Merge branch 'linus' into tracing/hw-breakpoints

Conflicts: arch/x86/Kconfig arch/x86/kernel/traps.c arch/x86/power/cpu.c arch/x86/power/cpu_32.c kernel/Makefile Semantic conflict: arch/x86/kernel/hw_breakpoint.c Merge reason: Resolve the conflicts, move from put_cpu_no_sched() to put_cpu() in arch/x86/kernel/hw_breakpoint.c. Signed-off-by: Ingo Molnar <mingo@elte.hu>
author: Ingo Molnar <mingo@elte.hu> 2009-06-17 12:52:15 +0200
committer: Ingo Molnar <mingo@elte.hu> 2009-06-17 12:56:49 +0200
commit: eadb8a091b27a840de7450f84ecff5ef13476424 (patch)
tree: 58c3782d40def63baa8167f3d31e3048cb4c7660 /Documentation
parent: 73874005cd8800440be4299bd095387fff4b90ac (diff)
parent: 65795efbd380a832ae508b04dba8f8e53f0b84d9 (diff)
download: kernel-crypto-eadb8a091b27a840de7450f84ecff5ef13476424.tar.gz
kernel-crypto-eadb8a091b27a840de7450f84ecff5ef13476424.tar.xz
kernel-crypto-eadb8a091b27a840de7450f84ecff5ef13476424.zip
150 files changed, 5414 insertions, 1820 deletions
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index 44f52a4f590..cbbd3e06994 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -60,3 +60,62 @@ Description:
 		Indicates whether the block layer should automatically
 		generate checksums for write requests bound for
 		devices that support receiving integrity metadata.
+
+What:		/sys/block/<disk>/alignment_offset
+Date:		April 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Storage devices may report a physical block size that is
+		bigger than the logical block size (for instance a drive
+		with 4KB physical sectors exposing 512-byte logical
+		blocks to the operating system).  This parameter
+		indicates how many bytes the beginning of the device is
+		offset from the disk's natural alignment.
+
+What:		/sys/block/<disk>/<partition>/alignment_offset
+Date:		April 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Storage devices may report a physical block size that is
+		bigger than the logical block size (for instance a drive
+		with 4KB physical sectors exposing 512-byte logical
+		blocks to the operating system).  This parameter
+		indicates how many bytes the beginning of the partition
+		is offset from the disk's natural alignment.
+
+What:		/sys/block/<disk>/queue/logical_block_size
+Date:		May 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		This is the smallest unit the storage device can
+		address.  It is typically 512 bytes.
+
+What:		/sys/block/<disk>/queue/physical_block_size
+Date:		May 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		This is the smallest unit the storage device can write
+		without resorting to read-modify-write operation.  It is
+		usually the same as the logical block size but may be
+		bigger.  One example is SATA drives with 4KB sectors
+		that expose a 512-byte logical block size to the
+		operating system.
+
+What:		/sys/block/<disk>/queue/minimum_io_size
+Date:		April 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Storage devices may report a preferred minimum I/O size,
+		which is the smallest request the device can perform
+		without incurring a read-modify-write penalty.  For disk
+		drives this is often the physical block size.  For RAID
+		arrays it is often the stripe chunk size.
+
+What:		/sys/block/<disk>/queue/optimal_io_size
+Date:		April 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Storage devices may report an optimal I/O size, which is
+		the device's preferred unit of receiving I/O.  This is
+		rarely reported for disk drives.  For RAID devices it is
+		usually the stripe width or the internal block size.
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss b/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss
new file mode 100644
index 00000000000..0a92a7c93a6
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss
@@ -0,0 +1,33 @@
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/model
+Date:		March 2009
+Kernel Version: 2.6.30
+Contact:	iss_storagedev@hp.com
+Description:	Displays the SCSI INQUIRY page 0 model for logical drive
+		Y of controller X.
+
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/rev
+Date:		March 2009
+Kernel Version: 2.6.30
+Contact:	iss_storagedev@hp.com
+Description:	Displays the SCSI INQUIRY page 0 revision for logical
+		drive Y of controller X.
+
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/unique_id
+Date:		March 2009
+Kernel Version: 2.6.30
+Contact:	iss_storagedev@hp.com
+Description:	Displays the SCSI INQUIRY page 83 serial number for logical
+		drive Y of controller X.
+
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/vendor
+Date:		March 2009
+Kernel Version: 2.6.30
+Contact:	iss_storagedev@hp.com
+Description:	Displays the SCSI INQUIRY page 0 vendor for logical drive
+		Y of controller X.
+
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/block:cciss!cXdY
+Date:		March 2009
+Kernel Version: 2.6.30
+Contact:	iss_storagedev@hp.com
+Description:	A symbolic link to /sys/block/cciss!cXdY
diff --git a/Documentation/ABI/testing/sysfs-devices-cache_disable b/Documentation/ABI/testing/sysfs-devices-cache_disable
new file mode 100644
index 00000000000..175bb4f7051
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-cache_disable
@@ -0,0 +1,18 @@
+What:      /sys/devices/system/cpu/cpu*/cache/index*/cache_disable_X
+Date:      August 2008
+KernelVersion:	2.6.27
+Contact:	mark.langsdorf@amd.com
+Description:	These files exist in every cpu's cache index directories.
+		There are currently 2 cache_disable_# files in each
+		directory.  Reading from these files on a supported
+		processor will return that cache disable index value
+		for that processor and node.  Writing to one of these
+		files will cause the specificed cache index to be disabled.
+
+		Currently, only AMD Family 10h Processors support cache index
+		disable, and only for their L3 caches.  See the BIOS and
+		Kernel Developer's Guide at
+		http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/31116-Public-GH-BKDG_3.20_2-4-09.pdf
+		for formatting information and other details on the
+		cache index disable.
+Users:    joachim.deguara@amd.com
diff --git a/Documentation/ABI/testing/sysfs-kernel-slab b/Documentation/ABI/testing/sysfs-kernel-slab
new file mode 100644
index 00000000000..6dcf75e594f
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-slab
@@ -0,0 +1,479 @@
+What:		/sys/kernel/slab
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The /sys/kernel/slab directory contains a snapshot of the
+		internal state of the SLUB allocator for each cache.  Certain
+		files may be modified to change the behavior of the cache (and
+		any cache it aliases, if any).
+Users:		kernel memory tuning tools
+
+What:		/sys/kernel/slab/cache/aliases
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The aliases file is read-only and specifies how many caches
+		have merged into this cache.
+
+What:		/sys/kernel/slab/cache/align
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The align file is read-only and specifies the cache's object
+		alignment in bytes.
+
+What:		/sys/kernel/slab/cache/alloc_calls
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The alloc_calls file is read-only and lists the kernel code
+		locations from which allocations for this cache were performed.
+		The alloc_calls file only contains information if debugging is
+		enabled for that cache (see Documentation/vm/slub.txt).
+
+What:		/sys/kernel/slab/cache/alloc_fastpath
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The alloc_fastpath file is read-only and specifies how many
+		objects have been allocated using the fast path.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/alloc_from_partial
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The alloc_from_partial file is read-only and specifies how
+		many times a cpu slab has been full and it has been refilled
+		by using a slab from the list of partially used slabs.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/alloc_refill
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The alloc_refill file is read-only and specifies how many
+		times the per-cpu freelist was empty but there were objects
+		available as the result of remote cpu frees.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/alloc_slab
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The alloc_slab file is read-only and specifies how many times
+		a new slab had to be allocated from the page allocator.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/alloc_slowpath
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The alloc_slowpath file is read-only and specifies how many
+		objects have been allocated using the slow path because of a
+		refill or allocation from a partial or new slab.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/cache_dma
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The cache_dma file is read-only and specifies whether objects
+		are from ZONE_DMA.
+		Available when CONFIG_ZONE_DMA is enabled.
+
+What:		/sys/kernel/slab/cache/cpu_slabs
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The cpu_slabs file is read-only and displays how many cpu slabs
+		are active and their NUMA locality.
+
+What:		/sys/kernel/slab/cache/cpuslab_flush
+Date:		April 2009
+KernelVersion:	2.6.31
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file cpuslab_flush is read-only and specifies how many
+		times a cache's cpu slabs have been flushed as the result of
+		destroying or shrinking a cache, a cpu going offline, or as
+		the result of forcing an allocation from a certain node.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/ctor
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The ctor file is read-only and specifies the cache's object
+		constructor function, which is invoked for each object when a
+		new slab is allocated.
+
+What:		/sys/kernel/slab/cache/deactivate_empty
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file deactivate_empty is read-only and specifies how many
+		times an empty cpu slab was deactivated.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/deactivate_full
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file deactivate_full is read-only and specifies how many
+		times a full cpu slab was deactivated.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/deactivate_remote_frees
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file deactivate_remote_frees is read-only and specifies how
+		many times a cpu slab has been deactivated and contained free
+		objects that were freed remotely.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/deactivate_to_head
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file deactivate_to_head is read-only and specifies how
+		many times a partial cpu slab was deactivated and added to the
+		head of its node's partial list.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/deactivate_to_tail
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file deactivate_to_tail is read-only and specifies how
+		many times a partial cpu slab was deactivated and added to the
+		tail of its node's partial list.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/destroy_by_rcu
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The destroy_by_rcu file is read-only and specifies whether
+		slabs (not objects) are freed by rcu.
+
+What:		/sys/kernel/slab/cache/free_add_partial
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file free_add_partial is read-only and specifies how many
+		times an object has been freed in a full slab so that it had to
+		added to its node's partial list.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/free_calls
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The free_calls file is read-only and lists the locations of
+		object frees if slab debugging is enabled (see
+		Documentation/vm/slub.txt).
+
+What:		/sys/kernel/slab/cache/free_fastpath
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The free_fastpath file is read-only and specifies how many
+		objects have been freed using the fast path because it was an
+		object from the cpu slab.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/free_frozen
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The free_frozen file is read-only and specifies how many
+		objects have been freed to a frozen slab (i.e. a remote cpu
+		slab).
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/free_remove_partial
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file free_remove_partial is read-only and specifies how
+		many times an object has been freed to a now-empty slab so
+		that it had to be removed from its node's partial list.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/free_slab
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The free_slab file is read-only and specifies how many times an
+		empty slab has been freed back to the page allocator.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/free_slowpath
+Date:		February 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The free_slowpath file is read-only and specifies how many
+		objects have been freed using the slow path (i.e. to a full or
+		partial slab).
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/hwcache_align
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The hwcache_align file is read-only and specifies whether
+		objects are aligned on cachelines.
+
+What:		/sys/kernel/slab/cache/min_partial
+Date:		February 2009
+KernelVersion:	2.6.30
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		David Rientjes <rientjes@google.com>
+Description:
+		The min_partial file specifies how many empty slabs shall
+		remain on a node's partial list to avoid the overhead of
+		allocating new slabs.  Such slabs may be reclaimed by utilizing
+		the shrink file.
+
+What:		/sys/kernel/slab/cache/object_size
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The object_size file is read-only and specifies the cache's
+		object size.
+
+What:		/sys/kernel/slab/cache/objects
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The objects file is read-only and displays how many objects are
+		active and from which nodes they are from.
+
+What:		/sys/kernel/slab/cache/objects_partial
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The objects_partial file is read-only and displays how many
+		objects are on partial slabs and from which nodes they are
+		from.
+
+What:		/sys/kernel/slab/cache/objs_per_slab
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file objs_per_slab is read-only and specifies how many
+		objects may be allocated from a single slab of the order
+		specified in /sys/kernel/slab/cache/order.
+
+What:		/sys/kernel/slab/cache/order
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The order file specifies the page order at which new slabs are
+		allocated.  It is writable and can be changed to increase the
+		number of objects per slab.  If a slab cannot be allocated
+		because of fragmentation, SLUB will retry with the minimum order
+		possible depending on its characteristics.
+
+What:		/sys/kernel/slab/cache/order_fallback
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file order_fallback is read-only and specifies how many
+		times an allocation of a new slab has not been possible at the
+		cache's order and instead fallen back to its minimum possible
+		order.
+		Available when CONFIG_SLUB_STATS is enabled.
+
+What:		/sys/kernel/slab/cache/partial
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The partial file is read-only and displays how long many
+		partial slabs there are and how long each node's list is.
+
+What:		/sys/kernel/slab/cache/poison
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The poison file specifies whether objects should be poisoned
+		when a new slab is allocated.
+
+What:		/sys/kernel/slab/cache/reclaim_account
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The reclaim_account file specifies whether the cache's objects
+		are reclaimable (and grouped by their mobility).
+
+What:		/sys/kernel/slab/cache/red_zone
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The red_zone file specifies whether the cache's objects are red
+		zoned.
+
+What:		/sys/kernel/slab/cache/remote_node_defrag_ratio
+Date:		January 2008
+KernelVersion:	2.6.25
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The file remote_node_defrag_ratio specifies the percentage of
+		times SLUB will attempt to refill the cpu slab with a partial
+		slab from a remote node as opposed to allocating a new slab on
+		the local node.  This reduces the amount of wasted memory over
+		the entire system but can be expensive.
+		Available when CONFIG_NUMA is enabled.
+
+What:		/sys/kernel/slab/cache/sanity_checks
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The sanity_checks file specifies whether expensive checks
+		should be performed on free and, at minimum, enables double free
+		checks.  Caches that enable sanity_checks cannot be merged with
+		caches that do not.
+
+What:		/sys/kernel/slab/cache/shrink
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The shrink file is written when memory should be reclaimed from
+		a cache.  Empty partial slabs are freed and the partial list is
+		sorted so the slabs with the fewest available objects are used
+		first.
+
+What:		/sys/kernel/slab/cache/slab_size
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The slab_size file is read-only and specifies the object size
+		with metadata (debugging information and alignment) in bytes.
+
+What:		/sys/kernel/slab/cache/slabs
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The slabs file is read-only and displays how long many slabs
+		there are (both cpu and partial) and from which nodes they are
+		from.
+
+What:		/sys/kernel/slab/cache/store_user
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The store_user file specifies whether the location of
+		allocation or free should be tracked for a cache.
+
+What:		/sys/kernel/slab/cache/total_objects
+Date:		April 2008
+KernelVersion:	2.6.26
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The total_objects file is read-only and displays how many total
+		objects a cache has and from which nodes they are from.
+
+What:		/sys/kernel/slab/cache/trace
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		The trace file specifies whether object allocations and frees
+		should be traced.
+
+What:		/sys/kernel/slab/cache/validate
+Date:		May 2007
+KernelVersion:	2.6.22
+Contact:	Pekka Enberg <penberg@cs.helsinki.fi>,
+		Christoph Lameter <cl@linux-foundation.org>
+Description:
+		Writing to the validate file causes SLUB to traverse all of its
+		cache's objects and check the validity of metadata.
diff --git a/Documentation/Changes b/Documentation/Changes
index b95082be4d5..664392481c8 100644
--- a/Documentation/Changes
+++ b/Documentation/Changes
@@ -29,7 +29,7 @@ hardware, for example, you probably needn't concern yourself with
 isdn4k-utils.
 
 o  Gnu C                  3.2                     # gcc --version
-o  Gnu make               3.79.1                  # make --version
+o  Gnu make               3.80                    # make --version
 o  binutils               2.12                    # ld -v
 o  util-linux             2.10o                   # fdformat --version
 o  module-init-tools      0.9.10                  # depmod -V
@@ -48,6 +48,7 @@ o  procps                 3.2.0                   # ps --version
 o  oprofile               0.9                     # oprofiled --version
 o  udev                   081                     # udevinfo -V
 o  grub                   0.93                    # grub --version
+o  mcelog		  0.6
 
 Kernel compilation
 ==================
@@ -61,7 +62,7 @@ computer.
 Make
 ----
 
-You will need Gnu make 3.79.1 or later to build the kernel.
+You will need Gnu make 3.80 or later to build the kernel.
 
 Binutils
 --------
@@ -276,6 +277,16 @@ before running exportfs or mountd.  It is recommended that all NFS
 services be protected from the internet-at-large by a firewall where
 that is possible.
 
+mcelog
+------
+
+In Linux 2.6.31+ the i386 kernel needs to run the mcelog utility
+as a regular cronjob similar to the x86-64 kernel to process and log
+machine check events when CONFIG_X86_NEW_MCE is enabled. Machine check
+events are errors reported by the CPU. Processing them is strongly encouraged.
+All x86-64 kernels since 2.6.4 require the mcelog utility to
+process machine checks.
+
 Getting updated software
 ========================
 
@@ -365,6 +376,10 @@ FUSE
 ----
 o <http://sourceforge.net/projects/fuse>
 
+mcelog
+------
+o <ftp://ftp.kernel.org/pub/linux/utils/cpu/mce/mcelog/>
+
 Networking
 **********
 
diff --git a/Documentation/CodingStyle b/Documentation/CodingStyle
index 72968cd5eaf..8bb37237ebd 100644
--- a/Documentation/CodingStyle
+++ b/Documentation/CodingStyle
@@ -698,8 +698,8 @@ very often is not. Abundant use of the inline keyword leads to a much bigger
 kernel, which in turn slows the system as a whole down, due to a bigger
 icache footprint for the CPU and simply because there is less memory
 available for the pagecache. Just think about it; a pagecache miss causes a
-disk seek, which easily takes 5 miliseconds. There are a LOT of cpu cycles
-that can go into these 5 miliseconds.
+disk seek, which easily takes 5 milliseconds. There are a LOT of cpu cycles
+that can go into these 5 milliseconds.
 
 A reasonable rule of thumb is to not put inline at functions that have more
 than 3 lines of code in them. An exception to this rule are the cases where
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index d9aa43d78bc..5aceb88b3f8 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -676,8 +676,8 @@ this directory the following files can currently be found:
 	dma-api/all_errors	This file contains a numeric value. If this
 				value is not equal to zero the debugging code
 				will print a warning for every error it finds
-				into the kernel log. Be carefull with this
-				option. It can easily flood your logs.
+				into the kernel log. Be careful with this
+				option, as it can easily flood your logs.
 
 	dma-api/disabled	This read-only file contains the character 'Y'
 				if the debugging code is disabled. This can
@@ -704,12 +704,24 @@ this directory the following files can currently be found:
 				The current number of free dma_debug_entries
 				in the allocator.
 
+	dma-api/driver-filter
+				You can write a name of a driver into this file
+				to limit the debug output to requests from that
+				particular driver. Write an empty string to
+				that file to disable the filter and see
+				all errors again.
+
 If you have this code compiled into your kernel it will be enabled by default.
 If you want to boot without the bookkeeping anyway you can provide
 'dma_debug=off' as a boot parameter. This will disable DMA-API debugging.
 Notice that you can not enable it again at runtime. You have to reboot to do
 so.
 
+If you want to see debug messages only for a special device driver you can
+specify the dma_debug_driver=<drivername> parameter. This will enable the
+driver filter at boot time. The debug code will only print errors for that
+driver afterwards. This filter can be disabled or changed later using debugfs.
+
 When the code disables itself at runtime this is most likely because it ran
 out of dma_debug_entries. These entries are preallocated at boot. The number
 of preallocated entries is defined per architecture. If it is too low for you
diff --git a/Documentation/DocBook/debugobjects.tmpl b/Documentation/DocBook/debugobjects.tmpl
index 7f5f218015f..08ff908aa7a 100644
--- a/Documentation/DocBook/debugobjects.tmpl
+++ b/Documentation/DocBook/debugobjects.tmpl
@@ -106,7 +106,7 @@
       number of errors are printk'ed including a full stack trace.
     </para>
     <para>
-      The statistics are available via debugfs/debug_objects/stats.
+      The statistics are available via /sys/kernel/debug/debug_objects/stats.
       They provide information about the number of warnings and the
       number of successful fixups along with information about the
       usage of the internal tracking objects and the state of the
diff --git a/Documentation/DocBook/mac80211.tmpl b/Documentation/DocBook/mac80211.tmpl
index fbeaffc1dcc..e3698666357 100644
--- a/Documentation/DocBook/mac80211.tmpl
+++ b/Documentation/DocBook/mac80211.tmpl
@@ -145,7 +145,6 @@ usage should require reading the full document.
         interface in STA mode at first!
       </para>
 !Finclude/net/mac80211.h ieee80211_if_init_conf
-!Finclude/net/mac80211.h ieee80211_if_conf
     </chapter>
 
     <chapter id="rx-tx">
diff --git a/Documentation/RCU/rculist_nulls.txt b/Documentation/RCU/rculist_nulls.txt
index 6389dec3345..93cb28d05dc 100644
--- a/Documentation/RCU/rculist_nulls.txt
+++ b/Documentation/RCU/rculist_nulls.txt
@@ -118,7 +118,7 @@ to another chain) checking the final 'nulls' value if
 the lookup met the end of chain. If final 'nulls' value
 is not the slot number, then we must restart the lookup at
 the beginning. If the object was moved to the same chain,
-then the reader doesnt care : It might eventually
+then the reader doesn't care : It might eventually
 scan the list again without harm.
 
 
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 068848240a8..02cced183b2 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -192,23 +192,24 @@ rcu/rcuhier (which displays the struct rcu_node hierarchy).
 The output of "cat rcu/rcudata" looks as follows:
 
 rcu:
-  0 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=1 rp=3c2a dt=23301/73 dn=2 df=1882 of=0 ri=2126 ql=2 b=10
-  1 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=3 rp=39a6 dt=78073/1 dn=2 df=1402 of=0 ri=1875 ql=46 b=10
-  2 c=4010 g=4010 pq=1 pqc=4010 qp=0 rpfq=-5 rp=1d12 dt=16646/0 dn=2 df=3140 of=0 ri=2080 ql=0 b=10
-  3 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=2b50 dt=21159/1 dn=2 df=2230 of=0 ri=1923 ql=72 b=10
-  4 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1644 dt=5783/1 dn=2 df=3348 of=0 ri=2805 ql=7 b=10
-  5 c=4012 g=4013 pq=0 pqc=4011 qp=1 rpfq=3 rp=1aac dt=5879/1 dn=2 df=3140 of=0 ri=2066 ql=10 b=10
-  6 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=ed8 dt=5847/1 dn=2 df=3797 of=0 ri=1266 ql=10 b=10
-  7 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1fa2 dt=6199/1 dn=2 df=2795 of=0 ri=2162 ql=28 b=10
+rcu:
+  0 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=10951/1 dn=0 df=1101 of=0 ri=36 ql=0 b=10
+  1 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=16117/1 dn=0 df=1015 of=0 ri=0 ql=0 b=10
+  2 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=1445/1 dn=0 df=1839 of=0 ri=0 ql=0 b=10
+  3 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=6681/1 dn=0 df=1545 of=0 ri=0 ql=0 b=10
+  4 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=1003/1 dn=0 df=1992 of=0 ri=0 ql=0 b=10
+  5 c=17829 g=17830 pq=1 pqc=17829 qp=1 dt=3887/1 dn=0 df=3331 of=0 ri=4 ql=2 b=10
+  6 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=859/1 dn=0 df=3224 of=0 ri=0 ql=0 b=10
+  7 c=17829 g=17830 pq=0 pqc=17829 qp=1 dt=3761/1 dn=0 df=1818 of=0 ri=0 ql=2 b=10
 rcu_bh:
-  0 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-145 rp=21d6 dt=23301/73 dn=2 df=0 of=0 ri=0 ql=0 b=10
-  1 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-170 rp=20ce dt=78073/1 dn=2 df=26 of=0 ri=5 ql=0 b=10
-  2 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-83 rp=fbd dt=16646/0 dn=2 df=28 of=0 ri=4 ql=0 b=10
-  3 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-105 rp=178c dt=21159/1 dn=2 df=28 of=0 ri=2 ql=0 b=10
-  4 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-30 rp=b54 dt=5783/1 dn=2 df=32 of=0 ri=0 ql=0 b=10
-  5 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-29 rp=df5 dt=5879/1 dn=2 df=30 of=0 ri=3 ql=0 b=10
-  6 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-28 rp=788 dt=5847/1 dn=2 df=32 of=0 ri=0 ql=0 b=10
-  7 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-53 rp=1098 dt=6199/1 dn=2 df=30 of=0 ri=3 ql=0 b=10
+  0 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=10951/1 dn=0 df=0 of=0 ri=0 ql=0 b=10
+  1 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=16117/1 dn=0 df=13 of=0 ri=0 ql=0 b=10
+  2 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=1445/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+  3 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=6681/1 dn=0 df=9 of=0 ri=0 ql=0 b=10
+  4 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=1003/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+  5 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3887/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+  6 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=859/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+  7 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3761/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
 
 The first section lists the rcu_data structures for rcu, the second for
 rcu_bh.  Each section has one line per CPU, or eight for this 8-CPU system.
@@ -253,12 +254,6 @@ o	"pqc" indicates which grace period the last-observed quiescent
 o	"qp" indicates that RCU still expects a quiescent state from
 	this CPU.
 
-o	"rpfq" is the number of rcu_pending() calls on this CPU required
-	to induce this CPU to invoke force_quiescent_state().
-
-o	"rp" is low-order four hex digits of the count of how many times
-	rcu_pending() has been invoked on this CPU.
-
 o	"dt" is the current value of the dyntick counter that is incremented
 	when entering or leaving dynticks idle state, either by the
 	scheduler or by irq.  The number after the "/" is the interrupt
@@ -305,6 +300,9 @@ o	"b" is the batch limit for this CPU.  If more than this number
 	of RCU callbacks is ready to invoke, then the remainder will
 	be deferred.
 
+There is also an rcu/rcudata.csv file with the same information in
+comma-separated-variable spreadsheet format.
+
 
 The output of "cat rcu/rcugp" looks as follows:
 
@@ -411,3 +409,63 @@ o	Each element of the form "1/1 0:127 ^0" represents one struct
 		For example, the first entry at the lowest level shows
 		"^0", indicating that it corresponds to bit zero in
 		the first entry at the middle level.
+
+
+The output of "cat rcu/rcu_pending" looks as follows:
+
+rcu:
+  0 np=255892 qsp=53936 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
+  1 np=261224 qsp=54638 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
+  2 np=237496 qsp=49664 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
+  3 np=236249 qsp=48766 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
+  4 np=221310 qsp=46850 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
+  5 np=237332 qsp=48449 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
+  6 np=219995 qsp=46718 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
+  7 np=249893 qsp=49390 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888
+rcu_bh:
+  0 np=146741 qsp=1419 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
+  1 np=155792 qsp=12597 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
+  2 np=136629 qsp=18680 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
+  3 np=137723 qsp=2843 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
+  4 np=123110 qsp=12433 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
+  5 np=137456 qsp=4210 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
+  6 np=120834 qsp=9902 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
+  7 np=144888 qsp=26336 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
+
+As always, this is once again split into "rcu" and "rcu_bh" portions.
+The fields are as follows:
+
+o	"np" is the number of times that __rcu_pending() has been invoked
+	for the corresponding flavor of RCU.
+
+o	"qsp" is the number of times that the RCU was waiting for a
+	quiescent state from this CPU.
+
+o	"cbr" is the number of times that this CPU had RCU callbacks
+	that had passed through a grace period, and were thus ready
+	to be invoked.
+
+o	"cng" is the number of times that this CPU needed another
+	grace period while RCU was idle.
+
+o	"gpc" is the number of times that an old grace period had
+	completed, but this CPU was not yet aware of it.
+
+o	"gps" is the number of times that a new grace period had started,
+	but this CPU was not yet aware of it.
+
+o	"nf" is the number of times that this CPU suspected that the
+	current grace period had run for too long, and thus needed to
+	be forced.
+
+	Please note that "forcing" consists of sending resched IPIs
+	to holdout CPUs.  If that CPU really still is in an old RCU
+	read-side critical section, then we really do have to wait for it.
+	The assumption behing "forcing" is that the CPU is not still in
+	an old RCU read-side critical section, but has not yet responded
+	for some other reason.
+
+o	"nn" is the number of times that this CPU needed nothing.  Alert
+	readers will note that the rcu "nn" number for a given CPU very
+	closely matches the rcu_bh "np" number for that same CPU.  This
+	is due to short-circuit evaluation in rcu_pending().
diff --git a/Documentation/SM501.txt b/Documentation/SM501.txt
index 6fc65603592..561826f8209 100644
--- a/Documentation/SM501.txt
+++ b/Documentation/SM501.txt
@@ -5,7 +5,7 @@ Copyright 2006, 2007 Simtec Electronics
 
 The Silicon Motion SM501 multimedia companion chip is a multifunction device
 which may provide numerous interfaces including USB host controller USB gadget,
-Asyncronous Serial ports, Audio functions and a dual display video interface.
+asynchronous serial ports, audio functions, and a dual display video interface.
 The device may be connected by PCI or local bus with varying functions enabled.
 
 Core
diff --git a/Documentation/Smack.txt b/Documentation/Smack.txt
index 629c92e9978..34614b4c708 100644
--- a/Documentation/Smack.txt
+++ b/Documentation/Smack.txt
@@ -184,8 +184,9 @@ length. Single character labels using special characters, that being anything
 other than a letter or digit, are reserved for use by the Smack development
 team. Smack labels are unstructured, case sensitive, and the only operation
 ever performed on them is comparison for equality. Smack labels cannot
-contain unprintable characters or the "/" (slash) character. Smack labels
-cannot begin with a '-', which is reserved for special options.
+contain unprintable characters, the "/" (slash), the "\" (backslash), the "'"
+(quote) and '"' (double-quote) characters.
+Smack labels cannot begin with a '-', which is reserved for special options.
 
 There are some predefined labels:
 
@@ -523,3 +524,18 @@ Smack supports some mount options:
 
 These mount options apply to all file system types.
 
+Smack auditing
+
+If you want Smack auditing of security events, you need to set CONFIG_AUDIT
+in your kernel configuration.
+By default, all denied events will be audited. You can change this behavior by
+writing a single character to the /smack/logging file :
+0 : no logging
+1 : log denied (default)
+2 : log accepted
+3 : log denied & accepted
+
+Events are logged as 'key=value' pairs, for each event you at least will get
+the subjet, the object, the rights requested, the action, the kernel function
+that triggered the event, plus other pairs depending on the type of event
+audited.
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index f309d3c6221..5c555a8b39e 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -91,6 +91,10 @@ Be as specific as possible.  The WORST descriptions possible include
 things like "update driver X", "bug fix for driver X", or "this patch
 includes updates for subsystem X.  Please apply."
 
+The maintainer will thank you if you write your patch description in a
+form which can be easily pulled into Linux's source code management
+system, git, as a "commit log".  See #15, below.
+
 If your description starts to get long, that's a sign that you probably
 need to split up your patch.  See #3, next.
 
@@ -183,8 +187,9 @@ Even if the maintainer did not respond in step #4, make sure to ALWAYS
 copy the maintainer when you change their code.
 
 For small patches you may want to CC the Trivial Patch Monkey
-trivial@kernel.org managed by Jesper Juhl; which collects "trivial"
-patches. Trivial patches must qualify for one of the following rules:
+trivial@kernel.org which collects "trivial" patches. Have a look
+into the MAINTAINERS file for its current manager.
+Trivial patches must qualify for one of the following rules:
  Spelling fixes in documentation
  Spelling fixes which could break grep(1)
  Warning fixes (cluttering with useless warnings is bad)
@@ -196,7 +201,6 @@ patches. Trivial patches must qualify for one of the following rules:
  since people copy, as long as it's trivial)
  Any fix by the author/maintainer of the file (ie. patch monkey
  in re-transmission mode)
-URL: <http://www.kernel.org/pub/linux/kernel/people/juhl/trivial/>
 
 
 
@@ -405,7 +409,14 @@ person it names.  This tag documents that potentially interested parties
 have been included in the discussion
 
 
-14) Using Tested-by: and Reviewed-by:
+14) Using Reported-by:, Tested-by: and Reviewed-by:
+
+If this patch fixes a problem reported by somebody else, consider adding a
+Reported-by: tag to credit the reporter for their contribution.  Please
+note that this tag should not be added without the reporter's permission,
+especially if the problem was not reported in a public forum.  That said,
+if we diligently credit our bug reporters, they will, hopefully, be
+inspired to help us again in the future.
 
 A Tested-by: tag indicates that the patch has been successfully tested (in
 some environment) by the person named.  This tag informs maintainers that
@@ -444,7 +455,7 @@ offer a Reviewed-by tag for a patch.  This tag serves to give credit to
 reviewers and to inform maintainers of the degree of review which has been
 done on the patch.  Reviewed-by: tags, when supplied by reviewers known to
 understand the subject area and to perform thorough reviews, will normally
-increase the liklihood of your patch getting into the kernel.
+increase the likelihood of your patch getting into the kernel.
 
 
 15) The canonical patch format
@@ -485,12 +496,33 @@ phrase" should not be a filename.  Do not use the same "summary
 phrase" for every patch in a whole patch series (where a "patch
 series" is an ordered sequence of multiple, related patches).
 
-Bear in mind that the "summary phrase" of your email becomes
-a globally-unique identifier for that patch.  It propagates
-all the way into the git changelog.  The "summary phrase" may
-later be used in developer discussions which refer to the patch.
-People will want to google for the "summary phrase" to read
-discussion regarding that patch.
+Bear in mind that the "summary phrase" of your email becomes a
+globally-unique identifier for that patch.  It propagates all the way
+into the git changelog.  The "summary phrase" may later be used in
+developer discussions which refer to the patch.  People will want to
+google for the "summary phrase" to read discussion regarding that
+patch.  It will also be the only thing that people may quickly see
+when, two or three months later, they are going through perhaps
+thousands of patches using tools such as "gitk" or "git log
+--oneline".
+
+For these reasons, the "summary" must be no more than 70-75
+characters, and it must describe both what the patch changes, as well
+as why the patch might be necessary.  It is challenging to be both
+succinct and descriptive, but that is what a well-written summary
+should do.
+
+The "summary phrase" may be prefixed by tags enclosed in square
+brackets: "Subject: [PATCH tag] <summary phrase>".  The tags are not
+considered part of the summary phrase, but describe how the patch
+should be treated.  Common tags might include a version descriptor if
+the multiple versions of the patch have been sent out in response to
+comments (i.e., "v1, v2, v3"), or "RFC" to indicate a request for
+comments.  If there are four patches in a patch series the individual
+patches may be numbered like this: 1/4, 2/4, 3/4, 4/4.  This assures
+that developers understand the order in which the patches should be
+applied and that they have reviewed or applied all of the patches in
+the patch series.
 
 A couple of example Subjects:
 
@@ -510,19 +542,31 @@ the patch author in the changelog.
 The explanation body will be committed to the permanent source
 changelog, so should make sense to a competent reader who has long
 since forgotten the immediate details of the discussion that might
-have led to this patch.
+have led to this patch.  Including symptoms of the failure which the
+patch addresses (kernel log messages, oops messages, etc.) is
+especially useful for people who might be searching the commit logs
+looking for the applicable patch.  If a patch fixes a compile failure,
+it may not be necessary to include _all_ of the compile failures; just
+enough that it is likely that someone searching for the patch can find
+it.  As in the "summary phrase", it is important to be both succinct as
+well as descriptive.
 
 The "---" marker line serves the essential purpose of marking for patch
 handling tools where the changelog message ends.
 
 One good use for the additional comments after the "---" marker is for
-a diffstat, to show what files have changed, and the number of inserted
-and deleted lines per file.  A diffstat is especially useful on bigger
-patches.  Other comments relevant only to the moment or the maintainer,
-not suitable for the permanent changelog, should also go here.
-Use diffstat options "-p 1 -w 70" so that filenames are listed from the
-top of the kernel source tree and don't use too much horizontal space
-(easily fit in 80 columns, maybe with some indentation).
+a diffstat, to show what files have changed, and the number of
+inserted and deleted lines per file.  A diffstat is especially useful
+on bigger patches.  Other comments relevant only to the moment or the
+maintainer, not suitable for the permanent changelog, should also go
+here.  A good example of such comments might be "patch changelogs"
+which describe what has changed between the v1 and v2 version of the
+patch.
+
+If you are going to include a diffstat after the "---" marker, please
+use diffstat options "-p 1 -w 70" so that filenames are listed from
+the top of the kernel source tree and don't use too much horizontal
+space (easily fit in 80 columns, maybe with some indentation).
 
 See more details on the proper patch format in the following
 references.
diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c
index 7ea231172c8..aa73e72fd79 100644
--- a/Documentation/accounting/getdelays.c
+++ b/Documentation/accounting/getdelays.c
@@ -246,7 +246,8 @@ void print_ioacct(struct taskstats *t)
 
 int main(int argc, char *argv[])
 {
-	int c, rc, rep_len, aggr_len, len2, cmd_type;
+	int c, rc, rep_len, aggr_len, len2;
+	int cmd_type = TASKSTATS_CMD_ATTR_UNSPEC;
 	__u16 id;
 	__u32 mypid;
 
diff --git a/Documentation/arm/Samsung-S3C24XX/GPIO.txt b/Documentation/arm/Samsung-S3C24XX/GPIO.txt
index ea7ccfc4b27..948c8718d96 100644
--- a/Documentation/arm/Samsung-S3C24XX/GPIO.txt
+++ b/Documentation/arm/Samsung-S3C24XX/GPIO.txt
@@ -51,7 +51,7 @@ PIN Numbers
 -----------
 
   Each pin has an unique number associated with it in regs-gpio.h,
-  eg S3C2410_GPA0 or S3C2410_GPF1. These defines are used to tell
+  eg S3C2410_GPA(0) or S3C2410_GPF(1). These defines are used to tell
   the GPIO functions which pin is to be used.
 
 
@@ -65,11 +65,11 @@ Configuring a pin
 
   Eg:
 
-     s3c2410_gpio_cfgpin(S3C2410_GPA0, S3C2410_GPA0_ADDR0);
-     s3c2410_gpio_cfgpin(S3C2410_GPE8, S3C2410_GPE8_SDDAT1);
+     s3c2410_gpio_cfgpin(S3C2410_GPA(0), S3C2410_GPA0_ADDR0);
+     s3c2410_gpio_cfgpin(S3C2410_GPE(8), S3C2410_GPE8_SDDAT1);
 
-   which would turn GPA0 into the lowest Address line A0, and set
-   GPE8 to be connected to the SDIO/MMC controller's SDDAT1 line.
+   which would turn GPA(0) into the lowest Address line A0, and set
+   GPE(8) to be connected to the SDIO/MMC controller's SDDAT1 line.
 
 
 Reading the current configuration
diff --git a/Documentation/atomic_ops.txt b/Documentation/atomic_ops.txt
index 4ef24501045..396bec3b74e 100644
--- a/Documentation/atomic_ops.txt
+++ b/Documentation/atomic_ops.txt
@@ -229,10 +229,10 @@ kernel.  It is the use of atomic counters to implement reference
 counting, and it works such that once the counter falls to zero it can
 be guaranteed that no other entity can be accessing the object:
 
-static void obj_list_add(struct obj *obj)
+static void obj_list_add(struct obj *obj, struct list_head *head)
 {
 	obj->active = 1;
-	list_add(&obj->list);
+	list_add(&obj->list, head);
 }
 
 static void obj_list_del(struct obj *obj)
diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt
index 6fab97ea7e6..8d2158a1c6a 100644
--- a/Documentation/block/biodoc.txt
+++ b/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/PCI/PCI-DMA-mapping.txt for a discussion
+Note: Please refer to Documentation/DMA-mapping.txt for a discussion
 on PCI high mem DMA aspects and mapping of scatter gather lists, and support
 for 64 bit PCI.
 
diff --git a/Documentation/block/deadline-iosched.txt b/Documentation/block/deadline-iosched.txt
index 72576769e0f..2d82c80322c 100644
--- a/Documentation/block/deadline-iosched.txt
+++ b/Documentation/block/deadline-iosched.txt
@@ -58,7 +58,7 @@ same criteria as reads.
 front_merges	(bool)
 ------------
 
-Sometimes it happens that a request enters the io scheduler that is contigious
+Sometimes it happens that a request enters the io scheduler that is contiguous
 with a request that is already on the queue. Either it fits in the back of that
 request, or it fits at the front. That is called either a back merge candidate
 or a front merge candidate. Due to the way files are typically laid out,
diff --git a/Documentation/braille-console.txt b/Documentation/braille-console.txt
index 000b0fbdc10..d0d042c2fd5 100644
--- a/Documentation/braille-console.txt
+++ b/Documentation/braille-console.txt
@@ -27,7 +27,7 @@ parameter.
 
 For simplicity, only one braille console can be enabled, other uses of
 console=brl,... will be discarded.  Also note that it does not interfere with
-the console selection mecanism described in serial-console.txt
+the console selection mechanism described in serial-console.txt
 
 For now, only the VisioBraille device is supported.
 
diff --git a/Documentation/cdrom/packet-writing.txt b/Documentation/cdrom/packet-writing.txt
index cf1f8126991..1c407778c8b 100644
--- a/Documentation/cdrom/packet-writing.txt
+++ b/Documentation/cdrom/packet-writing.txt
@@ -117,7 +117,7 @@ Using the pktcdvd debugfs interface
 
 To read pktcdvd device infos in human readable form, do:
 
-	# cat /debug/pktcdvd/pktcdvd[0-7]/info
+	# cat /sys/kernel/debug/pktcdvd/pktcdvd[0-7]/info
 
 For a description of the debugfs interface look into the file:
 
diff --git a/Documentation/dell_rbu.txt b/Documentation/dell_rbu.txt
index c11b931f8f9..15174985ad0 100644
--- a/Documentation/dell_rbu.txt
+++ b/Documentation/dell_rbu.txt
@@ -76,9 +76,9 @@ Do the steps below to download the BIOS image.
 
 The /sys/class/firmware/dell_rbu/ entries will remain till the following is
 done.
-echo -1 > /sys/class/firmware/dell_rbu/loading.
+echo -1 > /sys/class/firmware/dell_rbu/loading
 Until this step is completed the driver cannot be unloaded.
-Also echoing either mono ,packet or init in to image_type will free up the
+Also echoing either mono, packet or init in to image_type will free up the
 memory allocated by the driver.
 
 If a user by accident executes steps 1 and 3 above without executing step 2;
diff --git a/Documentation/development-process/5.Posting b/Documentation/development-process/5.Posting
index dd48132a74d..f622c1e9f0f 100644
--- a/Documentation/development-process/5.Posting
+++ b/Documentation/development-process/5.Posting
@@ -119,7 +119,7 @@ which takes quite a bit of time and thought after the "real work" has been
 done.  When done properly, though, it is time well spent.
 
 
-5.4: PATCH FORMATTING
+5.4: PATCH FORMATTING AND CHANGELOGS
 
 So now you have a perfect series of patches for posting, but the work is
 not done quite yet.  Each patch needs to be formatted into a message which
@@ -146,8 +146,33 @@ that end, each patch will be composed of the following:
  - One or more tag lines, with, at a minimum, one Signed-off-by: line from
    the author of the patch.  Tags will be described in more detail below.
 
-The above three items should, normally, be the text used when committing
-the change to a revision control system.  They are followed by:
+The items above, together, form the changelog for the patch.  Writing good
+changelogs is a crucial but often-neglected art; it's worth spending
+another moment discussing this issue.  When writing a changelog, you should
+bear in mind that a number of different people will be reading your words.
+These include subsystem maintainers and reviewers who need to decide
+whether the patch should be included, distributors and other maintainers
+trying to decide whether a patch should be backported to other kernels, bug
+hunters wondering whether the patch is responsible for a problem they are
+chasing, users who want to know how the kernel has changed, and more.  A
+good changelog conveys the needed information to all of these people in the
+most direct and concise way possible.
+
+To that end, the summary line should describe the effects of and motivation
+for the change as well as possible given the one-line constraint.  The
+detailed description can then amplify on those topics and provide any
+needed additional information.  If the patch fixes a bug, cite the commit
+which introduced the bug if possible.  If a problem is associated with
+specific log or compiler output, include that output to help others
+searching for a solution to the same problem.  If the change is meant to
+support other changes coming in later patch, say so.  If internal APIs are
+changed, detail those changes and how other developers should respond.  In
+general, the more you can put yourself into the shoes of everybody who will
+be reading your changelog, the better that changelog (and the kernel as a
+whole) will be.
+
+Needless to say, the changelog should be the text used when committing the
+change to a revision control system.  It will be followed by:
 
  - The patch itself, in the unified ("-u") patch format.  Using the "-p"
    option to diff will associate function names with changes, making the
diff --git a/Documentation/driver-model/device.txt b/Documentation/driver-model/device.txt
index a7cbfff40d0..a124f3126b0 100644
--- a/Documentation/driver-model/device.txt
+++ b/Documentation/driver-model/device.txt
@@ -162,3 +162,35 @@ device_remove_file(dev,&dev_attr_power);
 
 The file name will be 'power' with a mode of 0644 (-rw-r--r--).
 
+Word of warning:  While the kernel allows device_create_file() and
+device_remove_file() to be called on a device at any time, userspace has
+strict expectations on when attributes get created.  When a new device is
+registered in the kernel, a uevent is generated to notify userspace (like
+udev) that a new device is available.  If attributes are added after the
+device is registered, then userspace won't get notified and userspace will
+not know about the new attributes.
+
+This is important for device driver that need to publish additional
+attributes for a device at driver probe time.  If the device driver simply
+calls device_create_file() on the device structure passed to it, then
+userspace will never be notified of the new attributes.  Instead, it should
+probably use class_create() and class->dev_attrs to set up a list of
+desired attributes in the modules_init function, and then in the .probe()
+hook, and then use device_create() to create a new device as a child
+of the probed device.  The new device will generate a new uevent and
+properly advertise the new attributes to userspace.
+
+For example, if a driver wanted to add the following attributes:
+struct device_attribute mydriver_attribs[] = {
+	__ATTR(port_count, 0444, port_count_show),
+	__ATTR(serial_number, 0444, serial_number_show),
+	NULL
+};
+
+Then in the module init function is would do:
+	mydriver_class = class_create(THIS_MODULE, "my_attrs");
+	mydriver_class.dev_attr = mydriver_attribs;
+
+And assuming 'dev' is the struct device passed into the probe hook, the driver
+probe function would do something like:
+	create_device(&mydriver_class, dev, chrdev, &private_data, "my_name");
diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt
index 387b8a720f4..d79aead9418 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -188,7 +188,7 @@ For example, you can do something like the following.
 
   void my_midlayer_destroy_something()
   {
-	devres_release_group(dev, my_midlayer_create_soemthing);
+	devres_release_group(dev, my_midlayer_create_something);
   }
 
 
diff --git a/Documentation/dvb/get_dvb_firmware b/Documentation/dvb/get_dvb_firmware
index 2f21ecd4c20..a52adfc9a57 100644
--- a/Documentation/dvb/get_dvb_firmware
+++ b/Documentation/dvb/get_dvb_firmware
@@ -112,7 +112,7 @@ sub tda10045 {
 
 sub tda10046 {
 	my $sourcefile = "TT_PCI_2.19h_28_11_2006.zip";
-	my $url = "http://technotrend-online.com/download/software/219/$sourcefile";
+	my $url = "http://www.tt-download.com/download/updates/219/$sourcefile";
 	my $hash = "6a7e1e2f2644b162ff0502367553c72d";
 	my $outfile = "dvb-fe-tda10046.fw";
 	my $tmpdir = tempdir(DIR => "/tmp", CLEANUP => 1);
@@ -129,8 +129,8 @@ sub tda10046 {
 }
 
 sub tda10046lifeview {
-    my $sourcefile = "Drv_2.11.02.zip";
-    my $url = "http://www.lifeview.com.tw/drivers/pci_card/FlyDVB-T/$sourcefile";
+    my $sourcefile = "7%5Cdrv_2.11.02.zip";
+    my $url = "http://www.lifeview.hk/dbimages/document/$sourcefile";
     my $hash = "1ea24dee4eea8fe971686981f34fd2e0";
     my $outfile = "dvb-fe-tda10046.fw";
     my $tmpdir = tempdir(DIR => "/tmp", CLEANUP => 1);
@@ -317,7 +317,7 @@ sub nxt2002 {
 
 sub nxt2004 {
     my $sourcefile = "AVerTVHD_MCE_A180_Drv_v1.2.2.16.zip";
-    my $url = "http://www.aver.com/support/Drivers/$sourcefile";
+    my $url = "http://www.avermedia-usa.com/support/Drivers/$sourcefile";
     my $hash = "111cb885b1e009188346d72acfed024c";
     my $outfile = "dvb-fe-nxt2004.fw";
     my $tmpdir = tempdir(DIR => "/tmp", CLEANUP => 1);
diff --git a/Documentation/edac.txt b/Documentation/edac.txt
index 8eda3fb6641..06f8f46692d 100644
--- a/Documentation/edac.txt
+++ b/Documentation/edac.txt
@@ -23,8 +23,8 @@ first time, it was renamed to 'EDAC'.
 The bluesmoke project at sourceforge.net is now utilized as a 'staging area'
 for EDAC development, before it is sent upstream to kernel.org
 
-At the bluesmoke/EDAC project site, is a series of quilt patches against
-recent kernels, stored in a SVN respository. For easier downloading, there
+At the bluesmoke/EDAC project site is a series of quilt patches against
+recent kernels, stored in a SVN repository. For easier downloading, there
 is also a tarball snapshot available.
 
 ============================================================================
@@ -73,9 +73,9 @@ the vendor should tie the parity status bits to 0 if they do not intend
 to generate parity.  Some vendors do not do this, and thus the parity bit
 can "float" giving false positives.
 
-In the kernel there is a pci device attribute located in sysfs that is
+In the kernel there is a PCI device attribute located in sysfs that is
 checked by the EDAC PCI scanning code. If that attribute is set,
-PCI parity/error scannining is skipped for that device. The attribute
+PCI parity/error scanning is skipped for that device. The attribute
 is:
 
 	broken_parity_status
diff --git a/Documentation/fault-injection/fault-injection.txt b/Documentation/fault-injection/fault-injection.txt
index 4bc374a1434..07930564079 100644
--- a/Documentation/fault-injection/fault-injection.txt
+++ b/Documentation/fault-injection/fault-injection.txt
@@ -29,16 +29,16 @@ o debugfs entries
 fault-inject-debugfs kernel module provides some debugfs entries for runtime
 configuration of fault-injection capabilities.
 
-- /debug/fail*/probability:
+- /sys/kernel/debug/fail*/probability:
 
 	likelihood of failure injection, in percent.
 	Format: <percent>
 
 	Note that one-failure-per-hundred is a very high error rate
 	for some testcases.  Consider setting probability=100 and configure
-	/debug/fail*/interval for such testcases.
+	/sys/kernel/debug/fail*/interval for such testcases.
 
-- /debug/fail*/interval:
+- /sys/kernel/debug/fail*/interval:
 
 	specifies the interval between failures, for calls to
 	should_fail() that pass all the other tests.
@@ -46,18 +46,18 @@ configuration of fault-injection capabilities.
 	Note that if you enable this, by setting interval>1, you will
 	probably want to set probability=100.
 
-- /debug/fail*/times:
+- /sys/kernel/debug/fail*/times:
 
 	specifies how many times failures may happen at most.
 	A value of -1 means "no limit".
 
-- /debug/fail*/space:
+- /sys/kernel/debug/fail*/space:
 
 	specifies an initial resource "budget", decremented by "size"
 	on each call to should_fail(,size).  Failure injection is
 	suppressed until "space" reaches zero.
 
-- /debug/fail*/verbose
+- /sys/kernel/debug/fail*/verbose
 
 	Format: { 0 | 1 | 2 }
 	specifies the verbosity of the messages when failure is
@@ -65,17 +65,17 @@ configuration of fault-injection capabilities.
 	log line per failure; '2' will print a call trace too -- useful
 	to debug the problems revealed by fault injection.
 
-- /debug/fail*/task-filter:
+- /sys/kernel/debug/fail*/task-filter:
 
 	Format: { 'Y' | 'N' }
 	A value of 'N' disables filtering by process (default).
 	Any positive value limits failures to only processes indicated by
 	/proc/<pid>/make-it-fail==1.
 
-- /debug/fail*/require-start:
-- /debug/fail*/require-end:
-- /debug/fail*/reject-start:
-- /debug/fail*/reject-end:
+- /sys/kernel/debug/fail*/require-start:
+- /sys/kernel/debug/fail*/require-end:
+- /sys/kernel/debug/fail*/reject-start:
+- /sys/kernel/debug/fail*/reject-end:
 
 	specifies the range of virtual addresses tested during
 	stacktrace walking.  Failure is injected only if some caller
@@ -84,26 +84,26 @@ configuration of fault-injection capabilities.
 	Default required range is [0,ULONG_MAX) (whole of virtual address space).
 	Default rejected range is [0,0).
 
-- /debug/fail*/stacktrace-depth:
+- /sys/kernel/debug/fail*/stacktrace-depth:
 
 	specifies the maximum stacktrace depth walked during search
 	for a caller within [require-start,require-end) OR
 	[reject-start,reject-end).
 
-- /debug/fail_page_alloc/ignore-gfp-highmem:
+- /sys/kernel/debug/fail_page_alloc/ignore-gfp-highmem:
 
 	Format: { 'Y' | 'N' }
 	default is 'N', setting it to 'Y' won't inject failures into
 	highmem/user allocations.
 
-- /debug/failslab/ignore-gfp-wait:
-- /debug/fail_page_alloc/ignore-gfp-wait:
+- /sys/kernel/debug/failslab/ignore-gfp-wait:
+- /sys/kernel/debug/fail_page_alloc/ignore-gfp-wait:
 
 	Format: { 'Y' | 'N' }
 	default is 'N', setting it to 'Y' will inject failures
 	only into non-sleep allocations (GFP_ATOMIC allocations).
 
