Merge branch 'master' of /repos/git/linux-2.6

Conflicts:
	net/ipv4/netfilter/nf_nat_core.c
	net/netfilter/nf_conntrack_core.c
	net/netfilter/nf_conntrack_netlink.c

Signed-off-by: Patrick McHardy <kaber@trash.net>

.gitignore

@@ -22,6 +22,7 @@
 *.lst
 *.symtypes
 *.order
+modules.builtin
 *.elf
 *.bin
 *.gz
@@ -35,7 +36,9 @@
 #
 tags
 TAGS
+linux
 vmlinux
+vmlinuz
 System.map
 Module.markers
 Module.symvers
@@ -45,14 +48,8 @@ Module.symvers
 #
 # Generated include files
 #
-include/asm
-include/asm-*/asm-offsets.h
 include/config
-include/linux/autoconf.h
-include/linux/compile.h
 include/linux/version.h
-include/linux/utsrelease.h
-include/linux/bounds.h
 include/generated
 
 # stgit generated dirs

Documentation/ABI/stable/sysfs-devices-node

@@ -0,0 +1,7 @@
+What:		/sys/devices/system/node/nodeX
+Date:		October 2002
+Contact:	Linux Memory Management list <linux-mm@kvack.org>
+Description:
+		When CONFIG_NUMA is enabled, this is a directory containing
+		information on node X such as what CPUs are local to the
+		node.

Documentation/ABI/testing/ima_policy

@@ -20,7 +20,7 @@ Description:
 			lsm:	[[subj_user=] [subj_role=] [subj_type=]
 				 [obj_user=] [obj_role=] [obj_type=]]
 
-		base: 	func:= [BPRM_CHECK][FILE_MMAP][INODE_PERMISSION]
+		base: 	func:= [BPRM_CHECK][FILE_MMAP][FILE_CHECK]
 			mask:= [MAY_READ] [MAY_WRITE] [MAY_APPEND] [MAY_EXEC]
 			fsmagic:= hex value
 			uid:= decimal value
@@ -40,11 +40,11 @@ Description:
 
 			measure func=BPRM_CHECK
 			measure func=FILE_MMAP mask=MAY_EXEC
-			measure func=INODE_PERM mask=MAY_READ uid=0
+			measure func=FILE_CHECK mask=MAY_READ uid=0
 
 		The default policy measures all executables in bprm_check,
 		all files mmapped executable in file_mmap, and all files
-		open for read by root in inode_permission.
+		open for read by root in do_filp_open.
 
 		Examples of LSM specific definitions:
 
@@ -54,8 +54,8 @@ Description:
 
 			dont_measure obj_type=var_log_t
 			dont_measure obj_type=auditd_log_t
-			measure subj_user=system_u func=INODE_PERM mask=MAY_READ
-			measure subj_role=system_r func=INODE_PERM mask=MAY_READ
+			measure subj_user=system_u func=FILE_CHECK mask=MAY_READ
+			measure subj_role=system_r func=FILE_CHECK mask=MAY_READ
 
 		Smack:
-			measure subj_user=_ func=INODE_PERM mask=MAY_READ
+			measure subj_user=_ func=FILE_CHECK mask=MAY_READ

Documentation/ABI/testing/sysfs-block

@@ -128,3 +128,17 @@ Description:
 		preferred request size for workloads where sustained
 		throughput is desired.  If no optimal I/O size is
 		reported this file contains 0.
+
+What:		/sys/block/<disk>/queue/nomerges
+Date:		January 2010
+Contact:
+Description:
+		Standard I/O elevator operations include attempts to
+		merge contiguous I/Os. For known random I/O loads these
+		attempts will always fail and result in extra cycles
+		being spent in the kernel. This allows one to turn off
+		this behavior on one of two ways: When set to 1, complex
+		merge checks are disabled, but the simple one-shot merges
+		with the previous I/O request are enabled. When set to 2,
+		all merge tries are disabled. The default value is 0 -
+		which enables all types of merge tries.

Documentation/ABI/testing/sysfs-bus-usb

@@ -21,25 +21,27 @@ Contact:	Alan Stern <stern@rowland.harvard.edu>
 Description:
 		Each USB device directory will contain a file named
 		power/level.  This file holds a power-level setting for
-		the device, one of "on", "auto", or "suspend".
+		the device, either "on" or "auto".
 
 		"on" means that the device is not allowed to autosuspend,
 		although normal suspends for system sleep will still
 		be honored.  "auto" means the device will autosuspend
 		and autoresume in the usual manner, according to the
-		capabilities of its driver.  "suspend" means the device
-		is forced into a suspended state and it will not autoresume
-		in response to I/O requests.  However remote-wakeup requests
-		from the device may still be enabled (the remote-wakeup
-		setting is controlled separately by the power/wakeup
-		attribute).
+		capabilities of its driver.
 
 		During normal use, devices should be left in the "auto"
-		level.  The other levels are meant for administrative uses.
+		level.  The "on" level is meant for administrative uses.
 		If you want to suspend a device immediately but leave it
 		free to wake up in response to I/O requests, you should
 		write "0" to power/autosuspend.
 
+		Device not capable of proper suspend and resume should be
+		left in the "on" level.  Although the USB spec requires
+		devices to support suspend/resume, many of them do not.
+		In fact so many don't that by default, the USB core
+		initializes all non-hub devices in the "on" level.  Some
+		drivers may change this setting when they are bound.
+
 What:		/sys/bus/usb/devices/.../power/persist
 Date:		May 2007
 KernelVersion:	2.6.23
@@ -157,3 +159,14 @@ Description:
 		device.  This is useful to ensure auto probing won't
 		match the driver to the device.  For example:
 		# echo "046d c315" > /sys/bus/usb/drivers/foo/remove_id
+
+What:		/sys/bus/usb/device/.../avoid_reset
+Date:		December 2009
+Contact:	Oliver Neukum <oliver@neukum.org>
+Description:
+		Writing 1 to this file tells the kernel that this
+		device will morph into another mode when it is reset.
+		Drivers will not use reset for error handling for
+		such devices.
+Users:
+		usb_modeswitch

Documentation/ABI/testing/sysfs-devices-memory

@@ -60,6 +60,19 @@ Description:
 Users:		hotplug memory remove tools
 		https://w3.opensource.ibm.com/projects/powerpc-utils/
 
+
+What:		/sys/devices/system/memoryX/nodeY
+Date:		October 2009
+Contact:	Linux Memory Management list <linux-mm@kvack.org>
+Description:
+		When CONFIG_NUMA is enabled, a symbolic link that
+		points to the corresponding NUMA node directory.
+
+		For example, the following symbolic link is created for
+		memory section 9 on node0:
+		/sys/devices/system/memory/memory9/node0 -> ../../node/node0
+
+
 What:		/sys/devices/system/node/nodeX/memoryY
 Date:		September 2008
 Contact:	Gary Hade <garyhade@us.ibm.com>
@@ -70,4 +83,3 @@ Description:
 		memory section directory.  For example, the following symbolic
 		link is created for memory section 9 on node0.
 		/sys/devices/system/node/node0/memory9 -> ../../memory/memory9
-

Documentation/ABI/testing/sysfs-devices-power

@@ -0,0 +1,79 @@
+What:		/sys/devices/.../power/
+Date:		January 2009
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../power directory contains attributes
+		allowing the user space to check and modify some power
+		management related properties of given device.
+
+What:		/sys/devices/.../power/wakeup
+Date:		January 2009
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../power/wakeup attribute allows the user
+		space to check if the device is enabled to wake up the system
+		from sleep states, such as the memory sleep state (suspend to
+		RAM) and hibernation (suspend to disk), and to enable or disable
+		it to do that as desired.
+
+		Some devices support "wakeup" events, which are hardware signals
+		used to activate the system from a sleep state.  Such devices
+		have one of the following two values for the sysfs power/wakeup
+		file:
+
+		+ "enabled\n" to issue the events;
+		+ "disabled\n" not to do so;
+
+		In that cases the user space can change the setting represented
+		by the contents of this file by writing either "enabled", or
+		"disabled" to it.
+
+		For the devices that are not capable of generating system wakeup
+		events this file contains "\n".  In that cases the user space
+		cannot modify the contents of this file and the device cannot be
+		enabled to wake up the system.
+
+What:		/sys/devices/.../power/control
+Date:		January 2009
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../power/control attribute allows the user
+		space to control the run-time power management of the device.
+
+		All devices have one of the following two values for the
+		power/control file:
+
+		+ "auto\n" to allow the device to be power managed at run time;
+		+ "on\n" to prevent the device from being power managed;
+
+		The default for all devices is "auto", which means that they may
+		be subject to automatic power management, depending on their
+		drivers.  Changing this attribute to "on" prevents the driver
+		from power managing the device at run time.  Doing that while
+		the device is suspended causes it to be woken up.
+
+What:		/sys/devices/.../power/async
+Date:		January 2009
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../async attribute allows the user space to
+		enable or diasble the device's suspend and resume callbacks to
+		be executed asynchronously (ie. in separate threads, in parallel
+		with the main suspend/resume thread) during system-wide power
+		transitions (eg. suspend to RAM, hibernation).
+
+		All devices have one of the following two values for the
+		power/async file:
+
+		+ "enabled\n" to permit the asynchronous suspend/resume;
+		+ "disabled\n" to forbid it;
+
+		The value of this attribute may be changed by writing either
+		"enabled", or "disabled" to it.
+
+		It generally is unsafe to permit the asynchronous suspend/resume
+		of a device unless it is certain that all of the PM dependencies
+		of the device are known to the PM core.  However, for some
+		devices this attribute is set to "enabled" by bus type code or
+		device drivers and in that cases it should be safe to leave the
+		default value.

Documentation/ABI/testing/sysfs-devices-system-cpu

@@ -62,6 +62,35 @@ Description:	CPU topology files that describe kernel limits related to
 		See Documentation/cputopology.txt for more information.
 
 
+What:		/sys/devices/system/cpu/probe
+		/sys/devices/system/cpu/release
+Date:		November 2009
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Dynamic addition and removal of CPU's.  This is not hotplug
+		removal, this is meant complete removal/addition of the CPU
+		from the system.
+
+		probe: writes to this file will dynamically add a CPU to the
+		system.  Information written to the file to add CPU's is
+		architecture specific.
+
+		release: writes to this file dynamically remove a CPU from
+		the system.  Information writtento the file to remove CPU's
+		is architecture specific.
+
+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#/node
 Date:		October 2009

Documentation/ABI/testing/sysfs-kernel-slab

@@ -45,8 +45,9 @@ KernelVersion:	2.6.25
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The alloc_fastpath file is read-only and specifies how many
-		objects have been allocated using the fast path.
+		The alloc_fastpath file shows how many objects have been
+		allocated using the fast path.  It can be written to clear the
+		current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/alloc_from_partial
@@ -55,9 +56,10 @@ KernelVersion:	2.6.25
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The alloc_from_partial file is read-only and specifies how
-		many times a cpu slab has been full and it has been refilled
-		by using a slab from the list of partially used slabs.
+		The alloc_from_partial file shows how many times a cpu slab has
+		been full and it has been refilled by using a slab from the list
+		of partially used slabs.  It can be written to clear the current
+		count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/alloc_refill
@@ -66,9 +68,9 @@ KernelVersion:	2.6.25
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The alloc_refill file is read-only and specifies how many
-		times the per-cpu freelist was empty but there were objects
-		available as the result of remote cpu frees.
+		The alloc_refill file shows how many times the per-cpu freelist
+		was empty but there were objects available as the result of
+		remote cpu frees.  It can be written to clear the current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/alloc_slab
@@ -77,8 +79,9 @@ KernelVersion:	2.6.25
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The alloc_slab file is read-only and specifies how many times
-		a new slab had to be allocated from the page allocator.
+		The alloc_slab file is shows how many times a new slab had to
+		be allocated from the page allocator.  It can be written to
+		clear the current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/alloc_slowpath
@@ -87,9 +90,10 @@ KernelVersion:	2.6.25
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The alloc_slowpath file is read-only and specifies how many
-		objects have been allocated using the slow path because of a
-		refill or allocation from a partial or new slab.
+		The alloc_slowpath file shows how many objects have been
+		allocated using the slow path because of a refill or
+		allocation from a partial or new slab.  It can be written to
+		clear the current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/cache_dma
@@ -117,10 +121,11 @@ KernelVersion:	2.6.31
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The file cpuslab_flush is read-only and specifies how many
-		times a cache's cpu slabs have been flushed as the result of
-		destroying or shrinking a cache, a cpu going offline, or as
-		the result of forcing an allocation from a certain node.
+		The file cpuslab_flush shows how many times a cache's cpu slabs
+		have been flushed as the result of destroying or shrinking a
+		cache, a cpu going offline, or as the result of forcing an
+		allocation from a certain node.  It can be written to clear the
+		current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/ctor
@@ -139,8 +144,8 @@ KernelVersion:	2.6.25
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The file deactivate_empty is read-only and specifies how many
-		times an empty cpu slab was deactivated.
+		The deactivate_empty file shows how many times an empty cpu slab
+		was deactivated.  It can be written to clear the current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/deactivate_full
@@ -149,8 +154,8 @@ KernelVersion:	2.6.25
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The file deactivate_full is read-only and specifies how many
-		times a full cpu slab was deactivated.
+		The deactivate_full file shows how many times a full cpu slab
+		was deactivated.  It can be written to clear the current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/deactivate_remote_frees
@@ -159,9 +164,9 @@ KernelVersion:	2.6.25
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The file deactivate_remote_frees is read-only and specifies how
-		many times a cpu slab has been deactivated and contained free
-		objects that were freed remotely.
+		The deactivate_remote_frees file shows how many times a cpu slab
+		has been deactivated and contained free objects that were freed
+		remotely.  It can be written to clear the current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/deactivate_to_head
@@ -170,9 +175,9 @@ KernelVersion:	2.6.25
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The file deactivate_to_head is read-only and specifies how
-		many times a partial cpu slab was deactivated and added to the
-		head of its node's partial list.
+		The deactivate_to_head file shows how many times a partial cpu
+		slab was deactivated and added to the head of its node's partial
+		list.  It can be written to clear the current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/deactivate_to_tail
@@ -181,9 +186,9 @@ KernelVersion:	2.6.25
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The file deactivate_to_tail is read-only and specifies how
-		many times a partial cpu slab was deactivated and added to the
-		tail of its node's partial list.
+		The deactivate_to_tail file shows how many times a partial cpu
+		slab was deactivated and added to the tail of its node's partial
+		list.  It can be written to clear the current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/destroy_by_rcu
@@ -201,9 +206,9 @@ KernelVersion:	2.6.25
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The file free_add_partial is read-only and specifies how many
-		times an object has been freed in a full slab so that it had to
-		added to its node's partial list.
+		The free_add_partial file shows how many times an object has
+		been freed in a full slab so that it had to added to its node's
+		partial list.  It can be written to clear the current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/free_calls
@@ -222,9 +227,9 @@ KernelVersion:	2.6.25
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The free_fastpath file is read-only and specifies how many
-		objects have been freed using the fast path because it was an
-		object from the cpu slab.
+		The free_fastpath file shows how many objects have been freed
+		using the fast path because it was an object from the cpu slab.
+		It can be written to clear the current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/free_frozen
@@ -233,9 +238,9 @@ KernelVersion:	2.6.25
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The free_frozen file is read-only and specifies how many
-		objects have been freed to a frozen slab (i.e. a remote cpu
-		slab).
+		The free_frozen file shows how many objects have been freed to
+		a frozen slab (i.e. a remote cpu slab).  It can be written to
+		clear the current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/free_remove_partial
@@ -244,9 +249,10 @@ KernelVersion:	2.6.25
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The file free_remove_partial is read-only and specifies how
-		many times an object has been freed to a now-empty slab so
-		that it had to be removed from its node's partial list.
+		The free_remove_partial file shows how many times an object has
+		been freed to a now-empty slab so that it had to be removed from
+		its node's partial list.  It can be written to clear the current
+		count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/free_slab
@@ -255,8 +261,9 @@ KernelVersion:	2.6.25
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The free_slab file is read-only and specifies how many times an
-		empty slab has been freed back to the page allocator.
+		The free_slab file shows how many times an empty slab has been
+		freed back to the page allocator.  It can be written to clear
+		the current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/free_slowpath
@@ -265,9 +272,9 @@ KernelVersion:	2.6.25
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The free_slowpath file is read-only and specifies how many
-		objects have been freed using the slow path (i.e. to a full or
-		partial slab).
+		The free_slowpath file shows how many objects have been freed
+		using the slow path (i.e. to a full or partial slab).  It can
+		be written to clear the current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/hwcache_align
@@ -346,10 +353,10 @@ KernelVersion:	2.6.26
 Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
 		Christoph Lameter <cl@linux-foundation.org>
 Description:
-		The file order_fallback is read-only and specifies how many
-		times an allocation of a new slab has not been possible at the
-		cache's order and instead fallen back to its minimum possible
-		order.
+		The order_fallback file shows how many times an allocation of a
+		new slab has not been possible at the cache's order and instead
+		fallen back to its minimum possible order.  It can be written to
+		clear the current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
 What:		/sys/kernel/slab/cache/partial

Documentation/ABI/testing/sysfs-memory-page-offline

@@ -0,0 +1,44 @@
+What:		/sys/devices/system/memory/soft_offline_page
+Date:		Sep 2009
+KernelVersion:	2.6.33
+Contact:	andi@firstfloor.org
+Description:
+		Soft-offline the memory page containing the physical address
+		written into this file. Input is a hex number specifying the
+		physical address of the page. The kernel will then attempt
+		to soft-offline it, by moving the contents elsewhere or
+		dropping it if possible. The kernel will then be placed
+		on the bad page list and never be reused.
+
+		The offlining is done in kernel specific granuality.
+		Normally it's the base page size of the kernel, but
+		this might change.
+
+		The page must be still accessible, not poisoned. The
+		kernel will never kill anything for this, but rather
+		fail the offline.  Return value is the size of the
+		number, or a error when the offlining failed.  Reading
+		the file is not allowed.
+
+What:		/sys/devices/system/memory/hard_offline_page
+Date:		Sep 2009
+KernelVersion:	2.6.33
+Contact:	andi@firstfloor.org
+Description:
+		Hard-offline the memory page containing the physical
+		address written into this file. Input is a hex number
+		specifying the physical address of the page. The
+		kernel will then attempt to hard-offline the page, by
+		trying to drop the page or killing any owner or
+		triggering IO errors if needed.  Note this may kill
+		any processes owning the page. The kernel will avoid
+		to access this page assuming it's poisoned by the
+		hardware.
+
+		The offlining is done in kernel specific granuality.
+		Normally it's the base page size of the kernel, but
+		this might change.
+
+		Return value is the size of the number, or a error when
+		the offlining failed.
+		Reading the file is not allowed.

Documentation/ABI/testing/sysfs-platform-asus-laptop

@@ -1,4 +1,4 @@
-What:		/sys/devices/platform/asus-laptop/display
+What:		/sys/devices/platform/asus_laptop/display
 Date:		January 2007
 KernelVersion:	2.6.20
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
@@ -13,7 +13,7 @@ Description:
 		Ex: - 0 (0000b) means no display
 		    - 3 (0011b) CRT+LCD.
 
-What:		/sys/devices/platform/asus-laptop/gps
+What:		/sys/devices/platform/asus_laptop/gps
 Date:		January 2007
 KernelVersion:	2.6.20
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
@@ -21,7 +21,7 @@ Description:
 		Control the gps device. 1 means on, 0 means off.
 Users:		Lapsus
 
-What:		/sys/devices/platform/asus-laptop/ledd
+What:		/sys/devices/platform/asus_laptop/ledd
 Date:		January 2007
 KernelVersion:	2.6.20
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
@@ -29,11 +29,11 @@ Description:
 		Some models like the W1N have a LED display that can be
 		used to display several informations.
 		To control the LED display, use the following :
-		    echo 0x0T000DDD > /sys/devices/platform/asus-laptop/
+		    echo 0x0T000DDD > /sys/devices/platform/asus_laptop/
 		where T control the 3 letters display, and DDD the 3 digits display.
 		The DDD table can be found in Documentation/laptops/asus-laptop.txt
 
-What:		/sys/devices/platform/asus-laptop/bluetooth
+What:		/sys/devices/platform/asus_laptop/bluetooth
 Date:		January 2007
 KernelVersion:	2.6.20
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
@@ -42,7 +42,7 @@ Description:
 		This may control the led, the device or both.
 Users:		Lapsus
 
-What:		/sys/devices/platform/asus-laptop/wlan
+What:		/sys/devices/platform/asus_laptop/wlan
 Date:		January 2007
 KernelVersion:	2.6.20
 Contact:	"Corentin Chary" <corentincj@iksaif.net>

Documentation/ABI/testing/sysfs-platform-eeepc-laptop

@@ -1,4 +1,4 @@
-What:		/sys/devices/platform/eeepc-laptop/disp
+What:		/sys/devices/platform/eeepc/disp
 Date:		May 2008
 KernelVersion:	2.6.26
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
@@ -9,21 +9,21 @@ Description:
 		- 3 = LCD+CRT
 		If you run X11, you should use xrandr instead.
 
-What:		/sys/devices/platform/eeepc-laptop/camera
+What:		/sys/devices/platform/eeepc/camera
 Date:		May 2008
 KernelVersion:	2.6.26
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
 Description:
 		Control the camera. 1 means on, 0 means off.
 
-What:		/sys/devices/platform/eeepc-laptop/cardr
+What:		/sys/devices/platform/eeepc/cardr
 Date:		May 2008
 KernelVersion:	2.6.26
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
 Description:
 		Control the card reader. 1 means on, 0 means off.
 
-What:		/sys/devices/platform/eeepc-laptop/cpufv
+What:		/sys/devices/platform/eeepc/cpufv
 Date:		Jun 2009
 KernelVersion:	2.6.31
 Contact:	"Corentin Chary" <corentincj@iksaif.net>
@@ -42,7 +42,7 @@ Description:
 		    `------------ Availables modes
 		For example, 0x301 means: mode 1 selected, 3 available modes.
 
-What:		/sys/devices/platform/eeepc-laptop/available_cpufv
+What:		/sys/devices/platform/eeepc/available_cpufv
 Date:		Jun 2009
 KernelVersion:	2.6.31
 Contact:	"Corentin Chary" <corentincj@iksaif.net>

Documentation/ABI/testing/sysfs-power

@@ -101,3 +101,16 @@ Description:
 
 		CAUTION: Using it will cause your machine's real-time (CMOS)
 		clock to be set to a random invalid time after a resume.
+
+What:		/sys/power/pm_async
+Date:		January 2009
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/power/pm_async file controls the switch allowing the
+		user space to enable or disable asynchronous suspend and resume
+		of devices.  If enabled, this feature will cause some device
+		drivers' suspend and resume callbacks to be executed in parallel
+		with each other and with the main suspend thread.  It is enabled
+		if this file contains "1", which is the default.  It may be
+		disabled by writing "0" to this file, in which case all devices
+		will be suspended and resumed synchronously.

Documentation/DocBook/Makefile

@@ -8,7 +8,7 @@
 
 DOCBOOKS := z8530book.xml mcabook.xml device-drivers.xml \
 	    kernel-hacking.xml kernel-locking.xml deviceiobook.xml \
-	    procfs-guide.xml writing_usb_driver.xml networking.xml \
+	    writing_usb_driver.xml networking.xml \
 	    kernel-api.xml filesystems.xml lsm.xml usb.xml kgdb.xml \
 	    gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
 	    genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
@@ -32,10 +32,10 @@ PS_METHOD	= $(prefer-db2x)
 
 ###
 # The targets that may be used.
-PHONY += xmldocs sgmldocs psdocs pdfdocs htmldocs mandocs installmandocs cleandocs media
+PHONY += xmldocs sgmldocs psdocs pdfdocs htmldocs mandocs installmandocs cleandocs xmldoclinks
 
 BOOKS := $(addprefix $(obj)/,$(DOCBOOKS))
-xmldocs: $(BOOKS)
+xmldocs: $(BOOKS) xmldoclinks
 sgmldocs: xmldocs
 
 PS := $(patsubst %.xml, %.ps, $(BOOKS))
@@ -45,15 +45,24 @@ PDF := $(patsubst %.xml, %.pdf, $(BOOKS))
 pdfdocs: $(PDF)
 
 HTML := $(sort $(patsubst %.xml, %.html, $(BOOKS)))
-htmldocs: media $(HTML)
+htmldocs: $(HTML)
 	$(call build_main_index)
+	$(call build_images)
 
 MAN := $(patsubst %.xml, %.9, $(BOOKS))
 mandocs: $(MAN)
 
-media:
-	mkdir -p $(srctree)/Documentation/DocBook/media/
-	cp $(srctree)/Documentation/DocBook/dvb/*.png $(srctree)/Documentation/DocBook/v4l/*.gif $(srctree)/Documentation/DocBook/media/
+build_images = mkdir -p $(objtree)/Documentation/DocBook/media/ && \
+	       cp $(srctree)/Documentation/DocBook/dvb/*.png $(srctree)/Documentation/DocBook/v4l/*.gif $(objtree)/Documentation/DocBook/media/
+
+xmldoclinks:
+ifneq ($(objtree),$(srctree))
+	for dep in dvb media-entities.tmpl media-indices.tmpl v4l; do \
+		rm -f $(objtree)/Documentation/DocBook/$$dep \
+		&& ln -s $(srctree)/Documentation/DocBook/$$dep $(objtree)/Documentation/DocBook/ \
+		|| exit; \
+	done
+endif
 
 installmandocs: mandocs
 	mkdir -p /usr/local/man/man9/
@@ -65,7 +74,7 @@ KERNELDOC = $(srctree)/scripts/kernel-doc
 DOCPROC   = $(objtree)/scripts/basic/docproc
 
 XMLTOFLAGS = -m $(srctree)/Documentation/DocBook/stylesheet.xsl
-#XMLTOFLAGS += --skip-validation
+XMLTOFLAGS += --skip-validation
 
 ###
 # DOCPROC is used for two purposes:
@@ -101,17 +110,6 @@ endif
 # Changes in kernel-doc force a rebuild of all documentation
 $(BOOKS): $(KERNELDOC)
 
-###
-# procfs guide uses a .c file as example code.
-# This requires an explicit dependency
-C-procfs-example = procfs_example.xml
-C-procfs-example2 = $(addprefix $(obj)/,$(C-procfs-example))
-$(obj)/procfs-guide.xml: $(C-procfs-example2)
-
-# List of programs to build
-##oops, this is a kernel module::hostprogs-y := procfs_example
-obj-m += procfs_example.o
-
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
 
@@ -238,7 +236,7 @@ clean-files := $(DOCBOOKS) \
 	$(patsubst %.xml, %.pdf,  $(DOCBOOKS)) \
 	$(patsubst %.xml, %.html, $(DOCBOOKS)) \
 	$(patsubst %.xml, %.9,    $(DOCBOOKS)) \
-	$(C-procfs-example) $(index)
+	$(index)
 
 clean-dirs := $(patsubst %.xml,%,$(DOCBOOKS)) man
 

Documentation/DocBook/device-drivers.tmpl

@@ -45,7 +45,7 @@
      </sect1>
 
      <sect1><title>Atomic and pointer manipulation</title>
-!Iarch/x86/include/asm/atomic_32.h
+!Iarch/x86/include/asm/atomic.h
 !Iarch/x86/include/asm/unaligned.h
      </sect1>
 

Documentation/DocBook/deviceiobook.tmpl

@@ -316,7 +316,7 @@ CPU B:  spin_unlock_irqrestore(&dev_lock, flags)
 
   <chapter id="pubfunctions">
      <title>Public Functions Provided</title>
-!Iarch/x86/include/asm/io_32.h
+!Iarch/x86/include/asm/io.h
 !Elib/iomap.c
   </chapter>
 

Documentation/DocBook/mac80211.tmpl

@@ -144,7 +144,7 @@ usage should require reading the full document.
         this though and the recommendation to allow only a single
         interface in STA mode at first!
       </para>
-!Finclude/net/mac80211.h ieee80211_if_init_conf
+!Finclude/net/mac80211.h ieee80211_vif
     </chapter>
 
     <chapter id="rx-tx">
@@ -234,7 +234,6 @@ usage should require reading the full document.
       <title>Multiple queues and QoS support</title>
       <para>TBD</para>
 !Finclude/net/mac80211.h ieee80211_tx_queue_params
-!Finclude/net/mac80211.h ieee80211_tx_queue_stats
     </chapter>
 
     <chapter id="AP">

Documentation/DocBook/media-entities.tmpl

@@ -23,6 +23,7 @@
 <!ENTITY VIDIOC-ENUMINPUT "<link linkend='vidioc-enuminput'><constant>VIDIOC_ENUMINPUT</constant></link>">
 <!ENTITY VIDIOC-ENUMOUTPUT "<link linkend='vidioc-enumoutput'><constant>VIDIOC_ENUMOUTPUT</constant></link>">
 <!ENTITY VIDIOC-ENUMSTD "<link linkend='vidioc-enumstd'><constant>VIDIOC_ENUMSTD</constant></link>">
+<!ENTITY VIDIOC-ENUM-DV-PRESETS "<link linkend='vidioc-enum-dv-presets'><constant>VIDIOC_ENUM_DV_PRESETS</constant></link>">
 <!ENTITY VIDIOC-ENUM-FMT "<link linkend='vidioc-enum-fmt'><constant>VIDIOC_ENUM_FMT</constant></link>">
 <!ENTITY VIDIOC-ENUM-FRAMEINTERVALS "<link linkend='vidioc-enum-frameintervals'><constant>VIDIOC_ENUM_FRAMEINTERVALS</constant></link>">
 <!ENTITY VIDIOC-ENUM-FRAMESIZES "<link linkend='vidioc-enum-framesizes'><constant>VIDIOC_ENUM_FRAMESIZES</constant></link>">
@@ -30,6 +31,8 @@
 <!ENTITY VIDIOC-G-AUDOUT "<link linkend='vidioc-g-audioout'><constant>VIDIOC_G_AUDOUT</constant></link>">
 <!ENTITY VIDIOC-G-CROP "<link linkend='vidioc-g-crop'><constant>VIDIOC_G_CROP</constant></link>">
 <!ENTITY VIDIOC-G-CTRL "<link linkend='vidioc-g-ctrl'><constant>VIDIOC_G_CTRL</constant></link>">
+<!ENTITY VIDIOC-G-DV-PRESET "<link linkend='vidioc-g-dv-preset'><constant>VIDIOC_G_DV_PRESET</constant></link>">
+<!ENTITY VIDIOC-G-DV-TIMINGS "<link linkend='vidioc-g-dv-timings'><constant>VIDIOC_G_DV_TIMINGS</constant></link>">
 <!ENTITY VIDIOC-G-ENC-INDEX "<link linkend='vidioc-g-enc-index'><constant>VIDIOC_G_ENC_INDEX</constant></link>">
 <!ENTITY VIDIOC-G-EXT-CTRLS "<link linkend='vidioc-g-ext-ctrls'><constant>VIDIOC_G_EXT_CTRLS</constant></link>">
 <!ENTITY VIDIOC-G-FBUF "<link linkend='vidioc-g-fbuf'><constant>VIDIOC_G_FBUF</constant></link>">
@@ -53,6 +56,7 @@
 <!ENTITY VIDIOC-QUERYCTRL "<link linkend='vidioc-queryctrl'><constant>VIDIOC_QUERYCTRL</constant></link>">
 <!ENTITY VIDIOC-QUERYMENU "<link linkend='vidioc-queryctrl'><constant>VIDIOC_QUERYMENU</constant></link>">
 <!ENTITY VIDIOC-QUERYSTD "<link linkend='vidioc-querystd'><constant>VIDIOC_QUERYSTD</constant></link>">
+<!ENTITY VIDIOC-QUERY-DV-PRESET "<link linkend='vidioc-query-dv-preset'><constant>VIDIOC_QUERY_DV_PRESET</constant></link>">
 <!ENTITY VIDIOC-REQBUFS "<link linkend='vidioc-reqbufs'><constant>VIDIOC_REQBUFS</constant></link>">
 <!ENTITY VIDIOC-STREAMOFF "<link linkend='vidioc-streamon'><constant>VIDIOC_STREAMOFF</constant></link>">
 <!ENTITY VIDIOC-STREAMON "<link linkend='vidioc-streamon'><constant>VIDIOC_STREAMON</constant></link>">
@@ -60,6 +64,8 @@
 <!ENTITY VIDIOC-S-AUDOUT "<link linkend='vidioc-g-audioout'><constant>VIDIOC_S_AUDOUT</constant></link>">
 <!ENTITY VIDIOC-S-CROP "<link linkend='vidioc-g-crop'><constant>VIDIOC_S_CROP</constant></link>">
 <!ENTITY VIDIOC-S-CTRL "<link linkend='vidioc-g-ctrl'><constant>VIDIOC_S_CTRL</constant></link>">
+<!ENTITY VIDIOC-S-DV-PRESET "<link linkend='vidioc-g-dv-preset'><constant>VIDIOC_S_DV_PRESET</constant></link>">
+<!ENTITY VIDIOC-S-DV-TIMINGS "<link linkend='vidioc-g-dv-timings'><constant>VIDIOC_S_DV_TIMINGS</constant></link>">
 <!ENTITY VIDIOC-S-EXT-CTRLS "<link linkend='vidioc-g-ext-ctrls'><constant>VIDIOC_S_EXT_CTRLS</constant></link>">
 <!ENTITY VIDIOC-S-FBUF "<link linkend='vidioc-g-fbuf'><constant>VIDIOC_S_FBUF</constant></link>">
 <!ENTITY VIDIOC-S-FMT "<link linkend='vidioc-g-fmt'><constant>VIDIOC_S_FMT</constant></link>">
@@ -118,6 +124,7 @@
 <!-- Structures -->
 <!ENTITY v4l2-audio "struct&nbsp;<link linkend='v4l2-audio'>v4l2_audio</link>">
 <!ENTITY v4l2-audioout "struct&nbsp;<link linkend='v4l2-audioout'>v4l2_audioout</link>">
+<!ENTITY v4l2-bt-timings "struct&nbsp;<link linkend='v4l2-bt-timings'>v4l2_bt_timings</link>">
 <!ENTITY v4l2-buffer "struct&nbsp;<link linkend='v4l2-buffer'>v4l2_buffer</link>">
 <!ENTITY v4l2-capability "struct&nbsp;<link linkend='v4l2-capability'>v4l2_capability</link>">
 <!ENTITY v4l2-captureparm "struct&nbsp;<link linkend='v4l2-captureparm'>v4l2_captureparm</link>">
@@ -128,6 +135,9 @@
 <!ENTITY v4l2-dbg-chip-ident "struct&nbsp;<link linkend='v4l2-dbg-chip-ident'>v4l2_dbg_chip_ident</link>">
 <!ENTITY v4l2-dbg-match "struct&nbsp;<link linkend='v4l2-dbg-match'>v4l2_dbg_match</link>">
 <!ENTITY v4l2-dbg-register "struct&nbsp;<link linkend='v4l2-dbg-register'>v4l2_dbg_register</link>">
+<!ENTITY v4l2-dv-enum-preset "struct&nbsp;<link linkend='v4l2-dv-enum-preset'>v4l2_dv_enum_preset</link>">
+<!ENTITY v4l2-dv-preset "struct&nbsp;<link linkend='v4l2-dv-preset'>v4l2_dv_preset</link>">
+<!ENTITY v4l2-dv-timings "struct&nbsp;<link linkend='v4l2-dv-timings'>v4l2_dv_timings</link>">
 <!ENTITY v4l2-enc-idx "struct&nbsp;<link linkend='v4l2-enc-idx'>v4l2_enc_idx</link>">
 <!ENTITY v4l2-enc-idx-entry "struct&nbsp;<link linkend='v4l2-enc-idx-entry'>v4l2_enc_idx_entry</link>">
 <!ENTITY v4l2-encoder-cmd "struct&nbsp;<link linkend='v4l2-encoder-cmd'>v4l2_encoder_cmd</link>">
@@ -243,6 +253,10 @@
 <!ENTITY sub-enumaudioout SYSTEM "v4l/vidioc-enumaudioout.xml">
 <!ENTITY sub-enuminput SYSTEM "v4l/vidioc-enuminput.xml">
 <!ENTITY sub-enumoutput SYSTEM "v4l/vidioc-enumoutput.xml">
+<!ENTITY sub-enum-dv-presets SYSTEM "v4l/vidioc-enum-dv-presets.xml">
+<!ENTITY sub-g-dv-preset SYSTEM "v4l/vidioc-g-dv-preset.xml">
+<!ENTITY sub-query-dv-preset SYSTEM "v4l/vidioc-query-dv-preset.xml">
+<!ENTITY sub-g-dv-timings SYSTEM "v4l/vidioc-g-dv-timings.xml">
 <!ENTITY sub-enumstd SYSTEM "v4l/vidioc-enumstd.xml">
 <!ENTITY sub-g-audio SYSTEM "v4l/vidioc-g-audio.xml">
 <!ENTITY sub-g-audioout SYSTEM "v4l/vidioc-g-audioout.xml">
@@ -333,6 +347,10 @@
 <!ENTITY enumaudioout SYSTEM "v4l/vidioc-enumaudioout.xml">
 <!ENTITY enuminput SYSTEM "v4l/vidioc-enuminput.xml">
 <!ENTITY enumoutput SYSTEM "v4l/vidioc-enumoutput.xml">
+<!ENTITY enum-dv-presets SYSTEM "v4l/vidioc-enum-dv-presets.xml">
+<!ENTITY g-dv-preset SYSTEM "v4l/vidioc-g-dv-preset.xml">
+<!ENTITY query-dv-preset SYSTEM "v4l/vidioc-query-dv-preset.xml">
+<!ENTITY g-dv-timings SYSTEM "v4l/vidioc-g-dv-timings.xml">
 <!ENTITY enumstd SYSTEM "v4l/vidioc-enumstd.xml">
 <!ENTITY g-audio SYSTEM "v4l/vidioc-g-audio.xml">
 <!ENTITY g-audioout SYSTEM "v4l/vidioc-g-audioout.xml">

