Merge branch 'akpm-current/current'

Conflicts:
	fs/fs-writeback.c

414 files changed, 9734 insertions, 5010 deletions

diff --git a/CREDITS b/CREDITS
index c8dc099ca3ec..ae3dbc04490f 100644
--- a/CREDITS
+++ b/CREDITS
@@ -1377,6 +1377,9 @@ S: 17 rue Danton
 S: F - 94270 Le Kremlin-Bicêtre
 S: France
 
+N: Jack Hammer
+D: IBM ServeRAID RAID (ips) driver maintenance
+
 N: Greg Hankins
 E: gregh@cc.gatech.edu
 D: fixed keyboard driver to separate LED and locking status
@@ -1687,6 +1690,10 @@ S: Reading
 S: RG6 2NU
 S: United Kingdom
 
+N: Dave Jeffery
+E: dhjeffery@gmail.com
+D: SCSI hacks and IBM ServeRAID RAID driver maintenance
+
 N: Jakub Jelinek
 E: jakub@redhat.com
 W: http://sunsite.mff.cuni.cz/~jj
@@ -2571,6 +2578,10 @@ N: Wolfgang Muees
 E: wolfgang@iksw-muees.de
 D: Auerswald USB driver
 
+N: Paul Mundt
+E: paul.mundt@gmail.com
+D: SuperH maintainer
+
 N: Ian A. Murdock
 E: imurdock@gnu.ai.mit.edu
 D: Creator of Debian distribution
diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram
index 3f0b9ae61d8c..70ec992514d0 100644
--- a/Documentation/ABI/testing/sysfs-block-zram
+++ b/Documentation/ABI/testing/sysfs-block-zram
@@ -43,6 +43,36 @@ Description:
 		The invalid_io file is read-only and specifies the number of
 		non-page-size-aligned I/O requests issued to this device.
 
+What:		/sys/block/zram<id>/failed_reads
+Date:		February 2014
+Contact:	Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+		The failed_reads file is read-only and specifies the number of
+		failed reads happened on this device.
+
+What:		/sys/block/zram<id>/failed_writes
+Date:		February 2014
+Contact:	Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+		The failed_writes file is read-only and specifies the number of
+		failed writes happened on this device.
+
+What:		/sys/block/zram<id>/max_comp_streams
+Date:		February 2014
+Contact:	Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+		The max_comp_streams file is read-write and specifies the
+		number of backend's zcomp_strm compression streams (number of
+		concurrent compress operations).
+
+What:		/sys/block/zram<id>/comp_algorithm
+Date:		February 2014
+Contact:	Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+		The comp_algorithm file is read-write and lets to show
+		available and selected compression algorithms, change
+		compression algorithm selection.
+
 What:		/sys/block/zram<id>/notify_free
 Date:		August 2010
 Contact:	Nitin Gupta <ngupta@vflare.org>
@@ -53,15 +83,6 @@ Description:
 		is freed. This statistic is applicable only when this disk is
 		being used as a swap disk.
 
-What:		/sys/block/zram<id>/discard
-Date:		August 2010
-Contact:	Nitin Gupta <ngupta@vflare.org>
-Description:
-		The discard file is read-only and specifies the number of
-		discard requests received by this device. These requests
-		provide information to block device regarding blocks which are
-		no longer used by filesystem.
-
 What:		/sys/block/zram<id>/zero_pages
 Date:		August 2010
 Contact:	Nitin Gupta <ngupta@vflare.org>
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index 26b1e31d5a13..fdad7d197062 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -14,7 +14,10 @@ Read Documentation/SubmitChecklist for a list of items to check
 before submitting code.  If you are submitting a driver, also read
 Documentation/SubmittingDrivers.
 
-
+Many of these steps describe the default behavior of the git version
+control system; if you use git to prepare your patches, you'll find much
+of the mechanical work done for you, though you'll still need to prepare
+and document a sensible set of patches.
 
 --------------------------------------------
 SECTION 1 - CREATING AND SENDING YOUR CHANGE
@@ -25,7 +28,9 @@ SECTION 1 - CREATING AND SENDING YOUR CHANGE
 1) "diff -up"
 ------------
 
-Use "diff -up" or "diff -uprN" to create patches.
+Use "diff -up" or "diff -uprN" to create patches.  git generates patches
+in this form by default; if you're using git, you can skip this section
+entirely.
 
 All changes to the Linux kernel occur in the form of patches, as
 generated by diff(1).  When creating your patch, make sure to create it
@@ -66,19 +71,14 @@ Make sure your patch does not include any extra files which do not
 belong in a patch submission.  Make sure to review your patch -after-
 generated it with diff(1), to ensure accuracy.
 
-If your changes produce a lot of deltas, you may want to look into
-splitting them into individual patches which modify things in
-logical stages.  This will facilitate easier reviewing by other
-kernel developers, very important if you want your patch accepted.
-There are a number of scripts which can aid in this:
-
-Quilt:
-http://savannah.nongnu.org/projects/quilt
+If your changes produce a lot of deltas, you need to split them into
+individual patches which modify things in logical stages; see section
+#3.  This will facilitate easier reviewing by other kernel developers,
+very important if you want your patch accepted.
 
-Andrew Morton's patch scripts:
-http://userweb.kernel.org/~akpm/stuff/patch-scripts.tar.gz
-Instead of these scripts, quilt is the recommended patch management
-tool (see above).
+If you're using git, "git rebase -i" can help you with this process.  If
+you're not using git, quilt <http://savannah.nongnu.org/projects/quilt>
+is another popular alternative.
 
 
 
@@ -106,8 +106,21 @@ I.e., the patch (series) and its description should be self-contained.
 This benefits both the patch merger(s) and reviewers.  Some reviewers
 probably didn't even receive earlier versions of the patch.
 
+Describe your changes in imperative mood, e.g. "make xyzzy do frotz"
+instead of "[This patch] makes xyzzy do frotz" or "[I] changed xyzzy
+to do frotz", as if you are giving orders to the codebase to change
+its behaviour.
+
 If the patch fixes a logged bug entry, refer to that bug entry by
-number and URL.
+number and URL.  If the patch follows from a mailing list discussion,
+give a URL to the mailing list archive; use the https://lkml.kernel.org/
+redirector with a Message-Id, to ensure that the links cannot become
+stale.
+
+However, try to make your explanation understandable without external
+resources.  In addition to giving a URL to a mailing list archive or
+bug, summarize the relevant points of the discussion that led to the
+patch as submitted.
 
 If you want to refer to a specific commit, don't just refer to the
 SHA-1 ID of the commit. Please also include the oneline summary of
@@ -594,7 +607,8 @@ 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).
+space (easily fit in 80 columns, maybe with some indentation).  (git
+generates appropriate diffstats by default.)
 
 See more details on the proper patch format in the following
 references.
diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.txt
index 2eccddffa6c8..0595c3f56ccf 100644
--- a/Documentation/blockdev/zram.txt
+++ b/Documentation/blockdev/zram.txt
@@ -21,7 +21,43 @@ Following shows a typical sequence of steps for using zram.
 	This creates 4 devices: /dev/zram{0,1,2,3}
 	(num_devices parameter is optional. Default: 1)
 
-2) Set Disksize
+2) Set max number of compression streams
+	Compression backend may use up to max_comp_streams compression streams,
+	thus allowing up to max_comp_streams concurrent compression operations.
+	By default, compression backend uses single compression stream.
+
+	Examples:
+	#show max compression streams number
+	cat /sys/block/zram0/max_comp_streams
+
+	#set max compression streams number to 3
+	echo 3 > /sys/block/zram0/max_comp_streams
+
+Note:
+In order to enable compression backend's multi stream support max_comp_streams
+must be initially set to desired concurrency level before ZRAM device
+initialisation. Once the device initialised as a single stream compression
+backend (max_comp_streams equals to 1), you will see error if you try to change
+the value of max_comp_streams because single stream compression backend
+implemented as a special case by lock overhead issue and does not support
+dynamic max_comp_streams. Only multi stream backend supports dynamic
+max_comp_streams adjustment.
+
+3) Select compression algorithm
+	Using comp_algorithm device attribute one can see available and
+	currently selected (shown in square brackets) compression algortithms,
+	change selected compression algorithm (once the device is initialised
+	there is no way to change compression algorithm).
+
+	Examples:
+	#show supported compression algorithms
+	cat /sys/block/zram0/comp_algorithm
+	lzo [lz4]
+
+	#select lzo compression algorithm
+	echo lzo > /sys/block/zram0/comp_algorithm
+
+4) Set Disksize
         Set disk size by writing the value to sysfs node 'disksize'.
         The value can be either in bytes or you can use mem suffixes.
         Examples:
@@ -33,32 +69,38 @@ Following shows a typical sequence of steps for using zram.
             echo 512M > /sys/block/zram0/disksize
             echo 1G > /sys/block/zram0/disksize
 
-3) Activate:
+Note:
+There is little point creating a zram of greater than twice the size of memory
+since we expect a 2:1 compression ratio. Note that zram uses about 0.1% of the
+size of the disk when not in use so a huge zram is wasteful.
+
+5) Activate:
 	mkswap /dev/zram0
 	swapon /dev/zram0
 
 	mkfs.ext4 /dev/zram1
 	mount /dev/zram1 /tmp
 
-4) Stats:
+6) Stats:
 	Per-device statistics are exported as various nodes under
 	/sys/block/zram<id>/
 		disksize
 		num_reads
 		num_writes
+		failed_reads
+		failed_writes
 		invalid_io
 		notify_free
-		discard
 		zero_pages
 		orig_data_size
 		compr_data_size
 		mem_used_total
 
-5) Deactivate:
+7) Deactivate:
 	swapoff /dev/zram0
 	umount /dev/zram1
 
-6) Reset:
+8) Reset:
 	Write any positive value to 'reset' sysfs node
 	echo 1 > /sys/block/zram0/reset
 	echo 1 > /sys/block/zram1/reset
diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt
index ce94a83a7d9a..80ac454704b8 100644
--- a/Documentation/cgroups/memcg_test.txt
+++ b/Documentation/cgroups/memcg_test.txt
@@ -24,7 +24,7 @@ Please note that implementation details can be changed.
 
    a page/swp_entry may be charged (usage += PAGE_SIZE) at
 
-	mem_cgroup_newpage_charge()
+	mem_cgroup_charge_anon()
 	  Called at new page fault and Copy-On-Write.
 
 	mem_cgroup_try_charge_swapin()
@@ -32,7 +32,7 @@ Please note that implementation details can be changed.
 	  Followed by charge-commit-cancel protocol. (With swap accounting)
 	  At commit, a charge recorded in swap_cgroup is removed.
 
-	mem_cgroup_cache_charge()
+	mem_cgroup_charge_file()
 	  Called at add_to_page_cache()
 
 	mem_cgroup_cache_charge_swapin()
diff --git a/Documentation/cgroups/resource_counter.txt b/Documentation/cgroups/resource_counter.txt
index 5108afb3645c..762ca54eb929 100644
--- a/Documentation/cgroups/resource_counter.txt
+++ b/Documentation/cgroups/resource_counter.txt
@@ -76,15 +76,7 @@ to work with it.
 	limit_fail_at parameter is set to the particular res_counter element
 	where the charging failed.
 
- d. int res_counter_charge_locked
-			(struct res_counter *rc, unsigned long val, bool force)
-
-	The same as res_counter_charge(), but it must not acquire/release the
-	res_counter->lock internally (it must be called with res_counter->lock
-	held). The force parameter indicates whether we can bypass the limit.
-
- e. u64 res_counter_uncharge[_locked]
-			(struct res_counter *rc, unsigned long val)
+ d. u64 res_counter_uncharge(struct res_counter *rc, unsigned long val)
 
 	When a resource is released (freed) it should be de-accounted
 	from the resource counter it was accounted to.  This is called
@@ -93,7 +85,7 @@ to work with it.
 
 	The _locked routines imply that the res_counter->lock is taken.
 
- f. u64 res_counter_uncharge_until
+ e. u64 res_counter_uncharge_until
 		(struct res_counter *rc, struct res_counter *top,
 		 unsigned long val)
 
diff --git a/Documentation/devicetree/bindings/rtc/sunxi-rtc.txt b/Documentation/devicetree/bindings/rtc/sunxi-rtc.txt
index 7cb9dbf34878..6983aad376c3 100644
--- a/Documentation/devicetree/bindings/rtc/sunxi-rtc.txt
+++ b/Documentation/devicetree/bindings/rtc/sunxi-rtc.txt
@@ -3,7 +3,7 @@
 RTC controller for the Allwinner A10/A20
 
 Required properties:
-- compatible : Should be "allwinner,sun4i-rtc" or "allwinner,sun7i-a20-rtc"
+- compatible : Should be "allwinner,sun4i-a10-rtc" or "allwinner,sun7i-a20-rtc"
 - reg: physical base address of the controller and length of memory mapped
   region.
 - interrupts: IRQ line for the RTC.
@@ -11,7 +11,7 @@ Required properties:
 Example:
 
 rtc: rtc@01c20d00 {
-	compatible = "allwinner,sun4i-rtc";
+	compatible = "allwinner,sun4i-a10-rtc";
 	reg = <0x01c20d00 0x20>;
 	interrupts = <24>;
 };
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 5b0c083d7c0e..767930f04a12 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -525,6 +525,7 @@ locking rules:
 open:		yes
 close:		yes
 fault:		yes		can return with page locked
+map_pages:	yes
 page_mkwrite:	yes		can return with page locked
 access:		yes
 
@@ -536,6 +537,15 @@ the page, then ensure it is not already truncated (the page lock will block
 subsequent truncate), and then return with VM_FAULT_LOCKED, and the page
 locked. The VM will unlock the page.
 
+	->map_pages() is called when VM asks to map easy accessible pages.
+Filesystem should find and map pages associated with offsets from "pgoff"
+till "max_pgoff". ->map_pages() is called with page table locked and must
+not block.  If it's not possible to reach a page without blocking,
+filesystem should skip it. Filesystem should use do_set_pte() to setup
+page table entry. Pointer to entry associated with offset "pgoff" is
+passed in "pte" field in vm_fault structure. Pointers to entries for other
+offsets should be calculated relative to "pte".
+
 	->page_mkwrite() is called when a previously read-only pte is
 about to become writeable. The filesystem again must ensure that there are
 no truncate/invalidate races, and then return with the page locked. If
diff --git a/Documentation/filesystems/affs.txt b/Documentation/filesystems/affs.txt
index 81ac488e3758..71b63c2b9841 100644
--- a/Documentation/filesystems/affs.txt
+++ b/Documentation/filesystems/affs.txt
@@ -49,6 +49,10 @@ mode=mode	Sets the mode flags to the given (octal) value, regardless
 		This is useful since most of the plain AmigaOS files
 		will map to 600.
 
+nofilenametruncate
+		The file system will return an error when filename exceeds
+		standard maximum filename length (30 characters).
+
 reserved=num	Sets the number of reserved blocks at the start of the
 		partition to num. You should never need this option.
 		Default is 2.
@@ -181,9 +185,8 @@ tested, though several hundred MB have been read and written using
 this fs. For a most up-to-date list of bugs please consult
 fs/affs/Changes.
 
-Filenames are truncated to 30 characters without warning (this
-can be changed by setting the compile-time option AFFS_NO_TRUNCATE
-in include/linux/amigaffs.h).
+By default, filenames are truncated to 30 characters without warning.
+'nofilenametruncate' mount option can change that behavior.
 
 Case is ignored by the affs in filename matching, but Linux shells
 do care about the case. Example (with /wb being an affs mounted fs):
diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.txt
index 06887d46ccf2..41c3d332acc9 100644
--- a/Documentation/filesystems/nilfs2.txt
+++ b/Documentation/filesystems/nilfs2.txt
@@ -25,9 +25,8 @@ available from the following download page.  At least "mkfs.nilfs2",
 cleaner or garbage collector) are required.  Details on the tools are
 described in the man pages included in the package.
 
-Project web page:    http://www.nilfs.org/en/
-Download page:       http://www.nilfs.org/en/download.html
-Git tree web page:   http://www.nilfs.org/git/
+Project web page:    http://nilfs.sourceforge.net/
+Download page:       http://nilfs.sourceforge.net/en/download.html
 List info:           http://vger.kernel.org/vger-lists.html#linux-nilfs
 
 Caveats
@@ -111,6 +110,13 @@ Table of NILFS2 specific ioctls
 			        nilfs_resize utilities and by nilfs_cleanerd
 			        daemon.
 
+ NILFS_IOCTL_SET_SUINFO         Modify segment usage info of requested
+				segments. This ioctl is used by
+				nilfs_cleanerd daemon to skip unnecessary
+				cleaning operation of segments and reduce
+				performance penalty or wear of flash device
+				due to redundant move of in-use blocks.
+
  NILFS_IOCTL_GET_SUSTAT         Return segment usage statistics. This ioctl
 			        is used in lssu, nilfs_resize utilities and
 			        by nilfs_cleanerd daemon.
diff --git a/Documentation/filesystems/ntfs.txt b/Documentation/filesystems/ntfs.txt
index 791af8dac065..61947facfc07 100644
--- a/Documentation/filesystems/ntfs.txt
+++ b/Documentation/filesystems/ntfs.txt
@@ -455,8 +455,6 @@ not have this problem with odd numbers of sectors.
 ChangeLog
 =========
 
-Note, a technical ChangeLog aimed at kernel hackers is in fs/ntfs/ChangeLog.
-
 2.1.30:
 	- Fix writev() (it kept writing the first segment over and over again
 	  instead of moving onto subsequent segments).
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index fe2b7ae6f962..0f3a1390bf00 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -295,9 +295,9 @@ in the beginning of ->setattr unconditionally.
 	->clear_inode() and ->delete_inode() are gone; ->evict_inode() should
 be used instead.  It gets called whenever the inode is evicted, whether it has
 remaining links or not.  Caller does *not* evict the pagecache or inode-associated
-metadata buffers; getting rid of those is responsibility of method, as it had
-been for ->delete_inode(). Caller makes sure async writeback cannot be running
-for the inode while (or after) ->evict_inode() is called.
+metadata buffers; the method has to use truncate_inode_pages_final() to get rid
+of those. Caller makes sure async writeback cannot be running for the inode while
+(or after) ->evict_inode() is called.
 
 	->drop_inode() returns int now; it's called on final iput() with
 inode->i_lock held and it returns true if filesystems wants the inode to be
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index f00bee144add..8b9cd8eb3f91 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -1648,18 +1648,21 @@ pids, so one need to either stop or freeze processes being inspected
 if precise results are needed.
 
 
-3.7	/proc/<pid>/fdinfo/<fd> - Information about opened file
+3.8	/proc/<pid>/fdinfo/<fd> - Information about opened file
 ---------------------------------------------------------------
 This file provides information associated with an opened file. The regular
-files have at least two fields -- 'pos' and 'flags'. The 'pos' represents
-the current offset of the opened file in decimal form [see lseek(2) for
-details] and 'flags' denotes the octal O_xxx mask the file has been
-created with [see open(2) for details].
+files have at least three fields -- 'pos', 'flags' and mnt_id. The 'pos'
+represents the current offset of the opened file in decimal form [see lseek(2)
+for details], 'flags' denotes the octal O_xxx mask the file has been
+created with [see open(2) for details] and 'mnt_id' represents mount ID of
+the file system containing the opened file [see 3.5 /proc/<pid>/mountinfo
+for details].
 
 A typical output is
 
 	pos:	0
 	flags:	0100002
+	mnt_id:	19
 
 The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags
 pair provide additional information particular to the objects they represent.
@@ -1668,6 +1671,7 @@ pair provide additional information particular to the objects they represent.
 	~~~~~~~~~~~~~
 	pos:	0
 	flags:	04002
+	mnt_id:	9
 	eventfd-count:	5a
 
 	where 'eventfd-count' is hex value of a counter.
@@ -1676,6 +1680,7 @@ pair provide additional information particular to the objects they represent.
 	~~~~~~~~~~~~~~
 	pos:	0
 	flags:	04002
+	mnt_id:	9
 	sigmask:	0000000000000200
 
