Merge branch 'master' into next

Conflicts:
	fs/namei.c

Manually merged per:

diff --cc fs/namei.c
index 734f2b5,bbc15c2..0000000
--- a/fs/namei.c
+++ b/fs/namei.c
@@@ -860,9 -848,8 +849,10 @@@ static int __link_path_walk(const char
  		nd->flags |= LOOKUP_CONTINUE;
  		err = exec_permission_lite(inode);
  		if (err == -EAGAIN)
- 			err = vfs_permission(nd, MAY_EXEC);
+ 			err = inode_permission(nd->path.dentry->d_inode,
+ 					       MAY_EXEC);
 +		if (!err)
 +			err = ima_path_check(&nd->path, MAY_EXEC);
   		if (err)
  			break;

@@@ -1525,14 -1506,9 +1509,14 @@@ int may_open(struct path *path, int acc
  		flag &= ~O_TRUNC;
  	}

- 	error = vfs_permission(nd, acc_mode);
+ 	error = inode_permission(inode, acc_mode);
  	if (error)
  		return error;
 +
- 	error = ima_path_check(&nd->path,
++	error = ima_path_check(path,
 +			       acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC));
 +	if (error)
 +		return error;
  	/*
  	 * An append-only file must be opened in append mode for writing.
  	 */
Signed-off-by: NJames Morris <jmorris@namei.org>

.mailmap

@@ -32,6 +32,7 @@ Christoph Hellwig <hch@lst.de>
 Corey Minyard <minyard@acm.org>
 David Brownell <david-b@pacbell.net>
 David Woodhouse <dwmw2@shinybook.infradead.org>
+Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
 Domen Puncer <domen@coderock.org>
 Douglas Gilbert <dougg@torque.net>
 Ed L. Cashin <ecashin@coraid.com>

CREDITS

@@ -369,10 +369,10 @@ P: 1024/8462A731 4C 55 86 34 44 59 A7 99  2B 97 88 4A 88 9A 0D 97
 D: sun4 port, Sparc hacker
 
 N: Hugh Blemings
-E: hugh@misc.nu
-W: http://misc.nu/hugh/
-D: Author and maintainer of the Keyspan USB to Serial drivers
-S: Po Box 234
+E: hugh@blemings.org
+W: http://blemings.org/hugh
+D: Original author of the Keyspan USB to serial drivers, random PowerPC hacker
+S: PO Box 234
 S: Belconnen ACT 2616
 S: Australia
 
@@ -464,6 +464,11 @@ S: 1200 Goldenrod Dr.
 S: Nampa, Idaho 83686
 S: USA
 
+N: Dirk J. Brandewie
+E: dirk.j.brandewie@intel.com
+E: linux-wimax@intel.com
+D: Intel Wireless WiMAX Connection 2400 SDIO driver
+
 N: Derrick J. Brashear
 E: shadow@dementia.org
 W: http://www.dementia.org/~shadow
@@ -1681,7 +1686,7 @@ E: ajoshi@shell.unixbox.com
 D: fbdev hacking
 
 N: Jesper Juhl
-E: jesper.juhl@gmail.com
+E: jj@chaosbits.net
 D: Various fixes, cleanups and minor features all over the tree.
 D: Wrote initial version of the hdaps driver (since passed on to others).
 S: Lemnosvej 1, 3.tv
@@ -2119,6 +2124,11 @@ N: H.J. Lu
 E: hjl@gnu.ai.mit.edu
 D: GCC + libraries hacker
 
+N: Yanir Lubetkin
+E: yanirx.lubatkin@intel.com
+E: linux-wimax@intel.com
+D: Intel Wireless WiMAX Connection 2400 driver
+
 N: Michal Ludvig
 E: michal@logix.cz
 E: michal.ludvig@asterisk.co.nz
@@ -2693,6 +2703,13 @@ S: RR #5, 497 Pole Line Road
 S: Thunder Bay, Ontario
 S: CANADA P7C 5M9
 
+N: Inaky Perez-Gonzalez
+E: inaky.perez-gonzalez@intel.com
+E: linux-wimax@intel.com
+E: inakypg@yahoo.com
+D: WiMAX stack
+D: Intel Wireless WiMAX Connection 2400 driver
+
 N: Yuri Per
 E: yuri@pts.mipt.ru
 D: Some smbfs fixes
@@ -3769,14 +3786,11 @@ S: The Netherlands
 
 N: David Woodhouse
 E: dwmw2@infradead.org
-D: ARCnet stuff, Applicom board driver, SO_BINDTODEVICE,
-D: some Alpha platform porting from 2.0, Memory Technology Devices,
-D: Acquire watchdog timer, PC speaker driver maintenance,
+D: JFFS2 file system, Memory Technology Device subsystem,
 D: various other stuff that annoyed me by not working.
-S: c/o Red Hat Engineering
-S: Rustat House
-S: 60 Clifton Road
-S: Cambridge. CB1 7EG
+S: c/o Intel Corporation
+S: Pipers Way
+S: Swindon. SN3 1RJ
 S: England
 
 N: Chris Wright

Documentation/ABI/testing/sysfs-class-regulator

@@ -3,8 +3,9 @@ Date:		April 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
-		state. This holds the regulator output state.
+		Some regulator directories will contain a field called
+		state. This reports the regulator enable status, for
+		regulators which can report that value.
 
 		This will be one of the following strings:
 
@@ -18,7 +19,8 @@ Description:
 		'disabled' means the regulator output is OFF and is not
 		supplying power to the system..
 
-		'unknown' means software cannot determine the state.
+		'unknown' means software cannot determine the state, or
+		the reported state is invalid.
 
 		NOTE: this field can be used in conjunction with microvolts
 		and microamps to determine regulator output levels.
@@ -53,9 +55,10 @@ Date:		April 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
+		Some regulator directories will contain a field called
 		microvolts. This holds the regulator output voltage setting
-		measured in microvolts (i.e. E-6 Volts).
+		measured in microvolts (i.e. E-6 Volts), for regulators
+		which can report that voltage.
 
 		NOTE: This value should not be used to determine the regulator
 		output voltage level as this value is the same regardless of
@@ -67,9 +70,10 @@ Date:		April 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
+		Some regulator directories will contain a field called
 		microamps. This holds the regulator output current limit
-		setting measured in microamps (i.e. E-6 Amps).
+		setting measured in microamps (i.e. E-6 Amps), for regulators
+		which can report that current.
 
 		NOTE: This value should not be used to determine the regulator
 		output current level as this value is the same regardless of
@@ -81,8 +85,9 @@ Date:		April 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
-		opmode. This holds the regulator operating mode setting.
+		Some regulator directories will contain a field called
+		opmode. This holds the current regulator operating mode,
+		for regulators which can report it.
 
 		The opmode value can be one of the following strings:
 
@@ -92,7 +97,7 @@ Description:
 		'standby'
 		'unknown'
 
-		The modes are described in include/linux/regulator/regulator.h
+		The modes are described in include/linux/regulator/consumer.h
 
 		NOTE: This value should not be used to determine the regulator
 		output operating mode as this value is the same regardless of
@@ -104,9 +109,10 @@ Date:		April 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
+		Some regulator directories will contain a field called
 		min_microvolts. This holds the minimum safe working regulator
-		output voltage setting for this domain measured in microvolts.
+		output voltage setting for this domain measured in microvolts,
+		for regulators which support voltage constraints.
 
 		NOTE: this will return the string 'constraint not defined' if
 		the power domain has no min microvolts constraint defined by
@@ -118,9 +124,10 @@ Date:		April 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
+		Some regulator directories will contain a field called
 		max_microvolts. This holds the maximum safe working regulator
-		output voltage setting for this domain measured in microvolts.
+		output voltage setting for this domain measured in microvolts,
+		for regulators which support voltage constraints.
 
 		NOTE: this will return the string 'constraint not defined' if
 		the power domain has no max microvolts constraint defined by
@@ -132,10 +139,10 @@ Date:		April 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
+		Some regulator directories will contain a field called
 		min_microamps. This holds the minimum safe working regulator
 		output current limit setting for this domain measured in
-		microamps.
+		microamps, for regulators which support current constraints.
 
 		NOTE: this will return the string 'constraint not defined' if
 		the power domain has no min microamps constraint defined by
@@ -147,10 +154,10 @@ Date:		April 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
+		Some regulator directories will contain a field called
 		max_microamps. This holds the maximum safe working regulator
 		output current limit setting for this domain measured in
-		microamps.
+		microamps, for regulators which support current constraints.
 
 		NOTE: this will return the string 'constraint not defined' if
 		the power domain has no max microamps constraint defined by
@@ -185,7 +192,7 @@ Date:		April 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
+		Some regulator directories will contain a field called
 		requested_microamps. This holds the total requested load
 		current in microamps for this regulator from all its consumer
 		devices.
@@ -204,125 +211,102 @@ Date:		May 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
+		Some regulator directories will contain a field called
 		suspend_mem_microvolts. This holds the regulator output
 		voltage setting for this domain measured in microvolts when
-		the system is suspended to memory.
-
-		NOTE: this will return the string 'not defined' if
-		the power domain has no suspend to memory voltage defined by
-		platform code.
+		the system is suspended to memory, for voltage regulators
+		implementing suspend voltage configuration constraints.
 
 What:		/sys/class/regulator/.../suspend_disk_microvolts
 Date:		May 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
+		Some regulator directories will contain a field called
 		suspend_disk_microvolts. This holds the regulator output
 		voltage setting for this domain measured in microvolts when
-		the system is suspended to disk.
-
-		NOTE: this will return the string 'not defined' if
-		the power domain has no suspend to disk voltage defined by
-		platform code.
+		the system is suspended to disk, for voltage regulators
+		implementing suspend voltage configuration constraints.
 
 What:		/sys/class/regulator/.../suspend_standby_microvolts
 Date:		May 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
+		Some regulator directories will contain a field called
 		suspend_standby_microvolts. This holds the regulator output
 		voltage setting for this domain measured in microvolts when
-		the system is suspended to standby.
-
-		NOTE: this will return the string 'not defined' if
-		the power domain has no suspend to standby voltage defined by
-		platform code.
+		the system is suspended to standby, for voltage regulators
+		implementing suspend voltage configuration constraints.
 
 What:		/sys/class/regulator/.../suspend_mem_mode
 Date:		May 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
+		Some regulator directories will contain a field called
 		suspend_mem_mode. This holds the regulator operating mode
 		setting for this domain when the system is suspended to
-		memory.
-
-		NOTE: this will return the string 'not defined' if
-		the power domain has no suspend to memory mode defined by
-		platform code.
+		memory, for regulators implementing suspend mode
+		configuration constraints.
 
 What:		/sys/class/regulator/.../suspend_disk_mode
 Date:		May 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
+		Some regulator directories will contain a field called
 		suspend_disk_mode. This holds the regulator operating mode
-		setting for this domain when the system is suspended to disk.
-
-		NOTE: this will return the string 'not defined' if
-		the power domain has no suspend to disk mode defined by
-		platform code.
+		setting for this domain when the system is suspended to disk,
+		for regulators implementing suspend mode configuration
+		constraints.
 
 What:		/sys/class/regulator/.../suspend_standby_mode
 Date:		May 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
+		Some regulator directories will contain a field called
 		suspend_standby_mode. This holds the regulator operating mode
 		setting for this domain when the system is suspended to
-		standby.
-
-		NOTE: this will return the string 'not defined' if
-		the power domain has no suspend to standby mode defined by
-		platform code.
+		standby, for regulators implementing suspend mode
+		configuration constraints.
 
 What:		/sys/class/regulator/.../suspend_mem_state
 Date:		May 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
+		Some regulator directories will contain a field called
 		suspend_mem_state. This holds the regulator operating state
-		when suspended to memory.
-
-		This will be one of the following strings:
+		when suspended to memory, for regulators implementing suspend
+		configuration constraints.
 
-		'enabled'
-		'disabled'
-		'not defined'
+		This will be one of the same strings reported by
+		the "state" attribute.
 
 What:		/sys/class/regulator/.../suspend_disk_state
 Date:		May 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
+		Some regulator directories will contain a field called
 		suspend_disk_state. This holds the regulator operating state
-		when suspended to disk.
-
-		This will be one of the following strings:
+		when suspended to disk, for regulators implementing
+		suspend configuration constraints.
 
-		'enabled'
-		'disabled'
-		'not defined'
+		This will be one of the same strings reported by
+		the "state" attribute.
 
 What:		/sys/class/regulator/.../suspend_standby_state
 Date:		May 2008
 KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-		Each regulator directory will contain a field called
+		Some regulator directories will contain a field called
 		suspend_standby_state. This holds the regulator operating
-		state when suspended to standby.
-
-		This will be one of the following strings:
+		state when suspended to standby, for regulators implementing
+		suspend configuration constraints.
 
-		'enabled'
-		'disabled'
-		'not defined'
+		This will be one of the same strings reported by
+		the "state" attribute.

Documentation/ABI/testing/sysfs-class-uwb_rc

@@ -32,14 +32,16 @@ Contact:        linux-usb@vger.kernel.org
 Description:
                 Write:
 
-                <channel> [<bpst offset>]
+                <channel>
 
-                to start beaconing on a specific channel, or stop
-                beaconing if <channel> is -1.  Valid channels depends
-                on the radio controller's supported band groups.
+                to force a specific channel to be used when beaconing,
+                or, if <channel> is -1, to prohibit beaconing.  If
+                <channel> is 0, then the default channel selection
+                algorithm will be used.  Valid channels depends on the
+                radio controller's supported band groups.
 
-                <bpst offset> may be used to try and join a specific
-                beacon group if more than one was found during a scan.
+                Reading returns the currently active channel, or -1 if
+                the radio controller is not beaconing.
 
 What:           /sys/class/uwb_rc/uwbN/scan
 Date:           July 2008

Documentation/ABI/testing/sysfs-devices-memory

@@ -6,7 +6,6 @@ Description:
 		internal state of the kernel memory blocks. Files could be
 		added or removed dynamically to represent hot-add/remove
 		operations.
-
 Users:		hotplug memory add/remove tools
 		https://w3.opensource.ibm.com/projects/powerpc-utils/
 
@@ -19,6 +18,56 @@ Description:
 		This is useful for a user-level agent to determine
 		identify removable sections of the memory before attempting
 		potentially expensive hot-remove memory operation
+Users:		hotplug memory remove tools
+		https://w3.opensource.ibm.com/projects/powerpc-utils/
+
+What:		/sys/devices/system/memory/memoryX/phys_device
+Date:		September 2008
+Contact:	Badari Pulavarty <pbadari@us.ibm.com>
+Description:
+		The file /sys/devices/system/memory/memoryX/phys_device
+		is read-only and is designed to show the name of physical
+		memory device.  Implementation is currently incomplete.
 
+What:		/sys/devices/system/memory/memoryX/phys_index
+Date:		September 2008
+Contact:	Badari Pulavarty <pbadari@us.ibm.com>
+Description:
+		The file /sys/devices/system/memory/memoryX/phys_index
+		is read-only and contains the section ID in hexadecimal
+		which is equivalent to decimal X contained in the
+		memory section directory name.
+
+What:		/sys/devices/system/memory/memoryX/state
+Date:		September 2008
+Contact:	Badari Pulavarty <pbadari@us.ibm.com>
+Description:
+		The file /sys/devices/system/memory/memoryX/state
+		is read-write.  When read, it's contents show the
+		online/offline state of the memory section.  When written,
+		root can toggle the the online/offline state of a removable
+		memory section (see removable file description above)
+		using the following commands.
+		# echo online > /sys/devices/system/memory/memoryX/state
+		# echo offline > /sys/devices/system/memory/memoryX/state
+
+		For example, if /sys/devices/system/memory/memory22/removable
+		contains a value of 1 and
+		/sys/devices/system/memory/memory22/state contains the
+		string "online" the following command can be executed by
+		by root to offline that section.
+		# echo offline > /sys/devices/system/memory/memory22/state
 Users:		hotplug memory remove tools
 		https://w3.opensource.ibm.com/projects/powerpc-utils/
+
+What:		/sys/devices/system/node/nodeX/memoryY
+Date:		September 2008
+Contact:	Gary Hade <garyhade@us.ibm.com>
+Description:
+		When CONFIG_NUMA is enabled
+		/sys/devices/system/node/nodeX/memoryY is a symbolic link that
+		points to the corresponding /sys/devices/system/memory/memoryY
+		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/Changes

@@ -33,10 +33,12 @@ o  Gnu make               3.79.1                  # make --version
 o  binutils               2.12                    # ld -v
 o  util-linux             2.10o                   # fdformat --version
 o  module-init-tools      0.9.10                  # depmod -V
-o  e2fsprogs              1.29                    # tune2fs
+o  e2fsprogs              1.41.4                  # e2fsck -V
 o  jfsutils               1.1.3                   # fsck.jfs -V
 o  reiserfsprogs          3.6.3                   # reiserfsck -V 2>&1|grep reiserfsprogs
 o  xfsprogs               2.6.0                   # xfs_db -V
+o  squashfs-tools         4.0                     # mksquashfs -version
+o  btrfs-progs            0.18                    # btrfsck
 o  pcmciautils            004                     # pccardctl -V
 o  quota-tools            3.09                    # quota -V
 o  PPP                    2.4.0                   # pppd --version

Documentation/CodingStyle

@@ -483,17 +483,25 @@ values.  To do the latter, you can stick the following in your .emacs file:
     (* (max steps 1)
        c-basic-offset)))
 
+(add-hook 'c-mode-common-hook
+          (lambda ()
+            ;; Add kernel style
+            (c-add-style
+             "linux-tabs-only"
+             '("linux" (c-offsets-alist
+                        (arglist-cont-nonempty
+                         c-lineup-gcc-asm-reg
+                         c-lineup-arglist-tabs-only))))))
+
 (add-hook 'c-mode-hook
           (lambda ()
             (let ((filename (buffer-file-name)))
               ;; Enable kernel mode for the appropriate files
               (when (and filename
-                         (string-match "~/src/linux-trees" filename))
+                         (string-match (expand-file-name "~/src/linux-trees")
+                                       filename))
                 (setq indent-tabs-mode t)
-                (c-set-style "linux")
-                (c-set-offset 'arglist-cont-nonempty
-                              '(c-lineup-gcc-asm-reg
-                                c-lineup-arglist-tabs-only))))))
+                (c-set-style "linux-tabs-only")))))
 
 This will make emacs go better with the kernel coding style for C
 files below ~/src/linux-trees.

Documentation/DMA-API.txt

@@ -5,7 +5,7 @@
 
 This document describes the DMA API.  For a more gentle introduction
 phrased in terms of the pci_ equivalents (and actual examples) see
-DMA-mapping.txt
+Documentation/PCI/PCI-DMA-mapping.txt.
 
 This API is split into two pieces.  Part I describes the API and the
 corresponding pci_ API.  Part II describes the extensions to the API
@@ -170,16 +170,15 @@ Returns: 0 if successful and a negative error if not.
 u64
 dma_get_required_mask(struct device *dev)
 
-After setting the mask with dma_set_mask(), this API returns the
-actual mask (within that already set) that the platform actually
-requires to operate efficiently.  Usually this means the returned mask
+This API returns the mask that the platform requires to
+operate efficiently.  Usually this means the returned mask
 is the minimum required to cover all of memory.  Examining the
 required mask gives drivers with variable descriptor sizes the
 opportunity to use smaller descriptors as necessary.
 
 Requesting the required mask does not alter the current mask.  If you
-wish to take advantage of it, you should issue another dma_set_mask()
-call to lower the mask again.
+wish to take advantage of it, you should issue a dma_set_mask()
+call to set the mask to the value returned.
 
 
 Part Id - Streaming DMA mappings

Documentation/DMA-mapping.txt

@@ -26,7 +26,7 @@ mapped only for the time they are actually used and unmapped after the DMA
 transfer.
 
 The following API will work of course even on platforms where no such
-hardware exists, see e.g. include/asm-i386/pci.h for how it is implemented on
+hardware exists, see e.g. arch/x86/include/asm/pci.h for how it is implemented on
 top of the virt_to_bus interface.
 
 First of all, you should make sure

Documentation/DocBook/Makefile

@@ -12,7 +12,7 @@ DOCBOOKS := z8530book.xml mcabook.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 \
-	    mac80211.xml debugobjects.xml sh.xml
+	    mac80211.xml debugobjects.xml sh.xml regulator.xml
 
 ###
 # The build process is as follows (targets):

Documentation/DocBook/networking.tmpl

@@ -74,6 +74,14 @@
 !Enet/sunrpc/rpcb_clnt.c
 !Enet/sunrpc/clnt.c
      </sect1>
+     <sect1><title>WiMAX</title>
+!Enet/wimax/op-msg.c
+!Enet/wimax/op-reset.c
+!Enet/wimax/op-rfkill.c
+!Enet/wimax/stack.c
+!Iinclude/net/wimax.h
+!Iinclude/linux/wimax.h
+     </sect1>
   </chapter>
 