Documentation/DocBook/media-indices.tmpl

@@ -36,6 +36,7 @@
 <indexentry><primaryie>enum&nbsp;<link linkend='v4l2-preemphasis'>v4l2_preemphasis</link></primaryie></indexentry>
 <indexentry><primaryie>struct&nbsp;<link linkend='v4l2-audio'>v4l2_audio</link></primaryie></indexentry>
 <indexentry><primaryie>struct&nbsp;<link linkend='v4l2-audioout'>v4l2_audioout</link></primaryie></indexentry>
+<indexentry><primaryie>struct&nbsp;<link linkend='v4l2-bt-timings'>v4l2_bt_timings</link></primaryie></indexentry>
 <indexentry><primaryie>struct&nbsp;<link linkend='v4l2-buffer'>v4l2_buffer</link></primaryie></indexentry>
 <indexentry><primaryie>struct&nbsp;<link linkend='v4l2-capability'>v4l2_capability</link></primaryie></indexentry>
 <indexentry><primaryie>struct&nbsp;<link linkend='v4l2-captureparm'>v4l2_captureparm</link></primaryie></indexentry>
@@ -46,6 +47,9 @@
 <indexentry><primaryie>struct&nbsp;<link linkend='v4l2-dbg-chip-ident'>v4l2_dbg_chip_ident</link></primaryie></indexentry>
 <indexentry><primaryie>struct&nbsp;<link linkend='v4l2-dbg-match'>v4l2_dbg_match</link></primaryie></indexentry>
 <indexentry><primaryie>struct&nbsp;<link linkend='v4l2-dbg-register'>v4l2_dbg_register</link></primaryie></indexentry>
+<indexentry><primaryie>struct&nbsp;<link linkend='v4l2-dv-enum-preset'>v4l2_dv_enum_preset</link></primaryie></indexentry>
+<indexentry><primaryie>struct&nbsp;<link linkend='v4l2-dv-preset'>v4l2_dv_preset</link></primaryie></indexentry>
+<indexentry><primaryie>struct&nbsp;<link linkend='v4l2-dv-timings'>v4l2_dv_timings</link></primaryie></indexentry>
 <indexentry><primaryie>struct&nbsp;<link linkend='v4l2-enc-idx'>v4l2_enc_idx</link></primaryie></indexentry>
 <indexentry><primaryie>struct&nbsp;<link linkend='v4l2-enc-idx-entry'>v4l2_enc_idx_entry</link></primaryie></indexentry>
 <indexentry><primaryie>struct&nbsp;<link linkend='v4l2-encoder-cmd'>v4l2_encoder_cmd</link></primaryie></indexentry>

Documentation/DocBook/mtdnand.tmpl

@@ -174,7 +174,7 @@
 		</para>
 		<programlisting>
 static struct mtd_info *board_mtd;
-static unsigned long baseaddr;
+static void __iomem *baseaddr;
 		</programlisting>
 		<para>
 			Static example
@@ -182,7 +182,7 @@ static unsigned long baseaddr;
 		<programlisting>
 static struct mtd_info board_mtd;
 static struct nand_chip board_chip;
-static unsigned long baseaddr;
+static void __iomem *baseaddr;
 		</programlisting>
 	</sect1>
 	<sect1 id="Partition_defines">
@@ -283,8 +283,8 @@ int __init board_init (void)
 	}
 
 	/* map physical address */
-	baseaddr = (unsigned long)ioremap(CHIP_PHYSICAL_ADDRESS, 1024);
-	if(!baseaddr){
+	baseaddr = ioremap(CHIP_PHYSICAL_ADDRESS, 1024);
+	if (!baseaddr) {
 		printk("Ioremap to access NAND chip failed\n");
 		err = -EIO;
 		goto out_mtd;
@@ -316,7 +316,7 @@ int __init board_init (void)
 	goto out;
 
 out_ior:
-	iounmap((void *)baseaddr);
+	iounmap(baseaddr);
 out_mtd:
 	kfree (board_mtd);
 out:
@@ -341,7 +341,7 @@ static void __exit board_cleanup (void)
 	nand_release (board_mtd);
 
 	/* unmap physical address */
-	iounmap((void *)baseaddr);
+	iounmap(baseaddr);
 	
 	/* Free the MTD device structure */
 	kfree (board_mtd);

Documentation/DocBook/procfs-guide.tmpl

@@ -1,626 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
-	"http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" [
-<!ENTITY procfsexample SYSTEM "procfs_example.xml">
-]>
-
-<book id="LKProcfsGuide">
-  <bookinfo>
-    <title>Linux Kernel Procfs Guide</title>
-
-    <authorgroup>
-      <author>
-	<firstname>Erik</firstname>
-	<othername>(J.A.K.)</othername>
-	<surname>Mouw</surname>
-	<affiliation>
-	  <address>
-            <email>mouw@nl.linux.org</email>
-          </address>
-	</affiliation>
-      </author>
-      <othercredit>
-	<contrib>
-	This software and documentation were written while working on the
-	LART computing board
-	(<ulink url="http://www.lartmaker.nl/">http://www.lartmaker.nl/</ulink>),
-	which was sponsored by the Delt University of Technology projects
-	Mobile Multi-media Communications and Ubiquitous Communications.
-	</contrib>
-      </othercredit>
-    </authorgroup>
-
-    <revhistory>
-      <revision>
-	<revnumber>1.0</revnumber>
-	<date>May 30, 2001</date>
-	<revremark>Initial revision posted to linux-kernel</revremark>
-      </revision>
-      <revision>
-	<revnumber>1.1</revnumber>
-	<date>June 3, 2001</date>
-	<revremark>Revised after comments from linux-kernel</revremark>
-      </revision>
-    </revhistory>
-
-    <copyright>
-      <year>2001</year>
-      <holder>Erik Mouw</holder>
-    </copyright>
-
-
-    <legalnotice>
-      <para>
-        This documentation 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.
-      </para>
-      
-      <para>
-        This documentation 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.
-      </para>
-      
-      <para>
-        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
-      </para>
-      
-      <para>
-        For more details see the file COPYING in the source
-        distribution of Linux.
-      </para>
-    </legalnotice>
-  </bookinfo>
-
-
-
-
-  <toc>
-  </toc>
-
-
-
-
-  <preface id="Preface">
-    <title>Preface</title>
-
-    <para>
-      This guide describes the use of the procfs file system from
-      within the Linux kernel. The idea to write this guide came up on
-      the #kernelnewbies IRC channel (see <ulink
-      url="http://www.kernelnewbies.org/">http://www.kernelnewbies.org/</ulink>),
-      when Jeff Garzik explained the use of procfs and forwarded me a
-      message Alexander Viro wrote to the linux-kernel mailing list. I
-      agreed to write it up nicely, so here it is.
-    </para>
-
-    <para>
-      I'd like to thank Jeff Garzik
-      <email>jgarzik@pobox.com</email> and Alexander Viro
-      <email>viro@parcelfarce.linux.theplanet.co.uk</email> for their input,
-      Tim Waugh <email>twaugh@redhat.com</email> for his <ulink
-      url="http://people.redhat.com/twaugh/docbook/selfdocbook/">Selfdocbook</ulink>,
-      and Marc Joosen <email>marcj@historia.et.tudelft.nl</email> for
-      proofreading.
-    </para>
-
-    <para>
-      Erik
-    </para>
-  </preface>
-
-
-
-
-  <chapter id="intro">
-    <title>Introduction</title>
-
-    <para>
-      The <filename class="directory">/proc</filename> file system
-      (procfs) is a special file system in the linux kernel. It's a
-      virtual file system: it is not associated with a block device
-      but exists only in memory. The files in the procfs are there to
-      allow userland programs access to certain information from the
-      kernel (like process information in <filename
-      class="directory">/proc/[0-9]+/</filename>), but also for debug
-      purposes (like <filename>/proc/ksyms</filename>).
-    </para>
-
-    <para>
-      This guide describes the use of the procfs file system from
-      within the Linux kernel. It starts by introducing all relevant
-      functions to manage the files within the file system. After that
-      it shows how to communicate with userland, and some tips and
-      tricks will be pointed out. Finally a complete example will be
-      shown.
-    </para>
-
-    <para>
-      Note that the files in <filename
-      class="directory">/proc/sys</filename> are sysctl files: they
-      don't belong to procfs and are governed by a completely
-      different API described in the Kernel API book.
-    </para>
-  </chapter>
-
-
-
-
-  <chapter id="managing">
-    <title>Managing procfs entries</title>
-    
-    <para>
-      This chapter describes the functions that various kernel
-      components use to populate the procfs with files, symlinks,
-      device nodes, and directories.
-    </para>
-
-    <para>
-      A minor note before we start: if you want to use any of the
-      procfs functions, be sure to include the correct header file! 
-      This should be one of the first lines in your code:
-    </para>
-
-    <programlisting>
-#include &lt;linux/proc_fs.h&gt;
-    </programlisting>
-
-
-
-
-    <sect1 id="regularfile">
-      <title>Creating a regular file</title>
-      
-      <funcsynopsis>
-	<funcprototype>
-	  <funcdef>struct proc_dir_entry* <function>create_proc_entry</function></funcdef>
-	  <paramdef>const char* <parameter>name</parameter></paramdef>
-	  <paramdef>mode_t <parameter>mode</parameter></paramdef>
-	  <paramdef>struct proc_dir_entry* <parameter>parent</parameter></paramdef>
-	</funcprototype>
-      </funcsynopsis>
-
-      <para>
-        This function creates a regular file with the name
-        <parameter>name</parameter>, file mode
-        <parameter>mode</parameter> in the directory
-        <parameter>parent</parameter>. To create a file in the root of
-        the procfs, use <constant>NULL</constant> as
-        <parameter>parent</parameter> parameter. When successful, the
-        function will return a pointer to the freshly created
-        <structname>struct proc_dir_entry</structname>; otherwise it
-        will return <constant>NULL</constant>. <xref
-        linkend="userland"/> describes how to do something useful with
-        regular files.
-      </para>
-
-      <para>
-        Note that it is specifically supported that you can pass a
-        path that spans multiple directories. For example
-        <function>create_proc_entry</function>(<parameter>"drivers/via0/info"</parameter>)
-        will create the <filename class="directory">via0</filename>
-        directory if necessary, with standard
-        <constant>0755</constant> permissions.
-      </para>
-
-    <para>
-      If you only want to be able to read the file, the function
-      <function>create_proc_read_entry</function> described in <xref
-      linkend="convenience"/> may be used to create and initialise
-      the procfs entry in one single call.
-    </para>
-    </sect1>
-
-
-
-
-    <sect1 id="Creating_a_symlink">
-      <title>Creating a symlink</title>
-
-      <funcsynopsis>
-	<funcprototype>
-	  <funcdef>struct proc_dir_entry*
-	  <function>proc_symlink</function></funcdef> <paramdef>const
-	  char* <parameter>name</parameter></paramdef>
-	  <paramdef>struct proc_dir_entry*
-	  <parameter>parent</parameter></paramdef> <paramdef>const
-	  char* <parameter>dest</parameter></paramdef>
-	</funcprototype>
-      </funcsynopsis>
-      
-      <para>
-        This creates a symlink in the procfs directory
-        <parameter>parent</parameter> that points from
-        <parameter>name</parameter> to
-        <parameter>dest</parameter>. This translates in userland to
-        <literal>ln -s</literal> <parameter>dest</parameter>
-        <parameter>name</parameter>.
-      </para>
-    </sect1>
-
-    <sect1 id="Creating_a_directory">
-      <title>Creating a directory</title>
-      
-      <funcsynopsis>
-	<funcprototype>
-	  <funcdef>struct proc_dir_entry* <function>proc_mkdir</function></funcdef>
-	  <paramdef>const char* <parameter>name</parameter></paramdef>
-	  <paramdef>struct proc_dir_entry* <parameter>parent</parameter></paramdef>
-	</funcprototype>
-      </funcsynopsis>
-
-      <para>
-        Create a directory <parameter>name</parameter> in the procfs
-        directory <parameter>parent</parameter>.
-      </para>
-    </sect1>
-
-
-
-
-    <sect1 id="Removing_an_entry">
-      <title>Removing an entry</title>
-      
-      <funcsynopsis>
-	<funcprototype>
-	  <funcdef>void <function>remove_proc_entry</function></funcdef>
-	  <paramdef>const char* <parameter>name</parameter></paramdef>
-	  <paramdef>struct proc_dir_entry* <parameter>parent</parameter></paramdef>
-	</funcprototype>
-      </funcsynopsis>
-
-      <para>
-        Removes the entry <parameter>name</parameter> in the directory
-        <parameter>parent</parameter> from the procfs. Entries are
-        removed by their <emphasis>name</emphasis>, not by the
-        <structname>struct proc_dir_entry</structname> returned by the
-        various create functions. Note that this function doesn't
-        recursively remove entries.
-      </para>
-
-      <para>
-        Be sure to free the <structfield>data</structfield> entry from
-        the <structname>struct proc_dir_entry</structname> before
-        <function>remove_proc_entry</function> is called (that is: if
-        there was some <structfield>data</structfield> allocated, of
-        course). See <xref linkend="usingdata"/> for more information
-        on using the <structfield>data</structfield> entry.
-      </para>
-    </sect1>
-  </chapter>
-
-
-
-
-  <chapter id="userland">
-    <title>Communicating with userland</title>
-    
-    <para>
-       Instead of reading (or writing) information directly from
-       kernel memory, procfs works with <emphasis>call back
-       functions</emphasis> for files: functions that are called when
-       a specific file is being read or written. Such functions have
-       to be initialised after the procfs file is created by setting
-       the <structfield>read_proc</structfield> and/or
-       <structfield>write_proc</structfield> fields in the
-       <structname>struct proc_dir_entry*</structname> that the
-       function <function>create_proc_entry</function> returned:
-    </para>
-
-    <programlisting>
-struct proc_dir_entry* entry;
-
-entry->read_proc = read_proc_foo;
-entry->write_proc = write_proc_foo;
-    </programlisting>
-
-    <para>
-      If you only want to use a the
-      <structfield>read_proc</structfield>, the function
-      <function>create_proc_read_entry</function> described in <xref
-      linkend="convenience"/> may be used to create and initialise the
-      procfs entry in one single call.
-    </para>
-
-
-
-    <sect1 id="Reading_data">
-      <title>Reading data</title>
-
-      <para>
-        The read function is a call back function that allows userland
-        processes to read data from the kernel. The read function
-        should have the following format:
-      </para>
-
-      <funcsynopsis>
-	<funcprototype>
-	  <funcdef>int <function>read_func</function></funcdef>
-	  <paramdef>char* <parameter>buffer</parameter></paramdef>
-	  <paramdef>char** <parameter>start</parameter></paramdef>
-	  <paramdef>off_t <parameter>off</parameter></paramdef>
-	  <paramdef>int <parameter>count</parameter></paramdef>
-	  <paramdef>int* <parameter>peof</parameter></paramdef>
-	  <paramdef>void* <parameter>data</parameter></paramdef>
-	</funcprototype>
-      </funcsynopsis>
-
-      <para>
-        The read function should write its information into the
-        <parameter>buffer</parameter>, which will be exactly
-        <literal>PAGE_SIZE</literal> bytes long.
-      </para>
-
-      <para>
-        The parameter
-        <parameter>peof</parameter> should be used to signal that the
-        end of the file has been reached by writing
-        <literal>1</literal> to the memory location
-        <parameter>peof</parameter> points to.
-      </para>
-
-      <para>
-        The <parameter>data</parameter>
-        parameter can be used to create a single call back function for
-        several files, see <xref linkend="usingdata"/>.
-      </para>
-
-      <para>
-        The rest of the parameters and the return value are described
-	by a comment in <filename>fs/proc/generic.c</filename> as follows:
-      </para>
-
-      <blockquote>
-        <para>
-	You have three ways to return data:
-       	</para>
-        <orderedlist>
-          <listitem>
-            <para>
-	      Leave <literal>*start = NULL</literal>.  (This is the default.)
-	      Put the data of the requested offset at that
-	      offset within the buffer.  Return the number (<literal>n</literal>)
-	      of bytes there are from the beginning of the
-	      buffer up to the last byte of data.  If the
-	      number of supplied bytes (<literal>= n - offset</literal>) is
-	      greater than zero and you didn't signal eof
-	      and the reader is prepared to take more data
-	      you will be called again with the requested
-	      offset advanced by the number of bytes
-	      absorbed.  This interface is useful for files
-	      no larger than the buffer.
-	    </para>
-	  </listitem>
-	  <listitem>
-            <para>
-	      Set <literal>*start</literal> to an unsigned long value less than
-	      the buffer address but greater than zero.
-	      Put the data of the requested offset at the
-	      beginning of the buffer.  Return the number of
-	      bytes of data placed there.  If this number is
-	      greater than zero and you didn't signal eof
-	      and the reader is prepared to take more data
-	      you will be called again with the requested
-	      offset advanced by <literal>*start</literal>.  This interface is
-	      useful when you have a large file consisting
-	      of a series of blocks which you want to count
-	      and return as wholes.
-	      (Hack by Paul.Russell@rustcorp.com.au)
-	    </para>
-	  </listitem>
-	  <listitem>
-            <para>
-	      Set <literal>*start</literal> to an address within the buffer.
-	      Put the data of the requested offset at <literal>*start</literal>.
-	      Return the number of bytes of data placed there.
-	      If this number is greater than zero and you
-	      didn't signal eof and the reader is prepared to
-	      take more data you will be called again with the
-	      requested offset advanced by the number of bytes
-	      absorbed.
-	    </para>
-	  </listitem>
-	</orderedlist>
-      </blockquote>
-
-      <para>
-        <xref linkend="example"/> shows how to use a read call back
-        function.
-      </para>
-    </sect1>
-
-
-
-
-    <sect1 id="Writing_data">
-      <title>Writing data</title>
-
-      <para>
-        The write call back function allows a userland process to write
-        data to the kernel, so it has some kind of control over the
-        kernel. The write function should have the following format:
-      </para>
-
-      <funcsynopsis>
-	<funcprototype>
-	  <funcdef>int <function>write_func</function></funcdef>
-	  <paramdef>struct file* <parameter>file</parameter></paramdef>
-	  <paramdef>const char* <parameter>buffer</parameter></paramdef>
-	  <paramdef>unsigned long <parameter>count</parameter></paramdef>
-	  <paramdef>void* <parameter>data</parameter></paramdef>
-	</funcprototype>
-      </funcsynopsis>
-
-      <para>
-        The write function should read <parameter>count</parameter>
-        bytes at maximum from the <parameter>buffer</parameter>. Note
-        that the <parameter>buffer</parameter> doesn't live in the
-        kernel's memory space, so it should first be copied to kernel
-        space with <function>copy_from_user</function>. The
-        <parameter>file</parameter> parameter is usually
-        ignored. <xref linkend="usingdata"/> shows how to use the
-        <parameter>data</parameter> parameter.
-      </para>
-
-      <para>
-        Again, <xref linkend="example"/> shows how to use this call back
-        function.
-      </para>
-    </sect1>
-
-
-
-
-    <sect1 id="usingdata">
-      <title>A single call back for many files</title>
-
-      <para>
-         When a large number of almost identical files is used, it's
-         quite inconvenient to use a separate call back function for
-         each file. A better approach is to have a single call back
-         function that distinguishes between the files by using the
-         <structfield>data</structfield> field in <structname>struct
-         proc_dir_entry</structname>. First of all, the
-         <structfield>data</structfield> field has to be initialised:
-      </para>
-
-      <programlisting>
-struct proc_dir_entry* entry;
-struct my_file_data *file_data;
-
-file_data = kmalloc(sizeof(struct my_file_data), GFP_KERNEL);
-entry->data = file_data;
-      </programlisting>
-     
-      <para>
-          The <structfield>data</structfield> field is a <type>void
-          *</type>, so it can be initialised with anything.
-      </para>
-
-      <para>
-        Now that the <structfield>data</structfield> field is set, the
-        <function>read_proc</function> and
-        <function>write_proc</function> can use it to distinguish
-        between files because they get it passed into their
-        <parameter>data</parameter> parameter:
-      </para>
-
-      <programlisting>
-int foo_read_func(char *page, char **start, off_t off,
-                  int count, int *eof, void *data)
-{
-        int len;
-
-        if(data == file_data) {
-                /* special case for this file */
-        } else {
-                /* normal processing */
-        }
-
-        return len;
-}
-      </programlisting>
-
-      <para>
-        Be sure to free the <structfield>data</structfield> data field
-        when removing the procfs entry.
-      </para>
-    </sect1>
-  </chapter>
-
-
-
-
-  <chapter id="tips">
-    <title>Tips and tricks</title>
-
-
-
-
-    <sect1 id="convenience">
-      <title>Convenience functions</title>
-
-      <funcsynopsis>
-	<funcprototype>
-	  <funcdef>struct proc_dir_entry* <function>create_proc_read_entry</function></funcdef>
-	  <paramdef>const char* <parameter>name</parameter></paramdef>
-	  <paramdef>mode_t <parameter>mode</parameter></paramdef>
-	  <paramdef>struct proc_dir_entry* <parameter>parent</parameter></paramdef>
-	  <paramdef>read_proc_t* <parameter>read_proc</parameter></paramdef>
-	  <paramdef>void* <parameter>data</parameter></paramdef>
-	</funcprototype>
-      </funcsynopsis>
-      
-      <para>
-        This function creates a regular file in exactly the same way
-        as <function>create_proc_entry</function> from <xref
-        linkend="regularfile"/> does, but also allows to set the read
-        function <parameter>read_proc</parameter> in one call. This
-        function can set the <parameter>data</parameter> as well, like
-        explained in <xref linkend="usingdata"/>.
-      </para>
-    </sect1>
-
-
-
-    <sect1 id="Modules">
-      <title>Modules</title>
-
-      <para>
-        If procfs is being used from within a module, be sure to set
-        the <structfield>owner</structfield> field in the
-        <structname>struct proc_dir_entry</structname> to
-        <constant>THIS_MODULE</constant>.
-      </para>
-
-      <programlisting>
-struct proc_dir_entry* entry;
-
-entry->owner = THIS_MODULE;
-      </programlisting>
-    </sect1>
-
-
-
-
-    <sect1 id="Mode_and_ownership">
-      <title>Mode and ownership</title>
-
-      <para>
-        Sometimes it is useful to change the mode and/or ownership of
-        a procfs entry. Here is an example that shows how to achieve
-        that:
-      </para>
-
-      <programlisting>
-struct proc_dir_entry* entry;
-
-entry->mode =  S_IWUSR |S_IRUSR | S_IRGRP | S_IROTH;
-entry->uid = 0;
-entry->gid = 100;
-      </programlisting>
-
-    </sect1>
-  </chapter>
-
-
-
-
-  <chapter id="example">
-    <title>Example</title>
-
-    <!-- be careful with the example code: it shouldn't be wider than
-    approx. 60 columns, or otherwise it won't fit properly on a page
-    -->
-
-&procfsexample;
-
-  </chapter>
-</book>

Documentation/DocBook/procfs_example.c

@@ -1,201 +0,0 @@
-/*
- * procfs_example.c: an example proc interface
- *
- * Copyright (C) 2001, Erik Mouw (mouw@nl.linux.org)
- *
- * This file accompanies the procfs-guide in the Linux kernel
- * source. Its main use is to demonstrate the concepts and
- * functions described in the guide.
- *
- * This software has been developed while working on the LART
- * computing board (http://www.lartmaker.nl), which was sponsored
- * by the Delt University of Technology projects Mobile Multi-media
- * Communications and Ubiquitous Communications.
- *
- * 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., 59 Temple Place,
- * Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/proc_fs.h>
-#include <linux/jiffies.h>
-#include <asm/uaccess.h>
-
-
-#define MODULE_VERS "1.0"
-#define MODULE_NAME "procfs_example"
-
-#define FOOBAR_LEN 8
-
-struct fb_data_t {
-	char name[FOOBAR_LEN + 1];
-	char value[FOOBAR_LEN + 1];
-};
-
-
-static struct proc_dir_entry *example_dir, *foo_file,
-	*bar_file, *jiffies_file, *symlink;
-
-
-struct fb_data_t foo_data, bar_data;
-
-
-static int proc_read_jiffies(char *page, char **start,
-			     off_t off, int count,
-			     int *eof, void *data)
-{
-	int len;
-
-	len = sprintf(page, "jiffies = %ld\n",
-                      jiffies);
-
-	return len;
-}
-
-
-static int proc_read_foobar(char *page, char **start,
-			    off_t off, int count, 
-			    int *eof, void *data)
-{
-	int len;
-	struct fb_data_t *fb_data = (struct fb_data_t *)data;
-
-	/* DON'T DO THAT - buffer overruns are bad */
-	len = sprintf(page, "%s = '%s'\n", 
-		      fb_data->name, fb_data->value);
-
-	return len;
-}
-
-
-static int proc_write_foobar(struct file *file,
-			     const char *buffer,
-			     unsigned long count, 
-			     void *data)
-{
-	int len;
-	struct fb_data_t *fb_data = (struct fb_data_t *)data;
-
-	if(count > FOOBAR_LEN)
-		len = FOOBAR_LEN;
-	else
-		len = count;
-
-	if(copy_from_user(fb_data->value, buffer, len))
-		return -EFAULT;
-
-	fb_data->value[len] = '\0';
-
-	return len;
-}
-
-
-static int __init init_procfs_example(void)
-{
-	int rv = 0;
-
-	/* create directory */
-	example_dir = proc_mkdir(MODULE_NAME, NULL);
-	if(example_dir == NULL) {
-		rv = -ENOMEM;
-		goto out;
-	}
-	/* create jiffies using convenience function */
-	jiffies_file = create_proc_read_entry("jiffies", 
-					      0444, example_dir, 
-					      proc_read_jiffies,
-					      NULL);
-	if(jiffies_file == NULL) {
-		rv  = -ENOMEM;
-		goto no_jiffies;
-	}
-
-	/* create foo and bar files using same callback
-	 * functions 
-	 */
-	foo_file = create_proc_entry("foo", 0644, example_dir);
-	if(foo_file == NULL) {
-		rv = -ENOMEM;
-		goto no_foo;
-	}
-
-	strcpy(foo_data.name, "foo");
-	strcpy(foo_data.value, "foo");
-	foo_file->data = &foo_data;
-	foo_file->read_proc = proc_read_foobar;
-	foo_file->write_proc = proc_write_foobar;
-		
-	bar_file = create_proc_entry("bar", 0644, example_dir);
-	if(bar_file == NULL) {
-		rv = -ENOMEM;
-		goto no_bar;
-	}
-
-	strcpy(bar_data.name, "bar");
-	strcpy(bar_data.value, "bar");
-	bar_file->data = &bar_data;
-	bar_file->read_proc = proc_read_foobar;
-	bar_file->write_proc = proc_write_foobar;
-		
-	/* create symlink */
-	symlink = proc_symlink("jiffies_too", example_dir, 
-			       "jiffies");
-	if(symlink == NULL) {
-		rv = -ENOMEM;
-		goto no_symlink;
-	}
-
-	/* everything OK */
-	printk(KERN_INFO "%s %s initialised\n",
-	       MODULE_NAME, MODULE_VERS);
-	return 0;
-
-no_symlink:
-	remove_proc_entry("bar", example_dir);
-no_bar:
-	remove_proc_entry("foo", example_dir);
-no_foo:
-	remove_proc_entry("jiffies", example_dir);
-no_jiffies:			      
-	remove_proc_entry(MODULE_NAME, NULL);
-out:
-	return rv;
-}
-
-
-static void __exit cleanup_procfs_example(void)
-{
-	remove_proc_entry("jiffies_too", example_dir);
-	remove_proc_entry("bar", example_dir);
-	remove_proc_entry("foo", example_dir);
-	remove_proc_entry("jiffies", example_dir);
-	remove_proc_entry(MODULE_NAME, NULL);
-
-	printk(KERN_INFO "%s %s removed\n",
-	       MODULE_NAME, MODULE_VERS);
-}
-
-
-module_init(init_procfs_example);
-module_exit(cleanup_procfs_example);
-
-MODULE_AUTHOR("Erik Mouw");
-MODULE_DESCRIPTION("procfs examples");
-MODULE_LICENSE("GPL");

Documentation/DocBook/v4l/common.xml

@@ -716,6 +716,41 @@ if (-1 == ioctl (fd, &VIDIOC-S-STD;, &std_id)) {
 }
       </programlisting>
     </example>
+  <section id="dv-timings">
+	<title>Digital Video (DV) Timings</title>
+	<para>
+	The video standards discussed so far has been dealing with Analog TV and the
+corresponding video timings. Today there are many more different hardware interfaces
+such as High Definition TV interfaces (HDMI), VGA, DVI connectors etc., that carry
+video signals and there is a need to extend the API to select the video timings
+for these interfaces. Since it is not possible to extend the &v4l2-std-id; due to
+the limited bits available, a new set of IOCTLs is added to set/get video timings at
+the input and output: </para><itemizedlist>
+	<listitem>
+	<para>DV Presets: Digital Video (DV) presets. These are IDs representing a
+video timing at the input/output. Presets are pre-defined timings implemented
+by the hardware according to video standards. A __u32 data type is used to represent
+a preset unlike the bit mask that is used in &v4l2-std-id; allowing future extensions
+to support as many different presets as needed.</para>
+	</listitem>
+	<listitem>
+	<para>Custom DV Timings: This will allow applications to define more detailed
+custom video timings for the interface. This includes parameters such as width, height,
+polarities, frontporch, backporch etc.
+	</para>
+	</listitem>
+	</itemizedlist>
+	<para>To enumerate and query the attributes of DV presets supported by a device,
+applications use the &VIDIOC-ENUM-DV-PRESETS; ioctl. To get the current DV preset,
+applications use the &VIDIOC-G-DV-PRESET; ioctl and to set a preset they use the
+&VIDIOC-S-DV-PRESET; ioctl.</para>
+	<para>To set custom DV timings for the device, applications use the
+&VIDIOC-S-DV-TIMINGS; ioctl and to get current custom DV timings they use the
+&VIDIOC-G-DV-TIMINGS; ioctl.</para>
+	<para>Applications can make use of the <xref linkend="input-capabilities" /> and
+<xref linkend="output-capabilities"/> flags to decide what ioctls are available to set the
+video timings for the device.</para>
+	</section>
   </section>
 
   &sub-controls;

