Merge branch 'x86/asm' into x86/atomic

Merge reason:
	Conflict between LOCK_PREFIX_HERE and relative alternatives
	pointers

Resolved Conflicts:
	arch/x86/include/asm/alternative.h
	arch/x86/kernel/alternative.c
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

.gitignore

@@ -34,12 +34,18 @@ modules.builtin
 #
 # Top-level generic files
 #
-tags
-TAGS
-vmlinux
-System.map
-Module.markers
-Module.symvers
+/tags
+/TAGS
+/linux
+/vmlinux
+/vmlinuz
+/System.map
+/Module.markers
+/Module.symvers
+
+#
+# git files that we don't want to ignore even it they are dot-files
+#
 !.gitignore
 !.mailmap
 

Documentation/ABI/stable/sysfs-devices-node

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

Documentation/ABI/testing/ima_policy

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

Documentation/ABI/testing/sysfs-block

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

Documentation/ABI/testing/sysfs-bus-usb

@@ -159,3 +159,14 @@ Description:
 		device.  This is useful to ensure auto probing won't
 		match the driver to the device.  For example:
 		# echo "046d c315" > /sys/bus/usb/drivers/foo/remove_id
+
+What:		/sys/bus/usb/device/.../avoid_reset_quirk
+Date:		December 2009
+Contact:	Oliver Neukum <oliver@neukum.org>
+Description:
+		Writing 1 to this file tells the kernel that this
+		device will morph into another mode when it is reset.
+		Drivers will not use reset for error handling for
+		such devices.
+Users:
+		usb_modeswitch

Documentation/ABI/testing/sysfs-devices-power

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

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

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

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

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

Documentation/ABI/testing/sysfs-power

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

Documentation/DMA-API.txt

@@ -4,20 +4,18 @@
         James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
 
 This document describes the DMA API.  For a more gentle introduction
-phrased in terms of the pci_ equivalents (and actual examples) see
-Documentation/PCI/PCI-DMA-mapping.txt.
+of the API (and actual examples) see
+Documentation/DMA-API-HOWTO.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
-for supporting non-consistent memory machines.  Unless you know that
-your driver absolutely has to support non-consistent platforms (this
-is usually only legacy platforms) you should only use the API
-described in part I.
+This API is split into two pieces.  Part I describes the API.  Part II
+describes the extensions to the API for supporting non-consistent
+memory machines.  Unless you know that your driver absolutely has to
+support non-consistent platforms (this is usually only legacy
+platforms) you should only use the API described in part I.
 
-Part I - pci_ and dma_ Equivalent API 
+Part I - dma_ API
 -------------------------------------
 
-To get the pci_ API, you must #include <linux/pci.h>
 To get the dma_ API, you must #include <linux/dma-mapping.h>
 
 
@@ -27,9 +25,6 @@ Part Ia - Using large dma-coherent buffers
 void *
 dma_alloc_coherent(struct device *dev, size_t size,
 			     dma_addr_t *dma_handle, gfp_t flag)
-void *
-pci_alloc_consistent(struct pci_dev *dev, size_t size,
-			     dma_addr_t *dma_handle)
 
 Consistent memory is memory for which a write by either the device or
 the processor can immediately be read by the processor or device
@@ -53,15 +48,11 @@ The simplest way to do that is to use the dma_pool calls (see below).
 The flag parameter (dma_alloc_coherent only) allows the caller to
 specify the GFP_ flags (see kmalloc) for the allocation (the
 implementation may choose to ignore flags that affect the location of
-the returned memory, like GFP_DMA).  For pci_alloc_consistent, you
-must assume GFP_ATOMIC behaviour.
+the returned memory, like GFP_DMA).
 
 void
 dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
 			   dma_addr_t dma_handle)
-void
-pci_free_consistent(struct pci_dev *dev, size_t size, void *cpu_addr,
-			   dma_addr_t dma_handle)
 
 Free the region of consistent memory you previously allocated.  dev,
 size and dma_handle must all be the same as those passed into the
@@ -89,10 +80,6 @@ for alignment, like queue heads needing to be aligned on N-byte boundaries.
 	dma_pool_create(const char *name, struct device *dev,
 			size_t size, size_t align, size_t alloc);
 
-	struct pci_pool *
-	pci_pool_create(const char *name, struct pci_device *dev,
-			size_t size, size_t align, size_t alloc);
-
 The pool create() routines initialize a pool of dma-coherent buffers
 for use with a given device.  It must be called in a context which
 can sleep.
@@ -108,9 +95,6 @@ from this pool must not cross 4KByte boundaries.
 	void *dma_pool_alloc(struct dma_pool *pool, gfp_t gfp_flags,
 			dma_addr_t *dma_handle);
 
-	void *pci_pool_alloc(struct pci_pool *pool, gfp_t gfp_flags,
-			dma_addr_t *dma_handle);
-
 This allocates memory from the pool; the returned memory will meet the size
 and alignment requirements specified at creation time.  Pass GFP_ATOMIC to
 prevent blocking, or if it's permitted (not in_interrupt, not holding SMP locks),
@@ -122,9 +106,6 @@ pool's device.
 	void dma_pool_free(struct dma_pool *pool, void *vaddr,
 			dma_addr_t addr);
 
-	void pci_pool_free(struct pci_pool *pool, void *vaddr,
-			dma_addr_t addr);
-
 This puts memory back into the pool.  The pool is what was passed to
 the pool allocation routine; the cpu (vaddr) and dma addresses are what
 were returned when that routine allocated the memory being freed.
@@ -132,8 +113,6 @@ were returned when that routine allocated the memory being freed.
 
 	void dma_pool_destroy(struct dma_pool *pool);
 
-	void pci_pool_destroy(struct pci_pool *pool);
-
 The pool destroy() routines free the resources of the pool.  They must be
 called in a context which can sleep.  Make sure you've freed all allocated
 memory back to the pool before you destroy it.
@@ -144,8 +123,6 @@ Part Ic - DMA addressing limitations
 
 int
 dma_supported(struct device *dev, u64 mask)
-int
-pci_dma_supported(struct pci_dev *hwdev, u64 mask)
 
 Checks to see if the device can support DMA to the memory described by
 mask.
@@ -159,8 +136,14 @@ driver writers.
 
 int
 dma_set_mask(struct device *dev, u64 mask)
+
+Checks to see if the mask is possible and updates the device
+parameters if it is.
+
+Returns: 0 if successful and a negative error if not.
+
 int
-pci_set_dma_mask(struct pci_device *dev, u64 mask)
+dma_set_coherent_mask(struct device *dev, u64 mask)
 
 Checks to see if the mask is possible and updates the device
 parameters if it is.
@@ -187,9 +170,6 @@ Part Id - Streaming DMA mappings
 dma_addr_t
 dma_map_single(struct device *dev, void *cpu_addr, size_t size,
 		      enum dma_data_direction direction)
-dma_addr_t
-pci_map_single(struct pci_dev *hwdev, void *cpu_addr, size_t size,
-		      int direction)
 
 Maps a piece of processor virtual memory so it can be accessed by the
 device and returns the physical handle of the memory.
@@ -198,14 +178,10 @@ The direction for both api's may be converted freely by casting.
 However the dma_ API uses a strongly typed enumerator for its
 direction:
 
-DMA_NONE		= PCI_DMA_NONE		no direction (used for
-						debugging)
-DMA_TO_DEVICE		= PCI_DMA_TODEVICE	data is going from the
-						memory to the device
-DMA_FROM_DEVICE		= PCI_DMA_FROMDEVICE	data is coming from
-						the device to the
-						memory
-DMA_BIDIRECTIONAL	= PCI_DMA_BIDIRECTIONAL	direction isn't known
+DMA_NONE		no direction (used for debugging)
+DMA_TO_DEVICE		data is going from the memory to the device
+DMA_FROM_DEVICE		data is coming from the device to the memory
+DMA_BIDIRECTIONAL	direction isn't known
 
 Notes:  Not all memory regions in a machine can be mapped by this
 API.  Further, regions that appear to be physically contiguous in
@@ -268,9 +244,6 @@ cache lines are updated with data that the device may have changed).
 void
 dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
 		 enum dma_data_direction direction)
-void
-pci_unmap_single(struct pci_dev *hwdev, dma_addr_t dma_addr,
-		 size_t size, int direction)
 
 Unmaps the region previously mapped.  All the parameters passed in
 must be identical to those passed in (and returned) by the mapping
@@ -280,15 +253,9 @@ dma_addr_t
 dma_map_page(struct device *dev, struct page *page,
 		    unsigned long offset, size_t size,
 		    enum dma_data_direction direction)
-dma_addr_t
-pci_map_page(struct pci_dev *hwdev, struct page *page,
-		    unsigned long offset, size_t size, int direction)
 void
 dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
 	       enum dma_data_direction direction)
-void
-pci_unmap_page(struct pci_dev *hwdev, dma_addr_t dma_address,
-	       size_t size, int direction)
 
 API for mapping and unmapping for pages.  All the notes and warnings
 for the other mapping APIs apply here.  Also, although the <offset>
@@ -299,9 +266,6 @@ cache width is.
 int
 dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 
-int
-pci_dma_mapping_error(struct pci_dev *hwdev, dma_addr_t dma_addr)
-
 In some circumstances dma_map_single and dma_map_page will fail to create
 a mapping. A driver can check for these errors by testing the returned
 dma address with dma_mapping_error(). A non-zero return value means the mapping
@@ -311,9 +275,6 @@ reduce current DMA mapping usage or delay and try again later).
 	int
 	dma_map_sg(struct device *dev, struct scatterlist *sg,
 		int nents, enum dma_data_direction direction)
-	int
-	pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg,
-		int nents, int direction)
 
 Returns: the number of physical segments mapped (this may be shorter
 than <nents> passed in if some elements of the scatter/gather list are
@@ -353,9 +314,6 @@ accessed sg->address and sg->length as shown above.
 	void
 	dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 		int nhwentries, enum dma_data_direction direction)
-	void
-	pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sg,
-		int nents, int direction)
 
 Unmap the previously mapped scatter/gather list.  All the parameters
 must be the same as those and passed in to the scatter/gather mapping
@@ -365,21 +323,23 @@ Note: <nents> must be the number you passed in, *not* the number of
 physical entries returned.
 
 void
-dma_sync_single(struct device *dev, dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
+dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
+			enum dma_data_direction direction)
 void
-pci_dma_sync_single(struct pci_dev *hwdev, dma_addr_t dma_handle,
-			   size_t size, int direction)
+dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size,
+			   enum dma_data_direction direction)
 void
-dma_sync_sg(struct device *dev, struct scatterlist *sg, int nelems,
-			  enum dma_data_direction direction)
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
+		    enum dma_data_direction direction)
 void
-pci_dma_sync_sg(struct pci_dev *hwdev, struct scatterlist *sg,
-		       int nelems, int direction)
+dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
+		       enum dma_data_direction direction)
 
-Synchronise a single contiguous or scatter/gather mapping.  All the
-parameters must be the same as those passed into the single mapping
-API.
+Synchronise a single contiguous or scatter/gather mapping for the cpu
+and device. With the sync_sg API, all the parameters must be the same
+as those passed into the single mapping API. With the sync_single API,
+you can use dma_handle and size parameters that aren't identical to
+those passed into the single mapping API to do a partial sync.
 
 Notes:  You must do this:
 
@@ -461,9 +421,9 @@ void whizco_dma_map_sg_attrs(struct device *dev, dma_addr_t dma_addr,
 Part II - Advanced dma_ usage
 -----------------------------
 
-Warning: These pieces of the DMA API have no PCI equivalent.  They
-should also not be used in the majority of cases, since they cater for
-unlikely corner cases that don't belong in usual drivers.
+Warning: These pieces of the DMA API should not be used in the
+majority of cases, since they cater for unlikely corner cases that
+don't belong in usual drivers.
 
 If you don't understand how cache line coherency works between a
 processor and an I/O device, you should not be using this part of the
@@ -513,16 +473,6 @@ line, but it will guarantee that one or more cache lines fit exactly
 into the width returned by this call.  It will also always be a power
 of two for easy alignment.
 
