Merge branch 'drm-intel-fixes' into HEAD

Conflicts:
	drivers/char/agp/intel-agp.c
	drivers/gpu/drm/i915/intel_crt.c

Documentation/DocBook/device-drivers.tmpl

@@ -46,7 +46,6 @@
 
      <sect1><title>Atomic and pointer manipulation</title>
 !Iarch/x86/include/asm/atomic.h
-!Iarch/x86/include/asm/unaligned.h
      </sect1>
 
      <sect1><title>Delaying, scheduling, and timer routines</title>

Documentation/DocBook/kernel-api.tmpl

@@ -57,7 +57,6 @@
      </para>
 
      <sect1><title>String Conversions</title>
-!Ilib/vsprintf.c
 !Elib/vsprintf.c
      </sect1>
      <sect1><title>String Manipulation</title>

Documentation/DocBook/kernel-locking.tmpl

@@ -1961,6 +1961,12 @@ machines due to caching.
    </sect1>
   </chapter>
 
+  <chapter id="apiref">
+   <title>Mutex API reference</title>
+!Iinclude/linux/mutex.h
+!Ekernel/mutex.c
+  </chapter>
+
   <chapter id="references">
    <title>Further reading</title>
 

Documentation/DocBook/tracepoint.tmpl

@@ -104,4 +104,9 @@
    <title>Block IO</title>
 !Iinclude/trace/events/block.h
   </chapter>
+
+  <chapter id="workqueue">
+   <title>Workqueue</title>
+!Iinclude/trace/events/workqueue.h
+  </chapter>
 </book>

Documentation/block/cfq-iosched.txt

+CFQ ioscheduler tunables
+========================
+
+slice_idle
+----------
+This specifies how long CFQ should idle for next request on certain cfq queues
+(for sequential workloads) and service trees (for random workloads) before
+queue is expired and CFQ selects next queue to dispatch from.
+
+By default slice_idle is a non-zero value. That means by default we idle on
+queues/service trees. This can be very helpful on highly seeky media like
+single spindle SATA/SAS disks where we can cut down on overall number of
+seeks and see improved throughput.
+
+Setting slice_idle to 0 will remove all the idling on queues/service tree
+level and one should see an overall improved throughput on faster storage
+devices like multiple SATA/SAS disks in hardware RAID configuration. The down
+side is that isolation provided from WRITES also goes down and notion of
+IO priority becomes weaker.
+
+So depending on storage and workload, it might be useful to set slice_idle=0.
+In general I think for SATA/SAS disks and software RAID of SATA/SAS disks
+keeping slice_idle enabled should be useful. For any configurations where
+there are multiple spindles behind single LUN (Host based hardware RAID
+controller or for storage arrays), setting slice_idle=0 might end up in better
+throughput and acceptable latencies.
+
+CFQ IOPS Mode for group scheduling
+===================================
+Basic CFQ design is to provide priority based time slices. Higher priority
+process gets bigger time slice and lower priority process gets smaller time
+slice. Measuring time becomes harder if storage is fast and supports NCQ and
+it would be better to dispatch multiple requests from multiple cfq queues in
+request queue at a time. In such scenario, it is not possible to measure time
+consumed by single queue accurately.
+
+What is possible though is to measure number of requests dispatched from a
+single queue and also allow dispatch from multiple cfq queue at the same time.
+This effectively becomes the fairness in terms of IOPS (IO operations per
+second).
+
+If one sets slice_idle=0 and if storage supports NCQ, CFQ internally switches
+to IOPS mode and starts providing fairness in terms of number of requests
+dispatched. Note that this mode switching takes effect only for group
+scheduling. For non-cgroup users nothing should change.

Documentation/cgroups/blkio-controller.txt

@@ -217,6 +217,7 @@ Details of cgroup files
 CFQ sysfs tunable
 =================
 /sys/block/<disk>/queue/iosched/group_isolation
+-----------------------------------------------
 
 If group_isolation=1, it provides stronger isolation between groups at the
 expense of throughput. By default group_isolation is 0. In general that
@@ -243,6 +244,33 @@ By default one should run with group_isolation=0. If that is not sufficient
 and one wants stronger isolation between groups, then set group_isolation=1
 but this will come at cost of reduced throughput.
 