Documentation/DocBook/v4l/compat.xml

@@ -2291,8 +2291,8 @@ was renamed to <structname id="v4l2-chip-ident-old">v4l2_chip_ident_old</structn
 	<listitem>
 	  <para>New control <constant>V4L2_CID_COLORFX</constant> was added.</para>
 	</listitem>
-       </orderedlist>
-     </section>
+      </orderedlist>
+    </section>
     <section>
       <title>V4L2 in Linux 2.6.32</title>
       <orderedlist>
@@ -2322,8 +2322,16 @@ more information.</para>
 	<listitem>
 	  <para>Added Remote Controller chapter, describing the default Remote Controller mapping for media devices.</para>
 	</listitem>
-       </orderedlist>
-     </section>
+      </orderedlist>
+    </section>
+    <section>
+      <title>V4L2 in Linux 2.6.33</title>
+      <orderedlist>
+	<listitem>
+	  <para>Added support for Digital Video timings in order to support HDTV receivers and transmitters.</para>
+	</listitem>
+      </orderedlist>
+    </section>
    </section>
 
    <section id="other">

Documentation/DocBook/v4l/io.xml

@@ -589,7 +589,8 @@ number of a video input as in &v4l2-input; field
 	    <entry></entry>
 	    <entry>A place holder for future extensions and custom
 (driver defined) buffer types
-<constant>V4L2_BUF_TYPE_PRIVATE</constant> and higher.</entry>
+<constant>V4L2_BUF_TYPE_PRIVATE</constant> and higher. Applications
+should set this to 0.</entry>
 	  </row>
 	</tbody>
       </tgroup>

Documentation/DocBook/v4l/v4l2.xml

@@ -74,6 +74,17 @@ Remote Controller chapter.</contrib>
 	  </address>
 	</affiliation>
       </author>
+
+      <author>
+	<firstname>Muralidharan</firstname>
+	<surname>Karicheri</surname>
+	<contrib>Documented the Digital Video timings API.</contrib>
+	<affiliation>
+	  <address>
+	    <email>m-karicheri2@ti.com</email>
+	  </address>
+	</affiliation>
+      </author>
     </authorgroup>
 
     <copyright>
@@ -89,7 +100,7 @@ Remote Controller chapter.</contrib>
       <year>2008</year>
       <year>2009</year>
       <holder>Bill Dirks, Michael H. Schimek, Hans Verkuil, Martin
-Rubli, Andy Walls, Mauro Carvalho Chehab</holder>
+Rubli, Andy Walls, Muralidharan Karicheri, Mauro Carvalho Chehab</holder>
     </copyright>
     <legalnotice>
     <para>Except when explicitly stated as GPL, programming examples within
@@ -102,6 +113,13 @@ structs, ioctls) must be noted in more detail in the history chapter
 (compat.sgml), along with the possible impact on existing drivers and
 applications. -->
 
+      <revision>
+	<revnumber>2.6.33</revnumber>
+	<date>2009-12-03</date>
+	<authorinitials>mk</authorinitials>
+	<revremark>Added documentation for the Digital Video timings API.</revremark>
+      </revision>
+
       <revision>
 	<revnumber>2.6.32</revnumber>
 	<date>2009-08-31</date>
@@ -355,7 +373,7 @@ and discussions on the V4L mailing list.</revremark>
 </partinfo>
 
 <title>Video for Linux Two API Specification</title>
- <subtitle>Revision 2.6.32</subtitle>
+ <subtitle>Revision 2.6.33</subtitle>
 
   <chapter id="common">
     &sub-common;
@@ -411,6 +429,7 @@ and discussions on the V4L mailing list.</revremark>
     &sub-encoder-cmd;
     &sub-enumaudio;
     &sub-enumaudioout;
+    &sub-enum-dv-presets;
     &sub-enum-fmt;
     &sub-enum-framesizes;
     &sub-enum-frameintervals;
@@ -421,6 +440,8 @@ and discussions on the V4L mailing list.</revremark>
     &sub-g-audioout;
     &sub-g-crop;
     &sub-g-ctrl;
+    &sub-g-dv-preset;
+    &sub-g-dv-timings;
     &sub-g-enc-index;
     &sub-g-ext-ctrls;
     &sub-g-fbuf;
@@ -441,6 +462,7 @@ and discussions on the V4L mailing list.</revremark>
     &sub-querybuf;
     &sub-querycap;
     &sub-queryctrl;
+    &sub-query-dv-preset;
     &sub-querystd;
     &sub-reqbufs;
     &sub-s-hw-freq-seek;

Documentation/DocBook/v4l/videodev2.h.xml

@@ -733,6 +733,99 @@ struct <link linkend="v4l2-standard">v4l2_standard</link> {
         __u32                reserved[4];
 };
 
+/*
+ *      V I D E O       T I M I N G S   D V     P R E S E T
+ */
+struct <link linkend="v4l2-dv-preset">v4l2_dv_preset</link> {
+        __u32   preset;
+        __u32   reserved[4];
+};
+
+/*
+ *      D V     P R E S E T S   E N U M E R A T I O N
+ */
+struct <link linkend="v4l2-dv-enum-preset">v4l2_dv_enum_preset</link> {
+        __u32   index;
+        __u32   preset;
+        __u8    name[32]; /* Name of the preset timing */
+        __u32   width;
+        __u32   height;
+        __u32   reserved[4];
+};
+
+/*
+ *      D V     P R E S E T     V A L U E S
+ */
+#define         V4L2_DV_INVALID         0
+#define         V4L2_DV_480P59_94       1 /* BT.1362 */
+#define         V4L2_DV_576P50          2 /* BT.1362 */
+#define         V4L2_DV_720P24          3 /* SMPTE 296M */
+#define         V4L2_DV_720P25          4 /* SMPTE 296M */
+#define         V4L2_DV_720P30          5 /* SMPTE 296M */
+#define         V4L2_DV_720P50          6 /* SMPTE 296M */
+#define         V4L2_DV_720P59_94       7 /* SMPTE 274M */
+#define         V4L2_DV_720P60          8 /* SMPTE 274M/296M */
+#define         V4L2_DV_1080I29_97      9 /* BT.1120/ SMPTE 274M */
+#define         V4L2_DV_1080I30         10 /* BT.1120/ SMPTE 274M */
+#define         V4L2_DV_1080I25         11 /* BT.1120 */
+#define         V4L2_DV_1080I50         12 /* SMPTE 296M */
+#define         V4L2_DV_1080I60         13 /* SMPTE 296M */
+#define         V4L2_DV_1080P24         14 /* SMPTE 296M */
+#define         V4L2_DV_1080P25         15 /* SMPTE 296M */
+#define         V4L2_DV_1080P30         16 /* SMPTE 296M */
+#define         V4L2_DV_1080P50         17 /* BT.1120 */
+#define         V4L2_DV_1080P60         18 /* BT.1120 */
+
+/*
+ *      D V     B T     T I M I N G S
+ */
+
+/* BT.656/BT.1120 timing data */
+struct <link linkend="v4l2-bt-timings">v4l2_bt_timings</link> {
+        __u32   width;          /* width in pixels */
+        __u32   height;         /* height in lines */
+        __u32   interlaced;     /* Interlaced or progressive */
+        __u32   polarities;     /* Positive or negative polarity */
+        __u64   pixelclock;     /* Pixel clock in HZ. Ex. 74.25MHz-&gt;74250000 */
+        __u32   hfrontporch;    /* Horizpontal front porch in pixels */
+        __u32   hsync;          /* Horizontal Sync length in pixels */
+        __u32   hbackporch;     /* Horizontal back porch in pixels */
+        __u32   vfrontporch;    /* Vertical front porch in pixels */
+        __u32   vsync;          /* Vertical Sync length in lines */
+        __u32   vbackporch;     /* Vertical back porch in lines */
+        __u32   il_vfrontporch; /* Vertical front porch for bottom field of
+                                 * interlaced field formats
+                                 */
+        __u32   il_vsync;       /* Vertical sync length for bottom field of
+                                 * interlaced field formats
+                                 */
+        __u32   il_vbackporch;  /* Vertical back porch for bottom field of
+                                 * interlaced field formats
+                                 */
+        __u32   reserved[16];
+} __attribute__ ((packed));
+
+/* Interlaced or progressive format */
+#define V4L2_DV_PROGRESSIVE     0
+#define V4L2_DV_INTERLACED      1
+
+/* Polarities. If bit is not set, it is assumed to be negative polarity */
+#define V4L2_DV_VSYNC_POS_POL   0x00000001
+#define V4L2_DV_HSYNC_POS_POL   0x00000002
+
+
+/* DV timings */
+struct <link linkend="v4l2-dv-timings">v4l2_dv_timings</link> {
+        __u32 type;
+        union {
+                struct <link linkend="v4l2-bt-timings">v4l2_bt_timings</link>  bt;
+                __u32   reserved[32];
+        };
+} __attribute__ ((packed));
+
+/* Values for the type field */
+#define V4L2_DV_BT_656_1120     0       /* BT.656/1120 timing type */
+
 /*
  *      V I D E O   I N P U T S
  */
@@ -744,7 +837,8 @@ struct <link linkend="v4l2-input">v4l2_input</link> {
         __u32        tuner;             /*  Associated tuner */
         v4l2_std_id  std;
         __u32        status;
-        __u32        reserved[4];
+        __u32        capabilities;
+        __u32        reserved[3];
 };
 
 /*  Values for the 'type' field */
@@ -775,6 +869,11 @@ struct <link linkend="v4l2-input">v4l2_input</link> {
 #define V4L2_IN_ST_NO_ACCESS   0x02000000  /* Conditional access denied */
 #define V4L2_IN_ST_VTR         0x04000000  /* VTR time constant */
 
+/* capabilities flags */
+#define V4L2_IN_CAP_PRESETS             0x00000001 /* Supports S_DV_PRESET */
+#define V4L2_IN_CAP_CUSTOM_TIMINGS      0x00000002 /* Supports S_DV_TIMINGS */
+#define V4L2_IN_CAP_STD                 0x00000004 /* Supports S_STD */
+
 /*
  *      V I D E O   O U T P U T S
  */
@@ -785,13 +884,19 @@ struct <link linkend="v4l2-output">v4l2_output</link> {
         __u32        audioset;          /*  Associated audios (bitfield) */
         __u32        modulator;         /*  Associated modulator */
         v4l2_std_id  std;
-        __u32        reserved[4];
+        __u32        capabilities;
+        __u32        reserved[3];
 };
 /*  Values for the 'type' field */
 #define V4L2_OUTPUT_TYPE_MODULATOR              1
 #define V4L2_OUTPUT_TYPE_ANALOG                 2
 #define V4L2_OUTPUT_TYPE_ANALOGVGAOVERLAY       3
 
+/* capabilities flags */
+#define V4L2_OUT_CAP_PRESETS            0x00000001 /* Supports S_DV_PRESET */
+#define V4L2_OUT_CAP_CUSTOM_TIMINGS     0x00000002 /* Supports S_DV_TIMINGS */
+#define V4L2_OUT_CAP_STD                0x00000004 /* Supports S_STD */
+
 /*
  *      C O N T R O L S
  */
@@ -1626,6 +1731,13 @@ struct <link linkend="v4l2-dbg-chip-ident">v4l2_dbg_chip_ident</link> {
 #endif
 
 #define VIDIOC_S_HW_FREQ_SEEK    _IOW('V', 82, struct <link linkend="v4l2-hw-freq-seek">v4l2_hw_freq_seek</link>)
+#define VIDIOC_ENUM_DV_PRESETS  _IOWR('V', 83, struct <link linkend="v4l2-dv-enum-preset">v4l2_dv_enum_preset</link>)
+#define VIDIOC_S_DV_PRESET      _IOWR('V', 84, struct <link linkend="v4l2-dv-preset">v4l2_dv_preset</link>)
+#define VIDIOC_G_DV_PRESET      _IOWR('V', 85, struct <link linkend="v4l2-dv-preset">v4l2_dv_preset</link>)
+#define VIDIOC_QUERY_DV_PRESET  _IOR('V',  86, struct <link linkend="v4l2-dv-preset">v4l2_dv_preset</link>)
+#define VIDIOC_S_DV_TIMINGS     _IOWR('V', 87, struct <link linkend="v4l2-dv-timings">v4l2_dv_timings</link>)
+#define VIDIOC_G_DV_TIMINGS     _IOWR('V', 88, struct <link linkend="v4l2-dv-timings">v4l2_dv_timings</link>)
+
 /* Reminder: when adding new ioctls please add support for them to
    drivers/media/video/v4l2-compat-ioctl32.c as well! */
 

Documentation/DocBook/v4l/vidioc-enum-dv-presets.xml

@@ -0,0 +1,238 @@
+<refentry id="vidioc-enum-dv-presets">
+  <refmeta>
+    <refentrytitle>ioctl VIDIOC_ENUM_DV_PRESETS</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>VIDIOC_ENUM_DV_PRESETS</refname>
+    <refpurpose>Enumerate supported Digital Video presets</refpurpose>
+  </refnamediv>
+
+  <refsynopsisdiv>
+    <funcsynopsis>
+      <funcprototype>
+	<funcdef>int <function>ioctl</function></funcdef>
+	<paramdef>int <parameter>fd</parameter></paramdef>
+	<paramdef>int <parameter>request</parameter></paramdef>
+	<paramdef>struct v4l2_dv_enum_preset *<parameter>argp</parameter></paramdef>
+      </funcprototype>
+    </funcsynopsis>
+  </refsynopsisdiv>
+
+  <refsect1>
+    <title>Arguments</title>
+
+    <variablelist>
+      <varlistentry>
+	<term><parameter>fd</parameter></term>
+	<listitem>
+	  <para>&fd;</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>request</parameter></term>
+	<listitem>
+	  <para>VIDIOC_ENUM_DV_PRESETS</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>argp</parameter></term>
+	<listitem>
+	  <para></para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Description</title>
+
+    <para>To query the attributes of a DV preset, applications initialize the
+<structfield>index</structfield> field and zero the reserved array of &v4l2-dv-enum-preset;
+and call the <constant>VIDIOC_ENUM_DV_PRESETS</constant> ioctl with a pointer to this
+structure. Drivers fill the rest of the structure or return an
+&EINVAL; when the index is out of bounds. To enumerate all DV Presets supported,
+applications shall begin at index zero, incrementing by one until the
+driver returns <errorcode>EINVAL</errorcode>. Drivers may enumerate a
+different set of DV presets after switching the video input or
+output.</para>
+
+    <table pgwide="1" frame="none" id="v4l2-dv-enum-preset">
+      <title>struct <structname>v4l2_dv_enum_presets</structname></title>
+      <tgroup cols="3">
+	&cs-str;
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>index</structfield></entry>
+	    <entry>Number of the DV preset, set by the
+application.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>preset</structfield></entry>
+	    <entry>This field identifies one of the DV preset values listed in <xref linkend="v4l2-dv-presets-vals"/>.</entry>
+	  </row>
+	  <row>
+	    <entry>__u8</entry>
+	    <entry><structfield>name</structfield>[24]</entry>
+	    <entry>Name of the preset, a NUL-terminated ASCII string, for example: "720P-60", "1080I-60". This information is
+intended for the user.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>width</structfield></entry>
+	    <entry>Width of the active video in pixels for the DV preset.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>height</structfield></entry>
+	    <entry>Height of the active video in lines for the DV preset.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>reserved</structfield>[4]</entry>
+	    <entry>Reserved for future extensions. Drivers must set the array to zero.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="v4l2-dv-presets-vals">
+      <title>struct <structname>DV Presets</structname></title>
+      <tgroup cols="3">
+	&cs-str;
+	<tbody valign="top">
+	  <row>
+	    <entry>Preset</entry>
+	    <entry>Preset value</entry>
+	    <entry>Description</entry>
+	  </row>
+	  <row>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry></entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_INVALID</entry>
+	    <entry>0</entry>
+	    <entry>Invalid preset value.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_480P59_94</entry>
+	    <entry>1</entry>
+	    <entry>720x480 progressive video at 59.94 fps as per BT.1362.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_576P50</entry>
+	    <entry>2</entry>
+	    <entry>720x576 progressive video at 50 fps as per BT.1362.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_720P24</entry>
+	    <entry>3</entry>
+	    <entry>1280x720 progressive video at 24 fps as per SMPTE 296M.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_720P25</entry>
+	    <entry>4</entry>
+	    <entry>1280x720 progressive video at 25 fps as per SMPTE 296M.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_720P30</entry>
+	    <entry>5</entry>
+	    <entry>1280x720 progressive video at 30 fps as per SMPTE 296M.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_720P50</entry>
+	    <entry>6</entry>
+	    <entry>1280x720 progressive video at 50 fps as per SMPTE 296M.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_720P59_94</entry>
+	    <entry>7</entry>
+	    <entry>1280x720 progressive video at 59.94 fps as per SMPTE 274M.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_720P60</entry>
+	    <entry>8</entry>
+	    <entry>1280x720 progressive video at 60 fps as per SMPTE 274M/296M.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_1080I29_97</entry>
+	    <entry>9</entry>
+	    <entry>1920x1080 interlaced video at 29.97 fps as per BT.1120/SMPTE 274M.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_1080I30</entry>
+	    <entry>10</entry>
+	    <entry>1920x1080 interlaced video at 30 fps as per BT.1120/SMPTE 274M.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_1080I25</entry>
+	    <entry>11</entry>
+	    <entry>1920x1080 interlaced video at 25 fps as per BT.1120.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_1080I50</entry>
+	    <entry>12</entry>
+	    <entry>1920x1080 interlaced video at 50 fps as per SMPTE 296M.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_1080I60</entry>
+	    <entry>13</entry>
+	    <entry>1920x1080 interlaced video at 60 fps as per SMPTE 296M.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_1080P24</entry>
+	    <entry>14</entry>
+	    <entry>1920x1080 progressive video at 24 fps as per SMPTE 296M.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_1080P25</entry>
+	    <entry>15</entry>
+	    <entry>1920x1080 progressive video at 25 fps as per SMPTE 296M.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_1080P30</entry>
+	    <entry>16</entry>
+	    <entry>1920x1080 progressive video at 30 fps as per SMPTE 296M.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_1080P50</entry>
+	    <entry>17</entry>
+	    <entry>1920x1080 progressive video at 50 fps as per BT.1120.</entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_1080P60</entry>
+	    <entry>18</entry>
+	    <entry>1920x1080 progressive video at 60 fps as per BT.1120.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+  </refsect1>
+
+  <refsect1>
+    &return-value;
+
+    <variablelist>
+      <varlistentry>
+	<term><errorcode>EINVAL</errorcode></term>
+	<listitem>
+	  <para>The &v4l2-dv-enum-preset; <structfield>index</structfield>
+is out of bounds.</para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+</refentry>
+
+<!--
+Local Variables:
+mode: sgml
+sgml-parent-document: "v4l2.sgml"
+indent-tabs-mode: nil
+End:
+-->

Documentation/DocBook/v4l/vidioc-enuminput.xml

@@ -124,7 +124,13 @@ current input.</entry>
 	  </row>
 	  <row>
 	    <entry>__u32</entry>
-	    <entry><structfield>reserved</structfield>[4]</entry>
+	    <entry><structfield>capabilities</structfield></entry>
+	    <entry>This field provides capabilities for the
+input. See <xref linkend="input-capabilities" /> for flags.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>reserved</structfield>[3]</entry>
 	    <entry>Reserved for future extensions. Drivers must set
 the array to zero.</entry>
 	  </row>
@@ -261,6 +267,34 @@ flag is set Macrovision has been detected.</entry>
 	</tbody>
       </tgroup>
     </table>
+
+    <!-- Capability flags based on video timings RFC by Muralidharan
+Karicheri, titled RFC (v1.2): V4L - Support for video timings at the
+input/output interface to linux-media@vger.kernel.org on 19 Oct 2009.
+	-->
+    <table frame="none" pgwide="1" id="input-capabilities">
+      <title>Input capabilities</title>
+      <tgroup cols="3">
+	&cs-def;
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>V4L2_IN_CAP_PRESETS</constant></entry>
+	    <entry>0x00000001</entry>
+	    <entry>This input supports setting DV presets by using VIDIOC_S_DV_PRESET.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>V4L2_OUT_CAP_CUSTOM_TIMINGS</constant></entry>
+	    <entry>0x00000002</entry>
+	    <entry>This input supports setting custom video timings by using VIDIOC_S_DV_TIMINGS.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>V4L2_IN_CAP_STD</constant></entry>
+	    <entry>0x00000004</entry>
+	    <entry>This input supports setting the TV standard by using VIDIOC_S_STD.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
   </refsect1>
 
   <refsect1>

Documentation/DocBook/v4l/vidioc-enumoutput.xml

@@ -114,7 +114,13 @@ details on video standards and how to switch see <xref
 	  </row>
 	  <row>
 	    <entry>__u32</entry>
-	    <entry><structfield>reserved</structfield>[4]</entry>
+	    <entry><structfield>capabilities</structfield></entry>
+	    <entry>This field provides capabilities for the
+output. See <xref linkend="output-capabilities" /> for flags.</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>reserved</structfield>[3]</entry>
 	    <entry>Reserved for future extensions. Drivers must set
 the array to zero.</entry>
 	  </row>
@@ -147,6 +153,34 @@ CVBS, S-Video, RGB.</entry>
       </tgroup>
     </table>
 
+    <!-- Capabilities flags based on video timings RFC by Muralidharan
+Karicheri, titled RFC (v1.2): V4L - Support for video timings at the
+input/output interface to linux-media@vger.kernel.org on 19 Oct 2009.
+	-->
+    <table frame="none" pgwide="1" id="output-capabilities">
+      <title>Output capabilities</title>
+      <tgroup cols="3">
+	&cs-def;
+	<tbody valign="top">
+	  <row>
+	    <entry><constant>V4L2_OUT_CAP_PRESETS</constant></entry>
+	    <entry>0x00000001</entry>
+	    <entry>This output supports setting DV presets by using VIDIOC_S_DV_PRESET.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>V4L2_OUT_CAP_CUSTOM_TIMINGS</constant></entry>
+	    <entry>0x00000002</entry>
+	    <entry>This output supports setting custom video timings by using VIDIOC_S_DV_TIMINGS.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>V4L2_OUT_CAP_STD</constant></entry>
+	    <entry>0x00000004</entry>
+	    <entry>This output supports setting the TV standard by using VIDIOC_S_STD.</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
   </refsect1>
   <refsect1>
     &return-value;

Documentation/DocBook/v4l/vidioc-g-dv-preset.xml

@@ -0,0 +1,111 @@
+<refentry id="vidioc-g-dv-preset">
+  <refmeta>
+    <refentrytitle>ioctl VIDIOC_G_DV_PRESET, VIDIOC_S_DV_PRESET</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>VIDIOC_G_DV_PRESET</refname>
+    <refname>VIDIOC_S_DV_PRESET</refname>
+    <refpurpose>Query or select the DV preset of the current input or output</refpurpose>
+  </refnamediv>
+
+  <refsynopsisdiv>
+    <funcsynopsis>
+      <funcprototype>
+	<funcdef>int <function>ioctl</function></funcdef>
+	<paramdef>int <parameter>fd</parameter></paramdef>
+	<paramdef>int <parameter>request</parameter></paramdef>
+	<paramdef>&v4l2-dv-preset;
+*<parameter>argp</parameter></paramdef>
+      </funcprototype>
+    </funcsynopsis>
+  </refsynopsisdiv>
+
+  <refsect1>
+    <title>Arguments</title>
+
+    <variablelist>
+      <varlistentry>
+	<term><parameter>fd</parameter></term>
+	<listitem>
+	  <para>&fd;</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>request</parameter></term>
+	<listitem>
+	  <para>VIDIOC_G_DV_PRESET, VIDIOC_S_DV_PRESET</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>argp</parameter></term>
+	<listitem>
+	  <para></para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Description</title>
+    <para>To query and select the current DV preset, applications
+use the <constant>VIDIOC_G_DV_PRESET</constant> and <constant>VIDIOC_S_DV_PRESET</constant>
+ioctls which take a pointer to a &v4l2-dv-preset; type as argument.
+Applications must zero the reserved array in &v4l2-dv-preset;.
+<constant>VIDIOC_G_DV_PRESET</constant> returns a dv preset in the field
+<structfield>preset</structfield> of &v4l2-dv-preset;.</para>
+
+    <para><constant>VIDIOC_S_DV_PRESET</constant> accepts a pointer to a &v4l2-dv-preset;
+that has the preset value to be set. Applications must zero the reserved array in &v4l2-dv-preset;.
+If the preset is not supported, it returns an &EINVAL; </para>
+  </refsect1>
+
+  <refsect1>
+    &return-value;
+
+    <variablelist>
+      <varlistentry>
+	<term><errorcode>EINVAL</errorcode></term>
+	<listitem>
+	  <para>This ioctl is not supported, or the
+<constant>VIDIOC_S_DV_PRESET</constant>,<constant>VIDIOC_S_DV_PRESET</constant> parameter was unsuitable.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><errorcode>EBUSY</errorcode></term>
+	<listitem>
+	  <para>The device is busy and therefore can not change the preset.</para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+
+    <table pgwide="1" frame="none" id="v4l2-dv-preset">
+      <title>struct <structname>v4l2_dv_preset</structname></title>
+      <tgroup cols="3">
+	&cs-str;
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>preset</structfield></entry>
+	    <entry>Preset value to represent the digital video timings</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>reserved[4]</structfield></entry>
+	    <entry>Reserved fields for future use</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+  </refsect1>
+</refentry>
+
+<!--
+Local Variables:
+mode: sgml
+sgml-parent-document: "v4l2.sgml"
+indent-tabs-mode: nil
+End:
+-->

Documentation/DocBook/v4l/vidioc-g-dv-timings.xml

@@ -0,0 +1,224 @@
+<refentry id="vidioc-g-dv-timings">
+  <refmeta>
+    <refentrytitle>ioctl VIDIOC_G_DV_TIMINGS, VIDIOC_S_DV_TIMINGS</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>VIDIOC_G_DV_TIMINGS</refname>
+    <refname>VIDIOC_S_DV_TIMINGS</refname>
+    <refpurpose>Get or set custom DV timings for input or output</refpurpose>
+  </refnamediv>
+
+  <refsynopsisdiv>
+    <funcsynopsis>
+      <funcprototype>
+	<funcdef>int <function>ioctl</function></funcdef>
+	<paramdef>int <parameter>fd</parameter></paramdef>
+	<paramdef>int <parameter>request</parameter></paramdef>
+	<paramdef>&v4l2-dv-timings;
+*<parameter>argp</parameter></paramdef>
+      </funcprototype>
+    </funcsynopsis>
+  </refsynopsisdiv>
+
+  <refsect1>
+    <title>Arguments</title>
+
+    <variablelist>
+      <varlistentry>
+	<term><parameter>fd</parameter></term>
+	<listitem>
+	  <para>&fd;</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>request</parameter></term>
+	<listitem>
+	  <para>VIDIOC_G_DV_TIMINGS, VIDIOC_S_DV_TIMINGS</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>argp</parameter></term>
+	<listitem>
+	  <para></para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Description</title>
+    <para>To set custom DV timings for the input or output, applications use the
+<constant>VIDIOC_S_DV_TIMINGS</constant> ioctl and to get the current custom timings,
+applications use the <constant>VIDIOC_G_DV_TIMINGS</constant> ioctl. The detailed timing
+information is filled in using the structure &v4l2-dv-timings;. These ioctls take
+a pointer to the &v4l2-dv-timings; structure as argument. If the ioctl is not supported
+or the timing values are not correct, the driver returns &EINVAL;.</para>
+  </refsect1>
+
+  <refsect1>
+    &return-value;
+
+    <variablelist>
+      <varlistentry>
+	<term><errorcode>EINVAL</errorcode></term>
+	<listitem>
+	  <para>This ioctl is not supported, or the
+<constant>VIDIOC_S_DV_TIMINGS</constant> parameter was unsuitable.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><errorcode>EBUSY</errorcode></term>
+	<listitem>
+	  <para>The device is busy and therefore can not change the timings.</para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+
+    <table pgwide="1" frame="none" id="v4l2-bt-timings">
+      <title>struct <structname>v4l2_bt_timings</structname></title>
+      <tgroup cols="3">
+	&cs-str;
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>width</structfield></entry>
+	    <entry>Width of the active video in pixels</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>height</structfield></entry>
+	    <entry>Height of the active video in lines</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>interlaced</structfield></entry>
+	    <entry>Progressive (0) or interlaced (1)</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>polarities</structfield></entry>
+	    <entry>This is a bit mask that defines polarities of sync signals.
+bit 0 (V4L2_DV_VSYNC_POS_POL) is for vertical sync polarity and bit 1 (V4L2_DV_HSYNC_POS_POL) is for horizontal sync polarity. If the bit is set
+(1) it is positive polarity and if is cleared (0), it is negative polarity.</entry>
+	  </row>
+	  <row>
+	    <entry>__u64</entry>
+	    <entry><structfield>pixelclock</structfield></entry>
+	    <entry>Pixel clock in Hz. Ex. 74.25MHz->74250000</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>hfrontporch</structfield></entry>
+	    <entry>Horizontal front porch in pixels</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>hsync</structfield></entry>
+	    <entry>Horizontal sync length in pixels</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>hbackporch</structfield></entry>
+	    <entry>Horizontal back porch in pixels</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>vfrontporch</structfield></entry>
+	    <entry>Vertical front porch in lines</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>vsync</structfield></entry>
+	    <entry>Vertical sync length in lines</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>vbackporch</structfield></entry>
+	    <entry>Vertical back porch in lines</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>il_vfrontporch</structfield></entry>
+	    <entry>Vertical front porch in lines for bottom field of interlaced field formats</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>il_vsync</structfield></entry>
+	    <entry>Vertical sync length in lines for bottom field of interlaced field formats</entry>
+	  </row>
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>il_vbackporch</structfield></entry>
+	    <entry>Vertical back porch in lines for bottom field of interlaced field formats</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="v4l2-dv-timings">
+      <title>struct <structname>v4l2_dv_timings</structname></title>
+      <tgroup cols="4">
+	&cs-str;
+	<tbody valign="top">
+	  <row>
+	    <entry>__u32</entry>
+	    <entry><structfield>type</structfield></entry>
+	    <entry></entry>
+	    <entry>Type of DV timings as listed in <xref linkend="dv-timing-types"/>.</entry>
+	  </row>
+	  <row>
+	    <entry>union</entry>
+	    <entry><structfield></structfield></entry>
+	    <entry></entry>
+	  </row>
+	  <row>
+	    <entry></entry>
+	    <entry>&v4l2-bt-timings;</entry>
+	    <entry><structfield>bt</structfield></entry>
+	    <entry>Timings defined by BT.656/1120 specifications</entry>
+	  </row>
+	  <row>
+	    <entry></entry>
+	    <entry>__u32</entry>
+	    <entry><structfield>reserved</structfield>[32]</entry>
+	    <entry></entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+
+    <table pgwide="1" frame="none" id="dv-timing-types">
+      <title>DV Timing types</title>
+      <tgroup cols="3">
+	&cs-str;
+	<tbody valign="top">
+	  <row>
+	    <entry>Timing type</entry>
+	    <entry>value</entry>
+	    <entry>Description</entry>
+	  </row>
+	  <row>
+	    <entry></entry>
+	    <entry></entry>
+	    <entry></entry>
+	  </row>
+	  <row>
+	    <entry>V4L2_DV_BT_656_1120</entry>
+	    <entry>0</entry>
+	    <entry>BT.656/1120 timings</entry>
+	  </row>
+	</tbody>
+      </tgroup>
+    </table>
+  </refsect1>
+</refentry>
+
+<!--
+Local Variables:
+mode: sgml
+sgml-parent-document: "v4l2.sgml"
+indent-tabs-mode: nil
+End:
+-->

Documentation/DocBook/v4l/vidioc-g-std.xml

@@ -86,6 +86,12 @@ standards.</para>
 <constant>VIDIOC_S_STD</constant> parameter was unsuitable.</para>
 	</listitem>
       </varlistentry>
+      <varlistentry>
+	<term><errorcode>EBUSY</errorcode></term>
+	<listitem>
+	  <para>The device is busy and therefore can not change the standard</para>
+	</listitem>
+      </varlistentry>
     </variablelist>
   </refsect1>
 </refentry>

Documentation/DocBook/v4l/vidioc-qbuf.xml

@@ -54,12 +54,10 @@ to enqueue an empty (capturing) or filled (output) buffer in the
 driver's incoming queue. The semantics depend on the selected I/O
 method.</para>
 
-    <para>To enqueue a <link linkend="mmap">memory mapped</link>
-buffer applications set the <structfield>type</structfield> field of a
-&v4l2-buffer; to the same buffer type as previously &v4l2-format;
-<structfield>type</structfield> and &v4l2-requestbuffers;
-<structfield>type</structfield>, the <structfield>memory</structfield>
-field to <constant>V4L2_MEMORY_MMAP</constant> and the
+    <para>To enqueue a buffer applications set the <structfield>type</structfield>
+field of a &v4l2-buffer; to the same buffer type as was previously used
+with &v4l2-format; <structfield>type</structfield> and &v4l2-requestbuffers;
+<structfield>type</structfield>. Applications must also set the
 <structfield>index</structfield> field. Valid index numbers range from
 zero to the number of buffers allocated with &VIDIOC-REQBUFS;
 (&v4l2-requestbuffers; <structfield>count</structfield>) minus one. The
@@ -70,8 +68,19 @@ intended for output (<structfield>type</structfield> is
 <constant>V4L2_BUF_TYPE_VBI_OUTPUT</constant>) applications must also
 initialize the <structfield>bytesused</structfield>,
 <structfield>field</structfield> and
-<structfield>timestamp</structfield> fields. See <xref
-	linkend="buffer" /> for details. When
+<structfield>timestamp</structfield> fields, see <xref
+linkend="buffer" /> for details.
+Applications must also set <structfield>flags</structfield> to 0. If a driver
+supports capturing from specific video inputs and you want to specify a video
+input, then <structfield>flags</structfield> should be set to
+<constant>V4L2_BUF_FLAG_INPUT</constant> and the field
+<structfield>input</structfield> must be initialized to the desired input.
+The <structfield>reserved</structfield> field must be set to 0.
+</para>
+
+    <para>To enqueue a <link linkend="mmap">memory mapped</link>
+buffer applications set the <structfield>memory</structfield>
+field to <constant>V4L2_MEMORY_MMAP</constant>. When
 <constant>VIDIOC_QBUF</constant> is called with a pointer to this
 structure the driver sets the
 <constant>V4L2_BUF_FLAG_MAPPED</constant> and
@@ -81,14 +90,10 @@ structure the driver sets the
 &EINVAL;.</para>
 