 	where 'sigmask' is hex value of the signal mask associated
@@ -1685,6 +1690,7 @@ pair provide additional information particular to the objects they represent.
 	~~~~~~~~~~~
 	pos:	0
 	flags:	02
+	mnt_id:	9
 	tfd:        5 events:       1d data: ffffffffffffffff
 
 	where 'tfd' is a target file descriptor number in decimal form,
@@ -1718,6 +1724,7 @@ pair provide additional information particular to the objects they represent.
 
 	pos:	0
 	flags:	02
+	mnt_id:	9
 	fanotify flags:10 event-flags:0
 	fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003
 	fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4
diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt
index 4a93e98b290a..5cf57b368dc6 100644
--- a/Documentation/filesystems/vfat.txt
+++ b/Documentation/filesystems/vfat.txt
@@ -175,6 +175,16 @@ nfs=stale_rw|nostale_ro
 
 <bool>: 0,1,yes,no,true,false
 
+LIMITATION
+---------------------------------------------------------------------
+* The fallocated region of file is discarded at umount/evict time
+  when using fallocate with FALLOC_FL_KEEP_SIZE.
+  So, User should assume that fallocated region can be discarded at
+  last close if there is memory pressure resulting in eviction of
+  the inode from the memory. As a result, for any dependency on
+  the fallocated region, user should make sure to recheck fallocate
+  after reopening the file.
+
 TODO
 ----------------------------------------------------------------------
 * Need to get rid of the raw scanning stuff.  Instead, always use
diff --git a/Documentation/kbuild/kconfig-language.txt b/Documentation/kbuild/kconfig-language.txt
index c420676c6fe3..350f733bf2c7 100644
--- a/Documentation/kbuild/kconfig-language.txt
+++ b/Documentation/kbuild/kconfig-language.txt
@@ -157,6 +157,10 @@ applicable everywhere (see syntax).
     to the build environment (if this is desired, it can be done via
     another symbol).
 
+  - "allnoconfig_y"
+    This declares the symbol as one that should have the value y when
+    using "allnoconfig". Used for symbols that hide other symbols.
+
 Menu dependencies
 -----------------
 
diff --git a/Documentation/kmemleak.txt b/Documentation/kmemleak.txt
index b6e39739a36d..00aa013631db 100644
--- a/Documentation/kmemleak.txt
+++ b/Documentation/kmemleak.txt
@@ -11,9 +11,7 @@ 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.
-
-Please check DEBUG_KMEMLEAK dependencies in lib/Kconfig.debug for supported
-architectures.
+Kmemleak is supported on x86, arm, powerpc, sparc, sh, microblaze, ppc, mips, s390, metag and tile.
 
 Usage
 -----
@@ -44,7 +42,8 @@ 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)
+  off		- disable kmemleak, or free all kmemleak objects if kmemleak
+		  has been disabled due to fatal errors. (irreversible).
   stack=on	- enable the task stacks scanning (default)
   stack=off	- disable the tasks stacks scanning
   scan=on	- start the automatic memory scanning thread (default)
@@ -68,7 +67,7 @@ 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.
+information like size and stack trace, are stored in a rbtree.
 The corresponding freeing function calls are tracked and the pointers
 removed from the kmemleak data structures.
 
@@ -84,7 +83,7 @@ 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
+     the values against the addresses stored in the rbtree. 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
@@ -120,6 +119,17 @@ Then as usual to get your report with:
 
   # cat /sys/kernel/debug/kmemleak
 
+Freeing kmemleak internal objects
+---------------------------------
+
+To allow access to previously found memory leaks even when an error fatal
+to kmemleak happens, internal kmemleak objects won't be freed in this case.
+Those objects may occupy a large part of physical memory.
+
+You can reclaim memory from those objects with:
+
+  # echo off > /sys/kernel/debug/kmemleak
+
 Kmemleak API
 ------------
 
diff --git a/Documentation/leds/leds-class.txt b/Documentation/leds/leds-class.txt
index 79699c200766..62261c04060a 100644
--- a/Documentation/leds/leds-class.txt
+++ b/Documentation/leds/leds-class.txt
@@ -2,9 +2,6 @@
 LED handling under Linux
 ========================
 
-If you're reading this and thinking about keyboard leds, these are
-handled by the input subsystem and the led class is *not* needed.
-
 In its simplest form, the LED class just allows control of LEDs from
 userspace. LEDs appear in /sys/class/leds/. The maximum brightness of the
 LED is defined in max_brightness file. The brightness file will set the brightness
diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt
index 6f4eb322ffaf..94459b42e0ab 100644
--- a/Documentation/printk-formats.txt
+++ b/Documentation/printk-formats.txt
@@ -184,6 +184,12 @@ dentry names:
 	equivalent of %s dentry->d_name.name we used to use, %pd<n> prints
 	n last components.  %pD does the same thing for struct file.
 
+task_struct comm name:
+
+        %pT
+
+        For printing task_struct->comm.
+
 struct va_format:
 
 	%pV
diff --git a/Documentation/rapidio/sysfs.txt b/Documentation/rapidio/sysfs.txt
index 271438c0617f..47ce9a5336e1 100644
--- a/Documentation/rapidio/sysfs.txt
+++ b/Documentation/rapidio/sysfs.txt
@@ -2,8 +2,8 @@
 
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-1. Device Subdirectories
-------------------------
+1. RapidIO Device Subdirectories
+--------------------------------
 
 For each RapidIO device, the RapidIO subsystem creates files in an individual
 subdirectory with the following name, /sys/bus/rapidio/devices/<device_name>.
@@ -25,8 +25,8 @@ seen by the enumerating host (destID = 1):
 NOTE: An enumerating or discovering endpoint does not create a sysfs entry for
 itself, this is why an endpoint with destID=1 is not shown in the list.
 
-2. Attributes Common for All Devices
-------------------------------------
+2. Attributes Common for All RapidIO Devices
+--------------------------------------------
 
 Each device subdirectory contains the following informational read-only files:
 
@@ -52,16 +52,16 @@ This attribute is similar in behavior to the "config" attribute of PCI devices
 and provides an access to the RapidIO device registers using standard file read
 and write operations.
 
-3. Endpoint Device Attributes
------------------------------
+3. RapidIO Endpoint Device Attributes
+-------------------------------------
 
 Currently Linux RapidIO subsystem does not create any endpoint specific sysfs
 attributes. It is possible that RapidIO master port drivers and endpoint device
 drivers will add their device-specific sysfs attributes but such attributes are
 outside the scope of this document.
 
-4. Switch Device Attributes
----------------------------
+4. RapidIO Switch Device Attributes
+-----------------------------------
 
 RapidIO switches have additional attributes in sysfs. RapidIO subsystem supports
 common and device-specific sysfs attributes for switches. Because switches are
@@ -106,3 +106,53 @@ attribute:
 	 for that controller always will be 0.
 	 To initiate RapidIO enumeration/discovery on all available mports
 	 a user must write '-1' (or RIO_MPORT_ANY) into this attribute file.
+
+
+6. RapidIO Bus Controllers/Ports
+--------------------------------
+
+On-chip RapidIO controllers and PCIe-to-RapidIO bridges (referenced as
+"Master Port" or "mport") are presented in sysfs as the special class of
+devices: "rapidio_port".
+
+The /sys/class/rapidio_port subdirectory contains individual subdirectories
+named as "rapidioN" where N = mport ID registered with RapidIO subsystem.
+
+NOTE: An mport ID is not a RapidIO destination ID assigned to a given local
+mport device.
+
+Each mport device subdirectory in addition to standard entries contains the
+following device-specific attributes:
+
+   port_destid - reports RapidIO destination ID assigned to the given RapidIO
+                 mport device. If value 0xFFFFFFFF is returned this means that
+                 no valid destination ID have been assigned to the mport (yet).
+                 Normally, before enumeration/discovery have been executed only
+                 fabric enumerating mports have a valid destination ID assigned
+                 to them using "hdid=..." rapidio module parameter.
+      sys_size - reports RapidIO common transport system size:
+                   0 = small (8-bit destination ID, max. 256 devices),
+                   1 = large (16-bit destination ID, max. 65536 devices).
+
+After enumeration or discovery was performed for a given mport device,
+the corresponding subdirectory will also contain subdirectories for each
+child RapidIO device connected to the mport. Naming conventions for RapidIO
+devices are described in Section 1 above.
+
+The example below shows mport device subdirectory with several child RapidIO
+devices attached to it.
+
+[rio@rapidio ~]$ ls /sys/class/rapidio_port/rapidio0/ -l
+total 0
+drwxr-xr-x 3 root root    0 Feb 11 15:10 00:e:0001
+drwxr-xr-x 3 root root    0 Feb 11 15:10 00:e:0004
+drwxr-xr-x 3 root root    0 Feb 11 15:10 00:e:0007
+drwxr-xr-x 3 root root    0 Feb 11 15:10 00:s:0002
+drwxr-xr-x 3 root root    0 Feb 11 15:10 00:s:0003
+drwxr-xr-x 3 root root    0 Feb 11 15:10 00:s:0005
+lrwxrwxrwx 1 root root    0 Feb 11 15:11 device -> ../../../0000:01:00.0
+-r--r--r-- 1 root root 4096 Feb 11 15:11 port_destid
+drwxr-xr-x 2 root root    0 Feb 11 15:11 power
+lrwxrwxrwx 1 root root    0 Feb 11 15:04 subsystem -> ../../../../../../class/rapidio_port
+-r--r--r-- 1 root root 4096 Feb 11 15:11 sys_size
+-rw-r--r-- 1 root root 4096 Feb 11 15:04 uevent
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index d614a9b6a280..dd9d0e33b443 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -175,18 +175,39 @@ Setting this to zero disables periodic writeback altogether.
 
 drop_caches
 
-Writing to this will cause the kernel to drop clean caches, dentries and
-inodes from memory, causing that memory to become free.
+Writing to this will cause the kernel to drop clean caches, as well as
+reclaimable slab objects like dentries and inodes.  Once dropped, their
+memory becomes free.
 
 To free pagecache:
 	echo 1 > /proc/sys/vm/drop_caches
-To free dentries and inodes:
+To free reclaimable slab objects (includes dentries and inodes):
 	echo 2 > /proc/sys/vm/drop_caches
-To free pagecache, dentries and inodes:
+To free slab objects and pagecache:
 	echo 3 > /proc/sys/vm/drop_caches
 
-As this is a non-destructive operation and dirty objects are not freeable, the
-user should run `sync' first.
+This is a non-destructive operation and will not free any dirty objects.
+To increase the number of objects freed by this operation, the user may run
+`sync' prior to writing to /proc/sys/vm/drop_caches.  This will minimize the
+number of dirty objects on the system and create more candidates to be
+dropped.
+
+This file is not a means to control the growth of the various kernel caches
+(inodes, dentries, pagecache, etc...)  These objects are automatically
+reclaimed by the kernel when memory is needed elsewhere on the system.
+
+Use of this file can cause performance problems.  Since it discards cached
+objects, it may cost a significant amount of I/O and CPU to recreate the
+dropped objects, especially if they were under heavy use.  Because of this,
+use outside of a testing or debugging environment is not recommended.
+
+You may see informational messages in your kernel log when this file is
+used:
+
+	cat (1234): drop_caches: 3
+
+These are informational only.  They do not mean that anything is wrong
+with your system.  To disable them, echo 4 (bit 3) into drop_caches.
 
 ==============================================================
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 2ebc966cf3dc..a0c1e7f71592 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1720,6 +1720,8 @@ F:	drivers/net/wireless/b43legacy/
 
 BACKLIGHT CLASS/SUBSYSTEM
 M:	Jingoo Han <jg1.han@samsung.com>
+M:	Bryan Wu <cooloney@gmail.com>
+M:	Lee Jones <lee.jones@linaro.org>
 S:	Maintained
 F:	drivers/video/backlight/
 F:	include/linux/backlight.h
@@ -2759,6 +2761,31 @@ F:	include/linux/device-mapper.h
 F:	include/linux/dm-*.h
 F:	include/uapi/linux/dm-*.h
 
+DIALOG SEMICONDUCTOR DRIVERS
+M:	Support Opensource <support.opensource@diasemi.com>
+W:	http://www.dialog-semiconductor.com/products
+S:	Supported
+F:	Documentation/hwmon/da90??
+F:	drivers/gpio/gpio-da90??.c
+F:	drivers/hwmon/da90??-hwmon.c
+F:	drivers/input/misc/da90??_onkey.c
+F:	drivers/input/touchscreen/da9052_tsi.c
+F:	drivers/leds/leds-da90??.c
+F:	drivers/mfd/da903x.c
+F:	drivers/mfd/da90??-*.c
+F:	drivers/power/da9052-battery.c
+F:	drivers/regulator/da903x.c
+F:	drivers/regulator/da9???-regulator.[ch]
+F:	drivers/rtc/rtc-da90??.c
+F:	drivers/video/backlight/da90??_bl.c
+F:	drivers/watchdog/da90??_wdt.c
+F:	include/linux/mfd/da903x.h
+F:	include/linux/mfd/da9052/
+F:	include/linux/mfd/da9055/
+F:	include/linux/mfd/da9063/
+F:	include/sound/da[79]*.h
+F:	sound/soc/codecs/da[79]*.[ch]
+
 DIGI NEO AND CLASSIC PCI PRODUCTS
 M:	Lidza Louina <lidza.louina@gmail.com>
 L:	driverdev-devel@linuxdriverproject.org
@@ -4347,10 +4374,7 @@ F:	drivers/scsi/ibmvscsi/
 X:	drivers/scsi/ibmvscsi/ibmvstgt.c
 
 IBM ServeRAID RAID DRIVER
-P:	Jack Hammer
-M:	Dave Jeffery <ipslinux@adaptec.com>
-W:	http://www.developer.ibm.com/welcome/netfinity/serveraid.html
-S:	Supported
+S:	Orphan
 F:	drivers/scsi/ips.*
 
 ICH LPC AND GPIO DRIVER
@@ -4647,7 +4671,7 @@ F:	arch/x86/kernel/tboot.c
 INTEL WIRELESS WIMAX CONNECTION 2400
 M:	Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
 M:	linux-wimax@intel.com
-L:	wimax@linuxwimax.org
+L:     wimax@linuxwimax.org (subscribers-only)
 S:	Supported
 W:	http://linuxwimax.org
 F:	Documentation/wimax/README.i2400m
@@ -5745,7 +5769,6 @@ F:	fs/imgdafs/
 
 MICROBLAZE ARCHITECTURE
 M:	Michal Simek <monstr@monstr.eu>
-L:	microblaze-uclinux@itee.uq.edu.au (moderated for non-subscribers)
 W:	http://www.monstr.eu/fdt/
 T:	git git://git.monstr.eu/linux-2.6-microblaze.git
 S:	Supported
@@ -6188,10 +6211,10 @@ F:	include/uapi/linux/nfs*
 F:	include/uapi/linux/sunrpc/
 
 NILFS2 FILESYSTEM
-M:	KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp>
+M:	Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
 L:	linux-nilfs@vger.kernel.org
-W:	http://www.nilfs.org/en/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ryusuke/nilfs2.git
+W:	http://nilfs.sourceforge.net/
+T:	git git://github.com/konis/nilfs2.git
 S:	Supported
 F:	Documentation/filesystems/nilfs2.txt
 F:	fs/nilfs2/
@@ -8516,12 +8539,10 @@ S:	Maintained
 F:	drivers/net/ethernet/dlink/sundance.c
 
 SUPERH
-M:	Paul Mundt <lethal@linux-sh.org>
 L:	linux-sh@vger.kernel.org
 W:	http://www.linux-sh.org
 Q:	http://patchwork.kernel.org/project/linux-sh/list/
-T:	git git://github.com/pmundt/linux-sh.git sh-latest
-S:	Supported
+S:	Orphan
 F:	Documentation/sh/
 F:	arch/sh/
 F:	drivers/sh/
@@ -8805,6 +8826,7 @@ M:	Max Filippov <jcmvbkbc@gmail.com>
 L:	linux-xtensa@linux-xtensa.org
 S:	Maintained
 F:	arch/xtensa/
+F:	drivers/irqchip/irq-xtensa-*
 
 THANKO'S RAREMONO AM/FM/SW RADIO RECEIVER USB DRIVER
 M:	Hans Verkuil <hverkuil@xs4all.nl>
@@ -9696,7 +9718,7 @@ F:	drivers/media/rc/winbond-cir.c
 WIMAX STACK
 M:	Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
 M:	linux-wimax@intel.com
-L:	wimax@linuxwimax.org
+L:     wimax@linuxwimax.org (subscribers-only)
 S:	Supported
 W:	http://linuxwimax.org
 F:	Documentation/wimax/README.wimax
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index effc9c666e81..9174724571e2 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -544,7 +544,7 @@
 		};
 
 		rtc: rtc@01c20d00 {
-			compatible = "allwinner,sun4i-rtc";
+			compatible = "allwinner,sun4i-a10-rtc";
 			reg = <0x01c20d00 0x20>;
 			interrupts = <24>;
 		};
diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h
index bbae919bceb4..68ea615c2a28 100644
--- a/arch/arm/include/asm/fixmap.h
+++ b/arch/arm/include/asm/fixmap.h
@@ -14,28 +14,15 @@
  */
 
 #define FIXADDR_START		0xfff00000UL
-#define FIXADDR_TOP		0xfffe0000UL
-#define FIXADDR_SIZE		(FIXADDR_TOP - FIXADDR_START)
+#define FIXADDR_END		0xfffe0000UL
+#define FIXADDR_TOP		(FIXADDR_END - PAGE_SIZE)
 
-#define FIX_KMAP_BEGIN		0
-#define FIX_KMAP_END		(FIXADDR_SIZE >> PAGE_SHIFT)
+enum fixed_addresses {
+	FIX_KMAP_BEGIN,
+	FIX_KMAP_END = (FIXADDR_TOP - FIXADDR_START) >> PAGE_SHIFT,
+	__end_of_fixed_addresses
+};
 
-#define __fix_to_virt(x)	(FIXADDR_START + ((x) << PAGE_SHIFT))
-#define __virt_to_fix(x)	(((x) - FIXADDR_START) >> PAGE_SHIFT)
-
-extern void __this_fixmap_does_not_exist(void);
-
-static inline unsigned long fix_to_virt(const unsigned int idx)
-{
-	if (idx >= FIX_KMAP_END)
-		__this_fixmap_does_not_exist();
-	return __fix_to_virt(idx);
-}
-
-static inline unsigned int virt_to_fix(const unsigned long vaddr)
-{
-	BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
-	return __virt_to_fix(vaddr);
-}
+#include <asm-generic/fixmap.h>
 
 #endif
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 2a77ba8796ae..91a468225853 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -578,7 +578,7 @@ void __init mem_init(void)
 			MLK(DTCM_OFFSET, (unsigned long) dtcm_end),
 			MLK(ITCM_OFFSET, (unsigned long) itcm_end),
 #endif
-			MLK(FIXADDR_START, FIXADDR_TOP),
+			MLK(FIXADDR_START, FIXADDR_END),
 			MLM(VMALLOC_START, VMALLOC_END),
 			MLM(PAGE_OFFSET, (unsigned long)high_memory),
 #ifdef CONFIG_HIGHMEM
diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig
index ed0fcdf7e990..7cb90a54b598 100644
--- a/arch/cris/Kconfig
+++ b/arch/cris/Kconfig
@@ -138,6 +138,7 @@ config ETRAX_ARCH_V10
        bool
        default y if ETRAX100LX || ETRAX100LX_V2
        default n if !(ETRAX100LX || ETRAX100LX_V2)
+       select TTY
 
 config ETRAX_ARCH_V32
        bool
diff --git a/arch/cris/kernel/setup.c b/arch/cris/kernel/setup.c
index 32c3d248868e..905b70ea9939 100644
--- a/arch/cris/kernel/setup.c
+++ b/arch/cris/kernel/setup.c
@@ -165,6 +165,7 @@ void __init setup_arch(char **cmdline_p)
 	strcpy(init_utsname()->machine, cris_machine_name);
 }
 
+#ifdef CONFIG_PROC_FS
 static void *c_start(struct seq_file *m, loff_t *pos)
 {
 	return *pos < nr_cpu_ids ? (void *)(int)(*pos + 1) : NULL;
@@ -188,6 +189,7 @@ const struct seq_operations cpuinfo_op = {
 	.stop  = c_stop,
 	.show  = show_cpuinfo,
 };
+#endif /* CONFIG_PROC_FS */
 
 static int __init topology_init(void)
 {
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 5409bf46cb83..12c3afee0f6f 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -21,6 +21,7 @@ config IA64
 	select HAVE_FUNCTION_TRACER
 	select HAVE_DMA_ATTRS
 	select HAVE_KVM
+	select TTY
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_DMA_API_DEBUG
 	select HAVE_MEMBLOCK
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 88dbf9659185..a6774560afe3 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -210,7 +210,6 @@ extern int is_fadump_active(void);
 extern void crash_fadump(struct pt_regs *, const char *);
 extern void fadump_cleanup(void);
 
-extern void vmcore_cleanup(void);
 #else	/* CONFIG_FA_DUMP */
 static inline int is_fadump_active(void) { return 0; }
 static inline void crash_fadump(struct pt_regs *regs, const char *str) { }
diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c
index 6c0b1f5f8d2c..fa9fb5b4c66c 100644
--- a/arch/powerpc/mm/subpage-prot.c
+++ b/arch/powerpc/mm/subpage-prot.c
@@ -134,7 +134,7 @@ static void subpage_prot_clear(unsigned long addr, unsigned long len)
 static int subpage_walk_pmd_entry(pmd_t *pmd, unsigned long addr,
 				  unsigned long end, struct mm_walk *walk)
 {
-	struct vm_area_struct *vma = walk->private;
+	struct vm_area_struct *vma = walk->vma;
 	split_huge_page_pmd(vma, addr, pmd);
 	return 0;
 }
@@ -163,9 +163,7 @@ static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr,
 		if (vma->vm_start >= (addr + len))
 			break;
 		vma->vm_flags |= VM_NOHUGEPAGE;
-		subpage_proto_walk.private = vma;
-		walk_page_range(vma->vm_start, vma->vm_end,
-				&subpage_proto_walk);
+		walk_page_vma(vma, &subpage_proto_walk);
 		vma = vma->vm_next;
 	}
 }
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 434fda39bf8b..d9e2b19b7c8d 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -73,6 +73,7 @@ config PPC_BOOK3S_64
 	select SYS_SUPPORTS_HUGETLBFS
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if PPC_64K_PAGES
 	select ARCH_SUPPORTS_NUMA_BALANCING
+	select IRQ_WORK
 
 config PPC_BOOK3E_64
 	bool "Embedded processors"
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index 95dd892e9904..cf2b0840a672 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -531,6 +531,7 @@ int fsl_rio_setup(struct platform_device *dev)
 		sprintf(port->name, "RIO mport %d", i);
 
 		priv->dev = &dev->dev;
+		port->dev.parent = &dev->dev;
 		port->ops = ops;
 		port->priv = priv;
 		port->phys_efptr = 0x100;
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 796c9320c709..5d8324cd866b 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -505,6 +505,9 @@ static int gmap_connect_pgtable(unsigned long address, unsigned long segment,
 	if (!pmd_present(*pmd) &&
 	    __pte_alloc(mm, vma, pmd, vmaddr))
 		return -ENOMEM;
+	/* large pmds cannot yet be handled */
+	if (pmd_large(*pmd))
+		return -EFAULT;
 	/* pmd now points to a valid segment table entry. */
 	rmap = kmalloc(sizeof(*rmap), GFP_KERNEL|__GFP_REPEAT);
 	if (!rmap)
diff --git a/arch/score/Kconfig b/arch/score/Kconfig
index c75d06aa27c3..4ac8cae5727c 100644
--- a/arch/score/Kconfig
+++ b/arch/score/Kconfig
@@ -22,27 +22,21 @@ choice
 config ARCH_SCORE7
 	bool "SCORE7 processor"
 	select SYS_SUPPORTS_32BIT_KERNEL
-	select CPU_SCORE7
 	select GENERIC_HAS_IOMAP
 
 config MACH_SPCT6600
 	bool "SPCT6600 series based machines"
 	select SYS_SUPPORTS_32BIT_KERNEL
-	select CPU_SCORE7
 	select GENERIC_HAS_IOMAP
 
 config SCORE_SIM
 	bool "Score simulator"
 	select SYS_SUPPORTS_32BIT_KERNEL
-	select CPU_SCORE7
 	select GENERIC_HAS_IOMAP
 endchoice
 
 endmenu
 
-config CPU_SCORE7
-	bool
-
 config NO_DMA
 	bool
 	default y
diff --git a/arch/sh/boards/board-sh7757lcr.c b/arch/sh/boards/board-sh7757lcr.c
index 25c5a932f9fe..669df51a82e3 100644
--- a/arch/sh/boards/board-sh7757lcr.c
+++ b/arch/sh/boards/board-sh7757lcr.c
@@ -252,7 +252,7 @@ static struct sh_mobile_sdhi_info sdhi_info = {
 static struct resource sdhi_resources[] = {
 	[0] = {
 		.start  = 0xffe50000,
-		.end    = 0xffe501ff,
+		.end    = 0xffe500ff,
 		.flags  = IORESOURCE_MEM,
 	},
 	[1] = {
diff --git a/arch/sh/include/asm/syscalls_32.h b/arch/sh/include/asm/syscalls_32.h
index 4f97df87d7d5..4f643aa718e3 100644
--- a/arch/sh/include/asm/syscalls_32.h
+++ b/arch/sh/include/asm/syscalls_32.h
@@ -9,15 +9,9 @@
 
 struct pt_regs;
 
-asmlinkage int sys_sigreturn(unsigned long r4, unsigned long r5,
-			     unsigned long r6, unsigned long r7,
-			     struct pt_regs __regs);
-asmlinkage int sys_rt_sigreturn(unsigned long r4, unsigned long r5,
-				unsigned long r6, unsigned long r7,
-				struct pt_regs __regs);
-asmlinkage int sys_sh_pipe(unsigned long r4, unsigned long r5,
-			   unsigned long r6, unsigned long r7,
-			   struct pt_regs __regs);
+asmlinkage int sys_sigreturn(void);
+asmlinkage int sys_rt_sigreturn(void);
+asmlinkage int sys_sh_pipe(void);
 asmlinkage ssize_t sys_pread_wrapper(unsigned int fd, char __user *buf,
 				     size_t count, long dummy, loff_t pos);
 asmlinkage ssize_t sys_pwrite_wrapper(unsigned int fd, const char __user *buf,
diff --git a/arch/sh/include/asm/traps_32.h b/arch/sh/include/asm/traps_32.h
index cfd55ff9dff2..17e129fe459c 100644
--- a/arch/sh/include/asm/traps_32.h
+++ b/arch/sh/include/asm/traps_32.h
@@ -42,18 +42,10 @@ static inline void trigger_address_error(void)
 asmlinkage void do_address_error(struct pt_regs *regs,
 				 unsigned long writeaccess,
 				 unsigned long address);
-asmlinkage void do_divide_error(unsigned long r4, unsigned long r5,
-				unsigned long r6, unsigned long r7,
-				struct pt_regs __regs);
-asmlinkage void do_reserved_inst(unsigned long r4, unsigned long r5,
-				unsigned long r6, unsigned long r7,
-				struct pt_regs __regs);
-asmlinkage void do_illegal_slot_inst(unsigned long r4, unsigned long r5,
-				unsigned long r6, unsigned long r7,
-				struct pt_regs __regs);
-asmlinkage void do_exception_error(unsigned long r4, unsigned long r5,
-				   unsigned long r6, unsigned long r7,
-				   struct pt_regs __regs);
+asmlinkage void do_divide_error(unsigned long r4);
+asmlinkage void do_reserved_inst(void);
+asmlinkage void do_illegal_slot_inst(void);
+asmlinkage void do_exception_error(void);
 
 #define BUILD_TRAP_HANDLER(name)					\
 asmlinkage void name##_trap_handler(unsigned long r4, unsigned long r5,	\
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7757.c b/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
index e84a43229b9c..5c0e3c335161 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
@@ -132,7 +132,7 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_CON_ID("usb_fck", &mstp_clks[MSTP103]),
 	CLKDEV_DEV_ID("renesas_usbhs.0", &mstp_clks[MSTP102]),
 	CLKDEV_CON_ID("mmc0", &mstp_clks[MSTP220]),
-	CLKDEV_CON_ID("rspi2", &mstp_clks[MSTP127]),
+	CLKDEV_DEV_ID("rspi.2", &mstp_clks[MSTP127]),
 };
 
 int __init arch_clk_init(void)
diff --git a/arch/sh/kernel/dumpstack.c b/arch/sh/kernel/dumpstack.c
index b959f5592604..8dfe645bcc4b 100644
--- a/arch/sh/kernel/dumpstack.c
+++ b/arch/sh/kernel/dumpstack.c
@@ -115,7 +115,7 @@ static int print_trace_stack(void *data, char *name)
  */
 static void print_trace_address(void *data, unsigned long addr, int reliable)
 {
-	printk(data);
+	printk("%s", (char *)data);
 	printk_address(addr, reliable);
 }
 
diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S
index ca46834294b7..13047a4facd2 100644
--- a/arch/sh/kernel/entry-common.S
+++ b/arch/sh/kernel/entry-common.S
@@ -193,10 +193,10 @@ syscall_trace_entry:
 	!			Reload R0-R4 from kernel stack, where the
 	!   	    	    	parent may have modified them using
 	!   	    	    	ptrace(POKEUSR).  (Note that R0-R2 are
-	!   	    	    	used by the system call handler directly
-	!   	    	    	from the kernel stack anyway, so don't need
-	!   	    	    	to be reloaded here.)  This allows the parent
-	!   	    	    	to rewrite system calls and args on the fly.
+	!   	    	    	reloaded from the kernel stack by syscall_call
+	!   	    	    	below, so don't need to be reloaded here.)
+	!   	    	    	This allows the parent to rewrite system calls
+	!   	    	    	and args on the fly.
 	mov.l	@(OFF_R4,r15), r4   ! arg0
 	mov.l	@(OFF_R5,r15), r5
 	mov.l	@(OFF_R6,r15), r6
@@ -357,8 +357,15 @@ syscall_call:
 	mov.l	3f, r8		! Load the address of sys_call_table
 	add	r8, r3
 	mov.l	@r3, r8
+	mov.l	@(OFF_R2,r15), r2
+	mov.l	@(OFF_R1,r15), r1
+	mov.l	@(OFF_R0,r15), r0
+	mov.l	r2, @-r15
+	mov.l	r1, @-r15
+	mov.l	r0, @-r15
 	jsr	@r8	    	! jump to specific syscall handler
 	 nop
+	add	#12, r15
 	mov.l	@(OFF_R0,r15), r12		! save r0
 	mov.l	r0, @(OFF_R0,r15)		! save the return value
 	!
diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c
index 6af6e7c5cac8..594cd371aa28 100644
--- a/arch/sh/kernel/signal_32.c
+++ b/arch/sh/kernel/signal_32.c
@@ -148,11 +148,9 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *r0_p
 	return err;
 }
 
-asmlinkage int sys_sigreturn(unsigned long r4, unsigned long r5,
-			     unsigned long r6, unsigned long r7,
-			     struct pt_regs __regs)
+asmlinkage int sys_sigreturn(void)
 {
-	struct pt_regs *regs = RELOC_HIDE(&__regs, 0);
+	struct pt_regs *regs = current_pt_regs();
 	struct sigframe __user *frame = (struct sigframe __user *)regs->regs[15];
 	sigset_t set;
 	int r0;
@@ -180,11 +178,9 @@ badframe:
 	return 0;
 }
 
-asmlinkage int sys_rt_sigreturn(unsigned long r4, unsigned long r5,
-				unsigned long r6, unsigned long r7,
-				struct pt_regs __regs)
+asmlinkage int sys_rt_sigreturn(void)
 {
-	struct pt_regs *regs = RELOC_HIDE(&__regs, 0);
+	struct pt_regs *regs = current_pt_regs();
 	struct rt_sigframe __user *frame = (struct rt_sigframe __user *)regs->regs[15];
 	sigset_t set;
 	int r0;
diff --git a/arch/sh/kernel/sys_sh32.c b/arch/sh/kernel/sys_sh32.c
index 497bab3a0401..b66d1c62eb19 100644
--- a/arch/sh/kernel/sys_sh32.c
+++ b/arch/sh/kernel/sys_sh32.c
@@ -21,17 +21,14 @@
  * sys_pipe() is the normal C calling standard for creating
  * a pipe. It's not the way Unix traditionally does this, though.
  */
-asmlinkage int sys_sh_pipe(unsigned long r4, unsigned long r5,
-	unsigned long r6, unsigned long r7,
-	struct pt_regs __regs)
+asmlinkage int sys_sh_pipe(void)
 {
-	struct pt_regs *regs = RELOC_HIDE(&__regs, 0);
 	int fd[2];
 	int error;
 
 	error = do_pipe_flags(fd, 0);
 	if (!error) {
-		regs->regs[1] = fd[1];
+		current_pt_regs()->regs[1] = fd[1];
 		return fd[0];
 	}
 	return error;
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index 68e99f09171d..ff639342a8be 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -594,9 +594,7 @@ int is_dsp_inst(struct pt_regs *regs)
 #endif /* CONFIG_SH_DSP */
 
 #ifdef CONFIG_CPU_SH2A
-asmlinkage void do_divide_error(unsigned long r4, unsigned long r5,
-				unsigned long r6, unsigned long r7,
-				struct pt_regs __regs)
+asmlinkage void do_divide_error(unsigned long r4)
 {
 	siginfo_t info;
 
@@ -613,11 +611,9 @@ asmlinkage void do_divide_error(unsigned long r4, unsigned long r5,
 }
 #endif
 
-asmlinkage void do_reserved_inst(unsigned long r4, unsigned long r5,
-				unsigned long r6, unsigned long r7,
-				struct pt_regs __regs)
+asmlinkage void do_reserved_inst(void)
 {
-	struct pt_regs *regs = RELOC_HIDE(&__regs, 0);
+	struct pt_regs *regs = current_pt_regs();
 	unsigned long error_code;
 	struct task_struct *tsk = current;
 
@@ -701,11 +697,9 @@ static int emulate_branch(unsigned short inst, struct pt_regs *regs)
 }
 #endif
 
-asmlinkage void do_illegal_slot_inst(unsigned long r4, unsigned long r5,
-				unsigned long r6, unsigned long r7,
-				struct pt_regs __regs)
+asmlinkage void do_illegal_slot_inst(void)
 {
-	struct pt_regs *regs = RELOC_HIDE(&__regs, 0);
+	struct pt_regs *regs = current_pt_regs();
 	unsigned long inst;
 	struct task_struct *tsk = current;
 
@@ -730,15 +724,12 @@ asmlinkage void do_illegal_slot_inst(unsigned long r4, unsigned long r5,
 	die_if_no_fixup("illegal slot instruction", regs, inst);
 }
 
-asmlinkage void do_exception_error(unsigned long r4, unsigned long r5,
-				   unsigned long r6, unsigned long r7,
-				   struct pt_regs __regs)
+asmlinkage void do_exception_error(void)
 {
-	struct pt_regs *regs = RELOC_HIDE(&__regs, 0);
 	long ex;
 
 	ex = lookup_exception_vector();
-	die_if_kernel("exception", regs, ex);
+	die_if_kernel("exception", current_pt_regs(), ex);
 }
 
 void per_cpu_trap_init(void)
diff --git a/arch/sh/math-emu/math.c b/arch/sh/math-emu/math.c
index b876780c1e1c..04aa55fa8c75 100644
--- a/arch/sh/math-emu/math.c
+++ b/arch/sh/math-emu/math.c
@@ -574,24 +574,6 @@ static int ieee_fpe_handler(struct pt_regs *regs)
 	return 0;
 }
 
-asmlinkage void do_fpu_error(unsigned long r4, unsigned long r5,
-			     unsigned long r6, unsigned long r7,
-			     struct pt_regs regs)
-{
-	struct task_struct *tsk = current;
-	siginfo_t info;
-
-	if (ieee_fpe_handler (&regs))
-		return;
-
-	regs.pc += 2;
-	info.si_signo = SIGFPE;
-	info.si_errno = 0;
-	info.si_code = FPE_FLTINV;
-	info.si_addr = (void __user *)regs.pc;
-	force_sig_info(SIGFPE, &info, tsk);
-}
-
 /**
  * fpu_init - Initialize FPU registers
  * @fpu: Pointer to software emulated FPU registers.
diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h
index fb5e4c658f7a..ef470a7a3d0f 100644
--- a/arch/unicore32/include/asm/mmu_context.h
+++ b/arch/unicore32/include/asm/mmu_context.h
@@ -14,6 +14,8 @@
 
 #include <linux/compiler.h>
 #include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/io.h>
 
 #include <asm/cacheflush.h>
@@ -73,7 +75,7 @@ do { \
 		else \
 			mm->mmap = NULL; \
 		rb_erase(&high_vma->vm_rb, &mm->mm_rb); \
-		mm->mmap_cache = NULL; \
+		vmacache_invalidate(mm); \
 		mm->map_count--; \
 		remove_vma(high_vma); \
 	} \
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index 2f03ff018d36..ba38ebbaced3 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -1,7 +1,6 @@
 #ifndef _ASM_X86_BUG_H
 #define _ASM_X86_BUG_H
 
-#ifdef CONFIG_BUG
 #define HAVE_ARCH_BUG
 
 #ifdef CONFIG_DEBUG_BUGVERBOSE
@@ -33,8 +32,6 @@ do {								\
 } while (0)
 #endif
 
-#endif /* !CONFIG_BUG */
-
 #include <asm-generic/bug.h>
 
 #endif /* _ASM_X86_BUG_H */
diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c
index d87dd6d042d6..dd89a13f1051 100644
--- a/arch/x86/mm/kmemcheck/kmemcheck.c
+++ b/arch/x86/mm/kmemcheck/kmemcheck.c
@@ -78,10 +78,16 @@ early_initcall(kmemcheck_init);
  */
 static int __init param_kmemcheck(char *str)
 {
+	int val;
+	int ret;
+
 	if (!str)
 		return -EINVAL;
 
-	sscanf(str, "%d", &kmemcheck_enabled);
+	ret = kstrtoint(str, 0, &val);
+	if (ret)
+		return ret;
+	kmemcheck_enabled = val;
 	return 0;
 }
 
diff --git a/block/genhd.c b/block/genhd.c
index 791f41943132..7bd4372e8b6f 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -849,7 +849,7 @@ static int show_partition(struct seq_file *seqf, void *v)
 	char buf[BDEVNAME_SIZE];
 
 	/* Don't show non-partitionable removeable devices or empty devices */
-	if (!get_capacity(sgp) || (!disk_max_parts(sgp) &&
+	if (!get_capacity(sgp) || (!(disk_max_parts(sgp) > 1) &&
 				   (sgp->flags & GENHD_FL_REMOVABLE)))
 		return 0;
 	if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)
diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig
index 3450be850399..6489c0fd0ea6 100644
--- a/drivers/block/zram/Kconfig
+++ b/drivers/block/zram/Kconfig
@@ -15,6 +15,16 @@ config ZRAM
 
 	  See zram.txt for more information.
 
+config ZRAM_LZ4_COMPRESS
+	bool "Enable LZ4 algorithm support"
+	depends on ZRAM
+	select LZ4_COMPRESS
+	select LZ4_DECOMPRESS
+	default n
+	help
+	  This option enables LZ4 compression algorithm support. Compression
+	  algorithm can be changed using `comp_algorithm' device attribute.
+
 config ZRAM_DEBUG
 	bool "Compressed RAM block device debug support"
 	depends on ZRAM
diff --git a/drivers/block/zram/Makefile b/drivers/block/zram/Makefile
index cb0f9ced6a93..be0763ff57a2 100644
--- a/drivers/block/zram/Makefile
+++ b/drivers/block/zram/Makefile
@@ -1,3 +1,5 @@
-zram-y	:=	zram_drv.o
+zram-y	:=	zcomp_lzo.o zcomp.o zram_drv.o
+
+zram-$(CONFIG_ZRAM_LZ4_COMPRESS) += zcomp_lz4.o
 
 obj-$(CONFIG_ZRAM)	+=	zram.o
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
new file mode 100644
index 000000000000..f1ff39a3d1c1
--- /dev/null
+++ b/drivers/block/zram/zcomp.c
@@ -0,0 +1,353 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+#include <linux/sched.h>
+
+#include "zcomp.h"
+#include "zcomp_lzo.h"
+#ifdef CONFIG_ZRAM_LZ4_COMPRESS
+#include "zcomp_lz4.h"
+#endif
+
+/*
+ * single zcomp_strm backend
+ */
+struct zcomp_strm_single {
+	struct mutex strm_lock;
+	struct zcomp_strm *zstrm;
+};
+
+/*
+ * multi zcomp_strm backend
+ */
+struct zcomp_strm_multi {
+	/* protect strm list */
+	spinlock_t strm_lock;
+	/* max possible number of zstrm streams */
+	int max_strm;
+	/* number of available zstrm streams */
+	int avail_strm;
+	/* list of available strms */
+	struct list_head idle_strm;
+	wait_queue_head_t strm_wait;
+};
+
+static struct zcomp_backend *backends[] = {
+	&zcomp_lzo,
+#ifdef CONFIG_ZRAM_LZ4_COMPRESS
+	&zcomp_lz4,
+#endif
+	NULL
+};
+
+static struct zcomp_backend *find_backend(const char *compress)
+{
+	int i = 0;
+	while (backends[i]) {
+		if (sysfs_streq(compress, backends[i]->name))
+			break;
+		i++;
+	}
+	return backends[i];
+}
+
+static void zcomp_strm_free(struct zcomp *comp, struct zcomp_strm *zstrm)
+{
+	if (zstrm->private)
+		comp->backend->destroy(zstrm->private);
+	free_pages((unsigned long)zstrm->buffer, 1);
+	kfree(zstrm);
+}
+
+/*
+ * allocate new zcomp_strm structure with ->private initialized by
+ * backend, return NULL on error
+ */
+static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp)
+{
+	struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), GFP_KERNEL);
+	if (!zstrm)
+		return NULL;
+
+	zstrm->private = comp->backend->create();
+	/*
+	 * allocate 2 pages. 1 for compressed data, plus 1 extra for the
+	 * case when compressed size is larger than the original one
+	 */
+	zstrm->buffer = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
+	if (!zstrm->private || !zstrm->buffer) {
+		zcomp_strm_free(comp, zstrm);
+		zstrm = NULL;
+	}
+	return zstrm;
+}
+
+/*
+ * get idle zcomp_strm or wait until other process release
+ * (zcomp_strm_release()) one for us
+ */
+static struct zcomp_strm *zcomp_strm_multi_find(struct zcomp *comp)
+{
+	struct zcomp_strm_multi *zs = comp->stream;
+	struct zcomp_strm *zstrm;
+
+	while (1) {
+		spin_lock(&zs->strm_lock);
+		if (!list_empty(&zs->idle_strm)) {
+			zstrm = list_entry(zs->idle_strm.next,
+					struct zcomp_strm, list);
+			list_del(&zstrm->list);
+			spin_unlock(&zs->strm_lock);
+			return zstrm;
+		}
+		/* zstrm streams limit reached, wait for idle stream */
+		if (zs->avail_strm >= zs->max_strm) {
+			spin_unlock(&zs->strm_lock);
+			wait_event(zs->strm_wait, !list_empty(&zs->idle_strm));
+			continue;
+		}
+		/* allocate new zstrm stream */
+		zs->avail_strm++;
+		spin_unlock(&zs->strm_lock);
+
+		zstrm = zcomp_strm_alloc(comp);
+		if (!zstrm) {
+			spin_lock(&zs->strm_lock);
+			zs->avail_strm--;
+			spin_unlock(&zs->strm_lock);
+			wait_event(zs->strm_wait, !list_empty(&zs->idle_strm));
+			continue;
+		}
+		break;
+	}
+	return zstrm;
+}
+
+/* add stream back to idle list and wake up waiter or free the stream */
+static void zcomp_strm_multi_release(struct zcomp *comp, struct zcomp_strm *zstrm)
+{
+	struct zcomp_strm_multi *zs = comp->stream;
+
+	spin_lock(&zs->strm_lock);
+	if (zs->avail_strm <= zs->max_strm) {
+		list_add(&zstrm->list, &zs->idle_strm);
+		spin_unlock(&zs->strm_lock);
+		wake_up(&zs->strm_wait);
+		return;
+	}
+
+	zs->avail_strm--;
+	spin_unlock(&zs->strm_lock);
+	zcomp_strm_free(comp, zstrm);
+}
+
+/* change max_strm limit */
+static bool zcomp_strm_multi_set_max_streams(struct zcomp *comp, int num_strm)
+{
+	struct zcomp_strm_multi *zs = comp->stream;
+	struct zcomp_strm *zstrm;
+
+	spin_lock(&zs->strm_lock);
+	zs->max_strm = num_strm;
+	/*
+	 * if user has lowered the limit and there are idle streams,
+	 * immediately free as much streams (and memory) as we can.
+	 */
+	while (zs->avail_strm > num_strm && !list_empty(&zs->idle_strm)) {
+		zstrm = list_entry(zs->idle_strm.next,
+				struct zcomp_strm, list);
+		list_del(&zstrm->list);
+		zcomp_strm_free(comp, zstrm);
+		zs->avail_strm--;
+	}
+	spin_unlock(&zs->strm_lock);
+	return true;
+}
+
+static void zcomp_strm_multi_destroy(struct zcomp *comp)
+{
+	struct zcomp_strm_multi *zs = comp->stream;
+	struct zcomp_strm *zstrm;
+
+	while (!list_empty(&zs->idle_strm)) {
+		zstrm = list_entry(zs->idle_strm.next,
+				struct zcomp_strm, list);
+		list_del(&zstrm->list);
+		zcomp_strm_free(comp, zstrm);
+	}
+	kfree(zs);
+}
+
+static int zcomp_strm_multi_create(struct zcomp *comp, int max_strm)
+{
+	struct zcomp_strm *zstrm;
+	struct zcomp_strm_multi *zs;
+
+	comp->destroy = zcomp_strm_multi_destroy;
+	comp->strm_find = zcomp_strm_multi_find;
+	comp->strm_release = zcomp_strm_multi_release;
+	comp->set_max_streams = zcomp_strm_multi_set_max_streams;
+	zs = kmalloc(sizeof(struct zcomp_strm_multi), GFP_KERNEL);
+	if (!zs)
+		return -ENOMEM;
+
+	comp->stream = zs;
+	spin_lock_init(&zs->strm_lock);
+	INIT_LIST_HEAD(&zs->idle_strm);
+	init_waitqueue_head(&zs->strm_wait);
+	zs->max_strm = max_strm;
+	zs->avail_strm = 1;
+
+	zstrm = zcomp_strm_alloc(comp);
+	if (!zstrm) {
+		kfree(zs);
+		return -ENOMEM;
+	}
+	list_add(&zstrm->list, &zs->idle_strm);
+	return 0;
+}
+
+static struct zcomp_strm *zcomp_strm_single_find(struct zcomp *comp)
+{
+	struct zcomp_strm_single *zs = comp->stream;
+	mutex_lock(&zs->strm_lock);
+	return zs->zstrm;
+}
+
+static void zcomp_strm_single_release(struct zcomp *comp,
+		struct zcomp_strm *zstrm)
+{
+	struct zcomp_strm_single *zs = comp->stream;
+	mutex_unlock(&zs->strm_lock);
+}
+
+static bool zcomp_strm_single_set_max_streams(struct zcomp *comp, int num_strm)
+{
+	/* zcomp_strm_single support only max_comp_streams == 1 */
+	return false;
+}
+
+static void zcomp_strm_single_destroy(struct zcomp *comp)
+{
+	struct zcomp_strm_single *zs = comp->stream;
+	zcomp_strm_free(comp, zs->zstrm);
+	kfree(zs);
+}
+
+static int zcomp_strm_single_create(struct zcomp *comp)
+{
+	struct zcomp_strm_single *zs;
+
+	comp->destroy = zcomp_strm_single_destroy;
+	comp->strm_find = zcomp_strm_single_find;
+	comp->strm_release = zcomp_strm_single_release;
+	comp->set_max_streams = zcomp_strm_single_set_max_streams;
+	zs = kmalloc(sizeof(struct zcomp_strm_single), GFP_KERNEL);
+	if (!zs)
+		return -ENOMEM;
+
+	comp->stream = zs;
+	mutex_init(&zs->strm_lock);
+	zs->zstrm = zcomp_strm_alloc(comp);
+	if (!zs->zstrm) {
+		kfree(zs);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+/* show available compressors */
+ssize_t zcomp_available_show(const char *comp, char *buf)
+{
+	ssize_t sz = 0;
+	int i = 0;
+
+	while (backends[i]) {
+		if (sysfs_streq(comp, backends[i]->name))
+			sz += scnprintf(buf + sz, PAGE_SIZE - sz - 2,
+					"[%s] ", backends[i]->name);
+		else
+			sz += scnprintf(buf + sz, PAGE_SIZE - sz - 2,
+					"%s ", backends[i]->name);
+		i++;
+	}
+	sz += scnprintf(buf + sz, PAGE_SIZE - sz, "\n");
+	return sz;
+}
+
+bool zcomp_set_max_streams(struct zcomp *comp, int num_strm)
+{
+	return comp->set_max_streams(comp, num_strm);
+}
+
+struct zcomp_strm *zcomp_strm_find(struct zcomp *comp)
+{
+	return comp->strm_find(comp);
+}
+
+void zcomp_strm_release(struct zcomp *comp, struct zcomp_strm *zstrm)
+{
+	comp->strm_release(comp, zstrm);
+}
+
+int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm,
+		const unsigned char *src, size_t *dst_len)
+{
+	return comp->backend->compress(src, zstrm->buffer, dst_len,
+			zstrm->private);
+}
+
+int zcomp_decompress(struct zcomp *comp, const unsigned char *src,
+		size_t src_len, unsigned char *dst)
+{
+	return comp->backend->decompress(src, src_len, dst);
+}
+
+void zcomp_destroy(struct zcomp *comp)
+{
+	comp->destroy(comp);
+	kfree(comp);
+}
+
+/*
+ * search available compressors for requested algorithm.
+ * allocate new zcomp and initialize it. return compressing
+ * backend pointer or ERR_PTR if things went bad. ERR_PTR(-EINVAL)
+ * if requested algorithm is not supported, ERR_PTR(-ENOMEM) in
+ * case of allocation error.
+ */
+struct zcomp *zcomp_create(const char *compress, int max_strm)
+{
+	struct zcomp *comp;
+	struct zcomp_backend *backend;
+
+	backend = find_backend(compress);
+	if (!backend)
+		return ERR_PTR(-EINVAL);
+
+	comp = kzalloc(sizeof(struct zcomp), GFP_KERNEL);
+	if (!comp)
+		return ERR_PTR(-ENOMEM);
+
+	comp->backend = backend;
+	if (max_strm > 1)
+		zcomp_strm_multi_create(comp, max_strm);
+	else
+		zcomp_strm_single_create(comp);
+	if (!comp->stream) {
+		kfree(comp);
+		return ERR_PTR(-ENOMEM);
+	}
+	return comp;
+}
diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
new file mode 100644
index 000000000000..c59d1fca72c0
--- /dev/null
+++ b/drivers/block/zram/zcomp.h
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ZCOMP_H_
+#define _ZCOMP_H_
+
+#include <linux/mutex.h>
+
+struct zcomp_strm {
+	/* compression/decompression buffer */
+	void *buffer;
+	/*
+	 * The private data of the compression stream, only compression
+	 * stream backend can touch this (e.g. compression algorithm
+	 * working memory)
+	 */
+	void *private;
+	/* used in multi stream backend, protected by backend strm_lock */
+	struct list_head list;
+};
+
+/* static compression backend */
+struct zcomp_backend {
+	int (*compress)(const unsigned char *src, unsigned char *dst,
+			size_t *dst_len, void *private);
+
+	int (*decompress)(const unsigned char *src, size_t src_len,
+			unsigned char *dst);
+
+	void *(*create)(void);
+	void (*destroy)(void *private);
+
+	const char *name;
+};
+
+/* dynamic per-device compression frontend */
+struct zcomp {
+	void *stream;
+	struct zcomp_backend *backend;
+
+	struct zcomp_strm *(*strm_find)(struct zcomp *comp);
+	void (*strm_release)(struct zcomp *comp, struct zcomp_strm *zstrm);
+	bool (*set_max_streams)(struct zcomp *comp, int num_strm);
+	void (*destroy)(struct zcomp *comp);
+};
+
+ssize_t zcomp_available_show(const char *comp, char *buf);
+
+struct zcomp *zcomp_create(const char *comp, int max_strm);
+void zcomp_destroy(struct zcomp *comp);
+
+struct zcomp_strm *zcomp_strm_find(struct zcomp *comp);
+void zcomp_strm_release(struct zcomp *comp, struct zcomp_strm *zstrm);
+
+int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm,
+		const unsigned char *src, size_t *dst_len);
+
+int zcomp_decompress(struct zcomp *comp, const unsigned char *src,
+		size_t src_len, unsigned char *dst);
+
+bool zcomp_set_max_streams(struct zcomp *comp, int num_strm);
+#endif /* _ZCOMP_H_ */
diff --git a/drivers/block/zram/zcomp_lz4.c b/drivers/block/zram/zcomp_lz4.c
new file mode 100644
index 000000000000..f2afb7e988c3
--- /dev/null
+++ b/drivers/block/zram/zcomp_lz4.c
@@ -0,0 +1,47 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/lz4.h>
+
+#include "zcomp_lz4.h"
+
+static void *zcomp_lz4_create(void)
+{
+	return kzalloc(LZ4_MEM_COMPRESS, GFP_KERNEL);
+}
+
+static void zcomp_lz4_destroy(void *private)
+{
+	kfree(private);
+}
+
+static int zcomp_lz4_compress(const unsigned char *src, unsigned char *dst,
+		size_t *dst_len, void *private)
+{
+	/* return  : Success if return 0 */
+	return lz4_compress(src, PAGE_SIZE, dst, dst_len, private);
+}
+
+static int zcomp_lz4_decompress(const unsigned char *src, size_t src_len,
+		unsigned char *dst)
+{
+	size_t dst_len = PAGE_SIZE;
+	/* return  : Success if return 0 */
+	return lz4_decompress_unknownoutputsize(src, src_len, dst, &dst_len);
+}
+
+struct zcomp_backend zcomp_lz4 = {
+	.compress = zcomp_lz4_compress,
+	.decompress = zcomp_lz4_decompress,
+	.create = zcomp_lz4_create,
+	.destroy = zcomp_lz4_destroy,
+	.name = "lz4",
+};
diff --git a/drivers/block/zram/zcomp_lz4.h b/drivers/block/zram/zcomp_lz4.h
new file mode 100644
index 000000000000..60613fb29dd8
--- /dev/null
+++ b/drivers/block/zram/zcomp_lz4.h
@@ -0,0 +1,17 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ZCOMP_LZ4_H_
+#define _ZCOMP_LZ4_H_
+
+#include "zcomp.h"
+
+extern struct zcomp_backend zcomp_lz4;
+
+#endif /* _ZCOMP_LZ4_H_ */
diff --git a/drivers/block/zram/zcomp_lzo.c b/drivers/block/zram/zcomp_lzo.c
new file mode 100644
index 000000000000..da1bc47d588e
--- /dev/null
+++ b/drivers/block/zram/zcomp_lzo.c
@@ -0,0 +1,47 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/lzo.h>
+
+#include "zcomp_lzo.h"
+
+static void *lzo_create(void)
+{
+	return kzalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
+}
+
+static void lzo_destroy(void *private)
+{
+	kfree(private);
+}
+
+static int lzo_compress(const unsigned char *src, unsigned char *dst,
+		size_t *dst_len, void *private)
+{
+	int ret = lzo1x_1_compress(src, PAGE_SIZE, dst, dst_len, private);
+	return ret == LZO_E_OK ? 0 : ret;
+}
+
+static int lzo_decompress(const unsigned char *src, size_t src_len,
+		unsigned char *dst)
+{
+	size_t dst_len = PAGE_SIZE;
+	int ret = lzo1x_decompress_safe(src, src_len, dst, &dst_len);
+	return ret == LZO_E_OK ? 0 : ret;
+}
+
+struct zcomp_backend zcomp_lzo = {
+	.compress = lzo_compress,
+	.decompress = lzo_decompress,
+	.create = lzo_create,
+	.destroy = lzo_destroy,
+	.name = "lzo",
+};
diff --git a/drivers/block/zram/zcomp_lzo.h b/drivers/block/zram/zcomp_lzo.h
new file mode 100644
index 000000000000..128c5807fa14
--- /dev/null
+++ b/drivers/block/zram/zcomp_lzo.h
@@ -0,0 +1,17 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ZCOMP_LZO_H_
+#define _ZCOMP_LZO_H_
+
+#include "zcomp.h"
+
+extern struct zcomp_backend zcomp_lzo;
+
+#endif /* _ZCOMP_LZO_H_ */
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 51c557cfd92b..9849b5233bf4 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -29,19 +29,36 @@
 #include <linux/genhd.h>
 #include <linux/highmem.h>
 #include <linux/slab.h>
-#include <linux/lzo.h>
 #include <linux/string.h>
 #include <linux/vmalloc.h>
+#include <linux/err.h>
 
 #include "zram_drv.h"
 
 /* Globals */
 static int zram_major;
 static struct zram *zram_devices;
+static const char *default_compressor = "lzo";
 
 /* Module params (documentation at end) */
 static unsigned int num_devices = 1;
 
+#define ZRAM_ATTR_RO(name)						\
+static ssize_t zram_attr_##name##_show(struct device *d,		\
+				struct device_attribute *attr, char *b)	\
+{									\
+	struct zram *zram = dev_to_zram(d);				\
+	return scnprintf(b, PAGE_SIZE, "%llu\n",			\
+		(u64)atomic64_read(&zram->stats.name));			\
+}									\
+static struct device_attribute dev_attr_##name =			\
+	__ATTR(name, S_IRUGO, zram_attr_##name##_show, NULL);
+
+static inline int init_done(struct zram *zram)
+{
+	return zram->meta != NULL;
+}
+
 static inline struct zram *dev_to_zram(struct device *dev)
 {
 	return (struct zram *)dev_to_disk(dev)->private_data;
@@ -52,92 +69,114 @@ static ssize_t disksize_show(struct device *dev,
 {
 	struct zram *zram = dev_to_zram(dev);
 
-	return sprintf(buf, "%llu\n", zram->disksize);
+	return scnprintf(buf, PAGE_SIZE, "%llu\n", zram->disksize);
 }
 
 static ssize_t initstate_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
+	u32 val;
 	struct zram *zram = dev_to_zram(dev);
 
-	return sprintf(buf, "%u\n", zram->init_done);
-}
-
-static ssize_t num_reads_show(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	struct zram *zram = dev_to_zram(dev);
+	down_read(&zram->init_lock);
+	val = init_done(zram);
+	up_read(&zram->init_lock);
 
-	return sprintf(buf, "%llu\n",
-			(u64)atomic64_read(&zram->stats.num_reads));
+	return scnprintf(buf, PAGE_SIZE, "%u\n", val);
 }
 
-static ssize_t num_writes_show(struct device *dev,
+static ssize_t orig_data_size_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct zram *zram = dev_to_zram(dev);
 
-	return sprintf(buf, "%llu\n",
-			(u64)atomic64_read(&zram->stats.num_writes));
+	return scnprintf(buf, PAGE_SIZE, "%llu\n",
+		(u64)(atomic64_read(&zram->stats.pages_stored)) << PAGE_SHIFT);
 }
 
-static ssize_t invalid_io_show(struct device *dev,
+static ssize_t mem_used_total_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
+	u64 val = 0;
 	struct zram *zram = dev_to_zram(dev);
+	struct zram_meta *meta = zram->meta;
 
-	return sprintf(buf, "%llu\n",
-			(u64)atomic64_read(&zram->stats.invalid_io));
-}
-
-static ssize_t notify_free_show(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	struct zram *zram = dev_to_zram(dev);
+	down_read(&zram->init_lock);
+	if (init_done(zram))
+		val = zs_get_total_size_bytes(meta->mem_pool);
+	up_read(&zram->init_lock);
 
-	return sprintf(buf, "%llu\n",
-			(u64)atomic64_read(&zram->stats.notify_free));
+	return scnprintf(buf, PAGE_SIZE, "%llu\n", val);
 }
 
-static ssize_t zero_pages_show(struct device *dev,
+static ssize_t max_comp_streams_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
+	int val;
 	struct zram *zram = dev_to_zram(dev);
 
-	return sprintf(buf, "%u\n", atomic_read(&zram->stats.pages_zero));
+	down_read(&zram->init_lock);
+	val = zram->max_comp_streams;
+	up_read(&zram->init_lock);
+
+	return scnprintf(buf, PAGE_SIZE, "%d\n", val);
 }
 
-static ssize_t orig_data_size_show(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t max_comp_streams_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
 {
+	int num;
 	struct zram *zram = dev_to_zram(dev);
+	int ret;
 
-	return sprintf(buf, "%llu\n",
-		(u64)(atomic_read(&zram->stats.pages_stored)) << PAGE_SHIFT);
-}
+	ret = kstrtoint(buf, 0, &num);
+	if (ret < 0)
+		return ret;
+	if (num < 1)
+		return -EINVAL;
 
-static ssize_t compr_data_size_show(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	struct zram *zram = dev_to_zram(dev);
+	down_write(&zram->init_lock);
+	if (init_done(zram)) {
+		if (!zcomp_set_max_streams(zram->comp, num)) {
+			pr_info("Cannot change max compression streams\n");
+			ret = -EINVAL;
+			goto out;
+		}
+	}
 
-	return sprintf(buf, "%llu\n",
-			(u64)atomic64_read(&zram->stats.compr_size));
+	zram->max_comp_streams = num;
+	ret = len;
+out:
+	up_write(&zram->init_lock);
+	return ret;
 }
 
-static ssize_t mem_used_total_show(struct device *dev,
+static ssize_t comp_algorithm_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	u64 val = 0;
+	size_t sz;
 	struct zram *zram = dev_to_zram(dev);
-	struct zram_meta *meta = zram->meta;
 
 	down_read(&zram->init_lock);
-	if (zram->init_done)
-		val = zs_get_total_size_bytes(meta->mem_pool);
+	sz = zcomp_available_show(zram->compressor, buf);
 	up_read(&zram->init_lock);
 
-	return sprintf(buf, "%llu\n", val);
+	return sz;
+}
+
+static ssize_t comp_algorithm_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct zram *zram = dev_to_zram(dev);
+	down_write(&zram->init_lock);
+	if (init_done(zram)) {
+		up_write(&zram->init_lock);
+		pr_info("Can't change algorithm for initialized device\n");
+		return -EBUSY;
+	}
+	strlcpy(zram->compressor, buf, sizeof(zram->compressor));
+	up_write(&zram->init_lock);
+	return len;
 }
 
 /* flag operations needs meta->tb_lock */
@@ -192,8 +231,6 @@ static inline int valid_io_request(struct zram *zram, struct bio *bio)
 static void zram_meta_free(struct zram_meta *meta)
 {
 	zs_destroy_pool(meta->mem_pool);
-	kfree(meta->compress_workmem);
-	free_pages((unsigned long)meta->compress_buffer, 1);
 	vfree(meta->table);
 	kfree(meta);
 }
@@ -205,22 +242,11 @@ static struct zram_meta *zram_meta_alloc(u64 disksize)
 	if (!meta)
 		goto out;
 
-	meta->compress_workmem = kzalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
-	if (!meta->compress_workmem)
-		goto free_meta;
-
-	meta->compress_buffer =
-		(void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
-	if (!meta->compress_buffer) {
-		pr_err("Error allocating compressor buffer space\n");
-		goto free_workmem;
-	}
-
 	num_pages = disksize >> PAGE_SHIFT;
 	meta->table = vzalloc(num_pages * sizeof(*meta->table));
 	if (!meta->table) {
 		pr_err("Error allocating zram address table\n");
-		goto free_buffer;
+		goto free_meta;
 	}
 
 	meta->mem_pool = zs_create_pool(GFP_NOIO | __GFP_HIGHMEM);
@@ -230,15 +256,10 @@ static struct zram_meta *zram_meta_alloc(u64 disksize)
 	}
 
 	rwlock_init(&meta->tb_lock);
-	mutex_init(&meta->buffer_lock);
 	return meta;
 
 free_table:
 	vfree(meta->table);
-free_buffer:
-	free_pages((unsigned long)meta->compress_buffer, 1);
-free_workmem:
-	kfree(meta->compress_workmem);
 free_meta:
 	kfree(meta);
 	meta = NULL;
@@ -288,7 +309,6 @@ static void zram_free_page(struct zram *zram, size_t index)
 {
 	struct zram_meta *meta = zram->meta;
 	unsigned long handle = meta->table[index].handle;
-	u16 size = meta->table[index].size;
 
 	if (unlikely(!handle)) {
 		/*
@@ -297,21 +317,15 @@ static void zram_free_page(struct zram *zram, size_t index)
 		 */
 		if (zram_test_flag(meta, index, ZRAM_ZERO)) {
 			zram_clear_flag(meta, index, ZRAM_ZERO);
-			atomic_dec(&zram->stats.pages_zero);
+			atomic64_dec(&zram->stats.zero_pages);
 		}
 		return;
 	}
 
-	if (unlikely(size > max_zpage_size))
-		atomic_dec(&zram->stats.bad_compress);
-
 	zs_free(meta->mem_pool, handle);
 
-	if (size <= PAGE_SIZE / 2)
-		atomic_dec(&zram->stats.good_compress);
-
-	atomic64_sub(meta->table[index].size, &zram->stats.compr_size);
-	atomic_dec(&zram->stats.pages_stored);
+	atomic64_sub(meta->table[index].size, &zram->stats.compr_data_size);
+	atomic64_dec(&zram->stats.pages_stored);
 
 	meta->table[index].handle = 0;
 	meta->table[index].size = 0;
@@ -319,8 +333,7 @@ static void zram_free_page(struct zram *zram, size_t index)
 
 static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
 {
-	int ret = LZO_E_OK;
-	size_t clen = PAGE_SIZE;
+	int ret = 0;
 	unsigned char *cmem;
 	struct zram_meta *meta = zram->meta;
 	unsigned long handle;
@@ -340,12 +353,12 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
 	if (size == PAGE_SIZE)
 		copy_page(mem, cmem);
 	else
-		ret = lzo1x_decompress_safe(cmem, size,	mem, &clen);
+		ret = zcomp_decompress(zram->comp, cmem, size, mem);
 	zs_unmap_object(meta->mem_pool, handle);
 	read_unlock(&meta->tb_lock);
 
 	/* Should NEVER happen. Return bio error if it does. */
-	if (unlikely(ret != LZO_E_OK)) {
+	if (unlikely(ret)) {
 		pr_err("Decompression failed! err=%d, page=%u\n", ret, index);
 		atomic64_inc(&zram->stats.failed_reads);
 		return ret;
@@ -388,7 +401,7 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
 
 	ret = zram_decompress_page(zram, uncmem, index);
 	/* Should NEVER happen. Return bio error if it does. */
-	if (unlikely(ret != LZO_E_OK))
+	if (unlikely(ret))
 		goto out_cleanup;
 
 	if (is_partial_io(bvec))
@@ -413,11 +426,10 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 	struct page *page;
 	unsigned char *user_mem, *cmem, *src, *uncmem = NULL;
 	struct zram_meta *meta = zram->meta;
+	struct zcomp_strm *zstrm;
 	bool locked = false;
 
 	page = bvec->bv_page;
-	src = meta->compress_buffer;
-
 	if (is_partial_io(bvec)) {
 		/*
 		 * This is a partial IO. We need to read the full page
@@ -433,7 +445,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 			goto out;
 	}
 
-	mutex_lock(&meta->buffer_lock);
+	zstrm = zcomp_strm_find(zram->comp);
 	locked = true;
 	user_mem = kmap_atomic(page);
 
@@ -454,28 +466,25 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 		zram_set_flag(meta, index, ZRAM_ZERO);
 		write_unlock(&zram->meta->tb_lock);
 
-		atomic_inc(&zram->stats.pages_zero);
+		atomic64_inc(&zram->stats.zero_pages);
 		ret = 0;
 		goto out;
 	}
 
-	ret = lzo1x_1_compress(uncmem, PAGE_SIZE, src, &clen,
-			       meta->compress_workmem);
+	ret = zcomp_compress(zram->comp, zstrm, uncmem, &clen);
 	if (!is_partial_io(bvec)) {
 		kunmap_atomic(user_mem);
 		user_mem = NULL;
 		uncmem = NULL;
 	}
 
-	if (unlikely(ret != LZO_E_OK)) {
+	if (unlikely(ret)) {
 		pr_err("Compression failed! err=%d\n", ret);
 		goto out;
 	}
-
+	src = zstrm->buffer;
 	if (unlikely(clen > max_zpage_size)) {
-		atomic_inc(&zram->stats.bad_compress);
 		clen = PAGE_SIZE;
-		src = NULL;
 		if (is_partial_io(bvec))
 			src = uncmem;
 	}
@@ -497,6 +506,8 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 		memcpy(cmem, src, clen);
 	}
 
+	zcomp_strm_release(zram->comp, zstrm);
+	locked = false;
 	zs_unmap_object(meta->mem_pool, handle);
 
 	/*
@@ -511,49 +522,88 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 	write_unlock(&zram->meta->tb_lock);
 
 	/* Update stats */
-	atomic64_add(clen, &zram->stats.compr_size);
-	atomic_inc(&zram->stats.pages_stored);
-	if (clen <= PAGE_SIZE / 2)
-		atomic_inc(&zram->stats.good_compress);
-
+	atomic64_add(clen, &zram->stats.compr_data_size);
+	atomic64_inc(&zram->stats.pages_stored);
 out:
 	if (locked)
-		mutex_unlock(&meta->buffer_lock);
+		zcomp_strm_release(zram->comp, zstrm);
 	if (is_partial_io(bvec))
 		kfree(uncmem);
-
 	if (ret)
 		atomic64_inc(&zram->stats.failed_writes);
 	return ret;
 }
 
 static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
-			int offset, struct bio *bio, int rw)
+			int offset, struct bio *bio)
 {
 	int ret;
+	int rw = bio_data_dir(bio);
 
-	if (rw == READ)
+	if (rw == READ) {
+		atomic64_inc(&zram->stats.num_reads);
 		ret = zram_bvec_read(zram, bvec, index, offset, bio);
-	else
+	} else {
+		atomic64_inc(&zram->stats.num_writes);
 		ret = zram_bvec_write(zram, bvec, index, offset);
+	}
 
 	return ret;
 }
 
+/*
+ * zram_bio_discard - handler on discard request
+ * @index: physical block index in PAGE_SIZE units
+ * @offset: byte offset within physical block
+ */
+static void zram_bio_discard(struct zram *zram, u32 index,
+			     int offset, struct bio *bio)
+{
+	size_t n = bio->bi_iter.bi_size;
+
+	/*
+	 * zram manages data in physical block size units. Because logical block
+	 * size isn't identical with physical block size on some arch, we
+	 * could get a discard request pointing to a specific offset within a
+	 * certain physical block.  Although we can handle this request by
+	 * reading that physiclal block and decompressing and partially zeroing
+	 * and re-compressing and then re-storing it, this isn't reasonable
+	 * because our intent with a discard request is to save memory.  So
+	 * skipping this logical block is appropriate here.
+	 */
+	if (offset) {
+		if (n < offset)
+			return;
+
+		n -= offset;
+		index++;
+	}
+
+	while (n >= PAGE_SIZE) {
+		/*
+		 * Discard request can be large so the lock hold times could be
+		 * lengthy.  So take the lock once per page.
+		 */
+		write_lock(&zram->meta->tb_lock);
+		zram_free_page(zram, index);
+		write_unlock(&zram->meta->tb_lock);
+		index++;
+		n -= PAGE_SIZE;
+	}
+}
+
 static void zram_reset_device(struct zram *zram, bool reset_capacity)
 {
 	size_t index;
 	struct zram_meta *meta;
 
 	down_write(&zram->init_lock);
-	if (!zram->init_done) {
+	if (!init_done(zram)) {
 		up_write(&zram->init_lock);
 		return;
 	}
 
 	meta = zram->meta;
-	zram->init_done = 0;
-
 	/* Free all pages that are still in this zram device */
 	for (index = 0; index < zram->disksize >> PAGE_SHIFT; index++) {
 		unsigned long handle = meta->table[index].handle;
@@ -563,6 +613,9 @@ static void zram_reset_device(struct zram *zram, bool reset_capacity)
 		zs_free(meta->mem_pool, handle);
 	}
 
+	zcomp_destroy(zram->comp);
+	zram->max_comp_streams = 1;
+
 	zram_meta_free(zram->meta);
 	zram->meta = NULL;
 	/* Reset stats */
@@ -574,37 +627,14 @@ static void zram_reset_device(struct zram *zram, bool reset_capacity)
 	up_write(&zram->init_lock);
 }
 
-static void zram_init_device(struct zram *zram, struct zram_meta *meta)
-{
-	if (zram->disksize > 2 * (totalram_pages << PAGE_SHIFT)) {
-		pr_info(
-		"There is little point creating a zram of greater than "
-		"twice the size of memory since we expect a 2:1 compression "
-		"ratio. Note that zram uses about 0.1%% of the size of "
-		"the disk when not in use so a huge zram is "
-		"wasteful.\n"
-		"\tMemory Size: %lu kB\n"
-		"\tSize you selected: %llu kB\n"
-		"Continuing anyway ...\n",
-		(totalram_pages << PAGE_SHIFT) >> 10, zram->disksize >> 10
-		);
-	}
-
-	/* zram devices sort of resembles non-rotational disks */
-	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue);
-
-	zram->meta = meta;
-	zram->init_done = 1;
-
-	pr_debug("Initialization done!\n");
-}
-
 static ssize_t disksize_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
 {
 	u64 disksize;
+	struct zcomp *comp;
 	struct zram_meta *meta;
 	struct zram *zram = dev_to_zram(dev);
+	int err;
 
 	disksize = memparse(buf, NULL);
 	if (!disksize)
@@ -614,20 +644,35 @@ static ssize_t disksize_store(struct device *dev,
 	meta = zram_meta_alloc(disksize);
 	if (!meta)
 		return -ENOMEM;
+
+	comp = zcomp_create(zram->compressor, zram->max_comp_streams);
+	if (IS_ERR(comp)) {
+		pr_info("Cannot initialise %s compressing backend\n",
+				zram->compressor);
+		err = PTR_ERR(comp);
+		goto out_free_meta;
+	}
+
 	down_write(&zram->init_lock);
-	if (zram->init_done) {
-		up_write(&zram->init_lock);
-		zram_meta_free(meta);
+	if (init_done(zram)) {
 		pr_info("Cannot change disksize for initialized device\n");
-		return -EBUSY;
+		err = -EBUSY;
+		goto out_destroy_comp;
 	}
 
+	zram->meta = meta;
+	zram->comp = comp;
 	zram->disksize = disksize;
 	set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
-	zram_init_device(zram, meta);
 	up_write(&zram->init_lock);
-
 	return len;
+
+out_destroy_comp:
+	up_write(&zram->init_lock);
+	zcomp_destroy(comp);
+out_free_meta:
+	zram_meta_free(meta);
+	return err;
 }
 
 static ssize_t reset_store(struct device *dev,
@@ -671,26 +716,23 @@ out:
 	return ret;
 }
 
-static void __zram_make_request(struct zram *zram, struct bio *bio, int rw)
+static void __zram_make_request(struct zram *zram, struct bio *bio)
 {
 	int offset;
 	u32 index;
 	struct bio_vec bvec;
 	struct bvec_iter iter;
 
-	switch (rw) {
-	case READ:
-		atomic64_inc(&zram->stats.num_reads);
-		break;
-	case WRITE:
-		atomic64_inc(&zram->stats.num_writes);
-		break;
-	}
-
 	index = bio->bi_iter.bi_sector >> SECTORS_PER_PAGE_SHIFT;
 	offset = (bio->bi_iter.bi_sector &
 		  (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
 
+	if (unlikely(bio->bi_rw & REQ_DISCARD)) {
+		zram_bio_discard(zram, index, offset, bio);
+		bio_endio(bio, 0);
+		return;
+	}
+
 	bio_for_each_segment(bvec, bio, iter) {
 		int max_transfer_size = PAGE_SIZE - offset;
 
@@ -705,16 +747,15 @@ static void __zram_make_request(struct zram *zram, struct bio *bio, int rw)
 			bv.bv_len = max_transfer_size;
 			bv.bv_offset = bvec.bv_offset;
 
-			if (zram_bvec_rw(zram, &bv, index, offset, bio, rw) < 0)
+			if (zram_bvec_rw(zram, &bv, index, offset, bio) < 0)
 				goto out;
 
 			bv.bv_len = bvec.bv_len - max_transfer_size;
 			bv.bv_offset += max_transfer_size;
-			if (zram_bvec_rw(zram, &bv, index+1, 0, bio, rw) < 0)
+			if (zram_bvec_rw(zram, &bv, index + 1, 0, bio) < 0)
 				goto out;
 		} else
-			if (zram_bvec_rw(zram, &bvec, index, offset, bio, rw)
-			    < 0)
+			if (zram_bvec_rw(zram, &bvec, index, offset, bio) < 0)
 				goto out;
 
 		update_position(&index, &offset, &bvec);
@@ -736,7 +777,7 @@ static void zram_make_request(struct request_queue *queue, struct bio *bio)
 	struct zram *zram = queue->queuedata;
 
 	down_read(&zram->init_lock);
-	if (unlikely(!zram->init_done))
+	if (unlikely(!init_done(zram)))
 		goto error;
 
 	if (!valid_io_request(zram, bio)) {
@@ -744,7 +785,7 @@ static void zram_make_request(struct request_queue *queue, struct bio *bio)
 		goto error;
 	}
 
-	__zram_make_request(zram, bio, bio_data_dir(bio));
+	__zram_make_request(zram, bio);
 	up_read(&zram->init_lock);
 
 	return;
@@ -778,14 +819,21 @@ static DEVICE_ATTR(disksize, S_IRUGO | S_IWUSR,
 		disksize_show, disksize_store);
 static DEVICE_ATTR(initstate, S_IRUGO, initstate_show, NULL);
 static DEVICE_ATTR(reset, S_IWUSR, NULL, reset_store);
-static DEVICE_ATTR(num_reads, S_IRUGO, num_reads_show, NULL);
-static DEVICE_ATTR(num_writes, S_IRUGO, num_writes_show, NULL);
-static DEVICE_ATTR(invalid_io, S_IRUGO, invalid_io_show, NULL);
-static DEVICE_ATTR(notify_free, S_IRUGO, notify_free_show, NULL);
-static DEVICE_ATTR(zero_pages, S_IRUGO, zero_pages_show, NULL);
 static DEVICE_ATTR(orig_data_size, S_IRUGO, orig_data_size_show, NULL);
-static DEVICE_ATTR(compr_data_size, S_IRUGO, compr_data_size_show, NULL);
 static DEVICE_ATTR(mem_used_total, S_IRUGO, mem_used_total_show, NULL);
+static DEVICE_ATTR(max_comp_streams, S_IRUGO | S_IWUSR,
+		max_comp_streams_show, max_comp_streams_store);
+static DEVICE_ATTR(comp_algorithm, S_IRUGO | S_IWUSR,
+		comp_algorithm_show, comp_algorithm_store);
+
+ZRAM_ATTR_RO(num_reads);
+ZRAM_ATTR_RO(num_writes);
+ZRAM_ATTR_RO(failed_reads);
+ZRAM_ATTR_RO(failed_writes);
+ZRAM_ATTR_RO(invalid_io);
+ZRAM_ATTR_RO(notify_free);
+ZRAM_ATTR_RO(zero_pages);
+ZRAM_ATTR_RO(compr_data_size);
 
 static struct attribute *zram_disk_attrs[] = {
 	&dev_attr_disksize.attr,
@@ -793,12 +841,16 @@ static struct attribute *zram_disk_attrs[] = {
 	&dev_attr_reset.attr,
 	&dev_attr_num_reads.attr,
 	&dev_attr_num_writes.attr,
+	&dev_attr_failed_reads.attr,
+	&dev_attr_failed_writes.attr,
 	&dev_attr_invalid_io.attr,
 	&dev_attr_notify_free.attr,
 	&dev_attr_zero_pages.attr,
 	&dev_attr_orig_data_size.attr,
 	&dev_attr_compr_data_size.attr,
 	&dev_attr_mem_used_total.attr,
+	&dev_attr_max_comp_streams.attr,
+	&dev_attr_comp_algorithm.attr,
 	NULL,
 };
 
@@ -839,7 +891,8 @@ static int create_device(struct zram *zram, int device_id)
 
 	/* Actual capacity set using syfs (/sys/block/zram<id>/disksize */
 	set_capacity(zram->disk, 0);
-
+	/* zram devices sort of resembles non-rotational disks */
+	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue);
 	/*
 	 * To ensure that we always get PAGE_SIZE aligned
 	 * and n*PAGE_SIZED sized I/O requests.
@@ -849,6 +902,21 @@ static int create_device(struct zram *zram, int device_id)
 					ZRAM_LOGICAL_BLOCK_SIZE);
 	blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
 	blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
+	zram->disk->queue->limits.discard_granularity = PAGE_SIZE;
+	zram->disk->queue->limits.max_discard_sectors = UINT_MAX;
+	/*
+	 * zram_bio_discard() will clear all logical blocks if logical block
+	 * size is identical with physical block size(PAGE_SIZE). But if it is
+	 * different, we will skip discarding some parts of logical blocks in
+	 * the part of the request range which isn't aligned to physical block
+	 * size.  So we can't ensure that all discarded logical blocks are
+	 * zeroed.
+	 */
+	if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
+		zram->disk->queue->limits.discard_zeroes_data = 1;
+	else
+		zram->disk->queue->limits.discard_zeroes_data = 0;
+	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zram->disk->queue);
 
 	add_disk(zram->disk);
 
@@ -858,8 +926,9 @@ static int create_device(struct zram *zram, int device_id)
 		pr_warn("Error creating sysfs group");
 		goto out_free_disk;
 	}
-
-	zram->init_done = 0;
+	strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));
+	zram->meta = NULL;
+	zram->max_comp_streams = 1;
 	return 0;
 
 out_free_disk:
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index ad8aa35bae00..7f21c145e317 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -16,9 +16,10 @@
 #define _ZRAM_DRV_H_
 
 #include <linux/spinlock.h>
-#include <linux/mutex.h>
 #include <linux/zsmalloc.h>
 
+#include "zcomp.h"
+
 /*
  * Some arbitrary value. This is just to catch
  * invalid value for num_devices module parameter.
@@ -64,38 +65,33 @@ enum zram_pageflags {
 struct table {
 	unsigned long handle;
 	u16 size;	/* object size (excluding header) */
-	u8 count;	/* object ref count (not yet used) */
 	u8 flags;
 } __aligned(4);
 
 struct zram_stats {
-	atomic64_t compr_size;	/* compressed size of pages stored */
+	atomic64_t compr_data_size;	/* compressed size of pages stored */
 	atomic64_t num_reads;	/* failed + successful */
 	atomic64_t num_writes;	/* --do-- */
 	atomic64_t failed_reads;	/* should NEVER! happen */
 	atomic64_t failed_writes;	/* can happen when memory is too low */
 	atomic64_t invalid_io;	/* non-page-aligned I/O requests */
 	atomic64_t notify_free;	/* no. of swap slot free notifications */
-	atomic_t pages_zero;		/* no. of zero filled pages */
-	atomic_t pages_stored;	/* no. of pages currently stored */
-	atomic_t good_compress;	/* % of pages with compression ratio<=50% */
-	atomic_t bad_compress;	/* % of pages with compression ratio>=75% */
+	atomic64_t zero_pages;		/* no. of zero filled pages */
+	atomic64_t pages_stored;	/* no. of pages currently stored */
 };
 
 struct zram_meta {
 	rwlock_t tb_lock;	/* protect table */
-	void *compress_workmem;
-	void *compress_buffer;
 	struct table *table;
 	struct zs_pool *mem_pool;
-	struct mutex buffer_lock; /* protect compress buffers */
 };
 
 struct zram {
 	struct zram_meta *meta;
 	struct request_queue *queue;
 	struct gendisk *disk;
-	int init_done;
+	struct zcomp *comp;
+
 	/* Prevent concurrent execution of device init, reset and R/W request */
 	struct rw_semaphore init_lock;
 	/*
@@ -103,7 +99,8 @@ struct zram {
 	 * we can store in a disk.
 	 */
 	u64 disksize;	/* bytes */
-
+	int max_comp_streams;
 	struct zram_stats stats;
+	char compressor[10];
 };
 #endif
diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig
index a11ff74a5127..9eac8de9e8b7 100644
--- a/drivers/input/Kconfig
+++ b/drivers/input/Kconfig
@@ -178,6 +178,15 @@ comment "Input Device Drivers"
 
 source "drivers/input/keyboard/Kconfig"
 
+config INPUT_LEDS
+	bool "LED Support"
+	depends on LEDS_CLASS = INPUT || LEDS_CLASS = y
+	select LEDS_TRIGGERS
+	default y
+	help
+	  This option enables support for LEDs on keyboards managed
+	  by the input layer.
+
 source "drivers/input/mouse/Kconfig"
 
 source "drivers/input/joystick/Kconfig"
diff --git a/drivers/input/Makefile b/drivers/input/Makefile
index 5ca3f631497f..2ab5f3336da5 100644
--- a/drivers/input/Makefile
+++ b/drivers/input/Makefile
@@ -6,6 +6,9 @@
 
 obj-$(CONFIG_INPUT)		+= input-core.o
 input-core-y := input.o input-compat.o input-mt.o ff-core.o
+ifeq ($(CONFIG_INPUT_LEDS),y)
+input-core-y += leds.o
+endif
 
 obj-$(CONFIG_INPUT_FF_MEMLESS)	+= ff-memless.o
 obj-$(CONFIG_INPUT_POLLDEV)	+= input-polldev.o
diff --git a/drivers/input/input.c b/drivers/input/input.c
index 1c4c0db05550..3b9284b18e70 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -708,6 +708,9 @@ static void input_disconnect_device(struct input_dev *dev)
 		handle->open = 0;
 
 	spin_unlock_irq(&dev->event_lock);
+
+	if (is_event_supported(EV_LED, dev->evbit, EV_MAX))
+		input_led_disconnect(dev);
 }
 
 /**
@@ -2134,6 +2137,9 @@ int input_register_device(struct input_dev *dev)
 
 	list_add_tail(&dev->node, &input_dev_list);
 
+	if (is_event_supported(EV_LED, dev->evbit, EV_MAX))
+		input_led_connect(dev);
+
 	list_for_each_entry(handler, &input_handler_list, node)
 		input_attach_handler(dev, handler);
 
diff --git a/drivers/input/leds.c b/drivers/input/leds.c
new file mode 100644
index 000000000000..1d8a980719ab
--- /dev/null
+++ b/drivers/input/leds.c
@@ -0,0 +1,249 @@
+/*
+ * LED support for the input layer
+ *
+ * Copyright 2010-2013 Samuel Thibault <samuel.thibault@ens-lyon.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/leds.h>
+#include <linux/input.h>
+
+/*
+ * Keyboard LEDs are propagated by default like the following example:
+ *
+ * VT keyboard numlock trigger
+ * -> vt::numl VT LED
+ * -> vt-numl VT trigger
+ * -> per-device inputX::numl LED
+ *
+ * Userland can however choose the trigger for the vt::numl LED, or
+ * independently choose the trigger for any inputx::numl LED.
+ *
+ *
+ * VT LED classes and triggers are registered on-demand according to
+ * existing LED devices
+ */
+
+/* Handler for VT LEDs, just triggers the corresponding VT trigger. */
+static void vt_led_set(struct led_classdev *cdev,
+			  enum led_brightness brightness);
+static struct led_classdev vt_leds[LED_CNT] = {
+#define DEFINE_INPUT_LED(vt_led, nam, deftrig) \
+	[vt_led] = { \
+		.name = "vt::"nam, \
+		.max_brightness = 1, \
+		.brightness_set = vt_led_set, \
+		.default_trigger = deftrig, \
+	}
+/* Default triggers for the VT LEDs just correspond to the legacy
+ * usage. */
+	DEFINE_INPUT_LED(LED_NUML, "numl", "kbd-numlock"),
+	DEFINE_INPUT_LED(LED_CAPSL, "capsl", "kbd-capslock"),
+	DEFINE_INPUT_LED(LED_SCROLLL, "scrolll", "kbd-scrollock"),
+	DEFINE_INPUT_LED(LED_COMPOSE, "compose", NULL),
+	DEFINE_INPUT_LED(LED_KANA, "kana", "kbd-kanalock"),
+	DEFINE_INPUT_LED(LED_SLEEP, "sleep", NULL),
+	DEFINE_INPUT_LED(LED_SUSPEND, "suspend", NULL),
+	DEFINE_INPUT_LED(LED_MUTE, "mute", NULL),
+	DEFINE_INPUT_LED(LED_MISC, "misc", NULL),
+	DEFINE_INPUT_LED(LED_MAIL, "mail", NULL),
+	DEFINE_INPUT_LED(LED_CHARGING, "charging", NULL),
+};
+static const char *const vt_led_names[LED_CNT] = {
+	[LED_NUML] = "numl",
+	[LED_CAPSL] = "capsl",
+	[LED_SCROLLL] = "scrolll",
+	[LED_COMPOSE] = "compose",
+	[LED_KANA] = "kana",
+	[LED_SLEEP] = "sleep",
+	[LED_SUSPEND] = "suspend",
+	[LED_MUTE] = "mute",
+	[LED_MISC] = "misc",
+	[LED_MAIL] = "mail",
+	[LED_CHARGING] = "charging",
+};
+/* Handler for hotplug initialization */
+static void vt_led_trigger_activate(struct led_classdev *cdev);
+/* VT triggers */
+static struct led_trigger vt_led_triggers[LED_CNT] = {
+#define DEFINE_INPUT_LED_TRIGGER(vt_led, nam) \
+	[vt_led] = { \
+		.name = "vt-"nam, \
+		.activate = vt_led_trigger_activate, \
+	}
+	DEFINE_INPUT_LED_TRIGGER(LED_NUML, "numl"),
+	DEFINE_INPUT_LED_TRIGGER(LED_CAPSL, "capsl"),
+	DEFINE_INPUT_LED_TRIGGER(LED_SCROLLL, "scrolll"),
+	DEFINE_INPUT_LED_TRIGGER(LED_COMPOSE, "compose"),
+	DEFINE_INPUT_LED_TRIGGER(LED_KANA, "kana"),
+	DEFINE_INPUT_LED_TRIGGER(LED_SLEEP, "sleep"),
+	DEFINE_INPUT_LED_TRIGGER(LED_SUSPEND, "suspend"),
+	DEFINE_INPUT_LED_TRIGGER(LED_MUTE, "mute"),
+	DEFINE_INPUT_LED_TRIGGER(LED_MISC, "misc"),
+	DEFINE_INPUT_LED_TRIGGER(LED_MAIL, "mail"),
+	DEFINE_INPUT_LED_TRIGGER(LED_CHARGING, "charging"),
+};
+
+/* Lock for registration coherency */
+static DEFINE_MUTEX(vt_led_registered_lock);
+
+/* Which VT LED classes and triggers are registered */
+static unsigned long vt_led_registered[BITS_TO_LONGS(LED_CNT)];
+
+/* Number of input devices having each LED */
+static int vt_led_references[LED_CNT];
+
+/* VT LED state change, tell the VT trigger.  */
+static void vt_led_set(struct led_classdev *cdev,
+			  enum led_brightness brightness)
+{
+	int led = cdev - vt_leds;
+
+	led_trigger_event(&vt_led_triggers[led], !!brightness);
+}
+
+/* LED state change for some keyboard, notify that keyboard.  */
+static void perdevice_input_led_set(struct led_classdev *cdev,
+			  enum led_brightness brightness)
+{
+	struct input_dev *dev;
+	struct led_classdev *leds;
+	int led;
+
+	dev = cdev->dev->platform_data;
+	if (!dev)
+		/* Still initializing */
+		return;
+	leds = dev->leds;
+	led = cdev - leds;
+
+	input_event(dev, EV_LED, led, !!brightness);
+	input_event(dev, EV_SYN, SYN_REPORT, 0);
+}
+
+/* Keyboard hotplug, initialize its LED status */
+static void vt_led_trigger_activate(struct led_classdev *cdev)
+{
+	struct led_trigger *trigger = cdev->trigger;
+	int led = trigger - vt_led_triggers;
+
+	if (cdev->brightness_set)
+		cdev->brightness_set(cdev, vt_leds[led].brightness);
+}
+
+/* Free led stuff from input device, used at abortion and disconnection.  */
+static void input_led_delete(struct input_dev *dev)
+{
+	if (dev) {
+		struct led_classdev *leds = dev->leds;
+		if (leds) {
+			int i;
+			for (i = 0; i < LED_CNT; i++)
+				kfree(leds[i].name);
+			kfree(leds);
+			dev->leds = NULL;
+		}
+	}
+}
+
+/* A new input device with potential LEDs to connect.  */
+int input_led_connect(struct input_dev *dev)
+{
+	int i, error = 0;
+	struct led_classdev *leds;
+
+	dev->leds = leds = kzalloc(sizeof(*leds) * LED_CNT, GFP_KERNEL);
+	if (!dev->leds)
+		return -ENOMEM;
+
+	/* lazily register missing VT LEDs */
+	mutex_lock(&vt_led_registered_lock);
+	for (i = 0; i < LED_CNT; i++)
+		if (vt_leds[i].name && test_bit(i, dev->ledbit)) {
+			if (!vt_led_references[i]) {
+				led_trigger_register(&vt_led_triggers[i]);
+				/* This keyboard is first to have led i,
+				 * try to register it */
+				if (!led_classdev_register(NULL, &vt_leds[i]))
+					vt_led_references[i] = 1;
+				else
+					led_trigger_unregister(&vt_led_triggers[i]);
+			} else
+				vt_led_references[i]++;
+		}
+	mutex_unlock(&vt_led_registered_lock);
+
+	/* and register this device's LEDs */
+	for (i = 0; i < LED_CNT; i++)
+		if (vt_leds[i].name && test_bit(i, dev->ledbit)) {
+			leds[i].name = kasprintf(GFP_KERNEL, "%s::%s",
+						dev_name(&dev->dev),
+						vt_led_names[i]);
+			if (!leds[i].name) {
+				error = -ENOMEM;
+				goto err;
+			}
+			leds[i].max_brightness = 1;
+			leds[i].brightness_set = perdevice_input_led_set;
+			leds[i].default_trigger = vt_led_triggers[i].name;
+		}
+
+	/* No issue so far, we can register for real.  */
+	for (i = 0; i < LED_CNT; i++)
+		if (leds[i].name) {
+			led_classdev_register(&dev->dev, &leds[i]);
+			leds[i].dev->platform_data = dev;
+			perdevice_input_led_set(&leds[i],
+					vt_leds[i].brightness);
+		}
+
+	return 0;
+
+err:
+	input_led_delete(dev);
+	return error;
+}
+
+/*
+ * Disconnected input device. Clean it, and deregister now-useless VT LEDs and
+ * triggers.
+ */
+void input_led_disconnect(struct input_dev *dev)
+{
+	int i;
+	struct led_classdev *leds = dev->leds;
+
+	for (i = 0; i < LED_CNT; i++)
+		if (leds[i].name)
+			led_classdev_unregister(&leds[i]);
+
+	input_led_delete(dev);
+
+	mutex_lock(&vt_led_registered_lock);
+	for (i = 0; i < LED_CNT; i++) {
+		if (!vt_leds[i].name || !test_bit(i, dev->ledbit))
+			continue;
+
+		vt_led_references[i]--;
+		if (vt_led_references[i]) {
+			/* Still some devices needing it */
+			continue;
+		}
+
+		led_classdev_unregister(&vt_leds[i]);
+		led_trigger_unregister(&vt_led_triggers[i]);
+		clear_bit(i, vt_led_registered);
+	}
+	mutex_unlock(&vt_led_registered_lock);
+}
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("User LED support for input layer");
+MODULE_AUTHOR("Samuel Thibault <samuel.thibault@ens-lyon.org>");
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 6de9dfbf61c1..20626821b997 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -11,9 +11,6 @@ menuconfig NEW_LEDS
 	  Say Y to enable Linux LED support.  This allows control of supported
 	  LEDs from both userspace and optionally, by kernel events (triggers).
 
-	  This is not related to standard keyboard LEDs which are controlled
-	  via the input system.
-
 if NEW_LEDS
 
 config LEDS_CLASS
diff --git a/drivers/lguest/page_tables.c b/drivers/lguest/page_tables.c
index bfb39bb56ef1..e8b55c3a6170 100644
--- a/drivers/lguest/page_tables.c
+++ b/drivers/lguest/page_tables.c
@@ -887,7 +887,7 @@ void guest_new_pagetable(struct lg_cpu *cpu, unsigned long pgtable)
  * _PAGE_ACCESSED then we can put a read-only PTE entry in immediately, and if
  * they set _PAGE_DIRTY then we can put a writable PTE entry in immediately.
  */
-static void do_set_pte(struct lg_cpu *cpu, int idx,
+static void __guest_set_pte(struct lg_cpu *cpu, int idx,
 		       unsigned long vaddr, pte_t gpte)
 {
 	/* Look up the matching shadow page directory entry. */
@@ -960,13 +960,13 @@ void guest_set_pte(struct lg_cpu *cpu,
 		unsigned int i;
 		for (i = 0; i < ARRAY_SIZE(cpu->lg->pgdirs); i++)
 			if (cpu->lg->pgdirs[i].pgdir)
-				do_set_pte(cpu, i, vaddr, gpte);
+				__guest_set_pte(cpu, i, vaddr, gpte);
 	} else {
 		/* Is this page table one we have a shadow for? */
 		int pgdir = find_pgdir(cpu->lg, gpgdir);
 		if (pgdir != ARRAY_SIZE(cpu->lg->pgdirs))
 			/* If so, do the update. */
-			do_set_pte(cpu, pgdir, vaddr, gpte);
+			__guest_set_pte(cpu, pgdir, vaddr, gpte);
 	}
 }
 
diff --git a/drivers/misc/sgi-gru/grukdump.c b/drivers/misc/sgi-gru/grukdump.c
index 2bef3f76032a..a3700a56b8ff 100644
--- a/drivers/misc/sgi-gru/grukdump.c
+++ b/drivers/misc/sgi-gru/grukdump.c
@@ -178,10 +178,10 @@ static int gru_dump_context(struct gru_state *gru, int ctxnum,
 	hdr.cbrcnt = cbrcnt;
 	hdr.dsrcnt = dsrcnt;
 	hdr.cch_locked = cch_locked;
-	if (!ret && copy_to_user((void __user *)uhdr, &hdr, sizeof(hdr)))
-		ret = -EFAULT;
+	if (copy_to_user(uhdr, &hdr, sizeof(hdr)))
+		return -EFAULT;
 
-	return ret ? ret : bytes;
+	return bytes;
 }
 
 int gru_dump_chiplet_request(unsigned long arg)
diff --git a/drivers/misc/ti-st/st_core.c b/drivers/misc/ti-st/st_core.c
index 1972d57aadb3..e7fbc08a0627 100644
--- a/drivers/misc/ti-st/st_core.c
+++ b/drivers/misc/ti-st/st_core.c
@@ -342,7 +342,7 @@ void st_int_recv(void *disc_data,
 			/* Unknow packet? */
 		default:
 			type = *ptr;
-			if (st_gdata->list[type] == NULL) {
+			if (type >= ST_MAX_CHANNELS || st_gdata->list[type] == NULL) {
 				pr_err("chip/interface misbehavior dropping"
 					" frame starting with 0x%02x", type);
 				goto done;
diff --git a/drivers/net/irda/donauboe.c b/drivers/net/irda/donauboe.c
index 768dfe9a9315..6d3e2093bf7f 100644
--- a/drivers/net/irda/donauboe.c
+++ b/drivers/net/irda/donauboe.c
@@ -1755,17 +1755,4 @@ static struct pci_driver donauboe_pci_driver = {
 	.resume		= toshoboe_wakeup 
 };
 
-static int __init
-donauboe_init (void)
-{
-  return pci_register_driver(&donauboe_pci_driver);
-}
-
-static void __exit
-donauboe_cleanup (void)
-{
-  pci_unregister_driver(&donauboe_pci_driver);
-}
-
-module_init(donauboe_init);
-module_exit(donauboe_cleanup);
+module_pci_driver(donauboe_pci_driver);
diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c
index 6d1f6ed3113f..a8497183ff8b 100644
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -493,6 +493,7 @@ static int rionet_setup_netdev(struct rio_mport *mport, struct net_device *ndev)
 	ndev->netdev_ops = &rionet_netdev_ops;
 	ndev->mtu = RIO_MAX_MSG_SIZE - 14;
 	ndev->features = NETIF_F_LLTX;
+	SET_NETDEV_DEV(ndev, &mport->dev);
 	SET_ETHTOOL_OPS(ndev, &rionet_ethtool_ops);
 
 	spin_lock_init(&rnet->lock);
diff --git a/drivers/pps/pps.c b/drivers/pps/pps.c
index 2f07cd615665..983f50c4b7b4 100644
--- a/drivers/pps/pps.c
+++ b/drivers/pps/pps.c
@@ -152,35 +152,38 @@ static long pps_cdev_ioctl(struct file *file,
 		if (err)
 			return -EFAULT;
 
-		ev = pps->last_ev;
-
-		/* Manage the timeout */
-		if (fdata.timeout.flags & PPS_TIME_INVALID)
-			err = wait_event_interruptible(pps->queue,
-					ev != pps->last_ev);
-		else {
-			unsigned long ticks;
-
-			dev_dbg(pps->dev, "timeout %lld.%09d\n",
-					(long long) fdata.timeout.sec,
-					fdata.timeout.nsec);
-			ticks = fdata.timeout.sec * HZ;
-			ticks += fdata.timeout.nsec / (NSEC_PER_SEC / HZ);
-
-			if (ticks != 0) {
-				err = wait_event_interruptible_timeout(
-						pps->queue,
-						ev != pps->last_ev,
-						ticks);
-				if (err == 0)
-					return -ETIMEDOUT;
+		if (!(file->f_flags & O_NONBLOCK)) {
+			ev = pps->last_ev;
+
+			/* Manage the timeout */
+			if (fdata.timeout.flags & PPS_TIME_INVALID)
+				err = wait_event_interruptible(pps->queue,
+						ev != pps->last_ev);
+			else {
+				unsigned long ticks;
+
+				dev_dbg(pps->dev, "timeout %lld.%09d\n",
+						(long long) fdata.timeout.sec,
+						fdata.timeout.nsec);
+				ticks = fdata.timeout.sec * HZ;
+				ticks += fdata.timeout.nsec /
+					(NSEC_PER_SEC / HZ);
+
+				if (ticks != 0) {
+					err = wait_event_interruptible_timeout(
+							pps->queue,
+							ev != pps->last_ev,
+							ticks);
+					if (err == 0)
+						return -ETIMEDOUT;
+				}
 			}
-		}
 
-		/* Check for pending signals */
-		if (err == -ERESTARTSYS) {
-			dev_dbg(pps->dev, "pending signal caught\n");
-			return -EINTR;
+			/* Check for pending signals */
+			if (err == -ERESTARTSYS) {
+				dev_dbg(pps->dev, "pending signal caught\n");
+				return -EINTR;
+			}
 		}
 
 		/* Return the fetched timestamp */
diff --git a/drivers/rapidio/devices/tsi721.c b/drivers/rapidio/devices/tsi721.c
index ff7cbf2d28e3..1753dc693c15 100644
--- a/drivers/rapidio/devices/tsi721.c
+++ b/drivers/rapidio/devices/tsi721.c
@@ -2256,6 +2256,7 @@ static int tsi721_setup_mport(struct tsi721_device *priv)
 	mport->phy_type = RIO_PHY_SERIAL;
 	mport->priv = (void *)priv;
 	mport->phys_efptr = 0x100;
+	mport->dev.parent = &pdev->dev;
 	priv->mport = mport;
 
 	INIT_LIST_HEAD(&mport->dbells);
diff --git a/drivers/rapidio/devices/tsi721.h b/drivers/rapidio/devices/tsi721.h
index 7061ac0ad428..0305675270ee 100644
--- a/drivers/rapidio/devices/tsi721.h
+++ b/drivers/rapidio/devices/tsi721.h
@@ -644,6 +644,9 @@ enum tsi721_smsg_int_flag {
 
 #ifdef CONFIG_RAPIDIO_DMA_ENGINE
 
+#define TSI721_BDMA_BD_RING_SZ	128
+#define TSI721_BDMA_MAX_BCOUNT	(TSI721_DMAD_BCOUNT1 + 1)
+
 struct tsi721_tx_desc {
 	struct dma_async_tx_descriptor	txd;
 	struct tsi721_dma_desc		*hw_desc;
@@ -652,6 +655,7 @@ struct tsi721_tx_desc {
 	u64				rio_addr;
 	/* upper 2-bits of 66-bit RIO address */
 	u8				rio_addr_u;
+	u32				bcount;
 	bool				interrupt;
 	struct list_head		desc_node;
 	struct list_head		tx_list;
diff --git a/drivers/rapidio/devices/tsi721_dma.c b/drivers/rapidio/devices/tsi721_dma.c
index 91245f5dbe81..9b60b1f3261c 100644
--- a/drivers/rapidio/devices/tsi721_dma.c
+++ b/drivers/rapidio/devices/tsi721_dma.c
@@ -304,35 +304,17 @@ struct tsi721_tx_desc *tsi721_desc_get(struct tsi721_bdma_chan *bdma_chan)
 }
 
 static int
-tsi721_fill_desc(struct tsi721_bdma_chan *bdma_chan,
-	struct tsi721_tx_desc *desc, struct scatterlist *sg,
+tsi721_desc_fill_init(struct tsi721_tx_desc *desc, struct scatterlist *sg,
 	enum dma_rtype rtype, u32 sys_size)
 {
 	struct tsi721_dma_desc *bd_ptr = desc->hw_desc;
 	u64 rio_addr;
 
-	if (sg_dma_len(sg) > TSI721_DMAD_BCOUNT1 + 1) {
-		dev_err(bdma_chan->dchan.device->dev,
-			"SG element is too large\n");
-		return -EINVAL;
-	}
-
-	dev_dbg(bdma_chan->dchan.device->dev,
-		"desc: 0x%llx, addr: 0x%llx len: 0x%x\n",
-		(u64)desc->txd.phys, (unsigned long long)sg_dma_address(sg),
-		sg_dma_len(sg));
-
-	dev_dbg(bdma_chan->dchan.device->dev,
-		"bd_ptr = %p did=%d raddr=0x%llx\n",
-		bd_ptr, desc->destid, desc->rio_addr);
-
 	/* Initialize DMA descriptor */
 	bd_ptr->type_id = cpu_to_le32((DTYPE1 << 29) |
 					(rtype << 19) | desc->destid);
-	if (desc->interrupt)
-		bd_ptr->type_id |= cpu_to_le32(TSI721_DMAD_IOF);
 	bd_ptr->bcount = cpu_to_le32(((desc->rio_addr & 0x3) << 30) |
-					(sys_size << 26) | sg_dma_len(sg));
+				     (sys_size << 26));
 	rio_addr = (desc->rio_addr >> 2) |
 				((u64)(desc->rio_addr_u & 0x3) << 62);
 	bd_ptr->raddr_lo = cpu_to_le32(rio_addr & 0xffffffff);
@@ -346,6 +328,20 @@ tsi721_fill_desc(struct tsi721_bdma_chan *bdma_chan,
 	return 0;
 }
 
+static int
+tsi721_desc_fill_end(struct tsi721_tx_desc *desc)
+{
+	struct tsi721_dma_desc *bd_ptr = desc->hw_desc;
+
+	/* Update DMA descriptor */
+	if (desc->interrupt)
+		bd_ptr->type_id |= cpu_to_le32(TSI721_DMAD_IOF);
+	bd_ptr->bcount |= cpu_to_le32(desc->bcount & TSI721_DMAD_BCOUNT1);
+
+	return 0;
+}
+
+
 static void tsi721_dma_chain_complete(struct tsi721_bdma_chan *bdma_chan,
 				      struct tsi721_tx_desc *desc)
 {
@@ -674,6 +670,7 @@ struct dma_async_tx_descriptor *tsi721_prep_rio_sg(struct dma_chan *dchan,
 	unsigned int i;
 	u32 sys_size = dma_to_mport(dchan->device)->sys_size;
 	enum dma_rtype rtype;
+	dma_addr_t next_addr = -1;
 
 	if (!sgl || !sg_len) {
 		dev_err(dchan->device->dev, "%s: No SG list\n", __func__);
@@ -704,36 +701,84 @@ struct dma_async_tx_descriptor *tsi721_prep_rio_sg(struct dma_chan *dchan,
 	for_each_sg(sgl, sg, sg_len, i) {
 		int err;
 
-		dev_dbg(dchan->device->dev, "%s: sg #%d\n", __func__, i);
+		if (sg_dma_len(sg) > TSI721_BDMA_MAX_BCOUNT) {
+			dev_err(dchan->device->dev,
+				"%s: SG entry %d is too large\n", __func__, i);
+			goto err_desc_put;
+		}
+
+		/*
+		 * If this sg entry forms contiguous block with previous one,
+		 * try to merge it into existing DMA descriptor
+		 */
+		if (desc) {
+			if (next_addr == sg_dma_address(sg) &&
+			    desc->bcount + sg_dma_len(sg) <=
+						TSI721_BDMA_MAX_BCOUNT) {
+				/* Adjust byte count of the descriptor */
+				desc->bcount += sg_dma_len(sg);
+				goto entry_done;
+			}
+
+			/*
+			 * Finalize this descriptor using total
+			 * byte count value.
+			 */
+			tsi721_desc_fill_end(desc);
+			dev_dbg(dchan->device->dev, "%s: desc final len: %d\n",
+				__func__, desc->bcount);
+		}
+
+		/*
+		 * Obtain and initialize a new descriptor
+		 */
 		desc = tsi721_desc_get(bdma_chan);
 		if (!desc) {
 			dev_err(dchan->device->dev,
-				"Not enough descriptors available\n");
-			goto err_desc_get;
+				"%s: Failed to get new descriptor for SG %d\n",
+				__func__, i);
+			goto err_desc_put;
 		}
 
-		if (sg_is_last(sg))
-			desc->interrupt = (flags & DMA_PREP_INTERRUPT) != 0;
-		else
-			desc->interrupt = false;
-
 		desc->destid = rext->destid;
 		desc->rio_addr = rio_addr;
 		desc->rio_addr_u = 0;
+		desc->bcount = sg_dma_len(sg);
+
+		dev_dbg(dchan->device->dev,
+			"sg%d desc: 0x%llx, addr: 0x%llx len: %d\n",
+			i, (u64)desc->txd.phys,
+			(unsigned long long)sg_dma_address(sg),
+			sg_dma_len(sg));
+
+		dev_dbg(dchan->device->dev,
+			"bd_ptr = %p did=%d raddr=0x%llx\n",
+			desc->hw_desc, desc->destid, desc->rio_addr);
 
-		err = tsi721_fill_desc(bdma_chan, desc, sg, rtype, sys_size);
+		err = tsi721_desc_fill_init(desc, sg, rtype, sys_size);
 		if (err) {
 			dev_err(dchan->device->dev,
 				"Failed to build desc: %d\n", err);
-			goto err_desc_get;
+			goto err_desc_put;
 		}
 
-		rio_addr += sg_dma_len(sg);
+		next_addr = sg_dma_address(sg);
 
 		if (!first)
 			first = desc;
 		else
 			list_add_tail(&desc->desc_node, &first->tx_list);
+
+entry_done:
+		if (sg_is_last(sg)) {
+			desc->interrupt = (flags & DMA_PREP_INTERRUPT) != 0;
+			tsi721_desc_fill_end(desc);
+			dev_dbg(dchan->device->dev, "%s: desc final len: %d\n",
+				__func__, desc->bcount);
+		} else {
+			rio_addr += sg_dma_len(sg);
+			next_addr += sg_dma_len(sg);
+		}
 	}
 
 	first->txd.cookie = -EBUSY;
@@ -741,7 +786,7 @@ struct dma_async_tx_descriptor *tsi721_prep_rio_sg(struct dma_chan *dchan,
 
 	return &first->txd;
 
-err_desc_get:
+err_desc_put:
 	tsi721_desc_put(bdma_chan, first);
 	return NULL;
 }
@@ -792,7 +837,7 @@ int tsi721_register_dma(struct tsi721_device *priv)
 		if (i == TSI721_DMACH_MAINT)
 			continue;
 
-		bdma_chan->bd_num = 64;
+		bdma_chan->bd_num = TSI721_BDMA_BD_RING_SZ;
 		bdma_chan->regs = priv->regs + TSI721_DMAC_BASE(i);
 
 		bdma_chan->dchan.device = &mport->dma;
diff --git a/drivers/rapidio/rio-driver.c b/drivers/rapidio/rio-driver.c
index c9ae692d3451..f301f059bb85 100644
--- a/drivers/rapidio/rio-driver.c
+++ b/drivers/rapidio/rio-driver.c
@@ -167,7 +167,6 @@ void rio_unregister_driver(struct rio_driver *rdrv)
 void rio_attach_device(struct rio_dev *rdev)
 {
 	rdev->dev.bus = &rio_bus_type;
-	rdev->dev.parent = &rio_bus;
 }
 EXPORT_SYMBOL_GPL(rio_attach_device);
 
@@ -216,9 +215,12 @@ static int rio_uevent(struct device *dev, struct kobj_uevent_env *env)
 	return 0;
 }
 
-struct device rio_bus = {
-	.init_name = "rapidio",
+struct class rio_mport_class = {
+	.name		= "rapidio_port",
+	.owner		= THIS_MODULE,
+	.dev_groups	= rio_mport_groups,
 };
+EXPORT_SYMBOL_GPL(rio_mport_class);
 
 struct bus_type rio_bus_type = {
 	.name = "rapidio",
@@ -233,14 +235,20 @@ struct bus_type rio_bus_type = {
 /**
  *  rio_bus_init - Register the RapidIO bus with the device model
  *
- *  Registers the RIO bus device and RIO bus type with the Linux
+ *  Registers the RIO mport device class and RIO bus type with the Linux
  *  device model.
  */
 static int __init rio_bus_init(void)
 {
-	if (device_register(&rio_bus) < 0)
-		printk("RIO: failed to register RIO bus device\n");
-	return bus_register(&rio_bus_type);
+	int ret;
+
+	ret = class_register(&rio_mport_class);
+	if (!ret) {
+		ret = bus_register(&rio_bus_type);
+		if (ret)
+			class_unregister(&rio_mport_class);
+	}
+	return ret;
 }
 
 postcore_initcall(rio_bus_init);
diff --git a/drivers/rapidio/rio-scan.c b/drivers/rapidio/rio-scan.c
index d3a6539a77cc..47a1b2ea76c4 100644
--- a/drivers/rapidio/rio-scan.c
+++ b/drivers/rapidio/rio-scan.c
@@ -461,6 +461,7 @@ static struct rio_dev *rio_setup_device(struct rio_net *net,
 			     rdev->comp_tag & RIO_CTAG_UDEVID);
 	}
 
+	rdev->dev.parent = &port->dev;
 	rio_attach_device(rdev);
 
 	device_initialize(&rdev->dev);
diff --git a/drivers/rapidio/rio-sysfs.c b/drivers/rapidio/rio-sysfs.c
index e0221c6d0cc2..cdb005c0094d 100644
--- a/drivers/rapidio/rio-sysfs.c
+++ b/drivers/rapidio/rio-sysfs.c
@@ -341,3 +341,43 @@ const struct attribute_group *rio_bus_groups[] = {
 	&rio_bus_group,
 	NULL,
 };
+
+static ssize_t
+port_destid_show(struct device *dev, struct device_attribute *attr,
+		 char *buf)
+{
+	struct rio_mport *mport = to_rio_mport(dev);
+
+	if (mport)
+		return sprintf(buf, "0x%04x\n", mport->host_deviceid);
+	else
+		return -ENODEV;
+}
+static DEVICE_ATTR_RO(port_destid);
+
+static ssize_t sys_size_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct rio_mport *mport = to_rio_mport(dev);
+
+	if (mport)
+		return sprintf(buf, "%u\n", mport->sys_size);
+	else
+		return -ENODEV;
+}
+static DEVICE_ATTR_RO(sys_size);
+
+static struct attribute *rio_mport_attrs[] = {
+	&dev_attr_port_destid.attr,
+	&dev_attr_sys_size.attr,
+	NULL,
+};
+
+static const struct attribute_group rio_mport_group = {
+	.attrs = rio_mport_attrs,
+};
+
+const struct attribute_group *rio_mport_groups[] = {
+	&rio_mport_group,
+	NULL,
+};
diff --git a/drivers/rapidio/rio.c b/drivers/rapidio/rio.c
index 2e8a20cac588..a54ba0494dd3 100644
--- a/drivers/rapidio/rio.c
+++ b/drivers/rapidio/rio.c
@@ -1884,6 +1884,7 @@ static int rio_get_hdid(int index)
 int rio_register_mport(struct rio_mport *port)
 {
 	struct rio_scan_node *scan = NULL;
+	int res = 0;
 
 	if (next_portid >= RIO_MAX_MPORTS) {
 		pr_err("RIO: reached specified max number of mports\n");
@@ -1894,6 +1895,16 @@ int rio_register_mport(struct rio_mport *port)
 	port->host_deviceid = rio_get_hdid(port->id);
 	port->nscan = NULL;
 
+	dev_set_name(&port->dev, "rapidio%d", port->id);
+	port->dev.class = &rio_mport_class;
+
+	res = device_register(&port->dev);
+	if (res)
+		dev_err(&port->dev, "RIO: mport%d registration failed ERR=%d\n",
+			port->id, res);
+	else
+		dev_dbg(&port->dev, "RIO: mport%d registered\n", port->id);
+
 	mutex_lock(&rio_mport_list_lock);
 	list_add_tail(&port->node, &rio_mports);
 
diff --git a/drivers/rapidio/rio.h b/drivers/rapidio/rio.h
index 5f99d22ad0b0..2d0550e08ea2 100644
--- a/drivers/rapidio/rio.h
+++ b/drivers/rapidio/rio.h
@@ -50,6 +50,7 @@ extern int rio_mport_scan(int mport_id);
 /* Structures internal to the RIO core code */
 extern const struct attribute_group *rio_dev_groups[];
 extern const struct attribute_group *rio_bus_groups[];
+extern const struct attribute_group *rio_mport_groups[];
 
 #define RIO_GET_DID(size, x)	(size ? (x & 0xffff) : ((x & 0x00ff0000) >> 16))
 #define RIO_SET_DID(size, x)	(size ? (x & 0xffff) : ((x & 0x000000ff) << 16))
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index db933decc39c..2e565f8e5165 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -573,6 +573,18 @@ config RTC_DRV_DS1305
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-ds1305.
 
+config RTC_DRV_DS1347
+	tristate "Dallas/Maxim DS1347"
+	help
+	  If you say yes here you get support for the
+	  Dallas/Maxim DS1347 chips.
+
+	  This driver only supports the RTC feature, and not other chip
+	  features such as alarms.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-ds1347.
+
 config RTC_DRV_DS1390
 	tristate "Dallas/Maxim DS1390/93/94"
 	help
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index b427bf7dd20d..40a09915c8f6 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -40,6 +40,7 @@ obj-$(CONFIG_RTC_DRV_DS1286)	+= rtc-ds1286.o
 obj-$(CONFIG_RTC_DRV_DS1302)	+= rtc-ds1302.o
 obj-$(CONFIG_RTC_DRV_DS1305)	+= rtc-ds1305.o
 obj-$(CONFIG_RTC_DRV_DS1307)	+= rtc-ds1307.o
+obj-$(CONFIG_RTC_DRV_DS1347)	+= rtc-ds1347.o
 obj-$(CONFIG_RTC_DRV_DS1374)	+= rtc-ds1374.o
 obj-$(CONFIG_RTC_DRV_DS1390)	+= rtc-ds1390.o
 obj-$(CONFIG_RTC_DRV_DS1511)	+= rtc-ds1511.o
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index 544be722937c..c2eff6082363 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -584,6 +584,9 @@ enum hrtimer_restart rtc_pie_update_irq(struct hrtimer *timer)
 void rtc_update_irq(struct rtc_device *rtc,
 		unsigned long num, unsigned long events)
 {
+	if (unlikely(IS_ERR_OR_NULL(rtc)))
+		return;
+
 	pm_stay_awake(rtc->dev.parent);
 	schedule_work(&rtc->irqwork);
 }
diff --git a/drivers/rtc/rtc-as3722.c b/drivers/rtc/rtc-as3722.c
index 4af016985890..9f38eda69154 100644
--- a/drivers/rtc/rtc-as3722.c
+++ b/drivers/rtc/rtc-as3722.c
@@ -242,9 +242,8 @@ static int as3722_rtc_resume(struct device *dev)
 }
 #endif
 
-static const struct dev_pm_ops as3722_rtc_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(as3722_rtc_suspend, as3722_rtc_resume)
-};
+static SIMPLE_DEV_PM_OPS(as3722_rtc_pm_ops, as3722_rtc_suspend,
+			 as3722_rtc_resume);
 
 static struct platform_driver as3722_rtc_driver = {
 	.probe = as3722_rtc_probe,
diff --git a/drivers/rtc/rtc-at32ap700x.c b/drivers/rtc/rtc-at32ap700x.c
index 3161ab5263ed..aee3387fb099 100644
--- a/drivers/rtc/rtc-at32ap700x.c
+++ b/drivers/rtc/rtc-at32ap700x.c
@@ -204,10 +204,8 @@ static int __init at32_rtc_probe(struct platform_device *pdev)
 
 	rtc = devm_kzalloc(&pdev->dev, sizeof(struct rtc_at32ap700x),
 			   GFP_KERNEL);
-	if (!rtc) {
-		dev_dbg(&pdev->dev, "out of memory\n");
+	if (!rtc)
 		return -ENOMEM;
-	}
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!regs) {
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index cae212f30d65..0963c9309c74 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -837,7 +837,7 @@ static void __exit cmos_do_remove(struct device *dev)
 	cmos->dev = NULL;
 }
 
-#ifdef	CONFIG_PM
+#ifdef	CONFIG_PM_SLEEP
 
 static int cmos_suspend(struct device *dev)
 {
@@ -935,8 +935,6 @@ static int cmos_resume(struct device *dev)
 	return 0;
 }
 
-static SIMPLE_DEV_PM_OPS(cmos_pm_ops, cmos_suspend, cmos_resume);
-
 #else
 
 static inline int cmos_poweroff(struct device *dev)
@@ -946,6 +944,8 @@ static inline int cmos_poweroff(struct device *dev)
 
 #endif
 
+static SIMPLE_DEV_PM_OPS(cmos_pm_ops, cmos_suspend, cmos_resume);
+
 /*----------------------------------------------------------------*/
 
 /* On non-x86 systems, a "CMOS" RTC lives most naturally on platform_bus.
@@ -1088,11 +1088,9 @@ static struct pnp_driver cmos_pnp_driver = {
 
 	/* flag ensures resume() gets called, and stops syslog spam */
 	.flags		= PNP_DRIVER_RES_DO_NOT_CHANGE,
-#ifdef CONFIG_PM_SLEEP
 	.driver		= {
 			.pm = &cmos_pm_ops,
 	},
-#endif
 };
 
 #endif	/* CONFIG_PNP */
diff --git a/drivers/rtc/rtc-coh901331.c b/drivers/rtc/rtc-coh901331.c
index 73f157519dff..869cae273799 100644
--- a/drivers/rtc/rtc-coh901331.c
+++ b/drivers/rtc/rtc-coh901331.c
@@ -43,8 +43,6 @@
 struct coh901331_port {
 	struct rtc_device *rtc;
 	struct clk *clk;
-	u32 phybase;
-	u32 physize;
 	void __iomem *virtbase;
 	int irq;
 #ifdef CONFIG_PM_SLEEP
@@ -173,19 +171,9 @@ static int __init coh901331_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -ENOENT;
-
-	rtap->phybase = res->start;
-	rtap->physize = resource_size(res);
-
-	if (devm_request_mem_region(&pdev->dev, rtap->phybase, rtap->physize,
-				    "rtc-coh901331") == NULL)
-		return -EBUSY;
-
-	rtap->virtbase = devm_ioremap(&pdev->dev, rtap->phybase, rtap->physize);
-	if (!rtap->virtbase)
-		return -ENOMEM;
+	rtap->virtbase  = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(rtap->virtbase))
+		return PTR_ERR(rtap->virtbase);
 
 	rtap->irq = platform_get_irq(pdev, 0);
 	if (devm_request_irq(&pdev->dev, rtap->irq, coh901331_interrupt, 0,
diff --git a/drivers/rtc/rtc-da9052.c b/drivers/rtc/rtc-da9052.c
index 4385ca4503da..a1cbf64242a5 100644
--- a/drivers/rtc/rtc-da9052.c
+++ b/drivers/rtc/rtc-da9052.c
@@ -26,7 +26,6 @@
 struct da9052_rtc {
 	struct rtc_device *rtc;
 	struct da9052 *da9052;
-	int irq;
 };
 
 static int da9052_rtc_enable_alarm(struct da9052 *da9052, bool enable)
@@ -240,8 +239,7 @@ static int da9052_rtc_probe(struct platform_device *pdev)
 
 	rtc->da9052 = dev_get_drvdata(pdev->dev.parent);
 	platform_set_drvdata(pdev, rtc);
-	rtc->irq =  DA9052_IRQ_ALARM;
-	ret = da9052_request_irq(rtc->da9052, rtc->irq, "ALM",
+	ret = da9052_request_irq(rtc->da9052, DA9052_IRQ_ALARM, "ALM",
 				da9052_rtc_irq, rtc);
 	if (ret != 0) {
 		rtc_err(rtc->da9052, "irq registration failed: %d\n", ret);
diff --git a/drivers/rtc/rtc-davinci.c b/drivers/rtc/rtc-davinci.c
index 24677ef8c39a..c0a3b59f65a2 100644
--- a/drivers/rtc/rtc-davinci.c
+++ b/drivers/rtc/rtc-davinci.c
@@ -119,8 +119,6 @@ static DEFINE_SPINLOCK(davinci_rtc_lock);
 struct davinci_rtc {
 	struct rtc_device		*rtc;
 	void __iomem			*base;
-	resource_size_t			pbase;
-	size_t				base_size;
 	int				irq;
 };
 
@@ -482,14 +480,12 @@ static int __init davinci_rtc_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct davinci_rtc *davinci_rtc;
-	struct resource *res, *mem;
+	struct resource *res;
 	int ret = 0;
 
 	davinci_rtc = devm_kzalloc(&pdev->dev, sizeof(struct davinci_rtc), GFP_KERNEL);
-	if (!davinci_rtc) {
-		dev_dbg(dev, "could not allocate memory for private data\n");
+	if (!davinci_rtc)
 		return -ENOMEM;
-	}
 
 	davinci_rtc->irq = platform_get_irq(pdev, 0);
 	if (davinci_rtc->irq < 0) {
@@ -498,28 +494,9 @@ static int __init davinci_rtc_probe(struct platform_device *pdev)
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(dev, "no mem resource\n");
-		return -EINVAL;
-	}
-
-	davinci_rtc->pbase = res->start;
-	davinci_rtc->base_size = resource_size(res);
-
-	mem = devm_request_mem_region(dev, davinci_rtc->pbase,
-				davinci_rtc->base_size, pdev->name);
-	if (!mem) {
-		dev_err(dev, "RTC registers at %08x are not free\n",
-			davinci_rtc->pbase);
-		return -EBUSY;
-	}
-
-	davinci_rtc->base = devm_ioremap(dev, davinci_rtc->pbase,
-					davinci_rtc->base_size);
-	if (!davinci_rtc->base) {
-		dev_err(dev, "unable to ioremap MEM resource\n");
-		return -ENOMEM;
-	}
+	davinci_rtc->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(davinci_rtc->base))
+		return PTR_ERR(davinci_rtc->base);
 
 	platform_set_drvdata(pdev, davinci_rtc);
 
diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c
index 4e75345a559a..580379a97f0c 100644
--- a/drivers/rtc/rtc-ds1307.c
+++ b/drivers/rtc/rtc-ds1307.c
@@ -154,6 +154,7 @@ static const struct chip_desc chips[last_ds_type] = {
 		.alarm		= 1,
 	},
 	[mcp7941x] = {
+		.alarm		= 1,
 		/* this is battery backed SRAM */
 		.nvram_offset	= 0x20,
 		.nvram_size	= 0x40,
@@ -606,6 +607,178 @@ static const struct rtc_class_ops ds13xx_rtc_ops = {
 
 /*----------------------------------------------------------------------*/
 
+/*
+ * Alarm support for mcp7941x devices.
+ */
+
+#define MCP7941X_REG_CONTROL		0x07
+#	define MCP7941X_BIT_ALM0_EN	0x10
+#	define MCP7941X_BIT_ALM1_EN	0x20
+#define MCP7941X_REG_ALARM0_BASE	0x0a
+#define MCP7941X_REG_ALARM0_CTRL	0x0d
+#define MCP7941X_REG_ALARM1_BASE	0x11
+#define MCP7941X_REG_ALARM1_CTRL	0x14
+#	define MCP7941X_BIT_ALMX_IF	(1 << 3)
+#	define MCP7941X_BIT_ALMX_C0	(1 << 4)
+#	define MCP7941X_BIT_ALMX_C1	(1 << 5)
+#	define MCP7941X_BIT_ALMX_C2	(1 << 6)
+#	define MCP7941X_BIT_ALMX_POL	(1 << 7)
+#	define MCP7941X_MSK_ALMX_MATCH	(MCP7941X_BIT_ALMX_C0 | \
+					 MCP7941X_BIT_ALMX_C1 | \
+					 MCP7941X_BIT_ALMX_C2)
+
+static void mcp7941x_work(struct work_struct *work)
+{
+	struct ds1307 *ds1307 = container_of(work, struct ds1307, work);
+	struct i2c_client *client = ds1307->client;
+	int reg, ret;
+
+	mutex_lock(&ds1307->rtc->ops_lock);
+
+	/* Check and clear alarm 0 interrupt flag. */
+	reg = i2c_smbus_read_byte_data(client, MCP7941X_REG_ALARM0_CTRL);
+	if (reg < 0)
+		goto out;
+	if (!(reg & MCP7941X_BIT_ALMX_IF))
+		goto out;
+	reg &= ~MCP7941X_BIT_ALMX_IF;
+	ret = i2c_smbus_write_byte_data(client, MCP7941X_REG_ALARM0_CTRL, reg);
+	if (ret < 0)
+		goto out;
+
+	/* Disable alarm 0. */
+	reg = i2c_smbus_read_byte_data(client, MCP7941X_REG_CONTROL);
+	if (reg < 0)
+		goto out;
+	reg &= ~MCP7941X_BIT_ALM0_EN;
+	ret = i2c_smbus_write_byte_data(client, MCP7941X_REG_CONTROL, reg);
+	if (ret < 0)
+		goto out;
+
+	rtc_update_irq(ds1307->rtc, 1, RTC_AF | RTC_IRQF);
+
+out:
+	if (test_bit(HAS_ALARM, &ds1307->flags))
+		enable_irq(client->irq);
+	mutex_unlock(&ds1307->rtc->ops_lock);
+}
+
+static int mcp7941x_read_alarm(struct device *dev, struct rtc_wkalrm *t)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct ds1307 *ds1307 = i2c_get_clientdata(client);
+	u8 *regs = ds1307->regs;
+	int ret;
+
+	if (!test_bit(HAS_ALARM, &ds1307->flags))
+		return -EINVAL;
+
+	/* Read control and alarm 0 registers. */
+	ret = ds1307->read_block_data(client, MCP7941X_REG_CONTROL, 10, regs);
+	if (ret < 0)
+		return ret;
+
+	t->enabled = !!(regs[0] & MCP7941X_BIT_ALM0_EN);
+
+	/* Report alarm 0 time assuming 24-hour and day-of-month modes. */
+	t->time.tm_sec = bcd2bin(ds1307->regs[3] & 0x7f);
+	t->time.tm_min = bcd2bin(ds1307->regs[4] & 0x7f);
+	t->time.tm_hour = bcd2bin(ds1307->regs[5] & 0x3f);
+	t->time.tm_wday = bcd2bin(ds1307->regs[6] & 0x7) - 1;
+	t->time.tm_mday = bcd2bin(ds1307->regs[7] & 0x3f);
+	t->time.tm_mon = bcd2bin(ds1307->regs[8] & 0x1f) - 1;
+	t->time.tm_year = -1;
+	t->time.tm_yday = -1;
+	t->time.tm_isdst = -1;
+
+	dev_dbg(dev, "%s, sec=%d min=%d hour=%d wday=%d mday=%d mon=%d "
+		"enabled=%d polarity=%d irq=%d match=%d\n", __func__,
+		t->time.tm_sec, t->time.tm_min, t->time.tm_hour,
+		t->time.tm_wday, t->time.tm_mday, t->time.tm_mon, t->enabled,
+		!!(ds1307->regs[6] & MCP7941X_BIT_ALMX_POL),
+		!!(ds1307->regs[6] & MCP7941X_BIT_ALMX_IF),
+		(ds1307->regs[6] & MCP7941X_MSK_ALMX_MATCH) >> 4);
+
+	return 0;
+}
+
+static int mcp7941x_set_alarm(struct device *dev, struct rtc_wkalrm *t)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct ds1307 *ds1307 = i2c_get_clientdata(client);
+	unsigned char *regs = ds1307->regs;
+	int ret;
+
+	if (!test_bit(HAS_ALARM, &ds1307->flags))
+		return -EINVAL;
+
+	dev_dbg(dev, "%s, sec=%d min=%d hour=%d wday=%d mday=%d mon=%d "
+		"enabled=%d pending=%d\n", __func__,
+		t->time.tm_sec, t->time.tm_min, t->time.tm_hour,
+		t->time.tm_wday, t->time.tm_mday, t->time.tm_mon,
+		t->enabled, t->pending);
+
+	/* Read control and alarm 0 registers. */
+	ret = ds1307->read_block_data(client, MCP7941X_REG_CONTROL, 10, regs);
+	if (ret < 0)
+		return ret;
+
+	/* Set alarm 0, using 24-hour and day-of-month modes. */
+	regs[3] = bin2bcd(t->time.tm_sec);
+	regs[4] = bin2bcd(t->time.tm_min);
+	regs[5] = bin2bcd(t->time.tm_hour);
+	regs[6] = bin2bcd(t->time.tm_wday) + 1;
+	regs[7] = bin2bcd(t->time.tm_mday);
+	regs[8] = bin2bcd(t->time.tm_mon) + 1;
+
+	/* Clear the alarm 0 interrupt flag. */
+	regs[6] &= ~MCP7941X_BIT_ALMX_IF;
+	/* Set alarm match: second, minute, hour, day, date, month. */
+	regs[6] |= MCP7941X_MSK_ALMX_MATCH;
+
+	if (t->enabled)
+		regs[0] |= MCP7941X_BIT_ALM0_EN;
+	else
+		regs[0] &= ~MCP7941X_BIT_ALM0_EN;
+
+	ret = ds1307->write_block_data(client, MCP7941X_REG_CONTROL, 10, regs);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int mcp7941x_alarm_irq_enable(struct device *dev, unsigned int enabled)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct ds1307 *ds1307 = i2c_get_clientdata(client);
+	int reg;
+
+	if (!test_bit(HAS_ALARM, &ds1307->flags))
+		return -EINVAL;
+
+	reg = i2c_smbus_read_byte_data(client, MCP7941X_REG_CONTROL);
+	if (reg < 0)
+		return reg;
+
+	if (enabled)
+		reg |= MCP7941X_BIT_ALM0_EN;
+	else
+		reg &= ~MCP7941X_BIT_ALM0_EN;
+
+	return i2c_smbus_write_byte_data(client, MCP7941X_REG_CONTROL, reg);
+}
+
+static const struct rtc_class_ops mcp7941x_rtc_ops = {
+	.read_time	= ds1307_get_time,
+	.set_time	= ds1307_set_time,
+	.read_alarm	= mcp7941x_read_alarm,
+	.set_alarm	= mcp7941x_set_alarm,
+	.alarm_irq_enable = mcp7941x_alarm_irq_enable,
+};
+
+/*----------------------------------------------------------------------*/
+
 static ssize_t
 ds1307_nvram_read(struct file *filp, struct kobject *kobj,
 		struct bin_attribute *attr,
@@ -678,6 +851,7 @@ static int ds1307_probe(struct i2c_client *client,
 		[ds_1339] = DS1339_BIT_BBSQI,
 		[ds_3231] = DS3231_BIT_BBSQW,
 	};
+	const struct rtc_class_ops *rtc_ops = &ds13xx_rtc_ops;
 
 	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA)
 	    && !i2c_check_functionality(adapter, I2C_FUNC_SMBUS_I2C_BLOCK))
@@ -816,6 +990,13 @@ static int ds1307_probe(struct i2c_client *client,
 	case ds_1388:
 		ds1307->offset = 1; /* Seconds starts at 1 */
 		break;
+	case mcp7941x:
+		rtc_ops = &mcp7941x_rtc_ops;
+		if (ds1307->client->irq > 0 && chip->alarm) {
+			INIT_WORK(&ds1307->work, mcp7941x_work);
+			want_irq = true;
+		}
+		break;
 	default:
 		break;
 	}
@@ -927,8 +1108,9 @@ read_rtc:
 				bin2bcd(tmp));
 	}
 
+	device_set_wakeup_capable(&client->dev, want_irq);
 	ds1307->rtc = devm_rtc_device_register(&client->dev, client->name,
-				&ds13xx_rtc_ops, THIS_MODULE);
+				rtc_ops, THIS_MODULE);
 	if (IS_ERR(ds1307->rtc)) {
 		err = PTR_ERR(ds1307->rtc);
 		dev_err(&client->dev,
@@ -945,7 +1127,6 @@ read_rtc:
 			goto exit;
 		}
 
-		device_set_wakeup_capable(&client->dev, 1);
 		set_bit(HAS_ALARM, &ds1307->flags);
 		dev_dbg(&client->dev, "got IRQ %d\n", client->irq);
 	}
diff --git a/drivers/rtc/rtc-ds1347.c b/drivers/rtc/rtc-ds1347.c
new file mode 100644
index 000000000000..fffa51f50833
--- /dev/null
+++ b/drivers/rtc/rtc-ds1347.c
@@ -0,0 +1,167 @@
+/* rtc-ds1347.c
+ *
+ * Driver for Dallas Semiconductor DS1347 Low Current, SPI Compatible
+ * Real Time Clock
+ *
+ * Author : Raghavendra Chandra Ganiga <ravi23ganiga@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/rtc.h>
+#include <linux/spi/spi.h>
+#include <linux/bcd.h>
+
+/* Registers in ds1347 rtc */
+
+#define DS1347_SECONDS_REG	0x01
+#define DS1347_MINUTES_REG	0x03
+#define DS1347_HOURS_REG	0x05
+#define DS1347_DATE_REG		0x07
+#define DS1347_MONTH_REG	0x09
+#define DS1347_DAY_REG		0x0B
+#define DS1347_YEAR_REG		0x0D
+#define DS1347_CONTROL_REG	0x0F
+#define DS1347_STATUS_REG	0x17
+#define DS1347_CLOCK_BURST	0x3F
+
+static int ds1347_read_reg(struct device *dev, unsigned char address,
+				unsigned char *data)
+{
+	struct spi_device *spi = to_spi_device(dev);
+
+	*data = address | 0x80;
+
+	return spi_write_then_read(spi, data, 1, data, 1);
+}
+
+static int ds1347_write_reg(struct device *dev, unsigned char address,
+				unsigned char data)
+{
+	struct spi_device *spi = to_spi_device(dev);
+	unsigned char buf[2];
+
+	buf[0] = address & 0x7F;
+	buf[1] = data;
+
+	return spi_write_then_read(spi, buf, 2, NULL, 0);
+}
+
+static int ds1347_read_time(struct device *dev, struct rtc_time *dt)
+{
+	struct spi_device *spi = to_spi_device(dev);
+	int err;
+	unsigned char buf[8];
+
+	buf[0] = DS1347_CLOCK_BURST | 0x80;
+
+	err = spi_write_then_read(spi, buf, 1, buf, 8);
+	if (err)
+		return err;
+
+	dt->tm_sec = bcd2bin(buf[0]);
+	dt->tm_min = bcd2bin(buf[1]);
+	dt->tm_hour = bcd2bin(buf[2] & 0x3F);
+	dt->tm_mday = bcd2bin(buf[3]);
+	dt->tm_mon = bcd2bin(buf[4]) - 1;
+	dt->tm_wday = bcd2bin(buf[5]) - 1;
+	dt->tm_year = bcd2bin(buf[6]) + 100;
+
+	return rtc_valid_tm(dt);
+}
+
+static int ds1347_set_time(struct device *dev, struct rtc_time *dt)
+{
+	struct spi_device *spi = to_spi_device(dev);
+	unsigned char buf[9];
+
+	buf[0] = DS1347_CLOCK_BURST & 0x7F;
+	buf[1] = bin2bcd(dt->tm_sec);
+	buf[2] = bin2bcd(dt->tm_min);
+	buf[3] = (bin2bcd(dt->tm_hour) & 0x3F);
+	buf[4] = bin2bcd(dt->tm_mday);
+	buf[5] = bin2bcd(dt->tm_mon + 1);
+	buf[6] = bin2bcd(dt->tm_wday + 1);
+
+	/* year in linux is from 1900 i.e in range of 100
+	in rtc it is from 00 to 99 */
+	dt->tm_year = dt->tm_year % 100;
+
+	buf[7] = bin2bcd(dt->tm_year);
+	buf[8] = bin2bcd(0x00);
+
+	/* write the rtc settings */
+	return spi_write_then_read(spi, buf, 9, NULL, 0);
+}
+
+static const struct rtc_class_ops ds1347_rtc_ops = {
+	.read_time = ds1347_read_time,
+	.set_time = ds1347_set_time,
+};
+
+static int ds1347_probe(struct spi_device *spi)
+{
+	struct rtc_device *rtc;
+	unsigned char data;
+	int res;
+
+	/* spi setup with ds1347 in mode 3 and bits per word as 8 */
+	spi->mode = SPI_MODE_3;
+	spi->bits_per_word = 8;
+	spi_setup(spi);
+
+	/* RTC Settings */
+	res = ds1347_read_reg(&spi->dev, DS1347_SECONDS_REG, &data);
+	if (res)
+		return res;
+
+	/* Disable the write protect of rtc */
+	ds1347_read_reg(&spi->dev, DS1347_CONTROL_REG, &data);
+	data = data & ~(1<<7);
+	ds1347_write_reg(&spi->dev, DS1347_CONTROL_REG, data);
+
+	/* Enable the oscillator , disable the oscillator stop flag,
+	 and glitch filter to reduce current consumption */
+	ds1347_read_reg(&spi->dev, DS1347_STATUS_REG, &data);
+	data = data & 0x1B;
+	ds1347_write_reg(&spi->dev, DS1347_STATUS_REG, data);
+
+	/* display the settings */
+	ds1347_read_reg(&spi->dev, DS1347_CONTROL_REG, &data);
+	dev_info(&spi->dev, "DS1347 RTC CTRL Reg = 0x%02x\n", data);
+
+	ds1347_read_reg(&spi->dev, DS1347_STATUS_REG, &data);
+	dev_info(&spi->dev, "DS1347 RTC Status Reg = 0x%02x\n", data);
+
+	rtc = devm_rtc_device_register(&spi->dev, "ds1347",
+				&ds1347_rtc_ops, THIS_MODULE);
+
+	if (IS_ERR(rtc))
+		return PTR_ERR(rtc);
+
+	spi_set_drvdata(spi, rtc);
+
+	return 0;
+}
+
+static struct spi_driver ds1347_driver = {
+	.driver = {
+		.name = "ds1347",
+		.owner = THIS_MODULE,
+	},
+	.probe = ds1347_probe,
+};
+
+module_spi_driver(ds1347_driver);
+
+MODULE_DESCRIPTION("DS1347 SPI RTC DRIVER");
+MODULE_AUTHOR("Raghavendra C Ganiga <ravi23ganiga@gmail.com>");
+MODULE_LICENSE("GPL v2");
+
diff --git a/drivers/rtc/rtc-ds1390.c b/drivers/rtc/rtc-ds1390.c
index be9d8c0a7e3a..e67bfcb3a1aa 100644
--- a/drivers/rtc/rtc-ds1390.c
+++ b/drivers/rtc/rtc-ds1390.c
@@ -132,10 +132,9 @@ static int ds1390_probe(struct spi_device *spi)
 	spi_setup(spi);
 
 	chip = devm_kzalloc(&spi->dev, sizeof(*chip), GFP_KERNEL);
-	if (!chip) {
-		dev_err(&spi->dev, "unable to allocate device memory\n");
+	if (!chip)
 		return -ENOMEM;
-	}
+
 	spi_set_drvdata(spi, chip);
 
 	res = ds1390_get_reg(&spi->dev, DS1390_REG_SECONDS, &tmp);
diff --git a/drivers/rtc/rtc-ds3232.c b/drivers/rtc/rtc-ds3232.c
index b83bb5a527f8..9b9fe5f9fe41 100644
--- a/drivers/rtc/rtc-ds3232.c
+++ b/drivers/rtc/rtc-ds3232.c
@@ -57,6 +57,7 @@ struct ds3232 {
 	 * in the remove function.
 	 */
 	struct mutex mutex;
+	bool suspended;
 	int exiting;
 };
 
@@ -345,7 +346,15 @@ static irqreturn_t ds3232_irq(int irq, void *dev_id)
 	struct ds3232 *ds3232 = i2c_get_clientdata(client);
 
 	disable_irq_nosync(irq);
-	schedule_work(&ds3232->work);
+
+	/*
+	 * If rtc as a wakeup source, can't schedule the work
+	 * at system resume flow, because at this time the i2c bus
+	 * has not been resumed.
+	 */
+	if (!ds3232->suspended)
+		schedule_work(&ds3232->work);
+
 	return IRQ_HANDLED;
 }
 
@@ -363,22 +372,26 @@ static void ds3232_work(struct work_struct *work)
 
 	if (stat & DS3232_REG_SR_A1F) {
 		control = i2c_smbus_read_byte_data(client, DS3232_REG_CR);
-		if (control < 0)
-			goto out;
-		/* disable alarm1 interrupt */
-		control &= ~(DS3232_REG_CR_A1IE);
-		i2c_smbus_write_byte_data(client, DS3232_REG_CR, control);
-
-		/* clear the alarm pend flag */
-		stat &= ~DS3232_REG_SR_A1F;
-		i2c_smbus_write_byte_data(client, DS3232_REG_SR, stat);
-
-		rtc_update_irq(ds3232->rtc, 1, RTC_AF | RTC_IRQF);
+		if (control < 0) {
+			pr_warn("Read DS3232 Control Register error."
+				"Disable IRQ%d.\n", client->irq);
+		} else {
+			/* disable alarm1 interrupt */
+			control &= ~(DS3232_REG_CR_A1IE);
+			i2c_smbus_write_byte_data(client, DS3232_REG_CR,
+						control);
+
+			/* clear the alarm pend flag */
+			stat &= ~DS3232_REG_SR_A1F;
+			i2c_smbus_write_byte_data(client, DS3232_REG_SR, stat);
+
+			rtc_update_irq(ds3232->rtc, 1, RTC_AF | RTC_IRQF);
+
+			if (!ds3232->exiting)
+				enable_irq(client->irq);
+		}
 	}
 
-out:
-	if (!ds3232->exiting)
-		enable_irq(client->irq);
 unlock:
 	mutex_unlock(&ds3232->mutex);
 }
@@ -411,23 +424,18 @@ static int ds3232_probe(struct i2c_client *client,
 	if (ret)
 		return ret;
 
-	ds3232->rtc = devm_rtc_device_register(&client->dev, client->name,
-					  &ds3232_rtc_ops, THIS_MODULE);
-	if (IS_ERR(ds3232->rtc)) {
-		dev_err(&client->dev, "unable to register the class device\n");
-		return PTR_ERR(ds3232->rtc);
-	}
-
-	if (client->irq >= 0) {
-		ret = devm_request_irq(&client->dev, client->irq, ds3232_irq, 0,
-				 "ds3232", client);
+	if (client->irq > 0) {
+		ret = devm_request_irq(&client->dev, client->irq, ds3232_irq,
+				       IRQF_SHARED, "ds3232", client);
 		if (ret) {
 			dev_err(&client->dev, "unable to request IRQ\n");
 			return ret;
 		}
+		device_init_wakeup(&client->dev, 1);
 	}
-
-	return 0;
+	ds3232->rtc = devm_rtc_device_register(&client->dev, client->name,
+					  &ds3232_rtc_ops, THIS_MODULE);
+	return PTR_ERR_OR_ZERO(ds3232->rtc);
 }
 
 static int ds3232_remove(struct i2c_client *client)
@@ -446,6 +454,42 @@ static int ds3232_remove(struct i2c_client *client)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int ds3232_suspend(struct device *dev)
+{
+	struct ds3232 *ds3232 = dev_get_drvdata(dev);
+	struct i2c_client *client = to_i2c_client(dev);
+
+	if (device_can_wakeup(dev)) {
+		ds3232->suspended = true;
+		irq_set_irq_wake(client->irq, 1);
+	}
+
+	return 0;
+}
+
+static int ds3232_resume(struct device *dev)
+{
+	struct ds3232 *ds3232 = dev_get_drvdata(dev);
+	struct i2c_client *client = to_i2c_client(dev);
+
+	if (ds3232->suspended) {
+		ds3232->suspended = false;
+
+		/* Clear the hardware alarm pend flag */
+		schedule_work(&ds3232->work);
+
+		irq_set_irq_wake(client->irq, 0);
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops ds3232_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(ds3232_suspend, ds3232_resume)
+};
+
 static const struct i2c_device_id ds3232_id[] = {
 	{ "ds3232", 0 },
 	{ }
@@ -456,6 +500,7 @@ static struct i2c_driver ds3232_driver = {
 	.driver = {
 		.name = "rtc-ds3232",
 		.owner = THIS_MODULE,
+		.pm	= &ds3232_pm_ops,
 	},
 	.probe = ds3232_probe,
 	.remove = ds3232_remove,
diff --git a/drivers/rtc/rtc-imxdi.c b/drivers/rtc/rtc-imxdi.c
index abd7f9091f34..cd741c77e085 100644
--- a/drivers/rtc/rtc-imxdi.c
+++ b/drivers/rtc/rtc-imxdi.c
@@ -401,7 +401,9 @@ static int __init dryice_rtc_probe(struct platform_device *pdev)
 	imxdi->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(imxdi->clk))
 		return PTR_ERR(imxdi->clk);
-	clk_prepare_enable(imxdi->clk);
+	rc = clk_prepare_enable(imxdi->clk);
+	if (rc)
+		return rc;
 
 	/*
 	 * Initialize dryice hardware
diff --git a/drivers/rtc/rtc-isl12057.c b/drivers/rtc/rtc-isl12057.c
index 835b425549bd..41bd76aaff76 100644
--- a/drivers/rtc/rtc-isl12057.c
+++ b/drivers/rtc/rtc-isl12057.c
@@ -26,7 +26,6 @@
 #include <linux/rtc.h>
 #include <linux/i2c.h>
 #include <linux/bcd.h>
-#include <linux/rtc.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/regmap.h>
diff --git a/drivers/rtc/rtc-jz4740.c b/drivers/rtc/rtc-jz4740.c
index 1b126d2513de..08f5160fb6d4 100644
--- a/drivers/rtc/rtc-jz4740.c
+++ b/drivers/rtc/rtc-jz4740.c
@@ -38,7 +38,6 @@
 #define JZ_RTC_CTRL_ENABLE	BIT(0)
 
 struct jz4740_rtc {
-	struct resource *mem;
 	void __iomem *base;
 
 	struct rtc_device *rtc;
@@ -216,6 +215,7 @@ static int jz4740_rtc_probe(struct platform_device *pdev)
 	int ret;
 	struct jz4740_rtc *rtc;
 	uint32_t scratchpad;
+	struct resource *mem;
 
 	rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL);
 	if (!rtc)
@@ -227,25 +227,10 @@ static int jz4740_rtc_probe(struct platform_device *pdev)
 		return -ENOENT;
 	}
 
-	rtc->mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!rtc->mem) {
-		dev_err(&pdev->dev, "Failed to get platform mmio memory\n");
-		return -ENOENT;
-	}
-
-	rtc->mem = devm_request_mem_region(&pdev->dev, rtc->mem->start,
-					resource_size(rtc->mem), pdev->name);
-	if (!rtc->mem) {
-		dev_err(&pdev->dev, "Failed to request mmio memory region\n");
-		return -EBUSY;
-	}
-
-	rtc->base = devm_ioremap_nocache(&pdev->dev, rtc->mem->start,
-					resource_size(rtc->mem));
-	if (!rtc->base) {
-		dev_err(&pdev->dev, "Failed to ioremap mmio memory\n");
-		return -EBUSY;
-	}
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	rtc->base = devm_ioremap_resource(&pdev->dev, mem);
+	if (IS_ERR(rtc->base))
+		return PTR_ERR(rtc->base);
 
 	spin_lock_init(&rtc->lock);
 
diff --git a/drivers/rtc/rtc-lpc32xx.c b/drivers/rtc/rtc-lpc32xx.c
index bfdbcb82d069..f130c08c98f8 100644
--- a/drivers/rtc/rtc-lpc32xx.c
+++ b/drivers/rtc/rtc-lpc32xx.c
@@ -211,10 +211,9 @@ static int lpc32xx_rtc_probe(struct platform_device *pdev)
 	}
 
 	rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL);
-	if (unlikely(!rtc)) {
-		dev_err(&pdev->dev, "Can't allocate memory\n");
+	if (unlikely(!rtc))
 		return -ENOMEM;
-	}
+
 	rtc->irq = rtcirq;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/rtc/rtc-mc13xxx.c b/drivers/rtc/rtc-mc13xxx.c
index 77ea9896b5ba..0765606a2d14 100644
--- a/drivers/rtc/rtc-mc13xxx.c
+++ b/drivers/rtc/rtc-mc13xxx.c
@@ -23,6 +23,8 @@
 #define MC13XXX_RTCDAY	22
 #define MC13XXX_RTCDAYA	23
 
+#define SEC_PER_DAY	(24 * 60 * 60)
+
 struct mc13xxx_rtc {
 	struct rtc_device *rtc;
 	struct mc13xxx *mc13xxx;
@@ -42,15 +44,15 @@ static int mc13xxx_rtc_irq_enable_unlocked(struct device *dev,
 	return func(priv->mc13xxx, irq);
 }
 
-static int mc13xxx_rtc_irq_enable(struct device *dev,
-		unsigned int enabled, int irq)
+static int mc13xxx_rtc_alarm_irq_enable(struct device *dev,
+					unsigned int enabled)
 {
 	struct mc13xxx_rtc *priv = dev_get_drvdata(dev);
 	int ret;
 
 	mc13xxx_lock(priv->mc13xxx);
 
-	ret = mc13xxx_rtc_irq_enable_unlocked(dev, enabled, irq);
+	ret = mc13xxx_rtc_irq_enable_unlocked(dev, enabled, MC13XXX_IRQ_TODA);
 
 	mc13xxx_unlock(priv->mc13xxx);
 
@@ -61,44 +63,27 @@ static int mc13xxx_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
 	struct mc13xxx_rtc *priv = dev_get_drvdata(dev);
 	unsigned int seconds, days1, days2;
-	unsigned long s1970;
-	int ret;
-
-	mc13xxx_lock(priv->mc13xxx);
-
-	if (!priv->valid) {
-		ret = -ENODATA;
-		goto out;
-	}
 
-	ret = mc13xxx_reg_read(priv->mc13xxx, MC13XXX_RTCDAY, &days1);
-	if (unlikely(ret))
-		goto out;
-
-	ret = mc13xxx_reg_read(priv->mc13xxx, MC13XXX_RTCTOD, &seconds);
-	if (unlikely(ret))
-		goto out;
-
-	ret = mc13xxx_reg_read(priv->mc13xxx, MC13XXX_RTCDAY, &days2);
-out:
-	mc13xxx_unlock(priv->mc13xxx);
+	if (!priv->valid)
+		return -ENODATA;
 
-	if (ret)
-		return ret;
+	do {
+		int ret;
 
-	if (days2 == days1 + 1) {
-		if (seconds >= 86400 / 2)
-			days2 = days1;
-		else
-			days1 = days2;
-	}
+		ret = mc13xxx_reg_read(priv->mc13xxx, MC13XXX_RTCDAY, &days1);
+		if (ret)
+			return ret;
 
-	if (days1 != days2)
-		return -EIO;
+		ret = mc13xxx_reg_read(priv->mc13xxx, MC13XXX_RTCTOD, &seconds);
+		if (ret)
+			return ret;
 
-	s1970 = days1 * 86400 + seconds;
+		ret = mc13xxx_reg_read(priv->mc13xxx, MC13XXX_RTCDAY, &days2);
+		if (ret)
+			return ret;
+	} while (days1 != days2);
 
-	rtc_time_to_tm(s1970, tm);
+	rtc_time_to_tm(days1 * SEC_PER_DAY + seconds, tm);
 
 	return rtc_valid_tm(tm);
 }
@@ -110,8 +95,8 @@ static int mc13xxx_rtc_set_mmss(struct device *dev, unsigned long secs)
 	unsigned int alarmseconds;
 	int ret;
 
-	seconds = secs % 86400;
-	days = secs / 86400;
+	seconds = secs % SEC_PER_DAY;
+	days = secs / SEC_PER_DAY;
 
 	mc13xxx_lock(priv->mc13xxx);
 
@@ -123,7 +108,7 @@ static int mc13xxx_rtc_set_mmss(struct device *dev, unsigned long secs)
 	if (unlikely(ret))
 		goto out;
 
-	if (alarmseconds < 86400) {
+	if (alarmseconds < SEC_PER_DAY) {
 		ret = mc13xxx_reg_write(priv->mc13xxx,
 				MC13XXX_RTCTODA, 0x1ffff);
 		if (unlikely(ret))
@@ -147,18 +132,21 @@ static int mc13xxx_rtc_set_mmss(struct device *dev, unsigned long secs)
 		goto out;
 
 	/* restore alarm */
