Merge branch 'for-linus' into for-2.6.33

Conflicts:
	block/cfq-iosched.c

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

22 files changed, 800 insertions, 180 deletions

diff --git a/Documentation/ABI/testing/sysfs-class-usb_host b/Documentation/ABI/testing/sysfs-class-uwb_rc-wusbhc
index 46b66ad1f1b45..4e8106f7cfd9a 100644
--- a/Documentation/ABI/testing/sysfs-class-usb_host
+++ b/Documentation/ABI/testing/sysfs-class-uwb_rc-wusbhc
@@ -1,4 +1,4 @@
-What:           /sys/class/usb_host/usb_hostN/wusb_chid
+What:           /sys/class/uwb_rc/uwbN/wusbhc/wusb_chid
 Date:           July 2008
 KernelVersion:  2.6.27
 Contact:        David Vrabel <david.vrabel@csr.com>
@@ -9,7 +9,7 @@ Description:
 
                 Set an all zero CHID to stop the host controller.
 
-What:           /sys/class/usb_host/usb_hostN/wusb_trust_timeout
+What:           /sys/class/uwb_rc/uwbN/wusbhc/wusb_trust_timeout
 Date:           July 2008
 KernelVersion:  2.6.27
 Contact:        David Vrabel <david.vrabel@csr.com>
diff --git a/Documentation/ABI/testing/sysfs-devices-cache_disable b/Documentation/ABI/testing/sysfs-devices-cache_disable
deleted file mode 100644
index 175bb4f705124..0000000000000
--- a/Documentation/ABI/testing/sysfs-devices-cache_disable
+++ /dev/null
@@ -1,18 +0,0 @@
-What:      /sys/devices/system/cpu/cpu*/cache/index*/cache_disable_X
-Date:      August 2008
-KernelVersion:	2.6.27
-Contact:	mark.langsdorf@amd.com
-Description:	These files exist in every cpu's cache index directories.
-		There are currently 2 cache_disable_# files in each
-		directory.  Reading from these files on a supported
-		processor will return that cache disable index value
-		for that processor and node.  Writing to one of these
-		files will cause the specificed cache index to be disabled.
-
-		Currently, only AMD Family 10h Processors support cache index
-		disable, and only for their L3 caches.  See the BIOS and
-		Kernel Developer's Guide at
-		http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/31116-Public-GH-BKDG_3.20_2-4-09.pdf
-		for formatting information and other details on the
-		cache index disable.
-Users:    joachim.deguara@amd.com
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
new file mode 100644
index 0000000000000..a703b9e9aeb9d
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -0,0 +1,156 @@
+What:		/sys/devices/system/cpu/
+Date:		pre-git history
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:
+		A collection of both global and individual CPU attributes
+
+		Individual CPU attributes are contained in subdirectories
+		named by the kernel's logical CPU number, e.g.:
+
+		/sys/devices/system/cpu/cpu#/
+
+What:		/sys/devices/system/cpu/sched_mc_power_savings
+		/sys/devices/system/cpu/sched_smt_power_savings
+Date:		June 2006
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Discover and adjust the kernel's multi-core scheduler support.
+
+		Possible values are:
+
+		0 - No power saving load balance (default value)
+		1 - Fill one thread/core/package first for long running threads
+		2 - Also bias task wakeups to semi-idle cpu package for power
+		    savings
+
+		sched_mc_power_savings is dependent upon SCHED_MC, which is
+		itself architecture dependent.
+
+		sched_smt_power_savings is dependent upon SCHED_SMT, which
+		is itself architecture dependent.
+
+		The two files are independent of each other. It is possible
+		that one file may be present without the other.
+
+		Introduced by git commit 5c45bf27.
+
+
+What:		/sys/devices/system/cpu/kernel_max
+		/sys/devices/system/cpu/offline
+		/sys/devices/system/cpu/online
+		/sys/devices/system/cpu/possible
+		/sys/devices/system/cpu/present
+Date:		December 2008
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	CPU topology files that describe kernel limits related to
+		hotplug. Briefly:
+
+		kernel_max: the maximum cpu index allowed by the kernel
+		configuration.
+
+		offline: cpus that are not online because they have been
+		HOTPLUGGED off or exceed the limit of cpus allowed by the
+		kernel configuration (kernel_max above).
+
+		online: cpus that are online and being scheduled.
+
+		possible: cpus that have been allocated resources and can be
+		brought online if they are present.
+
+		present: cpus that have been identified as being present in
+		the system.
+
+		See Documentation/cputopology.txt for more information.
+
+
+
+What:		/sys/devices/system/cpu/cpu#/node
+Date:		October 2009
+Contact:	Linux memory management mailing list <linux-mm@kvack.org>
+Description:	Discover NUMA node a CPU belongs to
+
+		When CONFIG_NUMA is enabled, a symbolic link that points
+		to the corresponding NUMA node directory.
+
+		For example, the following symlink is created for cpu42
+		in NUMA node 2:
+
+		/sys/devices/system/cpu/cpu42/node2 -> ../../node/node2
+
+
+What:		/sys/devices/system/cpu/cpu#/topology/core_id
+		/sys/devices/system/cpu/cpu#/topology/core_siblings
+		/sys/devices/system/cpu/cpu#/topology/core_siblings_list
+		/sys/devices/system/cpu/cpu#/topology/physical_package_id
+		/sys/devices/system/cpu/cpu#/topology/thread_siblings
+		/sys/devices/system/cpu/cpu#/topology/thread_siblings_list
+Date:		December 2008
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	CPU topology files that describe a logical CPU's relationship
+		to other cores and threads in the same physical package.
+
+		One cpu# directory is created per logical CPU in the system,
+		e.g. /sys/devices/system/cpu/cpu42/.
+
+		Briefly, the files above are:
+
+		core_id: the CPU core ID of cpu#. Typically it is the
+		hardware platform's identifier (rather than the kernel's).
+		The actual value is architecture and platform dependent.
+
+		core_siblings: internal kernel map of cpu#'s hardware threads
+		within the same physical_package_id.
+
+		core_siblings_list: human-readable list of the logical CPU
+		numbers within the same physical_package_id as cpu#.
+
+		physical_package_id: physical package id of cpu#. Typically
+		corresponds to a physical socket number, but the actual value
+		is architecture and platform dependent.
+
+		thread_siblings: internel kernel map of cpu#'s hardware
+		threads within the same core as cpu#
+
+		thread_siblings_list: human-readable list of cpu#'s hardware
+		threads within the same core as cpu#
+
+		See Documentation/cputopology.txt for more information.
+
+
+What:		/sys/devices/system/cpu/cpuidle/current_driver
+		/sys/devices/system/cpu/cpuidle/current_governer_ro
+Date:		September 2007
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Discover cpuidle policy and mechanism
+
+		Various CPUs today support multiple idle levels that are
+		differentiated by varying exit latencies and power
+		consumption during idle.
+
+		Idle policy (governor) is differentiated from idle mechanism
+		(driver)
+
+		current_driver: displays current idle mechanism
+
+		current_governor_ro: displays current idle policy
+
+		See files in Documentation/cpuidle/ for more information.
+
+
+What:      /sys/devices/system/cpu/cpu*/cache/index*/cache_disable_X
+Date:      August 2008
+KernelVersion:	2.6.27
+Contact:	mark.langsdorf@amd.com
+Description:	These files exist in every cpu's cache index directories.
+		There are currently 2 cache_disable_# files in each
+		directory.  Reading from these files on a supported
+		processor will return that cache disable index value
+		for that processor and node.  Writing to one of these
+		files will cause the specificed cache index to be disabled.
+
+		Currently, only AMD Family 10h Processors support cache index
+		disable, and only for their L3 caches.  See the BIOS and
+		Kernel Developer's Guide at
+		http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/31116-Public-GH-BKDG_3.20_2-4-09.pdf
+		for formatting information and other details on the
+		cache index disable.
+Users:    joachim.deguara@amd.com
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 455d4e6d346d8..0b33bfe7dde99 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -227,7 +227,14 @@ as the path relative to the root of the cgroup file system.
 Each cgroup is represented by a directory in the cgroup file system
 containing the following files describing that cgroup:
 