   <chapter id="netdev">

Documentation/DocBook/regulator.tmpl

+<?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" []>
+
+<book id="regulator-api">
+ <bookinfo>
+  <title>Voltage and current regulator API</title>
+
+  <authorgroup>
+   <author>
+    <firstname>Liam</firstname>
+    <surname>Girdwood</surname>
+    <affiliation>
+     <address>
+      <email>lrg@slimlogic.co.uk</email>
+     </address>
+    </affiliation>
+   </author>
+   <author>
+    <firstname>Mark</firstname>
+    <surname>Brown</surname>
+    <affiliation>
+     <orgname>Wolfson Microelectronics</orgname>
+     <address>
+      <email>broonie@opensource.wolfsonmicro.com</email>
+     </address>
+    </affiliation>
+   </author>
+  </authorgroup>
+
+  <copyright>
+   <year>2007-2008</year>
+   <holder>Wolfson Microelectronics</holder>
+  </copyright>
+  <copyright>
+   <year>2008</year>
+   <holder>Liam Girdwood</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 version 2 as published by the Free Software Foundation.
+   </para>
+
+   <para>
+     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.
+   </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>
+
+  <chapter id="intro">
+    <title>Introduction</title>
+    <para>
+	This framework is designed to provide a standard kernel
+	interface to control voltage and current regulators.
+    </para>
+    <para>
+	The intention is to allow systems to dynamically control
+	regulator power output in order to save power and prolong
+	battery life.  This applies to both voltage regulators (where
+	voltage output is controllable) and current sinks (where current
+	limit is controllable).
+    </para>
+    <para>
+	Note that additional (and currently more complete) documentation
+	is available in the Linux kernel source under
+	<filename>Documentation/power/regulator</filename>.
+    </para>
+
+    <sect1 id="glossary">
+       <title>Glossary</title>
+       <para>
+	The regulator API uses a number of terms which may not be
+	familiar:
+       </para>
+       <glossary>
+
+         <glossentry>
+	   <glossterm>Regulator</glossterm>
+	   <glossdef>
+	     <para>
+	Electronic device that supplies power to other devices.  Most
+	regulators can enable and disable their output and some can also
+	control their output voltage or current.
+	     </para>
+	   </glossdef>
+         </glossentry>
+
+	 <glossentry>
+	   <glossterm>Consumer</glossterm>
+	   <glossdef>
+	     <para>
+	Electronic device which consumes power provided by a regulator.
+	These may either be static, requiring only a fixed supply, or
+	dynamic, requiring active management of the regulator at
+	runtime.
+	     </para>
+	   </glossdef>
+	 </glossentry>
+
+	 <glossentry>
+	   <glossterm>Power Domain</glossterm>
+	   <glossdef>
+	     <para>
+	The electronic circuit supplied by a given regulator, including
+	the regulator and all consumer devices.  The configuration of
+	the regulator is shared between all the components in the
+	circuit.
+	     </para>
+	   </glossdef>
+	 </glossentry>
+
+	 <glossentry>
+	   <glossterm>Power Management Integrated Circuit</glossterm>
+	   <acronym>PMIC</acronym>
+	   <glossdef>
+	     <para>
+	An IC which contains numerous regulators and often also other
+	subsystems.  In an embedded system the primary PMIC is often
+	equivalent to a combination of the PSU and southbridge in a
+	desktop system.
+	     </para>
+	   </glossdef>
+	 </glossentry>
+	</glossary>
+     </sect1>
+  </chapter>
+
+  <chapter id="consumer">
+     <title>Consumer driver interface</title>
+     <para>
+       This offers a similar API to the kernel clock framework.
+       Consumer drivers use <link
+       linkend='API-regulator-get'>get</link> and <link
+       linkend='API-regulator-put'>put</link> operations to acquire and
+       release regulators.  Functions are
+       provided to <link linkend='API-regulator-enable'>enable</link>
+       and <link linkend='API-regulator-disable'>disable</link> the
+       reguator and to get and set the runtime parameters of the
+       regulator.
+     </para>
+     <para>
+       When requesting regulators consumers use symbolic names for their
+       supplies, such as "Vcc", which are mapped into actual regulator
+       devices by the machine interface.
+     </para>
+     <para>
+	A stub version of this API is provided when the regulator
+	framework is not in use in order to minimise the need to use
+	ifdefs.
+     </para>
+
+     <sect1 id="consumer-enable">
+       <title>Enabling and disabling</title>
+       <para>
+         The regulator API provides reference counted enabling and
+	 disabling of regulators. Consumer devices use the <function><link
+	 linkend='API-regulator-enable'>regulator_enable</link></function>
+	 and <function><link
+	 linkend='API-regulator-disable'>regulator_disable</link>
+	 </function> functions to enable and disable regulators.  Calls
+	 to the two functions must be balanced.
+       </para>
+       <para>
+         Note that since multiple consumers may be using a regulator and
+	 machine constraints may not allow the regulator to be disabled
+	 there is no guarantee that calling
+	 <function>regulator_disable</function> will actually cause the
+	 supply provided by the regulator to be disabled. Consumer
+	 drivers should assume that the regulator may be enabled at all
+	 times.
+       </para>
+     </sect1>
+
+     <sect1 id="consumer-config">
+       <title>Configuration</title>
+       <para>
+         Some consumer devices may need to be able to dynamically
+	 configure their supplies.  For example, MMC drivers may need to
+	 select the correct operating voltage for their cards.  This may
+	 be done while the regulator is enabled or disabled.
+       </para>
+       <para>
+	 The <function><link
+	 linkend='API-regulator-set-voltage'>regulator_set_voltage</link>
+	 </function> and <function><link
+	 linkend='API-regulator-set-current-limit'
+	 >regulator_set_current_limit</link>
+	 </function> functions provide the primary interface for this.
+	 Both take ranges of voltages and currents, supporting drivers
+	 that do not require a specific value (eg, CPU frequency scaling
+	 normally permits the CPU to use a wider range of supply
+	 voltages at lower frequencies but does not require that the
+	 supply voltage be lowered).  Where an exact value is required
+	 both minimum and maximum values should be identical.
+       </para>
+     </sect1>
+
+     <sect1 id="consumer-callback">
+       <title>Callbacks</title>
+       <para>
+	  Callbacks may also be <link
+	  linkend='API-regulator-register-notifier'>registered</link>
+	  for events such as regulation failures.
+       </para>
+     </sect1>
+   </chapter>
+
+   <chapter id="driver">
+     <title>Regulator driver interface</title>
+     <para>
+       Drivers for regulator chips <link
+       linkend='API-regulator-register'>register</link> the regulators
+       with the regulator core, providing operations structures to the
+       core.  A <link
+       linkend='API-regulator-notifier-call-chain'>notifier</link> interface
+       allows error conditions to be reported to the core.
+     </para>
+     <para>
+       Registration should be triggered by explicit setup done by the
+       platform, supplying a <link
+       linkend='API-struct-regulator-init-data'>struct
+       regulator_init_data</link> for the regulator containing
+       <link linkend='machine-constraint'>constraint</link> and
+       <link linkend='machine-supply'>supply</link> information.
+     </para>
+   </chapter>
+
+   <chapter id="machine">
+     <title>Machine interface</title>
+     <para>
+       This interface provides a way to define how regulators are
+       connected to consumers on a given system and what the valid
+       operating parameters are for the system.
+     </para>
+
+     <sect1 id="machine-supply">
+       <title>Supplies</title>
+       <para>
+         Regulator supplies are specified using <link
+	 linkend='API-struct-regulator-consumer-supply'>struct
+	 regulator_consumer_supply</link>.  This is done at
+	 <link linkend='driver'>driver registration
+	 time</link> as part of the machine constraints.
+       </para>
+     </sect1>
+
+     <sect1 id="machine-constraint">
+       <title>Constraints</title>
+       <para>
+	 As well as definining the connections the machine interface
+	 also provides constraints definining the operations that
+	 clients are allowed to perform and the parameters that may be
+	 set.  This is required since generally regulator devices will
+	 offer more flexibility than it is safe to use on a given
+	 system, for example supporting higher supply voltages than the
+	 consumers are rated for.
+       </para>
+       <para>
+	 This is done at <link linkend='driver'>driver
+	 registration time</link> by providing a <link
+	 linkend='API-struct-regulation-constraints'>struct
+	 regulation_constraints</link>.
+       </para>
+       <para>
+         The constraints may also specify an initial configuration for the
+         regulator in the constraints, which is particularly useful for
+         use with static consumers.
+       </para>
+     </sect1>
+  </chapter>
+
+  <chapter id="api">
+    <title>API reference</title>
+    <para>
+      Due to limitations of the kernel documentation framework and the
+      existing layout of the source code the entire regulator API is
+      documented here.
+    </para>
+!Iinclude/linux/regulator/consumer.h
+!Iinclude/linux/regulator/machine.h
+!Iinclude/linux/regulator/driver.h
+!Edrivers/regulator/core.c
+  </chapter>
+</book>

Documentation/DocBook/uio-howto.tmpl

@@ -41,6 +41,18 @@ GPL version 2.
 </abstract>
 
 <revhistory>
+	<revision>
+	<revnumber>0.7</revnumber>
+	<date>2008-12-23</date>
+	<authorinitials>hjk</authorinitials>
+	<revremark>Added generic platform drivers and offset attribute.</revremark>
+	</revision>
+	<revision>
+	<revnumber>0.6</revnumber>
+	<date>2008-12-05</date>
+	<authorinitials>hjk</authorinitials>
+	<revremark>Added description of portio sysfs attributes.</revremark>
+	</revision>
 	<revision>
 	<revnumber>0.5</revnumber>
 	<date>2008-05-22</date>
@@ -306,6 +318,16 @@ interested in translating it, please email me
 	pointed to by addr.
 	</para>
 </listitem>
+<listitem>
+	<para>
+	<filename>offset</filename>: The offset, in bytes, that has to be
+	added to the pointer returned by <function>mmap()</function> to get
+	to the actual device memory. This is important if the device's memory
+	is not page aligned. Remember that pointers returned by
+	<function>mmap()</function> are always page aligned, so it is good
+	style to always add this offset.
+	</para>
+</listitem>
 </itemizedlist>
 
 <para>
@@ -318,6 +340,54 @@ interested in translating it, please email me
 offset = N * getpagesize();
 </programlisting>
 
+<para>
+	Sometimes there is hardware with memory-like regions that can not be
+	mapped with the technique described here, but there are still ways to
+	access them from userspace. The most common example are x86 ioports.
+	On x86 systems, userspace can access these ioports using
+	<function>ioperm()</function>, <function>iopl()</function>,
+	<function>inb()</function>, <function>outb()</function>, and similar
+	functions.
+</para>
+<para>
+	Since these ioport regions can not be mapped, they will not appear under
+	<filename>/sys/class/uio/uioX/maps/</filename> like the normal memory
+	described above. Without information about the port regions a hardware
+	has to offer, it becomes difficult for the userspace part of the
+	driver to find out which ports belong to which UIO device.
+</para>
+<para>
+	To address this situation, the new directory
+	<filename>/sys/class/uio/uioX/portio/</filename> was added. It only
+	exists if the driver wants to pass information about one or more port
+	regions to userspace. If that is the case, subdirectories named
+	<filename>port0</filename>, <filename>port1</filename>, and so on,
+	will appear underneath
+	<filename>/sys/class/uio/uioX/portio/</filename>.
+</para>
+<para>
+	Each <filename>portX/</filename> directory contains three read-only
+	files that show start, size, and type of the port region:
+</para>
+<itemizedlist>
+<listitem>
+	<para>
+	<filename>start</filename>: The first port of this region.
+	</para>
+</listitem>
+<listitem>
+	<para>
+	<filename>size</filename>: The number of ports in this region.
+	</para>
+</listitem>
+<listitem>
+	<para>
+	<filename>porttype</filename>: A string describing the type of port.
+	</para>
+</listitem>
+</itemizedlist>
+
+
 </sect1>
 </chapter>
 
@@ -339,12 +409,12 @@ offset = N * getpagesize();
 
 <itemizedlist>
 <listitem><para>
-<varname>char *name</varname>: Required. The name of your driver as
+<varname>const char *name</varname>: Required. The name of your driver as
 it will appear in sysfs. I recommend using the name of your module for this.
 </para></listitem>
 
 <listitem><para>
-<varname>char *version</varname>: Required. This string appears in
+<varname>const char *version</varname>: Required. This string appears in
 <filename>/sys/class/uio/uioX/version</filename>.
 </para></listitem>
 
@@ -355,6 +425,13 @@ mapping you need to fill one of the <varname>uio_mem</varname> structures.
 See the description below for details.
 </para></listitem>
 
+<listitem><para>
+<varname>struct uio_port port[ MAX_UIO_PORTS_REGIONS ]</varname>: Required
+if you want to pass information about ioports to userspace. For each port
+region you need to fill one of the <varname>uio_port</varname> structures.
+See the description below for details.
+</para></listitem>
+
 <listitem><para>
 <varname>long irq</varname>: Required. If your hardware generates an
 interrupt, it's your modules task to determine the irq number during
@@ -448,6 +525,42 @@ Please do not touch the <varname>kobj</varname> element of
 <varname>struct uio_mem</varname>! It is used by the UIO framework
 to set up sysfs files for this mapping. Simply leave it alone.
 </para>
+
+<para>
+Sometimes, your device can have one or more port regions which can not be
+mapped to userspace. But if there are other possibilities for userspace to
+access these ports, it makes sense to make information about the ports
+available in sysfs. For each region, you have to set up a
+<varname>struct uio_port</varname> in the <varname>port[]</varname> array.
+Here's a description of the fields of <varname>struct uio_port</varname>:
+</para>
+
+<itemizedlist>
+<listitem><para>
+<varname>char *porttype</varname>: Required. Set this to one of the predefined
+constants. Use <varname>UIO_PORT_X86</varname> for the ioports found in x86
+architectures.
+</para></listitem>
+
+<listitem><para>
+<varname>unsigned long start</varname>: Required if the port region is used.
+Fill in the number of the first port of this region.
+</para></listitem>
+
+<listitem><para>
+<varname>unsigned long size</varname>: Fill in the number of ports in this
+region. If <varname>size</varname> is zero, the region is considered unused.
+Note that you <emphasis>must</emphasis> initialize <varname>size</varname>
+with zero for all unused regions.
+</para></listitem>
+</itemizedlist>
+
+<para>
+Please do not touch the <varname>portio</varname> element of
+<varname>struct uio_port</varname>! It is used internally by the UIO
+framework to set up sysfs files for this region. Simply leave it alone.
+</para>
+
 </sect1>
 
 <sect1 id="adding_irq_handler">
@@ -497,6 +610,78 @@ to set up sysfs files for this mapping. Simply leave it alone.
 	</para>
 </sect1>
 
+<sect1 id="using_uio_pdrv">
+<title>Using uio_pdrv for platform devices</title>
+	<para>
+	In many cases, UIO drivers for platform devices can be handled in a
+	generic way. In the same place where you define your
+	<varname>struct platform_device</varname>, you simply also implement
+	your interrupt handler and fill your
+	<varname>struct uio_info</varname>. A pointer to this
+	<varname>struct uio_info</varname> is then used as
+	<varname>platform_data</varname> for your platform device.
+	</para>
+	<para>
+	You also need to set up an array of <varname>struct resource</varname>
+	containing addresses and sizes of your memory mappings. This
+	information is passed to the driver using the
+	<varname>.resource</varname> and <varname>.num_resources</varname>
+	elements of <varname>struct platform_device</varname>.
+	</para>
+	<para>
+	You now have to set the <varname>.name</varname> element of
+	<varname>struct platform_device</varname> to
+	<varname>"uio_pdrv"</varname> to use the generic UIO platform device
+	driver. This driver will fill the <varname>mem[]</varname> array
+	according to the resources given, and register the device.
+	</para>
+	<para>
+	The advantage of this approach is that you only have to edit a file
+	you need to edit anyway. You do not have to create an extra driver.
+	</para>
+</sect1>
+
+<sect1 id="using_uio_pdrv_genirq">
+<title>Using uio_pdrv_genirq for platform devices</title>
+	<para>
+	Especially in embedded devices, you frequently find chips where the
+	irq pin is tied to its own dedicated interrupt line. In such cases,
+	where you can be really sure the interrupt is not shared, we can take
+	the concept of <varname>uio_pdrv</varname> one step further and use a
+	generic interrupt handler. That's what
+	<varname>uio_pdrv_genirq</varname> does.
+	</para>
+	<para>
+	The setup for this driver is the same as described above for
+	<varname>uio_pdrv</varname>, except that you do not implement an
+	interrupt handler. The <varname>.handler</varname> element of
+	<varname>struct uio_info</varname> must remain
+	<varname>NULL</varname>. The  <varname>.irq_flags</varname> element
+	must not contain <varname>IRQF_SHARED</varname>.
+	</para>
+	<para>
+	You will set the <varname>.name</varname> element of
+	<varname>struct platform_device</varname> to
+	<varname>"uio_pdrv_genirq"</varname> to use this driver.
+	</para>
+	<para>
+	The generic interrupt handler of <varname>uio_pdrv_genirq</varname>
+	will simply disable the interrupt line using
+	<function>disable_irq_nosync()</function>. After doing its work,
+	userspace can reenable the interrupt by writing 0x00000001 to the UIO
+	device file. The driver already implements an
+	<function>irq_control()</function> to make this possible, you must not
+	implement your own.
+	</para>
+	<para>
+	Using <varname>uio_pdrv_genirq</varname> not only saves a few lines of
+	interrupt handler code. You also do not need to know anything about
+	the chip's internal registers to create the kernel part of the driver.
+	All you need to know is the irq number of the pin the chip is
+	connected to.
+	</para>
+</sect1>
+
 </chapter>
 
 <chapter id="userspace_driver" xreflabel="Writing a driver in user space">

Documentation/IO-mapping.txt

 [ NOTE: The virt_to_bus() and bus_to_virt() functions have been
-	superseded by the functionality provided by the PCI DMA
-	interface (see Documentation/DMA-mapping.txt).  They continue
+	superseded by the functionality provided by the PCI DMA interface
+	(see Documentation/PCI/PCI-DMA-mapping.txt).  They continue
 	to be documented below for historical purposes, but new code
 	must not use them. --davidm 00/12/12 ]
 

Documentation/PCI/pci.txt

@@ -294,7 +294,8 @@ NOTE: pci_enable_device() can fail! Check the return value.
 
 pci_set_master() will enable DMA by setting the bus master bit
 in the PCI_COMMAND register. It also fixes the latency timer value if
-it's set to something bogus by the BIOS.
+it's set to something bogus by the BIOS.  pci_clear_master() will
+disable DMA by clearing the bus master bit.
 
 If the PCI device can use the PCI Memory-Write-Invalidate transaction,
 call pci_set_mwi().  This enables the PCI_COMMAND bit for Mem-Wr-Inval

Documentation/RCU/00-INDEX

@@ -12,6 +12,8 @@ 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.
 torture.txt

Documentation/RCU/rcubarrier.txt

+RCU and Unloadable Modules
+
+[Originally published in LWN Jan. 14, 2007: http://lwn.net/Articles/217484/]
+
+RCU (read-copy update) is a synchronization mechanism that can be thought
+of as a replacement for read-writer locking (among other things), but with
+very low-overhead readers that are immune to deadlock, priority inversion,
+and unbounded latency. RCU read-side critical sections are delimited
+by rcu_read_lock() and rcu_read_unlock(), which, in non-CONFIG_PREEMPT
+kernels, generate no code whatsoever.
+
+This means that RCU writers are unaware of the presence of concurrent
+readers, so that RCU updates to shared data must be undertaken quite
+carefully, leaving an old version of the data structure in place until all
+pre-existing readers have finished. These old versions are needed because
+such readers might hold a reference to them. RCU updates can therefore be
+rather expensive, and RCU is thus best suited for read-mostly situations.
+
+How can an RCU writer possibly determine when all readers are finished,
+given that readers might well leave absolutely no trace of their
+presence? There is a synchronize_rcu() primitive that blocks until all
+pre-existing readers have completed. An updater wishing to delete an
+element p from a linked list might do the following, while holding an
+appropriate lock, of course:
+
+	list_del_rcu(p);
+	synchronize_rcu();
+	kfree(p);
+
+But the above code cannot be used in IRQ context -- the call_rcu()
+primitive must be used instead. This primitive takes a pointer to an
+rcu_head struct placed within the RCU-protected data structure and
+another pointer to a function that may be invoked later to free that
+structure. Code to delete an element p from the linked list from IRQ
+context might then be as follows:
+
+	list_del_rcu(p);
+	call_rcu(&p->rcu, p_callback);
+
+Since call_rcu() never blocks, this code can safely be used from within
+IRQ context. The function p_callback() might be defined as follows:
+
+	static void p_callback(struct rcu_head *rp)
+	{
+		struct pstruct *p = container_of(rp, struct pstruct, rcu);
+
+		kfree(p);
+	}
+
+
+Unloading Modules That Use call_rcu()
+
+But what if p_callback is defined in an unloadable module?
+
+If we unload the module while some RCU callbacks are pending,
+the CPUs executing these callbacks are going to be severely
+disappointed when they are later invoked, as fancifully depicted at
+http://lwn.net/images/ns/kernel/rcu-drop.jpg.
+
+We could try placing a synchronize_rcu() in the module-exit code path,
+but this is not sufficient. Although synchronize_rcu() does wait for a
+grace period to elapse, it does not wait for the callbacks to complete.
+
+One might be tempted to try several back-to-back synchronize_rcu()
+calls, but this is still not guaranteed to work. If there is a very
+heavy RCU-callback load, then some of the callbacks might be deferred
+in order to allow other processing to proceed. Such deferral is required
+in realtime kernels in order to avoid excessive scheduling latencies.
+
+
+rcu_barrier()
+
+We instead need the rcu_barrier() primitive. This primitive is similar
+to synchronize_rcu(), but instead of waiting solely for a grace
+period to elapse, it also waits for all outstanding RCU callbacks to
+complete. Pseudo-code using rcu_barrier() is as follows:
+
+   1. Prevent any new RCU callbacks from being posted.
+   2. Execute rcu_barrier().
+   3. Allow the module to be unloaded.
+
+Quick Quiz #1: Why is there no srcu_barrier()?
+
+The rcutorture module makes use of rcu_barrier in its exit function
+as follows:
+
+ 1 static void
+ 2 rcu_torture_cleanup(void)
+ 3 {
+ 4   int i;
+ 5
+ 6   fullstop = 1;
+ 7   if (shuffler_task != NULL) {
+ 8     VERBOSE_PRINTK_STRING("Stopping rcu_torture_shuffle task");
+ 9     kthread_stop(shuffler_task);
+10   }
+11   shuffler_task = NULL;
+12
+13   if (writer_task != NULL) {
+14     VERBOSE_PRINTK_STRING("Stopping rcu_torture_writer task");
+15     kthread_stop(writer_task);
+16   }
+17   writer_task = NULL;
+18
+19   if (reader_tasks != NULL) {
+20     for (i = 0; i < nrealreaders; i++) {
+21       if (reader_tasks[i] != NULL) {
+22         VERBOSE_PRINTK_STRING(
+23           "Stopping rcu_torture_reader task");
+24         kthread_stop(reader_tasks[i]);
+25       }
+26       reader_tasks[i] = NULL;
+27     }
+28     kfree(reader_tasks);
+29     reader_tasks = NULL;
+30   }
+31   rcu_torture_current = NULL;
+32
+33   if (fakewriter_tasks != NULL) {
+34     for (i = 0; i < nfakewriters; i++) {
+35       if (fakewriter_tasks[i] != NULL) {
+36         VERBOSE_PRINTK_STRING(
+37           "Stopping rcu_torture_fakewriter task");
+38         kthread_stop(fakewriter_tasks[i]);
+39       }
+40       fakewriter_tasks[i] = NULL;
+41     }
+42     kfree(fakewriter_tasks);
+43     fakewriter_tasks = NULL;
+44   }
+45
+46   if (stats_task != NULL) {
+47     VERBOSE_PRINTK_STRING("Stopping rcu_torture_stats task");
+48     kthread_stop(stats_task);
+49   }
+50   stats_task = NULL;
+51
+52   /* Wait for all RCU callbacks to fire. */
+53   rcu_barrier();
+54
+55   rcu_torture_stats_print(); /* -After- the stats thread is stopped! */
+56
+57   if (cur_ops->cleanup != NULL)
+58     cur_ops->cleanup();
+59   if (atomic_read(&n_rcu_torture_error))
+60     rcu_torture_print_module_parms("End of test: FAILURE");
+61   else
+62     rcu_torture_print_module_parms("End of test: SUCCESS");
+63 }
+
+Line 6 sets a global variable that prevents any RCU callbacks from
+re-posting themselves. This will not be necessary in most cases, since
+RCU callbacks rarely include calls to call_rcu(). However, the rcutorture
+module is an exception to this rule, and therefore needs to set this
+global variable.
+
+Lines 7-50 stop all the kernel tasks associated with the rcutorture
+module. Therefore, once execution reaches line 53, no more rcutorture
+RCU callbacks will be posted. The rcu_barrier() call on line 53 waits
+for any pre-existing callbacks to complete.
+
+Then lines 55-62 print status and do operation-specific cleanup, and
+then return, permitting the module-unload operation to be completed.
+
+Quick Quiz #2: Is there any other situation where rcu_barrier() might
+	be required?
+
+Your module might have additional complications. For example, if your
+module invokes call_rcu() from timers, you will need to first cancel all
+the timers, and only then invoke rcu_barrier() to wait for any remaining
+RCU callbacks to complete.
+
+
+Implementing rcu_barrier()
+
+Dipankar Sarma's implementation of rcu_barrier() makes use of the fact
+that RCU callbacks are never reordered once queued on one of the per-CPU
+queues. His implementation queues an RCU callback on each of the per-CPU
+callback queues, and then waits until they have all started executing, at
+which point, all earlier RCU callbacks are guaranteed to have completed.
+
+The original code for rcu_barrier() was as follows:
+
+ 1 void rcu_barrier(void)
+ 2 {
+ 3   BUG_ON(in_interrupt());
+ 4   /* Take cpucontrol mutex to protect against CPU hotplug */
+ 5   mutex_lock(&rcu_barrier_mutex);
+ 6   init_completion(&rcu_barrier_completion);
+ 7   atomic_set(&rcu_barrier_cpu_count, 0);
+ 8   on_each_cpu(rcu_barrier_func, NULL, 0, 1);
+ 9   wait_for_completion(&rcu_barrier_completion);
+10   mutex_unlock(&rcu_barrier_mutex);
+11 }
+
+Line 3 verifies that the caller is in process context, and lines 5 and 10
+use rcu_barrier_mutex to ensure that only one rcu_barrier() is using the
+global completion and counters at a time, which are initialized on lines
+6 and 7. Line 8 causes each CPU to invoke rcu_barrier_func(), which is
+shown below. Note that the final "1" in on_each_cpu()'s argument list
+ensures that all the calls to rcu_barrier_func() will have completed
+before on_each_cpu() returns. Line 9 then waits for the completion.
+
+This code was rewritten in 2008 to support rcu_barrier_bh() and
+rcu_barrier_sched() in addition to the original rcu_barrier().
+
+The rcu_barrier_func() runs on each CPU, where it invokes call_rcu()
+to post an RCU callback, as follows:
+
+ 1 static void rcu_barrier_func(void *notused)
+ 2 {
+ 3 int cpu = smp_processor_id();
+ 4 struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
+ 5 struct rcu_head *head;
+ 6
+ 7 head = &rdp->barrier;
+ 8 atomic_inc(&rcu_barrier_cpu_count);
+ 9 call_rcu(head, rcu_barrier_callback);
+10 }
+
+Lines 3 and 4 locate RCU's internal per-CPU rcu_data structure,
+which contains the struct rcu_head that needed for the later call to
+call_rcu(). Line 7 picks up a pointer to this struct rcu_head, and line
+8 increments a global counter. This counter will later be decremented
+by the callback. Line 9 then registers the rcu_barrier_callback() on
+the current CPU's queue.
+
+The rcu_barrier_callback() function simply atomically decrements the
+rcu_barrier_cpu_count variable and finalizes the completion when it
+reaches zero, as follows:
+
+ 1 static void rcu_barrier_callback(struct rcu_head *notused)
+ 2 {
+ 3 if (atomic_dec_and_test(&rcu_barrier_cpu_count))
+ 4 complete(&rcu_barrier_completion);
+ 5 }
+
+Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes
+	immediately (thus incrementing rcu_barrier_cpu_count to the
+	value one), but the other CPU's rcu_barrier_func() invocations
+	are delayed for a full grace period? Couldn't this result in
+	rcu_barrier() returning prematurely?
+
+
+rcu_barrier() Summary
+
+The rcu_barrier() primitive has seen relatively little use, since most
+code using RCU is in the core kernel rather than in modules. However, if
+you are using RCU from an unloadable module, you need to use rcu_barrier()
+so that your module may be safely unloaded.
+
+
+Answers to Quick Quizzes
+
+Quick Quiz #1: Why is there no srcu_barrier()?
+
+Answer: Since there is no call_srcu(), there can be no outstanding SRCU
+	callbacks. Therefore, there is no need to wait for them.
+
+Quick Quiz #2: Is there any other situation where rcu_barrier() might
+	be required?
+
+Answer: Interestingly enough, rcu_barrier() was not originally
+	implemented for module unloading. Nikita Danilov was using
+	RCU in a filesystem, which resulted in a similar situation at
+	filesystem-unmount time. Dipankar Sarma coded up rcu_barrier()
+	in response, so that Nikita could invoke it during the
+	filesystem-unmount process.
+
+	Much later, yours truly hit the RCU module-unload problem when
+	implementing rcutorture, and found that rcu_barrier() solves
+	this problem as well.
+
+Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes
+	immediately (thus incrementing rcu_barrier_cpu_count to the
+	value one), but the other CPU's rcu_barrier_func() invocations
+	are delayed for a full grace period? Couldn't this result in
+	rcu_barrier() returning prematurely?
+
+Answer: This cannot happen. The reason is that on_each_cpu() has its last
+	argument, the wait flag, set to "1". This flag is passed through
+	to smp_call_function() and further to smp_call_function_on_cpu(),
+	causing this latter to spin until the cross-CPU invocation of
+	rcu_barrier_func() has completed. This by itself would prevent
+	a grace period from completing on non-CONFIG_PREEMPT kernels,
+	since each CPU must undergo a context switch (or other quiescent
+	state) before the grace period can complete. However, this is
+	of no use in CONFIG_PREEMPT kernels.
+
+	Therefore, on_each_cpu() disables preemption across its call
+	to smp_call_function() and also across the local call to
+	rcu_barrier_func(). This prevents the local CPU from context
+	switching, again preventing grace periods from completing. This
+	means that all CPUs have executed rcu_barrier_func() before
+	the first rcu_barrier_callback() can possibly execute, in turn
+	preventing rcu_barrier_cpu_count from prematurely reaching zero.
+
+	Currently, -rt implementations of RCU keep but a single global
+	queue for RCU callbacks, and thus do not suffer from this
+	problem. However, when the -rt RCU eventually does have per-CPU
+	callback queues, things will have to change. One simple change
+	is to add an rcu_read_lock() before line 8 of rcu_barrier()
+	and an rcu_read_unlock() after line 8 of this same function. If
+	you can think of a better change, please let me know!