-	if (alarmseconds < 86400) {
+	if (alarmseconds < SEC_PER_DAY) {
 		ret = mc13xxx_reg_write(priv->mc13xxx,
 				MC13XXX_RTCTODA, alarmseconds);
 		if (unlikely(ret))
 			goto out;
 	}
 
-	ret = mc13xxx_irq_ack(priv->mc13xxx, MC13XXX_IRQ_RTCRST);
-	if (unlikely(ret))
-		goto out;
+	if (!priv->valid) {
+		ret = mc13xxx_irq_ack(priv->mc13xxx, MC13XXX_IRQ_RTCRST);
+		if (unlikely(ret))
+			goto out;
+
+		ret = mc13xxx_irq_unmask(priv->mc13xxx, MC13XXX_IRQ_RTCRST);
+	}
 
-	ret = mc13xxx_irq_unmask(priv->mc13xxx, MC13XXX_IRQ_RTCRST);
 out:
 	priv->valid = !ret;
 
@@ -180,7 +168,7 @@ static int mc13xxx_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 	ret = mc13xxx_reg_read(priv->mc13xxx, MC13XXX_RTCTODA, &seconds);
 	if (unlikely(ret))
 		goto out;
-	if (seconds >= 86400) {
+	if (seconds >= SEC_PER_DAY) {
 		ret = -ENODATA;
 		goto out;
 	}
@@ -201,7 +189,7 @@ out:
 	alarm->enabled = enabled;
 	alarm->pending = pending;
 
-	s1970 = days * 86400 + seconds;
+	s1970 = days * SEC_PER_DAY + seconds;
 
 	rtc_time_to_tm(s1970, &alarm->time);
 	dev_dbg(dev, "%s: %lu\n", __func__, s1970);
@@ -239,8 +227,8 @@ static int mc13xxx_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 	if (unlikely(ret))
 		goto out;
 
-	seconds = s1970 % 86400;
-	days = s1970 / 86400;
+	seconds = s1970 % SEC_PER_DAY;
+	days = s1970 / SEC_PER_DAY;
 
 	ret = mc13xxx_reg_write(priv->mc13xxx, MC13XXX_RTCDAYA, days);
 	if (unlikely(ret))
@@ -259,8 +247,6 @@ static irqreturn_t mc13xxx_rtc_alarm_handler(int irq, void *dev)
 	struct mc13xxx_rtc *priv = dev;
 	struct mc13xxx *mc13xxx = priv->mc13xxx;
 
-	dev_dbg(&priv->rtc->dev, "Alarm\n");
-
 	rtc_update_irq(priv->rtc, 1, RTC_IRQF | RTC_AF);
 
 	mc13xxx_irq_ack(mc13xxx, irq);
@@ -273,8 +259,6 @@ static irqreturn_t mc13xxx_rtc_update_handler(int irq, void *dev)
 	struct mc13xxx_rtc *priv = dev;
 	struct mc13xxx *mc13xxx = priv->mc13xxx;
 
-	dev_dbg(&priv->rtc->dev, "1HZ\n");
-
 	rtc_update_irq(priv->rtc, 1, RTC_IRQF | RTC_UF);
 
 	mc13xxx_irq_ack(mc13xxx, irq);
@@ -282,12 +266,6 @@ static irqreturn_t mc13xxx_rtc_update_handler(int irq, void *dev)
 	return IRQ_HANDLED;
 }
 
-static int mc13xxx_rtc_alarm_irq_enable(struct device *dev,
-		unsigned int enabled)
-{
-	return mc13xxx_rtc_irq_enable(dev, enabled, MC13XXX_IRQ_TODA);
-}
-
 static const struct rtc_class_ops mc13xxx_rtc_ops = {
 	.read_time = mc13xxx_rtc_read_time,
 	.set_mmss = mc13xxx_rtc_set_mmss,
@@ -301,7 +279,6 @@ static irqreturn_t mc13xxx_rtc_reset_handler(int irq, void *dev)
 	struct mc13xxx_rtc *priv = dev;
 	struct mc13xxx *mc13xxx = priv->mc13xxx;
 
-	dev_dbg(&priv->rtc->dev, "RTCRST\n");
 	priv->valid = 0;
 
 	mc13xxx_irq_mask(mc13xxx, irq);
@@ -314,7 +291,6 @@ static int __init mc13xxx_rtc_probe(struct platform_device *pdev)
 	int ret;
 	struct mc13xxx_rtc *priv;
 	struct mc13xxx *mc13xxx;
-	int rtcrst_pending;
 
 	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -322,60 +298,47 @@ static int __init mc13xxx_rtc_probe(struct platform_device *pdev)
 
 	mc13xxx = dev_get_drvdata(pdev->dev.parent);
 	priv->mc13xxx = mc13xxx;
+	priv->valid = 1;
 
 	platform_set_drvdata(pdev, priv);
 
 	mc13xxx_lock(mc13xxx);
 
+	mc13xxx_irq_ack(mc13xxx, MC13XXX_IRQ_RTCRST);
+
 	ret = mc13xxx_irq_request(mc13xxx, MC13XXX_IRQ_RTCRST,
 			mc13xxx_rtc_reset_handler, DRIVER_NAME, priv);
 	if (ret)
-		goto err_reset_irq_request;
-
-	ret = mc13xxx_irq_status(mc13xxx, MC13XXX_IRQ_RTCRST,
-			NULL, &rtcrst_pending);
-	if (ret)
-		goto err_reset_irq_status;
-
-	priv->valid = !rtcrst_pending;
+		goto err_irq_request;
 
-	ret = mc13xxx_irq_request_nounmask(mc13xxx, MC13XXX_IRQ_1HZ,
+	ret = mc13xxx_irq_request(mc13xxx, MC13XXX_IRQ_1HZ,
 			mc13xxx_rtc_update_handler, DRIVER_NAME, priv);
 	if (ret)
-		goto err_update_irq_request;
+		goto err_irq_request;
 
 	ret = mc13xxx_irq_request_nounmask(mc13xxx, MC13XXX_IRQ_TODA,
 			mc13xxx_rtc_alarm_handler, DRIVER_NAME, priv);
 	if (ret)
-		goto err_alarm_irq_request;
+		goto err_irq_request;
 
 	mc13xxx_unlock(mc13xxx);
 
 	priv->rtc = devm_rtc_device_register(&pdev->dev, pdev->name,
-					&mc13xxx_rtc_ops, THIS_MODULE);
-	if (IS_ERR(priv->rtc)) {
-		ret = PTR_ERR(priv->rtc);
+					     &mc13xxx_rtc_ops, THIS_MODULE);
 
-		mc13xxx_lock(mc13xxx);
-
-		mc13xxx_irq_free(mc13xxx, MC13XXX_IRQ_TODA, priv);
-err_alarm_irq_request:
-
-		mc13xxx_irq_free(mc13xxx, MC13XXX_IRQ_1HZ, priv);
-err_update_irq_request:
-
-err_reset_irq_status:
+	return 0;
 
-		mc13xxx_irq_free(mc13xxx, MC13XXX_IRQ_RTCRST, priv);
-err_reset_irq_request:
+err_irq_request:
+	mc13xxx_irq_free(mc13xxx, MC13XXX_IRQ_TODA, priv);
+	mc13xxx_irq_free(mc13xxx, MC13XXX_IRQ_1HZ, priv);
+	mc13xxx_irq_free(mc13xxx, MC13XXX_IRQ_RTCRST, priv);
 
-		mc13xxx_unlock(mc13xxx);
-	}
+	mc13xxx_unlock(mc13xxx);
 
 	return ret;
 }
 
-static int __exit mc13xxx_rtc_remove(struct platform_device *pdev)
+static int mc13xxx_rtc_remove(struct platform_device *pdev)
 {
 	struct mc13xxx_rtc *priv = platform_get_drvdata(pdev);
 
@@ -404,7 +367,7 @@ MODULE_DEVICE_TABLE(platform, mc13xxx_rtc_idtable);
 
 static struct platform_driver mc13xxx_rtc_driver = {
 	.id_table = mc13xxx_rtc_idtable,
-	.remove = __exit_p(mc13xxx_rtc_remove),
+	.remove = mc13xxx_rtc_remove,
 	.driver = {
 		.name = DRIVER_NAME,
 		.owner = THIS_MODULE,
diff --git a/drivers/rtc/rtc-moxart.c b/drivers/rtc/rtc-moxart.c
index c29dee0946e6..c31846238871 100644
--- a/drivers/rtc/rtc-moxart.c
+++ b/drivers/rtc/rtc-moxart.c
@@ -247,10 +247,8 @@ static int moxart_rtc_probe(struct platform_device *pdev)
 	int ret = 0;
 
 	moxart_rtc = devm_kzalloc(&pdev->dev, sizeof(*moxart_rtc), GFP_KERNEL);
-	if (!moxart_rtc) {
-		dev_err(&pdev->dev, "devm_kzalloc failed\n");
+	if (!moxart_rtc)
 		return -ENOMEM;
-	}
 
 	moxart_rtc->gpio_data = of_get_named_gpio(pdev->dev.of_node,
 						  "gpio-rtc-data", 0);
diff --git a/drivers/rtc/rtc-nuc900.c b/drivers/rtc/rtc-nuc900.c
index 248653c74b80..a53da0958e95 100644
--- a/drivers/rtc/rtc-nuc900.c
+++ b/drivers/rtc/rtc-nuc900.c
@@ -229,10 +229,9 @@ static int __init nuc900_rtc_probe(struct platform_device *pdev)
 
 	nuc900_rtc = devm_kzalloc(&pdev->dev, sizeof(struct nuc900_rtc),
 				GFP_KERNEL);
-	if (!nuc900_rtc) {
-		dev_err(&pdev->dev, "kzalloc nuc900_rtc failed\n");
+	if (!nuc900_rtc)
 		return -ENOMEM;
-	}
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	nuc900_rtc->rtc_reg = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(nuc900_rtc->rtc_reg))
diff --git a/drivers/rtc/rtc-palmas.c b/drivers/rtc/rtc-palmas.c
index fffb7d3449d7..c360d62fb3f6 100644
--- a/drivers/rtc/rtc-palmas.c
+++ b/drivers/rtc/rtc-palmas.c
@@ -348,9 +348,8 @@ static int palmas_rtc_resume(struct device *dev)
 }
 #endif
 
-static const struct dev_pm_ops palmas_rtc_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(palmas_rtc_suspend, palmas_rtc_resume)
-};
+static SIMPLE_DEV_PM_OPS(palmas_rtc_pm_ops, palmas_rtc_suspend,
+			 palmas_rtc_resume);
 
 #ifdef CONFIG_OF
 static struct of_device_id of_palmas_rtc_match[] = {
diff --git a/drivers/rtc/rtc-pm8xxx.c b/drivers/rtc/rtc-pm8xxx.c
index 03f8f75d5af2..197699f358c7 100644
--- a/drivers/rtc/rtc-pm8xxx.c
+++ b/drivers/rtc/rtc-pm8xxx.c
@@ -9,18 +9,16 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  */
-
+#include <linux/of.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/rtc.h>
+#include <linux/platform_device.h>
 #include <linux/pm.h>
+#include <linux/regmap.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 
-#include <linux/mfd/pm8xxx/core.h>
-#include <linux/mfd/pm8xxx/rtc.h>
-
-
 /* RTC Register offsets from RTC CTRL REG */
 #define PM8XXX_ALARM_CTRL_OFFSET	0x01
 #define PM8XXX_RTC_WRITE_OFFSET		0x02
@@ -37,6 +35,8 @@
 /**
  * struct pm8xxx_rtc -  rtc driver internal structure
  * @rtc:		rtc device for this driver.
+ * @regmap:		regmap used to access RTC registers
+ * @allow_set_time:	indicates whether writing to the RTC is allowed
  * @rtc_alarm_irq:	rtc alarm irq number.
  * @rtc_base:		address of rtc control register.
  * @rtc_read_base:	base address of read registers.
@@ -48,55 +48,19 @@
  */
 struct pm8xxx_rtc {
 	struct rtc_device *rtc;
+	struct regmap *regmap;
+	bool allow_set_time;
 	int rtc_alarm_irq;
 	int rtc_base;
 	int rtc_read_base;
 	int rtc_write_base;
 	int alarm_rw_base;
-	u8  ctrl_reg;
+	u8 ctrl_reg;
 	struct device *rtc_dev;
 	spinlock_t ctrl_reg_lock;
 };
 
 /*
- * The RTC registers need to be read/written one byte at a time. This is a
- * hardware limitation.
- */
-static int pm8xxx_read_wrapper(struct pm8xxx_rtc *rtc_dd, u8 *rtc_val,
-		int base, int count)
-{
-	int i, rc;
-	struct device *parent = rtc_dd->rtc_dev->parent;
-
-	for (i = 0; i < count; i++) {
-		rc = pm8xxx_readb(parent, base + i, &rtc_val[i]);
-		if (rc < 0) {
-			dev_err(rtc_dd->rtc_dev, "PMIC read failed\n");
-			return rc;
-		}
-	}
-
-	return 0;
-}
-
-static int pm8xxx_write_wrapper(struct pm8xxx_rtc *rtc_dd, u8 *rtc_val,
-		int base, int count)
-{
-	int i, rc;
-	struct device *parent = rtc_dd->rtc_dev->parent;
-
-	for (i = 0; i < count; i++) {
-		rc = pm8xxx_writeb(parent, base + i, rtc_val[i]);
-		if (rc < 0) {
-			dev_err(rtc_dd->rtc_dev, "PMIC write failed\n");
-			return rc;
-		}
-	}
-
-	return 0;
-}
-
-/*
  * Steps to write the RTC registers.
  * 1. Disable alarm if enabled.
  * 2. Write 0x00 to LSB.
@@ -107,9 +71,12 @@ static int pm8xxx_rtc_set_time(struct device *dev, struct rtc_time *tm)
 {
 	int rc, i;
 	unsigned long secs, irq_flags;
-	u8 value[NUM_8_BIT_RTC_REGS], reg = 0, alarm_enabled = 0, ctrl_reg;
+	u8 value[NUM_8_BIT_RTC_REGS], alarm_enabled = 0, ctrl_reg;
 	struct pm8xxx_rtc *rtc_dd = dev_get_drvdata(dev);
 
+	if (!rtc_dd->allow_set_time)
+		return -EACCES;
+
 	rtc_tm_to_time(tm, &secs);
 
 	for (i = 0; i < NUM_8_BIT_RTC_REGS; i++) {
@@ -125,47 +92,43 @@ static int pm8xxx_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	if (ctrl_reg & PM8xxx_RTC_ALARM_ENABLE) {
 		alarm_enabled = 1;
 		ctrl_reg &= ~PM8xxx_RTC_ALARM_ENABLE;
-		rc = pm8xxx_write_wrapper(rtc_dd, &ctrl_reg, rtc_dd->rtc_base,
-				1);
-		if (rc < 0) {
-			dev_err(dev, "Write to RTC control register "
-								"failed\n");
+		rc = regmap_write(rtc_dd->regmap, rtc_dd->rtc_base, ctrl_reg);
+		if (rc) {
+			dev_err(dev, "Write to RTC control register failed\n");
 			goto rtc_rw_fail;
 		}
 		rtc_dd->ctrl_reg = ctrl_reg;
-	} else
+	} else {
 		spin_unlock_irqrestore(&rtc_dd->ctrl_reg_lock, irq_flags);
+	}
 
 	/* Write 0 to Byte[0] */
-	reg = 0;
-	rc = pm8xxx_write_wrapper(rtc_dd, &reg, rtc_dd->rtc_write_base, 1);
-	if (rc < 0) {
+	rc = regmap_write(rtc_dd->regmap, rtc_dd->rtc_write_base, 0);
+	if (rc) {
 		dev_err(dev, "Write to RTC write data register failed\n");
 		goto rtc_rw_fail;
 	}
 
 	/* Write Byte[1], Byte[2], Byte[3] */
-	rc = pm8xxx_write_wrapper(rtc_dd, value + 1,
-					rtc_dd->rtc_write_base + 1, 3);
-	if (rc < 0) {
+	rc = regmap_bulk_write(rtc_dd->regmap, rtc_dd->rtc_write_base + 1,
+			       &value[1], sizeof(value) - 1);
+	if (rc) {
 		dev_err(dev, "Write to RTC write data register failed\n");
 		goto rtc_rw_fail;
 	}
 
 	/* Write Byte[0] */
-	rc = pm8xxx_write_wrapper(rtc_dd, value, rtc_dd->rtc_write_base, 1);
-	if (rc < 0) {
+	rc = regmap_write(rtc_dd->regmap, rtc_dd->rtc_write_base, value[0]);
+	if (rc) {
 		dev_err(dev, "Write to RTC write data register failed\n");
 		goto rtc_rw_fail;
 	}
 
 	if (alarm_enabled) {
 		ctrl_reg |= PM8xxx_RTC_ALARM_ENABLE;
-		rc = pm8xxx_write_wrapper(rtc_dd, &ctrl_reg, rtc_dd->rtc_base,
-									1);
-		if (rc < 0) {
-			dev_err(dev, "Write to RTC control register "
-								"failed\n");
+		rc = regmap_write(rtc_dd->regmap, rtc_dd->rtc_base, ctrl_reg);
+		if (rc) {
+			dev_err(dev, "Write to RTC control register failed\n");
 			goto rtc_rw_fail;
 		}
 		rtc_dd->ctrl_reg = ctrl_reg;
@@ -181,13 +144,14 @@ rtc_rw_fail:
 static int pm8xxx_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
 	int rc;
-	u8 value[NUM_8_BIT_RTC_REGS], reg;
+	u8 value[NUM_8_BIT_RTC_REGS];
 	unsigned long secs;
+	unsigned int reg;
 	struct pm8xxx_rtc *rtc_dd = dev_get_drvdata(dev);
 
-	rc = pm8xxx_read_wrapper(rtc_dd, value, rtc_dd->rtc_read_base,
-							NUM_8_BIT_RTC_REGS);
-	if (rc < 0) {
+	rc = regmap_bulk_read(rtc_dd->regmap, rtc_dd->rtc_read_base,
+			      value, sizeof(value));
+	if (rc) {
 		dev_err(dev, "RTC read data register failed\n");
 		return rc;
 	}
@@ -196,16 +160,16 @@ static int pm8xxx_rtc_read_time(struct device *dev, struct rtc_time *tm)
 	 * Read the LSB again and check if there has been a carry over.
 	 * If there is, redo the read operation.
 	 */
-	rc = pm8xxx_read_wrapper(rtc_dd, &reg, rtc_dd->rtc_read_base, 1);
+	rc = regmap_read(rtc_dd->regmap, rtc_dd->rtc_read_base, &reg);
 	if (rc < 0) {
 		dev_err(dev, "RTC read data register failed\n");
 		return rc;
 	}
 
 	if (unlikely(reg < value[0])) {
-		rc = pm8xxx_read_wrapper(rtc_dd, value,
-				rtc_dd->rtc_read_base, NUM_8_BIT_RTC_REGS);
-		if (rc < 0) {
+		rc = regmap_bulk_read(rtc_dd->regmap, rtc_dd->rtc_read_base,
+				      value, sizeof(value));
+		if (rc) {
 			dev_err(dev, "RTC read data register failed\n");
 			return rc;
 		}
@@ -222,8 +186,8 @@ static int pm8xxx_rtc_read_time(struct device *dev, struct rtc_time *tm)
 	}
 
 	dev_dbg(dev, "secs = %lu, h:m:s == %d:%d:%d, d/m/y = %d/%d/%d\n",
-				secs, tm->tm_hour, tm->tm_min, tm->tm_sec,
-				tm->tm_mday, tm->tm_mon, tm->tm_year);
+		secs, tm->tm_hour, tm->tm_min, tm->tm_sec,
+		tm->tm_mday, tm->tm_mon, tm->tm_year);
 
 	return 0;
 }
@@ -244,19 +208,22 @@ static int pm8xxx_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 
 	spin_lock_irqsave(&rtc_dd->ctrl_reg_lock, irq_flags);
 
-	rc = pm8xxx_write_wrapper(rtc_dd, value, rtc_dd->alarm_rw_base,
-							NUM_8_BIT_RTC_REGS);
-	if (rc < 0) {
+	rc = regmap_bulk_write(rtc_dd->regmap, rtc_dd->alarm_rw_base, value,
+			       sizeof(value));
+	if (rc) {
 		dev_err(dev, "Write to RTC ALARM register failed\n");
 		goto rtc_rw_fail;
 	}
 
 	ctrl_reg = rtc_dd->ctrl_reg;
-	ctrl_reg = alarm->enabled ? (ctrl_reg | PM8xxx_RTC_ALARM_ENABLE) :
-					(ctrl_reg & ~PM8xxx_RTC_ALARM_ENABLE);
 
-	rc = pm8xxx_write_wrapper(rtc_dd, &ctrl_reg, rtc_dd->rtc_base, 1);
-	if (rc < 0) {
+	if (alarm->enabled)
+		ctrl_reg |= PM8xxx_RTC_ALARM_ENABLE;
+	else
+		ctrl_reg &= ~PM8xxx_RTC_ALARM_ENABLE;
+
+	rc = regmap_write(rtc_dd->regmap, rtc_dd->rtc_base, ctrl_reg);
+	if (rc) {
 		dev_err(dev, "Write to RTC control register failed\n");
 		goto rtc_rw_fail;
 	}
@@ -264,9 +231,9 @@ static int pm8xxx_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 	rtc_dd->ctrl_reg = ctrl_reg;
 
 	dev_dbg(dev, "Alarm Set for h:r:s=%d:%d:%d, d/m/y=%d/%d/%d\n",
-				alarm->time.tm_hour, alarm->time.tm_min,
-				alarm->time.tm_sec, alarm->time.tm_mday,
-				alarm->time.tm_mon, alarm->time.tm_year);
+		alarm->time.tm_hour, alarm->time.tm_min,
+		alarm->time.tm_sec, alarm->time.tm_mday,
+		alarm->time.tm_mon, alarm->time.tm_year);
 rtc_rw_fail:
 	spin_unlock_irqrestore(&rtc_dd->ctrl_reg_lock, irq_flags);
 	return rc;
@@ -279,9 +246,9 @@ static int pm8xxx_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 	unsigned long secs;
 	struct pm8xxx_rtc *rtc_dd = dev_get_drvdata(dev);
 
-	rc = pm8xxx_read_wrapper(rtc_dd, value, rtc_dd->alarm_rw_base,
-			NUM_8_BIT_RTC_REGS);
-	if (rc < 0) {
+	rc = regmap_bulk_read(rtc_dd->regmap, rtc_dd->alarm_rw_base, value,
+			      sizeof(value));
+	if (rc) {
 		dev_err(dev, "RTC alarm time read failed\n");
 		return rc;
 	}
@@ -297,9 +264,9 @@ static int pm8xxx_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 	}
 
 	dev_dbg(dev, "Alarm set for - h:r:s=%d:%d:%d, d/m/y=%d/%d/%d\n",
-				alarm->time.tm_hour, alarm->time.tm_min,
-				alarm->time.tm_sec, alarm->time.tm_mday,
-				alarm->time.tm_mon, alarm->time.tm_year);
+		alarm->time.tm_hour, alarm->time.tm_min,
+		alarm->time.tm_sec, alarm->time.tm_mday,
+		alarm->time.tm_mon, alarm->time.tm_year);
 
 	return 0;
 }
@@ -312,12 +279,16 @@ static int pm8xxx_rtc_alarm_irq_enable(struct device *dev, unsigned int enable)
 	u8 ctrl_reg;
 
 	spin_lock_irqsave(&rtc_dd->ctrl_reg_lock, irq_flags);
+
 	ctrl_reg = rtc_dd->ctrl_reg;
-	ctrl_reg = (enable) ? (ctrl_reg | PM8xxx_RTC_ALARM_ENABLE) :
-				(ctrl_reg & ~PM8xxx_RTC_ALARM_ENABLE);
 
-	rc = pm8xxx_write_wrapper(rtc_dd, &ctrl_reg, rtc_dd->rtc_base, 1);
-	if (rc < 0) {
+	if (enable)
+		ctrl_reg |= PM8xxx_RTC_ALARM_ENABLE;
+	else
+		ctrl_reg &= ~PM8xxx_RTC_ALARM_ENABLE;
+
+	rc = regmap_write(rtc_dd->regmap, rtc_dd->rtc_base, ctrl_reg);
+	if (rc) {
 		dev_err(dev, "Write to RTC control register failed\n");
 		goto rtc_rw_fail;
 	}
@@ -329,8 +300,9 @@ rtc_rw_fail:
 	return rc;
 }
 
-static struct rtc_class_ops pm8xxx_rtc_ops = {
+static const struct rtc_class_ops pm8xxx_rtc_ops = {
 	.read_time	= pm8xxx_rtc_read_time,
+	.set_time	= pm8xxx_rtc_set_time,
 	.set_alarm	= pm8xxx_rtc_set_alarm,
 	.read_alarm	= pm8xxx_rtc_read_alarm,
 	.alarm_irq_enable = pm8xxx_rtc_alarm_irq_enable,
@@ -339,7 +311,7 @@ static struct rtc_class_ops pm8xxx_rtc_ops = {
 static irqreturn_t pm8xxx_alarm_trigger(int irq, void *dev_id)
 {
 	struct pm8xxx_rtc *rtc_dd = dev_id;
-	u8 ctrl_reg;
+	unsigned int ctrl_reg;
 	int rc;
 	unsigned long irq_flags;
 
@@ -351,11 +323,11 @@ static irqreturn_t pm8xxx_alarm_trigger(int irq, void *dev_id)
 	ctrl_reg = rtc_dd->ctrl_reg;
 	ctrl_reg &= ~PM8xxx_RTC_ALARM_ENABLE;
 
-	rc = pm8xxx_write_wrapper(rtc_dd, &ctrl_reg, rtc_dd->rtc_base, 1);
-	if (rc < 0) {
+	rc = regmap_write(rtc_dd->regmap, rtc_dd->rtc_base, ctrl_reg);
+	if (rc) {
 		spin_unlock_irqrestore(&rtc_dd->ctrl_reg_lock, irq_flags);
-		dev_err(rtc_dd->rtc_dev, "Write to RTC control register "
-								"failed\n");
+		dev_err(rtc_dd->rtc_dev,
+			"Write to RTC control register failed\n");
 		goto rtc_alarm_handled;
 	}
 
@@ -363,61 +335,71 @@ static irqreturn_t pm8xxx_alarm_trigger(int irq, void *dev_id)
 	spin_unlock_irqrestore(&rtc_dd->ctrl_reg_lock, irq_flags);
 
 	/* Clear RTC alarm register */
-	rc = pm8xxx_read_wrapper(rtc_dd, &ctrl_reg, rtc_dd->rtc_base +
-						PM8XXX_ALARM_CTRL_OFFSET, 1);
-	if (rc < 0) {
-		dev_err(rtc_dd->rtc_dev, "RTC Alarm control register read "
-								"failed\n");
+	rc = regmap_read(rtc_dd->regmap,
+			 rtc_dd->rtc_base + PM8XXX_ALARM_CTRL_OFFSET,
+			 &ctrl_reg);
+	if (rc) {
+		dev_err(rtc_dd->rtc_dev,
+			"RTC Alarm control register read failed\n");
 		goto rtc_alarm_handled;
 	}
 
 	ctrl_reg &= ~PM8xxx_RTC_ALARM_CLEAR;
-	rc = pm8xxx_write_wrapper(rtc_dd, &ctrl_reg, rtc_dd->rtc_base +
-						PM8XXX_ALARM_CTRL_OFFSET, 1);
-	if (rc < 0)
-		dev_err(rtc_dd->rtc_dev, "Write to RTC Alarm control register"
-								" failed\n");
+	rc = regmap_write(rtc_dd->regmap,
+			  rtc_dd->rtc_base + PM8XXX_ALARM_CTRL_OFFSET,
+			  ctrl_reg);
+	if (rc)
+		dev_err(rtc_dd->rtc_dev,
+			"Write to RTC Alarm control register failed\n");
 
 rtc_alarm_handled:
 	return IRQ_HANDLED;
 }
 
+/*
+ * Hardcoded RTC bases until IORESOURCE_REG mapping is figured out
+ */
+static const struct of_device_id pm8xxx_id_table[] = {
+	{ .compatible = "qcom,pm8921-rtc", .data = (void *) 0x11D },
+	{ .compatible = "qcom,pm8058-rtc", .data = (void *) 0x1E8 },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, pm8xxx_id_table);
+
 static int pm8xxx_rtc_probe(struct platform_device *pdev)
 {
 	int rc;
-	u8 ctrl_reg;
-	bool rtc_write_enable = false;
+	unsigned int ctrl_reg;
 	struct pm8xxx_rtc *rtc_dd;
-	struct resource *rtc_resource;
-	const struct pm8xxx_rtc_platform_data *pdata =
-						dev_get_platdata(&pdev->dev);
+	const struct of_device_id *match;
 
-	if (pdata != NULL)
-		rtc_write_enable = pdata->rtc_write_enable;
+	match = of_match_node(pm8xxx_id_table, pdev->dev.of_node);
+	if (!match)
+		return -ENXIO;
 
 	rtc_dd = devm_kzalloc(&pdev->dev, sizeof(*rtc_dd), GFP_KERNEL);
-	if (rtc_dd == NULL) {
-		dev_err(&pdev->dev, "Unable to allocate memory!\n");
+	if (rtc_dd == NULL)
 		return -ENOMEM;
-	}
 
 	/* Initialise spinlock to protect RTC control register */
 	spin_lock_init(&rtc_dd->ctrl_reg_lock);
 
+	rtc_dd->regmap = dev_get_regmap(pdev->dev.parent, NULL);
+	if (!rtc_dd->regmap) {
+		dev_err(&pdev->dev, "Parent regmap unavailable.\n");
+		return -ENXIO;
+	}
+
 	rtc_dd->rtc_alarm_irq = platform_get_irq(pdev, 0);
 	if (rtc_dd->rtc_alarm_irq < 0) {
 		dev_err(&pdev->dev, "Alarm IRQ resource absent!\n");
 		return -ENXIO;
 	}
 
-	rtc_resource = platform_get_resource_byname(pdev, IORESOURCE_IO,
-							"pmic_rtc_base");
-	if (!(rtc_resource && rtc_resource->start)) {
-		dev_err(&pdev->dev, "RTC IO resource absent!\n");
-		return -ENXIO;
-	}
+	rtc_dd->allow_set_time = of_property_read_bool(pdev->dev.of_node,
+						      "allow-set-time");
 
-	rtc_dd->rtc_base = rtc_resource->start;
+	rtc_dd->rtc_base = (long) match->data;
 
 	/* Setup RTC register addresses */
 	rtc_dd->rtc_write_base = rtc_dd->rtc_base + PM8XXX_RTC_WRITE_OFFSET;
@@ -427,64 +409,52 @@ static int pm8xxx_rtc_probe(struct platform_device *pdev)
 	rtc_dd->rtc_dev = &pdev->dev;
 
 	/* Check if the RTC is on, else turn it on */
-	rc = pm8xxx_read_wrapper(rtc_dd, &ctrl_reg, rtc_dd->rtc_base, 1);
-	if (rc < 0) {
+	rc = regmap_read(rtc_dd->regmap, rtc_dd->rtc_base, &ctrl_reg);
+	if (rc) {
 		dev_err(&pdev->dev, "RTC control register read failed!\n");
 		return rc;
 	}
 
 	if (!(ctrl_reg & PM8xxx_RTC_ENABLE)) {
 		ctrl_reg |= PM8xxx_RTC_ENABLE;
-		rc = pm8xxx_write_wrapper(rtc_dd, &ctrl_reg, rtc_dd->rtc_base,
-									1);
-		if (rc < 0) {
-			dev_err(&pdev->dev, "Write to RTC control register "
-								"failed\n");
+		rc = regmap_write(rtc_dd->regmap, rtc_dd->rtc_base, ctrl_reg);
+		if (rc) {
+			dev_err(&pdev->dev,
+				"Write to RTC control register failed\n");
 			return rc;
 		}
 	}
 
 	rtc_dd->ctrl_reg = ctrl_reg;
-	if (rtc_write_enable == true)
-		pm8xxx_rtc_ops.set_time = pm8xxx_rtc_set_time;
 
 	platform_set_drvdata(pdev, rtc_dd);
 
+	device_init_wakeup(&pdev->dev, 1);
+
 	/* Register the RTC device */
 	rtc_dd->rtc = devm_rtc_device_register(&pdev->dev, "pm8xxx_rtc",
-				&pm8xxx_rtc_ops, THIS_MODULE);
+					       &pm8xxx_rtc_ops, THIS_MODULE);
 	if (IS_ERR(rtc_dd->rtc)) {
 		dev_err(&pdev->dev, "%s: RTC registration failed (%ld)\n",
-					__func__, PTR_ERR(rtc_dd->rtc));
+			__func__, PTR_ERR(rtc_dd->rtc));
 		return PTR_ERR(rtc_dd->rtc);
 	}
 
 	/* Request the alarm IRQ */
-	rc = request_any_context_irq(rtc_dd->rtc_alarm_irq,
-				 pm8xxx_alarm_trigger, IRQF_TRIGGER_RISING,
-				 "pm8xxx_rtc_alarm", rtc_dd);
+	rc = devm_request_any_context_irq(&pdev->dev, rtc_dd->rtc_alarm_irq,
+					  pm8xxx_alarm_trigger,
+					  IRQF_TRIGGER_RISING,
+					  "pm8xxx_rtc_alarm", rtc_dd);
 	if (rc < 0) {
 		dev_err(&pdev->dev, "Request IRQ failed (%d)\n", rc);
 		return rc;
 	}
 
-	device_init_wakeup(&pdev->dev, 1);
-
 	dev_dbg(&pdev->dev, "Probe success !!\n");
 
 	return 0;
 }
 
-static int pm8xxx_rtc_remove(struct platform_device *pdev)
-{
-	struct pm8xxx_rtc *rtc_dd = platform_get_drvdata(pdev);
-
-	device_init_wakeup(&pdev->dev, 0);
-	free_irq(rtc_dd->rtc_alarm_irq, rtc_dd);
-
-	return 0;
-}
-
 #ifdef CONFIG_PM_SLEEP
 static int pm8xxx_rtc_resume(struct device *dev)
 {
@@ -507,15 +477,17 @@ static int pm8xxx_rtc_suspend(struct device *dev)
 }
 #endif
 
-static SIMPLE_DEV_PM_OPS(pm8xxx_rtc_pm_ops, pm8xxx_rtc_suspend, pm8xxx_rtc_resume);
+static SIMPLE_DEV_PM_OPS(pm8xxx_rtc_pm_ops,
+			 pm8xxx_rtc_suspend,
+			 pm8xxx_rtc_resume);
 
 static struct platform_driver pm8xxx_rtc_driver = {
 	.probe		= pm8xxx_rtc_probe,
-	.remove		= pm8xxx_rtc_remove,
 	.driver	= {
-		.name	= PM8XXX_RTC_DEV_NAME,
-		.owner	= THIS_MODULE,
-		.pm	= &pm8xxx_rtc_pm_ops,
+		.name		= "rtc-pm8xxx",
+		.owner		= THIS_MODULE,
+		.pm		= &pm8xxx_rtc_pm_ops,
+		.of_match_table	= pm8xxx_id_table,
 	},
 };
 
diff --git a/drivers/rtc/rtc-rx8025.c b/drivers/rtc/rtc-rx8025.c
index 8fa23eabcb68..e6298e02b400 100644
--- a/drivers/rtc/rtc-rx8025.c
+++ b/drivers/rtc/rtc-rx8025.c
@@ -551,7 +551,6 @@ static int rx8025_probe(struct i2c_client *client,
 
 	rx8025 = devm_kzalloc(&client->dev, sizeof(*rx8025), GFP_KERNEL);
 	if (!rx8025) {
-		dev_err(&adapter->dev, "failed to alloc memory\n");
 		err = -ENOMEM;
 		goto errout;
 	}
diff --git a/drivers/rtc/rtc-sirfsoc.c b/drivers/rtc/rtc-sirfsoc.c
index 3eb3642ae299..76e38007ba90 100644
--- a/drivers/rtc/rtc-sirfsoc.c
+++ b/drivers/rtc/rtc-sirfsoc.c
@@ -264,12 +264,8 @@ static int sirfsoc_rtc_probe(struct platform_device *pdev)
 
 	rtcdrv = devm_kzalloc(&pdev->dev,
 		sizeof(struct sirfsoc_rtc_drv), GFP_KERNEL);
-	if (rtcdrv == NULL) {
-		dev_err(&pdev->dev,
-			"%s: can't alloc mem for drv struct\n",
-			pdev->name);
+	if (rtcdrv == NULL)
 		return -ENOMEM;
-	}
 
 	err = of_property_read_u32(np, "reg", &rtcdrv->rtc_base);
 	if (err) {
@@ -335,39 +331,29 @@ static int sirfsoc_rtc_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
-
+#ifdef CONFIG_PM_SLEEP
 static int sirfsoc_rtc_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct sirfsoc_rtc_drv *rtcdrv = platform_get_drvdata(pdev);
+	struct sirfsoc_rtc_drv *rtcdrv = dev_get_drvdata(dev);
 	rtcdrv->overflow_rtc =
 		sirfsoc_rtc_iobrg_readl(rtcdrv->rtc_base + RTC_SW_VALUE);
 
 	rtcdrv->saved_counter =
 		sirfsoc_rtc_iobrg_readl(rtcdrv->rtc_base + RTC_CN);
 	rtcdrv->saved_overflow_rtc = rtcdrv->overflow_rtc;
-	if (device_may_wakeup(&pdev->dev) && !enable_irq_wake(rtcdrv->irq))
+	if (device_may_wakeup(dev) && !enable_irq_wake(rtcdrv->irq))
 		rtcdrv->irq_wake = 1;
 
 	return 0;
 }
 
-static int sirfsoc_rtc_freeze(struct device *dev)
-{
-	sirfsoc_rtc_suspend(dev);
-
-	return 0;
-}
-
-static int sirfsoc_rtc_thaw(struct device *dev)
+static int sirfsoc_rtc_resume(struct device *dev)
 {
 	u32 tmp;
-	struct sirfsoc_rtc_drv *rtcdrv;
-	rtcdrv = dev_get_drvdata(dev);
+	struct sirfsoc_rtc_drv *rtcdrv = dev_get_drvdata(dev);
 
 	/*
-	 * if resume from snapshot and the rtc power is losed,
+	 * if resume from snapshot and the rtc power is lost,
 	 * restroe the rtc settings
 	 */
 	if (SIRFSOC_RTC_CLK != sirfsoc_rtc_iobrg_readl(
@@ -407,57 +393,23 @@ static int sirfsoc_rtc_thaw(struct device *dev)
 	sirfsoc_rtc_iobrg_writel(rtcdrv->overflow_rtc,
 			rtcdrv->rtc_base + RTC_SW_VALUE);
 
-	return 0;
-}
-
-static int sirfsoc_rtc_resume(struct device *dev)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	struct sirfsoc_rtc_drv *rtcdrv = platform_get_drvdata(pdev);
-	sirfsoc_rtc_thaw(dev);
-	if (device_may_wakeup(&pdev->dev) && rtcdrv->irq_wake) {
+	if (device_may_wakeup(dev) && rtcdrv->irq_wake) {
 		disable_irq_wake(rtcdrv->irq);
 		rtcdrv->irq_wake = 0;
 	}
 
 	return 0;
 }
-
-static int sirfsoc_rtc_restore(struct device *dev)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	struct sirfsoc_rtc_drv *rtcdrv = platform_get_drvdata(pdev);
-
-	if (device_may_wakeup(&pdev->dev) && rtcdrv->irq_wake) {
-		disable_irq_wake(rtcdrv->irq);
-		rtcdrv->irq_wake = 0;
-	}
-	return 0;
-}
-
-#else
-#define sirfsoc_rtc_suspend	NULL
-#define sirfsoc_rtc_resume	NULL
-#define sirfsoc_rtc_freeze	NULL
-#define sirfsoc_rtc_thaw	NULL
-#define sirfsoc_rtc_restore	NULL
 #endif
 
-static const struct dev_pm_ops sirfsoc_rtc_pm_ops = {
-	.suspend = sirfsoc_rtc_suspend,
-	.resume = sirfsoc_rtc_resume,
-	.freeze = sirfsoc_rtc_freeze,
-	.thaw = sirfsoc_rtc_thaw,
-	.restore = sirfsoc_rtc_restore,
-};
+static SIMPLE_DEV_PM_OPS(sirfsoc_rtc_pm_ops,
+		sirfsoc_rtc_suspend, sirfsoc_rtc_resume);
 
 static struct platform_driver sirfsoc_rtc_driver = {
 	.driver = {
 		.name = "sirfsoc-rtc",
 		.owner = THIS_MODULE,
-#ifdef CONFIG_PM
 		.pm = &sirfsoc_rtc_pm_ops,
-#endif
 		.of_match_table = sirfsoc_rtc_of_match,
 	},
 	.probe = sirfsoc_rtc_probe,
diff --git a/drivers/rtc/rtc-spear.c b/drivers/rtc/rtc-spear.c
index c492cf0ab8cd..d2cdb9823a15 100644
--- a/drivers/rtc/rtc-spear.c
+++ b/drivers/rtc/rtc-spear.c
@@ -365,10 +365,8 @@ static int spear_rtc_probe(struct platform_device *pdev)
 	}
 
 	config = devm_kzalloc(&pdev->dev, sizeof(*config), GFP_KERNEL);
-	if (!config) {
-		dev_err(&pdev->dev, "out of memory\n");
+	if (!config)
 		return -ENOMEM;
-	}
 
 	/* alarm irqs */
 	irq = platform_get_irq(pdev, 0);
diff --git a/drivers/rtc/rtc-sunxi.c b/drivers/rtc/rtc-sunxi.c
index 68a35284e5ad..b6f21f73d508 100644
--- a/drivers/rtc/rtc-sunxi.c
+++ b/drivers/rtc/rtc-sunxi.c
@@ -428,7 +428,7 @@ static const struct rtc_class_ops sunxi_rtc_ops = {
 };
 
 static const struct of_device_id sunxi_rtc_dt_ids[] = {
-	{ .compatible = "allwinner,sun4i-rtc", .data = &data_year_param[0] },
+	{ .compatible = "allwinner,sun4i-a10-rtc", .data = &data_year_param[0] },
 	{ .compatible = "allwinner,sun7i-a20-rtc", .data = &data_year_param[1] },
 	{ /* sentinel */ },
 };
diff --git a/drivers/rtc/rtc-vt8500.c b/drivers/rtc/rtc-vt8500.c
index df2ef3eba7cd..051da968da6d 100644
--- a/drivers/rtc/rtc-vt8500.c
+++ b/drivers/rtc/rtc-vt8500.c
@@ -79,7 +79,6 @@
 
 struct vt8500_rtc {
 	void __iomem		*regbase;
-	struct resource		*res;
 	int			irq_alarm;
 	struct rtc_device	*rtc;
 	spinlock_t		lock;		/* Protects this structure */
@@ -209,6 +208,7 @@ static const struct rtc_class_ops vt8500_rtc_ops = {
 static int vt8500_rtc_probe(struct platform_device *pdev)
 {
 	struct vt8500_rtc *vt8500_rtc;
+	struct resource	*res;
 	int ret;
 
 	vt8500_rtc = devm_kzalloc(&pdev->dev,
@@ -219,34 +219,16 @@ static int vt8500_rtc_probe(struct platform_device *pdev)
 	spin_lock_init(&vt8500_rtc->lock);
 	platform_set_drvdata(pdev, vt8500_rtc);
 
-	vt8500_rtc->res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!vt8500_rtc->res) {
-		dev_err(&pdev->dev, "No I/O memory resource defined\n");
-		return -ENXIO;
-	}
-
 	vt8500_rtc->irq_alarm = platform_get_irq(pdev, 0);
 	if (vt8500_rtc->irq_alarm < 0) {
 		dev_err(&pdev->dev, "No alarm IRQ resource defined\n");
 		return vt8500_rtc->irq_alarm;
 	}
 
-	vt8500_rtc->res = devm_request_mem_region(&pdev->dev,
-					vt8500_rtc->res->start,
-					resource_size(vt8500_rtc->res),
-					"vt8500-rtc");
-	if (vt8500_rtc->res == NULL) {
-		dev_err(&pdev->dev, "failed to request I/O memory\n");
-		return -EBUSY;
-	}
-
-	vt8500_rtc->regbase = devm_ioremap(&pdev->dev, vt8500_rtc->res->start,
-				      resource_size(vt8500_rtc->res));
-	if (!vt8500_rtc->regbase) {
-		dev_err(&pdev->dev, "Unable to map RTC I/O memory\n");
-		ret = -EBUSY;
-		goto err_return;
-	}
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	vt8500_rtc->regbase = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(vt8500_rtc->regbase))
+		return PTR_ERR(vt8500_rtc->regbase);
 
 	/* Enable RTC and set it to 24-hour mode */
 	writel(VT8500_RTC_CR_ENABLE,
diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c
index 26003d3c1be7..7c4fd97a7fa0 100644
--- a/drivers/staging/lustre/lustre/llite/llite_lib.c
+++ b/drivers/staging/lustre/lustre/llite/llite_lib.c
@@ -1877,7 +1877,7 @@ void ll_delete_inode(struct inode *inode)
 		cl_sync_file_range(inode, 0, OBD_OBJECT_EOF,
 				   CL_FSYNC_DISCARD, 1);
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	/* Workaround for LU-118 */
 	if (inode->i_data.nrpages) {
diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig
index b24aa010f68c..65cd80bf9aec 100644
--- a/drivers/tty/Kconfig
+++ b/drivers/tty/Kconfig
@@ -13,6 +13,10 @@ config VT
 	bool "Virtual terminal" if EXPERT
 	depends on !S390 && !UML
 	select INPUT
+	select NEW_LEDS
+	select LEDS_CLASS
+	select LEDS_TRIGGERS
+	select INPUT_LEDS
 	default y
 	---help---
 	  If you say Y here, you will get support for terminal devices with
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index d0e3a4497707..d6ecfc9e734f 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -33,6 +33,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/leds.h>
 
 #include <linux/kbd_kern.h>
 #include <linux/kbd_diacr.h>
@@ -130,6 +131,7 @@ static char rep;					/* flag telling character repeat */
 static int shift_state = 0;
 
 static unsigned char ledstate = 0xff;			/* undefined */
+static unsigned char lockstate = 0xff;			/* undefined */
 static unsigned char ledioctl;
 
 /*
@@ -961,6 +963,41 @@ static void k_brl(struct vc_data *vc, unsigned char value, char up_flag)
 	}
 }
 
+/* We route VT keyboard "leds" through triggers */
+static void kbd_ledstate_trigger_activate(struct led_classdev *cdev);
+
+static struct led_trigger ledtrig_ledstate[] = {
+#define DEFINE_LEDSTATE_TRIGGER(kbd_led, nam) \
+	[kbd_led] = { \
+		.name = nam, \
+		.activate = kbd_ledstate_trigger_activate, \
+	}
+	DEFINE_LEDSTATE_TRIGGER(VC_SCROLLOCK, "kbd-scrollock"),
+	DEFINE_LEDSTATE_TRIGGER(VC_NUMLOCK,   "kbd-numlock"),
+	DEFINE_LEDSTATE_TRIGGER(VC_CAPSLOCK,  "kbd-capslock"),
+	DEFINE_LEDSTATE_TRIGGER(VC_KANALOCK,  "kbd-kanalock"),
+#undef DEFINE_LEDSTATE_TRIGGER
+};
+
+static void kbd_lockstate_trigger_activate(struct led_classdev *cdev);
+
+static struct led_trigger ledtrig_lockstate[] = {
+#define DEFINE_LOCKSTATE_TRIGGER(kbd_led, nam) \
+	[kbd_led] = { \
+		.name = nam, \
+		.activate = kbd_lockstate_trigger_activate, \
+	}
+	DEFINE_LOCKSTATE_TRIGGER(VC_SHIFTLOCK,  "kbd-shiftlock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_ALTGRLOCK,  "kbd-altgrlock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_CTRLLOCK,   "kbd-ctrllock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_ALTLOCK,    "kbd-altlock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_SHIFTLLOCK, "kbd-shiftllock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_SHIFTRLOCK, "kbd-shiftrlock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_CTRLLLOCK,  "kbd-ctrlllock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_CTRLRLOCK,  "kbd-ctrlrlock"),
+#undef DEFINE_LOCKSTATE_TRIGGER
+};
+
 /*
  * The leds display either (i) the status of NumLock, CapsLock, ScrollLock,
  * or (ii) whatever pattern of lights people want to show using KDSETLED,
@@ -995,18 +1032,25 @@ static inline unsigned char getleds(void)
 	return kbd->ledflagstate;
 }
 
-static int kbd_update_leds_helper(struct input_handle *handle, void *data)
+/* Called on trigger connection, to set initial state */
+static void kbd_ledstate_trigger_activate(struct led_classdev *cdev)
 {
-	unsigned char leds = *(unsigned char *)data;
+	struct led_trigger *trigger = cdev->trigger;
+	int led = trigger - ledtrig_ledstate;
 
-	if (test_bit(EV_LED, handle->dev->evbit)) {
-		input_inject_event(handle, EV_LED, LED_SCROLLL, !!(leds & 0x01));
-		input_inject_event(handle, EV_LED, LED_NUML,    !!(leds & 0x02));
-		input_inject_event(handle, EV_LED, LED_CAPSL,   !!(leds & 0x04));
-		input_inject_event(handle, EV_SYN, SYN_REPORT, 0);
-	}
+	tasklet_disable(&keyboard_tasklet);
+	led_trigger_event(trigger, ledstate & (1 << led) ? LED_FULL : LED_OFF);
+	tasklet_enable(&keyboard_tasklet);
+}
 
-	return 0;
+static void kbd_lockstate_trigger_activate(struct led_classdev *cdev)
+{
+	struct led_trigger *trigger = cdev->trigger;
+	int led = trigger - ledtrig_lockstate;
+
+	tasklet_disable(&keyboard_tasklet);
+	led_trigger_event(trigger, lockstate & (1 << led) ? LED_FULL : LED_OFF);
+	tasklet_enable(&keyboard_tasklet);
 }
 
 /**
@@ -1095,16 +1139,29 @@ static void kbd_bh(unsigned long dummy)
 {
 	unsigned char leds;
 	unsigned long flags;
-	
+	int i;
+
 	spin_lock_irqsave(&led_lock, flags);
 	leds = getleds();
 	spin_unlock_irqrestore(&led_lock, flags);
 
 	if (leds != ledstate) {
-		input_handler_for_each_handle(&kbd_handler, &leds,
-					      kbd_update_leds_helper);
+		for (i = 0; i < ARRAY_SIZE(ledtrig_ledstate); i++)
+			if ((leds ^ ledstate) & (1 << i))
+				led_trigger_event(&ledtrig_ledstate[i],
+						leds & (1 << i)
+						? LED_FULL : LED_OFF);
 		ledstate = leds;
 	}
+
+	if (kbd->lockstate != lockstate) {
+		for (i = 0; i < ARRAY_SIZE(ledtrig_lockstate); i++)
+			if ((kbd->lockstate ^ lockstate) & (1 << i))
+				led_trigger_event(&ledtrig_lockstate[i],
+						kbd->lockstate & (1 << i)
+						? LED_FULL : LED_OFF);
+		lockstate = kbd->lockstate;
+	}
 }
 
 DECLARE_TASKLET_DISABLED(keyboard_tasklet, kbd_bh, 0);
@@ -1442,20 +1499,6 @@ static void kbd_disconnect(struct input_handle *handle)
 	kfree(handle);
 }
 
-/*
- * Start keyboard handler on the new keyboard by refreshing LED state to
- * match the rest of the system.
- */
-static void kbd_start(struct input_handle *handle)
-{
-	tasklet_disable(&keyboard_tasklet);
-
-	if (ledstate != 0xff)
-		kbd_update_leds_helper(handle, &ledstate);
-
-	tasklet_enable(&keyboard_tasklet);
-}
-
 static const struct input_device_id kbd_ids[] = {
 	{
 		.flags = INPUT_DEVICE_ID_MATCH_EVBIT,
@@ -1477,7 +1520,6 @@ static struct input_handler kbd_handler = {
 	.match		= kbd_match,
 	.connect	= kbd_connect,
 	.disconnect	= kbd_disconnect,
-	.start		= kbd_start,
 	.name		= "kbd",
 	.id_table	= kbd_ids,
 };
@@ -1501,6 +1543,20 @@ int __init kbd_init(void)
 	if (error)
 		return error;
 
+	for (i = 0; i < ARRAY_SIZE(ledtrig_ledstate); i++) {
+		error = led_trigger_register(&ledtrig_ledstate[i]);
+		if (error)
+			pr_err("error %d while registering trigger %s\n",
+					error, ledtrig_ledstate[i].name);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(ledtrig_lockstate); i++) {
+		error = led_trigger_register(&ledtrig_lockstate[i]);
+		if (error)
+			pr_err("error %d while registering trigger %s\n",
+					error, ledtrig_lockstate[i].name);
+	}
+
 	tasklet_enable(&keyboard_tasklet);
 	tasklet_schedule(&keyboard_tasklet);
 
diff --git a/drivers/video/backlight/aat2870_bl.c b/drivers/video/backlight/aat2870_bl.c
index ee0c0a982e4e..ec5350f2c28a 100644
--- a/drivers/video/backlight/aat2870_bl.c
+++ b/drivers/video/backlight/aat2870_bl.c
@@ -149,8 +149,6 @@ static int aat2870_bl_probe(struct platform_device *pdev)
 				  sizeof(struct aat2870_bl_driver_data),
 				  GFP_KERNEL);
 	if (!aat2870_bl) {
-		dev_err(&pdev->dev,
-			"Failed to allocate memory for aat2870 backlight\n");
 		ret = -ENOMEM;
 		goto out;
 	}
diff --git a/drivers/video/backlight/adp8860_bl.c b/drivers/video/backlight/adp8860_bl.c
index 9d656717d0f7..be8d83deca7d 100644
--- a/drivers/video/backlight/adp8860_bl.c
+++ b/drivers/video/backlight/adp8860_bl.c
@@ -224,10 +224,8 @@ static int adp8860_led_probe(struct i2c_client *client)
 
 	led = devm_kzalloc(&client->dev, sizeof(*led) * pdata->num_leds,
 				GFP_KERNEL);
-	if (led == NULL) {
-		dev_err(&client->dev, "failed to alloc memory\n");
+	if (led == NULL)
 		return -ENOMEM;
-	}
 
 	ret = adp8860_write(client, ADP8860_ISCFR, pdata->led_fade_law);
 	ret = adp8860_write(client, ADP8860_ISCT1,
diff --git a/drivers/video/backlight/adp8870_bl.c b/drivers/video/backlight/adp8870_bl.c
index 63707205326b..251af4d38d86 100644
--- a/drivers/video/backlight/adp8870_bl.c
+++ b/drivers/video/backlight/adp8870_bl.c
@@ -246,10 +246,8 @@ static int adp8870_led_probe(struct i2c_client *client)
 
 	led = devm_kzalloc(&client->dev, pdata->num_leds * sizeof(*led),
 				GFP_KERNEL);
-	if (led == NULL) {
-		dev_err(&client->dev, "failed to alloc memory\n");
+	if (led == NULL)
 		return -ENOMEM;
-	}
 
 	ret = adp8870_write(client, ADP8870_ISCLAW, pdata->led_fade_law);
 	if (ret)
diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c
index 5d05555fe841..861df0fee11b 100644
--- a/drivers/video/backlight/backlight.c
+++ b/drivers/video/backlight/backlight.c
@@ -34,13 +34,15 @@ static const char *const backlight_types[] = {
 			   defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE))
 /* This callback gets called when something important happens inside a
  * framebuffer driver. We're looking if that important event is blanking,
- * and if it is, we're switching backlight power as well ...
+ * and if it is and necessary, we're switching backlight power as well ...
  */
 static int fb_notifier_callback(struct notifier_block *self,
 				unsigned long event, void *data)
 {
 	struct backlight_device *bd;
 	struct fb_event *evdata = data;
+	int node = evdata->info->node;
+	int fb_blank = 0;
 
 	/* If we aren't interested in this event, skip it immediately ... */
 	if (event != FB_EVENT_BLANK && event != FB_EVENT_CONBLANK)
@@ -51,12 +53,24 @@ static int fb_notifier_callback(struct notifier_block *self,
 	if (bd->ops)
 		if (!bd->ops->check_fb ||
 		    bd->ops->check_fb(bd, evdata->info)) {
-			bd->props.fb_blank = *(int *)evdata->data;
-			if (bd->props.fb_blank == FB_BLANK_UNBLANK)
-				bd->props.state &= ~BL_CORE_FBBLANK;
-			else
-				bd->props.state |= BL_CORE_FBBLANK;
-			backlight_update_status(bd);
+			fb_blank = *(int *)evdata->data;
+			if (fb_blank == FB_BLANK_UNBLANK &&
+			    !bd->fb_bl_on[node]) {
+				bd->fb_bl_on[node] = true;
+				if (!bd->use_count++) {
+					bd->props.state &= ~BL_CORE_FBBLANK;
+					bd->props.fb_blank = FB_BLANK_UNBLANK;
+					backlight_update_status(bd);
+				}
+			} else if (fb_blank != FB_BLANK_UNBLANK &&
+				   bd->fb_bl_on[node]) {
+				bd->fb_bl_on[node] = false;
+				if (!(--bd->use_count)) {
+					bd->props.state |= BL_CORE_FBBLANK;
+					bd->props.fb_blank = fb_blank;
+					backlight_update_status(bd);
+				}
+			}
 		}
 	mutex_unlock(&bd->ops_lock);
 	return 0;
@@ -175,8 +189,6 @@ static ssize_t brightness_store(struct device *dev,
 	}
 	mutex_unlock(&bd->ops_lock);
 
-	backlight_generate_event(bd, BACKLIGHT_UPDATE_SYSFS);
-
 	return rc;
 }
 static DEVICE_ATTR_RW(brightness);
diff --git a/drivers/video/backlight/corgi_lcd.c b/drivers/video/backlight/corgi_lcd.c
index db8db5fa6583..51d18d637e2b 100644
--- a/drivers/video/backlight/corgi_lcd.c
+++ b/drivers/video/backlight/corgi_lcd.c
@@ -543,10 +543,8 @@ static int corgi_lcd_probe(struct spi_device *spi)
 	}
 
 	lcd = devm_kzalloc(&spi->dev, sizeof(struct corgi_lcd), GFP_KERNEL);
-	if (!lcd) {
-		dev_err(&spi->dev, "failed to allocate memory\n");
+	if (!lcd)
 		return -ENOMEM;
-	}
 
 	lcd->spi_dev = spi;
 
diff --git a/drivers/video/backlight/hx8357.c b/drivers/video/backlight/hx8357.c
index 985e854e244b..23f50b92a930 100644
--- a/drivers/video/backlight/hx8357.c
+++ b/drivers/video/backlight/hx8357.c
@@ -587,10 +587,8 @@ static int hx8357_probe(struct spi_device *spi)
 	int i, ret;
 
 	lcd = devm_kzalloc(&spi->dev, sizeof(*lcd), GFP_KERNEL);
-	if (!lcd) {
-		dev_err(&spi->dev, "Couldn't allocate lcd internal structure!\n");
+	if (!lcd)
 		return -ENOMEM;
-	}
 
 	ret = spi_setup(spi);
 	if (ret < 0) {
diff --git a/drivers/video/backlight/ili922x.c b/drivers/video/backlight/ili922x.c
index 73464e4b4c74..ea67fe199e34 100644
--- a/drivers/video/backlight/ili922x.c
+++ b/drivers/video/backlight/ili922x.c
@@ -482,10 +482,8 @@ static int ili922x_probe(struct spi_device *spi)
 	u16 reg = 0;
 
 	ili = devm_kzalloc(&spi->dev, sizeof(*ili), GFP_KERNEL);
-	if (!ili) {
-		dev_err(&spi->dev, "cannot alloc priv data\n");
+	if (!ili)
 		return -ENOMEM;
-	}
 
 	ili->spi = spi;
 	spi_set_drvdata(spi, ili);
diff --git a/drivers/video/backlight/ili9320.c b/drivers/video/backlight/ili9320.c
index e2b8b40a9bd9..2cf39e6d519d 100644
--- a/drivers/video/backlight/ili9320.c
+++ b/drivers/video/backlight/ili9320.c
@@ -219,10 +219,8 @@ int ili9320_probe_spi(struct spi_device *spi,
 	/* allocate and initialse our state */
 
 	ili = devm_kzalloc(&spi->dev, sizeof(struct ili9320), GFP_KERNEL);
-	if (ili == NULL) {
-		dev_err(dev, "no memory for device\n");
+	if (ili == NULL)
 		return -ENOMEM;
-	}
 
 	ili->access.spi.id = ILI9320_SPI_IDCODE | ILI9320_SPI_ID(1);
 
diff --git a/drivers/video/backlight/l4f00242t03.c b/drivers/video/backlight/l4f00242t03.c
index 63e763828e0e..5fa2649c9631 100644
--- a/drivers/video/backlight/l4f00242t03.c
+++ b/drivers/video/backlight/l4f00242t03.c
@@ -181,11 +181,8 @@ static int l4f00242t03_probe(struct spi_device *spi)
 
 	priv = devm_kzalloc(&spi->dev, sizeof(struct l4f00242t03_priv),
 				GFP_KERNEL);
-
-	if (priv == NULL) {
-		dev_err(&spi->dev, "No memory for this device.\n");
+	if (priv == NULL)
 		return -ENOMEM;
-	}
 
 	spi_set_drvdata(spi, priv);
 	spi->bits_per_word = 9;
diff --git a/drivers/video/backlight/lm3533_bl.c b/drivers/video/backlight/lm3533_bl.c
index 187d1c283c1d..cff1fbe89a1b 100644
--- a/drivers/video/backlight/lm3533_bl.c
+++ b/drivers/video/backlight/lm3533_bl.c
@@ -296,11 +296,8 @@ static int lm3533_bl_probe(struct platform_device *pdev)
 	}
 
 	bl = devm_kzalloc(&pdev->dev, sizeof(*bl), GFP_KERNEL);
-	if (!bl) {
-		dev_err(&pdev->dev,
-				"failed to allocate memory for backlight\n");
+	if (!bl)
 		return -ENOMEM;
-	}
 
 	bl->lm3533 = lm3533;
 	bl->id = pdev->id;
diff --git a/drivers/video/backlight/lms283gf05.c b/drivers/video/backlight/lms283gf05.c
index de8832504f68..14590c54aedf 100644
--- a/drivers/video/backlight/lms283gf05.c
+++ b/drivers/video/backlight/lms283gf05.c
@@ -168,10 +168,8 @@ static int lms283gf05_probe(struct spi_device *spi)
 
 	st = devm_kzalloc(&spi->dev, sizeof(struct lms283gf05_state),
 				GFP_KERNEL);
-	if (st == NULL) {
-		dev_err(&spi->dev, "No memory for device state\n");
+	if (st == NULL)
 		return -ENOMEM;
-	}
 
 	ld = devm_lcd_device_register(&spi->dev, "lms283gf05", &spi->dev, st,
 					&lms_ops);
diff --git a/drivers/video/backlight/platform_lcd.c b/drivers/video/backlight/platform_lcd.c
index d01884d4f1bf..c3d2e209fc8f 100644
--- a/drivers/video/backlight/platform_lcd.c
+++ b/drivers/video/backlight/platform_lcd.c
@@ -94,10 +94,8 @@ static int platform_lcd_probe(struct platform_device *pdev)
 
 	plcd = devm_kzalloc(&pdev->dev, sizeof(struct platform_lcd),
 			    GFP_KERNEL);
-	if (!plcd) {
-		dev_err(dev, "no memory for state\n");
+	if (!plcd)
 		return -ENOMEM;
-	}
 
 	plcd->us = dev;
 	plcd->pdata = pdata;
diff --git a/drivers/video/backlight/tps65217_bl.c b/drivers/video/backlight/tps65217_bl.c
index cbba37e6836e..595dcf561020 100644
--- a/drivers/video/backlight/tps65217_bl.c
+++ b/drivers/video/backlight/tps65217_bl.c
@@ -200,7 +200,6 @@ tps65217_bl_parse_dt(struct platform_device *pdev)
 
 	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata) {
-		dev_err(&pdev->dev, "failed to allocate platform data\n");
 		err = ERR_PTR(-ENOMEM);
 		goto err;
 	}
@@ -296,10 +295,8 @@ static int tps65217_bl_probe(struct platform_device *pdev)
 
 	tps65217_bl = devm_kzalloc(&pdev->dev, sizeof(*tps65217_bl),
 				GFP_KERNEL);
-	if (tps65217_bl == NULL) {
-		dev_err(&pdev->dev, "allocation of struct tps65217_bl failed\n");
+	if (tps65217_bl == NULL)
 		return -ENOMEM;
-	}
 
 	tps65217_bl->tps = tps;
 	tps65217_bl->dev = &pdev->dev;
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index a16b0ff497ca..d8223209d4b1 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -832,6 +832,7 @@ static void v9fs_mmap_vm_close(struct vm_area_struct *vma)
 
 static const struct vm_operations_struct v9fs_file_vm_ops = {
 	.fault = filemap_fault,
+	.map_pages = filemap_map_pages,
 	.page_mkwrite = v9fs_vm_page_mkwrite,
 	.remap_pages = generic_file_remap_pages,
 };
@@ -839,6 +840,7 @@ static const struct vm_operations_struct v9fs_file_vm_ops = {
 static const struct vm_operations_struct v9fs_mmap_file_vm_ops = {
 	.close = v9fs_mmap_vm_close,
 	.fault = filemap_fault,
+	.map_pages = filemap_map_pages,
 	.page_mkwrite = v9fs_vm_page_mkwrite,
 	.remap_pages = generic_file_remap_pages,
 };
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index bb7991c7e5c7..53161ec058a7 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -451,7 +451,7 @@ void v9fs_evict_inode(struct inode *inode)
 {
 	struct v9fs_inode *v9inode = V9FS_I(inode);
 
-	truncate_inode_pages(inode->i_mapping, 0);
+	truncate_inode_pages_final(inode->i_mapping);
 	clear_inode(inode);
 	filemap_fdatawrite(inode->i_mapping);
 
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 952aeb048349..9852bdf34d76 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -266,7 +266,7 @@ static void init_once(void *foo)
 	inode_init_once(&ei->vfs_inode);
 }
 
-static int init_inodecache(void)
+static int __init init_inodecache(void)
 {
 	adfs_inode_cachep = kmem_cache_create("adfs_inode_cache",
 					     sizeof(struct adfs_inode_info),
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index 3952121f2f28..25b23b1e7f22 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -5,14 +5,6 @@
 #include <linux/mutex.h>
 #include <linux/workqueue.h>
 
-/* AmigaOS allows file names with up to 30 characters length.
- * Names longer than that will be silently truncated. If you
- * want to disallow this, comment out the following #define.
- * Creating filesystem objects with longer names will then
- * result in an error (ENAMETOOLONG).
- */
-/*#define AFFS_NO_TRUNCATE */
-
 /* Ugly macros make the code more pretty. */
 
 #define GET_END_PTR(st,p,sz)		 ((st *)((char *)(p)+((sz)-sizeof(st))))
@@ -28,7 +20,6 @@
 
 #define AFFS_CACHE_SIZE		PAGE_SIZE
 
-#define AFFS_MAX_PREALLOC	32
 #define AFFS_LC_SIZE		(AFFS_CACHE_SIZE/sizeof(u32)/2)
 #define AFFS_AC_SIZE		(AFFS_CACHE_SIZE/sizeof(struct affs_ext_key)/2)
 #define AFFS_AC_MASK		(AFFS_AC_SIZE-1)
@@ -118,6 +109,7 @@ struct affs_sb_info {
 #define SF_OFS		0x0200		/* Old filesystem */
 #define SF_PREFIX	0x0400		/* Buffer for prefix is allocated */
 #define SF_VERBOSE	0x0800		/* Talk about fs when mounting */
+#define SF_NO_TRUNCATE	0x1000		/* Don't truncate filenames */
 
 /* short cut to get to the affs specific sb data */
 static inline struct affs_sb_info *AFFS_SB(struct super_block *sb)
@@ -137,9 +129,13 @@ extern void	affs_fix_checksum(struct super_block *sb, struct buffer_head *bh);
 extern void	secs_to_datestamp(time_t secs, struct affs_date *ds);
 extern umode_t	prot_to_mode(u32 prot);
 extern void	mode_to_prot(struct inode *inode);
-extern void	affs_error(struct super_block *sb, const char *function, const char *fmt, ...);
-extern void	affs_warning(struct super_block *sb, const char *function, const char *fmt, ...);
-extern int	affs_check_name(const unsigned char *name, int len);
+extern void	affs_error(struct super_block *sb, const char *function,
+			   const char *fmt, ...);
+extern void	affs_warning(struct super_block *sb, const char *function,
+			     const char *fmt, ...);
+extern bool	affs_nofilenametruncate(const struct dentry *dentry);
+extern int	affs_check_name(const unsigned char *name, int len,
+				bool notruncate);
 extern int	affs_copy_name(unsigned char *bstr, struct dentry *dentry);
 
 /* bitmap. c */
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index d9a43674cb94..533a322c41c0 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -471,20 +471,27 @@ affs_warning(struct super_block *sb, const char *function, const char *fmt, ...)
 		function,ErrorBuffer);
 }
 
+bool
+affs_nofilenametruncate(const struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+	return AFFS_SB(inode->i_sb)->s_flags & SF_NO_TRUNCATE;
+
+}
+
 /* Check if the name is valid for a affs object. */
 
 int
-affs_check_name(const unsigned char *name, int len)
+affs_check_name(const unsigned char *name, int len, bool notruncate)
 {
 	int	 i;
 
-	if (len > 30)
-#ifdef AFFS_NO_TRUNCATE
-		return -ENAMETOOLONG;
-#else
-		len = 30;
-#endif
-
+	if (len > 30) {
+		if (notruncate)
+			return -ENAMETOOLONG;
+		else
+			len = 30;
+	}
 	for (i = 0; i < len; i++) {
 		if (name[i] < ' ' || name[i] == ':'
 		    || (name[i] > 0x7e && name[i] < 0xa0))
diff --git a/fs/affs/dir.c b/fs/affs/dir.c
index f1eba8c3644e..cbbda476a805 100644
--- a/fs/affs/dir.c
+++ b/fs/affs/dir.c
@@ -52,8 +52,10 @@ affs_readdir(struct file *file, struct dir_context *ctx)
 	int			 hash_pos;
 	int			 chain_pos;
 	u32			 ino;
+	int			 error = 0;
 
-	pr_debug("AFFS: readdir(ino=%lu,f_pos=%lx)\n",inode->i_ino,(unsigned long)ctx->pos);
+	pr_debug("AFFS: readdir(ino=%lu,f_pos=%lx)\n",
+		 inode->i_ino, (unsigned long)ctx->pos);
 
 	if (ctx->pos < 2) {
 		file->private_data = (void *)0;
@@ -72,7 +74,7 @@ affs_readdir(struct file *file, struct dir_context *ctx)
 	}
 	dir_bh = affs_bread(sb, inode->i_ino);
 	if (!dir_bh)
-		goto readdir_out;
+		goto out_unlock_dir;
 
 	/* If the directory hasn't changed since the last call to readdir(),
 	 * we can jump directly to where we left off.
@@ -88,7 +90,8 @@ affs_readdir(struct file *file, struct dir_context *ctx)
 		fh_bh = affs_bread(sb, ino);
 		if (!fh_bh) {
 			affs_error(sb, "readdir","Cannot read block %d", i);
-			return -EIO;
+			error = -EIO;
+			goto out_brelse_dir;
 		}
 		ino = be32_to_cpu(AFFS_TAIL(sb, fh_bh)->hash_chain);
 		affs_brelse(fh_bh);
@@ -107,29 +110,34 @@ inside:
 		do {
 			fh_bh = affs_bread(sb, ino);
 			if (!fh_bh) {
-				affs_error(sb, "readdir","Cannot read block %d", ino);
+				affs_error(sb, "readdir",
+					   "Cannot read block %d", ino);
 				break;
 			}
 
 			namelen = min(AFFS_TAIL(sb, fh_bh)->name[0], (u8)30);
 			name = AFFS_TAIL(sb, fh_bh)->name + 1;
-			pr_debug("AFFS: readdir(): filldir(\"%.*s\", ino=%u), hash=%d, f_pos=%x\n",
+			pr_debug("AFFS: readdir(): dir_emit(\"%.*s\", "
+				 "ino=%u), hash=%d, f_pos=%x\n",
 				 namelen, name, ino, hash_pos, (u32)ctx->pos);
+
 			if (!dir_emit(ctx, name, namelen, ino, DT_UNKNOWN))
-				goto readdir_done;
+				goto done;
 			ctx->pos++;
 			ino = be32_to_cpu(AFFS_TAIL(sb, fh_bh)->hash_chain);
 			affs_brelse(fh_bh);
 			fh_bh = NULL;
 		} while (ino);
 	}
-readdir_done:
+done:
 	file->f_version = inode->i_version;
 	file->private_data = (void *)(long)ino;
+	affs_brelse(fh_bh);
 
-readdir_out:
+out_brelse_dir:
 	affs_brelse(dir_bh);
-	affs_brelse(fh_bh);
+
+out_unlock_dir:
 	affs_unlock_dir(inode);
-	return 0;
+	return error;
 }
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index 0e092d08680e..96df91e8c334 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -259,7 +259,7 @@ affs_evict_inode(struct inode *inode)
 {
 	unsigned long cache_page;
 	pr_debug("AFFS: evict_inode(ino=%lu, nlink=%u)\n", inode->i_ino, inode->i_nlink);
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	if (!inode->i_nlink) {
 		inode->i_size = 0;
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index c36cbb4537a2..6dae1ccd176d 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -60,13 +60,13 @@ affs_get_toupper(struct super_block *sb)
  * Note: the dentry argument is the parent dentry.
  */
 static inline int
-__affs_hash_dentry(struct qstr *qstr, toupper_t toupper)
+__affs_hash_dentry(struct qstr *qstr, toupper_t toupper, bool notruncate)
 {
 	const u8 *name = qstr->name;
 	unsigned long hash;
 	int i;
 
-	i = affs_check_name(qstr->name, qstr->len);
+	i = affs_check_name(qstr->name, qstr->len, notruncate);
 	if (i)
 		return i;
 
@@ -82,16 +82,22 @@ __affs_hash_dentry(struct qstr *qstr, toupper_t toupper)
 static int
 affs_hash_dentry(const struct dentry *dentry, struct qstr *qstr)
 {
-	return __affs_hash_dentry(qstr, affs_toupper);
+	return __affs_hash_dentry(qstr, affs_toupper,
+				  affs_nofilenametruncate(dentry));
+
 }
+
 static int
 affs_intl_hash_dentry(const struct dentry *dentry, struct qstr *qstr)
 {
-	return __affs_hash_dentry(qstr, affs_intl_toupper);
+	return __affs_hash_dentry(qstr, affs_intl_toupper,
+				  affs_nofilenametruncate(dentry));
+
 }
 
 static inline int __affs_compare_dentry(unsigned int len,
-		const char *str, const struct qstr *name, toupper_t toupper)
+		const char *str, const struct qstr *name, toupper_t toupper,
+		bool notruncate)
 {
 	const u8 *aname = str;
 	const u8 *bname = name->name;
@@ -101,7 +107,7 @@ static inline int __affs_compare_dentry(unsigned int len,
 	 * must be valid. 'name' must be validated first.
 	 */
 
-	if (affs_check_name(name->name, name->len))
+	if (affs_check_name(name->name, name->len, notruncate))
 		return 1;
 
 	/*
@@ -126,13 +132,18 @@ static int
 affs_compare_dentry(const struct dentry *parent, const struct dentry *dentry,
 		unsigned int len, const char *str, const struct qstr *name)
 {
-	return __affs_compare_dentry(len, str, name, affs_toupper);
+
+	return __affs_compare_dentry(len, str, name, affs_toupper,
+				     affs_nofilenametruncate(parent));
 }
+
 static int
 affs_intl_compare_dentry(const struct dentry *parent, const struct dentry *dentry,
 		unsigned int len, const char *str, const struct qstr *name)
 {
-	return __affs_compare_dentry(len, str, name, affs_intl_toupper);
+	return __affs_compare_dentry(len, str, name, affs_intl_toupper,
+				     affs_nofilenametruncate(parent));
+
 }
 
 /*
@@ -411,7 +422,10 @@ affs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		 (u32)old_dir->i_ino, (int)old_dentry->d_name.len, old_dentry->d_name.name,
 		 (u32)new_dir->i_ino, (int)new_dentry->d_name.len, new_dentry->d_name.name);
 
-	retval = affs_check_name(new_dentry->d_name.name,new_dentry->d_name.len);
+	retval = affs_check_name(new_dentry->d_name.name,
+				 new_dentry->d_name.len,
+				 affs_nofilenametruncate(old_dentry));
+
 	if (retval)
 		return retval;
 
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 307453086c3f..6d589f28bf9b 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -128,7 +128,7 @@ static void init_once(void *foo)
 	inode_init_once(&ei->vfs_inode);
 }
 
-static int init_inodecache(void)
+static int __init init_inodecache(void)
 {
 	affs_inode_cachep = kmem_cache_create("affs_inode_cache",
 					     sizeof(struct affs_inode_info),
@@ -163,7 +163,7 @@ static const struct super_operations affs_sops = {
 };
 
 enum {
-	Opt_bs, Opt_mode, Opt_mufs, Opt_prefix, Opt_protect,
+	Opt_bs, Opt_mode, Opt_mufs, Opt_notruncate, Opt_prefix, Opt_protect,
 	Opt_reserved, Opt_root, Opt_setgid, Opt_setuid,
 	Opt_verbose, Opt_volume, Opt_ignore, Opt_err,
 };
@@ -172,6 +172,7 @@ static const match_table_t tokens = {
 	{Opt_bs, "bs=%u"},
 	{Opt_mode, "mode=%o"},
 	{Opt_mufs, "mufs"},
+	{Opt_notruncate, "nofilenametruncate"},
 	{Opt_prefix, "prefix=%s"},
 	{Opt_protect, "protect"},
 	{Opt_reserved, "reserved=%u"},
@@ -233,6 +234,9 @@ parse_options(char *options, kuid_t *uid, kgid_t *gid, int *mode, int *reserved,
 		case Opt_mufs:
 			*mount_opts |= SF_MUFS;
 			break;
+		case Opt_notruncate:
+			*mount_opts |= SF_NO_TRUNCATE;
+			break;
 		case Opt_prefix:
 			*prefix = match_strdup(&args[0]);
 			if (!*prefix)
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index ce25d755b7aa..294671288449 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -422,7 +422,7 @@ void afs_evict_inode(struct inode *inode)
 
 	ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode);
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 
 	afs_give_up_callback(vnode);
diff --git a/fs/befs/Makefile b/fs/befs/Makefile
index 2f370bd7a50d..8b9f66642a83 100644
--- a/fs/befs/Makefile
+++ b/fs/befs/Makefile
@@ -3,5 +3,5 @@
 #
  
 obj-$(CONFIG_BEFS_FS) += befs.o
-
+ccflags-$(CONFIG_BEFS_DEBUG)    += -DDEBUG
 befs-objs := datastream.o btree.o super.o inode.o debug.o io.o linuxvfs.o
diff --git a/fs/befs/befs.h b/fs/befs/befs.h
index b26642839156..3a7813ab8c95 100644
--- a/fs/befs/befs.h
+++ b/fs/befs/befs.h
@@ -88,8 +88,11 @@ enum befs_err {
 
 /****************************/
 /* debug.c */
+__printf(2, 3)
 void befs_error(const struct super_block *sb, const char *fmt, ...);
+__printf(2, 3)
 void befs_warning(const struct super_block *sb, const char *fmt, ...);
+__printf(2, 3)
 void befs_debug(const struct super_block *sb, const char *fmt, ...);
 
 void befs_dump_super_block(const struct super_block *sb, befs_super_block *);
diff --git a/fs/befs/btree.c b/fs/befs/btree.c
index 74e397db0b8b..a2cd305a993a 100644
--- a/fs/befs/btree.c
+++ b/fs/befs/btree.c
@@ -137,7 +137,7 @@ befs_bt_read_super(struct super_block *sb, befs_data_stream * ds,
 	struct buffer_head *bh = NULL;
 	befs_disk_btree_super *od_sup = NULL;
 
-	befs_debug(sb, "---> befs_btree_read_super()");
+	befs_debug(sb, "---> %s", __func__);
 
 	bh = befs_read_datastream(sb, ds, 0, NULL);
 
@@ -162,11 +162,11 @@ befs_bt_read_super(struct super_block *sb, befs_data_stream * ds,
 		goto error;
 	}
 
-	befs_debug(sb, "<--- befs_btree_read_super()");
+	befs_debug(sb, "<--- %s", __func__);
 	return BEFS_OK;
 
       error:
-	befs_debug(sb, "<--- befs_btree_read_super() ERROR");
+	befs_debug(sb, "<--- %s ERROR", __func__);
 	return BEFS_ERR;
 }
 
@@ -195,16 +195,16 @@ befs_bt_read_node(struct super_block *sb, befs_data_stream * ds,
 {
 	uint off = 0;
 
-	befs_debug(sb, "---> befs_bt_read_node()");
+	befs_debug(sb, "---> %s", __func__);
 
 	if (node->bh)
 		brelse(node->bh);
 
 	node->bh = befs_read_datastream(sb, ds, node_off, &off);
 	if (!node->bh) {
-		befs_error(sb, "befs_bt_read_node() failed to read "
-			   "node at %Lu", node_off);
-		befs_debug(sb, "<--- befs_bt_read_node() ERROR");
+		befs_error(sb, "%s failed to read "
+			   "node at %llu", __func__, node_off);
+		befs_debug(sb, "<--- %s ERROR", __func__);
 
 		return BEFS_ERR;
 	}
@@ -221,7 +221,7 @@ befs_bt_read_node(struct super_block *sb, befs_data_stream * ds,
 	node->head.all_key_length =
 	    fs16_to_cpu(sb, node->od_node->all_key_length);
 
-	befs_debug(sb, "<--- befs_btree_read_node()");
+	befs_debug(sb, "<--- %s", __func__);
 	return BEFS_OK;
 }
 
@@ -252,7 +252,7 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds,
 	befs_off_t node_off;
 	int res;
 
-	befs_debug(sb, "---> befs_btree_find() Key: %s", key);
+	befs_debug(sb, "---> %s Key: %s", __func__, key);
 
 	if (befs_bt_read_super(sb, ds, &bt_super) != BEFS_OK) {
 		befs_error(sb,
@@ -263,7 +263,7 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds,
 	this_node = kmalloc(sizeof (befs_btree_node),
 						GFP_NOFS);
 	if (!this_node) {
-		befs_error(sb, "befs_btree_find() failed to allocate %u "
+		befs_error(sb, "befs_btree_find() failed to allocate %zu "
 			   "bytes of memory", sizeof (befs_btree_node));
 		goto error;
 	}
@@ -274,7 +274,7 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds,
 	node_off = bt_super.root_node_ptr;
 	if (befs_bt_read_node(sb, ds, this_node, node_off) != BEFS_OK) {
 		befs_error(sb, "befs_btree_find() failed to read "
-			   "node at %Lu", node_off);
+			   "node at %llu", node_off);
 		goto error_alloc;
 	}
 
@@ -285,7 +285,7 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds,
 		/* if no match, go to overflow node */
 		if (befs_bt_read_node(sb, ds, this_node, node_off) != BEFS_OK) {
 			befs_error(sb, "befs_btree_find() failed to read "
-				   "node at %Lu", node_off);
+				   "node at %llu", node_off);
 			goto error_alloc;
 		}
 	}
@@ -298,11 +298,11 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds,
 	kfree(this_node);
 
 	if (res != BEFS_BT_MATCH) {
-		befs_debug(sb, "<--- befs_btree_find() Key %s not found", key);
+		befs_debug(sb, "<--- %s Key %s not found", __func__, key);
 		*value = 0;
 		return BEFS_BT_NOT_FOUND;
 	}
-	befs_debug(sb, "<--- befs_btree_find() Found key %s, value %Lu",
+	befs_debug(sb, "<--- %s Found key %s, value %llu", __func__,
 		   key, *value);
 	return BEFS_OK;
 
@@ -310,7 +310,7 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds,
 	kfree(this_node);
       error:
 	*value = 0;
-	befs_debug(sb, "<--- befs_btree_find() ERROR");
+	befs_debug(sb, "<--- %s ERROR", __func__);
 	return BEFS_ERR;
 }
 
@@ -343,7 +343,7 @@ befs_find_key(struct super_block *sb, befs_btree_node * node,
 	char *thiskey;
 	fs64 *valarray;
 
-	befs_debug(sb, "---> befs_find_key() %s", findkey);
+	befs_debug(sb, "---> %s %s", __func__, findkey);
 
 	*value = 0;
 
@@ -355,7 +355,7 @@ befs_find_key(struct super_block *sb, befs_btree_node * node,
 
 	eq = befs_compare_strings(thiskey, keylen, findkey, findkey_len);
 	if (eq < 0) {
-		befs_debug(sb, "<--- befs_find_key() %s not found", findkey);
+		befs_debug(sb, "<--- %s %s not found", __func__, findkey);
 		return BEFS_BT_NOT_FOUND;
 	}
 
@@ -373,8 +373,8 @@ befs_find_key(struct super_block *sb, befs_btree_node * node,
 					  findkey_len);
 
 		if (eq == 0) {
-			befs_debug(sb, "<--- befs_find_key() found %s at %d",
-				   thiskey, mid);
+			befs_debug(sb, "<--- %s found %s at %d",
+				   __func__, thiskey, mid);
 
 			*value = fs64_to_cpu(sb, valarray[mid]);
 			return BEFS_BT_MATCH;
@@ -388,7 +388,7 @@ befs_find_key(struct super_block *sb, befs_btree_node * node,
 		*value = fs64_to_cpu(sb, valarray[mid + 1]);
 	else
 		*value = fs64_to_cpu(sb, valarray[mid]);
-	befs_debug(sb, "<--- befs_find_key() found %s at %d", thiskey, mid);
+	befs_debug(sb, "<--- %s found %s at %d", __func__, thiskey, mid);
 	return BEFS_BT_PARMATCH;
 }
 
@@ -428,7 +428,7 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
 
 	uint key_sum = 0;
 
-	befs_debug(sb, "---> befs_btree_read()");
+	befs_debug(sb, "---> %s", __func__);
 
 	if (befs_bt_read_super(sb, ds, &bt_super) != BEFS_OK) {
 		befs_error(sb,
@@ -437,7 +437,7 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
 	}
 
 	if ((this_node = kmalloc(sizeof (befs_btree_node), GFP_NOFS)) == NULL) {
-		befs_error(sb, "befs_btree_read() failed to allocate %u "
+		befs_error(sb, "befs_btree_read() failed to allocate %zu "
 			   "bytes of memory", sizeof (befs_btree_node));
 		goto error;
 	}
@@ -452,7 +452,7 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
 		kfree(this_node);
 		*value = 0;
 		*keysize = 0;
-		befs_debug(sb, "<--- befs_btree_read() Tree is EMPTY");
+		befs_debug(sb, "<--- %s Tree is EMPTY", __func__);
 		return BEFS_BT_EMPTY;
 	} else if (res == BEFS_ERR) {
 		goto error_alloc;
@@ -467,7 +467,8 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
 			*keysize = 0;
 			*value = 0;
 			befs_debug(sb,
-				   "<--- befs_btree_read() END of keys at %Lu",
+				   "<--- %s END of keys at %llu", __func__,
+				   (unsigned long long)
 				   key_sum + this_node->head.all_key_count);
 			brelse(this_node->bh);
 			kfree(this_node);
@@ -478,8 +479,8 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
 		node_off = this_node->head.right;
 
 		if (befs_bt_read_node(sb, ds, this_node, node_off) != BEFS_OK) {
-			befs_error(sb, "befs_btree_read() failed to read "
-				   "node at %Lu", node_off);
+			befs_error(sb, "%s failed to read node at %llu",
+				  __func__, (unsigned long long)node_off);
 			goto error_alloc;
 		}
 	}
@@ -492,11 +493,13 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
 
 	keystart = befs_bt_get_key(sb, this_node, cur_key, &keylen);
 
-	befs_debug(sb, "Read [%Lu,%d]: keysize %d", node_off, cur_key, keylen);
+	befs_debug(sb, "Read [%llu,%d]: keysize %d",
+		   (long long unsigned int)node_off, (int)cur_key,
+		   (int)keylen);
 
 	if (bufsize < keylen + 1) {
-		befs_error(sb, "befs_btree_read() keybuf too small (%u) "
-			   "for key of size %d", bufsize, keylen);
+		befs_error(sb, "%s keybuf too small (%zu) "
+			   "for key of size %d", __func__, bufsize, keylen);
 		brelse(this_node->bh);
 		goto error_alloc;
 	};
@@ -506,13 +509,13 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
 	*keysize = keylen;
 	keybuf[keylen] = '\0';
 
-	befs_debug(sb, "Read [%Lu,%d]: Key \"%.*s\", Value %Lu", node_off,
+	befs_debug(sb, "Read [%llu,%d]: Key \"%.*s\", Value %llu", node_off,
 		   cur_key, keylen, keybuf, *value);
 
 	brelse(this_node->bh);
 	kfree(this_node);
 
-	befs_debug(sb, "<--- befs_btree_read()");
+	befs_debug(sb, "<--- %s", __func__);
 
 	return BEFS_OK;
 
@@ -522,7 +525,7 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
       error:
 	*keysize = 0;
 	*value = 0;
-	befs_debug(sb, "<--- befs_btree_read() ERROR");
+	befs_debug(sb, "<--- %s ERROR", __func__);
 	return BEFS_ERR;
 }
 
@@ -547,26 +550,26 @@ befs_btree_seekleaf(struct super_block *sb, befs_data_stream * ds,
 		    befs_off_t * node_off)
 {
 
-	befs_debug(sb, "---> befs_btree_seekleaf()");
+	befs_debug(sb, "---> %s", __func__);
 
 	if (befs_bt_read_node(sb, ds, this_node, *node_off) != BEFS_OK) {
-		befs_error(sb, "befs_btree_seekleaf() failed to read "
-			   "node at %Lu", *node_off);
+		befs_error(sb, "%s failed to read "
+			   "node at %llu", __func__, *node_off);
 		goto error;
 	}
-	befs_debug(sb, "Seekleaf to root node %Lu", *node_off);
+	befs_debug(sb, "Seekleaf to root node %llu", *node_off);
 
 	if (this_node->head.all_key_count == 0 && befs_leafnode(this_node)) {
-		befs_debug(sb, "<--- befs_btree_seekleaf() Tree is EMPTY");
+		befs_debug(sb, "<--- %s Tree is EMPTY", __func__);
 		return BEFS_BT_EMPTY;
 	}
 
 	while (!befs_leafnode(this_node)) {
 
 		if (this_node->head.all_key_count == 0) {
-			befs_debug(sb, "befs_btree_seekleaf() encountered "
-				   "an empty interior node: %Lu. Using Overflow "
-				   "node: %Lu", *node_off,
+			befs_debug(sb, "%s encountered "
+				   "an empty interior node: %llu. Using Overflow "
+				   "node: %llu", __func__, *node_off,
 				   this_node->head.overflow);
 			*node_off = this_node->head.overflow;
 		} else {
@@ -574,19 +577,19 @@ befs_btree_seekleaf(struct super_block *sb, befs_data_stream * ds,
 			*node_off = fs64_to_cpu(sb, valarray[0]);
 		}
 		if (befs_bt_read_node(sb, ds, this_node, *node_off) != BEFS_OK) {
-			befs_error(sb, "befs_btree_seekleaf() failed to read "
-				   "node at %Lu", *node_off);
+			befs_error(sb, "%s failed to read "
+				   "node at %llu", __func__, *node_off);
 			goto error;
 		}
 
-		befs_debug(sb, "Seekleaf to child node %Lu", *node_off);
+		befs_debug(sb, "Seekleaf to child node %llu", *node_off);
 	}
-	befs_debug(sb, "Node %Lu is a leaf node", *node_off);
+	befs_debug(sb, "Node %llu is a leaf node", *node_off);
 
 	return BEFS_OK;
 
       error:
-	befs_debug(sb, "<--- befs_btree_seekleaf() ERROR");
+	befs_debug(sb, "<--- %s ERROR", __func__);
 	return BEFS_ERR;
 }
 
diff --git a/fs/befs/datastream.c b/fs/befs/datastream.c
index 59096b5e0fc7..c467bebd50af 100644
--- a/fs/befs/datastream.c
+++ b/fs/befs/datastream.c
@@ -52,26 +52,25 @@ befs_read_datastream(struct super_block *sb, befs_data_stream * ds,
 	befs_block_run run;
 	befs_blocknr_t block;	/* block coresponding to pos */
 
-	befs_debug(sb, "---> befs_read_datastream() %Lu", pos);
+	befs_debug(sb, "---> %s %llu", __func__, pos);
 	block = pos >> BEFS_SB(sb)->block_shift;
 	if (off)
 		*off = pos - (block << BEFS_SB(sb)->block_shift);
 
 	if (befs_fblock2brun(sb, ds, block, &run) != BEFS_OK) {
 		befs_error(sb, "BeFS: Error finding disk addr of block %lu",
-			   block);
-		befs_debug(sb, "<--- befs_read_datastream() ERROR");
+			   (unsigned long)block);
+		befs_debug(sb, "<--- %s ERROR", __func__);
 		return NULL;
 	}
 	bh = befs_bread_iaddr(sb, run);
 	if (!bh) {
 		befs_error(sb, "BeFS: Error reading block %lu from datastream",
-			   block);
+			   (unsigned long)block);
 		return NULL;
 	}
 
-	befs_debug(sb, "<--- befs_read_datastream() read data, starting at %Lu",
-		   pos);
+	befs_debug(sb, "<--- %s read data, starting at %llu", __func__, pos);
 
 	return bh;
 }
@@ -106,7 +105,8 @@ befs_fblock2brun(struct super_block *sb, befs_data_stream * data,
 	} else {
 		befs_error(sb,
 			   "befs_fblock2brun() was asked to find block %lu, "
-			   "which is not mapped by the datastream\n", fblock);
+			   "which is not mapped by the datastream\n",
+			   (unsigned long)fblock);
 		err = BEFS_ERR;
 	}
 	return err;
@@ -128,14 +128,14 @@ befs_read_lsymlink(struct super_block * sb, befs_data_stream * ds, void *buff,
 	befs_off_t bytes_read = 0;	/* bytes readed */
 	u16 plen;
 	struct buffer_head *bh = NULL;
-	befs_debug(sb, "---> befs_read_lsymlink() length: %Lu", len);
+	befs_debug(sb, "---> %s length: %llu", __func__, len);
 
 	while (bytes_read < len) {
 		bh = befs_read_datastream(sb, ds, bytes_read, NULL);
 		if (!bh) {
 			befs_error(sb, "BeFS: Error reading datastream block "
-				   "starting from %Lu", bytes_read);
-			befs_debug(sb, "<--- befs_read_lsymlink() ERROR");
+				   "starting from %llu", bytes_read);
+			befs_debug(sb, "<--- %s ERROR", __func__);
 			return bytes_read;
 
 		}
@@ -146,7 +146,8 @@ befs_read_lsymlink(struct super_block * sb, befs_data_stream * ds, void *buff,
 		bytes_read += plen;
 	}
 
-	befs_debug(sb, "<--- befs_read_lsymlink() read %u bytes", bytes_read);
+	befs_debug(sb, "<--- %s read %u bytes", __func__, (unsigned int)
+		   bytes_read);
 	return bytes_read;
 }
 
@@ -169,7 +170,7 @@ befs_count_blocks(struct super_block * sb, befs_data_stream * ds)
 	befs_blocknr_t metablocks;	/* FS metadata blocks */
 	befs_sb_info *befs_sb = BEFS_SB(sb);
 
-	befs_debug(sb, "---> befs_count_blocks()");
+	befs_debug(sb, "---> %s", __func__);
 
 	datablocks = ds->size >> befs_sb->block_shift;
 	if (ds->size & (befs_sb->block_size - 1))
@@ -206,7 +207,7 @@ befs_count_blocks(struct super_block * sb, befs_data_stream * ds)
 	}
 
 	blocks = datablocks + metablocks;
-	befs_debug(sb, "<--- befs_count_blocks() %u blocks", blocks);
+	befs_debug(sb, "<--- %s %u blocks", __func__, (unsigned int)blocks);
 
 	return blocks;
 }
@@ -251,11 +252,11 @@ befs_find_brun_direct(struct super_block *sb, befs_data_stream * data,
 	befs_blocknr_t max_block =
 	    data->max_direct_range >> BEFS_SB(sb)->block_shift;
 
-	befs_debug(sb, "---> befs_find_brun_direct(), find %lu", blockno);
+	befs_debug(sb, "---> %s, find %lu", __func__, (unsigned long)blockno);
 
 	if (blockno > max_block) {
-		befs_error(sb, "befs_find_brun_direct() passed block outside of"
-			   "direct region");
+		befs_error(sb, "%s passed block outside of direct region",
+			   __func__);
 		return BEFS_ERR;
 	}
 
@@ -267,13 +268,14 @@ befs_find_brun_direct(struct super_block *sb, befs_data_stream * data,
 			run->start = array[i].start + offset;
 			run->len = array[i].len - offset;
 
-			befs_debug(sb, "---> befs_find_brun_direct(), "
-				   "found %lu at direct[%d]", blockno, i);
+			befs_debug(sb, "---> %s, "
+				   "found %lu at direct[%d]", __func__,
+				   (unsigned long)blockno, i);
 			return BEFS_OK;
 		}
 	}
 
-	befs_debug(sb, "---> befs_find_brun_direct() ERROR");
+	befs_debug(sb, "---> %s ERROR", __func__);
 	return BEFS_ERR;
 }
 
@@ -316,7 +318,7 @@ befs_find_brun_indirect(struct super_block *sb,
 	befs_blocknr_t indirblockno = iaddr2blockno(sb, &indirect);
 	int arraylen = befs_iaddrs_per_block(sb);
 
-	befs_debug(sb, "---> befs_find_brun_indirect(), find %lu", blockno);
+	befs_debug(sb, "---> %s, find %lu", __func__, (unsigned long)blockno);
 
 	indir_start_blk = data->max_direct_range >> BEFS_SB(sb)->block_shift;
 	search_blk = blockno - indir_start_blk;
@@ -325,10 +327,9 @@ befs_find_brun_indirect(struct super_block *sb,
 	for (i = 0; i < indirect.len; i++) {
 		indirblock = befs_bread(sb, indirblockno + i);
 		if (indirblock == NULL) {
-			befs_debug(sb,
-				   "---> befs_find_brun_indirect() failed to "
-				   "read disk block %lu from the indirect brun",
-				   indirblockno + i);
+			befs_debug(sb, "---> %s failed to read "
+				   "disk block %lu from the indirect brun",
+				   __func__, (unsigned long)indirblockno + i);
 			return BEFS_ERR;
 		}
 
@@ -348,9 +349,10 @@ befs_find_brun_indirect(struct super_block *sb,
 
 				brelse(indirblock);
 				befs_debug(sb,
-					   "<--- befs_find_brun_indirect() found "
-					   "file block %lu at indirect[%d]",
-					   blockno, j + (i * arraylen));
+					   "<--- %s found file block "
+					   "%lu at indirect[%d]", __func__,
+					   (unsigned long)blockno,
+					   j + (i * arraylen));
 				return BEFS_OK;
 			}
 			sum += len;
@@ -360,10 +362,10 @@ befs_find_brun_indirect(struct super_block *sb,
 	}
 
 	/* Only fallthrough is an error */
-	befs_error(sb, "BeFS: befs_find_brun_indirect() failed to find "
-		   "file block %lu", blockno);
+	befs_error(sb, "BeFS: %s failed to find "
+		   "file block %lu", __func__, (unsigned long)blockno);
 
-	befs_debug(sb, "<--- befs_find_brun_indirect() ERROR");
+	befs_debug(sb, "<--- %s ERROR", __func__);
 	return BEFS_ERR;
 }
 
@@ -444,7 +446,7 @@ befs_find_brun_dblindirect(struct super_block *sb,
 	size_t diblklen = iblklen * befs_iaddrs_per_block(sb)
 	    * BEFS_DBLINDIR_BRUN_LEN;
 
-	befs_debug(sb, "---> befs_find_brun_dblindirect() find %lu", blockno);
+	befs_debug(sb, "---> %s find %lu", __func__, (unsigned long)blockno);
 
 	/* First, discover which of the double_indir->indir blocks
 	 * contains pos. Then figure out how much of pos that
@@ -460,8 +462,9 @@ befs_find_brun_dblindirect(struct super_block *sb,
 	dbl_which_block = dblindir_indx / befs_iaddrs_per_block(sb);
 	if (dbl_which_block > data->double_indirect.len) {
 		befs_error(sb, "The double-indirect index calculated by "
-			   "befs_read_brun_dblindirect(), %d, is outside the range "
-			   "of the double-indirect block", dblindir_indx);
+			   "%s, %d, is outside the range "
+			   "of the double-indirect block", __func__,
+			   dblindir_indx);
 		return BEFS_ERR;
 	}
 
@@ -469,10 +472,10 @@ befs_find_brun_dblindirect(struct super_block *sb,
 	    befs_bread(sb, iaddr2blockno(sb, &data->double_indirect) +
 					dbl_which_block);
 	if (dbl_indir_block == NULL) {
-		befs_error(sb, "befs_read_brun_dblindirect() couldn't read the "
-			   "double-indirect block at blockno %lu",
-			   iaddr2blockno(sb,
-					 &data->double_indirect) +
+		befs_error(sb, "%s couldn't read the "
+			   "double-indirect block at blockno %lu", __func__,
+			   (unsigned long)
+			   iaddr2blockno(sb, &data->double_indirect) +
 			   dbl_which_block);
 		brelse(dbl_indir_block);
 		return BEFS_ERR;
@@ -489,16 +492,16 @@ befs_find_brun_dblindirect(struct super_block *sb,
 	which_block = indir_indx / befs_iaddrs_per_block(sb);
 	if (which_block > indir_run.len) {
 		befs_error(sb, "The indirect index calculated by "
-			   "befs_read_brun_dblindirect(), %d, is outside the range "
-			   "of the indirect block", indir_indx);
+			   "%s, %d, is outside the range "
+			   "of the indirect block", __func__, indir_indx);
 		return BEFS_ERR;
 	}
 
 	indir_block =
 	    befs_bread(sb, iaddr2blockno(sb, &indir_run) + which_block);
 	if (indir_block == NULL) {
-		befs_error(sb, "befs_read_brun_dblindirect() couldn't read the "
-			   "indirect block at blockno %lu",
+		befs_error(sb, "%s couldn't read the indirect block "
+			   "at blockno %lu", __func__, (unsigned long)
 			   iaddr2blockno(sb, &indir_run) + which_block);
 		brelse(indir_block);
 		return BEFS_ERR;
@@ -519,7 +522,7 @@ befs_find_brun_dblindirect(struct super_block *sb,
 	run->len -= offset;
 
 	befs_debug(sb, "Found file block %lu in double_indirect[%d][%d],"
-		   " double_indirect_leftover = %lu",
+		   " double_indirect_leftover = %lu", (unsigned long)
 		   blockno, dblindir_indx, indir_indx, dblindir_leftover);
 
 	return BEFS_OK;
diff --git a/fs/befs/debug.c b/fs/befs/debug.c
index 622e73775c83..4de7cffcd662 100644
--- a/fs/befs/debug.c
+++ b/fs/befs/debug.c
@@ -10,6 +10,7 @@
  * debug functions
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #ifdef __KERNEL__
 
 #include <stdarg.h>
@@ -23,43 +24,30 @@
 
 #include "befs.h"
 
-#define ERRBUFSIZE 1024
-
 void
 befs_error(const struct super_block *sb, const char *fmt, ...)
 {
+	struct va_format vaf;
 	va_list args;
-	char *err_buf = kmalloc(ERRBUFSIZE, GFP_KERNEL);
-	if (err_buf == NULL) {
-		printk(KERN_ERR "could not allocate %d bytes\n", ERRBUFSIZE);
-		return;
-	}
 
 	va_start(args, fmt);
-	vsnprintf(err_buf, ERRBUFSIZE, fmt, args);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	pr_err("(%s): %pV\n", sb->s_id, &vaf);
 	va_end(args);
-
-	printk(KERN_ERR "BeFS(%s): %s\n", sb->s_id, err_buf);
-	kfree(err_buf);
 }
 
 void
 befs_warning(const struct super_block *sb, const char *fmt, ...)
 {
+	struct va_format vaf;
 	va_list args;
-	char *err_buf = kmalloc(ERRBUFSIZE, GFP_KERNEL);
-	if (err_buf == NULL) {
-		printk(KERN_ERR "could not allocate %d bytes\n", ERRBUFSIZE);
-		return;
-	}
 
 	va_start(args, fmt);
-	vsnprintf(err_buf, ERRBUFSIZE, fmt, args);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	pr_warn("(%s): %pV\n", sb->s_id, &vaf);
 	va_end(args);
-
-	printk(KERN_WARNING "BeFS(%s): %s\n", sb->s_id, err_buf);
-
-	kfree(err_buf);
 }
 
 void
@@ -67,25 +55,13 @@ befs_debug(const struct super_block *sb, const char *fmt, ...)
 {
 #ifdef CONFIG_BEFS_DEBUG
 
+	struct va_format vaf;
 	va_list args;
-	char *err_buf = NULL;
-
-	if (BEFS_SB(sb)->mount_opts.debug) {
-		err_buf = kmalloc(ERRBUFSIZE, GFP_KERNEL);
-		if (err_buf == NULL) {
-			printk(KERN_ERR "could not allocate %d bytes\n",
-				ERRBUFSIZE);
-			return;
-		}
-
-		va_start(args, fmt);
-		vsnprintf(err_buf, ERRBUFSIZE, fmt, args);
-		va_end(args);
-
-		printk(KERN_DEBUG "BeFS(%s): %s\n", sb->s_id, err_buf);
-
-		kfree(err_buf);
-	}
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	pr_debug("(%s): %pV\n", sb->s_id, &vaf);
+	va_end(args);
 
 #endif				//CONFIG_BEFS_DEBUG
 }
@@ -109,9 +85,9 @@ befs_dump_inode(const struct super_block *sb, befs_inode * inode)
 	befs_debug(sb, "  gid %u", fs32_to_cpu(sb, inode->gid));
 	befs_debug(sb, "  mode %08x", fs32_to_cpu(sb, inode->mode));
 	befs_debug(sb, "  flags %08x", fs32_to_cpu(sb, inode->flags));
-	befs_debug(sb, "  create_time %Lu",
+	befs_debug(sb, "  create_time %llu",
 		   fs64_to_cpu(sb, inode->create_time));
-	befs_debug(sb, "  last_modified_time %Lu",
+	befs_debug(sb, "  last_modified_time %llu",
 		   fs64_to_cpu(sb, inode->last_modified_time));
 
 	tmp_run = fsrun_to_cpu(sb, inode->parent);
@@ -137,7 +113,7 @@ befs_dump_inode(const struct super_block *sb, befs_inode * inode)
 				   tmp_run.allocation_group, tmp_run.start,
 				   tmp_run.len);
 		}
-		befs_debug(sb, "  max_direct_range %Lu",
+		befs_debug(sb, "  max_direct_range %llu",
 			   fs64_to_cpu(sb,
 				       inode->data.datastream.
 				       max_direct_range));
@@ -147,7 +123,7 @@ befs_dump_inode(const struct super_block *sb, befs_inode * inode)
 			   tmp_run.allocation_group,
 			   tmp_run.start, tmp_run.len);
 
-		befs_debug(sb, "  max_indirect_range %Lu",
+		befs_debug(sb, "  max_indirect_range %llu",
 			   fs64_to_cpu(sb,
 				       inode->data.datastream.
 				       max_indirect_range));
@@ -158,12 +134,12 @@ befs_dump_inode(const struct super_block *sb, befs_inode * inode)
 			   tmp_run.allocation_group, tmp_run.start,
 			   tmp_run.len);
 
-		befs_debug(sb, "  max_double_indirect_range %Lu",
+		befs_debug(sb, "  max_double_indirect_range %llu",
 			   fs64_to_cpu(sb,
 				       inode->data.datastream.
 				       max_double_indirect_range));
 
-		befs_debug(sb, "  size %Lu",
+		befs_debug(sb, "  size %llu",
 			   fs64_to_cpu(sb, inode->data.datastream.size));
 	}
 
@@ -191,8 +167,8 @@ befs_dump_super_block(const struct super_block *sb, befs_super_block * sup)
 	befs_debug(sb, "  block_size %u", fs32_to_cpu(sb, sup->block_size));
 	befs_debug(sb, "  block_shift %u", fs32_to_cpu(sb, sup->block_shift));
 
-	befs_debug(sb, "  num_blocks %Lu", fs64_to_cpu(sb, sup->num_blocks));
-	befs_debug(sb, "  used_blocks %Lu", fs64_to_cpu(sb, sup->used_blocks));
+	befs_debug(sb, "  num_blocks %llu", fs64_to_cpu(sb, sup->num_blocks));
+	befs_debug(sb, "  used_blocks %llu", fs64_to_cpu(sb, sup->used_blocks));
 
 	befs_debug(sb, "  magic2 %08x", fs32_to_cpu(sb, sup->magic2));
 	befs_debug(sb, "  blocks_per_ag %u",
@@ -206,8 +182,8 @@ befs_dump_super_block(const struct super_block *sb, befs_super_block * sup)
 	befs_debug(sb, "  log_blocks %u, %hu, %hu",
 		   tmp_run.allocation_group, tmp_run.start, tmp_run.len);
 
-	befs_debug(sb, "  log_start %Ld", fs64_to_cpu(sb, sup->log_start));
-	befs_debug(sb, "  log_end %Ld", fs64_to_cpu(sb, sup->log_end));
+	befs_debug(sb, "  log_start %lld", fs64_to_cpu(sb, sup->log_start));
+	befs_debug(sb, "  log_end %lld", fs64_to_cpu(sb, sup->log_end));
 
 	befs_debug(sb, "  magic3 %08x", fs32_to_cpu(sb, sup->magic3));
 
diff --git a/fs/befs/inode.c b/fs/befs/inode.c
index 94c17f9a9576..fa4b718de597 100644
--- a/fs/befs/inode.c
+++ b/fs/befs/inode.c
@@ -25,7 +25,8 @@ befs_check_inode(struct super_block *sb, befs_inode * raw_inode,
 	/* check magic header. */
 	if (magic1 != BEFS_INODE_MAGIC1) {
 		befs_error(sb,
-			   "Inode has a bad magic header - inode = %lu", inode);
+			   "Inode has a bad magic header - inode = %lu",
+			   (unsigned long)inode);
 		return BEFS_BAD_INODE;
 	}
 
@@ -34,8 +35,8 @@ befs_check_inode(struct super_block *sb, befs_inode * raw_inode,
 	 */
 	if (inode != iaddr2blockno(sb, &ino_num)) {
 		befs_error(sb, "inode blocknr field disagrees with vfs "
-			   "VFS: %lu, Inode %lu",
-			   inode, iaddr2blockno(sb, &ino_num));
+			   "VFS: %lu, Inode %lu", (unsigned long)
+			   inode, (unsigned long)iaddr2blockno(sb, &ino_num));
 		return BEFS_BAD_INODE;
 	}
 
@@ -44,7 +45,8 @@ befs_check_inode(struct super_block *sb, befs_inode * raw_inode,
 	 */
 
 	if (!(flags & BEFS_INODE_IN_USE)) {
-		befs_error(sb, "inode is not used - inode = %lu", inode);
+		befs_error(sb, "inode is not used - inode = %lu",
+			   (unsigned long)inode);
 		return BEFS_BAD_INODE;
 	}
 
diff --git a/fs/befs/io.c b/fs/befs/io.c
index ddef98aa255d..0408a3d601d0 100644
--- a/fs/befs/io.c
+++ b/fs/befs/io.c
@@ -30,9 +30,9 @@ befs_bread_iaddr(struct super_block *sb, befs_inode_addr iaddr)
 	befs_blocknr_t block = 0;
 	befs_sb_info *befs_sb = BEFS_SB(sb);
 
-	befs_debug(sb, "---> Enter befs_read_iaddr() "
-		   "[%u, %hu, %hu]",
-		   iaddr.allocation_group, iaddr.start, iaddr.len);
+	befs_debug(sb, "---> Enter %s "
+		   "[%u, %hu, %hu]", __func__, iaddr.allocation_group,
+		   iaddr.start, iaddr.len);
 
 	if (iaddr.allocation_group > befs_sb->num_ags) {
 		befs_error(sb, "BEFS: Invalid allocation group %u, max is %u",
@@ -42,20 +42,21 @@ befs_bread_iaddr(struct super_block *sb, befs_inode_addr iaddr)
 
 	block = iaddr2blockno(sb, &iaddr);
 
-	befs_debug(sb, "befs_read_iaddr: offset = %lu", block);
+	befs_debug(sb, "%s: offset = %lu", __func__, (unsigned long)block);
 
 	bh = sb_bread(sb, block);
 
 	if (bh == NULL) {
-		befs_error(sb, "Failed to read block %lu", block);
+		befs_error(sb, "Failed to read block %lu",
+			   (unsigned long)block);
 		goto error;
 	}
 
-	befs_debug(sb, "<--- befs_read_iaddr()");
+	befs_debug(sb, "<--- %s", __func__);
 	return bh;
 
       error:
-	befs_debug(sb, "<--- befs_read_iaddr() ERROR");
+	befs_debug(sb, "<--- %s ERROR", __func__);
 	return NULL;
 }
 
@@ -64,20 +65,21 @@ befs_bread(struct super_block *sb, befs_blocknr_t block)
 {
 	struct buffer_head *bh = NULL;
 
-	befs_debug(sb, "---> Enter befs_read() %Lu", block);
+	befs_debug(sb, "---> Enter %s %lu", __func__, (unsigned long)block);
 
 	bh = sb_bread(sb, block);
 
 	if (bh == NULL) {
-		befs_error(sb, "Failed to read block %lu", block);
+		befs_error(sb, "Failed to read block %lu",
+			   (unsigned long)block);
 		goto error;
 	}
 
-	befs_debug(sb, "<--- befs_read()");
+	befs_debug(sb, "<--- %s", __func__);
 
 	return bh;
 
       error:
-	befs_debug(sb, "<--- befs_read() ERROR");
+	befs_debug(sb, "<--- %s ERROR", __func__);
 	return NULL;
 }
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 56d70c8a89b0..d626756ff721 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -5,6 +5,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
@@ -39,7 +41,6 @@ static struct dentry *befs_lookup(struct inode *, struct dentry *, unsigned int)
 static struct inode *befs_iget(struct super_block *, unsigned long);
 static struct inode *befs_alloc_inode(struct super_block *sb);
 static void befs_destroy_inode(struct inode *inode);
-static int befs_init_inodecache(void);
 static void befs_destroy_inodecache(void);
 static void *befs_follow_link(struct dentry *, struct nameidata *);
 static void *befs_fast_follow_link(struct dentry *, struct nameidata *);
@@ -131,26 +132,28 @@ befs_get_block(struct inode *inode, sector_t block,
 	ulong disk_off;
 
 	befs_debug(sb, "---> befs_get_block() for inode %lu, block %ld",
-		   inode->i_ino, block);
+		   (unsigned long)inode->i_ino, (long)block);
 
 	if (block < 0) {
 		befs_error(sb, "befs_get_block() was asked for a block "
 			   "number less than zero: block %ld in inode %lu",
-			   block, inode->i_ino);
+			   (long)block, (unsigned long)inode->i_ino);
 		return -EIO;
 	}
 
 	if (create) {
 		befs_error(sb, "befs_get_block() was asked to write to "
-			   "block %ld in inode %lu", block, inode->i_ino);
+			   "block %ld in inode %lu", (long)block,
+			   (unsigned long)inode->i_ino);
 		return -EPERM;
 	}
 
 	res = befs_fblock2brun(sb, ds, block, &run);
 	if (res != BEFS_OK) {
 		befs_error(sb,
-			   "<--- befs_get_block() for inode %lu, block "
-			   "%ld ERROR", inode->i_ino, block);
+			   "<--- %s for inode %lu, block %ld ERROR",
+			   __func__, (unsigned long)inode->i_ino,
+			   (long)block);
 		return -EFBIG;
 	}
 
@@ -158,8 +161,9 @@ befs_get_block(struct inode *inode, sector_t block,
 
 	map_bh(bh_result, inode->i_sb, disk_off);
 
-	befs_debug(sb, "<--- befs_get_block() for inode %lu, block %ld, "
-		   "disk address %lu", inode->i_ino, block, disk_off);
+	befs_debug(sb, "<--- %s for inode %lu, block %ld, disk address %lu",
+		  __func__, (unsigned long)inode->i_ino, (long)block,
+		  (unsigned long)disk_off);
 
 	return 0;
 }
@@ -176,15 +180,15 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 	char *utfname;
 	const char *name = dentry->d_name.name;
 
-	befs_debug(sb, "---> befs_lookup() "
-		   "name %s inode %ld", dentry->d_name.name, dir->i_ino);
+	befs_debug(sb, "---> %s name %s inode %ld", __func__,
+		   dentry->d_name.name, dir->i_ino);
 
 	/* Convert to UTF-8 */
 	if (BEFS_SB(sb)->nls) {
 		ret =
 		    befs_nls2utf(sb, name, strlen(name), &utfname, &utfnamelen);
 		if (ret < 0) {
-			befs_debug(sb, "<--- befs_lookup() ERROR");
+			befs_debug(sb, "<--- %s ERROR", __func__);
 			return ERR_PTR(ret);
 		}
 		ret = befs_btree_find(sb, ds, utfname, &offset);
@@ -195,12 +199,12 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 	}
 
 	if (ret == BEFS_BT_NOT_FOUND) {
-		befs_debug(sb, "<--- befs_lookup() %s not found",
+		befs_debug(sb, "<--- %s %s not found", __func__,
 			   dentry->d_name.name);
 		return ERR_PTR(-ENOENT);
 
 	} else if (ret != BEFS_OK || offset == 0) {
-		befs_warning(sb, "<--- befs_lookup() Error");
+		befs_warning(sb, "<--- %s Error", __func__);
 		return ERR_PTR(-ENODATA);
 	}
 
@@ -210,7 +214,7 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 
 	d_add(dentry, inode);
 
-	befs_debug(sb, "<--- befs_lookup()");
+	befs_debug(sb, "<--- %s", __func__);
 
 	return NULL;
 }
@@ -228,26 +232,25 @@ befs_readdir(struct file *file, struct dir_context *ctx)
 	char keybuf[BEFS_NAME_LEN + 1];
 	const char *dirname = file->f_path.dentry->d_name.name;
 
-	befs_debug(sb, "---> befs_readdir() "
-		   "name %s, inode %ld, ctx->pos %Ld",
-		   dirname, inode->i_ino, ctx->pos);
+	befs_debug(sb, "---> %s name %s, inode %ld, ctx->pos %lld",
+		  __func__, dirname, inode->i_ino, ctx->pos);
 
 more:
 	result = befs_btree_read(sb, ds, ctx->pos, BEFS_NAME_LEN + 1,
 				 keybuf, &keysize, &value);
 
 	if (result == BEFS_ERR) {
-		befs_debug(sb, "<--- befs_readdir() ERROR");
+		befs_debug(sb, "<--- %s ERROR", __func__);
 		befs_error(sb, "IO error reading %s (inode %lu)",
 			   dirname, inode->i_ino);
 		return -EIO;
 
 	} else if (result == BEFS_BT_END) {
-		befs_debug(sb, "<--- befs_readdir() END");
+		befs_debug(sb, "<--- %s END", __func__);
 		return 0;
 
 	} else if (result == BEFS_BT_EMPTY) {
-		befs_debug(sb, "<--- befs_readdir() Empty directory");
+		befs_debug(sb, "<--- %s Empty directory", __func__);
 		return 0;
 	}
 
@@ -260,7 +263,7 @@ more:
 		result =
 		    befs_utf2nls(sb, keybuf, keysize, &nlsname, &nlsnamelen);
 		if (result < 0) {
-			befs_debug(sb, "<--- befs_readdir() ERROR");
+			befs_debug(sb, "<--- %s ERROR", __func__);
 			return result;
 		}
 		if (!dir_emit(ctx, nlsname, nlsnamelen,
@@ -277,7 +280,7 @@ more:
 	ctx->pos++;
 	goto more;
 
-	befs_debug(sb, "<--- befs_readdir() pos %Ld", ctx->pos);
+	befs_debug(sb, "<--- %s pos %lld", __func__, ctx->pos);
 
 	return 0;
 }
@@ -321,7 +324,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
 	struct inode *inode;
 	long ret = -EIO;
 
-	befs_debug(sb, "---> befs_read_inode() " "inode = %lu", ino);
+	befs_debug(sb, "---> %s inode = %lu", __func__, ino);
 
 	inode = iget_locked(sb, ino);
 	if (!inode)
@@ -428,7 +431,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
 	}
 
 	brelse(bh);
-	befs_debug(sb, "<--- befs_read_inode()");
+	befs_debug(sb, "<--- %s", __func__);
 	unlock_new_inode(inode);
 	return inode;
 
@@ -437,7 +440,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
 
       unacquire_none:
 	iget_failed(inode);
-	befs_debug(sb, "<--- befs_read_inode() - Bad inode");
+	befs_debug(sb, "<--- %s - Bad inode", __func__);
 	return ERR_PTR(ret);
 }
 
@@ -445,7 +448,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
  *
  * Taken from NFS implementation by Al Viro.
  */
-static int
+static int __init
 befs_init_inodecache(void)
 {
 	befs_inode_cachep = kmem_cache_create("befs_inode_cache",
@@ -454,11 +457,9 @@ befs_init_inodecache(void)
 						SLAB_MEM_SPREAD),
 					      init_once);
 	if (befs_inode_cachep == NULL) {
-		printk(KERN_ERR "befs_init_inodecache: "
-		       "Couldn't initialize inode slabcache\n");
+		pr_err("%s: Couldn't initialize inode slabcache\n", __func__);
 		return -ENOMEM;
 	}
-
 	return 0;
 }
 
@@ -544,16 +545,16 @@ befs_utf2nls(struct super_block *sb, const char *in,
 	 */
 	int maxlen = in_len + 1;
 
-	befs_debug(sb, "---> utf2nls()");
+	befs_debug(sb, "---> %s", __func__);
 
 	if (!nls) {
-		befs_error(sb, "befs_utf2nls called with no NLS table loaded");
+		befs_error(sb, "%s called with no NLS table loaded", __func__);
 		return -EINVAL;
 	}
 
 	*out = result = kmalloc(maxlen, GFP_NOFS);
 	if (!*out) {
-		befs_error(sb, "befs_utf2nls() cannot allocate memory");
+		befs_error(sb, "%s cannot allocate memory", __func__);
 		*out_len = 0;
 		return -ENOMEM;
 	}
@@ -575,14 +576,14 @@ befs_utf2nls(struct super_block *sb, const char *in,
 	result[o] = '\0';
 	*out_len = o;
 
-	befs_debug(sb, "<--- utf2nls()");
+	befs_debug(sb, "<--- %s", __func__);
 
 	return o;
 
       conv_err:
 	befs_error(sb, "Name using character set %s contains a character that "
 		   "cannot be converted to unicode.", nls->charset);
-	befs_debug(sb, "<--- utf2nls()");
+	befs_debug(sb, "<--- %s", __func__);
 	kfree(result);
 	return -EILSEQ;
 }
@@ -623,16 +624,17 @@ befs_nls2utf(struct super_block *sb, const char *in,
 	 * in special cases */
 	int maxlen = (3 * in_len) + 1;
 
-	befs_debug(sb, "---> nls2utf()\n");
+	befs_debug(sb, "---> %s\n", __func__);
 
 	if (!nls) {
-		befs_error(sb, "befs_nls2utf called with no NLS table loaded.");
+		befs_error(sb, "%s called with no NLS table loaded.",
+			   __func__);
 		return -EINVAL;
 	}
 
 	*out = result = kmalloc(maxlen, GFP_NOFS);
 	if (!*out) {
-		befs_error(sb, "befs_nls2utf() cannot allocate memory");
+		befs_error(sb, "%s cannot allocate memory", __func__);
 		*out_len = 0;
 		return -ENOMEM;
 	}
@@ -653,14 +655,14 @@ befs_nls2utf(struct super_block *sb, const char *in,
 	result[o] = '\0';
 	*out_len = o;
 
-	befs_debug(sb, "<--- nls2utf()");
+	befs_debug(sb, "<--- %s", __func__);
 
 	return i;
 
       conv_err:
 	befs_error(sb, "Name using charecter set %s contains a charecter that "
 		   "cannot be converted to unicode.", nls->charset);
-	befs_debug(sb, "<--- nls2utf()");
+	befs_debug(sb, "<--- %s", __func__);
 	kfree(result);
 	return -EILSEQ;
 }
@@ -715,8 +717,8 @@ parse_options(char *options, befs_mount_options * opts)
 			if (option >= 0)
 				uid = make_kuid(current_user_ns(), option);
 			if (!uid_valid(uid)) {
-				printk(KERN_ERR "BeFS: Invalid uid %d, "
-						"using default\n", option);
+				pr_err("Invalid uid %d, "
+				       "using default\n", option);
 				break;
 			}
 			opts->uid = uid;
@@ -729,8 +731,8 @@ parse_options(char *options, befs_mount_options * opts)
 			if (option >= 0)
 				gid = make_kgid(current_user_ns(), option);
 			if (!gid_valid(gid)) {
-				printk(KERN_ERR "BeFS: Invalid gid %d, "
-						"using default\n", option);
+				pr_err("Invalid gid %d, "
+				       "using default\n", option);
 				break;
 			}
 			opts->gid = gid;
@@ -740,8 +742,8 @@ parse_options(char *options, befs_mount_options * opts)
 			kfree(opts->iocharset);
 			opts->iocharset = match_strdup(&args[0]);
 			if (!opts->iocharset) {
-				printk(KERN_ERR "BeFS: allocation failure for "
-						"iocharset string\n");
+				pr_err("allocation failure for "
+				       "iocharset string\n");
 				return 0;
 			}
 			break;
@@ -749,8 +751,8 @@ parse_options(char *options, befs_mount_options * opts)
 			opts->debug = 1;
 			break;
 		default:
-			printk(KERN_ERR "BeFS: Unrecognized mount option \"%s\" "
-					"or missing value\n", p);
+			pr_err("Unrecognized mount option \"%s\" "
+			       "or missing value\n", p);
 			return 0;
 		}
 	}
@@ -791,22 +793,20 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
 
 	save_mount_options(sb, data);
 
-	sb->s_fs_info = kmalloc(sizeof (*befs_sb), GFP_KERNEL);
+	sb->s_fs_info = kzalloc(sizeof(*befs_sb), GFP_KERNEL);
 	if (sb->s_fs_info == NULL) {
-		printk(KERN_ERR
-		       "BeFS(%s): Unable to allocate memory for private "
+		pr_err("(%s): Unable to allocate memory for private "
 		       "portion of superblock. Bailing.\n", sb->s_id);
 		goto unacquire_none;
 	}
 	befs_sb = BEFS_SB(sb);
-	memset(befs_sb, 0, sizeof(befs_sb_info));
 
 	if (!parse_options((char *) data, &befs_sb->mount_opts)) {
 		befs_error(sb, "cannot parse mount options");
 		goto unacquire_priv_sbp;
 	}
 
-	befs_debug(sb, "---> befs_fill_super()");
+	befs_debug(sb, "---> %s", __func__);
 
 #ifndef CONFIG_BEFS_RW
 	if (!(sb->s_flags & MS_RDONLY)) {
@@ -854,7 +854,7 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
 		goto unacquire_priv_sbp;
 
 	if( befs_sb->num_blocks > ~((sector_t)0) ) {
-		befs_error(sb, "blocks count: %Lu "
+		befs_error(sb, "blocks count: %llu "
 			"is larger than the host can use",
 			befs_sb->num_blocks);
 		goto unacquire_priv_sbp;
@@ -925,7 +925,7 @@ befs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct super_block *sb = dentry->d_sb;
 	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
-	befs_debug(sb, "---> befs_statfs()");
+	befs_debug(sb, "---> %s", __func__);
 
 	buf->f_type = BEFS_SUPER_MAGIC;
 	buf->f_bsize = sb->s_blocksize;
@@ -938,7 +938,7 @@ befs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_fsid.val[1] = (u32)(id >> 32);
 	buf->f_namelen = BEFS_NAME_LEN;
 
-	befs_debug(sb, "<--- befs_statfs()");
+	befs_debug(sb, "<--- %s", __func__);
 
 	return 0;
 }
@@ -964,7 +964,7 @@ init_befs_fs(void)
 {
 	int err;
 
-	printk(KERN_INFO "BeFS version: %s\n", BEFS_VERSION);
+	pr_info("version: %s\n", BEFS_VERSION);
 
 	err = befs_init_inodecache();
 	if (err)
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 8defc6b3f9a2..7041ac35ace8 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -172,7 +172,7 @@ static void bfs_evict_inode(struct inode *inode)
 
 	dprintf("ino=%08lx\n", ino);
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
 
@@ -266,7 +266,7 @@ static void init_once(void *foo)
 	inode_init_once(&bi->vfs_inode);
 }
 
-static int init_inodecache(void)
+static int __init init_inodecache(void)
 {
 	bfs_inode_cachep = kmem_cache_create("bfs_inode_cache",
 					     sizeof(struct bfs_inode_info),
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 67be2951b98a..c2e5d4647345 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -46,10 +46,15 @@
 #endif
 
 static int load_elf_binary(struct linux_binprm *bprm);
-static int load_elf_library(struct file *);
 static unsigned long elf_map(struct file *, unsigned long, struct elf_phdr *,
 				int, int, unsigned long);
 
+#ifdef CONFIG_USELIB
+static int load_elf_library(struct file *);
+#else
+#define load_elf_library NULL
+#endif
+
 /*
  * If we don't support core dumping, then supply a NULL so we
  * don't even try.
@@ -140,6 +145,25 @@ static int padzero(unsigned long elf_bss)
 #define ELF_BASE_PLATFORM NULL
 #endif
 
+/*
+ * Use get_random_int() to implement AT_RANDOM while avoiding depletion
+ * of the entropy pool.
+ */
+static void get_atrandom_bytes(unsigned char *buf, size_t nbytes)
+{
+	unsigned char *p = buf;
+
+	while (nbytes) {
+		unsigned int random_variable;
+		size_t chunk = min(nbytes, sizeof(random_variable));
+
+		random_variable = get_random_int();
+		memcpy(p, &random_variable, chunk);
+		p += chunk;
+		nbytes -= chunk;
+	}
+}
+
 static int
 create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 		unsigned long load_addr, unsigned long interp_load_addr)
@@ -201,7 +225,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 	/*
 	 * Generate 16 random bytes for userspace PRNG seeding.
 	 */
-	get_random_bytes(k_rand_bytes, sizeof(k_rand_bytes));
+	get_atrandom_bytes(k_rand_bytes, sizeof(k_rand_bytes));
 	u_rand_bytes = (elf_addr_t __user *)
 		       STACK_ALLOC(p, sizeof(k_rand_bytes));
 	if (__copy_to_user(u_rand_bytes, k_rand_bytes, sizeof(k_rand_bytes)))
@@ -579,7 +603,6 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	unsigned long start_code, end_code, start_data, end_data;
 	unsigned long reloc_func_desc __maybe_unused = 0;
 	int executable_stack = EXSTACK_DEFAULT;
-	unsigned long def_flags = 0;
 	struct pt_regs *regs = current_pt_regs();
 	struct {
 		struct elfhdr elf_ex;
@@ -719,9 +742,6 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	if (retval)
 		goto out_free_dentry;
 
-	/* OK, This is the point of no return */
-	current->mm->def_flags = def_flags;
-
 	/* Do this immediately, since STACK_TOP as used in setup_arg_pages
 	   may depend on the personality.  */
 	SET_PERSONALITY(loc->elf_ex);
@@ -1005,6 +1025,7 @@ out_free_ph:
 	goto out;
 }
 
+#ifdef CONFIG_USELIB
 /* This is really simpleminded and specialized - we are loading an
    a.out library that is given an ELF header. */
 static int load_elf_library(struct file *file)
@@ -1083,6 +1104,7 @@ out_free_ph:
 out:
 	return error;
 }
+#endif /* #ifdef CONFIG_USELIB */
 
 #ifdef CONFIG_ELF_CORE
 /*
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1e86823a9cbd..ba0d2b05bb78 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -83,7 +83,7 @@ void kill_bdev(struct block_device *bdev)
 {
 	struct address_space *mapping = bdev->bd_inode->i_mapping;
 
-	if (mapping->nrpages == 0)
+	if (mapping->nrpages == 0 && mapping->nrshadows == 0)
 		return;
 
 	invalidate_bh_lrus();
@@ -419,7 +419,7 @@ static void bdev_evict_inode(struct inode *inode)
 {
 	struct block_device *bdev = &BDEV_I(inode)->bdev;
 	struct list_head *p;
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	invalidate_inode_buffers(inode); /* is it needed here? */
 	clear_inode(inode);
 	spin_lock(&bdev_lock);
@@ -1523,7 +1523,7 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		ssize_t err;
 
 		err = generic_write_sync(file, pos, ret);
-		if (err < 0 && ret > 0)
+		if (err < 0)
 			ret = err;
 	}
 	blk_finish_plug(&plug);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b01fb6c527e3..d43c544d3b68 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -472,7 +472,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		rcu_read_lock();
 		page = radix_tree_lookup(&mapping->page_tree, pg_index);
 		rcu_read_unlock();
-		if (page) {
+		if (page && !radix_tree_exceptional_entry(page)) {
 			misses++;
 			if (misses > 4)
 				break;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 036f506cabd8..c660527af838 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1826,7 +1826,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	BTRFS_I(inode)->last_sub_trans = root->log_transid;
 	if (num_written > 0) {
 		err = generic_write_sync(file, pos, num_written);
-		if (err < 0 && num_written > 0)
+		if (err < 0)
 			num_written = err;
 	}
 
@@ -2025,6 +2025,7 @@ out:
 
 static const struct vm_operations_struct btrfs_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= btrfs_page_mkwrite,
 	.remap_pages	= generic_file_remap_pages,
 };
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 572d40b793ee..06e9a4152b14 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4596,7 +4596,7 @@ static void evict_inode_truncate_pages(struct inode *inode)
 	struct rb_node *node;
 
 	ASSERT(inode->i_state & I_FREEING);
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	write_lock(&map_tree->lock);
 	while (!RB_EMPTY_ROOT(&map_tree->map)) {
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index ebaff368120d..4b1fb5ca65b8 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -265,24 +265,22 @@ static int cachefiles_read_backing_file_one(struct cachefiles_object *object,
 				goto nomem_monitor;
 		}
 
-		ret = add_to_page_cache(newpage, bmapping,
-					netpage->index, cachefiles_gfp);
+		ret = add_to_page_cache_lru(newpage, bmapping,
+					    netpage->index, cachefiles_gfp);
 		if (ret == 0)
 			goto installed_new_backing_page;
 		if (ret != -EEXIST)
 			goto nomem_page;
 	}
 
-	/* we've installed a new backing page, so now we need to add it
-	 * to the LRU list and start it reading */
+	/* we've installed a new backing page, so now we need to start
+	 * it reading */
 installed_new_backing_page:
 	_debug("- new %p", newpage);
 
 	backpage = newpage;
 	newpage = NULL;
 
-	lru_cache_add_file(backpage);
-
 read_backing_page:
 	ret = bmapping->a_ops->readpage(NULL, backpage);
 	if (ret < 0)
@@ -510,24 +508,23 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 					goto nomem;
 			}
 
-			ret = add_to_page_cache(newpage, bmapping,
-						netpage->index, cachefiles_gfp);
+			ret = add_to_page_cache_lru(newpage, bmapping,
+						    netpage->index,
+						    cachefiles_gfp);
 			if (ret == 0)
 				goto installed_new_backing_page;
 			if (ret != -EEXIST)
 				goto nomem;
 		}
 
-		/* we've installed a new backing page, so now we need to add it
-		 * to the LRU list and start it reading */
+		/* we've installed a new backing page, so now we need
+		 * to start it reading */
 	installed_new_backing_page:
 		_debug("- new %p", newpage);
 
 		backpage = newpage;
 		newpage = NULL;
 
-		lru_cache_add_file(backpage);
-
 	reread_backing_page:
 		ret = bmapping->a_ops->readpage(NULL, backpage);
 		if (ret < 0)
@@ -538,8 +535,8 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 	monitor_backing_page:
 		_debug("- monitor add");
 
-		ret = add_to_page_cache(netpage, op->mapping, netpage->index,
-					cachefiles_gfp);
+		ret = add_to_page_cache_lru(netpage, op->mapping,
+					    netpage->index, cachefiles_gfp);
 		if (ret < 0) {
 			if (ret == -EEXIST) {
 				page_cache_release(netpage);
@@ -549,8 +546,6 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 			goto nomem;
 		}
 
-		lru_cache_add_file(netpage);
-
 		/* install a monitor */
 		page_cache_get(netpage);
 		monitor->netfs_page = netpage;
@@ -613,8 +608,8 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 	backing_page_already_uptodate:
 		_debug("- uptodate");
 
-		ret = add_to_page_cache(netpage, op->mapping, netpage->index,
-					cachefiles_gfp);
+		ret = add_to_page_cache_lru(netpage, op->mapping,
+					    netpage->index, cachefiles_gfp);
 		if (ret < 0) {
 			if (ret == -EEXIST) {
 				page_cache_release(netpage);
@@ -631,8 +626,6 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 
 		fscache_mark_page_cached(op, netpage);
 
-		lru_cache_add_file(netpage);
-
 		/* the netpage is unlocked and marked up to date here */
 		fscache_end_io(op, netpage, 0);
 		page_cache_release(netpage);
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 900f7afa887f..ade4f3f47e80 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -291,7 +291,7 @@ cifs_destroy_inode(struct inode *inode)
 static void
 cifs_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	cifs_fscache_release_inode_cookie(inode);
 }
@@ -1018,7 +1018,7 @@ cifs_init_once(void *inode)
 	init_rwsem(&cifsi->lock_sem);
 }
 
-static int
+static int __init
 cifs_init_inodecache(void)
 {
 	cifs_inode_cachep = kmem_cache_create("cifs_inode_cache",
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 87c4dd072cde..7a29f3291fe0 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3123,6 +3123,7 @@ cifs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 static struct vm_operations_struct cifs_file_vm_ops = {
 	.fault = filemap_fault,
+	.map_pages = filemap_map_pages,
 	.page_mkwrite = cifs_page_mkwrite,
 	.remap_pages = generic_file_remap_pages,
 };
diff --git a/fs/coda/coda_int.h b/fs/coda/coda_int.h
index b7143cf783ac..381c993b1427 100644
--- a/fs/coda/coda_int.h
+++ b/fs/coda/coda_int.h
@@ -10,7 +10,7 @@ extern int coda_hard;
 extern int coda_fake_statfs;
 
 void coda_destroy_inodecache(void);
-int coda_init_inodecache(void);
+int __init coda_init_inodecache(void);
 int coda_fsync(struct file *coda_file, loff_t start, loff_t end, int datasync);
 void coda_sysctl_init(void);
 void coda_sysctl_clean(void);
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 3f48000ef1a5..d9c7751f10ac 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -73,7 +73,7 @@ static void init_once(void *foo)
 	inode_init_once(&ei->vfs_inode);
 }
 
-int coda_init_inodecache(void)
+int __init coda_init_inodecache(void)
 {
 	coda_inode_cachep = kmem_cache_create("coda_inode_cache",
 				sizeof(struct coda_inode_info),
@@ -251,7 +251,7 @@ static void coda_put_super(struct super_block *sb)
 
 static void coda_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	coda_cache_clear_inode(inode);
 }
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index a2759112563c..ddcfe590b8a8 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -195,8 +195,7 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i
 		struct page *page = NULL;
 
 		if (blocknr + i < devsize) {
-			page = read_mapping_page_async(mapping, blocknr + i,
-									NULL);
+			page = read_mapping_page(mapping, blocknr + i, NULL);
 			/* synchronous error? */
 			if (IS_ERR(page))
 				page = NULL;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index a701752dd750..31ba0935e32e 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -664,7 +664,6 @@ static inline int dio_new_bio(struct dio *dio, struct dio_submit *sdio,
 		goto out;
 	sector = start_sector << (sdio->blkbits - 9);
 	nr_pages = min(sdio->pages_in_io, bio_get_nr_vecs(map_bh->b_bdev));
-	nr_pages = min(nr_pages, BIO_MAX_PAGES);
 	BUG_ON(nr_pages <= 0);
 	dio_bio_alloc(dio, sdio, map_bh->b_bdev, sector, nr_pages);
 	sdio->boundary = 0;
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 9fd702f5bfb2..9280202e488c 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -59,10 +59,22 @@ int drop_caches_sysctl_handler(ctl_table *table, int write,
 	if (ret)
 		return ret;
 	if (write) {
-		if (sysctl_drop_caches & 1)
+		static int stfu;
+
+		if (sysctl_drop_caches & 1) {
 			iterate_supers(drop_pagecache_sb, NULL);
-		if (sysctl_drop_caches & 2)
+			count_vm_event(DROP_PAGECACHE);
+		}
+		if (sysctl_drop_caches & 2) {
 			drop_slab();
+			count_vm_event(DROP_SLAB);
+		}
+		if (!stfu) {
+			pr_info("%s (%d): drop_caches: %d\n",
+				current->comm, task_pid_nr(current),
+				sysctl_drop_caches);
+		}
+		stfu |= sysctl_drop_caches & 4;
 	}
 	return 0;
 }
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index e879cf8ff0b1..afa1b81c3418 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -132,7 +132,7 @@ static int ecryptfs_statfs(struct dentry *dentry, struct kstatfs *buf)
  */
 static void ecryptfs_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	iput(ecryptfs_inode_to_lower(inode));
 }
diff --git a/fs/efs/super.c b/fs/efs/super.c
index 103bbd820b87..3befcc9f5d63 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -91,7 +91,7 @@ static void init_once(void *foo)
 	inode_init_once(&ei->vfs_inode);
 }
 
-static int init_inodecache(void)
+static int __init init_inodecache(void)
 {
 	efs_inode_cachep = kmem_cache_create("efs_inode_cache",
 				sizeof(struct efs_inode_info),
diff --git a/fs/exec.c b/fs/exec.c
index 4f59402fdda5..b60ccf969a8b 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -26,6 +26,7 @@
 #include <linux/file.h>
 #include <linux/fdtable.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/stat.h>
 #include <linux/fcntl.h>
 #include <linux/swap.h>
@@ -97,6 +98,7 @@ static inline void put_binfmt(struct linux_binfmt * fmt)
 	module_put(fmt->module);
 }
 
+#ifdef CONFIG_USELIB
 /*
  * Note that a shared library must be both readable and executable due to
  * security reasons.
@@ -156,6 +158,7 @@ exit:
 out:
   	return error;
 }
+#endif /* #ifdef CONFIG_USELIB */
 
 #ifdef CONFIG_MMU
 /*
@@ -820,7 +823,7 @@ EXPORT_SYMBOL(read_code);
 static int exec_mmap(struct mm_struct *mm)
 {
 	struct task_struct *tsk;
-	struct mm_struct * old_mm, *active_mm;
+	struct mm_struct *old_mm, *active_mm;
 
 	/* Notify parent that we're no longer interested in the old VM */
 	tsk = current;
@@ -846,6 +849,8 @@ static int exec_mmap(struct mm_struct *mm)
 	tsk->mm = mm;
 	tsk->active_mm = mm;
 	activate_mm(active_mm, mm);
+	tsk->mm->vmacache_seqnum = 0;
+	vmacache_flush(tsk);
 	task_unlock(tsk);
 	if (old_mm) {
 		up_read(&old_mm->mmap_sem);
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index ee4317faccb1..d1c244d67667 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -1486,7 +1486,7 @@ void exofs_evict_inode(struct inode *inode)
 	struct ore_io_state *ios;
 	int ret;
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	/* TODO: should do better here */
 	if (inode->i_nlink || is_bad_inode(inode))
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 94ed36849b71..b1d2a4675d42 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -78,7 +78,7 @@ void ext2_evict_inode(struct inode * inode)
 		dquot_drop(inode);
 	}
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	if (want_delete) {
 		sb_start_intwrite(inode->i_sb);
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 77042a2e017c..f5157d0d1b43 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -228,7 +228,7 @@ void ext3_evict_inode (struct inode *inode)
 		log_wait_commit(journal, commit_tid);
 		filemap_write_and_wait(&inode->i_data);
 	}
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	ext3_discard_reservation(inode);
 	rsv = ei->i_block_alloc_info;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 1a5073959f32..4e508fc83dcf 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -153,7 +153,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
 		ssize_t err;
 
 		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
-		if (err < 0 && ret > 0)
+		if (err < 0)
 			ret = err;
 	}
 	blk_finish_plug(&plug);
@@ -200,6 +200,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
 
 static const struct vm_operations_struct ext4_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite   = ext4_page_mkwrite,
 	.remap_pages	= generic_file_remap_pages,
 };
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 4c67172cfc69..5b0d2c7d5408 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -215,7 +215,7 @@ void ext4_evict_inode(struct inode *inode)
 			jbd2_complete_transaction(journal, commit_tid);
 			filemap_write_and_wait(&inode->i_data);
 		}
-		truncate_inode_pages(&inode->i_data, 0);
+		truncate_inode_pages_final(&inode->i_data);
 
 		WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
 		goto no_delete;
@@ -226,7 +226,7 @@ void ext4_evict_inode(struct inode *inode)
 
 	if (ext4_should_order_data(inode))
 		ext4_begin_ordered_truncate(inode, 0);
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
 	if (is_bad_inode(inode))
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 6ba26680c468..6f97fabfc220 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -84,6 +84,7 @@ out:
 
 static const struct vm_operations_struct f2fs_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= f2fs_vm_page_mkwrite,
 	.remap_pages	= generic_file_remap_pages,
 };
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 0d8e4a2302b7..ee829d360468 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -267,7 +267,7 @@ void f2fs_evict_inode(struct inode *inode)
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 
 	trace_f2fs_evict_inode(inode);
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	if (inode->i_ino == F2FS_NODE_INO(sbi) ||
 			inode->i_ino == F2FS_META_INO(sbi))
diff --git a/fs/fat/cache.c b/fs/fat/cache.c
index 91ad9e1c9441..e26bc9a22ac9 100644
--- a/fs/fat/cache.c
+++ b/fs/fat/cache.c
@@ -303,6 +303,31 @@ static int fat_bmap_cluster(struct inode *inode, int cluster)
 	return dclus;
 }
 
+static int fat_get_mapped_cluster(struct inode *inode, sector_t sector,
+				  sector_t last_block,
+				  unsigned long *mapped_blocks, sector_t *bmap)
+{
+	struct super_block *sb = inode->i_sb;
+	struct msdos_sb_info *sbi = MSDOS_SB(sb);
+	int cluster, offset;
+
+	cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits);
+	offset  = sector & (sbi->sec_per_clus - 1);
+	cluster = fat_bmap_cluster(inode, cluster);
+
+	if (cluster < 0)
+		return cluster;
+
+	else if (cluster) {
+		*bmap = fat_clus_to_blknr(sbi, cluster) + offset;
+		*mapped_blocks = sbi->sec_per_clus - offset;
+		if (*mapped_blocks > last_block - sector)
+			*mapped_blocks = last_block - sector;
+	}
+
+	return 0;
+}
+
 int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
 	     unsigned long *mapped_blocks, int create)
 {
@@ -311,7 +336,6 @@ int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
 	const unsigned long blocksize = sb->s_blocksize;
 	const unsigned char blocksize_bits = sb->s_blocksize_bits;
 	sector_t last_block;
-	int cluster, offset;
 
 	*phys = 0;
 	*mapped_blocks = 0;
@@ -329,25 +353,39 @@ int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
 			return 0;
 
 		/*
-		 * ->mmu_private can access on only allocation path.
-		 * (caller must hold ->i_mutex)
+		 * Both ->mmu_private and ->i_disksize can access
+		 * on only allocation path. (caller must hold ->i_mutex)
 		 */
-		last_block = (MSDOS_I(inode)->mmu_private + (blocksize - 1))
+		last_block = (MSDOS_I(inode)->i_disksize + (blocksize - 1))
 			>> blocksize_bits;
 		if (sector >= last_block)
 			return 0;
 	}
 
-	cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits);
-	offset  = sector & (sbi->sec_per_clus - 1);
-	cluster = fat_bmap_cluster(inode, cluster);
-	if (cluster < 0)
-		return cluster;
-	else if (cluster) {
-		*phys = fat_clus_to_blknr(sbi, cluster) + offset;
-		*mapped_blocks = sbi->sec_per_clus - offset;
-		if (*mapped_blocks > last_block - sector)
-			*mapped_blocks = last_block - sector;
-	}
-	return 0;
+	return fat_get_mapped_cluster(inode, sector, last_block, mapped_blocks,
+				      phys);
+}
+
+int fat_bmap2(struct inode *inode, sector_t sector,
+	      unsigned long *mapped_blocks, struct buffer_head *bh_result,
+	      int create, sector_t *bmap)
+{
+	struct super_block *sb = inode->i_sb;
+	sector_t last_block;
+	const unsigned long blocksize = sb->s_blocksize;
+	const unsigned char blocksize_bits = sb->s_blocksize_bits;
+
+	BUG_ON(create != 0);
+
+	*bmap = 0;
+	*mapped_blocks = 0;
+
+	last_block = (MSDOS_I(inode)->i_disksize + (blocksize - 1))
+		>> blocksize_bits;
+
+	if (sector >= last_block)
+		return 0;
+
+	return fat_get_mapped_cluster(inode, sector, last_block, mapped_blocks,
+				      bmap);
 }
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index 7c31f4bc74a9..7270bdbca9c3 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -118,7 +118,8 @@ struct msdos_inode_info {
 	unsigned int cache_valid_id;
 
 	/* NOTE: mmu_private is 64bits, so must hold ->i_mutex to access */
-	loff_t mmu_private;	/* physically allocated size */
+	loff_t mmu_private;	/* physically allocated size (initialized) */
+	loff_t i_disksize;	/* physically allocated size (uninitialized) */
 
 	int i_start;		/* first cluster or 0 */
 	int i_logstart;		/* logical first cluster */
@@ -289,6 +290,9 @@ extern int fat_get_cluster(struct inode *inode, int cluster,
 			   int *fclus, int *dclus);
 extern int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
 		    unsigned long *mapped_blocks, int create);
+extern int fat_bmap2(struct inode *inode, sector_t sector,
+		     unsigned long *mapped_blocks,
+		     struct buffer_head *bh_result, int create, sector_t *bmap);
 
 /* fat/dir.c */
 extern const struct file_operations fat_dir_operations;
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 9b104f543056..e33c8a2cb99c 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -17,8 +17,12 @@
 #include <linux/blkdev.h>
 #include <linux/fsnotify.h>
 #include <linux/security.h>
+#include <linux/falloc.h>
 #include "fat.h"
 
+static long fat_fallocate(struct file *file, int mode,
+			  loff_t offset, loff_t len);
+
 static int fat_ioctl_get_attributes(struct inode *inode, u32 __user *user_attr)
 {
 	u32 attr;
@@ -182,6 +186,7 @@ const struct file_operations fat_file_operations = {
 #endif
 	.fsync		= fat_file_fsync,
 	.splice_read	= generic_file_splice_read,
+	.fallocate	= fat_fallocate,
 };
 
 static int fat_cont_expand(struct inode *inode, loff_t size)
@@ -220,6 +225,75 @@ out:
 	return err;
 }
 
+/*
+ * Preallocate space for a file. This implements fat's fallocate file
+ * operation, which gets called from sys_fallocate system call. User
+ * space requests len bytes at offset. If FALLOC_FL_KEEP_SIZE is set
+ * we just allocate clusters without zeroing them out. Otherwise we
+ * allocate and zero out clusters via an expanding truncate.
+ */
+static long fat_fallocate(struct file *file, int mode,
+			  loff_t offset, loff_t len)
+{
+	int cluster;
+	int nr_cluster; /* Number of clusters to be allocated */
+	loff_t mm_bytes; /* Number of bytes to be allocated for file */
+	struct inode *inode = file->f_mapping->host;
+	struct super_block *sb = inode->i_sb;
+	struct msdos_sb_info *sbi = MSDOS_SB(sb);
+	int err = 0;
+
+	/* No support for hole punch or other fallocate flags. */
+	if (mode & ~FALLOC_FL_KEEP_SIZE)
+		return -EOPNOTSUPP;
+
+	/* No support for dir */
+	if (!S_ISREG(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	mutex_lock(&inode->i_mutex);
+	if ((offset + len) <= MSDOS_I(inode)->i_disksize)
+		goto error;
+
+	err = inode_newsize_ok(inode, (len + offset));
+	if (err)
+		goto error;
+
+	if (mode & FALLOC_FL_KEEP_SIZE) {
+		/* First compute the number of clusters to be allocated */
+		mm_bytes = offset + len - round_up(MSDOS_I(inode)->i_disksize,
+			sbi->cluster_size);
+		nr_cluster = (mm_bytes + (sbi->cluster_size - 1)) >>
+			sbi->cluster_bits;
+
+		/* Start the allocation.We are not zeroing out the clusters */
+		while (nr_cluster-- > 0) {
+			err = fat_alloc_clusters(inode, &cluster, 1);
+			if (err) {
+				fat_msg(sb, KERN_ERR,
+					"fat_fallocate(): fat_alloc_clusters() error");
+				goto error;
+			}
+			err = fat_chain_add(inode, cluster, 1);
+			if (err) {
+				fat_free_clusters(inode, cluster);
+				goto error;
+			}
+			MSDOS_I(inode)->i_disksize += sbi->cluster_size;
+		}
+	} else {
+		/* This is just an expanding truncate */
+		err = fat_cont_expand(inode, (offset + len));
+		if (err)
+			fat_msg(sb, KERN_ERR,
+				"fat_fallocate(): fat_cont_expand() error");
+	}
+
+error:
+	mutex_unlock(&inode->i_mutex);
+	return err;
+}
+
 /* Free all clusters after the skip'th cluster. */
 static int fat_free(struct inode *inode, int skip)
 {
@@ -300,8 +374,10 @@ void fat_truncate_blocks(struct inode *inode, loff_t offset)
 	 * This protects against truncating a file bigger than it was then
 	 * trying to write into the hole.
 	 */
-	if (MSDOS_I(inode)->mmu_private > offset)
+	if (MSDOS_I(inode)->i_disksize > offset) {
 		MSDOS_I(inode)->mmu_private = offset;
+		MSDOS_I(inode)->i_disksize = offset;
+	}
 
 	nr_clusters = (offset + (cluster_size - 1)) >> sbi->cluster_bits;
 
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 343e477c6dcb..992e8cb1132c 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -54,6 +54,25 @@ static int fat_add_cluster(struct inode *inode)
 	return err;
 }
 
+static void check_fallocated_region(struct inode *inode, sector_t iblock,
+		unsigned long *max_blocks, struct buffer_head *bh_result)
+{
+	struct super_block *sb = inode->i_sb;
+	sector_t last_block, disk_block;
+	const unsigned long blocksize = sb->s_blocksize;
+	const unsigned char blocksize_bits = sb->s_blocksize_bits;
+
+	last_block = (MSDOS_I(inode)->mmu_private + (blocksize - 1))
+		>> blocksize_bits;
+	disk_block = (MSDOS_I(inode)->i_disksize + (blocksize - 1))
+		>> blocksize_bits;
+	if (iblock >= last_block && iblock <= disk_block) {
+		MSDOS_I(inode)->mmu_private += *max_blocks << blocksize_bits;
+		set_buffer_new(bh_result);
+	}
+
+}
+
 static inline int __fat_get_block(struct inode *inode, sector_t iblock,
 				  unsigned long *max_blocks,
 				  struct buffer_head *bh_result, int create)
@@ -68,8 +87,11 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock,
 	if (err)
 		return err;
 	if (phys) {
-		map_bh(bh_result, sb, phys);
 		*max_blocks = min(mapped_blocks, *max_blocks);
+		if (create)
+			check_fallocated_region(inode, iblock, max_blocks,
+				bh_result);
+		map_bh(bh_result, sb, phys);
 		return 0;
 	}
 	if (!create)
@@ -93,6 +115,7 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock,
 
 	*max_blocks = min(mapped_blocks, *max_blocks);
 	MSDOS_I(inode)->mmu_private += *max_blocks << sb->s_blocksize_bits;
+	MSDOS_I(inode)->i_disksize = MSDOS_I(inode)->mmu_private;
 
 	err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create);
 	if (err)
@@ -206,6 +229,13 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
 		loff_t size = offset + iov_length(iov, nr_segs);
 		if (MSDOS_I(inode)->mmu_private < size)
 			return 0;
+
+		/*
+		 * In case of writing in fallocated region, return 0 and
+		 * fallback to buffered write.
+		 */
+		if (MSDOS_I(inode)->i_disksize > MSDOS_I(inode)->mmu_private)
+			return 0;
 	}
 
 	/*
@@ -220,13 +250,36 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
 	return ret;
 }
 
+static int fat_get_block_bmap(struct inode *inode, sector_t iblock,
+		struct buffer_head *bh_result, int create)
+{
+	struct super_block *sb = inode->i_sb;
+	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
+	int err;
+	sector_t bmap;
+	unsigned long mapped_blocks;
+
+	err = fat_bmap2(inode, iblock, &mapped_blocks, bh_result, create,
+			&bmap);
+	if (err)
+		return err;
+
+	if (bmap) {
+		map_bh(bh_result, sb, bmap);
+		max_blocks = min(mapped_blocks, max_blocks);
+	}
+
+	bh_result->b_size = max_blocks << sb->s_blocksize_bits;
+	return 0;
+}
+
 static sector_t _fat_bmap(struct address_space *mapping, sector_t block)
 {
 	sector_t blocknr;
 
 	/* fat_get_cluster() assumes the requested blocknr isn't truncated. */
 	down_read(&MSDOS_I(mapping->host)->truncate_lock);
-	blocknr = generic_block_bmap(mapping, block, fat_get_block);
+	blocknr = generic_block_bmap(mapping, block, fat_get_block_bmap);
 	up_read(&MSDOS_I(mapping->host)->truncate_lock);
 
 	return blocknr;
@@ -407,7 +460,6 @@ int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
 		error = fat_calc_dir_size(inode);
 		if (error < 0)