-void
-dma_sync_single_range(struct device *dev, dma_addr_t dma_handle,
-		      unsigned long offset, size_t size,
-		      enum dma_data_direction direction)
-
-Does a partial sync, starting at offset and continuing for size.  You
-must be careful to observe the cache alignment and width when doing
-anything like this.  You must also be extra careful about accessing
-memory you intend to sync partially.
-
 void
 dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 	       enum dma_data_direction direction)

Documentation/DocBook/device-drivers.tmpl

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

Documentation/DocBook/deviceiobook.tmpl

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

Documentation/DocBook/mac80211.tmpl

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

Documentation/DocBook/mtdnand.tmpl

@@ -174,7 +174,7 @@
 		</para>
 		<programlisting>
 static struct mtd_info *board_mtd;
-static unsigned long baseaddr;
+static void __iomem *baseaddr;
 		</programlisting>
 		<para>
 			Static example
@@ -182,7 +182,7 @@ static unsigned long baseaddr;
 		<programlisting>
 static struct mtd_info board_mtd;
 static struct nand_chip board_chip;
-static unsigned long baseaddr;
+static void __iomem *baseaddr;
 		</programlisting>
 	</sect1>
 	<sect1 id="Partition_defines">
@@ -283,8 +283,8 @@ int __init board_init (void)
 	}
 
 	/* map physical address */
-	baseaddr = (unsigned long)ioremap(CHIP_PHYSICAL_ADDRESS, 1024);
-	if(!baseaddr){
+	baseaddr = ioremap(CHIP_PHYSICAL_ADDRESS, 1024);
+	if (!baseaddr) {
 		printk("Ioremap to access NAND chip failed\n");
 		err = -EIO;
 		goto out_mtd;
@@ -316,7 +316,7 @@ int __init board_init (void)
 	goto out;
 
 out_ior:
-	iounmap((void *)baseaddr);
+	iounmap(baseaddr);
 out_mtd:
 	kfree (board_mtd);
 out:
@@ -341,7 +341,7 @@ static void __exit board_cleanup (void)
 	nand_release (board_mtd);
 
 	/* unmap physical address */
-	iounmap((void *)baseaddr);
+	iounmap(baseaddr);
 	
 	/* Free the MTD device structure */
 	kfree (board_mtd);
@@ -488,7 +488,7 @@ static void board_select_chip (struct mtd_info *mtd, int chip)
 				The ECC bytes must be placed immidiately after the data
 				bytes in order to make the syndrome generator work. This
 				is contrary to the usual layout used by software ECC. The
-				seperation of data and out of band area is not longer
+				separation of data and out of band area is not longer
 				possible. The nand driver code handles this layout and
 				the remaining free bytes in the oob area are managed by 
 				the autoplacement code. Provide a matching oob-layout
@@ -560,7 +560,7 @@ static void board_select_chip (struct mtd_info *mtd, int chip)
 				bad blocks. They have factory marked good blocks. The marker pattern
 				is erased when the block is erased to be reused. So in case of
 				powerloss before writing the pattern back to the chip this block 
-				would be lost and added to the bad blocks. Therefor we scan the 
+				would be lost and added to the bad blocks. Therefore we scan the 
 				chip(s) when we detect them the first time for good blocks and 
 				store this information in a bad block table before erasing any 
 				of the blocks.
@@ -1094,7 +1094,7 @@ in this page</entry>
 		manufacturers specifications. This applies similar to the spare area. 
 	</para>
 	<para>
-		Therefor NAND aware filesystems must either write in page size chunks
+		Therefore NAND aware filesystems must either write in page size chunks
 		or hold a writebuffer to collect smaller writes until they sum up to 
 		pagesize. Available NAND aware filesystems: JFFS2, YAFFS. 		
 	</para>

Documentation/DocBook/tracepoint.tmpl

@@ -16,6 +16,15 @@
      </address>
     </affiliation>
    </author>
+   <author>
+    <firstname>William</firstname>
+    <surname>Cohen</surname>
+    <affiliation>
+     <address>
+      <email>wcohen@redhat.com</email>
+     </address>
+    </affiliation>
+   </author>
   </authorgroup>
 
   <legalnotice>
@@ -91,4 +100,8 @@
 !Iinclude/trace/events/signal.h
   </chapter>
 
+  <chapter id="block">
+   <title>Block IO</title>
+!Iinclude/trace/events/block.h
+  </chapter>
 </book>

Documentation/DocBook/v4l/common.xml

@@ -1170,7 +1170,7 @@ frames per second. If less than this number of frames is to be
 captured or output, applications can request frame skipping or
 duplicating on the driver side. This is especially useful when using
 the &func-read; or &func-write;, which are not augmented by timestamps
-or sequence counters, and to avoid unneccessary data copying.</para>
+or sequence counters, and to avoid unnecessary data copying.</para>
 
     <para>Finally these ioctls can be used to determine the number of
 buffers used internally by a driver in read/write mode. For

Documentation/DocBook/v4l/io.xml

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

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

@@ -55,7 +55,7 @@ captured or output, applications can request frame skipping or
 duplicating on the driver side. This is especially useful when using
 the <function>read()</function> or <function>write()</function>, which
 are not augmented by timestamps or sequence counters, and to avoid
-unneccessary data copying.</para>
+unnecessary data copying.</para>
 
     <para>Further these ioctls can be used to determine the number of
 buffers used internally by a driver in read/write mode. For

Documentation/DocBook/v4l/vidioc-qbuf.xml

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

Documentation/DocBook/v4l/vidioc-querybuf.xml

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

Documentation/DocBook/v4l/vidioc-reqbufs.xml

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

Documentation/HOWTO

@@ -221,8 +221,8 @@ branches.  These different branches are:
   - main 2.6.x kernel tree
   - 2.6.x.y -stable kernel tree
   - 2.6.x -git kernel patches
-  - 2.6.x -mm kernel patches
   - subsystem specific kernel trees and patches
+  - the 2.6.x -next kernel tree for integration tests
 
 2.6.x kernel tree
 -----------------
@@ -232,9 +232,9 @@ process is as follows:
   - As soon as a new kernel is released a two weeks window is open,
     during this period of time maintainers can submit big diffs to
     Linus, usually the patches that have already been included in the
-    -mm kernel for a few weeks.  The preferred way to submit big changes
+    -next kernel for a few weeks.  The preferred way to submit big changes
     is using git (the kernel's source management tool, more information
-    can be found at http://git.or.cz/) but plain patches are also just
+    can be found at http://git-scm.com/) but plain patches are also just
     fine.
   - After two weeks a -rc1 kernel is released it is now possible to push
     only patches that do not include new features that could affect the
@@ -293,84 +293,43 @@ daily and represent the current state of Linus' tree.  They are more
 experimental than -rc kernels since they are generated automatically
 without even a cursory glance to see if they are sane.
 
-2.6.x -mm kernel patches
-------------------------
-These are experimental kernel patches released by Andrew Morton.  Andrew
-takes all of the different subsystem kernel trees and patches and mushes
-them together, along with a lot of patches that have been plucked from
-the linux-kernel mailing list.  This tree serves as a proving ground for
-new features and patches.  Once a patch has proved its worth in -mm for
-a while Andrew or the subsystem maintainer pushes it on to Linus for
-inclusion in mainline.
-
-It is heavily encouraged that all new patches get tested in the -mm tree
-before they are sent to Linus for inclusion in the main kernel tree.  Code
-which does not make an appearance in -mm before the opening of the merge
-window will prove hard to merge into the mainline.
-
-These kernels are not appropriate for use on systems that are supposed
-to be stable and they are more risky to run than any of the other
-branches.
-
-If you wish to help out with the kernel development process, please test
-and use these kernel releases and provide feedback to the linux-kernel
-mailing list if you have any problems, and if everything works properly.
-
-In addition to all the other experimental patches, these kernels usually
-also contain any changes in the mainline -git kernels available at the
-time of release.
-
-The -mm kernels are not released on a fixed schedule, but usually a few
--mm kernels are released in between each -rc kernel (1 to 3 is common).
-
 Subsystem Specific kernel trees and patches
 -------------------------------------------
-A number of the different kernel subsystem developers expose their
-development trees so that others can see what is happening in the
-different areas of the kernel.  These trees are pulled into the -mm
-kernel releases as described above.
-
-Here is a list of some of the different kernel trees available:
-  git trees:
-    - Kbuild development tree, Sam Ravnborg <sam@ravnborg.org>
-	git.kernel.org:/pub/scm/linux/kernel/git/sam/kbuild.git
-
-    - ACPI development tree, Len Brown <len.brown@intel.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6.git
-
-    - Block development tree, Jens Axboe <jens.axboe@oracle.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/axboe/linux-2.6-block.git
-
-    - DRM development tree, Dave Airlie <airlied@linux.ie>
-	git.kernel.org:/pub/scm/linux/kernel/git/airlied/drm-2.6.git
-
-    - ia64 development tree, Tony Luck <tony.luck@intel.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/aegl/linux-2.6.git
-
-    - infiniband, Roland Dreier <rolandd@cisco.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband.git
-
-    - libata, Jeff Garzik <jgarzik@pobox.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/jgarzik/libata-dev.git
-
-    - network drivers, Jeff Garzik <jgarzik@pobox.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/jgarzik/netdev-2.6.git
-
-    - pcmcia, Dominik Brodowski <linux@dominikbrodowski.net>
-	git.kernel.org:/pub/scm/linux/kernel/git/brodo/pcmcia-2.6.git
-
-    - SCSI, James Bottomley <James.Bottomley@hansenpartnership.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6.git
-
-    - x86, Ingo Molnar <mingo@elte.hu>
-	git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86.git
-
-  quilt trees:
-    - USB, Driver Core, and I2C, Greg Kroah-Hartman <gregkh@suse.de>
-	kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/
+The maintainers of the various kernel subsystems --- and also many
+kernel subsystem developers --- expose their current state of
+development in source repositories.  That way, others can see what is
+happening in the different areas of the kernel.  In areas where
+development is rapid, a developer may be asked to base his submissions
+onto such a subsystem kernel tree so that conflicts between the
+submission and other already ongoing work are avoided.
+
+Most of these repositories are git trees, but there are also other SCMs
+in use, or patch queues being published as quilt series.  Addresses of
+these subsystem repositories are listed in the MAINTAINERS file.  Many
+of them can be browsed at http://git.kernel.org/.
+
+Before a proposed patch is committed to such a subsystem tree, it is
+subject to review which primarily happens on mailing lists (see the
+respective section below).  For several kernel subsystems, this review
+process is tracked with the tool patchwork.  Patchwork offers a web
+interface which shows patch postings, any comments on a patch or
+revisions to it, and maintainers can mark patches as under review,
+accepted, or rejected.  Most of these patchwork sites are listed at
+http://patchwork.kernel.org/ or http://patchwork.ozlabs.org/.
+
+2.6.x -next kernel tree for integration tests
+---------------------------------------------
+Before updates from subsystem trees are merged into the mainline 2.6.x
+tree, they need to be integration-tested.  For this purpose, a special
+testing repository exists into which virtually all subsystem trees are
+pulled on an almost daily basis:
+	http://git.kernel.org/?p=linux/kernel/git/sfr/linux-next.git
+	http://linux.f-seidel.de/linux-next/pmwiki/
+
+This way, the -next kernel gives a summary outlook onto what will be
+expected to go into the mainline kernel at the next merge period.
+Adventurous testers are very welcome to runtime-test the -next kernel.
 
-  Other kernel trees can be found listed at http://git.kernel.org/ and in
-  the MAINTAINERS file.
 
 Bug Reporting
 -------------

Documentation/IO-mapping.txt

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

Documentation/IPMI.txt

@@ -365,6 +365,7 @@ You can change this at module load time (for a module) with:
        regshifts=<shift1>,<shift2>,...
        slave_addrs=<addr1>,<addr2>,...
        force_kipmid=<enable1>,<enable2>,...
+       kipmid_max_busy_us=<ustime1>,<ustime2>,...
        unload_when_empty=[0|1]
 
 Each of these except si_trydefaults is a list, the first item for the
@@ -433,6 +434,7 @@ kernel command line as:
        ipmi_si.regshifts=<shift1>,<shift2>,...
        ipmi_si.slave_addrs=<addr1>,<addr2>,...
        ipmi_si.force_kipmid=<enable1>,<enable2>,...
+       ipmi_si.kipmid_max_busy_us=<ustime1>,<ustime2>,...
 
 It works the same as the module parameters of the same names.
 
@@ -450,6 +452,16 @@ force this thread on or off.  If you force it off and don't have
 interrupts, the driver will run VERY slowly.  Don't blame me,
 these interfaces suck.
 
+Unfortunately, this thread can use a lot of CPU depending on the
+interface's performance.  This can waste a lot of CPU and cause
+various issues with detecting idle CPU and using extra power.  To
+avoid this, the kipmid_max_busy_us sets the maximum amount of time, in
+microseconds, that kipmid will spin before sleeping for a tick.  This
+value sets a balance between performance and CPU waste and needs to be
+tuned to your needs.  Maybe, someday, auto-tuning will be added, but
+that's not a simple thing and even the auto-tuning would need to be
+tuned to the user's desired performance.
+
 The driver supports a hot add and remove of interfaces.  This way,
 interfaces can be added or removed after the kernel is up and running.
 This is done using /sys/modules/ipmi_si/parameters/hotmod, which is a

Documentation/Makefile

 obj-m := DocBook/ accounting/ auxdisplay/ connector/ \
-	filesystems/configfs/ ia64/ networking/ \
-	pcmcia/ spi/ video4linux/ vm/ watchdog/src/
+	filesystems/ filesystems/configfs/ ia64/ laptops/ networking/ \
+	pcmcia/ spi/ timers/ video4linux/ vm/ watchdog/src/

Documentation/RCU/00-INDEX

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

Documentation/RCU/NMI-RCU.txt

@@ -34,7 +34,7 @@ NMI handler.
 		cpu = smp_processor_id();
 		++nmi_count(cpu);
 
-		if (!rcu_dereference(nmi_callback)(regs, cpu))
+		if (!rcu_dereference_sched(nmi_callback)(regs, cpu))
 			default_do_nmi(regs);
 
 		nmi_exit();
@@ -47,12 +47,13 @@ function pointer.  If this handler returns zero, do_nmi() invokes the
 default_do_nmi() function to handle a machine-specific NMI.  Finally,
 preemption is restored.
 