     <para>To enqueue a <link linkend="userp">user pointer</link>
-buffer applications set the <structfield>type</structfield> field of a
-&v4l2-buffer; to the same buffer type as previously &v4l2-format;
-<structfield>type</structfield> and &v4l2-requestbuffers;
-<structfield>type</structfield>, the <structfield>memory</structfield>
-field to <constant>V4L2_MEMORY_USERPTR</constant> and the
+buffer applications set the <structfield>memory</structfield>
+field to <constant>V4L2_MEMORY_USERPTR</constant>, the
 <structfield>m.userptr</structfield> field to the address of the
-buffer and <structfield>length</structfield> to its size. When the
-buffer is intended for output additional fields must be set as above.
+buffer and <structfield>length</structfield> to its size.
 When <constant>VIDIOC_QBUF</constant> is called with a pointer to this
 structure the driver sets the <constant>V4L2_BUF_FLAG_QUEUED</constant>
 flag and clears the <constant>V4L2_BUF_FLAG_MAPPED</constant> and
@@ -96,13 +101,14 @@ flag and clears the <constant>V4L2_BUF_FLAG_MAPPED</constant> and
 <structfield>flags</structfield> field, or it returns an error code.
 This ioctl locks the memory pages of the buffer in physical memory,
 they cannot be swapped out to disk. Buffers remain locked until
-dequeued, until the &VIDIOC-STREAMOFF; or &VIDIOC-REQBUFS; ioctl are
+dequeued, until the &VIDIOC-STREAMOFF; or &VIDIOC-REQBUFS; ioctl is
 called, or until the device is closed.</para>
 
     <para>Applications call the <constant>VIDIOC_DQBUF</constant>
 ioctl to dequeue a filled (capturing) or displayed (output) buffer
 from the driver's outgoing queue. They just set the
-<structfield>type</structfield> and <structfield>memory</structfield>
+<structfield>type</structfield>, <structfield>memory</structfield>
+and <structfield>reserved</structfield>
 fields of a &v4l2-buffer; as above, when <constant>VIDIOC_DQBUF</constant>
 is called with a pointer to this structure the driver fills the
 remaining fields or returns an error code.</para>

Documentation/DocBook/v4l/vidioc-query-dv-preset.xml

@@ -0,0 +1,85 @@
+<refentry id="vidioc-query-dv-preset">
+  <refmeta>
+    <refentrytitle>ioctl VIDIOC_QUERY_DV_PRESET</refentrytitle>
+    &manvol;
+  </refmeta>
+
+  <refnamediv>
+    <refname>VIDIOC_QUERY_DV_PRESET</refname>
+    <refpurpose>Sense the DV preset received by the current
+input</refpurpose>
+  </refnamediv>
+
+  <refsynopsisdiv>
+    <funcsynopsis>
+      <funcprototype>
+	<funcdef>int <function>ioctl</function></funcdef>
+	<paramdef>int <parameter>fd</parameter></paramdef>
+	<paramdef>int <parameter>request</parameter></paramdef>
+	<paramdef>&v4l2-dv-preset; *<parameter>argp</parameter></paramdef>
+      </funcprototype>
+    </funcsynopsis>
+  </refsynopsisdiv>
+
+  <refsect1>
+    <title>Arguments</title>
+
+    <variablelist>
+	<varlistentry>
+	<term><parameter>fd</parameter></term>
+	<listitem>
+	  <para>&fd;</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>request</parameter></term>
+	<listitem>
+	  <para>VIDIOC_QUERY_DV_PRESET</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><parameter>argp</parameter></term>
+	<listitem>
+	  <para></para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Description</title>
+
+    <para>The hardware may be able to detect the current DV preset
+automatically, similar to sensing the video standard. To do so, applications
+call <constant> VIDIOC_QUERY_DV_PRESET</constant> with a pointer to a
+&v4l2-dv-preset; type. Once the hardware detects a preset, that preset is
+returned in the preset field of &v4l2-dv-preset;. When detection is not
+possible or fails, the value V4L2_DV_INVALID is returned.</para>
+  </refsect1>
+
+  <refsect1>
+    &return-value;
+    <variablelist>
+      <varlistentry>
+	<term><errorcode>EINVAL</errorcode></term>
+	<listitem>
+	  <para>This ioctl is not supported.</para>
+	</listitem>
+    </varlistentry>
+      <varlistentry>
+	<term><errorcode>EBUSY</errorcode></term>
+	<listitem>
+	  <para>The device is busy and therefore can not sense the preset</para>
+	</listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+</refentry>
+
+<!--
+Local Variables:
+mode: sgml
+sgml-parent-document: "v4l2.sgml"
+indent-tabs-mode: nil
+End:
+-->

Documentation/DocBook/v4l/vidioc-querybuf.xml

@@ -54,12 +54,13 @@ buffer at any time after buffers have been allocated with the
 &VIDIOC-REQBUFS; ioctl.</para>
 
     <para>Applications set the <structfield>type</structfield> field
-    of a &v4l2-buffer; to the same buffer type as previously
+    of a &v4l2-buffer; to the same buffer type as was previously used with
 &v4l2-format; <structfield>type</structfield> and &v4l2-requestbuffers;
 <structfield>type</structfield>, and the <structfield>index</structfield>
     field. Valid index numbers range from zero
 to the number of buffers allocated with &VIDIOC-REQBUFS;
     (&v4l2-requestbuffers; <structfield>count</structfield>) minus one.
+The <structfield>reserved</structfield> field should to set to 0.
 After calling <constant>VIDIOC_QUERYBUF</constant> with a pointer to
     this structure drivers return an error code or fill the rest of
 the structure.</para>
@@ -68,8 +69,8 @@ the structure.</para>
 <constant>V4L2_BUF_FLAG_MAPPED</constant>,
 <constant>V4L2_BUF_FLAG_QUEUED</constant> and
 <constant>V4L2_BUF_FLAG_DONE</constant> flags will be valid. The
-<structfield>memory</structfield> field will be set to
-<constant>V4L2_MEMORY_MMAP</constant>, the <structfield>m.offset</structfield>
+<structfield>memory</structfield> field will be set to the current
+I/O method, the <structfield>m.offset</structfield>
 contains the offset of the buffer from the start of the device memory,
 the <structfield>length</structfield> field its size. The driver may
 or may not set the remaining fields and flags, they are meaningless in

Documentation/DocBook/v4l/vidioc-querystd.xml

@@ -70,6 +70,12 @@ current video input or output.</para>
 	  <para>This ioctl is not supported.</para>
 	</listitem>
       </varlistentry>
+      <varlistentry>
+	<term><errorcode>EBUSY</errorcode></term>
+	<listitem>
+	  <para>The device is busy and therefore can not detect the standard</para>
+	</listitem>
+      </varlistentry>
     </variablelist>
   </refsect1>
 </refentry>

Documentation/DocBook/v4l/vidioc-reqbufs.xml

@@ -54,23 +54,23 @@ I/O. Memory mapped buffers are located in device memory and must be
 allocated with this ioctl before they can be mapped into the
 application's address space. User buffers are allocated by
 applications themselves, and this ioctl is merely used to switch the
-driver into user pointer I/O mode.</para>
+driver into user pointer I/O mode and to setup some internal structures.</para>
 
-    <para>To allocate device buffers applications initialize three
-fields of a <structname>v4l2_requestbuffers</structname> structure.
+    <para>To allocate device buffers applications initialize all
+fields of the <structname>v4l2_requestbuffers</structname> structure.
 They set the <structfield>type</structfield> field to the respective
 stream or buffer type, the <structfield>count</structfield> field to
-the desired number of buffers, and <structfield>memory</structfield>
-must be set to <constant>V4L2_MEMORY_MMAP</constant>. When the ioctl
-is called with a pointer to this structure the driver attempts to
-allocate the requested number of buffers and stores the actual number
+the desired number of buffers, <structfield>memory</structfield>
+must be set to the requested I/O method and the reserved array
+must be zeroed. When the ioctl
+is called with a pointer to this structure the driver will attempt to allocate
+the requested number of buffers and it stores the actual number
 allocated in the <structfield>count</structfield> field. It can be
 smaller than the number requested, even zero, when the driver runs out
-of free memory. A larger number is possible when the driver requires
-more buffers to function correctly.<footnote>
-	<para>For example video output requires at least two buffers,
+of free memory. A larger number is also possible when the driver requires
+more buffers to function correctly. For example video output requires at least two buffers,
 one displayed and one filled by the application.</para>
-	</footnote> When memory mapping I/O is not supported the ioctl
+    <para>When the I/O method is not supported the ioctl
 returns an &EINVAL;.</para>
 
     <para>Applications can call <constant>VIDIOC_REQBUFS</constant>
@@ -81,14 +81,6 @@ in progress, an implicit &VIDIOC-STREAMOFF;. <!-- mhs: I see no
 reason why munmap()ping one or even all buffers must imply
 streamoff.--></para>
 
-    <para>To negotiate user pointer I/O, applications initialize only
-the <structfield>type</structfield> field and set
-<structfield>memory</structfield> to
-<constant>V4L2_MEMORY_USERPTR</constant>. When the ioctl is called
-with a pointer to this structure the driver prepares for user pointer
-I/O, when this I/O method is not supported the ioctl returns an
-&EINVAL;.</para>
-
     <table pgwide="1" frame="none" id="v4l2-requestbuffers">
       <title>struct <structname>v4l2_requestbuffers</structname></title>
       <tgroup cols="3">
@@ -97,9 +89,7 @@ I/O, when this I/O method is not supported the ioctl returns an
 	  <row>
 	    <entry>__u32</entry>
 	    <entry><structfield>count</structfield></entry>
-	    <entry>The number of buffers requested or granted. This
-field is only used when <structfield>memory</structfield> is set to
-<constant>V4L2_MEMORY_MMAP</constant>.</entry>
+	    <entry>The number of buffers requested or granted.</entry>
 	  </row>
 	  <row>
 	    <entry>&v4l2-buf-type;</entry>
@@ -120,7 +110,7 @@ as the &v4l2-format; <structfield>type</structfield> field. See <xref
 	    <entry><structfield>reserved</structfield>[2]</entry>
 	    <entry>A place holder for future extensions and custom
 (driver defined) buffer types <constant>V4L2_BUF_TYPE_PRIVATE</constant> and
-higher.</entry>
+higher. This array should be zeroed by applications.</entry>
 	  </row>
 	</tbody>
       </tgroup>

Documentation/IO-mapping.txt

@@ -157,7 +157,7 @@ For such memory, you can do things like
 	 * access only the 640k-1MB area, so anything else
 	 * has to be remapped.
 	 */
-	char * baseptr = ioremap(0xFC000000, 1024*1024);
+	void __iomem *baseptr = ioremap(0xFC000000, 1024*1024);
 
 	/* write a 'A' to the offset 10 of the area */
 	writeb('A',baseptr+10);

Documentation/RCU/00-INDEX

@@ -6,16 +6,22 @@ checklist.txt
 	- Review Checklist for RCU Patches
 listRCU.txt
 	- Using RCU to Protect Read-Mostly Linked Lists
+lockdep.txt
+	- RCU and lockdep checking
 NMI-RCU.txt
 	- Using RCU to Protect Dynamic NMI Handlers
+rcubarrier.txt
+	- RCU and Unloadable Modules
+rculist_nulls.txt
+	- RCU list primitives for use with SLAB_DESTROY_BY_RCU
 rcuref.txt
 	- Reference-count design for elements of lists/arrays protected by RCU
 rcu.txt
 	- RCU Concepts
-rcubarrier.txt
-	- Unloading modules that use RCU callbacks
 RTFP.txt
 	- List of RCU papers (bibliography) going back to 1980.
+stallwarn.txt
+	- RCU CPU stall warnings (CONFIG_RCU_CPU_STALL_DETECTOR)
 torture.txt
 	- RCU Torture Test Operation (CONFIG_RCU_TORTURE_TEST)
 trace.txt

Documentation/RCU/RTFP.txt

@@ -25,10 +25,10 @@ to be referencing the data structure.  However, this mechanism was not
 optimized for modern computer systems, which is not surprising given
 that these overheads were not so expensive in the mid-80s.  Nonetheless,
 passive serialization appears to be the first deferred-destruction
-mechanism to be used in production.  Furthermore, the relevant patent has
-lapsed, so this approach may be used in non-GPL software, if desired.
-(In contrast, use of RCU is permitted only in software licensed under
-GPL.  Sorry!!!)
+mechanism to be used in production.  Furthermore, the relevant patent
+has lapsed, so this approach may be used in non-GPL software, if desired.
+(In contrast, implementation of RCU is permitted only in software licensed
+under either GPL or LGPL.  Sorry!!!)
 
 In 1990, Pugh [Pugh90] noted that explicitly tracking which threads
 were reading a given data structure permitted deferred free to operate
@@ -150,6 +150,18 @@ preemptible RCU [PaulEMcKenney2007PreemptibleRCU], and the three-part
 LWN "What is RCU?" series [PaulEMcKenney2007WhatIsRCUFundamentally,
 PaulEMcKenney2008WhatIsRCUUsage, and PaulEMcKenney2008WhatIsRCUAPI].
 
+2008 saw a journal paper on real-time RCU [DinakarGuniguntala2008IBMSysJ],
+a history of how Linux changed RCU more than RCU changed Linux
+[PaulEMcKenney2008RCUOSR], and a design overview of hierarchical RCU
+[PaulEMcKenney2008HierarchicalRCU].
+
+2009 introduced user-level RCU algorithms [PaulEMcKenney2009MaliciousURCU],
+which Mathieu Desnoyers is now maintaining [MathieuDesnoyers2009URCU]
+[MathieuDesnoyersPhD].  TINY_RCU [PaulEMcKenney2009BloatWatchRCU] made
+its appearance, as did expedited RCU [PaulEMcKenney2009expeditedRCU].
+The problem of resizeable RCU-protected hash tables may now be on a path
+to a solution [JoshTriplett2009RPHash].
+
 Bibtex Entries
 
 @article{Kung80
@@ -730,6 +742,11 @@ Revised:
 "
 }
 
+#
+#	"What is RCU?" LWN series.
+#
+########################################################################
+
 @article{DinakarGuniguntala2008IBMSysJ
 ,author="D. Guniguntala and P. E. McKenney and J. Triplett and J. Walpole"
 ,title="The read-copy-update mechanism for supporting real-time applications on shared-memory multiprocessor systems with {Linux}"
@@ -820,3 +837,39 @@ Revised:
 	Uniprocessor assumptions allow simplified RCU implementation.
 "
 }
+
+@unpublished{PaulEMcKenney2009expeditedRCU
+,Author="Paul E. McKenney"
+,Title="[{PATCH} -tip 0/3] expedited 'big hammer' {RCU} grace periods"
+,month="June"
+,day="25"
+,year="2009"
+,note="Available:
+\url{http://lkml.org/lkml/2009/6/25/306}
+[Viewed August 16, 2009]"
+,annotation="
+	First posting of expedited RCU to be accepted into -tip.
+"
+}
+
+@unpublished{JoshTriplett2009RPHash
+,Author="Josh Triplett"
+,Title="Scalable concurrent hash tables via relativistic programming"
+,month="September"
+,year="2009"
+,note="Linux Plumbers Conference presentation"
+,annotation="
+	RP fun with hash tables.
+"
+}
+
+@phdthesis{MathieuDesnoyersPhD
+, title  = "Low-Impact Operating System Tracing"
+, author = "Mathieu Desnoyers"
+, school = "Ecole Polytechnique de Montr\'{e}al"
+, month  = "December"
+, year   = 2009
+,note="Available:
+\url{http://www.lttng.org/pub/thesis/desnoyers-dissertation-2009-12.pdf}
+[Viewed December 9, 2009]"
+}

Documentation/RCU/checklist.txt

@@ -8,13 +8,12 @@ would cause.  This list is based on experiences reviewing such patches
 over a rather long period of time, but improvements are always welcome!
 
 0.	Is RCU being applied to a read-mostly situation?  If the data
-	structure is updated more than about 10% of the time, then
-	you should strongly consider some other approach, unless
-	detailed performance measurements show that RCU is nonetheless
-	the right tool for the job.  Yes, you might think of RCU
-	as simply cutting overhead off of the readers and imposing it
-	on the writers.  That is exactly why normal uses of RCU will
-	do much more reading than updating.
+	structure is updated more than about 10% of the time, then you
+	should strongly consider some other approach, unless detailed
+	performance measurements show that RCU is nonetheless the right
+	tool for the job.  Yes, RCU does reduce read-side overhead by
+	increasing write-side overhead, which is exactly why normal uses
+	of RCU will do much more reading than updating.
 
 	Another exception is where performance is not an issue, and RCU
 	provides a simpler implementation.  An example of this situation
@@ -35,13 +34,13 @@ over a rather long period of time, but improvements are always welcome!
 
 	If you choose #b, be prepared to describe how you have handled
 	memory barriers on weakly ordered machines (pretty much all of
-	them -- even x86 allows reads to be reordered), and be prepared
-	to explain why this added complexity is worthwhile.  If you
-	choose #c, be prepared to explain how this single task does not
-	become a major bottleneck on big multiprocessor machines (for
-	example, if the task is updating information relating to itself
-	that other tasks can read, there by definition can be no
-	bottleneck).
+	them -- even x86 allows later loads to be reordered to precede
+	earlier stores), and be prepared to explain why this added
+	complexity is worthwhile.  If you choose #c, be prepared to
+	explain how this single task does not become a major bottleneck on
+	big multiprocessor machines (for example, if the task is updating
+	information relating to itself that other tasks can read, there
+	by definition can be no bottleneck).
 
 2.	Do the RCU read-side critical sections make proper use of
 	rcu_read_lock() and friends?  These primitives are needed
@@ -51,8 +50,10 @@ over a rather long period of time, but improvements are always welcome!
 	actuarial risk of your kernel.
 
 	As a rough rule of thumb, any dereference of an RCU-protected
-	pointer must be covered by rcu_read_lock() or rcu_read_lock_bh()
-	or by the appropriate update-side lock.
+	pointer must be covered by rcu_read_lock(), rcu_read_lock_bh(),
+	rcu_read_lock_sched(), or by the appropriate update-side lock.
+	Disabling of preemption can serve as rcu_read_lock_sched(), but
+	is less readable.
 
 3.	Does the update code tolerate concurrent accesses?
 
@@ -62,25 +63,27 @@ over a rather long period of time, but improvements are always welcome!
 	of ways to handle this concurrency, depending on the situation:
 
 	a.	Use the RCU variants of the list and hlist update
-		primitives to add, remove, and replace elements on an
-		RCU-protected list.  Alternatively, use the RCU-protected
-		trees that have been added to the Linux kernel.
+		primitives to add, remove, and replace elements on
+		an RCU-protected list.	Alternatively, use the other
+		RCU-protected data structures that have been added to
+		the Linux kernel.
 
 		This is almost always the best approach.
 
 	b.	Proceed as in (a) above, but also maintain per-element
 		locks (that are acquired by both readers and writers)
 		that guard per-element state.  Of course, fields that
-		the readers refrain from accessing can be guarded by the
-		update-side lock.
+		the readers refrain from accessing can be guarded by
+		some other lock acquired only by updaters, if desired.
 
 		This works quite well, also.
 
 	c.	Make updates appear atomic to readers.  For example,
-		pointer updates to properly aligned fields will appear
-		atomic, as will individual atomic primitives.  Operations
-		performed under a lock and sequences of multiple atomic
-		primitives will -not- appear to be atomic.
+		pointer updates to properly aligned fields will
+		appear atomic, as will individual atomic primitives.
+		Sequences of perations performed under a lock will -not-
+		appear to be atomic to RCU readers, nor will sequences
+		of multiple atomic primitives.
 
 		This can work, but is starting to get a bit tricky.
 
@@ -98,9 +101,9 @@ over a rather long period of time, but improvements are always welcome!
 		a new structure containing updated values.
 
 4.	Weakly ordered CPUs pose special challenges.  Almost all CPUs
-	are weakly ordered -- even i386 CPUs allow reads to be reordered.
-	RCU code must take all of the following measures to prevent
-	memory-corruption problems:
+	are weakly ordered -- even x86 CPUs allow later loads to be
+	reordered to precede earlier stores.  RCU code must take all of
+	the following measures to prevent memory-corruption problems:
 
 	a.	Readers must maintain proper ordering of their memory
 		accesses.  The rcu_dereference() primitive ensures that
@@ -113,14 +116,25 @@ over a rather long period of time, but improvements are always welcome!
 		The rcu_dereference() primitive is also an excellent
 		documentation aid, letting the person reading the code
 		know exactly which pointers are protected by RCU.
-
-		The rcu_dereference() primitive is used by the various
-		"_rcu()" list-traversal primitives, such as the
-		list_for_each_entry_rcu().  Note that it is perfectly
-		legal (if redundant) for update-side code to use
-		rcu_dereference() and the "_rcu()" list-traversal
-		primitives.  This is particularly useful in code
-		that is common to readers and updaters.
+		Please note that compilers can also reorder code, and
+		they are becoming increasingly aggressive about doing
+		just that.  The rcu_dereference() primitive therefore
+		also prevents destructive compiler optimizations.
+
+		The rcu_dereference() primitive is used by the
+		various "_rcu()" list-traversal primitives, such
+		as the list_for_each_entry_rcu().  Note that it is
+		perfectly legal (if redundant) for update-side code to
+		use rcu_dereference() and the "_rcu()" list-traversal
+		primitives.  This is particularly useful in code that
+		is common to readers and updaters.  However, lockdep
+		will complain if you access rcu_dereference() outside
+		of an RCU read-side critical section.  See lockdep.txt
+		to learn what to do about this.
+
+		Of course, neither rcu_dereference() nor the "_rcu()"
+		list-traversal primitives can substitute for a good
+		concurrency design coordinating among multiple updaters.
 
 	b.	If the list macros are being used, the list_add_tail_rcu()
 		and list_add_rcu() primitives must be used in order
@@ -135,11 +149,14 @@ over a rather long period of time, but improvements are always welcome!
 		readers.  Similarly, if the hlist macros are being used,
 		the hlist_del_rcu() primitive is required.
 
-		The list_replace_rcu() primitive may be used to
-		replace an old structure with a new one in an
-		RCU-protected list.
+		The list_replace_rcu() and hlist_replace_rcu() primitives
+		may be used to replace an old structure with a new one
+		in their respective types of RCU-protected lists.
+
+	d.	Rules similar to (4b) and (4c) apply to the "hlist_nulls"
+		type of RCU-protected linked lists.
 
-	d.	Updates must ensure that initialization of a given
+	e.	Updates must ensure that initialization of a given
 		structure happens before pointers to that structure are
 		publicized.  Use the rcu_assign_pointer() primitive
 		when publicizing a pointer to a structure that can
@@ -151,16 +168,31 @@ over a rather long period of time, but improvements are always welcome!
 	it cannot block.
 
 6.	Since synchronize_rcu() can block, it cannot be called from
-	any sort of irq context.  Ditto for synchronize_sched() and
-	synchronize_srcu().
-
-7.	If the updater uses call_rcu(), then the corresponding readers
-	must use rcu_read_lock() and rcu_read_unlock().  If the updater
-	uses call_rcu_bh(), then the corresponding readers must use
-	rcu_read_lock_bh() and rcu_read_unlock_bh().  If the updater
-	uses call_rcu_sched(), then the corresponding readers must
-	disable preemption.  Mixing things up will result in confusion
-	and broken kernels.
+	any sort of irq context.  The same rule applies for
+	synchronize_rcu_bh(), synchronize_sched(), synchronize_srcu(),
+	synchronize_rcu_expedited(), synchronize_rcu_bh_expedited(),
+	synchronize_sched_expedite(), and synchronize_srcu_expedited().
+
+	The expedited forms of these primitives have the same semantics
+	as the non-expedited forms, but expediting is both expensive
+	and unfriendly to real-time workloads.	Use of the expedited
+	primitives should be restricted to rare configuration-change
+	operations that would not normally be undertaken while a real-time
+	workload is running.
+
+7.	If the updater uses call_rcu() or synchronize_rcu(), then the
+	corresponding readers must use rcu_read_lock() and
+	rcu_read_unlock().  If the updater uses call_rcu_bh() or
+	synchronize_rcu_bh(), then the corresponding readers must
+	use rcu_read_lock_bh() and rcu_read_unlock_bh().  If the
+	updater uses call_rcu_sched() or synchronize_sched(), then
+	the corresponding readers must disable preemption, possibly
+	by calling rcu_read_lock_sched() and rcu_read_unlock_sched().
+	If the updater uses synchronize_srcu(), the the corresponding
+	readers must use srcu_read_lock() and srcu_read_unlock(),
+	and with the same srcu_struct.	The rules for the expedited
+	primitives are the same as for their non-expedited counterparts.
+	Mixing things up will result in confusion and broken kernels.
 
 	One exception to this rule: rcu_read_lock() and rcu_read_unlock()
 	may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh()
@@ -212,6 +244,8 @@ over a rather long period of time, but improvements are always welcome!
 	e.	Periodically invoke synchronize_rcu(), permitting a limited
 		number of updates per grace period.
 
+	The same cautions apply to call_rcu_bh() and call_rcu_sched().
+
 9.	All RCU list-traversal primitives, which include
 	rcu_dereference(), list_for_each_entry_rcu(),
 	list_for_each_continue_rcu(), and list_for_each_safe_rcu(),
@@ -219,7 +253,9 @@ over a rather long period of time, but improvements are always welcome!
 	must be protected by appropriate update-side locks.  RCU
 	read-side critical sections are delimited by rcu_read_lock()
 	and rcu_read_unlock(), or by similar primitives such as
-	rcu_read_lock_bh() and rcu_read_unlock_bh().
+	rcu_read_lock_bh() and rcu_read_unlock_bh(), in which case
+	the matching rcu_dereference() primitive must be used in order
+	to keep lockdep happy, in this case, rcu_dereference_bh().
 
 	The reason that it is permissible to use RCU list-traversal
 	primitives when the update-side lock is held is that doing so
@@ -229,7 +265,8 @@ over a rather long period of time, but improvements are always welcome!
 10.	Conversely, if you are in an RCU read-side critical section,
 	and you don't hold the appropriate update-side lock, you -must-
 	use the "_rcu()" variants of the list macros.  Failing to do so
-	will break Alpha and confuse people reading your code.
+	will break Alpha, cause aggressive compilers to generate bad code,
+	and confuse people trying to read your code.
 
 11.	Note that synchronize_rcu() -only- guarantees to wait until
 	all currently executing rcu_read_lock()-protected RCU read-side
@@ -239,15 +276,21 @@ over a rather long period of time, but improvements are always welcome!
 	rcu_read_lock()-protected read-side critical sections, do -not-
 	use synchronize_rcu().
 
-	If you want to wait for some of these other things, you might
-	instead need to use synchronize_irq() or synchronize_sched().
+	Similarly, disabling preemption is not an acceptable substitute
+	for rcu_read_lock().  Code that attempts to use preemption
+	disabling where it should be using rcu_read_lock() will break
+	in real-time kernel builds.
+
+	If you want to wait for interrupt handlers, NMI handlers, and
+	code under the influence of preempt_disable(), you instead
+	need to use synchronize_irq() or synchronize_sched().
 
 12.	Any lock acquired by an RCU callback must be acquired elsewhere
 	with softirq disabled, e.g., via spin_lock_irqsave(),
 	spin_lock_bh(), etc.  Failing to disable irq on a given
-	acquisition of that lock will result in deadlock as soon as the
-	RCU callback happens to interrupt that acquisition's critical
-	section.
+	acquisition of that lock will result in deadlock as soon as
+	the RCU softirq handler happens to run your RCU callback while
+	interrupting that acquisition's critical section.
 
 13.	RCU callbacks can be and are executed in parallel.  In many cases,
 	the callback code simply wrappers around kfree(), so that this
@@ -265,29 +308,30 @@ over a rather long period of time, but improvements are always welcome!
 	not the case, a self-spawning RCU callback would prevent the
 	victim CPU from ever going offline.)
 
-14.	SRCU (srcu_read_lock(), srcu_read_unlock(), and synchronize_srcu())
-	may only be invoked from process context.  Unlike other forms of
-	RCU, it -is- permissible to block in an SRCU read-side critical
-	section (demarked by srcu_read_lock() and srcu_read_unlock()),
-	hence the "SRCU": "sleepable RCU".  Please note that if you
-	don't need to sleep in read-side critical sections, you should
-	be using RCU rather than SRCU, because RCU is almost always
-	faster and easier to use than is SRCU.
+14.	SRCU (srcu_read_lock(), srcu_read_unlock(), srcu_dereference(),
+	synchronize_srcu(), and synchronize_srcu_expedited()) may only
+	be invoked from process context.  Unlike other forms of RCU, it
+	-is- permissible to block in an SRCU read-side critical section
+	(demarked by srcu_read_lock() and srcu_read_unlock()), hence the
+	"SRCU": "sleepable RCU".  Please note that if you don't need
+	to sleep in read-side critical sections, you should be using
+	RCU rather than SRCU, because RCU is almost always faster and
+	easier to use than is SRCU.
 
 	Also unlike other forms of RCU, explicit initialization
 	and cleanup is required via init_srcu_struct() and
 	cleanup_srcu_struct().	These are passed a "struct srcu_struct"
 	that defines the scope of a given SRCU domain.	Once initialized,
 	the srcu_struct is passed to srcu_read_lock(), srcu_read_unlock()
-	and synchronize_srcu().  A given synchronize_srcu() waits only
-	for SRCU read-side critical sections governed by srcu_read_lock()
-	and srcu_read_unlock() calls that have been passd the same
-	srcu_struct.  This property is what makes sleeping read-side
-	critical sections tolerable -- a given subsystem delays only
-	its own updates, not those of other subsystems using SRCU.
-	Therefore, SRCU is less prone to OOM the system than RCU would
-	be if RCU's read-side critical sections were permitted to
-	sleep.
+	synchronize_srcu(), and synchronize_srcu_expedited().  A given
+	synchronize_srcu() waits only for SRCU read-side critical
+	sections governed by srcu_read_lock() and srcu_read_unlock()
+	calls that have been passed the same srcu_struct.  This property
+	is what makes sleeping read-side critical sections tolerable --
+	a given subsystem delays only its own updates, not those of other
+	subsystems using SRCU.	Therefore, SRCU is less prone to OOM the
+	system than RCU would be if RCU's read-side critical sections
+	were permitted to sleep.
 
 	The ability to sleep in read-side critical sections does not
 	come for free.	First, corresponding srcu_read_lock() and
@@ -311,12 +355,12 @@ over a rather long period of time, but improvements are always welcome!
 	destructive operation, and -only- -then- invoke call_rcu(),
 	synchronize_rcu(), or friends.
 
-	Because these primitives only wait for pre-existing readers,
-	it is the caller's responsibility to guarantee safety to
-	any subsequent readers.
+	Because these primitives only wait for pre-existing readers, it
+	is the caller's responsibility to guarantee that any subsequent
+	readers will execute safely.
 
-16.	The various RCU read-side primitives do -not- contain memory
-	barriers.  The CPU (and in some cases, the compiler) is free
-	to reorder code into and out of RCU read-side critical sections.
-	It is the responsibility of the RCU update-side primitives to
-	deal with this.
+16.	The various RCU read-side primitives do -not- necessarily contain
+	memory barriers.  You should therefore plan for the CPU
+	and the compiler to freely reorder code into and out of RCU
+	read-side critical sections.  It is the responsibility of the
+	RCU update-side primitives to deal with this.

Documentation/RCU/lockdep.txt

@@ -0,0 +1,67 @@
+RCU and lockdep checking
+
+All flavors of RCU have lockdep checking available, so that lockdep is
+aware of when each task enters and leaves any flavor of RCU read-side
+critical section.  Each flavor of RCU is tracked separately (but note
+that this is not the case in 2.6.32 and earlier).  This allows lockdep's
+tracking to include RCU state, which can sometimes help when debugging
+deadlocks and the like.
+
+In addition, RCU provides the following primitives that check lockdep's
+state:
+
+	rcu_read_lock_held() for normal RCU.
+	rcu_read_lock_bh_held() for RCU-bh.
+	rcu_read_lock_sched_held() for RCU-sched.
+	srcu_read_lock_held() for SRCU.
+
+These functions are conservative, and will therefore return 1 if they
+aren't certain (for example, if CONFIG_DEBUG_LOCK_ALLOC is not set).
+This prevents things like WARN_ON(!rcu_read_lock_held()) from giving false
+positives when lockdep is disabled.
+
+In addition, a separate kernel config parameter CONFIG_PROVE_RCU enables
+checking of rcu_dereference() primitives:
+
+	rcu_dereference(p):
+		Check for RCU read-side critical section.
+	rcu_dereference_bh(p):
+		Check for RCU-bh read-side critical section.
+	rcu_dereference_sched(p):
+		Check for RCU-sched read-side critical section.
+	srcu_dereference(p, sp):
+		Check for SRCU read-side critical section.
+	rcu_dereference_check(p, c):
+		Use explicit check expression "c".
+	rcu_dereference_raw(p)
+		Don't check.  (Use sparingly, if at all.)
+
+The rcu_dereference_check() check expression can be any boolean
+expression, but would normally include one of the rcu_read_lock_held()
+family of functions and a lockdep expression.  However, any boolean
+expression can be used.  For a moderately ornate example, consider
+the following:
+
+	file = rcu_dereference_check(fdt->fd[fd],
+				     rcu_read_lock_held() ||
+				     lockdep_is_held(&files->file_lock) ||
+				     atomic_read(&files->count) == 1);
+
+This expression picks up the pointer "fdt->fd[fd]" in an RCU-safe manner,
+and, if CONFIG_PROVE_RCU is configured, verifies that this expression
+is used in:
+
+1.	An RCU read-side critical section, or
+2.	with files->file_lock held, or
+3.	on an unshared files_struct.
+
+In case (1), the pointer is picked up in an RCU-safe manner for vanilla
+RCU read-side critical sections, in case (2) the ->file_lock prevents
+any change from taking place, and finally, in case (3) the current task
+is the only task accessing the file_struct, again preventing any change
+from taking place.
+
+There are currently only "universal" versions of the rcu_assign_pointer()
+and RCU list-/tree-traversal primitives, which do not (yet) check for
+being in an RCU read-side critical section.  In the future, separate
+versions of these primitives might be created.