 			return error;
-		MSDOS_I(inode)->mmu_private = inode->i_size;
 
 		set_nlink(inode, fat_subdirs(inode));
 	} else { /* not a directory */
@@ -422,8 +474,12 @@ int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
 		inode->i_op = &fat_file_inode_operations;
 		inode->i_fop = &fat_file_operations;
 		inode->i_mapping->a_ops = &fat_aops;
-		MSDOS_I(inode)->mmu_private = inode->i_size;
 	}
+
+	MSDOS_I(inode)->mmu_private = inode->i_size;
+	MSDOS_I(inode)->i_disksize = round_up(inode->i_size,
+		inode->i_sb->s_blocksize);
+
 	if (de->attr & ATTR_SYS) {
 		if (sbi->options.sys_immutable)
 			inode->i_flags |= S_IMMUTABLE;
@@ -488,12 +544,34 @@ out:
 
 EXPORT_SYMBOL_GPL(fat_build_inode);
 
+static int __fat_write_inode(struct inode *inode, int wait);
 static void fat_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	if (!inode->i_nlink) {
 		inode->i_size = 0;
 		fat_truncate_blocks(inode, 0);
+	} else {
+		/* Release unwritten fallocated blocks on inode eviction. */
+		if (MSDOS_I(inode)->i_disksize >
+		    round_up(MSDOS_I(inode)->mmu_private,
+				inode->i_sb->s_blocksize)) {
+			int err;
+			fat_truncate_blocks(inode, MSDOS_I(inode)->mmu_private);
+			/* Fallocate results in updating the i_start/iogstart
+			 * for the zero byte file. So, make it return to
+			 * original state during evict and commit it to avoid
+			 * any corruption on the next access to the cluster
+			 * chain for the file.
+			 */
+			err = __fat_write_inode(inode, inode_needs_sync(inode));
+			if (err) {
+				fat_msg(inode->i_sb, KERN_WARNING, "Failed to "
+				"update on disk inode for unused fallocated "
+				"blocks, inode could be corrupted. Please run "
+				"fsck");
+			}
+		}
 	}
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
@@ -1225,6 +1303,7 @@ static int fat_read_root(struct inode *inode)
 			   & ~((loff_t)sbi->cluster_size - 1)) >> 9;
 	MSDOS_I(inode)->i_logstart = 0;
 	MSDOS_I(inode)->mmu_private = inode->i_size;
+	MSDOS_I(inode)->i_disksize = inode->i_size;
 
 	fat_save_attrs(inode, ATTR_DIR);
 	inode->i_mtime.tv_sec = inode->i_atime.tv_sec = inode->i_ctime.tv_sec = 0;
diff --git a/fs/filesystems.c b/fs/filesystems.c
index 92567d95ba6a..5797d45a78cb 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -121,6 +121,7 @@ int unregister_filesystem(struct file_system_type * fs)
 
 EXPORT_SYMBOL(unregister_filesystem);
 
+#ifdef CONFIG_SYSFS_SYSCALL
 static int fs_index(const char __user * __name)
 {
 	struct file_system_type * tmp;
@@ -199,6 +200,7 @@ SYSCALL_DEFINE3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2)
 	}
 	return retval;
 }
+#endif
 
 int __init get_filesystem_list(char *buf)
 {
diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c
index f47df72cef17..363e3ae25f6b 100644
--- a/fs/freevxfs/vxfs_inode.c
+++ b/fs/freevxfs/vxfs_inode.c
@@ -354,7 +354,7 @@ static void vxfs_i_callback(struct rcu_head *head)
 void
 vxfs_evict_inode(struct inode *ip)
 {
-	truncate_inode_pages(&ip->i_data, 0);
+	truncate_inode_pages_final(&ip->i_data);
 	clear_inode(ip);
 	call_rcu(&ip->i_rcu, vxfs_i_callback);
 }
diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c
index 25d4099a4aea..99c7f0a37af4 100644
--- a/fs/freevxfs/vxfs_lookup.c
+++ b/fs/freevxfs/vxfs_lookup.c
@@ -192,7 +192,7 @@ vxfs_inode_by_name(struct inode *dip, struct dentry *dp)
  * vxfs_lookup - lookup pathname component
  * @dip:	dir in which we lookup
  * @dp:		dentry we lookup
- * @nd:		lookup nameidata
+ * @flags:	lookup flags
  *
  * Description:
  *   vxfs_lookup tries to lookup the pathname component described
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 648d5db14e2c..be568b7311d6 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -91,16 +91,29 @@ static inline struct inode *wb_inode(struct list_head *head)
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage);
 
+static void bdi_wakeup_thread(struct backing_dev_info *bdi)
+{
+	spin_lock_bh(&bdi->wb_lock);
+	if (test_bit(BDI_registered, &bdi->state))
+		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+	spin_unlock_bh(&bdi->wb_lock);
+}
+
 static void bdi_queue_work(struct backing_dev_info *bdi,
 			   struct wb_writeback_work *work)
 {
 	trace_writeback_queue(bdi, work);
 
 	spin_lock_bh(&bdi->wb_lock);
+	if (!test_bit(BDI_registered, &bdi->state)) {
+		if (work->done)
+			complete(work->done);
+		goto out_unlock;
+	}
 	list_add_tail(&work->list, &bdi->work_list);
-	spin_unlock_bh(&bdi->wb_lock);
-
 	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+out_unlock:
+	spin_unlock_bh(&bdi->wb_lock);
 }
 
 static void
@@ -116,7 +129,7 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work) {
 		trace_writeback_nowork(bdi);
-		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+		bdi_wakeup_thread(bdi);
 		return;
 	}
 
@@ -163,7 +176,7 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi)
 	 * writeback as soon as there is no other work to do.
 	 */
 	trace_writeback_wake_background(bdi);
-	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+	bdi_wakeup_thread(bdi);
 }
 
 /*
@@ -1019,7 +1032,7 @@ void bdi_writeback_workfn(struct work_struct *work)
 	current->flags |= PF_SWAPWRITE;
 
 	if (likely(!current_is_workqueue_rescuer() ||
-		   list_empty(&bdi->bdi_list))) {
+		   !test_bit(BDI_registered, &bdi->state))) {
 		/*
 		 * The normal path.  Keep writing back @bdi until its
 		 * work_list is empty.  Note that this path is also taken
@@ -1041,10 +1054,10 @@ void bdi_writeback_workfn(struct work_struct *work)
 		trace_writeback_pages_written(pages_written);
 	}
 
-	if (!list_empty(&bdi->work_list) ||
-	    (wb_has_dirty_io(wb) && dirty_writeback_interval))
-		queue_delayed_work(bdi_wq, &wb->dwork,
-			msecs_to_jiffies(dirty_writeback_interval * 10));
+	if (!list_empty(&bdi->work_list))
+		mod_delayed_work(bdi_wq, &wb->dwork, 0);
+	else if (wb_has_dirty_io(wb) && dirty_writeback_interval)
+		bdi_wakeup_thread_delayed(bdi);
 
 	current->flags &= ~PF_SWAPWRITE;
 }
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 65df7d8be4f5..48992cac714b 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2117,6 +2117,7 @@ static int fuse_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 static const struct vm_operations_struct fuse_file_vm_ops = {
 	.close		= fuse_vma_close,
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= fuse_page_mkwrite,
 	.remap_pages	= generic_file_remap_pages,
 };
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index a4233c858fb4..8d611696fcad 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -123,7 +123,7 @@ static void fuse_destroy_inode(struct inode *inode)
 
 static void fuse_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	if (inode->i_sb->s_flags & MS_ACTIVE) {
 		struct fuse_conn *fc = get_fuse_conn(inode);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 6c794085abac..80d67253623c 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -494,6 +494,7 @@ out:
 
 static const struct vm_operations_struct gfs2_vm_ops = {
 	.fault = filemap_fault,
+	.map_pages = filemap_map_pages,
 	.page_mkwrite = gfs2_page_mkwrite,
 	.remap_pages = generic_file_remap_pages,
 };
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 47a67367ba1a..de8afad89e51 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1557,7 +1557,7 @@ out_unlock:
 		fs_warn(sdp, "gfs2_evict_inode: %d\n", error);
 out:
 	/* Case 3 starts here */
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	gfs2_rs_delete(ip, NULL);
 	gfs2_ordered_del_inode(ip);
 	clear_inode(inode);
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 380ab31b5e0f..9e2fecd62f62 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -547,7 +547,7 @@ out:
 
 void hfs_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	if (HFS_IS_RSRC(inode) && HFS_I(inode)->rsrc_inode) {
 		HFS_I(HFS_I(inode)->rsrc_inode)->rsrc_inode = NULL;
diff --git a/fs/hfsplus/attributes.c b/fs/hfsplus/attributes.c
index 0f47890299c4..caf89a7be0a1 100644
--- a/fs/hfsplus/attributes.c
+++ b/fs/hfsplus/attributes.c
@@ -11,7 +11,7 @@
 
 static struct kmem_cache *hfsplus_attr_tree_cachep;
 
-int hfsplus_create_attr_tree_cache(void)
+int __init hfsplus_create_attr_tree_cache(void)
 {
 	if (hfsplus_attr_tree_cachep)
 		return -EEXIST;
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index 32602c667b4a..7892e6fddb66 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -38,21 +38,30 @@ int hfsplus_cat_bin_cmp_key(const hfsplus_btree_key *k1,
 	return hfsplus_strcmp(&k1->cat.name, &k2->cat.name);
 }
 
-void hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key,
-			   u32 parent, struct qstr *str)
+/* Generates key for catalog file/folders record. */
+int hfsplus_cat_build_key(struct super_block *sb,
+		hfsplus_btree_key *key, u32 parent, struct qstr *str)
 {
-	int len;
+	int len, err;
 
 	key->cat.parent = cpu_to_be32(parent);
-	if (str) {
-		hfsplus_asc2uni(sb, &key->cat.name, HFSPLUS_MAX_STRLEN,
-					str->name, str->len);
-		len = be16_to_cpu(key->cat.name.length);
-	} else {
-		key->cat.name.length = 0;
-		len = 0;
-	}
+	err = hfsplus_asc2uni(sb, &key->cat.name, HFSPLUS_MAX_STRLEN,
+			str->name, str->len);
+	if (unlikely(err < 0))
+		return err;
+
+	len = be16_to_cpu(key->cat.name.length);
 	key->key_len = cpu_to_be16(6 + 2 * len);
+	return 0;
+}
+
+/* Generates key for catalog thread record. */
+void hfsplus_cat_build_key_with_cnid(struct super_block *sb,
+			hfsplus_btree_key *key, u32 parent)
+{
+	key->cat.parent = cpu_to_be32(parent);
+	key->cat.name.length = 0;
+	key->key_len = cpu_to_be16(6);
 }
 
 static void hfsplus_cat_build_key_uni(hfsplus_btree_key *key, u32 parent,
@@ -167,11 +176,16 @@ static int hfsplus_fill_cat_thread(struct super_block *sb,
 				   hfsplus_cat_entry *entry, int type,
 				   u32 parentid, struct qstr *str)
 {
+	int err;
+
 	entry->type = cpu_to_be16(type);
 	entry->thread.reserved = 0;
 	entry->thread.parentID = cpu_to_be32(parentid);
-	hfsplus_asc2uni(sb, &entry->thread.nodeName, HFSPLUS_MAX_STRLEN,
+	err = hfsplus_asc2uni(sb, &entry->thread.nodeName, HFSPLUS_MAX_STRLEN,
 				str->name, str->len);
+	if (unlikely(err < 0))
+		return err;
+
 	return 10 + be16_to_cpu(entry->thread.nodeName.length) * 2;
 }
 
@@ -183,7 +197,7 @@ int hfsplus_find_cat(struct super_block *sb, u32 cnid,
 	int err;
 	u16 type;
 
-	hfsplus_cat_build_key(sb, fd->search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd->search_key, cnid);
 	err = hfs_brec_read(fd, &tmp, sizeof(hfsplus_cat_entry));
 	if (err)
 		return err;
@@ -250,11 +264,16 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir,
 	if (err)
 		return err;
 
-	hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid);
 	entry_size = hfsplus_fill_cat_thread(sb, &entry,
 		S_ISDIR(inode->i_mode) ?
 			HFSPLUS_FOLDER_THREAD : HFSPLUS_FILE_THREAD,
 		dir->i_ino, str);
+	if (unlikely(entry_size < 0)) {
+		err = entry_size;
+		goto err2;
+	}
+
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err != -ENOENT) {
 		if (!err)
@@ -265,7 +284,10 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir,
 	if (err)
 		goto err2;
 
-	hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
+	err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
+	if (unlikely(err))
+		goto err1;
+
 	entry_size = hfsplus_cat_build_record(&entry, cnid, inode);
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err != -ENOENT) {
@@ -288,7 +310,7 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir,
 	return 0;
 
 err1:
-	hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid);
 	if (!hfs_brec_find(&fd, hfs_find_rec_by_key))
 		hfs_brec_remove(&fd);
 err2:
@@ -313,7 +335,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 	if (!str) {
 		int len;
 
-		hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
+		hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid);
 		err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 		if (err)
 			goto out;
@@ -329,7 +351,9 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 			off + 2, len);
 		fd.search_key->key_len = cpu_to_be16(6 + len);
 	} else
-		hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
+		err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
+		if (unlikely(err))
+			goto out;
 
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err)
@@ -360,7 +384,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 	if (err)
 		goto out;
 
-	hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid);
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
@@ -405,7 +429,11 @@ int hfsplus_rename_cat(u32 cnid,
 	dst_fd = src_fd;
 
 	/* find the old dir entry and read the data */
-	hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name);
+	err = hfsplus_cat_build_key(sb, src_fd.search_key,
+			src_dir->i_ino, src_name);
+	if (unlikely(err))
+		goto out;
+
 	err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
@@ -419,7 +447,11 @@ int hfsplus_rename_cat(u32 cnid,
 	type = be16_to_cpu(entry.type);
 
 	/* create new dir entry with the data from the old entry */
-	hfsplus_cat_build_key(sb, dst_fd.search_key, dst_dir->i_ino, dst_name);
+	err = hfsplus_cat_build_key(sb, dst_fd.search_key,
+			dst_dir->i_ino, dst_name);
+	if (unlikely(err))
+		goto out;
+
 	err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key);
 	if (err != -ENOENT) {
 		if (!err)
@@ -436,7 +468,11 @@ int hfsplus_rename_cat(u32 cnid,
 	dst_dir->i_mtime = dst_dir->i_ctime = CURRENT_TIME_SEC;
 
 	/* finally remove the old entry */
-	hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name);
+	err = hfsplus_cat_build_key(sb, src_fd.search_key,
+			src_dir->i_ino, src_name);
+	if (unlikely(err))
+		goto out;
+
 	err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
@@ -449,7 +485,7 @@ int hfsplus_rename_cat(u32 cnid,
 	src_dir->i_mtime = src_dir->i_ctime = CURRENT_TIME_SEC;
 
 	/* remove old thread entry */
-	hfsplus_cat_build_key(sb, src_fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, src_fd.search_key, cnid);
 	err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
@@ -459,9 +495,14 @@ int hfsplus_rename_cat(u32 cnid,
 		goto out;
 
 	/* create new thread entry */
-	hfsplus_cat_build_key(sb, dst_fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, dst_fd.search_key, cnid);
 	entry_size = hfsplus_fill_cat_thread(sb, &entry, type,
 		dst_dir->i_ino, dst_name);
+	if (unlikely(entry_size < 0)) {
+		err = entry_size;
+		goto out;
+	}
+
 	err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key);
 	if (err != -ENOENT) {
 		if (!err)
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index bdec66522de3..b306b66ccaba 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -43,7 +43,10 @@ static struct dentry *hfsplus_lookup(struct inode *dir, struct dentry *dentry,
 	err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 	if (err)
 		return ERR_PTR(err);
-	hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, &dentry->d_name);
+	err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino,
+			&dentry->d_name);
+	if (unlikely(err < 0))
+		goto fail;
 again:
 	err = hfs_brec_read(&fd, &entry, sizeof(entry));
 	if (err) {
@@ -96,9 +99,11 @@ again:
 					be32_to_cpu(entry.file.permissions.dev);
 				str.len = sprintf(name, "iNode%d", linkid);
 				str.name = name;
-				hfsplus_cat_build_key(sb, fd.search_key,
+				err = hfsplus_cat_build_key(sb, fd.search_key,
 					HFSPLUS_SB(sb)->hidden_dir->i_ino,
 					&str);
+				if (unlikely(err < 0))
+					goto fail;
 				goto again;
 			}
 		} else if (!dentry->d_fsdata)
@@ -139,7 +144,7 @@ static int hfsplus_readdir(struct file *file, struct dir_context *ctx)
 	err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 	if (err)
 		return err;
-	hfsplus_cat_build_key(sb, fd.search_key, inode->i_ino, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd.search_key, inode->i_ino);
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index fbb212fbb1ef..a7aafb35b624 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -227,10 +227,8 @@ int hfsplus_get_block(struct inode *inode, sector_t iblock,
 	u32 ablock, dblock, mask;
 	sector_t sector;
 	int was_dirty = 0;
-	int shift;
 
 	/* Convert inode block to disk allocation block */
-	shift = sbi->alloc_blksz_shift - sb->s_blocksize_bits;
 	ablock = iblock >> sbi->fs_shift;
 
 	if (iblock >= hip->fs_blocks) {
@@ -498,11 +496,13 @@ int hfsplus_file_extend(struct inode *inode)
 			goto insert_extent;
 	}
 out:
-	mutex_unlock(&hip->extents_lock);
 	if (!res) {
 		hip->alloc_blocks += len;
+		mutex_unlock(&hip->extents_lock);
 		hfsplus_mark_inode_dirty(inode, HFSPLUS_I_ALLOC_DIRTY);
+		return 0;
 	}
+	mutex_unlock(&hip->extents_lock);
 	return res;
 
 insert_extent:
@@ -556,11 +556,13 @@ void hfsplus_file_truncate(struct inode *inode)
 
 	blk_cnt = (inode->i_size + HFSPLUS_SB(sb)->alloc_blksz - 1) >>
 			HFSPLUS_SB(sb)->alloc_blksz_shift;
+
+	mutex_lock(&hip->extents_lock);
+
 	alloc_cnt = hip->alloc_blocks;
 	if (blk_cnt == alloc_cnt)
-		goto out;
+		goto out_unlock;
 
-	mutex_lock(&hip->extents_lock);
 	res = hfs_find_init(HFSPLUS_SB(sb)->ext_tree, &fd);
 	if (res) {
 		mutex_unlock(&hip->extents_lock);
@@ -592,10 +594,10 @@ void hfsplus_file_truncate(struct inode *inode)
 		hfs_brec_remove(&fd);
 	}
 	hfs_find_exit(&fd);
-	mutex_unlock(&hip->extents_lock);
 
 	hip->alloc_blocks = blk_cnt;
-out:
+out_unlock:
+	mutex_unlock(&hip->extents_lock);
 	hip->phys_size = inode->i_size;
 	hip->fs_blocks = (inode->i_size + sb->s_blocksize - 1) >>
 		sb->s_blocksize_bits;
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 62d571eb69ba..7f36453a788d 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -367,7 +367,7 @@ typedef int (*search_strategy_t)(struct hfs_bnode *,
  */
 
 /* attributes.c */
-int hfsplus_create_attr_tree_cache(void);
+int __init hfsplus_create_attr_tree_cache(void);
 void hfsplus_destroy_attr_tree_cache(void);
 hfsplus_attr_entry *hfsplus_alloc_attr_entry(void);
 void hfsplus_destroy_attr_entry(hfsplus_attr_entry *entry_p);
@@ -444,8 +444,10 @@ int hfsplus_cat_case_cmp_key(const hfsplus_btree_key *,
 		const hfsplus_btree_key *);
 int hfsplus_cat_bin_cmp_key(const hfsplus_btree_key *,
 		const hfsplus_btree_key *);
-void hfsplus_cat_build_key(struct super_block *sb,
+int hfsplus_cat_build_key(struct super_block *sb,
 		hfsplus_btree_key *, u32, struct qstr *);
+void hfsplus_cat_build_key_with_cnid(struct super_block *sb,
+		hfsplus_btree_key *, u32);
 int hfsplus_find_cat(struct super_block *, u32, struct hfs_find_data *);
 int hfsplus_create_cat(u32, struct inode *, struct qstr *, struct inode *);
 int hfsplus_delete_cat(u32, struct inode *, struct qstr *);
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 8eb787b52c05..dcb474129d5c 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -161,7 +161,7 @@ static int hfsplus_write_inode(struct inode *inode,
 static void hfsplus_evict_inode(struct inode *inode)
 {
 	hfs_dbg(INODE, "hfsplus_evict_inode: %lu\n", inode->i_ino);
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	if (HFSPLUS_IS_RSRC(inode)) {
 		HFSPLUS_I(HFSPLUS_I(inode)->rsrc_inode)->rsrc_inode = NULL;
@@ -514,7 +514,9 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 	err = hfs_find_init(sbi->cat_tree, &fd);
 	if (err)
 		goto out_put_root;
-	hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_ROOT_CNID, &str);
+	err = hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_ROOT_CNID, &str);
+	if (unlikely(err < 0))
+		goto out_put_root;
 	if (!hfs_brec_read(&fd, &entry, sizeof(entry))) {
 		hfs_find_exit(&fd);
 		if (entry.type != cpu_to_be16(HFSPLUS_FOLDER))
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index fe649d325b1f..9c470fde9878 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -230,7 +230,7 @@ static struct inode *hostfs_alloc_inode(struct super_block *sb)
 
 static void hostfs_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	if (HOSTFS_I(inode)->fd != -1) {
 		close_file(&HOSTFS_I(inode)->fd);
diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c
index 9edeeb0ea97e..50a427313835 100644
--- a/fs/hpfs/inode.c
+++ b/fs/hpfs/inode.c
@@ -304,7 +304,7 @@ void hpfs_write_if_changed(struct inode *inode)
 
 void hpfs_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	if (!inode->i_nlink) {
 		hpfs_lock(inode->i_sb);
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index d19b30ababf1..204027520937 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -366,7 +366,13 @@ static void truncate_hugepages(struct inode *inode, loff_t lstart)
 
 static void hugetlbfs_evict_inode(struct inode *inode)
 {
+	struct resv_map *resv_map;
+
 	truncate_hugepages(inode, 0);
+	resv_map = (struct resv_map *)inode->i_mapping->private_data;
+	/* root inode doesn't have the resv_map, so we should check it */
+	if (resv_map)
+		resv_map_release(&resv_map->refs);
 	clear_inode(inode);
 }
 
@@ -476,6 +482,11 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 					umode_t mode, dev_t dev)
 {
 	struct inode *inode;
+	struct resv_map *resv_map;
+
+	resv_map = resv_map_alloc();
+	if (!resv_map)
+		return NULL;
 
 	inode = new_inode(sb);
 	if (inode) {
@@ -487,7 +498,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
 		inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-		INIT_LIST_HEAD(&inode->i_mapping->private_list);
+		inode->i_mapping->private_data = resv_map;
 		info = HUGETLBFS_I(inode);
 		/*
 		 * The policy is initialized here even if we are creating a
@@ -517,7 +528,9 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 			break;
 		}
 		lockdep_annotate_inode_mutex_key(inode);
-	}
+	} else
+		kref_put(&resv_map->refs, resv_map_release);
+
 	return inode;
 }
 
diff --git a/fs/inode.c b/fs/inode.c
index 26f95ceb6250..111fd5e34009 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -503,6 +503,7 @@ void clear_inode(struct inode *inode)
 	 */
 	spin_lock_irq(&inode->i_data.tree_lock);
 	BUG_ON(inode->i_data.nrpages);
+	BUG_ON(inode->i_data.nrshadows);
 	spin_unlock_irq(&inode->i_data.tree_lock);
 	BUG_ON(!list_empty(&inode->i_data.private_list));
 	BUG_ON(!(inode->i_state & I_FREEING));
@@ -548,8 +549,7 @@ static void evict(struct inode *inode)
 	if (op->evict_inode) {
 		op->evict_inode(inode);
 	} else {
-		if (inode->i_data.nrpages)
-			truncate_inode_pages(&inode->i_data, 0);
+		truncate_inode_pages_final(&inode->i_data);
 		clear_inode(inode);
 	}
 	if (S_ISBLK(inode->i_mode) && inode->i_bdev)
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index 560821bff038..601afd1afddf 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -242,7 +242,7 @@ void jffs2_evict_inode (struct inode *inode)
 
 	jffs2_dbg(1, "%s(): ino #%lu mode %o\n",
 		  __func__, inode->i_ino, inode->i_mode);
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	jffs2_do_clear_inode(c, f);
 }
@@ -690,7 +690,7 @@ unsigned char *jffs2_gc_fetch_page(struct jffs2_sb_info *c,
 	struct inode *inode = OFNI_EDONI_2SFFJ(f);
 	struct page *pg;
 
-	pg = read_cache_page_async(inode->i_mapping, offset >> PAGE_CACHE_SHIFT,
+	pg = read_cache_page(inode->i_mapping, offset >> PAGE_CACHE_SHIFT,
 			     (void *)jffs2_do_readpage_unlock, inode);
 	if (IS_ERR(pg))
 		return (void *)pg;
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index f4aab719add5..6f8fe72c2a7a 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -154,7 +154,7 @@ void jfs_evict_inode(struct inode *inode)
 		dquot_initialize(inode);
 
 		if (JFS_IP(inode)->fileset == FILESYSTEM_I) {
-			truncate_inode_pages(&inode->i_data, 0);
+			truncate_inode_pages_final(&inode->i_data);
 
 			if (test_cflag(COMMIT_Freewmap, inode))
 				jfs_free_zero_link(inode);
@@ -168,7 +168,7 @@ void jfs_evict_inode(struct inode *inode)
 			dquot_free_inode(inode);
 		}
 	} else {
-		truncate_inode_pages(&inode->i_data, 0);
+		truncate_inode_pages_final(&inode->i_data);
 	}
 	clear_inode(inode);
 	dquot_drop(inode);
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index e55126f85bd2..abb0f1f53d93 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -355,7 +355,7 @@ void kernfs_evict_inode(struct inode *inode)
 {
 	struct kernfs_node *kn = inode->i_private;
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	kernfs_put(kn);
 }
diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c
index 9a59cbade2fb..48140315f627 100644
--- a/fs/logfs/readwrite.c
+++ b/fs/logfs/readwrite.c
@@ -2180,7 +2180,7 @@ void logfs_evict_inode(struct inode *inode)
 			do_delete_inode(inode);
 		}
 	}
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 
 	/* Cheaper version of write_inode.  All changes are concealed in
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index dcdc2989370d..f007a3355570 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -26,7 +26,7 @@ static int minix_remount (struct super_block * sb, int * flags, char * data);
 
 static void minix_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	if (!inode->i_nlink) {
 		inode->i_size = 0;
 		minix_truncate(inode);
@@ -86,7 +86,7 @@ static void init_once(void *foo)
 	inode_init_once(&ei->vfs_inode);
 }
 
-static int init_inodecache(void)
+static int __init init_inodecache(void)
 {
 	minix_inode_cachep = kmem_cache_create("minix_inode_cache",
 					     sizeof(struct minix_inode_info),
diff --git a/fs/mpage.c b/fs/mpage.c
index 4979ffa60aaa..4e0af5ae34fa 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -462,6 +462,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 	struct buffer_head map_bh;
 	loff_t i_size = i_size_read(inode);
 	int ret = 0;
+	int wr = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : WRITE);
 
 	if (page_has_buffers(page)) {
 		struct buffer_head *head = page_buffers(page);
@@ -570,7 +571,7 @@ page_is_mapped:
 	 * This page will go to BIO.  Do we need to send this BIO off first?
 	 */
 	if (bio && mpd->last_block_in_bio != blocks[0] - 1)
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 
 alloc_new:
 	if (bio == NULL) {
@@ -587,7 +588,7 @@ alloc_new:
 	 */
 	length = first_unmapped << blkbits;
 	if (bio_add_page(bio, page, length, 0) < length) {
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 		goto alloc_new;
 	}
 
@@ -620,7 +621,7 @@ alloc_new:
 	set_page_writeback(page);
 	unlock_page(page);
 	if (boundary || (first_unmapped != blocks_per_page)) {
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 		if (boundary_block) {
 			write_boundary_block(boundary_bdev,
 					boundary_block, 1 << blkbits);
@@ -632,7 +633,7 @@ alloc_new:
 
 confused:
 	if (bio)
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 
 	if (mpd->use_writepage) {
 		ret = mapping->a_ops->writepage(page, wbc);
@@ -688,8 +689,11 @@ mpage_writepages(struct address_space *mapping,
 		};
 
 		ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd);
-		if (mpd.bio)
-			mpage_bio_submit(WRITE, mpd.bio);
+		if (mpd.bio) {
+			int wr = (wbc->sync_mode == WB_SYNC_ALL ?
+				  WRITE_SYNC : WRITE);
+			mpage_bio_submit(wr, mpd.bio);
+		}
 	}
 	blk_finish_plug(&plug);
 	return ret;
@@ -706,8 +710,11 @@ int mpage_writepage(struct page *page, get_block_t get_block,
 		.use_writepage = 0,
 	};
 	int ret = __mpage_writepage(page, wbc, &mpd);
-	if (mpd.bio)
-		mpage_bio_submit(WRITE, mpd.bio);
+	if (mpd.bio) {
+		int wr = (wbc->sync_mode == WB_SYNC_ALL ?
+			  WRITE_SYNC : WRITE);
+		mpage_bio_submit(wr, mpd.bio);
+	}
 	return ret;
 }
 EXPORT_SYMBOL(mpage_writepage);
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index c320ac52353e..08b8ea8c353e 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -339,7 +339,7 @@ ncp_lookup_validate(struct dentry *dentry, unsigned int flags)
 	if (val)
 		goto finished;
 
-	DDPRINTK("ncp_lookup_validate: %pd2 not valid, age=%ld, server lookup\n",
+	ncp_dbg(2, "%pd2 not valid, age=%ld, server lookup\n",
 		dentry, NCP_GET_AGE(dentry));
 
 	len = sizeof(__name);
@@ -358,7 +358,7 @@ ncp_lookup_validate(struct dentry *dentry, unsigned int flags)
 			res = ncp_obtain_info(server, dir, __name, &(finfo.i));
 	}
 	finfo.volume = finfo.i.volNumber;
-	DDPRINTK("ncp_lookup_validate: looked for %pd/%s, res=%d\n",
+	ncp_dbg(2, "looked for %pd/%s, res=%d\n",
 		dentry->d_parent, __name, res);
 	/*
 	 * If we didn't find it, or if it has a different dirEntNum to
@@ -372,14 +372,14 @@ ncp_lookup_validate(struct dentry *dentry, unsigned int flags)
 			ncp_new_dentry(dentry);
 			val=1;
 		} else
-			DDPRINTK("ncp_lookup_validate: found, but dirEntNum changed\n");
+			ncp_dbg(2, "found, but dirEntNum changed\n");
 
 		ncp_update_inode2(inode, &finfo);
 		mutex_unlock(&inode->i_mutex);
 	}
 
 finished:
-	DDPRINTK("ncp_lookup_validate: result=%d\n", val);
+	ncp_dbg(2, "result=%d\n", val);
 	dput(parent);
 	return val;
 }
@@ -453,8 +453,7 @@ static int ncp_readdir(struct file *file, struct dir_context *ctx)
 	ctl.page  = NULL;
 	ctl.cache = NULL;
 
-	DDPRINTK("ncp_readdir: reading %pD2, pos=%d\n", file,
-		(int) ctx->pos);
+	ncp_dbg(2, "reading %pD2, pos=%d\n", file, (int)ctx->pos);
 
 	result = -EIO;
 	/* Do not generate '.' and '..' when server is dead. */
@@ -697,8 +696,7 @@ ncp_read_volume_list(struct file *file, struct dir_context *ctx,
 	struct ncp_entry_info entry;
 	int i;
 
-	DPRINTK("ncp_read_volume_list: pos=%ld\n",
-			(unsigned long) ctx->pos);
+	ncp_dbg(1, "pos=%ld\n", (unsigned long)ctx->pos);
 
 	for (i = 0; i < NCP_NUMBER_OF_VOLUMES; i++) {
 		int inval_dentry;
@@ -708,12 +706,11 @@ ncp_read_volume_list(struct file *file, struct dir_context *ctx,
 		if (!strlen(info.volume_name))
 			continue;
 
-		DPRINTK("ncp_read_volume_list: found vol: %s\n",
-			info.volume_name);
+		ncp_dbg(1, "found vol: %s\n", info.volume_name);
 
 		if (ncp_lookup_volume(server, info.volume_name,
 					&entry.i)) {
-			DPRINTK("ncpfs: could not lookup vol %s\n",
+			ncp_dbg(1, "could not lookup vol %s\n",
 				info.volume_name);
 			continue;
 		}
@@ -738,14 +735,13 @@ ncp_do_readdir(struct file *file, struct dir_context *ctx,
 	int more;
 	size_t bufsize;
 
-	DPRINTK("ncp_do_readdir: %pD2, fpos=%ld\n", file,
-		(unsigned long) ctx->pos);
-	PPRINTK("ncp_do_readdir: init %pD, volnum=%d, dirent=%u\n",
-		file, NCP_FINFO(dir)->volNumber, NCP_FINFO(dir)->dirEntNum);
+	ncp_dbg(1, "%pD2, fpos=%ld\n", file, (unsigned long)ctx->pos);
+	ncp_vdbg("init %pD, volnum=%d, dirent=%u\n",
+		 file, NCP_FINFO(dir)->volNumber, NCP_FINFO(dir)->dirEntNum);
 
 	err = ncp_initialize_search(server, dir, &seq);
 	if (err) {
-		DPRINTK("ncp_do_readdir: init failed, err=%d\n", err);
+		ncp_dbg(1, "init failed, err=%d\n", err);
 		return;
 	}
 	/* We MUST NOT use server->buffer_size handshaked with server if we are
@@ -808,8 +804,7 @@ int ncp_conn_logged_in(struct super_block *sb)
 			goto out;
 		result = -ENOENT;
 		if (ncp_get_volume_root(server, __name, &volNumber, &dirEntNum, &DosDirNum)) {
-			PPRINTK("ncp_conn_logged_in: %s not found\n",
-				server->m.mounted_vol);
+			ncp_vdbg("%s not found\n", server->m.mounted_vol);
 			goto out;
 		}
 		dent = sb->s_root;
@@ -822,10 +817,10 @@ int ncp_conn_logged_in(struct super_block *sb)
 				NCP_FINFO(ino)->DosDirNum = DosDirNum;
 				result = 0;
 			} else {
-				DPRINTK("ncpfs: sb->s_root->d_inode == NULL!\n");
+				ncp_dbg(1, "sb->s_root->d_inode == NULL!\n");
 			}
 		} else {
-			DPRINTK("ncpfs: sb->s_root == NULL!\n");
+			ncp_dbg(1, "sb->s_root == NULL!\n");
 		}
 	} else
 		result = 0;
@@ -846,7 +841,7 @@ static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, unsig
 	if (!ncp_conn_valid(server))
 		goto finished;
 
-	PPRINTK("ncp_lookup: server lookup for %pd2\n", dentry);
+	ncp_vdbg("server lookup for %pd2\n", dentry);
 
 	len = sizeof(__name);
 	if (ncp_is_server_root(dir)) {
@@ -854,15 +849,15 @@ static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, unsig
 				 dentry->d_name.len, 1);
 		if (!res)
 			res = ncp_lookup_volume(server, __name, &(finfo.i));
-			if (!res)
-				ncp_update_known_namespace(server, finfo.i.volNumber, NULL);
+		if (!res)
+			ncp_update_known_namespace(server, finfo.i.volNumber, NULL);
 	} else {
 		res = ncp_io2vol(server, __name, &len, dentry->d_name.name,
 				 dentry->d_name.len, !ncp_preserve_case(dir));
 		if (!res)
 			res = ncp_obtain_info(server, dir, __name, &(finfo.i));
 	}
-	PPRINTK("ncp_lookup: looked for %pd2, res=%d\n", dentry, res);
+	ncp_vdbg("looked for %pd2, res=%d\n", dentry, res);
 	/*
 	 * If we didn't find an entry, make a negative dentry.
 	 */
@@ -886,7 +881,7 @@ add_entry:
 	}
 
 finished:
-	PPRINTK("ncp_lookup: result=%d\n", error);
+	ncp_vdbg("result=%d\n", error);
 	return ERR_PTR(error);
 }
 
@@ -909,7 +904,7 @@ out:
 	return error;
 
 out_close:
-	PPRINTK("ncp_instantiate: %pd2 failed, closing file\n", dentry);
+	ncp_vdbg("%pd2 failed, closing file\n", dentry);
 	ncp_close_file(NCP_SERVER(dir), finfo->file_handle);
 	goto out;
 }
@@ -923,7 +918,7 @@ int ncp_create_new(struct inode *dir, struct dentry *dentry, umode_t mode,
 	int opmode;
 	__u8 __name[NCP_MAXPATHLEN + 1];
 	
-	PPRINTK("ncp_create_new: creating %pd2, mode=%hx\n", dentry, mode);
+	ncp_vdbg("creating %pd2, mode=%hx\n", dentry, mode);
 
 	ncp_age_dentry(server, dentry);
 	len = sizeof(__name);
@@ -952,7 +947,7 @@ int ncp_create_new(struct inode *dir, struct dentry *dentry, umode_t mode,
 				error = -ENAMETOOLONG;
 			else if (result < 0)
 				error = result;
-			DPRINTK("ncp_create: %pd2 failed\n", dentry);
+			ncp_dbg(1, "%pd2 failed\n", dentry);
 			goto out;
 		}
 		opmode = O_WRONLY;
@@ -985,7 +980,7 @@ static int ncp_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	int error, len;
 	__u8 __name[NCP_MAXPATHLEN + 1];
 
-	DPRINTK("ncp_mkdir: making %pd2\n", dentry);
+	ncp_dbg(1, "making %pd2\n", dentry);
 
 	ncp_age_dentry(server, dentry);
 	len = sizeof(__name);
@@ -1022,7 +1017,7 @@ static int ncp_rmdir(struct inode *dir, struct dentry *dentry)
 	int error, result, len;
 	__u8 __name[NCP_MAXPATHLEN + 1];
 
-	DPRINTK("ncp_rmdir: removing %pd2\n", dentry);
+	ncp_dbg(1, "removing %pd2\n", dentry);
 
 	len = sizeof(__name);
 	error = ncp_io2vol(server, __name, &len, dentry->d_name.name,
@@ -1067,13 +1062,13 @@ static int ncp_unlink(struct inode *dir, struct dentry *dentry)
 	int error;
 
 	server = NCP_SERVER(dir);
-	DPRINTK("ncp_unlink: unlinking %pd2\n", dentry);
+	ncp_dbg(1, "unlinking %pd2\n", dentry);
 	
 	/*
 	 * Check whether to close the file ...
 	 */
 	if (inode) {
-		PPRINTK("ncp_unlink: closing file\n");
+		ncp_vdbg("closing file\n");
 		ncp_make_closed(inode);
 	}
 
@@ -1087,7 +1082,7 @@ static int ncp_unlink(struct inode *dir, struct dentry *dentry)
 #endif
 	switch (error) {
 		case 0x00:
-			DPRINTK("ncp: removed %pd2\n", dentry);
+			ncp_dbg(1, "removed %pd2\n", dentry);
 			break;
 		case 0x85:
 		case 0x8A:
@@ -1120,7 +1115,7 @@ static int ncp_rename(struct inode *old_dir, struct dentry *old_dentry,
 	int old_len, new_len;
 	__u8 __old_name[NCP_MAXPATHLEN + 1], __new_name[NCP_MAXPATHLEN + 1];
 
-	DPRINTK("ncp_rename: %pd2 to %pd2\n", old_dentry, new_dentry);
+	ncp_dbg(1, "%pd2 to %pd2\n", old_dentry, new_dentry);
 
 	ncp_age_dentry(server, old_dentry);
 	ncp_age_dentry(server, new_dentry);
@@ -1150,8 +1145,8 @@ static int ncp_rename(struct inode *old_dir, struct dentry *old_dentry,
 #endif
 	switch (error) {
 		case 0x00:
-               	        DPRINTK("ncp renamed %pd -> %pd.\n",
-                                old_dentry, new_dentry);
+			ncp_dbg(1, "renamed %pd -> %pd\n",
+				old_dentry, new_dentry);
 			break;
 		case 0x9E:
 			error = -ENAMETOOLONG;
@@ -1173,7 +1168,7 @@ static int ncp_mknod(struct inode * dir, struct dentry *dentry,
 	if (!new_valid_dev(rdev))
 		return -EINVAL;
 	if (ncp_is_nfs_extras(NCP_SERVER(dir), NCP_FINFO(dir)->volNumber)) {
-		DPRINTK(KERN_DEBUG "ncp_mknod: mode = 0%ho\n", mode);
+		ncp_dbg(1, "mode = 0%ho\n", mode);
 		return ncp_create_new(dir, dentry, mode, rdev, 0);
 	}
 	return -EPERM; /* Strange, but true */
diff --git a/fs/ncpfs/file.c b/fs/ncpfs/file.c
index 8f5074e1ecb9..77640a8bfb87 100644
--- a/fs/ncpfs/file.c
+++ b/fs/ncpfs/file.c
@@ -6,6 +6,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <asm/uaccess.h>
 
 #include <linux/time.h>
@@ -34,11 +36,11 @@ int ncp_make_open(struct inode *inode, int right)
 
 	error = -EINVAL;
 	if (!inode) {
-		printk(KERN_ERR "ncp_make_open: got NULL inode\n");
+		pr_err("%s: got NULL inode\n", __func__);
 		goto out;
 	}
 
-	DPRINTK("ncp_make_open: opened=%d, volume # %u, dir entry # %u\n",
+	ncp_dbg(1, "opened=%d, volume # %u, dir entry # %u\n",
 		atomic_read(&NCP_FINFO(inode)->opened), 
 		NCP_FINFO(inode)->volNumber, 
 		NCP_FINFO(inode)->dirEntNum);
@@ -71,7 +73,7 @@ int ncp_make_open(struct inode *inode, int right)
 				break;
 		}
 		if (result) {
-			PPRINTK("ncp_make_open: failed, result=%d\n", result);
+			ncp_vdbg("failed, result=%d\n", result);
 			goto out_unlock;
 		}
 		/*
@@ -83,7 +85,7 @@ int ncp_make_open(struct inode *inode, int right)
 	}
 
 	access = NCP_FINFO(inode)->access;
-	PPRINTK("ncp_make_open: file open, access=%x\n", access);
+	ncp_vdbg("file open, access=%x\n", access);
 	if (access == right || access == O_RDWR) {
 		atomic_inc(&NCP_FINFO(inode)->opened);
 		error = 0;
@@ -107,7 +109,7 @@ ncp_file_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 	void* freepage;
 	size_t freelen;
 
-	DPRINTK("ncp_file_read: enter %pd2\n", dentry);
+	ncp_dbg(1, "enter %pd2\n", dentry);
 
 	pos = *ppos;
 
@@ -124,7 +126,7 @@ ncp_file_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 
 	error = ncp_make_open(inode, O_RDONLY);
 	if (error) {
-		DPRINTK(KERN_ERR "ncp_file_read: open failed, error=%d\n", error);
+		ncp_dbg(1, "open failed, error=%d\n", error);
 		return error;
 	}
 
@@ -165,7 +167,7 @@ ncp_file_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 
 	file_accessed(file);
 
-	DPRINTK("ncp_file_read: exit %pd2\n", dentry);
+	ncp_dbg(1, "exit %pd2\n", dentry);
 outrel:
 	ncp_inode_close(inode);		
 	return already_read ? already_read : error;
@@ -182,7 +184,7 @@ ncp_file_write(struct file *file, const char __user *buf, size_t count, loff_t *
 	int errno;
 	void* bouncebuffer;
 
-	DPRINTK("ncp_file_write: enter %pd2\n", dentry);
+	ncp_dbg(1, "enter %pd2\n", dentry);
 	if ((ssize_t) count < 0)
 		return -EINVAL;
 	pos = *ppos;
@@ -211,7 +213,7 @@ ncp_file_write(struct file *file, const char __user *buf, size_t count, loff_t *
 		return 0;
 	errno = ncp_make_open(inode, O_WRONLY);
 	if (errno) {
-		DPRINTK(KERN_ERR "ncp_file_write: open failed, error=%d\n", errno);
+		ncp_dbg(1, "open failed, error=%d\n", errno);
 		return errno;
 	}
 	bufsize = NCP_SERVER(inode)->buffer_size;
@@ -261,7 +263,7 @@ ncp_file_write(struct file *file, const char __user *buf, size_t count, loff_t *
 			i_size_write(inode, pos);
 		mutex_unlock(&inode->i_mutex);
 	}
-	DPRINTK("ncp_file_write: exit %pd2\n", dentry);
+	ncp_dbg(1, "exit %pd2\n", dentry);
 outrel:
 	ncp_inode_close(inode);		
 	return already_written ? already_written : errno;
@@ -269,7 +271,7 @@ outrel:
 
 static int ncp_release(struct inode *inode, struct file *file) {
 	if (ncp_make_closed(inode)) {
-		DPRINTK("ncp_release: failed to close\n");
+		ncp_dbg(1, "failed to close\n");
 	}
 	return 0;
 }
diff --git a/fs/ncpfs/getopt.c b/fs/ncpfs/getopt.c
index 0af3349de851..03ffde1f44d6 100644
--- a/fs/ncpfs/getopt.c
+++ b/fs/ncpfs/getopt.c
@@ -2,6 +2,8 @@
  * getopt.c
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/string.h>
 
@@ -46,8 +48,8 @@ int ncp_getopt(const char *caller, char **options, const struct ncp_option *opts
 				if (opts->has_arg & OPT_NOPARAM) {
 					return opts->val;
 				}
-				printk(KERN_INFO "%s: the %s option requires an argument\n",
-				       caller, token);
+				pr_info("%s: the %s option requires an argument\n",
+					caller, token);
 				return -EINVAL;
 			}
 			if (opts->has_arg & OPT_INT) {
@@ -57,18 +59,18 @@ int ncp_getopt(const char *caller, char **options, const struct ncp_option *opts
 				if (!*v) {
 					return opts->val;
 				}
-				printk(KERN_INFO "%s: invalid numeric value in %s=%s\n",
+				pr_info("%s: invalid numeric value in %s=%s\n",
 					caller, token, val);
 				return -EDOM;
 			}
 			if (opts->has_arg & OPT_STRING) {
 				return opts->val;
 			}
-			printk(KERN_INFO "%s: unexpected argument %s to the %s option\n",
+			pr_info("%s: unexpected argument %s to the %s option\n",
 				caller, val, token);
 			return -EINVAL;
 		}
 	}
-	printk(KERN_INFO "%s: Unrecognized mount option %s\n", caller, token);
+	pr_info("%s: Unrecognized mount option %s\n", caller, token);
 	return -EOPNOTSUPP;
 }
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 5f86e8080178..81b4f643ecef 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -9,6 +9,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 
 #include <asm/uaccess.h>
@@ -133,7 +135,7 @@ void ncp_update_inode(struct inode *inode, struct ncp_entry_info *nwinfo)
 	NCP_FINFO(inode)->access = nwinfo->access;
 	memcpy(NCP_FINFO(inode)->file_handle, nwinfo->file_handle,
 			sizeof(nwinfo->file_handle));
-	DPRINTK("ncp_update_inode: updated %s, volnum=%d, dirent=%u\n",
+	ncp_dbg(1, "updated %s, volnum=%d, dirent=%u\n",
 		nwinfo->i.entryName, NCP_FINFO(inode)->volNumber,
 		NCP_FINFO(inode)->dirEntNum);
 }
@@ -141,8 +143,7 @@ void ncp_update_inode(struct inode *inode, struct ncp_entry_info *nwinfo)
 static void ncp_update_dates(struct inode *inode, struct nw_info_struct *nwi)
 {
 	/* NFS namespace mode overrides others if it's set. */
-	DPRINTK(KERN_DEBUG "ncp_update_dates_and_mode: (%s) nfs.mode=0%o\n",
-		nwi->entryName, nwi->nfs.mode);
+	ncp_dbg(1, "(%s) nfs.mode=0%o\n", nwi->entryName, nwi->nfs.mode);
 	if (nwi->nfs.mode) {
 		/* XXX Security? */
 		inode->i_mode = nwi->nfs.mode;
@@ -230,7 +231,7 @@ static void ncp_set_attr(struct inode *inode, struct ncp_entry_info *nwinfo)
 	
 	ncp_update_attrs(inode, nwinfo);
 
-	DDPRINTK("ncp_read_inode: inode->i_mode = %u\n", inode->i_mode);
+	ncp_dbg(2, "inode->i_mode = %u\n", inode->i_mode);
 
 	set_nlink(inode, 1);
 	inode->i_uid = server->m.uid;
@@ -258,7 +259,7 @@ ncp_iget(struct super_block *sb, struct ncp_entry_info *info)
 	struct inode *inode;
 
 	if (info == NULL) {
-		printk(KERN_ERR "ncp_iget: info is NULL\n");
+		pr_err("%s: info is NULL\n", __func__);
 		return NULL;
 	}
 
@@ -290,23 +291,23 @@ ncp_iget(struct super_block *sb, struct ncp_entry_info *info)
 		}
 		insert_inode_hash(inode);
 	} else
-		printk(KERN_ERR "ncp_iget: iget failed!\n");
+		pr_err("%s: iget failed!\n", __func__);
 	return inode;
 }
 
 static void
 ncp_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 
 	if (S_ISDIR(inode->i_mode)) {
-		DDPRINTK("ncp_evict_inode: put directory %ld\n", inode->i_ino);
+		ncp_dbg(2, "put directory %ld\n", inode->i_ino);
 	}
 
 	if (ncp_make_closed(inode) != 0) {
 		/* We can't do anything but complain. */
-		printk(KERN_ERR "ncp_evict_inode: could not close\n");
+		pr_err("%s: could not close\n", __func__);
 	}
 }
 
@@ -621,7 +622,7 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
 	   now because of PATH_MAX changes.. */
 	if (server->m.time_out < 1) {
 		server->m.time_out = 10;
-		printk(KERN_INFO "You need to recompile your ncpfs utils..\n");
+		pr_info("You need to recompile your ncpfs utils..\n");
 	}
 	server->m.time_out = server->m.time_out * HZ / 100;
 	server->m.file_mode = (server->m.file_mode & S_IRWXUGO) | S_IFREG;
@@ -682,7 +683,7 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
 	ncp_unlock_server(server);
 	if (error < 0)
 		goto out_rxbuf;
-	DPRINTK("ncp_fill_super: NCP_SBP(sb) = %x\n", (int) NCP_SBP(sb));
+	ncp_dbg(1, "NCP_SBP(sb) = %p\n", NCP_SBP(sb));
 
 	error = -EMSGSIZE;	/* -EREMOTESIDEINCOMPATIBLE */
 #ifdef CONFIG_NCPFS_PACKET_SIGNING
@@ -710,7 +711,7 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
 	if (ncp_negotiate_buffersize(server, default_bufsize,
   				     &(server->buffer_size)) != 0)
 		goto out_disconnect;
-	DPRINTK("ncpfs: bufsize = %d\n", server->buffer_size);
+	ncp_dbg(1, "bufsize = %d\n", server->buffer_size);
 
 	memset(&finfo, 0, sizeof(finfo));
 	finfo.i.attributes	= aDIR;
@@ -739,7 +740,7 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
         root_inode = ncp_iget(sb, &finfo);
         if (!root_inode)
 		goto out_disconnect;
-	DPRINTK("ncp_fill_super: root vol=%d\n", NCP_FINFO(root_inode)->volNumber);
+	ncp_dbg(1, "root vol=%d\n", NCP_FINFO(root_inode)->volNumber);
 	sb->s_root = d_make_root(root_inode);
         if (!sb->s_root)
 		goto out_disconnect;
@@ -985,8 +986,7 @@ int ncp_notify_change(struct dentry *dentry, struct iattr *attr)
 	if ((attr->ia_valid & ATTR_SIZE) != 0) {
 		int written;
 
-		DPRINTK("ncpfs: trying to change size to %ld\n",
-			attr->ia_size);
+		ncp_dbg(1, "trying to change size to %llu\n", attr->ia_size);
 
 		if ((result = ncp_make_open(inode, O_WRONLY)) < 0) {
 			result = -EACCES;
@@ -1072,7 +1072,7 @@ MODULE_ALIAS_FS("ncpfs");
 static int __init init_ncp_fs(void)
 {
 	int err;
-	DPRINTK("ncpfs: init_ncp_fs called\n");
+	ncp_dbg(1, "called\n");
 
 	err = init_inodecache();
 	if (err)
@@ -1089,7 +1089,7 @@ out1:
 
 static void __exit exit_ncp_fs(void)
 {
-	DPRINTK("ncpfs: exit_ncp_fs called\n");
+	ncp_dbg(1, "called\n");
 	unregister_filesystem(&ncp_fs_type);
 	destroy_inodecache();
 }
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index 60426ccb3b65..d5659d96ee7f 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -41,7 +41,7 @@ ncp_get_fs_info(struct ncp_server * server, struct inode *inode,
 		return -EFAULT;
 
 	if (info.version != NCP_GET_FS_INFO_VERSION) {
-		DPRINTK("info.version invalid: %d\n", info.version);
+		ncp_dbg(1, "info.version invalid: %d\n", info.version);
 		return -EINVAL;
 	}
 	/* TODO: info.addr = server->m.serv_addr; */
@@ -66,7 +66,7 @@ ncp_get_fs_info_v2(struct ncp_server * server, struct inode *inode,
 		return -EFAULT;
 
 	if (info2.version != NCP_GET_FS_INFO_VERSION_V2) {
-		DPRINTK("info.version invalid: %d\n", info2.version);
+		ncp_dbg(1, "info.version invalid: %d\n", info2.version);
 		return -EINVAL;
 	}
 	info2.mounted_uid   = from_kuid_munged(current_user_ns(), server->m.mounted_uid);
@@ -132,7 +132,7 @@ ncp_get_compat_fs_info_v2(struct ncp_server * server, struct inode *inode,
 		return -EFAULT;
 
 	if (info2.version != NCP_GET_FS_INFO_VERSION_V2) {
-		DPRINTK("info.version invalid: %d\n", info2.version);
+		ncp_dbg(1, "info.version invalid: %d\n", info2.version);
 		return -EINVAL;
 	}
 	info2.mounted_uid   = from_kuid_munged(current_user_ns(), server->m.mounted_uid);
@@ -308,8 +308,7 @@ static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg
 		else
 			result = server->reply_size;
 		ncp_unlock_server(server);
-		DPRINTK("ncp_ioctl: copy %d bytes\n",
-			result);
+		ncp_dbg(1, "copy %d bytes\n", result);
 		if (result >= 0)
 			if (copy_to_user(request.data, bouncebuffer, result))
 				result = -EFAULT;
@@ -385,9 +384,9 @@ static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg
 						sr.namespace = server->name_space[sr.volNumber];
 						result = 0;
 					} else
-						DPRINTK("ncpfs: s_root->d_inode==NULL\n");
+						ncp_dbg(1, "s_root->d_inode==NULL\n");
 				} else
-					DPRINTK("ncpfs: s_root==NULL\n");
+					ncp_dbg(1, "s_root==NULL\n");
 			} else {
 				sr.volNumber = -1;
 				sr.namespace = 0;
@@ -440,11 +439,11 @@ static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg
 							NCP_FINFO(s_inode)->DosDirNum = dosde;
 							server->root_setuped = 1;
 						} else {
-							DPRINTK("ncpfs: s_root->d_inode==NULL\n");
+							ncp_dbg(1, "s_root->d_inode==NULL\n");
 							result = -EIO;
 						}
 					} else {
-						DPRINTK("ncpfs: s_root==NULL\n");
+						ncp_dbg(1, "s_root==NULL\n");
 						result = -EIO;
 					}
 				}
diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c
index 3c5dd55d284c..b359d12eb359 100644
--- a/fs/ncpfs/mmap.c
+++ b/fs/ncpfs/mmap.c
@@ -107,7 +107,7 @@ int ncp_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file_inode(file);
 	
-	DPRINTK("ncp_mmap: called\n");
+	ncp_dbg(1, "called\n");
 
 	if (!ncp_conn_valid(NCP_SERVER(inode)))
 		return -EIO;
diff --git a/fs/ncpfs/ncp_fs.h b/fs/ncpfs/ncp_fs.h
index 31831afe1c3b..b9f69e1b1f43 100644
--- a/fs/ncpfs/ncp_fs.h
+++ b/fs/ncpfs/ncp_fs.h
@@ -2,30 +2,32 @@
 #include "ncp_fs_i.h"
 #include "ncp_fs_sb.h"
 
-/* define because it is easy to change PRINTK to {*}PRINTK */
-#define PRINTK(format, args...) printk(KERN_DEBUG format , ## args)
-
 #undef NCPFS_PARANOIA
 #ifdef NCPFS_PARANOIA
-#define PPRINTK(format, args...) PRINTK(format , ## args)
+#define ncp_vdbg(fmt, ...)					\
+	pr_debug(fmt, ##__VA_ARGS__)
 #else
-#define PPRINTK(format, args...)
+#define ncp_vdbg(fmt, ...)					\
+do {								\
+	if (0)							\
+		pr_debug(fmt, ##__VA_ARGS__);			\
+} while (0)
 #endif
 
 #ifndef DEBUG_NCP
 #define DEBUG_NCP 0
 #endif
-#if DEBUG_NCP > 0
-#define DPRINTK(format, args...) PRINTK(format , ## args)
-#else
-#define DPRINTK(format, args...)
-#endif
-#if DEBUG_NCP > 1
-#define DDPRINTK(format, args...) PRINTK(format , ## args)
-#else
-#define DDPRINTK(format, args...)
+
+#if DEBUG_NCP > 0 && !defined(DEBUG)
+#define DEBUG
 #endif
 
+#define ncp_dbg(level, fmt, ...)				\
+do {								\
+	if (level <= DEBUG_NCP)					\
+		pr_debug(fmt, ##__VA_ARGS__);			\
+} while (0)
+
 #define NCP_MAX_RPC_TIMEOUT (6*HZ)
 
 
diff --git a/fs/ncpfs/ncplib_kernel.c b/fs/ncpfs/ncplib_kernel.c
index 981a95617fc9..482387532f54 100644
--- a/fs/ncpfs/ncplib_kernel.c
+++ b/fs/ncpfs/ncplib_kernel.c
@@ -9,14 +9,14 @@
  *
  */
 
-
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include "ncp_fs.h"
 
 static inline void assert_server_locked(struct ncp_server *server)
 {
 	if (server->lock == 0) {
-		DPRINTK("ncpfs: server not locked!\n");
+		ncp_dbg(1, "server not locked!\n");
 	}
 }
 
@@ -75,7 +75,7 @@ static void ncp_add_pstring(struct ncp_server *server, const char *s)
 	int len = strlen(s);
 	assert_server_locked(server);
 	if (len > 255) {
-		DPRINTK("ncpfs: string too long: %s\n", s);
+		ncp_dbg(1, "string too long: %s\n", s);
 		len = 255;
 	}
 	ncp_add_byte(server, len);
@@ -225,7 +225,7 @@ int ncp_get_volume_info_with_number(struct ncp_server* server,
 	result = -EIO;
 	len = ncp_reply_byte(server, 29);
 	if (len > NCP_VOLNAME_LEN) {
-		DPRINTK("ncpfs: volume name too long: %d\n", len);
+		ncp_dbg(1, "volume name too long: %d\n", len);
 		goto out;
 	}
 	memcpy(&(target->volume_name), ncp_reply_data(server, 30), len);
@@ -259,7 +259,7 @@ int ncp_get_directory_info(struct ncp_server* server, __u8 n,
 	result = -EIO;
 	len = ncp_reply_byte(server, 21);
 	if (len > NCP_VOLNAME_LEN) {
-		DPRINTK("ncpfs: volume name too long: %d\n", len);
+		ncp_dbg(1, "volume name too long: %d\n", len);
 		goto out;
 	}
 	memcpy(&(target->volume_name), ncp_reply_data(server, 22), len);
@@ -295,9 +295,9 @@ ncp_make_closed(struct inode *inode)
 		err = ncp_close_file(NCP_SERVER(inode), NCP_FINFO(inode)->file_handle);
 
 		if (!err)
-			PPRINTK("ncp_make_closed: volnum=%d, dirent=%u, error=%d\n",
-				NCP_FINFO(inode)->volNumber,
-				NCP_FINFO(inode)->dirEntNum, err);
+			ncp_vdbg("volnum=%d, dirent=%u, error=%d\n",
+				 NCP_FINFO(inode)->volNumber,
+				 NCP_FINFO(inode)->dirEntNum, err);
 	}
 	mutex_unlock(&NCP_FINFO(inode)->open_mutex);
 	return err;
@@ -394,8 +394,7 @@ int ncp_obtain_nfs_info(struct ncp_server *server,
 
 		if ((result = ncp_request(server, 87)) == 0) {
 			ncp_extract_nfs_info(ncp_reply_data(server, 0), &target->nfs);
-			DPRINTK(KERN_DEBUG
-				"ncp_obtain_nfs_info: (%s) mode=0%o, rdev=0x%x\n",
+			ncp_dbg(1, "(%s) mode=0%o, rdev=0x%x\n",
 				target->entryName, target->nfs.mode,
 				target->nfs.rdev);
 		} else {
@@ -425,7 +424,7 @@ int ncp_obtain_info(struct ncp_server *server, struct inode *dir, const char *pa
 	int result;
 
 	if (target == NULL) {
-		printk(KERN_ERR "ncp_obtain_info: invalid call\n");
+		pr_err("%s: invalid call\n", __func__);
 		return -EINVAL;
 	}
 	ncp_init_request(server);
@@ -498,7 +497,7 @@ ncp_get_known_namespace(struct ncp_server *server, __u8 volume)
 	namespace = ncp_reply_data(server, 2);
 
 	while (no_namespaces > 0) {
-		DPRINTK("get_namespaces: found %d on %d\n", *namespace, volume);
+		ncp_dbg(1, "found %d on %d\n", *namespace, volume);
 
 #ifdef CONFIG_NCPFS_NFS_NS
 		if ((*namespace == NW_NS_NFS) && !(server->m.flags&NCP_MOUNT_NO_NFS)) 
@@ -531,8 +530,7 @@ ncp_update_known_namespace(struct ncp_server *server, __u8 volume, int *ret_ns)
 	if (ret_ns)
 		*ret_ns = ns;
 
-	DPRINTK("lookup_vol: namespace[%d] = %d\n",
-		volume, server->name_space[volume]);
+	ncp_dbg(1, "namespace[%d] = %d\n", volume, server->name_space[volume]);
 
 	if (server->name_space[volume] == ns)
 		return 0;
@@ -596,7 +594,7 @@ ncp_get_volume_root(struct ncp_server *server,
 {
 	int result;
 
-	DPRINTK("ncp_get_volume_root: looking up vol %s\n", volname);
+	ncp_dbg(1, "looking up vol %s\n", volname);
 
 	ncp_init_request(server);
 	ncp_add_byte(server, 22);	/* Subfunction: Generate dir handle */
diff --git a/fs/ncpfs/sock.c b/fs/ncpfs/sock.c
index 3a1587222c8a..04a69a4d8e96 100644
--- a/fs/ncpfs/sock.c
+++ b/fs/ncpfs/sock.c
@@ -8,6 +8,7 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/time.h>
 #include <linux/errno.h>
@@ -231,7 +232,7 @@ static void __ncptcp_try_send(struct ncp_server *server)
 		return;
 
 	if (result < 0) {
-		printk(KERN_ERR "ncpfs: tcp: Send failed: %d\n", result);
+		pr_err("tcp: Send failed: %d\n", result);
 		__ncp_abort_request(server, rq, result);
 		return;
 	}
@@ -332,7 +333,7 @@ static int ncp_add_request(struct ncp_server *server, struct ncp_request_reply *
 	mutex_lock(&server->rcv.creq_mutex);
 	if (!ncp_conn_valid(server)) {
 		mutex_unlock(&server->rcv.creq_mutex);
-		printk(KERN_ERR "ncpfs: tcp: Server died\n");
+		pr_err("tcp: Server died\n");
 		return -EIO;
 	}
 	ncp_req_get(req);
@@ -405,15 +406,15 @@ void ncpdgram_rcv_proc(struct work_struct *work)
 				}
 				result = _recv(sock, buf, sizeof(buf), MSG_DONTWAIT);
 				if (result < 0) {
-					DPRINTK("recv failed with %d\n", result);
+					ncp_dbg(1, "recv failed with %d\n", result);
 					continue;
 				}
 				if (result < 10) {
-					DPRINTK("too short (%u) watchdog packet\n", result);
+					ncp_dbg(1, "too short (%u) watchdog packet\n", result);
 					continue;
 				}
 				if (buf[9] != '?') {
-					DPRINTK("bad signature (%02X) in watchdog packet\n", buf[9]);
+					ncp_dbg(1, "bad signature (%02X) in watchdog packet\n", buf[9]);
 					continue;
 				}
 				buf[9] = 'Y';
@@ -448,7 +449,7 @@ void ncpdgram_rcv_proc(struct work_struct *work)
 							result -= 8;
 							hdrl = sock->sk->sk_family == AF_INET ? 8 : 6;
 							if (sign_verify_reply(server, server->rxbuf + hdrl, result - hdrl, cpu_to_le32(result), server->rxbuf + result)) {
-								printk(KERN_INFO "ncpfs: Signature violation\n");
+								pr_info("Signature violation\n");
 								result = -EIO;
 							}
 						}
@@ -524,7 +525,7 @@ static int do_tcp_rcv(struct ncp_server *server, void *buffer, size_t len)
 		return result;
 	}
 	if (result > len) {
-		printk(KERN_ERR "ncpfs: tcp: bug in recvmsg (%u > %Zu)\n", result, len);
+		pr_err("tcp: bug in recvmsg (%u > %Zu)\n", result, len);
 		return -EIO;			
 	}
 	return result;
@@ -552,9 +553,9 @@ static int __ncptcp_rcv_proc(struct ncp_server *server)
 					__ncptcp_abort(server);
 				}
 				if (result < 0) {
-					printk(KERN_ERR "ncpfs: tcp: error in recvmsg: %d\n", result);
+					pr_err("tcp: error in recvmsg: %d\n", result);
 				} else {
-					DPRINTK(KERN_ERR "ncpfs: tcp: EOF\n");
+					ncp_dbg(1, "tcp: EOF\n");
 				}
 				return -EIO;
 			}
@@ -566,20 +567,20 @@ static int __ncptcp_rcv_proc(struct ncp_server *server)
 		switch (server->rcv.state) {
 			case 0:
 				if (server->rcv.buf.magic != htonl(NCP_TCP_RCVD_MAGIC)) {
-					printk(KERN_ERR "ncpfs: tcp: Unexpected reply type %08X\n", ntohl(server->rcv.buf.magic));
+					pr_err("tcp: Unexpected reply type %08X\n", ntohl(server->rcv.buf.magic));
 					__ncptcp_abort(server);
 					return -EIO;
 				}
 				datalen = ntohl(server->rcv.buf.len) & 0x0FFFFFFF;
 				if (datalen < 10) {
-					printk(KERN_ERR "ncpfs: tcp: Unexpected reply len %d\n", datalen);
+					pr_err("tcp: Unexpected reply len %d\n", datalen);
 					__ncptcp_abort(server);
 					return -EIO;
 				}
 #ifdef CONFIG_NCPFS_PACKET_SIGNING				
 				if (server->sign_active) {
 					if (datalen < 18) {
-						printk(KERN_ERR "ncpfs: tcp: Unexpected reply len %d\n", datalen);
+						pr_err("tcp: Unexpected reply len %d\n", datalen);
 						__ncptcp_abort(server);
 						return -EIO;
 					}
@@ -604,7 +605,7 @@ cont:;
 						server->rcv.len = datalen - 10;
 						break;
 					}					
-					DPRINTK("ncpfs: tcp: Unexpected NCP type %02X\n", type);
+					ncp_dbg(1, "tcp: Unexpected NCP type %02X\n", type);
 skipdata2:;
 					server->rcv.state = 2;
 skipdata:;
@@ -614,11 +615,11 @@ skipdata:;
 				}
 				req = server->rcv.creq;
 				if (!req) {
-					DPRINTK(KERN_ERR "ncpfs: Reply without appropriate request\n");
+					ncp_dbg(1, "Reply without appropriate request\n");
 					goto skipdata2;
 				}
 				if (datalen > req->datalen + 8) {
-					printk(KERN_ERR "ncpfs: tcp: Unexpected reply len %d (expected at most %Zd)\n", datalen, req->datalen + 8);
+					pr_err("tcp: Unexpected reply len %d (expected at most %Zd)\n", datalen, req->datalen + 8);
 					server->rcv.state = 3;
 					goto skipdata;
 				}
@@ -638,12 +639,12 @@ skipdata:;
 				req = server->rcv.creq;
 				if (req->tx_type != NCP_ALLOC_SLOT_REQUEST) {
 					if (((struct ncp_reply_header*)server->rxbuf)->sequence != server->sequence) {
-						printk(KERN_ERR "ncpfs: tcp: Bad sequence number\n");
+						pr_err("tcp: Bad sequence number\n");
 						__ncp_abort_request(server, req, -EIO);
 						return -EIO;
 					}
 					if ((((struct ncp_reply_header*)server->rxbuf)->conn_low | (((struct ncp_reply_header*)server->rxbuf)->conn_high << 8)) != server->connection) {
-						printk(KERN_ERR "ncpfs: tcp: Connection number mismatch\n");
+						pr_err("tcp: Connection number mismatch\n");
 						__ncp_abort_request(server, req, -EIO);
 						return -EIO;
 					}
@@ -651,7 +652,7 @@ skipdata:;
 #ifdef CONFIG_NCPFS_PACKET_SIGNING				
 				if (server->sign_active && req->tx_type != NCP_DEALLOC_SLOT_REQUEST) {
 					if (sign_verify_reply(server, server->rxbuf + 6, req->datalen - 6, cpu_to_be32(req->datalen + 16), &server->rcv.buf.type)) {
-						printk(KERN_ERR "ncpfs: tcp: Signature violation\n");
+						pr_err("tcp: Signature violation\n");
 						__ncp_abort_request(server, req, -EIO);
 						return -EIO;
 					}
@@ -742,7 +743,7 @@ static int ncp_do_request(struct ncp_server *server, int size,
 	int result;
 
 	if (server->lock == 0) {
-		printk(KERN_ERR "ncpfs: Server not locked!\n");
+		pr_err("Server not locked!\n");
 		return -EIO;
 	}
 	if (!ncp_conn_valid(server)) {
@@ -781,7 +782,7 @@ static int ncp_do_request(struct ncp_server *server, int size,
 		spin_unlock_irqrestore(&current->sighand->siglock, flags);
 	}
 
-	DDPRINTK("do_ncp_rpc_call returned %d\n", result);
+	ncp_dbg(2, "do_ncp_rpc_call returned %d\n", result);
 
 	return result;
 }
@@ -811,7 +812,7 @@ int ncp_request2(struct ncp_server *server, int function,
 
 	result = ncp_do_request(server, server->current_size, reply, size);
 	if (result < 0) {
-		DPRINTK("ncp_request_error: %d\n", result);
+		ncp_dbg(1, "ncp_request_error: %d\n", result);
 		goto out;
 	}
 	server->completion = reply->completion_code;
@@ -822,7 +823,7 @@ int ncp_request2(struct ncp_server *server, int function,
 	result = reply->completion_code;
 
 	if (result != 0)
-		PPRINTK("ncp_request: completion code=%x\n", result);
+		ncp_vdbg("completion code=%x\n", result);
 out:
 	return result;
 }
@@ -865,14 +866,14 @@ void ncp_lock_server(struct ncp_server *server)
 {
 	mutex_lock(&server->mutex);
 	if (server->lock)
-		printk(KERN_WARNING "ncp_lock_server: was locked!\n");
+		pr_warn("%s: was locked!\n", __func__);
 	server->lock = 1;
 }
 
 void ncp_unlock_server(struct ncp_server *server)
 {
 	if (!server->lock) {
-		printk(KERN_WARNING "ncp_unlock_server: was not locked!\n");
+		pr_warn("%s: was not locked!\n", __func__);
 		return;
 	}
 	server->lock = 0;
diff --git a/fs/ncpfs/symlink.c b/fs/ncpfs/symlink.c
index 52439ddc8de0..1a63bfdb4a65 100644
--- a/fs/ncpfs/symlink.c
+++ b/fs/ncpfs/symlink.c
@@ -112,7 +112,7 @@ int ncp_symlink(struct inode *dir, struct dentry *dentry, const char *symname) {
 	__le32 attr;
 	unsigned int hdr;
 
-	DPRINTK("ncp_symlink(dir=%p,dentry=%p,symname=%s)\n",dir,dentry,symname);
+	ncp_dbg(1, "dir=%p, dentry=%p, symname=%s\n", dir, dentry, symname);
 
 	if (ncp_is_nfs_extras(NCP_SERVER(dir), NCP_FINFO(dir)->volNumber))
 		kludge = 0;
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 56ff823ca82e..65d849bdf77a 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -1213,7 +1213,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx)
 	end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE);
 	if (end != NFS_I(inode)->npages) {
 		rcu_read_lock();
-		end = radix_tree_next_hole(&mapping->page_tree, idx + 1, ULONG_MAX);
+		end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX);
 		rcu_read_unlock();
 	}
 
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 5bb790a69c71..284ca901fe16 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -617,6 +617,7 @@ out:
 
 static const struct vm_operations_struct nfs_file_vm_ops = {
 	.fault = filemap_fault,
+	.map_pages = filemap_map_pages,
 	.page_mkwrite = nfs_vm_page_mkwrite,
 	.remap_pages = generic_file_remap_pages,
 };
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 9dbef878a2b2..0c438973f3c8 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -128,7 +128,7 @@ EXPORT_SYMBOL_GPL(nfs_clear_inode);
 
 void nfs_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	nfs_clear_inode(inode);
 }
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 808f29574412..6f340f02f2ba 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -90,7 +90,7 @@ static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc)
  */
 static void nfs4_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	pnfs_return_layout(inode);
 	pnfs_destroy_layout(NFS_I(inode));
diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c
index 06cddd572264..2645be435e75 100644
--- a/fs/nfsd/auth.c
+++ b/fs/nfsd/auth.c
@@ -71,10 +71,8 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 	if (gid_eq(new->fsgid, INVALID_GID))
 		new->fsgid = exp->ex_anon_gid;
 
-	ret = set_groups(new, gi);
+	set_groups(new, gi);
 	put_group_info(gi);
-	if (ret < 0)
-		goto error;
 
 	if (!uid_eq(new->fsuid, GLOBAL_ROOT_UID))
 		new->cap_effective = cap_drop_nfsd_set(new->cap_effective);
@@ -89,7 +87,6 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 
 oom:
 	ret = -ENOMEM;
-error:
 	abort_creds(new);
 	return ret;
 }
diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index deaa3d33a0aa..0d58075f34e2 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -942,6 +942,18 @@ int nilfs_cpfile_read(struct super_block *sb, size_t cpsize,
 	struct inode *cpfile;
 	int err;
 
+	if (cpsize > sb->s_blocksize) {
+		printk(KERN_ERR
+		       "NILFS: too large checkpoint size: %zu bytes.\n",
+		       cpsize);
+		return -EINVAL;
+	} else if (cpsize < NILFS_MIN_CHECKPOINT_SIZE) {
+		printk(KERN_ERR
+		       "NILFS: too small checkpoint size: %zu bytes.\n",
+		       cpsize);
+		return -EINVAL;
+	}
+
 	cpfile = nilfs_iget_locked(sb, NULL, NILFS_CPFILE_INO);
 	if (unlikely(!cpfile))
 		return -ENOMEM;
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index fa0f80308c2d..0d5fada91191 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -484,6 +484,18 @@ int nilfs_dat_read(struct super_block *sb, size_t entry_size,
 	struct nilfs_dat_info *di;
 	int err;
 
+	if (entry_size > sb->s_blocksize) {
+		printk(KERN_ERR
+		       "NILFS: too large DAT entry size: %zu bytes.\n",
+		       entry_size);
+		return -EINVAL;
+	} else if (entry_size < NILFS_MIN_DAT_ENTRY_SIZE) {
+		printk(KERN_ERR
+		       "NILFS: too small DAT entry size: %zu bytes.\n",
+		       entry_size);
+		return -EINVAL;
+	}
+
 	dat = nilfs_iget_locked(sb, NULL, NILFS_DAT_INO);
 	if (unlikely(!dat))
 		return -ENOMEM;
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 08fdb77852ac..f3a82fbcae02 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -134,6 +134,7 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 static const struct vm_operations_struct nilfs_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= nilfs_page_mkwrite,
 	.remap_pages	= generic_file_remap_pages,
 };
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 7e350c562e0e..b9c5726120e3 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -783,16 +783,14 @@ void nilfs_evict_inode(struct inode *inode)
 	int ret;
 
 	if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) {
-		if (inode->i_data.nrpages)
-			truncate_inode_pages(&inode->i_data, 0);
+		truncate_inode_pages_final(&inode->i_data);
 		clear_inode(inode);
 		nilfs_clear_inode(inode);
 		return;
 	}
 	nilfs_transaction_begin(sb, &ti, 0); /* never fails */
 
-	if (inode->i_data.nrpages)
-		truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	/* TODO: some of the following operations may fail.  */
 	nilfs_truncate_bmap(ii, 0);
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 2b34021948e4..422fb54b7377 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -1072,6 +1072,48 @@ out:
 }
 
 /**
+ * nilfs_ioctl_trim_fs() - trim ioctl handle function
+ * @inode: inode object
+ * @argp: pointer on argument from userspace
+ *
+ * Decription: nilfs_ioctl_trim_fs is the FITRIM ioctl handle function. It
+ * checks the arguments from userspace and calls nilfs_sufile_trim_fs, which
+ * performs the actual trim operation.
+ *
+ * Return Value: On success, 0 is returned or negative error code, otherwise.
+ */
+static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp)
+{
+	struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
+	struct request_queue *q = bdev_get_queue(nilfs->ns_bdev);
+	struct fstrim_range range;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!blk_queue_discard(q))
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&range, argp, sizeof(range)))
+		return -EFAULT;
+
+	range.minlen = max_t(u64, range.minlen, q->limits.discard_granularity);
+
+	down_read(&nilfs->ns_segctor_sem);
+	ret = nilfs_sufile_trim_fs(nilfs->ns_sufile, &range);
+	up_read(&nilfs->ns_segctor_sem);
+
+	if (ret < 0)
+		return ret;
+
+	if (copy_to_user(argp, &range, sizeof(range)))
+		return -EFAULT;
+
+	return 0;
+}
+
+/**
  * nilfs_ioctl_set_alloc_range - limit range of segments to be allocated
  * @inode: inode object
  * @argp: pointer on argument from userspace
@@ -1163,6 +1205,95 @@ static int nilfs_ioctl_get_info(struct inode *inode, struct file *filp,
 	return ret;
 }
 
+/**
+ * nilfs_ioctl_set_suinfo - set segment usage info
+ * @inode: inode object
+ * @filp: file object
+ * @cmd: ioctl's request code
+ * @argp: pointer on argument from userspace
+ *
+ * Description: Expects an array of nilfs_suinfo_update structures
+ * encapsulated in nilfs_argv and updates the segment usage info
+ * according to the flags in nilfs_suinfo_update.
+ *
+ * Return Value: On success, 0 is returned. On error, one of the
+ * following negative error codes is returned.
+ *
+ * %-EPERM - Not enough permissions
+ *
+ * %-EFAULT - Error copying input data
+ *
+ * %-EIO - I/O error.
+ *
+ * %-ENOMEM - Insufficient amount of memory available.
+ *
+ * %-EINVAL - Invalid values in input (segment number, flags or nblocks)
+ */
+static int nilfs_ioctl_set_suinfo(struct inode *inode, struct file *filp,
+				unsigned int cmd, void __user *argp)
+{
+	struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
+	struct nilfs_transaction_info ti;
+	struct nilfs_argv argv;
+	size_t len;
+	void __user *base;
+	void *kbuf;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
+	ret = -EFAULT;
+	if (copy_from_user(&argv, argp, sizeof(argv)))
+		goto out;
+
+	ret = -EINVAL;
+	if (argv.v_size < sizeof(struct nilfs_suinfo_update))
+		goto out;
+
+	if (argv.v_nmembs > nilfs->ns_nsegments)
+		goto out;
+
+	if (argv.v_nmembs >= UINT_MAX / argv.v_size)
+		goto out;
+
+	len = argv.v_size * argv.v_nmembs;
+	if (!len) {
+		ret = 0;
+		goto out;
+	}
+
+	base = (void __user *)(unsigned long)argv.v_base;
+	kbuf = vmalloc(len);
+	if (!kbuf) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	if (copy_from_user(kbuf, base, len)) {
+		ret = -EFAULT;
+		goto out_free;
+	}
+
+	nilfs_transaction_begin(inode->i_sb, &ti, 0);
+	ret = nilfs_sufile_set_suinfo(nilfs->ns_sufile, kbuf, argv.v_size,
+			argv.v_nmembs);
+	if (unlikely(ret < 0))
+		nilfs_transaction_abort(inode->i_sb);
+	else
+		nilfs_transaction_commit(inode->i_sb); /* never fails */
+
+out_free:
+	vfree(kbuf);
+out:
+	mnt_drop_write_file(filp);
+	return ret;
+}
+
 long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
@@ -1189,6 +1320,8 @@ long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return nilfs_ioctl_get_info(inode, filp, cmd, argp,
 					    sizeof(struct nilfs_suinfo),
 					    nilfs_ioctl_do_get_suinfo);
+	case NILFS_IOCTL_SET_SUINFO:
+		return nilfs_ioctl_set_suinfo(inode, filp, cmd, argp);
 	case NILFS_IOCTL_GET_SUSTAT:
 		return nilfs_ioctl_get_sustat(inode, filp, cmd, argp);
 	case NILFS_IOCTL_GET_VINFO:
@@ -1205,6 +1338,8 @@ long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return nilfs_ioctl_resize(inode, filp, argp);
 	case NILFS_IOCTL_SET_ALLOC_RANGE:
 		return nilfs_ioctl_set_alloc_range(inode, argp);
+	case FITRIM:
+		return nilfs_ioctl_trim_fs(inode, argp);
 	default:
 		return -ENOTTY;
 	}
@@ -1228,6 +1363,7 @@ long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	case NILFS_IOCTL_GET_CPINFO:
 	case NILFS_IOCTL_GET_CPSTAT:
 	case NILFS_IOCTL_GET_SUINFO:
+	case NILFS_IOCTL_SET_SUINFO:
 	case NILFS_IOCTL_GET_SUSTAT:
 	case NILFS_IOCTL_GET_VINFO:
 	case NILFS_IOCTL_GET_BDESCS:
@@ -1235,6 +1371,7 @@ long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	case NILFS_IOCTL_SYNC:
 	case NILFS_IOCTL_RESIZE:
 	case NILFS_IOCTL_SET_ALLOC_RANGE:
+	case FITRIM:
 		break;
 	default:
 		return -ENOIOCTLCMD;
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index 3127e9f438a7..2a869c35c362 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -870,6 +870,289 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
 }
 
 /**
+ * nilfs_sufile_set_suinfo - sets segment usage info
+ * @sufile: inode of segment usage file
+ * @buf: array of suinfo_update
+ * @supsz: byte size of suinfo_update
+ * @nsup: size of suinfo_update array
+ *
+ * Description: Takes an array of nilfs_suinfo_update structs and updates
+ * segment usage accordingly. Only the fields indicated by the sup_flags
+ * are updated.
+ *
+ * Return Value: On success, 0 is returned. On error, one of the
+ * following negative error codes is returned.
+ *
+ * %-EIO - I/O error.
+ *
+ * %-ENOMEM - Insufficient amount of memory available.
+ *
+ * %-EINVAL - Invalid values in input (segment number, flags or nblocks)
+ */
+ssize_t nilfs_sufile_set_suinfo(struct inode *sufile, void *buf,
+				unsigned supsz, size_t nsup)
+{
+	struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
+	struct buffer_head *header_bh, *bh;
+	struct nilfs_suinfo_update *sup, *supend = buf + supsz * nsup;
+	struct nilfs_segment_usage *su;
+	void *kaddr;
+	unsigned long blkoff, prev_blkoff;
+	int cleansi, cleansu, dirtysi, dirtysu;
+	long ncleaned = 0, ndirtied = 0;
+	int ret = 0;
+
+	if (unlikely(nsup == 0))
+		return ret;
+
+	for (sup = buf; sup < supend; sup = (void *)sup + supsz) {
+		if (sup->sup_segnum >= nilfs->ns_nsegments
+			|| (sup->sup_flags &
+				(~0UL << __NR_NILFS_SUINFO_UPDATE_FIELDS))
+			|| (nilfs_suinfo_update_nblocks(sup) &&
+				sup->sup_sui.sui_nblocks >
+				nilfs->ns_blocks_per_segment))
+			return -EINVAL;
+	}
+
+	down_write(&NILFS_MDT(sufile)->mi_sem);
+
+	ret = nilfs_sufile_get_header_block(sufile, &header_bh);
+	if (ret < 0)
+		goto out_sem;
+
+	sup = buf;
+	blkoff = nilfs_sufile_get_blkoff(sufile, sup->sup_segnum);
+	ret = nilfs_mdt_get_block(sufile, blkoff, 1, NULL, &bh);
+	if (ret < 0)
+		goto out_header;
+
+	for (;;) {
+		kaddr = kmap_atomic(bh->b_page);
+		su = nilfs_sufile_block_get_segment_usage(
+			sufile, sup->sup_segnum, bh, kaddr);
+
+		if (nilfs_suinfo_update_lastmod(sup))
+			su->su_lastmod = cpu_to_le64(sup->sup_sui.sui_lastmod);
+
+		if (nilfs_suinfo_update_nblocks(sup))
+			su->su_nblocks = cpu_to_le32(sup->sup_sui.sui_nblocks);
+
+		if (nilfs_suinfo_update_flags(sup)) {
+			/*
+			 * Active flag is a virtual flag projected by running
+			 * nilfs kernel code - drop it not to write it to
+			 * disk.
+			 */
+			sup->sup_sui.sui_flags &=
+					~(1UL << NILFS_SEGMENT_USAGE_ACTIVE);
+
+			cleansi = nilfs_suinfo_clean(&sup->sup_sui);
+			cleansu = nilfs_segment_usage_clean(su);
+			dirtysi = nilfs_suinfo_dirty(&sup->sup_sui);
+			dirtysu = nilfs_segment_usage_dirty(su);
+
+			if (cleansi && !cleansu)
+				++ncleaned;
+			else if (!cleansi && cleansu)
+				--ncleaned;
+
+			if (dirtysi && !dirtysu)
+				++ndirtied;
+			else if (!dirtysi && dirtysu)
+				--ndirtied;
+
+			su->su_flags = cpu_to_le32(sup->sup_sui.sui_flags);
+		}
+
+		kunmap_atomic(kaddr);
+
+		sup = (void *)sup + supsz;
+		if (sup >= supend)
+			break;
+
+		prev_blkoff = blkoff;
+		blkoff = nilfs_sufile_get_blkoff(sufile, sup->sup_segnum);
+		if (blkoff == prev_blkoff)
+			continue;
+
+		/* get different block */
+		mark_buffer_dirty(bh);
+		put_bh(bh);
+		ret = nilfs_mdt_get_block(sufile, blkoff, 1, NULL, &bh);
+		if (unlikely(ret < 0))
+			goto out_mark;
+	}
+	mark_buffer_dirty(bh);
+	put_bh(bh);
+
+ out_mark:
+	if (ncleaned || ndirtied) {
+		nilfs_sufile_mod_counter(header_bh, (u64)ncleaned,
+				(u64)ndirtied);
+		NILFS_SUI(sufile)->ncleansegs += ncleaned;
+	}
+	nilfs_mdt_mark_dirty(sufile);
+ out_header:
+	put_bh(header_bh);
+ out_sem:
+	up_write(&NILFS_MDT(sufile)->mi_sem);
+	return ret;
+}
+
+/**
+ * nilfs_sufile_trim_fs() - trim ioctl handle function
+ * @sufile: inode of segment usage file
+ * @range: fstrim_range structure
+ *
+ * start:	First Byte to trim
+ * len:		number of Bytes to trim from start
+ * minlen:	minimum extent length in Bytes
+ *
+ * Decription: nilfs_sufile_trim_fs goes through all segments containing bytes
+ * from start to start+len. start is rounded up to the next block boundary
+ * and start+len is rounded down. For each clean segment blkdev_issue_discard
+ * function is invoked.
+ *
+ * Return Value: On success, 0 is returned or negative error code, otherwise.
+ */
+int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range)
+{
+	struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
+	struct buffer_head *su_bh;
+	struct nilfs_segment_usage *su;
+	void *kaddr;
+	size_t n, i, susz = NILFS_MDT(sufile)->mi_entry_size;
+	sector_t seg_start, seg_end, start_block, end_block;
+	sector_t start = 0, nblocks = 0;
+	u64 segnum, segnum_end, minlen, len, max_blocks, ndiscarded = 0;
+	int ret = 0;
+	unsigned int sects_per_block;
+
+	sects_per_block = (1 << nilfs->ns_blocksize_bits) /
+			bdev_logical_block_size(nilfs->ns_bdev);
+	len = range->len >> nilfs->ns_blocksize_bits;
+	minlen = range->minlen >> nilfs->ns_blocksize_bits;
+	max_blocks = ((u64)nilfs->ns_nsegments * nilfs->ns_blocks_per_segment);
+
+	if (!len || range->start >= max_blocks << nilfs->ns_blocksize_bits)
+		return -EINVAL;
+
+	start_block = (range->start + nilfs->ns_blocksize - 1) >>
+			nilfs->ns_blocksize_bits;
+
+	/*
+	 * range->len can be very large (actually, it is set to
+	 * ULLONG_MAX by default) - truncate upper end of the range
+	 * carefully so as not to overflow.
+	 */
+	if (max_blocks - start_block < len)
+		end_block = max_blocks - 1;
+	else
+		end_block = start_block + len - 1;
+
+	segnum = nilfs_get_segnum_of_block(nilfs, start_block);
+	segnum_end = nilfs_get_segnum_of_block(nilfs, end_block);
+
+	down_read(&NILFS_MDT(sufile)->mi_sem);
+
+	while (segnum <= segnum_end) {
+		n = nilfs_sufile_segment_usages_in_block(sufile, segnum,
+				segnum_end);
+
+		ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0,
+							   &su_bh);
+		if (ret < 0) {
+			if (ret != -ENOENT)
+				goto out_sem;
+			/* hole */
+			segnum += n;
+			continue;
+		}
+
+		kaddr = kmap_atomic(su_bh->b_page);
+		su = nilfs_sufile_block_get_segment_usage(sufile, segnum,
+				su_bh, kaddr);
+		for (i = 0; i < n; ++i, ++segnum, su = (void *)su + susz) {
+			if (!nilfs_segment_usage_clean(su))
+				continue;
+
+			nilfs_get_segment_range(nilfs, segnum, &seg_start,
+						&seg_end);
+
+			if (!nblocks) {
+				/* start new extent */
+				start = seg_start;
+				nblocks = seg_end - seg_start + 1;
+				continue;
+			}
+
+			if (start + nblocks == seg_start) {
+				/* add to previous extent */
+				nblocks += seg_end - seg_start + 1;
+				continue;
+			}
+
+			/* discard previous extent */
+			if (start < start_block) {
+				nblocks -= start_block - start;
+				start = start_block;
+			}
+
+			if (nblocks >= minlen) {
+				kunmap_atomic(kaddr);
+
+				ret = blkdev_issue_discard(nilfs->ns_bdev,
+						start * sects_per_block,
+						nblocks * sects_per_block,
+						GFP_NOFS, 0);
+				if (ret < 0) {
+					put_bh(su_bh);
+					goto out_sem;
+				}
+
+				ndiscarded += nblocks;
+				kaddr = kmap_atomic(su_bh->b_page);
+				su = nilfs_sufile_block_get_segment_usage(
+					sufile, segnum, su_bh, kaddr);
+			}
+
+			/* start new extent */
+			start = seg_start;
+			nblocks = seg_end - seg_start + 1;
+		}
+		kunmap_atomic(kaddr);
+		put_bh(su_bh);
+	}
+
+
+	if (nblocks) {
+		/* discard last extent */
+		if (start < start_block) {
+			nblocks -= start_block - start;
+			start = start_block;
+		}
+		if (start + nblocks > end_block + 1)
+			nblocks = end_block - start + 1;
+
+		if (nblocks >= minlen) {
+			ret = blkdev_issue_discard(nilfs->ns_bdev,
+					start * sects_per_block,
+					nblocks * sects_per_block,
+					GFP_NOFS, 0);
+			if (!ret)
+				ndiscarded += nblocks;
+		}
+	}
+
+out_sem:
+	up_read(&NILFS_MDT(sufile)->mi_sem);
+
+	range->len = ndiscarded << nilfs->ns_blocksize_bits;
+	return ret;
+}
+
+/**
  * nilfs_sufile_read - read or get sufile inode
  * @sb: super block instance
  * @susize: size of a segment usage entry
@@ -886,6 +1169,18 @@ int nilfs_sufile_read(struct super_block *sb, size_t susize,
 	void *kaddr;
 	int err;
 
+	if (susize > sb->s_blocksize) {
+		printk(KERN_ERR
+		       "NILFS: too large segment usage size: %zu bytes.\n",
+		       susize);
+		return -EINVAL;
+	} else if (susize < NILFS_MIN_SEGMENT_USAGE_SIZE) {
+		printk(KERN_ERR
+		       "NILFS: too small segment usage size: %zu bytes.\n",
+		       susize);
+		return -EINVAL;
+	}
+
 	sufile = nilfs_iget_locked(sb, NULL, NILFS_SUFILE_INO);
 	if (unlikely(!sufile))
 		return -ENOMEM;
diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h
index e84bc5b51fc1..b8afd72f2379 100644
--- a/fs/nilfs2/sufile.h
+++ b/fs/nilfs2/sufile.h
@@ -44,6 +44,7 @@ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum,
 int nilfs_sufile_get_stat(struct inode *, struct nilfs_sustat *);
 ssize_t nilfs_sufile_get_suinfo(struct inode *, __u64, void *, unsigned,
 				size_t);
+ssize_t nilfs_sufile_set_suinfo(struct inode *, void *, unsigned , size_t);
 
 int nilfs_sufile_updatev(struct inode *, __u64 *, size_t, int, size_t *,
 			 void (*dofunc)(struct inode *, __u64,
@@ -65,6 +66,7 @@ void nilfs_sufile_do_set_error(struct inode *, __u64, struct buffer_head *,
 int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs);
 int nilfs_sufile_read(struct super_block *sb, size_t susize,
 		      struct nilfs_inode *raw_inode, struct inode **inodep);
+int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range);
 
 /**
  * nilfs_sufile_scrap - make a segment garbage
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 94c451ce6d24..8ba8229ba076 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -399,6 +399,16 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
 		return -EINVAL;
 
 	nilfs->ns_inode_size = le16_to_cpu(sbp->s_inode_size);
+	if (nilfs->ns_inode_size > nilfs->ns_blocksize) {
+		printk(KERN_ERR "NILFS: too large inode size: %d bytes.\n",
+		       nilfs->ns_inode_size);
+		return -EINVAL;
+	} else if (nilfs->ns_inode_size < NILFS_MIN_INODE_SIZE) {
+		printk(KERN_ERR "NILFS: too small inode size: %d bytes.\n",
+		       nilfs->ns_inode_size);
+		return -EINVAL;
+	}
+
 	nilfs->ns_first_ino = le32_to_cpu(sbp->s_first_ino);
 
 	nilfs->ns_blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment);
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index dc638f786d5c..ee9cb3795c2b 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -60,8 +60,8 @@ static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
 }
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-static int fanotify_get_response_from_access(struct fsnotify_group *group,
-					     struct fanotify_event_info *event)
+static int fanotify_get_response(struct fsnotify_group *group,
+				 struct fanotify_perm_event_info *event)
 {
 	int ret;
 
@@ -142,6 +142,40 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark,
 	return false;
 }
 
+struct fanotify_event_info *fanotify_alloc_event(struct inode *inode, u32 mask,
+						 struct path *path)
+{
+	struct fanotify_event_info *event;
+
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	if (mask & FAN_ALL_PERM_EVENTS) {
+		struct fanotify_perm_event_info *pevent;
+
+		pevent = kmem_cache_alloc(fanotify_perm_event_cachep,
+					  GFP_KERNEL);
+		if (!pevent)
+			return NULL;
+		event = &pevent->fae;
+		pevent->response = 0;
+		goto init;
+	}
+#endif
+	event = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL);
+	if (!event)
+		return NULL;
+init: __maybe_unused
+	fsnotify_init_event(&event->fse, inode, mask);
+	event->tgid = get_pid(task_tgid(current));
+	if (path) {
+		event->path = *path;
+		path_get(&event->path);
+	} else {
+		event->path.mnt = NULL;
+		event->path.dentry = NULL;
+	}
+	return event;
+}
+
 static int fanotify_handle_event(struct fsnotify_group *group,
 				 struct inode *inode,
 				 struct fsnotify_mark *inode_mark,
@@ -171,25 +205,11 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 	pr_debug("%s: group=%p inode=%p mask=%x\n", __func__, group, inode,
 		 mask);
 
-	event = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL);
+	event = fanotify_alloc_event(inode, mask, data);
 	if (unlikely(!event))
 		return -ENOMEM;
 
 	fsn_event = &event->fse;
-	fsnotify_init_event(fsn_event, inode, mask);
-	event->tgid = get_pid(task_tgid(current));
-	if (data_type == FSNOTIFY_EVENT_PATH) {
-		struct path *path = data;
-		event->path = *path;
-		path_get(&event->path);
-	} else {
-		event->path.mnt = NULL;
-		event->path.dentry = NULL;
-	}
-#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-	event->response = 0;
-#endif
-
 	ret = fsnotify_add_notify_event(group, fsn_event, fanotify_merge);
 	if (ret) {
 		/* Permission events shouldn't be merged */
@@ -202,7 +222,7 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 	if (mask & FAN_ALL_PERM_EVENTS) {
-		ret = fanotify_get_response_from_access(group, event);
+		ret = fanotify_get_response(group, FANOTIFY_PE(fsn_event));
 		fsnotify_destroy_event(group, fsn_event);
 	}
 #endif
@@ -225,6 +245,13 @@ static void fanotify_free_event(struct fsnotify_event *fsn_event)
 	event = FANOTIFY_E(fsn_event);
 	path_put(&event->path);
 	put_pid(event->tgid);
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	if (fsn_event->mask & FAN_ALL_PERM_EVENTS) {
+		kmem_cache_free(fanotify_perm_event_cachep,
+				FANOTIFY_PE(fsn_event));
+		return;
+	}
+#endif
 	kmem_cache_free(fanotify_event_cachep, event);
 }
 
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
index 32a2f034fb94..2a5fb14115df 100644
--- a/fs/notify/fanotify/fanotify.h
+++ b/fs/notify/fanotify/fanotify.h
@@ -3,13 +3,12 @@
 #include <linux/slab.h>
 
 extern struct kmem_cache *fanotify_event_cachep;
+extern struct kmem_cache *fanotify_perm_event_cachep;
 
 /*
- * Lifetime of the structure differs for normal and permission events. In both
- * cases the structure is allocated in fanotify_handle_event(). For normal
- * events the structure is freed immediately after reporting it to userspace.
- * For permission events we free it only after we receive response from
- * userspace.
+ * Structure for normal fanotify events. It gets allocated in
+ * fanotify_handle_event() and freed when the information is retrieved by
+ * userspace
  */
 struct fanotify_event_info {
 	struct fsnotify_event fse;
@@ -19,12 +18,33 @@ struct fanotify_event_info {
 	 */
 	struct path path;
 	struct pid *tgid;
+};
+
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-	u32 response;	/* userspace answer to question */
-#endif
+/*
+ * Structure for permission fanotify events. It gets allocated and freed in
+ * fanotify_handle_event() since we wait there for user response. When the
+ * information is retrieved by userspace the structure is moved from
+ * group->notification_list to group->fanotify_data.access_list to wait for
+ * user response.
+ */
+struct fanotify_perm_event_info {
+	struct fanotify_event_info fae;
+	int response;	/* userspace answer to question */
+	int fd;		/* fd we passed to userspace for this event */
 };
 
+static inline struct fanotify_perm_event_info *
+FANOTIFY_PE(struct fsnotify_event *fse)
+{
+	return container_of(fse, struct fanotify_perm_event_info, fae.fse);
+}
+#endif
+
 static inline struct fanotify_event_info *FANOTIFY_E(struct fsnotify_event *fse)
 {
 	return container_of(fse, struct fanotify_event_info, fse);
 }
+
+struct fanotify_event_info *fanotify_alloc_event(struct inode *inode, u32 mask,
+						 struct path *path);
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 287a22c04149..4e565c814309 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -28,14 +28,8 @@
 extern const struct fsnotify_ops fanotify_fsnotify_ops;
 
 static struct kmem_cache *fanotify_mark_cache __read_mostly;
-static struct kmem_cache *fanotify_response_event_cache __read_mostly;
 struct kmem_cache *fanotify_event_cachep __read_mostly;
-
-struct fanotify_response_event {
-	struct list_head list;
-	__s32 fd;
-	struct fanotify_event_info *event;
-};
+struct kmem_cache *fanotify_perm_event_cachep __read_mostly;
 
 /*
  * Get an fsnotify notification event if one exists and is small
@@ -135,33 +129,34 @@ static int fill_event_metadata(struct fsnotify_group *group,
 }
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-static struct fanotify_response_event *dequeue_re(struct fsnotify_group *group,
-						  __s32 fd)
+static struct fanotify_perm_event_info *dequeue_event(
+				struct fsnotify_group *group, int fd)
 {
-	struct fanotify_response_event *re, *return_re = NULL;
+	struct fanotify_perm_event_info *event, *return_e = NULL;
 
-	mutex_lock(&group->fanotify_data.access_mutex);
-	list_for_each_entry(re, &group->fanotify_data.access_list, list) {
-		if (re->fd != fd)
+	spin_lock(&group->fanotify_data.access_lock);
+	list_for_each_entry(event, &group->fanotify_data.access_list,
+			    fae.fse.list) {
+		if (event->fd != fd)
 			continue;
 
-		list_del_init(&re->list);
-		return_re = re;
+		list_del_init(&event->fae.fse.list);
+		return_e = event;
 		break;
 	}
-	mutex_unlock(&group->fanotify_data.access_mutex);
+	spin_unlock(&group->fanotify_data.access_lock);
 
-	pr_debug("%s: found return_re=%p\n", __func__, return_re);
+	pr_debug("%s: found return_re=%p\n", __func__, return_e);
 
-	return return_re;
+	return return_e;
 }
 
 static int process_access_response(struct fsnotify_group *group,
 				   struct fanotify_response *response_struct)
 {
-	struct fanotify_response_event *re;
-	__s32 fd = response_struct->fd;
-	__u32 response = response_struct->response;
+	struct fanotify_perm_event_info *event;
+	int fd = response_struct->fd;
+	int response = response_struct->response;
 
 	pr_debug("%s: group=%p fd=%d response=%d\n", __func__, group,
 		 fd, response);
@@ -181,58 +176,15 @@ static int process_access_response(struct fsnotify_group *group,
 	if (fd < 0)
 		return -EINVAL;
 
-	re = dequeue_re(group, fd);
-	if (!re)
+	event = dequeue_event(group, fd);
+	if (!event)
 		return -ENOENT;
 
-	re->event->response = response;
-
+	event->response = response;
 	wake_up(&group->fanotify_data.access_waitq);
 
-	kmem_cache_free(fanotify_response_event_cache, re);
-
-	return 0;
-}
-
-static int prepare_for_access_response(struct fsnotify_group *group,
-				       struct fsnotify_event *event,
-				       __s32 fd)
-{
-	struct fanotify_response_event *re;
-
-	if (!(event->mask & FAN_ALL_PERM_EVENTS))
-		return 0;
-
-	re = kmem_cache_alloc(fanotify_response_event_cache, GFP_KERNEL);
-	if (!re)
-		return -ENOMEM;
-
-	re->event = FANOTIFY_E(event);
-	re->fd = fd;
-
-	mutex_lock(&group->fanotify_data.access_mutex);
-
-	if (atomic_read(&group->fanotify_data.bypass_perm)) {
-		mutex_unlock(&group->fanotify_data.access_mutex);
-		kmem_cache_free(fanotify_response_event_cache, re);
-		FANOTIFY_E(event)->response = FAN_ALLOW;
-		return 0;
-	}
-		
-	list_add_tail(&re->list, &group->fanotify_data.access_list);
-	mutex_unlock(&group->fanotify_data.access_mutex);
-
-	return 0;
-}
-
-#else
-static int prepare_for_access_response(struct fsnotify_group *group,
-				       struct fsnotify_event *event,
-				       __s32 fd)
-{
 	return 0;
 }
-
 #endif
 
 static ssize_t copy_event_to_user(struct fsnotify_group *group,
@@ -247,7 +199,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 
 	ret = fill_event_metadata(group, &fanotify_event_metadata, event, &f);
 	if (ret < 0)
-		goto out;
+		return ret;
 
 	fd = fanotify_event_metadata.fd;
 	ret = -EFAULT;
@@ -255,9 +207,10 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 			 fanotify_event_metadata.event_len))
 		goto out_close_fd;
 
-	ret = prepare_for_access_response(group, event, fd);
-	if (ret)
-		goto out_close_fd;
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	if (event->mask & FAN_ALL_PERM_EVENTS)
+		FANOTIFY_PE(event)->fd = fd;
+#endif
 
 	if (fd != FAN_NOFD)
 		fd_install(fd, f);
@@ -268,13 +221,6 @@ out_close_fd:
 		put_unused_fd(fd);
 		fput(f);
 	}
-out:
-#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-	if (event->mask & FAN_ALL_PERM_EVENTS) {
-		FANOTIFY_E(event)->response = FAN_DENY;
-		wake_up(&group->fanotify_data.access_waitq);
-	}
-#endif
 	return ret;
 }
 
@@ -314,35 +260,50 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
 		kevent = get_one_event(group, count);
 		mutex_unlock(&group->notification_mutex);
 
-		if (kevent) {
+		if (IS_ERR(kevent)) {
 			ret = PTR_ERR(kevent);
-			if (IS_ERR(kevent))
+			break;
+		}
+
+		if (!kevent) {
+			ret = -EAGAIN;
+			if (file->f_flags & O_NONBLOCK)
 				break;
-			ret = copy_event_to_user(group, kevent, buf);
-			/*
-			 * Permission events get destroyed after we
-			 * receive response
-			 */
-			if (!(kevent->mask & FAN_ALL_PERM_EVENTS))
-				fsnotify_destroy_event(group, kevent);
-			if (ret < 0)
+
+			ret = -ERESTARTSYS;
+			if (signal_pending(current))
+				break;
+
+			if (start != buf)
 				break;
-			buf += ret;
-			count -= ret;
+			schedule();
 			continue;
 		}
 
-		ret = -EAGAIN;
-		if (file->f_flags & O_NONBLOCK)
-			break;
-		ret = -ERESTARTSYS;
-		if (signal_pending(current))
-			break;
-
-		if (start != buf)
-			break;
-
-		schedule();
+		ret = copy_event_to_user(group, kevent, buf);
+		/*
+		 * Permission events get queued to wait for response.  Other
+		 * events can be destroyed now.
+		 */
+		if (!(kevent->mask & FAN_ALL_PERM_EVENTS)) {
+			fsnotify_destroy_event(group, kevent);
+			if (ret < 0)
+				break;
+		} else {
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+			if (ret < 0) {
+				FANOTIFY_PE(kevent)->response = FAN_DENY;
+				wake_up(&group->fanotify_data.access_waitq);
+				break;
+			}
+			spin_lock(&group->fanotify_data.access_lock);
+			list_add_tail(&kevent->list,
+				      &group->fanotify_data.access_list);
+			spin_unlock(&group->fanotify_data.access_lock);
+#endif
+		}
+		buf += ret;
+		count -= ret;
 	}
 
 	finish_wait(&group->notification_waitq, &wait);
@@ -383,22 +344,21 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 	struct fsnotify_group *group = file->private_data;
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-	struct fanotify_response_event *re, *lre;
+	struct fanotify_perm_event_info *event, *next;
 
-	mutex_lock(&group->fanotify_data.access_mutex);
+	spin_lock(&group->fanotify_data.access_lock);
 
 	atomic_inc(&group->fanotify_data.bypass_perm);
 
-	list_for_each_entry_safe(re, lre, &group->fanotify_data.access_list, list) {
-		pr_debug("%s: found group=%p re=%p event=%p\n", __func__, group,
-			 re, re->event);
+	list_for_each_entry_safe(event, next, &group->fanotify_data.access_list,
+				 fae.fse.list) {
+		pr_debug("%s: found group=%p event=%p\n", __func__, group,
+			 event);
 
-		list_del_init(&re->list);
-		re->event->response = FAN_ALLOW;
-
-		kmem_cache_free(fanotify_response_event_cache, re);
+		list_del_init(&event->fae.fse.list);
+		event->response = FAN_ALLOW;
 	}
-	mutex_unlock(&group->fanotify_data.access_mutex);
+	spin_unlock(&group->fanotify_data.access_lock);
 
 	wake_up(&group->fanotify_data.access_waitq);
 #endif
@@ -731,21 +691,16 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	group->fanotify_data.user = user;
 	atomic_inc(&user->fanotify_listeners);
 
-	oevent = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL);
+	oevent = fanotify_alloc_event(NULL, FS_Q_OVERFLOW, NULL);
 	if (unlikely(!oevent)) {
 		fd = -ENOMEM;
 		goto out_destroy_group;
 	}
 	group->overflow_event = &oevent->fse;
-	fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW);
-	oevent->tgid = get_pid(task_tgid(current));
-	oevent->path.mnt = NULL;
-	oevent->path.dentry = NULL;
 
 	group->fanotify_data.f_flags = event_f_flags;
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-	oevent->response = 0;
-	mutex_init(&group->fanotify_data.access_mutex);
+	spin_lock_init(&group->fanotify_data.access_lock);
 	init_waitqueue_head(&group->fanotify_data.access_waitq);
 	INIT_LIST_HEAD(&group->fanotify_data.access_list);
 	atomic_set(&group->fanotify_data.bypass_perm, 0);
@@ -920,9 +875,11 @@ COMPAT_SYSCALL_DEFINE6(fanotify_mark,
 static int __init fanotify_user_setup(void)
 {
 	fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, SLAB_PANIC);
-	fanotify_response_event_cache = KMEM_CACHE(fanotify_response_event,
-						   SLAB_PANIC);
 	fanotify_event_cachep = KMEM_CACHE(fanotify_event_info, SLAB_PANIC);
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	fanotify_perm_event_cachep = KMEM_CACHE(fanotify_perm_event_info,
+						SLAB_PANIC);
+#endif
 
 	return 0;
 }
diff --git a/fs/ntfs/debug.c b/fs/ntfs/debug.c
index 807150e2c2b9..dd6103cc93c1 100644
--- a/fs/ntfs/debug.c
+++ b/fs/ntfs/debug.c
@@ -18,16 +18,9 @@
  * distribution in the file COPYING); if not, write to the Free Software
  * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
-
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #include "debug.h"
 
-/*
- * A static buffer to hold the error string being displayed and a spinlock
- * to protect concurrent accesses to it.
- */
-static char err_buf[1024];
-static DEFINE_SPINLOCK(err_buf_lock);
-
 /**
  * __ntfs_warning - output a warning to the syslog
  * @function:	name of function outputting the warning
@@ -50,6 +43,7 @@ static DEFINE_SPINLOCK(err_buf_lock);
 void __ntfs_warning(const char *function, const struct super_block *sb,
 		const char *fmt, ...)
 {
+	struct va_format vaf;
 	va_list args;
 	int flen = 0;
 
@@ -59,17 +53,15 @@ void __ntfs_warning(const char *function, const struct super_block *sb,
 #endif
 	if (function)
 		flen = strlen(function);
-	spin_lock(&err_buf_lock);
 	va_start(args, fmt);
-	vsnprintf(err_buf, sizeof(err_buf), fmt, args);
-	va_end(args);
+	vaf.fmt = fmt;
+	vaf.va = &args;
 	if (sb)
-		printk(KERN_ERR "NTFS-fs warning (device %s): %s(): %s\n",
-				sb->s_id, flen ? function : "", err_buf);
+		pr_warn("(device %s): %s(): %pV\n",
+			sb->s_id, flen ? function : "", &vaf);
 	else
-		printk(KERN_ERR "NTFS-fs warning: %s(): %s\n",
-				flen ? function : "", err_buf);
-	spin_unlock(&err_buf_lock);
+		pr_warn("%s(): %pV\n", flen ? function : "", &vaf);
+	va_end(args);
 }
 
 /**
@@ -94,6 +86,7 @@ void __ntfs_warning(const char *function, const struct super_block *sb,
 void __ntfs_error(const char *function, const struct super_block *sb,
 		const char *fmt, ...)
 {
+	struct va_format vaf;
 	va_list args;
 	int flen = 0;
 
@@ -103,17 +96,15 @@ void __ntfs_error(const char *function, const struct super_block *sb,
 #endif
 	if (function)
 		flen = strlen(function);
-	spin_lock(&err_buf_lock);
 	va_start(args, fmt);
-	vsnprintf(err_buf, sizeof(err_buf), fmt, args);
-	va_end(args);
+	vaf.fmt = fmt;
+	vaf.va = &args;
 	if (sb)
-		printk(KERN_ERR "NTFS-fs error (device %s): %s(): %s\n",
-				sb->s_id, flen ? function : "", err_buf);
+		pr_err("(device %s): %s(): %pV\n",
+		       sb->s_id, flen ? function : "", &vaf);
 	else
-		printk(KERN_ERR "NTFS-fs error: %s(): %s\n",
-				flen ? function : "", err_buf);
-	spin_unlock(&err_buf_lock);
+		pr_err("%s(): %pV\n", flen ? function : "", &vaf);
+	va_end(args);
 }
 
 #ifdef DEBUG
@@ -124,6 +115,7 @@ int debug_msgs = 0;
 void __ntfs_debug (const char *file, int line, const char *function,
 		const char *fmt, ...)
 {
+	struct va_format vaf;
 	va_list args;
 	int flen = 0;
 
@@ -131,13 +123,11 @@ void __ntfs_debug (const char *file, int line, const char *function,
 		return;
 	if (function)
 		flen = strlen(function);
-	spin_lock(&err_buf_lock);
 	va_start(args, fmt);
-	vsnprintf(err_buf, sizeof(err_buf), fmt, args);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	pr_debug("(%s, %d): %s(): %pV", file, line, flen ? function : "", &vaf);
 	va_end(args);
-	printk(KERN_DEBUG "NTFS-fs DEBUG (%s, %d): %s(): %s\n", file, line,
-			flen ? function : "", err_buf);
-	spin_unlock(&err_buf_lock);
 }
 
 /* Dump a runlist. Caller has to provide synchronisation for @rl. */
@@ -149,12 +139,12 @@ void ntfs_debug_dump_runlist(const runlist_element *rl)
 
 	if (!debug_msgs)
 		return;
-	printk(KERN_DEBUG "NTFS-fs DEBUG: Dumping runlist (values in hex):\n");
+	pr_debug("Dumping runlist (values in hex):\n");
 	if (!rl) {
-		printk(KERN_DEBUG "Run list not present.\n");
+		pr_debug("Run list not present.\n");
 		return;
 	}
-	printk(KERN_DEBUG "VCN              LCN               Run length\n");
+	pr_debug("VCN              LCN               Run length\n");
 	for (i = 0; ; i++) {
 		LCN lcn = (rl + i)->lcn;
 
@@ -163,13 +153,13 @@ void ntfs_debug_dump_runlist(const runlist_element *rl)
 
 			if (index > -LCN_ENOENT - 1)
 				index = 3;
-			printk(KERN_DEBUG "%-16Lx %s %-16Lx%s\n",
+			pr_debug("%-16Lx %s %-16Lx%s\n",
 					(long long)(rl + i)->vcn, lcn_str[index],
 					(long long)(rl + i)->length,
 					(rl + i)->length ? "" :
 						" (runlist end)");
 		} else
-			printk(KERN_DEBUG "%-16Lx %-16Lx  %-16Lx%s\n",
+			pr_debug("%-16Lx %-16Lx  %-16Lx%s\n",
 					(long long)(rl + i)->vcn,
 					(long long)(rl + i)->lcn,
 					(long long)(rl + i)->length,
diff --git a/fs/ntfs/debug.h b/fs/ntfs/debug.h
index 53c27eaf2307..61bf091e32a8 100644
--- a/fs/ntfs/debug.h
+++ b/fs/ntfs/debug.h
@@ -48,7 +48,12 @@ extern void ntfs_debug_dump_runlist(const runlist_element *rl);
 
 #else	/* !DEBUG */
 
-#define ntfs_debug(f, a...)		do {} while (0)
+#define ntfs_debug(fmt, ...)						\
+do {									\
+	if (0)								\
+		no_printk(fmt, ##__VA_ARGS__);				\
+} while (0)
+
 #define ntfs_debug_dump_runlist(rl)	do {} while (0)
 
 #endif	/* !DEBUG */
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index ffb9b3675736..9d8153ebacfb 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -2259,7 +2259,7 @@ void ntfs_evict_big_inode(struct inode *vi)
 {
 	ntfs_inode *ni = NTFS_I(vi);
 
-	truncate_inode_pages(&vi->i_data, 0);
+	truncate_inode_pages_final(&vi->i_data);
 	clear_inode(vi);
 
 #ifdef NTFS_RW
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index bd5610d48242..9de2491f2926 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -19,6 +19,7 @@
  * distribution in the file COPYING); if not, write to the Free Software
  * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/stddef.h>
 #include <linux/init.h>
@@ -1896,7 +1897,7 @@ get_ctx_vol_failed:
 	vol->minor_ver = vi->minor_ver;
 	ntfs_attr_put_search_ctx(ctx);
 	unmap_mft_record(NTFS_I(vol->vol_ino));
-	printk(KERN_INFO "NTFS volume version %i.%i.\n", vol->major_ver,
+	pr_info("volume version %i.%i.\n", vol->major_ver,
 			vol->minor_ver);
 	if (vol->major_ver < 3 && NVolSparseEnabled(vol)) {
 		ntfs_warning(vol->sb, "Disabling sparse support due to NTFS "
@@ -3095,7 +3096,7 @@ static int __init init_ntfs_fs(void)
 	int err = 0;
 
 	/* This may be ugly but it results in pretty output so who cares. (-8 */
-	printk(KERN_INFO "NTFS driver " NTFS_VERSION " [Flags: R/"
+	pr_info("driver " NTFS_VERSION " [Flags: R/"
 #ifdef NTFS_RW
 			"W"
 #else
@@ -3115,16 +3116,15 @@ static int __init init_ntfs_fs(void)
 			sizeof(ntfs_index_context), 0 /* offset */,
 			SLAB_HWCACHE_ALIGN, NULL /* ctor */);
 	if (!ntfs_index_ctx_cache) {
-		printk(KERN_CRIT "NTFS: Failed to create %s!\n",
-				ntfs_index_ctx_cache_name);
+		pr_crit("Failed to create %s!\n", ntfs_index_ctx_cache_name);
 		goto ictx_err_out;
 	}
 	ntfs_attr_ctx_cache = kmem_cache_create(ntfs_attr_ctx_cache_name,
 			sizeof(ntfs_attr_search_ctx), 0 /* offset */,
 			SLAB_HWCACHE_ALIGN, NULL /* ctor */);
 	if (!ntfs_attr_ctx_cache) {
-		printk(KERN_CRIT "NTFS: Failed to create %s!\n",
-				ntfs_attr_ctx_cache_name);
+		pr_crit("NTFS: Failed to create %s!\n",
+			ntfs_attr_ctx_cache_name);
 		goto actx_err_out;
 	}
 
@@ -3132,8 +3132,7 @@ static int __init init_ntfs_fs(void)
 			(NTFS_MAX_NAME_LEN+1) * sizeof(ntfschar), 0,
 			SLAB_HWCACHE_ALIGN, NULL);
 	if (!ntfs_name_cache) {
-		printk(KERN_CRIT "NTFS: Failed to create %s!\n",
-				ntfs_name_cache_name);
+		pr_crit("Failed to create %s!\n", ntfs_name_cache_name);
 		goto name_err_out;
 	}
 
@@ -3141,8 +3140,7 @@ static int __init init_ntfs_fs(void)
 			sizeof(ntfs_inode), 0,
 			SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
 	if (!ntfs_inode_cache) {
-		printk(KERN_CRIT "NTFS: Failed to create %s!\n",
-				ntfs_inode_cache_name);
+		pr_crit("Failed to create %s!\n", ntfs_inode_cache_name);
 		goto inode_err_out;
 	}
 
@@ -3151,15 +3149,14 @@ static int __init init_ntfs_fs(void)
 			SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD,
 			ntfs_big_inode_init_once);
 	if (!ntfs_big_inode_cache) {
-		printk(KERN_CRIT "NTFS: Failed to create %s!\n",
-				ntfs_big_inode_cache_name);
+		pr_crit("Failed to create %s!\n", ntfs_big_inode_cache_name);
 		goto big_inode_err_out;
 	}
 
 	/* Register the ntfs sysctls. */
 	err = ntfs_sysctl(1);
 	if (err) {
-		printk(KERN_CRIT "NTFS: Failed to register NTFS sysctls!\n");
+		pr_crit("Failed to register NTFS sysctls!\n");
 		goto sysctl_err_out;
 	}
 
@@ -3168,7 +3165,7 @@ static int __init init_ntfs_fs(void)
 		ntfs_debug("NTFS driver registered successfully.");
 		return 0; /* Success! */
 	}
-	printk(KERN_CRIT "NTFS: Failed to register NTFS filesystem driver!\n");
+	pr_crit("Failed to register NTFS filesystem driver!\n");
 
 	/* Unregister the ntfs sysctls. */
 	ntfs_sysctl(0);
@@ -3184,8 +3181,7 @@ actx_err_out:
 	kmem_cache_destroy(ntfs_index_ctx_cache);
 ictx_err_out:
 	if (!err) {
-		printk(KERN_CRIT "NTFS: Aborting NTFS filesystem driver "
-				"registration...\n");
+		pr_crit("Aborting NTFS filesystem driver registration...\n");
 		err = -ENOMEM;
 	}
 	return err;
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index 555f4cddefe3..7e8282dcea2a 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -205,6 +205,7 @@ static int ocfs2_acl_set_mode(struct inode *inode, struct buffer_head *di_bh,
 	di->i_mode = cpu_to_le16(inode->i_mode);
 	di->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
 	di->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
+	ocfs2_update_inode_fsync_trans(handle, inode, 0);
 
 	ocfs2_journal_dirty(handle, di_bh);
 
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index e2edff38be52..b4deb5f750d9 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -5728,6 +5728,7 @@ int ocfs2_remove_btree_range(struct inode *inode,
 	}
 
 	ocfs2_et_update_clusters(et, -len);
+	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 
 	ocfs2_journal_dirty(handle, et->et_root_bh);
 
@@ -6932,6 +6933,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 	di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features);
 	spin_unlock(&oi->ip_lock);
 
+	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 	ocfs2_dinode_new_extent_list(inode, di);
 
 	ocfs2_journal_dirty(handle, di_bh);
@@ -7208,6 +7210,7 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh,
 	di->i_ctime = di->i_mtime = cpu_to_le64(inode->i_ctime.tv_sec);
 	di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
 
+	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 	ocfs2_journal_dirty(handle, di_bh);
 
 out_commit:
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index aeb44e879c51..d310d12a9adc 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -571,7 +571,6 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	int level;
-	wait_queue_head_t *wq = ocfs2_ioend_wq(inode);
 
 	/* this io's submitter should not have unlocked this before we could */
 	BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
@@ -582,10 +581,7 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
 	if (ocfs2_iocb_is_unaligned_aio(iocb)) {
 		ocfs2_iocb_clear_unaligned_aio(iocb);
 
-		if (atomic_dec_and_test(&OCFS2_I(inode)->ip_unaligned_aio) &&
-		    waitqueue_active(wq)) {
-			wake_up_all(wq);
-		}
+		mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio);
 	}
 
 	ocfs2_iocb_clear_rw_locked(iocb);
@@ -2043,6 +2039,7 @@ out_write_size:
 	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 	di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
 	di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 	ocfs2_journal_dirty(handle, wc->w_di_bh);
 
 	ocfs2_commit_trans(osb, handle);
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index f671e49beb34..6cae155d54df 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -102,9 +102,4 @@ enum ocfs2_iocb_lock_bits {
 #define ocfs2_iocb_is_unaligned_aio(iocb) \
 	test_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
 
-#define OCFS2_IOEND_WQ_HASH_SZ	37
-#define ocfs2_ioend_wq(v)   (&ocfs2__ioend_wq[((unsigned long)(v)) %\
-					    OCFS2_IOEND_WQ_HASH_SZ])
-extern wait_queue_head_t ocfs2__ioend_wq[OCFS2_IOEND_WQ_HASH_SZ];
-
 #endif /* OCFS2_FILE_H */
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 2cd2406b4140..a3df40be6be2 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -262,17 +262,17 @@ static void o2net_update_recv_stats(struct o2net_sock_container *sc)
 
 #endif /* CONFIG_OCFS2_FS_STATS */
 
-static inline int o2net_reconnect_delay(void)
+static inline unsigned int o2net_reconnect_delay(void)
 {
 	return o2nm_single_cluster->cl_reconnect_delay_ms;
 }
 
-static inline int o2net_keepalive_delay(void)
+static inline unsigned int o2net_keepalive_delay(void)
 {
 	return o2nm_single_cluster->cl_keepalive_delay_ms;
 }
 
-static inline int o2net_idle_timeout(void)
+static inline unsigned int o2net_idle_timeout(void)
 {
 	return o2nm_single_cluster->cl_idle_timeout_ms;
 }
@@ -1826,7 +1826,7 @@ int o2net_register_hb_callbacks(void)
 
 /* ------------------------------------------------------------ */
 
-static int o2net_accept_one(struct socket *sock)
+static int o2net_accept_one(struct socket *sock, int *more)
 {
 	int ret, slen;
 	struct sockaddr_in sin;
@@ -1837,6 +1837,7 @@ static int o2net_accept_one(struct socket *sock)
 	struct o2net_node *nn;
 
 	BUG_ON(sock == NULL);
+	*more = 0;
 	ret = sock_create_lite(sock->sk->sk_family, sock->sk->sk_type,
 			       sock->sk->sk_protocol, &new_sock);
 	if (ret)
@@ -1848,6 +1849,7 @@ static int o2net_accept_one(struct socket *sock)
 	if (ret < 0)
 		goto out;
 
+	*more = 1;
 	new_sock->sk->sk_allocation = GFP_ATOMIC;
 
 	ret = o2net_set_nodelay(new_sock);
@@ -1949,8 +1951,15 @@ out:
 static void o2net_accept_many(struct work_struct *work)
 {
 	struct socket *sock = o2net_listen_sock;
-	while (o2net_accept_one(sock) == 0)
+	int	more;
+	int	err;
+
+	for (;;) {
+		err = o2net_accept_one(sock, &more);
+		if (!more)
+			break;
 		cond_resched();
+	}
 }
 
 static void o2net_listen_data_ready(struct sock *sk, int bytes)
@@ -1964,18 +1973,30 @@ static void o2net_listen_data_ready(struct sock *sk, int bytes)
 		goto out;
 	}
 
-	/* ->sk_data_ready is also called for a newly established child socket
-	 * before it has been accepted and the acceptor has set up their
-	 * data_ready.. we only want to queue listen work for our listening
-	 * socket */
+	/* This callback may called twice when a new connection
+	 * is  being established as a child socket inherits everything
+	 * from a parent LISTEN socket, including the data_ready cb of
+	 * the parent. This leads to a hazard. In o2net_accept_one()
+	 * we are still initializing the child socket but have not
+	 * changed the inherited data_ready callback yet when
+	 * data starts arriving.
+	 * We avoid this hazard by checking the state.
+	 * For the listening socket,  the state will be TCP_LISTEN; for the new
+	 * socket, will be  TCP_ESTABLISHED. Also, in this case,
+	 * sk->sk_user_data is not a valid function pointer.
+	 */
+
 	if (sk->sk_state == TCP_LISTEN) {
 		mlog(ML_TCP, "bytes: %d\n", bytes);
 		queue_work(o2net_wq, &o2net_listen_work);
+	} else {
+		ready = NULL;
 	}
 
 out:
 	read_unlock(&sk->sk_callback_lock);
-	ready(sk, bytes);
+	if (ready != NULL)
+		ready(sk, bytes);
 }
 
 static int o2net_open_listening_sock(__be32 addr, __be16 port)
diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index 0d3a97d2d5f6..e2e05a106beb 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -37,7 +37,6 @@
 #include "dlmglue.h"
 #include "file.h"
 #include "inode.h"
-#include "super.h"
 #include "ocfs2_trace.h"
 
 void ocfs2_dentry_attach_gen(struct dentry *dentry)
@@ -346,52 +345,6 @@ out_attach:
 	return ret;
 }
 
-DEFINE_SPINLOCK(dentry_list_lock);
-
-/* We limit the number of dentry locks to drop in one go. We have
- * this limit so that we don't starve other users of ocfs2_wq. */
-#define DL_INODE_DROP_COUNT 64
-
-/* Drop inode references from dentry locks */
-static void __ocfs2_drop_dl_inodes(struct ocfs2_super *osb, int drop_count)
-{
-	struct ocfs2_dentry_lock *dl;
-
-	spin_lock(&dentry_list_lock);
-	while (osb->dentry_lock_list && (drop_count < 0 || drop_count--)) {
-		dl = osb->dentry_lock_list;
-		osb->dentry_lock_list = dl->dl_next;
-		spin_unlock(&dentry_list_lock);
-		iput(dl->dl_inode);
-		kfree(dl);
-		spin_lock(&dentry_list_lock);
-	}
-	spin_unlock(&dentry_list_lock);
-}
-
-void ocfs2_drop_dl_inodes(struct work_struct *work)
-{
-	struct ocfs2_super *osb = container_of(work, struct ocfs2_super,
-					       dentry_lock_work);
-
-	__ocfs2_drop_dl_inodes(osb, DL_INODE_DROP_COUNT);
-	/*
-	 * Don't queue dropping if umount is in progress. We flush the
-	 * list in ocfs2_dismount_volume
-	 */
-	spin_lock(&dentry_list_lock);
-	if (osb->dentry_lock_list &&
-	    !ocfs2_test_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED))
-		queue_work(ocfs2_wq, &osb->dentry_lock_work);
-	spin_unlock(&dentry_list_lock);
-}
-
-/* Flush the whole work queue */
-void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb)
-{
-	__ocfs2_drop_dl_inodes(osb, -1);
-}
-
 /*
  * ocfs2_dentry_iput() and friends.
  *
@@ -416,24 +369,16 @@ void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb)
 static void ocfs2_drop_dentry_lock(struct ocfs2_super *osb,
 				   struct ocfs2_dentry_lock *dl)
 {
+	iput(dl->dl_inode);
 	ocfs2_simple_drop_lockres(osb, &dl->dl_lockres);
 	ocfs2_lock_res_free(&dl->dl_lockres);
-
-	/* We leave dropping of inode reference to ocfs2_wq as that can
-	 * possibly lead to inode deletion which gets tricky */
-	spin_lock(&dentry_list_lock);
-	if (!osb->dentry_lock_list &&
-	    !ocfs2_test_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED))
-		queue_work(ocfs2_wq, &osb->dentry_lock_work);
-	dl->dl_next = osb->dentry_lock_list;
-	osb->dentry_lock_list = dl;
-	spin_unlock(&dentry_list_lock);
+	kfree(dl);
 }
 
 void ocfs2_dentry_lock_put(struct ocfs2_super *osb,
 			   struct ocfs2_dentry_lock *dl)
 {
-	int unlock;
+	int unlock = 0;
 
 	BUG_ON(dl->dl_count == 0);
 
diff --git a/fs/ocfs2/dcache.h b/fs/ocfs2/dcache.h
index b79eff709958..55f58892b153 100644
--- a/fs/ocfs2/dcache.h
+++ b/fs/ocfs2/dcache.h
@@ -29,13 +29,8 @@
 extern const struct dentry_operations ocfs2_dentry_ops;
 
 struct ocfs2_dentry_lock {
-	/* Use count of dentry lock */
 	unsigned int		dl_count;
-	union {
-		/* Linked list of dentry locks to release */
-		struct ocfs2_dentry_lock *dl_next;
-		u64			dl_parent_blkno;
-	};
+	u64			dl_parent_blkno;
 
 	/*
 	 * The ocfs2_dentry_lock keeps an inode reference until
@@ -49,14 +44,9 @@ struct ocfs2_dentry_lock {
 int ocfs2_dentry_attach_lock(struct dentry *dentry, struct inode *inode,
 			     u64 parent_blkno);
 
-extern spinlock_t dentry_list_lock;
-
 void ocfs2_dentry_lock_put(struct ocfs2_super *osb,
 			   struct ocfs2_dentry_lock *dl);
 
-void ocfs2_drop_dl_inodes(struct work_struct *work);
-void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb);
-
 struct dentry *ocfs2_find_local_alias(struct inode *inode, u64 parent_blkno,
 				      int skip_unhashed);
 
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 91a7e85ac8fd..0717662b4aef 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -2957,6 +2957,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
 		ocfs2_init_dir_trailer(dir, dirdata_bh, i);
 	}
 
+	ocfs2_update_inode_fsync_trans(handle, dir, 1);
 	ocfs2_journal_dirty(handle, dirdata_bh);
 
 	if (ocfs2_supports_indexed_dirs(osb) && !dx_inline) {
@@ -3005,6 +3006,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
 	di->i_size = cpu_to_le64(sb->s_blocksize);
 	di->i_ctime = di->i_mtime = cpu_to_le64(dir->i_ctime.tv_sec);
 	di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(dir->i_ctime.tv_nsec);
+	ocfs2_update_inode_fsync_trans(handle, dir, 1);
 
 	/*
 	 * This should never fail as our extent list is empty and all
@@ -3338,6 +3340,7 @@ do_extend:
 	} else {
 		de->rec_len = cpu_to_le16(sb->s_blocksize);
 	}
+	ocfs2_update_inode_fsync_trans(handle, dir, 1);
 	ocfs2_journal_dirty(handle, new_bh);
 
 	dir_i_size += dir->i_sb->s_blocksize;
@@ -3896,6 +3899,7 @@ out_commit:
 		dquot_free_space_nodirty(dir,
 				ocfs2_clusters_to_bytes(dir->i_sb, 1));
 
+	ocfs2_update_inode_fsync_trans(handle, dir, 1);
 	ocfs2_commit_trans(osb, handle);
 
 out:
@@ -4134,6 +4138,7 @@ static int ocfs2_expand_inline_dx_root(struct inode *dir,
 		mlog_errno(ret);
 	did_quota = 0;
 
+	ocfs2_update_inode_fsync_trans(handle, dir, 1);
 	ocfs2_journal_dirty(handle, dx_root_bh);
 
 out_commit:
@@ -4401,6 +4406,7 @@ static int ocfs2_dx_dir_remove_index(struct inode *dir,
 	di->i_dyn_features = cpu_to_le16(OCFS2_I(dir)->ip_dyn_features);
 	spin_unlock(&OCFS2_I(dir)->ip_lock);
 	di->i_dx_root = cpu_to_le64(0ULL);
+	ocfs2_update_inode_fsync_trans(handle, dir, 1);
 
 	ocfs2_journal_dirty(handle, di_bh);
 
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 33660a4a52fa..c973690dc0bc 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -1123,7 +1123,6 @@ static int dlm_query_region_handler(struct o2net_msg *msg, u32 len,
 	struct dlm_ctxt *dlm = NULL;
 	char *local = NULL;
 	int status = 0;
-	int locked = 0;
 
 	qr = (struct dlm_query_region *) msg->buf;
 
@@ -1132,10 +1131,8 @@ static int dlm_query_region_handler(struct o2net_msg *msg, u32 len,
 
 	/* buffer used in dlm_mast_regions() */
 	local = kmalloc(sizeof(qr->qr_regions), GFP_KERNEL);
-	if (!local) {
-		status = -ENOMEM;
-		goto bail;
-	}
+	if (!local)
+		return -ENOMEM;
 
 	status = -EINVAL;
 
@@ -1144,16 +1141,15 @@ static int dlm_query_region_handler(struct o2net_msg *msg, u32 len,
 	if (!dlm) {
 		mlog(ML_ERROR, "Node %d queried hb regions on domain %s "
 		     "before join domain\n", qr->qr_node, qr->qr_domain);
-		goto bail;
+		goto out_domain_lock;
 	}
 
 	spin_lock(&dlm->spinlock);
-	locked = 1;
 	if (dlm->joining_node != qr->qr_node) {
 		mlog(ML_ERROR, "Node %d queried hb regions on domain %s "
 		     "but joining node is %d\n", qr->qr_node, qr->qr_domain,
 		     dlm->joining_node);
-		goto bail;
+		goto out_dlm_lock;
 	}
 
 	/* Support for global heartbeat was added in 1.1 */
@@ -1163,14 +1159,15 @@ static int dlm_query_region_handler(struct o2net_msg *msg, u32 len,
 		     "but active dlm protocol is %d.%d\n", qr->qr_node,
 		     qr->qr_domain, dlm->dlm_locking_proto.pv_major,
 		     dlm->dlm_locking_proto.pv_minor);
-		goto bail;
+		goto out_dlm_lock;
 	}
 
 	status = dlm_match_regions(dlm, qr, local, sizeof(qr->qr_regions));
 
-bail:
-	if (locked)
-		spin_unlock(&dlm->spinlock);
+out_dlm_lock:
+	spin_unlock(&dlm->spinlock);
+
+out_domain_lock:
 	spin_unlock(&dlm_domain_lock);
 
 	kfree(local);
@@ -1877,19 +1874,19 @@ static int dlm_join_domain(struct dlm_ctxt *dlm)
 		goto bail;
 	}
 
-	status = dlm_debug_init(dlm);
+	status = dlm_launch_thread(dlm);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
 	}
 
-	status = dlm_launch_thread(dlm);
+	status = dlm_launch_recovery_thread(dlm);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
 	}
 
-	status = dlm_launch_recovery_thread(dlm);
+	status = dlm_debug_init(dlm);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index af3f7aa73e13..1b11a47876e3 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -3084,11 +3084,15 @@ static int dlm_add_migration_mle(struct dlm_ctxt *dlm,
 			/* remove it so that only one mle will be found */
 			__dlm_unlink_mle(dlm, tmp);
 			__dlm_mle_detach_hb_events(dlm, tmp);
-			ret = DLM_MIGRATE_RESPONSE_MASTERY_REF;
-			mlog(0, "%s:%.*s: master=%u, newmaster=%u, "
-			    "telling master to get ref for cleared out mle "
-			    "during migration\n", dlm->name, namelen, name,
-			    master, new_master);
+			if (tmp->type == DLM_MLE_MASTER) {
+				ret = DLM_MIGRATE_RESPONSE_MASTERY_REF;
+				mlog(0, "%s:%.*s: master=%u, newmaster=%u, "
+						"telling master to get ref "
+						"for cleared out mle during "
+						"migration\n", dlm->name,
+						namelen, name, master,
+						new_master);
+			}
 		}
 		spin_unlock(&tmp->spinlock);
 	}
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 7035af09cc03..fe29f7978f81 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -537,7 +537,10 @@ master_here:
 		/* success!  see if any other nodes need recovery */
 		mlog(0, "DONE mastering recovery of %s:%u here(this=%u)!\n",
 		     dlm->name, dlm->reco.dead_node, dlm->node_num);
-		dlm_reset_recovery(dlm);
+		spin_lock(&dlm->spinlock);
+		__dlm_reset_recovery(dlm);
+		dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE;
+		spin_unlock(&dlm->spinlock);
 	}
 	dlm_end_recovery(dlm);
 
@@ -695,6 +698,14 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node)
 		if (all_nodes_done) {
 			int ret;
 
+			/* Set this flag on recovery master to avoid
+			 * a new recovery for another dead node start
+			 * before the recovery is not done. That may
+			 * cause recovery hung.*/
+			spin_lock(&dlm->spinlock);
+			dlm->reco.state |= DLM_RECO_STATE_FINALIZE;
+			spin_unlock(&dlm->spinlock);
+
 			/* all nodes are now in DLM_RECO_NODE_DATA_DONE state
 	 		 * just send a finalize message to everyone and
 	 		 * clean up */
@@ -1750,13 +1761,13 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm,
 				     struct dlm_migratable_lockres *mres)
 {
 	struct dlm_migratable_lock *ml;
-	struct list_head *queue;
+	struct list_head *queue, *iter;
 	struct list_head *tmpq = NULL;
 	struct dlm_lock *newlock = NULL;
 	struct dlm_lockstatus *lksb = NULL;
 	int ret = 0;
 	int i, j, bad;
-	struct dlm_lock *lock = NULL;
+	struct dlm_lock *lock;
 	u8 from = O2NM_MAX_NODES;
 	unsigned int added = 0;
 	__be64 c;
@@ -1791,14 +1802,16 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm,
 			/* MIGRATION ONLY! */
 			BUG_ON(!(mres->flags & DLM_MRES_MIGRATION));
 
+			lock = NULL;
 			spin_lock(&res->spinlock);
 			for (j = DLM_GRANTED_LIST; j <= DLM_BLOCKED_LIST; j++) {
 				tmpq = dlm_list_idx_to_ptr(res, j);
-				list_for_each_entry(lock, tmpq, list) {
-					if (lock->ml.cookie != ml->cookie)
-						lock = NULL;
-					else
+				list_for_each(iter, tmpq) {
+					lock = list_entry(iter,
+						  struct dlm_lock, list);
+					if (lock->ml.cookie == ml->cookie)
 						break;
+					lock = NULL;
 				}
 				if (lock)
 					break;
@@ -2882,8 +2895,8 @@ int dlm_finalize_reco_handler(struct o2net_msg *msg, u32 len, void *data,
 				BUG();
 			}
 			dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE;
+			__dlm_reset_recovery(dlm);
 			spin_unlock(&dlm->spinlock);
-			dlm_reset_recovery(dlm);
 			dlm_kick_recovery_thread(dlm);
 			break;
 		default:
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 19986959d149..6bd690b5a061 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -3144,22 +3144,60 @@ out:
 	return 0;
 }
 
+static void ocfs2_process_blocked_lock(struct ocfs2_super *osb,
+				       struct ocfs2_lock_res *lockres);
+
 /* Mark the lockres as being dropped. It will no longer be
  * queued if blocking, but we still may have to wait on it
  * being dequeued from the downconvert thread before we can consider
  * it safe to drop.
  *
  * You can *not* attempt to call cluster_lock on this lockres anymore. */
-void ocfs2_mark_lockres_freeing(struct ocfs2_lock_res *lockres)
+void ocfs2_mark_lockres_freeing(struct ocfs2_super *osb,
+				struct ocfs2_lock_res *lockres)
 {
 	int status;
 	struct ocfs2_mask_waiter mw;
-	unsigned long flags;
+	unsigned long flags, flags2;
 
 	ocfs2_init_mask_waiter(&mw);
 
 	spin_lock_irqsave(&lockres->l_lock, flags);
 	lockres->l_flags |= OCFS2_LOCK_FREEING;
+	if (lockres->l_flags & OCFS2_LOCK_QUEUED && current == osb->dc_task) {
+		/*
+		 * We know the downconvert is queued but not in progress
+		 * because we are the downconvert thread and processing
+		 * different lock. So we can just remove the lock from the
+		 * queue. This is not only an optimization but also a way
+		 * to avoid the following deadlock:
+		 *   ocfs2_dentry_post_unlock()
+		 *     ocfs2_dentry_lock_put()
+		 *       ocfs2_drop_dentry_lock()
+		 *         iput()
+		 *           ocfs2_evict_inode()
+		 *             ocfs2_clear_inode()
+		 *               ocfs2_mark_lockres_freeing()
+		 *                 ... blocks waiting for OCFS2_LOCK_QUEUED
+		 *                 since we are the downconvert thread which
+		 *                 should clear the flag.
+		 */
+		spin_unlock_irqrestore(&lockres->l_lock, flags);
+		spin_lock_irqsave(&osb->dc_task_lock, flags2);
+		list_del_init(&lockres->l_blocked_list);
+		osb->blocked_lock_count--;
+		spin_unlock_irqrestore(&osb->dc_task_lock, flags2);
+		/*
+		 * Warn if we recurse into another post_unlock call.  Strictly
+		 * speaking it isn't a problem but we need to be careful if
+		 * that happens (stack overflow, deadlocks, ...) so warn if
+		 * ocfs2 grows a path for which this can happen.
+		 */
+		WARN_ON_ONCE(lockres->l_ops->post_unlock);
+		/* Since the lock is freeing we don't do much in the fn below */
+		ocfs2_process_blocked_lock(osb, lockres);
+		return;
+	}
 	while (lockres->l_flags & OCFS2_LOCK_QUEUED) {
 		lockres_add_mask_waiter(lockres, &mw, OCFS2_LOCK_QUEUED, 0);
 		spin_unlock_irqrestore(&lockres->l_lock, flags);
@@ -3180,7 +3218,7 @@ void ocfs2_simple_drop_lockres(struct ocfs2_super *osb,
 {
 	int ret;
 
-	ocfs2_mark_lockres_freeing(lockres);
+	ocfs2_mark_lockres_freeing(osb, lockres);
 	ret = ocfs2_drop_lock(osb, lockres);
 	if (ret)
 		mlog_errno(ret);
diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h
index 1d596d8c4a4a..d293a22c32c5 100644
--- a/fs/ocfs2/dlmglue.h
+++ b/fs/ocfs2/dlmglue.h
@@ -157,7 +157,8 @@ int ocfs2_refcount_lock(struct ocfs2_refcount_tree *ref_tree, int ex);
 void ocfs2_refcount_unlock(struct ocfs2_refcount_tree *ref_tree, int ex);
 
 
-void ocfs2_mark_lockres_freeing(struct ocfs2_lock_res *lockres);
+void ocfs2_mark_lockres_freeing(struct ocfs2_super *osb,
+				struct ocfs2_lock_res *lockres);
 void ocfs2_simple_drop_lockres(struct ocfs2_super *osb,
 			       struct ocfs2_lock_res *lockres);
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 51632c40e896..ff33c5ef87f2 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -175,9 +175,13 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end,
 			   int datasync)
 {
 	int err = 0;
-	journal_t *journal;
 	struct inode *inode = file->f_mapping->host;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	journal_t *journal = osb->journal->j_journal;
+	int ret;
+	tid_t commit_tid;
+	bool needs_barrier = false;
 
 	trace_ocfs2_sync_file(inode, file, file->f_path.dentry,
 			      OCFS2_I(inode)->ip_blkno,
@@ -192,29 +196,19 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end,
 	if (err)
 		return err;
 
-	/*
-	 * Probably don't need the i_mutex at all in here, just putting it here
-	 * to be consistent with how fsync used to be called, someone more
-	 * familiar with the fs could possibly remove it.
-	 */
-	mutex_lock(&inode->i_mutex);
-	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) {
-		/*
-		 * We still have to flush drive's caches to get data to the
-		 * platter
-		 */
-		if (osb->s_mount_opt & OCFS2_MOUNT_BARRIER)
-			blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
-		goto bail;
+	commit_tid = datasync ? oi->i_datasync_tid : oi->i_sync_tid;
+	if (journal->j_flags & JBD2_BARRIER &&
+	    !jbd2_trans_will_send_data_barrier(journal, commit_tid))
+		needs_barrier = true;
+	err = jbd2_complete_transaction(journal, commit_tid);
+	if (needs_barrier) {
+		ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
+		if (!err)
+			err = ret;
 	}
 
-	journal = osb->journal->j_journal;
-	err = jbd2_journal_force_commit(journal);
-
-bail:
 	if (err)
 		mlog_errno(err);
-	mutex_unlock(&inode->i_mutex);
 
 	return (err < 0) ? -EIO : 0;
 }
@@ -292,6 +286,7 @@ int ocfs2_update_inode_atime(struct inode *inode,