-Strictly speaking, rcu_dereference() is not needed, since this code runs
-only on i386, which does not need rcu_dereference() anyway.  However,
-it is a good documentation aid, particularly for anyone attempting to
-do something similar on Alpha.
+In theory, rcu_dereference_sched() is not needed, since this code runs
+only on i386, which in theory does not need rcu_dereference_sched()
+anyway.  However, in practice it is a good documentation aid, particularly
+for anyone attempting to do something similar on Alpha or on systems
+with aggressive optimizing compilers.
 
-Quick Quiz:  Why might the rcu_dereference() be necessary on Alpha,
+Quick Quiz:  Why might the rcu_dereference_sched() be necessary on Alpha,
 	     given that the code referenced by the pointer is read-only?
 
 
@@ -99,17 +100,21 @@ invoke irq_enter() and irq_exit() on NMI entry and exit, respectively.
 
 Answer to Quick Quiz
 
-	Why might the rcu_dereference() be necessary on Alpha, given
+	Why might the rcu_dereference_sched() be necessary on Alpha, given
 	that the code referenced by the pointer is read-only?
 
 	Answer: The caller to set_nmi_callback() might well have
-		initialized some data that is to be used by the
-		new NMI handler.  In this case, the rcu_dereference()
-		would be needed, because otherwise a CPU that received
-		an NMI just after the new handler was set might see
-		the pointer to the new NMI handler, but the old
-		pre-initialized version of the handler's data.
-
-		More important, the rcu_dereference() makes it clear
-		to someone reading the code that the pointer is being
-		protected by RCU.
+		initialized some data that is to be used by the new NMI
+		handler.  In this case, the rcu_dereference_sched() would
+		be needed, because otherwise a CPU that received an NMI
+		just after the new handler was set might see the pointer
+		to the new NMI handler, but the old pre-initialized
+		version of the handler's data.
+
+		This same sad story can happen on other CPUs when using
+		a compiler with aggressive pointer-value speculation
+		optimizations.
+
+		More important, the rcu_dereference_sched() makes it
+		clear to someone reading the code that the pointer is
+		being protected by RCU-sched.

Documentation/RCU/RTFP.txt

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

Documentation/RCU/checklist.txt

@@ -8,13 +8,12 @@ would cause.  This list is based on experiences reviewing such patches
 over a rather long period of time, but improvements are always welcome!
 
 0.	Is RCU being applied to a read-mostly situation?  If the data
-	structure is updated more than about 10% of the time, then
-	you should strongly consider some other approach, unless
-	detailed performance measurements show that RCU is nonetheless
-	the right tool for the job.  Yes, you might think of RCU
-	as simply cutting overhead off of the readers and imposing it
-	on the writers.  That is exactly why normal uses of RCU will
-	do much more reading than updating.
+	structure is updated more than about 10% of the time, then you
+	should strongly consider some other approach, unless detailed
+	performance measurements show that RCU is nonetheless the right
+	tool for the job.  Yes, RCU does reduce read-side overhead by
+	increasing write-side overhead, which is exactly why normal uses
+	of RCU will do much more reading than updating.
 
 	Another exception is where performance is not an issue, and RCU
 	provides a simpler implementation.  An example of this situation
@@ -35,13 +34,13 @@ over a rather long period of time, but improvements are always welcome!
 
 	If you choose #b, be prepared to describe how you have handled
 	memory barriers on weakly ordered machines (pretty much all of
-	them -- even x86 allows reads to be reordered), and be prepared
-	to explain why this added complexity is worthwhile.  If you
-	choose #c, be prepared to explain how this single task does not
-	become a major bottleneck on big multiprocessor machines (for
-	example, if the task is updating information relating to itself
-	that other tasks can read, there by definition can be no
-	bottleneck).
+	them -- even x86 allows later loads to be reordered to precede
+	earlier stores), and be prepared to explain why this added
+	complexity is worthwhile.  If you choose #c, be prepared to
+	explain how this single task does not become a major bottleneck on
+	big multiprocessor machines (for example, if the task is updating
+	information relating to itself that other tasks can read, there
+	by definition can be no bottleneck).
 
 2.	Do the RCU read-side critical sections make proper use of
 	rcu_read_lock() and friends?  These primitives are needed
@@ -51,8 +50,10 @@ over a rather long period of time, but improvements are always welcome!
 	actuarial risk of your kernel.
 
 	As a rough rule of thumb, any dereference of an RCU-protected
-	pointer must be covered by rcu_read_lock() or rcu_read_lock_bh()
-	or by the appropriate update-side lock.
+	pointer must be covered by rcu_read_lock(), rcu_read_lock_bh(),
+	rcu_read_lock_sched(), or by the appropriate update-side lock.
+	Disabling of preemption can serve as rcu_read_lock_sched(), but
+	is less readable.
 
 3.	Does the update code tolerate concurrent accesses?
 
@@ -62,25 +63,27 @@ over a rather long period of time, but improvements are always welcome!
 	of ways to handle this concurrency, depending on the situation:
 
 	a.	Use the RCU variants of the list and hlist update
-		primitives to add, remove, and replace elements on an
-		RCU-protected list.  Alternatively, use the RCU-protected
-		trees that have been added to the Linux kernel.
+		primitives to add, remove, and replace elements on
+		an RCU-protected list.	Alternatively, use the other
+		RCU-protected data structures that have been added to
+		the Linux kernel.
 
 		This is almost always the best approach.
 
 	b.	Proceed as in (a) above, but also maintain per-element
 		locks (that are acquired by both readers and writers)
 		that guard per-element state.  Of course, fields that
-		the readers refrain from accessing can be guarded by the
-		update-side lock.
+		the readers refrain from accessing can be guarded by
+		some other lock acquired only by updaters, if desired.
 
 		This works quite well, also.
 
 	c.	Make updates appear atomic to readers.  For example,
-		pointer updates to properly aligned fields will appear
-		atomic, as will individual atomic primitives.  Operations
-		performed under a lock and sequences of multiple atomic
-		primitives will -not- appear to be atomic.
+		pointer updates to properly aligned fields will
+		appear atomic, as will individual atomic primitives.
+		Sequences of perations performed under a lock will -not-
+		appear to be atomic to RCU readers, nor will sequences
+		of multiple atomic primitives.
 
 		This can work, but is starting to get a bit tricky.
 
@@ -98,9 +101,9 @@ over a rather long period of time, but improvements are always welcome!
 		a new structure containing updated values.
 
 4.	Weakly ordered CPUs pose special challenges.  Almost all CPUs
-	are weakly ordered -- even i386 CPUs allow reads to be reordered.
-	RCU code must take all of the following measures to prevent
-	memory-corruption problems:
+	are weakly ordered -- even x86 CPUs allow later loads to be
+	reordered to precede earlier stores.  RCU code must take all of
+	the following measures to prevent memory-corruption problems:
 
 	a.	Readers must maintain proper ordering of their memory
 		accesses.  The rcu_dereference() primitive ensures that
@@ -113,14 +116,25 @@ over a rather long period of time, but improvements are always welcome!
 		The rcu_dereference() primitive is also an excellent
 		documentation aid, letting the person reading the code
 		know exactly which pointers are protected by RCU.
-
-		The rcu_dereference() primitive is used by the various
-		"_rcu()" list-traversal primitives, such as the
-		list_for_each_entry_rcu().  Note that it is perfectly
-		legal (if redundant) for update-side code to use
-		rcu_dereference() and the "_rcu()" list-traversal
-		primitives.  This is particularly useful in code
-		that is common to readers and updaters.
+		Please note that compilers can also reorder code, and
+		they are becoming increasingly aggressive about doing
+		just that.  The rcu_dereference() primitive therefore
+		also prevents destructive compiler optimizations.
+
+		The rcu_dereference() primitive is used by the
+		various "_rcu()" list-traversal primitives, such
+		as the list_for_each_entry_rcu().  Note that it is
+		perfectly legal (if redundant) for update-side code to
+		use rcu_dereference() and the "_rcu()" list-traversal
+		primitives.  This is particularly useful in code that
+		is common to readers and updaters.  However, lockdep
+		will complain if you access rcu_dereference() outside
+		of an RCU read-side critical section.  See lockdep.txt
+		to learn what to do about this.
+
+		Of course, neither rcu_dereference() nor the "_rcu()"
+		list-traversal primitives can substitute for a good
+		concurrency design coordinating among multiple updaters.
 
 	b.	If the list macros are being used, the list_add_tail_rcu()
 		and list_add_rcu() primitives must be used in order
@@ -135,11 +149,14 @@ over a rather long period of time, but improvements are always welcome!
 		readers.  Similarly, if the hlist macros are being used,
 		the hlist_del_rcu() primitive is required.
 
-		The list_replace_rcu() primitive may be used to
-		replace an old structure with a new one in an
-		RCU-protected list.
+		The list_replace_rcu() and hlist_replace_rcu() primitives
+		may be used to replace an old structure with a new one
+		in their respective types of RCU-protected lists.
+
+	d.	Rules similar to (4b) and (4c) apply to the "hlist_nulls"
+		type of RCU-protected linked lists.
 
-	d.	Updates must ensure that initialization of a given
+	e.	Updates must ensure that initialization of a given
 		structure happens before pointers to that structure are
 		publicized.  Use the rcu_assign_pointer() primitive
 		when publicizing a pointer to a structure that can
@@ -151,16 +168,31 @@ over a rather long period of time, but improvements are always welcome!
 	it cannot block.
 
 6.	Since synchronize_rcu() can block, it cannot be called from
-	any sort of irq context.  Ditto for synchronize_sched() and
-	synchronize_srcu().
-
-7.	If the updater uses call_rcu(), then the corresponding readers
-	must use rcu_read_lock() and rcu_read_unlock().  If the updater
-	uses call_rcu_bh(), then the corresponding readers must use
-	rcu_read_lock_bh() and rcu_read_unlock_bh().  If the updater
-	uses call_rcu_sched(), then the corresponding readers must
-	disable preemption.  Mixing things up will result in confusion
-	and broken kernels.
+	any sort of irq context.  The same rule applies for
+	synchronize_rcu_bh(), synchronize_sched(), synchronize_srcu(),
+	synchronize_rcu_expedited(), synchronize_rcu_bh_expedited(),
+	synchronize_sched_expedite(), and synchronize_srcu_expedited().
+
+	The expedited forms of these primitives have the same semantics
+	as the non-expedited forms, but expediting is both expensive
+	and unfriendly to real-time workloads.	Use of the expedited
+	primitives should be restricted to rare configuration-change
+	operations that would not normally be undertaken while a real-time
+	workload is running.
+
+7.	If the updater uses call_rcu() or synchronize_rcu(), then the
+	corresponding readers must use rcu_read_lock() and
+	rcu_read_unlock().  If the updater uses call_rcu_bh() or
+	synchronize_rcu_bh(), then the corresponding readers must
+	use rcu_read_lock_bh() and rcu_read_unlock_bh().  If the
+	updater uses call_rcu_sched() or synchronize_sched(), then
+	the corresponding readers must disable preemption, possibly
+	by calling rcu_read_lock_sched() and rcu_read_unlock_sched().
+	If the updater uses synchronize_srcu(), the the corresponding
+	readers must use srcu_read_lock() and srcu_read_unlock(),
+	and with the same srcu_struct.	The rules for the expedited
+	primitives are the same as for their non-expedited counterparts.
+	Mixing things up will result in confusion and broken kernels.
 
 	One exception to this rule: rcu_read_lock() and rcu_read_unlock()
 	may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh()
@@ -212,6 +244,8 @@ over a rather long period of time, but improvements are always welcome!
 	e.	Periodically invoke synchronize_rcu(), permitting a limited
 		number of updates per grace period.
 
+	The same cautions apply to call_rcu_bh() and call_rcu_sched().
+
 9.	All RCU list-traversal primitives, which include
 	rcu_dereference(), list_for_each_entry_rcu(),
 	list_for_each_continue_rcu(), and list_for_each_safe_rcu(),
@@ -219,17 +253,21 @@ over a rather long period of time, but improvements are always welcome!
 	must be protected by appropriate update-side locks.  RCU
 	read-side critical sections are delimited by rcu_read_lock()
 	and rcu_read_unlock(), or by similar primitives such as
-	rcu_read_lock_bh() and rcu_read_unlock_bh().
+	rcu_read_lock_bh() and rcu_read_unlock_bh(), in which case
+	the matching rcu_dereference() primitive must be used in order
+	to keep lockdep happy, in this case, rcu_dereference_bh().
 
 	The reason that it is permissible to use RCU list-traversal
 	primitives when the update-side lock is held is that doing so
 	can be quite helpful in reducing code bloat when common code is
-	shared between readers and updaters.
+	shared between readers and updaters.  Additional primitives
+	are provided for this case, as discussed in lockdep.txt.
 
 10.	Conversely, if you are in an RCU read-side critical section,
 	and you don't hold the appropriate update-side lock, you -must-
 	use the "_rcu()" variants of the list macros.  Failing to do so
-	will break Alpha and confuse people reading your code.
+	will break Alpha, cause aggressive compilers to generate bad code,
+	and confuse people trying to read your code.
 