-- /debug/fail_page_alloc/min-order:
+- /sys/kernel/debug/fail_page_alloc/min-order:
 
 	specifies the minimum page allocation order to be injected
 	failures.
@@ -166,13 +166,13 @@ o Inject slab allocation failures into module init/exit code
 #!/bin/bash
 
 FAILTYPE=failslab
-echo Y > /debug/$FAILTYPE/task-filter
-echo 10 > /debug/$FAILTYPE/probability
-echo 100 > /debug/$FAILTYPE/interval
-echo -1 > /debug/$FAILTYPE/times
-echo 0 > /debug/$FAILTYPE/space
-echo 2 > /debug/$FAILTYPE/verbose
-echo 1 > /debug/$FAILTYPE/ignore-gfp-wait
+echo Y > /sys/kernel/debug/$FAILTYPE/task-filter
+echo 10 > /sys/kernel/debug/$FAILTYPE/probability
+echo 100 > /sys/kernel/debug/$FAILTYPE/interval
+echo -1 > /sys/kernel/debug/$FAILTYPE/times
+echo 0 > /sys/kernel/debug/$FAILTYPE/space
+echo 2 > /sys/kernel/debug/$FAILTYPE/verbose
+echo 1 > /sys/kernel/debug/$FAILTYPE/ignore-gfp-wait
 
 faulty_system()
 {
@@ -217,20 +217,20 @@ then
 	exit 1
 fi
 
-cat /sys/module/$module/sections/.text > /debug/$FAILTYPE/require-start
-cat /sys/module/$module/sections/.data > /debug/$FAILTYPE/require-end
+cat /sys/module/$module/sections/.text > /sys/kernel/debug/$FAILTYPE/require-start
+cat /sys/module/$module/sections/.data > /sys/kernel/debug/$FAILTYPE/require-end
 
-echo N > /debug/$FAILTYPE/task-filter
-echo 10 > /debug/$FAILTYPE/probability
-echo 100 > /debug/$FAILTYPE/interval
-echo -1 > /debug/$FAILTYPE/times
-echo 0 > /debug/$FAILTYPE/space
-echo 2 > /debug/$FAILTYPE/verbose
-echo 1 > /debug/$FAILTYPE/ignore-gfp-wait
-echo 1 > /debug/$FAILTYPE/ignore-gfp-highmem
-echo 10 > /debug/$FAILTYPE/stacktrace-depth
+echo N > /sys/kernel/debug/$FAILTYPE/task-filter
+echo 10 > /sys/kernel/debug/$FAILTYPE/probability
+echo 100 > /sys/kernel/debug/$FAILTYPE/interval
+echo -1 > /sys/kernel/debug/$FAILTYPE/times
+echo 0 > /sys/kernel/debug/$FAILTYPE/space
+echo 2 > /sys/kernel/debug/$FAILTYPE/verbose
+echo 1 > /sys/kernel/debug/$FAILTYPE/ignore-gfp-wait
+echo 1 > /sys/kernel/debug/$FAILTYPE/ignore-gfp-highmem
+echo 10 > /sys/kernel/debug/$FAILTYPE/stacktrace-depth
 
-trap "echo 0 > /debug/$FAILTYPE/probability" SIGINT SIGTERM EXIT
+trap "echo 0 > /sys/kernel/debug/$FAILTYPE/probability" SIGINT SIGTERM EXIT
 
 echo "Injecting errors into the module $module... (interrupt to stop)"
 sleep 1000000
diff --git a/Documentation/fb/sh7760fb.txt b/Documentation/fb/sh7760fb.txt
index c87bfe5c630..b994c3b1054 100644
--- a/Documentation/fb/sh7760fb.txt
+++ b/Documentation/fb/sh7760fb.txt
@@ -1,7 +1,7 @@
 SH7760/SH7763 integrated LCDC Framebuffer driver
 ================================================
 
-0. Overwiew
+0. Overview
 -----------
 The SH7760/SH7763 have an integrated LCD Display controller (LCDC) which
 supports (in theory) resolutions ranging from 1x1 to 1024x1024,
diff --git a/Documentation/fb/vesafb.txt b/Documentation/fb/vesafb.txt
index ee277dd204b..950d5a658cb 100644
--- a/Documentation/fb/vesafb.txt
+++ b/Documentation/fb/vesafb.txt
@@ -95,7 +95,7 @@ There is no way to change the vesafb video mode and/or timings after
 booting linux.  If you are not happy with the 60 Hz refresh rate, you
 have these options:
 
- * configure and load the DOS-Tools for your the graphics board (if
+ * configure and load the DOS-Tools for the graphics board (if
    available) and boot linux with loadlin.
  * use a native driver (matroxfb/atyfb) instead if vesafb.  If none
    is available, write a new one!
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index de491a3e231..7129846a278 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -437,3 +437,20 @@ Why:	Superseded by tdfxfb. I2C/DDC support used to live in a separate
 	driver but this caused driver conflicts.
 Who:	Jean Delvare <khali@linux-fr.org>
 	Krzysztof Helt <krzysztof.h1@wp.pl>
+
+---------------------------
+
+What:	CONFIG_RFKILL_INPUT
+When:	2.6.33
+Why:	Should be implemented in userspace, policy daemon.
+Who:	Johannes Berg <johannes@sipsolutions.net>
+
+----------------------------
+
+What:	CONFIG_X86_OLD_MCE
+When:	2.6.32
+Why:	Remove the old legacy 32bit machine check code. This has been
+	superseded by the newer machine check code from the 64bit port,
+	but the old version has been kept around for easier testing. Note this
+	doesn't impact the old P5 and WinChip machine check handlers.
+Who:	Andi Kleen <andi@firstfloor.org>
diff --git a/Documentation/filesystems/autofs4-mount-control.txt b/Documentation/filesystems/autofs4-mount-control.txt
index c6341745df3..8f78ded4b64 100644
--- a/Documentation/filesystems/autofs4-mount-control.txt
+++ b/Documentation/filesystems/autofs4-mount-control.txt
@@ -369,7 +369,7 @@ The call requires an initialized struct autofs_dev_ioctl. There are two
 possible variations. Both use the path field set to the path of the mount
 point to check and the size field adjusted appropriately. One uses the
 ioctlfd field to identify a specific mount point to check while the other
-variation uses the path and optionaly arg1 set to an autofs mount type.
+variation uses the path and optionally arg1 set to an autofs mount type.
 The call returns 1 if this is a mount point and sets arg1 to the device
 number of the mount and field arg2 to the relevant super block magic
 number (described below) or 0 if it isn't a mountpoint. In both cases
diff --git a/Documentation/filesystems/caching/netfs-api.txt b/Documentation/filesystems/caching/netfs-api.txt
index 4db125b3a5c..2666b1ed5e9 100644
--- a/Documentation/filesystems/caching/netfs-api.txt
+++ b/Documentation/filesystems/caching/netfs-api.txt
@@ -184,7 +184,7 @@ This has the following fields:
      have index children.
 
      If this function is not supplied or if it returns NULL then the first
-     cache in the parent's list will be chosed, or failing that, the first
+     cache in the parent's list will be chosen, or failing that, the first
      cache in the master list.
 
  (4) A function to retrieve an object's key from the netfs [mandatory].
diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt
new file mode 100644
index 00000000000..ed52af60c2d
--- /dev/null
+++ b/Documentation/filesystems/debugfs.txt
@@ -0,0 +1,158 @@
+Copyright 2009 Jonathan Corbet <corbet@lwn.net>
+
+Debugfs exists as a simple way for kernel developers to make information
+available to user space.  Unlike /proc, which is only meant for information
+about a process, or sysfs, which has strict one-value-per-file rules,
+debugfs has no rules at all.  Developers can put any information they want
+there.  The debugfs filesystem is also intended to not serve as a stable
+ABI to user space; in theory, there are no stability constraints placed on
+files exported there.  The real world is not always so simple, though [1];
+even debugfs interfaces are best designed with the idea that they will need
+to be maintained forever.
+
+Debugfs is typically mounted with a command like:
+
+    mount -t debugfs none /sys/kernel/debug
+
+(Or an equivalent /etc/fstab line). 
+
+Note that the debugfs API is exported GPL-only to modules.
+
+Code using debugfs should include <linux/debugfs.h>.  Then, the first order
+of business will be to create at least one directory to hold a set of
+debugfs files:
+
+    struct dentry *debugfs_create_dir(const char *name, struct dentry *parent);
+
+This call, if successful, will make a directory called name underneath the
+indicated parent directory.  If parent is NULL, the directory will be
+created in the debugfs root.  On success, the return value is a struct
+dentry pointer which can be used to create files in the directory (and to
+clean it up at the end).  A NULL return value indicates that something went
+wrong.  If ERR_PTR(-ENODEV) is returned, that is an indication that the
+kernel has been built without debugfs support and none of the functions
+described below will work.
+
+The most general way to create a file within a debugfs directory is with:
+
+    struct dentry *debugfs_create_file(const char *name, mode_t mode,
+				       struct dentry *parent, void *data,
+				       const struct file_operations *fops);
+
+Here, name is the name of the file to create, mode describes the access
+permissions the file should have, parent indicates the directory which
+should hold the file, data will be stored in the i_private field of the
+resulting inode structure, and fops is a set of file operations which
+implement the file's behavior.  At a minimum, the read() and/or write()
+operations should be provided; others can be included as needed.  Again,
+the return value will be a dentry pointer to the created file, NULL for
+error, or ERR_PTR(-ENODEV) if debugfs support is missing.
+
+In a number of cases, the creation of a set of file operations is not
+actually necessary; the debugfs code provides a number of helper functions
+for simple situations.  Files containing a single integer value can be
+created with any of:
+
+    struct dentry *debugfs_create_u8(const char *name, mode_t mode,
+				     struct dentry *parent, u8 *value);
+    struct dentry *debugfs_create_u16(const char *name, mode_t mode,
+				      struct dentry *parent, u16 *value);
+    struct dentry *debugfs_create_u32(const char *name, mode_t mode,
+				      struct dentry *parent, u32 *value);
+    struct dentry *debugfs_create_u64(const char *name, mode_t mode,
+				      struct dentry *parent, u64 *value);
+
+These files support both reading and writing the given value; if a specific
+file should not be written to, simply set the mode bits accordingly.  The
+values in these files are in decimal; if hexadecimal is more appropriate,
+the following functions can be used instead:
+
+    struct dentry *debugfs_create_x8(const char *name, mode_t mode,
+				     struct dentry *parent, u8 *value);
+    struct dentry *debugfs_create_x16(const char *name, mode_t mode,
+				      struct dentry *parent, u16 *value);
+    struct dentry *debugfs_create_x32(const char *name, mode_t mode,
+				      struct dentry *parent, u32 *value);
+
+Note that there is no debugfs_create_x64().
+
+These functions are useful as long as the developer knows the size of the
+value to be exported.  Some types can have different widths on different
+architectures, though, complicating the situation somewhat.  There is a
+function meant to help out in one special case:
+
+    struct dentry *debugfs_create_size_t(const char *name, mode_t mode,
+				         struct dentry *parent, 
+					 size_t *value);
+
+As might be expected, this function will create a debugfs file to represent
+a variable of type size_t.
+
+Boolean values can be placed in debugfs with:
+
+    struct dentry *debugfs_create_bool(const char *name, mode_t mode,
+				       struct dentry *parent, u32 *value);
+
+A read on the resulting file will yield either Y (for non-zero values) or
+N, followed by a newline.  If written to, it will accept either upper- or
+lower-case values, or 1 or 0.  Any other input will be silently ignored.
+
+Finally, a block of arbitrary binary data can be exported with:
+
+    struct debugfs_blob_wrapper {
+	void *data;
+	unsigned long size;
+    };
+
+    struct dentry *debugfs_create_blob(const char *name, mode_t mode,
+				       struct dentry *parent,
+				       struct debugfs_blob_wrapper *blob);
+
+A read of this file will return the data pointed to by the
+debugfs_blob_wrapper structure.  Some drivers use "blobs" as a simple way
+to return several lines of (static) formatted text output.  This function
+can be used to export binary information, but there does not appear to be
+any code which does so in the mainline.  Note that all files created with
+debugfs_create_blob() are read-only.
+
+There are a couple of other directory-oriented helper functions:
+
+    struct dentry *debugfs_rename(struct dentry *old_dir, 
+    				  struct dentry *old_dentry,
+		                  struct dentry *new_dir, 
+				  const char *new_name);
+
+    struct dentry *debugfs_create_symlink(const char *name, 
+                                          struct dentry *parent,
+				      	  const char *target);
+
+A call to debugfs_rename() will give a new name to an existing debugfs
+file, possibly in a different directory.  The new_name must not exist prior
+to the call; the return value is old_dentry with updated information.
+Symbolic links can be created with debugfs_create_symlink().
+
+There is one important thing that all debugfs users must take into account:
+there is no automatic cleanup of any directories created in debugfs.  If a
+module is unloaded without explicitly removing debugfs entries, the result
+will be a lot of stale pointers and no end of highly antisocial behavior.
+So all debugfs users - at least those which can be built as modules - must
+be prepared to remove all files and directories they create there.  A file
+can be removed with:
+
+    void debugfs_remove(struct dentry *dentry);
+
+The dentry value can be NULL, in which case nothing will be removed.
+
+Once upon a time, debugfs users were required to remember the dentry
+pointer for every debugfs file they created so that all files could be
+cleaned up.  We live in more civilized times now, though, and debugfs users
+can call:
+
+    void debugfs_remove_recursive(struct dentry *dentry);
+
+If this function is passed a pointer for the dentry corresponding to the
+top-level directory, the entire hierarchy below that directory will be
+removed.
+
+Notes:
+	[1] http://lwn.net/Articles/309298/
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 97882df0486..608fdba97b7 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -294,7 +294,7 @@ max_batch_time=usec	Maximum amount of time ext4 should wait for
 			amount of time (on average) that it takes to
 			finish committing a transaction.  Call this time
 			the "commit time".  If the time that the
-			transactoin has been running is less than the
+			transaction has been running is less than the
 			commit time, ext4 will try sleeping for the
 			commit time to see if other operations will join
 			the transaction.   The commit time is capped by
@@ -328,7 +328,7 @@ noauto_da_alloc		replacing existing files via patterns such as
 			journal commit, in the default data=ordered
 			mode, the data blocks of the new file are forced
 			to disk before the rename() operation is
-			commited.  This provides roughly the same level
+			committed.  This provides roughly the same level
 			of guarantees as ext3, and avoids the
 			"zero-length" problem that can happen when a
 			system crashes before the delayed allocation
@@ -358,7 +358,7 @@ written to the journal first, and then to its final location.
 In the event of a crash, the journal can be replayed, bringing both data and
 metadata into a consistent state.  This mode is the slowest except when data
 needs to be read from and written to disk at the same time where it
-outperforms all others modes.  Curently ext4 does not have delayed
+outperforms all others modes.  Currently ext4 does not have delayed
 allocation support if this data journalling mode is selected.
 
 References
diff --git a/Documentation/filesystems/fiemap.txt b/Documentation/filesystems/fiemap.txt
index 1e3defcfe50..606233cd461 100644
--- a/Documentation/filesystems/fiemap.txt
+++ b/Documentation/filesystems/fiemap.txt
@@ -204,7 +204,7 @@ fiemap_check_flags() helper:
 
 int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
 
-The struct fieinfo should be passed in as recieved from ioctl_fiemap(). The
+The struct fieinfo should be passed in as received from ioctl_fiemap(). The
 set of fiemap flags which the fs understands should be passed via fs_flags. If
 fiemap_check_flags finds invalid user flags, it will place the bad values in
 fieinfo->fi_flags and return -EBADR. If the file system gets -EBADR, from
diff --git a/Documentation/filesystems/gfs2-glocks.txt b/Documentation/filesystems/gfs2-glocks.txt
index 4dae9a3840b..0494f78d87e 100644
--- a/Documentation/filesystems/gfs2-glocks.txt
+++ b/Documentation/filesystems/gfs2-glocks.txt
@@ -60,7 +60,7 @@ go_lock          | Called for the first local holder of a lock
 go_unlock        | Called on the final local unlock of a lock
 go_dump          | Called to print content of object for debugfs file, or on
                  | error to dump glock to the log.
-go_type;         | The type of the glock, LM_TYPE_.....
+go_type          | The type of the glock, LM_TYPE_.....
 go_min_hold_time | The minimum hold time
 
 The minimum hold time for each lock is the time after a remote lock
diff --git a/Documentation/filesystems/gfs2.txt b/Documentation/filesystems/gfs2.txt
index 593004b6bba..5e3ab8f3bef 100644
--- a/Documentation/filesystems/gfs2.txt
+++ b/Documentation/filesystems/gfs2.txt
@@ -11,18 +11,15 @@ their I/O so file system consistency is maintained.  One of the nifty
 features of GFS is perfect consistency -- changes made to the file system
 on one machine show up immediately on all other machines in the cluster.
 
-GFS uses interchangable inter-node locking mechanisms.  Different lock
-modules can plug into GFS and each file system selects the appropriate
-lock module at mount time.  Lock modules include:
+GFS uses interchangable inter-node locking mechanisms, the currently
+supported mechanisms are:
 
   lock_nolock -- allows gfs to be used as a local file system
 
   lock_dlm -- uses a distributed lock manager (dlm) for inter-node locking
   The dlm is found at linux/fs/dlm/
 
-In addition to interfacing with an external locking manager, a gfs lock
-module is responsible for interacting with external cluster management
-systems.  Lock_dlm depends on user space cluster management systems found
+Lock_dlm depends on user space cluster management systems found
 at the URL above.
 
 To use gfs as a local file system, no external clustering systems are
@@ -31,13 +28,19 @@ needed, simply:
   $ mkfs -t gfs2 -p lock_nolock -j 1 /dev/block_device
   $ mount -t gfs2 /dev/block_device /dir
 
-GFS2 is not on-disk compatible with previous versions of GFS.
+If you are using Fedora, you need to install the gfs2-utils package
+and, for lock_dlm, you will also need to install the cman package
+and write a cluster.conf as per the documentation.
+
+GFS2 is not on-disk compatible with previous versions of GFS, but it
+is pretty close.
 
 The following man pages can be found at the URL above:
-  gfs2_fsck	to repair a filesystem
+  fsck.gfs2	to repair a filesystem
   gfs2_grow	to expand a filesystem online
   gfs2_jadd	to add journals to a filesystem online
   gfs2_tool	to manipulate, examine and tune a filesystem
   gfs2_quota	to examine and change quota values in a filesystem
+  gfs2_convert	to convert a gfs filesystem to gfs2 in-place
   mount.gfs2	to help mount(8) mount a filesystem
   mkfs.gfs2	to make a filesystem
diff --git a/Documentation/filesystems/nfs-rdma.txt b/Documentation/filesystems/nfs-rdma.txt
index 85eaeaddd27..e386f7e4bce 100644
--- a/Documentation/filesystems/nfs-rdma.txt
+++ b/Documentation/filesystems/nfs-rdma.txt
@@ -100,7 +100,7 @@ Installation
     $ sudo cp utils/mount/mount.nfs /sbin/mount.nfs
 
     In this location, mount.nfs will be invoked automatically for NFS mounts
-    by the system mount commmand.
+    by the system mount command.
 
     NOTE: mount.nfs and therefore nfs-utils-1.1.2 or greater is only needed
     on the NFS client machine. You do not need this specific version of
diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.txt
index 55c4300abfc..01539f41067 100644
--- a/Documentation/filesystems/nilfs2.txt
+++ b/Documentation/filesystems/nilfs2.txt
@@ -39,9 +39,8 @@ Features which NILFS2 does not support yet:
 	- extended attributes
 	- POSIX ACLs
 	- quotas
-	- writable snapshots
-	- remote backup (CDP)
-	- data integrity
+	- fsck
+	- resize
 	- defragmentation
 
 Mount options
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index ce84cfc9eae..ebff3c10a07 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -366,7 +366,7 @@ just those considered 'most important'.  The new vectors are:
   RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are
   sent from one CPU to another per the needs of the OS.  Typically,
   their statistics are used by kernel developers and interested users to
-  determine the occurance of interrupt of the given type.
+  determine the occurrence of interrupts of the given type.
 
 The above IRQ vectors are displayed only when relevent.  For example,
 the threshold vector does not exist on x86_64 platforms.  Others are
@@ -551,7 +551,7 @@ Committed_AS: The amount of memory presently allocated on the system.
               memory once that memory has been successfully allocated.
 VmallocTotal: total size of vmalloc memory area
  VmallocUsed: amount of vmalloc area which is used
-VmallocChunk: largest contigious block of vmalloc area which is free
+VmallocChunk: largest contiguous block of vmalloc area which is free
 
 ..............................................................................
 
@@ -1003,11 +1003,13 @@ CHAPTER 3: PER-PROCESS PARAMETERS
 3.1 /proc/<pid>/oom_adj - Adjust the oom-killer score
 ------------------------------------------------------
 
-This file can be used to adjust the score used to select which processes
-should be killed in an  out-of-memory  situation.  Giving it a high score will
-increase the likelihood of this process being killed by the oom-killer.  Valid
-values are in the range -16 to +15, plus the special value -17, which disables
-oom-killing altogether for this process.
+This file can be used to adjust the score used to select which processes should
+be killed in an out-of-memory situation.  The oom_adj value is a characteristic
+of the task's mm, so all threads that share an mm with pid will have the same
+oom_adj value.  A high value will increase the likelihood of this process being
+killed by the oom-killer.  Valid values are in the range -16 to +15 as
+explained below and a special value of -17, which disables oom-killing
+altogether for threads sharing pid's mm.
 
 The process to be killed in an out-of-memory situation is selected among all others
 based on its badness score. This value equals the original memory size of the process
@@ -1021,6 +1023,9 @@ the parent's score if they do not share the same memory. Thus forking servers
 are the prime candidates to be killed. Having only one 'hungry' child will make
 parent less preferable than the child.
 
+/proc/<pid>/oom_adj cannot be changed for kthreads since they are immune from
+oom-killing already.
+
 /proc/<pid>/oom_score shows process' current badness score.
 
 The following heuristics are then applied:
diff --git a/Documentation/filesystems/sysfs-pci.txt b/Documentation/filesystems/sysfs-pci.txt
index 26e4b8bc53e..85354b32d73 100644
--- a/Documentation/filesystems/sysfs-pci.txt
+++ b/Documentation/filesystems/sysfs-pci.txt
@@ -72,7 +72,7 @@ The 'rom' file is special in that it provides read-only access to the device's
 ROM file, if available.  It's disabled by default, however, so applications
 should write the string "1" to the file to enable it before attempting a read
 call, and disable it following the access by writing "0" to the file.  Note
-that the device must be enabled for a rom read to return data succesfully.
+that the device must be enabled for a rom read to return data successfully.
 In the event a driver is not bound to the device, it can be enabled using the
 'enable' file, documented above.
 
diff --git a/Documentation/filesystems/tmpfs.txt b/Documentation/filesystems/tmpfs.txt
index 222437efd75..3015da0c6b2 100644
--- a/Documentation/filesystems/tmpfs.txt
+++ b/Documentation/filesystems/tmpfs.txt
@@ -133,4 +133,4 @@ RAM/SWAP in 10240 inodes and it is only accessible by root.
 Author:
    Christoph Rohland <cr@sap.com>, 1.12.01
 Updated:
-   Hugh Dickins <hugh@veritas.com>, 4 June 2007
+   Hugh Dickins, 4 June 2007
diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt
index 3a5ddc96901..b58b84b50fa 100644
--- a/Documentation/filesystems/vfat.txt
+++ b/Documentation/filesystems/vfat.txt
@@ -124,14 +124,19 @@ sys_immutable -- If set, ATTR_SYS attribute on FAT is handled as
 flush         -- If set, the filesystem will try to flush to disk more
 		 early than normal. Not set by default.
 
-rodir	      -- FAT has the ATTR_RO (read-only) attribute. But on Windows,
-		 the ATTR_RO of the directory will be just ignored actually,
-		 and is used by only applications as flag. E.g. it's setted
-		 for the customized folder.
+rodir	      -- FAT has the ATTR_RO (read-only) attribute. On Windows,
+		 the ATTR_RO of the directory will just be ignored,
+		 and is used only by applications as a flag (e.g. it's set
+		 for the customized folder).
 
 		 If you want to use ATTR_RO as read-only flag even for
 		 the directory, set this option.
 
+errors=panic|continue|remount-ro
+	      -- specify FAT behavior on critical errors: panic, continue
+		 without doing anything or remount the partition in
+		 read-only mode (default behavior).
+
 <bool>: 0,1,yes,no,true,false
 
 TODO
diff --git a/Documentation/firmware_class/README b/Documentation/firmware_class/README
index c3480aa66ba..7eceaff63f5 100644
--- a/Documentation/firmware_class/README
+++ b/Documentation/firmware_class/README
@@ -77,7 +77,8 @@
    seconds for the whole load operation.
 
  - request_firmware_nowait() is also provided for convenience in
-   non-user contexts.
+   user contexts to request firmware asynchronously, but can't be called
+   in atomic contexts.
 
 
  about in-kernel persistence:
diff --git a/Documentation/futex-requeue-pi.txt b/Documentation/futex-requeue-pi.txt
new file mode 100644
index 00000000000..9dc1ff4fd53
--- /dev/null
+++ b/Documentation/futex-requeue-pi.txt
@@ -0,0 +1,131 @@
+Futex Requeue PI
+----------------
+
+Requeueing of tasks from a non-PI futex to a PI futex requires
+special handling in order to ensure the underlying rt_mutex is never
+left without an owner if it has waiters; doing so would break the PI
+boosting logic [see rt-mutex-desgin.txt] For the purposes of
+brevity, this action will be referred to as "requeue_pi" throughout
+this document.  Priority inheritance is abbreviated throughout as
+"PI".
+
+Motivation
+----------
+
+Without requeue_pi, the glibc implementation of
+pthread_cond_broadcast() must resort to waking all the tasks waiting
+on a pthread_condvar and letting them try to sort out which task
+gets to run first in classic thundering-herd formation.  An ideal
+implementation would wake the highest-priority waiter, and leave the
+rest to the natural wakeup inherent in unlocking the mutex
+associated with the condvar.
+
+Consider the simplified glibc calls:
+
+/* caller must lock mutex */
+pthread_cond_wait(cond, mutex)
+{
+	lock(cond->__data.__lock);
+	unlock(mutex);
+	do {
+	   unlock(cond->__data.__lock);
+	   futex_wait(cond->__data.__futex);
+	   lock(cond->__data.__lock);
+	} while(...)
+	unlock(cond->__data.__lock);
+	lock(mutex);
+}
+
+pthread_cond_broadcast(cond)
+{
+	lock(cond->__data.__lock);
+	unlock(cond->__data.__lock);
+	futex_requeue(cond->data.__futex, cond->mutex);
+}
+
+Once pthread_cond_broadcast() requeues the tasks, the cond->mutex
+has waiters. Note that pthread_cond_wait() attempts to lock the
+mutex only after it has returned to user space.  This will leave the
+underlying rt_mutex with waiters, and no owner, breaking the
+previously mentioned PI-boosting algorithms.
+
+In order to support PI-aware pthread_condvar's, the kernel needs to
+be able to requeue tasks to PI futexes.  This support implies that
+upon a successful futex_wait system call, the caller would return to
+user space already holding the PI futex.  The glibc implementation
+would be modified as follows:
+
+
+/* caller must lock mutex */
+pthread_cond_wait_pi(cond, mutex)
+{
+	lock(cond->__data.__lock);
+	unlock(mutex);
+	do {
+	   unlock(cond->__data.__lock);
+	   futex_wait_requeue_pi(cond->__data.__futex);
+	   lock(cond->__data.__lock);
+	} while(...)
+	unlock(cond->__data.__lock);
+        /* the kernel acquired the the mutex for us */
+}
+
+pthread_cond_broadcast_pi(cond)
+{
+	lock(cond->__data.__lock);
+	unlock(cond->__data.__lock);
+	futex_requeue_pi(cond->data.__futex, cond->mutex);
+}
+
+The actual glibc implementation will likely test for PI and make the
+necessary changes inside the existing calls rather than creating new
+calls for the PI cases.  Similar changes are needed for
+pthread_cond_timedwait() and pthread_cond_signal().
+
+Implementation
+--------------
+
+In order to ensure the rt_mutex has an owner if it has waiters, it
+is necessary for both the requeue code, as well as the waiting code,
+to be able to acquire the rt_mutex before returning to user space.
+The requeue code cannot simply wake the waiter and leave it to
+acquire the rt_mutex as it would open a race window between the
+requeue call returning to user space and the waiter waking and
+starting to run.  This is especially true in the uncontended case.
+
+The solution involves two new rt_mutex helper routines,
+rt_mutex_start_proxy_lock() and rt_mutex_finish_proxy_lock(), which
+allow the requeue code to acquire an uncontended rt_mutex on behalf
+of the waiter and to enqueue the waiter on a contended rt_mutex.
+Two new system calls provide the kernel<->user interface to
+requeue_pi: FUTEX_WAIT_REQUEUE_PI and FUTEX_REQUEUE_CMP_PI.
+
+FUTEX_WAIT_REQUEUE_PI is called by the waiter (pthread_cond_wait()
+and pthread_cond_timedwait()) to block on the initial futex and wait
+to be requeued to a PI-aware futex.  The implementation is the
+result of a high-speed collision between futex_wait() and
+futex_lock_pi(), with some extra logic to check for the additional
+wake-up scenarios.
+
+FUTEX_REQUEUE_CMP_PI is called by the waker
+(pthread_cond_broadcast() and pthread_cond_signal()) to requeue and
+possibly wake the waiting tasks. Internally, this system call is
+still handled by futex_requeue (by passing requeue_pi=1).  Before
+requeueing, futex_requeue() attempts to acquire the requeue target
+PI futex on behalf of the top waiter.  If it can, this waiter is
+woken.  futex_requeue() then proceeds to requeue the remaining
+nr_wake+nr_requeue tasks to the PI futex, calling
+rt_mutex_start_proxy_lock() prior to each requeue to prepare the
+task as a waiter on the underlying rt_mutex.  It is possible that
+the lock can be acquired at this stage as well, if so, the next
+waiter is woken to finish the acquisition of the lock.
+
+FUTEX_REQUEUE_PI accepts nr_wake and nr_requeue as arguments, but
+their sum is all that really matters.  futex_requeue() will wake or
+requeue up to nr_wake + nr_requeue tasks.  It will wake only as many
+tasks as it can acquire the lock for, which in the majority of cases
+should be 0 as good programming practice dictates that the caller of
+either pthread_cond_broadcast() or pthread_cond_signal() acquire the
+mutex prior to making the call. FUTEX_REQUEUE_PI requires that
+nr_wake=1.  nr_requeue should be INT_MAX for broadcast and 0 for
+signal.
diff --git a/Documentation/gpio.txt b/Documentation/gpio.txt
index 145c25a170c..e4b6985044a 100644
--- a/Documentation/gpio.txt
+++ b/Documentation/gpio.txt
@@ -458,7 +458,7 @@ debugfs interface, since it provides control over GPIO direction and
 value instead of just showing a gpio state summary.  Plus, it could be
 present on production systems without debugging support.
 
-Given approprate hardware documentation for the system, userspace could
+Given appropriate hardware documentation for the system, userspace could
 know for example that GPIO #23 controls the write protect line used to
 protect boot loader segments in flash memory.  System upgrade procedures
 may need to temporarily remove that protection, first importing a GPIO,
diff --git a/Documentation/hwmon/f71882fg b/Documentation/hwmon/f71882fg
index a8321267b5b..bee4c30bc1e 100644
--- a/Documentation/hwmon/f71882fg
+++ b/Documentation/hwmon/f71882fg
@@ -2,14 +2,18 @@ Kernel driver f71882fg
 ======================
 
 Supported chips:
-  * Fintek F71882FG and F71883FG
-    Prefix: 'f71882fg'
+  * Fintek F71858FG
+    Prefix: 'f71858fg'
     Addresses scanned: none, address read from Super I/O config space
     Datasheet: Available from the Fintek website
   * Fintek F71862FG and F71863FG
     Prefix: 'f71862fg'
     Addresses scanned: none, address read from Super I/O config space
     Datasheet: Available from the Fintek website
+  * Fintek F71882FG and F71883FG
+    Prefix: 'f71882fg'
+    Addresses scanned: none, address read from Super I/O config space
+    Datasheet: Available from the Fintek website
   * Fintek F8000
     Prefix: 'f8000'
     Addresses scanned: none, address read from Super I/O config space
@@ -66,13 +70,13 @@ printed when loading the driver.
 
 Three different fan control modes are supported; the mode number is written
 to the pwm#_enable file. Note that not all modes are supported on all
-chips, and some modes may only be available in RPM / PWM mode on the F8000.
+chips, and some modes may only be available in RPM / PWM mode.
 Writing an unsupported mode will result in an invalid parameter error.
 
 * 1: Manual mode
   You ask for a specific PWM duty cycle / DC voltage or a specific % of
   fan#_full_speed by writing to the pwm# file. This mode is only
-  available on the F8000 if the fan channel is in RPM mode.
+  available on the F71858FG / F8000 if the fan channel is in RPM mode.
 
 * 2: Normal auto mode
   You can define a number of temperature/fan speed trip points, which % the
diff --git a/Documentation/hwmon/ibmaem b/Documentation/hwmon/ibmaem
index e98bdfea346..1e0d59e000b 100644
--- a/Documentation/hwmon/ibmaem
+++ b/Documentation/hwmon/ibmaem
@@ -7,7 +7,7 @@ henceforth as AEM.
 Supported systems:
   * Any recent IBM System X server with AEM support.
     This includes the x3350, x3550, x3650, x3655, x3755, x3850 M2,
-    x3950 M2, and certain HS2x/LS2x/QS2x blades.  The IPMI host interface
+    x3950 M2, and certain HC10/HS2x/LS2x/QS2x blades.  The IPMI host interface
     driver ("ipmi-si") needs to be loaded for this driver to do anything.
     Prefix: 'ibmaem'
     Datasheet: Not available
diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface
index 2f10ce6a879..dcbd502c879 100644
--- a/Documentation/hwmon/sysfs-interface
+++ b/Documentation/hwmon/sysfs-interface
@@ -70,6 +70,7 @@ are interpreted as 0! For more on how written strings are interpreted see the
 [0-*]	denotes any positive number starting from 0
 [1-*]	denotes any positive number starting from 1
 RO	read only value
+WO	write only value
 RW	read/write value
 
 Read/write values may be read-only for some chips, depending on the
@@ -150,6 +151,11 @@ fan[1-*]_min	Fan minimum value
 		Unit: revolution/min (RPM)
 		RW
 
+fan[1-*]_max	Fan maximum value
+		Unit: revolution/min (RPM)
+		Only rarely supported by the hardware.
+		RW
+
 fan[1-*]_input	Fan input value.
 		Unit: revolution/min (RPM)
 		RO
@@ -290,6 +296,24 @@ temp[1-*]_label	Suggested temperature channel label.
 		user-space.
 		RO
 
+temp[1-*]_lowest
+		Historical minimum temperature
+		Unit: millidegree Celsius
+		RO
+
+temp[1-*]_highest
+		Historical maximum temperature
+		Unit: millidegree Celsius
+		RO
+
+temp[1-*]_reset_history
+		Reset temp_lowest and temp_highest
+		WO
+
+temp_reset_history
+		Reset temp_lowest and temp_highest for all sensors
+		WO
+
 Some chips measure temperature using external thermistors and an ADC, and
 report the temperature measurement as a voltage. Converting this voltage
 back to a temperature (or the other way around for limits) requires
@@ -390,6 +414,7 @@ OR
 in[0-*]_min_alarm
 in[0-*]_max_alarm
 fan[1-*]_min_alarm
+fan[1-*]_max_alarm
 temp[1-*]_min_alarm
 temp[1-*]_max_alarm
 temp[1-*]_crit_alarm
diff --git a/Documentation/hwmon/tmp401 b/Documentation/hwmon/tmp401
new file mode 100644
index 00000000000..9fc44724921
--- /dev/null
+++ b/Documentation/hwmon/tmp401
@@ -0,0 +1,42 @@
+Kernel driver tmp401
+====================
+
+Supported chips:
+  * Texas Instruments TMP401
+    Prefix: 'tmp401'
+    Addresses scanned: I2C 0x4c
+    Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp401.html
+  * Texas Instruments TMP411
+    Prefix: 'tmp411'
+    Addresses scanned: I2C 0x4c
+    Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp411.html
+
+Authors:
+         Hans de Goede <hdegoede@redhat.com>
+	 Andre Prendel <andre.prendel@gmx.de>
+
+Description
+-----------
+
+This driver implements support for Texas Instruments TMP401 and
+TMP411 chips. These chips implements one remote and one local
+temperature sensor. Temperature is measured in degrees
+Celsius. Resolution of the remote sensor is 0.0625 degree. Local
+sensor resolution can be set to 0.5, 0.25, 0.125 or 0.0625 degree (not
+supported by the driver so far, so using the default resolution of 0.5
+degree).
+
+The driver provides the common sysfs-interface for temperatures (see
+/Documentation/hwmon/sysfs-interface under Temperatures).
+
+The TMP411 chip is compatible with TMP401. It provides some additional
+features.
+
+* Minimum and Maximum temperature measured since power-on, chip-reset
+
+  Exported via sysfs attributes tempX_lowest and tempX_highest.
+
+* Reset of historical minimum/maximum temperature measurements
+
+  Exported via sysfs attribute temp_reset_history. Writing 1 to this
+  file triggers a reset.
diff --git a/Documentation/hwmon/w83627ehf b/Documentation/hwmon/w83627ehf
index b6eb59384bb..02b74899eda 100644
--- a/Documentation/hwmon/w83627ehf
+++ b/Documentation/hwmon/w83627ehf
@@ -12,6 +12,10 @@ Supported chips:
     Addresses scanned: ISA address retrieved from Super I/O registers
     Datasheet:
         http://www.nuvoton.com.tw/NR/rdonlyres/7885623D-A487-4CF9-A47F-30C5F73D6FE6/0/W83627DHG.pdf
+  * Winbond W83627DHG-P
+    Prefix: 'w83627dhg'
+    Addresses scanned: ISA address retrieved from Super I/O registers
+    Datasheet: not available
   * Winbond W83667HG
     Prefix: 'w83667hg'
     Addresses scanned: ISA address retrieved from Super I/O registers
@@ -28,8 +32,8 @@ Description
 -----------
 
 This driver implements support for the Winbond W83627EHF, W83627EHG,
-W83627DHG and W83667HG super I/O chips. We will refer to them collectively
-as Winbond chips.
+W83627DHG, W83627DHG-P and W83667HG super I/O chips. We will refer to them
+collectively as Winbond chips.
 
 The chips implement three temperature sensors, five fan rotation
 speed sensors, ten analog voltage sensors (only nine for the 627DHG), one
@@ -135,3 +139,6 @@ done in the driver for all register addresses.
 The DHG also supports PECI, where the DHG queries Intel CPU temperatures, and
 the ICH8 southbridge gets that data via PECI from the DHG, so that the
 southbridge drives the fans. And the DHG supports SST, a one-wire serial bus.
+
+The DHG-P has an additional automatic fan speed control mode named Smart Fan
+(TM) III+. This mode is not yet supported by the driver.
diff --git a/Documentation/i2c/busses/i2c-ocores b/Documentation/i2c/busses/i2c-ocores
index cfcebb10d14..c269aaa2f26 100644
--- a/Documentation/i2c/busses/i2c-ocores
+++ b/Documentation/i2c/busses/i2c-ocores
@@ -20,6 +20,8 @@ platform_device with the base address and interrupt number. The
 dev.platform_data of the device should also point to a struct
 ocores_i2c_platform_data (see linux/i2c-ocores.h) describing the
 distance between registers and the input clock speed.
+There is also a possibility to attach a list of i2c_board_info which
+the i2c-ocores driver will add to the bus upon creation.
 
 E.G. something like:
 
@@ -36,9 +38,24 @@ static struct resource ocores_resources[] = {
 	},
 };
 
+/* optional board info */
+struct i2c_board_info ocores_i2c_board_info[] = {
+	{
+		I2C_BOARD_INFO("tsc2003", 0x48),
+		.platform_data = &tsc2003_platform_data,
+		.irq = TSC_IRQ
+	},
+	{
+		I2C_BOARD_INFO("adv7180", 0x42 >> 1),
+		.irq = ADV_IRQ
+	}
+};
+
 static struct ocores_i2c_platform_data myi2c_data = {
 	.regstep	= 2,		/* two bytes between registers */
 	.clock_khz	= 50000,	/* input clock of 50MHz */
+	.devices	= ocores_i2c_board_info, /* optional table of devices */
+	.num_devices	= ARRAY_SIZE(ocores_i2c_board_info), /* table size */
 };
 
 static struct platform_device myi2c = {
diff --git a/Documentation/i2c/busses/i2c-viapro b/Documentation/i2c/busses/i2c-viapro
index 22efedf60c8..2e758b0e945 100644
--- a/Documentation/i2c/busses/i2c-viapro
+++ b/Documentation/i2c/busses/i2c-viapro
@@ -19,6 +19,9 @@ Supported adapters:
   * VIA Technologies, Inc. VX800/VX820
     Datasheet: available on http://linux.via.com.tw
 
+  * VIA Technologies, Inc. VX855/VX875
+    Datasheet: Availability unknown
+
 Authors:
 	Kyösti Mälkki <kmalkki@cc.hut.fi>,
 	Mark D. Studebaker <mdsxyz123@yahoo.com>,
@@ -53,6 +56,7 @@ Your lspci -n listing must show one of these :
  device 1106:3287   (VT8251)
  device 1106:8324   (CX700)
  device 1106:8353   (VX800/VX820)
+ device 1106:8409   (VX855/VX875)
 
 If none of these show up, you should look in the BIOS for settings like
 enable ACPI / SMBus or even USB.
diff --git a/Documentation/ide/ide.txt b/Documentation/ide/ide.txt
index 0c78f4b1d9d..e77bebfa7b0 100644
--- a/Documentation/ide/ide.txt
+++ b/Documentation/ide/ide.txt
@@ -216,6 +216,8 @@ Other kernel parameters for ide_core are:
 
 * "noflush=[interface_number.device_number]" to disable flush requests
 
+* "nohpa=[interface_number.device_number]" to disable Host Protected Area
+
 * "noprobe=[interface_number.device_number]" to skip probing
 
 * "nowerr=[interface_number.device_number]" to ignore the WRERR_STAT bit
diff --git a/Documentation/input/multi-touch-protocol.txt b/Documentation/input/multi-touch-protocol.txt
index 9f09557aea3..a12ea3b586e 100644
--- a/Documentation/input/multi-touch-protocol.txt
+++ b/Documentation/input/multi-touch-protocol.txt
@@ -18,8 +18,12 @@ Usage
 Anonymous finger details are sent sequentially as separate packets of ABS
 events. Only the ABS_MT events are recognized as part of a finger
 packet. The end of a packet is marked by calling the input_mt_sync()
-function, which generates a SYN_MT_REPORT event. The end of multi-touch
-transfer is marked by calling the usual input_sync() function.
+function, which generates a SYN_MT_REPORT event. This instructs the
+receiver to accept the data for the current finger and prepare to receive
+another. The end of a multi-touch transfer is marked by calling the usual
+input_sync() function. This instructs the receiver to act upon events
+accumulated since last EV_SYN/SYN_REPORT and prepare to receive a new
+set of events/packets.
 
 A set of ABS_MT events with the desired properties is defined. The events
 are divided into categories, to allow for partial implementation.  The
@@ -27,11 +31,26 @@ minimum set consists of ABS_MT_TOUCH_MAJOR, ABS_MT_POSITION_X and
 ABS_MT_POSITION_Y, which allows for multiple fingers to be tracked.  If the
 device supports it, the ABS_MT_WIDTH_MAJOR may be used to provide the size
 of the approaching finger. Anisotropy and direction may be specified with
-ABS_MT_TOUCH_MINOR, ABS_MT_WIDTH_MINOR and ABS_MT_ORIENTATION. Devices with
-more granular information may specify general shapes as blobs, i.e., as a
-sequence of rectangular shapes grouped together by an
-ABS_MT_BLOB_ID. Finally, the ABS_MT_TOOL_TYPE may be used to specify
-whether the touching tool is a finger or a pen or something else.
+ABS_MT_TOUCH_MINOR, ABS_MT_WIDTH_MINOR and ABS_MT_ORIENTATION.  The
+ABS_MT_TOOL_TYPE may be used to specify whether the touching tool is a
+finger or a pen or something else.  Devices with more granular information
+may specify general shapes as blobs, i.e., as a sequence of rectangular
+shapes grouped together by an ABS_MT_BLOB_ID. Finally, for the few devices
+that currently support it, the ABS_MT_TRACKING_ID event may be used to
+report finger tracking from hardware [5].
+
+Here is what a minimal event sequence for a two-finger touch would look
+like:
+
+   ABS_MT_TOUCH_MAJOR
+   ABS_MT_POSITION_X
+   ABS_MT_POSITION_Y
+   SYN_MT_REPORT
+   ABS_MT_TOUCH_MAJOR
+   ABS_MT_POSITION_X
+   ABS_MT_POSITION_Y
+   SYN_MT_REPORT
+   SYN_REPORT
 
 
 Event Semantics
@@ -44,24 +63,24 @@ ABS_MT_TOUCH_MAJOR
 
 The length of the major axis of the contact. The length should be given in
 surface units. If the surface has an X times Y resolution, the largest
-possible value of ABS_MT_TOUCH_MAJOR is sqrt(X^2 + Y^2), the diagonal.
+possible value of ABS_MT_TOUCH_MAJOR is sqrt(X^2 + Y^2), the diagonal [4].
 
 ABS_MT_TOUCH_MINOR
 
 The length, in surface units, of the minor axis of the contact. If the
-contact is circular, this event can be omitted.
+contact is circular, this event can be omitted [4].
 
 ABS_MT_WIDTH_MAJOR
 
 The length, in surface units, of the major axis of the approaching
 tool. This should be understood as the size of the tool itself. The
 orientation of the contact and the approaching tool are assumed to be the
-same.
+same [4].
 
 ABS_MT_WIDTH_MINOR
 
 The length, in surface units, of the minor axis of the approaching
-tool. Omit if circular.
+tool. Omit if circular [4].
 
 The above four values can be used to derive additional information about
 the contact. The ratio ABS_MT_TOUCH_MAJOR / ABS_MT_WIDTH_MAJOR approximates
@@ -70,14 +89,17 @@ different characteristic widths [1].
 
 ABS_MT_ORIENTATION
 
-The orientation of the ellipse. The value should describe half a revolution
-clockwise around the touch center. The scale of the value is arbitrary, but
-zero should be returned for an ellipse aligned along the Y axis of the
-surface. As an example, an index finger placed straight onto the axis could
-return zero orientation, something negative when twisted to the left, and
-something positive when twisted to the right. This value can be omitted if
-the touching object is circular, or if the information is not available in
-the kernel driver.
+The orientation of the ellipse. The value should describe a signed quarter
+of a revolution clockwise around the touch center. The signed value range
+is arbitrary, but zero should be returned for a finger aligned along the Y
+axis of the surface, a negative value when finger is turned to the left, and
+a positive value when finger turned to the right. When completely aligned with
+the X axis, the range max should be returned.  Orientation can be omitted
+if the touching object is circular, or if the information is not available
+in the kernel driver. Partial orientation support is possible if the device
+can distinguish between the two axis, but not (uniquely) any values in
+between. In such cases, the range of ABS_MT_ORIENTATION should be [0, 1]
+[4].
 
 ABS_MT_POSITION_X
 
@@ -98,8 +120,35 @@ ABS_MT_BLOB_ID
 
 The BLOB_ID groups several packets together into one arbitrarily shaped
 contact. This is a low-level anonymous grouping, and should not be confused
-with the high-level contactID, explained below. Most kernel drivers will
-not have this capability, and can safely omit the event.
+with the high-level trackingID [5]. Most kernel drivers will not have blob
+capability, and can safely omit the event.
+
+ABS_MT_TRACKING_ID
+
+The TRACKING_ID identifies an initiated contact throughout its life cycle
+[5]. There are currently only a few devices that support it, so this event
+should normally be omitted.
+
+
+Event Computation
+-----------------
+
+The flora of different hardware unavoidably leads to some devices fitting
+better to the MT protocol than others. To simplify and unify the mapping,
+this section gives recipes for how to compute certain events.
+
+For devices reporting contacts as rectangular shapes, signed orientation
+cannot be obtained. Assuming X and Y are the lengths of the sides of the
+touching rectangle, here is a simple formula that retains the most
+information possible:
+
+   ABS_MT_TOUCH_MAJOR := max(X, Y)
+   ABS_MT_TOUCH_MINOR := min(X, Y)
+   ABS_MT_ORIENTATION := bool(X > Y)
+
+The range of ABS_MT_ORIENTATION should be set to [0, 1], to indicate that
+the device can distinguish between a finger along the Y axis (0) and a
+finger along the X axis (1).
 
 
 Finger Tracking
@@ -109,14 +158,18 @@ The kernel driver should generate an arbitrary enumeration of the set of
 anonymous contacts currently on the surface. The order in which the packets
 appear in the event stream is not important.
 
-The process of finger tracking, i.e., to assign a unique contactID to each
+The process of finger tracking, i.e., to assign a unique trackingID to each
 initiated contact on the surface, is left to user space; preferably the
-multi-touch X driver [3]. In that driver, the contactID stays the same and
+multi-touch X driver [3]. In that driver, the trackingID stays the same and
 unique until the contact vanishes (when the finger leaves the surface). The
 problem of assigning a set of anonymous fingers to a set of identified
 fingers is a euclidian bipartite matching problem at each event update, and
 relies on a sufficiently rapid update rate.
 
+There are a few devices that support trackingID in hardware. User space can
+make use of these native identifiers to reduce bandwidth and cpu usage.
+
+
 Notes
 -----
 
@@ -136,5 +189,7 @@ could be used to derive tilt.
 time of writing (April 2009), the MT protocol is not yet merged, and the
 prototype implements finger matching, basic mouse support and two-finger
 scrolling. The project aims at improving the quality of current multi-touch
-functionality available in the synaptics X driver, and in addition
+functionality available in the Synaptics X driver, and in addition
 implement more advanced gestures.
+[4] See the section on event computation.
+[5] See the section on finger tracking.
diff --git a/Documentation/isdn/00-INDEX b/Documentation/isdn/00-INDEX
index 5a2d69989a8..f6010a53659 100644
--- a/Documentation/isdn/00-INDEX
+++ b/Documentation/isdn/00-INDEX
@@ -22,16 +22,11 @@ README.gigaset
 	- info on the drivers for Siemens Gigaset ISDN adapters.
 README.icn
 	- info on the ICN-ISDN-card and its driver.
+>>>>>>> 93af7aca44f0e82e67bda10a0fb73d383edcc8bd:Documentation/isdn/00-INDEX
 README.HiSax
 	- info on the HiSax driver which replaces the old teles.
-README.hfc-pci
-	- info on hfc-pci based cards.
-README.pcbit
-	- info on the PCBIT-D ISDN adapter and driver.
-README.syncppp
-	- info on running Sync PPP over ISDN.
-syncPPP.FAQ
-	- frequently asked questions about running PPP over ISDN.
+README.audio
+	- info for running audio over ISDN.
 README.avmb1
 	- info on driver for AVM-B1 ISDN card.
 README.act2000
@@ -42,10 +37,28 @@ README.concap
 	- info on "CONCAP" encapsulation protocol interface used for X.25.
 README.diversion
 	- info on module for isdn diversion services.
+README.fax
+	- info for using Fax over ISDN.
+README.gigaset
+	- info on the drivers for Siemens Gigaset ISDN adapters
+README.hfc-pci
+	- info on hfc-pci based cards.
+README.hysdn
+        - info on driver for Hypercope active HYSDN cards
+README.icn
+	- info on the ICN-ISDN-card and its driver.
+README.mISDN
+	- info on the Modular ISDN subsystem (mISDN)
+README.pcbit
+	- info on the PCBIT-D ISDN adapter and driver.
 README.sc
 	- info on driver for Spellcaster cards.
+README.syncppp
+	- info on running Sync PPP over ISDN.
 README.x25
 	- info for running X.25 over ISDN.
+syncPPP.FAQ
+	- frequently asked questions about running PPP over ISDN.
 README.hysdn
 	- info on driver for Hypercope active HYSDN cards
 README.mISDN
diff --git a/Documentation/isdn/INTERFACE.CAPI b/Documentation/isdn/INTERFACE.CAPI
index 786d619b36e..686e107923e 100644
--- a/Documentation/isdn/INTERFACE.CAPI
+++ b/Documentation/isdn/INTERFACE.CAPI
@@ -45,7 +45,7 @@ From then on, Kernel CAPI may call the registered callback functions for the
 device.
 
 If the device becomes unusable for any reason (shutdown, disconnect ...), the
-driver has to call capi_ctr_reseted(). This will prevent further calls to the
+driver has to call capi_ctr_down(). This will prevent further calls to the
 callback functions by Kernel CAPI.
 