Documentation/accounting/getdelays.c

@@ -392,6 +392,10 @@ int main(int argc, char *argv[])
 			goto err;
 		}
 	}
+	if (!maskset && !tid && !containerset) {
+		usage();
+		goto err;
+	}
 
 	do {
 		int i;

Documentation/bad_memory.txt

+March 2008
+Jan-Simon Moeller, dl9pf@gmx.de
+
+
+How to deal with bad memory e.g. reported by memtest86+ ?
+#########################################################
+
+There are three possibilities I know of:
+
+1) Reinsert/swap the memory modules
+
+2) Buy new modules (best!) or try to exchange the memory
+   if you have spare-parts
+
+3) Use BadRAM or memmap
+
+This Howto is about number 3) .
+
+
+BadRAM
+######
+BadRAM is the actively developed and available as kernel-patch
+here:  http://rick.vanrein.org/linux/badram/
+
+For more details see the BadRAM documentation.
+
+memmap
+######
+
+memmap is already in the kernel and usable as kernel-parameter at
+boot-time.  Its syntax is slightly strange and you may need to
+calculate the values by yourself!
+
+Syntax to exclude a memory area (see kernel-parameters.txt for details):
+memmap=<size>$<address>
+
+Example: memtest86+ reported here errors at address 0x18691458, 0x18698424 and
+         some others. All had 0x1869xxxx in common, so I chose a pattern of
+         0x18690000,0xffff0000.
+
+With the numbers of the example above:
+memmap=64K$0x18690000
+ or
+memmap=0x10000$0x18690000
+

Documentation/blackfin/00-INDEX

@@ -9,3 +9,6 @@ cachefeatures.txt
 
 Filesystems
 	- Requirements for mounting the root file system.
+
+bfin-gpio-note.txt
+	- Notes in developing/using bfin-gpio driver.

Documentation/blackfin/bfin-gpio-notes.txt

+/*
+ * File:         Documentation/blackfin/bfin-gpio-note.txt
+ * Based on:
+ * Author:
+ *
+ * Created:      $Id: bfin-gpio-note.txt 2008-11-24 16:42 grafyang $
+ * Description:  This file contains the notes in developing/using bfin-gpio.
+ *
+ *
+ * Rev:
+ *
+ * Modified:
+ *               Copyright 2004-2008 Analog Devices Inc.
+ *
+ * Bugs:         Enter bugs at http://blackfin.uclinux.org/
+ *
+ */
+
+
+1. Blackfin GPIO introduction
+
+    There are many GPIO pins on Blackfin. Most of these pins are muxed to
+    multi-functions. They can be configured as peripheral, or just as GPIO,
+    configured to input with interrupt enabled, or output.
+
+    For detailed information, please see "arch/blackfin/kernel/bfin_gpio.c",
+    or the relevant HRM.
+
+
+2. Avoiding resource conflict
+
+    Followed function groups are used to avoiding resource conflict,
+    - Use the pin as peripheral,
+	int peripheral_request(unsigned short per, const char *label);
+	int peripheral_request_list(const unsigned short per[], const char *label);
+	void peripheral_free(unsigned short per);
+	void peripheral_free_list(const unsigned short per[]);
+    - Use the pin as GPIO,
+	int bfin_gpio_request(unsigned gpio, const char *label);
+	void bfin_gpio_free(unsigned gpio);
+    - Use the pin as GPIO interrupt,
+	int bfin_gpio_irq_request(unsigned gpio, const char *label);
+	void bfin_gpio_irq_free(unsigned gpio);
+
+    The request functions will record the function state for a certain pin,
+    the free functions will clear it's function state.
+    Once a pin is requested, it can't be requested again before it is freed by
+    previous caller, otherwise kernel will dump stacks, and the request
+    function fail.
+    These functions are wrapped by other functions, most of the users need not
+    care.
+
+
+3. But there are some exceptions
+    - Kernel permit the identical GPIO be requested both as GPIO and GPIO
+    interrut.
+    Some drivers, like gpio-keys, need this behavior. Kernel only print out
+    warning messages like,
+	bfin-gpio: GPIO 24 is already reserved by gpio-keys: BTN0, and you are
+configuring it as IRQ!
+
+        Note: Consider the case that, if there are two drivers need the
+	identical GPIO, one of them use it as GPIO, the other use it as
+	GPIO interrupt. This will really cause resource conflict. So if
+	there is any abnormal driver behavior, please check the bfin-gpio
+	warning messages.
+
+    - Kernel permit the identical GPIO be requested from the same driver twice.
+
+
+

Documentation/block/biodoc.txt

@@ -186,8 +186,9 @@ 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 DMA-mapping.txt for a discussion on PCI high mem DMA
-aspects and mapping of scatter gather lists, and support for 64 bit PCI.
+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.
 
 Special handling is required only for cases where i/o needs to happen on
 pages at physical memory addresses beyond what the device can support. In these
@@ -953,14 +954,14 @@ elevator_allow_merge_fn		called whenever the block layer determines
 				results in some sort of conflict internally,
 				this hook allows it to do that.
 
-elevator_dispatch_fn		fills the dispatch queue with ready requests.
+elevator_dispatch_fn*		fills the dispatch queue with ready requests.
 				I/O schedulers are free to postpone requests by
 				not filling the dispatch queue unless @force
 				is non-zero.  Once dispatched, I/O schedulers
 				are not allowed to manipulate the requests -
 				they belong to generic dispatch queue.
 
-elevator_add_req_fn		called to add a new request into the scheduler
+elevator_add_req_fn*		called to add a new request into the scheduler
 
 elevator_queue_empty_fn		returns true if the merge queue is empty.
 				Drivers shouldn't use this, but rather check
@@ -990,7 +991,7 @@ elevator_activate_req_fn	Called when device driver first sees a request.
 elevator_deactivate_req_fn	Called when device driver decides to delay
 				a request by requeueing it.
 
-elevator_init_fn
+elevator_init_fn*
 elevator_exit_fn		Allocate and free any elevator specific storage
 				for a queue.
 

Documentation/block/queue-sysfs.txt

+Queue sysfs files
+=================
+
+This text file will detail the queue files that are located in the sysfs tree
+for each block device. Note that stacked devices typically do not export
+any settings, since their queue merely functions are a remapping target.
+These files are the ones found in the /sys/block/xxx/queue/ directory.
+
+Files denoted with a RO postfix are readonly and the RW postfix means
+read-write.
+
+hw_sector_size (RO)
+-------------------
+This is the hardware sector size of the device, in bytes.
+
+max_hw_sectors_kb (RO)
+----------------------
+This is the maximum number of kilobytes supported in a single data transfer.
+
+max_sectors_kb (RW)
+-------------------
+This is the maximum number of kilobytes that the block layer will allow
+for a filesystem request. Must be smaller than or equal to the maximum
+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.
+
+nr_requests (RW)
+----------------
+This controls how many requests may be allocated in the block layer for
+read or write requests. Note that the total allocated number may be twice
+this amount, since it applies only to reads or writes (not the accumulated
+sum).
+
+read_ahead_kb (RW)
+------------------
+Maximum number of kilobytes to read-ahead for filesystems on this block
+device.
+
+rq_affinity (RW)
+----------------
+If this option is enabled, the block layer will migrate request completions
+to the CPU that originally submitted the request. For some workloads
+this provides a significant reduction in CPU cycles due to caching effects.
+
+scheduler (RW)
+--------------
+When read, this file will display the current and available IO schedulers
+for this block device. The currently active IO scheduler will be enclosed
+in [] brackets. Writing an IO scheduler name to this file will switch
+control of this block device to that new IO scheduler. Note that writing
+an IO scheduler name to this file will attempt to load that IO scheduler
+module, if it isn't already present in the system.
+
+
+
+Jens Axboe <jens.axboe@oracle.com>, February 2009

Documentation/cgroups/cgroups.txt

 				CGROUPS
 				-------
 
-Written by Paul Menage <menage@google.com> based on Documentation/cpusets.txt
+Written by Paul Menage <menage@google.com> based on
+Documentation/cgroups/cpusets.txt
 
 Original copyright statements from cpusets.txt:
 Portions Copyright (C) 2004 BULL SA.
@@ -68,7 +69,7 @@ On their own, the only use for cgroups is for simple job
 tracking. The intention is that other subsystems hook into the generic
 cgroup support to provide new attributes for cgroups, such as
 accounting/limiting the resources which processes in a cgroup can
-access. For example, cpusets (see Documentation/cpusets.txt) allows
+access. For example, cpusets (see Documentation/cgroups/cpusets.txt) allows
 you to associate a set of CPUs and a set of memory nodes with the
 tasks in each cgroup.
 
@@ -227,7 +228,6 @@ Each cgroup is represented by a directory in the cgroup file system
 containing the following files describing that cgroup:
 
  - tasks: list of tasks (by pid) attached to that cgroup
- - releasable flag: cgroup currently removeable?
  - notify_on_release flag: run the release agent on exit?
  - release_agent: the path to use for release notifications (this file
    exists in the top cgroup only)
@@ -360,7 +360,7 @@ Now you want to do something with this cgroup.
 
 In this directory you can find several files:
 # ls
-notify_on_release releasable tasks
+notify_on_release tasks
 (plus whatever files added by the attached subsystems)
 
 Now attach your shell to this cgroup:
@@ -479,7 +479,6 @@ newly-created cgroup if an error occurs after this subsystem's
 create() method has been called for the new cgroup).
 
 void pre_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp);
-(cgroup_mutex held by caller)
 
 Called before checking the reference count on each subsystem. This may
 be useful for subsystems which have some extra references even if
@@ -498,6 +497,7 @@ remain valid while the caller holds cgroup_mutex.
 
 void attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 	    struct cgroup *old_cgrp, struct task_struct *task)
+(cgroup_mutex held by caller)
 
 Called after the task has been attached to the cgroup, to allow any
 post-attachment activity that requires memory allocations or blocking.
@@ -511,6 +511,7 @@ void exit(struct cgroup_subsys *ss, struct task_struct *task)
 Called during task exit.
 
 int populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
+(cgroup_mutex held by caller)
 
 Called after creation of a cgroup to allow a subsystem to populate
 the cgroup directory with file entries.  The subsystem should make
@@ -520,6 +521,7 @@ method can return an error code, the error code is currently not
 always handled well.
 
 void post_clone(struct cgroup_subsys *ss, struct cgroup *cgrp)
+(cgroup_mutex held by caller)
 
 Called at the end of cgroup_clone() to do any paramater
 initialization which might be required before a task could attach.  For
@@ -527,7 +529,7 @@ example in cpusets, no task may attach before 'cpus' and 'mems' are set
 up.
 
 void bind(struct cgroup_subsys *ss, struct cgroup *root)
-(cgroup_mutex held by caller)
+(cgroup_mutex and ss->hierarchy_mutex held by caller)
 
 Called when a cgroup subsystem is rebound to a different hierarchy
 and root cgroup. Currently this will only involve movement between

Documentation/cgroups/memcg_test.txt

+Memory Resource Controller(Memcg)  Implementation Memo.
+Last Updated: 2009/1/19
+Base Kernel Version: based on 2.6.29-rc2.
+
+Because VM is getting complex (one of reasons is memcg...), memcg's behavior
+is complex. This is a document for memcg's internal behavior.
+Please note that implementation details can be changed.
+
+(*) Topics on API should be in Documentation/cgroups/memory.txt)
+
+0. How to record usage ?
+   2 objects are used.
+
+   page_cgroup ....an object per page.
+	Allocated at boot or memory hotplug. Freed at memory hot removal.
+
+   swap_cgroup ... an entry per swp_entry.
+	Allocated at swapon(). Freed at swapoff().
+
+   The page_cgroup has USED bit and double count against a page_cgroup never
+   occurs. swap_cgroup is used only when a charged page is swapped-out.
+
+1. Charge
+
+   a page/swp_entry may be charged (usage += PAGE_SIZE) at
+
+	mem_cgroup_newpage_charge()
+	  Called at new page fault and Copy-On-Write.
+
+	mem_cgroup_try_charge_swapin()
+	  Called at do_swap_page() (page fault on swap entry) and swapoff.
+	  Followed by charge-commit-cancel protocol. (With swap accounting)
+	  At commit, a charge recorded in swap_cgroup is removed.
+
+	mem_cgroup_cache_charge()
+	  Called at add_to_page_cache()
+
+	mem_cgroup_cache_charge_swapin()
+	  Called at shmem's swapin.
+
+	mem_cgroup_prepare_migration()
+	  Called before migration. "extra" charge is done and followed by
+	  charge-commit-cancel protocol.
+	  At commit, charge against oldpage or newpage will be committed.
+
+2. Uncharge
+  a page/swp_entry may be uncharged (usage -= PAGE_SIZE) by
+
+	mem_cgroup_uncharge_page()
+	  Called when an anonymous page is fully unmapped. I.e., mapcount goes
+	  to 0. If the page is SwapCache, uncharge is delayed until
+	  mem_cgroup_uncharge_swapcache().
+
+	mem_cgroup_uncharge_cache_page()
+	  Called when a page-cache is deleted from radix-tree. If the page is
+	  SwapCache, uncharge is delayed until mem_cgroup_uncharge_swapcache().
+
+	mem_cgroup_uncharge_swapcache()
+	  Called when SwapCache is removed from radix-tree. The charge itself
+	  is moved to swap_cgroup. (If mem+swap controller is disabled, no
+	  charge to swap occurs.)
+
+	mem_cgroup_uncharge_swap()
+	  Called when swp_entry's refcnt goes down to 0. A charge against swap
+	  disappears.
+
+	mem_cgroup_end_migration(old, new)
+	At success of migration old is uncharged (if necessary), a charge
+	to new page is committed. At failure, charge to old page is committed.
+
+3. charge-commit-cancel
+	In some case, we can't know this "charge" is valid or not at charging
+	(because of races).
+	To handle such case, there are charge-commit-cancel functions.
+		mem_cgroup_try_charge_XXX
+		mem_cgroup_commit_charge_XXX
+		mem_cgroup_cancel_charge_XXX
+	these are used in swap-in and migration.
+
+	At try_charge(), there are no flags to say "this page is charged".
+	at this point, usage += PAGE_SIZE.
+
+	At commit(), the function checks the page should be charged or not
+	and set flags or avoid charging.(usage -= PAGE_SIZE)
+
+	At cancel(), simply usage -= PAGE_SIZE.
+
+Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
+
+4. Anonymous
+	Anonymous page is newly allocated at
+		  - page fault into MAP_ANONYMOUS mapping.
+		  - Copy-On-Write.
+ 	It is charged right after it's allocated before doing any page table
+	related operations. Of course, it's uncharged when another page is used
+	for the fault address.
+
+	At freeing anonymous page (by exit() or munmap()), zap_pte() is called
+	and pages for ptes are freed one by one.(see mm/memory.c). Uncharges
+	are done at page_remove_rmap() when page_mapcount() goes down to 0.
+
+	Another page freeing is by page-reclaim (vmscan.c) and anonymous
+	pages are swapped out. In this case, the page is marked as
+	PageSwapCache(). uncharge() routine doesn't uncharge the page marked
+	as SwapCache(). It's delayed until __delete_from_swap_cache().
+
+	4.1 Swap-in.
+	At swap-in, the page is taken from swap-cache. There are 2 cases.
+
+	(a) If the SwapCache is newly allocated and read, it has no charges.
+	(b) If the SwapCache has been mapped by processes, it has been
+	    charged already.
+
+	This swap-in is one of the most complicated work. In do_swap_page(),
+	following events occur when pte is unchanged.
+
+	(1) the page (SwapCache) is looked up.
+	(2) lock_page()
+	(3) try_charge_swapin()
+	(4) reuse_swap_page() (may call delete_swap_cache())
+	(5) commit_charge_swapin()
+	(6) swap_free().
+
+	Considering following situation for example.
+
+	(A) The page has not been charged before (2) and reuse_swap_page()
+	    doesn't call delete_from_swap_cache().
+	(B) The page has not been charged before (2) and reuse_swap_page()
+	    calls delete_from_swap_cache().
+	(C) The page has been charged before (2) and reuse_swap_page() doesn't
+	    call delete_from_swap_cache().
+	(D) The page has been charged before (2) and reuse_swap_page() calls
+	    delete_from_swap_cache().
+
+	    memory.usage/memsw.usage changes to this page/swp_entry will be
+	 Case          (A)      (B)       (C)     (D)
+         Event
+       Before (2)     0/ 1     0/ 1      1/ 1    1/ 1
+          ===========================================
+          (3)        +1/+1    +1/+1     +1/+1   +1/+1
+          (4)          -       0/ 0       -     -1/ 0
+          (5)         0/-1     0/ 0     -1/-1    0/ 0
+          (6)          -       0/-1       -      0/-1
+          ===========================================
+       Result         1/ 1     1/ 1      1/ 1    1/ 1
+
+       In any cases, charges to this page should be 1/ 1.
+
+	4.2 Swap-out.
+	At swap-out, typical state transition is below.
+
+	(a) add to swap cache. (marked as SwapCache)
+	    swp_entry's refcnt += 1.
+	(b) fully unmapped.
+	    swp_entry's refcnt += # of ptes.
+	(c) write back to swap.
+	(d) delete from swap cache. (remove from SwapCache)
+	    swp_entry's refcnt -= 1.
+
+
+	At (b), the page is marked as SwapCache and not uncharged.
+	At (d), the page is removed from SwapCache and a charge in page_cgroup
+	is moved to swap_cgroup.
+
+	Finally, at task exit,
+	(e) zap_pte() is called and swp_entry's refcnt -=1 -> 0.
+	Here, a charge in swap_cgroup disappears.
+
+5. Page Cache
+   	Page Cache is charged at
+	- add_to_page_cache_locked().
+
+	uncharged at
+	- __remove_from_page_cache().
+
+	The logic is very clear. (About migration, see below)
+	Note: __remove_from_page_cache() is called by remove_from_page_cache()
+	and __remove_mapping().
+
+6. Shmem(tmpfs) Page Cache
+	Memcg's charge/uncharge have special handlers of shmem. The best way
+	to understand shmem's page state transition is to read mm/shmem.c.
+	But brief explanation of the behavior of memcg around shmem will be
+	helpful to understand the logic.
+
+	Shmem's page (just leaf page, not direct/indirect block) can be on
+		- radix-tree of shmem's inode.
+		- SwapCache.
+		- Both on radix-tree and SwapCache. This happens at swap-in
+		  and swap-out,
+
+	It's charged when...
+	- A new page is added to shmem's radix-tree.
+	- A swp page is read. (move a charge from swap_cgroup to page_cgroup)
+	It's uncharged when
+	- A page is removed from radix-tree and not SwapCache.
+	- When SwapCache is removed, a charge is moved to swap_cgroup.
+	- When swp_entry's refcnt goes down to 0, a charge in swap_cgroup
+	  disappears.
+
+7. Page Migration
+   	One of the most complicated functions is page-migration-handler.
+	Memcg has 2 routines. Assume that we are migrating a page's contents
+	from OLDPAGE to NEWPAGE.
+
+	Usual migration logic is..
+	(a) remove the page from LRU.
+	(b) allocate NEWPAGE (migration target)
+	(c) lock by lock_page().
+	(d) unmap all mappings.
+	(e-1) If necessary, replace entry in radix-tree.
+	(e-2) move contents of a page.
+	(f) map all mappings again.
+	(g) pushback the page to LRU.
+	(-) OLDPAGE will be freed.
+
+	Before (g), memcg should complete all necessary charge/uncharge to
+	NEWPAGE/OLDPAGE.
+
+	The point is....
+	- If OLDPAGE is anonymous, all charges will be dropped at (d) because
+          try_to_unmap() drops all mapcount and the page will not be
+	  SwapCache.
+
+	- If OLDPAGE is SwapCache, charges will be kept at (g) because
+	  __delete_from_swap_cache() isn't called at (e-1)
+
+	- If OLDPAGE is page-cache, charges will be kept at (g) because
+	  remove_from_swap_cache() isn't called at (e-1)
+
+	memcg provides following hooks.
+
+	- mem_cgroup_prepare_migration(OLDPAGE)
+	  Called after (b) to account a charge (usage += PAGE_SIZE) against
+	  memcg which OLDPAGE belongs to.
+
+        - mem_cgroup_end_migration(OLDPAGE, NEWPAGE)
+	  Called after (f) before (g).
+	  If OLDPAGE is used, commit OLDPAGE again. If OLDPAGE is already
+	  charged, a charge by prepare_migration() is automatically canceled.
+	  If NEWPAGE is used, commit NEWPAGE and uncharge OLDPAGE.
+
+	  But zap_pte() (by exit or munmap) can be called while migration,
+	  we have to check if OLDPAGE/NEWPAGE is a valid page after commit().
+
+8. LRU
+        Each memcg has its own private LRU. Now, it's handling is under global
+	VM's control (means that it's handled under global zone->lru_lock).
+	Almost all routines around memcg's LRU is called by global LRU's
+	list management functions under zone->lru_lock().
+
+	A special function is mem_cgroup_isolate_pages(). This scans
+	memcg's private LRU and call __isolate_lru_page() to extract a page
+	from LRU.
+	(By __isolate_lru_page(), the page is removed from both of global and
+	 private LRU.)
+
+
+9. Typical Tests.
+
+ Tests for racy cases.
+
+ 9.1 Small limit to memcg.
+	When you do test to do racy case, it's good test to set memcg's limit
+	to be very small rather than GB. Many races found in the test under
+	xKB or xxMB limits.
+	(Memory behavior under GB and Memory behavior under MB shows very
+	 different situation.)
+
+ 9.2 Shmem
+	Historically, memcg's shmem handling was poor and we saw some amount
+	of troubles here. This is because shmem is page-cache but can be
+	SwapCache. Test with shmem/tmpfs is always good test.
+
+ 9.3 Migration
+	For NUMA, migration is an another special case. To do easy test, cpuset
+	is useful. Following is a sample script to do migration.
+
+	mount -t cgroup -o cpuset none /opt/cpuset
+
+	mkdir /opt/cpuset/01
+	echo 1 > /opt/cpuset/01/cpuset.cpus
+	echo 0 > /opt/cpuset/01/cpuset.mems
+	echo 1 > /opt/cpuset/01/cpuset.memory_migrate
+	mkdir /opt/cpuset/02
+	echo 1 > /opt/cpuset/02/cpuset.cpus
+	echo 1 > /opt/cpuset/02/cpuset.mems
+	echo 1 > /opt/cpuset/02/cpuset.memory_migrate
+
+	In above set, when you moves a task from 01 to 02, page migration to
+	node 0 to node 1 will occur. Following is a script to migrate all
+	under cpuset.
+	--
+	move_task()
+	{
+	for pid in $1
+        do
+                /bin/echo $pid >$2/tasks 2>/dev/null
+		echo -n $pid
+		echo -n " "
+        done
+	echo END
+	}
+
+	G1_TASK=`cat ${G1}/tasks`
+	G2_TASK=`cat ${G2}/tasks`
+	move_task "${G1_TASK}" ${G2} &
+	--
+ 9.4 Memory hotplug.
+	memory hotplug test is one of good test.
+	to offline memory, do following.
+	# echo offline > /sys/devices/system/memory/memoryXXX/state
+	(XXX is the place of memory)
+	This is an easy way to test page migration, too.
+
+ 9.5 mkdir/rmdir
+	When using hierarchy, mkdir/rmdir test should be done.
+	Use tests like the following.
+
+	echo 1 >/opt/cgroup/01/memory/use_hierarchy
+	mkdir /opt/cgroup/01/child_a
+	mkdir /opt/cgroup/01/child_b
+
+	set limit to 01.
+	add limit to 01/child_b
+	run jobs under child_a and child_b
+
+	create/delete following groups at random while jobs are running.
+	/opt/cgroup/01/child_a/child_aa
+	/opt/cgroup/01/child_b/child_bb
+	/opt/cgroup/01/child_c
+
+	running new jobs in new group is also good.
+
+ 9.6 Mount with other subsystems.
+	Mounting with other subsystems is a good test because there is a
+	race and lock dependency with other cgroup subsystems.
+
+	example)
+	# mount -t cgroup none /cgroup -t cpuset,memory,cpu,devices
+
+	and do task move, mkdir, rmdir etc...under this.
+
+ 9.7 swapoff.
+	Besides management of swap is one of complicated parts of memcg,
+	call path of swap-in at swapoff is not same as usual swap-in path..
+	It's worth to be tested explicitly.
+
+	For example, test like following is good.
+	(Shell-A)
+	# mount -t cgroup none /cgroup -t memory
+	# mkdir /cgroup/test
+	# echo 40M > /cgroup/test/memory.limit_in_bytes
+	# echo 0 > /cgroup/test/tasks
+	Run malloc(100M) program under this. You'll see 60M of swaps.
+	(Shell-B)
+	# move all tasks in /cgroup/test to /cgroup
+	# /sbin/swapoff -a
+	# rmdir /test/cgroup
+	# kill malloc task.
+
+	Of course, tmpfs v.s. swapoff test should be tested, too.