 11.	Note that synchronize_rcu() -only- guarantees to wait until
 	all currently executing rcu_read_lock()-protected RCU read-side
@@ -239,15 +277,21 @@ over a rather long period of time, but improvements are always welcome!
 	rcu_read_lock()-protected read-side critical sections, do -not-
 	use synchronize_rcu().
 
-	If you want to wait for some of these other things, you might
-	instead need to use synchronize_irq() or synchronize_sched().
+	Similarly, disabling preemption is not an acceptable substitute
+	for rcu_read_lock().  Code that attempts to use preemption
+	disabling where it should be using rcu_read_lock() will break
+	in real-time kernel builds.
+
+	If you want to wait for interrupt handlers, NMI handlers, and
+	code under the influence of preempt_disable(), you instead
+	need to use synchronize_irq() or synchronize_sched().
 
 12.	Any lock acquired by an RCU callback must be acquired elsewhere
 	with softirq disabled, e.g., via spin_lock_irqsave(),
 	spin_lock_bh(), etc.  Failing to disable irq on a given
-	acquisition of that lock will result in deadlock as soon as the
-	RCU callback happens to interrupt that acquisition's critical
-	section.
+	acquisition of that lock will result in deadlock as soon as
+	the RCU softirq handler happens to run your RCU callback while
+	interrupting that acquisition's critical section.
 
 13.	RCU callbacks can be and are executed in parallel.  In many cases,
 	the callback code simply wrappers around kfree(), so that this
@@ -265,29 +309,30 @@ over a rather long period of time, but improvements are always welcome!
 	not the case, a self-spawning RCU callback would prevent the
 	victim CPU from ever going offline.)
 
-14.	SRCU (srcu_read_lock(), srcu_read_unlock(), and synchronize_srcu())
-	may only be invoked from process context.  Unlike other forms of
-	RCU, it -is- permissible to block in an SRCU read-side critical
-	section (demarked by srcu_read_lock() and srcu_read_unlock()),
-	hence the "SRCU": "sleepable RCU".  Please note that if you
-	don't need to sleep in read-side critical sections, you should
-	be using RCU rather than SRCU, because RCU is almost always
-	faster and easier to use than is SRCU.
+14.	SRCU (srcu_read_lock(), srcu_read_unlock(), srcu_dereference(),
+	synchronize_srcu(), and synchronize_srcu_expedited()) may only
+	be invoked from process context.  Unlike other forms of RCU, it
+	-is- permissible to block in an SRCU read-side critical section
+	(demarked by srcu_read_lock() and srcu_read_unlock()), hence the
+	"SRCU": "sleepable RCU".  Please note that if you don't need
+	to sleep in read-side critical sections, you should be using
+	RCU rather than SRCU, because RCU is almost always faster and
+	easier to use than is SRCU.
 
 	Also unlike other forms of RCU, explicit initialization
 	and cleanup is required via init_srcu_struct() and
 	cleanup_srcu_struct().	These are passed a "struct srcu_struct"
 	that defines the scope of a given SRCU domain.	Once initialized,
 	the srcu_struct is passed to srcu_read_lock(), srcu_read_unlock()
-	and synchronize_srcu().  A given synchronize_srcu() waits only
-	for SRCU read-side critical sections governed by srcu_read_lock()
-	and srcu_read_unlock() calls that have been passd the same
-	srcu_struct.  This property is what makes sleeping read-side
-	critical sections tolerable -- a given subsystem delays only
-	its own updates, not those of other subsystems using SRCU.
-	Therefore, SRCU is less prone to OOM the system than RCU would
-	be if RCU's read-side critical sections were permitted to
-	sleep.
+	synchronize_srcu(), and synchronize_srcu_expedited().  A given
+	synchronize_srcu() waits only for SRCU read-side critical
+	sections governed by srcu_read_lock() and srcu_read_unlock()
+	calls that have been passed the same srcu_struct.  This property
+	is what makes sleeping read-side critical sections tolerable --
+	a given subsystem delays only its own updates, not those of other
+	subsystems using SRCU.	Therefore, SRCU is less prone to OOM the
+	system than RCU would be if RCU's read-side critical sections
+	were permitted to sleep.
 
 	The ability to sleep in read-side critical sections does not
 	come for free.	First, corresponding srcu_read_lock() and
@@ -300,8 +345,8 @@ over a rather long period of time, but improvements are always welcome!
 	requiring SRCU's read-side deadlock immunity or low read-side
 	realtime latency.
 
-	Note that, rcu_assign_pointer() and rcu_dereference() relate to
-	SRCU just as they do to other forms of RCU.
+	Note that, rcu_assign_pointer() relates to SRCU just as they do
+	to other forms of RCU.
 
 15.	The whole point of call_rcu(), synchronize_rcu(), and friends
 	is to wait until all pre-existing readers have finished before
@@ -311,12 +356,12 @@ over a rather long period of time, but improvements are always welcome!
 	destructive operation, and -only- -then- invoke call_rcu(),
 	synchronize_rcu(), or friends.
 
-	Because these primitives only wait for pre-existing readers,
-	it is the caller's responsibility to guarantee safety to
-	any subsequent readers.
+	Because these primitives only wait for pre-existing readers, it
+	is the caller's responsibility to guarantee that any subsequent
+	readers will execute safely.
 
-16.	The various RCU read-side primitives do -not- contain memory
-	barriers.  The CPU (and in some cases, the compiler) is free
-	to reorder code into and out of RCU read-side critical sections.
-	It is the responsibility of the RCU update-side primitives to
-	deal with this.
+16.	The various RCU read-side primitives do -not- necessarily contain
+	memory barriers.  You should therefore plan for the CPU
+	and the compiler to freely reorder code into and out of RCU
+	read-side critical sections.  It is the responsibility of the
+	RCU update-side primitives to deal with this.

Documentation/RCU/lockdep.txt

+RCU and lockdep checking
+
+All flavors of RCU have lockdep checking available, so that lockdep is
+aware of when each task enters and leaves any flavor of RCU read-side
+critical section.  Each flavor of RCU is tracked separately (but note
+that this is not the case in 2.6.32 and earlier).  This allows lockdep's
+tracking to include RCU state, which can sometimes help when debugging
+deadlocks and the like.
+
+In addition, RCU provides the following primitives that check lockdep's
+state:
+
+	rcu_read_lock_held() for normal RCU.
+	rcu_read_lock_bh_held() for RCU-bh.
+	rcu_read_lock_sched_held() for RCU-sched.
+	srcu_read_lock_held() for SRCU.
+
+These functions are conservative, and will therefore return 1 if they
+aren't certain (for example, if CONFIG_DEBUG_LOCK_ALLOC is not set).
+This prevents things like WARN_ON(!rcu_read_lock_held()) from giving false
+positives when lockdep is disabled.
+
+In addition, a separate kernel config parameter CONFIG_PROVE_RCU enables
+checking of rcu_dereference() primitives:
+
+	rcu_dereference(p):
+		Check for RCU read-side critical section.
+	rcu_dereference_bh(p):
+		Check for RCU-bh read-side critical section.
+	rcu_dereference_sched(p):
+		Check for RCU-sched read-side critical section.
+	srcu_dereference(p, sp):
+		Check for SRCU read-side critical section.
+	rcu_dereference_check(p, c):
+		Use explicit check expression "c".  This is useful in
+		code that is invoked by both readers and updaters.
+	rcu_dereference_raw(p)
+		Don't check.  (Use sparingly, if at all.)
+	rcu_dereference_protected(p, c):
+		Use explicit check expression "c", and omit all barriers
+		and compiler constraints.  This is useful when the data
+		structure cannot change, for example, in code that is
+		invoked only by updaters.
+	rcu_access_pointer(p):
+		Return the value of the pointer and omit all barriers,
+		but retain the compiler constraints that prevent duplicating
+		or coalescsing.  This is useful when when testing the
+		value of the pointer itself, for example, against NULL.
+
+The rcu_dereference_check() check expression can be any boolean
+expression, but would normally include one of the rcu_read_lock_held()
+family of functions and a lockdep expression.  However, any boolean
+expression can be used.  For a moderately ornate example, consider
+the following:
+
+	file = rcu_dereference_check(fdt->fd[fd],
+				     rcu_read_lock_held() ||
+				     lockdep_is_held(&files->file_lock) ||
+				     atomic_read(&files->count) == 1);
+
+This expression picks up the pointer "fdt->fd[fd]" in an RCU-safe manner,
+and, if CONFIG_PROVE_RCU is configured, verifies that this expression
+is used in:
+
+1.	An RCU read-side critical section, or
+2.	with files->file_lock held, or
+3.	on an unshared files_struct.
+
+In case (1), the pointer is picked up in an RCU-safe manner for vanilla
+RCU read-side critical sections, in case (2) the ->file_lock prevents
+any change from taking place, and finally, in case (3) the current task
+is the only task accessing the file_struct, again preventing any change
+from taking place.  If the above statement was invoked only from updater
+code, it could instead be written as follows:
+
+	file = rcu_dereference_protected(fdt->fd[fd],
+					 lockdep_is_held(&files->file_lock) ||
+					 atomic_read(&files->count) == 1);
+
+This would verify cases #2 and #3 above, and furthermore lockdep would
+complain if this was used in an RCU read-side critical section unless one
+of these two cases held.  Because rcu_dereference_protected() omits all
+barriers and compiler constraints, it generates better code than do the
+other flavors of rcu_dereference().  On the other hand, it is illegal
+to use rcu_dereference_protected() if either the RCU-protected pointer
+or the RCU-protected data that it points to can change concurrently.
+
+There are currently only "universal" versions of the rcu_assign_pointer()
+and RCU list-/tree-traversal primitives, which do not (yet) check for
+being in an RCU read-side critical section.  In the future, separate
+versions of these primitives might be created.

Documentation/RCU/rcu.txt

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

Documentation/RCU/stallwarn.txt

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

Documentation/RCU/torture.txt

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

Documentation/RCU/whatisRCU.txt

@@ -323,14 +323,17 @@ used as follows:
 	Defer			Protect
 
 a.	synchronize_rcu()	rcu_read_lock() / rcu_read_unlock()
-	call_rcu()
+	call_rcu()		rcu_dereference()
 
 b.	call_rcu_bh()		rcu_read_lock_bh() / rcu_read_unlock_bh()
+				rcu_dereference_bh()
 
-c.	synchronize_sched()	preempt_disable() / preempt_enable()
+c.	synchronize_sched()	rcu_read_lock_sched() / rcu_read_unlock_sched()
+				preempt_disable() / preempt_enable()
 				local_irq_save() / local_irq_restore()
 				hardirq enter / hardirq exit
 				NMI enter / NMI exit
+				rcu_dereference_sched()
 
 These three mechanisms are used as follows:
 
@@ -780,9 +783,8 @@ Linux-kernel source code, but it helps to have a full list of the
 APIs, since there does not appear to be a way to categorize them
 in docbook.  Here is the list, by category.
 
-RCU pointer/list traversal:
+RCU list traversal:
 
-	rcu_dereference
 	list_for_each_entry_rcu
 	hlist_for_each_entry_rcu
 	hlist_nulls_for_each_entry_rcu
@@ -808,7 +810,7 @@ RCU:	Critical sections	Grace period		Barrier
 
 	rcu_read_lock		synchronize_net		rcu_barrier
 	rcu_read_unlock		synchronize_rcu
-				synchronize_rcu_expedited
+	rcu_dereference		synchronize_rcu_expedited
 				call_rcu
 
 
@@ -816,7 +818,7 @@ bh:	Critical sections	Grace period		Barrier
 
 	rcu_read_lock_bh	call_rcu_bh		rcu_barrier_bh
 	rcu_read_unlock_bh	synchronize_rcu_bh
-				synchronize_rcu_bh_expedited
+	rcu_dereference_bh	synchronize_rcu_bh_expedited
 
 
 sched:	Critical sections	Grace period		Barrier
@@ -825,17 +827,25 @@ sched:	Critical sections	Grace period		Barrier
 	rcu_read_unlock_sched	call_rcu_sched
 	[preempt_disable]	synchronize_sched_expedited
 	[and friends]
+	rcu_dereference_sched
 
 
 SRCU:	Critical sections	Grace period		Barrier
 
 	srcu_read_lock		synchronize_srcu	N/A
 	srcu_read_unlock	synchronize_srcu_expedited
+	srcu_dereference
 
 SRCU:	Initialization/cleanup
 	init_srcu_struct
 	cleanup_srcu_struct
 
+All:  lockdep-checked RCU-protected pointer access
+
+	rcu_dereference_check
+	rcu_dereference_protected
+	rcu_access_pointer
+
 See the comment headers in the source code (or the docbook generated
 from them) for more information.
 

Documentation/SubmitChecklist

@@ -9,10 +9,14 @@ Documentation/SubmittingPatches and elsewhere regarding submitting Linux
 kernel patches.
 
 
-1: Builds cleanly with applicable or modified CONFIG options =y, =m, and
+1: If you use a facility then #include the file that defines/declares
+   that facility.  Don't depend on other header files pulling in ones
+   that you use.
+
+2: Builds cleanly with applicable or modified CONFIG options =y, =m, and
    =n.  No gcc warnings/errors, no linker warnings/errors.
 