+/sys/block/<disk>/queue/iosched/slice_idle
+------------------------------------------
+On a faster hardware CFQ can be slow, especially with sequential workload.
+This happens because CFQ idles on a single queue and single queue might not
+drive deeper request queue depths to keep the storage busy. In such scenarios
+one can try setting slice_idle=0 and that would switch CFQ to IOPS
+(IO operations per second) mode on NCQ supporting hardware.
+
+That means CFQ will not idle between cfq queues of a cfq group and hence be
+able to driver higher queue depth and achieve better throughput. That also
+means that cfq provides fairness among groups in terms of IOPS and not in
+terms of disk time.
+
+/sys/block/<disk>/queue/iosched/group_idle
+------------------------------------------
+If one disables idling on individual cfq queues and cfq service trees by
+setting slice_idle=0, group_idle kicks in. That means CFQ will still idle
+on the group in an attempt to provide fairness among groups.
+
+By default group_idle is same as slice_idle and does not do anything if
+slice_idle is enabled.
+
+One can experience an overall throughput drop if you have created multiple
+groups and put applications in that group which are not driving enough
+IO to keep disk busy. In that case set group_idle=0, and CFQ will not idle
+on individual groups and throughput should improve.
+
 What works
 ==========
 - Currently only sync IO queues are support. All the buffered writes are

Documentation/gpio.txt

@@ -109,17 +109,19 @@ use numbers 2000-2063 to identify GPIOs in a bank of I2C GPIO expanders.
 
 If you want to initialize a structure with an invalid GPIO number, use
 some negative number (perhaps "-EINVAL"); that will never be valid.  To
-test if a number could reference a GPIO, you may use this predicate:
+test if such number from such a structure could reference a GPIO, you
+may use this predicate:
 
 	int gpio_is_valid(int number);
 
 A number that's not valid will be rejected by calls which may request
 or free GPIOs (see below).  Other numbers may also be rejected; for
-example, a number might be valid but unused on a given board.
-
-Whether a platform supports multiple GPIO controllers is currently a
-platform-specific implementation issue.
+example, a number might be valid but temporarily unused on a given board.
 
+Whether a platform supports multiple GPIO controllers is a platform-specific
+implementation issue, as are whether that support can leave "holes" in the space
+of GPIO numbers, and whether new controllers can be added at runtime.  Such issues
+can affect things including whether adjacent GPIO numbers are both valid.
 
 Using GPIOs
 -----------
@@ -480,12 +482,16 @@ To support this framework, a platform's Kconfig will "select" either
 ARCH_REQUIRE_GPIOLIB or ARCH_WANT_OPTIONAL_GPIOLIB
 and arrange that its <asm/gpio.h> includes <asm-generic/gpio.h> and defines
 three functions: gpio_get_value(), gpio_set_value(), and gpio_cansleep().
-They may also want to provide a custom value for ARCH_NR_GPIOS.
 
-ARCH_REQUIRE_GPIOLIB means that the gpio-lib code will always get compiled
+It may also provide a custom value for ARCH_NR_GPIOS, so that it better
+reflects the number of GPIOs in actual use on that platform, without
+wasting static table space.  (It should count both built-in/SoC GPIOs and
+also ones on GPIO expanders.
+
+ARCH_REQUIRE_GPIOLIB means that the gpiolib code will always get compiled
 into the kernel on that architecture.
 
-ARCH_WANT_OPTIONAL_GPIOLIB means the gpio-lib code defaults to off and the user
+ARCH_WANT_OPTIONAL_GPIOLIB means the gpiolib code defaults to off and the user
 can enable it and build it into the kernel optionally.
 
 If neither of these options are selected, the platform does not support

Documentation/hwmon/sysfs-interface

@@ -91,12 +91,11 @@ name		The chip name.
 		I2C devices get this attribute created automatically.
 		RO
 
-update_rate	The rate at which the chip will update readings.
+update_interval	The interval at which the chip will update readings.
 		Unit: millisecond
 		RW
-		Some devices have a variable update rate. This attribute
-		can be used to change the update rate to the desired
-		frequency.
+		Some devices have a variable update rate or interval.
+		This attribute can be used to change it to the desired value.
 
 
 ************

Documentation/kernel-doc-nano-HOWTO.txt

@@ -345,5 +345,10 @@ documentation, in <filename>, for the functions listed.
 section titled <section title> from <filename>.
 Spaces are allowed in <section title>; do not quote the <section title>.
 
+!C<filename> is replaced by nothing, but makes the tools check that
+all DOC: sections and documented functions, symbols, etc. are used.
+This makes sense to use when you use !F/!P only and want to verify
+that all documentation is included.
+
 Tim.
 */ <twaugh@redhat.com>

Documentation/kernel-parameters.txt

@@ -1974,15 +1974,18 @@ and is between 256 and 4096 characters. It is defined in the file
 		force	Enable ASPM even on devices that claim not to support it.
 			WARNING: Forcing ASPM on may cause system lockups.
 