- - tasks: list of tasks (by pid) attached to that cgroup
+ - tasks: list of tasks (by pid) attached to that cgroup.  This list
+   is not guaranteed to be sorted.  Writing a thread id into this file
+   moves the thread into this cgroup.
+ - cgroup.procs: list of tgids in the cgroup.  This list is not
+   guaranteed to be sorted or free of duplicate tgids, and userspace
+   should sort/uniquify the list if this property is required.
+   Writing a tgid into this file moves all threads with that tgid into
+   this cgroup.
  - notify_on_release flag: run the release agent on exit?
  - release_agent: the path to use for release notifications (this file
    exists in the top cgroup only)
@@ -374,7 +381,7 @@ Now you want to do something with this cgroup.
 
 In this directory you can find several files:
 # ls
-notify_on_release tasks
+cgroup.procs notify_on_release tasks
 (plus whatever files added by the attached subsystems)
 
 Now attach your shell to this cgroup:
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index b41f3e58aefa8..f1c5c4bccd3e8 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -1,15 +1,28 @@
 
-Export cpu topology info via sysfs. Items (attributes) are similar
+Export CPU topology info via sysfs. Items (attributes) are similar
 to /proc/cpuinfo.
 
 1) /sys/devices/system/cpu/cpuX/topology/physical_package_id:
-represent the physical package id of  cpu X;
+
+	physical package id of cpuX. Typically corresponds to a physical
+	socket number, but the actual value is architecture and platform
+	dependent.
+
 2) /sys/devices/system/cpu/cpuX/topology/core_id:
-represent the cpu core id to cpu X;
+
+	the CPU core ID of cpuX. Typically it is the hardware platform's
+	identifier (rather than the kernel's).  The actual value is
+	architecture and platform dependent.
+
 3) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
-represent the thread siblings to cpu X in the same core;
+
+	internel kernel map of cpuX's hardware threads within the same
+	core as cpuX
+
 4) /sys/devices/system/cpu/cpuX/topology/core_siblings:
-represent the thread siblings to cpu X in the same physical package;
+
+	internal kernel map of cpuX's hardware threads within the same
+	physical_package_id.
 
 To implement it in an architecture-neutral way, a new source file,
 drivers/base/topology.c, is to export the 4 attributes.
@@ -32,32 +45,32 @@ not defined by include/asm-XXX/topology.h:
 3) thread_siblings: just the given CPU
 4) core_siblings: just the given CPU
 
-Additionally, cpu topology information is provided under
+Additionally, CPU topology information is provided under
 /sys/devices/system/cpu and includes these files.  The internal
 source for the output is in brackets ("[]").
 
-    kernel_max: the maximum cpu index allowed by the kernel configuration.
+    kernel_max: the maximum CPU index allowed by the kernel configuration.
 		[NR_CPUS-1]
 
-    offline:	cpus that are not online because they have been
+    offline:	CPUs that are not online because they have been
 		HOTPLUGGED off (see cpu-hotplug.txt) or exceed the limit
-		of cpus allowed by the kernel configuration (kernel_max
+		of CPUs allowed by the kernel configuration (kernel_max
 		above). [~cpu_online_mask + cpus >= NR_CPUS]
 
-    online:	cpus that are online and being scheduled [cpu_online_mask]
+    online:	CPUs that are online and being scheduled [cpu_online_mask]
 
-    possible:	cpus that have been allocated resources and can be
+    possible:	CPUs that have been allocated resources and can be
 		brought online if they are present. [cpu_possible_mask]
 
-    present:	cpus that have been identified as being present in the
+    present:	CPUs that have been identified as being present in the
 		system. [cpu_present_mask]
 
 The format for the above output is compatible with cpulist_parse()
 [see <linux/cpumask.h>].  Some examples follow.
 
-In this example, there are 64 cpus in the system but cpus 32-63 exceed
+In this example, there are 64 CPUs in the system but cpus 32-63 exceed
 the kernel max which is limited to 0..31 by the NR_CPUS config option
-being 32.  Note also that cpus 2 and 4-31 are not online but could be
+being 32.  Note also that CPUs 2 and 4-31 are not online but could be
 brought online as they are both present and possible.
 
      kernel_max: 31
@@ -67,8 +80,8 @@ brought online as they are both present and possible.
         present: 0-31
 
 In this example, the NR_CPUS config option is 128, but the kernel was
-started with possible_cpus=144.  There are 4 cpus in the system and cpu2
-was manually taken offline (and is the only cpu that can be brought
+started with possible_cpus=144.  There are 4 CPUs in the system and cpu2
+was manually taken offline (and is the only CPU that can be brought
 online.)
 
      kernel_max: 127
@@ -78,4 +91,4 @@ online.)
         present: 0-3
 
 See cpu-hotplug.txt for the possible_cpus=NUM kernel start parameter
-as well as more information on the various cpumask's.
+as well as more information on the various cpumasks.
diff --git a/Documentation/debugging-via-ohci1394.txt b/Documentation/debugging-via-ohci1394.txt
index 59a91e5c69096..611f5a5499b15 100644
--- a/Documentation/debugging-via-ohci1394.txt
+++ b/Documentation/debugging-via-ohci1394.txt
@@ -64,14 +64,14 @@ be used to view the printk buffer of a remote machine, even with live update.
 
 Bernhard Kaindl enhanced firescope to support accessing 64-bit machines
 from 32-bit firescope and vice versa:
-- ftp://ftp.suse.de/private/bk/firewire/tools/firescope-0.2.2.tar.bz2
+- http://halobates.de/firewire/firescope-0.2.2.tar.bz2
 
 and he implemented fast system dump (alpha version - read README.txt):
-- ftp://ftp.suse.de/private/bk/firewire/tools/firedump-0.1.tar.bz2
+- http://halobates.de/firewire/firedump-0.1.tar.bz2
 
 There is also a gdb proxy for firewire which allows to use gdb to access
 data which can be referenced from symbols found by gdb in vmlinux:
-- ftp://ftp.suse.de/private/bk/firewire/tools/fireproxy-0.33.tar.bz2
+- http://halobates.de/firewire/fireproxy-0.33.tar.bz2
 
 The latest version of this gdb proxy (fireproxy-0.34) can communicate (not
 yet stable) with kgdb over an memory-based communication module (kgdbom).
@@ -178,7 +178,7 @@ Step-by-step instructions for using firescope with early OHCI initialization:
 
 Notes
 -----
-Documentation and specifications: ftp://ftp.suse.de/private/bk/firewire/docs
+Documentation and specifications: http://halobates.de/firewire/
 
 FireWire is a trademark of Apple Inc. - for more information please refer to:
 http://en.wikipedia.org/wiki/FireWire
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 89a47b5aff07f..bc693fffabe08 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -418,6 +418,14 @@ When:	2.6.33
 Why:	Should be implemented in userspace, policy daemon.
 Who:	Johannes Berg <johannes@sipsolutions.net>
 