-2: Passes allnoconfig, allmodconfig
+2b: Passes allnoconfig, allmodconfig
 
 3: Builds on multiple CPU architectures by using local cross-compile tools
    or some other build farm.

Documentation/arm/Samsung-S3C24XX/CPUfreq.txt

@@ -14,8 +14,8 @@ Introduction
  how the clocks are arranged. The first implementation used as single
  PLL to feed the ARM, memory and peripherals via a series of dividers
  and muxes and this is the implementation that is documented here. A
- newer version where there is a seperate PLL and clock divider for the
- ARM core is available as a seperate driver.
+ newer version where there is a separate PLL and clock divider for the
+ ARM core is available as a separate driver.
 
 
 Layout

Documentation/arm/Samsung/Overview.txt

+		Samsung ARM Linux Overview
+		==========================
+
+Introduction
+------------
+
+  The Samsung range of ARM SoCs spans many similar devices, from the initial
+  ARM9 through to the newest ARM cores. This document shows an overview of
+  the current kernel support, how to use it and where to find the code
+  that supports this.
+
+  The currently supported SoCs are:
+
+  - S3C24XX: See Documentation/arm/Samsung-S3C24XX/Overview.txt for full list
+  - S3C64XX: S3C6400 and S3C6410
+  - S5PC6440
+
+  S5PC100 and S5PC110 support is currently being merged
+
+
+S3C24XX Systems
+---------------
+
+  There is still documentation in Documnetation/arm/Samsung-S3C24XX/ which
+  deals with the architecture and drivers specific to these devices.
+
+  See Documentation/arm/Samsung-S3C24XX/Overview.txt for more information
+  on the implementation details and specific support.
+
+
+Configuration
+-------------
+
+  A number of configurations are supplied, as there is no current way of
+  unifying all the SoCs into one kernel.
+
+  s5p6440_defconfig - S5P6440 specific default configuration
+  s5pc100_defconfig - S5PC100 specific default configuration
+
+
+Layout
+------
+
+  The directory layout is currently being restructured, and consists of
+  several platform directories and then the machine specific directories
+  of the CPUs being built for.
+
+  plat-samsung provides the base for all the implementations, and is the
+  last in the line of include directories that are processed for the build
+  specific information. It contains the base clock, GPIO and device definitions
+  to get the system running.
+
+  plat-s3c is the s3c24xx/s3c64xx platform directory, although it is currently
+  involved in other builds this will be phased out once the relevant code is
+  moved elsewhere.
+
+  plat-s3c24xx is for s3c24xx specific builds, see the S3C24XX docs.
+
+  plat-s3c64xx is for the s3c64xx specific bits, see the S3C24XX docs.
+
+  plat-s5p is for s5p specific builds, more to be added.
+
+
+  [ to finish ]
+
+
+Port Contributors
+-----------------
+
+  Ben Dooks (BJD)
+  Vincent Sanders
+  Herbert Potzl
+  Arnaud Patard (RTP)
+  Roc Wu
+  Klaus Fetscher
+  Dimitry Andric
+  Shannon Holland
+  Guillaume Gourat (NexVision)
+  Christer Weinigel (wingel) (Acer N30)
+  Lucas Correia Villa Real (S3C2400 port)
+
+
+Document Author
+---------------
+
+Copyright 2009-2010 Ben Dooks <ben-linux@fluff.org>

Documentation/arm/Samsung/clksrc-change-registers.awk

+#!/usr/bin/awk -f
+#
+# Copyright 2010 Ben Dooks <ben-linux@fluff.org>
+#
+# Released under GPLv2
+
+# example usage
+# ./clksrc-change-registers.awk arch/arm/plat-s5pc1xx/include/plat/regs-clock.h < src > dst
+
+function extract_value(s)
+{
+    eqat = index(s, "=")
+    comat = index(s, ",")
+    return substr(s, eqat+2, (comat-eqat)-2)
+}
+
+function remove_brackets(b)
+{
+    return substr(b, 2, length(b)-2)
+}
+
+function splitdefine(l, p)
+{
+    r = split(l, tp)
+
+    p[0] = tp[2]
+    p[1] = remove_brackets(tp[3])
+}
+
+function find_length(f)
+{
+    if (0)
+	printf "find_length " f "\n" > "/dev/stderr"
+
+    if (f ~ /0x1/)
+	return 1
+    else if (f ~ /0x3/)
+	return 2
+    else if (f ~ /0x7/)
+	return 3
+    else if (f ~ /0xf/)
+	return 4
+
+    printf "unknown legnth " f "\n" > "/dev/stderr"
+    exit
+}
+
+function find_shift(s)
+{
+    id = index(s, "<")
+    if (id <= 0) {
+	printf "cannot find shift " s "\n" > "/dev/stderr"
+	exit
+    }
+
+    return substr(s, id+2)
+}
+
+
+BEGIN {
+    if (ARGC < 2) {
+	print "too few arguments" > "/dev/stderr"
+	exit
+    }
+
+# read the header file and find the mask values that we will need
+# to replace and create an associative array of values
+
+    while (getline line < ARGV[1] > 0) {
+	if (line ~ /\#define.*_MASK/ &&
+	    !(line ~ /S5PC100_EPLL_MASK/) &&
+	    !(line ~ /USB_SIG_MASK/)) {
+	    splitdefine(line, fields)
+	    name = fields[0]
+	    if (0)
+		printf "MASK " line "\n" > "/dev/stderr"
+	    dmask[name,0] = find_length(fields[1])
+	    dmask[name,1] = find_shift(fields[1])
+	    if (0)
+		printf "=> '" name "' LENGTH=" dmask[name,0] " SHIFT=" dmask[name,1] "\n" > "/dev/stderr"
+	} else {
+	}
+    }
+
+    delete ARGV[1]
+}
+
+/clksrc_clk.*=.*{/ {
+    shift=""
+    mask=""
+    divshift=""
+    reg_div=""
+    reg_src=""
+    indent=1
+
+    print $0
+
+    for(; indent >= 1;) {
+	if ((getline line) <= 0) {
+	    printf "unexpected end of file" > "/dev/stderr"
+	    exit 1;
+	}
+
+	if (line ~ /\.shift/) {
+	    shift = extract_value(line)
+	} else if (line ~ /\.mask/) {
+	    mask = extract_value(line)
+	} else if (line ~ /\.reg_divider/) {
+	    reg_div = extract_value(line)
+	} else if (line ~ /\.reg_source/) {
+	    reg_src = extract_value(line)
+	} else if (line ~ /\.divider_shift/) {
+	    divshift = extract_value(line)
+	} else if (line ~ /{/) {
+		indent++
+		print line
+	    } else if (line ~ /}/) {
+	    indent--
+
+	    if (indent == 0) {
+		if (0) {
+		    printf "shift '" shift   "' ='" dmask[shift,0] "'\n" > "/dev/stderr"
+		    printf "mask  '" mask    "'\n" > "/dev/stderr"
+		    printf "dshft '" divshift "'\n" > "/dev/stderr"
+		    printf "rdiv  '" reg_div "'\n" > "/dev/stderr"
+		    printf "rsrc  '" reg_src "'\n" > "/dev/stderr"
+		}
+
+		generated = mask
+		sub(reg_src, reg_div, generated)
+
+		if (0) {
+		    printf "/* rsrc " reg_src " */\n"
+		    printf "/* rdiv " reg_div " */\n"
+		    printf "/* shift " shift " */\n"
+		    printf "/* mask " mask " */\n"
+		    printf "/* generated " generated " */\n"
+		}
+
+		if (reg_div != "") {
+		    printf "\t.reg_div = { "
+		    printf ".reg = " reg_div ", "
+		    printf ".shift = " dmask[generated,1] ", "
+		    printf ".size = " dmask[generated,0] ", "
+		    printf "},\n"
+		}
+
+		printf "\t.reg_src = { "
+		printf ".reg = " reg_src ", "
+		printf ".shift = " dmask[mask,1] ", "
+		printf ".size = " dmask[mask,0] ", "
+
+		printf "},\n"
+
+	    }
+
+	    print line
+	} else {
+	    print line
+	}
+
+	if (0)
+	    printf indent ":" line "\n" > "/dev/stderr"
+    }
+}
+
+// && ! /clksrc_clk.*=.*{/ { print $0 }

Documentation/arm/memory.txt

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

Documentation/block/00-INDEX

 00-INDEX
 	- This file
-as-iosched.txt
-	- Anticipatory IO scheduler
 barrier.txt
 	- I/O Barriers
 biodoc.txt

Documentation/block/as-iosched.txt

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

Documentation/block/biodoc.txt

@@ -186,7 +186,7 @@ a virtual address mapping (unlike the earlier scheme of virtual address
 do not have a corresponding kernel virtual address space mapping) and
 low-memory pages.
 
-Note: Please refer to Documentation/DMA-mapping.txt for a discussion
+Note: Please refer to Documentation/PCI/PCI-DMA-mapping.txt for a discussion
 on PCI high mem DMA aspects and mapping of scatter gather lists, and support
 for 64 bit PCI.
 
@@ -1162,8 +1162,8 @@ where a driver received a request ala this before:
 
 As mentioned, there is no virtual mapping of a bio. For DMA, this is
 not a problem as the driver probably never will need a virtual mapping.
-Instead it needs a bus mapping (pci_map_page for a single segment or
-use blk_rq_map_sg for scatter gather) to be able to ship it to the driver. For
+Instead it needs a bus mapping (dma_map_page for a single segment or
+use dma_map_sg for scatter gather) to be able to ship it to the driver. For
 PIO drivers (or drivers that need to revert to PIO transfer once in a
 while (IDE for example)), where the CPU is doing the actual data
 transfer a virtual mapping is needed. If the driver supports highmem I/O,

Documentation/block/queue-sysfs.txt

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

Documentation/cachetlb.txt

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

Documentation/cdrom/ide-cd

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

Documentation/cgroups/cgroup_event_listener.c

+/*
+ * cgroup_event_listener.c - Simple listener of cgroup events
+ *
+ * Copyright (C) Kirill A. Shutemov <kirill@shutemov.name>
+ */
+
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <libgen.h>
+#include <limits.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/eventfd.h>
+
+#define USAGE_STR "Usage: cgroup_event_listener <path-to-control-file> <args>\n"
+
+int main(int argc, char **argv)
+{
+	int efd = -1;
+	int cfd = -1;
+	int event_control = -1;
+	char event_control_path[PATH_MAX];
+	char line[LINE_MAX];
+	int ret;
+
+	if (argc != 3) {
+		fputs(USAGE_STR, stderr);
+		return 1;
+	}
+
+	cfd = open(argv[1], O_RDONLY);
+	if (cfd == -1) {
+		fprintf(stderr, "Cannot open %s: %s\n", argv[1],
+				strerror(errno));
+		goto out;
+	}
+
+	ret = snprintf(event_control_path, PATH_MAX, "%s/cgroup.event_control",
+			dirname(argv[1]));
+	if (ret >= PATH_MAX) {
+		fputs("Path to cgroup.event_control is too long\n", stderr);
+		goto out;
+	}
+
+	event_control = open(event_control_path, O_WRONLY);
+	if (event_control == -1) {
+		fprintf(stderr, "Cannot open %s: %s\n", event_control_path,
+				strerror(errno));
+		goto out;
+	}
+
+	efd = eventfd(0, 0);
+	if (efd == -1) {
+		perror("eventfd() failed");
+		goto out;
+	}
+
+	ret = snprintf(line, LINE_MAX, "%d %d %s", efd, cfd, argv[2]);
+	if (ret >= LINE_MAX) {
+		fputs("Arguments string is too long\n", stderr);
+		goto out;
+	}
+
+	ret = write(event_control, line, strlen(line) + 1);
+	if (ret == -1) {
+		perror("Cannot write to cgroup.event_control");
+		goto out;
+	}
+
+	while (1) {
+		uint64_t result;
+
+		ret = read(efd, &result, sizeof(result));
+		if (ret == -1) {
+			if (errno == EINTR)
+				continue;
+			perror("Cannot read from eventfd");
+			break;
+		}
+		assert(ret == sizeof(result));
+
+		ret = access(event_control_path, W_OK);
+		if ((ret == -1) && (errno == ENOENT)) {
+				puts("The cgroup seems to have removed.");
+				ret = 0;
+				break;
+		}
+
+		if (ret == -1) {
+			perror("cgroup.event_control "
+					"is not accessable any more");
+			break;
+		}
+
+		printf("%s %s: crossed\n", argv[1], argv[2]);
+	}
+
+out:
+	if (efd >= 0)
+		close(efd);
+	if (event_control >= 0)
+		close(event_control);
+	if (cfd >= 0)
+		close(cfd);
+
+	return (ret != 0);
+}

Documentation/cgroups/cgroups.txt

@@ -22,6 +22,8 @@ CONTENTS:
 2. Usage Examples and Syntax
   2.1 Basic Usage
   2.2 Attaching processes
+  2.3 Mounting hierarchies by name
+  2.4 Notification API
 3. Kernel API
   3.1 Overview
   3.2 Synchronization
@@ -233,8 +235,7 @@ containing the following files describing that cgroup:
  - cgroup.procs: list of tgids in the cgroup.  This list is not
    guaranteed to be sorted or free of duplicate tgids, and userspace
    should sort/uniquify the list if this property is required.
-   Writing a tgid into this file moves all threads with that tgid into
-   this cgroup.
+   This is a read-only file, for now.
  - 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)
@@ -434,6 +435,25 @@ you give a subsystem a name.
 The name of the subsystem appears as part of the hierarchy description
 in /proc/mounts and /proc/<pid>/cgroups.
 
