mask (mSize - 1)
+#define FRAME_HEADER_SIZE 3
+
+enum {
+	CODE_PEA         =  1,
+	CODE_KEYS        =  2,
+	CODE_FORMAT      =  3,
+	CODE_MAPS        =  4,
+	CODE_COMM        =  5,
+	CODE_KEYS_OLD    =  6,
+	CODE_ONLINE_CPU  =  7,
+	CODE_OFFLINE_CPU =  8,
+	CODE_KALLSYMS    =  9,
+	CODE_COUNTERS    = 10,
+};
+
+// Summary Frame Messages
+enum {
+	MESSAGE_SUMMARY = 1,
+	MESSAGE_CORE_NAME = 3,
+};
+
+// From gator_marshaling.c
+#define NEWLINE_CANARY \
+	/* Unix */ \
+	"1\n" \
+	/* Windows */ \
+	"2\r\n" \
+	/* Mac OS */ \
+	"3\r" \
+	/* RISC OS */ \
+	"4\n\r" \
+	/* Add another character so the length isn't 0x0a bytes */ \
+	"5"
+
+Buffer::Buffer(const int32_t core, const int32_t buftype, const int size, sem_t *const readerSem) : mBuf(new char[size]), mReaderSem(readerSem), mCommitTime(gSessionData->mLiveRate), mSize(size), mReadPos(0), mWritePos(0), mCommitPos(0), mAvailable(true), mIsDone(false), mCore(core), mBufType(buftype) {
+	if ((mSize & mask) != 0) {
+		logg->logError("Buffer size is not a power of 2");
+		handleException();
+	}
+	sem_init(&mWriterSem, 0, 0);
+	frame();
+}
+
+Buffer::~Buffer() {
+	delete [] mBuf;
+	sem_destroy(&mWriterSem);
+}
+
+void Buffer::write(Sender *const sender) {
+	if (!commitReady()) {
+		return;
+	}
+
+	// commit and read are updated by the writer, only read them once
+	int commitPos = mCommitPos;
+	int readPos = mReadPos;
+
+	// determine the size of two halves
+	int length1 = commitPos - readPos;
+	char *buffer1 = mBuf + readPos;
+	int length2 = 0;
+	char *buffer2 = mBuf;
+	if (length1 < 0) {
+		length1 = mSize - readPos;
+		length2 = commitPos;
+	}
+
+	logg->logMessage("Sending data length1: %i length2: %i", length1, length2);
+
+	// start, middle or end
+	if (length1 > 0) {
+		sender->writeData(buffer1, length1, RESPONSE_APC_DATA);
+	}
+
+	// possible wrap around
+	if (length2 > 0) {
+		sender->writeData(buffer2, length2, RESPONSE_APC_DATA);
+	}
+
+	mReadPos = commitPos;
+
+	// send a notification that space is available
+	sem_post(&mWriterSem);
+}
+
+bool Buffer::commitReady() const {
+	return mCommitPos != mReadPos;
+}
+
+int Buffer::bytesAvailable() const {
+	int filled = mWritePos - mReadPos;
+	if (filled < 0) {
+		filled += mSize;
+	}
+
+	int remaining = mSize - filled;
+
+	if (mAvailable) {
+		// Give some extra room; also allows space to insert the overflow error packet
+		remaining -= 200;
+	} else {
+		// Hysteresis, prevents multiple overflow messages
+		remaining -= 2000;
+	}
+
+	return remaining;
+}
+
+bool Buffer::checkSpace(const int bytes) {
+	const int remaining = bytesAvailable();
+
+	if (remaining < bytes) {
+		mAvailable = false;
+	} else {
+		mAvailable = true;
+	}
+
+	return mAvailable;
+}
+
+int Buffer::contiguousSpaceAvailable() const {
+	int remaining = bytesAvailable();
+	int contiguous = mSize - mWritePos;
+	if (remaining < contiguous) {
+		return remaining;
+	} else {
+		return contiguous;
+	}
+}
+
+bool Buffer::hasUncommittedMessages() const {
+	const int typeLength = gSessionData->mLocalCapture ? 0 : 1;
+	int length = mWritePos - mCommitPos;
+	if (length < 0) {
+		length += mSize;
+	}
+	length = length - typeLength - sizeof(int32_t);
+	return length > FRAME_HEADER_SIZE;
+}
+
+void Buffer::commit(const uint64_t time, const bool force) {
+	// post-populate the length, which does not include the response type length nor the length itself, i.e. only the length of the payload
+	const int typeLength = gSessionData->mLocalCapture ? 0 : 1;
+	int length = mWritePos - mCommitPos;
+	if (length < 0) {
+		length += mSize;
+	}
+	length = length - typeLength - sizeof(int32_t);
+	if (!force && !mIsDone && length <= FRAME_HEADER_SIZE) {
+		// Nothing to write, only the frame header is present
+		return;
+	}
+	for (size_t byte = 0; byte < sizeof(int32_t); byte++) {
+		mBuf[(mCommitPos + typeLength + byte) & mask] = (length >> byte * 8) & 0xFF;
+	}
+
+	logg->logMessage("Committing data mReadPos: %i mWritePos: %i mCommitPos: %i", mReadPos, mWritePos, mCommitPos);
+	mCommitPos = mWritePos;
+
+	if (gSessionData->mLiveRate > 0) {
+		while (time > mCommitTime) {
+			mCommitTime += gSessionData->mLiveRate;
+		}
+	}
+
+	if (!mIsDone) {
+		frame();
+	}
+
+	// send a notification that data is ready
+	sem_post(mReaderSem);
+}
+
+void Buffer::check(const uint64_t time) {
+	int filled = mWritePos - mCommitPos;
+	if (filled < 0) {
+		filled += mSize;
+	}
+	if (filled >= ((mSize * 3) / 4) || (gSessionData->mLiveRate > 0 && time >= mCommitTime)) {
+		commit(time);
+	}
+}
+
+void Buffer::packInt(char *const buf, const int size, int &writePos, int32_t x) {
+	int packedBytes = 0;
+	int more = true;
+	while (more) {
+		// low order 7 bits of x
+		char b = x & 0x7f;
+		x >>= 7;
+
+		if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0)) {
+			more = false;
+		} else {
+			b |= 0x80;
+		}
+
+		buf[(writePos + packedBytes) & /*mask*/(size - 1)] = b;
+		packedBytes++;
+	}
+
+	writePos = (writePos + packedBytes) & /*mask*/(size - 1);
+}
+
+void Buffer::packInt(int32_t x) {
+	packInt(mBuf, mSize, mWritePos, x);
+}
+
+void Buffer::packInt64(char *const buf, const int size, int &writePos, int64_t x) {
+	int packedBytes = 0;
+	int more = true;
+	while (more) {
+		// low order 7 bits of x
+		char b = x & 0x7f;
+		x >>= 7;
+
+		if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0)) {
+			more = false;
+		} else {
+			b |= 0x80;
+		}
+
+		buf[(writePos + packedBytes) & /*mask*/(size - 1)] = b;
+		packedBytes++;
+	}
+
+	writePos = (writePos + packedBytes) & /*mask*/(size - 1);
+}
+
+void Buffer::packInt64(int64_t x) {
+	packInt64(mBuf, mSize, mWritePos, x);
+}
+
+void Buffer::writeBytes(const void *const data, size_t count) {
+	size_t i;
+	for (i = 0; i < count; ++i) {
+		mBuf[(mWritePos + i) & mask] = static_cast<const char *>(data)[i];
+	}
+
+	mWritePos = (mWritePos + i) & mask;
+}
+
+void Buffer::writeString(const char *const str) {
+	const int len = strlen(str);
+	packInt(len);
+	writeBytes(str, len);
+}
+
+void Buffer::frame() {
+	if (!gSessionData->mLocalCapture) {
+		packInt(RESPONSE_APC_DATA);
+	}
+	// Reserve space for the length
+	mWritePos += sizeof(int32_t);
+	packInt(mBufType);
+	if ((mBufType == FRAME_BLOCK_COUNTER) || (mBufType == FRAME_PERF_ATTRS) || (mBufType == FRAME_PERF)) {
+		packInt(mCore);
+	}
+}
+
+void Buffer::summary(const uint64_t currTime, const int64_t timestamp, const int64_t uptime, const int64_t monotonicDelta, const char *const uname, const long pageSize) {
+	packInt(MESSAGE_SUMMARY);
+	writeString(NEWLINE_CANARY);
+	packInt64(timestamp);
+	packInt64(uptime);
+	packInt64(monotonicDelta);
+	writeString("uname");
+	writeString(uname);
+	writeString("PAGESIZE");
+	char buf[32];
+	snprintf(buf, sizeof(buf), "%li", pageSize);
+	writeString(buf);
+	writeString("");
+	check(currTime);
+}
+
+void Buffer::coreName(const uint64_t currTime, const int core, const int cpuid, const char *const name) {
+	if (checkSpace(3 * MAXSIZE_PACK32 + 0x100)) {
+		packInt(MESSAGE_CORE_NAME);
+		packInt(core);
+		packInt(cpuid);
+		writeString(name);
+	}
+	check(currTime);
+}
+
+bool Buffer::eventHeader(const uint64_t curr_time) {
+	bool retval = false;
+	if (checkSpace(MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+		// key of zero indicates a timestamp
+		packInt(0);
+		packInt64(curr_time);
+		retval = true;
+	}
+
+	return retval;
+}
+
+bool Buffer::eventTid(const int tid) {
+	bool retval = false;
+	if (checkSpace(2 * MAXSIZE_PACK32)) {
+		// key of 1 indicates a tid
+		packInt(1);
+		packInt(tid);
+		retval = true;
+	}
+
+	return retval;
+}
+
+void Buffer::event(const int key, const int32_t value) {
+	if (checkSpace(2 * MAXSIZE_PACK32)) {
+		packInt(key);
+		packInt(value);
+	}
+}
+
+void Buffer::event64(const int key, const int64_t value) {
+	if (checkSpace(MAXSIZE_PACK64 + MAXSIZE_PACK32)) {
+		packInt(key);
+		packInt64(value);
+	}
+}
+
+void Buffer::marshalPea(const uint64_t currTime, const struct perf_event_attr *const pea, int key) {
+	while (!checkSpace(2 * MAXSIZE_PACK32 + pea->size)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_PEA);
+	writeBytes(pea, pea->size);
+	packInt(key);
+	check(currTime);
+}
+
+void Buffer::marshalKeys(const uint64_t currTime, const int count, const __u64 *const ids, const int *const keys) {
+	while (!checkSpace(2 * MAXSIZE_PACK32 + count * (MAXSIZE_PACK32 + MAXSIZE_PACK64))) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_KEYS);
+	packInt(count);
+	for (int i = 0; i < count; ++i) {
+		packInt64(ids[i]);
+		packInt(keys[i]);
+	}
+	check(currTime);
+}
+
+void Buffer::marshalKeysOld(const uint64_t currTime, const int keyCount, const int *const keys, const int bytes, const char *const buf) {
+	while (!checkSpace((2 + keyCount) * MAXSIZE_PACK32 + bytes)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_KEYS_OLD);
+	packInt(keyCount);
+	for (int i = 0; i < keyCount; ++i) {
+		packInt(keys[i]);
+	}
+	writeBytes(buf, bytes);
+	check(currTime);
+}
+
+void Buffer::marshalFormat(const uint64_t currTime, const int length, const char *const format) {
+	while (!checkSpace(MAXSIZE_PACK32 + length + 1)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_FORMAT);
+	writeBytes(format, length + 1);
+	check(currTime);
+}
+
+void Buffer::marshalMaps(const uint64_t currTime, const int pid, const int tid, const char *const maps) {
+	const int mapsLen = strlen(maps) + 1;
+	while (!checkSpace(3 * MAXSIZE_PACK32 + mapsLen)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_MAPS);
+	packInt(pid);
+	packInt(tid);
+	writeBytes(maps, mapsLen);
+	check(currTime);
+}
+
+void Buffer::marshalComm(const uint64_t currTime, const int pid, const int tid, const char *const image, const char *const comm) {
+	const int imageLen = strlen(image) + 1;
+	const int commLen = strlen(comm) + 1;
+	while (!checkSpace(3 * MAXSIZE_PACK32 + imageLen + commLen)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_COMM);
+	packInt(pid);
+	packInt(tid);
+	writeBytes(image, imageLen);
+	writeBytes(comm, commLen);
+	check(currTime);
+}
+
+void Buffer::onlineCPU(const uint64_t currTime, const int cpu) {
+	while (!checkSpace(MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_ONLINE_CPU);
+	packInt64(currTime);
+	packInt(cpu);
+	check(currTime);
+}
+
+void Buffer::offlineCPU(const uint64_t currTime, const int cpu) {
+	while (!checkSpace(MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_OFFLINE_CPU);
+	packInt64(currTime);
+	packInt(cpu);
+	check(currTime);
+}
+
+void Buffer::marshalKallsyms(const uint64_t currTime, const char *const kallsyms) {
+	const int kallsymsLen = strlen(kallsyms) + 1;
+	while (!checkSpace(3 * MAXSIZE_PACK32 + kallsymsLen)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_KALLSYMS);
+	writeBytes(kallsyms, kallsymsLen);
+	check(currTime);
+}
+
+void Buffer::perfCounterHeader(const uint64_t time) {
+	while (!checkSpace(MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_COUNTERS);
+	packInt64(time);
+}
+
+void Buffer::perfCounter(const int core, const int key, const int64_t value) {
+	while (!checkSpace(2*MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(core);
+	packInt(key);
+	packInt64(value);
+}
+
+void Buffer::perfCounterFooter(const uint64_t currTime) {
+	while (!checkSpace(MAXSIZE_PACK32)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(-1);
+	check(currTime);
+}
+
+void Buffer::setDone() {
+	mIsDone = true;
+	commit(0);
+}
+
+bool Buffer::isDone() const {
+	return mIsDone && mReadPos == mCommitPos && mCommitPos == mWritePos;
+}
diff --git a/tools/gator/daemon/Buffer.h b/tools/gator/daemon/Buffer.h
new file mode 100644
index 00000000000..ea250a910e4
--- /dev/null
+++ b/tools/gator/daemon/Buffer.h
@@ -0,0 +1,110 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef BUFFER_H
+#define BUFFER_H
+
+#include <stdint.h>
+#include <semaphore.h>
+
+#include "k/perf_event.h"
+
+class Sender;
+
+enum {
+	FRAME_SUMMARY       =  1,
+	FRAME_BLOCK_COUNTER =  5,
+	FRAME_EXTERNAL      = 10,
+	FRAME_PERF_ATTRS    = 11,
+	FRAME_PERF          = 12,
+};
+
+class Buffer {
+public:
+	static const size_t MAXSIZE_PACK32 = 5;
+	static const size_t MAXSIZE_PACK64 = 10;
+
+	Buffer(int32_t core, int32_t buftype, const int size, sem_t *const readerSem);
+	~Buffer();
+
+	void write(Sender *sender);
+
+	int bytesAvailable() const;
+	int contiguousSpaceAvailable() const;
+	bool hasUncommittedMessages() const;
+	void commit(const uint64_t time, const bool force = false);
+	void check(const uint64_t time);
+
+	// Summary messages
+	void summary(const uint64_t currTime, const int64_t timestamp, const int64_t uptime, const int64_t monotonicDelta, const char *const uname, const long pageSize);
+	void coreName(const uint64_t currTime, const int core, const int cpuid, const char *const name);
+
+	// Block Counter messages
+	bool eventHeader(uint64_t curr_time);
+	bool eventTid(int tid);
+	void event(int key, int32_t value);
+	void event64(int key, int64_t value);
+
+	// Perf Attrs messages
+	void marshalPea(const uint64_t currTime, const struct perf_event_attr *const pea, int key);
+	void marshalKeys(const uint64_t currTime, const int count, const __u64 *const ids, const int *const keys);
+	void marshalKeysOld(const uint64_t currTime, const int keyCount, const int *const keys, const int bytes, const char *const buf);
+	void marshalFormat(const uint64_t currTime, const int length, const char *const format);
+	void marshalMaps(const uint64_t currTime, const int pid, const int tid, const char *const maps);
+	void marshalComm(const uint64_t currTime, const int pid, const int tid, const char *const image, const char *const comm);
+	void onlineCPU(const uint64_t currTime, const int cpu);
+	void offlineCPU(const uint64_t currTime, const int cpu);
+	void marshalKallsyms(const uint64_t currTime, const char *const kallsyms);
+	void perfCounterHeader(const uint64_t time);
+	void perfCounter(const int core, const int key, const int64_t value);
+	void perfCounterFooter(const uint64_t currTime);
+
+	void setDone();
+	bool isDone() const;
+
+	// Prefer a new member to using these functions if possible
+	char *getWritePos() { return mBuf + mWritePos; }
+	void advanceWrite(int bytes) { mWritePos = (mWritePos + bytes) & /*mask*/(mSize - 1); }
+	static void packInt(char *const buf, const int size, int &writePos, int32_t x);
+	void packInt(int32_t x);
+	static void packInt64(char *const buf, const int size, int &writePos, int64_t x);
+	void packInt64(int64_t x);
+	void writeBytes(const void *const data, size_t count);
+	void writeString(const char *const str);
+
+	static void writeLEInt(unsigned char *buf, int v) {
+		buf[0] = (v >> 0) & 0xFF;
+		buf[1] = (v >> 8) & 0xFF;
+		buf[2] = (v >> 16) & 0xFF;
+		buf[3] = (v >> 24) & 0xFF;
+	}
+
+private:
+	void frame();
+	bool commitReady() const;
+	bool checkSpace(int bytes);
+
+	char *const mBuf;
+	sem_t *const mReaderSem;
+	uint64_t mCommitTime;
+	sem_t mWriterSem;
+	const int mSize;
+	int mReadPos;
+	int mWritePos;
+	int mCommitPos;
+	bool mAvailable;
+	bool mIsDone;
+	const int32_t mCore;
+	const int32_t mBufType;
+
+	// Intentionally unimplemented
+	Buffer(const Buffer &);
+	Buffer &operator=(const Buffer &);
+};
+
+#endif // BUFFER_H
diff --git a/tools/gator/daemon/CCNDriver.cpp b/tools/gator/daemon/CCNDriver.cpp
new file mode 100644
index 00000000000..24eda03b809
--- /dev/null
+++ b/tools/gator/daemon/CCNDriver.cpp
@@ -0,0 +1,329 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "CCNDriver.h"
+
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include "k/perf_event.h"
+
+#include "Config.h"
+#include "DriverSource.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+static const char TAG_CATEGORY[] = "category";
+static const char TAG_COUNTER_SET[] = "counter_set";
+static const char TAG_EVENT[] = "event";
+static const char TAG_OPTION[] = "option";
+static const char TAG_OPTION_SET[] = "option_set";
+
+static const char ATTR_AVERAGE_SELECTION[] = "average_selection";
+static const char ATTR_COUNTER[] = "counter";
+static const char ATTR_COUNT[] = "count";
+static const char ATTR_DESCRIPTION[] = "description";
+static const char ATTR_DISPLAY[] = "display";
+static const char ATTR_EVENT[] = "event";
+static const char ATTR_EVENT_DELTA[] = "event_delta";
+static const char ATTR_NAME[] = "name";
+static const char ATTR_OPTION_SET[] = "option_set";
+static const char ATTR_TITLE[] = "title";
+static const char ATTR_UNITS[] = "units";
+
+static const char XP_REGION[] = "XP_Region";
+static const char HNF_REGION[] = "HN-F_Region";
+static const char RNI_REGION[] = "RN-I_Region";
+static const char SBAS_REGION[] = "SBAS_Region";
+static const char CCN_5XX[] = "CCN-5xx";
+#define ARM_CCN_5XX "ARM_CCN_5XX_"
+#define CCN_COUNT 8
+static const char ARM_CCN_5XX_CNT[] = ARM_CCN_5XX "cnt";
+
+static const char *const VC_TYPES[] = { "REQ", "RSP", "SNP", "DAT" };
+static const char *const XP_EVENT_NAMES[] = { NULL, "H-bit", "S-bit", "P-Cnt", "TknV" };
+static const char *const XP_EVENT_DESCRIPTIONS[] = { NULL, "Set H-bit, signaled when this XP sets the H-bit.", "Set S-bit, signaled when this XP sets the S-bit.", "Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC.", "No TknV, signaled when this XP transmits a valid packet." };
+static const char *const HNF_EVENT_NAMES[] = { NULL, "Cache Miss", "L3 SF Cache Access", "Cache Fill", "POCQ Retry", "POCQ Reqs Recvd", "SF Hit", "SF Evictions", "Snoops Sent", "Snoops Broadcast", "L3 Eviction", "L3 Fill Invalid Way", "MC Retries", "MC Reqs", "QOS HH Retry" };
+static const char *const HNF_EVENT_DESCRIPTIONS[] = { NULL, "Counts the total cache misses. This is the first time lookup result, and is high priority.", "Counts the number of cache accesses. This is the first time access, and is high priority.", "Counts the total allocations in the HN L3 cache, and all cache line allocations to the L3 cache.", "Counts the number of requests that have been retried.", "Counts the number of requests received by HN.", "Counts the number of snoop filter hits.", "Counts the number of snoop filter evictions. Cache invalidations are initiated.", "Counts the number of snoops sent. Does not differentiate between broadcast or directed snoops.", "Counts the number of snoop broadcasts sent.", "Counts the number of L3 evictions.", "Counts the number of L3 fills to an invalid way.", "Counts the number of transactions retried by the memory controller.", "Counts the number of requests to the memory controller.", "Counts the number of times a highest-priority QoS class was retried at the HN-F." };
+static const char *const RNI_EVENT_NAMES[] = { NULL, "S0 RDataBeats", "S1 RDataBeats", "S2 RDataBeats", "RXDAT Flits received", "TXDAT Flits sent", "Total TXREQ Flits sent", "Retried TXREQ Flits sent", "RRT full", "WRT full", "Replayed TXREQ Flits" };
+static const char *const RNI_EVENT_DESCRIPTIONS[] = { NULL, "S0 RDataBeats.", "S1 RDataBeats.", "S2 RDataBeats.", "RXDAT Flits received.", "TXDAT Flits sent.", "Total TXREQ Flits sent.", "Retried TXREQ Flits sent.", "RRT full.", "WRT full.", "Replayed TXREQ Flits." };
+static const char *const SBAS_EVENT_NAMES[] = { NULL, "S0 RDataBeats", NULL, NULL, "RXDAT Flits received", "TXDAT Flits sent", "Total TXREQ Flits sent", "Retried TXREQ Flits sent", "RRT full", "WRT full", "Replayed TXREQ Flits" };
+static const char *const SBAS_EVENT_DESCRIPTIONS[] = { NULL, "S0 RDataBeats.", NULL, NULL, "RXDAT Flits received.", "TXDAT Flits sent.", "Total TXREQ Flits sent.", "Retried TXREQ Flits sent.", "RRT full.", "WRT full.", "Replayed TXREQ Flits." };
+
+// This class is used only to poll for CCN-5xx configuration and emit events XML for it. All other operations are handled by PerfDriver
+
+static int sys_perf_event_open(struct perf_event_attr *const attr, const pid_t pid, const int cpu, const int group_fd, const unsigned long flags) {
+	return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
+}
+
+static unsigned int getConfig(unsigned int node, unsigned int type, unsigned int event, unsigned int port, unsigned int vc) {
+  return
+    ((node  & 0xff) <<  0) |
+    ((type  & 0xff) <<  8) |
+    ((event & 0xff) << 16) |
+    ((port  & 0x03) << 24) |
+    ((vc    & 0x07) << 26) |
+    0;
+}
+
+static bool perfPoll(struct perf_event_attr *const pea) {
+	int fd = sys_perf_event_open(pea, -1, 0, -1, 0);
+	if (fd < 0) {
+		return false;
+	}
+	close(fd);
+	return true;
+}
+
+CCNDriver::CCNDriver() : mNodeTypes(NULL), mXpCount(0) {
+}
+
+CCNDriver::~CCNDriver() {
+	delete mNodeTypes;
+}
+
+bool CCNDriver::claimCounter(const Counter &) const {
+	// Handled by PerfDriver
+	return false;
+}
+
+void CCNDriver::resetCounters() {
+	// Handled by PerfDriver
+}
+
+void CCNDriver::setupCounter(Counter &) {
+	// Handled by PerfDriver
+}
+
+void CCNDriver::readEvents(mxml_node_t *const) {
+	struct stat st;
+	if (stat("/sys/bus/event_source/devices/ccn", &st) != 0) {
+		// Not found
+		return;
+	}
+
+	int type;
+	if (DriverSource::readIntDriver("/sys/bus/event_source/devices/ccn/type", &type) != 0) {
+		logg->logError("Unable to read CCN-5xx type");
+		handleException();
+	}
+
+	// Detect number of xps
+	struct perf_event_attr pea;
+	memset(&pea, 0, sizeof(pea));
+	pea.type = type;
+	pea.size = sizeof(pea);
+
+	mXpCount = 1;
+	while (true) {
+		pea.config = getConfig(0, 0x08, 1, 0, 1) | mXpCount;
+		if (!perfPoll(&pea)) {
+			break;
+		}
+		mXpCount *= 2;
+	};
+	{
+		int lower = mXpCount/2 + 1;
+		while (lower < mXpCount) {
+			int mid = (lower + mXpCount)/2;
+			pea.config = getConfig(0, 0x08, 1, 0, 1) | mid;
+			if (perfPoll(&pea)) {
+				lower = mid + 1;
+			} else {
+				mXpCount = mid;
+			}
+		}
+	}
+
+	mNodeTypes = new NodeType[2*mXpCount];
+
+	// Detect node types
+	for (int i = 0; i < 2*mXpCount; ++i) {
+		pea.config = getConfig(0, 0x04, 1, 0, 0) | i;
+		if (perfPoll(&pea)) {
+			mNodeTypes[i] = NT_HNF;
+			continue;
+		}
+
+		pea.config = getConfig(0, 0x16, 1, 0, 0) | i;
+		if (perfPoll(&pea)) {
+			mNodeTypes[i] = NT_RNI;
+			continue;
+		}
+
+		pea.config = getConfig(0, 0x10, 1, 0, 0) | i;
+		if (perfPoll(&pea)) {
+			mNodeTypes[i] = NT_SBAS;
+			continue;
+		}
+
+		mNodeTypes[i] = NT_UNKNOWN;
+	}
+}
+
+int CCNDriver::writeCounters(mxml_node_t *const) const {
+	// Handled by PerfDriver
+	return 0;
+}
+
+void CCNDriver::writeEvents(mxml_node_t *const root) const {
+	mxml_node_t *const counter_set = mxmlNewElement(root, TAG_COUNTER_SET);
+	mxmlElementSetAttr(counter_set, ATTR_NAME, ARM_CCN_5XX_CNT);
+	mxmlElementSetAttr(counter_set, ATTR_COUNT, STRIFY(CCN_COUNT));
+
+	mxml_node_t *const category = mxmlNewElement(root, TAG_CATEGORY);
+	mxmlElementSetAttr(category, ATTR_NAME, CCN_5XX);
+	mxmlElementSetAttr(category, TAG_COUNTER_SET, ARM_CCN_5XX_CNT);
+
+	mxml_node_t *const clock_event = mxmlNewElement(category, TAG_EVENT);
+	mxmlElementSetAttr(clock_event, ATTR_COUNTER, ARM_CCN_5XX "ccnt");
+	mxmlElementSetAttr(clock_event, ATTR_EVENT, "0xff00");
+	mxmlElementSetAttr(clock_event, ATTR_TITLE, "CCN-5xx Clock");
+	mxmlElementSetAttr(clock_event, ATTR_NAME, "Cycles");
+	mxmlElementSetAttr(clock_event, ATTR_DISPLAY, "hertz");
+	mxmlElementSetAttr(clock_event, ATTR_UNITS, "Hz");
+	mxmlElementSetAttr(clock_event, ATTR_AVERAGE_SELECTION, "yes");
+	mxmlElementSetAttr(clock_event, ATTR_DESCRIPTION, "The number of core clock cycles");
+
+	mxml_node_t *const xp_option_set = mxmlNewElement(category, TAG_OPTION_SET);
+	mxmlElementSetAttr(xp_option_set, ATTR_NAME, XP_REGION);
+
+	for (int i = 0; i < mXpCount; ++i) {
+		mxml_node_t *const option = mxmlNewElement(xp_option_set, TAG_OPTION);
+		mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0));
+		mxmlElementSetAttrf(option, ATTR_NAME, "XP %i", i);
+		mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "Crosspoint %i", i);
+	}
+
+	for (int vc = 0; vc < ARRAY_LENGTH(VC_TYPES); ++vc) {
+		if (VC_TYPES[vc] == NULL) {
+			continue;
+		}
+		for (int bus = 0; bus < 2; ++bus) {
+			for (int eventId = 0; eventId < ARRAY_LENGTH(XP_EVENT_NAMES); ++eventId) {
+				if (XP_EVENT_NAMES[eventId] == NULL) {
+					continue;
+				}
+				mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT);
+				mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x08, eventId, bus, vc));
+				mxmlElementSetAttr(event, ATTR_OPTION_SET, XP_REGION);
+				mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX);
+				mxmlElementSetAttrf(event, ATTR_NAME, "Bus %i: %s: %s", bus, VC_TYPES[vc], XP_EVENT_NAMES[eventId]);
+				mxmlElementSetAttrf(event, ATTR_DESCRIPTION, "Bus %i: %s: %s", bus, VC_TYPES[vc], XP_EVENT_DESCRIPTIONS[eventId]);
+			}
+		}
+	}
+
+	mxml_node_t *const hnf_option_set = mxmlNewElement(category, TAG_OPTION_SET);
+	mxmlElementSetAttr(hnf_option_set, ATTR_NAME, HNF_REGION);
+
+	for (int eventId = 0; eventId < ARRAY_LENGTH(HNF_EVENT_NAMES); ++eventId) {
+		if (HNF_EVENT_NAMES[eventId] == NULL) {
+			continue;
+		}
+		mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT);
+		mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x04, eventId, 0, 0));
+		mxmlElementSetAttr(event, ATTR_OPTION_SET, HNF_REGION);
+		mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX);
+		mxmlElementSetAttr(event, ATTR_NAME, HNF_EVENT_NAMES[eventId]);
+		mxmlElementSetAttr(event, ATTR_DESCRIPTION, HNF_EVENT_DESCRIPTIONS[eventId]);
+	}
+
+	mxml_node_t *const rni_option_set = mxmlNewElement(category, TAG_OPTION_SET);
+	mxmlElementSetAttr(rni_option_set, ATTR_NAME, RNI_REGION);
+
+	for (int eventId = 0; eventId < ARRAY_LENGTH(RNI_EVENT_NAMES); ++eventId) {
+		if (RNI_EVENT_NAMES[eventId] == NULL) {
+			continue;
+		}
+		mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT);
+		mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x16, eventId, 0, 0));
+		mxmlElementSetAttr(event, ATTR_OPTION_SET, RNI_REGION);
+		mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX);
+		mxmlElementSetAttr(event, ATTR_NAME, RNI_EVENT_NAMES[eventId]);
+		mxmlElementSetAttr(event, ATTR_DESCRIPTION, RNI_EVENT_DESCRIPTIONS[eventId]);
+	}
+
+	mxml_node_t *const sbas_option_set = mxmlNewElement(category, TAG_OPTION_SET);
+	mxmlElementSetAttr(sbas_option_set, ATTR_NAME, SBAS_REGION);
+
+	for (int eventId = 0; eventId < ARRAY_LENGTH(SBAS_EVENT_NAMES); ++eventId) {
+		if (SBAS_EVENT_NAMES[eventId] == NULL) {
+			continue;
+		}
+		mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT);
+		mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x10, eventId, 0, 0));
+		mxmlElementSetAttr(event, ATTR_OPTION_SET, SBAS_REGION);
+		mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX);
+		mxmlElementSetAttr(event, ATTR_NAME, SBAS_EVENT_NAMES[eventId]);
+		mxmlElementSetAttr(event, ATTR_DESCRIPTION, SBAS_EVENT_DESCRIPTIONS[eventId]);
+	}
+
+	for (int i = 0; i < 2*mXpCount; ++i) {
+		switch (mNodeTypes[i]) {
+		case NT_HNF: {
+			mxml_node_t *const option = mxmlNewElement(hnf_option_set, TAG_OPTION);
+			mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0));
+			mxmlElementSetAttrf(option, ATTR_NAME, "HN-F %i", i);
+			mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "Fully-coherent Home Node %i", i);
+			break;
+		}
+		case NT_RNI: {
+			mxml_node_t *const option = mxmlNewElement(rni_option_set, TAG_OPTION);
+			mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0));
+			mxmlElementSetAttrf(option, ATTR_NAME, "RN-I %i", i);
+			mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "I/O-coherent Requesting Node %i", i);
+			break;
+		}
+		case NT_SBAS: {
+			mxml_node_t *const option = mxmlNewElement(sbas_option_set, TAG_OPTION);
+			mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0));
+			mxmlElementSetAttrf(option, ATTR_NAME, "SBAS %i", i);
+			mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "ACE master to CHI protocol bridge %i", i);
+			break;
+		}
+		default:
+			continue;
+		}
+	}
+}
+
+void CCNDriver::validateCounters() const {
+	int counts[CCN_COUNT][2] = { { 0 } };
+	const unsigned int mask = getConfig(0xff, 0xff, 0, 0, 0);
+
+	for (int i = 0; i < ARRAY_LENGTH(gSessionData->mCounters); ++i) {
+		const Counter *const counter = &gSessionData->mCounters[i];
+
+		if (!counter->isEnabled()) {
+			continue;
+		}
+
+		if (strncmp(counter->getType(), ARM_CCN_5XX_CNT, sizeof(ARM_CCN_5XX_CNT) - 1) == 0) {
+			const int node = counter->getEvent() & mask;
+
+			for (int j = 0; j < ARRAY_LENGTH(counts); ++j) {
+				if (counts[j][0] == 0) {
+					counts[j][0] = node;
+				}
+				if (counts[j][0] == node) {
+					++counts[j][1];
+					if (counts[j][1] > 4) {
+						if (asprintf(&gSessionData->mCountersError, "More than 4 events are assigned to the same CCN node") <= 0) {
+							logg->logError("asprintf failed");
+							handleException();
+						}
+					}
+				}
+			}
+		}
+	}
+}
diff --git a/tools/gator/daemon/CCNDriver.h b/tools/gator/daemon/CCNDriver.h
new file mode 100644
index 00000000000..8a155a7fc83
--- /dev/null
+++ b/tools/gator/daemon/CCNDriver.h
@@ -0,0 +1,45 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef CCNDRIVER_H
+#define CCNDRIVER_H
+
+#include "Driver.h"
+
+class CCNDriver : public Driver {
+public:
+	CCNDriver();
+	~CCNDriver();
+
+	bool claimCounter(const Counter &counter) const;
+	void resetCounters();
+	void setupCounter(Counter &counter);
+
+	void readEvents(mxml_node_t *const);
+	int writeCounters(mxml_node_t *const root) const;
+	void writeEvents(mxml_node_t *const) const;
+
+	void validateCounters() const;
+
+private:
+	enum NodeType {
+		NT_UNKNOWN,
+		NT_HNF,
+		NT_RNI,
+		NT_SBAS,
+	};
+
+	NodeType *mNodeTypes;
+	int mXpCount;
+
+	// Intentionally unimplemented
+	CCNDriver(const CCNDriver &);
+	CCNDriver &operator=(const CCNDriver &);
+};
+
+#endif // CCNDRIVER_H
diff --git a/tools/gator/daemon/COPYING b/tools/gator/daemon/COPYING
new file mode 100644
index 00000000000..d159169d105
--- /dev/null
+++ b/tools/gator/daemon/COPYING
@@ -0,0 +1,339 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users.  This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it.  (Some other Free Software Foundation software is covered by
+the GNU Lesser General Public License instead.)  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must show them these terms so they know their
+rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary.  To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                    GNU GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License.  The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language.  (Hereinafter, translation is included without limitation in
+the term "modification".)  Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+  1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+  2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) You must cause the modified files to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in
+    whole or in part contains or is derived from the Program or any
+    part thereof, to be licensed as a whole at no charge to all third
+    parties under the terms of this License.
+
+    c) If the modified program normally reads commands interactively
+    when run, you must cause it, when started running for such
+    interactive use in the most ordinary way, to print or display an
+    announcement including an appropriate copyright notice and a
+    notice that there is no warranty (or else, saying that you provide
+    a warranty) and that users may redistribute the program under
+    these conditions, and telling the user how to view a copy of this
+    License.  (Exception: if the Program itself is interactive but
+    does not normally print such an announcement, your work based on
+    the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+    a) Accompany it with the complete corresponding machine-readable
+    source code, which must be distributed under the terms of Sections
+    1 and 2 above on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three
+    years, to give any third party, for a charge no more than your
+    cost of physically performing source distribution, a complete
+    machine-readable copy of the corresponding source code, to be
+    distributed under the terms of Sections 1 and 2 above on a medium
+    customarily used for software interchange; or,
+
+    c) Accompany it with the information you received as to the offer
+    to distribute corresponding source code.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form with such
+    an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it.  For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable.  However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License.  Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+  5. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Program or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+  6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded.  In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+  9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+  10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this.  Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+                            NO WARRANTY
+
+  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License along
+    with this program; if not, write to the Free Software Foundation, Inc.,
+    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+    Gnomovision version 69, Copyright (C) year name of author
+    Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+  `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+  <signature of Ty Coon>, 1 April 1989
+  Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs.  If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.
diff --git a/tools/gator/daemon/CapturedXML.cpp b/tools/gator/daemon/CapturedXML.cpp
new file mode 100644
index 00000000000..e87c909afd5
--- /dev/null
+++ b/tools/gator/daemon/CapturedXML.cpp
@@ -0,0 +1,144 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "CapturedXML.h"
+
+#include <stdlib.h>
+#include <string.h>
+#include <dirent.h>
+
+#include "SessionData.h"
+#include "Logging.h"
+#include "OlyUtility.h"
+
+CapturedXML::CapturedXML() {
+}
+
+CapturedXML::~CapturedXML() {
+}
+
+mxml_node_t* CapturedXML::getTree(bool includeTime) {
+	mxml_node_t *xml;
+	mxml_node_t *captured;
+	mxml_node_t *target;
+	int x;
+
+	xml = mxmlNewXML("1.0");
+
+	captured = mxmlNewElement(xml, "captured");
+	mxmlElementSetAttr(captured, "version", "1");
+	if (gSessionData->mPerf.isSetup()) {
+		mxmlElementSetAttr(captured, "type", "Perf");
+	}
+	mxmlElementSetAttrf(captured, "protocol", "%d", PROTOCOL_VERSION);
+	if (includeTime) { // Send the following only after the capture is complete
+		if (time(NULL) > 1267000000) { // If the time is reasonable (after Feb 23, 2010)
+			mxmlElementSetAttrf(captured, "created", "%lu", time(NULL)); // Valid until the year 2038
+		}
+	}
+
+	target = mxmlNewElement(captured, "target");
+	mxmlElementSetAttr(target, "name", gSessionData->mCoreName);
+	mxmlElementSetAttrf(target, "sample_rate", "%d", gSessionData->mSampleRate);
+	mxmlElementSetAttrf(target, "cores", "%d", gSessionData->mCores);
+	mxmlElementSetAttrf(target, "cpuid", "0x%x", gSessionData->mMaxCpuId);
+
+	if (!gSessionData->mOneShot && (gSessionData->mSampleRate > 0)) {
+		mxmlElementSetAttr(target, "supports_live", "yes");
+	}
+
+	if (gSessionData->mLocalCapture) {
+		mxmlElementSetAttr(target, "local_capture", "yes");
+	}
+
+	mxml_node_t *counters = NULL;
+	for (x = 0; x < MAX_PERFORMANCE_COUNTERS; x++) {
+		const Counter & counter = gSessionData->mCounters[x];
+		if (counter.isEnabled()) {
+			if (counters == NULL) {
+				counters = mxmlNewElement(captured, "counters");
+			}
+			mxml_node_t *const node = mxmlNewElement(counters, "counter");
+			mxmlElementSetAttrf(node, "key", "0x%x", counter.getKey());
+			mxmlElementSetAttr(node, "type", counter.getType());
+			if (counter.getEvent() != -1) {
+				mxmlElementSetAttrf(node, "event", "0x%x", counter.getEvent());
+			}
+			if (counter.getCount() > 0) {
+				mxmlElementSetAttrf(node, "count", "%d", counter.getCount());
+			}
+			if (counter.getCores() > 0) {
+				mxmlElementSetAttrf(node, "cores", "%d", counter.getCores());
+			}
+		}
+	}
+
+	return xml;
+}
+
+char* CapturedXML::getXML(bool includeTime) {
+	char* xml_string;
+	mxml_node_t *xml = getTree(includeTime);
+	xml_string = mxmlSaveAllocString(xml, mxmlWhitespaceCB);
+	mxmlDelete(xml);
+	return xml_string;
+}
+
+void CapturedXML::write(char* path) {
+	char file[PATH_MAX];
+
+	// Set full path
+	snprintf(file, PATH_MAX, "%s/captured.xml", path);
+
+	char* xml = getXML(true);
+	if (util->writeToDisk(file, xml) < 0) {
+		logg->logError("Error writing %s\nPlease verify the path.", file);
+		handleException();
+	}
+
+	free(xml);
+}
+
+// whitespace callback utility function used with mini-xml
+const char * mxmlWhitespaceCB(mxml_node_t *node, int loc) {
+	const char *name;
+
+	name = mxmlGetElement(node);
+
+	if (loc == MXML_WS_BEFORE_OPEN) {
+		// Single indentation
+		if (!strcmp(name, "target") || !strcmp(name, "counters"))
+			return "\n  ";
+
+		// Double indentation
+		if (!strcmp(name, "counter"))
+			return "\n    ";
+
+		// Avoid a carriage return on the first line of the xml file
+		if (!strncmp(name, "?xml", 4))
+			return NULL;
+
+		// Default - no indentation
+		return "\n";
+	}
+
+	if (loc == MXML_WS_BEFORE_CLOSE) {
+		// No indentation
+		if (!strcmp(name, "captured"))
+			return "\n";
+
+		// Single indentation
+		if (!strcmp(name, "counters"))
+			return "\n  ";
+
+		// Default - no carriage return
+		return NULL;
+	}
+
+	return NULL;
+}
diff --git a/tools/gator/daemon/CapturedXML.h b/tools/gator/daemon/CapturedXML.h
new file mode 100644
index 00000000000..69d80c09b51
--- /dev/null
+++ b/tools/gator/daemon/CapturedXML.h
@@ -0,0 +1,26 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __CAPTURED_XML_H__
+#define __CAPTURED_XML_H__
+
+#include "mxml/mxml.h"
+
+class CapturedXML {
+public:
+	CapturedXML();
+	~CapturedXML();
+	char* getXML(bool includeTime); // the string should be freed by the caller
+	void write(char* path);
+private:
+	mxml_node_t* getTree(bool includeTime);
+};
+
+const char * mxmlWhitespaceCB(mxml_node_t *node, int where);
+
+#endif //__CAPTURED_XML_H__
diff --git a/tools/gator/daemon/Child.cpp b/tools/gator/daemon/Child.cpp
new file mode 100644
index 00000000000..551ec6bd25f
--- /dev/null
+++ b/tools/gator/daemon/Child.cpp
@@ -0,0 +1,373 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Child.h"
+
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+#include <sys/prctl.h>
+
+#include "CapturedXML.h"
+#include "Command.h"
+#include "ConfigurationXML.h"
+#include "Driver.h"
+#include "DriverSource.h"
+#include "ExternalSource.h"
+#include "LocalCapture.h"
+#include "Logging.h"
+#include "OlySocket.h"
+#include "OlyUtility.h"
+#include "PerfSource.h"
+#include "Sender.h"
+#include "SessionData.h"
+#include "StreamlineSetup.h"
+#include "UserSpaceSource.h"
+
+static sem_t haltPipeline, senderThreadStarted, startProfile, senderSem; // Shared by Child and spawned threads
+static Source *primarySource = NULL;
+static Source *externalSource = NULL;
+static Source *userSpaceSource = NULL;
+static Sender* sender = NULL;        // Shared by Child.cpp and spawned threads
+Child* child = NULL;                 // shared by Child.cpp and main.cpp
+
+extern void cleanUp();
+void handleException() {
+	if (child && child->numExceptions++ > 0) {
+		// it is possible one of the below functions itself can cause an exception, thus allow only one exception
+		logg->logMessage("Received multiple exceptions, terminating the child");
+		// Something is really wrong, exit immediately
+		_exit(1);
+	}
+	fprintf(stderr, "%s", logg->getLastError());
+
+	if (child && child->socket) {
+		if (sender) {
+			// send the error, regardless of the command sent by Streamline
+			sender->writeData(logg->getLastError(), strlen(logg->getLastError()), RESPONSE_ERROR);
+
+			// cannot close the socket before Streamline issues the command, so wait for the command before exiting
+			if (gSessionData->mWaitingOnCommand) {
+				char discard;
+				child->socket->receiveNBytes(&discard, 1);
+			}
+
+			// Ensure all data is flushed
+			child->socket->shutdownConnection();
+
+			// this indirectly calls close socket which will ensure the data has been sent
+			delete sender;
+		}
+	}
+
+	if (gSessionData->mLocalCapture) {
+		cleanUp();
+	}
+
+	exit(1);
+}
+
+// CTRL C Signal Handler for child process
+static void child_handler(int signum) {
+	static bool beenHere = false;
+	if (beenHere == true) {
+		logg->logMessage("Gator is being forced to shut down.");
+		exit(1);
+	}
+	beenHere = true;
+	logg->logMessage("Gator is shutting down.");
+	if (signum == SIGALRM || !primarySource) {
+		exit(1);
+	} else {
+		child->endSession();
+		alarm(5); // Safety net in case endSession does not complete within 5 seconds
+	}
+}
+
+static void *durationThread(void *) {
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-duration", 0, 0, 0);
+	sem_wait(&startProfile);
+	if (gSessionData->mSessionIsActive) {
+		// Time out after duration seconds
+		// Add a second for host-side filtering
+		sleep(gSessionData->mDuration + 1);
+		if (gSessionData->mSessionIsActive) {
+			logg->logMessage("Duration expired.");
+			child->endSession();
+		}
+	}
+	logg->logMessage("Exit duration thread");
+	return 0;
+}
+
+static void *stopThread(void *) {
+	OlySocket* socket = child->socket;
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-stopper", 0, 0, 0);
+	while (gSessionData->mSessionIsActive) {
+		// This thread will stall until the APC_STOP or PING command is received over the socket or the socket is disconnected
+		unsigned char header[5];
+		const int result = socket->receiveNBytes((char*)&header, sizeof(header));
+		const char type = header[0];
+		const int length = (header[1] << 0) | (header[2] << 8) | (header[3] << 16) | (header[4] << 24);
+		if (result == -1) {
+			child->endSession();
+		} else if (result > 0) {
+			if ((type != COMMAND_APC_STOP) && (type != COMMAND_PING)) {
+				logg->logMessage("INVESTIGATE: Received unknown command type %d", type);
+			} else {
+				// verify a length of zero
+				if (length == 0) {
+					if (type == COMMAND_APC_STOP) {
+						logg->logMessage("Stop command received.");
+						child->endSession();
+					} else {
+						// Ping is used to make sure gator is alive and requires an ACK as the response
+						logg->logMessage("Ping command received.");
+						sender->writeData(NULL, 0, RESPONSE_ACK);
+					}
+				} else {
+					logg->logMessage("INVESTIGATE: Received stop command but with length = %d", length);
+				}
+			}
+		}
+	}
+
+	logg->logMessage("Exit stop thread");
+	return 0;
+}
+
+static void *senderThread(void *) {
+	char end_sequence[] = {RESPONSE_APC_DATA, 0, 0, 0, 0};
+
+	sem_post(&senderThreadStarted);
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-sender", 0, 0, 0);
+	sem_wait(&haltPipeline);
+
+	while (!externalSource->isDone() ||
+	       (userSpaceSource != NULL && !userSpaceSource->isDone()) ||
+	       !primarySource->isDone()) {
+		sem_wait(&senderSem);
+
+		externalSource->write(sender);
+		if (userSpaceSource != NULL) {
+			userSpaceSource->write(sender);
+		}
+		primarySource->write(sender);
+	}
+
+	// write end-of-capture sequence
+	if (!gSessionData->mLocalCapture) {
+		sender->writeData(end_sequence, sizeof(end_sequence), RESPONSE_APC_DATA);
+	}
+
+	logg->logMessage("Exit sender thread");
+	return 0;
+}
+
+Child::Child() {
+	initialization();
+	gSessionData->mLocalCapture = true;
+}
+
+Child::Child(OlySocket* sock, int conn) {
+	initialization();
+	socket = sock;
+	mNumConnections = conn;
+}
+
+Child::~Child() {
+}
+
+void Child::initialization() {
+	// Set up different handlers for signals
+	gSessionData->mSessionIsActive = true;
+	signal(SIGINT, child_handler);
+	signal(SIGTERM, child_handler);
+	signal(SIGABRT, child_handler);
+	signal(SIGALRM, child_handler);
+	socket = NULL;
+	numExceptions = 0;
+	mNumConnections = 0;
+
+	// Initialize semaphores
+	sem_init(&senderThreadStarted, 0, 0);
+	sem_init(&startProfile, 0, 0);
+	sem_init(&senderSem, 0, 0);
+}
+
+void Child::endSession() {
+	gSessionData->mSessionIsActive = false;
+	primarySource->interrupt();
+	externalSource->interrupt();
+	if (userSpaceSource != NULL) {
+		userSpaceSource->interrupt();
+	}
+	sem_post(&haltPipeline);
+}
+
+void Child::run() {
+	LocalCapture* localCapture = NULL;
+	pthread_t durationThreadID, stopThreadID, senderThreadID;
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-child", 0, 0, 0);
+
+	// Disable line wrapping when generating xml files; carriage returns and indentation to be added manually
+	mxmlSetWrapMargin(0);
+
+	// Instantiate the Sender - must be done first, after which error messages can be sent
+	sender = new Sender(socket);
+
+	if (mNumConnections > 1) {
+		logg->logError("Session already in progress");
+		handleException();
+	}
+
+	// Populate gSessionData with the configuration
+	{ ConfigurationXML configuration; }
+
+	// Set up the driver; must be done after gSessionData->mPerfCounterType[] is populated
+	if (!gSessionData->mPerf.isSetup()) {
+		primarySource = new DriverSource(&senderSem, &startProfile);
+	} else {
+		primarySource = new PerfSource(&senderSem, &startProfile);
+	}
+
+	// Initialize all drivers
+	for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+		driver->resetCounters();
+	}
+
+	// Set up counters using the associated driver's setup function
+	for (int i = 0; i < MAX_PERFORMANCE_COUNTERS; i++) {
+		Counter & counter = gSessionData->mCounters[i];
+		if (counter.isEnabled()) {
+			counter.getDriver()->setupCounter(counter);
+		}
+	}
+
+	// Start up and parse session xml
+	if (socket) {
+		// Respond to Streamline requests
+		StreamlineSetup ss(socket);
+	} else {
+		char* xmlString;
+		xmlString = util->readFromDisk(gSessionData->mSessionXMLPath);
+		if (xmlString == 0) {
+			logg->logError("Unable to read session xml file: %s", gSessionData->mSessionXMLPath);
+			handleException();
+		}
+		gSessionData->parseSessionXML(xmlString);
+		localCapture = new LocalCapture();
+		localCapture->createAPCDirectory(gSessionData->mTargetPath);
+		localCapture->copyImages(gSessionData->mImages);
+		localCapture->write(xmlString);
+		sender->createDataFile(gSessionData->mAPCDir);
+		free(xmlString);
+	}
+
+	if (gSessionData->mKmod.isMaliCapture() && (gSessionData->mSampleRate == 0)) {
+		logg->logError("Mali counters are not supported with Sample Rate: None.");
+		handleException();
+	}
+
+	// Initialize ftrace source before child as it's slow and dependens on nothing else
+	// If initialized later, us gator with ftrace has time sync issues
+	// Must be initialized before senderThread is started as senderThread checks externalSource
+	externalSource = new ExternalSource(&senderSem);
+	if (!externalSource->prepare()) {
+		logg->logError("Unable to prepare external source for capture");
+		handleException();
+	}
+	externalSource->start();
+
+	// Must be after session XML is parsed
+	if (!primarySource->prepare()) {
+		if (gSessionData->mPerf.isSetup()) {
+			logg->logError("Unable to communicate with the perf API, please ensure that CONFIG_TRACING and CONFIG_CONTEXT_SWITCH_TRACER are enabled. Please refer to README_Streamline.txt for more information.");
+		} else {
+			logg->logError("Unable to prepare gator driver for capture");
+		}
+		handleException();
+	}
+
+	// Sender thread shall be halted until it is signaled for one shot mode
+	sem_init(&haltPipeline, 0, gSessionData->mOneShot ? 0 : 2);
+
+	// Create the duration, stop, and sender threads
+	bool thread_creation_success = true;
+	if (gSessionData->mDuration > 0 && pthread_create(&durationThreadID, NULL, durationThread, NULL)) {
+		thread_creation_success = false;
+	} else if (socket && pthread_create(&stopThreadID, NULL, stopThread, NULL)) {
+		thread_creation_success = false;
+	} else if (pthread_create(&senderThreadID, NULL, senderThread, NULL)) {
+		thread_creation_success = false;
+	}
+
+	bool startUSSource = false;
+	for (int i = 0; i < ARRAY_LENGTH(gSessionData->mUsDrivers); ++i) {
+		if (gSessionData->mUsDrivers[i]->countersEnabled()) {
+			startUSSource = true;
+		}
+	}
+	if (startUSSource) {
+		userSpaceSource = new UserSpaceSource(&senderSem);
+		if (!userSpaceSource->prepare()) {
+			logg->logError("Unable to prepare userspace source for capture");
+			handleException();
+		}
+		userSpaceSource->start();
+	}
+
+	if (gSessionData->mAllowCommands && (gSessionData->mCaptureCommand != NULL)) {
+		pthread_t thread;
+		if (pthread_create(&thread, NULL, commandThread, NULL)) {
+			thread_creation_success = false;
+		}
+	}
+
+	if (!thread_creation_success) {
+		logg->logError("Failed to create gator threads");
+		handleException();
+	}
+
+	// Wait until thread has started
+	sem_wait(&senderThreadStarted);
+
+	// Start profiling
+	primarySource->run();
+
+	// Wait for the other threads to exit
+	if (userSpaceSource != NULL) {
+		userSpaceSource->join();
+	}
+	externalSource->join();
+	pthread_join(senderThreadID, NULL);
+
+	// Shutting down the connection should break the stop thread which is stalling on the socket recv() function
+	if (socket) {
+		logg->logMessage("Waiting on stop thread");
+		socket->shutdownConnection();
+		pthread_join(stopThreadID, NULL);
+	}
+
+	// Write the captured xml file
+	if (gSessionData->mLocalCapture) {
+		CapturedXML capturedXML;
+		capturedXML.write(gSessionData->mAPCDir);
+	}
+
+	logg->logMessage("Profiling ended.");
+
+	delete userSpaceSource;
+	delete externalSource;
+	delete primarySource;
+	delete sender;
+	delete localCapture;
+}
diff --git a/tools/gator/daemon/Child.h b/tools/gator/daemon/Child.h
new file mode 100644
index 00000000000..a6c54db70a7
--- /dev/null
+++ b/tools/gator/daemon/Child.h
@@ -0,0 +1,33 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __CHILD_H__
+#define __CHILD_H__
+
+class OlySocket;
+
+class Child {
+public:
+	Child();
+	Child(OlySocket* sock, int numConnections);
+	~Child();
+	void run();
+	OlySocket *socket;
+	void endSession();
+	int numExceptions;
+private:
+	int mNumConnections;
+
+	void initialization();
+
+	// Intentionally unimplemented
+	Child(const Child &);
+	Child &operator=(const Child &);
+};
+
+#endif //__CHILD_H__
diff --git a/tools/gator/daemon/Command.cpp b/tools/gator/daemon/Command.cpp
new file mode 100644
index 00000000000..22f8be70359
--- /dev/null
+++ b/tools/gator/daemon/Command.cpp
@@ -0,0 +1,165 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Command.h"
+
+#include <fcntl.h>
+#include <grp.h>
+#include <pwd.h>
+#include <stdio.h>
+#include <sys/prctl.h>
+#include <sys/resource.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "Logging.h"
+#include "SessionData.h"
+
+static int getUid(const char *const name, const char *const tmpDir, uid_t *const uid) {
+	// Lookups may fail when using a different libc or a statically compiled executable
+	char gatorTemp[32];
+	snprintf(gatorTemp, sizeof(gatorTemp), "%s/gator_temp", tmpDir);
+
+	const int fd = open(gatorTemp, 600, O_CREAT | O_CLOEXEC);
+	if (fd < 0) {
+		return false;
+	}
+	close(fd);
+
+	char cmd[128];
+	snprintf(cmd, sizeof(cmd), "chown %s %s || rm %s", name, gatorTemp, gatorTemp);
+
+	const int pid = fork();
+	if (pid < 0) {
+		logg->logError("fork failed");
+		handleException();
+	}
+	if (pid == 0) {
+		execlp("sh", "sh", "-c", cmd, NULL);
+		exit(-1);
+	}
+	while ((waitpid(pid, NULL, 0) < 0) && (errno == EINTR));
+
+	struct stat st;
+	int result = -1;
+	if (stat(gatorTemp, &st) == 0) {
+		result = st.st_uid;
+	}
+	unlink(gatorTemp);
+	*uid = result;
+	return true;
+}
+
+static bool getUid(const char *const name, uid_t *const uid, gid_t *const gid) {
+	// Look up the username
+	struct passwd *const user = getpwnam(name);
+	if (user != NULL) {
+		*uid = user->pw_uid;
+		*gid = user->pw_gid;
+		return true;
+	}
+
+	// Unable to get the user without getpwanm, so create a unique uid by adding a fixed number to the pid
+	*gid = 0x484560f8 + getpid();
+
+	// Are we on Linux
+	if (access("/tmp", W_OK) == 0) {
+		return getUid(name, "/tmp", uid);
+	}
+
+	// Are we on android
+	if (access("/data", W_OK) == 0) {
+		return getUid(name, "/data", uid);
+	}
+
+	return false;
+}
+
+void *commandThread(void *) {
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-command", 0, 0, 0);
+
+	const char *const name = gSessionData->mCaptureUser == NULL ? "nobody" : gSessionData->mCaptureUser;
+	uid_t uid;
+	gid_t gid;
+	if (!getUid(name, &uid, &gid)) {
+		logg->logError("Unable to look up the user %s, please double check that the user exists", name);
+		handleException();
+	}
+
+	sleep(3);
+
+	char buf[128];
+	int pipefd[2];
+	if (pipe_cloexec(pipefd) != 0) {
+		logg->logError("pipe failed");
+		handleException();
+	}
+
+	const int pid = fork();
+	if (pid < 0) {
+		logg->logError("fork failed");
+		handleException();
+	}
+	if (pid == 0) {
+		buf[0] = '\0';
+		close(pipefd[0]);
+
+		// Gator runs at a high priority, reset the priority to the default
+		if (setpriority(PRIO_PROCESS, syscall(__NR_gettid), 0) == -1) {
+			snprintf(buf, sizeof(buf), "setpriority failed");
+			goto fail_exit;
+		}
+
+		if (setgroups(1, &gid) != 0) {
+			snprintf(buf, sizeof(buf), "setgroups failed");
+			goto fail_exit;
+		}
+		if (setresgid(gid, gid, gid) != 0) {
+			snprintf(buf, sizeof(buf), "setresgid failed");
+			goto fail_exit;
+		}
+		if (setresuid(uid, uid, uid) != 0) {
+			snprintf(buf, sizeof(buf), "setresuid failed");
+			goto fail_exit;
+		}
+
+		{
+			const char *const path = gSessionData->mCaptureWorkingDir == NULL ? "/" : gSessionData->mCaptureWorkingDir;
+			if (chdir(path) != 0) {
+				snprintf(buf, sizeof(buf), "Unable to cd to %s, please verify the directory exists and is accessable to %s", path, name);
+				goto fail_exit;
+			}
+		}
+
+		execlp("sh", "sh", "-c", gSessionData->mCaptureCommand, NULL);
+		snprintf(buf, sizeof(buf), "execv failed");
+
+	fail_exit:
+		if (buf[0] != '\0') {
+			const ssize_t bytes = write(pipefd[1], buf, sizeof(buf));
+			// Can't do anything if this fails
+			(void)bytes;
+		}
+
+		exit(-1);
+	}
+
+	close(pipefd[1]);
+	const ssize_t bytes = read(pipefd[0], buf, sizeof(buf));
+	if (bytes > 0) {
+		logg->logError("%s", buf);
+		handleException();
+	}
+	close(pipefd[0]);
+
+	return NULL;
+}
diff --git a/tools/gator/daemon/Command.h b/tools/gator/daemon/Command.h
new file mode 100644
index 00000000000..2838adcec66
--- /dev/null
+++ b/tools/gator/daemon/Command.h
@@ -0,0 +1,14 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef COMMAND_H
+#define COMMAND_H
+
+void *commandThread(void *);
+
+#endif // COMMAND_H
diff --git a/tools/gator/daemon/Config.h b/tools/gator/daemon/Config.h
new file mode 100644
index 00000000000..3c6752eedfd
--- /dev/null
+++ b/tools/gator/daemon/Config.h
@@ -0,0 +1,35 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef CONFIG_H
+#define CONFIG_H
+
+#define STRIFY2(ARG) #ARG
+#define STRIFY(ARG) STRIFY2(ARG)
+
+#define ARRAY_LENGTH(A) static_cast<int>(sizeof(A)/sizeof((A)[0]))
+#define ACCESS_ONCE(x) (*(volatile typeof(x)*)&(x))
+
+#define MAX_PERFORMANCE_COUNTERS 50
+#define NR_CPUS 32
+
+// If debugfs is not mounted at /sys/kernel/debug, update TRACING_PATH
+#define TRACING_PATH "/sys/kernel/debug/tracing"
+#define EVENTS_PATH TRACING_PATH "/events"
+
+template<typename T>
+static inline T min(const T a, const T b) {
+	return (a < b ? a : b);
+}
+
+template<typename T>
+static inline T max(const T a, const T b) {
+	return (a > b ? a : b);
+}
+
+#endif // CONFIG_H
diff --git a/tools/gator/daemon/ConfigurationXML.cpp b/tools/gator/daemon/ConfigurationXML.cpp
new file mode 100644
index 00000000000..b433811fc48
--- /dev/null
+++ b/tools/gator/daemon/ConfigurationXML.cpp
@@ -0,0 +1,226 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "ConfigurationXML.h"
+
+#include <string.h>
+#include <stdlib.h>
+#include <dirent.h>
+
+#include "Driver.h"
+#include "Logging.h"
+#include "OlyUtility.h"
+#include "SessionData.h"
+
+static const char* ATTR_COUNTER            = "counter";
+static const char* ATTR_REVISION           = "revision";
+static const char* ATTR_EVENT              = "event";
+static const char* ATTR_COUNT              = "count";
+static const char* ATTR_CORES              = "cores";
+
+ConfigurationXML::ConfigurationXML() {
+	const char * configuration_xml;
+	unsigned int configuration_xml_len;
+	getDefaultConfigurationXml(configuration_xml, configuration_xml_len);
+
+	char path[PATH_MAX];
+
+	getPath(path);
+	mConfigurationXML = util->readFromDisk(path);
+
+	for (int retryCount = 0; retryCount < 2; ++retryCount) {
+		if (mConfigurationXML == NULL) {
+			logg->logMessage("Unable to locate configuration.xml, using default in binary");
+			// null-terminate configuration_xml
+			mConfigurationXML = (char*)malloc(configuration_xml_len + 1);
+			memcpy(mConfigurationXML, (const void*)configuration_xml, configuration_xml_len);
+			mConfigurationXML[configuration_xml_len] = 0;
+		}
+
+		int ret = parse(mConfigurationXML);
+		if (ret == 1) {
+			remove();
+
+			// Free the current configuration and reload
+			free((void*)mConfigurationXML);
+			mConfigurationXML = NULL;
+			continue;
+		}
+
+		break;
+	}
+
+	validate();
+}
+
+ConfigurationXML::~ConfigurationXML() {
+	if (mConfigurationXML) {
+		free((void*)mConfigurationXML);
+	}
+}
+
+int ConfigurationXML::parse(const char* configurationXML) {
+	mxml_node_t *tree, *node;
+	int ret;
+
+	if (gSessionData->mCountersError != NULL) {
+		free(gSessionData->mCountersError);
+		gSessionData->mCountersError = NULL;
+	}
+	gSessionData->mIsEBS = false;
+	mIndex = 0;
+
+	// disable all counters prior to parsing the configuration xml
+	for (int i = 0; i < MAX_PERFORMANCE_COUNTERS; i++) {
+		gSessionData->mCounters[i].setEnabled(false);
+	}
+
+	tree = mxmlLoadString(NULL, configurationXML, MXML_NO_CALLBACK);
+
+	node = mxmlGetFirstChild(tree);
+	while (node && mxmlGetType(node) != MXML_ELEMENT)
+		node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+
+	ret = configurationsTag(node);
+
+	node = mxmlGetFirstChild(node);
+	while (node) {
+		if (mxmlGetType(node) != MXML_ELEMENT) {
+			node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+			continue;
+		}
+		configurationTag(node);
+		node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+	}
+
+	mxmlDelete(tree);
+
+	if (gSessionData->mCountersError == NULL && mIndex > MAX_PERFORMANCE_COUNTERS) {
+		if (asprintf(&gSessionData->mCountersError, "Only %i performance counters are permitted, %i are selected", MAX_PERFORMANCE_COUNTERS, mIndex) <= 0) {
+			logg->logError("asprintf failed");
+			handleException();
+		}
+	}
+	gSessionData->mCcnDriver.validateCounters();
+
+	return ret;
+}
+
+void ConfigurationXML::validate(void) {
+	for (int i = 0; i < MAX_PERFORMANCE_COUNTERS; i++) {
+		const Counter & counter = gSessionData->mCounters[i];
+		if (counter.isEnabled()) {
+			if (strcmp(counter.getType(), "") == 0) {
+				logg->logError("Invalid required attribute in configuration.xml:\n  counter=\"%s\"\n  event=%d\n", counter.getType(), counter.getEvent());
+				handleException();
+			}
+
+			// iterate through the remaining enabled performance counters
+			for (int j = i + 1; j < MAX_PERFORMANCE_COUNTERS; j++) {
+				const Counter & counter2 = gSessionData->mCounters[j];
+				if (counter2.isEnabled()) {
+					// check if the types are the same
+					if (strcmp(counter.getType(), counter2.getType()) == 0) {
+						logg->logError("Duplicate performance counter type in configuration.xml: %s", counter.getType());
+						handleException();
+					}
+				}
+			}
+		}
+	}
+}
+
+#define CONFIGURATION_REVISION 3
+int ConfigurationXML::configurationsTag(mxml_node_t *node) {
+	const char* revision_string;
+
+	revision_string = mxmlElementGetAttr(node, ATTR_REVISION);
+	if (!revision_string) {
+		return 1; //revision issue;
+	}
+
+	int revision = strtol(revision_string, NULL, 10);
+	if (revision < CONFIGURATION_REVISION) {
+		return 1; // revision issue
+	}
+
+	// A revision >= CONFIGURATION_REVISION is okay
+	// Greater than can occur when Streamline is newer than gator
+
+	return 0;
+}
+
+void ConfigurationXML::configurationTag(mxml_node_t *node) {
+	// handle all other performance counters
+	if (mIndex >= MAX_PERFORMANCE_COUNTERS) {
+		mIndex++;
+		return;
+	}
+
+	// read attributes
+	Counter & counter = gSessionData->mCounters[mIndex];
+	counter.clear();
+	if (mxmlElementGetAttr(node, ATTR_COUNTER)) counter.setType(mxmlElementGetAttr(node, ATTR_COUNTER));
+	if (mxmlElementGetAttr(node, ATTR_EVENT)) counter.setEvent(strtol(mxmlElementGetAttr(node, ATTR_EVENT), NULL, 16));
+	if (mxmlElementGetAttr(node, ATTR_COUNT)) counter.setCount(strtol(mxmlElementGetAttr(node, ATTR_COUNT), NULL, 10));
+	if (mxmlElementGetAttr(node, ATTR_CORES)) counter.setCores(strtol(mxmlElementGetAttr(node, ATTR_CORES), NULL, 10));
+	if (counter.getCount() > 0) {
+		gSessionData->mIsEBS = true;
+	}
+	counter.setEnabled(true);
+
+	// Associate a driver with each counter
+	for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+		if (driver->claimCounter(counter)) {
+			if (counter.getDriver() != NULL) {
+				logg->logError("More than one driver has claimed %s:%i", counter.getType(), counter.getEvent());
+				handleException();
+			}
+			counter.setDriver(driver);
+		}
+	}
+
+	// If no driver is associated with the counter, disable it
+	if (counter.getDriver() == NULL) {
+		logg->logMessage("No driver has claimed %s:%i", counter.getType(), counter.getEvent());
+		counter.setEnabled(false);
+	}
+
+	if (counter.isEnabled()) {
+		// update counter index
+		mIndex++;
+	}
+}
+
+void ConfigurationXML::getDefaultConfigurationXml(const char * & xml, unsigned int & len) {
+#include "defaults_xml.h" // defines and initializes char defaults_xml[] and int defaults_xml_len
+	xml = (const char *)defaults_xml;
+	len = defaults_xml_len;
+}
+
+void ConfigurationXML::getPath(char* path) {
+	if (gSessionData->mConfigurationXMLPath) {
+		strncpy(path, gSessionData->mConfigurationXMLPath, PATH_MAX);
+	} else {
+		if (util->getApplicationFullPath(path, PATH_MAX) != 0) {
+			logg->logMessage("Unable to determine the full path of gatord, the cwd will be used");
+		}
+		strncat(path, "configuration.xml", PATH_MAX - strlen(path) - 1);
+	}
+}
+
+void ConfigurationXML::remove() {
+	char path[PATH_MAX];
+	getPath(path);
+
+	if (::remove(path) != 0) {
+		logg->logError("Invalid configuration.xml file detected and unable to delete it. To resolve, delete configuration.xml on disk");
+		handleException();
+	}
+	logg->logMessage("Invalid configuration.xml file detected and removed");
+}
diff --git a/tools/gator/daemon/ConfigurationXML.h b/tools/gator/daemon/ConfigurationXML.h
new file mode 100644
index 00000000000..a986ce99381
--- /dev/null
+++ b/tools/gator/daemon/ConfigurationXML.h
@@ -0,0 +1,38 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef COUNTERS_H
+#define COUNTERS_H
+
+#include "mxml/mxml.h"
+
+class ConfigurationXML {
+public:
+	static void getDefaultConfigurationXml(const char * & xml, unsigned int & len);
+	static void getPath(char* path);
+	static void remove();
+
+	ConfigurationXML();
+	~ConfigurationXML();
+	const char* getConfigurationXML() {return mConfigurationXML;}
+	void validate(void);
+
+private:
+	char* mConfigurationXML;
+	int mIndex;
+
+	int parse(const char* xmlFile);
+	int configurationsTag(mxml_node_t *node);
+	void configurationTag(mxml_node_t *node);
+
+	// Intentionally unimplemented
+	ConfigurationXML(const ConfigurationXML &);
+	ConfigurationXML &operator=(const ConfigurationXML &);
+};
+
+#endif // COUNTERS_H
diff --git a/tools/gator/daemon/Counter.h b/tools/gator/daemon/Counter.h
new file mode 100644
index 00000000000..a4c22f57134
--- /dev/null
+++ b/tools/gator/daemon/Counter.h
@@ -0,0 +1,65 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef COUNTER_H
+#define COUNTER_H
+
+#include <string.h>
+
+class Driver;
+
+class Counter {
+public:
+	static const size_t MAX_STRING_LEN = 80;
+	static const size_t MAX_DESCRIPTION_LEN = 400;
+
+	Counter () {
+		clear();
+	}
+
+	void clear () {
+		mType[0] = '\0';
+		mEnabled = false;
+		mEvent = -1;
+		mCount = 0;
+		mCores = -1;
+		mKey = 0;
+		mDriver = NULL;
+	}
+
+	void setType(const char *const type) { strncpy(mType, type, sizeof(mType)); mType[sizeof(mType) - 1] = '\0'; }
+	void setEnabled(const bool enabled) { mEnabled = enabled; }
+	void setEvent(const int event) { mEvent = event; }
+	void setCount(const int count) { mCount = count; }
+	void setCores(const int cores) { mCores = cores; }
+	void setKey(const int key) { mKey = key; }
+	void setDriver(Driver *const driver) { mDriver = driver; }
+
+	const char *getType() const { return mType;}
+	bool isEnabled() const { return mEnabled; }
+	int getEvent() const { return mEvent; }
+	int getCount() const { return mCount; }
+	int getCores() const { return mCores; }
+	int getKey() const { return mKey; }
+	Driver *getDriver() const { return mDriver; }
+
+private:
+	// Intentionally unimplemented
+	Counter(const Counter &);
+	Counter & operator=(const Counter &);
+
+	char mType[MAX_STRING_LEN];
+	bool mEnabled;
+	int mEvent;
+	int mCount;
+	int mCores;
+	int mKey;
+	Driver *mDriver;
+};
+
+#endif // COUNTER_H
diff --git a/tools/gator/daemon/DiskIODriver.cpp b/tools/gator/daemon/DiskIODriver.cpp
new file mode 100644
index 00000000000..bd18bbd08de
--- /dev/null
+++ b/tools/gator/daemon/DiskIODriver.cpp
@@ -0,0 +1,125 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+// Define to get format macros from inttypes.h
+#define __STDC_FORMAT_MACROS
+
+#include "DiskIODriver.h"
+
+#include <inttypes.h>
+
+#include "Logging.h"
+#include "SessionData.h"
+
+class DiskIOCounter : public DriverCounter {
+public:
+	DiskIOCounter(DriverCounter *next, char *const name, int64_t *const value);
+	~DiskIOCounter();
+
+	int64_t read();
+
+private:
+	int64_t *const mValue;
+	int64_t mPrev;
+
+	// Intentionally unimplemented
+	DiskIOCounter(const DiskIOCounter &);
+	DiskIOCounter &operator=(const DiskIOCounter &);
+};
+
+DiskIOCounter::DiskIOCounter(DriverCounter *next, char *const name, int64_t *const value) : DriverCounter(next, name), mValue(value), mPrev(0) {
+}
+
+DiskIOCounter::~DiskIOCounter() {
+}
+
+int64_t DiskIOCounter::read() {
+	int64_t result = *mValue - mPrev;
+	mPrev = *mValue;
+	// Kernel assumes a sector is 512 bytes
+	return result << 9;
+}
+
+DiskIODriver::DiskIODriver() : mBuf(), mReadBytes(0), mWriteBytes(0) {
+}
+
+DiskIODriver::~DiskIODriver() {
+}
+
+void DiskIODriver::readEvents(mxml_node_t *const) {
+	// Only for use with perf
+	if (!gSessionData->mPerf.isSetup()) {
+		return;
+	}
+
+	setCounters(new DiskIOCounter(getCounters(), strdup("Linux_block_rq_rd"), &mReadBytes));
+	setCounters(new DiskIOCounter(getCounters(), strdup("Linux_block_rq_wr"), &mWriteBytes));
+}
+
+void DiskIODriver::doRead() {
+	if (!countersEnabled()) {
+		return;
+	}
+
+	if (!mBuf.read("/proc/diskstats")) {
+		logg->logError("Unable to read /proc/diskstats");
+		handleException();
+	}
+
+	mReadBytes = 0;
+	mWriteBytes = 0;
+
+	char *lastName = NULL;
+	int lastNameLen = -1;
+	char *line = mBuf.getBuf();
+	while (*line != '\0') {
+		char *end = strchr(line, '\n');
+		if (end != NULL) {
+			*end = '\0';
+		}
+
+		int nameStart = -1;
+		int nameEnd = -1;
+		int64_t readBytes = -1;
+		int64_t writeBytes = -1;
+		const int count = sscanf(line, "%*d %*d %n%*s%n %*u %*u %" SCNu64 " %*u %*u %*u %" SCNu64, &nameStart, &nameEnd, &readBytes, &writeBytes);
+		if (count != 2) {
+			logg->logError("Unable to parse /proc/diskstats");
+			handleException();
+		}
+
+		// Skip partitions which are identified if the name is a substring of the last non-partition
+		if ((lastName == NULL) || (strncmp(lastName, line + nameStart, lastNameLen) != 0)) {
+			lastName = line + nameStart;
+			lastNameLen = nameEnd - nameStart;
+			mReadBytes += readBytes;
+			mWriteBytes += writeBytes;
+		}
+
+		if (end == NULL) {
+			break;
+		}
+		line = end + 1;
+	}
+}
+
+void DiskIODriver::start() {
+	doRead();
+	// Initialize previous values
+	for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		counter->read();
+	}
+}
+
+void DiskIODriver::read(Buffer *const buffer) {
+	doRead();
+	super::read(buffer);
+}
diff --git a/tools/gator/daemon/DiskIODriver.h b/tools/gator/daemon/DiskIODriver.h
new file mode 100644
index 00000000000..6ecda5afc25
--- /dev/null
+++ b/tools/gator/daemon/DiskIODriver.h
@@ -0,0 +1,39 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef DISKIODRIVER_H
+#define DISKIODRIVER_H
+
+#include "Driver.h"
+#include "DynBuf.h"
+
+class DiskIODriver : public PolledDriver {
+private:
+	typedef PolledDriver super;
+
+public:
+	DiskIODriver();
+	~DiskIODriver();
+
+	void readEvents(mxml_node_t *const root);
+	void start();
+	void read(Buffer *const buffer);
+
+private:
+	void doRead();
+
+	DynBuf mBuf;
+	int64_t mReadBytes;
+	int64_t mWriteBytes;
+
+	// Intentionally unimplemented
+	DiskIODriver(const DiskIODriver &);
+	DiskIODriver &operator=(const DiskIODriver &);
+};
+
+#endif // DISKIODRIVER_H
diff --git a/tools/gator/daemon/Driver.cpp b/tools/gator/daemon/Driver.cpp
new file mode 100644
index 00000000000..72c731424bd
--- /dev/null
+++ b/tools/gator/daemon/Driver.cpp
@@ -0,0 +1,96 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Driver.h"
+
+#include "Buffer.h"
+#include "SessionData.h"
+
+DriverCounter::DriverCounter(DriverCounter *const next, const char *const name) : mNext(next), mName(name), mKey(getEventKey()), mEnabled(false) {
+}
+
+DriverCounter::~DriverCounter() {
+	delete mName;
+}
+
+Driver *Driver::head = NULL;
+
+Driver::Driver() : next(head) {
+	head = this;
+}
+
+SimpleDriver::~SimpleDriver() {
+	DriverCounter *counters = mCounters;
+	while (counters != NULL) {
+		DriverCounter *counter = counters;
+		counters = counter->getNext();
+		delete counter;
+	}
+}
+
+DriverCounter *SimpleDriver::findCounter(const Counter &counter) const {
+	for (DriverCounter *driverCounter = mCounters; driverCounter != NULL; driverCounter = driverCounter->getNext()) {
+		if (strcmp(driverCounter->getName(), counter.getType()) == 0) {
+			return driverCounter;
+		}
+	}
+
+	return NULL;
+}
+
+bool SimpleDriver::claimCounter(const Counter &counter) const {
+	return findCounter(counter) != NULL;
+}
+
+bool SimpleDriver::countersEnabled() const {
+	for (DriverCounter *counter = mCounters; counter != NULL; counter = counter->getNext()) {
+		if (counter->isEnabled()) {
+			return true;
+		}
+	}
+	return false;
+}
+
+void SimpleDriver::resetCounters() {
+	for (DriverCounter *counter = mCounters; counter != NULL; counter = counter->getNext()) {
+		counter->setEnabled(false);
+	}
+}
+
+void SimpleDriver::setupCounter(Counter &counter) {
+	DriverCounter *const driverCounter = findCounter(counter);
+	if (driverCounter == NULL) {
+		counter.setEnabled(false);
+		return;
+	}
+	driverCounter->setEnabled(true);
+	counter.setKey(driverCounter->getKey());
+}
+
+int SimpleDriver::writeCounters(mxml_node_t *root) const {
+	int count = 0;
+	for (DriverCounter *counter = mCounters; counter != NULL; counter = counter->getNext()) {
+		mxml_node_t *node = mxmlNewElement(root, "counter");
+		mxmlElementSetAttr(node, "name", counter->getName());
+		++count;
+	}
+
+	return count;
+}
+
+PolledDriver::~PolledDriver() {
+}
+
+void PolledDriver::read(Buffer *const buffer) {
+	for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		buffer->event64(counter->getKey(), counter->read());
+	}
+}
diff --git a/tools/gator/daemon/Driver.h b/tools/gator/daemon/Driver.h
new file mode 100644
index 00000000000..19ec12775a3
--- /dev/null
+++ b/tools/gator/daemon/Driver.h
@@ -0,0 +1,118 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef DRIVER_H
+#define DRIVER_H
+
+#include <stdint.h>
+
+#include "mxml/mxml.h"
+
+class Buffer;
+class Counter;
+
+class DriverCounter {
+public:
+	DriverCounter(DriverCounter *const next, const char *const name);
+	virtual ~DriverCounter();
+
+	DriverCounter *getNext() const { return mNext; }
+	const char *getName() const { return mName; }
+	int getKey() const { return mKey; }
+	bool isEnabled() const { return mEnabled; }
+	void setEnabled(const bool enabled) { mEnabled = enabled; }
+	virtual int64_t read() { return -1; }
+
+private:
+	DriverCounter *const mNext;
+	const char *const mName;
+	const int mKey;
+	bool mEnabled;
+
+	// Intentionally unimplemented
+	DriverCounter(const DriverCounter &);
+	DriverCounter &operator=(const DriverCounter &);
+};
+
+class Driver {
+public:
+	static Driver *getHead() { return head; }
+
+	virtual ~Driver() {}
+
+	// Returns true if this driver can manage the counter
+	virtual bool claimCounter(const Counter &counter) const = 0;
+	// Clears and disables all counters
+	virtual void resetCounters() = 0;
+	// Enables and prepares the counter for capture
+	virtual void setupCounter(Counter &counter) = 0;
+
+	// Performs any actions needed for setup or based on eventsXML
+	virtual void readEvents(mxml_node_t *const) {}
+	// Emits available counters
+	virtual int writeCounters(mxml_node_t *const root) const = 0;
+	// Emits possible dynamically generated events/counters
+	virtual void writeEvents(mxml_node_t *const) const {}
+
+	Driver *getNext() const { return next; }
+
+protected:
+	Driver();
+
+private:
+	static Driver *head;
+	Driver *next;
+
+	// Intentionally unimplemented
+	Driver(const Driver &);
+	Driver &operator=(const Driver &);
+};
+
+class SimpleDriver : public Driver {
+public:
+	virtual ~SimpleDriver();
+
+	bool claimCounter(const Counter &counter) const;
+	bool countersEnabled() const;
+	void resetCounters();
+	void setupCounter(Counter &counter);
+	int writeCounters(mxml_node_t *root) const;
+
+protected:
+	SimpleDriver() : mCounters(NULL) {}
+
+	DriverCounter *getCounters() const { return mCounters; }
+	void setCounters(DriverCounter *const counter) { mCounters = counter; }
+
+	DriverCounter *findCounter(const Counter &counter) const;
+
+private:
+	DriverCounter *mCounters;
+
+	// Intentionally unimplemented
+	SimpleDriver(const SimpleDriver &);
+	SimpleDriver &operator=(const SimpleDriver &);
+};
+
+class PolledDriver : public SimpleDriver {
+public:
+	virtual ~PolledDriver();
+
+	virtual void start() {}
+	virtual void read(Buffer *const buffer);
+
+protected:
+	PolledDriver() {}
+
+private:
+	// Intentionally unimplemented
+	PolledDriver(const PolledDriver &);
+	PolledDriver &operator=(const PolledDriver &);
+};
+
+#endif // DRIVER_H
diff --git a/tools/gator/daemon/DriverSource.cpp b/tools/gator/daemon/DriverSource.cpp
new file mode 100644
index 00000000000..caa956ff75b
--- /dev/null
+++ b/tools/gator/daemon/DriverSource.cpp
@@ -0,0 +1,327 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+// Define to get format macros from inttypes.h
+#define __STDC_FORMAT_MACROS
+
+#include "DriverSource.h"
+
+#include <fcntl.h>
+#include <inttypes.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Child.h"
+#include "DynBuf.h"
+#include "Fifo.h"
+#include "Logging.h"
+#include "Proc.h"
+#include "Sender.h"
+#include "SessionData.h"
+
+extern Child *child;
+
+DriverSource::DriverSource(sem_t *senderSem, sem_t *startProfile) : mBuffer(NULL), mFifo(NULL), mSenderSem(senderSem), mStartProfile(startProfile), mBufferSize(0), mBufferFD(0), mLength(1) {
+	mBuffer = new Buffer(0, FRAME_PERF_ATTRS, 4*1024*1024, senderSem);
+	checkVersion();
+
+	int enable = -1;
+	if (readIntDriver("/dev/gator/enable", &enable) != 0 || enable != 0) {
+		logg->logError("Driver already enabled, possibly a session is already in progress.");
+		handleException();
+	}
+
+	readIntDriver("/dev/gator/cpu_cores", &gSessionData->mCores);
+	if (gSessionData->mCores == 0) {
+		gSessionData->mCores = 1;
+	}
+
+	if (readIntDriver("/dev/gator/buffer_size", &mBufferSize) || mBufferSize <= 0) {
+		logg->logError("Unable to read the driver buffer size");
+		handleException();
+	}
+}
+
+DriverSource::~DriverSource() {
+	delete mFifo;
+
+	// Write zero for safety, as a zero should have already been written
+	writeDriver("/dev/gator/enable", "0");
+
+	// Calls event_buffer_release in the driver
+	if (mBufferFD) {
+		close(mBufferFD);
+	}
+}
+
+void DriverSource::checkVersion() {
+	int driverVersion = 0;
+
+	if (readIntDriver("/dev/gator/version", &driverVersion) == -1) {
+		logg->logError("Error reading gator driver version");
+		handleException();
+	}
+
+	// Verify the driver version matches the daemon version
+	if (driverVersion != PROTOCOL_VERSION) {
+		if ((driverVersion > PROTOCOL_DEV) || (PROTOCOL_VERSION > PROTOCOL_DEV)) {
+			// One of the mismatched versions is development version
+			logg->logError(
+				"DEVELOPMENT BUILD MISMATCH: gator driver version \"%d\" is not in sync with gator daemon version \"%d\".\n"
+				">> The following must be synchronized from engineering repository:\n"
+				">> * gator driver\n"
+				">> * gator daemon\n"
+				">> * Streamline", driverVersion, PROTOCOL_VERSION);
+			handleException();
+		} else {
+			// Release version mismatch
+			logg->logError(
+				"gator driver version \"%d\" is different than gator daemon version \"%d\".\n"
+				">> Please upgrade the driver and daemon to the latest versions.", driverVersion, PROTOCOL_VERSION);
+			handleException();
+		}
+	}
+}
+
+bool DriverSource::prepare() {
+	// Create user-space buffers, add 5 to the size to account for the 1-byte type and 4-byte length
+	logg->logMessage("Created %d MB collector buffer with a %d-byte ragged end", gSessionData->mTotalBufferSize, mBufferSize);
+	mFifo = new Fifo(mBufferSize + 5, gSessionData->mTotalBufferSize*1024*1024, mSenderSem);
+
+	return true;
+}
+
+void DriverSource::bootstrapThread() {
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-proc", 0, 0, 0);
+
+	DynBuf printb;
+	DynBuf b1;
+	DynBuf b2;
+	// MonotonicStarted may not be not assigned yet
+	const uint64_t currTime = 0;//getTime() - gSessionData->mMonotonicStarted;
+
+	if (!readProcComms(currTime, mBuffer, &printb, &b1, &b2)) {
+		logg->logError("readProcComms failed");
+		handleException();
+	}
+
+	mBuffer->commit(currTime);
+	mBuffer->setDone();
+}
+
+void *DriverSource::bootstrapThreadStatic(void *arg) {
+	static_cast<DriverSource *>(arg)->bootstrapThread();
+	return NULL;
+}
+
+void DriverSource::run() {
+	// Get the initial pointer to the collect buffer
+	char *collectBuffer = mFifo->start();
+	int bytesCollected = 0;
+
+	logg->logMessage("********** Profiling started **********");
+
+	// Set the maximum backtrace depth
+	if (writeReadDriver("/dev/gator/backtrace_depth", &gSessionData->mBacktraceDepth)) {
+		logg->logError("Unable to set the driver backtrace depth");
+		handleException();
+	}
+
+	// open the buffer which calls userspace_buffer_open() in the driver
+	mBufferFD = open("/dev/gator/buffer", O_RDONLY | O_CLOEXEC);
+	if (mBufferFD < 0) {
+		logg->logError("The gator driver did not set up properly. Please view the linux console or dmesg log for more information on the failure.");
+		handleException();
+	}
+
+	// set the tick rate of the profiling timer
+	if (writeReadDriver("/dev/gator/tick", &gSessionData->mSampleRate) != 0) {
+		logg->logError("Unable to set the driver tick");
+		handleException();
+	}
+
+	// notify the kernel of the response type
+	int response_type = gSessionData->mLocalCapture ? 0 : RESPONSE_APC_DATA;
+	if (writeDriver("/dev/gator/response_type", response_type)) {
+		logg->logError("Unable to write the response type");
+		handleException();
+	}
+
+	// Set the live rate
+	if (writeReadDriver("/dev/gator/live_rate", &gSessionData->mLiveRate)) {
+		logg->logError("Unable to set the driver live rate");
+		handleException();
+	}
+
+	logg->logMessage("Start the driver");
+
+	// This command makes the driver start profiling by calling gator_op_start() in the driver
+	if (writeDriver("/dev/gator/enable", "1") != 0) {
+		logg->logError("The gator driver did not start properly. Please view the linux console or dmesg log for more information on the failure.");
+		handleException();
+	}
+
+	lseek(mBufferFD, 0, SEEK_SET);
+
+	sem_post(mStartProfile);
+
+	pthread_t bootstrapThreadID;
+	if (pthread_create(&bootstrapThreadID, NULL, bootstrapThreadStatic, this) != 0) {
+		logg->logError("Unable to start the gator_bootstrap thread");
+		handleException();
+	}
+
+	// Collect Data
+	do {
+		// This command will stall until data is received from the driver
+		// Calls event_buffer_read in the driver
+		errno = 0;
+		bytesCollected = read(mBufferFD, collectBuffer, mBufferSize);
+
+		// If read() returned due to an interrupt signal, re-read to obtain the last bit of collected data
+		if (bytesCollected == -1 && errno == EINTR) {
+			bytesCollected = read(mBufferFD, collectBuffer, mBufferSize);
+		}
+
+		// return the total bytes written
+		logg->logMessage("Driver read of %d bytes", bytesCollected);
+
+		// In one shot mode, stop collection once all the buffers are filled
+		if (gSessionData->mOneShot && gSessionData->mSessionIsActive) {
+			if (bytesCollected == -1 || mFifo->willFill(bytesCollected)) {
+				logg->logMessage("One shot (gator.ko)");
+				child->endSession();
+			}
+		}
+		collectBuffer = mFifo->write(bytesCollected);
+	} while (bytesCollected > 0);
+
+	logg->logMessage("Exit collect data loop");
+
+	pthread_join(bootstrapThreadID, NULL);
+}
+
+void DriverSource::interrupt() {
+	// This command should cause the read() function in collect() to return and stop the driver from profiling
+	if (writeDriver("/dev/gator/enable", "0") != 0) {
+		logg->logMessage("Stopping kernel failed");
+	}
+}
+
+bool DriverSource::isDone() {
+	return mLength <= 0 && (mBuffer == NULL || mBuffer->isDone());
+}
+
+void DriverSource::write(Sender *sender) {
+	char *data = mFifo->read(&mLength);
+	if (data != NULL) {
+		sender->writeData(data, mLength, RESPONSE_APC_DATA);
+		mFifo->release();
+		// Assume the summary packet is in the first block received from the driver
+		gSessionData->mSentSummary = true;
+	}
+	if (mBuffer != NULL && !mBuffer->isDone()) {
+		mBuffer->write(sender);
+		if (mBuffer->isDone()) {
+			Buffer *buf = mBuffer;
+			mBuffer = NULL;
+			delete buf;
+		}
+	}
+}
+
+int DriverSource::readIntDriver(const char *fullpath, int *value) {
+	char data[40]; // Sufficiently large to hold any integer
+	const int fd = open(fullpath, O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		return -1;
+	}
+
+	const ssize_t bytes = read(fd, data, sizeof(data) - 1);
+	close(fd);
+	if (bytes < 0) {
+		return -1;
+	}
+	data[bytes] = '\0';
+
+	char *endptr;
+	errno = 0;
+	*value = strtol(data, &endptr, 10);
+	if (errno != 0 || *endptr != '\n') {
+		logg->logMessage("Invalid value in file %s", fullpath);
+		return -1;
+	}
+
+	return 0;
+}
+
+int DriverSource::readInt64Driver(const char *fullpath, int64_t *value) {
+	char data[40]; // Sufficiently large to hold any integer
+	const int fd = open(fullpath, O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		return -1;
+	}
+
+	const ssize_t bytes = read(fd, data, sizeof(data) - 1);
+	close(fd);
+	if (bytes < 0) {
+		return -1;
+	}
+	data[bytes] = '\0';
+
+	char *endptr;
+	errno = 0;
+	*value = strtoll(data, &endptr, 10);
+	if (errno != 0 || (*endptr != '\n' && *endptr != '\0')) {
+		logg->logMessage("Invalid value in file %s", fullpath);
+		return -1;
+	}
+
+	return 0;
+}
+
+int DriverSource::writeDriver(const char *fullpath, const char *data) {
+	int fd = open(fullpath, O_WRONLY | O_CLOEXEC);
+	if (fd < 0) {
+		return -1;
+	}
+	if (::write(fd, data, strlen(data)) < 0) {
+		close(fd);
+		logg->logMessage("Opened but could not write to %s", fullpath);
+		return -1;
+	}
+	close(fd);
+	return 0;
+}
+
+int DriverSource::writeDriver(const char *path, int value) {
+	char data[40]; // Sufficiently large to hold any integer
+	snprintf(data, sizeof(data), "%d", value);
+	return writeDriver(path, data);
+}
+
+int DriverSource::writeDriver(const char *path, int64_t value) {
+	char data[40]; // Sufficiently large to hold any integer
+	snprintf(data, sizeof(data), "%" PRIi64, value);
+	return writeDriver(path, data);
+}
+
+int DriverSource::writeReadDriver(const char *path, int *value) {
+	if (writeDriver(path, *value) || readIntDriver(path, value)) {
+		return -1;
+	}
+	return 0;
+}
+
+int DriverSource::writeReadDriver(const char *path, int64_t *value) {
+	if (writeDriver(path, *value) || readInt64Driver(path, value)) {
+		return -1;
+	}
+	return 0;
+}
diff --git a/tools/gator/daemon/DriverSource.h b/tools/gator/daemon/DriverSource.h
new file mode 100644
index 00000000000..971a4d970e3
--- /dev/null
+++ b/tools/gator/daemon/DriverSource.h
@@ -0,0 +1,58 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef DRIVERSOURCE_H
+#define DRIVERSOURCE_H
+
+#include <semaphore.h>
+#include <stdint.h>
+
+#include "Source.h"
+
+class Buffer;
+class Fifo;
+
+class DriverSource : public Source {
+public:
+	DriverSource(sem_t *senderSem, sem_t *startProfile);
+	~DriverSource();
+
+	bool prepare();
+	void run();
+	void interrupt();
+
+	bool isDone();
+	void write(Sender *sender);
+
+	static void checkVersion();
+	static int readIntDriver(const char *fullpath, int *value);
+	static int readInt64Driver(const char *fullpath, int64_t *value);
+	static int writeDriver(const char *fullpath, const char *data);
+	static int writeDriver(const char *path, int value);
+	static int writeDriver(const char *path, int64_t value);
+	static int writeReadDriver(const char *path, int *value);
+	static int writeReadDriver(const char *path, int64_t *value);
+
+private:
+	static void *bootstrapThreadStatic(void *arg);
+	void bootstrapThread();
+
+	Buffer *mBuffer;
+	Fifo *mFifo;
+	sem_t *const mSenderSem;
+	sem_t *const mStartProfile;
+	int mBufferSize;
+	int mBufferFD;
+	int mLength;
+
+	// Intentionally unimplemented
+	DriverSource(const DriverSource &);
+	DriverSource &operator=(const DriverSource &);
+};
+
+#endif // DRIVERSOURCE_H
diff --git a/tools/gator/daemon/DynBuf.cpp b/tools/gator/daemon/DynBuf.cpp
new file mode 100644
index 00000000000..690cbcb9429
--- /dev/null
+++ b/tools/gator/daemon/DynBuf.cpp
@@ -0,0 +1,139 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "DynBuf.h"
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdarg.h>
+#include <stdio.h>
+#include <unistd.h>
+
+#include "Logging.h"
+
+// Pick an aggressive size as buffer is primarily used for disk IO
+#define MIN_BUFFER_FREE (1 << 12)
+
+int DynBuf::resize(const size_t minCapacity) {
+	size_t scaledCapacity = 2 * capacity;
+	if (scaledCapacity < minCapacity) {
+		scaledCapacity = minCapacity;
+	}
+	if (scaledCapacity < 2 * MIN_BUFFER_FREE) {
+		scaledCapacity = 2 * MIN_BUFFER_FREE;
+	}
+	capacity = scaledCapacity;
+
+	buf = static_cast<char *>(realloc(buf, capacity));
+	if (buf == NULL) {
+		return -errno;
+	}
+
+	return 0;
+}
+
+bool DynBuf::read(const char *const path) {
+	int result = false;
+
+	const int fd = open(path, O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		logg->logMessage("open failed");
+		return false;
+	}
+
+	length = 0;
+
+	for (;;) {
+		const size_t minCapacity = length + MIN_BUFFER_FREE + 1;
+		if (capacity < minCapacity) {
+			if (resize(minCapacity) != 0) {
+				logg->logMessage("DynBuf::resize failed");
+				goto fail;
+			}
+		}
+
+		const ssize_t bytes = ::read(fd, buf + length, capacity - length - 1);
+		if (bytes < 0) {
+			logg->logMessage("read failed");
+			goto fail;
+		} else if (bytes == 0) {
+			break;
+		}
+		length += bytes;
+	}
+
+	buf[length] = '\0';
+	result = true;
+
+ fail:
+	close(fd);
+
+	return result;
+}
+
+int DynBuf::readlink(const char *const path) {
+	ssize_t bytes = MIN_BUFFER_FREE;
+
+	for (;;) {
+		if (static_cast<size_t>(bytes) >= capacity) {
+			const int err = resize(2 * bytes);
+			if (err != 0) {
+				return err;
+			}
+		}
+		bytes = ::readlink(path, buf, capacity);
+		if (bytes < 0) {
+			return -errno;
+		} else if (static_cast<size_t>(bytes) < capacity) {
+			break;
+		}
+	}
+
+	length = bytes;
+	buf[bytes] = '\0';
+
+	return 0;
+}
+
+bool DynBuf::printf(const char *format, ...) {
+	va_list ap;
+
+	if (capacity <= 0) {
+		if (resize(2 * MIN_BUFFER_FREE) != 0) {
+			logg->logMessage("DynBuf::resize failed");
+			return false;
+		}
+	}
+
+	va_start(ap, format);
+	int bytes = vsnprintf(buf, capacity, format, ap);
+	va_end(ap);
+	if (bytes < 0) {
+		logg->logMessage("fsnprintf failed");
+		return false;
+	}
+
+	if (static_cast<size_t>(bytes) > capacity) {
+		if (resize(bytes + 1) != 0) {
+			logg->logMessage("DynBuf::resize failed");
+			return false;
+		}
+
+		va_start(ap, format);
+		bytes = vsnprintf(buf, capacity, format, ap);
+		va_end(ap);
+		if (bytes < 0) {
+			logg->logMessage("fsnprintf failed");
+			return false;
+		}
+	}
+
+	length = bytes;
+
+	return true;
+}
diff --git a/tools/gator/daemon/DynBuf.h b/tools/gator/daemon/DynBuf.h
new file mode 100644
index 00000000000..da83cd65ca3
--- /dev/null
+++ b/tools/gator/daemon/DynBuf.h
@@ -0,0 +1,52 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef DYNBUF_H
+#define DYNBUF_H
+
+#include <stdlib.h>
+
+class DynBuf {
+public:
+	DynBuf() : capacity(0), length(0), buf(NULL) {}
+	~DynBuf() {
+		reset();
+	}
+
+	inline void reset() {
+		capacity = 0;
+		length = 0;
+		if (buf != NULL) {
+			free(buf);
+			buf = NULL;
+		}
+	}
+
+	bool read(const char *const path);
+	// On error instead of printing the error and returning false, this returns -errno
+	int readlink(const char *const path);
+	__attribute__ ((format(printf, 2, 3)))
+	bool printf(const char *format, ...);
+
+	size_t getLength() const { return length; }
+	const char *getBuf() const { return buf; }
+	char *getBuf() { return buf; }
+
+private:
+	int resize(const size_t minCapacity);
+
+	size_t capacity;
+	size_t length;
+	char *buf;
+
+	// Intentionally undefined
+	DynBuf(const DynBuf &);
+	DynBuf &operator=(const DynBuf &);
+};
+
+#endif // DYNBUF_H
diff --git a/tools/gator/daemon/EventsXML.cpp b/tools/gator/daemon/EventsXML.cpp
new file mode 100644
index 00000000000..d8044d8b8ab
--- /dev/null
+++ b/tools/gator/daemon/EventsXML.cpp
@@ -0,0 +1,231 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "EventsXML.h"
+
+#include "CapturedXML.h"
+#include "Logging.h"
+#include "OlyUtility.h"
+#include "SessionData.h"
+
+class XMLList {
+public:
+	XMLList(XMLList *const prev, mxml_node_t *const node) : mPrev(prev), mNode(node) {}
+
+	XMLList *getPrev() { return mPrev; }
+	mxml_node_t *getNode() const { return mNode; }
+	void setNode(mxml_node_t *const node) { mNode = node; }
+
+	static void free(XMLList *list) {
+		while (list != NULL) {
+			XMLList *prev = list->getPrev();
+			delete list;
+			list = prev;
+		}
+	}
+
+private:
+	XMLList *const mPrev;
+	mxml_node_t *mNode;
+
+	// Intentionally unimplemented
+	XMLList(const XMLList &);
+	XMLList &operator=(const XMLList &);
+};
+
+mxml_node_t *EventsXML::getTree() {
+#include "events_xml.h" // defines and initializes char events_xml[] and int events_xml_len
+	char path[PATH_MAX];
+	mxml_node_t *xml = NULL;
+	FILE *fl;
+
+	// Avoid unused variable warning
+	(void)events_xml_len;
+
+	// Load the provided or default events xml
+	if (gSessionData->mEventsXMLPath) {
+		strncpy(path, gSessionData->mEventsXMLPath, PATH_MAX);
+		fl = fopen_cloexec(path, "r");
+		if (fl) {
+			xml = mxmlLoadFile(NULL, fl, MXML_NO_CALLBACK);
+			fclose(fl);
+		}
+	}
+	if (xml == NULL) {
+		logg->logMessage("Unable to locate events.xml, using default");
+		xml = mxmlLoadString(NULL, (const char *)events_xml, MXML_NO_CALLBACK);
+	}
+
+	// Append additional events XML
+	if (gSessionData->mEventsXMLAppend) {
+		fl = fopen_cloexec(gSessionData->mEventsXMLAppend, "r");
+		if (fl == NULL) {
+			logg->logError("Unable to open additional events XML %s", gSessionData->mEventsXMLAppend);
+			handleException();
+		}
+		mxml_node_t *append = mxmlLoadFile(NULL, fl, MXML_NO_CALLBACK);
+		fclose(fl);
+
+		mxml_node_t *events = mxmlFindElement(xml, xml, "events", NULL, NULL, MXML_DESCEND);
+		if (!events) {
+			logg->logError("Unable to find <events> node in the events.xml, please ensure the first two lines of events XML starts with:\n"
+				       "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"
+				       "<events>");
+			handleException();
+		}
+
+		XMLList *categoryList = NULL;
+		XMLList *eventList = NULL;
+		{
+			// Make list of all categories in xml
+			mxml_node_t *node = xml;
+			while (true) {
+				node = mxmlFindElement(node, xml, "category", NULL, NULL, MXML_DESCEND);
+				if (node == NULL) {
+					break;
+				}
+				categoryList = new XMLList(categoryList, node);
+			}
+
+			// Make list of all events in xml
+			node = xml;
+			while (true) {
+				node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND);
+				if (node == NULL) {
+					break;
+				}
+				eventList = new XMLList(eventList, node);
+			}
+		}
+
+		// Handle events
+		for (mxml_node_t *node = mxmlFindElement(append, append, "event", NULL, NULL, MXML_DESCEND),
+		       *next = mxmlFindElement(node, append, "event", NULL, NULL, MXML_DESCEND);
+		     node != NULL;
+		     node = next, next = mxmlFindElement(node, append, "event", NULL, NULL, MXML_DESCEND)) {
+			const char *const category = mxmlElementGetAttr(mxmlGetParent(node), "name");
+			const char *const title = mxmlElementGetAttr(node, "title");
+			const char *const name = mxmlElementGetAttr(node, "name");
+			if (category == NULL || title == NULL || name == NULL) {
+				logg->logError("Not all event XML nodes have the required title and name and parent name attributes");
+				handleException();
+			}
+
+			// Replace any duplicate events
+			for (XMLList *event = eventList; event != NULL; event = event->getPrev()) {
+				const char *const category2 = mxmlElementGetAttr(mxmlGetParent(event->getNode()), "name");
+				const char *const title2 = mxmlElementGetAttr(event->getNode(), "title");
+				const char *const name2 = mxmlElementGetAttr(event->getNode(), "name");
+				if (category2 == NULL || title2 == NULL || name2 == NULL) {
+					logg->logError("Not all event XML nodes have the required title and name and parent name attributes");
+					handleException();
+				}
+
+				if (strcmp(category, category2) == 0 && strcmp(title, title2) == 0 && strcmp(name, name2) == 0) {
+					logg->logMessage("Replacing counter %s %s: %s", category, title, name);
+					mxml_node_t *parent = mxmlGetParent(event->getNode());
+					mxmlDelete(event->getNode());
+					mxmlAdd(parent, MXML_ADD_AFTER, MXML_ADD_TO_PARENT, node);
+					event->setNode(node);
+					break;
+				}
+			}
+		}
+
+		// Handle categories
+		for (mxml_node_t *node = strcmp(mxmlGetElement(append), "category") == 0 ? append : mxmlFindElement(append, append, "category", NULL, NULL, MXML_DESCEND),
+		       *next = mxmlFindElement(node, append, "category", NULL, NULL, MXML_DESCEND);
+		     node != NULL;
+		     node = next, next = mxmlFindElement(node, append, "category", NULL, NULL, MXML_DESCEND)) {
+			// After replacing duplicate events, a category may be empty
+			if (mxmlGetFirstChild(node) == NULL) {
+				continue;
+			}
+
+			const char *const name = mxmlElementGetAttr(node, "name");
+			if (name == NULL) {
+				logg->logError("Not all event XML categories have the required name attribute");
+				handleException();
+			}
+
+			// Merge identically named categories
+			bool merged = false;
+			for (XMLList *category = categoryList; category != NULL; category = category->getPrev()) {
+				const char *const name2 = mxmlElementGetAttr(category->getNode(), "name");
+				if (name2 == NULL) {
+					logg->logError("Not all event XML categories have the required name attribute");
+					handleException();
+				}
+
+				if (strcmp(name, name2) == 0) {
+					logg->logMessage("Merging category %s", name);
+					while (true) {
+						mxml_node_t *child = mxmlGetFirstChild(node);
+						if (child == NULL) {
+							break;
+						}
+						mxmlAdd(category->getNode(), MXML_ADD_AFTER, mxmlGetLastChild(category->getNode()), child);
+					}
+					merged = true;
+					break;
+				}
+			}
+
+			if (merged) {
+				continue;
+			}
+
+			// Add new categories
+			logg->logMessage("Appending category %s", name);
+			mxmlAdd(events, MXML_ADD_AFTER, mxmlGetLastChild(events), node);
+		}
+
+		XMLList::free(eventList);
+		XMLList::free(categoryList);
+
+		mxmlDelete(append);
+	}
+
+	return xml;
+}
+
+char *EventsXML::getXML() {
+	mxml_node_t *xml = getTree();
+
+	// Add dynamic events from the drivers
+	mxml_node_t *events = mxmlFindElement(xml, xml, "events", NULL, NULL, MXML_DESCEND);
+	if (!events) {
+		logg->logError("Unable to find <events> node in the events.xml, please ensure the first two lines of events XML are:\n"
+			       "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"
+			       "<events>");
+		handleException();
+	}
+	for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+		driver->writeEvents(events);
+	}
+
+	char *string = mxmlSaveAllocString(xml, mxmlWhitespaceCB);
+	mxmlDelete(xml);
+
+	return string;
+}
+
+void EventsXML::write(const char *path) {
+	char file[PATH_MAX];
+
+	// Set full path
+	snprintf(file, PATH_MAX, "%s/events.xml", path);
+
+	char *buf = getXML();
+	if (util->writeToDisk(file, buf) < 0) {
+		logg->logError("Error writing %s\nPlease verify the path.", file);
+		handleException();
+	}
+
+	free(buf);
+}
diff --git a/tools/gator/daemon/EventsXML.h b/tools/gator/daemon/EventsXML.h
new file mode 100644
index 00000000000..2b38fa4364e
--- /dev/null
+++ b/tools/gator/daemon/EventsXML.h
@@ -0,0 +1,28 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef EVENTS_XML
+#define EVENTS_XML
+
+#include "mxml/mxml.h"
+
+class EventsXML {
+public:
+	EventsXML() {}
+
+	mxml_node_t *getTree();
+	char *getXML();
+	void write(const char* path);
+
+private:
+	// Intentionally unimplemented
+	EventsXML(const EventsXML &);
+	EventsXML &operator=(const EventsXML &);
+};
+
+#endif // EVENTS_XML
diff --git a/tools/gator/daemon/ExternalDriver.cpp b/tools/gator/daemon/ExternalDriver.cpp
new file mode 100644
index 00000000000..c1b79835251
--- /dev/null
+++ b/tools/gator/daemon/ExternalDriver.cpp
@@ -0,0 +1,269 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "ExternalDriver.h"
+
+#include <stdio.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Logging.h"
+#include "OlySocket.h"
+#include "SessionData.h"
+
+static const char MALI_UTGARD_SETUP[] = "\0mali-utgard-setup";
+static const char SETUP_VERSION[] = "ANNOTATE_SETUP 1\n";
+static const size_t HEADER_SIZE = 1 + sizeof(uint32_t);
+
+#define HEADER_ERROR            0x80
+#define HEADER_ACK              0x81
+#define HEADER_REQUEST_COUNTERS 0x82
+#define HEADER_COUNTERS         0x83
+#define HEADER_ENABLE_COUNTERS  0x84
+#define HEADER_START            0x85
+
+static uint32_t readLEInt(char *const buf)
+{
+	size_t i;
+	uint32_t v;
+
+	v = 0;
+	for (i = 0; i < sizeof(v); ++i)
+		v |= (uint32_t)buf[i] << 8*i;
+
+	return v;
+}
+
+static int readPackedInt(char *const buf, const size_t bufSize, size_t *const pos, uint64_t *const l)
+{
+	uint8_t shift = 0;
+	uint8_t b = ~0;
+
+	*l = 0;
+	while ((b & 0x80) != 0) {
+		if (*pos >= bufSize) {
+			return -1;
+		}
+		b = buf[*pos];
+		*pos += 1;
+		*l |= (uint64_t)(b & 0x7f) << shift;
+		shift += 7;
+	}
+
+	if (shift < 8*sizeof(*l) && (b & 0x40) != 0) {
+		*l |= -(1 << shift);
+	}
+
+	return 0;
+}
+
+class ExternalCounter : public DriverCounter {
+public:
+	ExternalCounter(DriverCounter *next, const char *name, int cores) : DriverCounter(next, name), mCores(cores), mEvent(-1) {}
+
+	~ExternalCounter() {
+	}
+
+	int getCores() const { return mCores; }
+	void setEvent(const int event) { mEvent = event; }
+	int getEvent() const { return mEvent; }
+
+private:
+	const int mCores;
+	int mEvent;
+
+	// Intentionally undefined
+	ExternalCounter(const ExternalCounter &);
+	ExternalCounter &operator=(const ExternalCounter &);
+};
+
+ExternalDriver::ExternalDriver() : mUds(-1), mQueried(false), mStarted(false) {
+}
+
+bool ExternalDriver::connect() const {
+	if (mUds < 0) {
+		mUds = OlySocket::connect(MALI_UTGARD_SETUP, sizeof(MALI_UTGARD_SETUP));
+		if (mUds >= 0 && !writeAll(mUds, SETUP_VERSION, sizeof(SETUP_VERSION) - 1)) {
+			logg->logError("Unable to send setup version");
+			handleException();
+		}
+	}
+	return mUds >= 0;
+}
+
+void ExternalDriver::disconnect() {
+	if (mUds >= 0) {
+		close(mUds);
+		mUds = -1;
+		mStarted = false;
+	}
+}
+
+void ExternalDriver::query() const {
+	if (mQueried) {
+		return;
+	}
+	// Only try once even if it fails otherwise not all the possible counters may be shown
+	mQueried = true;
+
+	char *const buf = gSessionData->mSharedData->mMaliUtgardCounters;
+	const size_t bufSize = sizeof(gSessionData->mSharedData->mMaliUtgardCounters);
+	size_t size = 0;
+
+	if (!connect()) {
+		size = gSessionData->mSharedData->mMaliUtgardCountersSize;
+		logg->logMessage("Unable to connect, using cached version; size: %zi", size);
+	} else {
+		gSessionData->mSharedData->mMaliUtgardCountersSize = 0;
+
+		buf[0] = HEADER_REQUEST_COUNTERS;
+		size_t pos = HEADER_SIZE;
+		Buffer::writeLEInt((unsigned char *)(buf + 1), pos);
+		if (!writeAll(mUds, buf, pos)) {
+			logg->logError("Unable to send request counters message");
+			handleException();
+		}
+
+		if (!readAll(mUds, buf, HEADER_SIZE) || buf[0] != (char)HEADER_COUNTERS) {
+			logg->logError("Unable to read request counters response header");
+			handleException();
+		}
+		size = readLEInt(buf + 1);
+		if (size > bufSize || !readAll(mUds, buf, size - HEADER_SIZE)) {
+			logg->logError("Unable to read request counters response");
+			handleException();
+		}
+
+		size -= HEADER_SIZE;
+		gSessionData->mSharedData->mMaliUtgardCountersSize = size;
+		logg->logMessage("Requested counters; size: %zi", size);
+	}
+
+	size_t pos = 0;
+	while (pos < size) {
+		size_t begin = pos;
+		char *name = NULL;
+		uint64_t cores = -1;
+		while (pos < size && buf[pos] != '\0') {
+			++pos;
+		}
+		if (pos > begin) {
+			name = strndup(buf + begin, pos - begin);
+		}
+		if (pos < size && buf[pos] == '\0') {
+			++pos;
+		}
+		;
+		if (name != NULL && readPackedInt(buf, bufSize, &pos, &cores) == 0) {
+			// Cheat so that this can be 'const'
+			((ExternalDriver *)(this))->setCounters(new ExternalCounter(getCounters(), name, cores));
+		}
+	}
+
+	if (pos != size) {
+		logg->logError("Unable to parse request counters response");
+		handleException();
+	}
+}
+
+void ExternalDriver::start() {
+	if (!connect()) {
+		return;
+	}
+
+	if (mStarted) {
+		return;
+	}
+	// Only start once
+	mStarted = true;
+
+	char buf[1<<12];
+	int pos;
+
+	buf[0] = HEADER_ENABLE_COUNTERS;
+	pos = HEADER_SIZE;
+	for (ExternalCounter *counter = static_cast<ExternalCounter *>(getCounters()); counter != NULL; counter = static_cast<ExternalCounter *>(counter->getNext())) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		size_t nameLen = strlen(counter->getName());
+		if (pos + nameLen + 1 + 2*Buffer::MAXSIZE_PACK32 > sizeof(buf)) {
+			logg->logError("Unable to enable counters, message is too large");
+			handleException();
+		}
+		memcpy(buf + pos, counter->getName(), nameLen + 1);
+		pos += nameLen + 1;
+		Buffer::packInt(buf, sizeof(buf), pos, counter->getEvent());
+		Buffer::packInt(buf, sizeof(buf), pos, counter->getKey());
+	}
+	Buffer::writeLEInt((unsigned char *)(buf + 1), pos);
+	if (!writeAll(mUds, buf, pos)) {
+		logg->logError("Unable to send enable counters message");
+		handleException();
+	}
+
+	size_t size = 0;
+	if (!readAll(mUds, buf, HEADER_SIZE) || buf[0] != (char)HEADER_ACK) {
+		logg->logError("Unable to read enable counters response header");
+		handleException();
+	}
+	size = readLEInt(buf + 1);
+	if (size != HEADER_SIZE) {
+		logg->logError("Unable to parse enable counters response");
+		handleException();
+	}
+
+	buf[0] = HEADER_START;
+	pos = HEADER_SIZE;
+	// ns/sec / samples/sec = ns/sample
+	// For sample rate of none, sample every 100ms
+	Buffer::packInt(buf, sizeof(buf), pos, NS_PER_S / (gSessionData->mSampleRate == 0 ? 10 : gSessionData->mSampleRate));
+	Buffer::packInt(buf, sizeof(buf), pos, gSessionData->mLiveRate);
+	Buffer::writeLEInt((unsigned char *)(buf + 1), pos);
+	if (!writeAll(mUds, buf, pos)) {
+		logg->logError("Unable to send start message");
+		handleException();
+	}
+
+	size = 0;
+	if (!readAll(mUds, buf, HEADER_SIZE) || buf[0] != (char)HEADER_ACK) {
+		logg->logError("Unable to read start response header");
+		handleException();
+	}
+	size = readLEInt(buf + 1);
+	if (size != HEADER_SIZE) {
+		logg->logError("Unable to parse start response");
+		handleException();
+	}
+}
+
+bool ExternalDriver::claimCounter(const Counter &counter) const {
+	query();
+	return super::claimCounter(counter);
+}
+
+void ExternalDriver::setupCounter(Counter &counter) {
+	ExternalCounter *const externalCounter = static_cast<ExternalCounter *>(findCounter(counter));
+	if (externalCounter == NULL) {
+		counter.setEnabled(false);
+		return;
+	}
+	externalCounter->setEnabled(true);
+	counter.setKey(externalCounter->getKey());
+	if (counter.getEvent() != -1) {
+		externalCounter->setEvent(counter.getEvent());
+	}
+	if (externalCounter->getCores() > 0) {
+		counter.setCores(externalCounter->getCores());
+	}
+}
+
+void ExternalDriver::resetCounters() {
+	query();
+	super::resetCounters();
+}
diff --git a/tools/gator/daemon/ExternalDriver.h b/tools/gator/daemon/ExternalDriver.h
new file mode 100644
index 00000000000..d88f9e125f9
--- /dev/null
+++ b/tools/gator/daemon/ExternalDriver.h
@@ -0,0 +1,41 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef EXTERNALDRIVER_H
+#define EXTERNALDRIVER_H
+
+#include "Driver.h"
+
+class ExternalDriver : public SimpleDriver {
+public:
+	ExternalDriver();
+
+	bool claimCounter(const Counter &counter) const;
+	void resetCounters();
+	void setupCounter(Counter &counter);
+
+	void start();
+
+	void disconnect();
+
+private:
+	typedef SimpleDriver super;
+
+	bool connect() const;
+	void query() const;
+
+	mutable int mUds;
+	mutable bool mQueried;
+	bool mStarted;
+
+	// Intentionally unimplemented
+	ExternalDriver(const ExternalDriver &);
+	ExternalDriver &operator=(const ExternalDriver &);
+};
+
+#endif // EXTERNALDRIVER_H
diff --git a/tools/gator/daemon/ExternalSource.cpp b/tools/gator/daemon/ExternalSource.cpp
new file mode 100644
index 00000000000..e87fb9ef02b
--- /dev/null
+++ b/tools/gator/daemon/ExternalSource.cpp
@@ -0,0 +1,321 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "ExternalSource.h"
+
+#include <fcntl.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+#include "Child.h"
+#include "DriverSource.h"
+#include "Logging.h"
+#include "OlySocket.h"
+#include "SessionData.h"
+
+extern Child *child;
+
+static const char STREAMLINE_ANNOTATE[] = "\0streamline-annotate";
+static const char MALI_VIDEO[] = "\0mali-video";
+static const char MALI_VIDEO_STARTUP[] = "\0mali-video-startup";
+static const char MALI_VIDEO_V1[] = "MALI_VIDEO 1\n";
+static const char MALI_GRAPHICS[] = "\0mali_thirdparty_server";
+static const char MALI_GRAPHICS_STARTUP[] = "\0mali_thirdparty_client";
+static const char MALI_GRAPHICS_V1[] = "MALI_GRAPHICS 1\n";
+static const char MALI_UTGARD_STARTUP[] = "\0mali-utgard-startup";
+static const char FTRACE_V1[] = "FTRACE 1\n";
+
+ExternalSource::ExternalSource(sem_t *senderSem) : mBuffer(0, FRAME_EXTERNAL, 128*1024, senderSem), mMonitor(), mMveStartupUds(MALI_VIDEO_STARTUP, sizeof(MALI_VIDEO_STARTUP)), mMaliStartupUds(MALI_GRAPHICS_STARTUP, sizeof(MALI_GRAPHICS_STARTUP)), mUtgardStartupUds(MALI_UTGARD_STARTUP, sizeof(MALI_UTGARD_STARTUP)), mAnnotate(8083), mAnnotateUds(STREAMLINE_ANNOTATE, sizeof(STREAMLINE_ANNOTATE), true), mInterruptFd(-1), mMaliUds(-1), mMveUds(-1), mFtraceFd(-1) {
+	sem_init(&mBufferSem, 0, 0);
+}
+
+ExternalSource::~ExternalSource() {
+}
+
+void ExternalSource::waitFor(const int bytes) {
+	while (mBuffer.bytesAvailable() <= bytes) {
+		if (gSessionData->mOneShot && gSessionData->mSessionIsActive) {
+			logg->logMessage("One shot (external)");
+			child->endSession();
+		}
+		sem_wait(&mBufferSem);
+	}
+}
+
+void ExternalSource::configureConnection(const int fd, const char *const handshake, size_t size) {
+	if (!setNonblock(fd)) {
+		logg->logError("Unable to set nonblock on fh");
+		handleException();
+	}
+
+	if (!mMonitor.add(fd)) {
+		logg->logError("Unable to add fh to monitor");
+		handleException();
+	}
+
+	// Write the handshake to the circular buffer
+	waitFor(Buffer::MAXSIZE_PACK32 + size - 1);
+	mBuffer.packInt(fd);
+	mBuffer.writeBytes(handshake, size - 1);
+	mBuffer.commit(1, true);
+}
+
+bool ExternalSource::connectMali() {
+	mMaliUds = OlySocket::connect(MALI_GRAPHICS, sizeof(MALI_GRAPHICS));
+	if (mMaliUds < 0) {
+		return false;
+	}
+
+	configureConnection(mMaliUds, MALI_GRAPHICS_V1, sizeof(MALI_GRAPHICS_V1));
+
+	return true;
+}
+
+bool ExternalSource::connectMve() {
+	if (!gSessionData->mMaliVideo.countersEnabled()) {
+		return true;
+	}
+
+	mMveUds = OlySocket::connect(MALI_VIDEO, sizeof(MALI_VIDEO));
+	if (mMveUds < 0) {
+		return false;
+	}
+
+	if (!gSessionData->mMaliVideo.start(mMveUds)) {
+		return false;
+	}
+
+	configureConnection(mMveUds, MALI_VIDEO_V1, sizeof(MALI_VIDEO_V1));
+
+	return true;
+}
+
+void ExternalSource::connectFtrace() {
+	if (!gSessionData->mFtraceDriver.isSupported()) {
+		return;
+	}
+
+	gSessionData->mFtraceDriver.prepare();
+
+	mFtraceFd = open(TRACING_PATH "/trace_pipe", O_RDONLY | O_CLOEXEC);
+	if (mFtraceFd < 0) {
+		logg->logError("Unable to open trace_pipe");
+		handleException();
+	}
+
+	configureConnection(mFtraceFd, FTRACE_V1, sizeof(FTRACE_V1));
+}
+
+bool ExternalSource::prepare() {
+	if (!mMonitor.init() ||
+			!setNonblock(mMveStartupUds.getFd()) || !mMonitor.add(mMveStartupUds.getFd()) ||
+			!setNonblock(mMaliStartupUds.getFd()) || !mMonitor.add(mMaliStartupUds.getFd()) ||
+			!setNonblock(mUtgardStartupUds.getFd()) || !mMonitor.add(mUtgardStartupUds.getFd()) ||
+			!setNonblock(mAnnotate.getFd()) || !mMonitor.add(mAnnotate.getFd()) ||
+			!setNonblock(mAnnotateUds.getFd()) || !mMonitor.add(mAnnotateUds.getFd()) ||
+			false) {
+		return false;
+	}
+
+	connectMali();
+	connectMve();
+	connectFtrace();
+	gSessionData->mExternalDriver.start();
+
+	return true;
+}
+
+void ExternalSource::run() {
+	int pipefd[2];
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-external", 0, 0, 0);
+
+	if (pipe_cloexec(pipefd) != 0) {
+		logg->logError("pipe failed");
+		handleException();
+	}
+	mInterruptFd = pipefd[1];
+
+	if (!mMonitor.add(pipefd[0])) {
+		logg->logError("Monitor::add failed");
+		handleException();
+	}
+
+	// Notify annotate clients to retry connecting to gatord
+	uint64_t val = 1;
+	if (::write(gSessionData->mAnnotateStart, &val, sizeof(val)) != sizeof(val)) {
+		logg->logMessage("Writing to annotate pipe failed");
+	}
+
+	if (mFtraceFd >= 0) {
+		gSessionData->mAtraceDriver.start();
+
+		if (DriverSource::writeDriver(TRACING_PATH "/tracing_on", "1") != 0) {
+			logg->logError("Unable to turn ftrace on");
+			handleException();
+		}
+	}
+
+	// Wait until monotonicStarted is set before sending data
+	int64_t monotonicStarted = 0;
+	while (monotonicStarted <= 0 && gSessionData->mSessionIsActive) {
+		usleep(10);
+
+		if (gSessionData->mPerf.isSetup()) {
+			monotonicStarted = gSessionData->mMonotonicStarted;
+		} else {
+			if (DriverSource::readInt64Driver("/dev/gator/started", &monotonicStarted) == -1) {
+				logg->logError("Error reading gator driver start time");
+				handleException();
+			}
+		}
+	}
+
+	while (gSessionData->mSessionIsActive) {
+		struct epoll_event events[16];
+		// Clear any pending sem posts
+		while (sem_trywait(&mBufferSem) == 0);
+		int ready = mMonitor.wait(events, ARRAY_LENGTH(events), -1);
+		if (ready < 0) {
+			logg->logError("Monitor::wait failed");
+			handleException();
+		}
+
+		const uint64_t currTime = getTime() - gSessionData->mMonotonicStarted;
+
+		for (int i = 0; i < ready; ++i) {
+			const int fd = events[i].data.fd;
+			if (fd == mMveStartupUds.getFd()) {
+				// Mali Video Engine says it's alive
+				int client = mMveStartupUds.acceptConnection();
+				// Don't read from this connection, establish a new connection to Mali-V500
+				close(client);
+				if (!connectMve()) {
+					logg->logError("Unable to configure incoming Mali video connection");
+					handleException();
+				}
+			} else if (fd == mMaliStartupUds.getFd()) {
+				// Mali Graphics says it's alive
+				int client = mMaliStartupUds.acceptConnection();
+				// Don't read from this connection, establish a new connection to Mali Graphics
+				close(client);
+				if (!connectMali()) {
+					logg->logError("Unable to configure incoming Mali graphics connection");
+					handleException();
+				}
+			} else if (fd == mUtgardStartupUds.getFd()) {
+				// Mali Utgard says it's alive
+				int client = mUtgardStartupUds.acceptConnection();
+				// Don't read from this connection, configure utgard and expect them to reconnect with annotations
+				close(client);
+				gSessionData->mExternalDriver.disconnect();
+				gSessionData->mExternalDriver.start();
+			} else if (fd == mAnnotate.getFd()) {
+				int client = mAnnotate.acceptConnection();
+				if (!setNonblock(client) || !mMonitor.add(client)) {
+					logg->logError("Unable to set socket options on incoming annotation connection");
+					handleException();
+				}
+			} else if (fd == mAnnotateUds.getFd()) {
+				int client = mAnnotateUds.acceptConnection();
+				if (!setNonblock(client) || !mMonitor.add(client)) {
+					logg->logError("Unable to set socket options on incoming annotation connection");
+					handleException();
+				}
+			} else if (fd == pipefd[0]) {
+				// Means interrupt has been called and mSessionIsActive should be reread
+			} else {
+				/* This can result in some starvation if there are multiple
+				 * threads which are annotating heavily, but it is not
+				 * recommended that threads annotate that much as it can also
+				 * starve out the gator data.
+				 */
+				while (gSessionData->mSessionIsActive) {
+					// Wait until there is enough room for the fd, two headers and two ints
+					waitFor(7*Buffer::MAXSIZE_PACK32 + 2*sizeof(uint32_t));
+					mBuffer.packInt(fd);
+					const int contiguous = mBuffer.contiguousSpaceAvailable();
+					const int bytes = read(fd, mBuffer.getWritePos(), contiguous);
+					if (bytes < 0) {
+						if (errno == EAGAIN) {
+							// Nothing left to read
+							mBuffer.commit(currTime, true);
+							break;
+						}
+						// Something else failed, close the socket
+						mBuffer.commit(currTime, true);
+						mBuffer.packInt(-1);
+						mBuffer.packInt(fd);
+						// Here and other commits, always force-flush the buffer as this frame don't work like others
+						mBuffer.commit(currTime, true);
+						close(fd);
+						break;
+					} else if (bytes == 0) {
+						// The other side is closed
+						mBuffer.commit(currTime, true);
+						mBuffer.packInt(-1);
+						mBuffer.packInt(fd);
+						mBuffer.commit(currTime, true);
+						close(fd);
+						break;
+					}
+
+					mBuffer.advanceWrite(bytes);
+					mBuffer.commit(currTime, true);
+
+					// Short reads also mean nothing is left to read
+					if (bytes < contiguous) {
+						break;
+					}
+				}
+			}
+		}
+	}
+
+	mBuffer.setDone();
+
+	if (mFtraceFd >= 0) {
+		gSessionData->mFtraceDriver.stop();
+		gSessionData->mAtraceDriver.stop();
+		close(mFtraceFd);
+	}
+
+	if (mMveUds >= 0) {
+		gSessionData->mMaliVideo.stop(mMveUds);
+	}
+
+	mInterruptFd = -1;
+	close(pipefd[0]);
+	close(pipefd[1]);
+}
+
+void ExternalSource::interrupt() {
+	if (mInterruptFd >= 0) {
+		int8_t c = 0;
+		// Write to the pipe to wake the monitor which will cause mSessionIsActive to be reread
+		if (::write(mInterruptFd, &c, sizeof(c)) != sizeof(c)) {
+			logg->logError("write failed");
+			handleException();
+		}
+	}
+}
+
+bool ExternalSource::isDone() {
+	return mBuffer.isDone();
+}
+
+void ExternalSource::write(Sender *sender) {
+	// Don't send external data until the summary packet is sent so that monotonic delta is available
+	if (!gSessionData->mSentSummary) {
+		return;
+	}
+	if (!mBuffer.isDone()) {
+		mBuffer.write(sender);
+		sem_post(&mBufferSem);
+	}
+}
diff --git a/tools/gator/daemon/ExternalSource.h b/tools/gator/daemon/ExternalSource.h
new file mode 100644
index 00000000000..69d16afeb76
--- /dev/null
+++ b/tools/gator/daemon/ExternalSource.h
@@ -0,0 +1,57 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef EXTERNALSOURCE_H
+#define EXTERNALSOURCE_H
+
+#include <semaphore.h>
+
+#include "Buffer.h"
+#include "Monitor.h"
+#include "OlySocket.h"
+#include "Source.h"
+
+// Counters from external sources like graphics drivers and annotations
+class ExternalSource : public Source {
+public:
+	ExternalSource(sem_t *senderSem);
+	~ExternalSource();
+
+	bool prepare();
+	void run();
+	void interrupt();
+
+	bool isDone();
+	void write(Sender *sender);
+
+private:
+	void waitFor(const int bytes);
+	void configureConnection(const int fd, const char *const handshake, size_t size);
+	bool connectMali();
+	bool connectMve();
+	void connectFtrace();
+
+	sem_t mBufferSem;
+	Buffer mBuffer;
+	Monitor mMonitor;
+	OlyServerSocket mMveStartupUds;
+	OlyServerSocket mMaliStartupUds;
+	OlyServerSocket mUtgardStartupUds;
+	OlyServerSocket mAnnotate;
+	OlyServerSocket mAnnotateUds;
+	int mInterruptFd;
+	int mMaliUds;
+	int mMveUds;
+	int mFtraceFd;
+
+	// Intentionally unimplemented
+	ExternalSource(const ExternalSource &);
+	ExternalSource &operator=(const ExternalSource &);
+};
+
+#endif // EXTERNALSOURCE_H
diff --git a/tools/gator/daemon/FSDriver.cpp b/tools/gator/daemon/FSDriver.cpp
new file mode 100644
index 00000000000..afac9dfb676
--- /dev/null
+++ b/tools/gator/daemon/FSDriver.cpp
@@ -0,0 +1,156 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "FSDriver.h"
+
+#include <fcntl.h>
+#include <regex.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "DriverSource.h"
+#include "Logging.h"
+
+class FSCounter : public DriverCounter {
+public:
+	FSCounter(DriverCounter *next, char *name, char *path, const char *regex);
+	~FSCounter();
+
+	const char *getPath() const { return mPath; }
+
+	int64_t read();
+
+private:
+	char *const mPath;
+	regex_t mReg;
+	bool mUseRegex;
+
+	// Intentionally unimplemented
+	FSCounter(const FSCounter &);
+	FSCounter &operator=(const FSCounter &);
+};
+
+FSCounter::FSCounter(DriverCounter *next, char *name, char *path, const char *regex) : DriverCounter(next, name), mPath(path), mUseRegex(regex != NULL) {
+	if (mUseRegex) {
+		int result = regcomp(&mReg, regex, REG_EXTENDED);
+		if (result != 0) {
+			char buf[128];
+			regerror(result, &mReg, buf, sizeof(buf));
+			logg->logError("Invalid regex '%s': %s", regex, buf);
+			handleException();
+		}
+	}
+}
+
+FSCounter::~FSCounter() {
+	free(mPath);
+	if (mUseRegex) {
+		regfree(&mReg);
+	}
+}
+
+int64_t FSCounter::read() {
+	int64_t value;
+	if (mUseRegex) {
+		char buf[4096];
+		size_t pos = 0;
+		const int fd = open(mPath, O_RDONLY | O_CLOEXEC);
+		if (fd < 0) {
+			goto fail;
+		}
+		while (pos < sizeof(buf) - 1) {
+			const ssize_t bytes = ::read(fd, buf + pos, sizeof(buf) - pos - 1);
+			if (bytes < 0) {
+				goto fail;
+			} else if (bytes == 0) {
+				break;
+			}
+			pos += bytes;
+		}
+		close(fd);
+		buf[pos] = '\0';
+
+		regmatch_t match[2];
+		int result = regexec(&mReg, buf, 2, match, 0);
+		if (result != 0) {
+			// No match
+			return 0;
+		}
+
+		if (match[1].rm_so < 0) {
+			value = 1;
+		} else {
+			errno = 0;
+			value = strtoll(buf + match[1].rm_so, NULL, 0);
+			if (errno != 0) {
+				logg->logError("Parsing %s failed: %s", mPath, strerror(errno));
+				handleException();
+			}
+		}
+	} else {
+		if (DriverSource::readInt64Driver(mPath, &value) != 0) {
+			goto fail;
+		}
+	}
+	return value;
+
+ fail:
+	logg->logError("Unable to read %s", mPath);
+	handleException();
+}
+
+FSDriver::FSDriver() {
+}
+
+FSDriver::~FSDriver() {
+}
+
+void FSDriver::readEvents(mxml_node_t *const xml) {
+	mxml_node_t *node = xml;
+	while (true) {
+		node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND);
+		if (node == NULL) {
+			break;
+		}
+		const char *counter = mxmlElementGetAttr(node, "counter");
+		if (counter == NULL) {
+			continue;
+		}
+
+		if (counter[0] == '/') {
+			logg->logError("Old style filesystem counter (%s) detected, please create a new unique counter value and move the filename into the path attribute, see events-Filesystem.xml for examples", counter);
+			handleException();
+		}
+
+		if (strncmp(counter, "filesystem_", 11) != 0) {
+			continue;
+		}
+
+		const char *path = mxmlElementGetAttr(node, "path");
+		if (path == NULL) {
+			logg->logError("The filesystem counter %s is missing the required path attribute", counter);
+			handleException();
+		}
+		const char *regex = mxmlElementGetAttr(node, "regex");
+		setCounters(new FSCounter(getCounters(), strdup(counter), strdup(path), regex));
+	}
+}
+
+int FSDriver::writeCounters(mxml_node_t *root) const {
+	int count = 0;
+	for (FSCounter *counter = static_cast<FSCounter *>(getCounters()); counter != NULL; counter = static_cast<FSCounter *>(counter->getNext())) {
+		if (access(counter->getPath(), R_OK) == 0) {
+			mxml_node_t *node = mxmlNewElement(root, "counter");
+			mxmlElementSetAttr(node, "name", counter->getName());
+			++count;
+		}
+	}
+
+	return count;
+}
diff --git a/tools/gator/daemon/FSDriver.h b/tools/gator/daemon/FSDriver.h
new file mode 100644
index 00000000000..63a4e90a2b4
--- /dev/null
+++ b/tools/gator/daemon/FSDriver.h
@@ -0,0 +1,29 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef FSDRIVER_H
+#define FSDRIVER_H
+
+#include "Driver.h"
+
+class FSDriver : public PolledDriver {
+public:
+	FSDriver();
+	~FSDriver();
+
+	void readEvents(mxml_node_t *const xml);
+
+	int writeCounters(mxml_node_t *root) const;
+
+private:
+	// Intentionally unimplemented
+	FSDriver(const FSDriver &);
+	FSDriver &operator=(const FSDriver &);
+};
+
+#endif // FSDRIVER_H
diff --git a/tools/gator/daemon/Fifo.cpp b/tools/gator/daemon/Fifo.cpp
new file mode 100644
index 00000000000..8d3b9ff8d38
--- /dev/null
+++ b/tools/gator/daemon/Fifo.cpp
@@ -0,0 +1,127 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Fifo.h"
+
+#include <stdlib.h>
+
+#include "Logging.h"
+
+// bufferSize is the amount of data to be filled
+// singleBufferSize is the maximum size that may be filled during a single write
+// (bufferSize + singleBufferSize) will be allocated
+Fifo::Fifo(int singleBufferSize, int bufferSize, sem_t* readerSem) {
+  mWrite = mRead = mReadCommit = mRaggedEnd = 0;
+  mWrapThreshold = bufferSize;
+  mSingleBufferSize = singleBufferSize;
+  mReaderSem = readerSem;
+  mBuffer = (char*)malloc(bufferSize + singleBufferSize);
+  mEnd = false;
+
+  if (mBuffer == NULL) {
+    logg->logError("failed to allocate %d bytes", bufferSize + singleBufferSize);
+    handleException();
+  }
+
+  if (sem_init(&mWaitForSpaceSem, 0, 0)) {
+    logg->logError("sem_init() failed");
+    handleException();
+  }
+}
+
+Fifo::~Fifo() {
+  free(mBuffer);
+  sem_destroy(&mWaitForSpaceSem);
+}
+
+int Fifo::numBytesFilled() const {
+  return mWrite - mRead + mRaggedEnd;
+}
+
+char* Fifo::start() const {
+  return mBuffer;
+}
+
+bool Fifo::isEmpty() const {
+  return mRead == mWrite && mRaggedEnd == 0;
+}
+
+bool Fifo::isFull() const {
+  return willFill(0);
+}
+
+// Determines if the buffer will fill assuming 'additional' bytes will be added to the buffer
+// 'full' means there is less than singleBufferSize bytes available contiguously; it does not mean there are zero bytes available
+bool Fifo::willFill(int additional) const {
+  if (mWrite > mRead) {
+    if (numBytesFilled() + additional < mWrapThreshold) {
+      return false;
+    }
+  } else {
+    if (numBytesFilled() + additional < mWrapThreshold - mSingleBufferSize) {
+      return false;
+    }
+  }
+  return true;
+}
+
+// This function will stall until contiguous singleBufferSize bytes are available
+char* Fifo::write(int length) {
+  if (length <= 0) {
+    length = 0;
+    mEnd = true;
+  }
+
+  // update the write pointer
+  mWrite += length;
+
+  // handle the wrap-around
+  if (mWrite >= mWrapThreshold) {
+    mRaggedEnd = mWrite;
+    mWrite = 0;
+  }
+
+  // send a notification that data is ready
+  sem_post(mReaderSem);
+
+  // wait for space
+  while (isFull()) {
+    sem_wait(&mWaitForSpaceSem);
+  }
+
+  return &mBuffer[mWrite];
+}
+
+void Fifo::release() {
+  // update the read pointer now that the data has been handled
+  mRead = mReadCommit;
+
+  // handle the wrap-around
+  if (mRead >= mWrapThreshold) {
+    mRaggedEnd = mRead = mReadCommit = 0;
+  }
+
+  // send a notification that data is free (space is available)
+  sem_post(&mWaitForSpaceSem);
+}
+
+// This function will return null if no data is available
+char* Fifo::read(int *const length) {
+  // wait for data
+  if (isEmpty() && !mEnd) {
+    return NULL;
+  }
+
+  // obtain the length
+  do {
+    mReadCommit = mRaggedEnd ? mRaggedEnd : mWrite;
+    *length = mReadCommit - mRead;
+  } while (*length < 0); // plugs race condition without using semaphores
+
+  return &mBuffer[mRead];
+}
diff --git a/tools/gator/daemon/Fifo.h b/tools/gator/daemon/Fifo.h
new file mode 100644
index 00000000000..01fa11b2f2c
--- /dev/null
+++ b/tools/gator/daemon/Fifo.h
@@ -0,0 +1,48 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __FIFO_H__
+#define __FIFO_H__
+
+#ifdef WIN32
+#include <windows.h>
+#define sem_t HANDLE
+#define sem_init(sem, pshared, value) ((*(sem) = CreateSemaphore(NULL, value, LONG_MAX, NULL)) == NULL)
+#define sem_wait(sem) WaitForSingleObject(*(sem), INFINITE)
+#define sem_post(sem) ReleaseSemaphore(*(sem), 1, NULL)
+#define sem_destroy(sem) CloseHandle(*(sem))
+#else
+#include <semaphore.h>
+#endif
+
+class Fifo {
+public:
+  Fifo(int singleBufferSize, int totalBufferSize, sem_t* readerSem);
+  ~Fifo();
+  int numBytesFilled() const;
+  bool isEmpty() const;
+  bool isFull() const;
+  bool willFill(int additional) const;
+  char* start() const;
+  char* write(int length);
+  void release();
+  char* read(int *const length);
+
+private:
+  int mSingleBufferSize, mWrite, mRead, mReadCommit, mRaggedEnd, mWrapThreshold;
+  sem_t mWaitForSpaceSem;
+  sem_t* mReaderSem;
+  char* mBuffer;
+  bool mEnd;
+
+  // Intentionally unimplemented
+  Fifo(const Fifo &);
+  Fifo &operator=(const Fifo &);
+};
+
+#endif //__FIFO_H__
diff --git a/tools/gator/daemon/FtraceDriver.cpp b/tools/gator/daemon/FtraceDriver.cpp
new file mode 100644
index 00000000000..7c57cfcbb1e
--- /dev/null
+++ b/tools/gator/daemon/FtraceDriver.cpp
@@ -0,0 +1,196 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "FtraceDriver.h"
+
+#include <regex.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+
+#include "Config.h"
+#include "DriverSource.h"
+#include "Logging.h"
+#include "SessionData.h"
+#include "Setup.h"
+
+class FtraceCounter : public DriverCounter {
+public:
+	FtraceCounter(DriverCounter *next, char *name, const char *enable);
+	~FtraceCounter();
+
+	void prepare();
+	void stop();
+
+private:
+	char *const mEnable;
+	int mWasEnabled;
+
+	// Intentionally unimplemented
+	FtraceCounter(const FtraceCounter &);
+	FtraceCounter &operator=(const FtraceCounter &);
+};
+
+FtraceCounter::FtraceCounter(DriverCounter *next, char *name, const char *enable) : DriverCounter(next, name), mEnable(enable == NULL ? NULL : strdup(enable)) {
+}
+
+FtraceCounter::~FtraceCounter() {
+	if (mEnable != NULL) {
+		free(mEnable);
+	}
+}
+
+void FtraceCounter::prepare() {
+	if (mEnable == NULL) {
+		return;
+	}
+
+	char buf[1<<10];
+	snprintf(buf, sizeof(buf), EVENTS_PATH "/%s/enable", mEnable);
+	if ((DriverSource::readIntDriver(buf, &mWasEnabled) != 0) ||
+			(DriverSource::writeDriver(buf, 1) != 0)) {
+		logg->logError("Unable to read or write to %s", buf);
+		handleException();
+	}
+}
+
+void FtraceCounter::stop() {
+	if (mEnable == NULL) {
+		return;
+	}
+
+	char buf[1<<10];
+	snprintf(buf, sizeof(buf), EVENTS_PATH "/%s/enable", mEnable);
+	DriverSource::writeDriver(buf, mWasEnabled);
+}
+
+FtraceDriver::FtraceDriver() : mValues(NULL), mSupported(false), mTracingOn(0) {
+}
+
+FtraceDriver::~FtraceDriver() {
+	delete [] mValues;
+}
+
+void FtraceDriver::readEvents(mxml_node_t *const xml) {
+	// Check the kernel version
+	int release[3];
+	if (!getLinuxVersion(release)) {
+		logg->logError("getLinuxVersion failed");
+		handleException();
+	}
+
+	// The perf clock was added in 3.10
+	if (KERNEL_VERSION(release[0], release[1], release[2]) < KERNEL_VERSION(3, 10, 0)) {
+		mSupported = false;
+		logg->logMessage("Unsupported kernel version, to use ftrace please upgrade to Linux 3.10 or later");
+		return;
+	}
+
+	// Is debugfs or tracefs available?
+	if (access(TRACING_PATH, R_OK) != 0) {
+		mSupported = false;
+		logg->logMessage("Unable to locate the tracing directory, disabling ftrace");
+		return;
+	}
+
+	mSupported = true;
+
+	mxml_node_t *node = xml;
+	int count = 0;
+	while (true) {
+		node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND);
+		if (node == NULL) {
+			break;
+		}
+		const char *counter = mxmlElementGetAttr(node, "counter");
+		if (counter == NULL) {
+			continue;
+		}
+
+		if (strncmp(counter, "ftrace_", 7) != 0) {
+			continue;
+		}
+
+		const char *regex = mxmlElementGetAttr(node, "regex");
+		if (regex == NULL) {
+			logg->logError("The regex counter %s is missing the required regex attribute", counter);
+			handleException();
+		}
+
+		const char *tracepoint = mxmlElementGetAttr(node, "tracepoint");
+		const char *enable = mxmlElementGetAttr(node, "enable");
+		if (enable == NULL) {
+			enable = tracepoint;
+		}
+		if (gSessionData->mPerf.isSetup() && tracepoint != NULL) {
+			logg->logMessage("Not using ftrace for counter %s", counter);
+			continue;
+		}
+		if (enable != NULL) {
+			char buf[1<<10];
+			snprintf(buf, sizeof(buf), EVENTS_PATH "/%s/enable", enable);
+			if (access(buf, W_OK) != 0) {
+				logg->logMessage("Disabling counter %s, %s not found", counter, buf);
+				continue;
+			}
+		}
+
+		logg->logMessage("Using ftrace for %s", counter);
+		setCounters(new FtraceCounter(getCounters(), strdup(counter), enable));
+		++count;
+	}
+
+	mValues = new int64_t[2*count];
+}
+
+void FtraceDriver::prepare() {
+	for (FtraceCounter *counter = static_cast<FtraceCounter *>(getCounters()); counter != NULL; counter = static_cast<FtraceCounter *>(counter->getNext())) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		counter->prepare();
+	}
+
+	if (DriverSource::readIntDriver(TRACING_PATH "/tracing_on", &mTracingOn)) {
+		logg->logError("Unable to read if ftrace is enabled");
+		handleException();
+	}
+
+	if (DriverSource::writeDriver(TRACING_PATH "/tracing_on", "0") != 0) {
+		logg->logError("Unable to turn ftrace off before truncating the buffer");
+		handleException();
+	}
+
+	{
+		int fd;
+		fd = open(TRACING_PATH "/trace", O_WRONLY | O_TRUNC | O_CLOEXEC, 0666);
+		if (fd < 0) {
+			logg->logError("Unable truncate ftrace buffer: %s", strerror(errno));
+			handleException();
+		}
+		close(fd);
+	}
+
+	if (DriverSource::writeDriver(TRACING_PATH "/trace_clock", "perf") != 0) {
+		logg->logError("Unable to switch ftrace to the perf clock, please ensure you are running Linux 3.10 or later");
+		handleException();
+	}
+}
+
+void FtraceDriver::stop() {
+	DriverSource::writeDriver(TRACING_PATH "/tracing_on", mTracingOn);
+	DriverSource::writeDriver(TRACING_PATH "/trace_clock", "local");
+
+	for (FtraceCounter *counter = static_cast<FtraceCounter *>(getCounters()); counter != NULL; counter = static_cast<FtraceCounter *>(counter->getNext())) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		counter->stop();
+	}
+}
diff --git a/tools/gator/daemon/FtraceDriver.h b/tools/gator/daemon/FtraceDriver.h
new file mode 100644
index 00000000000..6e592d78661
--- /dev/null
+++ b/tools/gator/daemon/FtraceDriver.h
@@ -0,0 +1,36 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef FTRACEDRIVER_H
+#define FTRACEDRIVER_H
+
+#include "Driver.h"
+
+class FtraceDriver : public SimpleDriver {
+public:
+	FtraceDriver();
+	~FtraceDriver();
+
+	void readEvents(mxml_node_t *const xml);
+
+	void prepare();
+	void stop();
+
+	bool isSupported() const { return mSupported; }
+
+private:
+	int64_t *mValues;
+	bool mSupported;
+	int mTracingOn;
+
+	// Intentionally unimplemented
+	FtraceDriver(const FtraceDriver &);
+	FtraceDriver &operator=(const FtraceDriver &);
+};
+
+#endif // FTRACEDRIVER_H
diff --git a/tools/gator/daemon/HwmonDriver.cpp b/tools/gator/daemon/HwmonDriver.cpp
new file mode 100644
index 00000000000..d8353b006e6
--- /dev/null
+++ b/tools/gator/daemon/HwmonDriver.cpp
@@ -0,0 +1,245 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "HwmonDriver.h"
+
+#include "libsensors/sensors.h"
+
+#include "Logging.h"
+
+// feature->type to input map
+static sensors_subfeature_type getInput(const sensors_feature_type type) {
+	switch (type) {
+	case SENSORS_FEATURE_IN: return SENSORS_SUBFEATURE_IN_INPUT;
+	case SENSORS_FEATURE_FAN: return SENSORS_SUBFEATURE_FAN_INPUT;
+	case SENSORS_FEATURE_TEMP: return SENSORS_SUBFEATURE_TEMP_INPUT;
+	case SENSORS_FEATURE_POWER: return SENSORS_SUBFEATURE_POWER_INPUT;
+	case SENSORS_FEATURE_ENERGY: return SENSORS_SUBFEATURE_ENERGY_INPUT;
+	case SENSORS_FEATURE_CURR: return SENSORS_SUBFEATURE_CURR_INPUT;
+	case SENSORS_FEATURE_HUMIDITY: return SENSORS_SUBFEATURE_HUMIDITY_INPUT;
+	default:
+		logg->logError("Unsupported hwmon feature %i", type);
+		handleException();
+	}
+};
+
+class HwmonCounter : public DriverCounter {
+public:
+	HwmonCounter(DriverCounter *next, char *const name, const sensors_chip_name *chip, const sensors_feature *feature);
+	~HwmonCounter();
+
+	const char *getLabel() const { return mLabel; }
+	const char *getTitle() const { return mTitle; }
+	bool isDuplicate() const { return mDuplicate; }
+	const char *getDisplay() const { return mDisplay; }
+	const char *getCounterClass() const { return mCounterClass; }
+	const char *getUnit() const { return mUnit; }
+	double getMultiplier() const { return mMultiplier; }
+
+	int64_t read();
+
+private:
+	void init(const sensors_chip_name *chip, const sensors_feature *feature);
+
+	const sensors_chip_name *mChip;
+	const sensors_feature *mFeature;
+	char *mLabel;
+	const char *mTitle;
+	const char *mDisplay;
+	const char *mCounterClass;
+	const char *mUnit;
+	double mPreviousValue;
+	double mMultiplier;
+	int mMonotonic: 1,
+		mDuplicate : 1;
+
+	// Intentionally unimplemented
+	HwmonCounter(const HwmonCounter &);
+	HwmonCounter &operator=(const HwmonCounter &);
+};
+
+HwmonCounter::HwmonCounter(DriverCounter *next, char *const name, const sensors_chip_name *const chip, const sensors_feature *feature) : DriverCounter(next, name), mChip(chip), mFeature(feature), mDuplicate(false) {
+	mLabel = sensors_get_label(mChip, mFeature);
+
+	switch (mFeature->type) {
+	case SENSORS_FEATURE_IN:
+		mTitle = "Voltage";
+		mDisplay = "maximum";
+		mCounterClass = "absolute";
+		mUnit = "V";
+		mMultiplier = 0.001;
+		mMonotonic = false;
+		break;
+	case SENSORS_FEATURE_FAN:
+		mTitle = "Fan";
+		mDisplay = "average";
+		mCounterClass = "absolute";
+		mUnit = "RPM";
+		mMultiplier = 1.0;
+		mMonotonic = false;
+		break;
+	case SENSORS_FEATURE_TEMP:
+		mTitle = "Temperature";
+		mDisplay = "maximum";
+		mCounterClass = "absolute";
+		mUnit = "°C";
+		mMultiplier = 0.001;
+		mMonotonic = false;
+		break;
+	case SENSORS_FEATURE_POWER:
+		mTitle = "Power";
+		mDisplay = "maximum";
+		mCounterClass = "absolute";
+		mUnit = "W";
+		mMultiplier = 0.000001;
+		mMonotonic = false;
+		break;
+	case SENSORS_FEATURE_ENERGY:
+		mTitle = "Energy";
+		mDisplay = "accumulate";
+		mCounterClass = "delta";
+		mUnit = "J";
+		mMultiplier = 0.000001;
+		mMonotonic = true;
+		break;
+	case SENSORS_FEATURE_CURR:
+		mTitle = "Current";
+		mDisplay = "maximum";
+		mCounterClass = "absolute";
+		mUnit = "A";
+		mMultiplier = 0.001;
+		mMonotonic = false;
+		break;
+	case SENSORS_FEATURE_HUMIDITY:
+		mTitle = "Humidity";
+		mDisplay = "average";
+		mCounterClass = "absolute";
+		mUnit = "%";
+		mMultiplier = 0.001;
+		mMonotonic = false;
+		break;
+	default:
+		logg->logError("Unsupported hwmon feature %i", mFeature->type);
+		handleException();
+	}
+
+	for (HwmonCounter * counter = static_cast<HwmonCounter *>(next); counter != NULL; counter = static_cast<HwmonCounter *>(counter->getNext())) {
+		if (strcmp(mLabel, counter->getLabel()) == 0 && strcmp(mTitle, counter->getTitle()) == 0) {
+			mDuplicate = true;
+			counter->mDuplicate = true;
+			break;
+		}
+	}
+}
+
+HwmonCounter::~HwmonCounter() {
+	free((void *)mLabel);
+}
+
+int64_t HwmonCounter::read() {
+	double value;
+	double result;
+	const sensors_subfeature *subfeature;
+
+	// Keep in sync with the read check in HwmonDriver::readEvents
+	subfeature = sensors_get_subfeature(mChip, mFeature, getInput(mFeature->type));
+	if (!subfeature) {
+		logg->logError("No input value for hwmon sensor %s", mLabel);
+		handleException();
+	}
+
+	if (sensors_get_value(mChip, subfeature->number, &value) != 0) {
+		logg->logError("Can't get input value for hwmon sensor %s", mLabel);
+		handleException();
+	}
+
+	result = (mMonotonic ? value - mPreviousValue : value);
+	mPreviousValue = value;
+
+	return result;
+}
+
+HwmonDriver::HwmonDriver() {
+}
+
+HwmonDriver::~HwmonDriver() {
+	sensors_cleanup();
+}
+
+void HwmonDriver::readEvents(mxml_node_t *const) {
+	int err = sensors_init(NULL);
+	if (err) {
+		logg->logMessage("Failed to initialize libsensors! (%d)", err);
+		return;
+	}
+	sensors_sysfs_no_scaling = 1;
+
+	int chip_nr = 0;
+	const sensors_chip_name *chip;
+	while ((chip = sensors_get_detected_chips(NULL, &chip_nr))) {
+		int feature_nr = 0;
+		const sensors_feature *feature;
+		while ((feature = sensors_get_features(chip, &feature_nr))) {
+			// Keep in sync with HwmonCounter::read
+			// Can this counter be read?
+			double value;
+			const sensors_subfeature *const subfeature = sensors_get_subfeature(chip, feature, getInput(feature->type));
+			if ((subfeature == NULL) || (sensors_get_value(chip, subfeature->number, &value) != 0)) {
+				continue;
+			}
+
+			// Get the name of the counter
+			int len = sensors_snprintf_chip_name(NULL, 0, chip) + 1;
+			char *chip_name = new char[len];
+			sensors_snprintf_chip_name(chip_name, len, chip);
+			len = snprintf(NULL, 0, "hwmon_%s_%d_%d", chip_name, chip_nr, feature->number) + 1;
+			char *const name = new char[len];
+			snprintf(name, len, "hwmon_%s_%d_%d", chip_name, chip_nr, feature->number);
+			delete [] chip_name;
+
+			setCounters(new HwmonCounter(getCounters(), name, chip, feature));
+		}
+	}
+}
+
+void HwmonDriver::writeEvents(mxml_node_t *root) const {
+	root = mxmlNewElement(root, "category");
+	mxmlElementSetAttr(root, "name", "Hardware Monitor");
+
+	char buf[1024];
+	for (HwmonCounter *counter = static_cast<HwmonCounter *>(getCounters()); counter != NULL; counter = static_cast<HwmonCounter *>(counter->getNext())) {
+		mxml_node_t *node = mxmlNewElement(root, "event");
+		mxmlElementSetAttr(node, "counter", counter->getName());
+		mxmlElementSetAttr(node, "title", counter->getTitle());
+		if (counter->isDuplicate()) {
+			mxmlElementSetAttrf(node, "name", "%s (0x%x)", counter->getLabel(), counter->getKey());
+		} else {
+			mxmlElementSetAttr(node, "name", counter->getLabel());
+		}
+		mxmlElementSetAttr(node, "display", counter->getDisplay());
+		mxmlElementSetAttr(node, "class", counter->getCounterClass());
+		mxmlElementSetAttr(node, "units", counter->getUnit());
+		if (counter->getMultiplier() != 1.0) {
+			mxmlElementSetAttrf(node, "multiplier", "%lf", counter->getMultiplier());
+		}
+		if (strcmp(counter->getDisplay(), "average") == 0 || strcmp(counter->getDisplay(), "maximum") == 0) {
+			mxmlElementSetAttr(node, "average_selection", "yes");
+		}
+		snprintf(buf, sizeof(buf), "libsensors %s sensor %s (%s)", counter->getTitle(), counter->getLabel(), counter->getName());
+		mxmlElementSetAttr(node, "description", buf);
+	}
+}
+
+void HwmonDriver::start() {
+	for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		counter->read();
+	}
+}
diff --git a/tools/gator/daemon/HwmonDriver.h b/tools/gator/daemon/HwmonDriver.h
new file mode 100644
index 00000000000..f15d557051d
--- /dev/null
+++ b/tools/gator/daemon/HwmonDriver.h
@@ -0,0 +1,31 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef HWMONDRIVER_H
+#define HWMONDRIVER_H
+
+#include "Driver.h"
+
+class HwmonDriver : public PolledDriver {
+public:
+	HwmonDriver();
+	~HwmonDriver();
+
+	void readEvents(mxml_node_t *const root);
+
+	void writeEvents(mxml_node_t *root) const;
+
+	void start();
+
+private:
+	// Intentionally unimplemented
+	HwmonDriver(const HwmonDriver &);
+	HwmonDriver &operator=(const HwmonDriver &);
+};
+
+#endif // HWMONDRIVER_H
diff --git a/tools/gator/daemon/KMod.cpp b/tools/gator/daemon/KMod.cpp
new file mode 100644
index 00000000000..e33b499d831
--- /dev/null
+++ b/tools/gator/daemon/KMod.cpp
@@ -0,0 +1,119 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "KMod.h"
+
+#include <sys/types.h>
+#include <dirent.h>
+#include <unistd.h>
+
+#include "ConfigurationXML.h"
+#include "Counter.h"
+#include "DriverSource.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+// Claim all the counters in /dev/gator/events
+bool KMod::claimCounter(const Counter &counter) const {
+	char text[128];
+	snprintf(text, sizeof(text), "/dev/gator/events/%s", counter.getType());
+	return access(text, F_OK) == 0;
+}
+
+void KMod::resetCounters() {
+	char base[128];
+	char text[128];
+
+	// Initialize all perf counters in the driver, i.e. set enabled to zero
+	struct dirent *ent;
+	DIR* dir = opendir("/dev/gator/events");
+	if (dir) {
+		while ((ent = readdir(dir)) != NULL) {
+			// skip hidden files, current dir, and parent dir
+			if (ent->d_name[0] == '.')
+				continue;
+			snprintf(base, sizeof(base), "/dev/gator/events/%s", ent->d_name);
+			snprintf(text, sizeof(text), "%s/enabled", base);
+			DriverSource::writeDriver(text, 0);
+			snprintf(text, sizeof(text), "%s/count", base);
+			DriverSource::writeDriver(text, 0);
+		}
+		closedir(dir);
+	}
+}
+
+static const char ARM_MALI_MIDGARD[] = "ARM_Mali-Midgard_";
+static const char ARM_MALI_T[] = "ARM_Mali-T";
+
+void KMod::setupCounter(Counter &counter) {
+	char base[128];
+	char text[128];
+	snprintf(base, sizeof(base), "/dev/gator/events/%s", counter.getType());
+
+	if ((strncmp(counter.getType(), ARM_MALI_MIDGARD, sizeof(ARM_MALI_MIDGARD) - 1) == 0 ||
+	     strncmp(counter.getType(), ARM_MALI_T, sizeof(ARM_MALI_T) - 1) == 0)) {
+		mIsMaliCapture = true;
+	}
+
+	snprintf(text, sizeof(text), "%s/enabled", base);
+	int enabled = true;
+	if (DriverSource::writeReadDriver(text, &enabled) || !enabled) {
+		counter.setEnabled(false);
+		return;
+	}
+
+	int value = 0;
+	snprintf(text, sizeof(text), "%s/key", base);
+	DriverSource::readIntDriver(text, &value);
+	counter.setKey(value);
+
+	snprintf(text, sizeof(text), "%s/cores", base);
+	if (DriverSource::readIntDriver(text, &value) == 0) {
+		counter.setCores(value);
+	}
+
+	snprintf(text, sizeof(text), "%s/event", base);
+	DriverSource::writeDriver(text, counter.getEvent());
+	snprintf(text, sizeof(text), "%s/count", base);
+	if (access(text, F_OK) == 0) {
+		int count = counter.getCount();
+		if (DriverSource::writeReadDriver(text, &count) && counter.getCount() > 0) {
+			logg->logError("Cannot enable EBS for %s:%i with a count of %d\n", counter.getType(), counter.getEvent(), counter.getCount());
+			handleException();
+		}
+		counter.setCount(count);
+	} else if (counter.getCount() > 0) {
+		ConfigurationXML::remove();
+		logg->logError("Event Based Sampling is only supported with kernel versions 3.0.0 and higher with CONFIG_PERF_EVENTS=y, and CONFIG_HW_PERF_EVENTS=y. The invalid configuration.xml has been removed.\n");
+		handleException();
+	}
+}
+
+int KMod::writeCounters(mxml_node_t *root) const {
+	struct dirent *ent;
+	mxml_node_t *counter;
+
+	// counters.xml is simply a file listing of /dev/gator/events
+	DIR* dir = opendir("/dev/gator/events");
+	if (dir == NULL) {
+		return 0;
+	}
+
+	int count = 0;
+	while ((ent = readdir(dir)) != NULL) {
+		// skip hidden files, current dir, and parent dir
+		if (ent->d_name[0] == '.')
+			continue;
+		counter = mxmlNewElement(root, "counter");
+		mxmlElementSetAttr(counter, "name", ent->d_name);
+		++count;
+	}
+	closedir(dir);
+
+	return count;
+}
diff --git a/tools/gator/daemon/KMod.h b/tools/gator/daemon/KMod.h
new file mode 100644
index 00000000000..7f06b4b34b5
--- /dev/null
+++ b/tools/gator/daemon/KMod.h
@@ -0,0 +1,32 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef KMOD_H
+#define KMOD_H
+
+#include "Driver.h"
+
+// Driver for the gator kernel module
+class KMod : public Driver {
+public:
+	KMod() : mIsMaliCapture(false) {}
+	~KMod() {}
+
+	bool claimCounter(const Counter &counter) const;
+	void resetCounters();
+	void setupCounter(Counter &counter);
+
+	int writeCounters(mxml_node_t *root) const;
+
+	bool isMaliCapture() const { return mIsMaliCapture; }
+
+private:
+	bool mIsMaliCapture;
+};
+
+#endif // KMOD_H
diff --git a/tools/gator/daemon/LocalCapture.cpp b/tools/gator/daemon/LocalCapture.cpp
new file mode 100644
index 00000000000..56899871c03
--- /dev/null
+++ b/tools/gator/daemon/LocalCapture.cpp
@@ -0,0 +1,131 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "LocalCapture.h"
+
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <dirent.h>
+#include <string.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "SessionData.h"
+#include "Logging.h"
+#include "OlyUtility.h"
+#include "EventsXML.h"
+
+LocalCapture::LocalCapture() {}
+
+LocalCapture::~LocalCapture() {}
+
+void LocalCapture::createAPCDirectory(char* target_path) {
+	gSessionData->mAPCDir = createUniqueDirectory(target_path, ".apc");
+	if ((removeDirAndAllContents(gSessionData->mAPCDir) != 0 || mkdir(gSessionData->mAPCDir, S_IRWXU | S_IRWXG | S_IROTH | S_IXOTH) != 0)) {
+		logg->logError("Unable to create directory %s", gSessionData->mAPCDir);
+		handleException();
+	}
+}
+
+void LocalCapture::write(char* string) {
+	char file[PATH_MAX];
+
+	// Set full path
+	snprintf(file, PATH_MAX, "%s/session.xml", gSessionData->mAPCDir);
+
+	// Write the file
+	if (util->writeToDisk(file, string) < 0) {
+		logg->logError("Error writing %s\nPlease verify the path.", file);
+		handleException();
+	}
+
+	// Write events XML
+	EventsXML eventsXML;
+	eventsXML.write(gSessionData->mAPCDir);
+}
+
+char* LocalCapture::createUniqueDirectory(const char* initialPath, const char* ending) {
+	char* output;
+	char path[PATH_MAX];
+
+	// Ensure the path is an absolute path, i.e. starts with a slash
+	if (initialPath == 0 || strlen(initialPath) == 0) {
+		logg->logError("Missing -o command line option required for a local capture.");
+		handleException();
+	} else if (initialPath[0] != '/') {
+		if (getcwd(path, PATH_MAX) == 0) {
+			logg->logMessage("Unable to retrieve the current working directory");
+		}
+		strncat(path, "/", PATH_MAX - strlen(path) - 1);
+		strncat(path, initialPath, PATH_MAX - strlen(path) - 1);
+	} else {
+		strncpy(path, initialPath, PATH_MAX);
+		path[PATH_MAX - 1] = 0; // strncpy does not guarantee a null-terminated string
+	}
+
+	// Add ending if it is not already there
+	if (strcmp(&path[strlen(path) - strlen(ending)], ending) != 0) {
+		strncat(path, ending, PATH_MAX - strlen(path) - 1);
+	}
+
+	output = strdup(path);
+
+	return output;
+}
+
+int LocalCapture::removeDirAndAllContents(char* path) {
+	int error = 0;
+	struct stat mFileInfo;
+	// Does the path exist?
+	if (stat(path, &mFileInfo) == 0) {
+		// Is it a directory?
+		if (mFileInfo.st_mode & S_IFDIR) {
+			DIR * dir = opendir(path);
+			dirent* entry = readdir(dir);
+			while (entry) {
+				if (strcmp(entry->d_name, ".") != 0 && strcmp(entry->d_name, "..") != 0) {
+					char* newpath = (char*)malloc(strlen(path) + strlen(entry->d_name) + 2);
+					sprintf(newpath, "%s/%s", path, entry->d_name);
+					error = removeDirAndAllContents(newpath);
+					free(newpath);
+					if (error) {
+						break;
+					}
+				}
+				entry = readdir(dir);
+			}
+			closedir(dir);
+			if (error == 0) {
+				error = rmdir(path);
+			}
+		} else {
+			error = remove(path);
+		}
+	}
+	return error;
+}
+
+void LocalCapture::copyImages(ImageLinkList* ptr) {
+	char dstfilename[PATH_MAX];
+
+	while (ptr) {
+		strncpy(dstfilename, gSessionData->mAPCDir, PATH_MAX);
+		dstfilename[PATH_MAX - 1] = 0; // strncpy does not guarantee a null-terminated string
+		if (gSessionData->mAPCDir[strlen(gSessionData->mAPCDir) - 1] != '/') {
+			strncat(dstfilename, "/", PATH_MAX - strlen(dstfilename) - 1);
+		}
+		strncat(dstfilename, util->getFilePart(ptr->path), PATH_MAX - strlen(dstfilename) - 1);
+		if (util->copyFile(ptr->path, dstfilename)) {
+			logg->logMessage("copied file %s to %s", ptr->path, dstfilename);
+		} else {
+			logg->logMessage("copy of file %s to %s failed", ptr->path, dstfilename);
+		}
+
+		ptr = ptr->next;
+	}
+}
diff --git a/tools/gator/daemon/LocalCapture.h b/tools/gator/daemon/LocalCapture.h
new file mode 100644
index 00000000000..807f49d1684
--- /dev/null
+++ b/tools/gator/daemon/LocalCapture.h
@@ -0,0 +1,26 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LOCAL_CAPTURE_H__
+#define __LOCAL_CAPTURE_H__
+
+struct ImageLinkList;
+
+class LocalCapture {
+public:
+	LocalCapture();
+	~LocalCapture();
+	void write(char* string);
+	void copyImages(ImageLinkList* ptr);
+	void createAPCDirectory(char* target_path);
+private:
+	char* createUniqueDirectory(const char* path, const char* ending);
+	int removeDirAndAllContents(char* path);
+};
+
+#endif //__LOCAL_CAPTURE_H__
diff --git a/tools/gator/daemon/Logging.cpp b/tools/gator/daemon/Logging.cpp
new file mode 100644
index 00000000000..8846622d950
--- /dev/null
+++ b/tools/gator/daemon/Logging.cpp
@@ -0,0 +1,78 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Logging.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdarg.h>
+#include <string.h>
+
+#ifdef WIN32
+#define MUTEX_INIT()    mLoggingMutex = CreateMutex(NULL, false, NULL);
+#define MUTEX_LOCK()    WaitForSingleObject(mLoggingMutex, 0xFFFFFFFF);
+#define MUTEX_UNLOCK()  ReleaseMutex(mLoggingMutex);
+#define snprintf _snprintf
+#else
+#include <pthread.h>
+#define MUTEX_INIT()    pthread_mutex_init(&mLoggingMutex, NULL)
+#define MUTEX_LOCK()    pthread_mutex_lock(&mLoggingMutex)
+#define MUTEX_UNLOCK()  pthread_mutex_unlock(&mLoggingMutex)
+#endif
+
+// Global thread-safe logging
+Logging* logg = NULL;
+
+Logging::Logging(bool debug) {
+	mDebug = debug;
+	MUTEX_INIT();
+
+	strcpy(mErrBuf, "Unknown Error");
+	strcpy(mLogBuf, "Unknown Message");
+}
+
+Logging::~Logging() {
+}
+
+void Logging::_logError(const char *function, const char *file, int line, const char *fmt, ...) {
+	va_list args;
+
+	MUTEX_LOCK();
+	if (mDebug) {
+		snprintf(mErrBuf, sizeof(mErrBuf), "ERROR: %s(%s:%i): ", function, file, line);