+---------------------------
+
+What:	CONFIG_INOTIFY
+When:	2.6.33
+Why:	last user (audit) will be converted to the newer more generic
+	and more easily maintained fsnotify subsystem
+Who:	Eric Paris <eparis@redhat.com>
+
 ----------------------------
 
 What:	lock_policy_rwsem_* and unlock_policy_rwsem_* will not be
@@ -451,3 +459,33 @@ Why:	OSS sound_core grabs all legacy minors (0-255) of SOUND_MAJOR
 	will also allow making ALSA OSS emulation independent of
 	sound_core.  The dependency will be broken then too.
 Who:	Tejun Heo <tj@kernel.org>
+
+----------------------------
+
+What:	Support for VMware's guest paravirtuliazation technique [VMI] will be
+	dropped.
+When:	2.6.37 or earlier.
+Why:	With the recent innovations in CPU hardware acceleration technologies
+	from Intel and AMD, VMware ran a few experiments to compare these
+	techniques to guest paravirtualization technique on VMware's platform.
+	These hardware assisted virtualization techniques have outperformed the
+	performance benefits provided by VMI in most of the workloads. VMware
+	expects that these hardware features will be ubiquitous in a couple of
+	years, as a result, VMware has started a phased retirement of this
+	feature from the hypervisor. We will be removing this feature from the
+	Kernel too. Right now we are targeting 2.6.37 but can retire earlier if
+	technical reasons (read opportunity to remove major chunk of pvops)
+	arise.
+
+	Please note that VMI has always been an optimization and non-VMI kernels
+	still work fine on VMware's platform.
+	Latest versions of VMware's product which support VMI are,
+	Workstation 7.0 and VSphere 4.0 on ESX side, future maintainence
+	releases for these products will continue supporting VMI.
+
+	For more details about VMI retirement take a look at this,
+	http://blogs.vmware.com/guestosguide/2009/09/vmi-retirement.html
+
+Who:	Alok N Kataria <akataria@vmware.com>
+
+----------------------------
diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.txt
index 570f9bd9be2be..05d5cf1d743f1 100644
--- a/Documentation/filesystems/ext3.txt
+++ b/Documentation/filesystems/ext3.txt
@@ -123,10 +123,18 @@ resuid=n		The user ID which may use the reserved blocks.
 
 sb=n			Use alternate superblock at this location.
 
-quota
-noquota
-grpquota
-usrquota
+quota			These options are ignored by the filesystem. They
+noquota			are used only by quota tools to recognize volumes
+grpquota		where quota should be turned on. See documentation
+usrquota		in the quota-tools package for more details
+			(http://sourceforge.net/projects/linuxquota).
+
+jqfmt=<quota type>	These options tell filesystem details about quota
+usrjquota=<file>	so that quota information can be properly updated
+grpjquota=<file>	during journal replay. They replace the above
+			quota options. See documentation in the quota-tools
+			package for more details
+			(http://sourceforge.net/projects/linuxquota).
 
 bh		(*)	ext3 associates buffer heads to data pages to
 nobh			(a) cache disk block mapping information
diff --git a/Documentation/flexible-arrays.txt b/Documentation/flexible-arrays.txt
index 84eb26808dee9..cb8a3a00cc926 100644
--- a/Documentation/flexible-arrays.txt
+++ b/Documentation/flexible-arrays.txt
@@ -1,5 +1,5 @@
 Using flexible arrays in the kernel
-Last updated for 2.6.31
+Last updated for 2.6.32
 Jonathan Corbet <corbet@lwn.net>
 
 Large contiguous memory allocations can be unreliable in the Linux kernel.
@@ -40,6 +40,13 @@ argument is passed directly to the internal memory allocation calls.  With
 the current code, using flags to ask for high memory is likely to lead to
 notably unpleasant side effects.
 
+It is also possible to define flexible arrays at compile time with:
+
+    DEFINE_FLEX_ARRAY(name, element_size, total);
+
+This macro will result in a definition of an array with the given name; the
+element size and total will be checked for validity at compile time.
+
 Storing data into a flexible array is accomplished with a call to:
 
     int flex_array_put(struct flex_array *array, unsigned int element_nr,
@@ -76,16 +83,30 @@ particular element has never been allocated.
 Note that it is possible to get back a valid pointer for an element which
 has never been stored in the array.  Memory for array elements is allocated
 one page at a time; a single allocation could provide memory for several
-adjacent elements.  The flexible array code does not know if a specific
-element has been written; it only knows if the associated memory is
-present.  So a flex_array_get() call on an element which was never stored
-in the array has the potential to return a pointer to random data.  If the
-caller does not have a separate way to know which elements were actually
-stored, it might be wise, at least, to add GFP_ZERO to the flags argument
-to ensure that all elements are zeroed.
-
-There is no way to remove a single element from the array.  It is possible,
-though, to remove all elements with a call to:
+adjacent elements.  Flexible array elements are normally initialized to the
+value FLEX_ARRAY_FREE (defined as 0x6c in <linux/poison.h>), so errors
+involving that number probably result from use of unstored array entries.
+Note that, if array elements are allocated with __GFP_ZERO, they will be
+initialized to zero and this poisoning will not happen.
+
+Individual elements in the array can be cleared with:
+
+    int flex_array_clear(struct flex_array *array, unsigned int element_nr);
+
+This function will set the given element to FLEX_ARRAY_FREE and return
+zero.  If storage for the indicated element is not allocated for the array,
+flex_array_clear() will return -EINVAL instead.  Note that clearing an
+element does not release the storage associated with it; to reduce the
+allocated size of an array, call:
+
+    int flex_array_shrink(struct flex_array *array);
+
+The return value will be the number of pages of memory actually freed.
+This function works by scanning the array for pages containing nothing but
+FLEX_ARRAY_FREE bytes, so (1) it can be expensive, and (2) it will not work
+if the array's pages are allocated with __GFP_ZERO.
+
+It is possible to remove all elements of an array with a call to:
 
     void flex_array_free_parts(struct flex_array *array);
 
diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface
index dcbd502c8792b..82def883361b1 100644
--- a/Documentation/hwmon/sysfs-interface
+++ b/Documentation/hwmon/sysfs-interface
@@ -353,10 +353,20 @@ power[1-*]_average		Average power use
 				Unit: microWatt
 				RO
 
-power[1-*]_average_interval	Power use averaging interval
+power[1-*]_average_interval	Power use averaging interval.  A poll
+				notification is sent to this file if the
+				hardware changes the averaging interval.
 				Unit: milliseconds
 				RW
 
+power[1-*]_average_interval_max	Maximum power use averaging interval
+				Unit: milliseconds
+				RO
+
+power[1-*]_average_interval_min	Minimum power use averaging interval
+				Unit: milliseconds
+				RO
+
 power[1-*]_average_highest	Historical average maximum power use
 				Unit: microWatt
 				RO
@@ -365,6 +375,18 @@ power[1-*]_average_lowest	Historical average minimum power use
 				Unit: microWatt
 				RO
 
+power[1-*]_average_max		A poll notification is sent to
+				power[1-*]_average when power use
+				rises above this value.
+				Unit: microWatt
+				RW
+
+power[1-*]_average_min		A poll notification is sent to
+				power[1-*]_average when power use
+				sinks below this value.
+				Unit: microWatt
+				RW
+
 power[1-*]_input		Instantaneous power use
 				Unit: microWatt
 				RO
@@ -381,6 +403,39 @@ power[1-*]_reset_history	Reset input_highest, input_lowest,
 				average_highest and average_lowest.
 				WO
 