 
@@ -114,20 +114,36 @@ char *driver_name
 int (*load_firmware)(struct capi_ctr *ctrlr, capiloaddata *ldata)
 	(optional) pointer to a callback function for sending firmware and
 	configuration data to the device
+	Return value: 0 on success, error code on error
+	Called in process context.
 
 void (*reset_ctr)(struct capi_ctr *ctrlr)
-	pointer to a callback function for performing a reset on the device,
-	releasing all registered applications
+	(optional) pointer to a callback function for performing a reset on
+	the device, releasing all registered applications
+	Called in process context.
 
 void (*register_appl)(struct capi_ctr *ctrlr, u16 applid,
 			capi_register_params *rparam)
 void (*release_appl)(struct capi_ctr *ctrlr, u16 applid)
 	pointers to callback functions for registration and deregistration of
 	applications with the device
+	Calls to these functions are serialized by Kernel CAPI so that only
+	one call to any of them is active at any time.
 
 u16  (*send_message)(struct capi_ctr *ctrlr, struct sk_buff *skb)
 	pointer to a callback function for sending a CAPI message to the
 	device
+	Return value: CAPI error code
+	If the method returns 0 (CAPI_NOERROR) the driver has taken ownership
+	of the skb and the caller may no longer access it. If it returns a
+	non-zero (error) value then ownership of the skb returns to the caller
+	who may reuse or free it.
+	The return value should only be used to signal problems with respect
+	to accepting or queueing the message. Errors occurring during the
+	actual processing of the message should be signaled with an
+	appropriate reply message.
+	Calls to this function are not serialized by Kernel CAPI, ie. it must
+	be prepared to be re-entered.
 
 char *(*procinfo)(struct capi_ctr *ctrlr)
 	pointer to a callback function returning the entry for the device in
@@ -138,6 +154,8 @@ read_proc_t *ctr_read_proc
 	system entry, /proc/capi/controllers/<n>; will be called with a
 	pointer to the device's capi_ctr structure as the last (data) argument
 
+Note: Callback functions are never called in interrupt context.
+
 - to be filled in before calling capi_ctr_ready():
 
 u8 manu[CAPI_MANUFACTURER_LEN]
@@ -153,6 +171,45 @@ u8 serial[CAPI_SERIAL_LEN]
 	value to return for CAPI_GET_SERIAL
 
 
+4.3 The _cmsg Structure
+
+(declared in <linux/isdn/capiutil.h>)
+
+The _cmsg structure stores the contents of a CAPI 2.0 message in an easily
+accessible form. It contains members for all possible CAPI 2.0 parameters, of
+which only those appearing in the message type currently being processed are
+actually used. Unused members should be set to zero.
+
+Members are named after the CAPI 2.0 standard names of the parameters they
+represent. See <linux/isdn/capiutil.h> for the exact spelling. Member data
+types are:
+
+u8          for CAPI parameters of type 'byte'
+
+u16         for CAPI parameters of type 'word'
+
+u32         for CAPI parameters of type 'dword'
+
+_cstruct    for CAPI parameters of type 'struct' not containing any
+	    variably-sized (struct) subparameters (eg. 'Called Party Number')
+	    The member is a pointer to a buffer containing the parameter in
+	    CAPI encoding (length + content). It may also be NULL, which will
+	    be taken to represent an empty (zero length) parameter.
+
+_cmstruct   for CAPI parameters of type 'struct' containing 'struct'
+	    subparameters ('Additional Info' and 'B Protocol')
+	    The representation is a single byte containing one of the values:
+	    CAPI_DEFAULT: the parameter is empty
+	    CAPI_COMPOSE: the values of the subparameters are stored
+	    individually in the corresponding _cmsg structure members
+
+Functions capi_cmsg2message() and capi_message2cmsg() are provided to convert
+messages between their transport encoding described in the CAPI 2.0 standard
+and their _cmsg structure representation. Note that capi_cmsg2message() does
+not know or check the size of its destination buffer. The caller must make
+sure it is big enough to accomodate the resulting CAPI message.
+
+
 5. Lower Layer Interface Functions
 
 (declared in <linux/isdn/capilli.h>)
@@ -166,7 +223,7 @@ int detach_capi_ctr(struct capi_ctr *ctrlr)
 	register/unregister a device (controller) with Kernel CAPI
 
 void capi_ctr_ready(struct capi_ctr *ctrlr)
-void capi_ctr_reseted(struct capi_ctr *ctrlr)
+void capi_ctr_down(struct capi_ctr *ctrlr)
 	signal controller ready/not ready
 
 void capi_ctr_suspend_output(struct capi_ctr *ctrlr)
@@ -211,3 +268,32 @@ CAPIMSG_CONTROL(m)	CAPIMSG_SETCONTROL(m, contr)	Controller/PLCI/NCCI
 							(u32)
 CAPIMSG_DATALEN(m)	CAPIMSG_SETDATALEN(m, len)	Data Length (u16)
 
+
+Library functions for working with _cmsg structures
+(from <linux/isdn/capiutil.h>):
+
+unsigned capi_cmsg2message(_cmsg *cmsg, u8 *msg)
+	Assembles a CAPI 2.0 message from the parameters in *cmsg, storing the
+	result in *msg.
+
+unsigned capi_message2cmsg(_cmsg *cmsg, u8 *msg)
+	Disassembles the CAPI 2.0 message in *msg, storing the parameters in
+	*cmsg.
+
+unsigned capi_cmsg_header(_cmsg *cmsg, u16 ApplId, u8 Command, u8 Subcommand,
+			  u16 Messagenumber, u32 Controller)
+	Fills the header part and address field of the _cmsg structure *cmsg
+	with the given values, zeroing the remainder of the structure so only
+	parameters with non-default values need to be changed before sending
+	the message.
+
+void capi_cmsg_answer(_cmsg *cmsg)
+	Sets the low bit of the Subcommand field in *cmsg, thereby converting
+	_REQ to _CONF and _IND to _RESP.
+
+char *capi_cmd2str(u8 Command, u8 Subcommand)
+	Returns the CAPI 2.0 message name corresponding to the given command
+	and subcommand values, as a static ASCII string. The return value may
+	be NULL if the command/subcommand is not one of those defined in the
+	CAPI 2.0 standard.
+
diff --git a/Documentation/isdn/README.gigaset b/Documentation/isdn/README.gigaset
index 02c0e9341dd..f9963103ae3 100644
--- a/Documentation/isdn/README.gigaset
+++ b/Documentation/isdn/README.gigaset
@@ -149,10 +149,8 @@ GigaSet 307x Device Driver
      configuration files and chat scripts in the gigaset-VERSION/ppp directory
      in the driver packages from http://sourceforge.net/projects/gigaset307x/.
      Please note that the USB drivers are not able to change the state of the
-     control lines (the M105 driver can be configured to use some undocumented
-     control requests, if you really need the control lines, though). This means
-     you must use "Stupid Mode" if you are using wvdial or you should use the
-     nocrtscts option of pppd.
+     control lines. This means you must use "Stupid Mode" if you are using
+     wvdial or you should use the nocrtscts option of pppd.
      You must also assure that the ppp_async module is loaded with the parameter
      flag_time=0. You can do this e.g. by adding a line like
 
@@ -190,20 +188,19 @@ GigaSet 307x Device Driver
      You can also use /sys/class/tty/ttyGxy/cidmode for changing the CID mode
      setting (ttyGxy is ttyGU0 or ttyGB0).
 
-2.6. M105 Undocumented USB Requests
-     ------------------------------
-
-     The Gigaset M105 USB data box understands a couple of useful, but
-     undocumented USB commands. These requests are not used in normal
-     operation (for wireless access to the base), but are needed for access
-     to the M105's own configuration mode (registration to the base, baudrate
-     and line format settings, device status queries) via the gigacontr
-     utility. Their use is controlled by the kernel configuration option
-     "Support for undocumented USB requests" (CONFIG_GIGASET_UNDOCREQ). If you
-     encounter error code -ENOTTY when trying to use some features of the
-     M105, try setting that option to "y" via 'make {x,menu}config' and
-     recompiling the driver.
-
+2.6. Unregistered Wireless Devices (M101/M105)
+     -----------------------------------------
+     The main purpose of the ser_gigaset and usb_gigaset drivers is to allow
+     the M101 and M105 wireless devices to be used as ISDN devices for ISDN
+     connections through a Gigaset base. Therefore they assume that the device
+     is registered to a DECT base.
+
+     If the M101/M105 device is not registered to a base, initialization of
+     the device fails, and a corresponding error message is logged by the
+     driver. In that situation, a restricted set of functions is available
+     which includes, in particular, those necessary for registering the device
+     to a base or for switching it between Fixed Part and Portable Part
+     modes.
 
 3.   Troubleshooting
      ---------------
@@ -234,11 +231,12 @@ GigaSet 307x Device Driver
         Select Unimodem mode for all DECT data adapters. (see section 2.4.)
 
      Problem:
-        You want to configure your USB DECT data adapter (M105) but gigacontr
-        reports an error: "/dev/ttyGU0: Inappropriate ioctl for device".
+	Messages like this:
+	    usb_gigaset 3-2:1.0: Could not initialize the device.
+	appear in your syslog.
      Solution:
-        Recompile the usb_gigaset driver with the kernel configuration option
-        CONFIG_GIGASET_UNDOCREQ set to 'y'. (see section 2.6.)
+	Check whether your M10x wireless device is correctly registered to the
+	Gigaset base. (see section 2.6.)
 
 3.2. Telling the driver to provide more information
      ----------------------------------------------
diff --git a/Documentation/kbuild/kconfig.txt b/Documentation/kbuild/kconfig.txt
index 26a7c0a9319..849b5e56d06 100644
--- a/Documentation/kbuild/kconfig.txt
+++ b/Documentation/kbuild/kconfig.txt
@@ -35,48 +35,26 @@ new .config files to see the differences:
 
 (Yes, we need something better here.)
 
-
-======================================================================
-menuconfig
---------------------------------------------------
-
-SEARCHING for CONFIG symbols
-
-Searching in menuconfig:
-
-	The Search function searches for kernel configuration symbol
-	names, so you have to know something close to what you are
-	looking for.
-
-	Example:
-		/hotplug
-		This lists all config symbols that contain "hotplug",
-		e.g., HOTPLUG, HOTPLUG_CPU, MEMORY_HOTPLUG.
-
-	For search help, enter / followed TAB-TAB-TAB (to highlight
-	<Help>) and Enter.  This will tell you that you can also use
-	regular expressions (regexes) in the search string, so if you
-	are not interested in MEMORY_HOTPLUG, you could try
-
-		/^hotplug
-
-
 ______________________________________________________________________
-Color Themes for 'menuconfig'
+Environment variables for '*config'
 
-It is possible to select different color themes using the variable
-MENUCONFIG_COLOR.  To select a theme use:
+KCONFIG_CONFIG
+--------------------------------------------------
+This environment variable can be used to specify a default kernel config
+file name to override the default name of ".config".
 
-	make MENUCONFIG_COLOR=<theme> menuconfig
+KCONFIG_OVERWRITECONFIG
+--------------------------------------------------
+If you set KCONFIG_OVERWRITECONFIG in the environment, Kconfig will not
+break symlinks when .config is a symlink to somewhere else.
 
-Available themes are:
-  mono       => selects colors suitable for monochrome displays
-  blackbg    => selects a color scheme with black background
-  classic    => theme with blue background. The classic look
-  bluetitle  => a LCD friendly version of classic. (default)
+KCONFIG_NOTIMESTAMP
+--------------------------------------------------
+If this environment variable exists and is non-null, the timestamp line
+in generated .config files is omitted.
 
 ______________________________________________________________________
-Environment variables in 'menuconfig'
+Environment variables for '{allyes/allmod/allno/rand}config'
 
 KCONFIG_ALLCONFIG
 --------------------------------------------------
@@ -95,8 +73,7 @@ values.
 This enables you to create "miniature" config (miniconfig) or custom
 config files containing just the config symbols that you are interested
 in.  Then the kernel config system generates the full .config file,
-including dependencies of your miniconfig file, based on the miniconfig
-file.
+including symbols of your miniconfig file.
 
 This 'KCONFIG_ALLCONFIG' file is a config file which contains
 (usually a subset of all) preset config symbols.  These variable
@@ -113,26 +90,14 @@ These examples will disable most options (allnoconfig) but enable or
 disable the options that are explicitly listed in the specified
 mini-config files.
 
+______________________________________________________________________
+Environment variables for 'silentoldconfig'
+
 KCONFIG_NOSILENTUPDATE
 --------------------------------------------------
 If this variable has a non-blank value, it prevents silent kernel
 config udpates (requires explicit updates).
 
-KCONFIG_CONFIG
---------------------------------------------------
-This environment variable can be used to specify a default kernel config
-file name to override the default name of ".config".
-
-KCONFIG_OVERWRITECONFIG
---------------------------------------------------
-If you set KCONFIG_OVERWRITECONFIG in the environment, Kconfig will not
-break symlinks when .config is a symlink to somewhere else.
-
-KCONFIG_NOTIMESTAMP
---------------------------------------------------
-If this environment variable exists and is non-null, the timestamp line
-in generated .config files is omitted.
-
 KCONFIG_AUTOCONFIG
 --------------------------------------------------
 This environment variable can be set to specify the path & name of the
@@ -143,15 +108,54 @@ KCONFIG_AUTOHEADER
 This environment variable can be set to specify the path & name of the
 "autoconf.h" (header) file.  Its default value is "include/linux/autoconf.h".
 
+
+======================================================================
+menuconfig
+--------------------------------------------------
+
+SEARCHING for CONFIG symbols
+
+Searching in menuconfig:
+
+	The Search function searches for kernel configuration symbol
+	names, so you have to know something close to what you are
+	looking for.
+
+	Example:
+		/hotplug
+		This lists all config symbols that contain "hotplug",
+		e.g., HOTPLUG, HOTPLUG_CPU, MEMORY_HOTPLUG.
+
+	For search help, enter / followed TAB-TAB-TAB (to highlight
+	<Help>) and Enter.  This will tell you that you can also use
+	regular expressions (regexes) in the search string, so if you
+	are not interested in MEMORY_HOTPLUG, you could try
+
+		/^hotplug
+
 ______________________________________________________________________
-menuconfig User Interface Options
-----------------------------------------------------------------------
+User interface options for 'menuconfig'
+
+MENUCONFIG_COLOR
+--------------------------------------------------
+It is possible to select different color themes using the variable
+MENUCONFIG_COLOR.  To select a theme use:
+
+	make MENUCONFIG_COLOR=<theme> menuconfig
+
+Available themes are:
+  mono       => selects colors suitable for monochrome displays
+  blackbg    => selects a color scheme with black background
+  classic    => theme with blue background. The classic look
+  bluetitle  => a LCD friendly version of classic. (default)
+
 MENUCONFIG_MODE
 --------------------------------------------------
 This mode shows all sub-menus in one large tree.
 
 Example:
-	MENUCONFIG_MODE=single_menu make menuconfig
+	make MENUCONFIG_MODE=single_menu menuconfig
+
 
 ======================================================================
 xconfig
diff --git a/Documentation/kbuild/modules.txt b/Documentation/kbuild/modules.txt
index b1096da953c..0767cf69c69 100644
--- a/Documentation/kbuild/modules.txt
+++ b/Documentation/kbuild/modules.txt
@@ -275,7 +275,7 @@ following files:
 
 		KERNELDIR := /lib/modules/`uname -r`/build
 		all::
-			$(MAKE) -C $KERNELDIR M=`pwd` $@
+			$(MAKE) -C $(KERNELDIR) M=`pwd` $@
 
 		# Module specific targets
 		genbin:
diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt
index 3f4bc840da8..cab61d84225 100644
--- a/Documentation/kdump/kdump.txt
+++ b/Documentation/kdump/kdump.txt
@@ -108,7 +108,7 @@ There are two possible methods of using Kdump.
 
 2) Or use the system kernel binary itself as dump-capture kernel and there is
    no need to build a separate dump-capture kernel. This is possible
-   only with the architecutres which support a relocatable kernel. As
+   only with the architectures which support a relocatable kernel. As
    of today, i386, x86_64, ppc64 and ia64 architectures support relocatable
    kernel.
 
@@ -222,7 +222,7 @@ Dump-capture kernel config options (Arch Dependent, ia64)
 ----------------------------------------------------------
 
 - No specific options are required to create a dump-capture kernel
-  for ia64, other than those specified in the arch idependent section
+  for ia64, other than those specified in the arch independent section
   above. This means that it is possible to use the system kernel
   as a dump-capture kernel if desired.
 
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 9243dd84f4d..5578248c18a 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -328,11 +328,6 @@ and is between 256 and 4096 characters. It is defined in the file
 				    flushed before they will be reused, which
 				    is a lot of faster
 
-	amd_iommu_size= [HW,X86-64]
-			Define the size of the aperture for the AMD IOMMU
-			driver. Possible values are:
-			'32M', '64M' (default), '128M', '256M', '512M', '1G'
-
 	amijoy.map=	[HW,JOY] Amiga joystick support
 			Map of devices attached to JOY0DAT and JOY1DAT
 			Format: <a>,<b>
@@ -496,6 +491,13 @@ and is between 256 and 4096 characters. It is defined in the file
 			Also note the kernel might malfunction if you disable
 			some critical bits.
 
+	cmo_free_hint=	[PPC] Format: { yes | no }
+			Specify whether pages are marked as being inactive
+			when they are freed.  This is used in CMO environments
+			to determine OS memory pressure for page stealing by
+			a hypervisor.
+			Default: yes
+
 	code_bytes	[X86] How many bytes of object code to print
 			in an oops report.
 			Range: 0 - 8192
@@ -544,6 +546,10 @@ and is between 256 and 4096 characters. It is defined in the file
 			console=brl,ttyS0
 		For now, only VisioBraille is supported.
 
+	consoleblank=	[KNL] The console blank (screen saver) timeout in
+			seconds. Defaults to 10*60 = 10mins. A value of 0
+			disables the blank timer.
+
 	coredump_filter=
 			[KNL] Change the default value for
 			/proc/<pid>/coredump_filter.
@@ -645,6 +651,13 @@ and is between 256 and 4096 characters. It is defined in the file
 			DMA-API debugging code disables itself because the
 			architectural default is too low.
 
+	dma_debug_driver=<driver_name>
+			With this option the DMA-API debugging driver
+			filter feature can be enabled at boot time. Just
+			pass the driver to filter for as the parameter.
+			The filter can be disabled or changed to another
+			driver later using sysfs.
+
 	dscc4.setup=	[NET]
 
 	dtc3181e=	[HW,SCSI]
@@ -751,12 +764,25 @@ and is between 256 and 4096 characters. It is defined in the file
 			ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
 
 	ftrace=[tracer]
-			[ftrace] will set and start the specified tracer
+			[FTRACE] will set and start the specified tracer
 			as early as possible in order to facilitate early
 			boot debugging.
 
 	ftrace_dump_on_oops
-			[ftrace] will dump the trace buffers on oops.
+			[FTRACE] will dump the trace buffers on oops.
+
+	ftrace_filter=[function-list]
+			[FTRACE] Limit the functions traced by the function
+			tracer at boot up. function-list is a comma separated
+			list of functions. This list can be changed at run
+			time by the set_ftrace_filter file in the debugfs
+			tracing directory. 
+
+	ftrace_notrace=[function-list]
+			[FTRACE] Do not trace the functions specified in
+			function-list. This list can be changed at run time
+			by the set_ftrace_notrace file in the debugfs
+			tracing directory.
 
 	gamecon.map[2|3]=
 			[HW,JOY] Multisystem joystick and NES/SNES/PSX pad
@@ -872,11 +898,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	ide-core.nodma=	[HW] (E)IDE subsystem
 			Format: =0.0 to prevent dma on hda, =0.1 hdb =1.0 hdc
-			.vlb_clock .pci_clock .noflush .noprobe .nowerr .cdrom
-			.chs .ignore_cable are additional options
-			See Documentation/ide/ide.txt.
-
-	idebus=		[HW] (E)IDE subsystem - VLB/PCI bus speed
+			.vlb_clock .pci_clock .noflush .nohpa .noprobe .nowerr
+			.cdrom .chs .ignore_cable are additional options
 			See Documentation/ide/ide.txt.
 
 	ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem
@@ -913,6 +936,12 @@ and is between 256 and 4096 characters. It is defined in the file
 			Formt: { "sha1" | "md5" }
 			default: "sha1"
 
+	ima_tcb		[IMA]
+			Load a policy which meets the needs of the Trusted
+			Computing Base.  This means IMA will measure all
+			programs exec'd, files mmap'd for exec, and all files
+			opened for read by uid=0.
+
 	in2000=		[HW,SCSI]
 			See header of drivers/scsi/in2000.c.
 
@@ -1055,13 +1084,17 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	kgdboc=		[HW] kgdb over consoles.
 			Requires a tty driver that supports console polling.
-			(only serial suported for now)
+			(only serial supported for now)
 			Format: <serial_device>[,baud]
 
 	kmac=		[MIPS] korina ethernet MAC address.
 			Configure the RouterBoard 532 series on-chip
 			Ethernet adapter MAC address.
 
+	kmemleak=	[KNL] Boot-time kmemleak enable/disable
+			Valid arguments: on, off
+			Default: on
+
 	kstack=N	[X86] Print N words from the kernel stack
 			in oops dumps.
 
@@ -1380,7 +1413,7 @@ and is between 256 and 4096 characters. It is defined in the file
 			('y', default) or cooked coordinates ('n')
 
 	mtrr_chunk_size=nn[KMG] [X86]
-			used for mtrr cleanup. It is largest continous chunk
+			used for mtrr cleanup. It is largest continuous chunk
 			that could hold holes aka. UC entries.
 
 	mtrr_gran_size=nn[KMG] [X86]
@@ -1525,6 +1558,10 @@ and is between 256 and 4096 characters. It is defined in the file
 			register save and restore. The kernel will only save
 			legacy floating-point registers on task switch.
 
+	noxsave		[BUGS=X86] Disables x86 extended register state save
+			and restore using xsave. The kernel will fallback to
+			enabling legacy floating-point and sse state.
+
 	nohlt		[BUGS=ARM,SH] Tells the kernel that the sleep(SH) or
 			wfi(ARM) instruction doesn't work correctly and not to
 			use it. This is also useful when using JTAG debugger.
@@ -1561,6 +1598,9 @@ and is between 256 and 4096 characters. It is defined in the file
 	noinitrd	[RAM] Tells the kernel not to load any configured
 			initial RAM disk.
 
+	nointremap	[X86-64, Intel-IOMMU] Do not enable interrupt
+			remapping.
+
 	nointroute	[IA-64]
 
 	nojitter	[IA64] Disables jitter checking for ITC timers.
@@ -1646,6 +1686,14 @@ and is between 256 and 4096 characters. It is defined in the file
 	oprofile.timer=	[HW]
 			Use timer interrupt instead of performance counters
 
+	oprofile.cpu_type=	Force an oprofile cpu type
+			This might be useful if you have an older oprofile
+			userland or if you want common events.
+			Format: { archperfmon }
+			archperfmon: [X86] Force use of architectural
+				perfmon on Intel CPUs instead of the
+				CPU specific event set.
+
 	osst=		[HW,SCSI] SCSI Tape Driver
 			Format: <buffer_size>,<write_threshold>
 			See also Documentation/scsi/st.txt.
diff --git a/Documentation/kmemcheck.txt b/Documentation/kmemcheck.txt
new file mode 100644
index 00000000000..363044609da
--- /dev/null
+++ b/Documentation/kmemcheck.txt
@@ -0,0 +1,773 @@
+GETTING STARTED WITH KMEMCHECK
+==============================
+
+Vegard Nossum <vegardno@ifi.uio.no>
+
+
+Contents
+========
+0. Introduction
+1. Downloading
+2. Configuring and compiling
+3. How to use
+3.1. Booting
+3.2. Run-time enable/disable
+3.3. Debugging
+3.4. Annotating false positives
+4. Reporting errors
+5. Technical description
+
+
+0. Introduction
+===============
+
+kmemcheck is a debugging feature for the Linux Kernel. More specifically, it
+is a dynamic checker that detects and warns about some uses of uninitialized
+memory.
+
+Userspace programmers might be familiar with Valgrind's memcheck. The main
+difference between memcheck and kmemcheck is that memcheck works for userspace
+programs only, and kmemcheck works for the kernel only. The implementations
+are of course vastly different. Because of this, kmemcheck is not as accurate
+as memcheck, but it turns out to be good enough in practice to discover real
+programmer errors that the compiler is not able to find through static
+analysis.
+
+Enabling kmemcheck on a kernel will probably slow it down to the extent that
+the machine will not be usable for normal workloads such as e.g. an
+interactive desktop. kmemcheck will also cause the kernel to use about twice
+as much memory as normal. For this reason, kmemcheck is strictly a debugging
+feature.
+
+
+1. Downloading
+==============
+
+kmemcheck can only be downloaded using git. If you want to write patches
+against the current code, you should use the kmemcheck development branch of
+the tip tree. It is also possible to use the linux-next tree, which also
+includes the latest version of kmemcheck.
+
+Assuming that you've already cloned the linux-2.6.git repository, all you
+have to do is add the -tip tree as a remote, like this:
+
+	$ git remote add tip git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git
+
+To actually download the tree, fetch the remote:
+
+	$ git fetch tip
+
+And to check out a new local branch with the kmemcheck code:
+
+	$ git checkout -b kmemcheck tip/kmemcheck
+
+General instructions for the -tip tree can be found here:
+http://people.redhat.com/mingo/tip.git/readme.txt
+
+
+2. Configuring and compiling
+============================
+
+kmemcheck only works for the x86 (both 32- and 64-bit) platform. A number of
+configuration variables must have specific settings in order for the kmemcheck
+menu to even appear in "menuconfig". These are:
+
+  o CONFIG_CC_OPTIMIZE_FOR_SIZE=n
+
+	This option is located under "General setup" / "Optimize for size".
+
+	Without this, gcc will use certain optimizations that usually lead to
+	false positive warnings from kmemcheck. An example of this is a 16-bit
+	field in a struct, where gcc may load 32 bits, then discard the upper
+	16 bits. kmemcheck sees only the 32-bit load, and may trigger a
+	warning for the upper 16 bits (if they're uninitialized).
+
+  o CONFIG_SLAB=y or CONFIG_SLUB=y
+
+	This option is located under "General setup" / "Choose SLAB
+	allocator".
+
+  o CONFIG_FUNCTION_TRACER=n
+
+	This option is located under "Kernel hacking" / "Tracers" / "Kernel
+	Function Tracer"
+
+	When function tracing is compiled in, gcc emits a call to another
+	function at the beginning of every function. This means that when the
+	page fault handler is called, the ftrace framework will be called
+	before kmemcheck has had a chance to handle the fault. If ftrace then
+	modifies memory that was tracked by kmemcheck, the result is an
+	endless recursive page fault.
+
+  o CONFIG_DEBUG_PAGEALLOC=n
+
+	This option is located under "Kernel hacking" / "Debug page memory
+	allocations".
+
+In addition, I highly recommend turning on CONFIG_DEBUG_INFO=y. This is also
+located under "Kernel hacking". With this, you will be able to get line number
+information from the kmemcheck warnings, which is extremely valuable in
+debugging a problem. This option is not mandatory, however, because it slows
+down the compilation process and produces a much bigger kernel image.
+
+Now the kmemcheck menu should be visible (under "Kernel hacking" / "kmemcheck:
+trap use of uninitialized memory"). Here follows a description of the
+kmemcheck configuration variables:
+
+  o CONFIG_KMEMCHECK
+
+	This must be enabled in order to use kmemcheck at all...
+
+  o CONFIG_KMEMCHECK_[DISABLED | ENABLED | ONESHOT]_BY_DEFAULT
+
+	This option controls the status of kmemcheck at boot-time. "Enabled"
+	will enable kmemcheck right from the start, "disabled" will boot the
+	kernel as normal (but with the kmemcheck code compiled in, so it can
+	be enabled at run-time after the kernel has booted), and "one-shot" is
+	a special mode which will turn kmemcheck off automatically after
+	detecting the first use of uninitialized memory.
+
+	If you are using kmemcheck to actively debug a problem, then you
+	probably want to choose "enabled" here.
+
+	The one-shot mode is mostly useful in automated test setups because it
+	can prevent floods of warnings and increase the chances of the machine
+	surviving in case something is really wrong. In other cases, the one-
+	shot mode could actually be counter-productive because it would turn
+	itself off at the very first error -- in the case of a false positive
+	too -- and this would come in the way of debugging the specific
+	problem you were interested in.
+
+	If you would like to use your kernel as normal, but with a chance to
+	enable kmemcheck in case of some problem, it might be a good idea to
+	choose "disabled" here. When kmemcheck is disabled, most of the run-
+	time overhead is not incurred, and the kernel will be almost as fast
+	as normal.
+
+  o CONFIG_KMEMCHECK_QUEUE_SIZE
+
+	Select the maximum number of error reports to store in an internal
+	(fixed-size) buffer. Since errors can occur virtually anywhere and in
+	any context, we need a temporary storage area which is guaranteed not
+	to generate any other page faults when accessed. The queue will be
+	emptied as soon as a tasklet may be scheduled. If the queue is full,
+	new error reports will be lost.
+
+	The default value of 64 is probably fine. If some code produces more
+	than 64 errors within an irqs-off section, then the code is likely to
+	produce many, many more, too, and these additional reports seldom give
+	any more information (the first report is usually the most valuable
+	anyway).
+
+	This number might have to be adjusted if you are not using serial
+	console or similar to capture the kernel log. If you are using the
+	"dmesg" command to save the log, then getting a lot of kmemcheck
+	warnings might overflow the kernel log itself, and the earlier reports
+	will get lost in that way instead. Try setting this to 10 or so on
+	such a setup.
+
+  o CONFIG_KMEMCHECK_SHADOW_COPY_SHIFT
+
+	Select the number of shadow bytes to save along with each entry of the
+	error-report queue. These bytes indicate what parts of an allocation
+	are initialized, uninitialized, etc. and will be displayed when an
+	error is detected to help the debugging of a particular problem.
+
+	The number entered here is actually the logarithm of the number of
+	bytes that will be saved. So if you pick for example 5 here, kmemcheck
+	will save 2^5 = 32 bytes.
+
+	The default value should be fine for debugging most problems. It also
+	fits nicely within 80 columns.
+
+  o CONFIG_KMEMCHECK_PARTIAL_OK
+
+	This option (when enabled) works around certain GCC optimizations that
+	produce 32-bit reads from 16-bit variables where the upper 16 bits are
+	thrown away afterwards.
+
+	The default value (enabled) is recommended. This may of course hide
+	some real errors, but disabling it would probably produce a lot of
+	false positives.
+
+  o CONFIG_KMEMCHECK_BITOPS_OK
+
+	This option silences warnings that would be generated for bit-field
+	accesses where not all the bits are initialized at the same time. This
+	may also hide some real bugs.
+
+	This option is probably obsolete, or it should be replaced with
+	the kmemcheck-/bitfield-annotations for the code in question. The
+	default value is therefore fine.
+
+Now compile the kernel as usual.
+
+
+3. How to use
+=============
+
+3.1. Booting
+============
+
+First some information about the command-line options. There is only one
+option specific to kmemcheck, and this is called "kmemcheck". It can be used
+to override the default mode as chosen by the CONFIG_KMEMCHECK_*_BY_DEFAULT
+option. Its possible settings are:
+
+  o kmemcheck=0 (disabled)
+  o kmemcheck=1 (enabled)
+  o kmemcheck=2 (one-shot mode)
+
+If SLUB debugging has been enabled in the kernel, it may take precedence over
+kmemcheck in such a way that the slab caches which are under SLUB debugging
+will not be tracked by kmemcheck. In order to ensure that this doesn't happen
+(even though it shouldn't by default), use SLUB's boot option "slub_debug",
+like this: slub_debug=-
+
+In fact, this option may also be used for fine-grained control over SLUB vs.
+kmemcheck. For example, if the command line includes "kmemcheck=1
+slub_debug=,dentry", then SLUB debugging will be used only for the "dentry"
+slab cache, and with kmemcheck tracking all the other caches. This is advanced
+usage, however, and is not generally recommended.
+
+
+3.2. Run-time enable/disable
+============================
+
+When the kernel has booted, it is possible to enable or disable kmemcheck at
+run-time. WARNING: This feature is still experimental and may cause false
+positive warnings to appear. Therefore, try not to use this. If you find that
+it doesn't work properly (e.g. you see an unreasonable amount of warnings), I
+will be happy to take bug reports.
+
+Use the file /proc/sys/kernel/kmemcheck for this purpose, e.g.:
+
+	$ echo 0 > /proc/sys/kernel/kmemcheck # disables kmemcheck
+
+The numbers are the same as for the kmemcheck= command-line option.
+
+
+3.3. Debugging
+==============
+
+A typical report will look something like this:
+
+WARNING: kmemcheck: Caught 32-bit read from uninitialized memory (ffff88003e4a2024)
+80000000000000000000000000000000000000000088ffff0000000000000000
+ i i i i u u u u i i i i i i i i u u u u u u u u u u u u u u u u
+         ^
+
+Pid: 1856, comm: ntpdate Not tainted 2.6.29-rc5 #264 945P-A
+RIP: 0010:[<ffffffff8104ede8>]  [<ffffffff8104ede8>] __dequeue_signal+0xc8/0x190
+RSP: 0018:ffff88003cdf7d98  EFLAGS: 00210002
+RAX: 0000000000000030 RBX: ffff88003d4ea968 RCX: 0000000000000009
+RDX: ffff88003e5d6018 RSI: ffff88003e5d6024 RDI: ffff88003cdf7e84
+RBP: ffff88003cdf7db8 R08: ffff88003e5d6000 R09: 0000000000000000
+R10: 0000000000000080 R11: 0000000000000000 R12: 000000000000000e
+R13: ffff88003cdf7e78 R14: ffff88003d530710 R15: ffff88003d5a98c8
+FS:  0000000000000000(0000) GS:ffff880001982000(0063) knlGS:00000
+CS:  0010 DS: 002b ES: 002b CR0: 0000000080050033
+CR2: ffff88003f806ea0 CR3: 000000003c036000 CR4: 00000000000006a0
+DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
+DR3: 0000000000000000 DR6: 00000000ffff4ff0 DR7: 0000000000000400
+ [<ffffffff8104f04e>] dequeue_signal+0x8e/0x170
+ [<ffffffff81050bd8>] get_signal_to_deliver+0x98/0x390
+ [<ffffffff8100b87d>] do_notify_resume+0xad/0x7d0
+ [<ffffffff8100c7b5>] int_signal+0x12/0x17
+ [<ffffffffffffffff>] 0xffffffffffffffff
+
+The single most valuable information in this report is the RIP (or EIP on 32-
+bit) value. This will help us pinpoint exactly which instruction that caused
+the warning.
+
+If your kernel was compiled with CONFIG_DEBUG_INFO=y, then all we have to do
+is give this address to the addr2line program, like this:
+
+	$ addr2line -e vmlinux -i ffffffff8104ede8
+	arch/x86/include/asm/string_64.h:12
+	include/asm-generic/siginfo.h:287
+	kernel/signal.c:380
+	kernel/signal.c:410
+
+The "-e vmlinux" tells addr2line which file to look in. IMPORTANT: This must
+be the vmlinux of the kernel that produced the warning in the first place! If
+not, the line number information will almost certainly be wrong.
+
+The "-i" tells addr2line to also print the line numbers of inlined functions.
+In this case, the flag was very important, because otherwise, it would only
+have printed the first line, which is just a call to memcpy(), which could be
+called from a thousand places in the kernel, and is therefore not very useful.
+These inlined functions would not show up in the stack trace above, simply
+because the kernel doesn't load the extra debugging information. This
+technique can of course be used with ordinary kernel oopses as well.
+
+In this case, it's the caller of memcpy() that is interesting, and it can be
+found in include/asm-generic/siginfo.h, line 287:
+
+281 static inline void copy_siginfo(struct siginfo *to, struct siginfo *from)
+282 {
+283         if (from->si_code < 0)
+284                 memcpy(to, from, sizeof(*to));
+285         else
+286                 /* _sigchld is currently the largest know union member */
+287                 memcpy(to, from, __ARCH_SI_PREAMBLE_SIZE + sizeof(from->_sifields._sigchld));
+288 }
+
+Since this was a read (kmemcheck usually warns about reads only, though it can
+warn about writes to unallocated or freed memory as well), it was probably the
+"from" argument which contained some uninitialized bytes. Following the chain
+of calls, we move upwards to see where "from" was allocated or initialized,
+kernel/signal.c, line 380:
+
+359 static void collect_signal(int sig, struct sigpending *list, siginfo_t *info)
+360 {
+...
+367         list_for_each_entry(q, &list->list, list) {
+368                 if (q->info.si_signo == sig) {
+369                         if (first)
+370                                 goto still_pending;
+371                         first = q;
+...
+377         if (first) {
+378 still_pending:
+379                 list_del_init(&first->list);
+380                 copy_siginfo(info, &first->info);
+381                 __sigqueue_free(first);
+...
+392         }
+393 }
+
+Here, it is &first->info that is being passed on to copy_siginfo(). The
+variable "first" was found on a list -- passed in as the second argument to
+collect_signal(). We  continue our journey through the stack, to figure out
+where the item on "list" was allocated or initialized. We move to line 410:
+
+395 static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
+396                         siginfo_t *info)
+397 {
+...
+410                 collect_signal(sig, pending, info);
+...
+414 }
+
+Now we need to follow the "pending" pointer, since that is being passed on to
+collect_signal() as "list". At this point, we've run out of lines from the
+"addr2line" output. Not to worry, we just paste the next addresses from the
+kmemcheck stack dump, i.e.:
+
+ [<ffffffff8104f04e>] dequeue_signal+0x8e/0x170
+ [<ffffffff81050bd8>] get_signal_to_deliver+0x98/0x390
+ [<ffffffff8100b87d>] do_notify_resume+0xad/0x7d0
+ [<ffffffff8100c7b5>] int_signal+0x12/0x17
+
+	$ addr2line -e vmlinux -i ffffffff8104f04e ffffffff81050bd8 \
+		ffffffff8100b87d ffffffff8100c7b5
+	kernel/signal.c:446
+	kernel/signal.c:1806
+	arch/x86/kernel/signal.c:805
+	arch/x86/kernel/signal.c:871
+	arch/x86/kernel/entry_64.S:694
+
+Remember that since these addresses were found on the stack and not as the
+RIP value, they actually point to the _next_ instruction (they are return
+addresses). This becomes obvious when we look at the code for line 446:
+
+422 int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
+423 {
+...
+431                 signr = __dequeue_signal(&tsk->signal->shared_pending,
+432                                          mask, info);
+433                 /*
+434                  * itimer signal ?
+435                  *
+436                  * itimers are process shared and we restart periodic
+437                  * itimers in the signal delivery path to prevent DoS
+438                  * attacks in the high resolution timer case. This is
+439                  * compliant with the old way of self restarting
+440                  * itimers, as the SIGALRM is a legacy signal and only
+441                  * queued once. Changing the restart behaviour to
+442                  * restart the timer in the signal dequeue path is
+443                  * reducing the timer noise on heavy loaded !highres
+444                  * systems too.
+445                  */
+446                 if (unlikely(signr == SIGALRM)) {
+...
+489 }
+
+So instead of looking at 446, we should be looking at 431, which is the line
+that executes just before 446. Here we see that what we are looking for is
+&tsk->signal->shared_pending.
+
+Our next task is now to figure out which function that puts items on this
+"shared_pending" list. A crude, but efficient tool, is git grep:
+
+	$ git grep -n 'shared_pending' kernel/
+	...
+	kernel/signal.c:828:    pending = group ? &t->signal->shared_pending : &t->pending;
+	kernel/signal.c:1339:   pending = group ? &t->signal->shared_pending : &t->pending;
+	...
+
+There were more results, but none of them were related to list operations,
+and these were the only assignments. We inspect the line numbers more closely
+and find that this is indeed where items are being added to the list:
+
+816 static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
+817                         int group)
+818 {
+...
+828         pending = group ? &t->signal->shared_pending : &t->pending;
+...
+851         q = __sigqueue_alloc(t, GFP_ATOMIC, (sig < SIGRTMIN &&
+852                                              (is_si_special(info) ||
+853                                               info->si_code >= 0)));
+854         if (q) {
+855                 list_add_tail(&q->list, &pending->list);
+...
+890 }
+
+and:
+
+1309 int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
+1310 {
+....
+1339         pending = group ? &t->signal->shared_pending : &t->pending;
+1340         list_add_tail(&q->list, &pending->list);
+....
+1347 }
+
+In the first case, the list element we are looking for, "q", is being returned
+from the function __sigqueue_alloc(), which looks like an allocation function.
+Let's take a look at it:
+
+187 static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
+188                                          int override_rlimit)
+189 {
+190         struct sigqueue *q = NULL;
+191         struct user_struct *user;
+192 
+193         /*
+194          * We won't get problems with the target's UID changing under us
+195          * because changing it requires RCU be used, and if t != current, the
+196          * caller must be holding the RCU readlock (by way of a spinlock) and
+197          * we use RCU protection here
+198          */
+199         user = get_uid(__task_cred(t)->user);
+200         atomic_inc(&user->sigpending);
+201         if (override_rlimit ||
+202             atomic_read(&user->sigpending) <=
+203                         t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur)
+204                 q = kmem_cache_alloc(sigqueue_cachep, flags);
+205         if (unlikely(q == NULL)) {
+206                 atomic_dec(&user->sigpending);
+207                 free_uid(user);
+208         } else {
+209                 INIT_LIST_HEAD(&q->list);
+210                 q->flags = 0;
+211                 q->user = user;
+212         }
+213 
+214         return q;
+215 }
+
+We see that this function initializes q->list, q->flags, and q->user. It seems
+that now is the time to look at the definition of "struct sigqueue", e.g.:
+
+14 struct sigqueue {
+15         struct list_head list;
+16         int flags;
+17         siginfo_t info;
+18         struct user_struct *user;
+19 };
+
+And, you might remember, it was a memcpy() on &first->info that caused the
+warning, so this makes perfect sense. It also seems reasonable to assume that
+it is the caller of __sigqueue_alloc() that has the responsibility of filling
+out (initializing) this member.
+
+But just which fields of the struct were uninitialized? Let's look at
+kmemcheck's report again:
+
+WARNING: kmemcheck: Caught 32-bit read from uninitialized memory (ffff88003e4a2024)
+80000000000000000000000000000000000000000088ffff0000000000000000
+ i i i i u u u u i i i i i i i i u u u u u u u u u u u u u u u u
+         ^
+
+These first two lines are the memory dump of the memory object itself, and the
+shadow bytemap, respectively. The memory object itself is in this case
+&first->info. Just beware that the start of this dump is NOT the start of the
+object itself! The position of the caret (^) corresponds with the address of
+the read (ffff88003e4a2024).
+
+The shadow bytemap dump legend is as follows:
+
+  i - initialized
+  u - uninitialized
+  a - unallocated (memory has been allocated by the slab layer, but has not
+      yet been handed off to anybody)
+  f - freed (memory has been allocated by the slab layer, but has been freed
+      by the previous owner)
+
+In order to figure out where (relative to the start of the object) the
+uninitialized memory was located, we have to look at the disassembly. For
+that, we'll need the RIP address again:
+
+RIP: 0010:[<ffffffff8104ede8>]  [<ffffffff8104ede8>] __dequeue_signal+0xc8/0x190
+
+	$ objdump -d --no-show-raw-insn vmlinux | grep -C 8 ffffffff8104ede8:
+	ffffffff8104edc8:       mov    %r8,0x8(%r8)
+	ffffffff8104edcc:       test   %r10d,%r10d
+	ffffffff8104edcf:       js     ffffffff8104ee88 <__dequeue_signal+0x168>
+	ffffffff8104edd5:       mov    %rax,%rdx
+	ffffffff8104edd8:       mov    $0xc,%ecx
+	ffffffff8104eddd:       mov    %r13,%rdi
+	ffffffff8104ede0:       mov    $0x30,%eax
+	ffffffff8104ede5:       mov    %rdx,%rsi
+	ffffffff8104ede8:       rep movsl %ds:(%rsi),%es:(%rdi)
+	ffffffff8104edea:       test   $0x2,%al
+	ffffffff8104edec:       je     ffffffff8104edf0 <__dequeue_signal+0xd0>
+	ffffffff8104edee:       movsw  %ds:(%rsi),%es:(%rdi)
+	ffffffff8104edf0:       test   $0x1,%al
+	ffffffff8104edf2:       je     ffffffff8104edf5 <__dequeue_signal+0xd5>
+	ffffffff8104edf4:       movsb  %ds:(%rsi),%es:(%rdi)
+	ffffffff8104edf5:       mov    %r8,%rdi
+	ffffffff8104edf8:       callq  ffffffff8104de60 <__sigqueue_free>
+
+As expected, it's the "rep movsl" instruction from the memcpy() that causes
+the warning. We know about REP MOVSL that it uses the register RCX to count
+the number of remaining iterations. By taking a look at the register dump
+again (from the kmemcheck report), we can figure out how many bytes were left
+to copy:
+
+RAX: 0000000000000030 RBX: ffff88003d4ea968 RCX: 0000000000000009
+
+By looking at the disassembly, we also see that %ecx is being loaded with the
+value $0xc just before (ffffffff8104edd8), so we are very lucky. Keep in mind
+that this is the number of iterations, not bytes. And since this is a "long"
+operation, we need to multiply by 4 to get the number of bytes. So this means
+that the uninitialized value was encountered at 4 * (0xc - 0x9) = 12 bytes
+from the start of the object.
+
+We can now try to figure out which field of the "struct siginfo" that was not
+initialized. This is the beginning of the struct:
+
+40 typedef struct siginfo {
+41         int si_signo;
+42         int si_errno;
+43         int si_code;
+44                 
+45         union {
+..
+92         } _sifields;
+93 } siginfo_t;
+
+On 64-bit, the int is 4 bytes long, so it must the the union member that has
+not been initialized. We can verify this using gdb:
+
+	$ gdb vmlinux
+	...
+	(gdb) p &((struct siginfo *) 0)->_sifields
+	$1 = (union {...} *) 0x10
+
+Actually, it seems that the union member is located at offset 0x10 -- which
+means that gcc has inserted 4 bytes of padding between the members si_code
+and _sifields. We can now get a fuller picture of the memory dump:
+
+         _----------------------------=> si_code
+        /        _--------------------=> (padding)
+       |        /        _------------=> _sifields(._kill._pid)
+       |       |        /        _----=> _sifields(._kill._uid)
+       |       |       |        / 
+-------|-------|-------|-------|
+80000000000000000000000000000000000000000088ffff0000000000000000
+ i i i i u u u u i i i i i i i i u u u u u u u u u u u u u u u u
+
+This allows us to realize another important fact: si_code contains the value
+0x80. Remember that x86 is little endian, so the first 4 bytes "80000000" are
+really the number 0x00000080. With a bit of research, we find that this is
+actually the constant SI_KERNEL defined in include/asm-generic/siginfo.h:
+
+144 #define SI_KERNEL       0x80            /* sent by the kernel from somewhere     */
+
+This macro is used in exactly one place in the x86 kernel: In send_signal()
+in kernel/signal.c:
+
+816 static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
+817                         int group)
+818 {
+...
+828         pending = group ? &t->signal->shared_pending : &t->pending;
+...
+851         q = __sigqueue_alloc(t, GFP_ATOMIC, (sig < SIGRTMIN &&
+852                                              (is_si_special(info) ||
+853                                               info->si_code >= 0)));
+854         if (q) {
+855                 list_add_tail(&q->list, &pending->list);
+856                 switch ((unsigned long) info) {
+...
+865                 case (unsigned long) SEND_SIG_PRIV:
+866                         q->info.si_signo = sig;
+867                         q->info.si_errno = 0;
+868                         q->info.si_code = SI_KERNEL;
+869                         q->info.si_pid = 0;
+870                         q->info.si_uid = 0;
+871                         break;
+...
+890 }
+
+Not only does this match with the .si_code member, it also matches the place
+we found earlier when looking for where siginfo_t objects are enqueued on the
+"shared_pending" list.
+
+So to sum up: It seems that it is the padding introduced by the compiler
+between two struct fields that is uninitialized, and this gets reported when
+we do a memcpy() on the struct. This means that we have identified a false
+positive warning.
+
+Normally, kmemcheck will not report uninitialized accesses in memcpy() calls
+when both the source and destination addresses are tracked. (Instead, we copy
+the shadow bytemap as well). In this case, the destination address clearly
+was not tracked. We can dig a little deeper into the stack trace from above:
+
+	arch/x86/kernel/signal.c:805
+	arch/x86/kernel/signal.c:871
+	arch/x86/kernel/entry_64.S:694
+
+And we clearly see that the destination siginfo object is located on the
+stack:
+
+782 static void do_signal(struct pt_regs *regs)
+783 {
+784         struct k_sigaction ka;
+785         siginfo_t info;
+...
+804         signr = get_signal_to_deliver(&info, &ka, regs, NULL);
+...
+854 }
+
+And this &info is what eventually gets passed to copy_siginfo() as the
+destination argument.
+
+Now, even though we didn't find an actual error here, the example is still a
+good one, because it shows how one would go about to find out what the report
+was all about.
+
+
+3.4. Annotating false positives
+===============================
+
+There are a few different ways to make annotations in the source code that
+will keep kmemcheck from checking and reporting certain allocations. Here
+they are:
+
+  o __GFP_NOTRACK_FALSE_POSITIVE
+
+	This flag can be passed to kmalloc() or kmem_cache_alloc() (therefore
+	also to other functions that end up calling one of these) to indicate
+	that the allocation should not be tracked because it would lead to
+	a false positive report. This is a "big hammer" way of silencing
+	kmemcheck; after all, even if the false positive pertains to 
+	particular field in a struct, for example, we will now lose the
+	ability to find (real) errors in other parts of the same struct.
+
+	Example:
+
+	    /* No warnings will ever trigger on accessing any part of x */
+	    x = kmalloc(sizeof *x, GFP_KERNEL | __GFP_NOTRACK_FALSE_POSITIVE);
+
+  o kmemcheck_bitfield_begin(name)/kmemcheck_bitfield_end(name) and
+	kmemcheck_annotate_bitfield(ptr, name)
+
+	The first two of these three macros can be used inside struct
+	definitions to signal, respectively, the beginning and end of a
+	bitfield. Additionally, this will assign the bitfield a name, which
+	is given as an argument to the macros.
+
+	Having used these markers, one can later use
+	kmemcheck_annotate_bitfield() at the point of allocation, to indicate
+	which parts of the allocation is part of a bitfield.
+
+	Example:
+
+	    struct foo {
+		int x;
+
+		kmemcheck_bitfield_begin(flags);
+		int flag_a:1;
+		int flag_b:1;
+		kmemcheck_bitfield_end(flags);
+
+		int y;
+	    };
+
+	    struct foo *x = kmalloc(sizeof *x);
+
+	    /* No warnings will trigger on accessing the bitfield of x */
+	    kmemcheck_annotate_bitfield(x, flags);
+
+	Note that kmemcheck_annotate_bitfield() can be used even before the
+	return value of kmalloc() is checked -- in other words, passing NULL
+	as the first argument is legal (and will do nothing).
+
+
+4. Reporting errors
+===================
+
+As we have seen, kmemcheck will produce false positive reports. Therefore, it
+is not very wise to blindly post kmemcheck warnings to mailing lists and
+maintainers. Instead, I encourage maintainers and developers to find errors
+in their own code. If you get a warning, you can try to work around it, try
+to figure out if it's a real error or not, or simply ignore it. Most
+developers know their own code and will quickly and efficiently determine the
+root cause of a kmemcheck report. This is therefore also the most efficient
+way to work with kmemcheck.
+
+That said, we (the kmemcheck maintainers) will always be on the lookout for
+false positives that we can annotate and silence. So whatever you find,
+please drop us a note privately! Kernel configs and steps to reproduce (if
+available) are of course a great help too.
+
+Happy hacking!
+
+
+5. Technical description
+========================
+
+kmemcheck works by marking memory pages non-present. This means that whenever
+somebody attempts to access the page, a page fault is generated. The page
+fault handler notices that the page was in fact only hidden, and so it calls
+on the kmemcheck code to make further investigations.
+
+When the investigations are completed, kmemcheck "shows" the page by marking
+it present (as it would be under normal circumstances). This way, the
+interrupted code can continue as usual.
+
+But after the instruction has been executed, we should hide the page again, so
+that we can catch the next access too! Now kmemcheck makes use of a debugging
+feature of the processor, namely single-stepping. When the processor has
+finished the one instruction that generated the memory access, a debug
+exception is raised. From here, we simply hide the page again and continue
+execution, this time with the single-stepping feature turned off.
+
+kmemcheck requires some assistance from the memory allocator in order to work.
+The memory allocator needs to
+
+  1. Tell kmemcheck about newly allocated pages and pages that are about to
+     be freed. This allows kmemcheck to set up and tear down the shadow memory
+     for the pages in question. The shadow memory stores the status of each
+     byte in the allocation proper, e.g. whether it is initialized or
+     uninitialized.
+
+  2. Tell kmemcheck which parts of memory should be marked uninitialized.
+     There are actually a few more states, such as "not yet allocated" and
+     "recently freed".
+
+If a slab cache is set up using the SLAB_NOTRACK flag, it will never return
+memory that can take page faults because of kmemcheck.
+
+If a slab cache is NOT set up using the SLAB_NOTRACK flag, callers can still
+request memory with the __GFP_NOTRACK or __GFP_NOTRACK_FALSE_POSITIVE flags.
+This does not prevent the page faults from occurring, however, but marks the
+object in question as being initialized so that no warnings will ever be
+produced for this object.
+
+Currently, the SLAB and SLUB allocators are supported by kmemcheck.
diff --git a/Documentation/kmemleak.txt b/Documentation/kmemleak.txt
new file mode 100644
index 00000000000..0112da3b9ab
--- /dev/null
+++ b/Documentation/kmemleak.txt
@@ -0,0 +1,142 @@
+Kernel Memory Leak Detector
+===========================
+
+Introduction
+------------
+
+Kmemleak provides a way of detecting possible kernel memory leaks in a
+way similar to a tracing garbage collector
+(http://en.wikipedia.org/wiki/Garbage_collection_%28computer_science%29#Tracing_garbage_collectors),
+with the difference that the orphan objects are not freed but only
+reported via /sys/kernel/debug/kmemleak. A similar method is used by the
+Valgrind tool (memcheck --leak-check) to detect the memory leaks in
+user-space applications.
+
+Usage
+-----
+
+CONFIG_DEBUG_KMEMLEAK in "Kernel hacking" has to be enabled. A kernel
+thread scans the memory every 10 minutes (by default) and prints any new
+unreferenced objects found. To trigger an intermediate scan and display
+all the possible memory leaks:
+
+  # mount -t debugfs nodev /sys/kernel/debug/
+  # cat /sys/kernel/debug/kmemleak
+
+Note that the orphan objects are listed in the order they were allocated
+and one object at the beginning of the list may cause other subsequent
+objects to be reported as orphan.
+
+Memory scanning parameters can be modified at run-time by writing to the
+/sys/kernel/debug/kmemleak file. The following parameters are supported:
+
+  off		- disable kmemleak (irreversible)
+  stack=on	- enable the task stacks scanning
+  stack=off	- disable the tasks stacks scanning
+  scan=on	- start the automatic memory scanning thread
+  scan=off	- stop the automatic memory scanning thread
+  scan=<secs>	- set the automatic memory scanning period in seconds (0
+		  to disable it)
+
+Kmemleak can also be disabled at boot-time by passing "kmemleak=off" on
+the kernel command line.
+
+Basic Algorithm
+---------------
+
+The memory allocations via kmalloc, vmalloc, kmem_cache_alloc and
+friends are traced and the pointers, together with additional
+information like size and stack trace, are stored in a prio search tree.
+The corresponding freeing function calls are tracked and the pointers
+removed from the kmemleak data structures.
+
+An allocated block of memory is considered orphan if no pointer to its
+start address or to any location inside the block can be found by
+scanning the memory (including saved registers). This means that there
+might be no way for the kernel to pass the address of the allocated
+block to a freeing function and therefore the block is considered a
+memory leak.
+
+The scanning algorithm steps:
+
+  1. mark all objects as white (remaining white objects will later be
+     considered orphan)
+  2. scan the memory starting with the data section and stacks, checking
+     the values against the addresses stored in the prio search tree. If
+     a pointer to a white object is found, the object is added to the
+     gray list
+  3. scan the gray objects for matching addresses (some white objects
+     can become gray and added at the end of the gray list) until the
+     gray set is finished
+  4. the remaining white objects are considered orphan and reported via
+     /sys/kernel/debug/kmemleak
+
+Some allocated memory blocks have pointers stored in the kernel's
+internal data structures and they cannot be detected as orphans. To
+avoid this, kmemleak can also store the number of values pointing to an
+address inside the block address range that need to be found so that the
+block is not considered a leak. One example is __vmalloc().
+
+Kmemleak API
+------------
+
+See the include/linux/kmemleak.h header for the functions prototype.
+
+kmemleak_init		 - initialize kmemleak
+kmemleak_alloc		 - notify of a memory block allocation
+kmemleak_free		 - notify of a memory block freeing
+kmemleak_not_leak	 - mark an object as not a leak
+kmemleak_ignore		 - do not scan or report an object as leak
+kmemleak_scan_area	 - add scan areas inside a memory block
+kmemleak_no_scan	 - do not scan a memory block
+kmemleak_erase		 - erase an old value in a pointer variable
+kmemleak_alloc_recursive - as kmemleak_alloc but checks the recursiveness
+kmemleak_free_recursive	 - as kmemleak_free but checks the recursiveness
+
+Dealing with false positives/negatives
+--------------------------------------
+
+The false negatives are real memory leaks (orphan objects) but not
+reported by kmemleak because values found during the memory scanning
+point to such objects. To reduce the number of false negatives, kmemleak
+provides the kmemleak_ignore, kmemleak_scan_area, kmemleak_no_scan and
+kmemleak_erase functions (see above). The task stacks also increase the
+amount of false negatives and their scanning is not enabled by default.
+
+The false positives are objects wrongly reported as being memory leaks
+(orphan). For objects known not to be leaks, kmemleak provides the
+kmemleak_not_leak function. The kmemleak_ignore could also be used if
+the memory block is known not to contain other pointers and it will no
+longer be scanned.
+
+Some of the reported leaks are only transient, especially on SMP
+systems, because of pointers temporarily stored in CPU registers or
+stacks. Kmemleak defines MSECS_MIN_AGE (defaulting to 1000) representing
+the minimum age of an object to be reported as a memory leak.
+
+Limitations and Drawbacks
+-------------------------
+
+The main drawback is the reduced performance of memory allocation and
+freeing. To avoid other penalties, the memory scanning is only performed
+when the /sys/kernel/debug/kmemleak file is read. Anyway, this tool is
+intended for debugging purposes where the performance might not be the
+most important requirement.
+
+To keep the algorithm simple, kmemleak scans for values pointing to any
+address inside a block's address range. This may lead to an increased
+number of false negatives. However, it is likely that a real memory leak
+will eventually become visible.
+
+Another source of false negatives is the data stored in non-pointer
+values. In a future version, kmemleak could only scan the pointer
+members in the allocated structures. This feature would solve many of
+the false negative cases described above.
+
+The tool can report false positives. These are cases where an allocated
+block doesn't need to be freed (some cases in the init_call functions),
+the pointer is calculated by other methods than the usual container_of
+macro or the pointer is stored in a location not scanned by kmemleak.
+
+Page allocations and ioremap are not tracked. Only the ARM and x86
+architectures are currently supported.
diff --git a/Documentation/kobject.txt b/Documentation/kobject.txt
index b2e374586bd..c79ab996dad 100644
--- a/Documentation/kobject.txt
+++ b/Documentation/kobject.txt
@@ -132,7 +132,7 @@ kobject_name():
     const char *kobject_name(const struct kobject * kobj);
 
 There is a helper function to both initialize and add the kobject to the
-kernel at the same time, called supprisingly enough kobject_init_and_add():
+kernel at the same time, called surprisingly enough kobject_init_and_add():
 
     int kobject_init_and_add(struct kobject *kobj, struct kobj_type *ktype,
                              struct kobject *parent, const char *fmt, ...);
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 1e7a769a10f..053037a1fe6 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -507,9 +507,9 @@ http://www.linuxsymposium.org/2006/linuxsymposium_procv2.pdf (pages 101-115)
 Appendix A: The kprobes debugfs interface
 
 With recent kernels (> 2.6.20) the list of registered kprobes is visible
-under the /debug/kprobes/ directory (assuming debugfs is mounted at /debug).
+under the /sys/kernel/debug/kprobes/ directory (assuming debugfs is mounted at //sys/kernel/debug).
 