 	inode->i_atime = CURRENT_TIME;
 	di->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
 	di->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec);
+	ocfs2_update_inode_fsync_trans(handle, inode, 0);
 	ocfs2_journal_dirty(handle, bh);
 
 out_commit:
@@ -341,6 +336,7 @@ int ocfs2_simple_size_update(struct inode *inode,
 	if (ret < 0)
 		mlog_errno(ret);
 
+	ocfs2_update_inode_fsync_trans(handle, inode, 0);
 	ocfs2_commit_trans(osb, handle);
 out:
 	return ret;
@@ -435,6 +431,7 @@ static int ocfs2_orphan_for_truncate(struct ocfs2_super *osb,
 	di->i_size = cpu_to_le64(new_i_size);
 	di->i_ctime = di->i_mtime = cpu_to_le64(inode->i_ctime.tv_sec);
 	di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
+	ocfs2_update_inode_fsync_trans(handle, inode, 0);
 
 	ocfs2_journal_dirty(handle, fe_bh);
 
@@ -650,7 +647,7 @@ restarted_transaction:
 			mlog_errno(status);
 		goto leave;
 	}
-
+	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 	ocfs2_journal_dirty(handle, bh);
 
 	spin_lock(&OCFS2_I(inode)->ip_lock);
@@ -743,6 +740,7 @@ static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode,
 				      OCFS2_JOURNAL_ACCESS_WRITE);
 	if (ret)
 		mlog_errno(ret);
+	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 
 out:
 	if (ret) {
@@ -840,6 +838,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 		di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
 		di->i_mtime_nsec = di->i_ctime_nsec;
 		ocfs2_journal_dirty(handle, di_bh);
+		ocfs2_update_inode_fsync_trans(handle, inode, 1);
 		ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
 	}
 
@@ -1344,6 +1343,7 @@ static int __ocfs2_write_remove_suid(struct inode *inode,
 
 	di = (struct ocfs2_dinode *) bh->b_data;
 	di->i_mode = cpu_to_le16(inode->i_mode);
+	ocfs2_update_inode_fsync_trans(handle, inode, 0);
 
 	ocfs2_journal_dirty(handle, bh);
 
@@ -1576,6 +1576,7 @@ static int ocfs2_zero_partial_clusters(struct inode *inode,
 		if (ret)
 			mlog_errno(ret);
 	}
+	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 
 	ocfs2_commit_trans(osb, handle);
 out:
@@ -2061,13 +2062,6 @@ out:
 	return ret;
 }
 
-static void ocfs2_aiodio_wait(struct inode *inode)
-{
-	wait_queue_head_t *wq = ocfs2_ioend_wq(inode);
-
-	wait_event(*wq, (atomic_read(&OCFS2_I(inode)->ip_unaligned_aio) == 0));
-}
-
 static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos)
 {
 	int blockmask = inode->i_sb->s_blocksize - 1;
@@ -2345,10 +2339,8 @@ relock:
 		 * Wait on previous unaligned aio to complete before
 		 * proceeding.
 		 */
-		ocfs2_aiodio_wait(inode);
-
-		/* Mark the iocb as needing a decrement in ocfs2_dio_end_io */
-		atomic_inc(&OCFS2_I(inode)->ip_unaligned_aio);
+		mutex_lock(&OCFS2_I(inode)->ip_unaligned_aio);
+		/* Mark the iocb as needing an unlock in ocfs2_dio_end_io */
 		ocfs2_iocb_set_unaligned_aio(iocb);
 	}
 
@@ -2428,7 +2420,7 @@ out_dio:
 
 	if (unaligned_dio) {
 		ocfs2_iocb_clear_unaligned_aio(iocb);
-		atomic_dec(&OCFS2_I(inode)->ip_unaligned_aio);
+		mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio);
 	}
 
 out:
@@ -2645,7 +2637,16 @@ static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int whence)
 	case SEEK_SET:
 		break;
 	case SEEK_END:
-		offset += inode->i_size;
+		/* SEEK_END requires the OCFS2 inode lock for the file
+		 * because it references the file's size.
+		 */
+		ret = ocfs2_inode_lock(inode, NULL, 0);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out;
+		}
+		offset += i_size_read(inode);
+		ocfs2_inode_unlock(inode, 0);
 		break;
 	case SEEK_CUR:
 		if (offset == 0) {
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index f29a90fde619..437de7f768c6 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -130,6 +130,7 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
 	struct inode *inode = NULL;
 	struct super_block *sb = osb->sb;
 	struct ocfs2_find_inode_args args;
+	journal_t *journal = OCFS2_SB(sb)->journal->j_journal;
 
 	trace_ocfs2_iget_begin((unsigned long long)blkno, flags,
 			       sysfile_type);
@@ -169,6 +170,32 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
 		goto bail;
 	}
 
+	/*
+	 * Set transaction id's of transactions that have to be committed
+	 * to finish f[data]sync. We set them to currently running transaction
+	 * as we cannot be sure that the inode or some of its metadata isn't
+	 * part of the transaction - the inode could have been reclaimed and
+	 * now it is reread from disk.
+	 */
+	if (journal) {
+		transaction_t *transaction;
+		tid_t tid;
+		struct ocfs2_inode_info *oi = OCFS2_I(inode);
+
+		read_lock(&journal->j_state_lock);
+		if (journal->j_running_transaction)
+			transaction = journal->j_running_transaction;
+		else
+			transaction = journal->j_committing_transaction;
+		if (transaction)
+			tid = transaction->t_tid;
+		else
+			tid = journal->j_commit_sequence;
+		read_unlock(&journal->j_state_lock);
+		oi->i_sync_tid = tid;
+		oi->i_datasync_tid = tid;
+	}
+
 bail:
 	if (!IS_ERR(inode)) {
 		trace_ocfs2_iget_end(inode, 
@@ -804,11 +831,13 @@ static int ocfs2_inode_is_valid_to_delete(struct inode *inode)
 		goto bail;
 	}
 
-	/* If we're coming from downconvert_thread we can't go into our own
-	 * voting [hello, deadlock city!], so unforuntately we just
-	 * have to skip deleting this guy. That's OK though because
-	 * the node who's doing the actual deleting should handle it
-	 * anyway. */
+	/*
+	 * If we're coming from downconvert_thread we can't go into our own
+	 * voting [hello, deadlock city!] so we cannot delete the inode. But
+	 * since we dropped last inode ref when downconverting dentry lock,
+	 * we cannot have the file open and thus the node doing unlink will
+	 * take care of deleting the inode.
+	 */
 	if (current == osb->dc_task)
 		goto bail;
 
@@ -822,12 +851,6 @@ static int ocfs2_inode_is_valid_to_delete(struct inode *inode)
 		goto bail_unlock;
 	}
 
-	/* If we have allowd wipe of this inode for another node, it
-	 * will be marked here so we can safely skip it. Recovery will
-	 * cleanup any inodes we might inadvertently skip here. */
-	if (oi->ip_flags & OCFS2_INODE_SKIP_DELETE)
-		goto bail_unlock;
-
 	ret = 1;
 bail_unlock:
 	spin_unlock(&oi->ip_lock);
@@ -941,7 +964,7 @@ static void ocfs2_cleanup_delete_inode(struct inode *inode,
 		(unsigned long long)OCFS2_I(inode)->ip_blkno, sync_data);
 	if (sync_data)
 		filemap_write_and_wait(inode->i_mapping);
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 }
 
 static void ocfs2_delete_inode(struct inode *inode)
@@ -960,8 +983,6 @@ static void ocfs2_delete_inode(struct inode *inode)
 	if (is_bad_inode(inode) || !OCFS2_I(inode)->ip_blkno)
 		goto bail;
 
-	dquot_initialize(inode);
-
 	if (!ocfs2_inode_is_valid_to_delete(inode)) {
 		/* It's probably not necessary to truncate_inode_pages
 		 * here but we do it for safety anyway (it will most
@@ -970,6 +991,8 @@ static void ocfs2_delete_inode(struct inode *inode)
 		goto bail;
 	}
 
+	dquot_initialize(inode);
+
 	/* We want to block signals in delete_inode as the lock and
 	 * messaging paths may return us -ERESTARTSYS. Which would
 	 * cause us to exit early, resulting in inodes being orphaned
@@ -1057,6 +1080,7 @@ static void ocfs2_clear_inode(struct inode *inode)
 {
 	int status;
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	clear_inode(inode);
 	trace_ocfs2_clear_inode((unsigned long long)oi->ip_blkno,
@@ -1073,9 +1097,9 @@ static void ocfs2_clear_inode(struct inode *inode)
 
 	/* Do these before all the other work so that we don't bounce
 	 * the downconvert thread while waiting to destroy the locks. */
-	ocfs2_mark_lockres_freeing(&oi->ip_rw_lockres);
-	ocfs2_mark_lockres_freeing(&oi->ip_inode_lockres);
-	ocfs2_mark_lockres_freeing(&oi->ip_open_lockres);
+	ocfs2_mark_lockres_freeing(osb, &oi->ip_rw_lockres);
+	ocfs2_mark_lockres_freeing(osb, &oi->ip_inode_lockres);
+	ocfs2_mark_lockres_freeing(osb, &oi->ip_open_lockres);
 
 	ocfs2_resv_discard(&OCFS2_SB(inode->i_sb)->osb_la_resmap,
 			   &oi->ip_la_data_resv);
@@ -1157,7 +1181,7 @@ void ocfs2_evict_inode(struct inode *inode)
 	    (OCFS2_I(inode)->ip_flags & OCFS2_INODE_MAYBE_ORPHANED)) {
 		ocfs2_delete_inode(inode);
 	} else {
-		truncate_inode_pages(&inode->i_data, 0);
+		truncate_inode_pages_final(&inode->i_data);
 	}
 	ocfs2_clear_inode(inode);
 }
@@ -1260,6 +1284,7 @@ int ocfs2_mark_inode_dirty(handle_t *handle,
 	fe->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
 
 	ocfs2_journal_dirty(handle, bh);
+	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 leave:
 	return status;
 }
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index 621fc73bf23d..a6c991c0fc98 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -44,7 +44,7 @@ struct ocfs2_inode_info
 	struct rw_semaphore		ip_xattr_sem;
 
 	/* Number of outstanding AIO's which are not page aligned */
-	atomic_t			ip_unaligned_aio;
+	struct mutex			ip_unaligned_aio;
 
 	/* These fields are protected by ip_lock */
 	spinlock_t			ip_lock;
@@ -73,6 +73,13 @@ struct ocfs2_inode_info
 	u32				ip_dir_lock_gen;
 
 	struct ocfs2_alloc_reservation	ip_la_data_resv;
+
+	/*
+	 * Transactions that contain inode's metadata needed to complete
+	 * fsync and fdatasync, respectively.
+	 */
+	tid_t i_sync_tid;
+	tid_t i_datasync_tid;
 };
 
 /*
@@ -84,8 +91,6 @@ struct ocfs2_inode_info
 #define OCFS2_INODE_BITMAP		0x00000004
 /* This inode has been wiped from disk */
 #define OCFS2_INODE_DELETED		0x00000008
-/* Another node is deleting, so our delete is a nop */
-#define OCFS2_INODE_SKIP_DELETE		0x00000010
 /* Has the inode been orphaned on another node?
  *
  * This hints to ocfs2_drop_inode that it should clear i_nlink before
@@ -100,11 +105,11 @@ struct ocfs2_inode_info
  * rely on ocfs2_delete_inode to sort things out under the proper
  * cluster locks.
  */
-#define OCFS2_INODE_MAYBE_ORPHANED	0x00000020
+#define OCFS2_INODE_MAYBE_ORPHANED	0x00000010
 /* Does someone have the file open O_DIRECT */
-#define OCFS2_INODE_OPEN_DIRECT		0x00000040
+#define OCFS2_INODE_OPEN_DIRECT		0x00000020
 /* Tell the inode wipe code it's not in orphan dir */
-#define OCFS2_INODE_SKIP_ORPHAN_DIR     0x00000080
+#define OCFS2_INODE_SKIP_ORPHAN_DIR     0x00000040
 
 static inline struct ocfs2_inode_info *OCFS2_I(struct inode *inode)
 {
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 44fc3e530c3d..03ea9314fecd 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -2132,12 +2132,6 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 		iter = oi->ip_next_orphan;
 
 		spin_lock(&oi->ip_lock);
-		/* The remote delete code may have set these on the
-		 * assumption that the other node would wipe them
-		 * successfully.  If they are still in the node's
-		 * orphan dir, we need to reset that state. */
-		oi->ip_flags &= ~(OCFS2_INODE_DELETED|OCFS2_INODE_SKIP_DELETE);
-
 		/* Set the proper information to get us going into
 		 * ocfs2_delete_inode. */
 		oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED;
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 9ff4e8cf9d97..7f8cde94abfe 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -626,4 +626,15 @@ static inline int ocfs2_begin_ordered_truncate(struct inode *inode,
 				new_size);
 }
 
+static inline void ocfs2_update_inode_fsync_trans(handle_t *handle,
+						  struct inode *inode,
+						  int datasync)
+{
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+
+	oi->i_sync_tid = handle->h_transaction->t_tid;
+	if (datasync)
+		oi->i_datasync_tid = handle->h_transaction->t_tid;
+}
+
 #endif /* OCFS2_JOURNAL_H */
diff --git a/fs/ocfs2/locks.c b/fs/ocfs2/locks.c
index e57c804069ea..6b6d092b0998 100644
--- a/fs/ocfs2/locks.c
+++ b/fs/ocfs2/locks.c
@@ -82,6 +82,8 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode,
 	}
 
 	ret = flock_lock_file_wait(file, fl);
+	if (ret)
+		ocfs2_file_unlock(file);
 
 out:
 	mutex_unlock(&fp->fp_mutex);
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 64c304d668f0..b97d608c07d7 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -151,6 +151,7 @@ static int __ocfs2_move_extent(handle_t *handle,
 							old_blkno, len);
 	}
 
+	ocfs2_update_inode_fsync_trans(handle, inode, 0);
 out:
 	ocfs2_free_path(path);
 	return ret;
@@ -681,18 +682,15 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context,
 	}
 
 	gd = (struct ocfs2_group_desc *)gd_bh->b_data;
-	ret = ocfs2_alloc_dinode_update_counts(gb_inode, handle, gb_bh, len,
-					       le16_to_cpu(gd->bg_chain));
+	ret = ocfs2_alloc_dinode_update_bitmap(handle,
+				gb_inode, gb_bh, gd, gb_bh,
+				le16_to_cpu(gd->bg_chain),
+				goal_bit, len);
 	if (ret) {
 		mlog_errno(ret);
 		goto out_commit;
 	}
 
-	ret = ocfs2_block_group_set_bits(handle, gb_inode, gd, gd_bh,
-					 goal_bit, len);
-	if (ret)
-		mlog_errno(ret);
-
 	/*
 	 * Here we should write the new page out first if we are
 	 * in write-back mode.
@@ -957,6 +955,7 @@ static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
 	inode->i_ctime = CURRENT_TIME;
 	di->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
 	di->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
+	ocfs2_update_inode_fsync_trans(handle, inode, 0);
 
 	ocfs2_journal_dirty(handle, di_bh);
 
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 3683643f3f0e..58c975c1236b 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -231,6 +231,7 @@ static int ocfs2_mknod(struct inode *dir,
 	sigset_t oldset;
 	int did_block_signals = 0;
 	struct posix_acl *default_acl = NULL, *acl = NULL;
+	struct ocfs2_dentry_lock *dl = NULL;
 
 	trace_ocfs2_mknod(dir, dentry, dentry->d_name.len, dentry->d_name.name,
 			  (unsigned long long)OCFS2_I(dir)->ip_blkno,
@@ -423,6 +424,8 @@ static int ocfs2_mknod(struct inode *dir,
 		goto leave;
 	}
 
+	dl = dentry->d_fsdata;
+
 	status = ocfs2_add_entry(handle, dentry, inode,
 				 OCFS2_I(inode)->ip_blkno, parent_fe_bh,
 				 &lookup);
@@ -470,6 +473,16 @@ leave:
 	 * ocfs2_delete_inode will mutex_lock again.
 	 */
 	if ((status < 0) && inode) {
+		if (dl) {
+			ocfs2_simple_drop_lockres(osb, &dl->dl_lockres);
+			ocfs2_lock_res_free(&dl->dl_lockres);
+			BUG_ON(dl->dl_count != 1);
+			spin_lock(&dentry_attach_lock);
+			dentry->d_fsdata = NULL;
+			spin_unlock(&dentry_attach_lock);
+			kfree(dl);
+			iput(inode);
+		}
 		OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR;
 		clear_nlink(inode);
 		iput(inode);
@@ -495,6 +508,7 @@ static int __ocfs2_mknod_locked(struct inode *dir,
 	struct ocfs2_dinode *fe = NULL;
 	struct ocfs2_extent_list *fel;
 	u16 feat;
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 
 	*new_fe_bh = NULL;
 
@@ -576,6 +590,9 @@ static int __ocfs2_mknod_locked(struct inode *dir,
 			mlog_errno(status);
 	}
 
+	oi->i_sync_tid = handle->h_transaction->t_tid;
+	oi->i_datasync_tid = handle->h_transaction->t_tid;
+
 	status = 0; /* error in ocfs2_create_new_inode_locks is not
 		     * critical */
 
@@ -991,6 +1008,65 @@ leave:
 	return status;
 }
 
+static int ocfs2_check_if_ancestor(struct ocfs2_super *osb,
+		u64 src_inode_no, u64 dest_inode_no)
+{
+	int ret = 0, i = 0;
+	u64 parent_inode_no = 0;
+	u64 child_inode_no = src_inode_no;
+	struct inode *child_inode;
+
+#define MAX_LOOKUP_TIMES 32
+	while (1) {
+		child_inode = ocfs2_iget(osb, child_inode_no, 0, 0);
+		if (IS_ERR(child_inode)) {
+			ret = PTR_ERR(child_inode);
+			break;
+		}
+
+		ret = ocfs2_inode_lock(child_inode, NULL, 0);
+		if (ret < 0) {
+			iput(child_inode);
+			if (ret != -ENOENT)
+				mlog_errno(ret);
+			break;
+		}
+
+		ret = ocfs2_lookup_ino_from_name(child_inode, "..", 2,
+				&parent_inode_no);
+		ocfs2_inode_unlock(child_inode, 0);
+		iput(child_inode);
+		if (ret < 0) {
+			ret = -ENOENT;
+			break;
+		}
+
+		if (parent_inode_no == dest_inode_no) {
+			ret = 1;
+			break;
+		}
+
+		if (parent_inode_no == osb->root_inode->i_ino) {
+			ret = 0;
+			break;
+		}
+
+		child_inode_no = parent_inode_no;
+
+		if (++i >= MAX_LOOKUP_TIMES) {
+			mlog(ML_NOTICE, "max lookup times reached, filesystem "
+					"may have nested directories, "
+					"src inode: %llu, dest inode: %llu.\n",
+					(unsigned long long)src_inode_no,
+					(unsigned long long)dest_inode_no);
+			ret = 0;
+			break;
+		}
+	}
+
+	return ret;
+}
+
 /*
  * The only place this should be used is rename!
  * if they have the same id, then the 1st one is the only one locked.
@@ -1002,6 +1078,7 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 			     struct inode *inode2)
 {
 	int status;
+	int inode1_is_ancestor, inode2_is_ancestor;
 	struct ocfs2_inode_info *oi1 = OCFS2_I(inode1);
 	struct ocfs2_inode_info *oi2 = OCFS2_I(inode2);
 	struct buffer_head **tmpbh;
@@ -1015,9 +1092,26 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 	if (*bh2)
 		*bh2 = NULL;
 
-	/* we always want to lock the one with the lower lockid first. */
+	/* we always want to lock the one with the lower lockid first.
+	 * and if they are nested, we lock ancestor first */
 	if (oi1->ip_blkno != oi2->ip_blkno) {
-		if (oi1->ip_blkno < oi2->ip_blkno) {
+		inode1_is_ancestor = ocfs2_check_if_ancestor(osb, oi2->ip_blkno,
+				oi1->ip_blkno);
+		if (inode1_is_ancestor < 0) {
+			status = inode1_is_ancestor;
+			goto bail;
+		}
+
+		inode2_is_ancestor = ocfs2_check_if_ancestor(osb, oi1->ip_blkno,
+				oi2->ip_blkno);
+		if (inode2_is_ancestor < 0) {
+			status = inode2_is_ancestor;
+			goto bail;
+		}
+
+		if ((inode1_is_ancestor == 1) ||
+				(oi1->ip_blkno < oi2->ip_blkno &&
+				inode2_is_ancestor == 0)) {
 			/* switch id1 and id2 around */
 			tmpbh = bh2;
 			bh2 = bh1;
@@ -1134,6 +1228,22 @@ static int ocfs2_rename(struct inode *old_dir,
 			goto bail;
 		}
 		rename_lock = 1;
+
+		/* here we cannot guarantee the inodes haven't just been
+		 * changed, so check if they are nested again */
+		status = ocfs2_check_if_ancestor(osb, new_dir->i_ino,
+				old_inode->i_ino);
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail;
+		} else if (status == 1) {
+			status = -EPERM;
+			mlog(ML_ERROR, "src inode %llu should not be ancestor "
+				"of new dir inode %llu\n",
+				(unsigned long long)old_inode->i_ino,
+				(unsigned long long)new_dir->i_ino);
+			goto bail;
+		}
 	}
 
 	/* if old and new are the same, this'll just do one lock. */
@@ -1642,6 +1752,7 @@ static int ocfs2_symlink(struct inode *dir,
 	struct ocfs2_dir_lookup_result lookup = { NULL, };
 	sigset_t oldset;
 	int did_block_signals = 0;
+	struct ocfs2_dentry_lock *dl = NULL;
 
 	trace_ocfs2_symlink_begin(dir, dentry, symname,
 				  dentry->d_name.len, dentry->d_name.name);
@@ -1830,6 +1941,8 @@ static int ocfs2_symlink(struct inode *dir,
 		goto bail;
 	}
 
+	dl = dentry->d_fsdata;
+
 	status = ocfs2_add_entry(handle, dentry, inode,
 				 le64_to_cpu(fe->i_blkno), parent_fe_bh,
 				 &lookup);
@@ -1865,6 +1978,16 @@ bail:
 	if (xattr_ac)
 		ocfs2_free_alloc_context(xattr_ac);
 	if ((status < 0) && inode) {
+		if (dl) {
+			ocfs2_simple_drop_lockres(osb, &dl->dl_lockres);
+			ocfs2_lock_res_free(&dl->dl_lockres);
+			BUG_ON(dl->dl_count != 1);
+			spin_lock(&dentry_attach_lock);
+			dentry->d_fsdata = NULL;
+			spin_unlock(&dentry_attach_lock);
+			kfree(dl);
+			iput(inode);
+		}
 		OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR;
 		clear_nlink(inode);
 		iput(inode);
@@ -2481,6 +2604,7 @@ int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 	di->i_orphaned_slot = 0;
 	set_nlink(inode, 1);
 	ocfs2_set_links_count(di, inode->i_nlink);
+	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 	ocfs2_journal_dirty(handle, di_bh);
 
 	status = ocfs2_add_entry(handle, dentry, inode,
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 553f53cc73ae..a780e20d4fba 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -30,6 +30,7 @@
 #include <linux/sched.h>
 #include <linux/wait.h>
 #include <linux/list.h>
+#include <linux/llist.h>
 #include <linux/rbtree.h>
 #include <linux/workqueue.h>
 #include <linux/kref.h>
@@ -274,19 +275,16 @@ enum ocfs2_mount_options
 	OCFS2_MOUNT_HB_GLOBAL = 1 << 14, /* Global heartbeat */
 };
 
-#define OCFS2_OSB_SOFT_RO			0x0001
-#define OCFS2_OSB_HARD_RO			0x0002
-#define OCFS2_OSB_ERROR_FS			0x0004
-#define OCFS2_OSB_DROP_DENTRY_LOCK_IMMED	0x0008
-
-#define OCFS2_DEFAULT_ATIME_QUANTUM		60
+#define OCFS2_OSB_SOFT_RO	0x0001
+#define OCFS2_OSB_HARD_RO	0x0002
+#define OCFS2_OSB_ERROR_FS	0x0004
+#define OCFS2_DEFAULT_ATIME_QUANTUM	60
 
 struct ocfs2_journal;
 struct ocfs2_slot_info;
 struct ocfs2_recovery_map;
 struct ocfs2_replay_map;
 struct ocfs2_quota_recovery;
-struct ocfs2_dentry_lock;
 struct ocfs2_super
 {
 	struct task_struct *commit_task;
@@ -414,10 +412,9 @@ struct ocfs2_super
 	struct list_head blocked_lock_list;
 	unsigned long blocked_lock_count;
 
-	/* List of dentry locks to release. Anyone can add locks to
-	 * the list, ocfs2_wq processes the list  */
-	struct ocfs2_dentry_lock *dentry_lock_list;
-	struct work_struct dentry_lock_work;
+	/* List of dquot structures to drop last reference to */
+	struct llist_head dquot_drop_list;
+	struct work_struct dquot_drop_work;
 
 	wait_queue_head_t		osb_mount_event;
 
@@ -579,18 +576,6 @@ static inline void ocfs2_set_osb_flag(struct ocfs2_super *osb,
 	spin_unlock(&osb->osb_lock);
 }
 
-
-static inline unsigned long  ocfs2_test_osb_flag(struct ocfs2_super *osb,
-						 unsigned long flag)
-{
-	unsigned long ret;
-
-	spin_lock(&osb->osb_lock);
-	ret = osb->osb_flags & flag;
-	spin_unlock(&osb->osb_lock);
-	return ret;
-}
-
 static inline void ocfs2_set_ro_flag(struct ocfs2_super *osb,
 				     int hard)
 {
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 1b60c62aa9d6..90c997e4f1e8 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -788,7 +788,7 @@ DEFINE_OCFS2_UINT_UINT_UINT_EVENT(ocfs2_reserve_suballoc_bits_no_new_group);
 
 DEFINE_OCFS2_ULL_EVENT(ocfs2_reserve_new_inode_new_group);
 
-DEFINE_OCFS2_UINT_UINT_EVENT(ocfs2_block_group_set_bits);
+DEFINE_OCFS2_UINT_UINT_EVENT(ocfs2_alloc_dinode_update_bitmap);
 
 TRACE_EVENT(ocfs2_relink_block_group,
 	TP_PROTO(unsigned long long i_blkno, unsigned int chain,
diff --git a/fs/ocfs2/quota.h b/fs/ocfs2/quota.h
index d5ab56cbe5c5..f266d67df3c6 100644
--- a/fs/ocfs2/quota.h
+++ b/fs/ocfs2/quota.h
@@ -28,6 +28,7 @@ struct ocfs2_dquot {
 	unsigned int dq_use_count;	/* Number of nodes having reference to this entry in global quota file */
 	s64 dq_origspace;	/* Last globally synced space usage */
 	s64 dq_originodes;	/* Last globally synced inode usage */
+	struct llist_node list;	/* Member of list of dquots to drop */
 };
 
 /* Description of one chunk to recover in memory */
@@ -110,6 +111,7 @@ int ocfs2_read_quota_phys_block(struct inode *inode, u64 p_block,
 int ocfs2_create_local_dquot(struct dquot *dquot);
 int ocfs2_local_release_dquot(handle_t *handle, struct dquot *dquot);
 int ocfs2_local_write_dquot(struct dquot *dquot);
+void ocfs2_drop_dquot_refs(struct work_struct *work);
 
 extern const struct dquot_operations ocfs2_quota_operations;
 extern struct quota_format_type ocfs2_quota_format;
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index d7b5108789e2..b990a62cff50 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -10,6 +10,7 @@
 #include <linux/jiffies.h>
 #include <linux/writeback.h>
 #include <linux/workqueue.h>
+#include <linux/llist.h>
 
 #include <cluster/masklog.h>
 
@@ -679,6 +680,27 @@ static int ocfs2_calc_qdel_credits(struct super_block *sb, int type)
 	       OCFS2_INODE_UPDATE_CREDITS;
 }
 
+void ocfs2_drop_dquot_refs(struct work_struct *work)
+{
+	struct ocfs2_super *osb = container_of(work, struct ocfs2_super,
+					       dquot_drop_work);
+	struct llist_node *list;
+	struct ocfs2_dquot *odquot, *next_odquot;
+
+	list = llist_del_all(&osb->dquot_drop_list);
+	llist_for_each_entry_safe(odquot, next_odquot, list, list) {
+		/* Drop the reference we acquired in ocfs2_dquot_release() */
+		dqput(&odquot->dq_dquot);
+	}
+}
+
+/*
+ * Called when the last reference to dquot is dropped. If we are called from
+ * downconvert thread, we cannot do all the handling here because grabbing
+ * quota lock could deadlock (the node holding the quota lock could need some
+ * other cluster lock to proceed but with blocked downconvert thread we cannot
+ * release any lock).
+ */
 static int ocfs2_release_dquot(struct dquot *dquot)
 {
 	handle_t *handle;
@@ -694,6 +716,19 @@ static int ocfs2_release_dquot(struct dquot *dquot)
 	/* Check whether we are not racing with some other dqget() */
 	if (atomic_read(&dquot->dq_count) > 1)
 		goto out;
+	/* Running from downconvert thread? Postpone quota processing to wq */
+	if (current == osb->dc_task) {
+		/*
+		 * Grab our own reference to dquot and queue it for delayed
+		 * dropping.  Quota code rechecks after calling
+		 * ->release_dquot() and won't free dquot structure.
+		 */
+		dqgrab(dquot);
+		/* First entry on list -> queue work */
+		if (llist_add(&OCFS2_DQUOT(dquot)->list, &osb->dquot_drop_list))
+			queue_work(ocfs2_wq, &osb->dquot_drop_work);
+		goto out;
+	}
 	status = ocfs2_lock_global_qf(oinfo, 1);
 	if (status < 0)
 		goto out;
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 7509fccc17a4..83f1a665ae97 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -603,11 +603,25 @@ static struct kobj_attribute ocfs2_attr_cluster_stack =
 	       ocfs2_cluster_stack_show,
 	       ocfs2_cluster_stack_store);
 
+
+
+static ssize_t ocfs2_dlm_recover_show(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "1\n");
+}
+
+static struct kobj_attribute ocfs2_attr_dlm_recover_support =
+	__ATTR(dlm_recover_callback_support, S_IRUGO,
+	       ocfs2_dlm_recover_show, NULL);
+
 static struct attribute *ocfs2_attrs[] = {
 	&ocfs2_attr_max_locking_protocol.attr,
 	&ocfs2_attr_loaded_cluster_plugins.attr,
 	&ocfs2_attr_active_cluster_plugin.attr,
 	&ocfs2_attr_cluster_stack.attr,
+	&ocfs2_attr_dlm_recover_support.attr,
 	NULL,
 };
 
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 47ae2663a6f5..f7a3a73c068c 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -771,6 +771,7 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
 	spin_unlock(&OCFS2_I(alloc_inode)->ip_lock);
 	i_size_write(alloc_inode, le64_to_cpu(fe->i_size));
 	alloc_inode->i_blocks = ocfs2_inode_sector_count(alloc_inode);
+	ocfs2_update_inode_fsync_trans(handle, alloc_inode, 0);
 
 	status = 0;
 
@@ -1337,54 +1338,6 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
 	return status;
 }
 
-int ocfs2_block_group_set_bits(handle_t *handle,
-					     struct inode *alloc_inode,
-					     struct ocfs2_group_desc *bg,
-					     struct buffer_head *group_bh,
-					     unsigned int bit_off,
-					     unsigned int num_bits)
-{
-	int status;
-	void *bitmap = bg->bg_bitmap;
-	int journal_type = OCFS2_JOURNAL_ACCESS_WRITE;
-
-	/* All callers get the descriptor via
-	 * ocfs2_read_group_descriptor().  Any corruption is a code bug. */
-	BUG_ON(!OCFS2_IS_VALID_GROUP_DESC(bg));
-	BUG_ON(le16_to_cpu(bg->bg_free_bits_count) < num_bits);
-
-	trace_ocfs2_block_group_set_bits(bit_off, num_bits);
-
-	if (ocfs2_is_cluster_bitmap(alloc_inode))
-		journal_type = OCFS2_JOURNAL_ACCESS_UNDO;
-
-	status = ocfs2_journal_access_gd(handle,
-					 INODE_CACHE(alloc_inode),
-					 group_bh,
-					 journal_type);
-	if (status < 0) {
-		mlog_errno(status);
-		goto bail;
-	}
-
-	le16_add_cpu(&bg->bg_free_bits_count, -num_bits);
-	if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) {
-		ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit"
-			    " count %u but claims %u are freed. num_bits %d",
-			    (unsigned long long)le64_to_cpu(bg->bg_blkno),
-			    le16_to_cpu(bg->bg_bits),
-			    le16_to_cpu(bg->bg_free_bits_count), num_bits);
-		return -EROFS;
-	}
-	while(num_bits--)
-		ocfs2_set_bit(bit_off++, bitmap);
-
-	ocfs2_journal_dirty(handle, group_bh);
-
-bail:
-	return status;
-}
-
 /* find the one with the most empty bits */
 static inline u16 ocfs2_find_victim_chain(struct ocfs2_chain_list *cl)
 {
@@ -1580,31 +1533,78 @@ static int ocfs2_block_group_search(struct inode *inode,
 	return ret;
 }
 
-int ocfs2_alloc_dinode_update_counts(struct inode *inode,
-				       handle_t *handle,
-				       struct buffer_head *di_bh,
-				       u32 num_bits,
-				       u16 chain)
+int ocfs2_alloc_dinode_update_bitmap(handle_t *handle,
+				struct inode *alloc_inode,
+				struct buffer_head *di_bh,
+				struct ocfs2_group_desc *bg,
+				struct buffer_head *group_bh,
+				u16 chain, u32 bit_off, u32 num_bits)
 {
 	int ret;
 	u32 tmp_used;
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data;
 	struct ocfs2_chain_list *cl = (struct ocfs2_chain_list *) &di->id2.i_chain;
+	void *bitmap = bg->bg_bitmap;
+	int journal_type = OCFS2_JOURNAL_ACCESS_WRITE;
 
-	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
-				      OCFS2_JOURNAL_ACCESS_WRITE);
+	/*
+	 * All callers get the descriptor via
+	 * ocfs2_read_group_descriptor().  Any corruption is a code bug.
+	 */
+	BUG_ON(!OCFS2_IS_VALID_GROUP_DESC(bg));
+	BUG_ON(le16_to_cpu(bg->bg_free_bits_count) < num_bits);
+
+	trace_ocfs2_alloc_dinode_update_bitmap(bit_off, num_bits);
+
+	ret = ocfs2_journal_access_di(handle,
+			INODE_CACHE(alloc_inode), di_bh, journal_type);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (ocfs2_is_cluster_bitmap(alloc_inode))
+		journal_type = OCFS2_JOURNAL_ACCESS_UNDO;
+
+	ret = ocfs2_journal_access_gd(handle,
+			INODE_CACHE(alloc_inode), group_bh, journal_type);
 	if (ret < 0) {
 		mlog_errno(ret);
 		goto out;
 	}
 
+	/* update alloc_dinode counts */
 	tmp_used = le32_to_cpu(di->id1.bitmap1.i_used);
 	di->id1.bitmap1.i_used = cpu_to_le32(num_bits + tmp_used);
 	le32_add_cpu(&cl->cl_recs[chain].c_free, -num_bits);
+
+	/* update bg counts and bitmap*/
+	le16_add_cpu(&bg->bg_free_bits_count, -num_bits);
+	if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) {
+		ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit"
+			" count %u but claims %u are freed. num_bits %d",
+			(unsigned long long)le64_to_cpu(bg->bg_blkno),
+			le16_to_cpu(bg->bg_bits),
+			le16_to_cpu(bg->bg_free_bits_count), num_bits);
+		ret = -EROFS;
+		goto out_rollback;
+	}
+	while (num_bits--)
+		ocfs2_set_bit(bit_off++, bitmap);
+
 	ocfs2_journal_dirty(handle, di_bh);
+	ocfs2_journal_dirty(handle, group_bh);
 
 out:
 	return ret;
+
+out_rollback:
+	le16_add_cpu(&bg->bg_free_bits_count, num_bits);
+
+	di->id1.bitmap1.i_used = cpu_to_le32(tmp_used - num_bits);
+	le32_add_cpu(&cl->cl_recs[chain].c_free, num_bits);
+
+	return ret;
 }
 
 static int ocfs2_bg_discontig_fix_by_rec(struct ocfs2_suballoc_result *res,
@@ -1697,19 +1697,15 @@ static int ocfs2_search_one_group(struct ocfs2_alloc_context *ac,
 	if (ac->ac_find_loc_only)
 		goto out_loc_only;
 
-	ret = ocfs2_alloc_dinode_update_counts(alloc_inode, handle, ac->ac_bh,
-					       res->sr_bits,
-					       le16_to_cpu(gd->bg_chain));
+	ret = ocfs2_alloc_dinode_update_bitmap(handle,
+			alloc_inode, ac->ac_bh, gd, group_bh,
+			le16_to_cpu(gd->bg_chain),
+			res->sr_bit_offset, res->sr_bits);
 	if (ret < 0) {
 		mlog_errno(ret);
 		goto out;
 	}
 
-	ret = ocfs2_block_group_set_bits(handle, alloc_inode, gd, group_bh,
-					 res->sr_bit_offset, res->sr_bits);
-	if (ret < 0)
-		mlog_errno(ret);
-
 out_loc_only:
 	*bits_left = le16_to_cpu(gd->bg_free_bits_count);
 
@@ -1823,20 +1819,9 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
 	if (ac->ac_find_loc_only)
 		goto out_loc_only;
 
-	status = ocfs2_alloc_dinode_update_counts(alloc_inode, handle,
-						  ac->ac_bh, res->sr_bits,
-						  chain);
-	if (status) {
-		mlog_errno(status);
-		goto bail;
-	}
-
-	status = ocfs2_block_group_set_bits(handle,
-					    alloc_inode,
-					    bg,
-					    group_bh,
-					    res->sr_bit_offset,
-					    res->sr_bits);
+	status = ocfs2_alloc_dinode_update_bitmap(handle,
+			alloc_inode, ac->ac_bh, bg, group_bh,
+			chain, res->sr_bit_offset, res->sr_bits);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
@@ -2091,7 +2076,7 @@ int ocfs2_find_new_inode_loc(struct inode *dir,
 
 	ac->ac_find_loc_priv = res;
 	*fe_blkno = res->sr_blkno;
-
+	ocfs2_update_inode_fsync_trans(handle, dir, 0);
 out:
 	if (handle)
 		ocfs2_commit_trans(OCFS2_SB(dir->i_sb), handle);
@@ -2134,20 +2119,9 @@ int ocfs2_claim_new_inode_at_loc(handle_t *handle,
 	bg = (struct ocfs2_group_desc *) bg_bh->b_data;
 	chain = le16_to_cpu(bg->bg_chain);
 
-	ret = ocfs2_alloc_dinode_update_counts(ac->ac_inode, handle,
-					       ac->ac_bh, res->sr_bits,
-					       chain);
-	if (ret) {
-		mlog_errno(ret);
-		goto out;
-	}
-
-	ret = ocfs2_block_group_set_bits(handle,
-					 ac->ac_inode,
-					 bg,
-					 bg_bh,
-					 res->sr_bit_offset,
-					 res->sr_bits);
+	ret = ocfs2_alloc_dinode_update_bitmap(handle,
+			ac->ac_inode, ac->ac_bh, bg, bg_bh,
+			chain, res->sr_bit_offset, res->sr_bits);
 	if (ret < 0) {
 		mlog_errno(ret);
 		goto out;
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index 218d8036b3e7..f704f3a1172b 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -85,19 +85,14 @@ int ocfs2_reserve_new_inode(struct ocfs2_super *osb,
 int ocfs2_reserve_clusters(struct ocfs2_super *osb,
 			   u32 bits_wanted,
 			   struct ocfs2_alloc_context **ac);
-
-int ocfs2_alloc_dinode_update_counts(struct inode *inode,
-			 handle_t *handle,
-			 struct buffer_head *di_bh,
-			 u32 num_bits,
-			 u16 chain);
-int ocfs2_block_group_set_bits(handle_t *handle,
-			 struct inode *alloc_inode,
-			 struct ocfs2_group_desc *bg,
-			 struct buffer_head *group_bh,
-			 unsigned int bit_off,
-			 unsigned int num_bits);
-
+int ocfs2_alloc_dinode_update_bitmap(handle_t *handle,
+				struct inode *alloc_inode,
+				struct buffer_head *di_bh,
+				struct ocfs2_group_desc *bg,
+				struct buffer_head *group_bh,
+				u16 chain,
+				u32 bit_off,
+				u32 num_bits);
 int ocfs2_claim_metadata(handle_t *handle,
 			 struct ocfs2_alloc_context *ac,
 			 u32 bits_wanted,
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 5f9bf8f9dfa7..6396494712d3 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -561,6 +561,9 @@ static struct inode *ocfs2_alloc_inode(struct super_block *sb)
 	if (!oi)
 		return NULL;
 
+	oi->i_sync_tid = 0;
+	oi->i_datasync_tid = 0;
+
 	jbd2_journal_init_jbd_inode(&oi->ip_jinode, &oi->vfs_inode);
 	return &oi->vfs_inode;
 }
@@ -1240,30 +1243,11 @@ static struct dentry *ocfs2_mount(struct file_system_type *fs_type,
 	return mount_bdev(fs_type, flags, dev_name, data, ocfs2_fill_super);
 }
 
-static void ocfs2_kill_sb(struct super_block *sb)
-{
-	struct ocfs2_super *osb = OCFS2_SB(sb);
-
-	/* Failed mount? */
-	if (!osb || atomic_read(&osb->vol_state) == VOLUME_DISABLED)
-		goto out;
-
-	/* Prevent further queueing of inode drop events */
-	spin_lock(&dentry_list_lock);
-	ocfs2_set_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED);
-	spin_unlock(&dentry_list_lock);
-	/* Wait for work to finish and/or remove it */
-	cancel_work_sync(&osb->dentry_lock_work);
-out:
-	kill_block_super(sb);
-}
-
 static struct file_system_type ocfs2_fs_type = {
 	.owner          = THIS_MODULE,
 	.name           = "ocfs2",
 	.mount          = ocfs2_mount,
-	.kill_sb        = ocfs2_kill_sb,
-
+	.kill_sb        = kill_block_super,
 	.fs_flags       = FS_REQUIRES_DEV|FS_RENAME_DOES_D_MOVE,
 	.next           = NULL
 };
@@ -1614,14 +1598,9 @@ static int ocfs2_show_options(struct seq_file *s, struct dentry *root)
 	return 0;
 }
 
-wait_queue_head_t ocfs2__ioend_wq[OCFS2_IOEND_WQ_HASH_SZ];
-
 static int __init ocfs2_init(void)
 {
-	int status, i;
-
-	for (i = 0; i < OCFS2_IOEND_WQ_HASH_SZ; i++)
-		init_waitqueue_head(&ocfs2__ioend_wq[i]);
+	int status;
 
 	status = init_ocfs2_uptodate_cache();
 	if (status < 0)
@@ -1763,7 +1742,7 @@ static void ocfs2_inode_init_once(void *data)
 	ocfs2_extent_map_init(&oi->vfs_inode);
 	INIT_LIST_HEAD(&oi->ip_io_markers);
 	oi->ip_dir_start_lookup = 0;
-	atomic_set(&oi->ip_unaligned_aio, 0);
+	mutex_init(&oi->ip_unaligned_aio);
 	init_rwsem(&oi->ip_alloc_sem);
 	init_rwsem(&oi->ip_xattr_sem);
 	mutex_init(&oi->ip_io_mutex);
@@ -1934,17 +1913,16 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 
 	debugfs_remove(osb->osb_ctxt);
 
-	/*
-	 * Flush inode dropping work queue so that deletes are
-	 * performed while the filesystem is still working
-	 */
-	ocfs2_drop_all_dl_inodes(osb);
-
 	/* Orphan scan should be stopped as early as possible */
 	ocfs2_orphan_scan_stop(osb);
 
 	ocfs2_disable_quotas(osb);
 
+	/* All dquots should be freed by now */
+	WARN_ON(!llist_empty(&osb->dquot_drop_list));
+	/* Wait for worker to be done with the work structure in osb */
+	cancel_work_sync(&osb->dquot_drop_work);
+
 	ocfs2_shutdown_local_alloc(osb);
 
 	/* This will disable recovery and flush any recovery work. */
@@ -2079,7 +2057,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
 	struct inode *inode = NULL;
 	struct ocfs2_journal *journal;
-	__le32 uuid_net_key;
 	struct ocfs2_super *osb;
 	u64 total_blocks;
 
@@ -2278,8 +2255,8 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	INIT_WORK(&journal->j_recovery_work, ocfs2_complete_recovery);
 	journal->j_state = OCFS2_JOURNAL_FREE;
 
-	INIT_WORK(&osb->dentry_lock_work, ocfs2_drop_dl_inodes);
-	osb->dentry_lock_list = NULL;
+	INIT_WORK(&osb->dquot_drop_work, ocfs2_drop_dquot_refs);
+	init_llist_head(&osb->dquot_drop_list);
 
 	/* get some pseudo constants for clustersize bits */
 	osb->s_clustersize_bits =
@@ -2313,8 +2290,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
 		goto bail;
 	}
 
-	memcpy(&uuid_net_key, di->id2.i_super.s_uuid, sizeof(uuid_net_key));
-
 	strncpy(osb->vol_label, di->id2.i_super.s_label, 63);
 	osb->vol_label[63] = '\0';
 	osb->root_blkno = le64_to_cpu(di->id2.i_super.s_root_blkno);
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 185fa3b7f962..14b8c46b4fbb 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -2602,6 +2602,7 @@ int ocfs2_xattr_remove(struct inode *inode, struct buffer_head *di_bh)
 	oi->ip_dyn_features &= ~(OCFS2_INLINE_XATTR_FL | OCFS2_HAS_XATTR_FL);
 	di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features);
 	spin_unlock(&oi->ip_lock);
+	ocfs2_update_inode_fsync_trans(handle, inode, 0);
 
 	ocfs2_journal_dirty(handle, di_bh);
 out_commit:
@@ -3200,8 +3201,15 @@ meta_guess:
 			clusters_add += 1;
 		}
 	} else {
-		meta_add += 1;
 		credits += OCFS2_XATTR_BLOCK_CREATE_CREDITS;
+		if (xi->xi_value_len > OCFS2_XATTR_INLINE_SIZE) {
+			struct ocfs2_extent_list *el = &def_xv.xv.xr_list;
+			meta_add += ocfs2_extend_meta_needed(el);
+			credits += ocfs2_calc_extend_credits(inode->i_sb,
+							     el);
+		} else {
+			meta_add += 1;
+		}
 	}
 out:
 	if (clusters_need)
@@ -3614,6 +3622,7 @@ int ocfs2_xattr_set(struct inode *inode,
 	}
 
 	ret = __ocfs2_xattr_set_handle(inode, di, &xi, &xis, &xbs, &ctxt);
+	ocfs2_update_inode_fsync_trans(ctxt.handle, inode, 0);
 
 	ocfs2_commit_trans(osb, ctxt.handle);
 
@@ -5476,6 +5485,7 @@ static int ocfs2_rm_xattr_cluster(struct inode *inode,
 	ret = ocfs2_truncate_log_append(osb, handle, blkno, len);
 	if (ret)
 		mlog_errno(ret);
+	ocfs2_update_inode_fsync_trans(handle, inode, 0);
 
 out_commit:
 	ocfs2_commit_trans(osb, handle);
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index d8b0afde2179..ec58c7659183 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -183,7 +183,7 @@ int omfs_sync_inode(struct inode *inode)
  */
 static void omfs_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 
 	if (inode->i_nlink)
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 656e401794de..64db2bceac59 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -138,8 +138,8 @@ static const char * const task_state_array[] = {
 	"D (disk sleep)",	/*   2 */
 	"T (stopped)",		/*   4 */
 	"t (tracing stop)",	/*   8 */
-	"Z (zombie)",		/*  16 */
-	"X (dead)",		/*  32 */
+	"X (dead)",		/*  16 */
+	"Z (zombie)",		/*  32 */
 };
 
 static inline const char *get_task_state(struct task_struct *tsk)
diff --git a/fs/proc/base.c b/fs/proc/base.c
index a9b591a29dcb..a6087f35d820 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1204,6 +1204,9 @@ static ssize_t proc_fault_inject_write(struct file * file,
 	make_it_fail = simple_strtol(strstrip(buffer), &end, 0);
 	if (*end)
 		return -EINVAL;
+	if (make_it_fail < 0 || make_it_fail > 1)
+		return -EINVAL;
+
 	task = get_proc_task(file_inode(file));
 	if (!task)
 		return -ESRCH;
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 985ea881b5bc..0788d093f5d8 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -11,6 +11,7 @@
 
 #include <linux/proc_fs.h>
 
+#include "../mount.h"
 #include "internal.h"
 #include "fd.h"
 
@@ -48,8 +49,9 @@ static int seq_show(struct seq_file *m, void *v)
 	}
 
 	if (!ret) {
-                seq_printf(m, "pos:\t%lli\nflags:\t0%o\n",
-			   (long long)file->f_pos, f_flags);
+		seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\n",
+			   (long long)file->f_pos, f_flags,
+			   real_mount(file->f_path.mnt)->mnt_id);
 		if (file->f_op->show_fdinfo)
 			ret = file->f_op->show_fdinfo(m, file);
 		fput(file);
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 124fc43c7090..8f20e3404fd2 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -35,7 +35,7 @@ static void proc_evict_inode(struct inode *inode)
 	const struct proc_ns_operations *ns_ops;
 	void *ns;
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 
 	/* Stop tracking associated processes */
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 136e548d9567..7445af0b1aa3 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -73,7 +73,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	available += pagecache;
 
 	/*
-	 * Part of the reclaimable swap consists of items that are in use,
+	 * Part of the reclaimable slab consists of items that are in use,
 	 * and cannot be freed. Cap this estimate at the low watermark.
 	 */
 	available += global_page_state(NR_SLAB_RECLAIMABLE) -
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index fb52b548080d..f75ce811d430 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1,4 +1,5 @@
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/hugetlb.h>
 #include <linux/huge_mm.h>
 #include <linux/mount.h>
@@ -152,7 +153,7 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 
 	/*
 	 * We remember last_addr rather than next_addr to hit with
-	 * mmap_cache most of the time. We have zero last_addr at
+	 * vmacache most of the time. We have zero last_addr at
 	 * the beginning and also after lseek. We will have -1 last_addr
 	 * after the end of the vmas.
 	 */
@@ -423,7 +424,6 @@ const struct file_operations proc_tid_maps_operations = {
 
 #ifdef CONFIG_PROC_PAGE_MONITOR
 struct mem_size_stats {
-	struct vm_area_struct *vma;
 	unsigned long resident;
 	unsigned long shared_clean;
 	unsigned long shared_dirty;
@@ -437,15 +437,16 @@ struct mem_size_stats {
 	u64 pss;
 };
 
-
-static void smaps_pte_entry(pte_t ptent, unsigned long addr,
-		unsigned long ptent_size, struct mm_walk *walk)
+static int smaps_pte(pte_t *pte, unsigned long addr, unsigned long end,
+			struct mm_walk *walk)
 {
 	struct mem_size_stats *mss = walk->private;
-	struct vm_area_struct *vma = mss->vma;
+	struct vm_area_struct *vma = walk->vma;
 	pgoff_t pgoff = linear_page_index(vma, addr);
 	struct page *page = NULL;
 	int mapcount;
+	pte_t ptent = *pte;
+	unsigned long ptent_size = end - addr;
 
 	if (pte_present(ptent)) {
 		page = vm_normal_page(vma, addr, ptent);
@@ -462,7 +463,7 @@ static void smaps_pte_entry(pte_t ptent, unsigned long addr,
 	}
 
 	if (!page)
-		return;
+		return 0;
 
 	if (PageAnon(page))
 		mss->anonymous += ptent_size;
@@ -488,35 +489,22 @@ static void smaps_pte_entry(pte_t ptent, unsigned long addr,
 			mss->private_clean += ptent_size;
 		mss->pss += (ptent_size << PSS_SHIFT);
 	}
+	return 0;
 }
 
-static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
-			   struct mm_walk *walk)
+static int smaps_pmd(pmd_t *pmd, unsigned long addr, unsigned long end,
+			struct mm_walk *walk)
 {
 	struct mem_size_stats *mss = walk->private;
-	struct vm_area_struct *vma = mss->vma;
-	pte_t *pte;
 	spinlock_t *ptl;
 
-	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
-		smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
+	if (pmd_trans_huge_lock(pmd, walk->vma, &ptl) == 1) {
+		smaps_pte((pte_t *)pmd, addr, addr + HPAGE_PMD_SIZE, walk);
 		spin_unlock(ptl);
 		mss->anonymous_thp += HPAGE_PMD_SIZE;
-		return 0;
+		/* don't call smaps_pte() */
+		walk->skip = 1;
 	}
-
-	if (pmd_trans_unstable(pmd))
-		return 0;
-	/*
-	 * The mmap_sem held all the way back in m_start() is what
-	 * keeps khugepaged out of here and from collapsing things
-	 * in here.
-	 */
-	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	for (; addr != end; pte++, addr += PAGE_SIZE)
-		smaps_pte_entry(*pte, addr, PAGE_SIZE, walk);
-	pte_unmap_unlock(pte - 1, ptl);
-	cond_resched();
 	return 0;
 }
 
@@ -581,16 +569,16 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 	struct vm_area_struct *vma = v;
 	struct mem_size_stats mss;
 	struct mm_walk smaps_walk = {
-		.pmd_entry = smaps_pte_range,
+		.pmd_entry = smaps_pmd,
+		.pte_entry = smaps_pte,
 		.mm = vma->vm_mm,
+		.vma = vma,
 		.private = &mss,
 	};
 
 	memset(&mss, 0, sizeof mss);
-	mss.vma = vma;
 	/* mmap_sem is held in m_start */
-	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
-		walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);
+	walk_page_vma(vma, &smaps_walk);
 
 	show_map_vma(m, vma, is_pid);
 
@@ -711,7 +699,6 @@ enum clear_refs_types {
 };
 
 struct clear_refs_private {
-	struct vm_area_struct *vma;
 	enum clear_refs_types type;
 };
 
@@ -743,41 +730,43 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 #endif
 }
 
-static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
+static int clear_refs_pte(pte_t *pte, unsigned long addr,
 				unsigned long end, struct mm_walk *walk)
 {
 	struct clear_refs_private *cp = walk->private;
-	struct vm_area_struct *vma = cp->vma;
-	pte_t *pte, ptent;
-	spinlock_t *ptl;
+	struct vm_area_struct *vma = walk->vma;
 	struct page *page;
 
-	split_huge_page_pmd(vma, addr, pmd);
-	if (pmd_trans_unstable(pmd))
+	if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
+		clear_soft_dirty(vma, addr, pte);
 		return 0;
+	}
+	if (!pte_present(*pte))
+		return 0;
+	page = vm_normal_page(vma, addr, *pte);
+	if (!page)
+		return 0;
+	/* Clear accessed and referenced bits. */
+	ptep_test_and_clear_young(vma, addr, pte);
+	ClearPageReferenced(page);
+	return 0;
+}
 
-	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	for (; addr != end; pte++, addr += PAGE_SIZE) {
-		ptent = *pte;
-
-		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
-			clear_soft_dirty(vma, addr, pte);
-			continue;
-		}
-
-		if (!pte_present(ptent))
-			continue;
-
-		page = vm_normal_page(vma, addr, ptent);
-		if (!page)
-			continue;
+static int clear_refs_test_walk(unsigned long start, unsigned long end,
+				struct mm_walk *walk)
+{
+	struct clear_refs_private *cp = walk->private;
+	struct vm_area_struct *vma = walk->vma;
 
-		/* Clear accessed and referenced bits. */
-		ptep_test_and_clear_young(vma, addr, pte);
-		ClearPageReferenced(page);
-	}
-	pte_unmap_unlock(pte - 1, ptl);
-	cond_resched();
+	/*
+	 * Writing 1 to /proc/pid/clear_refs affects all pages.
+	 * Writing 2 to /proc/pid/clear_refs only affects anonymous pages.
+	 * Writing 3 to /proc/pid/clear_refs only affects file mapped pages.
+	 */
+	if (cp->type == CLEAR_REFS_ANON && vma->vm_file)
+		walk->skip = 1;
+	if (cp->type == CLEAR_REFS_MAPPED && !vma->vm_file)
+		walk->skip = 1;
 	return 0;
 }
 
@@ -819,33 +808,16 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 			.type = type,
 		};
 		struct mm_walk clear_refs_walk = {
-			.pmd_entry = clear_refs_pte_range,
+			.pte_entry = clear_refs_pte,
+			.test_walk = clear_refs_test_walk,
 			.mm = mm,
 			.private = &cp,
 		};
 		down_read(&mm->mmap_sem);
 		if (type == CLEAR_REFS_SOFT_DIRTY)
 			mmu_notifier_invalidate_range_start(mm, 0, -1);
-		for (vma = mm->mmap; vma; vma = vma->vm_next) {
-			cp.vma = vma;
-			if (is_vm_hugetlb_page(vma))
-				continue;
-			/*
-			 * Writing 1 to /proc/pid/clear_refs affects all pages.
-			 *
-			 * Writing 2 to /proc/pid/clear_refs only affects
-			 * Anonymous pages.
-			 *
-			 * Writing 3 to /proc/pid/clear_refs only affects file
-			 * mapped pages.
-			 */
-			if (type == CLEAR_REFS_ANON && vma->vm_file)
-				continue;
-			if (type == CLEAR_REFS_MAPPED && !vma->vm_file)
-				continue;
-			walk_page_range(vma->vm_start, vma->vm_end,
-					&clear_refs_walk);
-		}
+		for (vma = mm->mmap; vma; vma = vma->vm_next)
+			walk_page_vma(vma, &clear_refs_walk);
 		if (type == CLEAR_REFS_SOFT_DIRTY)
 			mmu_notifier_invalidate_range_end(mm, 0, -1);
 		flush_tlb_mm(mm);
@@ -986,19 +958,33 @@ static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemap
 }
 #endif
 
-static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+static int pagemap_pte(pte_t *pte, unsigned long addr, unsigned long end,
 			     struct mm_walk *walk)
 {
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma = walk->vma;
 	struct pagemapread *pm = walk->private;
-	spinlock_t *ptl;
-	pte_t *pte;
+	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
+
+	if (vma && vma->vm_start <= addr && end <= vma->vm_end) {
+		pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
+		/* unmap before userspace copy */
+		pte_unmap(pte);
+	}
+	return add_to_pagemap(addr, &pme, pm);
+}
+
+static int pagemap_pmd(pmd_t *pmd, unsigned long addr, unsigned long end,
+			     struct mm_walk *walk)
+{
 	int err = 0;
+	struct vm_area_struct *vma = walk->vma;
+	struct pagemapread *pm = walk->private;
 	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
+	spinlock_t *ptl;
 
-	/* find the first VMA at or above 'addr' */
-	vma = find_vma(walk->mm, addr);
-	if (vma && pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	if (!vma)
+		return err;
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		int pmd_flags2;
 
 		if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(*pmd))
@@ -1017,41 +1003,9 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 				break;
 		}
 		spin_unlock(ptl);
-		return err;
-	}
-
-	if (pmd_trans_unstable(pmd))
-		return 0;
-	for (; addr != end; addr += PAGE_SIZE) {
-		int flags2;
-
-		/* check to see if we've left 'vma' behind
-		 * and need a new, higher one */
-		if (vma && (addr >= vma->vm_end)) {
-			vma = find_vma(walk->mm, addr);
-			if (vma && (vma->vm_flags & VM_SOFTDIRTY))
-				flags2 = __PM_SOFT_DIRTY;
-			else
-				flags2 = 0;
-			pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
-		}
-
-		/* check that 'vma' actually covers this address,
-		 * and that it isn't a huge page vma */
-		if (vma && (vma->vm_start <= addr) &&
-		    !is_vm_hugetlb_page(vma)) {
-			pte = pte_offset_map(pmd, addr);
-			pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
-			/* unmap before userspace copy */
-			pte_unmap(pte);
-		}
-		err = add_to_pagemap(addr, &pme, pm);
-		if (err)
-			return err;
+		/* don't call pagemap_pte() */
+		walk->skip = 1;
 	}
-
-	cond_resched();
-
 	return err;
 }
 
@@ -1069,24 +1023,22 @@ static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *
 }
 
 /* This function walks within one hugetlb entry in the single call */
-static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
-				 unsigned long addr, unsigned long end,
+static int pagemap_hugetlb(pte_t *pte, unsigned long addr, unsigned long end,
 				 struct mm_walk *walk)
 {
 	struct pagemapread *pm = walk->private;
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma = walk->vma;
 	int err = 0;
 	int flags2;
 	pagemap_entry_t pme;
+	unsigned long hmask;
 
-	vma = find_vma(walk->mm, addr);
-	WARN_ON_ONCE(!vma);
-
-	if (vma && (vma->vm_flags & VM_SOFTDIRTY))
+	if (vma->vm_flags & VM_SOFTDIRTY)
 		flags2 = __PM_SOFT_DIRTY;
 	else
 		flags2 = 0;
 
+	hmask = huge_page_mask(hstate_vma(vma));
 	for (; addr != end; addr += PAGE_SIZE) {
 		int offset = (addr & ~hmask) >> PAGE_SHIFT;
 		huge_pte_to_pagemap_entry(&pme, pm, *pte, offset, flags2);
@@ -1094,9 +1046,6 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
 		if (err)
 			return err;
 	}
-
-	cond_resched();
-
 	return err;
 }
 #endif /* HUGETLB_PAGE */
@@ -1163,10 +1112,11 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!mm || IS_ERR(mm))
 		goto out_free;
 
-	pagemap_walk.pmd_entry = pagemap_pte_range;
+	pagemap_walk.pte_entry = pagemap_pte;
+	pagemap_walk.pmd_entry = pagemap_pmd;
 	pagemap_walk.pte_hole = pagemap_pte_hole;
 #ifdef CONFIG_HUGETLB_PAGE
-	pagemap_walk.hugetlb_entry = pagemap_hugetlb_range;
+	pagemap_walk.hugetlb_entry = pagemap_hugetlb;
 #endif
 	pagemap_walk.mm = mm;
 	pagemap_walk.private = &pm;
@@ -1242,7 +1192,6 @@ const struct file_operations proc_pagemap_operations = {
 #ifdef CONFIG_NUMA
 
 struct numa_maps {
-	struct vm_area_struct *vma;
 	unsigned long pages;
 	unsigned long anon;
 	unsigned long active;
@@ -1308,44 +1257,42 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma,
 	return page;
 }
 
-static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
+static int gather_pte_stats(pte_t *pte, unsigned long addr,
 		unsigned long end, struct mm_walk *walk)
 {
-	struct numa_maps *md;
-	spinlock_t *ptl;
-	pte_t *orig_pte;
-	pte_t *pte;
+	struct numa_maps *md = walk->private;
 
-	md = walk->private;
+	struct page *page = can_gather_numa_stats(*pte, walk->vma, addr);
+	if (!page)
+		return 0;
+	gather_stats(page, md, pte_dirty(*pte), 1);
+	return 0;
+}
+
+static int gather_pmd_stats(pmd_t *pmd, unsigned long addr,
+		unsigned long end, struct mm_walk *walk)
+{
+	struct numa_maps *md = walk->private;
+	struct vm_area_struct *vma = walk->vma;
+	spinlock_t *ptl;
 
-	if (pmd_trans_huge_lock(pmd, md->vma, &ptl) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		pte_t huge_pte = *(pte_t *)pmd;
 		struct page *page;
 
-		page = can_gather_numa_stats(huge_pte, md->vma, addr);
+		page = can_gather_numa_stats(huge_pte, vma, addr);
 		if (page)
 			gather_stats(page, md, pte_dirty(huge_pte),
 				     HPAGE_PMD_SIZE/PAGE_SIZE);
 		spin_unlock(ptl);
-		return 0;
+		/* don't call gather_pte_stats() */
+		walk->skip = 1;
 	}
-
-	if (pmd_trans_unstable(pmd))
-		return 0;
-	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
-	do {
-		struct page *page = can_gather_numa_stats(*pte, md->vma, addr);
-		if (!page)
-			continue;
-		gather_stats(page, md, pte_dirty(*pte), 1);
-
-	} while (pte++, addr += PAGE_SIZE, addr != end);
-	pte_unmap_unlock(orig_pte, ptl);
 	return 0;
 }
 #ifdef CONFIG_HUGETLB_PAGE
-static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
-		unsigned long addr, unsigned long end, struct mm_walk *walk)
+static int gather_hugetlb_stats(pte_t *pte, unsigned long addr,
+				unsigned long end, struct mm_walk *walk)
 {
 	struct numa_maps *md;
 	struct page *page;
@@ -1353,6 +1300,9 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
 	if (pte_none(*pte))
 		return 0;
 
+	if (!pte_present(*pte))
+		return 0;
+
 	page = pte_page(*pte);
 	if (!page)
 		return 0;
@@ -1363,8 +1313,8 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
 }
 
 #else
-static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
-		unsigned long addr, unsigned long end, struct mm_walk *walk)
+static int gather_hugetlb_stats(pte_t *pte, unsigned long addr,
+				unsigned long end, struct mm_walk *walk)
 {
 	return 0;
 }
@@ -1393,12 +1343,12 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	/* Ensure we start with an empty set of numa_maps statistics. */
 	memset(md, 0, sizeof(*md));
 
-	md->vma = vma;
-
-	walk.hugetlb_entry = gather_hugetbl_stats;
-	walk.pmd_entry = gather_pte_stats;
+	walk.hugetlb_entry = gather_hugetlb_stats;
+	walk.pmd_entry = gather_pmd_stats;
+	walk.pte_entry = gather_pte_stats;
 	walk.private = md;
 	walk.mm = mm;
+	walk.vma = vma;
 
 	pol = get_vma_policy(task, vma, vma->vm_start);
 	mpol_to_str(buffer, sizeof(buffer), pol);
@@ -1429,6 +1379,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	if (is_vm_hugetlb_page(vma))
 		seq_printf(m, " huge");
 
+	/* mmap_sem is held by m_start */
 	walk_page_range(vma->vm_start, vma->vm_end, &walk);
 
 	if (!md->pages)
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 88d4585b30f1..6a8e785b29da 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -484,7 +484,6 @@ static int __init update_note_header_size_elf64(const Elf64_Ehdr *ehdr_ptr)
 		phdr_ptr->p_memsz = real_sz;
 		if (real_sz == 0) {
 			pr_warn("Warning: Zero PT_NOTE entries found\n");
-			return -EINVAL;
 		}
 	}
 
@@ -671,7 +670,6 @@ static int __init update_note_header_size_elf32(const Elf32_Ehdr *ehdr_ptr)
 		phdr_ptr->p_memsz = real_sz;
 		if (real_sz == 0) {
 			pr_warn("Warning: Zero PT_NOTE entries found\n");
-			return -EINVAL;
 		}
 	}
 
@@ -1118,4 +1116,3 @@ void vmcore_cleanup(void)
 	}
 	free_elfcorebuf();
 }
-EXPORT_SYMBOL_GPL(vmcore_cleanup);
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index cfc8dcc16043..9cd5f63715c0 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -528,7 +528,7 @@ restart:
 		if (atomic_read(&dquot->dq_count)) {
 			DEFINE_WAIT(wait);
 
-			atomic_inc(&dquot->dq_count);
+			dqgrab(dquot);
 			prepare_to_wait(&dquot->dq_wait_unused, &wait,
 					TASK_UNINTERRUPTIBLE);
 			spin_unlock(&dq_list_lock);
@@ -632,7 +632,7 @@ int dquot_writeback_dquots(struct super_block *sb, int type)
 			/* Now we have active dquot from which someone is
  			 * holding reference so we can safely just increase
 			 * use count */
-			atomic_inc(&dquot->dq_count);
+			dqgrab(dquot);
 			spin_unlock(&dq_list_lock);
 			dqstats_inc(DQST_LOOKUPS);
 			err = sb->dq_op->write_dquot(dquot);
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index ad62bdbb451e..bc8b8009897d 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -35,7 +35,7 @@ void reiserfs_evict_inode(struct inode *inode)
 	if (!inode->i_nlink && !is_bad_inode(inode))
 		dquot_initialize(inode);
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	if (inode->i_nlink)
 		goto no_delete;
 
diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h
index 8d06adf89948..83d4eac8059a 100644
--- a/fs/reiserfs/reiserfs.h
+++ b/fs/reiserfs/reiserfs.h
@@ -2831,6 +2831,7 @@ void reiserfs_init_alloc_options(struct super_block *s);
  */
 __le32 reiserfs_choose_packing(struct inode *dir);
 
+void show_alloc_options(struct seq_file *seq, struct super_block *s);
 int reiserfs_init_bitmap_cache(struct super_block *sb);
 void reiserfs_free_bitmap_cache(struct super_block *sb);
 void reiserfs_cache_bitmap_metadata(struct super_block *sb, struct buffer_head *bh, struct reiserfs_bitmap_info *info);
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index abf2b76c0d19..9fb20426005e 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -62,7 +62,6 @@ static int is_any_reiserfs_magic_string(struct reiserfs_super_block *rs)
 
 static int reiserfs_remount(struct super_block *s, int *flags, char *data);
 static int reiserfs_statfs(struct dentry *dentry, struct kstatfs *buf);
-void show_alloc_options(struct seq_file *seq, struct super_block *s);
 
 static int reiserfs_sync_fs(struct super_block *s, int wait)
 {
@@ -597,7 +596,7 @@ static void init_once(void *foo)
 	inode_init_once(&ei->vfs_inode);
 }
 
-static int init_inodecache(void)
+static int __init init_inodecache(void)
 {
 	reiserfs_inode_cachep = kmem_cache_create("reiser_inode_cache",
 						  sizeof(struct
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index 4742e58f3fc5..88956309cc86 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -296,7 +296,7 @@ int sysv_sync_inode(struct inode *inode)
 
 static void sysv_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	if (!inode->i_nlink) {
 		inode->i_size = 0;
 		sysv_truncate(inode);
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 123c79b7261e..4f34dbae823d 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1538,6 +1538,7 @@ out_unlock:
 
 static const struct vm_operations_struct ubifs_file_vm_ops = {
 	.fault        = filemap_fault,
+	.map_pages = filemap_map_pages,
 	.page_mkwrite = ubifs_vm_page_mkwrite,
 	.remap_pages = generic_file_remap_pages,
 };
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index e1598abd7475..a1266089eca1 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -351,7 +351,7 @@ static void ubifs_evict_inode(struct inode *inode)
 	dbg_gen("inode %lu, mode %#x", inode->i_ino, (int)inode->i_mode);
 	ubifs_assert(!atomic_read(&inode->i_count));
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	if (inode->i_nlink)
 		goto done;
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 982ce05c87ed..5d643706212f 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -146,8 +146,8 @@ void udf_evict_inode(struct inode *inode)
 		want_delete = 1;
 		udf_setsize(inode, 0);
 		udf_update_inode(inode, IS_SYNC(inode));
-	} else
-		truncate_inode_pages(&inode->i_data, 0);
+	}
+	truncate_inode_pages_final(&inode->i_data);
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
 	if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB &&
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index c8ca96086784..61e8a9b021dd 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -885,7 +885,7 @@ void ufs_evict_inode(struct inode * inode)
 	if (!inode->i_nlink && !is_bad_inode(inode))
 		want_delete = 1;
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	if (want_delete) {
 		loff_t old_i_size;
 		/*UFS_I(inode)->i_dtime = CURRENT_TIME;*/
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index f7abff8c16ca..003c0051b62f 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1483,6 +1483,7 @@ const struct file_operations xfs_dir_file_operations = {
 
 static const struct vm_operations_struct xfs_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= xfs_vm_page_mkwrite,
 	.remap_pages	= generic_file_remap_pages,
 };
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index ebd79be7d5f4..205376776377 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -996,7 +996,7 @@ xfs_fs_evict_inode(
 
 	trace_xfs_evict_inode(ip);
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	XFS_STATS_INC(vn_rele);
 	XFS_STATS_INC(vn_remove);
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 7d10f962aa13..630dd2372238 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -52,7 +52,7 @@ struct bug_entry {
 #endif
 
 #ifndef HAVE_ARCH_BUG_ON
-#define BUG_ON(condition) do { if (unlikely(condition)) BUG(); } while(0)
+#define BUG_ON(condition) do { if (unlikely(condition)) BUG(); } while (0)
 #endif
 
 /*
@@ -106,33 +106,6 @@ extern void warn_slowpath_null(const char *file, const int line);
 	unlikely(__ret_warn_on);					\
 })
 
-#else /* !CONFIG_BUG */
-#ifndef HAVE_ARCH_BUG
-#define BUG() do {} while(0)
-#endif
-
-#ifndef HAVE_ARCH_BUG_ON
-#define BUG_ON(condition) do { if (condition) ; } while(0)
-#endif
-
-#ifndef HAVE_ARCH_WARN_ON
-#define WARN_ON(condition) ({						\
-	int __ret_warn_on = !!(condition);				\
-	unlikely(__ret_warn_on);					\
-})
-#endif
-
-#ifndef WARN
-#define WARN(condition, format...) ({					\
-	int __ret_warn_on = !!(condition);				\
-	unlikely(__ret_warn_on);					\
-})
-#endif
-
-#define WARN_TAINT(condition, taint, format...) WARN_ON(condition)
-
-#endif
-
 #define WARN_ON_ONCE(condition)	({				\
 	static bool __section(.data.unlikely) __warned;		\
 	int __ret_warn_once = !!(condition);			\
@@ -163,6 +136,37 @@ extern void warn_slowpath_null(const char *file, const int line);
 	unlikely(__ret_warn_once);				\
 })
 
+#else /* !CONFIG_BUG */
+#ifndef HAVE_ARCH_BUG
+#define BUG() do {} while (1)
+#endif
+
+#ifndef HAVE_ARCH_BUG_ON
+#define BUG_ON(condition) do { if (condition) ; } while (0)
+#endif
+
+#ifndef HAVE_ARCH_WARN_ON
+#define WARN_ON(condition) ({						\
+	int __ret_warn_on = !!(condition);				\
+	unlikely(__ret_warn_on);					\
+})
+#endif
+
+#ifndef WARN
+#define WARN(condition, format...) ({					\
+	int __ret_warn_on = !!(condition);				\
+	no_printk(format);						\
+	unlikely(__ret_warn_on);					\
+})
+#endif
+
+#define WARN_ON_ONCE(condition) WARN_ON(condition)
+#define WARN_ONCE(condition, format...) WARN(condition, format)
+#define WARN_TAINT(condition, taint, format...) WARN(condition, format)
+#define WARN_TAINT_ONCE(condition, taint, format...) WARN(condition, format)
+
+#endif
+
 /*
  * WARN_ON_SMP() is for cases that the warning is either
  * meaningless for !SMP or may even cause failures.
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 24819001f5c8..e488e9459a93 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -95,7 +95,7 @@ struct backing_dev_info {
 	unsigned int max_ratio, max_prop_frac;
 
 	struct bdi_writeback wb;  /* default writeback info for this bdi */
-	spinlock_t wb_lock;	  /* protects work_list */
+	spinlock_t wb_lock;	  /* protects work_list & wb.dwork scheduling */
 
 	struct list_head work_list;
 
diff --git a/include/linux/backlight.h b/include/linux/backlight.h
index 5f9cd963213d..72647429adf6 100644
--- a/include/linux/backlight.h
+++ b/include/linux/backlight.h
@@ -9,6 +9,7 @@
 #define _LINUX_BACKLIGHT_H
 
 #include <linux/device.h>
+#include <linux/fb.h>
 #include <linux/mutex.h>
 #include <linux/notifier.h>
 
@@ -104,6 +105,11 @@ struct backlight_device {
 	struct list_head entry;
 
 	struct device dev;
+
+	/* Multiple framebuffers may share one backlight device */
+	bool fb_bl_on[FB_MAX];
+
+	int use_count;
 };
 
 static inline void backlight_update_status(struct backlight_device *bd)
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 3fe661fe96d1..b19d3dc2e651 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -87,25 +87,26 @@ extern void rebuild_sched_domains(void);
 extern void cpuset_print_task_mems_allowed(struct task_struct *p);
 
 /*
- * get_mems_allowed is required when making decisions involving mems_allowed
- * such as during page allocation. mems_allowed can be updated in parallel
- * and depending on the new value an operation can fail potentially causing
- * process failure. A retry loop with get_mems_allowed and put_mems_allowed
- * prevents these artificial failures.
+ * read_mems_allowed_begin is required when making decisions involving
+ * mems_allowed such as during page allocation. mems_allowed can be updated in
+ * parallel and depending on the new value an operation can fail potentially
+ * causing process failure. A retry loop with read_mems_allowed_begin and
+ * read_mems_allowed_retry prevents these artificial failures.
  */
-static inline unsigned int get_mems_allowed(void)
+static inline unsigned int read_mems_allowed_begin(void)
 {
 	return read_seqcount_begin(&current->mems_allowed_seq);
 }
 
 /*
- * If this returns false, the operation that took place after get_mems_allowed
- * may have failed. It is up to the caller to retry the operation if
+ * If this returns true, the operation that took place after
+ * read_mems_allowed_begin may have failed artificially due to a concurrent
+ * update of mems_allowed. It is up to the caller to retry the operation if
  * appropriate.
  */
-static inline bool put_mems_allowed(unsigned int seq)
+static inline bool read_mems_allowed_retry(unsigned int seq)
 {
-	return !read_seqcount_retry(&current->mems_allowed_seq, seq);
+	return read_seqcount_retry(&current->mems_allowed_seq, seq);
 }
 
 static inline void set_mems_allowed(nodemask_t nodemask)
@@ -225,14 +226,14 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 {
 }
 
-static inline unsigned int get_mems_allowed(void)
+static inline unsigned int read_mems_allowed_begin(void)
 {
 	return 0;
 }
 
-static inline bool put_mems_allowed(unsigned int seq)
+static inline bool read_mems_allowed_retry(unsigned int seq)
 {
-	return true;
+	return false;
 }
 
 #endif /* !CONFIG_CPUSETS */
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index 7032518f8542..72ab536ad3de 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -25,6 +25,7 @@ extern int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
 
 extern ssize_t copy_oldmem_page(unsigned long, char *, size_t,
 						unsigned long, int);
+void vmcore_cleanup(void);
 
 /* Architecture code defines this if there are other possible ELF
  * machine types, e.g. on bi-arch capable hardware. */
diff --git a/include/linux/crc64_ecma.h b/include/linux/crc64_ecma.h
new file mode 100644
index 000000000000..bba7a4d692b3
--- /dev/null
+++ b/include/linux/crc64_ecma.h
@@ -0,0 +1,56 @@
+/*
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __CRC64_ECMA_H_
+#define __CRC64_ECMA_H_
+
+#include <linux/types.h>
+
+
+#define CRC64_DEFAULT_INITVAL           0xFFFFFFFFFFFFFFFFULL
+
+
+/*
+ * crc64_ecma_seed - Initializes the CRC64 ECMA seed.
+ */
+u64 crc64_ecma_seed(void);
+
+/*
+ * crc64_ecma - Computes the 64 bit ECMA CRC.
+ *
+ * @pdata:	pointer to the data to compute checksum for.
+ * @nbytes:	number of bytes in data buffer.
+ * @seed:	CRC seed.
+ */
+u64 crc64_ecma(u8 const *pdata, u32 nbytes, u64 seed);
+
+#endif /* __CRC64_ECMA_H_ */
diff --git a/include/linux/cred.h b/include/linux/cred.h
index 04421e825365..f61d6c8f5ef3 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -66,7 +66,7 @@ extern struct group_info *groups_alloc(int);
 extern struct group_info init_groups;
 extern void groups_free(struct group_info *);
 extern int set_current_groups(struct group_info *);
-extern int set_groups(struct cred *, struct group_info *);
+extern void set_groups(struct cred *, struct group_info *);
 extern int groups_search(const struct group_info *, kgid_t);
 
 /* access the groups "array" with this macro */
diff --git a/include/linux/decompress/inflate.h b/include/linux/decompress/inflate.h
index 8c0aef1ba5f5..1d0aedef9822 100644
--- a/include/linux/decompress/inflate.h
+++ b/include/linux/decompress/inflate.h
@@ -1,5 +1,5 @@
-#ifndef INFLATE_H
-#define INFLATE_H
+#ifndef LINUX_DECOMPRESS_INFLATE_H
+#define LINUX_DECOMPRESS_INFLATE_H
 
 int gunzip(unsigned char *inbuf, int len,
 	   int(*fill)(void*, unsigned int),
diff --git a/include/linux/err.h b/include/linux/err.h
index 15f92e072450..a729120644d5 100644
--- a/include/linux/err.h
+++ b/include/linux/err.h
@@ -2,12 +2,13 @@
 #define _LINUX_ERR_H
 
 #include <linux/compiler.h>
+#include <linux/types.h>
 
 #include <asm/errno.h>
 
 /*
  * Kernel pointers have redundant information, so we can use a
- * scheme where we can return either an error code or a dentry
+ * scheme where we can return either an error code or a normal
  * pointer with the same return value.
  *
  * This should be a per-architecture thing, to allow different
@@ -29,12 +30,12 @@ static inline long __must_check PTR_ERR(__force const void *ptr)
 	return (long) ptr;
 }
 
-static inline long __must_check IS_ERR(__force const void *ptr)
+static inline bool __must_check IS_ERR(__force const void *ptr)
 {
 	return IS_ERR_VALUE((unsigned long)ptr);
 }
 
-static inline long __must_check IS_ERR_OR_NULL(__force const void *ptr)
+static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr)
 {
 	return !ptr || IS_ERR_VALUE((unsigned long)ptr);
 }
diff --git a/include/linux/fs.h b/include/linux/fs.h
index fe752ed108d3..cc56682f9ab2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -419,6 +419,7 @@ struct address_space {
 	struct mutex		i_mmap_mutex;	/* protect tree, count, list */
 	/* Protected by tree_lock together with the radix tree */
 	unsigned long		nrpages;	/* number of total pages */
+	unsigned long		nrshadows;	/* number of shadow entries */
 	pgoff_t			writeback_index;/* writeback starts here */
 	const struct address_space_operations *a_ops;	/* methods */
 	unsigned long		flags;		/* error bits/gfp mask */
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 64cf3ef50696..fc7718c6bd3e 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -178,7 +178,7 @@ struct fsnotify_group {
 		struct fanotify_group_private_data {
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 			/* allows a group to block waiting for a userspace response */
-			struct mutex access_mutex;
+			spinlock_t access_lock;
 			struct list_head access_list;
 			wait_queue_head_t access_waitq;
 			atomic_t bypass_perm;
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 8c43cc469d78..1ae16673c672 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -6,6 +6,8 @@
 #include <linux/fs.h>
 #include <linux/hugetlb_inline.h>
 #include <linux/cgroup.h>
+#include <linux/list.h>
+#include <linux/kref.h>
 
 struct ctl_table;
 struct user_struct;
@@ -23,6 +25,14 @@ struct hugepage_subpool {
 	long max_hpages, used_hpages;
 };
 
+struct resv_map {
+	struct kref refs;
+	spinlock_t lock;
+	struct list_head regions;
+};
+extern struct resv_map *resv_map_alloc(void);
+void resv_map_release(struct kref *ref);
+
 extern spinlock_t hugetlb_lock;
 extern int hugetlb_max_hstate __read_mostly;
 #define for_each_hstate(h) \
@@ -31,8 +41,6 @@ extern int hugetlb_max_hstate __read_mostly;
 struct hugepage_subpool *hugepage_new_subpool(long nr_blocks);
 void hugepage_put_subpool(struct hugepage_subpool *spool);
 
-int PageHuge(struct page *page);
-
 void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
 int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
 int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
@@ -99,11 +107,6 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 
 #else /* !CONFIG_HUGETLB_PAGE */
 
-static inline int PageHuge(struct page *page)
-{
-	return 0;
-}
-
 static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
 {
 }
diff --git a/include/linux/hugetlb_inline.h b/include/linux/hugetlb_inline.h
index 2bb681fbeb35..4d60c82e9fda 100644
--- a/include/linux/hugetlb_inline.h
+++ b/include/linux/hugetlb_inline.h
@@ -10,6 +10,8 @@ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
 	return !!(vma->vm_flags & VM_HUGETLB);
 }
 
+int PageHuge(struct page *page);
+
 #else
 
 static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
@@ -17,6 +19,11 @@ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
 	return 0;
 }
 
+static inline int PageHuge(struct page *page)
+{
+	return 0;
+}
+
 #endif
 
 #endif
diff --git a/include/linux/idr.h b/include/linux/idr.h
index f669585c4fc5..6af3400b9b2f 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -133,69 +133,6 @@ static inline void *idr_find(struct idr *idr, int id)
 	for (id = 0; ((entry) = idr_get_next(idp, &(id))) != NULL; ++id)
 
 /*
- * Don't use the following functions.  These exist only to suppress
- * deprecated warnings on EXPORT_SYMBOL()s.
- */
-int __idr_pre_get(struct idr *idp, gfp_t gfp_mask);
-int __idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id);
-void __idr_remove_all(struct idr *idp);
-
-/**
- * idr_pre_get - reserve resources for idr allocation
- * @idp:	idr handle
- * @gfp_mask:	memory allocation flags
- *
- * Part of old alloc interface.  This is going away.  Use
- * idr_preload[_end]() and idr_alloc() instead.
- */
-static inline int __deprecated idr_pre_get(struct idr *idp, gfp_t gfp_mask)
-{
-	return __idr_pre_get(idp, gfp_mask);
-}
-
-/**
- * idr_get_new_above - allocate new idr entry above or equal to a start id
- * @idp: idr handle
- * @ptr: pointer you want associated with the id
- * @starting_id: id to start search at
- * @id: pointer to the allocated handle
- *
- * Part of old alloc interface.  This is going away.  Use
- * idr_preload[_end]() and idr_alloc() instead.
- */
-static inline int __deprecated idr_get_new_above(struct idr *idp, void *ptr,
-						 int starting_id, int *id)
-{
-	return __idr_get_new_above(idp, ptr, starting_id, id);
-}
-
-/**
- * idr_get_new - allocate new idr entry
- * @idp: idr handle
- * @ptr: pointer you want associated with the id
- * @id: pointer to the allocated handle
- *
- * Part of old alloc interface.  This is going away.  Use
- * idr_preload[_end]() and idr_alloc() instead.
- */
-static inline int __deprecated idr_get_new(struct idr *idp, void *ptr, int *id)
-{
-	return __idr_get_new_above(idp, ptr, 0, id);
-}
-
-/**
- * idr_remove_all - remove all ids from the given idr tree
- * @idp: idr handle
- *
- * If you're trying to destroy @idp, calling idr_destroy() is enough.
- * This is going away.  Don't use.
- */
-static inline void __deprecated idr_remove_all(struct idr *idp)
-{
-	__idr_remove_all(idp);
-}
-
-/*
  * IDA - IDR based id allocator, use when translation from id to
  * pointer isn't necessary.
  *
diff --git a/include/linux/input.h b/include/linux/input.h
index 82ce323b9986..6453b22372ac 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -79,6 +79,7 @@ struct input_value {
  * @led: reflects current state of device's LEDs
  * @snd: reflects current state of sound effects
  * @sw: reflects current state of device's switches
+ * @leds: leds objects for the device's LEDs
  * @open: this method is called when the very first user calls
  *	input_open_device(). The driver must prepare the device
  *	to start generating events (start polling thread,
@@ -164,6 +165,8 @@ struct input_dev {
 	unsigned long snd[BITS_TO_LONGS(SND_CNT)];
 	unsigned long sw[BITS_TO_LONGS(SW_CNT)];
 
+	struct led_classdev *leds;
+
 	int (*open)(struct input_dev *dev);
 	void (*close)(struct input_dev *dev);
 	int (*flush)(struct input_dev *dev, struct file *file);
@@ -531,4 +534,22 @@ int input_ff_erase(struct input_dev *dev, int effect_id, struct file *file);
 int input_ff_create_memless(struct input_dev *dev, void *data,
 		int (*play_effect)(struct input_dev *, void *, struct ff_effect *));
 
+#ifdef CONFIG_INPUT_LEDS
+
+int input_led_connect(struct input_dev *dev);
+void input_led_disconnect(struct input_dev *dev);
+
+#else
+
+static inline int input_led_connect(struct input_dev *dev)
+{
+	return 0;
+}
+
+static inline void input_led_disconnect(struct input_dev *dev)
+{
+}
+
+#endif
+
 #endif
diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h
index 2a5e5548a1d2..5bb424659c04 100644
--- a/include/linux/kmemleak.h
+++ b/include/linux/kmemleak.h
@@ -30,8 +30,6 @@ extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size) __ref;
 extern void kmemleak_free(const void *ptr) __ref;
 extern void kmemleak_free_part(const void *ptr, size_t size) __ref;
 extern void kmemleak_free_percpu(const void __percpu *ptr) __ref;
-extern void kmemleak_padding(const void *ptr, unsigned long offset,
-			     size_t size) __ref;
 extern void kmemleak_not_leak(const void *ptr) __ref;
 extern void kmemleak_ignore(const void *ptr) __ref;
 extern void kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) __ref;
diff --git a/include/linux/kobject.h b/include/linux/kobject.h
index 926afb6f6b5f..f896a33e8341 100644
--- a/include/linux/kobject.h
+++ b/include/linux/kobject.h
@@ -119,6 +119,7 @@ struct kobj_type {
 };
 
 struct kobj_uevent_env {
+	char *argv[3];
 	char *envp[UEVENT_NUM_ENVP];
 	int envp_idx;
 	char buf[UEVENT_BUFFER_SIZE];
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index 7dcef3317689..50050ae17b00 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -51,6 +51,7 @@ void kthread_parkme(void);
 int kthreadd(void *unused);
 extern struct task_struct *kthreadd_task;
 extern int tsk_fork_get_node(struct task_struct *tsk);
+void set_kthreadd_affinity(void);
 
 /*
  * Simple work processor based on kthread.
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 3ce541753c88..f3434533fbf8 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -13,6 +13,8 @@
 /* list_lru_walk_cb has to always return one of those */
 enum lru_status {
 	LRU_REMOVED,		/* item removed from list */
+	LRU_REMOVED_RETRY,	/* item removed, but lock has been
+				   dropped and reacquired */
 	LRU_ROTATE,		/* item referenced, give another pass */
 	LRU_SKIP,		/* item cannot be locked, skip */
 	LRU_RETRY,		/* item not freeable. May drop the lock
@@ -32,7 +34,11 @@ struct list_lru {
 };
 
 void list_lru_destroy(struct list_lru *lru);
-int list_lru_init(struct list_lru *lru);
+int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key);
+static inline int list_lru_init(struct list_lru *lru)
+{
+	return list_lru_init_key(lru, NULL);
+}
 
 /**
  * list_lru_add: add an element to the lru list's tail
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index eccfb4a4b379..c58736481e79 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -65,7 +65,7 @@ struct mem_cgroup_reclaim_cookie {
  * (Of course, if memcg does memory allocation in future, GFP_KERNEL is sane.)
  */
 
-extern int mem_cgroup_newpage_charge(struct page *page, struct mm_struct *mm,
+extern int mem_cgroup_charge_anon(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask);
 /* for swap handling */
 extern int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
@@ -74,7 +74,7 @@ extern void mem_cgroup_commit_charge_swapin(struct page *page,
 					struct mem_cgroup *memcg);
 extern void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg);
 
-extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
+extern int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm,
 					gfp_t gfp_mask);
 
 struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
@@ -234,13 +234,13 @@ void mem_cgroup_print_bad_page(struct page *page);
 #else /* CONFIG_MEMCG */
 struct mem_cgroup;
 
-static inline int mem_cgroup_newpage_charge(struct page *page,
+static inline int mem_cgroup_charge_anon(struct page *page,
 					struct mm_struct *mm, gfp_t gfp_mask)
 {
 	return 0;
 }
 
-static inline int mem_cgroup_cache_charge(struct page *page,
+static inline int mem_cgroup_charge_file(struct page *page,
 					struct mm_struct *mm, gfp_t gfp_mask)
 {
 	return 0;
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 5f1ea756aace..3c1b968da0ca 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -143,7 +143,6 @@ extern void numa_policy_init(void);
 extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new,
 				enum mpol_rebind_step step);
 extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new);
-extern void mpol_fix_fork_child_flag(struct task_struct *p);
 
 extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
 				unsigned long addr, gfp_t gfp_flags,
@@ -151,7 +150,7 @@ extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
 extern bool init_nodemask_of_mempolicy(nodemask_t *mask);
 extern bool mempolicy_nodemask_intersects(struct task_struct *tsk,
 				const nodemask_t *mask);
-extern unsigned slab_node(void);
+extern unsigned int mempolicy_slab_node(void);
 
 extern enum zone_type policy_zone;
 
diff --git a/include/linux/mfd/pm8xxx/rtc.h b/include/linux/mfd/pm8xxx/rtc.h
deleted file mode 100644
index 14f1983eaecc..000000000000
--- a/include/linux/mfd/pm8xxx/rtc.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/* Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#ifndef __RTC_PM8XXX_H__
-#define __RTC_PM8XXX_H__
-
-#define PM8XXX_RTC_DEV_NAME     "rtc-pm8xxx"
-/**
- * struct pm8xxx_rtc_pdata - RTC driver platform data
- * @rtc_write_enable: variable stating RTC write capability
- */
-struct pm8xxx_rtc_platform_data {
-	bool rtc_write_enable;
-};
-
-#endif /* __RTC_PM8XXX_H__ */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1279d1fb6028..0bd43595ef98 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -177,6 +177,9 @@ extern unsigned int kobjsize(const void *objp);
  */
 #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)
 
+/* This mask defines which mm->def_flags a process can inherit its parent */
+#define VM_INIT_DEF_MASK	VM_NOHUGEPAGE
+
 /*
  * mapping from the currently active vm_flags protection bits (the
  * low four bits) to a page protection mask..
@@ -210,6 +213,10 @@ struct vm_fault {
 					 * is set (which is also implied by
 					 * VM_FAULT_ERROR).
 					 */
+	/* for ->map_pages() only */
+	pgoff_t max_pgoff;		/* map pages for offset from pgoff till
+					 * max_pgoff inclusive */
+	pte_t *pte;			/* pte entry associated with ->pgoff */
 };
 
 /*
@@ -221,6 +228,7 @@ struct vm_operations_struct {
 	void (*open)(struct vm_area_struct * area);
 	void (*close)(struct vm_area_struct * area);
 	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
+	void (*map_pages)(struct vm_area_struct *vma, struct vm_fault *vmf);
 
 	/* notification that a previously read-only page is about to become
 	 * writable, if an error is returned it will cause a SIGBUS */
@@ -581,6 +589,9 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 		pte = pte_mkwrite(pte);
 	return pte;
 }
+
+void do_set_pte(struct vm_area_struct *vma, unsigned long address,
+		struct page *page, pte_t *pte, bool write, bool anon);
 #endif
 
 /*
@@ -1041,6 +1052,14 @@ extern void show_free_areas(unsigned int flags);
 extern bool skip_free_areas_node(unsigned int flags, int nid);
 
 int shmem_zero_setup(struct vm_area_struct *);
+#ifdef CONFIG_SHMEM
+bool shmem_mapping(struct address_space *mapping);
+#else
+static inline bool shmem_mapping(struct address_space *mapping)
+{
+	return false;
+}
+#endif
 
 extern int can_do_mlock(void);
 extern int user_shm_lock(size_t, struct user_struct *);
@@ -1077,10 +1096,18 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
  * @pte_entry: if set, called for each non-empty PTE (4th-level) entry
  * @pte_hole: if set, called for each hole at all levels
  * @hugetlb_entry: if set, called for each hugetlb entry
- *		   *Caution*: The caller must hold mmap_sem() if @hugetlb_entry
- * 			      is used.
+ * @test_walk: caller specific callback function to determine whether
+ *             we walk over the current vma or not. A positive returned
+ *             value means "do page table walk over the current vma,"
+ *             and a negative one means "abort current page table walk
+ *             right now." 0 means "skip the current vma."
+ * @mm:        mm_struct representing the target process of page table walk
+ * @vma:       vma currently walked
+ * @skip:      internal control flag which is set when we skip the lower
+ *             level entries.
+ * @private:   private data for callbacks' use
  *
- * (see walk_page_range for more details)
+ * (see the comment on walk_page_range() for more details)
  */
 struct mm_walk {
 	int (*pgd_entry)(pgd_t *pgd, unsigned long addr,
@@ -1093,15 +1120,19 @@ struct mm_walk {
 			 unsigned long next, struct mm_walk *walk);
 	int (*pte_hole)(unsigned long addr, unsigned long next,
 			struct mm_walk *walk);
-	int (*hugetlb_entry)(pte_t *pte, unsigned long hmask,
-			     unsigned long addr, unsigned long next,
-			     struct mm_walk *walk);
+	int (*hugetlb_entry)(pte_t *pte, unsigned long addr,
+			unsigned long next, struct mm_walk *walk);
+	int (*test_walk)(unsigned long addr, unsigned long next,
+			struct mm_walk *walk);
 	struct mm_struct *mm;
+	struct vm_area_struct *vma;
+	int skip;
 	void *private;
 };
 
 int walk_page_range(unsigned long addr, unsigned long end,
 		struct mm_walk *walk);
+int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk);
 void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 		unsigned long end, unsigned long floor, unsigned long ceiling);
 int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
@@ -1659,10 +1690,8 @@ static inline int __early_pfn_to_nid(unsigned long pfn)
 #else
 /* please see mm/page_alloc.c */
 extern int __meminit early_pfn_to_nid(unsigned long pfn);
-#ifdef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
 /* there is a per-arch backend function. */
 extern int __meminit __early_pfn_to_nid(unsigned long pfn);
-#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
 #endif
 
 extern void set_dma_reserve(unsigned long new_dma_reserve);
@@ -1827,9 +1856,11 @@ vm_unmapped_area(struct vm_unmapped_area_info *info)
 extern void truncate_inode_pages(struct address_space *, loff_t);
 extern void truncate_inode_pages_range(struct address_space *,
 				       loff_t lstart, loff_t lend);
+extern void truncate_inode_pages_final(struct address_space *);
 
 /* generic vm_area_ops exported for stackable file systems */
 extern int filemap_fault(struct vm_area_struct *, struct vm_fault *);
+extern void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf);
 extern int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
 
 /* mm/page-writeback.c */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 290901a8c1de..8967e20cbe57 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -124,6 +124,8 @@ struct page {
 	union {
 		struct list_head lru;	/* Pageout list, eg. active_list
 					 * protected by zone->lru_lock !
+					 * Can be used as a generic list
+					 * by the page owner.
 					 */
 		struct {		/* slub per cpu partial pages */
 			struct page *next;	/* Next partial slab */
@@ -136,7 +138,6 @@ struct page {
 #endif
 		};
 
-		struct list_head list;	/* slobs list of pages */
 		struct slab *slab_page; /* slab fields */
 		struct rcu_head rcu_head;	/* Used by SLAB
 						 * when destroying via RCU
@@ -342,9 +343,9 @@ struct mm_rss_stat {
 
 struct kioctx_table;
 struct mm_struct {
-	struct vm_area_struct * mmap;		/* list of VMAs */
+	struct vm_area_struct *mmap;		/* list of VMAs */
 	struct rb_root mm_rb;
-	struct vm_area_struct * mmap_cache;	/* last find_vma result */
+	u32 vmacache_seqnum;                   /* per-thread vmacache */
 #ifdef CONFIG_MMU
 	unsigned long (*get_unmapped_area) (struct file *filp,
 				unsigned long addr, unsigned long len,
diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index 5042c036dda9..2d57efa64cc1 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -3,8 +3,8 @@
 
 struct page;
 
-extern void dump_page(struct page *page, char *reason);
-extern void dump_page_badflags(struct page *page, char *reason,
+extern void dump_page(struct page *page, const char *reason);
+extern void dump_page_badflags(struct page *page, const char *reason,
 			       unsigned long badflags);
 
 #ifdef CONFIG_DEBUG_VM
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 9b61b9bf81ac..fac5509c18f0 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -142,6 +142,9 @@ enum zone_stat_item {
 	NUMA_LOCAL,		/* allocation from local node */
 	NUMA_OTHER,		/* allocation from other node */
 #endif
+	WORKINGSET_REFAULT,
+	WORKINGSET_ACTIVATE,
+	WORKINGSET_NODERECLAIM,
 	NR_ANON_TRANSPARENT_HUGEPAGES,
 	NR_FREE_CMA_PAGES,
 	NR_VM_ZONE_STAT_ITEMS };
@@ -392,6 +395,9 @@ struct zone {
 	spinlock_t		lru_lock;
 	struct lruvec		lruvec;
 
+	/* Evictions & activations on the inactive file list */
+	atomic_long_t		inactive_age;
+
 	unsigned long		pages_scanned;	   /* since last reclaim */
 	unsigned long		flags;		   /* zone flags, see below */
 
diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h
index 98755767c7b0..ff3fea3194c6 100644
--- a/include/linux/nilfs2_fs.h
+++ b/include/linux/nilfs2_fs.h
@@ -82,6 +82,8 @@ struct nilfs_inode {
 	__le32	i_pad;
 };
 
+#define NILFS_MIN_INODE_SIZE		128
+
 /**
  * struct nilfs_super_root - structure of super root
  * @sr_sum: check sum
@@ -482,6 +484,8 @@ struct nilfs_dat_entry {
 	__le64 de_rsv;
 };
 
+#define NILFS_MIN_DAT_ENTRY_SIZE	32
+
 /**
  * struct nilfs_snapshot_list - snapshot list
  * @ssl_next: next checkpoint number on snapshot list
@@ -520,6 +524,8 @@ struct nilfs_checkpoint {
 	struct nilfs_inode cp_ifile_inode;
 };
 
+#define NILFS_MIN_CHECKPOINT_SIZE	(64 + NILFS_MIN_INODE_SIZE)
+
 /* checkpoint flags */
 enum {
 	NILFS_CHECKPOINT_SNAPSHOT,
@@ -615,6 +621,8 @@ struct nilfs_segment_usage {
 	__le32 su_flags;
 };
 
+#define NILFS_MIN_SEGMENT_USAGE_SIZE	16
+
 /* segment usage flag */
 enum {
 	NILFS_SEGMENT_USAGE_ACTIVE,
@@ -710,6 +718,48 @@ static inline int nilfs_suinfo_clean(const struct nilfs_suinfo *si)
 }
 
 /* ioctl */
+/**
+ * nilfs_suinfo_update - segment usage information update
+ * @sup_segnum: segment number
+ * @sup_flags: flags for which fields are active in sup_sui
+ * @sup_reserved: reserved necessary for alignment
+ * @sup_sui: segment usage information
+ */
+struct nilfs_suinfo_update {
+	__u64 sup_segnum;
+	__u32 sup_flags;
+	__u32 sup_reserved;
+	struct nilfs_suinfo sup_sui;
+};
+
+enum {
+	NILFS_SUINFO_UPDATE_LASTMOD,
+	NILFS_SUINFO_UPDATE_NBLOCKS,
+	NILFS_SUINFO_UPDATE_FLAGS,
+	__NR_NILFS_SUINFO_UPDATE_FIELDS,
+};
+
+#define NILFS_SUINFO_UPDATE_FNS(flag, name)				\
+static inline void							\
+nilfs_suinfo_update_set_##name(struct nilfs_suinfo_update *sup)		\
+{									\
+	sup->sup_flags |= 1UL << NILFS_SUINFO_UPDATE_##flag;		\
+}									\
+static inline void							\
+nilfs_suinfo_update_clear_##name(struct nilfs_suinfo_update *sup)	\
+{									\
+	sup->sup_flags &= ~(1UL << NILFS_SUINFO_UPDATE_##flag);		\
+}									\
+static inline int							\
+nilfs_suinfo_update_##name(const struct nilfs_suinfo_update *sup)	\
+{									\
+	return !!(sup->sup_flags & (1UL << NILFS_SUINFO_UPDATE_##flag));\
+}
+
+NILFS_SUINFO_UPDATE_FNS(LASTMOD, lastmod)
+NILFS_SUINFO_UPDATE_FNS(NBLOCKS, nblocks)
+NILFS_SUINFO_UPDATE_FNS(FLAGS, flags)
+
 enum {
 	NILFS_CHECKPOINT,
 	NILFS_SNAPSHOT,
@@ -863,5 +913,7 @@ struct nilfs_bdesc {
 	_IOW(NILFS_IOCTL_IDENT, 0x8B, __u64)
 #define NILFS_IOCTL_SET_ALLOC_RANGE  \
 	_IOW(NILFS_IOCTL_IDENT, 0x8C, __u64[2])
+#define NILFS_IOCTL_SET_SUINFO  \
+	_IOW(NILFS_IOCTL_IDENT, 0x8D, struct nilfs_argv)
 
 #endif	/* _LINUX_NILFS_FS_H */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 1710d1b060ba..d4acafc51949 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -25,6 +25,7 @@ enum mapping_flags {
 	AS_MM_ALL_LOCKS	= __GFP_BITS_SHIFT + 2,	/* under mm_take_all_locks() */
 	AS_UNEVICTABLE	= __GFP_BITS_SHIFT + 3,	/* e.g., ramdisk, SHM_LOCK */
 	AS_BALLOON_MAP  = __GFP_BITS_SHIFT + 4, /* balloon page special map */
+	AS_EXITING	= __GFP_BITS_SHIFT + 5, /* final truncate in progress */
 };
 
 static inline void mapping_set_error(struct address_space *mapping, int error)
@@ -69,6 +70,16 @@ static inline int mapping_balloon(struct address_space *mapping)
 	return mapping && test_bit(AS_BALLOON_MAP, &mapping->flags);
 }
 
+static inline void mapping_set_exiting(struct address_space *mapping)
+{
+	set_bit(AS_EXITING, &mapping->flags);
+}
+
+static inline int mapping_exiting(struct address_space *mapping)
+{
+	return test_bit(AS_EXITING, &mapping->flags);
+}
+
 static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
 {
 	return (__force gfp_t)mapping->flags & __GFP_BITS_MASK;
@@ -243,12 +254,20 @@ static inline struct page *page_cache_alloc_readahead(struct address_space *x)
 
 typedef int filler_t(void *, struct page *);
 
-extern struct page * find_get_page(struct address_space *mapping,
-				pgoff_t index);
-extern struct page * find_lock_page(struct address_space *mapping,
-				pgoff_t index);
-extern struct page * find_or_create_page(struct address_space *mapping,
-				pgoff_t index, gfp_t gfp_mask);
+pgoff_t page_cache_next_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan);
+pgoff_t page_cache_prev_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan);
+
+struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
+struct page *find_get_page(struct address_space *mapping, pgoff_t offset);
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset);
+struct page *find_lock_page(struct address_space *mapping, pgoff_t offset);
+struct page *find_or_create_page(struct address_space *mapping, pgoff_t index,
+				 gfp_t gfp_mask);
+unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
+			  unsigned int nr_entries, struct page **entries,
+			  pgoff_t *indices);
 unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
 			unsigned int nr_pages, struct page **pages);
 unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start,
@@ -270,8 +289,6 @@ static inline struct page *grab_cache_page(struct address_space *mapping,
 
 extern struct page * grab_cache_page_nowait(struct address_space *mapping,
 				pgoff_t index);
-extern struct page * read_cache_page_async(struct address_space *mapping,
-				pgoff_t index, filler_t *filler, void *data);
 extern struct page * read_cache_page(struct address_space *mapping,
 				pgoff_t index, filler_t *filler, void *data);
 extern struct page * read_cache_page_gfp(struct address_space *mapping,
@@ -279,14 +296,6 @@ extern struct page * read_cache_page_gfp(struct address_space *mapping,
 extern int read_cache_pages(struct address_space *mapping,
 		struct list_head *pages, filler_t *filler, void *data);
 
-static inline struct page *read_mapping_page_async(
-				struct address_space *mapping,
-				pgoff_t index, void *data)
-{
-	filler_t *filler = (filler_t *)mapping->a_ops->readpage;
-	return read_cache_page_async(mapping, index, filler, data);
-}
-
 static inline struct page *read_mapping_page(struct address_space *mapping,
 				pgoff_t index, void *data)
 {
@@ -307,6 +316,34 @@ static inline loff_t page_file_offset(struct page *page)
 	return ((loff_t)page_file_index(page)) << PAGE_CACHE_SHIFT;
 }
 
+/*
+ * Get the order of a given page in the context of the pagecache which it
+ * belongs to.
+ *
+ * Pagecache unit size is not a fixed value (hugetlbfs is an example), but the
+ * vma_interval_tree and anon_vma_interval_tree APIs assume that indices are in
+ * PAGE_SIZE units.  So this function helps us to get normalized indices.
+ *
+ * page_size_order() should be called only for pagecache pages/hugepages and
+ * anonymous pages/hugepages, because pagecache unit size is irrelevant except
+ * for those pages.
+ */
+static inline unsigned int page_size_order(struct page *page)
+{
+	return unlikely(PageHuge(page)) ?
+		compound_order(compound_head(page)) :
+		(PAGE_CACHE_SHIFT - PAGE_SHIFT);
+}
+
+/*
+ * page->index stores pagecache index whose unit is not always PAGE_SIZE.
+ * This function converts it into PAGE_SIZE offset.
+ */
+static inline pgoff_t page_pgoff(struct page *page)
+{
+	return page->index << page_size_order(page);
+}
+
 extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
 				     unsigned long address);
 
@@ -539,7 +576,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 				pgoff_t index, gfp_t gfp_mask);
 extern void delete_from_page_cache(struct page *page);
-extern void __delete_from_page_cache(struct page *page);
+extern void __delete_from_page_cache(struct page *page, void *shadow);
 int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
 
 /*
diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index e4dbfab37729..b45d391b4540 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -22,6 +22,11 @@ struct pagevec {
 
 void __pagevec_release(struct pagevec *pvec);
 void __pagevec_lru_add(struct pagevec *pvec);
+unsigned pagevec_lookup_entries(struct pagevec *pvec,
+				struct address_space *mapping,
+				pgoff_t start, unsigned nr_entries,
+				pgoff_t *indices);
+void pagevec_remove_exceptionals(struct pagevec *pvec);
 unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping,
 		pgoff_t start, unsigned nr_pages);
 unsigned pagevec_lookup_tag(struct pagevec *pvec,
diff --git a/include/linux/printk.h b/include/linux/printk.h
index fa47e2708c01..8752f7595b27 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -24,13 +24,9 @@ static inline int printk_get_level(const char *buffer)
 
 static inline const char *printk_skip_level(const char *buffer)
 {
-	if (printk_get_level(buffer)) {
-		switch (buffer[1]) {
-		case '0' ... '7':
-		case 'd':	/* KERN_DEFAULT */
-			return buffer + 2;
-		}
-	}
+	if (printk_get_level(buffer))
+		return buffer + 2;
+
 	return buffer;
 }
 
@@ -124,9 +120,9 @@ asmlinkage __printf(1, 0)
 int vprintk(const char *fmt, va_list args);
 
 asmlinkage __printf(5, 6) __cold
-asmlinkage int printk_emit(int facility, int level,
-			   const char *dict, size_t dictlen,
-			   const char *fmt, ...);
+int printk_emit(int facility, int level,
+		const char *dict, size_t dictlen,
+		const char *fmt, ...);
 
 asmlinkage __printf(1, 2) __cold
 int printk(const char *fmt, ...);
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 6965fe394c3b..1d3eee594cd6 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -46,6 +46,14 @@ void inode_reclaim_rsv_space(struct inode *inode, qsize_t number);
 void dquot_initialize(struct inode *inode);
 void dquot_drop(struct inode *inode);
 struct dquot *dqget(struct super_block *sb, struct kqid qid);
+static inline struct dquot *dqgrab(struct dquot *dquot)
+{
+	/* Make sure someone else has active reference to dquot */
+	WARN_ON_ONCE(!atomic_read(&dquot->dq_count));
+	WARN_ON_ONCE(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags));
+	atomic_inc(&dquot->dq_count);
+	return dquot;
+}
 void dqput(struct dquot *dquot);
 int dquot_scan_active(struct super_block *sb,
 		      int (*fn)(struct dquot *dquot, unsigned long priv),
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 403940787be1..33170dbd9db4 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -60,6 +60,49 @@ static inline int radix_tree_is_indirect_ptr(void *ptr)
 
 #define RADIX_TREE_MAX_TAGS 3
 
+#ifdef __KERNEL__
+#define RADIX_TREE_MAP_SHIFT	(CONFIG_BASE_SMALL ? 4 : 6)
+#else
+#define RADIX_TREE_MAP_SHIFT	3	/* For more stressful testing */
+#endif
+
+#define RADIX_TREE_MAP_SIZE	(1UL << RADIX_TREE_MAP_SHIFT)
+#define RADIX_TREE_MAP_MASK	(RADIX_TREE_MAP_SIZE-1)
+
+#define RADIX_TREE_TAG_LONGS	\
+	((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG)
+
+#define RADIX_TREE_INDEX_BITS  (8 /* CHAR_BIT */ * sizeof(unsigned long))
+#define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \
+					  RADIX_TREE_MAP_SHIFT))
+
+/* Height component in node->path */
+#define RADIX_TREE_HEIGHT_SHIFT	(RADIX_TREE_MAX_PATH + 1)
+#define RADIX_TREE_HEIGHT_MASK	((1UL << RADIX_TREE_HEIGHT_SHIFT) - 1)
+
+/* Internally used bits of node->count */
+#define RADIX_TREE_COUNT_SHIFT	(RADIX_TREE_MAP_SHIFT + 1)
+#define RADIX_TREE_COUNT_MASK	((1UL << RADIX_TREE_COUNT_SHIFT) - 1)
+
+struct radix_tree_node {
+	unsigned int	path;	/* Offset in parent & height from the bottom */
+	unsigned int	count;
+	union {
+		struct {
+			/* Used when ascending tree */
+			struct radix_tree_node *parent;
+			/* For tree user */
+			void *private_data;
+		};
+		/* Used when freeing node */
+		struct rcu_head	rcu_head;
+	};
+	/* For tree user */
+	struct list_head private_list;
+	void __rcu	*slots[RADIX_TREE_MAP_SIZE];
+	unsigned long	tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
+};
+
 /* root tags are stored in gfp_mask, shifted by __GFP_BITS_SHIFT */
 struct radix_tree_root {
 	unsigned int		height;
@@ -101,6 +144,7 @@ do {									\
  *   concurrently with other readers.
  *
  * The notable exceptions to this rule are the following functions:
+ * __radix_tree_lookup
  * radix_tree_lookup
  * radix_tree_lookup_slot
  * radix_tree_tag_get
@@ -216,9 +260,16 @@ static inline void radix_tree_replace_slot(void **pslot, void *item)
 	rcu_assign_pointer(*pslot, item);
 }
 
+int __radix_tree_create(struct radix_tree_root *root, unsigned long index,
+			struct radix_tree_node **nodep, void ***slotp);
 int radix_tree_insert(struct radix_tree_root *, unsigned long, void *);
+void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index,
+			  struct radix_tree_node **nodep, void ***slotp);
 void *radix_tree_lookup(struct radix_tree_root *, unsigned long);
 void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long);
+bool __radix_tree_delete_node(struct radix_tree_root *root,
+			      struct radix_tree_node *node);
+void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);
 void *radix_tree_delete(struct radix_tree_root *, unsigned long);
 unsigned int
 radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
@@ -226,10 +277,6 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root,
 			void ***results, unsigned long *indices,
 			unsigned long first_index, unsigned int max_items);
-unsigned long radix_tree_next_hole(struct radix_tree_root *root,
-				unsigned long index, unsigned long max_scan);
-unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
-				unsigned long index, unsigned long max_scan);
 int radix_tree_preload(gfp_t gfp_mask);
 int radix_tree_maybe_preload(gfp_t gfp_mask);
 void radix_tree_init(void);
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
index 201a69749659..56b7bc32db4f 100644
--- a/include/linux/res_counter.h
+++ b/include/linux/res_counter.h
@@ -104,15 +104,13 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent);
  *       units, e.g. numbers, bytes, Kbytes, etc
  *
  * returns 0 on success and <0 if the counter->usage will exceed the
- * counter->limit _locked call expects the counter->lock to be taken
+ * counter->limit
  *
  * charge_nofail works the same, except that it charges the resource
  * counter unconditionally, and returns < 0 if the after the current
  * charge we are over limit.
  */
 
-int __must_check res_counter_charge_locked(struct res_counter *counter,
-					   unsigned long val, bool force);
 int __must_check res_counter_charge(struct res_counter *counter,
 		unsigned long val, struct res_counter **limit_fail_at);
 int res_counter_charge_nofail(struct res_counter *counter,
@@ -125,12 +123,10 @@ int res_counter_charge_nofail(struct res_counter *counter,
  * @val: the amount of the resource
  *
  * these calls check for usage underflow and show a warning on the console
- * _locked call expects the counter->lock to be taken
  *
  * returns the total charges still present in @counter.
  */
 
-u64 res_counter_uncharge_locked(struct res_counter *counter, unsigned long val);
 u64 res_counter_uncharge(struct res_counter *counter, unsigned long val);
 
 u64 res_counter_uncharge_until(struct res_counter *counter,
diff --git a/include/linux/rio.h b/include/linux/rio.h
index b71d5738e683..6bda06f21930 100644
--- a/include/linux/rio.h
+++ b/include/linux/rio.h
@@ -83,7 +83,7 @@
 #define RIO_CTAG_UDEVID	0x0001ffff /* Unique device identifier */
 
 extern struct bus_type rio_bus_type;
-extern struct device rio_bus;
+extern struct class rio_mport_class;
 
 struct rio_mport;
 struct rio_dev;
@@ -201,6 +201,7 @@ struct rio_dev {
 #define rio_dev_f(n) list_entry(n, struct rio_dev, net_list)
 #define	to_rio_dev(n) container_of(n, struct rio_dev, dev)
 #define sw_to_rio_dev(n) container_of(n, struct rio_dev, rswitch[0])
+#define	to_rio_mport(n) container_of(n, struct rio_mport, dev)
 
 /**
  * struct rio_msg - RIO message event
@@ -248,6 +249,7 @@ enum rio_phy_type {
  * @phy_type: RapidIO phy type
  * @phys_efptr: RIO port extended features pointer
  * @name: Port name string
+ * @dev: device structure associated with an mport
  * @priv: Master port private data
  * @dma: DMA device associated with mport
  * @nscan: RapidIO network enumeration/discovery operations
@@ -272,6 +274,7 @@ struct rio_mport {
 	enum rio_phy_type phy_type;	/* RapidIO phy type */
 	u32 phys_efptr;
 	unsigned char name[RIO_MAX_MPORT_NAME];
+	struct device dev;
 	void *priv;		/* Master port private data */
 #ifdef CONFIG_RAPIDIO_DMA_ENGINE
 	struct dma_device	dma;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 984b55e6783e..859ddabcc74e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -132,6 +132,10 @@ struct perf_event_context;
 struct blk_plug;
 struct filename;
 
+#define VMACACHE_BITS 2
+#define VMACACHE_SIZE (1U << VMACACHE_BITS)
+#define VMACACHE_MASK (VMACACHE_SIZE - 1)
+
 /*
  * List of flags we want to share for kernel threads,
  * if only because they are not used by them anyway.
@@ -206,8 +210,9 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
 #define __TASK_STOPPED		4
 #define __TASK_TRACED		8
 /* in tsk->exit_state */
-#define EXIT_ZOMBIE		16
-#define EXIT_DEAD		32
+#define EXIT_DEAD		16
+#define EXIT_ZOMBIE		32
+#define EXIT_TRACE		(EXIT_ZOMBIE | EXIT_DEAD)
 /* in tsk->state again */
 #define TASK_DEAD		64
 #define TASK_WAKEKILL		128
@@ -1235,6 +1240,9 @@ struct task_struct {
 #ifdef CONFIG_COMPAT_BRK
 	unsigned brk_randomized:1;
 #endif
+	/* per-thread vma caching */
+	u32 vmacache_seqnum;
+	struct vm_area_struct *vmacache[VMACACHE_SIZE];
 #if defined(SPLIT_RSS_COUNTING)
 	struct task_rss_stat	rss_stat;
 #endif
@@ -1862,7 +1870,6 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define PF_SPREAD_SLAB	0x02000000	/* Spread some slab caches over cpuset */
 #define PF_NO_SETAFFINITY 0x04000000	/* Userland is not allowed to meddle with cpus_allowed */
 #define PF_MCE_EARLY    0x08000000      /* Early kill for mce process policy */
-#define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
 #define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
 #define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezable */
 #define PF_SUSPEND_TASK 0x80000000      /* this thread called freeze_processes and should not be frozen */
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 9d55438bc4ad..4d1771c2d29f 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -51,6 +51,7 @@ extern struct file *shmem_kernel_file_setup(const char *name, loff_t size,
 					    unsigned long flags);
 extern int shmem_zero_setup(struct vm_area_struct *);
 extern int shmem_lock(struct file *file, int lock, struct user_struct *user);
+extern bool shmem_mapping(struct address_space *mapping);
 extern void shmem_unlock_mapping(struct address_space *mapping);
 extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
 					pgoff_t index, gfp_t gfp_mask);
diff --git a/include/linux/string.h b/include/linux/string.h
index ac889c5ea11b..f29f9a0b7265 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -114,6 +114,7 @@ void *memchr_inv(const void *s, int c, size_t n);
 
 extern char *kstrdup(const char *s, gfp_t gfp);
 extern char *kstrndup(const char *s, size_t len, gfp_t gfp);
+extern char *kstrimdup(const char *s, gfp_t gfp);
 extern void *kmemdup(const void *src, size_t len, gfp_t gfp);
 
 extern char **argv_split(gfp_t gfp, const char *str, int *argcp);
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 46ba0c6c219f..350711560753 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -260,6 +260,42 @@ struct swap_list_t {
 	int next;	/* swapfile to be used next */
 };
 
+/* linux/mm/workingset.c */
+void *workingset_eviction(struct address_space *mapping, struct page *page);
+bool workingset_refault(void *shadow);
+void workingset_activation(struct page *page);
+extern struct list_lru workingset_shadow_nodes;
+
+static inline unsigned int workingset_node_pages(struct radix_tree_node *node)
+{
+	return node->count & RADIX_TREE_COUNT_MASK;
+}
+
+static inline void workingset_node_pages_inc(struct radix_tree_node *node)
+{
+	node->count++;
+}
+
+static inline void workingset_node_pages_dec(struct radix_tree_node *node)
+{
+	node->count--;
+}
+
+static inline unsigned int workingset_node_shadows(struct radix_tree_node *node)
+{
+	return node->count >> RADIX_TREE_COUNT_SHIFT;
+}
+
+static inline void workingset_node_shadows_inc(struct radix_tree_node *node)
+{
+	node->count += 1U << RADIX_TREE_COUNT_SHIFT;
+}
+
+static inline void workingset_node_shadows_dec(struct radix_tree_node *node)
+{
+	node->count -= 1U << RADIX_TREE_COUNT_SHIFT;
+}
+
 /* linux/mm/page_alloc.c */
 extern unsigned long totalram_pages;
 extern unsigned long totalreserve_pages;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 1e67b7a5968c..2aa8b749f13d 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -200,6 +200,8 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 	}								\
 	static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__))
 
+asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special,
+			       qid_t id, void __user *addr);
 asmlinkage long sys_time(time_t __user *tloc);
 asmlinkage long sys_stime(time_t __user *tptr);
 asmlinkage long sys_gettimeofday(struct timeval __user *tv,
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 3a712e2e7d76..486c3972c0be 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -37,6 +37,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL,
 		KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
 		PAGEOUTRUN, ALLOCSTALL, PGROTATED,
+		DROP_PAGECACHE, DROP_SLAB,
 #ifdef CONFIG_NUMA_BALANCING
 		NUMA_PTE_UPDATES,
 		NUMA_HUGE_PTE_UPDATES,
diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h
new file mode 100644
index 000000000000..c3fa0fd43949
--- /dev/null
+++ b/include/linux/vmacache.h
@@ -0,0 +1,38 @@
+#ifndef __LINUX_VMACACHE_H
+#define __LINUX_VMACACHE_H
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+
+/*
+ * Hash based on the page number. Provides a good hit rate for
+ * workloads with good locality and those with random accesses as well.
+ */
+#define VMACACHE_HASH(addr) ((addr >> PAGE_SHIFT) & VMACACHE_MASK)
+
+static inline void vmacache_flush(struct task_struct *tsk)
+{
+	memset(tsk->vmacache, 0, sizeof(tsk->vmacache));
+}
+
+extern void vmacache_flush_all(struct mm_struct *mm);
+extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma);
+extern struct vm_area_struct *vmacache_find(struct mm_struct *mm,
+						    unsigned long addr);
+
+#ifndef CONFIG_MMU
+extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm,
+						  unsigned long start,
+						  unsigned long end);
+#endif
+
+static inline void vmacache_invalidate(struct mm_struct *mm)
+{
+	mm->vmacache_seqnum++;
+
+	/* deal with overflows */
+	if (unlikely(mm->vmacache_seqnum == 0))
+		vmacache_flush_all(mm);
+}
+
+#endif /* __LINUX_VMACACHE_H */
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 67ce70c8279b..ea4476157e00 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -187,8 +187,6 @@ extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp);
 #define add_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, __d)
 #define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d))
 
-extern void inc_zone_state(struct zone *, enum zone_stat_item);
-
 #ifdef CONFIG_SMP
 void __mod_zone_page_state(struct zone *, enum zone_stat_item item, int);
 void __inc_zone_page_state(struct page *, enum zone_stat_item);
@@ -230,18 +228,18 @@ static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
 	atomic_long_inc(&vm_stat[item]);
 }
 
-static inline void __inc_zone_page_state(struct page *page,
-			enum zone_stat_item item)
-{
-	__inc_zone_state(page_zone(page), item);
-}
-
 static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
 {
 	atomic_long_dec(&zone->vm_stat[item]);
 	atomic_long_dec(&vm_stat[item]);
 }
 
+static inline void __inc_zone_page_state(struct page *page,
+			enum zone_stat_item item)
+{
+	__inc_zone_state(page_zone(page), item);
+}
+
 static inline void __dec_zone_page_state(struct page *page,
 			enum zone_stat_item item)
 {
@@ -256,6 +254,9 @@ static inline void __dec_zone_page_state(struct page *page,
 #define dec_zone_page_state __dec_zone_page_state
 #define mod_zone_page_state __mod_zone_page_state
 
+#define inc_zone_state __inc_zone_state
+#define dec_zone_state __dec_zone_state
+
 #define set_pgdat_percpu_threshold(pgdat, callback) { }
 
 static inline void refresh_cpu_vm_stats(int cpu) { }
diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h
index 335e8a7cad39..c140620dad92 100644
--- a/include/uapi/linux/libc-compat.h
+++ b/include/uapi/linux/libc-compat.h
@@ -85,6 +85,12 @@
 
 #endif /* _NETINET_IN_H */
 
+/* Definitions for xattr.h */
+#if defined(_SYS_XATTR_H)
+#define __UAPI_DEF_XATTR		0
+#else
+#define __UAPI_DEF_XATTR		1
+#endif
 
 /* If we did not see any headers from any supported C libraries,
  * or we are being included in the kernel, then define everything
@@ -98,6 +104,9 @@
 #define __UAPI_DEF_IPV6_MREQ		1
 #define __UAPI_DEF_IPPROTO_V6		1
 
+/* Definitions for xattr.h */
+#define __UAPI_DEF_XATTR		1
+
 #endif /* __GLIBC__ */
 
 #endif /* _UAPI_LIBC_COMPAT_H */
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 289760f424aa..58afc04c107e 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -149,4 +149,7 @@
 
 #define PR_GET_TID_ADDRESS	40
 
+#define PR_SET_THP_DISABLE	41
+#define PR_GET_THP_DISABLE	42
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h
index 40bbc04b6f81..c38355c1f3c9 100644
--- a/include/uapi/linux/xattr.h
+++ b/include/uapi/linux/xattr.h
@@ -7,11 +7,18 @@
   Copyright (c) 2001-2002 Silicon Graphics, Inc.  All Rights Reserved.
   Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
 */
+
+#include <linux/libc-compat.h>
+
 #ifndef _UAPI_LINUX_XATTR_H
 #define _UAPI_LINUX_XATTR_H
 
+#ifdef __UAPI_DEF_XATTR
+#define __USE_KERNEL_XATTR_DEFS
+
 #define XATTR_CREATE	0x1	/* set value, fail if attr already exists */
 #define XATTR_REPLACE	0x2	/* set value, fail if attr does not exist */
+#endif
 
 /* Namespaces */
 #define XATTR_OS2_PREFIX "os2."
diff --git a/init/Kconfig b/init/Kconfig
index 0dd355bb9967..765018c24cf9 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -273,6 +273,16 @@ config FHANDLE
 	  get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2)
 	  syscalls.
 
+config USELIB
+	bool "uselib syscall"
+	default y
+	help
+	  This option enables the uselib syscall, a system call used in the
+	  dynamic linker from libc5 and earlier.  glibc does not use this
+	  system call.  If you intend to run programs built on libc5 or
+	  earlier, you may need to enable this syscall.  Current systems
+	  running glibc can safely disable this.
+
 config AUDIT
 	bool "Auditing support"
 	depends on NET
@@ -1294,6 +1304,16 @@ config UID16
 	help
 	  This enables the legacy 16-bit UID syscall wrappers.
 
+config SYSFS_SYSCALL
+	bool "Sysfs syscall support" if EXPERT
+	default y
+	---help---
+	  sys_sysfs is an obsolete system call no longer supported in libc.
+	  Note that disabling this option is more secure but might break
+	  compatibility with some systems.
+
+	  If unsure say Y here.
+
 config SYSCTL_SYSCALL
 	bool "Sysctl syscall support" if EXPERT
 	depends on PROC_SYSCTL
@@ -1466,6 +1486,7 @@ config PCI_QUIRKS
 
 config EMBEDDED
 	bool "Embedded system"
+	option allnoconfig_y
 	select EXPERT
 	help
 	  This option should be enabled if compiling the kernel for
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 8e5addc45874..82f22885c87e 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -102,13 +102,13 @@ no_match:
 
 /**
  * devt_from_partuuid - looks up the dev_t of a partition by its UUID
- * @uuid:	char array containing ascii UUID
+ * @uuid_str:	char array containing ascii UUID
  *
  * The function will return the first partition which contains a matching
  * UUID value in its partition_meta_info struct.  This does not search
  * by filesystem UUIDs.
  *
- * If @uuid is followed by a "/PARTNROFF=%d", then the number will be
+ * If @uuid_str is followed by a "/PARTNROFF=%d", then the number will be
  * extracted and used as an offset from the partition identified by the UUID.
  *
  * Returns the matching dev_t on success or 0 on failure.
diff --git a/init/initramfs.c b/init/initramfs.c
index 93b61396756b..a8497fab1c3d 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -455,6 +455,7 @@ static char * __init unpack_to_rootfs(char *buf, unsigned len)
 		}
 		this_header = 0;
 		decompress = decompress_method(buf, len, &compress_name);
+		pr_debug("Detected %s compressed data\n", compress_name);
 		if (decompress) {
 			res = decompress(buf, len, NULL, flush_buffer, NULL,
 				   &my_inptr, error);
diff --git a/ipc/compat.c b/ipc/compat.c
index a4695ada3275..45d035d4cedc 100644
--- a/ipc/compat.c
+++ b/ipc/compat.c
@@ -113,9 +113,6 @@ struct compat_shm_info {
 	compat_ulong_t swap_attempts, swap_successes;
 };
 
-extern int sem_ctls[];
-#define sc_semopm	(sem_ctls[2])
-
 static inline int compat_ipc_parse_version(int *cmd)
 {
 #ifdef	CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index 17028648cfeb..998d31b230f1 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -281,4 +281,4 @@ static int __init ipc_sysctl_init(void)
 	return 0;
 }
 
-__initcall(ipc_sysctl_init);
+device_initcall(ipc_sysctl_init);
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index c3b31179122c..4fcf39af1776 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -1459,4 +1459,4 @@ out_sysctl:
 	return error;
 }
 
-__initcall(init_mqueue_fs);
+device_initcall(init_mqueue_fs);
diff --git a/ipc/util.c b/ipc/util.c
index e1b4c6db8aa0..2eb0d1eaa312 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -128,7 +128,7 @@ static int __init ipc_init(void)
 	register_ipcns_notifier(&init_ipc_ns);
 	return 0;
 }
-__initcall(ipc_init);
+device_initcall(ipc_init);
 
 /**
  * ipc_init_ids	- initialise ipc identifiers
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index e2dbb60004d4..3d54c418bd06 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -996,7 +996,7 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 	task_lock(tsk);
 	/*
 	 * Determine if a loop is necessary if another thread is doing
-	 * get_mems_allowed().  If at least one node remains unchanged and
+	 * read_mems_allowed_begin().  If at least one node remains unchanged and
 	 * tsk does not have a mempolicy, then an empty nodemask will not be
 	 * possible when mems_allowed is larger than a word.
 	 */
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 99982a70ddad..2956c8da1605 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -49,6 +49,7 @@
 #include <linux/pid.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/rcupdate.h>
 
 #include <asm/cacheflush.h>
@@ -224,10 +225,17 @@ static void kgdb_flush_swbreak_addr(unsigned long addr)
 	if (!CACHE_FLUSH_IS_SAFE)
 		return;
 
-	if (current->mm && current->mm->mmap_cache) {
-		flush_cache_range(current->mm->mmap_cache,
-				  addr, addr + BREAK_INSTR_SIZE);
+	if (current->mm) {
+		int i;
+
+		for (i = 0; i < VMACACHE_SIZE; i++) {
+			if (!current->vmacache[i])
+				continue;
+			flush_cache_range(current->vmacache[i],
+					  addr, addr + BREAK_INSTR_SIZE);
+		}
 	}
+
 	/* Force flush instruction cache if it was outside the mm */
 	flush_icache_range(addr, addr + BREAK_INSTR_SIZE);
 }
diff --git a/kernel/exit.c b/kernel/exit.c
index 6480d1c85d7a..6ed6a1d552b5 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -570,7 +570,7 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 	if (same_thread_group(p->real_parent, father))
 		return;
 
-	/* We don't want people slaying init.  */
+	/* We don't want people slaying init. */
 	p->exit_signal = SIGCHLD;
 
 	/* If it has exited notify the new parent about this child's death. */
@@ -784,9 +784,10 @@ void do_exit(long code)
 	exit_shm(tsk);
 	exit_files(tsk);
 	exit_fs(tsk);
+	if (group_dead)
+		disassociate_ctty(1);
 	exit_task_namespaces(tsk);
 	exit_task_work(tsk);
-	check_stack_usage();
 	exit_thread();
 
 	/*
@@ -799,19 +800,15 @@ void do_exit(long code)
 
 	cgroup_exit(tsk);
 
-	if (group_dead)
-		disassociate_ctty(1);
-
 	module_put(task_thread_info(tsk)->exec_domain->module);
 
-	proc_exit_connector(tsk);
-
 	/*
 	 * FIXME: do that only when needed, using sched_exit tracepoint
 	 */
 	flush_ptrace_hw_breakpoint(tsk);
 
 	exit_notify(tsk, group_dead);
+	proc_exit_connector(tsk);
 #ifdef CONFIG_NUMA
 	task_lock(tsk);
 	mpol_put(tsk->mempolicy);
@@ -844,6 +841,7 @@ void do_exit(long code)
 
 	validate_creds_for_do_exit(tsk);
 
+	check_stack_usage();
 	preempt_disable();
 	if (tsk->nr_dirtied)
 		__this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied);
@@ -1038,17 +1036,13 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		return wait_noreap_copyout(wo, p, pid, uid, why, status);
 	}
 
+	traced = ptrace_reparented(p);
 	/*
-	 * Try to move the task's state to DEAD
-	 * only one thread is allowed to do this:
+	 * Move the task's state to DEAD/TRACE, only one thread can do this.
 	 */
-	state = xchg(&p->exit_state, EXIT_DEAD);
-	if (state != EXIT_ZOMBIE) {
-		BUG_ON(state != EXIT_DEAD);
+	state = traced && thread_group_leader(p) ? EXIT_TRACE : EXIT_DEAD;
+	if (cmpxchg(&p->exit_state, EXIT_ZOMBIE, state) != EXIT_ZOMBIE)
 		return 0;
-	}
-
-	traced = ptrace_reparented(p);
 	/*
 	 * It can be ptraced but not reparented, check
 	 * thread_group_leader() to filter out sub-threads.
@@ -1109,7 +1103,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 
 	/*
 	 * Now we are sure this task is interesting, and no other
-	 * thread can reap it because we set its state to EXIT_DEAD.
+	 * thread can reap it because we its state == DEAD/TRACE.
 	 */
 	read_unlock(&tasklist_lock);
 
@@ -1146,22 +1140,19 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 	if (!retval)
 		retval = pid;
 
-	if (traced) {
+	if (state == EXIT_TRACE) {
 		write_lock_irq(&tasklist_lock);
 		/* We dropped tasklist, ptracer could die and untrace */
 		ptrace_unlink(p);
-		/*
-		 * If this is not a sub-thread, notify the parent.
-		 * If parent wants a zombie, don't release it now.
-		 */
-		if (thread_group_leader(p) &&
-		    !do_notify_parent(p, p->exit_signal)) {
-			p->exit_state = EXIT_ZOMBIE;
-			p = NULL;
-		}
+
+		/* If parent wants a zombie, don't release it now */
+		state = EXIT_ZOMBIE;
+		if (do_notify_parent(p, p->exit_signal))
+			state = EXIT_DEAD;
+		p->exit_state = state;
 		write_unlock_irq(&tasklist_lock);
 	}
-	if (p != NULL)
+	if (state == EXIT_DEAD)
 		release_task(p);
 
 	return retval;
@@ -1338,7 +1329,12 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
 static int wait_consider_task(struct wait_opts *wo, int ptrace,
 				struct task_struct *p)
 {
-	int ret = eligible_child(wo, p);
+	int ret;
+
+	if (unlikely(p->exit_state == EXIT_DEAD))
+		return 0;
+
+	ret = eligible_child(wo, p);
 	if (!ret)
 		return ret;
 
@@ -1356,33 +1352,44 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 		return 0;
 	}
 
-	/* dead body doesn't have much to contribute */
-	if (unlikely(p->exit_state == EXIT_DEAD)) {
+	if (unlikely(p->exit_state == EXIT_TRACE)) {
 		/*
-		 * But do not ignore this task until the tracer does
-		 * wait_task_zombie()->do_notify_parent().
+		 * ptrace == 0 means we are the natural parent. In this case
+		 * we should clear notask_error, debugger will notify us.
 		 */
-		if (likely(!ptrace) && unlikely(ptrace_reparented(p)))
+		if (likely(!ptrace))
 			wo->notask_error = 0;
 		return 0;
 	}
 
-	/* slay zombie? */
-	if (p->exit_state == EXIT_ZOMBIE) {
+	if (likely(!ptrace) && unlikely(p->ptrace)) {
 		/*
-		 * A zombie ptracee is only visible to its ptracer.
-		 * Notification and reaping will be cascaded to the real
-		 * parent when the ptracer detaches.
+		 * If it is traced by its real parent's group, just pretend
+		 * the caller is ptrace_do_wait() and reap this child if it
+		 * is zombie.
+		 *
+		 * This also hides group stop state from real parent; otherwise
+		 * a single stop can be reported twice as group and ptrace stop.
+		 * If a ptracer wants to distinguish these two events for its