+power[1-*]_accuracy		Accuracy of the power meter.
+				Unit: Percent
+				RO
+
+power[1-*]_alarm		1 if the system is drawing more power than the
+				cap allows; 0 otherwise.  A poll notification is
+				sent to this file when the power use exceeds the
+				cap.  This file only appears if the cap is known
+				to be enforced by hardware.
+				RO
+
+power[1-*]_cap			If power use rises above this limit, the
+				system should take action to reduce power use.
+				A poll notification is sent to this file if the
+				cap is changed by the hardware.  The *_cap
+				files only appear if the cap is known to be
+				enforced by hardware.
+				Unit: microWatt
+				RW
+
+power[1-*]_cap_hyst		Margin of hysteresis built around capping and
+				notification.
+				Unit: microWatt
+				RW
+
+power[1-*]_cap_max		Maximum cap that can be set.
+				Unit: microWatt
+				RO
+
+power[1-*]_cap_min		Minimum cap that can be set.
+				Unit: microWatt
+				RO
+
 **********
 * Energy *
 **********
diff --git a/Documentation/infiniband/user_mad.txt b/Documentation/infiniband/user_mad.txt
index 744687dd195bb..8a366959f5cc2 100644
--- a/Documentation/infiniband/user_mad.txt
+++ b/Documentation/infiniband/user_mad.txt
@@ -128,8 +128,8 @@ Setting IsSM Capability Bit
   To create the appropriate character device files automatically with
   udev, a rule like
 
-    KERNEL="umad*", NAME="infiniband/%k"
-    KERNEL="issm*", NAME="infiniband/%k"
+    KERNEL=="umad*", NAME="infiniband/%k"
+    KERNEL=="issm*", NAME="infiniband/%k"
 
   can be used.  This will create device nodes named
 
diff --git a/Documentation/infiniband/user_verbs.txt b/Documentation/infiniband/user_verbs.txt
index f847501e50b5e..afe3f8da9018e 100644
--- a/Documentation/infiniband/user_verbs.txt
+++ b/Documentation/infiniband/user_verbs.txt
@@ -58,7 +58,7 @@ Memory pinning
   To create the appropriate character device files automatically with
   udev, a rule like
 
-    KERNEL="uverbs*", NAME="infiniband/%k"
+    KERNEL=="uverbs*", NAME="infiniband/%k"
 
   can be used.  This will create device nodes named
 
diff --git a/Documentation/isdn/INTERFACE.CAPI b/Documentation/isdn/INTERFACE.CAPI
index 686e107923ec1..5fe8de5cc7275 100644
--- a/Documentation/isdn/INTERFACE.CAPI
+++ b/Documentation/isdn/INTERFACE.CAPI
@@ -60,10 +60,9 @@ open() operation on regular files or character devices.
 
 After a successful return from register_appl(), CAPI messages from the
 application may be passed to the driver for the device via calls to the
-send_message() callback function. The CAPI message to send is stored in the
-data portion of an skb. Conversely, the driver may call Kernel CAPI's
-capi_ctr_handle_message() function to pass a received CAPI message to Kernel
-CAPI for forwarding to an application, specifying its ApplID.
+send_message() callback function. Conversely, the driver may call Kernel
+CAPI's capi_ctr_handle_message() function to pass a received CAPI message to
+Kernel CAPI for forwarding to an application, specifying its ApplID.
 
 Deregistration requests (CAPI operation CAPI_RELEASE) from applications are
 forwarded as calls to the release_appl() callback function, passing the same
@@ -142,6 +141,7 @@ u16  (*send_message)(struct capi_ctr *ctrlr, struct sk_buff *skb)
 	to accepting or queueing the message. Errors occurring during the
 	actual processing of the message should be signaled with an
 	appropriate reply message.
+	May be called in process or interrupt context.
 	Calls to this function are not serialized by Kernel CAPI, ie. it must
 	be prepared to be re-entered.
 
@@ -154,7 +154,8 @@ read_proc_t *ctr_read_proc
 	system entry, /proc/capi/controllers/<n>; will be called with a
 	pointer to the device's capi_ctr structure as the last (data) argument
 
-Note: Callback functions are never called in interrupt context.
+Note: Callback functions except send_message() are never called in interrupt
+context.
 
 - to be filled in before calling capi_ctr_ready():
 
@@ -171,14 +172,40 @@ u8 serial[CAPI_SERIAL_LEN]
 	value to return for CAPI_GET_SERIAL
 
 
-4.3 The _cmsg Structure
+4.3 SKBs
+
+CAPI messages are passed between Kernel CAPI and the driver via send_message()
+and capi_ctr_handle_message(), stored in the data portion of a socket buffer
+(skb).  Each skb contains a single CAPI message coded according to the CAPI 2.0
+standard.
+
+For the data transfer messages, DATA_B3_REQ and DATA_B3_IND, the actual
+payload data immediately follows the CAPI message itself within the same skb.
+The Data and Data64 parameters are not used for processing. The Data64
+parameter may be omitted by setting the length field of the CAPI message to 22
+instead of 30.
+
+
+4.4 The _cmsg Structure
 
 (declared in <linux/isdn/capiutil.h>)
 
 The _cmsg structure stores the contents of a CAPI 2.0 message in an easily
-accessible form. It contains members for all possible CAPI 2.0 parameters, of
-which only those appearing in the message type currently being processed are
-actually used. Unused members should be set to zero.
+accessible form. It contains members for all possible CAPI 2.0 parameters,
+including subparameters of the Additional Info and B Protocol structured
+parameters, with the following exceptions:
+
+* second Calling party number (CONNECT_IND)
+
+* Data64 (DATA_B3_REQ and DATA_B3_IND)
+
+* Sending complete (subparameter of Additional Info, CONNECT_REQ and INFO_REQ)
+
+* Global Configuration (subparameter of B Protocol, CONNECT_REQ, CONNECT_RESP
+  and SELECT_B_PROTOCOL_REQ)
+
+Only those parameters appearing in the message type currently being processed
+are actually used. Unused members should be set to zero.
 
 Members are named after the CAPI 2.0 standard names of the parameters they
 represent. See <linux/isdn/capiutil.h> for the exact spelling. Member data
@@ -190,18 +217,19 @@ u16         for CAPI parameters of type 'word'
 
 u32         for CAPI parameters of type 'dword'
 
-_cstruct    for CAPI parameters of type 'struct' not containing any
-	    variably-sized (struct) subparameters (eg. 'Called Party Number')
+_cstruct    for CAPI parameters of type 'struct'
 	    The member is a pointer to a buffer containing the parameter in
 	    CAPI encoding (length + content). It may also be NULL, which will
 	    be taken to represent an empty (zero length) parameter.
+	    Subparameters are stored in encoded form within the content part.
 
-_cmstruct   for CAPI parameters of type 'struct' containing 'struct'
-	    subparameters ('Additional Info' and 'B Protocol')
+_cmstruct   alternative representation for CAPI parameters of type 'struct'
+	    (used only for the 'Additional Info' and 'B Protocol' parameters)
 	    The representation is a single byte containing one of the values:
-	    CAPI_DEFAULT: the parameter is empty
-	    CAPI_COMPOSE: the values of the subparameters are stored
-	    individually in the corresponding _cmsg structure members
+	    CAPI_DEFAULT: The parameter is empty/absent.
+	    CAPI_COMPOSE: The parameter is present.
+	    Subparameter values are stored individually in the corresponding
+	    _cmsg structure members.
 