+2.4 Notification API
+--------------------
+
+There is mechanism which allows to get notifications about changing
+status of a cgroup.
+
+To register new notification handler you need:
+ - create a file descriptor for event notification using eventfd(2);
+ - open a control file to be monitored (e.g. memory.usage_in_bytes);
+ - write "<event_fd> <control_fd> <args>" to cgroup.event_control.
+   Interpretation of args is defined by control file implementation;
+
+eventfd will be woken up by control file implementation or when the
+cgroup is removed.
+
+To unregister notification handler just close eventfd.
+
+NOTE: Support of notifications should be implemented for the control
+file. See documentation for the subsystem.
 
 3. Kernel API
 =============
@@ -488,6 +508,11 @@ Each subsystem should:
 - add an entry in linux/cgroup_subsys.h
 - define a cgroup_subsys object called <name>_subsys
 
+If a subsystem can be compiled as a module, it should also have in its
+module initcall a call to cgroup_load_subsys(), and in its exitcall a
+call to cgroup_unload_subsys(). It should also set its_subsys.module =
+THIS_MODULE in its .c file.
+
 Each subsystem may export the following methods. The only mandatory
 methods are create/destroy. Any others that are null are presumed to
 be successful no-ops.
@@ -536,10 +561,21 @@ returns an error, this will abort the attach operation.  If a NULL
 task is passed, then a successful result indicates that *any*
 unspecified task can be moved into the cgroup. Note that this isn't
 called on a fork. If this method returns 0 (success) then this should
-remain valid while the caller holds cgroup_mutex. If threadgroup is
+remain valid while the caller holds cgroup_mutex and it is ensured that either
+attach() or cancel_attach() will be called in future. If threadgroup is
 true, then a successful result indicates that all threads in the given
 thread's threadgroup can be moved together.
 
+void cancel_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+	       struct task_struct *task, bool threadgroup)
+(cgroup_mutex held by caller)
+
+Called when a task attach operation has failed after can_attach() has succeeded.
+A subsystem whose can_attach() has some side-effects should provide this
+function, so that the subsytem can implement a rollback. If not, not necessary.
+This will be called only about subsystems whose can_attach() operation have
+succeeded.
+
 void attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 	    struct cgroup *old_cgrp, struct task_struct *task,
 	    bool threadgroup)

Documentation/cgroups/cpusets.txt

@@ -168,20 +168,20 @@ Each cpuset is represented by a directory in the cgroup file system
 containing (on top of the standard cgroup files) the following
 files describing that cpuset:
 
- - cpus: list of CPUs in that cpuset
- - mems: list of Memory Nodes in that cpuset
- - memory_migrate flag: if set, move pages to cpusets nodes
- - cpu_exclusive flag: is cpu placement exclusive?
- - mem_exclusive flag: is memory placement exclusive?
- - mem_hardwall flag:  is memory allocation hardwalled
- - memory_pressure: measure of how much paging pressure in cpuset
- - memory_spread_page flag: if set, spread page cache evenly on allowed nodes
- - memory_spread_slab flag: if set, spread slab cache evenly on allowed nodes
- - sched_load_balance flag: if set, load balance within CPUs on that cpuset
- - sched_relax_domain_level: the searching range when migrating tasks
+ - cpuset.cpus: list of CPUs in that cpuset
+ - cpuset.mems: list of Memory Nodes in that cpuset
+ - cpuset.memory_migrate flag: if set, move pages to cpusets nodes
+ - cpuset.cpu_exclusive flag: is cpu placement exclusive?
+ - cpuset.mem_exclusive flag: is memory placement exclusive?
+ - cpuset.mem_hardwall flag:  is memory allocation hardwalled
+ - cpuset.memory_pressure: measure of how much paging pressure in cpuset
+ - cpuset.memory_spread_page flag: if set, spread page cache evenly on allowed nodes
+ - cpuset.memory_spread_slab flag: if set, spread slab cache evenly on allowed nodes
+ - cpuset.sched_load_balance flag: if set, load balance within CPUs on that cpuset
+ - cpuset.sched_relax_domain_level: the searching range when migrating tasks
 
 In addition, the root cpuset only has the following file:
- - memory_pressure_enabled flag: compute memory_pressure?
+ - cpuset.memory_pressure_enabled flag: compute memory_pressure?
 
 New cpusets are created using the mkdir system call or shell
 command.  The properties of a cpuset, such as its flags, allowed
@@ -229,7 +229,7 @@ If a cpuset is cpu or mem exclusive, no other cpuset, other than
 a direct ancestor or descendant, may share any of the same CPUs or
 Memory Nodes.
 
-A cpuset that is mem_exclusive *or* mem_hardwall is "hardwalled",
+A cpuset that is cpuset.mem_exclusive *or* cpuset.mem_hardwall is "hardwalled",
 i.e. it restricts kernel allocations for page, buffer and other data
 commonly shared by the kernel across multiple users.  All cpusets,
 whether hardwalled or not, restrict allocations of memory for user
@@ -304,15 +304,15 @@ times 1000.
 ---------------------------
 There are two boolean flag files per cpuset that control where the
 kernel allocates pages for the file system buffers and related in
-kernel data structures.  They are called 'memory_spread_page' and
-'memory_spread_slab'.
+kernel data structures.  They are called 'cpuset.memory_spread_page' and
+'cpuset.memory_spread_slab'.
 
-If the per-cpuset boolean flag file 'memory_spread_page' is set, then
+If the per-cpuset boolean flag file 'cpuset.memory_spread_page' is set, then
 the kernel will spread the file system buffers (page cache) evenly
 over all the nodes that the faulting task is allowed to use, instead
 of preferring to put those pages on the node where the task is running.
 
-If the per-cpuset boolean flag file 'memory_spread_slab' is set,
+If the per-cpuset boolean flag file 'cpuset.memory_spread_slab' is set,
 then the kernel will spread some file system related slab caches,
 such as for inodes and dentries evenly over all the nodes that the
 faulting task is allowed to use, instead of preferring to put those
@@ -337,21 +337,21 @@ their containing tasks memory spread settings.  If memory spreading
 is turned off, then the currently specified NUMA mempolicy once again
 applies to memory page allocations.
 
-Both 'memory_spread_page' and 'memory_spread_slab' are boolean flag
+Both 'cpuset.memory_spread_page' and 'cpuset.memory_spread_slab' are boolean flag
 files.  By default they contain "0", meaning that the feature is off
 for that cpuset.  If a "1" is written to that file, then that turns
 the named feature on.
 
 The implementation is simple.
 
-Setting the flag 'memory_spread_page' turns on a per-process flag
+Setting the flag 'cpuset.memory_spread_page' turns on a per-process flag
 PF_SPREAD_PAGE for each task that is in that cpuset or subsequently
 joins that cpuset.  The page allocation calls for the page cache
 is modified to perform an inline check for this PF_SPREAD_PAGE task
 flag, and if set, a call to a new routine cpuset_mem_spread_node()
 returns the node to prefer for the allocation.
 
-Similarly, setting 'memory_spread_slab' turns on the flag
+Similarly, setting 'cpuset.memory_spread_slab' turns on the flag
 PF_SPREAD_SLAB, and appropriately marked slab caches will allocate
 pages from the node returned by cpuset_mem_spread_node().
 
@@ -404,24 +404,24 @@ the following two situations:
     system overhead on those CPUs, including avoiding task load
     balancing if that is not needed.
 
-When the per-cpuset flag "sched_load_balance" is enabled (the default
-setting), it requests that all the CPUs in that cpusets allowed 'cpus'
+When the per-cpuset flag "cpuset.sched_load_balance" is enabled (the default
+setting), it requests that all the CPUs in that cpusets allowed 'cpuset.cpus'
 be contained in a single sched domain, ensuring that load balancing
 can move a task (not otherwised pinned, as by sched_setaffinity)
 from any CPU in that cpuset to any other.
 
-When the per-cpuset flag "sched_load_balance" is disabled, then the
+When the per-cpuset flag "cpuset.sched_load_balance" is disabled, then the
 scheduler will avoid load balancing across the CPUs in that cpuset,
 --except-- in so far as is necessary because some overlapping cpuset
 has "sched_load_balance" enabled.
 
-So, for example, if the top cpuset has the flag "sched_load_balance"
+So, for example, if the top cpuset has the flag "cpuset.sched_load_balance"
 enabled, then the scheduler will have one sched domain covering all
-CPUs, and the setting of the "sched_load_balance" flag in any other
+CPUs, and the setting of the "cpuset.sched_load_balance" flag in any other
 cpusets won't matter, as we're already fully load balancing.
 
 Therefore in the above two situations, the top cpuset flag
-"sched_load_balance" should be disabled, and only some of the smaller,
+"cpuset.sched_load_balance" should be disabled, and only some of the smaller,
 child cpusets have this flag enabled.
 
 When doing this, you don't usually want to leave any unpinned tasks in
@@ -433,7 +433,7 @@ scheduler might not consider the possibility of load balancing that
 task to that underused CPU.
 
 Of course, tasks pinned to a particular CPU can be left in a cpuset
-that disables "sched_load_balance" as those tasks aren't going anywhere
+that disables "cpuset.sched_load_balance" as those tasks aren't going anywhere
 else anyway.
 
 There is an impedance mismatch here, between cpusets and sched domains.
@@ -443,19 +443,19 @@ overlap and each CPU is in at most one sched domain.
 It is necessary for sched domains to be flat because load balancing
 across partially overlapping sets of CPUs would risk unstable dynamics
 that would be beyond our understanding.  So if each of two partially
-overlapping cpusets enables the flag 'sched_load_balance', then we
+overlapping cpusets enables the flag 'cpuset.sched_load_balance', then we
 form a single sched domain that is a superset of both.  We won't move
 a task to a CPU outside it cpuset, but the scheduler load balancing
 code might waste some compute cycles considering that possibility.
 
 This mismatch is why there is not a simple one-to-one relation
-between which cpusets have the flag "sched_load_balance" enabled,
+between which cpusets have the flag "cpuset.sched_load_balance" enabled,
 and the sched domain configuration.  If a cpuset enables the flag, it
 will get balancing across all its CPUs, but if it disables the flag,
 it will only be assured of no load balancing if no other overlapping
 cpuset enables the flag.
 
-If two cpusets have partially overlapping 'cpus' allowed, and only
+If two cpusets have partially overlapping 'cpuset.cpus' allowed, and only
 one of them has this flag enabled, then the other may find its
 tasks only partially load balanced, just on the overlapping CPUs.
 This is just the general case of the top_cpuset example given a few
@@ -468,23 +468,23 @@ load balancing to the other CPUs.
 1.7.1 sched_load_balance implementation details.
 ------------------------------------------------
 
-The per-cpuset flag 'sched_load_balance' defaults to enabled (contrary
+The per-cpuset flag 'cpuset.sched_load_balance' defaults to enabled (contrary
 to most cpuset flags.)  When enabled for a cpuset, the kernel will
 ensure that it can load balance across all the CPUs in that cpuset
 (makes sure that all the CPUs in the cpus_allowed of that cpuset are
 in the same sched domain.)
 
-If two overlapping cpusets both have 'sched_load_balance' enabled,
+If two overlapping cpusets both have 'cpuset.sched_load_balance' enabled,
 then they will be (must be) both in the same sched domain.
 
-If, as is the default, the top cpuset has 'sched_load_balance' enabled,
+If, as is the default, the top cpuset has 'cpuset.sched_load_balance' enabled,
 then by the above that means there is a single sched domain covering
 the whole system, regardless of any other cpuset settings.
 
 The kernel commits to user space that it will avoid load balancing
 where it can.  It will pick as fine a granularity partition of sched
 domains as it can while still providing load balancing for any set
-of CPUs allowed to a cpuset having 'sched_load_balance' enabled.
+of CPUs allowed to a cpuset having 'cpuset.sched_load_balance' enabled.
 
 The internal kernel cpuset to scheduler interface passes from the
 cpuset code to the scheduler code a partition of the load balanced
@@ -495,9 +495,9 @@ all the CPUs that must be load balanced.
 The cpuset code builds a new such partition and passes it to the
 scheduler sched domain setup code, to have the sched domains rebuilt
 as necessary, whenever:
- - the 'sched_load_balance' flag of a cpuset with non-empty CPUs changes,
+ - the 'cpuset.sched_load_balance' flag of a cpuset with non-empty CPUs changes,
  - or CPUs come or go from a cpuset with this flag enabled,
- - or 'sched_relax_domain_level' value of a cpuset with non-empty CPUs
+ - or 'cpuset.sched_relax_domain_level' value of a cpuset with non-empty CPUs
    and with this flag enabled changes,
  - or a cpuset with non-empty CPUs and with this flag enabled is removed,
  - or a cpu is offlined/onlined.
@@ -542,7 +542,7 @@ As the result, task B on CPU X need to wait task A or wait load balance
 on the next tick.  For some applications in special situation, waiting
 1 tick may be too long.
 