+		 * own children it should create a separate process which takes
+		 * the role of real parent.
 		 */
-		if (likely(!ptrace) && unlikely(p->ptrace)) {
-			/* it will become visible, clear notask_error */
-			wo->notask_error = 0;
-			return 0;
-		}
+		if (!ptrace_reparented(p))
+			ptrace = 1;
+	}
 
+	/* slay zombie? */
+	if (p->exit_state == EXIT_ZOMBIE) {
 		/* we don't reap group leaders with subthreads */
-		if (!delay_group_leader(p))
-			return wait_task_zombie(wo, p);
+		if (!delay_group_leader(p)) {
+			/*
+			 * A zombie ptracee is only visible to its ptracer.
+			 * Notification and reaping will be cascaded to the
+			 * real parent when the ptracer detaches.
+			 */
+			if (unlikely(ptrace) || likely(!p->ptrace))
+				return wait_task_zombie(wo, p);
+		}
 
 		/*
 		 * Allow access to stopped/continued state via zombie by
@@ -1408,19 +1415,6 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 			wo->notask_error = 0;
 	} else {
 		/*
-		 * If @p is ptraced by a task in its real parent's group,
-		 * hide group stop/continued state when looking at @p as
-		 * the real parent; otherwise, a single stop can be
-		 * reported twice as group and ptrace stops.
-		 *
-		 * If a ptracer wants to distinguish the two events for its
-		 * own children, it should create a separate process which
-		 * takes the role of real parent.
-		 */
-		if (likely(!ptrace) && p->ptrace && !ptrace_reparented(p))
-			return 0;
-
-		/*
 		 * @p is alive and it's gonna stop, continue or exit, so
 		 * there always is something to wait for.
 		 */
diff --git a/kernel/fork.c b/kernel/fork.c
index abc45890f0a5..e905e9c6b224 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -28,6 +28,8 @@
 #include <linux/mman.h>
 #include <linux/mmu_notifier.h>
 #include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/nsproxy.h>
 #include <linux/capability.h>
 #include <linux/cpu.h>
@@ -364,7 +366,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 
 	mm->locked_vm = 0;
 	mm->mmap = NULL;
-	mm->mmap_cache = NULL;
+	mm->vmacache_seqnum = 0;
 	mm->map_count = 0;
 	cpumask_clear(mm_cpumask(mm));
 	mm->mm_rb = RB_ROOT;
@@ -530,8 +532,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	atomic_set(&mm->mm_count, 1);
 	init_rwsem(&mm->mmap_sem);
 	INIT_LIST_HEAD(&mm->mmlist);
-	mm->flags = (current->mm) ?
-		(current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
 	mm->core_state = NULL;
 	atomic_long_set(&mm->nr_ptes, 0);
 	memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
@@ -540,8 +540,15 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	mm_init_owner(mm, p);
 	clear_tlb_flush_pending(mm);
 
-	if (likely(!mm_alloc_pgd(mm))) {
+	if (current->mm) {
+		mm->flags = current->mm->flags & MMF_INIT_MASK;
+		mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK;
+	} else {
+		mm->flags = default_dump_filter;
 		mm->def_flags = 0;
+	}
+
+	if (likely(!mm_alloc_pgd(mm))) {
 		mmu_notifier_mm_init(mm);
 		return mm;
 	}
@@ -877,6 +884,9 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
 	if (!oldmm)
 		return 0;
 
+	/* initialize the new vmacache entries */
+	vmacache_flush(tsk);
+
 	if (clone_flags & CLONE_VM) {
 		atomic_inc(&oldmm->mm_users);
 		mm = oldmm;
@@ -1070,15 +1080,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	return 0;
 }
 
-static void copy_flags(unsigned long clone_flags, struct task_struct *p)
-{
-	unsigned long new_flags = p->flags;
-
-	new_flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
-	new_flags |= PF_FORKNOEXEC;
-	p->flags = new_flags;
-}
-
 SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
 {
 	current->clear_child_tid = tidptr;
@@ -1228,7 +1229,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto bad_fork_cleanup_count;
 
 	delayacct_tsk_init(p);	/* Must remain after dup_task_struct() */
-	copy_flags(clone_flags, p);
+	p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
+	p->flags |= PF_FORKNOEXEC;
 	INIT_LIST_HEAD(&p->children);
 	INIT_LIST_HEAD(&p->sibling);
 	rcu_copy_process(p);
@@ -1274,7 +1276,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		p->mempolicy = NULL;
 		goto bad_fork_cleanup_threadgroup_lock;
 	}
-	mpol_fix_fork_child_flag(p);
 #endif
 #ifdef CONFIG_CPUSETS
 	p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
diff --git a/kernel/groups.c b/kernel/groups.c
index 90cf1c38c8ea..451698f86cfa 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -157,17 +157,13 @@ int groups_search(const struct group_info *group_info, kgid_t grp)
  * set_groups - Change a group subscription in a set of credentials
  * @new: The newly prepared set of credentials to alter
  * @group_info: The group list to install
- *
- * Validate a group subscription and, if valid, insert it into a set
- * of credentials.
  */
-int set_groups(struct cred *new, struct group_info *group_info)
+void set_groups(struct cred *new, struct group_info *group_info)
 {
 	put_group_info(new->group_info);
 	groups_sort(group_info);
 	get_group_info(group_info);
 	new->group_info = group_info;
-	return 0;
 }
 
 EXPORT_SYMBOL(set_groups);
@@ -182,18 +178,12 @@ EXPORT_SYMBOL(set_groups);
 int set_current_groups(struct group_info *group_info)
 {
 	struct cred *new;
-	int ret;
 
 	new = prepare_creds();
 	if (!new)
 		return -ENOMEM;
 
-	ret = set_groups(new, group_info);
-	if (ret < 0) {
-		abort_creds(new);
-		return ret;
-	}
-
+	set_groups(new, group_info);
 	return commit_creds(new);
 }
 
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 0b9c169d577f..06bb1417b063 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -246,5 +246,4 @@ static int __init hung_task_init(void)
 
 	return 0;
 }
-
-module_init(hung_task_init);
+subsys_initcall(hung_task_init);
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 45601cf41bee..c0d261c7db7b 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1235,7 +1235,7 @@ static int __init crash_notes_memory_init(void)
 	}
 	return 0;
 }
-module_init(crash_notes_memory_init)
+subsys_initcall(crash_notes_memory_init);
 
 
 /*
@@ -1629,7 +1629,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 	return 0;
 }
 
-module_init(crash_save_vmcoreinfo_init)
+subsys_initcall(crash_save_vmcoreinfo_init);
 
 /*
  * Move into place and start executing a preloaded standalone
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 6b375af4958d..55a36537fef4 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -40,6 +40,7 @@
 #include <linux/ptrace.h>
 #include <linux/async.h>
 #include <asm/uaccess.h>
+#include <linux/kthread.h>
 
 #include <trace/events/module.h>
 
@@ -209,8 +210,14 @@ static int ____call_usermodehelper(void *data)
 	flush_signal_handlers(current, 1);
 	spin_unlock_irq(&current->sighand->siglock);
 
-	/* We can run anywhere, unlike our parent keventd(). */
-	set_cpus_allowed_ptr(current, cpu_all_mask);
+	/*
+	 * Kthreadd can be restricted to a set of processors if the user wants
+	 * to protect other processors from OS latencies. If that has happened
+	 * then we do not want to disturb the other processors here either so we
+	 * start the usermode helper threads only on the processors allowed for
+	 * kthreadd.
+	 */
+	set_kthreadd_affinity();
 
 	/*
 	 * Our parent is keventd, which runs with elevated scheduling priority.
diff --git a/kernel/kthread.c b/kernel/kthread.c
index b5ae3ee860a9..2c355bf2f094 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -136,6 +136,15 @@ void *kthread_data(struct task_struct *task)
 	return to_kthread(task)->data;
 }
 
+/*
+ * Set the affinity of the calling task to be the same
+ * as the kthreadd affinities.
+ */
+void set_kthreadd_affinity(void)
+{
+	set_cpus_allowed_ptr(current, &kthreadd_task->cpus_allowed);
+}
+
 /**
  * probe_kthread_data - speculative version of kthread_data()
  * @task: possible kthread task in question
@@ -217,7 +226,7 @@ int tsk_fork_get_node(struct task_struct *tsk)
 	if (tsk == kthreadd_task)
 		return tsk->pref_node_fork;
 #endif
-	return numa_node_id();
+	return NUMA_NO_NODE;
 }
 
 static void create_kthread(struct kthread_create_info *create)
@@ -369,7 +378,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
 {
 	struct task_struct *p;
 
-	p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt,
+	p = kthread_create_on_node(threadfn, data, cpu_to_mem(cpu), namefmt,
 				   cpu);
 	if (IS_ERR(p))
 		return p;
diff --git a/kernel/panic.c b/kernel/panic.c
index 79fd820bb5e8..d02fa9fef46a 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -100,7 +100,7 @@ void panic(const char *fmt, ...)
 	va_start(args, fmt);
 	vsnprintf(buf, sizeof(buf), fmt, args);
 	va_end(args);
-	printk(KERN_EMERG "Kernel panic - not syncing: %s\n",buf);
+	pr_emerg("Kernel panic - not syncing: %s\n", buf);
 #ifdef CONFIG_DEBUG_BUGVERBOSE
 	/*
 	 * Avoid nested stack-dumping if a panic occurs during oops processing
@@ -141,7 +141,7 @@ void panic(const char *fmt, ...)
 		 * Delay timeout seconds before rebooting the machine.
 		 * We can't use the "normal" timers since we just panicked.
 		 */
-		printk(KERN_EMERG "Rebooting in %d seconds..", panic_timeout);
+		pr_emerg("Rebooting in %d seconds..", panic_timeout);
 
 		for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) {
 			touch_nmi_watchdog();
@@ -165,7 +165,7 @@ void panic(const char *fmt, ...)
 		extern int stop_a_enabled;
 		/* Make sure the user can actually press Stop-A (L1-A) */
 		stop_a_enabled = 1;
-		printk(KERN_EMERG "Press Stop-A (L1-A) to return to the boot prom\n");
+		pr_emerg("Press Stop-A (L1-A) to return to the boot prom\n");
 	}
 #endif
 #if defined(CONFIG_S390)
@@ -176,6 +176,7 @@ void panic(const char *fmt, ...)
 		disabled_wait(caller);
 	}
 #endif
+	pr_emerg("---[ end Kernel panic - not syncing: %s\n", buf);
 	local_irq_enable();
 	for (i = 0; ; i += PANIC_TIMER_STEP) {
 		touch_softlockup_watchdog();
@@ -276,8 +277,7 @@ unsigned long get_taint(void)
 void add_taint(unsigned flag, enum lockdep_ok lockdep_ok)
 {
 	if (lockdep_ok == LOCKDEP_NOW_UNRELIABLE && __debug_locks_off())
-		printk(KERN_WARNING
-		       "Disabling lock debugging due to kernel taint\n");
+		pr_warn("Disabling lock debugging due to kernel taint\n");
 
 	set_bit(flag, &tainted_mask);
 }
@@ -382,8 +382,7 @@ late_initcall(init_oops_id);
 void print_oops_end_marker(void)
 {
 	init_oops_id();
-	printk(KERN_WARNING "---[ end trace %016llx ]---\n",
-		(unsigned long long)oops_id);
+	pr_warn("---[ end trace %016llx ]---\n", (unsigned long long)oops_id);
 }
 
 /*
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 4dae9cbe9259..a45b50962295 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -319,7 +319,7 @@ static void log_store(int facility, int level,
 		else
 			free = log_first_idx - log_next_idx;
 
-		if (free > size + sizeof(struct printk_log))
+		if (free >= size + sizeof(struct printk_log))
 			break;
 
 		/* drop old messages until we have enough contiuous space */
@@ -327,7 +327,7 @@ static void log_store(int facility, int level,
 		log_first_seq++;
 	}
 
-	if (log_next_idx + size + sizeof(struct printk_log) >= log_buf_len) {
+	if (log_next_idx + size + sizeof(struct printk_log) > log_buf_len) {
 		/*
 		 * This message + an additional empty header does not fit
 		 * at the end of the buffer. Add an empty header with len == 0
@@ -351,7 +351,7 @@ static void log_store(int facility, int level,
 	else
 		msg->ts_nsec = local_clock();
 	memset(log_dict(msg) + dict_len, 0, pad_len);
-	msg->len = sizeof(struct printk_log) + text_len + dict_len + pad_len;
+	msg->len = size;
 
 	/* insert message */
 	log_next_idx += msg->len;
@@ -1560,9 +1560,12 @@ asmlinkage int vprintk_emit(int facility, int level,
 					level = kern_level - '0';
 			case 'd':	/* KERN_DEFAULT */
 				lflags |= LOG_PREFIX;
-			case 'c':	/* KERN_CONT */
-				break;
 			}
+			/*
+			 * No need to check length here because vscnprintf
+			 * put '\0' at the end of the string. Only valid and
+			 * newly printed level is detected.
+			 */
 			text_len -= end_of_header - text;
 			text = (char *)end_of_header;
 		}
@@ -1880,6 +1883,7 @@ void suspend_console(void)
 	console_lock();
 	console_suspended = 1;
 	up(&console_sem);
+	mutex_release(&console_lock_dep_map, 1, _RET_IP_);
 }
 
 void resume_console(void)
@@ -1887,6 +1891,7 @@ void resume_console(void)
 	if (!console_suspend_enabled)
 		return;
 	down(&console_sem);
+	mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_);
 	console_suspended = 0;
 	console_unlock();
 }
diff --git a/kernel/profile.c b/kernel/profile.c
index 93b2a3fe0a64..cb980f0c731b 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -614,5 +614,5 @@ out:
 	cpu_notifier_register_done();
 	return err;
 }
-module_init(create_proc_profile);
+subsys_initcall(create_proc_profile);
 #endif /* CONFIG_PROC_FS */
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index 4aa8a305aede..51dbac6a3633 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -22,8 +22,18 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent)
 	counter->parent = parent;
 }
 
-int res_counter_charge_locked(struct res_counter *counter, unsigned long val,
-			      bool force)
+static u64 res_counter_uncharge_locked(struct res_counter *counter,
+				       unsigned long val)
+{
+	if (WARN_ON(counter->usage < val))
+		val = counter->usage;
+
+	counter->usage -= val;
+	return counter->usage;
+}
+
+static int res_counter_charge_locked(struct res_counter *counter,
+				     unsigned long val, bool force)
 {
 	int ret = 0;
 
@@ -86,15 +96,6 @@ int res_counter_charge_nofail(struct res_counter *counter, unsigned long val,
 	return __res_counter_charge(counter, val, limit_fail_at, true);
 }
 
-u64 res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
-{
-	if (WARN_ON(counter->usage < val))
-		val = counter->usage;
-
-	counter->usage -= val;
-	return counter->usage;
-}
-
 u64 res_counter_uncharge_until(struct res_counter *counter,
 			       struct res_counter *top,
 			       unsigned long val)
diff --git a/kernel/resource.c b/kernel/resource.c
index 673061c06da1..8957d686e29b 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -511,7 +511,7 @@ static int find_resource(struct resource *root, struct resource *new,
  * @newsize: new size of the resource descriptor
  * @constraint: the size and alignment constraints to be met.
  */
-int reallocate_resource(struct resource *root, struct resource *old,
+static int reallocate_resource(struct resource *root, struct resource *old,
 			resource_size_t newsize,
 			struct resource_constraint  *constraint)
 {
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index da98af347e8b..a476bea17fbc 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -142,4 +142,4 @@ static int __init proc_schedstat_init(void)
 	proc_create("schedstat", 0, NULL, &proc_schedstat_operations);
 	return 0;
 }
-module_init(proc_schedstat_init);
+subsys_initcall(proc_schedstat_init);
diff --git a/kernel/sys.c b/kernel/sys.c
index adaeab6f7a87..fba0f29401ea 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1996,6 +1996,21 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		if (arg2 || arg3 || arg4 || arg5)
 			return -EINVAL;
 		return current->no_new_privs ? 1 : 0;
+	case PR_GET_THP_DISABLE:
+		if (arg2 || arg3 || arg4 || arg5)
+			return -EINVAL;
+		error = !!(me->mm->def_flags & VM_NOHUGEPAGE);
+		break;
+	case PR_SET_THP_DISABLE:
+		if (arg3 || arg4 || arg5)
+			return -EINVAL;
+		down_write(&me->mm->mmap_sem);
+		if (arg2)
+			me->mm->def_flags |= VM_NOHUGEPAGE;
+		else
+			me->mm->def_flags &= ~VM_NOHUGEPAGE;
+		up_write(&me->mm->mmap_sem);
+		break;
 	default:
 		error = -EINVAL;
 		break;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 7078052284fd..bc8d1b74a6b9 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -146,11 +146,13 @@ cond_syscall(sys_io_destroy);
 cond_syscall(sys_io_submit);
 cond_syscall(sys_io_cancel);
 cond_syscall(sys_io_getevents);
+cond_syscall(sys_sysfs);
 cond_syscall(sys_syslog);
 cond_syscall(sys_process_vm_readv);
 cond_syscall(sys_process_vm_writev);
 cond_syscall(compat_sys_process_vm_readv);
 cond_syscall(compat_sys_process_vm_writev);
+cond_syscall(sys_uselib);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 09d2e2413605..5c14b547882e 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -123,7 +123,7 @@ static int __maybe_unused neg_one = -1;
 static int zero;
 static int __maybe_unused one = 1;
 static int __maybe_unused two = 2;
-static int __maybe_unused three = 3;
+static int __maybe_unused four = 4;
 static unsigned long one_ul = 1;
 static int one_hundred = 100;
 #ifdef CONFIG_PRINTK
@@ -1264,7 +1264,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= drop_caches_sysctl_handler,
 		.extra1		= &one,
-		.extra2		= &three,
+		.extra2		= &four,
 	},
 #ifdef CONFIG_COMPACTION
 	{
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 4d23dc4d8139..5038b4d3b76d 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -154,6 +154,10 @@ void __init sched_clock_register(u64 (*read)(void), int bits,
 	raw_write_seqcount_end(&cd.seq);
 
 	r = rate;
+	/*
+	 * Use 4MHz instead of 1MHz so that things like 1.832Mhz show as
+	 * 1832Khz
+	 */
 	if (r >= 4000000) {
 		r /= 1000000;
 		r_unit = 'M';
diff --git a/kernel/user.c b/kernel/user.c
index c006131beb77..294fc6a94168 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -222,5 +222,4 @@ static int __init uid_cache_init(void)
 
 	return 0;
 }
-
-module_init(uid_cache_init);
+subsys_initcall(uid_cache_init);
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index dd06439b9c84..0d8f6023fd8d 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -902,4 +902,4 @@ static __init int user_namespaces_init(void)
 	user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC);
 	return 0;
 }
-module_init(user_namespaces_init);
+subsys_initcall(user_namespaces_init);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 01c6f979486f..18bc5c2a26df 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -158,14 +158,14 @@ void touch_all_softlockup_watchdogs(void)
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 void touch_nmi_watchdog(void)
 {
-	if (watchdog_user_enabled) {
-		unsigned cpu;
-
-		for_each_present_cpu(cpu) {
-			if (per_cpu(watchdog_nmi_touch, cpu) != true)
-				per_cpu(watchdog_nmi_touch, cpu) = true;
-		}
-	}
+	/*
+	 * Using __raw here because some code paths have
+	 * preemption enabled.  If preemption is enabled
+	 * then interrupts should be enabled too, in which
+	 * case we shouldn't have to worry about the watchdog
+	 * going off.
+	 */
+	__raw_get_cpu_var(watchdog_nmi_touch) = true;
 	touch_softlockup_watchdog();
 }
 EXPORT_SYMBOL(touch_nmi_watchdog);
@@ -239,10 +239,12 @@ static void watchdog_overflow_callback(struct perf_event *event,
 		if (__this_cpu_read(hard_watchdog_warn) == true)
 			return;
 
-		if (hardlockup_panic)
+		if (hardlockup_panic) {
+			trigger_all_cpu_backtrace();
 			panic("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
-		else
+		} else {
 			WARN(1, "Watchdog detected hard LOCKUP on cpu %d", this_cpu);
+		}
 
 		__this_cpu_write(hard_watchdog_warn, true);
 		return;
@@ -323,8 +325,10 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		else
 			dump_stack();
 
-		if (softlockup_panic)
+		if (softlockup_panic) {
+			trigger_all_cpu_backtrace();
 			panic("softlockup: hung tasks");
+		}
 		__this_cpu_write(soft_watchdog_warn, true);
 	} else
 		__this_cpu_write(soft_watchdog_warn, false);
diff --git a/lib/Kconfig b/lib/Kconfig
index 1e80cb3c77a9..ea321564b2b7 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -177,6 +177,13 @@ config CRC8
 	  when they need to do cyclic redundancy check according CRC8
 	  algorithm. Module will be called crc8.
 
+config CRC64_ECMA
+	tristate "CRC64 ECMA function"
+	help
+	  This option provides CRC64 ECMA function. Drivers may select this
+	  when they need to do cyclic redundancy check according to the CRC64
+	  ECMA algorithm.
+
 config AUDIT_GENERIC
 	bool
 	depends on AUDIT && !AUDIT_ARCH
diff --git a/lib/Makefile b/lib/Makefile
index 0cd7b68e1382..02da5b614a80 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -69,6 +69,7 @@ obj-$(CONFIG_CRC32)	+= crc32.o
 obj-$(CONFIG_CRC7)	+= crc7.o
 obj-$(CONFIG_LIBCRC32C)	+= libcrc32c.o
 obj-$(CONFIG_CRC8)	+= crc8.o
+obj-$(CONFIG_CRC64_ECMA)	+= crc64_ecma.o
 obj-$(CONFIG_GENERIC_ALLOCATOR) += genalloc.o
 
 obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
diff --git a/lib/clz_ctz.c b/lib/clz_ctz.c
index a8f8379eb49f..2e11e48446ab 100644
--- a/lib/clz_ctz.c
+++ b/lib/clz_ctz.c
@@ -6,6 +6,9 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
+ * The functions in this file aren't called directly, but are required by
+ * GCC builtins such as __builtin_ctz, and therefore they can't be removed
+ * despite appearing unreferenced in kernel source.
  *
  * __c[lt]z[sd]i2 can be overridden by linking arch-specific versions.
  */
@@ -13,18 +16,22 @@
 #include <linux/export.h>
 #include <linux/kernel.h>
 
+int __weak __ctzsi2(int val);
 int __weak __ctzsi2(int val)
 {
 	return __ffs(val);
 }
 EXPORT_SYMBOL(__ctzsi2);
 
+int __weak __clzsi2(int val);
 int __weak __clzsi2(int val)
 {
 	return 32 - fls(val);
 }
 EXPORT_SYMBOL(__clzsi2);
 
+int __weak __clzdi2(long val);
+int __weak __ctzdi2(long val);
 #if BITS_PER_LONG == 32
 
 int __weak __clzdi2(long val)
diff --git a/lib/crc64_ecma.c b/lib/crc64_ecma.c
new file mode 100644
index 000000000000..41629ea5a60c
--- /dev/null
+++ b/lib/crc64_ecma.c
@@ -0,0 +1,341 @@
+/*
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/module.h>
+#include <linux/crc64_ecma.h>
+
+
+#define CRC64_BYTE_MASK			0xFF
+#define CRC64_TABLE_SIZE		256
+
+
+struct crc64_table {
+	u64 seed;
+	u64 table[CRC64_TABLE_SIZE];
+};
+
+
+static struct crc64_table CRC64_ECMA_182 = {
+	CRC64_DEFAULT_INITVAL,
+	{
+		0x0000000000000000ULL,
+		0xb32e4cbe03a75f6fULL,
+		0xf4843657a840a05bULL,
+		0x47aa7ae9abe7ff34ULL,
+		0x7bd0c384ff8f5e33ULL,
+		0xc8fe8f3afc28015cULL,
+		0x8f54f5d357cffe68ULL,
+		0x3c7ab96d5468a107ULL,
+		0xf7a18709ff1ebc66ULL,
+		0x448fcbb7fcb9e309ULL,
+		0x0325b15e575e1c3dULL,
+		0xb00bfde054f94352ULL,
+		0x8c71448d0091e255ULL,
+		0x3f5f08330336bd3aULL,
+		0x78f572daa8d1420eULL,
+		0xcbdb3e64ab761d61ULL,
+		0x7d9ba13851336649ULL,
+		0xceb5ed8652943926ULL,
+		0x891f976ff973c612ULL,
+		0x3a31dbd1fad4997dULL,
+		0x064b62bcaebc387aULL,
+		0xb5652e02ad1b6715ULL,
+		0xf2cf54eb06fc9821ULL,
+		0x41e11855055bc74eULL,
+		0x8a3a2631ae2dda2fULL,
+		0x39146a8fad8a8540ULL,
+		0x7ebe1066066d7a74ULL,
+		0xcd905cd805ca251bULL,
+		0xf1eae5b551a2841cULL,
+		0x42c4a90b5205db73ULL,
+		0x056ed3e2f9e22447ULL,
+		0xb6409f5cfa457b28ULL,
+		0xfb374270a266cc92ULL,
+		0x48190ecea1c193fdULL,
+		0x0fb374270a266cc9ULL,
+		0xbc9d3899098133a6ULL,
+		0x80e781f45de992a1ULL,
+		0x33c9cd4a5e4ecdceULL,
+		0x7463b7a3f5a932faULL,
+		0xc74dfb1df60e6d95ULL,
+		0x0c96c5795d7870f4ULL,
+		0xbfb889c75edf2f9bULL,
+		0xf812f32ef538d0afULL,
+		0x4b3cbf90f69f8fc0ULL,
+		0x774606fda2f72ec7ULL,
+		0xc4684a43a15071a8ULL,
+		0x83c230aa0ab78e9cULL,
+		0x30ec7c140910d1f3ULL,
+		0x86ace348f355aadbULL,
+		0x3582aff6f0f2f5b4ULL,
+		0x7228d51f5b150a80ULL,
+		0xc10699a158b255efULL,
+		0xfd7c20cc0cdaf4e8ULL,
+		0x4e526c720f7dab87ULL,
+		0x09f8169ba49a54b3ULL,
+		0xbad65a25a73d0bdcULL,
+		0x710d64410c4b16bdULL,
+		0xc22328ff0fec49d2ULL,
+		0x85895216a40bb6e6ULL,
+		0x36a71ea8a7ace989ULL,
+		0x0adda7c5f3c4488eULL,
+		0xb9f3eb7bf06317e1ULL,
+		0xfe5991925b84e8d5ULL,
+		0x4d77dd2c5823b7baULL,
+		0x64b62bcaebc387a1ULL,
+		0xd7986774e864d8ceULL,
+		0x90321d9d438327faULL,
+		0x231c512340247895ULL,
+		0x1f66e84e144cd992ULL,
+		0xac48a4f017eb86fdULL,
+		0xebe2de19bc0c79c9ULL,
+		0x58cc92a7bfab26a6ULL,
+		0x9317acc314dd3bc7ULL,
+		0x2039e07d177a64a8ULL,
+		0x67939a94bc9d9b9cULL,
+		0xd4bdd62abf3ac4f3ULL,
+		0xe8c76f47eb5265f4ULL,
+		0x5be923f9e8f53a9bULL,
+		0x1c4359104312c5afULL,
+		0xaf6d15ae40b59ac0ULL,
+		0x192d8af2baf0e1e8ULL,
+		0xaa03c64cb957be87ULL,
+		0xeda9bca512b041b3ULL,
+		0x5e87f01b11171edcULL,
+		0x62fd4976457fbfdbULL,
+		0xd1d305c846d8e0b4ULL,
+		0x96797f21ed3f1f80ULL,
+		0x2557339fee9840efULL,
+		0xee8c0dfb45ee5d8eULL,
+		0x5da24145464902e1ULL,
+		0x1a083bacedaefdd5ULL,
+		0xa9267712ee09a2baULL,
+		0x955cce7fba6103bdULL,
+		0x267282c1b9c65cd2ULL,
+		0x61d8f8281221a3e6ULL,
+		0xd2f6b4961186fc89ULL,
+		0x9f8169ba49a54b33ULL,
+		0x2caf25044a02145cULL,
+		0x6b055fede1e5eb68ULL,
+		0xd82b1353e242b407ULL,
+		0xe451aa3eb62a1500ULL,
+		0x577fe680b58d4a6fULL,
+		0x10d59c691e6ab55bULL,
+		0xa3fbd0d71dcdea34ULL,
+		0x6820eeb3b6bbf755ULL,
+		0xdb0ea20db51ca83aULL,
+		0x9ca4d8e41efb570eULL,
+		0x2f8a945a1d5c0861ULL,
+		0x13f02d374934a966ULL,
+		0xa0de61894a93f609ULL,
+		0xe7741b60e174093dULL,
+		0x545a57dee2d35652ULL,
+		0xe21ac88218962d7aULL,
+		0x5134843c1b317215ULL,
+		0x169efed5b0d68d21ULL,
+		0xa5b0b26bb371d24eULL,
+		0x99ca0b06e7197349ULL,
+		0x2ae447b8e4be2c26ULL,
+		0x6d4e3d514f59d312ULL,
+		0xde6071ef4cfe8c7dULL,
+		0x15bb4f8be788911cULL,
+		0xa6950335e42fce73ULL,
+		0xe13f79dc4fc83147ULL,
+		0x521135624c6f6e28ULL,
+		0x6e6b8c0f1807cf2fULL,
+		0xdd45c0b11ba09040ULL,
+		0x9aefba58b0476f74ULL,
+		0x29c1f6e6b3e0301bULL,
+		0xc96c5795d7870f42ULL,
+		0x7a421b2bd420502dULL,
+		0x3de861c27fc7af19ULL,
+		0x8ec62d7c7c60f076ULL,
+		0xb2bc941128085171ULL,
+		0x0192d8af2baf0e1eULL,
+		0x4638a2468048f12aULL,
+		0xf516eef883efae45ULL,
+		0x3ecdd09c2899b324ULL,
+		0x8de39c222b3eec4bULL,
+		0xca49e6cb80d9137fULL,
+		0x7967aa75837e4c10ULL,
+		0x451d1318d716ed17ULL,
+		0xf6335fa6d4b1b278ULL,
+		0xb199254f7f564d4cULL,
+		0x02b769f17cf11223ULL,
+		0xb4f7f6ad86b4690bULL,
+		0x07d9ba1385133664ULL,
+		0x4073c0fa2ef4c950ULL,
+		0xf35d8c442d53963fULL,
+		0xcf273529793b3738ULL,
+		0x7c0979977a9c6857ULL,
+		0x3ba3037ed17b9763ULL,
+		0x888d4fc0d2dcc80cULL,
+		0x435671a479aad56dULL,
+		0xf0783d1a7a0d8a02ULL,
+		0xb7d247f3d1ea7536ULL,
+		0x04fc0b4dd24d2a59ULL,
+		0x3886b22086258b5eULL,
+		0x8ba8fe9e8582d431ULL,
+		0xcc0284772e652b05ULL,
+		0x7f2cc8c92dc2746aULL,
+		0x325b15e575e1c3d0ULL,
+		0x8175595b76469cbfULL,
+		0xc6df23b2dda1638bULL,
+		0x75f16f0cde063ce4ULL,
+		0x498bd6618a6e9de3ULL,
+		0xfaa59adf89c9c28cULL,
+		0xbd0fe036222e3db8ULL,
+		0x0e21ac88218962d7ULL,
+		0xc5fa92ec8aff7fb6ULL,
+		0x76d4de52895820d9ULL,
+		0x317ea4bb22bfdfedULL,
+		0x8250e80521188082ULL,
+		0xbe2a516875702185ULL,
+		0x0d041dd676d77eeaULL,
+		0x4aae673fdd3081deULL,
+		0xf9802b81de97deb1ULL,
+		0x4fc0b4dd24d2a599ULL,
+		0xfceef8632775faf6ULL,
+		0xbb44828a8c9205c2ULL,
+		0x086ace348f355aadULL,
+		0x34107759db5dfbaaULL,
+		0x873e3be7d8faa4c5ULL,
+		0xc094410e731d5bf1ULL,
+		0x73ba0db070ba049eULL,
+		0xb86133d4dbcc19ffULL,
+		0x0b4f7f6ad86b4690ULL,
+		0x4ce50583738cb9a4ULL,
+		0xffcb493d702be6cbULL,
+		0xc3b1f050244347ccULL,
+		0x709fbcee27e418a3ULL,
+		0x3735c6078c03e797ULL,
+		0x841b8ab98fa4b8f8ULL,
+		0xadda7c5f3c4488e3ULL,
+		0x1ef430e13fe3d78cULL,
+		0x595e4a08940428b8ULL,
+		0xea7006b697a377d7ULL,
+		0xd60abfdbc3cbd6d0ULL,
+		0x6524f365c06c89bfULL,
+		0x228e898c6b8b768bULL,
+		0x91a0c532682c29e4ULL,
+		0x5a7bfb56c35a3485ULL,
+		0xe955b7e8c0fd6beaULL,
+		0xaeffcd016b1a94deULL,
+		0x1dd181bf68bdcbb1ULL,
+		0x21ab38d23cd56ab6ULL,
+		0x9285746c3f7235d9ULL,
+		0xd52f0e859495caedULL,
+		0x6601423b97329582ULL,
+		0xd041dd676d77eeaaULL,
+		0x636f91d96ed0b1c5ULL,
+		0x24c5eb30c5374ef1ULL,
+		0x97eba78ec690119eULL,
+		0xab911ee392f8b099ULL,
+		0x18bf525d915feff6ULL,
+		0x5f1528b43ab810c2ULL,
+		0xec3b640a391f4fadULL,
+		0x27e05a6e926952ccULL,
+		0x94ce16d091ce0da3ULL,
+		0xd3646c393a29f297ULL,
+		0x604a2087398eadf8ULL,
+		0x5c3099ea6de60cffULL,
+		0xef1ed5546e415390ULL,
+		0xa8b4afbdc5a6aca4ULL,
+		0x1b9ae303c601f3cbULL,
+		0x56ed3e2f9e224471ULL,
+		0xe5c372919d851b1eULL,
+		0xa26908783662e42aULL,
+		0x114744c635c5bb45ULL,
+		0x2d3dfdab61ad1a42ULL,
+		0x9e13b115620a452dULL,
+		0xd9b9cbfcc9edba19ULL,
+		0x6a978742ca4ae576ULL,
+		0xa14cb926613cf817ULL,
+		0x1262f598629ba778ULL,
+		0x55c88f71c97c584cULL,
+		0xe6e6c3cfcadb0723ULL,
+		0xda9c7aa29eb3a624ULL,
+		0x69b2361c9d14f94bULL,
+		0x2e184cf536f3067fULL,
+		0x9d36004b35545910ULL,
+		0x2b769f17cf112238ULL,
+		0x9858d3a9ccb67d57ULL,
+		0xdff2a94067518263ULL,
+		0x6cdce5fe64f6dd0cULL,
+		0x50a65c93309e7c0bULL,
+		0xe388102d33392364ULL,
+		0xa4226ac498dedc50ULL,
+		0x170c267a9b79833fULL,
+		0xdcd7181e300f9e5eULL,
+		0x6ff954a033a8c131ULL,
+		0x28532e49984f3e05ULL,
+		0x9b7d62f79be8616aULL,
+		0xa707db9acf80c06dULL,
+		0x14299724cc279f02ULL,
+		0x5383edcd67c06036ULL,
+		0xe0ada17364673f59ULL
+	}
+};
+
+
+/*
+ * crc64_ecma_seed - Initializes the CRC64 ECMA seed.
+ */
+u64 crc64_ecma_seed(void)
+{
+	return CRC64_ECMA_182.seed;
+}
+EXPORT_SYMBOL(crc64_ecma_seed);
+
+/*
+ * crc64_ecma - Computes the 64 bit ECMA CRC.
+ *
+ * pdata: pointer to the data to compute checksum for.
+ * nbytes: number of bytes in data buffer.
+ * seed: CRC seed.
+ */
+u64 crc64_ecma(u8 const *pdata, u32 nbytes, u64 seed)
+{
+	unsigned int i;
+	u64 crc = seed;
+
+	for (i = 0; i < nbytes; i++)
+		crc = CRC64_ECMA_182.table[(crc ^ pdata[i]) & CRC64_BYTE_MASK] ^
+			(crc >> 8);
+
+	return crc;
+}
+EXPORT_SYMBOL(crc64_ecma);
+
+MODULE_DESCRIPTION("CRC64 ECMA function");
+MODULE_AUTHOR("Freescale Semiconductor Inc.");
+MODULE_LICENSE("GPL");
diff --git a/lib/decompress.c b/lib/decompress.c
index 4d1cd0397aab..86069d74c062 100644
--- a/lib/decompress.c
+++ b/lib/decompress.c
@@ -16,6 +16,7 @@
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/init.h>
+#include <linux/printk.h>
 
 #ifndef CONFIG_DECOMPRESS_GZIP
 # define gunzip NULL
@@ -61,6 +62,8 @@ decompress_fn __init decompress_method(const unsigned char *inbuf, int len,
 	if (len < 2)
 		return NULL;	/* Need at least this much... */
 
+	pr_debug("Compressed data magic: %#.2x %#.2x\n", inbuf[0], inbuf[1]);
+
 	for (cf = compressed_formats; cf->name; cf++) {
 		if (!memcmp(inbuf, cf->magic, 2))
 			break;
diff --git a/lib/decompress_inflate.c b/lib/decompress_inflate.c
index d619b28c456f..0edfd742a154 100644
--- a/lib/decompress_inflate.c
+++ b/lib/decompress_inflate.c
@@ -19,6 +19,7 @@
 #include "zlib_inflate/inflate.h"
 
 #include "zlib_inflate/infutil.h"
+#include <linux/decompress/inflate.h>
 
 #endif /* STATIC */
 
diff --git a/lib/devres.c b/lib/devres.c
index 823533138fa0..48cb3c7bd7de 100644
--- a/lib/devres.c
+++ b/lib/devres.c
@@ -81,11 +81,13 @@ EXPORT_SYMBOL(devm_ioremap_nocache);
 void devm_iounmap(struct device *dev, void __iomem *addr)
 {
 	WARN_ON(devres_destroy(dev, devm_ioremap_release, devm_ioremap_match,
-			       (void *)addr));
+			       (__force void *)addr));
 	iounmap(addr);
 }
 EXPORT_SYMBOL(devm_iounmap);
 
+#define IOMEM_ERR_PTR(err) (__force void __iomem *)ERR_PTR(err)
+
 /**
  * devm_ioremap_resource() - check, request region, and ioremap resource
  * @dev: generic device to handle the resource for
@@ -114,7 +116,7 @@ void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res)
 
 	if (!res || resource_type(res) != IORESOURCE_MEM) {
 		dev_err(dev, "invalid resource\n");
-		return ERR_PTR(-EINVAL);
+		return IOMEM_ERR_PTR(-EINVAL);
 	}
 
 	size = resource_size(res);
@@ -122,7 +124,7 @@ void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res)
 
 	if (!devm_request_mem_region(dev, res->start, size, name)) {
 		dev_err(dev, "can't request region for resource %pR\n", res);
-		return ERR_PTR(-EBUSY);
+		return IOMEM_ERR_PTR(-EBUSY);
 	}
 
 	if (res->flags & IORESOURCE_CACHEABLE)
@@ -133,7 +135,7 @@ void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res)
 	if (!dest_ptr) {
 		dev_err(dev, "ioremap failed for resource %pR\n", res);
 		devm_release_mem_region(dev, res->start, size);
-		dest_ptr = ERR_PTR(-ENOMEM);
+		dest_ptr = IOMEM_ERR_PTR(-ENOMEM);
 	}
 
 	return dest_ptr;
@@ -224,7 +226,7 @@ void devm_ioport_unmap(struct device *dev, void __iomem *addr)
 {
 	ioport_unmap(addr);
 	WARN_ON(devres_destroy(dev, devm_ioport_map_release,
-			       devm_ioport_map_match, (void *)addr));
+			       devm_ioport_map_match, (__force void *)addr));
 }
 EXPORT_SYMBOL(devm_ioport_unmap);
 #endif /* CONFIG_HAS_IOPORT */
diff --git a/lib/idr.c b/lib/idr.c
index 1ba4956bfbff..ba2df393c3b0 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -196,7 +196,7 @@ static void idr_mark_full(struct idr_layer **pa, int id)
 	}
 }
 
-int __idr_pre_get(struct idr *idp, gfp_t gfp_mask)
+static int __idr_pre_get(struct idr *idp, gfp_t gfp_mask)
 {
 	while (idp->id_free_cnt < MAX_IDR_FREE) {
 		struct idr_layer *new;
@@ -207,7 +207,6 @@ int __idr_pre_get(struct idr *idp, gfp_t gfp_mask)
 	}
 	return 1;
 }
-EXPORT_SYMBOL(__idr_pre_get);
 
 /**
  * sub_alloc - try to allocate an id without growing the tree depth
@@ -374,20 +373,6 @@ static void idr_fill_slot(struct idr *idr, void *ptr, int id,
 	idr_mark_full(pa, id);
 }
 
-int __idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id)
-{
-	struct idr_layer *pa[MAX_IDR_LEVEL + 1];
-	int rv;
-
-	rv = idr_get_empty_slot(idp, starting_id, pa, 0, idp);
-	if (rv < 0)
-		return rv == -ENOMEM ? -EAGAIN : rv;
-
-	idr_fill_slot(idp, ptr, rv, pa);
-	*id = rv;
-	return 0;
-}
-EXPORT_SYMBOL(__idr_get_new_above);
 
 /**
  * idr_preload - preload for idr_alloc()
@@ -607,7 +592,7 @@ void idr_remove(struct idr *idp, int id)
 }
 EXPORT_SYMBOL(idr_remove);
 
-void __idr_remove_all(struct idr *idp)
+static void __idr_remove_all(struct idr *idp)
 {
 	int n, id, max;
 	int bt_mask;
@@ -640,7 +625,6 @@ void __idr_remove_all(struct idr *idp)
 	}
 	idp->layers = 0;
 }
-EXPORT_SYMBOL(__idr_remove_all);
 
 /**
  * idr_destroy - release all cached layers within an idr tree
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 5f72767ddd9b..4e3bd71bd949 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -124,6 +124,30 @@ static int kobj_usermode_filter(struct kobject *kobj)
 	return 0;
 }
 
+static int init_uevent_argv(struct kobj_uevent_env *env, const char *subsystem)
+{
+	int len;
+
+	len = strlcpy(&env->buf[env->buflen], subsystem,
+		      sizeof(env->buf) - env->buflen);
+	if (len >= (sizeof(env->buf) - env->buflen)) {
+		WARN(1, KERN_ERR "init_uevent_argv: buffer size too small\n");
+		return -ENOMEM;
+	}
+
+	env->argv[0] = uevent_helper;
+	env->argv[1] = &env->buf[env->buflen];
+	env->argv[2] = NULL;
+
+	env->buflen += len + 1;
+	return 0;
+}
+
+static void cleanup_uevent_env(struct subprocess_info *info)
+{
+	kfree(info->data);
+}
+
 /**
  * kobject_uevent_env - send an uevent with environmental data
  *
@@ -301,11 +325,8 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 
 	/* call uevent_helper, usually only enabled during early boot */
 	if (uevent_helper[0] && !kobj_usermode_filter(kobj)) {
-		char *argv [3];
+		struct subprocess_info *info;
 
-		argv [0] = uevent_helper;
-		argv [1] = (char *)subsystem;
-		argv [2] = NULL;
 		retval = add_uevent_var(env, "HOME=/");
 		if (retval)
 			goto exit;
@@ -313,9 +334,18 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 					"PATH=/sbin:/bin:/usr/sbin:/usr/bin");
 		if (retval)
 			goto exit;
+		retval = init_uevent_argv(env, subsystem);
+		if (retval)
+			goto exit;
 
-		retval = call_usermodehelper(argv[0], argv,
-					     env->envp, UMH_WAIT_EXEC);
+		retval = -ENOMEM;
+		info = call_usermodehelper_setup(env->argv[0], env->argv,
+						 env->envp, GFP_KERNEL,
+						 NULL, cleanup_uevent_env, env);
+		if (info) {
+			retval = call_usermodehelper_exec(info, UMH_NO_WAIT);
+			env = NULL;	/* freed by cleanup_uevent_env */
+		}
 	}
 
 exit:
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index bd4a8dfdf0b8..9599aa72d7a0 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -35,33 +35,6 @@
 #include <linux/hardirq.h>		/* in_interrupt() */
 
 
-#ifdef __KERNEL__
-#define RADIX_TREE_MAP_SHIFT	(CONFIG_BASE_SMALL ? 4 : 6)
-#else
-#define RADIX_TREE_MAP_SHIFT	3	/* For more stressful testing */
-#endif
-
-#define RADIX_TREE_MAP_SIZE	(1UL << RADIX_TREE_MAP_SHIFT)
-#define RADIX_TREE_MAP_MASK	(RADIX_TREE_MAP_SIZE-1)
-
-#define RADIX_TREE_TAG_LONGS	\
-	((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG)
-
-struct radix_tree_node {
-	unsigned int	height;		/* Height from the bottom */
-	unsigned int	count;
-	union {
-		struct radix_tree_node *parent;	/* Used when ascending tree */
-		struct rcu_head	rcu_head;	/* Used when freeing node */
-	};
-	void __rcu	*slots[RADIX_TREE_MAP_SIZE];
-	unsigned long	tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
-};
-
-#define RADIX_TREE_INDEX_BITS  (8 /* CHAR_BIT */ * sizeof(unsigned long))
-#define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \
-					  RADIX_TREE_MAP_SHIFT))
-
 /*
  * The height_to_maxindex array needs to be one deeper than the maximum
  * path as height 0 holds only 1 entry.
@@ -369,7 +342,8 @@ static int radix_tree_extend(struct radix_tree_root *root, unsigned long index)
 
 		/* Increase the height.  */
 		newheight = root->height+1;
-		node->height = newheight;
+		BUG_ON(newheight & ~RADIX_TREE_HEIGHT_MASK);
+		node->path = newheight;
 		node->count = 1;
 		node->parent = NULL;
 		slot = root->rnode;
@@ -387,23 +361,28 @@ out:
 }
 
 /**
- *	radix_tree_insert    -    insert into a radix tree
+ *	__radix_tree_create	-	create a slot in a radix tree
  *	@root:		radix tree root
  *	@index:		index key
- *	@item:		item to insert
+ *	@nodep:		returns node
+ *	@slotp:		returns slot
  *
- *	Insert an item into the radix tree at position @index.
+ *	Create, if necessary, and return the node and slot for an item
+ *	at position @index in the radix tree @root.
+ *
+ *	Until there is more than one item in the tree, no nodes are
+ *	allocated and @root->rnode is used as a direct slot instead of
+ *	pointing to a node, in which case *@nodep will be NULL.
+ *
+ *	Returns -ENOMEM, or 0 for success.
  */
-int radix_tree_insert(struct radix_tree_root *root,
-			unsigned long index, void *item)
+int __radix_tree_create(struct radix_tree_root *root, unsigned long index,
+			struct radix_tree_node **nodep, void ***slotp)
 {
 	struct radix_tree_node *node = NULL, *slot;
-	unsigned int height, shift;
-	int offset;
+	unsigned int height, shift, offset;
 	int error;
 
-	BUG_ON(radix_tree_is_indirect_ptr(item));
-
 	/* Make sure the tree is high enough.  */
 	if (index > radix_tree_maxindex(root->height)) {
 		error = radix_tree_extend(root, index);
@@ -422,11 +401,12 @@ int radix_tree_insert(struct radix_tree_root *root,
 			/* Have to add a child node.  */
 			if (!(slot = radix_tree_node_alloc(root)))
 				return -ENOMEM;
-			slot->height = height;
+			slot->path = height;
 			slot->parent = node;
 			if (node) {
 				rcu_assign_pointer(node->slots[offset], slot);
 				node->count++;
+				slot->path |= offset << RADIX_TREE_HEIGHT_SHIFT;
 			} else
 				rcu_assign_pointer(root->rnode, ptr_to_indirect(slot));
 		}
@@ -439,16 +419,42 @@ int radix_tree_insert(struct radix_tree_root *root,
 		height--;
 	}
 
-	if (slot != NULL)
+	if (nodep)
+		*nodep = node;
+	if (slotp)
+		*slotp = node ? node->slots + offset : (void **)&root->rnode;
+	return 0;
+}
+
+/**
+ *	radix_tree_insert    -    insert into a radix tree
+ *	@root:		radix tree root
+ *	@index:		index key
+ *	@item:		item to insert
+ *
+ *	Insert an item into the radix tree at position @index.
+ */
+int radix_tree_insert(struct radix_tree_root *root,
+			unsigned long index, void *item)
+{
+	struct radix_tree_node *node;
+	void **slot;
+	int error;
+
+	BUG_ON(radix_tree_is_indirect_ptr(item));
+
+	error = __radix_tree_create(root, index, &node, &slot);
+	if (error)
+		return error;
+	if (*slot != NULL)
 		return -EEXIST;
+	rcu_assign_pointer(*slot, item);
 
 	if (node) {
 		node->count++;
-		rcu_assign_pointer(node->slots[offset], item);
-		BUG_ON(tag_get(node, 0, offset));
-		BUG_ON(tag_get(node, 1, offset));
+		BUG_ON(tag_get(node, 0, index & RADIX_TREE_MAP_MASK));
+		BUG_ON(tag_get(node, 1, index & RADIX_TREE_MAP_MASK));
 	} else {
-		rcu_assign_pointer(root->rnode, item);
 		BUG_ON(root_tag_get(root, 0));
 		BUG_ON(root_tag_get(root, 1));
 	}
@@ -457,15 +463,26 @@ int radix_tree_insert(struct radix_tree_root *root,
 }
 EXPORT_SYMBOL(radix_tree_insert);
 
-/*
- * is_slot == 1 : search for the slot.
- * is_slot == 0 : search for the node.
+/**
+ *	__radix_tree_lookup	-	lookup an item in a radix tree
+ *	@root:		radix tree root
+ *	@index:		index key
+ *	@nodep:		returns node
+ *	@slotp:		returns slot
+ *
+ *	Lookup and return the item at position @index in the radix
+ *	tree @root.
+ *
+ *	Until there is more than one item in the tree, no nodes are
+ *	allocated and @root->rnode is used as a direct slot instead of
+ *	pointing to a node, in which case *@nodep will be NULL.
  */
-static void *radix_tree_lookup_element(struct radix_tree_root *root,
-				unsigned long index, int is_slot)
+void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index,
+			  struct radix_tree_node **nodep, void ***slotp)
 {
+	struct radix_tree_node *node, *parent;
 	unsigned int height, shift;
-	struct radix_tree_node *node, **slot;
+	void **slot;
 
 	node = rcu_dereference_raw(root->rnode);
 	if (node == NULL)
@@ -474,19 +491,24 @@ static void *radix_tree_lookup_element(struct radix_tree_root *root,
 	if (!radix_tree_is_indirect_ptr(node)) {
 		if (index > 0)
 			return NULL;
-		return is_slot ? (void *)&root->rnode : node;
+
+		if (nodep)
+			*nodep = NULL;
+		if (slotp)
+			*slotp = (void **)&root->rnode;
+		return node;
 	}
 	node = indirect_to_ptr(node);
 
-	height = node->height;
+	height = node->path & RADIX_TREE_HEIGHT_MASK;
 	if (index > radix_tree_maxindex(height))
 		return NULL;
 
 	shift = (height-1) * RADIX_TREE_MAP_SHIFT;
 
 	do {
-		slot = (struct radix_tree_node **)
-			(node->slots + ((index>>shift) & RADIX_TREE_MAP_MASK));
+		parent = node;
+		slot = node->slots + ((index >> shift) & RADIX_TREE_MAP_MASK);
 		node = rcu_dereference_raw(*slot);
 		if (node == NULL)
 			return NULL;
@@ -495,7 +517,11 @@ static void *radix_tree_lookup_element(struct radix_tree_root *root,
 		height--;
 	} while (height > 0);
 
-	return is_slot ? (void *)slot : indirect_to_ptr(node);
+	if (nodep)
+		*nodep = parent;
+	if (slotp)
+		*slotp = slot;
+	return node;
 }
 
 /**
@@ -513,7 +539,11 @@ static void *radix_tree_lookup_element(struct radix_tree_root *root,
  */
 void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index)
 {
-	return (void **)radix_tree_lookup_element(root, index, 1);
+	void **slot;
+
+	if (!__radix_tree_lookup(root, index, NULL, &slot))
+		return NULL;
+	return slot;
 }
 EXPORT_SYMBOL(radix_tree_lookup_slot);
 
@@ -531,7 +561,7 @@ EXPORT_SYMBOL(radix_tree_lookup_slot);
  */
 void *radix_tree_lookup(struct radix_tree_root *root, unsigned long index)
 {
-	return radix_tree_lookup_element(root, index, 0);
+	return __radix_tree_lookup(root, index, NULL, NULL);
 }
 EXPORT_SYMBOL(radix_tree_lookup);
 
@@ -676,7 +706,7 @@ int radix_tree_tag_get(struct radix_tree_root *root,
 		return (index == 0);
 	node = indirect_to_ptr(node);
 
-	height = node->height;
+	height = node->path & RADIX_TREE_HEIGHT_MASK;
 	if (index > radix_tree_maxindex(height))
 		return 0;
 
@@ -713,7 +743,7 @@ void **radix_tree_next_chunk(struct radix_tree_root *root,
 {
 	unsigned shift, tag = flags & RADIX_TREE_ITER_TAG_MASK;
 	struct radix_tree_node *rnode, *node;
-	unsigned long index, offset;
+	unsigned long index, offset, height;
 
 	if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag))
 		return NULL;
@@ -744,7 +774,8 @@ void **radix_tree_next_chunk(struct radix_tree_root *root,
 		return NULL;
 
 restart:
-	shift = (rnode->height - 1) * RADIX_TREE_MAP_SHIFT;
+	height = rnode->path & RADIX_TREE_HEIGHT_MASK;
+	shift = (height - 1) * RADIX_TREE_MAP_SHIFT;
 	offset = index >> shift;
 
 	/* Index outside of the tree */
@@ -946,81 +977,6 @@ next:
 }
 EXPORT_SYMBOL(radix_tree_range_tag_if_tagged);
 
-
-/**
- *	radix_tree_next_hole    -    find the next hole (not-present entry)
- *	@root:		tree root
- *	@index:		index key
- *	@max_scan:	maximum range to search
- *
- *	Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the lowest
- *	indexed hole.
- *
- *	Returns: the index of the hole if found, otherwise returns an index
- *	outside of the set specified (in which case 'return - index >= max_scan'
- *	will be true). In rare cases of index wrap-around, 0 will be returned.
- *
- *	radix_tree_next_hole may be called under rcu_read_lock. However, like
- *	radix_tree_gang_lookup, this will not atomically search a snapshot of
- *	the tree at a single point in time. For example, if a hole is created
- *	at index 5, then subsequently a hole is created at index 10,
- *	radix_tree_next_hole covering both indexes may return 10 if called
- *	under rcu_read_lock.
- */
-unsigned long radix_tree_next_hole(struct radix_tree_root *root,
-				unsigned long index, unsigned long max_scan)
-{
-	unsigned long i;
-
-	for (i = 0; i < max_scan; i++) {
-		if (!radix_tree_lookup(root, index))
-			break;
-		index++;
-		if (index == 0)
-			break;
-	}
-
-	return index;
-}
-EXPORT_SYMBOL(radix_tree_next_hole);
-
-/**
- *	radix_tree_prev_hole    -    find the prev hole (not-present entry)
- *	@root:		tree root
- *	@index:		index key
- *	@max_scan:	maximum range to search
- *
- *	Search backwards in the range [max(index-max_scan+1, 0), index]
- *	for the first hole.
- *
- *	Returns: the index of the hole if found, otherwise returns an index
- *	outside of the set specified (in which case 'index - return >= max_scan'
- *	will be true). In rare cases of wrap-around, ULONG_MAX will be returned.
- *
- *	radix_tree_next_hole may be called under rcu_read_lock. However, like
- *	radix_tree_gang_lookup, this will not atomically search a snapshot of
- *	the tree at a single point in time. For example, if a hole is created
- *	at index 10, then subsequently a hole is created at index 5,
- *	radix_tree_prev_hole covering both indexes may return 5 if called under
- *	rcu_read_lock.
- */
-unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
-				   unsigned long index, unsigned long max_scan)
-{
-	unsigned long i;
-
-	for (i = 0; i < max_scan; i++) {
-		if (!radix_tree_lookup(root, index))
-			break;
-		index--;
-		if (index == ULONG_MAX)
-			break;
-	}
-
-	return index;
-}
-EXPORT_SYMBOL(radix_tree_prev_hole);
-
 /**
  *	radix_tree_gang_lookup - perform multiple lookup on a radix tree
  *	@root:		radix tree root
@@ -1189,7 +1145,7 @@ static unsigned long __locate(struct radix_tree_node *slot, void *item,
 	unsigned int shift, height;
 	unsigned long i;
 
-	height = slot->height;
+	height = slot->path & RADIX_TREE_HEIGHT_MASK;
 	shift = (height-1) * RADIX_TREE_MAP_SHIFT;
 
 	for ( ; height > 1; height--) {
@@ -1252,7 +1208,8 @@ unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item)
 		}
 
 		node = indirect_to_ptr(node);
-		max_index = radix_tree_maxindex(node->height);
+		max_index = radix_tree_maxindex(node->path &
+						RADIX_TREE_HEIGHT_MASK);
 		if (cur_index > max_index) {
 			rcu_read_unlock();
 			break;
@@ -1337,48 +1294,90 @@ static inline void radix_tree_shrink(struct radix_tree_root *root)
 }
 
 /**
- *	radix_tree_delete    -    delete an item from a radix tree
+ *	__radix_tree_delete_node    -    try to free node after clearing a slot
  *	@root:		radix tree root
  *	@index:		index key
+ *	@node:		node containing @index
  *
- *	Remove the item at @index from the radix tree rooted at @root.
+ *	After clearing the slot at @index in @node from radix tree
+ *	rooted at @root, call this function to attempt freeing the
+ *	node and shrinking the tree.
  *
- *	Returns the address of the deleted item, or NULL if it was not present.
+ *	Returns %true if @node was freed, %false otherwise.
  */
-void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
+bool __radix_tree_delete_node(struct radix_tree_root *root,
+			      struct radix_tree_node *node)
 {
-	struct radix_tree_node *node = NULL;
-	struct radix_tree_node *slot = NULL;
-	struct radix_tree_node *to_free;
-	unsigned int height, shift;
+	bool deleted = false;
+
+	do {
+		struct radix_tree_node *parent;
+
+		if (node->count) {
+			if (node == indirect_to_ptr(root->rnode)) {
+				radix_tree_shrink(root);
+				if (root->height == 0)
+					deleted = true;
+			}
+			return deleted;
+		}
+
+		parent = node->parent;
+		if (parent) {
+			unsigned int offset;
+
+			offset = node->path >> RADIX_TREE_HEIGHT_SHIFT;
+			parent->slots[offset] = NULL;
+			parent->count--;
+		} else {
+			root_tag_clear_all(root);
+			root->height = 0;
+			root->rnode = NULL;
+		}
+
+		radix_tree_node_free(node);
+		deleted = true;
+
+		node = parent;
+	} while (node);
+
+	return deleted;
+}
+
+/**
+ *	radix_tree_delete_item    -    delete an item from a radix tree
+ *	@root:		radix tree root
+ *	@index:		index key
+ *	@item:		expected item
+ *
+ *	Remove @item at @index from the radix tree rooted at @root.
+ *
+ *	Returns the address of the deleted item, or NULL if it was not present
+ *	or the entry at the given @index was not @item.
+ */
+void *radix_tree_delete_item(struct radix_tree_root *root,
+			     unsigned long index, void *item)
+{
+	struct radix_tree_node *node;
+	unsigned int offset;
+	void **slot;
+	void *entry;
 	int tag;
-	int uninitialized_var(offset);
 
-	height = root->height;
-	if (index > radix_tree_maxindex(height))
-		goto out;
+	entry = __radix_tree_lookup(root, index, &node, &slot);
+	if (!entry)
+		return NULL;
 
-	slot = root->rnode;
-	if (height == 0) {
+	if (item && entry != item)
+		return NULL;
+
+	if (!node) {
 		root_tag_clear_all(root);
 		root->rnode = NULL;
-		goto out;
+		return entry;
 	}
-	slot = indirect_to_ptr(slot);
-	shift = height * RADIX_TREE_MAP_SHIFT;
 
-	do {
-		if (slot == NULL)
-			goto out;
-
-		shift -= RADIX_TREE_MAP_SHIFT;
-		offset = (index >> shift) & RADIX_TREE_MAP_MASK;
-		node = slot;
-		slot = slot->slots[offset];
-	} while (shift);
-
-	if (slot == NULL)
-		goto out;
+	offset = index & RADIX_TREE_MAP_MASK;
 
 	/*
 	 * Clear all tags associated with the item to be deleted.
@@ -1389,40 +1388,27 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
 			radix_tree_tag_clear(root, index, tag);
 	}
 
-	to_free = NULL;
-	/* Now free the nodes we do not need anymore */
-	while (node) {
-		node->slots[offset] = NULL;
-		node->count--;
-		/*
-		 * Queue the node for deferred freeing after the
-		 * last reference to it disappears (set NULL, above).
-		 */
-		if (to_free)
-			radix_tree_node_free(to_free);
-
-		if (node->count) {
-			if (node == indirect_to_ptr(root->rnode))
-				radix_tree_shrink(root);
-			goto out;
-		}
+	node->slots[offset] = NULL;
+	node->count--;
 
-		/* Node with zero slots in use so free it */
-		to_free = node;
+	__radix_tree_delete_node(root, node);
 
-		index >>= RADIX_TREE_MAP_SHIFT;
-		offset = index & RADIX_TREE_MAP_MASK;
-		node = node->parent;
-	}
-
-	root_tag_clear_all(root);
-	root->height = 0;
-	root->rnode = NULL;
-	if (to_free)
-		radix_tree_node_free(to_free);
+	return entry;
+}
+EXPORT_SYMBOL(radix_tree_delete_item);
 
-out:
-	return slot;
+/**
+ *	radix_tree_delete    -    delete an item from a radix tree
+ *	@root:		radix tree root
+ *	@index:		index key
+ *
+ *	Remove the item at @index from the radix tree rooted at @root.
+ *
+ *	Returns the address of the deleted item, or NULL if it was not present.
+ */
+void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
+{
+	return radix_tree_delete_item(root, index, NULL);
 }
 EXPORT_SYMBOL(radix_tree_delete);
 
@@ -1438,9 +1424,12 @@ int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag)
 EXPORT_SYMBOL(radix_tree_tagged);
 
 static void
-radix_tree_node_ctor(void *node)
+radix_tree_node_ctor(void *arg)
 {
-	memset(node, 0, sizeof(struct radix_tree_node));
+	struct radix_tree_node *node = arg;
+
+	memset(node, 0, sizeof(*node));
+	INIT_LIST_HEAD(&node->private_list);
 }
 
 static __init unsigned long __maxindex(unsigned int height)
diff --git a/lib/random32.c b/lib/random32.c
index 614896778700..fa5da61ce7ad 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -1,37 +1,35 @@
 /*
-  This is a maximally equidistributed combined Tausworthe generator
-  based on code from GNU Scientific Library 1.5 (30 Jun 2004)
-
-  lfsr113 version:
-
-   x_n = (s1_n ^ s2_n ^ s3_n ^ s4_n)
-
-   s1_{n+1} = (((s1_n & 4294967294) << 18) ^ (((s1_n <<  6) ^ s1_n) >> 13))
-   s2_{n+1} = (((s2_n & 4294967288) <<  2) ^ (((s2_n <<  2) ^ s2_n) >> 27))
-   s3_{n+1} = (((s3_n & 4294967280) <<  7) ^ (((s3_n << 13) ^ s3_n) >> 21))
-   s4_{n+1} = (((s4_n & 4294967168) << 13) ^ (((s4_n <<  3) ^ s4_n) >> 12))
-
-   The period of this generator is about 2^113 (see erratum paper).
-
-   From: P. L'Ecuyer, "Maximally Equidistributed Combined Tausworthe
-   Generators", Mathematics of Computation, 65, 213 (1996), 203--213:
-   http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme.ps
-   ftp://ftp.iro.umontreal.ca/pub/simulation/lecuyer/papers/tausme.ps
-
-   There is an erratum in the paper "Tables of Maximally
-   Equidistributed Combined LFSR Generators", Mathematics of
-   Computation, 68, 225 (1999), 261--269:
-   http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme2.ps
-
-        ... the k_j most significant bits of z_j must be non-
-        zero, for each j. (Note: this restriction also applies to the
-        computer code given in [4], but was mistakenly not mentioned in
-        that paper.)
-
-   This affects the seeding procedure by imposing the requirement
-   s1 > 1, s2 > 7, s3 > 15, s4 > 127.
-
-*/
+ * This is a maximally equidistributed combined Tausworthe generator
+ * based on code from GNU Scientific Library 1.5 (30 Jun 2004)
+ *
+ * lfsr113 version:
+ *
+ * x_n = (s1_n ^ s2_n ^ s3_n ^ s4_n)
+ *
+ * s1_{n+1} = (((s1_n & 4294967294) << 18) ^ (((s1_n <<  6) ^ s1_n) >> 13))
+ * s2_{n+1} = (((s2_n & 4294967288) <<  2) ^ (((s2_n <<  2) ^ s2_n) >> 27))
+ * s3_{n+1} = (((s3_n & 4294967280) <<  7) ^ (((s3_n << 13) ^ s3_n) >> 21))
+ * s4_{n+1} = (((s4_n & 4294967168) << 13) ^ (((s4_n <<  3) ^ s4_n) >> 12))
+ *
+ * The period of this generator is about 2^113 (see erratum paper).
+ *
+ * From: P. L'Ecuyer, "Maximally Equidistributed Combined Tausworthe
+ * Generators", Mathematics of Computation, 65, 213 (1996), 203--213:
+ * http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme.ps
+ * ftp://ftp.iro.umontreal.ca/pub/simulation/lecuyer/papers/tausme.ps
+ *
+ * There is an erratum in the paper "Tables of Maximally Equidistributed
+ * Combined LFSR Generators", Mathematics of Computation, 68, 225 (1999),
+ * 261--269: http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme2.ps
+ *
+ *      ... the k_j most significant bits of z_j must be non-zero,
+ *      for each j. (Note: this restriction also applies to the
+ *      computer code given in [4], but was mistakenly not mentioned
+ *      in that paper.)
+ *
+ * This affects the seeding procedure by imposing the requirement
+ * s1 > 1, s2 > 7, s3 > 15, s4 > 127.
+ */
 
 #include <linux/types.h>
 #include <linux/percpu.h>
@@ -75,15 +73,17 @@ EXPORT_SYMBOL(prandom_u32_state);
  */
 u32 prandom_u32(void)
 {
-	unsigned long r;
 	struct rnd_state *state = &get_cpu_var(net_rand_state);
-	r = prandom_u32_state(state);
+	u32 res;
+
+	res = prandom_u32_state(state);
 	put_cpu_var(state);
-	return r;
+
+	return res;
 }
 EXPORT_SYMBOL(prandom_u32);
 
-/*
+/**
  *	prandom_bytes_state - get the requested number of pseudo-random bytes
  *
  *	@state: pointer to state structure holding seeded state.
@@ -204,6 +204,7 @@ static int __init prandom_init(void)
 		prandom_seed_very_weak(state, (i + jiffies) ^ random_get_entropy());
 		prandom_warmup(state);
 	}
+
 	return 0;
 }
 core_initcall(prandom_init);
@@ -259,6 +260,7 @@ static void __prandom_reseed(bool late)
 
 	if (latch && !late)
 		goto out;
+
 	latch = true;
 
 	for_each_possible_cpu(i) {
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 5e2cf6f342f8..e30d885d9631 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -364,7 +364,6 @@ enum format_type {
 	FORMAT_TYPE_SHORT,
 	FORMAT_TYPE_UINT,
 	FORMAT_TYPE_INT,
-	FORMAT_TYPE_NRCHARS,
 	FORMAT_TYPE_SIZE_T,
 	FORMAT_TYPE_PTRDIFF
 };
@@ -1184,6 +1183,21 @@ char *address_val(char *buf, char *end, const void *addr,
 	return number(buf, end, num, spec);
 }
 
+static noinline_for_stack
+char *comm_name(char *buf, char *end, struct task_struct *tsk,
+		struct printf_spec spec, const char *fmt)
+{
+	char name[TASK_COMM_LEN];
+
+	/* Caller can pass NULL instead of current. */
+	if (!tsk)
+		tsk = current;
+	/* Not using get_task_comm() in case I'm in IRQ context. */
+	memcpy(name, tsk->comm, TASK_COMM_LEN);
+	name[sizeof(name) - 1] = '\0';
+	return string(buf, end, name, spec);
+}
+
 int kptr_restrict __read_mostly;
 
 /*
@@ -1251,6 +1265,7 @@ int kptr_restrict __read_mostly;
  *           (default assumed to be phys_addr_t, passed by reference)
  * - 'd[234]' For a dentry name (optionally 2-4 last components)
  * - 'D[234]' Same as 'd' but for a struct file
+ * - 'T' task_struct->comm
  *
  * Note: The difference between 'S' and 'F' is that on ia64 and ppc64
  * function pointers are really function descriptors, which contain a
@@ -1262,7 +1277,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 {
 	int default_width = 2 * sizeof(void *) + (spec.flags & SPECIAL ? 2 : 0);
 
-	if (!ptr && *fmt != 'K') {
+	if (!ptr && *fmt != 'K' && *fmt != 'T') {
 		/*
 		 * Print (null) with the same width as a pointer so it makes
 		 * tabular output look nice.
@@ -1390,6 +1405,8 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 		return dentry_name(buf, end,
 				   ((const struct file *)ptr)->f_path.dentry,
 				   spec, fmt);
+	case 'T':
+		return comm_name(buf, end, ptr, spec, fmt);
 	}
 	spec.flags |= SMALL;
 	if (spec.field_width == -1) {
@@ -1538,10 +1555,6 @@ qualifier:
 		return fmt - start;
 		/* skip alnum */
 
-	case 'n':
-		spec->type = FORMAT_TYPE_NRCHARS;
-		return ++fmt - start;
-
 	case '%':
 		spec->type = FORMAT_TYPE_PERCENT_CHAR;
 		return ++fmt - start;
@@ -1564,6 +1577,15 @@ qualifier:
 	case 'u':
 		break;
 
+	case 'n':
+		/*
+		 * Since %n poses a greater security risk than utility, treat
+		 * it as an invalid format specifier. Warn about its use so
+		 * that new instances don't get added.
+		 */
+		WARN_ONCE(1, "Please remove ignored %%n in '%s'\n", fmt);
+		/* Fall-through */
+
 	default:
 		spec->type = FORMAT_TYPE_INVALID;
 		return fmt - start;
@@ -1737,20 +1759,6 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args)
 			++str;
 			break;
 
-		case FORMAT_TYPE_NRCHARS: {
-			/*
-			 * Since %n poses a greater security risk than
-			 * utility, ignore %n and skip its argument.
-			 */
-			void *skip_arg;
-
-			WARN_ONCE(1, "Please remove ignored %%n in '%s'\n",
-					old_fmt);
-
-			skip_arg = va_arg(args, void *);
-			break;
-		}
-
 		default:
 			switch (spec.type) {
 			case FORMAT_TYPE_LONG_LONG:
@@ -2025,19 +2033,6 @@ do {									\
 				fmt++;
 			break;
 
-		case FORMAT_TYPE_NRCHARS: {
-			/* skip %n 's argument */
-			u8 qualifier = spec.qualifier;
-			void *skip_arg;
-			if (qualifier == 'l')
-				skip_arg = va_arg(args, long *);
-			else if (_tolower(qualifier) == 'z')
-				skip_arg = va_arg(args, size_t *);
-			else
-				skip_arg = va_arg(args, int *);
-			break;
-		}
-
 		default:
 			switch (spec.type) {
 
@@ -2196,10 +2191,6 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf)
 			++str;
 			break;
 
-		case FORMAT_TYPE_NRCHARS:
-			/* skip */
-			break;
-
 		default: {
 			unsigned long long num;
 
diff --git a/lib/xz/Kconfig b/lib/xz/Kconfig
index 08837db52d94..12d2d777f36b 100644
--- a/lib/xz/Kconfig
+++ b/lib/xz/Kconfig
@@ -9,33 +9,33 @@ config XZ_DEC
 if XZ_DEC
 
 config XZ_DEC_X86
-	bool "x86 BCJ filter decoder"
-	default y if X86
+	bool "x86 BCJ filter decoder" if EXPERT
+	default y
 	select XZ_DEC_BCJ
 
 config XZ_DEC_POWERPC
-	bool "PowerPC BCJ filter decoder"
-	default y if PPC
+	bool "PowerPC BCJ filter decoder" if EXPERT
+	default y
 	select XZ_DEC_BCJ
 
 config XZ_DEC_IA64
-	bool "IA-64 BCJ filter decoder"
-	default y if IA64
+	bool "IA-64 BCJ filter decoder" if EXPERT
+	default y
 	select XZ_DEC_BCJ
 
 config XZ_DEC_ARM
-	bool "ARM BCJ filter decoder"
-	default y if ARM
+	bool "ARM BCJ filter decoder" if EXPERT
+	default y
 	select XZ_DEC_BCJ
 
 config XZ_DEC_ARMTHUMB
-	bool "ARM-Thumb BCJ filter decoder"
-	default y if (ARM && ARM_THUMB)
+	bool "ARM-Thumb BCJ filter decoder" if EXPERT
+	default y
 	select XZ_DEC_BCJ
 
 config XZ_DEC_SPARC
-	bool "SPARC BCJ filter decoder"
-	default y if SPARC
+	bool "SPARC BCJ filter decoder" if EXPERT
+	default y
 	select XZ_DEC_BCJ
 
 endif
diff --git a/mm/Kconfig b/mm/Kconfig
index 2888024e0b0a..37fbe1ef5239 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -216,6 +216,7 @@ config PAGEFLAGS_EXTENDED
 #
 config SPLIT_PTLOCK_CPUS
 	int
+	default "999999" if !MMU
 	default "999999" if ARM && !CPU_CACHE_VIPT
 	default "999999" if PARISC && !PA20
 	default "4"
diff --git a/mm/Makefile b/mm/Makefile
index 310c90a09264..23a6f7e23019 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -16,8 +16,8 @@ obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   util.o mmzone.o vmstat.o backing-dev.o \
 			   mm_init.o mmu_context.o percpu.o slab_common.o \
-			   compaction.o balloon_compaction.o \
-			   interval_tree.o list_lru.o $(mmu-y)
+			   compaction.o balloon_compaction.o vmacache.o \
+			   interval_tree.o list_lru.o workingset.o $(mmu-y)
 
 obj-y += init-mm.o
 
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index ce682f7a4f29..09d9591b7708 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -288,13 +288,19 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi)
  * Note, we wouldn't bother setting up the timer, but this function is on the
  * fast-path (used by '__mark_inode_dirty()'), so we save few context switches
  * by delaying the wake-up.
+ *
+ * We have to be careful not to postpone flush work if it is scheduled for
+ * earlier. Thus we use queue_delayed_work().
  */
 void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi)
 {
 	unsigned long timeout;
 
 	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
-	mod_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
+	spin_lock_bh(&bdi->wb_lock);
+	if (test_bit(BDI_registered, &bdi->state))
+		queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
+	spin_unlock_bh(&bdi->wb_lock);
 }
 
 /*
@@ -307,9 +313,6 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi)
 	spin_unlock_bh(&bdi_lock);
 
 	synchronize_rcu_expedited();
-
-	/* bdi_list is now unused, clear it to mark @bdi dying */
-	INIT_LIST_HEAD(&bdi->bdi_list);
 }
 
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
@@ -360,6 +363,11 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 	 */
 	bdi_remove_from_list(bdi);
 
+	/* Make sure nobody queues further work */
+	spin_lock_bh(&bdi->wb_lock);
+	clear_bit(BDI_registered, &bdi->state);
+	spin_unlock_bh(&bdi->wb_lock);
+
 	/*
 	 * Drain work list and shutdown the delayed_work.  At this point,
 	 * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi
diff --git a/mm/compaction.c b/mm/compaction.c
index 918577595ea8..9635083cd8ec 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -217,21 +217,12 @@ static inline bool compact_trylock_irqsave(spinlock_t *lock,
 /* Returns true if the page is within a block suitable for migration to */
 static bool suitable_migration_target(struct page *page)
 {
-	int migratetype = get_pageblock_migratetype(page);
-
-	/* Don't interfere with memory hot-remove or the min_free_kbytes blocks */
-	if (migratetype == MIGRATE_RESERVE)
-		return false;
-
-	if (is_migrate_isolate(migratetype))
-		return false;
-
-	/* If the page is a large free page, then allow migration */
+	/* If the page is a large free page, then disallow migration */
 	if (PageBuddy(page) && page_order(page) >= pageblock_order)
-		return true;
+		return false;
 
 	/* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */
-	if (migrate_async_suitable(migratetype))
+	if (migrate_async_suitable(get_pageblock_migratetype(page)))
 		return true;
 
 	/* Otherwise skip the block */
@@ -253,6 +244,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 	struct page *cursor, *valid_page = NULL;
 	unsigned long flags;
 	bool locked = false;
+	bool checked_pageblock = false;
 
 	cursor = pfn_to_page(blockpfn);
 
@@ -284,8 +276,16 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 			break;
 
 		/* Recheck this is a suitable migration target under lock */
-		if (!strict && !suitable_migration_target(page))
-			break;
+		if (!strict && !checked_pageblock) {
+			/*
+			 * We need to check suitability of pageblock only once
+			 * and this isolate_freepages_block() is called with
+			 * pageblock range, so just check once is sufficient.
+			 */
+			checked_pageblock = true;
+			if (!suitable_migration_target(page))
+				break;
+		}
 
 		/* Recheck this is a buddy page under lock */
 		if (!PageBuddy(page))
@@ -293,14 +293,14 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
 		/* Found a free page, break it into order-0 pages */
 		isolated = split_free_page(page);
-		total_isolated += isolated;
-		for (i = 0; i < isolated; i++) {
-			list_add(&page->lru, freelist);
-			page++;
-		}
-
-		/* If a page was split, advance to the end of it */
 		if (isolated) {
+			total_isolated += isolated;
+			for (i = 0; i < isolated; i++) {
+				list_add(&page->lru, freelist);
+				page++;
+			}
+
+			/* If a page was split, advance to the end of it */
 			blockpfn += isolated - 1;
 			cursor += isolated - 1;
 			continue;
@@ -309,9 +309,6 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 isolate_fail:
 		if (strict)
 			break;
-		else
-			continue;
-
 	}
 
 	trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
@@ -460,12 +457,13 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 	unsigned long last_pageblock_nr = 0, pageblock_nr;
 	unsigned long nr_scanned = 0, nr_isolated = 0;
 	struct list_head *migratelist = &cc->migratepages;
-	isolate_mode_t mode = 0;
 	struct lruvec *lruvec;
 	unsigned long flags;
 	bool locked = false;
 	struct page *page = NULL, *valid_page = NULL;
 	bool skipped_async_unsuitable = false;
+	const isolate_mode_t mode = (!cc->sync ? ISOLATE_ASYNC_MIGRATE : 0) |
+				    (unevictable ? ISOLATE_UNEVICTABLE : 0);
 
 	/*
 	 * Ensure that there are not too many pages isolated from the LRU
@@ -487,7 +485,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 	cond_resched();
 	for (; low_pfn < end_pfn; low_pfn++) {
 		/* give a chance to irqs before checking need_resched() */
-		if (locked && !((low_pfn+1) % SWAP_CLUSTER_MAX)) {
+		if (locked && !(low_pfn % SWAP_CLUSTER_MAX)) {
 			if (should_release_lock(&zone->lru_lock)) {
 				spin_unlock_irqrestore(&zone->lru_lock, flags);
 				locked = false;
@@ -526,8 +524,25 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 
 		/* If isolation recently failed, do not retry */
 		pageblock_nr = low_pfn >> pageblock_order;
-		if (!isolation_suitable(cc, page))
-			goto next_pageblock;
+		if (last_pageblock_nr != pageblock_nr) {
+			int mt;
+
+			last_pageblock_nr = pageblock_nr;
+			if (!isolation_suitable(cc, page))
+				goto next_pageblock;
+
+			/*
+			 * For async migration, also only scan in MOVABLE
+			 * blocks. Async migration is optimistic to see if
+			 * the minimum amount of work satisfies the allocation
+			 */
+			mt = get_pageblock_migratetype(page);
+			if (!cc->sync && !migrate_async_suitable(mt)) {
+				cc->finished_update_migrate = true;
+				skipped_async_unsuitable = true;
+				goto next_pageblock;
+			}
+		}
 
 		/*
 		 * Skip if free. page_order cannot be used without zone->lock
@@ -537,18 +552,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			continue;
 
 		/*
-		 * For async migration, also only scan in MOVABLE blocks. Async
-		 * migration is optimistic to see if the minimum amount of work
-		 * satisfies the allocation
-		 */
-		if (!cc->sync && last_pageblock_nr != pageblock_nr &&
-		    !migrate_async_suitable(get_pageblock_migratetype(page))) {
-			cc->finished_update_migrate = true;
-			skipped_async_unsuitable = true;
-			goto next_pageblock;
-		}
-
-		/*
 		 * Check may be lockless but that's ok as we recheck later.
 		 * It's possible to migrate LRU pages and balloon pages
 		 * Skip any other type of page
@@ -557,11 +560,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			if (unlikely(balloon_page_movable(page))) {
 				if (locked && balloon_page_isolate(page)) {
 					/* Successfully isolated */
-					cc->finished_update_migrate = true;
-					list_add(&page->lru, migratelist);
-					cc->nr_migratepages++;
-					nr_isolated++;
-					goto check_compact_cluster;
+					goto isolate_success;
 				}
 			}
 			continue;
@@ -584,6 +583,15 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			continue;
 		}
 
+		/*
+		 * Migration will fail if an anonymous page is pinned in memory,
+		 * so avoid taking lru_lock and isolating it unnecessarily in an
+		 * admittedly racy check.
+		 */
+		if (!page_mapping(page) &&
+		    page_count(page) > page_mapcount(page))
+			continue;
+
 		/* Check if it is ok to still hold the lock */
 		locked = compact_checklock_irqsave(&zone->lru_lock, &flags,
 								locked, cc);
@@ -598,12 +606,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			continue;
 		}
 
-		if (!cc->sync)
-			mode |= ISOLATE_ASYNC_MIGRATE;
-
-		if (unevictable)
-			mode |= ISOLATE_UNEVICTABLE;
-
 		lruvec = mem_cgroup_page_lruvec(page, zone);
 
 		/* Try isolate the page */
@@ -613,13 +615,14 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 		VM_BUG_ON_PAGE(PageTransCompound(page), page);
 
 		/* Successfully isolated */
-		cc->finished_update_migrate = true;
 		del_page_from_lru_list(page, lruvec, page_lru(page));
+
+isolate_success:
+		cc->finished_update_migrate = true;
 		list_add(&page->lru, migratelist);
 		cc->nr_migratepages++;
 		nr_isolated++;
 
-check_compact_cluster:
 		/* Avoid isolating too much */
 		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) {
 			++low_pfn;
@@ -630,7 +633,6 @@ check_compact_cluster:
 
 next_pageblock:
 		low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1;
-		last_pageblock_nr = pageblock_nr;
 	}
 
 	acct_isolated(zone, locked, cc);
@@ -1186,6 +1188,7 @@ static void compact_node(int nid)
 	struct compact_control cc = {
 		.order = -1,
 		.sync = true,
+		.ignore_skip_hint = true,
 	};
 
 	__compact_pgdat(NODE_DATA(nid), &cc);
@@ -1225,7 +1228,7 @@ int sysctl_extfrag_handler(struct ctl_table *table, int write,
 }
 
 #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
-ssize_t sysfs_compact_node(struct device *dev,
+static ssize_t sysfs_compact_node(struct device *dev,
 			struct device_attribute *attr,
 			const char *buf, size_t count)
 {
diff --git a/mm/filemap.c b/mm/filemap.c
index 7a13f6ac5421..27ebc0c9571b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -33,6 +33,7 @@
 #include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
 #include <linux/memcontrol.h>
 #include <linux/cleancache.h>
+#include <linux/rmap.h>
 #include "internal.h"
 
 #define CREATE_TRACE_POINTS
@@ -107,12 +108,75 @@
  *   ->tasklist_lock            (memory_failure, collect_procs_ao)
  */
 
+static void page_cache_tree_delete(struct address_space *mapping,
+				   struct page *page, void *shadow)
+{
+	struct radix_tree_node *node;
+	unsigned long index;
+	unsigned int offset;
+	unsigned int tag;
+	void **slot;
+
+	VM_BUG_ON(!PageLocked(page));
+
+	__radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot);
+
+	if (shadow) {
+		mapping->nrshadows++;
+		/*
+		 * Make sure the nrshadows update is committed before
+		 * the nrpages update so that final truncate racing
+		 * with reclaim does not see both counters 0 at the
+		 * same time and miss a shadow entry.
+		 */
+		smp_wmb();
+	}
+	mapping->nrpages--;
+
+	if (!node) {
+		/* Clear direct pointer tags in root node */
+		mapping->page_tree.gfp_mask &= __GFP_BITS_MASK;
+		radix_tree_replace_slot(slot, shadow);
+		return;
+	}
+
+	/* Clear tree tags for the removed page */
+	index = page->index;
+	offset = index & RADIX_TREE_MAP_MASK;
+	for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) {
+		if (test_bit(offset, node->tags[tag]))
+			radix_tree_tag_clear(&mapping->page_tree, index, tag);
+	}
+
+	/* Delete page, swap shadow entry */
+	radix_tree_replace_slot(slot, shadow);
+	workingset_node_pages_dec(node);
+	if (shadow)
+		workingset_node_shadows_inc(node);
+	else
+		if (__radix_tree_delete_node(&mapping->page_tree, node))
+			return;
+
+	/*
+	 * Track node that only contains shadow entries.
+	 *
+	 * Avoid acquiring the list_lru lock if already tracked.  The
+	 * list_empty() test is safe as node->private_list is
+	 * protected by mapping->tree_lock.
+	 */
+	if (!workingset_node_pages(node) &&
+	    list_empty(&node->private_list)) {
+		node->private_data = mapping;
+		list_lru_add(&workingset_shadow_nodes, &node->private_list);
+	}
+}
+
 /*
  * Delete a page from the page cache and free it. Caller has to make
  * sure the page is locked and that nobody else uses it - or that usage
  * is safe.  The caller must hold the mapping's tree_lock.
  */
-void __delete_from_page_cache(struct page *page)
+void __delete_from_page_cache(struct page *page, void *shadow)
 {
 	struct address_space *mapping = page->mapping;
 
@@ -127,10 +191,11 @@ void __delete_from_page_cache(struct page *page)
 	else
 		cleancache_invalidate_page(mapping, page);
 
-	radix_tree_delete(&mapping->page_tree, page->index);
+	page_cache_tree_delete(mapping, page, shadow);
+
 	page->mapping = NULL;
 	/* Leave page->index set: truncation lookup relies upon it */
-	mapping->nrpages--;
+
 	__dec_zone_page_state(page, NR_FILE_PAGES);
 	if (PageSwapBacked(page))
 		__dec_zone_page_state(page, NR_SHMEM);
@@ -166,7 +231,7 @@ void delete_from_page_cache(struct page *page)
 
 	freepage = mapping->a_ops->freepage;
 	spin_lock_irq(&mapping->tree_lock);
-	__delete_from_page_cache(page);
+	__delete_from_page_cache(page, NULL);
 	spin_unlock_irq(&mapping->tree_lock);
 	mem_cgroup_uncharge_cache_page(page);
 
@@ -426,7 +491,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 		new->index = offset;
 
 		spin_lock_irq(&mapping->tree_lock);
-		__delete_from_page_cache(old);
+		__delete_from_page_cache(old, NULL);
 		error = radix_tree_insert(&mapping->page_tree, offset, new);
 		BUG_ON(error);
 		mapping->nrpages++;
@@ -446,25 +511,59 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL_GPL(replace_page_cache_page);
 
-/**
- * add_to_page_cache_locked - add a locked page to the pagecache
- * @page:	page to add
- * @mapping:	the page's address_space
- * @offset:	page index
- * @gfp_mask:	page allocation mode
- *
- * This function is used to add a page to the pagecache. It must be locked.
- * This function does not add the page to the LRU.  The caller must do that.
- */
-int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
-		pgoff_t offset, gfp_t gfp_mask)
+static int page_cache_tree_insert(struct address_space *mapping,
+				  struct page *page, void **shadowp)
+{
+	struct radix_tree_node *node;
+	void **slot;
+	int error;
+
+	error = __radix_tree_create(&mapping->page_tree, page->index,
+				    &node, &slot);
+	if (error)
+		return error;
+	if (*slot) {
+		void *p;
+
+		p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+		if (!radix_tree_exceptional_entry(p))
+			return -EEXIST;
+		if (shadowp)
+			*shadowp = p;
+		mapping->nrshadows--;
+		if (node)
+			workingset_node_shadows_dec(node);
+	}
+	radix_tree_replace_slot(slot, page);
+	mapping->nrpages++;
+	if (node) {
+		workingset_node_pages_inc(node);
+		/*
+		 * Don't track node that contains actual pages.
+		 *
+		 * Avoid acquiring the list_lru lock if already
+		 * untracked.  The list_empty() test is safe as
+		 * node->private_list is protected by
+		 * mapping->tree_lock.
+		 */
+		if (!list_empty(&node->private_list))
+			list_lru_del(&workingset_shadow_nodes,
+				     &node->private_list);
+	}
+	return 0;
+}
+
+static int __add_to_page_cache_locked(struct page *page,
+				      struct address_space *mapping,
+				      pgoff_t offset, gfp_t gfp_mask,
+				      void **shadowp)
 {
 	int error;
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(PageSwapBacked(page), page);
 
-	error = mem_cgroup_cache_charge(page, current->mm,
+	error = mem_cgroup_charge_file(page, current->mm,
 					gfp_mask & GFP_RECLAIM_MASK);
 	if (error)
 		return error;
@@ -480,11 +579,10 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 	page->index = offset;
 
 	spin_lock_irq(&mapping->tree_lock);
-	error = radix_tree_insert(&mapping->page_tree, offset, page);
+	error = page_cache_tree_insert(mapping, page, shadowp);
 	radix_tree_preload_end();
 	if (unlikely(error))
 		goto err_insert;
-	mapping->nrpages++;
 	__inc_zone_page_state(page, NR_FILE_PAGES);
 	spin_unlock_irq(&mapping->tree_lock);
 	trace_mm_filemap_add_to_page_cache(page);
@@ -497,16 +595,49 @@ err_insert:
 	page_cache_release(page);
 	return error;
 }
+
+/**
+ * add_to_page_cache_locked - add a locked page to the pagecache
+ * @page:	page to add
+ * @mapping:	the page's address_space
+ * @offset:	page index
+ * @gfp_mask:	page allocation mode
+ *
+ * This function is used to add a page to the pagecache. It must be locked.
+ * This function does not add the page to the LRU.  The caller must do that.
+ */
+int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
+		pgoff_t offset, gfp_t gfp_mask)
+{
+	return __add_to_page_cache_locked(page, mapping, offset,
+					  gfp_mask, NULL);
+}
 EXPORT_SYMBOL(add_to_page_cache_locked);
 
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 				pgoff_t offset, gfp_t gfp_mask)
 {
+	void *shadow = NULL;
 	int ret;
 
-	ret = add_to_page_cache(page, mapping, offset, gfp_mask);
-	if (ret == 0)
-		lru_cache_add_file(page);
+	__set_page_locked(page);
+	ret = __add_to_page_cache_locked(page, mapping, offset,
+					 gfp_mask, &shadow);
+	if (unlikely(ret))
+		__clear_page_locked(page);
+	else {
+		/*
+		 * The page might have been evicted from cache only
+		 * recently, in which case it should be activated like
+		 * any other repeatedly accessed page.
+		 */
+		if (shadow && workingset_refault(shadow)) {
+			SetPageActive(page);
+			workingset_activation(page);
+		} else
+			ClearPageActive(page);
+		lru_cache_add(page);
+	}
 	return ret;
 }
 EXPORT_SYMBOL_GPL(add_to_page_cache_lru);
@@ -520,10 +651,10 @@ struct page *__page_cache_alloc(gfp_t gfp)
 	if (cpuset_do_page_mem_spread()) {
 		unsigned int cpuset_mems_cookie;
 		do {
-			cpuset_mems_cookie = get_mems_allowed();
+			cpuset_mems_cookie = read_mems_allowed_begin();
 			n = cpuset_mem_spread_node();
 			page = alloc_pages_exact_node(n, gfp, 0);
-		} while (!put_mems_allowed(cpuset_mems_cookie) && !page);
+		} while (!page && read_mems_allowed_retry(cpuset_mems_cookie));
 
 		return page;
 	}
@@ -686,14 +817,101 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 }
 
 /**
- * find_get_page - find and get a page reference
+ * page_cache_next_hole - find the next hole (not-present entry)
+ * @mapping: mapping
+ * @index: index
+ * @max_scan: maximum range to search
+ *
+ * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the
+ * lowest indexed hole.
+ *
+ * Returns: the index of the hole if found, otherwise returns an index
+ * outside of the set specified (in which case 'return - index >=
+ * max_scan' will be true). In rare cases of index wrap-around, 0 will
+ * be returned.
+ *
+ * page_cache_next_hole may be called under rcu_read_lock. However,
+ * like radix_tree_gang_lookup, this will not atomically search a
+ * snapshot of the tree at a single point in time. For example, if a
+ * hole is created at index 5, then subsequently a hole is created at
+ * index 10, page_cache_next_hole covering both indexes may return 10
+ * if called under rcu_read_lock.
+ */
+pgoff_t page_cache_next_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan)
+{
+	unsigned long i;
+
+	for (i = 0; i < max_scan; i++) {
+		struct page *page;
+
+		page = radix_tree_lookup(&mapping->page_tree, index);
+		if (!page || radix_tree_exceptional_entry(page))
+			break;
+		index++;
+		if (index == 0)
+			break;
+	}
+
+	return index;
+}
+EXPORT_SYMBOL(page_cache_next_hole);
+
+/**
+ * page_cache_prev_hole - find the prev hole (not-present entry)
+ * @mapping: mapping
+ * @index: index
+ * @max_scan: maximum range to search
+ *
+ * Search backwards in the range [max(index-max_scan+1, 0), index] for
+ * the first hole.
+ *
+ * Returns: the index of the hole if found, otherwise returns an index
+ * outside of the set specified (in which case 'index - return >=
+ * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX
+ * will be returned.
+ *
+ * page_cache_prev_hole may be called under rcu_read_lock. However,
+ * like radix_tree_gang_lookup, this will not atomically search a
+ * snapshot of the tree at a single point in time. For example, if a
+ * hole is created at index 10, then subsequently a hole is created at
+ * index 5, page_cache_prev_hole covering both indexes may return 5 if
+ * called under rcu_read_lock.
+ */
+pgoff_t page_cache_prev_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan)
+{
+	unsigned long i;
+
+	for (i = 0; i < max_scan; i++) {
+		struct page *page;
+
+		page = radix_tree_lookup(&mapping->page_tree, index);
+		if (!page || radix_tree_exceptional_entry(page))
+			break;
+		index--;
+		if (index == ULONG_MAX)
+			break;
+	}
+
+	return index;
+}
+EXPORT_SYMBOL(page_cache_prev_hole);
+
+/**
+ * find_get_entry - find and get a page cache entry
  * @mapping: the address_space to search
- * @offset: the page index
+ * @offset: the page cache index
+ *
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned with an increased refcount.
+ *
+ * If the slot holds a shadow entry of a previously evicted page, it
+ * is returned.
  *
- * Is there a pagecache struct page at the given (mapping, offset) tuple?
- * If yes, increment its refcount and return it; if no, return NULL.
+ * Otherwise, %NULL is returned.
  */
-struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
+struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
 {
 	void **pagep;
 	struct page *page;
@@ -734,24 +952,50 @@ out:
 
 	return page;
 }
-EXPORT_SYMBOL(find_get_page);
+EXPORT_SYMBOL(find_get_entry);
 
 /**
- * find_lock_page - locate, pin and lock a pagecache page
+ * find_get_page - find and get a page reference
  * @mapping: the address_space to search
  * @offset: the page index
  *
- * Locates the desired pagecache page, locks it, increments its reference
- * count and returns its address.
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned with an increased refcount.
  *
- * Returns zero if the page was not present. find_lock_page() may sleep.
+ * Otherwise, %NULL is returned.
  */
-struct page *find_lock_page(struct address_space *mapping, pgoff_t offset)
+struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
+{
+	struct page *page = find_get_entry(mapping, offset);
+
+	if (radix_tree_exceptional_entry(page))
+		page = NULL;
+	return page;
+}
+EXPORT_SYMBOL(find_get_page);
+
+/**
+ * find_lock_entry - locate, pin and lock a page cache entry
+ * @mapping: the address_space to search
+ * @offset: the page cache index
+ *
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * If the slot holds a shadow entry of a previously evicted page, it
+ * is returned.
+ *
+ * Otherwise, %NULL is returned.
+ *
+ * find_lock_entry() may sleep.
+ */
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset)
 {
 	struct page *page;
 
 repeat:
-	page = find_get_page(mapping, offset);
+	page = find_get_entry(mapping, offset);
 	if (page && !radix_tree_exception(page)) {
 		lock_page(page);
 		/* Has the page been truncated? */
@@ -764,6 +1008,29 @@ repeat:
 	}
 	return page;
 }
+EXPORT_SYMBOL(find_lock_entry);
+
+/**
+ * find_lock_page - locate, pin and lock a pagecache page
+ * @mapping: the address_space to search
+ * @offset: the page index
+ *
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * Otherwise, %NULL is returned.
+ *
+ * find_lock_page() may sleep.
+ */
+struct page *find_lock_page(struct address_space *mapping, pgoff_t offset)
+{
+	struct page *page = find_lock_entry(mapping, offset);
+
+	if (radix_tree_exceptional_entry(page))
+		page = NULL;
+	return page;
+}
 EXPORT_SYMBOL(find_lock_page);
 
 /**
@@ -772,16 +1039,18 @@ EXPORT_SYMBOL(find_lock_page);
  * @index: the page's index into the mapping
  * @gfp_mask: page allocation mode
  *
- * Locates a page in the pagecache.  If the page is not present, a new page
- * is allocated using @gfp_mask and is added to the pagecache and to the VM's
- * LRU list.  The returned page is locked and has its reference count
- * incremented.
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
  *
- * find_or_create_page() may sleep, even if @gfp_flags specifies an atomic
- * allocation!
+ * If the page is not present, a new page is allocated using @gfp_mask
+ * and added to the page cache and the VM's LRU list.  The page is
+ * returned locked and with an increased refcount.
  *
- * find_or_create_page() returns the desired page's address, or zero on
- * memory exhaustion.
+ * On memory exhaustion, %NULL is returned.
+ *
+ * find_or_create_page() may sleep, even if @gfp_flags specifies an
+ * atomic allocation!
  */
 struct page *find_or_create_page(struct address_space *mapping,
 		pgoff_t index, gfp_t gfp_mask)
@@ -814,6 +1083,76 @@ repeat:
 EXPORT_SYMBOL(find_or_create_page);
 
 /**
+ * find_get_entries - gang pagecache lookup
+ * @mapping:	The address_space to search
+ * @start:	The starting page cache index
+ * @nr_entries:	The maximum number of entries
+ * @entries:	Where the resulting entries are placed
+ * @indices:	The cache indices corresponding to the entries in @entries
+ *
+ * find_get_entries() will search for and return a group of up to
+ * @nr_entries entries in the mapping.  The entries are placed at
+ * @entries.  find_get_entries() takes a reference against any actual
+ * pages it returns.
+ *
+ * The search returns a group of mapping-contiguous page cache entries
+ * with ascending indexes.  There may be holes in the indices due to
+ * not-present pages.
+ *
+ * Any shadow entries of evicted pages are included in the returned
+ * array.
+ *
+ * find_get_entries() returns the number of pages and shadow entries
+ * which were found.
+ */
+unsigned find_get_entries(struct address_space *mapping,
+			  pgoff_t start, unsigned int nr_entries,
+			  struct page **entries, pgoff_t *indices)
+{
+	void **slot;
+	unsigned int ret = 0;
+	struct radix_tree_iter iter;
+
+	if (!nr_entries)
+		return 0;
+
+	rcu_read_lock();
+restart:
+	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
+		struct page *page;
+repeat:
+		page = radix_tree_deref_slot(slot);
+		if (unlikely(!page))
+			continue;
+		if (radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page))
+				goto restart;
+			/*
+			 * Otherwise, we must be storing a swap entry
+			 * here as an exceptional entry: so return it
+			 * without attempting to raise page count.
+			 */
+			goto export;
+		}
+		if (!page_cache_get_speculative(page))
+			goto repeat;
+
+		/* Has the page moved? */
+		if (unlikely(page != *slot)) {
+			page_cache_release(page);
+			goto repeat;
+		}
+export:
+		indices[ret] = iter.index;
+		entries[ret] = page;
+		if (++ret == nr_entries)
+			break;
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
  * find_get_pages - gang pagecache lookup
  * @mapping:	The address_space to search
  * @start:	The starting page index
@@ -1614,11 +1953,11 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct inode *inode = mapping->host;
 	pgoff_t offset = vmf->pgoff;
 	struct page *page;
-	pgoff_t size;
+	loff_t size;
 	int ret = 0;
 
-	size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	if (offset >= size)
+	size = round_up(i_size_read(inode), PAGE_CACHE_SIZE);
+	if (offset >= size >> PAGE_CACHE_SHIFT)
 		return VM_FAULT_SIGBUS;
 
 	/*
@@ -1667,8 +2006,8 @@ retry_find:
 	 * Found the page and have a reference on it.
 	 * We must recheck i_size under page lock.
 	 */
-	size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	if (unlikely(offset >= size)) {
+	size = round_up(i_size_read(inode), PAGE_CACHE_SIZE);
+	if (unlikely(offset >= size >> PAGE_CACHE_SHIFT)) {
 		unlock_page(page);
 		page_cache_release(page);
 		return VM_FAULT_SIGBUS;
@@ -1726,6 +2065,78 @@ page_not_uptodate:
 }
 EXPORT_SYMBOL(filemap_fault);
 
+void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct radix_tree_iter iter;
+	void **slot;
+	struct file *file = vma->vm_file;
+	struct address_space *mapping = file->f_mapping;
+	loff_t size;
+	struct page *page;
+	unsigned long address = (unsigned long) vmf->virtual_address;
+	unsigned long addr;
+	pte_t *pte;
+
+	rcu_read_lock();
+	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, vmf->pgoff) {
+		if (iter.index > vmf->max_pgoff)
+			break;
+repeat:
+		page = radix_tree_deref_slot(slot);
+		if (unlikely(!page))
+			goto next;
+		if (radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page))
+				break;
+			else
+				goto next;
+		}
+
+		if (!page_cache_get_speculative(page))
+			goto repeat;
+
+		/* Has the page moved? */
+		if (unlikely(page != *slot)) {
+			page_cache_release(page);
+			goto repeat;
+		}
+
+		if (!PageUptodate(page) ||
+				PageReadahead(page) ||
+				PageHWPoison(page))
+			goto skip;
+		if (!trylock_page(page))
+			goto skip;
+
+		if (page->mapping != mapping || !PageUptodate(page))
+			goto unlock;
+
+		size = round_up(i_size_read(mapping->host), PAGE_CACHE_SIZE);
+		if (page->index >= size >> PAGE_CACHE_SHIFT)
+			goto unlock;
+
+		pte = vmf->pte + page->index - vmf->pgoff;
+		if (!pte_none(*pte))
+			goto unlock;
+
+		if (file->f_ra.mmap_miss > 0)
+			file->f_ra.mmap_miss--;
+		addr = address + (page->index - vmf->pgoff) * PAGE_SIZE;
+		do_set_pte(vma, addr, page, pte, false, false);
+		unlock_page(page);
+		goto next;
+unlock:
+		unlock_page(page);
+skip:
+		page_cache_release(page);
+next:
+		if (iter.index == vmf->max_pgoff)
+			break;
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(filemap_map_pages);
+
 int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
@@ -1755,6 +2166,7 @@ EXPORT_SYMBOL(filemap_page_mkwrite);
 
 const struct vm_operations_struct generic_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= filemap_page_mkwrite,
 	.remap_pages	= generic_file_remap_pages,
 };
@@ -1795,6 +2207,18 @@ int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma)
 EXPORT_SYMBOL(generic_file_mmap);
 EXPORT_SYMBOL(generic_file_readonly_mmap);
 
+static struct page *wait_on_page_read(struct page *page)
+{
+	if (!IS_ERR(page)) {
+		wait_on_page_locked(page);
+		if (!PageUptodate(page)) {
+			page_cache_release(page);
+			page = ERR_PTR(-EIO);
+		}
+	}
+	return page;
+}
+
 static struct page *__read_cache_page(struct address_space *mapping,
 				pgoff_t index,
 				int (*filler)(void *, struct page *),
@@ -1821,6 +2245,8 @@ repeat:
 		if (err < 0) {
 			page_cache_release(page);
 			page = ERR_PTR(err);
+		} else {
+			page = wait_on_page_read(page);
 		}
 	}
 	return page;
@@ -1857,6 +2283,10 @@ retry:
 	if (err < 0) {
 		page_cache_release(page);
 		return ERR_PTR(err);
+	} else {
+		page = wait_on_page_read(page);
+		if (IS_ERR(page))
+			return page;
 	}
 out:
 	mark_page_accessed(page);
@@ -1864,40 +2294,25 @@ out:
 }
 
 /**
- * read_cache_page_async - read into page cache, fill it if needed
+ * read_cache_page - read into page cache, fill it if needed
  * @mapping:	the page's address_space
  * @index:	the page index
  * @filler:	function to perform the read
  * @data:	first arg to filler(data, page) function, often left as NULL
  *
- * Same as read_cache_page, but don't wait for page to become unlocked
- * after submitting it to the filler.
- *
  * Read into the page cache. If a page already exists, and PageUptodate() is
- * not set, try to fill the page but don't wait for it to become unlocked.
+ * not set, try to fill the page and wait for it to become unlocked.
  *
  * If the page does not get brought uptodate, return -EIO.
  */
-struct page *read_cache_page_async(struct address_space *mapping,
+struct page *read_cache_page(struct address_space *mapping,
 				pgoff_t index,
 				int (*filler)(void *, struct page *),
 				void *data)
 {
 	return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping));
 }
-EXPORT_SYMBOL(read_cache_page_async);
-
-static struct page *wait_on_page_read(struct page *page)
-{
-	if (!IS_ERR(page)) {
-		wait_on_page_locked(page);
-		if (!PageUptodate(page)) {
-			page_cache_release(page);
-			page = ERR_PTR(-EIO);
-		}
-	}
-	return page;
-}
+EXPORT_SYMBOL(read_cache_page);
 
 /**
  * read_cache_page_gfp - read into page cache, using specified page allocation flags.
@@ -1916,31 +2331,10 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
 {
 	filler_t *filler = (filler_t *)mapping->a_ops->readpage;
 
-	return wait_on_page_read(do_read_cache_page(mapping, index, filler, NULL, gfp));
+	return do_read_cache_page(mapping, index, filler, NULL, gfp);
 }
 EXPORT_SYMBOL(read_cache_page_gfp);
 
-/**
- * read_cache_page - read into page cache, fill it if needed
- * @mapping:	the page's address_space
- * @index:	the page index
- * @filler:	function to perform the read
- * @data:	first arg to filler(data, page) function, often left as NULL
- *
- * Read into the page cache. If a page already exists, and PageUptodate() is
- * not set, try to fill the page then wait for it to become unlocked.
- *
- * If the page does not get brought uptodate, return -EIO.
- */
-struct page *read_cache_page(struct address_space *mapping,
-				pgoff_t index,
-				int (*filler)(void *, struct page *),
-				void *data)
-{
-	return wait_on_page_read(read_cache_page_async(mapping, index, filler, data));
-}
-EXPORT_SYMBOL(read_cache_page);
-
 static size_t __iovec_copy_from_user_inatomic(char *vaddr,
 			const struct iovec *iov, size_t base, size_t bytes)
 {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1546655a2d78..7577c40f2ad7 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -827,7 +827,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
 	}
-	if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
+	if (unlikely(mem_cgroup_charge_anon(page, mm, GFP_KERNEL))) {
 		put_page(page);
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
@@ -941,81 +941,6 @@ unlock:
 	spin_unlock(ptl);
 }
 
-static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm,
-		struct vm_area_struct *vma, unsigned long address,
-		pmd_t *pmd, pmd_t orig_pmd, unsigned long haddr)
-{
-	spinlock_t *ptl;
-	pgtable_t pgtable;
-	pmd_t _pmd;
-	struct page *page;
-	int i, ret = 0;
-	unsigned long mmun_start;	/* For mmu_notifiers */
-	unsigned long mmun_end;		/* For mmu_notifiers */
-
-	page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
-	if (!page) {
-		ret |= VM_FAULT_OOM;
-		goto out;
-	}
-
-	if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) {
-		put_page(page);
-		ret |= VM_FAULT_OOM;
-		goto out;
-	}
-
-	clear_user_highpage(page, address);
-	__SetPageUptodate(page);
-
-	mmun_start = haddr;
-	mmun_end   = haddr + HPAGE_PMD_SIZE;
-	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
-
-	ptl = pmd_lock(mm, pmd);
-	if (unlikely(!pmd_same(*pmd, orig_pmd)))
-		goto out_free_page;
-
-	pmdp_clear_flush(vma, haddr, pmd);
-	/* leave pmd empty until pte is filled */
-
-	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
-	pmd_populate(mm, &_pmd, pgtable);
-
-	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
-		pte_t *pte, entry;
-		if (haddr == (address & PAGE_MASK)) {
-			entry = mk_pte(page, vma->vm_page_prot);
-			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
-			page_add_new_anon_rmap(page, vma, haddr);
-		} else {
-			entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot);
-			entry = pte_mkspecial(entry);
-		}
-		pte = pte_offset_map(&_pmd, haddr);
-		VM_BUG_ON(!pte_none(*pte));
-		set_pte_at(mm, haddr, pte, entry);
-		pte_unmap(pte);
-	}
-	smp_wmb(); /* make pte visible before pmd */
-	pmd_populate(mm, pmd, pgtable);
-	spin_unlock(ptl);
-	put_huge_zero_page();
-	inc_mm_counter(mm, MM_ANONPAGES);
-
-	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
-
-	ret |= VM_FAULT_WRITE;
-out:
-	return ret;
-out_free_page:
-	spin_unlock(ptl);
-	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
-	mem_cgroup_uncharge_page(page);
-	put_page(page);
-	goto out;
-}
-
 static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 					struct vm_area_struct *vma,
 					unsigned long address,
@@ -1043,7 +968,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 					       __GFP_OTHER_NODE,
 					       vma, address, page_to_nid(page));
 		if (unlikely(!pages[i] ||
-			     mem_cgroup_newpage_charge(pages[i], mm,
+			     mem_cgroup_charge_anon(pages[i], mm,
 						       GFP_KERNEL))) {
 			if (pages[i])
 				put_page(pages[i]);
@@ -1161,8 +1086,8 @@ alloc:
 
 	if (unlikely(!new_page)) {
 		if (!page) {
-			ret = do_huge_pmd_wp_zero_page_fallback(mm, vma,
-					address, pmd, orig_pmd, haddr);
+			split_huge_page_pmd(vma, address, pmd);
+			ret |= VM_FAULT_FALLBACK;
 		} else {
 			ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
 					pmd, orig_pmd, page, haddr);
@@ -1176,7 +1101,7 @@ alloc:
 		goto out;
 	}
 
-	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
+	if (unlikely(mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL))) {
 		put_page(new_page);
 		if (page) {
 			split_huge_page(page);
@@ -1875,7 +1800,7 @@ static void __split_huge_page(struct page *page,
 			      struct list_head *list)
 {
 	int mapcount, mapcount2;
-	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+	pgoff_t pgoff = page_pgoff(page);
 	struct anon_vma_chain *avc;
 
 	BUG_ON(!PageHead(page));
@@ -1966,17 +1891,22 @@ out:
 int hugepage_madvise(struct vm_area_struct *vma,
 		     unsigned long *vm_flags, int advice)
 {
-	struct mm_struct *mm = vma->vm_mm;
-
 	switch (advice) {
 	case MADV_HUGEPAGE:
+#ifdef CONFIG_S390
+		/*
+		 * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390
+		 * can't handle this properly after s390_enable_sie, so we simply
+		 * ignore the madvise to prevent qemu from causing a SIGSEGV.
+		 */
+		if (mm_has_pgste(vma->vm_mm))
+			return 0;
+#endif
 		/*
 		 * Be somewhat over-protective like KSM for now!
 		 */
 		if (*vm_flags & (VM_HUGEPAGE | VM_NO_THP))
 			return -EINVAL;
-		if (mm->def_flags & VM_NOHUGEPAGE)
-			return -EINVAL;
 		*vm_flags &= ~VM_NOHUGEPAGE;
 		*vm_flags |= VM_HUGEPAGE;
 		/*
@@ -2429,7 +2359,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	if (!new_page)
 		return;
 
-	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL)))
+	if (unlikely(mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL)))
 		return;
 
 	/*
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c01cb9fedb18..4f367df8a8dd 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -13,6 +13,7 @@
 #include <linux/nodemask.h>
 #include <linux/pagemap.h>
 #include <linux/mempolicy.h>
+#include <linux/compiler.h>
 #include <linux/cpuset.h>
 #include <linux/mutex.h>
 #include <linux/bootmem.h>
@@ -22,6 +23,7 @@
 #include <linux/swap.h>
 #include <linux/swapops.h>
 #include <linux/page-isolation.h>
+#include <linux/jhash.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -29,6 +31,7 @@
 
 #include <linux/io.h>
 #include <linux/hugetlb.h>
+#include <linux/hugetlb_inline.h>
 #include <linux/hugetlb_cgroup.h>
 #include <linux/node.h>
 #include "internal.h"
@@ -53,6 +56,13 @@ static unsigned long __initdata default_hstate_size;
  */
 DEFINE_SPINLOCK(hugetlb_lock);
 
+/*
+ * Serializes faults on the same logical page.  This is used to
+ * prevent spurious OOMs when the hugepage pool is fully utilized.
+ */
+static int num_fault_mutexes;
+static struct mutex *htlb_fault_mutex_table ____cacheline_aligned_in_smp;
+
 static inline void unlock_or_release_subpool(struct hugepage_subpool *spool)
 {
 	bool free = (spool->count == 0) && (spool->used_hpages == 0);
@@ -135,15 +145,8 @@ static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma)
  * Region tracking -- allows tracking of reservations and instantiated pages
  *                    across the pages in a mapping.
  *
- * The region data structures are protected by a combination of the mmap_sem
- * and the hugetlb_instantiation_mutex.  To access or modify a region the caller
- * must either hold the mmap_sem for write, or the mmap_sem for read and
- * the hugetlb_instantiation_mutex:
- *
- *	down_write(&mm->mmap_sem);
- * or
- *	down_read(&mm->mmap_sem);
- *	mutex_lock(&hugetlb_instantiation_mutex);
+ * The region data structures are embedded into a resv_map and
+ * protected by a resv_map's lock
  */
 struct file_region {
 	struct list_head link;
@@ -151,10 +154,12 @@ struct file_region {
 	long to;
 };
 
-static long region_add(struct list_head *head, long f, long t)
+static long region_add(struct resv_map *resv, long f, long t)
 {
+	struct list_head *head = &resv->regions;
 	struct file_region *rg, *nrg, *trg;
 
+	spin_lock(&resv->lock);
 	/* Locate the region we are either in or before. */
 	list_for_each_entry(rg, head, link)
 		if (f <= rg->to)
@@ -184,14 +189,18 @@ static long region_add(struct list_head *head, long f, long t)
 	}
 	nrg->from = f;
 	nrg->to = t;
+	spin_unlock(&resv->lock);
 	return 0;
 }
 
-static long region_chg(struct list_head *head, long f, long t)
+static long region_chg(struct resv_map *resv, long f, long t)
 {
-	struct file_region *rg, *nrg;
+	struct list_head *head = &resv->regions;
+	struct file_region *rg, *nrg = NULL;
 	long chg = 0;
 
+retry:
+	spin_lock(&resv->lock);
 	/* Locate the region we are before or in. */
 	list_for_each_entry(rg, head, link)
 		if (f <= rg->to)
@@ -201,15 +210,21 @@ static long region_chg(struct list_head *head, long f, long t)
 	 * Subtle, allocate a new region at the position but make it zero
 	 * size such that we can guarantee to record the reservation. */
 	if (&rg->link == head || t < rg->from) {
-		nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
-		if (!nrg)
-			return -ENOMEM;
-		nrg->from = f;
-		nrg->to   = f;
-		INIT_LIST_HEAD(&nrg->link);
-		list_add(&nrg->link, rg->link.prev);
+		if (!nrg) {
+			spin_unlock(&resv->lock);
+			nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
+			if (!nrg)
+				return -ENOMEM;
+
+			nrg->from = f;
+			nrg->to   = f;
+			INIT_LIST_HEAD(&nrg->link);
+			goto retry;
+		}
 
-		return t - f;
+		list_add(&nrg->link, rg->link.prev);
+		chg = t - f;
+		goto out_nrg;
 	}
 
 	/* Round our left edge to the current segment if it encloses us. */
@@ -222,7 +237,7 @@ static long region_chg(struct list_head *head, long f, long t)
 		if (&rg->link == head)
 			break;
 		if (rg->from > t)
-			return chg;
+			goto out;
 
 		/* We overlap with this area, if it extends further than
 		 * us then we must extend ourselves.  Account for its
@@ -233,20 +248,30 @@ static long region_chg(struct list_head *head, long f, long t)
 		}
 		chg -= rg->to - rg->from;
 	}
+
+out:
+	spin_unlock(&resv->lock);
+	/*  We already know we raced and no longer need the new region */
+	kfree(nrg);
+	return chg;
+out_nrg:
+	spin_unlock(&resv->lock);
 	return chg;
 }
 
-static long region_truncate(struct list_head *head, long end)
+static long region_truncate(struct resv_map *resv, long end)
 {
+	struct list_head *head = &resv->regions;
 	struct file_region *rg, *trg;
 	long chg = 0;
 
+	spin_lock(&resv->lock);
 	/* Locate the region we are either in or before. */
 	list_for_each_entry(rg, head, link)
 		if (end <= rg->to)
 			break;
 	if (&rg->link == head)
-		return 0;
+		goto out;
 
 	/* If we are in the middle of a region then adjust it. */
 	if (end > rg->from) {
@@ -263,14 +288,19 @@ static long region_truncate(struct list_head *head, long end)
 		list_del(&rg->link);
 		kfree(rg);
 	}
+
+out:
+	spin_unlock(&resv->lock);
 	return chg;
 }
 
-static long region_count(struct list_head *head, long f, long t)
+static long region_count(struct resv_map *resv, long f, long t)
 {
+	struct list_head *head = &resv->regions;
 	struct file_region *rg;
 	long chg = 0;
 
+	spin_lock(&resv->lock);
 	/* Locate each segment we overlap with, and count that overlap. */
 	list_for_each_entry(rg, head, link) {
 		long seg_from;
@@ -286,6 +316,7 @@ static long region_count(struct list_head *head, long f, long t)
 
 		chg += seg_to - seg_from;
 	}
+	spin_unlock(&resv->lock);
 
 	return chg;
 }
@@ -376,39 +407,46 @@ static void set_vma_private_data(struct vm_area_struct *vma,
 	vma->vm_private_data = (void *)value;
 }
 
-struct resv_map {
-	struct kref refs;
-	struct list_head regions;
-};
-
-static struct resv_map *resv_map_alloc(void)
+struct resv_map *resv_map_alloc(void)
 {
 	struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL);
 	if (!resv_map)
 		return NULL;
 
 	kref_init(&resv_map->refs);
+	spin_lock_init(&resv_map->lock);
 	INIT_LIST_HEAD(&resv_map->regions);
 
 	return resv_map;
 }
 
-static void resv_map_release(struct kref *ref)
+void resv_map_release(struct kref *ref)
 {
 	struct resv_map *resv_map = container_of(ref, struct resv_map, refs);
 
 	/* Clear out any active regions before we release the map. */
-	region_truncate(&resv_map->regions, 0);
+	region_truncate(resv_map, 0);
 	kfree(resv_map);
 }
 
+static inline struct resv_map *inode_resv_map(struct inode *inode)
+{
+	return inode->i_mapping->private_data;
+}
+
 static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
 {
 	VM_BUG_ON(!is_vm_hugetlb_page(vma));
-	if (!(vma->vm_flags & VM_MAYSHARE))
+	if (vma->vm_flags & VM_MAYSHARE) {
+		struct address_space *mapping = vma->vm_file->f_mapping;
+		struct inode *inode = mapping->host;
+
+		return inode_resv_map(inode);
+
+	} else {
 		return (struct resv_map *)(get_vma_private_data(vma) &
 							~HPAGE_RESV_MASK);
-	return NULL;
+	}
 }
 
 static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
@@ -540,7 +578,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 		goto err;
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 	zonelist = huge_zonelist(vma, address,
 					htlb_alloc_mask(h), &mpol, &nodemask);
 
@@ -562,7 +600,7 @@ retry_cpuset:
 	}
 
 	mpol_cond_put(mpol);
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 	return page;
 
@@ -653,7 +691,8 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 	put_page(page); /* free it into the hugepage allocator */
 }
 
-static void prep_compound_gigantic_page(struct page *page, unsigned long order)
+static void __init prep_compound_gigantic_page(struct page *page,
+					       unsigned long order)
 {
 	int i;
 	int nr_pages = 1 << order;
@@ -1150,45 +1189,34 @@ static void return_unused_surplus_pages(struct hstate *h,
 static long vma_needs_reservation(struct hstate *h,
 			struct vm_area_struct *vma, unsigned long addr)
 {
-	struct address_space *mapping = vma->vm_file->f_mapping;
-	struct inode *inode = mapping->host;
-
-	if (vma->vm_flags & VM_MAYSHARE) {
-		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
-		return region_chg(&inode->i_mapping->private_list,
-							idx, idx + 1);
+	struct resv_map *resv;
+	pgoff_t idx;
+	long chg;
 
-	} else if (!is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
+	resv = vma_resv_map(vma);
+	if (!resv)
 		return 1;
 
-	} else  {
-		long err;
-		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
-		struct resv_map *resv = vma_resv_map(vma);
+	idx = vma_hugecache_offset(h, vma, addr);
+	chg = region_chg(resv, idx, idx + 1);
 
-		err = region_chg(&resv->regions, idx, idx + 1);
-		if (err < 0)
-			return err;
-		return 0;
-	}
+	if (vma->vm_flags & VM_MAYSHARE)
+		return chg;
+	else
+		return chg < 0 ? chg : 0;
 }
 static void vma_commit_reservation(struct hstate *h,
 			struct vm_area_struct *vma, unsigned long addr)
 {
-	struct address_space *mapping = vma->vm_file->f_mapping;
-	struct inode *inode = mapping->host;
-
-	if (vma->vm_flags & VM_MAYSHARE) {
-		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
-		region_add(&inode->i_mapping->private_list, idx, idx + 1);
+	struct resv_map *resv;
+	pgoff_t idx;
 
-	} else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
-		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
-		struct resv_map *resv = vma_resv_map(vma);
+	resv = vma_resv_map(vma);
+	if (!resv)
+		return;
 
-		/* Mark this page used in the map. */
-		region_add(&resv->regions, idx, idx + 1);
-	}
+	idx = vma_hugecache_offset(h, vma, addr);
+	region_add(resv, idx, idx + 1);
 }
 
 static struct page *alloc_huge_page(struct vm_area_struct *vma,
@@ -1294,7 +1322,7 @@ found:
 	return 1;
 }
 
-static void prep_compound_huge_page(struct page *page, int order)
+static void __init prep_compound_huge_page(struct page *page, int order)
 {
 	if (unlikely(order > (MAX_ORDER - 1)))
 		prep_compound_gigantic_page(page, order);
@@ -1944,11 +1972,14 @@ static void __exit hugetlb_exit(void)
 	}
 
 	kobject_put(hugepages_kobj);
+	kfree(htlb_fault_mutex_table);
 }
 module_exit(hugetlb_exit);
 
 static int __init hugetlb_init(void)
 {
+	int i;
+
 	/* Some platform decide whether they support huge pages at boot
 	 * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when
 	 * there is no such support
@@ -1973,6 +2004,17 @@ static int __init hugetlb_init(void)
 	hugetlb_register_all_nodes();
 	hugetlb_cgroup_file_init();
 
+#ifdef CONFIG_SMP
+	num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus());
+#else
+	num_fault_mutexes = 1;
+#endif
+	htlb_fault_mutex_table =
+		kmalloc(sizeof(struct mutex) * num_fault_mutexes, GFP_KERNEL);
+	BUG_ON(!htlb_fault_mutex_table);
+
+	for (i = 0; i < num_fault_mutexes; i++)
+		mutex_init(&htlb_fault_mutex_table[i]);
 	return 0;
 }
 module_init(hugetlb_init);
@@ -2251,41 +2293,30 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma)
 	 * after this open call completes.  It is therefore safe to take a
 	 * new reference here without additional locking.
 	 */
-	if (resv)
+	if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
 		kref_get(&resv->refs);
 }
 
-static void resv_map_put(struct vm_area_struct *vma)
-{
-	struct resv_map *resv = vma_resv_map(vma);
-
-	if (!resv)
-		return;
-	kref_put(&resv->refs, resv_map_release);
-}
-
 static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 {
 	struct hstate *h = hstate_vma(vma);
 	struct resv_map *resv = vma_resv_map(vma);
 	struct hugepage_subpool *spool = subpool_vma(vma);
-	unsigned long reserve;
-	unsigned long start;
-	unsigned long end;
+	unsigned long reserve, start, end;
+
+	if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER))
+		return;
 
-	if (resv) {
-		start = vma_hugecache_offset(h, vma, vma->vm_start);
-		end = vma_hugecache_offset(h, vma, vma->vm_end);
+	start = vma_hugecache_offset(h, vma, vma->vm_start);
+	end = vma_hugecache_offset(h, vma, vma->vm_end);
 
-		reserve = (end - start) -
-			region_count(&resv->regions, start, end);
+	reserve = (end - start) - region_count(resv, start, end);
 
-		resv_map_put(vma);
+	kref_put(&resv->refs, resv_map_release);
 
-		if (reserve) {
-			hugetlb_acct_memory(h, -reserve);
-			hugepage_subpool_put_pages(spool, reserve);
-		}
+	if (reserve) {
+		hugetlb_acct_memory(h, -reserve);
+		hugepage_subpool_put_pages(spool, reserve);
 	}
 }
 
@@ -2761,15 +2792,14 @@ static bool hugetlbfs_pagecache_present(struct hstate *h,
 }
 
 static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
-			unsigned long address, pte_t *ptep, unsigned int flags)
+			   struct address_space *mapping, pgoff_t idx,
+			   unsigned long address, pte_t *ptep, unsigned int flags)
 {
 	struct hstate *h = hstate_vma(vma);
 	int ret = VM_FAULT_SIGBUS;
 	int anon_rmap = 0;
-	pgoff_t idx;
 	unsigned long size;
 	struct page *page;
-	struct address_space *mapping;
 	pte_t new_pte;
 	spinlock_t *ptl;
 
@@ -2784,9 +2814,6 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		return ret;
 	}
 
-	mapping = vma->vm_file->f_mapping;
-	idx = vma_hugecache_offset(h, vma, address);
-
 	/*
 	 * Use page lock to guard against racing truncation
 	 * before we get page_table_lock.
@@ -2871,8 +2898,7 @@ retry:
 	if (anon_rmap) {
 		ClearPagePrivate(page);
 		hugepage_add_new_anon_rmap(page, vma, address);
-	}
-	else
+	} else
 		page_dup_rmap(page);
 	new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
 				&& (vma->vm_flags & VM_SHARED)));
@@ -2896,17 +2922,53 @@ backout_unlocked:
 	goto out;
 }
 
+#ifdef CONFIG_SMP
+static u32 fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
+			    struct vm_area_struct *vma,
+			    struct address_space *mapping,
+			    pgoff_t idx, unsigned long address)
+{
+	unsigned long key[2];
+	u32 hash;
+
+	if (vma->vm_flags & VM_SHARED) {
+		key[0] = (unsigned long) mapping;
+		key[1] = idx;
+	} else {
+		key[0] = (unsigned long) mm;
+		key[1] = address >> huge_page_shift(h);
+	}
+
+	hash = jhash2((u32 *)&key, sizeof(key)/sizeof(u32), 0);
+
+	return hash & (num_fault_mutexes - 1);
+}
+#else
+/*
+ * For uniprocesor systems we always use a single mutex, so just
+ * return 0 and avoid the hashing overhead.
+ */
+static u32 fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
+			    struct vm_area_struct *vma,
+			    struct address_space *mapping,
+			    pgoff_t idx, unsigned long address)
+{
+	return 0;
+}
+#endif
+
 int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, unsigned int flags)
 {
-	pte_t *ptep;
-	pte_t entry;
+	pte_t *ptep, entry;
 	spinlock_t *ptl;
 	int ret;
+	u32 hash;
+	pgoff_t idx;
 	struct page *page = NULL;
 	struct page *pagecache_page = NULL;
-	static DEFINE_MUTEX(hugetlb_instantiation_mutex);
 	struct hstate *h = hstate_vma(vma);
+	struct address_space *mapping;
 
 	address &= huge_page_mask(h);
 
@@ -2925,15 +2987,20 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!ptep)
 		return VM_FAULT_OOM;
 
+	mapping = vma->vm_file->f_mapping;
+	idx = vma_hugecache_offset(h, vma, address);
+
 	/*
 	 * Serialize hugepage allocation and instantiation, so that we don't
 	 * get spurious allocation failures if two CPUs race to instantiate
 	 * the same page in the page cache.
 	 */
-	mutex_lock(&hugetlb_instantiation_mutex);
+	hash = fault_mutex_hash(h, mm, vma, mapping, idx, address);
+	mutex_lock(&htlb_fault_mutex_table[hash]);
+
 	entry = huge_ptep_get(ptep);
 	if (huge_pte_none(entry)) {
-		ret = hugetlb_no_page(mm, vma, address, ptep, flags);
+		ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags);
 		goto out_mutex;
 	}
 
@@ -3002,8 +3069,7 @@ out_ptl:
 	put_page(page);
 
 out_mutex:
-	mutex_unlock(&hugetlb_instantiation_mutex);
-
+	mutex_unlock(&htlb_fault_mutex_table[hash]);
 	return ret;
 }
 
@@ -3120,6 +3186,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	BUG_ON(address >= end);
 	flush_cache_range(vma, address, end);
 
+	mmu_notifier_invalidate_range_start(mm, start, end);
 	mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
 	for (; address < end; address += huge_page_size(h)) {
 		spinlock_t *ptl;
@@ -3149,6 +3216,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	 */
 	flush_tlb_range(vma, start, end);
 	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
+	mmu_notifier_invalidate_range_end(mm, start, end);
 
 	return pages << h->order;
 }
@@ -3161,6 +3229,7 @@ int hugetlb_reserve_pages(struct inode *inode,
 	long ret, chg;
 	struct hstate *h = hstate_inode(inode);
 	struct hugepage_subpool *spool = subpool_inode(inode);
+	struct resv_map *resv_map;
 
 	/*
 	 * Only apply hugepage reservation if asked. At fault time, an
@@ -3176,10 +3245,13 @@ int hugetlb_reserve_pages(struct inode *inode,
 	 * to reserve the full area even if read-only as mprotect() may be
 	 * called to make the mapping read-write. Assume !vma is a shm mapping
 	 */
-	if (!vma || vma->vm_flags & VM_MAYSHARE)
-		chg = region_chg(&inode->i_mapping->private_list, from, to);
-	else {
-		struct resv_map *resv_map = resv_map_alloc();
+	if (!vma || vma->vm_flags & VM_MAYSHARE) {
+		resv_map = inode_resv_map(inode);
+
+		chg = region_chg(resv_map, from, to);
+
+	} else {
+		resv_map = resv_map_alloc();
 		if (!resv_map)
 			return -ENOMEM;
 
@@ -3222,20 +3294,23 @@ int hugetlb_reserve_pages(struct inode *inode,
 	 * else has to be done for private mappings here
 	 */
 	if (!vma || vma->vm_flags & VM_MAYSHARE)
-		region_add(&inode->i_mapping->private_list, from, to);
+		region_add(resv_map, from, to);
 	return 0;
 out_err:
-	if (vma)
-		resv_map_put(vma);
+	if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
+		kref_put(&resv_map->refs, resv_map_release);
 	return ret;
 }
 
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 {
 	struct hstate *h = hstate_inode(inode);
-	long chg = region_truncate(&inode->i_mapping->private_list, offset);
+	struct resv_map *resv_map = inode_resv_map(inode);
+	long chg = 0;
 	struct hugepage_subpool *spool = subpool_inode(inode);
 
+	if (resv_map)
+		chg = region_truncate(resv_map, offset);
 	spin_lock(&inode->i_lock);
 	inode->i_blocks -= (blocks_per_huge_page(h) * freed);
 	spin_unlock(&inode->i_lock);
@@ -3446,7 +3521,7 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address,
 #else /* !CONFIG_ARCH_WANT_GENERAL_HUGETLB */
 
 /* Can be overriden by architectures */
-__attribute__((weak)) struct page *
+struct page * __weak
 follow_huge_pud(struct mm_struct *mm, unsigned long address,
 	       pud_t *pud, int write)
 {
diff --git a/mm/internal.h b/mm/internal.h
index 29e1e761f9eb..3e910000fda4 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -370,5 +370,6 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 #define ALLOC_HIGH		0x20 /* __GFP_HIGH set */
 #define ALLOC_CPUSET		0x40 /* check for correct cpuset */
 #define ALLOC_CMA		0x80 /* allow allocations from CMA areas */
+#define ALLOC_FAIR		0x100 /* fair zone allocation */
 
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 31f01c5011e5..c352c63e8de3 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -192,15 +192,15 @@ static struct kmem_cache *object_cache;
 static struct kmem_cache *scan_area_cache;
 
 /* set if tracing memory operations is enabled */
-static atomic_t kmemleak_enabled = ATOMIC_INIT(0);
+static int kmemleak_enabled;
 /* set in the late_initcall if there were no errors */
-static atomic_t kmemleak_initialized = ATOMIC_INIT(0);
+static int kmemleak_initialized;
 /* enables or disables early logging of the memory operations */
-static atomic_t kmemleak_early_log = ATOMIC_INIT(1);
+static int kmemleak_early_log = 1;
 /* set if a kmemleak warning was issued */
-static atomic_t kmemleak_warning = ATOMIC_INIT(0);
+static int kmemleak_warning;
 /* set if a fatal kmemleak error has occurred */
-static atomic_t kmemleak_error = ATOMIC_INIT(0);
+static int kmemleak_error;
 
 /* minimum and maximum address that may be valid pointers */
 static unsigned long min_addr = ULONG_MAX;
@@ -267,7 +267,7 @@ static void kmemleak_disable(void);
 #define kmemleak_warn(x...)	do {		\
 	pr_warning(x);				\
 	dump_stack();				\
-	atomic_set(&kmemleak_warning, 1);	\
+	kmemleak_warning = 1;			\
 } while (0)
 
 /*
@@ -805,7 +805,7 @@ static void __init log_early(int op_type, const void *ptr, size_t size,
 	unsigned long flags;
 	struct early_log *log;
 
-	if (atomic_read(&kmemleak_error)) {
+	if (kmemleak_error) {
 		/* kmemleak stopped recording, just count the requests */
 		crt_early_log++;
 		return;
@@ -840,7 +840,7 @@ static void early_alloc(struct early_log *log)
 	unsigned long flags;
 	int i;
 
-	if (!atomic_read(&kmemleak_enabled) || !log->ptr || IS_ERR(log->ptr))
+	if (!kmemleak_enabled || !log->ptr || IS_ERR(log->ptr))
 		return;
 
 	/*
@@ -893,9 +893,9 @@ void __ref kmemleak_alloc(const void *ptr, size_t size, int min_count,
 {
 	pr_debug("%s(0x%p, %zu, %d)\n", __func__, ptr, size, min_count);
 
-	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+	if (kmemleak_enabled && ptr && !IS_ERR(ptr))
 		create_object((unsigned long)ptr, size, min_count, gfp);
-	else if (atomic_read(&kmemleak_early_log))
+	else if (kmemleak_early_log)
 		log_early(KMEMLEAK_ALLOC, ptr, size, min_count);
 }
 EXPORT_SYMBOL_GPL(kmemleak_alloc);
@@ -919,11 +919,11 @@ void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size)
 	 * Percpu allocations are only scanned and not reported as leaks
 	 * (min_count is set to 0).
 	 */
-	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+	if (kmemleak_enabled && ptr && !IS_ERR(ptr))
 		for_each_possible_cpu(cpu)
 			create_object((unsigned long)per_cpu_ptr(ptr, cpu),
 				      size, 0, GFP_KERNEL);
-	else if (atomic_read(&kmemleak_early_log))
+	else if (kmemleak_early_log)
 		log_early(KMEMLEAK_ALLOC_PERCPU, ptr, size, 0);
 }
 EXPORT_SYMBOL_GPL(kmemleak_alloc_percpu);
@@ -939,9 +939,9 @@ void __ref kmemleak_free(const void *ptr)
 {
 	pr_debug("%s(0x%p)\n", __func__, ptr);
 
-	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+	if (kmemleak_enabled && ptr && !IS_ERR(ptr))
 		delete_object_full((unsigned long)ptr);
-	else if (atomic_read(&kmemleak_early_log))
+	else if (kmemleak_early_log)
 		log_early(KMEMLEAK_FREE, ptr, 0, 0);
 }
 EXPORT_SYMBOL_GPL(kmemleak_free);
@@ -959,9 +959,9 @@ void __ref kmemleak_free_part(const void *ptr, size_t size)
 {
 	pr_debug("%s(0x%p)\n", __func__, ptr);
 
-	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+	if (kmemleak_enabled && ptr && !IS_ERR(ptr))
 		delete_object_part((unsigned long)ptr, size);
-	else if (atomic_read(&kmemleak_early_log))
+	else if (kmemleak_early_log)
 		log_early(KMEMLEAK_FREE_PART, ptr, size, 0);
 }
 EXPORT_SYMBOL_GPL(kmemleak_free_part);
@@ -979,11 +979,11 @@ void __ref kmemleak_free_percpu(const void __percpu *ptr)
 
 	pr_debug("%s(0x%p)\n", __func__, ptr);
 
-	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+	if (kmemleak_enabled && ptr && !IS_ERR(ptr))
 		for_each_possible_cpu(cpu)
 			delete_object_full((unsigned long)per_cpu_ptr(ptr,
 								      cpu));
-	else if (atomic_read(&kmemleak_early_log))
+	else if (kmemleak_early_log)
 		log_early(KMEMLEAK_FREE_PERCPU, ptr, 0, 0);
 }
 EXPORT_SYMBOL_GPL(kmemleak_free_percpu);
@@ -999,9 +999,9 @@ void __ref kmemleak_not_leak(const void *ptr)
 {
 	pr_debug("%s(0x%p)\n", __func__, ptr);
 
-	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+	if (kmemleak_enabled && ptr && !IS_ERR(ptr))
 		make_gray_object((unsigned long)ptr);
-	else if (atomic_read(&kmemleak_early_log))
+	else if (kmemleak_early_log)
 		log_early(KMEMLEAK_NOT_LEAK, ptr, 0, 0);
 }
 EXPORT_SYMBOL(kmemleak_not_leak);
@@ -1019,9 +1019,9 @@ void __ref kmemleak_ignore(const void *ptr)
 {
 	pr_debug("%s(0x%p)\n", __func__, ptr);
 
-	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+	if (kmemleak_enabled && ptr && !IS_ERR(ptr))
 		make_black_object((unsigned long)ptr);
-	else if (atomic_read(&kmemleak_early_log))
+	else if (kmemleak_early_log)
 		log_early(KMEMLEAK_IGNORE, ptr, 0, 0);
 }
 EXPORT_SYMBOL(kmemleak_ignore);
@@ -1041,9 +1041,9 @@ void __ref kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp)
 {
 	pr_debug("%s(0x%p)\n", __func__, ptr);
 
-	if (atomic_read(&kmemleak_enabled) && ptr && size && !IS_ERR(ptr))
+	if (kmemleak_enabled && ptr && size && !IS_ERR(ptr))
 		add_scan_area((unsigned long)ptr, size, gfp);
-	else if (atomic_read(&kmemleak_early_log))
+	else if (kmemleak_early_log)
 		log_early(KMEMLEAK_SCAN_AREA, ptr, size, 0);
 }
 EXPORT_SYMBOL(kmemleak_scan_area);
@@ -1061,9 +1061,9 @@ void __ref kmemleak_no_scan(const void *ptr)
 {
 	pr_debug("%s(0x%p)\n", __func__, ptr);
 
-	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+	if (kmemleak_enabled && ptr && !IS_ERR(ptr))
 		object_no_scan((unsigned long)ptr);
-	else if (atomic_read(&kmemleak_early_log))
+	else if (kmemleak_early_log)
 		log_early(KMEMLEAK_NO_SCAN, ptr, 0, 0);
 }
 EXPORT_SYMBOL(kmemleak_no_scan);
@@ -1088,7 +1088,7 @@ static bool update_checksum(struct kmemleak_object *object)
  */
 static int scan_should_stop(void)
 {
-	if (!atomic_read(&kmemleak_enabled))
+	if (!kmemleak_enabled)
 		return 1;
 
 	/*
@@ -1545,11 +1545,6 @@ static int kmemleak_open(struct inode *inode, struct file *file)
 	return seq_open(file, &kmemleak_seq_ops);
 }
 
-static int kmemleak_release(struct inode *inode, struct file *file)
-{
-	return seq_release(inode, file);
-}
-
 static int dump_str_object_info(const char *str)
 {
 	unsigned long flags;
@@ -1616,9 +1611,6 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf,
 	int buf_size;
 	int ret;
 
-	if (!atomic_read(&kmemleak_enabled))
-		return -EBUSY;
-
 	buf_size = min(size, (sizeof(buf) - 1));
 	if (strncpy_from_user(buf, user_buf, buf_size) < 0)
 		return -EFAULT;
@@ -1628,9 +1620,18 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf,
 	if (ret < 0)
 		return ret;
 
-	if (strncmp(buf, "off", 3) == 0)
+	if (strncmp(buf, "off", 3) == 0) {
+		stop_scan_thread();
 		kmemleak_disable();
-	else if (strncmp(buf, "stack=on", 8) == 0)
+		goto out;
+	}
+
+	if (!kmemleak_enabled) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	if (strncmp(buf, "stack=on", 8) == 0)
 		kmemleak_stack_scan = 1;
 	else if (strncmp(buf, "stack=off", 9) == 0)
 		kmemleak_stack_scan = 0;
@@ -1674,7 +1675,7 @@ static const struct file_operations kmemleak_fops = {
 	.read		= seq_read,
 	.write		= kmemleak_write,
 	.llseek		= seq_lseek,
-	.release	= kmemleak_release,
+	.release	= seq_release,
 };
 
 /*
@@ -1695,6 +1696,11 @@ static void kmemleak_do_cleanup(struct work_struct *work)
 		list_for_each_entry_rcu(object, &object_list, object_list)
 			delete_object_full(object->pointer);
 		rcu_read_unlock();
+	} else {
+		pr_info("Disable kmemleak without freeing internal objects, "
+			"so you may still check information on memory leak. "
+			"You may reclaim memory by writing \"off\" to "
+			"/sys/kernel/debug/kmemleak\n");
 	}
 	mutex_unlock(&scan_mutex);
 }
@@ -1708,14 +1714,14 @@ static DECLARE_WORK(cleanup_work, kmemleak_do_cleanup);
 static void kmemleak_disable(void)
 {
 	/* atomically check whether it was already invoked */
-	if (atomic_cmpxchg(&kmemleak_error, 0, 1))
+	if (cmpxchg(&kmemleak_error, 0, 1))
 		return;
 
 	/* stop any memory operation tracing */
-	atomic_set(&kmemleak_enabled, 0);
+	kmemleak_enabled = 0;
 
 	/* check whether it is too early for a kernel thread */
-	if (atomic_read(&kmemleak_initialized))
+	if (kmemleak_initialized)
 		schedule_work(&cleanup_work);
 