Documentation/RCU/rcu.txt

@@ -75,6 +75,8 @@ o	I hear that RCU is patented?  What is with that?
 	search for the string "Patent" in RTFP.txt to find them.
 	Of these, one was allowed to lapse by the assignee, and the
 	others have been contributed to the Linux kernel under GPL.
+	There are now also LGPL implementations of user-level RCU
+	available (http://lttng.org/?q=node/18).
 
 o	I hear that RCU needs work in order to support realtime kernels?
 
@@ -91,48 +93,4 @@ o	Where can I find more information on RCU?
 
 o	What are all these files in this directory?
 
-
-	NMI-RCU.txt
-
-		Describes how to use RCU to implement dynamic
-		NMI handlers, which can be revectored on the fly,
-		without rebooting.
-
-	RTFP.txt
-
-		List of RCU-related publications and web sites.
-
-	UP.txt
-
-		Discussion of RCU usage in UP kernels.
-
-	arrayRCU.txt
-
-		Describes how to use RCU to protect arrays, with
-		resizeable arrays whose elements reference other
-		data structures being of the most interest.
-
-	checklist.txt
-
-		Lists things to check for when inspecting code that
-		uses RCU.
-
-	listRCU.txt
-
-		Describes how to use RCU to protect linked lists.
-		This is the simplest and most common use of RCU
-		in the Linux kernel.
-
-	rcu.txt
-
-		You are reading it!
-
-	rcuref.txt
-
-		Describes how to combine use of reference counts
-		with RCU.
-
-	whatisRCU.txt
-
-		Overview of how the RCU implementation works.  Along
-		the way, presents a conceptual view of RCU.
+	See 00-INDEX for the list.

Documentation/RCU/stallwarn.txt

@@ -0,0 +1,58 @@
+Using RCU's CPU Stall Detector
+
+The CONFIG_RCU_CPU_STALL_DETECTOR kernel config parameter enables
+RCU's CPU stall detector, which detects conditions that unduly delay
+RCU grace periods.  The stall detector's idea of what constitutes
+"unduly delayed" is controlled by a pair of C preprocessor macros:
+
+RCU_SECONDS_TILL_STALL_CHECK
+
+	This macro defines the period of time that RCU will wait from
+	the beginning of a grace period until it issues an RCU CPU
+	stall warning.	It is normally ten seconds.
+
+RCU_SECONDS_TILL_STALL_RECHECK
+
+	This macro defines the period of time that RCU will wait after
+	issuing a stall warning until it issues another stall warning.
+	It is normally set to thirty seconds.
+
+RCU_STALL_RAT_DELAY
+
+	The CPU stall detector tries to make the offending CPU rat on itself,
+	as this often gives better-quality stack traces.  However, if
+	the offending CPU does not detect its own stall in the number
+	of jiffies specified by RCU_STALL_RAT_DELAY, then other CPUs will
+	complain.  This is normally set to two jiffies.
+
+The following problems can result in an RCU CPU stall warning:
+
+o	A CPU looping in an RCU read-side critical section.
+	
+o	A CPU looping with interrupts disabled.
+
+o	A CPU looping with preemption disabled.
+
+o	For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
+	without invoking schedule().
+
+o	A bug in the RCU implementation.
+
+o	A hardware failure.  This is quite unlikely, but has occurred
+	at least once in a former life.  A CPU failed in a running system,
+	becoming unresponsive, but not causing an immediate crash.
+	This resulted in a series of RCU CPU stall warnings, eventually
+	leading the realization that the CPU had failed.
+
+The RCU, RCU-sched, and RCU-bh implementations have CPU stall warning.
+SRCU does not do so directly, but its calls to synchronize_sched() will
+result in RCU-sched detecting any CPU stalls that might be occurring.
+
+To diagnose the cause of the stall, inspect the stack traces.  The offending
+function will usually be near the top of the stack.  If you have a series
+of stall warnings from a single extended stall, comparing the stack traces
+can often help determine where the stall is occurring, which will usually
+be in the function nearest the top of the stack that stays the same from
+trace to trace.
+
+RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE.

Documentation/RCU/torture.txt

@@ -30,6 +30,18 @@ MODULE PARAMETERS
 
 This module has the following parameters:
 
+fqs_duration	Duration (in microseconds) of artificially induced bursts
+		of force_quiescent_state() invocations.  In RCU
+		implementations having force_quiescent_state(), these
+		bursts help force races between forcing a given grace
+		period and that grace period ending on its own.
+
+fqs_holdoff	Holdoff time (in microseconds) between consecutive calls
+		to force_quiescent_state() within a burst.
+
+fqs_stutter	Wait time (in seconds) between consecutive bursts
+		of calls to force_quiescent_state().
+
 irqreaders	Says to invoke RCU readers from irq level.  This is currently
 		done via timers.  Defaults to "1" for variants of RCU that
 		permit this.  (Or, more accurately, variants of RCU that do

Documentation/RCU/whatisRCU.txt

@@ -323,14 +323,17 @@ used as follows:
 	Defer			Protect
 
 a.	synchronize_rcu()	rcu_read_lock() / rcu_read_unlock()
-	call_rcu()
+	call_rcu()		rcu_dereference()
 
 b.	call_rcu_bh()		rcu_read_lock_bh() / rcu_read_unlock_bh()
+				rcu_dereference_bh()
 
-c.	synchronize_sched()	preempt_disable() / preempt_enable()
+c.	synchronize_sched()	rcu_read_lock_sched() / rcu_read_unlock_sched()
+				preempt_disable() / preempt_enable()
 				local_irq_save() / local_irq_restore()
 				hardirq enter / hardirq exit
 				NMI enter / NMI exit
+				rcu_dereference_sched()
 
 These three mechanisms are used as follows:
 
@@ -780,9 +783,8 @@ Linux-kernel source code, but it helps to have a full list of the
 APIs, since there does not appear to be a way to categorize them
 in docbook.  Here is the list, by category.
 
-RCU pointer/list traversal:
+RCU list traversal:
 
-	rcu_dereference
 	list_for_each_entry_rcu
 	hlist_for_each_entry_rcu
 	hlist_nulls_for_each_entry_rcu
@@ -808,7 +810,7 @@ RCU:	Critical sections	Grace period		Barrier
 
 	rcu_read_lock		synchronize_net		rcu_barrier
 	rcu_read_unlock		synchronize_rcu
-				synchronize_rcu_expedited
+	rcu_dereference		synchronize_rcu_expedited
 				call_rcu
 
 
@@ -816,7 +818,7 @@ bh:	Critical sections	Grace period		Barrier
 
 	rcu_read_lock_bh	call_rcu_bh		rcu_barrier_bh
 	rcu_read_unlock_bh	synchronize_rcu_bh
-				synchronize_rcu_bh_expedited
+	rcu_dereference_bh	synchronize_rcu_bh_expedited
 
 
 sched:	Critical sections	Grace period		Barrier
@@ -825,12 +827,14 @@ sched:	Critical sections	Grace period		Barrier
 	rcu_read_unlock_sched	call_rcu_sched
 	[preempt_disable]	synchronize_sched_expedited
 	[and friends]
+	rcu_dereference_sched
 
 
 SRCU:	Critical sections	Grace period		Barrier
 
 	srcu_read_lock		synchronize_srcu	N/A
 	srcu_read_unlock	synchronize_srcu_expedited
+	srcu_dereference
 
 SRCU:	Initialization/cleanup
 	init_srcu_struct

Documentation/SubmitChecklist

@@ -15,7 +15,7 @@ kernel patches.
 2: Passes allnoconfig, allmodconfig
 
 3: Builds on multiple CPU architectures by using local cross-compile tools
-   or something like PLM at OSDL.
+   or some other build farm.
 
 4: ppc64 is a good architecture for cross-compilation checking because it
    tends to use `unsigned long' for 64-bit quantities.
@@ -88,3 +88,6 @@ kernel patches.
 
 24: All memory barriers {e.g., barrier(), rmb(), wmb()} need a comment in the
     source code that explains the logic of what they are doing and why.
+
+25: If any ioctl's are added by the patch, then also update
+    Documentation/ioctl/ioctl-number.txt.

Documentation/acpi/method-customizing.txt

@@ -0,0 +1,66 @@
+Linux ACPI Custom Control Method How To
+=======================================
+
+Written by Zhang Rui <rui.zhang@intel.com>
+
+
+Linux supports customizing ACPI control methods at runtime.
+
+Users can use this to
+1. override an existing method which may not work correctly,
+   or just for debugging purposes.
+2. insert a completely new method in order to create a missing
+   method such as _OFF, _ON, _STA, _INI, etc.
+For these cases, it is far simpler to dynamically install a single
+control method rather than override the entire DSDT, because kernel
+rebuild/reboot is not needed and test result can be got in minutes.
+
+Note: Only ACPI METHOD can be overridden, any other object types like
+      "Device", "OperationRegion", are not recognized.
+Note: The same ACPI control method can be overridden for many times,
+      and it's always the latest one that used by Linux/kernel.
+
+1. override an existing method
+   a) get the ACPI table via ACPI sysfs I/F. e.g. to get the DSDT,
+      just run "cat /sys/firmware/acpi/tables/DSDT > /tmp/dsdt.dat"
+   b) disassemble the table by running "iasl -d dsdt.dat".
+   c) rewrite the ASL code of the method and save it in a new file,
+   d) package the new file (psr.asl) to an ACPI table format.
+      Here is an example of a customized \_SB._AC._PSR method,
+
+      DefinitionBlock ("", "SSDT", 1, "", "", 0x20080715)
+      {
+	External (ACON)
+
+	Method (\_SB_.AC._PSR, 0, NotSerialized)
+	{
+		Store ("In AC _PSR", Debug)
+		Return (ACON)
+	}
+      }
+      Note that the full pathname of the method in ACPI namespace
+      should be used.
+      And remember to use "External" to declare external objects.
+   e) assemble the file to generate the AML code of the method.
+      e.g. "iasl psr.asl" (psr.aml is generated as a result)
+   f) mount debugfs by "mount -t debugfs none /sys/kernel/debug"
+   g) override the old method via the debugfs by running
+      "cat /tmp/psr.aml > /sys/kernel/debug/acpi/custom_method"
+
+2. insert a new method
+   This is easier than overriding an existing method.
+   We just need to create the ASL code of the method we want to
+   insert and then follow the step c) ~ g) in section 1.
+
+3. undo your changes
+   The "undo" operation is not supported for a new inserted method
+   right now, i.e. we can not remove a method currently.
+   For an overrided method, in order to undo your changes, please
+   save a copy of the method original ASL code in step c) section 1,
+   and redo step c) ~ g) to override the method with the original one.
+
+
+Note: We can use a kernel with multiple custom ACPI method running,
+      But each individual write to debugfs can implement a SINGLE
+      method override. i.e. if we want to insert/override multiple
+      ACPI methods, we need to redo step c) ~ g) for multiple times.

Documentation/arm/memory.txt

@@ -59,7 +59,11 @@ PAGE_OFFSET	high_memory-1	Kernel direct-mapped RAM region.
 				This maps the platforms RAM, and typically
 				maps all platform RAM in a 1:1 relationship.
 
-TASK_SIZE	PAGE_OFFSET-1	Kernel module space
+PKMAP_BASE	PAGE_OFFSET-1	Permanent kernel mappings
+				One way of mapping HIGHMEM pages into kernel
+				space.
+
+MODULES_VADDR	MODULES_END-1	Kernel module space
 				Kernel modules inserted via insmod are
 				placed here using dynamic mappings.
 

Documentation/blackfin/00-INDEX

@@ -1,9 +1,6 @@
 00-INDEX
 	- This file
 
-cache-lock.txt
-	- HOWTO for blackfin cache locking.
-
 cachefeatures.txt
 	- Supported cache features.
 

Documentation/blackfin/Makefile

@@ -0,0 +1,6 @@
+obj-m := gptimers-example.o
+
+all: modules
+
+modules clean:
+	$(MAKE) -C ../.. SUBDIRS=$(PWD) $@

Documentation/blackfin/cache-lock.txt

@@ -1,48 +0,0 @@
-/*
- * File:         Documentation/blackfin/cache-lock.txt
- * Based on:
- * Author:
- *
- * Created:
- * Description:  This file contains the simple DMA Implementation for Blackfin
- *
- * Rev:          $Id: cache-lock.txt 2384 2006-11-01 04:12:43Z magicyang $
- *
- * Modified:
- *               Copyright 2004-2006 Analog Devices Inc.
- *
- * Bugs:         Enter bugs at http://blackfin.uclinux.org/
- *
- */
-
-How to lock your code in cache in uClinux/blackfin
---------------------------------------------------
-
-There are only a few steps required to lock your code into the cache.
-Currently you can lock the code by Way.
-
-Below are the interface provided for locking the cache.
-
-
-1. cache_grab_lock(int Ways);
-
-This function grab the lock for locking your code into the cache specified
-by Ways.
-
-
-2. cache_lock(int Ways);
-
-This function should be called after your critical code has been executed.
-Once the critical code exits, the code is now loaded into the cache. This
-function locks the code into the cache.
-
-
-So, the example sequence will be:
-
-	cache_grab_lock(WAY0_L);	/* Grab the lock */
-
-	critical_code();		/* Execute the code of interest */
-
-	cache_lock(WAY0_L);		/* Lock the cache */
-
-Where WAY0_L signifies WAY0 locking.

Documentation/blackfin/cachefeatures.txt

@@ -41,16 +41,6 @@
 		icplb_flush();
 		dcplb_flush();
 
-	- Locking the cache.
-
-		cache_grab_lock();
-		cache_lock();
-
-	Please refer linux-2.6.x/Documentation/blackfin/cache-lock.txt for how to
-	lock the cache.
-
-	Locking the cache is optional feature.
-
 	- Miscellaneous cache functions.
 
 		flush_cache_all();

Documentation/blackfin/gptimers-example.c

@@ -0,0 +1,83 @@
+/*
+ * Simple gptimers example
+ *	http://docs.blackfin.uclinux.org/doku.php?id=linux-kernel:drivers:gptimers
+ *
+ * Copyright 2007-2009 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/module.h>
+
+#include <asm/gptimers.h>
+#include <asm/portmux.h>
+
+/* ... random driver includes ... */
+
+#define DRIVER_NAME "gptimer_example"
+
+struct gptimer_data {
+	uint32_t period, width;
+};
+static struct gptimer_data data;
+
+/* ... random driver state ... */
+
+static irqreturn_t gptimer_example_irq(int irq, void *dev_id)
+{
+	struct gptimer_data *data = dev_id;
+
+	/* make sure it was our timer which caused the interrupt */
+	if (!get_gptimer_intr(TIMER5_id))
+		return IRQ_NONE;
+
+	/* read the width/period values that were captured for the waveform */
+	data->width = get_gptimer_pwidth(TIMER5_id);
+	data->period = get_gptimer_period(TIMER5_id);
+
+	/* acknowledge the interrupt */
+	clear_gptimer_intr(TIMER5_id);
+
+	/* tell the upper layers we took care of things */
+	return IRQ_HANDLED;
+}
+
+/* ... random driver code ... */
+
+static int __init gptimer_example_init(void)
+{
+	int ret;
+
+	/* grab the peripheral pins */
+	ret = peripheral_request(P_TMR5, DRIVER_NAME);
+	if (ret) {
+		printk(KERN_NOTICE DRIVER_NAME ": peripheral request failed\n");
+		return ret;
+	}
+
+	/* grab the IRQ for the timer */
+	ret = request_irq(IRQ_TIMER5, gptimer_example_irq, IRQF_SHARED, DRIVER_NAME, &data);
+	if (ret) {
+		printk(KERN_NOTICE DRIVER_NAME ": IRQ request failed\n");
+		peripheral_free(P_TMR5);
+		return ret;
+	}
+
+	/* setup the timer and enable it */
+	set_gptimer_config(TIMER5_id, WDTH_CAP | PULSE_HI | PERIOD_CNT | IRQ_ENA);
+	enable_gptimers(TIMER5bit);
+
+	return 0;
+}
+module_init(gptimer_example_init);
+
+static void __exit gptimer_example_exit(void)
+{
+	disable_gptimers(TIMER5bit);
+	free_irq(IRQ_TIMER5, &data);
+	peripheral_free(P_TMR5);
+}
+module_exit(gptimer_example_exit);
+
+MODULE_LICENSE("BSD");

Documentation/block/00-INDEX

@@ -1,7 +1,5 @@
 00-INDEX
 	- This file
-as-iosched.txt
-	- Anticipatory IO scheduler
 barrier.txt
 	- I/O Barriers
 biodoc.txt

Documentation/block/as-iosched.txt

@@ -1,172 +0,0 @@
-Anticipatory IO scheduler
--------------------------
-Nick Piggin <piggin@cyberone.com.au>    13 Sep 2003
-
-Attention! Database servers, especially those using "TCQ" disks should
-investigate performance with the 'deadline' IO scheduler. Any system with high
-disk performance requirements should do so, in fact.
-
-If you see unusual performance characteristics of your disk systems, or you
-see big performance regressions versus the deadline scheduler, please email
-me. Database users don't bother unless you're willing to test a lot of patches
-from me ;) its a known issue.
-
-Also, users with hardware RAID controllers, doing striping, may find
-highly variable performance results with using the as-iosched. The
-as-iosched anticipatory implementation is based on the notion that a disk
-device has only one physical seeking head.  A striped RAID controller
-actually has a head for each physical device in the logical RAID device.
-
-However, setting the antic_expire (see tunable parameters below) produces
-very similar behavior to the deadline IO scheduler.
-
-Selecting IO schedulers
------------------------
-Refer to Documentation/block/switching-sched.txt for information on
-selecting an io scheduler on a per-device basis.
-
-Anticipatory IO scheduler Policies
-----------------------------------
-The as-iosched implementation implements several layers of policies
-to determine when an IO request is dispatched to the disk controller.
-Here are the policies outlined, in order of application.
-
-1. one-way Elevator algorithm.
-
-The elevator algorithm is similar to that used in deadline scheduler, with
-the addition that it allows limited backward movement of the elevator
-(i.e. seeks backwards).  A seek backwards can occur when choosing between
-two IO requests where one is behind the elevator's current position, and
-the other is in front of the elevator's position. If the seek distance to
-the request in back of the elevator is less than half the seek distance to
-the request in front of the elevator, then the request in back can be chosen.
-Backward seeks are also limited to a maximum of MAXBACK (1024*1024) sectors.
-This favors forward movement of the elevator, while allowing opportunistic
-"short" backward seeks.
-
-2. FIFO expiration times for reads and for writes.
-
-This is again very similar to the deadline IO scheduler.  The expiration
-times for requests on these lists is tunable using the parameters read_expire
-and write_expire discussed below.  When a read or a write expires in this way,
-the IO scheduler will interrupt its current elevator sweep or read anticipation
-to service the expired request.
-
-3. Read and write request batching
-
-A batch is a collection of read requests or a collection of write
-requests.  The as scheduler alternates dispatching read and write batches
-to the driver.  In the case a read batch, the scheduler submits read
-requests to the driver as long as there are read requests to submit, and
-the read batch time limit has not been exceeded (read_batch_expire).
-The read batch time limit begins counting down only when there are
-competing write requests pending.
-
-In the case of a write batch, the scheduler submits write requests to
-the driver as long as there are write requests available, and the
-write batch time limit has not been exceeded (write_batch_expire).
-However, the length of write batches will be gradually shortened
-when read batches frequently exceed their time limit.
-
-When changing between batch types, the scheduler waits for all requests
-from the previous batch to complete before scheduling requests for the
-next batch.
-
-The read and write fifo expiration times described in policy 2 above
-are checked only when in scheduling IO of a batch for the corresponding
-(read/write) type.  So for example, the read FIFO timeout values are
-tested only during read batches.  Likewise, the write FIFO timeout
-values are tested only during write batches.  For this reason,
-it is generally not recommended for the read batch time
-to be longer than the write expiration time, nor for the write batch
-time to exceed the read expiration time (see tunable parameters below).
-
-When the IO scheduler changes from a read to a write batch,
-it begins the elevator from the request that is on the head of the
-write expiration FIFO.  Likewise, when changing from a write batch to
-a read batch, scheduler begins the elevator from the first entry
-on the read expiration FIFO.
-
-4. Read anticipation.
-
-Read anticipation occurs only when scheduling a read batch.
-This implementation of read anticipation allows only one read request
-to be dispatched to the disk controller at a time.  In
-contrast, many write requests may be dispatched to the disk controller
-at a time during a write batch.  It is this characteristic that can make
-the anticipatory scheduler perform anomalously with controllers supporting
-TCQ, or with hardware striped RAID devices. Setting the antic_expire
-queue parameter (see below) to zero disables this behavior, and the 
-anticipatory scheduler behaves essentially like the deadline scheduler.
-
-When read anticipation is enabled (antic_expire is not zero), reads
-are dispatched to the disk controller one at a time.
-At the end of each read request, the IO scheduler examines its next
-candidate read request from its sorted read list.  If that next request
-is from the same process as the request that just completed,
-or if the next request in the queue is "very close" to the
-just completed request, it is dispatched immediately.  Otherwise,
-statistics (average think time, average seek distance) on the process
-that submitted the just completed request are examined.  If it seems
-likely that that process will submit another request soon, and that
-request is likely to be near the just completed request, then the IO
-scheduler will stop dispatching more read requests for up to (antic_expire)
-milliseconds, hoping that process will submit a new request near the one
-that just completed.  If such a request is made, then it is dispatched
-immediately.  If the antic_expire wait time expires, then the IO scheduler
-will dispatch the next read request from the sorted read queue.
-
-To decide whether an anticipatory wait is worthwhile, the scheduler
-maintains statistics for each process that can be used to compute
-mean "think time" (the time between read requests), and mean seek
-distance for that process.  One observation is that these statistics
-are associated with each process, but those statistics are not associated
-with a specific IO device.  So for example, if a process is doing IO
-on several file systems on separate devices, the statistics will be
-a combination of IO behavior from all those devices.
-
-
-Tuning the anticipatory IO scheduler
-------------------------------------
-When using 'as', the anticipatory IO scheduler there are 5 parameters under
-/sys/block/*/queue/iosched/. All are units of milliseconds.
-
-The parameters are:
-* read_expire
-    Controls how long until a read request becomes "expired". It also controls the
-    interval between which expired requests are served, so set to 50, a request
-    might take anywhere < 100ms to be serviced _if_ it is the next on the
-    expired list. Obviously request expiration strategies won't make the disk
-    go faster. The result basically equates to the timeslice a single reader
-    gets in the presence of other IO. 100*((seek time / read_expire) + 1) is
-    very roughly the % streaming read efficiency your disk should get with
-    multiple readers.
-
-* read_batch_expire
-    Controls how much time a batch of reads is given before pending writes are
-    served. A higher value is more efficient. This might be set below read_expire
-    if writes are to be given higher priority than reads, but reads are to be
-    as efficient as possible when there are no writes. Generally though, it
-    should be some multiple of read_expire.
-
-* write_expire, and
-* write_batch_expire are equivalent to the above, for writes.
-
-* antic_expire
-    Controls the maximum amount of time we can anticipate a good read (one
-    with a short seek distance from the most recently completed request) before
-    giving up. Many other factors may cause anticipation to be stopped early,
-    or some processes will not be "anticipated" at all. Should be a bit higher
-    for big seek time devices though not a linear correspondence - most
-    processes have only a few ms thinktime.
-
-In addition to the tunables above there is a read-only file named est_time
-which, when read, will show:
-
-    - The probability of a task exiting without a cooperating task
-      submitting an anticipated IO.
-
-    - The current mean think time.
-
-    - The seek distance used to determine if an incoming IO is better.
-

Documentation/block/biodoc.txt

@@ -186,7 +186,7 @@ a virtual address mapping (unlike the earlier scheme of virtual address
 do not have a corresponding kernel virtual address space mapping) and
 low-memory pages.
 
-Note: Please refer to Documentation/DMA-mapping.txt for a discussion
+Note: Please refer to Documentation/PCI/PCI-DMA-mapping.txt for a discussion
 on PCI high mem DMA aspects and mapping of scatter gather lists, and support
 for 64 bit PCI.
 

Documentation/block/queue-sysfs.txt

@@ -25,11 +25,11 @@ size allowed by the hardware.
 
 nomerges (RW)
 -------------
-This enables the user to disable the lookup logic involved with IO merging
-requests in the block layer. Merging may still occur through a direct
-1-hit cache, since that comes for (almost) free. The IO scheduler will not
-waste cycles doing tree/hash lookups for merges if nomerges is 1. Defaults
-to 0, enabling all merges.
+This enables the user to disable the lookup logic involved with IO
+merging requests in the block layer. By default (0) all merges are
+enabled. When set to 1 only simple one-hit merges will be tried. When
+set to 2 no merge algorithms will be tried (including one-hit or more
+complex tree/hash lookups).
 
 nr_requests (RW)
 ----------------

Documentation/cachetlb.txt

@@ -88,12 +88,12 @@ changes occur:
 	This is used primarily during fault processing.
 
 5) void update_mmu_cache(struct vm_area_struct *vma,
-			 unsigned long address, pte_t pte)
+			 unsigned long address, pte_t *ptep)
 
 	At the end of every page fault, this routine is invoked to
 	tell the architecture specific code that a translation
-	described by "pte" now exists at virtual address "address"
-	for address space "vma->vm_mm", in the software page tables.
+	now exists at virtual address "address" for address space
+	"vma->vm_mm", in the software page tables.
 
 	A port may use this information in any way it so chooses.
 	For example, it could use this event to pre-load TLB
@@ -377,3 +377,27 @@ maps this page at its virtual address.
 	All the functionality of flush_icache_page can be implemented in
 	flush_dcache_page and update_mmu_cache. In 2.7 the hope is to
 	remove this interface completely.
+
+The final category of APIs is for I/O to deliberately aliased address
+ranges inside the kernel.  Such aliases are set up by use of the
+vmap/vmalloc API.  Since kernel I/O goes via physical pages, the I/O
+subsystem assumes that the user mapping and kernel offset mapping are
+the only aliases.  This isn't true for vmap aliases, so anything in
+the kernel trying to do I/O to vmap areas must manually manage
+coherency.  It must do this by flushing the vmap range before doing
+I/O and invalidating it after the I/O returns.
+
+  void flush_kernel_vmap_range(void *vaddr, int size)
+       flushes the kernel cache for a given virtual address range in
+       the vmap area.  This is to make sure that any data the kernel
+       modified in the vmap range is made visible to the physical
+       page.  The design is to make this area safe to perform I/O on.
+       Note that this API does *not* also flush the offset map alias
+       of the area.
+
+  void invalidate_kernel_vmap_range(void *vaddr, int size) invalidates
+       the cache for a given virtual address range in the vmap area
+       which prevents the processor from making the cache stale by
+       speculatively reading data while the I/O was occurring to the
+       physical pages.  This is only necessary for data reads into the
+       vmap area.

Documentation/cdrom/ide-cd

@@ -159,42 +159,7 @@ two arguments:  the CDROM device, and the slot number to which you wish
 to change.  If the slot number is -1, the drive is unloaded.
 
 
-4. Compilation options
-----------------------
-
-There are a few additional options which can be set when compiling the
-driver.  Most people should not need to mess with any of these; they
-are listed here simply for completeness.  A compilation option can be
-enabled by adding a line of the form `#define <option> 1' to the top
-of ide-cd.c.  All these options are disabled by default.
-
-VERBOSE_IDE_CD_ERRORS
-  If this is set, ATAPI error codes will be translated into textual
-  descriptions.  In addition, a dump is made of the command which
-  provoked the error.  This is off by default to save the memory used
-  by the (somewhat long) table of error descriptions.  
-
-STANDARD_ATAPI
-  If this is set, the code needed to deal with certain drives which do
-  not properly implement the ATAPI spec will be disabled.  If you know
-  your drive implements ATAPI properly, you can turn this on to get a
-  slightly smaller kernel.
-
-NO_DOOR_LOCKING
-  If this is set, the driver will never attempt to lock the door of
-  the drive.
-
-CDROM_NBLOCKS_BUFFER
-  This sets the size of the buffer to be used for a CDROMREADAUDIO
-  ioctl.  The default is 8.
-
-TEST
-  This currently enables an additional ioctl which enables a user-mode
-  program to execute an arbitrary packet command.  See the source for
-  details.  This should be left off unless you know what you're doing.
-
-
-5. Common problems
+4. Common problems
 ------------------
 
 This section discusses some common problems encountered when trying to
@@ -371,7 +336,7 @@ f. Data corruption.
     expense of low system performance.
 
 
-6. cdchange.c
+5. cdchange.c
 -------------
 
 /*

Documentation/cpu-freq/governors.txt

@@ -145,8 +145,8 @@ show_sampling_rate_max: THIS INTERFACE IS DEPRECATED, DON'T USE IT.
 up_threshold: defines what the average CPU usage between the samplings
 of 'sampling_rate' needs to be for the kernel to make a decision on
 whether it should increase the frequency.  For example when it is set
-to its default value of '80' it means that between the checking
-intervals the CPU needs to be on average more than 80% in use to then
+to its default value of '95' it means that between the checking
+intervals the CPU needs to be on average more than 95% in use to then
 decide that the CPU frequency needs to be increased.  
 
 ignore_nice_load: this parameter takes a value of '0' or '1'. When

Documentation/cpu-freq/pcc-cpufreq.txt

@@ -0,0 +1,207 @@
+/*
+ *  pcc-cpufreq.txt - PCC interface documentation
+ *
+ *  Copyright (C) 2009 Red Hat, Matthew Garrett <mjg@redhat.com>
+ *  Copyright (C) 2009 Hewlett-Packard Development Company, L.P.
+ *      Nagananda Chumbalkar <nagananda.chumbalkar@hp.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, GOOD TITLE or NON
+ *  INFRINGEMENT. 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.,
+ *  675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+
+			Processor Clocking Control Driver
+			---------------------------------
+
+Contents:
+---------
+1.	Introduction
+1.1	PCC interface
+1.1.1   Get Average Frequency
+1.1.2	Set Desired Frequency
+1.2	Platforms affected
+2.	Driver and /sys details
+2.1	scaling_available_frequencies
+2.2	cpuinfo_transition_latency
+2.3	cpuinfo_cur_freq
+2.4	related_cpus
+3.	Caveats
+
+1. Introduction:
+----------------
+Processor Clocking Control (PCC) is an interface between the platform
+firmware and OSPM. It is a mechanism for coordinating processor
+performance (ie: frequency) between the platform firmware and the OS.
+
+The PCC driver (pcc-cpufreq) allows OSPM to take advantage of the PCC
+interface.
+
+OS utilizes the PCC interface to inform platform firmware what frequency the
+OS wants for a logical processor. The platform firmware attempts to achieve
+the requested frequency. If the request for the target frequency could not be
+satisfied by platform firmware, then it usually means that power budget
+conditions are in place, and "power capping" is taking place.
+
+1.1 PCC interface:
+------------------
+The complete PCC specification is available here:
+http://www.acpica.org/download/Processor-Clocking-Control-v1p0.pdf
+
+PCC relies on a shared memory region that provides a channel for communication
+between the OS and platform firmware. PCC also implements a "doorbell" that
+is used by the OS to inform the platform firmware that a command has been
+sent.
+
+The ACPI PCCH() method is used to discover the location of the PCC shared
+memory region. The shared memory region header contains the "command" and
+"status" interface. PCCH() also contains details on how to access the platform
+doorbell.
+
+The following commands are supported by the PCC interface:
+* Get Average Frequency
+* Set Desired Frequency
+
+The ACPI PCCP() method is implemented for each logical processor and is
+used to discover the offsets for the input and output buffers in the shared
+memory region.
+
+When PCC mode is enabled, the platform will not expose processor performance
+or throttle states (_PSS, _TSS and related ACPI objects) to OSPM. Therefore,
+the native P-state driver (such as acpi-cpufreq for Intel, powernow-k8 for
+AMD) will not load.
+
+However, OSPM remains in control of policy. The governor (eg: "ondemand")
+computes the required performance for each processor based on server workload.
+The PCC driver fills in the command interface, and the input buffer and
+communicates the request to the platform firmware. The platform firmware is
+responsible for delivering the requested performance.
+
+Each PCC command is "global" in scope and can affect all the logical CPUs in
+the system. Therefore, PCC is capable of performing "group" updates. With PCC
+the OS is capable of getting/setting the frequency of all the logical CPUs in
+the system with a single call to the BIOS.
+
+1.1.1 Get Average Frequency:
+----------------------------
+This command is used by the OSPM to query the running frequency of the
+processor since the last time this command was completed. The output buffer
+indicates the average unhalted frequency of the logical processor expressed as
+a percentage of the nominal (ie: maximum) CPU frequency. The output buffer
+also signifies if the CPU frequency is limited by a power budget condition.
+
+1.1.2 Set Desired Frequency:
+----------------------------
+This command is used by the OSPM to communicate to the platform firmware the
+desired frequency for a logical processor. The output buffer is currently
+ignored by OSPM. The next invocation of "Get Average Frequency" will inform
+OSPM if the desired frequency was achieved or not.
+
+1.2 Platforms affected:
+-----------------------
+The PCC driver will load on any system where the platform firmware:
+* supports the PCC interface, and the associated PCCH() and PCCP() methods
+* assumes responsibility for managing the hardware clocking controls in order
+to deliver the requested processor performance
+
+Currently, certain HP ProLiant platforms implement the PCC interface. On those
+platforms PCC is the "default" choice.
+
+However, it is possible to disable this interface via a BIOS setting. In
+such an instance, as is also the case on platforms where the PCC interface
+is not implemented, the PCC driver will fail to load silently.
+
+2. Driver and /sys details:
+---------------------------
+When the driver loads, it merely prints the lowest and the highest CPU
+frequencies supported by the platform firmware.
+
+The PCC driver loads with a message such as:
+pcc-cpufreq: (v1.00.00) driver loaded with frequency limits: 1600 MHz, 2933
+MHz
+
+This means that the OPSM can request the CPU to run at any frequency in
+between the limits (1600 MHz, and 2933 MHz) specified in the message.
+
+Internally, there is no need for the driver to convert the "target" frequency
+to a corresponding P-state.
+
+The VERSION number for the driver will be of the format v.xy.ab.
+eg: 1.00.02
+   ----- --
+    |    |
+    |    -- this will increase with bug fixes/enhancements to the driver
+    |-- this is the version of the PCC specification the driver adheres to
+
+
+The following is a brief discussion on some of the fields exported via the
+/sys filesystem and how their values are affected by the PCC driver:
+
+2.1 scaling_available_frequencies:
+----------------------------------
+scaling_available_frequencies is not created in /sys. No intermediate
+frequencies need to be listed because the BIOS will try to achieve any
+frequency, within limits, requested by the governor. A frequency does not have
+to be strictly associated with a P-state.
+
+2.2 cpuinfo_transition_latency:
+-------------------------------
+The cpuinfo_transition_latency field is 0. The PCC specification does
+not include a field to expose this value currently.
+
+2.3 cpuinfo_cur_freq:
+---------------------
+A) Often cpuinfo_cur_freq will show a value different than what is declared
+in the scaling_available_frequencies or scaling_cur_freq, or scaling_max_freq.
+This is due to "turbo boost" available on recent Intel processors. If certain
+conditions are met the BIOS can achieve a slightly higher speed than requested
+by OSPM. An example:
+
+scaling_cur_freq	: 2933000
+cpuinfo_cur_freq	: 3196000
+
+B) There is a round-off error associated with the cpuinfo_cur_freq value.
+Since the driver obtains the current frequency as a "percentage" (%) of the
+nominal frequency from the BIOS, sometimes, the values displayed by
+scaling_cur_freq and cpuinfo_cur_freq may not match. An example:
+
+scaling_cur_freq	: 1600000
+cpuinfo_cur_freq	: 1583000
+
+In this example, the nominal frequency is 2933 MHz. The driver obtains the
+current frequency, cpuinfo_cur_freq, as 54% of the nominal frequency:
+
+	54% of 2933 MHz = 1583 MHz
+
+Nominal frequency is the maximum frequency of the processor, and it usually
+corresponds to the frequency of the P0 P-state.
+
+2.4 related_cpus:
+-----------------
+The related_cpus field is identical to affected_cpus.
+
+affected_cpus	: 4
+related_cpus	: 4
+
+Currently, the PCC driver does not evaluate _PSD. The platforms that support
+PCC do not implement SW_ALL. So OSPM doesn't need to perform any coordination
+to ensure that the same frequency is requested of all dependent CPUs.
+
+3. Caveats:
+-----------
+The "cpufreq_stats" module in its present form cannot be loaded and
+expected to work with the PCC driver. Since the "cpufreq_stats" module
+provides information wrt each P-state, it is not applicable to the PCC driver.