+	} else {
+		mErrBuf[0] = 0;
+	}
+
+	va_start(args, fmt);
+	vsnprintf(mErrBuf + strlen(mErrBuf), sizeof(mErrBuf) - 2 - strlen(mErrBuf), fmt, args); //  subtract 2 for \n and \0
+	va_end(args);
+
+	if (strlen(mErrBuf) > 0) {
+		strcat(mErrBuf, "\n");
+	}
+	MUTEX_UNLOCK();
+}
+
+void Logging::_logMessage(const char *function, const char *file, int line, const char *fmt, ...) {
+	if (mDebug) {
+		va_list args;
+
+		MUTEX_LOCK();
+		snprintf(mLogBuf, sizeof(mLogBuf), "INFO: %s(%s:%i): ", function, file, line);
+
+		va_start(args, fmt);
+		vsnprintf(mLogBuf + strlen(mLogBuf), sizeof(mLogBuf) - 2 - strlen(mLogBuf), fmt, args); //  subtract 2 for \n and \0
+		va_end(args);
+		strcat(mLogBuf, "\n");
+
+		fprintf(stdout, "%s", mLogBuf);
+		fflush(stdout);
+		MUTEX_UNLOCK();
+	}
+}
diff --git a/tools/gator/daemon/Logging.h b/tools/gator/daemon/Logging.h
new file mode 100644
index 00000000000..a7b45239f5d
--- /dev/null
+++ b/tools/gator/daemon/Logging.h
@@ -0,0 +1,40 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LOGGING_H__
+#define __LOGGING_H__
+
+#include <pthread.h>
+
+#define DRIVER_ERROR "\n Driver issue:\n  >> gator.ko must be built against the current kernel version & configuration\n  >> gator.ko should be co-located with gatord in the same directory\n  >>   OR insmod gator.ko prior to launching gatord"
+
+class Logging {
+public:
+	Logging(bool debug);
+	~Logging();
+#define logError(...) _logError(__func__, __FILE__, __LINE__, __VA_ARGS__)
+	__attribute__ ((format (printf, 5, 6)))
+	void _logError(const char *function, const char *file, int line, const char *fmt, ...);
+#define logMessage(...) _logMessage(__func__, __FILE__, __LINE__, __VA_ARGS__)
+	__attribute__ ((format (printf, 5, 6)))
+	void _logMessage(const char *function, const char *file, int line, const char *fmt, ...);
+	char *getLastError() {return mErrBuf;}
+	char *getLastMessage() {return mLogBuf;}
+
+private:
+	char mErrBuf[4096]; // Arbitrarily large buffer to hold a string
+	char mLogBuf[4096]; // Arbitrarily large buffer to hold a string
+	bool mDebug;
+	pthread_mutex_t mLoggingMutex;
+};
+
+extern Logging *logg;
+
+extern void handleException() __attribute__ ((noreturn));
+
+#endif //__LOGGING_H__
diff --git a/tools/gator/daemon/Makefile b/tools/gator/daemon/Makefile
new file mode 100644
index 00000000000..27531b438b6
--- /dev/null
+++ b/tools/gator/daemon/Makefile
@@ -0,0 +1,22 @@
+#
+# Makefile for ARM Streamline - Gator Daemon
+#
+
+# Uncomment and define CROSS_COMPILE if it is not already defined
+# CROSS_COMPILE=/path/to/cross-compiler/arm-linux-gnueabihf-
+# NOTE: This toolchain uses the hardfloat abi by default. For non-hardfloat
+# targets run 'make SOFTFLOAT=1 SYSROOT=/path/to/sysroot', see
+# README_Streamline.txt for more details
+
+CC = $(CROSS_COMPILE)gcc
+CXX = $(CROSS_COMPILE)g++
+
+ifeq ($(SOFTFLOAT),1)
+	CPPFLAGS += -marm -mthumb-interwork -march=armv4t -mfloat-abi=soft
+	LDFLAGS += -marm -march=armv4t -mfloat-abi=soft
+endif
+ifneq ($(SYSROOT),)
+	LDFLAGS += --sysroot=$(SYSROOT)
+endif
+
+include common.mk
diff --git a/tools/gator/daemon/Makefile_aarch64 b/tools/gator/daemon/Makefile_aarch64
new file mode 100644
index 00000000000..efd1fa00218
--- /dev/null
+++ b/tools/gator/daemon/Makefile_aarch64
@@ -0,0 +1,12 @@
+#
+# Makefile for ARM Streamline - Gator Daemon
+# make -f Makefile_aarch64
+#
+
+# Uncomment and define CROSS_COMPILE if it is not already defined
+# CROSS_COMPILE=/path/to/cross-compiler/aarch64-linux-gnu-
+
+CC = $(CROSS_COMPILE)gcc
+CXX = $(CROSS_COMPILE)g++
+
+include common.mk
diff --git a/tools/gator/daemon/MaliVideoDriver.cpp b/tools/gator/daemon/MaliVideoDriver.cpp
new file mode 100644
index 00000000000..209a2d3006d
--- /dev/null
+++ b/tools/gator/daemon/MaliVideoDriver.cpp
@@ -0,0 +1,187 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "MaliVideoDriver.h"
+
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Counter.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+// From instr/src/mve_instr_comm_protocol.h
+typedef enum mve_instr_configuration_type {
+	MVE_INSTR_RAW         = 1 << 0,
+	MVE_INSTR_COUNTERS    = 1 << 1,
+	MVE_INSTR_EVENTS      = 1 << 2,
+	MVE_INSTR_ACTIVITIES  = 1 << 3,
+
+	// Raw always pushed regardless
+	MVE_INSTR_PULL        = 1 << 12,
+	// Raw always unpacked regardless
+	MVE_INSTR_PACKED_COMM = 1 << 13,
+	// Don’t send ACKt response
+	MVE_INSTR_NO_AUTO_ACK   = 1 << 14,
+} mve_instr_configuration_type_t;
+
+static const char COUNTER[] = "ARM_Mali-V500_cnt";
+static const char EVENT[] = "ARM_Mali-V500_evn";
+static const char ACTIVITY[] = "ARM_Mali-V500_act";
+
+class MaliVideoCounter : public DriverCounter {
+public:
+	MaliVideoCounter(DriverCounter *next, const char *name, const MaliVideoCounterType type, const int id) : DriverCounter(next, name), mType(type), mId(id) {
+	}
+
+	~MaliVideoCounter() {
+	}
+
+	MaliVideoCounterType getType() const { return mType; }
+	int getId() const { return mId; }
+
+private:
+	const MaliVideoCounterType mType;
+	// Mali Video id
+	const int mId;
+};
+
+MaliVideoDriver::MaliVideoDriver() {
+}
+
+MaliVideoDriver::~MaliVideoDriver() {
+}
+
+void MaliVideoDriver::readEvents(mxml_node_t *const xml) {
+	// Always create the counters as /dev/mv500 may show up after gatord starts
+	mxml_node_t *node = xml;
+	while (true) {
+		node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND);
+		if (node == NULL) {
+			break;
+		}
+		const char *counter = mxmlElementGetAttr(node, "counter");
+		if (counter == NULL) {
+			// Ignore
+		} else if (strncmp(counter, COUNTER, sizeof(COUNTER) - 1) == 0) {
+			const int i = strtol(counter + sizeof(COUNTER) - 1, NULL, 10);
+			setCounters(new MaliVideoCounter(getCounters(), strdup(counter), MVCT_COUNTER, i));
+		} else if (strncmp(counter, EVENT, sizeof(EVENT) - 1) == 0) {
+			const int i = strtol(counter + sizeof(EVENT) - 1, NULL, 10);
+			setCounters(new MaliVideoCounter(getCounters(), strdup(counter), MVCT_EVENT, i));
+		} else if (strncmp(counter, ACTIVITY, sizeof(ACTIVITY) - 1) == 0) {
+			const int i = strtol(counter + sizeof(ACTIVITY) - 1, NULL, 10);
+			setCounters(new MaliVideoCounter(getCounters(), strdup(counter), MVCT_ACTIVITY, i));
+		}
+	}
+}
+
+int MaliVideoDriver::writeCounters(mxml_node_t *root) const {
+	if (access("/dev/mv500", F_OK) != 0) {
+		// Don't show the counters in counter configuration
+		return 0;
+	}
+
+	return super::writeCounters(root);
+}
+
+bool MaliVideoDriver::claimCounter(const Counter &counter) const {
+	if (access("/dev/mv500", F_OK) != 0) {
+		// Don't add the counters to captured XML
+		return 0;
+	}
+
+	return super::claimCounter(counter);
+}
+
+void MaliVideoDriver::marshalEnable(const MaliVideoCounterType type, char *const buf, const size_t bufsize, int &pos) {
+	// size
+	int numEnabled = 0;
+	for (MaliVideoCounter *counter = static_cast<MaliVideoCounter *>(getCounters()); counter != NULL; counter = static_cast<MaliVideoCounter *>(counter->getNext())) {
+		if (counter->isEnabled() && (counter->getType() == type)) {
+			++numEnabled;
+		}
+	}
+	Buffer::packInt(buf, bufsize, pos, numEnabled*sizeof(uint32_t));
+	for (MaliVideoCounter *counter = static_cast<MaliVideoCounter *>(getCounters()); counter != NULL; counter = static_cast<MaliVideoCounter *>(counter->getNext())) {
+		if (counter->isEnabled() && (counter->getType() == type)) {
+			Buffer::packInt(buf, bufsize, pos, counter->getId());
+		}
+	}
+}
+
+bool MaliVideoDriver::start(const int mveUds) {
+	char buf[256];
+	int pos = 0;
+
+	// code - MVE_INSTR_STARTUP
+	buf[pos++] = 'C';
+	buf[pos++] = 'L';
+	buf[pos++] = 'N';
+	buf[pos++] = 'T';
+	// size
+	Buffer::packInt(buf, sizeof(buf), pos, sizeof(uint32_t));
+	// client_version_number
+	Buffer::packInt(buf, sizeof(buf), pos, 1);
+
+	// code - MVE_INSTR_CONFIGURE
+	buf[pos++] = 'C';
+	buf[pos++] = 'N';
+	buf[pos++] = 'F';
+	buf[pos++] = 'G';
+	// size
+	Buffer::packInt(buf, sizeof(buf), pos, 5*sizeof(uint32_t));
+	// configuration
+	Buffer::packInt(buf, sizeof(buf), pos, MVE_INSTR_COUNTERS | MVE_INSTR_EVENTS | MVE_INSTR_ACTIVITIES | MVE_INSTR_PACKED_COMM);
+	// communication_protocol_version
+	Buffer::packInt(buf, sizeof(buf), pos, 1);
+	// data_protocol_version
+	Buffer::packInt(buf, sizeof(buf), pos, 1);
+	// sample_rate - convert samples/second to ms/sample
+	Buffer::packInt(buf, sizeof(buf), pos, gSessionData->mSampleRate/1000);
+	// live_rate - convert ns/flush to ms/flush
+	Buffer::packInt(buf, sizeof(buf), pos, gSessionData->mLiveRate/1000000);
+
+	// code - MVE_INSTR_ENABLE_COUNTERS
+	buf[pos++] = 'C';
+	buf[pos++] = 'F';
+	buf[pos++] = 'G';
+	buf[pos++] = 'c';
+	marshalEnable(MVCT_COUNTER, buf, sizeof(buf), pos);
+
+	// code - MVE_INSTR_ENABLE_EVENTS
+	buf[pos++] = 'C';
+	buf[pos++] = 'F';
+	buf[pos++] = 'G';
+	buf[pos++] = 'e';
+	marshalEnable(MVCT_EVENT, buf, sizeof(buf), pos);
+
+	// code - MVE_INSTR_ENABLE_ACTIVITIES
+	buf[pos++] = 'C';
+	buf[pos++] = 'F';
+	buf[pos++] = 'G';
+	buf[pos++] = 'a';
+	marshalEnable(MVCT_ACTIVITY, buf, sizeof(buf), pos);
+
+	return writeAll(mveUds, buf, pos);
+}
+
+void MaliVideoDriver::stop(const int mveUds) {
+	char buf[8];
+	int pos = 0;
+
+	// code - MVE_INSTR_STOP
+	buf[pos++] = 'S';
+	buf[pos++] = 'T';
+	buf[pos++] = 'O';
+	buf[pos++] = 'P';
+
+	writeAll(mveUds, buf, pos);
+
+	close(mveUds);
+}
diff --git a/tools/gator/daemon/MaliVideoDriver.h b/tools/gator/daemon/MaliVideoDriver.h
new file mode 100644
index 00000000000..fd01b1b2d85
--- /dev/null
+++ b/tools/gator/daemon/MaliVideoDriver.h
@@ -0,0 +1,46 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef MALIVIDEODRIVER_H
+#define MALIVIDEODRIVER_H
+
+#include "Driver.h"
+
+class MaliVideoCounter;
+
+enum MaliVideoCounterType {
+	MVCT_COUNTER,
+	MVCT_EVENT,
+	MVCT_ACTIVITY,
+};
+
+class MaliVideoDriver : public SimpleDriver {
+private:
+	typedef SimpleDriver super;
+
+public:
+	MaliVideoDriver();
+	~MaliVideoDriver();
+
+	void readEvents(mxml_node_t *const root);
+
+	int writeCounters(mxml_node_t *root) const;
+	bool claimCounter(const Counter &counter) const;
+
+	bool start(const int mveUds);
+	void stop(const int mveUds);
+
+private:
+	void marshalEnable(const MaliVideoCounterType type, char *const buf, const size_t bufsize, int &pos);
+
+	// Intentionally unimplemented
+	MaliVideoDriver(const MaliVideoDriver &);
+	MaliVideoDriver &operator=(const MaliVideoDriver &);
+};
+
+#endif // MALIVIDEODRIVER_H
diff --git a/tools/gator/daemon/MemInfoDriver.cpp b/tools/gator/daemon/MemInfoDriver.cpp
new file mode 100644
index 00000000000..4c0b0513194
--- /dev/null
+++ b/tools/gator/daemon/MemInfoDriver.cpp
@@ -0,0 +1,93 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "MemInfoDriver.h"
+
+#include "Logging.h"
+#include "SessionData.h"
+
+class MemInfoCounter : public DriverCounter {
+public:
+	MemInfoCounter(DriverCounter *next, char *const name, int64_t *const value);
+	~MemInfoCounter();
+
+	int64_t read();
+
+private:
+	int64_t *const mValue;
+
+	// Intentionally unimplemented
+	MemInfoCounter(const MemInfoCounter &);
+	MemInfoCounter &operator=(const MemInfoCounter &);
+};
+
+MemInfoCounter::MemInfoCounter(DriverCounter *next, char *const name, int64_t *const value) : DriverCounter(next, name), mValue(value) {
+}
+
+MemInfoCounter::~MemInfoCounter() {
+}
+
+int64_t MemInfoCounter::read() {
+	return *mValue;
+}
+
+MemInfoDriver::MemInfoDriver() : mBuf(), mMemUsed(0), mMemFree(0), mBuffers(0) {
+}
+
+MemInfoDriver::~MemInfoDriver() {
+}
+
+void MemInfoDriver::readEvents(mxml_node_t *const) {
+	// Only for use with perf
+	if (!gSessionData->mPerf.isSetup()) {
+		return;
+	}
+
+	setCounters(new MemInfoCounter(getCounters(), strdup("Linux_meminfo_memused2"), &mMemUsed));
+	setCounters(new MemInfoCounter(getCounters(), strdup("Linux_meminfo_memfree"), &mMemFree));
+	setCounters(new MemInfoCounter(getCounters(), strdup("Linux_meminfo_bufferram"), &mBuffers));
+}
+
+void MemInfoDriver::read(Buffer *const buffer) {
+	if (!countersEnabled()) {
+		return;
+	}
+
+	if (!mBuf.read("/proc/meminfo")) {
+		logg->logError("Failed to read /proc/meminfo");
+		handleException();
+	}
+
+	char *key = mBuf.getBuf();
+	char *colon;
+	int64_t memTotal = 0;
+	while ((colon = strchr(key, ':')) != NULL) {
+		char *end = strchr(colon + 1, '\n');
+		if (end != NULL) {
+			*end = '\0';
+		}
+		*colon = '\0';
+
+		if (strcmp(key, "MemTotal") == 0) {
+			memTotal = strtoll(colon + 1, NULL, 10) << 10;
+		} else if (strcmp(key, "MemFree") == 0) {
+			mMemFree = strtoll(colon + 1, NULL, 10) << 10;
+		} else if (strcmp(key, "Buffers") == 0) {
+			mBuffers = strtoll(colon + 1, NULL, 10) << 10;
+		}
+
+		if (end == NULL) {
+			break;
+		}
+		key = end + 1;
+	}
+
+	mMemUsed = memTotal - mMemFree;
+
+	super::read(buffer);
+}
diff --git a/tools/gator/daemon/MemInfoDriver.h b/tools/gator/daemon/MemInfoDriver.h
new file mode 100644
index 00000000000..ffeaf3009e9
--- /dev/null
+++ b/tools/gator/daemon/MemInfoDriver.h
@@ -0,0 +1,37 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef MEMINFODRIVER_H
+#define MEMINFODRIVER_H
+
+#include "Driver.h"
+#include "DynBuf.h"
+
+class MemInfoDriver : public PolledDriver {
+private:
+	typedef PolledDriver super;
+
+public:
+	MemInfoDriver();
+	~MemInfoDriver();
+
+	void readEvents(mxml_node_t *const root);
+	void read(Buffer *const buffer);
+
+private:
+	DynBuf mBuf;
+	int64_t mMemUsed;
+	int64_t mMemFree;
+	int64_t mBuffers;
+
+	// Intentionally unimplemented
+	MemInfoDriver(const MemInfoDriver &);
+	MemInfoDriver &operator=(const MemInfoDriver &);
+};
+
+#endif // MEMINFODRIVER_H
diff --git a/tools/gator/daemon/Monitor.cpp b/tools/gator/daemon/Monitor.cpp
new file mode 100644
index 00000000000..04288872f51
--- /dev/null
+++ b/tools/gator/daemon/Monitor.cpp
@@ -0,0 +1,82 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Monitor.h"
+
+#include <errno.h>
+#include <fcntl.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "Logging.h"
+
+Monitor::Monitor() : mFd(-1) {
+}
+
+Monitor::~Monitor() {
+	if (mFd >= 0) {
+		::close(mFd);
+	}
+}
+
+void Monitor::close() {
+	if (mFd >= 0) {
+		::close(mFd);
+		mFd = -1;
+	}
+}
+
+bool Monitor::init() {
+#ifdef EPOLL_CLOEXEC
+	mFd = epoll_create1(EPOLL_CLOEXEC);
+#else
+	mFd = epoll_create(16);
+#endif
+	if (mFd < 0) {
+		logg->logMessage("epoll_create1 failed");
+		return false;
+	}
+
+#ifndef EPOLL_CLOEXEC
+	int fdf = fcntl(mFd, F_GETFD);
+	if ((fdf == -1) || (fcntl(mFd, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+		logg->logMessage("fcntl failed");
+		::close(mFd);
+		return -1;
+	}
+#endif
+
+	return true;
+}
+
+bool Monitor::add(const int fd) {
+	struct epoll_event event;
+	memset(&event, 0, sizeof(event));
+	event.data.fd = fd;
+	event.events = EPOLLIN;
+	if (epoll_ctl(mFd, EPOLL_CTL_ADD, fd, &event) != 0) {
+		logg->logMessage("epoll_ctl failed");
+		return false;
+	}
+
+	return true;
+}
+
+int Monitor::wait(struct epoll_event *const events, int maxevents, int timeout) {
+	int result = epoll_wait(mFd, events, maxevents, timeout);
+	if (result < 0) {
+		// Ignore if the call was interrupted as this will happen when SIGINT is received
+		if (errno == EINTR) {
+			result = 0;
+		} else {
+			logg->logMessage("epoll_wait failed");
+		}
+	}
+
+	return result;
+}
diff --git a/tools/gator/daemon/Monitor.h b/tools/gator/daemon/Monitor.h
new file mode 100644
index 00000000000..55368fca3e0
--- /dev/null
+++ b/tools/gator/daemon/Monitor.h
@@ -0,0 +1,33 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef MONITOR_H
+#define MONITOR_H
+
+#include <sys/epoll.h>
+
+class Monitor {
+public:
+	Monitor();
+	~Monitor();
+
+	void close();
+	bool init();
+	bool add(const int fd);
+	int wait(struct epoll_event *const events, int maxevents, int timeout);
+
+private:
+
+	int mFd;
+
+	// Intentionally unimplemented
+	Monitor(const Monitor &);
+	Monitor &operator=(const Monitor &);
+};
+
+#endif // MONITOR_H
diff --git a/tools/gator/daemon/NetDriver.cpp b/tools/gator/daemon/NetDriver.cpp
new file mode 100644
index 00000000000..ab362115f29
--- /dev/null
+++ b/tools/gator/daemon/NetDriver.cpp
@@ -0,0 +1,129 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+// Define to get format macros from inttypes.h
+#define __STDC_FORMAT_MACROS
+
+#include "NetDriver.h"
+
+#include <inttypes.h>
+
+#include "Logging.h"
+#include "SessionData.h"
+
+class NetCounter : public DriverCounter {
+public:
+	NetCounter(DriverCounter *next, char *const name, int64_t *const value);
+	~NetCounter();
+
+	int64_t read();
+
+private:
+	int64_t *const mValue;
+	int64_t mPrev;
+
+	// Intentionally unimplemented
+	NetCounter(const NetCounter &);
+	NetCounter &operator=(const NetCounter &);
+};
+
+NetCounter::NetCounter(DriverCounter *next, char *const name, int64_t *const value) : DriverCounter(next, name), mValue(value), mPrev(0) {
+}
+
+NetCounter::~NetCounter() {
+}
+
+int64_t NetCounter::read() {
+	int64_t result = *mValue - mPrev;
+	mPrev = *mValue;
+	return result;
+}
+
+NetDriver::NetDriver() : mBuf(), mReceiveBytes(0), mTransmitBytes(0) {
+}
+
+NetDriver::~NetDriver() {
+}
+
+void NetDriver::readEvents(mxml_node_t *const) {
+	// Only for use with perf
+	if (!gSessionData->mPerf.isSetup()) {
+		return;
+	}
+
+	setCounters(new NetCounter(getCounters(), strdup("Linux_net_rx"), &mReceiveBytes));
+	setCounters(new NetCounter(getCounters(), strdup("Linux_net_tx"), &mTransmitBytes));
+}
+
+bool NetDriver::doRead() {
+	if (!countersEnabled()) {
+		return true;
+	}
+
+	if (!mBuf.read("/proc/net/dev")) {
+		return false;
+	}
+
+	// Skip the header
+	char *key;
+	if (((key = strchr(mBuf.getBuf(), '\n')) == NULL) ||
+			((key = strchr(key + 1, '\n')) == NULL)) {
+		return false;
+	}
+	key = key + 1;
+
+	mReceiveBytes = 0;
+	mTransmitBytes = 0;
+
+	char *colon;
+	while ((colon = strchr(key, ':')) != NULL) {
+		char *end = strchr(colon + 1, '\n');
+		if (end != NULL) {
+			*end = '\0';
+		}
+		*colon = '\0';
+
+		int64_t receiveBytes;
+		int64_t transmitBytes;
+		const int count = sscanf(colon + 1, " %" SCNu64 " %*u %*u %*u %*u %*u %*u %*u %" SCNu64, &receiveBytes, &transmitBytes);
+		if (count != 2) {
+			return false;
+		}
+		mReceiveBytes += receiveBytes;
+		mTransmitBytes += transmitBytes;
+
+		if (end == NULL) {
+			break;
+		}
+		key = end + 1;
+	}
+
+	return true;
+}
+
+void NetDriver::start() {
+	if (!doRead()) {
+		logg->logError("Unable to read network stats");
+		handleException();
+	}
+	// Initialize previous values
+	for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		counter->read();
+	}
+}
+
+void NetDriver::read(Buffer *const buffer) {
+	if (!doRead()) {
+		logg->logError("Unable to read network stats");
+		handleException();
+	}
+	super::read(buffer);
+}
diff --git a/tools/gator/daemon/NetDriver.h b/tools/gator/daemon/NetDriver.h
new file mode 100644
index 00000000000..5f722800f75
--- /dev/null
+++ b/tools/gator/daemon/NetDriver.h
@@ -0,0 +1,39 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef NETDRIVER_H
+#define NETDRIVER_H
+
+#include "Driver.h"
+#include "DynBuf.h"
+
+class NetDriver : public PolledDriver {
+private:
+	typedef PolledDriver super;
+
+public:
+	NetDriver();
+	~NetDriver();
+
+	void readEvents(mxml_node_t *const root);
+	void start();
+	void read(Buffer *const buffer);
+
+private:
+	bool doRead();
+
+	DynBuf mBuf;
+	int64_t mReceiveBytes;
+	int64_t mTransmitBytes;
+
+	// Intentionally unimplemented
+	NetDriver(const NetDriver &);
+	NetDriver &operator=(const NetDriver &);
+};
+
+#endif // NETDRIVER_H
diff --git a/tools/gator/daemon/OlySocket.cpp b/tools/gator/daemon/OlySocket.cpp
new file mode 100644
index 00000000000..078d2020922
--- /dev/null
+++ b/tools/gator/daemon/OlySocket.cpp
@@ -0,0 +1,331 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "OlySocket.h"
+
+#include <stdio.h>
+#include <string.h>
+#ifdef WIN32
+#include <Winsock2.h>
+#include <ws2tcpip.h>
+#else
+#include <netinet/in.h>
+#include <sys/un.h>
+#include <unistd.h>
+#include <netdb.h>
+#include <fcntl.h>
+#include <stddef.h>
+#endif
+
+#include "Logging.h"
+
+#ifdef WIN32
+#define CLOSE_SOCKET(x) closesocket(x)
+#define SHUTDOWN_RX_TX SD_BOTH
+#define snprintf       _snprintf
+#else
+#define CLOSE_SOCKET(x) close(x)
+#define SHUTDOWN_RX_TX SHUT_RDWR
+#endif
+
+int socket_cloexec(int domain, int type, int protocol) {
+#ifdef SOCK_CLOEXEC
+  return socket(domain, type | SOCK_CLOEXEC, protocol);
+#else
+  int sock = socket(domain, type, protocol);
+#ifdef FD_CLOEXEC
+  if (sock < 0) {
+    return -1;
+  }
+  int fdf = fcntl(sock, F_GETFD);
+  if ((fdf == -1) || (fcntl(sock, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+    close(sock);
+    return -1;
+  }
+#endif
+  return sock;
+#endif
+}
+
+int accept_cloexec(int sockfd, struct sockaddr *addr, socklen_t *addrlen) {
+  int sock;
+#ifdef SOCK_CLOEXEC
+  sock = accept4(sockfd, addr, addrlen, SOCK_CLOEXEC);
+  if (sock >= 0) {
+    return sock;
+  }
+  // accept4 with SOCK_CLOEXEC may not work on all kernels, so fallback
+#endif
+  sock = accept(sockfd, addr, addrlen);
+#ifdef FD_CLOEXEC
+  if (sock < 0) {
+    return -1;
+  }
+  int fdf = fcntl(sock, F_GETFD);
+  if ((fdf == -1) || (fcntl(sock, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+    close(sock);
+    return -1;
+  }
+#endif
+  return sock;
+}
+
+OlyServerSocket::OlyServerSocket(int port) {
+#ifdef WIN32
+  WSADATA wsaData;
+  if (WSAStartup(0x0202, &wsaData) != 0) {
+    logg->logError("Windows socket initialization failed");
+    handleException();
+  }
+#endif
+
+  createServerSocket(port);
+}
+
+OlySocket::OlySocket(int socketID) : mSocketID(socketID) {
+}
+
+#ifndef WIN32
+
+#define MIN(A, B) ({ \
+  const __typeof__(A) __a = A; \
+  const __typeof__(B) __b = B; \
+  __a > __b ? __b : __a; \
+})
+
+OlyServerSocket::OlyServerSocket(const char* path, const size_t pathSize, const bool calculateAddrlen) {
+  // Create socket
+  mFDServer = socket_cloexec(PF_UNIX, SOCK_STREAM, 0);
+  if (mFDServer < 0) {
+    logg->logError("Error creating server socket");
+    handleException();
+  }
+
+  // Create sockaddr_in structure, ensuring non-populated fields are zero
+  struct sockaddr_un sockaddr;
+  memset((void*)&sockaddr, 0, sizeof(sockaddr));
+  sockaddr.sun_family = AF_UNIX;
+  memcpy(sockaddr.sun_path, path, MIN(pathSize, sizeof(sockaddr.sun_path)));
+  sockaddr.sun_path[sizeof(sockaddr.sun_path) - 1] = '\0';
+
+  // Bind the socket to an address
+  if (bind(mFDServer, (const struct sockaddr*)&sockaddr, calculateAddrlen ? offsetof(struct sockaddr_un, sun_path) + pathSize - 1 : sizeof(sockaddr)) < 0) {
+    logg->logError("Binding of server socket failed.");
+    handleException();
+  }
+
+  // Listen for connections on this socket
+  if (listen(mFDServer, 1) < 0) {
+    logg->logError("Listening of server socket failed");
+    handleException();
+  }
+}
+
+int OlySocket::connect(const char* path, const size_t pathSize, const bool calculateAddrlen) {
+  int fd = socket_cloexec(PF_UNIX, SOCK_STREAM, 0);
+  if (fd < 0) {
+    return -1;
+  }
+
+  // Create sockaddr_in structure, ensuring non-populated fields are zero
+  struct sockaddr_un sockaddr;
+  memset((void*)&sockaddr, 0, sizeof(sockaddr));
+  sockaddr.sun_family = AF_UNIX;
+  memcpy(sockaddr.sun_path, path, MIN(pathSize, sizeof(sockaddr.sun_path)));
+  sockaddr.sun_path[sizeof(sockaddr.sun_path) - 1] = '\0';
+
+  if (::connect(fd, (const struct sockaddr*)&sockaddr, calculateAddrlen ? offsetof(struct sockaddr_un, sun_path) + pathSize - 1 : sizeof(sockaddr)) < 0) {
+    close(fd);
+    return -1;
+  }
+
+  return fd;
+}
+
+#endif
+
+OlySocket::~OlySocket() {
+  if (mSocketID > 0) {
+    CLOSE_SOCKET(mSocketID);
+  }
+}
+
+OlyServerSocket::~OlyServerSocket() {
+  if (mFDServer > 0) {
+    CLOSE_SOCKET(mFDServer);
+  }
+}
+
+void OlySocket::shutdownConnection() {
+  // Shutdown is primarily used to unblock other threads that are blocking on send/receive functions
+  shutdown(mSocketID, SHUTDOWN_RX_TX);
+}
+
+void OlySocket::closeSocket() {
+  // Used for closing an accepted socket but keeping the server socket active
+  if (mSocketID > 0) {
+    CLOSE_SOCKET(mSocketID);
+    mSocketID = -1;
+  }
+}
+
+void OlyServerSocket::closeServerSocket() {
+  if (mFDServer > 0 && CLOSE_SOCKET(mFDServer) != 0) {
+    logg->logError("Failed to close server socket.");
+    handleException();
+  }
+  mFDServer = -1;
+}
+
+void OlyServerSocket::createServerSocket(int port) {
+  int family = AF_INET6;
+
+  // Create socket
+  mFDServer = socket_cloexec(PF_INET6, SOCK_STREAM, IPPROTO_TCP);
+  if (mFDServer < 0) {
+    family = AF_INET;
+    mFDServer = socket_cloexec(PF_INET, SOCK_STREAM, IPPROTO_TCP);
+    if (mFDServer < 0) {
+      logg->logError("Error creating server socket");
+      handleException();
+    }
+  }
+
+  // Enable address reuse, another solution would be to create the server socket once and only close it when the object exits
+  int on = 1;
+  if (setsockopt(mFDServer, SOL_SOCKET, SO_REUSEADDR, (const char*)&on, sizeof(on)) != 0) {
+    logg->logError("Setting server socket reuse option failed");
+    handleException();
+  }
+
+  // Listen on both IPv4 and IPv6
+  on = 0;
+  if (setsockopt(mFDServer, IPPROTO_IPV6, IPV6_V6ONLY, (const char*)&on, sizeof(on)) != 0) {
+    logg->logMessage("setsockopt IPV6_V6ONLY failed");
+  }
+
+  // Create sockaddr_in structure, ensuring non-populated fields are zero
+  struct sockaddr_in6 sockaddr;
+  memset((void*)&sockaddr, 0, sizeof(sockaddr));
+  sockaddr.sin6_family = family;
+  sockaddr.sin6_port = htons(port);
+  sockaddr.sin6_addr = in6addr_any;
+
+  // Bind the socket to an address
+  if (bind(mFDServer, (const struct sockaddr*)&sockaddr, sizeof(sockaddr)) < 0) {
+    logg->logError("Binding of server socket on port %i failed.\nIs an instance already running or is another application using that port?", port);
+    handleException();
+  }
+
+  // Listen for connections on this socket
+  if (listen(mFDServer, 1) < 0) {
+    logg->logError("Listening of server socket failed");
+    handleException();
+  }
+}
+
+// mSocketID is always set to the most recently accepted connection
+// The user of this class should maintain the different socket connections, e.g. by forking the process
+int OlyServerSocket::acceptConnection() {
+  int socketID;
+  if (mFDServer <= 0) {
+    logg->logError("Attempting multiple connections on a single connection server socket or attempting to accept on a client socket");
+    handleException();
+  }
+
+  // Accept a connection, note that this call blocks until a client connects
+  socketID = accept_cloexec(mFDServer, NULL, NULL);
+  if (socketID < 0) {
+    logg->logError("Socket acceptance failed");
+    handleException();
+  }
+  return socketID;
+}
+
+void OlySocket::send(const char* buffer, int size) {
+  if (size <= 0 || buffer == NULL) {
+    return;
+  }
+
+  while (size > 0) {
+    int n = ::send(mSocketID, buffer, size, 0);
+    if (n < 0) {
+      logg->logError("Socket send error");
+      handleException();
+    }
+    size -= n;
+    buffer += n;
+  }
+}
+
+// Returns the number of bytes received
+int OlySocket::receive(char* buffer, int size) {
+  if (size <= 0 || buffer == NULL) {
+    return 0;
+  }
+
+  int bytes = recv(mSocketID, buffer, size, 0);
+  if (bytes < 0) {
+    logg->logError("Socket receive error");
+    handleException();
+  } else if (bytes == 0) {
+    logg->logMessage("Socket disconnected");
+    return -1;
+  }
+  return bytes;
+}
+
+// Receive exactly size bytes of data. Note, this function will block until all bytes are received
+int OlySocket::receiveNBytes(char* buffer, int size) {
+  int bytes = 0;
+  while (size > 0 && buffer != NULL) {
+    bytes = recv(mSocketID, buffer, size, 0);
+    if (bytes < 0) {
+      logg->logError("Socket receive error");
+      handleException();
+    } else if (bytes == 0) {
+      logg->logMessage("Socket disconnected");
+      return -1;
+    }
+    buffer += bytes;
+    size -= bytes;
+  }
+  return bytes;
+}
+
+// Receive data until a carriage return, line feed, or null is encountered, or the buffer fills
+int OlySocket::receiveString(char* buffer, int size) {
+  int bytes_received = 0;
+  bool found = false;
+
+  if (buffer == 0) {
+    return 0;
+  }
+
+  while (!found && bytes_received < size) {
+    // Receive a single character
+    int bytes = recv(mSocketID, &buffer[bytes_received], 1, 0);
+    if (bytes < 0) {
+      logg->logError("Socket receive error");
+      handleException();
+    } else if (bytes == 0) {
+      logg->logMessage("Socket disconnected");
+      return -1;
+    }
+
+    // Replace carriage returns and line feeds with zero
+    if (buffer[bytes_received] == '\n' || buffer[bytes_received] == '\r' || buffer[bytes_received] == '\0') {
+      buffer[bytes_received] = '\0';
+      found = true;
+    }
+
+    bytes_received++;
+  }
+
+  return bytes_received;
+}
diff --git a/tools/gator/daemon/OlySocket.h b/tools/gator/daemon/OlySocket.h
new file mode 100644
index 00000000000..757a2522f92
--- /dev/null
+++ b/tools/gator/daemon/OlySocket.h
@@ -0,0 +1,64 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __OLY_SOCKET_H__
+#define __OLY_SOCKET_H__
+
+#include <stddef.h>
+
+#ifdef WIN32
+typedef int socklen_t;
+#else
+#include <sys/socket.h>
+#endif
+
+class OlySocket {
+public:
+#ifndef WIN32
+  static int connect(const char* path, const size_t pathSize, const bool calculateAddrlen = false);
+#endif
+
+  OlySocket(int socketID);
+  ~OlySocket();
+
+  void closeSocket();
+  void shutdownConnection();
+  void send(const char* buffer, int size);
+  int receive(char* buffer, int size);
+  int receiveNBytes(char* buffer, int size);
+  int receiveString(char* buffer, int size);
+
+  bool isValid() const { return mSocketID >= 0; }
+
+private:
+  int mSocketID;
+};
+
+class OlyServerSocket {
+public:
+  OlyServerSocket(int port);
+#ifndef WIN32
+  OlyServerSocket(const char* path, const size_t pathSize, const bool calculateAddrlen = false);
+#endif
+  ~OlyServerSocket();
+
+  int acceptConnection();
+  void closeServerSocket();
+
+  int getFd() { return mFDServer; }
+
+private:
+  int mFDServer;
+
+  void createServerSocket(int port);
+};
+
+int socket_cloexec(int domain, int type, int protocol);
+int accept_cloexec(int sockfd, struct sockaddr *addr, socklen_t *addrlen);
+
+#endif //__OLY_SOCKET_H__
diff --git a/tools/gator/daemon/OlyUtility.cpp b/tools/gator/daemon/OlyUtility.cpp
new file mode 100644
index 00000000000..6f40168c1ee
--- /dev/null
+++ b/tools/gator/daemon/OlyUtility.cpp
@@ -0,0 +1,227 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "OlyUtility.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <ctype.h>
+
+#if defined(WIN32)
+#include <windows.h>
+#elif defined(__linux__)
+#include <unistd.h>
+#elif defined(DARWIN)
+#include <mach-o/dyld.h>
+#endif
+
+OlyUtility* util = NULL;
+
+bool OlyUtility::stringToBool(const char* string, bool defValue) {
+  char value[32];
+
+  if (string == NULL) {
+    return defValue;
+  }
+
+  strncpy(value, string, sizeof(value));
+  if (value[0] == 0) {
+    return defValue;
+  }
+  value[sizeof(value) - 1] = 0; // strncpy does not guarantee a null-terminated string
+
+  // Convert to lowercase
+  int i = 0;
+  while (value[i]) {
+    value[i] = tolower(value[i]);
+    i++;
+  }
+
+  if (strcmp(value, "true") == 0 || strcmp(value, "yes") == 0 || strcmp(value, "1") == 0 || strcmp(value, "on") == 0) {
+    return true;
+  } else if (strcmp(value, "false") == 0 || strcmp(value, "no") == 0 || strcmp(value, "0") == 0 || strcmp(value, "off") == 0) {
+    return false;
+  } else {
+    return defValue;
+  }
+}
+
+void OlyUtility::stringToLower(char* string) {
+  if (string == NULL) {
+    return;
+  }
+
+  while (*string) {
+    *string = tolower(*string);
+    string++;
+  }
+}
+
+// Modifies fullpath with the path part including the trailing path separator
+int OlyUtility::getApplicationFullPath(char* fullpath, int sizeOfPath) {
+  memset(fullpath, 0, sizeOfPath);
+#if defined(WIN32)
+  int length = GetModuleFileName(NULL, fullpath, sizeOfPath);
+#elif defined(__linux__)
+  int length = readlink("/proc/self/exe", fullpath, sizeOfPath);
+#elif defined(DARWIN)
+  uint32_t length_u = (uint32_t)sizeOfPath;
+  int length = sizeOfPath;
+  if (_NSGetExecutablePath(fullpath, &length_u) == 0) {
+    length = strlen(fullpath);
+  }
+#endif
+
+  if (length == sizeOfPath) {
+    return -1;
+  }
+
+  fullpath[length] = 0;
+  getPathPart(fullpath);
+
+  return 0;
+}
+
+char* OlyUtility::readFromDisk(const char* file, unsigned int *size, bool appendNull) {
+  // Open the file
+  FILE* pFile = fopen(file, "rb");
+  if (pFile==NULL) {
+    return NULL;
+  }
+
+  // Obtain file size
+  fseek(pFile , 0 , SEEK_END);
+  unsigned int lSize = ftell(pFile);
+  rewind(pFile);
+
+  // Allocate memory to contain the whole file
+  char* buffer = (char*)malloc(lSize + (int)appendNull);
+  if (buffer == NULL) {
+    fclose(pFile);
+    return NULL;
+  }
+
+  // Copy the file into the buffer
+  if (fread(buffer, 1, lSize, pFile) != lSize) {
+    free(buffer);
+    fclose(pFile);
+    return NULL;
+  }
+
+  // Terminate
+  fclose(pFile);
+
+  if (appendNull) {
+    buffer[lSize] = 0;
+  }
+
+  if (size) {
+    *size = lSize;
+  }
+
+  return buffer;
+}
+
+int OlyUtility::writeToDisk(const char* path, const char* data) {
+  // Open the file
+  FILE* pFile = fopen(path, "wb");
+  if (pFile == NULL) {
+    return -1;
+  }
+
+  // Write the data to disk
+  if (fwrite(data, 1, strlen(data), pFile) != strlen(data)) {
+    fclose(pFile);
+    return -1;
+  }
+
+  // Terminate
+  fclose(pFile);
+  return 0;
+}
+
+int OlyUtility::appendToDisk(const char* path, const char* data) {
+  // Open the file
+  FILE* pFile = fopen(path, "a");
+  if (pFile == NULL) {
+    return -1;
+  }
+
+  // Write the data to disk
+  if (fwrite(data, 1, strlen(data), pFile) != strlen(data)) {
+    fclose(pFile);
+    return -1;
+  }
+
+  // Terminate
+  fclose(pFile);
+  return 0;
+}
+
+/**
+ * Copies the srcFile into dstFile in 1kB chunks.
+ * The dstFile will be overwritten if it exists.
+ * 0 is returned on an error; otherwise 1.
+ */
+#define TRANSFER_SIZE 1024
+int OlyUtility::copyFile(const char* srcFile, const char* dstFile) {
+  char buffer[TRANSFER_SIZE];
+  FILE * f_src = fopen(srcFile,"rb");
+  if (!f_src) {
+    return 0;
+  }
+  FILE * f_dst = fopen(dstFile,"wb");
+  if (!f_dst) {
+    fclose(f_src);
+    return 0;
+  }
+  while (!feof(f_src)) {
+    int num_bytes_read = fread(buffer, 1, TRANSFER_SIZE, f_src);
+    if (num_bytes_read < TRANSFER_SIZE && !feof(f_src)) {
+      fclose(f_src);
+      fclose(f_dst);
+      return 0;
+    }
+    int num_bytes_written = fwrite(buffer, 1, num_bytes_read, f_dst);
+    if (num_bytes_written != num_bytes_read) {
+      fclose(f_src);
+      fclose(f_dst);
+      return 0;
+    }
+  }
+  fclose(f_src);
+  fclose(f_dst);
+  return 1;
+}
+
+const char* OlyUtility::getFilePart(const char* path) {
+  const char* last_sep = strrchr(path, PATH_SEPARATOR);
+
+  // in case path is not a full path
+  if (last_sep == NULL) {
+    return path;
+  }
+
+  return last_sep++;
+}
+
+// getPathPart may modify the contents of path
+// returns the path including the trailing path separator
+char* OlyUtility::getPathPart(char* path) {
+  char* last_sep = strrchr(path, PATH_SEPARATOR);
+
+  // in case path is not a full path
+  if (last_sep == NULL) {
+    return 0;
+  }
+  last_sep++;
+  *last_sep = 0;
+
+  return (path);
+}
diff --git a/tools/gator/daemon/OlyUtility.h b/tools/gator/daemon/OlyUtility.h
new file mode 100644
index 00000000000..1525081a97a
--- /dev/null
+++ b/tools/gator/daemon/OlyUtility.h
@@ -0,0 +1,42 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef OLY_UTILITY_H
+#define OLY_UTILITY_H
+
+#include <stddef.h>
+
+#ifdef WIN32
+#define PATH_SEPARATOR '\\'
+#define CAIMAN_PATH_MAX MAX_PATH
+#define snprintf _snprintf
+#else
+#include <limits.h>
+#define PATH_SEPARATOR '/'
+#define CAIMAN_PATH_MAX PATH_MAX
+#endif
+
+class OlyUtility {
+public:
+  OlyUtility() {};
+  ~OlyUtility() {};
+  bool stringToBool(const char* string, bool defValue);
+  void stringToLower(char* string);
+  int getApplicationFullPath(char* path, int sizeOfPath);
+  char* readFromDisk(const char* file, unsigned int *size = NULL, bool appendNull = true);
+  int writeToDisk(const char* path, const char* file);
+  int appendToDisk(const char* path, const char* file);
+  int copyFile(const char* srcFile, const char* dstFile);
+  const char* getFilePart(const char* path);
+  char* getPathPart(char* path);
+private:
+};
+
+extern OlyUtility* util;
+
+#endif // OLY_UTILITY_H
diff --git a/tools/gator/daemon/PerfBuffer.cpp b/tools/gator/daemon/PerfBuffer.cpp
new file mode 100644
index 00000000000..3b9da1dc659
--- /dev/null
+++ b/tools/gator/daemon/PerfBuffer.cpp
@@ -0,0 +1,223 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "PerfBuffer.h"
+
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+
+#include "Buffer.h"
+#include "Logging.h"
+#include "Sender.h"
+#include "SessionData.h"
+
+PerfBuffer::PerfBuffer() {
+	for (int cpu = 0; cpu < ARRAY_LENGTH(mBuf); ++cpu) {
+		mBuf[cpu] = MAP_FAILED;
+		mDiscard[cpu] = false;
+		mFds[cpu] = -1;
+	}
+}
+
+PerfBuffer::~PerfBuffer() {
+	for (int cpu = ARRAY_LENGTH(mBuf) - 1; cpu >= 0; --cpu) {
+		if (mBuf[cpu] != MAP_FAILED) {
+			munmap(mBuf[cpu], gSessionData->mPageSize + BUF_SIZE);
+		}
+	}
+}
+
+bool PerfBuffer::useFd(const int cpu, const int fd) {
+	if (mFds[cpu] < 0) {
+		if (mBuf[cpu] != MAP_FAILED) {
+			logg->logMessage("cpu %i already online or not correctly cleaned up", cpu);
+			return false;
+		}
+
+		// The buffer isn't mapped yet
+		mBuf[cpu] = mmap(NULL, gSessionData->mPageSize + BUF_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+		if (mBuf[cpu] == MAP_FAILED) {
+			logg->logMessage("mmap failed");
+			return false;
+		}
+		mFds[cpu] = fd;
+
+		// Check the version
+		struct perf_event_mmap_page *pemp = static_cast<struct perf_event_mmap_page *>(mBuf[cpu]);
+		if (pemp->compat_version != 0) {
+			logg->logMessage("Incompatible perf_event_mmap_page compat_version");
+			return false;
+		}
+	} else {
+		if (mBuf[cpu] == MAP_FAILED) {
+			logg->logMessage("cpu already online or not correctly cleaned up");
+			return false;
+		}
+
+		if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, mFds[cpu]) < 0) {
+			logg->logMessage("ioctl failed");
+			return false;
+		}
+	}
+
+	return true;
+}
+
+void PerfBuffer::discard(const int cpu) {
+	if (mBuf[cpu] != MAP_FAILED) {
+		mDiscard[cpu] = true;
+	}
+}
+
+bool PerfBuffer::isEmpty() {
+	for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+		if (mBuf[cpu] != MAP_FAILED) {
+			// Take a snapshot of the positions
+			struct perf_event_mmap_page *pemp = static_cast<struct perf_event_mmap_page *>(mBuf[cpu]);
+			const __u64 head = ACCESS_ONCE(pemp->data_head);
+			const __u64 tail = ACCESS_ONCE(pemp->data_tail);
+
+			if (head != tail) {
+				return false;
+			}
+		}
+	}
+
+	return true;
+}
+
+bool PerfBuffer::isFull() {
+	for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+		if (mBuf[cpu] != MAP_FAILED) {
+			// Take a snapshot of the positions
+			struct perf_event_mmap_page *pemp = static_cast<struct perf_event_mmap_page *>(mBuf[cpu]);
+			const __u64 head = ACCESS_ONCE(pemp->data_head);
+
+			if (head + 2000 <= (unsigned int)BUF_SIZE) {
+				return true;
+			}
+		}
+	}
+
+	return false;
+}
+
+class PerfFrame {
+public:
+	PerfFrame(Sender *const sender) : mSender(sender), mWritePos(-1), mCpuSizePos(-1) {}
+
+	void add(const int cpu, const __u64 head, __u64 tail, const uint8_t *const b) {
+		cpuHeader(cpu);
+
+		while (head > tail) {
+			const int count = reinterpret_cast<const struct perf_event_header *>(b + (tail & BUF_MASK))->size/sizeof(uint64_t);
+			// Can this whole message be written as Streamline assumes events are not split between frames
+			if (sizeof(mBuf) <= mWritePos + count*Buffer::MAXSIZE_PACK64) {
+				send();
+				cpuHeader(cpu);
+			}
+			for (int i = 0; i < count; ++i) {
+				// Must account for message size
+				Buffer::packInt64(mBuf, sizeof(mBuf), mWritePos, *reinterpret_cast<const uint64_t *>(b + (tail & BUF_MASK)));
+				tail += sizeof(uint64_t);
+			}
+		}
+	}
+
+	void send() {
+		if (mWritePos > 0) {
+			writeFrameSize();
+			mSender->writeData(mBuf, mWritePos, RESPONSE_APC_DATA);
+			mWritePos = -1;
+			mCpuSizePos = -1;
+		}
+	}
+
+private:
+	void writeFrameSize() {
+		writeCpuSize();
+		const int typeLength = gSessionData->mLocalCapture ? 0 : 1;
+		Buffer::writeLEInt(reinterpret_cast<unsigned char *>(mBuf + typeLength), mWritePos - typeLength - sizeof(uint32_t));
+	}
+
+	void frameHeader() {
+		if (mWritePos < 0) {
+			mWritePos = 0;
+			mCpuSizePos = -1;
+			if (!gSessionData->mLocalCapture) {
+				mBuf[mWritePos++] = RESPONSE_APC_DATA;
+			}
+			// Reserve space for frame size
+			mWritePos += sizeof(uint32_t);
+			Buffer::packInt(mBuf, sizeof(mBuf), mWritePos, FRAME_PERF);
+		}
+	}
+
+	void writeCpuSize() {
+		if (mCpuSizePos >= 0) {
+			Buffer::writeLEInt(reinterpret_cast<unsigned char *>(mBuf + mCpuSizePos), mWritePos - mCpuSizePos - sizeof(uint32_t));
+		}
+	}
+
+	void cpuHeader(const int cpu) {
+		if (sizeof(mBuf) <= mWritePos + Buffer::MAXSIZE_PACK32 + sizeof(uint32_t)) {
+			send();
+		}
+		frameHeader();
+		writeCpuSize();
+		Buffer::packInt(mBuf, sizeof(mBuf), mWritePos, cpu);
+		mCpuSizePos = mWritePos;
+		// Reserve space for cpu size
+		mWritePos += sizeof(uint32_t);
+	}
+
+	// Pick a big size but something smaller than the chunkSize in Sender::writeData which is 100k
+	char mBuf[1<<16];
+	Sender *const mSender;
+	int mWritePos;
+	int mCpuSizePos;
+
+	// Intentionally unimplemented
+	PerfFrame(const PerfFrame &);
+	PerfFrame& operator=(const PerfFrame &);
+};
+
+bool PerfBuffer::send(Sender *const sender) {
+	PerfFrame frame(sender);
+
+	for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+		if (mBuf[cpu] == MAP_FAILED) {
+			continue;
+		}
+
+		// Take a snapshot of the positions
+		struct perf_event_mmap_page *pemp = static_cast<struct perf_event_mmap_page *>(mBuf[cpu]);
+		const __u64 head = ACCESS_ONCE(pemp->data_head);
+		const __u64 tail = ACCESS_ONCE(pemp->data_tail);
+
+		if (head > tail) {
+			const uint8_t *const b = static_cast<uint8_t *>(mBuf[cpu]) + gSessionData->mPageSize;
+			frame.add(cpu, head, tail, b);
+
+			// Update tail with the data read
+			pemp->data_tail = head;
+		}
+
+		if (mDiscard[cpu]) {
+			munmap(mBuf[cpu], gSessionData->mPageSize + BUF_SIZE);
+			mBuf[cpu] = MAP_FAILED;
+			mDiscard[cpu] = false;
+			mFds[cpu] = -1;
+			logg->logMessage("Unmaped cpu %i", cpu);
+		}
+	}
+
+	frame.send();
+
+	return true;
+}
diff --git a/tools/gator/daemon/PerfBuffer.h b/tools/gator/daemon/PerfBuffer.h
new file mode 100644
index 00000000000..a2d0e9b4472
--- /dev/null
+++ b/tools/gator/daemon/PerfBuffer.h
@@ -0,0 +1,42 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PERF_BUFFER
+#define PERF_BUFFER
+
+#include "Config.h"
+
+#define BUF_SIZE (gSessionData->mTotalBufferSize * 1024 * 1024)
+#define BUF_MASK (BUF_SIZE - 1)
+
+class Sender;
+
+class PerfBuffer {
+public:
+	PerfBuffer();
+	~PerfBuffer();
+
+	bool useFd(const int cpu, const int fd);
+	void discard(const int cpu);
+	bool isEmpty();
+	bool isFull();
+	bool send(Sender *const sender);
+
+private:
+	void *mBuf[NR_CPUS];
+	// After the buffer is flushed it should be unmaped
+	bool mDiscard[NR_CPUS];
+	// fd that corresponds to the mBuf
+	int mFds[NR_CPUS];
+
+	// Intentionally undefined
+	PerfBuffer(const PerfBuffer &);
+	PerfBuffer &operator=(const PerfBuffer &);
+};
+
+#endif // PERF_BUFFER
diff --git a/tools/gator/daemon/PerfDriver.cpp b/tools/gator/daemon/PerfDriver.cpp
new file mode 100644
index 00000000000..e5f8aaa86c5
--- /dev/null
+++ b/tools/gator/daemon/PerfDriver.cpp
@@ -0,0 +1,509 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "PerfDriver.h"
+
+#include <dirent.h>
+#include <sys/utsname.h>
+#include <time.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Config.h"
+#include "ConfigurationXML.h"
+#include "Counter.h"
+#include "DriverSource.h"
+#include "DynBuf.h"
+#include "Logging.h"
+#include "PerfGroup.h"
+#include "SessionData.h"
+#include "Setup.h"
+
+#define PERF_DEVICES "/sys/bus/event_source/devices"
+
+#define TYPE_DERIVED ~0U
+
+// From gator.h
+struct gator_cpu {
+	const int cpuid;
+	// Human readable name
+	const char *const core_name;
+	// gatorfs event and Perf PMU name
+	const char *const pmnc_name;
+	const int pmnc_counters;
+};
+
+// From gator_main.c
+static const struct gator_cpu gator_cpus[] = {
+	{ 0x41b36, "ARM1136",      "ARM_ARM11",        3 },
+	{ 0x41b56, "ARM1156",      "ARM_ARM11",        3 },
+	{ 0x41b76, "ARM1176",      "ARM_ARM11",        3 },
+	{ 0x41b02, "ARM11MPCore",  "ARM_ARM11MPCore",  3 },
+	{ 0x41c05, "Cortex-A5",    "ARMv7_Cortex_A5",  2 },
+	{ 0x41c07, "Cortex-A7",    "ARMv7_Cortex_A7",  4 },
+	{ 0x41c08, "Cortex-A8",    "ARMv7_Cortex_A8",  4 },
+	{ 0x41c09, "Cortex-A9",    "ARMv7_Cortex_A9",  6 },
+	{ 0x41c0f, "Cortex-A15",   "ARMv7_Cortex_A15", 6 },
+	{ 0x41c0d, "Cortex-A17",   "ARMv7_Cortex_A17", 6 },
+	{ 0x41c0e, "Cortex-A17",   "ARMv7_Cortex_A17", 6 },
+	{ 0x5100f, "Scorpion",     "Scorpion",         4 },
+	{ 0x5102d, "ScorpionMP",   "ScorpionMP",       4 },
+	{ 0x51049, "KraitSIM",     "Krait",            4 },
+	{ 0x5104d, "Krait",        "Krait",            4 },
+	{ 0x5106f, "Krait S4 Pro", "Krait",            4 },
+	{ 0x41d03, "Cortex-A53",   "ARMv8_Cortex_A53", 6 },
+	{ 0x41d07, "Cortex-A57",   "ARMv8_Cortex_A57", 6 },
+	{ 0x41d08, "Cortex-A72",   "ARMv8_Cortex_A72", 6 },
+};
+
+static const char OLD_PMU_PREFIX[] = "ARMv7 Cortex-";
+static const char NEW_PMU_PREFIX[] = "ARMv7_Cortex_";
+
+struct uncore_counter {
+	// Perf PMU name
+	const char *const perfName;
+	// gatorfs event name
+	const char *const gatorName;
+	const int count;
+	const bool hasCyclesCounter;
+};
+
+static const struct uncore_counter uncore_counters[] = {
+	{ "CCI_400",    "CCI_400",     4, true },
+	{ "CCI_400_r1", "CCI_400_r1",  4, true },
+	{ "CCI_500",    "CCI_500",     8, false },
+	{ "ccn",        "ARM_CCN_5XX", 8, true },
+};
+
+class PerfCounter : public DriverCounter {
+public:
+	PerfCounter(DriverCounter *next, const char *name, uint32_t type, uint64_t config, uint64_t sampleType, uint64_t flags, const int count) : DriverCounter(next, name), mType(type), mConfig(config), mSampleType(sampleType), mFlags(flags), mCount(count) {}
+
+	~PerfCounter() {
+	}
+
+	uint32_t getType() const { return mType; }
+	int getCount() const { return mCount; }
+	void setCount(const int count) { mCount = count; }
+	uint64_t getConfig() const { return mConfig; }
+	void setConfig(const uint64_t config) { mConfig = config; }
+	uint64_t getSampleType() const { return mSampleType; }
+	void setSampleType(uint64_t sampleType) { mSampleType = sampleType; }
+	uint64_t getFlags() const { return mFlags; }
+	virtual void read(Buffer *const, const int) {}
+
+private:
+	const uint32_t mType;
+	uint64_t mConfig;
+	uint64_t mSampleType;
+	const uint64_t mFlags;
+	int mCount;
+
+	// Intentionally undefined
+	PerfCounter(const PerfCounter &);
+	PerfCounter &operator=(const PerfCounter &);
+};
+
+class CPUFreqDriver : public PerfCounter {
+public:
+	CPUFreqDriver(DriverCounter *next, uint64_t id) : PerfCounter(next, "Linux_power_cpu_freq", PERF_TYPE_TRACEPOINT, id, PERF_SAMPLE_RAW, PERF_GROUP_LEADER | PERF_GROUP_PER_CPU, 1) {}
+
+	void read(Buffer *const buffer, const int cpu) {
+		char buf[64];
+
+		snprintf(buf, sizeof(buf), "/sys/devices/system/cpu/cpu%i/cpufreq/cpuinfo_cur_freq", cpu);
+		int64_t freq;
+		if (DriverSource::readInt64Driver(buf, &freq) != 0) {
+			freq = 0;
+		}
+		buffer->perfCounter(cpu, getKey(), 1000*freq);
+	}
+
+private:
+	// Intentionally undefined
+	CPUFreqDriver(const CPUFreqDriver &);
+	CPUFreqDriver &operator=(const CPUFreqDriver &);
+};
+
+PerfDriver::PerfDriver() : mIsSetup(false), mLegacySupport(false) {
+}
+
+PerfDriver::~PerfDriver() {
+}
+
+class PerfTracepoint {
+public:
+	PerfTracepoint(PerfTracepoint *const next, const DriverCounter *const counter, const char *const tracepoint) : mNext(next), mCounter(counter), mTracepoint(tracepoint) {}
+
+	PerfTracepoint *getNext() const { return mNext; }
+	const DriverCounter *getCounter() const { return mCounter; }
+	const char *getTracepoint() const { return mTracepoint; }
+
+private:
+	PerfTracepoint *const mNext;
+	const DriverCounter *const mCounter;
+	const char *const mTracepoint;
+
+	// Intentionally undefined
+	PerfTracepoint(const PerfTracepoint &);
+	PerfTracepoint &operator=(const PerfTracepoint &);
+};
+
+void PerfDriver::addCpuCounters(const char *const counterName, const int type, const int numCounters) {
+	int len = snprintf(NULL, 0, "%s_ccnt", counterName) + 1;
+	char *name = new char[len];
+	snprintf(name, len, "%s_ccnt", counterName);
+	setCounters(new PerfCounter(getCounters(), name, type, -1, PERF_SAMPLE_READ, PERF_GROUP_PER_CPU | PERF_GROUP_CPU, 0));
+
+	for (int j = 0; j < numCounters; ++j) {
+		len = snprintf(NULL, 0, "%s_cnt%d", counterName, j) + 1;
+		name = new char[len];
+		snprintf(name, len, "%s_cnt%d", counterName, j);
+		setCounters(new PerfCounter(getCounters(), name, type, -1, PERF_SAMPLE_READ, PERF_GROUP_PER_CPU | PERF_GROUP_CPU, 0));
+	}
+}
+
+void PerfDriver::addUncoreCounters(const char *const counterName, const int type, const int numCounters, const bool hasCyclesCounter) {
+	int len;
+	char *name;
+
+	if (hasCyclesCounter) {
+		len = snprintf(NULL, 0, "%s_ccnt", counterName) + 1;
+		name = new char[len];
+		snprintf(name, len, "%s_ccnt", counterName);
+		setCounters(new PerfCounter(getCounters(), name, type, -1, PERF_SAMPLE_READ, 0, 0));
+	}
+
+	for (int j = 0; j < numCounters; ++j) {
+		len = snprintf(NULL, 0, "%s_cnt%d", counterName, j) + 1;
+		name = new char[len];
+		snprintf(name, len, "%s_cnt%d", counterName, j);
+		setCounters(new PerfCounter(getCounters(), name, type, -1, PERF_SAMPLE_READ, 0, 0));
+	}
+}
+
+void PerfDriver::readEvents(mxml_node_t *const xml) {
+	mxml_node_t *node = xml;
+	DynBuf printb;
+
+	// Only for use with perf
+	if (!isSetup()) {
+		return;
+	}
+
+	while (true) {
+		node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND);
+		if (node == NULL) {
+			break;
+		}
+		const char *counter = mxmlElementGetAttr(node, "counter");
+		if (counter == NULL) {
+			continue;
+		}
+
+		if (strncmp(counter, "ftrace_", 7) != 0) {
+			continue;
+		}
+
+		const char *tracepoint = mxmlElementGetAttr(node, "tracepoint");
+		if (tracepoint == NULL) {
+			const char *regex = mxmlElementGetAttr(node, "regex");
+			if (regex == NULL) {
+				logg->logError("The tracepoint counter %s is missing the required tracepoint attribute", counter);
+				handleException();
+			} else {
+				logg->logMessage("Not using perf for counter %s", counter);
+				continue;
+			}
+		}
+
+		const char *arg = mxmlElementGetAttr(node, "arg");
+
+		long long id = getTracepointId(tracepoint, &printb);
+		if (id >= 0) {
+			logg->logMessage("Using perf for %s", counter);
+			setCounters(new PerfCounter(getCounters(), strdup(counter), PERF_TYPE_TRACEPOINT, id, arg == NULL ? 0 : PERF_SAMPLE_RAW, PERF_GROUP_LEADER | PERF_GROUP_PER_CPU, 1));
+			mTracepoints = new PerfTracepoint(mTracepoints, getCounters(), strdup(tracepoint));
+		}
+	}
+}
+
+bool PerfDriver::setup() {
+	// Check the kernel version
+	int release[3];
+	if (!getLinuxVersion(release)) {
+		logg->logMessage("getLinuxVersion failed");
+		return false;
+	}
+
+	if (KERNEL_VERSION(release[0], release[1], release[2]) < KERNEL_VERSION(3, 4, 0)) {
+		logg->logMessage("Unsupported kernel version");
+		return false;
+	}
+	mLegacySupport = KERNEL_VERSION(release[0], release[1], release[2]) < KERNEL_VERSION(3, 12, 0);
+
+	if (access(EVENTS_PATH, R_OK) != 0) {
+		logg->logMessage(EVENTS_PATH " does not exist, is CONFIG_TRACING and CONFIG_CONTEXT_SWITCH_TRACER enabled?");
+		return false;
+	}
+
+	// Add supported PMUs
+	bool foundCpu = false;
+	DIR *dir = opendir(PERF_DEVICES);
+	if (dir == NULL) {
+		logg->logMessage("opendir failed");
+		return false;
+	}
+
+	struct dirent *dirent;
+	while ((dirent = readdir(dir)) != NULL) {
+		logg->logMessage("perf pmu: %s", dirent->d_name);
+		for (int i = 0; i < ARRAY_LENGTH(gator_cpus); ++i) {
+			const struct gator_cpu *const gator_cpu = &gator_cpus[i];
+
+			// Do the names match exactly?
+			if (strcasecmp(gator_cpu->pmnc_name, dirent->d_name) != 0 &&
+			    // Do these names match but have the old vs new prefix?
+			    ((strncasecmp(dirent->d_name, OLD_PMU_PREFIX, sizeof(OLD_PMU_PREFIX) - 1) != 0 ||
+			      strncasecmp(gator_cpu->pmnc_name, NEW_PMU_PREFIX, sizeof(NEW_PMU_PREFIX) - 1) != 0 ||
+			      strcasecmp(dirent->d_name + sizeof(OLD_PMU_PREFIX) - 1, gator_cpu->pmnc_name + sizeof(NEW_PMU_PREFIX) - 1) != 0))) {
+				continue;
+			}
+
+			int type;
+			char buf[256];
+			snprintf(buf, sizeof(buf), PERF_DEVICES "/%s/type", dirent->d_name);
+			if (DriverSource::readIntDriver(buf, &type) != 0) {
+				continue;
+			}
+
+			foundCpu = true;
+			logg->logMessage("Adding cpu counters for %s with type %i", gator_cpu->pmnc_name, type);
+			addCpuCounters(gator_cpu->pmnc_name, type, gator_cpu->pmnc_counters);
+		}
+
+		for (int i = 0; i < ARRAY_LENGTH(uncore_counters); ++i) {
+			if (strcmp(dirent->d_name, uncore_counters[i].perfName) != 0) {
+				continue;
+			}
+
+			int type;
+			char buf[256];
+			snprintf(buf, sizeof(buf), PERF_DEVICES "/%s/type", dirent->d_name);
+			if (DriverSource::readIntDriver(buf, &type) != 0) {
+				continue;
+			}
+
+			logg->logMessage("Adding uncore counters for %s with type %i", uncore_counters[i].gatorName, type);
+			addUncoreCounters(uncore_counters[i].gatorName, type, uncore_counters[i].count, uncore_counters[i].hasCyclesCounter);
+		}
+	}
+	closedir(dir);
+
+	if (!foundCpu) {
+		// If no cpu was found based on pmu names, try by cpuid
+		for (int i = 0; i < ARRAY_LENGTH(gator_cpus); ++i) {
+			if (gSessionData->mMaxCpuId != gator_cpus[i].cpuid) {
+				continue;
+			}
+
+			foundCpu = true;
+			logg->logMessage("Adding cpu counters (based on cpuid) for %s", gator_cpus[i].pmnc_name);
+			addCpuCounters(gator_cpus[i].pmnc_name, PERF_TYPE_RAW, gator_cpus[i].pmnc_counters);
+		}
+	}
+
+	if (!foundCpu) {
+		// If all else fails, use the ARM architected counters
+		logg->logMessage("Using Other cpu");
+		addCpuCounters("Other", PERF_TYPE_RAW, 6);
+	}
+
+	// Add supported software counters
+	long long id;
+	DynBuf printb;
+
+	id = getTracepointId("irq/softirq_exit", &printb);
+	if (id >= 0) {
+		setCounters(new PerfCounter(getCounters(), "Linux_irq_softirq", PERF_TYPE_TRACEPOINT, id, PERF_SAMPLE_READ, PERF_GROUP_PER_CPU | PERF_GROUP_CPU, 0));
+	}
+
+	id = getTracepointId("irq/irq_handler_exit", &printb);
+	if (id >= 0) {
+		setCounters(new PerfCounter(getCounters(), "Linux_irq_irq", PERF_TYPE_TRACEPOINT, id, PERF_SAMPLE_READ, PERF_GROUP_PER_CPU | PERF_GROUP_CPU, 0));
+	}
+
+	id = getTracepointId(SCHED_SWITCH, &printb);
+	if (id >= 0) {
+		setCounters(new PerfCounter(getCounters(), "Linux_sched_switch", PERF_TYPE_TRACEPOINT, id, PERF_SAMPLE_READ, PERF_GROUP_PER_CPU | PERF_GROUP_CPU, 0));
+	}
+
+	id = getTracepointId(CPU_FREQUENCY, &printb);
+	if (id >= 0 && access("/sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_cur_freq", R_OK) == 0) {
+		setCounters(new CPUFreqDriver(getCounters(), id));
+	}
+
+	setCounters(new PerfCounter(getCounters(), "Linux_cpu_wait_contention", TYPE_DERIVED, -1, 0, 0, 0));
+
+	//Linux_cpu_wait_io
+
+	mIsSetup = true;
+	return true;
+}
+
+bool PerfDriver::summary(Buffer *const buffer) {
+	struct utsname utsname;
+	if (uname(&utsname) != 0) {
+		logg->logMessage("uname failed");
+		return false;
+	}
+
+	char buf[512];
+	snprintf(buf, sizeof(buf), "%s %s %s %s %s GNU/Linux", utsname.sysname, utsname.nodename, utsname.release, utsname.version, utsname.machine);
+
+	long pageSize = sysconf(_SC_PAGESIZE);
+	if (pageSize < 0) {
+		logg->logMessage("sysconf _SC_PAGESIZE failed");
+		return false;
+	}
+
+	struct timespec ts;
+	if (clock_gettime(CLOCK_REALTIME, &ts) != 0) {
+		logg->logMessage("clock_gettime failed");
+		return false;
+	}
+	const int64_t timestamp = (int64_t)ts.tv_sec * NS_PER_S + ts.tv_nsec;
+
+	const uint64_t monotonicStarted = getTime();
+	gSessionData->mMonotonicStarted = monotonicStarted;
+	const uint64_t currTime = 0;//getTime() - gSessionData->mMonotonicStarted;
+
+	buffer->summary(currTime, timestamp, monotonicStarted, monotonicStarted, buf, pageSize);
+
+	for (int i = 0; i < gSessionData->mCores; ++i) {
+		coreName(currTime, buffer, i);
+	}
+	buffer->commit(currTime);
+
+	return true;
+}
+
+void PerfDriver::coreName(const uint64_t currTime, Buffer *const buffer, const int cpu) {
+	const SharedData *const sharedData = gSessionData->mSharedData;
+	// Don't send information on a cpu we know nothing about
+	if (sharedData->mCpuIds[cpu] == -1) {
+		return;
+	}
+
+	int j;
+	for (j = 0; j < ARRAY_LENGTH(gator_cpus); ++j) {
+		if (gator_cpus[j].cpuid == sharedData->mCpuIds[cpu]) {
+			break;
+		}
+	}
+	if (j < ARRAY_LENGTH(gator_cpus) && gator_cpus[j].cpuid == sharedData->mCpuIds[cpu]) {
+		buffer->coreName(currTime, cpu, sharedData->mCpuIds[cpu], gator_cpus[j].core_name);
+	} else {
+		char buf[32];
+		if (sharedData->mCpuIds[cpu] == -1) {
+			snprintf(buf, sizeof(buf), "Unknown");
+		} else {
+			snprintf(buf, sizeof(buf), "Unknown (0x%.3x)", sharedData->mCpuIds[cpu]);
+		}
+		buffer->coreName(currTime, cpu, sharedData->mCpuIds[cpu], buf);
+	}
+}
+
+void PerfDriver::setupCounter(Counter &counter) {
+	PerfCounter *const perfCounter = static_cast<PerfCounter *>(findCounter(counter));
+	if (perfCounter == NULL) {
+		counter.setEnabled(false);
+		return;
+	}
+
+	// Don't use the config from counters XML if it's not set, ex: software counters
+	if (counter.getEvent() != -1) {
+		perfCounter->setConfig(counter.getEvent());
+	}
+	if (counter.getCount() > 0) {
+		// EBS
+		perfCounter->setCount(counter.getCount());
+		// Collect samples
+		perfCounter->setSampleType(perfCounter->getSampleType() | PERF_SAMPLE_TID | PERF_SAMPLE_IP);
+	}
+	perfCounter->setEnabled(true);
+	counter.setKey(perfCounter->getKey());
+}
+
+bool PerfDriver::enable(const uint64_t currTime, PerfGroup *const group, Buffer *const buffer) const {
+	for (PerfCounter *counter = static_cast<PerfCounter *>(getCounters()); counter != NULL; counter = static_cast<PerfCounter *>(counter->getNext())) {
+		if (counter->isEnabled() && (counter->getType() != TYPE_DERIVED) &&
+				!group->add(currTime, buffer, counter->getKey(), counter->getType(), counter->getConfig(), counter->getCount(), counter->getSampleType(), counter->getFlags())) {
+			logg->logMessage("PerfGroup::add failed");
+			return false;
+		}
+	}
+
+	return true;
+}
+
+void PerfDriver::read(Buffer *const buffer, const int cpu) {
+	for (PerfCounter *counter = static_cast<PerfCounter *>(getCounters()); counter != NULL; counter = static_cast<PerfCounter *>(counter->getNext())) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		counter->read(buffer, cpu);
+	}
+}
+
+static bool sendTracepointFormat(const uint64_t currTime, Buffer *const buffer, const char *const name, DynBuf *const printb, DynBuf *const b) {
+	if (!printb->printf(EVENTS_PATH "/%s/format", name)) {
+		logg->logMessage("DynBuf::printf failed");
+		return false;
+	}
+	if (!b->read(printb->getBuf())) {
+		logg->logMessage("DynBuf::read failed");
+		return false;
+	}
+	buffer->marshalFormat(currTime, b->getLength(), b->getBuf());
+
+	return true;
+}
+
+bool PerfDriver::sendTracepointFormats(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b) {
+	if (
+		!sendTracepointFormat(currTime, buffer, SCHED_SWITCH, printb, b) ||
+		!sendTracepointFormat(currTime, buffer, CPU_IDLE, printb, b) ||
+		!sendTracepointFormat(currTime, buffer, CPU_FREQUENCY, printb, b) ||
+		false) {
+		return false;
+	}
+
+	for (PerfTracepoint *tracepoint = mTracepoints; tracepoint != NULL; tracepoint = tracepoint->getNext()) {
+		if (tracepoint->getCounter()->isEnabled() && !sendTracepointFormat(currTime, buffer, tracepoint->getTracepoint(), printb, b)) {
+			return false;
+		}
+	}
+
+	return true;
+}
+
+long long PerfDriver::getTracepointId(const char *const name, DynBuf *const printb) {
+	if (!printb->printf(EVENTS_PATH "/%s/id", name)) {
+		logg->logMessage("DynBuf::printf failed");
+		return -1;
+	}
+
+	int64_t result;
+	if (DriverSource::readInt64Driver(printb->getBuf(), &result) != 0) {
+		logg->logMessage("Unable to read tracepoint id for %s", printb->getBuf());
+		return -1;
+	}
+
+	return result;
+}
diff --git a/tools/gator/daemon/PerfDriver.h b/tools/gator/daemon/PerfDriver.h
new file mode 100644
index 00000000000..a38fcde06e8
--- /dev/null
+++ b/tools/gator/daemon/PerfDriver.h
@@ -0,0 +1,59 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PERFDRIVER_H
+#define PERFDRIVER_H
+
+#include <stdint.h>
+
+#include "Driver.h"
+
+#define SCHED_SWITCH "sched/sched_switch"
+#define CPU_IDLE "power/cpu_idle"
+#define CPU_FREQUENCY "power/cpu_frequency"
+
+class Buffer;
+class DynBuf;
+class PerfGroup;
+class PerfTracepoint;
+
+class PerfDriver : public SimpleDriver {
+public:
+	PerfDriver();
+	~PerfDriver();
+
+	bool getLegacySupport() const { return mLegacySupport; }
+
+	void readEvents(mxml_node_t *const xml);
+	bool setup();
+	bool summary(Buffer *const buffer);
+	void coreName(const uint64_t currTime, Buffer *const buffer, const int cpu);
+	bool isSetup() const { return mIsSetup; }
+
+	void setupCounter(Counter &counter);
+
+	bool enable(const uint64_t currTime, PerfGroup *const group, Buffer *const buffer) const;
+	void read(Buffer *const buffer, const int cpu);
+	bool sendTracepointFormats(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b);
+
+	static long long getTracepointId(const char *const name, DynBuf *const printb);
+
+private:
+	void addCpuCounters(const char *const counterName, const int type, const int numCounters);
+	void addUncoreCounters(const char *const counterName, const int type, const int numCounters, const bool hasCyclesCounter);
+
+	bool mIsSetup;
+	bool mLegacySupport;
+	PerfTracepoint *mTracepoints;
+
+	// Intentionally undefined
+	PerfDriver(const PerfDriver &);
+	PerfDriver &operator=(const PerfDriver &);
+};
+
+#endif // PERFDRIVER_H
diff --git a/tools/gator/daemon/PerfGroup.cpp b/tools/gator/daemon/PerfGroup.cpp
new file mode 100644
index 00000000000..9b71531d2b1
--- /dev/null
+++ b/tools/gator/daemon/PerfGroup.cpp
@@ -0,0 +1,353 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "PerfGroup.h"
+
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "DynBuf.h"
+#include "Logging.h"
+#include "Monitor.h"
+#include "PerfBuffer.h"
+#include "SessionData.h"
+
+static const int schedSwitchKey = getEventKey();
+
+#define DEFAULT_PEA_ARGS(pea, additionalSampleType) \
+	pea.size = sizeof(pea); \
+	/* Emit time, read_format below, group leader id, and raw tracepoint info */ \
+	pea.sample_type = (gSessionData->mPerf.getLegacySupport() \
+			   ? PERF_SAMPLE_TID | PERF_SAMPLE_IP | PERF_SAMPLE_ID \
+			   : PERF_SAMPLE_IDENTIFIER ) | PERF_SAMPLE_TIME | additionalSampleType; \
+	/* Emit emit value in group format */ \
+	pea.read_format = PERF_FORMAT_ID | PERF_FORMAT_GROUP; \
+	/* start out disabled */ \
+	pea.disabled = 1; \
+	/* have a sampling interrupt happen when we cross the wakeup_watermark boundary */ \
+	pea.watermark = 1; \
+	/* Be conservative in flush size as only one buffer set is monitored */ \
+	pea.wakeup_watermark = BUF_SIZE / 2
+
+static int sys_perf_event_open(struct perf_event_attr *const attr, const pid_t pid, const int cpu, const int group_fd, const unsigned long flags) {
+	int fd = syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
+	if (fd < 0) {
+		return -1;
+	}
+	int fdf = fcntl(fd, F_GETFD);
+	if ((fdf == -1) || (fcntl(fd, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+		close(fd);
+		return -1;
+	}
+	return fd;
+}
+
+PerfGroup::PerfGroup(PerfBuffer *const pb) : mPb(pb), mSchedSwitchId(-1) {
+	memset(&mAttrs, 0, sizeof(mAttrs));
+	memset(&mFlags, 0, sizeof(mFlags));
+	memset(&mKeys, -1, sizeof(mKeys));
+	memset(&mFds, -1, sizeof(mFds));
+	memset(&mLeaders, -1, sizeof(mLeaders));
+}
+
+PerfGroup::~PerfGroup() {
+	for (int pos = ARRAY_LENGTH(mFds) - 1; pos >= 0; --pos) {
+		if (mFds[pos] >= 0) {
+			close(mFds[pos]);
+		}
+	}
+}
+
+int PerfGroup::doAdd(const uint64_t currTime, Buffer *const buffer, const int key, const __u32 type, const __u64 config, const __u64 sample, const __u64 sampleType, const int flags) {
+	int i;
+	for (i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+		if (mKeys[i] < 0) {
+			break;
+		}
+	}
+
+	if (i >= ARRAY_LENGTH(mKeys)) {
+		logg->logMessage("Too many counters");
+		return -1;
+	}
+
+	DEFAULT_PEA_ARGS(mAttrs[i], sampleType);
+	mAttrs[i].type = type;
+	mAttrs[i].config = config;
+	mAttrs[i].sample_period = sample;
+	// always be on the CPU but only a group leader can be pinned
+	mAttrs[i].pinned = (flags & PERF_GROUP_LEADER ? 1 : 0);
+	mAttrs[i].mmap = (flags & PERF_GROUP_MMAP ? 1 : 0);
+	mAttrs[i].comm = (flags & PERF_GROUP_COMM ? 1 : 0);
+	mAttrs[i].freq = (flags & PERF_GROUP_FREQ ? 1 : 0);
+	mAttrs[i].task = (flags & PERF_GROUP_TASK ? 1 : 0);
+	mAttrs[i].sample_id_all = (flags & PERF_GROUP_SAMPLE_ID_ALL ? 1 : 0);
+	mFlags[i] = flags;
+
+	mKeys[i] = key;
+
+	buffer->marshalPea(currTime, &mAttrs[i], key);
+
+	return i;
+}
+
+/* Counters from different hardware PMUs need to be in different
+ * groups. Software counters can be in the same group as the CPU and
+ * should be marked as PERF_GROUP_CPU. The big and little clusters can
+ * be in the same group as only one or the other will be available on
+ * a given CPU.
+ */
+int PerfGroup::getEffectiveType(const int type, const int flags) {
+	const int effectiveType = flags & PERF_GROUP_CPU ? (int)PERF_TYPE_HARDWARE : type;
+	if (effectiveType >= ARRAY_LENGTH(mLeaders)) {
+		logg->logError("perf type is too large, please increase the size of PerfGroup::mLeaders");
+		handleException();
+	}
+	return effectiveType;
+}
+
+bool PerfGroup::createCpuGroup(const uint64_t currTime, Buffer *const buffer) {
+	if (mSchedSwitchId < 0) {
+		DynBuf b;
+		mSchedSwitchId = PerfDriver::getTracepointId(SCHED_SWITCH, &b);
+		if (mSchedSwitchId < 0) {
+			logg->logMessage("Unable to read sched_switch id");
+			return false;
+		}
+	}
+
+	mLeaders[PERF_TYPE_HARDWARE] = doAdd(currTime, buffer, schedSwitchKey, PERF_TYPE_TRACEPOINT, mSchedSwitchId, 1, PERF_SAMPLE_READ | PERF_SAMPLE_RAW, PERF_GROUP_MMAP | PERF_GROUP_COMM | PERF_GROUP_TASK | PERF_GROUP_SAMPLE_ID_ALL | PERF_GROUP_PER_CPU | PERF_GROUP_LEADER | PERF_GROUP_CPU);
+	if (mLeaders[PERF_TYPE_HARDWARE] < 0) {
+		return false;
+	}
+
+	if (gSessionData->mSampleRate > 0 && !gSessionData->mIsEBS && doAdd(currTime, buffer, INT_MAX-PERF_TYPE_HARDWARE, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK, 1000000000UL / gSessionData->mSampleRate, PERF_SAMPLE_TID | PERF_SAMPLE_IP | PERF_SAMPLE_READ, PERF_GROUP_PER_CPU | PERF_GROUP_CPU) < 0) {
+		return false;
+	}
+
+	return true;
+}
+
+bool PerfGroup::add(const uint64_t currTime, Buffer *const buffer, const int key, const __u32 type, const __u64 config, const __u64 sample, const __u64 sampleType, const int flags) {
+	const int effectiveType = getEffectiveType(type, flags);
+
+	// Does a group exist for this already?
+	if (!(flags & PERF_GROUP_LEADER) && mLeaders[effectiveType] < 0) {
+		// Create it
+		if (effectiveType == PERF_TYPE_HARDWARE) {
+			if (!createCpuGroup(currTime, buffer)) {
+				return false;
+			}
+		} else {
+			// Non-CPU PMUs are sampled every 100ms for Sample Rate: None and EBS, otherwise they would never be sampled
+			const uint64_t timeout = gSessionData->mSampleRate > 0 && !gSessionData->mIsEBS ? 1000000000UL / gSessionData->mSampleRate : 100000000UL;
+			mLeaders[effectiveType] = doAdd(currTime, buffer, INT_MAX-effectiveType, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK, timeout, PERF_SAMPLE_READ, PERF_GROUP_LEADER);
+			if (mLeaders[effectiveType] < 0) {
+				return false;
+			}
+		}
+	}
+
+	if (!(flags & PERF_GROUP_LEADER) && effectiveType != PERF_TYPE_HARDWARE && (flags & PERF_GROUP_PER_CPU)) {
+		logg->logError("'uncore' counters are not permitted to be per-cpu");
+		handleException();
+	}
+
+	return doAdd(currTime, buffer, key, type, config, sample, sampleType, flags) >= 0;
+}
+
+int PerfGroup::prepareCPU(const int cpu, Monitor *const monitor) {
+	logg->logMessage("Onlining cpu %i", cpu);
+
+	for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+		if (mKeys[i] < 0) {
+			continue;
+		}
+
+		if ((cpu != 0) && !(mFlags[i] & PERF_GROUP_PER_CPU)) {
+			continue;
+		}
+
+		const int offset = i * gSessionData->mCores + cpu;
+		if (mFds[offset] >= 0) {
+			logg->logMessage("cpu already online or not correctly cleaned up");
+			return PG_FAILURE;
+		}
+
+		logg->logMessage("perf_event_open cpu: %i type: %i config: %lli sample: %lli sample_type: 0x%llx pinned: %lli mmap: %lli comm: %lli freq: %lli task: %lli sample_id_all: %lli", cpu, mAttrs[i].type, mAttrs[i].config, mAttrs[i].sample_period, mAttrs[i].sample_type, mAttrs[i].pinned, mAttrs[i].mmap, mAttrs[i].comm, mAttrs[i].freq, mAttrs[i].task, mAttrs[i].sample_id_all);
+		mFds[offset] = sys_perf_event_open(&mAttrs[i], -1, cpu, mAttrs[i].pinned ? -1 : mFds[mLeaders[getEffectiveType(mAttrs[i].type, mFlags[i])] * gSessionData->mCores + cpu], mAttrs[i].pinned ? 0 : PERF_FLAG_FD_OUTPUT);
+		if (mFds[offset] < 0) {
+			logg->logMessage("failed %s", strerror(errno));
+			if (errno == ENODEV) {
+				// The core is offline
+				return PG_CPU_OFFLINE;
+			}
+			if (errno == ENOENT) {
+				// This event doesn't apply to this CPU but should apply to a different one, ex bL
+				continue;
+			}
+			logg->logMessage("perf_event_open failed");
+			return PG_FAILURE;
+		}
+
+		if (!mPb->useFd(cpu, mFds[offset])) {
+			logg->logMessage("PerfBuffer::useFd failed");
+			return PG_FAILURE;
+		}
+
+
+		if (!monitor->add(mFds[offset])) {
+			logg->logMessage("Monitor::add failed");
+			return PG_FAILURE;
+		}
+	}
+
+	return PG_SUCCESS;
+}
+
+static bool readAndSend(const uint64_t currTime, Buffer *const buffer, const int fd, const int keyCount, const int *const keys) {
+	char buf[1024];
+	ssize_t bytes = read(fd, buf, sizeof(buf));
+	if (bytes < 0) {
+		logg->logMessage("read failed");
+		return false;
+	}
+	buffer->marshalKeysOld(currTime, keyCount, keys, bytes, buf);
+
+	return true;
+}
+
+int PerfGroup::onlineCPU(const uint64_t currTime, const int cpu, const bool enable, Buffer *const buffer) {
+	bool addedEvents = false;
+
+	if (!gSessionData->mPerf.getLegacySupport()) {
+		int idCount = 0;
+		int coreKeys[ARRAY_LENGTH(mKeys)];
+		__u64 ids[ARRAY_LENGTH(mKeys)];
+
+		for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+			const int fd = mFds[cpu + i * gSessionData->mCores];
+			if (fd < 0) {
+				continue;
+			}
+
+			coreKeys[idCount] = mKeys[i];
+			if (ioctl(fd, PERF_EVENT_IOC_ID, &ids[idCount]) != 0 &&
+					// Workaround for running 32-bit gatord on 64-bit systems, kernel patch in the works
+					ioctl(fd, (PERF_EVENT_IOC_ID & ~IOCSIZE_MASK) | (8 << _IOC_SIZESHIFT), &ids[idCount]) != 0) {
+				logg->logMessage("ioctl failed");
+				return 0;
+			}
+			++idCount;
+			addedEvents = true;
+		}
+
+		buffer->marshalKeys(currTime, idCount, ids, coreKeys);
+	} else {
+		int idCounts[ARRAY_LENGTH(mLeaders)] = { 0 };
+		int coreKeys[ARRAY_LENGTH(mLeaders)][ARRAY_LENGTH(mKeys)];
+		for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+			const int fd = mFds[cpu + i * gSessionData->mCores];
+			if (fd < 0) {
+				continue;
+			}
+
+			const int effectiveType = getEffectiveType(mAttrs[i].type, mFlags[i]);
+			if (mAttrs[i].pinned && mLeaders[effectiveType] != i) {
+				if (!readAndSend(currTime, buffer, fd, 1, mKeys + i)) {
+					return 0;
+				}
+			} else {
+				coreKeys[effectiveType][idCounts[effectiveType]] = mKeys[i];
+				++idCounts[effectiveType];
+				addedEvents = true;
+			}
+		}
+
+		for (int i = 0; i < ARRAY_LENGTH(mLeaders); ++i) {
+			if (idCounts[i] > 0 && !readAndSend(currTime, buffer, mFds[mLeaders[i] * gSessionData->mCores + cpu], idCounts[i], coreKeys[i])) {
+					return 0;
+			}
+		}
+	}
+
+	if (enable) {
+		for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+			int offset = i * gSessionData->mCores + cpu;
+			if (mFds[offset] >= 0 && ioctl(mFds[offset], PERF_EVENT_IOC_ENABLE, 0) < 0) {
+				logg->logMessage("ioctl failed");
+				return 0;
+			}
+		}
+	}
+
+	if (!addedEvents) {
+		logg->logMessage("no events came online");
+	}
+
+	return 1;
+}
+
+bool PerfGroup::offlineCPU(const int cpu) {
+	logg->logMessage("Offlining cpu %i", cpu);
+
+	for (int i = ARRAY_LENGTH(mKeys) - 1; i >= 0; --i) {
+		int offset = i * gSessionData->mCores + cpu;
+		if (mFds[offset] >= 0 && ioctl(mFds[offset], PERF_EVENT_IOC_DISABLE, 0) < 0) {
+			logg->logMessage("ioctl failed");
+			return false;
+		}
+	}
+
+	// Mark the buffer so that it will be released next time it's read
+	mPb->discard(cpu);
+
+	for (int i = ARRAY_LENGTH(mKeys) - 1; i >= 0; --i) {
+		if (mKeys[i] < 0) {
+			continue;
+		}
+
+		int offset = i * gSessionData->mCores + cpu;
+		if (mFds[offset] >= 0) {
+			close(mFds[offset]);
+			mFds[offset] = -1;
+		}
+	}
+
+	return true;
+}
+
+bool PerfGroup::start() {
+	for (int pos = 0; pos < ARRAY_LENGTH(mFds); ++pos) {
+		if (mFds[pos] >= 0 && ioctl(mFds[pos], PERF_EVENT_IOC_ENABLE, 0) < 0) {
+			logg->logMessage("ioctl failed");
+			goto fail;
+		}
+	}
+
+	return true;
+
+ fail:
+	stop();
+
+	return false;
+}
+
+void PerfGroup::stop() {
+	for (int pos = ARRAY_LENGTH(mFds) - 1; pos >= 0; --pos) {
+		if (mFds[pos] >= 0) {
+			ioctl(mFds[pos], PERF_EVENT_IOC_DISABLE, 0);
+		}
+	}
+}
diff --git a/tools/gator/daemon/PerfGroup.h b/tools/gator/daemon/PerfGroup.h
new file mode 100644
index 00000000000..f30d3a6a9c6
--- /dev/null
+++ b/tools/gator/daemon/PerfGroup.h
@@ -0,0 +1,74 @@
+ /**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PERF_GROUP
+#define PERF_GROUP
+
+#include <stdint.h>
+
+// Use a snapshot of perf_event.h as it may be more recent than what is on the target and if not newer features won't be supported anyways
+#include "k/perf_event.h"
+
+#include "Config.h"
+
+class Buffer;
+class Monitor;
+class PerfBuffer;
+
+enum PerfGroupFlags {
+	PERF_GROUP_MMAP          = 1 << 0,
+	PERF_GROUP_COMM          = 1 << 1,
+	PERF_GROUP_FREQ          = 1 << 2,
+	PERF_GROUP_TASK          = 1 << 3,
+	PERF_GROUP_SAMPLE_ID_ALL = 1 << 4,
+	PERF_GROUP_PER_CPU       = 1 << 5,
+	PERF_GROUP_LEADER        = 1 << 6,
+	PERF_GROUP_CPU           = 1 << 7,
+};
+
+enum {
+	PG_SUCCESS = 0,
+	PG_FAILURE,
+	PG_CPU_OFFLINE,
+};
+
+class PerfGroup {
+public:
+	PerfGroup(PerfBuffer *const pb);
+	~PerfGroup();
+
+	bool createCpuGroup(const uint64_t currTime, Buffer *const buffer);
+	bool add(const uint64_t currTime, Buffer *const buffer, const int key, const __u32 type, const __u64 config, const __u64 sample, const __u64 sampleType, const int flags);
+	// Safe to call concurrently
+	int prepareCPU(const int cpu, Monitor *const monitor);
+	// Not safe to call concurrently. Returns the number of events enabled
+	int onlineCPU(const uint64_t currTime, const int cpu, const bool enable, Buffer *const buffer);
+	bool offlineCPU(int cpu);
+	bool start();
+	void stop();
+
+private:
+	int getEffectiveType(const int type, const int flags);
+	int doAdd(const uint64_t currTime, Buffer *const buffer, const int key, const __u32 type, const __u64 config, const __u64 sample, const __u64 sampleType, const int flags);
+
+	// 2* to be conservative for sched_switch, cpu_idle, hrtimer and non-CPU groups
+	struct perf_event_attr mAttrs[2*MAX_PERFORMANCE_COUNTERS];
+	PerfBuffer *const mPb;
+	int mFlags[2*MAX_PERFORMANCE_COUNTERS];
+	int mKeys[2*MAX_PERFORMANCE_COUNTERS];
+	int mFds[NR_CPUS * (2*MAX_PERFORMANCE_COUNTERS)];
+	// Offset in mAttrs, mFlags and mKeys of the group leaders for each perf type
+	int mLeaders[16];
+	int mSchedSwitchId;
+
+	// Intentionally undefined
+	PerfGroup(const PerfGroup &);
+	PerfGroup &operator=(const PerfGroup &);
+};
+
+#endif // PERF_GROUP
diff --git a/tools/gator/daemon/PerfSource.cpp b/tools/gator/daemon/PerfSource.cpp
new file mode 100644
index 00000000000..9f34bbd1e54
--- /dev/null
+++ b/tools/gator/daemon/PerfSource.cpp
@@ -0,0 +1,430 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "PerfSource.h"
+
+#include <dirent.h>
+#include <errno.h>
+#include <signal.h>
+#include <string.h>
+#include <sys/prctl.h>
+#include <sys/resource.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "Child.h"
+#include "DynBuf.h"
+#include "Logging.h"
+#include "PerfDriver.h"
+#include "Proc.h"
+#include "SessionData.h"
+
+#ifndef SCHED_RESET_ON_FORK
+#define SCHED_RESET_ON_FORK 0x40000000
+#endif
+
+extern Child *child;
+
+static const int cpuIdleKey = getEventKey();
+
+static void *syncFunc(void *arg)
+{
+	struct timespec ts;
+	int64_t nextTime = gSessionData->mMonotonicStarted;
+	int err;
+	(void)arg;
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-sync", 0, 0, 0);
+
+	// Mask all signals so that this thread will not be woken up
+	{
+		sigset_t set;
+		if (sigfillset(&set) != 0) {
+			logg->logError("sigfillset failed");
+			handleException();
+		}
+		if ((err = pthread_sigmask(SIG_SETMASK, &set, NULL)) != 0) {
+			logg->logError("pthread_sigmask failed");
+			handleException();
+		}
+	}
+
+	for (;;) {
+		if (clock_gettime(CLOCK_MONOTONIC_RAW, &ts) != 0) {
+			logg->logError("clock_gettime failed");
+			handleException();
+		}
+		const int64_t currTime = ts.tv_sec * NS_PER_S + ts.tv_nsec;
+
+		// Wake up once a second
+		nextTime += NS_PER_S;
+
+		// Always sleep more than 1 ms, hopefully things will line up better next time
+		const int64_t sleepTime = max(nextTime - currTime, (int64_t)(NS_PER_MS + 1));
+		ts.tv_sec = sleepTime/NS_PER_S;
+		ts.tv_nsec = sleepTime % NS_PER_S;
+
+		err = nanosleep(&ts, NULL);
+		if (err != 0) {
+			fprintf(stderr, "clock_nanosleep failed: %s\n", strerror(err));
+			return NULL;
+		}
+	}
+
+	return NULL;
+}
+
+static long getMaxCoreNum() {
+	DIR *dir = opendir("/sys/devices/system/cpu");
+	if (dir == NULL) {
+		logg->logError("Unable to determine the number of cores on the target, opendir failed");
+		handleException();
+	}
+
+	long maxCoreNum = -1;
+	struct dirent *dirent;
+	while ((dirent = readdir(dir)) != NULL) {
+		if (strncmp(dirent->d_name, "cpu", 3) == 0) {
+			char *endptr;
+			errno = 0;
+			long coreNum = strtol(dirent->d_name + 3, &endptr, 10);
+			if ((errno == 0) && (*endptr == '\0') && (coreNum >= maxCoreNum)) {
+				maxCoreNum = coreNum + 1;
+			}
+		}
+	}
+	closedir(dir);
+
+	if (maxCoreNum < 1) {
+		logg->logError("Unable to determine the number of cores on the target, no cpu# directories found");
+		handleException();
+	}
+
+	if (maxCoreNum >= NR_CPUS) {
+		logg->logError("Too many cores on the target, please increase NR_CPUS in Config.h");
+		handleException();
+	}
+
+	return maxCoreNum;
+}
+
+PerfSource::PerfSource(sem_t *senderSem, sem_t *startProfile) : mSummary(0, FRAME_SUMMARY, 1024, senderSem), mBuffer(NULL), mCountersBuf(), mCountersGroup(&mCountersBuf), mMonitor(), mUEvent(), mSenderSem(senderSem), mStartProfile(startProfile), mInterruptFd(-1), mIsDone(false) {
+	long l = sysconf(_SC_PAGE_SIZE);
+	if (l < 0) {
+		logg->logError("Unable to obtain the page size");
+		handleException();
+	}
+	gSessionData->mPageSize = static_cast<int>(l);
+	gSessionData->mCores = static_cast<int>(getMaxCoreNum());
+}
+
+PerfSource::~PerfSource() {
+	delete mBuffer;
+}
+
+bool PerfSource::prepare() {
+	DynBuf printb;
+	DynBuf b1;
+	long long cpuIdleId;
+
+	// MonotonicStarted has not yet been assigned!
+	const uint64_t currTime = 0;//getTime() - gSessionData->mMonotonicStarted;
+
+	mBuffer = new Buffer(0, FRAME_PERF_ATTRS, gSessionData->mTotalBufferSize*1024*1024, mSenderSem);
+
+	// Reread cpuinfo since cores may have changed since startup
+	gSessionData->readCpuInfo();
+
+	if (0
+			|| !mMonitor.init()
+			|| !mUEvent.init()
+			|| !mMonitor.add(mUEvent.getFd())
+
+			|| (cpuIdleId = PerfDriver::getTracepointId(CPU_IDLE, &printb)) < 0
+
+			|| !gSessionData->mPerf.sendTracepointFormats(currTime, mBuffer, &printb, &b1)
+
+			|| !mCountersGroup.createCpuGroup(currTime, mBuffer)
+			|| !mCountersGroup.add(currTime, mBuffer, cpuIdleKey, PERF_TYPE_TRACEPOINT, cpuIdleId, 1, PERF_SAMPLE_RAW, PERF_GROUP_LEADER | PERF_GROUP_PER_CPU)
+
+			|| !gSessionData->mPerf.enable(currTime, &mCountersGroup, mBuffer)
+			|| 0) {
+		logg->logMessage("perf setup failed, are you running Linux 3.4 or later?");
+		return false;
+	}
+
+	for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+		const int result = mCountersGroup.prepareCPU(cpu, &mMonitor);
+		if ((result != PG_SUCCESS) && (result != PG_CPU_OFFLINE)) {
+			logg->logError("PerfGroup::prepareCPU on mCountersGroup failed");
+			handleException();
+		}
+	}
+
+	int numEvents = 0;
+	for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+		numEvents += mCountersGroup.onlineCPU(currTime, cpu, false, mBuffer);
+	}
+	if (numEvents <= 0) {
+		logg->logMessage("PerfGroup::onlineCPU failed on all cores");
+		return false;
+	}
+
+	// Send the summary right before the start so that the monotonic delta is close to the start time
+	if (!gSessionData->mPerf.summary(&mSummary)) {
+		logg->logError("PerfDriver::summary failed");
+		handleException();
+	}
+
+	// Start the timer thread to used to sync perf and monotonic raw times
+	pthread_t syncThread;
+	if (pthread_create(&syncThread, NULL, syncFunc, NULL)) {
+		logg->logError("pthread_create failed");
+		handleException();
+	}
+	struct sched_param param;
+	param.sched_priority = sched_get_priority_max(SCHED_FIFO);
+	if (pthread_setschedparam(syncThread, SCHED_FIFO | SCHED_RESET_ON_FORK, &param) != 0) {
+		logg->logError("pthread_setschedparam failed");
+		handleException();
+	}
+
+	mBuffer->commit(currTime);
+
+	return true;
+}
+
+struct ProcThreadArgs {
+	Buffer *mBuffer;
+	uint64_t mCurrTime;
+	bool mIsDone;
+};
+
+void *procFunc(void *arg) {
+	DynBuf printb;
+	DynBuf b;
+	const ProcThreadArgs *const args = (ProcThreadArgs *)arg;
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-proc", 0, 0, 0);
+
+	// Gator runs at a high priority, reset the priority to the default
+	if (setpriority(PRIO_PROCESS, syscall(__NR_gettid), 0) == -1) {
+		logg->logError("setpriority failed");
+		handleException();
+	}
+
+	if (!readProcMaps(args->mCurrTime, args->mBuffer, &printb, &b)) {
+		logg->logError("readProcMaps failed");
+		handleException();
+	}
+
+	if (!readKallsyms(args->mCurrTime, args->mBuffer, &args->mIsDone)) {
+		logg->logError("readKallsyms failed");
+		handleException();
+	}
+	args->mBuffer->commit(args->mCurrTime);
+
+	return NULL;
+}
+
+static const char CPU_DEVPATH[] = "/devices/system/cpu/cpu";
+
+void PerfSource::run() {
+	int pipefd[2];
+	pthread_t procThread;
+	ProcThreadArgs procThreadArgs;
+
+	if (pipe_cloexec(pipefd) != 0) {
+		logg->logError("pipe failed");
+		handleException();
+	}
+	mInterruptFd = pipefd[1];
+
+	if (!mMonitor.add(pipefd[0])) {
+		logg->logError("Monitor::add failed");
+		handleException();
+	}
+
+	{
+		DynBuf printb;
+		DynBuf b1;
+		DynBuf b2;
+
+		const uint64_t currTime = getTime() - gSessionData->mMonotonicStarted;
+
+		// Start events before reading proc to avoid race conditions
+		if (!mCountersGroup.start()) {
+			logg->logError("PerfGroup::start failed");
+			handleException();
+		}
+
+		mBuffer->perfCounterHeader(currTime);
+		for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+			gSessionData->mPerf.read(mBuffer, cpu);
+		}
+		mBuffer->perfCounterFooter(currTime);
+
+		if (!readProcComms(currTime, mBuffer, &printb, &b1, &b2)) {
+			logg->logError("readProcComms failed");
+			handleException();
+		}
+		mBuffer->commit(currTime);
+
+		// Postpone reading kallsyms as on android adb gets too backed up and data is lost
+		procThreadArgs.mBuffer = mBuffer;
+		procThreadArgs.mCurrTime = currTime;
+		procThreadArgs.mIsDone = false;
+		if (pthread_create(&procThread, NULL, procFunc, &procThreadArgs)) {
+			logg->logError("pthread_create failed");
+			handleException();
+		}
+	}
+
+	sem_post(mStartProfile);
+
+	const uint64_t NO_RATE = ~0ULL;
+	const uint64_t rate = gSessionData->mLiveRate > 0 && gSessionData->mSampleRate > 0 ? gSessionData->mLiveRate : NO_RATE;
+	uint64_t nextTime = 0;
+	int timeout = rate != NO_RATE ? 0 : -1;
+	while (gSessionData->mSessionIsActive) {
+		// +1 for uevents, +1 for pipe
+		struct epoll_event events[NR_CPUS + 2];
+		int ready = mMonitor.wait(events, ARRAY_LENGTH(events), timeout);
+		if (ready < 0) {
+			logg->logError("Monitor::wait failed");
+			handleException();
+		}
+		const uint64_t currTime = getTime() - gSessionData->mMonotonicStarted;
+
+		for (int i = 0; i < ready; ++i) {
+			if (events[i].data.fd == mUEvent.getFd()) {
+				if (!handleUEvent(currTime)) {
+					logg->logError("PerfSource::handleUEvent failed");
+					handleException();
+				}
+				break;
+			}
+		}
+
+		// send a notification that data is ready
+		sem_post(mSenderSem);
+
+		// In one shot mode, stop collection once all the buffers are filled
+		if (gSessionData->mOneShot && gSessionData->mSessionIsActive && ((mSummary.bytesAvailable() <= 0) || (mBuffer->bytesAvailable() <= 0) || mCountersBuf.isFull())) {
+			logg->logMessage("One shot (perf)");
+			child->endSession();
+		}
+
+		if (rate != NO_RATE) {
+			while (currTime > nextTime) {
+				nextTime += rate;
+			}
+			// + NS_PER_MS - 1 to ensure always rounding up
+			timeout = max(0, (int)((nextTime + NS_PER_MS - 1 - getTime() + gSessionData->mMonotonicStarted)/NS_PER_MS));
+		}
+	}
+
+	procThreadArgs.mIsDone = true;
+	pthread_join(procThread, NULL);
+	mCountersGroup.stop();
+	mBuffer->setDone();
+	mIsDone = true;
+
+	// send a notification that data is ready
+	sem_post(mSenderSem);
+
+	mInterruptFd = -1;
+	close(pipefd[0]);
+	close(pipefd[1]);
+}
+
+bool PerfSource::handleUEvent(const uint64_t currTime) {
+	UEventResult result;
+	if (!mUEvent.read(&result)) {
+		logg->logMessage("UEvent::Read failed");
+		return false;
+	}
+
+	if (strcmp(result.mSubsystem, "cpu") == 0) {
+		if (strncmp(result.mDevPath, CPU_DEVPATH, sizeof(CPU_DEVPATH) - 1) != 0) {
+			logg->logMessage("Unexpected cpu DEVPATH format");
+			return false;
+		}
+		char *endptr;
+		errno = 0;
+		int cpu = strtol(result.mDevPath + sizeof(CPU_DEVPATH) - 1, &endptr, 10);
+		if (errno != 0 || *endptr != '\0') {
+			logg->logMessage("strtol failed");
+			return false;
+		}
+
+		if (cpu >= gSessionData->mCores) {
+			logg->logError("Only %i cores are expected but core %i reports %s", gSessionData->mCores, cpu, result.mAction);
+			handleException();
+		}
+
+		if (strcmp(result.mAction, "online") == 0) {
+			mBuffer->onlineCPU(currTime, cpu);
+			// Only call onlineCPU if prepareCPU succeeded
+			bool ret = false;
+			int err = mCountersGroup.prepareCPU(cpu, &mMonitor);
+			if (err == PG_CPU_OFFLINE) {
+				ret = true;
+			} else if (err == PG_SUCCESS) {
+				if (mCountersGroup.onlineCPU(currTime, cpu, true, mBuffer) > 0) {
+					mBuffer->perfCounterHeader(currTime);
+					gSessionData->mPerf.read(mBuffer, cpu);
+					mBuffer->perfCounterFooter(currTime);
+					ret = true;
+				}
+			}
+			mBuffer->commit(currTime);
+
+			gSessionData->readCpuInfo();
+			gSessionData->mPerf.coreName(currTime, &mSummary, cpu);
+			mSummary.commit(currTime);
+			return ret;
+		} else if (strcmp(result.mAction, "offline") == 0) {
+			const bool ret = mCountersGroup.offlineCPU(cpu);
+			mBuffer->offlineCPU(currTime, cpu);
+			return ret;
+		}
+	}
+
+	return true;
+}
+
+void PerfSource::interrupt() {
+	if (mInterruptFd >= 0) {
+		int8_t c = 0;
+		// Write to the pipe to wake the monitor which will cause mSessionIsActive to be reread
+		if (::write(mInterruptFd, &c, sizeof(c)) != sizeof(c)) {
+			logg->logError("write failed");
+			handleException();
+		}
+	}
+}
+
+bool PerfSource::isDone () {
+	return mBuffer->isDone() && mIsDone && mCountersBuf.isEmpty();
+}
+
+void PerfSource::write (Sender *sender) {
+	if (!mSummary.isDone()) {
+		mSummary.write(sender);
+		gSessionData->mSentSummary = true;
+	}
+	if (!mBuffer->isDone()) {
+		mBuffer->write(sender);
+	}
+	if (!mCountersBuf.send(sender)) {
+		logg->logError("PerfBuffer::send failed");
+		handleException();
+	}
+}
diff --git a/tools/gator/daemon/PerfSource.h b/tools/gator/daemon/PerfSource.h
new file mode 100644
index 00000000000..feec1c26992
--- /dev/null
+++ b/tools/gator/daemon/PerfSource.h
@@ -0,0 +1,54 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PERFSOURCE_H
+#define PERFSOURCE_H
+
+#include <semaphore.h>
+
+#include "Buffer.h"
+#include "Monitor.h"
+#include "PerfBuffer.h"
+#include "PerfGroup.h"
+#include "Source.h"
+#include "UEvent.h"
+
+class Sender;
+
+class PerfSource : public Source {
+public:
+	PerfSource(sem_t *senderSem, sem_t *startProfile);
+	~PerfSource();
+
+	bool prepare();
+	void run();
+	void interrupt();
+
+	bool isDone();
+	void write(Sender *sender);
+
+private:
+	bool handleUEvent(const uint64_t currTime);
+
+	Buffer mSummary;
+	Buffer *mBuffer;
+	PerfBuffer mCountersBuf;
+	PerfGroup mCountersGroup;
+	Monitor mMonitor;
+	UEvent mUEvent;
+	sem_t *const mSenderSem;
+	sem_t *const mStartProfile;
+	int mInterruptFd;
+	bool mIsDone;
+
+	// Intentionally undefined
+	PerfSource(const PerfSource &);
+	PerfSource &operator=(const PerfSource &);
+};
+
+#endif // PERFSOURCE_H
diff --git a/tools/gator/daemon/Proc.cpp b/tools/gator/daemon/Proc.cpp
new file mode 100644
index 00000000000..ffe1a786b98
--- /dev/null
+++ b/tools/gator/daemon/Proc.cpp
@@ -0,0 +1,307 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Proc.h"
+
+#include <dirent.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "DynBuf.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+struct ProcStat {
+	// From linux-dev/include/linux/sched.h
+#define TASK_COMM_LEN 16
+	// TASK_COMM_LEN may grow, so be ready for it to get larger
+	char comm[2*TASK_COMM_LEN];
+	long numThreads;
+};
+
+static bool readProcStat(ProcStat *const ps, const char *const pathname, DynBuf *const b) {
+	if (!b->read(pathname)) {
+		logg->logMessage("DynBuf::read failed, likely because the thread exited");
+		// This is not a fatal error - the thread just doesn't exist any more
+		return true;
+	}
+
+	char *comm = strchr(b->getBuf(), '(');
+	if (comm == NULL) {
+		logg->logMessage("parsing stat failed");
+		return false;
+	}
+	++comm;
+	char *const str = strrchr(comm, ')');
+	if (str == NULL) {
+		logg->logMessage("parsing stat failed");
+		return false;
+	}
+	*str = '\0';
+	strncpy(ps->comm, comm, sizeof(ps->comm) - 1);
+	ps->comm[sizeof(ps->comm) - 1] = '\0';
+
+	const int count = sscanf(str + 2, " %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %ld", &ps->numThreads);
+	if (count != 1) {
+		logg->logMessage("sscanf failed");
+		return false;
+	}
+
+	return true;
+}
+
+static const char APP_PROCESS[] = "app_process";
+
+static const char *readProcExe(DynBuf *const printb, const int pid, const int tid, DynBuf *const b) {
+	if (tid == -1 ? !printb->printf("/proc/%i/exe", pid)
+			: !printb->printf("/proc/%i/task/%i/exe", pid, tid)) {
+		logg->logMessage("DynBuf::printf failed");
+		return NULL;
+	}
+
+	const int err = b->readlink(printb->getBuf());
+	const char *image;
+	if (err == 0) {
+		image = b->getBuf();
+	} else if (err == -ENOENT) {
+		// readlink /proc/[pid]/exe returns ENOENT for kernel threads
+		image = "\0";
+	} else {
+		logg->logMessage("DynBuf::readlink failed");
+		return NULL;
+	}
+
+	// Android apps are run by app_process but the cmdline is changed to reference the actual app name
+	// On 64-bit android app_process can be app_process32 or app_process64
+	if (strstr(image, APP_PROCESS) == NULL) {
+		return image;
+	}
+
+	if (tid == -1 ? !printb->printf("/proc/%i/cmdline", pid)
+			: !printb->printf("/proc/%i/task/%i/cmdline", pid, tid)) {
+		logg->logMessage("DynBuf::printf failed");
+		return NULL;
+	}
+
+	if (!b->read(printb->getBuf())) {
+		logg->logMessage("DynBuf::read failed, likely because the thread exited");
+		return NULL;
+	}
+
+	return b->getBuf();
+}
+
+static bool readProcTask(const uint64_t currTime, Buffer *const buffer, const int pid, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2) {
+	bool result = false;
+
+	if (!b1->printf("/proc/%i/task", pid)) {
+		logg->logMessage("DynBuf::printf failed");
+		return result;
+	}
+	DIR *task = opendir(b1->getBuf());
+	if (task == NULL) {
+		logg->logMessage("opendir failed");
+		// This is not a fatal error - the thread just doesn't exist any more
+		return true;
+	}
+
+	struct dirent *dirent;
+	while ((dirent = readdir(task)) != NULL) {
+		char *endptr;
+		const int tid = strtol(dirent->d_name, &endptr, 10);
+		if (*endptr != '\0') {
+			// Ignore task items that are not integers like ., etc...
+			continue;
+		}
+
+		if (!printb->printf("/proc/%i/task/%i/stat", pid, tid)) {
+			logg->logMessage("DynBuf::printf failed");
+			goto fail;
+		}
+		ProcStat ps;
+		if (!readProcStat(&ps, printb->getBuf(), b1)) {
+			logg->logMessage("readProcStat failed");
+			goto fail;
+		}
+
+		const char *const image = readProcExe(printb, pid, tid, b2);
+		if (image == NULL) {
+			logg->logMessage("readImage failed");
+			goto fail;
+		}
+
+		buffer->marshalComm(currTime, pid, tid, image, ps.comm);
+	}
+
+	result = true;
+
+ fail:
+	closedir(task);
+
+	return result;
+}
+
+bool readProcComms(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2) {
+	bool result = false;
+
+	DIR *proc = opendir("/proc");
+	if (proc == NULL) {
+		logg->logMessage("opendir failed");
+		return result;
+	}
+
+	struct dirent *dirent;
+	while ((dirent = readdir(proc)) != NULL) {
+		char *endptr;
+		const int pid = strtol(dirent->d_name, &endptr, 10);
+		if (*endptr != '\0') {
+			// Ignore proc items that are not integers like ., cpuinfo, etc...
+			continue;
+		}
+
+		if (!printb->printf("/proc/%i/stat", pid)) {
+			logg->logMessage("DynBuf::printf failed");
+			goto fail;
+		}
+		ProcStat ps;
+		if (!readProcStat(&ps, printb->getBuf(), b1)) {
+			logg->logMessage("readProcStat failed");
+			goto fail;
+		}
+
+		if (ps.numThreads <= 1) {
+			const char *const image = readProcExe(printb, pid, -1, b1);
+			if (image == NULL) {
+				logg->logMessage("readImage failed");
+				goto fail;
+			}
+
+			buffer->marshalComm(currTime, pid, pid, image, ps.comm);
+		} else {
+			if (!readProcTask(currTime, buffer, pid, printb, b1, b2)) {
+				logg->logMessage("readProcTask failed");
+				goto fail;
+			}
+		}
+	}
+
+	result = true;
+
+ fail:
+	closedir(proc);
+
+	return result;
+}
+
+bool readProcMaps(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b) {
+	bool result = false;
+
+	DIR *proc = opendir("/proc");
+	if (proc == NULL) {
+		logg->logMessage("opendir failed");
+		return result;
+	}
+
+	struct dirent *dirent;
+	while ((dirent = readdir(proc)) != NULL) {
+		char *endptr;
+		const int pid = strtol(dirent->d_name, &endptr, 10);
+		if (*endptr != '\0') {
+			// Ignore proc items that are not integers like ., cpuinfo, etc...
+			continue;
+		}
+
+		if (!printb->printf("/proc/%i/maps", pid)) {
+			logg->logMessage("DynBuf::printf failed");
+			goto fail;
+		}
+		if (!b->read(printb->getBuf())) {
+			logg->logMessage("DynBuf::read failed, likely because the process exited");
+			// This is not a fatal error - the process just doesn't exist any more
+			continue;
+		}
+
+		buffer->marshalMaps(currTime, pid, pid, b->getBuf());
+	}
+
+	result = true;
+
+ fail:
+	closedir(proc);
+
+	return result;
+}
+
+bool readKallsyms(const uint64_t currTime, Buffer *const buffer, const bool *const isDone) {
+	int fd = ::open("/proc/kallsyms", O_RDONLY | O_CLOEXEC);
+
+	if (fd < 0) {
+		logg->logMessage("open failed");
+		return true;
+	};
+
+	char buf[1<<12];
+	ssize_t pos = 0;
+	while (gSessionData->mSessionIsActive && !ACCESS_ONCE(*isDone)) {
+		// Assert there is still space in the buffer
+		if (sizeof(buf) - pos - 1 == 0) {
+			logg->logError("no space left in buffer");
+			handleException();
+		}
+
+		{
+			// -1 to reserve space for \0
+			const ssize_t bytes = ::read(fd, buf + pos, sizeof(buf) - pos - 1);
+			if (bytes < 0) {
+				logg->logError("read failed");
+				handleException();
+			}
+			if (bytes == 0) {
+				// Assert the buffer is empty
+				if (pos != 0) {
+					logg->logError("buffer not empty on eof");
+					handleException();
+				}
+				break;
+			}
+			pos += bytes;
+		}
+
+		ssize_t newline;
+		// Find the last '\n'
+		for (newline = pos - 1; newline >= 0; --newline) {
+			if (buf[newline] == '\n') {
+				const char was = buf[newline + 1];
+				buf[newline + 1] = '\0';
+				buffer->marshalKallsyms(currTime, buf);
+				// Sleep 3 ms to avoid sending out too much data too quickly
+				usleep(3000);
+				buf[0] = was;
+				// Assert the memory regions do not overlap
+				if (pos - newline >= newline + 1) {
+					logg->logError("memcpy src and dst overlap");
+					handleException();
+				}
+				if (pos - newline - 2 > 0) {
+					memcpy(buf + 1, buf + newline + 2, pos - newline - 2);
+				}
+				pos -= newline + 1;
+				break;
+			}
+		}
+	}
+
+	close(fd);
+
+	return true;
+}
diff --git a/tools/gator/daemon/Proc.h b/tools/gator/daemon/Proc.h
new file mode 100644
index 00000000000..fcc48c546d0
--- /dev/null
+++ b/tools/gator/daemon/Proc.h
@@ -0,0 +1,21 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PROC_H
+#define PROC_H
+
+#include <stdint.h>
+
+class Buffer;
+class DynBuf;
+
+bool readProcComms(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2);
+bool readProcMaps(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b);
+bool readKallsyms(const uint64_t currTime, Buffer *const buffer, const bool *const isDone);
+
+#endif // PROC_H
diff --git a/tools/gator/daemon/Sender.cpp b/tools/gator/daemon/Sender.cpp
new file mode 100644
index 00000000000..71ddfced689
--- /dev/null
+++ b/tools/gator/daemon/Sender.cpp
@@ -0,0 +1,143 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Sender.h"
+
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Logging.h"
+#include "OlySocket.h"
+#include "SessionData.h"
+
+Sender::Sender(OlySocket* socket) {
+	mDataFile = NULL;
+	mDataSocket = NULL;
+
+	// Set up the socket connection
+	if (socket) {
+		char streamline[64] = {0};
+		mDataSocket = socket;
+
+		// Receive magic sequence - can wait forever
+		// Streamline will send data prior to the magic sequence for legacy support, which should be ignored for v4+
+		while (strcmp("STREAMLINE", streamline) != 0) {
+			if (mDataSocket->receiveString(streamline, sizeof(streamline)) == -1) {
+				logg->logError("Socket disconnected");
+				handleException();
+			}
+		}
+
+		// Send magic sequence - must be done first, after which error messages can be sent
+		char magic[32];
+		snprintf(magic, 32, "GATOR %i\n", PROTOCOL_VERSION);
+		mDataSocket->send(magic, strlen(magic));
+
+		gSessionData->mWaitingOnCommand = true;
+		logg->logMessage("Completed magic sequence");
+	}
+
+	pthread_mutexattr_t attr;
+	if (pthread_mutexattr_init(&attr) != 0 ||
+			pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_ERRORCHECK) != 0 ||
+			pthread_mutex_init(&mSendMutex, &attr) != 0 ||
+			pthread_mutexattr_destroy(&attr) != 0 ||
+			false) {
+		logg->logError("Unable to setup mutex");
+		handleException();
+	}
+}
+
+Sender::~Sender() {
+	// Just close it as the client socket is on the stack
+	if (mDataSocket != NULL) {
+		mDataSocket->closeSocket();
+		mDataSocket = NULL;
+	}
+	if (mDataFile != NULL) {
+		fclose(mDataFile);
+	}
+}
+
+void Sender::createDataFile(char* apcDir) {
+	if (apcDir == NULL) {
+		return;
+	}
+
+	mDataFileName = (char*)malloc(strlen(apcDir) + 12);
+	sprintf(mDataFileName, "%s/0000000000", apcDir);
+	mDataFile = fopen_cloexec(mDataFileName, "wb");
+	if (!mDataFile) {
+		logg->logError("Failed to open binary file: %s", mDataFileName);
+		handleException();
+	}
+}
+
+void Sender::writeData(const char* data, int length, int type) {
+	if (length < 0 || (data == NULL && length > 0)) {
+		return;
+	}
+
+	// Multiple threads call writeData()
+	if (pthread_mutex_lock(&mSendMutex) != 0) {
+		logg->logError("pthread_mutex_lock failed");
+		handleException();
+	}
+
+	// Send data over the socket connection
+	if (mDataSocket) {
+		// Start alarm
+		const int alarmDuration = 8;
+		alarm(alarmDuration);
+
+		// Send data over the socket, sending the type and size first
+		logg->logMessage("Sending data with length %d", length);
+		if (type != RESPONSE_APC_DATA) {
+			// type and length already added by the Collector for apc data
+			unsigned char header[5];
+			header[0] = type;
+			Buffer::writeLEInt(header + 1, length);
+			mDataSocket->send((char*)&header, sizeof(header));
+		}
+
+		// 100Kbits/sec * alarmDuration sec / 8 bits/byte
+		const int chunkSize = 100*1000 * alarmDuration / 8;
+		int pos = 0;
+		while (true) {
+			mDataSocket->send(data + pos, min(length - pos, chunkSize));
+			pos += chunkSize;
+			if (pos >= length) {
+				break;
+			}
+
+			// Reset the alarm
+			alarm(alarmDuration);
+			logg->logMessage("Resetting the alarm");
+		}
+
+		// Stop alarm
+		alarm(0);
+	}
+
+	// Write data to disk as long as it is not meta data
+	if (mDataFile && type == RESPONSE_APC_DATA) {
+		logg->logMessage("Writing data with length %d", length);
+		// Send data to the data file
+		if (fwrite(data, 1, length, mDataFile) != (unsigned int)length) {
+			logg->logError("Failed writing binary file %s", mDataFileName);
+			handleException();
+		}
+	}
+
+	if (pthread_mutex_unlock(&mSendMutex) != 0) {
+		logg->logError("pthread_mutex_unlock failed");
+		handleException();
+	}
+}
diff --git a/tools/gator/daemon/Sender.h b/tools/gator/daemon/Sender.h
new file mode 100644
index 00000000000..8f542026e90
--- /dev/null
+++ b/tools/gator/daemon/Sender.h
@@ -0,0 +1,42 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __SENDER_H__
+#define __SENDER_H__
+
+#include <stdio.h>
+#include <pthread.h>
+
+class OlySocket;
+
+enum {
+	RESPONSE_XML = 1,
+	RESPONSE_APC_DATA = 3,
+	RESPONSE_ACK = 4,
+	RESPONSE_NAK = 5,
+	RESPONSE_ERROR = 0xFF
+};
+
+class Sender {
+public:
+	Sender(OlySocket* socket);
+	~Sender();
+	void writeData(const char* data, int length, int type);
+	void createDataFile(char* apcDir);
+private:
+	OlySocket* mDataSocket;
+	FILE* mDataFile;
+	char* mDataFileName;
+	pthread_mutex_t mSendMutex;
+
+	// Intentionally unimplemented
+	Sender(const Sender &);
+	Sender &operator=(const Sender &);
+};
+
+#endif //__SENDER_H__
diff --git a/tools/gator/daemon/SessionData.cpp b/tools/gator/daemon/SessionData.cpp
new file mode 100644
index 00000000000..42917c034c5
--- /dev/null
+++ b/tools/gator/daemon/SessionData.cpp
@@ -0,0 +1,346 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "SessionData.h"
+
+#include <fcntl.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include "DiskIODriver.h"
+#include "FSDriver.h"
+#include "HwmonDriver.h"
+#include "Logging.h"
+#include "MemInfoDriver.h"
+#include "NetDriver.h"
+#include "SessionXML.h"
+
+#define CORE_NAME_UNKNOWN "unknown"
+
+SessionData* gSessionData = NULL;
+
+SharedData::SharedData() : mMaliUtgardCountersSize(0) {
+	memset(mCpuIds, -1, sizeof(mCpuIds));
+}
+
+SessionData::SessionData() {
+	mUsDrivers[0] = new HwmonDriver();
+	mUsDrivers[1] = new FSDriver();
+	mUsDrivers[2] = new MemInfoDriver();
+	mUsDrivers[3] = new NetDriver();
+	mUsDrivers[4] = new DiskIODriver();
+	initialize();
+}
+
+SessionData::~SessionData() {
+}
+
+// Needed to use placement new
+inline void *operator new(size_t, void *ptr) { return ptr; }
+
+void SessionData::initialize() {
+	mSharedData = (SharedData *)mmap(NULL, sizeof(*mSharedData), PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	if (mSharedData == MAP_FAILED) {
+		logg->logError("Unable to mmap shared memory for cpuids");
+		handleException();
+	}
+	// Use placement new to construct but not allocate the object
+	new ((char *)mSharedData) SharedData();
+
+	mWaitingOnCommand = false;
+	mSessionIsActive = false;
+	mLocalCapture = false;
+	mOneShot = false;
+	mSentSummary = false;
+	mAllowCommands = false;
+	strcpy(mCoreName, CORE_NAME_UNKNOWN);
+	readModel();
+	readCpuInfo();
+	mImages = NULL;
+	mConfigurationXMLPath = NULL;
+	mSessionXMLPath = NULL;
+	mEventsXMLPath = NULL;
+	mEventsXMLAppend = NULL;
+	mTargetPath = NULL;
+	mAPCDir = NULL;
+	mCaptureWorkingDir = NULL;
+	mCaptureCommand = NULL;
+	mCaptureUser = NULL;
+	mSampleRate = 0;
+	mLiveRate = 0;
+	mDuration = 0;
+	mMonotonicStarted = -1;
+	mBacktraceDepth = 0;
+	mTotalBufferSize = 0;
+	// sysconf(_SC_NPROCESSORS_CONF) is unreliable on 2.6 Android, get the value from the kernel module
+	mCores = 1;
+	mPageSize = 0;
+	mAnnotateStart = -1;
+}
+
+void SessionData::parseSessionXML(char* xmlString) {
+	SessionXML session(xmlString);
+	session.parse();
+
+	// Set session data values - use prime numbers just below the desired value to reduce the chance of events firing at the same time
+	if (strcmp(session.parameters.sample_rate, "high") == 0) {
+		mSampleRate = 10007; // 10000
+	} else if (strcmp(session.parameters.sample_rate, "normal") == 0) {
+		mSampleRate = 1009; // 1000
+	} else if (strcmp(session.parameters.sample_rate, "low") == 0) {
+		mSampleRate = 101; // 100
+	} else if (strcmp(session.parameters.sample_rate, "none") == 0) {
+		mSampleRate = 0;
+	} else {
+		logg->logError("Invalid sample rate (%s) in session xml.", session.parameters.sample_rate);
+		handleException();
+	}
+	mBacktraceDepth = session.parameters.call_stack_unwinding == true ? 128 : 0;
+
+	// Determine buffer size (in MB) based on buffer mode
+	mOneShot = true;
+	if (strcmp(session.parameters.buffer_mode, "streaming") == 0) {
+		mOneShot = false;
+		mTotalBufferSize = 1;
+	} else if (strcmp(session.parameters.buffer_mode, "small") == 0) {
+		mTotalBufferSize = 1;
+	} else if (strcmp(session.parameters.buffer_mode, "normal") == 0) {
+		mTotalBufferSize = 4;
+	} else if (strcmp(session.parameters.buffer_mode, "large") == 0) {
+		mTotalBufferSize = 16;
+	} else {
+		logg->logError("Invalid value for buffer mode in session xml.");
+		handleException();
+	}
+
+	// Convert milli- to nanoseconds
+	mLiveRate = session.parameters.live_rate * (int64_t)1000000;
+	if (mLiveRate > 0 && mLocalCapture) {
+		logg->logMessage("Local capture is not compatable with live, disabling live");
+		mLiveRate = 0;
+	}
+
+	if (!mAllowCommands && (mCaptureCommand != NULL)) {
+		logg->logError("Running a command during a capture is not currently allowed. Please restart gatord with the -a flag.");
+		handleException();
+	}
+}
+
+void SessionData::readModel() {
+	FILE *fh = fopen_cloexec("/proc/device-tree/model", "rb");
+	if (fh == NULL) {
+		return;
+	}
+
+	char buf[256];
+	if (fgets(buf, sizeof(buf), fh) != NULL) {
+		strcpy(mCoreName, buf);
+	}
+
+	fclose(fh);
+}
+
+static void setImplementer(int &cpuId, const int implementer) {
+	if (cpuId == -1) {
+		cpuId = 0;
+	}
+	cpuId |= implementer << 12;
+}
+
+static void setPart(int &cpuId, const int part) {
+	if (cpuId == -1) {
+		cpuId = 0;
+	}
+	cpuId |= part;
+}
+
+void SessionData::readCpuInfo() {
+	char temp[256]; // arbitrarily large amount
+	mMaxCpuId = -1;
+
+	FILE *f = fopen_cloexec("/proc/cpuinfo", "r");
+	if (f == NULL) {
+		logg->logMessage("Error opening /proc/cpuinfo\n"
+			"The core name in the captured xml file will be 'unknown'.");
+		return;
+	}
+
+	bool foundCoreName = (strcmp(mCoreName, CORE_NAME_UNKNOWN) != 0);
+	int processor = -1;
+	while (fgets(temp, sizeof(temp), f)) {
+		const size_t len = strlen(temp);
+
+		if (len > 0) {
+			// Replace the line feed with a null
+			temp[len - 1] = '\0';
+		}
+
+		logg->logMessage("cpuinfo: %s", temp);
+
+		if (len == 1) {
+			// New section, clear the processor. Streamline will not know the cpus if the pre Linux 3.8 format of cpuinfo is encountered but also that no incorrect information will be transmitted.
+			processor = -1;
+			continue;
+		}
+
+		const bool foundHardware = !foundCoreName && strstr(temp, "Hardware") != 0;
+		const bool foundCPUImplementer = strstr(temp, "CPU implementer") != 0;
+		const bool foundCPUPart = strstr(temp, "CPU part") != 0;
+		const bool foundProcessor = strstr(temp, "processor") != 0;
+		if (foundHardware || foundCPUImplementer || foundCPUPart || foundProcessor) {
+			char* position = strchr(temp, ':');
+			if (position == NULL || (unsigned int)(position - temp) + 2 >= strlen(temp)) {
+				logg->logMessage("Unknown format of /proc/cpuinfo\n"
+					"The core name in the captured xml file will be 'unknown'.");
+				return;
+			}
+			position += 2;
+
+			if (foundHardware) {
+				strncpy(mCoreName, position, sizeof(mCoreName));
+				mCoreName[sizeof(mCoreName) - 1] = 0; // strncpy does not guarantee a null-terminated string
+				foundCoreName = true;
+			}
+
+			if (foundCPUImplementer) {
+				const int implementer = strtol(position, NULL, 0);
+				if (processor >= NR_CPUS) {
+					logg->logMessage("Too many processors, please increase NR_CPUS");
+				} else if (processor >= 0) {
+					setImplementer(mSharedData->mCpuIds[processor], implementer);
+				} else {
+					setImplementer(mMaxCpuId, implementer);
+				}
+			}
+
+			if (foundCPUPart) {
+				const int cpuId = strtol(position, NULL, 0);
+				if (processor >= NR_CPUS) {
+					logg->logMessage("Too many processors, please increase NR_CPUS");
+				} else if (processor >= 0) {
+					setPart(mSharedData->mCpuIds[processor], cpuId);
+				} else {
+					setPart(mMaxCpuId, cpuId);
+				}
+			}
+
+			if (foundProcessor) {
+				processor = strtol(position, NULL, 0);
+			}
+		}
+	}
+
+	// If this does not have the full topology in /proc/cpuinfo, mCpuIds[0] may not have the 1 CPU part emitted - this guarantees it's in mMaxCpuId
+	for (int i = 0; i < NR_CPUS; ++i) {
+		if (mSharedData->mCpuIds[i] > mMaxCpuId) {
+			mMaxCpuId = mSharedData->mCpuIds[i];
+		}
+	}
+
+	if (!foundCoreName) {
+		logg->logMessage("Could not determine core name from /proc/cpuinfo\n"
+				 "The core name in the captured xml file will be 'unknown'.");
+	}
+	fclose(f);
+}
+
+uint64_t getTime() {
+	struct timespec ts;
+	if (clock_gettime(CLOCK_MONOTONIC_RAW, &ts) != 0) {
+		logg->logError("Failed to get uptime");
+		handleException();
+	}
+	return (NS_PER_S*ts.tv_sec + ts.tv_nsec);
+}
+
+int getEventKey() {
+	// key 0 is reserved as a timestamp
+	// key 1 is reserved as the marker for thread specific counters
+	// key 2 is reserved as the marker for core
+	// Odd keys are assigned by the driver, even keys by the daemon
+	static int key = 4;
+
+	const int ret = key;
+	key += 2;
+	return ret;
+}
+
+int pipe_cloexec(int pipefd[2]) {
+	if (pipe(pipefd) != 0) {
+		return -1;
+	}
+
+	int fdf;
+	if (((fdf = fcntl(pipefd[0], F_GETFD)) == -1) || (fcntl(pipefd[0], F_SETFD, fdf | FD_CLOEXEC) != 0) ||
+			((fdf = fcntl(pipefd[1], F_GETFD)) == -1) || (fcntl(pipefd[1], F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+		close(pipefd[0]);
+		close(pipefd[1]);
+		return -1;
+	}
+	return 0;
+}
+
+FILE *fopen_cloexec(const char *path, const char *mode) {
+	FILE *fh = fopen(path, mode);
+	if (fh == NULL) {
+		return NULL;
+	}
+	int fd = fileno(fh);
+	int fdf = fcntl(fd, F_GETFD);
+	if ((fdf == -1) || (fcntl(fd, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+		fclose(fh);
+		return NULL;
+	}
+	return fh;
+}
+
+bool setNonblock(const int fd) {
+	int flags;
+
+	flags = fcntl(fd, F_GETFL);
+	if (flags < 0) {
+		logg->logMessage("fcntl getfl failed");
+		return false;
+	}
+
+	if (fcntl(fd, F_SETFL, flags | O_NONBLOCK) != 0) {
+		logg->logMessage("fcntl setfl failed");
+		return false;
+	}
+
+	return true;
+}
+
+bool writeAll(const int fd, const void *const buf, const size_t pos) {
+	size_t written = 0;
+	while (written < pos) {
+		ssize_t bytes = write(fd, (const uint8_t *)buf + written, pos - written);
+		if (bytes <= 0) {
+			logg->logMessage("write failed");
+			return false;
+		}
+		written += bytes;
+	}
+
+	return true;
+}
+
+bool readAll(const int fd, void *const buf, const size_t count) {
+	size_t pos = 0;
+	while (pos < count) {
+		ssize_t bytes = read(fd, (uint8_t *)buf + pos, count - pos);
+		if (bytes <= 0) {
+			logg->logMessage("read failed");
+			return false;
+		}
+		pos += bytes;
+	}
+
+	return true;
+}
diff --git a/tools/gator/daemon/SessionData.h b/tools/gator/daemon/SessionData.h
new file mode 100644
index 00000000000..12432d02d85
--- /dev/null
+++ b/tools/gator/daemon/SessionData.h
@@ -0,0 +1,129 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef SESSION_DATA_H
+#define SESSION_DATA_H
+
+#include <stdint.h>
+
+#include "AtraceDriver.h"
+#include "CCNDriver.h"
+#include "Config.h"
+#include "Counter.h"
+#include "ExternalDriver.h"
+#include "FtraceDriver.h"
+#include "KMod.h"
+#include "MaliVideoDriver.h"
+#include "PerfDriver.h"
+
+#define PROTOCOL_VERSION 22
+// Differentiates development versions (timestamp) from release versions
+#define PROTOCOL_DEV 1000
+
+#define NS_PER_S 1000000000LL
+#define NS_PER_MS 1000000LL
+#define NS_PER_US 1000LL
+
+struct ImageLinkList {
+	char* path;
+	struct ImageLinkList *next;
+};
+
+class SharedData {
+public:
+	SharedData();
+
+	int mCpuIds[NR_CPUS];
+	size_t mMaliUtgardCountersSize;
+	char mMaliUtgardCounters[1<<12];
+
+private:
+	// Intentionally unimplemented
+	SharedData(const SharedData &);
+	SharedData &operator=(const SharedData &);
+};
+
+class SessionData {
+public:
+	static const size_t MAX_STRING_LEN = 80;
+
+	SessionData();
+	~SessionData();
+	void parseSessionXML(char* xmlString);
+	void readModel();
+	void readCpuInfo();
+
+	SharedData *mSharedData;
+
+	PolledDriver *mUsDrivers[5];
+	KMod mKmod;
+	PerfDriver mPerf;
+	MaliVideoDriver mMaliVideo;
+	// Intentionally above FtraceDriver as drivers are initialized in reverse order AtraceDriver references AtraceDriver
+	AtraceDriver mAtraceDriver;
+	FtraceDriver mFtraceDriver;
+	ExternalDriver mExternalDriver;
+	CCNDriver mCcnDriver;
+
+	char mCoreName[MAX_STRING_LEN];
+	struct ImageLinkList *mImages;
+	char *mConfigurationXMLPath;
+	char *mSessionXMLPath;
+	char *mEventsXMLPath;
+	char *mEventsXMLAppend;
+	char *mTargetPath;
+	char *mAPCDir;
+	char *mCaptureWorkingDir;
+	char *mCaptureCommand;
+	char *mCaptureUser;
+
+	bool mWaitingOnCommand;
+	bool mSessionIsActive;
+	bool mLocalCapture;
+	// halt processing of the driver data until profiling is complete or the buffer is filled
+	bool mOneShot;
+	bool mIsEBS;
+	bool mSentSummary;
+	bool mAllowCommands;
+
+	int64_t mMonotonicStarted;
+	int mBacktraceDepth;
+	// number of MB to use for the entire collection buffer
+	int mTotalBufferSize;
+	int mSampleRate;
+	int64_t mLiveRate;
+	int mDuration;
+	int mCores;
+	int mPageSize;
+	int mMaxCpuId;
+	int mAnnotateStart;
+
+	// PMU Counters
+	char *mCountersError;
+	Counter mCounters[MAX_PERFORMANCE_COUNTERS];
+
+private:
+	void initialize();
+
+	// Intentionally unimplemented
+	SessionData(const SessionData &);
+	SessionData &operator=(const SessionData &);
+};
+
+extern SessionData* gSessionData;
+extern const char *const gSrcMd5;
+
+uint64_t getTime();
+int getEventKey();
+int pipe_cloexec(int pipefd[2]);
+FILE *fopen_cloexec(const char *path, const char *mode);
+bool setNonblock(const int fd);
+bool writeAll(const int fd, const void *const buf, const size_t pos);
+bool readAll(const int fd, void *const buf, const size_t count);
+
+#endif // SESSION_DATA_H
diff --git a/tools/gator/daemon/SessionXML.cpp b/tools/gator/daemon/SessionXML.cpp
new file mode 100644
index 00000000000..c638dea4591
--- /dev/null
+++ b/tools/gator/daemon/SessionXML.cpp
@@ -0,0 +1,111 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "SessionXML.h"
+
+#include <string.h>
+#include <stdlib.h>
+#include <limits.h>
+
+#include "Logging.h"
+#include "OlyUtility.h"
+#include "SessionData.h"
+
+static const char *TAG_SESSION = "session";
+static const char *TAG_IMAGE   = "image";
+
+static const char *ATTR_VERSION              = "version";
+static const char *ATTR_CALL_STACK_UNWINDING = "call_stack_unwinding";
+static const char *ATTR_BUFFER_MODE          = "buffer_mode";
+static const char *ATTR_SAMPLE_RATE          = "sample_rate";
+static const char *ATTR_DURATION             = "duration";
+static const char *ATTR_PATH                 = "path";
+static const char *ATTR_LIVE_RATE            = "live_rate";
+static const char *ATTR_CAPTURE_WORKING_DIR  = "capture_working_dir";
+static const char *ATTR_CAPTURE_COMMAND      = "capture_command";
+static const char *ATTR_CAPTURE_USER         = "capture_user";
+
+SessionXML::SessionXML(const char *str) {
+	parameters.buffer_mode[0] = 0;
+	parameters.sample_rate[0] = 0;
+	parameters.call_stack_unwinding = false;
+	parameters.live_rate = 0;
+	mSessionXML = str;
+	logg->logMessage("%s", mSessionXML);
+}
+
+SessionXML::~SessionXML() {
+}
+
+void SessionXML::parse() {
+	mxml_node_t *tree;
+	mxml_node_t *node;
+
+	tree = mxmlLoadString(NULL, mSessionXML, MXML_NO_CALLBACK);
+	node = mxmlFindElement(tree, tree, TAG_SESSION, NULL, NULL, MXML_DESCEND);
+
+	if (node) {
+		sessionTag(tree, node);
+		mxmlDelete(tree);
+		return;
+	}
+
+	logg->logError("No session tag found in the session.xml file");
+	handleException();
+}
+
+void SessionXML::sessionTag(mxml_node_t *tree, mxml_node_t *node) {
+	int version = 0;
+	if (mxmlElementGetAttr(node, ATTR_VERSION)) version = strtol(mxmlElementGetAttr(node, ATTR_VERSION), NULL, 10);
+	if (version != 1) {
+		logg->logError("Invalid session.xml version: %d", version);
+		handleException();
+	}
+
+	// copy to pre-allocated strings
+	if (mxmlElementGetAttr(node, ATTR_BUFFER_MODE)) {
+		strncpy(parameters.buffer_mode, mxmlElementGetAttr(node, ATTR_BUFFER_MODE), sizeof(parameters.buffer_mode));
+		parameters.buffer_mode[sizeof(parameters.buffer_mode) - 1] = 0; // strncpy does not guarantee a null-terminated string
+	}
+	if (mxmlElementGetAttr(node, ATTR_SAMPLE_RATE)) {
+		strncpy(parameters.sample_rate, mxmlElementGetAttr(node, ATTR_SAMPLE_RATE), sizeof(parameters.sample_rate));
+		parameters.sample_rate[sizeof(parameters.sample_rate) - 1] = 0; // strncpy does not guarantee a null-terminated string
+	}
+	if (mxmlElementGetAttr(node, ATTR_CAPTURE_WORKING_DIR)) gSessionData->mCaptureWorkingDir = strdup(mxmlElementGetAttr(node, ATTR_CAPTURE_WORKING_DIR));
+	if (mxmlElementGetAttr(node, ATTR_CAPTURE_COMMAND)) gSessionData->mCaptureCommand = strdup(mxmlElementGetAttr(node, ATTR_CAPTURE_COMMAND));
+	if (mxmlElementGetAttr(node, ATTR_CAPTURE_USER)) gSessionData->mCaptureUser = strdup(mxmlElementGetAttr(node, ATTR_CAPTURE_USER));
+
+	// integers/bools
+	parameters.call_stack_unwinding = util->stringToBool(mxmlElementGetAttr(node, ATTR_CALL_STACK_UNWINDING), false);
+	if (mxmlElementGetAttr(node, ATTR_DURATION)) gSessionData->mDuration = strtol(mxmlElementGetAttr(node, ATTR_DURATION), NULL, 10);
+	if (mxmlElementGetAttr(node, ATTR_LIVE_RATE)) parameters.live_rate = strtol(mxmlElementGetAttr(node, ATTR_LIVE_RATE), NULL, 10);
+
+	// parse subtags
+	node = mxmlGetFirstChild(node);
+	while (node) {
+		if (mxmlGetType(node) != MXML_ELEMENT) {
+			node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+			continue;
+		}
+		if (strcmp(TAG_IMAGE, mxmlGetElement(node)) == 0) {
+			sessionImage(node);
+		}
+		node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+	}
+}
+
+void SessionXML::sessionImage(mxml_node_t *node) {
+	int length = strlen(mxmlElementGetAttr(node, ATTR_PATH));
+	struct ImageLinkList *image;
+
+	image = (struct ImageLinkList *)malloc(sizeof(struct ImageLinkList));
+	image->path = (char*)malloc(length + 1);
+	image->path = strdup(mxmlElementGetAttr(node, ATTR_PATH));
+	image->next = gSessionData->mImages;
+	gSessionData->mImages = image;
+}
diff --git a/tools/gator/daemon/SessionXML.h b/tools/gator/daemon/SessionXML.h
new file mode 100644
index 00000000000..2ba276a3802
--- /dev/null
+++ b/tools/gator/daemon/SessionXML.h
@@ -0,0 +1,42 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef SESSION_XML_H
+#define SESSION_XML_H
+
+#include "mxml/mxml.h"
+
+struct ImageLinkList;
+
+struct ConfigParameters {
+	// buffer mode, "streaming", "low", "normal", "high" defines oneshot and buffer size
+	char buffer_mode[64];
+	// capture mode, "high", "normal", or "low"
+	char sample_rate[64];
+	// whether stack unwinding is performed
+	bool call_stack_unwinding;
+	int live_rate;
+};
+
+class SessionXML {
+public:
+	SessionXML(const char *str);
+	~SessionXML();
+	void parse();
+	ConfigParameters parameters;
+private:
+	const char *mSessionXML;
+	void sessionTag(mxml_node_t *tree, mxml_node_t *node);
+	void sessionImage(mxml_node_t *node);
+
+	// Intentionally unimplemented
+	SessionXML(const SessionXML &);
+	SessionXML &operator=(const SessionXML &);
+};
+
+#endif // SESSION_XML_H
diff --git a/tools/gator/daemon/Setup.cpp b/tools/gator/daemon/Setup.cpp
new file mode 100644
index 00000000000..524a70204e2
--- /dev/null
+++ b/tools/gator/daemon/Setup.cpp
@@ -0,0 +1,332 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Setup.h"
+
+#include <dirent.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/utsname.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "Config.h"
+#include "DynBuf.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+#define GATOR_MSG "gator: "
+#define GATOR_ERROR "gator: error: "
+#define GATOR_CONFIRM "gator: confirm: "
+
+bool getLinuxVersion(int version[3]) {
+	// Check the kernel version
+	struct utsname utsname;
+	if (uname(&utsname) != 0) {
+		logg->logMessage("uname failed");
+		return false;
+	}
+
+	version[0] = 0;
+	version[1] = 0;
+	version[2] = 0;
+
+	int part = 0;
+	char *ch = utsname.release;
+	while (*ch >= '0' && *ch <= '9' && part < 3) {
+		version[part] = 10*version[part] + *ch - '0';
+
+		++ch;
+		if (*ch == '.') {
+			++part;
+			++ch;
+		}
+	}
+
+	return true;
+}
+
+static int pgrep_gator(DynBuf *const printb) {
+	DynBuf b;
+
+	DIR *proc = opendir("/proc");
+	if (proc == NULL) {
+		logg->logError(GATOR_ERROR "opendir failed");
+		handleException();
+	}
+
+	int self = getpid();
+
+	struct dirent *dirent;
+	while ((dirent = readdir(proc)) != NULL) {
+		char *endptr;
+		const int pid = strtol(dirent->d_name, &endptr, 10);
+		if (*endptr != '\0' || (pid == self)) {
+			// Ignore proc items that are not integers like ., cpuinfo, etc...
+			continue;
+		}
+
+		if (!printb->printf("/proc/%i/stat", pid)) {
+			logg->logError(GATOR_ERROR "DynBuf::printf failed");
+			handleException();
+		}
+
+		if (!b.read(printb->getBuf())) {
+			// This is not a fatal error - the thread just doesn't exist any more
+			continue;
+		}
+
+		char *comm = strchr(b.getBuf(), '(');
+		if (comm == NULL) {
+			logg->logError(GATOR_ERROR "parsing stat comm begin failed");
+			handleException();
+		}
+		++comm;
+		char *const str = strrchr(comm, ')');
+		if (str == NULL) {
+			logg->logError(GATOR_ERROR "parsing stat comm end failed");
+			handleException();
+		}
+		*str = '\0';
+
+		if (strncmp(comm, "gator", 5) != 0) {
+			continue;
+		}
+
+		char state;
+		const int count = sscanf(str + 2, " %c ", &state);
+		if (count != 1) {
+			logg->logError(GATOR_ERROR "parsing stat state failed");
+			handleException();
+		}
+
+		if (state == 'Z') {
+			// This gator is a zombie, ignore
+			continue;
+		}
+
+		// Assume there is only one gator process
+		return pid;
+	}
+
+	closedir(proc);
+
+	return -1;
+}
+
+static bool confirm(const char *const message) {
+	char buf[1<<10];
+
+	printf(GATOR_CONFIRM "%s\n", message);
+	while (fgets(buf, sizeof(buf), stdin) != NULL) {
+		if (strcmp(buf, "y\n") == 0) {
+			return true;
+		}
+		if (strcmp(buf, "n\n") == 0) {
+			return false;
+		}
+		// Ignore unrecognized input
+	}
+
+	return false;
+}
+
+void update(const char *const gatorPath) {
+	printf(GATOR_MSG "starting\n");
+
+	int version[3];
+	if (!getLinuxVersion(version)) {
+		logg->logError(GATOR_ERROR "getLinuxVersion failed");
+		handleException();
+	}
+
+	if (KERNEL_VERSION(version[0], version[1], version[2]) < KERNEL_VERSION(3, 4, 0)) {
+		logg->logError(GATOR_ERROR "Streamline can't automatically setup gator as this kernel version is not supported. Please upgrade the kernel on your device.");
+		handleException();
+	}
+
+	if (geteuid() != 0) {
+		char buf[1<<10];
+		snprintf(buf, sizeof(buf),
+			 "which sudo &&"
+			 "("
+			   "sudo -n %1$s -u ||"
+			   "("
+			     "echo " GATOR_MSG "trying sudo;"
+			     // Streamline will provide the password
+			     "sudo %1$s -u"
+			   ")"
+			 ") || ("
+			   "echo " GATOR_MSG "trying su;"
+		/*
+		 * Different versions of su handle additional -c command line options differently and expect the
+		 * arguments in different ways. Try both ways wrapped in a shell.
+		 *
+		 * Then invoke another shell after su as it avoids odd failures on some Android systems
+		 */
+			   "su -c \"sh -c '%1$s -u'\" ||"
+			   "su -c sh -c '%1$s -u'"
+			 ")",
+			 gatorPath);
+		execlp("sh", "sh", "-c", buf, NULL);
+		// Streamline will provide the password if needed
+
+		logg->logError(GATOR_ERROR "Streamline was unable to sudo to root on your device. Please double check passwords, ensure sudo or su work with this user or try a different username.");
+		handleException();
+	}
+	printf(GATOR_MSG "now root\n");
+
+	if (access("/sys/module/gator", F_OK) == 0) {
+		if (!confirm("Streamline has detected that the gator kernel module is loaded on your device. Click yes to switch to user space gator, click no to abort the install.")) {
+			printf("gator: cancel\n");
+			exit(-1);
+		}
+	}
+
+	// setenforce 0 not needed for userspace gator
+
+	// Kill existing gator
+	DynBuf printb;
+	int gator_main = pgrep_gator(&printb);
+	if (gator_main > 0) {
+		if (kill(gator_main, SIGTERM) != 0) {
+			logg->logError(GATOR_ERROR "kill SIGTERM failed");
+			handleException();
+		}
+		if (!printb.printf("/proc/%i/exe", gator_main)) {
+			logg->logError(GATOR_ERROR "DynBuf::printf failed");
+			handleException();
+		}
+		for (int i = 0; ; ++i) {
+			// /proc/<pid>/exe exists but will not be accessible for zombies
+			if (access(printb.getBuf(), F_OK) != 0) {
+				break;
+			}
+			if (i == 5) {
+				if (kill(gator_main, SIGKILL) != 0) {
+					logg->logError(GATOR_ERROR "kill SIGKILL failed");
+					handleException();
+				}
+			} else if (i >= 10) {
+				logg->logError(GATOR_ERROR "unable to kill running gator");
+				handleException();
+			}
+			sleep(1);
+		}
+	}
+	printf(GATOR_MSG "no gatord running\n");
+
+	umount("/dev/gator");
+	syscall(__NR_delete_module, "gator", O_NONBLOCK);
+
+	if (access("/sys/module/gator", F_OK) == 0) {
+		logg->logError(GATOR_ERROR "Unable to unload gator.ko, the gator module may be built into the kernel or gator.ko cannot be unloaded. Rebooting the device may resolve the issue.");
+		handleException();
+	}
+
+	rename("gatord", "gatord.old");
+	rename("gator.ko", "gator.ko.old");
+
+	// Rename gatord.YYYYMMDDHHMMSSMMMM to gatord
+	char *newGatorPath = strdup(gatorPath);
+	char *dot = strrchr(newGatorPath, '.');
+	if (dot != NULL) {
+		*dot = '\0';
+		if (rename(gatorPath, newGatorPath) != 0) {
+			logg->logError(GATOR_ERROR "rename failed");
+			handleException();
+		}
+	}
+
+	char buf[128];
+	int pipefd[2];
+	if (pipe_cloexec(pipefd) != 0) {
+		logg->logError(GATOR_ERROR "pipe failed");
+		handleException();
+	}
+
+	// Fork and start gatord (redirect stdin, stdout and stderr so shell can close)
+	int child = fork();
+	if (child < 0) {
+		logg->logError(GATOR_ERROR "fork failed");
+		handleException();
+	} else if (child == 0) {
+		int inFd;
+		int outFd;
+		int errFd;
+		int result = -1;
+
+		buf[0] = '\0';
+		close(pipefd[0]);
+
+		inFd = open("/dev/null", O_RDONLY | O_CLOEXEC);
+		if (inFd < 0) {
+			snprintf(buf, sizeof(buf), GATOR_ERROR "open of /dev/null failed");
+			goto fail_exit;
+		}
+		outFd = open("gatord.out", O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644);
+		if (outFd < 0) {
+			snprintf(buf, sizeof(buf), GATOR_ERROR "open of gatord.out failed");
+			goto fail_exit;
+		}
+		errFd = open("gatord.err", O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644);
+		if (errFd < 0) {
+			snprintf(buf, sizeof(buf), GATOR_ERROR "open of gatord.err failed");
+			goto fail_exit;
+		}
+		if (dup2(inFd, STDIN_FILENO) < 0) {
+			snprintf(buf, sizeof(buf), GATOR_ERROR "dup2 for stdin failed");
+			goto fail_exit;
+		}
+		fflush(stdout);
+		if (dup2(outFd, STDOUT_FILENO) < 0) {
+			snprintf(buf, sizeof(buf), GATOR_ERROR "dup2 for stdout failed");
+			goto fail_exit;
+		}
+		fflush(stderr);
+		if (dup2(errFd, STDERR_FILENO) < 0) {
+			snprintf(buf, sizeof(buf), GATOR_ERROR "dup2 for stderr failed");
+			goto fail_exit;
+		}
+
+		snprintf(buf, sizeof(buf), GATOR_MSG "done");
+		result = 0;
+
+	fail_exit:
+		if (buf[0] != '\0') {
+			const ssize_t bytes = write(pipefd[1], buf, sizeof(buf));
+			// Can't do anything if this fails
+			(void)bytes;
+		}
+		close(pipefd[1]);
+
+		if (result == 0) {
+			// Continue to execute gator normally
+			return;
+		}
+		exit(-1);
+	}
+
+	close(pipefd[1]);
+	const ssize_t bytes = read(pipefd[0], buf, sizeof(buf));
+	if (bytes > 0) {
+		printf("%s\n", buf);
+	}
+	close(pipefd[0]);
+
+	// Exit so parent shell can move on
+	exit(0);
+}
diff --git a/tools/gator/daemon/Setup.h b/tools/gator/daemon/Setup.h
new file mode 100644
index 00000000000..427e71788c3
--- /dev/null
+++ b/tools/gator/daemon/Setup.h
@@ -0,0 +1,18 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef SETUP_H
+#define SETUP_H
+
+// From include/generated/uapi/linux/version.h
+#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + (c))
+
+bool getLinuxVersion(int version[3]);
+void update(const char *const gatorPath);
+
+#endif // SETUP_H
diff --git a/tools/gator/daemon/Source.cpp b/tools/gator/daemon/Source.cpp
new file mode 100644
index 00000000000..64d6206895b
--- /dev/null
+++ b/tools/gator/daemon/Source.cpp
@@ -0,0 +1,33 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Source.h"
+
+#include "Logging.h"
+
+Source::Source() : mThreadID() {
+}
+
+Source::~Source() {
+}
+
+void Source::start() {
+	if (pthread_create(&mThreadID, NULL, runStatic, this)) {
+		logg->logError("Failed to create source thread");
+		handleException();
+	}
+}
+
+void Source::join() {
+	pthread_join(mThreadID, NULL);
+}
+
+void *Source::runStatic(void *arg) {
+	static_cast<Source *>(arg)->run();
+	return NULL;
+}
diff --git a/tools/gator/daemon/Source.h b/tools/gator/daemon/Source.h
new file mode 100644
index 00000000000..b9369be5198
--- /dev/null
+++ b/tools/gator/daemon/Source.h
@@ -0,0 +1,40 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef SOURCE_H
+#define SOURCE_H
+
+#include <pthread.h>
+
+class Sender;
+
+class Source {
+public:
+	Source();
+	virtual ~Source();
+
+	virtual bool prepare() = 0;
+	void start();
+	virtual void run() = 0;
+	virtual void interrupt() = 0;
+	void join();
+
+	virtual bool isDone() = 0;
+	virtual void write(Sender *sender) = 0;
+
+private:
+	static void *runStatic(void *arg);
+
+	pthread_t mThreadID;
+
+	// Intentionally undefined
+	Source(const Source &);
+	Source &operator=(const Source &);
+};
+
+#endif // SOURCE_H
diff --git a/tools/gator/daemon/StreamlineSetup.cpp b/tools/gator/daemon/StreamlineSetup.cpp
new file mode 100644
index 00000000000..66d1f4e94a2
--- /dev/null
+++ b/tools/gator/daemon/StreamlineSetup.cpp
@@ -0,0 +1,272 @@
+/**
+ * Copyright (C) ARM Limited 2011-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "StreamlineSetup.h"
+
+#include "Buffer.h"
+#include "CapturedXML.h"
+#include "ConfigurationXML.h"
+#include "Driver.h"
+#include "EventsXML.h"
+#include "Logging.h"
+#include "OlySocket.h"
+#include "OlyUtility.h"
+#include "Sender.h"
+#include "SessionData.h"
+
+static const char* TAG_SESSION = "session";
+static const char* TAG_REQUEST = "request";
+static const char* TAG_CONFIGURATIONS = "configurations";
+
+static const char* ATTR_TYPE           = "type";
+static const char* VALUE_EVENTS        = "events";
+static const char* VALUE_CONFIGURATION = "configuration";
+static const char* VALUE_COUNTERS      = "counters";
+static const char* VALUE_CAPTURED      = "captured";
+static const char* VALUE_DEFAULTS      = "defaults";
+
+StreamlineSetup::StreamlineSetup(OlySocket* s) {
+	bool ready = false;
+	char* data = NULL;
+	int type;
+
+	mSocket = s;
+
+	// Receive commands from Streamline (master)
+	while (!ready) {
+		// receive command over socket
+		gSessionData->mWaitingOnCommand = true;
+		data = readCommand(&type);
+
+		// parse and handle data
+		switch (type) {
+			case COMMAND_REQUEST_XML:
+				handleRequest(data);
+				break;
+			case COMMAND_DELIVER_XML:
+				handleDeliver(data);
+				break;
+			case COMMAND_APC_START:
+				logg->logMessage("Received apc start request");
+				ready = true;
+				break;
+			case COMMAND_APC_STOP:
+				logg->logMessage("Received apc stop request before apc start request");
+				exit(0);
+				break;
+			case COMMAND_DISCONNECT:
+				logg->logMessage("Received disconnect command");
+				exit(0);
+				break;
+			case COMMAND_PING:
+				logg->logMessage("Received ping command");
+				sendData(NULL, 0, RESPONSE_ACK);
+				break;
+			default:
+				logg->logError("Target error: Unknown command type, %d", type);
+				handleException();
+		}
+
+		free(data);
+	}
+
+	if (gSessionData->mCountersError != NULL) {
+		logg->logError("%s", gSessionData->mCountersError);
+		handleException();
+	}
+}
+
+StreamlineSetup::~StreamlineSetup() {
+}
+
+char* StreamlineSetup::readCommand(int* command) {
+	unsigned char header[5];
+	char* data;
+	int response;
+
+	// receive type and length
+	response = mSocket->receiveNBytes((char*)&header, sizeof(header));
+
+	// After receiving a single byte, we are no longer waiting on a command
+	gSessionData->mWaitingOnCommand = false;
+
+	if (response < 0) {
+		logg->logError("Target error: Unexpected socket disconnect");
+		handleException();
+	}
+
+	const char type = header[0];
+	const int length = (header[1] << 0) | (header[2] << 8) | (header[3] << 16) | (header[4] << 24);
+
+	// add artificial limit
+	if ((length < 0) || length > 1024 * 1024) {
+		logg->logError("Target error: Invalid length received, %d", length);
+		handleException();
+	}
+
+	// allocate memory to contain the xml file, size of zero returns a zero size object
+	data = (char*)calloc(length + 1, 1);
+	if (data == NULL) {
+		logg->logError("Unable to allocate memory for xml");
+		handleException();
+	}
+
+	// receive data
+	response = mSocket->receiveNBytes(data, length);
+	if (response < 0) {
+		logg->logError("Target error: Unexpected socket disconnect");
+		handleException();
+	}
+
+	// null terminate the data for string parsing
+	if (length > 0) {
+		data[length] = 0;
+	}
+
+	*command = type;
+	return data;
+}
+
+void StreamlineSetup::handleRequest(char* xml) {
+	mxml_node_t *tree, *node;
+	const char * attr = NULL;
+
+	tree = mxmlLoadString(NULL, xml, MXML_NO_CALLBACK);
+	node = mxmlFindElement(tree, tree, TAG_REQUEST, ATTR_TYPE, NULL, MXML_DESCEND_FIRST);
+	if (node) {
+		attr = mxmlElementGetAttr(node, ATTR_TYPE);
+	}
+	if (attr && strcmp(attr, VALUE_EVENTS) == 0) {
+		sendEvents();
+		logg->logMessage("Sent events xml response");
+	} else if (attr && strcmp(attr, VALUE_CONFIGURATION) == 0) {
+		sendConfiguration();
+		logg->logMessage("Sent configuration xml response");
+	} else if (attr && strcmp(attr, VALUE_COUNTERS) == 0) {
+		sendCounters();
+		logg->logMessage("Sent counters xml response");
+	} else if (attr && strcmp(attr, VALUE_CAPTURED) == 0) {
+		CapturedXML capturedXML;
+		char* capturedText = capturedXML.getXML(false);
+		sendData(capturedText, strlen(capturedText), RESPONSE_XML);
+		free(capturedText);
+		logg->logMessage("Sent captured xml response");
+	} else if (attr && strcmp(attr, VALUE_DEFAULTS) == 0) {
+		sendDefaults();
+		logg->logMessage("Sent default configuration xml response");
+	} else {
+		char error[] = "Unknown request";
+		sendData(error, strlen(error), RESPONSE_NAK);
+		logg->logMessage("Received unknown request:\n%s", xml);
+	}
+
+	mxmlDelete(tree);
+}
+
+void StreamlineSetup::handleDeliver(char* xml) {
+	mxml_node_t *tree;
+
+	// Determine xml type
+	tree = mxmlLoadString(NULL, xml, MXML_NO_CALLBACK);
+	if (mxmlFindElement(tree, tree, TAG_SESSION, NULL, NULL, MXML_DESCEND_FIRST)) {
+		// Session XML
+		gSessionData->parseSessionXML(xml);
+		sendData(NULL, 0, RESPONSE_ACK);
+		logg->logMessage("Received session xml");
+	} else if (mxmlFindElement(tree, tree, TAG_CONFIGURATIONS, NULL, NULL, MXML_DESCEND_FIRST)) {
+		// Configuration XML
+		writeConfiguration(xml);
+		sendData(NULL, 0, RESPONSE_ACK);
+		logg->logMessage("Received configuration xml");
+	} else {
+		// Unknown XML
+		logg->logMessage("Received unknown XML delivery type");
+		sendData(NULL, 0, RESPONSE_NAK);
+	}
+
+	mxmlDelete(tree);
+}
+
+void StreamlineSetup::sendData(const char* data, uint32_t length, char type) {
+	unsigned char header[5];
+	header[0] = type;
+	Buffer::writeLEInt(header + 1, length);
+	mSocket->send((char*)&header, sizeof(header));
+	mSocket->send(data, length);
+}
+
+void StreamlineSetup::sendEvents() {
+	EventsXML eventsXML;
+	char* string = eventsXML.getXML();
+	sendString(string, RESPONSE_XML);
+	free(string);
+}
+
+void StreamlineSetup::sendConfiguration() {
+	ConfigurationXML xml;
+
+	const char* string = xml.getConfigurationXML();
+	sendData(string, strlen(string), RESPONSE_XML);
+}
+
+void StreamlineSetup::sendDefaults() {
+	// Send the config built into the binary
+	const char* xml;
+	unsigned int size;
+	ConfigurationXML::getDefaultConfigurationXml(xml, size);
+
+	// Artificial size restriction
+	if (size > 1024*1024) {
+		logg->logError("Corrupt default configuration file");
+		handleException();
+	}
+
+	sendData(xml, size, RESPONSE_XML);
+}
+
+void StreamlineSetup::sendCounters() {
+	mxml_node_t *xml;
+	mxml_node_t *counters;
+
+	xml = mxmlNewXML("1.0");
+	counters = mxmlNewElement(xml, "counters");
+	int count = 0;
+	for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+		count += driver->writeCounters(counters);
+	}
+
+	if (count == 0) {
+		logg->logError("No counters found, this could be because /dev/gator/events can not be read or because perf is not working correctly");
+		handleException();
+	}
+
+	char* string = mxmlSaveAllocString(xml, mxmlWhitespaceCB);
+	sendString(string, RESPONSE_XML);
+
+	free(string);
+	mxmlDelete(xml);
+}
+
+void StreamlineSetup::writeConfiguration(char* xml) {
+	char path[PATH_MAX];
+
+	ConfigurationXML::getPath(path);
+
+	if (util->writeToDisk(path, xml) < 0) {
+		logg->logError("Error writing %s\nPlease verify write permissions to this path.", path);
+		handleException();
+	}
+
+	// Re-populate gSessionData with the configuration, as it has now changed
+	{ ConfigurationXML configuration; }
+
+	if (gSessionData->mCountersError != NULL) {
+		logg->logError("%s", gSessionData->mCountersError);
+		handleException();
+	}
+}
diff --git a/tools/gator/daemon/StreamlineSetup.h b/tools/gator/daemon/StreamlineSetup.h
new file mode 100644
index 00000000000..d8b16260643
--- /dev/null
+++ b/tools/gator/daemon/StreamlineSetup.h
@@ -0,0 +1,50 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __STREAMLINE_SETUP_H__
+#define __STREAMLINE_SETUP_H__
+
+#include <stdint.h>
+#include <string.h>
+
+class OlySocket;
+
+// Commands from Streamline
+enum {
+	COMMAND_REQUEST_XML = 0,
+	COMMAND_DELIVER_XML = 1,
+	COMMAND_APC_START   = 2,
+	COMMAND_APC_STOP    = 3,
+	COMMAND_DISCONNECT  = 4,
+	COMMAND_PING        = 5
+};
+
+class StreamlineSetup {
+public:
+	StreamlineSetup(OlySocket *socket);
+	~StreamlineSetup();
+private:
+	OlySocket* mSocket;
+
+	char* readCommand(int*);
+	void handleRequest(char* xml);
+	void handleDeliver(char* xml);
+	void sendData(const char* data, uint32_t length, char type);
+	void sendString(const char* string, int type) {sendData(string, strlen(string), type);}
+	void sendEvents();
+	void sendConfiguration();
+	void sendDefaults();
+	void sendCounters();
+	void writeConfiguration(char* xml);
+
+	// Intentionally unimplemented
+	StreamlineSetup(const StreamlineSetup &);
+	StreamlineSetup &operator=(const StreamlineSetup &);
+};
+
+#endif //__STREAMLINE_SETUP_H__
diff --git a/tools/gator/daemon/UEvent.cpp b/tools/gator/daemon/UEvent.cpp
new file mode 100644
index 00000000000..6a69f5ab137
--- /dev/null
+++ b/tools/gator/daemon/UEvent.cpp
@@ -0,0 +1,78 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "UEvent.h"
+
+#include <string.h>
+#include <sys/socket.h>
+#include <unistd.h>
+
+#include <linux/netlink.h>
+
+#include "Logging.h"
+#include "OlySocket.h"
+
+static const char EMPTY[] = "";
+static const char ACTION[] = "ACTION=";
+static const char DEVPATH[] = "DEVPATH=";
+static const char SUBSYSTEM[] = "SUBSYSTEM=";
+
+UEvent::UEvent() : mFd(-1) {
+}
+
+UEvent::~UEvent() {
+	if (mFd >= 0) {
+		close(mFd);
+	}
+}
+
+bool UEvent::init() {
+	mFd = socket_cloexec(PF_NETLINK, SOCK_RAW, NETLINK_KOBJECT_UEVENT);
+	if (mFd < 0) {
+		logg->logMessage("socket failed");
+		return false;
+	}
+
+	struct sockaddr_nl sockaddr;
+	memset(&sockaddr, 0, sizeof(sockaddr));
+	sockaddr.nl_family = AF_NETLINK;
+	sockaddr.nl_groups = 1; // bitmask: (1 << 0) == kernel events, (1 << 1) == udev events
+	sockaddr.nl_pid = 0;
+	if (bind(mFd, (struct sockaddr *)&sockaddr, sizeof(sockaddr)) != 0) {
+		logg->logMessage("bind failed");
+		return false;
+	}
+
+	return true;
+}
+
+bool UEvent::read(UEventResult *const result) {
+	ssize_t bytes = recv(mFd, result->mBuf, sizeof(result->mBuf), 0);
+	if (bytes <= 0) {
+		logg->logMessage("recv failed");
+		return false;
+	}
+
+	result->mAction = EMPTY;
+	result->mDevPath = EMPTY;
+	result->mSubsystem = EMPTY;
+
+	for (int pos = 0; pos < bytes; pos += strlen(result->mBuf + pos) + 1) {
+		char *const str = result->mBuf + pos;
+		logg->logMessage("uevent + %i: %s", pos, str);
+		if (strncmp(str, ACTION, sizeof(ACTION) - 1) == 0) {
+			result->mAction = str + sizeof(ACTION) - 1;
+		} else if (strncmp(str, DEVPATH, sizeof(DEVPATH) - 1) == 0) {
+			result->mDevPath = str + sizeof(DEVPATH) - 1;
+		} else if (strncmp(str, SUBSYSTEM, sizeof(SUBSYSTEM) - 1) == 0) {
+			result->mSubsystem = str + sizeof(SUBSYSTEM) - 1;
+		}
+	}
+
+	return true;
+}
diff --git a/tools/gator/daemon/UEvent.h b/tools/gator/daemon/UEvent.h
new file mode 100644
index 00000000000..4c00f6cff11
--- /dev/null
+++ b/tools/gator/daemon/UEvent.h
@@ -0,0 +1,36 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef UEVENT_H
+#define UEVENT_H
+
+struct UEventResult {
+	const char *mAction;
+	const char *mDevPath;
+	const char *mSubsystem;
+	char mBuf[1<<13];
+};
+
+class UEvent {
+public:
+	UEvent();
+	~UEvent();
+
+	bool init();
+	bool read(UEventResult *const result);
+	int getFd() const { return mFd; }
+
+private:
+	int mFd;
+
+	// Intentionally undefined
+	UEvent(const UEvent &);
+	UEvent &operator=(const UEvent &);
+};
+
+#endif // UEVENT_H
diff --git a/tools/gator/daemon/UserSpaceSource.cpp b/tools/gator/daemon/UserSpaceSource.cpp
new file mode 100644
index 00000000000..103631248bf
--- /dev/null
+++ b/tools/gator/daemon/UserSpaceSource.cpp
@@ -0,0 +1,97 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define __STDC_FORMAT_MACROS
+
+#include "UserSpaceSource.h"
+
+#include <inttypes.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+#include "Child.h"
+#include "DriverSource.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+extern Child *child;
+
+UserSpaceSource::UserSpaceSource(sem_t *senderSem) : mBuffer(0, FRAME_BLOCK_COUNTER, gSessionData->mTotalBufferSize*1024*1024, senderSem) {
+}
+
+UserSpaceSource::~UserSpaceSource() {
+}
+
+bool UserSpaceSource::prepare() {
+	return true;
+}
+
+void UserSpaceSource::run() {
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-counters", 0, 0, 0);
+
+	for (int i = 0; i < ARRAY_LENGTH(gSessionData->mUsDrivers); ++i) {
+		gSessionData->mUsDrivers[i]->start();
+	}
+
+	int64_t monotonicStarted = 0;
+	while (monotonicStarted <= 0 && gSessionData->mSessionIsActive) {
+		usleep(10);
+
+		if (gSessionData->mPerf.isSetup()) {
+			monotonicStarted = gSessionData->mMonotonicStarted;
+		} else {
+			if (DriverSource::readInt64Driver("/dev/gator/started", &monotonicStarted) == -1) {
+				logg->logError("Error reading gator driver start time");
+				handleException();
+			}
+			gSessionData->mMonotonicStarted = monotonicStarted;
+		}
+	}
+
+	uint64_t nextTime = 0;
+	while (gSessionData->mSessionIsActive) {
+		const uint64_t currTime = getTime() - monotonicStarted;
+		// Sample ten times a second ignoring gSessionData->mSampleRate
+		nextTime += NS_PER_S/10;//gSessionData->mSampleRate;
+		if (nextTime < currTime) {
+			logg->logMessage("Too slow, currTime: %" PRIi64 " nextTime: %" PRIi64, currTime, nextTime);
+			nextTime = currTime;
+		}
+
+		if (mBuffer.eventHeader(currTime)) {
+			for (int i = 0; i < ARRAY_LENGTH(gSessionData->mUsDrivers); ++i) {
+				gSessionData->mUsDrivers[i]->read(&mBuffer);
+			}
+			// Only check after writing all counters so that time and corresponding counters appear in the same frame
+			mBuffer.check(currTime);
+		}
+
+		if (gSessionData->mOneShot && gSessionData->mSessionIsActive && (mBuffer.bytesAvailable() <= 0)) {
+			logg->logMessage("One shot (counters)");
+			child->endSession();
+		}
+
+		usleep((nextTime - currTime)/NS_PER_US);
+	}
+
+	mBuffer.setDone();
+}
+
+void UserSpaceSource::interrupt() {
+	// Do nothing
+}
+
+bool UserSpaceSource::isDone() {
+	return mBuffer.isDone();
+}
+
+void UserSpaceSource::write(Sender *sender) {
+	if (!mBuffer.isDone()) {
+		mBuffer.write(sender);
+	}
+}
diff --git a/tools/gator/daemon/UserSpaceSource.h b/tools/gator/daemon/UserSpaceSource.h
new file mode 100644
index 00000000000..0038dcb4c3d
--- /dev/null
+++ b/tools/gator/daemon/UserSpaceSource.h
@@ -0,0 +1,38 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef USERSPACESOURCE_H
+#define USERSPACESOURCE_H
+
+#include <semaphore.h>
+
+#include "Buffer.h"
+#include "Source.h"
+
+// User space counters
+class UserSpaceSource : public Source {
+public:
+	UserSpaceSource(sem_t *senderSem);
+	~UserSpaceSource();
+
+	bool prepare();
+	void run();
+	void interrupt();
+
+	bool isDone();
+	void write(Sender *sender);
+
+private:
+	Buffer mBuffer;
+
+	// Intentionally unimplemented
+	UserSpaceSource(const UserSpaceSource &);
+	UserSpaceSource &operator=(const UserSpaceSource &);
+};
+
+#endif // USERSPACESOURCE_H
diff --git a/tools/gator/daemon/c++.cpp b/tools/gator/daemon/c++.cpp
new file mode 100644
index 00000000000..caf6f1efdcd
--- /dev/null
+++ b/tools/gator/daemon/c++.cpp
@@ -0,0 +1,40 @@
+/**
+ * Minimal set of C++ functions so that libstdc++ is not required
+ *
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+
+void operator delete(void *ptr) {
+  if (ptr != NULL) {
+    free(ptr);
+  }
+}
+
+void operator delete[](void *ptr) {
+  operator delete(ptr);
+}
+
+void *operator new(size_t size) {
+  void *ptr = malloc(size == 0 ? 1 : size);
+  if (ptr == NULL) {
+    abort();
+  }
+  return ptr;
+}
+
+void *operator new[](size_t size) {
+  return operator new(size);
+}
+
+extern "C"
+void __cxa_pure_virtual() {
+  printf("pure virtual method called\n");
+  abort();
+}
diff --git a/tools/gator/daemon/common.mk b/tools/gator/daemon/common.mk
new file mode 100644
index 00000000000..0d5a0a835d2
--- /dev/null
+++ b/tools/gator/daemon/common.mk
@@ -0,0 +1,55 @@
+# -g produces debugging information
+# -O3 maximum optimization
+# -O0 no optimization, used for debugging
+# -Wall enables most warnings
+# -Werror treats warnings as errors
+# -std=c++0x is the planned new c++ standard
+# -std=c++98 is the 1998 c++ standard
+CPPFLAGS += -O3 -Wall -fno-exceptions -pthread -MMD -DETCDIR=\"/etc\" -Ilibsensors
+CXXFLAGS += -fno-rtti -Wextra -Wshadow # -Weffc++
+ifeq ($(WERROR),1)
+	CPPFLAGS += -Werror
+endif
+# -s strips the binary of debug info
+LDFLAGS += -s
+LDLIBS += -lrt -lm -pthread
+TARGET = gatord
+C_SRC = $(wildcard mxml/*.c) $(wildcard libsensors/*.c)
+CXX_SRC = $(wildcard *.cpp)
+
+all: $(TARGET)
+
+events.xml: events_header.xml $(wildcard events-*.xml) events_footer.xml
+	cat $^ > $@
+
+include $(wildcard *.d)
+include $(wildcard mxml/*.d)
+
+EventsXML.cpp: events_xml.h
+ConfigurationXML.cpp: defaults_xml.h
+
+# Don't regenerate conf-lex.c or conf-parse.c
+libsensors/conf-lex.c: ;
+libsensors/conf-parse.c: ;
+
+%_xml.h: %.xml escape
+	./escape $< > $@
+
+%.o: %.c
+	$(CC) $(CFLAGS) $(CPPFLAGS) -c -o $@ $<
+
+%.o: %.cpp
+	$(CXX) $(CXXFLAGS) $(CPPFLAGS) -c -o $@ $<
+
+SrcMd5.cpp: $(wildcard *.cpp *.h mxml/*.c mxml/*.h libsensors/*.c libsensors/*.h)
+	echo 'extern const char *const gSrcMd5 = "'`ls $^ | grep -Ev '^(.*_xml\.h|$@)$$' | LC_ALL=C sort | xargs cat | md5sum | cut -b 1-32`'";' > $@
+
+$(TARGET): $(CXX_SRC:%.cpp=%.o) $(C_SRC:%.c=%.o) SrcMd5.o
+	$(CC) $(LDFLAGS) $^ $(LDLIBS) -o $@
+
+# Intentionally ignore CC as a native binary is required
+escape: escape.c
+	gcc $^ -o $@
+
+clean:
+	rm -f *.d *.o mxml/*.d mxml/*.o libsensors/*.d libsensors/*.o $(TARGET) escape events.xml events_xml.h defaults_xml.h SrcMd5.cpp
diff --git a/tools/gator/daemon/defaults.xml b/tools/gator/daemon/defaults.xml
new file mode 100644
index 00000000000..9adde32667d
--- /dev/null
+++ b/tools/gator/daemon/defaults.xml
@@ -0,0 +1,73 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<configurations revision="3">
+  <configuration counter="ARM_ARM11_ccnt" event="0xff"/>
+  <configuration counter="ARM_ARM11_cnt0" event="0x7"/>
+  <configuration counter="ARM_ARM11_cnt1" event="0xb"/>
+  <configuration counter="ARM_ARM11MPCore_ccnt" event="0xff"/>
+  <configuration counter="ARM_ARM11MPCore_cnt0" event="0x08"/>
+  <configuration counter="ARM_ARM11MPCore_cnt1" event="0x0b"/>
+  <configuration counter="ARMv7_Cortex_A5_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A5_cnt0" event="0x8"/>
+  <configuration counter="ARMv7_Cortex_A5_cnt1" event="0x1"/>
+  <configuration counter="ARMv7_Cortex_A7_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A7_cnt0" event="0x08"/>
+  <configuration counter="ARMv7_Cortex_A7_cnt1" event="0x10"/>
+  <configuration counter="ARMv7_Cortex_A7_cnt2" event="0x16"/>
+  <configuration counter="ARMv7_Cortex_A8_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A8_cnt0" event="0x8"/>
+  <configuration counter="ARMv7_Cortex_A8_cnt1" event="0x44"/>
+  <configuration counter="ARMv7_Cortex_A8_cnt2" event="0x43"/>
+  <configuration counter="ARMv7_Cortex_A8_cnt3" event="0x10"/>
+  <configuration counter="ARMv7_Cortex_A9_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A9_cnt0" event="0x68"/>
+  <configuration counter="ARMv7_Cortex_A9_cnt1" event="0x06"/>
+  <configuration counter="ARMv7_Cortex_A9_cnt2" event="0x07"/>
+  <configuration counter="ARMv7_Cortex_A9_cnt3" event="0x03"/>
+  <configuration counter="ARMv7_Cortex_A9_cnt4" event="0x04"/>
+  <configuration counter="ARMv7_Cortex_A15_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A15_cnt0" event="0x8"/>