Documentation/cgroups/memory.txt

+Memory Resource Controller
+
+NOTE: The Memory Resource Controller has been generically been referred
+to as the memory controller in this document. Do not confuse memory controller
+used here with the memory controller that is used in hardware.
+
+Salient features
+
+a. Enable control of both RSS (mapped) and Page Cache (unmapped) pages
+b. The infrastructure allows easy addition of other types of memory to control
+c. Provides *zero overhead* for non memory controller users
+d. Provides a double LRU: global memory pressure causes reclaim from the
+   global LRU; a cgroup on hitting a limit, reclaims from the per
+   cgroup LRU
+
+NOTE: Swap Cache (unmapped) is not accounted now.
+
+Benefits and Purpose of the memory controller
+
+The memory controller isolates the memory behaviour of a group of tasks
+from the rest of the system. The article on LWN [12] mentions some probable
+uses of the memory controller. The memory controller can be used to
+
+a. Isolate an application or a group of applications
+   Memory hungry applications can be isolated and limited to a smaller
+   amount of memory.
+b. Create a cgroup with limited amount of memory, this can be used
+   as a good alternative to booting with mem=XXXX.
+c. Virtualization solutions can control the amount of memory they want
+   to assign to a virtual machine instance.
+d. A CD/DVD burner could control the amount of memory used by the
+   rest of the system to ensure that burning does not fail due to lack
+   of available memory.
+e. There are several other use cases, find one or use the controller just
+   for fun (to learn and hack on the VM subsystem).
+
+1. History
+
+The memory controller has a long history. A request for comments for the memory
+controller was posted by Balbir Singh [1]. At the time the RFC was posted
+there were several implementations for memory control. The goal of the
+RFC was to build consensus and agreement for the minimal features required
+for memory control. The first RSS controller was posted by Balbir Singh[2]
+in Feb 2007. Pavel Emelianov [3][4][5] has since posted three versions of the
+RSS controller. At OLS, at the resource management BoF, everyone suggested
+that we handle both page cache and RSS together. Another request was raised
+to allow user space handling of OOM. The current memory controller is
+at version 6; it combines both mapped (RSS) and unmapped Page
+Cache Control [11].
+
+2. Memory Control
+
+Memory is a unique resource in the sense that it is present in a limited
+amount. If a task requires a lot of CPU processing, the task can spread
+its processing over a period of hours, days, months or years, but with
+memory, the same physical memory needs to be reused to accomplish the task.
+
+The memory controller implementation has been divided into phases. These
+are:
+
+1. Memory controller
+2. mlock(2) controller
+3. Kernel user memory accounting and slab control
+4. user mappings length controller
+
+The memory controller is the first controller developed.
+
+2.1. Design
+
+The core of the design is a counter called the res_counter. The res_counter
+tracks the current memory usage and limit of the group of processes associated
+with the controller. Each cgroup has a memory controller specific data
+structure (mem_cgroup) associated with it.
+
+2.2. Accounting
+
+		+--------------------+
+		|  mem_cgroup     |
+		|  (res_counter)     |
+		+--------------------+
+		 /            ^      \
+		/             |       \
+           +---------------+  |        +---------------+
+           | mm_struct     |  |....    | mm_struct     |
+           |               |  |        |               |
+           +---------------+  |        +---------------+
+                              |
+                              + --------------+
+                                              |
+           +---------------+           +------+--------+
+           | page          +---------->  page_cgroup|
+           |               |           |               |
+           +---------------+           +---------------+
+
+             (Figure 1: Hierarchy of Accounting)
+
+
+Figure 1 shows the important aspects of the controller
+
+1. Accounting happens per cgroup
+2. Each mm_struct knows about which cgroup it belongs to
+3. Each page has a pointer to the page_cgroup, which in turn knows the
+   cgroup it belongs to
+
+The accounting is done as follows: mem_cgroup_charge() is invoked to setup
+the necessary data structures and check if the cgroup that is being charged
+is over its limit. If it is then reclaim is invoked on the cgroup.
+More details can be found in the reclaim section of this document.
+If everything goes well, a page meta-data-structure called page_cgroup is
+allocated and associated with the page.  This routine also adds the page to
+the per cgroup LRU.
+
+2.2.1 Accounting details
+
+All mapped anon pages (RSS) and cache pages (Page Cache) are accounted.
+(some pages which never be reclaimable and will not be on global LRU
+ are not accounted. we just accounts pages under usual vm management.)
+
+RSS pages are accounted at page_fault unless they've already been accounted
+for earlier. A file page will be accounted for as Page Cache when it's
+inserted into inode (radix-tree). While it's mapped into the page tables of
+processes, duplicate accounting is carefully avoided.
+
+A RSS page is unaccounted when it's fully unmapped. A PageCache page is
+unaccounted when it's removed from radix-tree.
+
+At page migration, accounting information is kept.
+
+Note: we just account pages-on-lru because our purpose is to control amount
+of used pages. not-on-lru pages are tend to be out-of-control from vm view.
+
+2.3 Shared Page Accounting
+
+Shared pages are accounted on the basis of the first touch approach. The
+cgroup that first touches a page is accounted for the page. The principle
+behind this approach is that a cgroup that aggressively uses a shared
+page will eventually get charged for it (once it is uncharged from
+the cgroup that brought it in -- this will happen on memory pressure).
+
+Exception: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used..
+When you do swapoff and make swapped-out pages of shmem(tmpfs) to
+be backed into memory in force, charges for pages are accounted against the
+caller of swapoff rather than the users of shmem.
+
+
+2.4 Swap Extension (CONFIG_CGROUP_MEM_RES_CTLR_SWAP)
+Swap Extension allows you to record charge for swap. A swapped-in page is
+charged back to original page allocator if possible.
+
+When swap is accounted, following files are added.
+ - memory.memsw.usage_in_bytes.
+ - memory.memsw.limit_in_bytes.
+
+usage of mem+swap is limited by memsw.limit_in_bytes.
+
+Note: why 'mem+swap' rather than swap.
+The global LRU(kswapd) can swap out arbitrary pages. Swap-out means
+to move account from memory to swap...there is no change in usage of
+mem+swap.
+
+In other words, when we want to limit the usage of swap without affecting
+global LRU, mem+swap limit is better than just limiting swap from OS point
+of view.
+
+2.5 Reclaim
+
+Each cgroup maintains a per cgroup LRU that consists of an active
+and inactive list. When a cgroup goes over its limit, we first try
+to reclaim memory from the cgroup so as to make space for the new
+pages that the cgroup has touched. If the reclaim is unsuccessful,
+an OOM routine is invoked to select and kill the bulkiest task in the
+cgroup.
+
+The reclaim algorithm has not been modified for cgroups, except that
+pages that are selected for reclaiming come from the per cgroup LRU
+list.
+
+2. Locking
+
+The memory controller uses the following hierarchy
+
+1. zone->lru_lock is used for selecting pages to be isolated
+2. mem->per_zone->lru_lock protects the per cgroup LRU (per zone)
+3. lock_page_cgroup() is used to protect page->page_cgroup
+
+3. User Interface
+
+0. Configuration
+
+a. Enable CONFIG_CGROUPS
+b. Enable CONFIG_RESOURCE_COUNTERS
+c. Enable CONFIG_CGROUP_MEM_RES_CTLR
+
+1. Prepare the cgroups
+# mkdir -p /cgroups
+# mount -t cgroup none /cgroups -o memory
+
+2. Make the new group and move bash into it
+# mkdir /cgroups/0
+# echo $$ >  /cgroups/0/tasks
+
+Since now we're in the 0 cgroup,
+We can alter the memory limit:
+# echo 4M > /cgroups/0/memory.limit_in_bytes
+
+NOTE: We can use a suffix (k, K, m, M, g or G) to indicate values in kilo,
+mega or gigabytes.
+
+# cat /cgroups/0/memory.limit_in_bytes
+4194304
+
+NOTE: The interface has now changed to display the usage in bytes
+instead of pages
+
+We can check the usage:
+# cat /cgroups/0/memory.usage_in_bytes
+1216512
+
+A successful write to this file does not guarantee a successful set of
+this limit to the value written into the file.  This can be due to a
+number of factors, such as rounding up to page boundaries or the total
+availability of memory on the system.  The user is required to re-read
+this file after a write to guarantee the value committed by the kernel.
+
+# echo 1 > memory.limit_in_bytes
+# cat memory.limit_in_bytes
+4096
+
+The memory.failcnt field gives the number of times that the cgroup limit was
+exceeded.
+
+The memory.stat file gives accounting information. Now, the number of
+caches, RSS and Active pages/Inactive pages are shown.
+
+4. Testing
+
+Balbir posted lmbench, AIM9, LTP and vmmstress results [10] and [11].
+Apart from that v6 has been tested with several applications and regular
+daily use. The controller has also been tested on the PPC64, x86_64 and
+UML platforms.
+
+4.1 Troubleshooting
+
+Sometimes a user might find that the application under a cgroup is
+terminated. There are several causes for this:
+
+1. The cgroup limit is too low (just too low to do anything useful)
+2. The user is using anonymous memory and swap is turned off or too low
+
+A sync followed by echo 1 > /proc/sys/vm/drop_caches will help get rid of
+some of the pages cached in the cgroup (page cache pages).
+
+4.2 Task migration
+
+When a task migrates from one cgroup to another, it's charge is not
+carried forward. The pages allocated from the original cgroup still
+remain charged to it, the charge is dropped when the page is freed or
+reclaimed.
+
+4.3 Removing a cgroup
+
+A cgroup can be removed by rmdir, but as discussed in sections 4.1 and 4.2, a
+cgroup might have some charge associated with it, even though all
+tasks have migrated away from it.
+Such charges are freed(at default) or moved to its parent. When moved,
+both of RSS and CACHES are moved to parent.
+If both of them are busy, rmdir() returns -EBUSY. See 5.1 Also.
+
+Charges recorded in swap information is not updated at removal of cgroup.
+Recorded information is discarded and a cgroup which uses swap (swapcache)
+will be charged as a new owner of it.
+
+
+5. Misc. interfaces.
+
+5.1 force_empty
+  memory.force_empty interface is provided to make cgroup's memory usage empty.
+  You can use this interface only when the cgroup has no tasks.
+  When writing anything to this
+
+  # echo 0 > memory.force_empty
+
+  Almost all pages tracked by this memcg will be unmapped and freed. Some of
+  pages cannot be freed because it's locked or in-use. Such pages are moved
+  to parent and this cgroup will be empty. But this may return -EBUSY in
+  some too busy case.
+
+  Typical use case of this interface is that calling this before rmdir().
+  Because rmdir() moves all pages to parent, some out-of-use page caches can be
+  moved to the parent. If you want to avoid that, force_empty will be useful.
+
+5.2 stat file
+  memory.stat file includes following statistics (now)
+	cache			- # of pages from page-cache and shmem.
+	rss			- # of pages from anonymous memory.
+	pgpgin			- # of event of charging
+	pgpgout			- # of event of uncharging
+	active_anon		- # of pages on active lru of anon, shmem.
+	inactive_anon 		- # of pages on active lru of anon, shmem
+	active_file		- # of pages on active lru of file-cache
+	inactive_file		- # of pages on inactive lru of file cache
+	unevictable		- # of pages cannot be reclaimed.(mlocked etc)
+
+	Below is depend on CONFIG_DEBUG_VM.
+	inactive_ratio		- VM inernal parameter. (see mm/page_alloc.c)
+	recent_rotated_anon	- VM internal parameter. (see mm/vmscan.c)
+	recent_rotated_file	- VM internal parameter. (see mm/vmscan.c)
+	recent_scanned_anon 	- VM internal parameter. (see mm/vmscan.c)
+	recent_scanned_file 	- VM internal parameter. (see mm/vmscan.c)
+
+  Memo:
+	recent_rotated means recent frequency of lru rotation.
+	recent_scanned means recent # of scans to lru.
+	showing for better debug please see the code for meanings.
+
+
+5.3 swappiness
+  Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
+
+  Following cgroup's swapiness can't be changed.
+  - root cgroup (uses /proc/sys/vm/swappiness).
+  - a cgroup which uses hierarchy and it has child cgroup.
+  - a cgroup which uses hierarchy and not the root of hierarchy.
+
+
+6. Hierarchy support
+
+The memory controller supports a deep hierarchy and hierarchical accounting.
+The hierarchy is created by creating the appropriate cgroups in the
+cgroup filesystem. Consider for example, the following cgroup filesystem
+hierarchy
+
+		root
+	     /  |   \
+           /	|    \
+	  a	b	c
+			| \
+			|  \
+			d   e
+
+In the diagram above, with hierarchical accounting enabled, all memory
+usage of e, is accounted to its ancestors up until the root (i.e, c and root),
+that has memory.use_hierarchy enabled.  If one of the ancestors goes over its
+limit, the reclaim algorithm reclaims from the tasks in the ancestor and the
+children of the ancestor.
+
+6.1 Enabling hierarchical accounting and reclaim
+
+The memory controller by default disables the hierarchy feature. Support
+can be enabled by writing 1 to memory.use_hierarchy file of the root cgroup
+
+# echo 1 > memory.use_hierarchy
+
+The feature can be disabled by
+
+# echo 0 > memory.use_hierarchy
+
+NOTE1: Enabling/disabling will fail if the cgroup already has other
+cgroups created below it.
+
+NOTE2: This feature can be enabled/disabled per subtree.
+
+7. TODO
+
+1. Add support for accounting huge pages (as a separate controller)
+2. Make per-cgroup scanner reclaim not-shared pages first
+3. Teach controller to account for shared-pages
+4. Start reclamation in the background when the limit is
+   not yet hit but the usage is getting closer
+
+Summary
+
+Overall, the memory controller has been a stable controller and has been
+commented and discussed quite extensively in the community.
+
+References
+
+1. Singh, Balbir. RFC: Memory Controller, http://lwn.net/Articles/206697/
+2. Singh, Balbir. Memory Controller (RSS Control),
+   http://lwn.net/Articles/222762/
+3. Emelianov, Pavel. Resource controllers based on process cgroups
+   http://lkml.org/lkml/2007/3/6/198
+4. Emelianov, Pavel. RSS controller based on process cgroups (v2)
+   http://lkml.org/lkml/2007/4/9/78
+5. Emelianov, Pavel. RSS controller based on process cgroups (v3)
+   http://lkml.org/lkml/2007/5/30/244
+6. Menage, Paul. Control Groups v10, http://lwn.net/Articles/236032/
+7. Vaidyanathan, Srinivasan, Control Groups: Pagecache accounting and control
+   subsystem (v3), http://lwn.net/Articles/235534/
+8. Singh, Balbir. RSS controller v2 test results (lmbench),
+   http://lkml.org/lkml/2007/5/17/232
+9. Singh, Balbir. RSS controller v2 AIM9 results
+   http://lkml.org/lkml/2007/5/18/1
+10. Singh, Balbir. Memory controller v6 test results,
+    http://lkml.org/lkml/2007/8/19/36
+11. Singh, Balbir. Memory controller introduction (v6),
+    http://lkml.org/lkml/2007/8/17/69
+12. Corbet, Jonathan, Controlling memory use in cgroups,
+    http://lwn.net/Articles/243795/

Documentation/controllers/memory.txt

-Memory Resource Controller
-
-NOTE: The Memory Resource Controller has been generically been referred
-to as the memory controller in this document. Do not confuse memory controller
-used here with the memory controller that is used in hardware.
-
-Salient features
-
-a. Enable control of both RSS (mapped) and Page Cache (unmapped) pages
-b. The infrastructure allows easy addition of other types of memory to control
-c. Provides *zero overhead* for non memory controller users
-d. Provides a double LRU: global memory pressure causes reclaim from the
-   global LRU; a cgroup on hitting a limit, reclaims from the per
-   cgroup LRU
-
-NOTE: Swap Cache (unmapped) is not accounted now.
-
-Benefits and Purpose of the memory controller
-
-The memory controller isolates the memory behaviour of a group of tasks
-from the rest of the system. The article on LWN [12] mentions some probable
-uses of the memory controller. The memory controller can be used to
-
-a. Isolate an application or a group of applications
-   Memory hungry applications can be isolated and limited to a smaller
-   amount of memory.
-b. Create a cgroup with limited amount of memory, this can be used
-   as a good alternative to booting with mem=XXXX.
-c. Virtualization solutions can control the amount of memory they want
-   to assign to a virtual machine instance.
-d. A CD/DVD burner could control the amount of memory used by the
-   rest of the system to ensure that burning does not fail due to lack
-   of available memory.
-e. There are several other use cases, find one or use the controller just
-   for fun (to learn and hack on the VM subsystem).
-
-1. History
-
-The memory controller has a long history. A request for comments for the memory
-controller was posted by Balbir Singh [1]. At the time the RFC was posted
-there were several implementations for memory control. The goal of the
-RFC was to build consensus and agreement for the minimal features required
-for memory control. The first RSS controller was posted by Balbir Singh[2]
-in Feb 2007. Pavel Emelianov [3][4][5] has since posted three versions of the
-RSS controller. At OLS, at the resource management BoF, everyone suggested
-that we handle both page cache and RSS together. Another request was raised
-to allow user space handling of OOM. The current memory controller is
-at version 6; it combines both mapped (RSS) and unmapped Page
-Cache Control [11].
-
-2. Memory Control
-
-Memory is a unique resource in the sense that it is present in a limited
-amount. If a task requires a lot of CPU processing, the task can spread
-its processing over a period of hours, days, months or years, but with
-memory, the same physical memory needs to be reused to accomplish the task.
-
-The memory controller implementation has been divided into phases. These
-are:
-
-1. Memory controller
-2. mlock(2) controller
-3. Kernel user memory accounting and slab control
-4. user mappings length controller
-
-The memory controller is the first controller developed.
-
-2.1. Design
-
-The core of the design is a counter called the res_counter. The res_counter
-tracks the current memory usage and limit of the group of processes associated
-with the controller. Each cgroup has a memory controller specific data
-structure (mem_cgroup) associated with it.
-
-2.2. Accounting
-
-		+--------------------+
-		|  mem_cgroup     |
-		|  (res_counter)     |
-		+--------------------+
-		 /            ^      \
-		/             |       \
-           +---------------+  |        +---------------+
-           | mm_struct     |  |....    | mm_struct     |
-           |               |  |        |               |
-           +---------------+  |        +---------------+
-                              |
-                              + --------------+
-                                              |
-           +---------------+           +------+--------+
-           | page          +---------->  page_cgroup|
-           |               |           |               |
-           +---------------+           +---------------+
-
-             (Figure 1: Hierarchy of Accounting)
-
-
-Figure 1 shows the important aspects of the controller
-
-1. Accounting happens per cgroup
-2. Each mm_struct knows about which cgroup it belongs to
-3. Each page has a pointer to the page_cgroup, which in turn knows the
-   cgroup it belongs to
-
-The accounting is done as follows: mem_cgroup_charge() is invoked to setup
-the necessary data structures and check if the cgroup that is being charged
-is over its limit. If it is then reclaim is invoked on the cgroup.
-More details can be found in the reclaim section of this document.
-If everything goes well, a page meta-data-structure called page_cgroup is
-allocated and associated with the page.  This routine also adds the page to
-the per cgroup LRU.
-
-2.2.1 Accounting details
-
-All mapped anon pages (RSS) and cache pages (Page Cache) are accounted.
-(some pages which never be reclaimable and will not be on global LRU
- are not accounted. we just accounts pages under usual vm management.)
-
-RSS pages are accounted at page_fault unless they've already been accounted
-for earlier. A file page will be accounted for as Page Cache when it's
-inserted into inode (radix-tree). While it's mapped into the page tables of
-processes, duplicate accounting is carefully avoided.
-
-A RSS page is unaccounted when it's fully unmapped. A PageCache page is
-unaccounted when it's removed from radix-tree.
-
-At page migration, accounting information is kept.
-
-Note: we just account pages-on-lru because our purpose is to control amount
-of used pages. not-on-lru pages are tend to be out-of-control from vm view.
-
-2.3 Shared Page Accounting
-
-Shared pages are accounted on the basis of the first touch approach. The
-cgroup that first touches a page is accounted for the page. The principle
-behind this approach is that a cgroup that aggressively uses a shared
-page will eventually get charged for it (once it is uncharged from
-the cgroup that brought it in -- this will happen on memory pressure).
-
-2.4 Reclaim
-
-Each cgroup maintains a per cgroup LRU that consists of an active
-and inactive list. When a cgroup goes over its limit, we first try
-to reclaim memory from the cgroup so as to make space for the new
-pages that the cgroup has touched. If the reclaim is unsuccessful,
-an OOM routine is invoked to select and kill the bulkiest task in the
-cgroup.
-
-The reclaim algorithm has not been modified for cgroups, except that
-pages that are selected for reclaiming come from the per cgroup LRU
-list.
-
-2. Locking
-
-The memory controller uses the following hierarchy
-
-1. zone->lru_lock is used for selecting pages to be isolated
-2. mem->per_zone->lru_lock protects the per cgroup LRU (per zone)
-3. lock_page_cgroup() is used to protect page->page_cgroup
-
-3. User Interface
-
-0. Configuration
-
-a. Enable CONFIG_CGROUPS
-b. Enable CONFIG_RESOURCE_COUNTERS
-c. Enable CONFIG_CGROUP_MEM_RES_CTLR
-
-1. Prepare the cgroups
-# mkdir -p /cgroups
-# mount -t cgroup none /cgroups -o memory
-
-2. Make the new group and move bash into it
-# mkdir /cgroups/0
-# echo $$ >  /cgroups/0/tasks
-
-Since now we're in the 0 cgroup,
-We can alter the memory limit:
-# echo 4M > /cgroups/0/memory.limit_in_bytes
-
-NOTE: We can use a suffix (k, K, m, M, g or G) to indicate values in kilo,
-mega or gigabytes.
-
-# cat /cgroups/0/memory.limit_in_bytes
-4194304
-
-NOTE: The interface has now changed to display the usage in bytes
-instead of pages
-
-We can check the usage:
-# cat /cgroups/0/memory.usage_in_bytes
-1216512
-
-A successful write to this file does not guarantee a successful set of
-this limit to the value written into the file.  This can be due to a
-number of factors, such as rounding up to page boundaries or the total
-availability of memory on the system.  The user is required to re-read
-this file after a write to guarantee the value committed by the kernel.
-
-# echo 1 > memory.limit_in_bytes
-# cat memory.limit_in_bytes
-4096
-
-The memory.failcnt field gives the number of times that the cgroup limit was
-exceeded.
-
-The memory.stat file gives accounting information. Now, the number of
-caches, RSS and Active pages/Inactive pages are shown.
-
-The memory.force_empty gives an interface to drop *all* charges by force.
-
-# echo 1 > memory.force_empty
-
-will drop all charges in cgroup. Currently, this is maintained for test.
-
-4. Testing
-
-Balbir posted lmbench, AIM9, LTP and vmmstress results [10] and [11].
-Apart from that v6 has been tested with several applications and regular
-daily use. The controller has also been tested on the PPC64, x86_64 and
-UML platforms.
-
-4.1 Troubleshooting
-
-Sometimes a user might find that the application under a cgroup is
-terminated. There are several causes for this:
-
-1. The cgroup limit is too low (just too low to do anything useful)
-2. The user is using anonymous memory and swap is turned off or too low
-
-A sync followed by echo 1 > /proc/sys/vm/drop_caches will help get rid of
-some of the pages cached in the cgroup (page cache pages).
-
-4.2 Task migration
-
-When a task migrates from one cgroup to another, it's charge is not
-carried forward. The pages allocated from the original cgroup still
-remain charged to it, the charge is dropped when the page is freed or
-reclaimed.
-
-4.3 Removing a cgroup
-
-A cgroup can be removed by rmdir, but as discussed in sections 4.1 and 4.2, a
-cgroup might have some charge associated with it, even though all
-tasks have migrated away from it. Such charges are automatically dropped at
-rmdir() if there are no tasks.
-
-5. TODO
-
-1. Add support for accounting huge pages (as a separate controller)
-2. Make per-cgroup scanner reclaim not-shared pages first
-3. Teach controller to account for shared-pages
-4. Start reclamation in the background when the limit is
-   not yet hit but the usage is getting closer
-
-Summary
-
-Overall, the memory controller has been a stable controller and has been
-commented and discussed quite extensively in the community.
-
-References
-
-1. Singh, Balbir. RFC: Memory Controller, http://lwn.net/Articles/206697/
-2. Singh, Balbir. Memory Controller (RSS Control),
-   http://lwn.net/Articles/222762/
-3. Emelianov, Pavel. Resource controllers based on process cgroups
-   http://lkml.org/lkml/2007/3/6/198
-4. Emelianov, Pavel. RSS controller based on process cgroups (v2)
-   http://lkml.org/lkml/2007/4/9/78
-5. Emelianov, Pavel. RSS controller based on process cgroups (v3)
-   http://lkml.org/lkml/2007/5/30/244
-6. Menage, Paul. Control Groups v10, http://lwn.net/Articles/236032/
-7. Vaidyanathan, Srinivasan, Control Groups: Pagecache accounting and control
-   subsystem (v3), http://lwn.net/Articles/235534/
-8. Singh, Balbir. RSS controller v2 test results (lmbench),
-   http://lkml.org/lkml/2007/5/17/232
-9. Singh, Balbir. RSS controller v2 AIM9 results
-   http://lkml.org/lkml/2007/5/18/1
-10. Singh, Balbir. Memory controller v6 test results,
-    http://lkml.org/lkml/2007/8/19/36
-11. Singh, Balbir. Memory controller introduction (v6),
-    http://lkml.org/lkml/2007/8/17/69
-12. Corbet, Jonathan, Controlling memory use in cgroups,
-    http://lwn.net/Articles/243795/