+	pcie_ports=	[PCIE] PCIe ports handling:
+		auto	Ask the BIOS whether or not to use native PCIe services
+			associated with PCIe ports (PME, hot-plug, AER).  Use
+			them only if that is allowed by the BIOS.
+		native	Use native PCIe services associated with PCIe ports
+			unconditionally.
+		compat	Treat PCIe ports as PCI-to-PCI bridges, disable the PCIe
+			ports driver.
+
 	pcie_pme=	[PCIE,PM] Native PCIe PME signaling options:
-			Format: {auto|force}[,nomsi]
-		auto	Use native PCIe PME signaling if the BIOS allows the
-			kernel to control PCIe config registers of root ports.
-		force	Use native PCIe PME signaling even if the BIOS refuses
-			to allow the kernel to control the relevant PCIe config
-			registers.
 		nomsi	Do not use MSI for native PCIe PME signaling (this makes
-			all PCIe root ports use INTx for everything).
+			all PCIe root ports use INTx for all services).
 
 	pcmv=		[HW,PCMCIA] BadgePAD 4
 

Documentation/mutex-design.txt

@@ -9,7 +9,7 @@ firstly, there's nothing wrong with semaphores. But if the simpler
 mutex semantics are sufficient for your code, then there are a couple
 of advantages of mutexes:
 
- - 'struct mutex' is smaller on most architectures: .e.g on x86,
+ - 'struct mutex' is smaller on most architectures: E.g. on x86,
    'struct semaphore' is 20 bytes, 'struct mutex' is 16 bytes.
    A smaller structure size means less RAM footprint, and better
    CPU-cache utilization.
@@ -136,3 +136,4 @@ the APIs of 'struct mutex' have been streamlined:
  void mutex_lock_nested(struct mutex *lock, unsigned int subclass);
  int  mutex_lock_interruptible_nested(struct mutex *lock,
                                       unsigned int subclass);
+ int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);

Documentation/power/regulator/overview.txt

@@ -13,7 +13,7 @@ regulators (where voltage output is controllable) and current sinks (where
 current limit is controllable).
 
 (C) 2008  Wolfson Microelectronics PLC.
-Author: Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Author: Liam Girdwood <lrg@slimlogic.co.uk>
 
 
 Nomenclature

Documentation/sound/alsa/HD-Audio-Models.txt

@@ -296,6 +296,7 @@ Conexant 5051
 Conexant 5066
 =============
   laptop	Basic Laptop config (default)
+  hp-laptop	HP laptops, e g G60
   dell-laptop	Dell laptops
   dell-vostro	Dell Vostro
   olpc-xo-1_5	OLPC XO 1.5