 Functions capi_cmsg2message() and capi_message2cmsg() are provided to convert
 messages between their transport encoding described in the CAPI 2.0 standard
@@ -297,3 +325,26 @@ char *capi_cmd2str(u8 Command, u8 Subcommand)
 	be NULL if the command/subcommand is not one of those defined in the
 	CAPI 2.0 standard.
 
+
+7. Debugging
+
+The module kernelcapi has a module parameter showcapimsgs controlling some
+debugging output produced by the module. It can only be set when the module is
+loaded, via a parameter "showcapimsgs=<n>" to the modprobe command, either on
+the command line or in the configuration file.
+
+If the lowest bit of showcapimsgs is set, kernelcapi logs controller and
+application up and down events.
+
+In addition, every registered CAPI controller has an associated traceflag
+parameter controlling how CAPI messages sent from and to tha controller are
+logged. The traceflag parameter is initialized with the value of the
+showcapimsgs parameter when the controller is registered, but can later be
+changed via the MANUFACTURER_REQ command KCAPI_CMD_TRACE.
+
+If the value of traceflag is non-zero, CAPI messages are logged.
+DATA_B3 messages are only logged if the value of traceflag is > 2.
+
+If the lowest bit of traceflag is set, only the command/subcommand and message
+length are logged. Otherwise, kernelcapi logs a readable representation of
+the entire message.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 6fa7292947e5c..9107b387e91fc 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -671,6 +671,7 @@ and is between 256 and 4096 characters. It is defined in the file
 	earlyprintk=	[X86,SH,BLACKFIN]
 			earlyprintk=vga
 			earlyprintk=serial[,ttySn[,baudrate]]
+			earlyprintk=ttySn[,baudrate]
 			earlyprintk=dbgp[debugController#]
 
 			Append ",keep" to not disable it when the real console
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index ba9373f82ab5f..098de5bce00a7 100644
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/lguest/lguest.c
@@ -42,7 +42,6 @@
 #include <signal.h>
 #include "linux/lguest_launcher.h"
 #include "linux/virtio_config.h"
-#include <linux/virtio_ids.h>
 #include "linux/virtio_net.h"
 #include "linux/virtio_blk.h"
 #include "linux/virtio_console.h"
diff --git a/Documentation/networking/pktgen.txt b/Documentation/networking/pktgen.txt
index c6cf4a3c16e02..61bb645d50e06 100644
--- a/Documentation/networking/pktgen.txt
+++ b/Documentation/networking/pktgen.txt
@@ -90,6 +90,11 @@ Examples:
  pgset "dstmac 00:00:00:00:00:00"    sets MAC destination address
  pgset "srcmac 00:00:00:00:00:00"    sets MAC source address
 
+ pgset "queue_map_min 0" Sets the min value of tx queue interval
+ pgset "queue_map_max 7" Sets the max value of tx queue interval, for multiqueue devices
+                         To select queue 1 of a given device,
+                         use queue_map_min=1 and queue_map_max=1
+
  pgset "src_mac_count 1" Sets the number of MACs we'll range through.  
                          The 'minimum' MAC is what you set with srcmac.
 
@@ -101,6 +106,9 @@ Examples:
                               IPDST_RND, UDPSRC_RND,
                               UDPDST_RND, MACSRC_RND, MACDST_RND 
                               MPLS_RND, VID_RND, SVID_RND
+                              QUEUE_MAP_RND # queue map random
+                              QUEUE_MAP_CPU # queue map mirrors smp_processor_id()
+
 
  pgset "udp_src_min 9"   set UDP source port min, If < udp_src_max, then
                          cycle through the port range.
diff --git a/Documentation/scsi/hptiop.txt b/Documentation/scsi/hptiop.txt
index a6eb4add1be6d..9605179711f4d 100644
--- a/Documentation/scsi/hptiop.txt
+++ b/Documentation/scsi/hptiop.txt
@@ -3,6 +3,25 @@ HIGHPOINT ROCKETRAID 3xxx/4xxx ADAPTER DRIVER (hptiop)
 Controller Register Map
 -------------------------
 
+For RR44xx Intel IOP based adapters, the controller IOP is accessed via PCI BAR0 and BAR2:
+
+     BAR0 offset    Register
+            0x11C5C Link Interface IRQ Set
+            0x11C60 Link Interface IRQ Clear
+
+     BAR2 offset    Register
+            0x10    Inbound Message Register 0
+            0x14    Inbound Message Register 1
+            0x18    Outbound Message Register 0
+            0x1C    Outbound Message Register 1
+            0x20    Inbound Doorbell Register
+            0x24    Inbound Interrupt Status Register
+            0x28    Inbound Interrupt Mask Register
+            0x30    Outbound Interrupt Status Register
+            0x34    Outbound Interrupt Mask Register
+            0x40    Inbound Queue Port
+            0x44    Outbound Queue Port
+
 For Intel IOP based adapters, the controller IOP is accessed via PCI BAR0:
 
      BAR0 offset    Register
@@ -93,7 +112,7 @@ The driver exposes following sysfs attributes:
 
 
 -----------------------------------------------------------------------------
-Copyright (C) 2006-2007 HighPoint Technologies, Inc. All Rights Reserved.
+Copyright (C) 2006-2009 HighPoint Technologies, Inc. All Rights Reserved.
 
   This file is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt
index 75fddb40f4163..4c7f9aee5c4eb 100644
--- a/Documentation/sound/alsa/HD-Audio-Models.txt
+++ b/Documentation/sound/alsa/HD-Audio-Models.txt
@@ -359,6 +359,7 @@ STAC9227/9228/9229/927x
   5stack-no-fp	D965 5stack without front panel
   dell-3stack	Dell Dimension E520
   dell-bios	Fixes with Dell BIOS setup
+  volknob	Fixes with volume-knob widget 0x24
   auto		BIOS setup (default)
 