Documentation/cpu-hotplug.txt

@@ -50,16 +50,17 @@ additional_cpus=n (*)	Use this to limit hotpluggable cpus. This option sets
   			cpu_possible_map = cpu_present_map + additional_cpus
 
 (*) Option valid only for following architectures
-- x86_64, ia64
+- ia64
 
-ia64 and x86_64 use the number of disabled local apics in ACPI tables MADT
-to determine the number of potentially hot-pluggable cpus. The implementation
-should only rely on this to count the # of cpus, but *MUST* not rely on the
-apicid values in those tables for disabled apics. In the event BIOS doesn't
-mark such hot-pluggable cpus as disabled entries, one could use this
-parameter "additional_cpus=x" to represent those cpus in the cpu_possible_map.
+ia64 uses the number of disabled local apics in ACPI tables MADT to
+determine the number of potentially hot-pluggable cpus. The implementation
+should only rely on this to count the # of cpus, but *MUST* not rely
+on the apicid values in those tables for disabled apics. In the event
+BIOS doesn't mark such hot-pluggable cpus as disabled entries, one could
+use this parameter "additional_cpus=x" to represent those cpus in the
+cpu_possible_map.
 
-possible_cpus=n		[s390 only] use this to set hotpluggable cpus.
+possible_cpus=n		[s390,x86_64] use this to set hotpluggable cpus.
 			This option sets possible_cpus bits in
 			cpu_possible_map. Thus keeping the numbers of bits set
 			constant even if the machine gets rebooted.

Documentation/cputopology.txt

@@ -31,3 +31,51 @@ not defined by include/asm-XXX/topology.h:
 2) core_id: 0
 3) thread_siblings: just the given CPU
 4) core_siblings: just the given CPU
+
+Additionally, cpu topology information is provided under
+/sys/devices/system/cpu and includes these files.  The internal
+source for the output is in brackets ("[]").
+
+    kernel_max: the maximum cpu index allowed by the kernel configuration.
+		[NR_CPUS-1]
+
+    offline:	cpus that are not online because they have been
+		HOTPLUGGED off (see cpu-hotplug.txt) or exceed the limit
+		of cpus allowed by the kernel configuration (kernel_max
+		above). [~cpu_online_mask + cpus >= NR_CPUS]
+
+    online:	cpus that are online and being scheduled [cpu_online_mask]
+
+    possible:	cpus that have been allocated resources and can be
+		brought online if they are present. [cpu_possible_mask]
+
+    present:	cpus that have been identified as being present in the
+		system. [cpu_present_mask]
+
+The format for the above output is compatible with cpulist_parse()
+[see <linux/cpumask.h>].  Some examples follow.
+
+In this example, there are 64 cpus in the system but cpus 32-63 exceed
+the kernel max which is limited to 0..31 by the NR_CPUS config option
+being 32.  Note also that cpus 2 and 4-31 are not online but could be
+brought online as they are both present and possible.
+
+     kernel_max: 31
+        offline: 2,4-31,32-63
+         online: 0-1,3
+       possible: 0-31
+        present: 0-31
+
+In this example, the NR_CPUS config option is 128, but the kernel was
+started with possible_cpus=144.  There are 4 cpus in the system and cpu2
+was manually taken offline (and is the only cpu that can be brought
+online.)
+
+     kernel_max: 127
+        offline: 2,4-127,128-143
+         online: 0-1,3
+       possible: 0-127
+        present: 0-3
+
+See cpu-hotplug.txt for the possible_cpus=NUM kernel start parameter
+as well as more information on the various cpumask's.

Documentation/crypto/async-tx-api.txt

@@ -13,9 +13,9 @@
 3.6 Constraints
 3.7 Example
 
-4 DRIVER DEVELOPER NOTES
+4 DMAENGINE DRIVER DEVELOPER NOTES
 4.1 Conformance points
-4.2 "My application needs finer control of hardware channels"
+4.2 "My application needs exclusive control of hardware channels"
 
 5 SOURCE
 
@@ -150,6 +150,7 @@ ops_run_* and ops_complete_* routines in drivers/md/raid5.c for more
 implementation examples.
 
 4 DRIVER DEVELOPMENT NOTES
+
 4.1 Conformance points:
 There are a few conformance points required in dmaengine drivers to
 accommodate assumptions made by applications using the async_tx API:
@@ -158,58 +159,49 @@ accommodate assumptions made by applications using the async_tx API:
 3/ Use async_tx_run_dependencies() in the descriptor clean up path to
    handle submission of dependent operations
 
-4.2 "My application needs finer control of hardware channels"
-This requirement seems to arise from cases where a DMA engine driver is
-trying to support device-to-memory DMA.  The dmaengine and async_tx
-implementations were designed for offloading memory-to-memory
-operations; however, there are some capabilities of the dmaengine layer
-that can be used for platform-specific channel management.
-Platform-specific constraints can be handled by registering the
-application as a 'dma_client' and implementing a 'dma_event_callback' to
-apply a filter to the available channels in the system.  Before showing
-how to implement a custom dma_event callback some background of
-dmaengine's client support is required.
-
-The following routines in dmaengine support multiple clients requesting
-use of a channel:
-- dma_async_client_register(struct dma_client *client)
-- dma_async_client_chan_request(struct dma_client *client)
-
-dma_async_client_register takes a pointer to an initialized dma_client
-structure.  It expects that the 'event_callback' and 'cap_mask' fields
-are already initialized.
-
-dma_async_client_chan_request triggers dmaengine to notify the client of
-all channels that satisfy the capability mask.  It is up to the client's
-event_callback routine to track how many channels the client needs and
-how many it is currently using.  The dma_event_callback routine returns a
-dma_state_client code to let dmaengine know the status of the
-allocation.
-
-Below is the example of how to extend this functionality for
-platform-specific filtering of the available channels beyond the
-standard capability mask:
-
-static enum dma_state_client
-my_dma_client_callback(struct dma_client *client,
-			struct dma_chan *chan, enum dma_state state)
-{
-	struct dma_device *dma_dev;
-	struct my_platform_specific_dma *plat_dma_dev;
-	
-	dma_dev = chan->device;
-	plat_dma_dev = container_of(dma_dev,
-				    struct my_platform_specific_dma,
-				    dma_dev);
-
-	if (!plat_dma_dev->platform_specific_capability)
-		return DMA_DUP;
-
-	. . .
-}
+4.2 "My application needs exclusive control of hardware channels"
+Primarily this requirement arises from cases where a DMA engine driver
+is being used to support device-to-memory operations.  A channel that is
+performing these operations cannot, for many platform specific reasons,
+be shared.  For these cases the dma_request_channel() interface is
+provided.
+
+The interface is:
+struct dma_chan *dma_request_channel(dma_cap_mask_t mask,
+				     dma_filter_fn filter_fn,
+				     void *filter_param);
+
+Where dma_filter_fn is defined as:
+typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param);
+
+When the optional 'filter_fn' parameter is set to NULL
+dma_request_channel simply returns the first channel that satisfies the
+capability mask.  Otherwise, when the mask parameter is insufficient for
+specifying the necessary channel, the filter_fn routine can be used to
+disposition the available channels in the system. The filter_fn routine
+is called once for each free channel in the system.  Upon seeing a
+suitable channel filter_fn returns DMA_ACK which flags that channel to
+be the return value from dma_request_channel.  A channel allocated via
+this interface is exclusive to the caller, until dma_release_channel()
+is called.
+
+The DMA_PRIVATE capability flag is used to tag dma devices that should
+not be used by the general-purpose allocator.  It can be set at
+initialization time if it is known that a channel will always be
+private.  Alternatively, it is set when dma_request_channel() finds an
+unused "public" channel.
+
+A couple caveats to note when implementing a driver and consumer:
+1/ Once a channel has been privately allocated it will no longer be
+   considered by the general-purpose allocator even after a call to
+   dma_release_channel().
+2/ Since capabilities are specified at the device level a dma_device
+   with multiple channels will either have all channels public, or all
+   channels private.
 
 5 SOURCE
-include/linux/dmaengine.h: core header file for DMA drivers and clients
+
+include/linux/dmaengine.h: core header file for DMA drivers and api users
 drivers/dma/dmaengine.c: offload engine channel management routines
 drivers/dma/: location for offload engine drivers
 include/linux/async_tx.h: core header file for the async_tx api

Documentation/dell_rbu.txt

@@ -81,8 +81,8 @@ Until this step is completed the driver cannot be unloaded.
 Also echoing either mono ,packet or init in to image_type will free up the
 memory allocated by the driver.
 
-If an user by accident executes steps 1 and 3 above without executing step 2;
-it will make the /sys/class/firmware/dell_rbu/ entries to disappear.
+If a user by accident executes steps 1 and 3 above without executing step 2;
+it will make the /sys/class/firmware/dell_rbu/ entries disappear.
 The entries can be recreated by doing the following
 echo init > /sys/devices/platform/dell_rbu/image_type
 NOTE: echoing init in image_type does not change it original value.

Documentation/development-process/4.Coding

@@ -375,10 +375,10 @@ say, this can be a large job, so it is best to be sure that the
 justification is solid.
 
 When making an incompatible API change, one should, whenever possible,
-ensure that code which has not been updated is caught by the compiler.  
+ensure that code which has not been updated is caught by the compiler.
 This will help you to be sure that you have found all in-tree uses of that
 interface.  It will also alert developers of out-of-tree code that there is
 a change that they need to respond to.  Supporting out-of-tree code is not
 something that kernel developers need to be worried about, but we also do
-not have to make life harder for out-of-tree developers than it it needs to
-be. 
+not have to make life harder for out-of-tree developers than it needs to
+be.

Documentation/dmaengine.txt

+See Documentation/crypto/async-tx-api.txt

Documentation/feature-removal-schedule.txt

@@ -310,15 +310,6 @@ Who:  Krzysztof Piotr Oledzki <ole@ans.pl>
 
 ---------------------------
 
-What: ide-scsi (BLK_DEV_IDESCSI)
-When: 2.6.29
-Why:  The 2.6 kernel supports direct writing to ide CD drives, which
-      eliminates the need for ide-scsi. The new method is more
-      efficient in every way.
-Who:  FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
-
----------------------------
-
 What:	i2c_attach_client(), i2c_detach_client(), i2c_driver->detach_client()
 When:	2.6.29 (ideally) or 2.6.30 (more likely)
 Why:	Deprecated by the new (standard) device driver binding model. Use
@@ -327,6 +318,14 @@ Who:	Jean Delvare <khali@linux-fr.org>
 
 ---------------------------
 
+What:	fscher and fscpos drivers
+When:	June 2009
+Why:	Deprecated by the new fschmd driver.
+Who:	Hans de Goede <hdegoede@redhat.com>
+	Jean Delvare <khali@linux-fr.org>
+
+---------------------------
+
 What:	SELinux "compat_net" functionality
 When:	2.6.30 at the earliest
 Why:	In 2.6.18 the Secmark concept was introduced to replace the "compat_net"

Documentation/filesystems/Locking

@@ -97,8 +97,8 @@ prototypes:
 	void (*put_super) (struct super_block *);
 	void (*write_super) (struct super_block *);
 	int (*sync_fs)(struct super_block *sb, int wait);
-	void (*write_super_lockfs) (struct super_block *);
-	void (*unlockfs) (struct super_block *);
+	int (*freeze_fs) (struct super_block *);
+	int (*unfreeze_fs) (struct super_block *);
 	int (*statfs) (struct dentry *, struct kstatfs *);
 	int (*remount_fs) (struct super_block *, int *, char *);
 	void (*clear_inode) (struct inode *);
@@ -119,8 +119,8 @@ delete_inode:		no
 put_super:		yes	yes	no
 write_super:		no	yes	read
 sync_fs:		no	no	read
-write_super_lockfs:	?
-unlockfs:		?
+freeze_fs:		?
+unfreeze_fs:		?
 statfs:			no	no	no
 remount_fs:		yes	yes	maybe		(see below)
 clear_inode:		no
@@ -394,11 +394,10 @@ prototypes:
 	unsigned long (*get_unmapped_area)(struct file *, unsigned long,
 			unsigned long, unsigned long, unsigned long);
 	int (*check_flags)(int);
-	int (*dir_notify)(struct file *, unsigned long);
 };
 
 locking rules:
-	All except ->poll() may block.
+	All may block.
 			BKL
 llseek:			no	(see below)
 read:			no
@@ -424,7 +423,6 @@ sendfile:		no
 sendpage:		no
 get_unmapped_area:	no
 check_flags:		no
-dir_notify:		no
 
 ->llseek() locking has moved from llseek to the individual llseek
 implementations.  If your fs is not using generic_file_llseek, you

Documentation/filesystems/btrfs.txt

+
+	BTRFS
+	=====
+
+Btrfs is a new copy on write filesystem for Linux aimed at
+implementing advanced features while focusing on fault tolerance,
+repair and easy administration. Initially developed by Oracle, Btrfs
+is licensed under the GPL and open for contribution from anyone.
+
+Linux has a wealth of filesystems to choose from, but we are facing a
+number of challenges with scaling to the large storage subsystems that
+are becoming common in today's data centers. Filesystems need to scale
+in their ability to address and manage large storage, and also in
+their ability to detect, repair and tolerate errors in the data stored
+on disk.  Btrfs is under heavy development, and is not suitable for
+any uses other than benchmarking and review. The Btrfs disk format is
+not yet finalized.
+
+The main Btrfs features include:
+
+    * Extent based file storage (2^64 max file size)
+    * Space efficient packing of small files
+    * Space efficient indexed directories
+    * Dynamic inode allocation
+    * Writable snapshots
+    * Subvolumes (separate internal filesystem roots)
+    * Object level mirroring and striping
+    * Checksums on data and metadata (multiple algorithms available)
+    * Compression
+    * Integrated multiple device support, with several raid algorithms
+    * Online filesystem check (not yet implemented)
+    * Very fast offline filesystem check
+    * Efficient incremental backup and FS mirroring (not yet implemented)
+    * Online filesystem defragmentation
+
+
+
+	MAILING LIST
+	============
+
+There is a Btrfs mailing list hosted on vger.kernel.org. You can
+find details on how to subscribe here:
+
+http://vger.kernel.org/vger-lists.html#linux-btrfs
+
+Mailing list archives are available from gmane:
+
+http://dir.gmane.org/gmane.comp.file-systems.btrfs
+
+
+
+	IRC
+	===
+
+Discussion of Btrfs also occurs on the #btrfs channel of the Freenode
+IRC network.
+
+
+
+	UTILITIES
+	=========
+
+Userspace tools for creating and manipulating Btrfs file systems are
+available from the git repository at the following location:
+
+ http://git.kernel.org/?p=linux/kernel/git/mason/btrfs-progs-unstable.git
+ git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-progs-unstable.git
+
+These include the following tools:
+
+mkfs.btrfs: create a filesystem
+
+btrfsctl: control program to create snapshots and subvolumes:
+
+	mount /dev/sda2 /mnt
+	btrfsctl -s new_subvol_name /mnt
+	btrfsctl -s snapshot_of_default /mnt/default
+	btrfsctl -s snapshot_of_new_subvol /mnt/new_subvol_name
+	btrfsctl -s snapshot_of_a_snapshot /mnt/snapshot_of_new_subvol
+	ls /mnt
+	default snapshot_of_a_snapshot snapshot_of_new_subvol
+	new_subvol_name snapshot_of_default
+
+	Snapshots and subvolumes cannot be deleted right now, but you can
+	rm -rf all the files and directories inside them.
+
+btrfsck: do a limited check of the FS extent trees.
+
+btrfs-debug-tree: print all of the FS metadata in text form.  Example:
+
+	btrfs-debug-tree /dev/sda2 >& big_output_file

Documentation/filesystems/devpts.txt

+
+To support containers, we now allow multiple instances of devpts filesystem,
+such that indices of ptys allocated in one instance are independent of indices
+allocated in other instances of devpts.
+
+To preserve backward compatibility, this support for multiple instances is
+enabled only if:
+
+	- CONFIG_DEVPTS_MULTIPLE_INSTANCES=y, and
+	- '-o newinstance' mount option is specified while mounting devpts
+
+IOW, devpts now supports both single-instance and multi-instance semantics.
+
+If CONFIG_DEVPTS_MULTIPLE_INSTANCES=n, there is no change in behavior and
+this referred to as the "legacy" mode. In this mode, the new mount options
+(-o newinstance and -o ptmxmode) will be ignored with a 'bogus option' message
+on console.
+
+If CONFIG_DEVPTS_MULTIPLE_INSTANCES=y and devpts is mounted without the
+'newinstance' option (as in current start-up scripts) the new mount binds
+to the initial kernel mount of devpts. This mode is referred to as the
+'single-instance' mode and the current, single-instance semantics are
+preserved, i.e PTYs are common across the system.
+
+The only difference between this single-instance mode and the legacy mode
+is the presence of new, '/dev/pts/ptmx' node with permissions 0000, which
+can safely be ignored.
+
+If CONFIG_DEVPTS_MULTIPLE_INSTANCES=y and 'newinstance' option is specified,
+the mount is considered to be in the multi-instance mode and a new instance
+of the devpts fs is created. Any ptys created in this instance are independent
+of ptys in other instances of devpts. Like in the single-instance mode, the
+/dev/pts/ptmx node is present. To effectively use the multi-instance mode,
+open of /dev/ptmx must be a redirected to '/dev/pts/ptmx' using a symlink or
+bind-mount.
+
+Eg: A container startup script could do the following:
+
+	$ chmod 0666 /dev/pts/ptmx
+	$ rm /dev/ptmx
+	$ ln -s pts/ptmx /dev/ptmx
+	$ ns_exec -cm /bin/bash
+
+	# We are now in new container
+
+	$ umount /dev/pts
+	$ mount -t devpts -o newinstance lxcpts /dev/pts
+	$ sshd -p 1234
+
+where 'ns_exec -cm /bin/bash' calls clone() with CLONE_NEWNS flag and execs
+/bin/bash in the child process.  A pty created by the sshd is not visible in
+the original mount of /dev/pts.
+
+User-space changes
+------------------
+
+In multi-instance mode (i.e '-o newinstance' mount option is specified at least
+once), following user-space issues should be noted.
+
+1. If -o newinstance mount option is never used, /dev/pts/ptmx can be ignored
+   and no change is needed to system-startup scripts.
+
+2. To effectively use multi-instance mode (i.e -o newinstance is specified)
+   administrators or startup scripts should "redirect" open of /dev/ptmx to
+   /dev/pts/ptmx using either a bind mount or symlink.
+
+	$ mount -t devpts -o newinstance devpts /dev/pts
+
+   followed by either
+
+	$ rm /dev/ptmx
+	$ ln -s pts/ptmx /dev/ptmx
+	$ chmod 666 /dev/pts/ptmx
+   or
+	$ mount -o bind /dev/pts/ptmx /dev/ptmx
+
+3. The '/dev/ptmx -> pts/ptmx' symlink is the preferred method since it
+   enables better error-reporting and treats both single-instance and
+   multi-instance mounts similarly.
+
+   But this method requires that system-startup scripts set the mode of
+   /dev/pts/ptmx correctly (default mode is 0000). The scripts can set the
+   mode by, either
+
+   	- adding ptmxmode mount option to devpts entry in /etc/fstab, or
+	- using 'chmod 0666 /dev/pts/ptmx'
+
+4. If multi-instance mode mount is needed for containers, but the system
+   startup scripts have not yet been updated, container-startup scripts
+   should bind mount /dev/ptmx to /dev/pts/ptmx to avoid breaking single-
+   instance mounts.
+
+   Or, in general, container-startup scripts should use:
+
+	mount -t devpts -o newinstance -o ptmxmode=0666 devpts /dev/pts
+	if [ ! -L /dev/ptmx ]; then
+		mount -o bind /dev/pts/ptmx /dev/ptmx
+	fi
+
+   When all devpts mounts are multi-instance, /dev/ptmx can permanently be
+   a symlink to pts/ptmx and the bind mount can be ignored.
+
+5. A multi-instance mount that is not accompanied by the /dev/ptmx to
+   /dev/pts/ptmx redirection would result in an unusable/unreachable pty.
+
+	mount -t devpts -o newinstance lxcpts /dev/pts
+
+   immediately followed by:
+
+	open("/dev/ptmx")
+
+    would create a pty, say /dev/pts/7, in the initial kernel mount.
+    But /dev/pts/7 would be invisible in the new mount.
+
+6. The permissions for /dev/pts/ptmx node should be specified when mounting
+   /dev/pts, using the '-o ptmxmode=%o' mount option (default is 0000).
+
+	mount -t devpts -o newinstance -o ptmxmode=0644 devpts /dev/pts
+
+   The permissions can be later be changed as usual with 'chmod'.
+
+	chmod 666 /dev/pts/ptmx
+
+7. A mount of devpts without the 'newinstance' option results in binding to
+   initial kernel mount.  This behavior while preserving legacy semantics,
+   does not provide strict isolation in a container environment. i.e by
+   mounting devpts without the 'newinstance' option, a container could
+   get visibility into the 'host' or root container's devpts.
+   
+   To workaround this and have strict isolation, all mounts of devpts,
+   including the mount in the root container, should use the newinstance
+   option.