Documentation/cpu-hotplug.txt

@@ -49,6 +49,12 @@ maxcpus=n    Restrict boot time cpus to n. Say if you have 4 cpus, using
 additional_cpus=n (*)	Use this to limit hotpluggable cpus. This option sets
   			cpu_possible_map = cpu_present_map + additional_cpus
 
+cede_offline={"off","on"}  Use this option to disable/enable putting offlined
+		            processors to an extended H_CEDE state on
+			    supported pseries platforms.
+			    If nothing is specified,
+			    cede_offline is set to "on".
+
 (*) Option valid only for following architectures
 - ia64
 
@@ -309,41 +315,26 @@ A: The following are what is required for CPU hotplug infrastructure to work
 
 Q: I need to ensure that a particular cpu is not removed when there is some
    work specific to this cpu is in progress.
-A: First switch the current thread context to preferred cpu
+A: There are two ways.  If your code can be run in interrupt context, use
+   smp_call_function_single(), otherwise use work_on_cpu().  Note that
+   work_on_cpu() is slow, and can fail due to out of memory:
 
 	int my_func_on_cpu(int cpu)
 	{
-		cpumask_t saved_mask, new_mask = CPU_MASK_NONE;
-		int curr_cpu, err = 0;
-
-		saved_mask = current->cpus_allowed;
-		cpu_set(cpu, new_mask);
-		err = set_cpus_allowed(current, new_mask);
-
-		if (err)
-			return err;
-
-		/*
-		 * If we got scheduled out just after the return from
-		 * set_cpus_allowed() before running the work, this ensures
-		 * we stay locked.
-		 */
-		curr_cpu = get_cpu();
-
-		if (curr_cpu != cpu) {
-			err = -EAGAIN;
-			goto ret;
-		} else {
-			/*
-			 * Do work : But cant sleep, since get_cpu() disables preempt
-			 */
-		}
-		ret:
-			put_cpu();
-			set_cpus_allowed(current, saved_mask);
-			return err;
-		}
-
+		int err;
+		get_online_cpus();
+		if (!cpu_online(cpu))
+			err = -EINVAL;
+		else
+#if NEEDS_BLOCKING
+			err = work_on_cpu(cpu, __my_func_on_cpu, NULL);
+#else
+			smp_call_function_single(cpu, __my_func_on_cpu, &err,
+						 true);
+#endif
+		put_online_cpus();
+		return err;
+	}
 
 Q: How do we determine how many CPUs are available for hotplug.
 A: There is no clear spec defined way from ACPI that can give us that

Documentation/device-mapper/snapshot.txt

@@ -8,13 +8,19 @@ the block device which are also writable without interfering with the
 original content;
 *) To create device "forks", i.e. multiple different versions of the
 same data stream.
+*) To merge a snapshot of a block device back into the snapshot's origin
+device.
 
+In the first two cases, dm copies only the chunks of data that get
+changed and uses a separate copy-on-write (COW) block device for
+storage.
 
-In both cases, dm copies only the chunks of data that get changed and
-uses a separate copy-on-write (COW) block device for storage.
+For snapshot merge the contents of the COW storage are merged back into
+the origin device.
 
 
-There are two dm targets available: snapshot and snapshot-origin.
+There are three dm targets available:
+snapshot, snapshot-origin, and snapshot-merge.
 
 *) snapshot-origin <origin>
 
@@ -40,8 +46,25 @@ The difference is that for transient snapshots less metadata must be
 saved on disk - they can be kept in memory by the kernel.
 
 
-How this is used by LVM2
-========================
+* snapshot-merge <origin> <COW device> <persistent> <chunksize>
+
+takes the same table arguments as the snapshot target except it only
+works with persistent snapshots.  This target assumes the role of the
+"snapshot-origin" target and must not be loaded if the "snapshot-origin"
+is still present for <origin>.
+
+Creates a merging snapshot that takes control of the changed chunks
+stored in the <COW device> of an existing snapshot, through a handover
+procedure, and merges these chunks back into the <origin>.  Once merging
+has started (in the background) the <origin> may be opened and the merge
+will continue while I/O is flowing to it.  Changes to the <origin> are
+deferred until the merging snapshot's corresponding chunk(s) have been
+merged.  Once merging has started the snapshot device, associated with
+the "snapshot" target, will return -EIO when accessed.
+
+
+How snapshot is used by LVM2
+============================
 When you create the first LVM2 snapshot of a volume, four dm devices are used:
 
 1) a device containing the original mapping table of the source volume;
@@ -72,3 +95,74 @@ brw-------  1 root root 254, 12 29 ago 18:15 /dev/mapper/volumeGroup-snap-cow
 brw-------  1 root root 254, 13 29 ago 18:15 /dev/mapper/volumeGroup-snap
 brw-------  1 root root 254, 10 29 ago 18:14 /dev/mapper/volumeGroup-base
 
+
+How snapshot-merge is used by LVM2
+==================================
+A merging snapshot assumes the role of the "snapshot-origin" while
+merging.  As such the "snapshot-origin" is replaced with
+"snapshot-merge".  The "-real" device is not changed and the "-cow"
+device is renamed to <origin name>-cow to aid LVM2's cleanup of the
+merging snapshot after it completes.  The "snapshot" that hands over its
+COW device to the "snapshot-merge" is deactivated (unless using lvchange
+--refresh); but if it is left active it will simply return I/O errors.
+
+A snapshot will merge into its origin with the following command:
+
+lvconvert --merge volumeGroup/snap
+
+we'll now have this situation:
+
+# dmsetup table|grep volumeGroup
+
+volumeGroup-base-real: 0 2097152 linear 8:19 384
+volumeGroup-base-cow: 0 204800 linear 8:19 2097536
+volumeGroup-base: 0 2097152 snapshot-merge 254:11 254:12 P 16
+
+# ls -lL /dev/mapper/volumeGroup-*
+brw-------  1 root root 254, 11 29 ago 18:15 /dev/mapper/volumeGroup-base-real
+brw-------  1 root root 254, 12 29 ago 18:16 /dev/mapper/volumeGroup-base-cow
+brw-------  1 root root 254, 10 29 ago 18:16 /dev/mapper/volumeGroup-base
+
+
+How to determine when a merging is complete
+===========================================
+The snapshot-merge and snapshot status lines end with:
+  <sectors_allocated>/<total_sectors> <metadata_sectors>
+
+Both <sectors_allocated> and <total_sectors> include both data and metadata.
+During merging, the number of sectors allocated gets smaller and
+smaller.  Merging has finished when the number of sectors holding data
+is zero, in other words <sectors_allocated> == <metadata_sectors>.
+
+Here is a practical example (using a hybrid of lvm and dmsetup commands):
+
+# lvs
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup owi-a- 4.00g
+  snap    volumeGroup swi-a- 1.00g base  18.97
+
+# dmsetup status volumeGroup-snap
+0 8388608 snapshot 397896/2097152 1560
+                                  ^^^^ metadata sectors
+
+# lvconvert --merge -b volumeGroup/snap
+  Merging of volume snap started.
+
+# lvs volumeGroup/snap
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup Owi-a- 4.00g          17.23
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 281688/2097152 1104
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 180480/2097152 712
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 16/2097152 16
+
+Merging has finished.
+
+# lvs
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup owi-a- 4.00g

Documentation/dontdiff

@@ -69,7 +69,6 @@ av_permissions.h
 bbootsect
 bin2c
 binkernel.spec
-binoffset
 bootsect
 bounds.h
 bsetup
@@ -103,6 +102,7 @@ gconf
 gen-devlist
 gen_crc32table
 gen_init_cpio
+generated
 genheaders
 genksyms
 *_gray256.c

Documentation/driver-model/driver.txt

@@ -226,5 +226,5 @@ struct driver_attribute driver_attr_debug;
 This can then be used to add and remove the attribute from the
 driver's directory using:
 
-int driver_create_file(struct device_driver *, struct driver_attribute *);
-void driver_remove_file(struct device_driver *, struct driver_attribute *);
+int driver_create_file(struct device_driver *, const struct driver_attribute *);
+void driver_remove_file(struct device_driver *, const struct driver_attribute *);

Documentation/dvb/get_dvb_firmware

@@ -26,7 +26,7 @@ use IO::Handle;
 		"dec3000s", "vp7041", "dibusb", "nxt2002", "nxt2004",
 		"or51211", "or51132_qam", "or51132_vsb", "bluebird",
 		"opera1", "cx231xx", "cx18", "cx23885", "pvrusb2", "mpc718",
-		"af9015");
+		"af9015", "ngene");
 
 # Check args
 syntax() if (scalar(@ARGV) != 1);
@@ -39,7 +39,7 @@ for ($i=0; $i < scalar(@components); $i++) {
 	die $@ if $@;
 	print STDERR <<EOF;
 Firmware(s) $outfile extracted successfully.
-Now copy it(they) to either /usr/lib/hotplug/firmware or /lib/firmware
+Now copy it(them) to either /usr/lib/hotplug/firmware or /lib/firmware
 (depending on configuration of firmware hotplug).
 EOF
 	exit(0);
@@ -549,6 +549,24 @@ sub af9015 {
 	close INFILE;
 }
 
+sub ngene {
+    my $url = "http://www.digitaldevices.de/download/";
+    my $file1 = "ngene_15.fw";
+    my $hash1 = "d798d5a757121174f0dbc5f2833c0c85";
+    my $file2 = "ngene_17.fw";
+    my $hash2 = "26b687136e127b8ac24b81e0eeafc20b";
+
+    checkstandard();
+
+    wgetfile($file1, $url . $file1);
+    verify($file1, $hash1);
+
+    wgetfile($file2, $url . $file2);
+    verify($file2, $hash2);
+
+    "$file1, $file2";
+}
+
 # ---------------------------------------------------------------
 # Utilities
 
@@ -667,6 +685,7 @@ sub delzero{
 sub syntax() {
     print STDERR "syntax: get_dvb_firmware <component>\n";
     print STDERR "Supported components:\n";
+    @components = sort @components;
     for($i=0; $i < scalar(@components); $i++) {
 	print STDERR "\t" . $components[$i] . "\n";
     }

Documentation/fault-injection/fault-injection.txt

@@ -143,8 +143,8 @@ o provide a way to configure fault attributes
   failslab, fail_page_alloc, and fail_make_request use this way.
   Helper functions:
 
-	init_fault_attr_entries(entries, attr, name);
-	void cleanup_fault_attr_entries(entries);
+	init_fault_attr_dentries(entries, attr, name);
+	void cleanup_fault_attr_dentries(entries);
 
 - module parameters
 

Documentation/fault-injection/provoke-crashes.txt

@@ -0,0 +1,38 @@
+The lkdtm module provides an interface to crash or injure the kernel at
+predefined crashpoints to evaluate the reliability of crash dumps obtained
+using different dumping solutions. The module uses KPROBEs to instrument
+crashing points, but can also crash the kernel directly without KRPOBE
+support.
+
+
+You can provide the way either through module arguments when inserting
+the module, or through a debugfs interface.
+
+Usage: insmod lkdtm.ko [recur_count={>0}] cpoint_name=<> cpoint_type=<>
+				[cpoint_count={>0}]
+
+  recur_count : Recursion level for the stack overflow test. Default is 10.
+
+  cpoint_name : Crash point where the kernel is to be crashed. It can be
+	 one of INT_HARDWARE_ENTRY, INT_HW_IRQ_EN, INT_TASKLET_ENTRY,
+	 FS_DEVRW, MEM_SWAPOUT, TIMERADD, SCSI_DISPATCH_CMD,
+	 IDE_CORE_CP, DIRECT
+
+  cpoint_type : Indicates the action to be taken on hitting the crash point.
+     It can be one of PANIC, BUG, EXCEPTION, LOOP, OVERFLOW,
+     CORRUPT_STACK, UNALIGNED_LOAD_STORE_WRITE, OVERWRITE_ALLOCATION,
+     WRITE_AFTER_FREE,
+
+  cpoint_count : Indicates the number of times the crash point is to be hit
+    to trigger an action. The default is 10.
+
+You can also induce failures by mounting debugfs and writing the type to
+<mountpoint>/provoke-crash/<crashpoint>. E.g.,
+
+  mount -t debugfs debugfs /mnt
+  echo EXCEPTION > /mnt/provoke-crash/INT_HARDWARE_ENTRY
+
+
+A special file is `DIRECT' which will induce the crash directly without
+KPROBE instrumentation. This mode is the only one available when the module
+is built on a kernel without KPROBEs support.

Documentation/fb/viafb.txt

@@ -7,7 +7,7 @@
     VIA UniChrome Family(CLE266, PM800 / CN400 / CN300,
                         P4M800CE / P4M800Pro / CN700 / VN800,
                         CX700 / VX700, K8M890, P4M890,
-                        CN896 / P4M900, VX800)
+                        CN896 / P4M900, VX800, VX855)
 
 [Driver features]
 ------------------------
@@ -154,13 +154,6 @@
         0 : No Dual Edge Panel (default)
         1 : Dual Edge Panel
 
-    viafb_video_dev:
-        This option is used to specify video output devices(CRT, DVI, LCD) for
-        duoview case.
-        For example:
-        To output video on DVI, we should use:
-            modprobe viafb viafb_video_dev=DVI...
-
     viafb_lcd_port:
         This option is used to specify LCD output port,
         available values are "DVP0" "DVP1" "DFP_HIGHLOW" "DFP_HIGH" "DFP_LOW".
@@ -181,9 +174,6 @@ Notes:
        and bpp, need to call VIAFB specified ioctl interface VIAFB_SET_DEVICE
        instead of calling common ioctl function FBIOPUT_VSCREENINFO since
        viafb doesn't support multi-head well, or it will cause screen crush.
-    4. VX800 2D accelerator hasn't been supported in this driver yet. When
-       using driver on VX800, the driver will disable the acceleration
-       function as default.
 
 
 [Configure viafb with "fbset" tool]

Documentation/feature-removal-schedule.txt

@@ -6,21 +6,6 @@ be removed from this file.
 
 ---------------------------
 
-What:	USER_SCHED
-When:	2.6.34
-
-Why:	USER_SCHED was implemented as a proof of concept for group scheduling.
-	The effect of USER_SCHED can already be achieved from userspace with
-	the help of libcgroup. The removal of USER_SCHED will also simplify
-	the scheduler code with the removal of one major ifdef. There are also
-	issues USER_SCHED has with USER_NS. A decision was taken not to fix
-	those and instead remove USER_SCHED. Also new group scheduling
-	features will not be implemented for USER_SCHED.
-
-Who:	Dhaval Giani <dhaval@linux.vnet.ibm.com>
-
----------------------------
-
 What:	PRISM54
 When:	2.6.34
 
@@ -64,6 +49,17 @@ Who:	Robin Getz <rgetz@blackfin.uclinux.org> & Matt Mackall <mpm@selenic.com>
 
 ---------------------------
 
+What:	Deprecated snapshot ioctls
+When:	2.6.36
+
+Why:	The ioctls in kernel/power/user.c were marked as deprecated long time
+	ago. Now they notify users about that so that they need to replace
+	their userspace. After some more time, remove them completely.
+
+Who:	Jiri Slaby <jirislaby@gmail.com>
+
+---------------------------
+
 What:	The ieee80211_regdom module parameter
 When:	March 2010 / desktop catchup
 
@@ -88,27 +84,6 @@ Who:	Luis R. Rodriguez <lrodriguez@atheros.com>
 
 ---------------------------
 
-What:	CONFIG_WIRELESS_OLD_REGULATORY - old static regulatory information
-When:	March 2010 / desktop catchup
-
-Why:	The old regulatory infrastructure has been replaced with a new one
-	which does not require statically defined regulatory domains. We do
-	not want to keep static regulatory domains in the kernel due to the
-	the dynamic nature of regulatory law and localization. We kept around
-	the old static definitions for the regulatory domains of:
-
-		* US
-		* JP
-		* EU
-
-	and used by default the US when CONFIG_WIRELESS_OLD_REGULATORY was
-	set. We will remove this option once the standard Linux desktop catches
-	up with the new userspace APIs we have implemented.
-
-Who:	Luis R. Rodriguez <lrodriguez@atheros.com>
-
----------------------------
-
 What:	dev->power.power_state
 When:	July 2007
 Why:	Broken design for runtime control over driver power states, confusing
@@ -142,19 +117,25 @@ Who:	Mauro Carvalho Chehab <mchehab@infradead.org>
 ---------------------------
 
 What:	PCMCIA control ioctl (needed for pcmcia-cs [cardmgr, cardctl])
-When:	November 2005
+When:	2.6.35/2.6.36
 Files:	drivers/pcmcia/: pcmcia_ioctl.c
 Why:	With the 16-bit PCMCIA subsystem now behaving (almost) like a
 	normal hotpluggable bus, and with it using the default kernel
 	infrastructure (hotplug, driver core, sysfs) keeping the PCMCIA
 	control ioctl needed by cardmgr and cardctl from pcmcia-cs is
-	unnecessary, and makes further cleanups and integration of the
+	unnecessary and potentially harmful (it does not provide for
+	proper locking), and makes further cleanups and integration of the
 	PCMCIA subsystem into the Linux kernel device driver model more
 	difficult. The features provided by cardmgr and cardctl are either
 	handled by the kernel itself now or are available in the new
 	pcmciautils package available at
 	http://kernel.org/pub/linux/utils/kernel/pcmcia/
-Who:	Dominik Brodowski <linux@brodo.de>
+
+	For all architectures except ARM, the associated config symbol
+	has been removed from kernel 2.6.34; for ARM, it will be likely
+	be removed from kernel 2.6.35. The actual code will then likely
+	be removed from kernel 2.6.36.
+Who:	Dominik Brodowski <linux@dominikbrodowski.net>
 
 ---------------------------
 
@@ -291,22 +272,6 @@ Who:	Michael Buesch <mb@bu3sch.de>
 
 ---------------------------
 
-What:	usedac i386 kernel parameter
-When:	2.6.27
-Why:	replaced by allowdac and no dac combination
-Who:	Glauber Costa <gcosta@redhat.com>
-
----------------------------
-
-What: print_fn_descriptor_symbol()
-When: October 2009
-Why:  The %pF vsprintf format provides the same functionality in a
-      simpler way.  print_fn_descriptor_symbol() is deprecated but
-      still present to give out-of-tree modules time to change.
-Who:  Bjorn Helgaas <bjorn.helgaas@hp.com>
-
----------------------------
-
 What:	/sys/o2cb symlink
 When:	January 2010
 Why:	/sys/fs/o2cb is the proper location for this information - /sys/o2cb
@@ -484,9 +449,136 @@ Who:	Alok N Kataria <akataria@vmware.com>
 
 ----------------------------
 
-What:	adt7473 hardware monitoring driver
-When:	February 2010
-Why:	Obsoleted by the adt7475 driver.
-Who:	Jean Delvare <khali@linux-fr.org>
+What:	Support for lcd_switch and display_get in asus-laptop driver
+When:	March 2010
+Why:	These two features use non-standard interfaces. There are the
+	only features that really need multiple path to guess what's
+	the right method name on a specific laptop.
 
----------------------------
+	Removing them will allow to remove a lot of code an significantly
+	clean the drivers.
+
+	This will affect the backlight code which won't be able to know
+	if the backlight is on or off. The platform display file will also be
+	write only (like the one in eeepc-laptop).
+
+	This should'nt affect a lot of user because they usually know
+	when their display is on or off.
+
+Who:	Corentin Chary <corentin.chary@gmail.com>
+
+----------------------------
+
+What:	usbvideo quickcam_messenger driver
+When:	2.6.35
+Files:	drivers/media/video/usbvideo/quickcam_messenger.[ch]
+Why:	obsolete v4l1 driver replaced by gspca_stv06xx
+Who:	Hans de Goede <hdegoede@redhat.com>
+
+----------------------------
+
+What:	ov511 v4l1 driver
+When:	2.6.35
+Files:	drivers/media/video/ov511.[ch]
+Why:	obsolete v4l1 driver replaced by gspca_ov519
+Who:	Hans de Goede <hdegoede@redhat.com>
+
+----------------------------
+
+What:	w9968cf v4l1 driver
+When:	2.6.35
+Files:	drivers/media/video/w9968cf*.[ch]
+Why:	obsolete v4l1 driver replaced by gspca_ov519
+Who:	Hans de Goede <hdegoede@redhat.com>
+
+----------------------------
+
+What:	ovcamchip sensor framework
+When:	2.6.35
+Files:	drivers/media/video/ovcamchip/*
+Why:	Only used by obsoleted v4l1 drivers
+Who:	Hans de Goede <hdegoede@redhat.com>
+
+----------------------------
+
+What:	stv680 v4l1 driver
+When:	2.6.35
+Files:	drivers/media/video/stv680.[ch]
+Why:	obsolete v4l1 driver replaced by gspca_stv0680
+Who:	Hans de Goede <hdegoede@redhat.com>
+
+----------------------------
+
+What:	zc0301 v4l driver
+When:	2.6.35
+Files:	drivers/media/video/zc0301/*
+Why:	Duplicate functionality with the gspca_zc3xx driver, zc0301 only
+	supports 2 USB-ID's (because it only supports a limited set of
+	sensors) wich are also supported by the gspca_zc3xx driver
+	(which supports 53 USB-ID's in total)
+Who:	Hans de Goede <hdegoede@redhat.com>
+
+----------------------------
+
+What:	corgikbd, spitzkbd, tosakbd driver
+When:	2.6.35
+Files:	drivers/input/keyboard/{corgi,spitz,tosa}kbd.c
+Why:	We now have a generic GPIO based matrix keyboard driver that
+	are fully capable of handling all the keys on these devices.
+	The original drivers manipulate the GPIO registers directly
+	and so are difficult to maintain.
+Who:	Eric Miao <eric.y.miao@gmail.com>
+
+----------------------------
+
+What:	corgi_ssp and corgi_ts driver
+When:	2.6.35
+Files:	arch/arm/mach-pxa/corgi_ssp.c, drivers/input/touchscreen/corgi_ts.c
+Why:	The corgi touchscreen is now deprecated in favour of the generic
+	ads7846.c driver. The noise reduction technique used in corgi_ts.c,
+	that's to wait till vsync before ADC sampling, is also integrated into
+	ads7846 driver now. Provided that the original driver is not generic
+	and is difficult to maintain, it will be removed later.
+Who:	Eric Miao <eric.y.miao@gmail.com>
+
+----------------------------
+
+What:	capifs
+When:	February 2011
+Files:	drivers/isdn/capi/capifs.*
+Why:	udev fully replaces this special file system that only contains CAPI
+	NCCI TTY device nodes. User space (pppdcapiplugin) works without
+	noticing the difference.
+Who:	Jan Kiszka <jan.kiszka@web.de>
+
+----------------------------
+
+What:	KVM memory aliases support
+When:	July 2010
+Why:	Memory aliasing support is used for speeding up guest vga access
+	through the vga windows.
+
+	Modern userspace no longer uses this feature, so it's just bitrotted
+	code and can be removed with no impact.
+Who:	Avi Kivity <avi@redhat.com>
+
+----------------------------
+
+What:	KVM kernel-allocated memory slots
+When:	July 2010
+Why:	Since 2.6.25, kvm supports user-allocated memory slots, which are
+	much more flexible than kernel-allocated slots.  All current userspace
+	supports the newer interface and this code can be removed with no
+	impact.
+Who:	Avi Kivity <avi@redhat.com>
+
+----------------------------
+
+What:	KVM paravirt mmu host support
+When:	January 2011
+Why:	The paravirt mmu host support is slower than non-paravirt mmu, both
+	on newer and older hardware.  It is already not exposed to the guest,
+	and kept only for live migration purposes.
+Who:	Avi Kivity <avi@redhat.com>
+
+----------------------------

Documentation/filesystems/00-INDEX

@@ -1,7 +1,5 @@
 00-INDEX
 	- this file (info on some of the filesystems supported by linux).
-Exporting
-	- explanation of how to make filesystems exportable.
 Locking
 	- info on locking rules as they pertain to Linux VFS.
 9p.txt
@@ -64,16 +62,14 @@ jfs.txt
 	- info and mount options for the JFS filesystem.
 locks.txt
 	- info on file locking implementations, flock() vs. fcntl(), etc.
+logfs.txt
+	- info on the LogFS flash filesystem.
 mandatory-locking.txt
 	- info on the Linux implementation of Sys V mandatory file locking.
 ncpfs.txt
 	- info on Novell Netware(tm) filesystem using NCP protocol.
-nfs41-server.txt
-	- info on the Linux server implementation of NFSv4 minor version 1.
-nfs-rdma.txt
-	- how to install and setup the Linux NFS/RDMA client and server software.
-nfsroot.txt
-	- short guide on setting up a diskless box with NFS root filesystem.
+nfs/
+	- nfs-related documentation.
 nilfs2.txt
 	- info and mount options for the NILFS2 filesystem.
 ntfs.txt
@@ -92,8 +88,6 @@ relay.txt
 	- info on relay, for efficient streaming from kernel to user space.
 romfs.txt
 	- description of the ROMFS filesystem.
-rpc-cache.txt
-	- introduction to the caching mechanisms in the sunrpc layer.
 seq_file.txt
 	- how to use the seq_file API
 sharedsubtree.txt

Documentation/filesystems/Locking

@@ -460,13 +460,6 @@ in sys_read() and friends.
 
 --------------------------- dquot_operations -------------------------------
 prototypes:
-	int (*initialize) (struct inode *, int);
-	int (*drop) (struct inode *);
-	int (*alloc_space) (struct inode *, qsize_t, int);
-	int (*alloc_inode) (const struct inode *, unsigned long);
-	int (*free_space) (struct inode *, qsize_t);
-	int (*free_inode) (const struct inode *, unsigned long);
-	int (*transfer) (struct inode *, struct iattr *);
 	int (*write_dquot) (struct dquot *);
 	int (*acquire_dquot) (struct dquot *);
 	int (*release_dquot) (struct dquot *);
@@ -479,13 +472,6 @@ a proper locking wrt the filesystem and call the generic quota operations.
 What filesystem should expect from the generic quota functions:
 
 		FS recursion	Held locks when called
-initialize:	yes		maybe dqonoff_sem
-drop:		yes		-
-alloc_space:	->mark_dirty()	-
-alloc_inode:	->mark_dirty()	-
-free_space:	->mark_dirty()	-
-free_inode:	->mark_dirty()	-
-transfer:	yes		-
 write_dquot:	yes		dqonoff_sem or dqptr_sem
 acquire_dquot:	yes		dqonoff_sem or dqptr_sem
 release_dquot:	yes		dqonoff_sem or dqptr_sem
@@ -495,10 +481,6 @@ write_info:	yes		dqonoff_sem
 FS recursion means calling ->quota_read() and ->quota_write() from superblock
 operations.
 
-->alloc_space(), ->alloc_inode(), ->free_space(), ->free_inode() are called
-only directly by the filesystem and do not call any fs functions only
-the ->mark_dirty() operation.
-
 More details about quota locking can be found in fs/dquot.c.
 
 --------------------------- vm_operations_struct -----------------------------

Documentation/filesystems/dentry-locking.txt

@@ -62,7 +62,8 @@ changes are :
 2. Insertion of a dentry into the hash table is done using
    hlist_add_head_rcu() which take care of ordering the writes - the
    writes to the dentry must be visible before the dentry is
-   inserted. This works in conjunction with hlist_for_each_rcu() while
+   inserted. This works in conjunction with hlist_for_each_rcu(),
+   which has since been replaced by hlist_for_each_entry_rcu(), while
    walking the hash chain. The only requirement is that all
    initialization to the dentry must be done before
    hlist_add_head_rcu() since we don't have dcache_lock protection

Documentation/filesystems/ext4.txt

@@ -196,7 +196,7 @@ nobarrier		This also requires an IO stack which can support
 			also be used to enable or disable barriers, for
 			consistency with other ext4 mount options.
 
-inode_readahead=n	This tuning parameter controls the maximum
+inode_readahead_blks=n	This tuning parameter controls the maximum
 			number of inode table blocks that ext4's inode
 			table readahead algorithm will pre-read into
 			the buffer cache.  The default value is 32 blocks.