+  <configuration counter="ARMv7_Cortex_A15_cnt1" event="0x16"/>
+  <configuration counter="ARMv7_Cortex_A15_cnt2" event="0x10"/>
+  <configuration counter="ARMv7_Cortex_A15_cnt3" event="0x19"/>
+  <configuration counter="ARMv7_Cortex_A17_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A17_cnt0" event="0x08"/>
+  <configuration counter="ARMv7_Cortex_A17_cnt1" event="0x16"/>
+  <configuration counter="ARMv7_Cortex_A17_cnt2" event="0x10"/>
+  <configuration counter="ARMv7_Cortex_A17_cnt3" event="0x19"/>
+  <configuration counter="ARMv8_Cortex_A53_ccnt" event="0x11"/>
+  <configuration counter="ARMv8_Cortex_A53_cnt0" event="0x8"/>
+  <configuration counter="ARMv8_Cortex_A53_cnt1" event="0x16"/>
+  <configuration counter="ARMv8_Cortex_A53_cnt2" event="0x10"/>
+  <configuration counter="ARMv8_Cortex_A53_cnt3" event="0x19"/>
+  <configuration counter="ARMv8_Cortex_A57_ccnt" event="0x11"/>
+  <configuration counter="ARMv8_Cortex_A57_cnt0" event="0x8"/>
+  <configuration counter="ARMv8_Cortex_A57_cnt1" event="0x16"/>
+  <configuration counter="ARMv8_Cortex_A57_cnt2" event="0x10"/>
+  <configuration counter="ARMv8_Cortex_A57_cnt3" event="0x19"/>
+  <configuration counter="ARMv8_Cortex_A72_ccnt" event="0x11"/>
+  <configuration counter="ARMv8_Cortex_A72_cnt0" event="0x8"/>
+  <configuration counter="ARMv8_Cortex_A72_cnt1" event="0x16"/>
+  <configuration counter="ARMv8_Cortex_A72_cnt2" event="0x10"/>
+  <configuration counter="ARMv8_Cortex_A72_cnt3" event="0x19"/>
+  <configuration counter="Scorpion_ccnt" event="0xff"/>
+  <configuration counter="Scorpion_cnt0" event="0x08"/>
+  <configuration counter="Scorpion_cnt1" event="0x10"/>
+  <configuration counter="ScorpionMP_ccnt" event="0xff"/>
+  <configuration counter="ScorpionMP_cnt0" event="0x08"/>
+  <configuration counter="ScorpionMP_cnt1" event="0x10"/>
+  <configuration counter="Krait_ccnt" event="0xff"/>
+  <configuration counter="Krait_cnt0" event="0x08"/>
+  <configuration counter="Krait_cnt1" event="0x10"/>
+  <configuration counter="Linux_block_rq_wr"/>
+  <configuration counter="Linux_block_rq_rd"/>
+  <configuration counter="Linux_meminfo_memused"/>
+  <configuration counter="Linux_meminfo_memused2"/>
+  <configuration counter="Linux_meminfo_memfree"/>
+  <configuration counter="Linux_power_cpu_freq"/>
+  <configuration counter="ARM_Mali-4xx_fragment"/>
+  <configuration counter="ARM_Mali-4xx_vertex"/>
+  <configuration counter="ARM_Mali-Midgard_fragment" cores="1"/>
+  <configuration counter="ARM_Mali-Midgard_vertex" cores="1"/>
+  <configuration counter="ARM_Mali-Midgard_opencl" cores="1"/>
+  <configuration counter="L2C-310_cnt0" event="0x1"/>
+</configurations>
diff --git a/tools/gator/daemon/escape.c b/tools/gator/daemon/escape.c
new file mode 100644
index 00000000000..99f434848cb
--- /dev/null
+++ b/tools/gator/daemon/escape.c
@@ -0,0 +1,75 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * The Makefile in the daemon folder builds and executes 'escape'
+ * 'escape' creates configuration_xml.h from configuration.xml and events_xml.h from events-*.xml
+ * these genereated xml files are then #included and built as part of the gatord binary
+ */
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <ctype.h>
+
+static void print_escaped_path(char *path) {
+  if (isdigit(*path)) {
+    printf("__");
+  }
+  for (; *path != '\0'; ++path) {
+    printf("%c", isalnum(*path) ? *path : '_');
+  }
+}
+
+int main(int argc, char *argv[]) {
+  int i;
+  char *path;
+  FILE *in = NULL;
+  int ch;
+  unsigned int len = 0;
+
+  for (i = 1; i < argc && argv[i][0] == '-'; ++i) ;
+  if (i == argc) {
+    fprintf(stderr, "Usage: %s <filename>\n", argv[0]);
+    return EXIT_FAILURE;
+  }
+  path = argv[i];
+
+  errno = 0;
+  if ((in = fopen(path, "r")) == NULL) {
+    fprintf(stderr, "Unable to open '%s': %s\n", path, strerror(errno));
+    return EXIT_FAILURE;
+  }
+
+  printf("static const unsigned char ");
+  print_escaped_path(path);
+  printf("[] = {");
+  for (;;) {
+    ch = fgetc(in);
+    if (len != 0) {
+      printf(",");
+    }
+    if (len % 12 == 0) {
+      printf("\n ");
+    }
+    // Write out a null character after the contents of the file but do not increment len
+    printf(" 0x%.2x", (ch == EOF ? 0 : ch));
+    if (ch == EOF) {
+      break;
+    }
+    ++len;
+  }
+  printf("\n};\nstatic const unsigned int ");
+  print_escaped_path(path);
+  printf("_len = %i;\n", len);
+
+  fclose(in);
+
+  return EXIT_SUCCESS;
+}
diff --git a/tools/gator/daemon/events-ARM11.xml b/tools/gator/daemon/events-ARM11.xml
new file mode 100644
index 00000000000..e481267b21a
--- /dev/null
+++ b/tools/gator/daemon/events-ARM11.xml
@@ -0,0 +1,39 @@
+  <counter_set name="ARM_ARM11_cnt" count="3"/>
+  <category name="ARM11" counter_set="ARM_ARM11_cnt" per_cpu="yes">
+    <event counter="ARM_ARM11_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Cache" name="Inst miss" description="Instruction cache miss to a cacheable location, which requires a fetch from external memory"/>
+    <event event="0x01" title="Pipeline" name="Instruction stall" description="Stall because instruction buffer cannot deliver an instruction"/>
+    <event event="0x02" title="Pipeline" name="Data stall" description="Stall because of a data dependency"/>
+    <event event="0x03" title="Cache" name="Inst micro TLB miss" description="Instruction MicroTLB miss (unused on ARM1156)"/>
+    <event event="0x04" title="Cache" name="Data micro TLB miss" description="Data MicroTLB miss (unused on ARM1156)"/>
+    <event event="0x05" title="Branch" name="Instruction executed" description="Branch instruction executed, branch might or might not have changed program flow"/>
+    <event event="0x06" title="Branch" name="Mispredicted" description="Branch mis-predicted"/>
+    <event event="0x07" title="Instruction" name="Executed" description="Instructions executed"/>
+    <event event="0x09" title="Cache" name="Data access" description="Data cache access, not including Cache operations"/>
+    <event event="0x0a" title="Cache" name="Data all access" description="Data cache access, not including Cache Operations regardless of whether or not the location is cacheable"/>
+    <event event="0x0b" title="Cache" name="Data miss" description="Data cache miss, not including Cache Operations"/>
+    <event event="0x0c" title="Cache" name="Write-back" description="Data cache write-back"/>
+    <event event="0x0d" title="Program Counter" name="SW change" description="Software changed the PC"/>
+    <event event="0x0f" title="Cache " name="TLB miss" description="Main TLB miss (unused on ARM1156)"/>
+    <event event="0x10" title="External" name="Access" description="Explicit external data or peripheral access"/>
+    <event event="0x11" title="Cache" name="Stall" description="Stall because of Load Store Unit request queue being full"/>
+    <event event="0x12" title="Write Buffer" name="Drains" description="The number of times the Write Buffer was drained because of a Data Synchronization Barrier command or Strongly Ordered operation"/>
+    <event event="0x13" title="Disable Interrupts" name="FIQ" description="The number of cycles which FIQ interrupts are disabled (ARM1156 only)"/>
+    <event event="0x14" title="Disable Interrupts" name="IRQ" description="The number of cycles which IRQ interrupts are disabled (ARM1156 only)"/>
+    <event event="0x20" title="ETM" name="ETMEXTOUT[0]" description="ETMEXTOUT[0] signal was asserted for a cycle"/>
+    <event event="0x21" title="ETM" name="ETMEXTOUT[1]" description="ETMEXTOUT[1] signal was asserted for a cycle"/>
+    <event event="0x22" title="ETM" name="ETMEXTOUT[0,1]" description="ETMEXTOUT[0] or ETMEXTOUT[1] was asserted"/>
+    <event event="0x23" title="Procedure" name="Calls" description="Procedure call instruction executed"/>
+    <event event="0x24" title="Procedure" name="Returns" description="Procedure return instruction executed"/>
+    <event event="0x25" title="Procedure" name="Return and predicted" description="Procedure return instruction executed and return address predicted"/>
+    <event event="0x26" title="Procedure" name="Return and mispredicted" description="Procedure return instruction executed and return address predicted incorrectly"/>
+    <event event="0x30" title="Cache" name="Inst tag or parity error" description="Instruction cache Tag or Valid RAM parity error (ARM1156 only)"/>
+    <event event="0x31" title="Cache" name="Inst parity error" description="Instruction cache RAM parity error (ARM1156 only)"/>
+    <event event="0x32" title="Cache" name="Data tag or parity error" description="Data cache Tag or Valid RAM parity error (ARM1156 only)"/>
+    <event event="0x33" title="Cache" name="Data parity error" description="Data cache RAM parity error (ARM1156 only)"/>
+    <event event="0x34" title="ITCM" name="Error" description="ITCM error (ARM1156 only)"/>
+    <event event="0x35" title="DTCM" name="Error" description="DTCM error (ARM1156 only)"/>
+    <event event="0x36" title="Procedure" name="Return address pop" description="Procedure return address popped off the return stack (ARM1156 only)"/>
+    <event event="0x37" title="Procedure" name="Return address misprediction" description="Procedure return address popped off the return stack has been incorrectly predicted by the PFU (ARM1156 only)"/>
+    <event event="0x38" title="Cache" name="Data dirty parity error" description="Data cache Dirty RAM parity error (ARM1156 only)"/>
+  </category>
diff --git a/tools/gator/daemon/events-ARM11MPCore.xml b/tools/gator/daemon/events-ARM11MPCore.xml
new file mode 100644
index 00000000000..2d5c5e199e6
--- /dev/null
+++ b/tools/gator/daemon/events-ARM11MPCore.xml
@@ -0,0 +1,26 @@
+  <counter_set name="ARM_ARM11MPCore_cnt" count="3"/>
+  <category name="ARM11MPCore" counter_set="ARM_ARM11MPCore_cnt" per_cpu="yes">
+    <event counter="ARM_ARM11MPCore_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Cache" name="Inst miss" description="Instruction cache miss to a cacheable location, which requires a fetch from external memory"/>
+    <event event="0x01" title="Pipeline" name="Instruction stall" description="Stall because instruction buffer cannot deliver an instruction"/>
+    <event event="0x02" title="Pipeline" name="Data stall" description="Stall because of a data dependency"/>
+    <event event="0x03" title="Cache" name="Inst micro TLB miss" description="Instruction MicroTLB miss (unused on ARM1156)"/>
+    <event event="0x04" title="Cache" name="Data micro TLB miss" description="Data MicroTLB miss (unused on ARM1156)"/>
+    <event event="0x05" title="Branch" name="Instruction executed" description="Branch instructions executed, branch might or might not have changed program flow"/>
+    <event event="0x06" title="Branch" name="Not predicted" description="Branch not predicted"/>
+    <event event="0x07" title="Branch" name="Mispredicted" description="Branch mispredicted"/>
+    <event event="0x08" title="Core" name="Instructions" description="Instructions executed"/>
+    <event event="0x09" title="Core" name="Folded Instructions" description="Folded instructions executed"/>
+    <event event="0x0a" title="Cache" name="Data read access" description="Data cache read access, not including cache operations"/>
+    <event event="0x0b" title="Cache" name="Data read miss" description="Data cache miss, not including Cache Operations"/>
+    <event event="0x0c" title="Cache" name="Data write access" description="Data cache write access"/>
+    <event event="0x0d" title="Cache" name="Data write miss" description="Data cache write miss"/>
+    <event event="0x0e" title="Cache" name="Data line eviction" description="Data cache line eviction, not including cache operations"/>
+    <event event="0x0f" title="Branch" name="PC change w/o mode change" description="Software changed the PC and there is not a mode change"/>
+    <event event="0x10" title="Cache " name="TLB miss" description="Main TLB miss"/>
+    <event event="0x11" title="External" name="External Memory request" description="External memory request (cache refill, noncachable, write-back)"/>
+    <event event="0x12" title="Cache" name="Stall" description="Stall because of Load Store Unit request queue being full"/>
+    <event event="0x13" title="Write Buffer" name="Drains" description="The number of times the Write Buffer was drained because of LSU ordering constraints or CP15 operations (Data Synchronization Barrier command) or Strongly Ordered operation"/>
+    <event event="0x14" title="Write Buffer" name="Write Merges" description="Buffered write merged in a store buffer slot"/>
+    <event event="0xFF" title="Core" name="Cycle counter" description="An increment each cycle"/>
+  </category>
diff --git a/tools/gator/daemon/events-CCI-400.xml b/tools/gator/daemon/events-CCI-400.xml
new file mode 100644
index 00000000000..0dd72c02ec5
--- /dev/null
+++ b/tools/gator/daemon/events-CCI-400.xml
@@ -0,0 +1,98 @@
+  <counter_set name="CCI_400_cnt" count="4"/>
+  <category name="CCI-400" counter_set="CCI_400_cnt" per_cpu="no">
+    <event counter="CCI_400_ccnt" event="0xff" title="CCI-400 Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" description="The number of core clock cycles"/>
+    <option_set name="Slave">
+      <option event_delta="0x00" name="S0" description="Slave interface 0"/>
+      <option event_delta="0x20" name="S1" description="Slave interface 1"/>
+      <option event_delta="0x40" name="S2" description="Slave interface 2"/>
+      <option event_delta="0x60" name="S3" description="Slave interface 3"/>
+      <option event_delta="0x80" name="S4" description="Slave interface 4"/>
+    </option_set>
+    <event event="0x00" option_set="Slave" title="CCI-400" name="Read: any" description="Read request handshake: any"/>
+    <event event="0x01" option_set="Slave" title="CCI-400" name="Read: transaction" description="Read request handshake: device transaction"/>
+    <event event="0x02" option_set="Slave" title="CCI-400" name="Read: normal" description="Read request handshake: normal, non-shareable or system-shareable, but not barrier or cache maintenance operation"/>
+    <event event="0x03" option_set="Slave" title="CCI-400" name="Read: shareable" description="Read request handshake: inner- or outer-shareable, but not barrier, DVM message or cache maintenance operation"/>
+    <event event="0x04" option_set="Slave" title="CCI-400" name="Read: cache" description="Read request handshake: cache maintenance operation, CleanInvalid, CleanShared, MakeInvalid"/>
+    <event event="0x05" option_set="Slave" title="CCI-400" name="Read: memory barrier" description="Read request handshake: memory barrier"/>
+    <event event="0x06" option_set="Slave" title="CCI-400" name="Read: sync barrier" description="Read request handshake: synchronization barrier"/>
+    <event event="0x07" option_set="Slave" title="CCI-400" name="Read: DVM message, no sync" description="Read request handshake: DVM message, not synchronization"/>
+    <event event="0x08" option_set="Slave" title="CCI-400" name="Read: DVM message, sync" description="Read request handshake: DVM message, synchronization"/>
+    <event event="0x09" option_set="Slave" title="CCI-400" name="Read: stall" description="Read request stall cycle because the transaction tracker is full. Increase SIx_R_MAX to avoid this stall"/>
+    <event event="0x0a" option_set="Slave" title="CCI-400" name="Read data last handshake" description="Read data last handshake: data returned from the snoop instead of from downstream"/>
+    <event event="0x0b" option_set="Slave" title="CCI-400" name="Read data stall cycle" description="Read data stall cycle: RVALIDS is HIGH, RREADYS is LOW"/>
+    <event event="0x0c" option_set="Slave" title="CCI-400" name="Write: any" description="Write request handshake: any"/>
+    <event event="0x0d" option_set="Slave" title="CCI-400" name="Write: transaction" description="Write request handshake: device transaction"/>
+    <event event="0x0e" option_set="Slave" title="CCI-400" name="Write: normal" description="Write request handshake: normal, non-shareable, or system-shareable, but not barrier"/>
+    <event event="0x0f" option_set="Slave" title="CCI-400" name="Write: shareable" description="Write request handshake: inner- or outer-shareable, WriteBack or WriteClean"/>
+    <event event="0x10" option_set="Slave" title="CCI-400" name="Write: WriteUnique" description="Write request handshake: WriteUnique"/>
+    <event event="0x11" option_set="Slave" title="CCI-400" name="Write: WriteLineUnique" description="Write request handshake: WriteLineUnique"/>
+    <event event="0x12" option_set="Slave" title="CCI-400" name="Write: Evict" description="Write request handshake: Evict"/>
+    <event event="0x13" option_set="Slave" title="CCI-400" name="Write stall: tracker full" description="Write request stall cycle because the transaction tracker is full. Increase SIx_W_MAX to avoid this stall"/>
+    <option_set name="Master">
+      <option event_delta="0xa0" name="M0" description="Master interface 0"/>
+      <option event_delta="0xc0" name="M1" description="Master interface 1"/>
+      <option event_delta="0xe0" name="M2" description="Master interface 2"/>
+    </option_set>
+    <event event="0x14" option_set="Master" title="CCI-400" name="Retry fetch" description="RETRY of speculative fetch transaction"/>
+    <event event="0x15" option_set="Master" title="CCI-400" name="Read stall: address hazard" description="Read request stall cycle because of an address hazard"/>
+    <event event="0x16" option_set="Master" title="CCI-400" name="Read stall: ID hazard" description="Read request stall cycle because of an ID hazard"/>
+    <event event="0x17" option_set="Master" title="CCI-400" name="Read stall: tracker full" description="Read request stall cycle because the transaction tracker is full. Increase MIx_R_MAX to avoid this stall. See the CoreLink CCI-400 Cache Coherent Interconnect Integration Manual"/>
+    <event event="0x18" option_set="Master" title="CCI-400" name="Read stall: barrier hazard" description="Read request stall cycle because of a barrier hazard"/>
+    <event event="0x19" option_set="Master" title="CCI-400" name="Write stall: barrier hazard" description="Write request stall cycle because of a barrier hazard"/>
+    <event event="0x1a" option_set="Master" title="CCI-400" name="Write stall: tracker full" description="Write request stall cycle because the transaction tracker is full. Increase MIx_W_MAX to avoid this stall. See the CoreLink CCI-400 Cache Coherent Interconnect Integration Manual"/>
+  </category>
+  <counter_set name="CCI_400_r1_cnt" count="4"/>
+  <category name="CCI-400" counter_set="CCI_400_r1_cnt" per_cpu="no">
+    <event counter="CCI_400_r1_ccnt" event="0xff" title="CCI-400 Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" description="The number of core clock cycles"/>
+    <option_set name="Slave">
+      <option event_delta="0x00" name="S0" description="Slave interface 0"/>
+      <option event_delta="0x20" name="S1" description="Slave interface 1"/>
+      <option event_delta="0x40" name="S2" description="Slave interface 2"/>
+      <option event_delta="0x60" name="S3" description="Slave interface 3"/>
+      <option event_delta="0x80" name="S4" description="Slave interface 4"/>
+    </option_set>
+    <event event="0x00" option_set="Slave" title="CCI-400" name="Read: any" description="Read request handshake: any"/>
+    <event event="0x01" option_set="Slave" title="CCI-400" name="Read: transaction" description="Read request handshake: device transaction"/>
+    <event event="0x02" option_set="Slave" title="CCI-400" name="Read: normal" description="Read request handshake: normal, non-shareable or system-shareable, but not barrier or cache maintenance operation"/>
+    <event event="0x03" option_set="Slave" title="CCI-400" name="Read: shareable" description="Read request handshake: inner- or outer-shareable, but not barrier, DVM message or cache maintenance operation"/>
+    <event event="0x04" option_set="Slave" title="CCI-400" name="Read: cache" description="Read request handshake: cache maintenance operation"/>
+    <event event="0x05" option_set="Slave" title="CCI-400" name="Read: memory barrier" description="Read request handshake: memory barrier"/>
+    <event event="0x06" option_set="Slave" title="CCI-400" name="Read: sync barrier" description="Read request handshake: synchronization barrier"/>
+    <event event="0x07" option_set="Slave" title="CCI-400" name="Read: DVM message, no sync" description="Read request handshake: DVM message, not synchronization"/>
+    <event event="0x08" option_set="Slave" title="CCI-400" name="Read: DVM message, sync" description="Read request handshake: DVM message, synchronization"/>
+    <event event="0x09" option_set="Slave" title="CCI-400" name="Read: stall" description="Read request stall cycle because the transaction tracker is full. Increase SIx_R_MAX to avoid this stall"/>
+    <event event="0x0a" option_set="Slave" title="CCI-400" name="Read data last handshake" description="Read data last handshake: data returned from the snoop instead of from downstream"/>
+    <event event="0x0b" option_set="Slave" title="CCI-400" name="Read data stall cycle" description="Read data stall cycle: RVALIDS is HIGH, RREADYS is LOW"/>
+    <event event="0x0c" option_set="Slave" title="CCI-400" name="Write: any" description="Write request handshake: any"/>
+    <event event="0x0d" option_set="Slave" title="CCI-400" name="Write: transaction" description="Write request handshake: device transaction"/>
+    <event event="0x0e" option_set="Slave" title="CCI-400" name="Write: normal" description="Write request handshake: normal, non-shareable, or system-shareable, but not barrier"/>
+    <event event="0x0f" option_set="Slave" title="CCI-400" name="Write: shareable" description="Write request handshake: inner- or outer-shareable, WriteBack or WriteClean"/>
+    <event event="0x10" option_set="Slave" title="CCI-400" name="Write: WriteUnique" description="Write request handshake: WriteUnique"/>
+    <event event="0x11" option_set="Slave" title="CCI-400" name="Write: WriteLineUnique" description="Write request handshake: WriteLineUnique"/>
+    <event event="0x12" option_set="Slave" title="CCI-400" name="Write: Evict" description="Write request handshake: Evict"/>
+    <event event="0x13" option_set="Slave" title="CCI-400" name="Write stall: tracker full" description="Write request stall cycle because the transaction tracker is full. Increase SIx_W_MAX to avoid this stall"/>
+    <event event="0x14" option_set="Slave" title="CCI-400" name="Read stall: slave hazard" description="Read request stall cycle because of a slave interface ID hazard"/>
+    <option_set name="Master">
+      <option event_delta="0xa0" name="M0" description="Master interface 0"/>
+      <option event_delta="0xc0" name="M1" description="Master interface 1"/>
+      <option event_delta="0xe0" name="M2" description="Master interface 2"/>
+    </option_set>
+    <event event="0x00" option_set="Master" title="CCI-400" name="Retry fetch" description="RETRY of speculative fetch transaction"/>
+    <event event="0x01" option_set="Master" title="CCI-400" name="Read stall: address hazard" description="Stall cycle because of an address hazard. A read or write invalidation is stalled because of an outstanding transaction to an overlapping address"/>
+    <event event="0x02" option_set="Master" title="CCI-400" name="Read stall: ID hazard" description="Read request stall cycle because of a master interface ID hazard"/>
+    <event event="0x03" option_set="Master" title="CCI-400" name="Read stall: tracker full" description="A read request with a QoS value in the high priority group is stalled for a cycle because the read transaction queue is full. Increase MIx_R_MAX to avoid this stall"/>
+    <event event="0x04" option_set="Master" title="CCI-400" name="Read stall: barrier hazard" description="Read request stall cycle because of a barrier hazard"/>
+    <event event="0x05" option_set="Master" title="CCI-400" name="Write stall: barrier hazard" description="Write request stall cycle because of a barrier hazard"/>
+    <event event="0x06" option_set="Master" title="CCI-400" name="Write stall: tracker full" description="A write request is stalled for a cycle because the write transaction tracker is full. Increase MIx_W_MAX to avoid this stall"/>
+    <event event="0x07" option_set="Master" title="CCI-400" name="Read Stall: Low Priority" description="A read request with a QoS value in the low priority group is stalled for a cycle because there are no slots available in the read queue for the low priority group"/>
+    <event event="0x08" option_set="Master" title="CCI-400" name="Read Stall: Medium Priority" description="A read request with a QoS value in the medium priority group is stalled for a cycle because there are no slots available in the read queue for the medium priority group"/>
+    <event event="0x09" option_set="Master" title="CCI-400" name="Read Stall: VN0" description="A read request is stalled for a cycle while it was waiting for a QVN token on VN0"/>
+    <event event="0x0a" option_set="Master" title="CCI-400" name="Read Stall: VN1" description="A read request is stalled for a cycle while it was waiting for a QVN token on VN1"/>
+    <event event="0x0b" option_set="Master" title="CCI-400" name="Read Stall: VN2" description="A read request is stalled for a cycle while it was waiting for a QVN token on VN2"/>
+    <event event="0x0c" option_set="Master" title="CCI-400" name="Read Stall: VN3" description="A read request is stalled for a cycle while it was waiting for a QVN token on VN3"/>
+    <event event="0x0d" option_set="Master" title="CCI-400" name="Write Stall: VN0" description="A write request is stalled for a cycle while it was waiting for a QVN token on VN0"/>
+    <event event="0x0e" option_set="Master" title="CCI-400" name="Write Stall: VN1" description="A write request is stalled for a cycle while it was waiting for a QVN token on VN1"/>
+    <event event="0x0f" option_set="Master" title="CCI-400" name="Write Stall: VN2" description="A write request is stalled for a cycle while it was waiting for a QVN token on VN2"/>
+    <event event="0x10" option_set="Master" title="CCI-400" name="Write Stall: VN" description="A write request is stalled for a cycle while it was waiting for a QVN token on VN"/>
+    <event event="0x11" option_set="Master" title="CCI-400" name="WriteUnique or WriteLineUnique Stall" description="A WriteUnique or WriteLineUnique request is stalled for a cycle because of an address hazard"/>
+  </category>
diff --git a/tools/gator/daemon/events-CCI-500.xml b/tools/gator/daemon/events-CCI-500.xml
new file mode 100644
index 00000000000..e7cadc47b1d
--- /dev/null
+++ b/tools/gator/daemon/events-CCI-500.xml
@@ -0,0 +1,75 @@
+  <counter_set name="CCI_500_cnt" count="8"/>
+  <category name="CCI-500" counter_set="CCI_500_cnt" per_cpu="no">
+    <option_set name="Slave">
+      <option event_delta="0x00" name="S0" description="Slave interface 0"/>
+      <option event_delta="0x20" name="S1" description="Slave interface 1"/>
+      <option event_delta="0x40" name="S2" description="Slave interface 2"/>
+      <option event_delta="0x60" name="S3" description="Slave interface 3"/>
+      <option event_delta="0x80" name="S4" description="Slave interface 4"/>
+      <option event_delta="0xa0" name="S5" description="Slave interface 5"/>
+      <option event_delta="0xc0" name="S6" description="Slave interface 6"/>
+    </option_set>
+    <event event="0x00" option_set="Slave" title="CCI-500" name="Read ARVALID" description="Read request handshake: any ARVALID, ARREADY HIGH"/>
+    <event event="0x01" option_set="Slave" title="CCI-500" name="Read device" description="Read request: device"/>
+    <event event="0x02" option_set="Slave" title="CCI-500" name="Read non-shareable" description="Read request handshake: normal, non-shareable"/>
+    <event event="0x03" option_set="Slave" title="CCI-500" name="Read non-allocating" description="Read request handshake: normal, shareable, non-allocating, for example ReadOnce"/>
+    <event event="0x04" option_set="Slave" title="CCI-500" name="Read other" description="Read request handshake: normal, shareable allocating, for example ReadClean, ReadShared, ReadNotSharedDirty, ReadUnique"/>
+    <event event="0x05" option_set="Slave" title="CCI-500" name="Read invalidation" description="Read request handshake: invalidation, for example MakeUnique, CleanUnique"/>
+    <event event="0x06" option_set="Slave" title="CCI-500" name="Read maintenance" description="Read request handshake: cache maintenance operation, for example CleanInvalid, MakeInvalid, CleanShared"/>
+    <event event="0x07" option_set="Slave" title="CCI-500" name="Read DVM" description="Read request handshake: DVM message, any"/>
+    <event event="0x08" option_set="Slave" title="CCI-500" name="Read RVALID" description="Read data handshake: any RVALID, RREADY HIGH"/>
+    <event event="0x09" option_set="Slave" title="CCI-500" name="Read RLAST" description="Read data handshake with RLAST set, for a snoop hit"/>
+    <event event="0x0a" option_set="Slave" title="CCI-500" name="Write AWVALID" description="Write request: any AWVALID, AWREADY HIGH"/>
+    <event event="0x0b" option_set="Slave" title="CCI-500" name="Write device" description="Write request: device"/>
+    <event event="0x0c" option_set="Slave" title="CCI-500" name="Write non-shareable" description="Write request: non-shareable"/>
+    <event event="0x0d" option_set="Slave" title="CCI-500" name="Write shareable a" description="Write request handshake: shareable, for example WriteBack, WriteClean"/>
+    <event event="0x0e" option_set="Slave" title="CCI-500" name="Write shareable b" description="Write request handshake: shareable, for example WriteLineUnique"/>
+    <event event="0x0f" option_set="Slave" title="CCI-500" name="Write shareable c" description="Write request handshake: shareable, for example WriteUnique"/>
+    <event event="0x10" option_set="Slave" title="CCI-500" name="Write evict" description="Write request handshake, for example Evict"/>
+    <!--event event="0x11" option_set="Slave" title="CCI-500" name="Write evict ?" description="Write request handshake, for example WriteEvict. WriteEvict is not supported in the CCI-500, so does not fire."/-->
+    <event event="0x12" option_set="Slave" title="CCI-500" name="Write WVALID" description="Write data beat: any WVALID, WREADY HIGH"/>
+    <event event="0x13" option_set="Slave" title="CCI-500" name="Snoop ACVLID" description="Snoop request: any ACVALID, ACREADY HIGH"/>
+    <event event="0x14" option_set="Slave" title="CCI-500" name="Snoop read" description="Snoop request: read, for example ReadOnce, ReadClean, ReadNotSharedDirty, ReadShared, ReadUnique"/>
+    <event event="0x15" option_set="Slave" title="CCI-500" name="Snoop invalidate" description="Snoop request: clean or invalidate, for example MakeInvalid, CleanInvalid, CleanShared"/>
+    <event event="0x16" option_set="Slave" title="CCI-500" name="Snoop CRRESP" description="Snoop request: Data Transfer bit CRRESP[0] LOW"/>
+    <event event="0x17" option_set="Slave" title="CCI-500" name="Read request stall" description="Read request stall: ARVALID HIGH ARREADY LOW"/>
+    <event event="0x18" option_set="Slave" title="CCI-500" name="Read data stall" description="Read data stall: RVALID HIGH RREADY LOW"/>
+    <event event="0x19" option_set="Slave" title="CCI-500" name="Write request stall" description="Write request stall: AWVALID HIGH AWREADY LOW"/>
+    <event event="0x1a" option_set="Slave" title="CCI-500" name="Write data stall" description="Write data stall: WVALID HIGH WREADY LOW"/>
+    <event event="0x1b" option_set="Slave" title="CCI-500" name="Write response stall" description="Write response stall: BVALID HIGH BREADY LOW"/>
+    <event event="0x1c" option_set="Slave" title="CCI-500" name="Snoop request stall" description="Snoop request stall: ACVALID HIGH ACREADY LOW"/>
+    <event event="0x1d" option_set="Slave" title="CCI-500" name="Snoop data stall" description="Snoop data stall: CDVALID HIGH CDREADY LOW"/>
+    <event event="0x1e" option_set="Slave" title="CCI-500" name="Request stall" description="Request stall cycle because of OT transaction limit"/>
+    <event event="0x1f" option_set="Slave" title="CCI-500" name="Read stall" description="Read stall because of arbitration"/>
+    <option_set name="Master">
+      <option event_delta="0x100" name="M0" description="Master interface 0"/>
+      <option event_delta="0x120" name="M1" description="Master interface 1"/>
+      <option event_delta="0x140" name="M2" description="Master interface 2"/>
+      <option event_delta="0x160" name="M3" description="Master interface 3"/>
+      <option event_delta="0x180" name="M4" description="Master interface 4"/>
+      <option event_delta="0x1a0" name="M5" description="Master interface 5"/>
+    </option_set>
+    <event event="0x00" option_set="Master" title="CCI-500" name="Read data beat" description="Read data beat: any"/>
+    <event event="0x01" option_set="Master" title="CCI-500" name="Write data beat" description="Write data beat: any"/>
+    <event event="0x02" option_set="Master" title="CCI-500" name="Read request stall" description="Read request stall: ARVALID HIGH ARREADY LOW"/>
+    <event event="0x03" option_set="Master" title="CCI-500" name="Read data stall" description="Read data stall: RVALID HIGH RREADY LOW"/>
+    <event event="0x04" option_set="Master" title="CCI-500" name="Write request stall" description="Write request stall: AWVALID HIGH AWREADY LOW"/>
+    <event event="0x05" option_set="Master" title="CCI-500" name="Write data stall" description="Write data stall: WVALID HIGH WREADY LOW"/>
+    <event event="0x06" option_set="Master" title="CCI-500" name="Write response stall" description="Write response stall: BVALID HIGH BREADY LOW"/>
+    <event event="0x1e0" title="CCI-500" name="Snoop response 0/1" description="Access to snoop filter bank 0 or 1, any response"/>
+    <event event="0x1e1" title="CCI-500" name="Snoop response 2/3" description="Access to snoop filter bank 2 or 3, any response"/>
+    <event event="0x1e2" title="CCI-500" name="Snoop response 3/4" description="Access to snoop filter bank 4 or 5, any response"/>
+    <event event="0x1e3" title="CCI-500" name="Snoop response 6/7" description="Access to snoop filter bank 6 or 7, any response"/>
+    <event event="0x1e4" title="CCI-500" name="Snoop miss 0/1" description="Access to snoop filter bank 0 or 1, miss response"/>
+    <event event="0x1e5" title="CCI-500" name="Snoop miss 2/3" description="Access to snoop filter bank 2 or 3, miss response"/>
+    <event event="0x1e6" title="CCI-500" name="Snoop miss 4/5" description="Access to snoop filter bank 4 or 5, miss response"/>
+    <event event="0x1e7" title="CCI-500" name="Snoop miss 6/7" description="Access to snoop filter bank 6 or 7, miss response"/>
+    <event event="0x1e8" title="CCI-500" name="Snoop invalidation" description="Back invalidation from snoop filter"/>
+    <event event="0x1e9" title="CCI-500" name="Snoop small" description="Requests that allocate into a snoop filter bank might be stalled because all ways are used. The snoop filter RAM might be too small."/>
+    <event event="0x1ea" title="CCI-500" name="TT stall" description="Stall because TT full, increase TT_DEPTH parameter to avoid performance degradation"/>
+    <event event="0x1eb" title="CCI-500" name="Write request" description="CCI-generated write request"/>
+    <event event="0x1ec" title="CCI-500" name="Snoop handshake" description="CD handshake in snoop network, use this to measure snoop data bandwidth. Each event corresponds to 16 bytes of snoop data."/>
+    <event event="0x1ed" title="CCI-500" name="Address hazard" description="Request stall because of address hazard"/>
+    <event event="0x1ee" title="CCI-500" name="TT full" description="Snoop request stall because of snoop TT being full"/>
+    <event event="0x1ef" title="CCI-500" name="Snoop override" description="Snoop request type override for TZMP1 protection"/>
+  </category>
diff --git a/tools/gator/daemon/events-CCN-504.xml b/tools/gator/daemon/events-CCN-504.xml
new file mode 100644
index 00000000000..6ef3e648371
--- /dev/null
+++ b/tools/gator/daemon/events-CCN-504.xml
@@ -0,0 +1,113 @@
+  <counter_set name="CCN-504_cnt" count="4"/>
+  <category name="CCN-504" counter_set="CCN-504_cnt">
+    <event counter="CCN-504_ccnt" title="CCN-504 Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" description="The number of core clock cycles"/>
+    <option_set name="XP_Region">
+      <option event_delta="0x400000" name="XP 0" description="Crosspoint 0"/>
+      <option event_delta="0x410000" name="XP 1" description="Crosspoint 1"/>
+      <option event_delta="0x420000" name="XP 2" description="Crosspoint 2"/>
+      <option event_delta="0x430000" name="XP 3" description="Crosspoint 3"/>
+      <option event_delta="0x440000" name="XP 4" description="Crosspoint 4"/>
+      <option event_delta="0x450000" name="XP 5" description="Crosspoint 5"/>
+      <option event_delta="0x460000" name="XP 6" description="Crosspoint 6"/>
+      <option event_delta="0x470000" name="XP 7" description="Crosspoint 7"/>
+      <option event_delta="0x480000" name="XP 8" description="Crosspoint 8"/>
+      <option event_delta="0x490000" name="XP 9" description="Crosspoint 9"/>
+      <option event_delta="0x4A0000" name="XP 10" description="Crosspoint 10"/>
+    </option_set>
+    <event event="0x0801" option_set="XP_Region" title="CCN-504" name="Bus 0: REQ: H-bit" description="Bus 0: REQ: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x0802" option_set="XP_Region" title="CCN-504" name="Bus 0: REQ: S-bit" description="Bus 0: REQ: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x0803" option_set="XP_Region" title="CCN-504" name="Bus 0: REQ: P-Cnt" description="Bus 0: REQ: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x0804" option_set="XP_Region" title="CCN-504" name="Bus 0: REQ: TknV" description="Bus 0: REQ: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0809" option_set="XP_Region" title="CCN-504" name="Bus 1: REQ: H-bit" description="Bus 1: REQ: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x080A" option_set="XP_Region" title="CCN-504" name="Bus 1: REQ: S-bit" description="Bus 1: REQ: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x080B" option_set="XP_Region" title="CCN-504" name="Bus 1: REQ: P-Cnt" description="Bus 1: REQ: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x080C" option_set="XP_Region" title="CCN-504" name="Bus 1: REQ: TknV" description="Bus 1: REQ: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0811" option_set="XP_Region" title="CCN-504" name="Bus 0: RSP: H-bit" description="Bus 0: RSP: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x0812" option_set="XP_Region" title="CCN-504" name="Bus 0: RSP: S-bit" description="Bus 0: RSP: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x0813" option_set="XP_Region" title="CCN-504" name="Bus 0: RSP: P-Cnt" description="Bus 0: RSP: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x0814" option_set="XP_Region" title="CCN-504" name="Bus 0: RSP: TknV" description="Bus 0: RSP: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0819" option_set="XP_Region" title="CCN-504" name="Bus 1: RSP: H-bit" description="Bus 1: RSP: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x081A" option_set="XP_Region" title="CCN-504" name="Bus 1: RSP: S-bit" description="Bus 1: RSP: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x081B" option_set="XP_Region" title="CCN-504" name="Bus 1: RSP: P-Cnt" description="Bus 1: RSP: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x081C" option_set="XP_Region" title="CCN-504" name="Bus 1: RSP: TknV" description="Bus 1: RSP: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0821" option_set="XP_Region" title="CCN-504" name="Bus 0: SNP: H-bit" description="Bus 0: SNP: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x0822" option_set="XP_Region" title="CCN-504" name="Bus 0: SNP: S-bit" description="Bus 0: SNP: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x0823" option_set="XP_Region" title="CCN-504" name="Bus 0: SNP: P-Cnt" description="Bus 0: SNP: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x0824" option_set="XP_Region" title="CCN-504" name="Bus 0: SNP: TknV" description="Bus 0: SNP: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0829" option_set="XP_Region" title="CCN-504" name="Bus 1: SNP: H-bit" description="Bus 1: SNP: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x082A" option_set="XP_Region" title="CCN-504" name="Bus 1: SNP: S-bit" description="Bus 1: SNP: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x082B" option_set="XP_Region" title="CCN-504" name="Bus 1: SNP: P-Cnt" description="Bus 1: SNP: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x082C" option_set="XP_Region" title="CCN-504" name="Bus 1: SNP: TknV" description="Bus 1: SNP: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0831" option_set="XP_Region" title="CCN-504" name="Bus 0: DAT: H-bit" description="Bus 0: DAT: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x0832" option_set="XP_Region" title="CCN-504" name="Bus 0: DAT: S-bit" description="Bus 0: DAT: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x0833" option_set="XP_Region" title="CCN-504" name="Bus 0: DAT: P-Cnt" description="Bus 0: DAT: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x0834" option_set="XP_Region" title="CCN-504" name="Bus 0: DAT: TknV" description="Bus 0: DAT: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0839" option_set="XP_Region" title="CCN-504" name="Bus 1: DAT: H-bit" description="Bus 1: DAT: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x083A" option_set="XP_Region" title="CCN-504" name="Bus 1: DAT: S-bit" description="Bus 1: DAT: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x083B" option_set="XP_Region" title="CCN-504" name="Bus 1: DAT: P-Cnt" description="Bus 1: DAT: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x083C" option_set="XP_Region" title="CCN-504" name="Bus 1: DAT: TknV" description="Bus 1: DAT: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0871" option_set="XP_Region" title="CCN-504" name="Bus 0: DATB: H-bit" description="Bus 0: DATB: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x0872" option_set="XP_Region" title="CCN-504" name="Bus 0: DATB: S-bit" description="Bus 0: DATB: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x0873" option_set="XP_Region" title="CCN-504" name="Bus 0: DATB: P-Cnt" description="Bus 0: DATB: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x0874" option_set="XP_Region" title="CCN-504" name="Bus 0: DATB: TknV" description="Bus 0: DATB: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0879" option_set="XP_Region" title="CCN-504" name="Bus 1: DATB: H-bit" description="Bus 1: DATB: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x087A" option_set="XP_Region" title="CCN-504" name="Bus 1: DATB: S-bit" description="Bus 1: DATB: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x087B" option_set="XP_Region" title="CCN-504" name="Bus 1: DATB: P-Cnt" description="Bus 1: DATB: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x087C" option_set="XP_Region" title="CCN-504" name="Bus 1: DATB: TknV" description="Bus 1: DATB: No TknV, signaled when this XP transmits a valid packet."/>
+    <option_set name="HN-F_Region">
+      <option event_delta="0x200000" name="HN-F 3" description="Fully-coherent Home Node 3"/>
+      <option event_delta="0x210000" name="HN-F 5" description="Fully-coherent Home Node 5"/>
+      <option event_delta="0x220000" name="HN-F 7" description="Fully-coherent Home Node 7"/>
+      <option event_delta="0x230000" name="HN-F 8" description="Fully-coherent Home Node 8"/>
+      <option event_delta="0x240000" name="HN-F 13" description="Fully-coherent Home Node 13"/>
+      <option event_delta="0x250000" name="HN-F 15" description="Fully-coherent Home Node 15"/>
+      <option event_delta="0x260000" name="HN-F 17" description="Fully-coherent Home Node 17"/>
+      <option event_delta="0x270000" name="HN-F 18" description="Fully-coherent Home Node 18"/>
+    </option_set>
+    <event event="0x0401" option_set="HN-F_Region" title="CCN-504" name="Cache Miss" description="Counts the total cache misses. This is the first time lookup result, and is high priority."/>
+    <event event="0x0402" option_set="HN-F_Region" title="CCN-504" name="L3 SF Cache Access" description="Counts the number of cache accesses. This is the first time access, and is high priority."/>
+    <event event="0x0403" option_set="HN-F_Region" title="CCN-504" name="Cache Fill" description="Counts the total allocations in the HN L3 cache, and all cache line allocations to the L3 cache."/>
+    <event event="0x0404" option_set="HN-F_Region" title="CCN-504" name="POCQ Retry" description="Counts the number of requests that have been retried."/>
+    <event event="0x0405" option_set="HN-F_Region" title="CCN-504" name="POCQ Reqs Recvd" description="Counts the number of requests received by HN."/>
+    <event event="0x0406" option_set="HN-F_Region" title="CCN-504" name="SF Hit" description="Counts the number of snoop filter hits."/>
+    <event event="0x0407" option_set="HN-F_Region" title="CCN-504" name="SF Evictions" description="Counts the number of snoop filter evictions. Cache invalidations are initiated."/>
+    <event event="0x0408" option_set="HN-F_Region" title="CCN-504" name="Snoops Sent" description="Counts the number of snoops sent. Does not differentiate between broadcast or directed snoops."/>
+    <event event="0x0409" option_set="HN-F_Region" title="CCN-504" name="Snoops Broadcast" description="Counts the number of snoop broadcasts sent."/>
+    <event event="0x040A" option_set="HN-F_Region" title="CCN-504" name="L3 Eviction" description="Counts the number of L3 evictions."/>
+    <event event="0x040B" option_set="HN-F_Region" title="CCN-504" name="L3 Fill Invalid Way" description="Counts the number of L3 fills to an invalid way."/>
+    <event event="0x040C" option_set="HN-F_Region" title="CCN-504" name="MC Retries" description="Counts the number of transactions retried by the memory controller."/>
+    <event event="0x040D" option_set="HN-F_Region" title="CCN-504" name="MC Reqs" description="Counts the number of requests to the memory controller."/>
+    <event event="0x040E" option_set="HN-F_Region" title="CCN-504" name="QOS HH Retry" description="Counts the number of times a highest-priority QoS class was retried at the HN-F."/>
+    <option_set name="RN-I_Region">
+      <option event_delta="0x800000" name="RN-I 0" description="I/O-coherent Requesting Node 0"/>
+      <option event_delta="0x820000" name="RN-I 2" description="I/O-coherent Requesting Node 2"/>
+      <option event_delta="0x860000" name="RN-I 6" description="I/O-coherent Requesting Node 6"/>
+      <option event_delta="0x8C0000" name="RN-I 12" description="I/O-coherent Requesting Node 12"/>
+      <option event_delta="0x900000" name="RN-I 16" description="I/O-coherent Requesting Node 16"/>
+      <option event_delta="0x940000" name="RN-I 20" description="I/O-coherent Requesting Node 20"/>
+    </option_set>
+    <event event="0x1601" option_set="RN-I_Region" title="CCN-504" name="S0 RDataBeats" description="S0 RDataBeats."/>
+    <event event="0x1602" option_set="RN-I_Region" title="CCN-504" name="S1 RDataBeats" description="S1 RDataBeats."/>
+    <event event="0x1603" option_set="RN-I_Region" title="CCN-504" name="S2 RDataBeats" description="S2 RDataBeats."/>
+    <event event="0x1604" option_set="RN-I_Region" title="CCN-504" name="RXDAT Flits received" description="RXDAT Flits received."/>
+    <event event="0x1605" option_set="RN-I_Region" title="CCN-504" name="TXDAT Flits sent" description="TXDAT Flits sent."/>
+    <event event="0x1606" option_set="RN-I_Region" title="CCN-504" name="Total TXREQ Flits sent" description="Total TXREQ Flits sent."/>
+    <event event="0x1607" option_set="RN-I_Region" title="CCN-504" name="Retried TXREQ Flits sent" description="Retried TXREQ Flits sent."/>
+    <event event="0x1608" option_set="RN-I_Region" title="CCN-504" name="RRT full" description="RRT full."/>
+    <event event="0x1609" option_set="RN-I_Region" title="CCN-504" name="WRT full" description="WRT full."/>
+    <event event="0x160A" option_set="RN-I_Region" title="CCN-504" name="Replayed TXREQ Flits" description="Replayed TXREQ Flits."/>
+    <option_set name="SBAS_Region">
+      <option event_delta="0x810000" name="SBAS 1" description="ACE master to CHI protocol bridge 1"/>
+      <option event_delta="0x890000" name="SBAS 9" description="ACE master to CHI protocol bridge 9"/>
+      <option event_delta="0x8B0000" name="SBAS 11" description="ACE master to CHI protocol bridge 11"/>
+      <option event_delta="0x930000" name="SBAS 19" description="ACE master to CHI protocol bridge 19"/>
+    </option_set>
+    <event event="0x1001" option_set="SBAS_Region" title="CCN-504" name="S0 RDataBeats" description="S0 RDataBeats."/>
+    <event event="0x1004" option_set="SBAS_Region" title="CCN-504" name="RXDAT Flits received" description="RXDAT Flits received."/>
+    <event event="0x1005" option_set="SBAS_Region" title="CCN-504" name="TXDAT Flits sent" description="TXDAT Flits sent."/>
+    <event event="0x1006" option_set="SBAS_Region" title="CCN-504" name="Total TXREQ Flits sent" description="Total TXREQ Flits sent."/>
+    <event event="0x1007" option_set="SBAS_Region" title="CCN-504" name="Retried TXREQ Flits sent" description="Retried TXREQ Flits sent."/>
+    <event event="0x1008" option_set="SBAS_Region" title="CCN-504" name="RRT full" description="RRT full."/>
+    <event event="0x1009" option_set="SBAS_Region" title="CCN-504" name="WRT full" description="WRT full."/>
+    <event event="0x100A" option_set="SBAS_Region" title="CCN-504" name="Replayed TXREQ Flits" description="Replayed TXREQ Flits."/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A15.xml b/tools/gator/daemon/events-Cortex-A15.xml
new file mode 100644
index 00000000000..c0ccc8ac9c6
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A15.xml
@@ -0,0 +1,70 @@
+  <counter_set name="ARMv7_Cortex_A15_cnt" count="6"/>
+  <category name="Cortex-A15" counter_set="ARMv7_Cortex_A15_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A15_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Instruction architecturally executed, condition code check pass, software increment"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exception taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Instruction architecturally executed, condition code check pass, exception return"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction architecturally executed, condition code check pass, write to CONTEXTIDR"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Mispredicted or not predicted branch speculatively executed"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="L1 inst access" description="Level 1 instruction cache access"/>
+    <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache write-back"/>
+    <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+    <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+    <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache write-back"/>
+    <event event="0x19" title="Bus" name="Access" description="Bus access"/>
+    <event event="0x1a" title="Memory" name="Error" description="Local memory error"/>
+    <event event="0x1b" title="Instruction" name="Speculative" description="Instruction speculatively executed"/>
+    <event event="0x1c" title="Memory" name="Translation table" description="Instruction architecturally executed, condition code check pass, write to TTBR"/>
+    <event event="0x1d" title="Bus" name="Cycle" description="Bus cycle"/>
+    <event event="0x40" title="Cache" name="L1 data read" description="Level 1 data cache access, read"/>
+    <event event="0x41" title="Cache" name="L1 data access write" description="Level 1 data cache access, write"/>
+    <event event="0x42" title="Cache" name="L1 data refill read" description="Level 1 data cache refill, read"/>
+    <event event="0x43" title="Cache" name="L1 data refill write" description="Level 1 data cache refill, write"/>
+    <event event="0x46" title="Cache" name="L1 data victim" description="Level 1 data cache write-back, victim"/>
+    <event event="0x47" title="Cache" name="L1 data clean" description="Level 1 data cache write-back, cleaning and coherency"/>
+    <event event="0x48" title="Cache" name="L1 data invalidate" description="Level 1 data cache invalidate"/>
+    <event event="0x4c" title="Cache" name="L1 TLB refill read" description="Level 1 data TLB refill, read"/>
+    <event event="0x4d" title="Cache" name="L1 TLB refill write" description="Level 1 data TLB refill, write"/>
+    <event event="0x50" title="Cache" name="L2 data read" description="Level 2 data cache access, read"/>
+    <event event="0x51" title="Cache" name="L2 data access write" description="Level 2 data cache access, write"/>
+    <event event="0x52" title="Cache" name="L2 data refill read" description="Level 2 data cache refill, read"/>
+    <event event="0x53" title="Cache" name="L2 data refill write" description="Level 2 data cache refill, write"/>
+    <event event="0x56" title="Cache" name="L2 data victim" description="Level 2 data cache write-back, victim"/>
+    <event event="0x57" title="Cache" name="L2 data clean" description="Level 2 data cache write-back, cleaning and coherency"/>
+    <event event="0x58" title="Cache" name="L2 data invalidate" description="Level 2 data cache invalidate"/>
+    <event event="0x60" title="Bus" name="Read" description="Bus access, read"/>
+    <event event="0x61" title="Bus" name="Write" description="Bus access, write"/>
+    <event event="0x62" title="Bus" name="Cacheable normal" description="Bus access, Normal, Cacheable, Shareable"/>
+    <event event="0x63" title="Bus" name="Not normal" description="Bus access, not Normal, Cacheable, Shareable"/>
+    <event event="0x64" title="Bus" name="Access normal" description="Bus access, normal"/>
+    <event event="0x65" title="Bus" name="Peripheral" description="Bus access, peripheral"/>
+    <event event="0x66" title="Memory" name="Read" description="Data memory access, read"/>
+    <event event="0x67" title="Memory" name="Write" description="Data memory access, write"/>
+    <event event="0x68" title="Memory" name="Unaligned Read" description="Unaligned access, read"/>
+    <event event="0x69" title="Memory" name="Unaligned Write" description="Unaligned access, write"/>
+    <event event="0x6a" title="Memory" name="Unaligned" description="Unaligned access"/>
+    <event event="0x6c" title="Intrinsic" name="LDREX" description="Exclusive instruction speculatively executed, LDREX"/>
+    <event event="0x6d" title="Intrinsic" name="STREX pass" description="Exclusive instruction speculatively executed, STREX pass"/>
+    <event event="0x6e" title="Intrinsic" name="STREX fail" description="Exclusive instruction speculatively executed, STREX fail"/>
+    <event event="0x70" title="Instruction" name="Load" description="Instruction speculatively executed, load"/>
+    <event event="0x71" title="Instruction" name="Store" description="Instruction speculatively executed, store"/>
+    <event event="0x72" title="Instruction" name="Load/Store" description="Instruction speculatively executed, load or store"/>
+    <event event="0x73" title="Instruction" name="Integer" description="Instruction speculatively executed, integer data processing"/>
+    <event event="0x74" title="Instruction" name="Advanced SIMD" description="Instruction speculatively executed, Advanced SIMD Extension"/>
+    <event event="0x75" title="Instruction" name="VFP" description="Instruction speculatively executed, Floating-point Extension"/>
+    <event event="0x76" title="Instruction" name="Software change" description="Instruction speculatively executed, software change of the PC"/>
+    <event event="0x78" title="Branch" name="Immediate" description="Branch speculatively executed, immediate branch"/>
+    <event event="0x79" title="Procedure" name="Return" description="Branch speculatively executed, procedure return"/>
+    <event event="0x7a" title="Branch" name="Indirect" description="Branch speculatively executed, indirect branch"/>
+    <event event="0x7c" title="Instruction" name="ISB" description="Barrier speculatively executed, ISB"/>
+    <event event="0x7d" title="Instruction" name="DSB" description="Barrier speculatively executed, DSB"/>
+    <event event="0x7e" title="Instruction" name="DMB" description="Barrier speculatively executed, DMB"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A17.xml b/tools/gator/daemon/events-Cortex-A17.xml
new file mode 100644
index 00000000000..ce1b7810104
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A17.xml
@@ -0,0 +1,85 @@
+  <counter_set name="ARMv7_Cortex_A17_cnt" count="6"/>
+  <category name="Cortex-A17" counter_set="ARMv7_Cortex_A17_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A17_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill at (at least) the lowest level of instruction or unified cache. Includes the speculative linefills in the count."/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill at (at least) the lowest level of TLB. Includes the speculative requests in the count."/>
+    <event event="0x03" title="Cache" name="Data refill" description="Data read or write operation that causes a refill at (at least) the lowest level of data or unified cache. Counts the number of allocations performed in the Data Cache because of a read or a write."/>
+    <event event="0x04" title="Cache" name="Data access" description="Data read or write operation that causes a cache access at (at least) the lowest level of data or unified cache. This includes speculative reads."/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Data read or write operation that causes a TLB refill at (at least) the lowest level of TLB. This does not include micro TLB misses because of PLD, PLI, CP15 Cache operation by MVA and CP15 VA to PA operations."/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exception taken. Counts the number of exceptions architecturally taken."/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Change to ContextID retired. Counts the number of instructions architecturally executed writing into the ContextID register."/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted. Counts the number of mispredicted or not-predicted branches executed. This includes the branches which are flushed because of a previous load/store which aborts late."/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branches or other change in program flow that could have been predicted by the branch prediction resources of the processor. This includes the branches which are flushed because of a previous load/store which aborts late."/>
+    <event event="0x13" title="Memory" name="Memory access" description="Level 1 data memory access"/>
+    <event event="0x14" title="Cache" name="L1 inst access" description="Level 1 instruction cache access"/>
+    <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache eviction"/>
+    <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+    <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+    <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache write-back. Data transfers made as a result of a coherency request from the Level 2 caches to outside of the Level 1 and Level 2 caches are not counted. Write-backs made as a result of CP15 cache maintenance operations are counted."/>
+    <event event="0x19" title="Bus" name="Access" description="Bus accesses. Single transfer bus accesses on either of the ACE read or write channels might increment twice in one cycle if both the read and write channels are active simultaneously.Operations that utilise the bus that do not explicitly transfer data, such as barrier or coherency operations are counted as bus accesses."/>
+    <event event="0x1b" title="Instruction" name="Speculative" description="Instructions speculatively executed"/>
+    <event event="0x1c" title="Memory" name="Translation table" description="Write to translation table register (TTBR0 or TTBR1)"/>
+    <event event="0x1d" title="Bus" name="Cycle" description="Bus cycle"/>
+    <event event="0x40" title="Cache" name="L1 data read" description="Level 1 data cache access - Read"/>
+    <event event="0x41" title="Cache" name="L1 data access write" description="Level 1 data cache access - Write"/>
+    <event event="0x50" title="Cache" name="L2 data read" description="Level 2 data cache access - Read"/>
+    <event event="0x51" title="Cache" name="L2 data access write" description="Level 2 data cache access - Write"/>
+    <event event="0x56" title="Cache" name="L2 data victim" description="Level 2 data cache write-back - Victim"/>
+    <event event="0x57" title="Cache" name="L2 data clean" description="Level 2 data cache write-back - Cleaning and coherency"/>
+    <event event="0x58" title="Cache" name="L2 data invalidate" description="Level 2 data cache invalidate"/>
+    <event event="0x62" title="Bus" name="Access shared" description="Bus access - Normal Cacheable"/>
+    <event event="0x63" title="Bus" name="Access not shared" description="Bus access - Not Cacheable"/>
+    <event event="0x64" title="Bus" name="Access normal" description="Bus access - Normal"/>
+    <event event="0x65" title="Bus" name="Peripheral" description="Bus access - Peripheral"/>
+    <event event="0x66" title="Memory" name="Read" description="Data memory access - Read"/>
+    <event event="0x67" title="Memory" name="Write" description="Data memory access - Write"/>
+    <event event="0x68" title="Memory" name="Unaligned Read" description="Unaligned access - Read"/>
+    <event event="0x69" title="Memory" name="Unaligned Write" description="Unaligned access - Write"/>
+    <event event="0x6a" title="Memory" name="Unaligned" description="Unaligned access"/>
+    <event event="0x6c" title="Intrinsic" name="LDREX" description="Exclusive instruction speculatively executed - LDREX"/>
+    <event event="0x6e" title="Intrinsic" name="STREX fail" description="Exclusive instruction speculatively executed - STREX fail"/>
+    <event event="0x6f" title="Intrinsic" name="STREX" description="Exclusive instruction speculatively executed - STREX"/>
+    <event event="0x70" title="Instruction" name="Load" description="Load instruction speculatively executed"/>
+    <event event="0x71" title="Instruction" name="Store" description="Store instruction speculatively executed"/>
+    <event event="0x72" title="Instruction" name="Load/Store" description="Instruction speculatively executed - Load or store"/>
+    <event event="0x73" title="Instruction" name="Integer" description="Instruction speculatively executed - Data processing"/>
+    <event event="0x74" title="Instruction" name="Advanced SIMD" description="Instruction speculatively executed - Advanced SIMD"/>
+    <event event="0x75" title="Instruction" name="VFP" description="Instruction speculatively executed - VFP"/>
+    <event event="0x76" title="Instruction" name="Software change" description="Instruction speculatively executed - Software change of the PC"/>
+    <event event="0x78" title="Branch" name="Immediate" description="Branch speculatively executed - Immediate branch"/>
+    <event event="0x79" title="Procedure" name="Return" description="Branch speculatively executed - Procedure return"/>
+    <event event="0x7a" title="Branch" name="Indirect" description="Branch speculatively executed - Indirect branch"/>
+    <event event="0x7c" title="Instruction" name="ISB" description="Barrier speculatively executed - ISB"/>
+    <event event="0x7d" title="Instruction" name="DSB" description="Barrier speculatively executed - DSB"/>
+    <event event="0x7e" title="Instruction" name="DMB" description="Barrier speculatively executed - DMB"/>
+    <event event="0x81" title="Exception" name="Undefined" description="Exception taken - Undefined Instruction"/>
+    <event event="0x8a" title="Exception" name="Hypervisor call" description="Exception taken - Hypervisor Call"/>
+    <event event="0xc0" title="Instruction" name="Stalled Linefill" description="Instruction side stalled due to a linefill"/>
+    <event event="0xc1" title="Instruction" name="Stalled Page Table Walk" description="Instruction side stalled due to a translation table walk"/>
+    <event event="0xc2" title="Cache" name="4 Ways Read" description="Number of set of 4 ways read in the instruction cache - Tag RAM"/>
+    <event event="0xc3" title="Cache" name="Ways Read" description="Number of ways read in the instruction cache - Data RAM"/>
+    <event event="0xc4" title="Cache" name="BATC Read" description="Number of ways read in the instruction BTAC RAM"/>
+    <event event="0xca" title="Memory" name="Snoop" description="Data snooped from other processor. This event counts memory-read operations that read data from another processor within the local Cortex-A17 cluster, rather than accessing the L2 cache or issuing an external read. It increments on each transaction, rather than on each beat of data."/>
+    <event event="0xd3" title="Slots" name="Load-Store Unit" description="Duration during which all slots in the Load-Store Unit are busy"/>
+    <event event="0xd8" title="Slots" name="Load-Store Issue Queue" description="Duration during which all slots in the Load-Store Issue queue are busy"/>
+    <event event="0xd9" title="Slots" name="Data Processing Issue Queue" description="Duration during which all slots in the Data Processing issue queue are busy"/>
+    <event event="0xda" title="Slots" name="Data Engine Issue Queue" description="Duration during which all slots in the Data Engine issue queue are busy"/>
+    <event event="0xdb" title="NEON" name="Flush" description="Number of NEON instruction which fail their condition code and lead to a flush of the DE pipe"/>
+    <event event="0xdc" title="Hypervisor" name="Traps" description="Number of Trap to hypervisor"/>
+    <event event="0xde" title="PTM" name="EXTOUT 0" description="PTM EXTOUT 0"/>
+    <event event="0xdf" title="PTM" name="EXTOUT 1" description="PTM EXTOUT 1"/>
+    <event event="0xe0" title="MMU" name="Table Walk" description="Duration during which the MMU handle a translation table walk"/>
+    <event event="0xe1" title="MMU" name="Stage1 Table Walk" description="Duration during which the MMU handle a Stage1 translation table walk"/>
+    <event event="0xe2" title="MMU" name="Stage2 Table Walk" description="Duration during which the MMU handle a Stage2 translation table walk"/>
+    <event event="0xe3" title="MMU" name="LSU Table Walk" description="Duration during which the MMU handle a translation table walk requested by the Load Store Unit"/>
+    <event event="0xe4" title="MMU" name="Instruction Table Walk" description="Duration during which the MMU handle a translation table walk requested by the Instruction side"/>
+    <event event="0xe5" title="MMU" name="Preload Table Walk" description="Duration during which the MMU handle a translation table walk requested by a Preload instruction or Prefetch request"/>
+    <event event="0xe6" title="MMU" name="cp15 Table Walk" description="Duration during which the MMU handle a translation table walk requested by a CP15 operation (maintenance by MVA and VA-to-PA operation)"/>
+    <event event="0xe7" title="Cache" name="L1 PLD TLB refill" description="Level 1 PLD TLB refill"/>
+    <event event="0xe8" title="Cache" name="L1 CP15 TLB refill" description="Level 1 CP15 TLB refill"/>
+    <event event="0xe9" title="Cache" name="L1 TLB flush" description="Level 1 TLB flush"/>
+    <event event="0xea" title="Cache" name="L2 TLB access" description="Level 2 TLB access"/>
+    <event event="0xeb" title="Cache" name="L2 TLB miss" description="Level 2 TLB miss"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A5.xml b/tools/gator/daemon/events-Cortex-A5.xml
new file mode 100644
index 00000000000..9fd48abbd57
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A5.xml
@@ -0,0 +1,36 @@
+  <counter_set name="ARMv7_Cortex_A5_cnt" count="2"/>
+  <category name="Cortex-A5" counter_set="ARMv7_Cortex_A5_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A5_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Software increment. The register is incremented only on writes to the Software Increment Register."/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill at (at least) the lowest level of instruction or unified cache. Includes the speculative linefills in the count."/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill at (at least) the lowest level of TLB. Includes the speculative requests in the count."/>
+    <event event="0x03" title="Cache" name="Data refill" description="Data read or write operation that causes a refill at (at least) the lowest level of data or unified cache. Counts the number of allocations performed in the Data Cache because of a read or a write."/>
+    <event event="0x04" title="Cache" name="Data access" description="Data read or write operation that causes a cache access at (at least) the lowest level of data or unified cache. This includes speculative reads."/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Data read or write operation that causes a TLB refill at (at least) the lowest level of TLB. This does not include micro TLB misses because of PLD, PLI, CP15 Cache operation by MVA and CP15 VA to PA operations."/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Data read architecturally executed. Counts the number of data read instructions accepted by the Load Store Unit. This includes counting the speculative and aborted LDR/LDM, and the reads because of the SWP instructions."/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Data write architecturally executed. Counts the number of data write instructions accepted by the Load Store Unit. This includes counting the speculative and aborted STR/STM, and the writes because of the SWP instructions."/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exception taken. Counts the number of exceptions architecturally taken."/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Change to ContextID retired. Counts the number of instructions architecturally executed writing into the ContextID Register."/>
+    <event event="0x0c" title="Branch" name="PC change" description="Software change of PC"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed (taken or not taken). This includes the branches which are flushed due to a previous load/store which aborts late."/>
+    <event event="0x0e" title="Procedure" name="Return" description="Procedure return (other than exception returns) architecturally executed"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned load-store"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted/not predicted. Counts the number of mispredicted or not-predicted branches executed. This includes the branches which are flushed because of a previous load/store which aborts late."/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branches or other change in program flow that could have been predicted by the branch prediction resources of the processor. This includes the branches which are flushed because of a previous load/store which aborts late."/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="Instruction access" description="Instruction Cache access"/>
+    <event event="0x15" title="Cache" name="Data eviction" description="Data cache eviction"/>
+    <event event="0x86" title="Interrupts" name="IRQ" description="IRQ exception taken"/>
+    <event event="0x87" title="Interrupts" name="FIQ" description="FIQ exception taken"/>
+    <event event="0xc0" title="Memory" name="External request" description="External memory request"/>
+    <event event="0xc1" title="Memory" name="Non-cacheable ext req" description="Non-cacheable external memory request"/>
+    <event event="0xc2" title="Cache" name="Linefill" description="Linefill because of prefetch"/>
+    <event event="0xc3" title="Cache" name="Linefill dropped" description="Prefetch linefill dropped"/>
+    <event event="0xc4" title="Cache" name="Allocate mode enter" description="Entering read allocate mode"/>
+    <event event="0xc5" title="Cache" name="Allocate mode" description="Read allocate mode"/>
+    <event event="0xc7" title="ETM" name="ETM Ext Out[0]" description="ETM Ext Out[0]"/>
+    <event event="0xc8" title="ETM" name="ETM Ext Out[1]" description="ETM Ext Out[1]"/>
+    <event event="0xc9" title="Instruction" name="Pipeline stall" description="Data Write operation that stalls the pipeline because the store buffer is full"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A53.xml b/tools/gator/daemon/events-Cortex-A53.xml
new file mode 100644
index 00000000000..c15cbd8cbad
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A53.xml
@@ -0,0 +1,64 @@
+  <counter_set name="ARMv8_Cortex_A53_cnt" count="6"/>
+  <category name="Cortex-A53" counter_set="ARMv8_Cortex_A53_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv8_Cortex_A53_ccnt" event="0x11" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Software increment. The register is incremented only on writes to the Software Increment Register."/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Instruction" name="Data Read" description="Instruction architecturally executed, condition check pass - load"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Instruction architecturally executed, condition check pass - store"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exception taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Change to Context ID retired"/>
+    <event event="0x0c" title="Branch" name="PC change" description="Instruction architecturally executed, condition check pass, software change of the PC"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Instruction architecturally executed, immediate branch"/>
+    <event event="0x0e" title="Procedure" name="Return" description="Instruction architecturally executed, condition code check pass, procedure return"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Instruction architecturally executed, condition check pass, unaligned load or store"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Mispredicted or not predicted branch speculatively executed"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="L1 inst access" description="L1 Instruction cache access"/>
+    <event event="0x15" title="Cache" name="L1 data write" description="L1 Data cache Write-Back"/>
+    <event event="0x16" title="Cache" name="L2 data access" description="L2 Data cache access"/>
+    <event event="0x17" title="Cache" name="L2 data refill" description="L2 Data cache refill"/>
+    <event event="0x18" title="Cache" name="L2 data write" description="L2 Data cache Write-Back"/>
+    <event event="0x19" title="Bus" name="Access" description="Bus access"/>
+    <event event="0x1a" title="Memory" name="Error" description="Local memory error"/>
+    <event event="0x1d" title="Bus" name="Cycle" description="Bus cycle"/>
+    <event event="0x1e" title="Counter chain" name="Odd Performance" description="Odd performance counter chain mode"/>
+    <event event="0x60" title="Bus" name="Read" description="Bus access - Read"/>
+    <event event="0x61" title="Bus" name="Write" description="Bus access - Write"/>
+    <event event="0x7a" title="Branch" name="Indirect" description="Branch speculatively executed - Indirect branch"/>
+    <event event="0x86" title="Interrupts" name="IRQ" description="Exception taken, IRQ"/>
+    <event event="0x87" title="Interrupts" name="FIQ" description="Exception taken, FIQ"/>
+    <event event="0xc0" title="Memory" name="External request" description="External memory request"/>
+    <event event="0xc1" title="Memory" name="Non-cacheable ext req" description="Non-cacheable external memory request"/>
+    <event event="0xc2" title="Cache" name="Linefill" description="Linefill because of prefetch"/>
+    <event event="0xc3" title="Cache" name="Throttle" description="Instruction Cache Throttle occurred"/>
+    <event event="0xc4" title="Cache" name="Allocate mode enter" description="Entering read allocate mode"/>
+    <event event="0xc5" title="Cache" name="Allocate mode" description="Read allocate mode"/>
+    <event event="0xc6" title="Pre-decode" name="error" description="Pre-decode error"/>
+    <event event="0xc7" title="Memory" name="Write stall" description="Data Write operation that stalls the pipeline because the store buffer is full"/>
+    <event event="0xc8" title="Memory" name="Snoop" description="SCU Snooped data from another CPU for this CPU"/>
+    <event event="0xc9" title="Branch" name="Taken" description="Conditional branch executed"/>
+    <!--
+    <event event="0xca" title="Branch" name="Mispredicted a" description="Indirect branch mispredicted"/>
+    <event event="0xcb" title="Branch" name="Mispredicted b" description="Indirect branch mispredicted because of address miscompare"/>
+    <event event="0xcc" title="Branch" name="Mispredicted c" description="Conditional branch mispredicted"/>
+    -->
+    <event event="0xd0" title="Cache" name="L1 inst error" description="L1 Instruction Cache (data or tag) memory error"/>
+    <event event="0xd1" title="Cache" name="L1 data error" description="L1 Data Cache (data, tag or dirty) memory error, correctable or non-correctable"/>
+    <event event="0xd2" title="Cache" name="TLB error" description="TLB memory error"/>
+    <event event="0xe0" title="Stall" name="DPU IP empty" description="Attributable Performance Impact Event. Counts every cycle that the DPU IQ is empty and that is not because of a recent micro-TLB miss, instruction cache miss or pre-decode error."/>
+    <event event="0xe1" title="Stall" name="Cache miss" description="Attributable Performance Impact Event. Counts every cycle the DPU IQ is empty and there is an instruction cache miss being processed."/>
+    <event event="0xe2" title="Stall" name="TLB miss" description="Attributable Performance Impact Event. Counts every cycle the DPU IQ is empty and there is an instruction micro-TLB miss being processed."/>
+    <event event="0xe3" title="Stall" name="Pre-decode error" description="Attributable Performance Impact Event. Counts every cycle the DPU IQ is empty and there is a pre-decode error being processed."/>
+    <event event="0xe4" title="Stall" name="Interlock other" description="Attributable Performance Impact Event. Counts every cycle there is an interlock that is not because of an Advanced SIMD or Floating-point instruction, and not because of a load/store instruction waiting for data to calculate the address in the AGU. Stall cycles because of a stall in Wr, typically awaiting load data, are excluded."/>
+    <event event="0xe5" title="Stall" name="Interlock address" description="Attributable Performance Impact Event. Counts every cycle there is an interlock that is because of a load/store instruction waiting for data to calculate the address in the AGU. Stall cycles because of a stall in Wr, typically awaiting load data, are excluded."/>
+    <event event="0xe6" title="Stall" name="Interlock SIMD/FPU" description="Attributable Performance Impact Event. Counts every cycle there is an interlock that is because of an Advanced SIMD or Floating-point instruction. Stall cycles because of a stall in the Wr stage, typically awaiting load data, are excluded."/>
+    <event event="0xe7" title="Stall" name="Load miss" description="Attributable Performance Impact Event. Counts every cycle there is a stall in the Wr stage because of a load miss"/>
+    <event event="0xe8" title="Stall" name="Store" description="Attributable Performance Impact Event. Counts every cycle there is a stall in the Wr stage because of a store."/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A57.xml b/tools/gator/daemon/events-Cortex-A57.xml
new file mode 100644
index 00000000000..d1e97c36bd4
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A57.xml
@@ -0,0 +1,87 @@
+  <counter_set name="ARMv8_Cortex_A57_cnt" count="6"/>
+  <category name="Cortex-A57" counter_set="ARMv8_Cortex_A57_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv8_Cortex_A57_ccnt" event="0x11" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exception taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Instruction architecturally executed (condition check pass) - Exception return"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction architecturally executed (condition check pass) - Write to CONTEXTIDR"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Mispredicted or not predicted branch speculatively executed"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="L1 inst access" description="Level 1 instruction cache access"/>
+    <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache Write-Back"/>
+    <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+    <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+    <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache Write-Back"/>
+    <event event="0x19" title="Bus" name="Access" description="Bus access"/>
+    <event event="0x1a" title="Memory" name="Error" description="Local memory error"/>
+    <event event="0x1b" title="Instruction" name="Speculative" description="Operation speculatively executed"/>
+    <event event="0x1c" title="Memory" name="Translation table" description="Instruction architecturally executed (condition check pass) - Write to translation table base"/>
+    <event event="0x1d" title="Bus" name="Cycle" description="Bus cycle"/>
+    <event event="0x1e" title="Counter chain" name="Odd Performance" description="Odd performance counter chain mode"/>
+    <event event="0x40" title="Cache" name="L1 data read" description="Level 1 data cache access - Read"/>
+    <event event="0x41" title="Cache" name="L1 data access write" description="Level 1 data cache access - Write"/>
+    <event event="0x42" title="Cache" name="L1 data refill read" description="Level 1 data cache refill - Read"/>
+    <event event="0x43" title="Cache" name="L1 data refill write" description="Level 1 data cache refill - Write"/>
+    <event event="0x46" title="Cache" name="L1 data victim" description="Level 1 data cache Write-back - Victim"/>
+    <event event="0x47" title="Cache" name="L1 data clean" description="Level 1 data cache Write-back - Cleaning and coherency"/>
+    <event event="0x48" title="Cache" name="L1 data invalidate" description="Level 1 data cache invalidate"/>
+    <event event="0x4c" title="Cache" name="L1 TLB refill read" description="Level 1 data TLB refill - Read"/>
+    <event event="0x4d" title="Cache" name="L1 TLB refill write" description="Level 1 data TLB refill - Write"/>
+    <event event="0x50" title="Cache" name="L2 data read" description="Level 2 data cache access - Read"/>
+    <event event="0x51" title="Cache" name="L2 data access write" description="Level 2 data cache access - Write"/>
+    <event event="0x52" title="Cache" name="L2 data refill read" description="Level 2 data cache refill - Read"/>
+    <event event="0x53" title="Cache" name="L2 data refill write" description="Level 2 data cache refill - Write"/>
+    <event event="0x56" title="Cache" name="L2 data victim" description="Level 2 data cache Write-back - Victim"/>
+    <event event="0x57" title="Cache" name="L2 data clean" description="Level 2 data cache Write-back - Cleaning and coherency"/>
+    <event event="0x58" title="Cache" name="L2 data invalidate" description="Level 2 data cache invalidate"/>
+    <event event="0x60" title="Bus" name="Read" description="Bus access - Read"/>
+    <event event="0x61" title="Bus" name="Write" description="Bus access - Write"/>
+    <event event="0x62" title="Bus" name="Access shared" description="Bus access - Normal"/>
+    <event event="0x63" title="Bus" name="Access not shared" description="Bus access - Not normal"/>
+    <event event="0x64" title="Bus" name="Access normal" description="Bus access - Normal"/>
+    <event event="0x65" title="Bus" name="Peripheral" description="Bus access - Peripheral"/>
+    <event event="0x66" title="Memory" name="Read" description="Data memory access - Read"/>
+    <event event="0x67" title="Memory" name="Write" description="Data memory access - Write"/>
+    <event event="0x68" title="Memory" name="Unaligned Read" description="Unaligned access - Read"/>
+    <event event="0x69" title="Memory" name="Unaligned Write" description="Unaligned access - Write"/>
+    <event event="0x6a" title="Memory" name="Unaligned" description="Unaligned access"/>
+    <event event="0x6c" title="Intrinsic" name="LDREX" description="Exclusive operation speculatively executed - LDREX"/>
+    <event event="0x6d" title="Intrinsic" name="STREX pass" description="Exclusive instruction speculatively executed - STREX pass"/>
+    <event event="0x6e" title="Intrinsic" name="STREX fail" description="Exclusive operation speculatively executed - STREX fail"/>
+    <event event="0x70" title="Instruction" name="Load" description="Operation speculatively executed - Load"/>
+    <event event="0x71" title="Instruction" name="Store" description="Operation speculatively executed - Store"/>
+    <event event="0x72" title="Instruction" name="Load/Store" description="Operation speculatively executed - Load or store"/>
+    <event event="0x73" title="Instruction" name="Integer" description="Operation speculatively executed - Integer data processing"/>
+    <event event="0x74" title="Instruction" name="Advanced SIMD" description="Operation speculatively executed - Advanced SIMD"/>
+    <event event="0x75" title="Instruction" name="VFP" description="Operation speculatively executed - VFP"/>
+    <event event="0x76" title="Instruction" name="Software change" description="Operation speculatively executed - Software change of the PC"/>
+    <event event="0x77" title="Instruction" name="Crypto" description="Operation speculatively executed, crypto data processing"/>
+    <event event="0x78" title="Branch" name="Immediate" description="Branch speculatively executed - Immediate branch"/>
+    <event event="0x79" title="Procedure" name="Return" description="Branch speculatively executed - Procedure return"/>
+    <event event="0x7a" title="Branch" name="Indirect" description="Branch speculatively executed - Indirect branch"/>
+    <event event="0x7c" title="Instruction" name="ISB" description="Barrier speculatively executed - ISB"/>
+    <event event="0x7d" title="Instruction" name="DSB" description="Barrier speculatively executed - DSB"/>
+    <event event="0x7e" title="Instruction" name="DMB" description="Barrier speculatively executed - DMB"/>
+    <event event="0x81" title="Exception" name="Undefined" description="Exception taken, other synchronous"/>
+    <event event="0x82" title="Exception" name="Supervisor" description="Exception taken, Supervisor Call"/>
+    <event event="0x83" title="Exception" name="Instruction abort" description="Exception taken, Instruction Abort"/>
+    <event event="0x84" title="Exception" name="Data abort" description="Exception taken, Data Abort or SError"/>
+    <event event="0x86" title="Interrupts" name="IRQ" description="Exception taken, IRQ"/>
+    <event event="0x87" title="Interrupts" name="FIQ" description="Exception taken, FIQ"/>
+    <event event="0x88" title="Exception" name="Secure monitor call" description="Exception taken, Secure Monitor Call"/>
+    <event event="0x8a" title="Exception" name="Hypervisor call" description="Exception taken, Hypervisor Call"/>
+    <event event="0x8b" title="Exception" name="Instruction abort non-local" description="Exception taken, Instruction Abort not taken locally"/>
+    <event event="0x8c" title="Exception" name="Data abort non-local" description="Exception taken, Data Abort, or SError not taken locally"/>
+    <event event="0x8d" title="Exception" name="Other non-local" description="Exception taken - Other traps not taken locally"/>
+    <event event="0x8e" title="Exception" name="IRQ non-local" description="Exception taken, IRQ not taken locally"/>
+    <event event="0x8f" title="Exception" name="FIQ non-local" description="Exception taken, FIQ not taken locally"/>
+    <event event="0x90" title="Release Consistency" name="Load" description="Release consistency instruction speculatively executed - Load-Acquire"/>
+    <event event="0x91" title="Release Consistency" name="Store" description="Release consistency instruction speculatively executed - Store-Release"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A7.xml b/tools/gator/daemon/events-Cortex-A7.xml
new file mode 100644
index 00000000000..22fa9b7a414
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A7.xml
@@ -0,0 +1,44 @@
+  <counter_set name="ARMv7_Cortex_A7_cnt" count="4"/>
+  <category name="Cortex-A7" counter_set="ARMv7_Cortex_A7_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A7_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Software increment. The register is incremented only on writes to the Software Increment Register."/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill at (at least) the lowest level of instruction or unified cache. Includes the speculative linefills in the count."/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill at (at least) the lowest level of TLB. Includes the speculative requests in the count."/>
+    <event event="0x03" title="Cache" name="Data refill" description="Data read or write operation that causes a refill at (at least) the lowest level of data or unified cache. Counts the number of allocations performed in the Data Cache because of a read or a write."/>
+    <event event="0x04" title="Cache" name="Data access" description="Data read or write operation that causes a cache access at (at least) the lowest level of data or unified cache. This includes speculative reads."/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Data read or write operation that causes a TLB refill at (at least) the lowest level of TLB. This does not include micro TLB misses because of PLD, PLI, CP15 Cache operation by MVA and CP15 VA to PA operations."/>
+    <event event="0x06" title="Instruction" name="Memory Read" description="Data read architecturally executed. Counts the number of data read instructions accepted by the Load Store Unit. This includes counting the speculative and aborted LDR/LDM, and the reads because of the SWP instructions."/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Data write architecturally executed. Counts the number of data write instructions accepted by the Load Store Unit. This includes counting the speculative and aborted STR/STM, and the writes because of the SWP instructions."/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exception taken. Counts the number of exceptions architecturally taken."/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Change to ContextID retired. Counts the number of instructions architecturally executed writing into the ContextID Register."/>
+    <event event="0x0c" title="Branch" name="PC change" description="Software change of PC"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed (taken or not taken). This includes the branches which are flushed due to a previous load/store which aborts late."/>
+    <event event="0x0e" title="Procedure" name="Return" description="Procedure return (other than exception returns) architecturally executed"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned load-store"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted/not predicted. Counts the number of mispredicted or not-predicted branches executed. This includes the branches which are flushed because of a previous load/store which aborts late."/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branches or other change in program flow that could have been predicted by the branch prediction resources of the processor. This includes the branches which are flushed because of a previous load/store which aborts late."/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="L1 inst access" description="Instruction Cache access"/>
+    <event event="0x15" title="Cache" name="L1 data eviction" description="Data cache eviction"/>
+    <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+    <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+    <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache write-back. Data transfers made as a result of a coherency request from the Level 2 caches to outside of the Level 1 and Level 2 caches are not counted. Write-backs made as a result of CP15 cache maintenance operations are counted."/>
+    <event event="0x19" title="Bus" name="Access" description="Bus accesses. Single transfer bus accesses on either of the ACE read or write channels might increment twice in one cycle if both the read and write channels are active simultaneously. Operations that utilise the bus that do not explicitly transfer data, such as barrier or coherency operations are counted as bus accesses."/>
+    <event event="0x1d" title="Bus" name="Cycle" description="Bus cycle"/>
+    <event event="0x60" title="Bus" name="Read" description="Bus access, read"/>
+    <event event="0x61" title="Bus" name="Write" description="Bus access, write"/>
+    <event event="0x86" title="Exception" name="IRQ" description="IRQ exception taken"/>
+    <event event="0x87" title="Exception" name="FIQ" description="FIQ exception taken"/>
+    <event event="0xc0" title="Memory" name="External request" description="External memory request"/>
+    <event event="0xc1" title="Memory" name="Non-cacheable ext req" description="Non-cacheable external memory request"/>
+    <event event="0xc2" title="Cache" name="Linefill" description="Linefill because of prefetch"/>
+    <event event="0xc3" title="Cache" name="Linefill dropped" description="Prefetch linefill dropped"/>
+    <event event="0xc4" title="Cache" name="Allocate mode enter" description="Entering read allocate mode"/>
+    <event event="0xc5" title="Cache" name="Allocate mode" description="Read allocate mode"/>
+    <event event="0xc7" title="ETM" name="ETM Ext Out[0]" description="ETM Ext Out[0]"/>
+    <event event="0xc8" title="ETM" name="ETM Ext Out[1]" description="ETM Ext Out[1]"/>
+    <event event="0xc9" title="Instruction" name="Pipeline stall" description="Data Write operation that stalls the pipeline because the store buffer is full"/>
+    <event event="0xca" title="Memory" name="Snoop" description="Data snooped from other processor. This event counts memory-read operations that read data from another processor within the local Cortex-A7 cluster, rather than accessing the L2 cache or issuing an external read. It increments on each transaction, rather than on each beat of data."/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A72.xml b/tools/gator/daemon/events-Cortex-A72.xml
new file mode 100644
index 00000000000..683d0ae84ce
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A72.xml
@@ -0,0 +1,87 @@
+  <counter_set name="ARMv8_Cortex_A72_cnt" count="6"/>
+  <category name="Cortex-A72" counter_set="ARMv8_Cortex_A72_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv8_Cortex_A72_ccnt" event="0x11" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="L1 inst access" description="Level 1 instruction cache access"/>
+    <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache Write-Back"/>
+    <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+    <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+    <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache Write-Back"/>
+    <event event="0x19" title="Bus" name="Access" description="Bus access"/>
+    <event event="0x1A" title="Memory" name="Error" description="Local memory error"/>
+    <event event="0x1B" title="Instruction" name="Speculative" description="Operation speculatively executed"/>
+    <event event="0x1C" title="Memory" name="Translation table" description="Instruction architecturally executed (condition check pass) - Write to translation table base"/>
+    <event event="0x1D" title="Bus" name="Cycle" description="Bus cycle"/>
+    <event event="0x1E" title="Counter chain" name="Odd Performance" description="Odd performance counter chain mode"/>
+    <event event="0x40" title="Cache" name="L1 data read" description="Level 1 data cache access - Read"/>
+    <event event="0x41" title="Cache" name="L1 data access write" description="Level 1 data cache access - Write"/>
+    <event event="0x42" title="Cache" name="L1 data refill read" description="Level 1 data cache refill - Read"/>
+    <event event="0x43" title="Cache" name="L1 data refill write" description="Level 1 data cache refill - Write"/>
+    <event event="0x46" title="Cache" name="L1 data victim" description="Level 1 data cache Write-back - Victim"/>
+    <event event="0x47" title="Cache" name="L1 data clean" description="Level 1 data cache Write-back - Cleaning and coherency"/>
+    <event event="0x48" title="Cache" name="L1 data invalidate" description="Level 1 data cache invalidate"/>
+    <event event="0x4C" title="Cache" name="L1 TLB refill read" description="Level 1 data TLB refill - Read"/>
+    <event event="0x4D" title="Cache" name="L1 TLB refill write" description="Level 1 data TLB refill - Write"/>
+    <event event="0x50" title="Cache" name="L2 data read" description="Level 2 data cache access - Read"/>
+    <event event="0x51" title="Cache" name="L2 data access write" description="Level 2 data cache access - Write"/>
+    <event event="0x52" title="Cache" name="L2 data refill read" description="Level 2 data cache refill - Read"/>
+    <event event="0x53" title="Cache" name="L2 data refill write" description="Level 2 data cache refill - Write"/>
+    <event event="0x56" title="Cache" name="L2 data victim" description="Level 2 data cache Write-back - Victim"/>
+    <event event="0x57" title="Cache" name="L2 data clean" description="Level 2 data cache Write-back - Cleaning and coherency"/>
+    <event event="0x58" title="Cache" name="L2 data invalidate" description="Level 2 data cache invalidate"/>
+    <event event="0x60" title="Bus" name="Read" description="Bus access - Read"/>
+    <event event="0x61" title="Bus" name="Write" description="Bus access - Write"/>
+    <event event="0x62" title="Bus" name="Access shared" description="Bus access - Normal"/>
+    <event event="0x63" title="Bus" name="Access not shared" description="Bus access - Not normal"/>
+    <event event="0x64" title="Bus" name="Access normal" description="Bus access - Normal"/>
+    <event event="0x65" title="Bus" name="Peripheral" description="Bus access - Peripheral"/>
+    <event event="0x66" title="Memory" name="Read" description="Data memory access - Read"/>
+    <event event="0x67" title="Memory" name="Write" description="Data memory access - Write"/>
+    <event event="0x68" title="Memory" name="Unaligned Read" description="Unaligned access - Read"/>
+    <event event="0x69" title="Memory" name="Unaligned Write" description="Unaligned access - Write"/>
+    <event event="0x6A" title="Memory" name="Unaligned" description="Unaligned access"/>
+    <event event="0x6C" title="Intrinsic" name="LDREX" description="Exclusive operation speculatively executed - LDREX"/>
+    <event event="0x6D" title="Intrinsic" name="STREX pass" description="Exclusive instruction speculatively executed - STREX pass"/>
+    <event event="0x6E" title="Intrinsic" name="STREX fail" description="Exclusive operation speculatively executed - STREX fail"/>
+    <event event="0x70" title="Instruction" name="Load" description="Operation speculatively executed - Load"/>
+    <event event="0x71" title="Instruction" name="Store" description="Operation speculatively executed - Store"/>
+    <event event="0x72" title="Instruction" name="Load/Store" description="Operation speculatively executed - Load or store"/>
+    <event event="0x73" title="Instruction" name="Integer" description="Operation speculatively executed - Integer data processing"/>
+    <event event="0x74" title="Instruction" name="Advanced SIMD" description="Operation speculatively executed - Advanced SIMD"/>
+    <event event="0x75" title="Instruction" name="VFP" description="Operation speculatively executed - VFP"/>
+    <event event="0x76" title="Instruction" name="Software change" description="Operation speculatively executed - Software change of the PC"/>
+    <event event="0x77" title="Instruction" name="Crypto" description="Operation speculatively executed, crypto data processing"/>
+    <event event="0x78" title="Branch" name="Immediate" description="Branch speculatively executed - Immediate branch"/>
+    <event event="0x79" title="Procedure" name="Return" description="Branch speculatively executed - Procedure return"/>
+    <event event="0x7A" title="Branch" name="Indirect" description="Branch speculatively executed - Indirect branch"/>
+    <event event="0x7C" title="Instruction" name="ISB" description="Barrier speculatively executed - ISB"/>
+    <event event="0x7D" title="Instruction" name="DSB" description="Barrier speculatively executed - DSB"/>
+    <event event="0x7E" title="Instruction" name="DMB" description="Barrier speculatively executed - DMB"/>
+    <event event="0x81" title="Exception" name="Undefined" description="Exception taken, other synchronous"/>
+    <event event="0x82" title="Exception" name="Supervisor" description="Exception taken, Supervisor Call"/>
+    <event event="0x83" title="Exception" name="Instruction abort" description="Exception taken, Instruction Abort"/>
+    <event event="0x84" title="Exception" name="Data abort" description="Exception taken, Data Abort or SError"/>
+    <event event="0x86" title="Interrupts" name="IRQ" description="Exception taken, IRQ"/>
+    <event event="0x87" title="Interrupts" name="FIQ" description="Exception taken, FIQ"/>
+    <event event="0x88" title="Exception" name="Secure monitor call" description="Exception taken, Secure Monitor Call"/>
+    <event event="0x8A" title="Exception" name="Hypervisor call" description="Exception taken, Hypervisor Call"/>
+    <event event="0x8B" title="Exception" name="Instruction abort non-local" description="Exception taken, Instruction Abort not taken locally"/>
+    <event event="0x8C" title="Exception" name="Data abort non-local" description="Exception taken, Data Abort or SError not taken locally"/>
+    <event event="0x8D" title="Exception" name="Other non-local" description="Exception taken - Other traps not taken locally"/>
+    <event event="0x8E" title="Exception" name="IRQ non-local" description="Exception taken, IRQ not taken locally"/>
+    <event event="0x8F" title="Exception" name="FIQ non-local" description="Exception taken, FIQ not taken locally"/>
+    <event event="0x90" title="Release Consistency" name="Load" description="Release consistency instruction speculatively executed - Load Acquire"/>
+    <event event="0x91" title="Release Consistency" name="Store" description="Release consistency instruction speculatively executed - Store Release"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A8.xml b/tools/gator/daemon/events-Cortex-A8.xml
new file mode 100644
index 00000000000..7056efd35fe
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A8.xml
@@ -0,0 +1,52 @@
+  <counter_set name="ARMv7_Cortex_A8_cnt" count="4"/>
+  <category name="Cortex-A8" counter_set="ARMv7_Cortex_A8_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A8_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill at the lowest level of instruction or unified cache. Each instruction fetch from normal cacheable memory that causes a refill from outside of the cache is counted. Accesses that do not cause a new cache refill, but are satisfied from refilling data of a previous miss are not counted. Where instruction fetches consist of multiple instructions, these accesses count as single events. CP15 cache maintenance operations do not count as events. This counter increments for speculative instruction fetches and for fetches of instructions that reach execution."/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill at the lowest level of TLB. Each instruction fetch that causes a translation table walk or an access to another level of TLB caching is counted. CP15 TLB maintenance operations do not count as events. This counter increments for speculative instruction fetches and for fetches of instructions that reach execution."/>
+    <event event="0x03" title="Cache" name="Data refill" description="Data read or write operation that causes a refill at the lowest level of data or unified cache. Each data read from or write to normal cacheable memory that causes a refill from outside of the cache is counted. Accesses that do not cause a new cache refill, but are satisfied from refilling data of a previous miss are not counted. Each access to a cache line to normal cacheable memory that causes a new linefill is counted, including the multiple transaction of instructions such as LDM or STM, PUSH and POP. Write-through writes that hit in the cache do not cause a linefill and so are not counted. CP15 cache maintenance operations do not count as events. This counter increments for speculative data accesses and for data accesses that are explicitly made by instructions."/>
+    <event event="0x04" title="Cache" name="Data access" description="Data read or write operation that causes a cache access at the lowest level of data or unified cache. Each access to a cache line to normal cacheable memory is counted including the multiple transaction of instructions such as LDM or STM. CP15 cache maintenance operations do not count as events. This counter increments for speculative data accesses and for data accesses that are explicitly made by instructions."/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Data read or write operation that causes a TLB refill at the lowest level of TLB. Each data read or write operation that causes a translation table walk or an access to another level of TLB caching is counted. CP15 TLB maintenance operations do not count as events. This counter increments for speculative data accesses and for data accesses that are explicitly made by instructions."/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Data read architecturally executed. This counter increments for every instruction that explicitly read data, including SWP. This counter only increments for instructions that are unconditional or that pass their condition codes."/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Data write architecturally executed. The counter increments for every instruction that explicitly wrote data, including SWP. This counter only increments for instructions that are unconditional or that pass their condition codes."/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed. This counter counts for all instructions, including conditional instructions that fail their condition codes."/>
+    <event event="0x09" title="Exception" name="Taken" description="Exception taken. This counts for each exception taken."/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed. This counter only increments for instructions that are unconditional or that pass their condition codes."/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the Context ID Register architecturally executed. This counter only increments for instructions that are unconditional or that pass their condition codes."/>
+    <event event="0x0c" title="Branch" name="PC change" description="Software change of PC, except by an exception, architecturally executed. This counter only increments for instructions that are unconditional or that pass their condition codes."/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed, taken or not taken. This includes B{L}, BLX, CB{N}Z, HB{L}, and HBLP. This counter counts for all immediate branch instructions that are architecturally executed, including conditional instructions that fail their condition codes."/>
+    <event event="0x0e" title="Procedure" name="Return" description="Procedure return, other than exception returns, architecturally executed. This counter only increments for instructions that are unconditional or that pass their condition codes."/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed. This counts each instruction that is an access to an unaligned address. This counter only increments for instructions that are unconditional or that pass their condition codes."/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted. This counts for every pipeline flush because of a misprediction from the program flow prediction resources."/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branches or other change in the program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x40" title="Cache" name="Write buffer full" description="Any write buffer full cycle"/>
+    <event event="0x41" title="Cache" name="L2 store" description="Any store that is merged in the L2 memory system"/>
+    <event event="0x42" title="Cache" name="Bufferable transaction" description="Any bufferable store transaction from load/store to L2 cache, excluding eviction or cast out data"/>
+    <event event="0x43" title="Cache" name="L2 access" description="Any accesses to the L2 cache"/>
+    <event event="0x44" title="Cache" name="L2 miss" description="Any cacheable miss in the L2 cache"/>
+    <event event="0x45" title="AXI" name="Read" description="The number of AXI read data transfers"/>
+    <event event="0x46" title="AXI" name="Write" description="The number of AXI write data transfers"/>
+    <event event="0x47" title="Memory" name="Replay event" description="Any replay event in the memory system"/>
+    <event event="0x48" title="Memory" name="Unaligned access replay" description="Any unaligned memory access that results in a replay"/>
+    <event event="0x49" title="Cache" name="L1 data hash miss" description="Any L1 data memory access that misses in the cache as a result of the hashing algorithm. The cases covered are: hash hit and physical address miss, hash hit and physical address hit in another way and hash miss and physical address hit."/>
+    <event event="0x4a" title="Cache" name="L1 inst hash miss" description="Any L1 instruction memory access that misses in the cache as a result of the hashing algorithm. The cases covered are: hash hit and physical address miss, hash hit and physical address hit in another way and hash miss and physical address hit."/>
+    <event event="0x4b" title="Cache" name="L1 page coloring" description="Any L1 data memory access in which a page coloring alias occurs. alias = virtual address [12] ! = physical address [12]. This behavior results in a data memory eviction or cast out."/>
+    <event event="0x4c" title="NEON" name="L1 cache hit" description="Any NEON access that hits in the L1 data cache"/>
+    <event event="0x4d" title="NEON" name="L1 cache access" description="Any NEON cacheable data accesses for L1 data cache"/>
+    <event event="0x4e" title="NEON" name="L2 cache access" description="Any L2 cache accesses as a result of a NEON memory access"/>
+    <event event="0x4f" title="NEON" name="L2 cache hit" description="Any NEON hit in the L2 cache"/>
+    <event event="0x50" title="Cache" name="L1 inst access" description="Any L1 instruction cache access, excluding CP15 cache accesses"/>
+    <event event="0x51" title="Branch" name="Return stack misprediction" description="Any return stack misprediction because of incorrect target address for a taken return stack pop"/>
+    <event event="0x52" title="Branch" name="Direction misprediction" description="Two forms of branch direction misprediction: branch predicted taken, but was not taken and branch predicted not taken, but was taken"/>
+    <event event="0x53" title="Branch" name="Taken prediction" description="Any predictable branch that is predicted to be taken"/>
+    <event event="0x54" title="Branch" name="Executed and taken prediction" description="Any predictable branch that is executed and taken"/>
+    <event event="0x55" title="Core" name="Operations issued" description="Number of operations issued, where an operation is either: an instruction or one operation in a sequence of operations that make up a multi-cycle instruction"/>
+    <event event="0x56" title="Core" name="No issue cycles" description="Increment for every cycle that no instructions are available for issue"/>
+    <event event="0x57" title="Core" name="Issue cycles" description="For every cycle, this event counts the number of instructions issued in that cycle. Multi-cycle instructions are only counted once."/>
+    <event event="0x58" title="NEON" name="MRC data wait" description="Number of cycles the processor stalls waiting on MRC data from NEON"/>
+    <event event="0x59" title="NEON" name="Full queue" description="Number of cycles that the processor stalls as a result of a full NEON instruction queue or NEON load queue"/>
+    <event event="0x5a" title="NEON" name="Idle" description="Number of cycles that NEON and integer processors are both not idle"/>
+    <event event="0x70" title="External" name="PMUEXTIN[0]" description="Counts any event from external input source PMUEXTIN[0]"/>
+    <event event="0x71" title="External" name="PMUEXTIN[1]" description="Counts any event from external input source PMUEXTIN[1]"/>
+    <event event="0x72" title="External" name="PMUEXTIN[0,1]" description="Counts any event from both external input sources PMUEXTIN[0] and PMUEXTIN[1]"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A9.xml b/tools/gator/daemon/events-Cortex-A9.xml
new file mode 100644
index 00000000000..e17c03d7a63
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A9.xml
@@ -0,0 +1,65 @@
+  <counter_set name="ARMv7_Cortex_A9_cnt" count="6"/>
+  <category name="Cortex-A9" counter_set="ARMv7_Cortex_A9_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A9_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exception taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Branch" name="PC change" description="Software change of the Program Counter, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x40" title="Java" name="Bytecode execute" description="Counts the number of Java bytecodes being decoded, including speculative ones"/>
+    <event event="0x41" title="Java" name="SW bytecode execute" description="Counts the number of software Java bytecodes being decoded, including speculative ones"/>
+    <event event="0x42" title="Jazelle" name="Backward branch execute" description="Counts the number of Jazelle taken branches being executed. This includes the branches that are flushed because of a previous load/store that aborts late."/>
+    <event event="0x50" title="Cache" name="Coherency miss" description="Counts the number of coherent linefill requests performed by the Cortex-A9 processor that also miss in all the other Cortex-A9 processors. This means that the request is sent to the external memory."/>
+    <event event="0x51" title="Cache" name="Coherency hit" description="Counts the number of coherent linefill requests performed by the Cortex-A9 processor that hit in another Cortex-A9 processor. This means that the linefill data is fetched directly from the relevant Cortex-A9 cache."/>
+    <event event="0x60" title="Cache" name="Inst dependent stall" description="Counts the number of cycles where the processor: is ready to accept new instructions, does not receive a new instruction, because: the instruction side is unable to provide one or the instruction cache is performing at least one linefill"/>
+    <event event="0x61" title="Cache" name="Data dependent stall" description="Counts the number of cycles where the processor has some instructions that it cannot issue to any pipeline, and the Load Store unit has at least one pending linefill request, and no pending TLB requests"/>
+    <event event="0x62" title="Cache" name="TLB stall" description="Counts the number of cycles where the processor is stalled waiting for the completion of translation table walks from the main TLB. The processor stalls because the instruction side is not able to provide the instructions, or the data side is not able to provide the necessary data."/>
+    <event event="0x63" title="Intrinsic" name="STREX pass" description="Counts the number of STREX instructions architecturally executed and passed"/>
+    <event event="0x64" title="Intrinsic" name="STREX fail" description="Counts the number of STREX instructions architecturally executed and failed"/>
+    <event event="0x65" title="Cache" name="Data eviction" description="Counts the number of eviction requests because of a linefill in the data cache"/>
+    <event event="0x66" title="Pipeline" name="Issue stage no dispatch" description="Counts the number of cycles where the issue stage does not dispatch any instruction because it is empty or cannot dispatch any instructions"/>
+    <event event="0x67" title="Pipeline" name="Issue stage empty" description="Counts the number of cycles where the issue stage is empty"/>
+    <event event="0x68" title="Instruction" name="Executed" description="Counts the number of instructions going through the Register Renaming stage. This number is an approximate number of the total number of instructions speculatively executed, and an even more approximate number of the total number of instructions architecturally executed. The approximation depends mainly on the branch misprediction rate."/>
+    <event event="0x69" title="Cache" name="Data linefills" description="Counts the number of linefills performed on the external AXI bus. This event counts all data linefill requests, caused by: loads, including speculative ones, stores, PLD, prefetch or page table walk."/>
+    <event event="0x6a" title="Cache" name="Prefetch linefills" description="Counts the number of data linefills caused by prefetcher requests"/>
+    <event event="0x6b" title="Cache" name="Prefetch hits" description="Counts the number of cache hits in a line that belongs to a stream followed by the prefetcher. This includes: lines that have been prefetched by the automatic data prefetcher and lines already present in the cache, before the prefetcher action."/>
+    <event event="0x6e" title="Procedure" name="Return" description="Counts the number of procedure returns whose condition codes do not fail, excluding all returns from exception. This count includes procedure returns that are flushed because of a previous load/store that aborts late."/>
+    <event event="0x70" title="Instruction" name="Main execution unit" description="Counts the number of instructions being executed in the main execution pipeline of the processor, the multiply pipeline and arithmetic logic unit pipeline. The counted instructions are still speculative."/>
+    <event event="0x71" title="Instruction" name="Second execution unit" description="Counts the number of instructions being executed in the processor second execution pipeline (ALU). The counted instructions are still speculative."/>
+    <event event="0x72" title="Instruction" name="Load/Store" description="Counts the number of instructions being executed in the Load/Store unit. The counted instructions are still speculative."/>
+    <event event="0x73" title="Instruction" name="Floating point" description="Counts the number of floating-point instructions going through the Register Rename stage. Instructions are still speculative in this stage."/>
+    <event event="0x74" title="Instruction" name="NEON" description="Counts the number of NEON instructions going through the Register Rename stage. Instructions are still speculative in this stage."/>
+    <event event="0x80" title="Stalls" name="PLD" description="Counts the number of cycles where the processor is stalled because PLD slots are all full"/>
+    <event event="0x81" title="Stalls" name="Memory write" description="Counts the number of cycles when the processor is stalled. The data side is stalled also, because it is full and executes writes to the external memory."/>
+    <event event="0x82" title="Stalls" name="Inst main TLB miss" description="Counts the number of stall cycles because of main TLB misses on requests issued by the instruction side"/>
+    <event event="0x83" title="Stalls" name="Data main TLB miss" description="Counts the number of stall cycles because of main TLB misses on requests issued by the data side"/>
+    <event event="0x84" title="Stalls" name="Inst micro TLB miss" description="Counts the number of stall cycles because of micro TLB misses on the instruction side. This event does not include main TLB miss stall cycles that are already counted in the corresponding main TLB event."/>
+    <event event="0x85" title="Stalls" name="Data micro TLB miss" description="Counts the number of stall cycles because of micro TLB misses on the data side. This event does not include main TLB miss stall cycles that are already counted in the corresponding main TLB event."/>
+    <event event="0x86" title="Stalls" name="DMB" description="Counts the number of stall cycles because of the execution of a DMB. This includes all DMB instructions being executed, even speculatively."/>
+    <event event="0x8a" title="Clock" name="Integer core" description="Counts the number of cycles when the integer core clock is enabled"/>
+    <event event="0x8b" title="Clock" name="Data engine" description="Counts the number of cycles when the data engine clock is enabled"/>
+    <event event="0x8c" title="Clock" name="NEON" description="Counts the number of cycles when the NEON SIMD clock is enabled"/>
+    <event event="0x8d" title="Memory" name="TLB inst allocations" description="Counts the number of TLB allocations because of Instruction requests"/>
+    <event event="0x8e" title="Memory" name="TLB data allocations" description="Counts the number of TLB allocations because of Data requests"/>
+    <event event="0x90" title="Instruction" name="ISB" description="Counts the number of ISB instructions architecturally executed"/>
+    <event event="0x91" title="Instruction" name="DSB" description="Counts the number of DSB instructions architecturally executed"/>
+    <event event="0x92" title="Instruction" name="DMB" description="Counts the number of DMB instructions speculatively executed"/>
+    <event event="0x93" title="External" name="Interrupts" description="Counts the number of external interrupts executed by the processor"/>
+    <event event="0xa0" title="PLE" name="Cache line rq completed" description="Counts the number of PLE cache line requests completed"/>
+    <event event="0xa1" title="PLE" name="Cache line rq skipped" description="Counts the number of PLE cache line requests skipped"/>
+    <event event="0xa2" title="PLE" name="FIFO flush" description="Counts the number of PLE FIFO flush requests"/>
+    <event event="0xa3" title="PLE" name="Request completed" description="Counts the number of PLE FIFO flush completed"/>
+    <event event="0xa4" title="PLE" name="FIFO overflow" description="Counts the number of PLE FIFO flush overflowed"/>
+    <event event="0xa5" title="PLE" name="Request programmed" description="Counts the number of PLE FIFO flush program requests"/>
+  </category>
diff --git a/tools/gator/daemon/events-Filesystem.xml b/tools/gator/daemon/events-Filesystem.xml
new file mode 100644
index 00000000000..1fa3b3bba78
--- /dev/null
+++ b/tools/gator/daemon/events-Filesystem.xml
@@ -0,0 +1,10 @@
+  <category name="Filesystem">
+    <!-- counter attribute must start with filesystem_ and be unique -->
+    <!-- regex item in () is the value shown or, if the parentheses are missing, the number of times the regex matches is counted -->
+    <!--
+    <event counter="filesystem_loginuid" path="/proc/self/loginuid" title="loginuid" name="loginuid" class="absolute" description="loginuid"/>
+    <event counter="filesystem_gatord_rss" path="/proc/self/stat" title="stat" name="rss" class="absolute" regex="-?[0-9]+ \(.*\) . -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ (-?[0-9]+)" units="pages" description="resident set size"/>
+    <event counter="filesystem_processes" path="/proc/stat" title="proc-stat" name="processes" class="absolute" regex="processes ([0-9]+)" description="Number of processes and threads created"/>
+    <event counter="filesystem_context_switches" path="/proc/stat" title="proc-stat" name="context switches" class="absolute" regex="ctxt ([0-9]+)" description="Number of processes and threads created"/>
+    -->
+  </category>
diff --git a/tools/gator/daemon/events-Krait-architected.xml b/tools/gator/daemon/events-Krait-architected.xml
new file mode 100644
index 00000000000..b8d3bcb48de
--- /dev/null
+++ b/tools/gator/daemon/events-Krait-architected.xml
@@ -0,0 +1,22 @@
+  <counter_set name="Krait_cnt" count="4"/>
+  <category name="Krait" counter_set="Krait_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="Krait_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Program Counter" name="SW change" description="Software change of PC, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0e" title="Branch" name="Procedure Return" description="Procedure return architecturally executed (not by exceptions)"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+  </category>
diff --git a/tools/gator/daemon/events-L2C-310.xml b/tools/gator/daemon/events-L2C-310.xml
new file mode 100644
index 00000000000..055847c4ca1
--- /dev/null
+++ b/tools/gator/daemon/events-L2C-310.xml
@@ -0,0 +1,18 @@
+  <counter_set name="L2C-310_cnt" count="2"/>
+  <category name="L2C-310" counter_set="L2C-310_cnt" per_cpu="no">
+    <event event="0x1" title="L2 Cache" name="CastOUT" description="Eviction, CastOUT, of a line from the L2 cache"/>
+    <event event="0x2" title="L2 Cache" name="Data Read Hit" description="Data read hit in the L2 cache"/>
+    <event event="0x3" title="L2 Cache" name="Data Read Request" description="Data read lookup to the L2 cache. Subsequently results in a hit or miss"/>
+    <event event="0x4" title="L2 Cache" name="Data Write Hit" description="Data write hit in the L2 cache"/>
+    <event event="0x5" title="L2 Cache" name="Data Write Request" description="Data write lookup to the L2 cache. Subsequently results in a hit or miss"/>
+    <event event="0x6" title="L2 Cache" name="Data Write-Through Request" description="Data write lookup to the L2 cache with Write-Through attribute. Subsequently results in a hit or miss"/>
+    <event event="0x7" title="L2 Cache" name="Instruction Read Hit" description="Instruction read hit in the L2 cache"/>
+    <event event="0x8" title="L2 Cache" name="Instruction Read Request" description="Instruction read lookup to the L2 cache. Subsequently results in a hit or miss"/>
+    <event event="0x9" title="L2 Cache" name="Write Allocate Miss" description="Allocation into the L2 cache caused by a write, with Write-Allocate attribute, miss"/>
+    <event event="0xa" title="L2 Cache" name="Internal Prefetch Allocate" description="Allocation of a prefetch generated by L2C-310 into the L2 cache"/>
+    <event event="0xb" title="L2 Cache" name="Prefetch Hit" description="Prefetch hint hits in the L2 cache"/>
+    <event event="0xc" title="L2 Cache" name="Prefetch Allocate" description="Prefetch hint allocated into the L2 cache"/>
+    <event event="0xd" title="L2 Cache" name="Speculative Read Received" description="Speculative read received"/>
+    <event event="0xe" title="L2 Cache" name="Speculative Read Confirmed" description="Speculative read confirmed"/>
+    <event event="0xf" title="L2 Cache" name="Prefetch Hint Received" description="Prefetch hint received"/>
+  </category>
diff --git a/tools/gator/daemon/events-Linux.xml b/tools/gator/daemon/events-Linux.xml
new file mode 100644
index 00000000000..0350c0c4b57
--- /dev/null
+++ b/tools/gator/daemon/events-Linux.xml
@@ -0,0 +1,17 @@
+  <category name="Linux">
+    <event counter="Linux_irq_softirq" title="Interrupts" name="SoftIRQ" per_cpu="yes" description="Linux SoftIRQ taken"/>
+    <event counter="Linux_irq_irq" title="Interrupts" name="IRQ" per_cpu="yes" description="Linux IRQ taken"/>
+    <event counter="Linux_block_rq_wr" title="Disk I/O" name="Write" units="B" description="Disk I/O Bytes Written"/>
+    <event counter="Linux_block_rq_rd" title="Disk I/O" name="Read" units="B" description="Disk I/O Bytes Read"/>
+    <event counter="Linux_net_rx" title="Network" name="Receive" units="B" description="Receive network traffic, including effect from Streamline"/>
+    <event counter="Linux_net_tx" title="Network" name="Transmit" units="B" description="Transmit network traffic, including effect from Streamline"/>
+    <event counter="Linux_sched_switch" title="Scheduler" name="Switch" per_cpu="yes" description="Context switch events"/>
+    <event counter="Linux_meminfo_memused" title="Memory" name="Used" class="absolute" units="B" proc="yes" description="Total used memory size. Note: a process' used memory includes shared memory that may be counted more than once (equivalent to RES from top). Kernel threads are not filterable."/>
+    <event counter="Linux_meminfo_memused2" title="Memory" name="Used" class="absolute" units="B" description="Total used memory size"/>
+    <event counter="Linux_meminfo_memfree" title="Memory" name="Free" class="absolute" display="minimum" units="B" description="Available memory size"/>
+    <event counter="Linux_meminfo_bufferram" title="Memory" name="Buffer" class="absolute" units="B" description="Memory used by OS disk buffers"/>
+    <event counter="Linux_power_cpu_freq" title="Clock" name="Frequency" per_cpu="yes" class="absolute" units="Hz" series_composition="overlay" average_cores="yes" description="Frequency setting of the CPU"/>
+    <event counter="Linux_cpu_wait_contention" title="CPU Contention" name="Wait" per_cpu="no" class="activity" derived="yes" rendering_type="bar" average_selection="yes" percentage="yes" multiplier="0.0001" color="0x003c96fb" description="One or more threads are runnable but waiting due to CPU contention"/>
+    <event counter="Linux_cpu_wait_io" title="CPU I/O" name="Wait" per_cpu="no" class="activity" derived="yes" rendering_type="bar" average_selection="yes" percentage="yes" multiplier="0.0001" color="0x00b30000" description="One or more threads are blocked on an I/O resource"/>
+    <event counter="Linux_power_cpu" title="CPU Status" name="Activity" class="activity" activity1="Off" activity_color1="0x0000ff00" activity2="WFI" activity_color2="0x000000ff" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" description="CPU Status"/>
+  </category>
diff --git a/tools/gator/daemon/events-Mali-4xx.xml b/tools/gator/daemon/events-Mali-4xx.xml
new file mode 100644
index 00000000000..e2f4405719c
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-4xx.xml
@@ -0,0 +1,256 @@
+  <counter_set name="ARM_Mali-4xx_VP_0_cnt" count="2"/>
+  <counter_set name="ARM_Mali-4xx_SW_cnt" count="0"/>
+  <category name="Mali Vertex Processor" counter_set="ARM_Mali-4xx_VP_0_cnt" per_cpu="no">
+    <event event="0x01" title="Mali-4xx VP" name="Active cycles" description="Number of cycles per frame the MaliGP2 was active."/>
+    <event event="0x02" title="Mali-4xx VP" name="Active cycles, vertex shader" description="Number of cycles per frame the vertex shader unit was active."/>
+    <event event="0x03" title="Mali-4xx VP" name="Active cycles, vertex storer" description="Number of cycles per frame the vertex storer unit was active."/>
+    <event event="0x04" title="Mali-4xx VP" name="Active cycles, vertex loader" description="Number of cycles per frame the vertex loader unit was active."/>
+    <event event="0x05" title="Mali-4xx VP" name="Cycles vertex loader waiting for vertex shader" description="Number of cycles per frame the vertex loader was idle while waiting on the vertex shader."/>
+    <event event="0x06" title="Mali-4xx VP" name="Words read, system bus" description="Total number of 64 bit words read by the GP2 from the system bus per frame."/>
+    <event event="0x07" title="Mali-4xx VP" name="Words written, system bus" description="Total number of 64 bit words written by the GP2 to the system bus per frame."/>
+    <event event="0x08" title="Mali-4xx VP" name="Read bursts, system bus" description="Number of read bursts by the GP2 from the system bus per frame."/>
+    <event event="0x09" title="Mali-4xx VP" name="Write bursts, system bus" description="Number of write bursts from the MaliGP2 to the system bus per frame."/>
+    <event event="0x0a" title="Mali-4xx VP" name="Vertices processed" description="Number of vertices processed by the MaliGP2 per frame."/>
+    <event event="0x0b" title="Mali-4xx VP" name="Vertices fetched" description="Number of vertices fetched by the MaliGP2 per frame."/>
+    <event event="0x0c" title="Mali-4xx VP" name="Primitives fetched" description="Number of graphics primitives fetched by the MaliGP2 per frame."/>
+    <event event="0x0e" title="Mali-4xx VP" name="Primitives culled" description="Number of graphics primitives discarded per frame, because they were seen from the back or were offscreen."/>
+    <event event="0x0f" title="Mali-4xx VP" name="Commands written to tiles" description="Number of commands (8 Bytes, mainly primitives) written by GP2 to the PP input data structure per frame."/>
+    <event event="0x10" title="Mali-4xx VP" name="Memory blocks allocated" description="Number of overflow data blocks needed for outputting the PP input data structure per frame ."/>
+    <event event="0x13" title="Mali-4xx VP" name="Vertex loader cache misses" description="Number of cache misses for the vertex shader's vertex input unit per frame."/>
+    <event event="0x16" title="Mali-4xx VP" name="Active cycles, vertex shader command processor" description="Number of cycles per frame the GP2 vertex shader command processor was active. This includes time waiting for semaphores."/>
+    <event event="0x17" title="Mali-4xx VP" name="Active cycles, PLBU command processor" description="Number of cycles per frame the MaliGP2 PLBU command processor was active. This includes time waiting for semaphores."/>
+    <event event="0x18" title="Mali-4xx VP" name="Active Cycles, PLBU list writer" description="Number of cycles per frame the MaliGP2 PLBU output unit was active. This includes time spent waiting on the bus."/>
+    <event event="0x19" title="Mali-4xx VP" name="Active cycles, PLBU geometry processing" description="Number of cycles per frame the MaliGP2 PLBU was active, excepting final data output. In other words: active cycles through the prepare list commands. This includes time spent waiting on the bus."/>
+    <event event="0x1b" title="Mali-4xx VP" name="Active cycles, PLBU primitive assembly" description="Number of active cycles per frame spent by the MaliGP2 PLBU doing primitive assembly. This does not include scissoring or final output. This includes time spent waiting on the bus."/>
+    <event event="0x1c" title="Mali-4xx VP" name="Active cycles, PLBU vertex fetcher" description="Number of active cycles per frame spent by the MaliGP2 PLBU fetching vertex data. This includes time spent waiting on the bus."/>
+    <event event="0x1e" title="Mali-4xx VP" name="Active cycles, Bounding-box and command generator" description="Number of active cycles per frame spent by the MaliGP2 PLBU setting up bounding boxes and commands (mainly graphics primitives). This includes time spent waiting on the bus."/>
+    <event event="0x20" title="Mali-4xx VP" name="Active cycles, Scissor tile iterator" description="Number of active cycles per frame spent by the MaliGP2 PLBU iterating over tiles to perform scissoring. This includes time spent waiting on the bus."/>
+    <event event="0x21" title="Mali-4xx VP" name="Active cycles, PLBU tile iterator" description="Number of active cycles per frame spent by the MaliGP2 PLBU iterating over the tiles in the bounding box generating commands (mainly graphics primitives). This includes time spent waiting on the bus."/>
+  </category>
+  <category name="Mali Fragment Processor" per_cpu="no">
+    <counter_set name="ARM_Mali-4xx_FP_0_cnt" title="Mali-4xx FP0" description="Mali GPU Fragment Processor 0" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_1_cnt" title="Mali-4xx FP1" description="Mali GPU Fragment Processor 1" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_2_cnt" title="Mali-4xx FP2" description="Mali GPU Fragment Processor 2" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_3_cnt" title="Mali-4xx FP3" description="Mali GPU Fragment Processor 3" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_4_cnt" title="Mali-4xx FP4" description="Mali GPU Fragment Processor 4" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_5_cnt" title="Mali-4xx FP5" description="Mali GPU Fragment Processor 5" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_6_cnt" title="Mali-4xx FP6" description="Mali GPU Fragment Processor 6" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_7_cnt" title="Mali-4xx FP7" description="Mali GPU Fragment Processor 7" count="2"/>
+    <event event="0x00" title="Mali-4xx FP" name="Active clock cycles" description="Active clock cycles, between polygon start and IRQ."/>
+    <event event="0x02" title="Mali-4xx FP" name="Total bus reads" description="Total number of 64-bit words read from the bus."/>
+    <event event="0x03" title="Mali-4xx FP" name="Total bus writes" description="Total number of 64-bit words written to the bus."/>
+    <event event="0x04" title="Mali-4xx FP" name="Bus read request cycles" description="Number of cycles during which the bus read request signal was HIGH."/>
+    <event event="0x05" title="Mali-4xx FP" name="Bus write request cycles" description="Number of cycles during which the bus write request signal was HIGH."/>
+    <event event="0x06" title="Mali-4xx FP" name="Bus read transactions count" description="Number of read requests accepted by the bus."/>
+    <event event="0x07" title="Mali-4xx FP" name="Bus write transactions" description="Number of write requests accepted by the bus."/>
+    <event event="0x09" title="Mali-4xx FP" name="Tile writeback writes" description="64-bit words written to the bus by the writeback unit."/>
+    <event event="0x0a" title="Mali-4xx FP" name="Store unit writes" description="64-bit words written to the bus by the store unit."/>
+    <event event="0x0d" title="Mali-4xx FP" name="Texture cache uncompressed reads" description="Number of 64-bit words read from the bus into the uncompressed textures cache."/>
+    <event event="0x0e" title="Mali-4xx FP" name="Polygon list reads" description="Number of 64-bit words read from the bus by the polygon list reader."/>
+    <event event="0x0f" title="Mali-4xx FP" name="RSW reads" description="Number of 64-bit words read from the bus into the Render State Word register."/>
+    <event event="0x10" title="Mali-4xx FP" name="Vertex cache reads" description="Number of 64-bit words read from the bus into the vertex cache."/>
+    <event event="0x11" title="Mali-4xx FP" name="Uniform remapping reads" description="Number of 64-bit words read from the bus when reading from the uniform remapping table."/>
+    <event event="0x12" title="Mali-4xx FP" name="Program cache reads" description="Number of 64-bit words read from the bus into the fragment shader program cache."/>
+    <event event="0x13" title="Mali-4xx FP" name="Varying reads" description="Number of 64-bit words containing varyings generated by the vertex processing read from the bus."/>
+    <event event="0x14" title="Mali-4xx FP" name="Texture descriptors reads" description="Number of 64-bit words containing texture descriptors read from the bus."/>
+    <event event="0x15" title="Mali-4xx FP" name="Texture descriptor remapping reads" description="Number of 64-bit words read from the bus when reading from the texture descriptor remapping table."/>
+    <event event="0x17" title="Mali-4xx FP" name="Load unit reads" description="Number of 64-bit words read from the bus by the LOAD sub-instruction."/>
+    <event event="0x18" title="Mali-4xx FP" name="Polygon count" description="Number of triangles read from the polygon list."/>
+    <event event="0x19" title="Mali-4xx FP" name="Pixel rectangle count" description="Number of pixel rectangles read from the polygon list."/>
+    <event event="0x1a" title="Mali-4xx FP" name="Lines count" description="Number of lines read from the polygon list."/>
+    <event event="0x1b" title="Mali-4xx FP" name="Points count" description="Number of points read from the polygon list."/>
+    <event event="0x1c" title="Mali-4xx FP" name="Stall cycles PolygonListReader" description="Number of clock cycles the Polygon List Reader waited for output being collected."/>
+    <event event="0x1d" title="Mali-4xx FP" name="Stall cycles triangle setup" description="Number of clock cycles the TSC waited for input."/>
+    <event event="0x1e" title="Mali-4xx FP" name="Quad rasterized count" description="Number of 2x?2 quads output from rasterizer."/>
+    <event event="0x1f" title="Mali-4xx FP" name="Fragment rasterized count" description="Number of fragment rasterized. Fragments/(Quads*4) gives average actual fragments per quad."/>
+    <event event="0x20" title="Mali-4xx FP" name="Fragment rejected fragment-kill count" description="Number of fragments exiting the fragment shader as killed."/>
+    <event event="0x21" title="Mali-4xx FP" name="Fragment rejected fwd-fragment-kill count" description="Number of fragments killed by forward fragment kill."/>
+    <event event="0x22" title="Mali-4xx FP" name="Fragment passed z/stencil count" description="Number of fragments passing Z and stencil test."/>
+    <event event="0x23" title="Mali-4xx FP" name="Patches rejected early z/stencil count" description="Number of patches rejected by EarlyZ. A patch can be 8x8, 4x4 or 2x2 pixels."/>
+    <event event="0x24" title="Mali-4xx FP" name="Patches evaluated" description="Number of patches evaluated for EarlyZ rejection."/>
+    <event event="0x25" title="Mali-4xx FP" name="Instruction completed count" description="Number of fragment shader instruction words completed. It is a function of pixels processed and the length of the shader programs."/>
+    <event event="0x26" title="Mali-4xx FP" name="Instruction failed rendezvous count" description="Number of fragment shader instructions not completed because of failed Rendezvous."/>
+    <event event="0x27" title="Mali-4xx FP" name="Instruction failed varying-miss count" description="Number of fragment shader instructions not completed because of failed varying operation."/>
+    <event event="0x28" title="Mali-4xx FP" name="Instruction failed texture-miss count" description="Number of fragment shader instructions not completed because of failed texture operation."/>
+    <event event="0x29" title="Mali-4xx FP" name="Instruction failed load-miss count" description="Number of fragment shader instructions not completed because of failed load operation."/>
+    <event event="0x2a" title="Mali-4xx FP" name="Instruction failed tile read-miss count" description="Number of fragment shader instructions not completed because of failed read from the tilebuffer."/>
+    <event event="0x2b" title="Mali-4xx FP" name="Instruction failed store-miss count" description="Number of fragment shader instructions not completed because of failed store operation."/>
+    <event event="0x2c" title="Mali-4xx FP" name="Rendezvous breakage count" description="Number of Rendezvous breakages reported."/>
+    <event event="0x2d" title="Mali-4xx FP" name="Pipeline bubbles cycle count" description="Number of unused cycles in the fragment shader while rendering is active."/>
+    <event event="0x2e" title="Mali-4xx FP" name="Texture mapper multipass count" description="Number of texture operations looped because of more texture passes needed."/>
+    <event event="0x2f" title="Mali-4xx FP" name="Texture mapper cycle count" description="Number of texture operation cycles."/>
+    <event event="0x30" title="Mali-4xx FP" name="Vertex cache hit count" description="Number of times a requested vertex was found in the cache (Number of vertex cache hits)."/>
+    <event event="0x31" title="Mali-4xx FP" name="Vertex cache miss count" description="Number of times a requested vertex was not found in the cache (Number of vertex cache misses)."/>
+    <event event="0x32" title="Mali-4xx FP" name="Varying cache hit count" description="Number of times a requested varying was found in the cache (Number of varying cache hits)."/>
+    <event event="0x33" title="Mali-4xx FP" name="Varying cache miss count" description="Number of times a requested varying was not found in the cache (Number of varying cache misses)."/>
+    <event event="0x34" title="Mali-4xx FP" name="Varying cache conflict miss count" description="Number of times a requested varying was not in the cache and its value, retrieved from memory, must overwrite an older cache entry. This happens when an access pattern cannot be serviced by the cache."/>
+    <event event="0x35" title="Mali-4xx FP" name="Texture cache hit count" description="Number of times a requested texel was found in the texture cache (Number of texture cache hits)."/>
+    <event event="0x36" title="Mali-4xx FP" name="Texture cache miss count" description="Number of times a requested texel was not found in the texture cache (Number of texture cache misses)."/>
+    <event event="0x37" title="Mali-4xx FP" name="Texture cache conflict miss count" description="Number of times a requested texel was not in the cache and its value, retrieved from memory, must overwrite an older cache entry. This happens when an access pattern cannot be serviced by the cache."/>
+    <event event="0x38" title="Mali-4xx FP" name="Compressed texture cache hit count" description="Number of times a requested item was found in the cache."/>
+    <event event="0x39" title="Mali-4xx FP" name="Compressed texture cache miss count" description="Number of times a requested item was not found in the cache."/>
+    <event event="0x3a" title="Mali-4xx FP" name="Load/Store cache hit count" description="Number of hits in the load/store cache."/>
+    <event event="0x3b" title="Mali-4xx FP" name="Load/Store cache miss count" description="Number of misses in the load/store cache."/>
+    <event event="0x3c" title="Mali-4xx FP" name="Program cache hit count" description="Number of hits in the program cache."/>
+    <event event="0x3d" title="Mali-4xx FP" name="Program cache miss count" description="Number of misses in the program cache."/>
+  </category>
+  <counter_set name="ARM_Mali-4xx_L2_0_cnt" title="Mali-4xx L2" description="Mali GPU L2 Cache Core 0" count="2"/>
+  <category name="Mali-4xx L2" counter_set="ARM_Mali-4xx_L2_0_cnt" per_cpu="no">
+    <event event="0x01" title="Mali L2 Cache" name="Total clock cycles" description="Total clock cycles"/>
+    <event event="0x02" title="Mali L2 Cache" name="Active clock cycles" description="Active clock cycles"/>
+    <option_set name="All">
+      <option event_delta="0x08" name="Master" description="Master"/>
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <option_set name="Slaves">
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <event event="0x00" option_set="All" title="Mali L2 Cache" name="Read transactions" description="Read transactions"/>
+    <event event="0x01" option_set="All" title="Mali L2 Cache" name="Write transactions" description="Write transactions"/>
+    <event event="0x02" option_set="All" title="Mali L2 Cache" name="Words read" description="Words read"/>
+    <event event="0x03" option_set="All" title="Mali L2 Cache" name="Words written" description="Words written"/>
+    <event event="0x04" option_set="Slaves" title="Mali L2 Cache" name="Read hits" description="Read hits"/>
+    <event event="0x05" option_set="Slaves" title="Mali L2 Cache" name="Read misses" description="Read misses"/>
+    <event event="0x06" option_set="Slaves" title="Mali L2 Cache" name="Write invalidates" description="Write invalidates"/>
+    <event event="0x07" option_set="Slaves" title="Mali L2 Cache" name="Read invalidates" description="Read invalidates"/>
+    <event event="0x08" option_set="Slaves" title="Mali L2 Cache" name="Cacheable read transactions" description="Cacheable read transactions"/>
+  </category>
+  <counter_set name="ARM_Mali-4xx_L2_1_cnt" title="Mali-4xx L2 1" description="Mali GPU L2 Cache Core 1" count="2"/>
+  <category name="Mali-4xx L2_1" counter_set="ARM_Mali-4xx_L2_1_cnt" per_cpu="no">
+    <event event="0x01" title="Mali L2 Cache 1" name="Total clock cycles" description="Total clock cycles"/>
+    <event event="0x02" title="Mali L2 Cache 1" name="Active clock cycles" description="Active clock cycles"/>
+    <option_set name="All">
+      <option event_delta="0x08" name="Master" description="Master"/>
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <option_set name="Slaves">
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <event event="0x00" option_set="All" title="Mali L2 Cache 1" name="Read transactions" description="Read transactions"/>
+    <event event="0x01" option_set="All" title="Mali L2 Cache 1" name="Write transactions" description="Write transactions"/>
+    <event event="0x02" option_set="All" title="Mali L2 Cache 1" name="Words read" description="Words read"/>
+    <event event="0x03" option_set="All" title="Mali L2 Cache 1" name="Words written" description="Words written"/>
+    <event event="0x04" option_set="Slaves" title="Mali L2 Cache 1" name="Read hits" description="Read hits"/>