Documentation/filesystems/ext4.txt

@@ -58,13 +58,22 @@ Note: More extensive information for getting started with ext4 can be
 
 	# mount -t ext4 /dev/hda1 /wherever
 
-  - When comparing performance with other filesystems, remember that
-    ext3/4 by default offers higher data integrity guarantees than most.
-    So when comparing with a metadata-only journalling filesystem, such
-    as ext3, use `mount -o data=writeback'.  And you might as well use
-    `mount -o nobh' too along with it.  Making the journal larger than
-    the mke2fs default often helps performance with metadata-intensive
-    workloads.
+  - When comparing performance with other filesystems, it's always
+    important to try multiple workloads; very often a subtle change in a
+    workload parameter can completely change the ranking of which
+    filesystems do well compared to others.  When comparing versus ext3,
+    note that ext4 enables write barriers by default, while ext3 does
+    not enable write barriers by default.  So it is useful to use
+    explicitly specify whether barriers are enabled or not when via the
+    '-o barriers=[0|1]' mount option for both ext3 and ext4 filesystems
+    for a fair comparison.  When tuning ext3 for best benchmark numbers,
+    it is often worthwhile to try changing the data journaling mode; '-o
+    data=writeback,nobh' can be faster for some workloads.  (Note
+    however that running mounted with data=writeback can potentially
+    leave stale data exposed in recently written files in case of an
+    unclean shutdown, which could be a security exposure in some
+    situations.)  Configuring the filesystem with a large journal can
+    also be helpful for metadata-intensive workloads.
 
 2. Features
 ===========
@@ -74,7 +83,7 @@ Note: More extensive information for getting started with ext4 can be
 * ability to use filesystems > 16TB (e2fsprogs support not available yet)
 * extent format reduces metadata overhead (RAM, IO for access, transactions)
 * extent format more robust in face of on-disk corruption due to magics,
-* internal redunancy in tree
+* internal redundancy in tree
 * improved file allocation (multi-block alloc)
 * fix 32000 subdirectory limit
 * nsec timestamps for mtime, atime, ctime, create time
@@ -116,10 +125,11 @@ grouping of bitmaps and inode tables.  Some test results available here:
 When mounting an ext4 filesystem, the following option are accepted:
 (*) == default
 
-extents		(*)	ext4 will use extents to address file data.  The
-			file system will no longer be mountable by ext3.
-
-noextents		ext4 will not use extents for newly created files
+ro                   	Mount filesystem read only. Note that ext4 will
+                     	replay the journal (and thus write to the
+                     	partition) even when mounted "read only". The
+                     	mount options "ro,noload" can be used to prevent
+		     	writes to the filesystem.
 
 journal_checksum	Enable checksumming of the journal transactions.
 			This will allow the recovery code in e2fsck and the
@@ -134,17 +144,17 @@ journal_async_commit	Commit block can be written to disk without waiting
 journal=update		Update the ext4 file system's journal to the current
 			format.
 
-journal=inum		When a journal already exists, this option is ignored.
-			Otherwise, it specifies the number of the inode which
-			will represent the ext4 file system's journal file.
-
 journal_dev=devnum	When the external journal device's major/minor numbers
 			have changed, this option allows the user to specify
 			the new journal location.  The journal device is
 			identified through its new major/minor numbers encoded
 			in devnum.
 
-noload			Don't load the journal on mounting.
+noload			Don't load the journal on mounting.  Note that
+                     	if the filesystem was not unmounted cleanly,
+                     	skipping the journal replay will lead to the
+                     	filesystem containing inconsistencies that can
+                     	lead to any number of problems.
 
 data=journal		All data are committed into the journal prior to being
 			written into the main file system.
@@ -219,9 +229,12 @@ minixdf			Make 'df' act like Minix.
 
 debug			Extra debugging information is sent to syslog.
 
-errors=remount-ro(*)	Remount the filesystem read-only on an error.
+errors=remount-ro	Remount the filesystem read-only on an error.
 errors=continue		Keep going on a filesystem error.
 errors=panic		Panic and halt the machine if an error occurs.
+                        (These mount options override the errors behavior
+                        specified in the superblock, which can be configured
+                        using tune2fs)
 
 data_err=ignore(*)	Just print an error message if an error occurs
 			in a file data buffer in ordered mode.
@@ -261,6 +274,42 @@ delalloc	(*)	Deferring block allocation until write-out time.
 nodelalloc		Disable delayed allocation. Blocks are allocation
 			when data is copied from user to page cache.
 
+max_batch_time=usec	Maximum amount of time ext4 should wait for
+			additional filesystem operations to be batch
+			together with a synchronous write operation.
+			Since a synchronous write operation is going to
+			force a commit and then a wait for the I/O
+			complete, it doesn't cost much, and can be a
+			huge throughput win, we wait for a small amount
+			of time to see if any other transactions can
+			piggyback on the synchronous write.   The
+			algorithm used is designed to automatically tune
+			for the speed of the disk, by measuring the
+			amount of time (on average) that it takes to
+			finish committing a transaction.  Call this time
+			the "commit time".  If the time that the
+			transactoin has been running is less than the
+			commit time, ext4 will try sleeping for the
+			commit time to see if other operations will join
+			the transaction.   The commit time is capped by
+			the max_batch_time, which defaults to 15000us
+			(15ms).   This optimization can be turned off
+			entirely by setting max_batch_time to 0.
+
+min_batch_time=usec	This parameter sets the commit time (as
+			described above) to be at least min_batch_time.
+			It defaults to zero microseconds.  Increasing
+			this parameter may improve the throughput of
+			multi-threaded, synchronous workloads on very
+			fast disks, at the cost of increasing latency.
+
+journal_ioprio=prio	The I/O priority (from 0 to 7, where 0 is the
+			highest priorty) which should be used for I/O
+			operations submitted by kjournald2 during a
+			commit operation.  This defaults to 3, which is
+			a slightly higher priority than the default I/O
+			priority.
+
 Data Mode
 =========
 There are 3 different data modes:

Documentation/filesystems/files.txt

@@ -76,13 +76,13 @@ the fdtable structure -
 5. Handling of the file structures is special. Since the look-up
    of the fd (fget()/fget_light()) are lock-free, it is possible
    that look-up may race with the last put() operation on the
-   file structure. This is avoided using atomic_inc_not_zero()
+   file structure. This is avoided using atomic_long_inc_not_zero()
    on ->f_count :
 
 	rcu_read_lock();
 	file = fcheck_files(files, fd);
 	if (file) {
-		if (atomic_inc_not_zero(&file->f_count))
+		if (atomic_long_inc_not_zero(&file->f_count))
 			*fput_needed = 1;
 		else
 		/* Didn't get the reference, someone's freed */
@@ -92,7 +92,7 @@ the fdtable structure -
 	....
 	return file;
 
-   atomic_inc_not_zero() detects if refcounts is already zero or
+   atomic_long_inc_not_zero() detects if refcounts is already zero or
    goes to zero during increment. If it does, we fail
    fget()/fget_light().
 

Documentation/filesystems/nfs-rdma.txt

@@ -251,7 +251,7 @@ NFS/RDMA Setup
 
     Instruct the server to listen on the RDMA transport:
 
-    $ echo rdma 2050 > /proc/fs/nfsd/portlist
+    $ echo rdma 20049 > /proc/fs/nfsd/portlist
 
   - On the client system
 
@@ -263,7 +263,7 @@ NFS/RDMA Setup
     Regardless of how the client was built (module or built-in), use this
     command to mount the NFS/RDMA server:
 
-    $ mount -o rdma,port=2050 <IPoIB-server-name-or-address>:/<export> /mnt
+    $ mount -o rdma,port=20049 <IPoIB-server-name-or-address>:/<export> /mnt
 
     To verify that the mount is using RDMA, run "cat /proc/mounts" and check
     the "proto" field for the given mount.

Documentation/filesystems/ocfs2.txt

@@ -31,7 +31,6 @@ Features which OCFS2 does not support yet:
 	- quotas
 	- Directory change notification (F_NOTIFY)
 	- Distributed Caching (F_SETLEASE/F_GETLEASE/break_lease)
-	- POSIX ACLs
 
 Mount options
 =============
@@ -79,3 +78,5 @@ inode64			Indicates that Ocfs2 is allowed to create inodes at
 			bits of significance.
 user_xattr	(*)	Enables Extended User Attributes.
 nouser_xattr		Disables Extended User Attributes.
+acl			Enables POSIX Access Control Lists support.
+noacl		(*)	Disables POSIX Access Control Lists support.

Documentation/filesystems/proc.txt

@@ -140,6 +140,7 @@ Table 1-1: Process specific entries in /proc
  statm		Process memory status information
  status		Process status in human readable form
  wchan		If CONFIG_KALLSYMS is set, a pre-decoded wchan
+ stack		Report full stack trace, enable via CONFIG_STACKTRACE
  smaps		Extension based on maps, the rss size for each mapped file
 ..............................................................................
 
@@ -1370,268 +1371,8 @@ auto_msgmni default value is 1.
 2.4 /proc/sys/vm - The virtual memory subsystem
 -----------------------------------------------
 
-The files  in  this directory can be used to tune the operation of the virtual
-memory (VM)  subsystem  of  the  Linux  kernel.
-
-vfs_cache_pressure
-------------------
-
-Controls the tendency of the kernel to reclaim the memory which is used for
-caching of directory and inode objects.
-
-At the default value of vfs_cache_pressure=100 the kernel will attempt to
-reclaim dentries and inodes at a "fair" rate with respect to pagecache and
-swapcache reclaim.  Decreasing vfs_cache_pressure causes the kernel to prefer
-to retain dentry and inode caches.  Increasing vfs_cache_pressure beyond 100
-causes the kernel to prefer to reclaim dentries and inodes.
-
-dirty_background_ratio
-----------------------
-
-Contains, as a percentage of the dirtyable system memory (free pages + mapped
-pages + file cache, not including locked pages and HugePages), the number of
-pages at which the pdflush background writeback daemon will start writing out
-dirty data.
-
-dirty_ratio
------------------
-
-Contains, as a percentage of the dirtyable system memory (free pages + mapped
-pages + file cache, not including locked pages and HugePages), the number of
-pages at which a process which is generating disk writes will itself start
-writing out dirty data.
-
-dirty_writeback_centisecs
--------------------------
-
-The pdflush writeback daemons will periodically wake up and write `old' data
-out to disk.  This tunable expresses the interval between those wakeups, in
-100'ths of a second.
-
-Setting this to zero disables periodic writeback altogether.
-
-dirty_expire_centisecs
-----------------------
-
-This tunable is used to define when dirty data is old enough to be eligible
-for writeout by the pdflush daemons.  It is expressed in 100'ths of a second. 
-Data which has been dirty in-memory for longer than this interval will be
-written out next time a pdflush daemon wakes up.
-
-highmem_is_dirtyable
---------------------
-
-Only present if CONFIG_HIGHMEM is set.
-
-This defaults to 0 (false), meaning that the ratios set above are calculated
-as a percentage of lowmem only.  This protects against excessive scanning
-in page reclaim, swapping and general VM distress.
-
-Setting this to 1 can be useful on 32 bit machines where you want to make
-random changes within an MMAPed file that is larger than your available
-lowmem without causing large quantities of random IO.  Is is safe if the
-behavior of all programs running on the machine is known and memory will
-not be otherwise stressed.
-
-legacy_va_layout
-----------------
-
-If non-zero, this sysctl disables the new 32-bit mmap mmap layout - the kernel
-will use the legacy (2.4) layout for all processes.
-
-lowmem_reserve_ratio
----------------------
-
-For some specialised workloads on highmem machines it is dangerous for
-the kernel to allow process memory to be allocated from the "lowmem"
-zone.  This is because that memory could then be pinned via the mlock()
-system call, or by unavailability of swapspace.
-
-And on large highmem machines this lack of reclaimable lowmem memory
-can be fatal.
-
-So the Linux page allocator has a mechanism which prevents allocations
-which _could_ use highmem from using too much lowmem.  This means that
-a certain amount of lowmem is defended from the possibility of being
-captured into pinned user memory.
-
-(The same argument applies to the old 16 megabyte ISA DMA region.  This
-mechanism will also defend that region from allocations which could use
-highmem or lowmem).
-
-The `lowmem_reserve_ratio' tunable determines how aggressive the kernel is
-in defending these lower zones.
-
-If you have a machine which uses highmem or ISA DMA and your
-applications are using mlock(), or if you are running with no swap then
-you probably should change the lowmem_reserve_ratio setting.
-
-The lowmem_reserve_ratio is an array. You can see them by reading this file.
--
-% cat /proc/sys/vm/lowmem_reserve_ratio
-256     256     32
--
-Note: # of this elements is one fewer than number of zones. Because the highest
-      zone's value is not necessary for following calculation.
-
-But, these values are not used directly. The kernel calculates # of protection
-pages for each zones from them. These are shown as array of protection pages
-in /proc/zoneinfo like followings. (This is an example of x86-64 box).
-Each zone has an array of protection pages like this.
-
--
-Node 0, zone      DMA
-  pages free     1355
-        min      3
-        low      3
-        high     4
-	:
-	:
-    numa_other   0
-        protection: (0, 2004, 2004, 2004)
-	^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-  pagesets
-    cpu: 0 pcp: 0
-        :
--
-These protections are added to score to judge whether this zone should be used
-for page allocation or should be reclaimed.
-
-In this example, if normal pages (index=2) are required to this DMA zone and
-pages_high is used for watermark, the kernel judges this zone should not be
-used because pages_free(1355) is smaller than watermark + protection[2]
-(4 + 2004 = 2008). If this protection value is 0, this zone would be used for
-normal page requirement. If requirement is DMA zone(index=0), protection[0]
-(=0) is used.
-
-zone[i]'s protection[j] is calculated by following expression.
-
-(i < j):
-  zone[i]->protection[j]
-  = (total sums of present_pages from zone[i+1] to zone[j] on the node)
-    / lowmem_reserve_ratio[i];
-(i = j):
-   (should not be protected. = 0;
-(i > j):
-   (not necessary, but looks 0)
-
-The default values of lowmem_reserve_ratio[i] are
-    256 (if zone[i] means DMA or DMA32 zone)
-    32  (others).
-As above expression, they are reciprocal number of ratio.
-256 means 1/256. # of protection pages becomes about "0.39%" of total present
-pages of higher zones on the node.
-
-If you would like to protect more pages, smaller values are effective.
-The minimum value is 1 (1/1 -> 100%).
-
-page-cluster
-------------
-
-page-cluster controls the number of pages which are written to swap in
-a single attempt.  The swap I/O size.
-
-It is a logarithmic value - setting it to zero means "1 page", setting
-it to 1 means "2 pages", setting it to 2 means "4 pages", etc.
-
-The default value is three (eight pages at a time).  There may be some
-small benefits in tuning this to a different value if your workload is
-swap-intensive.
-
-overcommit_memory
------------------
-
-Controls overcommit of system memory, possibly allowing processes
-to allocate (but not use) more memory than is actually available.
-
-
-0	-	Heuristic overcommit handling. Obvious overcommits of
-		address space are refused. Used for a typical system. It
-		ensures a seriously wild allocation fails while allowing
-		overcommit to reduce swap usage.  root is allowed to
-		allocate slightly more memory in this mode. This is the
-		default.
-
-1	-	Always overcommit. Appropriate for some scientific
-		applications.
-
-2	-	Don't overcommit. The total address space commit
-		for the system is not permitted to exceed swap plus a
-		configurable percentage (default is 50) of physical RAM.
-		Depending on the percentage you use, in most situations
-		this means a process will not be killed while attempting
-		to use already-allocated memory but will receive errors
-		on memory allocation as	appropriate.
-
-overcommit_ratio
-----------------
-
-Percentage of physical memory size to include in overcommit calculations
-(see above.)
-
-Memory allocation limit = swapspace + physmem * (overcommit_ratio / 100)
-
-	swapspace = total size of all swap areas
-	physmem = size of physical memory in system
-
-nr_hugepages and hugetlb_shm_group
-----------------------------------
-
-nr_hugepages configures number of hugetlb page reserved for the system.
-
-hugetlb_shm_group contains group id that is allowed to create SysV shared
-memory segment using hugetlb page.
-
-hugepages_treat_as_movable
---------------------------
-
-This parameter is only useful when kernelcore= is specified at boot time to
-create ZONE_MOVABLE for pages that may be reclaimed or migrated. Huge pages
-are not movable so are not normally allocated from ZONE_MOVABLE. A non-zero
-value written to hugepages_treat_as_movable allows huge pages to be allocated
-from ZONE_MOVABLE.
-
-Once enabled, the ZONE_MOVABLE is treated as an area of memory the huge
-pages pool can easily grow or shrink within. Assuming that applications are
-not running that mlock() a lot of memory, it is likely the huge pages pool
-can grow to the size of ZONE_MOVABLE by repeatedly entering the desired value
-into nr_hugepages and triggering page reclaim.
-
-laptop_mode
------------
-
-laptop_mode is a knob that controls "laptop mode". All the things that are
-controlled by this knob are discussed in Documentation/laptops/laptop-mode.txt.
-
-block_dump
-----------
-
-block_dump enables block I/O debugging when set to a nonzero value. More
-information on block I/O debugging is in Documentation/laptops/laptop-mode.txt.
-
-swap_token_timeout
-------------------
-
-This file contains valid hold time of swap out protection token. The Linux
-VM has token based thrashing control mechanism and uses the token to prevent
-unnecessary page faults in thrashing situation. The unit of the value is
-second. The value would be useful to tune thrashing behavior.
-
-drop_caches
------------
-
-Writing to this will cause the kernel to drop clean caches, dentries and
-inodes from memory, causing that memory to become free.
-
-To free pagecache:
-	echo 1 > /proc/sys/vm/drop_caches
-To free dentries and inodes:
-	echo 2 > /proc/sys/vm/drop_caches
-To free pagecache, dentries and inodes:
-	echo 3 > /proc/sys/vm/drop_caches
-
-As this is a non-destructive operation and dirty objects are not freeable, the
-user should run `sync' first.
+Please see: Documentation/sysctls/vm.txt for a description of these
+entries.
 
 
 2.5 /proc/sys/dev - Device specific parameters
@@ -2286,6 +2027,34 @@ increase the likelihood of this process being killed by the oom-killer.  Valid
 values are in the range -16 to +15, plus the special value -17, which disables
 oom-killing altogether for this process.
 
+The process to be killed in an out-of-memory situation is selected among all others
+based on its badness score. This value equals the original memory size of the process
+and is then updated according to its CPU time (utime + stime) and the
+run time (uptime - start time). The longer it runs the smaller is the score.
+Badness score is divided by the square root of the CPU time and then by
+the double square root of the run time.
+
+Swapped out tasks are killed first. Half of each child's memory size is added to
+the parent's score if they do not share the same memory. Thus forking servers
+are the prime candidates to be killed. Having only one 'hungry' child will make
+parent less preferable than the child.
+
+/proc/<pid>/oom_score shows process' current badness score.
+
+The following heuristics are then applied:
+ * if the task was reniced, its score doubles
+ * superuser or direct hardware access tasks (CAP_SYS_ADMIN, CAP_SYS_RESOURCE
+ 	or CAP_SYS_RAWIO) have their score divided by 4
+ * if oom condition happened in one cpuset and checked task does not belong
+ 	to it, its score is divided by 8
+ * the resulting score is multiplied by two to the power of oom_adj, i.e.
+	points <<= oom_adj when it is positive and
+	points >>= -(oom_adj) otherwise
+
+The task with the highest badness score is then selected and its children
+are killed, process itself will be killed in an OOM situation when it does
+not have children or some of them disabled oom like described above.
+
 2.13 /proc/<pid>/oom_score - Display current oom-killer score
 -------------------------------------------------------------
 