-The 'sched_relax_domain_level' file allows you to request changing
+The 'cpuset.sched_relax_domain_level' file allows you to request changing
 this searching range as you like.  This file takes int value which
 indicates size of searching range in levels ideally as follows,
 otherwise initial value -1 that indicates the cpuset has no request.
@@ -559,8 +559,8 @@ The system default is architecture dependent.  The system default
 can be changed using the relax_domain_level= boot parameter.
 
 This file is per-cpuset and affect the sched domain where the cpuset
-belongs to.  Therefore if the flag 'sched_load_balance' of a cpuset
-is disabled, then 'sched_relax_domain_level' have no effect since
+belongs to.  Therefore if the flag 'cpuset.sched_load_balance' of a cpuset
+is disabled, then 'cpuset.sched_relax_domain_level' have no effect since
 there is no sched domain belonging the cpuset.
 
 If multiple cpusets are overlapping and hence they form a single sched
@@ -607,9 +607,9 @@ from one cpuset to another, then the kernel will adjust the tasks
 memory placement, as above, the next time that the kernel attempts
 to allocate a page of memory for that task.
 
-If a cpuset has its 'cpus' modified, then each task in that cpuset
+If a cpuset has its 'cpuset.cpus' modified, then each task in that cpuset
 will have its allowed CPU placement changed immediately.  Similarly,
-if a tasks pid is written to another cpusets 'tasks' file, then its
+if a tasks pid is written to another cpusets 'cpuset.tasks' file, then its
 allowed CPU placement is changed immediately.  If such a task had been
 bound to some subset of its cpuset using the sched_setaffinity() call,
 the task will be allowed to run on any CPU allowed in its new cpuset,
@@ -622,8 +622,8 @@ and the processor placement is updated immediately.
 Normally, once a page is allocated (given a physical page
 of main memory) then that page stays on whatever node it
 was allocated, so long as it remains allocated, even if the
-cpusets memory placement policy 'mems' subsequently changes.
-If the cpuset flag file 'memory_migrate' is set true, then when
+cpusets memory placement policy 'cpuset.mems' subsequently changes.
+If the cpuset flag file 'cpuset.memory_migrate' is set true, then when
 tasks are attached to that cpuset, any pages that task had
 allocated to it on nodes in its previous cpuset are migrated
 to the tasks new cpuset. The relative placement of the page within
@@ -631,12 +631,12 @@ the cpuset is preserved during these migration operations if possible.
 For example if the page was on the second valid node of the prior cpuset
 then the page will be placed on the second valid node of the new cpuset.
 
-Also if 'memory_migrate' is set true, then if that cpusets
-'mems' file is modified, pages allocated to tasks in that
-cpuset, that were on nodes in the previous setting of 'mems',
+Also if 'cpuset.memory_migrate' is set true, then if that cpusets
+'cpuset.mems' file is modified, pages allocated to tasks in that
+cpuset, that were on nodes in the previous setting of 'cpuset.mems',
 will be moved to nodes in the new setting of 'mems.'
 Pages that were not in the tasks prior cpuset, or in the cpusets
-prior 'mems' setting, will not be moved.
+prior 'cpuset.mems' setting, will not be moved.
 
 There is an exception to the above.  If hotplug functionality is used
 to remove all the CPUs that are currently assigned to a cpuset,
@@ -678,8 +678,8 @@ and then start a subshell 'sh' in that cpuset:
   cd /dev/cpuset
   mkdir Charlie
   cd Charlie
-  /bin/echo 2-3 > cpus
-  /bin/echo 1 > mems
+  /bin/echo 2-3 > cpuset.cpus
+  /bin/echo 1 > cpuset.mems
   /bin/echo $$ > tasks
   sh
   # The subshell 'sh' is now running in cpuset Charlie
@@ -725,10 +725,13 @@ Now you want to do something with this cpuset.
 
 In this directory you can find several files:
 # ls
-cpu_exclusive  memory_migrate      mems                      tasks
-cpus           memory_pressure     notify_on_release
-mem_exclusive  memory_spread_page  sched_load_balance
-mem_hardwall   memory_spread_slab  sched_relax_domain_level
+cpuset.cpu_exclusive       cpuset.memory_spread_slab
+cpuset.cpus                cpuset.mems
+cpuset.mem_exclusive       cpuset.sched_load_balance
+cpuset.mem_hardwall        cpuset.sched_relax_domain_level
+cpuset.memory_migrate      notify_on_release
+cpuset.memory_pressure     tasks
+cpuset.memory_spread_page
 
 Reading them will give you information about the state of this cpuset:
 the CPUs and Memory Nodes it can use, the processes that are using
@@ -736,13 +739,13 @@ it, its properties.  By writing to these files you can manipulate
 the cpuset.
 
 Set some flags:
-# /bin/echo 1 > cpu_exclusive
+# /bin/echo 1 > cpuset.cpu_exclusive
 
 Add some cpus:
-# /bin/echo 0-7 > cpus
+# /bin/echo 0-7 > cpuset.cpus
 
 Add some mems:
-# /bin/echo 0-7 > mems
+# /bin/echo 0-7 > cpuset.mems
 
 Now attach your shell to this cpuset:
 # /bin/echo $$ > tasks
@@ -774,28 +777,28 @@ echo "/sbin/cpuset_release_agent" > /dev/cpuset/release_agent
 This is the syntax to use when writing in the cpus or mems files
 in cpuset directories:
 
-# /bin/echo 1-4 > cpus		-> set cpus list to cpus 1,2,3,4
-# /bin/echo 1,2,3,4 > cpus	-> set cpus list to cpus 1,2,3,4
+# /bin/echo 1-4 > cpuset.cpus		-> set cpus list to cpus 1,2,3,4
+# /bin/echo 1,2,3,4 > cpuset.cpus	-> set cpus list to cpus 1,2,3,4
 
 To add a CPU to a cpuset, write the new list of CPUs including the
 CPU to be added. To add 6 to the above cpuset:
 
-# /bin/echo 1-4,6 > cpus	-> set cpus list to cpus 1,2,3,4,6
+# /bin/echo 1-4,6 > cpuset.cpus	-> set cpus list to cpus 1,2,3,4,6
 
 Similarly to remove a CPU from a cpuset, write the new list of CPUs
 without the CPU to be removed.
 
 To remove all the CPUs:
 
-# /bin/echo "" > cpus		-> clear cpus list
+# /bin/echo "" > cpuset.cpus		-> clear cpus list
 
 2.3 Setting flags
 -----------------
 
 The syntax is very simple:
 
-# /bin/echo 1 > cpu_exclusive 	-> set flag 'cpu_exclusive'
-# /bin/echo 0 > cpu_exclusive 	-> unset flag 'cpu_exclusive'
+# /bin/echo 1 > cpuset.cpu_exclusive 	-> set flag 'cpuset.cpu_exclusive'
+# /bin/echo 0 > cpuset.cpu_exclusive 	-> unset flag 'cpuset.cpu_exclusive'
 
 2.4 Attaching processes
 -----------------------

Documentation/cgroups/memcg_test.txt

 Memory Resource Controller(Memcg)  Implementation Memo.
-Last Updated: 2009/1/20
-Base Kernel Version: based on 2.6.29-rc2.
+Last Updated: 2010/2
+Base Kernel Version: based on 2.6.33-rc7-mm(candidate for 34).
 
 Because VM is getting complex (one of reasons is memcg...), memcg's behavior
 is complex. This is a document for memcg's internal behavior.
@@ -337,7 +337,7 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 	race and lock dependency with other cgroup subsystems.
 
 	example)
-	# mount -t cgroup none /cgroup -t cpuset,memory,cpu,devices
+	# mount -t cgroup none /cgroup -o cpuset,memory,cpu,devices
 
 	and do task move, mkdir, rmdir etc...under this.
 
@@ -348,7 +348,7 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 
 	For example, test like following is good.
 	(Shell-A)
-	# mount -t cgroup none /cgroup -t memory
+	# mount -t cgroup none /cgroup -o memory
 	# mkdir /cgroup/test
 	# echo 40M > /cgroup/test/memory.limit_in_bytes
 	# echo 0 > /cgroup/test/tasks
@@ -378,3 +378,42 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 	#echo 50M > memory.limit_in_bytes
 	#echo 50M > memory.memsw.limit_in_bytes
 	run 51M of malloc
+
+ 9.9 Move charges at task migration
+	Charges associated with a task can be moved along with task migration.
+
+	(Shell-A)
+	#mkdir /cgroup/A
+	#echo $$ >/cgroup/A/tasks
+	run some programs which uses some amount of memory in /cgroup/A.
+
+	(Shell-B)
+	#mkdir /cgroup/B
+	#echo 1 >/cgroup/B/memory.move_charge_at_immigrate
+	#echo "pid of the program running in group A" >/cgroup/B/tasks
+
+	You can see charges have been moved by reading *.usage_in_bytes or
+	memory.stat of both A and B.
+	See 8.2 of Documentation/cgroups/memory.txt to see what value should be
+	written to move_charge_at_immigrate.
+
+ 9.10 Memory thresholds
+	Memory controler implements memory thresholds using cgroups notification
+	API. You can use Documentation/cgroups/cgroup_event_listener.c to test
+	it.
+
+	(Shell-A) Create cgroup and run event listener
+	# mkdir /cgroup/A
+	# ./cgroup_event_listener /cgroup/A/memory.usage_in_bytes 5M
+
+	(Shell-B) Add task to cgroup and try to allocate and free memory
+	# echo $$ >/cgroup/A/tasks
+	# a="$(dd if=/dev/zero bs=1M count=10)"
+	# a=
+
+	You will see message from cgroup_event_listener every time you cross
+	the thresholds.
+
+	Use /cgroup/A/memory.memsw.usage_in_bytes to test memsw thresholds.
+
+	It's good idea to test root cgroup as well.

Documentation/cgroups/memory.txt

@@ -182,6 +182,8 @@ list.
 NOTE: Reclaim does not work for the root cgroup, since we cannot set any
 limits on the root cgroup.
 
+Note2: When panic_on_oom is set to "2", the whole system will panic.
+
 2. Locking
 
 The memory controller uses the following hierarchy
@@ -262,10 +264,12 @@ 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
+carried forward by default. The pages allocated from the original cgroup still
 remain charged to it, the charge is dropped when the page is freed or
 reclaimed.
 
+Note: You can move charges of a task along with task migration. See 8.
+
 4.3 Removing a cgroup
 
 A cgroup can be removed by rmdir, but as discussed in sections 4.1 and 4.2, a
@@ -336,7 +340,7 @@ Note:
 5.3 swappiness
   Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
 
-  Following cgroups' swapiness can't be changed.
+  Following cgroups' swappiness 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.
@@ -377,7 +381,8 @@ The feature can be disabled by
 NOTE1: Enabling/disabling will fail if the cgroup already has other
 cgroups created below it.
 
-NOTE2: This feature can be enabled/disabled per subtree.
+NOTE2: When panic_on_oom is set to "2", the whole system will panic in
+case of an oom event in any cgroup.
 
 7. Soft limits
 
@@ -414,7 +419,76 @@ NOTE1: Soft limits take effect over a long period of time, since they involve
 NOTE2: It is recommended to set the soft limit always below the hard limit,
        otherwise the hard limit will take precedence.
 