-/debug/kprobes/list: Lists all registered probes on the system
+/sys/kernel/debug/kprobes/list: Lists all registered probes on the system
 
 c015d71a  k  vfs_read+0x0
 c011a316  j  do_fork+0x0
@@ -525,7 +525,7 @@ virtual addresses that correspond to modules that've been unloaded),
 such probes are marked with [GONE]. If the probe is temporarily disabled,
 such probes are marked with [DISABLED].
 
-/debug/kprobes/enabled: Turn kprobes ON/OFF forcibly.
+/sys/kernel/debug/kprobes/enabled: Turn kprobes ON/OFF forcibly.
 
 Provides a knob to globally and forcibly turn registered kprobes ON or OFF.
 By default, all kprobes are enabled. By echoing "0" to this file, all
diff --git a/Documentation/laptops/acer-wmi.txt b/Documentation/laptops/acer-wmi.txt
index 5ee2a02b3b4..0768fcc3ba3 100644
--- a/Documentation/laptops/acer-wmi.txt
+++ b/Documentation/laptops/acer-wmi.txt
@@ -40,7 +40,7 @@ NOTE: The Acer Aspire One is not supported hardware. It cannot work with
 acer-wmi until Acer fix their ACPI-WMI implementation on them, so has been
 blacklisted until that happens.
 
-Please see the website for the current list of known working hardare:
+Please see the website for the current list of known working hardware:
 
 http://code.google.com/p/aceracpi/wiki/SupportedHardware
 
diff --git a/Documentation/laptops/sony-laptop.txt b/Documentation/laptops/sony-laptop.txt
index 8b2bc1572d9..23ce7d350d1 100644
--- a/Documentation/laptops/sony-laptop.txt
+++ b/Documentation/laptops/sony-laptop.txt
@@ -22,7 +22,7 @@ If your laptop model supports it, you will find sysfs files in the
 /sys/class/backlight/sony/
 directory. You will be able to query and set the current screen
 brightness:
-	brightness		get/set screen brightness (an iteger
+	brightness		get/set screen brightness (an integer
 				between 0 and 7)
 	actual_brightness	reading from this file will query the HW
 				to get real brightness value
diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt
index e7e9a69069e..78e354b42f6 100644
--- a/Documentation/laptops/thinkpad-acpi.txt
+++ b/Documentation/laptops/thinkpad-acpi.txt
@@ -506,7 +506,7 @@ generate input device EV_KEY events.
 In addition to the EV_KEY events, thinkpad-acpi may also issue EV_SW
 events for switches:
 
-SW_RFKILL_ALL	T60 and later hardare rfkill rocker switch
+SW_RFKILL_ALL	T60 and later hardware rfkill rocker switch
 SW_TABLET_MODE	Tablet ThinkPads HKEY events 0x5009 and 0x500A
 
 Non hot-key ACPI HKEY event map:
diff --git a/Documentation/lguest/Makefile b/Documentation/lguest/Makefile
index 1f4f9e888bd..28c8cdfcafd 100644
--- a/Documentation/lguest/Makefile
+++ b/Documentation/lguest/Makefile
@@ -1,6 +1,5 @@
 # This creates the demonstration utility "lguest" which runs a Linux guest.
-CFLAGS:=-Wall -Wmissing-declarations -Wmissing-prototypes -O3 -I../../include -I../../arch/x86/include -U_FORTIFY_SOURCE
-LDLIBS:=-lz
+CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -I../../include -I../../arch/x86/include -U_FORTIFY_SOURCE
 
 all: lguest
 
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index d36fcc0f271..9ebcd6ef361 100644
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/lguest/lguest.c
@@ -16,6 +16,7 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/wait.h>
+#include <sys/eventfd.h>
 #include <fcntl.h>
 #include <stdbool.h>
 #include <errno.h>
@@ -59,7 +60,6 @@ typedef uint8_t u8;
 /*:*/
 
 #define PAGE_PRESENT 0x7 	/* Present, RW, Execute */
-#define NET_PEERNUM 1
 #define BRIDGE_PFX "bridge:"
 #ifndef SIOCBRADDIF
 #define SIOCBRADDIF	0x89a2		/* add interface to bridge      */
@@ -76,19 +76,12 @@ static bool verbose;
 	do { if (verbose) printf(args); } while(0)
 /*:*/
 
-/* File descriptors for the Waker. */
-struct {
-	int pipe[2];
-	int lguest_fd;
-} waker_fds;
-
 /* The pointer to the start of guest memory. */
 static void *guest_base;
 /* The maximum guest physical address allowed, and maximum possible. */
 static unsigned long guest_limit, guest_max;
-/* The pipe for signal hander to write to. */
-static int timeoutpipe[2];
-static unsigned int timeout_usec = 500;
+/* The /dev/lguest file descriptor. */
+static int lguest_fd;
 
 /* a per-cpu variable indicating whose vcpu is currently running */
 static unsigned int __thread cpu_id;
@@ -96,11 +89,6 @@ static unsigned int __thread cpu_id;
 /* This is our list of devices. */
 struct device_list
 {
-	/* Summary information about the devices in our list: ready to pass to
-	 * select() to ask which need servicing.*/
-	fd_set infds;
-	int max_infd;
-
 	/* Counter to assign interrupt numbers. */
 	unsigned int next_irq;
 
@@ -126,22 +114,21 @@ struct device
 	/* The linked-list pointer. */
 	struct device *next;
 
-	/* The this device's descriptor, as mapped into the Guest. */
+	/* The device's descriptor, as mapped into the Guest. */
 	struct lguest_device_desc *desc;
 
+	/* We can't trust desc values once Guest has booted: we use these. */
+	unsigned int feature_len;
+	unsigned int num_vq;
+
 	/* The name of this device, for --verbose. */
 	const char *name;
 
-	/* If handle_input is set, it wants to be called when this file
-	 * descriptor is ready. */
-	int fd;
-	bool (*handle_input)(int fd, struct device *me);
-
 	/* Any queues attached to this device */
 	struct virtqueue *vq;
 
-	/* Handle status being finalized (ie. feature bits stable). */
-	void (*ready)(struct device *me);
+	/* Is it operational */
+	bool running;
 
 	/* Device-specific data. */
 	void *priv;
@@ -164,22 +151,28 @@ struct virtqueue
 	/* Last available index we saw. */
 	u16 last_avail_idx;
 
-	/* The routine to call when the Guest pings us, or timeout. */
-	void (*handle_output)(int fd, struct virtqueue *me, bool timeout);
+	/* How many are used since we sent last irq? */
+	unsigned int pending_used;
 
-	/* Outstanding buffers */
-	unsigned int inflight;
+	/* Eventfd where Guest notifications arrive. */
+	int eventfd;
 
-	/* Is this blocked awaiting a timer? */
-	bool blocked;
+	/* Function for the thread which is servicing this virtqueue. */
+	void (*service)(struct virtqueue *vq);
+	pid_t thread;
 };
 
 /* Remember the arguments to the program so we can "reboot" */
 static char **main_args;
 
-/* Since guest is UP and we don't run at the same time, we don't need barriers.
- * But I include them in the code in case others copy it. */
-#define wmb()
+/* The original tty settings to restore on exit. */
+static struct termios orig_term;
+
+/* We have to be careful with barriers: our devices are all run in separate
+ * threads and so we need to make sure that changes visible to the Guest happen
+ * in precise order. */
+#define wmb() __asm__ __volatile__("" : : : "memory")
+#define mb() __asm__ __volatile__("" : : : "memory")
 
 /* Convert an iovec element to the given type.
  *
@@ -245,7 +238,7 @@ static void iov_consume(struct iovec iov[], unsigned num_iov, unsigned len)
 static u8 *get_feature_bits(struct device *dev)
 {
 	return (u8 *)(dev->desc + 1)
-		+ dev->desc->num_vq * sizeof(struct lguest_vqconfig);
+		+ dev->num_vq * sizeof(struct lguest_vqconfig);
 }
 
 /*L:100 The Launcher code itself takes us out into userspace, that scary place
@@ -505,99 +498,19 @@ static void concat(char *dst, char *args[])
  * saw the arguments it expects when we looked at initialize() in lguest_user.c:
  * the base of Guest "physical" memory, the top physical page to allow and the
  * entry point for the Guest. */
-static int tell_kernel(unsigned long start)
+static void tell_kernel(unsigned long start)
 {
 	unsigned long args[] = { LHREQ_INITIALIZE,
 				 (unsigned long)guest_base,
 				 guest_limit / getpagesize(), start };
-	int fd;
-
 	verbose("Guest: %p - %p (%#lx)\n",
 		guest_base, guest_base + guest_limit, guest_limit);
-	fd = open_or_die("/dev/lguest", O_RDWR);
-	if (write(fd, args, sizeof(args)) < 0)
+	lguest_fd = open_or_die("/dev/lguest", O_RDWR);
+	if (write(lguest_fd, args, sizeof(args)) < 0)
 		err(1, "Writing to /dev/lguest");
-
-	/* We return the /dev/lguest file descriptor to control this Guest */
-	return fd;
 }
 /*:*/
 
-static void add_device_fd(int fd)
-{
-	FD_SET(fd, &devices.infds);
-	if (fd > devices.max_infd)
-		devices.max_infd = fd;
-}
-
-/*L:200
- * The Waker.
- *
- * With console, block and network devices, we can have lots of input which we
- * need to process.  We could try to tell the kernel what file descriptors to
- * watch, but handing a file descriptor mask through to the kernel is fairly
- * icky.
- *
- * Instead, we clone off a thread which watches the file descriptors and writes
- * the LHREQ_BREAK command to the /dev/lguest file descriptor to tell the Host
- * stop running the Guest.  This causes the Launcher to return from the
- * /dev/lguest read with -EAGAIN, where it will write to /dev/lguest to reset
- * the LHREQ_BREAK and wake us up again.
- *
- * This, of course, is merely a different *kind* of icky.
- *
- * Given my well-known antipathy to threads, I'd prefer to use processes.  But
- * it's easier to share Guest memory with threads, and trivial to share the
- * devices.infds as the Launcher changes it.
- */
-static int waker(void *unused)
-{
-	/* Close the write end of the pipe: only the Launcher has it open. */
-	close(waker_fds.pipe[1]);
-
-	for (;;) {
-		fd_set rfds = devices.infds;
-		unsigned long args[] = { LHREQ_BREAK, 1 };
-		unsigned int maxfd = devices.max_infd;
-
-		/* We also listen to the pipe from the Launcher. */
-		FD_SET(waker_fds.pipe[0], &rfds);
-		if (waker_fds.pipe[0] > maxfd)
-			maxfd = waker_fds.pipe[0];
-
-		/* Wait until input is ready from one of the devices. */
-		select(maxfd+1, &rfds, NULL, NULL, NULL);
-
-		/* Message from Launcher? */
-		if (FD_ISSET(waker_fds.pipe[0], &rfds)) {
-			char c;
-			/* If this fails, then assume Launcher has exited.
-			 * Don't do anything on exit: we're just a thread! */
-			if (read(waker_fds.pipe[0], &c, 1) != 1)
-				_exit(0);
-			continue;
-		}
-
-		/* Send LHREQ_BREAK command to snap the Launcher out of it. */
-		pwrite(waker_fds.lguest_fd, args, sizeof(args), cpu_id);
-	}
-	return 0;
-}
-
-/* This routine just sets up a pipe to the Waker process. */
-static void setup_waker(int lguest_fd)
-{
-	/* This pipe is closed when Launcher dies, telling Waker. */
-	if (pipe(waker_fds.pipe) != 0)
-		err(1, "Creating pipe for Waker");
-
-	/* Waker also needs to know the lguest fd */
-	waker_fds.lguest_fd = lguest_fd;
-
-	if (clone(waker, malloc(4096) + 4096, CLONE_VM | SIGCHLD, NULL) == -1)
-		err(1, "Creating Waker");
-}
-
 /*
  * Device Handling.
  *
@@ -623,49 +536,90 @@ static void *_check_pointer(unsigned long addr, unsigned int size,
 /* Each buffer in the virtqueues is actually a chain of descriptors.  This
  * function returns the next descriptor in the chain, or vq->vring.num if we're
  * at the end. */
-static unsigned next_desc(struct virtqueue *vq, unsigned int i)
+static unsigned next_desc(struct vring_desc *desc,
+			  unsigned int i, unsigned int max)
 {
 	unsigned int next;
 
 	/* If this descriptor says it doesn't chain, we're done. */
-	if (!(vq->vring.desc[i].flags & VRING_DESC_F_NEXT))
-		return vq->vring.num;
+	if (!(desc[i].flags & VRING_DESC_F_NEXT))
+		return max;
 
 	/* Check they're not leading us off end of descriptors. */
-	next = vq->vring.desc[i].next;
+	next = desc[i].next;
 	/* Make sure compiler knows to grab that: we don't want it changing! */
 	wmb();
 
-	if (next >= vq->vring.num)
+	if (next >= max)
 		errx(1, "Desc next is %u", next);
 
 	return next;
 }
 
+/* This actually sends the interrupt for this virtqueue */
+static void trigger_irq(struct virtqueue *vq)
+{
+	unsigned long buf[] = { LHREQ_IRQ, vq->config.irq };
+
+	/* Don't inform them if nothing used. */
+	if (!vq->pending_used)
+		return;
+	vq->pending_used = 0;
+
+	/* If they don't want an interrupt, don't send one, unless empty. */
+	if ((vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
+	    && lg_last_avail(vq) != vq->vring.avail->idx)
+		return;
+
+	/* Send the Guest an interrupt tell them we used something up. */
+	if (write(lguest_fd, buf, sizeof(buf)) != 0)
+		err(1, "Triggering irq %i", vq->config.irq);
+}
+
 /* This looks in the virtqueue and for the first available buffer, and converts
  * it to an iovec for convenient access.  Since descriptors consist of some
  * number of output then some number of input descriptors, it's actually two
  * iovecs, but we pack them into one and note how many of each there were.
  *
- * This function returns the descriptor number found, or vq->vring.num (which
- * is never a valid descriptor number) if none was found. */
-static unsigned get_vq_desc(struct virtqueue *vq,
-			    struct iovec iov[],
-			    unsigned int *out_num, unsigned int *in_num)
+ * This function returns the descriptor number found. */
+static unsigned wait_for_vq_desc(struct virtqueue *vq,
+				 struct iovec iov[],
+				 unsigned int *out_num, unsigned int *in_num)
 {
-	unsigned int i, head;
-	u16 last_avail;
+	unsigned int i, head, max;
+	struct vring_desc *desc;
+	u16 last_avail = lg_last_avail(vq);
+
+	while (last_avail == vq->vring.avail->idx) {
+		u64 event;
+
+		/* OK, tell Guest about progress up to now. */
+		trigger_irq(vq);
+
+		/* OK, now we need to know about added descriptors. */
+		vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY;
+
+		/* They could have slipped one in as we were doing that: make
+		 * sure it's written, then check again. */
+		mb();
+		if (last_avail != vq->vring.avail->idx) {
+			vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
+			break;
+		}
+
+		/* Nothing new?  Wait for eventfd to tell us they refilled. */
+		if (read(vq->eventfd, &event, sizeof(event)) != sizeof(event))
+			errx(1, "Event read failed?");
+
+		/* We don't need to be notified again. */
+		vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
+	}
 
 	/* Check it isn't doing very strange things with descriptor numbers. */
-	last_avail = lg_last_avail(vq);
 	if ((u16)(vq->vring.avail->idx - last_avail) > vq->vring.num)
 		errx(1, "Guest moved used index from %u to %u",
 		     last_avail, vq->vring.avail->idx);
 
-	/* If there's nothing new since last we looked, return invalid. */
-	if (vq->vring.avail->idx == last_avail)
-		return vq->vring.num;
-
 	/* Grab the next descriptor number they're advertising, and increment
 	 * the index we've seen. */
 	head = vq->vring.avail->ring[last_avail % vq->vring.num];
@@ -678,15 +632,28 @@ static unsigned get_vq_desc(struct virtqueue *vq,
 	/* When we start there are none of either input nor output. */
 	*out_num = *in_num = 0;
 
+	max = vq->vring.num;
+	desc = vq->vring.desc;
 	i = head;
+
+	/* If this is an indirect entry, then this buffer contains a descriptor
+	 * table which we handle as if it's any normal descriptor chain. */
+	if (desc[i].flags & VRING_DESC_F_INDIRECT) {
+		if (desc[i].len % sizeof(struct vring_desc))
+			errx(1, "Invalid size for indirect buffer table");
+
+		max = desc[i].len / sizeof(struct vring_desc);
+		desc = check_pointer(desc[i].addr, desc[i].len);
+		i = 0;
+	}
+
 	do {
 		/* Grab the first descriptor, and check it's OK. */
-		iov[*out_num + *in_num].iov_len = vq->vring.desc[i].len;
+		iov[*out_num + *in_num].iov_len = desc[i].len;
 		iov[*out_num + *in_num].iov_base
-			= check_pointer(vq->vring.desc[i].addr,
-					vq->vring.desc[i].len);
+			= check_pointer(desc[i].addr, desc[i].len);
 		/* If this is an input descriptor, increment that count. */
-		if (vq->vring.desc[i].flags & VRING_DESC_F_WRITE)
+		if (desc[i].flags & VRING_DESC_F_WRITE)
 			(*in_num)++;
 		else {
 			/* If it's an output descriptor, they're all supposed
@@ -697,11 +664,10 @@ static unsigned get_vq_desc(struct virtqueue *vq,
 		}
 
 		/* If we've got too many, that implies a descriptor loop. */
-		if (*out_num + *in_num > vq->vring.num)
+		if (*out_num + *in_num > max)
 			errx(1, "Looped descriptor");
-	} while ((i = next_desc(vq, i)) != vq->vring.num);
+	} while ((i = next_desc(desc, i, max)) != max);
 
-	vq->inflight++;
 	return head;
 }
 
@@ -719,44 +685,20 @@ static void add_used(struct virtqueue *vq, unsigned int head, int len)
 	/* Make sure buffer is written before we update index. */
 	wmb();
 	vq->vring.used->idx++;
-	vq->inflight--;
-}
-
-/* This actually sends the interrupt for this virtqueue */
-static void trigger_irq(int fd, struct virtqueue *vq)
-{
-	unsigned long buf[] = { LHREQ_IRQ, vq->config.irq };
-
-	/* If they don't want an interrupt, don't send one, unless empty. */
-	if ((vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
-	    && vq->inflight)
-		return;
-
-	/* Send the Guest an interrupt tell them we used something up. */
-	if (write(fd, buf, sizeof(buf)) != 0)
-		err(1, "Triggering irq %i", vq->config.irq);
+	vq->pending_used++;
 }
 
 /* And here's the combo meal deal.  Supersize me! */
-static void add_used_and_trigger(int fd, struct virtqueue *vq,
-				 unsigned int head, int len)
+static void add_used_and_trigger(struct virtqueue *vq, unsigned head, int len)
 {
 	add_used(vq, head, len);
-	trigger_irq(fd, vq);
+	trigger_irq(vq);
 }
 
 /*
  * The Console
  *
- * Here is the input terminal setting we save, and the routine to restore them
- * on exit so the user gets their terminal back. */
-static struct termios orig_term;
-static void restore_term(void)
-{
-	tcsetattr(STDIN_FILENO, TCSANOW, &orig_term);
-}
-
-/* We associate some data with the console for our exit hack. */
+ * We associate some data with the console for our exit hack. */
 struct console_abort
 {
 	/* How many times have they hit ^C? */
@@ -766,276 +708,275 @@ struct console_abort
 };
 
 /* This is the routine which handles console input (ie. stdin). */
-static bool handle_console_input(int fd, struct device *dev)
+static void console_input(struct virtqueue *vq)
 {
 	int len;
 	unsigned int head, in_num, out_num;
-	struct iovec iov[dev->vq->vring.num];
-	struct console_abort *abort = dev->priv;
-
-	/* First we need a console buffer from the Guests's input virtqueue. */
-	head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
-
-	/* If they're not ready for input, stop listening to this file
-	 * descriptor.  We'll start again once they add an input buffer. */
-	if (head == dev->vq->vring.num)
-		return false;
+	struct console_abort *abort = vq->dev->priv;
+	struct iovec iov[vq->vring.num];
 
+	/* Make sure there's a descriptor waiting. */
+	head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
 	if (out_num)
 		errx(1, "Output buffers in console in queue?");
 
-	/* This is why we convert to iovecs: the readv() call uses them, and so
-	 * it reads straight into the Guest's buffer. */
-	len = readv(dev->fd, iov, in_num);
+	/* Read it in. */
+	len = readv(STDIN_FILENO, iov, in_num);
 	if (len <= 0) {
-		/* This implies that the console is closed, is /dev/null, or
-		 * something went terribly wrong. */
+		/* Ran out of input? */
 		warnx("Failed to get console input, ignoring console.");
-		/* Put the input terminal back. */
-		restore_term();
-		/* Remove callback from input vq, so it doesn't restart us. */
-		dev->vq->handle_output = NULL;
-		/* Stop listening to this fd: don't call us again. */
-		return false;
+		/* For simplicity, dying threads kill the whole Launcher.  So
+		 * just nap here. */
+		for (;;)
+			pause();
 	}
 
-	/* Tell the Guest about the new input. */
-	add_used_and_trigger(fd, dev->vq, head, len);
+	add_used_and_trigger(vq, head, len);
 
 	/* Three ^C within one second?  Exit.
 	 *
-	 * This is such a hack, but works surprisingly well.  Each ^C has to be
-	 * in a buffer by itself, so they can't be too fast.  But we check that
-	 * we get three within about a second, so they can't be too slow. */
-	if (len == 1 && ((char *)iov[0].iov_base)[0] == 3) {
-		if (!abort->count++)
-			gettimeofday(&abort->start, NULL);
-		else if (abort->count == 3) {
-			struct timeval now;
-			gettimeofday(&now, NULL);
-			if (now.tv_sec <= abort->start.tv_sec+1) {
-				unsigned long args[] = { LHREQ_BREAK, 0 };
-				/* Close the fd so Waker will know it has to
-				 * exit. */
-				close(waker_fds.pipe[1]);
-				/* Just in case Waker is blocked in BREAK, send
-				 * unbreak now. */
-				write(fd, args, sizeof(args));
-				exit(2);
-			}
-			abort->count = 0;
-		}
-	} else
-		/* Any other key resets the abort counter. */
+	 * This is such a hack, but works surprisingly well.  Each ^C has to
+	 * be in a buffer by itself, so they can't be too fast.  But we check
+	 * that we get three within about a second, so they can't be too
+	 * slow. */
+	if (len != 1 || ((char *)iov[0].iov_base)[0] != 3) {
 		abort->count = 0;
+		return;
+	}
 
-	/* Everything went OK! */
-	return true;
+	abort->count++;
+	if (abort->count == 1)
+		gettimeofday(&abort->start, NULL);
+	else if (abort->count == 3) {
+		struct timeval now;
+		gettimeofday(&now, NULL);
+		/* Kill all Launcher processes with SIGINT, like normal ^C */
+		if (now.tv_sec <= abort->start.tv_sec+1)
+			kill(0, SIGINT);
+		abort->count = 0;
+	}
 }
 
-/* Handling output for console is simple: we just get all the output buffers
- * and write them to stdout. */
-static void handle_console_output(int fd, struct virtqueue *vq, bool timeout)
+/* This is the routine which handles console output (ie. stdout). */
+static void console_output(struct virtqueue *vq)
 {
 	unsigned int head, out, in;
-	int len;
 	struct iovec iov[vq->vring.num];
 
-	/* Keep getting output buffers from the Guest until we run out. */
-	while ((head = get_vq_desc(vq, iov, &out, &in)) != vq->vring.num) {
-		if (in)
-			errx(1, "Input buffers in output queue?");
-		len = writev(STDOUT_FILENO, iov, out);
-		add_used_and_trigger(fd, vq, head, len);
+	head = wait_for_vq_desc(vq, iov, &out, &in);
+	if (in)
+		errx(1, "Input buffers in console output queue?");
+	while (!iov_empty(iov, out)) {
+		int len = writev(STDOUT_FILENO, iov, out);
+		if (len <= 0)
+			err(1, "Write to stdout gave %i", len);
+		iov_consume(iov, out, len);
 	}
-}
-
-/* This is called when we no longer want to hear about Guest changes to a
- * virtqueue.  This is more efficient in high-traffic cases, but it means we
- * have to set a timer to check if any more changes have occurred. */
-static void block_vq(struct virtqueue *vq)
-{
-	struct itimerval itm;
-
-	vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
-	vq->blocked = true;
-
-	itm.it_interval.tv_sec = 0;
-	itm.it_interval.tv_usec = 0;
-	itm.it_value.tv_sec = 0;
-	itm.it_value.tv_usec = timeout_usec;
-
-	setitimer(ITIMER_REAL, &itm, NULL);
+	add_used(vq, head, 0);
 }
 
 /*
  * The Network
  *
  * Handling output for network is also simple: we get all the output buffers
- * and write them (ignoring the first element) to this device's file descriptor
- * (/dev/net/tun).
+ * and write them to /dev/net/tun.
  */
-static void handle_net_output(int fd, struct virtqueue *vq, bool timeout)
+struct net_info {
+	int tunfd;
+};
+
+static void net_output(struct virtqueue *vq)
 {
-	unsigned int head, out, in, num = 0;
-	int len;
+	struct net_info *net_info = vq->dev->priv;
+	unsigned int head, out, in;
 	struct iovec iov[vq->vring.num];
-	static int last_timeout_num;
-
-	/* Keep getting output buffers from the Guest until we run out. */
-	while ((head = get_vq_desc(vq, iov, &out, &in)) != vq->vring.num) {
-		if (in)
-			errx(1, "Input buffers in output queue?");
-		len = writev(vq->dev->fd, iov, out);
-		if (len < 0)
-			err(1, "Writing network packet to tun");
-		add_used_and_trigger(fd, vq, head, len);
-		num++;
-	}
 
-	/* Block further kicks and set up a timer if we saw anything. */
-	if (!timeout && num)
-		block_vq(vq);
-
-	/* We never quite know how long should we wait before we check the
-	 * queue again for more packets.  We start at 500 microseconds, and if
-	 * we get fewer packets than last time, we assume we made the timeout
-	 * too small and increase it by 10 microseconds.  Otherwise, we drop it
-	 * by one microsecond every time.  It seems to work well enough. */
-	if (timeout) {
-		if (num < last_timeout_num)
-			timeout_usec += 10;
-		else if (timeout_usec > 1)
-			timeout_usec--;
-		last_timeout_num = num;
-	}
+	head = wait_for_vq_desc(vq, iov, &out, &in);
+	if (in)
+		errx(1, "Input buffers in net output queue?");
+	if (writev(net_info->tunfd, iov, out) < 0)
+		errx(1, "Write to tun failed?");
+	add_used(vq, head, 0);
+}
+
+/* Will reading from this file descriptor block? */
+static bool will_block(int fd)
+{
+	fd_set fdset;
+	struct timeval zero = { 0, 0 };
+	FD_ZERO(&fdset);
+	FD_SET(fd, &fdset);
+	return select(fd+1, &fdset, NULL, NULL, &zero) != 1;
 }
 
-/* This is where we handle a packet coming in from the tun device to our
+/* This is where we handle packets coming in from the tun device to our
  * Guest. */
-static bool handle_tun_input(int fd, struct device *dev)
+static void net_input(struct virtqueue *vq)
 {
-	unsigned int head, in_num, out_num;
 	int len;
-	struct iovec iov[dev->vq->vring.num];
-
-	/* First we need a network buffer from the Guests's recv virtqueue. */
-	head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
-	if (head == dev->vq->vring.num) {
-		/* Now, it's expected that if we try to send a packet too
-		 * early, the Guest won't be ready yet.  Wait until the device
-		 * status says it's ready. */
-		/* FIXME: Actually want DRIVER_ACTIVE here. */
-
-		/* Now tell it we want to know if new things appear. */
-		dev->vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY;
-		wmb();
-
-		/* We'll turn this back on if input buffers are registered. */
-		return false;
-	} else if (out_num)
-		errx(1, "Output buffers in network recv queue?");
-
-	/* Read the packet from the device directly into the Guest's buffer. */
-	len = readv(dev->fd, iov, in_num);
-	if (len <= 0)
-		err(1, "reading network");
+	unsigned int head, out, in;
+	struct iovec iov[vq->vring.num];
+	struct net_info *net_info = vq->dev->priv;
 
-	/* Tell the Guest about the new packet. */
-	add_used_and_trigger(fd, dev->vq, head, len);
+	head = wait_for_vq_desc(vq, iov, &out, &in);
+	if (out)
+		errx(1, "Output buffers in net input queue?");
 
-	verbose("tun input packet len %i [%02x %02x] (%s)\n", len,
-		((u8 *)iov[1].iov_base)[0], ((u8 *)iov[1].iov_base)[1],
-		head != dev->vq->vring.num ? "sent" : "discarded");
+	/* Deliver interrupt now, since we're about to sleep. */
+	if (vq->pending_used && will_block(net_info->tunfd))
+		trigger_irq(vq);
 
-	/* All good. */
-	return true;
+	len = readv(net_info->tunfd, iov, in);
+	if (len <= 0)
+		err(1, "Failed to read from tun.");
+	add_used(vq, head, len);
 }
 
-/*L:215 This is the callback attached to the network and console input
- * virtqueues: it ensures we try again, in case we stopped console or net
- * delivery because Guest didn't have any buffers. */
-static void enable_fd(int fd, struct virtqueue *vq, bool timeout)
+/* This is the helper to create threads. */
+static int do_thread(void *_vq)
 {
-	add_device_fd(vq->dev->fd);
-	/* Snap the Waker out of its select loop. */
-	write(waker_fds.pipe[1], "", 1);
+	struct virtqueue *vq = _vq;
+
+	for (;;)
+		vq->service(vq);
+	return 0;
 }
 
-static void net_enable_fd(int fd, struct virtqueue *vq, bool timeout)
+/* When a child dies, we kill our entire process group with SIGTERM.  This
+ * also has the side effect that the shell restores the console for us! */
+static void kill_launcher(int signal)
 {
-	/* We don't need to know again when Guest refills receive buffer. */
-	vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
-	enable_fd(fd, vq, timeout);
+	kill(0, SIGTERM);
 }
 
-/* When the Guest tells us they updated the status field, we handle it. */
-static void update_device_status(struct device *dev)
+static void reset_device(struct device *dev)
 {
 	struct virtqueue *vq;
 
-	/* This is a reset. */
-	if (dev->desc->status == 0) {
-		verbose("Resetting device %s\n", dev->name);
+	verbose("Resetting device %s\n", dev->name);
 
-		/* Clear any features they've acked. */
-		memset(get_feature_bits(dev) + dev->desc->feature_len, 0,
-		       dev->desc->feature_len);
+	/* Clear any features they've acked. */
+	memset(get_feature_bits(dev) + dev->feature_len, 0, dev->feature_len);
 
-		/* Zero out the virtqueues. */
-		for (vq = dev->vq; vq; vq = vq->next) {
-			memset(vq->vring.desc, 0,
-			       vring_size(vq->config.num, LGUEST_VRING_ALIGN));
-			lg_last_avail(vq) = 0;
+	/* We're going to be explicitly killing threads, so ignore them. */
+	signal(SIGCHLD, SIG_IGN);
+
+	/* Zero out the virtqueues, get rid of their threads */
+	for (vq = dev->vq; vq; vq = vq->next) {
+		if (vq->thread != (pid_t)-1) {
+			kill(vq->thread, SIGTERM);
+			waitpid(vq->thread, NULL, 0);
+			vq->thread = (pid_t)-1;
 		}
-	} else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) {
+		memset(vq->vring.desc, 0,
+		       vring_size(vq->config.num, LGUEST_VRING_ALIGN));
+		lg_last_avail(vq) = 0;
+	}
+	dev->running = false;
+
+	/* Now we care if threads die. */
+	signal(SIGCHLD, (void *)kill_launcher);
+}
+
+static void create_thread(struct virtqueue *vq)
+{
+	/* Create stack for thread and run it.  Since stack grows
+	 * upwards, we point the stack pointer to the end of this
+	 * region. */
+	char *stack = malloc(32768);
+	unsigned long args[] = { LHREQ_EVENTFD,
+				 vq->config.pfn*getpagesize(), 0 };
+
+	/* Create a zero-initialized eventfd. */
+	vq->eventfd = eventfd(0, 0);
+	if (vq->eventfd < 0)
+		err(1, "Creating eventfd");
+	args[2] = vq->eventfd;
+
+	/* Attach an eventfd to this virtqueue: it will go off
+	 * when the Guest does an LHCALL_NOTIFY for this vq. */
+	if (write(lguest_fd, &args, sizeof(args)) != 0)
+		err(1, "Attaching eventfd");
+
+	/* CLONE_VM: because it has to access the Guest memory, and
+	 * SIGCHLD so we get a signal if it dies. */
+	vq->thread = clone(do_thread, stack + 32768, CLONE_VM | SIGCHLD, vq);
+	if (vq->thread == (pid_t)-1)
+		err(1, "Creating clone");
+	/* We close our local copy, now the child has it. */
+	close(vq->eventfd);
+}
+
+static void start_device(struct device *dev)
+{
+	unsigned int i;
+	struct virtqueue *vq;
+
+	verbose("Device %s OK: offered", dev->name);
+	for (i = 0; i < dev->feature_len; i++)
+		verbose(" %02x", get_feature_bits(dev)[i]);
+	verbose(", accepted");
+	for (i = 0; i < dev->feature_len; i++)
+		verbose(" %02x", get_feature_bits(dev)
+			[dev->feature_len+i]);
+
+	for (vq = dev->vq; vq; vq = vq->next) {
+		if (vq->service)
+			create_thread(vq);
+	}
+	dev->running = true;
+}
+
+static void cleanup_devices(void)
+{
+	struct device *dev;
+
+	for (dev = devices.dev; dev; dev = dev->next)
+		reset_device(dev);
+
+	/* If we saved off the original terminal settings, restore them now. */
+	if (orig_term.c_lflag & (ISIG|ICANON|ECHO))
+		tcsetattr(STDIN_FILENO, TCSANOW, &orig_term);
+}
+
+/* When the Guest tells us they updated the status field, we handle it. */
+static void update_device_status(struct device *dev)
+{
+	/* A zero status is a reset, otherwise it's a set of flags. */
+	if (dev->desc->status == 0)
+		reset_device(dev);
+	else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) {
 		warnx("Device %s configuration FAILED", dev->name);
+		if (dev->running)
+			reset_device(dev);
 	} else if (dev->desc->status & VIRTIO_CONFIG_S_DRIVER_OK) {
-		unsigned int i;
-
-		verbose("Device %s OK: offered", dev->name);
-		for (i = 0; i < dev->desc->feature_len; i++)
-			verbose(" %02x", get_feature_bits(dev)[i]);
-		verbose(", accepted");
-		for (i = 0; i < dev->desc->feature_len; i++)
-			verbose(" %02x", get_feature_bits(dev)
-				[dev->desc->feature_len+i]);
-
-		if (dev->ready)
-			dev->ready(dev);
+		if (!dev->running)
+			start_device(dev);
 	}
 }
 
 /* This is the generic routine we call when the Guest uses LHCALL_NOTIFY. */
-static void handle_output(int fd, unsigned long addr)
+static void handle_output(unsigned long addr)
 {
 	struct device *i;
-	struct virtqueue *vq;
 
-	/* Check each device and virtqueue. */
+	/* Check each device. */
 	for (i = devices.dev; i; i = i->next) {
+		struct virtqueue *vq;
+
 		/* Notifications to device descriptors update device status. */
 		if (from_guest_phys(addr) == i->desc) {
 			update_device_status(i);
 			return;
 		}
 
-		/* Notifications to virtqueues mean output has occurred. */
+		/* Devices *can* be used before status is set to DRIVER_OK. */
 		for (vq = i->vq; vq; vq = vq->next) {
-			if (vq->config.pfn != addr/getpagesize())
+			if (addr != vq->config.pfn*getpagesize())
 				continue;
-
-			/* Guest should acknowledge (and set features!)  before
-			 * using the device. */
-			if (i->desc->status == 0) {
-				warnx("%s gave early output", i->name);
-				return;
-			}
-
-			if (strcmp(vq->dev->name, "console") != 0)
-				verbose("Output to %s\n", vq->dev->name);
-			if (vq->handle_output)
-				vq->handle_output(fd, vq, false);
+			if (i->running)
+				errx(1, "Notification on running %s", i->name);
+			start_device(i);
 			return;
 		}
 	}
@@ -1049,71 +990,6 @@ static void handle_output(int fd, unsigned long addr)
 	      strnlen(from_guest_phys(addr), guest_limit - addr));
 }
 
-static void handle_timeout(int fd)
-{
-	char buf[32];
-	struct device *i;
-	struct virtqueue *vq;
-
-	/* Clear the pipe */
-	read(timeoutpipe[0], buf, sizeof(buf));
-
-	/* Check each device and virtqueue: flush blocked ones. */
-	for (i = devices.dev; i; i = i->next) {
-		for (vq = i->vq; vq; vq = vq->next) {
-			if (!vq->blocked)
-				continue;
-
-			vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY;
-			vq->blocked = false;
-			if (vq->handle_output)
-				vq->handle_output(fd, vq, true);
-		}
-	}
-}
-
-/* This is called when the Waker wakes us up: check for incoming file
- * descriptors. */
-static void handle_input(int fd)
-{
-	/* select() wants a zeroed timeval to mean "don't wait". */
-	struct timeval poll = { .tv_sec = 0, .tv_usec = 0 };
-
-	for (;;) {
-		struct device *i;
-		fd_set fds = devices.infds;
-		int num;
-
-		num = select(devices.max_infd+1, &fds, NULL, NULL, &poll);
-		/* Could get interrupted */
-		if (num < 0)
-			continue;
-		/* If nothing is ready, we're done. */
-		if (num == 0)
-			break;
-
-		/* Otherwise, call the device(s) which have readable file
-		 * descriptors and a method of handling them.  */
-		for (i = devices.dev; i; i = i->next) {
-			if (i->handle_input && FD_ISSET(i->fd, &fds)) {
-				if (i->handle_input(fd, i))
-					continue;
-
-				/* If handle_input() returns false, it means we
-				 * should no longer service it.  Networking and
-				 * console do this when there's no input
-				 * buffers to deliver into.  Console also uses
-				 * it when it discovers that stdin is closed. */
-				FD_CLR(i->fd, &devices.infds);
-			}
-		}
-
-		/* Is this the timeout fd? */
-		if (FD_ISSET(timeoutpipe[0], &fds))
-			handle_timeout(fd);
-	}
-}
-
 /*L:190
  * Device Setup
  *
@@ -1129,8 +1005,8 @@ static void handle_input(int fd)
 static u8 *device_config(const struct device *dev)
 {
 	return (void *)(dev->desc + 1)
-		+ dev->desc->num_vq * sizeof(struct lguest_vqconfig)
-		+ dev->desc->feature_len * 2;
+		+ dev->num_vq * sizeof(struct lguest_vqconfig)
+		+ dev->feature_len * 2;
 }
 
 /* This routine allocates a new "struct lguest_device_desc" from descriptor
@@ -1159,7 +1035,7 @@ static struct lguest_device_desc *new_dev_desc(u16 type)
 /* Each device descriptor is followed by the description of its virtqueues.  We
  * specify how many descriptors the virtqueue is to have. */
 static void add_virtqueue(struct device *dev, unsigned int num_descs,
-			  void (*handle_output)(int, struct virtqueue *, bool))
+			  void (*service)(struct virtqueue *))
 {
 	unsigned int pages;
 	struct virtqueue **i, *vq = malloc(sizeof(*vq));
@@ -1174,8 +1050,8 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
 	vq->next = NULL;
 	vq->last_avail_idx = 0;
 	vq->dev = dev;
-	vq->inflight = 0;
-	vq->blocked = false;
+	vq->service = service;
+	vq->thread = (pid_t)-1;
 
 	/* Initialize the configuration. */
 	vq->config.num = num_descs;
@@ -1191,6 +1067,7 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
 	 * yet, otherwise we'd be overwriting them. */
 	assert(dev->desc->config_len == 0 && dev->desc->feature_len == 0);
 	memcpy(device_config(dev), &vq->config, sizeof(vq->config));
+	dev->num_vq++;
 	dev->desc->num_vq++;
 
 	verbose("Virtqueue page %#lx\n", to_guest_phys(p));
@@ -1199,15 +1076,6 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
 	 * second.  */
 	for (i = &dev->vq; *i; i = &(*i)->next);
 	*i = vq;
-
-	/* Set the routine to call when the Guest does something to this
-	 * virtqueue. */
-	vq->handle_output = handle_output;
-
-	/* As an optimization, set the advisory "Don't Notify Me" flag if we
-	 * don't have a handler */
-	if (!handle_output)
-		vq->vring.used->flags = VRING_USED_F_NO_NOTIFY;
 }
 
 /* The first half of the feature bitmask is for us to advertise features.  The
@@ -1219,7 +1087,7 @@ static void add_feature(struct device *dev, unsigned bit)
 	/* We can't extend the feature bits once we've added config bytes */
 	if (dev->desc->feature_len <= bit / CHAR_BIT) {
 		assert(dev->desc->config_len == 0);
-		dev->desc->feature_len = (bit / CHAR_BIT) + 1;
+		dev->feature_len = dev->desc->feature_len = (bit/CHAR_BIT) + 1;
 	}
 
 	features[bit / CHAR_BIT] |= (1 << (bit % CHAR_BIT));
@@ -1243,22 +1111,17 @@ static void set_config(struct device *dev, unsigned len, const void *conf)
  * calling new_dev_desc() to allocate the descriptor and device memory.
  *
  * See what I mean about userspace being boring? */
-static struct device *new_device(const char *name, u16 type, int fd,
-				 bool (*handle_input)(int, struct device *))
+static struct device *new_device(const char *name, u16 type)
 {
 	struct device *dev = malloc(sizeof(*dev));
 
 	/* Now we populate the fields one at a time. */
-	dev->fd = fd;
-	/* If we have an input handler for this file descriptor, then we add it
-	 * to the device_list's fdset and maxfd. */
-	if (handle_input)
-		add_device_fd(dev->fd);
 	dev->desc = new_dev_desc(type);
-	dev->handle_input = handle_input;
 	dev->name = name;
 	dev->vq = NULL;
-	dev->ready = NULL;
+	dev->feature_len = 0;
+	dev->num_vq = 0;
+	dev->running = false;
 
 	/* Append to device list.  Prepending to a single-linked list is
 	 * easier, but the user expects the devices to be arranged on the bus
@@ -1286,13 +1149,10 @@ static void setup_console(void)
 		 * raw input stream to the Guest. */
 		term.c_lflag &= ~(ISIG|ICANON|ECHO);
 		tcsetattr(STDIN_FILENO, TCSANOW, &term);
-		/* If we exit gracefully, the original settings will be
-		 * restored so the user can see what they're typing. */
-		atexit(restore_term);
 	}
 
-	dev = new_device("console", VIRTIO_ID_CONSOLE,
-			 STDIN_FILENO, handle_console_input);
+	dev = new_device("console", VIRTIO_ID_CONSOLE);
+
 	/* We store the console state in dev->priv, and initialize it. */
 	dev->priv = malloc(sizeof(struct console_abort));
 	((struct console_abort *)dev->priv)->count = 0;
@@ -1301,31 +1161,13 @@ static void setup_console(void)
 	 * they put something the input queue, we make sure we're listening to
 	 * stdin.  When they put something in the output queue, we write it to
 	 * stdout. */
-	add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd);
-	add_virtqueue(dev, VIRTQUEUE_NUM, handle_console_output);
+	add_virtqueue(dev, VIRTQUEUE_NUM, console_input);
+	add_virtqueue(dev, VIRTQUEUE_NUM, console_output);
 
-	verbose("device %u: console\n", devices.device_num++);
+	verbose("device %u: console\n", ++devices.device_num);
 }
 /*:*/
 
-static void timeout_alarm(int sig)
-{
-	write(timeoutpipe[1], "", 1);
-}
-
-static void setup_timeout(void)
-{
-	if (pipe(timeoutpipe) != 0)
-		err(1, "Creating timeout pipe");
-
-	if (fcntl(timeoutpipe[1], F_SETFL,
-		  fcntl(timeoutpipe[1], F_GETFL) | O_NONBLOCK) != 0)
-		err(1, "Making timeout pipe nonblocking");
-
-	add_device_fd(timeoutpipe[0]);
-	signal(SIGALRM, timeout_alarm);
-}
-
 /*M:010 Inter-guest networking is an interesting area.  Simplest is to have a
  * --sharenet=<name> option which opens or creates a named pipe.  This can be
  * used to send packets to another guest in a 1:1 manner.
@@ -1447,21 +1289,23 @@ static int get_tun_device(char tapif[IFNAMSIZ])
 static void setup_tun_net(char *arg)
 {
 	struct device *dev;
-	int netfd, ipfd;
+	struct net_info *net_info = malloc(sizeof(*net_info));
+	int ipfd;
 	u32 ip = INADDR_ANY;
 	bool bridging = false;
 	char tapif[IFNAMSIZ], *p;
 	struct virtio_net_config conf;
 
-	netfd = get_tun_device(tapif);
+	net_info->tunfd = get_tun_device(tapif);
 
 	/* First we create a new network device. */
-	dev = new_device("net", VIRTIO_ID_NET, netfd, handle_tun_input);
+	dev = new_device("net", VIRTIO_ID_NET);
+	dev->priv = net_info;
 
 	/* Network devices need a receive and a send queue, just like
 	 * console. */
-	add_virtqueue(dev, VIRTQUEUE_NUM, net_enable_fd);
-	add_virtqueue(dev, VIRTQUEUE_NUM, handle_net_output);
+	add_virtqueue(dev, VIRTQUEUE_NUM, net_input);
+	add_virtqueue(dev, VIRTQUEUE_NUM, net_output);
 
 	/* We need a socket to perform the magic network ioctls to bring up the
 	 * tap interface, connect to the bridge etc.  Any socket will do! */
@@ -1502,6 +1346,8 @@ static void setup_tun_net(char *arg)
 	add_feature(dev, VIRTIO_NET_F_HOST_TSO4);
 	add_feature(dev, VIRTIO_NET_F_HOST_TSO6);
 	add_feature(dev, VIRTIO_NET_F_HOST_ECN);
+	/* We handle indirect ring entries */
+	add_feature(dev, VIRTIO_RING_F_INDIRECT_DESC);
 	set_config(dev, sizeof(conf), &conf);
 
 	/* We don't need the socket any more; setup is done. */
@@ -1550,20 +1396,18 @@ struct vblk_info
  * Remember that the block device is handled by a separate I/O thread.  We head
  * straight into the core of that thread here:
  */
-static bool service_io(struct device *dev)
+static void blk_request(struct virtqueue *vq)
 {
-	struct vblk_info *vblk = dev->priv;
+	struct vblk_info *vblk = vq->dev->priv;
 	unsigned int head, out_num, in_num, wlen;
 	int ret;
 	u8 *in;
 	struct virtio_blk_outhdr *out;
-	struct iovec iov[dev->vq->vring.num];
+	struct iovec iov[vq->vring.num];
 	off64_t off;
 
-	/* See if there's a request waiting.  If not, nothing to do. */
-	head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
-	if (head == dev->vq->vring.num)
-		return false;
+	/* Get the next request. */
+	head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
 
 	/* Every block request should contain at least one output buffer
 	 * (detailing the location on disk and the type of request) and one
@@ -1637,83 +1481,21 @@ static bool service_io(struct device *dev)
 	if (out->type & VIRTIO_BLK_T_BARRIER)
 		fdatasync(vblk->fd);
 