Documentation/workqueue.txt

+
+Concurrency Managed Workqueue (cmwq)
+
+September, 2010		Tejun Heo <tj@kernel.org>
+			Florian Mickler <florian@mickler.org>
+
+CONTENTS
+
+1. Introduction
+2. Why cmwq?
+3. The Design
+4. Application Programming Interface (API)
+5. Example Execution Scenarios
+6. Guidelines
+
+
+1. Introduction
+
+There are many cases where an asynchronous process execution context
+is needed and the workqueue (wq) API is the most commonly used
+mechanism for such cases.
+
+When such an asynchronous execution context is needed, a work item
+describing which function to execute is put on a queue.  An
+independent thread serves as the asynchronous execution context.  The
+queue is called workqueue and the thread is called worker.
+
+While there are work items on the workqueue the worker executes the
+functions associated with the work items one after the other.  When
+there is no work item left on the workqueue the worker becomes idle.
+When a new work item gets queued, the worker begins executing again.
+
+
+2. Why cmwq?
+
+In the original wq implementation, a multi threaded (MT) wq had one
+worker thread per CPU and a single threaded (ST) wq had one worker
+thread system-wide.  A single MT wq needed to keep around the same
+number of workers as the number of CPUs.  The kernel grew a lot of MT
+wq users over the years and with the number of CPU cores continuously
+rising, some systems saturated the default 32k PID space just booting
+up.
+
+Although MT wq wasted a lot of resource, the level of concurrency
+provided was unsatisfactory.  The limitation was common to both ST and
+MT wq albeit less severe on MT.  Each wq maintained its own separate
+worker pool.  A MT wq could provide only one execution context per CPU
+while a ST wq one for the whole system.  Work items had to compete for
+those very limited execution contexts leading to various problems
+including proneness to deadlocks around the single execution context.
+
+The tension between the provided level of concurrency and resource
+usage also forced its users to make unnecessary tradeoffs like libata
+choosing to use ST wq for polling PIOs and accepting an unnecessary
+limitation that no two polling PIOs can progress at the same time.  As
+MT wq don't provide much better concurrency, users which require
+higher level of concurrency, like async or fscache, had to implement
+their own thread pool.
+
+Concurrency Managed Workqueue (cmwq) is a reimplementation of wq with
+focus on the following goals.
+
+* Maintain compatibility with the original workqueue API.
+
+* Use per-CPU unified worker pools shared by all wq to provide
+  flexible level of concurrency on demand without wasting a lot of
+  resource.
+
+* Automatically regulate worker pool and level of concurrency so that
+  the API users don't need to worry about such details.
+
+
+3. The Design
+
+In order to ease the asynchronous execution of functions a new
+abstraction, the work item, is introduced.
+
+A work item is a simple struct that holds a pointer to the function
+that is to be executed asynchronously.  Whenever a driver or subsystem
+wants a function to be executed asynchronously it has to set up a work
+item pointing to that function and queue that work item on a
+workqueue.
+
+Special purpose threads, called worker threads, execute the functions
+off of the queue, one after the other.  If no work is queued, the
+worker threads become idle.  These worker threads are managed in so
+called thread-pools.
+
+The cmwq design differentiates between the user-facing workqueues that
+subsystems and drivers queue work items on and the backend mechanism
+which manages thread-pool and processes the queued work items.
+
+The backend is called gcwq.  There is one gcwq for each possible CPU
+and one gcwq to serve work items queued on unbound workqueues.
+
+Subsystems and drivers can create and queue work items through special
+workqueue API functions as they see fit. They can influence some
+aspects of the way the work items are executed by setting flags on the
+workqueue they are putting the work item on. These flags include
+things like CPU locality, reentrancy, concurrency limits and more. To
+get a detailed overview refer to the API description of
+alloc_workqueue() below.
+
+When a work item is queued to a workqueue, the target gcwq is
+determined according to the queue parameters and workqueue attributes
+and appended on the shared worklist of the gcwq.  For example, unless
+specifically overridden, a work item of a bound workqueue will be
+queued on the worklist of exactly that gcwq that is associated to the
+CPU the issuer is running on.
+
+For any worker pool implementation, managing the concurrency level
+(how many execution contexts are active) is an important issue.  cmwq
+tries to keep the concurrency at a minimal but sufficient level.
+Minimal to save resources and sufficient in that the system is used at
+its full capacity.
+
+Each gcwq bound to an actual CPU implements concurrency management by
+hooking into the scheduler.  The gcwq is notified whenever an active
+worker wakes up or sleeps and keeps track of the number of the
+currently runnable workers.  Generally, work items are not expected to
+hog a CPU and consume many cycles.  That means maintaining just enough
+concurrency to prevent work processing from stalling should be
+optimal.  As long as there are one or more runnable workers on the
+CPU, the gcwq doesn't start execution of a new work, but, when the
+last running worker goes to sleep, it immediately schedules a new
+worker so that the CPU doesn't sit idle while there are pending work
+items.  This allows using a minimal number of workers without losing
+execution bandwidth.
+
+Keeping idle workers around doesn't cost other than the memory space
+for kthreads, so cmwq holds onto idle ones for a while before killing
+them.
+
+For an unbound wq, the above concurrency management doesn't apply and
+the gcwq for the pseudo unbound CPU tries to start executing all work
+items as soon as possible.  The responsibility of regulating
+concurrency level is on the users.  There is also a flag to mark a
+bound wq to ignore the concurrency management.  Please refer to the
+API section for details.
+
+Forward progress guarantee relies on that workers can be created when
+more execution contexts are necessary, which in turn is guaranteed
+through the use of rescue workers.  All work items which might be used
+on code paths that handle memory reclaim are required to be queued on
+wq's that have a rescue-worker reserved for execution under memory
+pressure.  Else it is possible that the thread-pool deadlocks waiting
+for execution contexts to free up.
+
+
+4. Application Programming Interface (API)
+
+alloc_workqueue() allocates a wq.  The original create_*workqueue()
+functions are deprecated and scheduled for removal.  alloc_workqueue()
+takes three arguments - @name, @flags and @max_active.  @name is the
+name of the wq and also used as the name of the rescuer thread if
+there is one.
+
+A wq no longer manages execution resources but serves as a domain for
+forward progress guarantee, flush and work item attributes.  @flags
+and @max_active control how work items are assigned execution
+resources, scheduled and executed.
+
+@flags:
+
+  WQ_NON_REENTRANT
+
+	By default, a wq guarantees non-reentrance only on the same
+	CPU.  A work item may not be executed concurrently on the same
+	CPU by multiple workers but is allowed to be executed