 STAC92HD71B*
diff --git a/Documentation/vm/hwpoison.txt b/Documentation/vm/hwpoison.txt
new file mode 100644
index 0000000000000..3ffadf8da61fa
--- /dev/null
+++ b/Documentation/vm/hwpoison.txt
@@ -0,0 +1,136 @@
+What is hwpoison?
+
+Upcoming Intel CPUs have support for recovering from some memory errors
+(``MCA recovery''). This requires the OS to declare a page "poisoned",
+kill the processes associated with it and avoid using it in the future.
+
+This patchkit implements the necessary infrastructure in the VM.
+
+To quote the overview comment:
+
+ * High level machine check handler. Handles pages reported by the
+ * hardware as being corrupted usually due to a 2bit ECC memory or cache
+ * failure.
+ *
+ * This focusses on pages detected as corrupted in the background.
+ * When the current CPU tries to consume corruption the currently
+ * running process can just be killed directly instead. This implies
+ * that if the error cannot be handled for some reason it's safe to
+ * just ignore it because no corruption has been consumed yet. Instead
+ * when that happens another machine check will happen.
+ *
+ * Handles page cache pages in various states. The tricky part
+ * here is that we can access any page asynchronous to other VM
+ * users, because memory failures could happen anytime and anywhere,
+ * possibly violating some of their assumptions. This is why this code
+ * has to be extremely careful. Generally it tries to use normal locking
+ * rules, as in get the standard locks, even if that means the
+ * error handling takes potentially a long time.
+ *
+ * Some of the operations here are somewhat inefficient and have non
+ * linear algorithmic complexity, because the data structures have not
+ * been optimized for this case. This is in particular the case
+ * for the mapping from a vma to a process. Since this case is expected
+ * to be rare we hope we can get away with this.
+
+The code consists of a the high level handler in mm/memory-failure.c,
+a new page poison bit and various checks in the VM to handle poisoned
+pages.
+
+The main target right now is KVM guests, but it works for all kinds
+of applications. KVM support requires a recent qemu-kvm release.
+
+For the KVM use there was need for a new signal type so that
+KVM can inject the machine check into the guest with the proper
+address. This in theory allows other applications to handle
+memory failures too. The expection is that near all applications
+won't do that, but some very specialized ones might.
+
+---
+
+There are two (actually three) modi memory failure recovery can be in:
+
+vm.memory_failure_recovery sysctl set to zero:
+	All memory failures cause a panic. Do not attempt recovery.
+	(on x86 this can be also affected by the tolerant level of the
+	MCE subsystem)
+
+early kill
+	(can be controlled globally and per process)
+	Send SIGBUS to the application as soon as the error is detected
+	This allows applications who can process memory errors in a gentle
+	way (e.g. drop affected object)
+	This is the mode used by KVM qemu.
+
+late kill
+	Send SIGBUS when the application runs into the corrupted page.
+	This is best for memory error unaware applications and default
+	Note some pages are always handled as late kill.
+
+---
+
+User control:
+
+vm.memory_failure_recovery
+	See sysctl.txt
+
+vm.memory_failure_early_kill
+	Enable early kill mode globally
+
+PR_MCE_KILL
+	Set early/late kill mode/revert to system default
+	arg1: PR_MCE_KILL_CLEAR: Revert to system default
+	arg1: PR_MCE_KILL_SET: arg2 defines thread specific mode
+		PR_MCE_KILL_EARLY: Early kill
+		PR_MCE_KILL_LATE:  Late kill
+		PR_MCE_KILL_DEFAULT: Use system global default
+PR_MCE_KILL_GET
+	return current mode
+
+
+---
+
+Testing:
+
+madvise(MADV_POISON, ....)
+	(as root)
+	Poison a page in the process for testing
+
+
+hwpoison-inject module through debugfs
+	/sys/debug/hwpoison/corrupt-pfn
+
+Inject hwpoison fault at PFN echoed into this file
+
+
+Architecture specific MCE injector
+
+x86 has mce-inject, mce-test
+
+Some portable hwpoison test programs in mce-test, see blow.
+
+---
+
+References:
+
+http://halobates.de/mce-lc09-2.pdf
+	Overview presentation from LinuxCon 09
+
+git://git.kernel.org/pub/scm/utils/cpu/mce/mce-test.git
+	Test suite (hwpoison specific portable tests in tsrc)
+
+git://git.kernel.org/pub/scm/utils/cpu/mce/mce-inject.git
+	x86 specific injector
+
+
+---
+
+Limitations:
+
+- Not all page types are supported and never will. Most kernel internal
+objects cannot be recovered, only LRU pages for now.
+- Right now hugepage support is missing.
+
+---
+Andi Kleen, Oct 2009
+
diff --git a/Documentation/vm/ksm.txt b/Documentation/vm/ksm.txt
index 72a22f65960ed..262d8e6793a3e 100644
--- a/Documentation/vm/ksm.txt
+++ b/Documentation/vm/ksm.txt
@@ -52,15 +52,15 @@ The KSM daemon is controlled by sysfs files in /sys/kernel/mm/ksm/,
 readable by all but writable only by root:
 
 max_kernel_pages - set to maximum number of kernel pages that KSM may use
-                   e.g. "echo 2000 > /sys/kernel/mm/ksm/max_kernel_pages"
+                   e.g. "echo 100000 > /sys/kernel/mm/ksm/max_kernel_pages"
                    Value 0 imposes no limit on the kernel pages KSM may use;
                    but note that any process using MADV_MERGEABLE can cause
                    KSM to allocate these pages, unswappable until it exits.
-                   Default: 2000 (chosen for demonstration purposes)
+                   Default: quarter of memory (chosen to not pin too much)
 
 pages_to_scan    - how many present pages to scan before ksmd goes to sleep
-                   e.g. "echo 200 > /sys/kernel/mm/ksm/pages_to_scan"
-                   Default: 200 (chosen for demonstration purposes)
+                   e.g. "echo 100 > /sys/kernel/mm/ksm/pages_to_scan"
+                   Default: 100 (chosen for demonstration purposes)
 
 sleep_millisecs  - how many milliseconds ksmd should sleep before next scan
                    e.g. "echo 20 > /sys/kernel/mm/ksm/sleep_millisecs"
@@ -70,7 +70,8 @@ run              - set 0 to stop ksmd from running but keep merged pages,
                    set 1 to run ksmd e.g. "echo 1 > /sys/kernel/mm/ksm/run",
                    set 2 to stop ksmd and unmerge all pages currently merged,
                          but leave mergeable areas registered for next run
-                   Default: 1 (for immediate use by apps which register)
+                   Default: 0 (must be changed to 1 to activate KSM,
+                               except if CONFIG_SYSFS is disabled)
 
 The effectiveness of KSM and MADV_MERGEABLE is shown in /sys/kernel/mm/ksm/:
 
@@ -86,4 +87,4 @@ pages_volatile embraces several different kinds of activity, but a high
 proportion there would also indicate poor use of madvise MADV_MERGEABLE.
 
 Izik Eidus,
-Hugh Dickins, 30 July 2009
+Hugh Dickins, 24 Sept 2009
diff --git a/Documentation/vm/page-types.c b/Documentation/vm/page-types.c
index fa1a30d9e9d54..3ec4f2a225853 100644
--- a/Documentation/vm/page-types.c
+++ b/Documentation/vm/page-types.c
@@ -2,7 +2,10 @@
  * page-types: Tool for querying page flags
  *
  * Copyright (C) 2009 Intel corporation
- * Copyright (C) 2009 Wu Fengguang <fengguang.wu@intel.com>
+ *
+ * Authors: Wu Fengguang <fengguang.wu@intel.com>
+ *
+ * Released under the General Public License (GPL).
  */
 
 #define _LARGEFILE64_SOURCE
@@ -69,7 +72,9 @@
 #define KPF_COMPOUND_TAIL	16
 #define KPF_HUGE		17
 #define KPF_UNEVICTABLE		18
+#define KPF_HWPOISON		19
 #define KPF_NOPAGE		20
+#define KPF_KSM			21
 
 /* [32-] kernel hacking assistances */
 #define KPF_RESERVED		32
@@ -116,7 +121,9 @@ static char *page_flag_names[] = {
 	[KPF_COMPOUND_TAIL]	= "T:compound_tail",
 	[KPF_HUGE]		= "G:huge",
 	[KPF_UNEVICTABLE]	= "u:unevictable",
+	[KPF_HWPOISON]		= "X:hwpoison",
 	[KPF_NOPAGE]		= "n:nopage",
+	[KPF_KSM]		= "x:ksm",
 
 	[KPF_RESERVED]		= "r:reserved",
 	[KPF_MLOCKED]		= "m:mlocked",
@@ -152,9 +159,6 @@ static unsigned long	opt_size[MAX_ADDR_RANGES];
 static int		nr_vmas;
 static unsigned long	pg_start[MAX_VMAS];
 static unsigned long	pg_end[MAX_VMAS];
-static unsigned long	voffset;
-
-static int		pagemap_fd;
 