-	/* We can't trigger an IRQ, because we're not the Launcher.  It does
-	 * that when we tell it we're done. */
-	add_used(dev->vq, head, wlen);
-	return true;
-}
-
-/* This is the thread which actually services the I/O. */
-static int io_thread(void *_dev)
-{
-	struct device *dev = _dev;
-	struct vblk_info *vblk = dev->priv;
-	char c;
-
-	/* Close other side of workpipe so we get 0 read when main dies. */
-	close(vblk->workpipe[1]);
-	/* Close the other side of the done_fd pipe. */
-	close(dev->fd);
-
-	/* When this read fails, it means Launcher died, so we follow. */
-	while (read(vblk->workpipe[0], &c, 1) == 1) {
-		/* We acknowledge each request immediately to reduce latency,
-		 * rather than waiting until we've done them all.  I haven't
-		 * measured to see if it makes any difference.
-		 *
-		 * That would be an interesting test, wouldn't it?  You could
-		 * also try having more than one I/O thread. */
-		while (service_io(dev))
-			write(vblk->done_fd, &c, 1);
-	}
-	return 0;
-}
-
-/* Now we've seen the I/O thread, we return to the Launcher to see what happens
- * when that thread tells us it's completed some I/O. */
-static bool handle_io_finish(int fd, struct device *dev)
-{
-	char c;
-
-	/* If the I/O thread died, presumably it printed the error, so we
-	 * simply exit. */
-	if (read(dev->fd, &c, 1) != 1)
-		exit(1);
-
-	/* It did some work, so trigger the irq. */
-	trigger_irq(fd, dev->vq);
-	return true;
-}
-
-/* When the Guest submits some I/O, we just need to wake the I/O thread. */
-static void handle_virtblk_output(int fd, struct virtqueue *vq, bool timeout)
-{
-	struct vblk_info *vblk = vq->dev->priv;
-	char c = 0;
-
-	/* Wake up I/O thread and tell it to go to work! */
-	if (write(vblk->workpipe[1], &c, 1) != 1)
-		/* Presumably it indicated why it died. */
-		exit(1);
+	add_used(vq, head, wlen);
 }
 
 /*L:198 This actually sets up a virtual block device. */
 static void setup_block_file(const char *filename)
 {
-	int p[2];
 	struct device *dev;
 	struct vblk_info *vblk;
-	void *stack;
 	struct virtio_blk_config conf;
 
-	/* This is the pipe the I/O thread will use to tell us I/O is done. */
-	pipe(p);
-
 	/* The device responds to return from I/O thread. */
-	dev = new_device("block", VIRTIO_ID_BLOCK, p[0], handle_io_finish);
+	dev = new_device("block", VIRTIO_ID_BLOCK);
 
 	/* The device has one virtqueue, where the Guest places requests. */
-	add_virtqueue(dev, VIRTQUEUE_NUM, handle_virtblk_output);
+	add_virtqueue(dev, VIRTQUEUE_NUM, blk_request);
 
 	/* Allocate the room for our own bookkeeping */
 	vblk = dev->priv = malloc(sizeof(*vblk));
@@ -1735,49 +1517,29 @@ static void setup_block_file(const char *filename)
 
 	set_config(dev, sizeof(conf), &conf);
 
-	/* The I/O thread writes to this end of the pipe when done. */
-	vblk->done_fd = p[1];
-
-	/* This is the second pipe, which is how we tell the I/O thread about
-	 * more work. */
-	pipe(vblk->workpipe);
-
-	/* Create stack for thread and run it.  Since stack grows upwards, we
-	 * point the stack pointer to the end of this region. */
-	stack = malloc(32768);
-	/* SIGCHLD - We dont "wait" for our cloned thread, so prevent it from
-	 * becoming a zombie. */
-	if (clone(io_thread, stack + 32768, CLONE_VM | SIGCHLD, dev) == -1)
-		err(1, "Creating clone");
-
-	/* We don't need to keep the I/O thread's end of the pipes open. */
-	close(vblk->done_fd);
-	close(vblk->workpipe[0]);
-
 	verbose("device %u: virtblock %llu sectors\n",
-		devices.device_num, le64_to_cpu(conf.capacity));
+		++devices.device_num, le64_to_cpu(conf.capacity));
 }
 
+struct rng_info {
+	int rfd;
+};
+
 /* Our random number generator device reads from /dev/random into the Guest's
  * input buffers.  The usual case is that the Guest doesn't want random numbers
  * and so has no buffers although /dev/random is still readable, whereas
  * console is the reverse.
  *
  * The same logic applies, however. */
-static bool handle_rng_input(int fd, struct device *dev)
+static void rng_input(struct virtqueue *vq)
 {
 	int len;
 	unsigned int head, in_num, out_num, totlen = 0;
-	struct iovec iov[dev->vq->vring.num];
+	struct rng_info *rng_info = vq->dev->priv;
+	struct iovec iov[vq->vring.num];
 
 	/* First we need a buffer from the Guests's virtqueue. */
-	head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
-
-	/* If they're not ready for input, stop listening to this file
-	 * descriptor.  We'll start again once they add an input buffer. */
-	if (head == dev->vq->vring.num)
-		return false;
-
+	head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
 	if (out_num)
 		errx(1, "Output buffers in rng?");
 
@@ -1785,7 +1547,7 @@ static bool handle_rng_input(int fd, struct device *dev)
 	 * it reads straight into the Guest's buffer.  We loop to make sure we
 	 * fill it. */
 	while (!iov_empty(iov, in_num)) {
-		len = readv(dev->fd, iov, in_num);
+		len = readv(rng_info->rfd, iov, in_num);
 		if (len <= 0)
 			err(1, "Read from /dev/random gave %i", len);
 		iov_consume(iov, in_num, len);
@@ -1793,25 +1555,23 @@ static bool handle_rng_input(int fd, struct device *dev)
 	}
 
 	/* Tell the Guest about the new input. */
-	add_used_and_trigger(fd, dev->vq, head, totlen);
-
-	/* Everything went OK! */
-	return true;
+	add_used(vq, head, totlen);
 }
 
 /* And this creates a "hardware" random number device for the Guest. */
 static void setup_rng(void)
 {
 	struct device *dev;
-	int fd;
+	struct rng_info *rng_info = malloc(sizeof(*rng_info));
 
-	fd = open_or_die("/dev/random", O_RDONLY);
+	rng_info->rfd = open_or_die("/dev/random", O_RDONLY);
 
 	/* The device responds to return from I/O thread. */
-	dev = new_device("rng", VIRTIO_ID_RNG, fd, handle_rng_input);
+	dev = new_device("rng", VIRTIO_ID_RNG);
+	dev->priv = rng_info;
 
 	/* The device has one virtqueue, where the Guest places inbufs. */
-	add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd);
+	add_virtqueue(dev, VIRTQUEUE_NUM, rng_input);
 
 	verbose("device %u: rng\n", devices.device_num++);
 }
@@ -1827,17 +1587,18 @@ static void __attribute__((noreturn)) restart_guest(void)
 	for (i = 3; i < FD_SETSIZE; i++)
 		close(i);
 
-	/* The exec automatically gets rid of the I/O and Waker threads. */
+	/* Reset all the devices (kills all threads). */
+	cleanup_devices();
+
 	execv(main_args[0], main_args);
 	err(1, "Could not exec %s", main_args[0]);
 }
 
 /*L:220 Finally we reach the core of the Launcher which runs the Guest, serves
  * its input and output, and finally, lays it to rest. */
-static void __attribute__((noreturn)) run_guest(int lguest_fd)
+static void __attribute__((noreturn)) run_guest(void)
 {
 	for (;;) {
-		unsigned long args[] = { LHREQ_BREAK, 0 };
 		unsigned long notify_addr;
 		int readval;
 
@@ -1848,8 +1609,7 @@ static void __attribute__((noreturn)) run_guest(int lguest_fd)
 		/* One unsigned long means the Guest did HCALL_NOTIFY */
 		if (readval == sizeof(notify_addr)) {
 			verbose("Notify on address %#lx\n", notify_addr);
-			handle_output(lguest_fd, notify_addr);
-			continue;
+			handle_output(notify_addr);
 		/* ENOENT means the Guest died.  Reading tells us why. */
 		} else if (errno == ENOENT) {
 			char reason[1024] = { 0 };
@@ -1858,19 +1618,9 @@ static void __attribute__((noreturn)) run_guest(int lguest_fd)
 		/* ERESTART means that we need to reboot the guest */
 		} else if (errno == ERESTART) {
 			restart_guest();
-		/* EAGAIN means a signal (timeout).
-		 * Anything else means a bug or incompatible change. */
-		} else if (errno != EAGAIN)
+		/* Anything else means a bug or incompatible change. */
+		} else
 			err(1, "Running guest failed");
-
-		/* Only service input on thread for CPU 0. */
-		if (cpu_id != 0)
-			continue;
-
-		/* Service input, then unset the BREAK to release the Waker. */
-		handle_input(lguest_fd);
-		if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0)
-			err(1, "Resetting break");
 	}
 }
 /*L:240
@@ -1904,8 +1654,8 @@ int main(int argc, char *argv[])
 	/* Memory, top-level pagetable, code startpoint and size of the
 	 * (optional) initrd. */
 	unsigned long mem = 0, start, initrd_size = 0;
-	/* Two temporaries and the /dev/lguest file descriptor. */
-	int i, c, lguest_fd;
+	/* Two temporaries. */
+	int i, c;
 	/* The boot information for the Guest. */
 	struct boot_params *boot;
 	/* If they specify an initrd file to load. */
@@ -1913,18 +1663,10 @@ int main(int argc, char *argv[])
 
 	/* Save the args: we "reboot" by execing ourselves again. */
 	main_args = argv;
-	/* We don't "wait" for the children, so prevent them from becoming
-	 * zombies. */
-	signal(SIGCHLD, SIG_IGN);
 
-	/* First we initialize the device list.  Since console and network
-	 * device receive input from a file descriptor, we keep an fdset
-	 * (infds) and the maximum fd number (max_infd) with the head of the
-	 * list.  We also keep a pointer to the last device.  Finally, we keep
-	 * the next interrupt number to use for devices (1: remember that 0 is
-	 * used by the timer). */
-	FD_ZERO(&devices.infds);
-	devices.max_infd = -1;
+	/* First we initialize the device list.  We keep a pointer to the last
+	 * device, and the next interrupt number to use for devices (1:
+	 * remember that 0 is used by the timer). */
 	devices.lastdev = NULL;
 	devices.next_irq = 1;
 
@@ -1982,9 +1724,6 @@ int main(int argc, char *argv[])
 	/* We always have a console device */
 	setup_console();
 
-	/* We can timeout waiting for Guest network transmit. */
-	setup_timeout();
-
 	/* Now we load the kernel */
 	start = load_kernel(open_or_die(argv[optind+1], O_RDONLY));
 
@@ -2023,15 +1762,16 @@ int main(int argc, char *argv[])
 
 	/* We tell the kernel to initialize the Guest: this returns the open
 	 * /dev/lguest file descriptor. */
-	lguest_fd = tell_kernel(start);
+	tell_kernel(start);
+
+	/* Ensure that we terminate if a child dies. */
+	signal(SIGCHLD, kill_launcher);
 
-	/* We clone off a thread, which wakes the Launcher whenever one of the
-	 * input file descriptors needs attention.  We call this the Waker, and
-	 * we'll cover it in a moment. */
-	setup_waker(lguest_fd);
+	/* If we exit via err(), this kills all the threads, restores tty. */
+	atexit(cleanup_devices);
 
 	/* Finally, run the Guest.  This doesn't return. */
-	run_guest(lguest_fd);
+	run_guest();
 }
 /*:*/
 
diff --git a/Documentation/lguest/lguest.txt b/Documentation/lguest/lguest.txt
index 28c747362f9..efb3a6a045a 100644
--- a/Documentation/lguest/lguest.txt
+++ b/Documentation/lguest/lguest.txt
@@ -37,7 +37,6 @@ Running Lguest:
      "Paravirtualized guest support" = Y
         "Lguest guest support" = Y
      "High Memory Support" = off/4GB
-     "PAE (Physical Address Extension) Support" = N
      "Alignment value to which kernel should be aligned" = 0x100000
         (CONFIG_PARAVIRT=y, CONFIG_LGUEST_GUEST=y, CONFIG_HIGHMEM64G=n and
          CONFIG_PHYSICAL_ALIGN=0x100000)
diff --git a/Documentation/local_ops.txt b/Documentation/local_ops.txt
index 23045b8b50f..300da4bdfdb 100644
--- a/Documentation/local_ops.txt
+++ b/Documentation/local_ops.txt
@@ -34,7 +34,7 @@ out of order wrt other memory writes by the owner CPU.
 
 It can be done by slightly modifying the standard atomic operations : only
 their UP variant must be kept. It typically means removing LOCK prefix (on
-i386 and x86_64) and any SMP sychronization barrier. If the architecture does
+i386 and x86_64) and any SMP synchronization barrier. If the architecture does
 not have a different behavior between SMP and UP, including asm-generic/local.h
 in your architecture's local.h is sufficient.
 
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index f5b7127f54a..7f5809eddee 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -31,6 +31,7 @@ Contents:
 
      - Locking functions.
      - Interrupt disabling functions.
+     - Sleep and wake-up functions.
      - Miscellaneous functions.
 
  (*) Inter-CPU locking barrier effects.
@@ -1217,6 +1218,132 @@ barriers are required in such a situation, they must be provided from some
 other means.
 
 
+SLEEP AND WAKE-UP FUNCTIONS
+---------------------------
+
+Sleeping and waking on an event flagged in global data can be viewed as an
+interaction between two pieces of data: the task state of the task waiting for
+the event and the global data used to indicate the event.  To make sure that
+these appear to happen in the right order, the primitives to begin the process
+of going to sleep, and the primitives to initiate a wake up imply certain
+barriers.
+
+Firstly, the sleeper normally follows something like this sequence of events:
+
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (event_indicated)
+			break;
+		schedule();
+	}
+
+A general memory barrier is interpolated automatically by set_current_state()
+after it has altered the task state:
+
+	CPU 1
+	===============================
+	set_current_state();
+	  set_mb();
+	    STORE current->state
+	    <general barrier>
+	LOAD event_indicated
+
+set_current_state() may be wrapped by:
+
+	prepare_to_wait();
+	prepare_to_wait_exclusive();
+
+which therefore also imply a general memory barrier after setting the state.
+The whole sequence above is available in various canned forms, all of which
+interpolate the memory barrier in the right place:
+
+	wait_event();
+	wait_event_interruptible();
+	wait_event_interruptible_exclusive();
+	wait_event_interruptible_timeout();
+	wait_event_killable();
+	wait_event_timeout();
+	wait_on_bit();
+	wait_on_bit_lock();
+
+
+Secondly, code that performs a wake up normally follows something like this:
+
+	event_indicated = 1;
+	wake_up(&event_wait_queue);
+
+or:
+
+	event_indicated = 1;
+	wake_up_process(event_daemon);
+
+A write memory barrier is implied by wake_up() and co. if and only if they wake
+something up.  The barrier occurs before the task state is cleared, and so sits
+between the STORE to indicate the event and the STORE to set TASK_RUNNING:
+
+	CPU 1				CPU 2
+	===============================	===============================
+	set_current_state();		STORE event_indicated
+	  set_mb();			wake_up();
+	    STORE current->state	  <write barrier>
+	    <general barrier>		  STORE current->state
+	LOAD event_indicated
+
+The available waker functions include:
+
+	complete();
+	wake_up();
+	wake_up_all();
+	wake_up_bit();
+	wake_up_interruptible();
+	wake_up_interruptible_all();
+	wake_up_interruptible_nr();
+	wake_up_interruptible_poll();
+	wake_up_interruptible_sync();
+	wake_up_interruptible_sync_poll();
+	wake_up_locked();
+	wake_up_locked_poll();
+	wake_up_nr();
+	wake_up_poll();
+	wake_up_process();
+
+
+[!] Note that the memory barriers implied by the sleeper and the waker do _not_
+order multiple stores before the wake-up with respect to loads of those stored
+values after the sleeper has called set_current_state().  For instance, if the
+sleeper does:
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	if (event_indicated)
+		break;
+	__set_current_state(TASK_RUNNING);
+	do_something(my_data);
+
+and the waker does:
+
+	my_data = value;
+	event_indicated = 1;
+	wake_up(&event_wait_queue);
+
+there's no guarantee that the change to event_indicated will be perceived by
+the sleeper as coming after the change to my_data.  In such a circumstance, the
+code on both sides must interpolate its own memory barriers between the
+separate data accesses.  Thus the above sleeper ought to do:
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	if (event_indicated) {
+		smp_rmb();
+		do_something(my_data);
+	}
+
+and the waker should do:
+
+	my_data = value;
+	smp_wmb();
+	event_indicated = 1;
+	wake_up(&event_wait_queue);
+
+
 MISCELLANEOUS FUNCTIONS
 -----------------------
 
@@ -1366,7 +1493,7 @@ WHERE ARE MEMORY BARRIERS NEEDED?
 
 Under normal operation, memory operation reordering is generally not going to
 be a problem as a single-threaded linear piece of code will still appear to
-work correctly, even if it's in an SMP kernel.  There are, however, three
+work correctly, even if it's in an SMP kernel.  There are, however, four
 circumstances in which reordering definitely _could_ be a problem:
 
  (*) Interprocessor interaction.
diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt
index 4c2ecf537a4..bbc8a6a3692 100644
--- a/Documentation/memory-hotplug.txt
+++ b/Documentation/memory-hotplug.txt
@@ -73,13 +73,13 @@ this phase is triggered automatically. ACPI can notify this event. If not,
 (see Section 4.).
 
 Logical Memory Hotplug phase is to change memory state into
-avaiable/unavailable for users. Amount of memory from user's view is
+available/unavailable for users. Amount of memory from user's view is
 changed by this phase. The kernel makes all memory in it as free pages
 when a memory range is available.
 
 In this document, this phase is described as online/offline.
 
-Logical Memory Hotplug phase is triggred by write of sysfs file by system
+Logical Memory Hotplug phase is triggered by write of sysfs file by system
 administrator. For the hot-add case, it must be executed after Physical Hotplug
 phase by hand.
 (However, if you writes udev's hotplug scripts for memory hotplug, these
@@ -334,7 +334,7 @@ MEMORY_CANCEL_ONLINE
   Generated if MEMORY_GOING_ONLINE fails.
 
 MEMORY_ONLINE
-  Generated when memory has succesfully brought online. The callback may
+  Generated when memory has successfully brought online. The callback may
   allocate pages from the new memory.
 
 MEMORY_GOING_OFFLINE
@@ -359,7 +359,7 @@ The third argument is passed by pointer of struct memory_notify.
 struct memory_notify {
        unsigned long start_pfn;
        unsigned long nr_pages;
-       int status_cahnge_nid;
+       int status_change_nid;
 }
 
 start_pfn is start_pfn of online/offline memory.
diff --git a/Documentation/mn10300/ABI.txt b/Documentation/mn10300/ABI.txt
index 1fef1f06dfd..d3507bad428 100644
--- a/Documentation/mn10300/ABI.txt
+++ b/Documentation/mn10300/ABI.txt
@@ -26,7 +26,7 @@ registers and the stack. If the first argument is a 64-bit value, it will be
 passed in D0:D1. If the first argument is not a 64-bit value, but the second
 is, the second will be passed entirely on the stack and D1 will be unused.
 
-Arguments smaller than 32-bits are not coelesced within a register or a stack
+Arguments smaller than 32-bits are not coalesced within a register or a stack
 word. For example, two byte-sized arguments will always be passed in separate
 registers or word-sized stack slots.
 
diff --git a/Documentation/mtd/nand_ecc.txt b/Documentation/mtd/nand_ecc.txt
index bdf93b7f0f2..274821b35a7 100644
--- a/Documentation/mtd/nand_ecc.txt
+++ b/Documentation/mtd/nand_ecc.txt
@@ -50,7 +50,7 @@ byte 255:  bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0   rp1 rp3 rp5 ... rp15
            cp5  cp5  cp5  cp5  cp4  cp4  cp4  cp4
 
 This figure represents a sector of 256 bytes.
-cp is my abbreviaton for column parity, rp for row parity.
+cp is my abbreviation for column parity, rp for row parity.
 
 Let's start to explain column parity.
 cp0 is the parity that belongs to all bit0, bit2, bit4, bit6.
@@ -560,7 +560,7 @@ Measuring this code again showed big gain. When executing the original
 linux code 1 million times, this took about 1 second on my system.
 (using time to measure the performance). After this iteration I was back
 to 0.075 sec. Actually I had to decide to start measuring over 10
-million interations in order not to loose too much accuracy. This one
+million iterations in order not to lose too much accuracy. This one
 definitely seemed to be the jackpot!
 
 There is a little bit more room for improvement though. There are three
@@ -571,8 +571,8 @@ loop; This eliminates 3 statements per loop. Of course after the loop we
 need to correct by adding:
     rp4 ^= rp4_6;
     rp6 ^= rp4_6
-Furthermore there are 4 sequential assingments to rp8. This can be
-encoded slightly more efficient by saving tmppar before those 4 lines
+Furthermore there are 4 sequential assignments to rp8. This can be
+encoded slightly more efficiently by saving tmppar before those 4 lines
 and later do rp8 = rp8 ^ tmppar ^ notrp8;
 (where notrp8 is the value of rp8 before those 4 lines).
 Again a use of the commutative property of xor.
@@ -622,7 +622,7 @@ Not a big change, but every penny counts :-)
 Analysis 7
 ==========
 
-Acutally this made things worse. Not very much, but I don't want to move
+Actually this made things worse. Not very much, but I don't want to move
 into the wrong direction. Maybe something to investigate later. Could
 have to do with caching again.
 
@@ -642,7 +642,7 @@ Analysis 8
 This makes things worse. Let's stick with attempt 6 and continue from there.
 Although it seems that the code within the loop cannot be optimised
 further there is still room to optimize the generation of the ecc codes.
-We can simply calcualate the total parity. If this is 0 then rp4 = rp5
+We can simply calculate the total parity. If this is 0 then rp4 = rp5
 etc. If the parity is 1, then rp4 = !rp5;
 But if rp4 = rp5 we do not need rp5 etc. We can just write the even bits
 in the result byte and then do something like
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index 08762750f12..d5181ce9ff6 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -221,7 +221,7 @@ ad_select
 
 		- Any slave's 802.3ad association state changes
 
-		- The bond's adminstrative state changes to up
+		- The bond's administrative state changes to up
 
 	count or 2
 
@@ -369,7 +369,7 @@ fail_over_mac
 		When this policy is used in conjuction with the mii
 		monitor, devices which assert link up prior to being
 		able to actually transmit and receive are particularly
-		susecptible to loss of the gratuitous ARP, and an
+		susceptible to loss of the gratuitous ARP, and an
 		appropriate updelay setting may be required.
 
 	follow or 2
@@ -1794,7 +1794,7 @@ target to query.
 generally referred to as "trunk failover."  This is a feature of the
 switch that causes the link state of a particular switch port to be set
 down (or up) when the state of another switch port goes down (or up).
-It's purpose is to propogate link failures from logically "exterior" ports
+Its purpose is to propagate link failures from logically "exterior" ports
 to the logically "interior" ports that bonding is able to monitor via
 miimon.  Availability and configuration for trunk failover varies by
 switch, but this can be a viable alternative to the ARP monitor when using
diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt
index 2035bc4932f..cd79735013f 100644
--- a/Documentation/networking/can.txt
+++ b/Documentation/networking/can.txt
@@ -36,10 +36,15 @@ This file contains
     6.2 local loopback of sent frames
     6.3 CAN controller hardware filters
     6.4 The virtual CAN driver (vcan)
-    6.5 currently supported CAN hardware
-    6.6 todo
+    6.5 The CAN network device driver interface
+      6.5.1 Netlink interface to set/get devices properties
+      6.5.2 Setting the CAN bit-timing
+      6.5.3 Starting and stopping the CAN network device
+    6.6 supported CAN hardware
 
-  7 Credits
+  7 Socket CAN resources
+
+  8 Credits
 
 ============================================================================
 
@@ -234,6 +239,8 @@ solution for a couple of reasons:
   the user application using the common CAN filter mechanisms. Inside
   this filter definition the (interested) type of errors may be
   selected. The reception of error frames is disabled by default.
+  The format of the CAN error frame is briefly decribed in the Linux
+  header file "include/linux/can/error.h".
 
 4. How to use Socket CAN
 ------------------------
@@ -327,7 +334,7 @@ solution for a couple of reasons:
             return 1;
     }
 
-    /* paraniod check ... */
+    /* paranoid check ... */
     if (nbytes < sizeof(struct can_frame)) {
             fprintf(stderr, "read: incomplete CAN frame\n");
             return 1;
@@ -605,61 +612,213 @@ solution for a couple of reasons:
   removal of vcan network devices can be managed with the ip(8) tool:
 
   - Create a virtual CAN network interface:
-       ip link add type vcan
+       $ ip link add type vcan
 
   - Create a virtual CAN network interface with a specific name 'vcan42':
-       ip link add dev vcan42 type vcan
+       $ ip link add dev vcan42 type vcan
 
   - Remove a (virtual CAN) network interface 'vcan42':
-       ip link del vcan42
-
-  The tool 'vcan' from the SocketCAN SVN repository on BerliOS is obsolete.
-
-  Virtual CAN network device creation in older Kernels:
-  In Linux Kernel versions < 2.6.24 the vcan driver creates 4 vcan
-  netdevices at module load time by default. This value can be changed
-  with the module parameter 'numdev'. E.g. 'modprobe vcan numdev=8'
-
-  6.5 currently supported CAN hardware
+       $ ip link del vcan42
+
+  6.5 The CAN network device driver interface
+
+  The CAN network device driver interface provides a generic interface
+  to setup, configure and monitor CAN network devices. The user can then
+  configure the CAN device, like setting the bit-timing parameters, via
+  the netlink interface using the program "ip" from the "IPROUTE2"
+  utility suite. The following chapter describes briefly how to use it.
+  Furthermore, the interface uses a common data structure and exports a
+  set of common functions, which all real CAN network device drivers
+  should use. Please have a look to the SJA1000 or MSCAN driver to
+  understand how to use them. The name of the module is can-dev.ko.
+
+  6.5.1 Netlink interface to set/get devices properties
+
+  The CAN device must be configured via netlink interface. The supported
+  netlink message types are defined and briefly described in
+  "include/linux/can/netlink.h". CAN link support for the program "ip"
+  of the IPROUTE2 utility suite is avaiable and it can be used as shown
+  below:
+
+  - Setting CAN device properties:
+
+    $ ip link set can0 type can help
+    Usage: ip link set DEVICE type can
+    	[ bitrate BITRATE [ sample-point SAMPLE-POINT] ] |
+    	[ tq TQ prop-seg PROP_SEG phase-seg1 PHASE-SEG1
+     	  phase-seg2 PHASE-SEG2 [ sjw SJW ] ]
+
+    	[ loopback { on | off } ]
+    	[ listen-only { on | off } ]
+    	[ triple-sampling { on | off } ]
+
+    	[ restart-ms TIME-MS ]
+    	[ restart ]
+
+    	Where: BITRATE       := { 1..1000000 }
+    	       SAMPLE-POINT  := { 0.000..0.999 }
+    	       TQ            := { NUMBER }
+    	       PROP-SEG      := { 1..8 }
+    	       PHASE-SEG1    := { 1..8 }
+    	       PHASE-SEG2    := { 1..8 }
+    	       SJW           := { 1..4 }
+    	       RESTART-MS    := { 0 | NUMBER }
+
+  - Display CAN device details and statistics:
+
+    $ ip -details -statistics link show can0
+    2: can0: <NOARP,UP,LOWER_UP,ECHO> mtu 16 qdisc pfifo_fast state UP qlen 10
+      link/can
+      can <TRIPLE-SAMPLING> state ERROR-ACTIVE restart-ms 100
+      bitrate 125000 sample_point 0.875
+      tq 125 prop-seg 6 phase-seg1 7 phase-seg2 2 sjw 1
+      sja1000: tseg1 1..16 tseg2 1..8 sjw 1..4 brp 1..64 brp-inc 1
+      clock 8000000
+      re-started bus-errors arbit-lost error-warn error-pass bus-off
+      41         17457      0          41         42         41
+      RX: bytes  packets  errors  dropped overrun mcast
+      140859     17608    17457   0       0       0
+      TX: bytes  packets  errors  dropped carrier collsns
+      861        112      0       41      0       0
+
+  More info to the above output:
+
+    "<TRIPLE-SAMPLING>"
+	Shows the list of selected CAN controller modes: LOOPBACK,
+	LISTEN-ONLY, or TRIPLE-SAMPLING.
+
+    "state ERROR-ACTIVE"
+	The current state of the CAN controller: "ERROR-ACTIVE",
+	"ERROR-WARNING", "ERROR-PASSIVE", "BUS-OFF" or "STOPPED"
+
+    "restart-ms 100"
+	Automatic restart delay time. If set to a non-zero value, a
+	restart of the CAN controller will be triggered automatically
+	in case of a bus-off condition after the specified delay time
+	in milliseconds. By default it's off.
+
+    "bitrate 125000 sample_point 0.875"
+	Shows the real bit-rate in bits/sec and the sample-point in the
+	range 0.000..0.999. If the calculation of bit-timing parameters
+	is enabled in the kernel (CONFIG_CAN_CALC_BITTIMING=y), the
+	bit-timing can be defined by setting the "bitrate" argument.
+	Optionally the "sample-point" can be specified. By default it's
+	0.000 assuming CIA-recommended sample-points.
+
+    "tq 125 prop-seg 6 phase-seg1 7 phase-seg2 2 sjw 1"
+	Shows the time quanta in ns, propagation segment, phase buffer
+	segment 1 and 2 and the synchronisation jump width in units of
+	tq. They allow to define the CAN bit-timing in a hardware
+	independent format as proposed by the Bosch CAN 2.0 spec (see
+	chapter 8 of http://www.semiconductors.bosch.de/pdf/can2spec.pdf).
+
+    "sja1000: tseg1 1..16 tseg2 1..8 sjw 1..4 brp 1..64 brp-inc 1
+     clock 8000000"
+	Shows the bit-timing constants of the CAN controller, here the
+	"sja1000". The minimum and maximum values of the time segment 1
+	and 2, the synchronisation jump width in units of tq, the
+	bitrate pre-scaler and the CAN system clock frequency in Hz.
+	These constants could be used for user-defined (non-standard)
+	bit-timing calculation algorithms in user-space.
+
+    "re-started bus-errors arbit-lost error-warn error-pass bus-off"
+	Shows the number of restarts, bus and arbitration lost errors,
+	and the state changes to the error-warning, error-passive and
+	bus-off state. RX overrun errors are listed in the "overrun"
+	field of the standard network statistics.
+
+  6.5.2 Setting the CAN bit-timing
+
+  The CAN bit-timing parameters can always be defined in a hardware
+  independent format as proposed in the Bosch CAN 2.0 specification
+  specifying the arguments "tq", "prop_seg", "phase_seg1", "phase_seg2"
+  and "sjw":
+
+    $ ip link set canX type can tq 125 prop-seg 6 \
+				phase-seg1 7 phase-seg2 2 sjw 1
+
+  If the kernel option CONFIG_CAN_CALC_BITTIMING is enabled, CIA
+  recommended CAN bit-timing parameters will be calculated if the bit-
+  rate is specified with the argument "bitrate":
+
+    $ ip link set canX type can bitrate 125000
+
+  Note that this works fine for the most common CAN controllers with
+  standard bit-rates but may *fail* for exotic bit-rates or CAN system
+  clock frequencies. Disabling CONFIG_CAN_CALC_BITTIMING saves some
+  space and allows user-space tools to solely determine and set the
+  bit-timing parameters. The CAN controller specific bit-timing
+  constants can be used for that purpose. They are listed by the
+  following command:
+
+    $ ip -details link show can0
+    ...
+      sja1000: clock 8000000 tseg1 1..16 tseg2 1..8 sjw 1..4 brp 1..64 brp-inc 1
+
+  6.5.3 Starting and stopping the CAN network device
+
+  A CAN network device is started or stopped as usual with the command
+  "ifconfig canX up/down" or "ip link set canX up/down". Be aware that
+  you *must* define proper bit-timing parameters for real CAN devices
+  before you can start it to avoid error-prone default settings:
+
+    $ ip link set canX up type can bitrate 125000
+
+  A device may enter the "bus-off" state if too much errors occurred on
+  the CAN bus. Then no more messages are received or sent. An automatic
+  bus-off recovery can be enabled by setting the "restart-ms" to a
+  non-zero value, e.g.:
+
+    $ ip link set canX type can restart-ms 100
+
+  Alternatively, the application may realize the "bus-off" condition
+  by monitoring CAN error frames and do a restart when appropriate with
+  the command:
+
+    $ ip link set canX type can restart
+
+  Note that a restart will also create a CAN error frame (see also
+  chapter 3.4).
 
-  On the project website http://developer.berlios.de/projects/socketcan
-  there are different drivers available:
+  6.6 Supported CAN hardware
 
-    vcan:    Virtual CAN interface driver (if no real hardware is available)
-    sja1000: Philips SJA1000 CAN controller (recommended)
-    i82527:  Intel i82527 CAN controller
-    mscan:   Motorola/Freescale CAN controller (e.g. inside SOC MPC5200)
-    ccan:    CCAN controller core (e.g. inside SOC h7202)
-    slcan:   For a bunch of CAN adaptors that are attached via a
-             serial line ASCII protocol (for serial / USB adaptors)
+  Please check the "Kconfig" file in "drivers/net/can" to get an actual
+  list of the support CAN hardware. On the Socket CAN project website
+  (see chapter 7) there might be further drivers available, also for
+  older kernel versions.
 
-  Additionally the different CAN adaptors (ISA/PCI/PCMCIA/USB/Parport)
-  from PEAK Systemtechnik support the CAN netdevice driver model
-  since Linux driver v6.0: http://www.peak-system.com/linux/index.htm
+7. Socket CAN resources
+-----------------------
 
-  Please check the Mailing Lists on the berlios OSS project website.
+  You can find further resources for Socket CAN like user space tools,
+  support for old kernel versions, more drivers, mailing lists, etc.
+  at the BerliOS OSS project website for Socket CAN:
 
-  6.6 todo
+    http://developer.berlios.de/projects/socketcan
 
-  The configuration interface for CAN network drivers is still an open
-  issue that has not been finalized in the socketcan project. Also the
-  idea of having a library module (candev.ko) that holds functions
-  that are needed by all CAN netdevices is not ready to ship.
-  Your contribution is welcome.
+  If you have questions, bug fixes, etc., don't hesitate to post them to
+  the Socketcan-Users mailing list. But please search the archives first.
 
-7. Credits
+8. Credits
 ----------
 
-  Oliver Hartkopp (PF_CAN core, filters, drivers, bcm)
+  Oliver Hartkopp (PF_CAN core, filters, drivers, bcm, SJA1000 driver)
   Urs Thuermann (PF_CAN core, kernel integration, socket interfaces, raw, vcan)
   Jan Kizka (RT-SocketCAN core, Socket-API reconciliation)
-  Wolfgang Grandegger (RT-SocketCAN core & drivers, Raw Socket-API reviews)
+  Wolfgang Grandegger (RT-SocketCAN core & drivers, Raw Socket-API reviews,
+                       CAN device driver interface, MSCAN driver)
   Robert Schwebel (design reviews, PTXdist integration)
   Marc Kleine-Budde (design reviews, Kernel 2.6 cleanups, drivers)
   Benedikt Spranger (reviews)
   Thomas Gleixner (LKML reviews, coding style, posting hints)
-  Andrey Volkov (kernel subtree structure, ioctls, mscan driver)
+  Andrey Volkov (kernel subtree structure, ioctls, MSCAN driver)
   Matthias Brukner (first SJA1000 CAN netdevice implementation Q2/2003)
   Klaus Hitschler (PEAK driver integration)
   Uwe Koppe (CAN netdevices with PF_PACKET approach)
   Michael Schulze (driver layer loopback requirement, RT CAN drivers review)
+  Pavel Pisa (Bit-timing calculation)
+  Sascha Hauer (SJA1000 platform driver)
+  Sebastian Haas (SJA1000 EMS PCI driver)
+  Markus Plessing (SJA1000 EMS PCI driver)
+  Per Dalen (SJA1000 Kvaser PCI driver)
+  Sam Ravnborg (reviews, coding style, kbuild help)
diff --git a/Documentation/networking/dm9000.txt b/Documentation/networking/dm9000.txt
index 65df3dea556..5552e2e575c 100644
--- a/Documentation/networking/dm9000.txt
+++ b/Documentation/networking/dm9000.txt
@@ -129,7 +129,7 @@ PHY Link state polling
 ----------------------
 
 The driver keeps track of the link state and informs the network core
-about link (carrier) availablilty. This is managed by several methods
+about link (carrier) availability. This is managed by several methods
 depending on the version of the chip and on which PHY is being used.
 
 For the internal PHY, the original (and currently default) method is
diff --git a/Documentation/networking/ieee802154.txt b/Documentation/networking/ieee802154.txt
new file mode 100644
index 00000000000..a0280ad2edc
--- /dev/null
+++ b/Documentation/networking/ieee802154.txt
@@ -0,0 +1,76 @@
+
+		Linux IEEE 802.15.4 implementation
+
+
+Introduction
+============
+
+The Linux-ZigBee project goal is to provide complete implementation
+of IEEE 802.15.4 / ZigBee / 6LoWPAN protocols. IEEE 802.15.4 is a stack
+of protocols for organizing Low-Rate Wireless Personal Area Networks.
+
+Currently only IEEE 802.15.4 layer is implemented. We have choosen
+to use plain Berkeley socket API, the generic Linux networking stack
+to transfer IEEE 802.15.4 messages and a special protocol over genetlink
+for configuration/management
+
+
+Socket API
+==========
+
+int sd = socket(PF_IEEE802154, SOCK_DGRAM, 0);
+.....
+
+The address family, socket addresses etc. are defined in the
+include/net/ieee802154/af_ieee802154.h header or in the special header
+in our userspace package (see either linux-zigbee sourceforge download page
+or git tree at git://linux-zigbee.git.sourceforge.net/gitroot/linux-zigbee).
+
+One can use SOCK_RAW for passing raw data towards device xmit function. YMMV.
+
+
+MLME - MAC Level Management
+============================
+
+Most of IEEE 802.15.4 MLME interfaces are directly mapped on netlink commands.
+See the include/net/ieee802154/nl802154.h header. Our userspace tools package
+(see above) provides CLI configuration utility for radio interfaces and simple
+coordinator for IEEE 802.15.4 networks as an example users of MLME protocol.
+
+
+Kernel side
+=============
+
+Like with WiFi, there are several types of devices implementing IEEE 802.15.4.
+1) 'HardMAC'. The MAC layer is implemented in the device itself, the device
+   exports MLME and data API.
+2) 'SoftMAC' or just radio. These types of devices are just radio transceivers
+   possibly with some kinds of acceleration like automatic CRC computation and
+   comparation, automagic ACK handling, address matching, etc.
+
+Those types of devices require different approach to be hooked into Linux kernel.
+
+
+HardMAC
+=======
+
+See the header include/net/ieee802154/netdevice.h. You have to implement Linux
+net_device, with .type = ARPHRD_IEEE802154. Data is exchanged with socket family
+code via plain sk_buffs. The control block of sk_buffs will contain additional
+info as described in the struct ieee802154_mac_cb.
+
+To hook the MLME interface you have to populate the ml_priv field of your
+net_device with a pointer to struct ieee802154_mlme_ops instance. All fields are
+required.
+
+We provide an example of simple HardMAC driver at drivers/ieee802154/fakehard.c
+
+
+SoftMAC
+=======
+
+We are going to provide intermediate layer impelementing IEEE 802.15.4 MAC
+in software. This is currently WIP.
+
+See header include/net/ieee802154/mac802154.h and several drivers in
+drivers/ieee802154/
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index ec5de02f543..8be76235fe6 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -168,7 +168,16 @@ tcp_dsack - BOOLEAN
 	Allows TCP to send "duplicate" SACKs.
 
 tcp_ecn - BOOLEAN
-	Enable Explicit Congestion Notification in TCP.
+	Enable Explicit Congestion Notification (ECN) in TCP. ECN is only
+	used when both ends of the TCP flow support it. It is useful to
+	avoid losses due to congestion (when the bottleneck router supports
+	ECN).
+	Possible values are:
+		0 disable ECN
+		1 ECN enabled
+		2 Only server-side ECN enabled. If the other end does
+		  not support ECN, behavior is like with ECN disabled.
+	Default: 2
 
 tcp_fack - BOOLEAN
 	Enable FACK congestion avoidance and fast retransmission.
@@ -1048,6 +1057,13 @@ disable_ipv6 - BOOLEAN
 	address.
 	Default: FALSE (enable IPv6 operation)
 
+	When this value is changed from 1 to 0 (IPv6 is being enabled),
+	it will dynamically create a link-local address on the given
+	interface and start Duplicate Address Detection, if necessary.
+
+	When this value is changed from 0 to 1 (IPv6 is being disabled),
+	it will dynamically delete all address on the given interface.
+
 accept_dad - INTEGER
 	Whether to accept DAD (Duplicate Address Detection).
 	0: Disable DAD
@@ -1266,13 +1282,22 @@ sctp_rmem - vector of 3 INTEGERs: min, default, max
 sctp_wmem  - vector of 3 INTEGERs: min, default, max
 	See tcp_wmem for a description.
 
-UNDOCUMENTED:
 
 /proc/sys/net/core/*
-	dev_weight FIXME
+dev_weight - INTEGER
+	The maximum number of packets that kernel can handle on a NAPI
+	interrupt, it's a Per-CPU variable.
+
+	Default: 64
 
 /proc/sys/net/unix/*
-	max_dgram_qlen FIXME
+max_dgram_qlen - INTEGER
+	The maximum length of dgram socket receive queue
+
+	Default: 10
+
+
+UNDOCUMENTED:
 
 /proc/sys/net/irda/*
 	fast_poll_increase FIXME
diff --git a/Documentation/networking/ipv6.txt b/Documentation/networking/ipv6.txt
index 268e5c103dd..9fd7e21296c 100644
--- a/Documentation/networking/ipv6.txt
+++ b/Documentation/networking/ipv6.txt
@@ -33,3 +33,40 @@ disable
 
 		A reboot is required to enable IPv6.
 
+autoconf
+
+	Specifies whether to enable IPv6 address autoconfiguration
+	on all interfaces.  This might be used when one does not wish
+	for addresses to be automatically generated from prefixes
+	received in Router Advertisements.
+
+	The possible values and their effects are:
+
+	0
+		IPv6 address autoconfiguration is disabled on all interfaces.
+
+		Only the IPv6 loopback address (::1) and link-local addresses
+		will be added to interfaces.
+
+	1
+		IPv6 address autoconfiguration is enabled on all interfaces.
+
+		This is the default value.
+
+disable_ipv6
+
+	Specifies whether to disable IPv6 on all interfaces.
+	This might be used when no IPv6 addresses are desired.
+
+	The possible values and their effects are:
+
+	0
+		IPv6 is enabled on all interfaces.
+
+		This is the default value.
+
+	1
+		IPv6 is disabled on all interfaces.
+
+		No IPv6 addresses will be added to interfaces.
+
diff --git a/Documentation/networking/l2tp.txt b/Documentation/networking/l2tp.txt
index 2451f551c50..63214b280e0 100644
--- a/Documentation/networking/l2tp.txt
+++ b/Documentation/networking/l2tp.txt
@@ -158,7 +158,7 @@ Sample Userspace Code
         }
         return 0;
 
-Miscellanous
+Miscellaneous
 ============
 
 The PPPoL2TP driver was developed as part of the OpenL2TP project by
diff --git a/Documentation/networking/mac80211-injection.txt b/Documentation/networking/mac80211-injection.txt
index 84906ef3ed6..b30e81ad530 100644
--- a/Documentation/networking/mac80211-injection.txt
+++ b/Documentation/networking/mac80211-injection.txt
@@ -12,38 +12,22 @@ following format:
 The radiotap format is discussed in
 ./Documentation/networking/radiotap-headers.txt.
 
-Despite 13 radiotap argument types are currently defined, most only make sense
+Despite many radiotap parameters being currently defined, most only make sense
 to appear on received packets.  The following information is parsed from the
 radiotap headers and used to control injection:
 
- * IEEE80211_RADIOTAP_RATE
-
-   rate in 500kbps units, automatic if invalid or not present
-
-
- * IEEE80211_RADIOTAP_ANTENNA
-
-   antenna to use, automatic if not present
-
-
- * IEEE80211_RADIOTAP_DBM_TX_POWER
-
-   transmit power in dBm, automatic if not present
-
-
  * IEEE80211_RADIOTAP_FLAGS
 
    IEEE80211_RADIOTAP_F_FCS: FCS will be removed and recalculated
    IEEE80211_RADIOTAP_F_WEP: frame will be encrypted if key available
    IEEE80211_RADIOTAP_F_FRAG: frame will be fragmented if longer than the
-			      current fragmentation threshold. Note that
-			      this flag is only reliable when software
-			      fragmentation is enabled)
+			      current fragmentation threshold.
+
 
 The injection code can also skip all other currently defined radiotap fields
 facilitating replay of captured radiotap headers directly.
 
-Here is an example valid radiotap header defining these three parameters
+Here is an example valid radiotap header defining some parameters
 
 	0x00, 0x00, // <-- radiotap version
 	0x0b, 0x00, // <- radiotap header length
@@ -72,8 +56,8 @@ interface), along the following lines:
 ...
 	r = pcap_inject(ppcap, u8aSendBuffer, nLength);
 
-You can also find sources for a complete inject test applet here:
+You can also find a link to a complete inject application here:
 
-http://penumbra.warmcat.com/_twk/tiki-index.php?page=packetspammer
+http://wireless.kernel.org/en/users/Documentation/packetspammer
 
 Andy Green <andy@warmcat.com>
diff --git a/Documentation/networking/netdevices.txt b/Documentation/networking/netdevices.txt
index a2ab6a0b116..87b3d15f523 100644
--- a/Documentation/networking/netdevices.txt
+++ b/Documentation/networking/netdevices.txt
@@ -74,7 +74,7 @@ dev->hard_start_xmit:
 	for this and return NETDEV_TX_LOCKED when the spin lock fails.
 	The locking there should also properly protect against 
 	set_multicast_list. Note that the use of NETIF_F_LLTX is deprecated.
-	Dont use it for new drivers.
+	Don't use it for new drivers.
 
 	Context: Process with BHs disabled or BH (timer),
 	         will be called with interrupts disabled by netconsole.
diff --git a/Documentation/networking/operstates.txt b/Documentation/networking/operstates.txt
index c9074f9b78b..1a77a3cfae5 100644
--- a/Documentation/networking/operstates.txt
+++ b/Documentation/networking/operstates.txt
@@ -38,9 +38,6 @@ ifinfomsg::if_flags & IFF_LOWER_UP:
 ifinfomsg::if_flags & IFF_DORMANT:
  Driver has signaled netif_dormant_on()
 
-These interface flags can also be queried without netlink using the
-SIOCGIFFLAGS ioctl.
-
 TLV IFLA_OPERSTATE
 
 contains RFC2863 state of the interface in numeric representation:
diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt
index 07c53d59603..a22fd85e379 100644
--- a/Documentation/networking/packet_mmap.txt
+++ b/Documentation/networking/packet_mmap.txt
@@ -4,16 +4,18 @@
 
 This file documents the CONFIG_PACKET_MMAP option available with the PACKET
 socket interface on 2.4 and 2.6 kernels. This type of sockets is used for 
-capture network traffic with utilities like tcpdump or any other that uses 
-the libpcap library. 
-
-You can find the latest version of this document at
+capture network traffic with utilities like tcpdump or any other that needs
+raw access to network interface.
 
+You can find the latest version of this document at:
     http://pusa.uv.es/~ulisses/packet_mmap/
 
-Please send me your comments to
+Howto can be found at:
+    http://wiki.gnu-log.net (packet_mmap)
 
+Please send your comments to
     Ulisses Alonso Camaró <uaca@i.hate.spam.alumni.uv.es>
+    Johann Baudy <johann.baudy@gnu-log.net>
 
 -------------------------------------------------------------------------------
 + Why use PACKET_MMAP
@@ -25,19 +27,24 @@ to capture each packet, it requires two if you want to get packet's
 timestamp (like libpcap always does).
 
 In the other hand PACKET_MMAP is very efficient. PACKET_MMAP provides a size 
-configurable circular buffer mapped in user space. This way reading packets just 
-needs to wait for them, most of the time there is no need to issue a single 
-system call. By using a shared buffer between the kernel and the user 
-also has the benefit of minimizing packet copies.
-
-It's fine to use PACKET_MMAP to improve the performance of the capture process, 
-but it isn't everything. At least, if you are capturing at high speeds (this 
-is relative to the cpu speed), you should check if the device driver of your 
-network interface card supports some sort of interrupt load mitigation or 
-(even better) if it supports NAPI, also make sure it is enabled.
+configurable circular buffer mapped in user space that can be used to either
+send or receive packets. This way reading packets just needs to wait for them,
+most of the time there is no need to issue a single system call. Concerning
+transmission, multiple packets can be sent through one system call to get the
+highest bandwidth.
+By using a shared buffer between the kernel and the user also has the benefit
+of minimizing packet copies.
+
+It's fine to use PACKET_MMAP to improve the performance of the capture and
+transmission process, but it isn't everything. At least, if you are capturing
+at high speeds (this is relative to the cpu speed), you should check if the
+device driver of your network interface card supports some sort of interrupt
+load mitigation or (even better) if it supports NAPI, also make sure it is
+enabled. For transmission, check the MTU (Maximum Transmission Unit) used and
+supported by devices of your network.
 
 --------------------------------------------------------------------------------
-+ How to use CONFIG_PACKET_MMAP
++ How to use CONFIG_PACKET_MMAP to improve capture process
 --------------------------------------------------------------------------------
 
 From the user standpoint, you should use the higher level libpcap library, which
@@ -57,7 +64,7 @@ the low level details or want to improve libpcap by including PACKET_MMAP
 support.
 
 --------------------------------------------------------------------------------
-+ How to use CONFIG_PACKET_MMAP directly
++ How to use CONFIG_PACKET_MMAP directly to improve capture process
 --------------------------------------------------------------------------------
 
 From the system calls stand point, the use of PACKET_MMAP involves
@@ -66,6 +73,7 @@ the following process:
 
 [setup]     socket() -------> creation of the capture socket
             setsockopt() ---> allocation of the circular buffer (ring)
+                              option: PACKET_RX_RING
             mmap() ---------> mapping of the allocated buffer to the
                               user process
 
@@ -97,13 +105,75 @@ also the mapping of the circular buffer in the user process and
 the use of this buffer.
 
 --------------------------------------------------------------------------------
++ How to use CONFIG_PACKET_MMAP directly to improve transmission process
+--------------------------------------------------------------------------------
+Transmission process is similar to capture as shown below.
+
+[setup]          socket() -------> creation of the transmission socket
+                 setsockopt() ---> allocation of the circular buffer (ring)
+                                   option: PACKET_TX_RING
+                 bind() ---------> bind transmission socket with a network interface
+                 mmap() ---------> mapping of the allocated buffer to the
+                                   user process
+
+[transmission]   poll() ---------> wait for free packets (optional)
+                 send() ---------> send all packets that are set as ready in
+                                   the ring
+                                   The flag MSG_DONTWAIT can be used to return
+                                   before end of transfer.
+
+[shutdown]  close() --------> destruction of the transmission socket and
+                              deallocation of all associated resources.
+
+Binding the socket to your network interface is mandatory (with zero copy) to
+know the header size of frames used in the circular buffer.
+
+As capture, each frame contains two parts:
+
+ --------------------
+| struct tpacket_hdr | Header. It contains the status of
+|                    | of this frame
+|--------------------|
+| data buffer        |
+.                    .  Data that will be sent over the network interface.
+.                    .
+ --------------------
+
+ bind() associates the socket to your network interface thanks to
+ sll_ifindex parameter of struct sockaddr_ll.
+
+ Initialization example:
+
+ struct sockaddr_ll my_addr;
+ struct ifreq s_ifr;
+ ...
+
+ strncpy (s_ifr.ifr_name, "eth0", sizeof(s_ifr.ifr_name));
+
+ /* get interface index of eth0 */
+ ioctl(this->socket, SIOCGIFINDEX, &s_ifr);
+
+ /* fill sockaddr_ll struct to prepare binding */
+ my_addr.sll_family = AF_PACKET;
+ my_addr.sll_protocol = ETH_P_ALL;
+ my_addr.sll_ifindex =  s_ifr.ifr_ifindex;
+
+ /* bind socket to eth0 */
+ bind(this->socket, (struct sockaddr *)&my_addr, sizeof(struct sockaddr_ll));
+
+ A complete tutorial is available at: http://wiki.gnu-log.net/
+
+--------------------------------------------------------------------------------
 + PACKET_MMAP settings
 --------------------------------------------------------------------------------
 
 
 To setup PACKET_MMAP from user level code is done with a call like
 
+ - Capture process
      setsockopt(fd, SOL_PACKET, PACKET_RX_RING, (void *) &req, sizeof(req))
+ - Transmission process
+     setsockopt(fd, SOL_PACKET, PACKET_TX_RING, (void *) &req, sizeof(req))
 
 The most significant argument in the previous call is the req parameter, 
 this parameter must to have the following structure:
@@ -117,11 +187,11 @@ this parameter must to have the following structure:
     };
 
 This structure is defined in /usr/include/linux/if_packet.h and establishes a 
-circular buffer (ring) of unswappable memory mapped in the capture process. 
+circular buffer (ring) of unswappable memory.
 Being mapped in the capture process allows reading the captured frames and 
 related meta-information like timestamps without requiring a system call.
 
-Captured frames are grouped in blocks. Each block is a physically contiguous 
+Frames are grouped in blocks. Each block is a physically contiguous
 region of memory and holds tp_block_size/tp_frame_size frames. The total number 
 of blocks is tp_block_nr. Note that tp_frame_nr is a redundant parameter because
 
@@ -336,6 +406,7 @@ struct tpacket_hdr). If this field is 0 means that the frame is ready
 to be used for the kernel, If not, there is a frame the user can read 
 and the following flags apply:
 
++++ Capture process:
      from include/linux/if_packet.h
 
      #define TP_STATUS_COPY          2 
@@ -391,6 +462,37 @@ packets are in the ring:
 It doesn't incur in a race condition to first check the status value and 
 then poll for frames.
 
+
+++ Transmission process
+Those defines are also used for transmission:
+
+     #define TP_STATUS_AVAILABLE        0 // Frame is available
+     #define TP_STATUS_SEND_REQUEST     1 // Frame will be sent on next send()
+     #define TP_STATUS_SENDING          2 // Frame is currently in transmission
+     #define TP_STATUS_WRONG_FORMAT     4 // Frame format is not correct
+
+First, the kernel initializes all frames to TP_STATUS_AVAILABLE. To send a
+packet, the user fills a data buffer of an available frame, sets tp_len to
+current data buffer size and sets its status field to TP_STATUS_SEND_REQUEST.
+This can be done on multiple frames. Once the user is ready to transmit, it
+calls send(). Then all buffers with status equal to TP_STATUS_SEND_REQUEST are
+forwarded to the network device. The kernel updates each status of sent
+frames with TP_STATUS_SENDING until the end of transfer.
+At the end of each transfer, buffer status returns to TP_STATUS_AVAILABLE.
+
+    header->tp_len = in_i_size;
+    header->tp_status = TP_STATUS_SEND_REQUEST;
+    retval = send(this->socket, NULL, 0, 0);
+
+The user can also use poll() to check if a buffer is available:
+(status == TP_STATUS_SENDING)
+
+    struct pollfd pfd;
+    pfd.fd = fd;
+    pfd.revents = 0;
+    pfd.events = POLLOUT;
+    retval = poll(&pfd, 1, timeout);
+
 --------------------------------------------------------------------------------
 + THANKS
 --------------------------------------------------------------------------------
diff --git a/Documentation/networking/phonet.txt b/Documentation/networking/phonet.txt
index 6a07e45d4a9..6e8ce09f9c7 100644
--- a/Documentation/networking/phonet.txt
+++ b/Documentation/networking/phonet.txt
@@ -36,7 +36,7 @@ Phonet packets have a common header as follows:
 On Linux, the link-layer header includes the pn_media byte (see below).
 The next 7 bytes are part of the network-layer header.
 
-The device ID is split: the 6 higher-order bits consitute the device
+The device ID is split: the 6 higher-order bits constitute the device
 address, while the 2 lower-order bits are used for multiplexing, as are
 the 8-bit object identifiers. As such, Phonet can be considered as a
 network layer with 6 bits of address space and 10 bits for transport
diff --git a/Documentation/networking/regulatory.txt b/Documentation/networking/regulatory.txt
index dcf31648414..eaa1a25946c 100644
--- a/Documentation/networking/regulatory.txt
+++ b/Documentation/networking/regulatory.txt
@@ -89,7 +89,7 @@ added to this document when its support is enabled.
 Device drivers who provide their own built regulatory domain
 do not need a callback as the channels registered by them are
 the only ones that will be allowed and therefore *additional*
-cannels cannot be enabled.
+channels cannot be enabled.
 
 Example code - drivers hinting an alpha2:
 ------------------------------------------
diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt
index 421e7d00ffd..c9abbd86bc1 100644
--- a/Documentation/power/devices.txt
+++ b/Documentation/power/devices.txt
@@ -75,9 +75,6 @@ may need to apply in domain-specific ways to their devices:
 struct bus_type {
 	...
 	int  (*suspend)(struct device *dev, pm_message_t state);
-	int  (*suspend_late)(struct device *dev, pm_message_t state);
-
-	int  (*resume_early)(struct device *dev);
 	int  (*resume)(struct device *dev);
 };
 
@@ -226,20 +223,7 @@ The phases are seen by driver notifications issued in this order:
 
 	This call should handle parts of device suspend logic that require
 	sleeping.  It probably does work to quiesce the device which hasn't
-	been abstracted into class.suspend() or bus.suspend_late().
-
-   3	bus.suspend_late(dev, message) is called with IRQs disabled, and
-	with only one CPU active.  Until the bus.resume_early() phase
-	completes (see later), IRQs are not enabled again.  This method
-	won't be exposed by all busses; for message based busses like USB,
-	I2C, or SPI, device interactions normally require IRQs.  This bus
-	call may be morphed into a driver call with bus-specific parameters.
-
-	This call might save low level hardware state that might otherwise
-	be lost in the upcoming low power state, and actually put the
-	device into a low power state ... so that in some cases the device
-	may stay partly usable until this late.  This "late" call may also
-	help when coping with hardware that behaves badly.
+	been abstracted into class.suspend().
 
 The pm_message_t parameter is currently used to refine those semantics
 (described later).
@@ -351,19 +335,11 @@ devices processing each phase's calls before the next phase begins.
 
 The phases are seen by driver notifications issued in this order:
 
-   1	bus.resume_early(dev) is called with IRQs disabled, and with
-   	only one CPU active.  As with bus.suspend_late(), this method
-	won't be supported on busses that require IRQs in order to
-	interact with devices.
-
-	This reverses the effects of bus.suspend_late().
-
-   2	bus.resume(dev) is called next.  This may be morphed into a device
-   	driver call with bus-specific parameters; implementations may sleep.
-
-	This reverses the effects of bus.suspend().
+   1	bus.resume(dev) reverses the effects of bus.suspend().  This may
+	be morphed into a device driver call with bus-specific parameters;
+	implementations may sleep.
 
-   3	class.resume(dev) is called for devices associated with a class
+   2	class.resume(dev) is called for devices associated with a class
 	that has such a method.  Implementations may sleep.
 
 	This reverses the effects of class.suspend(), and would usually
diff --git a/Documentation/power/regulator/consumer.txt b/Documentation/power/regulator/consumer.txt
index 82b7a43aadb..5f83fd24ea8 100644
--- a/Documentation/power/regulator/consumer.txt
+++ b/Documentation/power/regulator/consumer.txt
@@ -178,5 +178,5 @@ Consumers can uregister interest by calling :-
 int regulator_unregister_notifier(struct regulator *regulator,
 				struct notifier_block *nb);
 
-Regulators use the kernel notifier framework to send event to thier interested
+Regulators use the kernel notifier framework to send event to their interested
 consumers.
diff --git a/Documentation/power/regulator/overview.txt b/Documentation/power/regulator/overview.txt
index bdcb332bd7f..0cded696ca0 100644
--- a/Documentation/power/regulator/overview.txt
+++ b/Documentation/power/regulator/overview.txt
@@ -119,7 +119,7 @@ Some terms used in this document:-
                    battery power, USB power)
 
                    Regulator Domains: is the new current limit within the
-                   regulator operating parameters for input/ouput voltage.
+                   regulator operating parameters for input/output voltage.
 
                    If the regulator request passes all the constraint tests
                    then the new regulator value is applied.
diff --git a/Documentation/power/s2ram.txt b/Documentation/power/s2ram.txt
index 2ebdc6091ce..514b94fc931 100644
--- a/Documentation/power/s2ram.txt
+++ b/Documentation/power/s2ram.txt
@@ -63,7 +63,7 @@ hardware during resume operations where a value can be set that will
 survive a reboot.
 
 Consequence is that after a resume (even if it is successful) your system
-clock will have a value corresponding to the magic mumber instead of the
+clock will have a value corresponding to the magic number instead of the
 correct date/time! It is therefore advisable to use a program like ntp-date
 or rdate to reset the correct date/time from an external time source when
 using this trace option.
diff --git a/Documentation/power/userland-swsusp.txt b/Documentation/power/userland-swsusp.txt
index 7b99636564c..b967cd9137d 100644
--- a/Documentation/power/userland-swsusp.txt
+++ b/Documentation/power/userland-swsusp.txt
@@ -109,7 +109,7 @@ unfreeze user space processes frozen by SNAPSHOT_UNFREEZE if they are
 still frozen when the device is being closed).
 
 Currently it is assumed that the userland utilities reading/writing the
-snapshot image from/to the kernel will use a swap parition, called the resume
+snapshot image from/to the kernel will use a swap partition, called the resume
 partition, or a swap file as storage space (if a swap file is used, the resume
 partition is the partition that holds this file).  However, this is not really
 required, as they can use, for example, a special (blank) suspend partition or
diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt
index d16b7a1c379..8d999d862d0 100644
--- a/Documentation/powerpc/booting-without-of.txt
+++ b/Documentation/powerpc/booting-without-of.txt
@@ -1356,7 +1356,7 @@ platforms are moved over to use the flattened-device-tree model.
     - phy-map           : 1 cell, optional, bitmap of addresses to probe the PHY
 			  for, used if phy-address is absent. bit 0x00000001 is
 			  MDIO address 0.
-			  For Axon it can be absent, thouugh my current driver
+			  For Axon it can be absent, though my current driver
 			  doesn't handle phy-address yet so for now, keep
 			  0x00ffffff in it.
     - rx-fifo-size-gige : 1 cell, Rx fifo size in bytes for 1000 Mb/sec
@@ -1438,7 +1438,7 @@ platforms are moved over to use the flattened-device-tree model.
 
    The Xilinx EDK toolchain ships with a set of IP cores (devices) for use
    in Xilinx Spartan and Virtex FPGAs.  The devices cover the whole range
-   of standard device types (network, serial, etc.) and miscellanious
+   of standard device types (network, serial, etc.) and miscellaneous
    devices (gpio, LCD, spi, etc).  Also, since these devices are
    implemented within the fpga fabric every instance of the device can be
    synthesised with different options that change the behaviour.
diff --git a/Documentation/powerpc/dts-bindings/can/sja1000.txt b/Documentation/powerpc/dts-bindings/can/sja1000.txt
new file mode 100644
index 00000000000..d6d209ded93
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/can/sja1000.txt
@@ -0,0 +1,53 @@
+Memory mapped SJA1000 CAN controller from NXP (formerly Philips)
+
+Required properties:
+
+- compatible : should be "nxp,sja1000".
+
+- reg : should specify the chip select, address offset and size required
+	to map the registers of the SJA1000. The size is usually 0x80.
+
+- interrupts: property with a value describing the interrupt source
+	(number and sensitivity) required for the SJA1000.
+
+Optional properties:
+
+- nxp,external-clock-frequency : Frequency of the external oscillator
+	clock in Hz. Note that the internal clock frequency used by the
+	SJA1000 is half of that value. If not specified, a default value
+	of 16000000 (16 MHz) is used.
+
+- nxp,tx-output-mode : operation mode of the TX output control logic:
+	<0x0> : bi-phase output mode
+	<0x1> : normal output mode (default)
+	<0x2> : test output mode
+	<0x3> : clock output mode
+
+- nxp,tx-output-config : TX output pin configuration:
+	<0x01> : TX0 invert
+	<0x02> : TX0 pull-down (default)
+	<0x04> : TX0 pull-up
+	<0x06> : TX0 push-pull
+	<0x08> : TX1 invert
+	<0x10> : TX1 pull-down
+	<0x20> : TX1 pull-up
+	<0x30> : TX1 push-pull
+
+- nxp,clock-out-frequency : clock frequency in Hz on the CLKOUT pin.
+	If not specified or if the specified value is 0, the CLKOUT pin
+	will be disabled.
+
+- nxp,no-comparator-bypass : Allows to disable the CAN input comperator.
+
+For futher information, please have a look to the SJA1000 data sheet.
+
+Examples:
+
+can@3,100 {
+	compatible = "nxp,sja1000";
+	reg = <3 0x100 0x80>;
+	interrupts = <2 0>;
+	interrupt-parent = <&mpic>;
+	nxp,external-clock-frequency = <16000000>;
+};
+
diff --git a/Documentation/powerpc/dts-bindings/ecm.txt b/Documentation/powerpc/dts-bindings/ecm.txt
new file mode 100644
index 00000000000..f514f29c67d
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/ecm.txt
@@ -0,0 +1,64 @@
+=====================================================================
+E500 LAW & Coherency Module Device Tree Binding
+Copyright (C) 2009 Freescale Semiconductor Inc.
+=====================================================================
+
+Local Access Window (LAW) Node
+
+The LAW node represents the region of CCSR space where local access
+windows are configured.  For ECM based devices this is the first 4k
+of CCSR space that includes CCSRBAR, ALTCBAR, ALTCAR, BPTR, and some
+number of local access windows as specified by fsl,num-laws.
+
+PROPERTIES
+
+  - compatible
+      Usage: required
+      Value type: <string>
+      Definition: Must include "fsl,ecm-law"
+
+  - reg
+      Usage: required
+      Value type: <prop-encoded-array>
+      Definition: A standard property.  The value specifies the
+          physical address offset and length of the CCSR space
+          registers.
+
+  - fsl,num-laws
+      Usage: required
+      Value type: <u32>
+      Definition: The value specifies the number of local access
+          windows for this device.
+
+=====================================================================
+
+E500 Coherency Module Node
+
+The E500 LAW node represents the region of CCSR space where ECM config
+and error reporting registers exist, this is the second 4k (0x1000)
+of CCSR space.
+
+PROPERTIES
+
+  - compatible
+      Usage: required
+      Value type: <string>
+      Definition: Must include "fsl,CHIP-ecm", "fsl,ecm" where
+      CHIP is the processor (mpc8572, mpc8544, etc.)
+
+  - reg
+      Usage: required
+      Value type: <prop-encoded-array>
+      Definition: A standard property.  The value specifies the
+          physical address offset and length of the CCSR space
+          registers.
+
+   - interrupts
+      Usage: required
+      Value type: <prop-encoded-array>
+
+   - interrupt-parent
+      Usage: required
+      Value type: <phandle>
+
+=====================================================================
diff --git a/Documentation/powerpc/dts-bindings/fsl/board.txt b/Documentation/powerpc/dts-bindings/fsl/board.txt
index 6c974d28eeb..e8b5bc24d0a 100644
--- a/Documentation/powerpc/dts-bindings/fsl/board.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/board.txt
@@ -38,7 +38,7 @@ Required properities:
 - reg : Should contain the address and the length of the GPIO bank
   register.
 - #gpio-cells : Should be two. The first cell is the pin number and the
-  second cell is used to specify optional paramters (currently unused).
+  second cell is used to specify optional parameters (currently unused).
 - gpio-controller : Marks the port as GPIO controller.
 
 Example:
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm.txt
index 088fc471e03..160c752484b 100644
--- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm.txt
@@ -19,7 +19,7 @@ Example:
 	reg = <119c0 30>;
      }
 
-* Properties common to mulitple CPM/QE devices
+* Properties common to multiple CPM/QE devices
 
 - fsl,cpm-command : This value is ORed with the opcode and command flag
                     to specify the device on which a CPM command operates.
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/gpio.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/gpio.txt
index 1815dfede1b..349f79fd707 100644
--- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/gpio.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/gpio.txt
@@ -11,7 +11,7 @@ Required properties:
   "fsl,cpm1-pario-bank-c", "fsl,cpm1-pario-bank-d",
   "fsl,cpm1-pario-bank-e", "fsl,cpm2-pario-bank"
 - #gpio-cells : Should be two. The first cell is the pin number and the
-  second cell is used to specify optional paramters (currently unused).
+  second cell is used to specify optional parameters (currently unused).
 - gpio-controller : Marks the port as GPIO controller.
 
 Example of three SOC GPIO banks defined as gpio-controller nodes:
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt
index 78790d58dc2..6e37be1eeb2 100644
--- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt
@@ -17,6 +17,9 @@ Required properties:
 - model : precise model of the QE, Can be "QE", "CPM", or "CPM2"
 - reg : offset and length of the device registers.
 - bus-frequency : the clock frequency for QUICC Engine.
+- fsl,qe-num-riscs: define how many RISC engines the QE has.
+- fsl,qe-num-snums: define how many serial number(SNUM) the QE can use for the
+  threads.
 
 Recommended properties
 - brg-frequency : the internal clock source frequency for baud-rate
diff --git a/Documentation/powerpc/dts-bindings/fsl/esdhc.txt b/Documentation/powerpc/dts-bindings/fsl/esdhc.txt
index 60084655776..5093ddf900d 100644
--- a/Documentation/powerpc/dts-bindings/fsl/esdhc.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/esdhc.txt
@@ -5,8 +5,7 @@ for MMC, SD, and SDIO types of memory cards.
 
 Required properties:
   - compatible : should be
-    "fsl,<chip>-esdhc", "fsl,mpc8379-esdhc" for MPC83xx processors.
-    "fsl,<chip>-esdhc", "fsl,mpc8536-esdhc" for MPC85xx processors.
+    "fsl,<chip>-esdhc", "fsl,esdhc"
   - reg : should contain eSDHC registers location and length.
   - interrupts : should contain eSDHC interrupt.
   - interrupt-parent : interrupt source phandle.
@@ -15,7 +14,7 @@ Required properties:
 Example:
 
 sdhci@2e000 {
-	compatible = "fsl,mpc8378-esdhc", "fsl,mpc8379-esdhc";
+	compatible = "fsl,mpc8378-esdhc", "fsl,esdhc";
 	reg = <0x2e000 0x1000>;
 	interrupts = <42 0x8>;
 	interrupt-parent = <&ipic>;
diff --git a/Documentation/powerpc/dts-bindings/fsl/mcm.txt b/Documentation/powerpc/dts-bindings/fsl/mcm.txt
new file mode 100644
index 00000000000..4ceda9b3b41
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/mcm.txt
@@ -0,0 +1,64 @@
+=====================================================================
+MPX LAW & Coherency Module Device Tree Binding
+Copyright (C) 2009 Freescale Semiconductor Inc.
+=====================================================================
+
+Local Access Window (LAW) Node
+
+The LAW node represents the region of CCSR space where local access
+windows are configured.  For MCM based devices this is the first 4k
+of CCSR space that includes CCSRBAR, ALTCBAR, ALTCAR, BPTR, and some
+number of local access windows as specified by fsl,num-laws.
+
+PROPERTIES
+
+  - compatible
+      Usage: required
+      Value type: <string>
+      Definition: Must include "fsl,mcm-law"
+
+  - reg
+      Usage: required
+      Value type: <prop-encoded-array>
+      Definition: A standard property.  The value specifies the
+          physical address offset and length of the CCSR space
+          registers.
+
+  - fsl,num-laws
+      Usage: required
+      Value type: <u32>
+      Definition: The value specifies the number of local access
+          windows for this device.
+
+=====================================================================
+
+MPX Coherency Module Node
+
+The MPX LAW node represents the region of CCSR space where MCM config
+and error reporting registers exist, this is the second 4k (0x1000)
+of CCSR space.
+
+PROPERTIES
+
+  - compatible
+      Usage: required
+      Value type: <string>
+      Definition: Must include "fsl,CHIP-mcm", "fsl,mcm" where
+      CHIP is the processor (mpc8641, mpc8610, etc.)
+
+  - reg
+      Usage: required
+      Value type: <prop-encoded-array>
+      Definition: A standard property.  The value specifies the
+          physical address offset and length of the CCSR space
+          registers.
+
+   - interrupts
+      Usage: required
+      Value type: <prop-encoded-array>
+
+   - interrupt-parent
+      Usage: required
+      Value type: <phandle>
+
+=====================================================================
diff --git a/Documentation/powerpc/dts-bindings/fsl/msi-pic.txt b/Documentation/powerpc/dts-bindings/fsl/msi-pic.txt
index b26b91992c5..bcc30bac683 100644
--- a/Documentation/powerpc/dts-bindings/fsl/msi-pic.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/msi-pic.txt
@@ -1,6 +1,6 @@
 * Freescale MSI interrupt controller
 
-Reguired properities:
+Required properties:
 - compatible : compatible list, contains 2 entries,
   first is "fsl,CHIP-msi", where CHIP is the processor(mpc8610, mpc8572,
   etc.) and the second is "fsl,mpic-msi" or "fsl,ipic-msi" depending on
diff --git a/Documentation/powerpc/dts-bindings/fsl/pmc.txt b/Documentation/powerpc/dts-bindings/fsl/pmc.txt
index 02f6f43ee1b..07256b7ffca 100644
--- a/Documentation/powerpc/dts-bindings/fsl/pmc.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/pmc.txt
@@ -15,8 +15,8 @@ Properties:
   compatible; all statements below that apply to "fsl,mpc8548-pmc" also
   apply to "fsl,mpc8641d-pmc".
 
-  Compatibility does not include bit assigments in SCCR/PMCDR/DEVDISR; these
-  bit assigments are indicated via the sleep specifier in each device's
+  Compatibility does not include bit assignments in SCCR/PMCDR/DEVDISR; these
+  bit assignments are indicated via the sleep specifier in each device's
   sleep property.
 
 - reg: For devices compatible with "fsl,mpc8349-pmc", the first resource
diff --git a/Documentation/powerpc/qe_firmware.txt b/Documentation/powerpc/qe_firmware.txt
index 06da4d4b44f..2031ddb33d0 100644
--- a/Documentation/powerpc/qe_firmware.txt
+++ b/Documentation/powerpc/qe_firmware.txt
@@ -225,7 +225,7 @@ For example, to match the 8323, revision 1.0:
      soc.major = 1
      soc.minor = 0
 
-'padding' is neccessary for structure alignment.  This field ensures that the
+'padding' is necessary for structure alignment.  This field ensures that the
 'extended_modes' field is aligned on a 64-bit boundary.
 
 'extended_modes' is a bitfield that defines special functionality which has an
diff --git a/Documentation/rbtree.txt b/Documentation/rbtree.txt
index 7224459b469..aae8355d316 100644
--- a/Documentation/rbtree.txt
+++ b/Documentation/rbtree.txt
@@ -131,8 +131,8 @@ Example:
   	}
 
   	/* Add new node and rebalance tree. */
-  	rb_link_node(data->node, parent, new);
-  	rb_insert_color(data->node, root);
+  	rb_link_node(&data->node, parent, new);
+  	rb_insert_color(&data->node, root);
 
 	return TRUE;
   }
@@ -146,10 +146,10 @@ To remove an existing node from a tree, call:
 
 Example:
 
-  struct mytype *data = mysearch(mytree, "walrus");
+  struct mytype *data = mysearch(&mytree, "walrus");
 
   if (data) {
-  	rb_erase(data->node, mytree);
+  	rb_erase(&data->node, &mytree);
   	myfree(data);
   }
 
@@ -188,5 +188,5 @@ Example:
 
   struct rb_node *node;
   for (node = rb_first(&mytree); node; node = rb_next(node))
-  	printk("key=%s\n", rb_entry(node, int, keystring));
+	printk("key=%s\n", rb_entry(node, struct mytype, node)->keystring);
 
diff --git a/Documentation/rfkill.txt b/Documentation/rfkill.txt
index 4d3ee317a4a..1b74b5f30af 100644
--- a/Documentation/rfkill.txt
+++ b/Documentation/rfkill.txt
@@ -1,575 +1,136 @@
-rfkill - RF switch subsystem support
-====================================
+rfkill - RF kill switch support
+===============================
 
-1 Introduction
-2 Implementation details
-3 Kernel driver guidelines
-3.1 wireless device drivers
-3.2 platform/switch drivers
-3.3 input device drivers
-4 Kernel API
-5 Userspace support
+1. Introduction
+2. Implementation details
+3. Kernel driver guidelines
+4. Kernel API
+5. Userspace support
 
 
-1. Introduction:
+1. Introduction
 
-The rfkill switch subsystem exists to add a generic interface to circuitry that
-can enable or disable the signal output of a wireless *transmitter* of any
-type.  By far, the most common use is to disable radio-frequency transmitters.
+The rfkill subsystem provides a generic interface to disabling any radio
+transmitter in the system. When a transmitter is blocked, it shall not
+radiate any power.
 
-Note that disabling the signal output means that the the transmitter is to be
-made to not emit any energy when "blocked".  rfkill is not about blocking data
-transmissions, it is about blocking energy emission.
+The subsystem also provides the ability to react on button presses and
+disable all transmitters of a certain type (or all). This is intended for
+situations where transmitters need to be turned off, for example on
+aircraft.
 
-The rfkill subsystem offers support for keys and switches often found on
-laptops to enable wireless devices like WiFi and Bluetooth, so that these keys
-and switches actually perform an action in all wireless devices of a given type
-attached to the system.
 
-The buttons to enable and disable the wireless transmitters are important in
-situations where the user is for example using his laptop on a location where
-radio-frequency transmitters _must_ be disabled (e.g. airplanes).
 
-Because of this requirement, userspace support for the keys should not be made
-mandatory.  Because userspace might want to perform some additional smarter
-tasks when the key is pressed, rfkill provides userspace the possibility to
-take over the task to handle the key events.
-
-===============================================================================
-2: Implementation details
+2. Implementation details
 
 The rfkill subsystem is composed of various components: the rfkill class, the
 rfkill-input module (an input layer handler), and some specific input layer
 events.
 
-The rfkill class provides kernel drivers with an interface that allows them to
-know when they should enable or disable a wireless network device transmitter.
-This is enabled by the CONFIG_RFKILL Kconfig option.
-
-The rfkill class support makes sure userspace will be notified of all state
-changes on rfkill devices through uevents.  It provides a notification chain
-for interested parties in the kernel to also get notified of rfkill state
-changes in other drivers.  It creates several sysfs entries which can be used
-by userspace.  See section "Userspace support".
-
-The rfkill-input module provides the kernel with the ability to implement a
-basic response when the user presses a key or button (or toggles a switch)
-related to rfkill functionality.  It is an in-kernel implementation of default
-policy of reacting to rfkill-related input events and neither mandatory nor
-required for wireless drivers to operate.  It is enabled by the
-CONFIG_RFKILL_INPUT Kconfig option.
-
-rfkill-input is a rfkill-related events input layer handler.  This handler will
-listen to all rfkill key events and will change the rfkill state of the
-wireless devices accordingly.  With this option enabled userspace could either
-do nothing or simply perform monitoring tasks.
-
-The rfkill-input module also provides EPO (emergency power-off) functionality
-for all wireless transmitters.  This function cannot be overridden, and it is
-always active.  rfkill EPO is related to *_RFKILL_ALL input layer events.
-
-
-Important terms for the rfkill subsystem:
-
-In order to avoid confusion, we avoid the term "switch" in rfkill when it is
-referring to an electronic control circuit that enables or disables a
-transmitter.  We reserve it for the physical device a human manipulates
-(which is an input device, by the way):
-
-rfkill switch:
-
-	A physical device a human manipulates.  Its state can be perceived by
-	the kernel either directly (through a GPIO pin, ACPI GPE) or by its
-	effect on a rfkill line of a wireless device.
-
-rfkill controller:
-
-	A hardware circuit that controls the state of a rfkill line, which a
-	kernel driver can interact with *to modify* that state (i.e. it has
-	either write-only or read/write access).
-
-rfkill line:
-
-	An input channel (hardware or software) of a wireless device, which
-	causes a wireless transmitter to stop emitting energy (BLOCK) when it
-	is active.  Point of view is extremely important here: rfkill lines are
-	always seen from the PoV of a wireless device (and its driver).
-
-soft rfkill line/software rfkill line:
-
-	A rfkill line the wireless device driver can directly change the state
-	of.  Related to rfkill_state RFKILL_STATE_SOFT_BLOCKED.
-
-hard rfkill line/hardware rfkill line:
-
-	A rfkill line that works fully in hardware or firmware, and that cannot
-	be overridden by the kernel driver.  The hardware device or the
-	firmware just exports its status to the driver, but it is read-only.
-	Related to rfkill_state RFKILL_STATE_HARD_BLOCKED.
-
-The enum rfkill_state describes the rfkill state of a transmitter:
-
-When a rfkill line or rfkill controller is in the RFKILL_STATE_UNBLOCKED state,
-the wireless transmitter (radio TX circuit for example) is *enabled*.  When the
-it is in the RFKILL_STATE_SOFT_BLOCKED or RFKILL_STATE_HARD_BLOCKED, the
-wireless transmitter is to be *blocked* from operating.
-
-RFKILL_STATE_SOFT_BLOCKED indicates that a call to toggle_radio() can change
-that state.  RFKILL_STATE_HARD_BLOCKED indicates that a call to toggle_radio()
-will not be able to change the state and will return with a suitable error if
-attempts are made to set the state to RFKILL_STATE_UNBLOCKED.
-
-RFKILL_STATE_HARD_BLOCKED is used by drivers to signal that the device is
-locked in the BLOCKED state by a hardwire rfkill line (typically an input pin
-that, when active, forces the transmitter to be disabled) which the driver
-CANNOT override.
-
-Full rfkill functionality requires two different subsystems to cooperate: the
-input layer and the rfkill class.  The input layer issues *commands* to the
-entire system requesting that devices registered to the rfkill class change
-state.  The way this interaction happens is not complex, but it is not obvious
-either:
-
-Kernel Input layer:
-
-	* Generates KEY_WWAN, KEY_WLAN, KEY_BLUETOOTH, SW_RFKILL_ALL, and
-	  other such events when the user presses certain keys, buttons, or
-	  toggles certain physical switches.
-
-	THE INPUT LAYER IS NEVER USED TO PROPAGATE STATUS, NOTIFICATIONS OR THE
-	KIND OF STUFF AN ON-SCREEN-DISPLAY APPLICATION WOULD REPORT.  It is
-	used to issue *commands* for the system to change behaviour, and these
-	commands may or may not be carried out by some kernel driver or
-	userspace application.  It follows that doing user feedback based only
-	on input events is broken, as there is no guarantee that an input event
-	will be acted upon.
-
-	Most wireless communication device drivers implementing rfkill
-	functionality MUST NOT generate these events, and have no reason to
-	register themselves with the input layer.  Doing otherwise is a common
-	misconception.  There is an API to propagate rfkill status change
-	information, and it is NOT the input layer.
-
-rfkill class:
-
-	* Calls a hook in a driver to effectively change the wireless
-	  transmitter state;
-	* Keeps track of the wireless transmitter state (with help from
-	  the driver);
-	* Generates userspace notifications (uevents) and a call to a
-	  notification chain (kernel) when there is a wireless transmitter
-	  state change;
-	* Connects a wireless communications driver with the common rfkill
-	  control system, which, for example, allows actions such as
-	  "switch all bluetooth devices offline" to be carried out by
-	  userspace or by rfkill-input.
-
-	THE RFKILL CLASS NEVER ISSUES INPUT EVENTS.  THE RFKILL CLASS DOES
-	NOT LISTEN TO INPUT EVENTS.  NO DRIVER USING THE RFKILL CLASS SHALL
-	EVER LISTEN TO, OR ACT ON RFKILL INPUT EVENTS.  Doing otherwise is
-	a layering violation.
-
-	Most wireless data communication drivers in the kernel have just to
-	implement the rfkill class API to work properly.  Interfacing to the
-	input layer is not often required (and is very often a *bug*) on
-	wireless drivers.
-
-	Platform drivers often have to attach to the input layer to *issue*
-	(but never to listen to) rfkill events for rfkill switches, and also to
-	the rfkill class to export a control interface for the platform rfkill
-	controllers to the rfkill subsystem.  This does NOT mean the rfkill
-	switch is attached to a rfkill class (doing so is almost always wrong).
-	It just means the same kernel module is the driver for different
-	devices (rfkill switches and rfkill controllers).
-
-
-Userspace input handlers (uevents) or kernel input handlers (rfkill-input):
-
-	* Implements the policy of what should happen when one of the input
-	  layer events related to rfkill operation is received.
-	* Uses the sysfs interface (userspace) or private rfkill API calls
-	  to tell the devices registered with the rfkill class to change
-	  their state (i.e. translates the input layer event into real
-	  action).
-
-	* rfkill-input implements EPO by handling EV_SW SW_RFKILL_ALL 0
-	  (power off all transmitters) in a special way: it ignores any
-	  overrides and local state cache and forces all transmitters to the
-	  RFKILL_STATE_SOFT_BLOCKED state (including those which are already
-	  supposed to be BLOCKED).
-	* rfkill EPO will remain active until rfkill-input receives an
-	  EV_SW SW_RFKILL_ALL 1 event.  While the EPO is active, transmitters
-	  are locked in the blocked state (rfkill will refuse to unblock them).
-	* rfkill-input implements different policies that the user can
-	  select for handling EV_SW SW_RFKILL_ALL 1.  It will unlock rfkill,
-	  and either do nothing (leave transmitters blocked, but now unlocked),
-	  restore the transmitters to their state before the EPO, or unblock
-	  them all.
-
-Userspace uevent handler or kernel platform-specific drivers hooked to the
-rfkill notifier chain:
-
-	* Taps into the rfkill notifier chain or to KOBJ_CHANGE uevents,
-	  in order to know when a device that is registered with the rfkill
-	  class changes state;
-	* Issues feedback notifications to the user;
-	* In the rare platforms where this is required, synthesizes an input
-	  event to command all *OTHER* rfkill devices to also change their
-	  statues when a specific rfkill device changes state.
-
-
-===============================================================================
-3: Kernel driver guidelines
-
-Remember: point-of-view is everything for a driver that connects to the rfkill
-subsystem.  All the details below must be measured/perceived from the point of
-view of the specific driver being modified.
-
-The first thing one needs to know is whether his driver should be talking to
-the rfkill class or to the input layer.  In rare cases (platform drivers), it
-could happen that you need to do both, as platform drivers often handle a
-variety of devices in the same driver.
-
-Do not mistake input devices for rfkill controllers.  The only type of "rfkill
-switch" device that is to be registered with the rfkill class are those
-directly controlling the circuits that cause a wireless transmitter to stop
-working (or the software equivalent of them), i.e. what we call a rfkill
-controller.  Every other kind of "rfkill switch" is just an input device and
-MUST NOT be registered with the rfkill class.
-
-A driver should register a device with the rfkill class when ALL of the
-following conditions are met (they define a rfkill controller):
-
-1. The device is/controls a data communications wireless transmitter;
-
-2. The kernel can interact with the hardware/firmware to CHANGE the wireless
-   transmitter state (block/unblock TX operation);
-
-3. The transmitter can be made to not emit any energy when "blocked":
-   rfkill is not about blocking data transmissions, it is about blocking
-   energy emission;
-
-A driver should register a device with the input subsystem to issue
-rfkill-related events (KEY_WLAN, KEY_BLUETOOTH, KEY_WWAN, KEY_WIMAX,
-SW_RFKILL_ALL, etc) when ALL of the folowing conditions are met:
-
-1. It is directly related to some physical device the user interacts with, to
-   command the O.S./firmware/hardware to enable/disable a data communications
-   wireless transmitter.
-
-   Examples of the physical device are: buttons, keys and switches the user
-   will press/touch/slide/switch to enable or disable the wireless
-   communication device.
-
-2. It is NOT slaved to another device, i.e. there is no other device that
-   issues rfkill-related input events in preference to this one.
-
-   Please refer to the corner cases and examples section for more details.
-
-When in doubt, do not issue input events.  For drivers that should generate
-input events in some platforms, but not in others (e.g. b43), the best solution
-is to NEVER generate input events in the first place.  That work should be
-deferred to a platform-specific kernel module (which will know when to generate
-events through the rfkill notifier chain) or to userspace.  This avoids the
-usual maintenance problems with DMI whitelisting.
-
-
-Corner cases and examples:
-====================================
-
-1. If the device is an input device that, because of hardware or firmware,
-causes wireless transmitters to be blocked regardless of the kernel's will, it
-is still just an input device, and NOT to be registered with the rfkill class.
-
-2. If the wireless transmitter switch control is read-only, it is an input
-device and not to be registered with the rfkill class (and maybe not to be made
-an input layer event source either, see below).
-
-3. If there is some other device driver *closer* to the actual hardware the
-user interacted with (the button/switch/key) to issue an input event, THAT is
-the device driver that should be issuing input events.
-
-E.g:
-  [RFKILL slider switch] -- [GPIO hardware] -- [WLAN card rf-kill input]
-                           (platform driver)    (wireless card driver)
-
-The user is closer to the RFKILL slide switch plaform driver, so the driver
-which must issue input events is the platform driver looking at the GPIO
-hardware, and NEVER the wireless card driver (which is just a slave).  It is
-very likely that there are other leaves than just the WLAN card rf-kill input
-(e.g. a bluetooth card, etc)...
-
-On the other hand, some embedded devices do this:
-
-  [RFKILL slider switch] -- [WLAN card rf-kill input]
-                             (wireless card driver)
-
-In this situation, the wireless card driver *could* register itself as an input
-device and issue rf-kill related input events... but in order to AVOID the need
-for DMI whitelisting, the wireless card driver does NOT do it.  Userspace (HAL)
-or a platform driver (that exists only on these embedded devices) will do the
-dirty job of issuing the input events.
-
-
-COMMON MISTAKES in kernel drivers, related to rfkill:
-====================================
-
-1. NEVER confuse input device keys and buttons with input device switches.
-
-  1a. Switches are always set or reset.  They report the current state
-      (on position or off position).
-
-  1b. Keys and buttons are either in the pressed or not-pressed state, and
-      that's it.  A "button" that latches down when you press it, and
-      unlatches when you press it again is in fact a switch as far as input
-      devices go.
-
-Add the SW_* events you need for switches, do NOT try to emulate a button using
-KEY_* events just because there is no such SW_* event yet.  Do NOT try to use,
-for example, KEY_BLUETOOTH when you should be using SW_BLUETOOTH instead.
-
-2. Input device switches (sources of EV_SW events) DO store their current state
-(so you *must* initialize it by issuing a gratuitous input layer event on
-driver start-up and also when resuming from sleep), and that state CAN be
-queried from userspace through IOCTLs.  There is no sysfs interface for this,
-but that doesn't mean you should break things trying to hook it to the rfkill
-class to get a sysfs interface :-)
-
-3. Do not issue *_RFKILL_ALL events by default, unless you are sure it is the
-correct event for your switch/button.  These events are emergency power-off
-events when they are trying to turn the transmitters off.  An example of an
-input device which SHOULD generate *_RFKILL_ALL events is the wireless-kill
-switch in a laptop which is NOT a hotkey, but a real sliding/rocker switch.
-An example of an input device which SHOULD NOT generate *_RFKILL_ALL events by
-default, is any sort of hot key that is type-specific (e.g. the one for WLAN).
-
-
-3.1 Guidelines for wireless device drivers
-------------------------------------------
-
-(in this text, rfkill->foo means the foo field of struct rfkill).
-
-1. Each independent transmitter in a wireless device (usually there is only one
-transmitter per device) should have a SINGLE rfkill class attached to it.
-
-2. If the device does not have any sort of hardware assistance to allow the
-driver to rfkill the device, the driver should emulate it by taking all actions
-required to silence the transmitter.
-
-3. If it is impossible to silence the transmitter (i.e. it still emits energy,
-even if it is just in brief pulses, when there is no data to transmit and there
-is no hardware support to turn it off) do NOT lie to the users.  Do not attach
-it to a rfkill class.  The rfkill subsystem does not deal with data
-transmission, it deals with energy emission.  If the transmitter is emitting
-energy, it is not blocked in rfkill terms.
-
-4. It doesn't matter if the device has multiple rfkill input lines affecting
-the same transmitter, their combined state is to be exported as a single state
-per transmitter (see rule 1).
-
-This rule exists because users of the rfkill subsystem expect to get (and set,
-when possible) the overall transmitter rfkill state, not of a particular rfkill
-line.
-
-5. The wireless device driver MUST NOT leave the transmitter enabled during
-suspend and hibernation unless:
+The rfkill class is provided for kernel drivers to register their radio
+transmitter with the kernel, provide methods for turning it on and off and,
+optionally, letting the system know about hardware-disabled states that may
+be implemented on the device. This code is enabled with the CONFIG_RFKILL
+Kconfig option, which drivers can "select".
 
-	5.1. The transmitter has to be enabled for some sort of functionality
-	like wake-on-wireless-packet or autonomous packed forwarding in a mesh
-	network, and that functionality is enabled for this suspend/hibernation
-	cycle.
+The rfkill class code also notifies userspace of state changes, this is
+achieved via uevents. It also provides some sysfs files for userspace to
+check the status of radio transmitters. See the "Userspace support" section
+below.
 
-AND
 
-	5.2. The device was not on a user-requested BLOCKED state before
-	the suspend (i.e. the driver must NOT unblock a device, not even
-	to support wake-on-wireless-packet or remain in the mesh).
+The rfkill-input code implements a basic response to rfkill buttons -- it
+implements turning on/off all devices of a certain class (or all).
 
-In other words, there is absolutely no allowed scenario where a driver can
-automatically take action to unblock a rfkill controller (obviously, this deals
-with scenarios where soft-blocking or both soft and hard blocking is happening.
-Scenarios where hardware rfkill lines are the only ones blocking the
-transmitter are outside of this rule, since the wireless device driver does not
-control its input hardware rfkill lines in the first place).
+When the device is hard-blocked (either by a call to rfkill_set_hw_state()
+or from query_hw_block) set_block() will be invoked but drivers can well
+ignore the method call since they can use the return value of the function
+rfkill_set_hw_state() to sync the software state instead of keeping track
+of calls to set_block().
 
-6. During resume, rfkill will try to restore its previous state.
 
-7. After a rfkill class is suspended, it will *not* call rfkill->toggle_radio
-until it is resumed.
+The entire functionality is spread over more than one subsystem:
 
+ * The kernel input layer generates KEY_WWAN, KEY_WLAN etc. and
+   SW_RFKILL_ALL -- when the user presses a button. Drivers for radio
+   transmitters generally do not register to the input layer, unless the
+   device really provides an input device (i.e. a button that has no
+   effect other than generating a button press event)
 
-Example of a WLAN wireless driver connected to the rfkill subsystem:
---------------------------------------------------------------------
+ * The rfkill-input code hooks up to these events and switches the soft-block
+   of the various radio transmitters, depending on the button type.
 
-A certain WLAN card has one input pin that causes it to block the transmitter
-and makes the status of that input pin available (only for reading!) to the
-kernel driver.  This is a hard rfkill input line (it cannot be overridden by
-the kernel driver).
+ * The rfkill drivers turn off/on their transmitters as requested.
 
-The card also has one PCI register that, if manipulated by the driver, causes
-it to block the transmitter.  This is a soft rfkill input line.
+ * The rfkill class will generate userspace notifications (uevents) to tell
+   userspace what the current state is.
 
-It has also a thermal protection circuitry that shuts down its transmitter if
-the card overheats, and makes the status of that protection available (only for
-reading!) to the kernel driver.  This is also a hard rfkill input line.
 
-If either one of these rfkill lines are active, the transmitter is blocked by
-the hardware and forced offline.
 
-The driver should allocate and attach to its struct device *ONE* instance of
-the rfkill class (there is only one transmitter).
+3. Kernel driver guidelines
 
-It can implement the get_state() hook, and return RFKILL_STATE_HARD_BLOCKED if
-either one of its two hard rfkill input lines are active.  If the two hard
-rfkill lines are inactive, it must return RFKILL_STATE_SOFT_BLOCKED if its soft
-rfkill input line is active.  Only if none of the rfkill input lines are
-active, will it return RFKILL_STATE_UNBLOCKED.
 
-Since the device has a hardware rfkill line, it IS subject to state changes
-external to rfkill.  Therefore, the driver must make sure that it calls
-rfkill_force_state() to keep the status always up-to-date, and it must do a
-rfkill_force_state() on resume from sleep.
+Drivers for radio transmitters normally implement only the rfkill class.
+These drivers may not unblock the transmitter based on own decisions, they
+should act on information provided by the rfkill class only.
 
-Every time the driver gets a notification from the card that one of its rfkill
-lines changed state (polling might be needed on badly designed cards that don't
-generate interrupts for such events), it recomputes the rfkill state as per
-above, and calls rfkill_force_state() to update it.
+Platform drivers might implement input devices if the rfkill button is just
+that, a button. If that button influences the hardware then you need to
+implement an rfkill class instead. This also applies if the platform provides
+a way to turn on/off the transmitter(s).
 
-The driver should implement the toggle_radio() hook, that:
+During suspend/hibernation, transmitters should only be left enabled when
+wake-on wlan or similar functionality requires it and the device wasn't
+blocked before suspend/hibernate. Note that it may be necessary to update
+the rfkill subsystem's idea of what the current state is at resume time if
+the state may have changed over suspend.
 
-1. Returns an error if one of the hardware rfkill lines are active, and the
-caller asked for RFKILL_STATE_UNBLOCKED.
 
-2. Activates the soft rfkill line if the caller asked for state
-RFKILL_STATE_SOFT_BLOCKED.  It should do this even if one of the hard rfkill
-lines are active, effectively double-blocking the transmitter.
 
-3. Deactivates the soft rfkill line if none of the hardware rfkill lines are
-active and the caller asked for RFKILL_STATE_UNBLOCKED.
-
-===============================================================================
-4: Kernel API
+4. Kernel API
 
 To build a driver with rfkill subsystem support, the driver should depend on
-(or select) the Kconfig symbol RFKILL; it should _not_ depend on RKFILL_INPUT.
+(or select) the Kconfig symbol RFKILL.
 
 The hardware the driver talks to may be write-only (where the current state
 of the hardware is unknown), or read-write (where the hardware can be queried
 about its current state).
 
-The rfkill class will call the get_state hook of a device every time it needs
-to know the *real* current state of the hardware.  This can happen often, but
-it does not do any polling, so it is not enough on hardware that is subject
-to state changes outside of the rfkill subsystem.
-
-Therefore, calling rfkill_force_state() when a state change happens is
-mandatory when the device has a hardware rfkill line, or when something else
-like the firmware could cause its state to be changed without going through the
-rfkill class.
-
-Some hardware provides events when its status changes.  In these cases, it is
-best for the driver to not provide a get_state hook, and instead register the
-rfkill class *already* with the correct status, and keep it updated using
-rfkill_force_state() when it gets an event from the hardware.
-
-rfkill_force_state() must be used on the device resume handlers to update the
-rfkill status, should there be any chance of the device status changing during
-the sleep.
-
-There is no provision for a statically-allocated rfkill struct.  You must
-use rfkill_allocate() to allocate one.
-
-You should:
-	- rfkill_allocate()
-	- modify rfkill fields (flags, name)
-	- modify state to the current hardware state (THIS IS THE ONLY TIME
-	  YOU CAN ACCESS state DIRECTLY)
-	- rfkill_register()
-
-The only way to set a device to the RFKILL_STATE_HARD_BLOCKED state is through
-a suitable return of get_state() or through rfkill_force_state().
+Calling rfkill_set_hw_state() when a state change happens is required from
+rfkill drivers that control devices that can be hard-blocked unless they also
+assign the poll_hw_block() callback (then the rfkill core will poll the
+device). Don't do this unless you cannot get the event in any other way.
 
-When a device is in the RFKILL_STATE_HARD_BLOCKED state, the only way to switch
-it to a different state is through a suitable return of get_state() or through
-rfkill_force_state().
 
-If toggle_radio() is called to set a device to state RFKILL_STATE_SOFT_BLOCKED
-when that device is already at the RFKILL_STATE_HARD_BLOCKED state, it should
-not return an error.  Instead, it should try to double-block the transmitter,
-so that its state will change from RFKILL_STATE_HARD_BLOCKED to
-RFKILL_STATE_SOFT_BLOCKED should the hardware blocking cease.
-
-Please refer to the source for more documentation.
-
-===============================================================================
-5: Userspace support
-
-rfkill devices issue uevents (with an action of "change"), with the following
-environment variables set:
-
-RFKILL_NAME
-RFKILL_STATE
-RFKILL_TYPE
 
-The ABI for these variables is defined by the sysfs attributes.  It is best
-to take a quick look at the source to make sure of the possible values.
+5. Userspace support
 
-It is expected that HAL will trap those, and bridge them to DBUS, etc.  These
-events CAN and SHOULD be used to give feedback to the user about the rfkill
-status of the system.
-
-Input devices may issue events that are related to rfkill.  These are the
-various KEY_* events and SW_* events supported by rfkill-input.c.
-
-******IMPORTANT******
-When rfkill-input is ACTIVE, userspace is NOT TO CHANGE THE STATE OF AN RFKILL
-SWITCH IN RESPONSE TO AN INPUT EVENT also handled by rfkill-input, unless it
-has set to true the user_claim attribute for that particular switch.  This rule
-is *absolute*; do NOT violate it.
-******IMPORTANT******
-
-Userspace must not assume it is the only source of control for rfkill switches.
-Their state CAN and WILL change due to firmware actions, direct user actions,
-and the rfkill-input EPO override for *_RFKILL_ALL.
-
-When rfkill-input is not active, userspace must initiate a rfkill status
-change by writing to the "state" attribute in order for anything to happen.
-
-Take particular care to implement EV_SW SW_RFKILL_ALL properly.  When that
-switch is set to OFF, *every* rfkill device *MUST* be immediately put into the
-RFKILL_STATE_SOFT_BLOCKED state, no questions asked.
-
-The following sysfs entries will be created:
+The following sysfs entries exist for every rfkill device:
 
 	name: Name assigned by driver to this key (interface or driver name).
 	type: Name of the key type ("wlan", "bluetooth", etc).
 	state: Current state of the transmitter
 		0: RFKILL_STATE_SOFT_BLOCKED
-			transmitter is forced off, but one can override it
-			by a write to the state attribute;
+			transmitter is turned off by software
 		1: RFKILL_STATE_UNBLOCKED
-			transmiter is NOT forced off, and may operate if
-			all other conditions for such operation are met
-			(such as interface is up and configured, etc);
+			transmitter is (potentially) active
 		2: RFKILL_STATE_HARD_BLOCKED
 			transmitter is forced off by something outside of
-			the driver's control.  One cannot set a device to
-			this state through writes to the state attribute;
-	claim: 1: Userspace handles events, 0: Kernel handles events
-
-Both the "state" and "claim" entries are also writable. For the "state" entry
-this means that when 1 or 0 is written, the device rfkill state (if not yet in
-the requested state), will be will be toggled accordingly.
-
-For the "claim" entry writing 1 to it means that the kernel no longer handles
-key events even though RFKILL_INPUT input was enabled. When "claim" has been
-set to 0, userspace should make sure that it listens for the input events or
-check the sysfs "state" entry regularly to correctly perform the required tasks
-when the rkfill key is pressed.
-
-A note about input devices and EV_SW events:
-
-In order to know the current state of an input device switch (like
-SW_RFKILL_ALL), you will need to use an IOCTL.  That information is not
-available through sysfs in a generic way at this time, and it is not available
-through the rfkill class AT ALL.
+			the driver's control.
+	claim: 0: Kernel handles events (currently always reads that value)
+
+rfkill devices also issue uevents (with an action of "change"), with the
+following environment variables set:
+
+RFKILL_NAME
+RFKILL_STATE
+RFKILL_TYPE
+
+The contents of these variables corresponds to the "name", "state" and
+"type" sysfs files explained above.
+
+An alternative userspace interface exists as a misc device /dev/rfkill,
+which allows userspace to obtain and set the state of rfkill devices and
+sets of devices. It also notifies userspace about device addition and
+removal. The API is a simple read/write API that is defined in
+linux/rfkill.h.
diff --git a/Documentation/s390/Debugging390.txt b/Documentation/s390/Debugging390.txt
index 10711d9f078..1eb576a023b 100644
--- a/Documentation/s390/Debugging390.txt
+++ b/Documentation/s390/Debugging390.txt
@@ -1984,7 +1984,7 @@ break *$pc
 
 break *0x400618
 
-heres a really useful one for large programs
+Here's a really useful one for large programs
 rbr
 Set a breakpoint for all functions matching REGEXP
 e.g.
@@ -2211,7 +2211,7 @@ Breakpoint 2 at 0x4d87a4: file top.c, line 2609.
 #5  0x51692c in readline_internal () at readline.c:521
 #6  0x5164fe in readline (prompt=0x7ffff810 "\177ÿøx\177ÿ÷Ø\177ÿøxÀ")
     at readline.c:349
-#7  0x4d7a8a in command_line_input (prrompt=0x564420 "(gdb) ", repeat=1,
+#7  0x4d7a8a in command_line_input (prompt=0x564420 "(gdb) ", repeat=1,
     annotation_suffix=0x4d6b44 "prompt") at top.c:2091
 #8  0x4d6cf0 in command_loop () at top.c:1345
 #9  0x4e25bc in main (argc=1, argv=0x7ffffdf4) at main.c:635
diff --git a/Documentation/scheduler/sched-nice-design.txt b/Documentation/scheduler/sched-nice-design.txt
index e2bae5a577e..3ac1e46d536 100644
--- a/Documentation/scheduler/sched-nice-design.txt
+++ b/Documentation/scheduler/sched-nice-design.txt
@@ -55,7 +55,7 @@ To sum it up: we always wanted to make nice levels more consistent, but
 within the constraints of HZ and jiffies and their nasty design level
 coupling to timeslices and granularity it was not really viable.
 
-The second (less frequent but still periodically occuring) complaint
+The second (less frequent but still periodically occurring) complaint
 about Linux's nice level support was its assymetry around the origo
 (which you can see demonstrated in the picture above), or more
 accurately: the fact that nice level behavior depended on the _absolute_
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index 5ba4d3fc625..1df7f9cdab0 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -4,6 +4,7 @@
 CONTENTS
 ========
 
+0. WARNING
 1. Overview
   1.1 The problem
   1.2 The solution
@@ -14,6 +15,23 @@ CONTENTS
 3. Future plans
 
 
+0. WARNING
+==========
+
+ Fiddling with these settings can result in an unstable system, the knobs are
+ root only and assumes root knows what he is doing.
+
+Most notable:
+
+ * very small values in sched_rt_period_us can result in an unstable
+   system when the period is smaller than either the available hrtimer
+   resolution, or the time it takes to handle the budget refresh itself.
+
+ * very small values in sched_rt_runtime_us can result in an unstable
+   system when the runtime is so small the system has difficulty making
+   forward progress (NOTE: the migration thread and kstopmachine both
+   are real-time processes).
+
 1. Overview
 ===========
 
@@ -169,7 +187,7 @@ get their allocated time.
 
 Implementing SCHED_EDF might take a while to complete. Priority Inheritance is
 the biggest challenge as the current linux PI infrastructure is geared towards
-the limited static priority levels 0-139. With deadline scheduling you need to
+the limited static priority levels 0-99. With deadline scheduling you need to
 do deadline inheritance (since priority is inversely proportional to the
 deadline delta (deadline - now).
 
diff --git a/Documentation/scsi/aic79xx.txt b/Documentation/scsi/aic79xx.txt
index 683ccae00ad..c014eccaf19 100644
--- a/Documentation/scsi/aic79xx.txt
+++ b/Documentation/scsi/aic79xx.txt
@@ -194,7 +194,7 @@ The following information is available in this file:
           - Packetized SCSI Protocol at 160MB/s and 320MB/s
           - Quick Arbitration Selection (QAS)
           - Retained Training Information (Rev B. ASIC only)
-        - Interrupt Coalessing
+        - Interrupt Coalescing
         - Initiator Mode (target mode not currently 
           supported)
         - Support for the PCI-X standard up to 133MHz
diff --git a/Documentation/scsi/ncr53c8xx.txt b/Documentation/scsi/ncr53c8xx.txt
index 230e30846ef..08e2b4d04aa 100644
--- a/Documentation/scsi/ncr53c8xx.txt
+++ b/Documentation/scsi/ncr53c8xx.txt
@@ -206,7 +206,7 @@ of MOVE MEMORY instructions.
 The 896 and the 895A allows handling of the phase mismatch context from 
 SCRIPTS (avoids the phase mismatch interrupt that stops the SCSI processor 
 until the C code has saved the context of the transfer).
-Implementing this without using LOAD/STORE instructions would be painfull 
+Implementing this without using LOAD/STORE instructions would be painful 
 and I didn't even want to try it.
 
 The 896 chip supports 64 bit PCI transactions and addressing, while the 
@@ -240,7 +240,7 @@ characteristics. This feature may also reduce average command latency.
 In order to really gain advantage of this feature, devices must have 
 a reasonable cache size (No miracle is to be expected for a low-end 
 hard disk with 128 KB or less).
-Some kown SCSI devices do not properly support tagged command queuing.
+Some known SCSI devices do not properly support tagged command queuing.
 Generally, firmware revisions that fix this kind of problems are available 
 at respective vendor web/ftp sites.
 All I can say is that the hard disks I use on my machines behave well with 
diff --git a/Documentation/scsi/sym53c8xx_2.txt b/Documentation/scsi/sym53c8xx_2.txt
index 49ea5c58c6b..eb9a7b905b6 100644
--- a/Documentation/scsi/sym53c8xx_2.txt
+++ b/Documentation/scsi/sym53c8xx_2.txt
@@ -206,7 +206,7 @@ characteristics. This feature may also reduce average command latency.
 In order to really gain advantage of this feature, devices must have 
 a reasonable cache size (No miracle is to be expected for a low-end 
 hard disk with 128 KB or less).
-Some kown old SCSI devices do not properly support tagged command queuing.
+Some known old SCSI devices do not properly support tagged command queuing.
 Generally, firmware revisions that fix this kind of problems are available 
 at respective vendor web/ftp sites.
 All I can say is that I never have had problem with tagged queuing using 
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index 012858d2b11..4252697a95d 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -460,6 +460,25 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
 
     The power-management is supported.
 
+  Module snd-ctxfi
+  ----------------
+
+    Module for Creative Sound Blaster X-Fi boards (20k1 / 20k2 chips)
+	* Creative Sound Blaster X-Fi Titanium Fatal1ty Champion Series
+	* Creative Sound Blaster X-Fi Titanium Fatal1ty Professional Series
+	* Creative Sound Blaster X-Fi Titanium Professional Audio
+	* Creative Sound Blaster X-Fi Titanium
+	* Creative Sound Blaster X-Fi Elite Pro
+	* Creative Sound Blaster X-Fi Platinum
+	* Creative Sound Blaster X-Fi Fatal1ty
+	* Creative Sound Blaster X-Fi XtremeGamer
+	* Creative Sound Blaster X-Fi XtremeMusic
+
+    reference_rate	- reference sample rate, 44100 or 48000 (default)
+    multiple		- multiple to ref. sample rate, 1 or 2 (default)
+
+    This module supports multiple cards.
+
   Module snd-darla20
   ------------------
 
@@ -754,7 +773,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
     single_cmd  - Use single immediate commands to communicate with
 		codecs (for debugging only)
     enable_msi	- Enable Message Signaled Interrupt (MSI) (default = off)
-    power_save	- Automatic power-saving timtout (in second, 0 =
+    power_save	- Automatic power-saving timeout (in second, 0 =
 		disable)
     power_save_controller - Reset HD-audio controller in power-saving mode
 		(default = on)
@@ -925,6 +944,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
 			* Onkyo SE-90PCI
 			* Onkyo SE-200PCI
 			* ESI Juli@
+			* ESI Maya44
 			* Hercules Fortissimo IV
 			* EGO-SYS WaveTerminal 192M
 
@@ -933,7 +953,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
 		  prodigy71xt, prodigy71hifi, prodigyhd2, prodigy192,
 		  juli, aureon51, aureon71, universe, ap192, k8x800,
 		  phase22, phase28, ms300, av710, se200pci, se90pci,
-		  fortissimo4, sn25p, WT192M
+		  fortissimo4, sn25p, WT192M, maya44
 
     This module supports multiple cards and autoprobe.
 
@@ -1093,6 +1113,13 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
     This module supports multiple cards.
     The driver requires the firmware loader support on kernel.
 
+  Module snd-lx6464es
+  -------------------
+
+    Module for Digigram LX6464ES boards
+
+    This module supports multiple cards.
+
   Module snd-maestro3
   -------------------
 
@@ -1543,13 +1570,15 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
   Module snd-sc6000
   -----------------
 
-    Module for Gallant SC-6000 soundcard.
+    Module for Gallant SC-6000 soundcard and later models: SC-6600
+    and SC-7000.
 
     port	- Port # (0x220 or 0x240)
     mss_port	- MSS Port # (0x530 or 0xe80)
     irq		- IRQ # (5,7,9,10,11)
     mpu_irq	- MPU-401 IRQ # (5,7,9,10) ,0 - no MPU-401 irq
     dma		- DMA # (1,3,0)
+    joystick	- Enable gameport - 0 = disable (default), 1 = enable
 
     This module supports multiple cards.
 
@@ -1859,7 +1888,8 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
   -------------------
 
     Module for sound cards based on the Asus AV100/AV200 chips,
-    i.e., Xonar D1, DX, D2, D2X, HDAV1.3 (Deluxe), and Essence STX.
+    i.e., Xonar D1, DX, D2, D2X, HDAV1.3 (Deluxe), Essence ST
+    (Deluxe) and Essence STX.
 
     This module supports autoprobe and multiple cards.
 
diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt
index 8eec05bc079..de8e10a9410 100644
--- a/Documentation/sound/alsa/HD-Audio-Models.txt
+++ b/Documentation/sound/alsa/HD-Audio-Models.txt
@@ -36,6 +36,7 @@ ALC260
   acer		Acer TravelMate
   will		Will laptops (PB V7900)
   replacer	Replacer 672V
+  favorit100	Maxdata Favorit 100XS
   basic		fixed pin assignment (old default model)
   test		for testing/debugging purpose, almost all controls can
 		adjusted.  Appearing only when compiled with
@@ -85,10 +86,11 @@ ALC269
   eeepc-p703	ASUS Eeepc P703 P900A
   eeepc-p901	ASUS Eeepc P901 S101
   fujitsu	FSC Amilo
+  lifebook	Fujitsu Lifebook S6420
   auto		auto-config reading BIOS (default)
 
-ALC662/663
-==========
+ALC662/663/272
+==============
   3stack-dig	3-stack (2-channel) with SPDIF
   3stack-6ch	 3-stack (6-channel)
   3stack-6ch-dig 3-stack (6-channel) with SPDIF
@@ -107,6 +109,9 @@ ALC662/663
   asus-mode4	ASUS
   asus-mode5	ASUS
   asus-mode6	ASUS
+  dell		Dell with ALC272
+  dell-zm1	Dell ZM1 with ALC272
+  samsung-nc10	Samsung NC10 mini notebook
   auto		auto-config reading BIOS (default)
 
 ALC882/885
@@ -118,6 +123,7 @@ ALC882/885
   asus-a7j	ASUS A7J
   asus-a7m	ASUS A7M
   macpro	MacPro support
+  mb5		Macbook 5,1
   mbp3		Macbook Pro rev3
   imac24	iMac 24'' with jack detection
   w2jc		ASUS W2JC
@@ -133,10 +139,12 @@ ALC883/888
   acer		Acer laptops (Travelmate 3012WTMi, Aspire 5600, etc)
   acer-aspire	Acer Aspire 9810
   acer-aspire-4930g Acer Aspire 4930G
+  acer-aspire-8930g Acer Aspire 8930G
   medion	Medion Laptops
   medion-md2	Medion MD2
   targa-dig	Targa/MSI
-  targa-2ch-dig	Targs/MSI with 2-channel
+  targa-2ch-dig	Targa/MSI with 2-channel
+  targa-8ch-dig Targa/MSI with 8-channel (MSI GX620)
   laptop-eapd   3-jack with SPDIF I/O and EAPD (Clevo M540JE, M550JE)
   lenovo-101e	Lenovo 101E
   lenovo-nb0763	Lenovo NB0763
@@ -150,6 +158,9 @@ ALC883/888
   fujitsu-pi2515 Fujitsu AMILO Pi2515
   fujitsu-xa3530 Fujitsu AMILO XA3530
   3stack-6ch-intel Intel DG33* boards
+  asus-p5q	ASUS P5Q-EM boards
+  mb31		MacBook 3,1
+  sony-vaio-tt  Sony VAIO TT
   auto		auto-config reading BIOS (default)
 
 ALC861/660
@@ -334,6 +345,7 @@ STAC9227/9228/9229/927x
   ref-no-jd	Reference board without HP/Mic jack detection
   3stack	D965 3stack
   5stack	D965 5stack + SPDIF
+  5stack-no-fp	D965 5stack without front panel
   dell-3stack	Dell Dimension E520
   dell-bios	Fixes with Dell BIOS setup
   auto		BIOS setup (default)
@@ -347,6 +359,7 @@ STAC92HD71B*
   hp-m4		HP mini 1000
   hp-dv5	HP dv series
   hp-hdx	HP HDX series
+  hp-dv4-1222nr	HP dv4-1222nr (with LED support)
   auto		BIOS setup (default)
 
 STAC92HD73*
diff --git a/Documentation/sound/alsa/HD-Audio.txt b/Documentation/sound/alsa/HD-Audio.txt
index 88b7433d2f1..71ac995b191 100644
--- a/Documentation/sound/alsa/HD-Audio.txt
+++ b/Documentation/sound/alsa/HD-Audio.txt
@@ -16,7 +16,7 @@ methods for the	HD-audio hardware.
 The HD-audio component consists of two parts: the controller chip and 
 the codec chips on the HD-audio bus.  Linux provides a single driver
 for all controllers, snd-hda-intel.  Although the driver name contains
-a word of a well-known harware vendor, it's not specific to it but for
+a word of a well-known hardware vendor, it's not specific to it but for
 all controller chips by other companies.  Since the HD-audio
 controllers are supposed to be compatible, the single snd-hda-driver
 should work in most cases.  But, not surprisingly, there are known
diff --git a/Documentation/sound/alsa/Procfile.txt b/Documentation/sound/alsa/Procfile.txt
index bba2dbb79d8..381908d8ca4 100644
--- a/Documentation/sound/alsa/Procfile.txt
+++ b/Documentation/sound/alsa/Procfile.txt
@@ -88,21 +88,34 @@ card*/pcm*/info
 	substreams, etc.
 
 card*/pcm*/xrun_debug
-	This file appears when CONFIG_SND_DEBUG=y.
-	This shows the status of xrun (= buffer overrun/xrun) debug of
-	ALSA PCM middle layer, as an integer from 0 to 2.  The value
-	can be changed by writing to this file, such as
-
-		 # cat 2 > /proc/asound/card0/pcm0p/xrun_debug
-
-	When this value is greater than 0, the driver will show the
-	messages to kernel log when an xrun is detected.  The debug
-	message is shown also when the invalid H/W pointer is detected
-	at the update of periods (usually called from the interrupt
+	This file appears when CONFIG_SND_DEBUG=y and
+	CONFIG_PCM_XRUN_DEBUG=y.
+	This shows the status of xrun (= buffer overrun/xrun) and
+	invalid PCM position debug/check of ALSA PCM middle layer.
+	It takes an integer value, can be changed by writing to this
+	file, such as
+
+		 # cat 5 > /proc/asound/card0/pcm0p/xrun_debug
+
+	The value consists of the following bit flags:
+	  bit 0 = Enable XRUN/jiffies debug messages
+	  bit 1 = Show stack trace at XRUN / jiffies check
+	  bit 2 = Enable additional jiffies check
+
+	When the bit 0 is set, the driver will show the messages to
+	kernel log when an xrun is detected.  The debug message is
+	shown also when the invalid H/W pointer is detected at the
+	update of periods (usually called from the interrupt
 	handler).
 
-	When this value is greater than 1, the driver will show the
-	stack trace additionally.  This may help the debugging.
+	When the bit 1 is set, the driver will show the stack trace
+	additionally.  This may help the debugging.
+
+	Since 2.6.30, this option can enable the hwptr check using
+	jiffies.  This detects spontaneous invalid pointer callback
+	values, but can be lead to too much corrections for a (mostly
+	buggy) hardware that doesn't give smooth pointer updates.
+	This feature is enabled via the bit 2.
 
 card*/pcm*/sub*/info
 	The general information of this PCM sub-stream.
diff --git a/Documentation/sound/alsa/README.maya44 b/Documentation/sound/alsa/README.maya44
new file mode 100644
index 00000000000..0e41576fa13
--- /dev/null
+++ b/Documentation/sound/alsa/README.maya44
@@ -0,0 +1,163 @@
+NOTE: The following is the original document of Rainer's patch that the
+current maya44 code based on.  Some contents might be obsoleted, but I
+keep here as reference -- tiwai
+
+----------------------------------------------------------------
+ 
+STATE OF DEVELOPMENT:
+
+This driver is being developed on the initiative of Piotr Makowski (oponek@gmail.com) and financed by Lars Bergmann.
+Development is carried out by Rainer Zimmermann (mail@lightshed.de).
+
+ESI provided a sample Maya44 card for the development work.
+
+However, unfortunately it has turned out difficult to get detailed programming information, so I (Rainer Zimmermann) had to find out some card-specific information by experiment and conjecture. Some information (in particular, several GPIO bits) is still missing.
+
+This is the first testing version of the Maya44 driver released to the alsa-devel mailing list (Feb 5, 2008).
+
+
+The following functions work, as tested by Rainer Zimmermann and Piotr Makowski:
+
+- playback and capture at all sampling rates
+- input/output level
+- crossmixing
+- line/mic switch
+- phantom power switch
+- analogue monitor a.k.a bypass
+
+
+The following functions *should* work, but are not fully tested:
+
+- Channel 3+4 analogue - S/PDIF input switching
+- S/PDIF output
+- all inputs/outputs on the M/IO/DIO extension card
+- internal/external clock selection
+
+
+*In particular, we would appreciate testing of these functions by anyone who has access to an M/IO/DIO extension card.*
+
+
+Things that do not seem to work:
+
+- The level meters ("multi track") in 'alsamixer' do not seem to react to signals in (if this is a bug, it would probably be in the existing ICE1724 code).
+
+- Ardour 2.1 seems to work only via JACK, not using ALSA directly or via OSS. This still needs to be tracked down.
+
+
+DRIVER DETAILS:
+
+the following files were added:
+
+pci/ice1724/maya44.c        - Maya44 specific code
+pci/ice1724/maya44.h
+pci/ice1724/ice1724.patch
+pci/ice1724/ice1724.h.patch - PROPOSED patch to ice1724.h (see SAMPLING RATES)
+i2c/other/wm8776.c  - low-level access routines for Wolfson WM8776 codecs 
+include/wm8776.h
+
+
+Note that the wm8776.c code is meant to be card-independent and does not actually register the codec with the ALSA infrastructure.
+This is done in maya44.c, mainly because some of the WM8776 controls are used in Maya44-specific ways, and should be named appropriately.
+
+
+the following files were created in pci/ice1724, simply #including the corresponding file from the alsa-kernel tree:
+
+wtm.h
+vt1720_mobo.h
+revo.h
+prodigy192.h
+pontis.h
+phase.h
+maya44.h
+juli.h
+aureon.h
+amp.h
+envy24ht.h
+se.h
+prodigy_hifi.h
+
+
+*I hope this is the correct way to do things.*
+
+
+SAMPLING RATES:
+
+The Maya44 card (or more exactly, the Wolfson WM8776 codecs) allow a maximum sampling rate of 192 kHz for playback and 92 kHz for capture.
+
+As the ICE1724 chip only allows one global sampling rate, this is handled as follows:
+
+* setting the sampling rate on any open PCM device on the maya44 card will always set the *global* sampling rate for all playback and capture channels.
+
+* In the current state of the driver, setting rates of up to 192 kHz is permitted even for capture devices.
+
+*AVOID CAPTURING AT RATES ABOVE 96kHz*, even though it may appear to work. The codec cannot actually capture at such rates, meaning poor quality.
+
+
+I propose some additional code for limiting the sampling rate when setting on a capture pcm device. However because of the global sampling rate, this logic would be somewhat problematic.
+
+The proposed code (currently deactivated) is in ice1712.h.patch, ice1724.c and maya44.c (in pci/ice1712).
+
+
+SOUND DEVICES:
+
+PCM devices correspond to inputs/outputs as follows (assuming Maya44 is card #0):
+
+hw:0,0 input - stereo, analog input 1+2
+hw:0,0 output - stereo, analog output 1+2
+hw:0,1 input - stereo, analog input 3+4 OR S/PDIF input
+hw:0,1 output - stereo, analog output 3+4 (and SPDIF out)
+
+
+NAMING OF MIXER CONTROLS:
+
+(for more information about the signal flow, please refer to the block diagram on p.24 of the ESI Maya44 manual, or in the ESI windows software).
+
+
+PCM: (digital) output level for channel 1+2
+PCM 1: same for channel 3+4
+
+Mic Phantom+48V: switch for +48V phantom power for electrostatic microphones on input 1/2.
+    Make sure this is not turned on while any other source is connected to input 1/2.
+    It might damage the source and/or the maya44 card.
+
+Mic/Line input: if switch is is on, input jack 1/2 is microphone input (mono), otherwise line input (stereo).
+
+Bypass: analogue bypass from ADC input to output for channel 1+2. Same as "Monitor" in the windows driver.
+Bypass 1: same for channel 3+4.
+
+Crossmix: cross-mixer from channels 1+2 to channels 3+4
+Crossmix 1: cross-mixer from channels 3+4 to channels 1+2
+
+IEC958 Output: switch for S/PDIF output.
+    This is not supported by the ESI windows driver.
+    S/PDIF should output the same signal as channel 3+4. [untested!]
+
+
+Digitial output selectors:
+
+    These switches allow a direct digital routing from the ADCs to the DACs.
+    Each switch determines where the digital input data to one of the DACs comes from.
+    They are not supported by the ESI windows driver.
+    For normal operation, they should all be set to "PCM out".
+
+H/W: Output source channel 1
+H/W 1: Output source channel 2
+H/W 2: Output source channel 3
+H/W 3: Output source channel 4
+
+H/W 4 ... H/W 9: unknown function, left in to enable testing.
+    Possibly some of these control S/PDIF output(s).
+    If these turn out to be unused, they will go away in later driver versions.
+
+Selectable values for each of the digital output selectors are:
+   "PCM out" -> DAC output of the corresponding channel (default setting)
+   "Input 1"...
+   "Input 4" -> direct routing from ADC output of the selected input channel
+
+
+--------
+
+Feb 14, 2008
+Rainer Zimmermann
+mail@lightshed.de
+
diff --git a/Documentation/sound/alsa/hda_codec.txt b/Documentation/sound/alsa/hda_codec.txt
index 34e87ec1379..de8efbc7e4b 100644
--- a/Documentation/sound/alsa/hda_codec.txt
+++ b/Documentation/sound/alsa/hda_codec.txt
@@ -114,7 +114,7 @@ For writing a sequence of verbs, use snd_hda_sequence_write().
 
 There are variants of cached read/write, snd_hda_codec_write_cache(),
 snd_hda_sequence_write_cache().  These are used for recording the
-register states for the power-mangement resume.  When no PM is needed,
+register states for the power-management resume.  When no PM is needed,
 these are equivalent with non-cached version.
 
 To retrieve the number of sub nodes connected to the given node, use
diff --git a/Documentation/sound/alsa/soc/dapm.txt b/Documentation/sound/alsa/soc/dapm.txt
index 9e6763264a2..9ac842be9b4 100644
--- a/Documentation/sound/alsa/soc/dapm.txt
+++ b/Documentation/sound/alsa/soc/dapm.txt
@@ -62,6 +62,7 @@ Audio DAPM widgets fall into a number of types:-
  o Mic        - Mic (and optional Jack)
  o Line       - Line Input/Output (and optional Jack)
  o Speaker    - Speaker
+ o Supply     - Power or clock supply widget used by other widgets.
  o Pre        - Special PRE widget (exec before all others)
  o Post       - Special POST widget (exec after all others)
 
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index f11ca7979fa..322a00bb99d 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -32,6 +32,7 @@ show up in /proc/sys/kernel:
 - kstack_depth_to_print       [ X86 only ]
 - l2cr                        [ PPC only ]
 - modprobe                    ==> Documentation/debugging-modules.txt
+- modules_disabled
 - msgmax
 - msgmnb
 - msgmni
@@ -184,6 +185,16 @@ kernel stack.
 
 ==============================================================
 
+modules_disabled:
+
+A toggle value indicating if modules are allowed to be loaded
+in an otherwise modular kernel.  This toggle defaults to off
+(0), but can be set true (1).  Once true, modules can be
+neither loaded nor unloaded, and the toggle cannot be set back
+to false.
+
+==============================================================
+
 osrelease, ostype & version:
 
 # cat osrelease
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index c302ddf629a..c4de6359d44 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -233,8 +233,8 @@ These protections are added to score to judge whether this zone should be used
 for page allocation or should be reclaimed.
 
 In this example, if normal pages (index=2) are required to this DMA zone and
-pages_high is used for watermark, the kernel judges this zone should not be
-used because pages_free(1355) is smaller than watermark + protection[2]
+watermark[WMARK_HIGH] is used for watermark, the kernel judges this zone should
+not be used because pages_free(1355) is smaller than watermark + protection[2]
 (4 + 2004 = 2008). If this protection value is 0, this zone would be used for
 normal page requirement. If requirement is DMA zone(index=0), protection[0]
 (=0) is used.
@@ -280,9 +280,10 @@ The default value is 65536.
 min_free_kbytes:
 
 This is used to force the Linux VM to keep a minimum number
-of kilobytes free.  The VM uses this number to compute a pages_min
-value for each lowmem zone in the system.  Each lowmem zone gets
-a number of reserved free pages based proportionally on its size.
+of kilobytes free.  The VM uses this number to compute a
+watermark[WMARK_MIN] value for each lowmem zone in the system.
+Each lowmem zone gets a number of reserved free pages based
+proportionally on its size.
 
 Some minimal amount of memory is needed to satisfy PF_MEMALLOC
 allocations; if you set this to lower than 1024KB, your system will
@@ -314,10 +315,14 @@ min_unmapped_ratio:
 
 This is available only on NUMA kernels.
 
-A percentage of the total pages in each zone.  Zone reclaim will only
-occur if more than this percentage of pages are file backed and unmapped.
-This is to insure that a minimal amount of local pages is still available for
-file I/O even if the node is overallocated.
+This is a percentage of the total pages in each zone. Zone reclaim will
+only occur if more than this percentage of pages are in a state that
+zone_reclaim_mode allows to be reclaimed.
+
+If zone_reclaim_mode has the value 4 OR'd, then the percentage is compared
+against all file-backed unmapped pages including swapcache pages and tmpfs
+files. Otherwise, only unmapped pages backed by normal files but not tmpfs
+files and similar are considered.
 
 The default is 1 percent.
 
@@ -358,7 +363,7 @@ nr_pdflush_threads
 The current number of pdflush threads.  This value is read-only.
 The value changes according to the number of dirty pages in the system.
 
-When neccessary, additional pdflush threads are created, one per second, up to
+When necessary, additional pdflush threads are created, one per second, up to
 nr_pdflush_threads_max.
 
 ==============================================================
@@ -565,7 +570,7 @@ swappiness
 
 This control is used to define how aggressive the kernel will swap
 memory pages.  Higher values will increase agressiveness, lower values
-descrease the amount of swap.
+decrease the amount of swap.
 
 The default value is 60.
 
diff --git a/Documentation/timers/hpet.txt b/Documentation/timers/hpet.txt
index e7c09abcfab..04763a32552 100644
--- a/Documentation/timers/hpet.txt
+++ b/Documentation/timers/hpet.txt
@@ -7,7 +7,7 @@ by Intel and Microsoft which can be found at
 
 Each HPET has one fixed-rate counter (at 10+ MHz, hence "High Precision")
 and up to 32 comparators.  Normally three or more comparators are provided,
-each of which can generate oneshot interupts and at least one of which has
+each of which can generate oneshot interrupts and at least one of which has
 additional hardware to support periodic interrupts.  The comparators are
 also called "timers", which can be misleading since usually timers are
 independent of each other ... these share a counter, complicating resets.
diff --git a/Documentation/timers/timer_stats.txt b/Documentation/timers/timer_stats.txt
index 20d368c5981..9bd00fc2e82 100644
--- a/Documentation/timers/timer_stats.txt
+++ b/Documentation/timers/timer_stats.txt
@@ -62,7 +62,7 @@ Timerstats sample period: 3.888770 s
 
 The first column is the number of events, the second column the pid, the third
 column is the name of the process. The forth column shows the function which
-initialized the timer and in parantheses the callback function which was
+initialized the timer and in parenthesis the callback function which was
 executed on expiry.
 
     Thomas, Ingo
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index fd9a3e69381..a39b3c749de 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -7,7 +7,6 @@ Copyright 2008 Red Hat Inc.
                (dual licensed under the GPL v2)
 Reviewers:   Elias Oltmanns, Randy Dunlap, Andrew Morton,
 	     John Kacur, and David Teigland.
-
 Written for: 2.6.28-rc2
 
 Introduction
@@ -33,13 +32,26 @@ The File System
 Ftrace uses the debugfs file system to hold the control files as
 well as the files to display output.
 
-To mount the debugfs system:
+When debugfs is configured into the kernel (which selecting any ftrace
+option will do) the directory /sys/kernel/debug will be created. To mount
+this directory, you can add to your /etc/fstab file:
+
+ debugfs       /sys/kernel/debug          debugfs defaults        0       0
+
+Or you can mount it at run time with:
+
+ mount -t debugfs nodev /sys/kernel/debug
 
-  # mkdir /debug
-  # mount -t debugfs nodev /debug
+For quicker access to that directory you may want to make a soft link to
+it:
 
-( Note: it is more common to mount at /sys/kernel/debug, but for
-  simplicity this document will use /debug)
+ ln -s /sys/kernel/debug /debug
+
+Any selected ftrace option will also create a directory called tracing
+within the debugfs. The rest of the document will assume that you are in
+the ftrace directory (cd /sys/kernel/debug/tracing) and will only concentrate
+on the files within that directory and not distract from the content with
+the extended "/sys/kernel/debug/tracing" path name.
 
 That's it! (assuming that you have ftrace configured into your kernel)
 
@@ -179,7 +191,7 @@ Here is the list of current tracers that may be configured.
 
 	Function call tracer to trace all kernel functions.
 
-  "function_graph_tracer"
+  "function_graph"
 
 	Similar to the function tracer except that the
 	function tracer probes the functions on their entry
@@ -389,18 +401,18 @@ trace_options
 The trace_options file is used to control what gets printed in
 the trace output. To see what is available, simply cat the file:
 
-  cat /debug/tracing/trace_options
+  cat trace_options
   print-parent nosym-offset nosym-addr noverbose noraw nohex nobin \
   noblock nostacktrace nosched-tree nouserstacktrace nosym-userobj
 
 To disable one of the options, echo in the option prepended with
 "no".
 
-  echo noprint-parent > /debug/tracing/trace_options
+  echo noprint-parent > trace_options
 
 To enable an option, leave off the "no".
 
-  echo sym-offset > /debug/tracing/trace_options
+  echo sym-offset > trace_options
 
 Here are the available options:
 
@@ -476,11 +488,11 @@ sched_switch
 This tracer simply records schedule switches. Here is an example
 of how to use it.
 
- # echo sched_switch > /debug/tracing/current_tracer
- # echo 1 > /debug/tracing/tracing_enabled
+ # echo sched_switch > current_tracer
+ # echo 1 > tracing_enabled
  # sleep 1
- # echo 0 > /debug/tracing/tracing_enabled
- # cat /debug/tracing/trace
+ # echo 0 > tracing_enabled
+ # cat trace
 
 # tracer: sched_switch
 #
@@ -518,9 +530,18 @@ priority with zero (0) being the highest priority and the nice
 values starting at 100 (nice -20). Below is a quick chart to map
 the kernel priority to user land priorities.
 
-  Kernel priority: 0 to 99    ==> user RT priority 99 to 0
-  Kernel priority: 100 to 139 ==> user nice -20 to 19
-  Kernel priority: 140        ==> idle task priority
+   Kernel Space                     User Space
+ ===============================================================
+   0(high) to  98(low)     user RT priority 99(high) to 1(low)
+                           with SCHED_RR or SCHED_FIFO
+ ---------------------------------------------------------------
+  99                       sched_priority is not used in scheduling
+                           decisions(it must be specified as 0)
+ ---------------------------------------------------------------
+ 100(high) to 139(low)     user nice -20(high) to 19(low)
+ ---------------------------------------------------------------
+ 140                       idle task priority
+ ---------------------------------------------------------------
 
 The task states are:
 
@@ -574,13 +595,13 @@ new trace is saved.
 To reset the maximum, echo 0 into tracing_max_latency. Here is
 an example:
 
- # echo irqsoff > /debug/tracing/current_tracer
- # echo 0 > /debug/tracing/tracing_max_latency
- # echo 1 > /debug/tracing/tracing_enabled
+ # echo irqsoff > current_tracer
+ # echo 0 > tracing_max_latency
+ # echo 1 > tracing_enabled
  # ls -ltr
  [...]
- # echo 0 > /debug/tracing/tracing_enabled
- # cat /debug/tracing/latency_trace
+ # echo 0 > tracing_enabled
+ # cat latency_trace
 # tracer: irqsoff
 #
 irqsoff latency trace v1.1.5 on 2.6.26
@@ -681,13 +702,13 @@ Like the irqsoff tracer, it records the maximum latency for
 which preemption was disabled. The control of preemptoff tracer
 is much like the irqsoff tracer.
 
- # echo preemptoff > /debug/tracing/current_tracer
- # echo 0 > /debug/tracing/tracing_max_latency
- # echo 1 > /debug/tracing/tracing_enabled
+ # echo preemptoff > current_tracer
+ # echo 0 > tracing_max_latency
+ # echo 1 > tracing_enabled
  # ls -ltr
  [...]
- # echo 0 > /debug/tracing/tracing_enabled
- # cat /debug/tracing/latency_trace
+ # echo 0 > tracing_enabled
+ # cat latency_trace
 # tracer: preemptoff
 #
 preemptoff latency trace v1.1.5 on 2.6.26-rc8
@@ -828,13 +849,13 @@ tracer.
 Again, using this trace is much like the irqsoff and preemptoff
 tracers.
 
- # echo preemptirqsoff > /debug/tracing/current_tracer
- # echo 0 > /debug/tracing/tracing_max_latency
- # echo 1 > /debug/tracing/tracing_enabled
+ # echo preemptirqsoff > current_tracer
+ # echo 0 > tracing_max_latency
+ # echo 1 > tracing_enabled
  # ls -ltr
  [...]
- # echo 0 > /debug/tracing/tracing_enabled
- # cat /debug/tracing/latency_trace
+ # echo 0 > tracing_enabled
+ # cat latency_trace
 # tracer: preemptirqsoff
 #
 preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8
@@ -990,12 +1011,12 @@ slightly differently than we did with the previous tracers.
 Instead of performing an 'ls', we will run 'sleep 1' under
 'chrt' which changes the priority of the task.
 
- # echo wakeup > /debug/tracing/current_tracer
- # echo 0 > /debug/tracing/tracing_max_latency
- # echo 1 > /debug/tracing/tracing_enabled
+ # echo wakeup > current_tracer
+ # echo 0 > tracing_max_latency
+ # echo 1 > tracing_enabled
  # chrt -f 5 sleep 1
- # echo 0 > /debug/tracing/tracing_enabled
- # cat /debug/tracing/latency_trace
+ # echo 0 > tracing_enabled
+ # cat latency_trace
 # tracer: wakeup
 #
 wakeup latency trace v1.1.5 on 2.6.26-rc8
@@ -1105,11 +1126,11 @@ can be done from the debug file system. Make sure the
 ftrace_enabled is set; otherwise this tracer is a nop.
 
  # sysctl kernel.ftrace_enabled=1
- # echo function > /debug/tracing/current_tracer
- # echo 1 > /debug/tracing/tracing_enabled
+ # echo function > current_tracer
+ # echo 1 > tracing_enabled
  # usleep 1
- # echo 0 > /debug/tracing/tracing_enabled
- # cat /debug/tracing/trace
+ # echo 0 > tracing_enabled
+ # cat trace
 # tracer: function
 #
 #           TASK-PID   CPU#    TIMESTAMP  FUNCTION
@@ -1146,7 +1167,7 @@ int trace_fd;
 [...]
 int main(int argc, char *argv[]) {
 	[...]
-	trace_fd = open("/debug/tracing/tracing_enabled", O_WRONLY);
+	trace_fd = open(tracing_file("tracing_enabled"), O_WRONLY);
 	[...]
 	if (condition_hit()) {
 		write(trace_fd, "0", 1);
@@ -1154,26 +1175,20 @@ int main(int argc, char *argv[]) {
 	[...]
 }
 
-Note: Here we hard coded the path name. The debugfs mount is not
-guaranteed to be at /debug (and is more commonly at
-/sys/kernel/debug). For simple one time traces, the above is
-sufficent. For anything else, a search through /proc/mounts may
-be needed to find where the debugfs file-system is mounted.
-
 
 Single thread tracing
 ---------------------
 
-By writing into /debug/tracing/set_ftrace_pid you can trace a
+By writing into set_ftrace_pid you can trace a
 single thread. For example:
 
-# cat /debug/tracing/set_ftrace_pid
+# cat set_ftrace_pid
 no pid
-# echo 3111 > /debug/tracing/set_ftrace_pid
-# cat /debug/tracing/set_ftrace_pid
+# echo 3111 > set_ftrace_pid
+# cat set_ftrace_pid
 3111
-# echo function > /debug/tracing/current_tracer
-# cat /debug/tracing/trace | head
+# echo function > current_tracer
+# cat trace | head
  # tracer: function
  #
  #           TASK-PID    CPU#    TIMESTAMP  FUNCTION
@@ -1184,8 +1199,8 @@ no pid
      yum-updatesd-3111  [003]  1637.254683: lock_hrtimer_base <-hrtimer_try_to_cancel
      yum-updatesd-3111  [003]  1637.254685: fget_light <-do_sys_poll
      yum-updatesd-3111  [003]  1637.254686: pipe_poll <-do_sys_poll
-# echo -1 > /debug/tracing/set_ftrace_pid
-# cat /debug/tracing/trace |head
+# echo -1 > set_ftrace_pid
+# cat trace |head
  # tracer: function
  #
  #           TASK-PID    CPU#    TIMESTAMP  FUNCTION
@@ -1207,6 +1222,51 @@ something like this simple program:
 #include <fcntl.h>
 #include <unistd.h>
 
+#define _STR(x) #x
+#define STR(x) _STR(x)
+#define MAX_PATH 256
+
+const char *find_debugfs(void)
+{
+       static char debugfs[MAX_PATH+1];
+       static int debugfs_found;
+       char type[100];
+       FILE *fp;
+
+       if (debugfs_found)
+               return debugfs;
+
+       if ((fp = fopen("/proc/mounts","r")) == NULL) {
+               perror("/proc/mounts");
+               return NULL;
+       }
+
+       while (fscanf(fp, "%*s %"
+                     STR(MAX_PATH)
+                     "s %99s %*s %*d %*d\n",
+                     debugfs, type) == 2) {
+               if (strcmp(type, "debugfs") == 0)
+                       break;
+       }
+       fclose(fp);
+
+       if (strcmp(type, "debugfs") != 0) {
+               fprintf(stderr, "debugfs not mounted");
+               return NULL;
+       }
+
+       debugfs_found = 1;
+
+       return debugfs;
+}
+
+const char *tracing_file(const char *file_name)
+{
+       static char trace_file[MAX_PATH+1];
+       snprintf(trace_file, MAX_PATH, "%s/%s", find_debugfs(), file_name);
+       return trace_file;
+}
+
 int main (int argc, char **argv)
 {
         if (argc < 1)
@@ -1217,12 +1277,12 @@ int main (int argc, char **argv)
                 char line[64];
                 int s;
 
-                ffd = open("/debug/tracing/current_tracer", O_WRONLY);
+                ffd = open(tracing_file("current_tracer"), O_WRONLY);
                 if (ffd < 0)
                         exit(-1);
                 write(ffd, "nop", 3);
 
-                fd = open("/debug/tracing/set_ftrace_pid", O_WRONLY);
+                fd = open(tracing_file("set_ftrace_pid"), O_WRONLY);
                 s = sprintf(line, "%d\n", getpid());
                 write(fd, line, s);
 
@@ -1374,22 +1434,22 @@ want, depending on your needs.
   tracing_cpu_mask file) or you might sometimes see unordered
   function calls while cpu tracing switch.
 
-	hide: echo nofuncgraph-cpu > /debug/tracing/trace_options
-	show: echo funcgraph-cpu > /debug/tracing/trace_options
+	hide: echo nofuncgraph-cpu > trace_options
+	show: echo funcgraph-cpu > trace_options
 
 - The duration (function's time of execution) is displayed on
   the closing bracket line of a function or on the same line
   than the current function in case of a leaf one. It is default
   enabled.
 
-	hide: echo nofuncgraph-duration > /debug/tracing/trace_options
-	show: echo funcgraph-duration > /debug/tracing/trace_options
+	hide: echo nofuncgraph-duration > trace_options
+	show: echo funcgraph-duration > trace_options
 
 - The overhead field precedes the duration field in case of
   reached duration thresholds.
 
-	hide: echo nofuncgraph-overhead > /debug/tracing/trace_options
-	show: echo funcgraph-overhead > /debug/tracing/trace_options
+	hide: echo nofuncgraph-overhead > trace_options
+	show: echo funcgraph-overhead > trace_options
 	depends on: funcgraph-duration
 
   ie:
@@ -1418,8 +1478,8 @@ want, depending on your needs.
 - The task/pid field displays the thread cmdline and pid which
   executed the function. It is default disabled.
 
-	hide: echo nofuncgraph-proc > /debug/tracing/trace_options
-	show: echo funcgraph-proc > /debug/tracing/trace_options
+	hide: echo nofuncgraph-proc > trace_options
+	show: echo funcgraph-proc > trace_options
 
   ie:
 
@@ -1442,8 +1502,8 @@ want, depending on your needs.
   system clock since it started. A snapshot of this time is
   given on each entry/exit of functions
 
-	hide: echo nofuncgraph-abstime > /debug/tracing/trace_options
-	show: echo funcgraph-abstime > /debug/tracing/trace_options
+	hide: echo nofuncgraph-abstime > trace_options
+	show: echo funcgraph-abstime > trace_options
 
   ie:
 
@@ -1540,7 +1600,7 @@ listed in:
 
    available_filter_functions
 
- # cat /debug/tracing/available_filter_functions
+ # cat available_filter_functions
 put_prev_task_idle
 kmem_cache_create
 pick_next_task_rt
@@ -1552,12 +1612,12 @@ mutex_lock
 If I am only interested in sys_nanosleep and hrtimer_interrupt:
 
  # echo sys_nanosleep hrtimer_interrupt \
-		> /debug/tracing/set_ftrace_filter
- # echo ftrace > /debug/tracing/current_tracer
- # echo 1 > /debug/tracing/tracing_enabled
+		> set_ftrace_filter
+ # echo ftrace > current_tracer
+ # echo 1 > tracing_enabled
  # usleep 1
- # echo 0 > /debug/tracing/tracing_enabled
- # cat /debug/tracing/trace
+ # echo 0 > tracing_enabled
+ # cat trace
 # tracer: ftrace
 #
 #           TASK-PID   CPU#    TIMESTAMP  FUNCTION
@@ -1568,7 +1628,7 @@ If I am only interested in sys_nanosleep and hrtimer_interrupt:
 
 To see which functions are being traced, you can cat the file:
 
- # cat /debug/tracing/set_ftrace_filter
+ # cat set_ftrace_filter
 hrtimer_interrupt
 sys_nanosleep
 
@@ -1588,7 +1648,7 @@ Note: It is better to use quotes to enclose the wild cards,
       otherwise the shell may expand the parameters into names
       of files in the local directory.
 
- # echo 'hrtimer_*' > /debug/tracing/set_ftrace_filter
+ # echo 'hrtimer_*' > set_ftrace_filter
 
 Produces:
 
@@ -1609,7 +1669,7 @@ Produces:
 
 Notice that we lost the sys_nanosleep.
 
- # cat /debug/tracing/set_ftrace_filter
+ # cat set_ftrace_filter
 hrtimer_run_queues
 hrtimer_run_pending
 hrtimer_init
@@ -1635,17 +1695,17 @@ To append to the filters, use '>>'
 To clear out a filter so that all functions will be recorded
 again:
 
- # echo > /debug/tracing/set_ftrace_filter
- # cat /debug/tracing/set_ftrace_filter
+ # echo > set_ftrace_filter
+ # cat set_ftrace_filter
  #
 
 Again, now we want to append.
 
- # echo sys_nanosleep > /debug/tracing/set_ftrace_filter
- # cat /debug/tracing/set_ftrace_filter
+ # echo sys_nanosleep > set_ftrace_filter
+ # cat set_ftrace_filter
 sys_nanosleep
- # echo 'hrtimer_*' >> /debug/tracing/set_ftrace_filter
- # cat /debug/tracing/set_ftrace_filter
+ # echo 'hrtimer_*' >> set_ftrace_filter
+ # cat set_ftrace_filter
 hrtimer_run_queues
 hrtimer_run_pending
 hrtimer_init
@@ -1668,7 +1728,7 @@ hrtimer_init_sleeper
 The set_ftrace_notrace prevents those functions from being
 traced.
 
- # echo '*preempt*' '*lock*' > /debug/tracing/set_ftrace_notrace
+ # echo '*preempt*' '*lock*' > set_ftrace_notrace
 
 Produces:
 
@@ -1758,13 +1818,13 @@ the effect on the tracing is different. Every read from
 trace_pipe is consumed. This means that subsequent reads will be
 different. The trace is live.
 
- # echo function > /debug/tracing/current_tracer
- # cat /debug/tracing/trace_pipe > /tmp/trace.out &
+ # echo function > current_tracer
+ # cat trace_pipe > /tmp/trace.out &
 [1] 4153
- # echo 1 > /debug/tracing/tracing_enabled
+ # echo 1 > tracing_enabled
  # usleep 1
- # echo 0 > /debug/tracing/tracing_enabled
- # cat /debug/tracing/trace
+ # echo 0 > tracing_enabled
+ # cat trace
 # tracer: function
 #
 #           TASK-PID   CPU#    TIMESTAMP  FUNCTION
@@ -1800,7 +1860,7 @@ number listed is the number of entries that can be recorded per
 CPU. To know the full size, multiply the number of possible CPUS
 with the number of entries.
 
- # cat /debug/tracing/buffer_size_kb
+ # cat buffer_size_kb
 1408 (units kilobytes)
 
 Note, to modify this, you must have tracing completely disabled.
@@ -1808,21 +1868,21 @@ To do that, echo "nop" into the current_tracer. If the
 current_tracer is not set to "nop", an EINVAL error will be
 returned.
 
- # echo nop > /debug/tracing/current_tracer
- # echo 10000 > /debug/tracing/buffer_size_kb
- # cat /debug/tracing/buffer_size_kb
+ # echo nop > current_tracer
+ # echo 10000 > buffer_size_kb
+ # cat buffer_size_kb
 10000 (units kilobytes)
 
 The number of pages which will be allocated is limited to a
 percentage of available memory. Allocating too much will produce
 an error.
 
- # echo 1000000000000 > /debug/tracing/buffer_size_kb
+ # echo 1000000000000 > buffer_size_kb
 -bash: echo: write error: Cannot allocate memory
- # cat /debug/tracing/buffer_size_kb
+ # cat buffer_size_kb
 85
 
 -----------
 
 More details can be found in the source code, in the
-kernel/tracing/*.c files.
+kernel/trace/*.c files.
diff --git a/Documentation/trace/kmemtrace.txt b/Documentation/trace/kmemtrace.txt
index a956d9b7f94..6308735e58c 100644
--- a/Documentation/trace/kmemtrace.txt
+++ b/Documentation/trace/kmemtrace.txt
@@ -64,7 +64,7 @@ III. Quick usage guide
 CONFIG_KMEMTRACE).
 
 2) Get the userspace tool and build it:
-$ git-clone git://repo.or.cz/kmemtrace-user.git		# current repository
+$ git clone git://repo.or.cz/kmemtrace-user.git		# current repository
 $ cd kmemtrace-user/
 $ ./autogen.sh
 $ ./configure
diff --git a/Documentation/trace/mmiotrace.txt b/Documentation/trace/mmiotrace.txt
index 5731c67abc5..162effbfbde 100644
--- a/Documentation/trace/mmiotrace.txt
+++ b/Documentation/trace/mmiotrace.txt
@@ -32,41 +32,41 @@ is no way to automatically detect if you are losing events due to CPUs racing.
 Usage Quick Reference
 ---------------------
 
-$ mount -t debugfs debugfs /debug
-$ echo mmiotrace > /debug/tracing/current_tracer
-$ cat /debug/tracing/trace_pipe > mydump.txt &
+$ mount -t debugfs debugfs /sys/kernel/debug
+$ echo mmiotrace > /sys/kernel/debug/tracing/current_tracer
+$ cat /sys/kernel/debug/tracing/trace_pipe > mydump.txt &
 Start X or whatever.
-$ echo "X is up" > /debug/tracing/trace_marker
-$ echo nop > /debug/tracing/current_tracer
+$ echo "X is up" > /sys/kernel/debug/tracing/trace_marker
+$ echo nop > /sys/kernel/debug/tracing/current_tracer
 Check for lost events.
 
 
 Usage
 -----
 
-Make sure debugfs is mounted to /debug. If not, (requires root privileges)
-$ mount -t debugfs debugfs /debug
+Make sure debugfs is mounted to /sys/kernel/debug. If not, (requires root privileges)
+$ mount -t debugfs debugfs /sys/kernel/debug
 
 Check that the driver you are about to trace is not loaded.
 
 Activate mmiotrace (requires root privileges):
-$ echo mmiotrace > /debug/tracing/current_tracer
+$ echo mmiotrace > /sys/kernel/debug/tracing/current_tracer
 
 Start storing the trace:
-$ cat /debug/tracing/trace_pipe > mydump.txt &
+$ cat /sys/kernel/debug/tracing/trace_pipe > mydump.txt &
 The 'cat' process should stay running (sleeping) in the background.
 
 Load the driver you want to trace and use it. Mmiotrace will only catch MMIO
 accesses to areas that are ioremapped while mmiotrace is active.
 
 During tracing you can place comments (markers) into the trace by
-$ echo "X is up" > /debug/tracing/trace_marker
+$ echo "X is up" > /sys/kernel/debug/tracing/trace_marker
 This makes it easier to see which part of the (huge) trace corresponds to
 which action. It is recommended to place descriptive markers about what you
 do.
 
 Shut down mmiotrace (requires root privileges):
-$ echo nop > /debug/tracing/current_tracer
+$ echo nop > /sys/kernel/debug/tracing/current_tracer
 The 'cat' process exits. If it does not, kill it by issuing 'fg' command and
 pressing ctrl+c.
 
@@ -78,10 +78,10 @@ to view your kernel log and look for "mmiotrace has lost events" warning. If
 events were lost, the trace is incomplete. You should enlarge the buffers and
 try again. Buffers are enlarged by first seeing how large the current buffers
 are:
-$ cat /debug/tracing/buffer_size_kb
+$ cat /sys/kernel/debug/tracing/buffer_size_kb
 gives you a number. Approximately double this number and write it back, for
 instance:
-$ echo 128000 > /debug/tracing/buffer_size_kb
+$ echo 128000 > /sys/kernel/debug/tracing/buffer_size_kb
 Then start again from the top.
 
 If you are doing a trace for a driver project, e.g. Nouveau, you should also
diff --git a/Documentation/usb/WUSB-Design-overview.txt b/Documentation/usb/WUSB-Design-overview.txt
index 4c3d62c7843..c480e9c32db 100644
--- a/Documentation/usb/WUSB-Design-overview.txt
+++ b/Documentation/usb/WUSB-Design-overview.txt
@@ -84,7 +84,7 @@ The different logical parts of this driver are:
 
       *UWB*: the Ultra-Wide-Band stack -- manages the radio and
       associated spectrum to allow for devices sharing it. Allows to
-      control bandwidth assingment, beaconing, scanning, etc
+      control bandwidth assignment, beaconing, scanning, etc
 
     *
 
@@ -184,7 +184,7 @@ and sends the replies and notifications back to the API
 [/uwb_rc_neh_grok()/]. Notifications are handled to the UWB daemon, that
 is chartered, among other things, to keep the tab of how the UWB radio
 neighborhood looks, creating and destroying devices as they show up or
-dissapear.
+disappear.
 
 Command execution is very simple: a command block is sent and a event
 block or reply is expected back. For sending/receiving command/events, a
@@ -333,7 +333,7 @@ read descriptors and move our data.
 
 *Device life cycle and keep alives*
 
-Everytime there is a succesful transfer to/from a device, we update a
+Every time there is a successful transfer to/from a device, we update a
 per-device activity timestamp. If not, every now and then we check and
 if the activity timestamp gets old, we ping the device by sending it a
 Keep Alive IE; it responds with a /DN_Alive/ pong during the DNTS (this
@@ -411,7 +411,7 @@ context (wa_xfer) and submit it. When the xfer is done, our callback is
 called and we assign the status bits and release the xfer resources.
 
 In dequeue() we are basically cancelling/aborting the transfer. We issue
-a xfer abort request to the HC, cancell all the URBs we had submitted
+a xfer abort request to the HC, cancel all the URBs we had submitted
 and not yet done and when all that is done, the xfer callback will be
 called--this will call the URB callback.
 
diff --git a/Documentation/usb/anchors.txt b/Documentation/usb/anchors.txt
index 6f24f566955..fe6a99a32bb 100644
--- a/Documentation/usb/anchors.txt
+++ b/Documentation/usb/anchors.txt
@@ -27,7 +27,7 @@ Association and disassociation of URBs with anchors
 
 An association of URBs to an anchor is made by an explicit
 call to usb_anchor_urb(). The association is maintained until
-an URB is finished by (successfull) completion. Thus disassociation
+an URB is finished by (successful) completion. Thus disassociation
 is automatic. A function is provided to forcibly finish (kill)
 all URBs associated with an anchor.
 Furthermore, disassociation can be made with usb_unanchor_urb()
@@ -76,4 +76,4 @@ usb_get_from_anchor()
 Returns the oldest anchored URB of an anchor. The URB is unanchored
 and returned with a reference. As you may mix URBs to several
 destinations in one anchor you have no guarantee the chronologically
-first submitted URB is returned.
-\ No newline at end of file
+first submitted URB is returned.
diff --git a/Documentation/usb/callbacks.txt b/Documentation/usb/callbacks.txt
index 7c812411945..bfb36b34b79 100644
--- a/Documentation/usb/callbacks.txt
+++ b/Documentation/usb/callbacks.txt
@@ -65,7 +65,7 @@ Accept or decline an interface. If you accept the device return 0,
 otherwise -ENODEV or -ENXIO. Other error codes should be used only if a
 genuine error occurred during initialisation which prevented a driver
 from accepting a device that would else have been accepted.
-You are strongly encouraged to use usbcore'sfacility,
+You are strongly encouraged to use usbcore's facility,
 usb_set_intfdata(), to associate a data structure with an interface, so
 that you know which internal state and identity you associate with a
 particular interface. The device will not be suspended and you may do IO
diff --git a/Documentation/video4linux/CARDLIST.cx23885 b/Documentation/video4linux/CARDLIST.cx23885
index 91aa3c0f0dd..450b8f8c389 100644
--- a/Documentation/video4linux/CARDLIST.cx23885
+++ b/Documentation/video4linux/CARDLIST.cx23885
@@ -16,3 +16,8 @@
  15 -> TeVii S470                                          [d470:9022]
  16 -> DVBWorld DVB-S2 2005                                [0001:2005]
  17 -> NetUP Dual DVB-S2 CI                                [1b55:2a2c]
+ 18 -> Hauppauge WinTV-HVR1270                             [0070:2211]
+ 19 -> Hauppauge WinTV-HVR1275                             [0070:2215]
+ 20 -> Hauppauge WinTV-HVR1255                             [0070:2251]
+ 21 -> Hauppauge WinTV-HVR1210                             [0070:2291,0070:2295]
+ 22 -> Mygica X8506 DMB-TH                                 [14f1:8651]
diff --git a/Documentation/video4linux/CARDLIST.cx88 b/Documentation/video4linux/CARDLIST.cx88
index 71e9db0b26f..89093f53172 100644
--- a/Documentation/video4linux/CARDLIST.cx88
+++ b/Documentation/video4linux/CARDLIST.cx88
@@ -78,3 +78,5 @@
  77 -> TBS 8910 DVB-S                                      [8910:8888]
  78 -> Prof 6200 DVB-S                                     [b022:3022]
  79 -> Terratec Cinergy HT PCI MKII                        [153b:1177]
+ 80 -> Hauppauge WinTV-IR Only                             [0070:9290]
+ 81 -> Leadtek WinFast DTV1800 Hybrid                      [107d:6654]
diff --git a/Documentation/video4linux/CARDLIST.em28xx b/Documentation/video4linux/CARDLIST.em28xx
index 78d0a6eed57..a98a688c11b 100644
--- a/Documentation/video4linux/CARDLIST.em28xx
+++ b/Documentation/video4linux/CARDLIST.em28xx
@@ -17,7 +17,7 @@
  16 -> Hauppauge WinTV HVR 950                  (em2883)        [2040:6513,2040:6517,2040:651b]
  17 -> Pinnacle PCTV HD Pro Stick               (em2880)        [2304:0227]
  18 -> Hauppauge WinTV HVR 900 (R2)             (em2880)        [2040:6502]
- 19 -> PointNix Intra-Oral Camera               (em2860)
+ 19 -> EM2860/SAA711X Reference Design          (em2860)
  20 -> AMD ATI TV Wonder HD 600                 (em2880)        [0438:b002]
  21 -> eMPIA Technology, Inc. GrabBeeX+ Video Encoder (em2800)        [eb1a:2801]
  22 -> Unknown EM2750/EM2751 webcam grabber     (em2750)        [eb1a:2750,eb1a:2751]
@@ -61,3 +61,7 @@
  63 -> Kaiomy TVnPC U2                          (em2860)        [eb1a:e303]
  64 -> Easy Cap Capture DC-60                   (em2860)
  65 -> IO-DATA GV-MVP/SZ                        (em2820/em2840) [04bb:0515]
+ 66 -> Empire dual TV                           (em2880)
+ 67 -> Terratec Grabby                          (em2860)        [0ccd:0096]
+ 68 -> Terratec AV350                           (em2860)        [0ccd:0084]
+ 69 -> KWorld ATSC 315U HDTV TV Box             (em2882)        [eb1a:a313]
diff --git a/Documentation/video4linux/CARDLIST.saa7134 b/Documentation/video4linux/CARDLIST.saa7134
index 6dacf282525..15562427e8a 100644
--- a/Documentation/video4linux/CARDLIST.saa7134
+++ b/Documentation/video4linux/CARDLIST.saa7134
@@ -124,10 +124,10 @@
 123 -> Beholder BeholdTV 407                    [0000:4070]
 124 -> Beholder BeholdTV 407 FM                 [0000:4071]
 125 -> Beholder BeholdTV 409                    [0000:4090]
-126 -> Beholder BeholdTV 505 FM/RDS             [0000:5051,0000:505B,5ace:5050]
-127 -> Beholder BeholdTV 507 FM/RDS / BeholdTV 509 FM [0000:5071,0000:507B,5ace:5070,5ace:5090]
+126 -> Beholder BeholdTV 505 FM                 [5ace:5050]
+127 -> Beholder BeholdTV 507 FM / BeholdTV 509 FM [5ace:5070,5ace:5090]
 128 -> Beholder BeholdTV Columbus TVFM          [0000:5201]
-129 -> Beholder BeholdTV 607 / BeholdTV 609     [5ace:6070,5ace:6071,5ace:6072,5ace:6073,5ace:6090,5ace:6091,5ace:6092,5ace:6093]
+129 -> Beholder BeholdTV 607 FM                 [5ace:6070]
 130 -> Beholder BeholdTV M6                     [5ace:6190]
 131 -> Twinhan Hybrid DTV-DVB 3056 PCI          [1822:0022]
 132 -> Genius TVGO AM11MCE
@@ -143,7 +143,7 @@
 142 -> Beholder BeholdTV H6                     [5ace:6290]
 143 -> Beholder BeholdTV M63                    [5ace:6191]
 144 -> Beholder BeholdTV M6 Extra               [5ace:6193]
-145 -> AVerMedia MiniPCI DVB-T Hybrid M103      [1461:f636]
+145 -> AVerMedia MiniPCI DVB-T Hybrid M103      [1461:f636,1461:f736]
 146 -> ASUSTeK P7131 Analog
 147 -> Asus Tiger 3in1                          [1043:4878]
 148 -> Encore ENLTV-FM v5.3                     [1a7f:2008]
@@ -154,4 +154,16 @@
 153 -> Kworld Plus TV Analog Lite PCI           [17de:7128]
 154 -> Avermedia AVerTV GO 007 FM Plus          [1461:f31d]
 155 -> Hauppauge WinTV-HVR1120 ATSC/QAM-Hybrid  [0070:6706,0070:6708]
-156 -> Hauppauge WinTV-HVR1110r3                [0070:6707,0070:6709,0070:670a]
+156 -> Hauppauge WinTV-HVR1110r3 DVB-T/Hybrid   [0070:6707,0070:6709,0070:670a]
+157 -> Avermedia AVerTV Studio 507UA            [1461:a11b]
+158 -> AVerMedia Cardbus TV/Radio (E501R)       [1461:b7e9]
+159 -> Beholder BeholdTV 505 RDS                [0000:505B]
+160 -> Beholder BeholdTV 507 RDS                [0000:5071]
+161 -> Beholder BeholdTV 507 RDS                [0000:507B]
+162 -> Beholder BeholdTV 607 FM                 [5ace:6071]
+163 -> Beholder BeholdTV 609 FM                 [5ace:6090]
+164 -> Beholder BeholdTV 609 FM                 [5ace:6091]
+165 -> Beholder BeholdTV 607 RDS                [5ace:6072]
+166 -> Beholder BeholdTV 607 RDS                [5ace:6073]
+167 -> Beholder BeholdTV 609 RDS                [5ace:6092]
+168 -> Beholder BeholdTV 609 RDS                [5ace:6093]
diff --git a/Documentation/video4linux/CARDLIST.tuner b/Documentation/video4linux/CARDLIST.tuner
index 691d2f37dc5..be67844074d 100644
--- a/Documentation/video4linux/CARDLIST.tuner
+++ b/Documentation/video4linux/CARDLIST.tuner
@@ -76,3 +76,5 @@ tuner=75 - Philips TEA5761 FM Radio
 tuner=76 - Xceive 5000 tuner
 tuner=77 - TCL tuner MF02GIP-5N-E
 tuner=78 - Philips FMD1216MEX MK3 Hybrid Tuner
+tuner=79 - Philips PAL/SECAM multi (FM1216 MK5)
+tuner=80 - Philips FQ1216LME MK3 PAL/SECAM w/active loopthrough
diff --git a/Documentation/video4linux/cx18.txt b/Documentation/video4linux/cx18.txt
index 914cb7e734a..4652c0f5da3 100644
--- a/Documentation/video4linux/cx18.txt
+++ b/Documentation/video4linux/cx18.txt
@@ -11,7 +11,7 @@ encoder chip:
 2) Some people have problems getting the i2c bus to work.
    The symptom is that the eeprom cannot be read and the card is
    unusable. This is probably fixed, but if you have problems
-   then post to the video4linux or ivtv-users mailinglist.
+   then post to the video4linux or ivtv-users mailing list.
 
 3) VBI (raw or sliced) has not yet been implemented.
 
diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt
index 98529e03a46..2bcf78896e2 100644
--- a/Documentation/video4linux/gspca.txt
+++ b/Documentation/video4linux/gspca.txt
@@ -163,10 +163,11 @@ sunplus		055f:c650	Mustek MDC5500Z
 zc3xx		055f:d003	Mustek WCam300A
 zc3xx		055f:d004	Mustek WCam300 AN
 conex		0572:0041	Creative Notebook cx11646
-ov519		05a9:0519	OmniVision
+ov519		05a9:0519	OV519 Microphone
 ov519		05a9:0530	OmniVision
-ov519		05a9:4519	OmniVision
+ov519		05a9:4519	Webcam Classic
 ov519		05a9:8519	OmniVision
+ov519		05a9:a518	D-Link DSB-C310 Webcam
 sunplus		05da:1018	Digital Dream Enigma 1.3
 stk014		05e1:0893	Syntek DV4000
 spca561		060b:a001	Maxell Compact Pc PM3
@@ -178,6 +179,7 @@ spca506		06e1:a190	ADS Instant VCD
 ov534		06f8:3002	Hercules Blog Webcam
 ov534		06f8:3003	Hercules Dualpix HD Weblog
 sonixj		06f8:3004	Hercules Classic Silver
+sonixj		06f8:3008	Hercules Deluxe Optical Glass
 spca508		0733:0110	ViewQuest VQ110
 spca508		0130:0130	Clone Digital Webcam 11043
 spca501		0733:0401	Intel Create and Share
@@ -209,6 +211,7 @@ sunplus		08ca:2050	Medion MD 41437
 sunplus		08ca:2060	Aiptek PocketDV5300
 tv8532		0923:010f	ICM532 cams
 mars		093a:050f	Mars-Semi Pc-Camera
+mr97310a	093a:010f	Sakar Digital no. 77379
 pac207		093a:2460	Qtec Webcam 100
 pac207		093a:2461	HP Webcam
 pac207		093a:2463	Philips SPC 220 NC
@@ -265,6 +268,11 @@ sonixj		0c45:60ec	SN9C105+MO4000
 sonixj		0c45:60fb	Surfer NoName
 sonixj		0c45:60fc	LG-LIC300
 sonixj		0c45:60fe	Microdia Audio
+sonixj		0c45:6100	PC Camera (SN9C128)
+sonixj		0c45:610a	PC Camera (SN9C128)
+sonixj		0c45:610b	PC Camera (SN9C128)
+sonixj		0c45:610c	PC Camera (SN9C128)
+sonixj		0c45:610e	PC Camera (SN9C128)
 sonixj		0c45:6128	Microdia/Sonix SNP325
 sonixj		0c45:612a	Avant Camera
 sonixj		0c45:612c	Typhoon Rasy Cam 1.3MPix
diff --git a/Documentation/video4linux/pxa_camera.txt b/Documentation/video4linux/pxa_camera.txt
index b1137f9a53e..4f6d0ca0195 100644
--- a/Documentation/video4linux/pxa_camera.txt
+++ b/Documentation/video4linux/pxa_camera.txt
@@ -26,6 +26,55 @@ Global video workflow
 
      Once the last buffer is filled in, the QCI interface stops.
 
+  c) Capture global finite state machine schema
+
+      +----+                             +---+  +----+
+      | DQ |                             | Q |  | DQ |
+      |    v                             |   v  |    v
+    +-----------+                     +------------------------+
+    |   STOP    |                     | Wait for capture start |
+    +-----------+         Q           +------------------------+
++-> | QCI: stop | ------------------> | QCI: run               | <------------+
+|   | DMA: stop |                     | DMA: stop              |              |
+|   +-----------+             +-----> +------------------------+              |
+|                            /                            |                   |
+|                           /             +---+  +----+   |                   |
+|capture list empty        /              | Q |  | DQ |   | QCI Irq EOF       |
+|                         /               |   v  |    v   v                   |
+|   +--------------------+             +----------------------+               |
+|   | DMA hotlink missed |             |    Capture running   |               |
+|   +--------------------+             +----------------------+               |
+|   | QCI: run           |     +-----> | QCI: run             | <-+           |
+|   | DMA: stop          |    /        | DMA: run             |   |           |
+|   +--------------------+   /         +----------------------+   | Other     |
+|     ^                     /DMA still            |               | channels  |
+|     | capture list       /  running             | DMA Irq End   | not       |
+|     | not empty         /                       |               | finished  |
+|     |                  /                        v               | yet       |
+|   +----------------------+           +----------------------+   |           |
+|   |  Videobuf released   |           |  Channel completed   |   |           |
+|   +----------------------+           +----------------------+   |           |
++-- | QCI: run             |           | QCI: run             | --+           |
+    | DMA: run             |           | DMA: run             |               |
+    +----------------------+           +----------------------+               |
+               ^                      /           |                           |
+               |          no overrun /            | overrun                   |
+               |                    /             v                           |
+    +--------------------+         /   +----------------------+               |
+    |  Frame completed   |        /    |     Frame overran    |               |
+    +--------------------+ <-----+     +----------------------+ restart frame |
+    | QCI: run           |             | QCI: stop            | --------------+
+    | DMA: run           |             | DMA: stop            |
+    +--------------------+             +----------------------+
+
+    Legend: - each box is a FSM state
+            - each arrow is the condition to transition to another state
+            - an arrow with a comment is a mandatory transition (no condition)
+            - arrow "Q" means : a buffer was enqueued
+            - arrow "DQ" means : a buffer was dequeued
+            - "QCI: stop" means the QCI interface is not enabled
+            - "DMA: stop" means all 3 DMA channels are stopped
+            - "DMA: run" means at least 1 DMA channel is still running
 
 DMA usage
 ---------
diff --git a/Documentation/video4linux/v4l2-framework.txt b/Documentation/video4linux/v4l2-framework.txt
index 854808b67fa..d54c1e4c6a9 100644
--- a/Documentation/video4linux/v4l2-framework.txt
+++ b/Documentation/video4linux/v4l2-framework.txt
@@ -89,6 +89,11 @@ from dev (driver name followed by the bus_id, to be precise). If you set it
 up before calling v4l2_device_register then it will be untouched. If dev is
 NULL, then you *must* setup v4l2_dev->name before calling v4l2_device_register.
 
+You can use v4l2_device_set_name() to set the name based on a driver name and
+a driver-global atomic_t instance. This will generate names like ivtv0, ivtv1,
+etc. If the name ends with a digit, then it will insert a dash: cx18-0,
+cx18-1, etc. This function returns the instance number.
+
 The first 'dev' argument is normally the struct device pointer of a pci_dev,
 usb_interface or platform_device. It is rare for dev to be NULL, but it happens
 with ISA devices or when one device creates multiple PCI devices, thus making
diff --git a/Documentation/vm/Makefile b/Documentation/vm/Makefile
index 6f562f778b2..27479d43a9b 100644
--- a/Documentation/vm/Makefile
+++ b/Documentation/vm/Makefile
@@ -2,7 +2,7 @@
 obj- := dummy.o
 
 # List of programs to build
-hostprogs-y := slabinfo
+hostprogs-y := slabinfo slqbinfo page-types
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
diff --git a/Documentation/vm/balance b/Documentation/vm/balance
index bd3d31bc491..c46e68cf934 100644
--- a/Documentation/vm/balance
+++ b/Documentation/vm/balance
@@ -75,15 +75,15 @@ Page stealing from process memory and shm is done if stealing the page would
 alleviate memory pressure on any zone in the page's node that has fallen below
 its watermark.
 
-pages_min/pages_low/pages_high/low_on_memory/zone_wake_kswapd: These are 
-per-zone fields, used to determine when a zone needs to be balanced. When
-the number of pages falls below pages_min, the hysteric field low_on_memory
-gets set. This stays set till the number of free pages becomes pages_high.
-When low_on_memory is set, page allocation requests will try to free some
-pages in the zone (providing GFP_WAIT is set in the request). Orthogonal
-to this, is the decision to poke kswapd to free some zone pages. That
-decision is not hysteresis based, and is done when the number of free
-pages is below pages_low; in which case zone_wake_kswapd is also set.
+watemark[WMARK_MIN/WMARK_LOW/WMARK_HIGH]/low_on_memory/zone_wake_kswapd: These
+are per-zone fields, used to determine when a zone needs to be balanced. When
+the number of pages falls below watermark[WMARK_MIN], the hysteric field
+low_on_memory gets set. This stays set till the number of free pages becomes
+watermark[WMARK_HIGH]. When low_on_memory is set, page allocation requests will
+try to free some pages in the zone (providing GFP_WAIT is set in the request).
+Orthogonal to this, is the decision to poke kswapd to free some zone pages.
+That decision is not hysteresis based, and is done when the number of free
+pages is below watermark[WMARK_LOW]; in which case zone_wake_kswapd is also set.
 
 
 (Good) Ideas that I have heard:
diff --git a/Documentation/vm/page-types.c b/Documentation/vm/page-types.c
new file mode 100644
index 00000000000..0833f44ba16
--- /dev/null
+++ b/Documentation/vm/page-types.c
@@ -0,0 +1,698 @@
+/*
+ * page-types: Tool for querying page flags
+ *
+ * Copyright (C) 2009 Intel corporation
+ * Copyright (C) 2009 Wu Fengguang <fengguang.wu@intel.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdint.h>
+#include <stdarg.h>
+#include <string.h>
+#include <getopt.h>
+#include <limits.h>
+#include <sys/types.h>
+#include <sys/errno.h>
+#include <sys/fcntl.h>
+
+
+/*
+ * kernel page flags
+ */
+
+#define KPF_BYTES		8
+#define PROC_KPAGEFLAGS		"/proc/kpageflags"
+
+/* copied from kpageflags_read() */
+#define KPF_LOCKED		0
+#define KPF_ERROR		1
+#define KPF_REFERENCED		2
+#define KPF_UPTODATE		3
+#define KPF_DIRTY		4
+#define KPF_LRU			5
+#define KPF_ACTIVE		6
+#define KPF_SLAB		7
+#define KPF_WRITEBACK		8
+#define KPF_RECLAIM		9
+#define KPF_BUDDY		10
+
+/* [11-20] new additions in 2.6.31 */
+#define KPF_MMAP		11
+#define KPF_ANON		12
+#define KPF_SWAPCACHE		13
+#define KPF_SWAPBACKED		14
+#define KPF_COMPOUND_HEAD	15
+#define KPF_COMPOUND_TAIL	16
+#define KPF_HUGE		17
+#define KPF_UNEVICTABLE		18
+#define KPF_NOPAGE		20
+
+/* [32-] kernel hacking assistances */
+#define KPF_RESERVED		32
+#define KPF_MLOCKED		33
+#define KPF_MAPPEDTODISK	34
+#define KPF_PRIVATE		35
+#define KPF_PRIVATE_2		36
+#define KPF_OWNER_PRIVATE	37
+#define KPF_ARCH		38
+#define KPF_UNCACHED		39
+
+/* [48-] take some arbitrary free slots for expanding overloaded flags
+ * not part of kernel API
+ */
+#define KPF_READAHEAD		48
+#define KPF_SLOB_FREE		49
+#define KPF_SLUB_FROZEN		50
+#define KPF_SLUB_DEBUG		51
+
+#define KPF_ALL_BITS		((uint64_t)~0ULL)
+#define KPF_HACKERS_BITS	(0xffffULL << 32)
+#define KPF_OVERLOADED_BITS	(0xffffULL << 48)
+#define BIT(name)		(1ULL << KPF_##name)
+#define BITS_COMPOUND		(BIT(COMPOUND_HEAD) | BIT(COMPOUND_TAIL))
+
+static char *page_flag_names[] = {
+	[KPF_LOCKED]		= "L:locked",
+	[KPF_ERROR]		= "E:error",
+	[KPF_REFERENCED]	= "R:referenced",
+	[KPF_UPTODATE]		= "U:uptodate",
+	[KPF_DIRTY]		= "D:dirty",
+	[KPF_LRU]		= "l:lru",
+	[KPF_ACTIVE]		= "A:active",
+	[KPF_SLAB]		= "S:slab",
+	[KPF_WRITEBACK]		= "W:writeback",
+	[KPF_RECLAIM]		= "I:reclaim",
+	[KPF_BUDDY]		= "B:buddy",
+
+	[KPF_MMAP]		= "M:mmap",
+	[KPF_ANON]		= "a:anonymous",
+	[KPF_SWAPCACHE]		= "s:swapcache",
+	[KPF_SWAPBACKED]	= "b:swapbacked",
+	[KPF_COMPOUND_HEAD]	= "H:compound_head",
+	[KPF_COMPOUND_TAIL]	= "T:compound_tail",
+	[KPF_HUGE]		= "G:huge",
+	[KPF_UNEVICTABLE]	= "u:unevictable",
+	[KPF_NOPAGE]		= "n:nopage",
+
+	[KPF_RESERVED]		= "r:reserved",
+	[KPF_MLOCKED]		= "m:mlocked",
+	[KPF_MAPPEDTODISK]	= "d:mappedtodisk",
+	[KPF_PRIVATE]		= "P:private",
+	[KPF_PRIVATE_2]		= "p:private_2",
+	[KPF_OWNER_PRIVATE]	= "O:owner_private",
+	[KPF_ARCH]		= "h:arch",
+	[KPF_UNCACHED]		= "c:uncached",
+
+	[KPF_READAHEAD]		= "I:readahead",
+	[KPF_SLOB_FREE]		= "P:slob_free",
+	[KPF_SLUB_FROZEN]	= "A:slub_frozen",
+	[KPF_SLUB_DEBUG]	= "E:slub_debug",
+};
+
+
+/*
+ * data structures
+ */
+
+static int		opt_raw;	/* for kernel developers */
+static int		opt_list;	/* list pages (in ranges) */
+static int		opt_no_summary;	/* don't show summary */
+static pid_t		opt_pid;	/* process to walk */
+
+#define MAX_ADDR_RANGES	1024
+static int		nr_addr_ranges;
+static unsigned long	opt_offset[MAX_ADDR_RANGES];
+static unsigned long	opt_size[MAX_ADDR_RANGES];
+
+#define MAX_BIT_FILTERS	64
+static int		nr_bit_filters;
+static uint64_t		opt_mask[MAX_BIT_FILTERS];
+static uint64_t		opt_bits[MAX_BIT_FILTERS];
+
+static int		page_size;
+
+#define PAGES_BATCH	(64 << 10)	/* 64k pages */
+static int		kpageflags_fd;
+static uint64_t		kpageflags_buf[KPF_BYTES * PAGES_BATCH];
+
+#define HASH_SHIFT	13
+#define HASH_SIZE	(1 << HASH_SHIFT)
+#define HASH_MASK	(HASH_SIZE - 1)
+#define HASH_KEY(flags)	(flags & HASH_MASK)
+
+static unsigned long	total_pages;
+static unsigned long	nr_pages[HASH_SIZE];
+static uint64_t 	page_flags[HASH_SIZE];
+
+
+/*
+ * helper functions
+ */
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+
+#define min_t(type, x, y) ({			\
+	type __min1 = (x);			\
+	type __min2 = (y);			\
+	__min1 < __min2 ? __min1 : __min2; })
+
+unsigned long pages2mb(unsigned long pages)
+{
+	return (pages * page_size) >> 20;
+}
+
+void fatal(const char *x, ...)
+{
+	va_list ap;
+
+	va_start(ap, x);
+	vfprintf(stderr, x, ap);
+	va_end(ap);
+	exit(EXIT_FAILURE);
+}
+
+
+/*
+ * page flag names
+ */
+
+char *page_flag_name(uint64_t flags)
+{
+	static char buf[65];
+	int present;
+	int i, j;
+
+	for (i = 0, j = 0; i < ARRAY_SIZE(page_flag_names); i++) {
+		present = (flags >> i) & 1;
+		if (!page_flag_names[i]) {
+			if (present)
+				fatal("unkown flag bit %d\n", i);
+			continue;
+		}
+		buf[j++] = present ? page_flag_names[i][0] : '_';
+	}
+
+	return buf;
+}
+
+char *page_flag_longname(uint64_t flags)
+{
+	static char buf[1024];
+	int i, n;
+
+	for (i = 0, n = 0; i < ARRAY_SIZE(page_flag_names); i++) {
+		if (!page_flag_names[i])
+			continue;
+		if ((flags >> i) & 1)
+			n += snprintf(buf + n, sizeof(buf) - n, "%s,",
+					page_flag_names[i] + 2);
+	}
+	if (n)
+		n--;
+	buf[n] = '\0';
+
+	return buf;
+}
+
+
+/*
+ * page list and summary
+ */
+
+void show_page_range(unsigned long offset, uint64_t flags)
+{
+	static uint64_t      flags0;
+	static unsigned long index;
+	static unsigned long count;
+
+	if (flags == flags0 && offset == index + count) {
+		count++;
+		return;
+	}
+
+	if (count)
+		printf("%lu\t%lu\t%s\n",
+				index, count, page_flag_name(flags0));
+
+	flags0 = flags;
+	index  = offset;
+	count  = 1;
+}
+
+void show_page(unsigned long offset, uint64_t flags)
+{
+	printf("%lu\t%s\n", offset, page_flag_name(flags));
+}
+
+void show_summary(void)
+{
+	int i;
+
+	printf("             flags\tpage-count       MB"
+		"  symbolic-flags\t\t\tlong-symbolic-flags\n");
+
+	for (i = 0; i < ARRAY_SIZE(nr_pages); i++) {
+		if (nr_pages[i])
+			printf("0x%016llx\t%10lu %8lu  %s\t%s\n",
+				(unsigned long long)page_flags[i],
+				nr_pages[i],
+				pages2mb(nr_pages[i]),
+				page_flag_name(page_flags[i]),
+				page_flag_longname(page_flags[i]));
+	}
+
+	printf("             total\t%10lu %8lu\n",
+			total_pages, pages2mb(total_pages));
+}
+
+
+/*
+ * page flag filters
+ */
+
+int bit_mask_ok(uint64_t flags)
+{
+	int i;
+
+	for (i = 0; i < nr_bit_filters; i++) {
+		if (opt_bits[i] == KPF_ALL_BITS) {
+			if ((flags & opt_mask[i]) == 0)
+				return 0;
+		} else {
+			if ((flags & opt_mask[i]) != opt_bits[i])
+				return 0;
+		}
+	}
+
+	return 1;
+}
+
+uint64_t expand_overloaded_flags(uint64_t flags)
+{
+	/* SLOB/SLUB overload several page flags */
+	if (flags & BIT(SLAB)) {
+		if (flags & BIT(PRIVATE))
+			flags ^= BIT(PRIVATE) | BIT(SLOB_FREE);
+		if (flags & BIT(ACTIVE))
+			flags ^= BIT(ACTIVE) | BIT(SLUB_FROZEN);
+		if (flags & BIT(ERROR))
+			flags ^= BIT(ERROR) | BIT(SLUB_DEBUG);
+	}
+
+	/* PG_reclaim is overloaded as PG_readahead in the read path */
+	if ((flags & (BIT(RECLAIM) | BIT(WRITEBACK))) == BIT(RECLAIM))
+		flags ^= BIT(RECLAIM) | BIT(READAHEAD);
+
+	return flags;
+}
+
+uint64_t well_known_flags(uint64_t flags)
+{
+	/* hide flags intended only for kernel hacker */
+	flags &= ~KPF_HACKERS_BITS;
+
+	/* hide non-hugeTLB compound pages */
+	if ((flags & BITS_COMPOUND) && !(flags & BIT(HUGE)))
+		flags &= ~BITS_COMPOUND;
+
+	return flags;
+}
+
+
+/*
+ * page frame walker
+ */
+
+int hash_slot(uint64_t flags)
+{
+	int k = HASH_KEY(flags);
+	int i;
+
+	/* Explicitly reserve slot 0 for flags 0: the following logic
+	 * cannot distinguish an unoccupied slot from slot (flags==0).
+	 */
+	if (flags == 0)
+		return 0;
+
+	/* search through the remaining (HASH_SIZE-1) slots */
+	for (i = 1; i < ARRAY_SIZE(page_flags); i++, k++) {
+		if (!k || k >= ARRAY_SIZE(page_flags))
+			k = 1;
+		if (page_flags[k] == 0) {
+			page_flags[k] = flags;
+			return k;
+		}
+		if (page_flags[k] == flags)
+			return k;
+	}
+
+	fatal("hash table full: bump up HASH_SHIFT?\n");
+	exit(EXIT_FAILURE);
+}
+
+void add_page(unsigned long offset, uint64_t flags)
+{
+	flags = expand_overloaded_flags(flags);
+
+	if (!opt_raw)
+		flags = well_known_flags(flags);
+
+	if (!bit_mask_ok(flags))
+		return;
+
+	if (opt_list == 1)
+		show_page_range(offset, flags);
+	else if (opt_list == 2)
+		show_page(offset, flags);
+
+	nr_pages[hash_slot(flags)]++;
+	total_pages++;
+}
+
+void walk_pfn(unsigned long index, unsigned long count)
+{
+	unsigned long batch;
+	unsigned long n;
+	unsigned long i;
+
+	if (index > ULONG_MAX / KPF_BYTES)
+		fatal("index overflow: %lu\n", index);
+
+	lseek(kpageflags_fd, index * KPF_BYTES, SEEK_SET);
+
+	while (count) {
+		batch = min_t(unsigned long, count, PAGES_BATCH);
+		n = read(kpageflags_fd, kpageflags_buf, batch * KPF_BYTES);
+		if (n == 0)
+			break;
+		if (n < 0) {
+			perror(PROC_KPAGEFLAGS);
+			exit(EXIT_FAILURE);
+		}
+
+		if (n % KPF_BYTES != 0)
+			fatal("partial read: %lu bytes\n", n);
+		n = n / KPF_BYTES;
+
+		for (i = 0; i < n; i++)
+			add_page(index + i, kpageflags_buf[i]);
+
+		index += batch;
+		count -= batch;
+	}
+}
+
+void walk_addr_ranges(void)
+{
+	int i;
+
+	kpageflags_fd = open(PROC_KPAGEFLAGS, O_RDONLY);
+	if (kpageflags_fd < 0) {
+		perror(PROC_KPAGEFLAGS);
+		exit(EXIT_FAILURE);
+	}
+
+	if (!nr_addr_ranges)
+		walk_pfn(0, ULONG_MAX);
+
+	for (i = 0; i < nr_addr_ranges; i++)
+		walk_pfn(opt_offset[i], opt_size[i]);
+
+	close(kpageflags_fd);
+}
+
+
+/*
+ * user interface
+ */
+
+const char *page_flag_type(uint64_t flag)
+{
+	if (flag & KPF_HACKERS_BITS)
+		return "(r)";
+	if (flag & KPF_OVERLOADED_BITS)
+		return "(o)";
+	return "   ";
+}
+
+void usage(void)
+{
+	int i, j;
+
+	printf(
+"page-types [options]\n"
+"            -r|--raw                  Raw mode, for kernel developers\n"
+"            -a|--addr    addr-spec    Walk a range of pages\n"
+"            -b|--bits    bits-spec    Walk pages with specified bits\n"
+#if 0 /* planned features */
+"            -p|--pid     pid          Walk process address space\n"
+"            -f|--file    filename     Walk file address space\n"
+#endif
+"            -l|--list                 Show page details in ranges\n"
+"            -L|--list-each            Show page details one by one\n"
+"            -N|--no-summary           Don't show summay info\n"
+"            -h|--help                 Show this usage message\n"
+"addr-spec:\n"
+"            N                         one page at offset N (unit: pages)\n"
+"            N+M                       pages range from N to N+M-1\n"
+"            N,M                       pages range from N to M-1\n"
+"            N,                        pages range from N to end\n"
+"            ,M                        pages range from 0 to M\n"
+"bits-spec:\n"
+"            bit1,bit2                 (flags & (bit1|bit2)) != 0\n"
+"            bit1,bit2=bit1            (flags & (bit1|bit2)) == bit1\n"
+"            bit1,~bit2                (flags & (bit1|bit2)) == bit1\n"
+"            =bit1,bit2                flags == (bit1|bit2)\n"
+"bit-names:\n"
+	);
+
+	for (i = 0, j = 0; i < ARRAY_SIZE(page_flag_names); i++) {
+		if (!page_flag_names[i])
+			continue;
+		printf("%16s%s", page_flag_names[i] + 2,
+				 page_flag_type(1ULL << i));
+		if (++j > 3) {
+			j = 0;
+			putchar('\n');
+		}
+	}
+	printf("\n                                   "
+		"(r) raw mode bits  (o) overloaded bits\n");
+}
+
+unsigned long long parse_number(const char *str)
+{
+	unsigned long long n;
+
+	n = strtoll(str, NULL, 0);
+
+	if (n == 0 && str[0] != '0')
+		fatal("invalid name or number: %s\n", str);
+
+	return n;
+}
+
+void parse_pid(const char *str)
+{
+	opt_pid = parse_number(str);
+}
+
+void parse_file(const char *name)
+{
+}
+
+void add_addr_range(unsigned long offset, unsigned long size)
+{
+	if (nr_addr_ranges >= MAX_ADDR_RANGES)
+		fatal("too much addr ranges\n");
+
+	opt_offset[nr_addr_ranges] = offset;
+	opt_size[nr_addr_ranges] = size;
+	nr_addr_ranges++;
+}
+
+void parse_addr_range(const char *optarg)
+{
+	unsigned long offset;
+	unsigned long size;
+	char *p;
+
+	p = strchr(optarg, ',');
+	if (!p)
+		p = strchr(optarg, '+');
+
+	if (p == optarg) {
+		offset = 0;
+		size   = parse_number(p + 1);
+	} else if (p) {
+		offset = parse_number(optarg);
+		if (p[1] == '\0')
+			size = ULONG_MAX;
+		else {
+			size = parse_number(p + 1);
+			if (*p == ',') {
+				if (size < offset)
+					fatal("invalid range: %lu,%lu\n",
+							offset, size);
+				size -= offset;
+			}
+		}
+	} else {
+		offset = parse_number(optarg);
+		size   = 1;
+	}
+
+	add_addr_range(offset, size);
+}
+
+void add_bits_filter(uint64_t mask, uint64_t bits)
+{
+	if (nr_bit_filters >= MAX_BIT_FILTERS)
+		fatal("too much bit filters\n");
+
+	opt_mask[nr_bit_filters] = mask;
+	opt_bits[nr_bit_filters] = bits;
+	nr_bit_filters++;
+}
+
+uint64_t parse_flag_name(const char *str, int len)
+{
+	int i;
+
+	if (!*str || !len)
+		return 0;
+
+	if (len <= 8 && !strncmp(str, "compound", len))
+		return BITS_COMPOUND;
+
+	for (i = 0; i < ARRAY_SIZE(page_flag_names); i++) {
+		if (!page_flag_names[i])
+			continue;
+		if (!strncmp(str, page_flag_names[i] + 2, len))
+			return 1ULL << i;
+	}
+
+	return parse_number(str);
+}
+
+uint64_t parse_flag_names(const char *str, int all)
+{
+	const char *p    = str;
+	uint64_t   flags = 0;
+
+	while (1) {
+		if (*p == ',' || *p == '=' || *p == '\0') {
+			if ((*str != '~') || (*str == '~' && all && *++str))
+				flags |= parse_flag_name(str, p - str);
+			if (*p != ',')
+				break;
+			str = p + 1;
+		}
+		p++;
+	}
+
+	return flags;
+}
+
+void parse_bits_mask(const char *optarg)
+{
+	uint64_t mask;
+	uint64_t bits;
+	const char *p;
+
+	p = strchr(optarg, '=');
+	if (p == optarg) {
+		mask = KPF_ALL_BITS;
+		bits = parse_flag_names(p + 1, 0);
+	} else if (p) {
+		mask = parse_flag_names(optarg, 0);
+		bits = parse_flag_names(p + 1, 0);
+	} else if (strchr(optarg, '~')) {
+		mask = parse_flag_names(optarg, 1);
+		bits = parse_flag_names(optarg, 0);
+	} else {
+		mask = parse_flag_names(optarg, 0);
+		bits = KPF_ALL_BITS;
+	}
+
+	add_bits_filter(mask, bits);
+}
+
+
+struct option opts[] = {
+	{ "raw"       , 0, NULL, 'r' },
+	{ "pid"       , 1, NULL, 'p' },
+	{ "file"      , 1, NULL, 'f' },
+	{ "addr"      , 1, NULL, 'a' },
+	{ "bits"      , 1, NULL, 'b' },
+	{ "list"      , 0, NULL, 'l' },
+	{ "list-each" , 0, NULL, 'L' },
+	{ "no-summary", 0, NULL, 'N' },
+	{ "help"      , 0, NULL, 'h' },
+	{ NULL        , 0, NULL, 0 }
+};
+
+int main(int argc, char *argv[])
+{
+	int c;
+
+	page_size = getpagesize();
+
+	while ((c = getopt_long(argc, argv,
+				"rp:f:a:b:lLNh", opts, NULL)) != -1) {
+		switch (c) {
+		case 'r':
+			opt_raw = 1;
+			break;
+		case 'p':
+			parse_pid(optarg);
+			break;
+		case 'f':
+			parse_file(optarg);
+			break;
+		case 'a':
+			parse_addr_range(optarg);
+			break;
+		case 'b':
+			parse_bits_mask(optarg);
+			break;
+		case 'l':
+			opt_list = 1;
+			break;
+		case 'L':
+			opt_list = 2;
+			break;
+		case 'N':
+			opt_no_summary = 1;
+			break;
+		case 'h':
+			usage();
+			exit(0);
+		default:
+			usage();
+			exit(1);
+		}
+	}
+
+	if (opt_list == 1)
+		printf("offset\tcount\tflags\n");
+	if (opt_list == 2)
+		printf("offset\tflags\n");
+
+	walk_addr_ranges();
+
+	if (opt_list == 1)
+		show_page_range(0, 0);  /* drain the buffer */
+
+	if (opt_no_summary)
+		return 0;
+
+	if (opt_list)
+		printf("\n\n");
+
+	show_summary();
+
+	return 0;
+}
diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt
index ce72c0fe617..600a304a828 100644
--- a/Documentation/vm/pagemap.txt
+++ b/Documentation/vm/pagemap.txt
@@ -12,9 +12,9 @@ There are three components to pagemap:
    value for each virtual page, containing the following data (from
    fs/proc/task_mmu.c, above pagemap_read):
 
-    * Bits 0-55  page frame number (PFN) if present
+    * Bits 0-54  page frame number (PFN) if present
     * Bits 0-4   swap type if swapped
-    * Bits 5-55  swap offset if swapped
+    * Bits 5-54  swap offset if swapped
     * Bits 55-60 page shift (page size = 1<<page shift)
     * Bit  61    reserved for future use
     * Bit  62    page swapped
@@ -36,7 +36,7 @@ There are three components to pagemap:
  * /proc/kpageflags.  This file contains a 64-bit set of flags for each
    page, indexed by PFN.
 
-   The flags are (from fs/proc/proc_misc, above kpageflags_read):
+   The flags are (from fs/proc/page.c, above kpageflags_read):
 
      0. LOCKED
      1. ERROR
@@ -49,6 +49,68 @@ There are three components to pagemap:
      8. WRITEBACK
      9. RECLAIM
     10. BUDDY
+    11. MMAP
+    12. ANON
+    13. SWAPCACHE
+    14. SWAPBACKED
+    15. COMPOUND_HEAD
+    16. COMPOUND_TAIL
+    16. HUGE
+    18. UNEVICTABLE
+    20. NOPAGE
+
+Short descriptions to the page flags:
+
+ 0. LOCKED
+    page is being locked for exclusive access, eg. by undergoing read/write IO
+
+ 7. SLAB
+    page is managed by the SLAB/SLOB/SLUB/SLQB kernel memory allocator
+    When compound page is used, SLUB/SLQB will only set this flag on the head
+    page; SLOB will not flag it at all.
+
+10. BUDDY
+    a free memory block managed by the buddy system allocator
+    The buddy system organizes free memory in blocks of various orders.
+    An order N block has 2^N physically contiguous pages, with the BUDDY flag
+    set for and _only_ for the first page.
+
+15. COMPOUND_HEAD
+16. COMPOUND_TAIL
+    A compound page with order N consists of 2^N physically contiguous pages.
+    A compound page with order 2 takes the form of "HTTT", where H donates its
+    head page and T donates its tail page(s).  The major consumers of compound
+    pages are hugeTLB pages (Documentation/vm/hugetlbpage.txt), the SLUB etc.
+    memory allocators and various device drivers. However in this interface,
+    only huge/giga pages are made visible to end users.
+17. HUGE
+    this is an integral part of a HugeTLB page
+
+20. NOPAGE
+    no page frame exists at the requested address
+
+    [IO related page flags]
+ 1. ERROR     IO error occurred
+ 3. UPTODATE  page has up-to-date data
+              ie. for file backed page: (in-memory data revision >= on-disk one)
+ 4. DIRTY     page has been written to, hence contains new data
+              ie. for file backed page: (in-memory data revision >  on-disk one)
+ 8. WRITEBACK page is being synced to disk
+
+    [LRU related page flags]
+ 5. LRU         page is in one of the LRU lists
+ 6. ACTIVE      page is in the active LRU list
+18. UNEVICTABLE page is in the unevictable (non-)LRU list
+                It is somehow pinned and not a candidate for LRU page reclaims,
+		eg. ramfs pages, shmctl(SHM_LOCK) and mlock() memory segments
+ 2. REFERENCED  page has been referenced since last LRU list enqueue/requeue
+ 9. RECLAIM     page will be reclaimed soon after its pageout IO completed
+11. MMAP        a memory mapped page
+12. ANON        a memory mapped page that is not part of a file
+13. SWAPCACHE   page is mapped to swap space, ie. has an associated swap entry
+14. SWAPBACKED  page is backed by swap/RAM
+
+The page-types tool in this directory can be used to query the above flags.
 
 Using pagemap to do something useful:
 
diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index e0203662f9e..8da3a795083 100644
--- a/Documentation/x86/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -50,6 +50,10 @@ Protocol 2.08:	(Kernel 2.6.26) Added crc32 checksum and ELF format
 Protocol 2.09:	(Kernel 2.6.26) Added a field of 64-bit physical
 		pointer to single linked list of struct	setup_data.
 
+Protocol 2.10:	(Kernel 2.6.31) Added a protocol for relaxed alignment
+		beyond the kernel_alignment added, new init_size and
+		pref_address fields.  Added extended boot loader IDs.
+
 **** MEMORY LAYOUT
 
 The traditional memory map for the kernel loader, used for Image or
@@ -168,12 +172,13 @@ Offset	Proto	Name		Meaning
 021C/4	2.00+	ramdisk_size	initrd size (set by boot loader)
 0220/4	2.00+	bootsect_kludge	DO NOT USE - for bootsect.S use only
 0224/2	2.01+	heap_end_ptr	Free memory after setup end
-0226/2	N/A	pad1		Unused
+0226/1	2.02+(3 ext_loader_ver	Extended boot loader version
+0227/1	2.02+(3	ext_loader_type	Extended boot loader ID
 0228/4	2.02+	cmd_line_ptr	32-bit pointer to the kernel command line
 022C/4	2.03+	ramdisk_max	Highest legal initrd address
 0230/4	2.05+	kernel_alignment Physical addr alignment required for kernel
 0234/1	2.05+	relocatable_kernel Whether kernel is relocatable or not
-0235/1	N/A	pad2		Unused
+0235/1	2.10+	min_alignment	Minimum alignment, as a power of two
 0236/2	N/A	pad3		Unused
 0238/4	2.06+	cmdline_size	Maximum size of the kernel command line
 023C/4	2.07+	hardware_subarch Hardware subarchitecture
@@ -182,6 +187,8 @@ Offset	Proto	Name		Meaning
 024C/4	2.08+	payload_length	Length of kernel payload
 0250/8	2.09+	setup_data	64-bit physical pointer to linked list
 				of struct setup_data
+0258/8	2.10+	pref_address	Preferred loading address
+0260/4	2.10+	init_size	Linear memory required during initialization
 
 (1) For backwards compatibility, if the setup_sects field contains 0, the
     real value is 4.
@@ -190,6 +197,8 @@ Offset	Proto	Name		Meaning
     field are unusable, which means the size of a bzImage kernel
     cannot be determined.
 
+(3) Ignored, but safe to set, for boot protocols 2.02-2.09.
+
 If the "HdrS" (0x53726448) magic number is not found at offset 0x202,
 the boot protocol version is "old".  Loading an old kernel, the
 following parameters should be assumed:
@@ -343,18 +352,32 @@ Protocol:	2.00+
   0xTV here, where T is an identifier for the boot loader and V is
   a version number.  Otherwise, enter 0xFF here.
 
+  For boot loader IDs above T = 0xD, write T = 0xE to this field and
+  write the extended ID minus 0x10 to the ext_loader_type field.
+  Similarly, the ext_loader_ver field can be used to provide more than
+  four bits for the bootloader version.
+
+  For example, for T = 0x15, V = 0x234, write:
+
+  type_of_loader  <- 0xE4
+  ext_loader_type <- 0x05
+  ext_loader_ver  <- 0x23
+
   Assigned boot loader ids:
 	0  LILO			(0x00 reserved for pre-2.00 bootloader)
 	1  Loadlin
 	2  bootsect-loader	(0x20, all other values reserved)
-	3  SYSLINUX
-	4  EtherBoot
+	3  Syslinux
+	4  Etherboot/gPXE
 	5  ELILO
 	7  GRUB
-	8  U-BOOT
+	8  U-Boot
 	9  Xen
 	A  Gujin
 	B  Qemu
+	C  Arcturus Networks uCbootloader
+	E  Extended		(see ext_loader_type)
+	F  Special		(0xFF = undefined)
 
   Please contact <hpa@zytor.com> if you need a bootloader ID
   value assigned.
@@ -453,6 +476,35 @@ Protocol:	2.01+
   Set this field to the offset (from the beginning of the real-mode
   code) of the end of the setup stack/heap, minus 0x0200.
 
+Field name:	ext_loader_ver
+Type:		write (optional)
+Offset/size:	0x226/1
+Protocol:	2.02+
+
+  This field is used as an extension of the version number in the
+  type_of_loader field.  The total version number is considered to be
+  (type_of_loader & 0x0f) + (ext_loader_ver << 4).
+
+  The use of this field is boot loader specific.  If not written, it
+  is zero.
+
+  Kernels prior to 2.6.31 did not recognize this field, but it is safe
+  to write for protocol version 2.02 or higher.
+
+Field name:	ext_loader_type
+Type:		write (obligatory if (type_of_loader & 0xf0) == 0xe0)
+Offset/size:	0x227/1
+Protocol:	2.02+
+
+  This field is used as an extension of the type number in
+  type_of_loader field.  If the type in type_of_loader is 0xE, then
+  the actual type is (ext_loader_type + 0x10).
+
+  This field is ignored if the type in type_of_loader is not 0xE.
+
+  Kernels prior to 2.6.31 did not recognize this field, but it is safe
+  to write for protocol version 2.02 or higher.
+
 Field name:	cmd_line_ptr
 Type:		write (obligatory)
 Offset/size:	0x228/4
@@ -482,11 +534,19 @@ Protocol:	2.03+
   0x37FFFFFF, you can start your ramdisk at 0x37FE0000.)
 
 Field name:	kernel_alignment
-Type:		read (reloc)
+Type:		read/modify (reloc)
 Offset/size:	0x230/4
-Protocol:	2.05+
+Protocol:	2.05+ (read), 2.10+ (modify)
+
+  Alignment unit required by the kernel (if relocatable_kernel is
+  true.)  A relocatable kernel that is loaded at an alignment
+  incompatible with the value in this field will be realigned during
+  kernel initialization.
 
-  Alignment unit required by the kernel (if relocatable_kernel is true.)
+  Starting with protocol version 2.10, this reflects the kernel
+  alignment preferred for optimal performance; it is possible for the
+  loader to modify this field to permit a lesser alignment.  See the
+  min_alignment and pref_address field below.
 
 Field name:	relocatable_kernel
 Type:		read (reloc)
@@ -498,6 +558,22 @@ Protocol:	2.05+
   After loading, the boot loader must set the code32_start field to
   point to the loaded code, or to a boot loader hook.
 
+Field name:	min_alignment
+Type:		read (reloc)
+Offset/size:	0x235/1
+Protocol:	2.10+
+
+  This field, if nonzero, indicates as a power of two the minimum
+  alignment required, as opposed to preferred, by the kernel to boot.
+  If a boot loader makes use of this field, it should update the
+  kernel_alignment field with the alignment unit desired; typically:
+
+	kernel_alignment = 1 << min_alignment
+
+  There may be a considerable performance cost with an excessively
+  misaligned kernel.  Therefore, a loader should typically try each
+  power-of-two alignment from kernel_alignment down to this alignment.
+
 Field name:	cmdline_size
 Type:		read
 Offset/size:	0x238/4
@@ -582,6 +658,36 @@ Protocol:	2.09+
   sure to consider the case where the linked list already contains
   entries.
 
+Field name:	pref_address
+Type:		read (reloc)
+Offset/size:	0x258/8
+Protocol:	2.10+
+
+  This field, if nonzero, represents a preferred load address for the
+  kernel.  A relocating bootloader should attempt to load at this
+  address if possible.
+
+  A non-relocatable kernel will unconditionally move itself and to run
+  at this address.
+
+Field name:	init_size
+Type:		read
+Offset/size:	0x25c/4
+
+  This field indicates the amount of linear contiguous memory starting
+  at the kernel runtime start address that the kernel needs before it
+  is capable of examining its memory map.  This is not the same thing
+  as the total amount of memory the kernel needs to boot, but it can
+  be used by a relocating boot loader to help select a safe load
+  address for the kernel.
+
+  The kernel runtime start address is determined by the following algorithm:
+
+  if (relocatable_kernel)
+	runtime_start = align_up(load_address, kernel_alignment)
+  else
+	runtime_start = pref_address
+
 
 **** THE IMAGE CHECKSUM
 
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 34c13040a71..29a6ff8bc7d 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -5,21 +5,51 @@ only the AMD64 specific ones are listed here.
 
 Machine check
 
-   mce=off disable machine check
-   mce=bootlog Enable logging of machine checks left over from booting.
-               Disabled by default on AMD because some BIOS leave bogus ones.
-               If your BIOS doesn't do that it's a good idea to enable though
-               to make sure you log even machine check events that result
-               in a reboot. On Intel systems it is enabled by default.
+   Please see Documentation/x86/x86_64/machinecheck for sysfs runtime tunables.
+
+   mce=off
+		Disable machine check
+   mce=no_cmci
+		Disable CMCI(Corrected Machine Check Interrupt) that
+		Intel processor supports.  Usually this disablement is
+		not recommended, but it might be handy if your hardware
+		is misbehaving.
+		Note that you'll get more problems without CMCI than with
+		due to the shared banks, i.e. you might get duplicated
+		error logs.
+   mce=dont_log_ce
+		Don't make logs for corrected errors.  All events reported
+		as corrected are silently cleared by OS.
+		This option will be useful if you have no interest in any
+		of corrected errors.
+   mce=ignore_ce
+		Disable features for corrected errors, e.g. polling timer
+		and CMCI.  All events reported as corrected are not cleared
+		by OS and remained in its error banks.
+		Usually this disablement is not recommended, however if
+		there is an agent checking/clearing corrected errors
+		(e.g. BIOS or hardware monitoring applications), conflicting
+		with OS's error handling, and you cannot deactivate the agent,
+		then this option will be a help.
+   mce=bootlog
+		Enable logging of machine checks left over from booting.
+		Disabled by default on AMD because some BIOS leave bogus ones.
+		If your BIOS doesn't do that it's a good idea to enable though
+		to make sure you log even machine check events that result
+		in a reboot. On Intel systems it is enabled by default.
    mce=nobootlog
 		Disable boot machine check logging.
-   mce=tolerancelevel (number)
+   mce=tolerancelevel[,monarchtimeout] (number,number)
+		tolerance levels:
 		0: always panic on uncorrected errors, log corrected errors
 		1: panic or SIGBUS on uncorrected errors, log corrected errors
 		2: SIGBUS or log uncorrected errors, log corrected errors
 		3: never panic or SIGBUS, log all errors (for testing only)
 		Default is 1
 		Can be also set using sysfs which is preferable.
+		monarchtimeout:
+		Sets the time in us to wait for other CPUs on machine checks. 0
+		to disable.
 
    nomce (for compatibility with i386): same as mce=off
 
@@ -150,11 +180,6 @@ NUMA
 		Otherwise, the remaining system RAM is allocated to an
 		additional node.
 
-  numa=hotadd=percent
-		Only allow hotadd memory to preallocate page structures upto
-		percent of already available memory.
-		numa=hotadd=0 will disable hotadd memory.
-
 ACPI
 
   acpi=off	Don't enable ACPI
diff --git a/Documentation/x86/x86_64/machinecheck b/Documentation/x86/x86_64/machinecheck
index a05e58e7b15..b1fb3027328 100644
--- a/Documentation/x86/x86_64/machinecheck
+++ b/Documentation/x86/x86_64/machinecheck
@@ -41,7 +41,9 @@ check_interval
 	the polling interval.  When the poller stops finding MCEs, it
 	triggers an exponential backoff (poll less often) on the polling
 	interval. The check_interval variable is both the initial and
-	maximum polling interval.
+	maximum polling interval. 0 means no polling for corrected machine
+	check errors (but some corrected errors might be still reported
+	in other ways)
 
 tolerant
 	Tolerance level. When a machine check exception occurs for a non
@@ -67,6 +69,10 @@ trigger
 	Program to run when a machine check event is detected.
 	This is an alternative to running mcelog regularly from cron
 	and allows to detect events faster.
+monarch_timeout
+	How long to wait for the other CPUs to machine check too on a
+	exception. 0 to disable waiting for other CPUs.
+	Unit: us
 
 TBD document entries for AMD threshold interrupt configuration
 
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 29b52b14d0b..d6498e3cd71 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -6,10 +6,11 @@ Virtual memory map with 4 level page tables:
 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
 hole caused by [48:63] sign extension
 ffff800000000000 - ffff80ffffffffff (=40 bits) guard hole
-ffff880000000000 - ffffc0ffffffffff (=57 TB) direct mapping of all phys. memory
-ffffc10000000000 - ffffc1ffffffffff (=40 bits) hole
-ffffc20000000000 - ffffe1ffffffffff (=45 bits) vmalloc/ioremap space
-ffffe20000000000 - ffffe2ffffffffff (=40 bits) virtual memory map (1TB)
+ffff880000000000 - ffffc7ffffffffff (=64 TB) direct mapping of all phys. memory
+ffffc80000000000 - ffffc8ffffffffff (=40 bits) hole
+ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space
+ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole
+ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
 ffffffff80000000 - ffffffffa0000000 (=512 MB)  kernel text mapping, from phys 0
 ffffffffa0000000 - fffffffffff00000 (=1536 MB) module mapping space
author	Ingo Molnar <mingo@elte.hu>	2009-06-17 12:52:15 +0200
committer	Ingo Molnar <mingo@elte.hu>	2009-06-17 12:56:49 +0200
commit	eadb8a091b27a840de7450f84ecff5ef13476424 (patch)
tree	58c3782d40def63baa8167f3d31e3048cb4c7660 /Documentation
parent	73874005cd8800440be4299bd095387fff4b90ac (diff)
parent	65795efbd380a832ae508b04dba8f8e53f0b84d9 (diff)
download	kernel-crypto-eadb8a091b27a840de7450f84ecff5ef13476424.tar.gz kernel-crypto-eadb8a091b27a840de7450f84ecff5ef13476424.tar.xz kernel-crypto-eadb8a091b27a840de7450f84ecff5ef13476424.zip