 	pr_info("Kernel memory leak detector disabled\n");
@@ -1757,9 +1763,10 @@ void __init kmemleak_init(void)
 	int i;
 	unsigned long flags;
 
+	kmemleak_early_log = 0;
+
 #ifdef CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF
 	if (!kmemleak_skip_disable) {
-		atomic_set(&kmemleak_early_log, 0);
 		kmemleak_disable();
 		return;
 	}
@@ -1777,12 +1784,11 @@ void __init kmemleak_init(void)
 
 	/* the kernel is still in UP mode, so disabling the IRQs is enough */
 	local_irq_save(flags);
-	atomic_set(&kmemleak_early_log, 0);
-	if (atomic_read(&kmemleak_error)) {
+	if (kmemleak_error) {
 		local_irq_restore(flags);
 		return;
 	} else
-		atomic_set(&kmemleak_enabled, 1);
+		kmemleak_enabled = 1;
 	local_irq_restore(flags);
 
 	/*
@@ -1826,9 +1832,9 @@ void __init kmemleak_init(void)
 				      log->op_type);
 		}
 
-		if (atomic_read(&kmemleak_warning)) {
+		if (kmemleak_warning) {
 			print_log_trace(log);
-			atomic_set(&kmemleak_warning, 0);
+			kmemleak_warning = 0;
 		}
 	}
 }
@@ -1840,9 +1846,9 @@ static int __init kmemleak_late_init(void)
 {
 	struct dentry *dentry;
 
-	atomic_set(&kmemleak_initialized, 1);
+	kmemleak_initialized = 1;
 
-	if (atomic_read(&kmemleak_error)) {
+	if (kmemleak_error) {
 		/*
 		 * Some error occurred and kmemleak was disabled. There is a
 		 * small chance that kmemleak_disable() was called immediately
diff --git a/mm/list_lru.c b/mm/list_lru.c
index 72f9decb0104..f1a0db194173 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -87,11 +87,20 @@ restart:
 
 		ret = isolate(item, &nlru->lock, cb_arg);
 		switch (ret) {
+		case LRU_REMOVED_RETRY:
+			assert_spin_locked(&nlru->lock);
 		case LRU_REMOVED:
 			if (--nlru->nr_items == 0)
 				node_clear(nid, lru->active_nodes);
 			WARN_ON_ONCE(nlru->nr_items < 0);
 			isolated++;
+			/*
+			 * If the lru lock has been dropped, our list
+			 * traversal is now invalid and so we have to
+			 * restart from scratch.
+			 */
+			if (ret == LRU_REMOVED_RETRY)
+				goto restart;
 			break;
 		case LRU_ROTATE:
 			list_move_tail(item, &nlru->list);
@@ -103,6 +112,7 @@ restart:
 			 * The lru lock has been dropped, our list traversal is
 			 * now invalid and so we have to restart from scratch.
 			 */
+			assert_spin_locked(&nlru->lock);
 			goto restart;
 		default:
 			BUG();
@@ -114,7 +124,7 @@ restart:
 }
 EXPORT_SYMBOL_GPL(list_lru_walk_node);
 
-int list_lru_init(struct list_lru *lru)
+int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key)
 {
 	int i;
 	size_t size = sizeof(*lru->node) * nr_node_ids;
@@ -126,12 +136,14 @@ int list_lru_init(struct list_lru *lru)
 	nodes_clear(lru->active_nodes);
 	for (i = 0; i < nr_node_ids; i++) {
 		spin_lock_init(&lru->node[i].lock);
+		if (key)
+			lockdep_set_class(&lru->node[i].lock, key);
 		INIT_LIST_HEAD(&lru->node[i].list);
 		lru->node[i].nr_items = 0;
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(list_lru_init);
+EXPORT_SYMBOL_GPL(list_lru_init_key);
 
 void list_lru_destroy(struct list_lru *lru)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index dcc8153a1681..ef00c57fe6bb 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -921,8 +921,6 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
 					 struct page *page,
 					 bool anon, int nr_pages)
 {
-	preempt_disable();
-
 	/*
 	 * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is
 	 * counted as CACHE even if it's on ANON LRU.
@@ -947,8 +945,6 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
 	}
 
 	__this_cpu_add(memcg->stat->nr_page_events, nr_pages);
-
-	preempt_enable();
 }
 
 unsigned long
@@ -1075,22 +1071,15 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 	return mem_cgroup_from_css(task_css(p, memory_cgrp_id));
 }
 
-struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
+struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 {
 	struct mem_cgroup *memcg = NULL;
 
-	if (!mm)
-		return NULL;
-	/*
-	 * Because we have no locks, mm->owner's may be being moved to other
-	 * cgroup. We use css_tryget() here even if this looks
-	 * pessimistic (rather than adding locks here).
-	 */
 	rcu_read_lock();
 	do {
 		memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
 		if (unlikely(!memcg))
-			break;
+			memcg = root_mem_cgroup;
 	} while (!css_tryget(&memcg->css));
 	rcu_read_unlock();
 	return memcg;
@@ -1486,7 +1475,7 @@ bool task_in_mem_cgroup(struct task_struct *task,
 
 	p = find_lock_task_mm(task);
 	if (p) {
-		curr = try_get_mem_cgroup_from_mm(p->mm);
+		curr = get_mem_cgroup_from_mm(p->mm);
 		task_unlock(p);
 	} else {
 		/*
@@ -1500,8 +1489,6 @@ bool task_in_mem_cgroup(struct task_struct *task,
 			css_get(&curr->css);
 		rcu_read_unlock();
 	}
-	if (!curr)
-		return false;
 	/*
 	 * We should check use_hierarchy of "memcg" not "curr". Because checking
 	 * use_hierarchy of "curr" here make this function true if hierarchy is
@@ -2588,7 +2575,7 @@ static int memcg_cpu_hotplug_callback(struct notifier_block *nb,
 }
 
 
-/* See __mem_cgroup_try_charge() for details */
+/* See mem_cgroup_try_charge() for details */
 enum {
 	CHARGE_OK,		/* success */
 	CHARGE_RETRY,		/* need to retry but retry is not bad */
@@ -2661,45 +2648,34 @@ static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	return CHARGE_NOMEM;
 }
 
-/*
- * __mem_cgroup_try_charge() does
- * 1. detect memcg to be charged against from passed *mm and *ptr,
- * 2. update res_counter
- * 3. call memory reclaim if necessary.
- *
- * In some special case, if the task is fatal, fatal_signal_pending() or
- * has TIF_MEMDIE, this function returns -EINTR while writing root_mem_cgroup
- * to *ptr. There are two reasons for this. 1: fatal threads should quit as soon
- * as possible without any hazards. 2: all pages should have a valid
- * pc->mem_cgroup. If mm is NULL and the caller doesn't pass a valid memcg
- * pointer, that is treated as a charge to root_mem_cgroup.
- *
- * So __mem_cgroup_try_charge() will return
- *  0       ...  on success, filling *ptr with a valid memcg pointer.
- *  -ENOMEM ...  charge failure because of resource limits.
- *  -EINTR  ...  if thread is fatal. *ptr is filled with root_mem_cgroup.
+/**
+ * mem_cgroup_try_charge - try charging a memcg
+ * @memcg: memcg to charge
+ * @nr_pages: number of pages to charge
+ * @oom: trigger OOM if reclaim fails
  *
- * Unlike the exported interface, an "oom" parameter is added. if oom==true,
- * the oom-killer can be invoked.
+ * Returns 0 if @memcg was charged successfully, -EINTR if the charge
+ * was bypassed to root_mem_cgroup, and -ENOMEM if the charge failed.
  */
-static int __mem_cgroup_try_charge(struct mm_struct *mm,
-				   gfp_t gfp_mask,
-				   unsigned int nr_pages,
-				   struct mem_cgroup **ptr,
-				   bool oom)
+static int mem_cgroup_try_charge(struct mem_cgroup *memcg,
+				 gfp_t gfp_mask,
+				 unsigned int nr_pages,
+				 bool oom)
 {
 	unsigned int batch = max(CHARGE_BATCH, nr_pages);
 	int nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
-	struct mem_cgroup *memcg = NULL;
 	int ret;
 
+	if (mem_cgroup_is_root(memcg))
+		goto done;
 	/*
-	 * Unlike gloval-vm's OOM-kill, we're not in memory shortage
-	 * in system level. So, allow to go ahead dying process in addition to
-	 * MEMDIE process.
+	 * Unlike in global OOM situations, memcg is not in a physical
+	 * memory shortage.  Allow dying and OOM-killed tasks to
+	 * bypass the last charges so that they can exit quickly and
+	 * free their memory.
 	 */
-	if (unlikely(test_thread_flag(TIF_MEMDIE)
-		     || fatal_signal_pending(current)))
+	if (unlikely(test_thread_flag(TIF_MEMDIE) ||
+		     fatal_signal_pending(current)))
 		goto bypass;
 
 	if (unlikely(task_in_memcg_oom(current)))
@@ -2707,73 +2683,16 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 
 	if (gfp_mask & __GFP_NOFAIL)
 		oom = false;
-
-	/*
-	 * We always charge the cgroup the mm_struct belongs to.
-	 * The mm_struct's mem_cgroup changes on task migration if the
-	 * thread group leader migrates. It's possible that mm is not
-	 * set, if so charge the root memcg (happens for pagecache usage).
-	 */
-	if (!*ptr && !mm)
-		*ptr = root_mem_cgroup;
 again:
-	if (*ptr) { /* css should be a valid one */
-		memcg = *ptr;
-		if (mem_cgroup_is_root(memcg))
-			goto done;
-		if (consume_stock(memcg, nr_pages))
-			goto done;
-		css_get(&memcg->css);
-	} else {
-		struct task_struct *p;
-
-		rcu_read_lock();
-		p = rcu_dereference(mm->owner);
-		/*
-		 * Because we don't have task_lock(), "p" can exit.
-		 * In that case, "memcg" can point to root or p can be NULL with
-		 * race with swapoff. Then, we have small risk of mis-accouning.
-		 * But such kind of mis-account by race always happens because
-		 * we don't have cgroup_mutex(). It's overkill and we allo that
-		 * small race, here.
-		 * (*) swapoff at el will charge against mm-struct not against
-		 * task-struct. So, mm->owner can be NULL.
-		 */
-		memcg = mem_cgroup_from_task(p);
-		if (!memcg)
-			memcg = root_mem_cgroup;
-		if (mem_cgroup_is_root(memcg)) {
-			rcu_read_unlock();
-			goto done;
-		}
-		if (consume_stock(memcg, nr_pages)) {
-			/*
-			 * It seems dagerous to access memcg without css_get().
-			 * But considering how consume_stok works, it's not
-			 * necessary. If consume_stock success, some charges
-			 * from this memcg are cached on this cpu. So, we
-			 * don't need to call css_get()/css_tryget() before
-			 * calling consume_stock().
-			 */
-			rcu_read_unlock();
-			goto done;
-		}
-		/* after here, we may be blocked. we need to get refcnt */
-		if (!css_tryget(&memcg->css)) {
-			rcu_read_unlock();
-			goto again;
-		}
-		rcu_read_unlock();
-	}
+	if (consume_stock(memcg, nr_pages))
+		goto done;
 
 	do {
 		bool invoke_oom = oom && !nr_oom_retries;
 
 		/* If killed, bypass charge */
-		if (fatal_signal_pending(current)) {
-			css_put(&memcg->css);
+		if (fatal_signal_pending(current))
 			goto bypass;
-		}
 
 		ret = mem_cgroup_do_charge(memcg, gfp_mask, batch,
 					   nr_pages, invoke_oom);
@@ -2782,17 +2701,12 @@ again:
 			break;
 		case CHARGE_RETRY: /* not in OOM situation but retry */
 			batch = nr_pages;
-			css_put(&memcg->css);
-			memcg = NULL;
 			goto again;
 		case CHARGE_WOULDBLOCK: /* !__GFP_WAIT */
-			css_put(&memcg->css);
 			goto nomem;
 		case CHARGE_NOMEM: /* OOM routine works */
-			if (!oom || invoke_oom) {
-				css_put(&memcg->css);
+			if (!oom || invoke_oom)
 				goto nomem;
-			}
 			nr_oom_retries--;
 			break;
 		}
@@ -2800,20 +2714,44 @@ again:
 
 	if (batch > nr_pages)
 		refill_stock(memcg, batch - nr_pages);
-	css_put(&memcg->css);
 done:
-	*ptr = memcg;
 	return 0;
 nomem:
-	if (!(gfp_mask & __GFP_NOFAIL)) {
-		*ptr = NULL;
+	if (!(gfp_mask & __GFP_NOFAIL))
 		return -ENOMEM;
-	}
 bypass:
-	*ptr = root_mem_cgroup;
 	return -EINTR;
 }
 
+/**
+ * mem_cgroup_try_charge_mm - try charging a mm
+ * @mm: mm_struct to charge
+ * @nr_pages: number of pages to charge
+ * @oom: trigger OOM if reclaim fails
+ *
+ * Returns the charged mem_cgroup associated with the given mm_struct or
+ * NULL the charge failed.
+ */
+static struct mem_cgroup *mem_cgroup_try_charge_mm(struct mm_struct *mm,
+				 gfp_t gfp_mask,
+				 unsigned int nr_pages,
+				 bool oom)
+
+{
+	struct mem_cgroup *memcg;
+	int ret;
+
+	memcg = get_mem_cgroup_from_mm(mm);
+	ret = mem_cgroup_try_charge(memcg, gfp_mask, nr_pages, oom);
+	css_put(&memcg->css);
+	if (ret == -EINTR)
+		memcg = root_mem_cgroup;
+	else if (ret)
+		memcg = NULL;
+
+	return memcg;
+}
+
 /*
  * Somemtimes we have to undo a charge we got by try_charge().
  * This function is for that and do uncharge, put css's refcnt.
@@ -3009,20 +2947,17 @@ static int mem_cgroup_slabinfo_read(struct seq_file *m, void *v)
 static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
 {
 	struct res_counter *fail_res;
-	struct mem_cgroup *_memcg;
 	int ret = 0;
 
 	ret = res_counter_charge(&memcg->kmem, size, &fail_res);
 	if (ret)
 		return ret;
 
-	_memcg = memcg;
-	ret = __mem_cgroup_try_charge(NULL, gfp, size >> PAGE_SHIFT,
-				      &_memcg, oom_gfp_allowed(gfp));
-
+	ret = mem_cgroup_try_charge(memcg, gfp, size >> PAGE_SHIFT,
+				    oom_gfp_allowed(gfp));
 	if (ret == -EINTR)  {
 		/*
-		 * __mem_cgroup_try_charge() chosed to bypass to root due to
+		 * mem_cgroup_try_charge() chosed to bypass to root due to
 		 * OOM kill or fatal signal.  Since our only options are to
 		 * either fail the allocation or charge it to this cgroup, do
 		 * it as a temporary condition. But we can't fail. From a
@@ -3032,7 +2967,7 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
 		 *
 		 * This condition will only trigger if the task entered
 		 * memcg_charge_kmem in a sane state, but was OOM-killed during
-		 * __mem_cgroup_try_charge() above. Tasks that were already
+		 * mem_cgroup_try_charge() above. Tasks that were already
 		 * dying when the allocation triggers should have been already
 		 * directed to the root cgroup in memcontrol.h
 		 */
@@ -3637,15 +3572,7 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
 	if (!current->mm || current->memcg_kmem_skip_account)
 		return true;
 
-	memcg = try_get_mem_cgroup_from_mm(current->mm);
-
-	/*
-	 * very rare case described in mem_cgroup_from_task. Unfortunately there
-	 * isn't much we can do without complicating this too much, and it would
-	 * be gfp-dependent anyway. Just let it go
-	 */
-	if (unlikely(!memcg))
-		return true;
+	memcg = get_mem_cgroup_from_mm(current->mm);
 
 	if (!memcg_can_account_kmem(memcg)) {
 		css_put(&memcg->css);
@@ -3748,19 +3675,6 @@ void mem_cgroup_split_huge_fixup(struct page *head)
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-static inline
-void mem_cgroup_move_account_page_stat(struct mem_cgroup *from,
-					struct mem_cgroup *to,
-					unsigned int nr_pages,
-					enum mem_cgroup_stat_index idx)
-{
-	/* Update stat data for mem_cgroup */
-	preempt_disable();
-	__this_cpu_sub(from->stat->count[idx], nr_pages);
-	__this_cpu_add(to->stat->count[idx], nr_pages);
-	preempt_enable();
-}
-
 /**
  * mem_cgroup_move_account - move account of the page
  * @page: the page
@@ -3806,13 +3720,19 @@ static int mem_cgroup_move_account(struct page *page,
 
 	move_lock_mem_cgroup(from, &flags);
 
-	if (!anon && page_mapped(page))
-		mem_cgroup_move_account_page_stat(from, to, nr_pages,
-			MEM_CGROUP_STAT_FILE_MAPPED);
+	if (!anon && page_mapped(page)) {
+		__this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED],
+			       nr_pages);
+		__this_cpu_add(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED],
+			       nr_pages);
+	}
 
-	if (PageWriteback(page))
-		mem_cgroup_move_account_page_stat(from, to, nr_pages,
-			MEM_CGROUP_STAT_WRITEBACK);
+	if (PageWriteback(page)) {
+		__this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_WRITEBACK],
+			       nr_pages);
+		__this_cpu_add(to->stat->count[MEM_CGROUP_STAT_WRITEBACK],
+			       nr_pages);
+	}
 
 	mem_cgroup_charge_statistics(from, page, anon, -nr_pages);
 
@@ -3898,19 +3818,19 @@ out:
 	return ret;
 }
 
-/*
- * Charge the memory controller for page usage.
- * Return
- * 0 if the charge was successful
- * < 0 if the cgroup is over its limit
- */
-static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
-				gfp_t gfp_mask, enum charge_type ctype)
+int mem_cgroup_charge_anon(struct page *page,
+			      struct mm_struct *mm, gfp_t gfp_mask)
 {
-	struct mem_cgroup *memcg = NULL;
 	unsigned int nr_pages = 1;
+	struct mem_cgroup *memcg;
 	bool oom = true;
-	int ret;
+
+	if (mem_cgroup_disabled())
+		return 0;
+
+	VM_BUG_ON_PAGE(page_mapped(page), page);
+	VM_BUG_ON_PAGE(page->mapping && !PageAnon(page), page);
+	VM_BUG_ON(!mm);
 
 	if (PageTransHuge(page)) {
 		nr_pages <<= compound_order(page);
@@ -3922,25 +3842,14 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 		oom = false;
 	}
 
-	ret = __mem_cgroup_try_charge(mm, gfp_mask, nr_pages, &memcg, oom);
-	if (ret == -ENOMEM)
-		return ret;
-	__mem_cgroup_commit_charge(memcg, page, nr_pages, ctype, false);
+	memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, nr_pages, oom);
+	if (!memcg)
+		return -ENOMEM;
+	__mem_cgroup_commit_charge(memcg, page, nr_pages,
+				   MEM_CGROUP_CHARGE_TYPE_ANON, false);
 	return 0;
 }
 
-int mem_cgroup_newpage_charge(struct page *page,
-			      struct mm_struct *mm, gfp_t gfp_mask)
-{
-	if (mem_cgroup_disabled())
-		return 0;
-	VM_BUG_ON_PAGE(page_mapped(page), page);
-	VM_BUG_ON_PAGE(page->mapping && !PageAnon(page), page);
-	VM_BUG_ON(!mm);
-	return mem_cgroup_charge_common(page, mm, gfp_mask,
-					MEM_CGROUP_CHARGE_TYPE_ANON);
-}
-
 /*
  * While swap-in, try_charge -> commit or cancel, the page is locked.
  * And when try_charge() successfully returns, one refcnt to memcg without
@@ -3952,7 +3861,7 @@ static int __mem_cgroup_try_charge_swapin(struct mm_struct *mm,
 					  gfp_t mask,
 					  struct mem_cgroup **memcgp)
 {
-	struct mem_cgroup *memcg;
+	struct mem_cgroup *memcg = NULL;
 	struct page_cgroup *pc;
 	int ret;
 
@@ -3965,31 +3874,29 @@ static int __mem_cgroup_try_charge_swapin(struct mm_struct *mm,
 	 * in turn serializes uncharging.
 	 */
 	if (PageCgroupUsed(pc))
-		return 0;
-	if (!do_swap_account)
-		goto charge_cur_mm;
-	memcg = try_get_mem_cgroup_from_page(page);
+		goto out;
+	if (do_swap_account)
+		memcg = try_get_mem_cgroup_from_page(page);
 	if (!memcg)
-		goto charge_cur_mm;
-	*memcgp = memcg;
-	ret = __mem_cgroup_try_charge(NULL, mask, 1, memcgp, true);
+		memcg = get_mem_cgroup_from_mm(mm);
+	ret = mem_cgroup_try_charge(memcg, mask, 1, true);
 	css_put(&memcg->css);
 	if (ret == -EINTR)
-		ret = 0;
-	return ret;
-charge_cur_mm:
-	ret = __mem_cgroup_try_charge(mm, mask, 1, memcgp, true);
-	if (ret == -EINTR)
-		ret = 0;
-	return ret;
+		memcg = root_mem_cgroup;
+	else if (ret)
+		return ret;
+out:
+	*memcgp = memcg;
+	return 0;
 }
 
 int mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct page *page,
 				 gfp_t gfp_mask, struct mem_cgroup **memcgp)
 {
-	*memcgp = NULL;
-	if (mem_cgroup_disabled())
+	if (mem_cgroup_disabled()) {
+		*memcgp = NULL;
 		return 0;
+	}
 	/*
 	 * A racing thread's fault, or swapoff, may have already
 	 * updated the pte, and even removed page from swap cache: in
@@ -3997,12 +3904,13 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct page *page,
 	 * there's also a KSM case which does need to charge the page.
 	 */
 	if (!PageSwapCache(page)) {
-		int ret;
+		struct mem_cgroup *memcg;
 
-		ret = __mem_cgroup_try_charge(mm, gfp_mask, 1, memcgp, true);
-		if (ret == -EINTR)
-			ret = 0;
-		return ret;
+		memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true);
+		if (!memcg)
+			return -ENOMEM;
+		*memcgp = memcg;
+		return 0;
 	}
 	return __mem_cgroup_try_charge_swapin(mm, page, gfp_mask, memcgp);
 }
@@ -4046,11 +3954,11 @@ void mem_cgroup_commit_charge_swapin(struct page *page,
 					  MEM_CGROUP_CHARGE_TYPE_ANON);
 }
 
-int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
+int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask)
 {
-	struct mem_cgroup *memcg = NULL;
 	enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE;
+	struct mem_cgroup *memcg;
 	int ret;
 
 	if (mem_cgroup_disabled())
@@ -4058,15 +3966,28 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 	if (PageCompound(page))
 		return 0;
 
-	if (!PageSwapCache(page))
-		ret = mem_cgroup_charge_common(page, mm, gfp_mask, type);
-	else { /* page is swapcache/shmem */
+	if (PageSwapCache(page)) { /* shmem */
 		ret = __mem_cgroup_try_charge_swapin(mm, page,
 						     gfp_mask, &memcg);
-		if (!ret)
-			__mem_cgroup_commit_charge_swapin(page, memcg, type);
+		if (ret)
+			return ret;
+		__mem_cgroup_commit_charge_swapin(page, memcg, type);
+		return 0;
 	}
-	return ret;
+
+	/*
+	 * Page cache insertions can happen without an actual mm
+	 * context, e.g. during disk probing on boot.
+	 */
+	if (unlikely(!mm))
+		memcg = root_mem_cgroup;
+	else {
+		memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true);
+		if (!memcg)
+			return -ENOMEM;
+	}
+	__mem_cgroup_commit_charge(memcg, page, 1, type, false);
+	return 0;
 }
 
 static void mem_cgroup_do_uncharge(struct mem_cgroup *memcg,
@@ -6678,8 +6599,7 @@ one_by_one:
 			batch_count = PRECHARGE_COUNT_AT_ONCE;
 			cond_resched();
 		}
-		ret = __mem_cgroup_try_charge(NULL,
-					GFP_KERNEL, 1, &memcg, false);
+		ret = mem_cgroup_try_charge(memcg, GFP_KERNEL, 1, false);
 		if (ret)
 			/* mem_cgroup_clear_mc() will do uncharge later */
 			return ret;
@@ -6874,30 +6794,29 @@ static inline enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
 }
 #endif
 
-static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
+static int mem_cgroup_count_precharge_pte(pte_t *pte,
 					unsigned long addr, unsigned long end,
 					struct mm_walk *walk)
 {
-	struct vm_area_struct *vma = walk->private;
-	pte_t *pte;
+	if (get_mctgt_type(walk->vma, addr, *pte, NULL))
+		mc.precharge++;	/* increment precharge temporarily */
+	return 0;
+}
+
+static int mem_cgroup_count_precharge_pmd(pmd_t *pmd,
+					unsigned long addr, unsigned long end,
+					struct mm_walk *walk)
+{
+	struct vm_area_struct *vma = walk->vma;
 	spinlock_t *ptl;
 
 	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE)
 			mc.precharge += HPAGE_PMD_NR;
 		spin_unlock(ptl);
-		return 0;
+		/* don't call mem_cgroup_count_precharge_pte() */
+		walk->skip = 1;
 	}
-
-	if (pmd_trans_unstable(pmd))
-		return 0;
-	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	for (; addr != end; pte++, addr += PAGE_SIZE)
-		if (get_mctgt_type(vma, addr, *pte, NULL))
-			mc.precharge++;	/* increment precharge temporarily */
-	pte_unmap_unlock(pte - 1, ptl);
-	cond_resched();
-
 	return 0;
 }
 
@@ -6906,18 +6825,14 @@ static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm)
 	unsigned long precharge;
 	struct vm_area_struct *vma;
 
+	struct mm_walk mem_cgroup_count_precharge_walk = {
+		.pmd_entry = mem_cgroup_count_precharge_pmd,
+		.pte_entry = mem_cgroup_count_precharge_pte,
+		.mm = mm,
+	};
 	down_read(&mm->mmap_sem);
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
-		struct mm_walk mem_cgroup_count_precharge_walk = {
-			.pmd_entry = mem_cgroup_count_precharge_pte_range,
-			.mm = mm,
-			.private = vma,
-		};
-		if (is_vm_hugetlb_page(vma))
-			continue;
-		walk_page_range(vma->vm_start, vma->vm_end,
-					&mem_cgroup_count_precharge_walk);
-	}
+	for (vma = mm->mmap; vma; vma = vma->vm_next)
+		walk_page_vma(vma, &mem_cgroup_count_precharge_walk);
 	up_read(&mm->mmap_sem);
 
 	precharge = mc.precharge;
@@ -7056,7 +6971,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 				struct mm_walk *walk)
 {
 	int ret = 0;
-	struct vm_area_struct *vma = walk->private;
+	struct vm_area_struct *vma = walk->vma;
 	pte_t *pte;
 	spinlock_t *ptl;
 	enum mc_target_type target_type;
@@ -7157,6 +7072,10 @@ put:			/* get_mctgt_type() gets the page */
 static void mem_cgroup_move_charge(struct mm_struct *mm)
 {
 	struct vm_area_struct *vma;
+	struct mm_walk mem_cgroup_move_charge_walk = {
+		.pmd_entry = mem_cgroup_move_charge_pte_range,
+		.mm = mm,
+	};
 
 	lru_add_drain_all();
 retry:
@@ -7172,24 +7091,8 @@ retry:
 		cond_resched();
 		goto retry;
 	}
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
-		int ret;
-		struct mm_walk mem_cgroup_move_charge_walk = {
-			.pmd_entry = mem_cgroup_move_charge_pte_range,
-			.mm = mm,
-			.private = vma,
-		};
-		if (is_vm_hugetlb_page(vma))
-			continue;
-		ret = walk_page_range(vma->vm_start, vma->vm_end,
-						&mem_cgroup_move_charge_walk);
-		if (ret)
-			/*
-			 * means we have consumed all precharges and failed in
-			 * doing additional charge. Just abandon here.
-			 */
-			break;
-	}
+	for (vma = mm->mmap; vma; vma = vma->vm_next)
+		walk_page_vma(vma, &mem_cgroup_move_charge_walk);
 	up_read(&mm->mmap_sem);
 }
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 35ef28acf137..12ac5df4d49a 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -202,7 +202,7 @@ static int kill_proc(struct task_struct *t, unsigned long addr, int trapno,
 #ifdef __ARCH_SI_TRAPNO
 	si.si_trapno = trapno;
 #endif
-	si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT;
+	si.si_addr_lsb = page_size_order(page) + PAGE_SHIFT;
 
 	if ((flags & MF_ACTION_REQUIRED) && t == current) {
 		si.si_code = BUS_MCEERR_AR;
@@ -404,7 +404,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 	if (av == NULL)	/* Not actually mapped anymore */
 		return;
 
-	pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+	pgoff = page_pgoff(page);
 	read_lock(&tasklist_lock);
 	for_each_process (tsk) {
 		struct anon_vma_chain *vmac;
@@ -437,7 +437,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 	mutex_lock(&mapping->i_mmap_mutex);
 	read_lock(&tasklist_lock);
 	for_each_process(tsk) {
-		pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+		pgoff_t pgoff = page_pgoff(page);
 
 		if (!task_early_kill(tsk))
 			continue;
diff --git a/mm/memory.c b/mm/memory.c
index 22dfa617bddb..b02c584d8891 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -60,6 +60,7 @@
 #include <linux/migrate.h>
 #include <linux/string.h>
 #include <linux/dma-debug.h>
+#include <linux/debugfs.h>
 
 #include <asm/io.h>
 #include <asm/pgalloc.h>
@@ -1320,9 +1321,9 @@ static void unmap_single_vma(struct mmu_gather *tlb,
 			 * It is undesirable to test vma->vm_file as it
 			 * should be non-null for valid hugetlb area.
 			 * However, vm_file will be NULL in the error
-			 * cleanup path of do_mmap_pgoff. When
+			 * cleanup path of mmap_region. When
 			 * hugetlbfs ->mmap method fails,
-			 * do_mmap_pgoff() nullifies vma->vm_file
+			 * mmap_region() nullifies vma->vm_file
 			 * before calling this function to clean up.
 			 * Since no pte has actually been setup, it is
 			 * safe to do nothing in this case.
@@ -2587,6 +2588,38 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo
 }
 
 /*
+ * Notify the address space that the page is about to become writable so that
+ * it can prohibit this or wait for the page to get into an appropriate state.
+ *
+ * We do this without the lock held, so that it can sleep if it needs to.
+ */
+static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page,
+	       unsigned long address)
+{
+	struct vm_fault vmf;
+	int ret;
+
+	vmf.virtual_address = (void __user *)(address & PAGE_MASK);
+	vmf.pgoff = page->index;
+	vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
+	vmf.page = page;
+
+	ret = vma->vm_ops->page_mkwrite(vma, &vmf);
+	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
+		return ret;
+	if (unlikely(!(ret & VM_FAULT_LOCKED))) {
+		lock_page(page);
+		if (!page->mapping) {
+			unlock_page(page);
+			return 0; /* retry */
+		}
+		ret |= VM_FAULT_LOCKED;
+	} else
+		VM_BUG_ON_PAGE(!PageLocked(page), page);
+	return ret;
+}
+
+/*
  * This routine handles present pages, when users try to write
  * to a shared page. It is done by copying the page to a new address
  * and decrementing the shared-page counter for the old page.
@@ -2668,42 +2701,15 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 * get_user_pages(.write=1, .force=1).
 		 */
 		if (vma->vm_ops && vma->vm_ops->page_mkwrite) {
-			struct vm_fault vmf;
 			int tmp;
-
-			vmf.virtual_address = (void __user *)(address &
-								PAGE_MASK);
-			vmf.pgoff = old_page->index;
-			vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
-			vmf.page = old_page;
-
-			/*
-			 * Notify the address space that the page is about to
-			 * become writable so that it can prohibit this or wait
-			 * for the page to get into an appropriate state.
-			 *
-			 * We do this without the lock held, so that it can
-			 * sleep if it needs to.
-			 */
 			page_cache_get(old_page);
 			pte_unmap_unlock(page_table, ptl);
-
-			tmp = vma->vm_ops->page_mkwrite(vma, &vmf);
-			if (unlikely(tmp &
-					(VM_FAULT_ERROR | VM_FAULT_NOPAGE))) {
-				ret = tmp;
-				goto unwritable_page;
+			tmp = do_page_mkwrite(vma, old_page, address);
+			if (unlikely(!tmp || (tmp &
+					(VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
+				page_cache_release(old_page);
+				return tmp;
 			}
-			if (unlikely(!(tmp & VM_FAULT_LOCKED))) {
-				lock_page(old_page);
-				if (!old_page->mapping) {
-					ret = 0; /* retry the fault */
-					unlock_page(old_page);
-					goto unwritable_page;
-				}
-			} else
-				VM_BUG_ON_PAGE(!PageLocked(old_page), old_page);
-
 			/*
 			 * Since we dropped the lock we need to revalidate
 			 * the PTE as someone else may have changed it.  If
@@ -2748,7 +2754,7 @@ reuse:
 		 * bit after it clear all dirty ptes, but before a racing
 		 * do_wp_page installs a dirty pte.
 		 *
-		 * __do_fault is protected similarly.
+		 * do_shared_fault is protected similarly.
 		 */
 		if (!page_mkwrite) {
 			wait_on_page_locked(dirty_page);
@@ -2798,7 +2804,7 @@ gotten:
 	}
 	__SetPageUptodate(new_page);
 
-	if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))
+	if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL))
 		goto oom_free_new;
 
 	mmun_start  = address & PAGE_MASK;
@@ -2892,10 +2898,6 @@ oom:
 	if (old_page)
 		page_cache_release(old_page);
 	return VM_FAULT_OOM;
-
-unwritable_page:
-	page_cache_release(old_page);
-	return ret;
 }
 
 static void unmap_mapping_range_vma(struct vm_area_struct *vma,
@@ -3255,7 +3257,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 */
 	__SetPageUptodate(page);
 
-	if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))
+	if (mem_cgroup_charge_anon(page, mm, GFP_KERNEL))
 		goto oom_free_page;
 
 	entry = mk_pte(page, vma->vm_page_prot);
@@ -3286,53 +3288,11 @@ oom:
 	return VM_FAULT_OOM;
 }
 
-/*
- * __do_fault() tries to create a new page mapping. It aggressively
- * tries to share with existing pages, but makes a separate copy if
- * the FAULT_FLAG_WRITE is set in the flags parameter in order to avoid
- * the next page fault.
- *
- * As this is called only for pages that do not currently exist, we
- * do not need to flush old virtual caches or the TLB.
- *
- * We enter with non-exclusive mmap_sem (to exclude vma changes,
- * but allow concurrent faults), and pte neither mapped nor locked.
- * We return with mmap_sem still held, but pte unmapped and unlocked.
- */
-static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
-		unsigned long address, pmd_t *pmd,
-		pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
+static int __do_fault(struct vm_area_struct *vma, unsigned long address,
+		pgoff_t pgoff, unsigned int flags, struct page **page)
 {
-	pte_t *page_table;
-	spinlock_t *ptl;
-	struct page *page;
-	struct page *cow_page;
-	pte_t entry;
-	int anon = 0;
-	struct page *dirty_page = NULL;
 	struct vm_fault vmf;
 	int ret;
-	int page_mkwrite = 0;
-
-	/*
-	 * If we do COW later, allocate page befor taking lock_page()
-	 * on the file cache page. This will reduce lock holding time.
-	 */
-	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
-
-		if (unlikely(anon_vma_prepare(vma)))
-			return VM_FAULT_OOM;
-
-		cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
-		if (!cow_page)
-			return VM_FAULT_OOM;
-
-		if (mem_cgroup_newpage_charge(cow_page, mm, GFP_KERNEL)) {
-			page_cache_release(cow_page);
-			return VM_FAULT_OOM;
-		}
-	} else
-		cow_page = NULL;
 
 	vmf.virtual_address = (void __user *)(address & PAGE_MASK);
 	vmf.pgoff = pgoff;
@@ -3340,151 +3300,312 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	vmf.page = NULL;
 
 	ret = vma->vm_ops->fault(vma, &vmf);
-	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE |
-			    VM_FAULT_RETRY)))
-		goto uncharge_out;
+	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
+		return ret;
 
 	if (unlikely(PageHWPoison(vmf.page))) {
 		if (ret & VM_FAULT_LOCKED)
 			unlock_page(vmf.page);
-		ret = VM_FAULT_HWPOISON;
 		page_cache_release(vmf.page);
-		goto uncharge_out;
+		return VM_FAULT_HWPOISON;
 	}
 
-	/*
-	 * For consistency in subsequent calls, make the faulted page always
-	 * locked.
-	 */
 	if (unlikely(!(ret & VM_FAULT_LOCKED)))
 		lock_page(vmf.page);
 	else
 		VM_BUG_ON_PAGE(!PageLocked(vmf.page), vmf.page);
 
+	*page = vmf.page;
+	return ret;
+}
+
+/**
+ * do_set_pte - setup new PTE entry for given page and add reverse page mapping.
+ *
+ * @vma: virtual memory area
+ * @address: user virtual address
+ * @page: page to map
+ * @pte: pointer to target page table entry
+ * @write: true, if new entry is writable
+ * @anon: true, if it's anonymous page
+ *
+ * Caller must hold page table lock relevant for @pte.
+ *
+ * Target users are page handler itself and implementations of
+ * vm_ops->map_pages.
+ */
+void do_set_pte(struct vm_area_struct *vma, unsigned long address,
+		struct page *page, pte_t *pte, bool write, bool anon)
+{
+	pte_t entry;
+
+	flush_icache_page(vma, page);
+	entry = mk_pte(page, vma->vm_page_prot);
+	if (write)
+		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+	else if (pte_file(*pte) && pte_file_soft_dirty(*pte))
+		pte_mksoft_dirty(entry);
+	if (anon) {
+		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
+		page_add_new_anon_rmap(page, vma, address);
+	} else {
+		inc_mm_counter_fast(vma->vm_mm, MM_FILEPAGES);
+		page_add_file_rmap(page);
+	}
+	set_pte_at(vma->vm_mm, address, pte, entry);
+
+	/* no need to invalidate: a not-present page won't be cached */
+	update_mmu_cache(vma, address, pte);
+}
+
+#define FAULT_AROUND_ORDER 4
+
+#ifdef CONFIG_DEBUG_FS
+static unsigned int fault_around_order = FAULT_AROUND_ORDER;
+
+static int fault_around_order_get(void *data, u64 *val)
+{
+	*val = fault_around_order;
+	return 0;
+}
+
+static int fault_around_order_set(void *data, u64 val)
+{
+	BUILD_BUG_ON((1UL << FAULT_AROUND_ORDER) > PTRS_PER_PTE);
+	if (1UL << val > PTRS_PER_PTE)
+		return -EINVAL;
+	fault_around_order = val;
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(fault_around_order_fops,
+		fault_around_order_get, fault_around_order_set, "%llu\n");
+
+static int __init fault_around_debugfs(void)
+{
+	void *ret;
+
+	ret = debugfs_create_file("fault_around_order",	0644, NULL, NULL,
+			&fault_around_order_fops);
+	if (!ret)
+		pr_warn("Failed to create fault_around_order in debugfs");
+	return 0;
+}
+late_initcall(fault_around_debugfs);
+
+static inline unsigned long fault_around_pages(void)
+{
+	return 1UL << fault_around_order;
+}
+
+static inline unsigned long fault_around_mask(void)
+{
+	return ~((1UL << (PAGE_SHIFT + fault_around_order)) - 1);
+}
+#else
+static inline unsigned long fault_around_pages(void)
+{
+	unsigned long nr_pages;
+
+	nr_pages = 1UL << FAULT_AROUND_ORDER;
+	BUILD_BUG_ON(nr_pages > PTRS_PER_PTE);
+	return nr_pages;
+}
+
+static inline unsigned long fault_around_mask(void)
+{
+	return ~((1UL << (PAGE_SHIFT + FAULT_AROUND_ORDER)) - 1);
+}
+#endif
+
+static void do_fault_around(struct vm_area_struct *vma, unsigned long address,
+		pte_t *pte, pgoff_t pgoff, unsigned int flags)
+{
+	unsigned long start_addr;
+	pgoff_t max_pgoff;
+	struct vm_fault vmf;
+	int off;
+
+	start_addr = max(address & fault_around_mask(), vma->vm_start);
+	off = ((address - start_addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
+	pte -= off;
+	pgoff -= off;
+
 	/*
-	 * Should we do an early C-O-W break?
+	 *  max_pgoff is either end of page table or end of vma
+	 *  or fault_around_pages() from pgoff, depending what is neast.
 	 */
-	page = vmf.page;
-	if (flags & FAULT_FLAG_WRITE) {
-		if (!(vma->vm_flags & VM_SHARED)) {
-			page = cow_page;
-			anon = 1;
-			copy_user_highpage(page, vmf.page, address, vma);
-			__SetPageUptodate(page);
-		} else {
-			/*
-			 * If the page will be shareable, see if the backing
-			 * address space wants to know that the page is about
-			 * to become writable
-			 */
-			if (vma->vm_ops->page_mkwrite) {
-				int tmp;
-
-				unlock_page(page);
-				vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
-				tmp = vma->vm_ops->page_mkwrite(vma, &vmf);
-				if (unlikely(tmp &
-					  (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) {
-					ret = tmp;
-					goto unwritable_page;
-				}
-				if (unlikely(!(tmp & VM_FAULT_LOCKED))) {
-					lock_page(page);
-					if (!page->mapping) {
-						ret = 0; /* retry the fault */
-						unlock_page(page);
-						goto unwritable_page;
-					}
-				} else
-					VM_BUG_ON_PAGE(!PageLocked(page), page);
-				page_mkwrite = 1;
-			}
-		}
-
+	max_pgoff = pgoff - ((start_addr >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +
+		PTRS_PER_PTE - 1;
+	max_pgoff = min3(max_pgoff, vma_pages(vma) + vma->vm_pgoff - 1,
+			pgoff + fault_around_pages() - 1);
+
+	/* Check if it makes any sense to call ->map_pages */
+	while (!pte_none(*pte)) {
+		if (++pgoff > max_pgoff)
+			return;
+		start_addr += PAGE_SIZE;
+		if (start_addr >= vma->vm_end)
+			return;
+		pte++;
 	}
 
-	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
+	vmf.virtual_address = (void __user *) start_addr;
+	vmf.pte = pte;
+	vmf.pgoff = pgoff;
+	vmf.max_pgoff = max_pgoff;
+	vmf.flags = flags;
+	vma->vm_ops->map_pages(vma, &vmf);
+}
+
+static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmd,
+		pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
+{
+	struct page *fault_page;
+	spinlock_t *ptl;
+	pte_t *pte;
+	int ret = 0;
 
 	/*
-	 * This silly early PAGE_DIRTY setting removes a race
-	 * due to the bad i386 page protection. But it's valid
-	 * for other architectures too.
-	 *
-	 * Note that if FAULT_FLAG_WRITE is set, we either now have
-	 * an exclusive copy of the page, or this is a shared mapping,
-	 * so we can make it writable and dirty to avoid having to
-	 * handle that later.
+	 * Let's call ->map_pages() first and use ->fault() as fallback
+	 * if page by the offset is not ready to be mapped (cold cache or
+	 * something).
 	 */
-	/* Only go through if we didn't race with anybody else... */
-	if (likely(pte_same(*page_table, orig_pte))) {
-		flush_icache_page(vma, page);
-		entry = mk_pte(page, vma->vm_page_prot);
-		if (flags & FAULT_FLAG_WRITE)
-			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
-		else if (pte_file(orig_pte) && pte_file_soft_dirty(orig_pte))
-			pte_mksoft_dirty(entry);
-		if (anon) {
-			inc_mm_counter_fast(mm, MM_ANONPAGES);
-			page_add_new_anon_rmap(page, vma, address);
-		} else {
-			inc_mm_counter_fast(mm, MM_FILEPAGES);
-			page_add_file_rmap(page);
-			if (flags & FAULT_FLAG_WRITE) {
-				dirty_page = page;
-				get_page(dirty_page);
-			}
-		}
-		set_pte_at(mm, address, page_table, entry);
+	if (vma->vm_ops->map_pages) {
+		pte = pte_offset_map_lock(mm, pmd, address, &ptl);
+		do_fault_around(vma, address, pte, pgoff, flags);
+		if (!pte_same(*pte, orig_pte))
+			goto unlock_out;
+		pte_unmap_unlock(pte, ptl);
+	}
 
-		/* no need to invalidate: a not-present page won't be cached */
-		update_mmu_cache(vma, address, page_table);
-	} else {
-		if (cow_page)
-			mem_cgroup_uncharge_page(cow_page);
-		if (anon)
-			page_cache_release(page);
-		else
-			anon = 1; /* no anon but release faulted_page */
+	ret = __do_fault(vma, address, pgoff, flags, &fault_page);
+	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
+		return ret;
+
+	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
+	if (unlikely(!pte_same(*pte, orig_pte))) {
+		pte_unmap_unlock(pte, ptl);
+		unlock_page(fault_page);
+		page_cache_release(fault_page);
+		return ret;
 	}
+	do_set_pte(vma, address, fault_page, pte, false, false);
+	unlock_page(fault_page);
+unlock_out:
+	pte_unmap_unlock(pte, ptl);
+	return ret;
+}
 
-	pte_unmap_unlock(page_table, ptl);
+static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmd,
+		pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
+{
+	struct page *fault_page, *new_page;
+	spinlock_t *ptl;
+	pte_t *pte;
+	int ret;
 
-	if (dirty_page) {
-		struct address_space *mapping = page->mapping;
-		int dirtied = 0;
+	if (unlikely(anon_vma_prepare(vma)))
+		return VM_FAULT_OOM;
 
-		if (set_page_dirty(dirty_page))
-			dirtied = 1;
-		unlock_page(dirty_page);
-		put_page(dirty_page);
-		if ((dirtied || page_mkwrite) && mapping) {
-			/*
-			 * Some device drivers do not set page.mapping but still
-			 * dirty their pages
-			 */
-			balance_dirty_pages_ratelimited(mapping);
-		}
+	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
+	if (!new_page)
+		return VM_FAULT_OOM;
 
-		/* file_update_time outside page_lock */
-		if (vma->vm_file && !page_mkwrite)
-			file_update_time(vma->vm_file);
-	} else {
-		unlock_page(vmf.page);
-		if (anon)
-			page_cache_release(vmf.page);
+	if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL)) {
+		page_cache_release(new_page);
+		return VM_FAULT_OOM;
 	}
 
-	return ret;
+	ret = __do_fault(vma, address, pgoff, flags, &fault_page);
+	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
+		goto uncharge_out;
 
-unwritable_page:
-	page_cache_release(page);
+	copy_user_highpage(new_page, fault_page, address, vma);
+	__SetPageUptodate(new_page);
+
+	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
+	if (unlikely(!pte_same(*pte, orig_pte))) {
+		pte_unmap_unlock(pte, ptl);
+		unlock_page(fault_page);
+		page_cache_release(fault_page);
+		goto uncharge_out;
+	}
+	do_set_pte(vma, address, new_page, pte, true, true);
+	pte_unmap_unlock(pte, ptl);
+	unlock_page(fault_page);
+	page_cache_release(fault_page);
 	return ret;
 uncharge_out:
-	/* fs's fault handler get error */
-	if (cow_page) {
-		mem_cgroup_uncharge_page(cow_page);
-		page_cache_release(cow_page);
+	mem_cgroup_uncharge_page(new_page);
+	page_cache_release(new_page);
+	return ret;
+}
+
+static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmd,
+		pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
+{
+	struct page *fault_page;
+	struct address_space *mapping;
+	spinlock_t *ptl;
+	pte_t *pte;
+	int dirtied = 0;
+	int ret, tmp;
+
+	WARN_ON_ONCE(!rwsem_is_locked(&mm->mmap_sem));
+
+	ret = __do_fault(vma, address, pgoff, flags, &fault_page);
+	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
+		return ret;
+
+	/*
+	 * Check if the backing address space wants to know that the page is
+	 * about to become writable
+	 */
+	if (vma->vm_ops->page_mkwrite) {
+		unlock_page(fault_page);
+		tmp = do_page_mkwrite(vma, fault_page, address);
+		if (unlikely(!tmp ||
+				(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
+			page_cache_release(fault_page);
+			return tmp;
+		}
 	}
+
+	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
+	if (unlikely(!pte_same(*pte, orig_pte))) {
+		pte_unmap_unlock(pte, ptl);
+		unlock_page(fault_page);
+		page_cache_release(fault_page);
+		return ret;
+	}
+	do_set_pte(vma, address, fault_page, pte, true, false);
+	pte_unmap_unlock(pte, ptl);
+
+	if (set_page_dirty(fault_page))
+		dirtied = 1;
+	/*
+	 * Take a local copy of the address_space - page.mapping may be zeroed
+	 * by truncate after unlock_page().   The address_space itself remains
+	 * pinned by vma->vm_file's reference.  We rely on unlock_page()'s
+	 * release semantics to prevent the compiler from undoing this copying.
+	 */
+	mapping = fault_page->mapping;
+	unlock_page(fault_page);
+	if ((dirtied || vma->vm_ops->page_mkwrite) && mapping) {
+		/*
+		 * Some device drivers do not set page.mapping but still
+		 * dirty their pages
+		 */
+		balance_dirty_pages_ratelimited(mapping);
+	}
+
+	/* file_update_time outside page_lock */
+	if (vma->vm_file && !vma->vm_ops->page_mkwrite)
+		file_update_time(vma->vm_file);
+
 	return ret;
 }
 
@@ -3496,7 +3617,13 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			- vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 
 	pte_unmap(page_table);
-	return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
+	if (!(flags & FAULT_FLAG_WRITE))
+		return do_read_fault(mm, vma, address, pmd, pgoff, flags,
+				orig_pte);
+	if (!(vma->vm_flags & VM_SHARED))
+		return do_cow_fault(mm, vma, address, pmd, pgoff, flags,
+				orig_pte);
+	return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
 }
 
 /*
@@ -3528,10 +3655,16 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 
 	pgoff = pte_to_pgoff(orig_pte);
-	return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
+	if (!(flags & FAULT_FLAG_WRITE))
+		return do_read_fault(mm, vma, address, pmd, pgoff, flags,
+				orig_pte);
+	if (!(vma->vm_flags & VM_SHARED))
+		return do_cow_fault(mm, vma, address, pmd, pgoff, flags,
+				orig_pte);
+	return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
 }
 
-int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
+static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
 				unsigned long addr, int page_nid,
 				int *flags)
 {
@@ -3546,7 +3679,7 @@ int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
 	return mpol_misplaced(page, vma, addr);
 }
 
-int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
+static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		   unsigned long addr, pte_t pte, pte_t *ptep, pmd_t *pmd)
 {
 	struct page *page = NULL;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 4755c8576942..9d2ef4111a4c 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -476,140 +476,70 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
 static void migrate_page_add(struct page *page, struct list_head *pagelist,
 				unsigned long flags);
 
+struct queue_pages {
+	struct list_head *pagelist;
+	unsigned long flags;
+	nodemask_t *nmask;
+	struct vm_area_struct *prev;
+};
+
 /*
  * Scan through pages checking if pages follow certain conditions,
  * and move them to the pagelist if they do.
  */
-static int queue_pages_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long addr, unsigned long end,
-		const nodemask_t *nodes, unsigned long flags,
-		void *private)
+static int queue_pages_pte(pte_t *pte, unsigned long addr,
+			unsigned long next, struct mm_walk *walk)
 {
-	pte_t *orig_pte;
-	pte_t *pte;
-	spinlock_t *ptl;
-
-	orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	do {
-		struct page *page;
-		int nid;
+	struct vm_area_struct *vma = walk->vma;
+	struct page *page;
+	struct queue_pages *qp = walk->private;
+	unsigned long flags = qp->flags;
+	int nid;
 
-		if (!pte_present(*pte))
-			continue;
-		page = vm_normal_page(vma, addr, *pte);
-		if (!page)
-			continue;
-		/*
-		 * vm_normal_page() filters out zero pages, but there might
-		 * still be PageReserved pages to skip, perhaps in a VDSO.
-		 */
-		if (PageReserved(page))
-			continue;
-		nid = page_to_nid(page);
-		if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
-			continue;
+	if (!pte_present(*pte))
+		return 0;
+	page = vm_normal_page(vma, addr, *pte);
+	if (!page)
+		return 0;
+	/*
+	 * vm_normal_page() filters out zero pages, but there might
+	 * still be PageReserved pages to skip, perhaps in a VDSO.
+	 */
+	if (PageReserved(page))
+		return 0;
+	nid = page_to_nid(page);
+	if (node_isset(nid, *qp->nmask) == !!(flags & MPOL_MF_INVERT))
+		return 0;
 
-		if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
-			migrate_page_add(page, private, flags);
-		else
-			break;
-	} while (pte++, addr += PAGE_SIZE, addr != end);
-	pte_unmap_unlock(orig_pte, ptl);
-	return addr != end;
+	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
+		migrate_page_add(page, qp->pagelist, flags);
+	return 0;
 }
 
-static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma,
-		pmd_t *pmd, const nodemask_t *nodes, unsigned long flags,
-				    void *private)
+static int queue_pages_hugetlb(pte_t *pte, unsigned long addr,
+				unsigned long next, struct mm_walk *walk)
 {
 #ifdef CONFIG_HUGETLB_PAGE
+	struct queue_pages *qp = walk->private;
+	unsigned long flags = qp->flags;
 	int nid;
 	struct page *page;
-	spinlock_t *ptl;
+	pte_t entry;
 
-	ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, (pte_t *)pmd);
-	page = pte_page(huge_ptep_get((pte_t *)pmd));
+	entry = huge_ptep_get(pte);
+	if (!pte_present(entry))
+		return 0;
+	page = pte_page(entry);
 	nid = page_to_nid(page);
-	if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
-		goto unlock;
+	if (node_isset(nid, *qp->nmask) == !!(flags & MPOL_MF_INVERT))
+		return 0;
 	/* With MPOL_MF_MOVE, we migrate only unshared hugepage. */
 	if (flags & (MPOL_MF_MOVE_ALL) ||
 	    (flags & MPOL_MF_MOVE && page_mapcount(page) == 1))
-		isolate_huge_page(page, private);
-unlock:
-	spin_unlock(ptl);
+		isolate_huge_page(page, qp->pagelist);
 #else
 	BUG();
 #endif
-}
-
-static inline int queue_pages_pmd_range(struct vm_area_struct *vma, pud_t *pud,
-		unsigned long addr, unsigned long end,
-		const nodemask_t *nodes, unsigned long flags,
-		void *private)
-{
-	pmd_t *pmd;
-	unsigned long next;
-
-	pmd = pmd_offset(pud, addr);
-	do {
-		next = pmd_addr_end(addr, end);
-		if (!pmd_present(*pmd))
-			continue;
-		if (pmd_huge(*pmd) && is_vm_hugetlb_page(vma)) {
-			queue_pages_hugetlb_pmd_range(vma, pmd, nodes,
-						flags, private);
-			continue;
-		}
-		split_huge_page_pmd(vma, addr, pmd);
-		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
-			continue;
-		if (queue_pages_pte_range(vma, pmd, addr, next, nodes,
-				    flags, private))
-			return -EIO;
-	} while (pmd++, addr = next, addr != end);
-	return 0;
-}
-
-static inline int queue_pages_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
-		unsigned long addr, unsigned long end,
-		const nodemask_t *nodes, unsigned long flags,
-		void *private)
-{
-	pud_t *pud;
-	unsigned long next;
-
-	pud = pud_offset(pgd, addr);
-	do {
-		next = pud_addr_end(addr, end);
-		if (pud_huge(*pud) && is_vm_hugetlb_page(vma))
-			continue;
-		if (pud_none_or_clear_bad(pud))
-			continue;
-		if (queue_pages_pmd_range(vma, pud, addr, next, nodes,
-				    flags, private))
-			return -EIO;
-	} while (pud++, addr = next, addr != end);
-	return 0;
-}
-
-static inline int queue_pages_pgd_range(struct vm_area_struct *vma,
-		unsigned long addr, unsigned long end,
-		const nodemask_t *nodes, unsigned long flags,
-		void *private)
-{
-	pgd_t *pgd;
-	unsigned long next;
-
-	pgd = pgd_offset(vma->vm_mm, addr);
-	do {
-		next = pgd_addr_end(addr, end);
-		if (pgd_none_or_clear_bad(pgd))
-			continue;
-		if (queue_pages_pud_range(vma, pgd, addr, next, nodes,
-				    flags, private))
-			return -EIO;
-	} while (pgd++, addr = next, addr != end);
 	return 0;
 }
 
@@ -642,6 +572,45 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma,
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
+static int queue_pages_test_walk(unsigned long start, unsigned long end,
+				struct mm_walk *walk)
+{
+	struct vm_area_struct *vma = walk->vma;
+	struct queue_pages *qp = walk->private;
+	unsigned long endvma = vma->vm_end;
+	unsigned long flags = qp->flags;
+
+	if (endvma > end)
+		endvma = end;
+	if (vma->vm_start > start)
+		start = vma->vm_start;
+
+	if (!(flags & MPOL_MF_DISCONTIG_OK)) {
+		if (!vma->vm_next && vma->vm_end < end)
+			return -EFAULT;
+		if (qp->prev && qp->prev->vm_end < vma->vm_start)
+			return -EFAULT;
+	}
+
+	qp->prev = vma;
+	walk->skip = 1;
+
+	if (vma->vm_flags & VM_PFNMAP)
+		return 0;
+
+	if (flags & MPOL_MF_LAZY) {
+		change_prot_numa(vma, start, endvma);
+		return 0;
+	}
+
+	if ((flags & MPOL_MF_STRICT) ||
+	    ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
+	     vma_migratable(vma)))
+		/* queue pages from current vma */
+		walk->skip = 0;
+	return 0;
+}
+
 /*
  * Walk through page tables and collect pages to be migrated.
  *
@@ -651,51 +620,29 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma,
  */
 static struct vm_area_struct *
 queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
-		const nodemask_t *nodes, unsigned long flags, void *private)
+		nodemask_t *nodes, unsigned long flags,
+		struct list_head *pagelist)
 {
 	int err;
-	struct vm_area_struct *first, *vma, *prev;
-
-
-	first = find_vma(mm, start);
-	if (!first)
-		return ERR_PTR(-EFAULT);
-	prev = NULL;
-	for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
-		unsigned long endvma = vma->vm_end;
-
-		if (endvma > end)
-			endvma = end;
-		if (vma->vm_start > start)
-			start = vma->vm_start;
-
-		if (!(flags & MPOL_MF_DISCONTIG_OK)) {
-			if (!vma->vm_next && vma->vm_end < end)
-				return ERR_PTR(-EFAULT);
-			if (prev && prev->vm_end < vma->vm_start)
-				return ERR_PTR(-EFAULT);
-		}
-
-		if (flags & MPOL_MF_LAZY) {
-			change_prot_numa(vma, start, endvma);
-			goto next;
-		}
-
-		if ((flags & MPOL_MF_STRICT) ||
-		     ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
-		      vma_migratable(vma))) {
-
-			err = queue_pages_pgd_range(vma, start, endvma, nodes,
-						flags, private);
-			if (err) {
-				first = ERR_PTR(err);
-				break;
-			}
-		}
-next:
-		prev = vma;
-	}
-	return first;
+	struct queue_pages qp = {
+		.pagelist = pagelist,
+		.flags = flags,
+		.nmask = nodes,
+		.prev = NULL,
+	};
+	struct mm_walk queue_pages_walk = {
+		.hugetlb_entry = queue_pages_hugetlb,
+		.pte_entry = queue_pages_pte,
+		.test_walk = queue_pages_test_walk,
+		.mm = mm,
+		.private = &qp,
+	};
+
+	err = walk_page_range(start, end, &queue_pages_walk);
+	if (err < 0)
+		return ERR_PTR(err);
+	else
+		return find_vma(mm, start);
 }
 
 /*
@@ -795,36 +742,6 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
 	return err;
 }
 
-/*
- * Update task->flags PF_MEMPOLICY bit: set iff non-default
- * mempolicy.  Allows more rapid checking of this (combined perhaps
- * with other PF_* flag bits) on memory allocation hot code paths.
- *
- * If called from outside this file, the task 'p' should -only- be
- * a newly forked child not yet visible on the task list, because
- * manipulating the task flags of a visible task is not safe.
- *
- * The above limitation is why this routine has the funny name
- * mpol_fix_fork_child_flag().
- *
- * It is also safe to call this with a task pointer of current,
- * which the static wrapper mpol_set_task_struct_flag() does,
- * for use within this file.
- */
-
-void mpol_fix_fork_child_flag(struct task_struct *p)
-{
-	if (p->mempolicy)
-		p->flags |= PF_MEMPOLICY;
-	else
-		p->flags &= ~PF_MEMPOLICY;
-}
-
-static void mpol_set_task_struct_flag(void)
-{
-	mpol_fix_fork_child_flag(current);
-}
-
 /* Set the process memory policy */
 static long do_set_mempolicy(unsigned short mode, unsigned short flags,
 			     nodemask_t *nodes)
@@ -861,7 +778,6 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
 	}
 	old = current->mempolicy;
 	current->mempolicy = new;
-	mpol_set_task_struct_flag();
 	if (new && new->mode == MPOL_INTERLEAVE &&
 	    nodes_weight(new->v.nodes))
 		current->il_next = first_node(new->v.nodes);
@@ -1782,21 +1698,18 @@ static unsigned interleave_nodes(struct mempolicy *policy)
 /*
  * Depending on the memory policy provide a node from which to allocate the
  * next slab entry.
- * @policy must be protected by freeing by the caller.  If @policy is
- * the current task's mempolicy, this protection is implicit, as only the
- * task can change it's policy.  The system default policy requires no
- * such protection.
  */
-unsigned slab_node(void)
+unsigned int mempolicy_slab_node(void)
 {
 	struct mempolicy *policy;
+	int node = numa_mem_id();
 
 	if (in_interrupt())
-		return numa_node_id();
+		return node;
 
 	policy = current->mempolicy;
 	if (!policy || policy->flags & MPOL_F_LOCAL)
-		return numa_node_id();
+		return node;
 
 	switch (policy->mode) {
 	case MPOL_PREFERRED:
@@ -1816,11 +1729,11 @@ unsigned slab_node(void)
 		struct zonelist *zonelist;
 		struct zone *zone;
 		enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL);
-		zonelist = &NODE_DATA(numa_node_id())->node_zonelists[0];
+		zonelist = &NODE_DATA(node)->node_zonelists[0];
 		(void)first_zones_zonelist(zonelist, highest_zoneidx,
 							&policy->v.nodes,
 							&zone);
-		return zone ? zone->node : numa_node_id();
+		return zone ? zone->node : node;
 	}
 
 	default:
@@ -1899,7 +1812,7 @@ int node_random(const nodemask_t *maskp)
  * If the effective policy is 'BIND, returns a pointer to the mempolicy's
  * @nodemask for filtering the zonelist.
  *
- * Must be protected by get_mems_allowed()
+ * Must be protected by read_mems_allowed_begin()
  */
 struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
 				gfp_t gfp_flags, struct mempolicy **mpol,
@@ -2063,7 +1976,7 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 
 retry_cpuset:
 	pol = get_vma_policy(current, vma, addr);
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
 		unsigned nid;
@@ -2071,7 +1984,7 @@ retry_cpuset:
 		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
 		mpol_cond_put(pol);
 		page = alloc_page_interleave(gfp, order, nid);
-		if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 			goto retry_cpuset;
 
 		return page;
@@ -2081,7 +1994,7 @@ retry_cpuset:
 				      policy_nodemask(gfp, pol));
 	if (unlikely(mpol_needs_cond_ref(pol)))
 		__mpol_put(pol);
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 	return page;
 }
@@ -2115,7 +2028,7 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 		pol = &default_policy;
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	/*
 	 * No reference counting needed for current->mempolicy
@@ -2128,7 +2041,7 @@ retry_cpuset:
 				policy_zonelist(gfp, pol, numa_node_id()),
 				policy_nodemask(gfp, pol));
 
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 
 	return page;
diff --git a/mm/mempool.c b/mm/mempool.c
index 659aa42bad16..905434f18c97 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -304,9 +304,9 @@ void mempool_free(void *element, mempool_t *pool)
 	 * ensures that there will be frees which return elements to the
 	 * pool waking up the waiters.
 	 */
-	if (pool->curr_nr < pool->min_nr) {
+	if (unlikely(pool->curr_nr < pool->min_nr)) {
 		spin_lock_irqsave(&pool->lock, flags);
-		if (pool->curr_nr < pool->min_nr) {
+		if (likely(pool->curr_nr < pool->min_nr)) {
 			add_element(pool, element);
 			spin_unlock_irqrestore(&pool->lock, flags);
 			wake_up(&pool->wait);
diff --git a/mm/mincore.c b/mm/mincore.c
index 101623378fbf..725c80961048 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -70,13 +70,21 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
 	 * any other file mapping (ie. marked !present and faulted in with
 	 * tmpfs's .fault). So swapped out tmpfs mappings are tested here.
 	 */
-	page = find_get_page(mapping, pgoff);
 #ifdef CONFIG_SWAP
-	/* shmem/tmpfs may return swap: account for swapcache page too. */
-	if (radix_tree_exceptional_entry(page)) {
-		swp_entry_t swap = radix_to_swp_entry(page);
-		page = find_get_page(swap_address_space(swap), swap.val);
-	}
+	if (shmem_mapping(mapping)) {
+		page = find_get_entry(mapping, pgoff);
+		/*
+		 * shmem/tmpfs may return swap: account for swapcache
+		 * page too.
+		 */
+		if (radix_tree_exceptional_entry(page)) {
+			swp_entry_t swp = radix_to_swp_entry(page);
+			page = find_get_page(swap_address_space(swp), swp.val);
+		}
+	} else
+		page = find_get_page(mapping, pgoff);
+#else
+	page = find_get_page(mapping, pgoff);
 #endif
 	if (page) {
 		present = PageUptodate(page);
diff --git a/mm/mlock.c b/mm/mlock.c
index 4e1a68162285..b1eb53634005 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -79,6 +79,7 @@ void clear_page_mlock(struct page *page)
  */
 void mlock_vma_page(struct page *page)
 {
+	/* Serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
 	if (!TestSetPageMlocked(page)) {
@@ -174,6 +175,7 @@ unsigned int munlock_vma_page(struct page *page)
 	unsigned int nr_pages;
 	struct zone *zone = page_zone(page);
 
+	/* For try_to_munlock() and to serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
 	/*
diff --git a/mm/mmap.c b/mm/mmap.c
index f12eee3860f7..b1202cf81f4b 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/backing-dev.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/shm.h>
 #include <linux/mman.h>
 #include <linux/pagemap.h>
@@ -405,7 +406,7 @@ static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore)
 	}
 }
 
-void validate_mm(struct mm_struct *mm)
+static void validate_mm(struct mm_struct *mm)
 {
 	int bug = 0;
 	int i = 0;
@@ -681,8 +682,9 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma,
 	prev->vm_next = next = vma->vm_next;
 	if (next)
 		next->vm_prev = prev;
-	if (mm->mmap_cache == vma)
-		mm->mmap_cache = prev;
+
+	/* Kill the cache */
+	vmacache_invalidate(mm);
 }
 
 /*
@@ -1989,34 +1991,33 @@ EXPORT_SYMBOL(get_unmapped_area);
 /* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
 struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 {
-	struct vm_area_struct *vma = NULL;
+	struct rb_node *rb_node;
+	struct vm_area_struct *vma;
 
 	/* Check the cache first. */
-	/* (Cache hit rate is typically around 35%.) */
-	vma = ACCESS_ONCE(mm->mmap_cache);
-	if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) {
-		struct rb_node *rb_node;
+	vma = vmacache_find(mm, addr);
+	if (likely(vma))
+		return vma;
 
-		rb_node = mm->mm_rb.rb_node;
-		vma = NULL;
+	rb_node = mm->mm_rb.rb_node;
+	vma = NULL;
 
-		while (rb_node) {
-			struct vm_area_struct *vma_tmp;
-
-			vma_tmp = rb_entry(rb_node,
-					   struct vm_area_struct, vm_rb);
-
-			if (vma_tmp->vm_end > addr) {
-				vma = vma_tmp;
-				if (vma_tmp->vm_start <= addr)
-					break;
-				rb_node = rb_node->rb_left;
-			} else
-				rb_node = rb_node->rb_right;
-		}
-		if (vma)
-			mm->mmap_cache = vma;
+	while (rb_node) {
+		struct vm_area_struct *tmp;
+
+		tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb);
+
+		if (tmp->vm_end > addr) {
+			vma = tmp;
+			if (tmp->vm_start <= addr)
+				break;
+			rb_node = rb_node->rb_left;
+		} else
+			rb_node = rb_node->rb_right;
 	}
+
+	if (vma)
+		vmacache_update(addr, vma);
 	return vma;
 }
 
@@ -2388,7 +2389,9 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 	} else
 		mm->highest_vm_end = prev ? prev->vm_end : 0;
 	tail_vma->vm_next = NULL;
-	mm->mmap_cache = NULL;		/* Kill the cache. */
+
+	/* Kill the cache */
+	vmacache_invalidate(mm);
 }
 
 /*
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 769a67a15803..c43d557941f8 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -36,6 +36,34 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 }
 #endif
 
+/*
+ * For a prot_numa update we only hold mmap_sem for read so there is a
+ * potential race with faulting where a pmd was temporarily none. This
+ * function checks for a transhuge pmd under the appropriate lock. It
+ * returns a pte if it was successfully locked or NULL if it raced with
+ * a transhuge insertion.
+ */
+static pte_t *lock_pte_protection(struct vm_area_struct *vma, pmd_t *pmd,
+			unsigned long addr, int prot_numa, spinlock_t **ptl)
+{
+	pte_t *pte;
+	spinlock_t *pmdl;
+
+	/* !prot_numa is protected by mmap_sem held for write */
+	if (!prot_numa)
+		return pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
+
+	pmdl = pmd_lock(vma->vm_mm, pmd);
+	if (unlikely(pmd_trans_huge(*pmd) || pmd_none(*pmd))) {
+		spin_unlock(pmdl);
+		return NULL;
+	}
+
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
+	spin_unlock(pmdl);
+	return pte;
+}
+
 static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
 		int dirty_accountable, int prot_numa)
@@ -45,7 +73,10 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	spinlock_t *ptl;
 	unsigned long pages = 0;
 
-	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	pte = lock_pte_protection(vma, pmd, addr, prot_numa, &ptl);
+	if (!pte)
+		return 0;
+
 	arch_enter_lazy_mmu_mode();
 	do {
 		oldpte = *pte;
@@ -109,15 +140,26 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		pgprot_t newprot, int dirty_accountable, int prot_numa)
 {
 	pmd_t *pmd;
+	struct mm_struct *mm = vma->vm_mm;
 	unsigned long next;
 	unsigned long pages = 0;
 	unsigned long nr_huge_updates = 0;
+	unsigned long mni_start = 0;
 
 	pmd = pmd_offset(pud, addr);
 	do {
 		unsigned long this_pages;
 
 		next = pmd_addr_end(addr, end);
+		if (!pmd_trans_huge(*pmd) && pmd_none_or_clear_bad(pmd))
+			continue;
+
+		/* invoke the mmu notifier if the pmd is populated */
+		if (!mni_start) {
+			mni_start = addr;
+			mmu_notifier_invalidate_range_start(mm, mni_start, end);
+		}
+
 		if (pmd_trans_huge(*pmd)) {
 			if (next - addr != HPAGE_PMD_SIZE)
 				split_huge_page_pmd(vma, addr, pmd);
@@ -130,18 +172,21 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 						pages += HPAGE_PMD_NR;
 						nr_huge_updates++;
 					}
+
+					/* huge pmd was handled */
 					continue;
 				}
 			}
-			/* fall through */
+			/* fall through, the trans huge pmd just split */
 		}
-		if (pmd_none_or_clear_bad(pmd))
-			continue;
 		this_pages = change_pte_range(vma, pmd, addr, next, newprot,
 				 dirty_accountable, prot_numa);
 		pages += this_pages;
 	} while (pmd++, addr = next, addr != end);
 
+	if (mni_start)
+		mmu_notifier_invalidate_range_end(mm, mni_start, end);
+
 	if (nr_huge_updates)
 		count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates);
 	return pages;
@@ -201,15 +246,12 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 		       unsigned long end, pgprot_t newprot,
 		       int dirty_accountable, int prot_numa)
 {
-	struct mm_struct *mm = vma->vm_mm;
 	unsigned long pages;
 
-	mmu_notifier_invalidate_range_start(mm, start, end);
 	if (is_vm_hugetlb_page(vma))
 		pages = hugetlb_change_protection(vma, start, end, newprot);
 	else
 		pages = change_protection_range(vma, start, end, newprot, dirty_accountable, prot_numa);
-	mmu_notifier_invalidate_range_end(mm, start, end);
 
 	return pages;
 }
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index f73f2987a852..04a9d94333a5 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -334,7 +334,7 @@ void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
 	return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
 }
 
-void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
+static void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 				    unsigned long align, unsigned long goal,
 				    unsigned long limit)
 {
diff --git a/mm/nommu.c b/mm/nommu.c
index a554e5a451cd..85f8d6698d48 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -15,6 +15,7 @@
 
 #include <linux/export.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/mman.h>
 #include <linux/swap.h>
 #include <linux/file.h>
@@ -24,6 +25,7 @@
 #include <linux/vmalloc.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
+#include <linux/compiler.h>
 #include <linux/mount.h>
 #include <linux/personality.h>
 #include <linux/security.h>
@@ -296,7 +298,7 @@ long vwrite(char *buf, char *addr, unsigned long count)
 		count = -(unsigned long) addr;
 
 	memcpy(addr, buf, count);
-	return(count);
+	return count;
 }
 
 /*
@@ -459,7 +461,7 @@ EXPORT_SYMBOL_GPL(vm_unmap_aliases);
  * Implement a stub for vmalloc_sync_all() if the architecture chose not to
  * have one.
  */
-void  __attribute__((weak)) vmalloc_sync_all(void)
+void __weak vmalloc_sync_all(void)
 {
 }
 
@@ -768,16 +770,23 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
  */
 static void delete_vma_from_mm(struct vm_area_struct *vma)
 {
+	int i;
 	struct address_space *mapping;
 	struct mm_struct *mm = vma->vm_mm;
+	struct task_struct *curr = current;
 
 	kenter("%p", vma);
 
 	protect_vma(vma, 0);
 
 	mm->map_count--;
-	if (mm->mmap_cache == vma)
-		mm->mmap_cache = NULL;
+	for (i = 0; i < VMACACHE_SIZE; i++) {
+		/* if the vma is cached, invalidate the entire cache */
+		if (curr->vmacache[i] == vma) {
+			vmacache_invalidate(curr->mm);
+			break;
+		}
+	}
 
 	/* remove the VMA from the mapping */
 	if (vma->vm_file) {
@@ -825,8 +834,8 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 	struct vm_area_struct *vma;
 
 	/* check the cache first */
-	vma = ACCESS_ONCE(mm->mmap_cache);
-	if (vma && vma->vm_start <= addr && vma->vm_end > addr)
+	vma = vmacache_find(mm, addr);
+	if (likely(vma))
 		return vma;
 
 	/* trawl the list (there may be multiple mappings in which addr
@@ -835,7 +844,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 		if (vma->vm_start > addr)
 			return NULL;
 		if (vma->vm_end > addr) {
-			mm->mmap_cache = vma;
+			vmacache_update(addr, vma);
 			return vma;
 		}
 	}
@@ -874,8 +883,8 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
 	unsigned long end = addr + len;
 
 	/* check the cache first */
-	vma = mm->mmap_cache;
-	if (vma && vma->vm_start == addr && vma->vm_end == end)
+	vma = vmacache_find_exact(mm, addr, end);
+	if (vma)
 		return vma;
 
 	/* trawl the list (there may be multiple mappings in which addr
@@ -886,7 +895,7 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
 		if (vma->vm_start > addr)
 			return NULL;
 		if (vma->vm_end == end) {
-			mm->mmap_cache = vma;
+			vmacache_update(addr, vma);
 			return vma;
 		}
 	}
@@ -1003,8 +1012,7 @@ static int validate_mmap_request(struct file *file,
 
 			/* we mustn't privatise shared mappings */
 			capabilities &= ~BDI_CAP_MAP_COPY;
-		}
-		else {
+		} else {
 			/* we're going to read the file into private memory we
 			 * allocate */
 			if (!(capabilities & BDI_CAP_MAP_COPY))
@@ -1035,23 +1043,20 @@ static int validate_mmap_request(struct file *file,
 		if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) {
 			if (prot & PROT_EXEC)
 				return -EPERM;
-		}
-		else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) {
+		} else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) {
 			/* handle implication of PROT_EXEC by PROT_READ */
 			if (current->personality & READ_IMPLIES_EXEC) {
 				if (capabilities & BDI_CAP_EXEC_MAP)
 					prot |= PROT_EXEC;
 			}
-		}
-		else if ((prot & PROT_READ) &&
+		} else if ((prot & PROT_READ) &&
 			 (prot & PROT_EXEC) &&
 			 !(capabilities & BDI_CAP_EXEC_MAP)
 			 ) {
 			/* backing file is not executable, try to copy */
 			capabilities &= ~BDI_CAP_MAP_DIRECT;
 		}
-	}
-	else {
+	} else {
 		/* anonymous mappings are always memory backed and can be
 		 * privately mapped
 		 */
@@ -1659,7 +1664,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 	/* find the first potentially overlapping VMA */
 	vma = find_vma(mm, start);
 	if (!vma) {
-		static int limit = 0;
+		static int limit;
 		if (limit < 5) {
 			printk(KERN_WARNING
 			       "munmap of memory not mmapped by process %d"
@@ -1985,6 +1990,12 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 EXPORT_SYMBOL(filemap_fault);
 
+void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	BUG();
+}
+EXPORT_SYMBOL(filemap_map_pages);
+
 int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr,
 			     unsigned long size, pgoff_t pgoff)
 {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3bac76ae4b30..2e5029cab14e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -295,7 +295,8 @@ static inline int bad_range(struct zone *zone, struct page *page)
 }
 #endif
 
-static void bad_page(struct page *page, char *reason, unsigned long bad_flags)
+static void bad_page(struct page *page, const char *reason,
+		unsigned long bad_flags)
 {
 	static unsigned long resume;
 	static unsigned long nr_shown;
@@ -623,7 +624,7 @@ out:
 
 static inline int free_pages_check(struct page *page)
 {
-	char *bad_reason = NULL;
+	const char *bad_reason = NULL;
 	unsigned long bad_flags = 0;
 
 	if (unlikely(page_mapcount(page)))
@@ -859,7 +860,7 @@ static inline void expand(struct zone *zone, struct page *page,
  */
 static inline int check_new_page(struct page *page)
 {
-	char *bad_reason = NULL;
+	const char *bad_reason = NULL;
 	unsigned long bad_flags = 0;
 
 	if (unlikely(page_mapcount(page)))
@@ -1238,15 +1239,6 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 	}
 	local_irq_restore(flags);
 }
-static bool gfp_thisnode_allocation(gfp_t gfp_mask)
-{
-	return (gfp_mask & GFP_THISNODE) == GFP_THISNODE;
-}
-#else
-static bool gfp_thisnode_allocation(gfp_t gfp_mask)
-{
-	return false;
-}
 #endif
 
 /*
@@ -1583,12 +1575,7 @@ again:
 					  get_pageblock_migratetype(page));
 	}
 
-	/*
-	 * NOTE: GFP_THISNODE allocations do not partake in the kswapd
-	 * aging protocol, so they can't be fair.
-	 */
-	if (!gfp_thisnode_allocation(gfp_flags))
-		__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+	__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
 
 	__count_zone_vm_events(PGALLOC, zone, 1 << order);
 	zone_statistics(preferred_zone, zone, gfp_flags);
@@ -1870,7 +1857,7 @@ static void __paginginit init_zone_allows_reclaim(int nid)
 {
 	int i;
 
-	for_each_online_node(i)
+	for_each_node_state(i, N_MEMORY)
 		if (node_distance(nid, i) <= RECLAIM_DISTANCE)
 			node_set(i, NODE_DATA(nid)->reclaim_nodes);
 		else
@@ -1954,23 +1941,12 @@ zonelist_scan:
 		 * zone size to ensure fair page aging.  The zone a
 		 * page was allocated in should have no effect on the
 		 * time the page has in memory before being reclaimed.
-		 *
-		 * Try to stay in local zones in the fastpath.  If
-		 * that fails, the slowpath is entered, which will do
-		 * another pass starting with the local zones, but
-		 * ultimately fall back to remote zones that do not
-		 * partake in the fairness round-robin cycle of this
-		 * zonelist.
-		 *
-		 * NOTE: GFP_THISNODE allocations do not partake in
-		 * the kswapd aging protocol, so they can't be fair.
 		 */
-		if ((alloc_flags & ALLOC_WMARK_LOW) &&
-		    !gfp_thisnode_allocation(gfp_mask)) {
-			if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
-				continue;
+		if (alloc_flags & ALLOC_FAIR) {
 			if (!zone_local(preferred_zone, zone))
 				continue;
+			if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
+				continue;
 		}
 		/*
 		 * When allocating a page cache page for writing, we
@@ -2408,32 +2384,40 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
 	return page;
 }
 
-static void prepare_slowpath(gfp_t gfp_mask, unsigned int order,
-			     struct zonelist *zonelist,
-			     enum zone_type high_zoneidx,
-			     struct zone *preferred_zone)
+static void reset_alloc_batches(struct zonelist *zonelist,
+				enum zone_type high_zoneidx,
+				struct zone *preferred_zone)
 {
 	struct zoneref *z;
 	struct zone *zone;
 
 	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
-		if (!(gfp_mask & __GFP_NO_KSWAPD))
-			wakeup_kswapd(zone, order, zone_idx(preferred_zone));
 		/*
 		 * Only reset the batches of zones that were actually
-		 * considered in the fast path, we don't want to
-		 * thrash fairness information for zones that are not
+		 * considered in the fairness pass, we don't want to
+		 * trash fairness information for zones that are not
 		 * actually part of this zonelist's round-robin cycle.
 		 */
 		if (!zone_local(preferred_zone, zone))
 			continue;
 		mod_zone_page_state(zone, NR_ALLOC_BATCH,
-				    high_wmark_pages(zone) -
-				    low_wmark_pages(zone) -
-				    zone_page_state(zone, NR_ALLOC_BATCH));
+			high_wmark_pages(zone) - low_wmark_pages(zone) -
+			atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
 	}
 }
 
+static void wake_all_kswapds(unsigned int order,
+			     struct zonelist *zonelist,
+			     enum zone_type high_zoneidx,
+			     struct zone *preferred_zone)
+{
+	struct zoneref *z;
+	struct zone *zone;
+
+	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
+		wakeup_kswapd(zone, order, zone_idx(preferred_zone));
+}
+
 static inline int
 gfp_to_alloc_flags(gfp_t gfp_mask)
 {
@@ -2522,12 +2506,13 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	 * allowed per node queues are empty and that nodes are
 	 * over allocated.
 	 */
-	if (gfp_thisnode_allocation(gfp_mask))
+	if (IS_ENABLED(CONFIG_NUMA) &&
+	    (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
 		goto nopage;
 
 restart:
-	prepare_slowpath(gfp_mask, order, zonelist,
-			 high_zoneidx, preferred_zone);
+	if (!(gfp_mask & __GFP_NO_KSWAPD))
+		wake_all_kswapds(order, zonelist, high_zoneidx, preferred_zone);
 
 	/*
 	 * OK, we're below the kswapd watermark and have kicked background
@@ -2691,11 +2676,7 @@ rebalance:
 
 nopage:
 	warn_alloc_failed(gfp_mask, order, NULL);
-	return page;
 got_pg:
-	if (kmemcheck_enabled)
-		kmemcheck_pagealloc_alloc(page, order, gfp_mask);
-
 	return page;
 }
 
@@ -2711,7 +2692,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	struct page *page = NULL;
 	int migratetype = allocflags_to_migratetype(gfp_mask);
 	unsigned int cpuset_mems_cookie;
-	int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET;
+	int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR;
 	struct mem_cgroup *memcg = NULL;
 
 	gfp_mask &= gfp_allowed_mask;
@@ -2739,7 +2720,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 		return NULL;
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	/* The preferred zone is used for statistics later */
 	first_zones_zonelist(zonelist, high_zoneidx,
@@ -2752,12 +2733,29 @@ retry_cpuset:
 	if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
 		alloc_flags |= ALLOC_CMA;
 #endif
+retry:
 	/* First allocation attempt */
 	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
 			zonelist, high_zoneidx, alloc_flags,
 			preferred_zone, migratetype);
 	if (unlikely(!page)) {
 		/*
+		 * The first pass makes sure allocations are spread
+		 * fairly within the local node.  However, the local
+		 * node might have free pages left after the fairness
+		 * batches are exhausted, and remote zones haven't
+		 * even been considered yet.  Try once more without
+		 * fairness, and include remote zones now, before
+		 * entering the slowpath and waking kswapd: prefer
+		 * spilling to a remote zone over swapping locally.
+		 */
+		if (alloc_flags & ALLOC_FAIR) {
+			reset_alloc_batches(zonelist, high_zoneidx,
+					    preferred_zone);
+			alloc_flags &= ~ALLOC_FAIR;
+			goto retry;
+		}
+		/*
 		 * Runtime PM, block IO and its error handling path
 		 * can deadlock because I/O on the device might not
 		 * complete.
@@ -2768,6 +2766,8 @@ retry_cpuset:
 				preferred_zone, migratetype);
 	}
 
+	if (kmemcheck_enabled && page)
+		kmemcheck_pagealloc_alloc(page, order, gfp_mask);
 	trace_mm_page_alloc(page, order, gfp_mask, migratetype);
 
 out:
@@ -2777,7 +2777,7 @@ out:
 	 * the mask is being updated. If a page allocation is about to fail,
 	 * check if the cpuset changed during allocation and if so, retry.
 	 */
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 
 	memcg_kmem_commit_charge(page, memcg, order);
@@ -3045,9 +3045,9 @@ bool skip_free_areas_node(unsigned int flags, int nid)
 		goto out;
 
 	do {
-		cpuset_mems_cookie = get_mems_allowed();
+		cpuset_mems_cookie = read_mems_allowed_begin();
 		ret = !node_isset(nid, cpuset_current_mems_allowed);
-	} while (!put_mems_allowed(cpuset_mems_cookie));
+	} while (read_mems_allowed_retry(cpuset_mems_cookie));
 out:
 	return ret;
 }
@@ -4919,7 +4919,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 
 	pgdat->node_id = nid;
 	pgdat->node_start_pfn = node_start_pfn;
-	init_zone_allows_reclaim(nid);
+	if (node_state(nid, N_MEMORY))
+		init_zone_allows_reclaim(nid);
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 	get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
 #endif
@@ -6544,7 +6545,8 @@ static void dump_page_flags(unsigned long flags)
 	printk(")\n");
 }
 
-void dump_page_badflags(struct page *page, char *reason, unsigned long badflags)
+void dump_page_badflags(struct page *page, const char *reason,
+		unsigned long badflags)
 {
 	printk(KERN_ALERT
 	       "page:%p count:%d mapcount:%d mapping:%p index:%#lx\n",
@@ -6560,7 +6562,7 @@ void dump_page_badflags(struct page *page, char *reason, unsigned long badflags)
 	mem_cgroup_print_bad_page(page);
 }
 
-void dump_page(struct page *page, char *reason)
+void dump_page(struct page *page, const char *reason)
 {
 	dump_page_badflags(page, reason, 0);
 }
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index cfd162882c00..3708264d2833 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -175,7 +175,7 @@ static void free_page_cgroup(void *addr)
 	}
 }
 
-void __free_page_cgroup(unsigned long pfn)
+static void __free_page_cgroup(unsigned long pfn)
 {
 	struct mem_section *ms;
 	struct page_cgroup *base;
@@ -188,9 +188,9 @@ void __free_page_cgroup(unsigned long pfn)
 	ms->page_cgroup = NULL;
 }
 
-int __meminit online_page_cgroup(unsigned long start_pfn,
-			unsigned long nr_pages,
-			int nid)
+static int __meminit online_page_cgroup(unsigned long start_pfn,
+				unsigned long nr_pages,
+				int nid)
 {
 	unsigned long start, end, pfn;
 	int fail = 0;
@@ -223,8 +223,8 @@ int __meminit online_page_cgroup(unsigned long start_pfn,
 	return -ENOMEM;
 }
 
-int __meminit offline_page_cgroup(unsigned long start_pfn,
-		unsigned long nr_pages, int nid)
+static int __meminit offline_page_cgroup(unsigned long start_pfn,
+				unsigned long nr_pages, int nid)
 {
 	unsigned long start, end, pfn;
 
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 2beeabf502c5..a834f4deb527 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -3,29 +3,58 @@
 #include <linux/sched.h>
 #include <linux/hugetlb.h>
 
-static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
-			  struct mm_walk *walk)
+/*
+ * Check the current skip status of page table walker.
+ *
+ * Here what I mean by skip is to skip lower level walking, and that was
+ * determined for each entry independently. For example, when walk_pmd_range
+ * handles a pmd_trans_huge we don't have to walk over ptes under that pmd,
+ * and the skipping does not affect the walking over ptes under other pmds.
+ * That's why we reset @walk->skip after tested.
+ */
+static bool skip_lower_level_walking(struct mm_walk *walk)
 {
+	if (walk->skip) {
+		walk->skip = 0;
+		return true;
+	}
+	return false;
+}
+
+static int walk_pte_range(pmd_t *pmd, unsigned long addr,
+				unsigned long end, struct mm_walk *walk)
+{
+	struct mm_struct *mm = walk->mm;
 	pte_t *pte;
+	pte_t *orig_pte;
+	spinlock_t *ptl;
 	int err = 0;
 
-	pte = pte_offset_map(pmd, addr);
-	for (;;) {
+	orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	do {
+		if (pte_none(*pte)) {
+			if (walk->pte_hole)
+				err = walk->pte_hole(addr, addr + PAGE_SIZE,
+							walk);
+			if (err)
+				break;
+			continue;
+		}
+		/*
+		 * Callers should have their own way to handle swap entries
+		 * in walk->pte_entry().
+		 */
 		err = walk->pte_entry(pte, addr, addr + PAGE_SIZE, walk);
 		if (err)
 		       break;
-		addr += PAGE_SIZE;
-		if (addr == end)
-			break;
-		pte++;
-	}
-
-	pte_unmap(pte);
-	return err;
+	} while (pte++, addr += PAGE_SIZE, addr < end);
+	pte_unmap_unlock(orig_pte, ptl);
+	cond_resched();
+	return addr == end ? 0 : err;
 }
 
-static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
-			  struct mm_walk *walk)
+static int walk_pmd_range(pud_t *pud, unsigned long addr,
+				unsigned long end, struct mm_walk *walk)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -35,6 +64,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 	do {
 again:
 		next = pmd_addr_end(addr, end);
+
 		if (pmd_none(*pmd)) {
 			if (walk->pte_hole)
 				err = walk->pte_hole(addr, next, walk);
@@ -42,35 +72,32 @@ again:
 				break;
 			continue;
 		}
-		/*
-		 * This implies that each ->pmd_entry() handler
-		 * needs to know about pmd_trans_huge() pmds
-		 */
-		if (walk->pmd_entry)
-			err = walk->pmd_entry(pmd, addr, next, walk);
-		if (err)
-			break;
 
-		/*
-		 * Check this here so we only break down trans_huge
-		 * pages when we _need_ to
-		 */
-		if (!walk->pte_entry)
-			continue;
+		if (walk->pmd_entry) {
+			err = walk->pmd_entry(pmd, addr, next, walk);
+			if (skip_lower_level_walking(walk))
+				continue;
+			if (err)
+				break;
+		}
 
-		split_huge_page_pmd_mm(walk->mm, addr, pmd);
-		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
-			goto again;
-		err = walk_pte_range(pmd, addr, next, walk);
-		if (err)
-			break;
-	} while (pmd++, addr = next, addr != end);
+		if (walk->pte_entry) {
+			if (walk->vma) {
+				split_huge_page_pmd(walk->vma, addr, pmd);
+				if (pmd_trans_unstable(pmd))
+					goto again;
+			}
+			err = walk_pte_range(pmd, addr, next, walk);
+			if (err)
+				break;
+		}
+	} while (pmd++, addr = next, addr < end);
 
 	return err;
 }
 
-static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
-			  struct mm_walk *walk)
+static int walk_pud_range(pgd_t *pgd, unsigned long addr,
+				unsigned long end, struct mm_walk *walk)
 {
 	pud_t *pud;
 	unsigned long next;
@@ -79,6 +106,7 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 	pud = pud_offset(pgd, addr);
 	do {
 		next = pud_addr_end(addr, end);
+
 		if (pud_none_or_clear_bad(pud)) {
 			if (walk->pte_hole)
 				err = walk->pte_hole(addr, next, walk);
@@ -86,13 +114,58 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 				break;
 			continue;
 		}
-		if (walk->pud_entry)
+
+		if (walk->pud_entry) {
 			err = walk->pud_entry(pud, addr, next, walk);
-		if (!err && (walk->pmd_entry || walk->pte_entry))
+			if (skip_lower_level_walking(walk))
+				continue;
+			if (err)
+				break;
+		}
+
+		if (walk->pmd_entry || walk->pte_entry) {
 			err = walk_pmd_range(pud, addr, next, walk);
-		if (err)
-			break;
-	} while (pud++, addr = next, addr != end);
+			if (err)
+				break;
+		}
+	} while (pud++, addr = next, addr < end);
+
+	return err;
+}
+
+static int walk_pgd_range(unsigned long addr, unsigned long end,
+			struct mm_walk *walk)
+{
+	pgd_t *pgd;
+	unsigned long next;
+	int err = 0;
+
+	pgd = pgd_offset(walk->mm, addr);
+	do {
+		next = pgd_addr_end(addr, end);
+
+		if (pgd_none_or_clear_bad(pgd)) {
+			if (walk->pte_hole)
+				err = walk->pte_hole(addr, next, walk);
+			if (err)
+				break;
+			continue;
+		}
+
+		if (walk->pgd_entry) {
+			err = walk->pgd_entry(pgd, addr, next, walk);
+			if (skip_lower_level_walking(walk))
+				continue;
+			if (err)
+				break;
+		}
+
+		if (walk->pud_entry || walk->pmd_entry || walk->pte_entry) {
+			err = walk_pud_range(pgd, addr, next, walk);
+			if (err)
+				break;
+		}
+	} while (pgd++, addr = next, addr < end);
 
 	return err;
 }
@@ -105,144 +178,178 @@ static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr,
 	return boundary < end ? boundary : end;
 }
 
-static int walk_hugetlb_range(struct vm_area_struct *vma,
-			      unsigned long addr, unsigned long end,
-			      struct mm_walk *walk)
+static int walk_hugetlb_range(unsigned long addr, unsigned long end,
+				struct mm_walk *walk)
 {
+	struct mm_struct *mm = walk->mm;
+	struct vm_area_struct *vma = walk->vma;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long next;
 	unsigned long hmask = huge_page_mask(h);
 	pte_t *pte;
 	int err = 0;
+	spinlock_t *ptl;
 
 	do {
 		next = hugetlb_entry_end(h, addr, end);
 		pte = huge_pte_offset(walk->mm, addr & hmask);
+		ptl = huge_pte_lock(h, mm, pte);
+		/*
+		 * Callers should have their own way to handle swap entries
+		 * in walk->hugetlb_entry().
+		 */
 		if (pte && walk->hugetlb_entry)
-			err = walk->hugetlb_entry(pte, hmask, addr, next, walk);
+			err = walk->hugetlb_entry(pte, addr, next, walk);
+		spin_unlock(ptl);
 		if (err)
-			return err;
+			break;
 	} while (addr = next, addr != end);
-
-	return 0;
+	cond_resched();
+	return err;
 }
 
 #else /* CONFIG_HUGETLB_PAGE */
-static int walk_hugetlb_range(struct vm_area_struct *vma,
-			      unsigned long addr, unsigned long end,
-			      struct mm_walk *walk)
+static inline int walk_hugetlb_range(unsigned long addr, unsigned long end,
+				struct mm_walk *walk)
 {
 	return 0;
 }
 
 #endif /* CONFIG_HUGETLB_PAGE */
 
+/*
+ * Decide whether we really walk over the current vma on [@start, @end)
+ * or skip it. When we skip it, we set @walk->skip to 1.
+ * The return value is used to control the page table walking to
+ * continue (for zero) or not (for non-zero).
+ *
+ * Default check (only VM_PFNMAP check for now) is used when the caller
+ * doesn't define test_walk() callback.
+ */
+static int walk_page_test(unsigned long start, unsigned long end,
+			struct mm_walk *walk)
+{
+	struct vm_area_struct *vma = walk->vma;
+
+	if (walk->test_walk)
+		return walk->test_walk(start, end, walk);
 
+	/*
+	 * Do not walk over vma(VM_PFNMAP), because we have no valid struct
+	 * page backing a VM_PFNMAP range. See also commit a9ff785e4437.
+	 */
+	if (vma->vm_flags & VM_PFNMAP)
+		walk->skip = 1;
+	return 0;
+}
+
+static int __walk_page_range(unsigned long start, unsigned long end,
+			struct mm_walk *walk)
+{
+	int err = 0;
+	struct vm_area_struct *vma = walk->vma;
+
+	if (vma && is_vm_hugetlb_page(vma)) {
+		if (walk->hugetlb_entry)
+			err = walk_hugetlb_range(start, end, walk);
+	} else
+		err = walk_pgd_range(start, end, walk);
+
+	return err;
+}
 
 /**
- * walk_page_range - walk a memory map's page tables with a callback
- * @addr: starting address
- * @end: ending address
- * @walk: set of callbacks to invoke for each level of the tree
+ * walk_page_range - walk page table with caller specific callbacks
+ *
+ * Recursively walk the page table tree of the process represented by
+ * @walk->mm within the virtual address range [@start, @end). In walking,
+ * we can call caller-specific callback functions against each entry.
  *
- * Recursively walk the page table for the memory area in a VMA,
- * calling supplied callbacks. Callbacks are called in-order (first
- * PGD, first PUD, first PMD, first PTE, second PTE... second PMD,
- * etc.). If lower-level callbacks are omitted, walking depth is reduced.
+ * Before starting to walk page table, some callers want to check whether
+ * they really want to walk over the vma (for example by checking vm_flags.)
+ * walk_page_test() and @walk->test_walk() do that check.
  *
- * Each callback receives an entry pointer and the start and end of the
- * associated range, and a copy of the original mm_walk for access to
- * the ->private or ->mm fields.
+ * If any callback returns a non-zero value, the page table walk is aborted
+ * immediately and the return value is propagated back to the caller.
+ * Note that the meaning of the positive returned value can be defined
+ * by the caller for its own purpose.
  *
- * Usually no locks are taken, but splitting transparent huge page may
- * take page table lock. And the bottom level iterator will map PTE
- * directories from highmem if necessary.
+ * If the caller defines multiple callbacks in different levels, the
+ * callbacks are called in depth-first manner. It could happen that
+ * multiple callbacks are called on a address. For example if some caller
+ * defines test_walk(), pmd_entry(), and pte_entry(), then callbacks are
+ * called in the order of test_walk(), pmd_entry(), and pte_entry().
+ * If you don't want to go down to lower level at some point and move to
+ * the next entry in the same level, you set @walk->skip to 1.
+ * For example if you succeed to handle some pmd entry as trans_huge entry,
+ * you need not call walk_pte_range() any more, so set it to avoid that.
+ * We can't determine whether to go down to lower level with the return
+ * value of the callback, because the whole range of return values (0, >0,
+ * and <0) are used up for other meanings.
  *
- * If any callback returns a non-zero value, the walk is aborted and
- * the return value is propagated back to the caller. Otherwise 0 is returned.
+ * Each callback can access to the vma over which it is doing page table
+ * walk right now via @walk->vma. @walk->vma is set to NULL in walking
+ * outside a vma. If you want to access to some caller-specific data from
+ * callbacks, @walk->private should be helpful.
  *
- * walk->mm->mmap_sem must be held for at least read if walk->hugetlb_entry
- * is !NULL.
+ * The callers should hold @walk->mm->mmap_sem. Note that the lower level
+ * iterators can take page table lock in lowest level iteration and/or
+ * in split_huge_page_pmd().
  */
-int walk_page_range(unsigned long addr, unsigned long end,
+int walk_page_range(unsigned long start, unsigned long end,
 		    struct mm_walk *walk)
 {
-	pgd_t *pgd;
-	unsigned long next;
 	int err = 0;
+	struct vm_area_struct *vma;
+	unsigned long next;
 
-	if (addr >= end)
-		return err;
+	if (start >= end)
+		return -EINVAL;
 
 	if (!walk->mm)
 		return -EINVAL;
 
 	VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem));
 
-	pgd = pgd_offset(walk->mm, addr);
 	do {
-		struct vm_area_struct *vma = NULL;
+		vma = find_vma(walk->mm, start);
+		if (!vma) { /* after the last vma */
+			walk->vma = NULL;
+			next = end;
+		} else if (start < vma->vm_start) { /* outside the found vma */
+			walk->vma = NULL;
+			next = vma->vm_start;
+		} else { /* inside the found vma */
+			walk->vma = vma;
+			next = min(end, vma->vm_end);
 
-		next = pgd_addr_end(addr, end);
-
-		/*
-		 * This function was not intended to be vma based.
-		 * But there are vma special cases to be handled:
-		 * - hugetlb vma's
-		 * - VM_PFNMAP vma's
-		 */
-		vma = find_vma(walk->mm, addr);
-		if (vma) {
-			/*
-			 * There are no page structures backing a VM_PFNMAP
-			 * range, so do not allow split_huge_page_pmd().
-			 */
-			if ((vma->vm_start <= addr) &&
-			    (vma->vm_flags & VM_PFNMAP)) {
-				next = vma->vm_end;
-				pgd = pgd_offset(walk->mm, next);
-				continue;
-			}
-			/*
-			 * Handle hugetlb vma individually because pagetable
-			 * walk for the hugetlb page is dependent on the
-			 * architecture and we can't handled it in the same
-			 * manner as non-huge pages.
-			 */
-			if (walk->hugetlb_entry && (vma->vm_start <= addr) &&
-			    is_vm_hugetlb_page(vma)) {
-				if (vma->vm_end < next)
-					next = vma->vm_end;
-				/*
-				 * Hugepage is very tightly coupled with vma,
-				 * so walk through hugetlb entries within a
-				 * given vma.
-				 */
-				err = walk_hugetlb_range(vma, addr, next, walk);
-				if (err)
-					break;
-				pgd = pgd_offset(walk->mm, next);
+			err = walk_page_test(start, next, walk);
+			if (skip_lower_level_walking(walk))
 				continue;
-			}
-		}
-
-		if (pgd_none_or_clear_bad(pgd)) {
-			if (walk->pte_hole)
-				err = walk->pte_hole(addr, next, walk);
 			if (err)
 				break;
-			pgd++;
-			continue;
 		}
-		if (walk->pgd_entry)
-			err = walk->pgd_entry(pgd, addr, next, walk);
-		if (!err &&
-		    (walk->pud_entry || walk->pmd_entry || walk->pte_entry))
-			err = walk_pud_range(pgd, addr, next, walk);
+		err = __walk_page_range(start, next, walk);
 		if (err)
 			break;
-		pgd++;
-	} while (addr = next, addr < end);
-
+	} while (start = next, start < end);
 	return err;
 }
+
+int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk)
+{
+	int err;
+
+	if (!walk->mm)
+		return -EINVAL;
+
+	VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem));
+	VM_BUG_ON(!vma);
+	walk->vma = vma;
+	err = walk_page_test(vma->vm_start, vma->vm_end, walk);
+	if (skip_lower_level_walking(walk))
+		return 0;
+	if (err)
+		return err;
+	return __walk_page_range(vma->vm_start, vma->vm_end, walk);
+}
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 3c5cf68566ec..cb79065c19e5 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -412,7 +412,7 @@ SYSCALL_DEFINE6(process_vm_writev, pid_t, pid,
 
 #ifdef CONFIG_COMPAT
 
-asmlinkage ssize_t
+static ssize_t
 compat_process_vm_rw(compat_pid_t pid,
 		     const struct compat_iovec __user *lvec,
 		     unsigned long liovcnt,
diff --git a/mm/readahead.c b/mm/readahead.c
index 0de2360d65f3..29c5e1af5a0c 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -179,7 +179,7 @@ __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
 		rcu_read_lock();
 		page = radix_tree_lookup(&mapping->page_tree, page_offset);
 		rcu_read_unlock();
-		if (page)
+		if (page && !radix_tree_exceptional_entry(page))
 			continue;
 
 		page = page_cache_alloc_readahead(mapping);
@@ -233,14 +233,14 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
 	return 0;
 }
 
+#define MAX_READAHEAD   ((512*4096)/PAGE_CACHE_SIZE)
 /*
  * Given a desired number of PAGE_CACHE_SIZE readahead pages, return a
  * sensible upper limit.
  */
 unsigned long max_sane_readahead(unsigned long nr)
 {
-	return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE_FILE)
-		+ node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2);
+	return min(nr, MAX_READAHEAD);
 }
 
 /*
@@ -347,7 +347,7 @@ static pgoff_t count_history_pages(struct address_space *mapping,
 	pgoff_t head;
 
 	rcu_read_lock();
-	head = radix_tree_prev_hole(&mapping->page_tree, offset - 1, max);
+	head = page_cache_prev_hole(mapping, offset - 1, max);
 	rcu_read_unlock();
 
 	return offset - 1 - head;
@@ -427,7 +427,7 @@ ondemand_readahead(struct address_space *mapping,
 		pgoff_t start;
 
 		rcu_read_lock();
-		start = radix_tree_next_hole(&mapping->page_tree, offset+1,max);
+		start = page_cache_next_hole(mapping, offset + 1, max);
 		rcu_read_unlock();
 
 		if (!start || start - offset > max)
diff --git a/mm/rmap.c b/mm/rmap.c
index 11cf322f8133..79f21809a9ec 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -515,11 +515,7 @@ void page_unlock_anon_vma_read(struct anon_vma *anon_vma)
 static inline unsigned long
 __vma_address(struct page *page, struct vm_area_struct *vma)
 {
-	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
-
-	if (unlikely(is_vm_hugetlb_page(vma)))
-		pgoff = page->index << huge_page_order(page_hstate(page));
-
+	pgoff_t pgoff = page_pgoff(page);
 	return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
 }
 
@@ -1332,9 +1328,19 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 		BUG_ON(!page || PageAnon(page));
 
 		if (locked_vma) {
-			mlock_vma_page(page);   /* no-op if already mlocked */
-			if (page == check_page)
+			if (page == check_page) {
+				/* we know we have check_page locked */
+				mlock_vma_page(page);
 				ret = SWAP_MLOCK;
+			} else if (trylock_page(page)) {
+				/*
+				 * If we can lock the page, perform mlock.
+				 * Otherwise leave the page alone, it will be
+				 * eventually encountered again later.
+				 */
+				mlock_vma_page(page);
+				unlock_page(page);
+			}
 			continue;	/* don't unmap */
 		}
 
@@ -1599,7 +1605,7 @@ static struct anon_vma *rmap_walk_anon_lock(struct page *page,
 static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc)
 {
 	struct anon_vma *anon_vma;
-	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+	pgoff_t pgoff = page_pgoff(page);
 	struct anon_vma_chain *avc;
 	int ret = SWAP_AGAIN;
 
@@ -1640,7 +1646,7 @@ static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc)
 static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc)
 {
 	struct address_space *mapping = page->mapping;
-	pgoff_t pgoff = page->index << compound_order(page);
+	pgoff_t pgoff = page_pgoff(page);
 	struct vm_area_struct *vma;
 	int ret = SWAP_AGAIN;
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 1f18c9d0d93e..70273f8df586 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -242,19 +242,17 @@ static int shmem_radix_tree_replace(struct address_space *mapping,
 			pgoff_t index, void *expected, void *replacement)
 {
 	void **pslot;
-	void *item = NULL;
+	void *item;
 
 	VM_BUG_ON(!expected);
+	VM_BUG_ON(!replacement);
 	pslot = radix_tree_lookup_slot(&mapping->page_tree, index);
-	if (pslot)
-		item = radix_tree_deref_slot_protected(pslot,
-							&mapping->tree_lock);
+	if (!pslot)
+		return -ENOENT;
+	item = radix_tree_deref_slot_protected(pslot, &mapping->tree_lock);
 	if (item != expected)
 		return -ENOENT;
-	if (replacement)
-		radix_tree_replace_slot(pslot, replacement);
-	else
-		radix_tree_delete(&mapping->page_tree, index);
+	radix_tree_replace_slot(pslot, replacement);
 	return 0;
 }
 
@@ -331,84 +329,20 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap)
 }
 
 /*
- * Like find_get_pages, but collecting swap entries as well as pages.
- */
-static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping,
-					pgoff_t start, unsigned int nr_pages,
-					struct page **pages, pgoff_t *indices)
-{
-	void **slot;
-	unsigned int ret = 0;
-	struct radix_tree_iter iter;
-
-	if (!nr_pages)
-		return 0;
-
-	rcu_read_lock();
-restart:
-	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
-		struct page *page;
-repeat:
-		page = radix_tree_deref_slot(slot);
-		if (unlikely(!page))
-			continue;
-		if (radix_tree_exception(page)) {
-			if (radix_tree_deref_retry(page))
-				goto restart;
-			/*
-			 * Otherwise, we must be storing a swap entry
-			 * here as an exceptional entry: so return it
-			 * without attempting to raise page count.
-			 */
-			goto export;
-		}
-		if (!page_cache_get_speculative(page))
-			goto repeat;
-
-		/* Has the page moved? */
-		if (unlikely(page != *slot)) {
-			page_cache_release(page);
-			goto repeat;
-		}
-export:
-		indices[ret] = iter.index;
-		pages[ret] = page;
-		if (++ret == nr_pages)
-			break;
-	}
-	rcu_read_unlock();
-	return ret;
-}
-
-/*
  * Remove swap entry from radix tree, free the swap and its page cache.
  */
 static int shmem_free_swap(struct address_space *mapping,
 			   pgoff_t index, void *radswap)
 {
-	int error;
+	void *old;
 
 	spin_lock_irq(&mapping->tree_lock);
-	error = shmem_radix_tree_replace(mapping, index, radswap, NULL);
+	old = radix_tree_delete_item(&mapping->page_tree, index, radswap);
 	spin_unlock_irq(&mapping->tree_lock);
-	if (!error)
-		free_swap_and_cache(radix_to_swp_entry(radswap));
-	return error;
-}
-
-/*
- * Pagevec may contain swap entries, so shuffle up pages before releasing.
- */
-static void shmem_deswap_pagevec(struct pagevec *pvec)
-{
-	int i, j;
-
-	for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
-		struct page *page = pvec->pages[i];
-		if (!radix_tree_exceptional_entry(page))
-			pvec->pages[j++] = page;
-	}
-	pvec->nr = j;
+	if (old != radswap)
+		return -ENOENT;
+	free_swap_and_cache(radix_to_swp_entry(radswap));
+	return 0;
 }
 
 /*
@@ -429,12 +363,12 @@ void shmem_unlock_mapping(struct address_space *mapping)
 		 * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it
 		 * has finished, if it hits a row of PAGEVEC_SIZE swap entries.
 		 */
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
-					PAGEVEC_SIZE, pvec.pages, indices);
+		pvec.nr = find_get_entries(mapping, index,
+					   PAGEVEC_SIZE, pvec.pages, indices);
 		if (!pvec.nr)
 			break;
 		index = indices[pvec.nr - 1] + 1;
-		shmem_deswap_pagevec(&pvec);
+		pagevec_remove_exceptionals(&pvec);
 		check_move_unevictable_pages(pvec.pages, pvec.nr);
 		pagevec_release(&pvec);
 		cond_resched();
@@ -466,9 +400,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 	pagevec_init(&pvec, 0);
 	index = start;
 	while (index < end) {
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
-				min(end - index, (pgoff_t)PAGEVEC_SIZE),
-							pvec.pages, indices);
+		pvec.nr = find_get_entries(mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE),
+			pvec.pages, indices);
 		if (!pvec.nr)
 			break;
 		mem_cgroup_uncharge_start();
@@ -497,7 +431,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			}
 			unlock_page(page);
 		}
-		shmem_deswap_pagevec(&pvec);
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
@@ -535,9 +469,10 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 	index = start;
 	for ( ; ; ) {
 		cond_resched();
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+
+		pvec.nr = find_get_entries(mapping, index,
 				min(end - index, (pgoff_t)PAGEVEC_SIZE),
-							pvec.pages, indices);
+				pvec.pages, indices);
 		if (!pvec.nr) {
 			if (index == start || unfalloc)
 				break;
@@ -545,7 +480,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			continue;
 		}
 		if ((index == start || unfalloc) && indices[0] >= end) {
-			shmem_deswap_pagevec(&pvec);
+			pagevec_remove_exceptionals(&pvec);
 			pagevec_release(&pvec);
 			break;
 		}
@@ -574,7 +509,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			}
 			unlock_page(page);
 		}
-		shmem_deswap_pagevec(&pvec);
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		index++;
@@ -748,7 +683,7 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
 	 * the shmem_swaplist_mutex which might hold up shmem_writepage().
 	 * Charged back to the user (not to caller) when swap account is used.
 	 */
-	error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL);
+	error = mem_cgroup_charge_file(page, current->mm, GFP_KERNEL);
 	if (error)
 		goto out;
 	/* No radix_tree_preload: swap entry keeps a place for page in tree */
@@ -1080,7 +1015,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 		return -EFBIG;
 repeat:
 	swap.val = 0;
-	page = find_lock_page(mapping, index);
+	page = find_lock_entry(mapping, index);
 	if (radix_tree_exceptional_entry(page)) {
 		swap = radix_to_swp_entry(page);
 		page = NULL;
@@ -1145,7 +1080,7 @@ repeat:
 				goto failed;
 		}
 
-		error = mem_cgroup_cache_charge(page, current->mm,
+		error = mem_cgroup_charge_file(page, current->mm,
 						gfp & GFP_RECLAIM_MASK);
 		if (!error) {
 			error = shmem_add_to_page_cache(page, mapping, index,
@@ -1199,7 +1134,7 @@ repeat:
 
 		SetPageSwapBacked(page);
 		__set_page_locked(page);
-		error = mem_cgroup_cache_charge(page, current->mm,
+		error = mem_cgroup_charge_file(page, current->mm,
 						gfp & GFP_RECLAIM_MASK);
 		if (error)
 			goto decused;
@@ -1417,6 +1352,11 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 	return inode;
 }
 
+bool shmem_mapping(struct address_space *mapping)
+{
+	return mapping->backing_dev_info == &shmem_backing_dev_info;
+}
+
 #ifdef CONFIG_TMPFS
 static const struct inode_operations shmem_symlink_inode_operations;
 static const struct inode_operations shmem_short_symlink_operations;
@@ -1729,7 +1669,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
 	pagevec_init(&pvec, 0);
 	pvec.nr = 1;		/* start small: we may be there already */
 	while (!done) {
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+		pvec.nr = find_get_entries(mapping, index,
 					pvec.nr, pvec.pages, indices);
 		if (!pvec.nr) {
 			if (whence == SEEK_DATA)
@@ -1756,7 +1696,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
 				break;
 			}
 		}
-		shmem_deswap_pagevec(&pvec);
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		pvec.nr = PAGEVEC_SIZE;
 		cond_resched();
@@ -2783,6 +2723,7 @@ static const struct super_operations shmem_ops = {
 
 static const struct vm_operations_struct shmem_vm_ops = {
 	.fault		= shmem_fault,
+	.map_pages	= filemap_map_pages,
 #ifdef CONFIG_NUMA
 	.set_policy     = shmem_set_policy,
 	.get_policy     = shmem_get_policy,
diff --git a/mm/slab.c b/mm/slab.c
index 8dd8e0875e4c..388cb1ae6fbc 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2922,9 +2922,9 @@ retry:
 		/* move slabp to correct slabp list: */
 		list_del(&page->lru);
 		if (page->active == cachep->num)
-			list_add(&page->list, &n->slabs_full);
+			list_add(&page->lru, &n->slabs_full);
 		else
-			list_add(&page->list, &n->slabs_partial);
+			list_add(&page->lru, &n->slabs_partial);
 	}
 
 must_grow:
@@ -3063,7 +3063,7 @@ out:
 
 #ifdef CONFIG_NUMA
 /*
- * Try allocating on another node if PF_SPREAD_SLAB|PF_MEMPOLICY.
+ * Try allocating on another node if PF_SPREAD_SLAB is a mempolicy is set.
  *
  * If we are in_interrupt, then process context, including cpusets and
  * mempolicy, may not apply and should not be used for allocation policy.
@@ -3078,7 +3078,7 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
 	if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
 		nid_alloc = cpuset_slab_spread_node();
 	else if (current->mempolicy)
-		nid_alloc = slab_node();
+		nid_alloc = mempolicy_slab_node();
 	if (nid_alloc != nid_here)
 		return ____cache_alloc_node(cachep, flags, nid_alloc);
 	return NULL;
@@ -3109,8 +3109,8 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
-	zonelist = node_zonelist(slab_node(), flags);
+	cpuset_mems_cookie = read_mems_allowed_begin();
+	zonelist = node_zonelist(mempolicy_slab_node(), flags);
 
 retry:
 	/*
@@ -3167,7 +3167,7 @@ retry:
 		}
 	}
 
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj))
+	if (unlikely(!obj && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 	return obj;
 }
@@ -3295,7 +3295,7 @@ __do_cache_alloc(struct kmem_cache *cache, gfp_t flags)
 {
 	void *objp;
 
-	if (unlikely(current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY))) {
+	if (current->mempolicy || unlikely(current->flags & PF_SPREAD_SLAB)) {
 		objp = alternate_node_alloc(cache, flags);
 		if (objp)
 			goto out;
diff --git a/mm/slob.c b/mm/slob.c
index 4bf8809dfcce..730cad45d4be 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -111,13 +111,13 @@ static inline int slob_page_free(struct page *sp)
 
 static void set_slob_page_free(struct page *sp, struct list_head *list)
 {
-	list_add(&sp->list, list);
+	list_add(&sp->lru, list);
 	__SetPageSlobFree(sp);
 }
 
 static inline void clear_slob_page_free(struct page *sp)
 {
-	list_del(&sp->list);
+	list_del(&sp->lru);
 	__ClearPageSlobFree(sp);
 }
 
@@ -282,7 +282,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
 
 	spin_lock_irqsave(&slob_lock, flags);
 	/* Iterate through each partially free page, try to find room */
-	list_for_each_entry(sp, slob_list, list) {
+	list_for_each_entry(sp, slob_list, lru) {
 #ifdef CONFIG_NUMA
 		/*
 		 * If there's a node specification, search for a partial
@@ -296,7 +296,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
 			continue;
 
 		/* Attempt to alloc */
-		prev = sp->list.prev;
+		prev = sp->lru.prev;
 		b = slob_page_alloc(sp, size, align);
 		if (!b)
 			continue;
@@ -322,7 +322,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
 		spin_lock_irqsave(&slob_lock, flags);
 		sp->units = SLOB_UNITS(PAGE_SIZE);
 		sp->freelist = b;
-		INIT_LIST_HEAD(&sp->list);
+		INIT_LIST_HEAD(&sp->lru);
 		set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE));
 		set_slob_page_free(sp, slob_list);
 		b = slob_page_alloc(sp, size, align);
diff --git a/mm/slub.c b/mm/slub.c
index 94d44bb2635c..93a5bd096ac7 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1685,8 +1685,8 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
 		return NULL;
 
 	do {
-		cpuset_mems_cookie = get_mems_allowed();
-		zonelist = node_zonelist(slab_node(), flags);
+		cpuset_mems_cookie = read_mems_allowed_begin();
+		zonelist = node_zonelist(mempolicy_slab_node(), flags);
 		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 			struct kmem_cache_node *n;
 
@@ -1697,19 +1697,17 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
 				object = get_partial_node(s, n, c, flags);
 				if (object) {
 					/*
-					 * Return the object even if
-					 * put_mems_allowed indicated that
-					 * the cpuset mems_allowed was
-					 * updated in parallel. It's a
-					 * harmless race between the alloc
-					 * and the cpuset update.
+					 * Don't check read_mems_allowed_retry()
+					 * here - if mems_allowed was updated in
+					 * parallel, that was a harmless race
+					 * between allocation and the cpuset
+					 * update
 					 */
-					put_mems_allowed(cpuset_mems_cookie);
 					return object;
 				}
 			}
 		}
-	} while (!put_mems_allowed(cpuset_mems_cookie));
+	} while (read_mems_allowed_retry(cpuset_mems_cookie));
 #endif
 	return NULL;
 }
@@ -3240,8 +3238,9 @@ int __kmem_cache_shutdown(struct kmem_cache *s)
 
 	if (!rc) {
 		/*
-		 * We do the same lock strategy around sysfs_slab_add, see
-		 * __kmem_cache_create. Because this is pretty much the last
+		 * Since slab_attr_store may take the slab_mutex, we should
+		 * release the lock while removing the sysfs entry in order to
+		 * avoid a deadlock. Because this is pretty much the last
 		 * operation we do and the lock will be released shortly after
 		 * that in slab_common.c, we could just move sysfs_slab_remove
 		 * to a later point in common code. We should do that when we
@@ -3781,10 +3780,7 @@ int __kmem_cache_create(struct kmem_cache *s, unsigned long flags)
 		return 0;
 
 	memcg_propagate_slab_attrs(s);
-	mutex_unlock(&slab_mutex);
 	err = sysfs_slab_add(s);
-	mutex_lock(&slab_mutex);
-
 	if (err)
 		kmem_cache_close(s);
 
diff --git a/mm/sparse.c b/mm/sparse.c
index 38cad8fd7397..d1b48b691ac8 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -5,10 +5,12 @@
 #include <linux/slab.h>
 #include <linux/mmzone.h>
 #include <linux/bootmem.h>
+#include <linux/compiler.h>
 #include <linux/highmem.h>
 #include <linux/export.h>
 #include <linux/spinlock.h>
 #include <linux/vmalloc.h>
+
 #include "internal.h"
 #include <asm/dma.h>
 #include <asm/pgalloc.h>
@@ -461,7 +463,7 @@ static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
 }
 #endif
 
-void __attribute__((weak)) __meminit vmemmap_populate_print_last(void)
+void __weak __meminit vmemmap_populate_print_last(void)
 {
 }
 
diff --git a/mm/swap.c b/mm/swap.c
index 0092097b3f4c..9ce43ba4498b 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -574,6 +574,8 @@ void mark_page_accessed(struct page *page)
 		else
 			__lru_cache_activate_page(page);
 		ClearPageReferenced(page);
+		if (page_is_file_cache(page))
+			workingset_activation(page);
 	} else if (!PageReferenced(page)) {
 		SetPageReferenced(page);
 	}
@@ -948,6 +950,57 @@ void __pagevec_lru_add(struct pagevec *pvec)
 EXPORT_SYMBOL(__pagevec_lru_add);
 
 /**
+ * pagevec_lookup_entries - gang pagecache lookup
+ * @pvec:	Where the resulting entries are placed
+ * @mapping:	The address_space to search
+ * @start:	The starting entry index
+ * @nr_entries:	The maximum number of entries
+ * @indices:	The cache indices corresponding to the entries in @pvec
+ *
+ * pagevec_lookup_entries() will search for and return a group of up
+ * to @nr_entries pages and shadow entries in the mapping.  All
+ * entries are placed in @pvec.  pagevec_lookup_entries() takes a
+ * reference against actual pages in @pvec.
+ *
+ * The search returns a group of mapping-contiguous entries with
+ * ascending indexes.  There may be holes in the indices due to
+ * not-present entries.
+ *
+ * pagevec_lookup_entries() returns the number of entries which were
+ * found.
+ */
+unsigned pagevec_lookup_entries(struct pagevec *pvec,
+				struct address_space *mapping,
+				pgoff_t start, unsigned nr_pages,
+				pgoff_t *indices)
+{
+	pvec->nr = find_get_entries(mapping, start, nr_pages,
+				    pvec->pages, indices);
+	return pagevec_count(pvec);
+}
+
+/**
+ * pagevec_remove_exceptionals - pagevec exceptionals pruning
+ * @pvec:	The pagevec to prune
+ *
+ * pagevec_lookup_entries() fills both pages and exceptional radix
+ * tree entries into the pagevec.  This function prunes all
+ * exceptionals from @pvec without leaving holes, so that it can be
+ * passed on to page-only pagevec operations.
+ */
+void pagevec_remove_exceptionals(struct pagevec *pvec)
+{
+	int i, j;
+
+	for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
+		struct page *page = pvec->pages[i];
+		if (!radix_tree_exceptional_entry(page))
+			pvec->pages[j++] = page;
+	}
+	pvec->nr = j;
+}
+
+/**
  * pagevec_lookup - gang pagecache lookup
  * @pvec:	Where the resulting pages are placed
  * @mapping:	The address_space to search
diff --git a/mm/truncate.c b/mm/truncate.c
index 353b683afd6e..e5cc39ab0751 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -22,6 +22,45 @@
 #include <linux/cleancache.h>
 #include "internal.h"
 
+static void clear_exceptional_entry(struct address_space *mapping,
+				    pgoff_t index, void *entry)
+{
+	struct radix_tree_node *node;
+	void **slot;
+
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return;
+
+	spin_lock_irq(&mapping->tree_lock);
+	/*
+	 * Regular page slots are stabilized by the page lock even
+	 * without the tree itself locked.  These unlocked entries
+	 * need verification under the tree lock.
+	 */
+	if (!__radix_tree_lookup(&mapping->page_tree, index, &node, &slot))
+		goto unlock;
+	if (*slot != entry)
+		goto unlock;
+	radix_tree_replace_slot(slot, NULL);
+	mapping->nrshadows--;
+	if (!node)
+		goto unlock;
+	workingset_node_shadows_dec(node);
+	/*
+	 * Don't track node without shadow entries.
+	 *
+	 * Avoid acquiring the list_lru lock if already untracked.
+	 * The list_empty() test is safe as node->private_list is
+	 * protected by mapping->tree_lock.
+	 */
+	if (!workingset_node_shadows(node) &&
+	    !list_empty(&node->private_list))
+		list_lru_del(&workingset_shadow_nodes, &node->private_list);
+	__radix_tree_delete_node(&mapping->page_tree, node);
+unlock:
+	spin_unlock_irq(&mapping->tree_lock);
+}
 
 /**
  * do_invalidatepage - invalidate part or all of a page
@@ -208,11 +247,12 @@ void truncate_inode_pages_range(struct address_space *mapping,
 	unsigned int	partial_start;	/* inclusive */
 	unsigned int	partial_end;	/* exclusive */
 	struct pagevec	pvec;
+	pgoff_t		indices[PAGEVEC_SIZE];
 	pgoff_t		index;
 	int		i;
 
 	cleancache_invalidate_inode(mapping);
-	if (mapping->nrpages == 0)
+	if (mapping->nrpages == 0 && mapping->nrshadows == 0)
 		return;
 
 	/* Offsets within partial pages */
@@ -238,17 +278,23 @@ void truncate_inode_pages_range(struct address_space *mapping,
 
 	pagevec_init(&pvec, 0);
 	index = start;
-	while (index < end && pagevec_lookup(&pvec, mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE))) {
+	while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE),
+			indices)) {
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
 			/* We rely upon deletion not changing page->index */
-			index = page->index;
+			index = indices[i];
 			if (index >= end)
 				break;
 
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
 			if (!trylock_page(page))
 				continue;
 			WARN_ON(page->index != index);
@@ -259,6 +305,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			truncate_inode_page(mapping, page);
 			unlock_page(page);
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
@@ -307,14 +354,16 @@ void truncate_inode_pages_range(struct address_space *mapping,
 	index = start;
 	for ( ; ; ) {
 		cond_resched();
-		if (!pagevec_lookup(&pvec, mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE))) {
+		if (!pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE),
+			indices)) {
 			if (index == start)
 				break;
 			index = start;
 			continue;
 		}
-		if (index == start && pvec.pages[0]->index >= end) {
+		if (index == start && indices[0] >= end) {
+			pagevec_remove_exceptionals(&pvec);
 			pagevec_release(&pvec);
 			break;
 		}
@@ -323,16 +372,22 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			struct page *page = pvec.pages[i];
 
 			/* We rely upon deletion not changing page->index */
-			index = page->index;
+			index = indices[i];
 			if (index >= end)
 				break;
 
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
 			lock_page(page);
 			WARN_ON(page->index != index);
 			wait_on_page_writeback(page);
 			truncate_inode_page(mapping, page);
 			unlock_page(page);
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		index++;
@@ -360,6 +415,53 @@ void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
 EXPORT_SYMBOL(truncate_inode_pages);
 
 /**
+ * truncate_inode_pages_final - truncate *all* pages before inode dies
+ * @mapping: mapping to truncate
+ *
+ * Called under (and serialized by) inode->i_mutex.
+ *
+ * Filesystems have to use this in the .evict_inode path to inform the
+ * VM that this is the final truncate and the inode is going away.
+ */
+void truncate_inode_pages_final(struct address_space *mapping)
+{
+	unsigned long nrshadows;
+	unsigned long nrpages;
+
+	/*
+	 * Page reclaim can not participate in regular inode lifetime
+	 * management (can't call iput()) and thus can race with the
+	 * inode teardown.  Tell it when the address space is exiting,
+	 * so that it does not install eviction information after the
+	 * final truncate has begun.
+	 */
+	mapping_set_exiting(mapping);
+
+	/*
+	 * When reclaim installs eviction entries, it increases
+	 * nrshadows first, then decreases nrpages.  Make sure we see
+	 * this in the right order or we might miss an entry.
+	 */
+	nrpages = mapping->nrpages;
+	smp_rmb();
+	nrshadows = mapping->nrshadows;
+
+	if (nrpages || nrshadows) {
+		/*
+		 * As truncation uses a lockless tree lookup, cycle
+		 * the tree lock to make sure any ongoing tree
+		 * modification that does not see AS_EXITING is
+		 * completed before starting the final truncate.
+		 */
+		spin_lock_irq(&mapping->tree_lock);
+		spin_unlock_irq(&mapping->tree_lock);
+
+		truncate_inode_pages(mapping, 0);
+	}
+}
+EXPORT_SYMBOL(truncate_inode_pages_final);
+
+/**
  * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
  * @mapping: the address_space which holds the pages to invalidate
  * @start: the offset 'from' which to invalidate
@@ -375,6 +477,7 @@ EXPORT_SYMBOL(truncate_inode_pages);
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
 		pgoff_t start, pgoff_t end)
 {
+	pgoff_t indices[PAGEVEC_SIZE];
 	struct pagevec pvec;
 	pgoff_t index = start;
 	unsigned long ret;
@@ -390,17 +493,23 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 	 */
 
 	pagevec_init(&pvec, 0);
-	while (index <= end && pagevec_lookup(&pvec, mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
+	while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+			indices)) {
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
 			/* We rely upon deletion not changing page->index */
-			index = page->index;
+			index = indices[i];
 			if (index > end)
 				break;
 
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
 			if (!trylock_page(page))
 				continue;
 			WARN_ON(page->index != index);
@@ -414,6 +523,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 				deactivate_page(page);
 			count += ret;
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
@@ -444,7 +554,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 		goto failed;
 
 	BUG_ON(page_has_private(page));
-	__delete_from_page_cache(page);
+	__delete_from_page_cache(page, NULL);
 	spin_unlock_irq(&mapping->tree_lock);
 	mem_cgroup_uncharge_cache_page(page);
 
@@ -481,6 +591,7 @@ static int do_launder_page(struct address_space *mapping, struct page *page)
 int invalidate_inode_pages2_range(struct address_space *mapping,
 				  pgoff_t start, pgoff_t end)
 {
+	pgoff_t indices[PAGEVEC_SIZE];
 	struct pagevec pvec;
 	pgoff_t index;
 	int i;
@@ -491,17 +602,23 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 	cleancache_invalidate_inode(mapping);
 	pagevec_init(&pvec, 0);
 	index = start;
-	while (index <= end && pagevec_lookup(&pvec, mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
+	while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+			indices)) {
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
 			/* We rely upon deletion not changing page->index */
-			index = page->index;
+			index = indices[i];
 			if (index > end)
 				break;
 
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
 			lock_page(page);
 			WARN_ON(page->index != index);
 			if (page->mapping != mapping) {
@@ -539,6 +656,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 				ret = ret2;
 			unlock_page(page);
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
diff --git a/mm/util.c b/mm/util.c
index 812271040b07..efadeaaef81e 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -1,7 +1,9 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/compiler.h>
 #include <linux/export.h>
+#include <linux/ctype.h>
 #include <linux/err.h>
 #include <linux/sched.h>
 #include <linux/security.h>
@@ -63,6 +65,35 @@ char *kstrndup(const char *s, size_t max, gfp_t gfp)
 EXPORT_SYMBOL(kstrndup);
 
 /**
+ * kstrimdup - Trim and copy a %NUL terminated string.
+ * @s: the string to trim and duplicate
+ * @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ *
+ * Returns an address, which the caller must kfree, containing
+ * a duplicate of the passed string with leading and/or trailing
+ * whitespace (as defined by isspace) removed.
+ */
+char *kstrimdup(const char *s, gfp_t gfp)
+{
+	char *buf;
+	char *begin = skip_spaces(s);
+	size_t len = strlen(begin);
+
+	while (len && isspace(begin[len - 1]))
+		len--;
+
+	buf = kmalloc_track_caller(len + 1, gfp);
+	if (!buf)
+		return NULL;
+
+	memcpy(buf, begin, len);
+	buf[len] = '\0';
+
+	return buf;
+}
+EXPORT_SYMBOL(kstrimdup);
+
+/**
  * kmemdup - duplicate region of memory
  *
  * @src: memory region to duplicate
@@ -307,7 +338,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
  * If the architecture not support this function, simply return with no
  * page pinned
  */
-int __attribute__((weak)) __get_user_pages_fast(unsigned long start,
+int __weak __get_user_pages_fast(unsigned long start,
 				 int nr_pages, int write, struct page **pages)
 {
 	return 0;
@@ -338,7 +369,7 @@ EXPORT_SYMBOL_GPL(__get_user_pages_fast);
  * callers need to carefully consider what to use. On many architectures,
  * get_user_pages_fast simply falls back to get_user_pages.
  */
-int __attribute__((weak)) get_user_pages_fast(unsigned long start,
+int __weak get_user_pages_fast(unsigned long start,
 				int nr_pages, int write, struct page **pages)
 {
 	struct mm_struct *mm = current->mm;
diff --git a/mm/vmacache.c b/mm/vmacache.c
new file mode 100644
index 000000000000..d4224b397c0e
--- /dev/null
+++ b/mm/vmacache.c
@@ -0,0 +1,112 @@
+/*
+ * Copyright (C) 2014 Davidlohr Bueso.
+ */
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/vmacache.h>
+
+/*
+ * Flush vma caches for threads that share a given mm.
+ *
+ * The operation is safe because the caller holds the mmap_sem
+ * exclusively and other threads accessing the vma cache will
+ * have mmap_sem held at least for read, so no extra locking
+ * is required to maintain the vma cache.
+ */
+void vmacache_flush_all(struct mm_struct *mm)
+{
+	struct task_struct *g, *p;
+
+	rcu_read_lock();
+	for_each_process_thread(g, p) {
+		/*
+		 * Only flush the vmacache pointers as the
+		 * mm seqnum is already set and curr's will
+		 * be set upon invalidation when the next
+		 * lookup is done.
+		 */
+		if (mm == p->mm)
+			vmacache_flush(p);
+	}
+	rcu_read_unlock();
+}
+
+/*
+ * This task may be accessing a foreign mm via (for example)
+ * get_user_pages()->find_vma().  The vmacache is task-local and this
+ * task's vmacache pertains to a different mm (ie, its own).  There is
+ * nothing we can do here.
+ *
+ * Also handle the case where a kernel thread has adopted this mm via use_mm().
+ * That kernel thread's vmacache is not applicable to this mm.
+ */
+static bool vmacache_valid_mm(struct mm_struct *mm)
+{
+	return current->mm == mm && !(current->flags & PF_KTHREAD);
+}
+
+void vmacache_update(unsigned long addr, struct vm_area_struct *newvma)
+{
+	if (vmacache_valid_mm(newvma->vm_mm))
+		current->vmacache[VMACACHE_HASH(addr)] = newvma;
+}
+
+static bool vmacache_valid(struct mm_struct *mm)
+{
+	struct task_struct *curr;
+
+	if (!vmacache_valid_mm(mm))
+		return false;
+
+	curr = current;
+	if (mm->vmacache_seqnum != curr->vmacache_seqnum) {
+		/*
+		 * First attempt will always be invalid, initialize
+		 * the new cache for this task here.
+		 */
+		curr->vmacache_seqnum = mm->vmacache_seqnum;
+		vmacache_flush(curr);
+		return false;
+	}
+	return true;
+}
+
+struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr)
+{
+	int i;
+
+	if (!vmacache_valid(mm))
+		return NULL;
+
+	for (i = 0; i < VMACACHE_SIZE; i++) {
+		struct vm_area_struct *vma = current->vmacache[i];
+
+		if (vma && vma->vm_start <= addr && vma->vm_end > addr) {
+			BUG_ON(vma->vm_mm != mm);
+			return vma;
+		}
+	}
+
+	return NULL;
+}
+
+#ifndef CONFIG_MMU
+struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm,
+					   unsigned long start,
+					   unsigned long end)
+{
+	int i;
+
+	if (!vmacache_valid(mm))
+		return NULL;
+
+	for (i = 0; i < VMACACHE_SIZE; i++) {
+		struct vm_area_struct *vma = current->vmacache[i];
+
+		if (vma && vma->vm_start == start && vma->vm_end == end)
+			return vma;
+	}
+
+	return NULL;
+}
+#endif
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 0fdf96803c5b..bf233b283319 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -27,7 +27,9 @@
 #include <linux/pfn.h>
 #include <linux/kmemleak.h>
 #include <linux/atomic.h>
+#include <linux/compiler.h>
 #include <linux/llist.h>
+
 #include <asm/uaccess.h>
 #include <asm/tlbflush.h>
 #include <asm/shmparam.h>
@@ -1083,6 +1085,12 @@ EXPORT_SYMBOL(vm_unmap_ram);
  * @node: prefer to allocate data structures on this node
  * @prot: memory protection to use. PAGE_KERNEL for regular RAM
  *
+ * If you use this function for less than VMAP_MAX_ALLOC pages, it could be
+ * faster than vmap so it's good.  But if you mix long-life and short-life
+ * objects with vm_map_ram(), it could consume lots of address space through
+ * fragmentation (especially on a 32bit machine).  You could see failures in
+ * the end.  Please use this function for short-lived objects.
+ *
  * Returns: a pointer to the address that has been mapped, or %NULL on failure
  */
 void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot)
@@ -2181,7 +2189,7 @@ EXPORT_SYMBOL(remap_vmalloc_range);
  * Implement a stub for vmalloc_sync_all() if the architecture chose not to
  * have one.
  */
-void  __attribute__((weak)) vmalloc_sync_all(void)
+void __weak vmalloc_sync_all(void)
 {
 }
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a9c74b409681..06879ead7380 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -224,15 +224,15 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 	unsigned long freed = 0;
 	unsigned long long delta;
 	long total_scan;
-	long max_pass;
+	long freeable;
 	long nr;
 	long new_nr;
 	int nid = shrinkctl->nid;
 	long batch_size = shrinker->batch ? shrinker->batch
 					  : SHRINK_BATCH;
 
-	max_pass = shrinker->count_objects(shrinker, shrinkctl);
-	if (max_pass == 0)
+	freeable = shrinker->count_objects(shrinker, shrinkctl);
+	if (freeable == 0)
 		return 0;
 
 	/*
@@ -244,14 +244,14 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 
 	total_scan = nr;
 	delta = (4 * nr_pages_scanned) / shrinker->seeks;
-	delta *= max_pass;
+	delta *= freeable;
 	do_div(delta, lru_pages + 1);
 	total_scan += delta;
 	if (total_scan < 0) {
 		printk(KERN_ERR
 		"shrink_slab: %pF negative objects to delete nr=%ld\n",
 		       shrinker->scan_objects, total_scan);
-		total_scan = max_pass;
+		total_scan = freeable;
 	}
 
 	/*
@@ -260,26 +260,26 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 	 * shrinkers to return -1 all the time. This results in a large
 	 * nr being built up so when a shrink that can do some work
 	 * comes along it empties the entire cache due to nr >>>
-	 * max_pass.  This is bad for sustaining a working set in
+	 * freeable. This is bad for sustaining a working set in
 	 * memory.
 	 *
 	 * Hence only allow the shrinker to scan the entire cache when
 	 * a large delta change is calculated directly.
 	 */
-	if (delta < max_pass / 4)
-		total_scan = min(total_scan, max_pass / 2);
+	if (delta < freeable / 4)
+		total_scan = min(total_scan, freeable / 2);
 
 	/*
 	 * Avoid risking looping forever due to too large nr value:
 	 * never try to free more than twice the estimate number of
 	 * freeable entries.
 	 */
-	if (total_scan > max_pass * 2)
-		total_scan = max_pass * 2;
+	if (total_scan > freeable * 2)
+		total_scan = freeable * 2;
 
 	trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
 				nr_pages_scanned, lru_pages,
-				max_pass, delta, total_scan);
+				freeable, delta, total_scan);
 
 	/*
 	 * Normally, we should not scan less than batch_size objects in one
@@ -292,12 +292,12 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 	 *
 	 * We detect the "tight on memory" situations by looking at the total
 	 * number of objects we want to scan (total_scan). If it is greater
-	 * than the total number of objects on slab (max_pass), we must be
+	 * than the total number of objects on slab (freeable), we must be
 	 * scanning at high prio and therefore should try to reclaim as much as
 	 * possible.
 	 */
 	while (total_scan >= batch_size ||
-	       total_scan >= max_pass) {
+	       total_scan >= freeable) {
 		unsigned long ret;
 		unsigned long nr_to_scan = min(batch_size, total_scan);
 
@@ -523,7 +523,8 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
  * Same as remove_mapping, but if the page is removed from the mapping, it
  * gets returned with a refcount of 0.
  */
-static int __remove_mapping(struct address_space *mapping, struct page *page)
+static int __remove_mapping(struct address_space *mapping, struct page *page,
+			    bool reclaimed)
 {
 	BUG_ON(!PageLocked(page));
 	BUG_ON(mapping != page_mapping(page));
@@ -569,10 +570,23 @@ static int __remove_mapping(struct address_space *mapping, struct page *page)
 		swapcache_free(swap, page);
 	} else {
 		void (*freepage)(struct page *);
+		void *shadow = NULL;
 
 		freepage = mapping->a_ops->freepage;
-
-		__delete_from_page_cache(page);
+		/*
+		 * Remember a shadow entry for reclaimed file cache in
+		 * order to detect refaults, thus thrashing, later on.
+		 *
+		 * But don't store shadows in an address space that is
+		 * already exiting.  This is not just an optizimation,
+		 * inode reclaim needs to empty out the radix tree or
+		 * the nodes are lost.  Don't plant shadows behind its
+		 * back.
+		 */
+		if (reclaimed && page_is_file_cache(page) &&
+		    !mapping_exiting(mapping))
+			shadow = workingset_eviction(mapping, page);
+		__delete_from_page_cache(page, shadow);
 		spin_unlock_irq(&mapping->tree_lock);
 		mem_cgroup_uncharge_cache_page(page);
 
@@ -595,7 +609,7 @@ cannot_free:
  */
 int remove_mapping(struct address_space *mapping, struct page *page)
 {
-	if (__remove_mapping(mapping, page)) {
+	if (__remove_mapping(mapping, page, false)) {
 		/*
 		 * Unfreezing the refcount with 1 rather than 2 effectively
 		 * drops the pagecache ref for us without requiring another
@@ -1065,7 +1079,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			}
 		}
 
-		if (!mapping || !__remove_mapping(mapping, page))
+		if (!mapping || !__remove_mapping(mapping, page, true))
 			goto keep_locked;
 
 		/*
@@ -2297,16 +2311,26 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 	struct zone *zone;
 	unsigned long nr_soft_reclaimed;
 	unsigned long nr_soft_scanned;
+	unsigned long lru_pages = 0;
 	bool aborted_reclaim = false;
+	struct reclaim_state *reclaim_state = current->reclaim_state;
+	gfp_t orig_mask;
+	struct shrink_control shrink = {
+		.gfp_mask = sc->gfp_mask,
+	};
+	enum zone_type requested_highidx = gfp_zone(sc->gfp_mask);
 
 	/*
 	 * If the number of buffer_heads in the machine exceeds the maximum
 	 * allowed level, force direct reclaim to scan the highmem zone as
 	 * highmem pages could be pinning lowmem pages storing buffer_heads
 	 */
+	orig_mask = sc->gfp_mask;
 	if (buffer_heads_over_limit)
 		sc->gfp_mask |= __GFP_HIGHMEM;
 
+	nodes_clear(shrink.nodes_to_scan);
+
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 					gfp_zone(sc->gfp_mask), sc->nodemask) {
 		if (!populated_zone(zone))
@@ -2318,6 +2342,10 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 		if (global_reclaim(sc)) {
 			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 				continue;
+
+			lru_pages += zone_reclaimable_pages(zone);
+			node_set(zone_to_nid(zone), shrink.nodes_to_scan);
+
 			if (sc->priority != DEF_PRIORITY &&
 			    !zone_reclaimable(zone))
 				continue;	/* Let kswapd poll it */
@@ -2331,7 +2359,8 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 				 * noticeable problem, like transparent huge
 				 * page allocations.
 				 */
-				if (compaction_ready(zone, sc)) {
+				if ((zonelist_zone_idx(z) <= requested_highidx)
+				    && compaction_ready(zone, sc)) {
 					aborted_reclaim = true;
 					continue;
 				}
@@ -2354,6 +2383,26 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 		shrink_zone(zone, sc);
 	}
 
+	/*
+	 * Don't shrink slabs when reclaiming memory from over limit cgroups
+	 * but do shrink slab at least once when aborting reclaim for
+	 * compaction to avoid unevenly scanning file/anon LRU pages over slab
+	 * pages.
+	 */
+	if (global_reclaim(sc)) {
+		shrink_slab(&shrink, sc->nr_scanned, lru_pages);
+		if (reclaim_state) {
+			sc->nr_reclaimed += reclaim_state->reclaimed_slab;
+			reclaim_state->reclaimed_slab = 0;
+		}
+	}
+
+	/*
+	 * Restore to original mask to avoid the impact on the caller if we
+	 * promoted it to __GFP_HIGHMEM.
+	 */
+	sc->gfp_mask = orig_mask;
+
 	return aborted_reclaim;
 }
 
@@ -2394,13 +2443,9 @@ static bool all_unreclaimable(struct zonelist *zonelist,
  * 		else, the number of pages reclaimed
  */
 static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
-					struct scan_control *sc,
-					struct shrink_control *shrink)
+					  struct scan_control *sc)
 {
 	unsigned long total_scanned = 0;
-	struct reclaim_state *reclaim_state = current->reclaim_state;
-	struct zoneref *z;
-	struct zone *zone;
 	unsigned long writeback_threshold;
 	bool aborted_reclaim;
 
@@ -2415,32 +2460,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		sc->nr_scanned = 0;
 		aborted_reclaim = shrink_zones(zonelist, sc);
 
-		/*
-		 * Don't shrink slabs when reclaiming memory from over limit
-		 * cgroups but do shrink slab at least once when aborting
-		 * reclaim for compaction to avoid unevenly scanning file/anon
-		 * LRU pages over slab pages.
-		 */
-		if (global_reclaim(sc)) {
-			unsigned long lru_pages = 0;
-
-			nodes_clear(shrink->nodes_to_scan);
-			for_each_zone_zonelist(zone, z, zonelist,
-					gfp_zone(sc->gfp_mask)) {
-				if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
-					continue;
-
-				lru_pages += zone_reclaimable_pages(zone);
-				node_set(zone_to_nid(zone),
-					 shrink->nodes_to_scan);
-			}
-
-			shrink_slab(shrink, sc->nr_scanned, lru_pages);
-			if (reclaim_state) {
-				sc->nr_reclaimed += reclaim_state->reclaimed_slab;
-				reclaim_state->reclaimed_slab = 0;
-			}
-		}
 		total_scanned += sc->nr_scanned;
 		if (sc->nr_reclaimed >= sc->nr_to_reclaim)
 			goto out;
@@ -2602,9 +2621,6 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 		.target_mem_cgroup = NULL,
 		.nodemask = nodemask,
 	};
-	struct shrink_control shrink = {
-		.gfp_mask = sc.gfp_mask,
-	};
 
 	/*
 	 * Do not enter reclaim if fatal signal was delivered while throttled.
@@ -2618,7 +2634,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 				sc.may_writepage,
 				gfp_mask);
 
-	nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
+	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
 	trace_mm_vmscan_direct_reclaim_end(nr_reclaimed);
 
@@ -2685,9 +2701,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 		.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 				(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
 	};
-	struct shrink_control shrink = {
-		.gfp_mask = sc.gfp_mask,
-	};
 
 	/*
 	 * Unlike direct reclaim via alloc_pages(), memcg's reclaim doesn't
@@ -2702,7 +2715,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 					    sc.may_writepage,
 					    sc.gfp_mask);
 
-	nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
+	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
 	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
 
@@ -3337,9 +3350,6 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 		.order = 0,
 		.priority = DEF_PRIORITY,
 	};
-	struct shrink_control shrink = {
-		.gfp_mask = sc.gfp_mask,
-	};
 	struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
 	struct task_struct *p = current;
 	unsigned long nr_reclaimed;
@@ -3349,7 +3359,7 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
-	nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
+	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
 	p->reclaim_state = NULL;
 	lockdep_clear_current_reclaim_state();
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 58c6f3d09735..302dd076b8bf 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -770,6 +770,9 @@ const char * const vmstat_text[] = {
 	"numa_local",
 	"numa_other",
 #endif
+	"workingset_refault",
+	"workingset_activate",
+	"workingset_nodereclaim",
 	"nr_anon_transparent_hugepages",
 	"nr_free_cma",
 	"nr_dirty_threshold",
@@ -810,6 +813,9 @@ const char * const vmstat_text[] = {
 
 	"pgrotated",
 
+	"drop_pagecache",
+	"drop_slab",
+
 #ifdef CONFIG_NUMA_BALANCING
 	"numa_pte_updates",
 	"numa_huge_pte_updates",
diff --git a/mm/workingset.c b/mm/workingset.c
new file mode 100644
index 000000000000..f7216fa7da27
--- /dev/null
+++ b/mm/workingset.c
@@ -0,0 +1,414 @@
+/*
+ * Workingset detection
+ *
+ * Copyright (C) 2013 Red Hat, Inc., Johannes Weiner
+ */
+
+#include <linux/memcontrol.h>
+#include <linux/writeback.h>
+#include <linux/pagemap.h>
+#include <linux/atomic.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+
+/*
+ *		Double CLOCK lists
+ *
+ * Per zone, two clock lists are maintained for file pages: the
+ * inactive and the active list.  Freshly faulted pages start out at
+ * the head of the inactive list and page reclaim scans pages from the
+ * tail.  Pages that are accessed multiple times on the inactive list
+ * are promoted to the active list, to protect them from reclaim,
+ * whereas active pages are demoted to the inactive list when the
+ * active list grows too big.
+ *
+ *   fault ------------------------+
+ *                                 |
+ *              +--------------+   |            +-------------+
+ *   reclaim <- |   inactive   | <-+-- demotion |    active   | <--+
+ *              +--------------+                +-------------+    |
+ *                     |                                           |
+ *                     +-------------- promotion ------------------+
+ *
+ *
+ *		Access frequency and refault distance
+ *
+ * A workload is thrashing when its pages are frequently used but they
+ * are evicted from the inactive list every time before another access
+ * would have promoted them to the active list.
+ *
+ * In cases where the average access distance between thrashing pages
+ * is bigger than the size of memory there is nothing that can be
+ * done - the thrashing set could never fit into memory under any
+ * circumstance.
+ *
+ * However, the average access distance could be bigger than the
+ * inactive list, yet smaller than the size of memory.  In this case,
+ * the set could fit into memory if it weren't for the currently
+ * active pages - which may be used more, hopefully less frequently:
+ *
+ *      +-memory available to cache-+
+ *      |                           |
+ *      +-inactive------+-active----+
+ *  a b | c d e f g h i | J K L M N |
+ *      +---------------+-----------+
+ *
+ * It is prohibitively expensive to accurately track access frequency
+ * of pages.  But a reasonable approximation can be made to measure
+ * thrashing on the inactive list, after which refaulting pages can be
+ * activated optimistically to compete with the existing active pages.
+ *
+ * Approximating inactive page access frequency - Observations:
+ *
+ * 1. When a page is accessed for the first time, it is added to the
+ *    head of the inactive list, slides every existing inactive page
+ *    towards the tail by one slot, and pushes the current tail page
+ *    out of memory.
+ *
+ * 2. When a page is accessed for the second time, it is promoted to
+ *    the active list, shrinking the inactive list by one slot.  This
+ *    also slides all inactive pages that were faulted into the cache
+ *    more recently than the activated page towards the tail of the
+ *    inactive list.
+ *
+ * Thus:
+ *
+ * 1. The sum of evictions and activations between any two points in
+ *    time indicate the minimum number of inactive pages accessed in
+ *    between.
+ *
+ * 2. Moving one inactive page N page slots towards the tail of the
+ *    list requires at least N inactive page accesses.
+ *
+ * Combining these:
+ *
+ * 1. When a page is finally evicted from memory, the number of
+ *    inactive pages accessed while the page was in cache is at least
+ *    the number of page slots on the inactive list.
+ *
+ * 2. In addition, measuring the sum of evictions and activations (E)
+ *    at the time of a page's eviction, and comparing it to another
+ *    reading (R) at the time the page faults back into memory tells
+ *    the minimum number of accesses while the page was not cached.
+ *    This is called the refault distance.
+ *
+ * Because the first access of the page was the fault and the second
+ * access the refault, we combine the in-cache distance with the
+ * out-of-cache distance to get the complete minimum access distance
+ * of this page:
+ *
+ *      NR_inactive + (R - E)
+ *
+ * And knowing the minimum access distance of a page, we can easily
+ * tell if the page would be able to stay in cache assuming all page
+ * slots in the cache were available:
+ *
+ *   NR_inactive + (R - E) <= NR_inactive + NR_active
+ *
+ * which can be further simplified to
+ *
+ *   (R - E) <= NR_active
+ *
+ * Put into words, the refault distance (out-of-cache) can be seen as
+ * a deficit in inactive list space (in-cache).  If the inactive list
+ * had (R - E) more page slots, the page would not have been evicted
+ * in between accesses, but activated instead.  And on a full system,
+ * the only thing eating into inactive list space is active pages.
+ *
+ *
+ *		Activating refaulting pages
+ *
+ * All that is known about the active list is that the pages have been
+ * accessed more than once in the past.  This means that at any given
+ * time there is actually a good chance that pages on the active list
+ * are no longer in active use.
+ *
+ * So when a refault distance of (R - E) is observed and there are at
+ * least (R - E) active pages, the refaulting page is activated
+ * optimistically in the hope that (R - E) active pages are actually
+ * used less frequently than the refaulting page - or even not used at
+ * all anymore.
+ *
+ * If this is wrong and demotion kicks in, the pages which are truly
+ * used more frequently will be reactivated while the less frequently
+ * used once will be evicted from memory.
+ *
+ * But if this is right, the stale pages will be pushed out of memory
+ * and the used pages get to stay in cache.
+ *
+ *
+ *		Implementation
+ *
+ * For each zone's file LRU lists, a counter for inactive evictions
+ * and activations is maintained (zone->inactive_age).
+ *
+ * On eviction, a snapshot of this counter (along with some bits to
+ * identify the zone) is stored in the now empty page cache radix tree
+ * slot of the evicted page.  This is called a shadow entry.
+ *
+ * On cache misses for which there are shadow entries, an eligible
+ * refault distance will immediately activate the refaulting page.
+ */
+
+static void *pack_shadow(unsigned long eviction, struct zone *zone)
+{
+	eviction = (eviction << NODES_SHIFT) | zone_to_nid(zone);
+	eviction = (eviction << ZONES_SHIFT) | zone_idx(zone);
+	eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT);
+
+	return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY);
+}
+
+static void unpack_shadow(void *shadow,
+			  struct zone **zone,
+			  unsigned long *distance)
+{
+	unsigned long entry = (unsigned long)shadow;
+	unsigned long eviction;
+	unsigned long refault;
+	unsigned long mask;
+	int zid, nid;
+
+	entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT;
+	zid = entry & ((1UL << ZONES_SHIFT) - 1);
+	entry >>= ZONES_SHIFT;
+	nid = entry & ((1UL << NODES_SHIFT) - 1);
+	entry >>= NODES_SHIFT;
+	eviction = entry;
+
+	*zone = NODE_DATA(nid)->node_zones + zid;
+
+	refault = atomic_long_read(&(*zone)->inactive_age);
+	mask = ~0UL >> (NODES_SHIFT + ZONES_SHIFT +
+			RADIX_TREE_EXCEPTIONAL_SHIFT);
+	/*
+	 * The unsigned subtraction here gives an accurate distance
+	 * across inactive_age overflows in most cases.
+	 *
+	 * There is a special case: usually, shadow entries have a
+	 * short lifetime and are either refaulted or reclaimed along
+	 * with the inode before they get too old.  But it is not
+	 * impossible for the inactive_age to lap a shadow entry in
+	 * the field, which can then can result in a false small
+	 * refault distance, leading to a false activation should this
+	 * old entry actually refault again.  However, earlier kernels
+	 * used to deactivate unconditionally with *every* reclaim
+	 * invocation for the longest time, so the occasional
+	 * inappropriate activation leading to pressure on the active
+	 * list is not a problem.
+	 */
+	*distance = (refault - eviction) & mask;
+}
+
+/**
+ * workingset_eviction - note the eviction of a page from memory
+ * @mapping: address space the page was backing
+ * @page: the page being evicted
+ *
+ * Returns a shadow entry to be stored in @mapping->page_tree in place
+ * of the evicted @page so that a later refault can be detected.
+ */
+void *workingset_eviction(struct address_space *mapping, struct page *page)
+{
+	struct zone *zone = page_zone(page);
+	unsigned long eviction;
+
+	eviction = atomic_long_inc_return(&zone->inactive_age);
+	return pack_shadow(eviction, zone);
+}
+
+/**
+ * workingset_refault - evaluate the refault of a previously evicted page
+ * @shadow: shadow entry of the evicted page
+ *
+ * Calculates and evaluates the refault distance of the previously
+ * evicted page in the context of the zone it was allocated in.
+ *
+ * Returns %true if the page should be activated, %false otherwise.
+ */
+bool workingset_refault(void *shadow)
+{
+	unsigned long refault_distance;
+	struct zone *zone;
+
+	unpack_shadow(shadow, &zone, &refault_distance);
+	inc_zone_state(zone, WORKINGSET_REFAULT);
+
+	if (refault_distance <= zone_page_state(zone, NR_ACTIVE_FILE)) {
+		inc_zone_state(zone, WORKINGSET_ACTIVATE);
+		return true;
+	}
+	return false;
+}
+
+/**
+ * workingset_activation - note a page activation
+ * @page: page that is being activated
+ */
+void workingset_activation(struct page *page)
+{
+	atomic_long_inc(&page_zone(page)->inactive_age);
+}
+
+/*
+ * Shadow entries reflect the share of the working set that does not
+ * fit into memory, so their number depends on the access pattern of
+ * the workload.  In most cases, they will refault or get reclaimed
+ * along with the inode, but a (malicious) workload that streams
+ * through files with a total size several times that of available
+ * memory, while preventing the inodes from being reclaimed, can
+ * create excessive amounts of shadow nodes.  To keep a lid on this,
+ * track shadow nodes and reclaim them when they grow way past the
+ * point where they would still be useful.
+ */
+
+struct list_lru workingset_shadow_nodes;
+
+static unsigned long count_shadow_nodes(struct shrinker *shrinker,
+					struct shrink_control *sc)
+{
+	unsigned long shadow_nodes;
+	unsigned long max_nodes;
+	unsigned long pages;
+
+	/* list_lru lock nests inside IRQ-safe mapping->tree_lock */
+	local_irq_disable();
+	shadow_nodes = list_lru_count_node(&workingset_shadow_nodes, sc->nid);
+	local_irq_enable();
+
+	pages = node_present_pages(sc->nid);
+	/*
+	 * Active cache pages are limited to 50% of memory, and shadow
+	 * entries that represent a refault distance bigger than that
+	 * do not have any effect.  Limit the number of shadow nodes
+	 * such that shadow entries do not exceed the number of active
+	 * cache pages, assuming a worst-case node population density
+	 * of 1/8th on average.
+	 *
+	 * On 64-bit with 7 radix_tree_nodes per page and 64 slots
+	 * each, this will reclaim shadow entries when they consume
+	 * ~2% of available memory:
+	 *
+	 * PAGE_SIZE / radix_tree_nodes / node_entries / PAGE_SIZE
+	 */
+	max_nodes = pages >> (1 + RADIX_TREE_MAP_SHIFT - 3);
+
+	if (shadow_nodes <= max_nodes)
+		return 0;
+
+	return shadow_nodes - max_nodes;
+}
+
+static enum lru_status shadow_lru_isolate(struct list_head *item,
+					  spinlock_t *lru_lock,
+					  void *arg)
+{
+	struct address_space *mapping;
+	struct radix_tree_node *node;
+	unsigned int i;
+	int ret;
+
+	/*
+	 * Page cache insertions and deletions synchroneously maintain
+	 * the shadow node LRU under the mapping->tree_lock and the
+	 * lru_lock.  Because the page cache tree is emptied before
+	 * the inode can be destroyed, holding the lru_lock pins any
+	 * address_space that has radix tree nodes on the LRU.
+	 *
+	 * We can then safely transition to the mapping->tree_lock to
+	 * pin only the address_space of the particular node we want
+	 * to reclaim, take the node off-LRU, and drop the lru_lock.
+	 */
+
+	node = container_of(item, struct radix_tree_node, private_list);
+	mapping = node->private_data;
+
+	/* Coming from the list, invert the lock order */
+	if (!spin_trylock(&mapping->tree_lock)) {
+		spin_unlock(lru_lock);
+		ret = LRU_RETRY;
+		goto out;
+	}
+
+	list_del_init(item);
+	spin_unlock(lru_lock);
+
+	/*
+	 * The nodes should only contain one or more shadow entries,
+	 * no pages, so we expect to be able to remove them all and
+	 * delete and free the empty node afterwards.
+	 */
+
+	BUG_ON(!node->count);
+	BUG_ON(node->count & RADIX_TREE_COUNT_MASK);
+
+	for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
+		if (node->slots[i]) {
+			BUG_ON(!radix_tree_exceptional_entry(node->slots[i]));
+			node->slots[i] = NULL;
+			BUG_ON(node->count < (1U << RADIX_TREE_COUNT_SHIFT));
+			node->count -= 1U << RADIX_TREE_COUNT_SHIFT;
+			BUG_ON(!mapping->nrshadows);
+			mapping->nrshadows--;
+		}
+	}
+	BUG_ON(node->count);
+	inc_zone_state(page_zone(virt_to_page(node)), WORKINGSET_NODERECLAIM);
+	if (!__radix_tree_delete_node(&mapping->page_tree, node))
+		BUG();
+
+	spin_unlock(&mapping->tree_lock);
+	ret = LRU_REMOVED_RETRY;
+out:
+	local_irq_enable();
+	cond_resched();
+	local_irq_disable();
+	spin_lock(lru_lock);
+	return ret;
+}
+
+static unsigned long scan_shadow_nodes(struct shrinker *shrinker,
+				       struct shrink_control *sc)
+{
+	unsigned long ret;
+
+	/* list_lru lock nests inside IRQ-safe mapping->tree_lock */
+	local_irq_disable();
+	ret =  list_lru_walk_node(&workingset_shadow_nodes, sc->nid,
+				  shadow_lru_isolate, NULL, &sc->nr_to_scan);
+	local_irq_enable();
+	return ret;
+}
+
+static struct shrinker workingset_shadow_shrinker = {
+	.count_objects = count_shadow_nodes,
+	.scan_objects = scan_shadow_nodes,
+	.seeks = DEFAULT_SEEKS,
+	.flags = SHRINKER_NUMA_AWARE,
+};
+
+/*
+ * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe
+ * mapping->tree_lock.
+ */
+static struct lock_class_key shadow_nodes_key;
+
+static int __init workingset_init(void)
+{
+	int ret;
+
+	ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key);
+	if (ret)
+		goto err;
+	ret = register_shrinker(&workingset_shadow_shrinker);
+	if (ret)
+		goto err_list_lru;
+	return 0;
+err_list_lru:
+	list_lru_destroy(&workingset_shadow_nodes);
+err:
+	return ret;
+}
+module_init(workingset_init);
diff --git a/mm/zswap.c b/mm/zswap.c
index d7337fbf6605..aeaef0fb5624 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -89,6 +89,9 @@ static unsigned int zswap_max_pool_percent = 20;
 module_param_named(max_pool_percent,
 			zswap_max_pool_percent, uint, 0644);
 
+/* zbud_pool is shared by all of zswap backend  */
+static struct zbud_pool *zswap_pool;
+
 /*********************************
 * compression functions
 **********************************/
@@ -160,14 +163,14 @@ static void zswap_comp_exit(void)
  * rbnode - links the entry into red-black tree for the appropriate swap type
  * refcount - the number of outstanding reference to the entry. This is needed
  *            to protect against premature freeing of the entry by code
- *            concurent calls to load, invalidate, and writeback.  The lock
+ *            concurrent calls to load, invalidate, and writeback.  The lock
  *            for the zswap_tree structure that contains the entry must
  *            be held while changing the refcount.  Since the lock must
  *            be held, there is no reason to also make refcount atomic.
  * offset - the swap offset for the entry.  Index into the red-black tree.
- * handle - zsmalloc allocation handle that stores the compressed page data
+ * handle - zbud allocation handle that stores the compressed page data
  * length - the length in bytes of the compressed page data.  Needed during
- *           decompression
+ *          decompression
  */
 struct zswap_entry {
 	struct rb_node rbnode;
@@ -189,7 +192,6 @@ struct zswap_header {
 struct zswap_tree {
 	struct rb_root rbroot;
 	spinlock_t lock;
-	struct zbud_pool *pool;
 };
 
 static struct zswap_tree *zswap_trees[MAX_SWAPFILES];
@@ -202,7 +204,7 @@ static struct kmem_cache *zswap_entry_cache;
 static int zswap_entry_cache_create(void)
 {
 	zswap_entry_cache = KMEM_CACHE(zswap_entry, 0);
-	return (zswap_entry_cache == NULL);
+	return zswap_entry_cache == NULL;
 }
 
 static void zswap_entry_cache_destory(void)
@@ -282,16 +284,15 @@ static void zswap_rb_erase(struct rb_root *root, struct zswap_entry *entry)
 }
 
 /*
- * Carries out the common pattern of freeing and entry's zsmalloc allocation,
+ * Carries out the common pattern of freeing and entry's zbud allocation,
  * freeing the entry itself, and decrementing the number of stored pages.
  */
-static void zswap_free_entry(struct zswap_tree *tree,
-			struct zswap_entry *entry)
+static void zswap_free_entry(struct zswap_entry *entry)
 {
-	zbud_free(tree->pool, entry->handle);
+	zbud_free(zswap_pool, entry->handle);
 	zswap_entry_cache_free(entry);
 	atomic_dec(&zswap_stored_pages);
-	zswap_pool_pages = zbud_get_pool_size(tree->pool);
+	zswap_pool_pages = zbud_get_pool_size(zswap_pool);
 }
 
 /* caller must hold the tree lock */
@@ -311,7 +312,7 @@ static void zswap_entry_put(struct zswap_tree *tree,
 	BUG_ON(refcount < 0);
 	if (refcount == 0) {
 		zswap_rb_erase(&tree->rbroot, entry);
-		zswap_free_entry(tree, entry);
+		zswap_free_entry(entry);
 	}
 }
 
@@ -407,8 +408,8 @@ cleanup:
 **********************************/
 static bool zswap_is_full(void)
 {
-	return (totalram_pages * zswap_max_pool_percent / 100 <
-		zswap_pool_pages);
+	return totalram_pages * zswap_max_pool_percent / 100 <
+		zswap_pool_pages;
 }
 
 /*********************************
@@ -545,7 +546,6 @@ static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle)
 	zbud_unmap(pool, handle);
 	tree = zswap_trees[swp_type(swpentry)];
 	offset = swp_offset(swpentry);
-	BUG_ON(pool != tree->pool);
 
 	/* find and ref zswap entry */
 	spin_lock(&tree->lock);
@@ -573,13 +573,13 @@ static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle)
 	case ZSWAP_SWAPCACHE_NEW: /* page is locked */
 		/* decompress */
 		dlen = PAGE_SIZE;
-		src = (u8 *)zbud_map(tree->pool, entry->handle) +
+		src = (u8 *)zbud_map(zswap_pool, entry->handle) +
 			sizeof(struct zswap_header);
 		dst = kmap_atomic(page);
 		ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src,
 				entry->length, dst, &dlen);
 		kunmap_atomic(dst);
-		zbud_unmap(tree->pool, entry->handle);
+		zbud_unmap(zswap_pool, entry->handle);
 		BUG_ON(ret);
 		BUG_ON(dlen != PAGE_SIZE);
 
@@ -652,7 +652,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 	/* reclaim space if needed */
 	if (zswap_is_full()) {
 		zswap_pool_limit_hit++;
-		if (zbud_reclaim_page(tree->pool, 8)) {
+		if (zbud_reclaim_page(zswap_pool, 8)) {
 			zswap_reject_reclaim_fail++;
 			ret = -ENOMEM;
 			goto reject;
@@ -679,7 +679,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 
 	/* store */
 	len = dlen + sizeof(struct zswap_header);
-	ret = zbud_alloc(tree->pool, len, __GFP_NORETRY | __GFP_NOWARN,
+	ret = zbud_alloc(zswap_pool, len, __GFP_NORETRY | __GFP_NOWARN,
 		&handle);
 	if (ret == -ENOSPC) {
 		zswap_reject_compress_poor++;
@@ -689,11 +689,11 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 		zswap_reject_alloc_fail++;
 		goto freepage;
 	}
-	zhdr = zbud_map(tree->pool, handle);
+	zhdr = zbud_map(zswap_pool, handle);
 	zhdr->swpentry = swp_entry(type, offset);
 	buf = (u8 *)(zhdr + 1);
 	memcpy(buf, dst, dlen);
-	zbud_unmap(tree->pool, handle);
+	zbud_unmap(zswap_pool, handle);
 	put_cpu_var(zswap_dstmem);
 
 	/* populate entry */
@@ -716,7 +716,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 
 	/* update stats */
 	atomic_inc(&zswap_stored_pages);
-	zswap_pool_pages = zbud_get_pool_size(tree->pool);
+	zswap_pool_pages = zbud_get_pool_size(zswap_pool);
 
 	return 0;
 
@@ -752,13 +752,13 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
 
 	/* decompress */
 	dlen = PAGE_SIZE;
-	src = (u8 *)zbud_map(tree->pool, entry->handle) +
+	src = (u8 *)zbud_map(zswap_pool, entry->handle) +
 			sizeof(struct zswap_header);
 	dst = kmap_atomic(page);
 	ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src, entry->length,
 		dst, &dlen);
 	kunmap_atomic(dst);
-	zbud_unmap(tree->pool, entry->handle);
+	zbud_unmap(zswap_pool, entry->handle);
 	BUG_ON(ret);
 
 	spin_lock(&tree->lock);
@@ -804,11 +804,9 @@ static void zswap_frontswap_invalidate_area(unsigned type)
 	/* walk the tree and free everything */
 	spin_lock(&tree->lock);
 	rbtree_postorder_for_each_entry_safe(entry, n, &tree->rbroot, rbnode)
-		zswap_free_entry(tree, entry);
+		zswap_free_entry(entry);
 	tree->rbroot = RB_ROOT;
 	spin_unlock(&tree->lock);
-
-	zbud_destroy_pool(tree->pool);
 	kfree(tree);
 	zswap_trees[type] = NULL;
 }
@@ -822,20 +820,14 @@ static void zswap_frontswap_init(unsigned type)
 	struct zswap_tree *tree;
 
 	tree = kzalloc(sizeof(struct zswap_tree), GFP_KERNEL);
-	if (!tree)
-		goto err;
-	tree->pool = zbud_create_pool(GFP_KERNEL, &zswap_zbud_ops);
-	if (!tree->pool)
-		goto freetree;
+	if (!tree) {
+		pr_err("alloc failed, zswap disabled for swap type %d\n", type);
+		return;
+	}
+
 	tree->rbroot = RB_ROOT;
 	spin_lock_init(&tree->lock);
 	zswap_trees[type] = tree;
-	return;
-
-freetree:
-	kfree(tree);
-err:
-	pr_err("alloc failed, zswap disabled for swap type %d\n", type);
 }
 
 static struct frontswap_ops zswap_frontswap_ops = {
@@ -907,9 +899,16 @@ static int __init init_zswap(void)
 		return 0;
 
 	pr_info("loading zswap\n");
+
+	zswap_pool = zbud_create_pool(GFP_KERNEL, &zswap_zbud_ops);
+	if (!zswap_pool) {
+		pr_err("zbud pool creation failed\n");
+		goto error;
+	}
+
 	if (zswap_entry_cache_create()) {
 		pr_err("entry cache creation failed\n");
-		goto error;
+		goto cachefail;
 	}
 	if (zswap_comp_init()) {
 		pr_err("compressor initialization failed\n");
@@ -919,6 +918,7 @@ static int __init init_zswap(void)
 		pr_err("per-cpu initialization failed\n");
 		goto pcpufail;
 	}
+
 	frontswap_register_ops(&zswap_frontswap_ops);
 	if (zswap_debugfs_init())
 		pr_warn("debugfs initialization failed\n");
@@ -927,6 +927,8 @@ pcpufail:
 	zswap_comp_exit();
 compfail:
 	zswap_entry_cache_destory();
+cachefail:
+	zbud_destroy_pool(zswap_pool);
 error:
 	return -ENOMEM;
 }
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index d4ff41739b0f..31ca3dc4c888 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2587,7 +2587,7 @@ static int rtnl_bridge_notify(struct net_device *dev, u16 flags)
 
 	if ((!flags || (flags & BRIDGE_FLAGS_MASTER)) &&
 	    br_dev && br_dev->netdev_ops->ndo_bridge_getlink) {
-		err = br_dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0);
+		err = br_dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, br_dev, 0);
 		if (err < 0)
 			goto errout;
 	}
diff --git a/samples/seccomp/Makefile b/samples/seccomp/Makefile
index 7203e66dcd6f..1b4e4b8f5e47 100644
--- a/samples/seccomp/Makefile
+++ b/samples/seccomp/Makefile
@@ -18,8 +18,8 @@ HOSTCFLAGS_bpf-direct.o += -idirafter $(objtree)/include
 bpf-direct-objs := bpf-direct.o
 
 # Try to match the kernel target.
-ifndef CONFIG_64BIT
 ifndef CROSS_COMPILE
+ifndef CONFIG_64BIT
 
 # s390 has -m31 flag to build 31 bit binaries
 ifndef CONFIG_S390
@@ -36,7 +36,13 @@ HOSTLOADLIBES_bpf-direct += $(MFLAG)
 HOSTLOADLIBES_bpf-fancy += $(MFLAG)
 HOSTLOADLIBES_dropper += $(MFLAG)
 endif
-endif
-
-# Tell kbuild to always build the programs
 always := $(hostprogs-y)
+else
+# MIPS system calls are defined based on the -mabi that is passed
+# to the toolchain which may or may not be a valid option
+# for the host toolchain. So disable tests if target architecture
+# is MIPS but the host isn't.
+ifndef CONFIG_MIPS
+always := $(hostprogs-y)
+endif
+endif
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 464dcef79b35..889929d10cd8 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -289,19 +289,21 @@ our $Int_type	= qr{(?i)llu|ull|ll|lu|ul|l|u};
 our $Binary	= qr{(?i)0b[01]+$Int_type?};
 our $Hex	= qr{(?i)0x[0-9a-f]+$Int_type?};
 our $Int	= qr{[0-9]+$Int_type?};
+our $Octal	= qr{0[0-7]+$Int_type?};
 our $Float_hex	= qr{(?i)0x[0-9a-f]+p-?[0-9]+[fl]?};
 our $Float_dec	= qr{(?i)(?:[0-9]+\.[0-9]*|[0-9]*\.[0-9]+)(?:e-?[0-9]+)?[fl]?};
 our $Float_int	= qr{(?i)[0-9]+e-?[0-9]+[fl]?};
 our $Float	= qr{$Float_hex|$Float_dec|$Float_int};
-our $Constant	= qr{$Float|$Binary|$Hex|$Int};
+our $Constant	= qr{$Float|$Binary|$Octal|$Hex|$Int};
 our $Assignment	= qr{\*\=|/=|%=|\+=|-=|<<=|>>=|&=|\^=|\|=|=};
-our $Compare    = qr{<=|>=|==|!=|<|>};
+our $Compare    = qr{<=|>=|==|!=|<|(?<!-)>};
 our $Arithmetic = qr{\+|-|\*|\/|%};
 our $Operators	= qr{
 			<=|>=|==|!=|
 			=>|->|<<|>>|<|>|!|~|
 			&&|\|\||,|\^|\+\+|--|&|\||$Arithmetic
 		  }x;
+our $c90_Keywords = qr{do|for|while|if|else|return|goto|continue|switch|default|case|break}x;
 
 our $NonptrType;
 our $NonptrTypeWithAttr;
@@ -378,6 +380,27 @@ our @modifierList = (
 	qr{fastcall},
 );
 
+our @mode_permission_funcs = (
+	["module_param", 3],
+	["module_param_(?:array|named|string)", 4],
+	["module_param_array_named", 5],
+	["debugfs_create_(?:file|u8|u16|u32|u64|x8|x16|x32|x64|size_t|atomic_t|bool|blob|regset32|u32_array)", 2],
+	["proc_create(?:_data|)", 2],
+	["(?:CLASS|DEVICE|SENSOR)_ATTR", 2],
+);
+
+#Create a search pattern for all these functions to speed up a loop below
+our $mode_perms_search = "";
+foreach my $entry (@mode_permission_funcs) {
+	$mode_perms_search .= '|' if ($mode_perms_search ne "");
+	$mode_perms_search .= $entry->[0];
+}
+
+our $declaration_macros = qr{(?x:
+	(?:$Storage\s+)?(?:DECLARE|DEFINE)_[A-Z]+\s*\(|
+	(?:$Storage\s+)?LIST_HEAD\s*\(
+)};
+
 our $allowed_asm_includes = qr{(?x:
 	irq|
 	memory
@@ -423,15 +446,20 @@ our $Typecast	= qr{\s*(\(\s*$NonptrType\s*\)){0,1}\s*};
 # Any use must be runtime checked with $^V
 
 our $balanced_parens = qr/(\((?:[^\(\)]++|(?-1))*\))/;
-our $LvalOrFunc	= qr{($Lval)\s*($balanced_parens{0,1})\s*};
+our $LvalOrFunc	= qr{((?:[\&\*]\s*)?$Lval)\s*($balanced_parens{0,1})\s*};
 our $FuncArg = qr{$Typecast{0,1}($LvalOrFunc|$Constant)};
 
 sub deparenthesize {
 	my ($string) = @_;
 	return "" if (!defined($string));
-	$string =~ s@^\s*\(\s*@@g;
-	$string =~ s@\s*\)\s*$@@g;
+
+	while ($string =~ /^\s*\(.*\)\s*$/) {
+		$string =~ s@^\s*\(\s*@@;
+		$string =~ s@\s*\)\s*$@@;
+	}
+
 	$string =~ s@\s+@ @g;
+
 	return $string;
 }
 
@@ -1421,21 +1449,25 @@ sub possible {
 my $prefix = '';
 
 sub show_type {
-	return defined $use_type{$_[0]} if (scalar keys %use_type > 0);
+	my ($type) = @_;
+
+	return defined $use_type{$type} if (scalar keys %use_type > 0);
 
-	return !defined $ignore_type{$_[0]};
+	return !defined $ignore_type{$type};
 }
 
 sub report {
-	if (!show_type($_[1]) ||
-	    (defined $tst_only && $_[2] !~ /\Q$tst_only\E/)) {
+	my ($level, $type, $msg) = @_;
+
+	if (!show_type($type) ||
+	    (defined $tst_only && $msg !~ /\Q$tst_only\E/)) {
 		return 0;
 	}
 	my $line;
 	if ($show_types) {
-		$line = "$prefix$_[0]:$_[1]: $_[2]\n";
+		$line = "$prefix$level:$type: $msg\n";
 	} else {
-		$line = "$prefix$_[0]: $_[2]\n";
+		$line = "$prefix$level: $msg\n";
 	}
 	$line = (split('\n', $line))[0] . "\n" if ($terse);
 
@@ -1443,12 +1475,15 @@ sub report {
 
 	return 1;
 }
+
 sub report_dump {
 	our @report;
 }
 
 sub ERROR {
-	if (report("ERROR", $_[0], $_[1])) {
+	my ($type, $msg) = @_;
+
+	if (report("ERROR", $type, $msg)) {
 		our $clean = 0;
 		our $cnt_error++;
 		return 1;
@@ -1456,7 +1491,9 @@ sub ERROR {
 	return 0;
 }
 sub WARN {
-	if (report("WARNING", $_[0], $_[1])) {
+	my ($type, $msg) = @_;
+
+	if (report("WARNING", $type, $msg)) {
 		our $clean = 0;
 		our $cnt_warn++;
 		return 1;
@@ -1464,7 +1501,9 @@ sub WARN {
 	return 0;
 }
 sub CHK {
-	if ($check && report("CHECK", $_[0], $_[1])) {
+	my ($type, $msg) = @_;
+
+	if ($check && report("CHECK", $type, $msg)) {
 		our $clean = 0;
 		our $cnt_chk++;
 		return 1;
@@ -2041,13 +2080,17 @@ sub process {
 		}
 
 # check for DT compatible documentation
-		if (defined $root && $realfile =~ /\.dts/ &&
-		    $rawline =~ /^\+\s*compatible\s*=/) {
+		if (defined $root &&
+			(($realfile =~ /\.dtsi?$/ && $line =~ /^\+\s*compatible\s*=\s*\"/) ||
+			 ($realfile =~ /\.[ch]$/ && $line =~ /^\+.*\.compatible\s*=\s*\"/))) {
+
 			my @compats = $rawline =~ /\"([a-zA-Z0-9\-\,\.\+_]+)\"/g;
 
+			my $dt_path = $root . "/Documentation/devicetree/bindings/";
+			my $vp_file = $dt_path . "vendor-prefixes.txt";
+
 			foreach my $compat (@compats) {
 				my $compat2 = $compat;
-				my $dt_path =  $root . "/Documentation/devicetree/bindings/";
 				$compat2 =~ s/\,[a-z]*\-/\,<\.\*>\-/;
 				`grep -Erq "$compat|$compat2" $dt_path`;
 				if ( $? >> 8 ) {
@@ -2055,14 +2098,12 @@ sub process {
 					     "DT compatible string \"$compat\" appears un-documented -- check $dt_path\n" . $herecurr);
 				}
 
-				my $vendor = $compat;
-				my $vendor_path = $dt_path . "vendor-prefixes.txt";
-				next if (! -f $vendor_path);
-				$vendor =~ s/^([a-zA-Z0-9]+)\,.*/$1/;
-				`grep -Eq "$vendor" $vendor_path`;
+				next if $compat !~ /^([a-zA-Z0-9\-]+)\,/;
+				my $vendor = $1;
+				`grep -Eq "^$vendor\\b" $vp_file`;
 				if ( $? >> 8 ) {
 					WARN("UNDOCUMENTED_DT_STRING",
-					     "DT compatible string vendor \"$vendor\" appears un-documented -- check $vendor_path\n" . $herecurr);
+					     "DT compatible string vendor \"$vendor\" appears un-documented -- check $vp_file\n" . $herecurr);
 				}
 			}
 		}
@@ -2198,7 +2239,8 @@ sub process {
 
 		if ($realfile =~ m@^(drivers/net/|net/)@ &&
 		    $prevrawline =~ /^\+[ \t]*\/\*[ \t]*$/ &&
-		    $rawline =~ /^\+[ \t]*\*/) {
+		    $rawline =~ /^\+[ \t]*\*/ &&
+		    $realline > 2) {
 			WARN("NETWORKING_BLOCK_COMMENT_STYLE",
 			     "networking block comments don't use an empty /* line, use /* Comment...\n" . $hereprev);
 		}
@@ -2221,6 +2263,38 @@ sub process {
 			     "networking block comments put the trailing */ on a separate line\n" . $herecurr);
 		}
 
+# check for missing blank lines after declarations
+		if ($sline =~ /^\+\s+\S/ &&			#Not at char 1
+			# actual declarations
+		    ($prevline =~ /^\+\s+$Declare\s+$Ident\s*[=,;\[]/ ||
+			# foo bar; where foo is some local typedef or #define
+		     $prevline =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ ||
+			# known declaration macros
+		     $prevline =~ /^\+\s+$declaration_macros/) &&
+			# for "else if" which can look like "$Ident $Ident"
+		    !($prevline =~ /^\+\s+$c90_Keywords\b/ ||
+			# other possible extensions of declaration lines
+		      $prevline =~ /(?:$Compare|$Assignment|$Operators)\s*$/ ||
+			# not starting a section or a macro "\" extended line
+		      $prevline =~ /(?:\{\s*|\\)$/) &&
+			# looks like a declaration
+		    !($sline =~ /^\+\s+$Declare/ ||
+			# foo bar; where foo is some local typedef or #define
+		      $sline =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ ||
+			# known declaration macros
+		      $sline =~ /^\+\s+$declaration_macros/ ||
+			# start of struct or union or enum
+		      $sline =~ /^\+\s+(?:union|struct|enum|typedef)\b/ ||
+			# start or end of block or continuation of declaration
+		      $sline =~ /^\+\s+(?:$|[\{\}\.\#\"\?\:\(\[])/ ||
+			# bitfield continuation
+		      $sline =~ /^\+\s+$Ident\s*:\s*\d+\s*[,;]/ ||
+			# other possible extensions of declaration lines
+		      $sline =~ /^\+\s+\(?\s*(?:$Compare|$Assignment|$Operators)/)) {
+			WARN("SPACING",
+			     "Missing a blank line after declarations\n" . $hereprev);
+		}
+
 # check for spaces at the beginning of a line.
 # Exceptions:
 #  1) within comments
@@ -2665,6 +2739,13 @@ sub process {
 				$herecurr);
                }
 
+# check for non-global char *foo[] = {"bar", ...} declarations.
+		if ($line =~ /^.\s+(?:static\s+|const\s+)?char\s+\*\s*\w+\s*\[\s*\]\s*=\s*\{/) {
+			WARN("STATIC_CONST_CHAR_ARRAY",
+			     "char * array declaration might be better as static const\n" .
+				$herecurr);
+               }
+
 # check for function declarations without arguments like "int foo()"
 		if ($line =~ /(\b$Type\s+$Ident)\s*\(\s*\)/) {
 			if (ERROR("FUNCTION_WITHOUT_ARGS",
@@ -2799,7 +2880,7 @@ sub process {
 			my $level2 = $level;
 			$level2 = "dbg" if ($level eq "debug");
 			WARN("PREFER_PR_LEVEL",
-			     "Prefer netdev_$level2(netdev, ... then dev_$level2(dev, ... then pr_$level(...  to printk(KERN_$orig ...\n" . $herecurr);
+			     "Prefer [subsystem eg: netdev]_$level2([subsystem]dev, ... then dev_$level2(dev, ... then pr_$level(...  to printk(KERN_$orig ...\n" . $herecurr);
 		}
 
 		if ($line =~ /\bpr_warning\s*\(/) {
@@ -2848,10 +2929,7 @@ sub process {
 # Function pointer declarations
 # check spacing between type, funcptr, and args
 # canonical declaration is "type (*funcptr)(args...)"
-#
-# the $Declare variable will capture all spaces after the type
-# so check it for trailing missing spaces or multiple spaces
-		if ($line =~ /^.\s*($Declare)\((\s*)\*(\s*)$Ident(\s*)\)(\s*)\(/) {
+		if ($line =~ /^.\s*($Declare)\((\s*)\*(\s*)($Ident)(\s*)\)(\s*)\(/) {
 			my $declare = $1;
 			my $pre_pointer_space = $2;
 			my $post_pointer_space = $3;
@@ -2859,16 +2937,30 @@ sub process {
 			my $post_funcname_space = $5;
 			my $pre_args_space = $6;
 
-			if ($declare !~ /\s$/) {
+# the $Declare variable will capture all spaces after the type
+# so check it for a missing trailing missing space but pointer return types
+# don't need a space so don't warn for those.
+			my $post_declare_space = "";
+			if ($declare =~ /(\s+)$/) {
+				$post_declare_space = $1;
+				$declare = rtrim($declare);
+			}
+			if ($declare !~ /\*$/ && $post_declare_space =~ /^$/) {
 				WARN("SPACING",
 				     "missing space after return type\n" . $herecurr);
+				$post_declare_space = " ";
 			}
 
 # unnecessary space "type  (*funcptr)(args...)"
-			elsif ($declare =~ /\s{2,}$/) {
-				WARN("SPACING",
-				     "Multiple spaces after return type\n" . $herecurr);
-			}
+# This test is not currently implemented because these declarations are
+# equivalent to
+#	int  foo(int bar, ...)
+# and this is form shouldn't/doesn't generate a checkpatch warning.
+#
+#			elsif ($declare =~ /\s{2,}$/) {
+#				WARN("SPACING",
+#				     "Multiple spaces after return type\n" . $herecurr);
+#			}
 
 # unnecessary space "type ( *funcptr)(args...)"
 			if (defined $pre_pointer_space &&
@@ -2900,7 +2992,7 @@ sub process {
 
 			if (show_type("SPACING") && $fix) {
 				$fixed[$linenr - 1] =~
-				    s/^(.\s*$Declare)\(\s*\*\s*($Ident)\s*\)\s*\(/rtrim($1) . " " . "\(\*$2\)\("/ex;
+				    s/^(.\s*)$Declare\s*\(\s*\*\s*$Ident\s*\)\s*\(/$1 . $declare . $post_declare_space . '(*' . $funcname . ')('/ex;
 			}
 		}
 
@@ -3334,14 +3426,17 @@ sub process {
 			}
 		}
 
-# Return is not a function.
+# return is not a function
 		if (defined($stat) && $stat =~ /^.\s*return(\s*)\(/s) {
 			my $spacing = $1;
 			if ($^V && $^V ge 5.10.0 &&
-			    $stat =~ /^.\s*return\s*$balanced_parens\s*;\s*$/) {
-				ERROR("RETURN_PARENTHESES",
-				      "return is not a function, parentheses are not required\n" . $herecurr);
-
+			    $stat =~ /^.\s*return\s*($balanced_parens)\s*;\s*$/) {
+				my $value = $1;
+				$value = deparenthesize($value);
+				if ($value =~ m/^\s*$FuncArg\s*(?:\?|$)/) {
+					ERROR("RETURN_PARENTHESES",
+					      "return is not a function, parentheses are not required\n" . $herecurr);
+				}
 			} elsif ($spacing !~ /\s+/) {
 				ERROR("SPACING",
 				      "space required before the open parenthesis '('\n" . $herecurr);
@@ -3910,12 +4005,30 @@ sub process {
 			}
 		}
 
+# don't use __constant_<foo> functions outside of include/uapi/
+		if ($realfile !~ m@^include/uapi/@ &&
+		    $line =~ /(__constant_(?:htons|ntohs|[bl]e(?:16|32|64)_to_cpu|cpu_to_[bl]e(?:16|32|64)))\s*\(/) {
+			my $constant_func = $1;
+			my $func = $constant_func;
+			$func =~ s/^__constant_//;
+			if (WARN("CONSTANT_CONVERSION",
+				 "$constant_func should be $func\n" . $herecurr) &&
+			    $fix) {
+				$fixed[$linenr - 1] =~ s/\b$constant_func\b/$func/g;
+			}
+		}
+
 # prefer usleep_range over udelay
 		if ($line =~ /\budelay\s*\(\s*(\d+)\s*\)/) {
+			my $delay = $1;
 			# ignore udelay's < 10, however
-			if (! ($1 < 10) ) {
+			if (! ($delay < 10) ) {
 				CHK("USLEEP_RANGE",
-				    "usleep_range is preferred over udelay; see Documentation/timers/timers-howto.txt\n" . $line);
+				    "usleep_range is preferred over udelay; see Documentation/timers/timers-howto.txt\n" . $herecurr);
+			}
+			if ($delay > 2000) {
+				WARN("LONG_UDELAY",
+				     "long udelay - prefer mdelay; see arch/arm/include/asm/delay.h\n" . $herecurr);
 			}
 		}
 
@@ -3923,7 +4036,7 @@ sub process {
 		if ($line =~ /\bmsleep\s*\((\d+)\);/) {
 			if ($1 < 20) {
 				WARN("MSLEEP",
-				     "msleep < 20ms can sleep for up to 20ms; see Documentation/timers/timers-howto.txt\n" . $line);
+				     "msleep < 20ms can sleep for up to 20ms; see Documentation/timers/timers-howto.txt\n" . $herecurr);
 			}
 		}
 
@@ -4149,7 +4262,7 @@ sub process {
 # check for naked sscanf
 		if ($^V && $^V ge 5.10.0 &&
 		    defined $stat &&
-		    $stat =~ /\bsscanf\b/ &&
+		    $line =~ /\bsscanf\b/ &&
 		    ($stat !~ /$Ident\s*=\s*sscanf\s*$balanced_parens/ &&
 		     $stat !~ /\bsscanf\s*$balanced_parens\s*(?:$Compare)/ &&
 		     $stat !~ /(?:$Compare)\s*\bsscanf\s*$balanced_parens/)) {
@@ -4457,6 +4570,34 @@ sub process {
 			WARN("EXPORTED_WORLD_WRITABLE",
 			     "Exporting world writable files is usually an error. Consider more restrictive permissions.\n" . $herecurr);
 		}
+
+# Mode permission misuses where it seems decimal should be octal
+# This uses a shortcut match to avoid unnecessary uses of a slow foreach loop
+		if ($^V && $^V ge 5.10.0 &&
+		    $line =~ /$mode_perms_search/) {
+			foreach my $entry (@mode_permission_funcs) {
+				my $func = $entry->[0];
+				my $arg_pos = $entry->[1];
+
+				my $skip_args = "";
+				if ($arg_pos > 1) {
+					$arg_pos--;
+					$skip_args = "(?:\\s*$FuncArg\\s*,\\s*){$arg_pos,$arg_pos}";
+				}
+				my $test = "\\b$func\\s*\\(${skip_args}([\\d]+)\\s*[,\\)]";
+				if ($line =~ /$test/) {
+					my $val = $1;
+					$val = $6 if ($skip_args ne "");
+
+					if ($val !~ /^0$/ &&
+					    (($val =~ /^$Int$/ && $val !~ /^$Octal$/) ||
+					     length($val) ne 4)) {
+						ERROR("NON_OCTAL_PERMISSIONS",
+						      "Use 4 digit octal (0777) not decimal permissions\n" . $herecurr);
+					}
+				}
+			}
+		}
 	}
 
 	# If we have no input at all, then there is nothing to report on
diff --git a/scripts/genksyms/keywords.gperf b/scripts/genksyms/keywords.gperf
index 3e77a943e7b7..a9096d993172 100644
--- a/scripts/genksyms/keywords.gperf
+++ b/scripts/genksyms/keywords.gperf
@@ -23,6 +23,8 @@ __inline, INLINE_KEYW
 __inline__, INLINE_KEYW
 __signed, SIGNED_KEYW
 __signed__, SIGNED_KEYW
+__typeof, TYPEOF_KEYW
+__typeof__, TYPEOF_KEYW
 __volatile, VOLATILE_KEYW
 __volatile__, VOLATILE_KEYW
 # According to rth, c99 defines _Bool, __restrict, __restrict__, restrict.  KAO
@@ -51,9 +53,8 @@ signed, SIGNED_KEYW
 static, STATIC_KEYW
 struct, STRUCT_KEYW
 typedef, TYPEDEF_KEYW
+typeof, TYPEOF_KEYW
 union, UNION_KEYW
 unsigned, UNSIGNED_KEYW
 void, VOID_KEYW
 volatile, VOLATILE_KEYW
-typeof, TYPEOF_KEYW
-__typeof__, TYPEOF_KEYW
diff --git a/scripts/genksyms/keywords.hash.c_shipped b/scripts/genksyms/keywords.hash.c_shipped
index 82062607e8c0..e9452482e198 100644
--- a/scripts/genksyms/keywords.hash.c_shipped
+++ b/scripts/genksyms/keywords.hash.c_shipped
@@ -34,7 +34,7 @@ struct resword;
 static const struct resword *is_reserved_word(register const char *str, register unsigned int len);
 #line 8 "scripts/genksyms/keywords.gperf"
 struct resword { const char *name; int token; };
-/* maximum key range = 64, duplicates = 0 */
+/* maximum key range = 98, duplicates = 0 */
 
 #ifdef __GNUC__
 __inline
@@ -48,32 +48,32 @@ is_reserved_hash (register const char *str, register unsigned int len)
 {
   static const unsigned char asso_values[] =
     {
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67,  0,
-      67, 67, 67, 67, 67, 67, 15, 67, 67, 67,
-       0, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67,  0, 67,  0, 67,  5,
-      25, 20, 15, 30, 67, 15, 67, 67, 10,  0,
-      10, 40, 20, 67, 10,  5,  0, 10, 15, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101,   0,
+      101, 101, 101, 101, 101, 101,  15, 101, 101, 101,
+        0, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101,   0, 101,   0, 101,   5,
+       25,  20,  55,  30, 101,  15, 101, 101,  10,   0,
+       10,  40,  10, 101,  10,   5,   0,  10,  15, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101, 101, 101, 101, 101,
+      101, 101, 101, 101, 101, 101
     };
   return len + asso_values[(unsigned char)str[2]] + asso_values[(unsigned char)str[0]] + asso_values[(unsigned char)str[len - 1]];
 }
@@ -89,17 +89,17 @@ is_reserved_word (register const char *str, register unsigned int len)
 {
   enum
     {
-      TOTAL_KEYWORDS = 45,
+      TOTAL_KEYWORDS = 46,
       MIN_WORD_LENGTH = 3,
       MAX_WORD_LENGTH = 24,
       MIN_HASH_VALUE = 3,
-      MAX_HASH_VALUE = 66
+      MAX_HASH_VALUE = 100
     };
 
   static const struct resword wordlist[] =
     {
       {""}, {""}, {""},
-#line 33 "scripts/genksyms/keywords.gperf"
+#line 35 "scripts/genksyms/keywords.gperf"
       {"asm", ASM_KEYW},
       {""},
 #line 15 "scripts/genksyms/keywords.gperf"
@@ -108,7 +108,7 @@ is_reserved_word (register const char *str, register unsigned int len)
 #line 16 "scripts/genksyms/keywords.gperf"
       {"__asm__", ASM_KEYW},
       {""}, {""},
-#line 59 "scripts/genksyms/keywords.gperf"
+#line 27 "scripts/genksyms/keywords.gperf"
       {"__typeof__", TYPEOF_KEYW},
       {""},
 #line 19 "scripts/genksyms/keywords.gperf"
@@ -119,31 +119,31 @@ is_reserved_word (register const char *str, register unsigned int len)
       {"__const__", CONST_KEYW},
 #line 25 "scripts/genksyms/keywords.gperf"
       {"__signed__", SIGNED_KEYW},
-#line 51 "scripts/genksyms/keywords.gperf"
+#line 53 "scripts/genksyms/keywords.gperf"
       {"static", STATIC_KEYW},
       {""},
-#line 46 "scripts/genksyms/keywords.gperf"
+#line 48 "scripts/genksyms/keywords.gperf"
       {"int", INT_KEYW},
-#line 39 "scripts/genksyms/keywords.gperf"
+#line 41 "scripts/genksyms/keywords.gperf"
       {"char", CHAR_KEYW},
-#line 40 "scripts/genksyms/keywords.gperf"
+#line 42 "scripts/genksyms/keywords.gperf"
       {"const", CONST_KEYW},
-#line 52 "scripts/genksyms/keywords.gperf"
+#line 54 "scripts/genksyms/keywords.gperf"
       {"struct", STRUCT_KEYW},
-#line 31 "scripts/genksyms/keywords.gperf"
+#line 33 "scripts/genksyms/keywords.gperf"
       {"__restrict__", RESTRICT_KEYW},
-#line 32 "scripts/genksyms/keywords.gperf"
+#line 34 "scripts/genksyms/keywords.gperf"
       {"restrict", RESTRICT_KEYW},
 #line 12 "scripts/genksyms/keywords.gperf"
       {"EXPORT_SYMBOL_GPL_FUTURE", EXPORT_SYMBOL_KEYW},
 #line 23 "scripts/genksyms/keywords.gperf"
       {"__inline__", INLINE_KEYW},
       {""},
-#line 27 "scripts/genksyms/keywords.gperf"
+#line 29 "scripts/genksyms/keywords.gperf"
       {"__volatile__", VOLATILE_KEYW},
 #line 10 "scripts/genksyms/keywords.gperf"
       {"EXPORT_SYMBOL", EXPORT_SYMBOL_KEYW},
-#line 30 "scripts/genksyms/keywords.gperf"
+#line 32 "scripts/genksyms/keywords.gperf"
       {"_restrict", RESTRICT_KEYW},
       {""},
 #line 17 "scripts/genksyms/keywords.gperf"
@@ -152,56 +152,65 @@ is_reserved_word (register const char *str, register unsigned int len)
       {"EXPORT_SYMBOL_GPL", EXPORT_SYMBOL_KEYW},
 #line 21 "scripts/genksyms/keywords.gperf"
       {"__extension__", EXTENSION_KEYW},
-#line 42 "scripts/genksyms/keywords.gperf"
+#line 44 "scripts/genksyms/keywords.gperf"
       {"enum", ENUM_KEYW},
 #line 13 "scripts/genksyms/keywords.gperf"
       {"EXPORT_UNUSED_SYMBOL", EXPORT_SYMBOL_KEYW},
-#line 43 "scripts/genksyms/keywords.gperf"
+#line 45 "scripts/genksyms/keywords.gperf"
       {"extern", EXTERN_KEYW},
       {""},
 #line 24 "scripts/genksyms/keywords.gperf"
       {"__signed", SIGNED_KEYW},
 #line 14 "scripts/genksyms/keywords.gperf"
       {"EXPORT_UNUSED_SYMBOL_GPL", EXPORT_SYMBOL_KEYW},
-#line 54 "scripts/genksyms/keywords.gperf"
+#line 57 "scripts/genksyms/keywords.gperf"
       {"union", UNION_KEYW},
-#line 58 "scripts/genksyms/keywords.gperf"
-      {"typeof", TYPEOF_KEYW},
-#line 53 "scripts/genksyms/keywords.gperf"
-      {"typedef", TYPEDEF_KEYW},
+      {""}, {""},
 #line 22 "scripts/genksyms/keywords.gperf"
       {"__inline", INLINE_KEYW},
-#line 38 "scripts/genksyms/keywords.gperf"
+#line 40 "scripts/genksyms/keywords.gperf"
       {"auto", AUTO_KEYW},
-#line 26 "scripts/genksyms/keywords.gperf"
+#line 28 "scripts/genksyms/keywords.gperf"
       {"__volatile", VOLATILE_KEYW},
       {""}, {""},
-#line 55 "scripts/genksyms/keywords.gperf"
+#line 58 "scripts/genksyms/keywords.gperf"
       {"unsigned", UNSIGNED_KEYW},
       {""},
-#line 49 "scripts/genksyms/keywords.gperf"
+#line 51 "scripts/genksyms/keywords.gperf"
       {"short", SHORT_KEYW},
-#line 45 "scripts/genksyms/keywords.gperf"
+#line 47 "scripts/genksyms/keywords.gperf"
       {"inline", INLINE_KEYW},
       {""},
-#line 57 "scripts/genksyms/keywords.gperf"
+#line 60 "scripts/genksyms/keywords.gperf"
       {"volatile", VOLATILE_KEYW},
-#line 47 "scripts/genksyms/keywords.gperf"
+#line 49 "scripts/genksyms/keywords.gperf"
       {"long", LONG_KEYW},
-#line 29 "scripts/genksyms/keywords.gperf"
+#line 31 "scripts/genksyms/keywords.gperf"
       {"_Bool", BOOL_KEYW},
       {""}, {""},
-#line 48 "scripts/genksyms/keywords.gperf"
+#line 50 "scripts/genksyms/keywords.gperf"
       {"register", REGISTER_KEYW},
-#line 56 "scripts/genksyms/keywords.gperf"
+#line 59 "scripts/genksyms/keywords.gperf"
       {"void", VOID_KEYW},
-#line 44 "scripts/genksyms/keywords.gperf"
-      {"float", FLOAT_KEYW},
-#line 41 "scripts/genksyms/keywords.gperf"
+      {""},
+#line 43 "scripts/genksyms/keywords.gperf"
       {"double", DOUBLE_KEYW},
+      {""},
+#line 26 "scripts/genksyms/keywords.gperf"
+      {"__typeof", TYPEOF_KEYW},
+      {""}, {""},
+#line 52 "scripts/genksyms/keywords.gperf"
+      {"signed", SIGNED_KEYW},
       {""}, {""}, {""}, {""},
-#line 50 "scripts/genksyms/keywords.gperf"
-      {"signed", SIGNED_KEYW}
+#line 56 "scripts/genksyms/keywords.gperf"
+      {"typeof", TYPEOF_KEYW},
+#line 55 "scripts/genksyms/keywords.gperf"
+      {"typedef", TYPEDEF_KEYW},
+      {""}, {""}, {""}, {""}, {""}, {""}, {""}, {""}, {""},
+      {""}, {""}, {""}, {""}, {""}, {""}, {""}, {""}, {""},
+      {""}, {""}, {""}, {""}, {""}, {""}, {""}, {""}, {""},
+#line 46 "scripts/genksyms/keywords.gperf"
+      {"float", FLOAT_KEYW}
     };
 
   if (len <= MAX_WORD_LENGTH && len >= MIN_WORD_LENGTH)
diff --git a/scripts/genksyms/lex.l b/scripts/genksyms/lex.l
index f770071719cb..e583565f2011 100644
--- a/scripts/genksyms/lex.l
+++ b/scripts/genksyms/lex.l
@@ -129,8 +129,9 @@ int
 yylex(void)
 {
   static enum {
-    ST_NOTSTARTED, ST_NORMAL, ST_ATTRIBUTE, ST_ASM, ST_BRACKET, ST_BRACE,
-    ST_EXPRESSION, ST_TABLE_1, ST_TABLE_2, ST_TABLE_3, ST_TABLE_4,
+    ST_NOTSTARTED, ST_NORMAL, ST_ATTRIBUTE, ST_ASM, ST_TYPEOF, ST_TYPEOF_1,
+    ST_BRACKET, ST_BRACE, ST_EXPRESSION,
+    ST_TABLE_1, ST_TABLE_2, ST_TABLE_3, ST_TABLE_4,
     ST_TABLE_5, ST_TABLE_6
   } lexstate = ST_NOTSTARTED;
 
@@ -198,6 +199,10 @@ repeat:
 		    lexstate = ST_ASM;
 		    count = 0;
 		    goto repeat;
+		  case TYPEOF_KEYW:
+		    lexstate = ST_TYPEOF;
+		    count = 0;
+		    goto repeat;
 
 		  case STRUCT_KEYW:
 		  case UNION_KEYW:
@@ -284,6 +289,48 @@ repeat:
 	}
       break;
 
+    case ST_TYPEOF:
+      switch (token)
+	{
+	case '(':
+	  if ( ++count == 1 )
+	    lexstate = ST_TYPEOF_1;
+	  else
+	    APP;
+	  goto repeat;
+	case ')':
+	  APP;
+	  if (--count == 0)
+	    {
+	      lexstate = ST_NORMAL;
+	      token = TYPEOF_PHRASE;
+	      break;
+	    }
+	  goto repeat;
+	default:
+	  APP;
+	  goto repeat;
+	}
+      break;
+
+    case ST_TYPEOF_1:
+      if (token == IDENT)
+	{
+	  if (is_reserved_word(yytext, yyleng)
+	      || find_symbol(yytext, SYM_TYPEDEF, 1))
+	    {
+	      yyless(0);
+	      unput('(');
+	      lexstate = ST_NORMAL;
+	      token = TYPEOF_KEYW;
+	      break;
+	    }
+	  _APP("(", 1);
+	}
+	APP;
+	lexstate = ST_TYPEOF;
+	goto repeat;
+
     case ST_BRACKET:
       APP;
       switch (token)
diff --git a/scripts/genksyms/lex.lex.c_shipped b/scripts/genksyms/lex.lex.c_shipped
index 0bf4157e6161..f82740a69b85 100644
--- a/scripts/genksyms/lex.lex.c_shipped
+++ b/scripts/genksyms/lex.lex.c_shipped
@@ -1938,8 +1938,9 @@ int
 yylex(void)
 {
   static enum {
-    ST_NOTSTARTED, ST_NORMAL, ST_ATTRIBUTE, ST_ASM, ST_BRACKET, ST_BRACE,
-    ST_EXPRESSION, ST_TABLE_1, ST_TABLE_2, ST_TABLE_3, ST_TABLE_4,
+    ST_NOTSTARTED, ST_NORMAL, ST_ATTRIBUTE, ST_ASM, ST_TYPEOF, ST_TYPEOF_1,
+    ST_BRACKET, ST_BRACE, ST_EXPRESSION,
+    ST_TABLE_1, ST_TABLE_2, ST_TABLE_3, ST_TABLE_4,
     ST_TABLE_5, ST_TABLE_6
   } lexstate = ST_NOTSTARTED;
 
@@ -2007,6 +2008,10 @@ repeat:
 		    lexstate = ST_ASM;
 		    count = 0;
 		    goto repeat;
+		  case TYPEOF_KEYW:
+		    lexstate = ST_TYPEOF;
+		    count = 0;
+		    goto repeat;
 
 		  case STRUCT_KEYW:
 		  case UNION_KEYW:
@@ -2093,6 +2098,48 @@ repeat:
 	}
       break;
 
+    case ST_TYPEOF:
+      switch (token)
+	{
+	case '(':
+	  if ( ++count == 1 )
+	    lexstate = ST_TYPEOF_1;
+	  else
+	    APP;
+	  goto repeat;
+	case ')':
+	  APP;
+	  if (--count == 0)
+	    {
+	      lexstate = ST_NORMAL;
+	      token = TYPEOF_PHRASE;
+	      break;
+	    }
+	  goto repeat;
+	default:
+	  APP;
+	  goto repeat;
+	}
+      break;
+
+    case ST_TYPEOF_1:
+      if (token == IDENT)
+	{
+	  if (is_reserved_word(yytext, yyleng)
+	      || find_symbol(yytext, SYM_TYPEDEF, 1))
+	    {
+	      yyless(0);
+	      unput('(');
+	      lexstate = ST_NORMAL;
+	      token = TYPEOF_KEYW;
+	      break;
+	    }
+	  _APP("(", 1);
+	}
+	APP;
+	lexstate = ST_TYPEOF;
+	goto repeat;
+
     case ST_BRACKET:
       APP;
       switch (token)
diff --git a/scripts/genksyms/parse.tab.c_shipped b/scripts/genksyms/parse.tab.c_shipped
index ece53c79bb59..c9f0f0ce82ff 100644
--- a/scripts/genksyms/parse.tab.c_shipped
+++ b/scripts/genksyms/parse.tab.c_shipped
@@ -1,8 +1,8 @@
-/* A Bison parser, made by GNU Bison 2.5.  */
+/* A Bison parser, made by GNU Bison 2.5.1.  */
 
 /* Bison implementation for Yacc-like parsers in C
    
-      Copyright (C) 1984, 1989-1990, 2000-2011 Free Software Foundation, Inc.
+      Copyright (C) 1984, 1989-1990, 2000-2012 Free Software Foundation, Inc.
    
    This program is free software: you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
@@ -44,7 +44,7 @@
 #define YYBISON 1
 
 /* Bison version.  */
-#define YYBISON_VERSION "2.5"
+#define YYBISON_VERSION "2.5.1"
 
 /* Skeleton name.  */
 #define YYSKELETON_NAME "yacc.c"
@@ -117,6 +117,14 @@ static void record_compound(struct string_list **keyw,
 
 
 
+# ifndef YY_NULL
+#  if defined __cplusplus && 201103L <= __cplusplus
+#   define YY_NULL nullptr
+#  else
+#   define YY_NULL 0
+#  endif
+# endif
+
 /* Enabling traces.  */
 #ifndef YYDEBUG
 # define YYDEBUG 1
@@ -171,18 +179,19 @@ static void record_compound(struct string_list **keyw,
      EXPORT_SYMBOL_KEYW = 284,
      ASM_PHRASE = 285,
      ATTRIBUTE_PHRASE = 286,
-     BRACE_PHRASE = 287,
-     BRACKET_PHRASE = 288,
-     EXPRESSION_PHRASE = 289,
-     CHAR = 290,
-     DOTS = 291,
-     IDENT = 292,
-     INT = 293,
-     REAL = 294,
-     STRING = 295,
-     TYPE = 296,
-     OTHER = 297,
-     FILENAME = 298
+     TYPEOF_PHRASE = 287,
+     BRACE_PHRASE = 288,
+     BRACKET_PHRASE = 289,
+     EXPRESSION_PHRASE = 290,
+     CHAR = 291,
+     DOTS = 292,
+     IDENT = 293,
+     INT = 294,
+     REAL = 295,
+     STRING = 296,
+     TYPE = 297,
+     OTHER = 298,
+     FILENAME = 299
    };
 #endif
 
@@ -304,6 +313,7 @@ YYID (yyi)
 #    if ! defined _ALLOCA_H && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
      || defined __cplusplus || defined _MSC_VER)
 #     include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
+      /* Use EXIT_SUCCESS as a witness for stdlib.h.  */
 #     ifndef EXIT_SUCCESS
 #      define EXIT_SUCCESS 0
 #     endif
@@ -395,20 +405,20 @@ union yyalloc
 #endif
 
 #if defined YYCOPY_NEEDED && YYCOPY_NEEDED
-/* Copy COUNT objects from FROM to TO.  The source and destination do
+/* Copy COUNT objects from SRC to DST.  The source and destination do
    not overlap.  */
 # ifndef YYCOPY
 #  if defined __GNUC__ && 1 < __GNUC__
-#   define YYCOPY(To, From, Count) \
-      __builtin_memcpy (To, From, (Count) * sizeof (*(From)))
+#   define YYCOPY(Dst, Src, Count) \
+      __builtin_memcpy (Dst, Src, (Count) * sizeof (*(Src)))
 #  else
-#   define YYCOPY(To, From, Count)		\
-      do					\
-	{					\
-	  YYSIZE_T yyi;				\
-	  for (yyi = 0; yyi < (Count); yyi++)	\
-	    (To)[yyi] = (From)[yyi];		\
-	}					\
+#   define YYCOPY(Dst, Src, Count)              \
+      do                                        \
+        {                                       \
+          YYSIZE_T yyi;                         \
+          for (yyi = 0; yyi < (Count); yyi++)   \
+            (Dst)[yyi] = (Src)[yyi];            \
+        }                                       \
       while (YYID (0))
 #  endif
 # endif
@@ -417,20 +427,20 @@ union yyalloc
 /* YYFINAL -- State number of the termination state.  */
 #define YYFINAL  4
 /* YYLAST -- Last index in YYTABLE.  */
-#define YYLAST   532
+#define YYLAST   514
 
 /* YYNTOKENS -- Number of terminals.  */
-#define YYNTOKENS  53
+#define YYNTOKENS  54
 /* YYNNTS -- Number of nonterminals.  */
 #define YYNNTS  49
 /* YYNRULES -- Number of rules.  */
 #define YYNRULES  132
 /* YYNRULES -- Number of states.  */
-#define YYNSTATES  188
+#define YYNSTATES  187
 
 /* YYTRANSLATE(YYLEX) -- Bison symbol number corresponding to YYLEX.  */
 #define YYUNDEFTOK  2
-#define YYMAXUTOK   298
+#define YYMAXUTOK   299
 
 #define YYTRANSLATE(YYX)						\
   ((unsigned int) (YYX) <= YYMAXUTOK ? yytranslate[YYX] : YYUNDEFTOK)
@@ -442,15 +452,15 @@ static const yytype_uint8 yytranslate[] =
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
-      47,    49,    48,     2,    46,     2,     2,     2,     2,     2,
-       2,     2,     2,     2,     2,     2,     2,     2,    52,    44,
-       2,    50,     2,     2,     2,     2,     2,     2,     2,     2,
+      48,    49,    50,     2,    47,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,    53,    45,
+       2,    51,     2,     2,     2,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
-       2,     2,     2,    51,     2,    45,     2,     2,     2,     2,
+       2,     2,     2,    52,     2,    46,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
        2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
@@ -467,7 +477,7 @@ static const yytype_uint8 yytranslate[] =
        5,     6,     7,     8,     9,    10,    11,    12,    13,    14,
       15,    16,    17,    18,    19,    20,    21,    22,    23,    24,
       25,    26,    27,    28,    29,    30,    31,    32,    33,    34,
-      35,    36,    37,    38,    39,    40,    41,    42,    43
+      35,    36,    37,    38,    39,    40,    41,    42,    43,    44
 };
 
 #if YYDEBUG
@@ -478,78 +488,77 @@ static const yytype_uint16 yyprhs[] =
        0,     0,     3,     5,     8,     9,    12,    13,    18,    19,
       23,    25,    27,    29,    31,    34,    37,    41,    42,    44,
       46,    50,    55,    56,    58,    60,    63,    65,    67,    69,
-      71,    73,    75,    77,    79,    81,    87,    92,    95,    98,
-     101,   105,   109,   113,   116,   119,   122,   124,   126,   128,
-     130,   132,   134,   136,   138,   140,   142,   144,   147,   148,
-     150,   152,   155,   157,   159,   161,   163,   166,   168,   170,
-     175,   180,   183,   187,   191,   194,   196,   198,   200,   205,
-     210,   213,   217,   221,   224,   226,   230,   231,   233,   235,
-     239,   242,   245,   247,   248,   250,   252,   257,   262,   265,
-     269,   273,   277,   278,   280,   283,   287,   291,   292,   294,
-     296,   299,   303,   306,   307,   309,   311,   315,   318,   321,
-     323,   326,   327,   330,   334,   339,   341,   345,   347,   351,
-     354,   355,   357
+      71,    73,    75,    77,    79,    81,    86,    88,    91,    94,
+      97,   101,   105,   109,   112,   115,   118,   120,   122,   124,
+     126,   128,   130,   132,   134,   136,   138,   140,   143,   144,
+     146,   148,   151,   153,   155,   157,   159,   162,   164,   166,
+     171,   176,   179,   183,   187,   190,   192,   194,   196,   201,
+     206,   209,   213,   217,   220,   222,   226,   227,   229,   231,
+     235,   238,   241,   243,   244,   246,   248,   253,   258,   261,
+     265,   269,   273,   274,   276,   279,   283,   287,   288,   290,
+     292,   295,   299,   302,   303,   305,   307,   311,   314,   317,
+     319,   322,   323,   326,   330,   335,   337,   341,   343,   347,
+     350,   351,   353
 };
 
 /* YYRHS -- A `-1'-separated list of the rules' RHS.  */
 static const yytype_int8 yyrhs[] =
 {
-      54,     0,    -1,    55,    -1,    54,    55,    -1,    -1,    56,
-      57,    -1,    -1,    12,    23,    58,    60,    -1,    -1,    23,
-      59,    60,    -1,    60,    -1,    84,    -1,    99,    -1,   101,
-      -1,     1,    44,    -1,     1,    45,    -1,    64,    61,    44,
-      -1,    -1,    62,    -1,    63,    -1,    62,    46,    63,    -1,
-      74,   100,    95,    85,    -1,    -1,    65,    -1,    66,    -1,
-      65,    66,    -1,    67,    -1,    68,    -1,     5,    -1,    17,
-      -1,    21,    -1,    11,    -1,    14,    -1,    69,    -1,    73,
-      -1,    28,    47,    65,    48,    49,    -1,    28,    47,    65,
-      49,    -1,    22,    37,    -1,    24,    37,    -1,    10,    37,
-      -1,    22,    37,    87,    -1,    24,    37,    87,    -1,    10,
-      37,    96,    -1,    10,    96,    -1,    22,    87,    -1,    24,
-      87,    -1,     7,    -1,    19,    -1,    15,    -1,    16,    -1,
-      20,    -1,    25,    -1,    13,    -1,     9,    -1,    26,    -1,
-       6,    -1,    41,    -1,    48,    71,    -1,    -1,    72,    -1,
-      73,    -1,    72,    73,    -1,     8,    -1,    27,    -1,    31,
-      -1,    18,    -1,    70,    74,    -1,    75,    -1,    37,    -1,
-      75,    47,    78,    49,    -1,    75,    47,     1,    49,    -1,
-      75,    33,    -1,    47,    74,    49,    -1,    47,     1,    49,
-      -1,    70,    76,    -1,    77,    -1,    37,    -1,    41,    -1,
-      77,    47,    78,    49,    -1,    77,    47,     1,    49,    -1,
-      77,    33,    -1,    47,    76,    49,    -1,    47,     1,    49,
-      -1,    79,    36,    -1,    79,    -1,    80,    46,    36,    -1,
-      -1,    80,    -1,    81,    -1,    80,    46,    81,    -1,    65,
-      82,    -1,    70,    82,    -1,    83,    -1,    -1,    37,    -1,
-      41,    -1,    83,    47,    78,    49,    -1,    83,    47,     1,
-      49,    -1,    83,    33,    -1,    47,    82,    49,    -1,    47,
-       1,    49,    -1,    64,    74,    32,    -1,    -1,    86,    -1,
-      50,    34,    -1,    51,    88,    45,    -1,    51,     1,    45,
-      -1,    -1,    89,    -1,    90,    -1,    89,    90,    -1,    64,
-      91,    44,    -1,     1,    44,    -1,    -1,    92,    -1,    93,
-      -1,    92,    46,    93,    -1,    76,    95,    -1,    37,    94,
-      -1,    94,    -1,    52,    34,    -1,    -1,    95,    31,    -1,
-      51,    97,    45,    -1,    51,    97,    46,    45,    -1,    98,
-      -1,    97,    46,    98,    -1,    37,    -1,    37,    50,    34,
-      -1,    30,    44,    -1,    -1,    30,    -1,    29,    47,    37,
-      49,    44,    -1
+      55,     0,    -1,    56,    -1,    55,    56,    -1,    -1,    57,
+      58,    -1,    -1,    12,    23,    59,    61,    -1,    -1,    23,
+      60,    61,    -1,    61,    -1,    85,    -1,   100,    -1,   102,
+      -1,     1,    45,    -1,     1,    46,    -1,    65,    62,    45,
+      -1,    -1,    63,    -1,    64,    -1,    63,    47,    64,    -1,
+      75,   101,    96,    86,    -1,    -1,    66,    -1,    67,    -1,
+      66,    67,    -1,    68,    -1,    69,    -1,     5,    -1,    17,
+      -1,    21,    -1,    11,    -1,    14,    -1,    70,    -1,    74,
+      -1,    28,    48,    82,    49,    -1,    32,    -1,    22,    38,
+      -1,    24,    38,    -1,    10,    38,    -1,    22,    38,    88,
+      -1,    24,    38,    88,    -1,    10,    38,    97,    -1,    10,
+      97,    -1,    22,    88,    -1,    24,    88,    -1,     7,    -1,
+      19,    -1,    15,    -1,    16,    -1,    20,    -1,    25,    -1,
+      13,    -1,     9,    -1,    26,    -1,     6,    -1,    42,    -1,
+      50,    72,    -1,    -1,    73,    -1,    74,    -1,    73,    74,
+      -1,     8,    -1,    27,    -1,    31,    -1,    18,    -1,    71,
+      75,    -1,    76,    -1,    38,    -1,    76,    48,    79,    49,
+      -1,    76,    48,     1,    49,    -1,    76,    34,    -1,    48,
+      75,    49,    -1,    48,     1,    49,    -1,    71,    77,    -1,
+      78,    -1,    38,    -1,    42,    -1,    78,    48,    79,    49,
+      -1,    78,    48,     1,    49,    -1,    78,    34,    -1,    48,
+      77,    49,    -1,    48,     1,    49,    -1,    80,    37,    -1,
+      80,    -1,    81,    47,    37,    -1,    -1,    81,    -1,    82,
+      -1,    81,    47,    82,    -1,    66,    83,    -1,    71,    83,
+      -1,    84,    -1,    -1,    38,    -1,    42,    -1,    84,    48,
+      79,    49,    -1,    84,    48,     1,    49,    -1,    84,    34,
+      -1,    48,    83,    49,    -1,    48,     1,    49,    -1,    65,
+      75,    33,    -1,    -1,    87,    -1,    51,    35,    -1,    52,
+      89,    46,    -1,    52,     1,    46,    -1,    -1,    90,    -1,
+      91,    -1,    90,    91,    -1,    65,    92,    45,    -1,     1,
+      45,    -1,    -1,    93,    -1,    94,    -1,    93,    47,    94,
+      -1,    77,    96,    -1,    38,    95,    -1,    95,    -1,    53,
+      35,    -1,    -1,    96,    31,    -1,    52,    98,    46,    -1,
+      52,    98,    47,    46,    -1,    99,    -1,    98,    47,    99,
+      -1,    38,    -1,    38,    51,    35,    -1,    30,    45,    -1,
+      -1,    30,    -1,    29,    48,    38,    49,    45,    -1
 };
 
 /* YYRLINE[YYN] -- source line where rule number YYN was defined.  */
 static const yytype_uint16 yyrline[] =
 {
-       0,   123,   123,   124,   128,   128,   134,   134,   136,   136,
-     138,   139,   140,   141,   142,   143,   147,   161,   162,   166,
-     174,   187,   193,   194,   198,   199,   203,   209,   213,   214,
-     215,   216,   217,   221,   222,   223,   224,   228,   230,   232,
-     236,   238,   240,   245,   248,   249,   253,   254,   255,   256,
-     257,   258,   259,   260,   261,   262,   263,   267,   272,   273,
-     277,   278,   282,   282,   282,   283,   291,   292,   296,   305,
-     307,   309,   311,   313,   320,   321,   325,   326,   327,   329,
-     331,   333,   335,   340,   341,   342,   346,   347,   351,   352,
-     357,   362,   364,   368,   369,   377,   381,   383,   385,   387,
-     389,   394,   403,   404,   409,   414,   415,   419,   420,   424,
-     425,   429,   431,   436,   437,   441,   442,   446,   447,   448,
-     452,   456,   457,   461,   462,   466,   467,   470,   475,   483,
-     487,   488,   492
+       0,   124,   124,   125,   129,   129,   135,   135,   137,   137,
+     139,   140,   141,   142,   143,   144,   148,   162,   163,   167,
+     175,   188,   194,   195,   199,   200,   204,   210,   214,   215,
+     216,   217,   218,   222,   223,   224,   225,   229,   231,   233,
+     237,   239,   241,   246,   249,   250,   254,   255,   256,   257,
+     258,   259,   260,   261,   262,   263,   264,   268,   273,   274,
+     278,   279,   283,   283,   283,   284,   292,   293,   297,   306,
+     308,   310,   312,   314,   321,   322,   326,   327,   328,   330,
+     332,   334,   336,   341,   342,   343,   347,   348,   352,   353,
+     358,   363,   365,   369,   370,   378,   382,   384,   386,   388,
+     390,   395,   404,   405,   410,   415,   416,   420,   421,   425,
+     426,   430,   432,   437,   438,   442,   443,   447,   448,   449,
+     453,   457,   458,   462,   463,   467,   468,   471,   476,   484,
+     488,   489,   493
 };
 #endif
 
@@ -565,9 +574,9 @@ static const char *const yytname[] =
   "SHORT_KEYW", "SIGNED_KEYW", "STATIC_KEYW", "STRUCT_KEYW",
   "TYPEDEF_KEYW", "UNION_KEYW", "UNSIGNED_KEYW", "VOID_KEYW",
   "VOLATILE_KEYW", "TYPEOF_KEYW", "EXPORT_SYMBOL_KEYW", "ASM_PHRASE",
-  "ATTRIBUTE_PHRASE", "BRACE_PHRASE", "BRACKET_PHRASE",
+  "ATTRIBUTE_PHRASE", "TYPEOF_PHRASE", "BRACE_PHRASE", "BRACKET_PHRASE",
   "EXPRESSION_PHRASE", "CHAR", "DOTS", "IDENT", "INT", "REAL", "STRING",
-  "TYPE", "OTHER", "FILENAME", "';'", "'}'", "','", "'('", "'*'", "')'",
+  "TYPE", "OTHER", "FILENAME", "';'", "'}'", "','", "'('", "')'", "'*'",
   "'='", "'{'", "':'", "$accept", "declaration_seq", "declaration", "$@1",
   "declaration1", "$@2", "$@3", "simple_declaration",
   "init_declarator_list_opt", "init_declarator_list", "init_declarator",
@@ -584,7 +593,7 @@ static const char *const yytname[] =
   "member_declarator_list_opt", "member_declarator_list",
   "member_declarator", "member_bitfield_declarator", "attribute_opt",
   "enum_body", "enumerator_list", "enumerator", "asm_definition",
-  "asm_phrase_opt", "export_definition", 0
+  "asm_phrase_opt", "export_definition", YY_NULL
 };
 #endif
 
@@ -597,28 +606,28 @@ static const yytype_uint16 yytoknum[] =
      265,   266,   267,   268,   269,   270,   271,   272,   273,   274,
      275,   276,   277,   278,   279,   280,   281,   282,   283,   284,
      285,   286,   287,   288,   289,   290,   291,   292,   293,   294,
-     295,   296,   297,   298,    59,   125,    44,    40,    42,    41,
-      61,   123,    58
+     295,   296,   297,   298,   299,    59,   125,    44,    40,    41,
+      42,    61,   123,    58
 };
 # endif
 
 /* YYR1[YYN] -- Symbol number of symbol that rule YYN derives.  */
 static const yytype_uint8 yyr1[] =
 {
-       0,    53,    54,    54,    56,    55,    58,    57,    59,    57,
-      57,    57,    57,    57,    57,    57,    60,    61,    61,    62,
-      62,    63,    64,    64,    65,    65,    66,    66,    67,    67,
-      67,    67,    67,    68,    68,    68,    68,    68,    68,    68,
-      68,    68,    68,    68,    68,    68,    69,    69,    69,    69,
-      69,    69,    69,    69,    69,    69,    69,    70,    71,    71,
-      72,    72,    73,    73,    73,    73,    74,    74,    75,    75,
-      75,    75,    75,    75,    76,    76,    77,    77,    77,    77,
-      77,    77,    77,    78,    78,    78,    79,    79,    80,    80,
-      81,    82,    82,    83,    83,    83,    83,    83,    83,    83,
-      83,    84,    85,    85,    86,    87,    87,    88,    88,    89,
-      89,    90,    90,    91,    91,    92,    92,    93,    93,    93,
-      94,    95,    95,    96,    96,    97,    97,    98,    98,    99,
-     100,   100,   101
+       0,    54,    55,    55,    57,    56,    59,    58,    60,    58,
+      58,    58,    58,    58,    58,    58,    61,    62,    62,    63,
+      63,    64,    65,    65,    66,    66,    67,    67,    68,    68,
+      68,    68,    68,    69,    69,    69,    69,    69,    69,    69,
+      69,    69,    69,    69,    69,    69,    70,    70,    70,    70,
+      70,    70,    70,    70,    70,    70,    70,    71,    72,    72,
+      73,    73,    74,    74,    74,    74,    75,    75,    76,    76,
+      76,    76,    76,    76,    77,    77,    78,    78,    78,    78,
+      78,    78,    78,    79,    79,    79,    80,    80,    81,    81,
+      82,    83,    83,    84,    84,    84,    84,    84,    84,    84,
+      84,    85,    86,    86,    87,    88,    88,    89,    89,    90,
+      90,    91,    91,    92,    92,    93,    93,    94,    94,    94,
+      95,    96,    96,    97,    97,    98,    98,    99,    99,   100,
+     101,   101,   102
 };
 
 /* YYR2[YYN] -- Number of symbols composing right hand side of rule YYN.  */
@@ -627,7 +636,7 @@ static const yytype_uint8 yyr2[] =
        0,     2,     1,     2,     0,     2,     0,     4,     0,     3,
        1,     1,     1,     1,     2,     2,     3,     0,     1,     1,
        3,     4,     0,     1,     1,     2,     1,     1,     1,     1,
-       1,     1,     1,     1,     1,     5,     4,     2,     2,     2,
+       1,     1,     1,     1,     1,     4,     1,     2,     2,     2,
        3,     3,     3,     2,     2,     2,     1,     1,     1,     1,
        1,     1,     1,     1,     1,     1,     1,     2,     0,     1,
        1,     2,     1,     1,     1,     1,     2,     1,     1,     4,
@@ -648,68 +657,68 @@ static const yytype_uint8 yydefact[] =
        4,     4,     2,     0,     1,     3,     0,    28,    55,    46,
       62,    53,     0,    31,     0,    52,    32,    48,    49,    29,
       65,    47,    50,    30,     0,     8,     0,    51,    54,    63,
-       0,     0,     0,    64,    56,     5,    10,    17,    23,    24,
-      26,    27,    33,    34,    11,    12,    13,    14,    15,    39,
-       0,    43,     6,    37,     0,    44,    22,    38,    45,     0,
-       0,   129,    68,     0,    58,     0,    18,    19,     0,   130,
-      67,    25,    42,   127,     0,   125,    22,    40,     0,   113,
-       0,     0,   109,     9,    17,    41,     0,     0,     0,     0,
-      57,    59,    60,    16,     0,    66,   131,   101,   121,    71,
-       0,     0,   123,     0,     7,   112,   106,    76,    77,     0,
-       0,     0,   121,    75,     0,   114,   115,   119,   105,     0,
-     110,   130,     0,    36,     0,    73,    72,    61,    20,   102,
-       0,    93,     0,    84,    87,    88,   128,   124,   126,   118,
-       0,    76,     0,   120,    74,   117,    80,     0,   111,     0,
-      35,   132,   122,     0,    21,   103,    70,    94,    56,     0,
-      93,    90,    92,    69,    83,     0,    82,    81,     0,     0,
-     116,   104,     0,    95,     0,    91,    98,     0,    85,    89,
-      79,    78,   100,    99,     0,     0,    97,    96
+       0,     0,     0,    64,    36,    56,     5,    10,    17,    23,
+      24,    26,    27,    33,    34,    11,    12,    13,    14,    15,
+      39,     0,    43,     6,    37,     0,    44,    22,    38,    45,
+       0,     0,   129,    68,     0,    58,     0,    18,    19,     0,
+     130,    67,    25,    42,   127,     0,   125,    22,    40,     0,
+     113,     0,     0,   109,     9,    17,    41,    93,     0,     0,
+       0,     0,    57,    59,    60,    16,     0,    66,   131,   101,
+     121,    71,     0,     0,   123,     0,     7,   112,   106,    76,
+      77,     0,     0,     0,   121,    75,     0,   114,   115,   119,
+     105,     0,   110,   130,    94,    56,     0,    93,    90,    92,
+      35,     0,    73,    72,    61,    20,   102,     0,     0,    84,
+      87,    88,   128,   124,   126,   118,     0,    76,     0,   120,
+      74,   117,    80,     0,   111,     0,     0,    95,     0,    91,
+      98,     0,   132,   122,     0,    21,   103,    70,    69,    83,
+       0,    82,    81,     0,     0,   116,   100,    99,     0,     0,
+     104,    85,    89,    79,    78,    97,    96
 };
 
 /* YYDEFGOTO[NTERM-NUM].  */
 static const yytype_int16 yydefgoto[] =
 {
-      -1,     1,     2,     3,    35,    76,    56,    36,    65,    66,
-      67,    79,    38,    39,    40,    41,    42,    68,    90,    91,
-      43,   121,    70,   112,   113,   132,   133,   134,   135,   161,
-     162,    44,   154,   155,    55,    80,    81,    82,   114,   115,
-     116,   117,   129,    51,    74,    75,    45,    98,    46
+      -1,     1,     2,     3,    36,    77,    57,    37,    66,    67,
+      68,    80,    39,    40,    41,    42,    43,    69,    92,    93,
+      44,   123,    71,   114,   115,   138,   139,   140,   141,   128,
+     129,    45,   165,   166,    56,    81,    82,    83,   116,   117,
+     118,   119,   136,    52,    75,    76,    46,   100,    47
 };
 
 /* YYPACT[STATE-NUM] -- Index in YYTABLE of the portion describing
    STATE-NUM.  */
-#define YYPACT_NINF -135
+#define YYPACT_NINF -140
 static const yytype_int16 yypact[] =
 {
-    -135,    20,  -135,   321,  -135,  -135,    30,  -135,  -135,  -135,
-    -135,  -135,   -28,  -135,     2,  -135,  -135,  -135,  -135,  -135,
-    -135,  -135,  -135,  -135,    -6,  -135,     9,  -135,  -135,  -135,
-      -5,    15,   -17,  -135,  -135,  -135,  -135,    18,   491,  -135,
-    -135,  -135,  -135,  -135,  -135,  -135,  -135,  -135,  -135,   -22,
-      31,  -135,  -135,    19,   106,  -135,   491,    19,  -135,   491,
-      50,  -135,  -135,    11,    -3,    51,    57,  -135,    18,   -14,
-      14,  -135,  -135,    48,    46,  -135,   491,  -135,    33,    32,
-      59,   154,  -135,  -135,    18,  -135,   365,    56,    60,    61,
-    -135,    -3,  -135,  -135,    18,  -135,  -135,  -135,  -135,  -135,
-     202,    74,  -135,   -23,  -135,  -135,  -135,    77,  -135,    16,
-     101,    49,  -135,    34,    92,    93,  -135,  -135,  -135,    94,
-    -135,   110,    95,  -135,    97,  -135,  -135,  -135,  -135,   -20,
-      96,   410,    99,   113,   100,  -135,  -135,  -135,  -135,  -135,
-     103,  -135,   107,  -135,  -135,   111,  -135,   239,  -135,    32,
-    -135,  -135,  -135,   123,  -135,  -135,  -135,  -135,  -135,     3,
-      52,  -135,    38,  -135,  -135,   454,  -135,  -135,   117,   128,
-    -135,  -135,   134,  -135,   135,  -135,  -135,   276,  -135,  -135,
-    -135,  -135,  -135,  -135,   137,   138,  -135,  -135
+    -140,    29,  -140,   207,  -140,  -140,    40,  -140,  -140,  -140,
+    -140,  -140,   -27,  -140,    44,  -140,  -140,  -140,  -140,  -140,
+    -140,  -140,  -140,  -140,   -22,  -140,   -18,  -140,  -140,  -140,
+      -9,    22,    28,  -140,  -140,  -140,  -140,  -140,    42,   472,
+    -140,  -140,  -140,  -140,  -140,  -140,  -140,  -140,  -140,  -140,
+      46,    43,  -140,  -140,    47,   107,  -140,   472,    47,  -140,
+     472,    62,  -140,  -140,    16,    -3,    57,    56,  -140,    42,
+      35,   -11,  -140,  -140,    53,    48,  -140,   472,  -140,    51,
+      21,    59,   157,  -140,  -140,    42,  -140,   388,    58,    60,
+      70,    81,  -140,    -3,  -140,  -140,    42,  -140,  -140,  -140,
+    -140,  -140,   253,    71,  -140,   -20,  -140,  -140,  -140,    83,
+    -140,     5,   102,    34,  -140,    12,    95,    94,  -140,  -140,
+    -140,    97,  -140,   113,  -140,  -140,     2,    41,  -140,    27,
+    -140,    99,  -140,  -140,  -140,  -140,   -24,    98,   101,   109,
+     104,  -140,  -140,  -140,  -140,  -140,   105,  -140,   110,  -140,
+    -140,   117,  -140,   298,  -140,    21,   112,  -140,   120,  -140,
+    -140,   343,  -140,  -140,   121,  -140,  -140,  -140,  -140,  -140,
+     434,  -140,  -140,   131,   137,  -140,  -140,  -140,   138,   141,
+    -140,  -140,  -140,  -140,  -140,  -140,  -140
 };
 
 /* YYPGOTO[NTERM-NUM].  */
 static const yytype_int16 yypgoto[] =
 {
-    -135,  -135,   187,  -135,  -135,  -135,  -135,   -50,  -135,  -135,
-      98,     0,   -59,   -37,  -135,  -135,  -135,   -77,  -135,  -135,
-     -54,   -30,  -135,   -90,  -135,  -134,  -135,  -135,    24,   -58,
-    -135,  -135,  -135,  -135,   -18,  -135,  -135,   109,  -135,  -135,
-      44,    87,    84,   148,  -135,   102,  -135,  -135,  -135
+    -140,  -140,   190,  -140,  -140,  -140,  -140,   -45,  -140,  -140,
+      96,     1,   -60,   -31,  -140,  -140,  -140,   -78,  -140,  -140,
+     -55,    -7,  -140,   -92,  -140,  -139,  -140,  -140,   -59,   -39,
+    -140,  -140,  -140,  -140,   -13,  -140,  -140,   111,  -140,  -140,
+      39,    87,    84,   147,  -140,   106,  -140,  -140,  -140
 };
 
 /* YYTABLE[YYPACT[STATE-NUM]].  What to do in state STATE-NUM.  If
@@ -718,149 +727,145 @@ static const yytype_int16 yypgoto[] =
 #define YYTABLE_NINF -109
 static const yytype_int16 yytable[] =
 {
-      86,    71,   111,    37,   172,    10,    83,    69,    58,    49,
-      92,   152,    88,   169,    73,    20,    96,   140,    97,   142,
-       4,   144,   137,    50,    29,    52,   104,    61,    33,    50,
-     153,    53,   111,    89,   111,    77,   -93,   127,    95,    85,
-     157,   131,    59,   185,   173,    54,    57,    99,    62,    71,
-     159,    64,   -93,   141,   160,    62,    84,   108,    63,    64,
-      54,   100,    60,   109,    64,    63,    64,   146,    73,   107,
-      54,   176,   111,   108,    47,    48,    84,   105,   106,   109,
-      64,   147,   160,   160,   110,   177,   141,    87,   131,   157,
-     108,   102,   103,   173,    71,    93,   109,    64,   101,   159,
-      64,   174,   175,    94,   118,   124,   131,    78,   136,   125,
-     126,     7,     8,     9,    10,    11,    12,    13,   131,    15,
-      16,    17,    18,    19,    20,    21,    22,    23,    24,   110,
-      26,    27,    28,    29,    30,   143,   148,    33,   105,   149,
-      96,   151,   152,   -22,   150,   156,   165,    34,   163,   164,
-     -22,  -107,   166,   -22,   -22,   119,   167,   171,   -22,     7,
-       8,     9,    10,    11,    12,    13,   180,    15,    16,    17,
-      18,    19,    20,    21,    22,    23,    24,   181,    26,    27,
-      28,    29,    30,   182,   183,    33,   186,   187,     5,   179,
-     120,   -22,   128,   170,   139,    34,   145,    72,   -22,  -108,
-       0,   -22,   -22,   130,     0,   138,   -22,     7,     8,     9,
-      10,    11,    12,    13,     0,    15,    16,    17,    18,    19,
-      20,    21,    22,    23,    24,     0,    26,    27,    28,    29,
-      30,     0,     0,    33,     0,     0,     0,     0,   -86,     0,
-     168,     0,     0,    34,     7,     8,     9,    10,    11,    12,
-      13,   -86,    15,    16,    17,    18,    19,    20,    21,    22,
-      23,    24,     0,    26,    27,    28,    29,    30,     0,     0,
-      33,     0,     0,     0,     0,   -86,     0,   184,     0,     0,
-      34,     7,     8,     9,    10,    11,    12,    13,   -86,    15,
-      16,    17,    18,    19,    20,    21,    22,    23,    24,     0,
-      26,    27,    28,    29,    30,     0,     0,    33,     0,     0,
-       0,     0,   -86,     0,     0,     0,     0,    34,     0,     0,
-       0,     0,     6,     0,     0,   -86,     7,     8,     9,    10,
-      11,    12,    13,    14,    15,    16,    17,    18,    19,    20,
-      21,    22,    23,    24,    25,    26,    27,    28,    29,    30,
-      31,    32,    33,     0,     0,     0,     0,     0,   -22,     0,
-       0,     0,    34,     0,     0,   -22,     0,     0,   -22,   -22,
-       7,     8,     9,    10,    11,    12,    13,     0,    15,    16,
-      17,    18,    19,    20,    21,    22,    23,    24,     0,    26,
-      27,    28,    29,    30,     0,     0,    33,     0,     0,     0,
-       0,     0,     0,     0,     0,     0,    34,     0,     0,     0,
-       0,     0,     0,   122,   123,     7,     8,     9,    10,    11,
-      12,    13,     0,    15,    16,    17,    18,    19,    20,    21,
-      22,    23,    24,     0,    26,    27,    28,    29,    30,     0,
-       0,    33,     0,     0,     0,     0,     0,   157,     0,     0,
-       0,   158,     0,     0,     0,     0,     0,   159,    64,     7,
+      87,    88,   113,   156,    38,    10,   146,   163,    72,   127,
+      94,    50,    84,    59,   174,    20,    54,    90,    74,   148,
+      58,   150,   179,   101,    29,    51,   143,   164,    33,     4,
+      55,    70,   106,   113,    55,   113,   -93,   102,   134,    60,
+     124,    78,    87,   147,   157,    86,   152,   110,   127,   127,
+     126,   -93,    65,   111,    63,    65,    72,    91,    85,   109,
+     153,   160,    97,   110,    64,    98,    65,    53,    99,   111,
+      61,    65,   147,    62,   112,   161,   110,   113,    85,   124,
+      63,    74,   111,   157,    65,    48,    49,   158,   159,   126,
+      64,    65,    65,    87,   104,   105,   107,   108,    51,    55,
+      89,    87,    95,    96,   103,   120,   142,   130,    79,   131,
+      87,   182,     7,     8,     9,    10,    11,    12,    13,   132,
+      15,    16,    17,    18,    19,    20,    21,    22,    23,    24,
+     133,    26,    27,    28,    29,    30,   112,   149,    33,    34,
+     154,   155,   107,    98,   162,   -22,   169,   167,   163,    35,
+     168,   170,   -22,  -107,   171,   -22,   180,   -22,   121,   172,
+     -22,   176,     7,     8,     9,    10,    11,    12,    13,   177,
+      15,    16,    17,    18,    19,    20,    21,    22,    23,    24,
+     183,    26,    27,    28,    29,    30,   184,   185,    33,    34,
+     186,     5,   135,   122,   175,   -22,   145,    73,   151,    35,
+       0,     0,   -22,  -108,     0,   -22,     0,   -22,     6,     0,
+     -22,   144,     7,     8,     9,    10,    11,    12,    13,    14,
+      15,    16,    17,    18,    19,    20,    21,    22,    23,    24,
+      25,    26,    27,    28,    29,    30,    31,    32,    33,    34,
+       0,     0,     0,     0,     0,   -22,     0,     0,     0,    35,
+       0,     0,   -22,     0,   137,   -22,     0,   -22,     7,     8,
+       9,    10,    11,    12,    13,     0,    15,    16,    17,    18,
+      19,    20,    21,    22,    23,    24,     0,    26,    27,    28,
+      29,    30,     0,     0,    33,    34,     0,     0,     0,     0,
+     -86,     0,     0,     0,     0,    35,     0,     0,     0,   173,
+       0,     0,   -86,     7,     8,     9,    10,    11,    12,    13,
+       0,    15,    16,    17,    18,    19,    20,    21,    22,    23,
+      24,     0,    26,    27,    28,    29,    30,     0,     0,    33,
+      34,     0,     0,     0,     0,   -86,     0,     0,     0,     0,
+      35,     0,     0,     0,   178,     0,     0,   -86,     7,     8,
+       9,    10,    11,    12,    13,     0,    15,    16,    17,    18,
+      19,    20,    21,    22,    23,    24,     0,    26,    27,    28,
+      29,    30,     0,     0,    33,    34,     0,     0,     0,     0,
+     -86,     0,     0,     0,     0,    35,     0,     0,     0,     0,
+       0,     0,   -86,     7,     8,     9,    10,    11,    12,    13,
+       0,    15,    16,    17,    18,    19,    20,    21,    22,    23,
+      24,     0,    26,    27,    28,    29,    30,     0,     0,    33,
+      34,     0,     0,     0,     0,     0,   124,     0,     0,     0,
+     125,     0,     0,     0,     0,     0,   126,     0,    65,     7,
        8,     9,    10,    11,    12,    13,     0,    15,    16,    17,
       18,    19,    20,    21,    22,    23,    24,     0,    26,    27,
-      28,    29,    30,     0,     0,    33,     0,     0,     0,     0,
-     178,     0,     0,     0,     0,    34,     7,     8,     9,    10,
-      11,    12,    13,     0,    15,    16,    17,    18,    19,    20,
-      21,    22,    23,    24,     0,    26,    27,    28,    29,    30,
-       0,     0,    33,     0,     0,     0,     0,     0,     0,     0,
-       0,     0,    34
+      28,    29,    30,     0,     0,    33,    34,     0,     0,     0,
+       0,   181,     0,     0,     0,     0,    35,     7,     8,     9,
+      10,    11,    12,    13,     0,    15,    16,    17,    18,    19,
+      20,    21,    22,    23,    24,     0,    26,    27,    28,    29,
+      30,     0,     0,    33,    34,     0,     0,     0,     0,     0,
+       0,     0,     0,     0,    35
 };
 
 #define yypact_value_is_default(yystate) \
-  ((yystate) == (-135))
+  ((yystate) == (-140))
 
 #define yytable_value_is_error(yytable_value) \
   YYID (0)
 
 static const yytype_int16 yycheck[] =
 {
-      59,    38,    79,     3,     1,     8,    56,    37,    26,    37,
-      64,    31,     1,   147,    37,    18,    30,     1,    32,   109,
-       0,   111,    45,    51,    27,    23,    76,    44,    31,    51,
-      50,    37,   109,    63,   111,    53,    33,    91,    68,    57,
-      37,   100,    47,   177,    41,    51,    37,    33,    37,    86,
-      47,    48,    49,    37,   131,    37,    56,    41,    47,    48,
-      51,    47,    47,    47,    48,    47,    48,    33,    37,    37,
-      51,    33,   149,    41,    44,    45,    76,    44,    45,    47,
-      48,    47,   159,   160,    52,    47,    37,    37,   147,    37,
-      41,    45,    46,    41,   131,    44,    47,    48,    50,    47,
-      48,   159,   160,    46,    45,    49,   165,     1,    34,    49,
-      49,     5,     6,     7,     8,     9,    10,    11,   177,    13,
-      14,    15,    16,    17,    18,    19,    20,    21,    22,    52,
-      24,    25,    26,    27,    28,    34,    44,    31,    44,    46,
-      30,    44,    31,    37,    49,    49,    46,    41,    49,    36,
-      44,    45,    49,    47,    48,     1,    49,    34,    52,     5,
-       6,     7,     8,     9,    10,    11,    49,    13,    14,    15,
-      16,    17,    18,    19,    20,    21,    22,    49,    24,    25,
-      26,    27,    28,    49,    49,    31,    49,    49,     1,   165,
-      81,    37,    94,   149,   107,    41,   112,    49,    44,    45,
-      -1,    47,    48,     1,    -1,   103,    52,     5,     6,     7,
-       8,     9,    10,    11,    -1,    13,    14,    15,    16,    17,
-      18,    19,    20,    21,    22,    -1,    24,    25,    26,    27,
-      28,    -1,    -1,    31,    -1,    -1,    -1,    -1,    36,    -1,
-       1,    -1,    -1,    41,     5,     6,     7,     8,     9,    10,
-      11,    49,    13,    14,    15,    16,    17,    18,    19,    20,
-      21,    22,    -1,    24,    25,    26,    27,    28,    -1,    -1,
-      31,    -1,    -1,    -1,    -1,    36,    -1,     1,    -1,    -1,
-      41,     5,     6,     7,     8,     9,    10,    11,    49,    13,
-      14,    15,    16,    17,    18,    19,    20,    21,    22,    -1,
-      24,    25,    26,    27,    28,    -1,    -1,    31,    -1,    -1,
-      -1,    -1,    36,    -1,    -1,    -1,    -1,    41,    -1,    -1,
-      -1,    -1,     1,    -1,    -1,    49,     5,     6,     7,     8,
-       9,    10,    11,    12,    13,    14,    15,    16,    17,    18,
-      19,    20,    21,    22,    23,    24,    25,    26,    27,    28,
-      29,    30,    31,    -1,    -1,    -1,    -1,    -1,    37,    -1,
-      -1,    -1,    41,    -1,    -1,    44,    -1,    -1,    47,    48,
-       5,     6,     7,     8,     9,    10,    11,    -1,    13,    14,
-      15,    16,    17,    18,    19,    20,    21,    22,    -1,    24,
-      25,    26,    27,    28,    -1,    -1,    31,    -1,    -1,    -1,
-      -1,    -1,    -1,    -1,    -1,    -1,    41,    -1,    -1,    -1,
-      -1,    -1,    -1,    48,    49,     5,     6,     7,     8,     9,
-      10,    11,    -1,    13,    14,    15,    16,    17,    18,    19,
-      20,    21,    22,    -1,    24,    25,    26,    27,    28,    -1,
-      -1,    31,    -1,    -1,    -1,    -1,    -1,    37,    -1,    -1,
-      -1,    41,    -1,    -1,    -1,    -1,    -1,    47,    48,     5,
+      60,    60,    80,     1,     3,     8,     1,    31,    39,    87,
+      65,    38,    57,    26,   153,    18,    38,     1,    38,   111,
+      38,   113,   161,    34,    27,    52,    46,    51,    31,     0,
+      52,    38,    77,   111,    52,   113,    34,    48,    93,    48,
+      38,    54,   102,    38,    42,    58,    34,    42,   126,   127,
+      48,    49,    50,    48,    38,    50,    87,    64,    57,    38,
+      48,    34,    69,    42,    48,    30,    50,    23,    33,    48,
+      48,    50,    38,    45,    53,    48,    42,   155,    77,    38,
+      38,    38,    48,    42,    50,    45,    46,   126,   127,    48,
+      48,    50,    50,   153,    46,    47,    45,    46,    52,    52,
+      38,   161,    45,    47,    51,    46,    35,    49,     1,    49,
+     170,   170,     5,     6,     7,     8,     9,    10,    11,    49,
+      13,    14,    15,    16,    17,    18,    19,    20,    21,    22,
+      49,    24,    25,    26,    27,    28,    53,    35,    31,    32,
+      45,    47,    45,    30,    45,    38,    37,    49,    31,    42,
+      49,    47,    45,    46,    49,    48,    35,    50,     1,    49,
+      53,    49,     5,     6,     7,     8,     9,    10,    11,    49,
+      13,    14,    15,    16,    17,    18,    19,    20,    21,    22,
+      49,    24,    25,    26,    27,    28,    49,    49,    31,    32,
+      49,     1,    96,    82,   155,    38,   109,    50,   114,    42,
+      -1,    -1,    45,    46,    -1,    48,    -1,    50,     1,    -1,
+      53,   105,     5,     6,     7,     8,     9,    10,    11,    12,
+      13,    14,    15,    16,    17,    18,    19,    20,    21,    22,
+      23,    24,    25,    26,    27,    28,    29,    30,    31,    32,
+      -1,    -1,    -1,    -1,    -1,    38,    -1,    -1,    -1,    42,
+      -1,    -1,    45,    -1,     1,    48,    -1,    50,     5,     6,
+       7,     8,     9,    10,    11,    -1,    13,    14,    15,    16,
+      17,    18,    19,    20,    21,    22,    -1,    24,    25,    26,
+      27,    28,    -1,    -1,    31,    32,    -1,    -1,    -1,    -1,
+      37,    -1,    -1,    -1,    -1,    42,    -1,    -1,    -1,     1,
+      -1,    -1,    49,     5,     6,     7,     8,     9,    10,    11,
+      -1,    13,    14,    15,    16,    17,    18,    19,    20,    21,
+      22,    -1,    24,    25,    26,    27,    28,    -1,    -1,    31,
+      32,    -1,    -1,    -1,    -1,    37,    -1,    -1,    -1,    -1,
+      42,    -1,    -1,    -1,     1,    -1,    -1,    49,     5,     6,
+       7,     8,     9,    10,    11,    -1,    13,    14,    15,    16,
+      17,    18,    19,    20,    21,    22,    -1,    24,    25,    26,
+      27,    28,    -1,    -1,    31,    32,    -1,    -1,    -1,    -1,
+      37,    -1,    -1,    -1,    -1,    42,    -1,    -1,    -1,    -1,
+      -1,    -1,    49,     5,     6,     7,     8,     9,    10,    11,
+      -1,    13,    14,    15,    16,    17,    18,    19,    20,    21,
+      22,    -1,    24,    25,    26,    27,    28,    -1,    -1,    31,
+      32,    -1,    -1,    -1,    -1,    -1,    38,    -1,    -1,    -1,
+      42,    -1,    -1,    -1,    -1,    -1,    48,    -1,    50,     5,
        6,     7,     8,     9,    10,    11,    -1,    13,    14,    15,
       16,    17,    18,    19,    20,    21,    22,    -1,    24,    25,
-      26,    27,    28,    -1,    -1,    31,    -1,    -1,    -1,    -1,
-      36,    -1,    -1,    -1,    -1,    41,     5,     6,     7,     8,
-       9,    10,    11,    -1,    13,    14,    15,    16,    17,    18,
-      19,    20,    21,    22,    -1,    24,    25,    26,    27,    28,
-      -1,    -1,    31,    -1,    -1,    -1,    -1,    -1,    -1,    -1,
-      -1,    -1,    41
+      26,    27,    28,    -1,    -1,    31,    32,    -1,    -1,    -1,
+      -1,    37,    -1,    -1,    -1,    -1,    42,     5,     6,     7,
+       8,     9,    10,    11,    -1,    13,    14,    15,    16,    17,
+      18,    19,    20,    21,    22,    -1,    24,    25,    26,    27,
+      28,    -1,    -1,    31,    32,    -1,    -1,    -1,    -1,    -1,
+      -1,    -1,    -1,    -1,    42
 };
 
 /* YYSTOS[STATE-NUM] -- The (internal number of the) accessing
    symbol of state STATE-NUM.  */
 static const yytype_uint8 yystos[] =
 {
-       0,    54,    55,    56,     0,    55,     1,     5,     6,     7,
+       0,    55,    56,    57,     0,    56,     1,     5,     6,     7,
        8,     9,    10,    11,    12,    13,    14,    15,    16,    17,
       18,    19,    20,    21,    22,    23,    24,    25,    26,    27,
-      28,    29,    30,    31,    41,    57,    60,    64,    65,    66,
-      67,    68,    69,    73,    84,    99,   101,    44,    45,    37,
-      51,    96,    23,    37,    51,    87,    59,    37,    87,    47,
-      47,    44,    37,    47,    48,    61,    62,    63,    70,    74,
-      75,    66,    96,    37,    97,    98,    58,    87,     1,    64,
-      88,    89,    90,    60,    64,    87,    65,    37,     1,    74,
-      71,    72,    73,    44,    46,    74,    30,    32,   100,    33,
-      47,    50,    45,    46,    60,    44,    45,    37,    41,    47,
-      52,    70,    76,    77,    91,    92,    93,    94,    45,     1,
-      90,    74,    48,    49,    49,    49,    49,    73,    63,    95,
-       1,    65,    78,    79,    80,    81,    34,    45,    98,    94,
-       1,    37,    76,    34,    76,    95,    33,    47,    44,    46,
-      49,    44,    31,    50,    85,    86,    49,    37,    41,    47,
-      70,    82,    83,    49,    36,    46,    49,    49,     1,    78,
-      93,    34,     1,    41,    82,    82,    33,    47,    36,    81,
-      49,    49,    49,    49,     1,    78,    49,    49
+      28,    29,    30,    31,    32,    42,    58,    61,    65,    66,
+      67,    68,    69,    70,    74,    85,   100,   102,    45,    46,
+      38,    52,    97,    23,    38,    52,    88,    60,    38,    88,
+      48,    48,    45,    38,    48,    50,    62,    63,    64,    71,
+      75,    76,    67,    97,    38,    98,    99,    59,    88,     1,
+      65,    89,    90,    91,    61,    65,    88,    66,    82,    38,
+       1,    75,    72,    73,    74,    45,    47,    75,    30,    33,
+     101,    34,    48,    51,    46,    47,    61,    45,    46,    38,
+      42,    48,    53,    71,    77,    78,    92,    93,    94,    95,
+      46,     1,    91,    75,    38,    42,    48,    71,    83,    84,
+      49,    49,    49,    49,    74,    64,    96,     1,    79,    80,
+      81,    82,    35,    46,    99,    95,     1,    38,    77,    35,
+      77,    96,    34,    48,    45,    47,     1,    42,    83,    83,
+      34,    48,    45,    31,    51,    86,    87,    49,    49,    37,
+      47,    49,    49,     1,    79,    94,    49,    49,     1,    79,
+      35,    37,    82,    49,    49,    49,    49
 };
 
 #define yyerrok		(yyerrstatus = 0)
@@ -890,17 +895,18 @@ static const yytype_uint8 yystos[] =
 
 #define YYRECOVERING()  (!!yyerrstatus)
 
-#define YYBACKUP(Token, Value)					\
-do								\
-  if (yychar == YYEMPTY && yylen == 1)				\
-    {								\
-      yychar = (Token);						\
-      yylval = (Value);						\
-      YYPOPSTACK (1);						\
-      goto yybackup;						\
-    }								\
-  else								\
-    {								\
+#define YYBACKUP(Token, Value)                                  \
+do                                                              \
+  if (yychar == YYEMPTY)                                        \
+    {                                                           \
+      yychar = (Token);                                         \
+      yylval = (Value);                                         \
+      YYPOPSTACK (yylen);                                       \
+      yystate = *yyssp;                                         \
+      goto yybackup;                                            \
+    }                                                           \
+  else                                                          \
+    {                                                           \
       yyerror (YY_("syntax error: cannot back up")); \
       YYERROR;							\
     }								\
@@ -995,6 +1001,8 @@ yy_symbol_value_print (yyoutput, yytype, yyvaluep)
     YYSTYPE const * const yyvaluep;
 #endif
 {
+  FILE *yyo = yyoutput;
+  YYUSE (yyo);
   if (!yyvaluep)
     return;
 # ifdef YYPRINT
@@ -1246,12 +1254,12 @@ static int
 yysyntax_error (YYSIZE_T *yymsg_alloc, char **yymsg,
                 yytype_int16 *yyssp, int yytoken)
 {
-  YYSIZE_T yysize0 = yytnamerr (0, yytname[yytoken]);
+  YYSIZE_T yysize0 = yytnamerr (YY_NULL, yytname[yytoken]);
   YYSIZE_T yysize = yysize0;
   YYSIZE_T yysize1;
   enum { YYERROR_VERBOSE_ARGS_MAXIMUM = 5 };
   /* Internationalized format string. */
-  const char *yyformat = 0;
+  const char *yyformat = YY_NULL;
   /* Arguments of yyformat. */
   char const *yyarg[YYERROR_VERBOSE_ARGS_MAXIMUM];
   /* Number of reported tokens (one for the "unexpected", one per
@@ -1311,7 +1319,7 @@ yysyntax_error (YYSIZE_T *yymsg_alloc, char **yymsg,
                     break;
                   }
                 yyarg[yycount++] = yytname[yyx];
-                yysize1 = yysize + yytnamerr (0, yytname[yyx]);
+                yysize1 = yysize + yytnamerr (YY_NULL, yytname[yyx]);
                 if (! (yysize <= yysize1
                        && yysize1 <= YYSTACK_ALLOC_MAXIMUM))
                   return 2;
@@ -1463,7 +1471,7 @@ yyparse ()
        `yyss': related to states.
        `yyvs': related to semantic values.
 
-       Refer to the stacks thru separate pointers, to allow yyoverflow
+       Refer to the stacks through separate pointers, to allow yyoverflow
        to reallocate them elsewhere.  */
 
     /* The state stack.  */
@@ -2346,7 +2354,7 @@ yyabortlab:
   yyresult = 1;
   goto yyreturn;
 
-#if !defined(yyoverflow) || YYERROR_VERBOSE
+#if !defined yyoverflow || YYERROR_VERBOSE
 /*-------------------------------------------------.
 | yyexhaustedlab -- memory exhaustion comes here.  |
 `-------------------------------------------------*/
diff --git a/scripts/genksyms/parse.tab.h_shipped b/scripts/genksyms/parse.tab.h_shipped
index 93240a3cdecc..a4737dec4532 100644
--- a/scripts/genksyms/parse.tab.h_shipped
+++ b/scripts/genksyms/parse.tab.h_shipped
@@ -1,8 +1,8 @@
-/* A Bison parser, made by GNU Bison 2.5.  */
+/* A Bison parser, made by GNU Bison 2.5.1.  */
 
 /* Bison interface for Yacc-like parsers in C
    
-      Copyright (C) 1984, 1989-1990, 2000-2011 Free Software Foundation, Inc.
+      Copyright (C) 1984, 1989-1990, 2000-2012 Free Software Foundation, Inc.
    
    This program is free software: you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
@@ -66,18 +66,19 @@
      EXPORT_SYMBOL_KEYW = 284,
      ASM_PHRASE = 285,
      ATTRIBUTE_PHRASE = 286,
-     BRACE_PHRASE = 287,
-     BRACKET_PHRASE = 288,
-     EXPRESSION_PHRASE = 289,
-     CHAR = 290,
-     DOTS = 291,
-     IDENT = 292,
-     INT = 293,
-     REAL = 294,
-     STRING = 295,
-     TYPE = 296,
-     OTHER = 297,
-     FILENAME = 298
+     TYPEOF_PHRASE = 287,
+     BRACE_PHRASE = 288,
+     BRACKET_PHRASE = 289,
+     EXPRESSION_PHRASE = 290,
+     CHAR = 291,
+     DOTS = 292,
+     IDENT = 293,
+     INT = 294,
+     REAL = 295,
+     STRING = 296,
+     TYPE = 297,
+     OTHER = 298,
+     FILENAME = 299
    };
 #endif
 
diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y
index 23c39998ad86..b9f4cf202302 100644
--- a/scripts/genksyms/parse.y
+++ b/scripts/genksyms/parse.y
@@ -103,6 +103,7 @@ static void record_compound(struct string_list **keyw,
 
 %token ASM_PHRASE
 %token ATTRIBUTE_PHRASE
+%token TYPEOF_PHRASE
 %token BRACE_PHRASE
 %token BRACKET_PHRASE
 %token EXPRESSION_PHRASE
@@ -220,8 +221,8 @@ storage_class_specifier:
 type_specifier:
 	simple_type_specifier
 	| cvar_qualifier
-	| TYPEOF_KEYW '(' decl_specifier_seq '*' ')'
-	| TYPEOF_KEYW '(' decl_specifier_seq ')'
+	| TYPEOF_KEYW '(' parameter_declaration ')'
+	| TYPEOF_PHRASE
 
 	/* References to s/u/e's defined elsewhere.  Rearrange things
 	   so that it is easier to expand the definition fully later.  */
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 87f723804079..f88d90f20228 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -1178,7 +1178,10 @@ bool conf_set_all_new_symbols(enum conf_def_mode mode)
 				sym->def[S_DEF_USER].tri = mod;
 				break;
 			case def_no:
-				sym->def[S_DEF_USER].tri = no;
+				if (sym->flags & SYMBOL_ALLNOCONFIG_Y)
+					sym->def[S_DEF_USER].tri = yes;
+				else
+					sym->def[S_DEF_USER].tri = no;
 				break;
 			case def_random:
 				sym->def[S_DEF_USER].tri = no;
diff --git a/scripts/kconfig/expr.h b/scripts/kconfig/expr.h
index ba663e1dc7e3..412ea8a2abb8 100644
--- a/scripts/kconfig/expr.h
+++ b/scripts/kconfig/expr.h
@@ -109,6 +109,9 @@ struct symbol {
 /* choice values need to be set before calculating this symbol value */
 #define SYMBOL_NEED_SET_CHOICE_VALUES  0x100000
 
+/* Set symbol to y if allnoconfig; used for symbols that hide others */
+#define SYMBOL_ALLNOCONFIG_Y 0x200000
+
 #define SYMBOL_MAXLENGTH	256
 #define SYMBOL_HASHSIZE		9973
 
diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h
index 09f4edfdc911..d5daa7af8b49 100644
--- a/scripts/kconfig/lkc.h
+++ b/scripts/kconfig/lkc.h
@@ -61,6 +61,7 @@ enum conf_def_mode {
 #define T_OPT_MODULES		1
 #define T_OPT_DEFCONFIG_LIST	2
 #define T_OPT_ENV		3
+#define T_OPT_ALLNOCONFIG_Y	4
 
 struct kconf_id {
 	int name;
diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c
index db1512ae30cc..3ac2c9c6e280 100644
--- a/scripts/kconfig/menu.c
+++ b/scripts/kconfig/menu.c
@@ -217,6 +217,9 @@ void menu_add_option(int token, char *arg)
 	case T_OPT_ENV:
 		prop_add_env(arg);
 		break;
+	case T_OPT_ALLNOCONFIG_Y:
+		current_entry->sym->flags |= SYMBOL_ALLNOCONFIG_Y;
+		break;
 	}
 }
 
diff --git a/scripts/kconfig/zconf.gperf b/scripts/kconfig/zconf.gperf
index f14ab41154b6..b6ac02d604f1 100644
--- a/scripts/kconfig/zconf.gperf
+++ b/scripts/kconfig/zconf.gperf
@@ -44,4 +44,5 @@ on,		T_ON,		TF_PARAM
 modules,	T_OPT_MODULES,	TF_OPTION
 defconfig_list,	T_OPT_DEFCONFIG_LIST,TF_OPTION
 env,		T_OPT_ENV,	TF_OPTION
+allnoconfig_y,	T_OPT_ALLNOCONFIG_Y,TF_OPTION
 %%
diff --git a/scripts/kconfig/zconf.hash.c_shipped b/scripts/kconfig/zconf.hash.c_shipped
index 40df0005daa9..c77a8eff1ef2 100644
--- a/scripts/kconfig/zconf.hash.c_shipped
+++ b/scripts/kconfig/zconf.hash.c_shipped
@@ -55,10 +55,10 @@ kconf_id_hash (register const char *str, register unsigned int len)
       73, 73, 73, 73, 73, 73, 73, 73, 73, 73,
       73, 73, 73, 73, 73, 73, 73, 73, 73, 73,
       73, 73, 73, 73, 73, 73, 73, 73, 73, 73,
-      73, 73, 73, 73, 73, 73, 73, 73, 25, 25,
+      73, 73, 73, 73, 73, 73, 73,  5, 25, 25,
        0,  0,  0,  5,  0,  0, 73, 73,  5,  0,
       10,  5, 45, 73, 20, 20,  0, 15, 15, 73,
-      20, 73, 73, 73, 73, 73, 73, 73, 73, 73,
+      20,  5, 73, 73, 73, 73, 73, 73, 73, 73,
       73, 73, 73, 73, 73, 73, 73, 73, 73, 73,
       73, 73, 73, 73, 73, 73, 73, 73, 73, 73,
       73, 73, 73, 73, 73, 73, 73, 73, 73, 73,
@@ -106,6 +106,7 @@ struct kconf_id_strings_t
     char kconf_id_strings_str23[sizeof("mainmenu")];
     char kconf_id_strings_str25[sizeof("menuconfig")];
     char kconf_id_strings_str27[sizeof("modules")];
+    char kconf_id_strings_str28[sizeof("allnoconfig_y")];
     char kconf_id_strings_str29[sizeof("menu")];
     char kconf_id_strings_str31[sizeof("select")];
     char kconf_id_strings_str32[sizeof("comment")];
@@ -141,6 +142,7 @@ static const struct kconf_id_strings_t kconf_id_strings_contents =
     "mainmenu",
     "menuconfig",
     "modules",
+    "allnoconfig_y",
     "menu",
     "select",
     "comment",
@@ -170,7 +172,7 @@ kconf_id_lookup (register const char *str, register unsigned int len)
 {
   enum
     {
-      TOTAL_KEYWORDS = 32,
+      TOTAL_KEYWORDS = 33,
       MIN_WORD_LENGTH = 2,
       MAX_WORD_LENGTH = 14,
       MIN_HASH_VALUE = 2,
@@ -219,7 +221,8 @@ kconf_id_lookup (register const char *str, register unsigned int len)
       {-1},
 #line 44 "scripts/kconfig/zconf.gperf"
       {(int)(long)&((struct kconf_id_strings_t *)0)->kconf_id_strings_str27,	T_OPT_MODULES,	TF_OPTION},
-      {-1},
+#line 47 "scripts/kconfig/zconf.gperf"
+      {(int)(long)&((struct kconf_id_strings_t *)0)->kconf_id_strings_str28,	T_OPT_ALLNOCONFIG_Y,TF_OPTION},
 #line 16 "scripts/kconfig/zconf.gperf"
       {(int)(long)&((struct kconf_id_strings_t *)0)->kconf_id_strings_str29,		T_MENU,		TF_COMMAND},
       {-1},
@@ -282,5 +285,5 @@ kconf_id_lookup (register const char *str, register unsigned int len)
     }
   return 0;
 }
-#line 47 "scripts/kconfig/zconf.gperf"
+#line 48 "scripts/kconfig/zconf.gperf"
 
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index f9be24d9efac..05654f5e48d5 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -19,7 +19,8 @@
  * Authors: Wu Fengguang <fengguang.wu@intel.com>
  */
 
-#define _LARGEFILE64_SOURCE
+#define _FILE_OFFSET_BITS 64
+#define _GNU_SOURCE
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
@@ -29,11 +30,14 @@
 #include <getopt.h>
 #include <limits.h>
 #include <assert.h>
+#include <ftw.h>
+#include <time.h>
 #include <sys/types.h>
 #include <sys/errno.h>
 #include <sys/fcntl.h>
 #include <sys/mount.h>
 #include <sys/statfs.h>
+#include <sys/mman.h>
 #include "../../include/uapi/linux/magic.h"
 #include "../../include/uapi/linux/kernel-page-flags.h"
 #include <api/fs/debugfs.h>
@@ -158,6 +162,7 @@ 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 */
+const char *		opt_file;
 
 #define MAX_ADDR_RANGES	1024
 static int		nr_addr_ranges;
@@ -253,12 +258,7 @@ static unsigned long do_u64_read(int fd, char *name,
 	if (index > ULONG_MAX / 8)
 		fatal("index overflow: %lu\n", index);
 
-	if (lseek(fd, index * 8, SEEK_SET) < 0) {
-		perror(name);
-		exit(EXIT_FAILURE);
-	}
-
-	bytes = read(fd, buf, count * 8);
+	bytes = pread(fd, buf, count * 8, (off_t)index * 8);
 	if (bytes < 0) {
 		perror(name);
 		exit(EXIT_FAILURE);
@@ -343,8 +343,8 @@ static char *page_flag_longname(uint64_t flags)
  * page list and summary
  */
 
-static void show_page_range(unsigned long voffset,
-			    unsigned long offset, uint64_t flags)
+static void show_page_range(unsigned long voffset, unsigned long offset,
+			    unsigned long size, uint64_t flags)
 {
 	static uint64_t      flags0;
 	static unsigned long voff;
@@ -352,14 +352,16 @@ static void show_page_range(unsigned long voffset,
 	static unsigned long count;
 
 	if (flags == flags0 && offset == index + count &&
-	    (!opt_pid || voffset == voff + count)) {
-		count++;
+	    size && voffset == voff + count) {
+		count += size;
 		return;
 	}
 
 	if (count) {
 		if (opt_pid)
 			printf("%lx\t", voff);
+		if (opt_file)
+			printf("%lu\t", voff);
 		printf("%lx\t%lx\t%s\n",
 				index, count, page_flag_name(flags0));
 	}
@@ -367,7 +369,12 @@ static void show_page_range(unsigned long voffset,
 	flags0 = flags;
 	index  = offset;
 	voff   = voffset;
-	count  = 1;
+	count  = size;
+}
+
+static void flush_page_range(void)
+{
+	show_page_range(0, 0, 0, 0);
 }
 
 static void show_page(unsigned long voffset,
@@ -375,6 +382,8 @@ static void show_page(unsigned long voffset,
 {
 	if (opt_pid)
 		printf("%lx\t", voffset);
+	if (opt_file)
+		printf("%lu\t", voffset);
 	printf("%lx\t%s\n", offset, page_flag_name(flags));
 }
 
@@ -565,7 +574,7 @@ static void add_page(unsigned long voffset,
 		unpoison_page(offset);
 
 	if (opt_list == 1)
-		show_page_range(voffset, offset, flags);
+		show_page_range(voffset, offset, 1, flags);
 	else if (opt_list == 2)
 		show_page(voffset, offset, flags);
 
@@ -667,7 +676,7 @@ static void walk_addr_ranges(void)
 
 	for (i = 0; i < nr_addr_ranges; i++)
 		if (!opt_pid)
-			walk_pfn(0, opt_offset[i], opt_size[i], 0);
+			walk_pfn(opt_offset[i], opt_offset[i], opt_size[i], 0);
 		else
 			walk_task(opt_offset[i], opt_size[i]);
 
@@ -699,9 +708,7 @@ static void usage(void)
 "            -a|--addr    addr-spec     Walk a range of pages\n"
 "            -b|--bits    bits-spec     Walk pages with specified bits\n"
 "            -p|--pid     pid           Walk process address space\n"
-#if 0 /* planned features */
 "            -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 summary info\n"
@@ -799,8 +806,130 @@ static void parse_pid(const char *str)
 	fclose(file);
 }
 
+static void show_file(const char *name, const struct stat *st)
+{
+	unsigned long long size = st->st_size;
+	char atime[64], mtime[64];
+	long now = time(NULL);
+
+	printf("%s\tInode: %u\tSize: %llu (%llu pages)\n",
+			name, (unsigned)st->st_ino,
+			size, (size + page_size - 1) / page_size);
+
+	strftime(atime, sizeof(atime), "%c", localtime(&st->st_atime));
+	strftime(mtime, sizeof(mtime), "%c", localtime(&st->st_mtime));
+
+	printf("Modify: %s (%ld seconds ago)\nAccess: %s (%ld seconds ago)\n",
+			mtime, now - st->st_mtime,
+			atime, now - st->st_atime);
+}
+
+static void walk_file(const char *name, const struct stat *st)
+{
+	uint8_t vec[PAGEMAP_BATCH];
+	uint64_t buf[PAGEMAP_BATCH], flags;
+	unsigned long nr_pages, pfn, i;
+	int fd;
+	off_t off;
+	ssize_t len;
+	void *ptr;
+	int first = 1;
+
+	fd = checked_open(name, O_RDONLY|O_NOATIME|O_NOFOLLOW);
+
+	for (off = 0; off < st->st_size; off += len) {
+		nr_pages = (st->st_size - off + page_size - 1) / page_size;
+		if (nr_pages > PAGEMAP_BATCH)
+			nr_pages = PAGEMAP_BATCH;
+		len = nr_pages * page_size;
+
+		ptr = mmap(NULL, len, PROT_READ, MAP_SHARED, fd, off);
+		if (ptr == MAP_FAILED)
+			fatal("mmap failed: %s", name);
+
+		/* determine cached pages */
+		if (mincore(ptr, len, vec))
+			fatal("mincore failed: %s", name);
+
+		/* turn off readahead */
+		if (madvise(ptr, len, MADV_RANDOM))
+			fatal("madvice failed: %s", name);
+
+		/* populate ptes */
+		for (i = 0; i < nr_pages ; i++) {
+			if (vec[i] & 1)
+				(void)*(volatile int *)(ptr + i * page_size);
+		}
+
+		/* turn off harvesting reference bits */
+		if (madvise(ptr, len, MADV_SEQUENTIAL))
+			fatal("madvice failed: %s", name);
+
+		if (pagemap_read(buf, (unsigned long)ptr / page_size,
+					nr_pages) != nr_pages)
+			fatal("cannot read pagemap");
+
+		munmap(ptr, len);
+
+		for (i = 0; i < nr_pages; i++) {
+			pfn = pagemap_pfn(buf[i]);
+			if (!pfn)
+				continue;
+			if (!kpageflags_read(&flags, pfn, 1))
+				continue;
+			if (first && opt_list) {
+				first = 0;
+				flush_page_range();
+				show_file(name, st);
+			}
+			add_page(off / page_size + i, pfn, flags, buf[i]);
+		}
+	}
+
+	close(fd);
+}
+
+int walk_tree(const char *name, const struct stat *st, int type, struct FTW *f)
+{
+	(void)f;
+	switch (type) {
+	case FTW_F:
+		if (S_ISREG(st->st_mode))
+			walk_file(name, st);
+		break;
+	case FTW_DNR:
+		fprintf(stderr, "cannot read dir: %s\n", name);
+		break;
+	}
+	return 0;
+}
+
+static void walk_page_cache(void)
+{
+	struct stat st;
+
+	kpageflags_fd = checked_open(PROC_KPAGEFLAGS, O_RDONLY);
+	pagemap_fd = checked_open("/proc/self/pagemap", O_RDONLY);
+
+	if (stat(opt_file, &st))
+		fatal("stat failed: %s\n", opt_file);
+
+	if (S_ISREG(st.st_mode)) {
+		walk_file(opt_file, &st);
+	} else if (S_ISDIR(st.st_mode)) {
+		/* do not follow symlinks and mountpoints */
+		if (nftw(opt_file, walk_tree, 64, FTW_MOUNT | FTW_PHYS) < 0)
+			fatal("nftw failed: %s\n", opt_file);
+	} else
+		fatal("unhandled file type: %s\n", opt_file);
+
+	close(kpageflags_fd);
+	close(pagemap_fd);
+}
+
 static void parse_file(const char *name)
 {
+	opt_file = name;
 }
 
 static void parse_addr_range(const char *optarg)
@@ -991,15 +1120,20 @@ int main(int argc, char *argv[])
 
 	if (opt_list && opt_pid)
 		printf("voffset\t");
+	if (opt_list && opt_file)
+		printf("foffset\t");
 	if (opt_list == 1)
 		printf("offset\tlen\tflags\n");
 	if (opt_list == 2)
 		printf("offset\tflags\n");
 
-	walk_addr_ranges();
+	if (opt_file)
+		walk_page_cache();
+	else
+		walk_addr_ranges();
 
 	if (opt_list == 1)
-		show_page_range(0, 0, 0);  /* drain the buffer */
+		flush_page_range();
 
 	if (opt_no_summary)
 		return 0;