 #define MAX_BIT_FILTERS	64
 static int		nr_bit_filters;
@@ -163,9 +167,16 @@ static uint64_t		opt_bits[MAX_BIT_FILTERS];
 
 static int		page_size;
 
-#define PAGES_BATCH	(64 << 10)	/* 64k pages */
+static int		pagemap_fd;
 static int		kpageflags_fd;
 
+static int		opt_hwpoison;
+static int		opt_unpoison;
+
+static char		*hwpoison_debug_fs = "/debug/hwpoison";
+static int		hwpoison_inject_fd;
+static int		hwpoison_forget_fd;
+
 #define HASH_SHIFT	13
 #define HASH_SIZE	(1 << HASH_SHIFT)
 #define HASH_MASK	(HASH_SIZE - 1)
@@ -207,6 +218,74 @@ static void fatal(const char *x, ...)
 	exit(EXIT_FAILURE);
 }
 
+int checked_open(const char *pathname, int flags)
+{
+	int fd = open(pathname, flags);
+
+	if (fd < 0) {
+		perror(pathname);
+		exit(EXIT_FAILURE);
+	}
+
+	return fd;
+}
+
+/*
+ * pagemap/kpageflags routines
+ */
+
+static unsigned long do_u64_read(int fd, char *name,
+				 uint64_t *buf,
+				 unsigned long index,
+				 unsigned long count)
+{
+	long bytes;
+
+	if (index > ULONG_MAX / 8)
+		fatal("index overflow: %lu\n", index);
+
+	if (lseek(fd, index * 8, SEEK_SET) < 0) {
+		perror(name);
+		exit(EXIT_FAILURE);
+	}
+
+	bytes = read(fd, buf, count * 8);
+	if (bytes < 0) {
+		perror(name);
+		exit(EXIT_FAILURE);
+	}
+	if (bytes % 8)
+		fatal("partial read: %lu bytes\n", bytes);
+
+	return bytes / 8;
+}
+
+static unsigned long kpageflags_read(uint64_t *buf,
+				     unsigned long index,
+				     unsigned long pages)
+{
+	return do_u64_read(kpageflags_fd, PROC_KPAGEFLAGS, buf, index, pages);
+}
+
+static unsigned long pagemap_read(uint64_t *buf,
+				  unsigned long index,
+				  unsigned long pages)
+{
+	return do_u64_read(pagemap_fd, "/proc/pid/pagemap", buf, index, pages);
+}
+
+static unsigned long pagemap_pfn(uint64_t val)
+{
+	unsigned long pfn;
+
+	if (val & PM_PRESENT)
+		pfn = PM_PFRAME(val);
+	else
+		pfn = 0;
+
+	return pfn;
+}
+
 
 /*
  * page flag names
@@ -255,7 +334,8 @@ static char *page_flag_longname(uint64_t flags)
  * page list and summary
  */
 
-static void show_page_range(unsigned long offset, uint64_t flags)
+static void show_page_range(unsigned long voffset,
+			    unsigned long offset, uint64_t flags)
 {
 	static uint64_t      flags0;
 	static unsigned long voff;
@@ -281,7 +361,8 @@ static void show_page_range(unsigned long offset, uint64_t flags)
 	count  = 1;
 }
 
-static void show_page(unsigned long offset, uint64_t flags)
+static void show_page(unsigned long voffset,
+		      unsigned long offset, uint64_t flags)
 {
 	if (opt_pid)
 		printf("%lx\t", voffset);
@@ -362,6 +443,62 @@ static uint64_t well_known_flags(uint64_t flags)
 	return flags;
 }
 
+static uint64_t kpageflags_flags(uint64_t flags)
+{
+	flags = expand_overloaded_flags(flags);
+
+	if (!opt_raw)
+		flags = well_known_flags(flags);
+
+	return flags;
+}
+
+/*
+ * page actions
+ */
+
+static void prepare_hwpoison_fd(void)
+{
+	char buf[100];
+
+	if (opt_hwpoison && !hwpoison_inject_fd) {
+		sprintf(buf, "%s/corrupt-pfn", hwpoison_debug_fs);
+		hwpoison_inject_fd = checked_open(buf, O_WRONLY);
+	}
+
+	if (opt_unpoison && !hwpoison_forget_fd) {
+		sprintf(buf, "%s/renew-pfn", hwpoison_debug_fs);
+		hwpoison_forget_fd = checked_open(buf, O_WRONLY);
+	}
+}
+
+static int hwpoison_page(unsigned long offset)
+{
+	char buf[100];
+	int len;
+
+	len = sprintf(buf, "0x%lx\n", offset);
+	len = write(hwpoison_inject_fd, buf, len);
+	if (len < 0) {
+		perror("hwpoison inject");
+		return len;
+	}
+	return 0;
+}
+
+static int unpoison_page(unsigned long offset)
+{
+	char buf[100];
+	int len;
+
+	len = sprintf(buf, "0x%lx\n", offset);
+	len = write(hwpoison_forget_fd, buf, len);
+	if (len < 0) {
+		perror("hwpoison forget");
+		return len;
+	}
+	return 0;
+}
 
 /*
  * page frame walker
@@ -394,104 +531,83 @@ static int hash_slot(uint64_t flags)
 	exit(EXIT_FAILURE);
 }
 
-static void add_page(unsigned long offset, uint64_t flags)
+static void add_page(unsigned long voffset,
+		     unsigned long offset, uint64_t flags)
 {
-	flags = expand_overloaded_flags(flags);
-
-	if (!opt_raw)
-		flags = well_known_flags(flags);
+	flags = kpageflags_flags(flags);
 
 	if (!bit_mask_ok(flags))
 		return;
 
+	if (opt_hwpoison)
+		hwpoison_page(offset);
+	if (opt_unpoison)
+		unpoison_page(offset);
+
 	if (opt_list == 1)
-		show_page_range(offset, flags);
+		show_page_range(voffset, offset, flags);
 	else if (opt_list == 2)
-		show_page(offset, flags);
+		show_page(voffset, offset, flags);
 
 	nr_pages[hash_slot(flags)]++;
 	total_pages++;
 }
 
-static void walk_pfn(unsigned long index, unsigned long count)
+#define KPAGEFLAGS_BATCH	(64 << 10)	/* 64k pages */
+static void walk_pfn(unsigned long voffset,
+		     unsigned long index,
+		     unsigned long count)
 {
+	uint64_t buf[KPAGEFLAGS_BATCH];
 	unsigned long batch;
-	unsigned long n;
+	unsigned long pages;
 	unsigned long i;
 
-	if (index > ULONG_MAX / KPF_BYTES)
-		fatal("index overflow: %lu\n", index);
-
-	lseek(kpageflags_fd, index * KPF_BYTES, SEEK_SET);
-
 	while (count) {
-		uint64_t kpageflags_buf[KPF_BYTES * PAGES_BATCH];
-
-		batch = min_t(unsigned long, count, PAGES_BATCH);
-		n = read(kpageflags_fd, kpageflags_buf, batch * KPF_BYTES);
-		if (n == 0)
+		batch = min_t(unsigned long, count, KPAGEFLAGS_BATCH);
+		pages = kpageflags_read(buf, index, batch);
+		if (pages == 0)
 			break;
-		if (n < 0) {
-			perror(PROC_KPAGEFLAGS);
-			exit(EXIT_FAILURE);
-		}
 
-		if (n % KPF_BYTES != 0)
-			fatal("partial read: %lu bytes\n", n);
-		n = n / KPF_BYTES;
+		for (i = 0; i < pages; i++)
+			add_page(voffset + i, index + i, buf[i]);
 
-		for (i = 0; i < n; i++)
-			add_page(index + i, kpageflags_buf[i]);
-
-		index += batch;
-		count -= batch;
+		index += pages;
+		count -= pages;
 	}
 }
 
-
-#define PAGEMAP_BATCH	4096
-static unsigned long task_pfn(unsigned long pgoff)
+#define PAGEMAP_BATCH	(64 << 10)
+static void walk_vma(unsigned long index, unsigned long count)
 {
-	static uint64_t buf[PAGEMAP_BATCH];
-	static unsigned long start;
-	static long count;
-	uint64_t pfn;
+	uint64_t buf[PAGEMAP_BATCH];
+	unsigned long batch;
+	unsigned long pages;
+	unsigned long pfn;
+	unsigned long i;
 
-	if (pgoff < start || pgoff >= start + count) {
-		if (lseek64(pagemap_fd,
-			    (uint64_t)pgoff * PM_ENTRY_BYTES,
-			    SEEK_SET) < 0) {
-			perror("pagemap seek");
-			exit(EXIT_FAILURE);
-		}
-		count = read(pagemap_fd, buf, sizeof(buf));
-		if (count == 0)
-			return 0;
-		if (count < 0) {
-			perror("pagemap read");
-			exit(EXIT_FAILURE);
-		}
-		if (count % PM_ENTRY_BYTES) {
-			fatal("pagemap read not aligned.\n");
-			exit(EXIT_FAILURE);
-		}
-		count /= PM_ENTRY_BYTES;
-		start = pgoff;
-	}
+	while (count) {
+		batch = min_t(unsigned long, count, PAGEMAP_BATCH);
+		pages = pagemap_read(buf, index, batch);
+		if (pages == 0)
+			break;
 
-	pfn = buf[pgoff - start];
-	if (pfn & PM_PRESENT)
-		pfn = PM_PFRAME(pfn);
-	else
-		pfn = 0;
+		for (i = 0; i < pages; i++) {
+			pfn = pagemap_pfn(buf[i]);
+			if (pfn)
+				walk_pfn(index + i, pfn, 1);
+		}
 
-	return pfn;
+		index += pages;
+		count -= pages;
+	}
 }
 
 static void walk_task(unsigned long index, unsigned long count)
 {
-	int i = 0;
 	const unsigned long end = index + count;
+	unsigned long start;
+	int i = 0;
 
 	while (index < end) {
 
@@ -501,15 +617,11 @@ static void walk_task(unsigned long index, unsigned long count)
 		if (pg_start[i] >= end)
 			return;
 
-		voffset = max_t(unsigned long, pg_start[i], index);
-		index   = min_t(unsigned long, pg_end[i], end);
+		start = max_t(unsigned long, pg_start[i], index);
+		index = min_t(unsigned long, pg_end[i], end);
 
-		assert(voffset < index);
-		for (; voffset < index; voffset++) {
-			unsigned long pfn = task_pfn(voffset);
-			if (pfn)
-				walk_pfn(pfn, 1);
-		}
+		assert(start < index);
+		walk_vma(start, index - start);
 	}
 }
 
@@ -527,18 +639,14 @@ static void walk_addr_ranges(void)
 {
 	int i;
 
-	kpageflags_fd = open(PROC_KPAGEFLAGS, O_RDONLY);
-	if (kpageflags_fd < 0) {
-		perror(PROC_KPAGEFLAGS);
-		exit(EXIT_FAILURE);
-	}
+	kpageflags_fd = checked_open(PROC_KPAGEFLAGS, O_RDONLY);
 
 	if (!nr_addr_ranges)
 		add_addr_range(0, ULONG_MAX);
 
 	for (i = 0; i < nr_addr_ranges; i++)
 		if (!opt_pid)
-			walk_pfn(opt_offset[i], opt_size[i]);
+			walk_pfn(0, opt_offset[i], opt_size[i]);
 		else
 			walk_task(opt_offset[i], opt_size[i]);
 
@@ -575,6 +683,8 @@ static void usage(void)
 "            -l|--list                 Show page details in ranges\n"
 "            -L|--list-each            Show page details one by one\n"
 "            -N|--no-summary           Don't show summay info\n"
+"            -X|--hwpoison             hwpoison pages\n"
+"            -x|--unpoison             unpoison pages\n"
 "            -h|--help                 Show this usage message\n"
 "addr-spec:\n"
 "            N                         one page at offset N (unit: pages)\n"
@@ -624,11 +734,7 @@ static void parse_pid(const char *str)
 	opt_pid = parse_number(str);
 
 	sprintf(buf, "/proc/%d/pagemap", opt_pid);
-	pagemap_fd = open(buf, O_RDONLY);
-	if (pagemap_fd < 0) {
-		perror(buf);
-		exit(EXIT_FAILURE);
-	}
+	pagemap_fd = checked_open(buf, O_RDONLY);
 
 	sprintf(buf, "/proc/%d/maps", opt_pid);
 	file = fopen(buf, "r");
@@ -788,6 +894,8 @@ static struct option opts[] = {
 	{ "list"      , 0, NULL, 'l' },
 	{ "list-each" , 0, NULL, 'L' },
 	{ "no-summary", 0, NULL, 'N' },
+	{ "hwpoison"  , 0, NULL, 'X' },
+	{ "unpoison"  , 0, NULL, 'x' },
 	{ "help"      , 0, NULL, 'h' },
 	{ NULL        , 0, NULL, 0 }
 };
@@ -799,7 +907,7 @@ int main(int argc, char *argv[])
 	page_size = getpagesize();
 
 	while ((c = getopt_long(argc, argv,
-				"rp:f:a:b:lLNh", opts, NULL)) != -1) {
+				"rp:f:a:b:lLNXxh", opts, NULL)) != -1) {
 		switch (c) {
 		case 'r':
 			opt_raw = 1;
@@ -825,6 +933,14 @@ int main(int argc, char *argv[])
 		case 'N':
 			opt_no_summary = 1;
 			break;
+		case 'X':
+			opt_hwpoison = 1;
+			prepare_hwpoison_fd();
+			break;
+		case 'x':
+			opt_unpoison = 1;
+			prepare_hwpoison_fd();
+			break;
 		case 'h':
 			usage();
 			exit(0);
@@ -844,7 +960,7 @@ int main(int argc, char *argv[])
 	walk_addr_ranges();
 
 	if (opt_list == 1)
-		show_page_range(0, 0);  /* drain the buffer */
+		show_page_range(0, 0, 0);  /* drain the buffer */
 
 	if (opt_no_summary)
 		return 0;
diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt
index 600a304a828cb..df09b9650a811 100644
--- a/Documentation/vm/pagemap.txt
+++ b/Documentation/vm/pagemap.txt
@@ -57,7 +57,9 @@ There are three components to pagemap:
     16. COMPOUND_TAIL
     16. HUGE
     18. UNEVICTABLE
+    19. HWPOISON
     20. NOPAGE
+    21. KSM
 
 Short descriptions to the page flags:
 
@@ -86,9 +88,15 @@ Short descriptions to the page flags:
 17. HUGE
     this is an integral part of a HugeTLB page
 
+19. HWPOISON
+    hardware detected memory corruption on this page: don't touch the data!
+
 20. NOPAGE
     no page frame exists at the requested address
 
+21. KSM
+    identical memory pages dynamically shared between one or more processes
+
     [IO related page flags]
  1. ERROR     IO error occurred
  3. UPTODATE  page has up-to-date data