Documentation/filesystems/squashfs.txt

+SQUASHFS 4.0 FILESYSTEM
+=======================
+
+Squashfs is a compressed read-only filesystem for Linux.
+It uses zlib compression to compress files, inodes and directories.
+Inodes in the system are very small and all blocks are packed to minimise
+data overhead. Block sizes greater than 4K are supported up to a maximum
+of 1Mbytes (default block size 128K).
+
+Squashfs is intended for general read-only filesystem use, for archival
+use (i.e. in cases where a .tar.gz file may be used), and in constrained
+block device/memory systems (e.g. embedded systems) where low overhead is
+needed.
+
+Mailing list: squashfs-devel@lists.sourceforge.net
+Web site: www.squashfs.org
+
+1. FILESYSTEM FEATURES
+----------------------
+
+Squashfs filesystem features versus Cramfs:
+
+				Squashfs		Cramfs
+
+Max filesystem size:		2^64			16 MiB
+Max file size:			~ 2 TiB			16 MiB
+Max files:			unlimited		unlimited
+Max directories:		unlimited		unlimited
+Max entries per directory:	unlimited		unlimited
+Max block size:			1 MiB			4 KiB
+Metadata compression:		yes			no
+Directory indexes:		yes			no
+Sparse file support:		yes			no
+Tail-end packing (fragments):	yes			no
+Exportable (NFS etc.):		yes			no
+Hard link support:		yes			no
+"." and ".." in readdir:	yes			no
+Real inode numbers:		yes			no
+32-bit uids/gids:		yes			no
+File creation time:		yes			no
+Xattr and ACL support:		no			no
+
+Squashfs compresses data, inodes and directories.  In addition, inode and
+directory data are highly compacted, and packed on byte boundaries.  Each
+compressed inode is on average 8 bytes in length (the exact length varies on
+file type, i.e. regular file, directory, symbolic link, and block/char device
+inodes have different sizes).
+
+2. USING SQUASHFS
+-----------------
+
+As squashfs is a read-only filesystem, the mksquashfs program must be used to
+create populated squashfs filesystems.  This and other squashfs utilities
+can be obtained from http://www.squashfs.org.  Usage instructions can be
+obtained from this site also.
+
+
+3. SQUASHFS FILESYSTEM DESIGN
+-----------------------------
+
+A squashfs filesystem consists of seven parts, packed together on a byte
+alignment:
+
+	 ---------------
+	|  superblock 	|
+	|---------------|
+	|  datablocks   |
+	|  & fragments  |
+	|---------------|
+	|  inode table	|
+	|---------------|
+	|   directory	|
+	|     table     |
+	|---------------|
+	|   fragment	|
+	|    table      |
+	|---------------|
+	|    export     |
+	|    table      |
+	|---------------|
+	|    uid/gid	|
+	|  lookup table	|
+	 ---------------
+
+Compressed data blocks are written to the filesystem as files are read from
+the source directory, and checked for duplicates.  Once all file data has been
+written the completed inode, directory, fragment, export and uid/gid lookup
+tables are written.
+
+3.1 Inodes
+----------
+
+Metadata (inodes and directories) are compressed in 8Kbyte blocks.  Each
+compressed block is prefixed by a two byte length, the top bit is set if the
+block is uncompressed.  A block will be uncompressed if the -noI option is set,
+or if the compressed block was larger than the uncompressed block.
+
+Inodes are packed into the metadata blocks, and are not aligned to block
+boundaries, therefore inodes overlap compressed blocks.  Inodes are identified
+by a 48-bit number which encodes the location of the compressed metadata block
+containing the inode, and the byte offset into that block where the inode is
+placed (<block, offset>).
+
+To maximise compression there are different inodes for each file type
+(regular file, directory, device, etc.), the inode contents and length
+varying with the type.
+
+To further maximise compression, two types of regular file inode and
+directory inode are defined: inodes optimised for frequently occurring
+regular files and directories, and extended types where extra
+information has to be stored.
+
+3.2 Directories
+---------------
+
+Like inodes, directories are packed into compressed metadata blocks, stored
+in a directory table.  Directories are accessed using the start address of
+the metablock containing the directory and the offset into the
+decompressed block (<block, offset>).
+
+Directories are organised in a slightly complex way, and are not simply
+a list of file names.  The organisation takes advantage of the
+fact that (in most cases) the inodes of the files will be in the same
+compressed metadata block, and therefore, can share the start block.
+Directories are therefore organised in a two level list, a directory
+header containing the shared start block value, and a sequence of directory
+entries, each of which share the shared start block.  A new directory header
+is written once/if the inode start block changes.  The directory
+header/directory entry list is repeated as many times as necessary.
+
+Directories are sorted, and can contain a directory index to speed up
+file lookup.  Directory indexes store one entry per metablock, each entry
+storing the index/filename mapping to the first directory header
+in each metadata block.  Directories are sorted in alphabetical order,
+and at lookup the index is scanned linearly looking for the first filename
+alphabetically larger than the filename being looked up.  At this point the
+location of the metadata block the filename is in has been found.
+The general idea of the index is ensure only one metadata block needs to be
+decompressed to do a lookup irrespective of the length of the directory.
+This scheme has the advantage that it doesn't require extra memory overhead
+and doesn't require much extra storage on disk.
+
+3.3 File data
+-------------
+
+Regular files consist of a sequence of contiguous compressed blocks, and/or a
+compressed fragment block (tail-end packed block).   The compressed size
+of each datablock is stored in a block list contained within the
+file inode.
+
+To speed up access to datablocks when reading 'large' files (256 Mbytes or
+larger), the code implements an index cache that caches the mapping from
+block index to datablock location on disk.
+
+The index cache allows Squashfs to handle large files (up to 1.75 TiB) while
+retaining a simple and space-efficient block list on disk.  The cache
+is split into slots, caching up to eight 224 GiB files (128 KiB blocks).
+Larger files use multiple slots, with 1.75 TiB files using all 8 slots.
+The index cache is designed to be memory efficient, and by default uses
+16 KiB.
+
+3.4 Fragment lookup table
+-------------------------
+
+Regular files can contain a fragment index which is mapped to a fragment
+location on disk and compressed size using a fragment lookup table.  This
+fragment lookup table is itself stored compressed into metadata blocks.
+A second index table is used to locate these.  This second index table for
+speed of access (and because it is small) is read at mount time and cached
+in memory.
+
+3.5 Uid/gid lookup table
+------------------------
+
+For space efficiency regular files store uid and gid indexes, which are
+converted to 32-bit uids/gids using an id look up table.  This table is
+stored compressed into metadata blocks.  A second index table is used to
+locate these.  This second index table for speed of access (and because it
+is small) is read at mount time and cached in memory.
+
+3.6 Export table
+----------------
+
+To enable Squashfs filesystems to be exportable (via NFS etc.) filesystems
+can optionally (disabled with the -no-exports Mksquashfs option) contain
+an inode number to inode disk location lookup table.  This is required to
+enable Squashfs to map inode numbers passed in filehandles to the inode
+location on disk, which is necessary when the export code reinstantiates
+expired/flushed inodes.
+
+This table is stored compressed into metadata blocks.  A second index table is
+used to locate these.  This second index table for speed of access (and because
+it is small) is read at mount time and cached in memory.
+
+
+4. TODOS AND OUTSTANDING ISSUES
+-------------------------------
+
+4.1 Todo list
+-------------
+
+Implement Xattr and ACL support.  The Squashfs 4.0 filesystem layout has hooks
+for these but the code has not been written.  Once the code has been written
+the existing layout should not require modification.
+
+4.2 Squashfs internal cache
+---------------------------
+
+Blocks in Squashfs are compressed.  To avoid repeatedly decompressing
+recently accessed data Squashfs uses two small metadata and fragment caches.
+
+The cache is not used for file datablocks, these are decompressed and cached in
+the page-cache in the normal way.  The cache is used to temporarily cache
+fragment and metadata blocks which have been read as a result of a metadata
+(i.e. inode or directory) or fragment access.  Because metadata and fragments
+are packed together into blocks (to gain greater compression) the read of a
+particular piece of metadata or fragment will retrieve other metadata/fragments
+which have been packed with it, these because of locality-of-reference may be
+read in the near future. Temporarily caching them ensures they are available
+for near future access without requiring an additional read and decompress.
+
+In the future this internal cache may be replaced with an implementation which
+uses the kernel page cache.  Because the page cache operates on page sized
+units this may introduce additional complexity in terms of locking and
+associated race conditions.

Documentation/filesystems/ubifs.txt

@@ -79,13 +79,6 @@ Mount options
 
 (*) == default.
 
-norm_unmount (*)	commit on unmount; the journal is committed
-			when the file-system is unmounted so that the
-			next mount does not have to replay the journal
-			and it becomes very fast;
-fast_unmount		do not commit on unmount; this option makes
-			unmount faster, but the next mount slower
-			because of the need to replay the journal.
 bulk_read		read more in one go to take advantage of flash
 			media that read faster sequentially
 no_bulk_read (*)	do not bulk-read
@@ -95,6 +88,9 @@ no_chk_data_crc		skip checking of CRCs on data nodes in order to
 			of this option is that corruption of the contents
 			of a file can go unnoticed.
 chk_data_crc (*)	do not skip checking CRCs on data nodes
+compr=none              override default compressor and set it to "none"
+compr=lzo               override default compressor and set it to "lzo"
+compr=zlib              override default compressor and set it to "zlib"
 
 
 Quick usage instructions

Documentation/filesystems/vfs.txt

@@ -210,8 +210,8 @@ struct super_operations {
         void (*put_super) (struct super_block *);
         void (*write_super) (struct super_block *);
         int (*sync_fs)(struct super_block *sb, int wait);
-        void (*write_super_lockfs) (struct super_block *);
-        void (*unlockfs) (struct super_block *);
+        int (*freeze_fs) (struct super_block *);
+        int (*unfreeze_fs) (struct super_block *);
         int (*statfs) (struct dentry *, struct kstatfs *);
         int (*remount_fs) (struct super_block *, int *, char *);
         void (*clear_inode) (struct inode *);
@@ -270,11 +270,11 @@ or bottom half).
   	a superblock. The second parameter indicates whether the method
 	should wait until the write out has been completed. Optional.
 
-  write_super_lockfs: called when VFS is locking a filesystem and
+  freeze_fs: called when VFS is locking a filesystem and
   	forcing it into a consistent state.  This method is currently
   	used by the Logical Volume Manager (LVM).
 
-  unlockfs: called when VFS is unlocking a filesystem and making it writable
+  unfreeze_fs: called when VFS is unlocking a filesystem and making it writable
   	again.
 
   statfs: called when the VFS needs to get filesystem statistics. This
@@ -733,7 +733,6 @@ struct file_operations {
 	ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
 	unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
 	int (*check_flags)(int);
-	int (*dir_notify)(struct file *filp, unsigned long arg);
 	int (*flock) (struct file *, int, struct file_lock *);
 	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, struct pipe_inode_info *, size_t, unsigned int);
@@ -800,8 +799,6 @@ otherwise noted.
 
   check_flags: called by the fcntl(2) system call for F_SETFL command
 
-  dir_notify: called by the fcntl(2) system call for F_NOTIFY command
-
   flock: called by the flock(2) system call
 
   splice_write: called by the VFS to splice data from a pipe to a file. This
@@ -931,7 +928,7 @@ manipulate dentries:
   d_lookup: look up a dentry given its parent and path name component
 	It looks up the child of that given name from the dcache
 	hash table. If it is found, the reference count is incremented
-	and the dentry is returned. The caller must use d_put()
+	and the dentry is returned. The caller must use dput()
 	to free the dentry when it finishes using it.
 
 For further information on dentry locking, please refer to the document

Documentation/hwmon/abituguru-datasheet

@@ -74,7 +74,7 @@ a sensor.
 Notice that some banks have both a read and a write address this is how the
 uGuru determines if a read from or a write to the bank is taking place, thus
 when reading you should always use the read address and when writing the
-write address. The write address is always one (1) more then the read address.
+write address. The write address is always one (1) more than the read address.
 
 
 uGuru ready
@@ -121,7 +121,7 @@ Once all bytes have been read data will hold 0x09, but there is no reason to
 test for this. Notice that the number of bytes is bank address dependent see
 above and below.
 
-After completing a successfull read it is advised to put the uGuru back in
+After completing a successful read it is advised to put the uGuru back in
 ready mode, so that it is ready for the next read / write cycle. This way
 if your program / driver is unloaded and later loaded again the detection
 algorithm described above will still work.
@@ -141,7 +141,7 @@ don't ask why this is the way it is.
 
 Once DATA holds 0x01 read CMD it should hold 0xAC now.
 
-After completing a successfull write it is advised to put the uGuru back in
+After completing a successful write it is advised to put the uGuru back in
 ready mode, so that it is ready for the next read / write cycle. This way
 if your program / driver is unloaded and later loaded again the detection
 algorithm described above will still work.
@@ -224,7 +224,7 @@ Bit 3: Beep if alarm							(RW)
 Bit 4: 1 if alarm cause measured temp is over the warning threshold	(R)
 Bit 5: 1 if alarm cause measured volt is over the max threshold		(R)
 Bit 6: 1 if alarm cause measured volt is under the min threshold	(R)
-Bit 7: Volt sensor: Shutdown if alarm persist for more then 4 seconds	(RW)
+Bit 7: Volt sensor: Shutdown if alarm persist for more than 4 seconds	(RW)
        Temp sensor: Shutdown if temp is over the shutdown threshold	(RW)
 
 *  This bit is only honored/used by the uGuru if a temp sensor is connected
@@ -293,7 +293,7 @@ Byte 0:
 Alarm behaviour for the selected sensor. A 1 enables the described behaviour.
 Bit 0: Give an alarm if measured rpm is under the min threshold	(RW)
 Bit 3: Beep if alarm						(RW)
-Bit 7: Shutdown if alarm persist for more then 4 seconds	(RW)
+Bit 7: Shutdown if alarm persist for more than 4 seconds	(RW)
 
 Byte 1:
 min threshold (scale as bank 0x26)

Documentation/hwmon/adt7470

@@ -31,15 +31,11 @@ Each of the measured inputs (temperature, fan speed) has corresponding high/low
 limit values. The ADT7470 will signal an ALARM if any measured value exceeds
 either limit.
 
-The ADT7470 DOES NOT sample all inputs continuously.  A single pin on the
-ADT7470 is connected to a multitude of thermal diodes, but the chip must be
-instructed explicitly to read the multitude of diodes.  If you want to use
-automatic fan control mode, you must manually read any of the temperature
-sensors or the fan control algorithm will not run.  The chip WILL NOT DO THIS
-AUTOMATICALLY; this must be done from userspace.  This may be a bug in the chip
-design, given that many other AD chips take care of this.  The driver will not
-read the registers more often than once every 5 seconds.  Further,
-configuration data is only read once per minute.
+The ADT7470 samples all inputs continuously.  A kernel thread is started up for
+the purpose of periodically querying the temperature sensors, thus allowing the
+automatic fan pwm control to set the fan speed.  The driver will not read the
+registers more often than once every 5 seconds.  Further, configuration data is
+only read once per minute.
 
 Special Features
 ----------------
@@ -72,5 +68,6 @@ pwm#_auto_point2_temp.
 Notes
 -----
 
-As stated above, the temperature inputs must be read periodically from
-userspace in order for the automatic pwm algorithm to run.
+The temperature inputs no longer need to be read periodically from userspace in
+order for the automatic pwm algorithm to run.  This was the case for earlier
+versions of the driver.

Documentation/hwmon/adt7475

+This describes the interface for the ADT7475 driver:
+
+(there are 4 fans, numbered fan1 to fan4):
+
+fanX_input		Read the current speed of the fan (in RPMs)
+fanX_min		Read/write the minimum speed of the fan.  Dropping
+			below this sets an alarm.
+
+(there are three PWMs, numbered pwm1 to pwm3):
+
+pwmX			Read/write the current duty cycle of the PWM.  Writes
+			only have effect when auto mode is turned off (see
+			below).  Range is 0 - 255.
+
+pwmX_enable		Fan speed control method:
+
+			0 - No control (fan at full speed)
+			1 - Manual fan speed control (using pwm[1-*])
+			2 - Automatic fan speed control
+
+pwmX_auto_channels_temp	Select which channels affect this PWM
+
+			1 - TEMP1 controls PWM
+			2 - TEMP2 controls PWM
+			4 - TEMP3 controls PWM
+			6 - TEMP2 and TEMP3 control PWM
+			7 - All three inputs control PWM
+
+pwmX_freq		Read/write the PWM frequency in Hz. The number
+			should be one of the following:
+
+			11 Hz
+			14 Hz
+			22 Hz
+			29 Hz
+			35 Hz
+			44 Hz
+			58 Hz
+			88 Hz
+
+pwmX_auto_point1_pwm	Read/write the minimum PWM duty cycle in automatic mode
+
+pwmX_auto_point2_pwm	Read/write the maximum PWM duty cycle in automatic mode
+
+(there are three temperature settings numbered temp1 to temp3):
+
+tempX_input		Read the current temperature.  The value is in milli
+			degrees of Celsius.
+
+tempX_max		Read/write the upper temperature limit - exceeding this
+			will cause an alarm.
+
+tempX_min		Read/write the lower temperature limit - exceeding this
+			will cause an alarm.
+
+tempX_offset		Read/write the temperature adjustment offset
+
+tempX_crit		Read/write the THERM limit for remote1.
+
+tempX_crit_hyst		Set the temperature value below crit where the
+			fans will stay on - this helps drive the temperature
+			low enough so it doesn't stay near the edge and
+			cause THERM to keep tripping.
+
+tempX_auto_point1_temp	Read/write the minimum temperature where the fans will
+			turn on in automatic mode.
+
+tempX_auto_point2_temp	Read/write the maximum temperature over which the fans
+			will run in automatic mode.  tempX_auto_point1_temp
+			and tempX_auto_point2_temp together define the
+			range of automatic control.
+
+tempX_alarm		Read a 1 if the max/min alarm is set
+tempX_fault		Read a 1 if either temp1 or temp3 diode has a fault
+
+(There are two voltage settings, in1 and in2):
+
+inX_input		Read the current voltage on VCC.  Value is in
+			millivolts.
+
+inX_min			read/write the minimum voltage limit.
+			Dropping below this causes an alarm.
+
+inX_max			read/write the maximum voltage limit.
+			Exceeding this causes an alarm.
+
+inX_alarm		Read a 1 if the max/min alarm is set.

Documentation/hwmon/f71882fg

+Kernel driver f71882fg
+======================
+
+Supported chips:
+  * Fintek F71882FG and F71883FG
+    Prefix: 'f71882fg'
+    Addresses scanned: none, address read from Super I/O config space
+    Datasheet: Available from the Fintek website
+  * Fintek F71862FG and F71863FG
+    Prefix: 'f71862fg'
+    Addresses scanned: none, address read from Super I/O config space
+    Datasheet: Available from the Fintek website
+  * Fintek F8000
+    Prefix: 'f8000'
+    Addresses scanned: none, address read from Super I/O config space
+    Datasheet: Not public
+
+Author: Hans de Goede <hdegoede@redhat.com>
+
+
+Description
+-----------
+
+Fintek F718xxFG/F8000 Super I/O chips include complete hardware monitoring
+capabilities. They can monitor up to 9 voltages (3 for the F8000), 4 fans and
+3 temperature sensors.
+
+These chips also have fan controlling features, using either DC or PWM, in
+three different modes (one manual, two automatic).
+
+The driver assumes that no more than one chip is present, which seems
+reasonable.
+
+
+Monitoring
+----------
+
+The Voltage, Fan and Temperature Monitoring uses the standard sysfs
+interface as documented in sysfs-interface, without any exceptions.
+
+
+Fan Control
+-----------
+
+Both PWM (pulse-width modulation) and DC fan speed control methods are
+supported. The right one to use depends on external circuitry on the
+motherboard, so the driver assumes that the BIOS set the method
+properly.
+
+There are 2 modes to specify the speed of the fan, PWM duty cycle (or DC
+voltage) mode, where 0-100% duty cycle (0-100% of 12V) is specified. And RPM
+mode where the actual RPM of the fan (as measured) is controlled and the speed
+gets specified as 0-100% of the fan#_full_speed file.
+
+Since both modes work in a 0-100% (mapped to 0-255) scale, there isn't a
+whole lot of a difference when modifying fan control settings. The only
+important difference is that in RPM mode the 0-100% controls the fan speed
+between 0-100% of fan#_full_speed. It is assumed that if the BIOS programs
+RPM mode, it will also set fan#_full_speed properly, if it does not then
+fan control will not work properly, unless you set a sane fan#_full_speed
+value yourself.
+
+Switching between these modes requires re-initializing a whole bunch of
+registers, so the mode which the BIOS has set is kept. The mode is
+printed when loading the driver.
+
+Three different fan control modes are supported; the mode number is written
+to the pwm#_enable file. Note that not all modes are supported on all
+chips, and some modes may only be available in RPM / PWM mode on the F8000.
+Writing an unsupported mode will result in an invalid parameter error.
+
+* 1: Manual mode
+  You ask for a specific PWM duty cycle / DC voltage or a specific % of
+  fan#_full_speed by writing to the pwm# file. This mode is only
+  available on the F8000 if the fan channel is in RPM mode.
+
+* 2: Normal auto mode
+  You can define a number of temperature/fan speed trip points, which % the
+  fan should run at at this temp and which temp a fan should follow using the
+  standard sysfs interface. The number and type of trip points is chip
+  depended, see which files are available in sysfs.
+  Fan/PWM channel 3 of the F8000 is always in this mode!
+
+* 3: Thermostat mode (Only available on the F8000 when in duty cycle mode)
+  The fan speed is regulated to keep the temp the fan is mapped to between
+  temp#_auto_point2_temp and temp#_auto_point3_temp.
+
+Both of the automatic modes require that pwm1 corresponds to fan1, pwm2 to
+fan2 and pwm3 to fan3.

Documentation/hwmon/it87

@@ -26,6 +26,10 @@ Supported chips:
     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
+  * IT8720F
+    Prefix: 'it8720'
+    Addresses scanned: from Super I/O config space (8 I/O ports)
+    Datasheet: Not yet publicly available.
   * SiS950   [clone of IT8705F]
     Prefix: 'it87'
     Addresses scanned: from Super I/O config space (8 I/O ports)
@@ -71,7 +75,7 @@ Description
 -----------
 
 This driver implements support for the IT8705F, IT8712F, IT8716F,
-IT8718F, IT8726F and SiS950 chips.
+IT8718F, IT8720F, IT8726F and SiS950 chips.
 
 These chips are 'Super I/O chips', supporting floppy disks, infrared ports,
 joysticks and other miscellaneous stuff. For hardware monitoring, they
@@ -84,19 +88,19 @@ the IT8716F and late IT8712F have 6. They are shared with other functions
 though, so the functionality may not be available on a given system.
 The driver dumbly assume it is there.
 
-The IT8718F also features VID inputs (up to 8 pins) but the value is
-stored in the Super-I/O configuration space. Due to technical limitations,
+The IT8718F and IT8720F also features VID inputs (up to 8 pins) but the value
+is stored in the Super-I/O configuration space. Due to technical limitations,
 this value can currently only be read once at initialization time, so
 the driver won't notice and report changes in the VID value. The two
 upper VID bits share their pins with voltage inputs (in5 and in6) so you
 can't have both on a given board.
 
-The IT8716F, IT8718F and later IT8712F revisions have support for
+The IT8716F, IT8718F, IT8720F and later IT8712F revisions have support for
 2 additional fans. The additional fans are supported by the driver.
 
-The IT8716F and IT8718F, and late IT8712F and IT8705F also have optional
-16-bit tachometer counters for fans 1 to 3. This is better (no more fan
-clock divider mess) but not compatible with the older chips and
+The IT8716F, IT8718F and IT8720F, and late IT8712F and IT8705F also have
+optional 16-bit tachometer counters for fans 1 to 3. This is better (no more
+fan clock divider mess) but not compatible with the older chips and
 revisions. The 16-bit tachometer mode is enabled by the driver when one
 of the above chips is detected.
 
@@ -122,7 +126,7 @@ zero'; this is important for negative voltage measurements. All voltage
 inputs can measure voltages between 0 and 4.08 volts, with a resolution of
 0.016 volt. The battery voltage in8 does not have limit registers.
 
-The VID lines (IT8712F/IT8716F/IT8718F) encode the core voltage value:
+The VID lines (IT8712F/IT8716F/IT8718F/IT8720F) encode the core voltage value:
 the voltage level your processor should work with. This is hardcoded by
 the mainboard and/or processor itself. It is a value in volts.
 

Documentation/hwmon/lis3lv02d

@@ -13,18 +13,21 @@ Author:
 Description
 -----------
 
-This driver provides support for the accelerometer found in various HP laptops
-sporting the feature officially called "HP Mobile Data Protection System 3D" or
-"HP 3D DriveGuard". It detect automatically laptops with this sensor. Known models
-(for now the HP 2133, nc6420, nc2510, nc8510, nc84x0, nw9440 and nx9420) will
-have their axis automatically oriented on standard way (eg: you can directly
-play neverball).  The accelerometer data is readable via
+This driver provides support for the accelerometer found in various HP
+laptops sporting the feature officially called "HP Mobile Data
+Protection System 3D" or "HP 3D DriveGuard". It detect automatically
+laptops with this sensor. Known models (for now the HP 2133, nc6420,
+nc2510, nc8510, nc84x0, nw9440 and nx9420) will have their axis
+automatically oriented on standard way (eg: you can directly play
+neverball).  The accelerometer data is readable via
 /sys/devices/platform/lis3lv02d.
 
 Sysfs attributes under /sys/devices/platform/lis3lv02d/:
 position - 3D position that the accelerometer reports. Format: "(x,y,z)"
-calibrate - read: values (x, y, z) that are used as the base for input class device operation.
-            write: forces the base to be recalibrated with the current position.
+calibrate - read: values (x, y, z) that are used as the base for input
+		  class device operation.
+            write: forces the base to be recalibrated with the current
+		  position.
 rate - reports the sampling rate of the accelerometer device in HZ
 
 This driver also provides an absolute input class device, allowing
@@ -39,11 +42,12 @@ the accelerometer are converted into a "standard" organisation of the axes
  * When the laptop is horizontal the position reported is about 0 for X and Y
 and a positive value for Z
  * If the left side is elevated, X increases (becomes positive)
- * If the front side (where the touchpad is) is elevated, Y decreases (becomes negative)
+ * If the front side (where the touchpad is) is elevated, Y decreases
+	(becomes negative)
  * If the laptop is put upside-down, Z becomes negative
 
-If your laptop model is not recognized (cf "dmesg"), you can send an email to the
-authors to add it to the database.  When reporting a new laptop, please include
-the output of "dmidecode" plus the value of /sys/devices/platform/lis3lv02d/position
-in these four cases.
+If your laptop model is not recognized (cf "dmesg"), you can send an
+email to the authors to add it to the database.  When reporting a new
+laptop, please include the output of "dmidecode" plus the value of
+/sys/devices/platform/lis3lv02d/position in these four cases.
 

Documentation/hwmon/lm70

 Kernel driver lm70
 ==================
 
-Supported chip:
+Supported chips:
   * National Semiconductor LM70
     Datasheet: http://www.national.com/pf/LM/LM70.html
+  * Texas Instruments TMP121/TMP123
+    Information: http://focus.ti.com/docs/prod/folders/print/tmp121.html
 
 Author:
         Kaiwan N Billimoria <kaiwan@designergraphix.com>
@@ -25,6 +27,14 @@ complement digital temperature (sent via the SIO line), is available in the
 driver for interpretation. This driver makes use of the kernel's in-core
 SPI support.
 
+As a real (in-tree) example of this "SPI protocol driver" interfacing
+with a "SPI master controller driver", see drivers/spi/spi_lm70llp.c
+and its associated documentation.
+
+The TMP121/TMP123 are very similar; main differences are 4 wire SPI inter-
+face (read only) and 13-bit temperature data (0.0625 degrees celsius reso-
+lution).
+
 Thanks to
 ---------
 Jean Delvare <khali@linux-fr.org> for mentoring the hwmon-side driver

Documentation/hwmon/lm85

@@ -164,7 +164,7 @@ configured individually according to the following options.
                       temperature. (PWM value from 0 to 255)
 
 * pwm#_auto_pwm_minctl - this flags selects for temp#_auto_temp_off temperature
-                         the bahaviour of fans. Write 1 to let fans spinning at
+                         the behaviour of fans. Write 1 to let fans spinning at
 			 pwm#_auto_pwm_min or write 0 to let them off.
 