+    <event event="0x05" option_set="Slaves" title="Mali L2 Cache 1" name="Read misses" description="Read misses"/>
+    <event event="0x06" option_set="Slaves" title="Mali L2 Cache 1" name="Write invalidates" description="Write invalidates"/>
+    <event event="0x07" option_set="Slaves" title="Mali L2 Cache 1" name="Read invalidates" description="Read invalidates"/>
+    <event event="0x08" option_set="Slaves" title="Mali L2 Cache 1" name="Cacheable read transactions" description="Cacheable read transactions"/>
+  </category>
+  <counter_set name="ARM_Mali-4xx_L2_2_cnt" title="Mali-4xx L2 2" description="Mali GPU L2 Cache Core 2" count="2"/>
+  <category name="Mali-4xx L2_2" counter_set="ARM_Mali-4xx_L2_2_cnt" per_cpu="no">
+    <event event="0x01" title="Mali L2 Cache 2" name="Total clock cycles" description="Total clock cycles"/>
+    <event event="0x02" title="Mali L2 Cache 2" name="Active clock cycles" description="Active clock cycles"/>
+    <option_set name="All">
+      <option event_delta="0x08" name="Master" description="Master"/>
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <option_set name="Slaves">
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <event event="0x00" option_set="All" title="Mali L2 Cache 2" name="Read transactions" description="Read transactions"/>
+    <event event="0x01" option_set="All" title="Mali L2 Cache 2" name="Write transactions" description="Write transactions"/>
+    <event event="0x02" option_set="All" title="Mali L2 Cache 2" name="Words read" description="Words read"/>
+    <event event="0x03" option_set="All" title="Mali L2 Cache 2" name="Words written" description="Words written"/>
+    <event event="0x04" option_set="Slaves" title="Mali L2 Cache 2" name="Read hits" description="Read hits"/>
+    <event event="0x05" option_set="Slaves" title="Mali L2 Cache 2" name="Read misses" description="Read misses"/>
+    <event event="0x06" option_set="Slaves" title="Mali L2 Cache 2" name="Write invalidates" description="Write invalidates"/>
+    <event event="0x07" option_set="Slaves" title="Mali L2 Cache 2" name="Read invalidates" description="Read invalidates"/>
+    <event event="0x08" option_set="Slaves" title="Mali L2 Cache 2" name="Cacheable read transactions" description="Cacheable read transactions"/>
+  </category>
+  <counter_set name="ARM_Mali-4xx_Filmstrip_cnt" count="1"/>
+  <category name="Mali-4xx Filmstrip" counter_set="ARM_Mali-4xx_Filmstrip_cnt" per_cpu="no">
+    <option_set name="fs">
+      <option event_delta="0x3c" name="1:60" description="captures every 60th frame"/>
+      <option event_delta="0x1e" name="1:30" description="captures every 30th frame"/>
+      <option event_delta="0xa" name="1:10" description="captures every 10th frame"/>
+    </option_set>
+    <event event="0x0400" option_set="fs" title="ARM Mali-4xx" name="Filmstrip" description="Scaled framebuffer"/>
+  </category>
+  <category name="ARM_Mali-4xx_Voltage" per_cpu="no">
+    <event counter="ARM_Mali-4xx_Voltage" title="Mali GPU Voltage" name="Voltage" class="absolute" display="average" average_selection="yes" units="mV" description="GPU core voltage."/>
+  </category>
+  <category name="ARM_Mali-4xx_Frequency" per_cpu="no">
+    <event counter="ARM_Mali-4xx_Frequency" title="Mali GPU Frequency" name="Frequency" class="absolute" display="average" average_selection="yes" units="MHz" description="GPU core frequency."/>
+  </category>
+  <category name="Mali-4xx Activity" counter_set="ARM_Mali-4xx_Activity_cnt" per_cpu="yes">
+    <event counter="ARM_Mali-4xx_fragment" title="GPU Fragment" name="Activity" class="activity" activity1="Activity" activity_color1="0x00006fcc" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" description="GPU Fragment Activity"/>
+    <event counter="ARM_Mali-4xx_vertex" title="GPU Vertex" name="Activity" class="activity" activity1="Activity" activity_color1="0x00eda000" rendering_type="bar" average_selection="yes" percentage="yes" description="GPU Vertex Activity"/>
+  </category>
+  <category name="Mali-4xx Software Counters" counter_set="ARM_Mali-4xx_SW_cnt" per_cpu="no">
+    <!-- EGL Counters -->
+    <event counter="ARM_Mali-4xx_SW_0" title="Mali EGL Software Counters" name="Blit Time" description="Time spent blitting the framebuffer from video memory to framebuffer."/>
+    <!-- glDrawElements Counters -->
+    <event counter="ARM_Mali-4xx_SW_1" title="glDrawElements Statistics" name="Calls to glDrawElements" description="Number of calls to glDrawElements."/>
+    <event counter="ARM_Mali-4xx_SW_2" title="glDrawElements Statistics" name="Indices to glDrawElements" description="Number of indices to glDrawElements."/>
+    <event counter="ARM_Mali-4xx_SW_3" title="glDrawElements Statistics" name="Transformed by glDrawElements" description="Number of vertices transformed by glDrawElements."/>
+    <!-- glDrawArrays Counters -->
+    <event counter="ARM_Mali-4xx_SW_4" title="glDrawArrays Statistics" name="Calls to glDrawArrays" description="Number of calls to glDrawArrays."/>
+    <event counter="ARM_Mali-4xx_SW_5" title="glDrawArrays Statistics" name="Transformed by glDrawArrays" description="Number of vertices transformed by glDrawArrays."/>
+    <!-- Draw Call Counters -->
+    <event counter="ARM_Mali-4xx_SW_6" title="Drawcall Statistics" name="Points" description="Number of calls to glDraw* with parameter GL_POINTS."/>
+    <event counter="ARM_Mali-4xx_SW_7" title="Drawcall Statistics" name="Lines" description="Number of calls to glDraw* with parameter GL_LINES."/>
+    <event counter="ARM_Mali-4xx_SW_8" title="Drawcall Statistics" name="Lineloop" description="Number of calls to glDraw* with parameter GL_LINE_LOOP."/>
+    <event counter="ARM_Mali-4xx_SW_9" title="Drawcall Statistics" name="Linestrip" description="Number of calls to glDraw* with parameter GL_LINE_STRIP."/>
+    <event counter="ARM_Mali-4xx_SW_10" title="Drawcall Statistics" name="Triangles" description="Number of calls to glDraw* with parameter GL_TRIANGLES."/>
+    <event counter="ARM_Mali-4xx_SW_11" title="Drawcall Statistics" name="Trianglestrip" description="Number of calls to glDraw* with parameter GL_TRIANGLE_STRIP."/>
+    <event counter="ARM_Mali-4xx_SW_12" title="Drawcall Statistics" name="Trianglefan" description="Number of calls to glDraw* with parameter GL_TRIANGLE_FAN."/>
+    <event counter="ARM_Mali-4xx_SW_13" title="Drawcall Statistics" name="Vertex Upload Time (us)" description="Time spent uploading vertex attributes and faceindex data not present in a VBO."/>
+    <event counter="ARM_Mali-4xx_SW_14" title="Drawcall Statistics" name="Uniform Bytes Copied (bytes)" description="Number of bytes copied to Mali memory as a result of uniforms update."/>
+    <!-- Buffer Profiling Counters -->
+    <event counter="ARM_Mali-4xx_SW_15" title="Buffer Profiling" name="Texture Upload Time (ms)" description="Time spent uploading textures."/>
+    <event counter="ARM_Mali-4xx_SW_16" title="Buffer Profiling" name="VBO Upload Time (ms)" description="Time spent uploading vertex buffer objects."/>
+    <event counter="ARM_Mali-4xx_SW_17" title="Buffer Profiling" name="FBO Flushes" description="Number of flushed on framebuffer attachment."/>
+    <!-- OpenGL ES 1.1 Emulation -->
+    <event counter="ARM_Mali-4xx_SW_18" title="Fixed-function Emulation" name="# Vertex Shaders Generated" description="Number of vertex shaders generated."/>
+    <event counter="ARM_Mali-4xx_SW_19" title="Fixed-function Emulation" name="# Fragment Shaders Generated" description="Number of fragment shaders generated."/>
+    <!-- Geometry Statistics -->
+    <event counter="ARM_Mali-4xx_SW_33" title="Geometry Statistics" name="Triangles" description="The total number of triangles passed to GLES per-frame."/>
+    <event counter="ARM_Mali-4xx_SW_34" title="Geometry Statistics" name="Independent Triangles" description="Number of triangles passed to GLES using the mode GL_TRIANGLES."/>
+    <event counter="ARM_Mali-4xx_SW_35" title="Geometry Statistics" name="Strip Triangles" description="Number of triangles passed to GLES using the mode GL_TRIANGLE_STRIP."/>
+    <event counter="ARM_Mali-4xx_SW_36" title="Geometry Statistics" name="Fan Triangles" description="Number of triangles passed to GLES using the mode GL_TRIANGLE_FAN."/>
+    <event counter="ARM_Mali-4xx_SW_37" title="Geometry Statistics" name="Lines" description="Number of lines passed to GLES per-frame."/>
+    <event counter="ARM_Mali-4xx_SW_38" title="Geometry Statistics" name="Independent Lines" description="Number of lines passed to GLES using the mode GL_LINES."/>
+    <event counter="ARM_Mali-4xx_SW_39" title="Geometry Statistics" name="Strip Lines" description="Number of lines passed to GLES using the mode GL_LINE_STRIP."/>
+    <event counter="ARM_Mali-4xx_SW_40" title="Geometry Statistics" name="Loop Lines" description="Number of lines passed to GLES using the mode GL_LINE_LOOP."/>
+  </category>
+  <category name="ARM_Mali-4xx_Total_alloc_pages" per_cpu="no">
+    <event counter="ARM_Mali-4xx_Total_alloc_pages" title="Mali GPU Alloc" name="pages" class="absolute" display="average" average_selection="yes" description="Total number of allocated pages"/>
+  </category>
+  <category name="Mali-4xx Session Memory usage" per_cpu="no">
+    <event counter="ARM_Mali-4xx_vertex_index_buffer" title="Mali Memory" name="Vertex and Index buffer" units="B" dclass="absolute" display="average" average_selection="yes" description="Vertex and index input"/>
+    <event counter="ARM_Mali-4xx_texture_buffer" title="Mali Memory" name="Texture buffer" units="B" dclass="absolute" display="average" average_selection="yes" description="Texture data"/>
+    <event counter="ARM_Mali-4xx_varying_buffer" title="Mali Memory" name="Varying buffer" units="B" dclass="absolute" display="average" average_selection="yes" description="Varying buffer"/>
+    <event counter="ARM_Mali-4xx_render_target" title="Mali Memory" name="Render target buffer" units="B" dclass="absolute" display="average" average_selection="yes" description="Render target buffer"/>
+    <event counter="ARM_Mali-4xx_plbu_heap" title="Mali Memory" name="Plbu heap" units="B" dclass="absolute" display="average" average_selection="yes" description="The memory to store commands from PLBU when Slave tilelist memory isn't enough"/>
+    <event counter="ARM_Mali-4xx_slave_tilelist" title="Mali Memory" name="Slave tilelist" units="B" dclass="absolute" display="average" average_selection="yes" description="Slave tilelist memory"/>
+  </category>
diff --git a/tools/gator/daemon/events-Mali-Midgard.xml b/tools/gator/daemon/events-Mali-Midgard.xml
new file mode 100644
index 00000000000..33c1a406225
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-Midgard.xml
@@ -0,0 +1,49 @@
+  <category name="Mali-Midgard Software Counters" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_TOTAL_ALLOC_PAGES" title="Mali Total Alloc Pages" name="Total number of allocated pages" description="Mali total number of allocated pages."/>
+  </category>
+<!--
+power management is disabled during profiling so these counters are not useful as they always return zero
+  <category name="Mali-Midgard PM Shader" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_PM_SHADER_0" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 0" description="Mali PM Shader: PM Shader Core 0."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_1" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 1" description="Mali PM Shader: PM Shader Core 1."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_2" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 2" description="Mali PM Shader: PM Shader Core 2."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_3" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 3" description="Mali PM Shader: PM Shader Core 3."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_4" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 4" description="Mali PM Shader: PM Shader Core 4."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_5" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 5" description="Mali PM Shader: PM Shader Core 5."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_6" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 6" description="Mali PM Shader: PM Shader Core 6."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_7" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 7" description="Mali PM Shader: PM Shader Core 7."/>
+  </category>
+  <category name="Mali-Midgard PM Tiler" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_PM_TILER_0" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Tiler" name="PM Tiler Core 0" description="Mali PM Tiler: PM Tiler Core 0."/>
+  </category>
+  <category name="Mali-Midgard PM L2" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_PM_L2_0" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM L2" name="PM L2 Core 0" description="Mali PM L2: PM L2 Core 0."/>
+    <event counter="ARM_Mali-Midgard_PM_L2_1" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM L2" name="PM L2 Core 1" description="Mali PM L2: PM L2 Core 1."/>
+  </category>
+-->
+  <category name="Mali-Midgard MMU Address Space" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_MMU_AS_0" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 0" description="Mali MMU Address Space 0 usage."/>
+    <event counter="ARM_Mali-Midgard_MMU_AS_1" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 1" description="Mali MMU Address Space 1 usage."/>
+    <event counter="ARM_Mali-Midgard_MMU_AS_2" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 2" description="Mali MMU Address Space 2 usage."/>
+    <event counter="ARM_Mali-Midgard_MMU_AS_3" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 3" description="Mali MMU Address Space 3 usage."/>
+  </category>
+  <category name="Mali-Midgard MMU Page Fault" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_0" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 0" description="Reports the number of newly allocated pages after a MMU page fault in address space 0."/>
+    <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_1" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 1" description="Reports the number of newly allocated pages after a MMU page fault in address space 1."/>
+    <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_2" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 2" description="Reports the number of newly allocated pages after a MMU page fault in address space 2."/>
+    <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_3" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 3" description="Reports the number of newly allocated pages after a MMU page fault in address space 3."/>
+  </category>
+  <counter_set name="ARM_Mali-Midgard_Filmstrip_cnt" count="1"/>
+  <category name="Mali-Midgard Filmstrip" counter_set="ARM_Mali-Midgard_Filmstrip_cnt" per_cpu="no">
+    <option_set name="fs">
+      <option event_delta="0x3c" name="1:60" description="captures every 60th frame"/>
+      <option event_delta="0x1e" name="1:30" description="captures every 30th frame"/>
+      <option event_delta="0xa" name="1:10" description="captures every 10th frame"/>
+    </option_set>
+    <event event="0x0400" option_set="fs" title="ARM Mali-Midgard" name="Filmstrip" description="Scaled framebuffer"/>
+  </category>
+  <category name="Mali-Midgard Activity" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_fragment" title="GPU Fragment" name="Activity" class="activity" activity1="Activity" activity_color1="0x00006fcc" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 0 Activity"/>
+    <event counter="ARM_Mali-Midgard_vertex" title="GPU Vertex-Tiling-Compute" name="Activity" class="activity" activity1="Activity" activity_color1="0x00eda000" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 1 Activity"/>
+    <event counter="ARM_Mali-Midgard_opencl" title="GPU Vertex-Compute" name="Activity" class="activity" activity1="Activity" activity_color1="0x00ef022f" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 2 Activity"/>
+  </category>
diff --git a/tools/gator/daemon/events-Mali-Midgard_hw.xml b/tools/gator/daemon/events-Mali-Midgard_hw.xml
new file mode 100644
index 00000000000..802db8b68a2
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-Midgard_hw.xml
@@ -0,0 +1,98 @@
+<!-- this file is valid for Midgard r4p0 and earlier and replaced with the core-specific files in r5p0 -->
+  <category name="Mali-Midgard Job Manager" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles the GPU was active"/>
+    <event counter="ARM_Mali-Midgard_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles the GPU had a pending interrupt"/>
+    <event counter="ARM_Mali-Midgard_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) was active"/>
+    <event counter="ARM_Mali-Midgard_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) was active"/>
+    <event counter="ARM_Mali-Midgard_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) was active"/>
+
+    <event counter="ARM_Mali-Midgard_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-Midgard_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-Midgard_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+    <event counter="ARM_Mali-Midgard_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-Midgard_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-Midgard_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+  </category>
+  <category name="Mali-Midgard Tiler" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-Midgard_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-Midgard_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-Midgard_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-Midgard_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+    <event counter="ARM_Mali-Midgard_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-Midgard_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-Midgard_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-Midgard_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-Midgard_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+    <event counter="ARM_Mali-Midgard_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+    <event counter="ARM_Mali-Midgard_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+    <event counter="ARM_Mali-Midgard_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+    <event counter="ARM_Mali-Midgard_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+    <event counter="ARM_Mali-Midgard_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+    <event counter="ARM_Mali-Midgard_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+    <event counter="ARM_Mali-Midgard_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+    <event counter="ARM_Mali-Midgard_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+  </category>
+  <category name="Mali-Midgard Shader Core" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles the Tripipe was active"/>
+    <event counter="ARM_Mali-Midgard_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-Midgard_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-Midgard_FRAG_CYCLE_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+
+    <event counter="ARM_Mali-Midgard_FRAG_THREADS" title="Mali Core Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-Midgard_FRAG_DUMMY_THREADS" title="Mali Core Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-Midgard_FRAG_QUADS_LZS_TEST" title="Mali Core Threads" name="Frag threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-Midgard_FRAG_QUADS_LZS_KILLED" title="Mali Core Threads" name="Frag threads killed late ZS" description="Number of threads killed by late ZS test"/>
+    <event counter="ARM_Mali-Midgard_FRAG_THREADS_LZS_TEST" title="Mali Core Threads" name="Frag threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-Midgard_FRAG_THREADS_LZS_KILLED" title="Mali Core Threads" name="Frag threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+    <event counter="ARM_Mali-Midgard_COMPUTE_TASKS" title="Mali Compute Threads" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-Midgard_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads started" description="Number of compute threads started"/>
+    <event counter="ARM_Mali-Midgard_COMPUTE_CYCLES_DESC" title="Mali Compute Threads" name="Compute cycles awaiting descriptors" description="Number of compute cycles spent waiting for descriptors"/>
+
+    <event counter="ARM_Mali-Midgard_FRAG_PRIMATIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-Midgard_FRAG_PRIMATIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+    <event counter="ARM_Mali-Midgard_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-Midgard_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+    <event counter="ARM_Mali-Midgard_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-Midgard_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-Midgard_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+    <event counter="ARM_Mali-Midgard_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-Midgard_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+    <event counter="ARM_Mali-Midgard_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+    <event counter="ARM_Mali-Midgard_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-Midgard_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+    <event counter="ARM_Mali-Midgard_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-Midgard_TEX_THREADS" title="Mali Texture Pipe" name="T instruction issues" description="Number of instructions issused to the T-pipe, including restarts"/>
+    <event counter="ARM_Mali-Midgard_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+    <event counter="ARM_Mali-Midgard_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_READ_MISSES" title="Mali Load/Store Cache Reads" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_WRITE_MISSES" title="Mali Load/Store Cache Writes" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache Atomics" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+  </category>
+  <category name="Mali-Midgard L2 and MMU" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_L2_WRITE_BEATS" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-Midgard_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+
+    <event counter="ARM_Mali-Midgard_L2_READ_BEATS" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-Midgard_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+
+    <event counter="ARM_Mali-Midgard_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-Midgard_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+    <event counter="ARM_Mali-Midgard_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-Midgard_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+  </category>
diff --git a/tools/gator/daemon/events-Mali-T60x_hw.xml b/tools/gator/daemon/events-Mali-T60x_hw.xml
new file mode 100644
index 00000000000..c35bcd11d79
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T60x_hw.xml
@@ -0,0 +1,116 @@
+
+  <category name="Mali Job Manager" per_cpu="no">
+
+    <event counter="ARM_Mali-T60x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+    <event counter="ARM_Mali-T60x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+    <event counter="ARM_Mali-T60x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+    <event counter="ARM_Mali-T60x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+    <event counter="ARM_Mali-T60x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+    <event counter="ARM_Mali-T60x_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-T60x_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-T60x_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+    <event counter="ARM_Mali-T60x_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-T60x_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-T60x_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+
+  </category>
+
+  <category name="Mali Tiler" per_cpu="no">
+
+    <event counter="ARM_Mali-T60x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+    <event counter="ARM_Mali-T60x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-T60x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-T60x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-T60x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-T60x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+    <event counter="ARM_Mali-T60x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-T60x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-T60x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-T60x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-T60x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+    <event counter="ARM_Mali-T60x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+
+  </category>
+
+  <category name="Mali Shader Core" per_cpu="no">
+
+    <event counter="ARM_Mali-T60x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+    <event counter="ARM_Mali-T60x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-T60x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-T60x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+
+    <event counter="ARM_Mali-T60x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-T60x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-T60x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-T60x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+    <event counter="ARM_Mali-T60x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-T60x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+    <event counter="ARM_Mali-T60x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-T60x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+    <event counter="ARM_Mali-T60x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-T60x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-T60x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+    <event counter="ARM_Mali-T60x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-T60x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+    <event counter="ARM_Mali-T60x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+    <event counter="ARM_Mali-T60x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-T60x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+    <event counter="ARM_Mali-T60x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-T60x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+    <event counter="ARM_Mali-T60x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+    <event counter="ARM_Mali-T60x_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_READ_MISSES" title="Mali Load/Store Cache Reads" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T60x_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_WRITE_MISSES" title="Mali Load/Store Cache Writes" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T60x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache Atomics" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T60x_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T60x_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+  </category>
+
+  <category name="Mali L2 Cache" per_cpu="no">
+
+    <event counter="ARM_Mali-T60x_L2_READ_LOOKUP" title="Mali L2 Cache Reads" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+    <event counter="ARM_Mali-T60x_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-T60x_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+
+    <event counter="ARM_Mali-T60x_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-T60x_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T60x_L2_WRITE_LOOKUP" title="Mali L2 Cache Writes" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+    <event counter="ARM_Mali-T60x_L2_EXT_READ_BEATS" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-T60x_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T60x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+    <event counter="ARM_Mali-T60x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+
+    <event counter="ARM_Mali-T60x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-T60x_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T60x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache Ext Writes" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+
+  </category>
\ No newline at end of file
diff --git a/tools/gator/daemon/events-Mali-T62x_hw.xml b/tools/gator/daemon/events-Mali-T62x_hw.xml
new file mode 100644
index 00000000000..4bc93068f75
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T62x_hw.xml
@@ -0,0 +1,116 @@
+
+  <category name="Mali Job Manager" per_cpu="no">
+
+    <event counter="ARM_Mali-T62x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+    <event counter="ARM_Mali-T62x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+    <event counter="ARM_Mali-T62x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+    <event counter="ARM_Mali-T62x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+    <event counter="ARM_Mali-T62x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+    <event counter="ARM_Mali-T62x_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-T62x_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-T62x_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+    <event counter="ARM_Mali-T62x_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-T62x_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-T62x_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+
+  </category>
+
+  <category name="Mali Tiler" per_cpu="no">
+
+    <event counter="ARM_Mali-T62x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+    <event counter="ARM_Mali-T62x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-T62x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-T62x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-T62x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-T62x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+    <event counter="ARM_Mali-T62x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-T62x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-T62x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-T62x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-T62x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+    <event counter="ARM_Mali-T62x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+
+  </category>
+
+  <category name="Mali Shader Core" per_cpu="no">
+
+    <event counter="ARM_Mali-T62x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+    <event counter="ARM_Mali-T62x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-T62x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-T62x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+    <event counter="ARM_Mali-T62x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/>
+
+    <event counter="ARM_Mali-T62x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-T62x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-T62x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-T62x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+    <event counter="ARM_Mali-T62x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-T62x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+    <event counter="ARM_Mali-T62x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-T62x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+    <event counter="ARM_Mali-T62x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-T62x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-T62x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+    <event counter="ARM_Mali-T62x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-T62x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+    <event counter="ARM_Mali-T62x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+    <event counter="ARM_Mali-T62x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-T62x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+    <event counter="ARM_Mali-T62x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-T62x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+    <event counter="ARM_Mali-T62x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+    <event counter="ARM_Mali-T62x_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_READ_MISSES" title="Mali Load/Store Cache Reads" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T62x_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_WRITE_MISSES" title="Mali Load/Store Cache Writes" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T62x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache Atomics" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T62x_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+  </category>
+
+  <category name="Mali L2 Cache" per_cpu="no">
+
+    <event counter="ARM_Mali-T62x_L2_READ_LOOKUP" title="Mali L2 Cache Reads" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+    <event counter="ARM_Mali-T62x_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-T62x_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+
+    <event counter="ARM_Mali-T62x_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-T62x_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T62x_L2_WRITE_LOOKUP" title="Mali L2 Cache Writes" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+    <event counter="ARM_Mali-T62x_L2_EXT_READ_BEATS" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-T62x_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T62x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+    <event counter="ARM_Mali-T62x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+
+    <event counter="ARM_Mali-T62x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-T62x_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T62x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache Ext Writes" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+
+  </category>
\ No newline at end of file
diff --git a/tools/gator/daemon/events-Mali-T72x_hw.xml b/tools/gator/daemon/events-Mali-T72x_hw.xml
new file mode 100644
index 00000000000..fd9cb0f16c6
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T72x_hw.xml
@@ -0,0 +1,101 @@
+
+  <category name="Mali Job Manager" per_cpu="no">
+
+    <event counter="ARM_Mali-T72x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+    <event counter="ARM_Mali-T72x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+    <event counter="ARM_Mali-T72x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+    <event counter="ARM_Mali-T72x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+    <event counter="ARM_Mali-T72x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+    <event counter="ARM_Mali-T72x_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-T72x_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-T72x_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+    <event counter="ARM_Mali-T72x_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-T72x_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-T72x_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+
+  </category>
+
+  <category name="Mali Tiler" per_cpu="no">
+
+    <event counter="ARM_Mali-T72x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+    <event counter="ARM_Mali-T72x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-T72x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-T72x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-T72x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-T72x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+    <event counter="ARM_Mali-T72x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-T72x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-T72x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-T72x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-T72x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+  </category>
+
+  <category name="Mali Shader Core" per_cpu="no">
+
+    <event counter="ARM_Mali-T72x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+    <event counter="ARM_Mali-T72x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-T72x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-T72x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+
+    <event counter="ARM_Mali-T72x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-T72x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-T72x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-T72x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+    <event counter="ARM_Mali-T72x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-T72x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+    <event counter="ARM_Mali-T72x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-T72x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+    <event counter="ARM_Mali-T72x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-T72x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-T72x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+    <event counter="ARM_Mali-T72x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-T72x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+    <event counter="ARM_Mali-T72x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of batched instructions executed by the A-pipe"/>
+
+    <event counter="ARM_Mali-T72x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-T72x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+    <event counter="ARM_Mali-T72x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-T72x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+
+
+    <event counter="ARM_Mali-T72x_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_READ_MISSES" title="Mali Load/Store Cache Reads" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T72x_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_WRITE_MISSES" title="Mali Load/Store Cache Writes" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T72x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache Atomics" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T72x_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+  </category>
+
+  <category name="Mali L2 Cache" per_cpu="no">
+
+    <event counter="ARM_Mali-T72x_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-T72x_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+
+    <event counter="ARM_Mali-T72x_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-T72x_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+
+    <event counter="ARM_Mali-T72x_L2_EXT_READ_BEAT" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-T72x_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+
+    <event counter="ARM_Mali-T72x_L2_EXT_WRITE_BEAT" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-T72x_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+
+  </category>
diff --git a/tools/gator/daemon/events-Mali-T76x_hw.xml b/tools/gator/daemon/events-Mali-T76x_hw.xml
new file mode 100644
index 00000000000..94d059fc09d
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T76x_hw.xml
@@ -0,0 +1,117 @@
+
+  <category name="Mali Job Manager" per_cpu="no">
+
+    <event counter="ARM_Mali-T76x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+    <event counter="ARM_Mali-T76x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+    <event counter="ARM_Mali-T76x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+    <event counter="ARM_Mali-T76x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+    <event counter="ARM_Mali-T76x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+    <event counter="ARM_Mali-T76x_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-T76x_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-T76x_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+    <event counter="ARM_Mali-T76x_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-T76x_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-T76x_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+
+  </category>
+
+  <category name="Mali Tiler" per_cpu="no">
+
+    <event counter="ARM_Mali-T76x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+    <event counter="ARM_Mali-T76x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-T76x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-T76x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-T76x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-T76x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+    <event counter="ARM_Mali-T76x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-T76x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-T76x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-T76x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-T76x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+    <event counter="ARM_Mali-T76x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+
+  </category>
+
+  <category name="Mali Shader Core" per_cpu="no">
+
+    <event counter="ARM_Mali-T76x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+    <event counter="ARM_Mali-T76x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-T76x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-T76x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+    <event counter="ARM_Mali-T76x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/>
+
+    <event counter="ARM_Mali-T76x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-T76x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-T76x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-T76x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+    <event counter="ARM_Mali-T76x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-T76x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+    <event counter="ARM_Mali-T76x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-T76x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+    <event counter="ARM_Mali-T76x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-T76x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-T76x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+    <event counter="ARM_Mali-T76x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-T76x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+    <event counter="ARM_Mali-T76x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+    <event counter="ARM_Mali-T76x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-T76x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+    <event counter="ARM_Mali-T76x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-T76x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+    <event counter="ARM_Mali-T76x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+    <event counter="ARM_Mali-T76x_LSC_READ_OP" title="Mali Load/Store Cache Reads" name="Read operations" description="Number of read operations in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T76x_LSC_WRITE_OP" title="Mali Load/Store Cache Writes" name="Write operations" description="Number of write operations in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T76x_LSC_ATOMIC_OP" title="Mali Load/Store Cache Atomics" name="Atomic operations" description="Number of atomic operations in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T76x_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T76x_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+  </category>
+
+  <category name="Mali L2 Cache" per_cpu="no">
+
+    <event counter="ARM_Mali-T76x_L2_READ_LOOKUP" title="Mali L2 Cache Reads" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+    <event counter="ARM_Mali-T76x_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-T76x_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+
+    <event counter="ARM_Mali-T76x_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-T76x_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T76x_L2_WRITE_LOOKUP" title="Mali L2 Cache Writes" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+    <event counter="ARM_Mali-T76x_L2_EXT_READ_BEATS" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-T76x_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T76x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+    <event counter="ARM_Mali-T76x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+
+    <event counter="ARM_Mali-T76x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-T76x_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T76x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache Ext Writes" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+
+  </category>
\ No newline at end of file
diff --git a/tools/gator/daemon/events-Mali-T82x_hw.xml b/tools/gator/daemon/events-Mali-T82x_hw.xml
new file mode 100644
index 00000000000..994c8b15418
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T82x_hw.xml
@@ -0,0 +1,108 @@
+
+  <category name="Mali Job Manager" per_cpu="no">
+
+    <event counter="ARM_Mali-T82x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+    <event counter="ARM_Mali-T82x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+    <event counter="ARM_Mali-T82x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+    <event counter="ARM_Mali-T82x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+    <event counter="ARM_Mali-T82x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+    <event counter="ARM_Mali-T82x_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-T82x_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-T82x_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+    <event counter="ARM_Mali-T82x_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-T82x_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-T82x_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+
+  </category>
+
+  <category name="Mali Tiler" per_cpu="no">
+
+    <event counter="ARM_Mali-T82x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+    <event counter="ARM_Mali-T82x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-T82x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-T82x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-T82x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-T82x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+    <event counter="ARM_Mali-T82x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-T82x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-T82x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-T82x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-T82x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+  </category>
+
+  <category name="Mali Shader Core" per_cpu="no">
+
+    <event counter="ARM_Mali-T82x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+    <event counter="ARM_Mali-T82x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-T82x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-T82x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+    <event counter="ARM_Mali-T82x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/>
+
+    <event counter="ARM_Mali-T82x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-T82x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-T82x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-T82x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+    <event counter="ARM_Mali-T82x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-T82x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+    <event counter="ARM_Mali-T82x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-T82x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+    <event counter="ARM_Mali-T82x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-T82x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-T82x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+    <event counter="ARM_Mali-T82x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-T82x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+    <event counter="ARM_Mali-T82x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of batched instructions executed by the A-pipe (normalized per pipe)"/>
+
+    <event counter="ARM_Mali-T82x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-T82x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+    <event counter="ARM_Mali-T82x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-T82x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+    <event counter="ARM_Mali-T82x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+    <event counter="ARM_Mali-T82x_LSC_READ_OP" title="Mali Load/Store Cache Reads" name="Read operations" description="Number of read operations in the Load/Store cache"/>
+    <event counter="ARM_Mali-T82x_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T82x_LSC_WRITE_OP" title="Mali Load/Store Cache Writes" name="Write operations" description="Number of write operations in the Load/Store cache"/>
+    <event counter="ARM_Mali-T82x_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T82x_LSC_ATOMIC_OP" title="Mali Load/Store Cache Atomics" name="Atomic operations" description="Number of atomic operations in the Load/Store cache"/>
+    <event counter="ARM_Mali-T82x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T82x_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-T82x_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T82x_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+  </category>
+
+  <category name="Mali L2 Cache" per_cpu="no">
+
+    <event counter="ARM_Mali-T82x_L2_READ_LOOKUP" title="Mali L2 Cache Reads" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+    <event counter="ARM_Mali-T82x_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-T82x_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+
+    <event counter="ARM_Mali-T82x_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-T82x_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T82x_L2_WRITE_LOOKUP" title="Mali L2 Cache Writes" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+    <event counter="ARM_Mali-T82x_L2_EXT_READ_BEATS" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-T82x_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T82x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+    <event counter="ARM_Mali-T82x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+
+    <event counter="ARM_Mali-T82x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-T82x_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T82x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache Ext Writes" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+
+  </category>
diff --git a/tools/gator/daemon/events-Mali-T83x_hw.xml b/tools/gator/daemon/events-Mali-T83x_hw.xml
new file mode 100644
index 00000000000..39f7acf3179
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T83x_hw.xml
@@ -0,0 +1,108 @@
+
+  <category name="Mali Job Manager" per_cpu="no">
+
+    <event counter="ARM_Mali-T83x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+    <event counter="ARM_Mali-T83x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+    <event counter="ARM_Mali-T83x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+    <event counter="ARM_Mali-T83x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+    <event counter="ARM_Mali-T83x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+    <event counter="ARM_Mali-T83x_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-T83x_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-T83x_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+    <event counter="ARM_Mali-T83x_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-T83x_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-T83x_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+
+  </category>
+
+  <category name="Mali Tiler" per_cpu="no">
+
+    <event counter="ARM_Mali-T83x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+    <event counter="ARM_Mali-T83x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-T83x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-T83x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-T83x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-T83x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+    <event counter="ARM_Mali-T83x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-T83x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-T83x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-T83x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-T83x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+  </category>
+
+  <category name="Mali Shader Core" per_cpu="no">
+
+    <event counter="ARM_Mali-T83x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+    <event counter="ARM_Mali-T83x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-T83x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-T83x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+    <event counter="ARM_Mali-T83x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/>
+
+    <event counter="ARM_Mali-T83x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-T83x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-T83x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-T83x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+    <event counter="ARM_Mali-T83x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-T83x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+    <event counter="ARM_Mali-T83x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-T83x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+    <event counter="ARM_Mali-T83x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-T83x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-T83x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+    <event counter="ARM_Mali-T83x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-T83x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+    <event counter="ARM_Mali-T83x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of batched instructions executed by the A-pipe (normalized per pipe)"/>
+
+    <event counter="ARM_Mali-T83x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-T83x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+    <event counter="ARM_Mali-T83x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-T83x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+    <event counter="ARM_Mali-T83x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+    <event counter="ARM_Mali-T83x_LSC_READ_OP" title="Mali Load/Store Cache Reads" name="Read operations" description="Number of read operations in the Load/Store cache"/>
+    <event counter="ARM_Mali-T83x_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T83x_LSC_WRITE_OP" title="Mali Load/Store Cache Writes" name="Write operations" description="Number of write operations in the Load/Store cache"/>
+    <event counter="ARM_Mali-T83x_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T83x_LSC_ATOMIC_OP" title="Mali Load/Store Cache Atomics" name="Atomic operations" description="Number of atomic operations in the Load/Store cache"/>
+    <event counter="ARM_Mali-T83x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T83x_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-T83x_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T83x_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+  </category>
+
+  <category name="Mali L2 Cache" per_cpu="no">
+
+    <event counter="ARM_Mali-T83x_L2_READ_LOOKUP" title="Mali L2 Cache Reads" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+    <event counter="ARM_Mali-T83x_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-T83x_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+
+    <event counter="ARM_Mali-T83x_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-T83x_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T83x_L2_WRITE_LOOKUP" title="Mali L2 Cache Writes" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+    <event counter="ARM_Mali-T83x_L2_EXT_READ_BEATS" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-T83x_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T83x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+    <event counter="ARM_Mali-T83x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+
+    <event counter="ARM_Mali-T83x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-T83x_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T83x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache Ext Writes" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+
+  </category>
diff --git a/tools/gator/daemon/events-Mali-T86x_hw.xml b/tools/gator/daemon/events-Mali-T86x_hw.xml
new file mode 100644
index 00000000000..6653543d5ca
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T86x_hw.xml
@@ -0,0 +1,117 @@
+
+  <category name="Mali Job Manager" per_cpu="no">
+
+    <event counter="ARM_Mali-T86x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+    <event counter="ARM_Mali-T86x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+    <event counter="ARM_Mali-T86x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+    <event counter="ARM_Mali-T86x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+    <event counter="ARM_Mali-T86x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+    <event counter="ARM_Mali-T86x_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-T86x_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-T86x_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+    <event counter="ARM_Mali-T86x_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-T86x_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-T86x_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+
+  </category>
+
+  <category name="Mali Tiler" per_cpu="no">
+
+    <event counter="ARM_Mali-T86x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+    <event counter="ARM_Mali-T86x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-T86x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-T86x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-T86x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-T86x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+    <event counter="ARM_Mali-T86x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-T86x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-T86x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-T86x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-T86x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+    <event counter="ARM_Mali-T86x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+    <event counter="ARM_Mali-T86x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+    <event counter="ARM_Mali-T86x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+    <event counter="ARM_Mali-T86x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+    <event counter="ARM_Mali-T86x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+    <event counter="ARM_Mali-T86x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+    <event counter="ARM_Mali-T86x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+    <event counter="ARM_Mali-T86x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+
+  </category>
+
+  <category name="Mali Shader Core" per_cpu="no">
+
+    <event counter="ARM_Mali-T86x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+    <event counter="ARM_Mali-T86x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-T86x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-T86x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+    <event counter="ARM_Mali-T86x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/>
+
+    <event counter="ARM_Mali-T86x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-T86x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-T86x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-T86x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+    <event counter="ARM_Mali-T86x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-T86x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+    <event counter="ARM_Mali-T86x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-T86x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+    <event counter="ARM_Mali-T86x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-T86x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-T86x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+    <event counter="ARM_Mali-T86x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-T86x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+    <event counter="ARM_Mali-T86x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+    <event counter="ARM_Mali-T86x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-T86x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+    <event counter="ARM_Mali-T86x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-T86x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+    <event counter="ARM_Mali-T86x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+    <event counter="ARM_Mali-T86x_LSC_READ_OP" title="Mali Load/Store Cache Reads" name="Read operations" description="Number of read operations in the Load/Store cache"/>
+    <event counter="ARM_Mali-T86x_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T86x_LSC_WRITE_OP" title="Mali Load/Store Cache Writes" name="Write operations" description="Number of write operations in the Load/Store cache"/>
+    <event counter="ARM_Mali-T86x_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T86x_LSC_ATOMIC_OP" title="Mali Load/Store Cache Atomics" name="Atomic operations" description="Number of atomic operations in the Load/Store cache"/>
+    <event counter="ARM_Mali-T86x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T86x_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-T86x_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T86x_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+  </category>
+
+  <category name="Mali L2 Cache" per_cpu="no">
+
+    <event counter="ARM_Mali-T86x_L2_READ_LOOKUP" title="Mali L2 Cache Reads" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+    <event counter="ARM_Mali-T86x_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-T86x_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+
+    <event counter="ARM_Mali-T86x_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-T86x_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T86x_L2_WRITE_LOOKUP" title="Mali L2 Cache Writes" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+    <event counter="ARM_Mali-T86x_L2_EXT_READ_BEATS" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-T86x_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T86x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+    <event counter="ARM_Mali-T86x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+
+    <event counter="ARM_Mali-T86x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-T86x_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T86x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache Ext Writes" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+
+  </category>
diff --git a/tools/gator/daemon/events-Mali-T88x_hw.xml b/tools/gator/daemon/events-Mali-T88x_hw.xml
new file mode 100644
index 00000000000..19385d19c9d
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T88x_hw.xml
@@ -0,0 +1,117 @@
+
+  <category name="Mali Job Manager" per_cpu="no">
+
+    <event counter="ARM_Mali-T88x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+    <event counter="ARM_Mali-T88x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+    <event counter="ARM_Mali-T88x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+    <event counter="ARM_Mali-T88x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+    <event counter="ARM_Mali-T88x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+    <event counter="ARM_Mali-T88x_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-T88x_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-T88x_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+    <event counter="ARM_Mali-T88x_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-T88x_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-T88x_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+
+  </category>
+
+  <category name="Mali Tiler" per_cpu="no">
+
+    <event counter="ARM_Mali-T88x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+    <event counter="ARM_Mali-T88x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-T88x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-T88x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-T88x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-T88x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+    <event counter="ARM_Mali-T88x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-T88x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-T88x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-T88x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-T88x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+    <event counter="ARM_Mali-T88x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+    <event counter="ARM_Mali-T88x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+    <event counter="ARM_Mali-T88x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+    <event counter="ARM_Mali-T88x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+    <event counter="ARM_Mali-T88x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+    <event counter="ARM_Mali-T88x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+    <event counter="ARM_Mali-T88x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+    <event counter="ARM_Mali-T88x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+
+  </category>
+
+  <category name="Mali Shader Core" per_cpu="no">
+
+    <event counter="ARM_Mali-T88x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+    <event counter="ARM_Mali-T88x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-T88x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-T88x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+    <event counter="ARM_Mali-T88x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/>
+
+    <event counter="ARM_Mali-T88x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-T88x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-T88x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-T88x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+    <event counter="ARM_Mali-T88x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-T88x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+    <event counter="ARM_Mali-T88x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-T88x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+    <event counter="ARM_Mali-T88x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-T88x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-T88x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+    <event counter="ARM_Mali-T88x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-T88x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+    <event counter="ARM_Mali-T88x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+    <event counter="ARM_Mali-T88x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-T88x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+    <event counter="ARM_Mali-T88x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-T88x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+    <event counter="ARM_Mali-T88x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+    <event counter="ARM_Mali-T88x_LSC_READ_OP" title="Mali Load/Store Cache Reads" name="Read operations" description="Number of read operations in the Load/Store cache"/>
+    <event counter="ARM_Mali-T88x_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T88x_LSC_WRITE_OP" title="Mali Load/Store Cache Writes" name="Write operations" description="Number of write operations in the Load/Store cache"/>
+    <event counter="ARM_Mali-T88x_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T88x_LSC_ATOMIC_OP" title="Mali Load/Store Cache Atomics" name="Atomic operations" description="Number of atomic operations in the Load/Store cache"/>
+    <event counter="ARM_Mali-T88x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T88x_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-T88x_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+
+    <event counter="ARM_Mali-T88x_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+  </category>
+
+  <category name="Mali L2 Cache" per_cpu="no">
+
+    <event counter="ARM_Mali-T88x_L2_READ_LOOKUP" title="Mali L2 Cache Reads" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+    <event counter="ARM_Mali-T88x_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-T88x_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+
+    <event counter="ARM_Mali-T88x_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-T88x_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T88x_L2_WRITE_LOOKUP" title="Mali L2 Cache Writes" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+    <event counter="ARM_Mali-T88x_L2_EXT_READ_BEATS" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-T88x_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T88x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+    <event counter="ARM_Mali-T88x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+
+    <event counter="ARM_Mali-T88x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-T88x_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T88x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache Ext Writes" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+
+  </category>
diff --git a/tools/gator/daemon/events-Mali-V500.xml b/tools/gator/daemon/events-Mali-V500.xml
new file mode 100644
index 00000000000..bc2d6aa74af
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-V500.xml
@@ -0,0 +1,30 @@
+  <category name="Mali-V500">
+    <event counter="ARM_Mali-V500_cnt0" title="MVE-V500 Stats" name="Samples" class="absolute" description="The number of times we have taken a sample"/>
+    <event counter="ARM_Mali-V500_cnt1" title="MVE-V500 Input Totals" name="Queued input-buffers" class="absolute" description="The number of input-buffers that has been queued for consumption by the MVE"/>
+    <event counter="ARM_Mali-V500_cnt2" title="MVE-V500 Input Totals" name="Consumed input-buffers" class="absolute" description="The number of input-buffers that has been consumed by the MVE and returned to the application"/>
+    <event counter="ARM_Mali-V500_cnt3" title="MVE-V500 Output Totals" name="Queued output-buffers" class="absolute" description="The number of output-buffers that has been queued for usage by the MVE"/>
+    <event counter="ARM_Mali-V500_cnt4" title="MVE-V500 Output Totals" name="Consumed output-buffers" class="absolute" description="The number of output-buffers that has been consumed by the MVE and returned to the application"/>
+    <event counter="ARM_Mali-V500_cnt5" title="MVE-V500 Stats" name="Created Sessions" class="absolute" description="The number of created sessions throughout the lifetime of the process"/>
+    <event counter="ARM_Mali-V500_cnt6" title="MVE-V500 Sessions" name="Active Sessions" description="The number of currently existing sessions"/>
+    <event counter="ARM_Mali-V500_cnt7" title="MVE-V500 Stats" name="Processed Frames" class="absolute" description="The number of processed frames. A processed frame is one where the encode or decode is complete for that particular frame. Frames can be processed out of order so this is not the same as the number of output-buffers returned"/>
+    <event counter="ARM_Mali-V500_cnt8" title="MVE-V500 Input Totals" name="Input Flushes Requested" class="absolute" description="The number of requested flushes of the input queue"/>
+    <event counter="ARM_Mali-V500_cnt9" title="MVE-V500 Input Totals" name="Input Flushes Complete" class="absolute" description="The number of completed flushes of the input queue"/>
+    <event counter="ARM_Mali-V500_cnt10" title="MVE-V500 Output Totals" name="Output Flushes Requested" class="absolute" description="The number of requested flushes of the output queue"/>
+    <event counter="ARM_Mali-V500_cnt11" title="MVE-V500 Output Totals" name="Output Flushes Complete" class="absolute" description="The number of completed flushes of the output queue"/>
+    <event counter="ARM_Mali-V500_cnt12" title="MVE-V500 Output" name="Queued Output Buffers (current)" description="The number of output-buffers that are currently queued for usage by the MVE"/>
+    <event counter="ARM_Mali-V500_cnt13" title="MVE-V500 Input" name="Queued Input Buffers (current)" description="The number of input-buffers that are currently queued for consumption by the MVE"/>
+    <event counter="ARM_Mali-V500_cnt14" title="MVE-V500 Output" name="Output Queue Flushes" description="The number of pending flushes for the MVE output-queue"/>
+    <event counter="ARM_Mali-V500_cnt15" title="MVE-V500 Input" name="Input Queue Flushes" description="The number of pending flushes for the MVE input-queue"/>
+    <event counter="ARM_Mali-V500_cnt16" title="MVE-V500 Stats" name="Errors encountered" class="absolute" description="The number of errors encountered"/>
+    <event counter="ARM_Mali-V500_cnt17" title="MVE-V500 Bandwidth" name="Bits consumed" class="absolute" description="The number of bits consumed during decode"/>
+    <event counter="ARM_Mali-V500_cnt18" title="MVE-V500 Bandwidth" name="AFBC bandwidth" class="absolute" description="The amount of AFBC-encoded bytes read or written"/>
+    <event counter="ARM_Mali-V500_cnt19" title="MVE-V500 Bandwidth" name="Bandwidth (read)" class="absolute" description="The amount of bytes read over the AXI bus"/>
+    <event counter="ARM_Mali-V500_cnt20" title="MVE-V500 Bandwidth" name="Bandwidth (write)" class="absolute" description="The amount of bytes written over the AXI bus"/>
+    <event counter="ARM_Mali-V500_evn0" title="MVE-V500 Sessions" name="Session created" description="Generated when a session has been created"/>
+    <event counter="ARM_Mali-V500_evn1" title="MVE-V500 Sessions" name="Session destroyed" description="Generated when a session has been destroyed"/>
+    <event counter="ARM_Mali-V500_evn2" title="MVE-V500 Frames" name="Frame Processed" description="Generated when the MVE has finished processing a frame"/>
+    <event counter="ARM_Mali-V500_evn3" title="MVE-V500 Output" name="Output buffer received" description="Generated when an an output buffer is returned to us from the MVE"/>
+    <event counter="ARM_Mali-V500_evn4" title="MVE-V500 Input" name="Input buffer received" description="Generated when we an input buffer is returned to us from the MVE"/>
+    <event counter="ARM_Mali-V500_act0" title="MVE-V500 Parsed" name="Activity" class="activity" activity1="activity" activity_color1="0x000000ff" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" per_cpu="yes" cores="8" description="Mali-V500 Activity"/>
+    <event counter="ARM_Mali-V500_act1" title="MVE-V500 Piped" name="Activity" class="activity" activity1="activity" activity_color1="0x0000ff00" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" per_cpu="yes" cores="8" description="Mali-V500 Activity"/>
+  </category>
diff --git a/tools/gator/daemon/events-Other.xml b/tools/gator/daemon/events-Other.xml
new file mode 100644
index 00000000000..8aec282b7e1
--- /dev/null
+++ b/tools/gator/daemon/events-Other.xml
@@ -0,0 +1,33 @@
+  <counter_set name="Other_cnt" count="6"/>
+  <category name="Other" counter_set="Other_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="Other_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Instruction architecturally executed, condition code check pass, software increment"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Level 1 instruction cache refill"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Level 1 instruction TLB refill"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Level 1 data cache refill"/>
+    <event event="0x04" title="Cache" name="Data access" description="Level 1 data cache access"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Level 1 data TLB refill"/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Instruction architecturally executed, condition code check pass, load"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Instruction architecturally executed, condition code check pass, store"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exception taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Instruction architecturally executed, condition code check pass, exception return"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction architecturally executed, condition code check pass, write to CONTEXTIDR"/>
+    <event event="0x0c" title="Branch" name="PC change" description="Instruction architecturally executed, condition code check pass, software change of the PC"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Instruction architecturally executed, immediate branch"/>
+    <event event="0x0e" title="Procedure" name="Return" description="Instruction architecturally executed, condition code check pass, procedure return"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Instruction architecturally executed, condition code check pass, unaligned load or store"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Mispredicted or not predicted branch speculatively executed"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Predictable branch speculatively executed"/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="L1 inst access" description="Level 1 instruction cache access"/>
+    <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache write-back"/>
+    <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+    <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+    <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache write-back"/>
+    <event event="0x19" title="Bus" name="Access" description="Bus access"/>
+    <event event="0x1a" title="Memory" name="Error" description="Local memory error"/>
+    <event event="0x1b" title="Instruction" name="Speculative" description="Instruction speculatively executed"/>
+    <event event="0x1c" title="Memory" name="Translation table" description="Instruction architecturally executed, condition code check pass, write to TTBR"/>
+    <event event="0x1d" title="Bus" name="Cycle" description="Bus cycle"/>
+  </category>
diff --git a/tools/gator/daemon/events-Perf-Hardware.xml b/tools/gator/daemon/events-Perf-Hardware.xml
new file mode 100644
index 00000000000..423696f8242
--- /dev/null
+++ b/tools/gator/daemon/events-Perf-Hardware.xml
@@ -0,0 +1,12 @@
+  <counter_set name="Perf_Hardware_cnt" count="6"/>
+  <category name="Perf Hardware" counter_set="Perf_Hardware_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="Perf_Hardware_ccnt" event="0" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="1" title="Instruction" name="Executed" description="Instruction executed"/>
+    <event event="2" title="Cache" name="References" description="Cache References"/>
+    <event event="3" title="Cache" name="Misses" description="Cache Misses"/>
+    <event event="4" title="Branch" name="Instructions" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="5" title="Branch" name="Misses" description="Branch mispredicted or not predicted"/>
+    <event event="6" title="Bus" name="Cycles" description="Bus Cycles"/>
+    <event event="7" title="Instruction" name="Stalled Frontend" description="Stalled Frontend Cycles"/>
+    <event event="8" title="Instruction" name="Stalled Backend" description="Stalled Backend Cycles"/>
+  </category>
diff --git a/tools/gator/daemon/events-Scorpion.xml b/tools/gator/daemon/events-Scorpion.xml
new file mode 100644
index 00000000000..fa716fdc484
--- /dev/null
+++ b/tools/gator/daemon/events-Scorpion.xml
@@ -0,0 +1,107 @@
+  <counter_set name="Scorpion_cnt" count="4"/>
+  <category name="Scorpion" counter_set="Scorpion_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="Scorpion_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Program Counter" name="SW change" description="Software change of PC, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0e" title="Branch" name="Procedure Return" description="Procedure return architecturally executed (not by exceptions)"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x4c" title="Scorpion" name="ICACHE_EXPL_INV" description="I-cache explicit invalidates"/>
+    <event event="0x4d" title="Scorpion" name="ICACHE_MISS" description="I-cache misses"/>
+    <event event="0x4e" title="Scorpion" name="ICACHE_ACCESS" description="I-cache accesses"/>
+    <event event="0x4f" title="Scorpion" name="ICACHE_CACHEREQ_L2" description="I-cache cacheable requests to L2"/>
+    <event event="0x50" title="Scorpion" name="ICACHE_NOCACHE_L2" description="I-cache non-cacheable requests to L2"/>
+    <event event="0x51" title="Scorpion" name="HIQUP_NOPED" description="Conditional instructions HIQUPs NOPed"/>
+    <event event="0x52" title="Scorpion" name="DATA_ABORT" description="Interrupts and Exceptions Data Abort"/>
+    <event event="0x53" title="Scorpion" name="IRQ" description="Interrupts and Exceptions IRQ"/>
+    <event event="0x54" title="Scorpion" name="FIQ" description="Interrupts and Exceptions FIQ"/>
+    <event event="0x55" title="Scorpion" name="ALL_EXCPT" description="Interrupts and Exceptions All interrupts"/>
+    <event event="0x56" title="Scorpion" name="UNDEF" description="Interrupts and Exceptions Undefined"/>
+    <event event="0x57" title="Scorpion" name="SVC" description="Interrupts and Exceptions SVC"/>
+    <event event="0x58" title="Scorpion" name="SMC" description="Interrupts and Exceptions SMC"/>
+    <event event="0x59" title="Scorpion" name="PREFETCH_ABORT" description="Interrupts and Exceptions Prefetch Abort"/>
+    <event event="0x5a" title="Scorpion" name="INDEX_CHECK" description="Interrupts and Exceptions Index Check"/>
+    <event event="0x5b" title="Scorpion" name="NULL_CHECK" description="Interrupts and Exceptions Null Check"/>
+    <event event="0x5c" title="Scorpion" name="EXPL_ICIALLU" description="I-cache and BTAC Invalidates Explicit ICIALLU"/>
+    <event event="0x5d" title="Scorpion" name="IMPL_ICIALLU" description="I-cache and BTAC Invalidates Implicit ICIALLU"/>
+    <event event="0x5e" title="Scorpion" name="NONICIALLU_BTAC_INV" description="I-cache and BTAC Invalidates Non-ICIALLU BTAC Invalidate"/>
+    <event event="0x5f" title="Scorpion" name="ICIMVAU_IMPL_ICIALLU" description="I-cache and BTAC Invalidates ICIMVAU-implied ICIALLU"/>
+    <event event="0x60" title="Scorpion" name="SPIPE_ONLY_CYCLES" description="Issue S-pipe only issue cycles"/>
+    <event event="0x61" title="Scorpion" name="XPIPE_ONLY_CYCLES" description="Issue X-pipe only issue cycles"/>
+    <event event="0x62" title="Scorpion" name="DUAL_CYCLES" description="Issue dual issue cycles"/>
+    <event event="0x63" title="Scorpion" name="DISPATCH_ANY_CYCLES" description="Dispatch any dispatch cycles"/>
+    <event event="0x64" title="Scorpion" name="FIFO_FULLBLK_CMT" description="Commits Trace FIFO full Blk CMT"/>
+    <event event="0x65" title="Scorpion" name="FAIL_COND_INST" description="Conditional instructions failing conditional instrs (excluding branches)"/>
+    <event event="0x66" title="Scorpion" name="PASS_COND_INST" description="Conditional instructions passing conditional instrs (excluding branches)"/>
+    <event event="0x67" title="Scorpion" name="ALLOW_VU_CLK" description="Unit Clock Gating Allow VU Clks"/>
+    <event event="0x68" title="Scorpion" name="VU_IDLE" description="Unit Clock Gating VU Idle"/>
+    <event event="0x69" title="Scorpion" name="ALLOW_L2_CLK" description="Unit Clock Gating Allow L2 Clks"/>
+    <event event="0x6a" title="Scorpion" name="L2_IDLE" description="Unit Clock Gating L2 Idle"/>
+    <event event="0x6b" title="Scorpion" name="DTLB_IMPL_INV_SCTLR_DACR" description="DTLB implicit invalidates writes to SCTLR and DACR"/>
+    <event event="0x6c" title="Scorpion" name="DTLB_EXPL_INV" description="DTLB explicit invalidates"/>
+    <event event="0x6d" title="Scorpion" name="DTLB_MISS" description="DTLB misses"/>
+    <event event="0x6e" title="Scorpion" name="DTLB_ACCESS" description="DTLB accesses"/>
+    <event event="0x6f" title="Scorpion" name="ITLB_MISS" description="ITLB misses"/>
+    <event event="0x70" title="Scorpion" name="ITLB_IMPL_INV" description="ITLB implicit ITLB invalidates"/>
+    <event event="0x71" title="Scorpion" name="ITLB_EXPL_INV" description="ITLB explicit ITLB invalidates"/>
+    <event event="0x72" title="Scorpion" name="UTLB_D_MISS" description="UTLB d-side misses"/>
+    <event event="0x73" title="Scorpion" name="UTLB_D_ACCESS" description="UTLB d-side accesses"/>
+    <event event="0x74" title="Scorpion" name="UTLB_I_MISS" description="UTLB i-side misses"/>
+    <event event="0x75" title="Scorpion" name="UTLB_I_ACCESS" description="UTLB i-side accesses"/>
+    <event event="0x76" title="Scorpion" name="UTLB_INV_ASID" description="UTLB invalidate by ASID"/>
+    <event event="0x77" title="Scorpion" name="UTLB_INV_MVA" description="UTLB invalidate by MVA"/>
+    <event event="0x78" title="Scorpion" name="UTLB_INV_ALL" description="UTLB invalidate all"/>
+    <event event="0x79" title="Scorpion" name="S2_HOLD_RDQ_UNAVAIL" description="S2 hold RDQ unavail"/>
+    <event event="0x7a" title="Scorpion" name="S2_HOLD" description="S2 hold"/>
+    <event event="0x7b" title="Scorpion" name="S2_HOLD_DEV_OP" description="S2 hold device op"/>
+    <event event="0x7c" title="Scorpion" name="S2_HOLD_ORDER" description="S2 hold strongly ordered op"/>
+    <event event="0x7d" title="Scorpion" name="S2_HOLD_BARRIER" description="S2 hold barrier"/>
+    <event event="0x7e" title="Scorpion" name="VIU_DUAL_CYCLE" description="Scorpion VIU dual cycle"/>
+    <event event="0x7f" title="Scorpion" name="VIU_SINGLE_CYCLE" description="Scorpion VIU single cycle"/>
+    <event event="0x80" title="Scorpion" name="VX_PIPE_WAR_STALL_CYCLES" description="Scorpion VX pipe WAR cycles"/>
+    <event event="0x81" title="Scorpion" name="VX_PIPE_WAW_STALL_CYCLES" description="Scorpion VX pipe WAW cycles"/>
+    <event event="0x82" title="Scorpion" name="VX_PIPE_RAW_STALL_CYCLES" description="Scorpion VX pipe RAW cycles"/>
+    <event event="0x83" title="Scorpion" name="VX_PIPE_LOAD_USE_STALL" description="Scorpion VX pipe load use stall"/>
+    <event event="0x84" title="Scorpion" name="VS_PIPE_WAR_STALL_CYCLES" description="Scorpion VS pipe WAR stall cycles"/>
+    <event event="0x85" title="Scorpion" name="VS_PIPE_WAW_STALL_CYCLES" description="Scorpion VS pipe WAW stall cycles"/>
+    <event event="0x86" title="Scorpion" name="VS_PIPE_RAW_STALL_CYCLES" description="Scorpion VS pipe RAW stall cycles"/>
+    <event event="0x87" title="Scorpion" name="EXCEPTIONS_INV_OPERATION" description="Scorpion invalid operation exceptions"/>
+    <event event="0x88" title="Scorpion" name="EXCEPTIONS_DIV_BY_ZERO" description="Scorpion divide by zero exceptions"/>
+    <event event="0x89" title="Scorpion" name="COND_INST_FAIL_VX_PIPE" description="Scorpion conditional instruction fail VX pipe"/>
+    <event event="0x8a" title="Scorpion" name="COND_INST_FAIL_VS_PIPE" description="Scorpion conditional instruction fail VS pipe"/>
+    <event event="0x8b" title="Scorpion" name="EXCEPTIONS_OVERFLOW" description="Scorpion overflow exceptions"/>
+    <event event="0x8c" title="Scorpion" name="EXCEPTIONS_UNDERFLOW" description="Scorpion underflow exceptions"/>
+    <event event="0x8d" title="Scorpion" name="EXCEPTIONS_DENORM" description="Scorpion denorm exceptions"/>
+    <event event="0x8e" title="Scorpion" name="BANK_AB_HIT" description="L2 hit rates bank A/B hits"/>
+    <event event="0x8f" title="Scorpion" name="BANK_AB_ACCESS" description="L2 hit rates bank A/B accesses"/>
+    <event event="0x90" title="Scorpion" name="BANK_CD_HIT" description="L2 hit rates bank C/D hits"/>
+    <event event="0x91" title="Scorpion" name="BANK_CD_ACCESS" description="L2 hit rates bank C/D accesses"/>
+    <event event="0x92" title="Scorpion" name="BANK_AB_DSIDE_HIT" description="L2 hit rates bank A/B d-side hits"/>
+    <event event="0x93" title="Scorpion" name="BANK_AB_DSIDE_ACCESS" description="L2 hit rates bank A/B d-side accesses"/>
+    <event event="0x94" title="Scorpion" name="BANK_CD_DSIDE_HIT" description="L2 hit rates bank C/D d-side hits"/>
+    <event event="0x95" title="Scorpion" name="BANK_CD_DSIDE_ACCESS" description="L2 hit rates bank C/D d-side accesses"/>
+    <event event="0x96" title="Scorpion" name="BANK_AB_ISIDE_HIT" description="L2 hit rates bank A/B i-side hits"/>
+    <event event="0x97" title="Scorpion" name="BANK_AB_ISIDE_ACCESS" description="L2 hit rates bank A/B i-side accesses"/>
+    <event event="0x98" title="Scorpion" name="BANK_CD_ISIDE_HIT" description="L2 hit rates bank C/D i-side hits"/>
+    <event event="0x99" title="Scorpion" name="BANK_CD_ISIDE_ACCESS" description="L2 hit rates bank C/D i-side accesses"/>
+    <event event="0x9a" title="Scorpion" name="ISIDE_RD_WAIT" description="fills and castouts cycles that i-side RD requests wait on data from bus"/>
+    <event event="0x9b" title="Scorpion" name="DSIDE_RD_WAIT" description="fills and castouts cycles that d-side RD requests wait on data from bus"/>
+    <event event="0x9c" title="Scorpion" name="BANK_BYPASS_WRITE" description="fills and castouts bank bypass writes"/>
+    <event event="0x9d" title="Scorpion" name="BANK_AB_NON_CASTOUT" description="fills and castouts bank A/B non-castout writes to bus"/>
+    <event event="0x9e" title="Scorpion" name="BANK_AB_L2_CASTOUT" description="fills and castouts bank A/B L2 castouts (granules)"/>
+    <event event="0x9f" title="Scorpion" name="BANK_CD_NON_CASTOUT" description="fills and castouts bank C/D non-castout writes to bus"/>
+    <event event="0xa0" title="Scorpion" name="BANK_CD_L2_CASTOUT" description="fills and castouts bank C/D L2 castouts (granules)"/>
+  </category>
diff --git a/tools/gator/daemon/events-ScorpionMP.xml b/tools/gator/daemon/events-ScorpionMP.xml
new file mode 100644
index 00000000000..c648ccefb28
--- /dev/null
+++ b/tools/gator/daemon/events-ScorpionMP.xml
@@ -0,0 +1,90 @@
+  <counter_set name="ScorpionMP_cnt" count="4"/>
+  <category name="ScorpionMP" counter_set="ScorpionMP_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ScorpionMP_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Program Counter" name="SW change" description="Software change of PC, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0e" title="Branch" name="Procedure Return" description="Procedure return architecturally executed (not by exceptions)"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x4c" title="Scorpion" name="ICACHE_EXPL_INV" description="I-cache explicit invalidates"/>
+    <event event="0x4d" title="Scorpion" name="ICACHE_MISS" description="I-cache misses"/>
+    <event event="0x4e" title="Scorpion" name="ICACHE_ACCESS" description="I-cache accesses"/>
+    <event event="0x4f" title="Scorpion" name="ICACHE_CACHEREQ_L2" description="I-cache cacheable requests to L2"/>
+    <event event="0x50" title="Scorpion" name="ICACHE_NOCACHE_L2" description="I-cache non-cacheable requests to L2"/>
+    <event event="0x51" title="Scorpion" name="HIQUP_NOPED" description="Conditional instructions HIQUPs NOPed"/>
+    <event event="0x52" title="Scorpion" name="DATA_ABORT" description="Interrupts and Exceptions Data Abort"/>
+    <event event="0x53" title="Scorpion" name="IRQ" description="Interrupts and Exceptions IRQ"/>
+    <event event="0x54" title="Scorpion" name="FIQ" description="Interrupts and Exceptions FIQ"/>
+    <event event="0x55" title="Scorpion" name="ALL_EXCPT" description="Interrupts and Exceptions All interrupts"/>
+    <event event="0x56" title="Scorpion" name="UNDEF" description="Interrupts and Exceptions Undefined"/>
+    <event event="0x57" title="Scorpion" name="SVC" description="Interrupts and Exceptions SVC"/>
+    <event event="0x58" title="Scorpion" name="SMC" description="Interrupts and Exceptions SMC"/>
+    <event event="0x59" title="Scorpion" name="PREFETCH_ABORT" description="Interrupts and Exceptions Prefetch Abort"/>
+    <event event="0x5a" title="Scorpion" name="INDEX_CHECK" description="Interrupts and Exceptions Index Check"/>
+    <event event="0x5b" title="Scorpion" name="NULL_CHECK" description="Interrupts and Exceptions Null Check"/>
+    <event event="0x5c" title="Scorpion" name="EXPL_ICIALLU" description="I-cache and BTAC Invalidates Explicit ICIALLU"/>
+    <event event="0x5d" title="Scorpion" name="IMPL_ICIALLU" description="I-cache and BTAC Invalidates Implicit ICIALLU"/>
+    <event event="0x5e" title="Scorpion" name="NONICIALLU_BTAC_INV" description="I-cache and BTAC Invalidates Non-ICIALLU BTAC Invalidate"/>
+    <event event="0x5f" title="Scorpion" name="ICIMVAU_IMPL_ICIALLU" description="I-cache and BTAC Invalidates ICIMVAU-implied ICIALLU"/>
+    <event event="0x60" title="Scorpion" name="SPIPE_ONLY_CYCLES" description="Issue S-pipe only issue cycles"/>
+    <event event="0x61" title="Scorpion" name="XPIPE_ONLY_CYCLES" description="Issue X-pipe only issue cycles"/>
+    <event event="0x62" title="Scorpion" name="DUAL_CYCLES" description="Issue dual issue cycles"/>
+    <event event="0x63" title="Scorpion" name="DISPATCH_ANY_CYCLES" description="Dispatch any dispatch cycles"/>
+    <event event="0x64" title="Scorpion" name="FIFO_FULLBLK_CMT" description="Commits Trace FIFO full Blk CMT"/>
+    <event event="0x65" title="Scorpion" name="FAIL_COND_INST" description="Conditional instructions failing conditional instrs (excluding branches)"/>
+    <event event="0x66" title="Scorpion" name="PASS_COND_INST" description="Conditional instructions passing conditional instrs (excluding branches)"/>
+    <event event="0x67" title="Scorpion" name="ALLOW_VU_CLK" description="Unit Clock Gating Allow VU Clks"/>
+    <event event="0x68" title="Scorpion" name="VU_IDLE" description="Unit Clock Gating VU Idle"/>
+    <event event="0x69" title="Scorpion" name="ALLOW_L2_CLK" description="Unit Clock Gating Allow L2 Clks"/>
+    <event event="0x6a" title="Scorpion" name="L2_IDLE" description="Unit Clock Gating L2 Idle"/>
+    <event event="0x6b" title="Scorpion" name="DTLB_IMPL_INV_SCTLR_DACR" description="DTLB implicit invalidates writes to SCTLR and DACR"/>
+    <event event="0x6c" title="Scorpion" name="DTLB_EXPL_INV" description="DTLB explicit invalidates"/>
+    <event event="0x6d" title="Scorpion" name="DTLB_MISS" description="DTLB misses"/>
+    <event event="0x6e" title="Scorpion" name="DTLB_ACCESS" description="DTLB accesses"/>
+    <event event="0x6f" title="Scorpion" name="ITLB_MISS" description="ITLB misses"/>
+    <event event="0x70" title="Scorpion" name="ITLB_IMPL_INV" description="ITLB implicit ITLB invalidates"/>
+    <event event="0x71" title="Scorpion" name="ITLB_EXPL_INV" description="ITLB explicit ITLB invalidates"/>
+    <event event="0x72" title="Scorpion" name="UTLB_D_MISS" description="UTLB d-side misses"/>
+    <event event="0x73" title="Scorpion" name="UTLB_D_ACCESS" description="UTLB d-side accesses"/>
+    <event event="0x74" title="Scorpion" name="UTLB_I_MISS" description="UTLB i-side misses"/>
+    <event event="0x75" title="Scorpion" name="UTLB_I_ACCESS" description="UTLB i-side accesses"/>
+    <event event="0x76" title="Scorpion" name="UTLB_INV_ASID" description="UTLB invalidate by ASID"/>
+    <event event="0x77" title="Scorpion" name="UTLB_INV_MVA" description="UTLB invalidate by MVA"/>
+    <event event="0x78" title="Scorpion" name="UTLB_INV_ALL" description="UTLB invalidate all"/>
+    <event event="0x79" title="Scorpion" name="S2_HOLD_RDQ_UNAVAIL" description="S2 hold RDQ unavail"/>
+    <event event="0x7a" title="Scorpion" name="S2_HOLD" description="S2 hold"/>
+    <event event="0x7b" title="Scorpion" name="S2_HOLD_DEV_OP" description="S2 hold device op"/>
+    <event event="0x7c" title="Scorpion" name="S2_HOLD_ORDER" description="S2 hold strongly ordered op"/>
+    <event event="0x7d" title="Scorpion" name="S2_HOLD_BARRIER" description="S2 hold barrier"/>
+    <event event="0x7e" title="Scorpion" name="VIU_DUAL_CYCLE" description="Scorpion VIU dual cycle"/>
+    <event event="0x7f" title="Scorpion" name="VIU_SINGLE_CYCLE" description="Scorpion VIU single cycle"/>
+    <event event="0x80" title="Scorpion" name="VX_PIPE_WAR_STALL_CYCLES" description="Scorpion VX pipe WAR cycles"/>
+    <event event="0x81" title="Scorpion" name="VX_PIPE_WAW_STALL_CYCLES" description="Scorpion VX pipe WAW cycles"/>
+    <event event="0x82" title="Scorpion" name="VX_PIPE_RAW_STALL_CYCLES" description="Scorpion VX pipe RAW cycles"/>
+    <event event="0x83" title="Scorpion" name="VX_PIPE_LOAD_USE_STALL" description="Scorpion VX pipe load use stall"/>
+    <event event="0x84" title="Scorpion" name="VS_PIPE_WAR_STALL_CYCLES" description="Scorpion VS pipe WAR stall cycles"/>
+    <event event="0x85" title="Scorpion" name="VS_PIPE_WAW_STALL_CYCLES" description="Scorpion VS pipe WAW stall cycles"/>
+    <event event="0x86" title="Scorpion" name="VS_PIPE_RAW_STALL_CYCLES" description="Scorpion VS pipe RAW stall cycles"/>
+    <event event="0x87" title="Scorpion" name="EXCEPTIONS_INV_OPERATION" description="Scorpion invalid operation exceptions"/>
+    <event event="0x88" title="Scorpion" name="EXCEPTIONS_DIV_BY_ZERO" description="Scorpion divide by zero exceptions"/>
+    <event event="0x89" title="Scorpion" name="COND_INST_FAIL_VX_PIPE" description="Scorpion conditional instruction fail VX pipe"/>
+    <event event="0x8a" title="Scorpion" name="COND_INST_FAIL_VS_PIPE" description="Scorpion conditional instruction fail VS pipe"/>
+    <event event="0x8b" title="Scorpion" name="EXCEPTIONS_OVERFLOW" description="Scorpion overflow exceptions"/>
+    <event event="0x8c" title="Scorpion" name="EXCEPTIONS_UNDERFLOW" description="Scorpion underflow exceptions"/>
+    <event event="0x8d" title="Scorpion" name="EXCEPTIONS_DENORM" description="Scorpion denorm exceptions"/>
+    <event event="0x8e" title="ScorpionMP" name="NUM_BARRIERS" description="Barriers"/>
+    <event event="0x8f" title="ScorpionMP" name="BARRIER_CYCLES" description="Barrier cycles"/>
+  </category>
diff --git a/tools/gator/daemon/events-atrace.xml b/tools/gator/daemon/events-atrace.xml
new file mode 100644
index 00000000000..432b6af70f7
--- /dev/null
+++ b/tools/gator/daemon/events-atrace.xml
@@ -0,0 +1,19 @@
+  <category name="Atrace">
+    <event counter="atrace_graphics" flag="0x2" title="Atrace" name="Graphics" description="Graphics"/>
+    <event counter="atrace_input" flag="0x4" title="Atrace" name="Input" description="Input"/>
+    <event counter="atrace_view" flag="0x8" title="Atrace" name="View" description="View"/>
+    <event counter="atrace_webview" flag="0x10" title="Atrace" name="Webview" description="Webview"/>
+    <event counter="atrace_window_manager" flag="0x20" title="Atrace" name="Window manager" description="Window manager"/>
+    <event counter="atrace_activity_manager" flag="0x40" title="Atrace" name="Activity manager" description="Activity manager"/>
+    <event counter="atrace_sync_manager" flag="0x80" title="Atrace" name="Sync manager" description="Sync manager"/>
+    <event counter="atrace_audio" flag="0x100" title="Atrace" name="Audio" description="Audio"/>
+    <event counter="atrace_video" flag="0x200" title="Atrace" name="Video" description="Video"/>
+    <event counter="atrace_camera" flag="0x400" title="Atrace" name="Camera" description="Camera"/>
+    <event counter="atrace_hal" flag="0x800" title="Atrace" name="Hal" description="Hal"/>
+    <event counter="atrace_app" flag="0x1000" title="Atrace" name="App" description="App"/>
+    <event counter="atrace_resources" flag="0x2000" title="Atrace" name="Resources" description="Resources"/>
+    <event counter="atrace_dalvik" flag="0x4000" title="Atrace" name="Dalvik" description="Dalvik"/>
+    <event counter="atrace_rs" flag="0x8000" title="Atrace" name="Rs" description="Rs"/>
+    <event counter="atrace_bionic" flag="0x10000" title="Atrace" name="Bionic" description="Bionic"/>
+    <event counter="atrace_power" flag="0x20000" title="Atrace" name="Power" description="Power"/>
+  </category>
diff --git a/tools/gator/daemon/events-ftrace.xml b/tools/gator/daemon/events-ftrace.xml
new file mode 100644
index 00000000000..17fad176b1e
--- /dev/null
+++ b/tools/gator/daemon/events-ftrace.xml
@@ -0,0 +1,24 @@
+  <category name="Ftrace">
+    <!--
+	ftrace counters require Linux 3.10 or later; if you do not see ftrace counters in counter configuration, please check your Linux version
+	'counter' attribute must start with ftrace_ and be unique
+	the regex item in () is the value shown or, if the parentheses are missing, the number of regex matches is counted
+	'enable' (optional) is the ftrace event to enable associated with the gator event
+	'tracepoint' (optional) same meaning as enable, but will use perf instead of ftrace when using user space gator
+	'arg' (optional) used in conjunction with 'tracepoint' to specify the value to show otherwise the number of tracepoint events is counted
+    -->
+    <!--
+    <event counter="ftrace_trace_marker_numbers" title="ftrace" name="trace_marker" regex="^tracing_mark_write: ([0-9]+)$" class="absolute" description="Numbers written to /sys/kernel/debug/tracing/trace_marker, ex: echo 42 > /sys/kernel/debug/tracing/trace_marker"/>
+    -->
+
+    <!-- ftrace counters -->
+    <event counter="ftrace_kmem_kmalloc" title="Kmem" name="kmalloc" regex="^kmalloc:.* bytes_alloc=([0-9]+) " tracepoint="kmem/kmalloc" arg="bytes_alloc" class="incident" description="Number of bytes allocated in the kernel using kmalloc"/>
+    <event counter="ftrace_ext4_ext4_da_write" title="Ext4" name="ext4_da_write" regex="^ext4_da_write_end:.* len ([0-9]+) " tracepoint="ext4/ext4_da_write_end" arg="len" class="incident" description="Number of bytes written to an ext4 filesystem"/>
+    <event counter="ftrace_f2fs_f2fs_write" title="F2FS" name="f2fs_write" regex="^f2fs_write_end:.* len ([0-9]+), " tracepoint="f2fs/f2fs_write_end" arg="len" class="incident" description="Number of bytes written to an f2fs filesystem"/>
+    <event counter="ftrace_power_clock_set_rate" title="Power" name="clock_set_rate" regex="^clock_set_rate:.* state=([0-9]+) " tracepoint="power/clock_set_rate" arg="state" class="absolute" description="Clock rate state"/>
+
+    <!-- counting ftrace counters -->
+    <event counter="ftrace_block_block_rq_complete" title="Block" name="block_rq_complete" regex="^block_rq_complete: " tracepoint="block/block_rq_complete" class="delta" description="Number of block IO operations completed by device driver"/>
+    <event counter="ftrace_block_block_rq_issue" title="Block" name="block_rq_issue" regex="^block_rq_issue: " tracepoint="block/block_rq_issue" class="delta" description="Number of block IO operations issued to device driver"/>
+    <event counter="ftrace_power_cpu_idle" title="Power" name="cpu_idle" regex="^cpu_idle: " tracepoint="power/cpu_idle" class="delta" description="Number of times cpu_idle is entered or exited"/>
+  </category>
diff --git a/tools/gator/daemon/events_footer.xml b/tools/gator/daemon/events_footer.xml
new file mode 100644
index 00000000000..cd2b44665ba
--- /dev/null
+++ b/tools/gator/daemon/events_footer.xml
@@ -0,0 +1 @@
+</events>
diff --git a/tools/gator/daemon/events_header.xml b/tools/gator/daemon/events_header.xml
new file mode 100644
index 00000000000..38ec4c03246
--- /dev/null
+++ b/tools/gator/daemon/events_header.xml
@@ -0,0 +1,2 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<events>
diff --git a/tools/gator/daemon/k/perf_event.h b/tools/gator/daemon/k/perf_event.h
new file mode 100644
index 00000000000..e886c48cadf
--- /dev/null
+++ b/tools/gator/daemon/k/perf_event.h
@@ -0,0 +1,792 @@
+/*
+ * Performance events:
+ *
+ *    Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
+ *    Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar
+ *    Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra
+ *
+ * Data type definitions, declarations, prototypes.
+ *
+ *    Started by: Thomas Gleixner and Ingo Molnar
+ *
+ * For licencing details see kernel-base/COPYING
+ */
+#ifndef _LINUX_PERF_EVENT_H
+#define _LINUX_PERF_EVENT_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+#include <asm/byteorder.h>
+
+/*
+ * User-space ABI bits:
+ */
+
+/*
+ * attr.type
+ */
+enum perf_type_id {
+	PERF_TYPE_HARDWARE			= 0,
+	PERF_TYPE_SOFTWARE			= 1,
+	PERF_TYPE_TRACEPOINT			= 2,
+	PERF_TYPE_HW_CACHE			= 3,
+	PERF_TYPE_RAW				= 4,
+	PERF_TYPE_BREAKPOINT			= 5,
+
+	PERF_TYPE_MAX,				/* non-ABI */
+};
+
+/*
+ * Generalized performance event event_id types, used by the
+ * attr.event_id parameter of the sys_perf_event_open()
+ * syscall:
+ */
+enum perf_hw_id {
+	/*
+	 * Common hardware events, generalized by the kernel:
+	 */
+	PERF_COUNT_HW_CPU_CYCLES		= 0,
+	PERF_COUNT_HW_INSTRUCTIONS		= 1,
+	PERF_COUNT_HW_CACHE_REFERENCES		= 2,
+	PERF_COUNT_HW_CACHE_MISSES		= 3,
+	PERF_COUNT_HW_BRANCH_INSTRUCTIONS	= 4,
+	PERF_COUNT_HW_BRANCH_MISSES		= 5,
+	PERF_COUNT_HW_BUS_CYCLES		= 6,
+	PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	= 7,
+	PERF_COUNT_HW_STALLED_CYCLES_BACKEND	= 8,
+	PERF_COUNT_HW_REF_CPU_CYCLES		= 9,
+
+	PERF_COUNT_HW_MAX,			/* non-ABI */
+};
+
+/*
+ * Generalized hardware cache events:
+ *
+ *       { L1-D, L1-I, LLC, ITLB, DTLB, BPU, NODE } x
+ *       { read, write, prefetch } x
+ *       { accesses, misses }
+ */
+enum perf_hw_cache_id {
+	PERF_COUNT_HW_CACHE_L1D			= 0,
+	PERF_COUNT_HW_CACHE_L1I			= 1,
+	PERF_COUNT_HW_CACHE_LL			= 2,
+	PERF_COUNT_HW_CACHE_DTLB		= 3,
+	PERF_COUNT_HW_CACHE_ITLB		= 4,
+	PERF_COUNT_HW_CACHE_BPU			= 5,
+	PERF_COUNT_HW_CACHE_NODE		= 6,
+
+	PERF_COUNT_HW_CACHE_MAX,		/* non-ABI */
+};
+
+enum perf_hw_cache_op_id {
+	PERF_COUNT_HW_CACHE_OP_READ		= 0,
+	PERF_COUNT_HW_CACHE_OP_WRITE		= 1,
+	PERF_COUNT_HW_CACHE_OP_PREFETCH		= 2,
+
+	PERF_COUNT_HW_CACHE_OP_MAX,		/* non-ABI */
+};
+
+enum perf_hw_cache_op_result_id {
+	PERF_COUNT_HW_CACHE_RESULT_ACCESS	= 0,
+	PERF_COUNT_HW_CACHE_RESULT_MISS		= 1,
+
+	PERF_COUNT_HW_CACHE_RESULT_MAX,		/* non-ABI */
+};
+
+/*
+ * Special "software" events provided by the kernel, even if the hardware
+ * does not support performance events. These events measure various
+ * physical and sw events of the kernel (and allow the profiling of them as
+ * well):
+ */
+enum perf_sw_ids {
+	PERF_COUNT_SW_CPU_CLOCK			= 0,
+	PERF_COUNT_SW_TASK_CLOCK		= 1,
+	PERF_COUNT_SW_PAGE_FAULTS		= 2,
+	PERF_COUNT_SW_CONTEXT_SWITCHES		= 3,
+	PERF_COUNT_SW_CPU_MIGRATIONS		= 4,
+	PERF_COUNT_SW_PAGE_FAULTS_MIN		= 5,
+	PERF_COUNT_SW_PAGE_FAULTS_MAJ		= 6,
+	PERF_COUNT_SW_ALIGNMENT_FAULTS		= 7,
+	PERF_COUNT_SW_EMULATION_FAULTS		= 8,
+	PERF_COUNT_SW_DUMMY			= 9,
+
+	PERF_COUNT_SW_MAX,			/* non-ABI */
+};
+
+/*
+ * Bits that can be set in attr.sample_type to request information
+ * in the overflow packets.
+ */
+enum perf_event_sample_format {
+	PERF_SAMPLE_IP				= 1U << 0,
+	PERF_SAMPLE_TID				= 1U << 1,
+	PERF_SAMPLE_TIME			= 1U << 2,
+	PERF_SAMPLE_ADDR			= 1U << 3,
+	PERF_SAMPLE_READ			= 1U << 4,
+	PERF_SAMPLE_CALLCHAIN			= 1U << 5,
+	PERF_SAMPLE_ID				= 1U << 6,
+	PERF_SAMPLE_CPU				= 1U << 7,
+	PERF_SAMPLE_PERIOD			= 1U << 8,
+	PERF_SAMPLE_STREAM_ID			= 1U << 9,
+	PERF_SAMPLE_RAW				= 1U << 10,
+	PERF_SAMPLE_BRANCH_STACK		= 1U << 11,
+	PERF_SAMPLE_REGS_USER			= 1U << 12,
+	PERF_SAMPLE_STACK_USER			= 1U << 13,
+	PERF_SAMPLE_WEIGHT			= 1U << 14,
+	PERF_SAMPLE_DATA_SRC			= 1U << 15,
+	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
+
+	PERF_SAMPLE_MAX = 1U << 17,		/* non-ABI */
+};
+
+/*
+ * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set
+ *
+ * If the user does not pass priv level information via branch_sample_type,
+ * the kernel uses the event's priv level. Branch and event priv levels do
+ * not have to match. Branch priv level is checked for permissions.
+ *
+ * The branch types can be combined, however BRANCH_ANY covers all types
+ * of branches and therefore it supersedes all the other types.
+ */
+enum perf_branch_sample_type {
+	PERF_SAMPLE_BRANCH_USER		= 1U << 0, /* user branches */
+	PERF_SAMPLE_BRANCH_KERNEL	= 1U << 1, /* kernel branches */
+	PERF_SAMPLE_BRANCH_HV		= 1U << 2, /* hypervisor branches */
+
+	PERF_SAMPLE_BRANCH_ANY		= 1U << 3, /* any branch types */
+	PERF_SAMPLE_BRANCH_ANY_CALL	= 1U << 4, /* any call branch */
+	PERF_SAMPLE_BRANCH_ANY_RETURN	= 1U << 5, /* any return branch */
+	PERF_SAMPLE_BRANCH_IND_CALL	= 1U << 6, /* indirect calls */
+	PERF_SAMPLE_BRANCH_ABORT_TX	= 1U << 7, /* transaction aborts */
+	PERF_SAMPLE_BRANCH_IN_TX	= 1U << 8, /* in transaction */
+	PERF_SAMPLE_BRANCH_NO_TX	= 1U << 9, /* not in transaction */
+
+	PERF_SAMPLE_BRANCH_MAX		= 1U << 10, /* non-ABI */
+};
+
+#define PERF_SAMPLE_BRANCH_PLM_ALL \
+	(PERF_SAMPLE_BRANCH_USER|\
+	 PERF_SAMPLE_BRANCH_KERNEL|\
+	 PERF_SAMPLE_BRANCH_HV)
+
+/*
+ * Values to determine ABI of the registers dump.
+ */
+enum perf_sample_regs_abi {
+	PERF_SAMPLE_REGS_ABI_NONE	= 0,
+	PERF_SAMPLE_REGS_ABI_32		= 1,
+	PERF_SAMPLE_REGS_ABI_64		= 2,
+};
+
+/*
+ * The format of the data returned by read() on a perf event fd,
+ * as specified by attr.read_format:
+ *
+ * struct read_format {
+ *	{ u64		value;
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
+ *	  { u64		id;           } && PERF_FORMAT_ID
+ *	} && !PERF_FORMAT_GROUP
+ *
+ *	{ u64		nr;
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
+ *	  { u64		value;
+ *	    { u64	id;           } && PERF_FORMAT_ID
+ *	  }		cntr[nr];
+ *	} && PERF_FORMAT_GROUP
+ * };
+ */
+enum perf_event_read_format {
+	PERF_FORMAT_TOTAL_TIME_ENABLED		= 1U << 0,
+	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
+	PERF_FORMAT_ID				= 1U << 2,
+	PERF_FORMAT_GROUP			= 1U << 3,
+
+	PERF_FORMAT_MAX = 1U << 4,		/* non-ABI */
+};
+
+#define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */
+#define PERF_ATTR_SIZE_VER1	72	/* add: config2 */
+#define PERF_ATTR_SIZE_VER2	80	/* add: branch_sample_type */
+#define PERF_ATTR_SIZE_VER3	96	/* add: sample_regs_user */
+					/* add: sample_stack_user */
+
+/*
+ * Hardware event_id to monitor via a performance monitoring event:
+ */
+struct perf_event_attr {
+
+	/*
+	 * Major type: hardware/software/tracepoint/etc.
+	 */
+	__u32			type;
+
+	/*
+	 * Size of the attr structure, for fwd/bwd compat.
+	 */
+	__u32			size;
+
+	/*
+	 * Type specific configuration information.
+	 */
+	__u64			config;
+
+	union {
+		__u64		sample_period;
+		__u64		sample_freq;
+	};
+
+	__u64			sample_type;
+	__u64			read_format;
+
+	__u64			disabled       :  1, /* off by default        */
+				inherit	       :  1, /* children inherit it   */
+				pinned	       :  1, /* must always be on PMU */
+				exclusive      :  1, /* only group on PMU     */
+				exclude_user   :  1, /* don't count user      */
+				exclude_kernel :  1, /* ditto kernel          */
+				exclude_hv     :  1, /* ditto hypervisor      */
+				exclude_idle   :  1, /* don't count when idle */
+				mmap           :  1, /* include mmap data     */
+				comm	       :  1, /* include comm data     */
+				freq           :  1, /* use freq, not period  */
+				inherit_stat   :  1, /* per task counts       */
+				enable_on_exec :  1, /* next exec enables     */
+				task           :  1, /* trace fork/exit       */
+				watermark      :  1, /* wakeup_watermark      */
+				/*
+				 * precise_ip:
+				 *
+				 *  0 - SAMPLE_IP can have arbitrary skid
+				 *  1 - SAMPLE_IP must have constant skid
+				 *  2 - SAMPLE_IP requested to have 0 skid
+				 *  3 - SAMPLE_IP must have 0 skid
+				 *
+				 *  See also PERF_RECORD_MISC_EXACT_IP
+				 */
+				precise_ip     :  2, /* skid constraint       */
+				mmap_data      :  1, /* non-exec mmap data    */
+				sample_id_all  :  1, /* sample_type all events */
+
+				exclude_host   :  1, /* don't count in host   */
+				exclude_guest  :  1, /* don't count in guest  */
+
+				exclude_callchain_kernel : 1, /* exclude kernel callchains */
+				exclude_callchain_user   : 1, /* exclude user callchains */
+				mmap2          :  1, /* include mmap with inode data     */
+
+				__reserved_1   : 40;
+
+	union {
+		__u32		wakeup_events;	  /* wakeup every n events */
+		__u32		wakeup_watermark; /* bytes before wakeup   */
+	};
+
+	__u32			bp_type;
+	union {
+		__u64		bp_addr;
+		__u64		config1; /* extension of config */
+	};
+	union {
+		__u64		bp_len;
+		__u64		config2; /* extension of config1 */
+	};
+	__u64	branch_sample_type; /* enum perf_branch_sample_type */
+
+	/*
+	 * Defines set of user regs to dump on samples.
+	 * See asm/perf_regs.h for details.
+	 */
+	__u64	sample_regs_user;
+
+	/*
+	 * Defines size of the user stack to dump on samples.
+	 */
+	__u32	sample_stack_user;
+
+	/* Align to u64. */
+	__u32	__reserved_2;
+};
+
+#define perf_flags(attr)	(*(&(attr)->read_format + 1))
+
+/*
+ * Ioctls that can be done on a perf event fd:
+ */
+#define PERF_EVENT_IOC_ENABLE		_IO ('$', 0)
+#define PERF_EVENT_IOC_DISABLE		_IO ('$', 1)
+#define PERF_EVENT_IOC_REFRESH		_IO ('$', 2)
+#define PERF_EVENT_IOC_RESET		_IO ('$', 3)
+#define PERF_EVENT_IOC_PERIOD		_IOW('$', 4, __u64)
+#define PERF_EVENT_IOC_SET_OUTPUT	_IO ('$', 5)
+#define PERF_EVENT_IOC_SET_FILTER	_IOW('$', 6, char *)
+#define PERF_EVENT_IOC_ID		_IOR('$', 7, __u64 *)
+
+enum perf_event_ioc_flags {
+	PERF_IOC_FLAG_GROUP		= 1U << 0,
+};
+
+/*
+ * Structure of the page that can be mapped via mmap
+ */
+struct perf_event_mmap_page {
+	__u32	version;		/* version number of this structure */
+	__u32	compat_version;		/* lowest version this is compat with */
+
+	/*
+	 * Bits needed to read the hw events in user-space.
+	 *
+	 *   u32 seq, time_mult, time_shift, idx, width;
+	 *   u64 count, enabled, running;
+	 *   u64 cyc, time_offset;
+	 *   s64 pmc = 0;
+	 *
+	 *   do {
+	 *     seq = pc->lock;
+	 *     barrier()
+	 *
+	 *     enabled = pc->time_enabled;
+	 *     running = pc->time_running;
+	 *
+	 *     if (pc->cap_usr_time && enabled != running) {
+	 *       cyc = rdtsc();
+	 *       time_offset = pc->time_offset;
+	 *       time_mult   = pc->time_mult;
+	 *       time_shift  = pc->time_shift;
+	 *     }
+	 *
+	 *     idx = pc->index;
+	 *     count = pc->offset;
+	 *     if (pc->cap_usr_rdpmc && idx) {
+	 *       width = pc->pmc_width;
+	 *       pmc = rdpmc(idx - 1);
+	 *     }
+	 *
+	 *     barrier();
+	 *   } while (pc->lock != seq);
+	 *
+	 * NOTE: for obvious reason this only works on self-monitoring
+	 *       processes.
+	 */
+	__u32	lock;			/* seqlock for synchronization */
+	__u32	index;			/* hardware event identifier */
+	__s64	offset;			/* add to hardware event value */
+	__u64	time_enabled;		/* time event active */
+	__u64	time_running;		/* time event on cpu */
+	union {
+		__u64	capabilities;
+		struct {
+			__u64	cap_bit0		: 1, /* Always 0, deprecated, see commit 860f085b74e9 */
+				cap_bit0_is_deprecated	: 1, /* Always 1, signals that bit 0 is zero */
+
+				cap_user_rdpmc		: 1, /* The RDPMC instruction can be used to read counts */
+				cap_user_time		: 1, /* The time_* fields are used */
+				cap_user_time_zero	: 1, /* The time_zero field is used */
+				cap_____res		: 59;
+		};
+	};
+
+	/*
+	 * If cap_usr_rdpmc this field provides the bit-width of the value
+	 * read using the rdpmc() or equivalent instruction. This can be used
+	 * to sign extend the result like:
+	 *
+	 *   pmc <<= 64 - width;
+	 *   pmc >>= 64 - width; // signed shift right
+	 *   count += pmc;
+	 */
+	__u16	pmc_width;
+
+	/*
+	 * If cap_usr_time the below fields can be used to compute the time
+	 * delta since time_enabled (in ns) using rdtsc or similar.
+	 *
+	 *   u64 quot, rem;
+	 *   u64 delta;
+	 *
+	 *   quot = (cyc >> time_shift);
+	 *   rem = cyc & ((1 << time_shift) - 1);
+	 *   delta = time_offset + quot * time_mult +
+	 *              ((rem * time_mult) >> time_shift);
+	 *
+	 * Where time_offset,time_mult,time_shift and cyc are read in the
+	 * seqcount loop described above. This delta can then be added to
+	 * enabled and possible running (if idx), improving the scaling:
+	 *
+	 *   enabled += delta;
+	 *   if (idx)
+	 *     running += delta;
+	 *
+	 *   quot = count / running;
+	 *   rem  = count % running;
+	 *   count = quot * enabled + (rem * enabled) / running;
+	 */
+	__u16	time_shift;
+	__u32	time_mult;
+	__u64	time_offset;
+	/*
+	 * If cap_usr_time_zero, the hardware clock (e.g. TSC) can be calculated
+	 * from sample timestamps.
+	 *
+	 *   time = timestamp - time_zero;
+	 *   quot = time / time_mult;
+	 *   rem  = time % time_mult;
+	 *   cyc = (quot << time_shift) + (rem << time_shift) / time_mult;
+	 *
+	 * And vice versa:
+	 *
+	 *   quot = cyc >> time_shift;
+	 *   rem  = cyc & ((1 << time_shift) - 1);
+	 *   timestamp = time_zero + quot * time_mult +
+	 *               ((rem * time_mult) >> time_shift);
+	 */
+	__u64	time_zero;
+	__u32	size;			/* Header size up to __reserved[] fields. */
+
+		/*
+		 * Hole for extension of the self monitor capabilities
+		 */
+
+	__u8	__reserved[118*8+4];	/* align to 1k. */
+
+	/*
+	 * Control data for the mmap() data buffer.
+	 *
+	 * User-space reading the @data_head value should issue an smp_rmb(),
+	 * after reading this value.
+	 *
+	 * When the mapping is PROT_WRITE the @data_tail value should be
+	 * written by userspace to reflect the last read data, after issueing
+	 * an smp_mb() to separate the data read from the ->data_tail store.
+	 * In this case the kernel will not over-write unread data.
+	 *
+	 * See perf_output_put_handle() for the data ordering.
+	 */
+	__u64   data_head;		/* head in the data section */
+	__u64	data_tail;		/* user-space written tail */
+};
+
+#define PERF_RECORD_MISC_CPUMODE_MASK		(7 << 0)
+#define PERF_RECORD_MISC_CPUMODE_UNKNOWN	(0 << 0)
+#define PERF_RECORD_MISC_KERNEL			(1 << 0)
+#define PERF_RECORD_MISC_USER			(2 << 0)
+#define PERF_RECORD_MISC_HYPERVISOR		(3 << 0)
+#define PERF_RECORD_MISC_GUEST_KERNEL		(4 << 0)
+#define PERF_RECORD_MISC_GUEST_USER		(5 << 0)
+
+#define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
+/*
+ * Indicates that the content of PERF_SAMPLE_IP points to
+ * the actual instruction that triggered the event. See also
+ * perf_event_attr::precise_ip.
+ */
+#define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
+/*
+ * Reserve the last bit to indicate some extended misc field
+ */
+#define PERF_RECORD_MISC_EXT_RESERVED		(1 << 15)
+
+struct perf_event_header {
+	__u32	type;
+	__u16	misc;
+	__u16	size;
+};
+
+enum perf_event_type {
+
+	/*
+	 * If perf_event_attr.sample_id_all is set then all event types will
+	 * have the sample_type selected fields related to where/when
+	 * (identity) an event took place (TID, TIME, ID, STREAM_ID, CPU,
+	 * IDENTIFIER) described in PERF_RECORD_SAMPLE below, it will be stashed
+	 * just after the perf_event_header and the fields already present for
+	 * the existing fields, i.e. at the end of the payload. That way a newer
+	 * perf.data file will be supported by older perf tools, with these new
+	 * optional fields being ignored.
+	 *
+	 * struct sample_id {
+	 * 	{ u32			pid, tid; } && PERF_SAMPLE_TID
+	 * 	{ u64			time;     } && PERF_SAMPLE_TIME
+	 * 	{ u64			id;       } && PERF_SAMPLE_ID
+	 * 	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
+	 * 	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
+	 * } && perf_event_attr::sample_id_all
+	 *
+	 * Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.  The
+	 * advantage of PERF_SAMPLE_IDENTIFIER is that its position is fixed
+	 * relative to header.size.
+	 */
+
+	/*
+	 * The MMAP events record the PROT_EXEC mappings so that we can
+	 * correlate userspace IPs to code. They have the following structure:
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	u64				addr;
+	 *	u64				len;
+	 *	u64				pgoff;
+	 *	char				filename[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_MMAP			= 1,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				id;
+	 *	u64				lost;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_LOST			= 2,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	char				comm[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_COMM			= 3,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, ppid;
+	 *	u32				tid, ptid;
+	 *	u64				time;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_EXIT			= 4,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				time;
+	 *	u64				id;
+	 *	u64				stream_id;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_THROTTLE			= 5,
+	PERF_RECORD_UNTHROTTLE			= 6,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, ppid;
+	 *	u32				tid, ptid;
+	 *	u64				time;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_FORK			= 7,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, tid;
+	 *
+	 *	struct read_format		values;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_READ			= 8,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	#
+	 *	# Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.
+	 *	# The advantage of PERF_SAMPLE_IDENTIFIER is that its position
+	 *	# is fixed relative to header.
+	 *	#
+	 *
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
+	 *	{ u64			ip;	  } && PERF_SAMPLE_IP
+	 *	{ u32			pid, tid; } && PERF_SAMPLE_TID
+	 *	{ u64			time;     } && PERF_SAMPLE_TIME
+	 *	{ u64			addr;     } && PERF_SAMPLE_ADDR
+	 *	{ u64			id;	  } && PERF_SAMPLE_ID
+	 *	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
+	 *	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 *	{ u64			period;   } && PERF_SAMPLE_PERIOD
+	 *
+	 *	{ struct read_format	values;	  } && PERF_SAMPLE_READ
+	 *
+	 *	{ u64			nr,
+	 *	  u64			ips[nr];  } && PERF_SAMPLE_CALLCHAIN
+	 *
+	 *	#
+	 *	# The RAW record below is opaque data wrt the ABI
+	 *	#
+	 *	# That is, the ABI doesn't make any promises wrt to
+	 *	# the stability of its content, it may vary depending
+	 *	# on event, hardware, kernel version and phase of
+	 *	# the moon.
+	 *	#
+	 *	# In other words, PERF_SAMPLE_RAW contents are not an ABI.
+	 *	#
+	 *
+	 *	{ u32			size;
+	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
+	 *
+	 *	{ u64                   nr;
+	 *        { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+	 *
+	 * 	{ u64			abi; # enum perf_sample_regs_abi
+	 * 	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
+	 *
+	 * 	{ u64			size;
+	 * 	  char			data[size];
+	 * 	  u64			dyn_size; } && PERF_SAMPLE_STACK_USER
+	 *
+	 *	{ u64			weight;   } && PERF_SAMPLE_WEIGHT
+	 *	{ u64			data_src; } && PERF_SAMPLE_DATA_SRC
+	 * };
+	 */
+	PERF_RECORD_SAMPLE			= 9,
+
+	/*
+	 * The MMAP2 records are an augmented version of MMAP, they add
+	 * maj, min, ino numbers to be used to uniquely identify each mapping
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	u64				addr;
+	 *	u64				len;
+	 *	u64				pgoff;
+	 *	u32				maj;
+	 *	u32				min;
+	 *	u64				ino;
+	 *	u64				ino_generation;
+	 *	char				filename[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_MMAP2			= 10,
+
+	PERF_RECORD_MAX,			/* non-ABI */
+};
+
+#define PERF_MAX_STACK_DEPTH		127
+
+enum perf_callchain_context {
+	PERF_CONTEXT_HV			= (__u64)-32,
+	PERF_CONTEXT_KERNEL		= (__u64)-128,
+	PERF_CONTEXT_USER		= (__u64)-512,
+
+	PERF_CONTEXT_GUEST		= (__u64)-2048,
+	PERF_CONTEXT_GUEST_KERNEL	= (__u64)-2176,
+	PERF_CONTEXT_GUEST_USER		= (__u64)-2560,
+
+	PERF_CONTEXT_MAX		= (__u64)-4095,
+};
+
+#define PERF_FLAG_FD_NO_GROUP		(1U << 0)
+#define PERF_FLAG_FD_OUTPUT		(1U << 1)
+#define PERF_FLAG_PID_CGROUP		(1U << 2) /* pid=cgroup id, per-cpu mode only */
+
+union perf_mem_data_src {
+	__u64 val;
+	struct {
+		__u64   mem_op:5,	/* type of opcode */
+			mem_lvl:14,	/* memory hierarchy level */
+			mem_snoop:5,	/* snoop mode */
+			mem_lock:2,	/* lock instr */
+			mem_dtlb:7,	/* tlb access */
+			mem_rsvd:31;
+	};
+};
+
+/* type of opcode (load/store/prefetch,code) */
+#define PERF_MEM_OP_NA		0x01 /* not available */
+#define PERF_MEM_OP_LOAD	0x02 /* load instruction */
+#define PERF_MEM_OP_STORE	0x04 /* store instruction */
+#define PERF_MEM_OP_PFETCH	0x08 /* prefetch */
+#define PERF_MEM_OP_EXEC	0x10 /* code (execution) */
+#define PERF_MEM_OP_SHIFT	0
+
+/* memory hierarchy (memory level, hit or miss) */
+#define PERF_MEM_LVL_NA		0x01  /* not available */
+#define PERF_MEM_LVL_HIT	0x02  /* hit level */
+#define PERF_MEM_LVL_MISS	0x04  /* miss level  */
+#define PERF_MEM_LVL_L1		0x08  /* L1 */
+#define PERF_MEM_LVL_LFB	0x10  /* Line Fill Buffer */
+#define PERF_MEM_LVL_L2		0x20  /* L2 */
+#define PERF_MEM_LVL_L3		0x40  /* L3 */
+#define PERF_MEM_LVL_LOC_RAM	0x80  /* Local DRAM */
+#define PERF_MEM_LVL_REM_RAM1	0x100 /* Remote DRAM (1 hop) */
+#define PERF_MEM_LVL_REM_RAM2	0x200 /* Remote DRAM (2 hops) */
+#define PERF_MEM_LVL_REM_CCE1	0x400 /* Remote Cache (1 hop) */
+#define PERF_MEM_LVL_REM_CCE2	0x800 /* Remote Cache (2 hops) */
+#define PERF_MEM_LVL_IO		0x1000 /* I/O memory */
+#define PERF_MEM_LVL_UNC	0x2000 /* Uncached memory */
+#define PERF_MEM_LVL_SHIFT	5
+
+/* snoop mode */
+#define PERF_MEM_SNOOP_NA	0x01 /* not available */
+#define PERF_MEM_SNOOP_NONE	0x02 /* no snoop */
+#define PERF_MEM_SNOOP_HIT	0x04 /* snoop hit */
+#define PERF_MEM_SNOOP_MISS	0x08 /* snoop miss */
+#define PERF_MEM_SNOOP_HITM	0x10 /* snoop hit modified */
+#define PERF_MEM_SNOOP_SHIFT	19
+
+/* locked instruction */
+#define PERF_MEM_LOCK_NA	0x01 /* not available */
+#define PERF_MEM_LOCK_LOCKED	0x02 /* locked transaction */
+#define PERF_MEM_LOCK_SHIFT	24
+
+/* TLB access */
+#define PERF_MEM_TLB_NA		0x01 /* not available */
+#define PERF_MEM_TLB_HIT	0x02 /* hit level */
+#define PERF_MEM_TLB_MISS	0x04 /* miss level */
+#define PERF_MEM_TLB_L1		0x08 /* L1 */
+#define PERF_MEM_TLB_L2		0x10 /* L2 */
+#define PERF_MEM_TLB_WK		0x20 /* Hardware Walker*/
+#define PERF_MEM_TLB_OS		0x40 /* OS fault handler */
+#define PERF_MEM_TLB_SHIFT	26
+
+#define PERF_MEM_S(a, s) \
+	(((u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
+
+/*
+ * single taken branch record layout:
+ *
+ *      from: source instruction (may not always be a branch insn)
+ *        to: branch target
+ *   mispred: branch target was mispredicted
+ * predicted: branch target was predicted
+ *
+ * support for mispred, predicted is optional. In case it
+ * is not supported mispred = predicted = 0.
+ *
+ *     in_tx: running in a hardware transaction
+ *     abort: aborting a hardware transaction
+ */
+struct perf_branch_entry {
+	__u64	from;
+	__u64	to;
+	__u64	mispred:1,  /* target mispredicted */
+		predicted:1,/* target predicted */
+		in_tx:1,    /* in transaction */
+		abort:1,    /* transaction abort */
+		reserved:60;
+};
+
+#endif /* _LINUX_PERF_EVENT_H */
diff --git a/tools/gator/daemon/libsensors/COPYING.LGPL b/tools/gator/daemon/libsensors/COPYING.LGPL
new file mode 100644
index 00000000000..4362b49151d
--- /dev/null
+++ b/tools/gator/daemon/libsensors/COPYING.LGPL
@@ -0,0 +1,502 @@
+                  GNU LESSER GENERAL PUBLIC LICENSE
+                       Version 2.1, February 1999
+
+ Copyright (C) 1991, 1999 Free Software Foundation, Inc.
+ 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+[This is the first released version of the Lesser GPL.  It also counts
+ as the successor of the GNU Library Public License, version 2, hence
+ the version number 2.1.]
+
+                            Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+Licenses are intended to guarantee your freedom to share and change
+free software--to make sure the software is free for all its users.
+
+  This license, the Lesser General Public License, applies to some
+specially designated software packages--typically libraries--of the
+Free Software Foundation and other authors who decide to use it.  You
+can use it too, but we suggest you first think carefully about whether
+this license or the ordinary General Public License is the better
+strategy to use in any particular case, based on the explanations below.
+
+  When we speak of free software, we are referring to freedom of use,
+not price.  Our General Public Licenses are designed to make sure that
+you have the freedom to distribute copies of free software (and charge
+for this service if you wish); that you receive source code or can get
+it if you want it; that you can change the software and use pieces of
+it in new free programs; and that you are informed that you can do
+these things.
+
+  To protect your rights, we need to make restrictions that forbid
+distributors to deny you these rights or to ask you to surrender these
+rights.  These restrictions translate to certain responsibilities for
+you if you distribute copies of the library or if you modify it.
+
+  For example, if you distribute copies of the library, whether gratis
+or for a fee, you must give the recipients all the rights that we gave
+you.  You must make sure that they, too, receive or can get the source
+code.  If you link other code with the library, you must provide
+complete object files to the recipients, so that they can relink them
+with the library after making changes to the library and recompiling
+it.  And you must show them these terms so they know their rights.
+
+  We protect your rights with a two-step method: (1) we copyright the
+library, and (2) we offer you this license, which gives you legal
+permission to copy, distribute and/or modify the library.
+
+  To protect each distributor, we want to make it very clear that
+there is no warranty for the free library.  Also, if the library is
+modified by someone else and passed on, the recipients should know
+that what they have is not the original version, so that the original
+author's reputation will not be affected by problems that might be
+introduced by others.
+
+  Finally, software patents pose a constant threat to the existence of
+any free program.  We wish to make sure that a company cannot
+effectively restrict the users of a free program by obtaining a
+restrictive license from a patent holder.  Therefore, we insist that
+any patent license obtained for a version of the library must be
+consistent with the full freedom of use specified in this license.
+
+  Most GNU software, including some libraries, is covered by the
+ordinary GNU General Public License.  This license, the GNU Lesser
+General Public License, applies to certain designated libraries, and
+is quite different from the ordinary General Public License.  We use
+this license for certain libraries in order to permit linking those
+libraries into non-free programs.
+
+  When a program is linked with a library, whether statically or using
+a shared library, the combination of the two is legally speaking a
+combined work, a derivative of the original library.  The ordinary
+General Public License therefore permits such linking only if the
+entire combination fits its criteria of freedom.  The Lesser General
+Public License permits more lax criteria for linking other code with
+the library.
+
+  We call this license the "Lesser" General Public License because it
+does Less to protect the user's freedom than the ordinary General
+Public License.  It also provides other free software developers Less
+of an advantage over competing non-free programs.  These disadvantages
+are the reason we use the ordinary General Public License for many
+libraries.  However, the Lesser license provides advantages in certain
+special circumstances.
+
+  For example, on rare occasions, there may be a special need to
+encourage the widest possible use of a certain library, so that it becomes
+a de-facto standard.  To achieve this, non-free programs must be
+allowed to use the library.  A more frequent case is that a free
+library does the same job as widely used non-free libraries.  In this
+case, there is little to gain by limiting the free library to free
+software only, so we use the Lesser General Public License.
+
+  In other cases, permission to use a particular library in non-free
+programs enables a greater number of people to use a large body of
+free software.  For example, permission to use the GNU C Library in
+non-free programs enables many more people to use the whole GNU
+operating system, as well as its variant, the GNU/Linux operating
+system.
+
+  Although the Lesser General Public License is Less protective of the
+users' freedom, it does ensure that the user of a program that is
+linked with the Library has the freedom and the wherewithal to run
+that program using a modified version of the Library.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.  Pay close attention to the difference between a
+"work based on the library" and a "work that uses the library".  The
+former contains code derived from the library, whereas the latter must
+be combined with the library in order to run.
+
+                  GNU LESSER GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License Agreement applies to any software library or other
+program which contains a notice placed by the copyright holder or
+other authorized party saying it may be distributed under the terms of
+this Lesser General Public License (also called "this License").
+Each licensee is addressed as "you".
+
+  A "library" means a collection of software functions and/or data
+prepared so as to be conveniently linked with application programs
+(which use some of those functions and data) to form executables.
+
+  The "Library", below, refers to any such software library or work
+which has been distributed under these terms.  A "work based on the
+Library" means either the Library or any derivative work under
+copyright law: that is to say, a work containing the Library or a
+portion of it, either verbatim or with modifications and/or translated
+straightforwardly into another language.  (Hereinafter, translation is
+included without limitation in the term "modification".)
+
+  "Source code" for a work means the preferred form of the work for
+making modifications to it.  For a library, complete source code means
+all the source code for all modules it contains, plus any associated
+interface definition files, plus the scripts used to control compilation
+and installation of the library.
+
+  Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running a program using the Library is not restricted, and output from
+such a program is covered only if its contents constitute a work based
+on the Library (independent of the use of the Library in a tool for
+writing it).  Whether that is true depends on what the Library does
+and what the program that uses the Library does.
+
+  1. You may copy and distribute verbatim copies of the Library's
+complete source code as you receive it, in any medium, provided that
+you conspicuously and appropriately publish on each copy an
+appropriate copyright notice and disclaimer of warranty; keep intact
+all the notices that refer to this License and to the absence of any
+warranty; and distribute a copy of this License along with the
+Library.
+
+  You may charge a fee for the physical act of transferring a copy,
+and you may at your option offer warranty protection in exchange for a
+fee.
+
+  2. You may modify your copy or copies of the Library or any portion
+of it, thus forming a work based on the Library, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) The modified work must itself be a software library.
+
+    b) You must cause the files modified to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    c) You must cause the whole of the work to be licensed at no
+    charge to all third parties under the terms of this License.
+
+    d) If a facility in the modified Library refers to a function or a
+    table of data to be supplied by an application program that uses
+    the facility, other than as an argument passed when the facility
+    is invoked, then you must make a good faith effort to ensure that,
+    in the event an application does not supply such function or
+    table, the facility still operates, and performs whatever part of
+    its purpose remains meaningful.
+
+    (For example, a function in a library to compute square roots has
+    a purpose that is entirely well-defined independent of the
+    application.  Therefore, Subsection 2d requires that any
+    application-supplied function or table used by this function must
+    be optional: if the application does not supply it, the square
+    root function must still compute square roots.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Library,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Library, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote
+it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Library.
+
+In addition, mere aggregation of another work not based on the Library
+with the Library (or with a work based on the Library) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may opt to apply the terms of the ordinary GNU General Public
+License instead of this License to a given copy of the Library.  To do
+this, you must alter all the notices that refer to this License, so
+that they refer to the ordinary GNU General Public License, version 2,
+instead of to this License.  (If a newer version than version 2 of the
+ordinary GNU General Public License has appeared, then you can specify
+that version instead if you wish.)  Do not make any other change in
+these notices.
+
+  Once this change is made in a given copy, it is irreversible for
+that copy, so the ordinary GNU General Public License applies to all
+subsequent copies and derivative works made from that copy.
+
+  This option is useful when you wish to copy part of the code of
+the Library into a program that is not a library.
+
+  4. You may copy and distribute the Library (or a portion or
+derivative of it, under Section 2) in object code or executable form
+under the terms of Sections 1 and 2 above provided that you accompany
+it with the complete corresponding machine-readable source code, which
+must be distributed under the terms of Sections 1 and 2 above on a
+medium customarily used for software interchange.
+
+  If distribution of object code is made by offering access to copy
+from a designated place, then offering equivalent access to copy the
+source code from the same place satisfies the requirement to
+distribute the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  5. A program that contains no derivative of any portion of the
+Library, but is designed to work with the Library by being compiled or
+linked with it, is called a "work that uses the Library".  Such a
+work, in isolation, is not a derivative work of the Library, and
+therefore falls outside the scope of this License.
+
+  However, linking a "work that uses the Library" with the Library
+creates an executable that is a derivative of the Library (because it
+contains portions of the Library), rather than a "work that uses the
+library".  The executable is therefore covered by this License.
+Section 6 states terms for distribution of such executables.
+
+  When a "work that uses the Library" uses material from a header file
+that is part of the Library, the object code for the work may be a
+derivative work of the Library even though the source code is not.
+Whether this is true is especially significant if the work can be
+linked without the Library, or if the work is itself a library.  The
+threshold for this to be true is not precisely defined by law.
+
+  If such an object file uses only numerical parameters, data
+structure layouts and accessors, and small macros and small inline
+functions (ten lines or less in length), then the use of the object
+file is unrestricted, regardless of whether it is legally a derivative
+work.  (Executables containing this object code plus portions of the
+Library will still fall under Section 6.)
+
+  Otherwise, if the work is a derivative of the Library, you may
+distribute the object code for the work under the terms of Section 6.
+Any executables containing that work also fall under Section 6,
+whether or not they are linked directly with the Library itself.
+
+  6. As an exception to the Sections above, you may also combine or
+link a "work that uses the Library" with the Library to produce a
+work containing portions of the Library, and distribute that work
+under terms of your choice, provided that the terms permit
+modification of the work for the customer's own use and reverse
+engineering for debugging such modifications.
+
+  You must give prominent notice with each copy of the work that the
+Library is used in it and that the Library and its use are covered by
+this License.  You must supply a copy of this License.  If the work
+during execution displays copyright notices, you must include the
+copyright notice for the Library among them, as well as a reference
+directing the user to the copy of this License.  Also, you must do one
+of these things:
+
+    a) Accompany the work with the complete corresponding
+    machine-readable source code for the Library including whatever
+    changes were used in the work (which must be distributed under
+    Sections 1 and 2 above); and, if the work is an executable linked
+    with the Library, with the complete machine-readable "work that
+    uses the Library", as object code and/or source code, so that the
+    user can modify the Library and then relink to produce a modified
+    executable containing the modified Library.  (It is understood
+    that the user who changes the contents of definitions files in the
+    Library will not necessarily be able to recompile the application
+    to use the modified definitions.)
+
+    b) Use a suitable shared library mechanism for linking with the
+    Library.  A suitable mechanism is one that (1) uses at run time a
+    copy of the library already present on the user's computer system,
+    rather than copying library functions into the executable, and (2)
+    will operate properly with a modified version of the library, if
+    the user installs one, as long as the modified version is
+    interface-compatible with the version that the work was made with.
+
+    c) Accompany the work with a written offer, valid for at
+    least three years, to give the same user the materials
+    specified in Subsection 6a, above, for a charge no more
+    than the cost of performing this distribution.
+
+    d) If distribution of the work is made by offering access to copy
+    from a designated place, offer equivalent access to copy the above
+    specified materials from the same place.
+
+    e) Verify that the user has already received a copy of these
+    materials or that you have already sent this user a copy.
+
+  For an executable, the required form of the "work that uses the
+Library" must include any data and utility programs needed for
+reproducing the executable from it.  However, as a special exception,
+the materials to be distributed need not include anything that is
+normally distributed (in either source or binary form) with the major
+components (compiler, kernel, and so on) of the operating system on
+which the executable runs, unless that component itself accompanies
+the executable.
+
+  It may happen that this requirement contradicts the license
+restrictions of other proprietary libraries that do not normally
+accompany the operating system.  Such a contradiction means you cannot
+use both them and the Library together in an executable that you
+distribute.
+
+  7. You may place library facilities that are a work based on the
+Library side-by-side in a single library together with other library
+facilities not covered by this License, and distribute such a combined
+library, provided that the separate distribution of the work based on
+the Library and of the other library facilities is otherwise
+permitted, and provided that you do these two things:
+
+    a) Accompany the combined library with a copy of the same work
+    based on the Library, uncombined with any other library
+    facilities.  This must be distributed under the terms of the
+    Sections above.
+
+    b) Give prominent notice with the combined library of the fact
+    that part of it is a work based on the Library, and explaining
+    where to find the accompanying uncombined form of the same work.
+
+  8. You may not copy, modify, sublicense, link with, or distribute
+the Library except as expressly provided under this License.  Any
+attempt otherwise to copy, modify, sublicense, link with, or
+distribute the Library is void, and will automatically terminate your
+rights under this License.  However, parties who have received copies,
+or rights, from you under this License will not have their licenses
+terminated so long as such parties remain in full compliance.
+
+  9. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Library or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Library (or any work based on the
+Library), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Library or works based on it.
+
+  10. Each time you redistribute the Library (or any work based on the
+Library), the recipient automatically receives a license from the
+original licensor to copy, distribute, link with or modify the Library
+subject to these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties with
+this License.
+
+  11. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Library at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Library by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Library.
+
+If any portion of this section is held invalid or unenforceable under any
+particular circumstance, the balance of the section is intended to apply,
+and the section as a whole is intended to apply in other circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  12. If the distribution and/or use of the Library is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Library under this License may add
+an explicit geographical distribution limitation excluding those countries,
+so that distribution is permitted only in or among countries not thus
+excluded.  In such case, this License incorporates the limitation as if
+written in the body of this License.
+
+  13. The Free Software Foundation may publish revised and/or new
+versions of the Lesser General Public License from time to time.
+Such new versions will be similar in spirit to the present version,
+but may differ in detail to address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Library
+specifies a version number of this License which applies to it and
+"any later version", you have the option of following the terms and
+conditions either of that version or of any later version published by
+the Free Software Foundation.  If the Library does not specify a
+license version number, you may choose any version ever published by
+the Free Software Foundation.
+
+  14. If you wish to incorporate parts of the Library into other free
+programs whose distribution conditions are incompatible with these,
+write to the author to ask for permission.  For software which is
+copyrighted by the Free Software Foundation, write to the Free
+Software Foundation; we sometimes make exceptions for this.  Our
+decision will be guided by the two goals of preserving the free status
+of all derivatives of our free software and of promoting the sharing
+and reuse of software generally.
+
+                            NO WARRANTY
+
+  15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
+WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
+EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
+OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY
+KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE
+LIBRARY IS WITH YOU.  SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
+THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
+WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
+AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU
+FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR
+CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE
+LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
+RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
+FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
+SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
+DAMAGES.
+
+                     END OF TERMS AND CONDITIONS
+
+           How to Apply These Terms to Your New Libraries
+
+  If you develop a new library, and you want it to be of the greatest
+possible use to the public, we recommend making it free software that
+everyone can redistribute and change.  You can do so by permitting
+redistribution under these terms (or, alternatively, under the terms of the
+ordinary General Public License).
+
+  To apply these terms, attach the following notices to the library.  It is
+safest to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least the
+"copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the library's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+    Lesser General Public License for more details.
+
+    You should have received a copy of the GNU Lesser General Public
+    License along with this library; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+
+Also add information on how to contact you by electronic and paper mail.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the library, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the
+  library `Frob' (a library for tweaking knobs) written by James Random Hacker.
+
+  <signature of Ty Coon>, 1 April 1990
+  Ty Coon, President of Vice
+
+That's all there is to it!
diff --git a/tools/gator/daemon/libsensors/access.c b/tools/gator/daemon/libsensors/access.c
new file mode 100644
index 00000000000..8e227e2550d
--- /dev/null
+++ b/tools/gator/daemon/libsensors/access.c
@@ -0,0 +1,561 @@
+/*
+    access.c - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007-2009   Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#include <stdlib.h>
+#include <string.h>
+#include <math.h>
+#include "access.h"
+#include "sensors.h"
+#include "data.h"
+#include "error.h"
+#include "sysfs.h"
+
+/* We watch the recursion depth for variables only, as an easy way to
+   detect cycles. */
+#define DEPTH_MAX	8
+
+static int sensors_eval_expr(const sensors_chip_features *chip_features,
