Merge branch 'rtmerge'

Signed-off-by: Scott Wood <scottwood@freescale.com>

Conflicts:
	arch/arm/kvm/mmu.c
	arch/arm/mm/proc-v7-3level.S
	arch/powerpc/kernel/vdso32/getcpu.S
	drivers/crypto/caam/error.c
	drivers/crypto/caam/sg_sw_sec4.h
	drivers/usb/host/ehci-fsl.c

20 files changed, 270 insertions, 32 deletions

diff --git a/Documentation/ABI/testing/ima_policy b/Documentation/ABI/testing/ima_policy
index f1c5cc9..4c3efe4 100644
--- a/Documentation/ABI/testing/ima_policy
+++ b/Documentation/ABI/testing/ima_policy
@@ -23,7 +23,7 @@ Description:
 				 [fowner]]
 			lsm:	[[subj_user=] [subj_role=] [subj_type=]
 				 [obj_user=] [obj_role=] [obj_type=]]
-			option:	[[appraise_type=]]
+			option:	[[appraise_type=]] [permit_directio]
 
 		base: 	func:= [BPRM_CHECK][MMAP_CHECK][FILE_CHECK][MODULE_CHECK]
 			mask:= [MAY_READ] [MAY_WRITE] [MAY_APPEND] [MAY_EXEC]
diff --git a/Documentation/DMA-API-HOWTO.txt b/Documentation/DMA-API-HOWTO.txt
index 14129f1..5e98303 100644
--- a/Documentation/DMA-API-HOWTO.txt
+++ b/Documentation/DMA-API-HOWTO.txt
@@ -101,14 +101,23 @@ style to do this even if your device holds the default setting,
 because this shows that you did think about these issues wrt. your
 device.
 
-The query is performed via a call to dma_set_mask():
+The query is performed via a call to dma_set_mask_and_coherent():
 
-	int dma_set_mask(struct device *dev, u64 mask);
+	int dma_set_mask_and_coherent(struct device *dev, u64 mask);
 
-The query for consistent allocations is performed via a call to
-dma_set_coherent_mask():
+which will query the mask for both streaming and coherent APIs together.
+If you have some special requirements, then the following two separate
+queries can be used instead:
 
-	int dma_set_coherent_mask(struct device *dev, u64 mask);
+	The query for streaming mappings is performed via a call to
+	dma_set_mask():
+
+		int dma_set_mask(struct device *dev, u64 mask);
+
+	The query for consistent allocations is performed via a call
+	to dma_set_coherent_mask():
+
+		int dma_set_coherent_mask(struct device *dev, u64 mask);
 
 Here, dev is a pointer to the device struct of your device, and mask
 is a bit mask describing which bits of an address your device
@@ -137,7 +146,7 @@ exactly why.
 
 The standard 32-bit addressing device would do something like this:
 
-	if (dma_set_mask(dev, DMA_BIT_MASK(32))) {
+	if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32))) {
 		printk(KERN_WARNING
 		       "mydev: No suitable DMA available.\n");
 		goto ignore_this_device;
@@ -171,22 +180,20 @@ the case would look like this:
 
 	int using_dac, consistent_using_dac;
 
-	if (!dma_set_mask(dev, DMA_BIT_MASK(64))) {
+	if (!dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64))) {
 		using_dac = 1;
 	   	consistent_using_dac = 1;
-		dma_set_coherent_mask(dev, DMA_BIT_MASK(64));
-	} else if (!dma_set_mask(dev, DMA_BIT_MASK(32))) {
+	} else if (!dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32))) {
 		using_dac = 0;
 		consistent_using_dac = 0;
-		dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
 	} else {
 		printk(KERN_WARNING
 		       "mydev: No suitable DMA available.\n");
 		goto ignore_this_device;
 	}
 
-dma_set_coherent_mask() will always be able to set the same or a
-smaller mask as dma_set_mask(). However for the rare case that a
+The coherent coherent mask will always be able to set the same or a
+smaller mask as the streaming mask. However for the rare case that a
 device driver only uses consistent allocations, one would have to
 check the return value from dma_set_coherent_mask().
 