+	concurrently on multiple CPUs.  This flag makes sure
+	non-reentrance is enforced across all CPUs.  Work items queued
+	to a non-reentrant wq are guaranteed to be executed by at most
+	one worker system-wide at any given time.
+
+  WQ_UNBOUND
+
+	Work items queued to an unbound wq are served by a special
+	gcwq which hosts workers which are not bound to any specific
+	CPU.  This makes the wq behave as a simple execution context
+	provider without concurrency management.  The unbound gcwq
+	tries to start execution of work items as soon as possible.
+	Unbound wq sacrifices locality but is useful for the following
+	cases.
+
+	* Wide fluctuation in the concurrency level requirement is
+	  expected and using bound wq may end up creating large number
+	  of mostly unused workers across different CPUs as the issuer
+	  hops through different CPUs.
+
+	* Long running CPU intensive workloads which can be better
+	  managed by the system scheduler.
+
+  WQ_FREEZEABLE
+
+	A freezeable wq participates in the freeze phase of the system
+	suspend operations.  Work items on the wq are drained and no
+	new work item starts execution until thawed.
+
+  WQ_RESCUER
+
+	All wq which might be used in the memory reclaim paths _MUST_
+	have this flag set.  This reserves one worker exclusively for
+	the execution of this wq under memory pressure.
+
+  WQ_HIGHPRI
+
+	Work items of a highpri wq are queued at the head of the
+	worklist of the target gcwq and start execution regardless of
+	the current concurrency level.  In other words, highpri work
+	items will always start execution as soon as execution
+	resource is available.
+
+	Ordering among highpri work items is preserved - a highpri
+	work item queued after another highpri work item will start
+	execution after the earlier highpri work item starts.
+
+	Although highpri work items are not held back by other
+	runnable work items, they still contribute to the concurrency
+	level.  Highpri work items in runnable state will prevent
+	non-highpri work items from starting execution.
+
+	This flag is meaningless for unbound wq.
+
+  WQ_CPU_INTENSIVE
+
+	Work items of a CPU intensive wq do not contribute to the
+	concurrency level.  In other words, runnable CPU intensive
+	work items will not prevent other work items from starting
+	execution.  This is useful for bound work items which are
+	expected to hog CPU cycles so that their execution is
+	regulated by the system scheduler.
+
+	Although CPU intensive work items don't contribute to the
+	concurrency level, start of their executions is still
+	regulated by the concurrency management and runnable
+	non-CPU-intensive work items can delay execution of CPU
+	intensive work items.
+
+	This flag is meaningless for unbound wq.
+
+  WQ_HIGHPRI | WQ_CPU_INTENSIVE
+
+	This combination makes the wq avoid interaction with
+	concurrency management completely and behave as a simple
+	per-CPU execution context provider.  Work items queued on a
+	highpri CPU-intensive wq start execution as soon as resources
+	are available and don't affect execution of other work items.
+
+@max_active:
+
+@max_active determines the maximum number of execution contexts per
+CPU which can be assigned to the work items of a wq.  For example,
+with @max_active of 16, at most 16 work items of the wq can be
+executing at the same time per CPU.
+
+Currently, for a bound wq, the maximum limit for @max_active is 512
+and the default value used when 0 is specified is 256.  For an unbound
+wq, the limit is higher of 512 and 4 * num_possible_cpus().  These
+values are chosen sufficiently high such that they are not the
+limiting factor while providing protection in runaway cases.
+
+The number of active work items of a wq is usually regulated by the
+users of the wq, more specifically, by how many work items the users
+may queue at the same time.  Unless there is a specific need for
+throttling the number of active work items, specifying '0' is
+recommended.
+
+Some users depend on the strict execution ordering of ST wq.  The
+combination of @max_active of 1 and WQ_UNBOUND is used to achieve this
+behavior.  Work items on such wq are always queued to the unbound gcwq
+and only one work item can be active at any given time thus achieving
+the same ordering property as ST wq.
+
+
+5. Example Execution Scenarios
+
+The following example execution scenarios try to illustrate how cmwq
+behave under different configurations.
+
+ Work items w0, w1, w2 are queued to a bound wq q0 on the same CPU.
+ w0 burns CPU for 5ms then sleeps for 10ms then burns CPU for 5ms
+ again before finishing.  w1 and w2 burn CPU for 5ms then sleep for
+ 10ms.
+
+Ignoring all other tasks, works and processing overhead, and assuming
+simple FIFO scheduling, the following is one highly simplified version
+of possible sequences of events with the original wq.
+
+ TIME IN MSECS	EVENT
+ 0		w0 starts and burns CPU
+ 5		w0 sleeps
+ 15		w0 wakes up and burns CPU
+ 20		w0 finishes
+ 20		w1 starts and burns CPU
+ 25		w1 sleeps
+ 35		w1 wakes up and finishes
+ 35		w2 starts and burns CPU
+ 40		w2 sleeps
+ 50		w2 wakes up and finishes
+
+And with cmwq with @max_active >= 3,
+
+ TIME IN MSECS	EVENT
+ 0		w0 starts and burns CPU
+ 5		w0 sleeps
+ 5		w1 starts and burns CPU
+ 10		w1 sleeps
+ 10		w2 starts and burns CPU
+ 15		w2 sleeps
+ 15		w0 wakes up and burns CPU
+ 20		w0 finishes
+ 20		w1 wakes up and finishes
+ 25		w2 wakes up and finishes
+
+If @max_active == 2,
+
+ TIME IN MSECS	EVENT
+ 0		w0 starts and burns CPU
+ 5		w0 sleeps
+ 5		w1 starts and burns CPU
+ 10		w1 sleeps
+ 15		w0 wakes up and burns CPU
+ 20		w0 finishes
+ 20		w1 wakes up and finishes
+ 20		w2 starts and burns CPU
+ 25		w2 sleeps
+ 35		w2 wakes up and finishes
+
+Now, let's assume w1 and w2 are queued to a different wq q1 which has
+WQ_HIGHPRI set,
+
+ TIME IN MSECS	EVENT
+ 0		w1 and w2 start and burn CPU
+ 5		w1 sleeps
+ 10		w2 sleeps
+ 10		w0 starts and burns CPU
+ 15		w0 sleeps
+ 15		w1 wakes up and finishes
+ 20		w2 wakes up and finishes
+ 25		w0 wakes up and burns CPU
+ 30		w0 finishes
+
+If q1 has WQ_CPU_INTENSIVE set,
+
+ TIME IN MSECS	EVENT
+ 0		w0 starts and burns CPU
+ 5		w0 sleeps
+ 5		w1 and w2 start and burn CPU
+ 10		w1 sleeps
+ 15		w2 sleeps
+ 15		w0 wakes up and burns CPU
+ 20		w0 finishes
+ 20		w1 wakes up and finishes
+ 25		w2 wakes up and finishes
+
+
+6. Guidelines
+
+* Do not forget to use WQ_RESCUER if a wq may process work items which
+  are used during memory reclaim.  Each wq with WQ_RESCUER set has one
+  rescuer thread reserved for it.  If there is dependency among
+  multiple work items used during memory reclaim, they should be
+  queued to separate wq each with WQ_RESCUER.
+
+* Unless strict ordering is required, there is no need to use ST wq.
+
+* Unless there is a specific need, using 0 for @max_active is
+  recommended.  In most use cases, concurrency level usually stays
+  well under the default limit.
+
+* A wq serves as a domain for forward progress guarantee (WQ_RESCUER),
+  flush and work item attributes.  Work items which are not involved
+  in memory reclaim and don't need to be flushed as a part of a group
+  of work items, and don't require any special attribute, can use one
+  of the system wq.  There is no difference in execution
+  characteristics between using a dedicated wq and a system wq.
+
+* Unless work items are expected to consume a huge amount of CPU
+  cycles, using a bound wq is usually beneficial due to the increased
+  level of locality in wq operations and work item execution.

MAINTAINERS

@@ -1135,7 +1135,7 @@ ATLX ETHERNET DRIVERS
 M:	Jay Cliburn <jcliburn@gmail.com>
 M:	Chris Snook <chris.snook@gmail.com>
 M:	Jie Yang <jie.yang@atheros.com>
-L:	atl1-devel@lists.sourceforge.net
+L:	netdev@vger.kernel.org
 W:	http://sourceforge.net/projects/atl1
 W:	http://atl1.sourceforge.net
 S:	Maintained
@@ -1445,6 +1445,16 @@ S:	Maintained
 F:	Documentation/video4linux/cafe_ccic
 F:	drivers/media/video/cafe_ccic*
 
+CAIF NETWORK LAYER
+M:	Sjur Braendeland <sjur.brandeland@stericsson.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	Documentation/networking/caif/
+F:	drivers/net/caif/
+F:	include/linux/caif/
+F:	include/net/caif/
+F:	net/caif/
+
 CALGARY x86-64 IOMMU
 M:	Muli Ben-Yehuda <muli@il.ibm.com>
 M:	"Jon D. Mason" <jdmason@kudzu.us>
@@ -2201,6 +2211,12 @@ L:	linux-rdma@vger.kernel.org
 S:	Supported
 F:	drivers/infiniband/hw/ehca/
 
+EHEA (IBM pSeries eHEA 10Gb ethernet adapter) DRIVER
+M:	Breno Leitao <leitao@linux.vnet.ibm.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/ehea/
+
 EMBEDDED LINUX
 M:	Paul Gortmaker <paul.gortmaker@windriver.com>
 M:	Matt Mackall <mpm@selenic.com>
@@ -2641,9 +2657,12 @@ S:	Maintained
 F:	drivers/media/video/gspca/
 
 HARDWARE MONITORING
+M:	Jean Delvare <khali@linux-fr.org>
+M:	Guenter Roeck <guenter.roeck@ericsson.com>
 L:	lm-sensors@lm-sensors.org
 W:	http://www.lm-sensors.org/
-S:	Orphan
+T:	quilt kernel.org/pub/linux/kernel/people/jdelvare/linux-2.6/jdelvare-hwmon/
+S:	Maintained
 F:	Documentation/hwmon/
 F:	drivers/hwmon/
 F:	include/linux/hwmon*.h
@@ -2781,11 +2800,6 @@ S:	Maintained
 F:	arch/x86/kernel/hpet.c
 F:	arch/x86/include/asm/hpet.h
 
-HPET:	ACPI
-M:	Bob Picco <bob.picco@hp.com>
-S:	Maintained
-F:	drivers/char/hpet.c
-
 HPFS FILESYSTEM
 M:	Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz>
 W:	http://artax.karlin.mff.cuni.cz/~mikulas/vyplody/hpfs/index-e.cgi
@@ -3398,7 +3412,7 @@ F:	drivers/s390/kvm/
 
 KEXEC
 M:	Eric Biederman <ebiederm@xmission.com>
-W:	http://ftp.kernel.org/pub/linux/kernel/people/horms/kexec-tools/
+W:	http://kernel.org/pub/linux/utils/kernel/kexec/
 L:	kexec@lists.infradead.org
 S:	Maintained
 F:	include/linux/kexec.h
@@ -3923,13 +3937,12 @@ F:	Documentation/sound/oss/MultiSound
 F:	sound/oss/msnd*
 
 MULTITECH MULTIPORT CARD (ISICOM)
-M:	Jiri Slaby <jirislaby@gmail.com>
-S:	Maintained
+S:	Orphan
 F:	drivers/char/isicom.c
 F:	include/linux/isicom.h
 
 MUSB MULTIPOINT HIGH SPEED DUAL-ROLE CONTROLLER
-M:	Felipe Balbi <felipe.balbi@nokia.com>
+M:	Felipe Balbi <balbi@ti.com>
 L:	linux-usb@vger.kernel.org
 T:	git git://gitorious.org/usb/usb.git
 S:	Maintained
@@ -4227,7 +4240,7 @@ S:	Maintained
 F:	drivers/char/hw_random/omap-rng.c
 
 OMAP USB SUPPORT
-M:	Felipe Balbi <felipe.balbi@nokia.com>
+M:	Felipe Balbi <balbi@ti.com>
 M:	David Brownell <dbrownell@users.sourceforge.net>
 L:	linux-usb@vger.kernel.org
 L:	linux-omap@vger.kernel.org
@@ -4604,7 +4617,7 @@ F:	include/linux/preempt.h
 PRISM54 WIRELESS DRIVER
 M:	"Luis R. Rodriguez" <mcgrof@gmail.com>
 L:	linux-wireless@vger.kernel.org
-W:	http://prism54.org
+W:	http://wireless.kernel.org/en/users/Drivers/p54
 S:	Obsolete
 F:	drivers/net/wireless/prism54/
 
@@ -4805,6 +4818,7 @@ RCUTORTURE MODULE
 M:	Josh Triplett <josh@freedesktop.org>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 S:	Supported
+T:	git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-2.6-rcu.git
 F:	Documentation/RCU/torture.txt
 F:	kernel/rcutorture.c
 
@@ -4829,6 +4843,7 @@ M:	Dipankar Sarma <dipankar@in.ibm.com>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 W:	http://www.rdrop.com/users/paulmck/rclock/
 S:	Supported
+T:	git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-2.6-rcu.git
 F:	Documentation/RCU/
 F:	include/linux/rcu*
 F:	include/linux/srcu*
@@ -4836,12 +4851,10 @@ F:	kernel/rcu*
 F:	kernel/srcu*
 X:	kernel/rcutorture.c
 
-REAL TIME CLOCK DRIVER
+REAL TIME CLOCK DRIVER (LEGACY)
 M:	Paul Gortmaker <p_gortmaker@yahoo.com>
 S:	Maintained
-F:	Documentation/rtc.txt
-F:	drivers/rtc/
-F:	include/linux/rtc.h
+F:	drivers/char/rtc.c
 
 REAL TIME CLOCK (RTC) SUBSYSTEM
 M:	Alessandro Zummo <a.zummo@towertech.it>

Makefile

 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 36
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc5
 NAME = Sheep on Meth
 
 # *DOCUMENTATION*

arch/alpha/include/asm/cache.h

@@ -17,7 +17,6 @@
 # define L1_CACHE_SHIFT     5
 #endif
 
-#define L1_CACHE_ALIGN(x)  (((x)+(L1_CACHE_BYTES-1))&~(L1_CACHE_BYTES-1))
 #define SMP_CACHE_BYTES    L1_CACHE_BYTES
 
 #endif

arch/alpha/include/asm/cacheflush.h

@@ -43,6 +43,8 @@ extern void smp_imb(void);
 /* ??? Ought to use this in arch/alpha/kernel/signal.c too.  */
 
 #ifndef CONFIG_SMP
+#include <linux/sched.h>
+
 extern void __load_new_mm_context(struct mm_struct *);
 static inline void
 flush_icache_user_range(struct vm_area_struct *vma, struct page *page,

arch/alpha/include/asm/unistd.h

@@ -449,10 +449,13 @@
 #define __NR_pwritev			491
 #define __NR_rt_tgsigqueueinfo		492
 #define __NR_perf_event_open		493
+#define __NR_fanotify_init		494
+#define __NR_fanotify_mark		495
+#define __NR_prlimit64			496
 
 #ifdef __KERNEL__
 
-#define NR_SYSCALLS			494
+#define NR_SYSCALLS			497
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
@@ -463,6 +466,7 @@
 #define __ARCH_WANT_SYS_OLD_GETRLIMIT
 #define __ARCH_WANT_SYS_OLDUMOUNT
 #define __ARCH_WANT_SYS_SIGPENDING
+#define __ARCH_WANT_SYS_RT_SIGSUSPEND
 
 /* "Conditional" syscalls.  What we want is
 

arch/alpha/kernel/entry.S

@@ -317,14 +317,14 @@ ret_from_sys_call:
 	ldq	$0, SP_OFF($sp)
 	and	$0, 8, $0
 	beq	$0, restore_all
-ret_from_reschedule:
+ret_to_user:
 	/* Make sure need_resched and sigpending don't change between
 		sampling and the rti.  */
 	lda	$16, 7
 	call_pal PAL_swpipl
 	ldl	$5, TI_FLAGS($8)
 	and	$5, _TIF_WORK_MASK, $2
-	bne	$5, work_pending
+	bne	$2, work_pending
 restore_all:
 	RESTORE_ALL
 	call_pal PAL_rti
@@ -363,7 +363,7 @@ $ret_success:
  *       $8: current.
  *      $19: The old syscall number, or zero if this is not a return
  *           from a syscall that errored and is possibly restartable.
- *      $20: Error indication.
+ *      $20: The old a3 value
  */
 
 	.align	4
@@ -392,12 +392,18 @@ $work_resched:
 
 $work_notifysig:
 	mov	$sp, $16
-	br	$1, do_switch_stack
+	bsr	$1, do_switch_stack
 	mov	$sp, $17
 	mov	$5, $18
+	mov	$19, $9		/* save old syscall number */
+	mov	$20, $10	/* save old a3 */
+	and	$5, _TIF_SIGPENDING, $2
+	cmovne	$2, 0, $9	/* we don't want double syscall restarts */
 	jsr	$26, do_notify_resume
+	mov	$9, $19
+	mov	$10, $20
 	bsr	$1, undo_switch_stack
-	br	restore_all
+	br	ret_to_user
 .end work_pending
 
 /*
@@ -430,6 +436,7 @@ strace:
 	beq	$1, 1f
 	ldq	$27, 0($2)
 1:	jsr	$26, ($27), sys_gettimeofday
+ret_from_straced:
 	ldgp	$gp, 0($26)
 
 	/* check return.. */
@@ -757,11 +764,15 @@ sys_vfork:
 	.ent	sys_sigreturn
 sys_sigreturn:
 	.prologue 0
+	lda	$9, ret_from_straced
+	cmpult	$26, $9, $9
 	mov	$sp, $17
 	lda	$18, -SWITCH_STACK_SIZE($sp)
 	lda	$sp, -SWITCH_STACK_SIZE($sp)
 	jsr	$26, do_sigreturn
-	br	$1, undo_switch_stack
+	bne	$9, 1f
+	jsr	$26, syscall_trace
+1:	br	$1, undo_switch_stack
 	br	ret_from_sys_call
 .end sys_sigreturn
 
@@ -770,46 +781,18 @@ sys_sigreturn:
 	.ent	sys_rt_sigreturn
 sys_rt_sigreturn:
 	.prologue 0
+	lda	$9, ret_from_straced
+	cmpult	$26, $9, $9
 	mov	$sp, $17
 	lda	$18, -SWITCH_STACK_SIZE($sp)
 	lda	$sp, -SWITCH_STACK_SIZE($sp)
 	jsr	$26, do_rt_sigreturn
-	br	$1, undo_switch_stack
+	bne	$9, 1f
+	jsr	$26, syscall_trace
+1:	br	$1, undo_switch_stack
 	br	ret_from_sys_call
 .end sys_rt_sigreturn
 
-	.align	4
-	.globl	sys_sigsuspend
-	.ent	sys_sigsuspend
-sys_sigsuspend:
-	.prologue 0
-	mov	$sp, $17
-	br	$1, do_switch_stack
-	mov	$sp, $18
-	subq	$sp, 16, $sp
-	stq	$26, 0($sp)
-	jsr	$26, do_sigsuspend
-	ldq	$26, 0($sp)
-	lda	$sp, SWITCH_STACK_SIZE+16($sp)
-	ret
-.end sys_sigsuspend
-
-	.align	4
-	.globl	sys_rt_sigsuspend
-	.ent	sys_rt_sigsuspend
-sys_rt_sigsuspend:
-	.prologue 0
-	mov	$sp, $18
-	br	$1, do_switch_stack
-	mov	$sp, $19
-	subq	$sp, 16, $sp
-	stq	$26, 0($sp)
-	jsr	$26, do_rt_sigsuspend
-	ldq	$26, 0($sp)
-	lda	$sp, SWITCH_STACK_SIZE+16($sp)
-	ret
-.end sys_rt_sigsuspend
-
 	.align	4
 	.globl	sys_sethae
 	.ent	sys_sethae