+			     const sensors_expr *expr,
+			     double val, int depth, double *result);
+
+/* Compare two chips name descriptions, to see whether they could match.
+   Return 0 if it does not match, return 1 if it does match. */
+static int sensors_match_chip(const sensors_chip_name *chip1,
+		       const sensors_chip_name *chip2)
+{
+	if ((chip1->prefix != SENSORS_CHIP_NAME_PREFIX_ANY) &&
+	    (chip2->prefix != SENSORS_CHIP_NAME_PREFIX_ANY) &&
+	    strcmp(chip1->prefix, chip2->prefix))
+		return 0;
+
+	if ((chip1->bus.type != SENSORS_BUS_TYPE_ANY) &&
+	    (chip2->bus.type != SENSORS_BUS_TYPE_ANY) &&
+	    (chip1->bus.type != chip2->bus.type))
+		return 0;
+
+	if ((chip1->bus.nr != SENSORS_BUS_NR_ANY) &&
+	    (chip2->bus.nr != SENSORS_BUS_NR_ANY) &&
+	    (chip1->bus.nr != chip2->bus.nr))
+		return 0;
+
+	if ((chip1->addr != chip2->addr) &&
+	    (chip1->addr != SENSORS_CHIP_NAME_ADDR_ANY) &&
+	    (chip2->addr != SENSORS_CHIP_NAME_ADDR_ANY))
+		return 0;
+
+	return 1;
+}
+
+/* Returns, one by one, a pointer to all sensor_chip structs of the
+   config file which match with the given chip name. Last should be
+   the value returned by the last call, or NULL if this is the first
+   call. Returns NULL if no more matches are found. Do not modify
+   the struct the return value points to! 
+   Note that this visits the list of chips from last to first. Usually,
+   you want the match that was latest in the config file. */
+static sensors_chip *
+sensors_for_all_config_chips(const sensors_chip_name *name,
+			     const sensors_chip *last)
+{
+	int nr, i;
+	sensors_chip_name_list chips;
+
+	for (nr = last ? last - sensors_config_chips - 1 :
+			 sensors_config_chips_count - 1; nr >= 0; nr--) {
+
+		chips = sensors_config_chips[nr].chips;
+		for (i = 0; i < chips.fits_count; i++) {
+			if (sensors_match_chip(&chips.fits[i], name))
+				return sensors_config_chips + nr;
+		}
+	}
+	return NULL;
+}
+
+/* Look up a chip in the intern chip list, and return a pointer to it.
+   Do not modify the struct the return value points to! Returns NULL if
+   not found.*/
+static const sensors_chip_features *
+sensors_lookup_chip(const sensors_chip_name *name)
+{
+	int i;
+
+	for (i = 0; i < sensors_proc_chips_count; i++)
+		if (sensors_match_chip(&sensors_proc_chips[i].chip, name))
+			return &sensors_proc_chips[i];
+
+	return NULL;
+}
+
+/* Look up a subfeature of the given chip, and return a pointer to it.
+   Do not modify the struct the return value points to! Returns NULL if
+   not found.*/
+static const sensors_subfeature *
+sensors_lookup_subfeature_nr(const sensors_chip_features *chip,
+			     int subfeat_nr)
+{
+	if (subfeat_nr < 0 ||
+	    subfeat_nr >= chip->subfeature_count)
+		return NULL;
+	return chip->subfeature + subfeat_nr;
+}
+
+/* Look up a feature of the given chip, and return a pointer to it.
+   Do not modify the struct the return value points to! Returns NULL if
+   not found.*/
+static const sensors_feature *
+sensors_lookup_feature_nr(const sensors_chip_features *chip, int feat_nr)
+{
+	if (feat_nr < 0 ||
+	    feat_nr >= chip->feature_count)
+		return NULL;
+	return chip->feature + feat_nr;
+}
+
+/* Look up a subfeature by name, and return a pointer to it.
+   Do not modify the struct the return value points to! Returns NULL if 
+   not found.*/
+static const sensors_subfeature *
+sensors_lookup_subfeature_name(const sensors_chip_features *chip,
+			       const char *name)
+{
+	int j;
+
+	for (j = 0; j < chip->subfeature_count; j++)
+		if (!strcmp(chip->subfeature[j].name, name))
+			return chip->subfeature + j;
+	return NULL;
+}
+
+/* Check whether the chip name is an 'absolute' name, which can only match
+   one chip, or whether it has wildcards. Returns 0 if it is absolute, 1
+   if there are wildcards. */
+int sensors_chip_name_has_wildcards(const sensors_chip_name *chip)
+{
+	if ((chip->prefix == SENSORS_CHIP_NAME_PREFIX_ANY) ||
+	    (chip->bus.type == SENSORS_BUS_TYPE_ANY) ||
+	    (chip->bus.nr == SENSORS_BUS_NR_ANY) ||
+	    (chip->addr == SENSORS_CHIP_NAME_ADDR_ANY))
+		return 1;
+	else
+		return 0;
+}
+
+/* Look up the label for a given feature. Note that chip should not
+   contain wildcard values! The returned string is newly allocated (free it
+   yourself). On failure, NULL is returned.
+   If no label exists for this feature, its name is returned itself. */
+char *sensors_get_label(const sensors_chip_name *name,
+			const sensors_feature *feature)
+{
+	char *label;
+	const sensors_chip *chip;
+	char buf[PATH_MAX];
+	FILE *f;
+	int i;
+
+	if (sensors_chip_name_has_wildcards(name))
+		return NULL;
+
+	for (chip = NULL; (chip = sensors_for_all_config_chips(name, chip));)
+		for (i = 0; i < chip->labels_count; i++)
+			if (!strcmp(feature->name, chip->labels[i].name)) {
+				label = chip->labels[i].value;
+				goto sensors_get_label_exit;
+			}
+
+	/* No user specified label, check for a _label sysfs file */
+	snprintf(buf, PATH_MAX, "%s/%s_label", name->path, feature->name);
+	
+	if ((f = fopen(buf, "r"))) {
+		i = fread(buf, 1, sizeof(buf), f);
+		fclose(f);
+		if (i > 0) {
+			/* i - 1 to strip the '\n' at the end */
+			buf[i - 1] = 0;
+			label = buf;
+			goto sensors_get_label_exit;
+		}
+	}
+
+	/* No label, return the feature name instead */
+	label = feature->name;
+	
+sensors_get_label_exit:
+	label = strdup(label);
+	if (!label)
+		sensors_fatal_error(__func__, "Allocating label text");
+	return label;
+}
+
+/* Looks up whether a feature should be ignored. Returns
+   1 if it should be ignored, 0 if not. */
+static int sensors_get_ignored(const sensors_chip_name *name,
+			       const sensors_feature *feature)
+{
+	const sensors_chip *chip;
+	int i;
+
+	for (chip = NULL; (chip = sensors_for_all_config_chips(name, chip));)
+		for (i = 0; i < chip->ignores_count; i++)
+			if (!strcmp(feature->name, chip->ignores[i].name))
+				return 1;
+	return 0;
+}
+
+/* Read the value of a subfeature of a certain chip. Note that chip should not
+   contain wildcard values! This function will return 0 on success, and <0
+   on failure. */
+static int __sensors_get_value(const sensors_chip_name *name, int subfeat_nr,
+			       int depth, double *result)
+{
+	const sensors_chip_features *chip_features;
+	const sensors_subfeature *subfeature;
+	const sensors_expr *expr = NULL;
+	double val;
+	int res, i;
+
+	if (depth >= DEPTH_MAX)
+		return -SENSORS_ERR_RECURSION;
+	if (sensors_chip_name_has_wildcards(name))
+		return -SENSORS_ERR_WILDCARDS;
+	if (!(chip_features = sensors_lookup_chip(name)))
+		return -SENSORS_ERR_NO_ENTRY;
+	if (!(subfeature = sensors_lookup_subfeature_nr(chip_features,
+							subfeat_nr)))
+		return -SENSORS_ERR_NO_ENTRY;
+	if (!(subfeature->flags & SENSORS_MODE_R))
+		return -SENSORS_ERR_ACCESS_R;
+
+	/* Apply compute statement if it exists */
+	if (subfeature->flags & SENSORS_COMPUTE_MAPPING) {
+		const sensors_feature *feature;
+		const sensors_chip *chip;
+
+		feature = sensors_lookup_feature_nr(chip_features,
+					subfeature->mapping);
+
+		chip = NULL;
+		while (!expr &&
+		       (chip = sensors_for_all_config_chips(name, chip)))
+			for (i = 0; i < chip->computes_count; i++) {
+				if (!strcmp(feature->name,
+					    chip->computes[i].name)) {
+					expr = chip->computes[i].from_proc;
+					break;
+				}
+			}
+	}
+
+	res = sensors_read_sysfs_attr(name, subfeature, &val);
+	if (res)
+		return res;
+	if (!expr)
+		*result = val;
+	else if ((res = sensors_eval_expr(chip_features, expr, val, depth,
+					  result)))
+		return res;
+	return 0;
+}
+
+int sensors_get_value(const sensors_chip_name *name, int subfeat_nr,
+		      double *result)
+{
+	return __sensors_get_value(name, subfeat_nr, 0, result);
+}
+
+/* Set the value of a subfeature of a certain chip. Note that chip should not
+   contain wildcard values! This function will return 0 on success, and <0
+   on failure. */
+int sensors_set_value(const sensors_chip_name *name, int subfeat_nr,
+		      double value)
+{
+	const sensors_chip_features *chip_features;
+	const sensors_subfeature *subfeature;
+	const sensors_expr *expr = NULL;
+	int i, res;
+	double to_write;
+
+	if (sensors_chip_name_has_wildcards(name))
+		return -SENSORS_ERR_WILDCARDS;
+	if (!(chip_features = sensors_lookup_chip(name)))
+		return -SENSORS_ERR_NO_ENTRY;
+	if (!(subfeature = sensors_lookup_subfeature_nr(chip_features,
+							subfeat_nr)))
+		return -SENSORS_ERR_NO_ENTRY;
+	if (!(subfeature->flags & SENSORS_MODE_W))
+		return -SENSORS_ERR_ACCESS_W;
+
+	/* Apply compute statement if it exists */
+	if (subfeature->flags & SENSORS_COMPUTE_MAPPING) {
+		const sensors_feature *feature;
+		const sensors_chip *chip;
+
+		feature = sensors_lookup_feature_nr(chip_features,
+					subfeature->mapping);
+
+		chip = NULL;
+		while (!expr &&
+		       (chip = sensors_for_all_config_chips(name, chip)))
+			for (i = 0; i < chip->computes_count; i++) {
+				if (!strcmp(feature->name,
+					    chip->computes[i].name)) {
+					expr = chip->computes[i].to_proc;
+					break;
+				}
+			}
+	}
+
+	to_write = value;
+	if (expr)
+		if ((res = sensors_eval_expr(chip_features, expr,
+					     value, 0, &to_write)))
+			return res;
+	return sensors_write_sysfs_attr(name, subfeature, to_write);
+}
+
+const sensors_chip_name *sensors_get_detected_chips(const sensors_chip_name
+						    *match, int *nr)
+{
+	const sensors_chip_name *res;
+
+	while (*nr < sensors_proc_chips_count) {
+		res = &sensors_proc_chips[(*nr)++].chip;
+		if (!match || sensors_match_chip(res, match))
+			return res;
+	}
+	return NULL;
+}
+
+const char *sensors_get_adapter_name(const sensors_bus_id *bus)
+{
+	int i;
+
+	/* bus types with a single instance */
+	switch (bus->type) {
+	case SENSORS_BUS_TYPE_ISA:
+		return "ISA adapter";
+	case SENSORS_BUS_TYPE_PCI:
+		return "PCI adapter";
+	/* SPI should not be here, but for now SPI adapters have no name
+	   so we don't have any custom string to return. */
+	case SENSORS_BUS_TYPE_SPI:
+		return "SPI adapter";
+	case SENSORS_BUS_TYPE_VIRTUAL:
+		return "Virtual device";
+	case SENSORS_BUS_TYPE_ACPI:
+		return "ACPI interface";
+	/* HID should probably not be there either, but I don't know if
+	   HID buses have a name nor where to find it. */
+	case SENSORS_BUS_TYPE_HID:
+		return "HID adapter";
+	}
+
+	/* bus types with several instances */
+	for (i = 0; i < sensors_proc_bus_count; i++)
+		if (sensors_proc_bus[i].bus.type == bus->type &&
+		    sensors_proc_bus[i].bus.nr == bus->nr)
+			return sensors_proc_bus[i].adapter;
+	return NULL;
+}
+
+const sensors_feature *
+sensors_get_features(const sensors_chip_name *name, int *nr)
+{
+	const sensors_chip_features *chip;
+
+	if (!(chip = sensors_lookup_chip(name)))
+		return NULL;	/* No such chip */
+
+	while (*nr < chip->feature_count
+	    && sensors_get_ignored(name, &chip->feature[*nr]))
+		(*nr)++;
+	if (*nr >= chip->feature_count)
+		return NULL;
+	return &chip->feature[(*nr)++];
+}
+
+const sensors_subfeature *
+sensors_get_all_subfeatures(const sensors_chip_name *name,
+			const sensors_feature *feature, int *nr)
+{
+	const sensors_chip_features *chip;
+	const sensors_subfeature *subfeature;
+
+	if (!(chip = sensors_lookup_chip(name)))
+		return NULL;	/* No such chip */
+
+	/* Seek directly to the first subfeature */
+	if (*nr < feature->first_subfeature)
+		*nr = feature->first_subfeature;
+
+	if (*nr >= chip->subfeature_count)
+		return NULL;	/* end of list */
+	subfeature = &chip->subfeature[(*nr)++];
+	if (subfeature->mapping == feature->number)
+		return subfeature;
+	return NULL;	/* end of subfeature list */
+}
+
+const sensors_subfeature *
+sensors_get_subfeature(const sensors_chip_name *name,
+		       const sensors_feature *feature,
+		       sensors_subfeature_type type)
+{
+	const sensors_chip_features *chip;
+	int i;
+
+	if (!(chip = sensors_lookup_chip(name)))
+		return NULL;	/* No such chip */
+
+	for (i = feature->first_subfeature; i < chip->subfeature_count &&
+	     chip->subfeature[i].mapping == feature->number; i++) {
+		if (chip->subfeature[i].type == type)
+			return &chip->subfeature[i];
+	}
+	return NULL;	/* No such subfeature */
+}
+
+/* Evaluate an expression */
+int sensors_eval_expr(const sensors_chip_features *chip_features,
+		      const sensors_expr *expr,
+		      double val, int depth, double *result)
+{
+	double res1, res2;
+	int res;
+	const sensors_subfeature *subfeature;
+
+	if (expr->kind == sensors_kind_val) {
+		*result = expr->data.val;
+		return 0;
+	}
+	if (expr->kind == sensors_kind_source) {
+		*result = val;
+		return 0;
+	}
+	if (expr->kind == sensors_kind_var) {
+		if (!(subfeature = sensors_lookup_subfeature_name(chip_features,
+							    expr->data.var)))
+			return -SENSORS_ERR_NO_ENTRY;
+		return __sensors_get_value(&chip_features->chip,
+					   subfeature->number, depth + 1,
+					   result);
+	}
+	if ((res = sensors_eval_expr(chip_features, expr->data.subexpr.sub1,
+				     val, depth, &res1)))
+		return res;
+	if (expr->data.subexpr.sub2 &&
+	    (res = sensors_eval_expr(chip_features, expr->data.subexpr.sub2,
+				     val, depth, &res2)))
+		return res;
+	switch (expr->data.subexpr.op) {
+	case sensors_add:
+		*result = res1 + res2;
+		return 0;
+	case sensors_sub:
+		*result = res1 - res2;
+		return 0;
+	case sensors_multiply:
+		*result = res1 * res2;
+		return 0;
+	case sensors_divide:
+		if (res2 == 0.0)
+			return -SENSORS_ERR_DIV_ZERO;
+		*result = res1 / res2;
+		return 0;
+	case sensors_negate:
+		*result = -res1;
+		return 0;
+	case sensors_exp:
+		*result = exp(res1);
+		return 0;
+	case sensors_log:
+		if (res1 < 0.0)
+			return -SENSORS_ERR_DIV_ZERO;
+		*result = log(res1);
+		return 0;
+	}
+	return 0;
+}
+
+/* Execute all set statements for this particular chip. The chip may not 
+   contain wildcards!  This function will return 0 on success, and <0 on 
+   failure. */
+static int sensors_do_this_chip_sets(const sensors_chip_name *name)
+{
+	const sensors_chip_features *chip_features;
+	sensors_chip *chip;
+	double value;
+	int i;
+	int err = 0, res;
+	const sensors_subfeature *subfeature;
+
+	chip_features = sensors_lookup_chip(name);	/* Can't fail */
+
+	for (chip = NULL; (chip = sensors_for_all_config_chips(name, chip));)
+		for (i = 0; i < chip->sets_count; i++) {
+			subfeature = sensors_lookup_subfeature_name(chip_features,
+							chip->sets[i].name);
+			if (!subfeature) {
+				sensors_parse_error_wfn("Unknown feature name",
+						    chip->sets[i].line.filename,
+						    chip->sets[i].line.lineno);
+				err = -SENSORS_ERR_NO_ENTRY;
+				continue;
+			}
+
+			res = sensors_eval_expr(chip_features,
+						chip->sets[i].value, 0,
+						0, &value);
+			if (res) {
+				sensors_parse_error_wfn("Error parsing expression",
+						    chip->sets[i].line.filename,
+						    chip->sets[i].line.lineno);
+				err = res;
+				continue;
+			}
+			if ((res = sensors_set_value(name, subfeature->number,
+						     value))) {
+				sensors_parse_error_wfn("Failed to set value",
+						chip->sets[i].line.filename,
+						chip->sets[i].line.lineno);
+				err = res;
+				continue;
+			}
+		}
+	return err;
+}
+
+/* Execute all set statements for this particular chip. The chip may contain
+   wildcards!  This function will return 0 on success, and <0 on failure. */
+int sensors_do_chip_sets(const sensors_chip_name *name)
+{
+	int nr, this_res;
+	const sensors_chip_name *found_name;
+	int res = 0;
+
+	for (nr = 0; (found_name = sensors_get_detected_chips(name, &nr));) {
+		this_res = sensors_do_this_chip_sets(found_name);
+		if (this_res)
+			res = this_res;
+	}
+	return res;
+}
diff --git a/tools/gator/daemon/libsensors/access.h b/tools/gator/daemon/libsensors/access.h
new file mode 100644
index 00000000000..1d378434075
--- /dev/null
+++ b/tools/gator/daemon/libsensors/access.h
@@ -0,0 +1,33 @@
+/*
+    access.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007        Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_ACCESS_H
+#define LIB_SENSORS_ACCESS_H
+
+#include "sensors.h"
+#include "data.h"
+
+/* Check whether the chip name is an 'absolute' name, which can only match
+   one chip, or whether it has wildcards. Returns 0 if it is absolute, 1
+   if there are wildcards. */
+int sensors_chip_name_has_wildcards(const sensors_chip_name *chip);
+
+#endif /* def LIB_SENSORS_ACCESS_H */
diff --git a/tools/gator/daemon/libsensors/conf-lex.c b/tools/gator/daemon/libsensors/conf-lex.c
new file mode 100644
index 00000000000..a54664b3d77
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-lex.c
@@ -0,0 +1,2881 @@
+
+#line 3 "<stdout>"
+
+#define  YY_INT_ALIGNED short int
+
+/* A lexical scanner generated by flex */
+
+#define yy_create_buffer sensors_yy_create_buffer
+#define yy_delete_buffer sensors_yy_delete_buffer
+#define yy_flex_debug sensors_yy_flex_debug
+#define yy_init_buffer sensors_yy_init_buffer
+#define yy_flush_buffer sensors_yy_flush_buffer
+#define yy_load_buffer_state sensors_yy_load_buffer_state
+#define yy_switch_to_buffer sensors_yy_switch_to_buffer
+#define yyin sensors_yyin
+#define yyleng sensors_yyleng
+#define yylex sensors_yylex
+#define yylineno sensors_yylineno
+#define yyout sensors_yyout
+#define yyrestart sensors_yyrestart
+#define yytext sensors_yytext
+#define yywrap sensors_yywrap
+#define yyalloc sensors_yyalloc
+#define yyrealloc sensors_yyrealloc
+#define yyfree sensors_yyfree
+
+#define FLEX_SCANNER
+#define YY_FLEX_MAJOR_VERSION 2
+#define YY_FLEX_MINOR_VERSION 5
+#define YY_FLEX_SUBMINOR_VERSION 35
+#if YY_FLEX_SUBMINOR_VERSION > 0
+#define FLEX_BETA
+#endif
+
+/* First, we deal with  platform-specific or compiler-specific issues. */
+
+/* begin standard C headers. */
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <stdlib.h>
+
+/* end standard C headers. */
+
+/* flex integer type definitions */
+
+#ifndef FLEXINT_H
+#define FLEXINT_H
+
+/* C99 systems have <inttypes.h>. Non-C99 systems may or may not. */
+
+#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
+
+/* C99 says to define __STDC_LIMIT_MACROS before including stdint.h,
+ * if you want the limit (max/min) macros for int types. 
+ */
+#ifndef __STDC_LIMIT_MACROS
+#define __STDC_LIMIT_MACROS 1
+#endif
+
+#include <inttypes.h>
+typedef int8_t flex_int8_t;
+typedef uint8_t flex_uint8_t;
+typedef int16_t flex_int16_t;
+typedef uint16_t flex_uint16_t;
+typedef int32_t flex_int32_t;
+typedef uint32_t flex_uint32_t;
+#else
+typedef signed char flex_int8_t;
+typedef short int flex_int16_t;
+typedef int flex_int32_t;
+typedef unsigned char flex_uint8_t; 
+typedef unsigned short int flex_uint16_t;
+typedef unsigned int flex_uint32_t;
+
+/* Limits of integral types. */
+#ifndef INT8_MIN
+#define INT8_MIN               (-128)
+#endif
+#ifndef INT16_MIN
+#define INT16_MIN              (-32767-1)
+#endif
+#ifndef INT32_MIN
+#define INT32_MIN              (-2147483647-1)
+#endif
+#ifndef INT8_MAX
+#define INT8_MAX               (127)
+#endif
+#ifndef INT16_MAX
+#define INT16_MAX              (32767)
+#endif
+#ifndef INT32_MAX
+#define INT32_MAX              (2147483647)
+#endif
+#ifndef UINT8_MAX
+#define UINT8_MAX              (255U)
+#endif
+#ifndef UINT16_MAX
+#define UINT16_MAX             (65535U)
+#endif
+#ifndef UINT32_MAX
+#define UINT32_MAX             (4294967295U)
+#endif
+
+#endif /* ! C99 */
+
+#endif /* ! FLEXINT_H */
+
+#ifdef __cplusplus
+
+/* The "const" storage-class-modifier is valid. */
+#define YY_USE_CONST
+
+#else	/* ! __cplusplus */
+
+/* C99 requires __STDC__ to be defined as 1. */
+#if defined (__STDC__)
+
+#define YY_USE_CONST
+
+#endif	/* defined (__STDC__) */
+#endif	/* ! __cplusplus */
+
+#ifdef YY_USE_CONST
+#define yyconst const
+#else
+#define yyconst
+#endif
+
+/* Returned upon end-of-file. */
+#define YY_NULL 0
+
+/* Promotes a possibly negative, possibly signed char to an unsigned
+ * integer for use as an array index.  If the signed char is negative,
+ * we want to instead treat it as an 8-bit unsigned char, hence the
+ * double cast.
+ */
+#define YY_SC_TO_UI(c) ((unsigned int) (unsigned char) c)
+
+/* Enter a start condition.  This macro really ought to take a parameter,
+ * but we do it the disgusting crufty way forced on us by the ()-less
+ * definition of BEGIN.
+ */
+#define BEGIN (yy_start) = 1 + 2 *
+
+/* Translate the current start state into a value that can be later handed
+ * to BEGIN to return to the state.  The YYSTATE alias is for lex
+ * compatibility.
+ */
+#define YY_START (((yy_start) - 1) / 2)
+#define YYSTATE YY_START
+
+/* Action number for EOF rule of a given start state. */
+#define YY_STATE_EOF(state) (YY_END_OF_BUFFER + state + 1)
+
+/* Special action meaning "start processing a new file". */
+#define YY_NEW_FILE sensors_yyrestart(sensors_yyin  )
+
+#define YY_END_OF_BUFFER_CHAR 0
+
+/* Size of default input buffer. */
+#ifndef YY_BUF_SIZE
+#ifdef __ia64__
+/* On IA-64, the buffer size is 16k, not 8k.
+ * Moreover, YY_BUF_SIZE is 2*YY_READ_BUF_SIZE in the general case.
+ * Ditto for the __ia64__ case accordingly.
+ */
+#define YY_BUF_SIZE 32768
+#else
+#define YY_BUF_SIZE 16384
+#endif /* __ia64__ */
+#endif
+
+/* The state buf must be large enough to hold one state per character in the main buffer.
+ */
+#define YY_STATE_BUF_SIZE   ((YY_BUF_SIZE + 2) * sizeof(yy_state_type))
+
+#ifndef YY_TYPEDEF_YY_BUFFER_STATE
+#define YY_TYPEDEF_YY_BUFFER_STATE
+typedef struct yy_buffer_state *YY_BUFFER_STATE;
+#endif
+
+extern int sensors_yyleng;
+
+extern FILE *sensors_yyin, *sensors_yyout;
+
+#define EOB_ACT_CONTINUE_SCAN 0
+#define EOB_ACT_END_OF_FILE 1
+#define EOB_ACT_LAST_MATCH 2
+
+    #define YY_LESS_LINENO(n)
+    
+/* Return all but the first "n" matched characters back to the input stream. */
+#define yyless(n) \
+	do \
+		{ \
+		/* Undo effects of setting up sensors_yytext. */ \
+        int yyless_macro_arg = (n); \
+        YY_LESS_LINENO(yyless_macro_arg);\
+		*yy_cp = (yy_hold_char); \
+		YY_RESTORE_YY_MORE_OFFSET \
+		(yy_c_buf_p) = yy_cp = yy_bp + yyless_macro_arg - YY_MORE_ADJ; \
+		YY_DO_BEFORE_ACTION; /* set up sensors_yytext again */ \
+		} \
+	while ( 0 )
+
+#define unput(c) yyunput( c, (yytext_ptr)  )
+
+#ifndef YY_TYPEDEF_YY_SIZE_T
+#define YY_TYPEDEF_YY_SIZE_T
+typedef size_t yy_size_t;
+#endif
+
+#ifndef YY_STRUCT_YY_BUFFER_STATE
+#define YY_STRUCT_YY_BUFFER_STATE
+struct yy_buffer_state
+	{
+	FILE *yy_input_file;
+
+	char *yy_ch_buf;		/* input buffer */
+	char *yy_buf_pos;		/* current position in input buffer */
+
+	/* Size of input buffer in bytes, not including room for EOB
+	 * characters.
+	 */
+	yy_size_t yy_buf_size;
+
+	/* Number of characters read into yy_ch_buf, not including EOB
+	 * characters.
+	 */
+	int yy_n_chars;
+
+	/* Whether we "own" the buffer - i.e., we know we created it,
+	 * and can realloc() it to grow it, and should free() it to
+	 * delete it.
+	 */
+	int yy_is_our_buffer;
+
+	/* Whether this is an "interactive" input source; if so, and
+	 * if we're using stdio for input, then we want to use getc()
+	 * instead of fread(), to make sure we stop fetching input after
+	 * each newline.
+	 */
+	int yy_is_interactive;
+
+	/* Whether we're considered to be at the beginning of a line.
+	 * If so, '^' rules will be active on the next match, otherwise
+	 * not.
+	 */
+	int yy_at_bol;
+
+    int yy_bs_lineno; /**< The line count. */
+    int yy_bs_column; /**< The column count. */
+    
+	/* Whether to try to fill the input buffer when we reach the
+	 * end of it.
+	 */
+	int yy_fill_buffer;
+
+	int yy_buffer_status;
+
+#define YY_BUFFER_NEW 0
+#define YY_BUFFER_NORMAL 1
+	/* When an EOF's been seen but there's still some text to process
+	 * then we mark the buffer as YY_EOF_PENDING, to indicate that we
+	 * shouldn't try reading from the input source any more.  We might
+	 * still have a bunch of tokens to match, though, because of
+	 * possible backing-up.
+	 *
+	 * When we actually see the EOF, we change the status to "new"
+	 * (via sensors_yyrestart()), so that the user can continue scanning by
+	 * just pointing sensors_yyin at a new input file.
+	 */
+#define YY_BUFFER_EOF_PENDING 2
+
+	};
+#endif /* !YY_STRUCT_YY_BUFFER_STATE */
+
+/* Stack of input buffers. */
+static size_t yy_buffer_stack_top = 0; /**< index of top of stack. */
+static size_t yy_buffer_stack_max = 0; /**< capacity of stack. */
+static YY_BUFFER_STATE * yy_buffer_stack = 0; /**< Stack as an array. */
+
+/* We provide macros for accessing buffer states in case in the
+ * future we want to put the buffer states in a more general
+ * "scanner state".
+ *
+ * Returns the top of the stack, or NULL.
+ */
+#define YY_CURRENT_BUFFER ( (yy_buffer_stack) \
+                          ? (yy_buffer_stack)[(yy_buffer_stack_top)] \
+                          : NULL)
+
+/* Same as previous macro, but useful when we know that the buffer stack is not
+ * NULL or when we need an lvalue. For internal use only.
+ */
+#define YY_CURRENT_BUFFER_LVALUE (yy_buffer_stack)[(yy_buffer_stack_top)]
+
+/* yy_hold_char holds the character lost when sensors_yytext is formed. */
+static char yy_hold_char;
+static int yy_n_chars;		/* number of characters read into yy_ch_buf */
+int sensors_yyleng;
+
+/* Points to current character in buffer. */
+static char *yy_c_buf_p = (char *) 0;
+static int yy_init = 0;		/* whether we need to initialize */
+static int yy_start = 0;	/* start state number */
+
+/* Flag which is used to allow sensors_yywrap()'s to do buffer switches
+ * instead of setting up a fresh sensors_yyin.  A bit of a hack ...
+ */
+static int yy_did_buffer_switch_on_eof;
+
+void sensors_yyrestart (FILE *input_file  );
+void sensors_yy_switch_to_buffer (YY_BUFFER_STATE new_buffer  );
+YY_BUFFER_STATE sensors_yy_create_buffer (FILE *file,int size  );
+void sensors_yy_delete_buffer (YY_BUFFER_STATE b  );
+void sensors_yy_flush_buffer (YY_BUFFER_STATE b  );
+void sensors_yypush_buffer_state (YY_BUFFER_STATE new_buffer  );
+void sensors_yypop_buffer_state (void );
+
+static void sensors_yyensure_buffer_stack (void );
+static void sensors_yy_load_buffer_state (void );
+static void sensors_yy_init_buffer (YY_BUFFER_STATE b,FILE *file  );
+
+#define YY_FLUSH_BUFFER sensors_yy_flush_buffer(YY_CURRENT_BUFFER )
+
+YY_BUFFER_STATE sensors_yy_scan_buffer (char *base,yy_size_t size  );
+YY_BUFFER_STATE sensors_yy_scan_string (yyconst char *yy_str  );
+YY_BUFFER_STATE sensors_yy_scan_bytes (yyconst char *bytes,int len  );
+
+void *sensors_yyalloc (yy_size_t  );
+void *sensors_yyrealloc (void *,yy_size_t  );
+void sensors_yyfree (void *  );
+
+#define yy_new_buffer sensors_yy_create_buffer
+
+#define yy_set_interactive(is_interactive) \
+	{ \
+	if ( ! YY_CURRENT_BUFFER ){ \
+        sensors_yyensure_buffer_stack (); \
+		YY_CURRENT_BUFFER_LVALUE =    \
+            sensors_yy_create_buffer(sensors_yyin,YY_BUF_SIZE ); \
+	} \
+	YY_CURRENT_BUFFER_LVALUE->yy_is_interactive = is_interactive; \
+	}
+
+#define yy_set_bol(at_bol) \
+	{ \
+	if ( ! YY_CURRENT_BUFFER ){\
+        sensors_yyensure_buffer_stack (); \
+		YY_CURRENT_BUFFER_LVALUE =    \
+            sensors_yy_create_buffer(sensors_yyin,YY_BUF_SIZE ); \
+	} \
+	YY_CURRENT_BUFFER_LVALUE->yy_at_bol = at_bol; \
+	}
+
+#define YY_AT_BOL() (YY_CURRENT_BUFFER_LVALUE->yy_at_bol)
+
+/* Begin user sect3 */
+
+#define sensors_yywrap(n) 1
+#define YY_SKIP_YYWRAP
+
+typedef unsigned char YY_CHAR;
+
+FILE *sensors_yyin = (FILE *) 0, *sensors_yyout = (FILE *) 0;
+
+typedef int yy_state_type;
+
+extern int sensors_yylineno;
+
+int sensors_yylineno = 1;
+
+extern char *sensors_yytext;
+#define yytext_ptr sensors_yytext
+static yyconst flex_int16_t yy_nxt[][39] =
+    {
+    {
+        0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
+        0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
+        0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
+        0,    0,    0,    0,    0,    0,    0,    0,    0
+    },
+
+    {
+        9,   10,   11,   12,   10,   13,   10,   10,   10,   10,
+       10,   10,   10,   10,   10,   10,   10,   10,   10,   10,
+       14,   15,   16,   14,   14,   14,   14,   14,   17,   18,
+       14,   14,   14,   14,   14,   19,   14,   14,   14
+    },
+
+    {
+        9,   10,   11,   12,   10,   13,   10,   10,   10,   10,
+       10,   10,   10,   10,   10,   10,   10,   10,   10,   10,
+
+       14,   15,   16,   14,   14,   14,   14,   14,   17,   18,
+       14,   14,   14,   14,   14,   19,   14,   14,   14
+    },
+
+    {
+        9,   20,   21,   22,   23,   24,   25,   26,   27,   28,
+       29,   30,   31,   32,   33,   34,   35,   36,   37,   38,
+       35,   35,   35,   35,   35,   35,   35,   35,   35,   35,
+       35,   35,   35,   35,   35,   35,   35,   35,   35
+    },
+
+    {
+        9,   20,   21,   22,   23,   24,   25,   26,   27,   28,
+       29,   30,   31,   32,   33,   34,   35,   36,   37,   38,
+       35,   35,   35,   35,   35,   35,   35,   35,   35,   35,
+       35,   35,   35,   35,   35,   35,   35,   35,   35
+
+    },
+
+    {
+        9,   39,   39,   40,   41,   39,   39,   39,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   42,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   39,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   39,   39
+    },
+
+    {
+        9,   39,   39,   40,   41,   39,   39,   39,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   42,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   39,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   39,   39
+    },
+
+    {
+        9,   43,   43,   44,   43,   43,   43,   43,   43,   43,
+       43,   43,   43,   43,   43,   43,   43,   43,   43,   43,
+
+       43,   43,   43,   43,   43,   43,   43,   43,   43,   43,
+       43,   43,   43,   43,   43,   43,   43,   43,   43
+    },
+
+    {
+        9,   43,   43,   44,   43,   43,   43,   43,   43,   43,
+       43,   43,   43,   43,   43,   43,   43,   43,   43,   43,
+       43,   43,   43,   43,   43,   43,   43,   43,   43,   43,
+       43,   43,   43,   43,   43,   43,   43,   43,   43
+    },
+
+    {
+       -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,
+       -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,
+       -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,
+       -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9
+
+    },
+
+    {
+        9,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,
+      -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,
+      -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,
+      -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10
+    },
+
+    {
+        9,  -11,   45,   46,  -11,  -11,  -11,  -11,  -11,  -11,
+      -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,
+      -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,
+      -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11
+    },
+
+    {
+        9,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,
+      -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,
+
+      -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,
+      -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12
+    },
+
+    {
+        9,   47,   47,   48,   47,   47,   47,   47,   47,   47,
+       47,   47,   47,   47,   47,   47,   47,   47,   47,   47,
+       47,   47,   47,   47,   47,   47,   47,   47,   47,   47,
+       47,   47,   47,   47,   47,   47,   47,   47,   47
+    },
+
+    {
+        9,  -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,
+      -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -15,  -15,  -15,  -15,  -15,  -15,  -15,  -15,  -15,
+      -15,  -15,  -15,  -15,  -15,  -15,  -15,  -15,  -15,  -15,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   50,   49
+    },
+
+    {
+        9,  -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,
+      -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,
+       49,   49,   49,   49,   49,   49,   49,   51,   49,   49,
+       49,   49,   52,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,
+      -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,
+
+       49,   49,   49,   49,   49,   49,   53,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -18,  -18,  -18,  -18,  -18,  -18,  -18,  -18,  -18,
+      -18,  -18,  -18,  -18,  -18,  -18,  -18,  -18,  -18,  -18,
+       54,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -19,  -19,  -19,  -19,  -19,  -19,  -19,  -19,  -19,
+      -19,  -19,  -19,  -19,  -19,  -19,  -19,  -19,  -19,  -19,
+       49,   49,   49,   49,   55,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,
+      -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,
+      -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,
+      -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20
+    },
+
+    {
+        9,  -21,   56,  -21,  -21,  -21,  -21,  -21,  -21,  -21,
+      -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,
+      -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,
+      -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21
+    },
+
+    {
+        9,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,
+      -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,
+
+      -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,
+      -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22
+    },
+
+    {
+        9,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,
+      -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,
+      -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,
+      -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23
+    },
+
+    {
+        9,   57,   57,   58,   57,   57,   57,   57,   57,   57,
+       57,   57,   57,   57,   57,   57,   57,   57,   57,   57,
+       57,   57,   57,   57,   57,   57,   57,   57,   57,   57,
+       57,   57,   57,   57,   57,   57,   57,   57,   57
+
+    },
+
+    {
+        9,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,
+      -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,
+      -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,
+      -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25
+    },
+
+    {
+        9,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,
+      -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,
+      -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,
+      -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26
+    },
+
+    {
+        9,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,
+      -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,
+
+      -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,
+      -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27
+    },
+
+    {
+        9,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,
+      -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,
+      -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,
+      -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28
+    },
+
+    {
+        9,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,
+      -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,
+      -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,
+      -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29
+
+    },
+
+    {
+        9,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,
+      -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,
+      -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,
+      -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30
+    },
+
+    {
+        9,  -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,
+      -31,  -31,  -31,  -31,   59,  -31,  -31,  -31,  -31,  -31,
+      -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,
+      -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31
+    },
+
+    {
+        9,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,
+      -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,
+
+      -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,
+      -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32
+    },
+
+    {
+        9,  -33,  -33,  -33,  -33,  -33,  -33,  -33,  -33,  -33,
+      -33,  -33,   60,  -33,   61,  -33,   62,  -33,  -33,  -33,
+       62,   62,   62,   62,   62,   62,   62,   62,   62,   62,
+       62,   62,   62,   62,   62,   62,   62,   62,   62
+    },
+
+    {
+        9,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,
+      -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,
+      -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,
+      -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34
+
+    },
+
+    {
+        9,  -35,  -35,  -35,  -35,  -35,  -35,  -35,  -35,  -35,
+      -35,  -35,  -35,  -35,   62,  -35,   62,  -35,  -35,  -35,
+       62,   62,   62,   62,   62,   62,   62,   62,   62,   62,
+       62,   62,   62,   62,   62,   62,   62,   62,   62
+    },
+
+    {
+        9,  -36,   63,   64,  -36,  -36,  -36,  -36,  -36,  -36,
+      -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,
+      -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,
+      -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36
+    },
+
+    {
+        9,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,
+      -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,
+
+      -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,
+      -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37
+    },
+
+    {
+        9,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,
+      -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,
+      -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,
+      -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38
+    },
+
+    {
+        9,   65,   65,  -39,  -39,   65,   65,   65,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,  -39,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,   65,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,   65,   65
+
+    },
+
+    {
+        9,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,
+      -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,
+      -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,
+      -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40
+    },
+
+    {
+        9,  -41,  -41,  -41,   66,  -41,  -41,  -41,  -41,  -41,
+      -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,
+      -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,
+      -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41
+    },
+
+    {
+        9,   67,   67,   68,   67,   67,   67,   67,   67,   67,
+       67,   67,   67,   67,   67,   67,   67,   67,   67,   67,
+
+       69,   70,   67,   67,   67,   71,   67,   67,   67,   67,
+       67,   72,   67,   67,   73,   67,   74,   67,   75
+    },
+
+    {
+        9,   76,   76,  -43,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76
+    },
+
+    {
+        9,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,
+      -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,
+      -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,
+      -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44
+
+    },
+
+    {
+        9,  -45,   45,   46,  -45,  -45,  -45,  -45,  -45,  -45,
+      -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,
+      -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,
+      -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45
+    },
+
+    {
+        9,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,
+      -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,
+      -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,
+      -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46
+    },
+
+    {
+        9,   47,   47,   48,   47,   47,   47,   47,   47,   47,
+       47,   47,   47,   47,   47,   47,   47,   47,   47,   47,
+
+       47,   47,   47,   47,   47,   47,   47,   47,   47,   47,
+       47,   47,   47,   47,   47,   47,   47,   47,   47
+    },
+
+    {
+        9,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,
+      -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,
+      -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,
+      -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48
+    },
+
+    {
+        9,  -49,  -49,  -49,  -49,  -49,  -49,  -49,  -49,  -49,
+      -49,  -49,  -49,  -49,  -49,  -49,  -49,  -49,  -49,  -49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -50,  -50,  -50,  -50,  -50,  -50,  -50,  -50,  -50,
+      -50,  -50,  -50,  -50,  -50,  -50,  -50,  -50,  -50,  -50,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   77,   49,   49,   49
+    },
+
+    {
+        9,  -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,
+      -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,
+       49,   49,   49,   49,   49,   49,   49,   49,   78,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -52,  -52,  -52,  -52,  -52,  -52,  -52,  -52,  -52,
+      -52,  -52,  -52,  -52,  -52,  -52,  -52,  -52,  -52,  -52,
+
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       79,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,
+      -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   80,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -54,  -54,  -54,  -54,  -54,  -54,  -54,  -54,  -54,
+      -54,  -54,  -54,  -54,  -54,  -54,  -54,  -54,  -54,  -54,
+       49,   81,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,
+      -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   82,   49,   49
+    },
+
+    {
+        9,  -56,   56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,
+      -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,
+      -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,
+      -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56
+    },
+
+    {
+        9,   57,   57,   58,   57,   57,   57,   57,   57,   57,
+       57,   57,   57,   57,   57,   57,   57,   57,   57,   57,
+
+       57,   57,   57,   57,   57,   57,   57,   57,   57,   57,
+       57,   57,   57,   57,   57,   57,   57,   57,   57
+    },
+
+    {
+        9,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,
+      -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,
+      -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,
+      -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58
+    },
+
+    {
+        9,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,
+      -59,  -59,  -59,  -59,   59,  -59,  -59,  -59,  -59,  -59,
+      -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,
+      -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59
+
+    },
+
+    {
+        9,  -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,
+      -60,  -60,  -60,  -60,   59,  -60,  -60,  -60,  -60,  -60,
+      -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,
+      -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60
+    },
+
+    {
+        9,  -61,  -61,  -61,  -61,  -61,  -61,  -61,  -61,  -61,
+      -61,  -61,   60,  -61,   61,  -61,   62,  -61,  -61,  -61,
+       62,   62,   62,   62,   62,   62,   62,   62,   62,   62,
+       62,   62,   62,   62,   62,   62,   62,   62,   62
+    },
+
+    {
+        9,  -62,  -62,  -62,  -62,  -62,  -62,  -62,  -62,  -62,
+      -62,  -62,  -62,  -62,   62,  -62,   62,  -62,  -62,  -62,
+
+       62,   62,   62,   62,   62,   62,   62,   62,   62,   62,
+       62,   62,   62,   62,   62,   62,   62,   62,   62
+    },
+
+    {
+        9,  -63,   63,   64,  -63,  -63,  -63,  -63,  -63,  -63,
+      -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,
+      -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,
+      -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63
+    },
+
+    {
+        9,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,
+      -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,
+      -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,
+      -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64
+
+    },
+
+    {
+        9,   65,   65,  -65,  -65,   65,   65,   65,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,  -65,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,   65,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,   65,   65
+    },
+
+    {
+        9,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,
+      -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,
+      -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,
+      -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66
+    },
+
+    {
+        9,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,
+      -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,
+
+      -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,
+      -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67
+    },
+
+    {
+        9,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,
+      -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,
+      -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,
+      -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68
+    },
+
+    {
+        9,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,
+      -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,
+      -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,
+      -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69
+
+    },
+
+    {
+        9,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,
+      -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,
+      -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,
+      -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70
+    },
+
+    {
+        9,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,
+      -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,
+      -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,
+      -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71
+    },
+
+    {
+        9,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,
+      -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,
+
+      -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,
+      -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72
+    },
+
+    {
+        9,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,
+      -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,
+      -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,
+      -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73
+    },
+
+    {
+        9,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,
+      -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,
+      -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,
+      -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74
+
+    },
+
+    {
+        9,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,
+      -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,
+      -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,
+      -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75
+    },
+
+    {
+        9,   76,   76,  -76,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76
+    },
+
+    {
+        9,  -77,   83,  -77,  -77,  -77,  -77,  -77,  -77,  -77,
+      -77,  -77,  -77,  -77,  -77,  -77,  -77,  -77,  -77,  -77,
+
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -78,  -78,  -78,  -78,  -78,  -78,  -78,  -78,  -78,
+      -78,  -78,  -78,  -78,  -78,  -78,  -78,  -78,  -78,  -78,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   84,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -79,  -79,  -79,  -79,  -79,  -79,  -79,  -79,  -79,
+      -79,  -79,  -79,  -79,  -79,  -79,  -79,  -79,  -79,  -79,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   85,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -80,  -80,  -80,  -80,  -80,  -80,  -80,  -80,  -80,
+      -80,  -80,  -80,  -80,  -80,  -80,  -80,  -80,  -80,  -80,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   86,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -81,  -81,  -81,  -81,  -81,  -81,  -81,  -81,  -81,
+      -81,  -81,  -81,  -81,  -81,  -81,  -81,  -81,  -81,  -81,
+       49,   49,   49,   49,   87,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -82,   88,  -82,  -82,  -82,  -82,  -82,  -82,  -82,
+      -82,  -82,  -82,  -82,  -82,  -82,  -82,  -82,  -82,  -82,
+
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -83,   83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,
+      -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,
+      -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,
+      -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83
+    },
+
+    {
+        9,  -84,   89,  -84,  -84,  -84,  -84,  -84,  -84,  -84,
+      -84,  -84,  -84,  -84,  -84,  -84,  -84,  -84,  -84,  -84,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -85,  -85,  -85,  -85,  -85,  -85,  -85,  -85,  -85,
+      -85,  -85,  -85,  -85,  -85,  -85,  -85,  -85,  -85,  -85,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   90,   49
+    },
+
+    {
+        9,  -86,  -86,  -86,  -86,  -86,  -86,  -86,  -86,  -86,
+      -86,  -86,  -86,  -86,  -86,  -86,  -86,  -86,  -86,  -86,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   91,   49,   49,   49,   49
+    },
+
+    {
+        9,  -87,  -87,  -87,  -87,  -87,  -87,  -87,  -87,  -87,
+      -87,  -87,  -87,  -87,  -87,  -87,  -87,  -87,  -87,  -87,
+
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   92,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -88,   88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,
+      -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,
+      -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,
+      -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88
+    },
+
+    {
+        9,  -89,   89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,
+      -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,
+      -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,
+      -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89
+
+    },
+
+    {
+        9,  -90,  -90,  -90,  -90,  -90,  -90,  -90,  -90,  -90,
+      -90,  -90,  -90,  -90,  -90,  -90,  -90,  -90,  -90,  -90,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   93,   49,   49
+    },
+
+    {
+        9,  -91,  -91,  -91,  -91,  -91,  -91,  -91,  -91,  -91,
+      -91,  -91,  -91,  -91,  -91,  -91,  -91,  -91,  -91,  -91,
+       49,   49,   49,   49,   94,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -92,   95,  -92,  -92,  -92,  -92,  -92,  -92,  -92,
+      -92,  -92,  -92,  -92,  -92,  -92,  -92,  -92,  -92,  -92,
+
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -93,  -93,  -93,  -93,  -93,  -93,  -93,  -93,  -93,
+      -93,  -93,  -93,  -93,  -93,  -93,  -93,  -93,  -93,  -93,
+       49,   49,   49,   49,   96,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -94,   97,  -94,  -94,  -94,  -94,  -94,  -94,  -94,
+      -94,  -94,  -94,  -94,  -94,  -94,  -94,  -94,  -94,  -94,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -95,   95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,
+      -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,
+      -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,
+      -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95
+    },
+
+    {
+        9,  -96,   98,  -96,  -96,  -96,  -96,  -96,  -96,  -96,
+      -96,  -96,  -96,  -96,  -96,  -96,  -96,  -96,  -96,  -96,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -97,   97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,
+      -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,
+
+      -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,
+      -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97
+    },
+
+    {
+        9,  -98,   98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,
+      -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,
+      -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,
+      -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98
+    },
+
+    } ;
+
+static yy_state_type yy_get_previous_state (void );
+static yy_state_type yy_try_NUL_trans (yy_state_type current_state  );
+static int yy_get_next_buffer (void );
+static void yy_fatal_error (yyconst char msg[]  );
+
+/* Done after the current pattern has been matched and before the
+ * corresponding action - sets up sensors_yytext.
+ */
+#define YY_DO_BEFORE_ACTION \
+	(yytext_ptr) = yy_bp; \
+	sensors_yyleng = (size_t) (yy_cp - yy_bp); \
+	(yy_hold_char) = *yy_cp; \
+	*yy_cp = '\0'; \
+	(yy_c_buf_p) = yy_cp;
+
+#define YY_NUM_RULES 50
+#define YY_END_OF_BUFFER 51
+/* This struct is not used in this scanner,
+   but its presence is necessary. */
+struct yy_trans_info
+	{
+	flex_int32_t yy_verify;
+	flex_int32_t yy_nxt;
+	};
+static yyconst flex_int16_t yy_accept[99] =
+    {   0,
+        0,    0,    0,    0,    0,    0,   13,   13,   51,   12,
+        1,    2,    3,   11,   11,   11,   11,   11,   11,   33,
+       15,   16,   31,   18,   25,   26,   23,   21,   27,   22,
+       33,   24,   20,   28,   32,   33,   29,   30,   49,   36,
+       39,   48,   13,   14,    1,    2,    3,    4,   11,   11,
+       11,   11,   11,   11,   11,   15,   18,   19,   20,   34,
+       20,   32,   35,   17,   49,   38,   47,   37,   40,   41,
+       42,   43,   44,   45,   46,   13,    8,   11,   11,   11,
+       11,    6,    8,    9,   11,   11,   11,    6,    9,   11,
+       11,    5,   11,   10,    5,    7,   10,    7
+
+    } ;
+
+static yyconst flex_int32_t yy_ec[256] =
+    {   0,
+        1,    1,    1,    1,    1,    1,    1,    1,    2,    3,
+        2,    2,    2,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    2,    1,    4,    5,    1,    1,    1,    1,    6,
+        7,    8,    9,   10,   11,   12,   13,   14,   14,   14,
+       14,   14,   14,   14,   14,   14,   14,    1,    1,    1,
+        1,    1,    1,   15,   16,   16,   16,   16,   16,   16,
+       16,   16,   16,   16,   16,   16,   16,   16,   16,   16,
+       16,   16,   16,   16,   16,   16,   16,   16,   16,   16,
+        1,   17,    1,   18,   16,   19,   20,   21,   22,   23,
+
+       24,   25,   26,   27,   28,   23,   23,   29,   30,   31,
+       32,   33,   23,   34,   35,   36,   37,   38,   23,   23,
+       23,   23,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1
+    } ;
+
+extern int sensors_yy_flex_debug;
+int sensors_yy_flex_debug = 0;
+
+/* The intent behind this definition is that it'll catch
+ * any uses of REJECT which flex missed.
+ */
+#define REJECT reject_used_but_not_detected
+#define yymore() yymore_used_but_not_detected
+#define YY_MORE_ADJ 0
+#define YY_RESTORE_YY_MORE_OFFSET
+char *sensors_yytext;
+#line 1 "lib/conf-lex.l"
+#line 2 "lib/conf-lex.l"
+/*
+    conf-lex.l - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl> 
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "general.h"
+#include "data.h"
+#include "conf-parse.h"
+#include "error.h"
+#include "scanner.h"
+
+static int buffer_count;
+static int buffer_max;
+static char *buffer;
+
+char sensors_lex_error[100];
+
+const char *sensors_yyfilename;
+int sensors_yylineno;
+
+#define buffer_malloc() sensors_malloc_array(&buffer,&buffer_count,\
+                                             &buffer_max,1)
+#define buffer_free() sensors_free_array(&buffer,&buffer_count,\
+                                         &buffer_max)
+#define buffer_add_char(c) sensors_add_array_el(c,&buffer,\
+                                                &buffer_count,\
+                                                &buffer_max,1)
+#define buffer_add_string(s) sensors_add_array_els(s,strlen(s),\
+                                                   &buffer, \
+                                                   &buffer_count,&buffer_max,1)
+
+/* Scanner for configuration files */
+/* All states are exclusive */
+
+
+
+/* Any whitespace-like character */
+/* Note: `10', `10.4' and `.4' are valid, `10.' is not */
+/* Only positive whole numbers are recognized here */
+#line 1255 "<stdout>"
+
+#define INITIAL 0
+#define MIDDLE 1
+#define STRING 2
+#define ERR 3
+
+#ifndef YY_NO_UNISTD_H
+/* Special case for "unistd.h", since it is non-ANSI. We include it way
+ * down here because we want the user's section 1 to have been scanned first.
+ * The user has a chance to override it with an option.
+ */
+#include <unistd.h>
+#endif
+
+#ifndef YY_EXTRA_TYPE
+#define YY_EXTRA_TYPE void *
+#endif
+
+static int yy_init_globals (void );
+
+/* Accessor methods to globals.
+   These are made visible to non-reentrant scanners for convenience. */
+
+int sensors_yylex_destroy (void );
+
+int sensors_yyget_debug (void );
+
+void sensors_yyset_debug (int debug_flag  );
+
+YY_EXTRA_TYPE sensors_yyget_extra (void );
+
+void sensors_yyset_extra (YY_EXTRA_TYPE user_defined  );
+
+FILE *sensors_yyget_in (void );
+
+void sensors_yyset_in  (FILE * in_str  );
+
+FILE *sensors_yyget_out (void );
+
+void sensors_yyset_out  (FILE * out_str  );
+
+int sensors_yyget_leng (void );
+
+char *sensors_yyget_text (void );
+
+int sensors_yyget_lineno (void );
+
+void sensors_yyset_lineno (int line_number  );
+
+/* Macros after this point can all be overridden by user definitions in
+ * section 1.
+ */
+
+#ifndef YY_SKIP_YYWRAP
+#ifdef __cplusplus
+extern "C" int sensors_yywrap (void );
+#else
+extern int sensors_yywrap (void );
+#endif
+#endif
+
+#ifndef yytext_ptr
+static void yy_flex_strncpy (char *,yyconst char *,int );
+#endif
+
+#ifdef YY_NEED_STRLEN
+static int yy_flex_strlen (yyconst char * );
+#endif
+
+#ifndef YY_NO_INPUT
+
+#ifdef __cplusplus
+static int yyinput (void );
+#else
+static int input (void );
+#endif
+
+#endif
+
+/* Amount of stuff to slurp up with each read. */
+#ifndef YY_READ_BUF_SIZE
+#ifdef __ia64__
+/* On IA-64, the buffer size is 16k, not 8k */
+#define YY_READ_BUF_SIZE 16384
+#else
+#define YY_READ_BUF_SIZE 8192
+#endif /* __ia64__ */
+#endif
+
+/* Copy whatever the last rule matched to the standard output. */
+#ifndef ECHO
+/* This used to be an fputs(), but since the string might contain NUL's,
+ * we now use fwrite().
+ */
+#define ECHO do { if (fwrite( sensors_yytext, sensors_yyleng, 1, sensors_yyout )) {} } while (0)
+#endif
+
+/* Gets input and stuffs it into "buf".  number of characters read, or YY_NULL,
+ * is returned in "result".
+ */
+#ifndef YY_INPUT
+#define YY_INPUT(buf,result,max_size) \
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_is_interactive ) \
+		{ \
+		int c = '*'; \
+		size_t n; \
+		for ( n = 0; n < max_size && \
+			     (c = getc( sensors_yyin )) != EOF && c != '\n'; ++n ) \
+			buf[n] = (char) c; \
+		if ( c == '\n' ) \
+			buf[n++] = (char) c; \
+		if ( c == EOF && ferror( sensors_yyin ) ) \
+			YY_FATAL_ERROR( "input in flex scanner failed" ); \
+		result = n; \
+		} \
+	else \
+		{ \
+		errno=0; \
+		while ( (result = fread(buf, 1, max_size, sensors_yyin))==0 && ferror(sensors_yyin)) \
+			{ \
+			if( errno != EINTR) \
+				{ \
+				YY_FATAL_ERROR( "input in flex scanner failed" ); \
+				break; \
+				} \
+			errno=0; \
+			clearerr(sensors_yyin); \
+			} \
+		}\
+\
+
+#endif
+
+/* No semi-colon after return; correct usage is to write "yyterminate();" -
+ * we don't want an extra ';' after the "return" because that will cause
+ * some compilers to complain about unreachable statements.
+ */
+#ifndef yyterminate
+#define yyterminate() return YY_NULL
+#endif
+
+/* Number of entries by which start-condition stack grows. */
+#ifndef YY_START_STACK_INCR
+#define YY_START_STACK_INCR 25
+#endif
+
+/* Report a fatal error. */
+#ifndef YY_FATAL_ERROR
+#define YY_FATAL_ERROR(msg) yy_fatal_error( msg )
+#endif
+
+/* end tables serialization structures and prototypes */
+
+/* Default declaration of generated scanner - a define so the user can
+ * easily add parameters.
+ */
+#ifndef YY_DECL
+#define YY_DECL_IS_OURS 1
+
+extern int sensors_yylex (void);
+
+#define YY_DECL int sensors_yylex (void)
+#endif /* !YY_DECL */
+
+/* Code executed at the beginning of each rule, after sensors_yytext and sensors_yyleng
+ * have been set up.
+ */
+#ifndef YY_USER_ACTION
+#define YY_USER_ACTION
+#endif
+
+/* Code executed at the end of each rule. */
+#ifndef YY_BREAK
+#define YY_BREAK break;
+#endif
+
+#define YY_RULE_SETUP \
+	YY_USER_ACTION
+
+/** The main scanner function which does all the work.
+ */
+YY_DECL
+{
+	register yy_state_type yy_current_state;
+	register char *yy_cp, *yy_bp;
+	register int yy_act;
+    
+#line 80 "lib/conf-lex.l"
+
+
+ /*
+  * STATE: INITIAL
+  */
+
+#line 1450 "<stdout>"
+
+	if ( !(yy_init) )
+		{
+		(yy_init) = 1;
+
+#ifdef YY_USER_INIT
+		YY_USER_INIT;
+#endif
+
+		if ( ! (yy_start) )
+			(yy_start) = 1;	/* first start state */
+
+		if ( ! sensors_yyin )
+			sensors_yyin = stdin;
+
+		if ( ! sensors_yyout )
+			sensors_yyout = stdout;
+
+		if ( ! YY_CURRENT_BUFFER ) {
+			sensors_yyensure_buffer_stack ();
+			YY_CURRENT_BUFFER_LVALUE =
+				sensors_yy_create_buffer(sensors_yyin,YY_BUF_SIZE );
+		}
+
+		sensors_yy_load_buffer_state( );
+		}
+
+	while ( 1 )		/* loops until end-of-file is reached */
+		{
+		yy_cp = (yy_c_buf_p);
+
+		/* Support of sensors_yytext. */
+		*yy_cp = (yy_hold_char);
+
+		/* yy_bp points to the position in yy_ch_buf of the start of
+		 * the current run.
+		 */
+		yy_bp = yy_cp;
+
+		yy_current_state = (yy_start);
+yy_match:
+		while ( (yy_current_state = yy_nxt[yy_current_state][ yy_ec[YY_SC_TO_UI(*yy_cp)]  ]) > 0 )
+			++yy_cp;
+
+		yy_current_state = -yy_current_state;
+
+yy_find_action:
+		yy_act = yy_accept[yy_current_state];
+
+		YY_DO_BEFORE_ACTION;
+
+do_action:	/* This label is used only to access EOF actions. */
+
+		switch ( yy_act )
+	{ /* beginning of action switch */
+
+case YY_STATE_EOF(INITIAL):
+#line 88 "lib/conf-lex.l"
+{ /* EOF from this state terminates */
+		  return 0;
+		}
+	YY_BREAK
+case 1:
+YY_RULE_SETUP
+#line 92 "lib/conf-lex.l"
+; /* eat as many blanks as possible at once */
+	YY_BREAK
+case 2:
+/* rule 2 can match eol */
+YY_RULE_SETUP
+#line 94 "lib/conf-lex.l"
+{ /* eat a bare newline (possibly preceded by blanks) */
+		  sensors_yylineno++;
+		}
+	YY_BREAK
+/* comments */
+case 3:
+YY_RULE_SETUP
+#line 100 "lib/conf-lex.l"
+; /* eat the rest of the line after comment char */
+	YY_BREAK
+case 4:
+/* rule 4 can match eol */
+YY_RULE_SETUP
+#line 102 "lib/conf-lex.l"
+{ /* eat the rest of the line after comment char */
+		  sensors_yylineno++;
+		}
+	YY_BREAK
+/*
+  * Keywords must be followed by whitespace - eat that too.
+  * If there isn't trailing whitespace, we still need to
+  * accept it as lexically correct (even though the parser
+  * will reject it anyway.)
+  */
+case 5:
+YY_RULE_SETUP
+#line 113 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return LABEL;
+		}
+	YY_BREAK
+case 6:
+YY_RULE_SETUP
+#line 120 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return SET;
+		}
+	YY_BREAK
+case 7:
+YY_RULE_SETUP
+#line 127 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return COMPUTE;
+		}
+	YY_BREAK
+case 8:
+YY_RULE_SETUP
+#line 134 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return BUS;
+		}
+	YY_BREAK
+case 9:
+YY_RULE_SETUP
+#line 141 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return CHIP;
+		}
+	YY_BREAK
+case 10:
+YY_RULE_SETUP
+#line 148 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return IGNORE;
+		}
+	YY_BREAK
+/* Anything else at the beginning of a line is an error */
+case 11:
+#line 158 "lib/conf-lex.l"
+case 12:
+YY_RULE_SETUP
+#line 158 "lib/conf-lex.l"
+{
+		  BEGIN(ERR);
+		  strcpy(sensors_lex_error,"Invalid keyword");
+		  return ERROR;
+		}
+	YY_BREAK
+
+/*
+  * STATE: ERROR
+  */
+
+case 13:
+YY_RULE_SETUP
+#line 171 "lib/conf-lex.l"
+; /* eat whatever is left on this line */
+	YY_BREAK
+case 14:
+/* rule 14 can match eol */
+YY_RULE_SETUP
+#line 173 "lib/conf-lex.l"
+{
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+	YY_BREAK
+
+/*
+  * STATE: MIDDLE
+  */
+
+case 15:
+YY_RULE_SETUP
+#line 186 "lib/conf-lex.l"
+; /* eat as many blanks as possible at once */
+	YY_BREAK
+case 16:
+/* rule 16 can match eol */
+YY_RULE_SETUP
+#line 188 "lib/conf-lex.l"
+{ /* newline here sends EOL token to parser */
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+	YY_BREAK
+case YY_STATE_EOF(MIDDLE):
+#line 194 "lib/conf-lex.l"
+{ /* EOF here sends EOL token to parser also */
+		  BEGIN(INITIAL);
+		  return EOL;
+		}
+	YY_BREAK
+case 17:
+/* rule 17 can match eol */
+YY_RULE_SETUP
+#line 199 "lib/conf-lex.l"
+{ /* eat an escaped newline with no state change */
+		  sensors_yylineno++;
+		}
+	YY_BREAK
+/* comments */
+case 18:
+YY_RULE_SETUP
+#line 205 "lib/conf-lex.l"
+; /* eat the rest of the line after comment char */
+	YY_BREAK
+case 19:
+/* rule 19 can match eol */
+YY_RULE_SETUP
+#line 207 "lib/conf-lex.l"
+{ /* eat the rest of the line after comment char */
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+	YY_BREAK
+/* A number */
+case 20:
+YY_RULE_SETUP
+#line 215 "lib/conf-lex.l"
+{
+		  sensors_yylval.value = atof(sensors_yytext);
+		  return FLOAT;
+		}
+	YY_BREAK
+/* Some operators */
+case 21:
+YY_RULE_SETUP
+#line 222 "lib/conf-lex.l"
+return '+';
+	YY_BREAK
+case 22:
+YY_RULE_SETUP
+#line 223 "lib/conf-lex.l"
+return '-';
+	YY_BREAK
+case 23:
+YY_RULE_SETUP
+#line 224 "lib/conf-lex.l"
+return '*';
+	YY_BREAK
+case 24:
+YY_RULE_SETUP
+#line 225 "lib/conf-lex.l"
+return '/';
+	YY_BREAK
+case 25:
+YY_RULE_SETUP
+#line 226 "lib/conf-lex.l"
+return '(';
+	YY_BREAK
+case 26:
+YY_RULE_SETUP
+#line 227 "lib/conf-lex.l"
+return ')';
+	YY_BREAK
+case 27:
+YY_RULE_SETUP
+#line 228 "lib/conf-lex.l"
+return ',';
+	YY_BREAK
+case 28:
+YY_RULE_SETUP
+#line 229 "lib/conf-lex.l"
+return '@';
+	YY_BREAK
+case 29:
+YY_RULE_SETUP
+#line 230 "lib/conf-lex.l"
+return '^';
+	YY_BREAK
+case 30:
+YY_RULE_SETUP
+#line 231 "lib/conf-lex.l"
+return '`';
+	YY_BREAK
+/* Quoted string */
+case 31:
+YY_RULE_SETUP
+#line 235 "lib/conf-lex.l"
+{
+		  buffer_malloc();
+		  BEGIN(STRING);
+		}
+	YY_BREAK
+/* A normal, unquoted identifier */
+case 32:
+YY_RULE_SETUP
+#line 242 "lib/conf-lex.l"
+{
+		  sensors_yylval.name = strdup(sensors_yytext);
+		  if (! sensors_yylval.name)
+		    sensors_fatal_error("conf-lex.l",
+                                        "Allocating a new string");
+		  
+		  return NAME;
+		}
+	YY_BREAK
+/* anything else is bogus */
+case 33:
+#line 254 "lib/conf-lex.l"
+case 34:
+#line 255 "lib/conf-lex.l"
+case 35:
+YY_RULE_SETUP
+#line 255 "lib/conf-lex.l"
+{
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+	YY_BREAK
+
+/*
+  * STATE: STRING
+  */
+
+/* Oops, newline or EOF while in a string is not good */
+case 36:
+/* rule 36 can match eol */
+#line 270 "lib/conf-lex.l"
+case 37:
+/* rule 37 can match eol */
+YY_RULE_SETUP
+#line 270 "lib/conf-lex.l"
+{
+		  buffer_add_char("\0");
+		  strcpy(sensors_lex_error,
+			"No matching double quote.");
+		  buffer_free();
+		  yyless(0);
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+	YY_BREAK
+case YY_STATE_EOF(STRING):
+#line 280 "lib/conf-lex.l"
+{
+		  strcpy(sensors_lex_error,
+			"Reached end-of-file without a matching double quote.");
+		  buffer_free();
+		  BEGIN(MIDDLE);
+		  return ERROR;
+		}
+	YY_BREAK
+/* At the end */
+case 38:
+YY_RULE_SETUP
+#line 290 "lib/conf-lex.l"
+{
+		  buffer_add_char("\0");
+		  strcpy(sensors_lex_error,
+			"Quoted strings must be separated by whitespace.");
+		  buffer_free();
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+	YY_BREAK
+case 39:
+YY_RULE_SETUP
+#line 299 "lib/conf-lex.l"
+{
+		  buffer_add_char("\0");
+		  sensors_yylval.name = strdup(buffer);
+		  if (! sensors_yylval.name)
+		    sensors_fatal_error("conf-lex.l",
+                                        "Allocating a new string");
+		  buffer_free();
+		  BEGIN(MIDDLE);
+		  return NAME;
+		}
+	YY_BREAK
+case 40:
+YY_RULE_SETUP
+#line 310 "lib/conf-lex.l"
+buffer_add_char("\a");
+	YY_BREAK
+case 41:
+YY_RULE_SETUP
+#line 311 "lib/conf-lex.l"
+buffer_add_char("\b");
+	YY_BREAK
+case 42:
+YY_RULE_SETUP
+#line 312 "lib/conf-lex.l"
+buffer_add_char("\f");
+	YY_BREAK
+case 43:
+YY_RULE_SETUP
+#line 313 "lib/conf-lex.l"
+buffer_add_char("\n");
+	YY_BREAK
+case 44:
+YY_RULE_SETUP
+#line 314 "lib/conf-lex.l"
+buffer_add_char("\r");
+	YY_BREAK
+case 45:
+YY_RULE_SETUP
+#line 315 "lib/conf-lex.l"
+buffer_add_char("\t");
+	YY_BREAK
+case 46:
+YY_RULE_SETUP
+#line 316 "lib/conf-lex.l"
+buffer_add_char("\v");
+	YY_BREAK
+/* Other escapes: just copy the character behind the slash */
+case 47:
+YY_RULE_SETUP
+#line 320 "lib/conf-lex.l"
+{
+		  buffer_add_char(&sensors_yytext[1]);
+		}
+	YY_BREAK
+/* Anything else (including a bare '\' which may be followed by EOF) */
+case 48:
+#line 327 "lib/conf-lex.l"
+case 49:
+YY_RULE_SETUP
+#line 327 "lib/conf-lex.l"
+{
+		  buffer_add_string(sensors_yytext);
+		}
+	YY_BREAK
+
+case 50:
+YY_RULE_SETUP
+#line 332 "lib/conf-lex.l"
+YY_FATAL_ERROR( "flex scanner jammed" );
+	YY_BREAK
+#line 1903 "<stdout>"
+			case YY_STATE_EOF(ERR):
+				yyterminate();
+
+	case YY_END_OF_BUFFER:
+		{
+		/* Amount of text matched not including the EOB char. */
+		int yy_amount_of_matched_text = (int) (yy_cp - (yytext_ptr)) - 1;
+
+		/* Undo the effects of YY_DO_BEFORE_ACTION. */
+		*yy_cp = (yy_hold_char);
+		YY_RESTORE_YY_MORE_OFFSET
+
+		if ( YY_CURRENT_BUFFER_LVALUE->yy_buffer_status == YY_BUFFER_NEW )
+			{
+			/* We're scanning a new file or input source.  It's
+			 * possible that this happened because the user
+			 * just pointed sensors_yyin at a new source and called
+			 * sensors_yylex().  If so, then we have to assure
+			 * consistency between YY_CURRENT_BUFFER and our
+			 * globals.  Here is the right place to do so, because
+			 * this is the first action (other than possibly a
+			 * back-up) that will match for the new input source.
+			 */
+			(yy_n_chars) = YY_CURRENT_BUFFER_LVALUE->yy_n_chars;
+			YY_CURRENT_BUFFER_LVALUE->yy_input_file = sensors_yyin;
+			YY_CURRENT_BUFFER_LVALUE->yy_buffer_status = YY_BUFFER_NORMAL;
+			}
+
+		/* Note that here we test for yy_c_buf_p "<=" to the position
+		 * of the first EOB in the buffer, since yy_c_buf_p will
+		 * already have been incremented past the NUL character
+		 * (since all states make transitions on EOB to the
+		 * end-of-buffer state).  Contrast this with the test
+		 * in input().
+		 */
+		if ( (yy_c_buf_p) <= &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] )
+			{ /* This was really a NUL. */
+			yy_state_type yy_next_state;
+
+			(yy_c_buf_p) = (yytext_ptr) + yy_amount_of_matched_text;
+
+			yy_current_state = yy_get_previous_state(  );
+
+			/* Okay, we're now positioned to make the NUL
+			 * transition.  We couldn't have
+			 * yy_get_previous_state() go ahead and do it
+			 * for us because it doesn't know how to deal
+			 * with the possibility of jamming (and we don't
+			 * want to build jamming into it because then it
+			 * will run more slowly).
+			 */
+
+			yy_next_state = yy_try_NUL_trans( yy_current_state );
+
+			yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+
+			if ( yy_next_state )
+				{
+				/* Consume the NUL. */
+				yy_cp = ++(yy_c_buf_p);
+				yy_current_state = yy_next_state;
+				goto yy_match;
+				}
+
+			else
+				{
+				yy_cp = (yy_c_buf_p);
+				goto yy_find_action;
+				}
+			}
+
+		else switch ( yy_get_next_buffer(  ) )
+			{
+			case EOB_ACT_END_OF_FILE:
+				{
+				(yy_did_buffer_switch_on_eof) = 0;
+
+				if ( sensors_yywrap( ) )
+					{
+					/* Note: because we've taken care in
+					 * yy_get_next_buffer() to have set up
+					 * sensors_yytext, we can now set up
+					 * yy_c_buf_p so that if some total
+					 * hoser (like flex itself) wants to
+					 * call the scanner after we return the
+					 * YY_NULL, it'll still work - another
+					 * YY_NULL will get returned.
+					 */
+					(yy_c_buf_p) = (yytext_ptr) + YY_MORE_ADJ;
+
+					yy_act = YY_STATE_EOF(YY_START);
+					goto do_action;
+					}
+
+				else
+					{
+					if ( ! (yy_did_buffer_switch_on_eof) )
+						YY_NEW_FILE;
+					}
+				break;
+				}
+
+			case EOB_ACT_CONTINUE_SCAN:
+				(yy_c_buf_p) =
+					(yytext_ptr) + yy_amount_of_matched_text;
+
+				yy_current_state = yy_get_previous_state(  );
+
+				yy_cp = (yy_c_buf_p);
+				yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+				goto yy_match;
+
+			case EOB_ACT_LAST_MATCH:
+				(yy_c_buf_p) =
+				&YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)];
+
+				yy_current_state = yy_get_previous_state(  );
+
+				yy_cp = (yy_c_buf_p);
+				yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+				goto yy_find_action;
+			}
+		break;
+		}
+
+	default:
+		YY_FATAL_ERROR(
+			"fatal flex scanner internal error--no action found" );
+	} /* end of action switch */
+		} /* end of scanning one token */
+} /* end of sensors_yylex */
+
+/* yy_get_next_buffer - try to read in a new buffer
+ *
+ * Returns a code representing an action:
+ *	EOB_ACT_LAST_MATCH -
+ *	EOB_ACT_CONTINUE_SCAN - continue scanning from current position
+ *	EOB_ACT_END_OF_FILE - end of file
+ */
+static int yy_get_next_buffer (void)
+{
+    	register char *dest = YY_CURRENT_BUFFER_LVALUE->yy_ch_buf;
+	register char *source = (yytext_ptr);
+	register int number_to_move, i;
+	int ret_val;
+
+	if ( (yy_c_buf_p) > &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars) + 1] )
+		YY_FATAL_ERROR(
+		"fatal flex scanner internal error--end of buffer missed" );
+
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_fill_buffer == 0 )
+		{ /* Don't try to fill the buffer, so this is an EOF. */
+		if ( (yy_c_buf_p) - (yytext_ptr) - YY_MORE_ADJ == 1 )
+			{
+			/* We matched a single character, the EOB, so
+			 * treat this as a final EOF.
+			 */
+			return EOB_ACT_END_OF_FILE;
+			}
+
+		else
+			{
+			/* We matched some text prior to the EOB, first
+			 * process it.
+			 */
+			return EOB_ACT_LAST_MATCH;
+			}
+		}
+
+	/* Try to read more data. */
+
+	/* First move last chars to start of buffer. */
+	number_to_move = (int) ((yy_c_buf_p) - (yytext_ptr)) - 1;
+
+	for ( i = 0; i < number_to_move; ++i )
+		*(dest++) = *(source++);
+
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_buffer_status == YY_BUFFER_EOF_PENDING )
+		/* don't do the read, it's not guaranteed to return an EOF,
+		 * just force an EOF
+		 */
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars) = 0;
+
+	else
+		{
+			int num_to_read =
+			YY_CURRENT_BUFFER_LVALUE->yy_buf_size - number_to_move - 1;
+
+		while ( num_to_read <= 0 )
+			{ /* Not enough room in the buffer - grow it. */
+
+			/* just a shorter name for the current buffer */
+			YY_BUFFER_STATE b = YY_CURRENT_BUFFER;
+
+			int yy_c_buf_p_offset =
+				(int) ((yy_c_buf_p) - b->yy_ch_buf);
+
+			if ( b->yy_is_our_buffer )
+				{
+				int new_size = b->yy_buf_size * 2;
+
+				if ( new_size <= 0 )
+					b->yy_buf_size += b->yy_buf_size / 8;
+				else
+					b->yy_buf_size *= 2;
+
+				b->yy_ch_buf = (char *)
+					/* Include room in for 2 EOB chars. */
+					sensors_yyrealloc((void *) b->yy_ch_buf,b->yy_buf_size + 2  );
+				}
+			else
+				/* Can't grow it, we don't own it. */
+				b->yy_ch_buf = 0;
+
+			if ( ! b->yy_ch_buf )
+				YY_FATAL_ERROR(
+				"fatal error - scanner input buffer overflow" );
+
+			(yy_c_buf_p) = &b->yy_ch_buf[yy_c_buf_p_offset];
+
+			num_to_read = YY_CURRENT_BUFFER_LVALUE->yy_buf_size -
+						number_to_move - 1;
+
+			}
+
+		if ( num_to_read > YY_READ_BUF_SIZE )
+			num_to_read = YY_READ_BUF_SIZE;
+
+		/* Read in more data. */
+		YY_INPUT( (&YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[number_to_move]),
+			(yy_n_chars), (size_t) num_to_read );
+
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	if ( (yy_n_chars) == 0 )
+		{
+		if ( number_to_move == YY_MORE_ADJ )
+			{
+			ret_val = EOB_ACT_END_OF_FILE;
+			sensors_yyrestart(sensors_yyin  );
+			}
+
+		else
+			{
+			ret_val = EOB_ACT_LAST_MATCH;
+			YY_CURRENT_BUFFER_LVALUE->yy_buffer_status =
+				YY_BUFFER_EOF_PENDING;
+			}
+		}
+
+	else
+		ret_val = EOB_ACT_CONTINUE_SCAN;
+
+	if ((yy_size_t) ((yy_n_chars) + number_to_move) > YY_CURRENT_BUFFER_LVALUE->yy_buf_size) {
+		/* Extend the array by 50%, plus the number we really need. */
+		yy_size_t new_size = (yy_n_chars) + number_to_move + ((yy_n_chars) >> 1);
+		YY_CURRENT_BUFFER_LVALUE->yy_ch_buf = (char *) sensors_yyrealloc((void *) YY_CURRENT_BUFFER_LVALUE->yy_ch_buf,new_size  );
+		if ( ! YY_CURRENT_BUFFER_LVALUE->yy_ch_buf )
+			YY_FATAL_ERROR( "out of dynamic memory in yy_get_next_buffer()" );
+	}
+
+	(yy_n_chars) += number_to_move;
+	YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] = YY_END_OF_BUFFER_CHAR;
+	YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars) + 1] = YY_END_OF_BUFFER_CHAR;
+
+	(yytext_ptr) = &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[0];
+
+	return ret_val;
+}
+
+/* yy_get_previous_state - get the state just before the EOB char was reached */
+
+    static yy_state_type yy_get_previous_state (void)
+{
+	register yy_state_type yy_current_state;
+	register char *yy_cp;
+    
+	yy_current_state = (yy_start);
+
+	for ( yy_cp = (yytext_ptr) + YY_MORE_ADJ; yy_cp < (yy_c_buf_p); ++yy_cp )
+		{
+		yy_current_state = yy_nxt[yy_current_state][(*yy_cp ? yy_ec[YY_SC_TO_UI(*yy_cp)] : 1)];
+		}
+
+	return yy_current_state;
+}
+
+/* yy_try_NUL_trans - try to make a transition on the NUL character
+ *
+ * synopsis
+ *	next_state = yy_try_NUL_trans( current_state );
+ */
+    static yy_state_type yy_try_NUL_trans  (yy_state_type yy_current_state )
+{
+	register int yy_is_jam;
+    
+	yy_current_state = yy_nxt[yy_current_state][1];
+	yy_is_jam = (yy_current_state <= 0);
+
+	return yy_is_jam ? 0 : yy_current_state;
+}
+
+#ifndef YY_NO_INPUT
+#ifdef __cplusplus
+    static int yyinput (void)
+#else
+    static int input  (void)
+#endif
+
+{
+	int c;
+    
+	*(yy_c_buf_p) = (yy_hold_char);
+
+	if ( *(yy_c_buf_p) == YY_END_OF_BUFFER_CHAR )
+		{
+		/* yy_c_buf_p now points to the character we want to return.
+		 * If this occurs *before* the EOB characters, then it's a
+		 * valid NUL; if not, then we've hit the end of the buffer.
+		 */
+		if ( (yy_c_buf_p) < &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] )
+			/* This was really a NUL. */
+			*(yy_c_buf_p) = '\0';
+
+		else
+			{ /* need more input */
+			int offset = (yy_c_buf_p) - (yytext_ptr);
+			++(yy_c_buf_p);
+
+			switch ( yy_get_next_buffer(  ) )
+				{
+				case EOB_ACT_LAST_MATCH:
+					/* This happens because yy_g_n_b()
+					 * sees that we've accumulated a
+					 * token and flags that we need to
+					 * try matching the token before
+					 * proceeding.  But for input(),
+					 * there's no matching to consider.
+					 * So convert the EOB_ACT_LAST_MATCH
+					 * to EOB_ACT_END_OF_FILE.
+					 */
+
+					/* Reset buffer status. */
+					sensors_yyrestart(sensors_yyin );
+
+					/*FALLTHROUGH*/
+
+				case EOB_ACT_END_OF_FILE:
+					{
+					if ( sensors_yywrap( ) )
+						return EOF;
+
+					if ( ! (yy_did_buffer_switch_on_eof) )
+						YY_NEW_FILE;
+#ifdef __cplusplus
+					return yyinput();
+#else
+					return input();
+#endif
+					}
+
+				case EOB_ACT_CONTINUE_SCAN:
+					(yy_c_buf_p) = (yytext_ptr) + offset;
+					break;
+				}
+			}
+		}
+
+	c = *(unsigned char *) (yy_c_buf_p);	/* cast for 8-bit char's */
+	*(yy_c_buf_p) = '\0';	/* preserve sensors_yytext */
+	(yy_hold_char) = *++(yy_c_buf_p);
+
+	return c;
+}
+#endif	/* ifndef YY_NO_INPUT */
+
+/** Immediately switch to a different input stream.
+ * @param input_file A readable stream.
+ * 
+ * @note This function does not reset the start condition to @c INITIAL .
+ */
+    void sensors_yyrestart  (FILE * input_file )
+{
+    
+	if ( ! YY_CURRENT_BUFFER ){
+        sensors_yyensure_buffer_stack ();
+		YY_CURRENT_BUFFER_LVALUE =
+            sensors_yy_create_buffer(sensors_yyin,YY_BUF_SIZE );
+	}
+
+	sensors_yy_init_buffer(YY_CURRENT_BUFFER,input_file );
+	sensors_yy_load_buffer_state( );
+}
+
+/** Switch to a different input buffer.
+ * @param new_buffer The new input buffer.
+ * 
+ */
+    void sensors_yy_switch_to_buffer  (YY_BUFFER_STATE  new_buffer )
+{
+    
+	/* TODO. We should be able to replace this entire function body
+	 * with
+	 *		sensors_yypop_buffer_state();
+	 *		sensors_yypush_buffer_state(new_buffer);
+     */
+	sensors_yyensure_buffer_stack ();
+	if ( YY_CURRENT_BUFFER == new_buffer )
+		return;
+
+	if ( YY_CURRENT_BUFFER )
+		{
+		/* Flush out information for old buffer. */
+		*(yy_c_buf_p) = (yy_hold_char);
+		YY_CURRENT_BUFFER_LVALUE->yy_buf_pos = (yy_c_buf_p);
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	YY_CURRENT_BUFFER_LVALUE = new_buffer;
+	sensors_yy_load_buffer_state( );
+
+	/* We don't actually know whether we did this switch during
+	 * EOF (sensors_yywrap()) processing, but the only time this flag
+	 * is looked at is after sensors_yywrap() is called, so it's safe
+	 * to go ahead and always set it.
+	 */
+	(yy_did_buffer_switch_on_eof) = 1;
+}
+
+static void sensors_yy_load_buffer_state  (void)
+{
+    	(yy_n_chars) = YY_CURRENT_BUFFER_LVALUE->yy_n_chars;
+	(yytext_ptr) = (yy_c_buf_p) = YY_CURRENT_BUFFER_LVALUE->yy_buf_pos;
+	sensors_yyin = YY_CURRENT_BUFFER_LVALUE->yy_input_file;
+	(yy_hold_char) = *(yy_c_buf_p);
+}
+
+/** Allocate and initialize an input buffer state.
+ * @param file A readable stream.
+ * @param size The character buffer size in bytes. When in doubt, use @c YY_BUF_SIZE.
+ * 
+ * @return the allocated buffer state.
+ */
+    YY_BUFFER_STATE sensors_yy_create_buffer  (FILE * file, int  size )
+{
+	YY_BUFFER_STATE b;
+    
+	b = (YY_BUFFER_STATE) sensors_yyalloc(sizeof( struct yy_buffer_state )  );
+	if ( ! b )
+		YY_FATAL_ERROR( "out of dynamic memory in sensors_yy_create_buffer()" );
+
+	b->yy_buf_size = size;
+
+	/* yy_ch_buf has to be 2 characters longer than the size given because
+	 * we need to put in 2 end-of-buffer characters.
+	 */
+	b->yy_ch_buf = (char *) sensors_yyalloc(b->yy_buf_size + 2  );
+	if ( ! b->yy_ch_buf )
+		YY_FATAL_ERROR( "out of dynamic memory in sensors_yy_create_buffer()" );
+
+	b->yy_is_our_buffer = 1;
+
+	sensors_yy_init_buffer(b,file );
+
+	return b;
+}
+
+/** Destroy the buffer.
+ * @param b a buffer created with sensors_yy_create_buffer()
+ * 
+ */
+    void sensors_yy_delete_buffer (YY_BUFFER_STATE  b )
+{
+    
+	if ( ! b )
+		return;
+
+	if ( b == YY_CURRENT_BUFFER ) /* Not sure if we should pop here. */
+		YY_CURRENT_BUFFER_LVALUE = (YY_BUFFER_STATE) 0;
+
+	if ( b->yy_is_our_buffer )
+		sensors_yyfree((void *) b->yy_ch_buf  );
+
+	sensors_yyfree((void *) b  );
+}
+
+#ifndef __cplusplus
+extern int isatty (int );
+#endif /* __cplusplus */
+    
+/* Initializes or reinitializes a buffer.
+ * This function is sometimes called more than once on the same buffer,
+ * such as during a sensors_yyrestart() or at EOF.
+ */
+    static void sensors_yy_init_buffer  (YY_BUFFER_STATE  b, FILE * file )
+
+{
+	int oerrno = errno;
+    
+	sensors_yy_flush_buffer(b );
+
+	b->yy_input_file = file;
+	b->yy_fill_buffer = 1;
+
+    /* If b is the current buffer, then sensors_yy_init_buffer was _probably_
+     * called from sensors_yyrestart() or through yy_get_next_buffer.
+     * In that case, we don't want to reset the lineno or column.
+     */
+    if (b != YY_CURRENT_BUFFER){
+        b->yy_bs_lineno = 1;
+        b->yy_bs_column = 0;
+    }
+
+        b->yy_is_interactive = file ? (isatty( fileno(file) ) > 0) : 0;
+    
+	errno = oerrno;
+}
+
+/** Discard all buffered characters. On the next scan, YY_INPUT will be called.
+ * @param b the buffer state to be flushed, usually @c YY_CURRENT_BUFFER.
+ * 
+ */
+    void sensors_yy_flush_buffer (YY_BUFFER_STATE  b )
+{
+    	if ( ! b )
+		return;
+
+	b->yy_n_chars = 0;
+
+	/* We always need two end-of-buffer characters.  The first causes
+	 * a transition to the end-of-buffer state.  The second causes
+	 * a jam in that state.
+	 */
+	b->yy_ch_buf[0] = YY_END_OF_BUFFER_CHAR;
+	b->yy_ch_buf[1] = YY_END_OF_BUFFER_CHAR;
+
+	b->yy_buf_pos = &b->yy_ch_buf[0];
+
+	b->yy_at_bol = 1;
+	b->yy_buffer_status = YY_BUFFER_NEW;
+
+	if ( b == YY_CURRENT_BUFFER )
+		sensors_yy_load_buffer_state( );
+}
+
+/** Pushes the new state onto the stack. The new state becomes
+ *  the current state. This function will allocate the stack
+ *  if necessary.
+ *  @param new_buffer The new state.
+ *  
+ */
+void sensors_yypush_buffer_state (YY_BUFFER_STATE new_buffer )
+{
+    	if (new_buffer == NULL)
+		return;
+
+	sensors_yyensure_buffer_stack();
+
+	/* This block is copied from sensors_yy_switch_to_buffer. */
+	if ( YY_CURRENT_BUFFER )
+		{
+		/* Flush out information for old buffer. */
+		*(yy_c_buf_p) = (yy_hold_char);
+		YY_CURRENT_BUFFER_LVALUE->yy_buf_pos = (yy_c_buf_p);
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	/* Only push if top exists. Otherwise, replace top. */
+	if (YY_CURRENT_BUFFER)
+		(yy_buffer_stack_top)++;
+	YY_CURRENT_BUFFER_LVALUE = new_buffer;
+
+	/* copied from sensors_yy_switch_to_buffer. */
+	sensors_yy_load_buffer_state( );
+	(yy_did_buffer_switch_on_eof) = 1;
+}
+
+/** Removes and deletes the top of the stack, if present.
+ *  The next element becomes the new top.
+ *  
+ */
+void sensors_yypop_buffer_state (void)
+{
+    	if (!YY_CURRENT_BUFFER)
+		return;
+
+	sensors_yy_delete_buffer(YY_CURRENT_BUFFER );
+	YY_CURRENT_BUFFER_LVALUE = NULL;
+	if ((yy_buffer_stack_top) > 0)
+		--(yy_buffer_stack_top);
+
+	if (YY_CURRENT_BUFFER) {
+		sensors_yy_load_buffer_state( );
+		(yy_did_buffer_switch_on_eof) = 1;
+	}
+}
+
+/* Allocates the stack if it does not exist.
+ *  Guarantees space for at least one push.
+ */
+static void sensors_yyensure_buffer_stack (void)
+{
+	int num_to_alloc;
+    
+	if (!(yy_buffer_stack)) {
+
+		/* First allocation is just for 2 elements, since we don't know if this
+		 * scanner will even need a stack. We use 2 instead of 1 to avoid an
+		 * immediate realloc on the next call.
+         */
+		num_to_alloc = 1;
+		(yy_buffer_stack) = (struct yy_buffer_state**)sensors_yyalloc
+								(num_to_alloc * sizeof(struct yy_buffer_state*)
+								);
+		if ( ! (yy_buffer_stack) )
+			YY_FATAL_ERROR( "out of dynamic memory in sensors_yyensure_buffer_stack()" );
+								  
+		memset((yy_buffer_stack), 0, num_to_alloc * sizeof(struct yy_buffer_state*));
+				
+		(yy_buffer_stack_max) = num_to_alloc;
+		(yy_buffer_stack_top) = 0;
+		return;
+	}
+
+	if ((yy_buffer_stack_top) >= ((yy_buffer_stack_max)) - 1){
+
+		/* Increase the buffer to prepare for a possible push. */
+		int grow_size = 8 /* arbitrary grow size */;
+
+		num_to_alloc = (yy_buffer_stack_max) + grow_size;
+		(yy_buffer_stack) = (struct yy_buffer_state**)sensors_yyrealloc
+								((yy_buffer_stack),
+								num_to_alloc * sizeof(struct yy_buffer_state*)
+								);
+		if ( ! (yy_buffer_stack) )
+			YY_FATAL_ERROR( "out of dynamic memory in sensors_yyensure_buffer_stack()" );
+
+		/* zero only the new slots.*/
+		memset((yy_buffer_stack) + (yy_buffer_stack_max), 0, grow_size * sizeof(struct yy_buffer_state*));
+		(yy_buffer_stack_max) = num_to_alloc;
+	}
+}
+
+/** Setup the input buffer state to scan directly from a user-specified character buffer.
+ * @param base the character buffer
+ * @param size the size in bytes of the character buffer
+ * 
+ * @return the newly allocated buffer state object. 
+ */
+YY_BUFFER_STATE sensors_yy_scan_buffer  (char * base, yy_size_t  size )
+{
+	YY_BUFFER_STATE b;
+    
+	if ( size < 2 ||
+	     base[size-2] != YY_END_OF_BUFFER_CHAR ||
+	     base[size-1] != YY_END_OF_BUFFER_CHAR )
+		/* They forgot to leave room for the EOB's. */
+		return 0;
+
+	b = (YY_BUFFER_STATE) sensors_yyalloc(sizeof( struct yy_buffer_state )  );
+	if ( ! b )
+		YY_FATAL_ERROR( "out of dynamic memory in sensors_yy_scan_buffer()" );
+
+	b->yy_buf_size = size - 2;	/* "- 2" to take care of EOB's */
+	b->yy_buf_pos = b->yy_ch_buf = base;
+	b->yy_is_our_buffer = 0;
+	b->yy_input_file = 0;
+	b->yy_n_chars = b->yy_buf_size;
+	b->yy_is_interactive = 0;
+	b->yy_at_bol = 1;
+	b->yy_fill_buffer = 0;
+	b->yy_buffer_status = YY_BUFFER_NEW;
+
+	sensors_yy_switch_to_buffer(b  );
+
+	return b;
+}
+
+/** Setup the input buffer state to scan a string. The next call to sensors_yylex() will
+ * scan from a @e copy of @a str.
+ * @param yystr a NUL-terminated string to scan
+ * 
+ * @return the newly allocated buffer state object.
+ * @note If you want to scan bytes that may contain NUL values, then use
+ *       sensors_yy_scan_bytes() instead.
+ */
+YY_BUFFER_STATE sensors_yy_scan_string (yyconst char * yystr )
+{
+    
+	return sensors_yy_scan_bytes(yystr,strlen(yystr) );
+}
+
+/** Setup the input buffer state to scan the given bytes. The next call to sensors_yylex() will
+ * scan from a @e copy of @a bytes.
+ * @param yybytes the byte buffer to scan
+ * @param _yybytes_len the number of bytes in the buffer pointed to by @a bytes.
+ * 
+ * @return the newly allocated buffer state object.
+ */
+YY_BUFFER_STATE sensors_yy_scan_bytes  (yyconst char * yybytes, int  _yybytes_len )
+{
+	YY_BUFFER_STATE b;
+	char *buf;
+	yy_size_t n;
+	int i;
+    
+	/* Get memory for full buffer, including space for trailing EOB's. */
+	n = _yybytes_len + 2;
+	buf = (char *) sensors_yyalloc(n  );
+	if ( ! buf )
+		YY_FATAL_ERROR( "out of dynamic memory in sensors_yy_scan_bytes()" );
+
+	for ( i = 0; i < _yybytes_len; ++i )
+		buf[i] = yybytes[i];
+
+	buf[_yybytes_len] = buf[_yybytes_len+1] = YY_END_OF_BUFFER_CHAR;
+
+	b = sensors_yy_scan_buffer(buf,n );
+	if ( ! b )
+		YY_FATAL_ERROR( "bad buffer in sensors_yy_scan_bytes()" );
+
+	/* It's okay to grow etc. this buffer, and we should throw it
+	 * away when we're done.
+	 */
+	b->yy_is_our_buffer = 1;
+
+	return b;
+}
+
+#ifndef YY_EXIT_FAILURE
+#define YY_EXIT_FAILURE 2
+#endif
+
+static void yy_fatal_error (yyconst char* msg )
+{
+    	(void) fprintf( stderr, "%s\n", msg );
+	exit( YY_EXIT_FAILURE );
+}
+
+/* Redefine yyless() so it works in section 3 code. */
+
+#undef yyless
+#define yyless(n) \
+	do \
+		{ \
+		/* Undo effects of setting up sensors_yytext. */ \
+        int yyless_macro_arg = (n); \
+        YY_LESS_LINENO(yyless_macro_arg);\
+		sensors_yytext[sensors_yyleng] = (yy_hold_char); \
+		(yy_c_buf_p) = sensors_yytext + yyless_macro_arg; \
+		(yy_hold_char) = *(yy_c_buf_p); \
+		*(yy_c_buf_p) = '\0'; \
+		sensors_yyleng = yyless_macro_arg; \
+		} \
+	while ( 0 )
+
+/* Accessor  methods (get/set functions) to struct members. */
+
+/** Get the current line number.
+ * 
+ */
+int sensors_yyget_lineno  (void)
+{
+        
+    return sensors_yylineno;
+}
+
+/** Get the input stream.
+ * 
+ */
+FILE *sensors_yyget_in  (void)
+{
+        return sensors_yyin;
+}
+
+/** Get the output stream.
+ * 
+ */
+FILE *sensors_yyget_out  (void)
+{
+        return sensors_yyout;
+}
+
+/** Get the length of the current token.
+ * 
+ */
+int sensors_yyget_leng  (void)
+{
+        return sensors_yyleng;
+}
+
+/** Get the current token.
+ * 
+ */
+
+char *sensors_yyget_text  (void)
+{
+        return sensors_yytext;
+}
+
+/** Set the current line number.
+ * @param line_number
+ * 
+ */
+void sensors_yyset_lineno (int  line_number )
+{
+    
+    sensors_yylineno = line_number;
+}
+
+/** Set the input stream. This does not discard the current
+ * input buffer.
+ * @param in_str A readable stream.
+ * 
+ * @see sensors_yy_switch_to_buffer
+ */
+void sensors_yyset_in (FILE *  in_str )
+{
+        sensors_yyin = in_str ;
+}
+
+void sensors_yyset_out (FILE *  out_str )
+{
+        sensors_yyout = out_str ;
+}
+
+int sensors_yyget_debug  (void)
+{
+        return sensors_yy_flex_debug;
+}
+
+void sensors_yyset_debug (int  bdebug )
+{
+        sensors_yy_flex_debug = bdebug ;
+}
+
+static int yy_init_globals (void)
+{
+        /* Initialization is the same as for the non-reentrant scanner.
+     * This function is called from sensors_yylex_destroy(), so don't allocate here.
+     */
+
+    (yy_buffer_stack) = 0;
+    (yy_buffer_stack_top) = 0;
+    (yy_buffer_stack_max) = 0;
+    (yy_c_buf_p) = (char *) 0;
+    (yy_init) = 0;
+    (yy_start) = 0;
+
+/* Defined in main.c */
+#ifdef YY_STDINIT
+    sensors_yyin = stdin;
+    sensors_yyout = stdout;
+#else
+    sensors_yyin = (FILE *) 0;
+    sensors_yyout = (FILE *) 0;
+#endif
+
+    /* For future reference: Set errno on error, since we are called by
+     * sensors_yylex_init()
+     */
+    return 0;
+}
+
+/* sensors_yylex_destroy is for both reentrant and non-reentrant scanners. */
+int sensors_yylex_destroy  (void)
+{
+    
+    /* Pop the buffer stack, destroying each element. */
+	while(YY_CURRENT_BUFFER){
+		sensors_yy_delete_buffer(YY_CURRENT_BUFFER  );
+		YY_CURRENT_BUFFER_LVALUE = NULL;
+		sensors_yypop_buffer_state();
+	}
+
+	/* Destroy the stack itself. */
+	sensors_yyfree((yy_buffer_stack) );
+	(yy_buffer_stack) = NULL;
+
+    /* Reset the globals. This is important in a non-reentrant scanner so the next time
+     * sensors_yylex() is called, initialization will occur. */
+    yy_init_globals( );
+
+    return 0;
+}
+
+/*
+ * Internal utility routines.
+ */
+
+#ifndef yytext_ptr
+static void yy_flex_strncpy (char* s1, yyconst char * s2, int n )
+{
+	register int i;
+	for ( i = 0; i < n; ++i )
+		s1[i] = s2[i];
+}
+#endif
+
+#ifdef YY_NEED_STRLEN
+static int yy_flex_strlen (yyconst char * s )
+{
+	register int n;
+	for ( n = 0; s[n]; ++n )
+		;
+
+	return n;
+}
+#endif
+
+void *sensors_yyalloc (yy_size_t  size )
+{
+	return (void *) malloc( size );
+}
+
+void *sensors_yyrealloc  (void * ptr, yy_size_t  size )
+{
+	/* The cast to (char *) in the following accommodates both
+	 * implementations that use char* generic pointers, and those
+	 * that use void* generic pointers.  It works with the latter
+	 * because both ANSI C and C++ allow castless assignment from
+	 * any pointer type to void*, and deal with argument conversions
+	 * as though doing an assignment.
+	 */
+	return (void *) realloc( (char *) ptr, size );
+}
+
+void sensors_yyfree (void * ptr )
+{
+	free( (char *) ptr );	/* see sensors_yyrealloc() for (char *) cast */
+}
+
+#define YYTABLES_NAME "yytables"
+
+#line 332 "lib/conf-lex.l"
+
+
+
+/*
+	Do the buffer handling manually.  This allows us to scan as many
+	config files as we need to, while cleaning up properly after each
+	one.  The "BEGIN(0)" line ensures that we start in the default state,
+	even if e.g. the previous config file was syntactically broken.
+
+	Returns 0 if successful, !0 otherwise.
+*/
+
+static YY_BUFFER_STATE scan_buf = (YY_BUFFER_STATE)0;
+
+int sensors_scanner_init(FILE *input, const char *filename)
+{
+	BEGIN(0);
+	if (!(scan_buf = sensors_yy_create_buffer(input, YY_BUF_SIZE)))
+		return -1;
+
+	sensors_yy_switch_to_buffer(scan_buf);
+	sensors_yyfilename = filename;
+	sensors_yylineno = 1;
+	return 0;
+}
+
+void sensors_scanner_exit(void)
+{
+	sensors_yy_delete_buffer(scan_buf);
+	scan_buf = (YY_BUFFER_STATE)0;
+
+/* As of flex 2.5.9, sensors_yylex_destroy() must be called when done with the
+   scaller, otherwise we'll leak memory. */
+#if defined(YY_FLEX_MAJOR_VERSION) && defined(YY_FLEX_MINOR_VERSION) && defined(YY_FLEX_SUBMINOR_VERSION)
+#if YY_FLEX_MAJOR_VERSION > 2 || \
+    (YY_FLEX_MAJOR_VERSION == 2 && (YY_FLEX_MINOR_VERSION > 5 || \
+				    (YY_FLEX_MINOR_VERSION == 5 && YY_FLEX_SUBMINOR_VERSION >= 9)))
+	sensors_yylex_destroy();
+#endif
+#endif
+}
+
+
diff --git a/tools/gator/daemon/libsensors/conf-lex.l b/tools/gator/daemon/libsensors/conf-lex.l
new file mode 100644
index 00000000000..43ddbd8f5bd
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-lex.l
@@ -0,0 +1,372 @@
+%{
+/*
+    conf-lex.l - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl> 
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "general.h"
+#include "data.h"
+#include "conf-parse.h"
+#include "error.h"
+#include "scanner.h"
+
+static int buffer_count;
+static int buffer_max;
+static char *buffer;
+
+char sensors_lex_error[100];
+
+const char *sensors_yyfilename;
+int sensors_yylineno;
+
+#define buffer_malloc() sensors_malloc_array(&buffer,&buffer_count,\
+                                             &buffer_max,1)
+#define buffer_free() sensors_free_array(&buffer,&buffer_count,\
+                                         &buffer_max)
+#define buffer_add_char(c) sensors_add_array_el(c,&buffer,\
+                                                &buffer_count,\
+                                                &buffer_max,1)
+#define buffer_add_string(s) sensors_add_array_els(s,strlen(s),\
+                                                   &buffer, \
+                                                   &buffer_count,&buffer_max,1)
+
+%}
+
+ /* Scanner for configuration files */
+
+%option nodefault
+%option noyywrap
+%option nounput
+
+ /* All states are exclusive */
+
+%x MIDDLE
+%x STRING
+%x ERR
+
+ /* Any whitespace-like character */
+
+BLANK		[ \f\r\t\v]
+
+IDCHAR		[[:alnum:]_]
+
+ /* Note: `10', `10.4' and `.4' are valid, `10.' is not */
+
+FLOAT   [[:digit:]]*\.?[[:digit:]]+
+
+ /* Only positive whole numbers are recognized here */
+
+NUM	0|([1-9][[:digit:]]*)
+
+
+%%
+
+ /*
+  * STATE: INITIAL
+  */
+
+<INITIAL>{
+
+<<EOF>>		{ /* EOF from this state terminates */
+		  return 0;
+		}
+
+{BLANK}+	; /* eat as many blanks as possible at once */
+
+{BLANK}*\n	{ /* eat a bare newline (possibly preceded by blanks) */
+		  sensors_yylineno++;
+		}
+
+ /* comments */
+
+#.*		; /* eat the rest of the line after comment char */
+
+#.*\n		{ /* eat the rest of the line after comment char */
+		  sensors_yylineno++;
+		}
+
+ /*
+  * Keywords must be followed by whitespace - eat that too.
+  * If there isn't trailing whitespace, we still need to
+  * accept it as lexically correct (even though the parser
+  * will reject it anyway.)
+  */
+
+label{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return LABEL;
+		}
+
+set{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return SET;
+		}
+
+compute{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return COMPUTE;
+		}
+
+bus{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return BUS;
+		}
+
+chip{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return CHIP;
+		}
+
+ignore{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return IGNORE;
+		}
+
+ /* Anything else at the beginning of a line is an error */
+
+[a-z]+		|
+.		{
+		  BEGIN(ERR);
+		  strcpy(sensors_lex_error,"Invalid keyword");
+		  return ERROR;
+		}
+}
+
+ /*
+  * STATE: ERROR
+  */
+
+<ERR>{
+
+.*		; /* eat whatever is left on this line */
+
+\n		{
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+}
+
+ /*
+  * STATE: MIDDLE
+  */
+
+<MIDDLE>{
+
+{BLANK}+	; /* eat as many blanks as possible at once */
+
+\n		{ /* newline here sends EOL token to parser */
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+
+<<EOF>>		{ /* EOF here sends EOL token to parser also */
+		  BEGIN(INITIAL);
+		  return EOL;
+		}
+
+\\{BLANK}*\n	{ /* eat an escaped newline with no state change */
+		  sensors_yylineno++;
+		}
+
+ /* comments */
+
+#.*		; /* eat the rest of the line after comment char */
+
+#.*\n		{ /* eat the rest of the line after comment char */
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+
+ /* A number */
+
+{FLOAT}		{
+		  sensors_yylval.value = atof(sensors_yytext);
+		  return FLOAT;
+		}
+
+ /* Some operators */
+
+"+"		return '+';
+"-"		return '-';
+"*"		return '*';
+"/"		return '/';
+"("		return '(';
+")"		return ')';
+","		return ',';
+"@"		return '@';
+"^"		return '^';
+"`"		return '`';
+
+ /* Quoted string */
+
+\"		{
+		  buffer_malloc();
+		  BEGIN(STRING);
+		}
+
+ /* A normal, unquoted identifier */
+
+{IDCHAR}+	{
+		  sensors_yylval.name = strdup(sensors_yytext);
+		  if (! sensors_yylval.name)
+		    sensors_fatal_error("conf-lex.l",
+                                        "Allocating a new string");
+		  
+		  return NAME;
+		}
+
+ /* anything else is bogus */
+
+.		|
+[[:digit:]]*\.	|
+\\{BLANK}*	{
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+}
+
+ /*
+  * STATE: STRING
+  */
+
+<STRING>{
+
+ /* Oops, newline or EOF while in a string is not good */
+
+\n		|
+\\\n		{
+		  buffer_add_char("\0");
+		  strcpy(sensors_lex_error,
+			"No matching double quote.");
+		  buffer_free();
+		  yyless(0);
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+
+<<EOF>>		{
+		  strcpy(sensors_lex_error,
+			"Reached end-of-file without a matching double quote.");
+		  buffer_free();
+		  BEGIN(MIDDLE);
+		  return ERROR;
+		}
+
+ /* At the end */
+
+\"\"		{
+		  buffer_add_char("\0");
+		  strcpy(sensors_lex_error,
+			"Quoted strings must be separated by whitespace.");
+		  buffer_free();
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+		
+\"		{
+		  buffer_add_char("\0");
+		  sensors_yylval.name = strdup(buffer);
+		  if (! sensors_yylval.name)
+		    sensors_fatal_error("conf-lex.l",
+                                        "Allocating a new string");
+		  buffer_free();
+		  BEGIN(MIDDLE);
+		  return NAME;
+		}
+
+\\a		buffer_add_char("\a");
+\\b		buffer_add_char("\b");
+\\f		buffer_add_char("\f");
+\\n		buffer_add_char("\n");
+\\r		buffer_add_char("\r");
+\\t		buffer_add_char("\t");
+\\v		buffer_add_char("\v");
+
+ /* Other escapes: just copy the character behind the slash */
+
+\\.		{
+		  buffer_add_char(&sensors_yytext[1]);
+		}
+
+ /* Anything else (including a bare '\' which may be followed by EOF) */
+
+\\		|
+[^\\\n\"]+	{
+		  buffer_add_string(sensors_yytext);
+		}
+}
+
+%%
+
+/*
+	Do the buffer handling manually.  This allows us to scan as many
+	config files as we need to, while cleaning up properly after each
+	one.  The "BEGIN(0)" line ensures that we start in the default state,
+	even if e.g. the previous config file was syntactically broken.
+
+	Returns 0 if successful, !0 otherwise.
+*/
+
+static YY_BUFFER_STATE scan_buf = (YY_BUFFER_STATE)0;
+
+int sensors_scanner_init(FILE *input, const char *filename)
+{
+	BEGIN(0);
+	if (!(scan_buf = sensors_yy_create_buffer(input, YY_BUF_SIZE)))
+		return -1;
+
+	sensors_yy_switch_to_buffer(scan_buf);
+	sensors_yyfilename = filename;
+	sensors_yylineno = 1;
+	return 0;
+}
+
+void sensors_scanner_exit(void)
+{
+	sensors_yy_delete_buffer(scan_buf);
+	scan_buf = (YY_BUFFER_STATE)0;
+
+/* As of flex 2.5.9, yylex_destroy() must be called when done with the
+   scaller, otherwise we'll leak memory. */
+#if defined(YY_FLEX_MAJOR_VERSION) && defined(YY_FLEX_MINOR_VERSION) && defined(YY_FLEX_SUBMINOR_VERSION)
+#if YY_FLEX_MAJOR_VERSION > 2 || \
+    (YY_FLEX_MAJOR_VERSION == 2 && (YY_FLEX_MINOR_VERSION > 5 || \
+				    (YY_FLEX_MINOR_VERSION == 5 && YY_FLEX_SUBMINOR_VERSION >= 9)))
+	sensors_yylex_destroy();
+#endif
+#endif
+}
+
diff --git a/tools/gator/daemon/libsensors/conf-parse.c b/tools/gator/daemon/libsensors/conf-parse.c
new file mode 100644
index 00000000000..fb775460a1c
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-parse.c
@@ -0,0 +1,2042 @@
+/* A Bison parser, made by GNU Bison 2.5.  */
+
+/* Bison implementation for Yacc-like parsers in C
+   
+      Copyright (C) 1984, 1989-1990, 2000-2011 Free Software Foundation, Inc.
+   
+   This program is free software: you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation, either version 3 of the License, or
+   (at your option) any later version.
+   
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+   
+   You should have received a copy of the GNU General Public License
+   along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
+
+/* As a special exception, you may create a larger work that contains
+   part or all of the Bison parser skeleton and distribute that work
+   under terms of your choice, so long as that work isn't itself a
+   parser generator using the skeleton or a modified version thereof
+   as a parser skeleton.  Alternatively, if you modify or redistribute
+   the parser skeleton itself, you may (at your option) remove this
+   special exception, which will cause the skeleton and the resulting
+   Bison output files to be licensed under the GNU General Public
+   License without this special exception.
+   
+   This special exception was added by the Free Software Foundation in
+   version 2.2 of Bison.  */
+
+/* C LALR(1) parser skeleton written by Richard Stallman, by
+   simplifying the original so-called "semantic" parser.  */
+
+/* All symbols defined below should begin with yy or YY, to avoid
+   infringing on user name space.  This should be done even for local
+   variables, as they might otherwise be expanded by user macros.
+   There are some unavoidable exceptions within include files to
+   define necessary library symbols; they are noted "INFRINGES ON
+   USER NAME SPACE" below.  */
+
+/* Identify Bison output.  */
+#define YYBISON 1
+
+/* Bison version.  */
+#define YYBISON_VERSION "2.5"
+
+/* Skeleton name.  */
+#define YYSKELETON_NAME "yacc.c"
+
+/* Pure parsers.  */
+#define YYPURE 0
+
+/* Push parsers.  */
+#define YYPUSH 0
+
+/* Pull parsers.  */
+#define YYPULL 1
+
+/* Using locations.  */
+#define YYLSP_NEEDED 0
+
+/* Substitute the variable and function names.  */
+#define yyparse         sensors_yyparse
+#define yylex           sensors_yylex
+#define yyerror         sensors_yyerror
+#define yylval          sensors_yylval
+#define yychar          sensors_yychar
+#define yydebug         sensors_yydebug
+#define yynerrs         sensors_yynerrs
+
+
+/* Copy the first part of user declarations.  */
+
+/* Line 268 of yacc.c  */
+#line 1 "lib/conf-parse.y"
+
+/*
+    conf-parse.y - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#define YYERROR_VERBOSE
+
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+
+#include "data.h"
+#include "general.h"
+#include "error.h"
+#include "conf.h"
+#include "access.h"
+#include "init.h"
+
+static void sensors_yyerror(const char *err);
+static sensors_expr *malloc_expr(void);
+
+static sensors_chip *current_chip = NULL;
+
+#define bus_add_el(el) sensors_add_array_el(el,\
+                                      &sensors_config_busses,\
+                                      &sensors_config_busses_count,\
+                                      &sensors_config_busses_max,\
+                                      sizeof(sensors_bus))
+#define label_add_el(el) sensors_add_array_el(el,\
+                                        &current_chip->labels,\
+                                        &current_chip->labels_count,\
+                                        &current_chip->labels_max,\
+                                        sizeof(sensors_label));
+#define set_add_el(el) sensors_add_array_el(el,\
+                                      &current_chip->sets,\
+                                      &current_chip->sets_count,\
+                                      &current_chip->sets_max,\
+                                      sizeof(sensors_set));
+#define compute_add_el(el) sensors_add_array_el(el,\
+                                          &current_chip->computes,\
+                                          &current_chip->computes_count,\
+                                          &current_chip->computes_max,\
+                                          sizeof(sensors_compute));
+#define ignore_add_el(el) sensors_add_array_el(el,\
+                                          &current_chip->ignores,\
+                                          &current_chip->ignores_count,\
+                                          &current_chip->ignores_max,\
+                                          sizeof(sensors_ignore));
+#define chip_add_el(el) sensors_add_array_el(el,\
+                                       &sensors_config_chips,\
+                                       &sensors_config_chips_count,\
+                                       &sensors_config_chips_max,\
+                                       sizeof(sensors_chip));
+
+#define fits_add_el(el,list) sensors_add_array_el(el,\
+                                                  &(list).fits,\
+                                                  &(list).fits_count,\
+                                                  &(list).fits_max, \
+		                                  sizeof(sensors_chip_name));
+
+
+
+/* Line 268 of yacc.c  */
+#line 158 "lib/conf-parse.c"
+
+/* Enabling traces.  */
+#ifndef YYDEBUG
+# define YYDEBUG 0
+#endif
+
+/* Enabling verbose error messages.  */
+#ifdef YYERROR_VERBOSE
+# undef YYERROR_VERBOSE
+# define YYERROR_VERBOSE 1
+#else
+# define YYERROR_VERBOSE 0
+#endif
+
+/* Enabling the token table.  */
+#ifndef YYTOKEN_TABLE
+# define YYTOKEN_TABLE 0
+#endif
+
+
+/* Tokens.  */
+#ifndef YYTOKENTYPE
+# define YYTOKENTYPE
+   /* Put the tokens into the symbol table, so that GDB and other debuggers
+      know about them.  */
+   enum yytokentype {
+     NEG = 258,
+     EOL = 259,
+     BUS = 260,
+     LABEL = 261,
+     SET = 262,
+     CHIP = 263,
+     COMPUTE = 264,
+     IGNORE = 265,
+     FLOAT = 266,
+     NAME = 267,
+     ERROR = 268
+   };
+#endif
+
+
+
+#if ! defined YYSTYPE && ! defined YYSTYPE_IS_DECLARED
+typedef union YYSTYPE
+{
+
+/* Line 293 of yacc.c  */
+#line 79 "lib/conf-parse.y"
+
+  double value;
+  char *name;
+  void *nothing;
+  sensors_chip_name_list chips;
+  sensors_expr *expr;
+  sensors_bus_id bus;
+  sensors_chip_name chip;
+  sensors_config_line line;
+
+
+
+/* Line 293 of yacc.c  */
+#line 220 "lib/conf-parse.c"
+} YYSTYPE;
+# define YYSTYPE_IS_TRIVIAL 1
+# define yystype YYSTYPE /* obsolescent; will be withdrawn */
+# define YYSTYPE_IS_DECLARED 1
+#endif
+
+
+/* Copy the second part of user declarations.  */
+
+
+/* Line 343 of yacc.c  */
+#line 232 "lib/conf-parse.c"
+
+#ifdef short
+# undef short
+#endif
+
+#ifdef YYTYPE_UINT8
+typedef YYTYPE_UINT8 yytype_uint8;
+#else
+typedef unsigned char yytype_uint8;
+#endif
+
+#ifdef YYTYPE_INT8
+typedef YYTYPE_INT8 yytype_int8;
+#elif (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+typedef signed char yytype_int8;
+#else
+typedef short int yytype_int8;
+#endif
+
+#ifdef YYTYPE_UINT16
+typedef YYTYPE_UINT16 yytype_uint16;
+#else
+typedef unsigned short int yytype_uint16;
+#endif
+
+#ifdef YYTYPE_INT16
+typedef YYTYPE_INT16 yytype_int16;
+#else
+typedef short int yytype_int16;
+#endif
+
+#ifndef YYSIZE_T
+# ifdef __SIZE_TYPE__
+#  define YYSIZE_T __SIZE_TYPE__
+# elif defined size_t
+#  define YYSIZE_T size_t
+# elif ! defined YYSIZE_T && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+#  include <stddef.h> /* INFRINGES ON USER NAME SPACE */
+#  define YYSIZE_T size_t
+# else
+#  define YYSIZE_T unsigned int
+# endif
+#endif
+
+#define YYSIZE_MAXIMUM ((YYSIZE_T) -1)
+
+#ifndef YY_
+# if defined YYENABLE_NLS && YYENABLE_NLS
+#  if ENABLE_NLS
+#   include <libintl.h> /* INFRINGES ON USER NAME SPACE */
+#   define YY_(msgid) dgettext ("bison-runtime", msgid)
+#  endif
+# endif
+# ifndef YY_
+#  define YY_(msgid) msgid
+# endif
+#endif
+
+/* Suppress unused-variable warnings by "using" E.  */
+#if ! defined lint || defined __GNUC__
+# define YYUSE(e) ((void) (e))
+#else
+# define YYUSE(e) /* empty */
+#endif
+
+/* Identity function, used to suppress warnings about constant conditions.  */
+#ifndef lint
+# define YYID(n) (n)
+#else
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static int
+YYID (int yyi)
+#else
+static int
+YYID (yyi)
+    int yyi;
+#endif
+{
+  return yyi;
+}
+#endif
+
+#if ! defined yyoverflow || YYERROR_VERBOSE
+
+/* The parser invokes alloca or malloc; define the necessary symbols.  */
+
+# ifdef YYSTACK_USE_ALLOCA
+#  if YYSTACK_USE_ALLOCA
+#   ifdef __GNUC__
+#    define YYSTACK_ALLOC __builtin_alloca
+#   elif defined __BUILTIN_VA_ARG_INCR
+#    include <alloca.h> /* INFRINGES ON USER NAME SPACE */
+#   elif defined _AIX
+#    define YYSTACK_ALLOC __alloca
+#   elif defined _MSC_VER
+#    include <malloc.h> /* INFRINGES ON USER NAME SPACE */
+#    define alloca _alloca
+#   else
+#    define YYSTACK_ALLOC alloca
+#    if ! defined _ALLOCA_H && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+#     include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
+#     ifndef EXIT_SUCCESS
+#      define EXIT_SUCCESS 0
+#     endif
+#    endif
+#   endif
+#  endif
+# endif
+
+# ifdef YYSTACK_ALLOC
+   /* Pacify GCC's `empty if-body' warning.  */
+#  define YYSTACK_FREE(Ptr) do { /* empty */; } while (YYID (0))
+#  ifndef YYSTACK_ALLOC_MAXIMUM
+    /* The OS might guarantee only one guard page at the bottom of the stack,
+       and a page size can be as small as 4096 bytes.  So we cannot safely
+       invoke alloca (N) if N exceeds 4096.  Use a slightly smaller number
+       to allow for a few compiler-allocated temporary stack slots.  */
+#   define YYSTACK_ALLOC_MAXIMUM 4032 /* reasonable circa 2006 */
+#  endif
+# else
+#  define YYSTACK_ALLOC YYMALLOC
+#  define YYSTACK_FREE YYFREE
+#  ifndef YYSTACK_ALLOC_MAXIMUM
+#   define YYSTACK_ALLOC_MAXIMUM YYSIZE_MAXIMUM
+#  endif
+#  if (defined __cplusplus && ! defined EXIT_SUCCESS \
+       && ! ((defined YYMALLOC || defined malloc) \
+	     && (defined YYFREE || defined free)))
+#   include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
+#   ifndef EXIT_SUCCESS
+#    define EXIT_SUCCESS 0
+#   endif
+#  endif
+#  ifndef YYMALLOC
+#   define YYMALLOC malloc
+#   if ! defined malloc && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+void *malloc (YYSIZE_T); /* INFRINGES ON USER NAME SPACE */
+#   endif
+#  endif
+#  ifndef YYFREE
+#   define YYFREE free
+#   if ! defined free && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+void free (void *); /* INFRINGES ON USER NAME SPACE */
+#   endif
+#  endif
+# endif
+#endif /* ! defined yyoverflow || YYERROR_VERBOSE */
+
+
+#if (! defined yyoverflow \
+     && (! defined __cplusplus \
+	 || (defined YYSTYPE_IS_TRIVIAL && YYSTYPE_IS_TRIVIAL)))
+
+/* A type that is properly aligned for any stack member.  */
+union yyalloc
+{
+  yytype_int16 yyss_alloc;
+  YYSTYPE yyvs_alloc;
+};
+
+/* The size of the maximum gap between one aligned stack and the next.  */
+# define YYSTACK_GAP_MAXIMUM (sizeof (union yyalloc) - 1)
+
+/* The size of an array large to enough to hold all stacks, each with
+   N elements.  */
+# define YYSTACK_BYTES(N) \
+     ((N) * (sizeof (yytype_int16) + sizeof (YYSTYPE)) \
+      + YYSTACK_GAP_MAXIMUM)
+
+# define YYCOPY_NEEDED 1
+
+/* Relocate STACK from its old location to the new one.  The
+   local variables YYSIZE and YYSTACKSIZE give the old and new number of
+   elements in the stack, and YYPTR gives the new location of the
+   stack.  Advance YYPTR to a properly aligned location for the next
+   stack.  */
+# define YYSTACK_RELOCATE(Stack_alloc, Stack)				\
+    do									\
+      {									\
+	YYSIZE_T yynewbytes;						\
+	YYCOPY (&yyptr->Stack_alloc, Stack, yysize);			\
+	Stack = &yyptr->Stack_alloc;					\
+	yynewbytes = yystacksize * sizeof (*Stack) + YYSTACK_GAP_MAXIMUM; \
+	yyptr += yynewbytes / sizeof (*yyptr);				\
+      }									\
+    while (YYID (0))
+
+#endif
+
+#if defined YYCOPY_NEEDED && YYCOPY_NEEDED
+/* Copy COUNT objects from FROM to TO.  The source and destination do
+   not overlap.  */
+# ifndef YYCOPY
+#  if defined __GNUC__ && 1 < __GNUC__
+#   define YYCOPY(To, From, Count) \
+      __builtin_memcpy (To, From, (Count) * sizeof (*(From)))
+#  else
+#   define YYCOPY(To, From, Count)		\
+      do					\
+	{					\
+	  YYSIZE_T yyi;				\
+	  for (yyi = 0; yyi < (Count); yyi++)	\
+	    (To)[yyi] = (From)[yyi];		\
+	}					\
+      while (YYID (0))
+#  endif
+# endif
+#endif /* !YYCOPY_NEEDED */
+
+/* YYFINAL -- State number of the termination state.  */
+#define YYFINAL  2
+/* YYLAST -- Last index in YYTABLE.  */
+#define YYLAST   58
+
+/* YYNTOKENS -- Number of terminals.  */
+#define YYNTOKENS  24
+/* YYNNTS -- Number of nonterminals.  */
+#define YYNNTS  16
+/* YYNRULES -- Number of rules.  */
+#define YYNRULES  34
+/* YYNRULES -- Number of states.  */
+#define YYNSTATES  63
+
+/* YYTRANSLATE(YYLEX) -- Bison symbol number corresponding to YYLEX.  */
+#define YYUNDEFTOK  2
+#define YYMAXUTOK   268
+
+#define YYTRANSLATE(YYX)						\
+  ((unsigned int) (YYX) <= YYMAXUTOK ? yytranslate[YYX] : YYUNDEFTOK)
+
+/* YYTRANSLATE[YYLEX] -- Bison symbol number corresponding to YYLEX.  */
+static const yytype_uint8 yytranslate[] =
+{
+       0,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+      22,    23,     5,     4,    10,     3,     2,     6,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,    21,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     8,     2,     9,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     1,     2,     7,    11,
+      12,    13,    14,    15,    16,    17,    18,    19,    20
+};
+
+#if YYDEBUG
+/* YYPRHS[YYN] -- Index of the first RHS symbol of rule number YYN in
+   YYRHS.  */
+static const yytype_uint8 yyprhs[] =
+{
+       0,     0,     3,     4,     7,    10,    13,    16,    19,    22,
+      25,    28,    32,    36,    40,    46,    49,    52,    54,    57,
+      59,    61,    63,    67,    71,    75,    79,    82,    86,    89,
+      92,    94,    96,    98,   100
+};
+
+/* YYRHS -- A `-1'-separated list of the rules' RHS.  */
+static const yytype_int8 yyrhs[] =
+{
+      25,     0,    -1,    -1,    25,    26,    -1,    27,    11,    -1,
+      28,    11,    -1,    29,    11,    -1,    32,    11,    -1,    30,
+      11,    -1,    31,    11,    -1,     1,    11,    -1,    12,    35,
+      36,    -1,    13,    37,    38,    -1,    14,    37,    34,    -1,
+      16,    37,    34,    10,    34,    -1,    17,    37,    -1,    15,
+      33,    -1,    39,    -1,    33,    39,    -1,    18,    -1,    19,
+      -1,    21,    -1,    34,     4,    34,    -1,    34,     3,    34,
+      -1,    34,     5,    34,    -1,    34,     6,    34,    -1,     3,
+      34,    -1,    22,    34,    23,    -1,     8,    34,    -1,     9,
+      34,    -1,    19,    -1,    19,    -1,    19,    -1,    19,    -1,
+      19,    -1
+};
+
+/* YYRLINE[YYN] -- source line where rule number YYN was defined.  */
+static const yytype_uint16 yyrline[] =
+{
+       0,   119,   119,   120,   123,   124,   125,   126,   127,   128,
+     129,   132,   141,   156,   171,   188,   201,   219,   225,   231,
+     236,   241,   245,   252,   259,   266,   273,   280,   282,   289,
+     298,   308,   312,   316,   320
+};
+#endif
+
+#if YYDEBUG || YYERROR_VERBOSE || YYTOKEN_TABLE
+/* YYTNAME[SYMBOL-NUM] -- String name of the symbol SYMBOL-NUM.
+   First, the terminals, then, starting at YYNTOKENS, nonterminals.  */
+static const char *const yytname[] =
+{
+  "$end", "error", "$undefined", "'-'", "'+'", "'*'", "'/'", "NEG", "'^'",
+  "'`'", "','", "EOL", "BUS", "LABEL", "SET", "CHIP", "COMPUTE", "IGNORE",
+  "FLOAT", "NAME", "ERROR", "'@'", "'('", "')'", "$accept", "input",
+  "line", "bus_statement", "label_statement", "set_statement",
+  "compute_statement", "ignore_statement", "chip_statement",
+  "chip_name_list", "expression", "bus_id", "adapter_name",
+  "function_name", "string", "chip_name", 0
+};
+#endif
+
+# ifdef YYPRINT
+/* YYTOKNUM[YYLEX-NUM] -- Internal token number corresponding to
+   token YYLEX-NUM.  */
+static const yytype_uint16 yytoknum[] =
+{
+       0,   256,   257,    45,    43,    42,    47,   258,    94,    96,
+      44,   259,   260,   261,   262,   263,   264,   265,   266,   267,
+     268,    64,    40,    41
+};
+# endif
+
+/* YYR1[YYN] -- Symbol number of symbol that rule YYN derives.  */
+static const yytype_uint8 yyr1[] =
+{
+       0,    24,    25,    25,    26,    26,    26,    26,    26,    26,
+      26,    27,    28,    29,    30,    31,    32,    33,    33,    34,
+      34,    34,    34,    34,    34,    34,    34,    34,    34,    34,
+      35,    36,    37,    38,    39
+};
+
+/* YYR2[YYN] -- Number of symbols composing right hand side of rule YYN.  */
+static const yytype_uint8 yyr2[] =
+{
+       0,     2,     0,     2,     2,     2,     2,     2,     2,     2,
+       2,     3,     3,     3,     5,     2,     2,     1,     2,     1,
+       1,     1,     3,     3,     3,     3,     2,     3,     2,     2,
+       1,     1,     1,     1,     1
+};
+
+/* YYDEFACT[STATE-NAME] -- Default reduction number in state STATE-NUM.
+   Performed when YYTABLE doesn't specify something else to do.  Zero
+   means the default is an error.  */
+static const yytype_uint8 yydefact[] =
+{
+       2,     0,     1,     0,     0,     0,     0,     0,     0,     0,
+       3,     0,     0,     0,     0,     0,     0,    10,    30,     0,
+      32,     0,     0,    34,    16,    17,     0,    15,     4,     5,
+       6,     8,     9,     7,    31,    11,    33,    12,     0,     0,
+       0,    19,    20,    21,     0,    13,    18,     0,    26,    28,
+      29,     0,     0,     0,     0,     0,     0,    27,    23,    22,
+      24,    25,    14
+};
+
+/* YYDEFGOTO[NTERM-NUM].  */
+static const yytype_int8 yydefgoto[] =
+{
+      -1,     1,    10,    11,    12,    13,    14,    15,    16,    24,
+      45,    19,    35,    21,    37,    25
+};
+
+/* YYPACT[STATE-NUM] -- Index in YYTABLE of the portion describing
+   STATE-NUM.  */
+#define YYPACT_NINF -27
+static const yytype_int8 yypact[] =
+{
+     -27,    37,   -27,    -4,    -3,     1,     1,     6,     1,     1,
+     -27,     8,    13,    20,    23,    32,    34,   -27,   -27,    29,
+     -27,    39,    14,   -27,     6,   -27,    14,   -27,   -27,   -27,
+     -27,   -27,   -27,   -27,   -27,   -27,   -27,   -27,    14,    14,
+      14,   -27,   -27,   -27,    14,    36,   -27,     5,   -27,   -27,
+     -27,    -2,    14,    14,    14,    14,    14,   -27,     0,     0,
+     -27,   -27,    36
+};
+
+/* YYPGOTO[NTERM-NUM].  */
+static const yytype_int8 yypgoto[] =
+{
+     -27,   -27,   -27,   -27,   -27,   -27,   -27,   -27,   -27,   -27,
+     -26,   -27,   -27,    38,   -27,    31
+};
+
+/* YYTABLE[YYPACT[STATE-NUM]].  What to do in state STATE-NUM.  If
+   positive, shift that token.  If negative, reduce the rule which
+   number is the opposite.  If YYTABLE_NINF, syntax error.  */
+#define YYTABLE_NINF -1
+static const yytype_uint8 yytable[] =
+{
+      47,    52,    53,    54,    55,    54,    55,    17,    52,    53,
+      54,    55,    48,    49,    50,    56,    18,    38,    51,    28,
+      20,    57,    39,    40,    29,    23,    58,    59,    60,    61,
+      62,    30,    41,    42,    31,    43,    44,     2,     3,    52,
+      53,    54,    55,    32,    22,    33,    26,    27,    34,     4,
+       5,     6,     7,     8,     9,    46,     0,     0,    36
+};
+
+#define yypact_value_is_default(yystate) \
+  ((yystate) == (-27))
+
+#define yytable_value_is_error(yytable_value) \
+  YYID (0)
+
+static const yytype_int8 yycheck[] =
+{
+      26,     3,     4,     5,     6,     5,     6,    11,     3,     4,
+       5,     6,    38,    39,    40,    10,    19,     3,    44,    11,
+      19,    23,     8,     9,    11,    19,    52,    53,    54,    55,
+      56,    11,    18,    19,    11,    21,    22,     0,     1,     3,
+       4,     5,     6,    11,     6,    11,     8,     9,    19,    12,
+      13,    14,    15,    16,    17,    24,    -1,    -1,    19
+};
+
+/* YYSTOS[STATE-NUM] -- The (internal number of the) accessing
+   symbol of state STATE-NUM.  */
+static const yytype_uint8 yystos[] =
+{
+       0,    25,     0,     1,    12,    13,    14,    15,    16,    17,
+      26,    27,    28,    29,    30,    31,    32,    11,    19,    35,
+      19,    37,    37,    19,    33,    39,    37,    37,    11,    11,
+      11,    11,    11,    11,    19,    36,    19,    38,     3,     8,
+       9,    18,    19,    21,    22,    34,    39,    34,    34,    34,
+      34,    34,     3,     4,     5,     6,    10,    23,    34,    34,
+      34,    34,    34
+};
+
+#define yyerrok		(yyerrstatus = 0)
+#define yyclearin	(yychar = YYEMPTY)
+#define YYEMPTY		(-2)
+#define YYEOF		0
+
+#define YYACCEPT	goto yyacceptlab
+#define YYABORT		goto yyabortlab
+#define YYERROR		goto yyerrorlab
+
+
+/* Like YYERROR except do call yyerror.  This remains here temporarily
+   to ease the transition to the new meaning of YYERROR, for GCC.
+   Once GCC version 2 has supplanted version 1, this can go.  However,
+   YYFAIL appears to be in use.  Nevertheless, it is formally deprecated
+   in Bison 2.4.2's NEWS entry, where a plan to phase it out is
+   discussed.  */
+
+#define YYFAIL		goto yyerrlab
+#if defined YYFAIL
+  /* This is here to suppress warnings from the GCC cpp's
+     -Wunused-macros.  Normally we don't worry about that warning, but
+     some users do, and we want to make it easy for users to remove
+     YYFAIL uses, which will produce warnings from Bison 2.5.  */
+#endif
+
+#define YYRECOVERING()  (!!yyerrstatus)
+
+#define YYBACKUP(Token, Value)					\
+do								\
+  if (yychar == YYEMPTY && yylen == 1)				\
+    {								\
+      yychar = (Token);						\
+      yylval = (Value);						\
+      YYPOPSTACK (1);						\
+      goto yybackup;						\
+    }								\
+  else								\
+    {								\
+      yyerror (YY_("syntax error: cannot back up")); \
+      YYERROR;							\
+    }								\
+while (YYID (0))
+
+
+#define YYTERROR	1
+#define YYERRCODE	256
+
+
+/* YYLLOC_DEFAULT -- Set CURRENT to span from RHS[1] to RHS[N].
+   If N is 0, then set CURRENT to the empty location which ends
+   the previous symbol: RHS[0] (always defined).  */
+
+#define YYRHSLOC(Rhs, K) ((Rhs)[K])
+#ifndef YYLLOC_DEFAULT
+# define YYLLOC_DEFAULT(Current, Rhs, N)				\
+    do									\
+      if (YYID (N))                                                    \
+	{								\
+	  (Current).first_line   = YYRHSLOC (Rhs, 1).first_line;	\
+	  (Current).first_column = YYRHSLOC (Rhs, 1).first_column;	\
+	  (Current).last_line    = YYRHSLOC (Rhs, N).last_line;		\
+	  (Current).last_column  = YYRHSLOC (Rhs, N).last_column;	\
+	}								\
+      else								\
+	{								\
+	  (Current).first_line   = (Current).last_line   =		\
+	    YYRHSLOC (Rhs, 0).last_line;				\
+	  (Current).first_column = (Current).last_column =		\
+	    YYRHSLOC (Rhs, 0).last_column;				\
+	}								\
+    while (YYID (0))
+#endif
+
+
+/* This macro is provided for backward compatibility. */
+
+#ifndef YY_LOCATION_PRINT
+# define YY_LOCATION_PRINT(File, Loc) ((void) 0)
+#endif
+
+
+/* YYLEX -- calling `yylex' with the right arguments.  */
+
+#ifdef YYLEX_PARAM
+# define YYLEX yylex (YYLEX_PARAM)
+#else
+# define YYLEX yylex ()
+#endif
+
+/* Enable debugging if requested.  */
+#if YYDEBUG
+
+# ifndef YYFPRINTF
+#  include <stdio.h> /* INFRINGES ON USER NAME SPACE */
+#  define YYFPRINTF fprintf
+# endif
+
+# define YYDPRINTF(Args)			\
+do {						\
+  if (yydebug)					\
+    YYFPRINTF Args;				\
+} while (YYID (0))
+
+# define YY_SYMBOL_PRINT(Title, Type, Value, Location)			  \
+do {									  \
+  if (yydebug)								  \
+    {									  \
+      YYFPRINTF (stderr, "%s ", Title);					  \
+      yy_symbol_print (stderr,						  \
+		  Type, Value); \
+      YYFPRINTF (stderr, "\n");						  \
+    }									  \
+} while (YYID (0))
+
+
+/*--------------------------------.
+| Print this symbol on YYOUTPUT.  |
+`--------------------------------*/
+
+/*ARGSUSED*/
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_symbol_value_print (FILE *yyoutput, int yytype, YYSTYPE const * const yyvaluep)
+#else
+static void
+yy_symbol_value_print (yyoutput, yytype, yyvaluep)
+    FILE *yyoutput;
+    int yytype;
+    YYSTYPE const * const yyvaluep;
+#endif
+{
+  if (!yyvaluep)
+    return;
+# ifdef YYPRINT
+  if (yytype < YYNTOKENS)
+    YYPRINT (yyoutput, yytoknum[yytype], *yyvaluep);
+# else
+  YYUSE (yyoutput);
+# endif
+  switch (yytype)
+    {
+      default:
+	break;
+    }
+}
+
+
+/*--------------------------------.
+| Print this symbol on YYOUTPUT.  |
+`--------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_symbol_print (FILE *yyoutput, int yytype, YYSTYPE const * const yyvaluep)
+#else
+static void
+yy_symbol_print (yyoutput, yytype, yyvaluep)
+    FILE *yyoutput;
+    int yytype;
+    YYSTYPE const * const yyvaluep;
+#endif
+{
+  if (yytype < YYNTOKENS)
+    YYFPRINTF (yyoutput, "token %s (", yytname[yytype]);
+  else
+    YYFPRINTF (yyoutput, "nterm %s (", yytname[yytype]);
+
+  yy_symbol_value_print (yyoutput, yytype, yyvaluep);
+  YYFPRINTF (yyoutput, ")");
+}
+
+/*------------------------------------------------------------------.
+| yy_stack_print -- Print the state stack from its BOTTOM up to its |
+| TOP (included).                                                   |
+`------------------------------------------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_stack_print (yytype_int16 *yybottom, yytype_int16 *yytop)
+#else
+static void
+yy_stack_print (yybottom, yytop)
+    yytype_int16 *yybottom;
+    yytype_int16 *yytop;
+#endif
+{
+  YYFPRINTF (stderr, "Stack now");
+  for (; yybottom <= yytop; yybottom++)
+    {
+      int yybot = *yybottom;
+      YYFPRINTF (stderr, " %d", yybot);
+    }
+  YYFPRINTF (stderr, "\n");
+}
+
+# define YY_STACK_PRINT(Bottom, Top)				\
+do {								\
+  if (yydebug)							\
+    yy_stack_print ((Bottom), (Top));				\
+} while (YYID (0))
+
+
+/*------------------------------------------------.
+| Report that the YYRULE is going to be reduced.  |
+`------------------------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_reduce_print (YYSTYPE *yyvsp, int yyrule)
+#else
+static void
+yy_reduce_print (yyvsp, yyrule)
+    YYSTYPE *yyvsp;
+    int yyrule;
+#endif
+{
+  int yynrhs = yyr2[yyrule];
+  int yyi;
+  unsigned long int yylno = yyrline[yyrule];
+  YYFPRINTF (stderr, "Reducing stack by rule %d (line %lu):\n",
+	     yyrule - 1, yylno);
+  /* The symbols being reduced.  */
+  for (yyi = 0; yyi < yynrhs; yyi++)
+    {
+      YYFPRINTF (stderr, "   $%d = ", yyi + 1);
+      yy_symbol_print (stderr, yyrhs[yyprhs[yyrule] + yyi],
+		       &(yyvsp[(yyi + 1) - (yynrhs)])
+		       		       );
+      YYFPRINTF (stderr, "\n");
+    }
+}
+
+# define YY_REDUCE_PRINT(Rule)		\
+do {					\
+  if (yydebug)				\
+    yy_reduce_print (yyvsp, Rule); \
+} while (YYID (0))
+
+/* Nonzero means print parse trace.  It is left uninitialized so that
+   multiple parsers can coexist.  */
+int yydebug;
+#else /* !YYDEBUG */
+# define YYDPRINTF(Args)
+# define YY_SYMBOL_PRINT(Title, Type, Value, Location)
+# define YY_STACK_PRINT(Bottom, Top)
+# define YY_REDUCE_PRINT(Rule)
+#endif /* !YYDEBUG */
+
+
+/* YYINITDEPTH -- initial size of the parser's stacks.  */
+#ifndef	YYINITDEPTH
+# define YYINITDEPTH 200
+#endif
+
+/* YYMAXDEPTH -- maximum size the stacks can grow to (effective only
+   if the built-in stack extension method is used).
+
+   Do not make this value too large; the results are undefined if
+   YYSTACK_ALLOC_MAXIMUM < YYSTACK_BYTES (YYMAXDEPTH)
+   evaluated with infinite-precision integer arithmetic.  */
+
+#ifndef YYMAXDEPTH
+# define YYMAXDEPTH 10000
+#endif
+
+
+#if YYERROR_VERBOSE
+
+# ifndef yystrlen
+#  if defined __GLIBC__ && defined _STRING_H
+#   define yystrlen strlen
+#  else
+/* Return the length of YYSTR.  */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static YYSIZE_T
+yystrlen (const char *yystr)
+#else
+static YYSIZE_T
+yystrlen (yystr)
+    const char *yystr;
+#endif
+{
+  YYSIZE_T yylen;
+  for (yylen = 0; yystr[yylen]; yylen++)
+    continue;
+  return yylen;
+}
+#  endif
+# endif
+
+# ifndef yystpcpy
+#  if defined __GLIBC__ && defined _STRING_H && defined _GNU_SOURCE
+#   define yystpcpy stpcpy
+#  else
+/* Copy YYSRC to YYDEST, returning the address of the terminating '\0' in
+   YYDEST.  */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static char *
+yystpcpy (char *yydest, const char *yysrc)
+#else
+static char *
+yystpcpy (yydest, yysrc)
+    char *yydest;
+    const char *yysrc;
+#endif
+{
+  char *yyd = yydest;
+  const char *yys = yysrc;
+
+  while ((*yyd++ = *yys++) != '\0')
+    continue;
+
+  return yyd - 1;
+}
+#  endif
+# endif
+
+# ifndef yytnamerr
+/* Copy to YYRES the contents of YYSTR after stripping away unnecessary
+   quotes and backslashes, so that it's suitable for yyerror.  The
+   heuristic is that double-quoting is unnecessary unless the string
+   contains an apostrophe, a comma, or backslash (other than
+   backslash-backslash).  YYSTR is taken from yytname.  If YYRES is
+   null, do not copy; instead, return the length of what the result
+   would have been.  */
+static YYSIZE_T
+yytnamerr (char *yyres, const char *yystr)
+{
+  if (*yystr == '"')
+    {
+      YYSIZE_T yyn = 0;
+      char const *yyp = yystr;
+
+      for (;;)
+	switch (*++yyp)
+	  {
+	  case '\'':
+	  case ',':
+	    goto do_not_strip_quotes;
+
+	  case '\\':
+	    if (*++yyp != '\\')
+	      goto do_not_strip_quotes;
+	    /* Fall through.  */
+	  default:
+	    if (yyres)
+	      yyres[yyn] = *yyp;
+	    yyn++;
+	    break;
+
+	  case '"':
+	    if (yyres)
+	      yyres[yyn] = '\0';
+	    return yyn;
+	  }
+    do_not_strip_quotes: ;
+    }
+
+  if (! yyres)
+    return yystrlen (yystr);
+
+  return yystpcpy (yyres, yystr) - yyres;
+}
+# endif
+
+/* Copy into *YYMSG, which is of size *YYMSG_ALLOC, an error message
+   about the unexpected token YYTOKEN for the state stack whose top is
+   YYSSP.
+
+   Return 0 if *YYMSG was successfully written.  Return 1 if *YYMSG is
+   not large enough to hold the message.  In that case, also set
+   *YYMSG_ALLOC to the required number of bytes.  Return 2 if the
+   required number of bytes is too large to store.  */
+static int
+yysyntax_error (YYSIZE_T *yymsg_alloc, char **yymsg,
+                yytype_int16 *yyssp, int yytoken)
+{
+  YYSIZE_T yysize0 = yytnamerr (0, yytname[yytoken]);
+  YYSIZE_T yysize = yysize0;
+  YYSIZE_T yysize1;
+  enum { YYERROR_VERBOSE_ARGS_MAXIMUM = 5 };
+  /* Internationalized format string. */
+  const char *yyformat = 0;
+  /* Arguments of yyformat. */
+  char const *yyarg[YYERROR_VERBOSE_ARGS_MAXIMUM];
+  /* Number of reported tokens (one for the "unexpected", one per
+     "expected"). */
+  int yycount = 0;
+
+  /* There are many possibilities here to consider:
+     - Assume YYFAIL is not used.  It's too flawed to consider.  See
+       <http://lists.gnu.org/archive/html/bison-patches/2009-12/msg00024.html>
+       for details.  YYERROR is fine as it does not invoke this
+       function.
+     - If this state is a consistent state with a default action, then
+       the only way this function was invoked is if the default action
+       is an error action.  In that case, don't check for expected
+       tokens because there are none.
+     - The only way there can be no lookahead present (in yychar) is if
+       this state is a consistent state with a default action.  Thus,
+       detecting the absence of a lookahead is sufficient to determine
+       that there is no unexpected or expected token to report.  In that
+       case, just report a simple "syntax error".
+     - Don't assume there isn't a lookahead just because this state is a
+       consistent state with a default action.  There might have been a
+       previous inconsistent state, consistent state with a non-default
+       action, or user semantic action that manipulated yychar.
+     - Of course, the expected token list depends on states to have
+       correct lookahead information, and it depends on the parser not
+       to perform extra reductions after fetching a lookahead from the
+       scanner and before detecting a syntax error.  Thus, state merging
+       (from LALR or IELR) and default reductions corrupt the expected
+       token list.  However, the list is correct for canonical LR with
+       one exception: it will still contain any token that will not be
+       accepted due to an error action in a later state.
+  */
+  if (yytoken != YYEMPTY)
+    {
+      int yyn = yypact[*yyssp];
+      yyarg[yycount++] = yytname[yytoken];
+      if (!yypact_value_is_default (yyn))
+        {
+          /* Start YYX at -YYN if negative to avoid negative indexes in
+             YYCHECK.  In other words, skip the first -YYN actions for
+             this state because they are default actions.  */
+          int yyxbegin = yyn < 0 ? -yyn : 0;
+          /* Stay within bounds of both yycheck and yytname.  */
+          int yychecklim = YYLAST - yyn + 1;
+          int yyxend = yychecklim < YYNTOKENS ? yychecklim : YYNTOKENS;
+          int yyx;
+
+          for (yyx = yyxbegin; yyx < yyxend; ++yyx)
+            if (yycheck[yyx + yyn] == yyx && yyx != YYTERROR
+                && !yytable_value_is_error (yytable[yyx + yyn]))
+              {
+                if (yycount == YYERROR_VERBOSE_ARGS_MAXIMUM)
+                  {
+                    yycount = 1;
+                    yysize = yysize0;
+                    break;
+                  }
+                yyarg[yycount++] = yytname[yyx];
+                yysize1 = yysize + yytnamerr (0, yytname[yyx]);
+                if (! (yysize <= yysize1
+                       && yysize1 <= YYSTACK_ALLOC_MAXIMUM))
+                  return 2;
+                yysize = yysize1;
+              }
+        }
+    }
+
+  switch (yycount)
+    {
+# define YYCASE_(N, S)                      \
+      case N:                               \
+        yyformat = S;                       \
+      break
+      YYCASE_(0, YY_("syntax error"));
+      YYCASE_(1, YY_("syntax error, unexpected %s"));
+      YYCASE_(2, YY_("syntax error, unexpected %s, expecting %s"));
+      YYCASE_(3, YY_("syntax error, unexpected %s, expecting %s or %s"));
+      YYCASE_(4, YY_("syntax error, unexpected %s, expecting %s or %s or %s"));
+      YYCASE_(5, YY_("syntax error, unexpected %s, expecting %s or %s or %s or %s"));
+# undef YYCASE_
+    }
+
+  yysize1 = yysize + yystrlen (yyformat);
+  if (! (yysize <= yysize1 && yysize1 <= YYSTACK_ALLOC_MAXIMUM))
+    return 2;
+  yysize = yysize1;
+
+  if (*yymsg_alloc < yysize)
+    {
+      *yymsg_alloc = 2 * yysize;
+      if (! (yysize <= *yymsg_alloc
+             && *yymsg_alloc <= YYSTACK_ALLOC_MAXIMUM))
+        *yymsg_alloc = YYSTACK_ALLOC_MAXIMUM;
+      return 1;
+    }
+
+  /* Avoid sprintf, as that infringes on the user's name space.
+     Don't have undefined behavior even if the translation
+     produced a string with the wrong number of "%s"s.  */
+  {
+    char *yyp = *yymsg;
+    int yyi = 0;
+    while ((*yyp = *yyformat) != '\0')
+      if (*yyp == '%' && yyformat[1] == 's' && yyi < yycount)
+        {
+          yyp += yytnamerr (yyp, yyarg[yyi++]);
+          yyformat += 2;
+        }
+      else
+        {
+          yyp++;
+          yyformat++;
+        }
+  }
+  return 0;
+}
+#endif /* YYERROR_VERBOSE */
+
+/*-----------------------------------------------.
+| Release the memory associated to this symbol.  |
+`-----------------------------------------------*/
+
+/*ARGSUSED*/
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yydestruct (const char *yymsg, int yytype, YYSTYPE *yyvaluep)
+#else
+static void
+yydestruct (yymsg, yytype, yyvaluep)
+    const char *yymsg;
+    int yytype;
+    YYSTYPE *yyvaluep;
+#endif
+{
+  YYUSE (yyvaluep);
+
+  if (!yymsg)
+    yymsg = "Deleting";
+  YY_SYMBOL_PRINT (yymsg, yytype, yyvaluep, yylocationp);
+
+  switch (yytype)
+    {
+
+      default:
+	break;
+    }
+}
+
+
+/* Prevent warnings from -Wmissing-prototypes.  */
+#ifdef YYPARSE_PARAM
+#if defined __STDC__ || defined __cplusplus
+int yyparse (void *YYPARSE_PARAM);
+#else
+int yyparse ();
+#endif
+#else /* ! YYPARSE_PARAM */
+#if defined __STDC__ || defined __cplusplus
+int yyparse (void);
+#else
+int yyparse ();
+#endif
+#endif /* ! YYPARSE_PARAM */
+
+
+/* The lookahead symbol.  */
+int yychar;
+
+/* The semantic value of the lookahead symbol.  */
+YYSTYPE yylval;
+
+/* Number of syntax errors so far.  */
+int yynerrs;
+
+
+/*----------.
+| yyparse.  |
+`----------*/
+
+#ifdef YYPARSE_PARAM
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+int
+yyparse (void *YYPARSE_PARAM)
+#else
+int
+yyparse (YYPARSE_PARAM)
+    void *YYPARSE_PARAM;
+#endif
+#else /* ! YYPARSE_PARAM */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+int
+yyparse (void)
+#else
+int
+yyparse ()
+
+#endif
+#endif
+{
+    int yystate;
+    /* Number of tokens to shift before error messages enabled.  */
+    int yyerrstatus;
+
+    /* The stacks and their tools:
+       `yyss': related to states.
+       `yyvs': related to semantic values.
+
+       Refer to the stacks thru separate pointers, to allow yyoverflow
+       to reallocate them elsewhere.  */
+
+    /* The state stack.  */
+    yytype_int16 yyssa[YYINITDEPTH];
+    yytype_int16 *yyss;
+    yytype_int16 *yyssp;
+
+    /* The semantic value stack.  */
+    YYSTYPE yyvsa[YYINITDEPTH];
+    YYSTYPE *yyvs;
+    YYSTYPE *yyvsp;
+
+    YYSIZE_T yystacksize;
+
+  int yyn;
+  int yyresult;
+  /* Lookahead token as an internal (translated) token number.  */
+  int yytoken;
+  /* The variables used to return semantic value and location from the
+     action routines.  */
+  YYSTYPE yyval;
+
+#if YYERROR_VERBOSE
+  /* Buffer for error messages, and its allocated size.  */
+  char yymsgbuf[128];
+  char *yymsg = yymsgbuf;
+  YYSIZE_T yymsg_alloc = sizeof yymsgbuf;
+#endif
+
+#define YYPOPSTACK(N)   (yyvsp -= (N), yyssp -= (N))
+
+  /* The number of symbols on the RHS of the reduced rule.
+     Keep to zero when no symbol should be popped.  */
+  int yylen = 0;
+
+  yytoken = 0;
+  yyss = yyssa;
+  yyvs = yyvsa;
+  yystacksize = YYINITDEPTH;
+
+  YYDPRINTF ((stderr, "Starting parse\n"));
+
+  yystate = 0;
+  yyerrstatus = 0;
+  yynerrs = 0;
+  yychar = YYEMPTY; /* Cause a token to be read.  */
+
+  /* Initialize stack pointers.
+     Waste one element of value and location stack
+     so that they stay on the same level as the state stack.
+     The wasted elements are never initialized.  */
+  yyssp = yyss;
+  yyvsp = yyvs;
+
+  goto yysetstate;
+
+/*------------------------------------------------------------.
+| yynewstate -- Push a new state, which is found in yystate.  |
+`------------------------------------------------------------*/
+ yynewstate:
+  /* In all cases, when you get here, the value and location stacks
+     have just been pushed.  So pushing a state here evens the stacks.  */
+  yyssp++;
+
+ yysetstate:
+  *yyssp = yystate;
+
+  if (yyss + yystacksize - 1 <= yyssp)
+    {
+      /* Get the current used size of the three stacks, in elements.  */
+      YYSIZE_T yysize = yyssp - yyss + 1;
+
+#ifdef yyoverflow
+      {
+	/* Give user a chance to reallocate the stack.  Use copies of
+	   these so that the &'s don't force the real ones into
+	   memory.  */
+	YYSTYPE *yyvs1 = yyvs;
+	yytype_int16 *yyss1 = yyss;
+
+	/* Each stack pointer address is followed by the size of the
+	   data in use in that stack, in bytes.  This used to be a
+	   conditional around just the two extra args, but that might
+	   be undefined if yyoverflow is a macro.  */
+	yyoverflow (YY_("memory exhausted"),
+		    &yyss1, yysize * sizeof (*yyssp),
+		    &yyvs1, yysize * sizeof (*yyvsp),
+		    &yystacksize);
+
+	yyss = yyss1;
+	yyvs = yyvs1;
+      }
+#else /* no yyoverflow */
+# ifndef YYSTACK_RELOCATE
+      goto yyexhaustedlab;
+# else
+      /* Extend the stack our own way.  */
+      if (YYMAXDEPTH <= yystacksize)
+	goto yyexhaustedlab;
+      yystacksize *= 2;
+      if (YYMAXDEPTH < yystacksize)
+	yystacksize = YYMAXDEPTH;
+
+      {
+	yytype_int16 *yyss1 = yyss;
+	union yyalloc *yyptr =
+	  (union yyalloc *) YYSTACK_ALLOC (YYSTACK_BYTES (yystacksize));
+	if (! yyptr)
+	  goto yyexhaustedlab;
+	YYSTACK_RELOCATE (yyss_alloc, yyss);
+	YYSTACK_RELOCATE (yyvs_alloc, yyvs);
+#  undef YYSTACK_RELOCATE
+	if (yyss1 != yyssa)
+	  YYSTACK_FREE (yyss1);
+      }
+# endif
+#endif /* no yyoverflow */
+
+      yyssp = yyss + yysize - 1;
+      yyvsp = yyvs + yysize - 1;
+
+      YYDPRINTF ((stderr, "Stack size increased to %lu\n",
+		  (unsigned long int) yystacksize));
+
+      if (yyss + yystacksize - 1 <= yyssp)
+	YYABORT;
+    }
+
+  YYDPRINTF ((stderr, "Entering state %d\n", yystate));
+
+  if (yystate == YYFINAL)
+    YYACCEPT;
+
+  goto yybackup;
+
+/*-----------.
+| yybackup.  |
+`-----------*/
+yybackup:
+
+  /* Do appropriate processing given the current state.  Read a
+     lookahead token if we need one and don't already have one.  */
+
+  /* First try to decide what to do without reference to lookahead token.  */
+  yyn = yypact[yystate];
+  if (yypact_value_is_default (yyn))
+    goto yydefault;
+
+  /* Not known => get a lookahead token if don't already have one.  */
+
+  /* YYCHAR is either YYEMPTY or YYEOF or a valid lookahead symbol.  */
+  if (yychar == YYEMPTY)
+    {
+      YYDPRINTF ((stderr, "Reading a token: "));
+      yychar = YYLEX;
+    }
+
+  if (yychar <= YYEOF)
+    {
+      yychar = yytoken = YYEOF;
+      YYDPRINTF ((stderr, "Now at end of input.\n"));
+    }
+  else
+    {
+      yytoken = YYTRANSLATE (yychar);
+      YY_SYMBOL_PRINT ("Next token is", yytoken, &yylval, &yylloc);
+    }
+
+  /* If the proper action on seeing token YYTOKEN is to reduce or to
+     detect an error, take that action.  */
+  yyn += yytoken;
+  if (yyn < 0 || YYLAST < yyn || yycheck[yyn] != yytoken)
+    goto yydefault;
+  yyn = yytable[yyn];
+  if (yyn <= 0)
+    {
+      if (yytable_value_is_error (yyn))
+        goto yyerrlab;
+      yyn = -yyn;
+      goto yyreduce;
+    }
+
+  /* Count tokens shifted since error; after three, turn off error
+     status.  */
+  if (yyerrstatus)
+    yyerrstatus--;
+
+  /* Shift the lookahead token.  */
+  YY_SYMBOL_PRINT ("Shifting", yytoken, &yylval, &yylloc);
+
+  /* Discard the shifted token.  */
+  yychar = YYEMPTY;
+
+  yystate = yyn;
+  *++yyvsp = yylval;
+
+  goto yynewstate;
+
+
+/*-----------------------------------------------------------.
+| yydefault -- do the default action for the current state.  |
+`-----------------------------------------------------------*/
+yydefault:
+  yyn = yydefact[yystate];
+  if (yyn == 0)
+    goto yyerrlab;
+  goto yyreduce;
+
+
+/*-----------------------------.
+| yyreduce -- Do a reduction.  |
+`-----------------------------*/
+yyreduce:
+  /* yyn is the number of a rule to reduce with.  */
+  yylen = yyr2[yyn];
+
+  /* If YYLEN is nonzero, implement the default value of the action:
+     `$$ = $1'.
+
+     Otherwise, the following line sets YYVAL to garbage.
+     This behavior is undocumented and Bison
+     users should not rely upon it.  Assigning to YYVAL
+     unconditionally makes the parser a bit smaller, and it avoids a
+     GCC warning that YYVAL may be used uninitialized.  */
+  yyval = yyvsp[1-yylen];
+
+
+  YY_REDUCE_PRINT (yyn);
+  switch (yyn)
+    {
+        case 11:
+
+/* Line 1806 of yacc.c  */
+#line 133 "lib/conf-parse.y"
+    { sensors_bus new_el;
+		    new_el.line = (yyvsp[(1) - (3)].line);
+		    new_el.bus = (yyvsp[(2) - (3)].bus);
+                    new_el.adapter = (yyvsp[(3) - (3)].name);
+		    bus_add_el(&new_el);
+		  }
+    break;
+
+  case 12:
+
+/* Line 1806 of yacc.c  */
+#line 142 "lib/conf-parse.y"
+    { sensors_label new_el;
+			    if (!current_chip) {
+			      sensors_yyerror("Label statement before first chip statement");
+			      free((yyvsp[(2) - (3)].name));
+			      free((yyvsp[(3) - (3)].name));
+			      YYERROR;
+			    }
+			    new_el.line = (yyvsp[(1) - (3)].line);
+			    new_el.name = (yyvsp[(2) - (3)].name);
+			    new_el.value = (yyvsp[(3) - (3)].name);
+			    label_add_el(&new_el);
+			  }
+    break;
+
+  case 13:
+
+/* Line 1806 of yacc.c  */
+#line 157 "lib/conf-parse.y"
+    { sensors_set new_el;
+		    if (!current_chip) {
+		      sensors_yyerror("Set statement before first chip statement");
+		      free((yyvsp[(2) - (3)].name));
+		      sensors_free_expr((yyvsp[(3) - (3)].expr));
+		      YYERROR;
+		    }
+		    new_el.line = (yyvsp[(1) - (3)].line);
+		    new_el.name = (yyvsp[(2) - (3)].name);
+		    new_el.value = (yyvsp[(3) - (3)].expr);
+		    set_add_el(&new_el);
+		  }
+    break;
+
+  case 14:
+
+/* Line 1806 of yacc.c  */
+#line 172 "lib/conf-parse.y"
+    { sensors_compute new_el;
+			    if (!current_chip) {
+			      sensors_yyerror("Compute statement before first chip statement");
+			      free((yyvsp[(2) - (5)].name));
+			      sensors_free_expr((yyvsp[(3) - (5)].expr));
+			      sensors_free_expr((yyvsp[(5) - (5)].expr));
+			      YYERROR;
+			    }
+			    new_el.line = (yyvsp[(1) - (5)].line);
+			    new_el.name = (yyvsp[(2) - (5)].name);
+			    new_el.from_proc = (yyvsp[(3) - (5)].expr);
+			    new_el.to_proc = (yyvsp[(5) - (5)].expr);
+			    compute_add_el(&new_el);
+			  }
+    break;
+
+  case 15:
+
+/* Line 1806 of yacc.c  */
+#line 189 "lib/conf-parse.y"
+    { sensors_ignore new_el;
+			  if (!current_chip) {
+			    sensors_yyerror("Ignore statement before first chip statement");
+			    free((yyvsp[(2) - (2)].name));
+			    YYERROR;
+			  }
+			  new_el.line = (yyvsp[(1) - (2)].line);
+			  new_el.name = (yyvsp[(2) - (2)].name);
+			  ignore_add_el(&new_el);
+			}
+    break;
+
+  case 16:
+
+/* Line 1806 of yacc.c  */
+#line 202 "lib/conf-parse.y"
+    { sensors_chip new_el;
+		    new_el.line = (yyvsp[(1) - (2)].line);
+		    new_el.labels = NULL;
+		    new_el.sets = NULL;
+		    new_el.computes = NULL;
+		    new_el.ignores = NULL;
+		    new_el.labels_count = new_el.labels_max = 0;
+		    new_el.sets_count = new_el.sets_max = 0;
+		    new_el.computes_count = new_el.computes_max = 0;
+		    new_el.ignores_count = new_el.ignores_max = 0;
+		    new_el.chips = (yyvsp[(2) - (2)].chips);
+		    chip_add_el(&new_el);
+		    current_chip = sensors_config_chips + 
+		                   sensors_config_chips_count - 1;
+		  }
+    break;
+
+  case 17:
+
+/* Line 1806 of yacc.c  */
+#line 220 "lib/conf-parse.y"
+    { 
+		    (yyval.chips).fits = NULL;
+		    (yyval.chips).fits_count = (yyval.chips).fits_max = 0;
+		    fits_add_el(&(yyvsp[(1) - (1)].chip),(yyval.chips));
+		  }
+    break;
+
+  case 18:
+
+/* Line 1806 of yacc.c  */
+#line 226 "lib/conf-parse.y"
+    { (yyval.chips) = (yyvsp[(1) - (2)].chips);
+		    fits_add_el(&(yyvsp[(2) - (2)].chip),(yyval.chips));
+		  }
+    break;
+
+  case 19:
+
+/* Line 1806 of yacc.c  */
+#line 232 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->data.val = (yyvsp[(1) - (1)].value); 
+		    (yyval.expr)->kind = sensors_kind_val;
+		  }
+    break;
+
+  case 20:
+
+/* Line 1806 of yacc.c  */
+#line 237 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->data.var = (yyvsp[(1) - (1)].name);
+		    (yyval.expr)->kind = sensors_kind_var;
+		  }
+    break;
+
+  case 21:
+
+/* Line 1806 of yacc.c  */