@@ -199,9 +206,9 @@ address you might do something like:
 		goto ignore_this_device;
 	}
 
-When dma_set_mask() is successful, and returns zero, the kernel saves
-away this mask you have provided.  The kernel will use this
-information later when you make DMA mappings.
+When dma_set_mask() or dma_set_mask_and_coherent() is successful, and
+returns zero, the kernel saves away this mask you have provided.  The
+kernel will use this information later when you make DMA mappings.
 
 There is a case which we are aware of at this time, which is worth
 mentioning in this documentation.  If your device supports multiple
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index 78a6c56..e865279 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -142,6 +142,14 @@ internal API for use by the platform than an external API for use by
 driver writers.
 
 int
+dma_set_mask_and_coherent(struct device *dev, u64 mask)
+
+Checks to see if the mask is possible and updates the device
+streaming and coherent DMA mask parameters if it is.
+
+Returns: 0 if successful and a negative error if not.
+
+int
 dma_set_mask(struct device *dev, u64 mask)
 
 Checks to see if the mask is possible and updates the device
diff --git a/Documentation/DocBook/media/Makefile b/Documentation/DocBook/media/Makefile
index f9fd615..1d27f0a 100644
--- a/Documentation/DocBook/media/Makefile
+++ b/Documentation/DocBook/media/Makefile
@@ -195,7 +195,7 @@ DVB_DOCUMENTED = \
 #
 
 install_media_images = \
-	$(Q)cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api
+	$(Q)-cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api
 
 $(MEDIA_OBJ_DIR)/%: $(MEDIA_SRC_DIR)/%.b64
 	$(Q)base64 -d $< >$@
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index 26b1e31..1ec219a 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -119,6 +119,20 @@ Example:
 	platform_set_drvdata(), but left the variable "dev" unused,
 	delete it.
 
+If your patch fixes a bug in a specific commit, e.g. you found an issue using
+git-bisect, please use the 'Fixes:' tag with the first 12 characters of the
+SHA-1 ID, and the one line summary.
+Example:
+
+	Fixes: e21d2170f366 ("video: remove unnecessary platform_set_drvdata()")
+
+The following git-config settings can be used to add a pretty format for
+outputting the above style in the git log or git show commands
+
+	[core]
+		abbrev = 12
+	[pretty]
+		fixes = Fixes: %h (\"%s\")
 
 3) Separate your changes.
 
@@ -430,7 +444,7 @@ person it names.  This tag documents that potentially interested parties
 have been included in the discussion
 
 
-14) Using Reported-by:, Tested-by:, Reviewed-by: and Suggested-by:
+14) Using Reported-by:, Tested-by:, Reviewed-by:, Suggested-by: and Fixes:
 
 If this patch fixes a problem reported by somebody else, consider adding a
 Reported-by: tag to credit the reporter for their contribution.  Please
@@ -485,6 +499,12 @@ idea was not posted in a public forum. That said, if we diligently credit our
 idea reporters, they will, hopefully, be inspired to help us again in the
 future.
 
+A Fixes: tag indicates that the patch fixes an issue in a previous commit. It
+is used to make it easy to determine where a bug originated, which can help
+review a bug fix. This tag also assists the stable kernel team in determining
+which stable kernel versions should receive your fix. This is the preferred
+method for indicating a bug fixed by the patch. See #2 above for more details.
+
 
 15) The canonical patch format
 
diff --git a/Documentation/devicetree/bindings/spi/efm32-spi.txt b/Documentation/devicetree/bindings/spi/efm32-spi.txt
index a590ca5..f762e11 100644
--- a/Documentation/devicetree/bindings/spi/efm32-spi.txt
+++ b/Documentation/devicetree/bindings/spi/efm32-spi.txt
@@ -3,7 +3,7 @@
 Required properties:
 - #address-cells: see spi-bus.txt
 - #size-cells: see spi-bus.txt
-- compatible: should be "efm32,spi"
+- compatible: should be "energymicro,efm32-spi"
 - reg: Offset and length of the register set for the controller
 - interrupts: pair specifying rx and tx irq
 - clocks: phandle to the spi clock
@@ -15,7 +15,7 @@ Example:
 spi1: spi@0x4000c400 { /* USART1 */
 	#address-cells = <1>;
 	#size-cells = <0>;
-	compatible = "efm32,spi";
+	compatible = "energymicro,efm32-spi";
 	reg = <0x4000c400 0x400>;
 	interrupts = <15 16>;
 	clocks = <&cmu 20>;
diff --git a/Documentation/input/elantech.txt b/Documentation/input/elantech.txt
index 5602eb7..e1ae127 100644
--- a/Documentation/input/elantech.txt
+++ b/Documentation/input/elantech.txt
@@ -504,9 +504,12 @@ byte 5:
 * reg_10
 
    bit   7   6   5   4   3   2   1   0
-         0   0   0   0   0   0   0   A
+         0   0   0   0   R   F   T   A
 
          A: 1 = enable absolute tracking
+         T: 1 = enable two finger mode auto correct
+         F: 1 = disable ABS Position Filter
+         R: 1 = enable real hardware resolution
 
 6.2 Native absolute mode 6 byte packet format
     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/Documentation/ja_JP/HOWTO b/Documentation/ja_JP/HOWTO
index 8148a47..52cf275 100644
--- a/Documentation/ja_JP/HOWTO
+++ b/Documentation/ja_JP/HOWTO
@@ -315,7 +315,7 @@ Andrew Morton が Linux-kernel メーリングリストにカーネルリリー�
 もし、3.x.y カーネルが存在しない場合には、番号が一番大きい 3.x が
 最新の安定版カーネルです。
 
-3.x.y は "stable" チーム <stable@kernel.org> でメンテされており、必
+3.x.y は "stable" チーム <stable@vger.kernel.org> でメンテされており、必
 要に応じてリリースされます。通常のリリース期間は 2週間毎ですが、差し迫っ
 た問題がなければもう少し長くなることもあります。セキュリティ関連の問題
 の場合はこれに対してだいたいの場合、すぐにリリースがされます。
diff --git a/Documentation/ja_JP/stable_kernel_rules.txt b/Documentation/ja_JP/stable_kernel_rules.txt
index 1426583..9dbda9b 100644
--- a/Documentation/ja_JP/stable_kernel_rules.txt
+++ b/Documentation/ja_JP/stable_kernel_rules.txt
@@ -50,16 +50,16 @@ linux-2.6.29/Documentation/stable_kernel_rules.txt
 
 -stable ツリーにパッチを送付する手続き-
 
- - 上記の規則に従っているかを確認した後に、stable@kernel.org にパッチ
+ - 上記の規則に従っているかを確認した後に、stable@vger.kernel.org にパッチ
    を送る。
  - 送信者はパッチがキューに受け付けられた際には ACK を、却下された場合
    には NAK を受け取る。この反応は開発者たちのスケジュールによって、数
    日かかる場合がある。
  - もし受け取られたら、パッチは他の開発者たちと関連するサブシステムの
    メンテナーによるレビューのために -stable キューに追加される。
- - パッチに stable@kernel.org のアドレスが付加されているときには、それ
+ - パッチに stable@vger.kernel.org のアドレスが付加されているときには、それ
    が Linus のツリーに入る時に自動的に stable チームに email される。
- - セキュリティパッチはこのエイリアス (stable@kernel.org) に送られるべ
+ - セキュリティパッチはこのエイリアス (stable@vger.kernel.org) に送られるべ
    きではなく、代わりに security@kernel.org のアドレスに送られる。
 
 レビューサイクル-
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index f5a6087..ebd2c25 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -343,6 +343,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			no: ACPI OperationRegions are not marked as reserved,
 			no further checks are performed.
 
+	acpi_no_memhotplug [ACPI] Disable memory hotplug.  Useful for kdump
+			   kernels.
+
 	add_efi_memmap	[EFI; X86] Include EFI memory map in
 			kernel's map of available physical RAM.
 
@@ -1119,6 +1122,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	i8042.notimeout	[HW] Ignore timeout condition signalled by controller
 	i8042.reset	[HW] Reset the controller during init and cleanup
 	i8042.unlock	[HW] Unlock (ignore) the keylock
+	i8042.kbdreset  [HW] Reset device connected to KBD port
 
 	i810=		[HW,DRM]
 
diff --git a/Documentation/lzo.txt b/Documentation/lzo.txt
new file mode 100644
index 0000000..ea45dd3
--- /dev/null
+++ b/Documentation/lzo.txt
@@ -0,0 +1,164 @@
+
+LZO stream format as understood by Linux's LZO decompressor
+===========================================================
+
+Introduction
+
+  This is not a specification. No specification seems to be publicly available
+  for the LZO stream format. This document describes what input format the LZO
+  decompressor as implemented in the Linux kernel understands. The file subject
+  of this analysis is lib/lzo/lzo1x_decompress_safe.c. No analysis was made on
+  the compressor nor on any other implementations though it seems likely that
+  the format matches the standard one. The purpose of this document is to
+  better understand what the code does in order to propose more efficient fixes
+  for future bug reports.
+
+Description
+
+  The stream is composed of a series of instructions, operands, and data. The
+  instructions consist in a few bits representing an opcode, and bits forming
+  the operands for the instruction, whose size and position depend on the
+  opcode and on the number of literals copied by previous instruction. The
+  operands are used to indicate :
+
+    - a distance when copying data from the dictionary (past output buffer)
+    - a length (number of bytes to copy from dictionary)
+    - the number of literals to copy, which is retained in variable "state"
+      as a piece of information for next instructions.
+
+  Optionally depending on the opcode and operands, extra data may follow. These
+  extra data can be a complement for the operand (eg: a length or a distance
+  encoded on larger values), or a literal to be copied to the output buffer.
+
+  The first byte of the block follows a different encoding from other bytes, it
+  seems to be optimized for literal use only, since there is no dictionary yet
+  prior to that byte.
+
+  Lengths are always encoded on a variable size starting with a small number
+  of bits in the operand. If the number of bits isn't enough to represent the
+  length, up to 255 may be added in increments by consuming more bytes with a
+  rate of at most 255 per extra byte (thus the compression ratio cannot exceed
+  around 255:1). The variable length encoding using #bits is always the same :
+
+       length = byte & ((1 << #bits) - 1)
+       if (!length) {
+               length = ((1 << #bits) - 1)
+               length += 255*(number of zero bytes)
+               length += first-non-zero-byte
+       }
+       length += constant (generally 2 or 3)
+
+  For references to the dictionary, distances are relative to the output
+  pointer. Distances are encoded using very few bits belonging to certain
+  ranges, resulting in multiple copy instructions using different encodings.
+  Certain encodings involve one extra byte, others involve two extra bytes
+  forming a little-endian 16-bit quantity (marked LE16 below).
+
+  After any instruction except the large literal copy, 0, 1, 2 or 3 literals
+  are copied before starting the next instruction. The number of literals that
+  were copied may change the meaning and behaviour of the next instruction. In
+  practice, only one instruction needs to know whether 0, less than 4, or more
+  literals were copied. This is the information stored in the <state> variable
+  in this implementation. This number of immediate literals to be copied is
+  generally encoded in the last two bits of the instruction but may also be
+  taken from the last two bits of an extra operand (eg: distance).
+
+  End of stream is declared when a block copy of distance 0 is seen. Only one
+  instruction may encode this distance (0001HLLL), it takes one LE16 operand
+  for the distance, thus requiring 3 bytes.
+
+  IMPORTANT NOTE : in the code some length checks are missing because certain
+  instructions are called under the assumption that a certain number of bytes
+  follow because it has already been garanteed before parsing the instructions.
+  They just have to "refill" this credit if they consume extra bytes. This is
+  an implementation design choice independant on the algorithm or encoding.
+
+Byte sequences
+
+  First byte encoding :
+
+      0..17   : follow regular instruction encoding, see below. It is worth
+                noting that codes 16 and 17 will represent a block copy from
+                the dictionary which is empty, and that they will always be
+                invalid at this place.
+
+      18..21  : copy 0..3 literals
+                state = (byte - 17) = 0..3  [ copy <state> literals ]
+                skip byte
+
+      22..255 : copy literal string
+                length = (byte - 17) = 4..238
+                state = 4 [ don't copy extra literals ]
+                skip byte
+
+  Instruction encoding :
+
+      0 0 0 0 X X X X  (0..15)
+        Depends on the number of literals copied by the last instruction.
+        If last instruction did not copy any literal (state == 0), this
+        encoding will be a copy of 4 or more literal, and must be interpreted
+        like this :
+
+           0 0 0 0 L L L L  (0..15)  : copy long literal string
+           length = 3 + (L ?: 15 + (zero_bytes * 255) + non_zero_byte)
+           state = 4  (no extra literals are copied)
+
+        If last instruction used to copy between 1 to 3 literals (encoded in
+        the instruction's opcode or distance), the instruction is a copy of a
+        2-byte block from the dictionary within a 1kB distance. It is worth
+        noting that this instruction provides little savings since it uses 2
+        bytes to encode a copy of 2 other bytes but it encodes the number of
+        following literals for free. It must be interpreted like this :
+
+           0 0 0 0 D D S S  (0..15)  : copy 2 bytes from <= 1kB distance
+           length = 2
+           state = S (copy S literals after this block)
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 2) + D + 1
+
+        If last instruction used to copy 4 or more literals (as detected by
+        state == 4), the instruction becomes a copy of a 3-byte block from the
+        dictionary from a 2..3kB distance, and must be interpreted like this :
+
+           0 0 0 0 D D S S  (0..15)  : copy 3 bytes from 2..3 kB distance
+           length = 3
+           state = S (copy S literals after this block)
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 2) + D + 2049
+
+      0 0 0 1 H L L L  (16..31)
+           Copy of a block within 16..48kB distance (preferably less than 10B)
+           length = 2 + (L ?: 7 + (zero_bytes * 255) + non_zero_byte)
+        Always followed by exactly one LE16 :  D D D D D D D D : D D D D D D S S
+           distance = 16384 + (H << 14) + D
+           state = S (copy S literals after this block)
+           End of stream is reached if distance == 16384
+
+      0 0 1 L L L L L  (32..63)
+           Copy of small block within 16kB distance (preferably less than 34B)
+           length = 2 + (L ?: 31 + (zero_bytes * 255) + non_zero_byte)
+        Always followed by exactly one LE16 :  D D D D D D D D : D D D D D D S S
+           distance = D + 1
+           state = S (copy S literals after this block)
+
+      0 1 L D D D S S  (64..127)
+           Copy 3-4 bytes from block within 2kB distance
+           state = S (copy S literals after this block)
+           length = 3 + L
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 3) + D + 1
+
+      1 L L D D D S S  (128..255)
+           Copy 5-8 bytes from block within 2kB distance
+           state = S (copy S literals after this block)
+           length = 5 + L
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 3) + D + 1
+
+Authors
+
+  This document was written by Willy Tarreau <w@1wt.eu> on 2014/07/19 during an
+  analysis of the decompression code available in Linux 3.16-rc5. The code is
+  tricky, it is possible that this document contains mistakes or that a few
+  corner cases were overlooked. In any case, please report any doubt, fix, or
+  proposed updates to the author(s) so that the document can be updated.
diff --git a/Documentation/ramoops.txt b/Documentation/ramoops.txt
index 69b3cac..5d86756 100644
--- a/Documentation/ramoops.txt
+++ b/Documentation/ramoops.txt
@@ -14,11 +14,19 @@ survive after a restart.
 
 1. Ramoops concepts
 
-Ramoops uses a predefined memory area to store the dump. The start and size of
-the memory area are set using two variables:
+Ramoops uses a predefined memory area to store the dump. The start and size
+and type of the memory area are set using three variables:
   * "mem_address" for the start
   * "mem_size" for the size. The memory size will be rounded down to a
   power of two.
+  * "mem_type" to specifiy if the memory type (default is pgprot_writecombine).
+
+Typically the default value of mem_type=0 should be used as that sets the pstore
+mapping to pgprot_writecombine. Setting mem_type=1 attempts to use
+pgprot_noncached, which only works on some platforms. This is because pstore
+depends on atomic operations. At least on ARM, pgprot_noncached causes the
+memory to be mapped strongly ordered, and atomic operations on strongly ordered
+memory are implementation defined, and won't work on many ARMs such as omaps.
 
 The memory area is divided into "record_size" chunks (also rounded down to
 power of two) and each oops/panic writes a "record_size" chunk of
@@ -55,6 +63,7 @@ Setting the ramoops parameters can be done in 2 different manners:
 static struct ramoops_platform_data ramoops_data = {
         .mem_size               = <...>,
         .mem_address            = <...>,
+        .mem_type               = <...>,
         .record_size            = <...>,
         .dump_oops              = <...>,
         .ecc                    = <...>,
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index 95731a0..8f08b2a 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -2026,8 +2026,8 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
   -------------------
 
     Module for sound cards based on the Asus AV66/AV100/AV200 chips,
-    i.e., Xonar D1, DX, D2, D2X, DS, Essence ST (Deluxe), Essence STX,
-    HDAV1.3 (Deluxe), and HDAV1.3 Slim.
+    i.e., Xonar D1, DX, D2, D2X, DS, DSX, Essence ST (Deluxe),
+    Essence STX (II), HDAV1.3 (Deluxe), and HDAV1.3 Slim.
 
     This module supports autoprobe and multiple cards.
 
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 79a797e..138fe43 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -664,7 +664,8 @@ The batch value of each per cpu pagelist is also updated as a result.  It is
 set to pcp->high/4.  The upper limit of batch is (PAGE_SHIFT * 8)
 
 The initial value is zero.  Kernel does not use this value at boot time to set
-the high water marks for each per cpu page list.
+the high water marks for each per cpu page list.  If the user writes '0' to this
+sysctl, it will revert to this default behavior.
 
 ==============================================================
 
diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt
index 1e6b653..d2ba80b 100644
--- a/Documentation/video4linux/gspca.txt
+++ b/Documentation/video4linux/gspca.txt
@@ -55,6 +55,7 @@ zc3xx		0458:700f	Genius VideoCam Web V2
 sonixj		0458:7025	Genius Eye 311Q
 sn9c20x		0458:7029	Genius Look 320s
 sonixj		0458:702e	Genius Slim 310 NB
+sn9c20x		0458:7045	Genius Look 1320 V2
 sn9c20x		0458:704a	Genius Slim 1320
 sn9c20x		0458:704c	Genius i-Look 1321
 sn9c20x		045e:00f4	LifeCam VX-6000 (SN9C20x + OV9650)
diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index 2908941..53838d9 100644
--- a/Documentation/virtual/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
@@ -425,6 +425,20 @@ fault through the slow path.
 Since only 19 bits are used to store generation-number on mmio spte, all
 pages are zapped when there is an overflow.
 
+Unfortunately, a single memory access might access kvm_memslots(kvm) multiple
+times, the last one happening when the generation number is retrieved and
+stored into the MMIO spte.  Thus, the MMIO spte might be created based on
+out-of-date information, but with an up-to-date generation number.
+
+To avoid this, the generation number is incremented again after synchronize_srcu
+returns; thus, the low bit of kvm_memslots(kvm)->generation is only 1 during a
+memslot update, while some SRCU readers might be using the old copy.  We do not
+want to use an MMIO sptes created with an odd generation number, and we can do
+this without losing a bit in the MMIO spte.  The low bit of the generation
+is not stored in MMIO spte, and presumed zero when it is extracted out of the
+spte.  If KVM is unlucky and creates an MMIO spte while the low bit is 1,
+the next access to the spte will always be a cache miss.
+
 
 Further reading
 ===============
diff --git a/Documentation/vm/hwpoison.txt b/Documentation/vm/hwpoison.txt
index 5500684..6ae89a9 100644
--- a/Documentation/vm/hwpoison.txt
+++ b/Documentation/vm/hwpoison.txt
@@ -84,6 +84,11 @@ PR_MCE_KILL
 		PR_MCE_KILL_EARLY: Early kill
 		PR_MCE_KILL_LATE:  Late kill
 		PR_MCE_KILL_DEFAULT: Use system global default
+	Note that if you want to have a dedicated thread which handles
+	the SIGBUS(BUS_MCEERR_AO) on behalf of the process, you should
+	call prctl(PR_MCE_KILL_EARLY) on the designated thread. Otherwise,
+	the SIGBUS is sent to the main thread.
+
 PR_MCE_KILL_GET
 	return current mode
 
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 881582f..bd43704 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -12,6 +12,8 @@ ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space
 ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole
 ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
+ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
+... unused hole ...
 ffffffff80000000 - ffffffffa0000000 (=512 MB)  kernel text mapping, from phys 0
 ffffffffa0000000 - ffffffffff5fffff (=1525 MB) module mapping space
 ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
diff --git a/Documentation/zh_CN/HOWTO b/Documentation/zh_CN/HOWTO
index 7fba5aa..7599eb3 100644
--- a/Documentation/zh_CN/HOWTO
+++ b/Documentation/zh_CN/HOWTO
@@ -237,7 +237,7 @@ kernel.org网站的pub/linux/kernel/v2.6/目录下找到它。它的开发遵循
 如果没有2.6.x.y版本内核存在，那么最新的2.6.x版本内核就相当于是当前的稳定
 版内核。
 
-2.6.x.y版本由“稳定版”小组（邮件地址<stable@kernel.org>）维护，一般隔周发
+2.6.x.y版本由“稳定版”小组（邮件地址<stable@vger.kernel.org>）维护，一般隔周发
 布新版本。
 
 内核源码中的Documentation/stable_kernel_rules.txt文件具体描述了可被稳定
diff --git a/Documentation/zh_CN/stable_kernel_rules.txt b/Documentation/zh_CN/stable_kernel_rules.txt
index b5b9b0a..26ea5ed 100644
--- a/Documentation/zh_CN/stable_kernel_rules.txt
+++ b/Documentation/zh_CN/stable_kernel_rules.txt
@@ -42,7 +42,7 @@ Documentation/stable_kernel_rules.txt 的中文翻译
 
 向稳定版代码树提交补丁的过程：
 
-  - 在确认了补丁符合以上的规则后，将补丁发送到stable@kernel.org。
+  - 在确认了补丁符合以上的规则后，将补丁发送到stable@vger.kernel.org。
   - 如果补丁被接受到队列里，发送者会收到一个ACK回复，如果没有被接受，收
     到的是NAK回复。回复需要几天的时间，这取决于开发者的时间安排。
   - 被接受的补丁会被加到稳定版本队列里，等待其他开发者的审查。