 NOTE: It has been reported that there is a bug in the LM85 that causes the flag

Documentation/hwmon/ltc4245

+Kernel driver ltc4245
+=====================
+
+Supported chips:
+  * Linear Technology LTC4245
+    Prefix: 'ltc4245'
+    Addresses scanned: 0x20-0x3f
+    Datasheet:
+        http://www.linear.com/pc/downloadDocument.do?navId=H0,C1,C1003,C1006,C1140,P19392,D13517
+
+Author: Ira W. Snyder <iws@ovro.caltech.edu>
+
+
+Description
+-----------
+
+The LTC4245 controller allows a board to be safely inserted and removed
+from a live backplane in multiple supply systems such as CompactPCI and
+PCI Express.
+
+
+Usage Notes
+-----------
+
+This driver does not probe for LTC4245 devices, due to the fact that some
+of the possible addresses are unfriendly to probing. You will need to use
+the "force" parameter to tell the driver where to find the device.
+
+Example: the following will load the driver for an LTC4245 at address 0x23
+on I2C bus #1:
+$ modprobe ltc4245 force=1,0x23
+
+
+Sysfs entries
+-------------
+
+The LTC4245 has built-in limits for over and under current warnings. This
+makes it very likely that the reference circuit will be used.
+
+This driver uses the values in the datasheet to change the register values
+into the values specified in the sysfs-interface document. The current readings
+rely on the sense resistors listed in Table 2: "Sense Resistor Values".
+
+in1_input		12v input voltage (mV)
+in2_input		5v  input voltage (mV)
+in3_input		3v  input voltage (mV)
+in4_input		Vee (-12v) input voltage (mV)
+
+in1_min_alarm		12v input undervoltage alarm
+in2_min_alarm		5v  input undervoltage alarm
+in3_min_alarm		3v  input undervoltage alarm
+in4_min_alarm		Vee (-12v) input undervoltage alarm
+
+curr1_input		12v current (mA)
+curr2_input		5v  current (mA)
+curr3_input		3v  current (mA)
+curr4_input		Vee (-12v) current (mA)
+
+curr1_max_alarm		12v overcurrent alarm
+curr2_max_alarm		5v  overcurrent alarm
+curr3_max_alarm		3v  overcurrent alarm
+curr4_max_alarm		Vee (-12v) overcurrent alarm
+
+in5_input		12v output voltage (mV)
+in6_input		5v  output voltage (mV)
+in7_input		3v  output voltage (mV)
+in8_input		Vee (-12v) output voltage (mV)
+
+in5_min_alarm		12v output undervoltage alarm
+in6_min_alarm		5v  output undervoltage alarm
+in7_min_alarm		3v  output undervoltage alarm
+in8_min_alarm		Vee (-12v) output undervoltage alarm
+
+in9_input		GPIO #1 voltage data
+in10_input		GPIO #2 voltage data
+in11_input		GPIO #3 voltage data
+
+power1_input		12v power usage (mW)
+power2_input		5v  power usage (mW)
+power3_input		3v  power usage (mW)
+power4_input		Vee (-12v) power usage (mW)

Documentation/ide/warm-plug-howto.txt

@@ -11,3 +11,8 @@ unplug old device(s) and plug new device(s)
 # echo -n "1" > /sys/class/ide_port/idex/scan
 
 done
+
+NOTE: please make sure that partitions are unmounted and that there are
+no other active references to devices before doing "delete_devices" step,
+also do not attempt "scan" step on devices currently in use -- otherwise
+results may be unpredictable and lead to data loss if you're unlucky

Documentation/input/walkera0701.txt

+
+Walkera WK-0701 transmitter is supplied with a ready to fly Walkera
+helicopters such as HM36, HM37, HM60. The walkera0701 module enables to use
+this transmitter as joystick
+
+Devel homepage and download:
+http://zub.fei.tuke.sk/walkera-wk0701/
+
+or use cogito:
+cg-clone http://zub.fei.tuke.sk/GIT/walkera0701-joystick
+
+
+Connecting to PC:
+
+At back side of transmitter S-video connector can be found. Modulation
+pulses from processor to HF part can be found at pin 2 of this connector,
+pin 3 is GND. Between pin 3 and CPU 5k6 resistor can be found. To get
+modulation pulses to PC, signal pulses must be amplified.
+
+Cable: (walkera TX to parport)
+
+Walkera WK-0701 TX S-VIDEO connector:
+ (back side of TX)
+     __   __              S-video:                                  canon25
+    /  |_|  \             pin 2 (signal)              NPN           parport
+   / O 4 3 O \            pin 3 (GND)        LED        ________________  10 ACK
+  ( O 2   1 O )                                         | C
+   \   ___   /      2 ________________________|\|_____|/
+    | [___] |                                 |/|   B |\
+     -------        3 __________________________________|________________ 25 GND
+                                                          E
+
+
+I use green LED and BC109 NPN transistor.
+
+Software:
+
+Build kernel with walkera0701 module. Module walkera0701 need exclusive
+access to parport, modules like lp must be unloaded before loading
+walkera0701 module, check dmesg for error messages. Connect TX to PC by
+cable and run jstest /dev/input/js0 to see values from TX. If no value can
+be changed by TX "joystick", check output from /proc/interrupts. Value for
+(usually irq7) parport must increase if TX is on.
+
+
+
+Technical details:
+
+Driver use interrupt from parport ACK input bit to measure pulse length
+using hrtimers.
+
+Frame format:
+Based on walkera WK-0701 PCM Format description by Shaul Eizikovich.
+(downloaded from http://www.smartpropoplus.com/Docs/Walkera_Wk-0701_PCM.pdf)
+
+Signal pulses:
+                   (ANALOG)
+    SYNC      BIN   OCT
+  +---------+      +------+
+  |         |      |      |
+--+         +------+      +---
+
+Frame:
+ SYNC , BIN1, OCT1, BIN2, OCT2 ... BIN24, OCT24, BIN25, next frame SYNC ..
+
+pulse length:
+   Binary values:		Analog octal values:
+
+   288 uS Binary 0		318 uS       000
+   438 uS Binary 1		398 uS       001
+				478 uS       010
+				558 uS       011
+				638 uS       100
+  1306 uS SYNC			718 uS       101
+				798 uS       110
+				878 uS       111
+
+24 bin+oct values + 1 bin value = 24*4+1 bits  = 97 bits
+
+(Warning, pulses on ACK ar inverted by transistor, irq is rised up on sync
+to bin change or octal value to bin change).
+
+Binary data representations:
+
+One binary and octal value can be grouped to nibble. 24 nibbles + one binary
+values can be sampled between sync pulses.
+
+Values for first four channels (analog joystick values) can be found in
+first 10 nibbles. Analog value is represented by one sign bit and 9 bit
+absolute binary value. (10 bits per channel). Next nibble is checksum for
+first ten nibbles.
+
+Next nibbles 12 .. 21 represents four channels (not all channels can be
+directly controlled from TX). Binary representations ar the same as in first
+four channels. In nibbles 22 and 23 is a special magic number. Nibble 24 is
+checksum for nibbles 12..23.
+
+After last octal value for nibble 24 and next sync pulse one additional
+binary value can be sampled. This bit and magic number is not used in
+software driver. Some details about this magic numbers can be found in
+Walkera_Wk-0701_PCM.pdf.
+
+Checksum calculation:
+
+Summary of octal values in nibbles must be same as octal value in checksum
+nibble (only first 3 bits are used). Binary value for checksum nibble is
+calculated by sum of binary values in checked nibbles + sum of octal values
+in checked nibbles divided by 8. Only bit 0 of this sum is used.
+

Documentation/ioctl/ioctl-number.txt

@@ -84,7 +84,7 @@ Code	Seq#	Include File		Comments
 'B'	C0-FF				advanced bbus
 					<mailto:maassen@uni-freiburg.de>
 'C'	all	linux/soundcard.h
-'D'	all	asm-s390/dasd.h
+'D'	all	arch/s390/include/asm/dasd.h
 'E'	all	linux/input.h
 'F'	all	linux/fb.h
 'H'	all	linux/hiddev.h
@@ -97,6 +97,7 @@ Code	Seq#	Include File		Comments
 					<http://linux01.gwdg.de/~alatham/ppdd.html>
 'M'	all	linux/soundcard.h
 'N'	00-1F	drivers/usb/scanner.h
+'O'     00-02   include/mtd/ubi-user.h UBI
 'P'	all	linux/soundcard.h
 'Q'	all	linux/soundcard.h
 'R'	00-1F	linux/random.h
@@ -104,7 +105,7 @@ Code	Seq#	Include File		Comments
 'S'	80-81	scsi/scsi_ioctl.h	conflict!
 'S'	82-FF	scsi/scsi.h		conflict!
 'T'	all	linux/soundcard.h	conflict!
-'T'	all	asm-i386/ioctls.h	conflict!
+'T'	all	arch/x86/include/asm/ioctls.h	conflict!
 'U'	00-EF	linux/drivers/usb/usb.h
 'V'	all	linux/vt.h
 'W'	00-1F	linux/watchdog.h	conflict!
@@ -119,7 +120,7 @@ Code	Seq#	Include File		Comments
 					<mailto:natalia@nikhefk.nikhef.nl>
 'c'	00-7F	linux/comstats.h	conflict!
 'c'	00-7F	linux/coda.h		conflict!
-'c'	80-9F	asm-s390/chsc.h
+'c'	80-9F	arch/s390/include/asm/chsc.h
 'd'	00-FF	linux/char/drm/drm/h	conflict!
 'd'	00-DF	linux/video_decoder.h	conflict!
 'd'	F0-FF	linux/digi1.h
@@ -142,6 +143,9 @@ Code	Seq#	Include File		Comments
 'n'	00-7F	linux/ncp_fs.h
 'n'	E0-FF	video/matrox.h          matroxfb
 'o'	00-1F	fs/ocfs2/ocfs2_fs.h	OCFS2
+'o'     00-03   include/mtd/ubi-user.h  conflict! (OCFS2 and UBI overlaps)
+'o'     40-41   include/mtd/ubi-user.h  UBI
+'o'     01-A1   include/linux/dvb/*.h DVB
 'p'	00-0F	linux/phantom.h		conflict! (OpenHaptics needs this)
 'p'	00-3F	linux/mc146818rtc.h	conflict!
 'p'	40-7F	linux/nvram.h
@@ -166,7 +170,7 @@ Code	Seq#	Include File		Comments
 					<mailto:oe@port.de>
 0x80	00-1F	linux/fb.h
 0x81	00-1F	linux/videotext.h
-0x89	00-06	asm-i386/sockios.h
+0x89	00-06	arch/x86/include/asm/sockios.h
 0x89	0B-DF	linux/sockios.h
 0x89	E0-EF	linux/sockios.h		SIOCPROTOPRIVATE range
 0x89	F0-FF	linux/sockios.h		SIOCDEVPRIVATE range

Documentation/ja_JP/stable_kernel_rules.txt

@@ -12,11 +12,11 @@ file at first.
 
 ==================================
 これは、
-linux-2.6.24/Documentation/stable_kernel_rules.txt
+linux-2.6.29/Documentation/stable_kernel_rules.txt
 の和訳です。
 
 翻訳団体： JF プロジェクト < http://www.linux.or.jp/JF/ >
-翻訳日： 2007/12/30
+翻訳日： 2009/1/14
 翻訳者： Tsugikazu Shibata <tshibata at ab dot jp dot nec dot com>
 校正者： 武井伸光さん、<takei at webmasters dot gr dot jp>
          かねこさん (Seiji Kaneko) <skaneko at a2 dot mbn dot or dot jp>
@@ -38,12 +38,15 @@ linux-2.6.24/Documentation/stable_kernel_rules.txt
  - ビルドエラー(CONFIG_BROKENになっているものを除く), oops, ハング、デー
    タ破壊、現実のセキュリティ問題、その他 "ああ、これはダメだね"という
    ようなものを修正しなければならない。短く言えば、重大な問題。
+ - 新しい device ID とクオークも受け入れられる。
  - どのように競合状態が発生するかの説明も一緒に書かれていない限り、
    "理論的には競合状態になる"ようなものは不可。
  - いかなる些細な修正も含めることはできない。(スペルの修正、空白のクリー
    ンアップなど)
- - 対応するサブシステムメンテナが受け入れたものでなければならない。
  - Documentation/SubmittingPatches の規則に従ったものでなければならない。
+ - パッチ自体か同等の修正が Linus のツリーに既に存在しなければならない。
+　 Linus のツリーでのコミットID を -stable へのパッチ投稿の際に引用す
+   ること。
 
 -stable ツリーにパッチを送付する手続き-
 
@@ -52,8 +55,10 @@ linux-2.6.24/Documentation/stable_kernel_rules.txt
  - 送信者はパッチがキューに受け付けられた際には ACK を、却下された場合
    には NAK を受け取る。この反応は開発者たちのスケジュールによって、数
    日かかる場合がある。
- - もし受け取られたら、パッチは他の開発者たちのレビューのために
-   -stable キューに追加される。
+ - もし受け取られたら、パッチは他の開発者たちと関連するサブシステムの
+   メンテナーによるレビューのために -stable キューに追加される。
+ - パッチに stable@kernel.org のアドレスが付加されているときには、それ
+   が Linus のツリーに入る時に自動的に stable チームに email される。
  - セキュリティパッチはこのエイリアス (stable@kernel.org) に送られるべ
    きではなく、代わりに security@kernel.org のアドレスに送られる。
 

Documentation/kbuild/00-INDEX

 00-INDEX
-    	- this file: info on the kernel build process
+	- this file: info on the kernel build process
+kbuild.txt
+	- developer information on kbuild
+kconfig.txt
+	- usage help for make *config
 kconfig-language.txt
 	- specification of Config Language, the language in Kconfig files
 makefiles.txt

Documentation/kbuild/kbuild.txt

+Environment variables
+
+KCPPFLAGS
+--------------------------------------------------
+Additional options to pass when preprocessing. The preprocessing options
+will be used in all cases where kbuild does preprocessing including
+building C files and assembler files.
+
+KAFLAGS
+--------------------------------------------------
+Additional options to the assembler.
+
+KCFLAGS
+--------------------------------------------------
+Additional options to the C compiler.
+
+KBUILD_VERBOSE
+--------------------------------------------------
+Set the kbuild verbosity. Can be assigned same values as "V=...".
+See make help for the full list.
+Setting "V=..." takes precedence over KBUILD_VERBOSE.
+
+KBUILD_EXTMOD
+--------------------------------------------------
+Set the directory to look for the kernel source when building external
+modules.
+The directory can be specified in several ways:
+1) Use "M=..." on the command line
+2) Environmnet variable KBUILD_EXTMOD
+3) Environmnet variable SUBDIRS
+The possibilities are listed in the order they take precedence.
+Using "M=..." will always override the others.
+
+KBUILD_OUTPUT
+--------------------------------------------------
+Specify the output directory when building the kernel.
+The output directory can also be specificed using "O=...".
+Setting "O=..." takes precedence over KBUILD_OUTPUT.
+
+ARCH
+--------------------------------------------------
+Set ARCH to the architecture to be built.
+In most cases the name of the architecture is the same as the
+directory name found in the arch/ directory.
+But some architectures such as x86 and sparc have aliases.
+x86: i386 for 32 bit, x86_64 for 64 bit
+sparc: sparc for 32 bit, sparc64 for 64 bit
+
+CROSS_COMPILE
+--------------------------------------------------
+Specify an optional fixed part of the binutils filename.
+CROSS_COMPILE can be a part of the filename or the full path.
+
+CROSS_COMPILE is also used for ccache is some setups.
+
+CF
+--------------------------------------------------
+Additional options for sparse.
+CF is often used on the command-line like this:
+
+    make CF=-Wbitwise C=2
+
+INSTALL_PATH
+--------------------------------------------------
+INSTALL_PATH specifies where to place the updated kernel and system map
+images. Default is /boot, but you can set it to other values.
+
+
+MODLIB
+--------------------------------------------------
+Specify where to install modules.
+The default value is:
+
+     $(INSTALL_MOD_PATH)/lib/modules/$(KERNELRELEASE)
+
+The value can be overridden in which case the default value is ignored.
+
+INSTALL_MOD_PATH
+--------------------------------------------------
+INSTALL_MOD_PATH specifies a prefix to MODLIB for module directory
+relocations required by build roots.  This is not defined in the
+makefile but the argument can be passed to make if needed.
+
+INSTALL_MOD_STRIP
+--------------------------------------------------
+INSTALL_MOD_STRIP, if defined, will cause modules to be
+stripped after they are installed.  If INSTALL_MOD_STRIP is '1', then
+the default option --strip-debug will be used.  Otherwise,
+INSTALL_MOD_STRIP will used as the options to the strip command.
+
+INSTALL_FW_PATH
+--------------------------------------------------
+INSTALL_FW_PATH specifies where to install the firmware blobs.
+The default value is:
+
+    $(INSTALL_MOD_PATH)/lib/firmware
+
+The value can be overridden in which case the default value is ignored.
+
+INSTALL_HDR_PATH
+--------------------------------------------------
+INSTALL_HDR_PATH specifies where to install user space headers when
+executing "make headers_*".
+The default value is:
+
+    $(objtree)/usr
+
+$(objtree) is the directory where output files are saved.
+The output directory is often set using "O=..." on the commandline.
+
+The value can be overridden in which case the default value is ignored.
+
+KBUILD_MODPOST_WARN
+--------------------------------------------------
+KBUILD_MODPOST_WARN can be set to avoid errors in case of undefined
+symbols in the final module linking stage. It changes such errors
+into warnings.
+
+KBUILD_MODPOST_NOFINAL
+--------------------------------------------------
+KBUILD_MODPOST_NOFINAL can be set to skip the final link of modules.
+This is solely useful to speed up test compiles.
+
+KBUILD_EXTRA_SYMBOLS
+--------------------------------------------------
+For modules that use symbols from other modules.
+See more details in modules.txt.
+
+ALLSOURCE_ARCHS
+--------------------------------------------------
+For tags/TAGS/cscope targets, you can specify more than one arch
+to be included in the databases, separated by blank space. E.g.:
+
+    $ make ALLSOURCE_ARCHS="x86 mips arm" tags

Documentation/kbuild/modules.txt

@@ -253,7 +253,7 @@ following files:
 
 		# Module specific targets
 		genbin:
-			echo "X" > 8123_bin_shipped
+			echo "X" > 8123_bin.o_shipped
 
 
 	In example 2, we are down to two fairly simple files and for simple
@@ -279,7 +279,7 @@ following files:
 
 		# Module specific targets
 		genbin:
-			echo "X" > 8123_bin_shipped
+			echo "X" > 8123_bin.o_shipped
 
 		endif
 

Documentation/kernel-doc-nano-HOWTO.txt

@@ -71,6 +71,11 @@ The @argument descriptions must begin on the very next line following
 this opening short function description line, with no intervening
 empty comment lines.
 
+If a function parameter is "..." (varargs), it should be listed in
+kernel-doc notation as:
+ * @...: description
+
+
 Example kernel-doc data structure comment.
 
 /**
@@ -282,6 +287,32 @@ struct my_struct {
 };
 
 
+Including documentation blocks in source files
+----------------------------------------------
+
+To facilitate having source code and comments close together, you can
+include kernel-doc documentation blocks that are free-form comments
+instead of being kernel-doc for functions, structures, unions,
+enums, or typedefs.  This could be used for something like a
+theory of operation for a driver or library code, for example.
+
+This is done by using a DOC: section keyword with a section title.  E.g.:
+
+/**
+ * DOC: Theory of Operation
+ *
+ * The whizbang foobar is a dilly of a gizmo.  It can do whatever you
+ * want it to do, at any time.  It reads your mind.  Here's how it works.
+ *
+ * foo bar splat
+ *
+ * The only drawback to this gizmo is that is can sometimes damage
+ * hardware, software, or its subject(s).
+ */
+
+DOC: sections are used in SGML templates files as indicated below.
+
+
 How to make new SGML template files
 -----------------------------------
 
@@ -302,6 +333,9 @@ exported using EXPORT_SYMBOL.
 !F<filename> <function [functions...]> is replaced by the
 documentation, in <filename>, for the functions listed.
 
+!P<filename> <section title> is replaced by the contents of the DOC:
+section titled <section title> from <filename>.
+Spaces are allowed in <section title>; do not quote the <section title>.
 
 Tim.
 */ <twaugh@redhat.com>

Documentation/kobject.txt

@@ -118,8 +118,8 @@ the name of the kobject, call kobject_rename():
 
     int kobject_rename(struct kobject *kobj, const char *new_name);
 
-Note kobject_rename does perform any locking or have a solid notion of
-what names are valid so the provide must provide their own sanity checking
+kobject_rename does not perform any locking or have a solid notion of
+what names are valid so the caller must provide their own sanity checking
 and serialization.
 
 There is a function called kobject_set_name() but that is legacy cruft and

Documentation/kprobes.txt

@@ -497,7 +497,10 @@ The first column provides the kernel address where the probe is inserted.
 The second column identifies the type of probe (k - kprobe, r - kretprobe
 and j - jprobe), while the third column specifies the symbol+offset of
 the probe. If the probed function belongs to a module, the module name
-is also specified.
+is also specified. Following columns show probe status. If the probe is on
+a virtual address that is no longer valid (module init sections, module
+virtual addresses that correspond to modules that've been unloaded),
+such probes are marked with [GONE].
 
 /debug/kprobes/enabled: Turn kprobes ON/OFF
 

Documentation/laptops/thinkpad-acpi.txt

 		     ThinkPad ACPI Extras Driver
 
-                            Version 0.21
-                           May 29th, 2008
+                            Version 0.22
+                        November 23rd,  2008
 
                Borislav Deianov <borislav@users.sf.net>
              Henrique de Moraes Holschuh <hmh@hmh.eng.br>
@@ -16,7 +16,8 @@ supported by the generic Linux ACPI drivers.
 This driver used to be named ibm-acpi until kernel 2.6.21 and release
 0.13-20070314.  It used to be in the drivers/acpi tree, but it was
 moved to the drivers/misc tree and renamed to thinkpad-acpi for kernel
-2.6.22, and release 0.14.
+2.6.22, and release 0.14.  It was moved to drivers/platform/x86 for
+kernel 2.6.29 and release 0.22.
 
 The driver is named "thinkpad-acpi".  In some places, like module
 names, "thinkpad_acpi" is used because of userspace issues.
@@ -1412,6 +1413,24 @@ Sysfs notes:
 	rfkill controller switch "tpacpi_wwan_sw": refer to
 	Documentation/rfkill.txt for details.
 
+EXPERIMENTAL: UWB
+-----------------
+
+This feature is marked EXPERIMENTAL because it has not been extensively
+tested and validated in various ThinkPad models yet.  The feature may not
+work as expected. USE WITH CAUTION! To use this feature, you need to supply
+the experimental=1 parameter when loading the module.
+
+sysfs rfkill class: switch "tpacpi_uwb_sw"
+
+This feature exports an rfkill controller for the UWB device, if one is
+present and enabled in the BIOS.
+
+Sysfs notes:
+
+	rfkill controller switch "tpacpi_uwb_sw": refer to
+	Documentation/rfkill.txt for details.
+
 Multiple Commands, Module Parameters
 ------------------------------------
 
@@ -1475,7 +1494,7 @@ Sysfs interface changelog:
 
 0x020100:	Marker for thinkpad-acpi with hot key NVRAM polling
 		support.  If you must, use it to know you should not
-		start an userspace NVRAM poller (allows to detect when
+		start a userspace NVRAM poller (allows to detect when
 		NVRAM is compiled out by the user because it is
 		unneeded/undesired in the first place).
 0x020101:	Marker for thinkpad-acpi with hot key NVRAM polling

Documentation/lguest/Makefile

 # This creates the demonstration utility "lguest" which runs a Linux guest.
-CFLAGS:=-Wall -Wmissing-declarations -Wmissing-prototypes -O3 -I../../include -I../../arch/x86/include
+CFLAGS:=-Wall -Wmissing-declarations -Wmissing-prototypes -O3 -I../../include -I../../arch/x86/include -U_FORTIFY_SOURCE
 LDLIBS:=-lz
 
 all: lguest