+#line 242 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr();
+		    (yyval.expr)->kind = sensors_kind_source;
+		  }
+    break;
+
+  case 22:
+
+/* Line 1806 of yacc.c  */
+#line 246 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_add;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(1) - (3)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = (yyvsp[(3) - (3)].expr);
+		  }
+    break;
+
+  case 23:
+
+/* Line 1806 of yacc.c  */
+#line 253 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_sub;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(1) - (3)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = (yyvsp[(3) - (3)].expr);
+		  }
+    break;
+
+  case 24:
+
+/* Line 1806 of yacc.c  */
+#line 260 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_multiply;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(1) - (3)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = (yyvsp[(3) - (3)].expr);
+		  }
+    break;
+
+  case 25:
+
+/* Line 1806 of yacc.c  */
+#line 267 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_divide;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(1) - (3)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = (yyvsp[(3) - (3)].expr);
+		  }
+    break;
+
+  case 26:
+
+/* Line 1806 of yacc.c  */
+#line 274 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_negate;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(2) - (2)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = NULL;
+		  }
+    break;
+
+  case 27:
+
+/* Line 1806 of yacc.c  */
+#line 281 "lib/conf-parse.y"
+    { (yyval.expr) = (yyvsp[(2) - (3)].expr); }
+    break;
+
+  case 28:
+
+/* Line 1806 of yacc.c  */
+#line 283 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_exp;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(2) - (2)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = NULL;
+		  }
+    break;
+
+  case 29:
+
+/* Line 1806 of yacc.c  */
+#line 290 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_log;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(2) - (2)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = NULL;
+		  }
+    break;
+
+  case 30:
+
+/* Line 1806 of yacc.c  */
+#line 299 "lib/conf-parse.y"
+    { int res = sensors_parse_bus_id((yyvsp[(1) - (1)].name),&(yyval.bus));
+		    free((yyvsp[(1) - (1)].name));
+		    if (res) {
+                      sensors_yyerror("Parse error in bus id");
+		      YYERROR;
+                    }
+		  }
+    break;
+
+  case 31:
+
+/* Line 1806 of yacc.c  */
+#line 309 "lib/conf-parse.y"
+    { (yyval.name) = (yyvsp[(1) - (1)].name); }
+    break;
+
+  case 32:
+
+/* Line 1806 of yacc.c  */
+#line 313 "lib/conf-parse.y"
+    { (yyval.name) = (yyvsp[(1) - (1)].name); }
+    break;
+
+  case 33:
+
+/* Line 1806 of yacc.c  */
+#line 317 "lib/conf-parse.y"
+    { (yyval.name) = (yyvsp[(1) - (1)].name); }
+    break;
+
+  case 34:
+
+/* Line 1806 of yacc.c  */
+#line 321 "lib/conf-parse.y"
+    { int res = sensors_parse_chip_name((yyvsp[(1) - (1)].name),&(yyval.chip)); 
+		    free((yyvsp[(1) - (1)].name));
+		    if (res) {
+		      sensors_yyerror("Parse error in chip name");
+		      YYERROR;
+		    }
+		  }
+    break;
+
+
+
+/* Line 1806 of yacc.c  */
+#line 1793 "lib/conf-parse.c"
+      default: break;
+    }
+  /* User semantic actions sometimes alter yychar, and that requires
+     that yytoken be updated with the new translation.  We take the
+     approach of translating immediately before every use of yytoken.
+     One alternative is translating here after every semantic action,
+     but that translation would be missed if the semantic action invokes
+     YYABORT, YYACCEPT, or YYERROR immediately after altering yychar or
+     if it invokes YYBACKUP.  In the case of YYABORT or YYACCEPT, an
+     incorrect destructor might then be invoked immediately.  In the
+     case of YYERROR or YYBACKUP, subsequent parser actions might lead
+     to an incorrect destructor call or verbose syntax error message
+     before the lookahead is translated.  */
+  YY_SYMBOL_PRINT ("-> $$ =", yyr1[yyn], &yyval, &yyloc);
+
+  YYPOPSTACK (yylen);
+  yylen = 0;
+  YY_STACK_PRINT (yyss, yyssp);
+
+  *++yyvsp = yyval;
+
+  /* Now `shift' the result of the reduction.  Determine what state
+     that goes to, based on the state we popped back to and the rule
+     number reduced by.  */
+
+  yyn = yyr1[yyn];
+
+  yystate = yypgoto[yyn - YYNTOKENS] + *yyssp;
+  if (0 <= yystate && yystate <= YYLAST && yycheck[yystate] == *yyssp)
+    yystate = yytable[yystate];
+  else
+    yystate = yydefgoto[yyn - YYNTOKENS];
+
+  goto yynewstate;
+
+
+/*------------------------------------.
+| yyerrlab -- here on detecting error |
+`------------------------------------*/
+yyerrlab:
+  /* Make sure we have latest lookahead translation.  See comments at
+     user semantic actions for why this is necessary.  */
+  yytoken = yychar == YYEMPTY ? YYEMPTY : YYTRANSLATE (yychar);
+
+  /* If not already recovering from an error, report this error.  */
+  if (!yyerrstatus)
+    {
+      ++yynerrs;
+#if ! YYERROR_VERBOSE
+      yyerror (YY_("syntax error"));
+#else
+# define YYSYNTAX_ERROR yysyntax_error (&yymsg_alloc, &yymsg, \
+                                        yyssp, yytoken)
+      {
+        char const *yymsgp = YY_("syntax error");
+        int yysyntax_error_status;
+        yysyntax_error_status = YYSYNTAX_ERROR;
+        if (yysyntax_error_status == 0)
+          yymsgp = yymsg;
+        else if (yysyntax_error_status == 1)
+          {
+            if (yymsg != yymsgbuf)
+              YYSTACK_FREE (yymsg);
+            yymsg = (char *) YYSTACK_ALLOC (yymsg_alloc);
+            if (!yymsg)
+              {
+                yymsg = yymsgbuf;
+                yymsg_alloc = sizeof yymsgbuf;
+                yysyntax_error_status = 2;
+              }
+            else
+              {
+                yysyntax_error_status = YYSYNTAX_ERROR;
+                yymsgp = yymsg;
+              }
+          }
+        yyerror (yymsgp);
+        if (yysyntax_error_status == 2)
+          goto yyexhaustedlab;
+      }
+# undef YYSYNTAX_ERROR
+#endif
+    }
+
+
+
+  if (yyerrstatus == 3)
+    {
+      /* If just tried and failed to reuse lookahead token after an
+	 error, discard it.  */
+
+      if (yychar <= YYEOF)
+	{
+	  /* Return failure if at end of input.  */
+	  if (yychar == YYEOF)
+	    YYABORT;
+	}
+      else
+	{
+	  yydestruct ("Error: discarding",
+		      yytoken, &yylval);
+	  yychar = YYEMPTY;
+	}
+    }
+
+  /* Else will try to reuse lookahead token after shifting the error
+     token.  */
+  goto yyerrlab1;
+
+
+/*---------------------------------------------------.
+| yyerrorlab -- error raised explicitly by YYERROR.  |
+`---------------------------------------------------*/
+yyerrorlab:
+
+  /* Pacify compilers like GCC when the user code never invokes
+     YYERROR and the label yyerrorlab therefore never appears in user
+     code.  */
+  if (/*CONSTCOND*/ 0)
+     goto yyerrorlab;
+
+  /* Do not reclaim the symbols of the rule which action triggered
+     this YYERROR.  */
+  YYPOPSTACK (yylen);
+  yylen = 0;
+  YY_STACK_PRINT (yyss, yyssp);
+  yystate = *yyssp;
+  goto yyerrlab1;
+
+
+/*-------------------------------------------------------------.
+| yyerrlab1 -- common code for both syntax error and YYERROR.  |
+`-------------------------------------------------------------*/
+yyerrlab1:
+  yyerrstatus = 3;	/* Each real token shifted decrements this.  */
+
+  for (;;)
+    {
+      yyn = yypact[yystate];
+      if (!yypact_value_is_default (yyn))
+	{
+	  yyn += YYTERROR;
+	  if (0 <= yyn && yyn <= YYLAST && yycheck[yyn] == YYTERROR)
+	    {
+	      yyn = yytable[yyn];
+	      if (0 < yyn)
+		break;
+	    }
+	}
+
+      /* Pop the current state because it cannot handle the error token.  */
+      if (yyssp == yyss)
+	YYABORT;
+
+
+      yydestruct ("Error: popping",
+		  yystos[yystate], yyvsp);
+      YYPOPSTACK (1);
+      yystate = *yyssp;
+      YY_STACK_PRINT (yyss, yyssp);
+    }
+
+  *++yyvsp = yylval;
+
+
+  /* Shift the error token.  */
+  YY_SYMBOL_PRINT ("Shifting", yystos[yyn], yyvsp, yylsp);
+
+  yystate = yyn;
+  goto yynewstate;
+
+
+/*-------------------------------------.
+| yyacceptlab -- YYACCEPT comes here.  |
+`-------------------------------------*/
+yyacceptlab:
+  yyresult = 0;
+  goto yyreturn;
+
+/*-----------------------------------.
+| yyabortlab -- YYABORT comes here.  |
+`-----------------------------------*/
+yyabortlab:
+  yyresult = 1;
+  goto yyreturn;
+
+#if !defined(yyoverflow) || YYERROR_VERBOSE
+/*-------------------------------------------------.
+| yyexhaustedlab -- memory exhaustion comes here.  |
+`-------------------------------------------------*/
+yyexhaustedlab:
+  yyerror (YY_("memory exhausted"));
+  yyresult = 2;
+  /* Fall through.  */
+#endif
+
+yyreturn:
+  if (yychar != YYEMPTY)
+    {
+      /* Make sure we have latest lookahead translation.  See comments at
+         user semantic actions for why this is necessary.  */
+      yytoken = YYTRANSLATE (yychar);
+      yydestruct ("Cleanup: discarding lookahead",
+                  yytoken, &yylval);
+    }
+  /* Do not reclaim the symbols of the rule which action triggered
+     this YYABORT or YYACCEPT.  */
+  YYPOPSTACK (yylen);
+  YY_STACK_PRINT (yyss, yyssp);
+  while (yyssp != yyss)
+    {
+      yydestruct ("Cleanup: popping",
+		  yystos[*yyssp], yyvsp);
+      YYPOPSTACK (1);
+    }
+#ifndef yyoverflow
+  if (yyss != yyssa)
+    YYSTACK_FREE (yyss);
+#endif
+#if YYERROR_VERBOSE
+  if (yymsg != yymsgbuf)
+    YYSTACK_FREE (yymsg);
+#endif
+  /* Make sure YYID is used.  */
+  return YYID (yyresult);
+}
+
+
+
+/* Line 2067 of yacc.c  */
+#line 330 "lib/conf-parse.y"
+
+
+void sensors_yyerror(const char *err)
+{
+  if (sensors_lex_error[0]) {
+    sensors_parse_error_wfn(sensors_lex_error, sensors_yyfilename, sensors_yylineno);
+    sensors_lex_error[0] = '\0';
+  } else
+    sensors_parse_error_wfn(err, sensors_yyfilename, sensors_yylineno);
+}
+
+sensors_expr *malloc_expr(void)
+{
+  sensors_expr *res = malloc(sizeof(sensors_expr));
+  if (! res)
+    sensors_fatal_error(__func__, "Allocating a new expression");
+  return res;
+}
+
diff --git a/tools/gator/daemon/libsensors/conf-parse.h b/tools/gator/daemon/libsensors/conf-parse.h
new file mode 100644
index 00000000000..89c9c1a0d59
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-parse.h
@@ -0,0 +1,84 @@
+/* A Bison parser, made by GNU Bison 2.5.  */
+
+/* Bison interface for Yacc-like parsers in C
+   
+      Copyright (C) 1984, 1989-1990, 2000-2011 Free Software Foundation, Inc.
+   
+   This program is free software: you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation, either version 3 of the License, or
+   (at your option) any later version.
+   
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+   
+   You should have received a copy of the GNU General Public License
+   along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
+
+/* As a special exception, you may create a larger work that contains
+   part or all of the Bison parser skeleton and distribute that work
+   under terms of your choice, so long as that work isn't itself a
+   parser generator using the skeleton or a modified version thereof
+   as a parser skeleton.  Alternatively, if you modify or redistribute
+   the parser skeleton itself, you may (at your option) remove this
+   special exception, which will cause the skeleton and the resulting
+   Bison output files to be licensed under the GNU General Public
+   License without this special exception.
+   
+   This special exception was added by the Free Software Foundation in
+   version 2.2 of Bison.  */
+
+
+/* Tokens.  */
+#ifndef YYTOKENTYPE
+# define YYTOKENTYPE
+   /* Put the tokens into the symbol table, so that GDB and other debuggers
+      know about them.  */
+   enum yytokentype {
+     NEG = 258,
+     EOL = 259,
+     BUS = 260,
+     LABEL = 261,
+     SET = 262,
+     CHIP = 263,
+     COMPUTE = 264,
+     IGNORE = 265,
+     FLOAT = 266,
+     NAME = 267,
+     ERROR = 268
+   };
+#endif
+
+
+
+#if ! defined YYSTYPE && ! defined YYSTYPE_IS_DECLARED
+typedef union YYSTYPE
+{
+
+/* Line 2068 of yacc.c  */
+#line 79 "lib/conf-parse.y"
+
+  double value;
+  char *name;
+  void *nothing;
+  sensors_chip_name_list chips;
+  sensors_expr *expr;
+  sensors_bus_id bus;
+  sensors_chip_name chip;
+  sensors_config_line line;
+
+
+
+/* Line 2068 of yacc.c  */
+#line 76 "lib/conf-parse.h"
+} YYSTYPE;
+# define YYSTYPE_IS_TRIVIAL 1
+# define yystype YYSTYPE /* obsolescent; will be withdrawn */
+# define YYSTYPE_IS_DECLARED 1
+#endif
+
+extern YYSTYPE sensors_yylval;
+
+
diff --git a/tools/gator/daemon/libsensors/conf-parse.y b/tools/gator/daemon/libsensors/conf-parse.y
new file mode 100644
index 00000000000..1937f544dc6
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-parse.y
@@ -0,0 +1,347 @@
+%{
+/*
+    conf-parse.y - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#define YYERROR_VERBOSE
+
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+
+#include "data.h"
+#include "general.h"
+#include "error.h"
+#include "conf.h"
+#include "access.h"
+#include "init.h"
+
+static void sensors_yyerror(const char *err);
+static sensors_expr *malloc_expr(void);
+
+static sensors_chip *current_chip = NULL;
+
+#define bus_add_el(el) sensors_add_array_el(el,\
+                                      &sensors_config_busses,\
+                                      &sensors_config_busses_count,\
+                                      &sensors_config_busses_max,\
+                                      sizeof(sensors_bus))
+#define label_add_el(el) sensors_add_array_el(el,\
+                                        &current_chip->labels,\
+                                        &current_chip->labels_count,\
+                                        &current_chip->labels_max,\
+                                        sizeof(sensors_label));
+#define set_add_el(el) sensors_add_array_el(el,\
+                                      &current_chip->sets,\
+                                      &current_chip->sets_count,\
+                                      &current_chip->sets_max,\
+                                      sizeof(sensors_set));
+#define compute_add_el(el) sensors_add_array_el(el,\
+                                          &current_chip->computes,\
+                                          &current_chip->computes_count,\
+                                          &current_chip->computes_max,\
+                                          sizeof(sensors_compute));
+#define ignore_add_el(el) sensors_add_array_el(el,\
+                                          &current_chip->ignores,\
+                                          &current_chip->ignores_count,\
+                                          &current_chip->ignores_max,\
+                                          sizeof(sensors_ignore));
+#define chip_add_el(el) sensors_add_array_el(el,\
+                                       &sensors_config_chips,\
+                                       &sensors_config_chips_count,\
+                                       &sensors_config_chips_max,\
+                                       sizeof(sensors_chip));
+
+#define fits_add_el(el,list) sensors_add_array_el(el,\
+                                                  &(list).fits,\
+                                                  &(list).fits_count,\
+                                                  &(list).fits_max, \
+		                                  sizeof(sensors_chip_name));
+
+%}
+
+%union {
+  double value;
+  char *name;
+  void *nothing;
+  sensors_chip_name_list chips;
+  sensors_expr *expr;
+  sensors_bus_id bus;
+  sensors_chip_name chip;
+  sensors_config_line line;
+}  
+
+%left <nothing> '-' '+'
+%left <nothing> '*' '/'
+%left <nothing> NEG
+%right <nothing> '^' '`'
+
+%token <nothing> ','
+%token <nothing> EOL
+%token <line> BUS
+%token <line> LABEL
+%token <line> SET
+%token <line> CHIP
+%token <line> COMPUTE
+%token <line> IGNORE
+%token <value> FLOAT
+%token <name> NAME
+%token <nothing> ERROR
+
+%type <chips> chip_name_list
+%type <expr> expression
+%type <bus> bus_id
+%type <name> adapter_name
+%type <name> function_name
+%type <name> string
+%type <chip> chip_name
+
+%start input
+
+%%
+
+input:	  /* empty */
+	| input line
+;
+
+line:	  bus_statement EOL
+	| label_statement EOL
+	| set_statement EOL
+	| chip_statement EOL
+	| compute_statement EOL
+	| ignore_statement EOL
+	| error	EOL
+;
+
+bus_statement:	  BUS bus_id adapter_name
+		  { sensors_bus new_el;
+		    new_el.line = $1;
+		    new_el.bus = $2;
+                    new_el.adapter = $3;
+		    bus_add_el(&new_el);
+		  }
+;
+
+label_statement:	  LABEL function_name string
+			  { sensors_label new_el;
+			    if (!current_chip) {
+			      sensors_yyerror("Label statement before first chip statement");
+			      free($2);
+			      free($3);
+			      YYERROR;
+			    }
+			    new_el.line = $1;
+			    new_el.name = $2;
+			    new_el.value = $3;
+			    label_add_el(&new_el);
+			  }
+;
+
+set_statement:	  SET function_name expression
+		  { sensors_set new_el;
+		    if (!current_chip) {
+		      sensors_yyerror("Set statement before first chip statement");
+		      free($2);
+		      sensors_free_expr($3);
+		      YYERROR;
+		    }
+		    new_el.line = $1;
+		    new_el.name = $2;
+		    new_el.value = $3;
+		    set_add_el(&new_el);
+		  }
+;
+
+compute_statement:	  COMPUTE function_name expression ',' expression
+			  { sensors_compute new_el;
+			    if (!current_chip) {
+			      sensors_yyerror("Compute statement before first chip statement");
+			      free($2);
+			      sensors_free_expr($3);
+			      sensors_free_expr($5);
+			      YYERROR;
+			    }
+			    new_el.line = $1;
+			    new_el.name = $2;
+			    new_el.from_proc = $3;
+			    new_el.to_proc = $5;
+			    compute_add_el(&new_el);
+			  }
+;
+
+ignore_statement:	IGNORE function_name
+			{ sensors_ignore new_el;
+			  if (!current_chip) {
+			    sensors_yyerror("Ignore statement before first chip statement");
+			    free($2);
+			    YYERROR;
+			  }
+			  new_el.line = $1;
+			  new_el.name = $2;
+			  ignore_add_el(&new_el);
+			}
+;
+
+chip_statement:	  CHIP chip_name_list
+		  { sensors_chip new_el;
+		    new_el.line = $1;
+		    new_el.labels = NULL;
+		    new_el.sets = NULL;
+		    new_el.computes = NULL;
+		    new_el.ignores = NULL;
+		    new_el.labels_count = new_el.labels_max = 0;
+		    new_el.sets_count = new_el.sets_max = 0;
+		    new_el.computes_count = new_el.computes_max = 0;
+		    new_el.ignores_count = new_el.ignores_max = 0;
+		    new_el.chips = $2;
+		    chip_add_el(&new_el);
+		    current_chip = sensors_config_chips + 
+		                   sensors_config_chips_count - 1;
+		  }
+;
+
+chip_name_list:	  chip_name
+		  { 
+		    $$.fits = NULL;
+		    $$.fits_count = $$.fits_max = 0;
+		    fits_add_el(&$1,$$);
+		  }
+		| chip_name_list chip_name
+		  { $$ = $1;
+		    fits_add_el(&$2,$$);
+		  }
+;
+	
+expression:	  FLOAT	
+		  { $$ = malloc_expr(); 
+		    $$->data.val = $1; 
+		    $$->kind = sensors_kind_val;
+		  }
+		| NAME
+		  { $$ = malloc_expr(); 
+		    $$->data.var = $1;
+		    $$->kind = sensors_kind_var;
+		  }
+		| '@'
+		  { $$ = malloc_expr();
+		    $$->kind = sensors_kind_source;
+		  }
+		| expression '+' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_add;
+		    $$->data.subexpr.sub1 = $1;
+		    $$->data.subexpr.sub2 = $3;
+		  }
+		| expression '-' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_sub;
+		    $$->data.subexpr.sub1 = $1;
+		    $$->data.subexpr.sub2 = $3;
+		  }
+		| expression '*' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_multiply;
+		    $$->data.subexpr.sub1 = $1;
+		    $$->data.subexpr.sub2 = $3;
+		  }
+		| expression '/' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_divide;
+		    $$->data.subexpr.sub1 = $1;
+		    $$->data.subexpr.sub2 = $3;
+		  }
+		| '-' expression  %prec NEG
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_negate;
+		    $$->data.subexpr.sub1 = $2;
+		    $$->data.subexpr.sub2 = NULL;
+		  }
+		| '(' expression ')'
+		  { $$ = $2; }
+		| '^' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_exp;
+		    $$->data.subexpr.sub1 = $2;
+		    $$->data.subexpr.sub2 = NULL;
+		  }
+		| '`' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_log;
+		    $$->data.subexpr.sub1 = $2;
+		    $$->data.subexpr.sub2 = NULL;
+		  }
+;
+
+bus_id:		  NAME
+		  { int res = sensors_parse_bus_id($1,&$$);
+		    free($1);
+		    if (res) {
+                      sensors_yyerror("Parse error in bus id");
+		      YYERROR;
+                    }
+		  }
+;
+
+adapter_name:	  NAME
+		  { $$ = $1; }
+;
+
+function_name:	  NAME
+		  { $$ = $1; }
+;
+
+string:	  NAME
+	  { $$ = $1; }
+;
+
+chip_name:	  NAME
+		  { int res = sensors_parse_chip_name($1,&$$); 
+		    free($1);
+		    if (res) {
+		      sensors_yyerror("Parse error in chip name");
+		      YYERROR;
+		    }
+		  }
+;
+
+%%
+
+void sensors_yyerror(const char *err)
+{
+  if (sensors_lex_error[0]) {
+    sensors_parse_error_wfn(sensors_lex_error, sensors_yyfilename, sensors_yylineno);
+    sensors_lex_error[0] = '\0';
+  } else
+    sensors_parse_error_wfn(err, sensors_yyfilename, sensors_yylineno);
+}
+
+sensors_expr *malloc_expr(void)
+{
+  sensors_expr *res = malloc(sizeof(sensors_expr));
+  if (! res)
+    sensors_fatal_error(__func__, "Allocating a new expression");
+  return res;
+}
diff --git a/tools/gator/daemon/libsensors/conf.h b/tools/gator/daemon/libsensors/conf.h
new file mode 100644
index 00000000000..b7ce4f7ca83
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf.h
@@ -0,0 +1,34 @@
+/*
+    conf.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_CONF_H
+#define LIB_SENSORS_CONF_H
+
+/* This is defined in conf-lex.l */
+int sensors_yylex(void);
+extern char sensors_lex_error[];
+extern const char *sensors_yyfilename;
+extern int sensors_yylineno;
+extern FILE *sensors_yyin;
+
+/* This is defined in conf-parse.y */
+int sensors_yyparse(void);
+
+#endif /* LIB_SENSORS_CONF_H */
diff --git a/tools/gator/daemon/libsensors/data.c b/tools/gator/daemon/libsensors/data.c
new file mode 100644
index 00000000000..cac9c8dc6eb
--- /dev/null
+++ b/tools/gator/daemon/libsensors/data.c
@@ -0,0 +1,278 @@
+/*
+    data.c - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007, 2009  Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to move version.h to the current directory. ***/
+
+/* this define needed for strndup() */
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "access.h"
+#include "error.h"
+#include "data.h"
+#include "sensors.h"
+#include "version.h"
+
+const char *libsensors_version = LM_VERSION;
+
+char **sensors_config_files = NULL;
+int sensors_config_files_count = 0;
+int sensors_config_files_max = 0;
+
+sensors_chip *sensors_config_chips = NULL;
+int sensors_config_chips_count = 0;
+int sensors_config_chips_subst = 0;
+int sensors_config_chips_max = 0;
+
+sensors_bus *sensors_config_busses = NULL;
+int sensors_config_busses_count = 0;
+int sensors_config_busses_max = 0;
+
+sensors_chip_features *sensors_proc_chips = NULL;
+int sensors_proc_chips_count = 0;
+int sensors_proc_chips_max = 0;
+
+sensors_bus *sensors_proc_bus = NULL;
+int sensors_proc_bus_count = 0;
+int sensors_proc_bus_max = 0;
+
+void sensors_free_chip_name(sensors_chip_name *chip)
+{
+	free(chip->prefix);
+}
+
+/*
+   Parse a chip name to the internal representation. These are valid names:
+
+     lm78-i2c-10-5e		*-i2c-10-5e
+     lm78-i2c-10-*		*-i2c-10-*
+     lm78-i2c-*-5e		*-i2c-*-5e
+     lm78-i2c-*-*		*-i2c-*-*
+     lm78-isa-10dd		*-isa-10dd
+     lm78-isa-*			*-isa-*
+     lm78-*			*-*
+
+   Here 'lm78' can be any prefix. 'i2c' and 'isa' are
+   literal strings, just like all dashes '-' and wildcards '*'. '10' can
+   be any decimal i2c bus number. '5e' can be any hexadecimal i2c device
+   address, and '10dd' any hexadecimal isa address.
+
+   The 'prefix' part in the result is freshly allocated. All old contents
+   of res is overwritten. res itself is not allocated. In case of an error
+   return (ie. != 0), res is undefined, but all allocations are undone.
+*/
+
+int sensors_parse_chip_name(const char *name, sensors_chip_name *res)
+{
+	char *dash;
+
+	/* First, the prefix. It's either "*" or a real chip name. */
+	if (!strncmp(name, "*-", 2)) {
+		res->prefix = SENSORS_CHIP_NAME_PREFIX_ANY;
+		name += 2;
+	} else {
+		if (!(dash = strchr(name, '-')))
+			return -SENSORS_ERR_CHIP_NAME;
+		res->prefix = strndup(name, dash - name);
+		if (!res->prefix)
+			sensors_fatal_error(__func__,
+					    "Allocating name prefix");
+		name = dash + 1;
+	}
+
+	/* Then we have either a sole "*" (all chips with this name) or a bus
+	   type and an address. */
+	if (!strcmp(name, "*")) {
+		res->bus.type = SENSORS_BUS_TYPE_ANY;
+		res->bus.nr = SENSORS_BUS_NR_ANY;
+		res->addr = SENSORS_CHIP_NAME_ADDR_ANY;
+		return 0;
+	}
+
+	if (!(dash = strchr(name, '-')))
+		goto ERROR;
+	if (!strncmp(name, "i2c", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_I2C;
+	else if (!strncmp(name, "isa", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_ISA;
+	else if (!strncmp(name, "pci", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_PCI;
+	else if (!strncmp(name, "spi", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_SPI;
+	else if (!strncmp(name, "virtual", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_VIRTUAL;
+	else if (!strncmp(name, "acpi", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_ACPI;
+	else if (!strncmp(name, "hid", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_HID;
+	else
+		goto ERROR;
+	name = dash + 1;
+
+	/* Some bus types (i2c, spi) have an additional bus number.
+	   For these, the next part is either a "*" (any bus of that type)
+	   or a decimal number. */
+	switch (res->bus.type) {
+	case SENSORS_BUS_TYPE_I2C:
+	case SENSORS_BUS_TYPE_SPI:
+	case SENSORS_BUS_TYPE_HID:
+		if (!strncmp(name, "*-", 2)) {
+			res->bus.nr = SENSORS_BUS_NR_ANY;
+			name += 2;
+			break;
+		}
+
+		res->bus.nr = strtoul(name, &dash, 10);
+		if (*name == '\0' || *dash != '-' || res->bus.nr < 0)
+			goto ERROR;
+		name = dash + 1;
+		break;
+	default:
+		res->bus.nr = SENSORS_BUS_NR_ANY;
+	}
+
+	/* Last part is the chip address, or "*" for any address. */
+	if (!strcmp(name, "*")) {
+		res->addr = SENSORS_CHIP_NAME_ADDR_ANY;
+	} else {
+		res->addr = strtoul(name, &dash, 16);
+		if (*name == '\0' || *dash != '\0' || res->addr < 0)
+			goto ERROR;
+	}
+
+	return 0;
+
+ERROR:
+	free(res->prefix);
+	return -SENSORS_ERR_CHIP_NAME;
+}
+
+int sensors_snprintf_chip_name(char *str, size_t size,
+			       const sensors_chip_name *chip)
+{
+	if (sensors_chip_name_has_wildcards(chip))
+		return -SENSORS_ERR_WILDCARDS;
+
+	switch (chip->bus.type) {
+	case SENSORS_BUS_TYPE_ISA:
+		return snprintf(str, size, "%s-isa-%04x", chip->prefix,
+				chip->addr);
+	case SENSORS_BUS_TYPE_PCI:
+		return snprintf(str, size, "%s-pci-%04x", chip->prefix,
+				chip->addr);
+	case SENSORS_BUS_TYPE_I2C:
+		return snprintf(str, size, "%s-i2c-%hd-%02x", chip->prefix,
+				chip->bus.nr, chip->addr);
+	case SENSORS_BUS_TYPE_SPI:
+		return snprintf(str, size, "%s-spi-%hd-%x", chip->prefix,
+				chip->bus.nr, chip->addr);
+	case SENSORS_BUS_TYPE_VIRTUAL:
+		return snprintf(str, size, "%s-virtual-%x", chip->prefix,
+				chip->addr);
+	case SENSORS_BUS_TYPE_ACPI:
+		return snprintf(str, size, "%s-acpi-%x", chip->prefix,
+				chip->addr);
+	case SENSORS_BUS_TYPE_HID:
+		return snprintf(str, size, "%s-hid-%hd-%x", chip->prefix,
+				chip->bus.nr, chip->addr);
+	}
+
+	return -SENSORS_ERR_CHIP_NAME;
+}
+
+int sensors_parse_bus_id(const char *name, sensors_bus_id *bus)
+{
+	char *endptr;
+
+	if (strncmp(name, "i2c-", 4)) {
+		return -SENSORS_ERR_BUS_NAME;
+	}
+	name += 4;
+	bus->type = SENSORS_BUS_TYPE_I2C;
+	bus->nr = strtoul(name, &endptr, 10);
+	if (*name == '\0' || *endptr != '\0' || bus->nr < 0)
+		return -SENSORS_ERR_BUS_NAME;
+	return 0;
+}
+
+static int sensors_substitute_chip(sensors_chip_name *name,
+				   const char *filename, int lineno)
+{
+	int i, j;
+	for (i = 0; i < sensors_config_busses_count; i++)
+		if (sensors_config_busses[i].bus.type == name->bus.type &&
+		    sensors_config_busses[i].bus.nr == name->bus.nr)
+			break;
+
+	if (i == sensors_config_busses_count) {
+		sensors_parse_error_wfn("Undeclared bus id referenced",
+					filename, lineno);
+		name->bus.nr = SENSORS_BUS_NR_IGNORE;
+		return -SENSORS_ERR_BUS_NAME;
+	}
+
+	/* Compare the adapter names */
+	for (j = 0; j < sensors_proc_bus_count; j++) {
+		if (!strcmp(sensors_config_busses[i].adapter,
+			    sensors_proc_bus[j].adapter)) {
+			name->bus.nr = sensors_proc_bus[j].bus.nr;
+			return 0;
+		}
+	}
+
+	/* We did not find a matching bus name, simply ignore this chip
+	   config entry. */
+	name->bus.nr = SENSORS_BUS_NR_IGNORE;
+	return 0;
+}
+
+/* Bus substitution is on a per-configuration file basis, so we keep
+   memory (in sensors_config_chips_subst) of which chip entries have been
+   already substituted. */
+int sensors_substitute_busses(void)
+{
+	int err, i, j, lineno;
+	sensors_chip_name_list *chips;
+	const char *filename;
+	int res = 0;
+
+	for (i = sensors_config_chips_subst;
+	     i < sensors_config_chips_count; i++) {
+		filename = sensors_config_chips[i].line.filename;
+		lineno = sensors_config_chips[i].line.lineno;
+		chips = &sensors_config_chips[i].chips;
+		for (j = 0; j < chips->fits_count; j++) {
+			/* We can only substitute if a specific bus number
+			   is given. */
+			if (chips->fits[j].bus.nr == SENSORS_BUS_NR_ANY)
+				continue;
+
+			err = sensors_substitute_chip(&chips->fits[j],
+						      filename, lineno);
+			if (err)
+				res = err;
+		}
+	}
+	sensors_config_chips_subst = sensors_config_chips_count;
+	return res;
+}
diff --git a/tools/gator/daemon/libsensors/data.h b/tools/gator/daemon/libsensors/data.h
new file mode 100644
index 00000000000..4a23eabe141
--- /dev/null
+++ b/tools/gator/daemon/libsensors/data.h
@@ -0,0 +1,184 @@
+/*
+    data.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007, 2009  Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_DATA_H
+#define LIB_SENSORS_DATA_H
+
+#include "sensors.h"
+#include "general.h"
+
+/* This header file contains all kinds of data structures which are used
+   for the representation of the config file data and the sensors
+   data. */
+
+/* Kinds of expression operators recognized */
+typedef enum sensors_operation {
+	sensors_add, sensors_sub, sensors_multiply, sensors_divide,
+	sensors_negate, sensors_exp, sensors_log,
+} sensors_operation;
+
+/* An expression can have several forms */
+typedef enum sensors_expr_kind {
+	sensors_kind_val, sensors_kind_source, sensors_kind_var,
+	sensors_kind_sub
+} sensors_expr_kind;
+
+/* An expression. It is either a floating point value, a variable name,
+   an operation on subexpressions, or the special value 'sub' } */
+struct sensors_expr;
+
+typedef struct sensors_subexpr {
+	sensors_operation op;
+	struct sensors_expr *sub1;
+	struct sensors_expr *sub2;
+} sensors_subexpr;
+
+typedef struct sensors_expr {
+	sensors_expr_kind kind;
+	union {
+		double val;
+		char *var;
+		sensors_subexpr subexpr;
+	} data;
+} sensors_expr;
+
+/* Config file line reference */
+typedef struct sensors_config_line {
+	const char *filename;
+	int lineno;
+} sensors_config_line;
+
+/* Config file label declaration: a feature name, combined with the label
+   value */
+typedef struct sensors_label {
+	char *name;
+	char *value;
+	sensors_config_line line;
+} sensors_label;
+
+/* Config file set declaration: a subfeature name, combined with an
+   expression */
+typedef struct sensors_set {
+	char *name;
+	sensors_expr *value;
+	sensors_config_line line;
+} sensors_set;
+
+/* Config file compute declaration: a feature name, combined with two
+   expressions */
+typedef struct sensors_compute {
+	char *name;
+	sensors_expr *from_proc;
+	sensors_expr *to_proc;
+	sensors_config_line line;
+} sensors_compute;
+
+/* Config file ignore declaration: a feature name */
+typedef struct sensors_ignore {
+	char *name;
+	sensors_config_line line;
+} sensors_ignore;
+
+/* A list of chip names, used to represent a config file chips declaration */
+typedef struct sensors_chip_name_list {
+	sensors_chip_name *fits;
+	int fits_count;
+	int fits_max;
+} sensors_chip_name_list;
+
+/* A config file chip block */
+typedef struct sensors_chip {
+	sensors_chip_name_list chips;
+	sensors_label *labels;
+	int labels_count;
+	int labels_max;
+	sensors_set *sets;
+	int sets_count;
+	int sets_max;
+	sensors_compute *computes;
+	int computes_count;
+	int computes_max;
+	sensors_ignore *ignores;
+	int ignores_count;
+	int ignores_max;
+	sensors_config_line line;
+} sensors_chip;
+
+/* Config file bus declaration: the bus type and number, combined with adapter
+   name */
+typedef struct sensors_bus {
+	char *adapter;
+	sensors_bus_id bus;
+	sensors_config_line line;
+} sensors_bus;
+
+/* Internal data about all features and subfeatures of a chip */
+typedef struct sensors_chip_features {
+	struct sensors_chip_name chip;
+	struct sensors_feature *feature;
+	struct sensors_subfeature *subfeature;
+	int feature_count;
+	int subfeature_count;
+} sensors_chip_features;
+
+extern char **sensors_config_files;
+extern int sensors_config_files_count;
+extern int sensors_config_files_max;
+
+#define sensors_add_config_files(el) sensors_add_array_el( \
+	(el), &sensors_config_files, &sensors_config_files_count, \
+	&sensors_config_files_max, sizeof(char *))
+
+extern sensors_chip *sensors_config_chips;
+extern int sensors_config_chips_count;
+extern int sensors_config_chips_subst;
+extern int sensors_config_chips_max;
+
+extern sensors_bus *sensors_config_busses;
+extern int sensors_config_busses_count;
+extern int sensors_config_busses_max;
+
+extern sensors_chip_features *sensors_proc_chips;
+extern int sensors_proc_chips_count;
+extern int sensors_proc_chips_max;
+
+#define sensors_add_proc_chips(el) sensors_add_array_el( \
+	(el), &sensors_proc_chips, &sensors_proc_chips_count,\
+	&sensors_proc_chips_max, sizeof(struct sensors_chip_features))
+
+extern sensors_bus *sensors_proc_bus;
+extern int sensors_proc_bus_count;
+extern int sensors_proc_bus_max;
+
+#define sensors_add_proc_bus(el) sensors_add_array_el( \
+	(el), &sensors_proc_bus, &sensors_proc_bus_count,\
+	&sensors_proc_bus_max, sizeof(struct sensors_bus))
+
+/* Substitute configuration bus numbers with real-world bus numbers
+   in the chips lists */
+int sensors_substitute_busses(void);
+
+
+/* Parse a bus id into its components. Returns 0 on success, a value from
+   error.h on failure. */
+int sensors_parse_bus_id(const char *name, sensors_bus_id *bus);
+
+#endif /* def LIB_SENSORS_DATA_H */
diff --git a/tools/gator/daemon/libsensors/error.c b/tools/gator/daemon/libsensors/error.c
new file mode 100644
index 00000000000..55bde81295f
--- /dev/null
+++ b/tools/gator/daemon/libsensors/error.c
@@ -0,0 +1,92 @@
+/*
+    error.c - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007-2009   Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#include <stdlib.h>
+#include <stdio.h>
+#include "error.h"
+#include "general.h"
+
+static void sensors_default_parse_error(const char *err, int lineno);
+static void sensors_default_parse_error_wfn(const char *err,
+					    const char *filename, int lineno);
+static void sensors_default_fatal_error(const char *proc, const char *err);
+
+void (*sensors_parse_error) (const char *err, int lineno) =
+						sensors_default_parse_error;
+void (*sensors_parse_error_wfn) (const char *err, const char *filename,
+				 int lineno) = sensors_default_parse_error_wfn;
+void (*sensors_fatal_error) (const char *proc, const char *err) =
+						sensors_default_fatal_error;
+
+static const char *errorlist[] = {
+	/* Invalid error code    */ "Unknown error",
+	/* SENSORS_ERR_WILDCARDS */ "Wildcard found in chip name",
+	/* SENSORS_ERR_NO_ENTRY  */ "No such subfeature known",
+	/* SENSORS_ERR_ACCESS_R  */ "Can't read",
+	/* SENSORS_ERR_KERNEL    */ "Kernel interface error",
+	/* SENSORS_ERR_DIV_ZERO  */ "Divide by zero",
+	/* SENSORS_ERR_CHIP_NAME */ "Can't parse chip name",
+	/* SENSORS_ERR_BUS_NAME  */ "Can't parse bus name",
+	/* SENSORS_ERR_PARSE     */ "General parse error",
+	/* SENSORS_ERR_ACCESS_W  */ "Can't write",
+	/* SENSORS_ERR_IO        */ "I/O error",
+	/* SENSORS_ERR_RECURSION */ "Evaluation recurses too deep",
+};
+
+const char *sensors_strerror(int errnum)
+{
+	if (errnum < 0)
+		errnum = -errnum;
+	if (errnum >= ARRAY_SIZE(errorlist))
+		errnum = 0;
+	return errorlist[errnum];
+}
+
+void sensors_default_parse_error(const char *err, int lineno)
+{
+	if (lineno)
+		fprintf(stderr, "Error: Line %d: %s\n", lineno, err);
+	else
+		fprintf(stderr, "Error: %s\n", err);
+}
+
+void sensors_default_parse_error_wfn(const char *err,
+				     const char *filename, int lineno)
+{
+	/* If application provided a custom parse error reporting function
+	   but not the variant with the filename, fall back to the original
+	   variant without the filename, for backwards compatibility. */
+	if (sensors_parse_error != sensors_default_parse_error ||
+	    !filename)
+		return sensors_parse_error(err, lineno);
+
+	if (lineno)
+		fprintf(stderr, "Error: File %s, line %d: %s\n", filename,
+			lineno, err);
+	else
+		fprintf(stderr, "Error: File %s: %s\n", filename, err);
+}
+
+void sensors_default_fatal_error(const char *proc, const char *err)
+{
+	fprintf(stderr, "Fatal error in `%s': %s\n", proc, err);
+	exit(1);
+}
diff --git a/tools/gator/daemon/libsensors/error.h b/tools/gator/daemon/libsensors/error.h
new file mode 100644
index 00000000000..37cdc956151
--- /dev/null
+++ b/tools/gator/daemon/libsensors/error.h
@@ -0,0 +1,74 @@
+/*
+    error.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007-2009   Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_ERROR_H
+#define LIB_SENSORS_ERROR_H
+
+#define SENSORS_ERR_WILDCARDS	1 /* Wildcard found in chip name */
+#define SENSORS_ERR_NO_ENTRY	2 /* No such subfeature known */
+#define SENSORS_ERR_ACCESS_R	3 /* Can't read */
+#define SENSORS_ERR_KERNEL	4 /* Kernel interface error */
+#define SENSORS_ERR_DIV_ZERO	5 /* Divide by zero */
+#define SENSORS_ERR_CHIP_NAME	6 /* Can't parse chip name */
+#define SENSORS_ERR_BUS_NAME	7 /* Can't parse bus name */
+#define SENSORS_ERR_PARSE	8 /* General parse error */
+#define SENSORS_ERR_ACCESS_W	9 /* Can't write */
+#define SENSORS_ERR_IO		10 /* I/O error */
+#define SENSORS_ERR_RECURSION	11 /* Evaluation recurses too deep */
+
+#ifdef __cplusplus
+extern "C" {
+#endif /* __cplusplus */
+
+
+/* This function returns a pointer to a string which describes the error.
+   errnum may be negative (the corresponding positive error is returned).
+   You may not modify the result! */
+const char *sensors_strerror(int errnum);
+
+/* These functions are called when a parse error is detected. Give them new
+   values, and your own functions are called instead of the default (which
+   print to stderr). These functions may terminate the program, but they
+   usually output an error and return. The first function is the original
+   one, the second one was added later when support for multiple
+   configuration files was added.
+   The library code now only calls the second function. However, for
+   backwards compatibility, if an application provides a custom handling
+   function for the first function but not the second, then all parse
+   errors will be reported using the first function (that is, the filename
+   is never reported.)
+   Note that filename can be NULL (if filename isn't known) and lineno
+   can be 0 (if the error occurs before the actual parsing starts.) */
+extern void (*sensors_parse_error) (const char *err, int lineno);
+extern void (*sensors_parse_error_wfn) (const char *err,
+					const char *filename, int lineno);
+
+/* This function is called when an immediately fatal error (like no
+   memory left) is detected. Give it a new value, and your own function
+   is called instead of the default (which prints to stderr and ends
+   the program). Never let it return! */
+extern void (*sensors_fatal_error) (const char *proc, const char *err);
+
+#ifdef __cplusplus
+}
+#endif /* __cplusplus */
+
+#endif /* def LIB_SENSORS_ERROR_H */
diff --git a/tools/gator/daemon/libsensors/general.c b/tools/gator/daemon/libsensors/general.c
new file mode 100644
index 00000000000..f237e3b59c2
--- /dev/null
+++ b/tools/gator/daemon/libsensors/general.c
@@ -0,0 +1,85 @@
+/*
+    general.c - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#include "error.h"
+#include "general.h"
+#include <errno.h>
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+
+
+#define A_BUNCH 16
+
+void sensors_malloc_array(void *list, int *num_el, int *max_el, int el_size)
+{
+	void **my_list = (void **)list;
+
+	*my_list = malloc(el_size*A_BUNCH);
+	if (! *my_list)
+		sensors_fatal_error(__func__, "Allocating new elements");
+	*max_el = A_BUNCH;
+	*num_el = 0;
+}
+
+void sensors_free_array(void *list, int *num_el, int *max_el)
+{
+	void **my_list = (void **)list;
+
+	free(*my_list);
+	*my_list = NULL;
+	*num_el = 0;
+	*max_el = 0;
+}
+
+void sensors_add_array_el(const void *el, void *list, int *num_el,
+			  int *max_el, int el_size)
+{
+	int new_max_el;
+	void **my_list = (void *)list;
+	if (*num_el + 1 > *max_el) {
+		new_max_el = *max_el + A_BUNCH;
+		*my_list = realloc(*my_list, new_max_el * el_size);
+		if (! *my_list)
+			sensors_fatal_error(__func__,
+					    "Allocating new elements");
+		*max_el = new_max_el;
+	}
+	memcpy(((char *) *my_list) + *num_el * el_size, el, el_size);
+	(*num_el) ++;
+}
+
+void sensors_add_array_els(const void *els, int nr_els, void *list,
+			   int *num_el, int *max_el, int el_size)
+{
+	int new_max_el;
+	void **my_list = (void *)list;
+	if (*num_el + nr_els > *max_el) {
+		new_max_el = (*max_el + nr_els + A_BUNCH);
+		new_max_el -= new_max_el % A_BUNCH;
+		*my_list = realloc(*my_list, new_max_el * el_size);
+		if (! *my_list)
+			sensors_fatal_error(__func__,
+					    "Allocating new elements");
+		*max_el = new_max_el;
+	}
+	memcpy(((char *)*my_list) + *num_el * el_size, els, el_size * nr_els);
+	*num_el += nr_els;
+}
diff --git a/tools/gator/daemon/libsensors/general.h b/tools/gator/daemon/libsensors/general.h
new file mode 100644
index 00000000000..a3971e02e1b
--- /dev/null
+++ b/tools/gator/daemon/libsensors/general.h
@@ -0,0 +1,39 @@
+/*
+    general.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_GENERAL
+#define LIB_SENSORS_GENERAL
+
+/* These are general purpose functions. They allow you to use variable-
+   length arrays, which are extended automatically. A distinction is
+   made between the current number of elements and the maximum number.
+   You can only add elements at the end. Primitive, but very useful
+   for internal use. */
+void sensors_malloc_array(void *list, int *num_el, int *max_el,
+			  int el_size);
+void sensors_free_array(void *list, int *num_el, int *max_el);
+void sensors_add_array_el(const void *el, void *list, int *num_el,
+			  int *max_el, int el_size);
+void sensors_add_array_els(const void *els, int nr_els, void *list,
+			   int *num_el, int *max_el, int el_size);
+
+#define ARRAY_SIZE(arr)	(int)(sizeof(arr) / sizeof((arr)[0]))
+
+#endif /* LIB_SENSORS_GENERAL */
diff --git a/tools/gator/daemon/libsensors/init.c b/tools/gator/daemon/libsensors/init.c
new file mode 100644
index 00000000000..558046e76c2
--- /dev/null
+++ b/tools/gator/daemon/libsensors/init.c
@@ -0,0 +1,341 @@
+/*
+    init.c - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007, 2009  Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to cast alphasort to supress a warning as it's prototype is different on android. ***/
+
+/* Needed for scandir() and alphasort() */
+#define _BSD_SOURCE
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <locale.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <dirent.h>
+#include <unistd.h>
+#include "sensors.h"
+#include "data.h"
+#include "error.h"
+#include "access.h"
+#include "conf.h"
+#include "sysfs.h"
+#include "scanner.h"
+#include "init.h"
+
+#define DEFAULT_CONFIG_FILE	ETCDIR "/sensors3.conf"
+#define ALT_CONFIG_FILE		ETCDIR "/sensors.conf"
+#define DEFAULT_CONFIG_DIR	ETCDIR "/sensors.d"
+
+/* Wrapper around sensors_yyparse(), which clears the locale so that
+   the decimal numbers are always parsed properly. */
+static int sensors_parse(void)
+{
+	int res;
+	char *locale;
+
+	/* Remember the current locale and clear it */
+	locale = setlocale(LC_ALL, NULL);
+	if (locale) {
+		locale = strdup(locale);
+		if (!locale)
+			sensors_fatal_error(__func__, "Out of memory");
+
+		setlocale(LC_ALL, "C");
+	}
+
+	res = sensors_yyparse();
+
+	/* Restore the old locale */
+	if (locale) {
+		setlocale(LC_ALL, locale);
+		free(locale);
+	}
+
+	return res;
+}
+
+static void free_bus(sensors_bus *bus)
+{
+	free(bus->adapter);
+}
+
+static void free_config_busses(void)
+{
+	int i;
+
+	for (i = 0; i < sensors_config_busses_count; i++)
+		free_bus(&sensors_config_busses[i]);
+	free(sensors_config_busses);
+	sensors_config_busses = NULL;
+	sensors_config_busses_count = sensors_config_busses_max = 0;
+}
+
+static int parse_config(FILE *input, const char *name)
+{
+	int err;
+	char *name_copy;
+
+	if (name) {
+		/* Record configuration file name for error reporting */
+		name_copy = strdup(name);
+		if (!name_copy)
+			sensors_fatal_error(__func__, "Out of memory");
+		sensors_add_config_files(&name_copy);
+	} else
+		name_copy = NULL;
+
+	if (sensors_scanner_init(input, name_copy)) {
+		err = -SENSORS_ERR_PARSE;
+		goto exit_cleanup;
+	}
+	err = sensors_parse();
+	sensors_scanner_exit();
+	if (err) {
+		err = -SENSORS_ERR_PARSE;
+		goto exit_cleanup;
+	}
+
+	err = sensors_substitute_busses();
+
+exit_cleanup:
+	free_config_busses();
+	return err;
+}
+
+static int config_file_filter(const struct dirent *entry)
+{
+	return entry->d_name[0] != '.';		/* Skip hidden files */
+}
+
+static int add_config_from_dir(const char *dir)
+{
+	int count, res, i;
+	struct dirent **namelist;
+
+	count = scandir(dir, &namelist, config_file_filter, (int (*)(const struct dirent **, const struct dirent **))alphasort);
+	if (count < 0) {
+		/* Do not return an error if directory does not exist */
+		if (errno == ENOENT)
+			return 0;
+		
+		sensors_parse_error_wfn(strerror(errno), NULL, 0);
+		return -SENSORS_ERR_PARSE;
+	}
+
+	for (res = 0, i = 0; !res && i < count; i++) {
+		int len;
+		char path[PATH_MAX];
+		FILE *input;
+		struct stat st;
+
+		len = snprintf(path, sizeof(path), "%s/%s", dir,
+			       namelist[i]->d_name);
+		if (len < 0 || len >= (int)sizeof(path)) {
+			res = -SENSORS_ERR_PARSE;
+			continue;
+		}
+
+		/* Only accept regular files */
+		if (stat(path, &st) < 0 || !S_ISREG(st.st_mode))
+			continue;
+
+		input = fopen(path, "r");
+		if (input) {
+			res = parse_config(input, path);
+			fclose(input);
+		} else {
+			res = -SENSORS_ERR_PARSE;
+			sensors_parse_error_wfn(strerror(errno), path, 0);
+		}
+	}
+
+	/* Free memory allocated by scandir() */
+	for (i = 0; i < count; i++)
+		free(namelist[i]);
+	free(namelist);
+
+	return res;
+}
+
+int sensors_init(FILE *input)
+{
+	int res;
+
+	if (!sensors_init_sysfs())
+		return -SENSORS_ERR_KERNEL;
+	if ((res = sensors_read_sysfs_bus()) ||
+	    (res = sensors_read_sysfs_chips()))
+		goto exit_cleanup;
+
+	if (input) {
+		res = parse_config(input, NULL);
+		if (res)
+			goto exit_cleanup;
+	} else {
+		const char* name;
+
+		/* No configuration provided, use default */
+		input = fopen(name = DEFAULT_CONFIG_FILE, "r");
+		if (!input && errno == ENOENT)
+			input = fopen(name = ALT_CONFIG_FILE, "r");
+		if (input) {
+			res = parse_config(input, name);
+			fclose(input);
+			if (res)
+				goto exit_cleanup;
+
+		} else if (errno != ENOENT) {
+			sensors_parse_error_wfn(strerror(errno), name, 0);
+			res = -SENSORS_ERR_PARSE;
+			goto exit_cleanup;
+		}
+
+		/* Also check for files in default directory */
+		res = add_config_from_dir(DEFAULT_CONFIG_DIR);
+		if (res)
+			goto exit_cleanup;
+	}
+
+	return 0;
+
+exit_cleanup:
+	sensors_cleanup();
+	return res;
+}
+
+static void free_chip_name(sensors_chip_name *name)
+{
+	free(name->prefix);
+	free(name->path);
+}
+
+static void free_chip_features(sensors_chip_features *features)
+{
+	int i;
+
+	for (i = 0; i < features->subfeature_count; i++)
+		free(features->subfeature[i].name);
+	free(features->subfeature);
+	for (i = 0; i < features->feature_count; i++)
+		free(features->feature[i].name);
+	free(features->feature);
+}
+
+static void free_label(sensors_label *label)
+{
+	free(label->name);
+	free(label->value);
+}
+
+void sensors_free_expr(sensors_expr *expr)
+{
+	if (expr->kind == sensors_kind_var)
+		free(expr->data.var);
+	else if (expr->kind == sensors_kind_sub) {
+		if (expr->data.subexpr.sub1)
+			sensors_free_expr(expr->data.subexpr.sub1);
+		if (expr->data.subexpr.sub2)
+			sensors_free_expr(expr->data.subexpr.sub2);
+	}
+	free(expr);
+}
+
+static void free_set(sensors_set *set)
+{
+	free(set->name);
+	sensors_free_expr(set->value);
+}
+
+static void free_compute(sensors_compute *compute)
+{
+	free(compute->name);
+	sensors_free_expr(compute->from_proc);
+	sensors_free_expr(compute->to_proc);
+}
+
+static void free_ignore(sensors_ignore *ignore)
+{
+	free(ignore->name);
+}
+
+static void free_chip(sensors_chip *chip)
+{
+	int i;
+
+	for (i = 0; i < chip->chips.fits_count; i++)
+		free_chip_name(&chip->chips.fits[i]);
+	free(chip->chips.fits);
+	chip->chips.fits_count = chip->chips.fits_max = 0;
+
+	for (i = 0; i < chip->labels_count; i++)
+		free_label(&chip->labels[i]);
+	free(chip->labels);
+	chip->labels_count = chip->labels_max = 0;
+
+	for (i = 0; i < chip->sets_count; i++)
+		free_set(&chip->sets[i]);
+	free(chip->sets);
+	chip->sets_count = chip->sets_max = 0;
+
+	for (i = 0; i < chip->computes_count; i++)
+		free_compute(&chip->computes[i]);
+	free(chip->computes);
+	chip->computes_count = chip->computes_max = 0;
+
+	for (i = 0; i < chip->ignores_count; i++)
+		free_ignore(&chip->ignores[i]);
+	free(chip->ignores);
+	chip->ignores_count = chip->ignores_max = 0;
+}
+
+void sensors_cleanup(void)
+{
+	int i;
+
+	for (i = 0; i < sensors_proc_chips_count; i++) {
+		free_chip_name(&sensors_proc_chips[i].chip);
+		free_chip_features(&sensors_proc_chips[i]);
+	}
+	free(sensors_proc_chips);
+	sensors_proc_chips = NULL;
+	sensors_proc_chips_count = sensors_proc_chips_max = 0;
+
+	for (i = 0; i < sensors_config_chips_count; i++)
+		free_chip(&sensors_config_chips[i]);
+	free(sensors_config_chips);
+	sensors_config_chips = NULL;
+	sensors_config_chips_count = sensors_config_chips_max = 0;
+	sensors_config_chips_subst = 0;
+
+	for (i = 0; i < sensors_proc_bus_count; i++)
+		free_bus(&sensors_proc_bus[i]);
+	free(sensors_proc_bus);
+	sensors_proc_bus = NULL;
+	sensors_proc_bus_count = sensors_proc_bus_max = 0;
+
+	for (i = 0; i < sensors_config_files_count; i++)
+		free(sensors_config_files[i]);
+	free(sensors_config_files);
+	sensors_config_files = NULL;
+	sensors_config_files_count = sensors_config_files_max = 0;
+}
diff --git a/tools/gator/daemon/libsensors/init.h b/tools/gator/daemon/libsensors/init.h
new file mode 100644
index 00000000000..47006a62db6
--- /dev/null
+++ b/tools/gator/daemon/libsensors/init.h
@@ -0,0 +1,28 @@
+/*
+    init.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (C) 2007  Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_INIT_H
+#define LIB_SENSORS_INIT_H
+
+#include "data.h"
+
+void sensors_free_expr(sensors_expr *expr);
+
+#endif /* def LIB_SENSORS_INIT_H */
diff --git a/tools/gator/daemon/libsensors/scanner.h b/tools/gator/daemon/libsensors/scanner.h
new file mode 100644
index 00000000000..4c415167de5
--- /dev/null
+++ b/tools/gator/daemon/libsensors/scanner.h
@@ -0,0 +1,32 @@
+/*
+    scanner.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 2006 Mark M. Hoffman <mhoffman@lightlink.com>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to fix input defined but not used warning from conf-lex.c. ***/
+
+#ifndef LIB_SENSORS_SCANNER_H
+#define LIB_SENSORS_SCANNER_H
+
+int sensors_scanner_init(FILE *input, const char *filename);
+void sensors_scanner_exit(void);
+
+#define YY_NO_INPUT
+
+#endif
+
diff --git a/tools/gator/daemon/libsensors/sensors.h b/tools/gator/daemon/libsensors/sensors.h
new file mode 100644
index 00000000000..7874d028dc8
--- /dev/null
+++ b/tools/gator/daemon/libsensors/sensors.h
@@ -0,0 +1,311 @@
+/*
+    sensors.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007, 2010  Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to read non-scaled values. ***/
+
+#ifndef LIB_SENSORS_SENSORS_H
+#define LIB_SENSORS_SENSORS_H
+
+#include <stdio.h>
+#include <limits.h>
+
+/* Publicly accessible library functions */
+
+/* libsensors API version define, first digit is the major version (changed
+   when the API + ABI breaks), the third digit is incremented to track small
+   API additions like new flags / enum values. The second digit is for tracking
+   larger additions like new methods. */
+#define SENSORS_API_VERSION		0x432
+
+#define SENSORS_CHIP_NAME_PREFIX_ANY	NULL
+#define SENSORS_CHIP_NAME_ADDR_ANY	(-1)
+
+#define SENSORS_BUS_TYPE_ANY		(-1)
+#define SENSORS_BUS_TYPE_I2C		0
+#define SENSORS_BUS_TYPE_ISA		1
+#define SENSORS_BUS_TYPE_PCI		2
+#define SENSORS_BUS_TYPE_SPI		3
+#define SENSORS_BUS_TYPE_VIRTUAL	4
+#define SENSORS_BUS_TYPE_ACPI		5
+#define SENSORS_BUS_TYPE_HID		6
+#define SENSORS_BUS_NR_ANY		(-1)
+#define SENSORS_BUS_NR_IGNORE		(-2)
+
+#ifdef __cplusplus
+extern "C" {
+#endif /* __cplusplus */
+
+extern const char *libsensors_version;
+
+extern int sensors_sysfs_no_scaling;
+
+typedef struct sensors_bus_id {
+	short type;
+	short nr;
+} sensors_bus_id;
+
+/* A chip name is encoded in this structure */
+typedef struct sensors_chip_name {
+	char *prefix;
+	sensors_bus_id bus;
+	int addr;
+	char *path;
+} sensors_chip_name;
+
+/* Load the configuration file and the detected chips list. If this
+   returns a value unequal to zero, you are in trouble; you can not
+   assume anything will be initialized properly. If you want to
+   reload the configuration file, call sensors_cleanup() below before
+   calling sensors_init() again. */
+int sensors_init(FILE *input);
+
+/* Clean-up function: You can't access anything after
+   this, until the next sensors_init() call! */
+void sensors_cleanup(void);
+
+/* Parse a chip name to the internal representation. Return 0 on success, <0
+   on error. */
+int sensors_parse_chip_name(const char *orig_name, sensors_chip_name *res);
+
+/* Free memory allocated for the internal representation of a chip name. */
+void sensors_free_chip_name(sensors_chip_name *chip);
+
+/* Print a chip name from its internal representation. Note that chip should
+   not contain wildcard values! Return the number of characters printed on
+   success (same as snprintf), <0 on error. */
+int sensors_snprintf_chip_name(char *str, size_t size,
+			       const sensors_chip_name *chip);
+
+/* This function returns the adapter name of a bus,
+   as used within the sensors_chip_name structure. If it could not be found,
+   it returns NULL */
+const char *sensors_get_adapter_name(const sensors_bus_id *bus);
+
+typedef struct sensors_feature sensors_feature;
+
+/* Look up the label for a given feature. Note that chip should not
+   contain wildcard values! The returned string is newly allocated (free it
+   yourself). On failure, NULL is returned.
+   If no label exists for this feature, its name is returned itself. */
+char *sensors_get_label(const sensors_chip_name *name,
+			const sensors_feature *feature);
+
+/* Read the value of a subfeature of a certain chip. Note that chip should not
+   contain wildcard values! This function will return 0 on success, and <0
+   on failure.  */
+int sensors_get_value(const sensors_chip_name *name, int subfeat_nr,
+		      double *value);
+
+/* Set the value of a subfeature of a certain chip. Note that chip should not
+   contain wildcard values! This function will return 0 on success, and <0
+   on failure. */
+int sensors_set_value(const sensors_chip_name *name, int subfeat_nr,
+		      double value);
+
+/* Execute all set statements for this particular chip. The chip may contain
+   wildcards!  This function will return 0 on success, and <0 on failure. */
+int sensors_do_chip_sets(const sensors_chip_name *name);
+
+/* This function returns all detected chips that match a given chip name,
+   one by one. If no chip name is provided, all detected chips are returned.
+   To start at the beginning of the list, use 0 for nr; NULL is returned if
+   we are at the end of the list. Do not try to change these chip names, as
+   they point to internal structures! */
+const sensors_chip_name *sensors_get_detected_chips(const sensors_chip_name
+						    *match, int *nr);
+
+/* These defines are used in the flags field of sensors_subfeature */
+#define SENSORS_MODE_R			1
+#define SENSORS_MODE_W			2
+#define SENSORS_COMPUTE_MAPPING		4
+
+typedef enum sensors_feature_type {
+	SENSORS_FEATURE_IN		= 0x00,
+	SENSORS_FEATURE_FAN		= 0x01,
+	SENSORS_FEATURE_TEMP		= 0x02,
+	SENSORS_FEATURE_POWER		= 0x03,
+	SENSORS_FEATURE_ENERGY		= 0x04,
+	SENSORS_FEATURE_CURR		= 0x05,
+	SENSORS_FEATURE_HUMIDITY	= 0x06,
+	SENSORS_FEATURE_MAX_MAIN,
+	SENSORS_FEATURE_VID		= 0x10,
+	SENSORS_FEATURE_INTRUSION	= 0x11,
+	SENSORS_FEATURE_MAX_OTHER,
+	SENSORS_FEATURE_BEEP_ENABLE	= 0x18,
+	SENSORS_FEATURE_UNKNOWN		= INT_MAX,
+} sensors_feature_type;
+
+/* All the sensor types (in, fan, temp, vid) are a multiple of 0x100 apart,
+   and sensor subfeatures which have no compute mapping have bit 7 set. */
+typedef enum sensors_subfeature_type {
+	SENSORS_SUBFEATURE_IN_INPUT = SENSORS_FEATURE_IN << 8,
+	SENSORS_SUBFEATURE_IN_MIN,
+	SENSORS_SUBFEATURE_IN_MAX,
+	SENSORS_SUBFEATURE_IN_LCRIT,
+	SENSORS_SUBFEATURE_IN_CRIT,
+	SENSORS_SUBFEATURE_IN_AVERAGE,
+	SENSORS_SUBFEATURE_IN_LOWEST,
+	SENSORS_SUBFEATURE_IN_HIGHEST,
+	SENSORS_SUBFEATURE_IN_ALARM = (SENSORS_FEATURE_IN << 8) | 0x80,
+	SENSORS_SUBFEATURE_IN_MIN_ALARM,
+	SENSORS_SUBFEATURE_IN_MAX_ALARM,
+	SENSORS_SUBFEATURE_IN_BEEP,
+	SENSORS_SUBFEATURE_IN_LCRIT_ALARM,
+	SENSORS_SUBFEATURE_IN_CRIT_ALARM,
+
+	SENSORS_SUBFEATURE_FAN_INPUT = SENSORS_FEATURE_FAN << 8,
+	SENSORS_SUBFEATURE_FAN_MIN,
+	SENSORS_SUBFEATURE_FAN_MAX,
+	SENSORS_SUBFEATURE_FAN_ALARM = (SENSORS_FEATURE_FAN << 8) | 0x80,
+	SENSORS_SUBFEATURE_FAN_FAULT,
+	SENSORS_SUBFEATURE_FAN_DIV,
+	SENSORS_SUBFEATURE_FAN_BEEP,
+	SENSORS_SUBFEATURE_FAN_PULSES,
+	SENSORS_SUBFEATURE_FAN_MIN_ALARM,
+	SENSORS_SUBFEATURE_FAN_MAX_ALARM,
+
+	SENSORS_SUBFEATURE_TEMP_INPUT = SENSORS_FEATURE_TEMP << 8,
+	SENSORS_SUBFEATURE_TEMP_MAX,
+	SENSORS_SUBFEATURE_TEMP_MAX_HYST,
+	SENSORS_SUBFEATURE_TEMP_MIN,
+	SENSORS_SUBFEATURE_TEMP_CRIT,
+	SENSORS_SUBFEATURE_TEMP_CRIT_HYST,
+	SENSORS_SUBFEATURE_TEMP_LCRIT,
+	SENSORS_SUBFEATURE_TEMP_EMERGENCY,
+	SENSORS_SUBFEATURE_TEMP_EMERGENCY_HYST,
+	SENSORS_SUBFEATURE_TEMP_LOWEST,
+	SENSORS_SUBFEATURE_TEMP_HIGHEST,
+	SENSORS_SUBFEATURE_TEMP_ALARM = (SENSORS_FEATURE_TEMP << 8) | 0x80,
+	SENSORS_SUBFEATURE_TEMP_MAX_ALARM,
+	SENSORS_SUBFEATURE_TEMP_MIN_ALARM,
+	SENSORS_SUBFEATURE_TEMP_CRIT_ALARM,
+	SENSORS_SUBFEATURE_TEMP_FAULT,
+	SENSORS_SUBFEATURE_TEMP_TYPE,
+	SENSORS_SUBFEATURE_TEMP_OFFSET,
+	SENSORS_SUBFEATURE_TEMP_BEEP,
+	SENSORS_SUBFEATURE_TEMP_EMERGENCY_ALARM,
+	SENSORS_SUBFEATURE_TEMP_LCRIT_ALARM,
+
+	SENSORS_SUBFEATURE_POWER_AVERAGE = SENSORS_FEATURE_POWER << 8,
+	SENSORS_SUBFEATURE_POWER_AVERAGE_HIGHEST,
+	SENSORS_SUBFEATURE_POWER_AVERAGE_LOWEST,
+	SENSORS_SUBFEATURE_POWER_INPUT,
+	SENSORS_SUBFEATURE_POWER_INPUT_HIGHEST,
+	SENSORS_SUBFEATURE_POWER_INPUT_LOWEST,
+	SENSORS_SUBFEATURE_POWER_CAP,
+	SENSORS_SUBFEATURE_POWER_CAP_HYST,
+	SENSORS_SUBFEATURE_POWER_MAX,
+	SENSORS_SUBFEATURE_POWER_CRIT,
+	SENSORS_SUBFEATURE_POWER_AVERAGE_INTERVAL = (SENSORS_FEATURE_POWER << 8) | 0x80,
+	SENSORS_SUBFEATURE_POWER_ALARM,
+	SENSORS_SUBFEATURE_POWER_CAP_ALARM,
+	SENSORS_SUBFEATURE_POWER_MAX_ALARM,
+	SENSORS_SUBFEATURE_POWER_CRIT_ALARM,
+
+	SENSORS_SUBFEATURE_ENERGY_INPUT = SENSORS_FEATURE_ENERGY << 8,
+
+	SENSORS_SUBFEATURE_CURR_INPUT = SENSORS_FEATURE_CURR << 8,
+	SENSORS_SUBFEATURE_CURR_MIN,
+	SENSORS_SUBFEATURE_CURR_MAX,
+	SENSORS_SUBFEATURE_CURR_LCRIT,
+	SENSORS_SUBFEATURE_CURR_CRIT,
+	SENSORS_SUBFEATURE_CURR_AVERAGE,
+	SENSORS_SUBFEATURE_CURR_LOWEST,
+	SENSORS_SUBFEATURE_CURR_HIGHEST,
+	SENSORS_SUBFEATURE_CURR_ALARM = (SENSORS_FEATURE_CURR << 8) | 0x80,
+	SENSORS_SUBFEATURE_CURR_MIN_ALARM,
+	SENSORS_SUBFEATURE_CURR_MAX_ALARM,
+	SENSORS_SUBFEATURE_CURR_BEEP,
+	SENSORS_SUBFEATURE_CURR_LCRIT_ALARM,
+	SENSORS_SUBFEATURE_CURR_CRIT_ALARM,
+
+	SENSORS_SUBFEATURE_HUMIDITY_INPUT = SENSORS_FEATURE_HUMIDITY << 8,
+
+	SENSORS_SUBFEATURE_VID = SENSORS_FEATURE_VID << 8,
+
+	SENSORS_SUBFEATURE_INTRUSION_ALARM = SENSORS_FEATURE_INTRUSION << 8,
+	SENSORS_SUBFEATURE_INTRUSION_BEEP,
+
+	SENSORS_SUBFEATURE_BEEP_ENABLE = SENSORS_FEATURE_BEEP_ENABLE << 8,
+
+	SENSORS_SUBFEATURE_UNKNOWN = INT_MAX,
+} sensors_subfeature_type;
+
+/* Data about a single chip feature (or category leader) */
+struct sensors_feature {
+	char *name;
+	int number;
+	sensors_feature_type type;
+	/* Members below are for libsensors internal use only */
+	int first_subfeature;
+	int padding1;
+};
+
+/* Data about a single chip subfeature:
+   name is the string name used to refer to this subfeature (in config files)
+   number is the internal subfeature number, used in many functions to refer
+     to this subfeature
+   type is the subfeature type
+   mapping is the number of a main feature this subfeature belongs to
+     (for example subfeatures fan1_input, fan1_min, fan1_div and fan1_alarm
+      are mapped to main feature fan1)
+   flags is a bitfield, its value is a combination of SENSORS_MODE_R (readable),
+     SENSORS_MODE_W (writable) and SENSORS_COMPUTE_MAPPING (affected by the
+     computation rules of the main feature) */
+typedef struct sensors_subfeature {
+	char *name;
+	int number;
+	sensors_subfeature_type type;
+	int mapping;
+	unsigned int flags;
+} sensors_subfeature;
+
+/* This returns all main features of a specific chip. nr is an internally
+   used variable. Set it to zero to start at the begin of the list. If no
+   more features are found NULL is returned.
+   Do not try to change the returned structure; you will corrupt internal
+   data structures. */
+const sensors_feature *
+sensors_get_features(const sensors_chip_name *name, int *nr);
+
+/* This returns all subfeatures of a given main feature. nr is an internally
+   used variable. Set it to zero to start at the begin of the list. If no
+   more features are found NULL is returned.
+   Do not try to change the returned structure; you will corrupt internal
+   data structures. */
+const sensors_subfeature *
+sensors_get_all_subfeatures(const sensors_chip_name *name,
+			    const sensors_feature *feature, int *nr);
+
+/* This returns the subfeature of the given type for a given main feature,
+   if it exists, NULL otherwise.
+   Do not try to change the returned structure; you will corrupt internal
+   data structures. */
+const sensors_subfeature *
+sensors_get_subfeature(const sensors_chip_name *name,
+		       const sensors_feature *feature,
+		       sensors_subfeature_type type);
+
+#ifdef __cplusplus
+}
+#endif /* __cplusplus */
+
+#endif /* def LIB_SENSORS_ERROR_H */
diff --git a/tools/gator/daemon/libsensors/sysfs.c b/tools/gator/daemon/libsensors/sysfs.c
new file mode 100644
index 00000000000..2b494c9975b
--- /dev/null
+++ b/tools/gator/daemon/libsensors/sysfs.c
@@ -0,0 +1,926 @@
+/*
+    sysfs.c - Part of libsensors, a library for reading Linux sensor data
+    Copyright (c) 2005 Mark M. Hoffman <mhoffman@lightlink.com>
+    Copyright (C) 2007-2010 Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to improve performance by substituting calls to fread() with calls to read() and to read non-scaled values. ***/
+
+/* this define needed for strndup() */
+#define _GNU_SOURCE
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/vfs.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdlib.h>
+#include <limits.h>
+#include <errno.h>
+#include <dirent.h>
+#include <fcntl.h>
+#include "data.h"
+#include "error.h"
+#include "access.h"
+#include "general.h"
+#include "sysfs.h"
+
+
+/****************************************************************************/
+
+#define ATTR_MAX	128
+#define SYSFS_MAGIC	0x62656572
+
+int sensors_sysfs_no_scaling;
+
+/*
+ * Read an attribute from sysfs
+ * Returns a pointer to a freshly allocated string; free it yourself.
+ * If the file doesn't exist or can't be read, NULL is returned.
+ */
+static char *sysfs_read_attr(const char *device, const char *attr)
+{
+	char path[NAME_MAX];
+	char buf[ATTR_MAX], *p;
+	FILE *f;
+
+	snprintf(path, NAME_MAX, "%s/%s", device, attr);
+
+	if (!(f = fopen(path, "r")))
+		return NULL;
+	p = fgets(buf, ATTR_MAX, f);
+	fclose(f);
+	if (!p)
+		return NULL;
+
+	/* Last byte is a '\n'; chop that off */
+	p = strndup(buf, strlen(buf) - 1);
+	if (!p)
+		sensors_fatal_error(__func__, "Out of memory");
+	return p;
+}
+
+/*
+ * Call an arbitrary function for each class device of the given class
+ * Returns 0 on success (all calls returned 0), a positive errno for
+ * local errors, or a negative error value if any call fails.
+ */
+static int sysfs_foreach_classdev(const char *class_name,
+				   int (*func)(const char *, const char *))
+{
+	char path[NAME_MAX];
+	int path_off, ret;
+	DIR *dir;
+	struct dirent *ent;
+
+	path_off = snprintf(path, NAME_MAX, "%s/class/%s",
+			    sensors_sysfs_mount, class_name);
+	if (!(dir = opendir(path)))
+		return errno;
+
+	ret = 0;
+	while (!ret && (ent = readdir(dir))) {
+		if (ent->d_name[0] == '.')	/* skip hidden entries */
+			continue;
+
+		snprintf(path + path_off, NAME_MAX - path_off, "/%s",
+			 ent->d_name);
+		ret = func(path, ent->d_name);
+	}
+
+	closedir(dir);
+	return ret;
+}
+
+/*
+ * Call an arbitrary function for each device of the given bus type
+ * Returns 0 on success (all calls returned 0), a positive errno for
+ * local errors, or a negative error value if any call fails.
+ */
+static int sysfs_foreach_busdev(const char *bus_type,
+				 int (*func)(const char *, const char *))
+{
+	char path[NAME_MAX];
+	int path_off, ret;
+	DIR *dir;
+	struct dirent *ent;
+
+	path_off = snprintf(path, NAME_MAX, "%s/bus/%s/devices",
+			    sensors_sysfs_mount, bus_type);
+	if (!(dir = opendir(path)))
+		return errno;
+
+	ret = 0;
+	while (!ret && (ent = readdir(dir))) {
+		if (ent->d_name[0] == '.')	/* skip hidden entries */
+			continue;
+
+		snprintf(path + path_off, NAME_MAX - path_off, "/%s",
+			 ent->d_name);
+		ret = func(path, ent->d_name);
+	}
+
+	closedir(dir);
+	return ret;
+}
+
+/****************************************************************************/
+
+char sensors_sysfs_mount[NAME_MAX];
+
+#define MAX_MAIN_SENSOR_TYPES	(SENSORS_FEATURE_MAX_MAIN - SENSORS_FEATURE_IN)
+#define MAX_OTHER_SENSOR_TYPES	(SENSORS_FEATURE_MAX_OTHER - SENSORS_FEATURE_VID)
+#define MAX_SENSORS_PER_TYPE	24
+/* max_subfeatures is now computed dynamically */
+#define FEATURE_SIZE		(max_subfeatures * 2)
+#define FEATURE_TYPE_SIZE	(MAX_SENSORS_PER_TYPE * FEATURE_SIZE)
+
+/*
+ * Room for all 7 main types (in, fan, temp, power, energy, current, humidity)
+ * and 2 other types (VID, intrusion) with all their subfeatures + misc features
+ */
+#define SUB_OFFSET_OTHER	(MAX_MAIN_SENSOR_TYPES * FEATURE_TYPE_SIZE)
+#define SUB_OFFSET_MISC		(SUB_OFFSET_OTHER + \
+				 MAX_OTHER_SENSOR_TYPES * FEATURE_TYPE_SIZE)
+#define ALL_POSSIBLE_SUBFEATURES	(SUB_OFFSET_MISC + 1)
+
+static
+int get_type_scaling(sensors_subfeature_type type)
+{
+	/* Multipliers for subfeatures */
+	switch (type & 0xFF80) {
+	case SENSORS_SUBFEATURE_IN_INPUT:
+	case SENSORS_SUBFEATURE_TEMP_INPUT:
+	case SENSORS_SUBFEATURE_CURR_INPUT:
+	case SENSORS_SUBFEATURE_HUMIDITY_INPUT:
+		return 1000;
+	case SENSORS_SUBFEATURE_FAN_INPUT:
+		return 1;
+	case SENSORS_SUBFEATURE_POWER_AVERAGE:
+	case SENSORS_SUBFEATURE_ENERGY_INPUT:
+		return 1000000;
+	}
+
+	/* Multipliers for second class subfeatures
+	   that need their own multiplier */
+	switch (type) {
+	case SENSORS_SUBFEATURE_POWER_AVERAGE_INTERVAL:
+	case SENSORS_SUBFEATURE_VID:
+	case SENSORS_SUBFEATURE_TEMP_OFFSET:
+		return 1000;
+	default:
+		return 1;
+	}
+}
+
+static
+char *get_feature_name(sensors_feature_type ftype, char *sfname)
+{
+	char *name, *underscore;
+
+	switch (ftype) {
+	case SENSORS_FEATURE_IN:
+	case SENSORS_FEATURE_FAN:
+	case SENSORS_FEATURE_TEMP:
+	case SENSORS_FEATURE_POWER:
+	case SENSORS_FEATURE_ENERGY:
+	case SENSORS_FEATURE_CURR:
+	case SENSORS_FEATURE_HUMIDITY:
+	case SENSORS_FEATURE_INTRUSION:
+		underscore = strchr(sfname, '_');
+		name = strndup(sfname, underscore - sfname);
+		if (!name)
+			sensors_fatal_error(__func__, "Out of memory");
+
+		break;
+	default:
+		name = strdup(sfname);
+		if (!name)
+			sensors_fatal_error(__func__, "Out of memory");
+	}
+
+	return name;
+}
+
+/* Static mappings for use by sensors_subfeature_get_type() */
+struct subfeature_type_match
+{
+	const char *name;
+	sensors_subfeature_type type;
+};
+
+struct feature_type_match
+{
+	const char *name;
+	const struct subfeature_type_match *submatches;
+};
+
+static const struct subfeature_type_match temp_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_TEMP_INPUT },
+	{ "max", SENSORS_SUBFEATURE_TEMP_MAX },
+	{ "max_hyst", SENSORS_SUBFEATURE_TEMP_MAX_HYST },
+	{ "min", SENSORS_SUBFEATURE_TEMP_MIN },
+	{ "crit", SENSORS_SUBFEATURE_TEMP_CRIT },
+	{ "crit_hyst", SENSORS_SUBFEATURE_TEMP_CRIT_HYST },
+	{ "lcrit", SENSORS_SUBFEATURE_TEMP_LCRIT },
+	{ "emergency", SENSORS_SUBFEATURE_TEMP_EMERGENCY },
+	{ "emergency_hyst", SENSORS_SUBFEATURE_TEMP_EMERGENCY_HYST },
+	{ "lowest", SENSORS_SUBFEATURE_TEMP_LOWEST },
+	{ "highest", SENSORS_SUBFEATURE_TEMP_HIGHEST },
+	{ "alarm", SENSORS_SUBFEATURE_TEMP_ALARM },
+	{ "min_alarm", SENSORS_SUBFEATURE_TEMP_MIN_ALARM },
+	{ "max_alarm", SENSORS_SUBFEATURE_TEMP_MAX_ALARM },
+	{ "crit_alarm", SENSORS_SUBFEATURE_TEMP_CRIT_ALARM },
+	{ "emergency_alarm", SENSORS_SUBFEATURE_TEMP_EMERGENCY_ALARM },
+	{ "lcrit_alarm", SENSORS_SUBFEATURE_TEMP_LCRIT_ALARM },
+	{ "fault", SENSORS_SUBFEATURE_TEMP_FAULT },
+	{ "type", SENSORS_SUBFEATURE_TEMP_TYPE },
+	{ "offset", SENSORS_SUBFEATURE_TEMP_OFFSET },
+	{ "beep", SENSORS_SUBFEATURE_TEMP_BEEP },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match in_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_IN_INPUT },
+	{ "min", SENSORS_SUBFEATURE_IN_MIN },
+	{ "max", SENSORS_SUBFEATURE_IN_MAX },
+	{ "lcrit", SENSORS_SUBFEATURE_IN_LCRIT },
+	{ "crit", SENSORS_SUBFEATURE_IN_CRIT },
+	{ "average", SENSORS_SUBFEATURE_IN_AVERAGE },
+	{ "lowest", SENSORS_SUBFEATURE_IN_LOWEST },
+	{ "highest", SENSORS_SUBFEATURE_IN_HIGHEST },
+	{ "alarm", SENSORS_SUBFEATURE_IN_ALARM },
+	{ "min_alarm", SENSORS_SUBFEATURE_IN_MIN_ALARM },
+	{ "max_alarm", SENSORS_SUBFEATURE_IN_MAX_ALARM },
+	{ "lcrit_alarm", SENSORS_SUBFEATURE_IN_LCRIT_ALARM },
+	{ "crit_alarm", SENSORS_SUBFEATURE_IN_CRIT_ALARM },
+	{ "beep", SENSORS_SUBFEATURE_IN_BEEP },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match fan_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_FAN_INPUT },
+	{ "min", SENSORS_SUBFEATURE_FAN_MIN },
+	{ "max", SENSORS_SUBFEATURE_FAN_MAX },
+	{ "div", SENSORS_SUBFEATURE_FAN_DIV },
+	{ "pulses", SENSORS_SUBFEATURE_FAN_PULSES },
+	{ "alarm", SENSORS_SUBFEATURE_FAN_ALARM },
+	{ "min_alarm", SENSORS_SUBFEATURE_FAN_MIN_ALARM },
+	{ "max_alarm", SENSORS_SUBFEATURE_FAN_MAX_ALARM },
+	{ "fault", SENSORS_SUBFEATURE_FAN_FAULT },
+	{ "beep", SENSORS_SUBFEATURE_FAN_BEEP },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match power_matches[] = {
+	{ "average", SENSORS_SUBFEATURE_POWER_AVERAGE },
+	{ "average_highest", SENSORS_SUBFEATURE_POWER_AVERAGE_HIGHEST },
+	{ "average_lowest", SENSORS_SUBFEATURE_POWER_AVERAGE_LOWEST },
+	{ "input", SENSORS_SUBFEATURE_POWER_INPUT },
+	{ "input_highest", SENSORS_SUBFEATURE_POWER_INPUT_HIGHEST },
+	{ "input_lowest", SENSORS_SUBFEATURE_POWER_INPUT_LOWEST },
+	{ "cap", SENSORS_SUBFEATURE_POWER_CAP },
+	{ "cap_hyst", SENSORS_SUBFEATURE_POWER_CAP_HYST },
+	{ "cap_alarm", SENSORS_SUBFEATURE_POWER_CAP_ALARM },
+	{ "alarm", SENSORS_SUBFEATURE_POWER_ALARM },
+	{ "max", SENSORS_SUBFEATURE_POWER_MAX },
+	{ "max_alarm", SENSORS_SUBFEATURE_POWER_MAX_ALARM },
+	{ "crit", SENSORS_SUBFEATURE_POWER_CRIT },
+	{ "crit_alarm", SENSORS_SUBFEATURE_POWER_CRIT_ALARM },
+	{ "average_interval", SENSORS_SUBFEATURE_POWER_AVERAGE_INTERVAL },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match energy_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_ENERGY_INPUT },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match curr_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_CURR_INPUT },
+	{ "min", SENSORS_SUBFEATURE_CURR_MIN },
+	{ "max", SENSORS_SUBFEATURE_CURR_MAX },
+	{ "lcrit", SENSORS_SUBFEATURE_CURR_LCRIT },
+	{ "crit", SENSORS_SUBFEATURE_CURR_CRIT },
+	{ "average", SENSORS_SUBFEATURE_CURR_AVERAGE },
+	{ "lowest", SENSORS_SUBFEATURE_CURR_LOWEST },
+	{ "highest", SENSORS_SUBFEATURE_CURR_HIGHEST },
+	{ "alarm", SENSORS_SUBFEATURE_CURR_ALARM },
+	{ "min_alarm", SENSORS_SUBFEATURE_CURR_MIN_ALARM },
+	{ "max_alarm", SENSORS_SUBFEATURE_CURR_MAX_ALARM },
+	{ "lcrit_alarm", SENSORS_SUBFEATURE_CURR_LCRIT_ALARM },
+	{ "crit_alarm", SENSORS_SUBFEATURE_CURR_CRIT_ALARM },
+	{ "beep", SENSORS_SUBFEATURE_CURR_BEEP },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match humidity_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_HUMIDITY_INPUT },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match cpu_matches[] = {
+	{ "vid", SENSORS_SUBFEATURE_VID },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match intrusion_matches[] = {
+	{ "alarm", SENSORS_SUBFEATURE_INTRUSION_ALARM },
+	{ "beep", SENSORS_SUBFEATURE_INTRUSION_BEEP },
+	{ NULL, 0 }
+};
+static struct feature_type_match matches[] = {
+	{ "temp%d%c", temp_matches },
+	{ "in%d%c", in_matches },
+	{ "fan%d%c", fan_matches },
+	{ "cpu%d%c", cpu_matches },
+	{ "power%d%c", power_matches },
+	{ "curr%d%c", curr_matches },
+	{ "energy%d%c", energy_matches },
+	{ "intrusion%d%c", intrusion_matches },
+	{ "humidity%d%c", humidity_matches },
+};
+
+/* Return the subfeature type and channel number based on the subfeature
+   name */
+static
+sensors_subfeature_type sensors_subfeature_get_type(const char *name, int *nr)
+{
+	char c;
+	int i, count;
+	const struct subfeature_type_match *submatches;
+
+	/* Special case */
+	if (!strcmp(name, "beep_enable")) {
+		*nr = 0;
+		return SENSORS_SUBFEATURE_BEEP_ENABLE;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(matches); i++)
+		if ((count = sscanf(name, matches[i].name, nr, &c)))
+			break;
+
+	if (i == ARRAY_SIZE(matches) || count != 2 || c != '_')
+		return SENSORS_SUBFEATURE_UNKNOWN;  /* no match */
+
+	submatches = matches[i].submatches;
+	name = strchr(name + 3, '_') + 1;
+	for (i = 0; submatches[i].name != NULL; i++)
+		if (!strcmp(name, submatches[i].name))
+			return submatches[i].type;
+
+	return SENSORS_SUBFEATURE_UNKNOWN;
+}
+
+static int sensors_compute_max(void)
+{
+	int i, j, max, offset;
+	const struct subfeature_type_match *submatches;
+	sensors_feature_type ftype;
+
+	max = 0;
+	for (i = 0; i < ARRAY_SIZE(matches); i++) {
+		submatches = matches[i].submatches;
+		for (j = 0; submatches[j].name != NULL; j++) {
+			ftype = submatches[j].type >> 8;
+
+			if (ftype < SENSORS_FEATURE_VID) {
+				offset = submatches[j].type & 0x7F;
+				if (offset >= max)
+					max = offset + 1;
+			} else {
+				offset = submatches[j].type & 0xFF;
+				if (offset >= max * 2)
+					max = ((offset + 1) + 1) / 2;
+			}
+		}
+	}
+
+	return max;
+}
+
+static int sensors_get_attr_mode(const char *device, const char *attr)
+{
+	char path[NAME_MAX];
+	struct stat st;
+	int mode = 0;
+
+	snprintf(path, NAME_MAX, "%s/%s", device, attr);
+	if (!stat(path, &st)) {
+		if (st.st_mode & S_IRUSR)
+			mode |= SENSORS_MODE_R;
+		if (st.st_mode & S_IWUSR)
+			mode |= SENSORS_MODE_W;
+	}
+	return mode;
+}
+
+static int sensors_read_dynamic_chip(sensors_chip_features *chip,
+				     const char *dev_path)
+{
+	int i, fnum = 0, sfnum = 0, prev_slot;
+	static int max_subfeatures;
+	DIR *dir;
+	struct dirent *ent;
+	sensors_subfeature *all_subfeatures;
+	sensors_subfeature *dyn_subfeatures;
+	sensors_feature *dyn_features;
+	sensors_feature_type ftype;
+	sensors_subfeature_type sftype;
+
+	if (!(dir = opendir(dev_path)))
+		return -errno;
+
+	/* Dynamically figure out the max number of subfeatures */
+	if (!max_subfeatures)
+		max_subfeatures = sensors_compute_max();
+
+	/* We use a large sparse table at first to store all found
+	   subfeatures, so that we can store them sorted at type and index
+	   and then later create a dense sorted table. */
+	all_subfeatures = calloc(ALL_POSSIBLE_SUBFEATURES,
+				 sizeof(sensors_subfeature));
+	if (!all_subfeatures)
+		sensors_fatal_error(__func__, "Out of memory");
+
+	while ((ent = readdir(dir))) {
+		char *name;
+		int nr;
+
+		/* Skip directories and symlinks */
+		if (ent->d_type != DT_REG)
+			continue;
+
+		name = ent->d_name;
+
+		sftype = sensors_subfeature_get_type(name, &nr);
+		if (sftype == SENSORS_SUBFEATURE_UNKNOWN)
+			continue;
+		ftype = sftype >> 8;
+
+		/* Adjust the channel number */
+		switch (ftype) {
+		case SENSORS_FEATURE_FAN:
+		case SENSORS_FEATURE_TEMP:
+		case SENSORS_FEATURE_POWER:
+		case SENSORS_FEATURE_ENERGY:
+		case SENSORS_FEATURE_CURR:
+		case SENSORS_FEATURE_HUMIDITY:
+			nr--;
+			break;
+		default:
+			break;
+		}
+
+		if (nr < 0 || nr >= MAX_SENSORS_PER_TYPE) {
+			/* More sensors of one type than MAX_SENSORS_PER_TYPE,
+			   we have to ignore it */
+#ifdef DEBUG
+			sensors_fatal_error(__func__,
+					    "Increase MAX_SENSORS_PER_TYPE!");
+#endif
+			continue;
+		}
+
+		/* "calculate" a place to store the subfeature in our sparse,
+		   sorted table */
+		switch (ftype) {
+		case SENSORS_FEATURE_VID:
+		case SENSORS_FEATURE_INTRUSION:
+			i = SUB_OFFSET_OTHER +
+			    (ftype - SENSORS_FEATURE_VID) * FEATURE_TYPE_SIZE +
+			    nr * FEATURE_SIZE + (sftype & 0xFF);
+			break;
+		case SENSORS_FEATURE_BEEP_ENABLE:
+			i = SUB_OFFSET_MISC +
+			    (ftype - SENSORS_FEATURE_BEEP_ENABLE);
+			break;
+		default:
+			i = ftype * FEATURE_TYPE_SIZE +
+			    nr * FEATURE_SIZE +
+			    ((sftype & 0x80) >> 7) * max_subfeatures +
+			    (sftype & 0x7F);
+		}
+
+		if (all_subfeatures[i].name) {
+#ifdef DEBUG
+			sensors_fatal_error(__func__, "Duplicate subfeature");
+#endif
+			continue;
+		}
+
+		/* fill in the subfeature members */
+		all_subfeatures[i].type = sftype;
+		all_subfeatures[i].name = strdup(name);
+		if (!all_subfeatures[i].name)
+			sensors_fatal_error(__func__, "Out of memory");
+
+		/* Other and misc subfeatures are never scaled */
+		if (sftype < SENSORS_SUBFEATURE_VID && !(sftype & 0x80))
+			all_subfeatures[i].flags |= SENSORS_COMPUTE_MAPPING;
+		all_subfeatures[i].flags |= sensors_get_attr_mode(dev_path, name);
+
+		sfnum++;
+	}
+	closedir(dir);
+
+	if (!sfnum) { /* No subfeature */
+		chip->subfeature = NULL;
+		goto exit_free;
+	}
+
+	/* How many main features? */
+	prev_slot = -1;
+	for (i = 0; i < ALL_POSSIBLE_SUBFEATURES; i++) {
+		if (!all_subfeatures[i].name)
+			continue;
+
+		if (i >= SUB_OFFSET_MISC || i / FEATURE_SIZE != prev_slot) {
+			fnum++;
+			prev_slot = i / FEATURE_SIZE;
+		}
+	}
+
+	dyn_subfeatures = calloc(sfnum, sizeof(sensors_subfeature));
+	dyn_features = calloc(fnum, sizeof(sensors_feature));
+	if (!dyn_subfeatures || !dyn_features)
+		sensors_fatal_error(__func__, "Out of memory");
+
+	/* Copy from the sparse array to the compact array */
+	sfnum = 0;
+	fnum = -1;
+	prev_slot = -1;
+	for (i = 0; i < ALL_POSSIBLE_SUBFEATURES; i++) {
+		if (!all_subfeatures[i].name)
+			continue;
+
+		/* New main feature? */
+		if (i >= SUB_OFFSET_MISC || i / FEATURE_SIZE != prev_slot) {
+			ftype = all_subfeatures[i].type >> 8;
+			fnum++;
+			prev_slot = i / FEATURE_SIZE;
+
+			dyn_features[fnum].name = get_feature_name(ftype,
+						all_subfeatures[i].name);
+			dyn_features[fnum].number = fnum;
+			dyn_features[fnum].first_subfeature = sfnum;
+			dyn_features[fnum].type = ftype;
+		}
+
+		dyn_subfeatures[sfnum] = all_subfeatures[i];
+		dyn_subfeatures[sfnum].number = sfnum;
+		/* Back to the feature */
+		dyn_subfeatures[sfnum].mapping = fnum;
+
+		sfnum++;
+	}
+
+	chip->subfeature = dyn_subfeatures;
+	chip->subfeature_count = sfnum;
+	chip->feature = dyn_features;
+	chip->feature_count = ++fnum;
+
+exit_free:
+	free(all_subfeatures);
+	return 0;
+}
+
+/* returns !0 if sysfs filesystem was found, 0 otherwise */
+int sensors_init_sysfs(void)
+{
+	struct statfs statfsbuf;
+
+	snprintf(sensors_sysfs_mount, NAME_MAX, "%s", "/sys");
+	if (statfs(sensors_sysfs_mount, &statfsbuf) < 0
+	 || statfsbuf.f_type != SYSFS_MAGIC)
+		return 0;
+
+	return 1;
+}
+
+/* returns: number of devices added (0 or 1) if successful, <0 otherwise */
+static int sensors_read_one_sysfs_chip(const char *dev_path,
+				       const char *dev_name,
+				       const char *hwmon_path)
+{
+	int domain, bus, slot, fn, vendor, product, id;
+	int err = -SENSORS_ERR_KERNEL;
+	char *bus_attr;
+	char bus_path[NAME_MAX];
+	char linkpath[NAME_MAX];
+	char subsys_path[NAME_MAX], *subsys;
+	int sub_len;
+	sensors_chip_features entry;
+
+	/* ignore any device without name attribute */
+	if (!(entry.chip.prefix = sysfs_read_attr(hwmon_path, "name")))
+		return 0;
+
+	entry.chip.path = strdup(hwmon_path);
+	if (!entry.chip.path)
+		sensors_fatal_error(__func__, "Out of memory");
+
+	if (dev_path == NULL) {
+		/* Virtual device */
+		entry.chip.bus.type = SENSORS_BUS_TYPE_VIRTUAL;
+		entry.chip.bus.nr = 0;
+		/* For now we assume that virtual devices are unique */
+		entry.chip.addr = 0;
+		goto done;
+	}
+
+	/* Find bus type */
+	snprintf(linkpath, NAME_MAX, "%s/subsystem", dev_path);
+	sub_len = readlink(linkpath, subsys_path, NAME_MAX - 1);
+	if (sub_len < 0 && errno == ENOENT) {
+		/* Fallback to "bus" link for kernels <= 2.6.17 */
+		snprintf(linkpath, NAME_MAX, "%s/bus", dev_path);
+		sub_len = readlink(linkpath, subsys_path, NAME_MAX - 1);
+	}
+	if (sub_len < 0) {
+		/* Older kernels (<= 2.6.11) have neither the subsystem
+		   symlink nor the bus symlink */
+		if (errno == ENOENT)
+			subsys = NULL;
+		else
+			goto exit_free;
+	} else {
+		subsys_path[sub_len] = '\0';
+		subsys = strrchr(subsys_path, '/') + 1;
+	}
+
+	if ((!subsys || !strcmp(subsys, "i2c")) &&
+	    sscanf(dev_name, "%hd-%x", &entry.chip.bus.nr,
+		   &entry.chip.addr) == 2) {
+		/* find out if legacy ISA or not */
+		if (entry.chip.bus.nr == 9191) {
+			entry.chip.bus.type = SENSORS_BUS_TYPE_ISA;
+			entry.chip.bus.nr = 0;
+		} else {
+			entry.chip.bus.type = SENSORS_BUS_TYPE_I2C;
+			snprintf(bus_path, sizeof(bus_path),
+				"%s/class/i2c-adapter/i2c-%d/device",
+				sensors_sysfs_mount, entry.chip.bus.nr);
+
+			if ((bus_attr = sysfs_read_attr(bus_path, "name"))) {
+				if (!strncmp(bus_attr, "ISA ", 4)) {
+					entry.chip.bus.type = SENSORS_BUS_TYPE_ISA;
+					entry.chip.bus.nr = 0;
+				}
+
+				free(bus_attr);
+			}
+		}
+	} else
+	if ((!subsys || !strcmp(subsys, "spi")) &&
+	    sscanf(dev_name, "spi%hd.%d", &entry.chip.bus.nr,
+		   &entry.chip.addr) == 2) {
+		/* SPI */
+		entry.chip.bus.type = SENSORS_BUS_TYPE_SPI;
+	} else
+	if ((!subsys || !strcmp(subsys, "pci")) &&
+	    sscanf(dev_name, "%x:%x:%x.%x", &domain, &bus, &slot, &fn) == 4) {
+		/* PCI */
+		entry.chip.addr = (domain << 16) + (bus << 8) + (slot << 3) + fn;
+		entry.chip.bus.type = SENSORS_BUS_TYPE_PCI;
+		entry.chip.bus.nr = 0;
+	} else
+	if ((!subsys || !strcmp(subsys, "platform") ||
+			!strcmp(subsys, "of_platform"))) {
+		/* must be new ISA (platform driver) */
+		if (sscanf(dev_name, "%*[a-z0-9_].%d", &entry.chip.addr) != 1)
+			entry.chip.addr = 0;
+		entry.chip.bus.type = SENSORS_BUS_TYPE_ISA;
+		entry.chip.bus.nr = 0;
+	} else if (subsys && !strcmp(subsys, "acpi")) {
+		entry.chip.bus.type = SENSORS_BUS_TYPE_ACPI;
+		/* For now we assume that acpi devices are unique */
+		entry.chip.bus.nr = 0;
+		entry.chip.addr = 0;
+	} else
+	if (subsys && !strcmp(subsys, "hid") &&
+	    sscanf(dev_name, "%x:%x:%x.%x", &bus, &vendor, &product, &id) == 4) {
+		entry.chip.bus.type = SENSORS_BUS_TYPE_HID;
+		/* As of kernel 2.6.32, the hid device names don't look good */
+		entry.chip.bus.nr = bus;
+		entry.chip.addr = id;
+	} else {
+		/* Ignore unknown device */
+		err = 0;
+		goto exit_free;
+	}
+
+done:
+	if (sensors_read_dynamic_chip(&entry, hwmon_path) < 0)
+		goto exit_free;
+	if (!entry.subfeature) { /* No subfeature, discard chip */
+		err = 0;
+		goto exit_free;
+	}
+	sensors_add_proc_chips(&entry);
+
+	return 1;
+
+exit_free:
+	free(entry.chip.prefix);
+	free(entry.chip.path);
+	return err;
+}
+
+static int sensors_add_hwmon_device_compat(const char *path,
+					   const char *dev_name)
+{
+	int err;
+
+	err = sensors_read_one_sysfs_chip(path, dev_name, path);
+	if (err < 0)
+		return err;
+	return 0;
+}
+
+/* returns 0 if successful, !0 otherwise */
+static int sensors_read_sysfs_chips_compat(void)
+{
+	int ret;
+
+	ret = sysfs_foreach_busdev("i2c", sensors_add_hwmon_device_compat);
+	if (ret && ret != ENOENT)
+		return -SENSORS_ERR_KERNEL;
+
+	return 0;
+}
+
+static int sensors_add_hwmon_device(const char *path, const char *classdev)
+{
+	char linkpath[NAME_MAX];
+	char device[NAME_MAX], *device_p;
+	int dev_len, err;
+	(void)classdev; /* hide warning */
+
+	snprintf(linkpath, NAME_MAX, "%s/device", path);
+	dev_len = readlink(linkpath, device, NAME_MAX - 1);
+	if (dev_len < 0) {
+		/* No device link? Treat as virtual */
+		err = sensors_read_one_sysfs_chip(NULL, NULL, path);
+	} else {
+		device[dev_len] = '\0';
+		device_p = strrchr(device, '/') + 1;
+
+		/* The attributes we want might be those of the hwmon class
+		   device, or those of the device itself. */
+		err = sensors_read_one_sysfs_chip(linkpath, device_p, path);
+		if (err == 0)
+			err = sensors_read_one_sysfs_chip(linkpath, device_p,
+							  linkpath);
+	}
+	if (err < 0)
+		return err;
+	return 0;
+}
+
+/* returns 0 if successful, !0 otherwise */
+int sensors_read_sysfs_chips(void)
+{
+	int ret;
+
+	ret = sysfs_foreach_classdev("hwmon", sensors_add_hwmon_device);
+	if (ret == ENOENT) {
+		/* compatibility function for kernel 2.6.n where n <= 13 */
+		return sensors_read_sysfs_chips_compat();
+	}
+
+	if (ret > 0)
+		ret = -SENSORS_ERR_KERNEL;
+	return ret;
+}
+
+/* returns 0 if successful, !0 otherwise */
+static int sensors_add_i2c_bus(const char *path, const char *classdev)
+{
+	sensors_bus entry;
+
+	if (sscanf(classdev, "i2c-%hd", &entry.bus.nr) != 1 ||
+	    entry.bus.nr == 9191) /* legacy ISA */
+		return 0;
+	entry.bus.type = SENSORS_BUS_TYPE_I2C;
+
+	/* Get the adapter name from the classdev "name" attribute
+	 * (Linux 2.6.20 and later). If it fails, fall back to
+	 * the device "name" attribute (for older kernels). */
+	entry.adapter = sysfs_read_attr(path, "name");
+	if (!entry.adapter)
+		entry.adapter = sysfs_read_attr(path, "device/name");
+	if (entry.adapter)
+		sensors_add_proc_bus(&entry);
+
+	return 0;
+}
+
+/* returns 0 if successful, !0 otherwise */
+int sensors_read_sysfs_bus(void)
+{
+	int ret;
+
+	ret = sysfs_foreach_classdev("i2c-adapter", sensors_add_i2c_bus);
+	if (ret == ENOENT)
+		ret = sysfs_foreach_busdev("i2c", sensors_add_i2c_bus);
+	if (ret && ret != ENOENT)
+		return -SENSORS_ERR_KERNEL;
+
+	return 0;
+}
+
+int sensors_read_sysfs_attr(const sensors_chip_name *name,
+			    const sensors_subfeature *subfeature,
+			    double *value)
+{
+	char n[NAME_MAX];
+	int f;
+
+	snprintf(n, NAME_MAX, "%s/%s", name->path, subfeature->name);
+	if ((f = open(n, O_RDONLY)) != -1) {
+		int res, err = 0;
+		char buf[512];
+		int count;
+
+		errno = 0;
+		if ((count = read(f, buf, sizeof(buf) - 1)) == -1) {
+			if (errno == EIO)
+				err = -SENSORS_ERR_IO;
+			else 
+				err = -SENSORS_ERR_ACCESS_R;
+		} else {
+			buf[count] = '\0';
+			errno = 0;
+			res = sscanf(buf, "%lf", value);
+			if (res == EOF && errno == EIO)
+				err = -SENSORS_ERR_IO;
+			else if (res != 1)
+				err = -SENSORS_ERR_ACCESS_R;
+		}
+		res = close(f);
+		if (err)
+			return err;
+
+		if (res != 0) {
+			if (errno == EIO)
+				return -SENSORS_ERR_IO;
+			else 
+				return -SENSORS_ERR_ACCESS_R;
+		}
+		if (!sensors_sysfs_no_scaling)
+			*value /= get_type_scaling(subfeature->type);
+	} else
+		return -SENSORS_ERR_KERNEL;
+
+	return 0;
+}
+
+int sensors_write_sysfs_attr(const sensors_chip_name *name,
+			     const sensors_subfeature *subfeature,
+			     double value)
+{
+	char n[NAME_MAX];
+	FILE *f;
+
+	snprintf(n, NAME_MAX, "%s/%s", name->path, subfeature->name);
+	if ((f = fopen(n, "w"))) {
+		int res, err = 0;
+
+		if (!sensors_sysfs_no_scaling)
+			value *= get_type_scaling(subfeature->type);
+		res = fprintf(f, "%d", (int) value);
+		if (res == -EIO)
+			err = -SENSORS_ERR_IO;
+		else if (res < 0)
+			err = -SENSORS_ERR_ACCESS_W;
+		res = fclose(f);
+		if (err)
+			return err;
+
+		if (res == EOF) {
+			if (errno == EIO)
+				return -SENSORS_ERR_IO;
+			else 
+				return -SENSORS_ERR_ACCESS_W;
+		}
+	} else
+		return -SENSORS_ERR_KERNEL;
+
+	return 0;
+}
diff --git a/tools/gator/daemon/libsensors/sysfs.h b/tools/gator/daemon/libsensors/sysfs.h
new file mode 100644
index 00000000000..38584afd028
--- /dev/null
+++ b/tools/gator/daemon/libsensors/sysfs.h
@@ -0,0 +1,43 @@
+/*
+    sysfs.h - part of libsensors, a library for reading Linux sensor data
+    Copyright (C)             Mark M. Hoffman <mhoffman@lightlink.com>
+    Copyright (C) 2007        Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef SENSORS_LIB_SYSFS_H
+#define SENSORS_LIB_SYSFS_H
+
+extern char sensors_sysfs_mount[];
+
+int sensors_init_sysfs(void);
+
+int sensors_read_sysfs_chips(void);
+
+int sensors_read_sysfs_bus(void);
+
+/* Read a value out of a sysfs attribute file */
+int sensors_read_sysfs_attr(const sensors_chip_name *name,
+			    const sensors_subfeature *subfeature,
+			    double *value);
+
+/* Write a value to a sysfs attribute file */
+int sensors_write_sysfs_attr(const sensors_chip_name *name,
+			     const sensors_subfeature *subfeature,
+			     double value);
+
+#endif /* !SENSORS_LIB_SYSFS_H */
diff --git a/tools/gator/daemon/libsensors/version.h b/tools/gator/daemon/libsensors/version.h
new file mode 100644
index 00000000000..76ceb08c29d
--- /dev/null
+++ b/tools/gator/daemon/libsensors/version.h
@@ -0,0 +1 @@
+#define LM_VERSION "3.3.2"
diff --git a/tools/gator/daemon/main.cpp b/tools/gator/daemon/main.cpp
new file mode 100644
index 00000000000..95e179ef445
--- /dev/null
+++ b/tools/gator/daemon/main.cpp
@@ -0,0 +1,615 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <arpa/inet.h>
+#include <fcntl.h>
+#include <pthread.h>
+#include <sys/mman.h>
+#include <sys/mount.h>
+#include <sys/prctl.h>
+#include <sys/resource.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "AnnotateListener.h"
+#include "Child.h"
+#include "DriverSource.h"
+#include "EventsXML.h"
+#include "Logging.h"
+#include "Monitor.h"
+#include "OlySocket.h"
+#include "OlyUtility.h"
+#include "SessionData.h"
+#include "Setup.h"
+
+extern Child* child;
+static int shutdownFilesystem();
+static pthread_mutex_t numSessions_mutex;
+static OlyServerSocket* sock = NULL;
+static Monitor monitor;
+static int numSessions = 0;
+static bool driverRunningAtStart = false;
+static bool driverMountedAtStart = false;
+
+struct cmdline_t {
+	char *module;
+	int port;
+	bool update;
+};
+
+#define DEFAULT_PORT 8080
+
+void cleanUp() {
+	if (shutdownFilesystem() == -1) {
+		logg->logMessage("Error shutting down gator filesystem");
+	}
+	delete sock;
+	delete util;
+	delete logg;
+}
+
+// CTRL C Signal Handler
+static void handler(int signum) {
+	logg->logMessage("Received signal %d, gator daemon exiting", signum);
+
+	// Case 1: both child and parent receive the signal
+	if (numSessions > 0) {
+		// Arbitrary sleep of 1 second to give time for the child to exit;
+		// if something bad happens, continue the shutdown process regardless
+		sleep(1);
+	}
+
+	// Case 2: only the parent received the signal
+	if (numSessions > 0) {
+		// Kill child threads - the first signal exits gracefully
+		logg->logMessage("Killing process group as %d child was running when signal was received", numSessions);
+		kill(0, SIGINT);
+
+		// Give time for the child to exit
+		sleep(1);
+
+		if (numSessions > 0) {
+			// The second signal force kills the child
+			logg->logMessage("Force kill the child");
+			kill(0, SIGINT);
+			// Again, sleep for 1 second
+			sleep(1);
+
+			if (numSessions > 0) {
+				// Something bad has really happened; the child is not exiting and therefore may hold the /dev/gator resource open
+				printf("Unable to kill the gatord child process, thus gator.ko may still be loaded.\n");
+			}
+		}
+	}
+
+	cleanUp();
+	exit(0);
+}
+
+// Child exit Signal Handler
+static void child_exit(int) {
+	int status;
+	int pid = wait(&status);
+	if (pid != -1) {
+		pthread_mutex_lock(&numSessions_mutex);
+		numSessions--;
+		pthread_mutex_unlock(&numSessions_mutex);
+		logg->logMessage("Child process %d exited with status %d", pid, status);
+	}
+}
+
+static const int UDP_REQ_PORT = 30001;
+
+typedef struct {
+	char rviHeader[8];
+	uint32_t messageID;
+	uint8_t ethernetAddress[8];
+	uint32_t ethernetType;
+	uint32_t dhcp;
+	char dhcpName[40];
+	uint32_t ipAddress;
+	uint32_t defaultGateway;
+	uint32_t subnetMask;
+	uint32_t activeConnections;
+} RVIConfigureInfo;
+
+static const char DST_REQ[] = { 'D', 'S', 'T', '_', 'R', 'E', 'Q', ' ', 0, 0, 0, 0x64 };
+
+class UdpListener {
+public:
+	UdpListener() : mDstAns(), mReq(-1) {}
+
+	void setup(int port) {
+		mReq = udpPort(UDP_REQ_PORT);
+
+		// Format the answer buffer
+		memset(&mDstAns, 0, sizeof(mDstAns));
+		memcpy(mDstAns.rviHeader, "STR_ANS ", sizeof(mDstAns.rviHeader));
+		if (gethostname(mDstAns.dhcpName, sizeof(mDstAns.dhcpName) - 1) != 0) {
+			logg->logError("gethostname failed");
+			handleException();
+		}
+		// Subvert the defaultGateway field for the port number
+		if (port != DEFAULT_PORT) {
+			mDstAns.defaultGateway = port;
+		}
+		// Subvert the subnetMask field for the protocol version
+		mDstAns.subnetMask = PROTOCOL_VERSION;
+	}
+
+	int getReq() const {
+		return mReq;
+	}
+
+	void handle() {
+		char buf[128];
+		struct sockaddr_in6 sockaddr;
+		socklen_t addrlen;
+		int read;
+		addrlen = sizeof(sockaddr);
+		read = recvfrom(mReq, &buf, sizeof(buf), 0, (struct sockaddr *)&sockaddr, &addrlen);
+		if (read < 0) {
+			logg->logError("recvfrom failed");
+			handleException();
+		} else if ((read == 12) && (memcmp(buf, DST_REQ, sizeof(DST_REQ)) == 0)) {
+			// Don't care if sendto fails - gatord shouldn't exit because of it and Streamline will retry
+			sendto(mReq, &mDstAns, sizeof(mDstAns), 0, (struct sockaddr *)&sockaddr, addrlen);
+		}
+	}
+
+	void close() {
+		::close(mReq);
+	}
+
+private:
+	int udpPort(int port) {
+		int s;
+		struct sockaddr_in6 sockaddr;
+		int on;
+		int family = AF_INET6;
+
+		s = socket_cloexec(AF_INET6, SOCK_DGRAM, IPPROTO_UDP);
+		if (s == -1) {
+			family = AF_INET;
+			s = socket_cloexec(AF_INET, SOCK_DGRAM, IPPROTO_UDP);
+			if (s == -1) {
+				logg->logError("socket failed");
+				handleException();
+			}
+		}
+
+		on = 1;
+		if (setsockopt(s, SOL_SOCKET, SO_REUSEADDR, (const char*)&on, sizeof(on)) != 0) {
+			logg->logError("setsockopt REUSEADDR failed");
+			handleException();
+		}
+
+		// Listen on both IPv4 and IPv6
+		on = 0;
+		if (setsockopt(s, IPPROTO_IPV6, IPV6_V6ONLY, (const char*)&on, sizeof(on)) != 0) {
+			logg->logMessage("setsockopt IPV6_V6ONLY failed");
+		}
+
+		memset((void*)&sockaddr, 0, sizeof(sockaddr));
+		sockaddr.sin6_family = family;
+		sockaddr.sin6_port = htons(port);
+		sockaddr.sin6_addr = in6addr_any;
+		if (bind(s, (struct sockaddr *)&sockaddr, sizeof(sockaddr)) < 0) {
+			logg->logError("socket failed");
+			handleException();
+		}
+
+		return s;
+	}
+
+	RVIConfigureInfo mDstAns;
+	int mReq;
+};
+
+static UdpListener udpListener;
+
+// retval: -1 = failure; 0 = was already mounted; 1 = successfully mounted
+static int mountGatorFS() {
+	// If already mounted,
+	if (access("/dev/gator/buffer", F_OK) == 0) {
+		return 0;
+	}
+
+	// else, mount the filesystem
+	mkdir("/dev/gator", S_IRWXU | S_IRWXG | S_IROTH | S_IXOTH);
+	if (mount("nodev", "/dev/gator", "gatorfs", 0, NULL) != 0) {
+		return -1;
+	} else {
+		return 1;
+	}
+}
+
+static bool init_module (const char * const location) {
+	bool ret(false);
+	const int fd = open(location, O_RDONLY | O_CLOEXEC);
+	if (fd >= 0) {
+		struct stat st;
+		if (fstat(fd, &st) == 0) {
+			void * const p = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
+			if (p != MAP_FAILED) {
+				if (syscall(__NR_init_module, p, (unsigned long)st.st_size, "") == 0) {
+					ret = true;
+				}
+				munmap(p, st.st_size);
+			}
+		}
+		close(fd);
+	}
+
+	return ret;
+}
+
+static bool setupFilesystem(char* module) {
+	if (module) {
+		// unmount and rmmod if the module was specified on the commandline, i.e. ensure that the specified module is indeed running
+		shutdownFilesystem();
+
+		// if still mounted
+		if (access("/dev/gator/buffer", F_OK) == 0) {
+			logg->logError("Unable to remove the running gator.ko. Manually remove the module or use the running module by not specifying one on the commandline");
+			handleException();
+		}
+	}
+
+	const int retval = mountGatorFS();
+	if (retval == 1) {
+		logg->logMessage("Driver already running at startup");
+		driverRunningAtStart = true;
+	} else if (retval == 0) {
+		logg->logMessage("Driver already mounted at startup");
+		driverRunningAtStart = driverMountedAtStart = true;
+	} else {
+		char command[256]; // arbitrarily large amount
+		char location[256]; // arbitrarily large amount
+
+		if (module) {
+			strncpy(location, module, sizeof(location));
+		} else {
+			// Is the driver co-located in the same directory?
+			if (util->getApplicationFullPath(location, sizeof(location)) != 0) { // allow some buffer space
+				logg->logMessage("Unable to determine the full path of gatord, the cwd will be used");
+			}
+			strncat(location, "gator.ko", sizeof(location) - strlen(location) - 1);
+		}
+
+		if (access(location, F_OK) == -1) {
+			if (module == NULL) {
+				// The gator kernel is not already loaded and unable to locate gator.ko in the default location
+				return false;
+			} else {
+				// gator location specified on the command line but it was not found
+				logg->logError("gator module not found at %s", location);
+				handleException();
+			}
+		}
+
+		// Load driver
+		if (!init_module(location)) {
+			logg->logMessage("Unable to load gator.ko driver with command: %s", command);
+			logg->logError("Unable to load (insmod) gator.ko driver:\n  >>> gator.ko must be built against the current kernel version & configuration\n  >>> See dmesg for more details");
+			handleException();
+		}
+
+		if (mountGatorFS() == -1) {
+			logg->logError("Unable to mount the gator filesystem needed for profiling.");
+			handleException();
+		}
+	}
+
+	return true;
+}
+
+static int shutdownFilesystem() {
+	if (driverMountedAtStart == false) {
+		umount("/dev/gator");
+	}
+	if (driverRunningAtStart == false) {
+		if (syscall(__NR_delete_module, "gator", O_NONBLOCK) != 0) {
+			return -1;
+		}
+	}
+
+	return 0; // success
+}
+
+static const char OPTSTRING[] = "hvVudap:s:c:e:E:m:o:";
+
+static bool hasDebugFlag(int argc, char** argv) {
+	int c;
+
+	optind = 1;
+	while ((c = getopt(argc, argv, OPTSTRING)) != -1) {
+		if (c == 'd') {
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static struct cmdline_t parseCommandLine(int argc, char** argv) {
+	struct cmdline_t cmdline;
+	cmdline.port = DEFAULT_PORT;
+	cmdline.module = NULL;
+	cmdline.update = false;
+	char version_string[256]; // arbitrary length to hold the version information
+	int c;
+
+	// build the version string
+	if (PROTOCOL_VERSION < PROTOCOL_DEV) {
+		snprintf(version_string, sizeof(version_string), "Streamline gatord version %d (DS-5 v5.%d)", PROTOCOL_VERSION, PROTOCOL_VERSION);
+	} else {
+		snprintf(version_string, sizeof(version_string), "Streamline gatord development version %d", PROTOCOL_VERSION);
+	}
+
+	optind = 1;
+	while ((c = getopt(argc, argv, OPTSTRING)) != -1) {
+		switch (c) {
+			case 'c':
+				gSessionData->mConfigurationXMLPath = optarg;
+				break;
+			case 'd':
+				// Already handled
+				break;
+			case 'e':
+				gSessionData->mEventsXMLPath = optarg;
+				break;
+			case 'E':
+				gSessionData->mEventsXMLAppend = optarg;
+				break;
+			case 'm':
+				cmdline.module = optarg;
+				break;
+			case 'p':
+				cmdline.port = strtol(optarg, NULL, 10);
+				if ((cmdline.port == 8082) || (cmdline.port == 8083)) {
+					logg->logError("Gator can't use port %i, as it already uses ports 8082 and 8083 for annotations. Please select a different port.", cmdline.port);
+					handleException();
+				}
+				break;
+			case 's':
+				gSessionData->mSessionXMLPath = optarg;
+				break;
+			case 'o':
+				gSessionData->mTargetPath = optarg;
+				break;
+			case 'u':
+				cmdline.update = true;
+				break;
+			case 'a':
+				gSessionData->mAllowCommands = true;
+				break;
+			case 'h':
+			case '?':
+				logg->logError(
+					"%s. All parameters are optional:\n"
+					"-c config_xml   path and filename of the configuration XML to use\n"
+					"-e events_xml   path and filename of the events XML to use\n"
+					"-E events_xml   path and filename of events XML to append\n"
+					"-h              this help page\n"
+					"-m module       path and filename of gator.ko\n"
+					"-p port_number  port upon which the server listens; default is 8080\n"
+					"-s session_xml  path and filename of a session.xml used for local capture\n"
+					"-o apc_dir      path and name of the output for a local capture\n"
+					"-v              version information\n"
+					"-d              enable debug messages\n"
+					"-a              allow the user to issue a command from Streamline"
+					, version_string);
+				handleException();
+				break;
+			case 'v':
+				logg->logError("%s", version_string);
+				handleException();
+				break;
+			case 'V':
+				logg->logError("%s\nSRC_MD5: %s", version_string, gSrcMd5);
+				handleException();
+				break;
+		}
+	}
+
+	// Error checking
+	if (cmdline.port != DEFAULT_PORT && gSessionData->mSessionXMLPath != NULL) {
+		logg->logError("Only a port or a session xml can be specified, not both");
+		handleException();
+	}
+
+	if (gSessionData->mTargetPath != NULL && gSessionData->mSessionXMLPath == NULL) {
+		logg->logError("Missing -s command line option required for a local capture.");
+		handleException();
+	}
+
+	if (optind < argc) {
+		logg->logError("Unknown argument: %s. Use '-h' for help.", argv[optind]);
+		handleException();
+	}
+
+	return cmdline;
+}
+
+static AnnotateListener annotateListener;
+
+static void handleClient() {
+	OlySocket client(sock->acceptConnection());
+
+	int pid = fork();
+	if (pid < 0) {
+		// Error
+		logg->logError("Fork process failed. Please power cycle the target device if this error persists.");
+	} else if (pid == 0) {
+		// Child
+		sock->closeServerSocket();
+		udpListener.close();
+		monitor.close();
+		annotateListener.close();
+		child = new Child(&client, numSessions + 1);
+		child->run();
+		delete child;
+		exit(0);
+	} else {
+		// Parent
+		client.closeSocket();
+
+		pthread_mutex_lock(&numSessions_mutex);
+		numSessions++;
+		pthread_mutex_unlock(&numSessions_mutex);
+
+		// Maximum number of connections is 2
+		int wait = 0;
+		while (numSessions > 1) {
+			// Throttle until one of the children exits before continuing to accept another socket connection
+			logg->logMessage("%d sessions active!", numSessions);
+			if (wait++ >= 10) { // Wait no more than 10 seconds
+				// Kill last created child
+				kill(pid, SIGALRM);
+				break;
+			}
+			sleep(1);
+		}
+	}
+}
+
+// Gator data flow: collector -> collector fifo -> sender
+int main(int argc, char** argv) {
+	// Ensure proper signal handling by making gatord the process group leader
+	//   e.g. it may not be the group leader when launched as 'sudo gatord'
+	setsid();
+
+	// Set up global thread-safe logging
+	logg = new Logging(hasDebugFlag(argc, argv));
+	// Global data class
+	gSessionData = new SessionData();
+	// Set up global utility class
+	util = new OlyUtility();
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-main", 0, 0, 0);
+	pthread_mutex_init(&numSessions_mutex, NULL);
+
+	signal(SIGINT, handler);
+	signal(SIGTERM, handler);
+	signal(SIGABRT, handler);
+
+	// Set to high priority
+	if (setpriority(PRIO_PROCESS, syscall(__NR_gettid), -19) == -1) {
+		logg->logMessage("setpriority() failed");
+	}
+
+	// Parse the command line parameters
+	struct cmdline_t cmdline = parseCommandLine(argc, argv);
+
+	if (cmdline.update) {
+		update(argv[0]);
+		cmdline.update = false;
+		gSessionData->mAllowCommands = true;
+	}
+
+	// Verify root permissions
+	uid_t euid = geteuid();
+	if (euid) {
+		logg->logError("gatord must be launched with root privileges");
+		handleException();
+	}
+
+	// Call before setting up the SIGCHLD handler, as system() spawns child processes
+	if (setupFilesystem(cmdline.module)) {
+		DriverSource::checkVersion();
+	} else {
+		logg->logMessage("Unable to set up gatorfs, trying perf");
+		if (!gSessionData->mPerf.setup()) {
+			logg->logError(
+				       "Unable to locate gator.ko driver:\n"
+				       "  >>> gator.ko should be co-located with gatord in the same directory\n"
+				       "  >>> OR insmod gator.ko prior to launching gatord\n"
+				       "  >>> OR specify the location of gator.ko on the command line\n"
+				       "  >>> OR run Linux 3.4 or later with perf (CONFIG_PERF_EVENTS and CONFIG_HW_PERF_EVENTS) and tracing (CONFIG_TRACING and CONFIG_CONTEXT_SWITCH_TRACER) support to collect data via userspace only");
+			handleException();
+		}
+	}
+
+	{
+		EventsXML eventsXML;
+		mxml_node_t *xml = eventsXML.getTree();
+		// Initialize all drivers
+		for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+			driver->readEvents(xml);
+		}
+		mxmlDelete(xml);
+	}
+
+	// Handle child exit codes
+	signal(SIGCHLD, child_exit);
+
+	// Ignore the SIGPIPE signal so that any send to a broken socket will return an error code instead of asserting a signal
+	// Handling the error at the send function call is much easier than trying to do anything intelligent in the sig handler
+	signal(SIGPIPE, SIG_IGN);
+
+	// If the command line argument is a session xml file, no need to open a socket
+	if (gSessionData->mSessionXMLPath) {
+		child = new Child();
+		child->run();
+		delete child;
+	} else {
+		annotateListener.setup();
+		int pipefd[2];
+		if (pipe_cloexec(pipefd) != 0) {
+			logg->logError("Unable to set up annotate pipe");
+			handleException();
+		}
+		gSessionData->mAnnotateStart = pipefd[1];
+		sock = new OlyServerSocket(cmdline.port);
+		udpListener.setup(cmdline.port);
+		if (!monitor.init() ||
+				!monitor.add(sock->getFd()) ||
+				!monitor.add(udpListener.getReq()) ||
+				!monitor.add(annotateListener.getSockFd()) ||
+				!monitor.add(annotateListener.getUdsFd()) ||
+				!monitor.add(pipefd[0]) ||
+				false) {
+			logg->logError("Monitor setup failed");
+			handleException();
+		}
+		// Forever loop, can be exited via a signal or exception
+		while (1) {
+			struct epoll_event events[2];
+			logg->logMessage("Waiting on connection...");
+			int ready = monitor.wait(events, ARRAY_LENGTH(events), -1);
+			if (ready < 0) {
+				logg->logError("Monitor::wait failed");
+				handleException();
+			}
+			for (int i = 0; i < ready; ++i) {
+				if (events[i].data.fd == sock->getFd()) {
+					handleClient();
+				} else if (events[i].data.fd == udpListener.getReq()) {
+					udpListener.handle();
+				} else if (events[i].data.fd == annotateListener.getSockFd()) {
+					annotateListener.handleSock();
+				} else if (events[i].data.fd == annotateListener.getUdsFd()) {
+					annotateListener.handleUds();
+				} else if (events[i].data.fd == pipefd[0]) {
+					uint64_t val;
+					if (read(pipefd[0], &val, sizeof(val)) != sizeof(val)) {
+						logg->logMessage("Reading annotate pipe failed");
+					}
+					annotateListener.signal();
+				}
+			}
+		}
+	}
+
+	cleanUp();
+	return 0;
+}
diff --git a/tools/gator/daemon/mxml/COPYING b/tools/gator/daemon/mxml/COPYING
new file mode 100644
index 00000000000..4d0aa78af22
--- /dev/null
+++ b/tools/gator/daemon/mxml/COPYING
@@ -0,0 +1,507 @@
+			   Mini-XML License
+			  September 18, 2010
+
+
+The Mini-XML library and included programs are provided under the
+terms of the GNU Library General Public License version 2 (LGPL2)
+with the following exceptions:
+
+  1. Static linking of applications to the Mini-XML library
+does not constitute a derivative work and does not require
+the author to provide source code for the application, use
+the shared Mini-XML libraries, or link their applications
+against a user-supplied version of Mini-XML.
+
+If you link the application to a modified version of
+Mini-XML, then the changes to Mini-XML must be provided
+under the terms of the LGPL2 in sections 1, 2, and 4.
+
+  2. You do not have to provide a copy of the Mini-XML license
+with programs that are linked to the Mini-XML library, nor
+do you have to identify the Mini-XML license in your
+program or documentation as required by section 6 of the
+LGPL2.
+
+
+		  GNU LIBRARY GENERAL PUBLIC LICENSE
+			 Version 2, June 1991
+
+	  Copyright (C) 1991 Free Software Foundation, Inc.
+       59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+     Everyone is permitted to copy and distribute verbatim copies
+      of this license document, but changing it is not allowed.
+
+    [This is the first released version of the library GPL.  It is
+   numbered 2 because it goes with version 2 of the ordinary GPL.]
+
+			       Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+Licenses are intended to guarantee your freedom to share and change
+free software--to make sure the software is free for all its users.
+
+  This license, the Library General Public License, applies to some
+specially designated Free Software Foundation software, and to any
+other libraries whose authors decide to use it.  You can use it for
+your libraries, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if
+you distribute copies of the library, or if you modify it.
+
+  For example, if you distribute copies of the library, whether gratis
+or for a fee, you must give the recipients all the rights that we gave
+you.  You must make sure that they, too, receive or can get the source
+code.  If you link a program with the library, you must provide
+complete object files to the recipients so that they can relink them
+with the library, after making changes to the library and recompiling
+it.  And you must show them these terms so they know their rights.
+
+  Our method of protecting your rights has two steps: (1) copyright
+the library, and (2) offer you this license which gives you legal
+permission to copy, distribute and/or modify the library.
+
+  Also, for each distributor's protection, we want to make certain
+that everyone understands that there is no warranty for this free
+library.  If the library is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original
+version, so that any problems introduced by others will not reflect on
+the original authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that companies distributing free
+software will individually obtain patent licenses, thus in effect
+transforming the program into proprietary software.  To prevent this,
+we have made it clear that any patent must be licensed for everyone's
+free use or not licensed at all.
+
+  Most GNU software, including some libraries, is covered by the ordinary
+GNU General Public License, which was designed for utility programs.  This
+license, the GNU Library General Public License, applies to certain
+designated libraries.  This license is quite different from the ordinary
+one; be sure to read it in full, and don't assume that anything in it is
+the same as in the ordinary license.
+
+  The reason we have a separate public license for some libraries is that
+they blur the distinction we usually make between modifying or adding to a
+program and simply using it.  Linking a program with a library, without
+changing the library, is in some sense simply using the library, and is
+analogous to running a utility program or application program.  However, in
+a textual and legal sense, the linked executable is a combined work, a
+derivative of the original library, and the ordinary General Public License
+treats it as such.
+
+  Because of this blurred distinction, using the ordinary General
+Public License for libraries did not effectively promote software
+sharing, because most developers did not use the libraries.  We
+concluded that weaker conditions might promote sharing better.
+
+  However, unrestricted linking of non-free programs would deprive the
+users of those programs of all benefit from the free status of the
+libraries themselves.  This Library General Public License is intended to
+permit developers of non-free programs to use free libraries, while
+preserving your freedom as a user of such programs to change the free
+libraries that are incorporated in them.  (We have not seen how to achieve
+this as regards changes in header files, but we have achieved it as regards
+changes in the actual functions of the Library.)  The hope is that this
+will lead to faster development of free libraries.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.  Pay close attention to the difference between a
+"work based on the library" and a "work that uses the library".  The
+former contains code derived from the library, while the latter only
+works together with the library.
+
+  Note that it is possible for a library to be covered by the ordinary
+General Public License rather than by this special one.
+
+		  GNU LIBRARY GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License Agreement applies to any software library which
+contains a notice placed by the copyright holder or other authorized
+party saying it may be distributed under the terms of this Library
+General Public License (also called "this License").  Each licensee is
+addressed as "you".
+
+  A "library" means a collection of software functions and/or data
+prepared so as to be conveniently linked with application programs
+(which use some of those functions and data) to form executables.
+
+  The "Library", below, refers to any such software library or work
+which has been distributed under these terms.  A "work based on the
+Library" means either the Library or any derivative work under
+copyright law: that is to say, a work containing the Library or a
+portion of it, either verbatim or with modifications and/or translated
+straightforwardly into another language.  (Hereinafter, translation is
+included without limitation in the term "modification".)
+
+  "Source code" for a work means the preferred form of the work for
+making modifications to it.  For a library, complete source code means
+all the source code for all modules it contains, plus any associated
+interface definition files, plus the scripts used to control compilation
+and installation of the library.
+
+  Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running a program using the Library is not restricted, and output from
+such a program is covered only if its contents constitute a work based
+on the Library (independent of the use of the Library in a tool for
+writing it).  Whether that is true depends on what the Library does
+and what the program that uses the Library does.
+
+  1. You may copy and distribute verbatim copies of the Library's
+complete source code as you receive it, in any medium, provided that
+you conspicuously and appropriately publish on each copy an
+appropriate copyright notice and disclaimer of warranty; keep intact
+all the notices that refer to this License and to the absence of any
+warranty; and distribute a copy of this License along with the
+Library.
+
+  You may charge a fee for the physical act of transferring a copy,
+and you may at your option offer warranty protection in exchange for a
+fee.
+
+  2. You may modify your copy or copies of the Library or any portion
+of it, thus forming a work based on the Library, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) The modified work must itself be a software library.
+
+    b) You must cause the files modified to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    c) You must cause the whole of the work to be licensed at no
+    charge to all third parties under the terms of this License.
+
+    d) If a facility in the modified Library refers to a function or a
+    table of data to be supplied by an application program that uses
+    the facility, other than as an argument passed when the facility
+    is invoked, then you must make a good faith effort to ensure that,
+    in the event an application does not supply such function or
+    table, the facility still operates, and performs whatever part of
+    its purpose remains meaningful.
+
+    (For example, a function in a library to compute square roots has
+    a purpose that is entirely well-defined independent of the
+    application.  Therefore, Subsection 2d requires that any
+    application-supplied function or table used by this function must
+    be optional: if the application does not supply it, the square
+    root function must still compute square roots.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Library,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Library, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote
+it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Library.
+
+In addition, mere aggregation of another work not based on the Library
+with the Library (or with a work based on the Library) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may opt to apply the terms of the ordinary GNU General Public
+License instead of this License to a given copy of the Library.  To do
+this, you must alter all the notices that refer to this License, so
+that they refer to the ordinary GNU General Public License, version 2,
+instead of to this License.  (If a newer version than version 2 of the
+ordinary GNU General Public License has appeared, then you can specify
+that version instead if you wish.)  Do not make any other change in
+these notices.
+
+  Once this change is made in a given copy, it is irreversible for
+that copy, so the ordinary GNU General Public License applies to all
+subsequent copies and derivative works made from that copy.
+
+  This option is useful when you wish to copy part of the code of
+the Library into a program that is not a library.
+
+  4. You may copy and distribute the Library (or a portion or
+derivative of it, under Section 2) in object code or executable form
+under the terms of Sections 1 and 2 above provided that you accompany
+it with the complete corresponding machine-readable source code, which
+must be distributed under the terms of Sections 1 and 2 above on a
+medium customarily used for software interchange.
+
+  If distribution of object code is made by offering access to copy
+from a designated place, then offering equivalent access to copy the
+source code from the same place satisfies the requirement to
+distribute the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  5. A program that contains no derivative of any portion of the
+Library, but is designed to work with the Library by being compiled or
+linked with it, is called a "work that uses the Library".  Such a
+work, in isolation, is not a derivative work of the Library, and
+therefore falls outside the scope of this License.
+
+  However, linking a "work that uses the Library" with the Library
+creates an executable that is a derivative of the Library (because it
+contains portions of the Library), rather than a "work that uses the
+library".  The executable is therefore covered by this License.
+Section 6 states terms for distribution of such executables.
+
+  When a "work that uses the Library" uses material from a header file
+that is part of the Library, the object code for the work may be a
+derivative work of the Library even though the source code is not.
+Whether this is true is especially significant if the work can be
+linked without the Library, or if the work is itself a library.  The
+threshold for this to be true is not precisely defined by law.
+
+  If such an object file uses only numerical parameters, data
+structure layouts and accessors, and small macros and small inline
+functions (ten lines or less in length), then the use of the object
+file is unrestricted, regardless of whether it is legally a derivative
+work.  (Executables containing this object code plus portions of the
+Library will still fall under Section 6.)
+
+  Otherwise, if the work is a derivative of the Library, you may
+distribute the object code for the work under the terms of Section 6.
+Any executables containing that work also fall under Section 6,
+whether or not they are linked directly with the Library itself.
+
+  6. As an exception to the Sections above, you may also compile or
+link a "work that uses the Library" with the Library to produce a
+work containing portions of the Library, and distribute that work
+under terms of your choice, provided that the terms permit
+modification of the work for the customer's own use and reverse
+engineering for debugging such modifications.
+
+  You must give prominent notice with each copy of the work that the
+Library is used in it and that the Library and its use are covered by
+this License.  You must supply a copy of this License.  If the work
+during execution displays copyright notices, you must include the
+copyright notice for the Library among them, as well as a reference
+directing the user to the copy of this License.  Also, you must do one
+of these things:
+
+    a) Accompany the work with the complete corresponding
+    machine-readable source code for the Library including whatever
+    changes were used in the work (which must be distributed under
+    Sections 1 and 2 above); and, if the work is an executable linked
+    with the Library, with the complete machine-readable "work that
+    uses the Library", as object code and/or source code, so that the
+    user can modify the Library and then relink to produce a modified
+    executable containing the modified Library.  (It is understood
+    that the user who changes the contents of definitions files in the
+    Library will not necessarily be able to recompile the application
+    to use the modified definitions.)
+
+    b) Accompany the work with a written offer, valid for at
+    least three years, to give the same user the materials
+    specified in Subsection 6a, above, for a charge no more
+    than the cost of performing this distribution.
+
+    c) If distribution of the work is made by offering access to copy
+    from a designated place, offer equivalent access to copy the above
+    specified materials from the same place.
+
+    d) Verify that the user has already received a copy of these
+    materials or that you have already sent this user a copy.
+
+  For an executable, the required form of the "work that uses the
+Library" must include any data and utility programs needed for
+reproducing the executable from it.  However, as a special exception,
+the source code distributed need not include anything that is normally
+distributed (in either source or binary form) with the major
+components (compiler, kernel, and so on) of the operating system on
+which the executable runs, unless that component itself accompanies
+the executable.
+
+  It may happen that this requirement contradicts the license
+restrictions of other proprietary libraries that do not normally
+accompany the operating system.  Such a contradiction means you cannot
+use both them and the Library together in an executable that you
+distribute.
+
+  7. You may place library facilities that are a work based on the
+Library side-by-side in a single library together with other library
+facilities not covered by this License, and distribute such a combined
+library, provided that the separate distribution of the work based on
+the Library and of the other library facilities is otherwise
+permitted, and provided that you do these two things:
+
+    a) Accompany the combined library with a copy of the same work
+    based on the Library, uncombined with any other library
+    facilities.  This must be distributed under the terms of the
+    Sections above.
+
+    b) Give prominent notice with the combined library of the fact
+    that part of it is a work based on the Library, and explaining
+    where to find the accompanying uncombined form of the same work.
+
+  8. You may not copy, modify, sublicense, link with, or distribute
+the Library except as expressly provided under this License.  Any
+attempt otherwise to copy, modify, sublicense, link with, or
+distribute the Library is void, and will automatically terminate your
+rights under this License.  However, parties who have received copies,
+or rights, from you under this License will not have their licenses
+terminated so long as such parties remain in full compliance.
+
+  9. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Library or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Library (or any work based on the
+Library), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Library or works based on it.
+
+  10. Each time you redistribute the Library (or any work based on the
+Library), the recipient automatically receives a license from the
+original licensor to copy, distribute, link with or modify the Library
+subject to these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  11. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Library at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Library by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Library.
+
+If any portion of this section is held invalid or unenforceable under any
+particular circumstance, the balance of the section is intended to apply,
+and the section as a whole is intended to apply in other circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  12. If the distribution and/or use of the Library is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Library under this License may add
+an explicit geographical distribution limitation excluding those countries,
+so that distribution is permitted only in or among countries not thus
+excluded.  In such case, this License incorporates the limitation as if
+written in the body of this License.
+
+  13. The Free Software Foundation may publish revised and/or new
+versions of the Library General Public License from time to time.
+Such new versions will be similar in spirit to the present version,
+but may differ in detail to address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Library
+specifies a version number of this License which applies to it and
+"any later version", you have the option of following the terms and
+conditions either of that version or of any later version published by
+the Free Software Foundation.  If the Library does not specify a
+license version number, you may choose any version ever published by
+the Free Software Foundation.
+
+  14. If you wish to incorporate parts of the Library into other free
+programs whose distribution conditions are incompatible with these,
+write to the author to ask for permission.  For software which is
+copyrighted by the Free Software Foundation, write to the Free
+Software Foundation; we sometimes make exceptions for this.  Our
+decision will be guided by the two goals of preserving the free status
+of all derivatives of our free software and of promoting the sharing
+and reuse of software generally.
+
+			    NO WARRANTY
+
+  15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
+WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
+EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
+OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY
+KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE
+LIBRARY IS WITH YOU.  SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
+THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
+WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
+AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU
+FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR
+CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE
+LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
+RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
+FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
+SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
+DAMAGES.
+
+		     END OF TERMS AND CONDITIONS
+
+     Appendix: How to Apply These Terms to Your New Libraries
+
+  If you develop a new library, and you want it to be of the greatest
+possible use to the public, we recommend making it free software that
+everyone can redistribute and change.  You can do so by permitting
+redistribution under these terms (or, alternatively, under the terms of the
+ordinary General Public License).
+
+  To apply these terms, attach the following notices to the library.  It is
+safest to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least the
+"copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the library's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Library General Public
+    License as published by the Free Software Foundation; either
+    version 2 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+    Library General Public License for more details.
+
+    You should have received a copy of the GNU Library General Public
+    License along with this library; if not, write to the Free
+    Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the library, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the
+  library `Frob' (a library for tweaking knobs) written by James Random Hacker.
+
+  <signature of Ty Coon>, 1 April 1990
+  Ty Coon, President of Vice
+
+That's all there is to it!
diff --git a/tools/gator/daemon/mxml/config.h b/tools/gator/daemon/mxml/config.h
new file mode 100644
index 00000000000..ad6df1d7deb
--- /dev/null
+++ b/tools/gator/daemon/mxml/config.h
@@ -0,0 +1,96 @@
+/* config.h.  Generated from config.h.in by configure.  */
+/*
+ * "$Id: config.h.in 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Configuration file for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdarg.h>
+#include <ctype.h>
+
+
+/*
+ * Version number...
+ */
+
+#define MXML_VERSION "Mini-XML v2.8"
+
+
+/*
+ * Inline function support...
+ */
+
+#define inline
+
+
+/*
+ * Long long support...
+ */
+
+#define HAVE_LONG_LONG 1
+
+
+/*
+ * Do we have the snprintf() and vsnprintf() functions?
+ */
+
+#define HAVE_SNPRINTF 1
+#define HAVE_VSNPRINTF 1
+
+
+/*
+ * Do we have the strXXX() functions?
+ */
+
+#define HAVE_STRDUP 1
+
+
+/*
+ * Do we have threading support?
+ */
+
+#define HAVE_PTHREAD_H 1
+
+
+/*
+ * Define prototypes for string functions as needed...
+ */
+
+#  ifndef HAVE_STRDUP
+extern char	*_mxml_strdup(const char *);
+#    define strdup _mxml_strdup
+#  endif /* !HAVE_STRDUP */
+
+extern char	*_mxml_strdupf(const char *, ...);
+extern char	*_mxml_vstrdupf(const char *, va_list);
+
+#  ifndef HAVE_SNPRINTF
+extern int	_mxml_snprintf(char *, size_t, const char *, ...);
+#    define snprintf _mxml_snprintf
+#  endif /* !HAVE_SNPRINTF */
+
+#  ifndef HAVE_VSNPRINTF
+extern int	_mxml_vsnprintf(char *, size_t, const char *, va_list);
+#    define vsnprintf _mxml_vsnprintf
+#  endif /* !HAVE_VSNPRINTF */
+
+/*
+ * End of "$Id: config.h.in 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-attr.c b/tools/gator/daemon/mxml/mxml-attr.c
new file mode 100644
index 00000000000..8e89cc1474f
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-attr.c
@@ -0,0 +1,314 @@
+/*
+ * "$Id: mxml-attr.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Attribute support code for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * Local functions...
+ */
+
+static int	mxml_set_attr(mxml_node_t *node, const char *name,
+		              char *value);
+
+
+/*
+ * 'mxmlElementDeleteAttr()' - Delete an attribute.
+ *
+ * @since Mini-XML 2.4@
+ */
+
+void
+mxmlElementDeleteAttr(mxml_node_t *node,/* I - Element */
+                      const char  *name)/* I - Attribute name */
+{
+  int		i;			/* Looping var */
+  mxml_attr_t	*attr;			/* Cirrent attribute */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlElementDeleteAttr(node=%p, name=\"%s\")\n",
+          node, name ? name : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT || !name)
+    return;
+
+ /*
+  * Look for the attribute...
+  */
+
+  for (i = node->value.element.num_attrs, attr = node->value.element.attrs;
+       i > 0;
+       i --, attr ++)
+  {
+#ifdef DEBUG
+    printf("    %s=\"%s\"\n", attr->name, attr->value);
+#endif /* DEBUG */
+
+    if (!strcmp(attr->name, name))
+    {
+     /*
+      * Delete this attribute...
+      */
+
+      free(attr->name);
+      free(attr->value);
+
+      i --;
+      if (i > 0)
+        memmove(attr, attr + 1, i * sizeof(mxml_attr_t));
+
+      node->value.element.num_attrs --;
+
+      if (node->value.element.num_attrs == 0)
+        free(node->value.element.attrs);
+      return;
+    }
+  }
+}
+
+
+/*
+ * 'mxmlElementGetAttr()' - Get an attribute.
+ *
+ * This function returns NULL if the node is not an element or the
+ * named attribute does not exist.
+ */
+
+const char *				/* O - Attribute value or NULL */
+mxmlElementGetAttr(mxml_node_t *node,	/* I - Element node */
+                   const char  *name)	/* I - Name of attribute */
+{
+  int		i;			/* Looping var */
+  mxml_attr_t	*attr;			/* Cirrent attribute */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlElementGetAttr(node=%p, name=\"%s\")\n",
+          node, name ? name : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT || !name)
+    return (NULL);
+
+ /*
+  * Look for the attribute...
+  */
+
+  for (i = node->value.element.num_attrs, attr = node->value.element.attrs;
+       i > 0;
+       i --, attr ++)
+  {
+#ifdef DEBUG
+    printf("    %s=\"%s\"\n", attr->name, attr->value);
+#endif /* DEBUG */
+
+    if (!strcmp(attr->name, name))
+    {
+#ifdef DEBUG
+      printf("    Returning \"%s\"!\n", attr->value);
+#endif /* DEBUG */
+      return (attr->value);
+    }
+  }
+
+ /*
+  * Didn't find attribute, so return NULL...
+  */
+
+#ifdef DEBUG
+  puts("    Returning NULL!\n");
+#endif /* DEBUG */
+
+  return (NULL);
+}
+
+
+/*
+ * 'mxmlElementSetAttr()' - Set an attribute.
+ *
+ * If the named attribute already exists, the value of the attribute
+ * is replaced by the new string value. The string value is copied
+ * into the element node. This function does nothing if the node is
+ * not an element.
+ */
+
+void
+mxmlElementSetAttr(mxml_node_t *node,	/* I - Element node */
+                   const char  *name,	/* I - Name of attribute */
+                   const char  *value)	/* I - Attribute value */
+{
+  char	*valuec;			/* Copy of value */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlElementSetAttr(node=%p, name=\"%s\", value=\"%s\")\n",
+          node, name ? name : "(null)", value ? value : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT || !name)
+    return;
+
+  if (value)
+    valuec = strdup(value);
+  else
+    valuec = NULL;
+
+  if (mxml_set_attr(node, name, valuec))
+    free(valuec);
+}
+
+
+/*
+ * 'mxmlElementSetAttrf()' - Set an attribute with a formatted value.
+ *
+ * If the named attribute already exists, the value of the attribute
+ * is replaced by the new formatted string. The formatted string value is
+ * copied into the element node. This function does nothing if the node
+ * is not an element.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+void
+mxmlElementSetAttrf(mxml_node_t *node,	/* I - Element node */
+                    const char  *name,	/* I - Name of attribute */
+                    const char  *format,/* I - Printf-style attribute value */
+		    ...)		/* I - Additional arguments as needed */
+{
+  va_list	ap;			/* Argument pointer */
+  char		*value;			/* Value */
+
+
+#ifdef DEBUG
+  fprintf(stderr,
+          "mxmlElementSetAttrf(node=%p, name=\"%s\", format=\"%s\", ...)\n",
+          node, name ? name : "(null)", format ? format : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT || !name || !format)
+    return;
+
+ /*
+  * Format the value...
+  */
+
+  va_start(ap, format);
+  value = _mxml_vstrdupf(format, ap);
+  va_end(ap);
+
+  if (!value)
+    mxml_error("Unable to allocate memory for attribute '%s' in element %s!",
+               name, node->value.element.name);
+  else if (mxml_set_attr(node, name, value))
+    free(value);
+}
+
+
+/*
+ * 'mxml_set_attr()' - Set or add an attribute name/value pair.
+ */
+
+static int				/* O - 0 on success, -1 on failure */
+mxml_set_attr(mxml_node_t *node,	/* I - Element node */
+              const char  *name,	/* I - Attribute name */
+              char        *value)	/* I - Attribute value */
+{
+  int		i;			/* Looping var */
+  mxml_attr_t	*attr;			/* New attribute */
+
+
+ /*
+  * Look for the attribute...
+  */
+
+  for (i = node->value.element.num_attrs, attr = node->value.element.attrs;
+       i > 0;
+       i --, attr ++)
+    if (!strcmp(attr->name, name))
+    {
+     /*
+      * Free the old value as needed...
+      */
+
+      if (attr->value)
+        free(attr->value);
+
+      attr->value = value;
+
+      return (0);
+    }
+
+ /*
+  * Add a new attribute...
+  */
+
+  if (node->value.element.num_attrs == 0)
+    attr = malloc(sizeof(mxml_attr_t));
+  else
+    attr = realloc(node->value.element.attrs,
+                   (node->value.element.num_attrs + 1) * sizeof(mxml_attr_t));
+
+  if (!attr)
+  {
+    mxml_error("Unable to allocate memory for attribute '%s' in element %s!",
+               name, node->value.element.name);
+    return (-1);
+  }
+
+  node->value.element.attrs = attr;
+  attr += node->value.element.num_attrs;
+
+  if ((attr->name = strdup(name)) == NULL)
+  {
+    mxml_error("Unable to allocate memory for attribute '%s' in element %s!",
+               name, node->value.element.name);
+    return (-1);
+  }
+
+  attr->value = value;
+
+  node->value.element.num_attrs ++;
+
+  return (0);
+}
+
+
+/*
+ * End of "$Id: mxml-attr.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-entity.c b/tools/gator/daemon/mxml/mxml-entity.c
new file mode 100644
index 00000000000..0d11df6a70b
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-entity.c
@@ -0,0 +1,449 @@
+/*
+ * "$Id: mxml-entity.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Character entity support code for Mini-XML, a small XML-like
+ * file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "mxml-private.h"
+
+
+/*
+ * 'mxmlEntityAddCallback()' - Add a callback to convert entities to Unicode.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlEntityAddCallback(
+    mxml_entity_cb_t cb)		/* I - Callback function to add */
+{
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  if (global->num_entity_cbs < (int)(sizeof(global->entity_cbs) / sizeof(global->entity_cbs[0])))
+  {
+    global->entity_cbs[global->num_entity_cbs] = cb;
+    global->num_entity_cbs ++;
+
+    return (0);
+  }
+  else
+  {
+    mxml_error("Unable to add entity callback!");
+
+    return (-1);
+  }
+}
+
+
+/*
+ * 'mxmlEntityGetName()' - Get the name that corresponds to the character value.
+ *
+ * If val does not need to be represented by a named entity, NULL is returned.
+ */
+
+const char *				/* O - Entity name or NULL */
+mxmlEntityGetName(int val)		/* I - Character value */
+{
+  switch (val)
+  {
+    case '&' :
+        return ("amp");
+
+    case '<' :
+        return ("lt");
+
+    case '>' :
+        return ("gt");
+
+    case '\"' :
+        return ("quot");
+
+    default :
+        return (NULL);
+  }
+}
+
+
+/*
+ * 'mxmlEntityGetValue()' - Get the character corresponding to a named entity.
+ *
+ * The entity name can also be a numeric constant. -1 is returned if the
+ * name is not known.
+ */
+
+int					/* O - Character value or -1 on error */
+mxmlEntityGetValue(const char *name)	/* I - Entity name */
+{
+  int		i;			/* Looping var */
+  int		ch;			/* Character value */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  for (i = 0; i < global->num_entity_cbs; i ++)
+    if ((ch = (global->entity_cbs[i])(name)) >= 0)
+      return (ch);
+
+  return (-1);
+}
+
+
+/*
+ * 'mxmlEntityRemoveCallback()' - Remove a callback.
+ */
+
+void
+mxmlEntityRemoveCallback(
+    mxml_entity_cb_t cb)		/* I - Callback function to remove */
+{
+  int		i;			/* Looping var */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  for (i = 0; i < global->num_entity_cbs; i ++)
+    if (cb == global->entity_cbs[i])
+    {
+     /*
+      * Remove the callback...
+      */
+
+      global->num_entity_cbs --;
+
+      if (i < global->num_entity_cbs)
+        memmove(global->entity_cbs + i, global->entity_cbs + i + 1,
+	        (global->num_entity_cbs - i) * sizeof(global->entity_cbs[0]));
+
+      return;
+    }
+}
+
+
+/*
+ * '_mxml_entity_cb()' - Lookup standard (X)HTML entities.
+ */
+
+int					/* O - Unicode value or -1 */
+_mxml_entity_cb(const char *name)	/* I - Entity name */
+{
+  int	diff,				/* Difference between names */
+	current,			/* Current entity in search */
+	first,				/* First entity in search */
+	last;				/* Last entity in search */
+  static const struct
+  {
+    const char	*name;			/* Entity name */
+    int		val;			/* Character value */
+  }	entities[] =
+  {
+    { "AElig",		198 },
+    { "Aacute",		193 },
+    { "Acirc",		194 },
+    { "Agrave",		192 },
+    { "Alpha",		913 },
+    { "Aring",		197 },
+    { "Atilde",		195 },
+    { "Auml",		196 },
+    { "Beta",		914 },
+    { "Ccedil",		199 },
+    { "Chi",		935 },
+    { "Dagger",		8225 },
+    { "Delta",		916 },
+    { "Dstrok",		208 },
+    { "ETH",		208 },
+    { "Eacute",		201 },
+    { "Ecirc",		202 },
+    { "Egrave",		200 },
+    { "Epsilon",	917 },
+    { "Eta",		919 },
+    { "Euml",		203 },
+    { "Gamma",		915 },
+    { "Iacute",		205 },
+    { "Icirc",		206 },
+    { "Igrave",		204 },
+    { "Iota",		921 },
+    { "Iuml",		207 },
+    { "Kappa",		922 },
+    { "Lambda",		923 },
+    { "Mu",		924 },
+    { "Ntilde",		209 },
+    { "Nu",		925 },
+    { "OElig",		338 },
+    { "Oacute",		211 },
+    { "Ocirc",		212 },
+    { "Ograve",		210 },
+    { "Omega",		937 },
+    { "Omicron",	927 },
+    { "Oslash",		216 },
+    { "Otilde",		213 },
+    { "Ouml",		214 },
+    { "Phi",		934 },
+    { "Pi",		928 },
+    { "Prime",		8243 },
+    { "Psi",		936 },
+    { "Rho",		929 },
+    { "Scaron",		352 },
+    { "Sigma",		931 },
+    { "THORN",		222 },
+    { "Tau",		932 },
+    { "Theta",		920 },
+    { "Uacute",		218 },
+    { "Ucirc",		219 },
+    { "Ugrave",		217 },
+    { "Upsilon",	933 },
+    { "Uuml",		220 },
+    { "Xi",		926 },
+    { "Yacute",		221 },
+    { "Yuml",		376 },
+    { "Zeta",		918 },
+    { "aacute",		225 },
+    { "acirc",		226 },
+    { "acute",		180 },
+    { "aelig",		230 },
+    { "agrave",		224 },
+    { "alefsym",	8501 },
+    { "alpha",		945 },
+    { "amp",		'&' },
+    { "and",		8743 },
+    { "ang",		8736 },
+    { "apos",           '\'' },
+    { "aring",		229 },
+    { "asymp",		8776 },
+    { "atilde",		227 },
+    { "auml",		228 },
+    { "bdquo",		8222 },
+    { "beta",		946 },
+    { "brkbar",		166 },
+    { "brvbar",		166 },
+    { "bull",		8226 },
+    { "cap",		8745 },
+    { "ccedil",		231 },
+    { "cedil",		184 },
+    { "cent",		162 },
+    { "chi",		967 },
+    { "circ",		710 },
+    { "clubs",		9827 },
+    { "cong",		8773 },
+    { "copy",		169 },
+    { "crarr",		8629 },
+    { "cup",		8746 },
+    { "curren",		164 },
+    { "dArr",		8659 },
+    { "dagger",		8224 },
+    { "darr",		8595 },
+    { "deg",		176 },
+    { "delta",		948 },
+    { "diams",		9830 },
+    { "die",		168 },
+    { "divide",		247 },
+    { "eacute",		233 },
+    { "ecirc",		234 },
+    { "egrave",		232 },
+    { "empty",		8709 },
+    { "emsp",		8195 },
+    { "ensp",		8194 },
+    { "epsilon",	949 },
+    { "equiv",		8801 },
+    { "eta",		951 },
+    { "eth",		240 },
+    { "euml",		235 },
+    { "euro",		8364 },
+    { "exist",		8707 },
+    { "fnof",		402 },
+    { "forall",		8704 },
+    { "frac12",		189 },
+    { "frac14",		188 },
+    { "frac34",		190 },
+    { "frasl",		8260 },
+    { "gamma",		947 },
+    { "ge",		8805 },
+    { "gt",		'>' },
+    { "hArr",		8660 },
+    { "harr",		8596 },
+    { "hearts",		9829 },
+    { "hellip",		8230 },
+    { "hibar",		175 },
+    { "iacute",		237 },
+    { "icirc",		238 },
+    { "iexcl",		161 },
+    { "igrave",		236 },
+    { "image",		8465 },
+    { "infin",		8734 },
+    { "int",		8747 },
+    { "iota",		953 },
+    { "iquest",		191 },
+    { "isin",		8712 },
+    { "iuml",		239 },
+    { "kappa",		954 },
+    { "lArr",		8656 },
+    { "lambda",		955 },
+    { "lang",		9001 },
+    { "laquo",		171 },
+    { "larr",		8592 },
+    { "lceil",		8968 },
+    { "ldquo",		8220 },
+    { "le",		8804 },
+    { "lfloor",		8970 },
+    { "lowast",		8727 },
+    { "loz",		9674 },
+    { "lrm",		8206 },
+    { "lsaquo",		8249 },
+    { "lsquo",		8216 },
+    { "lt",		'<' },
+    { "macr",		175 },
+    { "mdash",		8212 },
+    { "micro",		181 },
+    { "middot",		183 },
+    { "minus",		8722 },
+    { "mu",		956 },
+    { "nabla",		8711 },
+    { "nbsp",		160 },
+    { "ndash",		8211 },
+    { "ne",		8800 },
+    { "ni",		8715 },
+    { "not",		172 },
+    { "notin",		8713 },
+    { "nsub",		8836 },
+    { "ntilde",		241 },
+    { "nu",		957 },
+    { "oacute",		243 },
+    { "ocirc",		244 },
+    { "oelig",		339 },
+    { "ograve",		242 },
+    { "oline",		8254 },
+    { "omega",		969 },
+    { "omicron",	959 },
+    { "oplus",		8853 },
+    { "or",		8744 },
+    { "ordf",		170 },
+    { "ordm",		186 },
+    { "oslash",		248 },
+    { "otilde",		245 },
+    { "otimes",		8855 },
+    { "ouml",		246 },
+    { "para",		182 },
+    { "part",		8706 },
+    { "permil",		8240 },
+    { "perp",		8869 },
+    { "phi",		966 },
+    { "pi",		960 },
+    { "piv",		982 },
+    { "plusmn",		177 },
+    { "pound",		163 },
+    { "prime",		8242 },
+    { "prod",		8719 },
+    { "prop",		8733 },
+    { "psi",		968 },
+    { "quot",		'\"' },
+    { "rArr",		8658 },
+    { "radic",		8730 },
+    { "rang",		9002 },
+    { "raquo",		187 },
+    { "rarr",		8594 },
+    { "rceil",		8969 },
+    { "rdquo",		8221 },
+    { "real",		8476 },
+    { "reg",		174 },
+    { "rfloor",		8971 },
+    { "rho",		961 },
+    { "rlm",		8207 },
+    { "rsaquo",		8250 },
+    { "rsquo",		8217 },
+    { "sbquo",		8218 },
+    { "scaron",		353 },
+    { "sdot",		8901 },
+    { "sect",		167 },
+    { "shy",		173 },
+    { "sigma",		963 },
+    { "sigmaf",		962 },
+    { "sim",		8764 },
+    { "spades",		9824 },
+    { "sub",		8834 },
+    { "sube",		8838 },
+    { "sum",		8721 },
+    { "sup",		8835 },
+    { "sup1",		185 },
+    { "sup2",		178 },
+    { "sup3",		179 },
+    { "supe",		8839 },
+    { "szlig",		223 },
+    { "tau",		964 },
+    { "there4",		8756 },
+    { "theta",		952 },
+    { "thetasym",	977 },
+    { "thinsp",		8201 },
+    { "thorn",		254 },
+    { "tilde",		732 },
+    { "times",		215 },
+    { "trade",		8482 },
+    { "uArr",		8657 },
+    { "uacute",		250 },
+    { "uarr",		8593 },
+    { "ucirc",		251 },
+    { "ugrave",		249 },
+    { "uml",		168 },
+    { "upsih",		978 },
+    { "upsilon",	965 },
+    { "uuml",		252 },
+    { "weierp",		8472 },
+    { "xi",		958 },
+    { "yacute",		253 },
+    { "yen",		165 },
+    { "yuml",		255 },
+    { "zeta",		950 },
+    { "zwj",		8205 },
+    { "zwnj",		8204 }
+  };
+
+
+ /*
+  * Do a binary search for the named entity...
+  */
+
+  first = 0;
+  last  = (int)(sizeof(entities) / sizeof(entities[0]) - 1);
+
+  while ((last - first) > 1)
+  {
+    current = (first + last) / 2;
+
+    if ((diff = strcmp(name, entities[current].name)) == 0)
+      return (entities[current].val);
+    else if (diff < 0)
+      last = current;
+    else
+      first = current;
+  }
+
+ /*
+  * If we get here, there is a small chance that there is still
+  * a match; check first and last...
+  */
+
+  if (!strcmp(name, entities[first].name))
+    return (entities[first].val);
+  else if (!strcmp(name, entities[last].name))
+    return (entities[last].val);
+  else
+    return (-1);
+}
+
+
+/*
+ * End of "$Id: mxml-entity.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-file.c b/tools/gator/daemon/mxml/mxml-file.c
new file mode 100644
index 00000000000..3812c253fc3
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-file.c
@@ -0,0 +1,3056 @@
+/*
+ * "$Id: mxml-file.c 455 2014-01-05 03:28:03Z msweet $"
+ *
+ * File loading code for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*** This file modified by ARM on 25 Aug 2014 to avoid pointer overflow when checking if the write position is beyond the end of the buffer in mxmlSaveString and mxml_string_putc ***/
+
+/*
+ * Include necessary headers...
+ */
+
+#ifndef WIN32
+#  include <unistd.h>
+#endif /* !WIN32 */
+#include "mxml-private.h"
+
+
+/*
+ * Character encoding...
+ */
+
+#define ENCODE_UTF8	0		/* UTF-8 */
+#define ENCODE_UTF16BE	1		/* UTF-16 Big-Endian */
+#define ENCODE_UTF16LE	2		/* UTF-16 Little-Endian */
+
+
+/*
+ * Macro to test for a bad XML character...
+ */
+
+#define mxml_bad_char(ch) ((ch) < ' ' && (ch) != '\n' && (ch) != '\r' && (ch) != '\t')
+
+
+/*
+ * Types and structures...
+ */
+
+typedef int (*_mxml_getc_cb_t)(void *, int *);
+typedef int (*_mxml_putc_cb_t)(int, void *);
+
+typedef struct _mxml_fdbuf_s		/**** File descriptor buffer ****/
+{
+  int		fd;			/* File descriptor */