-8. TODO
+8. Move charges at task migration
+
+Users can move charges associated with a task along with task migration, that
+is, uncharge task's pages from the old cgroup and charge them to the new cgroup.
+This feature is not supported in !CONFIG_MMU environments because of lack of
+page tables.
+
+8.1 Interface
+
+This feature is disabled by default. It can be enabled(and disabled again) by
+writing to memory.move_charge_at_immigrate of the destination cgroup.
+
+If you want to enable it:
+
+# echo (some positive value) > memory.move_charge_at_immigrate
+
+Note: Each bits of move_charge_at_immigrate has its own meaning about what type
+      of charges should be moved. See 8.2 for details.
+Note: Charges are moved only when you move mm->owner, IOW, a leader of a thread
+      group.
+Note: If we cannot find enough space for the task in the destination cgroup, we
+      try to make space by reclaiming memory. Task migration may fail if we
+      cannot make enough space.
+Note: It can take several seconds if you move charges in giga bytes order.
+
+And if you want disable it again:
+
+# echo 0 > memory.move_charge_at_immigrate
+
+8.2 Type of charges which can be move
+
+Each bits of move_charge_at_immigrate has its own meaning about what type of
+charges should be moved.
+
+  bit | what type of charges would be moved ?
+ -----+------------------------------------------------------------------------
+   0  | A charge of an anonymous page(or swap of it) used by the target task.
+      | Those pages and swaps must be used only by the target task. You must
+      | enable Swap Extension(see 2.4) to enable move of swap charges.
+
+Note: Those pages and swaps must be charged to the old cgroup.
+Note: More type of pages(e.g. file cache, shmem,) will be supported by other
+      bits in future.
+
+8.3 TODO
+
+- Add support for other types of pages(e.g. file cache, shmem, etc.).
+- Implement madvise(2) to let users decide the vma to be moved or not to be
+  moved.
+- All of moving charge operations are done under cgroup_mutex. It's not good
+  behavior to hold the mutex too long, so we may need some trick.
+
+9. Memory thresholds
+
+Memory controler implements memory thresholds using cgroups notification
+API (see cgroups.txt). It allows to register multiple memory and memsw
+thresholds and gets notifications when it crosses.
+
+To register a threshold application need:
+ - create an eventfd using eventfd(2);
+ - open memory.usage_in_bytes or memory.memsw.usage_in_bytes;
+ - write string like "<event_fd> <memory.usage_in_bytes> <threshold>" to
+   cgroup.event_control.
+
+Application will be notified through eventfd when memory usage crosses
+threshold in any direction.
+
+It's applicable for root and non-root cgroup.
+
+10. TODO
 
 1. Add support for accounting huge pages (as a separate controller)
 2. Make per-cgroup scanner reclaim not-shared pages first

Documentation/circular-buffers.txt

+			       ================
+			       CIRCULAR BUFFERS
+			       ================
+
+By: David Howells <dhowells@redhat.com>
+    Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+
+Linux provides a number of features that can be used to implement circular
+buffering.  There are two sets of such features:
+
+ (1) Convenience functions for determining information about power-of-2 sized
+     buffers.
+
+ (2) Memory barriers for when the producer and the consumer of objects in the
+     buffer don't want to share a lock.
+
+To use these facilities, as discussed below, there needs to be just one
+producer and just one consumer.  It is possible to handle multiple producers by
+serialising them, and to handle multiple consumers by serialising them.
+
+
+Contents:
+
+ (*) What is a circular buffer?
+
+ (*) Measuring power-of-2 buffers.
+
+ (*) Using memory barriers with circular buffers.
+     - The producer.
+     - The consumer.
+
+
+==========================
+WHAT IS A CIRCULAR BUFFER?
+==========================
+
+First of all, what is a circular buffer?  A circular buffer is a buffer of
+fixed, finite size into which there are two indices:
+
+ (1) A 'head' index - the point at which the producer inserts items into the
+     buffer.
+
+ (2) A 'tail' index - the point at which the consumer finds the next item in
+     the buffer.
+
+Typically when the tail pointer is equal to the head pointer, the buffer is
+empty; and the buffer is full when the head pointer is one less than the tail
+pointer.
+
+The head index is incremented when items are added, and the tail index when
+items are removed.  The tail index should never jump the head index, and both
+indices should be wrapped to 0 when they reach the end of the buffer, thus
+allowing an infinite amount of data to flow through the buffer.
+
+Typically, items will all be of the same unit size, but this isn't strictly
+required to use the techniques below.  The indices can be increased by more
+than 1 if multiple items or variable-sized items are to be included in the
+buffer, provided that neither index overtakes the other.  The implementer must
+be careful, however, as a region more than one unit in size may wrap the end of
+the buffer and be broken into two segments.
+
+
+============================
+MEASURING POWER-OF-2 BUFFERS
+============================
+
+Calculation of the occupancy or the remaining capacity of an arbitrarily sized
+circular buffer would normally be a slow operation, requiring the use of a
+modulus (divide) instruction.  However, if the buffer is of a power-of-2 size,
+then a much quicker bitwise-AND instruction can be used instead.
+
+Linux provides a set of macros for handling power-of-2 circular buffers.  These
+can be made use of by:
+
+	#include <linux/circ_buf.h>
+
+The macros are:
+
+ (*) Measure the remaining capacity of a buffer:
+
+	CIRC_SPACE(head_index, tail_index, buffer_size);
+
+     This returns the amount of space left in the buffer[1] into which items
+     can be inserted.
+
+
+ (*) Measure the maximum consecutive immediate space in a buffer:
+
+	CIRC_SPACE_TO_END(head_index, tail_index, buffer_size);
+
+     This returns the amount of consecutive space left in the buffer[1] into
+     which items can be immediately inserted without having to wrap back to the
+     beginning of the buffer.
+
+
+ (*) Measure the occupancy of a buffer:
+
+	CIRC_CNT(head_index, tail_index, buffer_size);
+
+     This returns the number of items currently occupying a buffer[2].
+
+
+ (*) Measure the non-wrapping occupancy of a buffer:
+
+	CIRC_CNT_TO_END(head_index, tail_index, buffer_size);
+
+     This returns the number of consecutive items[2] that can be extracted from
+     the buffer without having to wrap back to the beginning of the buffer.
+
+
+Each of these macros will nominally return a value between 0 and buffer_size-1,
+however:
+
+ [1] CIRC_SPACE*() are intended to be used in the producer.  To the producer
+     they will return a lower bound as the producer controls the head index,
+     but the consumer may still be depleting the buffer on another CPU and
+     moving the tail index.
+
+     To the consumer it will show an upper bound as the producer may be busy
+     depleting the space.
+
+ [2] CIRC_CNT*() are intended to be used in the consumer.  To the consumer they
+     will return a lower bound as the consumer controls the tail index, but the
+     producer may still be filling the buffer on another CPU and moving the
+     head index.
+
+     To the producer it will show an upper bound as the consumer may be busy
+     emptying the buffer.
+
+ [3] To a third party, the order in which the writes to the indices by the
+     producer and consumer become visible cannot be guaranteed as they are
+     independent and may be made on different CPUs - so the result in such a
+     situation will merely be a guess, and may even be negative.
+
+
+===========================================
+USING MEMORY BARRIERS WITH CIRCULAR BUFFERS
+===========================================
+
+By using memory barriers in conjunction with circular buffers, you can avoid
+the need to:
+
+ (1) use a single lock to govern access to both ends of the buffer, thus
+     allowing the buffer to be filled and emptied at the same time; and
+
+ (2) use atomic counter operations.
+
+There are two sides to this: the producer that fills the buffer, and the
+consumer that empties it.  Only one thing should be filling a buffer at any one
+time, and only one thing should be emptying a buffer at any one time, but the
+two sides can operate simultaneously.
+
+
+THE PRODUCER
+------------
+
+The producer will look something like this:
+
+	spin_lock(&producer_lock);
+
+	unsigned long head = buffer->head;
+	unsigned long tail = ACCESS_ONCE(buffer->tail);
+
+	if (CIRC_SPACE(head, tail, buffer->size) >= 1) {
+		/* insert one item into the buffer */
+		struct item *item = buffer[head];
+
+		produce_item(item);
+
+		smp_wmb(); /* commit the item before incrementing the head */
+
+		buffer->head = (head + 1) & (buffer->size - 1);
+
+		/* wake_up() will make sure that the head is committed before
+		 * waking anyone up */
+		wake_up(consumer);
+	}
+
+	spin_unlock(&producer_lock);
+
+This will instruct the CPU that the contents of the new item must be written
+before the head index makes it available to the consumer and then instructs the
+CPU that the revised head index must be written before the consumer is woken.
+
+Note that wake_up() doesn't have to be the exact mechanism used, but whatever
+is used must guarantee a (write) memory barrier between the update of the head
+index and the change of state of the consumer, if a change of state occurs.
+
+
+THE CONSUMER
+------------
+
+The consumer will look something like this:
+
+	spin_lock(&consumer_lock);
+
+	unsigned long head = ACCESS_ONCE(buffer->head);
+	unsigned long tail = buffer->tail;
+
+	if (CIRC_CNT(head, tail, buffer->size) >= 1) {
+		/* read index before reading contents at that index */
+		smp_read_barrier_depends();
+
+		/* extract one item from the buffer */
+		struct item *item = buffer[tail];
+
+		consume_item(item);
+
+		smp_mb(); /* finish reading descriptor before incrementing tail */
+
+		buffer->tail = (tail + 1) & (buffer->size - 1);
+	}
+
+	spin_unlock(&consumer_lock);
+
+This will instruct the CPU to make sure the index is up to date before reading
+the new item, and then it shall make sure the CPU has finished reading the item
+before it writes the new tail pointer, which will erase the item.
+
+
+Note the use of ACCESS_ONCE() in both algorithms to read the opposition index.
+This prevents the compiler from discarding and reloading its cached value -
+which some compilers will do across smp_read_barrier_depends().  This isn't
+strictly needed if you can be sure that the opposition index will _only_ be
+used the once.
+
+
+===============
+FURTHER READING
+===============
+
+See also Documentation/memory-barriers.txt for a description of Linux's memory
+barrier facilities.

Documentation/connector/cn_test.c

@@ -25,6 +25,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/skbuff.h>
+#include <linux/slab.h>
 #include <linux/timer.h>
 
 #include <linux/connector.h>

Documentation/console/console.txt

@@ -74,7 +74,7 @@ driver takes over the consoles vacated by the driver. Binding, on the other
 hand, will bind the driver to the consoles that are currently occupied by a
 system driver.
 
-NOTE1: Binding and binding must be selected in Kconfig. It's under:
+NOTE1: Binding and unbinding must be selected in Kconfig. It's under:
 
 Device Drivers -> Character devices -> Support for binding and unbinding
 console drivers

Documentation/cpu-freq/governors.txt

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

Documentation/device-mapper/snapshot.txt

@@ -122,3 +122,47 @@ volumeGroup-base: 0 2097152 snapshot-merge 254:11 254:12 P 16
 brw-------  1 root root 254, 11 29 ago 18:15 /dev/mapper/volumeGroup-base-real
 brw-------  1 root root 254, 12 29 ago 18:16 /dev/mapper/volumeGroup-base-cow
 brw-------  1 root root 254, 10 29 ago 18:16 /dev/mapper/volumeGroup-base
+
+
+How to determine when a merging is complete
+===========================================
+The snapshot-merge and snapshot status lines end with:
+  <sectors_allocated>/<total_sectors> <metadata_sectors>
+
+Both <sectors_allocated> and <total_sectors> include both data and metadata.
+During merging, the number of sectors allocated gets smaller and
+smaller.  Merging has finished when the number of sectors holding data
+is zero, in other words <sectors_allocated> == <metadata_sectors>.
+
+Here is a practical example (using a hybrid of lvm and dmsetup commands):
+
+# lvs
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup owi-a- 4.00g
+  snap    volumeGroup swi-a- 1.00g base  18.97
+
+# dmsetup status volumeGroup-snap
+0 8388608 snapshot 397896/2097152 1560
+                                  ^^^^ metadata sectors
+
+# lvconvert --merge -b volumeGroup/snap
+  Merging of volume snap started.
+
+# lvs volumeGroup/snap
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup Owi-a- 4.00g          17.23
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 281688/2097152 1104
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 180480/2097152 712
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 16/2097152 16
+
+Merging has finished.
+
+# lvs
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup owi-a- 4.00g

Documentation/dontdiff

@@ -69,7 +69,6 @@ av_permissions.h
 bbootsect
 bin2c
 binkernel.spec
-binoffset
 bootsect
 bounds.h
 bsetup

Documentation/driver-model/platform.txt

@@ -192,7 +192,7 @@ command line. This will execute all matching early_param() callbacks.
 User specified early platform devices will be registered at this point.
 For the early serial console case the user can specify port on the
 kernel command line as "earlyprintk=serial.0" where "earlyprintk" is
-the class string, "serial" is the name of the platfrom driver and
+the class string, "serial" is the name of the platform driver and
 0 is the platform device id. If the id is -1 then the dot and the
 id can be omitted.
 

Documentation/dvb/get_dvb_firmware

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

Documentation/eisa.txt

@@ -171,7 +171,7 @@ device.
 virtual_root.force_probe :
 
 Force the probing code to probe EISA slots even when it cannot find an
-EISA compliant mainboard (nothing appears on slot 0). Defaultd to 0
+EISA compliant mainboard (nothing appears on slot 0). Defaults to 0
 (don't force), and set to 1 (force probing) when either
 CONFIG_ALPHA_JENSEN or CONFIG_EISA_VLB_PRIMING are set.
 

Documentation/fault-injection/fault-injection.txt

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

Documentation/filesystems/00-INDEX

@@ -16,6 +16,8 @@ befs.txt
 	- information about the BeOS filesystem for Linux.
 bfs.txt
 	- info for the SCO UnixWare Boot Filesystem (BFS).
+ceph.txt
+	- info for the Ceph Distributed File System
 cifs.txt
 	- description of the CIFS filesystem.
 coda.txt
@@ -32,6 +34,8 @@ dlmfs.txt
 	- info on the userspace interface to the OCFS2 DLM.
 dnotify.txt
 	- info about directory notification in Linux.
+dnotify_test.c
+	- example program for dnotify
 ecryptfs.txt
 	- docs on eCryptfs: stacked cryptographic filesystem for Linux.
 exofs.txt
@@ -62,6 +66,8 @@ jfs.txt
 	- info and mount options for the JFS filesystem.
 locks.txt
 	- info on file locking implementations, flock() vs. fcntl(), etc.
+logfs.txt
+	- info on the LogFS flash filesystem.
 mandatory-locking.txt
 	- info on the Linux implementation of Sys V mandatory file locking.
 ncpfs.txt