Documentation/filesystems/logfs.txt

@@ -0,0 +1,241 @@
+
+The LogFS Flash Filesystem
+==========================
+
+Specification
+=============
+
+Superblocks
+-----------
+
+Two superblocks exist at the beginning and end of the filesystem.
+Each superblock is 256 Bytes large, with another 3840 Bytes reserved
+for future purposes, making a total of 4096 Bytes.
+
+Superblock locations may differ for MTD and block devices.  On MTD the
+first non-bad block contains a superblock in the first 4096 Bytes and
+the last non-bad block contains a superblock in the last 4096 Bytes.
+On block devices, the first 4096 Bytes of the device contain the first
+superblock and the last aligned 4096 Byte-block contains the second
+superblock.
+
+For the most part, the superblocks can be considered read-only.  They
+are written only to correct errors detected within the superblocks,
+move the journal and change the filesystem parameters through tunefs.
+As a result, the superblock does not contain any fields that require
+constant updates, like the amount of free space, etc.
+
+Segments
+--------
+
+The space in the device is split up into equal-sized segments.
+Segments are the primary write unit of LogFS.  Within each segments,
+writes happen from front (low addresses) to back (high addresses.  If
+only a partial segment has been written, the segment number, the
+current position within and optionally a write buffer are stored in
+the journal.
+
+Segments are erased as a whole.  Therefore Garbage Collection may be
+required to completely free a segment before doing so.
+
+Journal
+--------
+
+The journal contains all global information about the filesystem that
+is subject to frequent change.  At mount time, it has to be scanned
+for the most recent commit entry, which contains a list of pointers to
+all currently valid entries.
+
+Object Store
+------------
+
+All space except for the superblocks and journal is part of the object
+store.  Each segment contains a segment header and a number of
+objects, each consisting of the object header and the payload.
+Objects are either inodes, directory entries (dentries), file data
+blocks or indirect blocks.
+
+Levels
+------
+
+Garbage collection (GC) may fail if all data is written
+indiscriminately.  One requirement of GC is that data is seperated
+roughly according to the distance between the tree root and the data.
+Effectively that means all file data is on level 0, indirect blocks
+are on levels 1, 2, 3 4 or 5 for 1x, 2x, 3x, 4x or 5x indirect blocks,
+respectively.  Inode file data is on level 6 for the inodes and 7-11
+for indirect blocks.
+
+Each segment contains objects of a single level only.  As a result,
+each level requires its own seperate segment to be open for writing.
+
+Inode File
+----------
+
+All inodes are stored in a special file, the inode file.  Single
+exception is the inode file's inode (master inode) which for obvious
+reasons is stored in the journal instead.  Instead of data blocks, the
+leaf nodes of the inode files are inodes.
+
+Aliases
+-------
+
+Writes in LogFS are done by means of a wandering tree.  A naïve
+implementation would require that for each write or a block, all
+parent blocks are written as well, since the block pointers have
+changed.  Such an implementation would not be very efficient.
+
+In LogFS, the block pointer changes are cached in the journal by means
+of alias entries.  Each alias consists of its logical address - inode
+number, block index, level and child number (index into block) - and
+the changed data.  Any 8-byte word can be changes in this manner.
+
+Currently aliases are used for block pointers, file size, file used
+bytes and the height of an inodes indirect tree.
+
+Segment Aliases
+---------------
+
+Related to regular aliases, these are used to handle bad blocks.
+Initially, bad blocks are handled by moving the affected segment
+content to a spare segment and noting this move in the journal with a
+segment alias, a simple (to, from) tupel.  GC will later empty this
+segment and the alias can be removed again.  This is used on MTD only.
+
+Vim
+---
+
+By cleverly predicting the life time of data, it is possible to
+seperate long-living data from short-living data and thereby reduce
+the GC overhead later.  Each type of distinc life expectency (vim) can
+have a seperate segment open for writing.  Each (level, vim) tupel can
+be open just once.  If an open segment with unknown vim is encountered
+at mount time, it is closed and ignored henceforth.
+
+Indirect Tree
+-------------
+
+Inodes in LogFS are similar to FFS-style filesystems with direct and
+indirect block pointers.  One difference is that LogFS uses a single
+indirect pointer that can be either a 1x, 2x, etc. indirect pointer.
+A height field in the inode defines the height of the indirect tree
+and thereby the indirection of the pointer.
+
+Another difference is the addressing of indirect blocks.  In LogFS,
+the first 16 pointers in the first indirect block are left empty,
+corresponding to the 16 direct pointers in the inode.  In ext2 (maybe
+others as well) the first pointer in the first indirect block
+corresponds to logical block 12, skipping the 12 direct pointers.
+So where ext2 is using arithmetic to better utilize space, LogFS keeps
+arithmetic simple and uses compression to save space.
+
+Compression
+-----------
+
+Both file data and metadata can be compressed.  Compression for file
+data can be enabled with chattr +c and disabled with chattr -c.  Doing
+so has no effect on existing data, but new data will be stored
+accordingly.  New inodes will inherit the compression flag of the
+parent directory.
+
+Metadata is always compressed.  However, the space accounting ignores
+this and charges for the uncompressed size.  Failing to do so could
+result in GC failures when, after moving some data, indirect blocks
+compress worse than previously.  Even on a 100% full medium, GC may
+not consume any extra space, so the compression gains are lost space
+to the user.
+
+However, they are not lost space to the filesystem internals.  By
+cheating the user for those bytes, the filesystem gained some slack
+space and GC will run less often and faster.
+
+Garbage Collection and Wear Leveling
+------------------------------------
+
+Garbage collection is invoked whenever the number of free segments
+falls below a threshold.  The best (known) candidate is picked based
+on the least amount of valid data contained in the segment.  All
+remaining valid data is copied elsewhere, thereby invalidating it.
+
+The GC code also checks for aliases and writes then back if their
+number gets too large.
+
+Wear leveling is done by occasionally picking a suboptimal segment for
+garbage collection.  If a stale segments erase count is significantly
+lower than the active segments' erase counts, it will be picked.  Wear
+leveling is rate limited, so it will never monopolize the device for
+more than one segment worth at a time.
+
+Values for "occasionally", "significantly lower" are compile time
+constants.
+
+Hashed directories
+------------------
+
+To satisfy efficient lookup(), directory entries are hashed and
+located based on the hash.  In order to both support large directories
+and not be overly inefficient for small directories, several hash
+tables of increasing size are used.  For each table, the hash value
+modulo the table size gives the table index.
+
+Tables sizes are chosen to limit the number of indirect blocks with a
+fully populated table to 0, 1, 2 or 3 respectively.  So the first
+table contains 16 entries, the second 512-16, etc.
+
+The last table is special in several ways.  First its size depends on
+the effective 32bit limit on telldir/seekdir cookies.  Since logfs
+uses the upper half of the address space for indirect blocks, the size
+is limited to 2^31.  Secondly the table contains hash buckets with 16
+entries each.
+
+Using single-entry buckets would result in birthday "attacks".  At
+just 2^16 used entries, hash collisions would be likely (P >= 0.5).
+My math skills are insufficient to do the combinatorics for the 17x
+collisions necessary to overflow a bucket, but testing showed that in
+10,000 runs the lowest directory fill before a bucket overflow was
+188,057,130 entries with an average of 315,149,915 entries.  So for
+directory sizes of up to a million, bucket overflows should be
+virtually impossible under normal circumstances.
+
+With carefully chosen filenames, it is obviously possible to cause an
+overflow with just 21 entries (4 higher tables + 16 entries + 1).  So
+there may be a security concern if a malicious user has write access
+to a directory.
+
+Open For Discussion
+===================
+
+Device Address Space
+--------------------
+
+A device address space is used for caching.  Both block devices and
+MTD provide functions to either read a single page or write a segment.
+Partial segments may be written for data integrity, but where possible
+complete segments are written for performance on simple block device
+flash media.
+
+Meta Inodes
+-----------
+
+Inodes are stored in the inode file, which is just a regular file for
+most purposes.  At umount time, however, the inode file needs to
+remain open until all dirty inodes are written.  So
+generic_shutdown_super() may not close this inode, but shouldn't
+complain about remaining inodes due to the inode file either.  Same
+goes for mapping inode of the device address space.
+
+Currently logfs uses a hack that essentially copies part of fs/inode.c
+code over.  A general solution would be preferred.
+
+Indirect block mapping
+----------------------
+
+With compression, the block device (or mapping inode) cannot be used
+to cache indirect blocks.  Some other place is required.  Currently
+logfs uses the top half of each inode's address space.  The low 8TB
+(on 32bit) are filled with file data, the high 8TB are used for
+indirect blocks.
+
+One problem is that 16TB files created on 64bit systems actually have
+data in the top 8TB.  But files >16TB would cause problems anyway, so
+only the limit has changed.

Documentation/filesystems/nfs/00-INDEX

@@ -0,0 +1,16 @@
+00-INDEX
+	- this file (nfs-related documentation).
+Exporting
+	- explanation of how to make filesystems exportable.
+knfsd-stats.txt
+	- statistics which the NFS server makes available to user space.
+nfs.txt
+	- nfs client, and DNS resolution for fs_locations.
+nfs41-server.txt
+	- info on the Linux server implementation of NFSv4 minor version 1.
+nfs-rdma.txt
+	- how to install and setup the Linux NFS/RDMA client and server software
+nfsroot.txt
+	- short guide on setting up a diskless box with NFS root filesystem.
+rpc-cache.txt
+	- introduction to the caching mechanisms in the sunrpc layer.

Documentation/filesystems/nfs/nfs41-server.txt

@@ -0,0 +1,221 @@
+NFSv4.1 Server Implementation
+
+Server support for minorversion 1 can be controlled using the
+/proc/fs/nfsd/versions control file.  The string output returned
+by reading this file will contain either "+4.1" or "-4.1"
+correspondingly.
+
+Currently, server support for minorversion 1 is disabled by default.
+It can be enabled at run time by writing the string "+4.1" to
+the /proc/fs/nfsd/versions control file.  Note that to write this
+control file, the nfsd service must be taken down.  Use your user-mode
+nfs-utils to set this up; see rpc.nfsd(8)
+
+(Warning: older servers will interpret "+4.1" and "-4.1" as "+4" and
+"-4", respectively.  Therefore, code meant to work on both new and old
+kernels must turn 4.1 on or off *before* turning support for version 4
+on or off; rpc.nfsd does this correctly.)
+
+The NFSv4 minorversion 1 (NFSv4.1) implementation in nfsd is based
+on RFC 5661.
+
+From the many new features in NFSv4.1 the current implementation
+focuses on the mandatory-to-implement NFSv4.1 Sessions, providing
+"exactly once" semantics and better control and throttling of the
+resources allocated for each client.
+
+Other NFSv4.1 features, Parallel NFS operations in particular,
+are still under development out of tree.
+See http://wiki.linux-nfs.org/wiki/index.php/PNFS_prototype_design
+for more information.
+
+The current implementation is intended for developers only: while it
+does support ordinary file operations on clients we have tested against
+(including the linux client), it is incomplete in ways which may limit
+features unexpectedly, cause known bugs in rare cases, or cause
+interoperability problems with future clients.  Known issues:
+
+	- gss support is questionable: currently mounts with kerberos
+	  from a linux client are possible, but we aren't really
+	  conformant with the spec (for example, we don't use kerberos
+	  on the backchannel correctly).
+	- no trunking support: no clients currently take advantage of
+	  trunking, but this is a mandatory feature, and its use is
+	  recommended to clients in a number of places.  (E.g. to ensure
+	  timely renewal in case an existing connection's retry timeouts
+	  have gotten too long; see section 8.3 of the RFC.)
+	  Therefore, lack of this feature may cause future clients to
+	  fail.
+	- Incomplete backchannel support: incomplete backchannel gss
+	  support and no support for BACKCHANNEL_CTL mean that
+	  callbacks (hence delegations and layouts) may not be
+	  available and clients confused by the incomplete
+	  implementation may fail.
+	- Server reboot recovery is unsupported; if the server reboots,
+	  clients may fail.
+	- We do not support SSV, which provides security for shared
+	  client-server state (thus preventing unauthorized tampering
+	  with locks and opens, for example).  It is mandatory for
+	  servers to support this, though no clients use it yet.
+	- Mandatory operations which we do not support, such as
+	  DESTROY_CLIENTID, FREE_STATEID, SECINFO_NO_NAME, and
+	  TEST_STATEID, are not currently used by clients, but will be
+	  (and the spec recommends their uses in common cases), and
+	  clients should not be expected to know how to recover from the
+	  case where they are not supported.  This will eventually cause
+	  interoperability failures.
+
+In addition, some limitations are inherited from the current NFSv4
+implementation:
+
+	- Incomplete delegation enforcement: if a file is renamed or
+	  unlinked, a client holding a delegation may continue to
+	  indefinitely allow opens of the file under the old name.
+
+The table below, taken from the NFSv4.1 document, lists
+the operations that are mandatory to implement (REQ), optional
+(OPT), and NFSv4.0 operations that are required not to implement (MNI)
+in minor version 1.  The first column indicates the operations that
+are not supported yet by the linux server implementation.
+
+The OPTIONAL features identified and their abbreviations are as follows:
+	pNFS	Parallel NFS
+	FDELG	File Delegations
+	DDELG	Directory Delegations
+
+The following abbreviations indicate the linux server implementation status.
+	I	Implemented NFSv4.1 operations.
+	NS	Not Supported.
+	NS*	unimplemented optional feature.
+	P	pNFS features implemented out of tree.
+	PNS	pNFS features that are not supported yet (out of tree).
+
+Operations
+
+   +----------------------+------------+--------------+----------------+
+   | Operation            | REQ, REC,  | Feature      | Definition     |
+   |                      | OPT, or    | (REQ, REC,   |                |
+   |                      | MNI        | or OPT)      |                |
+   +----------------------+------------+--------------+----------------+
+   | ACCESS               | REQ        |              | Section 18.1   |
+NS | BACKCHANNEL_CTL      | REQ        |              | Section 18.33  |
+NS | BIND_CONN_TO_SESSION | REQ        |              | Section 18.34  |
+   | CLOSE                | REQ        |              | Section 18.2   |
+   | COMMIT               | REQ        |              | Section 18.3   |
+   | CREATE               | REQ        |              | Section 18.4   |
+I  | CREATE_SESSION       | REQ        |              | Section 18.36  |
+NS*| DELEGPURGE           | OPT        | FDELG (REQ)  | Section 18.5   |
+   | DELEGRETURN          | OPT        | FDELG,       | Section 18.6   |
+   |                      |            | DDELG, pNFS  |                |
+   |                      |            | (REQ)        |                |
+NS | DESTROY_CLIENTID     | REQ        |              | Section 18.50  |
+I  | DESTROY_SESSION      | REQ        |              | Section 18.37  |
+I  | EXCHANGE_ID          | REQ        |              | Section 18.35  |
+NS | FREE_STATEID         | REQ        |              | Section 18.38  |
+   | GETATTR              | REQ        |              | Section 18.7   |
+P  | GETDEVICEINFO        | OPT        | pNFS (REQ)   | Section 18.40  |
+P  | GETDEVICELIST        | OPT        | pNFS (OPT)   | Section 18.41  |
+   | GETFH                | REQ        |              | Section 18.8   |
+NS*| GET_DIR_DELEGATION   | OPT        | DDELG (REQ)  | Section 18.39  |
+P  | LAYOUTCOMMIT         | OPT        | pNFS (REQ)   | Section 18.42  |
+P  | LAYOUTGET            | OPT        | pNFS (REQ)   | Section 18.43  |
+P  | LAYOUTRETURN         | OPT        | pNFS (REQ)   | Section 18.44  |
+   | LINK                 | OPT        |              | Section 18.9   |
+   | LOCK                 | REQ        |              | Section 18.10  |
+   | LOCKT                | REQ        |              | Section 18.11  |
+   | LOCKU                | REQ        |              | Section 18.12  |
+   | LOOKUP               | REQ        |              | Section 18.13  |
+   | LOOKUPP              | REQ        |              | Section 18.14  |
+   | NVERIFY              | REQ        |              | Section 18.15  |
+   | OPEN                 | REQ        |              | Section 18.16  |
+NS*| OPENATTR             | OPT        |              | Section 18.17  |
+   | OPEN_CONFIRM         | MNI        |              | N/A            |
+   | OPEN_DOWNGRADE       | REQ        |              | Section 18.18  |
+   | PUTFH                | REQ        |              | Section 18.19  |
+   | PUTPUBFH             | REQ        |              | Section 18.20  |
+   | PUTROOTFH            | REQ        |              | Section 18.21  |
+   | READ                 | REQ        |              | Section 18.22  |
+   | READDIR              | REQ        |              | Section 18.23  |
+   | READLINK             | OPT        |              | Section 18.24  |
+NS | RECLAIM_COMPLETE     | REQ        |              | Section 18.51  |
+   | RELEASE_LOCKOWNER    | MNI        |              | N/A            |
+   | REMOVE               | REQ        |              | Section 18.25  |
+   | RENAME               | REQ        |              | Section 18.26  |
+   | RENEW                | MNI        |              | N/A            |
+   | RESTOREFH            | REQ        |              | Section 18.27  |
+   | SAVEFH               | REQ        |              | Section 18.28  |
+   | SECINFO              | REQ        |              | Section 18.29  |
+NS | SECINFO_NO_NAME      | REC        | pNFS files   | Section 18.45, |
+   |                      |            | layout (REQ) | Section 13.12  |
+I  | SEQUENCE             | REQ        |              | Section 18.46  |
+   | SETATTR              | REQ        |              | Section 18.30  |
+   | SETCLIENTID          | MNI        |              | N/A            |
+   | SETCLIENTID_CONFIRM  | MNI        |              | N/A            |
+NS | SET_SSV              | REQ        |              | Section 18.47  |
+NS | TEST_STATEID         | REQ        |              | Section 18.48  |
+   | VERIFY               | REQ        |              | Section 18.31  |
+NS*| WANT_DELEGATION      | OPT        | FDELG (OPT)  | Section 18.49  |
+   | WRITE                | REQ        |              | Section 18.32  |
+
+Callback Operations
+
+   +-------------------------+-----------+-------------+---------------+
+   | Operation               | REQ, REC, | Feature     | Definition    |
+   |                         | OPT, or   | (REQ, REC,  |               |
+   |                         | MNI       | or OPT)     |               |
+   +-------------------------+-----------+-------------+---------------+
+   | CB_GETATTR              | OPT       | FDELG (REQ) | Section 20.1  |
+P  | CB_LAYOUTRECALL         | OPT       | pNFS (REQ)  | Section 20.3  |
+NS*| CB_NOTIFY               | OPT       | DDELG (REQ) | Section 20.4  |
+P  | CB_NOTIFY_DEVICEID      | OPT       | pNFS (OPT)  | Section 20.12 |
+NS*| CB_NOTIFY_LOCK          | OPT       |             | Section 20.11 |
+NS*| CB_PUSH_DELEG           | OPT       | FDELG (OPT) | Section 20.5  |
+   | CB_RECALL               | OPT       | FDELG,      | Section 20.2  |
+   |                         |           | DDELG, pNFS |               |
+   |                         |           | (REQ)       |               |
+NS*| CB_RECALL_ANY           | OPT       | FDELG,      | Section 20.6  |
+   |                         |           | DDELG, pNFS |               |
+   |                         |           | (REQ)       |               |
+NS | CB_RECALL_SLOT          | REQ       |             | Section 20.8  |
+NS*| CB_RECALLABLE_OBJ_AVAIL | OPT       | DDELG, pNFS | Section 20.7  |
+   |                         |           | (REQ)       |               |
+I  | CB_SEQUENCE             | OPT       | FDELG,      | Section 20.9  |
+   |                         |           | DDELG, pNFS |               |
+   |                         |           | (REQ)       |               |
+NS*| CB_WANTS_CANCELLED      | OPT       | FDELG,      | Section 20.10 |
+   |                         |           | DDELG, pNFS |               |
+   |                         |           | (REQ)       |               |
+   +-------------------------+-----------+-------------+---------------+
+
+Implementation notes:
+
+DELEGPURGE:
+* mandatory only for servers that support CLAIM_DELEGATE_PREV and/or
+  CLAIM_DELEG_PREV_FH (which allows clients to keep delegations that
+  persist across client reboots).  Thus we need not implement this for
+  now.
+
+EXCHANGE_ID:
+* only SP4_NONE state protection supported
+* implementation ids are ignored
+
+CREATE_SESSION:
+* backchannel attributes are ignored
+* backchannel security parameters are ignored
+
+SEQUENCE:
+* no support for dynamic slot table renegotiation (optional)
+
+nfsv4.1 COMPOUND rules:
+The following cases aren't supported yet:
+* Enforcing of NFS4ERR_NOT_ONLY_OP for: BIND_CONN_TO_SESSION, CREATE_SESSION,
+  DESTROY_CLIENTID, DESTROY_SESSION, EXCHANGE_ID.
+* DESTROY_SESSION MUST be the final operation in the COMPOUND request.
+
+Nonstandard compound limitations:
+* No support for a sessions fore channel RPC compound that requires both a
+  ca_maxrequestsize request and a ca_maxresponsesize reply, so we may
+  fail to live up to the promise we made in CREATE_SESSION fore channel
+  negotiation.
+* No more than one IO operation (read, write, readdir) allowed per
+  compound.

Documentation/filesystems/nfs41-server.txt

@@ -1,215 +0,0 @@
-NFSv4.1 Server Implementation
-
-Server support for minorversion 1 can be controlled using the
-/proc/fs/nfsd/versions control file.  The string output returned
-by reading this file will contain either "+4.1" or "-4.1"
-correspondingly.
-
-Currently, server support for minorversion 1 is disabled by default.
-It can be enabled at run time by writing the string "+4.1" to
-the /proc/fs/nfsd/versions control file.  Note that to write this
-control file, the nfsd service must be taken down.  Use your user-mode
-nfs-utils to set this up; see rpc.nfsd(8)
-
-(Warning: older servers will interpret "+4.1" and "-4.1" as "+4" and
-"-4", respectively.  Therefore, code meant to work on both new and old
-kernels must turn 4.1 on or off *before* turning support for version 4
-on or off; rpc.nfsd does this correctly.)
-
-The NFSv4 minorversion 1 (NFSv4.1) implementation in nfsd is based
-on the latest NFSv4.1 Internet Draft:
-http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-29
-
-From the many new features in NFSv4.1 the current implementation
-focuses on the mandatory-to-implement NFSv4.1 Sessions, providing
-"exactly once" semantics and better control and throttling of the
-resources allocated for each client.
-
-Other NFSv4.1 features, Parallel NFS operations in particular,
-are still under development out of tree.
-See http://wiki.linux-nfs.org/wiki/index.php/PNFS_prototype_design
-for more information.
-
-The current implementation is intended for developers only: while it
-does support ordinary file operations on clients we have tested against
-(including the linux client), it is incomplete in ways which may limit
-features unexpectedly, cause known bugs in rare cases, or cause
-interoperability problems with future clients.  Known issues:
-
-	- gss support is questionable: currently mounts with kerberos
-	  from a linux client are possible, but we aren't really
-	  conformant with the spec (for example, we don't use kerberos
-	  on the backchannel correctly).
-	- no trunking support: no clients currently take advantage of
-	  trunking, but this is a mandatory failure, and its use is
-	  recommended to clients in a number of places.  (E.g. to ensure
-	  timely renewal in case an existing connection's retry timeouts
-	  have gotten too long; see section 8.3 of the draft.)
-	  Therefore, lack of this feature may cause future clients to
-	  fail.
-	- Incomplete backchannel support: incomplete backchannel gss
-	  support and no support for BACKCHANNEL_CTL mean that
-	  callbacks (hence delegations and layouts) may not be
-	  available and clients confused by the incomplete
-	  implementation may fail.
-	- Server reboot recovery is unsupported; if the server reboots,
-	  clients may fail.
-	- We do not support SSV, which provides security for shared
-	  client-server state (thus preventing unauthorized tampering
-	  with locks and opens, for example).  It is mandatory for
-	  servers to support this, though no clients use it yet.
-	- Mandatory operations which we do not support, such as
-	  DESTROY_CLIENTID, FREE_STATEID, SECINFO_NO_NAME, and
-	  TEST_STATEID, are not currently used by clients, but will be
-	  (and the spec recommends their uses in common cases), and
-	  clients should not be expected to know how to recover from the
-	  case where they are not supported.  This will eventually cause
-	  interoperability failures.
-
-In addition, some limitations are inherited from the current NFSv4
-implementation:
-
-	- Incomplete delegation enforcement: if a file is renamed or
-	  unlinked, a client holding a delegation may continue to
-	  indefinitely allow opens of the file under the old name.
-
-The table below, taken from the NFSv4.1 document, lists
-the operations that are mandatory to implement (REQ), optional
-(OPT), and NFSv4.0 operations that are required not to implement (MNI)
-in minor version 1.  The first column indicates the operations that
-are not supported yet by the linux server implementation.
-
-The OPTIONAL features identified and their abbreviations are as follows:
-	pNFS	Parallel NFS
-	FDELG	File Delegations
-	DDELG	Directory Delegations
-
-The following abbreviations indicate the linux server implementation status.
-	I	Implemented NFSv4.1 operations.
-	NS	Not Supported.
-	NS*	unimplemented optional feature.
-	P	pNFS features implemented out of tree.
-	PNS	pNFS features that are not supported yet (out of tree).
-
-Operations
-
-   +----------------------+------------+--------------+----------------+
-   | Operation            | REQ, REC,  | Feature      | Definition     |
-   |                      | OPT, or    | (REQ, REC,   |                |
-   |                      | MNI        | or OPT)      |                |
-   +----------------------+------------+--------------+----------------+
-   | ACCESS               | REQ        |              | Section 18.1   |
-NS | BACKCHANNEL_CTL      | REQ        |              | Section 18.33  |
-NS | BIND_CONN_TO_SESSION | REQ        |              | Section 18.34  |
-   | CLOSE                | REQ        |              | Section 18.2   |
-   | COMMIT               | REQ        |              | Section 18.3   |
-   | CREATE               | REQ        |              | Section 18.4   |
-I  | CREATE_SESSION       | REQ        |              | Section 18.36  |
-NS*| DELEGPURGE           | OPT        | FDELG (REQ)  | Section 18.5   |
-   | DELEGRETURN          | OPT        | FDELG,       | Section 18.6   |
-   |                      |            | DDELG, pNFS  |                |
-   |                      |            | (REQ)        |                |
-NS | DESTROY_CLIENTID     | REQ        |              | Section 18.50  |
-I  | DESTROY_SESSION      | REQ        |              | Section 18.37  |
-I  | EXCHANGE_ID          | REQ        |              | Section 18.35  |
-NS | FREE_STATEID         | REQ        |              | Section 18.38  |
-   | GETATTR              | REQ        |              | Section 18.7   |
-P  | GETDEVICEINFO        | OPT        | pNFS (REQ)   | Section 18.40  |
-P  | GETDEVICELIST        | OPT        | pNFS (OPT)   | Section 18.41  |
-   | GETFH                | REQ        |              | Section 18.8   |
-NS*| GET_DIR_DELEGATION   | OPT        | DDELG (REQ)  | Section 18.39  |
-P  | LAYOUTCOMMIT         | OPT        | pNFS (REQ)   | Section 18.42  |
-P  | LAYOUTGET            | OPT        | pNFS (REQ)   | Section 18.43  |
-P  | LAYOUTRETURN         | OPT        | pNFS (REQ)   | Section 18.44  |
-   | LINK                 | OPT        |              | Section 18.9   |
-   | LOCK                 | REQ        |              | Section 18.10  |
-   | LOCKT                | REQ        |              | Section 18.11  |
-   | LOCKU                | REQ        |              | Section 18.12  |
-   | LOOKUP               | REQ        |              | Section 18.13  |
-   | LOOKUPP              | REQ        |              | Section 18.14  |
-   | NVERIFY              | REQ        |              | Section 18.15  |
-   | OPEN                 | REQ        |              | Section 18.16  |
-NS*| OPENATTR             | OPT        |              | Section 18.17  |
-   | OPEN_CONFIRM         | MNI        |              | N/A            |
-   | OPEN_DOWNGRADE       | REQ        |              | Section 18.18  |
-   | PUTFH                | REQ        |              | Section 18.19  |
-   | PUTPUBFH             | REQ        |              | Section 18.20  |
-   | PUTROOTFH            | REQ        |              | Section 18.21  |
-   | READ                 | REQ        |              | Section 18.22  |
-   | READDIR              | REQ        |              | Section 18.23  |
-   | READLINK             | OPT        |              | Section 18.24  |
-NS | RECLAIM_COMPLETE     | REQ        |              | Section 18.51  |
-   | RELEASE_LOCKOWNER    | MNI        |              | N/A            |
-   | REMOVE               | REQ        |              | Section 18.25  |
-   | RENAME               | REQ        |              | Section 18.26  |
-   | RENEW                | MNI        |              | N/A            |
-   | RESTOREFH            | REQ        |              | Section 18.27  |
-   | SAVEFH               | REQ        |              | Section 18.28  |
-   | SECINFO              | REQ        |              | Section 18.29  |
-NS | SECINFO_NO_NAME      | REC        | pNFS files   | Section 18.45, |
-   |                      |            | layout (REQ) | Section 13.12  |
-I  | SEQUENCE             | REQ        |              | Section 18.46  |
-   | SETATTR              | REQ        |              | Section 18.30  |
-   | SETCLIENTID          | MNI        |              | N/A            |
-   | SETCLIENTID_CONFIRM  | MNI        |              | N/A            |
-NS | SET_SSV              | REQ        |              | Section 18.47  |
-NS | TEST_STATEID         | REQ        |              | Section 18.48  |
-   | VERIFY               | REQ        |              | Section 18.31  |
-NS*| WANT_DELEGATION      | OPT        | FDELG (OPT)  | Section 18.49  |
-   | WRITE                | REQ        |              | Section 18.32  |
-
-Callback Operations
-
-   +-------------------------+-----------+-------------+---------------+
-   | Operation               | REQ, REC, | Feature     | Definition    |
-   |                         | OPT, or   | (REQ, REC,  |               |
-   |                         | MNI       | or OPT)     |               |
-   +-------------------------+-----------+-------------+---------------+
-   | CB_GETATTR              | OPT       | FDELG (REQ) | Section 20.1  |
-P  | CB_LAYOUTRECALL         | OPT       | pNFS (REQ)  | Section 20.3  |
-NS*| CB_NOTIFY               | OPT       | DDELG (REQ) | Section 20.4  |
-P  | CB_NOTIFY_DEVICEID      | OPT       | pNFS (OPT)  | Section 20.12 |
-NS*| CB_NOTIFY_LOCK          | OPT       |             | Section 20.11 |
-NS*| CB_PUSH_DELEG           | OPT       | FDELG (OPT) | Section 20.5  |
-   | CB_RECALL               | OPT       | FDELG,      | Section 20.2  |
-   |                         |           | DDELG, pNFS |               |
-   |                         |           | (REQ)       |               |
-NS*| CB_RECALL_ANY           | OPT       | FDELG,      | Section 20.6  |
-   |                         |           | DDELG, pNFS |               |
-   |                         |           | (REQ)       |               |
-NS | CB_RECALL_SLOT          | REQ       |             | Section 20.8  |
-NS*| CB_RECALLABLE_OBJ_AVAIL | OPT       | DDELG, pNFS | Section 20.7  |
-   |                         |           | (REQ)       |               |
-I  | CB_SEQUENCE             | OPT       | FDELG,      | Section 20.9  |
-   |                         |           | DDELG, pNFS |               |
-   |                         |           | (REQ)       |               |
-NS*| CB_WANTS_CANCELLED      | OPT       | FDELG,      | Section 20.10 |
-   |                         |           | DDELG, pNFS |               |
-   |                         |           | (REQ)       |               |
-   +-------------------------+-----------+-------------+---------------+
-
-Implementation notes:
-
-DELEGPURGE:
-* mandatory only for servers that support CLAIM_DELEGATE_PREV and/or
-  CLAIM_DELEG_PREV_FH (which allows clients to keep delegations that
-  persist across client reboots).  Thus we need not implement this for
-  now.
-
-EXCHANGE_ID:
-* only SP4_NONE state protection supported
-* implementation ids are ignored
-
-CREATE_SESSION:
-* backchannel attributes are ignored
-* backchannel security parameters are ignored
-
-SEQUENCE:
-* no support for dynamic slot table renegotiation (optional)
-
-nfsv4.1 COMPOUND rules:
-The following cases aren't supported yet:
-* Enforcing of NFS4ERR_NOT_ONLY_OP for: BIND_CONN_TO_SESSION, CREATE_SESSION,
-  DESTROY_CLIENTID, DESTROY_SESSION, EXCHANGE_ID.
-* DESTROY_SESSION MUST be the final operation in the COMPOUND request.
-

Documentation/filesystems/nilfs2.txt

@@ -28,7 +28,7 @@ described in the man pages included in the package.
 Project web page:    http://www.nilfs.org/en/
 Download page:       http://www.nilfs.org/en/download.html
 Git tree web page:   http://www.nilfs.org/git/
-NILFS mailing lists: http://www.nilfs.org/mailman/listinfo/users
+List info:           http://vger.kernel.org/vger-lists.html#linux-nilfs
 
 Caveats
 =======
@@ -74,6 +74,9 @@ norecovery		Disable recovery of the filesystem on mount.
 			This disables every write access on the device for
 			read-only mounts or snapshots.  This option will fail
 			for r/w mounts on an unclean volume.
+discard			Issue discard/TRIM commands to the underlying block
+			device when blocks are freed.  This is useful for SSD
+			devices and sparse/thinly-provisioned LUNs.
 
 NILFS2 usage
 ============

Documentation/filesystems/porting

@@ -140,7 +140,7 @@ Callers of notify_change() need ->i_mutex now.
 New super_block field "struct export_operations *s_export_op" for
 explicit support for exporting, e.g. via NFS.  The structure is fully
 documented at its declaration in include/linux/fs.h, and in
-Documentation/filesystems/Exporting.
+Documentation/filesystems/nfs/Exporting.
 
 Briefly it allows for the definition of decode_fh and encode_fh operations
 to encode and decode filehandles, and allows the filesystem to use

Documentation/filesystems/proc.txt

@@ -38,6 +38,7 @@ Table of Contents
   3.3	/proc/<pid>/io - Display the IO accounting fields
   3.4	/proc/<pid>/coredump_filter - Core dump filtering settings
   3.5	/proc/<pid>/mountinfo - Information about mounts
+  3.6	/proc/<pid>/comm  & /proc/<pid>/task/<tid>/comm
 
 
 ------------------------------------------------------------------------------
@@ -163,6 +164,7 @@ read the file /proc/PID/status:
   VmExe:        68 kB
   VmLib:      1412 kB
   VmPTE:        20 kb
+  VmSwap:        0 kB
   Threads:        1
   SigQ:   0/28578
   SigPnd: 0000000000000000
@@ -176,7 +178,6 @@ read the file /proc/PID/status:
   CapBnd: ffffffffffffffff
   voluntary_ctxt_switches:        0
   nonvoluntary_ctxt_switches:     1
-  Stack usage:    12 kB
 
 This shows you nearly the same information you would get if you viewed it with
 the ps  command.  In  fact,  ps  uses  the  proc  file  system  to  obtain its
@@ -188,6 +189,12 @@ memory usage. Its seven fields are explained in Table 1-3.  The stat file
 contains details information about the process itself.  Its fields are
 explained in Table 1-4.
 
+(for SMP CONFIG users)
+For making accounting scalable, RSS related information are handled in
+asynchronous manner and the vaule may not be very precise. To see a precise
+snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
+It's slow but very precise.
+
 Table 1-2: Contents of the statm files (as of 2.6.30-rc7)
 ..............................................................................
  Field                       Content
@@ -213,6 +220,7 @@ Table 1-2: Contents of the statm files (as of 2.6.30-rc7)
  VmExe                       size of text segment
  VmLib                       size of shared library code
  VmPTE                       size of page table entries
+ VmSwap                      size of swap usage (the number of referred swapents)
  Threads                     number of threads
  SigQ                        number of signals queued/max. number for queue
  SigPnd                      bitmap of pending signals for the thread
@@ -230,7 +238,6 @@ Table 1-2: Contents of the statm files (as of 2.6.30-rc7)
  Mems_allowed_list           Same as previous, but in "list format"
  voluntary_ctxt_switches     number of voluntary context switches
  nonvoluntary_ctxt_switches  number of non voluntary context switches
- Stack usage:                stack usage high water mark (round up to page size)
 ..............................................................................
 
 Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
@@ -431,6 +438,7 @@ Table 1-5: Kernel info in /proc
  modules     List of loaded modules                            
  mounts      Mounted filesystems                               
  net         Networking info (see text)                        
+ pagetypeinfo Additional page allocator information (see text)  (2.5)
  partitions  Table of partitions known to the system           
  pci	     Deprecated info of PCI bus (new way -> /proc/bus/pci/,
              decoupled by lspci					(2.4)
@@ -585,7 +593,7 @@ Node 0, zone      DMA      0      4      5      4      4      3 ...
 Node 0, zone   Normal      1      0      0      1    101      8 ...
 Node 0, zone  HighMem      2      0      0      1      1      0 ...
 
-Memory fragmentation is a problem under some workloads, and buddyinfo is a 
+External fragmentation is a problem under some workloads, and buddyinfo is a
 useful tool for helping diagnose these problems.  Buddyinfo will give you a 
 clue as to how big an area you can safely allocate, or why a previous
 allocation failed.
@@ -595,6 +603,48 @@ available.  In this case, there are 0 chunks of 2^0*PAGE_SIZE available in
 ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE 
 available in ZONE_NORMAL, etc... 
 
+More information relevant to external fragmentation can be found in
+pagetypeinfo.
+
+> cat /proc/pagetypeinfo
+Page block order: 9
+Pages per block:  512
+
+Free pages count per migrate type at order       0      1      2      3      4      5      6      7      8      9     10
+Node    0, zone      DMA, type    Unmovable      0      0      0      1      1      1      1      1      1      1      0
+Node    0, zone      DMA, type  Reclaimable      0      0      0      0      0      0      0      0      0      0      0
+Node    0, zone      DMA, type      Movable      1      1      2      1      2      1      1      0      1      0      2
+Node    0, zone      DMA, type      Reserve      0      0      0      0      0      0      0      0      0      1      0
+Node    0, zone      DMA, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
+Node    0, zone    DMA32, type    Unmovable    103     54     77      1      1      1     11      8      7      1      9
+Node    0, zone    DMA32, type  Reclaimable      0      0      2      1      0      0      0      0      1      0      0
+Node    0, zone    DMA32, type      Movable    169    152    113     91     77     54     39     13      6      1    452
+Node    0, zone    DMA32, type      Reserve      1      2      2      2      2      0      1      1      1      1      0
+Node    0, zone    DMA32, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
+
+Number of blocks type     Unmovable  Reclaimable      Movable      Reserve      Isolate
+Node 0, zone      DMA            2            0            5            1            0
+Node 0, zone    DMA32           41            6          967            2            0
+
+Fragmentation avoidance in the kernel works by grouping pages of different
+migrate types into the same contiguous regions of memory called page blocks.
+A page block is typically the size of the default hugepage size e.g. 2MB on
+X86-64. By keeping pages grouped based on their ability to move, the kernel
+can reclaim pages within a page block to satisfy a high-order allocation.
+
+The pagetypinfo begins with information on the size of a page block. It
+then gives the same type of information as buddyinfo except broken down
+by migrate-type and finishes with details on how many page blocks of each
+type exist.
+
+If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
+from libhugetlbfs http://sourceforge.net/projects/libhugetlbfs/), one can
+make an estimate of the likely number of huge pages that can be allocated
+at a given point in time. All the "Movable" blocks should be allocatable
+unless memory has been mlock()'d. Some of the Reclaimable blocks should
+also be allocatable although a lot of filesystem metadata may have to be
+reclaimed to achieve this.
+
 ..............................................................................
 
 meminfo:
@@ -1409,3 +1459,11 @@ For more information on mount propagation see:
 
   Documentation/filesystems/sharedsubtree.txt
 
+
+3.6	/proc/<pid>/comm  & /proc/<pid>/task/<tid>/comm
+--------------------------------------------------------
+These files provide a method to access a tasks comm value. It also allows for
+a task to set its own or one of its thread siblings comm value. The comm value
+is limited in size compared to the cmdline value, so writing anything longer
+then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated
+comm value.

Documentation/filesystems/seq_file.txt

@@ -248,9 +248,7 @@ code, that is done in the initialization code in the usual way:
 	{
 	        struct proc_dir_entry *entry;
 
-	        entry = create_proc_entry("sequence", 0, NULL);
-	        if (entry)
-	                entry->proc_fops = &ct_file_ops;
+	        proc_create("sequence", 0, NULL, &ct_file_ops);
 	        return 0;
 	}
 

Documentation/filesystems/sharedsubtree.txt

@@ -837,6 +837,9 @@ replicas continue to be exactly same.
 	 individual lists does not affect propagation or the way propagation
 	 tree is modified by operations.
 
+	All vfsmounts in a peer group have the same ->mnt_master.  If it is
+	non-NULL, they form a contiguous (ordered) segment of slave list.
+
 	A example propagation tree looks as shown in the figure below.
 	[ NOTE: Though it looks like a forest, if we consider all the shared
 	mounts as a conceptual entity called 'pnode', it becomes a tree]
@@ -874,8 +877,19 @@ replicas continue to be exactly same.
 
 	NOTE: The propagation tree is orthogonal to the mount tree.
 
+8B Locking:
+
+	->mnt_share, ->mnt_slave, ->mnt_slave_list, ->mnt_master are protected
+	by namespace_sem (exclusive for modifications, shared for reading).
+
+	Normally we have ->mnt_flags modifications serialized by vfsmount_lock.
+	There are two exceptions: do_add_mount() and clone_mnt().
+	The former modifies a vfsmount that has not been visible in any shared
+	data structures yet.
+	The latter holds namespace_sem and the only references to vfsmount
+	are in lists that can't be traversed without namespace_sem.
 
-8B Algorithm:
+8C Algorithm:
 
 	The crux of the implementation resides in rbind/move operation.
 

Documentation/filesystems/sysfs.txt

@@ -91,8 +91,8 @@ struct device_attribute {
 			 const char *buf, size_t count);
 };
 
-int device_create_file(struct device *, struct device_attribute *);
-void device_remove_file(struct device *, struct device_attribute *);
+int device_create_file(struct device *, const struct device_attribute *);
+void device_remove_file(struct device *, const struct device_attribute *);
 
 It also defines this helper for defining device attributes: 
 
@@ -316,8 +316,8 @@ DEVICE_ATTR(_name, _mode, _show, _store);
 
 Creation/Removal:
 
-int device_create_file(struct device *device, struct device_attribute * attr);
-void device_remove_file(struct device * dev, struct device_attribute * attr);
+int device_create_file(struct device *dev, const struct device_attribute * attr);
+void device_remove_file(struct device *dev, const struct device_attribute * attr);
 
 
 - bus drivers (include/linux/device.h)
@@ -358,7 +358,7 @@ DRIVER_ATTR(_name, _mode, _show, _store)
 
 Creation/Removal:
 
-int driver_create_file(struct device_driver *, struct driver_attribute *);
-void driver_remove_file(struct device_driver *, struct driver_attribute *);
+int driver_create_file(struct device_driver *, const struct driver_attribute *);
+void driver_remove_file(struct device_driver *, const struct driver_attribute *);
 
 

Documentation/gpio.txt

@@ -253,6 +253,70 @@ pin setup (e.g. controlling which pin the GPIO uses, pullup/pulldown).
 Also note that it's your responsibility to have stopped using a GPIO
 before you free it.
 
+Considering in most cases GPIOs are actually configured right after they
+are claimed, three additional calls are defined:
+
+	/* request a single GPIO, with initial configuration specified by
+	 * 'flags', identical to gpio_request() wrt other arguments and
+	 * return value
+	 */
+	int gpio_request_one(unsigned gpio, unsigned long flags, const char *label);
+
+	/* request multiple GPIOs in a single call
+	 */
+	int gpio_request_array(struct gpio *array, size_t num);
+
+	/* release multiple GPIOs in a single call
+	 */
+	void gpio_free_array(struct gpio *array, size_t num);
+
+where 'flags' is currently defined to specify the following properties:
+
+	* GPIOF_DIR_IN		- to configure direction as input
+	* GPIOF_DIR_OUT		- to configure direction as output
+
+	* GPIOF_INIT_LOW	- as output, set initial level to LOW
+	* GPIOF_INIT_HIGH	- as output, set initial level to HIGH
+
+since GPIOF_INIT_* are only valid when configured as output, so group valid
+combinations as:
+
+	* GPIOF_IN		- configure as input
+	* GPIOF_OUT_INIT_LOW	- configured as output, initial level LOW
+	* GPIOF_OUT_INIT_HIGH	- configured as output, initial level HIGH
+
+In the future, these flags can be extended to support more properties such
+as open-drain status.
+
+Further more, to ease the claim/release of multiple GPIOs, 'struct gpio' is
+introduced to encapsulate all three fields as:
+
+	struct gpio {
+		unsigned	gpio;
+		unsigned long	flags;
+		const char	*label;
+	};
+
+A typical example of usage:
+
+	static struct gpio leds_gpios[] = {
+		{ 32, GPIOF_OUT_INIT_HIGH, "Power LED" }, /* default to ON */
+		{ 33, GPIOF_OUT_INIT_LOW,  "Green LED" }, /* default to OFF */
+		{ 34, GPIOF_OUT_INIT_LOW,  "Red LED"   }, /* default to OFF */
+		{ 35, GPIOF_OUT_INIT_LOW,  "Blue LED"  }, /* default to OFF */
+		{ ... },
+	};
+
+	err = gpio_request_one(31, GPIOF_IN, "Reset Button");
+	if (err)
+		...
+
+	err = gpio_request_array(leds_gpios, ARRAY_SIZE(leds_gpios));
+	if (err)
+		...
+
+	gpio_free_array(leds_gpios, ARRAY_SIZE(leds_gpios));
+
 
 GPIOs mapped to IRQs
 --------------------
@@ -531,6 +595,13 @@ and have the following read/write attributes:
 		This file exists only if the pin can be configured as an
 		interrupt generating input pin.
 
+	"active_low" ... reads as either 0 (false) or 1 (true).  Write
+		any nonzero value to invert the value attribute both
+		for reading and writing.  Existing and subsequent
+		poll(2) support configuration via the edge attribute
+		for "rising" and "falling" edges will follow this
+		setting.
+
 GPIO controllers have paths like /sys/class/gpio/gpiochip42/ (for the
 controller implementing GPIOs starting at #42) and have the following
 read-only attributes:
@@ -566,6 +637,8 @@ requested using gpio_request():
 	int gpio_export_link(struct device *dev, const char *name,
 		unsigned gpio)
 
+	/* change the polarity of a GPIO node in sysfs */
+	int gpio_sysfs_set_active_low(unsigned gpio, int value);
 
 After a kernel driver requests a GPIO, it may only be made available in
 the sysfs interface by gpio_export().  The driver can control whether the
@@ -580,3 +653,9 @@ After the GPIO has been exported, gpio_export_link() allows creating
 symlinks from elsewhere in sysfs to the GPIO sysfs node.  Drivers can
 use this to provide the interface under their own device in sysfs with
 a descriptive name.
+
+Drivers can use gpio_sysfs_set_active_low() to hide GPIO line polarity
+differences between boards from user space.  This only affects the
+sysfs interface.  Polarity change can be done both before and after
+gpio_export(), and previously enabled poll(2) support for either
+rising or falling edge will be reconfigured to follow this setting.

Documentation/hwmon/adt7411

@@ -0,0 +1,42 @@
+Kernel driver adt7411
+=====================
+
+Supported chips:
+  * Analog Devices ADT7411
+    Prefix: 'adt7411'
+    Addresses scanned: 0x48, 0x4a, 0x4b
+    Datasheet: Publicly available at the Analog Devices website
+
+Author: Wolfram Sang (based on adt7470 by Darrick J. Wong)
+
+Description
+-----------
+
+This driver implements support for the Analog Devices ADT7411 chip. There may
+be other chips that implement this interface.
+
+The ADT7411 can use an I2C/SMBus compatible 2-wire interface or an
+SPI-compatible 4-wire interface. It provides a 10-bit analog to digital
+converter which measures 1 temperature, vdd and 8 input voltages. It has an
+internal temperature sensor, but an external one can also be connected (one
+loses 2 inputs then). There are high- and low-limit registers for all inputs.
+
+Check the datasheet for details.
+
+sysfs-Interface
+---------------
+
+in0_input	- vdd voltage input
+in[1-8]_input	- analog 1-8 input
+temp1_input	- temperature input
+
+Besides standard interfaces, this driver adds (0 = off, 1 = on):
+
+  adc_ref_vdd	- Use vdd as reference instead of 2.25 V
+  fast_sampling	- Sample at 22.5 kHz instead of 1.4 kHz, but drop filters
+  no_average	- Turn off averaging over 16 samples
+
+Notes
+-----
+
+SPI, external temperature sensor and limit registers are not supported yet.

Documentation/hwmon/adt7473

@@ -1,74 +0,0 @@
-Kernel driver adt7473
-======================
-
-Supported chips:
-  * Analog Devices ADT7473
-    Prefix: 'adt7473'
-    Addresses scanned: I2C 0x2C, 0x2D, 0x2E
-    Datasheet: Publicly available at the Analog Devices website
-
-Author: Darrick J. Wong
-
-This driver is depreacted, please use the adt7475 driver instead.
-
-Description
------------
-
-This driver implements support for the Analog Devices ADT7473 chip family.
-
-The ADT7473 uses the 2-wire interface compatible with the SMBUS 2.0
-specification. Using an analog to digital converter it measures three (3)
-temperatures and two (2) voltages. It has four (4) 16-bit counters for
-measuring fan speed. There are three (3) PWM outputs that can be used
-to control fan speed.
-
-A sophisticated control system for the PWM outputs is designed into the
-ADT7473 that allows fan speed to be adjusted automatically based on any of the
-three temperature sensors. Each PWM output is individually adjustable and
-programmable. Once configured, the ADT7473 will adjust the PWM outputs in
-response to the measured temperatures without further host intervention.
-This feature can also be disabled for manual control of the PWM's.
-
-Each of the measured inputs (voltage, temperature, fan speed) has
-corresponding high/low limit values. The ADT7473 will signal an ALARM if
-any measured value exceeds either limit.
-
-The ADT7473 samples all inputs continuously. The driver will not read
-the registers more often than once every other second. Further,
-configuration data is only read once per minute.
-
-Special Features
-----------------
-
-The ADT7473 have a 10-bit ADC and can therefore measure temperatures
-with 0.25 degC resolution. Temperature readings can be configured either
-for twos complement format or "Offset 64" format, wherein 63 is subtracted
-from the raw value to get the temperature value.
-
-The Analog Devices datasheet is very detailed and describes a procedure for
-determining an optimal configuration for the automatic PWM control.
-
-Configuration Notes
--------------------
-
-Besides standard interfaces driver adds the following:
-
-* PWM Control
-
-* pwm#_auto_point1_pwm and temp#_auto_point1_temp and
-* pwm#_auto_point2_pwm and temp#_auto_point2_temp -
-
-point1: Set the pwm speed at a lower temperature bound.
-point2: Set the pwm speed at a higher temperature bound.
-
-The ADT7473 will scale the pwm between the lower and higher pwm speed when
-the temperature is between the two temperature boundaries.  PWM values range
-from 0 (off) to 255 (full speed).  Fan speed will be set to maximum when the
-temperature sensor associated with the PWM control exceeds temp#_max.
-
-Notes
------
-
-The NVIDIA binary driver presents an ADT7473 chip via an on-card i2c bus.
-Unfortunately, they fail to set the i2c adapter class, so this driver may
-fail to find the chip until the nvidia driver is patched.

Documentation/hwmon/amc6821

@@ -0,0 +1,102 @@
+Kernel driver amc6821
+=====================
+
+Supported chips:
+	Texas Instruments AMC6821
+	Prefix: 'amc6821'
+	Addresses scanned: 0x18, 0x19, 0x1a, 0x2c, 0x2d, 0x2e, 0x4c, 0x4d, 0x4e
+	Datasheet: http://focus.ti.com/docs/prod/folders/print/amc6821.html
+
+Authors:
+	Tomaz Mertelj <tomaz.mertelj@guest.arnes.si>
+
+
+Description
+-----------
+
+This driver implements support for the Texas Instruments amc6821 chip.
+The chip has one on-chip and one remote temperature sensor and one pwm fan
+regulator.
+The pwm can be controlled either from software or automatically.
+
+The driver provides the following sensor accesses in sysfs:
+
+temp1_input		ro	on-chip temperature
+temp1_min		rw	"
+temp1_max		rw	"
+temp1_crit	 	rw	"
+temp1_min_alarm		ro	"
+temp1_max_alarm		ro	"
+temp1_crit_alarm	ro	"
+
+temp2_input		ro	remote temperature
+temp2_min		rw	"
+temp2_max		rw	"
+temp2_crit	 	rw	"
+temp2_min_alarm		ro	"
+temp2_max_alarm		ro	"
+temp2_crit_alarm	ro	"
+temp2_fault		ro	"
+
+fan1_input	 	ro	tachometer speed
+fan1_min		rw	"
+fan1_max		rw	"
+fan1_fault	 	ro	"
+fan1_div		rw	Fan divisor can be either 2 or 4.
+
+pwm1			rw	pwm1
+pwm1_enable		rw	regulator mode, 1=open loop, 2=fan controlled
+				by remote temperature, 3=fan controlled by
+				combination of the on-chip temperature and
+				remote-sensor temperature,
+pwm1_auto_channels_temp ro	1 if pwm_enable==2, 3 if pwm_enable==3
+pwm1_auto_point1_pwm	ro	Hardwired to 0, shared for both
+				temperature channels.
+pwm1_auto_point2_pwm	rw	This value is shared for both temperature
+				channels.
+pwm1_auto_point3_pwm	rw	Hardwired to 255, shared for both
+				temperature channels.
+
+temp1_auto_point1_temp	ro	Hardwired to temp2_auto_point1_temp
+				which is rw. Below this temperature fan stops.
+temp1_auto_point2_temp	rw	The low-temperature limit of the proportional
+				range. Below this temperature
+				pwm1 = pwm1_auto_point2_pwm. It can go from
+				0 degree C to 124 degree C in steps of
+				4 degree C. Read it out after writing to get
+				the actual value.
+temp1_auto_point3_temp	rw	Above this temperature fan runs at maximum
+				speed. It can go from temp1_auto_point2_temp.
+				It can only have certain discrete values
+				which depend on temp1_auto_point2_temp and
+				pwm1_auto_point2_pwm. Read it out after
+				writing to get the actual value.
+
+temp2_auto_point1_temp	rw	Must be between 0 degree C and 63 degree C and
+				it defines the passive cooling temperature.
+				Below this temperature the fan stops in
+				the closed loop mode.
+temp2_auto_point2_temp	rw	The low-temperature limit of the proportional
+				range. Below this temperature
+				pwm1 = pwm1_auto_point2_pwm. It can go from
+				0 degree C to 124 degree C in steps
+				of 4 degree C.
+
+temp2_auto_point3_temp	rw	Above this temperature fan runs at maximum
+				speed. It can only have certain discrete
+				values which depend on temp2_auto_point2_temp
+				and pwm1_auto_point2_pwm. Read it out after
+				writing to get actual value.
+
+
+Module parameters
+-----------------
+
+If your board has a BIOS that initializes the amc6821 correctly, you should
+load the module with: init=0.
+
+If your board BIOS doesn't initialize the chip, or you want
+different settings, you can set the following parameters:
+init=1,
+pwminv: 0 default pwm output, 1 inverts pwm output.
+

Documentation/hwmon/asc7621

@@ -0,0 +1,296 @@
+Kernel driver asc7621
+==================
+
+Supported chips:
+    Andigilog aSC7621 and aSC7621a
+    Prefix: 'asc7621'
+    Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+    Datasheet: http://www.fairview5.com/linux/asc7621/asc7621.pdf
+
+Author:
+		George Joseph
+
+Description provided by Dave Pivin @ Andigilog:
+
+Andigilog has both the PECI and pre-PECI versions of the Heceta-6, as
+Intel calls them. Heceta-6e has high frequency PWM and Heceta-6p has
+added PECI and a 4th thermal zone. The Andigilog aSC7611 is the
+Heceta-6e part and aSC7621 is the Heceta-6p part. They are both in
+volume production, shipping to Intel and their subs.
+
+We have enhanced both parts relative to the governing Intel
+specification. First enhancement is temperature reading resolution. We
+have used registers below 20h for vendor-specific functions in addition
+to those in the Intel-specified vendor range.
+
+Our conversion process produces a result that is reported as two bytes.
+The fan speed control uses this finer value to produce a "step-less" fan
+PWM output. These two bytes are "read-locked" to guarantee that once a
+high or low byte is read, the other byte is locked-in until after the
+next read of any register. So to get an atomic reading, read high or low
+byte, then the very next read should be the opposite byte. Our data
+sheet says 10-bits of resolution, although you may find the lower bits
+are active, they are not necessarily reliable or useful externally. We
+chose not to mask them.
+
+We employ significant filtering that is user tunable as described in the
+data sheet. Our temperature reports and fan PWM outputs are very smooth
+when compared to the competition, in addition to the higher resolution
+temperature reports. The smoother PWM output does not require user
+intervention.
+
+We offer GPIO features on the former VID pins. These are open-drain
+outputs or inputs and may be used as general purpose I/O or as alarm
+outputs that are based on temperature limits. These are in 19h and 1Ah.
+
+We offer flexible mapping of temperature readings to thermal zones. Any
+temperature may be mapped to any zone, which has a default assignment
+that follows Intel's specs.
+
+Since there is a fan to zone assignment that allows for the "hotter" of
+a set of zones to control the PWM of an individual fan, but there is no
+indication to the user, we have added an indicator that shows which zone
+is currently controlling the PWM for a given fan. This is in register
+00h.
+
+Both remote diode temperature readings may be given an offset value such
+that the reported reading as well as the temperature used to determine
+PWM may be offset for system calibration purposes.
+
+PECI Extended configuration allows for having more than two domains per
+PECI address and also provides an enabling function for each PECI
+address. One could use our flexible zone assignment to have a zone
+assigned to up to 4 PECI addresses. This is not possible in the default
+Intel configuration. This would be useful in multi-CPU systems with
+individual fans on each that would benefit from individual fan control.
+This is in register 0Eh.
+
+The tachometer measurement system is flexible and able to adapt to many
+fan types. We can also support pulse-stretched PWM so that 3-wire fans
+may be used. These characteristics are in registers 04h to 07h.
+
+Finally, we have added a tach disable function that turns off the tach
+measurement system for individual tachs in order to save power. That is
+in register 75h.
+
+--
+aSC7621 Product Description
+
+The aSC7621 has a two wire digital interface compatible with SMBus 2.0.
+Using a 10-bit ADC, the aSC7621 measures the temperature of two remote diode
+connected transistors as well as its own die. Support for Platform
+Environmental Control Interface (PECI) is included.
+
+Using temperature information from these four zones, an automatic fan speed
+control algorithm is employed to minimize acoustic impact while achieving
+recommended CPU temperature under varying operational loads.
+
+To set fan speed, the aSC7621 has three independent pulse width modulation
+(PWM) outputs that are controlled by one, or a combination of three,
+temperature zones. Both high- and low-frequency PWM ranges are supported.
+
+The aSC7621 also includes a digital filter that can be invoked to smooth
+temperature readings for better control of fan speed and minimum acoustic
+impact.
+
+The aSC7621 has tachometer inputs to measure fan speed on up to four fans.
+Limit and status registers for all measured values are included to alert
+the system host that any measurements are outside of programmed limits
+via status registers.
+
+System voltages of VCCP, 2.5V, 3.3V, 5.0V, and 12V motherboard power are
+monitored efficiently with internal scaling resistors.
+
+Features
+- Supports PECI interface and monitors internal and remote thermal diodes
+- 2-wire, SMBus 2.0 compliant, serial interface
+- 10-bit ADC
+- Monitors VCCP, 2.5V, 3.3V, 5.0V, and 12V motherboard/processor supplies
+- Programmable autonomous fan control based on temperature readings
+- Noise filtering of temperature reading for fan speed control
+- 0.25C digital temperature sensor resolution
+- 3 PWM fan speed control outputs for 2-, 3- or 4-wire fans and up to 4 fan
+	tachometer inputs
+- Enhanced measured temperature to Temperature Zone assignment.
+- Provides high and low PWM frequency ranges
+- 3 GPIO pins for custom use
+- 24-Lead QSOP package
+
+Configuration Notes
+===================
+
+Except where noted below, the sysfs entries created by this driver follow
+the standards defined in "sysfs-interface".
+
+temp1_source
+	0 	(default) peci_legacy = 0, Remote 1 Temperature
+			peci_legacy = 1, PECI Processor Temperature 0
+	1 	Remote 1 Temperature
+	2 	Remote 2 Temperature
+	3 	Internal Temperature
+	4 	PECI Processor Temperature 0
+	5 	PECI Processor Temperature 1
+	6 	PECI Processor Temperature 2
+	7  PECI Processor Temperature 3
+
+temp2_source
+	0 	(default) Internal Temperature
+	1 	Remote 1 Temperature
+	2 	Remote 2 Temperature
+	3 	Internal Temperature
+	4 	PECI Processor Temperature 0
+	5 	PECI Processor Temperature 1
+	6 	PECI Processor Temperature 2
+	7 	PECI Processor Temperature 3
+
+temp3_source
+	0 	(default) Remote 2 Temperature
+	1 	Remote 1 Temperature
+	2 	Remote 2 Temperature
+	3 	Internal Temperature
+	4 	PECI Processor Temperature 0
+	5 	PECI Processor Temperature 1
+	6 	PECI Processor Temperature 2
+	7 	PECI Processor Temperature 3
+
+temp4_source
+	0 	(default) peci_legacy = 0, PECI Processor Temperature 0
+			peci_legacy = 1, Remote 1 Temperature
+	1 	Remote 1 Temperature
+	2 	Remote 2 Temperature
+	3 	Internal Temperature
+	4 	PECI Processor Temperature 0
+	5 	PECI Processor Temperature 1
+	6 	PECI Processor Temperature 2
+	7 	PECI Processor Temperature 3
+
+temp[1-4]_smoothing_enable
+temp[1-4]_smoothing_time
+	Smooths spikes in temp readings caused by noise.
+	Valid values in milliseconds are:
+	35000
+	17600
+	11800
+	 7000
+	 4400
+	 3000
+	 1600
+	  800
+
+temp[1-4]_crit
+	When the corresponding zone temperature reaches this value,
+	ALL pwm outputs will got to 100%.
+
+temp[5-8]_input
+temp[5-8]_enable
+	The aSC7621 can also read temperatures provided by the processor
+	via the PECI bus.  Usually these are "core" temps and are relative
+	to the point where the automatic thermal control circuit starts
+	throttling.  This means that these are usually negative numbers.
+
+pwm[1-3]_enable
+	0		Fan off.
+	1		Fan on manual control.
+	2		Fan on automatic control and will run at the minimum pwm
+				if the temperature for the zone is below the minimum.
+	3		Fan on automatic control but will be off if the temperature
+				for the zone is below the minimum.
+	4-254	Ignored.
+	255		Fan on full.
+
+pwm[1-3]_auto_channels
+	Bitmap as described in sysctl-interface with the following
+	exceptions...
+	Only the following combination of zones (and their corresponding masks)
+	are valid:
+	1
+	2
+	3
+	2,3
+	1,2,3
+	4
+	1,2,3,4
+
+	Special values:
+	0			Disabled.
+	16		Fan on manual control.
+	31		Fan on full.
+
+
+pwm[1-3]_invert
+	When set, inverts the meaning of pwm[1-3].
+	i.e.  when pwm = 0, the fan will be on full and
+	when pwm = 255 the fan will be off.
+
+pwm[1-3]_freq
+	PWM frequency in Hz
+	Valid values in Hz are:
+
+	10
+	15
+	23
+	30  (default)
+	38
+	47
+	62
+	94
+	23000
+	24000
+	25000
+	26000
+	27000
+	28000
+	29000
+	30000
+
+	Setting any other value will be ignored.
+
+peci_enable
+	Enables or disables PECI
+
+peci_avg
+	Input filter average time.
+
+	0 	0 Sec. (no Smoothing) (default)
+	1 	0.25 Sec.
+	2 	0.5 Sec.
+	3 	1.0 Sec.
+	4 	2.0 Sec.
+	5 	4.0 Sec.
+	6 	8.0 Sec.
+	7 	0.0 Sec.
+
+peci_legacy
+
+	0	Standard Mode (default)
+		Remote Diode 1 reading is associated with
+		Temperature Zone 1, PECI is associated with
+		Zone 4
+
+	1	Legacy Mode
+		PECI is associated with Temperature Zone 1,
+		Remote Diode 1 is associated with Zone 4
+
+peci_diode
+	Diode filter
+
+	0	0.25 Sec.
+	1 	1.1 Sec.
+	2 	2.4 Sec.  (default)
+	3 	3.4 Sec.
+	4 	5.0 Sec.
+	5 	6.8 Sec.
+	6 	10.2 Sec.
+	7 	16.4 Sec.
+
+peci_4domain
+	Four domain enable
+
+	0 	1 or 2 Domains for enabled processors (default)
+	1 	3 or 4 Domains for enabled processors
+
+peci_domain
+	Domain
+
+	0 	Processor contains a single domain (0) 	 (default)
+	1 	Processor contains two domains (0,1)

Documentation/hwmon/it87

@@ -5,31 +5,23 @@ Supported chips:
   * IT8705F
     Prefix: 'it87'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/product_info/file/pc/IT8705F_V.0.4.1.pdf
+    Datasheet: Once publicly available at the ITE website, but no longer
   * IT8712F
     Prefix: 'it8712'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/product_info/file/pc/IT8712F_V0.9.1.pdf
-               http://www.ite.com.tw/product_info/file/pc/Errata%20V0.1%20for%20IT8712F%20V0.9.1.pdf
-               http://www.ite.com.tw/product_info/file/pc/IT8712F_V0.9.3.pdf
+    Datasheet: Once publicly available at the ITE website, but no longer
   * IT8716F/IT8726F
     Prefix: 'it8716'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/product_info/file/pc/IT8716F_V0.3.ZIP
-               http://www.ite.com.tw/product_info/file/pc/IT8726F_V0.3.pdf
+    Datasheet: Once publicly available at the ITE website, but no longer
   * IT8718F
     Prefix: 'it8718'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/product_info/file/pc/IT8718F_V0.2.zip
-               http://www.ite.com.tw/product_info/file/pc/IT8718F_V0%203_(for%20C%20version).zip
+    Datasheet: Once publicly available at the ITE website, but no longer
   * IT8720F
     Prefix: 'it8720'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Not yet publicly available.
+    Datasheet: Not publicly available
   * SiS950   [clone of IT8705F]
     Prefix: 'it87'
     Addresses scanned: from Super I/O config space (8 I/O ports)
@@ -136,6 +128,10 @@ registers are read whenever any data is read (unless it is less than 1.5
 seconds since the last update). This means that you can easily miss
 once-only alarms.
 
+Out-of-limit readings can also result in beeping, if the chip is properly
+wired and configured. Beeping can be enabled or disabled per sensor type
+(temperatures, voltages and fans.)
+
 The IT87xx only updates its values each 1.5 seconds; reading it more often
 will do no harm, but will return 'old' values.
 
@@ -150,11 +146,38 @@ Fan speed control
 -----------------
 
 The fan speed control features are limited to manual PWM mode. Automatic
-"Smart Guardian" mode control handling is not implemented. However
-if you want to go for "manual mode" just write 1 to pwmN_enable.
+"Smart Guardian" mode control handling is only implemented for older chips
+(see below.) However if you want to go for "manual mode" just write 1 to
+pwmN_enable.
 
 If you are only able to control the fan speed with very small PWM values,
 try lowering the PWM base frequency (pwm1_freq). Depending on the fan,
 it may give you a somewhat greater control range. The same frequency is
 used to drive all fan outputs, which is why pwm2_freq and pwm3_freq are
 read-only.
+
+
+Automatic fan speed control (old interface)
+-------------------------------------------
+
+The driver supports the old interface to automatic fan speed control
+which is implemented by IT8705F chips up to revision F and IT8712F
+chips up to revision G.
+
+This interface implements 4 temperature vs. PWM output trip points.
+The PWM output of trip point 4 is always the maximum value (fan running
+at full speed) while the PWM output of the other 3 trip points can be
+freely chosen. The temperature of all 4 trip points can be freely chosen.
+Additionally, trip point 1 has an hysteresis temperature attached, to
+prevent fast switching between fan on and off.
+
+The chip automatically computes the PWM output value based on the input
+temperature, based on this simple rule: if the temperature value is
+between trip point N and trip point N+1 then the PWM output value is
+the one of trip point N. The automatic control mode is less flexible
+than the manual control mode, but it reacts faster, is more robust and
+doesn't use CPU cycles.
+
+Trip points must be set properly before switching to automatic fan speed
+control mode. The driver will perform basic integrity checks before
+actually switching to automatic control mode.

Documentation/hwmon/k10temp

@@ -0,0 +1,65 @@
+Kernel driver k10temp
+=====================
+
+Supported chips:
+* AMD Family 10h processors:
+  Socket F: Quad-Core/Six-Core/Embedded Opteron (but see below)
+  Socket AM2+: Quad-Core Opteron, Phenom (II) X3/X4, Athlon X2 (but see below)
+  Socket AM3: Quad-Core Opteron, Athlon/Phenom II X2/X3/X4, Sempron II
+  Socket S1G3: Athlon II, Sempron, Turion II
+* AMD Family 11h processors:
+  Socket S1G2: Athlon (X2), Sempron (X2), Turion X2 (Ultra)
+
+  Prefix: 'k10temp'
+  Addresses scanned: PCI space
+  Datasheets:
+  BIOS and Kernel Developer's Guide (BKDG) For AMD Family 10h Processors:
+    http://support.amd.com/us/Processor_TechDocs/31116.pdf
+  BIOS and Kernel Developer's Guide (BKDG) for AMD Family 11h Processors:
+    http://support.amd.com/us/Processor_TechDocs/41256.pdf
+  Revision Guide for AMD Family 10h Processors:
+    http://support.amd.com/us/Processor_TechDocs/41322.pdf
+  Revision Guide for AMD Family 11h Processors:
+    http://support.amd.com/us/Processor_TechDocs/41788.pdf
+  AMD Family 11h Processor Power and Thermal Data Sheet for Notebooks:
+    http://support.amd.com/us/Processor_TechDocs/43373.pdf
+  AMD Family 10h Server and Workstation Processor Power and Thermal Data Sheet:
+    http://support.amd.com/us/Processor_TechDocs/43374.pdf
+  AMD Family 10h Desktop Processor Power and Thermal Data Sheet:
+    http://support.amd.com/us/Processor_TechDocs/43375.pdf
+
+Author: Clemens Ladisch <clemens@ladisch.de>
+
+Description
+-----------
+
+This driver permits reading of the internal temperature sensor of AMD
+Family 10h and 11h processors.
+
+All these processors have a sensor, but on those for Socket F or AM2+,
+the sensor may return inconsistent values (erratum 319).  The driver
+will refuse to load on these revisions unless you specify the "force=1"
+module parameter.
+
+Due to technical reasons, the driver can detect only the mainboard's
+socket type, not the processor's actual capabilities.  Therefore, if you
+are using an AM3 processor on an AM2+ mainboard, you can safely use the
+"force=1" parameter.
+
+There is one temperature measurement value, available as temp1_input in
+sysfs. It is measured in degrees Celsius with a resolution of 1/8th degree.
+Please note that it is defined as a relative value; to quote the AMD manual:
+
+  Tctl is the processor temperature control value, used by the platform to
+  control cooling systems. Tctl is a non-physical temperature on an
+  arbitrary scale measured in degrees. It does _not_ represent an actual
+  physical temperature like die or case temperature. Instead, it specifies
+  the processor temperature relative to the point at which the system must
+  supply the maximum cooling for the processor's specified maximum case
+  temperature and maximum thermal power dissipation.
+
+The maximum value for Tctl is available in the file temp1_max.
+
+If the BIOS has enabled hardware temperature control, the threshold at
+which the processor will throttle itself to avoid damage is available in
+temp1_crit and temp1_crit_hyst.