+  unsigned char	*current,		/* Current position in buffer */
+		*end,			/* End of buffer */
+		buffer[8192];		/* Character buffer */
+} _mxml_fdbuf_t;
+
+
+/*
+ * Local functions...
+ */
+
+static int		mxml_add_char(int ch, char **ptr, char **buffer,
+			              int *bufsize);
+static int		mxml_fd_getc(void *p, int *encoding);
+static int		mxml_fd_putc(int ch, void *p);
+static int		mxml_fd_read(_mxml_fdbuf_t *buf);
+static int		mxml_fd_write(_mxml_fdbuf_t *buf);
+static int		mxml_file_getc(void *p, int *encoding);
+static int		mxml_file_putc(int ch, void *p);
+static int		mxml_get_entity(mxml_node_t *parent, void *p,
+			                int *encoding,
+					_mxml_getc_cb_t getc_cb);
+static inline int	mxml_isspace(int ch)
+			{
+			  return (ch == ' ' || ch == '\t' || ch == '\r' ||
+			          ch == '\n');
+			}
+static mxml_node_t	*mxml_load_data(mxml_node_t *top, void *p,
+			                mxml_load_cb_t cb,
+			                _mxml_getc_cb_t getc_cb,
+                                        mxml_sax_cb_t sax_cb, void *sax_data);
+static int		mxml_parse_element(mxml_node_t *node, void *p,
+			                   int *encoding,
+					   _mxml_getc_cb_t getc_cb);
+static int		mxml_string_getc(void *p, int *encoding);
+static int		mxml_string_putc(int ch, void *p);
+static int		mxml_write_name(const char *s, void *p,
+					_mxml_putc_cb_t putc_cb);
+static int		mxml_write_node(mxml_node_t *node, void *p,
+			                mxml_save_cb_t cb, int col,
+					_mxml_putc_cb_t putc_cb,
+					_mxml_global_t *global);
+static int		mxml_write_string(const char *s, void *p,
+					  _mxml_putc_cb_t putc_cb);
+static int		mxml_write_ws(mxml_node_t *node, void *p,
+			              mxml_save_cb_t cb, int ws,
+				      int col, _mxml_putc_cb_t putc_cb);
+
+
+/*
+ * 'mxmlLoadFd()' - Load a file descriptor into an XML node tree.
+ *
+ * The nodes in the specified file are added to the specified top node.
+ * If no top node is provided, the XML file MUST be well-formed with a
+ * single parent node like <?xml> for the entire file. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ */
+
+mxml_node_t *				/* O - First node or NULL if the file could not be read. */
+mxmlLoadFd(mxml_node_t    *top,		/* I - Top node */
+           int            fd,		/* I - File descriptor to read from */
+           mxml_load_cb_t cb)		/* I - Callback function or MXML_NO_CALLBACK */
+{
+  _mxml_fdbuf_t	buf;			/* File descriptor buffer */
+
+
+ /*
+  * Initialize the file descriptor buffer...
+  */
+
+  buf.fd      = fd;
+  buf.current = buf.buffer;
+  buf.end     = buf.buffer;
+
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, &buf, cb, mxml_fd_getc, MXML_NO_CALLBACK, NULL));
+}
+
+
+/*
+ * 'mxmlLoadFile()' - Load a file into an XML node tree.
+ *
+ * The nodes in the specified file are added to the specified top node.
+ * If no top node is provided, the XML file MUST be well-formed with a
+ * single parent node like <?xml> for the entire file. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ */
+
+mxml_node_t *				/* O - First node or NULL if the file could not be read. */
+mxmlLoadFile(mxml_node_t    *top,	/* I - Top node */
+             FILE           *fp,	/* I - File to read from */
+             mxml_load_cb_t cb)		/* I - Callback function or MXML_NO_CALLBACK */
+{
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, fp, cb, mxml_file_getc, MXML_NO_CALLBACK, NULL));
+}
+
+
+/*
+ * 'mxmlLoadString()' - Load a string into an XML node tree.
+ *
+ * The nodes in the specified string are added to the specified top node.
+ * If no top node is provided, the XML string MUST be well-formed with a
+ * single parent node like <?xml> for the entire string. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ */
+
+mxml_node_t *				/* O - First node or NULL if the string has errors. */
+mxmlLoadString(mxml_node_t    *top,	/* I - Top node */
+               const char     *s,	/* I - String to load */
+               mxml_load_cb_t cb)	/* I - Callback function or MXML_NO_CALLBACK */
+{
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, (void *)&s, cb, mxml_string_getc, MXML_NO_CALLBACK,
+                         NULL));
+}
+
+
+/*
+ * 'mxmlSaveAllocString()' - Save an XML tree to an allocated string.
+ *
+ * This function returns a pointer to a string containing the textual
+ * representation of the XML node tree.  The string should be freed
+ * using the free() function when you are done with it.  NULL is returned
+ * if the node would produce an empty string or if the string cannot be
+ * allocated.
+ *
+ * The callback argument specifies a function that returns a whitespace
+ * string or NULL before and after each element. If MXML_NO_CALLBACK
+ * is specified, whitespace will only be added before MXML_TEXT nodes
+ * with leading whitespace and before attribute names inside opening
+ * element tags.
+ */
+
+char *					/* O - Allocated string or NULL */
+mxmlSaveAllocString(
+    mxml_node_t    *node,		/* I - Node to write */
+    mxml_save_cb_t cb)			/* I - Whitespace callback or MXML_NO_CALLBACK */
+{
+  int	bytes;				/* Required bytes */
+  char	buffer[8192];			/* Temporary buffer */
+  char	*s;				/* Allocated string */
+
+
+ /*
+  * Write the node to the temporary buffer...
+  */
+
+  bytes = mxmlSaveString(node, buffer, sizeof(buffer), cb);
+
+  if (bytes <= 0)
+    return (NULL);
+
+  if (bytes < (int)(sizeof(buffer) - 1))
+  {
+   /*
+    * Node fit inside the buffer, so just duplicate that string and
+    * return...
+    */
+
+    return (strdup(buffer));
+  }
+
+ /*
+  * Allocate a buffer of the required size and save the node to the
+  * new buffer...
+  */
+
+  if ((s = malloc(bytes + 1)) == NULL)
+    return (NULL);
+
+  mxmlSaveString(node, s, bytes + 1, cb);
+
+ /*
+  * Return the allocated string...
+  */
+
+  return (s);
+}
+
+
+/*
+ * 'mxmlSaveFd()' - Save an XML tree to a file descriptor.
+ *
+ * The callback argument specifies a function that returns a whitespace
+ * string or NULL before and after each element. If MXML_NO_CALLBACK
+ * is specified, whitespace will only be added before MXML_TEXT nodes
+ * with leading whitespace and before attribute names inside opening
+ * element tags.
+ */
+
+int					/* O - 0 on success, -1 on error. */
+mxmlSaveFd(mxml_node_t    *node,	/* I - Node to write */
+           int            fd,		/* I - File descriptor to write to */
+	   mxml_save_cb_t cb)		/* I - Whitespace callback or MXML_NO_CALLBACK */
+{
+  int		col;			/* Final column */
+  _mxml_fdbuf_t	buf;			/* File descriptor buffer */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+ /*
+  * Initialize the file descriptor buffer...
+  */
+
+  buf.fd      = fd;
+  buf.current = buf.buffer;
+  buf.end     = buf.buffer + sizeof(buf.buffer);
+
+ /*
+  * Write the node...
+  */
+
+  if ((col = mxml_write_node(node, &buf, cb, 0, mxml_fd_putc, global)) < 0)
+    return (-1);
+
+  if (col > 0)
+    if (mxml_fd_putc('\n', &buf) < 0)
+      return (-1);
+
+ /*
+  * Flush and return...
+  */
+
+  return (mxml_fd_write(&buf));
+}
+
+
+/*
+ * 'mxmlSaveFile()' - Save an XML tree to a file.
+ *
+ * The callback argument specifies a function that returns a whitespace
+ * string or NULL before and after each element. If MXML_NO_CALLBACK
+ * is specified, whitespace will only be added before MXML_TEXT nodes
+ * with leading whitespace and before attribute names inside opening
+ * element tags.
+ */
+
+int					/* O - 0 on success, -1 on error. */
+mxmlSaveFile(mxml_node_t    *node,	/* I - Node to write */
+             FILE           *fp,	/* I - File to write to */
+	     mxml_save_cb_t cb)		/* I - Whitespace callback or MXML_NO_CALLBACK */
+{
+  int	col;				/* Final column */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+ /*
+  * Write the node...
+  */
+
+  if ((col = mxml_write_node(node, fp, cb, 0, mxml_file_putc, global)) < 0)
+    return (-1);
+
+  if (col > 0)
+    if (putc('\n', fp) < 0)
+      return (-1);
+
+ /*
+  * Return 0 (success)...
+  */
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSaveString()' - Save an XML node tree to a string.
+ *
+ * This function returns the total number of bytes that would be
+ * required for the string but only copies (bufsize - 1) characters
+ * into the specified buffer.
+ *
+ * The callback argument specifies a function that returns a whitespace
+ * string or NULL before and after each element. If MXML_NO_CALLBACK
+ * is specified, whitespace will only be added before MXML_TEXT nodes
+ * with leading whitespace and before attribute names inside opening
+ * element tags.
+ */
+
+int					/* O - Size of string */
+mxmlSaveString(mxml_node_t    *node,	/* I - Node to write */
+               char           *buffer,	/* I - String buffer */
+               int            bufsize,	/* I - Size of string buffer */
+               mxml_save_cb_t cb)	/* I - Whitespace callback or MXML_NO_CALLBACK */
+{
+  int	col;				/* Final column */
+  char	*ptr[3];			/* Pointers for putc_cb */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+ /*
+  * Write the node...
+  */
+
+  ptr[0] = buffer;
+  ptr[1] = buffer + bufsize;
+  ptr[2] = 0;
+
+  if ((col = mxml_write_node(node, ptr, cb, 0, mxml_string_putc, global)) < 0)
+    return (-1);
+
+  if (col > 0)
+    mxml_string_putc('\n', ptr);
+
+ /*
+  * Nul-terminate the buffer...
+  */
+
+  if (ptr[2] != 0)
+    buffer[bufsize - 1] = '\0';
+  else
+    ptr[0][0] = '\0';
+
+ /*
+  * Return the number of characters...
+  */
+
+  return (ptr[0] - buffer);
+}
+
+
+/*
+ * 'mxmlSAXLoadFd()' - Load a file descriptor into an XML node tree
+ *                     using a SAX callback.
+ *
+ * The nodes in the specified file are added to the specified top node.
+ * If no top node is provided, the XML file MUST be well-formed with a
+ * single parent node like <?xml> for the entire file. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ *
+ * The SAX callback must call mxmlRetain() for any nodes that need to
+ * be kept for later use. Otherwise, nodes are deleted when the parent
+ * node is closed or after each data, comment, CDATA, or directive node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t *				/* O - First node or NULL if the file could not be read. */
+mxmlSAXLoadFd(mxml_node_t    *top,	/* I - Top node */
+              int            fd,	/* I - File descriptor to read from */
+              mxml_load_cb_t cb,	/* I - Callback function or MXML_NO_CALLBACK */
+              mxml_sax_cb_t  sax_cb,	/* I - SAX callback or MXML_NO_CALLBACK */
+              void           *sax_data)	/* I - SAX user data */
+{
+  _mxml_fdbuf_t	buf;			/* File descriptor buffer */
+
+
+ /*
+  * Initialize the file descriptor buffer...
+  */
+
+  buf.fd      = fd;
+  buf.current = buf.buffer;
+  buf.end     = buf.buffer;
+
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, &buf, cb, mxml_fd_getc, sax_cb, sax_data));
+}
+
+
+/*
+ * 'mxmlSAXLoadFile()' - Load a file into an XML node tree
+ *                       using a SAX callback.
+ *
+ * The nodes in the specified file are added to the specified top node.
+ * If no top node is provided, the XML file MUST be well-formed with a
+ * single parent node like <?xml> for the entire file. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ *
+ * The SAX callback must call mxmlRetain() for any nodes that need to
+ * be kept for later use. Otherwise, nodes are deleted when the parent
+ * node is closed or after each data, comment, CDATA, or directive node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t *				/* O - First node or NULL if the file could not be read. */
+mxmlSAXLoadFile(
+    mxml_node_t    *top,		/* I - Top node */
+    FILE           *fp,			/* I - File to read from */
+    mxml_load_cb_t cb,			/* I - Callback function or MXML_NO_CALLBACK */
+    mxml_sax_cb_t  sax_cb,		/* I - SAX callback or MXML_NO_CALLBACK */
+    void           *sax_data)		/* I - SAX user data */
+{
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, fp, cb, mxml_file_getc, sax_cb, sax_data));
+}
+
+
+/*
+ * 'mxmlSAXLoadString()' - Load a string into an XML node tree
+ *                         using a SAX callback.
+ *
+ * The nodes in the specified string are added to the specified top node.
+ * If no top node is provided, the XML string MUST be well-formed with a
+ * single parent node like <?xml> for the entire string. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ *
+ * The SAX callback must call mxmlRetain() for any nodes that need to
+ * be kept for later use. Otherwise, nodes are deleted when the parent
+ * node is closed or after each data, comment, CDATA, or directive node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t *				/* O - First node or NULL if the string has errors. */
+mxmlSAXLoadString(
+    mxml_node_t    *top,		/* I - Top node */
+    const char     *s,			/* I - String to load */
+    mxml_load_cb_t cb,			/* I - Callback function or MXML_NO_CALLBACK */
+    mxml_sax_cb_t  sax_cb,		/* I - SAX callback or MXML_NO_CALLBACK */
+    void           *sax_data)		/* I - SAX user data */
+{
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, (void *)&s, cb, mxml_string_getc, sax_cb, sax_data));
+}
+
+
+/*
+ * 'mxmlSetCustomHandlers()' - Set the handling functions for custom data.
+ *
+ * The load function accepts a node pointer and a data string and must
+ * return 0 on success and non-zero on error.
+ *
+ * The save function accepts a node pointer and must return a malloc'd
+ * string on success and NULL on error.
+ *
+ */
+
+void
+mxmlSetCustomHandlers(
+    mxml_custom_load_cb_t load,		/* I - Load function */
+    mxml_custom_save_cb_t save)		/* I - Save function */
+{
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  global->custom_load_cb = load;
+  global->custom_save_cb = save;
+}
+
+
+/*
+ * 'mxmlSetErrorCallback()' - Set the error message callback.
+ */
+
+void
+mxmlSetErrorCallback(mxml_error_cb_t cb)/* I - Error callback function */
+{
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  global->error_cb = cb;
+}
+
+
+/*
+ * 'mxmlSetWrapMargin()' - Set the wrap margin when saving XML data.
+ *
+ * Wrapping is disabled when "column" is 0.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+void
+mxmlSetWrapMargin(int column)		/* I - Column for wrapping, 0 to disable wrapping */
+{
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  global->wrap = column;
+}
+
+
+/*
+ * 'mxml_add_char()' - Add a character to a buffer, expanding as needed.
+ */
+
+static int				/* O  - 0 on success, -1 on error */
+mxml_add_char(int  ch,			/* I  - Character to add */
+              char **bufptr,		/* IO - Current position in buffer */
+	      char **buffer,		/* IO - Current buffer */
+	      int  *bufsize)		/* IO - Current buffer size */
+{
+  char	*newbuffer;			/* New buffer value */
+
+
+  if (*bufptr >= (*buffer + *bufsize - 4))
+  {
+   /*
+    * Increase the size of the buffer...
+    */
+
+    if (*bufsize < 1024)
+      (*bufsize) *= 2;
+    else
+      (*bufsize) += 1024;
+
+    if ((newbuffer = realloc(*buffer, *bufsize)) == NULL)
+    {
+      free(*buffer);
+
+      mxml_error("Unable to expand string buffer to %d bytes!", *bufsize);
+
+      return (-1);
+    }
+
+    *bufptr = newbuffer + (*bufptr - *buffer);
+    *buffer = newbuffer;
+  }
+
+  if (ch < 0x80)
+  {
+   /*
+    * Single byte ASCII...
+    */
+
+    *(*bufptr)++ = ch;
+  }
+  else if (ch < 0x800)
+  {
+   /*
+    * Two-byte UTF-8...
+    */
+
+    *(*bufptr)++ = 0xc0 | (ch >> 6);
+    *(*bufptr)++ = 0x80 | (ch & 0x3f);
+  }
+  else if (ch < 0x10000)
+  {
+   /*
+    * Three-byte UTF-8...
+    */
+
+    *(*bufptr)++ = 0xe0 | (ch >> 12);
+    *(*bufptr)++ = 0x80 | ((ch >> 6) & 0x3f);
+    *(*bufptr)++ = 0x80 | (ch & 0x3f);
+  }
+  else
+  {
+   /*
+    * Four-byte UTF-8...
+    */
+
+    *(*bufptr)++ = 0xf0 | (ch >> 18);
+    *(*bufptr)++ = 0x80 | ((ch >> 12) & 0x3f);
+    *(*bufptr)++ = 0x80 | ((ch >> 6) & 0x3f);
+    *(*bufptr)++ = 0x80 | (ch & 0x3f);
+  }
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_fd_getc()' - Read a character from a file descriptor.
+ */
+
+static int				/* O  - Character or EOF */
+mxml_fd_getc(void *p,			/* I  - File descriptor buffer */
+             int  *encoding)		/* IO - Encoding */
+{
+  _mxml_fdbuf_t	*buf;			/* File descriptor buffer */
+  int		ch,			/* Current character */
+		temp;			/* Temporary character */
+
+
+ /*
+  * Grab the next character in the buffer...
+  */
+
+  buf = (_mxml_fdbuf_t *)p;
+
+  if (buf->current >= buf->end)
+    if (mxml_fd_read(buf) < 0)
+      return (EOF);
+
+  ch = *(buf->current)++;
+
+  switch (*encoding)
+  {
+    case ENCODE_UTF8 :
+       /*
+	* Got a UTF-8 character; convert UTF-8 to Unicode and return...
+	*/
+
+	if (!(ch & 0x80))
+	{
+#if DEBUG > 1
+          printf("mxml_fd_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	  if (mxml_bad_char(ch))
+	  {
+	    mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	       ch);
+	    return (EOF);
+	  }
+
+	  return (ch);
+        }
+	else if (ch == 0xfe)
+	{
+	 /*
+	  * UTF-16 big-endian BOM?
+	  */
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  ch = *(buf->current)++;
+
+	  if (ch != 0xff)
+	    return (EOF);
+
+	  *encoding = ENCODE_UTF16BE;
+
+	  return (mxml_fd_getc(p, encoding));
+	}
+	else if (ch == 0xff)
+	{
+	 /*
+	  * UTF-16 little-endian BOM?
+	  */
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  ch = *(buf->current)++;
+
+	  if (ch != 0xfe)
+	    return (EOF);
+
+	  *encoding = ENCODE_UTF16LE;
+
+	  return (mxml_fd_getc(p, encoding));
+	}
+	else if ((ch & 0xe0) == 0xc0)
+	{
+	 /*
+	  * Two-byte value...
+	  */
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x1f) << 6) | (temp & 0x3f);
+
+	  if (ch < 0x80)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+	}
+	else if ((ch & 0xf0) == 0xe0)
+	{
+	 /*
+	  * Three-byte value...
+	  */
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x0f) << 6) | (temp & 0x3f);
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if (ch < 0x800)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+
+         /*
+	  * Ignore (strip) Byte Order Mark (BOM)...
+	  */
+
+	  if (ch == 0xfeff)
+	    return (mxml_fd_getc(p, encoding));
+	}
+	else if ((ch & 0xf8) == 0xf0)
+	{
+	 /*
+	  * Four-byte value...
+	  */
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x07) << 6) | (temp & 0x3f);
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if (ch < 0x10000)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+	}
+	else
+	  return (EOF);
+	break;
+
+    case ENCODE_UTF16BE :
+       /*
+        * Read UTF-16 big-endian char...
+	*/
+
+	if (buf->current >= buf->end)
+	  if (mxml_fd_read(buf) < 0)
+	    return (EOF);
+
+	temp = *(buf->current)++;
+
+	ch = (ch << 8) | temp;
+
+	if (mxml_bad_char(ch))
+	{
+	  mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	     ch);
+	  return (EOF);
+	}
+        else if (ch >= 0xd800 && ch <= 0xdbff)
+	{
+	 /*
+	  * Multi-word UTF-16 char...
+	  */
+
+          int lch;
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  lch = *(buf->current)++;
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  lch = (lch << 8) | temp;
+
+          if (lch < 0xdc00 || lch >= 0xdfff)
+	    return (EOF);
+
+          ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	}
+	break;
+
+    case ENCODE_UTF16LE :
+       /*
+        * Read UTF-16 little-endian char...
+	*/
+
+	if (buf->current >= buf->end)
+	  if (mxml_fd_read(buf) < 0)
+	    return (EOF);
+
+	temp = *(buf->current)++;
+
+	ch |= (temp << 8);
+
+        if (mxml_bad_char(ch))
+	{
+	  mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	     ch);
+	  return (EOF);
+	}
+        else if (ch >= 0xd800 && ch <= 0xdbff)
+	{
+	 /*
+	  * Multi-word UTF-16 char...
+	  */
+
+          int lch;
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  lch = *(buf->current)++;
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  lch |= (temp << 8);
+
+          if (lch < 0xdc00 || lch >= 0xdfff)
+	    return (EOF);
+
+          ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	}
+	break;
+  }
+
+#if DEBUG > 1
+  printf("mxml_fd_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+  return (ch);
+}
+
+
+/*
+ * 'mxml_fd_putc()' - Write a character to a file descriptor.
+ */
+
+static int				/* O - 0 on success, -1 on error */
+mxml_fd_putc(int  ch,			/* I - Character */
+             void *p)			/* I - File descriptor buffer */
+{
+  _mxml_fdbuf_t	*buf;			/* File descriptor buffer */
+
+
+ /*
+  * Flush the write buffer as needed...
+  */
+
+  buf = (_mxml_fdbuf_t *)p;
+
+  if (buf->current >= buf->end)
+    if (mxml_fd_write(buf) < 0)
+      return (-1);
+
+  *(buf->current)++ = ch;
+
+ /*
+  * Return successfully...
+  */
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_fd_read()' - Read a buffer of data from a file descriptor.
+ */
+
+static int				/* O - 0 on success, -1 on error */
+mxml_fd_read(_mxml_fdbuf_t *buf)		/* I - File descriptor buffer */
+{
+  int	bytes;				/* Bytes read... */
+
+
+ /*
+  * Range check input...
+  */
+
+  if (!buf)
+    return (-1);
+
+ /*
+  * Read from the file descriptor...
+  */
+
+  while ((bytes = read(buf->fd, buf->buffer, sizeof(buf->buffer))) < 0)
+#ifdef EINTR
+    if (errno != EAGAIN && errno != EINTR)
+#else
+    if (errno != EAGAIN)
+#endif /* EINTR */
+      return (-1);
+
+  if (bytes == 0)
+    return (-1);
+
+ /*
+  * Update the pointers and return success...
+  */
+
+  buf->current = buf->buffer;
+  buf->end     = buf->buffer + bytes;
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_fd_write()' - Write a buffer of data to a file descriptor.
+ */
+
+static int				/* O - 0 on success, -1 on error */
+mxml_fd_write(_mxml_fdbuf_t *buf)	/* I - File descriptor buffer */
+{
+  int		bytes;			/* Bytes written */
+  unsigned char	*ptr;			/* Pointer into buffer */
+
+
+ /*
+  * Range check...
+  */
+
+  if (!buf)
+    return (-1);
+
+ /*
+  * Return 0 if there is nothing to write...
+  */
+
+  if (buf->current == buf->buffer)
+    return (0);
+
+ /*
+  * Loop until we have written everything...
+  */
+
+  for (ptr = buf->buffer; ptr < buf->current; ptr += bytes)
+    if ((bytes = write(buf->fd, ptr, buf->current - ptr)) < 0)
+      return (-1);
+
+ /*
+  * All done, reset pointers and return success...
+  */
+
+  buf->current = buf->buffer;
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_file_getc()' - Get a character from a file.
+ */
+
+static int				/* O  - Character or EOF */
+mxml_file_getc(void *p,			/* I  - Pointer to file */
+               int  *encoding)		/* IO - Encoding */
+{
+  int	ch,				/* Character from file */
+	temp;				/* Temporary character */
+  FILE	*fp;				/* Pointer to file */
+
+
+ /*
+  * Read a character from the file and see if it is EOF or ASCII...
+  */
+
+  fp = (FILE *)p;
+  ch = getc(fp);
+
+  if (ch == EOF)
+    return (EOF);
+
+  switch (*encoding)
+  {
+    case ENCODE_UTF8 :
+       /*
+	* Got a UTF-8 character; convert UTF-8 to Unicode and return...
+	*/
+
+	if (!(ch & 0x80))
+	{
+	  if (mxml_bad_char(ch))
+	  {
+	    mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	       ch);
+	    return (EOF);
+	  }
+
+#if DEBUG > 1
+          printf("mxml_file_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	  return (ch);
+        }
+	else if (ch == 0xfe)
+	{
+	 /*
+	  * UTF-16 big-endian BOM?
+	  */
+
+          ch = getc(fp);
+	  if (ch != 0xff)
+	    return (EOF);
+
+	  *encoding = ENCODE_UTF16BE;
+
+	  return (mxml_file_getc(p, encoding));
+	}
+	else if (ch == 0xff)
+	{
+	 /*
+	  * UTF-16 little-endian BOM?
+	  */
+
+          ch = getc(fp);
+	  if (ch != 0xfe)
+	    return (EOF);
+
+	  *encoding = ENCODE_UTF16LE;
+
+	  return (mxml_file_getc(p, encoding));
+	}
+	else if ((ch & 0xe0) == 0xc0)
+	{
+	 /*
+	  * Two-byte value...
+	  */
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x1f) << 6) | (temp & 0x3f);
+
+	  if (ch < 0x80)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+	}
+	else if ((ch & 0xf0) == 0xe0)
+	{
+	 /*
+	  * Three-byte value...
+	  */
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x0f) << 6) | (temp & 0x3f);
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if (ch < 0x800)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+
+         /*
+	  * Ignore (strip) Byte Order Mark (BOM)...
+	  */
+
+	  if (ch == 0xfeff)
+	    return (mxml_file_getc(p, encoding));
+	}
+	else if ((ch & 0xf8) == 0xf0)
+	{
+	 /*
+	  * Four-byte value...
+	  */
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x07) << 6) | (temp & 0x3f);
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if (ch < 0x10000)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+	}
+	else
+	  return (EOF);
+	break;
+
+    case ENCODE_UTF16BE :
+       /*
+        * Read UTF-16 big-endian char...
+	*/
+
+	ch = (ch << 8) | getc(fp);
+
+	if (mxml_bad_char(ch))
+	{
+	  mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	     ch);
+	  return (EOF);
+	}
+        else if (ch >= 0xd800 && ch <= 0xdbff)
+	{
+	 /*
+	  * Multi-word UTF-16 char...
+	  */
+
+          int lch = getc(fp);
+          lch = (lch << 8) | getc(fp);
+
+          if (lch < 0xdc00 || lch >= 0xdfff)
+	    return (EOF);
+
+          ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	}
+	break;
+
+    case ENCODE_UTF16LE :
+       /*
+        * Read UTF-16 little-endian char...
+	*/
+
+	ch |= (getc(fp) << 8);
+
+        if (mxml_bad_char(ch))
+	{
+	  mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	     ch);
+	  return (EOF);
+	}
+        else if (ch >= 0xd800 && ch <= 0xdbff)
+	{
+	 /*
+	  * Multi-word UTF-16 char...
+	  */
+
+          int lch = getc(fp);
+          lch |= (getc(fp) << 8);
+
+          if (lch < 0xdc00 || lch >= 0xdfff)
+	    return (EOF);
+
+          ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	}
+	break;
+  }
+
+#if DEBUG > 1
+  printf("mxml_file_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+  return (ch);
+}
+
+
+/*
+ * 'mxml_file_putc()' - Write a character to a file.
+ */
+
+static int				/* O - 0 on success, -1 on failure */
+mxml_file_putc(int  ch,			/* I - Character to write */
+               void *p)			/* I - Pointer to file */
+{
+  return (putc(ch, (FILE *)p) == EOF ? -1 : 0);
+}
+
+
+/*
+ * 'mxml_get_entity()' - Get the character corresponding to an entity...
+ */
+
+static int				/* O  - Character value or EOF on error */
+mxml_get_entity(mxml_node_t *parent,	/* I  - Parent node */
+		void        *p,		/* I  - Pointer to source */
+		int         *encoding,	/* IO - Character encoding */
+                int         (*getc_cb)(void *, int *))
+					/* I  - Get character function */
+{
+  int	ch;				/* Current character */
+  char	entity[64],			/* Entity string */
+	*entptr;			/* Pointer into entity */
+
+
+  entptr = entity;
+
+  while ((ch = (*getc_cb)(p, encoding)) != EOF)
+    if (ch > 126 || (!isalnum(ch) && ch != '#'))
+      break;
+    else if (entptr < (entity + sizeof(entity) - 1))
+      *entptr++ = ch;
+    else
+    {
+      mxml_error("Entity name too long under parent <%s>!",
+	         parent ? parent->value.element.name : "null");
+      break;
+    }
+
+  *entptr = '\0';
+
+  if (ch != ';')
+  {
+    mxml_error("Character entity \"%s\" not terminated under parent <%s>!",
+	       entity, parent ? parent->value.element.name : "null");
+    return (EOF);
+  }
+
+  if (entity[0] == '#')
+  {
+    if (entity[1] == 'x')
+      ch = strtol(entity + 2, NULL, 16);
+    else
+      ch = strtol(entity + 1, NULL, 10);
+  }
+  else if ((ch = mxmlEntityGetValue(entity)) < 0)
+    mxml_error("Entity name \"%s;\" not supported under parent <%s>!",
+	       entity, parent ? parent->value.element.name : "null");
+
+  if (mxml_bad_char(ch))
+  {
+    mxml_error("Bad control character 0x%02x under parent <%s> not allowed by XML standard!",
+               ch, parent ? parent->value.element.name : "null");
+    return (EOF);
+  }
+
+  return (ch);
+}
+
+
+/*
+ * 'mxml_load_data()' - Load data into an XML node tree.
+ */
+
+static mxml_node_t *			/* O - First node or NULL if the file could not be read. */
+mxml_load_data(
+    mxml_node_t     *top,		/* I - Top node */
+    void            *p,			/* I - Pointer to data */
+    mxml_load_cb_t  cb,			/* I - Callback function or MXML_NO_CALLBACK */
+    _mxml_getc_cb_t getc_cb,		/* I - Read function */
+    mxml_sax_cb_t   sax_cb,		/* I - SAX callback or MXML_NO_CALLBACK */
+    void            *sax_data)		/* I - SAX user data */
+{
+  mxml_node_t	*node,			/* Current node */
+		*first,			/* First node added */
+		*parent;		/* Current parent node */
+  int		ch,			/* Character from file */
+		whitespace;		/* Non-zero if whitespace seen */
+  char		*buffer,		/* String buffer */
+		*bufptr;		/* Pointer into buffer */
+  int		bufsize;		/* Size of buffer */
+  mxml_type_t	type;			/* Current node type */
+  int		encoding;		/* Character encoding */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+  static const char * const types[] =	/* Type strings... */
+		{
+		  "MXML_ELEMENT",	/* XML element with attributes */
+		  "MXML_INTEGER",	/* Integer value */
+		  "MXML_OPAQUE",	/* Opaque string */
+		  "MXML_REAL",		/* Real value */
+		  "MXML_TEXT",		/* Text fragment */
+		  "MXML_CUSTOM"		/* Custom data */
+		};
+
+
+ /*
+  * Read elements and other nodes from the file...
+  */
+
+  if ((buffer = malloc(64)) == NULL)
+  {
+    mxml_error("Unable to allocate string buffer!");
+    return (NULL);
+  }
+
+  bufsize    = 64;
+  bufptr     = buffer;
+  parent     = top;
+  first      = NULL;
+  whitespace = 0;
+  encoding   = ENCODE_UTF8;
+
+  if (cb && parent)
+    type = (*cb)(parent);
+  else if (parent)
+    type = MXML_TEXT;
+  else
+    type = MXML_IGNORE;
+
+  while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+  {
+    if ((ch == '<' ||
+         (mxml_isspace(ch) && type != MXML_OPAQUE && type != MXML_CUSTOM)) &&
+        bufptr > buffer)
+    {
+     /*
+      * Add a new value node...
+      */
+
+      *bufptr = '\0';
+
+      switch (type)
+      {
+	case MXML_INTEGER :
+            node = mxmlNewInteger(parent, strtol(buffer, &bufptr, 0));
+	    break;
+
+	case MXML_OPAQUE :
+            node = mxmlNewOpaque(parent, buffer);
+	    break;
+
+	case MXML_REAL :
+            node = mxmlNewReal(parent, strtod(buffer, &bufptr));
+	    break;
+
+	case MXML_TEXT :
+            node = mxmlNewText(parent, whitespace, buffer);
+	    break;
+
+	case MXML_CUSTOM :
+	    if (global->custom_load_cb)
+	    {
+	     /*
+	      * Use the callback to fill in the custom data...
+	      */
+
+              node = mxmlNewCustom(parent, NULL, NULL);
+
+	      if ((*global->custom_load_cb)(node, buffer))
+	      {
+	        mxml_error("Bad custom value '%s' in parent <%s>!",
+		           buffer, parent ? parent->value.element.name : "null");
+		mxmlDelete(node);
+		node = NULL;
+	      }
+	      break;
+	    }
+
+        default : /* Ignore... */
+	    node = NULL;
+	    break;
+      }
+
+      if (*bufptr)
+      {
+       /*
+        * Bad integer/real number value...
+	*/
+
+        mxml_error("Bad %s value '%s' in parent <%s>!",
+	           type == MXML_INTEGER ? "integer" : "real", buffer,
+		   parent ? parent->value.element.name : "null");
+	break;
+      }
+
+      bufptr     = buffer;
+      whitespace = mxml_isspace(ch) && type == MXML_TEXT;
+
+      if (!node && type != MXML_IGNORE)
+      {
+       /*
+	* Print error and return...
+	*/
+
+	mxml_error("Unable to add value node of type %s to parent <%s>!",
+	           types[type], parent ? parent->value.element.name : "null");
+	goto error;
+      }
+
+      if (sax_cb)
+      {
+        (*sax_cb)(node, MXML_SAX_DATA, sax_data);
+
+        if (!mxmlRelease(node))
+          node = NULL;
+      }
+
+      if (!first && node)
+        first = node;
+    }
+    else if (mxml_isspace(ch) && type == MXML_TEXT)
+      whitespace = 1;
+
+   /*
+    * Add lone whitespace node if we have an element and existing
+    * whitespace...
+    */
+
+    if (ch == '<' && whitespace && type == MXML_TEXT)
+    {
+      if (parent)
+      {
+	node = mxmlNewText(parent, whitespace, "");
+
+	if (sax_cb)
+	{
+	  (*sax_cb)(node, MXML_SAX_DATA, sax_data);
+
+	  if (!mxmlRelease(node))
+	    node = NULL;
+	}
+
+	if (!first && node)
+	  first = node;
+      }
+
+      whitespace = 0;
+    }
+
+    if (ch == '<')
+    {
+     /*
+      * Start of open/close tag...
+      */
+
+      bufptr = buffer;
+
+      while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+        if (mxml_isspace(ch) || ch == '>' || (ch == '/' && bufptr > buffer))
+	  break;
+	else if (ch == '<')
+	{
+	  mxml_error("Bare < in element!");
+	  goto error;
+	}
+	else if (ch == '&')
+	{
+	  if ((ch = mxml_get_entity(parent, p, &encoding, getc_cb)) == EOF)
+	    goto error;
+
+	  if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	    goto error;
+	}
+	else if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	  goto error;
+	else if (((bufptr - buffer) == 1 && buffer[0] == '?') ||
+	         ((bufptr - buffer) == 3 && !strncmp(buffer, "!--", 3)) ||
+	         ((bufptr - buffer) == 8 && !strncmp(buffer, "![CDATA[", 8)))
+	  break;
+
+      *bufptr = '\0';
+
+      if (!strcmp(buffer, "!--"))
+      {
+       /*
+        * Gather rest of comment...
+	*/
+
+	while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+	{
+	  if (ch == '>' && bufptr > (buffer + 4) &&
+	      bufptr[-3] != '-' && bufptr[-2] == '-' && bufptr[-1] == '-')
+	    break;
+	  else if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	    goto error;
+	}
+
+       /*
+        * Error out if we didn't get the whole comment...
+	*/
+
+        if (ch != '>')
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Early EOF in comment node!");
+	  goto error;
+	}
+
+
+       /*
+        * Otherwise add this as an element under the current parent...
+	*/
+
+	*bufptr = '\0';
+
+        if (!parent && first)
+	{
+	 /*
+	  * There can only be one root element!
+	  */
+
+	  mxml_error("<%s> cannot be a second root node after <%s>",
+	             buffer, first->value.element.name);
+          goto error;
+	}
+
+	if ((node = mxmlNewElement(parent, buffer)) == NULL)
+	{
+	 /*
+	  * Just print error for now...
+	  */
+
+	  mxml_error("Unable to add comment node to parent <%s>!",
+	             parent ? parent->value.element.name : "null");
+	  break;
+	}
+
+        if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_COMMENT, sax_data);
+
+          if (!mxmlRelease(node))
+            node = NULL;
+        }
+
+	if (node && !first)
+	  first = node;
+      }
+      else if (!strcmp(buffer, "![CDATA["))
+      {
+       /*
+        * Gather CDATA section...
+	*/
+
+	while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+	{
+	  if (ch == '>' && !strncmp(bufptr - 2, "]]", 2))
+	    break;
+	  else if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	    goto error;
+	}
+
+       /*
+        * Error out if we didn't get the whole comment...
+	*/
+
+        if (ch != '>')
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Early EOF in CDATA node!");
+	  goto error;
+	}
+
+
+       /*
+        * Otherwise add this as an element under the current parent...
+	*/
+
+	*bufptr = '\0';
+
+        if (!parent && first)
+	{
+	 /*
+	  * There can only be one root element!
+	  */
+
+	  mxml_error("<%s> cannot be a second root node after <%s>",
+	             buffer, first->value.element.name);
+          goto error;
+	}
+
+	if ((node = mxmlNewElement(parent, buffer)) == NULL)
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Unable to add CDATA node to parent <%s>!",
+	             parent ? parent->value.element.name : "null");
+	  goto error;
+	}
+
+        if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_CDATA, sax_data);
+
+          if (!mxmlRelease(node))
+            node = NULL;
+        }
+
+	if (node && !first)
+	  first = node;
+      }
+      else if (buffer[0] == '?')
+      {
+       /*
+        * Gather rest of processing instruction...
+	*/
+
+	while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+	{
+	  if (ch == '>' && bufptr > buffer && bufptr[-1] == '?')
+	    break;
+	  else if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	    goto error;
+	}
+
+       /*
+        * Error out if we didn't get the whole processing instruction...
+	*/
+
+        if (ch != '>')
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Early EOF in processing instruction node!");
+	  goto error;
+	}
+
+       /*
+        * Otherwise add this as an element under the current parent...
+	*/
+
+	*bufptr = '\0';
+
+        if (!parent && first)
+	{
+	 /*
+	  * There can only be one root element!
+	  */
+
+	  mxml_error("<%s> cannot be a second root node after <%s>",
+	             buffer, first->value.element.name);
+          goto error;
+	}
+
+	if ((node = mxmlNewElement(parent, buffer)) == NULL)
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Unable to add processing instruction node to parent <%s>!",
+	             parent ? parent->value.element.name : "null");
+	  goto error;
+	}
+
+        if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_DIRECTIVE, sax_data);
+
+          if (!mxmlRelease(node))
+            node = NULL;
+        }
+
+        if (node)
+	{
+	  if (!first)
+            first = node;
+
+	  if (!parent)
+	  {
+	    parent = node;
+
+	    if (cb)
+	      type = (*cb)(parent);
+	  }
+	}
+      }
+      else if (buffer[0] == '!')
+      {
+       /*
+        * Gather rest of declaration...
+	*/
+
+	do
+	{
+	  if (ch == '>')
+	    break;
+	  else
+	  {
+            if (ch == '&')
+	      if ((ch = mxml_get_entity(parent, p, &encoding, getc_cb)) == EOF)
+		goto error;
+
+	    if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	      goto error;
+	  }
+	}
+        while ((ch = (*getc_cb)(p, &encoding)) != EOF);
+
+       /*
+        * Error out if we didn't get the whole declaration...
+	*/
+
+        if (ch != '>')
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Early EOF in declaration node!");
+	  goto error;
+	}
+
+       /*
+        * Otherwise add this as an element under the current parent...
+	*/
+
+	*bufptr = '\0';
+
+        if (!parent && first)
+	{
+	 /*
+	  * There can only be one root element!
+	  */
+
+	  mxml_error("<%s> cannot be a second root node after <%s>",
+	             buffer, first->value.element.name);
+          goto error;
+	}
+
+	if ((node = mxmlNewElement(parent, buffer)) == NULL)
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Unable to add declaration node to parent <%s>!",
+	             parent ? parent->value.element.name : "null");
+	  goto error;
+	}
+
+        if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_DIRECTIVE, sax_data);
+
+          if (!mxmlRelease(node))
+            node = NULL;
+        }
+
+        if (node)
+	{
+	  if (!first)
+            first = node;
+
+	  if (!parent)
+	  {
+	    parent = node;
+
+	    if (cb)
+	      type = (*cb)(parent);
+	  }
+	}
+      }
+      else if (buffer[0] == '/')
+      {
+       /*
+        * Handle close tag...
+	*/
+
+        if (!parent || strcmp(buffer + 1, parent->value.element.name))
+	{
+	 /*
+	  * Close tag doesn't match tree; print an error for now...
+	  */
+
+	  mxml_error("Mismatched close tag <%s> under parent <%s>!",
+	             buffer, parent ? parent->value.element.name : "(null)");
+          goto error;
+	}
+
+       /*
+        * Keep reading until we see >...
+	*/
+
+        while (ch != '>' && ch != EOF)
+	  ch = (*getc_cb)(p, &encoding);
+
+        node   = parent;
+        parent = parent->parent;
+
+        if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_ELEMENT_CLOSE, sax_data);
+
+          if (!mxmlRelease(node) && first == node)
+	    first = NULL;
+        }
+
+       /*
+	* Ascend into the parent and set the value type as needed...
+	*/
+
+	if (cb && parent)
+	  type = (*cb)(parent);
+      }
+      else
+      {
+       /*
+        * Handle open tag...
+	*/
+
+        if (!parent && first)
+	{
+	 /*
+	  * There can only be one root element!
+	  */
+
+	  mxml_error("<%s> cannot be a second root node after <%s>",
+	             buffer, first->value.element.name);
+          goto error;
+	}
+
+        if ((node = mxmlNewElement(parent, buffer)) == NULL)
+	{
+	 /*
+	  * Just print error for now...
+	  */
+
+	  mxml_error("Unable to add element node to parent <%s>!",
+	             parent ? parent->value.element.name : "null");
+	  goto error;
+	}
+
+        if (mxml_isspace(ch))
+        {
+	  if ((ch = mxml_parse_element(node, p, &encoding, getc_cb)) == EOF)
+	    goto error;
+        }
+        else if (ch == '/')
+	{
+	  if ((ch = (*getc_cb)(p, &encoding)) != '>')
+	  {
+	    mxml_error("Expected > but got '%c' instead for element <%s/>!",
+	               ch, buffer);
+            mxmlDelete(node);
+            goto error;
+	  }
+
+	  ch = '/';
+	}
+
+        if (sax_cb)
+          (*sax_cb)(node, MXML_SAX_ELEMENT_OPEN, sax_data);
+
+        if (!first)
+	  first = node;
+
+	if (ch == EOF)
+	  break;
+
+        if (ch != '/')
+	{
+	 /*
+	  * Descend into this node, setting the value type as needed...
+	  */
+
+	  parent = node;
+
+	  if (cb && parent)
+	    type = (*cb)(parent);
+	}
+        else if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_ELEMENT_CLOSE, sax_data);
+
+          if (!mxmlRelease(node) && first == node)
+            first = NULL;
+        }
+      }
+
+      bufptr  = buffer;
+    }
+    else if (ch == '&')
+    {
+     /*
+      * Add character entity to current buffer...
+      */
+
+      if ((ch = mxml_get_entity(parent, p, &encoding, getc_cb)) == EOF)
+	goto error;
+
+      if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	goto error;
+    }
+    else if (type == MXML_OPAQUE || type == MXML_CUSTOM || !mxml_isspace(ch))
+    {
+     /*
+      * Add character to current buffer...
+      */
+
+      if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	goto error;
+    }
+  }
+
+ /*
+  * Free the string buffer - we don't need it anymore...
+  */
+
+  free(buffer);
+
+ /*
+  * Find the top element and return it...
+  */
+
+  if (parent)
+  {
+    node = parent;
+
+    while (parent != top && parent->parent)
+      parent = parent->parent;
+
+    if (node != parent)
+    {
+      mxml_error("Missing close tag </%s> under parent <%s>!",
+	         node->value.element.name,
+		 node->parent ? node->parent->value.element.name : "(null)");
+
+      mxmlDelete(first);
+
+      return (NULL);
+    }
+  }
+
+  if (parent)
+    return (parent);
+  else
+    return (first);
+
+ /*
+  * Common error return...
+  */
+
+error:
+
+  mxmlDelete(first);
+
+  free(buffer);
+
+  return (NULL);
+}
+
+
+/*
+ * 'mxml_parse_element()' - Parse an element for any attributes...
+ */
+
+static int				/* O  - Terminating character */
+mxml_parse_element(
+    mxml_node_t     *node,		/* I  - Element node */
+    void            *p,			/* I  - Data to read from */
+    int             *encoding,		/* IO - Encoding */
+    _mxml_getc_cb_t getc_cb)		/* I  - Data callback */
+{
+  int	ch,				/* Current character in file */
+	quote;				/* Quoting character */
+  char	*name,				/* Attribute name */
+	*value,				/* Attribute value */
+	*ptr;				/* Pointer into name/value */
+  int	namesize,			/* Size of name string */
+	valsize;			/* Size of value string */
+
+
+ /*
+  * Initialize the name and value buffers...
+  */
+
+  if ((name = malloc(64)) == NULL)
+  {
+    mxml_error("Unable to allocate memory for name!");
+    return (EOF);
+  }
+
+  namesize = 64;
+
+  if ((value = malloc(64)) == NULL)
+  {
+    free(name);
+    mxml_error("Unable to allocate memory for value!");
+    return (EOF);
+  }
+
+  valsize = 64;
+
+ /*
+  * Loop until we hit a >, /, ?, or EOF...
+  */
+
+  while ((ch = (*getc_cb)(p, encoding)) != EOF)
+  {
+#if DEBUG > 1
+    fprintf(stderr, "parse_element: ch='%c'\n", ch);
+#endif /* DEBUG > 1 */
+
+   /*
+    * Skip leading whitespace...
+    */
+
+    if (mxml_isspace(ch))
+      continue;
+
+   /*
+    * Stop at /, ?, or >...
+    */
+
+    if (ch == '/' || ch == '?')
+    {
+     /*
+      * Grab the > character and print an error if it isn't there...
+      */
+
+      quote = (*getc_cb)(p, encoding);
+
+      if (quote != '>')
+      {
+        mxml_error("Expected '>' after '%c' for element %s, but got '%c'!",
+	           ch, node->value.element.name, quote);
+        goto error;
+      }
+
+      break;
+    }
+    else if (ch == '<')
+    {
+      mxml_error("Bare < in element %s!", node->value.element.name);
+      goto error;
+    }
+    else if (ch == '>')
+      break;
+
+   /*
+    * Read the attribute name...
+    */
+
+    name[0] = ch;
+    ptr     = name + 1;
+
+    if (ch == '\"' || ch == '\'')
+    {
+     /*
+      * Name is in quotes, so get a quoted string...
+      */
+
+      quote = ch;
+
+      while ((ch = (*getc_cb)(p, encoding)) != EOF)
+      {
+        if (ch == '&')
+	  if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF)
+	    goto error;
+
+	if (mxml_add_char(ch, &ptr, &name, &namesize))
+	  goto error;
+
+	if (ch == quote)
+          break;
+      }
+    }
+    else
+    {
+     /*
+      * Grab an normal, non-quoted name...
+      */
+
+      while ((ch = (*getc_cb)(p, encoding)) != EOF)
+	if (mxml_isspace(ch) || ch == '=' || ch == '/' || ch == '>' ||
+	    ch == '?')
+          break;
+	else
+	{
+          if (ch == '&')
+	    if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF)
+	      goto error;
+
+	  if (mxml_add_char(ch, &ptr, &name, &namesize))
+	    goto error;
+	}
+    }
+
+    *ptr = '\0';
+
+    if (mxmlElementGetAttr(node, name))
+      goto error;
+
+    while (ch != EOF && mxml_isspace(ch))
+      ch = (*getc_cb)(p, encoding);
+
+    if (ch == '=')
+    {
+     /*
+      * Read the attribute value...
+      */
+
+      while ((ch = (*getc_cb)(p, encoding)) != EOF && mxml_isspace(ch));
+
+      if (ch == EOF)
+      {
+        mxml_error("Missing value for attribute '%s' in element %s!",
+	           name, node->value.element.name);
+        goto error;
+      }
+
+      if (ch == '\'' || ch == '\"')
+      {
+       /*
+        * Read quoted value...
+	*/
+
+        quote = ch;
+	ptr   = value;
+
+        while ((ch = (*getc_cb)(p, encoding)) != EOF)
+	  if (ch == quote)
+	    break;
+	  else
+	  {
+	    if (ch == '&')
+	      if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF)
+	        goto error;
+
+	    if (mxml_add_char(ch, &ptr, &value, &valsize))
+	      goto error;
+	  }
+
+        *ptr = '\0';
+      }
+      else
+      {
+       /*
+        * Read unquoted value...
+	*/
+
+	value[0] = ch;
+	ptr      = value + 1;
+
+	while ((ch = (*getc_cb)(p, encoding)) != EOF)
+	  if (mxml_isspace(ch) || ch == '=' || ch == '/' || ch == '>')
+            break;
+	  else
+	  {
+	    if (ch == '&')
+	      if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF)
+	        goto error;
+
+	    if (mxml_add_char(ch, &ptr, &value, &valsize))
+	      goto error;
+	  }
+
+        *ptr = '\0';
+      }
+
+     /*
+      * Set the attribute with the given string value...
+      */
+
+      mxmlElementSetAttr(node, name, value);
+    }
+    else
+    {
+      mxml_error("Missing value for attribute '%s' in element %s!",
+	         name, node->value.element.name);
+      goto error;
+    }
+
+   /*
+    * Check the end character...
+    */
+
+    if (ch == '/' || ch == '?')
+    {
+     /*
+      * Grab the > character and print an error if it isn't there...
+      */
+
+      quote = (*getc_cb)(p, encoding);
+
+      if (quote != '>')
+      {
+        mxml_error("Expected '>' after '%c' for element %s, but got '%c'!",
+	           ch, node->value.element.name, quote);
+        ch = EOF;
+      }
+
+      break;
+    }
+    else if (ch == '>')
+      break;
+  }
+
+ /*
+  * Free the name and value buffers and return...
+  */
+
+  free(name);
+  free(value);
+
+  return (ch);
+
+ /*
+  * Common error return point...
+  */
+
+error:
+
+  free(name);
+  free(value);
+
+  return (EOF);
+}
+
+
+/*
+ * 'mxml_string_getc()' - Get a character from a string.
+ */
+
+static int				/* O  - Character or EOF */
+mxml_string_getc(void *p,		/* I  - Pointer to file */
+                 int  *encoding)	/* IO - Encoding */
+{
+  int		ch;			/* Character */
+  const char	**s;			/* Pointer to string pointer */
+
+
+  s = (const char **)p;
+
+  if ((ch = (*s)[0] & 255) != 0 || *encoding == ENCODE_UTF16LE)
+  {
+   /*
+    * Got character; convert UTF-8 to integer and return...
+    */
+
+    (*s)++;
+
+    switch (*encoding)
+    {
+      case ENCODE_UTF8 :
+	  if (!(ch & 0x80))
+	  {
+#if DEBUG > 1
+            printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	    if (mxml_bad_char(ch))
+	    {
+	      mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        		 ch);
+	      return (EOF);
+	    }
+
+	    return (ch);
+          }
+	  else if (ch == 0xfe)
+	  {
+	   /*
+	    * UTF-16 big-endian BOM?
+	    */
+
+            if (((*s)[0] & 255) != 0xff)
+	      return (EOF);
+
+	    *encoding = ENCODE_UTF16BE;
+	    (*s)++;
+
+	    return (mxml_string_getc(p, encoding));
+	  }
+	  else if (ch == 0xff)
+	  {
+	   /*
+	    * UTF-16 little-endian BOM?
+	    */
+
+            if (((*s)[0] & 255) != 0xfe)
+	      return (EOF);
+
+	    *encoding = ENCODE_UTF16LE;
+	    (*s)++;
+
+	    return (mxml_string_getc(p, encoding));
+	  }
+	  else if ((ch & 0xe0) == 0xc0)
+	  {
+	   /*
+	    * Two-byte value...
+	    */
+
+	    if (((*s)[0] & 0xc0) != 0x80)
+              return (EOF);
+
+	    ch = ((ch & 0x1f) << 6) | ((*s)[0] & 0x3f);
+
+	    (*s)++;
+
+	    if (ch < 0x80)
+	    {
+	      mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	      return (EOF);
+	    }
+
+#if DEBUG > 1
+            printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	    return (ch);
+	  }
+	  else if ((ch & 0xf0) == 0xe0)
+	  {
+	   /*
+	    * Three-byte value...
+	    */
+
+	    if (((*s)[0] & 0xc0) != 0x80 ||
+        	((*s)[1] & 0xc0) != 0x80)
+              return (EOF);
+
+	    ch = ((((ch & 0x0f) << 6) | ((*s)[0] & 0x3f)) << 6) | ((*s)[1] & 0x3f);
+
+	    (*s) += 2;
+
+	    if (ch < 0x800)
+	    {
+	      mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	      return (EOF);
+	    }
+
+	   /*
+	    * Ignore (strip) Byte Order Mark (BOM)...
+	    */
+
+	    if (ch == 0xfeff)
+	      return (mxml_string_getc(p, encoding));
+
+#if DEBUG > 1
+            printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	    return (ch);
+	  }
+	  else if ((ch & 0xf8) == 0xf0)
+	  {
+	   /*
+	    * Four-byte value...
+	    */
+
+	    if (((*s)[0] & 0xc0) != 0x80 ||
+        	((*s)[1] & 0xc0) != 0x80 ||
+        	((*s)[2] & 0xc0) != 0x80)
+              return (EOF);
+
+	    ch = ((((((ch & 0x07) << 6) | ((*s)[0] & 0x3f)) << 6) |
+        	   ((*s)[1] & 0x3f)) << 6) | ((*s)[2] & 0x3f);
+
+	    (*s) += 3;
+
+	    if (ch < 0x10000)
+	    {
+	      mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	      return (EOF);
+	    }
+
+#if DEBUG > 1
+            printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	    return (ch);
+	  }
+	  else
+	    return (EOF);
+
+      case ENCODE_UTF16BE :
+	 /*
+          * Read UTF-16 big-endian char...
+	  */
+
+	  ch = (ch << 8) | ((*s)[0] & 255);
+	  (*s) ++;
+
+          if (mxml_bad_char(ch))
+	  {
+	    mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	       ch);
+	    return (EOF);
+	  }
+          else if (ch >= 0xd800 && ch <= 0xdbff)
+	  {
+	   /*
+	    * Multi-word UTF-16 char...
+	    */
+
+            int lch;			/* Lower word */
+
+
+            if (!(*s)[0])
+	      return (EOF);
+
+            lch = (((*s)[0] & 255) << 8) | ((*s)[1] & 255);
+	    (*s) += 2;
+
+            if (lch < 0xdc00 || lch >= 0xdfff)
+	      return (EOF);
+
+            ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	  }
+
+#if DEBUG > 1
+          printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	  return (ch);
+
+      case ENCODE_UTF16LE :
+	 /*
+          * Read UTF-16 little-endian char...
+	  */
+
+	  ch = ch | (((*s)[0] & 255) << 8);
+
+	  if (!ch)
+	  {
+	    (*s) --;
+	    return (EOF);
+	  }
+
+	  (*s) ++;
+
+          if (mxml_bad_char(ch))
+	  {
+	    mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	       ch);
+	    return (EOF);
+	  }
+          else if (ch >= 0xd800 && ch <= 0xdbff)
+	  {
+	   /*
+	    * Multi-word UTF-16 char...
+	    */
+
+            int lch;			/* Lower word */
+
+
+            if (!(*s)[1])
+	      return (EOF);
+
+            lch = (((*s)[1] & 255) << 8) | ((*s)[0] & 255);
+	    (*s) += 2;
+
+            if (lch < 0xdc00 || lch >= 0xdfff)
+	      return (EOF);
+
+            ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	  }
+
+#if DEBUG > 1
+          printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	  return (ch);
+    }
+  }
+
+  return (EOF);
+}
+
+
+/*
+ * 'mxml_string_putc()' - Write a character to a string.
+ */
+
+static int				/* O - 0 on success, -1 on failure */
+mxml_string_putc(int  ch,		/* I - Character to write */
+                 void *p)		/* I - Pointer to string pointers */
+{
+  char	**pp;				/* Pointer to string pointers */
+
+
+  pp = (char **)p;
+
+  if (pp[2] == 0) {
+    if (pp[0] < pp[1])
+      pp[0][0] = ch;
+    else
+      pp[2] = (char *)1;
+  }
+
+  pp[0] ++;
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_write_name()' - Write a name string.
+ */
+
+static int				/* O - 0 on success, -1 on failure */
+mxml_write_name(const char *s,		/* I - Name to write */
+                void       *p,		/* I - Write pointer */
+		int        (*putc_cb)(int, void *))
+					/* I - Write callback */
+{
+  char		quote;			/* Quote character */
+  const char	*name;			/* Entity name */
+
+
+  if (*s == '\"' || *s == '\'')
+  {
+   /*
+    * Write a quoted name string...
+    */
+
+    if ((*putc_cb)(*s, p) < 0)
+      return (-1);
+
+    quote = *s++;
+
+    while (*s && *s != quote)
+    {
+      if ((name = mxmlEntityGetName(*s)) != NULL)
+      {
+	if ((*putc_cb)('&', p) < 0)
+          return (-1);
+
+        while (*name)
+	{
+	  if ((*putc_cb)(*name, p) < 0)
+            return (-1);
+
+          name ++;
+	}
+
+	if ((*putc_cb)(';', p) < 0)
+          return (-1);
+      }
+      else if ((*putc_cb)(*s, p) < 0)
+	return (-1);
+
+      s ++;
+    }
+
+   /*
+    * Write the end quote...
+    */
+
+    if ((*putc_cb)(quote, p) < 0)
+      return (-1);
+  }
+  else
+  {
+   /*
+    * Write a non-quoted name string...
+    */
+
+    while (*s)
+    {
+      if ((*putc_cb)(*s, p) < 0)
+	return (-1);
+
+      s ++;
+    }
+  }
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_write_node()' - Save an XML node to a file.
+ */
+
+static int				/* O - Column or -1 on error */
+mxml_write_node(mxml_node_t     *node,	/* I - Node to write */
+                void            *p,	/* I - File to write to */
+	        mxml_save_cb_t  cb,	/* I - Whitespace callback */
+		int             col,	/* I - Current column */
+		_mxml_putc_cb_t putc_cb,/* I - Output callback */
+		_mxml_global_t  *global)/* I - Global data */
+{
+  int		i,			/* Looping var */
+		width;			/* Width of attr + value */
+  mxml_attr_t	*attr;			/* Current attribute */
+  char		s[255];			/* Temporary string */
+
+
+ /*
+  * Print the node value...
+  */
+
+  switch (node->type)
+  {
+    case MXML_ELEMENT :
+	col = mxml_write_ws(node, p, cb, MXML_WS_BEFORE_OPEN, col, putc_cb);
+
+	if ((*putc_cb)('<', p) < 0)
+	  return (-1);
+	if (node->value.element.name[0] == '?' ||
+	    !strncmp(node->value.element.name, "!--", 3) ||
+	    !strncmp(node->value.element.name, "![CDATA[", 8))
+	{
+	 /*
+	  * Comments, CDATA, and processing instructions do not
+	  * use character entities.
+	  */
+
+	  const char	*ptr;		/* Pointer into name */
+
+
+	  for (ptr = node->value.element.name; *ptr; ptr ++)
+	    if ((*putc_cb)(*ptr, p) < 0)
+	      return (-1);
+	}
+	else if (mxml_write_name(node->value.element.name, p, putc_cb) < 0)
+	  return (-1);
+
+	col += strlen(node->value.element.name) + 1;
+
+	for (i = node->value.element.num_attrs, attr = node->value.element.attrs;
+	     i > 0;
+	     i --, attr ++)
+	{
+	  width = strlen(attr->name);
+
+	  if (attr->value)
+	    width += strlen(attr->value) + 3;
+
+	  if (global->wrap > 0 && (col + width) > global->wrap)
+	  {
+	    if ((*putc_cb)('\n', p) < 0)
+	      return (-1);
+
+	    col = 0;
+	  }
+	  else
+	  {
+	    if ((*putc_cb)(' ', p) < 0)
+	      return (-1);
+
+	    col ++;
+	  }
+
+	  if (mxml_write_name(attr->name, p, putc_cb) < 0)
+	    return (-1);
+
+	  if (attr->value)
+	  {
+	    if ((*putc_cb)('=', p) < 0)
+	      return (-1);
+	    if ((*putc_cb)('\"', p) < 0)
+	      return (-1);
+	    if (mxml_write_string(attr->value, p, putc_cb) < 0)
+	      return (-1);
+	    if ((*putc_cb)('\"', p) < 0)
+	      return (-1);
+	  }
+
+	  col += width;
+	}
+
+	if (node->child)
+	{
+	 /*
+	  * Write children...
+	  */
+
+	  mxml_node_t *child;		/* Current child */
+
+
+	  if ((*putc_cb)('>', p) < 0)
+	    return (-1);
+	  else
+	    col ++;
+
+	  col = mxml_write_ws(node, p, cb, MXML_WS_AFTER_OPEN, col, putc_cb);
+
+          for (child = node->child; child; child = child->next)
+	  {
+	    if ((col = mxml_write_node(child, p, cb, col, putc_cb, global)) < 0)
+	      return (-1);
+	  }
+
+	 /*
+	  * The ? and ! elements are special-cases and have no end tags...
+	  */
+
+	  if (node->value.element.name[0] != '!' &&
+	      node->value.element.name[0] != '?')
+	  {
+	    col = mxml_write_ws(node, p, cb, MXML_WS_BEFORE_CLOSE, col, putc_cb);
+
+	    if ((*putc_cb)('<', p) < 0)
+	      return (-1);
+	    if ((*putc_cb)('/', p) < 0)
+	      return (-1);
+	    if (mxml_write_string(node->value.element.name, p, putc_cb) < 0)
+	      return (-1);
+	    if ((*putc_cb)('>', p) < 0)
+	      return (-1);
+
+	    col += strlen(node->value.element.name) + 3;
+
+	    col = mxml_write_ws(node, p, cb, MXML_WS_AFTER_CLOSE, col, putc_cb);
+	  }
+	}
+	else if (node->value.element.name[0] == '!' ||
+		 node->value.element.name[0] == '?')
+	{
+	 /*
+	  * The ? and ! elements are special-cases...
+	  */
+
+	  if ((*putc_cb)('>', p) < 0)
+	    return (-1);
+	  else
+	    col ++;
+
+	  col = mxml_write_ws(node, p, cb, MXML_WS_AFTER_OPEN, col, putc_cb);
+	}
+	else
+	{
+	  if ((*putc_cb)(' ', p) < 0)
+	    return (-1);
+	  if ((*putc_cb)('/', p) < 0)
+	    return (-1);
+	  if ((*putc_cb)('>', p) < 0)
+	    return (-1);
+
+	  col += 3;
+
+	  col = mxml_write_ws(node, p, cb, MXML_WS_AFTER_OPEN, col, putc_cb);
+	}
+	break;
+
+    case MXML_INTEGER :
+	if (node->prev)
+	{
+	  if (global->wrap > 0 && col > global->wrap)
+	  {
+	    if ((*putc_cb)('\n', p) < 0)
+	      return (-1);
+
+	    col = 0;
+	  }
+	  else if ((*putc_cb)(' ', p) < 0)
+	    return (-1);
+	  else
+	    col ++;
+	}
+
+	sprintf(s, "%d", node->value.integer);
+	if (mxml_write_string(s, p, putc_cb) < 0)
+	  return (-1);
+
+	col += strlen(s);
+	break;
+
+    case MXML_OPAQUE :
+	if (mxml_write_string(node->value.opaque, p, putc_cb) < 0)
+	  return (-1);
+
+	col += strlen(node->value.opaque);
+	break;
+
+    case MXML_REAL :
+	if (node->prev)
+	{
+	  if (global->wrap > 0 && col > global->wrap)
+	  {
+	    if ((*putc_cb)('\n', p) < 0)
+	      return (-1);
+
+	    col = 0;
+	  }
+	  else if ((*putc_cb)(' ', p) < 0)
+	    return (-1);
+	  else
+	    col ++;
+	}
+
+	sprintf(s, "%f", node->value.real);
+	if (mxml_write_string(s, p, putc_cb) < 0)
+	  return (-1);
+
+	col += strlen(s);
+	break;
+
+    case MXML_TEXT :
+	if (node->value.text.whitespace && col > 0)
+	{
+	  if (global->wrap > 0 && col > global->wrap)
+	  {
+	    if ((*putc_cb)('\n', p) < 0)
+	      return (-1);
+
+	    col = 0;
+	  }
+	  else if ((*putc_cb)(' ', p) < 0)
+	    return (-1);
+	  else
+	    col ++;
+	}
+
+	if (mxml_write_string(node->value.text.string, p, putc_cb) < 0)
+	  return (-1);
+
+	col += strlen(node->value.text.string);
+	break;
+
+    case MXML_CUSTOM :
+	if (global->custom_save_cb)
+	{
+	  char	*data;		/* Custom data string */
+	  const char	*newline;	/* Last newline in string */
+
+
+	  if ((data = (*global->custom_save_cb)(node)) == NULL)
+	    return (-1);
+
+	  if (mxml_write_string(data, p, putc_cb) < 0)
+	    return (-1);
+
+	  if ((newline = strrchr(data, '\n')) == NULL)
+	    col += strlen(data);
+	  else
+	    col = strlen(newline);
+
+	  free(data);
+	  break;
+	}
+
+    default : /* Should never happen */
+	return (-1);
+  }
+
+  return (col);
+}
+
+
+/*
+ * 'mxml_write_string()' - Write a string, escaping & and < as needed.
+ */
+
+static int				/* O - 0 on success, -1 on failure */
+mxml_write_string(
+    const char      *s,			/* I - String to write */
+    void            *p,			/* I - Write pointer */
+    _mxml_putc_cb_t putc_cb)		/* I - Write callback */
+{
+  const char	*name;			/* Entity name, if any */
+
+
+  while (*s)
+  {
+    if ((name = mxmlEntityGetName(*s)) != NULL)
+    {
+      if ((*putc_cb)('&', p) < 0)
+        return (-1);
+
+      while (*name)
+      {
+	if ((*putc_cb)(*name, p) < 0)
+          return (-1);
+        name ++;
+      }
+
+      if ((*putc_cb)(';', p) < 0)
+        return (-1);
+    }
+    else if ((*putc_cb)(*s, p) < 0)
+      return (-1);
+
+    s ++;
+  }
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_write_ws()' - Do whitespace callback...
+ */
+
+static int				/* O - New column */
+mxml_write_ws(mxml_node_t     *node,	/* I - Current node */
+              void            *p,	/* I - Write pointer */
+              mxml_save_cb_t  cb,	/* I - Callback function */
+	      int             ws,	/* I - Where value */
+	      int             col,	/* I - Current column */
+              _mxml_putc_cb_t putc_cb)	/* I - Write callback */
+{
+  const char	*s;			/* Whitespace string */
+
+
+  if (cb && (s = (*cb)(node, ws)) != NULL)
+  {
+    while (*s)
+    {
+      if ((*putc_cb)(*s, p) < 0)
+	return (-1);
+      else if (*s == '\n')
+	col = 0;
+      else if (*s == '\t')
+      {
+	col += MXML_TAB;
+	col = col - (col % MXML_TAB);
+      }
+      else
+	col ++;
+
+      s ++;
+    }
+  }
+
+  return (col);
+}
+
+
+/*
+ * End of "$Id: mxml-file.c 455 2014-01-05 03:28:03Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-get.c b/tools/gator/daemon/mxml/mxml-get.c
new file mode 100644
index 00000000000..40ed3d0839b
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-get.c
@@ -0,0 +1,452 @@
+/*
+ * "$Id: mxml-get.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Node get functions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * 'mxmlGetCDATA()' - Get the value for a CDATA node.
+ *
+ * @code NULL@ is returned if the node is not a CDATA element.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const char *				/* O - CDATA value or NULL */
+mxmlGetCDATA(mxml_node_t *node)		/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT ||
+      strncmp(node->value.element.name, "![CDATA[", 8))
+    return (NULL);
+
+ /*
+  * Return the text following the CDATA declaration...
+  */
+
+  return (node->value.element.name + 8);
+}
+
+
+/*
+ * 'mxmlGetCustom()' - Get the value for a custom node.
+ *
+ * @code NULL@ is returned if the node (or its first child) is not a custom
+ * value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const void *				/* O - Custom value or NULL */
+mxmlGetCustom(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the integer value...
+  */
+
+  if (node->type == MXML_CUSTOM)
+    return (node->value.custom.data);
+  else if (node->type == MXML_ELEMENT &&
+           node->child &&
+	   node->child->type == MXML_CUSTOM)
+    return (node->child->value.custom.data);
+  else
+    return (NULL);
+}
+
+
+/*
+ * 'mxmlGetElement()' - Get the name for an element node.
+ *
+ * @code NULL@ is returned if the node is not an element node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const char *				/* O - Element name or NULL */
+mxmlGetElement(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT)
+    return (NULL);
+
+ /*
+  * Return the element name...
+  */
+
+  return (node->value.element.name);
+}
+
+
+/*
+ * 'mxmlGetFirstChild()' - Get the first child of an element node.
+ *
+ * @code NULL@ is returned if the node is not an element node or if the node
+ * has no children.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *				/* O - First child or NULL */
+mxmlGetFirstChild(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT)
+    return (NULL);
+
+ /*
+  * Return the first child node...
+  */
+
+  return (node->child);
+}
+
+
+/*
+ * 'mxmlGetInteger()' - Get the integer value from the specified node or its
+ *                      first child.
+ *
+ * 0 is returned if the node (or its first child) is not an integer value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+int					/* O - Integer value or 0 */
+mxmlGetInteger(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (0);
+
+ /*
+  * Return the integer value...
+  */
+
+  if (node->type == MXML_INTEGER)
+    return (node->value.integer);
+  else if (node->type == MXML_ELEMENT &&
+           node->child &&
+	   node->child->type == MXML_INTEGER)
+    return (node->child->value.integer);
+  else
+    return (0);
+}
+
+
+/*
+ * 'mxmlGetLastChild()' - Get the last child of an element node.
+ *
+ * @code NULL@ is returned if the node is not an element node or if the node
+ * has no children.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *				/* O - Last child or NULL */
+mxmlGetLastChild(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT)
+    return (NULL);
+
+ /*
+  * Return the node type...
+  */
+
+  return (node->last_child);
+}
+
+
+/*
+ * 'mxmlGetNextSibling()' - Get the next node for the current parent.
+ *
+ * @code NULL@ is returned if this is the last child for the current parent.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *
+mxmlGetNextSibling(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the node type...
+  */
+
+  return (node->next);
+}
+
+
+/*
+ * 'mxmlGetOpaque()' - Get an opaque string value for a node or its first child.
+ *
+ * @code NULL@ is returned if the node (or its first child) is not an opaque
+ * value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const char *				/* O - Opaque string or NULL */
+mxmlGetOpaque(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the integer value...
+  */
+
+  if (node->type == MXML_OPAQUE)
+    return (node->value.opaque);
+  else if (node->type == MXML_ELEMENT &&
+           node->child &&
+	   node->child->type == MXML_OPAQUE)
+    return (node->child->value.opaque);
+  else
+    return (NULL);
+}
+
+
+/*
+ * 'mxmlGetParent()' - Get the parent node.
+ *
+ * @code NULL@ is returned for a root node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *				/* O - Parent node or NULL */
+mxmlGetParent(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the node type...
+  */
+
+  return (node->parent);
+}
+
+
+/*
+ * 'mxmlGetPrevSibling()' - Get the previous node for the current parent.
+ *
+ * @code NULL@ is returned if this is the first child for the current parent.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *				/* O - Previous node or NULL */
+mxmlGetPrevSibling(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the node type...
+  */
+
+  return (node->prev);
+}
+
+
+/*
+ * 'mxmlGetReal()' - Get the real value for a node or its first child.
+ *
+ * 0.0 is returned if the node (or its first child) is not a real value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+double					/* O - Real value or 0.0 */
+mxmlGetReal(mxml_node_t *node)		/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (0.0);
+
+ /*
+  * Return the integer value...
+  */
+
+  if (node->type == MXML_REAL)
+    return (node->value.real);
+  else if (node->type == MXML_ELEMENT &&
+           node->child &&
+	   node->child->type == MXML_REAL)
+    return (node->child->value.real);
+  else
+    return (0.0);
+}
+
+
+/*
+ * 'mxmlGetText()' - Get the text value for a node or its first child.
+ *
+ * @code NULL@ is returned if the node (or its first child) is not a text node.
+ * The "whitespace" argument can be NULL.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const char *				/* O - Text string or NULL */
+mxmlGetText(mxml_node_t *node,		/* I - Node to get */
+            int         *whitespace)	/* O - 1 if string is preceded by whitespace, 0 otherwise */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+  {
+    if (whitespace)
+      *whitespace = 0;
+
+    return (NULL);
+  }
+
+ /*
+  * Return the integer value...
+  */
+
+  if (node->type == MXML_TEXT)
+  {
+    if (whitespace)
+      *whitespace = node->value.text.whitespace;
+
+    return (node->value.text.string);
+  }
+  else if (node->type == MXML_ELEMENT &&
+           node->child &&
+	   node->child->type == MXML_TEXT)
+  {
+    if (whitespace)
+      *whitespace = node->child->value.text.whitespace;
+
+    return (node->child->value.text.string);
+  }
+  else
+  {
+    if (whitespace)
+      *whitespace = 0;
+
+    return (NULL);
+  }
+}
+
+
+/*
+ * 'mxmlGetType()' - Get the node type.
+ *
+ * @code MXML_IGNORE@ is returned if "node" is @code NULL@.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_type_t				/* O - Type of node */
+mxmlGetType(mxml_node_t *node)		/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (MXML_IGNORE);
+
+ /*
+  * Return the node type...
+  */
+
+  return (node->type);
+}
+
+
+/*
+ * 'mxmlGetUserData()' - Get the user data pointer for a node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+void *					/* O - User data pointer */
+mxmlGetUserData(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the user data pointer...
+  */
+
+  return (node->user_data);
+}
+
+
+/*
+ * End of "$Id: mxml-get.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-index.c b/tools/gator/daemon/mxml/mxml-index.c
new file mode 100644
index 00000000000..10814390d3a
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-index.c
@@ -0,0 +1,659 @@
+/*
+ * "$Id: mxml-index.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Index support code for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * Sort functions...
+ */
+
+static int	index_compare(mxml_index_t *ind, mxml_node_t *first,
+		              mxml_node_t *second);
+static int	index_find(mxml_index_t *ind, const char *element,
+		           const char *value, mxml_node_t *node);
+static void	index_sort(mxml_index_t *ind, int left, int right);
+
+
+/*
+ * 'mxmlIndexDelete()' - Delete an index.
+ */
+
+void
+mxmlIndexDelete(mxml_index_t *ind)	/* I - Index to delete */
+{
+ /*
+  * Range check input..
+  */
+
+  if (!ind)
+    return;
+
+ /*
+  * Free memory...
+  */
+
+  if (ind->attr)
+    free(ind->attr);
+
+  if (ind->alloc_nodes)
+    free(ind->nodes);
+
+  free(ind);
+}
+
+
+/*
+ * 'mxmlIndexEnum()' - Return the next node in the index.
+ *
+ * Nodes are returned in the sorted order of the index.
+ */
+
+mxml_node_t *				/* O - Next node or NULL if there is none */
+mxmlIndexEnum(mxml_index_t *ind)	/* I - Index to enumerate */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!ind)
+    return (NULL);
+
+ /*
+  * Return the next node...
+  */
+
+  if (ind->cur_node < ind->num_nodes)
+    return (ind->nodes[ind->cur_node ++]);
+  else
+    return (NULL);
+}
+
+
+/*
+ * 'mxmlIndexFind()' - Find the next matching node.
+ *
+ * You should call mxmlIndexReset() prior to using this function for
+ * the first time with a particular set of "element" and "value"
+ * strings. Passing NULL for both "element" and "value" is equivalent
+ * to calling mxmlIndexEnum().
+ */
+
+mxml_node_t *				/* O - Node or NULL if none found */
+mxmlIndexFind(mxml_index_t *ind,	/* I - Index to search */
+              const char   *element,	/* I - Element name to find, if any */
+	      const char   *value)	/* I - Attribute value, if any */
+{
+  int		diff,			/* Difference between names */
+		current,		/* Current entity in search */
+		first,			/* First entity in search */
+		last;			/* Last entity in search */
+
+
+#ifdef DEBUG
+  printf("mxmlIndexFind(ind=%p, element=\"%s\", value=\"%s\")\n",
+         ind, element ? element : "(null)", value ? value : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!ind || (!ind->attr && value))
+  {
+#ifdef DEBUG
+    puts("    returning NULL...");
+    printf("    ind->attr=\"%s\"\n", ind->attr ? ind->attr : "(null)");
+#endif /* DEBUG */
+
+    return (NULL);
+  }
+
+ /*
+  * If both element and value are NULL, just enumerate the nodes in the
+  * index...
+  */
+
+  if (!element && !value)
+    return (mxmlIndexEnum(ind));
+
+ /*
+  * If there are no nodes in the index, return NULL...
+  */
+
+  if (!ind->num_nodes)
+  {
+#ifdef DEBUG
+    puts("    returning NULL...");
+    puts("    no nodes!");
+#endif /* DEBUG */
+
+    return (NULL);
+  }
+
+ /*
+  * If cur_node == 0, then find the first matching node...
+  */
+
+  if (ind->cur_node == 0)
+  {
+   /*
+    * Find the first node using a modified binary search algorithm...
+    */
+
+    first = 0;
+    last  = ind->num_nodes - 1;
+
+#ifdef DEBUG
+    printf("    find first time, num_nodes=%d...\n", ind->num_nodes);
+#endif /* DEBUG */
+
+    while ((last - first) > 1)
+    {
+      current = (first + last) / 2;
+
+#ifdef DEBUG
+      printf("    first=%d, last=%d, current=%d\n", first, last, current);
+#endif /* DEBUG */
+
+      if ((diff = index_find(ind, element, value, ind->nodes[current])) == 0)
+      {
+       /*
+        * Found a match, move back to find the first...
+	*/
+
+#ifdef DEBUG
+        puts("    match!");
+#endif /* DEBUG */
+
+        while (current > 0 &&
+	       !index_find(ind, element, value, ind->nodes[current - 1]))
+	  current --;
+
+#ifdef DEBUG
+        printf("    returning first match=%d\n", current);
+#endif /* DEBUG */
+
+       /*
+        * Return the first match and save the index to the next...
+	*/
+
+        ind->cur_node = current + 1;
+
+	return (ind->nodes[current]);
+      }
+      else if (diff < 0)
+	last = current;
+      else
+	first = current;
+
+#ifdef DEBUG
+      printf("    diff=%d\n", diff);
+#endif /* DEBUG */
+    }
+
+   /*
+    * If we get this far, then we found exactly 0 or 1 matches...
+    */
+
+    for (current = first; current <= last; current ++)
+      if (!index_find(ind, element, value, ind->nodes[current]))
+      {
+       /*
+	* Found exactly one (or possibly two) match...
+	*/
+
+#ifdef DEBUG
+	printf("    returning only match %d...\n", current);
+#endif /* DEBUG */
+
+	ind->cur_node = current + 1;
+
+	return (ind->nodes[current]);
+      }
+
+   /*
+    * No matches...
+    */
+
+    ind->cur_node = ind->num_nodes;
+
+#ifdef DEBUG
+    puts("    returning NULL...");
+#endif /* DEBUG */
+
+    return (NULL);
+  }
+  else if (ind->cur_node < ind->num_nodes &&
+           !index_find(ind, element, value, ind->nodes[ind->cur_node]))
+  {
+   /*
+    * Return the next matching node...
+    */
+
+#ifdef DEBUG
+    printf("    returning next match %d...\n", ind->cur_node);
+#endif /* DEBUG */
+
+    return (ind->nodes[ind->cur_node ++]);
+  }
+
+ /*
+  * If we get this far, then we have no matches...
+  */
+
+  ind->cur_node = ind->num_nodes;
+
+#ifdef DEBUG
+  puts("    returning NULL...");
+#endif /* DEBUG */
+
+  return (NULL);
+}
+
+
+/*
+ * 'mxmlIndexGetCount()' - Get the number of nodes in an index.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+int					/* I - Number of nodes in index */
+mxmlIndexGetCount(mxml_index_t *ind)	/* I - Index of nodes */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!ind)
+    return (0);
+
+ /*
+  * Return the number of nodes in the index...
+  */
+
+  return (ind->num_nodes);
+}
+
+
+/*
+ * 'mxmlIndexNew()' - Create a new index.
+ *
+ * The index will contain all nodes that contain the named element and/or
+ * attribute. If both "element" and "attr" are NULL, then the index will
+ * contain a sorted list of the elements in the node tree.  Nodes are
+ * sorted by element name and optionally by attribute value if the "attr"
+ * argument is not NULL.
+ */
+
+mxml_index_t *				/* O - New index */
+mxmlIndexNew(mxml_node_t *node,		/* I - XML node tree */
+             const char  *element,	/* I - Element to index or NULL for all */
+             const char  *attr)		/* I - Attribute to index or NULL for none */
+{
+  mxml_index_t	*ind;			/* New index */
+  mxml_node_t	*current,		/* Current node in index */
+  		**temp;			/* Temporary node pointer array */
+
+
+ /*
+  * Range check input...
+  */
+
+#ifdef DEBUG
+  printf("mxmlIndexNew(node=%p, element=\"%s\", attr=\"%s\")\n",
+         node, element ? element : "(null)", attr ? attr : "(null)");
+#endif /* DEBUG */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Create a new index...
+  */
+
+  if ((ind = calloc(1, sizeof(mxml_index_t))) == NULL)
+  {
+    mxml_error("Unable to allocate %d bytes for index - %s",
+               sizeof(mxml_index_t), strerror(errno));
+    return (NULL);
+  }
+
+  if (attr)
+    ind->attr = strdup(attr);
+
+  if (!element && !attr)
+    current = node;
+  else
+    current = mxmlFindElement(node, node, element, attr, NULL, MXML_DESCEND);
+
+  while (current)
+  {
+    if (ind->num_nodes >= ind->alloc_nodes)
+    {
+      if (!ind->alloc_nodes)
+        temp = malloc(64 * sizeof(mxml_node_t *));
+      else
+        temp = realloc(ind->nodes, (ind->alloc_nodes + 64) * sizeof(mxml_node_t *));
+
+      if (!temp)
+      {
+       /*
+        * Unable to allocate memory for the index, so abort...
+	*/
+
+        mxml_error("Unable to allocate %d bytes for index: %s",
+	           (ind->alloc_nodes + 64) * sizeof(mxml_node_t *),
+		   strerror(errno));
+
+        mxmlIndexDelete(ind);
+	return (NULL);
+      }
+
+      ind->nodes       = temp;
+      ind->alloc_nodes += 64;
+    }
+
+    ind->nodes[ind->num_nodes ++] = current;
+
+    current = mxmlFindElement(current, node, element, attr, NULL, MXML_DESCEND);
+  }
+
+ /*
+  * Sort nodes based upon the search criteria...
+  */
+
+#ifdef DEBUG
+  {
+    int i;				/* Looping var */
+
+
+    printf("%d node(s) in index.\n\n", ind->num_nodes);
+
+    if (attr)
+    {
+      printf("Node      Address   Element         %s\n", attr);
+      puts("--------  --------  --------------  ------------------------------");
+
+      for (i = 0; i < ind->num_nodes; i ++)
+	printf("%8d  %-8p  %-14.14s  %s\n", i, ind->nodes[i],
+	       ind->nodes[i]->value.element.name,
+	       mxmlElementGetAttr(ind->nodes[i], attr));
+    }
+    else
+    {
+      puts("Node      Address   Element");
+      puts("--------  --------  --------------");
+
+      for (i = 0; i < ind->num_nodes; i ++)
+	printf("%8d  %-8p  %s\n", i, ind->nodes[i],
+	       ind->nodes[i]->value.element.name);
+    }
+
+    putchar('\n');
+  }
+#endif /* DEBUG */
+
+  if (ind->num_nodes > 1)
+    index_sort(ind, 0, ind->num_nodes - 1);
+
+#ifdef DEBUG
+  {
+    int i;				/* Looping var */
+
+
+    puts("After sorting:\n");
+
+    if (attr)
+    {
+      printf("Node      Address   Element         %s\n", attr);
+      puts("--------  --------  --------------  ------------------------------");
+
+      for (i = 0; i < ind->num_nodes; i ++)
+	printf("%8d  %-8p  %-14.14s  %s\n", i, ind->nodes[i],
+	       ind->nodes[i]->value.element.name,
+	       mxmlElementGetAttr(ind->nodes[i], attr));
+    }
+    else
+    {
+      puts("Node      Address   Element");
+      puts("--------  --------  --------------");
+
+      for (i = 0; i < ind->num_nodes; i ++)
+	printf("%8d  %-8p  %s\n", i, ind->nodes[i],
+	       ind->nodes[i]->value.element.name);
+    }
+
+    putchar('\n');
+  }
+#endif /* DEBUG */
+
+ /*
+  * Return the new index...
+  */
+
+  return (ind);
+}
+
+
+/*
+ * 'mxmlIndexReset()' - Reset the enumeration/find pointer in the index and
+ *                      return the first node in the index.
+ *
+ * This function should be called prior to using mxmlIndexEnum() or
+ * mxmlIndexFind() for the first time.
+ */
+
+mxml_node_t *				/* O - First node or NULL if there is none */
+mxmlIndexReset(mxml_index_t *ind)	/* I - Index to reset */
+{
+#ifdef DEBUG
+  printf("mxmlIndexReset(ind=%p)\n", ind);
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!ind)
+    return (NULL);
+
+ /*
+  * Set the index to the first element...
+  */
+
+  ind->cur_node = 0;
+
+ /*
+  * Return the first node...
+  */
+
+  if (ind->num_nodes)
+    return (ind->nodes[0]);
+  else
+    return (NULL);
+}
+
+
+/*
+ * 'index_compare()' - Compare two nodes.
+ */
+
+static int				/* O - Result of comparison */
+index_compare(mxml_index_t *ind,	/* I - Index */
+              mxml_node_t  *first,	/* I - First node */
+              mxml_node_t  *second)	/* I - Second node */
+{
+  int	diff;				/* Difference */
+
+
+ /*
+  * Check the element name...
+  */
+
+  if ((diff = strcmp(first->value.element.name,
+                     second->value.element.name)) != 0)
+    return (diff);
+
+ /*
+  * Check the attribute value...
+  */
+
+  if (ind->attr)
+  {
+    if ((diff = strcmp(mxmlElementGetAttr(first, ind->attr),
+                       mxmlElementGetAttr(second, ind->attr))) != 0)
+      return (diff);
+  }
+
+ /*
+  * No difference, return 0...
+  */
+
+  return (0);
+}
+
+
+/*
+ * 'index_find()' - Compare a node with index values.
+ */
+
+static int				/* O - Result of comparison */
+index_find(mxml_index_t *ind,		/* I - Index */
+           const char   *element,	/* I - Element name or NULL */
+	   const char   *value,		/* I - Attribute value or NULL */
+           mxml_node_t  *node)		/* I - Node */
+{
+  int	diff;				/* Difference */
+
+
+ /*
+  * Check the element name...
+  */
+
+  if (element)
+  {
+    if ((diff = strcmp(element, node->value.element.name)) != 0)
+      return (diff);
+  }
+
+ /*
+  * Check the attribute value...
+  */
+
+  if (value)
+  {
+    if ((diff = strcmp(value, mxmlElementGetAttr(node, ind->attr))) != 0)
+      return (diff);
+  }
+
+ /*
+  * No difference, return 0...
+  */
+
+  return (0);
+}
+
+
+/*
+ * 'index_sort()' - Sort the nodes in the index...
+ *
+ * This function implements the classic quicksort algorithm...
+ */
+
+static void
+index_sort(mxml_index_t *ind,		/* I - Index to sort */
+           int          left,		/* I - Left node in partition */
+	   int          right)		/* I - Right node in partition */
+{
+  mxml_node_t	*pivot,			/* Pivot node */
+		*temp;			/* Swap node */
+  int		templ,			/* Temporary left node */
+		tempr;			/* Temporary right node */
+
+
+ /*
+  * Loop until we have sorted all the way to the right...
+  */
+
+  do
+  {
+   /*
+    * Sort the pivot in the current partition...
+    */
+
+    pivot = ind->nodes[left];
+
+    for (templ = left, tempr = right; templ < tempr;)
+    {
+     /*
+      * Move left while left node <= pivot node...
+      */
+
+      while ((templ < right) &&
+             index_compare(ind, ind->nodes[templ], pivot) <= 0)
+	templ ++;
+
+     /*
+      * Move right while right node > pivot node...
+      */
+
+      while ((tempr > left) &&
+             index_compare(ind, ind->nodes[tempr], pivot) > 0)
+	tempr --;
+
+     /*
+      * Swap nodes if needed...
+      */
+
+      if (templ < tempr)
+      {
+	temp              = ind->nodes[templ];
+	ind->nodes[templ] = ind->nodes[tempr];
+	ind->nodes[tempr] = temp;
+      }
+    }
+
+   /*
+    * When we get here, the right (tempr) node is the new position for the
+    * pivot node...
+    */
+
+    if (index_compare(ind, pivot, ind->nodes[tempr]) > 0)
+    {
+      ind->nodes[left]  = ind->nodes[tempr];
+      ind->nodes[tempr] = pivot;
+    }
+
+   /*
+    * Recursively sort the left partition as needed...
+    */
+
+    if (left < (tempr - 1))
+      index_sort(ind, left, tempr - 1);
+  }
+  while (right > (left = tempr + 1));
+}
+
+
+/*
+ * End of "$Id: mxml-index.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-node.c b/tools/gator/daemon/mxml/mxml-node.c
new file mode 100644
index 00000000000..128cda1a4cf
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-node.c
@@ -0,0 +1,788 @@
+/*
+ * "$Id: mxml-node.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Node support code for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * Local functions...
+ */
+
+static mxml_node_t	*mxml_new(mxml_node_t *parent, mxml_type_t type);
+
+
+/*
+ * 'mxmlAdd()' - Add a node to a tree.
+ *
+ * Adds the specified node to the parent. If the child argument is not
+ * NULL, puts the new node before or after the specified child depending
+ * on the value of the where argument. If the child argument is NULL,
+ * puts the new node at the beginning of the child list (MXML_ADD_BEFORE)
+ * or at the end of the child list (MXML_ADD_AFTER). The constant
+ * MXML_ADD_TO_PARENT can be used to specify a NULL child pointer.
+ */
+
+void
+mxmlAdd(mxml_node_t *parent,		/* I - Parent node */
+        int         where,		/* I - Where to add, MXML_ADD_BEFORE or MXML_ADD_AFTER */
+        mxml_node_t *child,		/* I - Child node for where or MXML_ADD_TO_PARENT */
+	mxml_node_t *node)		/* I - Node to add */
+{
+#ifdef DEBUG
+  fprintf(stderr, "mxmlAdd(parent=%p, where=%d, child=%p, node=%p)\n", parent,
+          where, child, node);
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!parent || !node)
+    return;
+
+#if DEBUG > 1
+  fprintf(stderr, "    BEFORE: node->parent=%p\n", node->parent);
+  if (parent)
+  {
+    fprintf(stderr, "    BEFORE: parent->child=%p\n", parent->child);
+    fprintf(stderr, "    BEFORE: parent->last_child=%p\n", parent->last_child);
+    fprintf(stderr, "    BEFORE: parent->prev=%p\n", parent->prev);
+    fprintf(stderr, "    BEFORE: parent->next=%p\n", parent->next);
+  }
+#endif /* DEBUG > 1 */
+
+ /*
+  * Remove the node from any existing parent...
+  */
+
+  if (node->parent)
+    mxmlRemove(node);
+
+ /*
+  * Reset pointers...
+  */
+
+  node->parent = parent;
+
+  switch (where)
+  {
+    case MXML_ADD_BEFORE :
+        if (!child || child == parent->child || child->parent != parent)
+	{
+	 /*
+	  * Insert as first node under parent...
+	  */
+
+	  node->next = parent->child;
+
+	  if (parent->child)
+	    parent->child->prev = node;
+	  else
+	    parent->last_child = node;
+
+	  parent->child = node;
+	}
+	else
+	{
+	 /*
+	  * Insert node before this child...
+	  */
+
+	  node->next = child;
+	  node->prev = child->prev;
+
+	  if (child->prev)
+	    child->prev->next = node;
+	  else
+	    parent->child = node;
+
+	  child->prev = node;
+	}
+        break;
+
+    case MXML_ADD_AFTER :
+        if (!child || child == parent->last_child || child->parent != parent)
+	{
+	 /*
+	  * Insert as last node under parent...
+	  */
+
+	  node->parent = parent;
+	  node->prev   = parent->last_child;
+
+	  if (parent->last_child)
+	    parent->last_child->next = node;
+	  else
+	    parent->child = node;
+
+	  parent->last_child = node;
+        }
+	else
+	{
+	 /*
+	  * Insert node after this child...
+	  */
+
+	  node->prev = child;
+	  node->next = child->next;
+
+	  if (child->next)
+	    child->next->prev = node;
+	  else
+	    parent->last_child = node;
+
+	  child->next = node;
+	}
+        break;
+  }
+
+#if DEBUG > 1
+  fprintf(stderr, "    AFTER: node->parent=%p\n", node->parent);
+  if (parent)
+  {
+    fprintf(stderr, "    AFTER: parent->child=%p\n", parent->child);
+    fprintf(stderr, "    AFTER: parent->last_child=%p\n", parent->last_child);
+    fprintf(stderr, "    AFTER: parent->prev=%p\n", parent->prev);
+    fprintf(stderr, "    AFTER: parent->next=%p\n", parent->next);
+  }
+#endif /* DEBUG > 1 */
+}
+
+
+/*
+ * 'mxmlDelete()' - Delete a node and all of its children.
+ *
+ * If the specified node has a parent, this function first removes the
+ * node from its parent using the mxmlRemove() function.
+ */
+
+void
+mxmlDelete(mxml_node_t *node)		/* I - Node to delete */
+{
+  int	i;				/* Looping var */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlDelete(node=%p)\n", node);
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return;
+
+ /*
+  * Remove the node from its parent, if any...
+  */
+
+  mxmlRemove(node);
+
+ /*
+  * Delete children...
+  */
+
+  while (node->child)
+    mxmlDelete(node->child);
+
+ /*
+  * Now delete any node data...
+  */
+
+  switch (node->type)
+  {
+    case MXML_ELEMENT :
+        if (node->value.element.name)
+	  free(node->value.element.name);
+
+	if (node->value.element.num_attrs)
+	{
+	  for (i = 0; i < node->value.element.num_attrs; i ++)
+	  {
+	    if (node->value.element.attrs[i].name)
+	      free(node->value.element.attrs[i].name);
+	    if (node->value.element.attrs[i].value)
+	      free(node->value.element.attrs[i].value);
+	  }
+
+          free(node->value.element.attrs);
+	}
+        break;
+    case MXML_INTEGER :
+       /* Nothing to do */
+        break;
+    case MXML_OPAQUE :
+        if (node->value.opaque)
+	  free(node->value.opaque);
+        break;
+    case MXML_REAL :
+       /* Nothing to do */
+        break;
+    case MXML_TEXT :
+        if (node->value.text.string)
+	  free(node->value.text.string);
+        break;
+    case MXML_CUSTOM :
+        if (node->value.custom.data &&
+	    node->value.custom.destroy)
+	  (*(node->value.custom.destroy))(node->value.custom.data);
+	break;
+    default :
+        break;
+  }
+
+ /*
+  * Free this node...
+  */
+
+  free(node);
+}
+
+
+/*
+ * 'mxmlGetRefCount()' - Get the current reference (use) count for a node.
+ *
+ * The initial reference count of new nodes is 1. Use the @link mxmlRetain@
+ * and @link mxmlRelease@ functions to increment and decrement a node's
+ * reference count.
+ *
+ * @since Mini-XML 2.7@.
+ */
+
+int					/* O - Reference count */
+mxmlGetRefCount(mxml_node_t *node)	/* I - Node */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (0);
+
+ /*
+  * Return the reference count...
+  */
+
+  return (node->ref_count);
+}
+
+
+/*
+ * 'mxmlNewCDATA()' - Create a new CDATA node.
+ *
+ * The new CDATA node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * CDATA node has no parent. The data string must be nul-terminated and
+ * is copied into the new node. CDATA nodes use the MXML_ELEMENT type.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewCDATA(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+	     const char  *data)		/* I - Data string */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewCDATA(parent=%p, data=\"%s\")\n",
+          parent, data ? data : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!data)
+    return (NULL);
+
+ /*
+  * Create the node and set the name value...
+  */
+
+  if ((node = mxml_new(parent, MXML_ELEMENT)) != NULL)
+    node->value.element.name = _mxml_strdupf("![CDATA[%s]]", data);
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewCustom()' - Create a new custom data node.
+ *
+ * The new custom node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * element node has no parent. NULL can be passed when the data in the
+ * node is not dynamically allocated or is separately managed.
+ *
+ * @since Mini-XML 2.1@
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewCustom(
+    mxml_node_t              *parent,	/* I - Parent node or MXML_NO_PARENT */
+    void                     *data,	/* I - Pointer to data */
+    mxml_custom_destroy_cb_t destroy)	/* I - Function to destroy data */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewCustom(parent=%p, data=%p, destroy=%p)\n", parent,
+          data, destroy);
+#endif /* DEBUG */
+
+ /*
+  * Create the node and set the value...
+  */
+
+  if ((node = mxml_new(parent, MXML_CUSTOM)) != NULL)
+  {
+    node->value.custom.data    = data;
+    node->value.custom.destroy = destroy;
+  }
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewElement()' - Create a new element node.
+ *
+ * The new element node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * element node has no parent.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewElement(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+               const char  *name)	/* I - Name of element */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewElement(parent=%p, name=\"%s\")\n", parent,
+          name ? name : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!name)
+    return (NULL);
+
+ /*
+  * Create the node and set the element name...
+  */
+
+  if ((node = mxml_new(parent, MXML_ELEMENT)) != NULL)
+    node->value.element.name = strdup(name);
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewInteger()' - Create a new integer node.
+ *
+ * The new integer node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * integer node has no parent.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewInteger(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+               int         integer)	/* I - Integer value */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewInteger(parent=%p, integer=%d)\n", parent, integer);
+#endif /* DEBUG */
+
+ /*
+  * Create the node and set the element name...
+  */
+
+  if ((node = mxml_new(parent, MXML_INTEGER)) != NULL)
+    node->value.integer = integer;
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewOpaque()' - Create a new opaque string.
+ *
+ * The new opaque node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * opaque node has no parent. The opaque string must be nul-terminated and
+ * is copied into the new node.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewOpaque(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+              const char  *opaque)	/* I - Opaque string */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewOpaque(parent=%p, opaque=\"%s\")\n", parent,
+          opaque ? opaque : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!opaque)
+    return (NULL);
+
+ /*
+  * Create the node and set the element name...
+  */
+
+  if ((node = mxml_new(parent, MXML_OPAQUE)) != NULL)
+    node->value.opaque = strdup(opaque);
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewReal()' - Create a new real number node.
+ *
+ * The new real number node is added to the end of the specified parent's
+ * child list. The constant MXML_NO_PARENT can be used to specify that
+ * the new real number node has no parent.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewReal(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+            double      real)		/* I - Real number value */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewReal(parent=%p, real=%g)\n", parent, real);
+#endif /* DEBUG */
+
+ /*
+  * Create the node and set the element name...
+  */
+
+  if ((node = mxml_new(parent, MXML_REAL)) != NULL)
+    node->value.real = real;
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewText()' - Create a new text fragment node.
+ *
+ * The new text node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * text node has no parent. The whitespace parameter is used to specify
+ * whether leading whitespace is present before the node. The text
+ * string must be nul-terminated and is copied into the new node.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewText(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+            int         whitespace,	/* I - 1 = leading whitespace, 0 = no whitespace */
+	    const char  *string)	/* I - String */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewText(parent=%p, whitespace=%d, string=\"%s\")\n",
+          parent, whitespace, string ? string : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!string)
+    return (NULL);
+
+ /*
+  * Create the node and set the text value...
+  */
+
+  if ((node = mxml_new(parent, MXML_TEXT)) != NULL)
+  {
+    node->value.text.whitespace = whitespace;
+    node->value.text.string     = strdup(string);
+  }
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewTextf()' - Create a new formatted text fragment node.
+ *
+ * The new text node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * text node has no parent. The whitespace parameter is used to specify
+ * whether leading whitespace is present before the node. The format
+ * string must be nul-terminated and is formatted into the new node.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewTextf(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+             int         whitespace,	/* I - 1 = leading whitespace, 0 = no whitespace */
+	     const char  *format,	/* I - Printf-style frmat string */
+	     ...)			/* I - Additional args as needed */
+{
+  mxml_node_t	*node;			/* New node */
+  va_list	ap;			/* Pointer to arguments */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewTextf(parent=%p, whitespace=%d, format=\"%s\", ...)\n",
+          parent, whitespace, format ? format : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!format)
+    return (NULL);
+
+ /*
+  * Create the node and set the text value...
+  */
+
+  if ((node = mxml_new(parent, MXML_TEXT)) != NULL)
+  {
+    va_start(ap, format);
+
+    node->value.text.whitespace = whitespace;
+    node->value.text.string     = _mxml_vstrdupf(format, ap);
+
+    va_end(ap);
+  }
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlRemove()' - Remove a node from its parent.
+ *
+ * Does not free memory used by the node - use mxmlDelete() for that.
+ * This function does nothing if the node has no parent.
+ */
+
+void
+mxmlRemove(mxml_node_t *node)		/* I - Node to remove */
+{
+#ifdef DEBUG
+  fprintf(stderr, "mxmlRemove(node=%p)\n", node);
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || !node->parent)
+    return;
+
+ /*
+  * Remove from parent...
+  */
+
+#if DEBUG > 1
+  fprintf(stderr, "    BEFORE: node->parent=%p\n", node->parent);
+  if (node->parent)
+  {
+    fprintf(stderr, "    BEFORE: node->parent->child=%p\n", node->parent->child);
+    fprintf(stderr, "    BEFORE: node->parent->last_child=%p\n", node->parent->last_child);
+  }
+  fprintf(stderr, "    BEFORE: node->child=%p\n", node->child);
+  fprintf(stderr, "    BEFORE: node->last_child=%p\n", node->last_child);
+  fprintf(stderr, "    BEFORE: node->prev=%p\n", node->prev);
+  fprintf(stderr, "    BEFORE: node->next=%p\n", node->next);
+#endif /* DEBUG > 1 */
+
+  if (node->prev)
+    node->prev->next = node->next;
+  else
+    node->parent->child = node->next;
+
+  if (node->next)
+    node->next->prev = node->prev;
+  else
+    node->parent->last_child = node->prev;
+
+  node->parent = NULL;
+  node->prev   = NULL;
+  node->next   = NULL;
+
+#if DEBUG > 1
+  fprintf(stderr, "    AFTER: node->parent=%p\n", node->parent);
+  if (node->parent)
+  {
+    fprintf(stderr, "    AFTER: node->parent->child=%p\n", node->parent->child);
+    fprintf(stderr, "    AFTER: node->parent->last_child=%p\n", node->parent->last_child);
+  }
+  fprintf(stderr, "    AFTER: node->child=%p\n", node->child);
+  fprintf(stderr, "    AFTER: node->last_child=%p\n", node->last_child);
+  fprintf(stderr, "    AFTER: node->prev=%p\n", node->prev);
+  fprintf(stderr, "    AFTER: node->next=%p\n", node->next);
+#endif /* DEBUG > 1 */
+}
+
+
+/*
+ * 'mxmlNewXML()' - Create a new XML document tree.
+ *
+ * The "version" argument specifies the version number to put in the
+ * ?xml element node. If NULL, version 1.0 is assumed.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t *				/* O - New ?xml node */
+mxmlNewXML(const char *version)		/* I - Version number to use */
+{
+  char	element[1024];			/* Element text */
+
+
+  snprintf(element, sizeof(element), "?xml version=\"%s\" encoding=\"utf-8\"?",
+           version ? version : "1.0");
+
+  return (mxmlNewElement(NULL, element));
+}
+
+
+/*
+ * 'mxmlRelease()' - Release a node.
+ *
+ * When the reference count reaches zero, the node (and any children)
+ * is deleted via mxmlDelete().
+ *
+ * @since Mini-XML 2.3@
+ */
+
+int					/* O - New reference count */
+mxmlRelease(mxml_node_t *node)		/* I - Node */
+{
+  if (node)
+  {
+    if ((-- node->ref_count) <= 0)
+    {
+      mxmlDelete(node);
+      return (0);
+    }
+    else
+      return (node->ref_count);
+  }
+  else
+    return (-1);
+}
+
+
+/*
+ * 'mxmlRetain()' - Retain a node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+int					/* O - New reference count */
+mxmlRetain(mxml_node_t *node)		/* I - Node */
+{
+  if (node)
+    return (++ node->ref_count);
+  else
+    return (-1);
+}
+
+
+/*
+ * 'mxml_new()' - Create a new node.
+ */
+
+static mxml_node_t *			/* O - New node */
+mxml_new(mxml_node_t *parent,		/* I - Parent node */
+         mxml_type_t type)		/* I - Node type */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#if DEBUG > 1
+  fprintf(stderr, "mxml_new(parent=%p, type=%d)\n", parent, type);
+#endif /* DEBUG > 1 */
+
+ /*
+  * Allocate memory for the node...
+  */
+
+  if ((node = calloc(1, sizeof(mxml_node_t))) == NULL)
+  {
+#if DEBUG > 1
+    fputs("    returning NULL\n", stderr);
+#endif /* DEBUG > 1 */
+
+    return (NULL);
+  }
+
+#if DEBUG > 1
+  fprintf(stderr, "    returning %p\n", node);
+#endif /* DEBUG > 1 */
+
+ /*
+  * Set the node type...
+  */
+
+  node->type      = type;
+  node->ref_count = 1;
+
+ /*
+  * Add to the parent if present...
+  */
+
+  if (parent)
+    mxmlAdd(parent, MXML_ADD_AFTER, MXML_ADD_TO_PARENT, node);
+
+ /*
+  * Return the new node...
+  */
+
+  return (node);
+}
+
+
+/*
+ * End of "$Id: mxml-node.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-private.c b/tools/gator/daemon/mxml/mxml-private.c
new file mode 100644
index 00000000000..bec4bbfbf37
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-private.c
@@ -0,0 +1,323 @@
+/*
+ * "$Id: mxml-private.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Private functions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "mxml-private.h"
+
+
+/*
+ * Some crazy people think that unloading a shared object is a good or safe
+ * thing to do.  Unfortunately, most objects are simply *not* safe to unload
+ * and bad things *will* happen.
+ *
+ * The following mess of conditional code allows us to provide a destructor
+ * function in Mini-XML for our thread-global storage so that it can possibly
+ * be unloaded safely, although since there is no standard way to do so I
+ * can't even provide any guarantees that you can do it safely on all platforms.
+ *
+ * This code currently supports AIX, HP-UX, Linux, Mac OS X, Solaris, and
+ * Windows.  It might work on the BSDs and IRIX, but I haven't tested that.
+ */
+
+#if defined(__sun) || defined(_AIX)
+#  pragma fini(_mxml_fini)
+#  define _MXML_FINI _mxml_fini
+#elif defined(__hpux)
+#  pragma FINI _mxml_fini
+#  define _MXML_FINI _mxml_fini
+#elif defined(__GNUC__) /* Linux and Mac OS X */
+#  define _MXML_FINI __attribute((destructor)) _mxml_fini
+#else
+#  define _MXML_FINI _fini
+#endif /* __sun */
+
+
+/*
+ * 'mxml_error()' - Display an error message.
+ */
+
+void
+mxml_error(const char *format,		/* I - Printf-style format string */
+           ...)				/* I - Additional arguments as needed */
+{
+  va_list	ap;			/* Pointer to arguments */
+  char		s[1024];		/* Message string */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+ /*
+  * Range check input...
+  */
+
+  if (!format)
+    return;
+
+ /*
+  * Format the error message string...
+  */
+
+  va_start(ap, format);
+
+  vsnprintf(s, sizeof(s), format, ap);
+
+  va_end(ap);
+
+ /*
+  * And then display the error message...
+  */
+
+  if (global->error_cb)
+    (*global->error_cb)(s);
+  else
+    fprintf(stderr, "mxml: %s\n", s);
+}
+
+
+/*
+ * 'mxml_ignore_cb()' - Default callback for ignored values.
+ */
+
+mxml_type_t				/* O - Node type */
+mxml_ignore_cb(mxml_node_t *node)	/* I - Current node */
+{
+  (void)node;
+
+  return (MXML_IGNORE);
+}
+
+
+/*
+ * 'mxml_integer_cb()' - Default callback for integer values.
+ */
+
+mxml_type_t				/* O - Node type */
+mxml_integer_cb(mxml_node_t *node)	/* I - Current node */
+{
+  (void)node;
+
+  return (MXML_INTEGER);
+}
+
+
+/*
+ * 'mxml_opaque_cb()' - Default callback for opaque values.
+ */
+
+mxml_type_t				/* O - Node type */
+mxml_opaque_cb(mxml_node_t *node)	/* I - Current node */
+{
+  (void)node;
+
+  return (MXML_OPAQUE);
+}
+
+
+/*
+ * 'mxml_real_cb()' - Default callback for real number values.
+ */
+
+mxml_type_t				/* O - Node type */
+mxml_real_cb(mxml_node_t *node)		/* I - Current node */
+{
+  (void)node;
+
+  return (MXML_REAL);
+}
+
+
+#ifdef HAVE_PTHREAD_H			/**** POSIX threading ****/
+#  include <pthread.h>
+
+static pthread_key_t	_mxml_key = -1;	/* Thread local storage key */
+static pthread_once_t	_mxml_key_once = PTHREAD_ONCE_INIT;
+					/* One-time initialization object */
+static void		_mxml_init(void);
+static void		_mxml_destructor(void *g);
+
+
+/*
+ * '_mxml_destructor()' - Free memory used for globals...
+ */
+
+static void
+_mxml_destructor(void *g)		/* I - Global data */
+{
+  free(g);
+}
+
+
+/*
+ * '_mxml_fini()' - Clean up when unloaded.
+ */
+
+static void
+_MXML_FINI(void)
+{
+  _mxml_global_t	*global;	/* Global data */
+
+
+  if (_mxml_key != -1)
+  {
+    if ((global = (_mxml_global_t *)pthread_getspecific(_mxml_key)) != NULL)
+      _mxml_destructor(global);
+
+    pthread_key_delete(_mxml_key);
+    _mxml_key = -1;
+  }
+}
+
+
+/*
+ * '_mxml_global()' - Get global data.
+ */
+
+_mxml_global_t *			/* O - Global data */
+_mxml_global(void)
+{
+  _mxml_global_t	*global;	/* Global data */
+
+
+  pthread_once(&_mxml_key_once, _mxml_init);
+
+  if ((global = (_mxml_global_t *)pthread_getspecific(_mxml_key)) == NULL)
+  {
+    global = (_mxml_global_t *)calloc(1, sizeof(_mxml_global_t));
+    pthread_setspecific(_mxml_key, global);
+
+    global->num_entity_cbs = 1;
+    global->entity_cbs[0]  = _mxml_entity_cb;
+    global->wrap           = 72;
+  }
+
+  return (global);
+}
+
+
+/*
+ * '_mxml_init()' - Initialize global data...
+ */
+
+static void
+_mxml_init(void)
+{
+  pthread_key_create(&_mxml_key, _mxml_destructor);
+}
+
+
+#elif defined(WIN32) && defined(MXML1_EXPORTS) /**** WIN32 threading ****/
+#  include <windows.h>
+
+static DWORD _mxml_tls_index;		/* Index for global storage */
+
+
+/*
+ * 'DllMain()' - Main entry for library.
+ */
+
+BOOL WINAPI				/* O - Success/failure */
+DllMain(HINSTANCE hinst,		/* I - DLL module handle */
+        DWORD     reason,		/* I - Reason */
+        LPVOID    reserved)		/* I - Unused */
+{
+  _mxml_global_t	*global;	/* Global data */
+
+
+  (void)hinst;
+  (void)reserved;
+
+  switch (reason)
+  {
+    case DLL_PROCESS_ATTACH :		/* Called on library initialization */
+        if ((_mxml_tls_index = TlsAlloc()) == TLS_OUT_OF_INDEXES)
+          return (FALSE);
+        break;
+
+    case DLL_THREAD_DETACH :		/* Called when a thread terminates */
+        if ((global = (_mxml_global_t *)TlsGetValue(_mxml_tls_index)) != NULL)
+          free(global);
+        break;
+
+    case DLL_PROCESS_DETACH :		/* Called when library is unloaded */
+        if ((global = (_mxml_global_t *)TlsGetValue(_mxml_tls_index)) != NULL)
+          free(global);
+
+        TlsFree(_mxml_tls_index);
+        break;
+
+    default:
+        break;
+  }
+
+  return (TRUE);
+}
+
+
+/*
+ * '_mxml_global()' - Get global data.
+ */
+
+_mxml_global_t *			/* O - Global data */
+_mxml_global(void)
+{
+  _mxml_global_t	*global;	/* Global data */
+
+
+  if ((global = (_mxml_global_t *)TlsGetValue(_mxml_tls_index)) == NULL)
+  {
+    global = (_mxml_global_t *)calloc(1, sizeof(_mxml_global_t));
+
+    global->num_entity_cbs = 1;
+    global->entity_cbs[0]  = _mxml_entity_cb;
+    global->wrap           = 72;
+
+    TlsSetValue(_mxml_tls_index, (LPVOID)global);
+  }
+
+  return (global);
+}
+
+
+#else					/**** No threading ****/
+/*
+ * '_mxml_global()' - Get global data.
+ */
+
+_mxml_global_t *			/* O - Global data */
+_mxml_global(void)
+{
+  static _mxml_global_t	global =	/* Global data */
+  {
+    NULL,				/* error_cb */
+    1,					/* num_entity_cbs */
+    { _mxml_entity_cb },		/* entity_cbs */
+    72,					/* wrap */
+    NULL,				/* custom_load_cb */
+    NULL				/* custom_save_cb */
+  };
+
+
+  return (&global);
+}
+#endif /* HAVE_PTHREAD_H */
+
+
+/*
+ * End of "$Id: mxml-private.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-private.h b/tools/gator/daemon/mxml/mxml-private.h
new file mode 100644
index 00000000000..c5e4e6b6f27
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-private.h
@@ -0,0 +1,50 @@
+/*
+ * "$Id: mxml-private.h 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Private definitions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * Global, per-thread data...
+ */
+
+typedef struct _mxml_global_s
+{
+  void	(*error_cb)(const char *);
+  int	num_entity_cbs;
+  int	(*entity_cbs[100])(const char *name);
+  int	wrap;
+  mxml_custom_load_cb_t	custom_load_cb;
+  mxml_custom_save_cb_t	custom_save_cb;
+} _mxml_global_t;
+
+
+/*
+ * Functions...
+ */
+
+extern _mxml_global_t	*_mxml_global(void);
+extern int		_mxml_entity_cb(const char *name);
+
+
+/*
+ * End of "$Id: mxml-private.h 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-search.c b/tools/gator/daemon/mxml/mxml-search.c
new file mode 100644
index 00000000000..313a52f0ce2
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-search.c
@@ -0,0 +1,280 @@
+/*
+ * "$Id: mxml-search.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Search/navigation functions for Mini-XML, a small XML-like file
+ * parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * 'mxmlFindElement()' - Find the named element.
+ *
+ * The search is constrained by the name, attribute name, and value; any
+ * NULL names or values are treated as wildcards, so different kinds of
+ * searches can be implemented by looking for all elements of a given name
+ * or all elements with a specific attribute. The descend argument determines
+ * whether the search descends into child nodes; normally you will use
+ * MXML_DESCEND_FIRST for the initial search and MXML_NO_DESCEND to find
+ * additional direct descendents of the node. The top node argument
+ * constrains the search to a particular node's children.
+ */
+
+mxml_node_t *				/* O - Element node or NULL */
+mxmlFindElement(mxml_node_t *node,	/* I - Current node */
+                mxml_node_t *top,	/* I - Top node */
+                const char  *name,	/* I - Element name or NULL for any */
+		const char  *attr,	/* I - Attribute name, or NULL for none */
+		const char  *value,	/* I - Attribute value, or NULL for any */
+		int         descend)	/* I - Descend into tree - MXML_DESCEND, MXML_NO_DESCEND, or MXML_DESCEND_FIRST */
+{
+  const char	*temp;			/* Current attribute value */
+
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || !top || (!attr && value))
+    return (NULL);
+
+ /*
+  * Start with the next node...
+  */
+
+  node = mxmlWalkNext(node, top, descend);
+
+ /*
+  * Loop until we find a matching element...
+  */
+
+  while (node != NULL)
+  {
+   /*
+    * See if this node matches...
+    */
+
+    if (node->type == MXML_ELEMENT &&
+        node->value.element.name &&
+	(!name || !strcmp(node->value.element.name, name)))
+    {
+     /*
+      * See if we need to check for an attribute...
+      */
+
+      if (!attr)
+        return (node);			/* No attribute search, return it... */
+
+     /*
+      * Check for the attribute...
+      */
+
+      if ((temp = mxmlElementGetAttr(node, attr)) != NULL)
+      {
+       /*
+        * OK, we have the attribute, does it match?
+	*/
+
+	if (!value || !strcmp(value, temp))
+	  return (node);		/* Yes, return it... */
+      }
+    }
+
+   /*
+    * No match, move on to the next node...
+    */
+
+    if (descend == MXML_DESCEND)
+      node = mxmlWalkNext(node, top, MXML_DESCEND);
+    else
+      node = node->next;
+  }
+
+  return (NULL);
+}
+
+
+/*
+ * 'mxmlFindPath()' - Find a node with the given path.
+ *
+ * The "path" is a slash-separated list of element names. The name "*" is
+ * considered a wildcard for one or more levels of elements.  For example,
+ * "foo/one/two", "bar/two/one", "*\/one", and so forth.
+ *
+ * The first child node of the found node is returned if the given node has
+ * children and the first child is a value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *				/* O - Found node or NULL */
+mxmlFindPath(mxml_node_t *top,		/* I - Top node */
+	     const char  *path)		/* I - Path to element */
+{
+  mxml_node_t	*node;			/* Current node */
+  char		element[256];		/* Current element name */
+  const char	*pathsep;		/* Separator in path */
+  int		descend;		/* mxmlFindElement option */
+
+
+ /*
+  * Range check input...
+  */
+
+  if (!top || !path || !*path)
+    return (NULL);
+
+ /*
+  * Search each element in the path...
+  */
+
+  node = top;
+  while (*path)
+  {
+   /*
+    * Handle wildcards...
+    */
+
+    if (!strncmp(path, "*/", 2))
+    {
+      path += 2;
+      descend = MXML_DESCEND;
+    }
+    else
+      descend = MXML_DESCEND_FIRST;
+
+   /*
+    * Get the next element in the path...
+    */
+
+    if ((pathsep = strchr(path, '/')) == NULL)
+      pathsep = path + strlen(path);
+
+    if (pathsep == path || (pathsep - path) >= sizeof(element))
+      return (NULL);
+
+    memcpy(element, path, pathsep - path);
+    element[pathsep - path] = '\0';
+
+    if (*pathsep)
+      path = pathsep + 1;
+    else
+      path = pathsep;
+
+   /*
+    * Search for the element...
+    */
+
+    if ((node = mxmlFindElement(node, node, element, NULL, NULL,
+                                descend)) == NULL)
+      return (NULL);
+  }
+
+ /*
+  * If we get this far, return the node or its first child...
+  */
+
+  if (node->child && node->child->type != MXML_ELEMENT)
+    return (node->child);
+  else
+    return (node);
+}
+
+
+/*
+ * 'mxmlWalkNext()' - Walk to the next logical node in the tree.
+ *
+ * The descend argument controls whether the first child is considered
+ * to be the next node. The top node argument constrains the walk to
+ * the node's children.
+ */
+
+mxml_node_t *				/* O - Next node or NULL */
+mxmlWalkNext(mxml_node_t *node,		/* I - Current node */
+             mxml_node_t *top,		/* I - Top node */
+             int         descend)	/* I - Descend into tree - MXML_DESCEND, MXML_NO_DESCEND, or MXML_DESCEND_FIRST */
+{
+  if (!node)
+    return (NULL);
+  else if (node->child && descend)
+    return (node->child);
+  else if (node == top)
+    return (NULL);
+  else if (node->next)
+    return (node->next);
+  else if (node->parent && node->parent != top)
+  {
+    node = node->parent;
+
+    while (!node->next)
+      if (node->parent == top || !node->parent)
+        return (NULL);
+      else
+        node = node->parent;
+
+    return (node->next);
+  }
+  else
+    return (NULL);
+}
+
+
+/*
+ * 'mxmlWalkPrev()' - Walk to the previous logical node in the tree.
+ *
+ * The descend argument controls whether the previous node's last child
+ * is considered to be the previous node. The top node argument constrains
+ * the walk to the node's children.
+ */
+
+mxml_node_t *				/* O - Previous node or NULL */
+mxmlWalkPrev(mxml_node_t *node,		/* I - Current node */
+             mxml_node_t *top,		/* I - Top node */
+             int         descend)	/* I - Descend into tree - MXML_DESCEND, MXML_NO_DESCEND, or MXML_DESCEND_FIRST */
+{
+  if (!node || node == top)
+    return (NULL);
+  else if (node->prev)
+  {
+    if (node->prev->last_child && descend)
+    {
+     /*
+      * Find the last child under the previous node...
+      */
+
+      node = node->prev->last_child;
+
+      while (node->last_child)
+        node = node->last_child;
+
+      return (node);
+    }
+    else
+      return (node->prev);
+  }
+  else if (node->parent != top)
+    return (node->parent);
+  else
+    return (NULL);
+}
+
+
+/*
+ * End of "$Id: mxml-search.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-set.c b/tools/gator/daemon/mxml/mxml-set.c
new file mode 100644
index 00000000000..16d4bf1050d
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-set.c
@@ -0,0 +1,337 @@
+/*
+ * "$Id: mxml-set.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Node set functions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * 'mxmlSetCDATA()' - Set the element name of a CDATA node.
+ *
+ * The node is not changed if it (or its first child) is not a CDATA element node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetCDATA(mxml_node_t *node,		/* I - Node to set */
+             const char  *data)		/* I - New data string */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      strncmp(node->value.element.name, "![CDATA[", 8) &&
+      node->child && node->child->type == MXML_ELEMENT &&
+      !strncmp(node->child->value.element.name, "![CDATA[", 8))
+    node = node->child;
+
+  if (!node || node->type != MXML_ELEMENT || !data ||
+      strncmp(node->value.element.name, "![CDATA[", 8))
+    return (-1);
+
+ /*
+  * Free any old element value and set the new value...
+  */
+
+  if (node->value.element.name)
+    free(node->value.element.name);
+
+  node->value.element.name = _mxml_strdupf("![CDATA[%s]]", data);
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetCustom()' - Set the data and destructor of a custom data node.
+ *
+ * The node is not changed if it (or its first child) is not a custom node.
+ *
+ * @since Mini-XML 2.1@
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetCustom(
+    mxml_node_t              *node,	/* I - Node to set */
+    void                     *data,	/* I - New data pointer */
+    mxml_custom_destroy_cb_t destroy)	/* I - New destructor function */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_CUSTOM)
+    node = node->child;
+
+  if (!node || node->type != MXML_CUSTOM)
+    return (-1);
+
+ /*
+  * Free any old element value and set the new value...
+  */
+
+  if (node->value.custom.data && node->value.custom.destroy)
+    (*(node->value.custom.destroy))(node->value.custom.data);
+
+  node->value.custom.data    = data;
+  node->value.custom.destroy = destroy;
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetElement()' - Set the name of an element node.
+ *
+ * The node is not changed if it is not an element node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetElement(mxml_node_t *node,	/* I - Node to set */
+               const char  *name)	/* I - New name string */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT || !name)
+    return (-1);
+
+ /*
+  * Free any old element value and set the new value...
+  */
+
+  if (node->value.element.name)
+    free(node->value.element.name);
+
+  node->value.element.name = strdup(name);
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetInteger()' - Set the value of an integer node.
+ *
+ * The node is not changed if it (or its first child) is not an integer node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetInteger(mxml_node_t *node,	/* I - Node to set */
+               int         integer)	/* I - Integer value */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_INTEGER)
+    node = node->child;
+
+  if (!node || node->type != MXML_INTEGER)
+    return (-1);
+
+ /*
+  * Set the new value and return...
+  */
+
+  node->value.integer = integer;
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetOpaque()' - Set the value of an opaque node.
+ *
+ * The node is not changed if it (or its first child) is not an opaque node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetOpaque(mxml_node_t *node,	/* I - Node to set */
+              const char  *opaque)	/* I - Opaque string */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_OPAQUE)
+    node = node->child;
+
+  if (!node || node->type != MXML_OPAQUE || !opaque)
+    return (-1);
+
+ /*
+  * Free any old opaque value and set the new value...
+  */
+
+  if (node->value.opaque)
+    free(node->value.opaque);
+
+  node->value.opaque = strdup(opaque);
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetReal()' - Set the value of a real number node.
+ *
+ * The node is not changed if it (or its first child) is not a real number node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetReal(mxml_node_t *node,		/* I - Node to set */
+            double      real)		/* I - Real number value */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_REAL)
+    node = node->child;
+
+  if (!node || node->type != MXML_REAL)
+    return (-1);
+
+ /*
+  * Set the new value and return...
+  */
+
+  node->value.real = real;
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetText()' - Set the value of a text node.
+ *
+ * The node is not changed if it (or its first child) is not a text node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetText(mxml_node_t *node,		/* I - Node to set */
+            int         whitespace,	/* I - 1 = leading whitespace, 0 = no whitespace */
+	    const char  *string)	/* I - String */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_TEXT)
+    node = node->child;
+
+  if (!node || node->type != MXML_TEXT || !string)
+    return (-1);
+
+ /*
+  * Free any old string value and set the new value...
+  */
+
+  if (node->value.text.string)
+    free(node->value.text.string);
+
+  node->value.text.whitespace = whitespace;
+  node->value.text.string     = strdup(string);
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetTextf()' - Set the value of a text node to a formatted string.
+ *
+ * The node is not changed if it (or its first child) is not a text node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetTextf(mxml_node_t *node,		/* I - Node to set */
+             int         whitespace,	/* I - 1 = leading whitespace, 0 = no whitespace */
+             const char  *format,	/* I - Printf-style format string */
+	     ...)			/* I - Additional arguments as needed */
+{
+  va_list	ap;			/* Pointer to arguments */
+
+
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_TEXT)
+    node = node->child;
+
+  if (!node || node->type != MXML_TEXT || !format)
+    return (-1);
+
+ /*
+  * Free any old string value and set the new value...
+  */
+
+  if (node->value.text.string)
+    free(node->value.text.string);
+
+  va_start(ap, format);
+
+  node->value.text.whitespace = whitespace;
+  node->value.text.string     = _mxml_strdupf(format, ap);
+
+  va_end(ap);
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetUserData()' - Set the user data pointer for a node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetUserData(mxml_node_t *node,	/* I - Node to set */
+                void        *data)	/* I - User data pointer */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (-1);
+
+ /*
+  * Set the user data pointer and return...
+  */
+
+  node->user_data = data;
+  return (0);
+}
+
+
+/*
+ * End of "$Id: mxml-set.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-string.c b/tools/gator/daemon/mxml/mxml-string.c
new file mode 100644
index 00000000000..9d5b58e6adb
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-string.c
@@ -0,0 +1,469 @@
+/*
+ * "$Id: mxml-string.c 454 2014-01-05 03:25:07Z msweet $"
+ *
+ * String functions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+
+
+/*
+ * The va_copy macro is part of C99, but many compilers don't implement it.
+ * Provide a "direct assignment" implmentation when va_copy isn't defined...
+ */
+
+#ifndef va_copy
+#  ifdef __va_copy
+#    define va_copy(dst,src) __va_copy(dst,src)
+#  else
+#    define va_copy(dst,src) memcpy(&dst, src, sizeof(va_list))
+#  endif /* __va_copy */
+#endif /* va_copy */
+
+
+#ifndef HAVE_SNPRINTF
+/*
+ * '_mxml_snprintf()' - Format a string.
+ */
+
+int					/* O - Number of bytes formatted */
+_mxml_snprintf(char       *buffer,	/* I - Output buffer */
+               size_t     bufsize,	/* I - Size of output buffer */
+	       const char *format,	/* I - Printf-style format string */
+	       ...)			/* I - Additional arguments as needed */
+{
+  va_list	ap;			/* Argument list */
+  int		bytes;			/* Number of bytes formatted */
+
+
+  va_start(ap, format);
+  bytes = vsnprintf(buffer, bufsize, format, ap);
+  va_end(ap);
+
+  return (bytes);
+}
+#endif /* !HAVE_SNPRINTF */
+
+
+/*
+ * '_mxml_strdup()' - Duplicate a string.
+ */
+
+#ifndef HAVE_STRDUP
+char *					/* O - New string pointer */
+_mxml_strdup(const char *s)		/* I - String to duplicate */
+{
+  char	*t;				/* New string pointer */
+
+
+  if (s == NULL)
+    return (NULL);
+
+  if ((t = malloc(strlen(s) + 1)) == NULL)
+    return (NULL);
+
+  return (strcpy(t, s));
+}
+#endif /* !HAVE_STRDUP */
+
+
+/*
+ * '_mxml_strdupf()' - Format and duplicate a string.
+ */
+
+char *					/* O - New string pointer */
+_mxml_strdupf(const char *format,	/* I - Printf-style format string */
+              ...)			/* I - Additional arguments as needed */
+{
+  va_list	ap;			/* Pointer to additional arguments */
+  char		*s;			/* Pointer to formatted string */
+
+
+ /*
+  * Get a pointer to the additional arguments, format the string,
+  * and return it...
+  */
+
+  va_start(ap, format);
+  s = _mxml_vstrdupf(format, ap);
+  va_end(ap);
+
+  return (s);
+}
+
+
+#ifndef HAVE_VSNPRINTF
+/*
+ * '_mxml_vsnprintf()' - Format a string into a fixed size buffer.
+ */
+
+int					/* O - Number of bytes formatted */
+_mxml_vsnprintf(char       *buffer,	/* O - Output buffer */
+                size_t     bufsize,	/* O - Size of output buffer */
+		const char *format,	/* I - Printf-style format string */
+ 		va_list    ap)		/* I - Pointer to additional arguments */
+{
+  char		*bufptr,		/* Pointer to position in buffer */
+		*bufend,		/* Pointer to end of buffer */
+		sign,			/* Sign of format width */
+		size,			/* Size character (h, l, L) */
+		type;			/* Format type character */
+  int		width,			/* Width of field */
+		prec;			/* Number of characters of precision */
+  char		tformat[100],		/* Temporary format string for sprintf() */
+		*tptr,			/* Pointer into temporary format */
+		temp[1024];		/* Buffer for formatted numbers */
+  char		*s;			/* Pointer to string */
+  int		slen;			/* Length of string */
+  int		bytes;			/* Total number of bytes needed */
+
+
+ /*
+  * Loop through the format string, formatting as needed...
+  */
+
+  bufptr = buffer;
+  bufend = buffer + bufsize - 1;
+  bytes  = 0;
+
+  while (*format)
+  {
+    if (*format == '%')
+    {
+      tptr = tformat;
+      *tptr++ = *format++;
+
+      if (*format == '%')
+      {
+        if (bufptr && bufptr < bufend)
+          *bufptr++ = *format;
+        bytes ++;
+        format ++;
+	continue;
+      }
+      else if (strchr(" -+#\'", *format))
+      {
+        *tptr++ = *format;
+        sign = *format++;
+      }
+      else
+        sign = 0;
+
+      if (*format == '*')
+      {
+       /*
+        * Get width from argument...
+	*/
+
+	format ++;
+	width = va_arg(ap, int);
+
+	snprintf(tptr, sizeof(tformat) - (tptr - tformat), "%d", width);
+	tptr += strlen(tptr);
+      }
+      else
+      {
+	width = 0;
+
+	while (isdigit(*format & 255))
+	{
+	  if (tptr < (tformat + sizeof(tformat) - 1))
+	    *tptr++ = *format;
+
+	  width = width * 10 + *format++ - '0';
+	}
+      }
+
+      if (*format == '.')
+      {
+	if (tptr < (tformat + sizeof(tformat) - 1))
+	  *tptr++ = *format;
+
+        format ++;
+
+        if (*format == '*')
+	{
+         /*
+	  * Get precision from argument...
+	  */
+
+	  format ++;
+	  prec = va_arg(ap, int);
+
+	  snprintf(tptr, sizeof(tformat) - (tptr - tformat), "%d", prec);
+	  tptr += strlen(tptr);
+	}
+	else
+	{
+	  prec = 0;
+
+	  while (isdigit(*format & 255))
+	  {
+	    if (tptr < (tformat + sizeof(tformat) - 1))
+	      *tptr++ = *format;
+
+	    prec = prec * 10 + *format++ - '0';
+	  }
+	}
+      }
+      else
+        prec = -1;
+
+      if (*format == 'l' && format[1] == 'l')
+      {
+        size = 'L';
+
+	if (tptr < (tformat + sizeof(tformat) - 2))
+	{
+	  *tptr++ = 'l';
+	  *tptr++ = 'l';
+	}
+
+	format += 2;
+      }
+      else if (*format == 'h' || *format == 'l' || *format == 'L')
+      {
+	if (tptr < (tformat + sizeof(tformat) - 1))
+	  *tptr++ = *format;
+
+        size = *format++;
+      }
+
+      if (!*format)
+        break;
+
+      if (tptr < (tformat + sizeof(tformat) - 1))
+        *tptr++ = *format;
+
+      type  = *format++;
+      *tptr = '\0';
+
+      switch (type)
+      {
+	case 'E' : /* Floating point formats */
+	case 'G' :
+	case 'e' :
+	case 'f' :
+	case 'g' :
+	    if ((width + 2) > sizeof(temp))
+	      break;
+
+	    sprintf(temp, tformat, va_arg(ap, double));
+
+            bytes += strlen(temp);
+
+            if (bufptr)
+	    {
+	      if ((bufptr + strlen(temp)) > bufend)
+	      {
+		strncpy(bufptr, temp, (size_t)(bufend - bufptr));
+		bufptr = bufend;
+	      }
+	      else
+	      {
+		strcpy(bufptr, temp);
+		bufptr += strlen(temp);
+	      }
+	    }
+	    break;
+
+        case 'B' : /* Integer formats */
+	case 'X' :
+	case 'b' :
+        case 'd' :
+	case 'i' :
+	case 'o' :
+	case 'u' :
+	case 'x' :
+	    if ((width + 2) > sizeof(temp))
+	      break;
+
+#ifdef HAVE_LONG_LONG
+	    if (size == 'L')
+	      sprintf(temp, tformat, va_arg(ap, long long));
+	    else
+#endif /* HAVE_LONG_LONG */
+	    sprintf(temp, tformat, va_arg(ap, int));
+
+            bytes += strlen(temp);
+
+	    if (bufptr)
+	    {
+	      if ((bufptr + strlen(temp)) > bufend)
+	      {
+		strncpy(bufptr, temp, (size_t)(bufend - bufptr));
+		bufptr = bufend;
+	      }
+	      else
+	      {
+		strcpy(bufptr, temp);
+		bufptr += strlen(temp);
+	      }
+	    }
+	    break;
+
+	case 'p' : /* Pointer value */
+	    if ((width + 2) > sizeof(temp))
+	      break;
+
+	    sprintf(temp, tformat, va_arg(ap, void *));
+
+            bytes += strlen(temp);
+
+	    if (bufptr)
+	    {
+	      if ((bufptr + strlen(temp)) > bufend)
+	      {
+		strncpy(bufptr, temp, (size_t)(bufend - bufptr));
+		bufptr = bufend;
+	      }
+	      else
+	      {
+		strcpy(bufptr, temp);
+		bufptr += strlen(temp);
+	      }
+	    }
+	    break;
+
+        case 'c' : /* Character or character array */
+	    bytes += width;
+
+	    if (bufptr)
+	    {
+	      if (width <= 1)
+	        *bufptr++ = va_arg(ap, int);
+	      else
+	      {
+		if ((bufptr + width) > bufend)
+		  width = bufend - bufptr;
+
+		memcpy(bufptr, va_arg(ap, char *), (size_t)width);
+		bufptr += width;
+	      }
+	    }
+	    break;
+
+	case 's' : /* String */
+	    if ((s = va_arg(ap, char *)) == NULL)
+	      s = "(null)";
+
+	    slen = strlen(s);
+	    if (slen > width && prec != width)
+	      width = slen;
+
+            bytes += width;
+
+	    if (bufptr)
+	    {
+	      if ((bufptr + width) > bufend)
+	        width = bufend - bufptr;
+
+              if (slen > width)
+	        slen = width;
+
+	      if (sign == '-')
+	      {
+		strncpy(bufptr, s, (size_t)slen);
+		memset(bufptr + slen, ' ', (size_t)(width - slen));
+	      }
+	      else
+	      {
+		memset(bufptr, ' ', (size_t)(width - slen));
+		strncpy(bufptr + width - slen, s, (size_t)slen);
+	      }
+
+	      bufptr += width;
+	    }
+	    break;
+
+	case 'n' : /* Output number of chars so far */
+	    *(va_arg(ap, int *)) = bytes;
+	    break;
+      }
+    }
+    else
+    {
+      bytes ++;
+
+      if (bufptr && bufptr < bufend)
+        *bufptr++ = *format;
+
+      format ++;
+    }
+  }
+
+ /*
+  * Nul-terminate the string and return the number of characters needed.
+  */
+
+  *bufptr = '\0';
+
+  return (bytes);
+}
+#endif /* !HAVE_VSNPRINTF */
+
+
+/*
+ * '_mxml_vstrdupf()' - Format and duplicate a string.
+ */
+
+char *					/* O - New string pointer */
+_mxml_vstrdupf(const char *format,	/* I - Printf-style format string */
+               va_list    ap)		/* I - Pointer to additional arguments */
+{
+  int		bytes;			/* Number of bytes required */
+  char		*buffer,		/* String buffer */
+		temp[256];		/* Small buffer for first vsnprintf */
+  va_list	apcopy;			/* Copy of argument list */
+
+
+ /*
+  * First format with a tiny buffer; this will tell us how many bytes are
+  * needed...
+  */
+
+  va_copy(apcopy, ap);
+  bytes = vsnprintf(temp, sizeof(temp), format, apcopy);
+
+  if (bytes < sizeof(temp))
+  {
+   /*
+    * Hey, the formatted string fits in the tiny buffer, so just dup that...
+    */
+
+    return (strdup(temp));
+  }
+
+ /*
+  * Allocate memory for the whole thing and reformat to the new, larger
+  * buffer...
+  */
+
+  if ((buffer = calloc(1, bytes + 1)) != NULL)
+    vsnprintf(buffer, bytes + 1, format, ap);
+
+ /*
+  * Return the new string...
+  */
+
+  return (buffer);
+}
+
+
+/*
+ * End of "$Id: mxml-string.c 454 2014-01-05 03:25:07Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml.h b/tools/gator/daemon/mxml/mxml.h
new file mode 100644
index 00000000000..bba5fd23a67
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml.h
@@ -0,0 +1,332 @@
+/*
+ * "$Id: mxml.h 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Header file for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Prevent multiple inclusion...
+ */
+
+#ifndef _mxml_h_
+#  define _mxml_h_
+
+/*
+ * Include necessary headers...
+ */
+
+#  include <stdio.h>
+#  include <stdlib.h>
+#  include <string.h>
+#  include <ctype.h>
+#  include <errno.h>
+
+
+/*
+ * Constants...
+ */
+
+#  define MXML_MAJOR_VERSION	2	/* Major version number */
+#  define MXML_MINOR_VERSION	8	/* Minor version number */
+
+#  define MXML_TAB		8	/* Tabs every N columns */
+
+#  define MXML_NO_CALLBACK	0	/* Don't use a type callback */
+#  define MXML_INTEGER_CALLBACK	mxml_integer_cb
+					/* Treat all data as integers */
+#  define MXML_OPAQUE_CALLBACK	mxml_opaque_cb
+					/* Treat all data as opaque */
+#  define MXML_REAL_CALLBACK	mxml_real_cb
+					/* Treat all data as real numbers */
+#  define MXML_TEXT_CALLBACK	0	/* Treat all data as text */
+#  define MXML_IGNORE_CALLBACK	mxml_ignore_cb
+					/* Ignore all non-element content */
+
+#  define MXML_NO_PARENT	0	/* No parent for the node */
+
+#  define MXML_DESCEND		1	/* Descend when finding/walking */
+#  define MXML_NO_DESCEND	0	/* Don't descend when finding/walking */
+#  define MXML_DESCEND_FIRST	-1	/* Descend for first find */
+
+#  define MXML_WS_BEFORE_OPEN	0	/* Callback for before open tag */
+#  define MXML_WS_AFTER_OPEN	1	/* Callback for after open tag */
+#  define MXML_WS_BEFORE_CLOSE	2	/* Callback for before close tag */
+#  define MXML_WS_AFTER_CLOSE	3	/* Callback for after close tag */
+
+#  define MXML_ADD_BEFORE	0	/* Add node before specified node */
+#  define MXML_ADD_AFTER	1	/* Add node after specified node */
+#  define MXML_ADD_TO_PARENT	NULL	/* Add node relative to parent */
+
+
+/*
+ * Data types...
+ */
+
+typedef enum mxml_sax_event_e		/**** SAX event type. ****/
+{
+  MXML_SAX_CDATA,			/* CDATA node */
+  MXML_SAX_COMMENT,			/* Comment node */
+  MXML_SAX_DATA,			/* Data node */
+  MXML_SAX_DIRECTIVE,			/* Processing directive node */
+  MXML_SAX_ELEMENT_CLOSE,		/* Element closed */
+  MXML_SAX_ELEMENT_OPEN			/* Element opened */
+} mxml_sax_event_t;
+
+typedef enum mxml_type_e		/**** The XML node type. ****/
+{
+  MXML_IGNORE = -1,			/* Ignore/throw away node @since Mini-XML 2.3@ */
+  MXML_ELEMENT,				/* XML element with attributes */
+  MXML_INTEGER,				/* Integer value */
+  MXML_OPAQUE,				/* Opaque string */
+  MXML_REAL,				/* Real value */
+  MXML_TEXT,				/* Text fragment */
+  MXML_CUSTOM				/* Custom data @since Mini-XML 2.1@ */
+} mxml_type_t;
+
+typedef void (*mxml_custom_destroy_cb_t)(void *);
+					/**** Custom data destructor ****/
+
+typedef void (*mxml_error_cb_t)(const char *);
+					/**** Error callback function ****/
+
+typedef struct mxml_attr_s		/**** An XML element attribute value. @private@ ****/
+{
+  char			*name;		/* Attribute name */
+  char			*value;		/* Attribute value */
+} mxml_attr_t;
+
+typedef struct mxml_element_s		/**** An XML element value. @private@ ****/
+{
+  char			*name;		/* Name of element */
+  int			num_attrs;	/* Number of attributes */
+  mxml_attr_t		*attrs;		/* Attributes */
+} mxml_element_t;
+
+typedef struct mxml_text_s		/**** An XML text value. @private@ ****/
+{
+  int			whitespace;	/* Leading whitespace? */
+  char			*string;	/* Fragment string */
+} mxml_text_t;
+
+typedef struct mxml_custom_s		/**** An XML custom value. @private@ ****/
+{
+  void			*data;		/* Pointer to (allocated) custom data */
+  mxml_custom_destroy_cb_t destroy;	/* Pointer to destructor function */
+} mxml_custom_t;
+
+typedef union mxml_value_u		/**** An XML node value. @private@ ****/
+{
+  mxml_element_t	element;	/* Element */
+  int			integer;	/* Integer number */
+  char			*opaque;	/* Opaque string */
+  double		real;		/* Real number */
+  mxml_text_t		text;		/* Text fragment */
+  mxml_custom_t		custom;		/* Custom data @since Mini-XML 2.1@ */
+} mxml_value_t;
+
+struct mxml_node_s			/**** An XML node. @private@ ****/
+{
+  mxml_type_t		type;		/* Node type */
+  struct mxml_node_s	*next;		/* Next node under same parent */
+  struct mxml_node_s	*prev;		/* Previous node under same parent */
+  struct mxml_node_s	*parent;	/* Parent node */
+  struct mxml_node_s	*child;		/* First child node */
+  struct mxml_node_s	*last_child;	/* Last child node */
+  mxml_value_t		value;		/* Node value */
+  int			ref_count;	/* Use count */
+  void			*user_data;	/* User data */
+};
+
+typedef struct mxml_node_s mxml_node_t;	/**** An XML node. ****/
+
+struct mxml_index_s			 /**** An XML node index. @private@ ****/
+{
+  char			*attr;		/* Attribute used for indexing or NULL */
+  int			num_nodes;	/* Number of nodes in index */
+  int			alloc_nodes;	/* Allocated nodes in index */
+  int			cur_node;	/* Current node */
+  mxml_node_t		**nodes;	/* Node array */
+};
+
+typedef struct mxml_index_s mxml_index_t;
+					/**** An XML node index. ****/
+
+typedef int (*mxml_custom_load_cb_t)(mxml_node_t *, const char *);
+					/**** Custom data load callback function ****/
+
+typedef char *(*mxml_custom_save_cb_t)(mxml_node_t *);
+					/**** Custom data save callback function ****/
+
+typedef int (*mxml_entity_cb_t)(const char *);
+					/**** Entity callback function */
+
+typedef mxml_type_t (*mxml_load_cb_t)(mxml_node_t *);
+					/**** Load callback function ****/
+
+typedef const char *(*mxml_save_cb_t)(mxml_node_t *, int);
+					/**** Save callback function ****/
+
+typedef void (*mxml_sax_cb_t)(mxml_node_t *, mxml_sax_event_t, void *);
+					/**** SAX callback function ****/
+
+
+/*
+ * C++ support...
+ */
+
+#  ifdef __cplusplus
+extern "C" {
+#  endif /* __cplusplus */
+
+/*
+ * Prototypes...
+ */
+
+extern void		mxmlAdd(mxml_node_t *parent, int where,
+			        mxml_node_t *child, mxml_node_t *node);
+extern void		mxmlDelete(mxml_node_t *node);
+extern void		mxmlElementDeleteAttr(mxml_node_t *node,
+			                      const char *name);
+extern const char	*mxmlElementGetAttr(mxml_node_t *node, const char *name);
+extern void		mxmlElementSetAttr(mxml_node_t *node, const char *name,
+			                   const char *value);
+extern void		mxmlElementSetAttrf(mxml_node_t *node, const char *name,
+			                    const char *format, ...)
+#    ifdef __GNUC__
+__attribute__ ((__format__ (__printf__, 3, 4)))
+#    endif /* __GNUC__ */
+;
+extern int		mxmlEntityAddCallback(mxml_entity_cb_t cb);
+extern const char	*mxmlEntityGetName(int val);
+extern int		mxmlEntityGetValue(const char *name);
+extern void		mxmlEntityRemoveCallback(mxml_entity_cb_t cb);
+extern mxml_node_t	*mxmlFindElement(mxml_node_t *node, mxml_node_t *top,
+			                 const char *name, const char *attr,
+					 const char *value, int descend);
+extern mxml_node_t	*mxmlFindPath(mxml_node_t *node, const char *path);
+extern const char	*mxmlGetCDATA(mxml_node_t *node);
+extern const void	*mxmlGetCustom(mxml_node_t *node);
+extern const char	*mxmlGetElement(mxml_node_t *node);
+extern mxml_node_t	*mxmlGetFirstChild(mxml_node_t *node);
+extern int		mxmlGetInteger(mxml_node_t *node);
+extern mxml_node_t	*mxmlGetLastChild(mxml_node_t *node);
+extern mxml_node_t	*mxmlGetNextSibling(mxml_node_t *node);
+extern const char	*mxmlGetOpaque(mxml_node_t *node);
+extern mxml_node_t	*mxmlGetParent(mxml_node_t *node);
+extern mxml_node_t	*mxmlGetPrevSibling(mxml_node_t *node);
+extern double		mxmlGetReal(mxml_node_t *node);
+extern int		mxmlGetRefCount(mxml_node_t *node);
+extern const char	*mxmlGetText(mxml_node_t *node, int *whitespace);
+extern mxml_type_t	mxmlGetType(mxml_node_t *node);
+extern void		*mxmlGetUserData(mxml_node_t *node);
+extern void		mxmlIndexDelete(mxml_index_t *ind);
+extern mxml_node_t	*mxmlIndexEnum(mxml_index_t *ind);
+extern mxml_node_t	*mxmlIndexFind(mxml_index_t *ind,
+			               const char *element,
+			               const char *value);
+extern int		mxmlIndexGetCount(mxml_index_t *ind);
+extern mxml_index_t	*mxmlIndexNew(mxml_node_t *node, const char *element,
+			              const char *attr);
+extern mxml_node_t	*mxmlIndexReset(mxml_index_t *ind);
+extern mxml_node_t	*mxmlLoadFd(mxml_node_t *top, int fd,
+			            mxml_type_t (*cb)(mxml_node_t *));
+extern mxml_node_t	*mxmlLoadFile(mxml_node_t *top, FILE *fp,
+			              mxml_type_t (*cb)(mxml_node_t *));
+extern mxml_node_t	*mxmlLoadString(mxml_node_t *top, const char *s,
+			                mxml_type_t (*cb)(mxml_node_t *));
+extern mxml_node_t	*mxmlNewCDATA(mxml_node_t *parent, const char *string);
+extern mxml_node_t	*mxmlNewCustom(mxml_node_t *parent, void *data,
+			               mxml_custom_destroy_cb_t destroy);
+extern mxml_node_t	*mxmlNewElement(mxml_node_t *parent, const char *name);
+extern mxml_node_t	*mxmlNewInteger(mxml_node_t *parent, int integer);
+extern mxml_node_t	*mxmlNewOpaque(mxml_node_t *parent, const char *opaque);
+extern mxml_node_t	*mxmlNewReal(mxml_node_t *parent, double real);
+extern mxml_node_t	*mxmlNewText(mxml_node_t *parent, int whitespace,
+			             const char *string);
+extern mxml_node_t	*mxmlNewTextf(mxml_node_t *parent, int whitespace,
+			              const char *format, ...)
+#    ifdef __GNUC__
+__attribute__ ((__format__ (__printf__, 3, 4)))
+#    endif /* __GNUC__ */
+;
+extern mxml_node_t	*mxmlNewXML(const char *version);
+extern int		mxmlRelease(mxml_node_t *node);
+extern void		mxmlRemove(mxml_node_t *node);
+extern int		mxmlRetain(mxml_node_t *node);
+extern char		*mxmlSaveAllocString(mxml_node_t *node,
+			        	     mxml_save_cb_t cb);
+extern int		mxmlSaveFd(mxml_node_t *node, int fd,
+			           mxml_save_cb_t cb);
+extern int		mxmlSaveFile(mxml_node_t *node, FILE *fp,
+			             mxml_save_cb_t cb);
+extern int		mxmlSaveString(mxml_node_t *node, char *buffer,
+			               int bufsize, mxml_save_cb_t cb);
+extern mxml_node_t	*mxmlSAXLoadFd(mxml_node_t *top, int fd,
+			               mxml_type_t (*cb)(mxml_node_t *),
+			               mxml_sax_cb_t sax, void *sax_data);
+extern mxml_node_t	*mxmlSAXLoadFile(mxml_node_t *top, FILE *fp,
+			                 mxml_type_t (*cb)(mxml_node_t *),
+			                 mxml_sax_cb_t sax, void *sax_data);
+extern mxml_node_t	*mxmlSAXLoadString(mxml_node_t *top, const char *s,
+			                   mxml_type_t (*cb)(mxml_node_t *),
+			                   mxml_sax_cb_t sax, void *sax_data);
+extern int		mxmlSetCDATA(mxml_node_t *node, const char *data);
+extern int		mxmlSetCustom(mxml_node_t *node, void *data,
+			              mxml_custom_destroy_cb_t destroy);
+extern void		mxmlSetCustomHandlers(mxml_custom_load_cb_t load,
+			                      mxml_custom_save_cb_t save);
+extern int		mxmlSetElement(mxml_node_t *node, const char *name);
+extern void		mxmlSetErrorCallback(mxml_error_cb_t cb);
+extern int		mxmlSetInteger(mxml_node_t *node, int integer);
+extern int		mxmlSetOpaque(mxml_node_t *node, const char *opaque);
+extern int		mxmlSetReal(mxml_node_t *node, double real);
+extern int		mxmlSetText(mxml_node_t *node, int whitespace,
+			            const char *string);
+extern int		mxmlSetTextf(mxml_node_t *node, int whitespace,
+			             const char *format, ...)
+#    ifdef __GNUC__
+__attribute__ ((__format__ (__printf__, 3, 4)))
+#    endif /* __GNUC__ */
+;
+extern int		mxmlSetUserData(mxml_node_t *node, void *data);
+extern void		mxmlSetWrapMargin(int column);
+extern mxml_node_t	*mxmlWalkNext(mxml_node_t *node, mxml_node_t *top,
+			              int descend);
+extern mxml_node_t	*mxmlWalkPrev(mxml_node_t *node, mxml_node_t *top,
+			              int descend);
+
+
+/*
+ * Semi-private functions...
+ */
+
+extern void		mxml_error(const char *format, ...);
+extern mxml_type_t	mxml_ignore_cb(mxml_node_t *node);
+extern mxml_type_t	mxml_integer_cb(mxml_node_t *node);
+extern mxml_type_t	mxml_opaque_cb(mxml_node_t *node);
+extern mxml_type_t	mxml_real_cb(mxml_node_t *node);
+
+
+/*
+ * C++ support...
+ */
+
+#  ifdef __cplusplus
+}
+#  endif /* __cplusplus */
+#endif /* !_mxml_h_ */
+
+
+/*
+ * End of "$Id: mxml.h 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/notify/COPYING b/tools/gator/daemon/notify/COPYING
new file mode 100644
index 00000000000..d159169d105
--- /dev/null
+++ b/tools/gator/daemon/notify/COPYING
@@ -0,0 +1,339 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users.  This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it.  (Some other Free Software Foundation software is covered by
+the GNU Lesser General Public License instead.)  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must show them these terms so they know their
+rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary.  To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                    GNU GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License.  The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language.  (Hereinafter, translation is included without limitation in
+the term "modification".)  Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+  1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+  2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) You must cause the modified files to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in
+    whole or in part contains or is derived from the Program or any
+    part thereof, to be licensed as a whole at no charge to all third
+    parties under the terms of this License.
+
+    c) If the modified program normally reads commands interactively
+    when run, you must cause it, when started running for such
+    interactive use in the most ordinary way, to print or display an
+    announcement including an appropriate copyright notice and a
+    notice that there is no warranty (or else, saying that you provide
+    a warranty) and that users may redistribute the program under
+    these conditions, and telling the user how to view a copy of this
+    License.  (Exception: if the Program itself is interactive but
+    does not normally print such an announcement, your work based on
+    the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+    a) Accompany it with the complete corresponding machine-readable
+    source code, which must be distributed under the terms of Sections
+    1 and 2 above on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three
+    years, to give any third party, for a charge no more than your
+    cost of physically performing source distribution, a complete
+    machine-readable copy of the corresponding source code, to be
+    distributed under the terms of Sections 1 and 2 above on a medium
+    customarily used for software interchange; or,
+
+    c) Accompany it with the information you received as to the offer
+    to distribute corresponding source code.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form with such
+    an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it.  For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable.  However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License.  Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+  5. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Program or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+  6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded.  In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+  9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+  10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this.  Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+                            NO WARRANTY
+
+  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License along
+    with this program; if not, write to the Free Software Foundation, Inc.,
+    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+    Gnomovision version 69, Copyright (C) year name of author
+    Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+  `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+  <signature of Ty Coon>, 1 April 1989
+  Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs.  If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.
diff --git a/tools/gator/daemon/notify/Makefile b/tools/gator/daemon/notify/Makefile
new file mode 100644
index 00000000000..0d8f0415f0e
--- /dev/null
+++ b/tools/gator/daemon/notify/Makefile
@@ -0,0 +1,24 @@
+ifneq ($(SDKDIR),)
+
+# Find the oldest SDK Platform installed >= 16
+SDK_PLATFORM := $(shell ls -d $(SDKDIR)/platforms/android-1[6-9] $(SDKDIR)/platforms/android-[2-9][0-9] | head -1)
+# Find the newest SDK Build-tools
+SDK_BUILD_TOOLS := $(shell ls -d $(SDKDIR)/build-tools/* | tail -1)
+
+all: notify.dex
+
+notify.dex: Notify.java
+	javac -cp $(SDK_PLATFORM)/data/layoutlib.jar -source 1.6 -target 1.6 $^
+	$(SDK_BUILD_TOOLS)/dx --dex --output=$@ $(^:%.java=%.class)
+
+else
+
+all:
+	$(error Please specify SDKDIR as the location to the Android SDK)
+
+endif
+
+.PHONY: clean
+
+clean:
+	rm -f *~ *.class *.dex
diff --git a/tools/gator/daemon/notify/Notify.java b/tools/gator/daemon/notify/Notify.java
new file mode 100644
index 00000000000..97024511488
--- /dev/null
+++ b/tools/gator/daemon/notify/Notify.java
@@ -0,0 +1,31 @@
+/**
+ * Copyright (C) ARM Limited 2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+import android.os.IBinder;
+import android.os.Parcel;
+import android.os.RemoteException;
+import android.os.ServiceManager;
+
+public class Notify {
+	public static void main(String[] args) throws RemoteException {
+		for (String service : ServiceManager.listServices()) {
+			IBinder b = ServiceManager.checkService(service);
+			if (b != null) {
+				Parcel p = null;
+				try {
+					p = Parcel.obtain();
+					b.transact(IBinder.SYSPROPS_TRANSACTION, p, null, 0);
+				} finally {
+					if (p != null) {
+						p.recycle();
+					}
+				}
+			}
+		}
+	}
+}
diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c
index dcc665228c7..deb3569ab00 100644
--- a/tools/lib/traceevent/kbuffer-parse.c
+++ b/tools/lib/traceevent/kbuffer-parse.c
@@ -372,7 +372,6 @@ translate_data(struct kbuffer *kbuf, void *data, void **rptr,
 	switch (type_len) {
 	case KBUFFER_TYPE_PADDING:
 		*length = read_4(kbuf, data);
-		data += *length;
 		break;
 
 	case KBUFFER_TYPE_TIME_EXTEND:
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index 47b78b3f032..85b523885f9 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -7,6 +7,12 @@
 
 static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
 
+int __weak sched_getcpu(void)
+{
+	errno = ENOSYS;
+	return -1;
+}
+
 static int perf_flag_probe(void)
 {
 	/* use 'safest' configuration as used in perf_evsel__fallback() */
@@ -25,6 +31,10 @@ static int perf_flag_probe(void)
 	if (cpu < 0)
 		cpu = 0;
 
+	/*
+	 * Using -1 for the pid is a workaround to avoid gratuitous jump label
+	 * changes.
+	 */
 	while (1) {
 		/* check cloexec flag */
 		fd = sys_perf_event_open(&attr, pid, cpu, -1,
@@ -47,16 +57,24 @@ static int perf_flag_probe(void)
 		  err, strerror_r(err, sbuf, sizeof(sbuf)));
 
 	/* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */
-	fd = sys_perf_event_open(&attr, pid, cpu, -1, 0);
+	while (1) {
+		fd = sys_perf_event_open(&attr, pid, cpu, -1, 0);
+		if (fd < 0 && pid == -1 && errno == EACCES) {
+			pid = 0;
+			continue;
+		}
+		break;
+	}
 	err = errno;
 
+	if (fd >= 0)
+		close(fd);
+
 	if (WARN_ONCE(fd < 0 && err != EBUSY,
 		      "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n",
 		      err, strerror_r(err, sbuf, sizeof(sbuf))))
 		return -1;
 
-	close(fd);
-
 	return 0;
 }
 
diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h
index 94a5a7d829d..68888c29b04 100644
--- a/tools/perf/util/cloexec.h
+++ b/tools/perf/util/cloexec.h
@@ -3,4 +3,10 @@
 
 unsigned long perf_event_open_cloexec_flag(void);
 
+#ifdef __GLIBC_PREREQ
+#if !__GLIBC_PREREQ(2, 6)
+extern int sched_getcpu(void) __THROW;
+#endif
+#endif
+
 #endif /* __PERF_CLOEXEC_H */
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 5699e7e2a79..50a7b115698 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -214,6 +214,7 @@ struct events_stats {
 	u32 nr_invalid_chains;
 	u32 nr_unknown_id;
 	u32 nr_unprocessable_samples;
+	u32 nr_unordered_events;
 };
 
 struct attr_event {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 6702ac28754..80dbba095f3 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -521,15 +521,11 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event,
 		return -ETIME;
 
 	if (timestamp < oe->last_flush) {
-		WARN_ONCE(1, "Timestamp below last timeslice flush\n");
-
-		pr_oe_time(timestamp,      "out of order event");
+		pr_oe_time(timestamp,      "out of order event\n");
 		pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n",
 			   oe->last_flush_type);
 
-		/* We could get out of order messages after forced flush. */
-		if (oe->last_flush_type != OE_FLUSH__HALF)
-			return -EINVAL;
+		s->stats.nr_unordered_events++;
 	}
 
 	new = ordered_events__new(oe, timestamp, event);
@@ -1057,6 +1053,9 @@ static void perf_session__warn_about_errors(const struct perf_session *session,
 			    "Do you have a KVM guest running and not using 'perf kvm'?\n",
 			    session->stats.nr_unprocessable_samples);
 	}
+
+	if (session->stats.nr_unordered_events != 0)
+		ui__warning("%u out of order events recorded.\n", session->stats.nr_unordered_events);
 }
 
 volatile int session_done;
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 1e23a5bfb04..fcaf06b4055 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -48,6 +48,10 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym)
 	return GELF_ST_TYPE(sym->st_info);
 }
 
+#ifndef STT_GNU_IFUNC
+#define STT_GNU_IFUNC 10
+#endif
+
 static inline int elf_sym__is_function(const GElf_Sym *sym)
 {
 	return (elf_sym__type(sym) == STT_FUNC ||
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index d1b3a361e52..4039854560d 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -1,8 +1,12 @@
 CC		= $(CROSS_COMPILE)gcc
-BUILD_OUTPUT	:= $(PWD)
+BUILD_OUTPUT	:= $(CURDIR)
 PREFIX		:= /usr
 DESTDIR		:=
 
+ifeq ("$(origin O)", "command line")
+	BUILD_OUTPUT := $(O)
+endif
+
 turbostat : turbostat.c
 CFLAGS +=	-Wall
 CFLAGS +=	-DMSRHEADER='"../../../../arch/x86/include/uapi/asm/msr-index.h"'
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index bf139818078..dcb1e9ac949 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -3571,7 +3571,9 @@ sub test_this_config {
     undef %configs;
     assign_configs \%configs, $output_config;
 
-    return $config if (!defined($configs{$config}));
+    if (!defined($configs{$config}) || $configs{$config} =~ /^#/) {
+	return $config;
+    }
 
     doprint "disabling config $config did not change .config\n";
 
diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c
index 1b3ff2fda4d..517785052f1 100644
--- a/tools/testing/selftests/mount/unprivileged-remount-test.c
+++ b/tools/testing/selftests/mount/unprivileged-remount-test.c
@@ -6,6 +6,8 @@
 #include <sys/types.h>
 #include <sys/mount.h>
 #include <sys/wait.h>
+#include <sys/vfs.h>
+#include <sys/statvfs.h>
 #include <stdlib.h>
 #include <unistd.h>
 #include <fcntl.h>
@@ -32,11 +34,14 @@
 # define CLONE_NEWPID 0x20000000
 #endif
 
+#ifndef MS_REC
+# define MS_REC 16384
+#endif
 #ifndef MS_RELATIME
-#define MS_RELATIME (1 << 21)
+# define MS_RELATIME (1 << 21)
 #endif
 #ifndef MS_STRICTATIME
-#define MS_STRICTATIME (1 << 24)
+# define MS_STRICTATIME (1 << 24)
 #endif
 
 static void die(char *fmt, ...)
@@ -48,17 +53,14 @@ static void die(char *fmt, ...)
 	exit(EXIT_FAILURE);
 }
 
-static void write_file(char *filename, char *fmt, ...)
+static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list ap)
 {
 	char buf[4096];
 	int fd;
 	ssize_t written;
 	int buf_len;
-	va_list ap;
 
-	va_start(ap, fmt);
 	buf_len = vsnprintf(buf, sizeof(buf), fmt, ap);
-	va_end(ap);
 	if (buf_len < 0) {
 		die("vsnprintf failed: %s\n",
 		    strerror(errno));
@@ -69,6 +71,8 @@ static void write_file(char *filename, char *fmt, ...)
 
 	fd = open(filename, O_WRONLY);
 	if (fd < 0) {
+		if ((errno == ENOENT) && enoent_ok)
+			return;
 		die("open of %s failed: %s\n",
 		    filename, strerror(errno));
 	}
@@ -87,6 +91,65 @@ static void write_file(char *filename, char *fmt, ...)
 	}
 }
 
+static void maybe_write_file(char *filename, char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vmaybe_write_file(true, filename, fmt, ap);
+	va_end(ap);
+
+}
+
+static void write_file(char *filename, char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vmaybe_write_file(false, filename, fmt, ap);
+	va_end(ap);
+
+}
+
+static int read_mnt_flags(const char *path)
+{
+	int ret;
+	struct statvfs stat;
+	int mnt_flags;
+
+	ret = statvfs(path, &stat);
+	if (ret != 0) {
+		die("statvfs of %s failed: %s\n",
+			path, strerror(errno));
+	}
+	if (stat.f_flag & ~(ST_RDONLY | ST_NOSUID | ST_NODEV | \
+			ST_NOEXEC | ST_NOATIME | ST_NODIRATIME | ST_RELATIME | \
+			ST_SYNCHRONOUS | ST_MANDLOCK)) {
+		die("Unrecognized mount flags\n");
+	}
+	mnt_flags = 0;
+	if (stat.f_flag & ST_RDONLY)
+		mnt_flags |= MS_RDONLY;
+	if (stat.f_flag & ST_NOSUID)
+		mnt_flags |= MS_NOSUID;
+	if (stat.f_flag & ST_NODEV)
+		mnt_flags |= MS_NODEV;
+	if (stat.f_flag & ST_NOEXEC)
+		mnt_flags |= MS_NOEXEC;
+	if (stat.f_flag & ST_NOATIME)
+		mnt_flags |= MS_NOATIME;
+	if (stat.f_flag & ST_NODIRATIME)
+		mnt_flags |= MS_NODIRATIME;
+	if (stat.f_flag & ST_RELATIME)
+		mnt_flags |= MS_RELATIME;
+	if (stat.f_flag & ST_SYNCHRONOUS)
+		mnt_flags |= MS_SYNCHRONOUS;
+	if (stat.f_flag & ST_MANDLOCK)
+		mnt_flags |= ST_MANDLOCK;
+
+	return mnt_flags;
+}
+
 static void create_and_enter_userns(void)
 {
 	uid_t uid;
@@ -100,13 +163,10 @@ static void create_and_enter_userns(void)
 			strerror(errno));
 	}
 
+	maybe_write_file("/proc/self/setgroups", "deny");
 	write_file("/proc/self/uid_map", "0 %d 1", uid);
 	write_file("/proc/self/gid_map", "0 %d 1", gid);
 
-	if (setgroups(0, NULL) != 0) {
-		die("setgroups failed: %s\n",
-			strerror(errno));
-	}
 	if (setgid(0) != 0) {
 		die ("setgid(0) failed %s\n",
 			strerror(errno));
@@ -118,7 +178,8 @@ static void create_and_enter_userns(void)
 }
 
 static
-bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags)
+bool test_unpriv_remount(const char *fstype, const char *mount_options,
+			 int mount_flags, int remount_flags, int invalid_flags)
 {
 	pid_t child;
 
@@ -151,9 +212,11 @@ bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags)
 			strerror(errno));
 	}
 
-	if (mount("testing", "/tmp", "ramfs", mount_flags, NULL) != 0) {
-		die("mount of /tmp failed: %s\n",
-			strerror(errno));
+	if (mount("testing", "/tmp", fstype, mount_flags, mount_options) != 0) {
+		die("mount of %s with options '%s' on /tmp failed: %s\n",
+		    fstype,
+		    mount_options? mount_options : "",
+		    strerror(errno));
 	}
 
 	create_and_enter_userns();
@@ -181,62 +244,127 @@ bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags)
 
 static bool test_unpriv_remount_simple(int mount_flags)
 {
-	return test_unpriv_remount(mount_flags, mount_flags, 0);
+	return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags, 0);
 }
 
 static bool test_unpriv_remount_atime(int mount_flags, int invalid_flags)
 {
-	return test_unpriv_remount(mount_flags, mount_flags, invalid_flags);
+	return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags,
+				   invalid_flags);
+}
+
+static bool test_priv_mount_unpriv_remount(void)
+{
+	pid_t child;
+	int ret;
+	const char *orig_path = "/dev";
+	const char *dest_path = "/tmp";
+	int orig_mnt_flags, remount_mnt_flags;
+
+	child = fork();
+	if (child == -1) {
+		die("fork failed: %s\n",
+			strerror(errno));
+	}
+	if (child != 0) { /* parent */
+		pid_t pid;
+		int status;
+		pid = waitpid(child, &status, 0);
+		if (pid == -1) {
+			die("waitpid failed: %s\n",
+				strerror(errno));
+		}
+		if (pid != child) {
+			die("waited for %d got %d\n",
+				child, pid);
+		}
+		if (!WIFEXITED(status)) {
+			die("child did not terminate cleanly\n");
+		}
+		return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false;
+	}
+
+	orig_mnt_flags = read_mnt_flags(orig_path);
+
+	create_and_enter_userns();
+	ret = unshare(CLONE_NEWNS);
+	if (ret != 0) {
+		die("unshare(CLONE_NEWNS) failed: %s\n",
+			strerror(errno));
+	}
+
+	ret = mount(orig_path, dest_path, "bind", MS_BIND | MS_REC, NULL);
+	if (ret != 0) {
+		die("recursive bind mount of %s onto %s failed: %s\n",
+			orig_path, dest_path, strerror(errno));
+	}
+
+	ret = mount(dest_path, dest_path, "none",
+		    MS_REMOUNT | MS_BIND | orig_mnt_flags , NULL);
+	if (ret != 0) {
+		/* system("cat /proc/self/mounts"); */
+		die("remount of /tmp failed: %s\n",
+		    strerror(errno));
+	}
+
+	remount_mnt_flags = read_mnt_flags(dest_path);
+	if (orig_mnt_flags != remount_mnt_flags) {
+		die("Mount flags unexpectedly changed during remount of %s originally mounted on %s\n",
+			dest_path, orig_path);
+	}
+	exit(EXIT_SUCCESS);
 }
 
 int main(int argc, char **argv)
 {
-	if (!test_unpriv_remount_simple(MS_RDONLY|MS_NODEV)) {
+	if (!test_unpriv_remount_simple(MS_RDONLY)) {
 		die("MS_RDONLY malfunctions\n");
 	}
-	if (!test_unpriv_remount_simple(MS_NODEV)) {
+	if (!test_unpriv_remount("devpts", "newinstance", MS_NODEV, MS_NODEV, 0)) {
 		die("MS_NODEV malfunctions\n");
 	}
-	if (!test_unpriv_remount_simple(MS_NOSUID|MS_NODEV)) {
+	if (!test_unpriv_remount_simple(MS_NOSUID)) {
 		die("MS_NOSUID malfunctions\n");
 	}
-	if (!test_unpriv_remount_simple(MS_NOEXEC|MS_NODEV)) {
+	if (!test_unpriv_remount_simple(MS_NOEXEC)) {
 		die("MS_NOEXEC malfunctions\n");
 	}
-	if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODEV,
-				       MS_NOATIME|MS_NODEV))
+	if (!test_unpriv_remount_atime(MS_RELATIME,
+				       MS_NOATIME))
 	{
 		die("MS_RELATIME malfunctions\n");
 	}
-	if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODEV,
-				       MS_NOATIME|MS_NODEV))
+	if (!test_unpriv_remount_atime(MS_STRICTATIME,
+				       MS_NOATIME))
 	{
 		die("MS_STRICTATIME malfunctions\n");
 	}
-	if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODEV,
-				       MS_STRICTATIME|MS_NODEV))
+	if (!test_unpriv_remount_atime(MS_NOATIME,
+				       MS_STRICTATIME))
 	{
-		die("MS_RELATIME malfunctions\n");
+		die("MS_NOATIME malfunctions\n");
 	}
-	if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME|MS_NODEV,
-				       MS_NOATIME|MS_NODEV))
+	if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME,
+				       MS_NOATIME))
 	{
-		die("MS_RELATIME malfunctions\n");
+		die("MS_RELATIME|MS_NODIRATIME malfunctions\n");
 	}
-	if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME|MS_NODEV,
-				       MS_NOATIME|MS_NODEV))
+	if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME,
+				       MS_NOATIME))
 	{
-		die("MS_RELATIME malfunctions\n");
+		die("MS_STRICTATIME|MS_NODIRATIME malfunctions\n");
 	}
-	if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME|MS_NODEV,
-				       MS_STRICTATIME|MS_NODEV))
+	if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME,
+				       MS_STRICTATIME))
 	{
-		die("MS_RELATIME malfunctions\n");
+		die("MS_NOATIME|MS_DIRATIME malfunctions\n");
 	}
-	if (!test_unpriv_remount(MS_STRICTATIME|MS_NODEV, MS_NODEV,
-				 MS_NOATIME|MS_NODEV))
+	if (!test_unpriv_remount("ramfs", NULL, MS_STRICTATIME, 0, MS_NOATIME))
 	{
 		die("Default atime malfunctions\n");
 	}
+	if (!test_priv_mount_unpriv_remount()) {
+		die("Mount flags unexpectedly changed after remount\n");
+	}
 	return EXIT_SUCCESS;
 }
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 22fa819a9b6..1c0772b340d 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -61,12 +61,14 @@ static void timer_disarm(struct arch_timer_cpu *timer)
 
 static void kvm_timer_inject_irq(struct kvm_vcpu *vcpu)
 {
+	int ret;
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
 
 	timer->cntv_ctl |= ARCH_TIMER_CTRL_IT_MASK;
-	kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
-			    timer->irq->irq,
-			    timer->irq->level);
+	ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+				  timer->irq->irq,
+				  timer->irq->level);
+	WARN_ON(ret);
 }
 
 static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id)
@@ -307,12 +309,24 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu)
 	timer_disarm(timer);
 }
 
-int kvm_timer_init(struct kvm *kvm)
+void kvm_timer_enable(struct kvm *kvm)
 {
-	if (timecounter && wqueue) {
-		kvm->arch.timer.cntvoff = kvm_phys_timer_read();
+	if (kvm->arch.timer.enabled)
+		return;
+
+	/*
+	 * There is a potential race here between VCPUs starting for the first
+	 * time, which may be enabling the timer multiple times.  That doesn't
+	 * hurt though, because we're just setting a variable to the same
+	 * variable that it already was.  The important thing is that all
+	 * VCPUs have the enabled variable set, before entering the guest, if
+	 * the arch timers are enabled.
+	 */
+	if (timecounter && wqueue)
 		kvm->arch.timer.enabled = 1;
-	}
+}
 
-	return 0;
+void kvm_timer_init(struct kvm *kvm)
+{
+	kvm->arch.timer.cntvoff = kvm_phys_timer_read();
 }
diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c
index 2935405ad22..b9d48e8e1eb 100644
--- a/virt/kvm/arm/vgic-v2.c
+++ b/virt/kvm/arm/vgic-v2.c
@@ -72,6 +72,8 @@ static void vgic_v2_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
 {
 	if (!(lr_desc.state & LR_STATE_MASK))
 		vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr |= (1ULL << lr);
+	else
+		vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr &= ~(1ULL << lr);
 }
 
 static u64 vgic_v2_get_elrsr(const struct kvm_vcpu *vcpu)
@@ -84,6 +86,11 @@ static u64 vgic_v2_get_eisr(const struct kvm_vcpu *vcpu)
 	return vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr;
 }
 
+static void vgic_v2_clear_eisr(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr = 0;
+}
+
 static u32 vgic_v2_get_interrupt_status(const struct kvm_vcpu *vcpu)
 {
 	u32 misr = vcpu->arch.vgic_cpu.vgic_v2.vgic_misr;
@@ -148,6 +155,7 @@ static const struct vgic_ops vgic_v2_ops = {
 	.sync_lr_elrsr		= vgic_v2_sync_lr_elrsr,
 	.get_elrsr		= vgic_v2_get_elrsr,
 	.get_eisr		= vgic_v2_get_eisr,
+	.clear_eisr		= vgic_v2_clear_eisr,
 	.get_interrupt_status	= vgic_v2_get_interrupt_status,
 	.enable_underflow	= vgic_v2_enable_underflow,
 	.disable_underflow	= vgic_v2_disable_underflow,
diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c
index 1c2c8eef059..58b8af00ee4 100644
--- a/virt/kvm/arm/vgic-v3.c
+++ b/virt/kvm/arm/vgic-v3.c
@@ -86,6 +86,8 @@ static void vgic_v3_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
 {
 	if (!(lr_desc.state & LR_STATE_MASK))
 		vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr |= (1U << lr);
+	else
+		vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr &= ~(1U << lr);
 }
 
 static u64 vgic_v3_get_elrsr(const struct kvm_vcpu *vcpu)
@@ -98,6 +100,11 @@ static u64 vgic_v3_get_eisr(const struct kvm_vcpu *vcpu)
 	return vcpu->arch.vgic_cpu.vgic_v3.vgic_eisr;
 }
 
+static void vgic_v3_clear_eisr(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.vgic_cpu.vgic_v3.vgic_eisr = 0;
+}
+
 static u32 vgic_v3_get_interrupt_status(const struct kvm_vcpu *vcpu)
 {
 	u32 misr = vcpu->arch.vgic_cpu.vgic_v3.vgic_misr;
@@ -162,6 +169,7 @@ static const struct vgic_ops vgic_v3_ops = {
 	.sync_lr_elrsr		= vgic_v3_sync_lr_elrsr,
 	.get_elrsr		= vgic_v3_get_elrsr,
 	.get_eisr		= vgic_v3_get_eisr,
+	.clear_eisr		= vgic_v3_clear_eisr,
 	.get_interrupt_status	= vgic_v3_get_interrupt_status,
 	.enable_underflow	= vgic_v3_enable_underflow,
 	.disable_underflow	= vgic_v3_disable_underflow,
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index aacdb59f30d..d7cf2ffc56e 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -91,6 +91,7 @@
 #define ACCESS_WRITE_VALUE	(3 << 1)
 #define ACCESS_WRITE_MASK(x)	((x) & (3 << 1))
 
+static int vgic_init(struct kvm *kvm);
 static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
 static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu);
 static void vgic_update_state(struct kvm *kvm);
@@ -1218,6 +1219,11 @@ static inline u64 vgic_get_eisr(struct kvm_vcpu *vcpu)
 	return vgic_ops->get_eisr(vcpu);
 }
 
+static inline void vgic_clear_eisr(struct kvm_vcpu *vcpu)
+{
+	vgic_ops->clear_eisr(vcpu);
+}
+
 static inline u32 vgic_get_interrupt_status(struct kvm_vcpu *vcpu)
 {
 	return vgic_ops->get_interrupt_status(vcpu);
@@ -1257,6 +1263,7 @@ static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu)
 	vgic_set_lr(vcpu, lr_nr, vlr);
 	clear_bit(lr_nr, vgic_cpu->lr_used);
 	vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
+	vgic_sync_lr_elrsr(vcpu, lr_nr, vlr);
 }
 
 /*
@@ -1312,6 +1319,7 @@ static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
 			BUG_ON(!test_bit(lr, vgic_cpu->lr_used));
 			vlr.state |= LR_STATE_PENDING;
 			vgic_set_lr(vcpu, lr, vlr);
+			vgic_sync_lr_elrsr(vcpu, lr, vlr);
 			return true;
 		}
 	}
@@ -1333,6 +1341,7 @@ static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
 		vlr.state |= LR_EOI_INT;
 
 	vgic_set_lr(vcpu, lr, vlr);
+	vgic_sync_lr_elrsr(vcpu, lr, vlr);
 
 	return true;
 }
@@ -1501,6 +1510,14 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 	if (status & INT_STATUS_UNDERFLOW)
 		vgic_disable_underflow(vcpu);
 
+	/*
+	 * In the next iterations of the vcpu loop, if we sync the vgic state
+	 * after flushing it, but before entering the guest (this happens for
+	 * pending signals and vmid rollovers), then make sure we don't pick
+	 * up any old maintenance interrupts here.
+	 */
+	vgic_clear_eisr(vcpu);
+
 	return level_pending;
 }
 
@@ -1607,7 +1624,7 @@ static int vgic_validate_injection(struct kvm_vcpu *vcpu, int irq, int level)
 	}
 }
 
-static bool vgic_update_irq_pending(struct kvm *kvm, int cpuid,
+static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
 				  unsigned int irq_num, bool level)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
@@ -1672,7 +1689,7 @@ static bool vgic_update_irq_pending(struct kvm *kvm, int cpuid,
 out:
 	spin_unlock(&dist->lock);
 
-	return ret;
+	return ret ? cpuid : -EINVAL;
 }
 
 /**
@@ -1692,11 +1709,29 @@ out:
 int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
 			bool level)
 {
-	if (likely(vgic_initialized(kvm)) &&
-	    vgic_update_irq_pending(kvm, cpuid, irq_num, level))
-		vgic_kick_vcpus(kvm);
+	int ret = 0;
+	int vcpu_id;
 
-	return 0;
+	if (unlikely(!vgic_initialized(kvm))) {
+		mutex_lock(&kvm->lock);
+		ret = vgic_init(kvm);
+		mutex_unlock(&kvm->lock);
+
+		if (ret)
+			goto out;
+	}
+
+	if (irq_num >= min(kvm->arch.vgic.nr_irqs, 1020))
+		return -EINVAL;
+
+	vcpu_id = vgic_update_irq_pending(kvm, cpuid, irq_num, level);
+	if (vcpu_id >= 0) {
+		/* kick the specified vcpu */
+		kvm_vcpu_kick(kvm_get_vcpu(kvm, vcpu_id));
+	}
+
+out:
+	return ret;
 }
 
 static irqreturn_t vgic_maintenance_handler(int irq, void *data)
@@ -1726,39 +1761,14 @@ static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs)
 
 	int sz = (nr_irqs - VGIC_NR_PRIVATE_IRQS) / 8;
 	vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL);
-	vgic_cpu->vgic_irq_lr_map = kzalloc(nr_irqs, GFP_KERNEL);
+	vgic_cpu->vgic_irq_lr_map = kmalloc(nr_irqs, GFP_KERNEL);
 
 	if (!vgic_cpu->pending_shared || !vgic_cpu->vgic_irq_lr_map) {
 		kvm_vgic_vcpu_destroy(vcpu);
 		return -ENOMEM;
 	}
 
-	return 0;
-}
-
-/**
- * kvm_vgic_vcpu_init - Initialize per-vcpu VGIC state
- * @vcpu: pointer to the vcpu struct
- *
- * Initialize the vgic_cpu struct and vgic_dist struct fields pertaining to
- * this vcpu and enable the VGIC for this VCPU
- */
-static void kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
-{
-	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	int i;
-
-	for (i = 0; i < dist->nr_irqs; i++) {
-		if (i < VGIC_NR_PPIS)
-			vgic_bitmap_set_irq_val(&dist->irq_enabled,
-						vcpu->vcpu_id, i, 1);
-		if (i < VGIC_NR_PRIVATE_IRQS)
-			vgic_bitmap_set_irq_val(&dist->irq_cfg,
-						vcpu->vcpu_id, i, VGIC_CFG_EDGE);
-
-		vgic_cpu->vgic_irq_lr_map[i] = LR_EMPTY;
-	}
+	memset(vgic_cpu->vgic_irq_lr_map, LR_EMPTY, nr_irqs);
 
 	/*
 	 * Store the number of LRs per vcpu, so we don't have to go
@@ -1767,7 +1777,7 @@ static void kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 	 */
 	vgic_cpu->nr_lr = vgic->nr_lr;
 
-	vgic_enable(vcpu);
+	return 0;
 }
 
 void kvm_vgic_destroy(struct kvm *kvm)
@@ -1804,19 +1814,19 @@ void kvm_vgic_destroy(struct kvm *kvm)
  * Allocate and initialize the various data structures. Must be called
  * with kvm->lock held!
  */
-static int vgic_init_maps(struct kvm *kvm)
+static int vgic_init(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	struct kvm_vcpu *vcpu;
 	int nr_cpus, nr_irqs;
-	int ret, i;
+	int ret, i, vcpu_id;
 
 	if (dist->nr_cpus)	/* Already allocated */
 		return 0;
 
 	nr_cpus = dist->nr_cpus = atomic_read(&kvm->online_vcpus);
 	if (!nr_cpus)		/* No vcpus? Can't be good... */
-		return -EINVAL;
+		return -ENODEV;
 
 	/*
 	 * If nobody configured the number of interrupts, use the
@@ -1859,16 +1869,28 @@ static int vgic_init_maps(struct kvm *kvm)
 	if (ret)
 		goto out;
 
-	kvm_for_each_vcpu(i, vcpu, kvm) {
+	for (i = VGIC_NR_PRIVATE_IRQS; i < dist->nr_irqs; i += 4)
+		vgic_set_target_reg(kvm, 0, i);
+
+	kvm_for_each_vcpu(vcpu_id, vcpu, kvm) {
 		ret = vgic_vcpu_init_maps(vcpu, nr_irqs);
 		if (ret) {
 			kvm_err("VGIC: Failed to allocate vcpu memory\n");
 			break;
 		}
-	}
 
-	for (i = VGIC_NR_PRIVATE_IRQS; i < dist->nr_irqs; i += 4)
-		vgic_set_target_reg(kvm, 0, i);
+		for (i = 0; i < dist->nr_irqs; i++) {
+			if (i < VGIC_NR_PPIS)
+				vgic_bitmap_set_irq_val(&dist->irq_enabled,
+							vcpu->vcpu_id, i, 1);
+			if (i < VGIC_NR_PRIVATE_IRQS)
+				vgic_bitmap_set_irq_val(&dist->irq_cfg,
+							vcpu->vcpu_id, i,
+							VGIC_CFG_EDGE);
+		}
+
+		vgic_enable(vcpu);
+	}
 
 out:
 	if (ret)
@@ -1878,18 +1900,16 @@ out:
 }
 
 /**
- * kvm_vgic_init - Initialize global VGIC state before running any VCPUs
+ * kvm_vgic_map_resources - Configure global VGIC state before running any VCPUs
  * @kvm: pointer to the kvm struct
  *
  * Map the virtual CPU interface into the VM before running any VCPUs.  We
  * can't do this at creation time, because user space must first set the
- * virtual CPU interface address in the guest physical address space.  Also
- * initialize the ITARGETSRn regs to 0 on the emulated distributor.
+ * virtual CPU interface address in the guest physical address space.
  */
-int kvm_vgic_init(struct kvm *kvm)
+int kvm_vgic_map_resources(struct kvm *kvm)
 {
-	struct kvm_vcpu *vcpu;
-	int ret = 0, i;
+	int ret = 0;
 
 	if (!irqchip_in_kernel(kvm))
 		return 0;
@@ -1906,7 +1926,11 @@ int kvm_vgic_init(struct kvm *kvm)
 		goto out;
 	}
 
-	ret = vgic_init_maps(kvm);
+	/*
+	 * Initialize the vgic if this hasn't already been done on demand by
+	 * accessing the vgic state from userspace.
+	 */
+	ret = vgic_init(kvm);
 	if (ret) {
 		kvm_err("Unable to allocate maps\n");
 		goto out;
@@ -1920,9 +1944,6 @@ int kvm_vgic_init(struct kvm *kvm)
 		goto out;
 	}
 
-	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_vgic_vcpu_init(vcpu);
-
 	kvm->arch.vgic.ready = true;
 out:
 	if (ret)
@@ -2167,7 +2188,7 @@ static int vgic_attr_regs_access(struct kvm_device *dev,
 
 	mutex_lock(&dev->kvm->lock);
 
-	ret = vgic_init_maps(dev->kvm);
+	ret = vgic_init(dev->kvm);
 	if (ret)
 		goto out;
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 3cee7b16705..4e52bb92637 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -478,7 +478,7 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
 
 	r = -ENOMEM;
-	kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
+	kvm->memslots = kvm_kvzalloc(sizeof(struct kvm_memslots));
 	if (!kvm->memslots)
 		goto out_err_no_srcu;
 
@@ -529,7 +529,7 @@ out_err_no_srcu:
 out_err_no_disable:
 	for (i = 0; i < KVM_NR_BUSES; i++)
 		kfree(kvm->buses[i]);
-	kfree(kvm->memslots);
+	kvfree(kvm->memslots);
 	kvm_arch_free_vm(kvm);
 	return ERR_PTR(r);
 }
@@ -585,7 +585,7 @@ static void kvm_free_physmem(struct kvm *kvm)
 	kvm_for_each_memslot(memslot, slots)
 		kvm_free_physmem_slot(kvm, memslot, NULL);
 
-	kfree(kvm->memslots);
+	kvfree(kvm->memslots);
 }
 
 static void kvm_destroy_devices(struct kvm *kvm)
@@ -867,10 +867,11 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	}
 
 	if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) {
-		slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),
-				GFP_KERNEL);
+		slots = kvm_kvzalloc(sizeof(struct kvm_memslots));
 		if (!slots)
 			goto out_free;
+		memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
+
 		slot = id_to_memslot(slots, mem->slot);
 		slot->flags |= KVM_MEMSLOT_INVALID;
 
@@ -900,10 +901,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	 * will get overwritten by update_memslots anyway.
 	 */
 	if (!slots) {
-		slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),
-				GFP_KERNEL);
+		slots = kvm_kvzalloc(sizeof(struct kvm_memslots));
 		if (!slots)
 			goto out_free;
+		memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
 	}
 
 	/* actual memory is freed via old in kvm_free_physmem_slot below */
@@ -917,7 +918,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	kvm_arch_commit_memory_region(kvm, mem, &old, change);
 
 	kvm_free_physmem_slot(kvm, &old, &new);
-	kfree(old_memslots);
+	kvfree(old_memslots);
 
 	/*
 	 * IOMMU mapping:  New slots need to be mapped.  Old slots need to be
@@ -936,7 +937,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	return 0;
 
 out_slots:
-	kfree(slots);
+	kvfree(slots);
 out_free:
 	kvm_free_physmem_slot(kvm, &new, &old);
 out:
@@ -1614,8 +1615,8 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 	ghc->generation = slots->generation;
 	ghc->len = len;
 	ghc->memslot = gfn_to_memslot(kvm, start_gfn);
-	ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, &nr_pages_avail);
-	if (!kvm_is_error_hva(ghc->hva) && nr_pages_avail >= nr_pages_needed) {
+	ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, NULL);
+	if (!kvm_is_error_hva(ghc->hva) && nr_pages_needed <= 1) {
 		ghc->hva += offset;
 	} else {
 		/*
@@ -2417,6 +2418,7 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_SIGNAL_MSI:
 #endif
 #ifdef CONFIG_HAVE_KVM_IRQFD
+	case KVM_CAP_IRQFD:
 	case KVM_CAP_IRQFD_RESAMPLE:
 #endif
 	case KVM_CAP_CHECK_EXTENSION_VM: