Merge branch 'akpm-current/current'

Conflicts:
	arch/arm64/Kconfig
	drivers/rapidio/devices/tsi721_dma.c
	include/linux/glob.h
	kernel/acct.c
	kernel/kexec.c
	mm/huge_memory.c
	mm/memcontrol.c
	mm/memory.c
	mm/oom_kill.c
	net/batman-adv/fragmentation.c

266 files changed, 5956 insertions, 3190 deletions

diff --git a/Documentation/ABI/testing/sysfs-fs-nilfs2 b/Documentation/ABI/testing/sysfs-fs-nilfs2
new file mode 100644
index 000000000000..304ba84a973a
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-fs-nilfs2
@@ -0,0 +1,269 @@
+
+What:		/sys/fs/nilfs2/features/revision
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show current revision of NILFS file system driver.
+		This value informs about file system revision that
+		driver is ready to support.
+
+What:		/sys/fs/nilfs2/features/README
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Describe attributes of /sys/fs/nilfs2/features group.
+
+What:		/sys/fs/nilfs2/<device>/revision
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show NILFS file system revision on volume.
+		This value informs about metadata structures'
+		revision on mounted volume.
+
+What:		/sys/fs/nilfs2/<device>/blocksize
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show volume's block size in bytes.
+
+What:		/sys/fs/nilfs2/<device>/device_size
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show volume size in bytes.
+
+What:		/sys/fs/nilfs2/<device>/free_blocks
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show count of free blocks on volume.
+
+What:		/sys/fs/nilfs2/<device>/uuid
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show volume's UUID (Universally Unique Identifier).
+
+What:		/sys/fs/nilfs2/<device>/volume_name
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show volume's label.
+
+What:		/sys/fs/nilfs2/<device>/README
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Describe attributes of /sys/fs/nilfs2/<device> group.
+
+What:		/sys/fs/nilfs2/<device>/superblock/sb_write_time
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show last write time of super block in human-readable
+		format.
+
+What:		/sys/fs/nilfs2/<device>/superblock/sb_write_time_secs
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show last write time of super block in seconds.
+
+What:		/sys/fs/nilfs2/<device>/superblock/sb_write_count
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show current write count of super block.
+
+What:		/sys/fs/nilfs2/<device>/superblock/sb_update_frequency
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show/Set interval of periodical update of superblock
+		(in seconds).
+
+What:		/sys/fs/nilfs2/<device>/superblock/README
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Describe attributes of /sys/fs/nilfs2/<device>/superblock
+		group.
+
+What:		/sys/fs/nilfs2/<device>/segctor/last_pseg_block
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show start block number of the latest segment.
+
+What:		/sys/fs/nilfs2/<device>/segctor/last_seg_sequence
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show sequence value of the latest segment.
+
+What:		/sys/fs/nilfs2/<device>/segctor/last_seg_checkpoint
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show checkpoint number of the latest segment.
+
+What:		/sys/fs/nilfs2/<device>/segctor/current_seg_sequence
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show segment sequence counter.
+
+What:		/sys/fs/nilfs2/<device>/segctor/current_last_full_seg
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show index number of the latest full segment.
+
+What:		/sys/fs/nilfs2/<device>/segctor/next_full_seg
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show index number of the full segment index
+		to be used next.
+
+What:		/sys/fs/nilfs2/<device>/segctor/next_pseg_offset
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show offset of next partial segment in the current
+		full segment.
+
+What:		/sys/fs/nilfs2/<device>/segctor/next_checkpoint
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show next checkpoint number.
+
+What:		/sys/fs/nilfs2/<device>/segctor/last_seg_write_time
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show write time of the last segment in
+		human-readable format.
+
+What:		/sys/fs/nilfs2/<device>/segctor/last_seg_write_time_secs
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show write time of the last segment in seconds.
+
+What:		/sys/fs/nilfs2/<device>/segctor/last_nongc_write_time
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show write time of the last segment not for cleaner
+		operation in human-readable format.
+
+What:		/sys/fs/nilfs2/<device>/segctor/last_nongc_write_time_secs
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show write time of the last segment not for cleaner
+		operation in seconds.
+
+What:		/sys/fs/nilfs2/<device>/segctor/dirty_data_blocks_count
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show number of dirty data blocks.
+
+What:		/sys/fs/nilfs2/<device>/segctor/README
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Describe attributes of /sys/fs/nilfs2/<device>/segctor
+		group.
+
+What:		/sys/fs/nilfs2/<device>/segments/segments_number
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show number of segments on a volume.
+
+What:		/sys/fs/nilfs2/<device>/segments/blocks_per_segment
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show number of blocks in segment.
+
+What:		/sys/fs/nilfs2/<device>/segments/clean_segments
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show count of clean segments.
+
+What:		/sys/fs/nilfs2/<device>/segments/dirty_segments
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show count of dirty segments.
+
+What:		/sys/fs/nilfs2/<device>/segments/README
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Describe attributes of /sys/fs/nilfs2/<device>/segments
+		group.
+
+What:		/sys/fs/nilfs2/<device>/checkpoints/checkpoints_number
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show number of checkpoints on volume.
+
+What:		/sys/fs/nilfs2/<device>/checkpoints/snapshots_number
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show number of snapshots on volume.
+
+What:		/sys/fs/nilfs2/<device>/checkpoints/last_seg_checkpoint
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show checkpoint number of the latest segment.
+
+What:		/sys/fs/nilfs2/<device>/checkpoints/next_checkpoint
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show next checkpoint number.
+
+What:		/sys/fs/nilfs2/<device>/checkpoints/README
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Describe attributes of /sys/fs/nilfs2/<device>/checkpoints
+		group.
+
+What:		/sys/fs/nilfs2/<device>/mounted_snapshots/README
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Describe content of /sys/fs/nilfs2/<device>/mounted_snapshots
+		group.
+
+What:		/sys/fs/nilfs2/<device>/mounted_snapshots/<id>/inodes_count
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show number of inodes for snapshot.
+
+What:		/sys/fs/nilfs2/<device>/mounted_snapshots/<id>/blocks_count
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Show number of blocks for snapshot.
+
+What:		/sys/fs/nilfs2/<device>/mounted_snapshots/<id>/README
+Date:		April 2014
+Contact:	"Vyacheslav Dubeyko" <slava@dubeyko.com>
+Description:
+		Describe attributes of /sys/fs/nilfs2/<device>/mounted_snapshots/<id>
+		group.
diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt
index 80ac454704b8..8870b0212150 100644
--- a/Documentation/cgroups/memcg_test.txt
+++ b/Documentation/cgroups/memcg_test.txt
@@ -24,64 +24,27 @@ Please note that implementation details can be changed.
 
    a page/swp_entry may be charged (usage += PAGE_SIZE) at
 
-	mem_cgroup_charge_anon()
-	  Called at new page fault and Copy-On-Write.
-
-	mem_cgroup_try_charge_swapin()
-	  Called at do_swap_page() (page fault on swap entry) and swapoff.
-	  Followed by charge-commit-cancel protocol. (With swap accounting)
-	  At commit, a charge recorded in swap_cgroup is removed.
-
-	mem_cgroup_charge_file()
-	  Called at add_to_page_cache()
-
-	mem_cgroup_cache_charge_swapin()
-	  Called at shmem's swapin.
-
-	mem_cgroup_prepare_migration()
-	  Called before migration. "extra" charge is done and followed by
-	  charge-commit-cancel protocol.
-	  At commit, charge against oldpage or newpage will be committed.
+	mem_cgroup_try_charge()
 
 2. Uncharge
   a page/swp_entry may be uncharged (usage -= PAGE_SIZE) by
 
-	mem_cgroup_uncharge_page()
-	  Called when an anonymous page is fully unmapped. I.e., mapcount goes
-	  to 0. If the page is SwapCache, uncharge is delayed until
-	  mem_cgroup_uncharge_swapcache().
-
-	mem_cgroup_uncharge_cache_page()
-	  Called when a page-cache is deleted from radix-tree. If the page is
-	  SwapCache, uncharge is delayed until mem_cgroup_uncharge_swapcache().
-
-	mem_cgroup_uncharge_swapcache()
-	  Called when SwapCache is removed from radix-tree. The charge itself
-	  is moved to swap_cgroup. (If mem+swap controller is disabled, no
-	  charge to swap occurs.)
+	mem_cgroup_uncharge()
+	  Called when a page's refcount goes down to 0.
 
 	mem_cgroup_uncharge_swap()
 	  Called when swp_entry's refcnt goes down to 0. A charge against swap
 	  disappears.
 
-	mem_cgroup_end_migration(old, new)
-	At success of migration old is uncharged (if necessary), a charge
-	to new page is committed. At failure, charge to old page is committed.
-
 3. charge-commit-cancel
-	In some case, we can't know this "charge" is valid or not at charging
-	(because of races).
-	To handle such case, there are charge-commit-cancel functions.
-		mem_cgroup_try_charge_XXX
-		mem_cgroup_commit_charge_XXX
-		mem_cgroup_cancel_charge_XXX
-	these are used in swap-in and migration.
+	Memcg pages are charged in two steps:
+		mem_cgroup_try_charge()
+		mem_cgroup_commit_charge() or mem_cgroup_cancel_charge()
 
 	At try_charge(), there are no flags to say "this page is charged".
 	at this point, usage += PAGE_SIZE.
 
-	At commit(), the function checks the page should be charged or not
-	and set flags or avoid charging.(usage -= PAGE_SIZE)
+	At commit(), the page is associated with the memcg.
 
 	At cancel(), simply usage -= PAGE_SIZE.
 
@@ -91,18 +54,6 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 	Anonymous page is newly allocated at
 		  - page fault into MAP_ANONYMOUS mapping.
 		  - Copy-On-Write.
- 	It is charged right after it's allocated before doing any page table
-	related operations. Of course, it's uncharged when another page is used
-	for the fault address.
-
-	At freeing anonymous page (by exit() or munmap()), zap_pte() is called
-	and pages for ptes are freed one by one.(see mm/memory.c). Uncharges
-	are done at page_remove_rmap() when page_mapcount() goes down to 0.
-
-	Another page freeing is by page-reclaim (vmscan.c) and anonymous
-	pages are swapped out. In this case, the page is marked as
-	PageSwapCache(). uncharge() routine doesn't uncharge the page marked
-	as SwapCache(). It's delayed until __delete_from_swap_cache().
 
 	4.1 Swap-in.
 	At swap-in, the page is taken from swap-cache. There are 2 cases.
@@ -111,41 +62,6 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 	(b) If the SwapCache has been mapped by processes, it has been
 	    charged already.
 
-	This swap-in is one of the most complicated work. In do_swap_page(),
-	following events occur when pte is unchanged.
-
-	(1) the page (SwapCache) is looked up.
-	(2) lock_page()
-	(3) try_charge_swapin()
-	(4) reuse_swap_page() (may call delete_swap_cache())
-	(5) commit_charge_swapin()
-	(6) swap_free().
-
-	Considering following situation for example.
-
-	(A) The page has not been charged before (2) and reuse_swap_page()
-	    doesn't call delete_from_swap_cache().
-	(B) The page has not been charged before (2) and reuse_swap_page()
-	    calls delete_from_swap_cache().
-	(C) The page has been charged before (2) and reuse_swap_page() doesn't
-	    call delete_from_swap_cache().
-	(D) The page has been charged before (2) and reuse_swap_page() calls
-	    delete_from_swap_cache().
-
-	    memory.usage/memsw.usage changes to this page/swp_entry will be
-	 Case          (A)      (B)       (C)     (D)
-         Event
-       Before (2)     0/ 1     0/ 1      1/ 1    1/ 1
-          ===========================================
-          (3)        +1/+1    +1/+1     +1/+1   +1/+1
-          (4)          -       0/ 0       -     -1/ 0
-          (5)         0/-1     0/ 0     -1/-1    0/ 0
-          (6)          -       0/-1       -      0/-1
-          ===========================================
-       Result         1/ 1     1/ 1      1/ 1    1/ 1
-
-       In any cases, charges to this page should be 1/ 1.
-
 	4.2 Swap-out.
 	At swap-out, typical state transition is below.
 
@@ -158,28 +74,20 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 	    swp_entry's refcnt -= 1.
 
 
-	At (b), the page is marked as SwapCache and not uncharged.
-	At (d), the page is removed from SwapCache and a charge in page_cgroup
-	is moved to swap_cgroup.
-
 	Finally, at task exit,
 	(e) zap_pte() is called and swp_entry's refcnt -=1 -> 0.
-	Here, a charge in swap_cgroup disappears.
 
 5. Page Cache
    	Page Cache is charged at
 	- add_to_page_cache_locked().
 
-	uncharged at
-	- __remove_from_page_cache().
-
 	The logic is very clear. (About migration, see below)
 	Note: __remove_from_page_cache() is called by remove_from_page_cache()
 	and __remove_mapping().
 
 6. Shmem(tmpfs) Page Cache
-	Memcg's charge/uncharge have special handlers of shmem. The best way
-	to understand shmem's page state transition is to read mm/shmem.c.
+	The best way to understand shmem's page state transition is to read
+	mm/shmem.c.
 	But brief explanation of the behavior of memcg around shmem will be
 	helpful to understand the logic.
 
@@ -192,56 +100,10 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 	It's charged when...
 	- A new page is added to shmem's radix-tree.
 	- A swp page is read. (move a charge from swap_cgroup to page_cgroup)
-	It's uncharged when
-	- A page is removed from radix-tree and not SwapCache.
-	- When SwapCache is removed, a charge is moved to swap_cgroup.
-	- When swp_entry's refcnt goes down to 0, a charge in swap_cgroup
-	  disappears.
 
 7. Page Migration
-   	One of the most complicated functions is page-migration-handler.
-	Memcg has 2 routines. Assume that we are migrating a page's contents
-	from OLDPAGE to NEWPAGE.
-
-	Usual migration logic is..
-	(a) remove the page from LRU.
-	(b) allocate NEWPAGE (migration target)
-	(c) lock by lock_page().
-	(d) unmap all mappings.
-	(e-1) If necessary, replace entry in radix-tree.
-	(e-2) move contents of a page.
-	(f) map all mappings again.
-	(g) pushback the page to LRU.
-	(-) OLDPAGE will be freed.
-
-	Before (g), memcg should complete all necessary charge/uncharge to
-	NEWPAGE/OLDPAGE.
-
-	The point is....
-	- If OLDPAGE is anonymous, all charges will be dropped at (d) because
-          try_to_unmap() drops all mapcount and the page will not be
-	  SwapCache.
-
-	- If OLDPAGE is SwapCache, charges will be kept at (g) because
-	  __delete_from_swap_cache() isn't called at (e-1)
-
-	- If OLDPAGE is page-cache, charges will be kept at (g) because
-	  remove_from_swap_cache() isn't called at (e-1)
-
-	memcg provides following hooks.
-
-	- mem_cgroup_prepare_migration(OLDPAGE)
-	  Called after (b) to account a charge (usage += PAGE_SIZE) against
-	  memcg which OLDPAGE belongs to.
-
-        - mem_cgroup_end_migration(OLDPAGE, NEWPAGE)
-	  Called after (f) before (g).
-	  If OLDPAGE is used, commit OLDPAGE again. If OLDPAGE is already
-	  charged, a charge by prepare_migration() is automatically canceled.
-	  If NEWPAGE is used, commit NEWPAGE and uncharge OLDPAGE.
-
-	  But zap_pte() (by exit or munmap) can be called while migration,
-	  we have to check if OLDPAGE/NEWPAGE is a valid page after commit().
+
+	mem_cgroup_migrate()
 
 8. LRU
         Each memcg has its own private LRU. Now, its handling is under global
diff --git a/Documentation/devicetree/bindings/i2c/trivial-devices.txt b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
index 37803eb5521e..6af570ec53b4 100644
--- a/Documentation/devicetree/bindings/i2c/trivial-devices.txt
+++ b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
@@ -70,6 +70,7 @@ nuvoton,npct501		i2c trusted platform module (TPM)
 nxp,pca9556		Octal SMBus and I2C registered interface
 nxp,pca9557		8-bit I2C-bus and SMBus I/O port with reset
 nxp,pcf8563		Real-time clock/calendar
+nxp,pcf85063		Tiny Real-Time Clock
 ovti,ov5642		OV5642: Color CMOS QSXGA (5-megapixel) Image Sensor with OmniBSI and Embedded TrueFocus
 pericom,pt7c4338	Real-time Clock Module
 plx,pex8648		48-Lane, 12-Port PCI Express Gen 2 (5.0 GT/s) Switch
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/oops-tracing.txt b/Documentation/oops-tracing.txt
index e3155995ddd8..beefb9f82902 100644
--- a/Documentation/oops-tracing.txt
+++ b/Documentation/oops-tracing.txt
@@ -268,6 +268,8 @@ characters, each representing a particular tainted value.
  14: 'E' if an unsigned module has been loaded in a kernel supporting
      module signature.
 
+ 15: 'L' if a soft lockup has previously occurred on the system.
+
 The primary reason for the 'Tainted: ' string is to tell kernel
 debuggers if this is a clean kernel or if anything unusual has
 occurred.  Tainting is permanent: even if an offending module is
diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt
index b4498218c474..3b56a991f52e 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/tsi721.txt b/Documentation/rapidio/tsi721.txt
index 335f3c6087dc..626052f403bb 100644
--- a/Documentation/rapidio/tsi721.txt
+++ b/Documentation/rapidio/tsi721.txt
@@ -20,13 +20,26 @@ II. Known problems
 
   None.
 
-III. To do
+III. DMA Engine Support
 
- Add DMA data transfers (non-messaging).
- Add inbound region (SRIO-to-PCIe) mapping.
+Tsi721 mport driver supports DMA data transfers between local system memory and
+remote RapidIO devices. This functionality is implemented according to SLAVE
+mode API defined by common Linux kernel DMA Engine framework.
+
+Depending on system requirements RapidIO DMA operations can be included/excluded
+by setting CONFIG_RAPIDIO_DMA_ENGINE option. Tsi721 miniport driver uses seven
+out of eight available BDMA channels to support DMA data transfers.
+One BDMA channel is reserved for generation of maintenance read/write requests.
+
+If Tsi721 mport driver have been built with RAPIDIO_DMA_ENGINE support included,
+this driver will accept DMA-specific module parameter:
+  "dma_desc_per_channel" - defines number of hardware buffer descriptors used by
+                           each BDMA channel of Tsi721 (by default - 128).
 
 IV. Version History
 
+  1.1.0 - DMA operations re-worked to support data scatter/gather lists larger
+          than hardware buffer descriptors ring.
   1.0.0 - Initial driver release.
 
 V.  License
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index c14374e71775..f79eb9666379 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -826,6 +826,7 @@ can be ORed together:
 4096 - An out-of-tree module has been loaded.
 8192 - An unsigned module has been loaded in a kernel supporting module
        signature.
+16384 - A soft lockup has previously occurred on the system.
 
 ==============================================================
 
diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index 96e54bed5088..e858aa0ad8af 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -6,4 +6,5 @@ generic-y += exec.h
 generic-y += hash.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
+generic-y += scatterlist.h
 generic-y += trace_clock.h
diff --git a/arch/alpha/include/asm/scatterlist.h b/arch/alpha/include/asm/scatterlist.h
deleted file mode 100644
index 017d7471c3c4..000000000000
--- a/arch/alpha/include/asm/scatterlist.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ALPHA_SCATTERLIST_H
-#define _ALPHA_SCATTERLIST_H
-
-#include <asm-generic/scatterlist.h>
-
-#endif /* !(_ALPHA_SCATTERLIST_H) */
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 916cedbd7a67..32cbbd565902 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -83,6 +83,7 @@ config ARM
 	  <http://www.arm.linux.org.uk/>.
 
 config ARM_HAS_SG_CHAIN
+	select ARCH_HAS_SG_CHAIN
 	bool
 
 config NEED_SG_DMA_LENGTH
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index f5a357601983..70cd84eb7fda 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -22,6 +22,7 @@ generic-y += poll.h
 generic-y += preempt.h
 generic-y += resource.h
 generic-y += rwsem.h
+generic-y += scatterlist.h
 generic-y += sections.h
 generic-y += segment.h
 generic-y += sembuf.h
diff --git a/arch/arm/include/asm/scatterlist.h b/arch/arm/include/asm/scatterlist.h
deleted file mode 100644
index cefdb8f898a1..000000000000
--- a/arch/arm/include/asm/scatterlist.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASMARM_SCATTERLIST_H
-#define _ASMARM_SCATTERLIST_H
-
-#ifdef CONFIG_ARM_HAS_SG_CHAIN
-#define ARCH_HAS_SG_CHAIN
-#endif
-
-#include <asm/memory.h>
-#include <asm/types.h>
-#include <asm-generic/scatterlist.h>
-
-#endif /* _ASMARM_SCATTERLIST_H */
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a5dc5ff145a3..62b4ae1c5bbf 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1,6 +1,7 @@
 config ARM64
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
+	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_SUPPORTS_ATOMIC_RMW
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index afff5105909d..31742dfadff9 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -13,6 +13,7 @@ generic-y += linkage.h
 generic-y += mcs_spinlock.h
 generic-y += module.h
 generic-y += preempt.h
+generic-y += scatterlist.h
 generic-y += trace_clock.h
 generic-y += vga.h
 generic-y += xor.h
diff --git a/arch/cris/include/asm/scatterlist.h b/arch/cris/include/asm/scatterlist.h
deleted file mode 100644
index f11f8f40ec4a..000000000000
--- a/arch/cris/include/asm/scatterlist.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_CRIS_SCATTERLIST_H
-#define __ASM_CRIS_SCATTERLIST_H
-
-#include <asm-generic/scatterlist.h>
-
-#endif /* !(__ASM_CRIS_SCATTERLIST_H) */
diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild
index 87b95eb8aee5..5b73921b6e9d 100644
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -5,4 +5,5 @@ generic-y += exec.h
 generic-y += hash.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
+generic-y += scatterlist.h
 generic-y += trace_clock.h
diff --git a/arch/frv/include/asm/scatterlist.h b/arch/frv/include/asm/scatterlist.h
deleted file mode 100644
index 0e5eb3018468..000000000000
--- a/arch/frv/include/asm/scatterlist.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_SCATTERLIST_H
-#define _ASM_SCATTERLIST_H
-
-#include <asm-generic/scatterlist.h>
-
-#endif /* !_ASM_SCATTERLIST_H */
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 44a6915ab13d..c84c88bbbbd7 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -28,6 +28,7 @@ config IA64
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_VIRT_CPU_ACCOUNTING
+	select ARCH_HAS_SG_CHAIN
 	select VIRT_TO_BUS
 	select ARCH_DISCARD_MEMBLOCK
 	select GENERIC_IRQ_PROBE
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index 0da4aa2602ae..e8317d2d6c8d 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -5,5 +5,6 @@ generic-y += hash.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
+generic-y += scatterlist.h
 generic-y += trace_clock.h
 generic-y += vtime.h
diff --git a/arch/ia64/include/asm/scatterlist.h b/arch/ia64/include/asm/scatterlist.h
deleted file mode 100644
index 08fd93bff1db..000000000000
--- a/arch/ia64/include/asm/scatterlist.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _ASM_IA64_SCATTERLIST_H
-#define _ASM_IA64_SCATTERLIST_H
-
-#include <asm-generic/scatterlist.h>
-#define ARCH_HAS_SG_CHAIN
-
-#endif /* _ASM_IA64_SCATTERLIST_H */
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 3e71ef85e439..9a0104a38cd3 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -384,21 +384,6 @@ static struct irqaction timer_irqaction = {
 	.name =		"timer"
 };
 
-static struct platform_device rtc_efi_dev = {
-	.name = "rtc-efi",
-	.id = -1,
-};
-
-static int __init rtc_init(void)
-{
-	if (platform_device_register(&rtc_efi_dev) < 0)
-		printk(KERN_ERR "unable to register rtc device...\n");
-
-	/* not necessarily an error */
-	return 0;
-}
-module_init(rtc_init);
-
 void read_persistent_clock(struct timespec *ts)
 {
 	efi_gettimeofday(ts);
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index 67779a74b62d..accc10a3dc78 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -6,4 +6,5 @@ generic-y += hash.h
 generic-y += mcs_spinlock.h
 generic-y += module.h
 generic-y += preempt.h
+generic-y += scatterlist.h
 generic-y += trace_clock.h
diff --git a/arch/m32r/include/asm/scatterlist.h b/arch/m32r/include/asm/scatterlist.h
deleted file mode 100644
index 7370b8b6243e..000000000000
--- a/arch/m32r/include/asm/scatterlist.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_M32R_SCATTERLIST_H
-#define _ASM_M32R_SCATTERLIST_H
-
-#include <asm-generic/scatterlist.h>
-
-#endif /* _ASM_M32R_SCATTERLIST_H */
diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c
index 3a480b3df0d6..d2263a0bdc3d 100644
--- a/arch/m68k/kernel/sys_m68k.c
+++ b/arch/m68k/kernel/sys_m68k.c
@@ -376,7 +376,6 @@ cache_flush_060 (unsigned long addr, int scope, int cache, unsigned long len)
 asmlinkage int
 sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
 {
-	struct vm_area_struct *vma;
 	int ret = -EINVAL;
 
 	if (scope < FLUSH_SCOPE_LINE || scope > FLUSH_SCOPE_ALL ||
@@ -389,16 +388,23 @@ sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
 		if (!capable(CAP_SYS_ADMIN))
 			goto out;
 	} else {
+		struct vm_area_struct *vma;
+		bool invalid;
+
+		/* Check for overflow.  */
+		if (addr + len < addr)
+			goto out;
+
 		/*
 		 * Verify that the specified address region actually belongs
 		 * to this process.
 		 */
-		vma = find_vma (current->mm, addr);
 		ret = -EINVAL;
-		/* Check for overflow.  */
-		if (addr + len < addr)
-			goto out;
-		if (vma == NULL || addr < vma->vm_start || addr + len > vma->vm_end)
+		down_read(&current->mm->mmap_sem);
+		vma = find_vma(current->mm, addr);
+		invalid = !vma || addr < vma->vm_start || addr + len > vma->vm_end;
+		up_read(&current->mm->mmap_sem);
+		if (invalid)
 			goto out;
 	}
 
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 35b3ecaf25d5..27a3acda6c19 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -7,5 +7,6 @@ generic-y += exec.h
 generic-y += hash.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
+generic-y += scatterlist.h
 generic-y += syscalls.h
 generic-y += trace_clock.h
diff --git a/arch/microblaze/include/asm/scatterlist.h b/arch/microblaze/include/asm/scatterlist.h
deleted file mode 100644
index 35d786fe93ae..000000000000
--- a/arch/microblaze/include/asm/scatterlist.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/scatterlist.h>
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index 654d5ba6e310..ecbd6676bd33 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -6,4 +6,5 @@ generic-y += exec.h
 generic-y += hash.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
+generic-y += scatterlist.h
 generic-y += trace_clock.h
diff --git a/arch/mn10300/include/asm/scatterlist.h b/arch/mn10300/include/asm/scatterlist.h
deleted file mode 100644
index 7baa4006008a..000000000000
--- a/arch/mn10300/include/asm/scatterlist.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* MN10300 Scatterlist definitions
- *
- * Copyright (C) 2007 Matsushita Electric Industrial Co., Ltd.
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-#ifndef _ASM_SCATTERLIST_H
-#define _ASM_SCATTERLIST_H
-
-#include <asm-generic/scatterlist.h>
-
-#endif /* _ASM_SCATTERLIST_H */
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 80b94b0add1f..4bc7b62fb4b6 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -111,6 +111,7 @@ config PPC
 	select HAVE_DMA_API_DEBUG
 	select HAVE_OPROFILE
 	select HAVE_DEBUG_KMEMLEAK
+	select ARCH_HAS_SG_CHAIN
 	select GENERIC_ATOMIC64 if PPC32
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select HAVE_PERF_EVENTS
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 3fb1bc432f4f..7f23f162ce9c 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -4,5 +4,6 @@ generic-y += hash.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += rwsem.h
+generic-y += scatterlist.h
 generic-y += trace_clock.h
 generic-y += vtime.h
diff --git a/arch/powerpc/include/asm/scatterlist.h b/arch/powerpc/include/asm/scatterlist.h
deleted file mode 100644
index de1f620bd5c9..000000000000
--- a/arch/powerpc/include/asm/scatterlist.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef _ASM_POWERPC_SCATTERLIST_H
-#define _ASM_POWERPC_SCATTERLIST_H
-/*
- * Copyright (C) 2001 PPC64 Team, IBM Corp
- *
- * 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 <asm/dma.h>
-#include <asm-generic/scatterlist.h>
-
-#define ARCH_HAS_SG_CHAIN
-
-#endif /* _ASM_POWERPC_SCATTERLIST_H */
diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c
index 7b6c10750179..d85e86aac7fb 100644
--- a/arch/powerpc/mm/dma-noncoherent.c
+++ b/arch/powerpc/mm/dma-noncoherent.c
@@ -33,6 +33,7 @@
 #include <linux/export.h>
 
 #include <asm/tlbflush.h>
+#include <asm/dma.h>
 
 #include "mmu_decl.h"
 
diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c
index 534574a97ec9..3a104284b338 100644
--- a/arch/powerpc/platforms/44x/warp.c
+++ b/arch/powerpc/platforms/44x/warp.c
@@ -25,6 +25,7 @@
 #include <asm/time.h>
 #include <asm/uic.h>
 #include <asm/ppc4xx.h>
+#include <asm/dma.h>
 
 
 static __initdata struct of_device_id warp_of_bus[] = {
diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c
index 6e19b0ad5d26..3feffde9128d 100644
--- a/arch/powerpc/platforms/52xx/efika.c
+++ b/arch/powerpc/platforms/52xx/efika.c
@@ -13,6 +13,7 @@
 #include <generated/utsrelease.h>
 #include <linux/pci.h>
 #include <linux/of.h>
+#include <asm/dma.h>
 #include <asm/prom.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/amigaone/setup.c b/arch/powerpc/platforms/amigaone/setup.c
index 03aabc0e16ac..2fe12046279e 100644
--- a/arch/powerpc/platforms/amigaone/setup.c
+++ b/arch/powerpc/platforms/amigaone/setup.c
@@ -24,6 +24,7 @@
 #include <asm/i8259.h>
 #include <asm/time.h>
 #include <asm/udbg.h>
+#include <asm/dma.h>
 
 extern void __flush_disable_L1(void);
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 8ca60f8d5683..05c78bb5f570 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -145,6 +145,7 @@ config S390
 	select TTY
 	select VIRT_CPU_ACCOUNTING
 	select VIRT_TO_BUS
+	select ARCH_HAS_SG_CHAIN
 
 config SCHED_OMIT_FRAME_POINTER
 	def_bool y
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 57892a8a9055..b3fea0722ff1 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -4,4 +4,5 @@ generic-y += clkdev.h
 generic-y += hash.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
+generic-y += scatterlist.h
 generic-y += trace_clock.h
diff --git a/arch/s390/include/asm/scatterlist.h b/arch/s390/include/asm/scatterlist.h
deleted file mode 100644
index 6d45ef6c12a7..000000000000
--- a/arch/s390/include/asm/scatterlist.h
+++ /dev/null
@@ -1,3 +0,0 @@
-#include <asm-generic/scatterlist.h>
-
-#define ARCH_HAS_SG_CHAIN
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index 2f947aba4bd4..aad209199f7e 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -8,5 +8,6 @@ generic-y += cputime.h
 generic-y += hash.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
+generic-y += scatterlist.h
 generic-y += trace_clock.h
 generic-y += xor.h
diff --git a/arch/score/include/asm/scatterlist.h b/arch/score/include/asm/scatterlist.h
deleted file mode 100644
index 9f533b8362c7..000000000000
--- a/arch/score/include/asm/scatterlist.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_SCORE_SCATTERLIST_H
-#define _ASM_SCORE_SCATTERLIST_H
-
-#include <asm-generic/scatterlist.h>
-
-#endif /* _ASM_SCORE_SCATTERLIST_H */
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 4692c90936f1..a537816613f9 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -42,6 +42,7 @@ config SPARC
 	select MODULES_USE_ELF_RELA
 	select ODD_RT_SIGACTION
 	select OLD_SIGSUSPEND
+	select ARCH_HAS_SG_CHAIN
 
 config SPARC32
 	def_bool !64BIT
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index a45821818003..cdd1b447bb6c 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -15,6 +15,7 @@ generic-y += mcs_spinlock.h
 generic-y += module.h
 generic-y += mutex.h
 generic-y += preempt.h
+generic-y += scatterlist.h
 generic-y += serial.h
 generic-y += trace_clock.h
 generic-y += types.h
diff --git a/arch/sparc/include/asm/scatterlist.h b/arch/sparc/include/asm/scatterlist.h
deleted file mode 100644
index 92bb638313f8..000000000000
--- a/arch/sparc/include/asm/scatterlist.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef _SPARC_SCATTERLIST_H
-#define _SPARC_SCATTERLIST_H
-
-#include <asm-generic/scatterlist.h>
-
-#define ARCH_HAS_SG_CHAIN
-
-#endif /* !(_SPARC_SCATTERLIST_H) */
diff --git a/arch/tile/include/asm/hardwall.h b/arch/tile/include/asm/hardwall.h
index 2f572b6b7bc2..44d2765bde2b 100644
--- a/arch/tile/include/asm/hardwall.h
+++ b/arch/tile/include/asm/hardwall.h
@@ -23,7 +23,7 @@
 struct proc_dir_entry;
 #ifdef CONFIG_HARDWALL
 void proc_tile_hardwall_init(struct proc_dir_entry *root);
-int proc_pid_hardwall(struct task_struct *task, char *buffer);
+int proc_pid_hardwall(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task);
 #else
 static inline void proc_tile_hardwall_init(struct proc_dir_entry *root) {}
 #endif
diff --git a/arch/tile/kernel/hardwall.c b/arch/tile/kernel/hardwall.c
index 531f4c365351..aca6000bca75 100644
--- a/arch/tile/kernel/hardwall.c
+++ b/arch/tile/kernel/hardwall.c
@@ -947,15 +947,15 @@ static void hardwall_remove_proc(struct hardwall_info *info)
 	remove_proc_entry(buf, info->type->proc_dir);
 }
 
-int proc_pid_hardwall(struct task_struct *task, char *buffer)
+int proc_pid_hardwall(struct seq_file *m, struct pid_namespace *ns,
+		      struct pid *pid, struct task_struct *task)
 {
 	int i;
 	int n = 0;
 	for (i = 0; i < HARDWALL_TYPES; ++i) {
 		struct hardwall_info *info = task->thread.hardwall[i].info;
 		if (info)
-			n += sprintf(&buffer[n], "%s: %d\n",
-				     info->type->name, info->id);
+			seq_printf(m, "%s: %d\n", info->type->name, info->id);
 	}
 	return n;
 }
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index a5e4b6068213..7bd64aa2e94a 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -21,6 +21,7 @@ generic-y += param.h
 generic-y += pci.h
 generic-y += percpu.h
 generic-y += preempt.h
+generic-y += scatterlist.h
 generic-y += sections.h
 generic-y += switch_to.h
 generic-y += topology.h
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3d11ae495816..fcbe79ee86a2 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -96,6 +96,7 @@ config X86
 	select IRQ_FORCED_THREADING
 	select HAVE_BPF_JIT if X86_64
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	select ARCH_HAS_SG_CHAIN
 	select CLKEVT_I8253
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_IOMAP
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 3ca9762e1649..3bf000fab0ae 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -5,6 +5,7 @@ genhdr-y += unistd_64.h
 genhdr-y += unistd_x32.h
 
 generic-y += clkdev.h
-generic-y += early_ioremap.h
 generic-y += cputime.h
+generic-y += early_ioremap.h
 generic-y += mcs_spinlock.h
+generic-y += scatterlist.h
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 4064acae625d..01b493e5a99b 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -9,7 +9,6 @@
 #ifdef CONFIG_NUMA
 
 #define NR_NODE_MEMBLKS		(MAX_NUMNODES*2)
-#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
 
 /*
  * Too small node sizes may confuse the VM badly. Usually they
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 5be9063545d2..809abb335627 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -115,7 +115,8 @@ static inline void native_pgd_clear(pgd_t *pgd)
 	native_set_pgd(pgd, native_make_pgd(0));
 }
 
-extern void sync_global_pgds(unsigned long start, unsigned long end);
+extern void sync_global_pgds(unsigned long start, unsigned long end,
+			     int removed);
 
 /*
  * Conversion functions: convert a page and protection to a page entry,
diff --git a/arch/x86/include/asm/scatterlist.h b/arch/x86/include/asm/scatterlist.h
deleted file mode 100644
index 4240878b9d76..000000000000
--- a/arch/x86/include/asm/scatterlist.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef _ASM_X86_SCATTERLIST_H
-#define _ASM_X86_SCATTERLIST_H
-
-#include <asm-generic/scatterlist.h>
-
-#define ARCH_HAS_SG_CHAIN
-
-#endif /* _ASM_X86_SCATTERLIST_H */
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index a24194681513..d393ac669cc0 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -350,7 +350,7 @@ out:
 
 void vmalloc_sync_all(void)
 {
-	sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END);
+	sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END, 0);
 }
 
 /*
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 5621c47d7a1a..529625118ff6 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -178,7 +178,7 @@ __setup("noexec32=", nonx32_setup);
  * When memory was added/removed make sure all the processes MM have
  * suitable PGD entries in the local PGD level page.
  */
-void sync_global_pgds(unsigned long start, unsigned long end)
+void sync_global_pgds(unsigned long start, unsigned long end, int removed)
 {
 	unsigned long address;
 
@@ -186,7 +186,12 @@ void sync_global_pgds(unsigned long start, unsigned long end)
 		const pgd_t *pgd_ref = pgd_offset_k(address);
 		struct page *page;
 
-		if (pgd_none(*pgd_ref))
+		/*
+		 * When it is called after memory hot remove, pgd_none()
+		 * returns true. In this case (removed == 1), we must clear
+		 * the PGD entries in the local PGD level page.
+		 */
+		if (pgd_none(*pgd_ref) && !removed)
 			continue;
 
 		spin_lock(&pgd_lock);
@@ -199,12 +204,18 @@ void sync_global_pgds(unsigned long start, unsigned long end)
 			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
 			spin_lock(pgt_lock);
 
-			if (pgd_none(*pgd))
-				set_pgd(pgd, *pgd_ref);
-			else
+			if (!pgd_none(*pgd_ref) && !pgd_none(*pgd))
 				BUG_ON(pgd_page_vaddr(*pgd)
 				       != pgd_page_vaddr(*pgd_ref));
 
+			if (removed) {
+				if (pgd_none(*pgd_ref) && !pgd_none(*pgd))
+					pgd_clear(pgd);
+			} else {
+				if (pgd_none(*pgd))
+					set_pgd(pgd, *pgd_ref);
+			}
+
 			spin_unlock(pgt_lock);
 		}
 		spin_unlock(&pgd_lock);
@@ -633,7 +644,7 @@ kernel_physical_mapping_init(unsigned long start,
 	}
 
 	if (pgd_changed)
-		sync_global_pgds(addr, end - 1);
+		sync_global_pgds(addr, end - 1, 0);
 
 	__flush_tlb_all();
 
@@ -976,25 +987,26 @@ static void __meminit
 remove_pagetable(unsigned long start, unsigned long end, bool direct)
 {
 	unsigned long next;
+	unsigned long addr;
 	pgd_t *pgd;
 	pud_t *pud;
 	bool pgd_changed = false;
 
-	for (; start < end; start = next) {
-		next = pgd_addr_end(start, end);
+	for (addr = start; addr < end; addr = next) {
+		next = pgd_addr_end(addr, end);
 
-		pgd = pgd_offset_k(start);
+		pgd = pgd_offset_k(addr);
 		if (!pgd_present(*pgd))
 			continue;
 
 		pud = (pud_t *)pgd_page_vaddr(*pgd);
-		remove_pud_table(pud, start, next, direct);
+		remove_pud_table(pud, addr, next, direct);
 		if (free_pud_table(pud, pgd))
 			pgd_changed = true;
 	}
 
 	if (pgd_changed)
-		sync_global_pgds(start, end - 1);
+		sync_global_pgds(start, end - 1, 1);
 
 	flush_tlb_all();
 }
@@ -1341,7 +1353,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 	else
 		err = vmemmap_populate_basepages(start, end, node);
 	if (!err)
-		sync_global_pgds(start, end - 1);
+		sync_global_pgds(start, end - 1, 0);
 	return err;
 }
 
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index a32b706c401a..d221374d5ce8 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -185,8 +185,8 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
 	return numa_add_memblk_to(nid, start, end, &numa_meminfo);
 }
 
-/* Initialize NODE_DATA for a node on the local memory */
-static void __init setup_node_data(int nid, u64 start, u64 end)
+/* Allocate NODE_DATA for a node on the local memory */
+static void __init alloc_node_data(int nid)
 {
 	const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
 	u64 nd_pa;
@@ -194,18 +194,6 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 	int tnid;
 
 	/*
-	 * Don't confuse VM with a node that doesn't have the
-	 * minimum amount of memory:
-	 */
-	if (end && (end - start) < NODE_MIN_SIZE)
-		return;
-
-	start = roundup(start, ZONE_ALIGN);
-
-	printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
-	       nid, start, end - 1);
-
-	/*
 	 * Allocate node data.  Try node-local memory and then any node.
 	 * Never allocate in DMA zone.
 	 */
@@ -222,7 +210,7 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 	nd = __va(nd_pa);
 
 	/* report and initialize */
-	printk(KERN_INFO "  NODE_DATA [mem %#010Lx-%#010Lx]\n",
+	printk(KERN_INFO "NODE_DATA(%d) allocated [mem %#010Lx-%#010Lx]\n", nid,
 	       nd_pa, nd_pa + nd_size - 1);
 	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
 	if (tnid != nid)
@@ -230,9 +218,6 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 
 	node_data[nid] = nd;
 	memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
-	NODE_DATA(nid)->node_id = nid;
-	NODE_DATA(nid)->node_start_pfn = start >> PAGE_SHIFT;
-	NODE_DATA(nid)->node_spanned_pages = (end - start) >> PAGE_SHIFT;
 
 	node_set_online(nid);
 }
@@ -523,8 +508,17 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 			end = max(mi->blk[i].end, end);
 		}
 
-		if (start < end)
-			setup_node_data(nid, start, end);
+		if (start >= end)
+			continue;
+
+		/*
+		 * Don't confuse VM with a node that doesn't have the
+		 * minimum amount of memory:
+		 */
+		if (end && (end - start) < NODE_MIN_SIZE)
+			continue;
+
+		alloc_node_data(nid);
 	}
 
 	/* Dump memblock with node info and return. */
diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c
index f15103dff4b4..d143d216d52b 100644
--- a/arch/x86/platform/efi/efi-bgrt.c
+++ b/arch/x86/platform/efi/efi-bgrt.c
@@ -40,20 +40,40 @@ void __init efi_bgrt_init(void)
 	if (ACPI_FAILURE(status))
 		return;
 
-	if (bgrt_tab->header.length < sizeof(*bgrt_tab))
+	if (bgrt_tab->header.length < sizeof(*bgrt_tab)) {
+		pr_err("Ignoring BGRT: invalid length %u (expected %zu)\n",
+		       bgrt_tab->header.length, sizeof(*bgrt_tab));
 		return;
-	if (bgrt_tab->version != 1 || bgrt_tab->status != 1)
+	}
+	if (bgrt_tab->version != 1) {
+		pr_err("Ignoring BGRT: invalid version %u (expected 1)\n",
+		       bgrt_tab->version);
+		return;
+	}
+	if (bgrt_tab->status != 1) {
+		pr_err("Ignoring BGRT: invalid status %u (expected 1)\n",
+		       bgrt_tab->status);
+		return;
+	}
+	if (bgrt_tab->image_type != 0) {
+		pr_err("Ignoring BGRT: invalid image type %u (expected 0)\n",
+		       bgrt_tab->image_type);
 		return;
-	if (bgrt_tab->image_type != 0 || !bgrt_tab->image_address)
+	}
+	if (!bgrt_tab->image_address) {
+		pr_err("Ignoring BGRT: null image address\n");
 		return;
+	}
 
 	image = efi_lookup_mapped_addr(bgrt_tab->image_address);
 	if (!image) {
 		image = early_memremap(bgrt_tab->image_address,
 				       sizeof(bmp_header));
 		ioremapped = true;
-		if (!image)
+		if (!image) {
+			pr_err("Ignoring BGRT: failed to map image header memory\n");
 			return;
+		}
 	}
 
 	memcpy_fromio(&bmp_header, image, sizeof(bmp_header));
@@ -61,14 +81,18 @@ void __init efi_bgrt_init(void)
 		early_iounmap(image, sizeof(bmp_header));
 	bgrt_image_size = bmp_header.size;
 
-	bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL);
-	if (!bgrt_image)
+	bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL | __GFP_NOWARN);
+	if (!bgrt_image) {
+		pr_err("Ignoring BGRT: failed to allocate memory for image (wanted %zu bytes)\n",
+		       bgrt_image_size);
 		return;
+	}
 
 	if (ioremapped) {
 		image = early_memremap(bgrt_tab->image_address,
 				       bmp_header.size);
 		if (!image) {
+			pr_err("Ignoring BGRT: failed to map image memory\n");
 			kfree(bgrt_image);
 			bgrt_image = NULL;
 			return;
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index bc423f7b02da..38c8ac2970ac 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -646,6 +646,4 @@ void __init bio_integrity_init(void)
 				     sizeof(struct bio_integrity_payload) +
 				     sizeof(struct bio_vec) * BIP_INLINE_VECS,
 				     0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
-	if (!bip_slab)
-		panic("Failed to create slab\n");
 }
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/crypto/zlib.c b/crypto/zlib.c
index 06b62e5cdcc7..c9ee681d57fd 100644
--- a/crypto/zlib.c
+++ b/crypto/zlib.c
@@ -168,7 +168,7 @@ static int zlib_compress_update(struct crypto_pcomp *tfm,
 	}
 
 	ret = req->avail_out - stream->avail_out;
-	pr_debug("avail_in %u, avail_out %u (consumed %u, produced %u)\n",
+	pr_debug("avail_in %lu, avail_out %lu (consumed %lu, produced %u)\n",
 		 stream->avail_in, stream->avail_out,
 		 req->avail_in - stream->avail_in, ret);
 	req->next_in = stream->next_in;
@@ -198,7 +198,7 @@ static int zlib_compress_final(struct crypto_pcomp *tfm,
 	}
 
 	ret = req->avail_out - stream->avail_out;
-	pr_debug("avail_in %u, avail_out %u (consumed %u, produced %u)\n",
+	pr_debug("avail_in %lu, avail_out %lu (consumed %lu, produced %u)\n",
 		 stream->avail_in, stream->avail_out,
 		 req->avail_in - stream->avail_in, ret);
 	req->next_in = stream->next_in;
@@ -283,7 +283,7 @@ static int zlib_decompress_update(struct crypto_pcomp *tfm,
 	}
 
 	ret = req->avail_out - stream->avail_out;
-	pr_debug("avail_in %u, avail_out %u (consumed %u, produced %u)\n",
+	pr_debug("avail_in %lu, avail_out %lu (consumed %lu, produced %u)\n",
 		 stream->avail_in, stream->avail_out,
 		 req->avail_in - stream->avail_in, ret);
 	req->next_in = stream->next_in;
@@ -331,7 +331,7 @@ static int zlib_decompress_final(struct crypto_pcomp *tfm,
 	}
 
 	ret = req->avail_out - stream->avail_out;
-	pr_debug("avail_in %u, avail_out %u (consumed %u, produced %u)\n",
+	pr_debug("avail_in %lu, avail_out %lu (consumed %lu, produced %u)\n",
 		 stream->avail_in, stream->avail_out,
 		 req->avail_in - stream->avail_in, ret);
 	req->next_in = stream->next_in;
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 29ca0bb4f561..236bc56e6a81 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -710,6 +710,9 @@ 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);
 }
 
 /**
@@ -2136,6 +2139,9 @@ 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..985fa7ebeec7
--- /dev/null
+++ b/drivers/input/leds.c
@@ -0,0 +1,249 @@
+/*
+ * LED support for the input layer
+ *
+ * Copyright 2010-2014 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 = kcalloc(LED_CNT, sizeof(*leds), 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 8c96e2ddf43b..f6e32ba50674 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/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/parport/parport_ip32.c b/drivers/parport/parport_ip32.c
index c864f82bd37d..30e981be14c2 100644
--- a/drivers/parport/parport_ip32.c
+++ b/drivers/parport/parport_ip32.c
@@ -2204,7 +2204,7 @@ static int __init parport_ip32_init(void)
 {
 	pr_info(PPIP32 "SGI IP32 built-in parallel port driver v0.6\n");
 	this_port = parport_ip32_probe_port();
-	return IS_ERR(this_port) ? PTR_ERR(this_port) : 0;
+	return PTR_ERR_OR_ZERO(this_port);
 }
 
 /**
diff --git a/drivers/rapidio/devices/tsi721.h b/drivers/rapidio/devices/tsi721.h
index 0305675270ee..a7b42680a06a 100644
--- a/drivers/rapidio/devices/tsi721.h
+++ b/drivers/rapidio/devices/tsi721.h
@@ -644,27 +644,26 @@ 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;
 	u16				destid;
 	/* low 64-bits of 66-bit RIO address */
 	u64				rio_addr;
 	/* upper 2-bits of 66-bit RIO address */
 	u8				rio_addr_u;
-	u32				bcount;
-	bool				interrupt;
+	enum dma_rtype			rtype;
 	struct list_head		desc_node;
-	struct list_head		tx_list;
+	struct scatterlist		*sg;
+	unsigned int			sg_len;
+	enum dma_status			status;
 };
 
 struct tsi721_bdma_chan {
 	int		id;
 	void __iomem	*regs;
-	int		bd_num;		/* number of buffer descriptors */
+	int		bd_num;		/* number of HW buffer descriptors */
 	void		*bd_base;	/* start of DMA descriptors */
 	dma_addr_t	bd_phys;
 	void		*sts_base;	/* start of DMA BD status FIFO */
@@ -680,7 +679,6 @@ struct tsi721_bdma_chan {
 	struct list_head	active_list;
 	struct list_head	queue;
 	struct list_head	free_list;
-	dma_cookie_t		completed_cookie;
 	struct tasklet_struct	tasklet;
 	bool			active;
 };
diff --git a/drivers/rapidio/devices/tsi721_dma.c b/drivers/rapidio/devices/tsi721_dma.c
index 44341dc5b148..f64c5decb747 100644
--- a/drivers/rapidio/devices/tsi721_dma.c
+++ b/drivers/rapidio/devices/tsi721_dma.c
@@ -1,7 +1,7 @@
 /*
  * DMA Engine support for Tsi721 PCIExpress-to-SRIO bridge
  *
- * Copyright 2011 Integrated Device Technology, Inc.
+ * Copyright (c) 2011-2014 Integrated Device Technology, Inc.
  * Alexandre Bounine <alexandre.bounine@idt.com>
  *
  * This program is free software; you can redistribute it and/or modify it
@@ -14,9 +14,8 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ * The full GNU General Public License is included in this distribution in the
+ * file called COPYING.
  */
 
 #include <linux/io.h>
@@ -32,9 +31,22 @@
 #include <linux/interrupt.h>
 #include <linux/kfifo.h>
 #include <linux/delay.h>
+#include "../../dma/dmaengine.h"
 
 #include "tsi721.h"
 
+#define TSI721_DMA_TX_QUEUE_SZ	16	/* number of transaction descriptors */
+
+#ifdef CONFIG_PCI_MSI
+static irqreturn_t tsi721_bdma_msix(int irq, void *ptr);
+#endif
+static int tsi721_submit_sg(struct tsi721_tx_desc *desc);
+
+static unsigned int dma_desc_per_channel = 128;
+module_param(dma_desc_per_channel, uint, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(dma_desc_per_channel,
+		 "Number of DMA descriptors per channel (default: 128)");
+
 static inline struct tsi721_bdma_chan *to_tsi721_chan(struct dma_chan *chan)
 {
 	return container_of(chan, struct tsi721_bdma_chan, dchan);
@@ -59,7 +71,7 @@ struct tsi721_tx_desc *tsi721_dma_first_active(
 				struct tsi721_tx_desc, desc_node);
 }
 
-static int tsi721_bdma_ch_init(struct tsi721_bdma_chan *bdma_chan)
+static int tsi721_bdma_ch_init(struct tsi721_bdma_chan *bdma_chan, int bd_num)
 {
 	struct tsi721_dma_desc *bd_ptr;
 	struct device *dev = bdma_chan->dchan.device->dev;
@@ -67,17 +79,23 @@ static int tsi721_bdma_ch_init(struct tsi721_bdma_chan *bdma_chan)
 	dma_addr_t	bd_phys;
 	dma_addr_t	sts_phys;
 	int		sts_size;
-	int		bd_num = bdma_chan->bd_num;
+#ifdef CONFIG_PCI_MSI
+	struct tsi721_device *priv = to_tsi721(bdma_chan->dchan.device);
+#endif
 
 	dev_dbg(dev, "Init Block DMA Engine, CH%d\n", bdma_chan->id);
 
-	/* Allocate space for DMA descriptors */
+	/*
+	 * Allocate space for DMA descriptors
+	 * (add an extra element for link descriptor)
+	 */
 	bd_ptr = dma_zalloc_coherent(dev,
-				bd_num * sizeof(struct tsi721_dma_desc),
+				(bd_num + 1) * sizeof(struct tsi721_dma_desc),
 				&bd_phys, GFP_KERNEL);
 	if (!bd_ptr)
 		return -ENOMEM;
 
+	bdma_chan->bd_num = bd_num;
 	bdma_chan->bd_phys = bd_phys;
 	bdma_chan->bd_base = bd_ptr;
 
@@ -85,8 +103,8 @@ static int tsi721_bdma_ch_init(struct tsi721_bdma_chan *bdma_chan)
 		bd_ptr, (unsigned long long)bd_phys);
 
 	/* Allocate space for descriptor status FIFO */
-	sts_size = (bd_num >= TSI721_DMA_MINSTSSZ) ?
-					bd_num : TSI721_DMA_MINSTSSZ;
+	sts_size = ((bd_num + 1) >= TSI721_DMA_MINSTSSZ) ?
+					(bd_num + 1) : TSI721_DMA_MINSTSSZ;
 	sts_size = roundup_pow_of_two(sts_size);
 	sts_ptr = dma_zalloc_coherent(dev,
 				     sts_size * sizeof(struct tsi721_dma_sts),
@@ -94,7 +112,7 @@ static int tsi721_bdma_ch_init(struct tsi721_bdma_chan *bdma_chan)
 	if (!sts_ptr) {
 		/* Free space allocated for DMA descriptors */
 		dma_free_coherent(dev,
-				  bd_num * sizeof(struct tsi721_dma_desc),
+				  (bd_num + 1) * sizeof(struct tsi721_dma_desc),
 				  bd_ptr, bd_phys);
 		bdma_chan->bd_base = NULL;
 		return -ENOMEM;
@@ -108,11 +126,11 @@ static int tsi721_bdma_ch_init(struct tsi721_bdma_chan *bdma_chan)
 		"desc status FIFO @ %p (phys = %llx) size=0x%x\n",
 		sts_ptr, (unsigned long long)sts_phys, sts_size);
 
-	/* Initialize DMA descriptors ring */
-	bd_ptr[bd_num - 1].type_id = cpu_to_le32(DTYPE3 << 29);
-	bd_ptr[bd_num - 1].next_lo = cpu_to_le32((u64)bd_phys &
+	/* Initialize DMA descriptors ring using added link descriptor */
+	bd_ptr[bd_num].type_id = cpu_to_le32(DTYPE3 << 29);
+	bd_ptr[bd_num].next_lo = cpu_to_le32((u64)bd_phys &
 						 TSI721_DMAC_DPTRL_MASK);
-	bd_ptr[bd_num - 1].next_hi = cpu_to_le32((u64)bd_phys >> 32);
+	bd_ptr[bd_num].next_hi = cpu_to_le32((u64)bd_phys >> 32);
 
 	/* Setup DMA descriptor pointers */
 	iowrite32(((u64)bd_phys >> 32),
@@ -134,6 +152,55 @@ static int tsi721_bdma_ch_init(struct tsi721_bdma_chan *bdma_chan)
 
 	ioread32(bdma_chan->regs + TSI721_DMAC_INT);
 
+#ifdef CONFIG_PCI_MSI
+	/* Request interrupt service if we are in MSI-X mode */
+	if (priv->flags & TSI721_USING_MSIX) {
+		int rc, idx;
+
+		idx = TSI721_VECT_DMA0_DONE + bdma_chan->id;
+
+		rc = request_irq(priv->msix[idx].vector, tsi721_bdma_msix, 0,
+				 priv->msix[idx].irq_name, (void *)bdma_chan);
+
+		if (rc) {
+			dev_dbg(dev, "Unable to get MSI-X for BDMA%d-DONE\n",
+				bdma_chan->id);
+			goto err_out;
+		}
+
+		idx = TSI721_VECT_DMA0_INT + bdma_chan->id;
+
+		rc = request_irq(priv->msix[idx].vector, tsi721_bdma_msix, 0,
+				priv->msix[idx].irq_name, (void *)bdma_chan);
+
+		if (rc)	{
+			dev_dbg(dev, "Unable to get MSI-X for BDMA%d-INT\n",
+				bdma_chan->id);
+			free_irq(
+				priv->msix[TSI721_VECT_DMA0_DONE +
+					    bdma_chan->id].vector,
+				(void *)bdma_chan);
+		}
+
+err_out:
+		if (rc) {
+			/* Free space allocated for DMA descriptors */
+			dma_free_coherent(dev,
+				(bd_num + 1) * sizeof(struct tsi721_dma_desc),
+				bd_ptr, bd_phys);
+			bdma_chan->bd_base = NULL;
+
+			/* Free space allocated for status descriptors */
+			dma_free_coherent(dev,
+				sts_size * sizeof(struct tsi721_dma_sts),
+				sts_ptr, sts_phys);
+			bdma_chan->sts_base = NULL;
+
+			return -EIO;
+		}
+	}
+#endif /* CONFIG_PCI_MSI */
+
 	/* Toggle DMA channel initialization */
 	iowrite32(TSI721_DMAC_CTL_INIT,	bdma_chan->regs + TSI721_DMAC_CTL);
 	ioread32(bdma_chan->regs + TSI721_DMAC_CTL);
@@ -147,6 +214,9 @@ static int tsi721_bdma_ch_init(struct tsi721_bdma_chan *bdma_chan)
 static int tsi721_bdma_ch_free(struct tsi721_bdma_chan *bdma_chan)
 {
 	u32 ch_stat;
+#ifdef CONFIG_PCI_MSI
+	struct tsi721_device *priv = to_tsi721(bdma_chan->dchan.device);
+#endif
 
 	if (bdma_chan->bd_base == NULL)
 		return 0;
@@ -159,9 +229,18 @@ static int tsi721_bdma_ch_free(struct tsi721_bdma_chan *bdma_chan)
 	/* Put DMA channel into init state */
 	iowrite32(TSI721_DMAC_CTL_INIT,	bdma_chan->regs + TSI721_DMAC_CTL);
 
+#ifdef CONFIG_PCI_MSI
+	if (priv->flags & TSI721_USING_MSIX) {
+		free_irq(priv->msix[TSI721_VECT_DMA0_DONE +
+				    bdma_chan->id].vector, (void *)bdma_chan);
+		free_irq(priv->msix[TSI721_VECT_DMA0_INT +
+				    bdma_chan->id].vector, (void *)bdma_chan);
+	}
+#endif /* CONFIG_PCI_MSI */
+
 	/* Free space allocated for DMA descriptors */
 	dma_free_coherent(bdma_chan->dchan.device->dev,
-		bdma_chan->bd_num * sizeof(struct tsi721_dma_desc),
+		(bdma_chan->bd_num + 1) * sizeof(struct tsi721_dma_desc),
 		bdma_chan->bd_base, bdma_chan->bd_phys);
 	bdma_chan->bd_base = NULL;
 
@@ -243,8 +322,8 @@ static void tsi721_start_dma(struct tsi721_bdma_chan *bdma_chan)
 	}
 
 	dev_dbg(bdma_chan->dchan.device->dev,
-		"tx_chan: %p, chan: %d, regs: %p\n",
-		bdma_chan, bdma_chan->dchan.chan_id, bdma_chan->regs);
+		"%s: chan_%d (wrc=%d)\n", __func__, bdma_chan->id,
+		bdma_chan->wr_count_next);
 
 	iowrite32(bdma_chan->wr_count_next,
 		bdma_chan->regs + TSI721_DMAC_DWRCNT);
@@ -253,72 +332,19 @@ static void tsi721_start_dma(struct tsi721_bdma_chan *bdma_chan)
 	bdma_chan->wr_count = bdma_chan->wr_count_next;
 }
 
-static void tsi721_desc_put(struct tsi721_bdma_chan *bdma_chan,
-			    struct tsi721_tx_desc *desc)
-{
-	dev_dbg(bdma_chan->dchan.device->dev,
-		"Put desc: %p into free list\n", desc);
-
-	if (desc) {
-		spin_lock_bh(&bdma_chan->lock);
-		list_splice_init(&desc->tx_list, &bdma_chan->free_list);
-		list_add(&desc->desc_node, &bdma_chan->free_list);
-		bdma_chan->wr_count_next = bdma_chan->wr_count;
-		spin_unlock_bh(&bdma_chan->lock);
-	}
-}
-
-static
-struct tsi721_tx_desc *tsi721_desc_get(struct tsi721_bdma_chan *bdma_chan)
-{
-	struct tsi721_tx_desc *tx_desc, *_tx_desc;
-	struct tsi721_tx_desc *ret = NULL;
-	int i;
-
-	spin_lock_bh(&bdma_chan->lock);
-	list_for_each_entry_safe(tx_desc, _tx_desc,
-				 &bdma_chan->free_list, desc_node) {
-		if (async_tx_test_ack(&tx_desc->txd)) {
-			list_del(&tx_desc->desc_node);
-			ret = tx_desc;
-			break;
-		}
-		dev_dbg(bdma_chan->dchan.device->dev,
-			"desc %p not ACKed\n", tx_desc);
-	}
-
-	if (ret == NULL) {
-		dev_dbg(bdma_chan->dchan.device->dev,
-			"%s: unable to obtain tx descriptor\n", __func__);
-		goto err_out;
-	}
-
-	i = bdma_chan->wr_count_next % bdma_chan->bd_num;
-	if (i == bdma_chan->bd_num - 1) {
-		i = 0;
-		bdma_chan->wr_count_next++; /* skip link descriptor */
-	}
-
-	bdma_chan->wr_count_next++;
-	tx_desc->txd.phys = bdma_chan->bd_phys +
-				i * sizeof(struct tsi721_dma_desc);
-	tx_desc->hw_desc = &((struct tsi721_dma_desc *)bdma_chan->bd_base)[i];
-err_out:
-	spin_unlock_bh(&bdma_chan->lock);
-
-	return ret;
-}
-
 static int
-tsi721_desc_fill_init(struct tsi721_tx_desc *desc, struct scatterlist *sg,
-	enum dma_rtype rtype, u32 sys_size)
+tsi721_desc_fill_init(struct tsi721_tx_desc *desc,
+		      struct tsi721_dma_desc *bd_ptr,
+		      struct scatterlist *sg, u32 sys_size)
 {
-	struct tsi721_dma_desc *bd_ptr = desc->hw_desc;
 	u64 rio_addr;
 
+	if (bd_ptr == NULL)
+		return -EINVAL;
+
 	/* Initialize DMA descriptor */
 	bd_ptr->type_id = cpu_to_le32((DTYPE1 << 29) |
-					(rtype << 19) | desc->destid);
+				      (desc->rtype << 19) | desc->destid);
 	bd_ptr->bcount = cpu_to_le32(((desc->rio_addr & 0x3) << 30) |
 				     (sys_size << 26));
 	rio_addr = (desc->rio_addr >> 2) |
@@ -335,51 +361,32 @@ tsi721_desc_fill_init(struct tsi721_tx_desc *desc, struct scatterlist *sg,
 }
 
 static int
-tsi721_desc_fill_end(struct tsi721_tx_desc *desc)
+tsi721_desc_fill_end(struct tsi721_dma_desc *bd_ptr, u32 bcount, bool interrupt)
 {
-	struct tsi721_dma_desc *bd_ptr = desc->hw_desc;
+	if (bd_ptr == NULL)
+		return -EINVAL;
 
 	/* Update DMA descriptor */
-	if (desc->interrupt)
+	if (interrupt)
 		bd_ptr->type_id |= cpu_to_le32(TSI721_DMAD_IOF);
-	bd_ptr->bcount |= cpu_to_le32(desc->bcount & TSI721_DMAD_BCOUNT1);
+	bd_ptr->bcount |= cpu_to_le32(bcount & TSI721_DMAD_BCOUNT1);
 
 	return 0;
 }
 
-
-static void tsi721_dma_chain_complete(struct tsi721_bdma_chan *bdma_chan,
-				      struct tsi721_tx_desc *desc)
+static void tsi721_dma_tx_err(struct tsi721_bdma_chan *bdma_chan,
+			      struct tsi721_tx_desc *desc)
 {
 	struct dma_async_tx_descriptor *txd = &desc->txd;
 	dma_async_tx_callback callback = txd->callback;
 	void *param = txd->callback_param;
 
-	list_splice_init(&desc->tx_list, &bdma_chan->free_list);
 	list_move(&desc->desc_node, &bdma_chan->free_list);
-	bdma_chan->completed_cookie = txd->cookie;
 
 	if (callback)
 		callback(param);
 }
 
-static void tsi721_dma_complete_all(struct tsi721_bdma_chan *bdma_chan)
-{
-	struct tsi721_tx_desc *desc, *_d;
-	LIST_HEAD(list);
-
-	BUG_ON(!tsi721_dma_is_idle(bdma_chan));
-
-	if (!list_empty(&bdma_chan->queue))
-		tsi721_start_dma(bdma_chan);
-
-	list_splice_init(&bdma_chan->active_list, &list);
-	list_splice_init(&bdma_chan->queue, &bdma_chan->active_list);
-
-	list_for_each_entry_safe(desc, _d, &list, desc_node)
-		tsi721_dma_chain_complete(bdma_chan, desc);
-}
-
 static void tsi721_clr_stat(struct tsi721_bdma_chan *bdma_chan)
 {
 	u32 srd_ptr;
@@ -403,20 +410,159 @@ static void tsi721_clr_stat(struct tsi721_bdma_chan *bdma_chan)
 	bdma_chan->sts_rdptr = srd_ptr;
 }
 
+/* Must be called with the channel spinlock held */
+static int tsi721_submit_sg(struct tsi721_tx_desc *desc)
+{
+	struct dma_chan *dchan = desc->txd.chan;
+	struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(dchan);
+	u32 sys_size;
+	u64 rio_addr;
+	dma_addr_t next_addr;
+	u32 bcount;
+	struct scatterlist *sg;
+	unsigned int i;
+	int err = 0;
+	struct tsi721_dma_desc *bd_ptr = NULL;
+	u32 idx, rd_idx;
+	u32 add_count = 0;
+
+	if (!tsi721_dma_is_idle(bdma_chan)) {
+		dev_err(bdma_chan->dchan.device->dev,
+			"BUG: Attempt to use non-idle channel\n");
+		return -EIO;
+	}
+
+	/*
+	 * Fill DMA channel's hardware buffer descriptors.
+	 * (NOTE: RapidIO destination address is limited to 64 bits for now)
+	 */
+	rio_addr = desc->rio_addr;
+	next_addr = -1;
+	bcount = 0;
+	sys_size = dma_to_mport(bdma_chan->dchan.device)->sys_size;
+
+	rd_idx = ioread32(bdma_chan->regs + TSI721_DMAC_DRDCNT);
+	rd_idx %= (bdma_chan->bd_num + 1);
+
+	idx = bdma_chan->wr_count_next % (bdma_chan->bd_num + 1);
+	if (idx == bdma_chan->bd_num) {
+		/* wrap around link descriptor */
+		idx = 0;
+		add_count++;
+	}
+
+	dev_dbg(dchan->device->dev, "%s: BD ring status: rdi=%d wri=%d\n",
+		__func__, rd_idx, idx);
+
+	for_each_sg(desc->sg, sg, desc->sg_len, i) {
+
+		dev_dbg(dchan->device->dev, "sg%d/%d addr: 0x%llx len: %d\n",
+			i, desc->sg_len,
+			(unsigned long long)sg_dma_address(sg), sg_dma_len(sg));
+
+		if (sg_dma_len(sg) > TSI721_BDMA_MAX_BCOUNT) {
+			dev_err(dchan->device->dev,
+				"%s: SG entry %d is too large\n", __func__, i);
+			err = -EINVAL;
+			break;
+		}
+
+		/*
+		 * If this sg entry forms contiguous block with previous one,
+		 * try to merge it into existing DMA descriptor
+		 */
+		if (next_addr == sg_dma_address(sg) &&
+		    bcount + sg_dma_len(sg) <= TSI721_BDMA_MAX_BCOUNT) {
+			/* Adjust byte count of the descriptor */
+			bcount += sg_dma_len(sg);
+			goto entry_done;
+		} else if (next_addr != -1) {
+			/* Finalize descriptor using total byte count value */
+			tsi721_desc_fill_end(bd_ptr, bcount, 0);
+			dev_dbg(dchan->device->dev,
+				"%s: prev desc final len: %d\n",
+				__func__, bcount);
+		}
+
+		desc->rio_addr = rio_addr;
+
+		if (i && idx == rd_idx) {
+			dev_dbg(dchan->device->dev,
+				"%s: HW descriptor ring is full @ %d\n",
+				__func__, i);
+			desc->sg = sg;
+			desc->sg_len -= i;
+			break;
+		}
+
+		bd_ptr = &((struct tsi721_dma_desc *)bdma_chan->bd_base)[idx];
+		err = tsi721_desc_fill_init(desc, bd_ptr, sg, sys_size);
+		if (err) {
+			dev_err(dchan->device->dev,
+				"Failed to build desc: err=%d\n", err);
+			break;
+		}
+
+		dev_dbg(dchan->device->dev, "bd_ptr = %p did=%d raddr=0x%llx\n",
+			bd_ptr, desc->destid, desc->rio_addr);
+
+		next_addr = sg_dma_address(sg);
+		bcount = sg_dma_len(sg);
+
+		add_count++;
+		if (++idx == bdma_chan->bd_num) {
+			/* wrap around link descriptor */
+			idx = 0;
+			add_count++;
+		}
+
+entry_done:
+		if (sg_is_last(sg)) {
+			tsi721_desc_fill_end(bd_ptr, bcount, 0);
+			dev_dbg(dchan->device->dev, "%s: last desc final len: %d\n",
+				__func__, bcount);
+			desc->sg_len = 0;
+		} else {
+			rio_addr += sg_dma_len(sg);
+			next_addr += sg_dma_len(sg);
+		}
+	}
+
+	if (!err)
+		bdma_chan->wr_count_next += add_count;
+
+	return err;
+}
+
 static void tsi721_advance_work(struct tsi721_bdma_chan *bdma_chan)
 {
-	if (list_empty(&bdma_chan->active_list) ||
-		list_is_singular(&bdma_chan->active_list)) {
-		dev_dbg(bdma_chan->dchan.device->dev,
-			"%s: Active_list empty\n", __func__);
-		tsi721_dma_complete_all(bdma_chan);
-	} else {
-		dev_dbg(bdma_chan->dchan.device->dev,
-			"%s: Active_list NOT empty\n", __func__);
-		tsi721_dma_chain_complete(bdma_chan,
-					tsi721_dma_first_active(bdma_chan));
-		tsi721_start_dma(bdma_chan);
+	struct tsi721_tx_desc *desc;
+	int err;
+
+	dev_dbg(bdma_chan->dchan.device->dev, "%s: Enter\n", __func__);
+
+	/*
+	 * If there are any new transactions in the queue add them
+	 * into the processing list
+	 */
+	if (!list_empty(&bdma_chan->queue))
+		list_splice_init(&bdma_chan->queue, &bdma_chan->active_list);
+
+	/* Start new transaction (if available) */
+	if (!list_empty(&bdma_chan->active_list)) {
+		desc = tsi721_dma_first_active(bdma_chan);
+		err = tsi721_submit_sg(desc);
+		if (!err)
+			tsi721_start_dma(bdma_chan);
+		else {
+			tsi721_dma_tx_err(bdma_chan, desc);
+			dev_dbg(bdma_chan->dchan.device->dev,
+				"ERR: tsi721_submit_sg failed with err=%d\n",
+				err);
+		}
 	}
+
+	dev_dbg(bdma_chan->dchan.device->dev, "%s: Exit\n", __func__);
 }
 
 static void tsi721_dma_tasklet(unsigned long data)
@@ -444,8 +590,29 @@ static void tsi721_dma_tasklet(unsigned long data)
 	}
 
 	if (dmac_int & (TSI721_DMAC_INT_DONE | TSI721_DMAC_INT_IOFDONE)) {
+		struct tsi721_tx_desc *desc;
+
 		tsi721_clr_stat(bdma_chan);
 		spin_lock(&bdma_chan->lock);
+		desc = tsi721_dma_first_active(bdma_chan);
+
+		if (desc->sg_len == 0) {
+			dma_async_tx_callback callback = NULL;
+			void *param = NULL;
+
+			desc->status = DMA_COMPLETE;
+			dma_cookie_complete(&desc->txd);
+			if (desc->txd.flags & DMA_PREP_INTERRUPT) {
+				callback = desc->txd.callback;
+				param = desc->txd.callback_param;
+			}
+			list_move(&desc->desc_node, &bdma_chan->free_list);
+			spin_unlock(&bdma_chan->lock);
+			if (callback)
+				callback(param);
+			spin_lock(&bdma_chan->lock);
+		}
+
 		tsi721_advance_work(bdma_chan);
 		spin_unlock(&bdma_chan->lock);
 	}
@@ -460,21 +627,24 @@ static dma_cookie_t tsi721_tx_submit(struct dma_async_tx_descriptor *txd)
 	struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(txd->chan);
 	dma_cookie_t cookie;
 
-	spin_lock_bh(&bdma_chan->lock);
+	/* Check if the descriptor is detached from any lists */
+	if (!list_empty(&desc->desc_node)) {
+		dev_err(bdma_chan->dchan.device->dev,
+			"%s: wrong state of descriptor %p\n", __func__, txd);
+		return -EIO;
+	}
 
-	cookie = txd->chan->cookie;
-	if (++cookie < 0)
-		cookie = 1;
-	txd->chan->cookie = cookie;
-	txd->cookie = cookie;
+	spin_lock_bh(&bdma_chan->lock);
 
-	if (list_empty(&bdma_chan->active_list)) {
-		list_add_tail(&desc->desc_node, &bdma_chan->active_list);
-		tsi721_start_dma(bdma_chan);
-	} else {
-		list_add_tail(&desc->desc_node, &bdma_chan->queue);
+	if (!bdma_chan->active) {
+		spin_unlock_bh(&bdma_chan->lock);
+		return -ENODEV;
 	}
 
+	cookie = dma_cookie_assign(txd);
+	desc->status = DMA_IN_PROGRESS;
+	list_add_tail(&desc->desc_node, &bdma_chan->queue);
+
 	spin_unlock_bh(&bdma_chan->lock);
 	return cookie;
 }
@@ -482,115 +652,52 @@ static dma_cookie_t tsi721_tx_submit(struct dma_async_tx_descriptor *txd)
 static int tsi721_alloc_chan_resources(struct dma_chan *dchan)
 {
 	struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(dchan);
-#ifdef CONFIG_PCI_MSI
-	struct tsi721_device *priv = to_tsi721(dchan->device);
-#endif
 	struct tsi721_tx_desc *desc = NULL;
-	LIST_HEAD(tmp_list);
 	int i;
-	int rc;
+
+	dev_dbg(dchan->device->dev, "%s: for channel %d\n",
+		__func__, bdma_chan->id);
 
 	if (bdma_chan->bd_base)
-		return bdma_chan->bd_num - 1;
+		return TSI721_DMA_TX_QUEUE_SZ;
 
 	/* Initialize BDMA channel */
-	if (tsi721_bdma_ch_init(bdma_chan)) {
+	if (tsi721_bdma_ch_init(bdma_chan, dma_desc_per_channel)) {
 		dev_err(dchan->device->dev, "Unable to initialize data DMA"
 			" channel %d, aborting\n", bdma_chan->id);
-		return -ENOMEM;
+		return -ENODEV;
 	}
 
-	/* Alocate matching number of logical descriptors */
-	desc = kcalloc((bdma_chan->bd_num - 1), sizeof(struct tsi721_tx_desc),
+	/* Allocate queue of transaction descriptors */
+	desc = kcalloc(TSI721_DMA_TX_QUEUE_SZ, sizeof(struct tsi721_tx_desc),
 			GFP_KERNEL);
 	if (!desc) {
 		dev_err(dchan->device->dev,
 			"Failed to allocate logical descriptors\n");
-		rc = -ENOMEM;
-		goto err_out;
+		tsi721_bdma_ch_free(bdma_chan);
+		return -ENOMEM;
 	}
 
 	bdma_chan->tx_desc = desc;
 
-	for (i = 0; i < bdma_chan->bd_num - 1; i++) {
+	for (i = 0; i < TSI721_DMA_TX_QUEUE_SZ; i++) {
 		dma_async_tx_descriptor_init(&desc[i].txd, dchan);
 		desc[i].txd.tx_submit = tsi721_tx_submit;
 		desc[i].txd.flags = DMA_CTRL_ACK;
-		INIT_LIST_HEAD(&desc[i].tx_list);
-		list_add_tail(&desc[i].desc_node, &tmp_list);
+		list_add(&desc[i].desc_node, &bdma_chan->free_list);
 	}
 
-	spin_lock_bh(&bdma_chan->lock);
-	list_splice(&tmp_list, &bdma_chan->free_list);
-	bdma_chan->completed_cookie = dchan->cookie = 1;
-	spin_unlock_bh(&bdma_chan->lock);
-
-#ifdef CONFIG_PCI_MSI
-	if (priv->flags & TSI721_USING_MSIX) {
-		/* Request interrupt service if we are in MSI-X mode */
-		rc = request_irq(
-			priv->msix[TSI721_VECT_DMA0_DONE +
-				   bdma_chan->id].vector,
-			tsi721_bdma_msix, 0,
-			priv->msix[TSI721_VECT_DMA0_DONE +
-				   bdma_chan->id].irq_name,
-			(void *)bdma_chan);
-
-		if (rc) {
-			dev_dbg(dchan->device->dev,
-				"Unable to allocate MSI-X interrupt for "
-				"BDMA%d-DONE\n", bdma_chan->id);
-			goto err_out;
-		}
-
-		rc = request_irq(priv->msix[TSI721_VECT_DMA0_INT +
-					    bdma_chan->id].vector,
-				tsi721_bdma_msix, 0,
-				priv->msix[TSI721_VECT_DMA0_INT +
-					   bdma_chan->id].irq_name,
-				(void *)bdma_chan);
-
-		if (rc)	{
-			dev_dbg(dchan->device->dev,
-				"Unable to allocate MSI-X interrupt for "
-				"BDMA%d-INT\n", bdma_chan->id);
-			free_irq(
-				priv->msix[TSI721_VECT_DMA0_DONE +
-					   bdma_chan->id].vector,
-				(void *)bdma_chan);
-			rc = -EIO;
-			goto err_out;
-		}
-	}
-#endif /* CONFIG_PCI_MSI */
+	dma_cookie_init(dchan);
 
 	bdma_chan->active = true;
 	tsi721_bdma_interrupt_enable(bdma_chan, 1);
 
-	return bdma_chan->bd_num - 1;
-
-err_out:
-	kfree(desc);
-	tsi721_bdma_ch_free(bdma_chan);
-	return rc;
+	return TSI721_DMA_TX_QUEUE_SZ;
 }
 
-static void tsi721_free_chan_resources(struct dma_chan *dchan)
+static void tsi721_sync_dma_irq(struct tsi721_bdma_chan *bdma_chan)
 {
-	struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(dchan);
-	struct tsi721_device *priv = to_tsi721(dchan->device);
-	LIST_HEAD(list);
-
-	dev_dbg(dchan->device->dev, "%s: Entry\n", __func__);
-
-	if (bdma_chan->bd_base == NULL)
-		return;
-
-	BUG_ON(!list_empty(&bdma_chan->active_list));
-	BUG_ON(!list_empty(&bdma_chan->queue));
-
-	tsi721_bdma_interrupt_enable(bdma_chan, 0);
-	bdma_chan->active = false;
+	struct tsi721_device *priv = to_tsi721(bdma_chan->dchan.device);
 
 #ifdef CONFIG_PCI_MSI
 	if (priv->flags & TSI721_USING_MSIX) {
@@ -601,64 +708,48 @@ static void tsi721_free_chan_resources(struct dma_chan *dchan)
 	} else
 #endif
 	synchronize_irq(priv->pdev->irq);
+}
 
-	tasklet_kill(&bdma_chan->tasklet);
+static void tsi721_free_chan_resources(struct dma_chan *dchan)
+{
+	struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(dchan);
 
-	spin_lock_bh(&bdma_chan->lock);
-	list_splice_init(&bdma_chan->free_list, &list);
-	spin_unlock_bh(&bdma_chan->lock);
+	dev_dbg(dchan->device->dev, "%s: for channel %d\n",
+		__func__, bdma_chan->id);
 
-#ifdef CONFIG_PCI_MSI
-	if (priv->flags & TSI721_USING_MSIX) {
-		free_irq(priv->msix[TSI721_VECT_DMA0_DONE +
-				    bdma_chan->id].vector, (void *)bdma_chan);
-		free_irq(priv->msix[TSI721_VECT_DMA0_INT +
-				    bdma_chan->id].vector, (void *)bdma_chan);
-	}
-#endif /* CONFIG_PCI_MSI */
+	if (bdma_chan->bd_base == NULL)
+		return;
 
-	tsi721_bdma_ch_free(bdma_chan);
+	BUG_ON(!list_empty(&bdma_chan->active_list));
+	BUG_ON(!list_empty(&bdma_chan->queue));
+
+	tsi721_bdma_interrupt_enable(bdma_chan, 0);
+	bdma_chan->active = false;
+	tsi721_sync_dma_irq(bdma_chan);
+	tasklet_kill(&bdma_chan->tasklet);
+	INIT_LIST_HEAD(&bdma_chan->free_list);
 	kfree(bdma_chan->tx_desc);
+	tsi721_bdma_ch_free(bdma_chan);
 }
 
 static
 enum dma_status tsi721_tx_status(struct dma_chan *dchan, dma_cookie_t cookie,
 				 struct dma_tx_state *txstate)
 {
-	struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(dchan);
-	dma_cookie_t		last_used;
-	dma_cookie_t		last_completed;
-	int			ret;
-
-	spin_lock_bh(&bdma_chan->lock);
-	last_completed = bdma_chan->completed_cookie;
-	last_used = dchan->cookie;
-	spin_unlock_bh(&bdma_chan->lock);
-
-	ret = dma_async_is_complete(cookie, last_completed, last_used);
-
-	dma_set_tx_state(txstate, last_completed, last_used, 0);
-
-	dev_dbg(dchan->device->dev,
-		"%s: exit, ret: %d, last_completed: %d, last_used: %d\n",
-		__func__, ret, last_completed, last_used);
-
-	return ret;
+	return dma_cookie_status(dchan, cookie, txstate);
 }
 
 static void tsi721_issue_pending(struct dma_chan *dchan)
 {
 	struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(dchan);
 
-	dev_dbg(dchan->device->dev, "%s: Entry\n", __func__);
+	dev_dbg(dchan->device->dev, "%s: Enter\n", __func__);
 
-	if (tsi721_dma_is_idle(bdma_chan)) {
+	if (tsi721_dma_is_idle(bdma_chan) && bdma_chan->active) {
 		spin_lock_bh(&bdma_chan->lock);
 		tsi721_advance_work(bdma_chan);
 		spin_unlock_bh(&bdma_chan->lock);
-	} else
-		dev_dbg(dchan->device->dev,
-			"%s: DMA channel still busy\n", __func__);
+	}
 }
 
 static
@@ -668,21 +759,19 @@ struct dma_async_tx_descriptor *tsi721_prep_rio_sg(struct dma_chan *dchan,
 			void *tinfo)
 {
 	struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(dchan);
-	struct tsi721_tx_desc *desc = NULL;
-	struct tsi721_tx_desc *first = NULL;
-	struct scatterlist *sg;
+	struct tsi721_tx_desc *desc, *_d;
 	struct rio_dma_ext *rext = tinfo;
-	u64 rio_addr = rext->rio_addr; /* limited to 64-bit rio_addr for now */
-	unsigned int i;
-	u32 sys_size = dma_to_mport(dchan->device)->sys_size;
 	enum dma_rtype rtype;
-	dma_addr_t next_addr = -1;
+	struct dma_async_tx_descriptor *txd = NULL;
 
 	if (!sgl || !sg_len) {
 		dev_err(dchan->device->dev, "%s: No SG list\n", __func__);
 		return NULL;
 	}
 
+	dev_dbg(dchan->device->dev, "%s: %s\n", __func__,
+		(dir == DMA_DEV_TO_MEM)?"READ":"WRITE");
+
 	if (dir == DMA_DEV_TO_MEM)
 		rtype = NREAD;
 	else if (dir == DMA_MEM_TO_DEV) {
@@ -704,97 +793,26 @@ struct dma_async_tx_descriptor *tsi721_prep_rio_sg(struct dma_chan *dchan,
 		return NULL;
 	}
 
-	for_each_sg(sgl, sg, sg_len, i) {
-		int err;
-
-		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,
-				"%s: Failed to get new descriptor for SG %d\n",
-				__func__, i);
-			goto err_desc_put;
-		}
-
-		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_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_put;
-		}
-
-		next_addr = sg_dma_address(sg);
-
-		if (!first)
-			first = desc;
-		else
-			list_add_tail(&desc->desc_node, &first->tx_list);
+	spin_lock_bh(&bdma_chan->lock);
 
-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);
+	list_for_each_entry_safe(desc, _d, &bdma_chan->free_list, desc_node) {
+		if (async_tx_test_ack(&desc->txd)) {
+			list_del_init(&desc->desc_node);
+			desc->destid = rext->destid;
+			desc->rio_addr = rext->rio_addr;
+			desc->rio_addr_u = 0;
+			desc->rtype = rtype;
+			desc->sg_len	= sg_len;
+			desc->sg	= sgl;
+			txd		= &desc->txd;
+			txd->flags	= flags;
+			break;
 		}
 	}
 
-	first->txd.cookie = -EBUSY;
-	desc->txd.flags = flags;
-
-	return &first->txd;
+	spin_unlock_bh(&bdma_chan->lock);
 
-err_desc_put:
-	tsi721_desc_put(bdma_chan, first);
-	return NULL;
+	return txd;
 }
 
 static int tsi721_device_control(struct dma_chan *dchan, enum dma_ctrl_cmd cmd,
@@ -802,23 +820,34 @@ static int tsi721_device_control(struct dma_chan *dchan, enum dma_ctrl_cmd cmd,
 {
 	struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(dchan);
 	struct tsi721_tx_desc *desc, *_d;
+	u32 dmac_int;
 	LIST_HEAD(list);
 
 	dev_dbg(dchan->device->dev, "%s: Entry\n", __func__);
 
 	if (cmd != DMA_TERMINATE_ALL)
-		return -ENXIO;
+		return -ENOSYS;
 
 	spin_lock_bh(&bdma_chan->lock);
 
-	/* make sure to stop the transfer */
-	iowrite32(TSI721_DMAC_CTL_SUSP, bdma_chan->regs + TSI721_DMAC_CTL);
+	bdma_chan->active = false;
+
+	if (!tsi721_dma_is_idle(bdma_chan)) {
+		/* make sure to stop the transfer */
+		iowrite32(TSI721_DMAC_CTL_SUSP,
+			  bdma_chan->regs + TSI721_DMAC_CTL);
+
+		/* Wait until DMA channel stops */
+		do {
+			dmac_int = ioread32(bdma_chan->regs + TSI721_DMAC_INT);
+		} while ((dmac_int & TSI721_DMAC_INT_SUSP) == 0);
+	}
 
 	list_splice_init(&bdma_chan->active_list, &list);
 	list_splice_init(&bdma_chan->queue, &list);
 
 	list_for_each_entry_safe(desc, _d, &list, desc_node)
-		tsi721_dma_chain_complete(bdma_chan, desc);
+		tsi721_dma_tx_err(bdma_chan, desc);
 
 	spin_unlock_bh(&bdma_chan->lock);
 
@@ -828,22 +857,18 @@ static int tsi721_device_control(struct dma_chan *dchan, enum dma_ctrl_cmd cmd,
 int tsi721_register_dma(struct tsi721_device *priv)
 {
 	int i;
-	int nr_channels = TSI721_DMA_MAXCH;
+	int nr_channels = 0;
 	int err;
 	struct rio_mport *mport = priv->mport;
 
-	mport->dma.dev = &priv->pdev->dev;
-	mport->dma.chancnt = nr_channels;
-
 	INIT_LIST_HEAD(&mport->dma.channels);
 
-	for (i = 0; i < nr_channels; i++) {
+	for (i = 0; i < TSI721_DMA_MAXCH; i++) {
 		struct tsi721_bdma_chan *bdma_chan = &priv->bdma[i];
 
 		if (i == TSI721_DMACH_MAINT)
 			continue;
 
-		bdma_chan->bd_num = TSI721_BDMA_BD_RING_SZ;
 		bdma_chan->regs = priv->regs + TSI721_DMAC_BASE(i);
 
 		bdma_chan->dchan.device = &mport->dma;
@@ -862,12 +887,15 @@ int tsi721_register_dma(struct tsi721_device *priv)
 			     (unsigned long)bdma_chan);
 		list_add_tail(&bdma_chan->dchan.device_node,
 			      &mport->dma.channels);
+		nr_channels++;
 	}
 
+	mport->dma.chancnt = nr_channels;
 	dma_cap_zero(mport->dma.cap_mask);
 	dma_cap_set(DMA_PRIVATE, mport->dma.cap_mask);
 	dma_cap_set(DMA_SLAVE, mport->dma.cap_mask);
 
+	mport->dma.dev = &priv->pdev->dev;
 	mport->dma.device_alloc_chan_resources = tsi721_alloc_chan_resources;
 	mport->dma.device_free_chan_resources = tsi721_free_chan_resources;
 	mport->dma.device_tx_status = tsi721_tx_status;
diff --git a/drivers/rapidio/rio.c b/drivers/rapidio/rio.c
index a54ba0494dd3..d7b87c64b7cd 100644
--- a/drivers/rapidio/rio.c
+++ b/drivers/rapidio/rio.c
@@ -1509,30 +1509,39 @@ EXPORT_SYMBOL_GPL(rio_route_clr_table);
 
 static bool rio_chan_filter(struct dma_chan *chan, void *arg)
 {
-	struct rio_dev *rdev = arg;
+	struct rio_mport *mport = arg;
 
 	/* Check that DMA device belongs to the right MPORT */
-	return (rdev->net->hport ==
-		container_of(chan->device, struct rio_mport, dma));
+	return mport == container_of(chan->device, struct rio_mport, dma);
 }
 
 /**
- * rio_request_dma - request RapidIO capable DMA channel that supports
- *   specified target RapidIO device.
- * @rdev: RIO device control structure
+ * rio_request_mport_dma - request RapidIO capable DMA channel associated
+ *   with specified local RapidIO mport device.
+ * @mport: RIO mport to perform DMA data transfers
  *
  * Returns pointer to allocated DMA channel or NULL if failed.
  */
-struct dma_chan *rio_request_dma(struct rio_dev *rdev)
+struct dma_chan *rio_request_mport_dma(struct rio_mport *mport)
 {
 	dma_cap_mask_t mask;
-	struct dma_chan *dchan;
 
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
-	dchan = dma_request_channel(mask, rio_chan_filter, rdev);
+	return dma_request_channel(mask, rio_chan_filter, mport);
+}
+EXPORT_SYMBOL_GPL(rio_request_mport_dma);
 
-	return dchan;
+/**
+ * rio_request_dma - request RapidIO capable DMA channel that supports
+ *   specified target RapidIO device.
+ * @rdev: RIO device associated with DMA transfer
+ *
+ * Returns pointer to allocated DMA channel or NULL if failed.
+ */
+struct dma_chan *rio_request_dma(struct rio_dev *rdev)
+{
+	return rio_request_mport_dma(rdev->net->hport);
 }
 EXPORT_SYMBOL_GPL(rio_request_dma);
 
@@ -1547,10 +1556,10 @@ void rio_release_dma(struct dma_chan *dchan)
 EXPORT_SYMBOL_GPL(rio_release_dma);
 
 /**
- * rio_dma_prep_slave_sg - RapidIO specific wrapper
+ * rio_dma_prep_xfer - RapidIO specific wrapper
  *   for device_prep_slave_sg callback defined by DMAENGINE.
- * @rdev: RIO device control structure
  * @dchan: DMA channel to configure
+ * @destid: target RapidIO device destination ID
  * @data: RIO specific data descriptor
  * @direction: DMA data transfer direction (TO or FROM the device)
  * @flags: dmaengine defined flags
@@ -1560,11 +1569,10 @@ EXPORT_SYMBOL_GPL(rio_release_dma);
  * target RIO device.
  * Returns pointer to DMA transaction descriptor or NULL if failed.
  */
-struct dma_async_tx_descriptor *rio_dma_prep_slave_sg(struct rio_dev *rdev,
-	struct dma_chan *dchan, struct rio_dma_data *data,
+struct dma_async_tx_descriptor *rio_dma_prep_xfer(struct dma_chan *dchan,
+	u16 destid, struct rio_dma_data *data,
 	enum dma_transfer_direction direction, unsigned long flags)
 {
-	struct dma_async_tx_descriptor *txd = NULL;
 	struct rio_dma_ext rio_ext;
 
 	if (dchan->device->device_prep_slave_sg == NULL) {
@@ -1572,15 +1580,35 @@ struct dma_async_tx_descriptor *rio_dma_prep_slave_sg(struct rio_dev *rdev,
 		return NULL;
 	}
 
-	rio_ext.destid = rdev->destid;
+	rio_ext.destid = destid;
 	rio_ext.rio_addr_u = data->rio_addr_u;
 	rio_ext.rio_addr = data->rio_addr;
 	rio_ext.wr_type = data->wr_type;
 
-	txd = dmaengine_prep_rio_sg(dchan, data->sg, data->sg_len,
-					direction, flags, &rio_ext);
+	return dmaengine_prep_rio_sg(dchan, data->sg, data->sg_len,
+				     direction, flags, &rio_ext);
+}
+EXPORT_SYMBOL_GPL(rio_dma_prep_xfer);
 
-	return txd;
+/**
+ * rio_dma_prep_slave_sg - RapidIO specific wrapper
+ *   for device_prep_slave_sg callback defined by DMAENGINE.
+ * @rdev: RIO device control structure
+ * @dchan: DMA channel to configure
+ * @data: RIO specific data descriptor
+ * @direction: DMA data transfer direction (TO or FROM the device)
+ * @flags: dmaengine defined flags
+ *
+ * Initializes RapidIO capable DMA channel for the specified data transfer.
+ * Uses DMA channel private extension to pass information related to remote
+ * target RIO device.
+ * Returns pointer to DMA transaction descriptor or NULL if failed.
+ */
+struct dma_async_tx_descriptor *rio_dma_prep_slave_sg(struct rio_dev *rdev,
+	struct dma_chan *dchan, struct rio_dma_data *data,
+	enum dma_transfer_direction direction, unsigned long flags)
+{
+	return rio_dma_prep_xfer(dchan,	rdev->destid, data, direction, flags);
 }
 EXPORT_SYMBOL_GPL(rio_dma_prep_slave_sg);
 
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 0754f5c7cb3b..a168e96142b9 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -373,6 +373,14 @@ config RTC_DRV_PCF8563
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-pcf8563.
 
+config RTC_DRV_PCF85063
+	tristate "nxp PCF85063"
+	help
+	  If you say yes here you get support for the PCF85063 RTC chip
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-pcf85063.
+
 config RTC_DRV_PCF8583
 	tristate "Philips PCF8583"
 	help
@@ -760,6 +768,15 @@ config RTC_DRV_DS1742
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-ds1742.
 
+config RTC_DRV_DS2404
+	tristate "Maxim/Dallas DS2404"
+	help
+	  If you say yes here you get support for the
+	  Dallas DS2404 RTC chip.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-ds2404.
+
 config RTC_DRV_DA9052
 	tristate "Dialog DA9052/DA9053 RTC"
 	depends on PMIC_DA9052
@@ -789,7 +806,7 @@ config RTC_DRV_DA9063
 
 config RTC_DRV_EFI
 	tristate "EFI RTC"
-	depends on IA64
+	depends on EFI
 	help
 	  If you say yes here you will get support for the EFI
 	  Real Time Clock.
@@ -873,15 +890,6 @@ config RTC_DRV_V3020
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-v3020.
 
-config RTC_DRV_DS2404
-	tristate "Dallas DS2404"
-	help
-	  If you say yes here you get support for the
-	  Dallas DS2404 RTC chip.
-
-	  This driver can also be built as a module. If so, the module
-	  will be called rtc-ds2404.
-
 config RTC_DRV_WM831X
 	tristate "Wolfson Microelectronics WM831x RTC"
 	depends on MFD_WM831X
@@ -1349,6 +1357,7 @@ config RTC_DRV_SIRFSOC
 
 config RTC_DRV_MOXART
 	tristate "MOXA ART RTC"
+	depends on ARCH_MOXART || COMPILE_TEST
 	help
 	   If you say yes here you get support for the MOXA ART
 	   RTC module.
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index 70347d041d10..56f061c7c815 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -10,6 +10,10 @@ obj-$(CONFIG_RTC_SYSTOHC)	+= systohc.o
 obj-$(CONFIG_RTC_CLASS)		+= rtc-core.o
 rtc-core-y			:= class.o interface.o
 
+ifdef CONFIG_RTC_DRV_EFI
+rtc-core-y			+= rtc-efi-platform.o
+endif
+
 rtc-core-$(CONFIG_RTC_INTF_DEV)	+= rtc-dev.o
 rtc-core-$(CONFIG_RTC_INTF_PROC) += rtc-proc.o
 rtc-core-$(CONFIG_RTC_INTF_SYSFS) += rtc-sysfs.o
@@ -93,6 +97,7 @@ obj-$(CONFIG_RTC_DRV_PCAP)	+= rtc-pcap.o
 obj-$(CONFIG_RTC_DRV_PCF2127)	+= rtc-pcf2127.o
 obj-$(CONFIG_RTC_DRV_PCF8523)	+= rtc-pcf8523.o
 obj-$(CONFIG_RTC_DRV_PCF8563)	+= rtc-pcf8563.o
+obj-$(CONFIG_RTC_DRV_PCF85063)	+= rtc-pcf85063.o
 obj-$(CONFIG_RTC_DRV_PCF8583)	+= rtc-pcf8583.o
 obj-$(CONFIG_RTC_DRV_PCF2123)	+= rtc-pcf2123.o
 obj-$(CONFIG_RTC_DRV_PCF50633)	+= rtc-pcf50633.o
diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index 589351ef75d0..38e26be705be 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -53,6 +53,7 @@ static int rtc_suspend(struct device *dev)
 	struct rtc_device	*rtc = to_rtc_device(dev);
 	struct rtc_time		tm;
 	struct timespec		delta, delta_delta;
+	int err;
 
 	if (has_persistent_clock())
 		return 0;
@@ -61,7 +62,12 @@ static int rtc_suspend(struct device *dev)
 		return 0;
 
 	/* snapshot the current RTC and system time at suspend*/
-	rtc_read_time(rtc, &tm);
+	err = rtc_read_time(rtc, &tm);
+	if (err < 0) {
+		pr_debug("%s:  fail to read rtc time\n", dev_name(&rtc->dev));
+		return 0;
+	}
+
 	getnstimeofday(&old_system);
 	rtc_tm_to_time(&tm, &old_rtc.tv_sec);
 
@@ -94,6 +100,7 @@ static int rtc_resume(struct device *dev)
 	struct rtc_time		tm;
 	struct timespec		new_system, new_rtc;
 	struct timespec		sleep_time;
+	int err;
 
 	if (has_persistent_clock())
 		return 0;
@@ -104,7 +111,12 @@ static int rtc_resume(struct device *dev)
 
 	/* snapshot the current rtc and system time at resume */
 	getnstimeofday(&new_system);
-	rtc_read_time(rtc, &tm);
+	err = rtc_read_time(rtc, &tm);
+	if (err < 0) {
+		pr_debug("%s:  fail to read rtc time\n", dev_name(&rtc->dev));
+		return 0;
+	}
+
 	if (rtc_valid_tm(&tm) != 0) {
 		pr_debug("%s:  bogus resume time\n", dev_name(&rtc->dev));
 		return 0;
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index 5813fa52c3d4..5b2717f5dafa 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -348,6 +348,8 @@ static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 
 	/* Make sure we're not setting alarms in the past */
 	err = __rtc_read_time(rtc, &tm);
+	if (err)
+		return err;
 	rtc_tm_to_time(&tm, &now);
 	if (scheduled <= now)
 		return -ETIME;
diff --git a/drivers/rtc/rtc-ds1343.c b/drivers/rtc/rtc-ds1343.c
index c3719189dd96..ae9f997223b1 100644
--- a/drivers/rtc/rtc-ds1343.c
+++ b/drivers/rtc/rtc-ds1343.c
@@ -4,6 +4,7 @@
  * Real Time Clock
  *
  * Author : Raghavendra Chandra Ganiga <ravi23ganiga@gmail.com>
+ *	    Ankur Srivastava <sankurece@gmail.com> : DS1343 Nvram Support
  *
  * 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
@@ -45,6 +46,9 @@
 #define DS1343_CONTROL_REG	0x0F
 #define DS1343_STATUS_REG	0x10
 #define DS1343_TRICKLE_REG	0x11
+#define DS1343_NVRAM		0x20
+
+#define DS1343_NVRAM_LEN	96
 
 /* DS1343 Control Registers bits */
 #define DS1343_EOSC		0x80
@@ -149,6 +153,64 @@ static ssize_t ds1343_store_glitchfilter(struct device *dev,
 static DEVICE_ATTR(glitch_filter, S_IRUGO | S_IWUSR, ds1343_show_glitchfilter,
 			ds1343_store_glitchfilter);
 
+static ssize_t ds1343_nvram_write(struct file *filp, struct kobject *kobj,
+			struct bin_attribute *attr,
+			char *buf, loff_t off, size_t count)
+{
+	int ret;
+	unsigned char address;
+	struct device *dev = kobj_to_dev(kobj);
+	struct ds1343_priv *priv = dev_get_drvdata(dev);
+
+	if (unlikely(!count))
+		return count;
+
+	if ((count + off) > DS1343_NVRAM_LEN)
+		count = DS1343_NVRAM_LEN - off;
+
+	address = DS1343_NVRAM + off;
+
+	ret = regmap_bulk_write(priv->map, address, buf, count);
+	if (ret < 0)
+		dev_err(&priv->spi->dev, "Error in nvram write %d", ret);
+
+	return (ret < 0) ? ret : count;
+}
+
+
+static ssize_t ds1343_nvram_read(struct file *filp, struct kobject *kobj,
+				struct bin_attribute *attr,
+				char *buf, loff_t off, size_t count)
+{
+	int ret;
+	unsigned char address;
+	struct device *dev = kobj_to_dev(kobj);
+	struct ds1343_priv *priv = dev_get_drvdata(dev);
+
+	if (unlikely(!count))
+		return count;
+
+	if ((count + off) > DS1343_NVRAM_LEN)
+		count = DS1343_NVRAM_LEN - off;
+
+	address = DS1343_NVRAM + off;
+
+	ret = regmap_bulk_read(priv->map, address, buf, count);
+	if (ret < 0)
+		dev_err(&priv->spi->dev, "Error in nvram read %d\n", ret);
+
+	return (ret < 0) ? ret : count;
+}
+
+
+static struct bin_attribute nvram_attr = {
+	.attr.name	= "nvram",
+	.attr.mode	= S_IRUGO | S_IWUSR,
+	.read		= ds1343_nvram_read,
+	.write		= ds1343_nvram_write,
+	.size		= DS1343_NVRAM_LEN,
+};
+
 static ssize_t ds1343_show_alarmstatus(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
@@ -274,12 +336,16 @@ static int ds1343_sysfs_register(struct device *dev)
 	if (err)
 		goto error1;
 
+	err = device_create_bin_file(dev, &nvram_attr);
+	if (err)
+		goto error2;
+
 	if (priv->irq <= 0)
 		return err;
 
 	err = device_create_file(dev, &dev_attr_alarm_mode);
 	if (err)
-		goto error2;
+		goto error3;
 
 	err = device_create_file(dev, &dev_attr_alarm_status);
 	if (!err)
@@ -287,6 +353,9 @@ static int ds1343_sysfs_register(struct device *dev)
 
 	device_remove_file(dev, &dev_attr_alarm_mode);
 
+error3:
+	device_remove_bin_file(dev, &nvram_attr);
+
 error2:
 	device_remove_file(dev, &dev_attr_trickle_charger);
 
@@ -302,6 +371,7 @@ static void ds1343_sysfs_unregister(struct device *dev)
 
 	device_remove_file(dev, &dev_attr_glitch_filter);
 	device_remove_file(dev, &dev_attr_trickle_charger);
+	device_remove_bin_file(dev, &nvram_attr);
 
 	if (priv->irq <= 0)
 		return;
@@ -684,6 +754,7 @@ static struct spi_driver ds1343_driver = {
 module_spi_driver(ds1343_driver);
 
 MODULE_DESCRIPTION("DS1343 RTC SPI Driver");
-MODULE_AUTHOR("Raghavendra Chandra Ganiga <ravi23ganiga@gmail.com>");
+MODULE_AUTHOR("Raghavendra Chandra Ganiga <ravi23ganiga@gmail.com>,"
+		"Ankur Srivastava <sankurece@gmail.com>");
 MODULE_LICENSE("GPL v2");
 MODULE_VERSION(DS1343_DRV_VERSION);
diff --git a/drivers/rtc/rtc-ds1742.c b/drivers/rtc/rtc-ds1742.c
index c6b2191a4128..9822715db8ba 100644
--- a/drivers/rtc/rtc-ds1742.c
+++ b/drivers/rtc/rtc-ds1742.c
@@ -231,7 +231,7 @@ static struct platform_driver ds1742_rtc_driver = {
 	.driver		= {
 		.name	= "rtc-ds1742",
 		.owner	= THIS_MODULE,
-		.of_match_table = ds1742_rtc_of_match,
+		.of_match_table = of_match_ptr(ds1742_rtc_of_match),
 	},
 };
 
diff --git a/drivers/rtc/rtc-efi-platform.c b/drivers/rtc/rtc-efi-platform.c
new file mode 100644
index 000000000000..b40fbe332af4
--- /dev/null
+++ b/drivers/rtc/rtc-efi-platform.c
@@ -0,0 +1,31 @@
+/*
+ * Moved from arch/ia64/kernel/time.c
+ *
+ * Copyright (C) 1998-2003 Hewlett-Packard Co
+ *	Stephane Eranian <eranian@hpl.hp.com>
+ *	David Mosberger <davidm@hpl.hp.com>
+ * Copyright (C) 1999 Don Dugger <don.dugger@intel.com>
+ * Copyright (C) 1999-2000 VA Linux Systems
+ * Copyright (C) 1999-2000 Walt Drummond <drummond@valinux.com>
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/efi.h>
+#include <linux/platform_device.h>
+
+static struct platform_device rtc_efi_dev = {
+	.name = "rtc-efi",
+	.id = -1,
+};
+
+static int __init rtc_init(void)
+{
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
+		if (platform_device_register(&rtc_efi_dev) < 0)
+			pr_err("unable to register rtc device...\n");
+
+	/* not necessarily an error */
+	return 0;
+}
+module_init(rtc_init);
diff --git a/drivers/rtc/rtc-efi.c b/drivers/rtc/rtc-efi.c
index c4c38431012e..8225b89de810 100644
--- a/drivers/rtc/rtc-efi.c
+++ b/drivers/rtc/rtc-efi.c
@@ -17,6 +17,7 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/stringify.h>
 #include <linux/time.h>
 #include <linux/platform_device.h>
 #include <linux/rtc.h>
@@ -48,8 +49,8 @@ compute_wday(efi_time_t *eft)
 	int y;
 	int ndays = 0;
 
-	if (eft->year < 1998) {
-		pr_err("EFI year < 1998, invalid date\n");
+	if (eft->year < EFI_RTC_EPOCH) {
+		pr_err("EFI year < " __stringify(EFI_RTC_EPOCH) ", invalid date\n");
 		return -1;
 	}
 
@@ -78,19 +79,36 @@ convert_to_efi_time(struct rtc_time *wtime, efi_time_t *eft)
 	eft->timezone	= EFI_UNSPECIFIED_TIMEZONE;
 }
 
-static void
+static bool
 convert_from_efi_time(efi_time_t *eft, struct rtc_time *wtime)
 {
 	memset(wtime, 0, sizeof(*wtime));
+
+	if (eft->second >= 60)
+		return false;
 	wtime->tm_sec  = eft->second;
+
+	if (eft->minute >= 60)
+		return false;
 	wtime->tm_min  = eft->minute;
+
+	if (eft->hour >= 24)
+		return false;
 	wtime->tm_hour = eft->hour;
+
+	if (!eft->day || eft->day > 31)
+		return false;
 	wtime->tm_mday = eft->day;
+
+	if (!eft->month || eft->month > 12)
+		return false;
 	wtime->tm_mon  = eft->month - 1;
 	wtime->tm_year = eft->year - 1900;
 
 	/* day of the week [0-6], Sunday=0 */
 	wtime->tm_wday = compute_wday(eft);
+	if (wtime->tm_wday < 0)
+		return false;
 
 	/* day in the year [1-365]*/
 	wtime->tm_yday = compute_yday(eft);
@@ -106,6 +124,8 @@ convert_from_efi_time(efi_time_t *eft, struct rtc_time *wtime)
 	default:
 		wtime->tm_isdst = -1;
 	}
+
+	return true;
 }
 
 static int efi_read_alarm(struct device *dev, struct rtc_wkalrm *wkalrm)
@@ -122,7 +142,8 @@ static int efi_read_alarm(struct device *dev, struct rtc_wkalrm *wkalrm)
 	if (status != EFI_SUCCESS)
 		return -EINVAL;
 
-	convert_from_efi_time(&eft, &wkalrm->time);
+	if (!convert_from_efi_time(&eft, &wkalrm->time))
+		return -EIO;
 
 	return rtc_valid_tm(&wkalrm->time);
 }
@@ -163,7 +184,8 @@ static int efi_read_time(struct device *dev, struct rtc_time *tm)
 		return -EINVAL;
 	}
 
-	convert_from_efi_time(&eft, tm);
+	if (!convert_from_efi_time(&eft, tm))
+		return -EIO;
 
 	return rtc_valid_tm(tm);
 }
diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c
index 03b891129428..aa55f081c505 100644
--- a/drivers/rtc/rtc-isl12022.c
+++ b/drivers/rtc/rtc-isl12022.c
@@ -17,6 +17,8 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/err.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
 
 #define DRV_VERSION "0.1"
 
@@ -271,6 +273,13 @@ static int isl12022_probe(struct i2c_client *client,
 	return PTR_ERR_OR_ZERO(isl12022->rtc);
 }
 
+#ifdef CONFIG_OF
+static struct of_device_id isl12022_dt_match[] = {
+	{ .compatible = "isl,isl12022" },
+	{ },
+};
+#endif
+
 static const struct i2c_device_id isl12022_id[] = {
 	{ "isl12022", 0 },
 	{ }
@@ -280,6 +289,9 @@ MODULE_DEVICE_TABLE(i2c, isl12022_id);
 static struct i2c_driver isl12022_driver = {
 	.driver		= {
 		.name	= "rtc-isl12022",
+#ifdef CONFIG_OF
+		.of_match_table = of_match_ptr(isl12022_dt_match),
+#endif
 	},
 	.probe		= isl12022_probe,
 	.id_table	= isl12022_id,
diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c
new file mode 100644
index 000000000000..6a12bf62c504
--- /dev/null
+++ b/drivers/rtc/rtc-pcf85063.c
@@ -0,0 +1,204 @@
+/*
+ * An I2C driver for the PCF85063 RTC
+ * Copyright 2014 Rose Technology
+ *
+ * Author: Søren Andersen <san@rosetechnology.dk>
+ * Maintainers: http://www.nslu2-linux.org/
+ *
+ * based on the other drivers in this same directory.
+ *
+ * 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/i2c.h>
+#include <linux/bcd.h>
+#include <linux/rtc.h>
+#include <linux/module.h>
+
+#define DRV_VERSION "0.0.1"
+
+#define PCF85063_REG_CTRL1		0x00 /* status */
+#define PCF85063_REG_CTRL2		0x01
+
+#define PCF85063_REG_SC			0x04 /* datetime */
+#define PCF85063_REG_MN			0x05
+#define PCF85063_REG_HR			0x06
+#define PCF85063_REG_DM			0x07
+#define PCF85063_REG_DW			0x08
+#define PCF85063_REG_MO			0x09
+#define PCF85063_REG_YR			0x0A
+
+#define PCF85063_MO_C			0x80 /* century */
+
+static struct i2c_driver pcf85063_driver;
+
+struct pcf85063 {
+	struct rtc_device *rtc;
+	int c_polarity;	/* 0: MO_C=1 means 19xx, otherwise MO_C=1 means 20xx */
+	int voltage_low; /* indicates if a low_voltage was detected */
+};
+
+/*
+ * In the routines that deal directly with the pcf85063 hardware, we use
+ * rtc_time -- month 0-11, hour 0-23, yr = calendar year-epoch.
+ */
+static int pcf85063_get_datetime(struct i2c_client *client, struct rtc_time *tm)
+{
+	struct pcf85063 *pcf85063 = i2c_get_clientdata(client);
+	unsigned char buf[13] = { PCF85063_REG_CTRL1 };
+	struct i2c_msg msgs[] = {
+		{/* setup read ptr */
+			.addr = client->addr,
+			.len = 1,
+			.buf = buf
+		},
+		{/* read status + date */
+			.addr = client->addr,
+			.flags = I2C_M_RD,
+			.len = 13,
+			.buf = buf
+		},
+	};
+
+	/* read registers */
+	if ((i2c_transfer(client->adapter, msgs, 2)) != 2) {
+		dev_err(&client->dev, "%s: read error\n", __func__);
+		return -EIO;
+	}
+
+	tm->tm_sec = bcd2bin(buf[PCF85063_REG_SC] & 0x7F);
+	tm->tm_min = bcd2bin(buf[PCF85063_REG_MN] & 0x7F);
+	tm->tm_hour = bcd2bin(buf[PCF85063_REG_HR] & 0x3F); /* rtc hr 0-23 */
+	tm->tm_mday = bcd2bin(buf[PCF85063_REG_DM] & 0x3F);
+	tm->tm_wday = buf[PCF85063_REG_DW] & 0x07;
+	tm->tm_mon = bcd2bin(buf[PCF85063_REG_MO] & 0x1F) - 1; /* rtc mn 1-12 */
+	tm->tm_year = bcd2bin(buf[PCF85063_REG_YR]);
+	if (tm->tm_year < 70)
+		tm->tm_year += 100;	/* assume we are in 1970...2069 */
+	/* detect the polarity heuristically. see note above. */
+	pcf85063->c_polarity = (buf[PCF85063_REG_MO] & PCF85063_MO_C) ?
+		(tm->tm_year >= 100) : (tm->tm_year < 100);
+
+	/* the clock can give out invalid datetime, but we cannot return
+	 * -EINVAL otherwise hwclock will refuse to set the time on bootup.
+	 */
+	if (rtc_valid_tm(tm) < 0)
+		dev_err(&client->dev, "retrieved date/time is not valid.\n");
+
+	return 0;
+}
+
+static int pcf85063_set_datetime(struct i2c_client *client, struct rtc_time *tm)
+{
+	int i = 0, err = 0;
+	unsigned char buf[11];
+
+	/* Control & status */
+	buf[PCF85063_REG_CTRL1] = 0;
+	buf[PCF85063_REG_CTRL2] = 5;
+
+	/* hours, minutes and seconds */
+	buf[PCF85063_REG_SC] = bin2bcd(tm->tm_sec) & 0x7F;
+
+	buf[PCF85063_REG_MN] = bin2bcd(tm->tm_min);
+	buf[PCF85063_REG_HR] = bin2bcd(tm->tm_hour);
+
+	/* Day of month, 1 - 31 */
+	buf[PCF85063_REG_DM] = bin2bcd(tm->tm_mday);
+
+	/* Day, 0 - 6 */
+	buf[PCF85063_REG_DW] = tm->tm_wday & 0x07;
+
+	/* month, 1 - 12 */
+	buf[PCF85063_REG_MO] = bin2bcd(tm->tm_mon + 1);
+
+	/* year and century */
+	buf[PCF85063_REG_YR] = bin2bcd(tm->tm_year % 100);
+
+	/* write register's data */
+	for (i = 0; i < sizeof(buf); i++) {
+		unsigned char data[2] = { i, buf[i] };
+
+		err = i2c_master_send(client, data, sizeof(data));
+		if (err != sizeof(data)) {
+			dev_err(&client->dev, "%s: err=%d addr=%02x, data=%02x\n",
+					__func__, err, data[0], data[1]);
+			return -EIO;
+		}
+	}
+
+	return 0;
+}
+
+static int pcf85063_rtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+	return pcf85063_get_datetime(to_i2c_client(dev), tm);
+}
+
+static int pcf85063_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+	return pcf85063_set_datetime(to_i2c_client(dev), tm);
+}
+
+static const struct rtc_class_ops pcf85063_rtc_ops = {
+	.read_time	= pcf85063_rtc_read_time,
+	.set_time	= pcf85063_rtc_set_time
+};
+
+static int pcf85063_probe(struct i2c_client *client,
+				const struct i2c_device_id *id)
+{
+	struct pcf85063 *pcf85063;
+
+	dev_dbg(&client->dev, "%s\n", __func__);
+
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
+		return -ENODEV;
+
+	pcf85063 = devm_kzalloc(&client->dev, sizeof(struct pcf85063),
+				GFP_KERNEL);
+	if (!pcf85063)
+		return -ENOMEM;
+
+	dev_info(&client->dev, "chip found, driver version " DRV_VERSION "\n");
+
+	i2c_set_clientdata(client, pcf85063);
+
+	pcf85063->rtc = devm_rtc_device_register(&client->dev,
+				pcf85063_driver.driver.name,
+				&pcf85063_rtc_ops, THIS_MODULE);
+
+	return PTR_ERR_OR_ZERO(pcf85063->rtc);
+}
+
+static const struct i2c_device_id pcf85063_id[] = {
+	{ "pcf85063", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, pcf85063_id);
+
+#ifdef CONFIG_OF
+static const struct of_device_id pcf85063_of_match[] = {
+	{ .compatible = "nxp,pcf85063" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, pcf85063_of_match);
+#endif
+
+static struct i2c_driver pcf85063_driver = {
+	.driver		= {
+		.name	= "rtc-pcf85063",
+		.owner	= THIS_MODULE,
+		.of_match_table = of_match_ptr(pcf85063_of_match),
+	},
+	.probe		= pcf85063_probe,
+	.id_table	= pcf85063_id,
+};
+
+module_i2c_driver(pcf85063_driver);
+
+MODULE_AUTHOR("Søren Andersen <san@rosetechnology.dk>");
+MODULE_DESCRIPTION("PCF85063 RTC driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(DRV_VERSION);
diff --git a/drivers/rtc/rtc-pcf8563.c b/drivers/rtc/rtc-pcf8563.c
index 63b558c48196..5a197d9dc7e7 100644
--- a/drivers/rtc/rtc-pcf8563.c
+++ b/drivers/rtc/rtc-pcf8563.c
@@ -26,6 +26,8 @@
 
 #define PCF8563_REG_ST1		0x00 /* status */
 #define PCF8563_REG_ST2		0x01
+#define PCF8563_BIT_AIE		(1 << 1)
+#define PCF8563_BIT_AF		(1 << 3)
 
 #define PCF8563_REG_SC		0x02 /* datetime */
 #define PCF8563_REG_MN		0x03
@@ -36,9 +38,6 @@
 #define PCF8563_REG_YR		0x08
 
 #define PCF8563_REG_AMN		0x09 /* alarm */
-#define PCF8563_REG_AHR		0x0A
-#define PCF8563_REG_ADM		0x0B
-#define PCF8563_REG_ADW		0x0C
 
 #define PCF8563_REG_CLKO	0x0D /* clock out */
 #define PCF8563_REG_TMRC	0x0E /* timer control */
@@ -67,37 +66,133 @@ struct pcf8563 {
 	 */
 	int c_polarity;	/* 0: MO_C=1 means 19xx, otherwise MO_C=1 means 20xx */
 	int voltage_low; /* incicates if a low_voltage was detected */
+
+	struct i2c_client *client;
 };
 
-/*
- * In the routines that deal directly with the pcf8563 hardware, we use
- * rtc_time -- month 0-11, hour 0-23, yr = calendar year-epoch.
- */
-static int pcf8563_get_datetime(struct i2c_client *client, struct rtc_time *tm)
+static int pcf8563_read_block_data(struct i2c_client *client, unsigned char reg,
+				   unsigned char length, unsigned char *buf)
 {
-	struct pcf8563 *pcf8563 = i2c_get_clientdata(client);
-	unsigned char buf[13] = { PCF8563_REG_ST1 };
-
 	struct i2c_msg msgs[] = {
 		{/* setup read ptr */
 			.addr = client->addr,
 			.len = 1,
-			.buf = buf
+			.buf = &reg,
 		},
-		{/* read status + date */
+		{
 			.addr = client->addr,
 			.flags = I2C_M_RD,
-			.len = 13,
+			.len = length,
 			.buf = buf
 		},
 	};
 
-	/* read registers */
 	if ((i2c_transfer(client->adapter, msgs, 2)) != 2) {
 		dev_err(&client->dev, "%s: read error\n", __func__);
 		return -EIO;
 	}
 
+	return 0;
+}
+
+static int pcf8563_write_block_data(struct i2c_client *client,
+				   unsigned char reg, unsigned char length,
+				   unsigned char *buf)
+{
+	int i, err;
+
+	for (i = 0; i < length; i++) {
+		unsigned char data[2] = { reg + i, buf[i] };
+
+		err = i2c_master_send(client, data, sizeof(data));
+		if (err != sizeof(data)) {
+			dev_err(&client->dev,
+				"%s: err=%d addr=%02x, data=%02x\n",
+				__func__, err, data[0], data[1]);
+			return -EIO;
+		}
+	}
+
+	return 0;
+}
+
+static int pcf8563_set_alarm_mode(struct i2c_client *client, bool on)
+{
+	unsigned char buf[2];
+	int err;
+
+	err = pcf8563_read_block_data(client, PCF8563_REG_ST2, 1, buf + 1);
+	if (err < 0)
+		return err;
+
+	if (on)
+		buf[1] |= PCF8563_BIT_AIE;
+	else
+		buf[1] &= ~PCF8563_BIT_AIE;
+
+	buf[1] &= ~PCF8563_BIT_AF;
+	buf[0] = PCF8563_REG_ST2;
+
+	err = pcf8563_write_block_data(client, PCF8563_REG_ST2, 1, buf + 1);
+	if (err < 0) {
+		dev_err(&client->dev, "%s: write error\n", __func__);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int pcf8563_get_alarm_mode(struct i2c_client *client, unsigned char *en,
+				  unsigned char *pen)
+{
+	unsigned char buf;
+	int err;
+
+	err = pcf8563_read_block_data(client, PCF8563_REG_ST2, 1, &buf);
+	if (err)
+		return err;
+
+	if (en)
+		*en = !!(buf & PCF8563_BIT_AIE);
+	if (pen)
+		*pen = !!(buf & PCF8563_BIT_AF);
+
+	return 0;
+}
+
+static irqreturn_t pcf8563_irq(int irq, void *dev_id)
+{
+	struct pcf8563 *pcf8563 = i2c_get_clientdata(dev_id);
+	int err;
+	char pending;
+
+	err = pcf8563_get_alarm_mode(pcf8563->client, NULL, &pending);
+	if (err < 0)
+		return err;
+
+	if (pending) {
+		rtc_update_irq(pcf8563->rtc, 1, RTC_IRQF | RTC_AF);
+		pcf8563_set_alarm_mode(pcf8563->client, 1);
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
+/*
+ * In the routines that deal directly with the pcf8563 hardware, we use
+ * rtc_time -- month 0-11, hour 0-23, yr = calendar year-epoch.
+ */
+static int pcf8563_get_datetime(struct i2c_client *client, struct rtc_time *tm)
+{
+	struct pcf8563 *pcf8563 = i2c_get_clientdata(client);
+	unsigned char buf[9];
+	int err;
+
+	err = pcf8563_read_block_data(client, PCF8563_REG_ST1, 9, buf);
+	if (err)
+		return err;
+
 	if (buf[PCF8563_REG_SC] & PCF8563_SC_LV) {
 		pcf8563->voltage_low = 1;
 		dev_info(&client->dev,
@@ -144,7 +239,7 @@ static int pcf8563_get_datetime(struct i2c_client *client, struct rtc_time *tm)
 static int pcf8563_set_datetime(struct i2c_client *client, struct rtc_time *tm)
 {
 	struct pcf8563 *pcf8563 = i2c_get_clientdata(client);
-	int i, err;
+	int err;
 	unsigned char buf[9];
 
 	dev_dbg(&client->dev, "%s: secs=%d, mins=%d, hours=%d, "
@@ -170,19 +265,10 @@ static int pcf8563_set_datetime(struct i2c_client *client, struct rtc_time *tm)
 
 	buf[PCF8563_REG_DW] = tm->tm_wday & 0x07;
 
-	/* write register's data */
-	for (i = 0; i < 7; i++) {
-		unsigned char data[2] = { PCF8563_REG_SC + i,
-						buf[PCF8563_REG_SC + i] };
-
-		err = i2c_master_send(client, data, sizeof(data));
-		if (err != sizeof(data)) {
-			dev_err(&client->dev,
-				"%s: err=%d addr=%02x, data=%02x\n",
-				__func__, err, data[0], data[1]);
-			return -EIO;
-		}
-	}
+	err = pcf8563_write_block_data(client, PCF8563_REG_SC,
+				9 - PCF8563_REG_SC, buf + PCF8563_REG_SC);
+	if (err)
+		return err;
 
 	return 0;
 }
@@ -235,16 +321,83 @@ static int pcf8563_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	return pcf8563_set_datetime(to_i2c_client(dev), tm);
 }
 
+static int pcf8563_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *tm)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	unsigned char buf[4];
+	int err;
+
+	err = pcf8563_read_block_data(client, PCF8563_REG_AMN, 4, buf);
+	if (err)
+		return err;
+
+	dev_dbg(&client->dev,
+		"%s: raw data is min=%02x, hr=%02x, mday=%02x, wday=%02x\n",
+		__func__, buf[0], buf[1], buf[2], buf[3]);
+
+	tm->time.tm_min = bcd2bin(buf[0] & 0x7F);
+	tm->time.tm_hour = bcd2bin(buf[1] & 0x7F);
+	tm->time.tm_mday = bcd2bin(buf[2] & 0x1F);
+	tm->time.tm_wday = bcd2bin(buf[3] & 0x7);
+	tm->time.tm_mon = -1;
+	tm->time.tm_year = -1;
+	tm->time.tm_yday = -1;
+	tm->time.tm_isdst = -1;
+
+	err = pcf8563_get_alarm_mode(client, &tm->enabled, &tm->pending);
+	if (err < 0)
+		return err;
+
+	dev_dbg(&client->dev, "%s: tm is mins=%d, hours=%d, mday=%d, wday=%d,"
+		" enabled=%d, pending=%d\n", __func__, tm->time.tm_min,
+		tm->time.tm_hour, tm->time.tm_mday, tm->time.tm_wday,
+		tm->enabled, tm->pending);
+
+	return 0;
+}
+
+static int pcf8563_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *tm)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	unsigned char buf[4];
+	int err;
+
+	dev_dbg(dev, "%s, min=%d hour=%d wday=%d mday=%d "
+		"enabled=%d pending=%d\n", __func__,
+		tm->time.tm_min, tm->time.tm_hour, tm->time.tm_wday,
+		tm->time.tm_mday, tm->enabled, tm->pending);
+
+	buf[0] = bin2bcd(tm->time.tm_min);
+	buf[1] = bin2bcd(tm->time.tm_hour);
+	buf[2] = bin2bcd(tm->time.tm_mday);
+	buf[3] = tm->time.tm_wday & 0x07;
+
+	err = pcf8563_write_block_data(client, PCF8563_REG_AMN, 4, buf);
+	if (err)
+		return err;
+
+	return pcf8563_set_alarm_mode(client, 1);
+}
+
+static int pcf8563_irq_enable(struct device *dev, unsigned int enabled)
+{
+	return pcf8563_set_alarm_mode(to_i2c_client(dev), !!enabled);
+}
+
 static const struct rtc_class_ops pcf8563_rtc_ops = {
 	.ioctl		= pcf8563_rtc_ioctl,
 	.read_time	= pcf8563_rtc_read_time,
 	.set_time	= pcf8563_rtc_set_time,
+	.read_alarm	= pcf8563_rtc_read_alarm,
+	.set_alarm	= pcf8563_rtc_set_alarm,
+	.alarm_irq_enable = pcf8563_irq_enable,
 };
 
 static int pcf8563_probe(struct i2c_client *client,
 				const struct i2c_device_id *id)
 {
 	struct pcf8563 *pcf8563;
+	int err;
 
 	dev_dbg(&client->dev, "%s\n", __func__);
 
@@ -259,12 +412,30 @@ static int pcf8563_probe(struct i2c_client *client,
 	dev_info(&client->dev, "chip found, driver version " DRV_VERSION "\n");
 
 	i2c_set_clientdata(client, pcf8563);
+	pcf8563->client = client;
+	device_set_wakeup_capable(&client->dev, 1);
 
 	pcf8563->rtc = devm_rtc_device_register(&client->dev,
 				pcf8563_driver.driver.name,
 				&pcf8563_rtc_ops, THIS_MODULE);
 
-	return PTR_ERR_OR_ZERO(pcf8563->rtc);
+	if (IS_ERR(pcf8563->rtc))
+		return PTR_ERR(pcf8563->rtc);
+
+	if (client->irq > 0) {
+		err = devm_request_threaded_irq(&client->dev, client->irq,
+				NULL, pcf8563_irq,
+				IRQF_SHARED|IRQF_ONESHOT|IRQF_TRIGGER_FALLING,
+				pcf8563->rtc->name, client);
+		if (err) {
+			dev_err(&client->dev, "unable to request IRQ %d\n",
+								client->irq);
+			return err;
+		}
+
+	}
+
+	return 0;
 }
 
 static const struct i2c_device_id pcf8563_id[] = {
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/backlight.c b/drivers/video/backlight/backlight.c
index bddc8b17a4d8..0ce8823952a8 100644
--- a/drivers/video/backlight/backlight.c
+++ b/drivers/video/backlight/backlight.c
@@ -190,8 +190,6 @@ 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/fs/adfs/adfs.h b/fs/adfs/adfs.h
index c770337c4b45..24575d9d882d 100644
--- a/fs/adfs/adfs.h
+++ b/fs/adfs/adfs.h
@@ -153,6 +153,7 @@ extern int adfs_map_lookup(struct super_block *sb, unsigned int frag_id, unsigne
 extern unsigned int adfs_map_free(struct super_block *sb);
 
 /* Misc */
+__printf(3, 4)
 void __adfs_error(struct super_block *sb, const char *function,
 		  const char *fmt, ...);
 #define adfs_error(sb, fmt...) __adfs_error(sb, __func__, fmt)
diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c
index 0d138c0de293..51c279a29845 100644
--- a/fs/adfs/dir.c
+++ b/fs/adfs/dir.c
@@ -138,7 +138,7 @@ adfs_dir_lookup_byname(struct inode *inode, struct qstr *name, struct object_inf
 		goto out;
 
 	if (ADFS_I(inode)->parent_id != dir.parent_id) {
-		adfs_error(sb, "parent directory changed under me! (%lx but got %lx)\n",
+		adfs_error(sb, "parent directory changed under me! (%lx but got %x)\n",
 			   ADFS_I(inode)->parent_id, dir.parent_id);
 		ret = -EIO;
 		goto free_out;
diff --git a/fs/adfs/dir_fplus.c b/fs/adfs/dir_fplus.c
index d9e3bee4e653..f2ba88ab4aed 100644
--- a/fs/adfs/dir_fplus.c
+++ b/fs/adfs/dir_fplus.c
@@ -55,10 +55,10 @@ adfs_fplus_read(struct super_block *sb, unsigned int id, unsigned int sz, struct
 	}
 
 	size >>= sb->s_blocksize_bits;
-	if (size > sizeof(dir->bh)/sizeof(dir->bh[0])) {
+	if (size > ARRAY_SIZE(dir->bh)) {
 		/* this directory is too big for fixed bh set, must allocate */
 		struct buffer_head **bh_fplus =
-			kzalloc(size * sizeof(struct buffer_head *),
+			kcalloc(size, sizeof(struct buffer_head *),
 				GFP_KERNEL);
 		if (!bh_fplus) {
 			adfs_error(sb, "not enough memory for"
@@ -79,9 +79,8 @@ adfs_fplus_read(struct super_block *sb, unsigned int id, unsigned int sz, struct
 
 		dir->bh_fplus[blk] = sb_bread(sb, block);
 		if (!dir->bh_fplus[blk]) {
-			adfs_error(sb,	"dir object %X failed read for"
-					" offset %d, mapped block %X",
-					id, blk, block);
+			adfs_error(sb,	"dir object %x failed read for offset %d, mapped block %lX",
+				   id, blk, block);
 			goto out;
 		}
 
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index acf32054edd8..9e359fb20c0a 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -143,20 +143,6 @@ static inline int autofs4_oz_mode(struct autofs_sb_info *sbi) {
 	return sbi->catatonic || task_pgrp(current) == sbi->oz_pgrp;
 }
 
-/* Does a dentry have some pending activity? */
-static inline int autofs4_ispending(struct dentry *dentry)
-{
-	struct autofs_info *inf = autofs4_dentry_ino(dentry);
-
-	if (inf->flags & AUTOFS_INF_PENDING)
-		return 1;
-
-	if (inf->flags & AUTOFS_INF_EXPIRING)
-		return 1;
-
-	return 0;
-}
-
 struct inode *autofs4_get_inode(struct super_block *, umode_t);
 void autofs4_free_ino(struct autofs_info *);
 
@@ -191,55 +177,6 @@ extern const struct file_operations autofs4_root_operations;
 extern const struct dentry_operations autofs4_dentry_operations;
 
 /* VFS automount flags management functions */
-
-static inline void __managed_dentry_set_automount(struct dentry *dentry)
-{
-	dentry->d_flags |= DCACHE_NEED_AUTOMOUNT;
-}
-
-static inline void managed_dentry_set_automount(struct dentry *dentry)
-{
-	spin_lock(&dentry->d_lock);
-	__managed_dentry_set_automount(dentry);
-	spin_unlock(&dentry->d_lock);
-}
-
-static inline void __managed_dentry_clear_automount(struct dentry *dentry)
-{
-	dentry->d_flags &= ~DCACHE_NEED_AUTOMOUNT;
-}
-
-static inline void managed_dentry_clear_automount(struct dentry *dentry)
-{
-	spin_lock(&dentry->d_lock);
-	__managed_dentry_clear_automount(dentry);
-	spin_unlock(&dentry->d_lock);
-}
-
-static inline void __managed_dentry_set_transit(struct dentry *dentry)
-{
-	dentry->d_flags |= DCACHE_MANAGE_TRANSIT;
-}
-
-static inline void managed_dentry_set_transit(struct dentry *dentry)
-{
-	spin_lock(&dentry->d_lock);
-	__managed_dentry_set_transit(dentry);
-	spin_unlock(&dentry->d_lock);
-}
-
-static inline void __managed_dentry_clear_transit(struct dentry *dentry)
-{
-	dentry->d_flags &= ~DCACHE_MANAGE_TRANSIT;
-}
-
-static inline void managed_dentry_clear_transit(struct dentry *dentry)
-{
-	spin_lock(&dentry->d_lock);
-	__managed_dentry_clear_transit(dentry);
-	spin_unlock(&dentry->d_lock);
-}
-
 static inline void __managed_dentry_set_managed(struct dentry *dentry)
 {
 	dentry->d_flags |= (DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT);
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 394e90b02c5e..a7be57e39be7 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -333,7 +333,6 @@ struct dentry *autofs4_expire_direct(struct super_block *sb,
 	if (ino->flags & AUTOFS_INF_PENDING)
 		goto out;
 	if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
-		struct autofs_info *ino = autofs4_dentry_ino(root);
 		ino->flags |= AUTOFS_INF_EXPIRING;
 		init_completion(&ino->expire_complete);
 		spin_unlock(&sbi->fs_lock);
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index cc87c1abac97..cdb25ebccc4c 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -166,8 +166,10 @@ static struct dentry *autofs4_lookup_active(struct dentry *dentry)
 	const unsigned char *str = name->name;
 	struct list_head *p, *head;
 
-	spin_lock(&sbi->lookup_lock);
 	head = &sbi->active_list;
+	if (list_empty(head))
+		return NULL;
+	spin_lock(&sbi->lookup_lock);
 	list_for_each(p, head) {
 		struct autofs_info *ino;
 		struct dentry *active;
@@ -218,8 +220,10 @@ static struct dentry *autofs4_lookup_expiring(struct dentry *dentry)
 	const unsigned char *str = name->name;
 	struct list_head *p, *head;
 
-	spin_lock(&sbi->lookup_lock);
 	head = &sbi->expiring_list;
+	if (list_empty(head))
+		return NULL;
+	spin_lock(&sbi->lookup_lock);
 	list_for_each(p, head) {
 		struct autofs_info *ino;
 		struct dentry *expiring;
@@ -373,7 +377,7 @@ static struct vfsmount *autofs4_d_automount(struct path *path)
 		 * this because the leaves of the directory tree under the
 		 * mount never trigger mounts themselves (they have an autofs
 		 * trigger mount mounted on them). But v4 pseudo direct mounts
-		 * do need the leaves to to trigger mounts. In this case we
+		 * do need the leaves to trigger mounts. In this case we
 		 * have no choice but to use the list_empty() check and
 		 * require user space behave.
 		 */
diff --git a/fs/bfs/bfs.h b/fs/bfs/bfs.h
index f7f87e233dd9..f40006db36df 100644
--- a/fs/bfs/bfs.h
+++ b/fs/bfs/bfs.h
@@ -46,6 +46,7 @@ static inline struct bfs_inode_info *BFS_I(struct inode *inode)
 
 /* inode.c */
 extern struct inode *bfs_iget(struct super_block *sb, unsigned long ino);
+extern void bfs_dump_imap(const char *, struct super_block *);
 
 /* file.c */
 extern const struct inode_operations bfs_file_inops;
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index a399e6d9dc74..08063ae0a17c 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -75,8 +75,6 @@ const struct file_operations bfs_dir_operations = {
 	.llseek		= generic_file_llseek,
 };
 
-extern void dump_imap(const char *, struct super_block *);
-
 static int bfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 						bool excl)
 {
@@ -110,7 +108,7 @@ static int bfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	BFS_I(inode)->i_eblock = 0;
 	insert_inode_hash(inode);
         mark_inode_dirty(inode);
-	dump_imap("create", s);
+	bfs_dump_imap("create", s);
 
 	err = bfs_add_entry(dir, dentry->d_name.name, dentry->d_name.len,
 							inode->i_ino);
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 7041ac35ace8..90bc079d9982 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -30,8 +30,6 @@ MODULE_LICENSE("GPL");
 #define dprintf(x...)
 #endif
 
-void dump_imap(const char *prefix, struct super_block *s);
-
 struct inode *bfs_iget(struct super_block *sb, unsigned long ino)
 {
 	struct bfs_inode *di;
@@ -194,7 +192,7 @@ static void bfs_evict_inode(struct inode *inode)
 			info->si_freeb += bi->i_eblock + 1 - bi->i_sblock;
 		info->si_freei++;
 		clear_bit(ino, info->si_imap);
-		dump_imap("delete_inode", s);
+		bfs_dump_imap("delete_inode", s);
         }
 
 	/*
@@ -297,7 +295,7 @@ static const struct super_operations bfs_sops = {
 	.statfs		= bfs_statfs,
 };
 
-void dump_imap(const char *prefix, struct super_block *s)
+void bfs_dump_imap(const char *prefix, struct super_block *s)
 {
 #ifdef DEBUG
 	int i;
@@ -443,7 +441,7 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
 	}
 	brelse(bh);
 	brelse(sbh);
-	dump_imap("read_super", s);
+	bfs_dump_imap("read_super", s);
 	return 0;
 
 out3:
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 3892c1a23241..d94672a1f272 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -145,6 +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_t(size_t, 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)
@@ -206,7 +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)))
diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c
index d749731dc0ee..dd333a67ebc2 100644
--- a/fs/cachefiles/bind.c
+++ b/fs/cachefiles/bind.c
@@ -39,13 +39,11 @@ int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args)
 	       args);
 
 	/* start by checking things over */
-	ASSERT(cache->fstop_percent >= 0 &&
-	       cache->fstop_percent < cache->fcull_percent &&
+	ASSERT(cache->fstop_percent < cache->fcull_percent &&
 	       cache->fcull_percent < cache->frun_percent &&
 	       cache->frun_percent  < 100);
 
-	ASSERT(cache->bstop_percent >= 0 &&
-	       cache->bstop_percent < cache->bcull_percent &&
+	ASSERT(cache->bstop_percent < cache->bcull_percent &&
 	       cache->bcull_percent < cache->brun_percent &&
 	       cache->brun_percent  < 100);
 
diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
index b078d3081d6c..ff43e5a8711f 100644
--- a/fs/cachefiles/daemon.c
+++ b/fs/cachefiles/daemon.c
@@ -222,7 +222,7 @@ static ssize_t cachefiles_daemon_write(struct file *file,
 	if (test_bit(CACHEFILES_DEAD, &cache->flags))
 		return -EIO;
 
-	if (datalen < 0 || datalen > PAGE_SIZE - 1)
+	if (datalen > PAGE_SIZE - 1)
 		return -EOPNOTSUPP;
 
 	/* drag the command string into the kernel so we can parse it */
@@ -385,7 +385,7 @@ static int cachefiles_daemon_fstop(struct cachefiles_cache *cache, char *args)
 	if (args[0] != '%' || args[1] != '\0')
 		return -EINVAL;
 
-	if (fstop < 0 || fstop >= cache->fcull_percent)
+	if (fstop >= cache->fcull_percent)
 		return cachefiles_daemon_range_error(cache, args);
 
 	cache->fstop_percent = fstop;
@@ -457,7 +457,7 @@ static int cachefiles_daemon_bstop(struct cachefiles_cache *cache, char *args)
 	if (args[0] != '%' || args[1] != '\0')
 		return -EINVAL;
 
-	if (bstop < 0 || bstop >= cache->bcull_percent)
+	if (bstop >= cache->bcull_percent)
 		return cachefiles_daemon_range_error(cache, args);
 
 	cache->bstop_percent = bstop;
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 7ff866dbb89e..54ac0e8ad96c 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -38,7 +38,7 @@ static const struct cifs_sid sid_everyone = {
 	1, 1, {0, 0, 0, 0, 0, 1}, {0} };
 /* security id for Authenticated Users system group */
 static const struct cifs_sid sid_authusers = {
-	1, 1, {0, 0, 0, 0, 0, 5}, {__constant_cpu_to_le32(11)} };
+	1, 1, {0, 0, 0, 0, 0, 5}, {cpu_to_le32(11)} };
 /* group users */
 static const struct cifs_sid sid_user = {1, 2 , {0, 0, 0, 0, 0, 5}, {} };
 
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 66f65001a6d8..86a2aa57560c 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -2477,14 +2477,14 @@ CIFSSMBPosixLock(const unsigned int xid, struct cifs_tcon *tcon,
 		}
 		parm_data = (struct cifs_posix_lock *)
 			((char *)&pSMBr->hdr.Protocol + data_offset);
-		if (parm_data->lock_type == __constant_cpu_to_le16(CIFS_UNLCK))
+		if (parm_data->lock_type == cpu_to_le16(CIFS_UNLCK))
 			pLockData->fl_type = F_UNLCK;
 		else {
 			if (parm_data->lock_type ==
-					__constant_cpu_to_le16(CIFS_RDLCK))
+					cpu_to_le16(CIFS_RDLCK))
 				pLockData->fl_type = F_RDLCK;
 			else if (parm_data->lock_type ==
-					__constant_cpu_to_le16(CIFS_WRLCK))
+					cpu_to_le16(CIFS_WRLCK))
 				pLockData->fl_type = F_WRLCK;
 
 			pLockData->fl_start = le64_to_cpu(parm_data->start);
@@ -3276,25 +3276,25 @@ CIFSSMB_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 	pSMB->compression_state = cpu_to_le16(COMPRESSION_FORMAT_DEFAULT);
 
 	pSMB->TotalParameterCount = 0;
-	pSMB->TotalDataCount = __constant_cpu_to_le32(2);
+	pSMB->TotalDataCount = cpu_to_le32(2);
 	pSMB->MaxParameterCount = 0;
 	pSMB->MaxDataCount = 0;
 	pSMB->MaxSetupCount = 4;
 	pSMB->Reserved = 0;
 	pSMB->ParameterOffset = 0;
-	pSMB->DataCount = __constant_cpu_to_le32(2);
+	pSMB->DataCount = cpu_to_le32(2);
 	pSMB->DataOffset =
 		cpu_to_le32(offsetof(struct smb_com_transaction_compr_ioctl_req,
 				compression_state) - 4);  /* 84 */
 	pSMB->SetupCount = 4;
-	pSMB->SubCommand = __constant_cpu_to_le16(NT_TRANSACT_IOCTL);
+	pSMB->SubCommand = cpu_to_le16(NT_TRANSACT_IOCTL);
 	pSMB->ParameterCount = 0;
-	pSMB->FunctionCode = __constant_cpu_to_le32(FSCTL_SET_COMPRESSION);
+	pSMB->FunctionCode = cpu_to_le32(FSCTL_SET_COMPRESSION);
 	pSMB->IsFsctl = 1; /* FSCTL */
 	pSMB->IsRootFlag = 0;
 	pSMB->Fid = fid; /* file handle always le */
 	/* 3 byte pad, followed by 2 byte compress state */
-	pSMB->ByteCount = __constant_cpu_to_le16(5);
+	pSMB->ByteCount = cpu_to_le16(5);
 	inc_rfc1001_len(pSMB, 5);
 
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
@@ -3430,10 +3430,10 @@ static __u16 ACL_to_cifs_posix(char *parm_data, const char *pACL,
 	cifs_acl->version = cpu_to_le16(1);
 	if (acl_type == ACL_TYPE_ACCESS) {
 		cifs_acl->access_entry_count = cpu_to_le16(count);
-		cifs_acl->default_entry_count = __constant_cpu_to_le16(0xFFFF);
+		cifs_acl->default_entry_count = cpu_to_le16(0xFFFF);
 	} else if (acl_type == ACL_TYPE_DEFAULT) {
 		cifs_acl->default_entry_count = cpu_to_le16(count);
-		cifs_acl->access_entry_count = __constant_cpu_to_le16(0xFFFF);
+		cifs_acl->access_entry_count = cpu_to_le16(0xFFFF);
 	} else {
 		cifs_dbg(FYI, "unknown ACL type %d\n", acl_type);
 		return 0;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 4ab2f79ffa7a..553747f8127e 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1058,7 +1058,7 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile)
 
 	max_num = (max_buf - sizeof(struct smb_hdr)) /
 						sizeof(LOCKING_ANDX_RANGE);
-	buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
+	buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
 	if (!buf) {
 		free_xid(xid);
 		return -ENOMEM;
@@ -1393,7 +1393,7 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
 
 	max_num = (max_buf - sizeof(struct smb_hdr)) /
 						sizeof(LOCKING_ANDX_RANGE);
-	buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
+	buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 39ee32688eac..39b850786e12 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -46,7 +46,7 @@ static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, SESSION_SETUP_ANDX *pSMB)
 					CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4,
 					USHRT_MAX));
 	pSMB->req.MaxMpxCount = cpu_to_le16(ses->server->maxReq);
-	pSMB->req.VcNumber = __constant_cpu_to_le16(1);
+	pSMB->req.VcNumber = cpu_to_le16(1);
 
 	/* Now no need to set SMBFLG_CASELESS or obsolete CANONICAL PATH */
 
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index 3f17b4550831..e5100b8fb3a0 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -111,7 +111,7 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
 		return -EINVAL;
 
 	max_num = max_buf / sizeof(struct smb2_lock_element);
-	buf = kzalloc(max_num * sizeof(struct smb2_lock_element), GFP_KERNEL);
+	buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
@@ -247,7 +247,7 @@ smb2_push_mandatory_locks(struct cifsFileInfo *cfile)
 	}
 
 	max_num = max_buf / sizeof(struct smb2_lock_element);
-	buf = kzalloc(max_num * sizeof(struct smb2_lock_element), GFP_KERNEL);
+	buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL);
 	if (!buf) {
 		free_xid(xid);
 		return -ENOMEM;
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index f2e6ac29a8d6..da0faf6e13f2 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -67,27 +67,27 @@ check_smb2_hdr(struct smb2_hdr *hdr, __u64 mid)
  *  indexed by command in host byte order
  */
 static const __le16 smb2_rsp_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
-	/* SMB2_NEGOTIATE */ __constant_cpu_to_le16(65),
-	/* SMB2_SESSION_SETUP */ __constant_cpu_to_le16(9),
-	/* SMB2_LOGOFF */ __constant_cpu_to_le16(4),
-	/* SMB2_TREE_CONNECT */ __constant_cpu_to_le16(16),
-	/* SMB2_TREE_DISCONNECT */ __constant_cpu_to_le16(4),
-	/* SMB2_CREATE */ __constant_cpu_to_le16(89),
-	/* SMB2_CLOSE */ __constant_cpu_to_le16(60),
-	/* SMB2_FLUSH */ __constant_cpu_to_le16(4),
-	/* SMB2_READ */ __constant_cpu_to_le16(17),
-	/* SMB2_WRITE */ __constant_cpu_to_le16(17),
-	/* SMB2_LOCK */ __constant_cpu_to_le16(4),
-	/* SMB2_IOCTL */ __constant_cpu_to_le16(49),
+	/* SMB2_NEGOTIATE */ cpu_to_le16(65),
+	/* SMB2_SESSION_SETUP */ cpu_to_le16(9),
+	/* SMB2_LOGOFF */ cpu_to_le16(4),
+	/* SMB2_TREE_CONNECT */ cpu_to_le16(16),
+	/* SMB2_TREE_DISCONNECT */ cpu_to_le16(4),
+	/* SMB2_CREATE */ cpu_to_le16(89),
+	/* SMB2_CLOSE */ cpu_to_le16(60),
+	/* SMB2_FLUSH */ cpu_to_le16(4),
+	/* SMB2_READ */ cpu_to_le16(17),
+	/* SMB2_WRITE */ cpu_to_le16(17),
+	/* SMB2_LOCK */ cpu_to_le16(4),
+	/* SMB2_IOCTL */ cpu_to_le16(49),
 	/* BB CHECK this ... not listed in documentation */
-	/* SMB2_CANCEL */ __constant_cpu_to_le16(0),
-	/* SMB2_ECHO */ __constant_cpu_to_le16(4),
-	/* SMB2_QUERY_DIRECTORY */ __constant_cpu_to_le16(9),
-	/* SMB2_CHANGE_NOTIFY */ __constant_cpu_to_le16(9),
-	/* SMB2_QUERY_INFO */ __constant_cpu_to_le16(9),
-	/* SMB2_SET_INFO */ __constant_cpu_to_le16(2),
+	/* SMB2_CANCEL */ cpu_to_le16(0),
+	/* SMB2_ECHO */ cpu_to_le16(4),
+	/* SMB2_QUERY_DIRECTORY */ cpu_to_le16(9),
+	/* SMB2_CHANGE_NOTIFY */ cpu_to_le16(9),
+	/* SMB2_QUERY_INFO */ cpu_to_le16(9),
+	/* SMB2_SET_INFO */ cpu_to_le16(2),
 	/* BB FIXME can also be 44 for lease break */
-	/* SMB2_OPLOCK_BREAK */ __constant_cpu_to_le16(24)
+	/* SMB2_OPLOCK_BREAK */ cpu_to_le16(24)
 };
 
 int
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 77f8aeb9c2fc..527833197fb3 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -597,7 +597,7 @@ smb2_clone_range(const unsigned int xid,
 		goto cchunk_out;
 
 	/* For now array only one chunk long, will make more flexible later */
-	pcchunk->ChunkCount = __constant_cpu_to_le32(1);
+	pcchunk->ChunkCount = cpu_to_le32(1);
 	pcchunk->Reserved = 0;
 	pcchunk->Reserved2 = 0;
 
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 42ebc1a8be6c..a5f2a5ce4cca 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1354,7 +1354,7 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 	char *ret_data = NULL;
 
 	fsctl_input.CompressionState =
-			__constant_cpu_to_le16(COMPRESSION_FORMAT_DEFAULT);
+			cpu_to_le16(COMPRESSION_FORMAT_DEFAULT);
 
 	rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid,
 			FSCTL_SET_COMPRESSION, true /* is_fsctl */,
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 69f3595d3952..d03adad014db 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -85,7 +85,7 @@
 /* BB FIXME - analyze following length BB */
 #define MAX_SMB2_HDR_SIZE 0x78 /* 4 len + 64 hdr + (2*24 wct) + 2 bct + 2 pad */
 
-#define SMB2_PROTO_NUMBER __constant_cpu_to_le32(0x424d53fe)
+#define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe)
 
 /*
  * SMB2 Header Definition
@@ -96,7 +96,7 @@
  *
  */
 
-#define SMB2_HEADER_STRUCTURE_SIZE __constant_cpu_to_le16(64)
+#define SMB2_HEADER_STRUCTURE_SIZE cpu_to_le16(64)
 
 struct smb2_hdr {
 	__be32 smb2_buf_length;	/* big endian on wire */
@@ -137,16 +137,16 @@ struct smb2_transform_hdr {
 } __packed;
 
 /* Encryption Algorithms */
-#define SMB2_ENCRYPTION_AES128_CCM	__constant_cpu_to_le16(0x0001)
+#define SMB2_ENCRYPTION_AES128_CCM	cpu_to_le16(0x0001)
 
 /*
  *	SMB2 flag definitions
  */
-#define SMB2_FLAGS_SERVER_TO_REDIR	__constant_cpu_to_le32(0x00000001)
-#define SMB2_FLAGS_ASYNC_COMMAND	__constant_cpu_to_le32(0x00000002)
-#define SMB2_FLAGS_RELATED_OPERATIONS	__constant_cpu_to_le32(0x00000004)
-#define SMB2_FLAGS_SIGNED		__constant_cpu_to_le32(0x00000008)
-#define SMB2_FLAGS_DFS_OPERATIONS	__constant_cpu_to_le32(0x10000000)
+#define SMB2_FLAGS_SERVER_TO_REDIR	cpu_to_le32(0x00000001)
+#define SMB2_FLAGS_ASYNC_COMMAND	cpu_to_le32(0x00000002)
+#define SMB2_FLAGS_RELATED_OPERATIONS	cpu_to_le32(0x00000004)
+#define SMB2_FLAGS_SIGNED		cpu_to_le32(0x00000008)
+#define SMB2_FLAGS_DFS_OPERATIONS	cpu_to_le32(0x10000000)
 
 /*
  *	Definitions for SMB2 Protocol Data Units (network frames)
@@ -157,7 +157,7 @@ struct smb2_transform_hdr {
  *
  */
 
-#define SMB2_ERROR_STRUCTURE_SIZE2 __constant_cpu_to_le16(9)
+#define SMB2_ERROR_STRUCTURE_SIZE2 cpu_to_le16(9)
 
 struct smb2_err_rsp {
 	struct smb2_hdr hdr;
@@ -500,12 +500,12 @@ struct create_context {
 #define SMB2_LEASE_HANDLE_CACHING_HE	0x02
 #define SMB2_LEASE_WRITE_CACHING_HE	0x04
 
-#define SMB2_LEASE_NONE			__constant_cpu_to_le32(0x00)
-#define SMB2_LEASE_READ_CACHING		__constant_cpu_to_le32(0x01)
-#define SMB2_LEASE_HANDLE_CACHING	__constant_cpu_to_le32(0x02)
-#define SMB2_LEASE_WRITE_CACHING	__constant_cpu_to_le32(0x04)
+#define SMB2_LEASE_NONE			cpu_to_le32(0x00)
+#define SMB2_LEASE_READ_CACHING		cpu_to_le32(0x01)
+#define SMB2_LEASE_HANDLE_CACHING	cpu_to_le32(0x02)
+#define SMB2_LEASE_WRITE_CACHING	cpu_to_le32(0x04)
 
-#define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS __constant_cpu_to_le32(0x02)
+#define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS cpu_to_le32(0x02)
 
 #define SMB2_LEASE_KEY_SIZE 16
 
diff --git a/fs/coda/cache.c b/fs/coda/cache.c
index 1da168c61d35..278f8fdeb9ef 100644
--- a/fs/coda/cache.c
+++ b/fs/coda/cache.c
@@ -13,7 +13,7 @@
 #include <linux/fs.h>
 #include <linux/stat.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/string.h>
 #include <linux/list.h>
 #include <linux/sched.h>
diff --git a/fs/coda/coda_linux.c b/fs/coda/coda_linux.c
index 2849f41e72a2..1326d38960db 100644
--- a/fs/coda/coda_linux.c
+++ b/fs/coda/coda_linux.c
@@ -13,7 +13,7 @@
 #include <linux/fs.h>
 #include <linux/stat.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/string.h>
 
 #include <linux/coda.h>
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index cd8a63238b11..9c3dedc000d1 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -19,8 +19,7 @@
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/namei.h>
-
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/coda.h>
 #include <linux/coda_psdev.h>
diff --git a/fs/coda/file.c b/fs/coda/file.c
index 9e83b7790212..d244d743a232 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -18,7 +18,7 @@
 #include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/coda.h>
 #include <linux/coda_psdev.h>
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index fe3afb2de880..b945410bfcd5 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -21,9 +21,7 @@
 #include <linux/vfs.h>
 #include <linux/slab.h>
 #include <linux/pid_namespace.h>
-
-#include <asm/uaccess.h>
-
+#include <linux/uaccess.h>
 #include <linux/fs.h>
 #include <linux/vmalloc.h>
 
diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c
index 3f5de96bbb58..4326d172fc27 100644
--- a/fs/coda/pioctl.c
+++ b/fs/coda/pioctl.c
@@ -16,7 +16,7 @@
 #include <linux/string.h>
 #include <linux/namei.h>
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/coda.h>
 #include <linux/coda_psdev.h>
diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c
index 5c1e4242368b..822629126e89 100644
--- a/fs/coda/psdev.c
+++ b/fs/coda/psdev.c
@@ -40,7 +40,7 @@
 #include <linux/pid_namespace.h>
 #include <asm/io.h>
 #include <asm/poll.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/coda.h>
 #include <linux/coda_psdev.h>
diff --git a/fs/coda/upcall.c b/fs/coda/upcall.c
index 21fcf8dcb9cd..5bb6e27298a4 100644
--- a/fs/coda/upcall.c
+++ b/fs/coda/upcall.c
@@ -27,7 +27,7 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/vmalloc.h>
 #include <linux/vfs.h>
 
diff --git a/fs/compat.c b/fs/compat.c
index 66d3d3c6b4b2..6917fdba382c 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -562,7 +562,7 @@ ssize_t compat_rw_copy_check_uvector(int type,
 		goto out;
 
 	ret = -EINVAL;
-	if (nr_segs > UIO_MAXIOV || nr_segs < 0)
+	if (nr_segs > UIO_MAXIOV)
 		goto out;
 	if (nr_segs > fast_segs) {
 		ret = -ENOMEM;
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index ddcfe590b8a8..355c522f3585 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -11,6 +11,8 @@
  * The actual compression is based on zlib, see the other files.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
@@ -21,7 +23,7 @@
 #include <linux/vfs.h>
 #include <linux/mutex.h>
 #include <uapi/linux/cramfs_fs.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "internal.h"
 
@@ -153,7 +155,7 @@ static struct inode *get_cramfs_inode(struct super_block *sb,
 
 static unsigned char read_buffers[READ_BUFFERS][BUFFER_SIZE];
 static unsigned buffer_blocknr[READ_BUFFERS];
-static struct super_block * buffer_dev[READ_BUFFERS];
+static struct super_block *buffer_dev[READ_BUFFERS];
 static int next_buffer;
 
 /*
@@ -205,6 +207,7 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i
 
 	for (i = 0; i < BLKS_PER_BUF; i++) {
 		struct page *page = pages[i];
+
 		if (page) {
 			wait_on_page_locked(page);
 			if (!PageUptodate(page)) {
@@ -223,6 +226,7 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i
 	data = read_buffers[buffer];
 	for (i = 0; i < BLKS_PER_BUF; i++) {
 		struct page *page = pages[i];
+
 		if (page) {
 			memcpy(data, kmap(page), PAGE_CACHE_SIZE);
 			kunmap(page);
@@ -237,6 +241,7 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i
 static void cramfs_kill_sb(struct super_block *sb)
 {
 	struct cramfs_sb_info *sbi = CRAMFS_SB(sb);
+
 	kill_block_super(sb);
 	kfree(sbi);
 }
@@ -277,7 +282,7 @@ static int cramfs_fill_super(struct super_block *sb, void *data, int silent)
 		/* check for wrong endianness */
 		if (super.magic == CRAMFS_MAGIC_WEND) {
 			if (!silent)
-				printk(KERN_ERR "cramfs: wrong endianness\n");
+				pr_err("wrong endianness\n");
 			return -EINVAL;
 		}
 
@@ -287,22 +292,22 @@ static int cramfs_fill_super(struct super_block *sb, void *data, int silent)
 		mutex_unlock(&read_mutex);
 		if (super.magic != CRAMFS_MAGIC) {
 			if (super.magic == CRAMFS_MAGIC_WEND && !silent)
-				printk(KERN_ERR "cramfs: wrong endianness\n");
+				pr_err("wrong endianness\n");
 			else if (!silent)
-				printk(KERN_ERR "cramfs: wrong magic\n");
+				pr_err("wrong magic\n");
 			return -EINVAL;
 		}
 	}
 
 	/* get feature flags first */
 	if (super.flags & ~CRAMFS_SUPPORTED_FLAGS) {
-		printk(KERN_ERR "cramfs: unsupported filesystem features\n");
+		pr_err("unsupported filesystem features\n");
 		return -EINVAL;
 	}
 
 	/* Check that the root inode is in a sane state */
 	if (!S_ISDIR(super.root.mode)) {
-		printk(KERN_ERR "cramfs: root is not a directory\n");
+		pr_err("root is not a directory\n");
 		return -EINVAL;
 	}
 	/* correct strange, hard-coded permissions of mkcramfs */
@@ -310,23 +315,23 @@ static int cramfs_fill_super(struct super_block *sb, void *data, int silent)
 
 	root_offset = super.root.offset << 2;
 	if (super.flags & CRAMFS_FLAG_FSID_VERSION_2) {
-		sbi->size=super.size;
-		sbi->blocks=super.fsid.blocks;
-		sbi->files=super.fsid.files;
+		sbi->size = super.size;
+		sbi->blocks = super.fsid.blocks;
+		sbi->files = super.fsid.files;
 	} else {
-		sbi->size=1<<28;
-		sbi->blocks=0;
-		sbi->files=0;
+		sbi->size = 1<<28;
+		sbi->blocks = 0;
+		sbi->files = 0;
 	}
-	sbi->magic=super.magic;
-	sbi->flags=super.flags;
+	sbi->magic = super.magic;
+	sbi->flags = super.flags;
 	if (root_offset == 0)
-		printk(KERN_INFO "cramfs: empty filesystem");
+		pr_info("empty filesystem");
 	else if (!(super.flags & CRAMFS_FLAG_SHIFTED_ROOT_OFFSET) &&
 		 ((root_offset != sizeof(struct cramfs_super)) &&
 		  (root_offset != 512 + sizeof(struct cramfs_super))))
 	{
-		printk(KERN_ERR "cramfs: bad root offset %lu\n", root_offset);
+		pr_err("bad root offset %lu\n", root_offset);
 		return -EINVAL;
 	}
 
@@ -425,7 +430,7 @@ static int cramfs_readdir(struct file *file, struct dir_context *ctx)
 /*
  * Lookup and fill in the inode data..
  */
-static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
+static struct dentry *cramfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 {
 	unsigned int offset = 0;
 	struct inode *inode = NULL;
@@ -483,7 +488,7 @@ out:
 	return NULL;
 }
 
-static int cramfs_readpage(struct file *file, struct page * page)
+static int cramfs_readpage(struct file *file, struct page *page)
 {
 	struct inode *inode = page->mapping->host;
 	u32 maxblock;
@@ -511,7 +516,7 @@ static int cramfs_readpage(struct file *file, struct page * page)
 		if (compr_len == 0)
 			; /* hole */
 		else if (unlikely(compr_len > (PAGE_CACHE_SIZE << 1))) {
-			pr_err("cramfs: bad compressed blocksize %u\n",
+			pr_err("bad compressed blocksize %u\n",
 				compr_len);
 			goto err;
 		} else {
diff --git a/fs/cramfs/uncompress.c b/fs/cramfs/uncompress.c
index 1760c1b84d97..ec4f1d4fdad0 100644
--- a/fs/cramfs/uncompress.c
+++ b/fs/cramfs/uncompress.c
@@ -15,6 +15,8 @@
  * then is used by multiple filesystems.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/vmalloc.h>
@@ -37,7 +39,7 @@ int cramfs_uncompress_block(void *dst, int dstlen, void *src, int srclen)
 
 	err = zlib_inflateReset(&stream);
 	if (err != Z_OK) {
-		printk("zlib_inflateReset error %d\n", err);
+		pr_err("zlib_inflateReset error %d\n", err);
 		zlib_inflateEnd(&stream);
 		zlib_inflateInit(&stream);
 	}
@@ -48,8 +50,8 @@ int cramfs_uncompress_block(void *dst, int dstlen, void *src, int srclen)
 	return stream.total_out;
 
 err:
-	printk("Error %d while decompressing!\n", err);
-	printk("%p(%d)->%p(%d)\n", src, srclen, dst, dstlen);
+	pr_err("Error %d while decompressing!\n", err);
+	pr_err("%p(%d)->%p(%d)\n", src, srclen, dst, dstlen);
 	return -EIO;
 }
 
@@ -57,7 +59,7 @@ int cramfs_uncompress_init(void)
 {
 	if (!initialized++) {
 		stream.workspace = vmalloc(zlib_inflate_workspacesize());
-		if ( !stream.workspace ) {
+		if (!stream.workspace) {
 			initialized = 0;
 			return -ENOMEM;
 		}
diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c
index 8d77ba7b1756..1323c568e362 100644
--- a/fs/dlm/debug_fs.c
+++ b/fs/dlm/debug_fs.c
@@ -718,16 +718,11 @@ static const struct file_operations waiters_fops = {
 
 void dlm_delete_debug_file(struct dlm_ls *ls)
 {
-	if (ls->ls_debug_rsb_dentry)
-		debugfs_remove(ls->ls_debug_rsb_dentry);
-	if (ls->ls_debug_waiters_dentry)
-		debugfs_remove(ls->ls_debug_waiters_dentry);
-	if (ls->ls_debug_locks_dentry)
-		debugfs_remove(ls->ls_debug_locks_dentry);
-	if (ls->ls_debug_all_dentry)
-		debugfs_remove(ls->ls_debug_all_dentry);
-	if (ls->ls_debug_toss_dentry)
-		debugfs_remove(ls->ls_debug_toss_dentry);
+	debugfs_remove(ls->ls_debug_rsb_dentry);
+	debugfs_remove(ls->ls_debug_waiters_dentry);
+	debugfs_remove(ls->ls_debug_locks_dentry);
+	debugfs_remove(ls->ls_debug_all_dentry);
+	debugfs_remove(ls->ls_debug_toss_dentry);
 }
 
 int dlm_create_debug_file(struct dlm_ls *ls)
diff --git a/fs/efs/namei.c b/fs/efs/namei.c
index 356c044e2cd3..bbee8f063dfa 100644
--- a/fs/efs/namei.c
+++ b/fs/efs/namei.c
@@ -12,7 +12,8 @@
 #include "efs.h"
 
 
-static efs_ino_t efs_find_entry(struct inode *inode, const char *name, int len) {
+static efs_ino_t efs_find_entry(struct inode *inode, const char *name, int len)
+{
 	struct buffer_head *bh;
 
 	int			slot, namelen;
@@ -40,10 +41,10 @@ static efs_ino_t efs_find_entry(struct inode *inode, const char *name, int len)
 		if (be16_to_cpu(dirblock->magic) != EFS_DIRBLK_MAGIC) {
 			pr_err("%s(): invalid directory block\n", __func__);
 			brelse(bh);
-			return(0);
+			return 0;
 		}
 
-		for(slot = 0; slot < dirblock->slots; slot++) {
+		for (slot = 0; slot < dirblock->slots; slot++) {
 			dirslot  = (struct efs_dentry *) (((char *) bh->b_data) + EFS_SLOTAT(dirblock, slot));
 
 			namelen  = dirslot->namelen;
@@ -52,12 +53,12 @@ static efs_ino_t efs_find_entry(struct inode *inode, const char *name, int len)
 			if ((namelen == len) && (!memcmp(name, nameptr, len))) {
 				inodenum = be32_to_cpu(dirslot->inode);
 				brelse(bh);
-				return(inodenum);
+				return inodenum;
 			}
 		}
 		brelse(bh);
 	}
-	return(0);
+	return 0;
 }
 
 struct dentry *efs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
diff --git a/fs/exec.c b/fs/exec.c
index ab1f1200ce5d..a2b42a98c743 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -368,10 +368,6 @@ static int bprm_mm_init(struct linux_binprm *bprm)
 	if (!mm)
 		goto err;
 
-	err = init_new_context(current, mm);
-	if (err)
-		goto err;
-
 	err = __bprm_mm_init(bprm);
 	if (err)
 		goto err;
diff --git a/fs/exofs/ore_raid.c b/fs/exofs/ore_raid.c
index 7f20f25c232c..84529b8a331b 100644
--- a/fs/exofs/ore_raid.c
+++ b/fs/exofs/ore_raid.c
@@ -116,7 +116,7 @@ static int _sp2d_alloc(unsigned pages_in_unit, unsigned group_width,
 			num_a1pa = min_t(unsigned, PAGE_SIZE / sizeof__a1pa,
 							pages_in_unit - i);
 
-			__a1pa = kzalloc(num_a1pa * sizeof__a1pa, GFP_KERNEL);
+			__a1pa = kcalloc(num_a1pa, sizeof__a1pa, GFP_KERNEL);
 			if (unlikely(!__a1pa)) {
 				ORE_DBGMSG("!! Failed to _alloc_1p_arrays=%d\n",
 					   num_a1pa);
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index a8bc47f75fa0..5b6e9f246233 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -107,7 +107,10 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	}
 
 	if (!journal) {
-		ret = generic_file_fsync(file, start, end, datasync);
+		if (test_opt(inode->i_sb, BARRIER))
+			ret = generic_file_fsync(file, start, end, datasync);
+		else
+			ret = __generic_file_fsync(file, start, end, datasync);
 		if (!ret && !hlist_empty(&inode->i_dentry))
 			ret = ext4_sync_parent(inode);
 		goto out;
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 610a3260bef1..435bea231cc6 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -44,7 +44,10 @@ 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) {
@@ -97,9 +100,11 @@ 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)
@@ -145,7 +150,7 @@ static int hfsplus_readdir(struct file *file, struct dir_context *ctx)
 		err = -ENOMEM;
 		goto out;
 	}
-	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/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index eb5e059f481a..b0441d65fa54 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -443,8 +443,10 @@ int hfsplus_cat_case_cmp_key(const hfsplus_btree_key *k1,
 			     const hfsplus_btree_key *k2);
 int hfsplus_cat_bin_cmp_key(const hfsplus_btree_key *k1,
 			    const hfsplus_btree_key *k2);
-void hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key,
+int hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key,
 			   u32 parent, struct qstr *str);
+void hfsplus_cat_build_key_with_cnid(struct super_block *sb,
+				     hfsplus_btree_key *key, u32 parent);
 void hfsplus_cat_set_perms(struct inode *inode, struct hfsplus_perm *perms);
 int hfsplus_find_cat(struct super_block *sb, u32 cnid,
 		     struct hfs_find_data *fd);
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 4cf2024b87da..593af2fdcc2d 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -515,7 +515,9 @@ 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/hpfs/dnode.c b/fs/hpfs/dnode.c
index f36fc010fccb..2923a7bd82ac 100644
--- a/fs/hpfs/dnode.c
+++ b/fs/hpfs/dnode.c
@@ -545,12 +545,13 @@ static void delete_empty_dnode(struct inode *i, dnode_secno dno)
 			struct dnode *d1;
 			struct quad_buffer_head qbh1;
 			if (hpfs_sb(i->i_sb)->sb_chk)
-			    if (up != i->i_ino) {
-				hpfs_error(i->i_sb,
-					"bad pointer to fnode, dnode %08x, pointing to %08x, should be %08lx",
-					dno, up, (unsigned long)i->i_ino);
-				return;
-			    }
+				if (up != i->i_ino) {
+					hpfs_error(i->i_sb,
+						   "bad pointer to fnode, dnode %08x, pointing to %08x, should be %08lx",
+						   dno, up,
+						   (unsigned long)i->i_ino);
+					return;
+				}
 			if ((d1 = hpfs_map_dnode(i->i_sb, down, &qbh1))) {
 				d1->up = cpu_to_le32(up);
 				d1->root_dnode = 1;
@@ -1061,8 +1062,8 @@ struct hpfs_dirent *map_fnode_dirent(struct super_block *s, fnode_secno fno,
 		hpfs_brelse4(qbh);
 		if (hpfs_sb(s)->sb_chk)
 			if (hpfs_stop_cycles(s, dno, &c1, &c2, "map_fnode_dirent #1")) {
-			kfree(name2);
-			return NULL;
+				kfree(name2);
+				return NULL;
 		}
 		goto go_down;
 	}
diff --git a/fs/isofs/Makefile b/fs/isofs/Makefile
index bf162f0942d5..47a68e357512 100644
--- a/fs/isofs/Makefile
+++ b/fs/isofs/Makefile
@@ -8,3 +8,5 @@ isofs-objs-y 			:= namei.o inode.o dir.o util.o rock.o export.o
 isofs-objs-$(CONFIG_JOLIET)	+= joliet.o
 isofs-objs-$(CONFIG_ZISOFS)	+= compress.o
 isofs-objs			:= $(isofs-objs-y)
+
+# ccflags-y := -DDEBUG_FLAGS=1
diff --git a/fs/isofs/compress.c b/fs/isofs/compress.c
index 592e5115a561..c9ba688dc407 100644
--- a/fs/isofs/compress.c
+++ b/fs/isofs/compress.c
@@ -15,6 +15,8 @@
  *
  * Transparent decompression of files on an iso9660 filesystem
  */
+#define DEBUG
+#define pr_fmt(fmt) "zisofs: " fmt
 
 #include <linux/module.h>
 #include <linux/init.h>
@@ -110,7 +112,7 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
 			*errp = -ENOMEM;
 		else
 			*errp = -EIO;
-		printk(KERN_DEBUG "zisofs: zisofs_inflateInit returned %d\n",
+		pr_debug("zisofs_inflateInit returned %d\n",
 			       zerr);
 		goto z_eio;
 	}
@@ -154,12 +156,12 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
 				if (zerr == Z_MEM_ERROR)
 					*errp = -ENOMEM;
 				else {
-					printk(KERN_DEBUG
+					pr_debug(
 					       "zisofs: zisofs_inflate returned"
 					       " %d, inode = %lu,"
 					       " page idx = %d, bh idx = %d,"
-					       " avail_in = %d,"
-					       " avail_out = %d\n",
+					       " avail_in = %ld,"
+					       " avail_out = %ld\n",
 					       zerr, inode->i_ino, curpage,
 					       curbh, stream.avail_in,
 					       stream.avail_out);
diff --git a/fs/isofs/export.c b/fs/isofs/export.c
index 12088d8de3fa..44d1053dfad5 100644
--- a/fs/isofs/export.c
+++ b/fs/isofs/export.c
@@ -12,7 +12,7 @@
  *     Documentation/filesystems/nfs/Exporting
  *     fs/exportfs/expfs.c.
  */
-
+#define pr_fmt(fmt) "ISOFS: " fmt
 #include "isofs.h"
 
 static struct dentry *
@@ -52,8 +52,7 @@ static struct dentry *isofs_export_get_parent(struct dentry *child)
 
 	/* "child" must always be a directory. */
 	if (!S_ISDIR(child_inode->i_mode)) {
-		printk(KERN_ERR "isofs: isofs_export_get_parent(): "
-		       "child is not a directory!\n");
+		pr_err("%s(): child is not a directory!\n", __func__);
 		rv = ERR_PTR(-EACCES);
 		goto out;
 	}
@@ -62,8 +61,7 @@ static struct dentry *isofs_export_get_parent(struct dentry *child)
 	 * it is not zero, it means the directory failed to be
 	 * normalized for some reason. */
 	if (e_child_inode->i_iget5_offset != 0) {
-		printk(KERN_ERR "isofs: isofs_export_get_parent(): "
-		       "child directory not normalized!\n");
+		pr_err("isofs_export_get_parent(): child directory not normalized!\n");
 		rv = ERR_PTR(-EACCES);
 		goto out;
 	}
@@ -89,8 +87,7 @@ static struct dentry *isofs_export_get_parent(struct dentry *child)
 
 	/* Verify it is in fact the ".." entry. */
 	if ((isonum_711(de->name_len) != 1) || (de->name[0] != 1)) {
-		printk(KERN_ERR "isofs: Unable to find the \"..\" "
-		       "directory for NFS.\n");
+		pr_err("Unable to find the \"..\" directory for NFS.\n");
 		rv = ERR_PTR(-EACCES);
 		goto out;
 	}
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 4556ce1af5b0..cc23d86e174a 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -10,6 +10,8 @@
  *	2004  Paul Serice - Inode Support pushed out from 4GB to 128GB
  *	2004  Paul Serice - NFS Export Operations
  */
+#define DEBUG
+#define pr_fmt(fmt) "ISOFS: " fmt
 
 #include <linux/init.h>
 #include <linux/module.h>
@@ -528,23 +530,25 @@ static unsigned int isofs_get_last_session(struct super_block *sb, s32 session)
 		Te.cdte_format=CDROM_LBA;
 		i = ioctl_by_bdev(bdev, CDROMREADTOCENTRY, (unsigned long) &Te);
 		if (!i) {
-			printk(KERN_DEBUG "ISOFS: Session %d start %d type %d\n",
+			pr_debug("Session %d start %d type %d\n",
 				session, Te.cdte_addr.lba,
 				Te.cdte_ctrl&CDROM_DATA_TRACK);
 			if ((Te.cdte_ctrl&CDROM_DATA_TRACK) == 4)
 				return Te.cdte_addr.lba;
 		}
 
-		printk(KERN_ERR "ISOFS: Invalid session number or type of track\n");
+		pr_err("Invalid session number or type of track\n");
 	}
 	i = ioctl_by_bdev(bdev, CDROMMULTISESSION, (unsigned long) &ms_info);
 	if (session > 0)
-		printk(KERN_ERR "ISOFS: Invalid session number\n");
+		pr_err("Invalid session number\n");
 #if 0
-	printk(KERN_DEBUG "isofs.inode: CDROMMULTISESSION: rc=%d\n",i);
+	pr_debug("isofs.inode: CDROMMULTISESSION: rc=%d\n", i);
 	if (i==0) {
-		printk(KERN_DEBUG "isofs.inode: XA disk: %s\n",ms_info.xa_flag?"yes":"no");
-		printk(KERN_DEBUG "isofs.inode: vol_desc_start = %d\n", ms_info.addr.lba);
+		pr_debug("isofs.inode: XA disk: %s\n",
+			 ms_info.xa_flag?"yes":"no");
+		pr_debug("isofs.inode: vol_desc_start = %d\n",
+			 ms_info.addr.lba);
 	}
 #endif
 	if (i==0)
@@ -672,8 +676,7 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent)
 						else if (sec->escape[2] == 0x45)
 							joliet_level = 3;
 
-						printk(KERN_DEBUG "ISO 9660 Extensions: "
-							"Microsoft Joliet Level %d\n",
+						pr_debug("ISO 9660 Extensions: Microsoft Joliet Level %d\n",
 							joliet_level);
 					}
 					goto root_found;
@@ -771,11 +774,11 @@ root_found:
 			  isonum_711(rootp->ext_attr_length);
 	sbi->s_firstdatazone = first_data_zone;
 #ifndef BEQUIET
-	printk(KERN_DEBUG "ISOFS: Max size:%ld   Log zone size:%ld\n",
+	pr_debug("Max size:%ld   Log zone size:%ld\n",
 		sbi->s_max_size, 1UL << sbi->s_log_zone_size);
-	printk(KERN_DEBUG "ISOFS: First datazone:%ld\n", sbi->s_firstdatazone);
+	pr_debug("First datazone:%ld\n", sbi->s_firstdatazone);
 	if(sbi->s_high_sierra)
-		printk(KERN_DEBUG "ISOFS: Disc in High Sierra format.\n");
+		pr_debug("Disc in High Sierra format.\n");
 #endif
 
 	/*
@@ -878,9 +881,7 @@ root_found:
 	 */
 	if (sbi->s_rock == 1 && joliet_level &&
 				rootdir_empty(s, sbi->s_firstdatazone)) {
-		printk(KERN_NOTICE
-			"ISOFS: primary root directory is empty. "
-			"Disabling Rock Ridge and switching to Joliet.");
+		pr_notice("primary root directory is empty. Disabling Rock Ridge and switching to Joliet.");
 		sbi->s_rock = 0;
 	}
 
@@ -898,8 +899,7 @@ root_found:
 		sbi->s_rock = 0;
 		if (sbi->s_firstdatazone != first_data_zone) {
 			sbi->s_firstdatazone = first_data_zone;
-			printk(KERN_DEBUG
-				"ISOFS: changing to secondary root\n");
+			pr_debug("changing to secondary root\n");
 			iput(inode);
 			inode = isofs_iget(s, sbi->s_firstdatazone, 0);
 			if (IS_ERR(inode))
@@ -918,9 +918,8 @@ root_found:
 
 	/* Make sure the root inode is a directory */
 	if (!S_ISDIR(inode->i_mode)) {
-		printk(KERN_WARNING
-			"isofs_fill_super: root inode is not a directory. "
-			"Corrupted media?\n");
+		pr_warn("%s: root inode is not a directory. Corrupted media?\n",
+			__func__);
 		goto out_iput;
 	}
 
@@ -952,27 +951,26 @@ out_iput:
 out_no_root:
 	error = PTR_ERR(inode);
 	if (error != -ENOMEM)
-		printk(KERN_WARNING "%s: get root inode failed\n", __func__);
+		pr_warn("%s: get root inode failed\n", __func__);
 out_no_inode:
 #ifdef CONFIG_JOLIET
 	unload_nls(sbi->s_nls_iocharset);
 #endif
 	goto out_freesbi;
 out_no_read:
-	printk(KERN_WARNING "%s: bread failed, dev=%s, iso_blknum=%d, block=%d\n",
+	pr_warn("%s: bread failed, dev=%s, iso_blknum=%d, block=%d\n",
 		__func__, s->s_id, iso_blknum, block);
 	goto out_freebh;
 out_bad_zone_size:
-	printk(KERN_WARNING "ISOFS: Bad logical zone size %ld\n",
-		sbi->s_log_zone_size);
+	pr_warn("Bad logical zone size %ld\n", sbi->s_log_zone_size);
 	goto out_freebh;
 out_bad_size:
-	printk(KERN_WARNING "ISOFS: Logical zone size(%d) < hardware blocksize(%u)\n",
+	pr_warn("Logical zone size(%d) < hardware blocksize(%u)\n",
 		orig_zonesize, opt.blocksize);
 	goto out_freebh;
 out_unknown_format:
 	if (!silent)
-		printk(KERN_WARNING "ISOFS: Unable to identify CD-ROM format.\n");
+		pr_warn("Unable to identify CD-ROM format.\n");
 
 out_freebh:
 	brelse(bh);
@@ -1021,7 +1019,7 @@ int isofs_get_blocks(struct inode *inode, sector_t iblock,
 	error = -EIO;
 	rv = 0;
 	if (iblock != b_off) {
-		printk(KERN_DEBUG "%s: block number too large\n", __func__);
+		pr_debug("%s: block number too large\n", __func__);
 		goto abort;
 	}
 
@@ -1042,7 +1040,7 @@ int isofs_get_blocks(struct inode *inode, sector_t iblock,
 		 * I/O errors.
 		 */
 		if (b_off > ((inode->i_size + PAGE_CACHE_SIZE - 1) >> ISOFS_BUFFER_BITS(inode))) {
-			printk(KERN_DEBUG "%s: block >= EOF (%lu, %llu)\n",
+			pr_debug("%s: block >= EOF (%lu, %llu)\n",
 				__func__, b_off,
 				(unsigned long long)inode->i_size);
 			goto abort;
@@ -1068,12 +1066,11 @@ int isofs_get_blocks(struct inode *inode, sector_t iblock,
 			iput(ninode);
 
 			if (++section > 100) {
-				printk(KERN_DEBUG "%s: More than 100 file sections ?!?"
-					" aborting...\n", __func__);
-				printk(KERN_DEBUG "%s: block=%lu firstext=%u sect_size=%u "
-					"nextblk=%lu nextoff=%lu\n", __func__,
-					b_off, firstext, (unsigned) sect_size,
-					nextblk, nextoff);
+				pr_debug("%s: More than 100 file sections ?!? aborting...\n",
+					 __func__);
+				pr_debug("%s: block=%lu firstext=%u sect_size=%u nextblk=%lu nextoff=%lu\n",
+					__func__, b_off, firstext,
+					(unsigned) sect_size, nextblk, nextoff);
 				goto abort;
 			}
 		}
@@ -1105,7 +1102,7 @@ static int isofs_get_block(struct inode *inode, sector_t iblock,
 	int ret;
 
 	if (create) {
-		printk(KERN_DEBUG "%s: Kernel tries to allocate a block\n", __func__);
+		pr_debug("%s: Kernel tries to allocate a block\n", __func__);
 		return -EROFS;
 	}
 
@@ -1248,13 +1245,12 @@ out_nomem:
 	return -ENOMEM;
 
 out_noread:
-	printk(KERN_INFO "ISOFS: unable to read i-node block %lu\n", block);
+	pr_info("unable to read i-node block %lu\n", block);
 	kfree(tmpde);
 	return -EIO;
 
 out_toomany:
-	printk(KERN_INFO "%s: More than 100 file sections ?!?, aborting...\n"
-		"isofs_read_level3_size: inode=%lu\n",
+	pr_info("%s: More than 100 file sections ?!?, aborting...\n isofs_read_level3_size: inode=%lu\n",
 		__func__, inode->i_ino);
 	goto out;
 }
@@ -1289,7 +1285,7 @@ static int isofs_read_inode(struct inode *inode)
 
 		tmpde = kmalloc(de_len, GFP_KERNEL);
 		if (tmpde == NULL) {
-			printk(KERN_INFO "%s: out of memory\n", __func__);
+			pr_info("%s: out of memory\n", __func__);
 			ret = -ENOMEM;
 			goto fail;
 		}
@@ -1364,24 +1360,23 @@ static int isofs_read_inode(struct inode *inode)
 		inode->i_size &= 0x00ffffff;
 
 	if (de->interleave[0]) {
-		printk(KERN_DEBUG "ISOFS: Interleaved files not (yet) supported.\n");
+		pr_debug("Interleaved files not (yet) supported.\n");
 		inode->i_size = 0;
 	}
 
 	/* I have no idea what file_unit_size is used for, so
 	   we will flag it for now */
 	if (de->file_unit_size[0] != 0) {
-		printk(KERN_DEBUG "ISOFS: File unit size != 0 for ISO file (%ld).\n",
-			inode->i_ino);
+		pr_debug("File unit size != 0 for ISO file (%ld).\n",
+			 inode->i_ino);
 	}
 
 	/* I have no idea what other flag bits are used for, so
 	   we will flag it for now */
-#ifdef DEBUG
+#ifdef DEBUG_FLAGS
 	if((de->flags[-high_sierra] & ~2)!= 0){
-		printk(KERN_DEBUG "ISOFS: Unusual flag settings for ISO file "
-				"(%ld %x).\n",
-			inode->i_ino, de->flags[-high_sierra]);
+		pr_debug("Unusual flag settings for ISO file (%ld %x).\n",
+			 inode->i_ino, de->flags[-high_sierra]);
 	}
 #endif
 
@@ -1450,7 +1445,7 @@ out:
 	return ret;
 
 out_badread:
-	printk(KERN_WARNING "ISOFS: unable to read i-node block\n");
+	pr_warn("unable to read i-node block\n");
 fail:
 	goto out;
 }
@@ -1541,6 +1536,7 @@ MODULE_ALIAS("iso9660");
 static int __init init_iso9660_fs(void)
 {
 	int err = init_inodecache();
+
 	if (err)
 		goto out;
 #ifdef CONFIG_ZISOFS
diff --git a/fs/isofs/namei.c b/fs/isofs/namei.c
index 95295640d9c8..c5ed09733112 100644
--- a/fs/isofs/namei.c
+++ b/fs/isofs/namei.c
@@ -113,9 +113,8 @@ isofs_find_entry(struct inode *dir, struct dentry *dentry,
 		dpnt = de->name;
 		/* Basic sanity check, whether name doesn't exceed dir entry */
 		if (de_len < dlen + sizeof(struct iso_directory_record)) {
-			printk(KERN_NOTICE "iso9660: Corrupted directory entry"
-			       " in block %lu of inode %lu\n", block,
-			       dir->i_ino);
+			pr_notice("Corrupted directory entry in block %lu of inode %lu\n",
+				  block, dir->i_ino);
 			return 0;
 		}
 
diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c
index c0bf42472e40..b13119556e5d 100644
--- a/fs/isofs/rock.c
+++ b/fs/isofs/rock.c
@@ -5,6 +5,8 @@
  *
  *  Rock Ridge Extensions to iso9660
  */
+#define DEBUG
+#define pr_fmt(fmt) "ISOFS: rock: " fmt
 
 #include <linux/slab.h>
 #include <linux/pagemap.h>
@@ -89,9 +91,8 @@ static int rock_continue(struct rock_state *rs)
 	if ((unsigned)rs->cont_offset > blocksize - min_de_size ||
 	    (unsigned)rs->cont_size > blocksize ||
 	    (unsigned)(rs->cont_offset + rs->cont_size) > blocksize) {
-		printk(KERN_NOTICE "rock: corrupted directory entry. "
-			"extent=%d, offset=%d, size=%d\n",
-			rs->cont_extent, rs->cont_offset, rs->cont_size);
+		pr_notice("corrupted directory entry. extent=%d, offset=%d, size=%d\n",
+			  rs->cont_extent, rs->cont_offset, rs->cont_size);
 		ret = -EIO;
 		goto out;
 	}
@@ -117,7 +118,7 @@ static int rock_continue(struct rock_state *rs)
 			rs->cont_offset = 0;
 			return 0;
 		}
-		printk("Unable to read rock-ridge attributes\n");
+		pr_warn("Unable to read rock-ridge attributes\n");
 	}
 out:
 	kfree(rs->buffer);
@@ -176,10 +177,9 @@ static int rock_check_overflow(struct rock_state *rs, int sig)
 	}
 	len += offsetof(struct rock_ridge, u);
 	if (len > rs->len) {
-		printk(KERN_NOTICE "rock: directory entry would overflow "
-				"storage\n");
-		printk(KERN_NOTICE "rock: sig=0x%02x, size=%d, remaining=%d\n",
-				sig, len, rs->len);
+		pr_notice("directory entry would overflow storage\n");
+		pr_notice("sig=0x%02x, size=%d, remaining=%d\n",
+			  sig, len, rs->len);
 		return -EIO;
 	}
 	return 0;
@@ -257,7 +257,7 @@ repeat:
 				break;
 
 			if (rr->u.NM.flags & ~1) {
-				printk("Unsupported NM flag settings (%d)\n",
+				pr_warn("Unsupported NM flag settings (%d)\n",
 					rr->u.NM.flags);
 				break;
 			}
@@ -353,13 +353,13 @@ repeat:
 			break;
 		case SIG('E', 'R'):
 			ISOFS_SB(inode->i_sb)->s_rock = 1;
-			printk(KERN_DEBUG "ISO 9660 Extensions: ");
+			pr_debug("ISO 9660 Extensions: ");
 			{
 				int p;
 				for (p = 0; p < rr->u.ER.len_id; p++)
-					printk("%c", rr->u.ER.data[p]);
+					pr_warn("%c", rr->u.ER.data[p]);
 			}
-			printk("\n");
+			pr_warn("\n");
 			break;
 		case SIG('P', 'X'):
 			inode->i_mode = isonum_733(rr->u.PX.mode);
@@ -450,8 +450,7 @@ repeat:
 						inode->i_size += 1;
 						break;
 					default:
-						printk("Symlink component flag "
-							"not implemented\n");
+						pr_warn("Symlink component flag not implemented\n");
 					}
 					slen -= slp->len + 2;
 					oldslp = slp;
@@ -481,8 +480,7 @@ repeat:
 			symlink_len = inode->i_size;
 			break;
 		case SIG('R', 'E'):
-			printk(KERN_WARNING "Attempt to read inode for "
-					"relocated directory\n");
+			pr_warn("Attempt to read inode for relocated directory\n");
 			goto out;
 		case SIG('C', 'L'):
 			ISOFS_I(inode)->i_first_extent =
@@ -518,9 +516,7 @@ repeat:
 				int block_shift =
 					isonum_711(&rr->u.ZF.parms[1]);
 				if (block_shift > 17) {
-					printk(KERN_WARNING "isofs: "
-						"Can't handle ZF block "
-						"size of 2^%d\n",
+					pr_warn("Can't handle ZF block size of 2^%d\n",
 						block_shift);
 				} else {
 					/*
@@ -543,9 +539,7 @@ repeat:
 						       real_size);
 				}
 			} else {
-				printk(KERN_WARNING
-				       "isofs: Unknown ZF compression "
-						"algorithm: %c%c\n",
+				pr_warn("Unknown ZF compression algorithm: %c%c\n",
 				       rr->u.ZF.algorithm[0],
 				       rr->u.ZF.algorithm[1]);
 			}
@@ -604,7 +598,7 @@ static char *get_symlink_chunk(char *rpnt, struct rock_ridge *rr, char *plimit)
 			*rpnt++ = '/';
 			break;
 		default:
-			printk("Symlink component flag not implemented (%d)\n",
+			pr_warn("Symlink component flag not implemented (%d)\n",
 			       slp->flags);
 		}
 		slen -= slp->len + 2;
@@ -757,10 +751,10 @@ out:
 	kfree(rs.buffer);
 	goto fail;
 out_noread:
-	printk("unable to read i-node block");
+	pr_warn("unable to read i-node block");
 	goto fail;
 out_bad_span:
-	printk("symlink spans iso9660 blocks\n");
+	pr_warn("symlink spans iso9660 blocks\n");
 fail:
 	brelse(bh);
 error:
diff --git a/fs/jffs2/compr_zlib.c b/fs/jffs2/compr_zlib.c
index 0b9a1e44e833..5698dae5d92d 100644
--- a/fs/jffs2/compr_zlib.c
+++ b/fs/jffs2/compr_zlib.c
@@ -94,11 +94,12 @@ static int jffs2_zlib_compress(unsigned char *data_in,
 
 	while (def_strm.total_out < *dstlen - STREAM_END_SPACE && def_strm.total_in < *sourcelen) {
 		def_strm.avail_out = *dstlen - (def_strm.total_out + STREAM_END_SPACE);
-		def_strm.avail_in = min((unsigned)(*sourcelen-def_strm.total_in), def_strm.avail_out);
-		jffs2_dbg(1, "calling deflate with avail_in %d, avail_out %d\n",
+		def_strm.avail_in = min_t(unsigned long,
+			(*sourcelen-def_strm.total_in), def_strm.avail_out);
+		jffs2_dbg(1, "calling deflate with avail_in %ld, avail_out %ld\n",
 			  def_strm.avail_in, def_strm.avail_out);
 		ret = zlib_deflate(&def_strm, Z_PARTIAL_FLUSH);
-		jffs2_dbg(1, "deflate returned with avail_in %d, avail_out %d, total_in %ld, total_out %ld\n",
+		jffs2_dbg(1, "deflate returned with avail_in %ld, avail_out %ld, total_in %ld, total_out %ld\n",
 			  def_strm.avail_in, def_strm.avail_out,
 			  def_strm.total_in, def_strm.total_out);
 		if (ret != Z_OK) {
diff --git a/fs/mpage.c b/fs/mpage.c
index 5f9ed622274f..003f6fe3cdb6 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -480,6 +480,7 @@ 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);
@@ -588,7 +589,7 @@ 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) {
@@ -612,7 +613,7 @@ 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;
 	}
 
@@ -622,7 +623,7 @@ 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);
@@ -634,7 +635,7 @@ 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);
@@ -690,8 +691,11 @@ 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;
@@ -708,8 +712,11 @@ 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/nilfs2/Makefile b/fs/nilfs2/Makefile
index 85c98737a146..fc603e0431bb 100644
--- a/fs/nilfs2/Makefile
+++ b/fs/nilfs2/Makefile
@@ -2,4 +2,4 @@ obj-$(CONFIG_NILFS2_FS) += nilfs2.o
 nilfs2-y := inode.o file.o dir.o super.o namei.o page.o mdt.o \
 	btnode.o bmap.o btree.o direct.o dat.o recovery.o \
 	the_nilfs.o segbuf.o segment.o cpfile.o sufile.o \
-	ifile.o alloc.o gcinode.o ioctl.o
+	ifile.o alloc.o gcinode.o ioctl.o sysfs.o
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 9bc72dec3fa6..0696161bf59d 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -320,6 +320,14 @@ int nilfs_gccache_wait_and_mark_dirty(struct buffer_head *);
 int nilfs_init_gcinode(struct inode *inode);
 void nilfs_remove_all_gcinodes(struct the_nilfs *nilfs);
 
+/* sysfs.c */
+int __init nilfs_sysfs_init(void);
+void nilfs_sysfs_exit(void);
+int nilfs_sysfs_create_device_group(struct super_block *);
+void nilfs_sysfs_delete_device_group(struct the_nilfs *);
+int nilfs_sysfs_create_snapshot_group(struct nilfs_root *);
+void nilfs_sysfs_delete_snapshot_group(struct nilfs_root *);
+
 /*
  * Inodes and files operations
  */
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index ac914994dfed..058470602cd1 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1014,7 +1014,7 @@ int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno)
 	struct dentry *dentry;
 	int ret;
 
-	if (cno < 0 || cno > nilfs->ns_cno)
+	if (cno > nilfs->ns_cno)
 		return false;
 
 	if (cno >= nilfs_last_cno(nilfs))
@@ -1452,13 +1452,19 @@ static int __init init_nilfs_fs(void)
 	if (err)
 		goto fail;
 
-	err = register_filesystem(&nilfs_fs_type);
+	err = nilfs_sysfs_init();
 	if (err)
 		goto free_cachep;
 
+	err = register_filesystem(&nilfs_fs_type);
+	if (err)
+		goto deinit_sysfs_entry;
+
 	printk(KERN_INFO "NILFS version 2 loaded\n");
 	return 0;
 
+deinit_sysfs_entry:
+	nilfs_sysfs_exit();
 free_cachep:
 	nilfs_destroy_cachep();
 fail:
@@ -1468,6 +1474,7 @@ fail:
 static void __exit exit_nilfs_fs(void)
 {
 	nilfs_destroy_cachep();
+	nilfs_sysfs_exit();
 	unregister_filesystem(&nilfs_fs_type);
 }
 
diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c
new file mode 100644
index 000000000000..bbb0dcc35905
--- /dev/null
+++ b/fs/nilfs2/sysfs.c
@@ -0,0 +1,1137 @@
+/*
+ * sysfs.c - sysfs support implementation.
+ *
+ * Copyright (C) 2005-2014 Nippon Telegraph and Telephone Corporation.
+ * Copyright (C) 2014 HGST, Inc., a Western Digital Company.
+ *
+ * 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.
+ *
+ * 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.
+ *
+ * Written by Vyacheslav Dubeyko <Vyacheslav.Dubeyko@hgst.com>
+ */
+
+#include <linux/kobject.h>
+
+#include "nilfs.h"
+#include "mdt.h"
+#include "sufile.h"
+#include "cpfile.h"
+#include "sysfs.h"
+
+/* /sys/fs/<nilfs>/ */
+static struct kset *nilfs_kset;
+
+#define NILFS_SHOW_TIME(time_t_val, buf) ({ \
+		struct tm res; \
+		int count = 0; \
+		time_to_tm(time_t_val, 0, &res); \
+		res.tm_year += 1900; \
+		res.tm_mon += 1; \
+		count = scnprintf(buf, PAGE_SIZE, \
+				    "%ld-%.2d-%.2d %.2d:%.2d:%.2d\n", \
+				    res.tm_year, res.tm_mon, res.tm_mday, \
+				    res.tm_hour, res.tm_min, res.tm_sec);\
+		count; \
+})
+
+#define NILFS_DEV_INT_GROUP_OPS(name, parent_name) \
+static ssize_t nilfs_##name##_attr_show(struct kobject *kobj, \
+					struct attribute *attr, char *buf) \
+{ \
+	struct the_nilfs *nilfs = container_of(kobj->parent, \
+						struct the_nilfs, \
+						ns_##parent_name##_kobj); \
+	struct nilfs_##name##_attr *a = container_of(attr, \
+						struct nilfs_##name##_attr, \
+						attr); \
+	return a->show ? a->show(a, nilfs, buf) : 0; \
+} \
+static ssize_t nilfs_##name##_attr_store(struct kobject *kobj, \
+					 struct attribute *attr, \
+					 const char *buf, size_t len) \
+{ \
+	struct the_nilfs *nilfs = container_of(kobj->parent, \
+						struct the_nilfs, \
+						ns_##parent_name##_kobj); \
+	struct nilfs_##name##_attr *a = container_of(attr, \
+						struct nilfs_##name##_attr, \
+						attr); \
+	return a->store ? a->store(a, nilfs, buf, len) : 0; \
+} \
+static const struct sysfs_ops nilfs_##name##_attr_ops = { \
+	.show	= nilfs_##name##_attr_show, \
+	.store	= nilfs_##name##_attr_store, \
+};
+
+#define NILFS_DEV_INT_GROUP_TYPE(name, parent_name) \
+static void nilfs_##name##_attr_release(struct kobject *kobj) \
+{ \
+	struct nilfs_sysfs_##parent_name##_subgroups *subgroups; \
+	struct the_nilfs *nilfs = container_of(kobj->parent, \
+						struct the_nilfs, \
+						ns_##parent_name##_kobj); \
+	subgroups = nilfs->ns_##parent_name##_subgroups; \
+	complete(&subgroups->sg_##name##_kobj_unregister); \
+} \
+static struct kobj_type nilfs_##name##_ktype = { \
+	.default_attrs	= nilfs_##name##_attrs, \
+	.sysfs_ops	= &nilfs_##name##_attr_ops, \
+	.release	= nilfs_##name##_attr_release, \
+};
+
+#define NILFS_DEV_INT_GROUP_FNS(name, parent_name) \
+static int nilfs_sysfs_create_##name##_group(struct the_nilfs *nilfs) \
+{ \
+	struct kobject *parent; \
+	struct kobject *kobj; \
+	struct completion *kobj_unregister; \
+	struct nilfs_sysfs_##parent_name##_subgroups *subgroups; \
+	int err; \
+	subgroups = nilfs->ns_##parent_name##_subgroups; \
+	kobj = &subgroups->sg_##name##_kobj; \
+	kobj_unregister = &subgroups->sg_##name##_kobj_unregister; \
+	parent = &nilfs->ns_##parent_name##_kobj; \
+	kobj->kset = nilfs_kset; \
+	init_completion(kobj_unregister); \
+	err = kobject_init_and_add(kobj, &nilfs_##name##_ktype, parent, \
+				    #name); \
+	if (err) \
+		return err; \
+	return 0; \
+} \
+static void nilfs_sysfs_delete_##name##_group(struct the_nilfs *nilfs) \
+{ \
+	kobject_del(&nilfs->ns_##parent_name##_subgroups->sg_##name##_kobj); \
+}
+
+/************************************************************************
+ *                        NILFS snapshot attrs                          *
+ ************************************************************************/
+
+static ssize_t
+nilfs_snapshot_inodes_count_show(struct nilfs_snapshot_attr *attr,
+				 struct nilfs_root *root, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%llu\n",
+			(unsigned long long)atomic64_read(&root->inodes_count));
+}
+
+static ssize_t
+nilfs_snapshot_blocks_count_show(struct nilfs_snapshot_attr *attr,
+				 struct nilfs_root *root, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%llu\n",
+			(unsigned long long)atomic64_read(&root->blocks_count));
+}
+
+static const char snapshot_readme_str[] =
+	"The group contains details about mounted snapshot.\n\n"
+	"(1) inodes_count\n\tshow number of inodes for snapshot.\n\n"
+	"(2) blocks_count\n\tshow number of blocks for snapshot.\n\n";
+
+static ssize_t
+nilfs_snapshot_README_show(struct nilfs_snapshot_attr *attr,
+			    struct nilfs_root *root, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, snapshot_readme_str);
+}
+
+NILFS_SNAPSHOT_RO_ATTR(inodes_count);
+NILFS_SNAPSHOT_RO_ATTR(blocks_count);
+NILFS_SNAPSHOT_RO_ATTR(README);
+
+static struct attribute *nilfs_snapshot_attrs[] = {
+	NILFS_SNAPSHOT_ATTR_LIST(inodes_count),
+	NILFS_SNAPSHOT_ATTR_LIST(blocks_count),
+	NILFS_SNAPSHOT_ATTR_LIST(README),
+	NULL,
+};
+
+static ssize_t nilfs_snapshot_attr_show(struct kobject *kobj,
+					struct attribute *attr, char *buf)
+{
+	struct nilfs_root *root =
+			container_of(kobj, struct nilfs_root, snapshot_kobj);
+	struct nilfs_snapshot_attr *a =
+			container_of(attr, struct nilfs_snapshot_attr, attr);
+
+	return a->show ? a->show(a, root, buf) : 0;
+}
+
+static ssize_t nilfs_snapshot_attr_store(struct kobject *kobj,
+					 struct attribute *attr,
+					 const char *buf, size_t len)
+{
+	struct nilfs_root *root =
+			container_of(kobj, struct nilfs_root, snapshot_kobj);
+	struct nilfs_snapshot_attr *a =
+			container_of(attr, struct nilfs_snapshot_attr, attr);
+
+	return a->store ? a->store(a, root, buf, len) : 0;
+}
+
+static void nilfs_snapshot_attr_release(struct kobject *kobj)
+{
+	struct nilfs_root *root = container_of(kobj, struct nilfs_root,
+						snapshot_kobj);
+	complete(&root->snapshot_kobj_unregister);
+}
+
+static const struct sysfs_ops nilfs_snapshot_attr_ops = {
+	.show	= nilfs_snapshot_attr_show,
+	.store	= nilfs_snapshot_attr_store,
+};
+
+static struct kobj_type nilfs_snapshot_ktype = {
+	.default_attrs	= nilfs_snapshot_attrs,
+	.sysfs_ops	= &nilfs_snapshot_attr_ops,
+	.release	= nilfs_snapshot_attr_release,
+};
+
+int nilfs_sysfs_create_snapshot_group(struct nilfs_root *root)
+{
+	struct the_nilfs *nilfs;
+	struct kobject *parent;
+	int err;
+
+	nilfs = root->nilfs;
+	parent = &nilfs->ns_dev_subgroups->sg_mounted_snapshots_kobj;
+	root->snapshot_kobj.kset = nilfs_kset;
+	init_completion(&root->snapshot_kobj_unregister);
+
+	if (root->cno == NILFS_CPTREE_CURRENT_CNO) {
+		err = kobject_init_and_add(&root->snapshot_kobj,
+					    &nilfs_snapshot_ktype,
+					    &nilfs->ns_dev_kobj,
+					    "current_checkpoint");
+	} else {
+		err = kobject_init_and_add(&root->snapshot_kobj,
+					    &nilfs_snapshot_ktype,
+					    parent,
+					    "%llu", root->cno);
+	}
+
+	if (err)
+		return err;
+
+	return 0;
+}
+
+void nilfs_sysfs_delete_snapshot_group(struct nilfs_root *root)
+{
+	kobject_del(&root->snapshot_kobj);
+}
+
+/************************************************************************
+ *                    NILFS mounted snapshots attrs                     *
+ ************************************************************************/
+
+static const char mounted_snapshots_readme_str[] =
+	"The mounted_snapshots group contains group for\n"
+	"every mounted snapshot.\n";
+
+static ssize_t
+nilfs_mounted_snapshots_README_show(struct nilfs_mounted_snapshots_attr *attr,
+				    struct the_nilfs *nilfs, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, mounted_snapshots_readme_str);
+}
+
+NILFS_MOUNTED_SNAPSHOTS_RO_ATTR(README);
+
+static struct attribute *nilfs_mounted_snapshots_attrs[] = {
+	NILFS_MOUNTED_SNAPSHOTS_ATTR_LIST(README),
+	NULL,
+};
+
+NILFS_DEV_INT_GROUP_OPS(mounted_snapshots, dev);
+NILFS_DEV_INT_GROUP_TYPE(mounted_snapshots, dev);
+NILFS_DEV_INT_GROUP_FNS(mounted_snapshots, dev);
+
+/************************************************************************
+ *                      NILFS checkpoints attrs                         *
+ ************************************************************************/
+
+static ssize_t
+nilfs_checkpoints_checkpoints_number_show(struct nilfs_checkpoints_attr *attr,
+					    struct the_nilfs *nilfs,
+					    char *buf)
+{
+	__u64 ncheckpoints;
+	struct nilfs_cpstat cpstat;
+	int err;
+
+	down_read(&nilfs->ns_segctor_sem);
+	err = nilfs_cpfile_get_stat(nilfs->ns_cpfile, &cpstat);
+	up_read(&nilfs->ns_segctor_sem);
+	if (err < 0) {
+		printk(KERN_ERR "NILFS: unable to get checkpoint stat: err=%d\n",
+			err);
+		return err;
+	}
+
+	ncheckpoints = cpstat.cs_ncps;
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n", ncheckpoints);
+}
+
+static ssize_t
+nilfs_checkpoints_snapshots_number_show(struct nilfs_checkpoints_attr *attr,
+					struct the_nilfs *nilfs,
+					char *buf)
+{
+	__u64 nsnapshots;
+	struct nilfs_cpstat cpstat;
+	int err;
+
+	down_read(&nilfs->ns_segctor_sem);
+	err = nilfs_cpfile_get_stat(nilfs->ns_cpfile, &cpstat);
+	up_read(&nilfs->ns_segctor_sem);
+	if (err < 0) {
+		printk(KERN_ERR "NILFS: unable to get checkpoint stat: err=%d\n",
+			err);
+		return err;
+	}
+
+	nsnapshots = cpstat.cs_nsss;
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n", nsnapshots);
+}
+
+static ssize_t
+nilfs_checkpoints_last_seg_checkpoint_show(struct nilfs_checkpoints_attr *attr,
+					    struct the_nilfs *nilfs,
+					    char *buf)
+{
+	__u64 last_cno;
+
+	spin_lock(&nilfs->ns_last_segment_lock);
+	last_cno = nilfs->ns_last_cno;
+	spin_unlock(&nilfs->ns_last_segment_lock);
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n", last_cno);
+}
+
+static ssize_t
+nilfs_checkpoints_next_checkpoint_show(struct nilfs_checkpoints_attr *attr,
+					struct the_nilfs *nilfs,
+					char *buf)
+{
+	__u64 cno;
+
+	down_read(&nilfs->ns_sem);
+	cno = nilfs->ns_cno;
+	up_read(&nilfs->ns_sem);
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n", cno);
+}
+
+static const char checkpoints_readme_str[] =
+	"The checkpoints group contains attributes that describe\n"
+	"details about volume's checkpoints.\n\n"
+	"(1) checkpoints_number\n\tshow number of checkpoints on volume.\n\n"
+	"(2) snapshots_number\n\tshow number of snapshots on volume.\n\n"
+	"(3) last_seg_checkpoint\n"
+	"\tshow checkpoint number of the latest segment.\n\n"
+	"(4) next_checkpoint\n\tshow next checkpoint number.\n\n";
+
+static ssize_t
+nilfs_checkpoints_README_show(struct nilfs_checkpoints_attr *attr,
+				struct the_nilfs *nilfs, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, checkpoints_readme_str);
+}
+
+NILFS_CHECKPOINTS_RO_ATTR(checkpoints_number);
+NILFS_CHECKPOINTS_RO_ATTR(snapshots_number);
+NILFS_CHECKPOINTS_RO_ATTR(last_seg_checkpoint);
+NILFS_CHECKPOINTS_RO_ATTR(next_checkpoint);
+NILFS_CHECKPOINTS_RO_ATTR(README);
+
+static struct attribute *nilfs_checkpoints_attrs[] = {
+	NILFS_CHECKPOINTS_ATTR_LIST(checkpoints_number),
+	NILFS_CHECKPOINTS_ATTR_LIST(snapshots_number),
+	NILFS_CHECKPOINTS_ATTR_LIST(last_seg_checkpoint),
+	NILFS_CHECKPOINTS_ATTR_LIST(next_checkpoint),
+	NILFS_CHECKPOINTS_ATTR_LIST(README),
+	NULL,
+};
+
+NILFS_DEV_INT_GROUP_OPS(checkpoints, dev);
+NILFS_DEV_INT_GROUP_TYPE(checkpoints, dev);
+NILFS_DEV_INT_GROUP_FNS(checkpoints, dev);
+
+/************************************************************************
+ *                        NILFS segments attrs                          *
+ ************************************************************************/
+
+static ssize_t
+nilfs_segments_segments_number_show(struct nilfs_segments_attr *attr,
+				     struct the_nilfs *nilfs,
+				     char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%lu\n", nilfs->ns_nsegments);
+}
+
+static ssize_t
+nilfs_segments_blocks_per_segment_show(struct nilfs_segments_attr *attr,
+					struct the_nilfs *nilfs,
+					char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%lu\n", nilfs->ns_blocks_per_segment);
+}
+
+static ssize_t
+nilfs_segments_clean_segments_show(struct nilfs_segments_attr *attr,
+				    struct the_nilfs *nilfs,
+				    char *buf)
+{
+	unsigned long ncleansegs;
+
+	down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
+	ncleansegs = nilfs_sufile_get_ncleansegs(nilfs->ns_sufile);
+	up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
+
+	return snprintf(buf, PAGE_SIZE, "%lu\n", ncleansegs);
+}
+
+static ssize_t
+nilfs_segments_dirty_segments_show(struct nilfs_segments_attr *attr,
+				    struct the_nilfs *nilfs,
+				    char *buf)
+{
+	struct nilfs_sustat sustat;
+	int err;
+
+	down_read(&nilfs->ns_segctor_sem);
+	err = nilfs_sufile_get_stat(nilfs->ns_sufile, &sustat);
+	up_read(&nilfs->ns_segctor_sem);
+	if (err < 0) {
+		printk(KERN_ERR "NILFS: unable to get segment stat: err=%d\n",
+			err);
+		return err;
+	}
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n", sustat.ss_ndirtysegs);
+}
+
+static const char segments_readme_str[] =
+	"The segments group contains attributes that describe\n"
+	"details about volume's segments.\n\n"
+	"(1) segments_number\n\tshow number of segments on volume.\n\n"
+	"(2) blocks_per_segment\n\tshow number of blocks in segment.\n\n"
+	"(3) clean_segments\n\tshow count of clean segments.\n\n"
+	"(4) dirty_segments\n\tshow count of dirty segments.\n\n";
+
+static ssize_t
+nilfs_segments_README_show(struct nilfs_segments_attr *attr,
+			    struct the_nilfs *nilfs,
+			    char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, segments_readme_str);
+}
+
+NILFS_SEGMENTS_RO_ATTR(segments_number);
+NILFS_SEGMENTS_RO_ATTR(blocks_per_segment);
+NILFS_SEGMENTS_RO_ATTR(clean_segments);
+NILFS_SEGMENTS_RO_ATTR(dirty_segments);
+NILFS_SEGMENTS_RO_ATTR(README);
+
+static struct attribute *nilfs_segments_attrs[] = {
+	NILFS_SEGMENTS_ATTR_LIST(segments_number),
+	NILFS_SEGMENTS_ATTR_LIST(blocks_per_segment),
+	NILFS_SEGMENTS_ATTR_LIST(clean_segments),
+	NILFS_SEGMENTS_ATTR_LIST(dirty_segments),
+	NILFS_SEGMENTS_ATTR_LIST(README),
+	NULL,
+};
+
+NILFS_DEV_INT_GROUP_OPS(segments, dev);
+NILFS_DEV_INT_GROUP_TYPE(segments, dev);
+NILFS_DEV_INT_GROUP_FNS(segments, dev);
+
+/************************************************************************
+ *                        NILFS segctor attrs                           *
+ ************************************************************************/
+
+static ssize_t
+nilfs_segctor_last_pseg_block_show(struct nilfs_segctor_attr *attr,
+				    struct the_nilfs *nilfs,
+				    char *buf)
+{
+	sector_t last_pseg;
+
+	spin_lock(&nilfs->ns_last_segment_lock);
+	last_pseg = nilfs->ns_last_pseg;
+	spin_unlock(&nilfs->ns_last_segment_lock);
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n",
+			(unsigned long long)last_pseg);
+}
+
+static ssize_t
+nilfs_segctor_last_seg_sequence_show(struct nilfs_segctor_attr *attr,
+					struct the_nilfs *nilfs,
+					char *buf)
+{
+	u64 last_seq;
+
+	spin_lock(&nilfs->ns_last_segment_lock);
+	last_seq = nilfs->ns_last_seq;
+	spin_unlock(&nilfs->ns_last_segment_lock);
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n", last_seq);
+}
+
+static ssize_t
+nilfs_segctor_last_seg_checkpoint_show(struct nilfs_segctor_attr *attr,
+					struct the_nilfs *nilfs,
+					char *buf)
+{
+	__u64 last_cno;
+
+	spin_lock(&nilfs->ns_last_segment_lock);
+	last_cno = nilfs->ns_last_cno;
+	spin_unlock(&nilfs->ns_last_segment_lock);
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n", last_cno);
+}
+
+static ssize_t
+nilfs_segctor_current_seg_sequence_show(struct nilfs_segctor_attr *attr,
+					struct the_nilfs *nilfs,
+					char *buf)
+{
+	u64 seg_seq;
+
+	down_read(&nilfs->ns_sem);
+	seg_seq = nilfs->ns_seg_seq;
+	up_read(&nilfs->ns_sem);
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n", seg_seq);
+}
+
+static ssize_t
+nilfs_segctor_current_last_full_seg_show(struct nilfs_segctor_attr *attr,
+					 struct the_nilfs *nilfs,
+					 char *buf)
+{
+	__u64 segnum;
+
+	down_read(&nilfs->ns_sem);
+	segnum = nilfs->ns_segnum;
+	up_read(&nilfs->ns_sem);
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n", segnum);
+}
+
+static ssize_t
+nilfs_segctor_next_full_seg_show(struct nilfs_segctor_attr *attr,
+				 struct the_nilfs *nilfs,
+				 char *buf)
+{
+	__u64 nextnum;
+
+	down_read(&nilfs->ns_sem);
+	nextnum = nilfs->ns_nextnum;
+	up_read(&nilfs->ns_sem);
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n", nextnum);
+}
+
+static ssize_t
+nilfs_segctor_next_pseg_offset_show(struct nilfs_segctor_attr *attr,
+					struct the_nilfs *nilfs,
+					char *buf)
+{
+	unsigned long pseg_offset;
+
+	down_read(&nilfs->ns_sem);
+	pseg_offset = nilfs->ns_pseg_offset;
+	up_read(&nilfs->ns_sem);
+
+	return snprintf(buf, PAGE_SIZE, "%lu\n", pseg_offset);
+}
+
+static ssize_t
+nilfs_segctor_next_checkpoint_show(struct nilfs_segctor_attr *attr,
+					struct the_nilfs *nilfs,
+					char *buf)
+{
+	__u64 cno;
+
+	down_read(&nilfs->ns_sem);
+	cno = nilfs->ns_cno;
+	up_read(&nilfs->ns_sem);
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n", cno);
+}
+
+static ssize_t
+nilfs_segctor_last_seg_write_time_show(struct nilfs_segctor_attr *attr,
+					struct the_nilfs *nilfs,
+					char *buf)
+{
+	time_t ctime;
+
+	down_read(&nilfs->ns_sem);
+	ctime = nilfs->ns_ctime;
+	up_read(&nilfs->ns_sem);
+
+	return NILFS_SHOW_TIME(ctime, buf);
+}
+
+static ssize_t
+nilfs_segctor_last_seg_write_time_secs_show(struct nilfs_segctor_attr *attr,
+					    struct the_nilfs *nilfs,
+					    char *buf)
+{
+	time_t ctime;
+
+	down_read(&nilfs->ns_sem);
+	ctime = nilfs->ns_ctime;
+	up_read(&nilfs->ns_sem);
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n", (unsigned long long)ctime);
+}
+
+static ssize_t
+nilfs_segctor_last_nongc_write_time_show(struct nilfs_segctor_attr *attr,
+					 struct the_nilfs *nilfs,
+					 char *buf)
+{
+	time_t nongc_ctime;
+
+	down_read(&nilfs->ns_sem);
+	nongc_ctime = nilfs->ns_nongc_ctime;
+	up_read(&nilfs->ns_sem);
+
+	return NILFS_SHOW_TIME(nongc_ctime, buf);
+}
+
+static ssize_t
+nilfs_segctor_last_nongc_write_time_secs_show(struct nilfs_segctor_attr *attr,
+						struct the_nilfs *nilfs,
+						char *buf)
+{
+	time_t nongc_ctime;
+
+	down_read(&nilfs->ns_sem);
+	nongc_ctime = nilfs->ns_nongc_ctime;
+	up_read(&nilfs->ns_sem);
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n",
+			(unsigned long long)nongc_ctime);
+}
+
+static ssize_t
+nilfs_segctor_dirty_data_blocks_count_show(struct nilfs_segctor_attr *attr,
+					    struct the_nilfs *nilfs,
+					    char *buf)
+{
+	u32 ndirtyblks;
+
+	down_read(&nilfs->ns_sem);
+	ndirtyblks = atomic_read(&nilfs->ns_ndirtyblks);
+	up_read(&nilfs->ns_sem);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", ndirtyblks);
+}
+
+static const char segctor_readme_str[] =
+	"The segctor group contains attributes that describe\n"
+	"segctor thread activity details.\n\n"
+	"(1) last_pseg_block\n"
+	"\tshow start block number of the latest segment.\n\n"
+	"(2) last_seg_sequence\n"
+	"\tshow sequence value of the latest segment.\n\n"
+	"(3) last_seg_checkpoint\n"
+	"\tshow checkpoint number of the latest segment.\n\n"
+	"(4) current_seg_sequence\n\tshow segment sequence counter.\n\n"
+	"(5) current_last_full_seg\n"
+	"\tshow index number of the latest full segment.\n\n"
+	"(6) next_full_seg\n"
+	"\tshow index number of the full segment index to be used next.\n\n"
+	"(7) next_pseg_offset\n"
+	"\tshow offset of next partial segment in the current full segment.\n\n"
+	"(8) next_checkpoint\n\tshow next checkpoint number.\n\n"
+	"(9) last_seg_write_time\n"
+	"\tshow write time of the last segment in human-readable format.\n\n"
+	"(10) last_seg_write_time_secs\n"
+	"\tshow write time of the last segment in seconds.\n\n"
+	"(11) last_nongc_write_time\n"
+	"\tshow write time of the last segment not for cleaner operation "
+	"in human-readable format.\n\n"
+	"(12) last_nongc_write_time_secs\n"
+	"\tshow write time of the last segment not for cleaner operation "
+	"in seconds.\n\n"
+	"(13) dirty_data_blocks_count\n"
+	"\tshow number of dirty data blocks.\n\n";
+
+static ssize_t
+nilfs_segctor_README_show(struct nilfs_segctor_attr *attr,
+			  struct the_nilfs *nilfs, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, segctor_readme_str);
+}
+
+NILFS_SEGCTOR_RO_ATTR(last_pseg_block);
+NILFS_SEGCTOR_RO_ATTR(last_seg_sequence);
+NILFS_SEGCTOR_RO_ATTR(last_seg_checkpoint);
+NILFS_SEGCTOR_RO_ATTR(current_seg_sequence);
+NILFS_SEGCTOR_RO_ATTR(current_last_full_seg);
+NILFS_SEGCTOR_RO_ATTR(next_full_seg);
+NILFS_SEGCTOR_RO_ATTR(next_pseg_offset);
+NILFS_SEGCTOR_RO_ATTR(next_checkpoint);
+NILFS_SEGCTOR_RO_ATTR(last_seg_write_time);
+NILFS_SEGCTOR_RO_ATTR(last_seg_write_time_secs);
+NILFS_SEGCTOR_RO_ATTR(last_nongc_write_time);
+NILFS_SEGCTOR_RO_ATTR(last_nongc_write_time_secs);
+NILFS_SEGCTOR_RO_ATTR(dirty_data_blocks_count);
+NILFS_SEGCTOR_RO_ATTR(README);
+
+static struct attribute *nilfs_segctor_attrs[] = {
+	NILFS_SEGCTOR_ATTR_LIST(last_pseg_block),
+	NILFS_SEGCTOR_ATTR_LIST(last_seg_sequence),
+	NILFS_SEGCTOR_ATTR_LIST(last_seg_checkpoint),
+	NILFS_SEGCTOR_ATTR_LIST(current_seg_sequence),
+	NILFS_SEGCTOR_ATTR_LIST(current_last_full_seg),
+	NILFS_SEGCTOR_ATTR_LIST(next_full_seg),
+	NILFS_SEGCTOR_ATTR_LIST(next_pseg_offset),
+	NILFS_SEGCTOR_ATTR_LIST(next_checkpoint),
+	NILFS_SEGCTOR_ATTR_LIST(last_seg_write_time),
+	NILFS_SEGCTOR_ATTR_LIST(last_seg_write_time_secs),
+	NILFS_SEGCTOR_ATTR_LIST(last_nongc_write_time),
+	NILFS_SEGCTOR_ATTR_LIST(last_nongc_write_time_secs),
+	NILFS_SEGCTOR_ATTR_LIST(dirty_data_blocks_count),
+	NILFS_SEGCTOR_ATTR_LIST(README),
+	NULL,
+};
+
+NILFS_DEV_INT_GROUP_OPS(segctor, dev);
+NILFS_DEV_INT_GROUP_TYPE(segctor, dev);
+NILFS_DEV_INT_GROUP_FNS(segctor, dev);
+
+/************************************************************************
+ *                        NILFS superblock attrs                        *
+ ************************************************************************/
+
+static ssize_t
+nilfs_superblock_sb_write_time_show(struct nilfs_superblock_attr *attr,
+				     struct the_nilfs *nilfs,
+				     char *buf)
+{
+	time_t sbwtime;
+
+	down_read(&nilfs->ns_sem);
+	sbwtime = nilfs->ns_sbwtime;
+	up_read(&nilfs->ns_sem);
+
+	return NILFS_SHOW_TIME(sbwtime, buf);
+}
+
+static ssize_t
+nilfs_superblock_sb_write_time_secs_show(struct nilfs_superblock_attr *attr,
+					 struct the_nilfs *nilfs,
+					 char *buf)
+{
+	time_t sbwtime;
+
+	down_read(&nilfs->ns_sem);
+	sbwtime = nilfs->ns_sbwtime;
+	up_read(&nilfs->ns_sem);
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n", (unsigned long long)sbwtime);
+}
+
+static ssize_t
+nilfs_superblock_sb_write_count_show(struct nilfs_superblock_attr *attr,
+				      struct the_nilfs *nilfs,
+				      char *buf)
+{
+	unsigned sbwcount;
+
+	down_read(&nilfs->ns_sem);
+	sbwcount = nilfs->ns_sbwcount;
+	up_read(&nilfs->ns_sem);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", sbwcount);
+}
+
+static ssize_t
+nilfs_superblock_sb_update_frequency_show(struct nilfs_superblock_attr *attr,
+					    struct the_nilfs *nilfs,
+					    char *buf)
+{
+	unsigned sb_update_freq;
+
+	down_read(&nilfs->ns_sem);
+	sb_update_freq = nilfs->ns_sb_update_freq;
+	up_read(&nilfs->ns_sem);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", sb_update_freq);
+}
+
+static ssize_t
+nilfs_superblock_sb_update_frequency_store(struct nilfs_superblock_attr *attr,
+					    struct the_nilfs *nilfs,
+					    const char *buf, size_t count)
+{
+	unsigned val;
+	int err;
+
+	err = kstrtouint(skip_spaces(buf), 0, &val);
+	if (err) {
+		printk(KERN_ERR "NILFS: unable to convert string: err=%d\n",
+			err);
+		return err;
+	}
+
+	if (val < NILFS_SB_FREQ) {
+		val = NILFS_SB_FREQ;
+		printk(KERN_WARNING "NILFS: superblock update frequency cannot be lesser than 10 seconds\n");
+	}
+
+	down_write(&nilfs->ns_sem);
+	nilfs->ns_sb_update_freq = val;
+	up_write(&nilfs->ns_sem);
+
+	return count;
+}
+
+static const char sb_readme_str[] =
+	"The superblock group contains attributes that describe\n"
+	"superblock's details.\n\n"
+	"(1) sb_write_time\n\tshow previous write time of super block "
+	"in human-readable format.\n\n"
+	"(2) sb_write_time_secs\n\tshow previous write time of super block "
+	"in seconds.\n\n"
+	"(3) sb_write_count\n\tshow write count of super block.\n\n"
+	"(4) sb_update_frequency\n"
+	"\tshow/set interval of periodical update of superblock (in seconds).\n\n"
+	"\tYou can set preferable frequency of superblock update by command:\n\n"
+	"\t'echo <val> > /sys/fs/<nilfs>/<dev>/superblock/sb_update_frequency'\n";
+
+static ssize_t
+nilfs_superblock_README_show(struct nilfs_superblock_attr *attr,
+				struct the_nilfs *nilfs, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, sb_readme_str);
+}
+
+NILFS_SUPERBLOCK_RO_ATTR(sb_write_time);
+NILFS_SUPERBLOCK_RO_ATTR(sb_write_time_secs);
+NILFS_SUPERBLOCK_RO_ATTR(sb_write_count);
+NILFS_SUPERBLOCK_RW_ATTR(sb_update_frequency);
+NILFS_SUPERBLOCK_RO_ATTR(README);
+
+static struct attribute *nilfs_superblock_attrs[] = {
+	NILFS_SUPERBLOCK_ATTR_LIST(sb_write_time),
+	NILFS_SUPERBLOCK_ATTR_LIST(sb_write_time_secs),
+	NILFS_SUPERBLOCK_ATTR_LIST(sb_write_count),
+	NILFS_SUPERBLOCK_ATTR_LIST(sb_update_frequency),
+	NILFS_SUPERBLOCK_ATTR_LIST(README),
+	NULL,
+};
+
+NILFS_DEV_INT_GROUP_OPS(superblock, dev);
+NILFS_DEV_INT_GROUP_TYPE(superblock, dev);
+NILFS_DEV_INT_GROUP_FNS(superblock, dev);
+
+/************************************************************************
+ *                        NILFS device attrs                            *
+ ************************************************************************/
+
+static
+ssize_t nilfs_dev_revision_show(struct nilfs_dev_attr *attr,
+				struct the_nilfs *nilfs,
+				char *buf)
+{
+	struct nilfs_super_block **sbp = nilfs->ns_sbp;
+	u32 major = le32_to_cpu(sbp[0]->s_rev_level);
+	u16 minor = le16_to_cpu(sbp[0]->s_minor_rev_level);
+
+	return snprintf(buf, PAGE_SIZE, "%d.%d\n", major, minor);
+}
+
+static
+ssize_t nilfs_dev_blocksize_show(struct nilfs_dev_attr *attr,
+				 struct the_nilfs *nilfs,
+				 char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%u\n", nilfs->ns_blocksize);
+}
+
+static
+ssize_t nilfs_dev_device_size_show(struct nilfs_dev_attr *attr,
+				    struct the_nilfs *nilfs,
+				    char *buf)
+{
+	struct nilfs_super_block **sbp = nilfs->ns_sbp;
+	u64 dev_size = le64_to_cpu(sbp[0]->s_dev_size);
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n", dev_size);
+}
+
+static
+ssize_t nilfs_dev_free_blocks_show(struct nilfs_dev_attr *attr,
+				   struct the_nilfs *nilfs,
+				   char *buf)
+{
+	sector_t free_blocks = 0;
+
+	nilfs_count_free_blocks(nilfs, &free_blocks);
+	return snprintf(buf, PAGE_SIZE, "%llu\n",
+			(unsigned long long)free_blocks);
+}
+
+static
+ssize_t nilfs_dev_uuid_show(struct nilfs_dev_attr *attr,
+			    struct the_nilfs *nilfs,
+			    char *buf)
+{
+	struct nilfs_super_block **sbp = nilfs->ns_sbp;
+
+	return snprintf(buf, PAGE_SIZE, "%pUb\n", sbp[0]->s_uuid);
+}
+
+static
+ssize_t nilfs_dev_volume_name_show(struct nilfs_dev_attr *attr,
+				    struct the_nilfs *nilfs,
+				    char *buf)
+{
+	struct nilfs_super_block **sbp = nilfs->ns_sbp;
+
+	return scnprintf(buf, sizeof(sbp[0]->s_volume_name), "%s\n",
+			 sbp[0]->s_volume_name);
+}
+
+static const char dev_readme_str[] =
+	"The <device> group contains attributes that describe file system\n"
+	"partition's details.\n\n"
+	"(1) revision\n\tshow NILFS file system revision.\n\n"
+	"(2) blocksize\n\tshow volume block size in bytes.\n\n"
+	"(3) device_size\n\tshow volume size in bytes.\n\n"
+	"(4) free_blocks\n\tshow count of free blocks on volume.\n\n"
+	"(5) uuid\n\tshow volume's UUID.\n\n"
+	"(6) volume_name\n\tshow volume's name.\n\n";
+
+static ssize_t nilfs_dev_README_show(struct nilfs_dev_attr *attr,
+				     struct the_nilfs *nilfs,
+				     char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, dev_readme_str);
+}
+
+NILFS_DEV_RO_ATTR(revision);
+NILFS_DEV_RO_ATTR(blocksize);
+NILFS_DEV_RO_ATTR(device_size);
+NILFS_DEV_RO_ATTR(free_blocks);
+NILFS_DEV_RO_ATTR(uuid);
+NILFS_DEV_RO_ATTR(volume_name);
+NILFS_DEV_RO_ATTR(README);
+
+static struct attribute *nilfs_dev_attrs[] = {
+	NILFS_DEV_ATTR_LIST(revision),
+	NILFS_DEV_ATTR_LIST(blocksize),
+	NILFS_DEV_ATTR_LIST(device_size),
+	NILFS_DEV_ATTR_LIST(free_blocks),
+	NILFS_DEV_ATTR_LIST(uuid),
+	NILFS_DEV_ATTR_LIST(volume_name),
+	NILFS_DEV_ATTR_LIST(README),
+	NULL,
+};
+
+static ssize_t nilfs_dev_attr_show(struct kobject *kobj,
+				    struct attribute *attr, char *buf)
+{
+	struct the_nilfs *nilfs = container_of(kobj, struct the_nilfs,
+						ns_dev_kobj);
+	struct nilfs_dev_attr *a = container_of(attr, struct nilfs_dev_attr,
+						attr);
+
+	return a->show ? a->show(a, nilfs, buf) : 0;
+}
+
+static ssize_t nilfs_dev_attr_store(struct kobject *kobj,
+				    struct attribute *attr,
+				    const char *buf, size_t len)
+{
+	struct the_nilfs *nilfs = container_of(kobj, struct the_nilfs,
+						ns_dev_kobj);
+	struct nilfs_dev_attr *a = container_of(attr, struct nilfs_dev_attr,
+						attr);
+
+	return a->store ? a->store(a, nilfs, buf, len) : 0;
+}
+
+static void nilfs_dev_attr_release(struct kobject *kobj)
+{
+	struct the_nilfs *nilfs = container_of(kobj, struct the_nilfs,
+						ns_dev_kobj);
+	complete(&nilfs->ns_dev_kobj_unregister);
+}
+
+static const struct sysfs_ops nilfs_dev_attr_ops = {
+	.show	= nilfs_dev_attr_show,
+	.store	= nilfs_dev_attr_store,
+};
+
+static struct kobj_type nilfs_dev_ktype = {
+	.default_attrs	= nilfs_dev_attrs,
+	.sysfs_ops	= &nilfs_dev_attr_ops,
+	.release	= nilfs_dev_attr_release,
+};
+
+int nilfs_sysfs_create_device_group(struct super_block *sb)
+{
+	struct the_nilfs *nilfs = sb->s_fs_info;
+	size_t devgrp_size = sizeof(struct nilfs_sysfs_dev_subgroups);
+	int err;
+
+	nilfs->ns_dev_subgroups = kzalloc(devgrp_size, GFP_KERNEL);
+	if (unlikely(!nilfs->ns_dev_subgroups)) {
+		err = -ENOMEM;
+		printk(KERN_ERR "NILFS: unable to allocate memory for device group\n");
+		goto failed_create_device_group;
+	}
+
+	nilfs->ns_dev_kobj.kset = nilfs_kset;
+	init_completion(&nilfs->ns_dev_kobj_unregister);
+	err = kobject_init_and_add(&nilfs->ns_dev_kobj, &nilfs_dev_ktype, NULL,
+				    "%s", sb->s_id);
+	if (err)
+		goto free_dev_subgroups;
+
+	err = nilfs_sysfs_create_mounted_snapshots_group(nilfs);
+	if (err)
+		goto cleanup_dev_kobject;
+
+	err = nilfs_sysfs_create_checkpoints_group(nilfs);
+	if (err)
+		goto delete_mounted_snapshots_group;
+
+	err = nilfs_sysfs_create_segments_group(nilfs);
+	if (err)
+		goto delete_checkpoints_group;
+
+	err = nilfs_sysfs_create_superblock_group(nilfs);
+	if (err)
+		goto delete_segments_group;
+
+	err = nilfs_sysfs_create_segctor_group(nilfs);
+	if (err)
+		goto delete_superblock_group;
+
+	return 0;
+
+delete_superblock_group:
+	nilfs_sysfs_delete_superblock_group(nilfs);
+
+delete_segments_group:
+	nilfs_sysfs_delete_segments_group(nilfs);
+
+delete_checkpoints_group:
+	nilfs_sysfs_delete_checkpoints_group(nilfs);
+
+delete_mounted_snapshots_group:
+	nilfs_sysfs_delete_mounted_snapshots_group(nilfs);
+
+cleanup_dev_kobject:
+	kobject_del(&nilfs->ns_dev_kobj);
+
+free_dev_subgroups:
+	kfree(nilfs->ns_dev_subgroups);
+
+failed_create_device_group:
+	return err;
+}
+
+void nilfs_sysfs_delete_device_group(struct the_nilfs *nilfs)
+{
+	nilfs_sysfs_delete_mounted_snapshots_group(nilfs);
+	nilfs_sysfs_delete_checkpoints_group(nilfs);
+	nilfs_sysfs_delete_segments_group(nilfs);
+	nilfs_sysfs_delete_superblock_group(nilfs);
+	nilfs_sysfs_delete_segctor_group(nilfs);
+	kobject_del(&nilfs->ns_dev_kobj);
+	kfree(nilfs->ns_dev_subgroups);
+}
+
+/************************************************************************
+ *                        NILFS feature attrs                           *
+ ************************************************************************/
+
+static ssize_t nilfs_feature_revision_show(struct kobject *kobj,
+					    struct attribute *attr, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d.%d\n",
+			NILFS_CURRENT_REV, NILFS_MINOR_REV);
+}
+
+static const char features_readme_str[] =
+	"The features group contains attributes that describe NILFS file\n"
+	"system driver features.\n\n"
+	"(1) revision\n\tshow current revision of NILFS file system driver.\n";
+
+static ssize_t nilfs_feature_README_show(struct kobject *kobj,
+					 struct attribute *attr,
+					 char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, features_readme_str);
+}
+
+NILFS_FEATURE_RO_ATTR(revision);
+NILFS_FEATURE_RO_ATTR(README);
+
+static struct attribute *nilfs_feature_attrs[] = {
+	NILFS_FEATURE_ATTR_LIST(revision),
+	NILFS_FEATURE_ATTR_LIST(README),
+	NULL,
+};
+
+static const struct attribute_group nilfs_feature_attr_group = {
+	.name = "features",
+	.attrs = nilfs_feature_attrs,
+};
+
+int __init nilfs_sysfs_init(void)
+{
+	int err;
+
+	nilfs_kset = kset_create_and_add(NILFS_ROOT_GROUP_NAME, NULL, fs_kobj);
+	if (!nilfs_kset) {
+		err = -ENOMEM;
+		printk(KERN_ERR "NILFS: unable to create sysfs entry: err %d\n",
+			err);
+		goto failed_sysfs_init;
+	}
+
+	err = sysfs_create_group(&nilfs_kset->kobj, &nilfs_feature_attr_group);
+	if (unlikely(err)) {
+		printk(KERN_ERR "NILFS: unable to create feature group: err %d\n",
+			err);
+		goto cleanup_sysfs_init;
+	}
+
+	return 0;
+
+cleanup_sysfs_init:
+	kset_unregister(nilfs_kset);
+
+failed_sysfs_init:
+	return err;
+}
+
+void nilfs_sysfs_exit(void)
+{
+	sysfs_remove_group(&nilfs_kset->kobj, &nilfs_feature_attr_group);
+	kset_unregister(nilfs_kset);
+}
diff --git a/fs/nilfs2/sysfs.h b/fs/nilfs2/sysfs.h
new file mode 100644
index 000000000000..677e3a1a8370
--- /dev/null
+++ b/fs/nilfs2/sysfs.h
@@ -0,0 +1,176 @@
+/*
+ * sysfs.h - sysfs support declarations.
+ *
+ * Copyright (C) 2005-2014 Nippon Telegraph and Telephone Corporation.
+ * Copyright (C) 2014 HGST, Inc., a Western Digital Company.
+ *
+ * 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.
+ *
+ * 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.
+ *
+ * Written by Vyacheslav Dubeyko <Vyacheslav.Dubeyko@hgst.com>
+ */
+
+#ifndef _NILFS_SYSFS_H
+#define _NILFS_SYSFS_H
+
+#include <linux/sysfs.h>
+
+#define NILFS_ROOT_GROUP_NAME	"nilfs2"
+
+/*
+ * struct nilfs_sysfs_dev_subgroups - device subgroup kernel objects
+ * @sg_superblock_kobj: /sys/fs/<nilfs>/<device>/superblock
+ * @sg_superblock_kobj_unregister: completion state
+ * @sg_segctor_kobj: /sys/fs/<nilfs>/<device>/segctor
+ * @sg_segctor_kobj_unregister: completion state
+ * @sg_mounted_snapshots_kobj: /sys/fs/<nilfs>/<device>/mounted_snapshots
+ * @sg_mounted_snapshots_kobj_unregister: completion state
+ * @sg_checkpoints_kobj: /sys/fs/<nilfs>/<device>/checkpoints
+ * @sg_checkpoints_kobj_unregister: completion state
+ * @sg_segments_kobj: /sys/fs/<nilfs>/<device>/segments
+ * @sg_segments_kobj_unregister: completion state
+ */
+struct nilfs_sysfs_dev_subgroups {
+	/* /sys/fs/<nilfs>/<device>/superblock */
+	struct kobject sg_superblock_kobj;
+	struct completion sg_superblock_kobj_unregister;
+
+	/* /sys/fs/<nilfs>/<device>/segctor */
+	struct kobject sg_segctor_kobj;
+	struct completion sg_segctor_kobj_unregister;
+
+	/* /sys/fs/<nilfs>/<device>/mounted_snapshots */
+	struct kobject sg_mounted_snapshots_kobj;
+	struct completion sg_mounted_snapshots_kobj_unregister;
+
+	/* /sys/fs/<nilfs>/<device>/checkpoints */
+	struct kobject sg_checkpoints_kobj;
+	struct completion sg_checkpoints_kobj_unregister;
+
+	/* /sys/fs/<nilfs>/<device>/segments */
+	struct kobject sg_segments_kobj;
+	struct completion sg_segments_kobj_unregister;
+};
+
+#define NILFS_COMMON_ATTR_STRUCT(name) \
+struct nilfs_##name##_attr { \
+	struct attribute attr; \
+	ssize_t (*show)(struct kobject *, struct attribute *, \
+			char *); \
+	ssize_t (*store)(struct kobject *, struct attribute *, \
+			 const char *, size_t); \
+};
+
+NILFS_COMMON_ATTR_STRUCT(feature);
+
+#define NILFS_DEV_ATTR_STRUCT(name) \
+struct nilfs_##name##_attr { \
+	struct attribute attr; \
+	ssize_t (*show)(struct nilfs_##name##_attr *, struct the_nilfs *, \
+			char *); \
+	ssize_t (*store)(struct nilfs_##name##_attr *, struct the_nilfs *, \
+			 const char *, size_t); \
+};
+
+NILFS_DEV_ATTR_STRUCT(dev);
+NILFS_DEV_ATTR_STRUCT(segments);
+NILFS_DEV_ATTR_STRUCT(mounted_snapshots);
+NILFS_DEV_ATTR_STRUCT(checkpoints);
+NILFS_DEV_ATTR_STRUCT(superblock);
+NILFS_DEV_ATTR_STRUCT(segctor);
+
+#define NILFS_CP_ATTR_STRUCT(name) \
+struct nilfs_##name##_attr { \
+	struct attribute attr; \
+	ssize_t (*show)(struct nilfs_##name##_attr *, struct nilfs_root *, \
+			char *); \
+	ssize_t (*store)(struct nilfs_##name##_attr *, struct nilfs_root *, \
+			 const char *, size_t); \
+};
+
+NILFS_CP_ATTR_STRUCT(snapshot);
+
+#define NILFS_ATTR(type, name, mode, show, store) \
+	static struct nilfs_##type##_attr nilfs_##type##_attr_##name = \
+		__ATTR(name, mode, show, store)
+
+#define NILFS_INFO_ATTR(type, name) \
+	NILFS_ATTR(type, name, 0444, NULL, NULL)
+#define NILFS_RO_ATTR(type, name) \
+	NILFS_ATTR(type, name, 0444, nilfs_##type##_##name##_show, NULL)
+#define NILFS_RW_ATTR(type, name) \
+	NILFS_ATTR(type, name, 0644, \
+		    nilfs_##type##_##name##_show, \
+		    nilfs_##type##_##name##_store)
+
+#define NILFS_FEATURE_INFO_ATTR(name) \
+	NILFS_INFO_ATTR(feature, name)
+#define NILFS_FEATURE_RO_ATTR(name) \
+	NILFS_RO_ATTR(feature, name)
+#define NILFS_FEATURE_RW_ATTR(name) \
+	NILFS_RW_ATTR(feature, name)
+
+#define NILFS_DEV_INFO_ATTR(name) \
+	NILFS_INFO_ATTR(dev, name)
+#define NILFS_DEV_RO_ATTR(name) \
+	NILFS_RO_ATTR(dev, name)
+#define NILFS_DEV_RW_ATTR(name) \
+	NILFS_RW_ATTR(dev, name)
+
+#define NILFS_SEGMENTS_RO_ATTR(name) \
+	NILFS_RO_ATTR(segments, name)
+#define NILFS_SEGMENTS_RW_ATTR(name) \
+	NILFS_RW_ATTR(segs_info, name)
+
+#define NILFS_MOUNTED_SNAPSHOTS_RO_ATTR(name) \
+	NILFS_RO_ATTR(mounted_snapshots, name)
+
+#define NILFS_CHECKPOINTS_RO_ATTR(name) \
+	NILFS_RO_ATTR(checkpoints, name)
+#define NILFS_CHECKPOINTS_RW_ATTR(name) \
+	NILFS_RW_ATTR(checkpoints, name)
+
+#define NILFS_SNAPSHOT_INFO_ATTR(name) \
+	NILFS_INFO_ATTR(snapshot, name)
+#define NILFS_SNAPSHOT_RO_ATTR(name) \
+	NILFS_RO_ATTR(snapshot, name)
+#define NILFS_SNAPSHOT_RW_ATTR(name) \
+	NILFS_RW_ATTR(snapshot, name)
+
+#define NILFS_SUPERBLOCK_RO_ATTR(name) \
+	NILFS_RO_ATTR(superblock, name)
+#define NILFS_SUPERBLOCK_RW_ATTR(name) \
+	NILFS_RW_ATTR(superblock, name)
+
+#define NILFS_SEGCTOR_INFO_ATTR(name) \
+	NILFS_INFO_ATTR(segctor, name)
+#define NILFS_SEGCTOR_RO_ATTR(name) \
+	NILFS_RO_ATTR(segctor, name)
+#define NILFS_SEGCTOR_RW_ATTR(name) \
+	NILFS_RW_ATTR(segctor, name)
+
+#define NILFS_FEATURE_ATTR_LIST(name) \
+	(&nilfs_feature_attr_##name.attr)
+#define NILFS_DEV_ATTR_LIST(name) \
+	(&nilfs_dev_attr_##name.attr)
+#define NILFS_SEGMENTS_ATTR_LIST(name) \
+	(&nilfs_segments_attr_##name.attr)
+#define NILFS_MOUNTED_SNAPSHOTS_ATTR_LIST(name) \
+	(&nilfs_mounted_snapshots_attr_##name.attr)
+#define NILFS_CHECKPOINTS_ATTR_LIST(name) \
+	(&nilfs_checkpoints_attr_##name.attr)
+#define NILFS_SNAPSHOT_ATTR_LIST(name) \
+	(&nilfs_snapshot_attr_##name.attr)
+#define NILFS_SUPERBLOCK_ATTR_LIST(name) \
+	(&nilfs_superblock_attr_##name.attr)
+#define NILFS_SEGCTOR_ATTR_LIST(name) \
+	(&nilfs_segctor_attr_##name.attr)
+
+#endif /* _NILFS_SYSFS_H */
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 8ba8229ba076..9da25fe9ea61 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -85,6 +85,7 @@ struct the_nilfs *alloc_nilfs(struct block_device *bdev)
 	nilfs->ns_cptree = RB_ROOT;
 	spin_lock_init(&nilfs->ns_cptree_lock);
 	init_rwsem(&nilfs->ns_segctor_sem);
+	nilfs->ns_sb_update_freq = NILFS_SB_FREQ;
 
 	return nilfs;
 }
@@ -97,6 +98,7 @@ void destroy_nilfs(struct the_nilfs *nilfs)
 {
 	might_sleep();
 	if (nilfs_init(nilfs)) {
+		nilfs_sysfs_delete_device_group(nilfs);
 		brelse(nilfs->ns_sbh[0]);
 		brelse(nilfs->ns_sbh[1]);
 	}
@@ -640,6 +642,10 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
 	if (err)
 		goto failed_sbh;
 
+	err = nilfs_sysfs_create_device_group(sb);
+	if (err)
+		goto failed_sbh;
+
 	set_nilfs_init(nilfs);
 	err = 0;
  out:
@@ -740,12 +746,13 @@ nilfs_find_or_create_root(struct the_nilfs *nilfs, __u64 cno)
 {
 	struct rb_node **p, *parent;
 	struct nilfs_root *root, *new;
+	int err;
 
 	root = nilfs_lookup_root(nilfs, cno);
 	if (root)
 		return root;
 
-	new = kmalloc(sizeof(*root), GFP_KERNEL);
+	new = kzalloc(sizeof(*root), GFP_KERNEL);
 	if (!new)
 		return NULL;
 
@@ -782,6 +789,12 @@ nilfs_find_or_create_root(struct the_nilfs *nilfs, __u64 cno)
 
 	spin_unlock(&nilfs->ns_cptree_lock);
 
+	err = nilfs_sysfs_create_snapshot_group(new);
+	if (err) {
+		kfree(new);
+		new = NULL;
+	}
+
 	return new;
 }
 
@@ -790,6 +803,8 @@ void nilfs_put_root(struct nilfs_root *root)
 	if (atomic_dec_and_test(&root->count)) {
 		struct the_nilfs *nilfs = root->nilfs;
 
+		nilfs_sysfs_delete_snapshot_group(root);
+
 		spin_lock(&nilfs->ns_cptree_lock);
 		rb_erase(&root->rb_node, &nilfs->ns_cptree);
 		spin_unlock(&nilfs->ns_cptree_lock);
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index de8cc53b4a5c..d01ead1bea9a 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -33,6 +33,7 @@
 #include <linux/slab.h>
 
 struct nilfs_sc_info;
+struct nilfs_sysfs_dev_subgroups;
 
 /* the_nilfs struct */
 enum {
@@ -54,6 +55,7 @@ enum {
  * @ns_sbwcount: write count of super block
  * @ns_sbsize: size of valid data in super block
  * @ns_mount_state: file system state
+ * @ns_sb_update_freq: interval of periodical update of superblocks (in seconds)
  * @ns_seg_seq: segment sequence counter
  * @ns_segnum: index number of the latest full segment.
  * @ns_nextnum: index number of the full segment index to be used next
@@ -95,6 +97,9 @@ enum {
  * @ns_inode_size: size of on-disk inode
  * @ns_first_ino: first not-special inode number
  * @ns_crc_seed: seed value of CRC32 calculation
+ * @ns_dev_kobj: /sys/fs/<nilfs>/<device>
+ * @ns_dev_kobj_unregister: completion state
+ * @ns_dev_subgroups: <device> subgroups pointer
  */
 struct the_nilfs {
 	unsigned long		ns_flags;
@@ -114,6 +119,7 @@ struct the_nilfs {
 	unsigned		ns_sbwcount;
 	unsigned		ns_sbsize;
 	unsigned		ns_mount_state;
+	unsigned		ns_sb_update_freq;
 
 	/*
 	 * Following fields are dedicated to a writable FS-instance.
@@ -188,6 +194,11 @@ struct the_nilfs {
 	int			ns_inode_size;
 	int			ns_first_ino;
 	u32			ns_crc_seed;
+
+	/* /sys/fs/<nilfs>/<device> */
+	struct kobject ns_dev_kobj;
+	struct completion ns_dev_kobj_unregister;
+	struct nilfs_sysfs_dev_subgroups *ns_dev_subgroups;
 };
 
 #define THE_NILFS_FNS(bit, name)					\
@@ -232,6 +243,8 @@ THE_NILFS_FNS(SB_DIRTY, sb_dirty)
  * @ifile: inode file
  * @inodes_count: number of inodes
  * @blocks_count: number of blocks
+ * @snapshot_kobj: /sys/fs/<nilfs>/<device>/mounted_snapshots/<snapshot>
+ * @snapshot_kobj_unregister: completion state for kernel object
  */
 struct nilfs_root {
 	__u64 cno;
@@ -243,6 +256,10 @@ struct nilfs_root {
 
 	atomic64_t inodes_count;
 	atomic64_t blocks_count;
+
+	/* /sys/fs/<nilfs>/<device>/mounted_snapshots/<snapshot> */
+	struct kobject snapshot_kobj;
+	struct completion snapshot_kobj_unregister;
 };
 
 /* Special checkpoint number */
@@ -254,7 +271,8 @@ struct nilfs_root {
 static inline int nilfs_sb_need_update(struct the_nilfs *nilfs)
 {
 	u64 t = get_seconds();
-	return t < nilfs->ns_sbwtime || t > nilfs->ns_sbwtime + NILFS_SB_FREQ;
+	return t < nilfs->ns_sbwtime ||
+		t > nilfs->ns_sbwtime + nilfs->ns_sb_update_freq;
 }
 
 static inline int nilfs_sb_will_flip(struct the_nilfs *nilfs)
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index a93bf9892256..fcae9ef1a328 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -5662,7 +5662,7 @@ int ocfs2_remove_btree_range(struct inode *inode,
 			     struct ocfs2_extent_tree *et,
 			     u32 cpos, u32 phys_cpos, u32 len, int flags,
 			     struct ocfs2_cached_dealloc_ctxt *dealloc,
-			     u64 refcount_loc)
+			     u64 refcount_loc, bool refcount_tree_locked)
 {
 	int ret, credits = 0, extra_blocks = 0;
 	u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);
@@ -5676,11 +5676,13 @@ int ocfs2_remove_btree_range(struct inode *inode,
 		BUG_ON(!(OCFS2_I(inode)->ip_dyn_features &
 			 OCFS2_HAS_REFCOUNT_FL));
 
-		ret = ocfs2_lock_refcount_tree(osb, refcount_loc, 1,
-					       &ref_tree, NULL);
-		if (ret) {
-			mlog_errno(ret);
-			goto bail;
+		if (!refcount_tree_locked) {
+			ret = ocfs2_lock_refcount_tree(osb, refcount_loc, 1,
+						       &ref_tree, NULL);
+			if (ret) {
+				mlog_errno(ret);
+				goto bail;
+			}
 		}
 
 		ret = ocfs2_prepare_refcount_change_for_del(inode,
@@ -7021,6 +7023,7 @@ int ocfs2_commit_truncate(struct ocfs2_super *osb,
 	u64 refcount_loc = le64_to_cpu(di->i_refcount_loc);
 	struct ocfs2_extent_tree et;
 	struct ocfs2_cached_dealloc_ctxt dealloc;
+	struct ocfs2_refcount_tree *ref_tree = NULL;
 
 	ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh);
 	ocfs2_init_dealloc_ctxt(&dealloc);
@@ -7130,9 +7133,18 @@ start:
 
 	phys_cpos = ocfs2_blocks_to_clusters(inode->i_sb, blkno);
 
+	if ((flags & OCFS2_EXT_REFCOUNTED) && trunc_len && !ref_tree) {
+		status = ocfs2_lock_refcount_tree(osb, refcount_loc, 1,
+				&ref_tree, NULL);
+		if (status) {
+			mlog_errno(status);
+			goto bail;
+		}
+	}
+
 	status = ocfs2_remove_btree_range(inode, &et, trunc_cpos,
 					  phys_cpos, trunc_len, flags, &dealloc,
-					  refcount_loc);
+					  refcount_loc, true);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
@@ -7147,6 +7159,8 @@ start:
 	goto start;
 
 bail:
+	if (ref_tree)
+		ocfs2_unlock_refcount_tree(osb, ref_tree, 1);
 
 	ocfs2_schedule_truncate_log_flush(osb, 1);
 
diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h
index ca381c584127..fb09b97db162 100644
--- a/fs/ocfs2/alloc.h
+++ b/fs/ocfs2/alloc.h
@@ -142,7 +142,7 @@ int ocfs2_remove_btree_range(struct inode *inode,
 			     struct ocfs2_extent_tree *et,
 			     u32 cpos, u32 phys_cpos, u32 len, int flags,
 			     struct ocfs2_cached_dealloc_ctxt *dealloc,
-			     u64 refcount_loc);
+			     u64 refcount_loc, bool refcount_tree_locked);
 
 int ocfs2_num_free_extents(struct ocfs2_super *osb,
 			   struct ocfs2_extent_tree *et);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 4a231a166cf8..2e636217a360 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -894,7 +894,7 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
 	}
 }
 
-static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc)
 {
 	int i;
 
@@ -915,7 +915,11 @@ static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
 		page_cache_release(wc->w_target_page);
 	}
 	ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
+}
 
+static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+{
+	ocfs2_unlock_pages(wc);
 	brelse(wc->w_di_bh);
 	kfree(wc);
 }
@@ -1817,16 +1821,6 @@ try_again:
 		if (ret)
 			goto out_commit;
 	}
-	/*
-	 * We don't want this to fail in ocfs2_write_end(), so do it
-	 * here.
-	 */
-	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
-				      OCFS2_JOURNAL_ACCESS_WRITE);
-	if (ret) {
-		mlog_errno(ret);
-		goto out_quota;
-	}
 
 	/*
 	 * Fill our page array first. That way we've grabbed enough so
@@ -1977,7 +1971,7 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 			   loff_t pos, unsigned len, unsigned copied,
 			   struct page *page, void *fsdata)
 {
-	int i;
+	int i, ret;
 	unsigned from, to, start = pos & (PAGE_CACHE_SIZE - 1);
 	struct inode *inode = mapping->host;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
@@ -2027,6 +2021,14 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 		}
 	}
 
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		copied = ret;
+		mlog_errno(ret);
+		goto out;
+	}
+
 out_write_size:
 	pos += copied;
 	if (pos > i_size_read(inode)) {
@@ -2041,11 +2043,20 @@ out_write_size:
 	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 	ocfs2_journal_dirty(handle, wc->w_di_bh);
 
+out:
+	/* unlock pages before dealloc since it needs acquiring j_trans_barrier
+	 * lock, or it will cause a deadlock since journal commit threads holds
+	 * this lock and will ask for the page lock when flushing the data.
+	 * put it here to preserve the unlock order.
+	 */
+	ocfs2_unlock_pages(wc);
+
 	ocfs2_commit_trans(osb, handle);
 
 	ocfs2_run_deallocs(osb, &wc->w_dealloc);
 
-	ocfs2_free_write_ctxt(wc);
+	brelse(wc->w_di_bh);
+	kfree(wc);
 
 	return copied;
 }
diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c
index 1ec141e758d7..62e8ec619b4c 100644
--- a/fs/ocfs2/cluster/quorum.c
+++ b/fs/ocfs2/cluster/quorum.c
@@ -160,9 +160,18 @@ static void o2quo_make_decision(struct work_struct *work)
 	}
 
 out:
-	spin_unlock(&qs->qs_lock);
-	if (fence)
+	if (fence) {
+		spin_unlock(&qs->qs_lock);
 		o2quo_fence_self();
+	} else {
+		mlog(ML_NOTICE, "not fencing this node, heartbeating: %d, "
+			"connected: %d, lowest: %d (%sreachable)\n",
+			qs->qs_heartbeating, qs->qs_connected, lowest_hb,
+			lowest_reachable ? "" : "un");
+		spin_unlock(&qs->qs_lock);
+
+	}
+
 }
 
 static void o2quo_set_hold(struct o2quo_state *qs, u8 node)
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 681691bc233a..ea34952f9496 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1480,6 +1480,14 @@ static int o2net_set_nodelay(struct socket *sock)
 	return ret;
 }
 
+static int o2net_set_usertimeout(struct socket *sock)
+{
+	int user_timeout = O2NET_TCP_USER_TIMEOUT;
+
+	return kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
+				(char *)&user_timeout, sizeof(user_timeout));
+}
+
 static void o2net_initialize_handshake(void)
 {
 	o2net_hand->o2hb_heartbeat_timeout_ms = cpu_to_be32(
@@ -1536,16 +1544,20 @@ static void o2net_idle_timer(unsigned long data)
 #endif
 
 	printk(KERN_NOTICE "o2net: Connection to " SC_NODEF_FMT " has been "
-	       "idle for %lu.%lu secs, shutting it down.\n", SC_NODEF_ARGS(sc),
-	       msecs / 1000, msecs % 1000);
+	       "idle for %lu.%lu secs.\n",
+	       SC_NODEF_ARGS(sc), msecs / 1000, msecs % 1000);
 
-	/*
-	 * Initialize the nn_timeout so that the next connection attempt
-	 * will continue in o2net_start_connect.
+	/* idle timerout happen, don't shutdown the connection, but
+	 * make fence decision. Maybe the connection can recover before
+	 * the decision is made.
 	 */
 	atomic_set(&nn->nn_timeout, 1);
+	o2quo_conn_err(o2net_num_from_nn(nn));
+	queue_delayed_work(o2net_wq, &nn->nn_still_up,
+			msecs_to_jiffies(O2NET_QUORUM_DELAY_MS));
+
+	o2net_sc_reset_idle_timer(sc);
 
-	o2net_sc_queue_work(sc, &sc->sc_shutdown_work);
 }
 
 static void o2net_sc_reset_idle_timer(struct o2net_sock_container *sc)
@@ -1560,6 +1572,15 @@ static void o2net_sc_reset_idle_timer(struct o2net_sock_container *sc)
 
 static void o2net_sc_postpone_idle(struct o2net_sock_container *sc)
 {
+	struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num);
+
+	/* clear fence decision since the connection recover from timeout*/
+	if (atomic_read(&nn->nn_timeout)) {
+		o2quo_conn_up(o2net_num_from_nn(nn));
+		cancel_delayed_work(&nn->nn_still_up);
+		atomic_set(&nn->nn_timeout, 0);
+	}
+
 	/* Only push out an existing timer */
 	if (timer_pending(&sc->sc_idle_timeout))
 		o2net_sc_reset_idle_timer(sc);
@@ -1650,6 +1671,12 @@ static void o2net_start_connect(struct work_struct *work)
 		goto out;
 	}
 
+	ret = o2net_set_usertimeout(sock);
+	if (ret) {
+		mlog(ML_ERROR, "set TCP_USER_TIMEOUT failed with %d\n", ret);
+		goto out;
+	}
+
 	o2net_register_callbacks(sc->sc_sock->sk, sc);
 
 	spin_lock(&nn->nn_lock);
@@ -1831,6 +1858,12 @@ static int o2net_accept_one(struct socket *sock, int *more)
 		goto out;
 	}
 
+	ret = o2net_set_usertimeout(new_sock);
+	if (ret) {
+		mlog(ML_ERROR, "set TCP_USER_TIMEOUT failed with %d\n", ret);
+		goto out;
+	}
+
 	slen = sizeof(sin);
 	ret = new_sock->ops->getname(new_sock, (struct sockaddr *) &sin,
 				       &slen, 1);
diff --git a/fs/ocfs2/cluster/tcp.h b/fs/ocfs2/cluster/tcp.h
index 5bada2a69b50..c571e849fda4 100644
--- a/fs/ocfs2/cluster/tcp.h
+++ b/fs/ocfs2/cluster/tcp.h
@@ -63,6 +63,7 @@ typedef void (o2net_post_msg_handler_func)(int status, void *data,
 #define O2NET_KEEPALIVE_DELAY_MS_DEFAULT	2000
 #define O2NET_IDLE_TIMEOUT_MS_DEFAULT		30000
 
+#define O2NET_TCP_USER_TIMEOUT			0x7fffffff
 
 /* TODO: figure this out.... */
 static inline int o2net_link_down(int err, struct socket *sock)
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 0717662b4aef..e737a4ce7d7a 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -4477,7 +4477,7 @@ int ocfs2_dx_dir_truncate(struct inode *dir, struct buffer_head *di_bh)
 		p_cpos = ocfs2_blocks_to_clusters(dir->i_sb, blkno);
 
 		ret = ocfs2_remove_btree_range(dir, &et, cpos, p_cpos, clen, 0,
-					       &dealloc, 0);
+					       &dealloc, 0, false);
 		if (ret) {
 			mlog_errno(ret);
 			goto out;
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 3ec906ef5d9a..a875436461fa 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -498,16 +498,6 @@ static void dlm_lockres_release(struct kref *kref)
 	mlog(0, "destroying lockres %.*s\n", res->lockname.len,
 	     res->lockname.name);
 
-	spin_lock(&dlm->track_lock);
-	if (!list_empty(&res->tracking))
-		list_del_init(&res->tracking);
-	else {
-		mlog(ML_ERROR, "Resource %.*s not on the Tracking list\n",
-		     res->lockname.len, res->lockname.name);
-		dlm_print_one_lock_resource(res);
-	}
-	spin_unlock(&dlm->track_lock);
-
 	atomic_dec(&dlm->res_cur_count);
 
 	if (!hlist_unhashed(&res->hash_node) ||
@@ -694,14 +684,6 @@ void __dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
 			res->inflight_assert_workers);
 }
 
-static void dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
-		struct dlm_lock_resource *res)
-{
-	spin_lock(&res->spinlock);
-	__dlm_lockres_grab_inflight_worker(dlm, res);
-	spin_unlock(&res->spinlock);
-}
-
 static void __dlm_lockres_drop_inflight_worker(struct dlm_ctxt *dlm,
 		struct dlm_lock_resource *res)
 {
@@ -1635,6 +1617,7 @@ send_response:
 		}
 		mlog(0, "%u is the owner of %.*s, cleaning everyone else\n",
 			     dlm->node_num, res->lockname.len, res->lockname.name);
+		spin_lock(&res->spinlock);
 		ret = dlm_dispatch_assert_master(dlm, res, 0, request->node_idx,
 						 DLM_ASSERT_MASTER_MLE_CLEANUP);
 		if (ret < 0) {
@@ -1642,7 +1625,8 @@ send_response:
 			response = DLM_MASTER_RESP_ERROR;
 			dlm_lockres_put(res);
 		} else
-			dlm_lockres_grab_inflight_worker(dlm, res);
+			__dlm_lockres_grab_inflight_worker(dlm, res);
+		spin_unlock(&res->spinlock);
 	} else {
 		if (res)
 			dlm_lockres_put(res);
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 69aac6f088ad..cd75e186cfc5 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -211,6 +211,16 @@ static void dlm_purge_lockres(struct dlm_ctxt *dlm,
 
 	__dlm_unhash_lockres(dlm, res);
 
+	spin_lock(&dlm->track_lock);
+	if (!list_empty(&res->tracking))
+		list_del_init(&res->tracking);
+	else {
+		mlog(ML_ERROR, "Resource %.*s not on the Tracking list\n",
+				res->lockname.len, res->lockname.name);
+		dlm_print_one_lock_resource(res);
+	}
+	spin_unlock(&dlm->track_lock);
+
 	/* lockres is not in the hash now.  drop the flag and wake up
 	 * any processes waiting in dlm_get_lock_resource. */
 	if (!master) {
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 2930e231f3f9..319c858e70bf 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1804,7 +1804,7 @@ static int ocfs2_remove_inode_range(struct inode *inode,
 
 		ret = ocfs2_remove_btree_range(inode, &et, trunc_cpos,
 					       phys_cpos, trunc_len, flags,
-					       &dealloc, refcount_loc);
+					       &dealloc, refcount_loc, false);
 		if (ret < 0) {
 			mlog_errno(ret);
 			goto out;
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 437de7f768c6..21708cda4b8a 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -1192,17 +1192,9 @@ void ocfs2_evict_inode(struct inode *inode)
 int ocfs2_drop_inode(struct inode *inode)
 {
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
-	int res;
-
 	trace_ocfs2_drop_inode((unsigned long long)oi->ip_blkno,
 				inode->i_nlink, oi->ip_flags);
-
-	if (oi->ip_flags & OCFS2_INODE_MAYBE_ORPHANED)
-		res = 1;
-	else
-		res = generic_drop_inode(inode);
-
-	return res;
+	return 1;
 }
 
 /*
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 6f66b3751ace..53e6c40ed4c6 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -35,9 +35,8 @@
 		copy_to_user((typeof(a) __user *)b, &(a), sizeof(a))
 
 /*
- * This call is void because we are already reporting an error that may
- * be -EFAULT.  The error will be returned from the ioctl(2) call.  It's
- * just a best-effort to tell userspace that this request caused the error.
+ * This is just a best-effort to tell userspace that this request
+ * caused the error.
  */
 static inline void o2info_set_request_error(struct ocfs2_info_request *kreq,
 					struct ocfs2_info_request __user *req)
@@ -146,136 +145,105 @@ bail:
 static int ocfs2_info_handle_blocksize(struct inode *inode,
 				       struct ocfs2_info_request __user *req)
 {
-	int status = -EFAULT;
 	struct ocfs2_info_blocksize oib;
 
 	if (o2info_from_user(oib, req))
-		goto bail;
+		return -EFAULT;
 
 	oib.ib_blocksize = inode->i_sb->s_blocksize;
 
 	o2info_set_request_filled(&oib.ib_req);
 
 	if (o2info_to_user(oib, req))
-		goto bail;
-
-	status = 0;
-bail:
-	if (status)
-		o2info_set_request_error(&oib.ib_req, req);
+		return -EFAULT;
 
-	return status;
+	return 0;
 }
 
 static int ocfs2_info_handle_clustersize(struct inode *inode,
 					 struct ocfs2_info_request __user *req)
 {
-	int status = -EFAULT;
 	struct ocfs2_info_clustersize oic;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	if (o2info_from_user(oic, req))
-		goto bail;
+		return -EFAULT;
 
 	oic.ic_clustersize = osb->s_clustersize;
 
 	o2info_set_request_filled(&oic.ic_req);
 
 	if (o2info_to_user(oic, req))
-		goto bail;
-
-	status = 0;
-bail:
-	if (status)
-		o2info_set_request_error(&oic.ic_req, req);
+		return -EFAULT;
 
-	return status;
+	return 0;
 }
 
 static int ocfs2_info_handle_maxslots(struct inode *inode,
 				      struct ocfs2_info_request __user *req)
 {
-	int status = -EFAULT;
 	struct ocfs2_info_maxslots oim;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	if (o2info_from_user(oim, req))
-		goto bail;
+		return -EFAULT;
 
 	oim.im_max_slots = osb->max_slots;
 
 	o2info_set_request_filled(&oim.im_req);
 
 	if (o2info_to_user(oim, req))
-		goto bail;
+		return -EFAULT;
 
-	status = 0;
-bail:
-	if (status)
-		o2info_set_request_error(&oim.im_req, req);
-
-	return status;
+	return 0;
 }
 
 static int ocfs2_info_handle_label(struct inode *inode,
 				   struct ocfs2_info_request __user *req)
 {
-	int status = -EFAULT;
 	struct ocfs2_info_label oil;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	if (o2info_from_user(oil, req))
-		goto bail;
+		return -EFAULT;
 
 	memcpy(oil.il_label, osb->vol_label, OCFS2_MAX_VOL_LABEL_LEN);
 
 	o2info_set_request_filled(&oil.il_req);
 
 	if (o2info_to_user(oil, req))
-		goto bail;
+		return -EFAULT;
 
-	status = 0;
-bail:
-	if (status)
-		o2info_set_request_error(&oil.il_req, req);
-
-	return status;
+	return 0;
 }
 
 static int ocfs2_info_handle_uuid(struct inode *inode,
 				  struct ocfs2_info_request __user *req)
 {
-	int status = -EFAULT;
 	struct ocfs2_info_uuid oiu;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	if (o2info_from_user(oiu, req))
-		goto bail;
+		return -EFAULT;
 
 	memcpy(oiu.iu_uuid_str, osb->uuid_str, OCFS2_TEXT_UUID_LEN + 1);
 
 	o2info_set_request_filled(&oiu.iu_req);
 
 	if (o2info_to_user(oiu, req))
-		goto bail;
-
-	status = 0;
-bail:
-	if (status)
-		o2info_set_request_error(&oiu.iu_req, req);
+		return -EFAULT;
 
-	return status;
+	return 0;
 }
 
 static int ocfs2_info_handle_fs_features(struct inode *inode,
 					 struct ocfs2_info_request __user *req)
 {
-	int status = -EFAULT;
 	struct ocfs2_info_fs_features oif;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	if (o2info_from_user(oif, req))
-		goto bail;
+		return -EFAULT;
 
 	oif.if_compat_features = osb->s_feature_compat;
 	oif.if_incompat_features = osb->s_feature_incompat;
@@ -284,39 +252,28 @@ static int ocfs2_info_handle_fs_features(struct inode *inode,
 	o2info_set_request_filled(&oif.if_req);
 
 	if (o2info_to_user(oif, req))
-		goto bail;
+		return -EFAULT;
 
-	status = 0;
-bail:
-	if (status)
-		o2info_set_request_error(&oif.if_req, req);
-
-	return status;
+	return 0;
 }
 
 static int ocfs2_info_handle_journal_size(struct inode *inode,
 					  struct ocfs2_info_request __user *req)
 {
-	int status = -EFAULT;
 	struct ocfs2_info_journal_size oij;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	if (o2info_from_user(oij, req))
-		goto bail;
+		return -EFAULT;
 
 	oij.ij_journal_size = i_size_read(osb->journal->j_inode);
 
 	o2info_set_request_filled(&oij.ij_req);
 
 	if (o2info_to_user(oij, req))
-		goto bail;
+		return -EFAULT;
 
-	status = 0;
-bail:
-	if (status)
-		o2info_set_request_error(&oij.ij_req, req);
-
-	return status;
+	return 0;
 }
 
 static int ocfs2_info_scan_inode_alloc(struct ocfs2_super *osb,
@@ -373,7 +330,7 @@ static int ocfs2_info_handle_freeinode(struct inode *inode,
 	u32 i;
 	u64 blkno = -1;
 	char namebuf[40];
-	int status = -EFAULT, type = INODE_ALLOC_SYSTEM_INODE;
+	int status, type = INODE_ALLOC_SYSTEM_INODE;
 	struct ocfs2_info_freeinode *oifi = NULL;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct inode *inode_alloc = NULL;
@@ -385,8 +342,10 @@ static int ocfs2_info_handle_freeinode(struct inode *inode,
 		goto out_err;
 	}
 
-	if (o2info_from_user(*oifi, req))
-		goto bail;
+	if (o2info_from_user(*oifi, req)) {
+		status = -EFAULT;
+		goto out_free;
+	}
 
 	oifi->ifi_slotnum = osb->max_slots;
 
@@ -424,14 +383,16 @@ static int ocfs2_info_handle_freeinode(struct inode *inode,
 
 	o2info_set_request_filled(&oifi->ifi_req);
 
-	if (o2info_to_user(*oifi, req))
-		goto bail;
+	if (o2info_to_user(*oifi, req)) {
+		status = -EFAULT;
+		goto out_free;
+	}
 
 	status = 0;
 bail:
 	if (status)
 		o2info_set_request_error(&oifi->ifi_req, req);
-
+out_free:
 	kfree(oifi);
 out_err:
 	return status;
@@ -658,7 +619,7 @@ static int ocfs2_info_handle_freefrag(struct inode *inode,
 {
 	u64 blkno = -1;
 	char namebuf[40];
-	int status = -EFAULT, type = GLOBAL_BITMAP_SYSTEM_INODE;
+	int status, type = GLOBAL_BITMAP_SYSTEM_INODE;
 
 	struct ocfs2_info_freefrag *oiff;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
@@ -671,8 +632,10 @@ static int ocfs2_info_handle_freefrag(struct inode *inode,
 		goto out_err;
 	}
 
-	if (o2info_from_user(*oiff, req))
-		goto bail;
+	if (o2info_from_user(*oiff, req)) {
+		status = -EFAULT;
+		goto out_free;
+	}
 	/*
 	 * chunksize from userspace should be power of 2.
 	 */
@@ -711,14 +674,14 @@ static int ocfs2_info_handle_freefrag(struct inode *inode,
 
 	if (o2info_to_user(*oiff, req)) {
 		status = -EFAULT;
-		goto bail;
+		goto out_free;
 	}
 
 	status = 0;
 bail:
 	if (status)
 		o2info_set_request_error(&oiff->iff_req, req);
-
+out_free:
 	kfree(oiff);
 out_err:
 	return status;
@@ -727,23 +690,17 @@ out_err:
 static int ocfs2_info_handle_unknown(struct inode *inode,
 				     struct ocfs2_info_request __user *req)
 {
-	int status = -EFAULT;
 	struct ocfs2_info_request oir;
 
 	if (o2info_from_user(oir, req))
-		goto bail;
+		return -EFAULT;
 
 	o2info_clear_request_filled(&oir);
 
 	if (o2info_to_user(oir, req))
-		goto bail;
+		return -EFAULT;
 
-	status = 0;
-bail:
-	if (status)
-		o2info_set_request_error(&oir, req);
-
-	return status;
+	return 0;
 }
 
 /*
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index ec58c7659183..ba8819702c56 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -321,7 +321,7 @@ static int omfs_get_imap(struct super_block *sb)
 		goto out;
 
 	sbi->s_imap_size = array_size;
-	sbi->s_imap = kzalloc(array_size * sizeof(unsigned long *), GFP_KERNEL);
+	sbi->s_imap = kcalloc(array_size, sizeof(unsigned long *), GFP_KERNEL);
 	if (!sbi->s_imap)
 		goto nomem;
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 0131156ce7c9..baf852b648ad 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -105,7 +105,7 @@
  */
 
 struct pid_entry {
-	char *name;
+	const char *name;
 	int len;
 	umode_t mode;
 	const struct inode_operations *iop;
@@ -130,10 +130,6 @@ struct pid_entry {
 		{ .proc_get_link = get_link } )
 #define REG(NAME, MODE, fops)				\
 	NOD(NAME, (S_IFREG|(MODE)), NULL, &fops, {})
-#define INF(NAME, MODE, read)				\
-	NOD(NAME, (S_IFREG|(MODE)), 			\
-		NULL, &proc_info_file_operations,	\
-		{ .proc_read = read } )
 #define ONE(NAME, MODE, show)				\
 	NOD(NAME, (S_IFREG|(MODE)), 			\
 		NULL, &proc_single_file_operations,	\
@@ -200,27 +196,32 @@ static int proc_root_link(struct dentry *dentry, struct path *path)
 	return result;
 }
 
-static int proc_pid_cmdline(struct task_struct *task, char *buffer)
+static int proc_pid_cmdline(struct seq_file *m, struct pid_namespace *ns,
+			    struct pid *pid, struct task_struct *task)
 {
-	return get_cmdline(task, buffer, PAGE_SIZE);
+	/*
+	 * Rely on struct seq_operations::show() being called once
+	 * per internal buffer allocation. See single_open(), traverse().
+	 */
+	BUG_ON(m->size < PAGE_SIZE);
+	m->count += get_cmdline(task, m->buf, PAGE_SIZE);
+	return 0;
 }
 
-static int proc_pid_auxv(struct task_struct *task, char *buffer)
+static int proc_pid_auxv(struct seq_file *m, struct pid_namespace *ns,
+			 struct pid *pid, struct task_struct *task)
 {
 	struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ);
-	int res = PTR_ERR(mm);
 	if (mm && !IS_ERR(mm)) {
 		unsigned int nwords = 0;
 		do {
 			nwords += 2;
 		} while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */
-		res = nwords * sizeof(mm->saved_auxv[0]);
-		if (res > PAGE_SIZE)
-			res = PAGE_SIZE;
-		memcpy(buffer, mm->saved_auxv, res);
+		seq_write(m, mm->saved_auxv, nwords * sizeof(mm->saved_auxv[0]));
 		mmput(mm);
-	}
-	return res;
+		return 0;
+	} else
+		return PTR_ERR(mm);
 }
 
 
@@ -229,7 +230,8 @@ static int proc_pid_auxv(struct task_struct *task, char *buffer)
  * Provides a wchan file via kallsyms in a proper one-value-per-file format.
  * Returns the resolved symbol.  If that fails, simply return the address.
  */
-static int proc_pid_wchan(struct task_struct *task, char *buffer)
+static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
+			  struct pid *pid, struct task_struct *task)
 {
 	unsigned long wchan;
 	char symname[KSYM_NAME_LEN];
@@ -240,9 +242,9 @@ static int proc_pid_wchan(struct task_struct *task, char *buffer)
 		if (!ptrace_may_access(task, PTRACE_MODE_READ))
 			return 0;
 		else
-			return sprintf(buffer, "%lu", wchan);
+			return seq_printf(m, "%lu", wchan);
 	else
-		return sprintf(buffer, "%s", symname);
+		return seq_printf(m, "%s", symname);
 }
 #endif /* CONFIG_KALLSYMS */
 
@@ -304,9 +306,10 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
 /*
  * Provides /proc/PID/schedstat
  */
-static int proc_pid_schedstat(struct task_struct *task, char *buffer)
+static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns,
+			      struct pid *pid, struct task_struct *task)
 {
-	return sprintf(buffer, "%llu %llu %lu\n",
+	return seq_printf(m, "%llu %llu %lu\n",
 			(unsigned long long)task->se.sum_exec_runtime,
 			(unsigned long long)task->sched_info.run_delay,
 			task->sched_info.pcount);
@@ -404,7 +407,8 @@ static const struct file_operations proc_cpuset_operations = {
 };
 #endif
 
-static int proc_oom_score(struct task_struct *task, char *buffer)
+static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns,
+			  struct pid *pid, struct task_struct *task)
 {
 	unsigned long totalpages = totalram_pages + total_swap_pages;
 	unsigned long points = 0;
@@ -414,12 +418,12 @@ static int proc_oom_score(struct task_struct *task, char *buffer)
 		points = oom_badness(task, NULL, NULL, totalpages) *
 						1000 / totalpages;
 	read_unlock(&tasklist_lock);
-	return sprintf(buffer, "%lu\n", points);
+	return seq_printf(m, "%lu\n", points);
 }
 
 struct limit_names {
-	char *name;
-	char *unit;
+	const char *name;
+	const char *unit;
 };
 
 static const struct limit_names lnames[RLIM_NLIMITS] = {
@@ -442,12 +446,11 @@ static const struct limit_names lnames[RLIM_NLIMITS] = {
 };
 
 /* Display limits for a process */
-static int proc_pid_limits(struct task_struct *task, char *buffer)
+static int proc_pid_limits(struct seq_file *m, struct pid_namespace *ns,
+			   struct pid *pid, struct task_struct *task)
 {
 	unsigned int i;
-	int count = 0;
 	unsigned long flags;
-	char *bufptr = buffer;
 
 	struct rlimit rlim[RLIM_NLIMITS];
 
@@ -459,35 +462,34 @@ static int proc_pid_limits(struct task_struct *task, char *buffer)
 	/*
 	 * print the file header
 	 */
-	count += sprintf(&bufptr[count], "%-25s %-20s %-20s %-10s\n",
+       seq_printf(m, "%-25s %-20s %-20s %-10s\n",
 			"Limit", "Soft Limit", "Hard Limit", "Units");
 
 	for (i = 0; i < RLIM_NLIMITS; i++) {
 		if (rlim[i].rlim_cur == RLIM_INFINITY)
-			count += sprintf(&bufptr[count], "%-25s %-20s ",
+			seq_printf(m, "%-25s %-20s ",
 					 lnames[i].name, "unlimited");
 		else
-			count += sprintf(&bufptr[count], "%-25s %-20lu ",
+			seq_printf(m, "%-25s %-20lu ",
 					 lnames[i].name, rlim[i].rlim_cur);
 
 		if (rlim[i].rlim_max == RLIM_INFINITY)
-			count += sprintf(&bufptr[count], "%-20s ", "unlimited");
+			seq_printf(m, "%-20s ", "unlimited");
 		else
-			count += sprintf(&bufptr[count], "%-20lu ",
-					 rlim[i].rlim_max);
+			seq_printf(m, "%-20lu ", rlim[i].rlim_max);
 
 		if (lnames[i].unit)
-			count += sprintf(&bufptr[count], "%-10s\n",
-					 lnames[i].unit);
+			seq_printf(m, "%-10s\n", lnames[i].unit);
 		else
-			count += sprintf(&bufptr[count], "\n");
+			seq_putc(m, '\n');
 	}
 
-	return count;
+	return 0;
 }
 
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK
-static int proc_pid_syscall(struct task_struct *task, char *buffer)
+static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns,
+			    struct pid *pid, struct task_struct *task)
 {
 	long nr;
 	unsigned long args[6], sp, pc;
@@ -496,11 +498,11 @@ static int proc_pid_syscall(struct task_struct *task, char *buffer)
 		return res;
 
 	if (task_current_syscall(task, &nr, args, 6, &sp, &pc))
-		res = sprintf(buffer, "running\n");
+		seq_puts(m, "running\n");
 	else if (nr < 0)
-		res = sprintf(buffer, "%ld 0x%lx 0x%lx\n", nr, sp, pc);
+		seq_printf(m, "%ld 0x%lx 0x%lx\n", nr, sp, pc);
 	else
-		res = sprintf(buffer,
+		seq_printf(m,
 		       "%ld 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n",
 		       nr,
 		       args[0], args[1], args[2], args[3], args[4], args[5],
@@ -598,43 +600,6 @@ static const struct inode_operations proc_def_inode_operations = {
 	.setattr	= proc_setattr,
 };
 
-#define PROC_BLOCK_SIZE	(3*1024)		/* 4K page size but our output routines use some slack for overruns */
-
-static ssize_t proc_info_read(struct file * file, char __user * buf,
-			  size_t count, loff_t *ppos)
-{
-	struct inode * inode = file_inode(file);
-	unsigned long page;
-	ssize_t length;
-	struct task_struct *task = get_proc_task(inode);
-
-	length = -ESRCH;
-	if (!task)
-		goto out_no_task;
-
-	if (count > PROC_BLOCK_SIZE)
-		count = PROC_BLOCK_SIZE;
-
-	length = -ENOMEM;
-	if (!(page = __get_free_page(GFP_TEMPORARY)))
-		goto out;
-
-	length = PROC_I(inode)->op.proc_read(task, (char*)page);
-
-	if (length >= 0)
-		length = simple_read_from_buffer(buf, count, ppos, (char *)page, length);
-	free_page(page);
-out:
-	put_task_struct(task);
-out_no_task:
-	return length;
-}
-
-static const struct file_operations proc_info_file_operations = {
-	.read		= proc_info_read,
-	.llseek		= generic_file_llseek,
-};
-
 static int proc_single_show(struct seq_file *m, void *v)
 {
 	struct inode *inode = m->private;
@@ -2056,7 +2021,7 @@ static int show_timer(struct seq_file *m, void *v)
 	struct k_itimer *timer;
 	struct timers_private *tp = m->private;
 	int notify;
-	static char *nstr[] = {
+	static const char * const nstr[] = {
 		[SIGEV_SIGNAL] = "signal",
 		[SIGEV_NONE] = "none",
 		[SIGEV_THREAD] = "thread",
@@ -2392,7 +2357,7 @@ static const struct file_operations proc_coredump_filter_operations = {
 #endif
 
 #ifdef CONFIG_TASK_IO_ACCOUNTING
-static int do_io_accounting(struct task_struct *task, char *buffer, int whole)
+static int do_io_accounting(struct task_struct *task, struct seq_file *m, int whole)
 {
 	struct task_io_accounting acct = task->ioac;
 	unsigned long flags;
@@ -2416,7 +2381,7 @@ static int do_io_accounting(struct task_struct *task, char *buffer, int whole)
 
 		unlock_task_sighand(task, &flags);
 	}
-	result = sprintf(buffer,
+	result = seq_printf(m,
 			"rchar: %llu\n"
 			"wchar: %llu\n"
 			"syscr: %llu\n"
@@ -2436,20 +2401,22 @@ out_unlock:
 	return result;
 }
 
-static int proc_tid_io_accounting(struct task_struct *task, char *buffer)
+static int proc_tid_io_accounting(struct seq_file *m, struct pid_namespace *ns,
+				  struct pid *pid, struct task_struct *task)
 {
-	return do_io_accounting(task, buffer, 0);
+	return do_io_accounting(task, m, 0);
 }
 
-static int proc_tgid_io_accounting(struct task_struct *task, char *buffer)
+static int proc_tgid_io_accounting(struct seq_file *m, struct pid_namespace *ns,
+				   struct pid *pid, struct task_struct *task)
 {
-	return do_io_accounting(task, buffer, 1);
+	return do_io_accounting(task, m, 1);
 }
 #endif /* CONFIG_TASK_IO_ACCOUNTING */
 
 #ifdef CONFIG_USER_NS
 static int proc_id_map_open(struct inode *inode, struct file *file,
-	struct seq_operations *seq_ops)
+	const struct seq_operations *seq_ops)
 {
 	struct user_namespace *ns = NULL;
 	struct task_struct *task;
@@ -2557,10 +2524,10 @@ static const struct pid_entry tgid_base_stuff[] = {
 	DIR("net",        S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations),
 #endif
 	REG("environ",    S_IRUSR, proc_environ_operations),
-	INF("auxv",       S_IRUSR, proc_pid_auxv),
+	ONE("auxv",       S_IRUSR, proc_pid_auxv),
 	ONE("status",     S_IRUGO, proc_pid_status),
 	ONE("personality", S_IRUSR, proc_pid_personality),
-	INF("limits",	  S_IRUGO, proc_pid_limits),
+	ONE("limits",	  S_IRUGO, proc_pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
 	REG("sched",      S_IRUGO|S_IWUSR, proc_pid_sched_operations),
 #endif
@@ -2569,9 +2536,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 #endif
 	REG("comm",      S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK
-	INF("syscall",    S_IRUSR, proc_pid_syscall),
+	ONE("syscall",    S_IRUSR, proc_pid_syscall),
 #endif
-	INF("cmdline",    S_IRUGO, proc_pid_cmdline),
+	ONE("cmdline",    S_IRUGO, proc_pid_cmdline),
 	ONE("stat",       S_IRUGO, proc_tgid_stat),
 	ONE("statm",      S_IRUGO, proc_pid_statm),
 	REG("maps",       S_IRUGO, proc_pid_maps_operations),
@@ -2594,13 +2561,13 @@ static const struct pid_entry tgid_base_stuff[] = {
 	DIR("attr",       S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations),
 #endif
 #ifdef CONFIG_KALLSYMS
-	INF("wchan",      S_IRUGO, proc_pid_wchan),
+	ONE("wchan",      S_IRUGO, proc_pid_wchan),
 #endif
 #ifdef CONFIG_STACKTRACE
 	ONE("stack",      S_IRUSR, proc_pid_stack),
 #endif
 #ifdef CONFIG_SCHEDSTATS
-	INF("schedstat",  S_IRUGO, proc_pid_schedstat),
+	ONE("schedstat",  S_IRUGO, proc_pid_schedstat),
 #endif
 #ifdef CONFIG_LATENCYTOP
 	REG("latency",  S_IRUGO, proc_lstats_operations),
@@ -2611,7 +2578,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_CGROUPS
 	REG("cgroup",  S_IRUGO, proc_cgroup_operations),
 #endif
-	INF("oom_score",  S_IRUGO, proc_oom_score),
+	ONE("oom_score",  S_IRUGO, proc_oom_score),
 	REG("oom_adj",    S_IRUGO|S_IWUSR, proc_oom_adj_operations),
 	REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
 #ifdef CONFIG_AUDITSYSCALL
@@ -2625,10 +2592,10 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("coredump_filter", S_IRUGO|S_IWUSR, proc_coredump_filter_operations),
 #endif
 #ifdef CONFIG_TASK_IO_ACCOUNTING
-	INF("io",	S_IRUSR, proc_tgid_io_accounting),
+	ONE("io",	S_IRUSR, proc_tgid_io_accounting),
 #endif
 #ifdef CONFIG_HARDWALL
-	INF("hardwall",   S_IRUGO, proc_pid_hardwall),
+	ONE("hardwall",   S_IRUGO, proc_pid_hardwall),
 #endif
 #ifdef CONFIG_USER_NS
 	REG("uid_map",    S_IRUGO|S_IWUSR, proc_uid_map_operations),
@@ -2780,12 +2747,12 @@ out:
 
 struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
 {
-	int result = 0;
+	int result = -ENOENT;
 	struct task_struct *task;
 	unsigned tgid;
 	struct pid_namespace *ns;
 
-	tgid = name_to_int(dentry);
+	tgid = name_to_int(&dentry->d_name);
 	if (tgid == ~0U)
 		goto out;
 
@@ -2904,18 +2871,18 @@ static const struct pid_entry tid_base_stuff[] = {
 	DIR("net",        S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations),
 #endif
 	REG("environ",   S_IRUSR, proc_environ_operations),
-	INF("auxv",      S_IRUSR, proc_pid_auxv),
+	ONE("auxv",      S_IRUSR, proc_pid_auxv),
 	ONE("status",    S_IRUGO, proc_pid_status),
 	ONE("personality", S_IRUSR, proc_pid_personality),
-	INF("limits",	 S_IRUGO, proc_pid_limits),
+	ONE("limits",	 S_IRUGO, proc_pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
 	REG("sched",     S_IRUGO|S_IWUSR, proc_pid_sched_operations),
 #endif
 	REG("comm",      S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK
-	INF("syscall",   S_IRUSR, proc_pid_syscall),
+	ONE("syscall",   S_IRUSR, proc_pid_syscall),
 #endif
-	INF("cmdline",   S_IRUGO, proc_pid_cmdline),
+	ONE("cmdline",   S_IRUGO, proc_pid_cmdline),
 	ONE("stat",      S_IRUGO, proc_tid_stat),
 	ONE("statm",     S_IRUGO, proc_pid_statm),
 	REG("maps",      S_IRUGO, proc_tid_maps_operations),
@@ -2940,13 +2907,13 @@ static const struct pid_entry tid_base_stuff[] = {
 	DIR("attr",      S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations),
 #endif
 #ifdef CONFIG_KALLSYMS
-	INF("wchan",     S_IRUGO, proc_pid_wchan),
+	ONE("wchan",     S_IRUGO, proc_pid_wchan),
 #endif
 #ifdef CONFIG_STACKTRACE
 	ONE("stack",      S_IRUSR, proc_pid_stack),
 #endif
 #ifdef CONFIG_SCHEDSTATS
-	INF("schedstat", S_IRUGO, proc_pid_schedstat),
+	ONE("schedstat", S_IRUGO, proc_pid_schedstat),
 #endif
 #ifdef CONFIG_LATENCYTOP
 	REG("latency",  S_IRUGO, proc_lstats_operations),
@@ -2957,7 +2924,7 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_CGROUPS
 	REG("cgroup",  S_IRUGO, proc_cgroup_operations),
 #endif
-	INF("oom_score", S_IRUGO, proc_oom_score),
+	ONE("oom_score", S_IRUGO, proc_oom_score),
 	REG("oom_adj",   S_IRUGO|S_IWUSR, proc_oom_adj_operations),
 	REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
 #ifdef CONFIG_AUDITSYSCALL
@@ -2968,10 +2935,10 @@ static const struct pid_entry tid_base_stuff[] = {
 	REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations),
 #endif
 #ifdef CONFIG_TASK_IO_ACCOUNTING
-	INF("io",	S_IRUSR, proc_tid_io_accounting),
+	ONE("io",	S_IRUSR, proc_tid_io_accounting),
 #endif
 #ifdef CONFIG_HARDWALL
-	INF("hardwall",   S_IRUGO, proc_pid_hardwall),
+	ONE("hardwall",   S_IRUGO, proc_pid_hardwall),
 #endif
 #ifdef CONFIG_USER_NS
 	REG("uid_map",    S_IRUGO|S_IWUSR, proc_uid_map_operations),
@@ -3041,7 +3008,7 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry
 	if (!leader)
 		goto out_no_task;
 
-	tid = name_to_int(dentry);
+	tid = name_to_int(&dentry->d_name);
 	if (tid == ~0U)
 		goto out;
 
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 0788d093f5d8..955bb55fab8c 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -206,7 +206,7 @@ static struct dentry *proc_lookupfd_common(struct inode *dir,
 {
 	struct task_struct *task = get_proc_task(dir);
 	int result = -ENOENT;
-	unsigned fd = name_to_int(dentry);
+	unsigned fd = name_to_int(&dentry->d_name);
 
 	if (!task)
 		goto out_no_task;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index b7f268eb5f45..317b72641ebf 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -27,7 +27,7 @@
 
 #include "internal.h"
 
-DEFINE_SPINLOCK(proc_subdir_lock);
+static DEFINE_SPINLOCK(proc_subdir_lock);
 
 static int proc_match(unsigned int len, const char *name, struct proc_dir_entry *de)
 {
@@ -330,28 +330,28 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
 					  nlink_t nlink)
 {
 	struct proc_dir_entry *ent = NULL;
-	const char *fn = name;
-	unsigned int len;
-
-	/* make sure name is valid */
-	if (!name || !strlen(name))
-		goto out;
+	const char *fn;
+	struct qstr qstr;
 
 	if (xlate_proc_name(name, parent, &fn) != 0)
 		goto out;
+	qstr.name = fn;
+	qstr.len = strlen(fn);
+	if (qstr.len == 0 || qstr.len >= 256) {
+		WARN(1, "name len %u\n", qstr.len);
+		return NULL;
+	}
+	if (*parent == &proc_root && name_to_int(&qstr) != ~0U) {
+		WARN(1, "create '/proc/%s' by hand\n", qstr.name);
+		return NULL;
+	}
 
-	/* At this point there must not be any '/' characters beyond *fn */
-	if (strchr(fn, '/'))
-		goto out;
-
-	len = strlen(fn);
-
-	ent = kzalloc(sizeof(struct proc_dir_entry) + len + 1, GFP_KERNEL);
+	ent = kzalloc(sizeof(struct proc_dir_entry) + qstr.len + 1, GFP_KERNEL);
 	if (!ent)
 		goto out;
 
-	memcpy(ent->name, fn, len + 1);
-	ent->namelen = len;
+	memcpy(ent->name, fn, qstr.len + 1);
+	ent->namelen = qstr.len;
 	ent->mode = mode;
 	ent->nlink = nlink;
 	atomic_set(&ent->count, 1);
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index ee04619173b2..7da13e49128a 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -52,7 +52,6 @@ struct proc_dir_entry {
 
 union proc_op {
 	int (*proc_get_link)(struct dentry *, struct path *);
-	int (*proc_read)(struct task_struct *task, char *page);
 	int (*proc_show)(struct seq_file *m,
 		struct pid_namespace *ns, struct pid *pid,
 		struct task_struct *task);
@@ -112,10 +111,10 @@ static inline int task_dumpable(struct task_struct *task)
 	return 0;
 }
 
-static inline unsigned name_to_int(struct dentry *dentry)
+static inline unsigned name_to_int(const struct qstr *qstr)
 {
-	const char *name = dentry->d_name.name;
-	int len = dentry->d_name.len;
+	const char *name = qstr->name;
+	int len = qstr->len;
 	unsigned n = 0;
 
 	if (len > 1 && *name == '0')
@@ -178,8 +177,6 @@ extern bool proc_fill_cache(struct file *, struct dir_context *, const char *, i
 /*
  * generic.c
  */
-extern spinlock_t proc_subdir_lock;
-
 extern struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int);
 extern struct dentry *proc_lookup_de(struct proc_dir_entry *, struct inode *,
 				     struct dentry *);
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 39e6ef32f0bd..6df8d0722c97 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -172,7 +172,7 @@ get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
 
 	start = ((unsigned long)pfn_to_page(pfn)) & PAGE_MASK;
 	end = ((unsigned long)pfn_to_page(pfn + nr_pages)) - 1;
-	end = ALIGN(end, PAGE_SIZE);
+	end = PAGE_ALIGN(end);
 	/* overlap check (because we have to align page */
 	list_for_each_entry(tmp, head, list) {
 		if (tmp->type != KCORE_VMEMMAP)
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 71290463a1d3..f92d5dd578a4 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -632,7 +632,7 @@ out:
 	return ret;
 }
 
-static int scan(struct ctl_table_header *head, ctl_table *table,
+static int scan(struct ctl_table_header *head, struct ctl_table *table,
 		unsigned long *pos, struct file *file,
 		struct dir_context *ctx)
 {
diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c
index cb761f010300..15f327bed8c6 100644
--- a/fs/proc/proc_tty.c
+++ b/fs/proc/proc_tty.c
@@ -18,7 +18,7 @@
 /*
  * The /proc/tty directory inodes...
  */
-static struct proc_dir_entry *proc_tty_ldisc, *proc_tty_driver;
+static struct proc_dir_entry *proc_tty_driver;
 
 /*
  * This is the handler for /proc/tty/drivers
@@ -176,7 +176,7 @@ void __init proc_tty_init(void)
 {
 	if (!proc_mkdir("tty", NULL))
 		return;
-	proc_tty_ldisc = proc_mkdir("tty/ldisc", NULL);
+	proc_mkdir("tty/ldisc", NULL);	/* Preserved: it's userspace visible */
 	/*
 	 * /proc/tty/driver/serial reveals the exact character counts for
 	 * serial links which is just too easy to abuse for inferring
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 92c12c243ce3..6296c7626963 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -202,10 +202,10 @@ static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct
 
 static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags)
 {
-	if (!proc_lookup(dir, dentry, flags))
+	if (!proc_pid_lookup(dir, dentry, flags))
 		return NULL;
 	
-	return proc_pid_lookup(dir, dentry, flags);
+	return proc_lookup(dir, dentry, flags);
 }
 
 static int proc_root_readdir(struct file *file, struct dir_context *ctx)
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 382aa890e228..a90d6d354199 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -328,6 +328,82 @@ static inline char *alloc_elfnotes_buf(size_t notes_sz)
  * virtually contiguous user-space in ELF layout.
  */
 #ifdef CONFIG_MMU
+/*
+ * remap_oldmem_pfn_checked - do remap_oldmem_pfn_range replacing all pages
+ * reported as not being ram with the zero page.
+ *
+ * @vma: vm_area_struct describing requested mapping
+ * @from: start remapping from
+ * @pfn: page frame number to start remapping to
+ * @size: remapping size
+ * @prot: protection bits
+ *
+ * Returns zero on success, -EAGAIN on failure.
+ */
+static int remap_oldmem_pfn_checked(struct vm_area_struct *vma,
+				    unsigned long from, unsigned long pfn,
+				    unsigned long size, pgprot_t prot)
+{
+	unsigned long map_size;
+	unsigned long pos_start, pos_end, pos;
+	unsigned long zeropage_pfn = my_zero_pfn(0);
+	size_t len = 0;
+
+	pos_start = pfn;
+	pos_end = pfn + (size >> PAGE_SHIFT);
+
+	for (pos = pos_start; pos < pos_end; ++pos) {
+		if (!pfn_is_ram(pos)) {
+			/*
+			 * We hit a page which is not ram. Remap the continuous
+			 * region between pos_start and pos-1 and replace
+			 * the non-ram page at pos with the zero page.
+			 */
+			if (pos > pos_start) {
+				/* Remap continuous region */
+				map_size = (pos - pos_start) << PAGE_SHIFT;
+				if (remap_oldmem_pfn_range(vma, from + len,
+							   pos_start, map_size,
+							   prot))
+					goto fail;
+				len += map_size;
+			}
+			/* Remap the zero page */
+			if (remap_oldmem_pfn_range(vma, from + len,
+						   zeropage_pfn,
+						   PAGE_SIZE, prot))
+				goto fail;
+			len += PAGE_SIZE;
+			pos_start = pos + 1;
+		}
+	}
+	if (pos > pos_start) {
+		/* Remap the rest */
+		map_size = (pos - pos_start) << PAGE_SHIFT;
+		if (remap_oldmem_pfn_range(vma, from + len, pos_start,
+					   map_size, prot))
+			goto fail;
+	}
+	return 0;
+fail:
+	do_munmap(vma->vm_mm, from, len);
+	return -EAGAIN;
+}
+
+static int vmcore_remap_oldmem_pfn(struct vm_area_struct *vma,
+			    unsigned long from, unsigned long pfn,
+			    unsigned long size, pgprot_t prot)
+{
+	/*
+	 * Check if oldmem_pfn_is_ram was registered to avoid
+	 * looping over all pages without a reason.
+	 */
+	if (oldmem_pfn_is_ram)
+		return remap_oldmem_pfn_checked(vma, from, pfn, size, prot);
+	else
+		return remap_oldmem_pfn_range(vma, from, pfn, size, prot);
+}
+
 static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 {
 	size_t size = vma->vm_end - vma->vm_start;
@@ -387,9 +463,9 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 
 			tsz = min_t(size_t, m->offset + m->size - start, size);
 			paddr = m->paddr + start - m->offset;
-			if (remap_oldmem_pfn_range(vma, vma->vm_start + len,
-						   paddr >> PAGE_SHIFT, tsz,
-						   vma->vm_page_prot))
+			if (vmcore_remap_oldmem_pfn(vma, vma->vm_start + len,
+						    paddr >> PAGE_SHIFT, tsz,
+						    vma->vm_page_prot))
 				goto fail;
 			size -= tsz;
 			start += tsz;
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index 34a1e5aa848c..9d7b9a83699e 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -394,7 +394,7 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size)
 
 	prot = pgprot_noncached(PAGE_KERNEL);
 
-	pages = kmalloc(sizeof(struct page *) * page_count, GFP_KERNEL);
+	pages = kmalloc_array(page_count, sizeof(struct page *), GFP_KERNEL);
 	if (!pages) {
 		pr_err("%s: Failed to allocate array for %u pages\n",
 		       __func__, page_count);
diff --git a/fs/qnx6/Makefile b/fs/qnx6/Makefile
index 9dd06199afc9..5e6bae6fae50 100644
--- a/fs/qnx6/Makefile
+++ b/fs/qnx6/Makefile
@@ -5,3 +5,4 @@
 obj-$(CONFIG_QNX6FS_FS) += qnx6.o
 
 qnx6-objs := inode.o dir.o namei.o super_mmi.o
+ccflags-$(CONFIG_QNX6FS_DEBUG)	+= -DDEBUG
diff --git a/fs/qnx6/dir.c b/fs/qnx6/dir.c
index 15b7d92ed60d..8d64bb5366bf 100644
--- a/fs/qnx6/dir.c
+++ b/fs/qnx6/dir.c
@@ -77,21 +77,20 @@ static int qnx6_dir_longfilename(struct inode *inode,
 	if (de->de_size != 0xff) {
 		/* error - long filename entries always have size 0xff
 		   in direntry */
-		printk(KERN_ERR "qnx6: invalid direntry size (%i).\n",
-				de->de_size);
+		pr_err("invalid direntry size (%i).\n", de->de_size);
 		return 0;
 	}
 	lf = qnx6_longname(s, de, &page);
 	if (IS_ERR(lf)) {
-		printk(KERN_ERR "qnx6:Error reading longname\n");
+		pr_err("Error reading longname\n");
 		return 0;
 	}
 
 	lf_size = fs16_to_cpu(sbi, lf->lf_size);
 
 	if (lf_size > QNX6_LONG_NAME_MAX) {
-		QNX6DEBUG((KERN_INFO "file %s\n", lf->lf_fname));
-		printk(KERN_ERR "qnx6:Filename too long (%i)\n", lf_size);
+		pr_debug("file %s\n", lf->lf_fname);
+		pr_err("Filename too long (%i)\n", lf_size);
 		qnx6_put_page(page);
 		return 0;
 	}
@@ -100,10 +99,10 @@ static int qnx6_dir_longfilename(struct inode *inode,
 	   mmi 3g filesystem does not have that checksum */
 	if (!test_opt(s, MMI_FS) && fs32_to_cpu(sbi, de->de_checksum) !=
 			qnx6_lfile_checksum(lf->lf_fname, lf_size))
-		printk(KERN_INFO "qnx6: long filename checksum error.\n");
+		pr_info("long filename checksum error.\n");
 
-	QNX6DEBUG((KERN_INFO "qnx6_readdir:%.*s inode:%u\n",
-					lf_size, lf->lf_fname, de_inode));
+	pr_debug("qnx6_readdir:%.*s inode:%u\n",
+		 lf_size, lf->lf_fname, de_inode);
 	if (!dir_emit(ctx, lf->lf_fname, lf_size, de_inode, DT_UNKNOWN)) {
 		qnx6_put_page(page);
 		return 0;
@@ -136,7 +135,7 @@ static int qnx6_readdir(struct file *file, struct dir_context *ctx)
 		int i = start;
 
 		if (IS_ERR(page)) {
-			printk(KERN_ERR "qnx6_readdir: read failed\n");
+			pr_err("%s(): read failed\n", __func__);
 			ctx->pos = (n + 1) << PAGE_CACHE_SHIFT;
 			return PTR_ERR(page);
 		}
@@ -159,9 +158,9 @@ static int qnx6_readdir(struct file *file, struct dir_context *ctx)
 					break;
 				}
 			} else {
-				QNX6DEBUG((KERN_INFO "qnx6_readdir:%.*s"
-				   " inode:%u\n", size, de->de_fname,
-							no_inode));
+				pr_debug("%s():%.*s inode:%u\n",
+					 __func__, size, de->de_fname,
+					 no_inode);
 				if (!dir_emit(ctx, de->de_fname, size,
 				      no_inode, DT_UNKNOWN)) {
 					done = true;
@@ -259,8 +258,7 @@ unsigned qnx6_find_entry(int len, struct inode *dir, const char *name,
 					if (ino)
 						goto found;
 				} else
-					printk(KERN_ERR "qnx6: undefined "
-						"filename size in inode.\n");
+					pr_err("undefined filename size in inode.\n");
 			}
 			qnx6_put_page(page);
 		}
diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c
index 65cdaab3ed49..44e73923670d 100644
--- a/fs/qnx6/inode.c
+++ b/fs/qnx6/inode.c
@@ -73,8 +73,8 @@ static int qnx6_get_block(struct inode *inode, sector_t iblock,
 {
 	unsigned phys;
 
-	QNX6DEBUG((KERN_INFO "qnx6: qnx6_get_block inode=[%ld] iblock=[%ld]\n",
-			inode->i_ino, (unsigned long)iblock));
+	pr_debug("qnx6_get_block inode=[%ld] iblock=[%ld]\n",
+		 inode->i_ino, (unsigned long)iblock);
 
 	phys = qnx6_block_map(inode, iblock);
 	if (phys) {
@@ -87,7 +87,7 @@ static int qnx6_get_block(struct inode *inode, sector_t iblock,
 static int qnx6_check_blockptr(__fs32 ptr)
 {
 	if (ptr == ~(__fs32)0) {
-		printk(KERN_ERR "qnx6: hit unused blockpointer.\n");
+		pr_err("hit unused blockpointer.\n");
 		return 0;
 	}
 	return 1;
@@ -127,8 +127,7 @@ static unsigned qnx6_block_map(struct inode *inode, unsigned no)
 	levelptr = no >> bitdelta;
 
 	if (levelptr > QNX6_NO_DIRECT_POINTERS - 1) {
-		printk(KERN_ERR "qnx6:Requested file block number (%u) too big.",
-				no);
+		pr_err("Requested file block number (%u) too big.", no);
 		return 0;
 	}
 
@@ -137,8 +136,7 @@ static unsigned qnx6_block_map(struct inode *inode, unsigned no)
 	for (i = 0; i < depth; i++) {
 		bh = sb_bread(s, block);
 		if (!bh) {
-			printk(KERN_ERR "qnx6:Error reading block (%u)\n",
-					block);
+			pr_err("Error reading block (%u)\n", block);
 			return 0;
 		}
 		bitdelta -= ptrbits;
@@ -207,26 +205,16 @@ void qnx6_superblock_debug(struct qnx6_super_block *sb, struct super_block *s)
 {
 	struct qnx6_sb_info *sbi = QNX6_SB(s);
 
-	QNX6DEBUG((KERN_INFO "magic: %08x\n",
-				fs32_to_cpu(sbi, sb->sb_magic)));
-	QNX6DEBUG((KERN_INFO "checksum: %08x\n",
-				fs32_to_cpu(sbi, sb->sb_checksum)));
-	QNX6DEBUG((KERN_INFO "serial: %llx\n",
-				fs64_to_cpu(sbi, sb->sb_serial)));
-	QNX6DEBUG((KERN_INFO "flags: %08x\n",
-				fs32_to_cpu(sbi, sb->sb_flags)));
-	QNX6DEBUG((KERN_INFO "blocksize: %08x\n",
-				fs32_to_cpu(sbi, sb->sb_blocksize)));
-	QNX6DEBUG((KERN_INFO "num_inodes: %08x\n",
-				fs32_to_cpu(sbi, sb->sb_num_inodes)));
-	QNX6DEBUG((KERN_INFO "free_inodes: %08x\n",
-				fs32_to_cpu(sbi, sb->sb_free_inodes)));
-	QNX6DEBUG((KERN_INFO "num_blocks: %08x\n",
-				fs32_to_cpu(sbi, sb->sb_num_blocks)));
-	QNX6DEBUG((KERN_INFO "free_blocks: %08x\n",
-				fs32_to_cpu(sbi, sb->sb_free_blocks)));
-	QNX6DEBUG((KERN_INFO "inode_levels: %02x\n",
-				sb->Inode.levels));
+	pr_debug("magic: %08x\n", fs32_to_cpu(sbi, sb->sb_magic));
+	pr_debug("checksum: %08x\n", fs32_to_cpu(sbi, sb->sb_checksum));
+	pr_debug("serial: %llx\n", fs64_to_cpu(sbi, sb->sb_serial));
+	pr_debug("flags: %08x\n", fs32_to_cpu(sbi, sb->sb_flags));
+	pr_debug("blocksize: %08x\n", fs32_to_cpu(sbi, sb->sb_blocksize));
+	pr_debug("num_inodes: %08x\n", fs32_to_cpu(sbi, sb->sb_num_inodes));
+	pr_debug("free_inodes: %08x\n", fs32_to_cpu(sbi, sb->sb_free_inodes));
+	pr_debug("num_blocks: %08x\n", fs32_to_cpu(sbi, sb->sb_num_blocks));
+	pr_debug("free_blocks: %08x\n", fs32_to_cpu(sbi, sb->sb_free_blocks));
+	pr_debug("inode_levels: %02x\n", sb->Inode.levels);
 }
 #endif
 
@@ -277,7 +265,7 @@ static struct buffer_head *qnx6_check_first_superblock(struct super_block *s,
 	   start with the first superblock */
 	bh = sb_bread(s, offset);
 	if (!bh) {
-		printk(KERN_ERR "qnx6: unable to read the first superblock\n");
+		pr_err("unable to read the first superblock\n");
 		return NULL;
 	}
 	sb = (struct qnx6_super_block *)bh->b_data;
@@ -285,20 +273,16 @@ static struct buffer_head *qnx6_check_first_superblock(struct super_block *s,
 		sbi->s_bytesex = BYTESEX_BE;
 		if (fs32_to_cpu(sbi, sb->sb_magic) == QNX6_SUPER_MAGIC) {
 			/* we got a big endian fs */
-			QNX6DEBUG((KERN_INFO "qnx6: fs got different"
-					" endianness.\n"));
+			pr_debug("fs got different endianness.\n");
 			return bh;
 		} else
 			sbi->s_bytesex = BYTESEX_LE;
 		if (!silent) {
 			if (offset == 0) {
-				printk(KERN_ERR "qnx6: wrong signature (magic)"
-					" in superblock #1.\n");
+				pr_err("wrong signature (magic) in superblock #1.\n");
 			} else {
-				printk(KERN_INFO "qnx6: wrong signature (magic)"
-					" at position (0x%lx) - will try"
-					" alternative position (0x0000).\n",
-						offset * s->s_blocksize);
+				pr_info("wrong signature (magic) at position (0x%lx) - will try alternative position (0x0000).\n",
+					offset * s->s_blocksize);
 			}
 		}
 		brelse(bh);
@@ -329,13 +313,13 @@ static int qnx6_fill_super(struct super_block *s, void *data, int silent)
 
 	/* Superblock always is 512 Byte long */
 	if (!sb_set_blocksize(s, QNX6_SUPERBLOCK_SIZE)) {
-		printk(KERN_ERR "qnx6: unable to set blocksize\n");
+		pr_err("unable to set blocksize\n");
 		goto outnobh;
 	}
 
 	/* parse the mount-options */
 	if (!qnx6_parse_options((char *) data, s)) {
-		printk(KERN_ERR "qnx6: invalid mount options.\n");
+		pr_err("invalid mount options.\n");
 		goto outnobh;
 	}
 	if (test_opt(s, MMI_FS)) {
@@ -355,7 +339,7 @@ static int qnx6_fill_super(struct super_block *s, void *data, int silent)
 		/* try again without bootblock offset */
 		bh1 = qnx6_check_first_superblock(s, 0, silent);
 		if (!bh1) {
-			printk(KERN_ERR "qnx6: unable to read the first superblock\n");
+			pr_err("unable to read the first superblock\n");
 			goto outnobh;
 		}
 		/* seems that no bootblock at partition start */
@@ -370,13 +354,13 @@ static int qnx6_fill_super(struct super_block *s, void *data, int silent)
 	/* checksum check - start at byte 8 and end at byte 512 */
 	if (fs32_to_cpu(sbi, sb1->sb_checksum) !=
 			crc32_be(0, (char *)(bh1->b_data + 8), 504)) {
-		printk(KERN_ERR "qnx6: superblock #1 checksum error\n");
+		pr_err("superblock #1 checksum error\n");
 		goto out;
 	}
 
 	/* set new blocksize */
 	if (!sb_set_blocksize(s, fs32_to_cpu(sbi, sb1->sb_blocksize))) {
-		printk(KERN_ERR "qnx6: unable to set blocksize\n");
+		pr_err("unable to set blocksize\n");
 		goto out;
 	}
 	/* blocksize invalidates bh - pull it back in */
@@ -398,21 +382,20 @@ static int qnx6_fill_super(struct super_block *s, void *data, int silent)
 	/* next the second superblock */
 	bh2 = sb_bread(s, offset);
 	if (!bh2) {
-		printk(KERN_ERR "qnx6: unable to read the second superblock\n");
+		pr_err("unable to read the second superblock\n");
 		goto out;
 	}
 	sb2 = (struct qnx6_super_block *)bh2->b_data;
 	if (fs32_to_cpu(sbi, sb2->sb_magic) != QNX6_SUPER_MAGIC) {
 		if (!silent)
-			printk(KERN_ERR "qnx6: wrong signature (magic)"
-					" in superblock #2.\n");
+			pr_err("wrong signature (magic) in superblock #2.\n");
 		goto out;
 	}
 
 	/* checksum check - start at byte 8 and end at byte 512 */
 	if (fs32_to_cpu(sbi, sb2->sb_checksum) !=
 				crc32_be(0, (char *)(bh2->b_data + 8), 504)) {
-		printk(KERN_ERR "qnx6: superblock #2 checksum error\n");
+		pr_err("superblock #2 checksum error\n");
 		goto out;
 	}
 
@@ -422,25 +405,24 @@ static int qnx6_fill_super(struct super_block *s, void *data, int silent)
 		sbi->sb_buf = bh1;
 		sbi->sb = (struct qnx6_super_block *)bh1->b_data;
 		brelse(bh2);
-		printk(KERN_INFO "qnx6: superblock #1 active\n");
+		pr_info("superblock #1 active\n");
 	} else {
 		/* superblock #2 active */
 		sbi->sb_buf = bh2;
 		sbi->sb = (struct qnx6_super_block *)bh2->b_data;
 		brelse(bh1);
-		printk(KERN_INFO "qnx6: superblock #2 active\n");
+		pr_info("superblock #2 active\n");
 	}
 mmi_success:
 	/* sanity check - limit maximum indirect pointer levels */
 	if (sb1->Inode.levels > QNX6_PTR_MAX_LEVELS) {
-		printk(KERN_ERR "qnx6: too many inode levels (max %i, sb %i)\n",
-			QNX6_PTR_MAX_LEVELS, sb1->Inode.levels);
+		pr_err("too many inode levels (max %i, sb %i)\n",
+		       QNX6_PTR_MAX_LEVELS, sb1->Inode.levels);
 		goto out;
 	}
 	if (sb1->Longfile.levels > QNX6_PTR_MAX_LEVELS) {
-		printk(KERN_ERR "qnx6: too many longfilename levels"
-				" (max %i, sb %i)\n",
-			QNX6_PTR_MAX_LEVELS, sb1->Longfile.levels);
+		pr_err("too many longfilename levels (max %i, sb %i)\n",
+		       QNX6_PTR_MAX_LEVELS, sb1->Longfile.levels);
 		goto out;
 	}
 	s->s_op = &qnx6_sops;
@@ -460,7 +442,7 @@ mmi_success:
 	/* prefetch root inode */
 	root = qnx6_iget(s, QNX6_ROOT_INO);
 	if (IS_ERR(root)) {
-		printk(KERN_ERR "qnx6: get inode failed\n");
+		pr_err("get inode failed\n");
 		ret = PTR_ERR(root);
 		goto out2;
 	}
@@ -474,7 +456,7 @@ mmi_success:
 	errmsg = qnx6_checkroot(s);
 	if (errmsg != NULL) {
 		if (!silent)
-			printk(KERN_ERR "qnx6: %s\n", errmsg);
+			pr_err("%s\n", errmsg);
 		goto out3;
 	}
 	return 0;
@@ -555,8 +537,7 @@ struct inode *qnx6_iget(struct super_block *sb, unsigned ino)
 	inode->i_mode = 0;
 
 	if (ino == 0) {
-		printk(KERN_ERR "qnx6: bad inode number on dev %s: %u is "
-				"out of range\n",
+		pr_err("bad inode number on dev %s: %u is out of range\n",
 		       sb->s_id, ino);
 		iget_failed(inode);
 		return ERR_PTR(-EIO);
@@ -566,8 +547,8 @@ struct inode *qnx6_iget(struct super_block *sb, unsigned ino)
 	mapping = sbi->inodes->i_mapping;
 	page = read_mapping_page(mapping, n, NULL);
 	if (IS_ERR(page)) {
-		printk(KERN_ERR "qnx6: major problem: unable to read inode from "
-		       "dev %s\n", sb->s_id);
+		pr_err("major problem: unable to read inode from dev %s\n",
+		       sb->s_id);
 		iget_failed(inode);
 		return ERR_CAST(page);
 	}
@@ -689,7 +670,7 @@ static int __init init_qnx6_fs(void)
 		return err;
 	}
 
-	printk(KERN_INFO "QNX6 filesystem 1.0.0 registered.\n");
+	pr_info("QNX6 filesystem 1.0.0 registered.\n");
 	return 0;
 }
 
diff --git a/fs/qnx6/namei.c b/fs/qnx6/namei.c
index 0561326a94f5..6c1a323137dd 100644
--- a/fs/qnx6/namei.c
+++ b/fs/qnx6/namei.c
@@ -29,12 +29,12 @@ struct dentry *qnx6_lookup(struct inode *dir, struct dentry *dentry,
 		foundinode = qnx6_iget(dir->i_sb, ino);
 		qnx6_put_page(page);
 		if (IS_ERR(foundinode)) {
-			QNX6DEBUG((KERN_ERR "qnx6: lookup->iget -> "
-				" error %ld\n", PTR_ERR(foundinode)));
+			pr_debug("lookup->iget ->  error %ld\n",
+				 PTR_ERR(foundinode));
 			return ERR_CAST(foundinode);
 		}
 	} else {
-		QNX6DEBUG((KERN_INFO "qnx6_lookup: not found %s\n", name));
+		pr_debug("%s(): not found %s\n", __func__, name);
 		return NULL;
 	}
 	d_add(dentry, foundinode);
diff --git a/fs/qnx6/qnx6.h b/fs/qnx6/qnx6.h
index b00fcc960d37..d3fb2b698800 100644
--- a/fs/qnx6/qnx6.h
+++ b/fs/qnx6/qnx6.h
@@ -10,6 +10,12 @@
  *
  */
 
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 
@@ -19,12 +25,6 @@ typedef __u64 __bitwise __fs64;
 
 #include <linux/qnx6_fs.h>
 
-#ifdef CONFIG_QNX6FS_DEBUG
-#define QNX6DEBUG(X) printk X
-#else
-#define QNX6DEBUG(X) (void) 0
-#endif
-
 struct qnx6_sb_info {
 	struct buffer_head	*sb_buf;	/* superblock buffer */
 	struct qnx6_super_block	*sb;		/* our superblock */
diff --git a/fs/qnx6/super_mmi.c b/fs/qnx6/super_mmi.c
index 29c32cba62d6..62aaf3e3126a 100644
--- a/fs/qnx6/super_mmi.c
+++ b/fs/qnx6/super_mmi.c
@@ -44,15 +44,14 @@ struct qnx6_super_block *qnx6_mmi_fill_super(struct super_block *s, int silent)
 	   start with the first superblock */
 	bh1 = sb_bread(s, 0);
 	if (!bh1) {
-		printk(KERN_ERR "qnx6: Unable to read first mmi superblock\n");
+		pr_err("Unable to read first mmi superblock\n");
 		return NULL;
 	}
 	sb1 = (struct qnx6_mmi_super_block *)bh1->b_data;
 	sbi = QNX6_SB(s);
 	if (fs32_to_cpu(sbi, sb1->sb_magic) != QNX6_SUPER_MAGIC) {
 		if (!silent) {
-			printk(KERN_ERR "qnx6: wrong signature (magic) in"
-					" superblock #1.\n");
+			pr_err("wrong signature (magic) in superblock #1.\n");
 			goto out;
 		}
 	}
@@ -60,7 +59,7 @@ struct qnx6_super_block *qnx6_mmi_fill_super(struct super_block *s, int silent)
 	/* checksum check - start at byte 8 and end at byte 512 */
 	if (fs32_to_cpu(sbi, sb1->sb_checksum) !=
 				crc32_be(0, (char *)(bh1->b_data + 8), 504)) {
-		printk(KERN_ERR "qnx6: superblock #1 checksum error\n");
+		pr_err("superblock #1 checksum error\n");
 		goto out;
 	}
 
@@ -70,7 +69,7 @@ struct qnx6_super_block *qnx6_mmi_fill_super(struct super_block *s, int silent)
 
 	/* set new blocksize */
 	if (!sb_set_blocksize(s, fs32_to_cpu(sbi, sb1->sb_blocksize))) {
-		printk(KERN_ERR "qnx6: unable to set blocksize\n");
+		pr_err("unable to set blocksize\n");
 		goto out;
 	}
 	/* blocksize invalidates bh - pull it back in */
@@ -83,27 +82,26 @@ struct qnx6_super_block *qnx6_mmi_fill_super(struct super_block *s, int silent)
 	/* read second superblock */
 	bh2 = sb_bread(s, offset);
 	if (!bh2) {
-		printk(KERN_ERR "qnx6: unable to read the second superblock\n");
+		pr_err("unable to read the second superblock\n");
 		goto out;
 	}
 	sb2 = (struct qnx6_mmi_super_block *)bh2->b_data;
 	if (fs32_to_cpu(sbi, sb2->sb_magic) != QNX6_SUPER_MAGIC) {
 		if (!silent)
-			printk(KERN_ERR "qnx6: wrong signature (magic) in"
-					" superblock #2.\n");
+			pr_err("wrong signature (magic) in superblock #2.\n");
 		goto out;
 	}
 
 	/* checksum check - start at byte 8 and end at byte 512 */
 	if (fs32_to_cpu(sbi, sb2->sb_checksum)
 			!= crc32_be(0, (char *)(bh2->b_data + 8), 504)) {
-		printk(KERN_ERR "qnx6: superblock #1 checksum error\n");
+		pr_err("superblock #1 checksum error\n");
 		goto out;
 	}
 
 	qsb = kmalloc(sizeof(*qsb), GFP_KERNEL);
 	if (!qsb) {
-		printk(KERN_ERR "qnx6: unable to allocate memory.\n");
+		pr_err("unable to allocate memory.\n");
 		goto out;
 	}
 
@@ -119,7 +117,7 @@ struct qnx6_super_block *qnx6_mmi_fill_super(struct super_block *s, int silent)
 		sbi->sb_buf = bh1;
 		sbi->sb = (struct qnx6_super_block *)bh1->b_data;
 		brelse(bh2);
-		printk(KERN_INFO "qnx6: superblock #1 active\n");
+		pr_info("superblock #1 active\n");
 	} else {
 		/* superblock #2 active */
 		qnx6_mmi_copy_sb(qsb, sb2);
@@ -131,7 +129,7 @@ struct qnx6_super_block *qnx6_mmi_fill_super(struct super_block *s, int silent)
 		sbi->sb_buf = bh2;
 		sbi->sb = (struct qnx6_super_block *)bh2->b_data;
 		brelse(bh1);
-		printk(KERN_INFO "qnx6: superblock #2 active\n");
+		pr_info("superblock #2 active\n");
 	}
 	kfree(qsb);
 
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index dda012ad4208..bbafbde3471a 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -222,7 +222,7 @@ static unsigned long ramfs_nommu_get_unmapped_area(struct file *file,
 
 	/* gang-find the pages */
 	ret = -ENOMEM;
-	pages = kzalloc(lpages * sizeof(struct page *), GFP_KERNEL);
+	pages = kcalloc(lpages, sizeof(struct page *), GFP_KERNEL);
 	if (!pages)
 		goto out_free;
 
diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c
index d9f5a60dd59b..0a7dc941aaf4 100644
--- a/fs/reiserfs/dir.c
+++ b/fs/reiserfs/dir.c
@@ -9,7 +9,7 @@
 #include <linux/stat.h>
 #include <linux/buffer_head.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 extern const struct reiserfs_key MIN_KEY;
 
diff --git a/fs/reiserfs/do_balan.c b/fs/reiserfs/do_balan.c
index 4d5e5297793f..9c02d96d3a42 100644
--- a/fs/reiserfs/do_balan.c
+++ b/fs/reiserfs/do_balan.c
@@ -10,7 +10,7 @@
  * and using buffers obtained after all above.
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/time.h>
 #include "reiserfs.h"
 #include <linux/buffer_head.h>
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index db9e80ba53a0..751dd3f4346b 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -6,7 +6,7 @@
 #include "reiserfs.h"
 #include "acl.h"
 #include "xattr.h"
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
 #include <linux/writeback.h>
diff --git a/fs/reiserfs/ibalance.c b/fs/reiserfs/ibalance.c
index 73231b1ebdbe..b751eea32e20 100644
--- a/fs/reiserfs/ibalance.c
+++ b/fs/reiserfs/ibalance.c
@@ -2,7 +2,7 @@
  * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/string.h>
 #include <linux/time.h>
 #include "reiserfs.h"
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 63b2b0ec49e6..a7eec9888f10 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -11,7 +11,7 @@
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unaligned.h>
 #include <linux/buffer_head.h>
 #include <linux/mpage.h>
diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c
index 501ed6811a2b..6ec8a30a0911 100644
--- a/fs/reiserfs/ioctl.c
+++ b/fs/reiserfs/ioctl.c
@@ -7,7 +7,7 @@
 #include <linux/mount.h>
 #include "reiserfs.h"
 #include <linux/time.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/pagemap.h>
 #include <linux/compat.h>
 
diff --git a/fs/reiserfs/item_ops.c b/fs/reiserfs/item_ops.c
index cfaee912ee09..aca73dd73906 100644
--- a/fs/reiserfs/item_ops.c
+++ b/fs/reiserfs/item_ops.c
@@ -54,7 +54,7 @@ static void sd_print_item(struct item_head *ih, char *item)
 	} else {
 		struct stat_data *sd = (struct stat_data *)item;
 
-		printk("\t0%-6o | %6Lu | %2u | %d | %s\n", sd_v2_mode(sd),
+		printk("\t0%-6o | %6llu | %2u | %d | %s\n", sd_v2_mode(sd),
 		       (unsigned long long)sd_v2_size(sd), sd_v2_nlink(sd),
 		       sd_v2_rdev(sd), print_time(sd_v2_mtime(sd)));
 	}
@@ -408,7 +408,7 @@ static void direntry_print_item(struct item_head *ih, char *item)
 			namebuf[namelen + 2] = 0;
 		}
 
-		printk("%d:  %-15s%-15d%-15d%-15Ld%-15Ld(%s)\n",
+		printk("%d:  %-15s%-15d%-15d%-15lld%-15lld(%s)\n",
 		       i, namebuf,
 		       deh_dir_id(deh), deh_objectid(deh),
 		       GET_HASH_VALUE(deh_offset(deh)),
diff --git a/fs/reiserfs/lbalance.c b/fs/reiserfs/lbalance.c
index 3a74d15eb814..249594a821e0 100644
--- a/fs/reiserfs/lbalance.c
+++ b/fs/reiserfs/lbalance.c
@@ -2,7 +2,7 @@
  * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/string.h>
 #include <linux/time.h>
 #include "reiserfs.h"
diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c
index c9b47e91baf8..ae1dc841db3a 100644
--- a/fs/reiserfs/prints.c
+++ b/fs/reiserfs/prints.c
@@ -17,7 +17,7 @@ static char off_buf[80];
 static char *reiserfs_cpu_offset(struct cpu_key *key)
 {
 	if (cpu_key_k_type(key) == TYPE_DIRENTRY)
-		sprintf(off_buf, "%Lu(%Lu)",
+		sprintf(off_buf, "%llu(%llu)",
 			(unsigned long long)
 			GET_HASH_VALUE(cpu_key_k_offset(key)),
 			(unsigned long long)
@@ -34,7 +34,7 @@ static char *le_offset(struct reiserfs_key *key)
 
 	version = le_key_version(key);
 	if (le_key_k_type(version, key) == TYPE_DIRENTRY)
-		sprintf(off_buf, "%Lu(%Lu)",
+		sprintf(off_buf, "%llu(%llu)",
 			(unsigned long long)
 			GET_HASH_VALUE(le_key_k_offset(version, key)),
 			(unsigned long long)
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index 02b0b7d0f7d5..621b9f381fe1 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -11,7 +11,7 @@
 #include <linux/module.h>
 #include <linux/time.h>
 #include <linux/seq_file.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "reiserfs.h"
 #include <linux/init.h>
 #include <linux/proc_fs.h>
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index dd44468edc2b..24cbe013240f 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -2006,7 +2006,7 @@ int reiserfs_do_truncate(struct reiserfs_transaction_handle *th,
 					    &s_search_path) == POSITION_FOUND);
 
 	RFALSE(file_size > ROUND_UP(new_file_size),
-	       "PAP-5680: truncate did not finish: new_file_size %Ld, current %Ld, oid %d",
+	       "PAP-5680: truncate did not finish: new_file_size %lld, current %lld, oid %d",
 	       new_file_size, file_size, s_item_key.on_disk_key.k_objectid);
 
 update_and_out:
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index a392cef6acc6..709ea92d716f 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -15,7 +15,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/time.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "reiserfs.h"
 #include "acl.h"
 #include "xattr.h"
@@ -331,7 +331,7 @@ static int finish_unfinished(struct super_block *s)
 			 * not completed truncate found. New size was
 			 * committed together with "save" link
 			 */
-			reiserfs_info(s, "Truncating %k to %Ld ..",
+			reiserfs_info(s, "Truncating %k to %lld ..",
 				      INODE_PKEY(inode), inode->i_size);
 
 			/* don't update modification time */
@@ -1577,7 +1577,7 @@ static int read_super_block(struct super_block *s, int offset)
 	rs = (struct reiserfs_super_block *)bh->b_data;
 	if (sb_blocksize(rs) != s->s_blocksize) {
 		reiserfs_warning(s, "sh-2011", "can't find a reiserfs "
-				 "filesystem on (dev %s, block %Lu, size %lu)",
+				 "filesystem on (dev %s, block %llu, size %lu)",
 				 s->s_id,
 				 (unsigned long long)bh->b_blocknr,
 				 s->s_blocksize);
@@ -2441,8 +2441,7 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type,
 	struct buffer_head tmp_bh, *bh;
 
 	if (!current->journal_info) {
-		printk(KERN_WARNING "reiserfs: Quota write (off=%Lu, len=%Lu)"
-			" cancelled because transaction is not started.\n",
+		printk(KERN_WARNING "reiserfs: Quota write (off=%llu, len=%llu) cancelled because transaction is not started.\n",
 			(unsigned long long)off, (unsigned long long)len);
 		return -EIO;
 	}
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index ca416d099e7d..7c36898af402 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -45,7 +45,7 @@
 #include <linux/xattr.h>
 #include "xattr.h"
 #include "acl.h"
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <net/checksum.h>
 #include <linux/stat.h>
 #include <linux/quotaops.h>
@@ -84,6 +84,7 @@ static int xattr_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 static int xattr_unlink(struct inode *dir, struct dentry *dentry)
 {
 	int error;
+
 	BUG_ON(!mutex_is_locked(&dir->i_mutex));
 
 	mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD);
@@ -98,6 +99,7 @@ static int xattr_unlink(struct inode *dir, struct dentry *dentry)
 static int xattr_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	int error;
+
 	BUG_ON(!mutex_is_locked(&dir->i_mutex));
 
 	mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD);
@@ -117,6 +119,7 @@ static struct dentry *open_xa_root(struct super_block *sb, int flags)
 {
 	struct dentry *privroot = REISERFS_SB(sb)->priv_root;
 	struct dentry *xaroot;
+
 	if (!privroot->d_inode)
 		return ERR_PTR(-ENODATA);
 
@@ -127,6 +130,7 @@ static struct dentry *open_xa_root(struct super_block *sb, int flags)
 		xaroot = ERR_PTR(-ENODATA);
 	else if (!xaroot->d_inode) {
 		int err = -ENODATA;
+
 		if (xattr_may_create(flags))
 			err = xattr_mkdir(privroot->d_inode, xaroot, 0700);
 		if (err) {
@@ -157,6 +161,7 @@ static struct dentry *open_xa_dir(const struct inode *inode, int flags)
 	xadir = lookup_one_len(namebuf, xaroot, strlen(namebuf));
 	if (!IS_ERR(xadir) && !xadir->d_inode) {
 		int err = -ENODATA;
+
 		if (xattr_may_create(flags))
 			err = xattr_mkdir(xaroot->d_inode, xadir, 0700);
 		if (err) {
@@ -188,6 +193,7 @@ fill_with_dentries(void *buf, const char *name, int namelen, loff_t offset,
 {
 	struct reiserfs_dentry_buf *dbuf = buf;
 	struct dentry *dentry;
+
 	WARN_ON_ONCE(!mutex_is_locked(&dbuf->xadir->d_inode->i_mutex));
 
 	if (dbuf->count == ARRAY_SIZE(dbuf->dentries))
@@ -218,6 +224,7 @@ static void
 cleanup_dentry_buf(struct reiserfs_dentry_buf *buf)
 {
 	int i;
+
 	for (i = 0; i < buf->count; i++)
 		if (buf->dentries[i])
 			dput(buf->dentries[i]);
@@ -283,11 +290,13 @@ static int reiserfs_for_each_xattr(struct inode *inode,
 		int blocks = JOURNAL_PER_BALANCE_CNT * 2 + 2 +
 			     4 * REISERFS_QUOTA_TRANS_BLOCKS(inode->i_sb);
 		struct reiserfs_transaction_handle th;
+
 		reiserfs_write_lock(inode->i_sb);
 		err = journal_begin(&th, inode->i_sb, blocks);
 		reiserfs_write_unlock(inode->i_sb);
 		if (!err) {
 			int jerror;
+
 			mutex_lock_nested(&dir->d_parent->d_inode->i_mutex,
 					  I_MUTEX_XATTR);
 			err = action(dir, data);
@@ -340,6 +349,7 @@ static int chown_one_xattr(struct dentry *dentry, void *data)
 int reiserfs_delete_xattrs(struct inode *inode)
 {
 	int err = reiserfs_for_each_xattr(inode, delete_one_xattr, NULL);
+
 	if (err)
 		reiserfs_warning(inode->i_sb, "jdm-20004",
 				 "Couldn't delete all xattrs (%d)\n", err);
@@ -350,6 +360,7 @@ int reiserfs_delete_xattrs(struct inode *inode)
 int reiserfs_chown_xattrs(struct inode *inode, struct iattr *attrs)
 {
 	int err = reiserfs_for_each_xattr(inode, chown_one_xattr, attrs);
+
 	if (err)
 		reiserfs_warning(inode->i_sb, "jdm-20007",
 				 "Couldn't chown all xattrs (%d)\n", err);
@@ -439,6 +450,7 @@ int reiserfs_commit_write(struct file *f, struct page *page,
 static void update_ctime(struct inode *inode)
 {
 	struct timespec now = current_fs_time(inode->i_sb);
+
 	if (inode_unhashed(inode) || !inode->i_nlink ||
 	    timespec_equal(&inode->i_ctime, &now))
 		return;
@@ -514,6 +526,7 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th,
 		size_t chunk;
 		size_t skip = 0;
 		size_t page_offset = (file_pos & (PAGE_CACHE_SIZE - 1));
+
 		if (buffer_size - buffer_pos > PAGE_CACHE_SIZE)
 			chunk = PAGE_CACHE_SIZE;
 		else
@@ -530,6 +543,7 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th,
 
 		if (file_pos == 0) {
 			struct reiserfs_xattr_header *rxh;
+
 			skip = file_pos = sizeof(struct reiserfs_xattr_header);
 			if (chunk + skip > PAGE_CACHE_SIZE)
 				chunk = PAGE_CACHE_SIZE - skip;
@@ -659,6 +673,7 @@ reiserfs_xattr_get(struct inode *inode, const char *name, void *buffer,
 		size_t chunk;
 		char *data;
 		size_t skip = 0;
+
 		if (isize - file_pos > PAGE_CACHE_SIZE)
 			chunk = PAGE_CACHE_SIZE;
 		else
@@ -792,6 +807,7 @@ reiserfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 int reiserfs_removexattr(struct dentry *dentry, const char *name)
 {
 	const struct xattr_handler *handler;
+
 	handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name);
 
 	if (!handler || get_inode_sd_version(dentry->d_inode) == STAT_DATA_V1)
@@ -813,9 +829,11 @@ static int listxattr_filler(void *buf, const char *name, int namelen,
 {
 	struct listxattr_buf *b = (struct listxattr_buf *)buf;
 	size_t size;
+
 	if (name[0] != '.' ||
 	    (namelen != 1 && (name[1] != '.' || namelen != 2))) {
 		const struct xattr_handler *handler;
+
 		handler = find_xattr_handler_prefix(b->dentry->d_sb->s_xattr,
 						    name);
 		if (!handler)	/* Unsupported xattr name */
@@ -885,6 +903,7 @@ static int create_privroot(struct dentry *dentry)
 {
 	int err;
 	struct inode *inode = dentry->d_parent->d_inode;
+
 	WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex));
 
 	err = xattr_mkdir(inode, dentry, 0700);
@@ -1015,6 +1034,7 @@ int reiserfs_xattr_init(struct super_block *s, int mount_flags)
 		mutex_lock(&privroot->d_inode->i_mutex);
 		if (!REISERFS_SB(s)->xattr_root) {
 			struct dentry *dentry;
+
 			dentry = lookup_one_len(XAROOT_NAME, privroot,
 						strlen(XAROOT_NAME));
 			if (!IS_ERR(dentry))
diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index 44503e293790..4b34b9dc03dd 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -9,7 +9,7 @@
 #include <linux/posix_acl_xattr.h>
 #include "xattr.h"
 #include "acl.h"
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static int __reiserfs_set_acl(struct reiserfs_transaction_handle *th,
 			    struct inode *inode, int type,
diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c
index 800a3cef6f62..e7f8939a4cb5 100644
--- a/fs/reiserfs/xattr_security.c
+++ b/fs/reiserfs/xattr_security.c
@@ -6,7 +6,7 @@
 #include <linux/slab.h>
 #include "xattr.h"
 #include <linux/security.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static int
 security_get(struct dentry *dentry, const char *name, void *buffer, size_t size,
diff --git a/fs/reiserfs/xattr_trusted.c b/fs/reiserfs/xattr_trusted.c
index a0035719f66b..5eeb0c48ba46 100644
--- a/fs/reiserfs/xattr_trusted.c
+++ b/fs/reiserfs/xattr_trusted.c
@@ -5,7 +5,7 @@
 #include <linux/pagemap.h>
 #include <linux/xattr.h>
 #include "xattr.h"
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static int
 trusted_get(struct dentry *dentry, const char *name, void *buffer, size_t size,
diff --git a/fs/reiserfs/xattr_user.c b/fs/reiserfs/xattr_user.c
index 8667491ae7c3..e50eab046471 100644
--- a/fs/reiserfs/xattr_user.c
+++ b/fs/reiserfs/xattr_user.c
@@ -4,7 +4,7 @@
 #include <linux/pagemap.h>
 #include <linux/xattr.h>
 #include "xattr.h"
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static int
 user_get(struct dentry *dentry, const char *name, void *buffer, size_t size,
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index ef90e8bca95a..e98dd88197d5 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -56,6 +56,8 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/string.h>
 #include <linux/fs.h>
@@ -380,7 +382,7 @@ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos)
 eio:
 	ret = -EIO;
 error:
-	printk(KERN_ERR "ROMFS: read error for inode 0x%lx\n", pos);
+	pr_err("read error for inode 0x%lx\n", pos);
 	return ERR_PTR(ret);
 }
 
@@ -390,6 +392,7 @@ error:
 static struct inode *romfs_alloc_inode(struct super_block *sb)
 {
 	struct romfs_inode_info *inode;
+
 	inode = kmem_cache_alloc(romfs_inode_cachep, GFP_KERNEL);
 	return inode ? &inode->vfs_inode : NULL;
 }
@@ -400,6 +403,7 @@ static struct inode *romfs_alloc_inode(struct super_block *sb)
 static void romfs_i_callback(struct rcu_head *head)
 {
 	struct inode *inode = container_of(head, struct inode, i_rcu);
+
 	kmem_cache_free(romfs_inode_cachep, ROMFS_I(inode));
 }
 
@@ -507,15 +511,13 @@ static int romfs_fill_super(struct super_block *sb, void *data, int silent)
 	if (rsb->word0 != ROMSB_WORD0 || rsb->word1 != ROMSB_WORD1 ||
 	    img_size < ROMFH_SIZE) {
 		if (!silent)
-			printk(KERN_WARNING "VFS:"
-			       " Can't find a romfs filesystem on dev %s.\n",
+			pr_warn("VFS: Can't find a romfs filesystem on dev %s.\n",
 			       sb->s_id);
 		goto error_rsb_inval;
 	}
 
 	if (romfs_checksum(rsb, min_t(size_t, img_size, 512))) {
-		printk(KERN_ERR "ROMFS: bad initial checksum on dev %s.\n",
-		       sb->s_id);
+		pr_err("bad initial checksum on dev %s.\n", sb->s_id);
 		goto error_rsb_inval;
 	}
 
@@ -523,8 +525,8 @@ static int romfs_fill_super(struct super_block *sb, void *data, int silent)
 
 	len = strnlen(rsb->name, ROMFS_MAXFN);
 	if (!silent)
-		printk(KERN_NOTICE "ROMFS: Mounting image '%*.*s' through %s\n",
-		       (unsigned) len, (unsigned) len, rsb->name, storage);
+		pr_notice("Mounting image '%*.*s' through %s\n",
+			  (unsigned) len, (unsigned) len, rsb->name, storage);
 
 	kfree(rsb);
 	rsb = NULL;
@@ -614,7 +616,7 @@ static int __init init_romfs_fs(void)
 {
 	int ret;
 
-	printk(KERN_INFO "ROMFS MTD (C) 2007 Red Hat, Inc.\n");
+	pr_info("ROMFS MTD (C) 2007 Red Hat, Inc.\n");
 
 	romfs_inode_cachep =
 		kmem_cache_create("romfs_i",
@@ -623,13 +625,12 @@ static int __init init_romfs_fs(void)
 				  romfs_i_init_once);
 
 	if (!romfs_inode_cachep) {
-		printk(KERN_ERR
-		       "ROMFS error: Failed to initialise inode cache\n");
+		pr_err("Failed to initialise inode cache\n");
 		return -ENOMEM;
 	}
 	ret = register_filesystem(&romfs_fs_type);
 	if (ret) {
-		printk(KERN_ERR "ROMFS error: Failed to register filesystem\n");
+		pr_err("Failed to register filesystem\n");
 		goto error_register;
 	}
 	return 0;
diff --git a/fs/ufs/Makefile b/fs/ufs/Makefile
index dd39980437fc..4d0e02b022b3 100644
--- a/fs/ufs/Makefile
+++ b/fs/ufs/Makefile
@@ -6,3 +6,4 @@ obj-$(CONFIG_UFS_FS) += ufs.o
 
 ufs-objs := balloc.o cylinder.o dir.o file.o ialloc.o inode.o \
 	    namei.o super.o symlink.o truncate.o util.o
+ccflags-$(CONFIG_UFS_DEBUG)    += -DDEBUG
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index 61e8a9b021dd..7c580c97990e 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -158,16 +158,16 @@ out:
 
 /**
  * ufs_inode_getfrag() - allocate new fragment(s)
- * @inode - pointer to inode
- * @fragment - number of `fragment' which hold pointer
+ * @inode: pointer to inode
+ * @fragment: number of `fragment' which hold pointer
  *   to new allocated fragment(s)
- * @new_fragment - number of new allocated fragment(s)
- * @required - how many fragment(s) we require
- * @err - we set it if something wrong
- * @phys - pointer to where we save physical number of new allocated fragments,
+ * @new_fragment: number of new allocated fragment(s)
+ * @required: how many fragment(s) we require
+ * @err: we set it if something wrong
+ * @phys: pointer to where we save physical number of new allocated fragments,
  *   NULL if we allocate not data(indirect blocks for example).
- * @new - we set it if we allocate new block
- * @locked_page - for ufs_new_fragments()
+ * @new: we set it if we allocate new block
+ * @locked_page: for ufs_new_fragments()
  */
 static struct buffer_head *
 ufs_inode_getfrag(struct inode *inode, u64 fragment,
@@ -315,16 +315,16 @@ repeat2:
 
 /**
  * ufs_inode_getblock() - allocate new block
- * @inode - pointer to inode
- * @bh - pointer to block which hold "pointer" to new allocated block
- * @fragment - number of `fragment' which hold pointer
+ * @inode: pointer to inode
+ * @bh: pointer to block which hold "pointer" to new allocated block
+ * @fragment: number of `fragment' which hold pointer
  *   to new allocated block
- * @new_fragment - number of new allocated fragment
+ * @new_fragment: number of new allocated fragment
  *  (block will hold this fragment and also uspi->s_fpb-1)
- * @err - see ufs_inode_getfrag()
- * @phys - see ufs_inode_getfrag()
- * @new - see ufs_inode_getfrag()
- * @locked_page - see ufs_inode_getfrag()
+ * @err: see ufs_inode_getfrag()
+ * @phys: see ufs_inode_getfrag()
+ * @new: see ufs_inode_getfrag()
+ * @locked_page: see ufs_inode_getfrag()
  */
 static struct buffer_head *
 ufs_inode_getblock(struct inode *inode, struct buffer_head *bh,
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index b879f1ba3439..da73801301d5 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -65,7 +65,6 @@
  * Evgeniy Dushistov <dushistov@mail.ru>, 2007
  */
 
-
 #include <linux/exportfs.h>
 #include <linux/module.h>
 #include <linux/bitops.h>
@@ -172,73 +171,73 @@ static void ufs_print_super_stuff(struct super_block *sb,
 {
 	u32 magic = fs32_to_cpu(sb, usb3->fs_magic);
 
-	printk("ufs_print_super_stuff\n");
-	printk("  magic:     0x%x\n", magic);
+	pr_debug("ufs_print_super_stuff\n");
+	pr_debug("  magic:     0x%x\n", magic);
 	if (fs32_to_cpu(sb, usb3->fs_magic) == UFS2_MAGIC) {
-		printk("  fs_size:   %llu\n", (unsigned long long)
-		       fs64_to_cpu(sb, usb3->fs_un1.fs_u2.fs_size));
-		printk("  fs_dsize:  %llu\n", (unsigned long long)
-		       fs64_to_cpu(sb, usb3->fs_un1.fs_u2.fs_dsize));
-		printk("  bsize:         %u\n",
-		       fs32_to_cpu(sb, usb1->fs_bsize));
-		printk("  fsize:         %u\n",
-		       fs32_to_cpu(sb, usb1->fs_fsize));
-		printk("  fs_volname:  %s\n", usb2->fs_un.fs_u2.fs_volname);
-		printk("  fs_sblockloc: %llu\n", (unsigned long long)
-		       fs64_to_cpu(sb, usb2->fs_un.fs_u2.fs_sblockloc));
-		printk("  cs_ndir(No of dirs):  %llu\n", (unsigned long long)
-		       fs64_to_cpu(sb, usb2->fs_un.fs_u2.cs_ndir));
-		printk("  cs_nbfree(No of free blocks):  %llu\n",
-		       (unsigned long long)
-		       fs64_to_cpu(sb, usb2->fs_un.fs_u2.cs_nbfree));
-		printk(KERN_INFO"  cs_nifree(Num of free inodes): %llu\n",
-		       (unsigned long long)
-		       fs64_to_cpu(sb, usb3->fs_un1.fs_u2.cs_nifree));
-		printk(KERN_INFO"  cs_nffree(Num of free frags): %llu\n",
-		       (unsigned long long)
-		       fs64_to_cpu(sb, usb3->fs_un1.fs_u2.cs_nffree));
-		printk(KERN_INFO"  fs_maxsymlinklen: %u\n",
-		       fs32_to_cpu(sb, usb3->fs_un2.fs_44.fs_maxsymlinklen));
+		pr_debug("  fs_size:   %llu\n", (unsigned long long)
+			 fs64_to_cpu(sb, usb3->fs_un1.fs_u2.fs_size));
+		pr_debug("  fs_dsize:  %llu\n", (unsigned long long)
+			 fs64_to_cpu(sb, usb3->fs_un1.fs_u2.fs_dsize));
+		pr_debug("  bsize:         %u\n",
+			 fs32_to_cpu(sb, usb1->fs_bsize));
+		pr_debug("  fsize:         %u\n",
+			 fs32_to_cpu(sb, usb1->fs_fsize));
+		pr_debug("  fs_volname:  %s\n", usb2->fs_un.fs_u2.fs_volname);
+		pr_debug("  fs_sblockloc: %llu\n", (unsigned long long)
+			 fs64_to_cpu(sb, usb2->fs_un.fs_u2.fs_sblockloc));
+		pr_debug("  cs_ndir(No of dirs):  %llu\n", (unsigned long long)
+			 fs64_to_cpu(sb, usb2->fs_un.fs_u2.cs_ndir));
+		pr_debug("  cs_nbfree(No of free blocks):  %llu\n",
+			 (unsigned long long)
+			 fs64_to_cpu(sb, usb2->fs_un.fs_u2.cs_nbfree));
+		pr_info("  cs_nifree(Num of free inodes): %llu\n",
+			(unsigned long long)
+			fs64_to_cpu(sb, usb3->fs_un1.fs_u2.cs_nifree));
+		pr_info("  cs_nffree(Num of free frags): %llu\n",
+			(unsigned long long)
+			fs64_to_cpu(sb, usb3->fs_un1.fs_u2.cs_nffree));
+		pr_info("  fs_maxsymlinklen: %u\n",
+			fs32_to_cpu(sb, usb3->fs_un2.fs_44.fs_maxsymlinklen));
 	} else {
-		printk(" sblkno:      %u\n", fs32_to_cpu(sb, usb1->fs_sblkno));
-		printk(" cblkno:      %u\n", fs32_to_cpu(sb, usb1->fs_cblkno));
-		printk(" iblkno:      %u\n", fs32_to_cpu(sb, usb1->fs_iblkno));
-		printk(" dblkno:      %u\n", fs32_to_cpu(sb, usb1->fs_dblkno));
-		printk(" cgoffset:    %u\n",
-		       fs32_to_cpu(sb, usb1->fs_cgoffset));
-		printk(" ~cgmask:     0x%x\n",
-		       ~fs32_to_cpu(sb, usb1->fs_cgmask));
-		printk(" size:        %u\n", fs32_to_cpu(sb, usb1->fs_size));
-		printk(" dsize:       %u\n", fs32_to_cpu(sb, usb1->fs_dsize));
-		printk(" ncg:         %u\n", fs32_to_cpu(sb, usb1->fs_ncg));
-		printk(" bsize:       %u\n", fs32_to_cpu(sb, usb1->fs_bsize));
-		printk(" fsize:       %u\n", fs32_to_cpu(sb, usb1->fs_fsize));
-		printk(" frag:        %u\n", fs32_to_cpu(sb, usb1->fs_frag));
-		printk(" fragshift:   %u\n",
-		       fs32_to_cpu(sb, usb1->fs_fragshift));
-		printk(" ~fmask:      %u\n", ~fs32_to_cpu(sb, usb1->fs_fmask));
-		printk(" fshift:      %u\n", fs32_to_cpu(sb, usb1->fs_fshift));
-		printk(" sbsize:      %u\n", fs32_to_cpu(sb, usb1->fs_sbsize));
-		printk(" spc:         %u\n", fs32_to_cpu(sb, usb1->fs_spc));
-		printk(" cpg:         %u\n", fs32_to_cpu(sb, usb1->fs_cpg));
-		printk(" ipg:         %u\n", fs32_to_cpu(sb, usb1->fs_ipg));
-		printk(" fpg:         %u\n", fs32_to_cpu(sb, usb1->fs_fpg));
-		printk(" csaddr:      %u\n", fs32_to_cpu(sb, usb1->fs_csaddr));
-		printk(" cssize:      %u\n", fs32_to_cpu(sb, usb1->fs_cssize));
-		printk(" cgsize:      %u\n", fs32_to_cpu(sb, usb1->fs_cgsize));
-		printk(" fstodb:      %u\n",
-		       fs32_to_cpu(sb, usb1->fs_fsbtodb));
-		printk(" nrpos:       %u\n", fs32_to_cpu(sb, usb3->fs_nrpos));
-		printk(" ndir         %u\n",
-		       fs32_to_cpu(sb, usb1->fs_cstotal.cs_ndir));
-		printk(" nifree       %u\n",
-		       fs32_to_cpu(sb, usb1->fs_cstotal.cs_nifree));
-		printk(" nbfree       %u\n",
-		       fs32_to_cpu(sb, usb1->fs_cstotal.cs_nbfree));
-		printk(" nffree       %u\n",
-		       fs32_to_cpu(sb, usb1->fs_cstotal.cs_nffree));
+		pr_debug(" sblkno:      %u\n", fs32_to_cpu(sb, usb1->fs_sblkno));
+		pr_debug(" cblkno:      %u\n", fs32_to_cpu(sb, usb1->fs_cblkno));
+		pr_debug(" iblkno:      %u\n", fs32_to_cpu(sb, usb1->fs_iblkno));
+		pr_debug(" dblkno:      %u\n", fs32_to_cpu(sb, usb1->fs_dblkno));
+		pr_debug(" cgoffset:    %u\n",
+			 fs32_to_cpu(sb, usb1->fs_cgoffset));
+		pr_debug(" ~cgmask:     0x%x\n",
+			 ~fs32_to_cpu(sb, usb1->fs_cgmask));
+		pr_debug(" size:        %u\n", fs32_to_cpu(sb, usb1->fs_size));
+		pr_debug(" dsize:       %u\n", fs32_to_cpu(sb, usb1->fs_dsize));
+		pr_debug(" ncg:         %u\n", fs32_to_cpu(sb, usb1->fs_ncg));
+		pr_debug(" bsize:       %u\n", fs32_to_cpu(sb, usb1->fs_bsize));
+		pr_debug(" fsize:       %u\n", fs32_to_cpu(sb, usb1->fs_fsize));
+		pr_debug(" frag:        %u\n", fs32_to_cpu(sb, usb1->fs_frag));
+		pr_debug(" fragshift:   %u\n",
+			 fs32_to_cpu(sb, usb1->fs_fragshift));
+		pr_debug(" ~fmask:      %u\n", ~fs32_to_cpu(sb, usb1->fs_fmask));
+		pr_debug(" fshift:      %u\n", fs32_to_cpu(sb, usb1->fs_fshift));
+		pr_debug(" sbsize:      %u\n", fs32_to_cpu(sb, usb1->fs_sbsize));
+		pr_debug(" spc:         %u\n", fs32_to_cpu(sb, usb1->fs_spc));
+		pr_debug(" cpg:         %u\n", fs32_to_cpu(sb, usb1->fs_cpg));
+		pr_debug(" ipg:         %u\n", fs32_to_cpu(sb, usb1->fs_ipg));
+		pr_debug(" fpg:         %u\n", fs32_to_cpu(sb, usb1->fs_fpg));
+		pr_debug(" csaddr:      %u\n", fs32_to_cpu(sb, usb1->fs_csaddr));
+		pr_debug(" cssize:      %u\n", fs32_to_cpu(sb, usb1->fs_cssize));
+		pr_debug(" cgsize:      %u\n", fs32_to_cpu(sb, usb1->fs_cgsize));
+		pr_debug(" fstodb:      %u\n",
+			 fs32_to_cpu(sb, usb1->fs_fsbtodb));
+		pr_debug(" nrpos:       %u\n", fs32_to_cpu(sb, usb3->fs_nrpos));
+		pr_debug(" ndir         %u\n",
+			 fs32_to_cpu(sb, usb1->fs_cstotal.cs_ndir));
+		pr_debug(" nifree       %u\n",
+			 fs32_to_cpu(sb, usb1->fs_cstotal.cs_nifree));
+		pr_debug(" nbfree       %u\n",
+			 fs32_to_cpu(sb, usb1->fs_cstotal.cs_nbfree));
+		pr_debug(" nffree       %u\n",
+			 fs32_to_cpu(sb, usb1->fs_cstotal.cs_nffree));
 	}
-	printk("\n");
+	pr_debug("\n");
 }
 
 /*
@@ -247,38 +246,38 @@ static void ufs_print_super_stuff(struct super_block *sb,
 static void ufs_print_cylinder_stuff(struct super_block *sb,
 				     struct ufs_cylinder_group *cg)
 {
-	printk("\nufs_print_cylinder_stuff\n");
-	printk("size of ucg: %zu\n", sizeof(struct ufs_cylinder_group));
-	printk("  magic:        %x\n", fs32_to_cpu(sb, cg->cg_magic));
-	printk("  time:         %u\n", fs32_to_cpu(sb, cg->cg_time));
-	printk("  cgx:          %u\n", fs32_to_cpu(sb, cg->cg_cgx));
-	printk("  ncyl:         %u\n", fs16_to_cpu(sb, cg->cg_ncyl));
-	printk("  niblk:        %u\n", fs16_to_cpu(sb, cg->cg_niblk));
-	printk("  ndblk:        %u\n", fs32_to_cpu(sb, cg->cg_ndblk));
-	printk("  cs_ndir:      %u\n", fs32_to_cpu(sb, cg->cg_cs.cs_ndir));
-	printk("  cs_nbfree:    %u\n", fs32_to_cpu(sb, cg->cg_cs.cs_nbfree));
-	printk("  cs_nifree:    %u\n", fs32_to_cpu(sb, cg->cg_cs.cs_nifree));
-	printk("  cs_nffree:    %u\n", fs32_to_cpu(sb, cg->cg_cs.cs_nffree));
-	printk("  rotor:        %u\n", fs32_to_cpu(sb, cg->cg_rotor));
-	printk("  frotor:       %u\n", fs32_to_cpu(sb, cg->cg_frotor));
-	printk("  irotor:       %u\n", fs32_to_cpu(sb, cg->cg_irotor));
-	printk("  frsum:        %u, %u, %u, %u, %u, %u, %u, %u\n",
+	pr_debug("\nufs_print_cylinder_stuff\n");
+	pr_debug("size of ucg: %zu\n", sizeof(struct ufs_cylinder_group));
+	pr_debug("  magic:        %x\n", fs32_to_cpu(sb, cg->cg_magic));
+	pr_debug("  time:         %u\n", fs32_to_cpu(sb, cg->cg_time));
+	pr_debug("  cgx:          %u\n", fs32_to_cpu(sb, cg->cg_cgx));
+	pr_debug("  ncyl:         %u\n", fs16_to_cpu(sb, cg->cg_ncyl));
+	pr_debug("  niblk:        %u\n", fs16_to_cpu(sb, cg->cg_niblk));
+	pr_debug("  ndblk:        %u\n", fs32_to_cpu(sb, cg->cg_ndblk));
+	pr_debug("  cs_ndir:      %u\n", fs32_to_cpu(sb, cg->cg_cs.cs_ndir));
+	pr_debug("  cs_nbfree:    %u\n", fs32_to_cpu(sb, cg->cg_cs.cs_nbfree));
+	pr_debug("  cs_nifree:    %u\n", fs32_to_cpu(sb, cg->cg_cs.cs_nifree));
+	pr_debug("  cs_nffree:    %u\n", fs32_to_cpu(sb, cg->cg_cs.cs_nffree));
+	pr_debug("  rotor:        %u\n", fs32_to_cpu(sb, cg->cg_rotor));
+	pr_debug("  frotor:       %u\n", fs32_to_cpu(sb, cg->cg_frotor));
+	pr_debug("  irotor:       %u\n", fs32_to_cpu(sb, cg->cg_irotor));
+	pr_debug("  frsum:        %u, %u, %u, %u, %u, %u, %u, %u\n",
 	    fs32_to_cpu(sb, cg->cg_frsum[0]), fs32_to_cpu(sb, cg->cg_frsum[1]),
 	    fs32_to_cpu(sb, cg->cg_frsum[2]), fs32_to_cpu(sb, cg->cg_frsum[3]),
 	    fs32_to_cpu(sb, cg->cg_frsum[4]), fs32_to_cpu(sb, cg->cg_frsum[5]),
 	    fs32_to_cpu(sb, cg->cg_frsum[6]), fs32_to_cpu(sb, cg->cg_frsum[7]));
-	printk("  btotoff:      %u\n", fs32_to_cpu(sb, cg->cg_btotoff));
-	printk("  boff:         %u\n", fs32_to_cpu(sb, cg->cg_boff));
-	printk("  iuseoff:      %u\n", fs32_to_cpu(sb, cg->cg_iusedoff));
-	printk("  freeoff:      %u\n", fs32_to_cpu(sb, cg->cg_freeoff));
-	printk("  nextfreeoff:  %u\n", fs32_to_cpu(sb, cg->cg_nextfreeoff));
-	printk("  clustersumoff %u\n",
-	       fs32_to_cpu(sb, cg->cg_u.cg_44.cg_clustersumoff));
-	printk("  clusteroff    %u\n",
-	       fs32_to_cpu(sb, cg->cg_u.cg_44.cg_clusteroff));
-	printk("  nclusterblks  %u\n",
-	       fs32_to_cpu(sb, cg->cg_u.cg_44.cg_nclusterblks));
-	printk("\n");
+	pr_debug("  btotoff:      %u\n", fs32_to_cpu(sb, cg->cg_btotoff));
+	pr_debug("  boff:         %u\n", fs32_to_cpu(sb, cg->cg_boff));
+	pr_debug("  iuseoff:      %u\n", fs32_to_cpu(sb, cg->cg_iusedoff));
+	pr_debug("  freeoff:      %u\n", fs32_to_cpu(sb, cg->cg_freeoff));
+	pr_debug("  nextfreeoff:  %u\n", fs32_to_cpu(sb, cg->cg_nextfreeoff));
+	pr_debug("  clustersumoff %u\n",
+		 fs32_to_cpu(sb, cg->cg_u.cg_44.cg_clustersumoff));
+	pr_debug("  clusteroff    %u\n",
+		 fs32_to_cpu(sb, cg->cg_u.cg_44.cg_clusteroff));
+	pr_debug("  nclusterblks  %u\n",
+		 fs32_to_cpu(sb, cg->cg_u.cg_44.cg_nclusterblks));
+	pr_debug("\n");
 }
 #else
 #  define ufs_print_super_stuff(sb, usb1, usb2, usb3) /**/
@@ -287,13 +286,12 @@ static void ufs_print_cylinder_stuff(struct super_block *sb,
 
 static const struct super_operations ufs_super_ops;
 
-static char error_buf[1024];
-
 void ufs_error (struct super_block * sb, const char * function,
 	const char * fmt, ...)
 {
 	struct ufs_sb_private_info * uspi;
 	struct ufs_super_block_first * usb1;
+	struct va_format vaf;
 	va_list args;
 
 	uspi = UFS_SB(sb)->s_uspi;
@@ -305,20 +303,21 @@ void ufs_error (struct super_block * sb, const char * function,
 		ufs_mark_sb_dirty(sb);
 		sb->s_flags |= MS_RDONLY;
 	}
-	va_start (args, fmt);
-	vsnprintf (error_buf, sizeof(error_buf), fmt, args);
-	va_end (args);
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
 	switch (UFS_SB(sb)->s_mount_opt & UFS_MOUNT_ONERROR) {
 	case UFS_MOUNT_ONERROR_PANIC:
-		panic ("UFS-fs panic (device %s): %s: %s\n", 
-			sb->s_id, function, error_buf);
+		panic("panic (device %s): %s: %pV\n",
+		      sb->s_id, function, &vaf);
 
 	case UFS_MOUNT_ONERROR_LOCK:
 	case UFS_MOUNT_ONERROR_UMOUNT:
 	case UFS_MOUNT_ONERROR_REPAIR:
-		printk (KERN_CRIT "UFS-fs error (device %s): %s: %s\n",
-			sb->s_id, function, error_buf);
-	}		
+		pr_crit("error (device %s): %s: %pV\n",
+			sb->s_id, function, &vaf);
+	}
+	va_end(args);
 }
 
 void ufs_panic (struct super_block * sb, const char * function,
@@ -326,6 +325,7 @@ void ufs_panic (struct super_block * sb, const char * function,
 {
 	struct ufs_sb_private_info * uspi;
 	struct ufs_super_block_first * usb1;
+	struct va_format vaf;
 	va_list args;
 	
 	uspi = UFS_SB(sb)->s_uspi;
@@ -336,24 +336,27 @@ void ufs_panic (struct super_block * sb, const char * function,
 		ubh_mark_buffer_dirty(USPI_UBH(uspi));
 		ufs_mark_sb_dirty(sb);
 	}
-	va_start (args, fmt);
-	vsnprintf (error_buf, sizeof(error_buf), fmt, args);
-	va_end (args);
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
 	sb->s_flags |= MS_RDONLY;
-	printk (KERN_CRIT "UFS-fs panic (device %s): %s: %s\n",
-		sb->s_id, function, error_buf);
+	pr_crit("panic (device %s): %s: %pV\n",
+		sb->s_id, function, &vaf);
+	va_end(args);
 }
 
 void ufs_warning (struct super_block * sb, const char * function,
 	const char * fmt, ...)
 {
+	struct va_format vaf;
 	va_list args;
 
-	va_start (args, fmt);
-	vsnprintf (error_buf, sizeof(error_buf), fmt, args);
-	va_end (args);
-	printk (KERN_WARNING "UFS-fs warning (device %s): %s: %s\n",
-		sb->s_id, function, error_buf);
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	pr_warn("(device %s): %s: %pV\n",
+		sb->s_id, function, &vaf);
+	va_end(args);
 }
 
 enum {
@@ -464,14 +467,12 @@ static int ufs_parse_options (char * options, unsigned * mount_options)
 			ufs_set_opt (*mount_options, ONERROR_UMOUNT);
 			break;
 		case Opt_onerror_repair:
-			printk("UFS-fs: Unable to do repair on error, "
-				"will lock lock instead\n");
+			pr_err("Unable to do repair on error, will lock lock instead\n");
 			ufs_clear_opt (*mount_options, ONERROR);
 			ufs_set_opt (*mount_options, ONERROR_REPAIR);
 			break;
 		default:
-			printk("UFS-fs: Invalid option: \"%s\" "
-					"or missing value\n", p);
+			pr_err("Invalid option: \"%s\" or missing value\n", p);
 			return 0;
 		}
 	}
@@ -788,8 +789,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 
 #ifndef CONFIG_UFS_FS_WRITE
 	if (!(sb->s_flags & MS_RDONLY)) {
-		printk("ufs was compiled with read-only support, "
-		       "can't be mounted as read-write\n");
+		pr_err("ufs was compiled with read-only support, can't be mounted as read-write\n");
 		return -EROFS;
 	}
 #endif
@@ -812,12 +812,12 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_mount_opt = 0;
 	ufs_set_opt (sbi->s_mount_opt, ONERROR_LOCK);
 	if (!ufs_parse_options ((char *) data, &sbi->s_mount_opt)) {
-		printk("wrong mount options\n");
+		pr_err("wrong mount options\n");
 		goto failed;
 	}
 	if (!(sbi->s_mount_opt & UFS_MOUNT_UFSTYPE)) {
 		if (!silent)
-			printk("You didn't specify the type of your ufs filesystem\n\n"
+			pr_err("You didn't specify the type of your ufs filesystem\n\n"
 			"mount -t ufs -o ufstype="
 			"sun|sunx86|44bsd|ufs2|5xbsd|old|hp|nextstep|nextstep-cd|openstep ...\n\n"
 			">>>WARNING<<< Wrong ufstype may corrupt your filesystem, "
@@ -868,7 +868,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 		break;
 
 	case UFS_MOUNT_UFSTYPE_SUNOS:
-		UFSD(("ufstype=sunos\n"))
+		UFSD("ufstype=sunos\n");
 		uspi->s_fsize = block_size = 1024;
 		uspi->s_fmask = ~(1024 - 1);
 		uspi->s_fshift = 10;
@@ -900,7 +900,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 		flags |= UFS_DE_OLD | UFS_UID_OLD | UFS_ST_OLD | UFS_CG_OLD;
 		if (!(sb->s_flags & MS_RDONLY)) {
 			if (!silent)
-				printk(KERN_INFO "ufstype=old is supported read-only\n");
+				pr_info("ufstype=old is supported read-only\n");
 			sb->s_flags |= MS_RDONLY;
 		}
 		break;
@@ -916,7 +916,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 		flags |= UFS_DE_OLD | UFS_UID_OLD | UFS_ST_OLD | UFS_CG_OLD;
 		if (!(sb->s_flags & MS_RDONLY)) {
 			if (!silent)
-				printk(KERN_INFO "ufstype=nextstep is supported read-only\n");
+				pr_info("ufstype=nextstep is supported read-only\n");
 			sb->s_flags |= MS_RDONLY;
 		}
 		break;
@@ -932,7 +932,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 		flags |= UFS_DE_OLD | UFS_UID_OLD | UFS_ST_OLD | UFS_CG_OLD;
 		if (!(sb->s_flags & MS_RDONLY)) {
 			if (!silent)
-				printk(KERN_INFO "ufstype=nextstep-cd is supported read-only\n");
+				pr_info("ufstype=nextstep-cd is supported read-only\n");
 			sb->s_flags |= MS_RDONLY;
 		}
 		break;
@@ -948,7 +948,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 		flags |= UFS_DE_44BSD | UFS_UID_44BSD | UFS_ST_44BSD | UFS_CG_44BSD;
 		if (!(sb->s_flags & MS_RDONLY)) {
 			if (!silent)
-				printk(KERN_INFO "ufstype=openstep is supported read-only\n");
+				pr_info("ufstype=openstep is supported read-only\n");
 			sb->s_flags |= MS_RDONLY;
 		}
 		break;
@@ -963,19 +963,19 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 		flags |= UFS_DE_OLD | UFS_UID_OLD | UFS_ST_OLD | UFS_CG_OLD;
 		if (!(sb->s_flags & MS_RDONLY)) {
 			if (!silent)
-				printk(KERN_INFO "ufstype=hp is supported read-only\n");
+				pr_info("ufstype=hp is supported read-only\n");
 			sb->s_flags |= MS_RDONLY;
  		}
  		break;
 	default:
 		if (!silent)
-			printk("unknown ufstype\n");
+			pr_err("unknown ufstype\n");
 		goto failed;
 	}
 	
 again:	
 	if (!sb_set_blocksize(sb, block_size)) {
-		printk(KERN_ERR "UFS: failed to set blocksize\n");
+		pr_err("failed to set blocksize\n");
 		goto failed;
 	}
 
@@ -1034,7 +1034,7 @@ again:
 		goto again;
 	}
 	if (!silent)
-		printk("ufs_read_super: bad magic number\n");
+		pr_err("%s(): bad magic number\n", __func__);
 	goto failed;
 
 magic_found:
@@ -1048,33 +1048,33 @@ magic_found:
 	uspi->s_fshift = fs32_to_cpu(sb, usb1->fs_fshift);
 
 	if (!is_power_of_2(uspi->s_fsize)) {
-		printk(KERN_ERR "ufs_read_super: fragment size %u is not a power of 2\n",
-			uspi->s_fsize);
-			goto failed;
+		pr_err("%s(): fragment size %u is not a power of 2\n",
+		       __func__, uspi->s_fsize);
+		goto failed;
 	}
 	if (uspi->s_fsize < 512) {
-		printk(KERN_ERR "ufs_read_super: fragment size %u is too small\n",
-			uspi->s_fsize);
+		pr_err("%s(): fragment size %u is too small\n",
+		       __func__, uspi->s_fsize);
 		goto failed;
 	}
 	if (uspi->s_fsize > 4096) {
-		printk(KERN_ERR "ufs_read_super: fragment size %u is too large\n",
-			uspi->s_fsize);
+		pr_err("%s(): fragment size %u is too large\n",
+		       __func__, uspi->s_fsize);
 		goto failed;
 	}
 	if (!is_power_of_2(uspi->s_bsize)) {
-		printk(KERN_ERR "ufs_read_super: block size %u is not a power of 2\n",
-			uspi->s_bsize);
+		pr_err("%s(): block size %u is not a power of 2\n",
+		       __func__, uspi->s_bsize);
 		goto failed;
 	}
 	if (uspi->s_bsize < 4096) {
-		printk(KERN_ERR "ufs_read_super: block size %u is too small\n",
-			uspi->s_bsize);
+		pr_err("%s(): block size %u is too small\n",
+		       __func__, uspi->s_bsize);
 		goto failed;
 	}
 	if (uspi->s_bsize / uspi->s_fsize > 8) {
-		printk(KERN_ERR "ufs_read_super: too many fragments per block (%u)\n",
-			uspi->s_bsize / uspi->s_fsize);
+		pr_err("%s(): too many fragments per block (%u)\n",
+		       __func__, uspi->s_bsize / uspi->s_fsize);
 		goto failed;
 	}
 	if (uspi->s_fsize != block_size || uspi->s_sbsize != super_block_size) {
@@ -1113,20 +1113,21 @@ magic_found:
 			UFSD("fs is DEC OSF/1\n");
 			break;
 		case UFS_FSACTIVE:
-			printk("ufs_read_super: fs is active\n");
+			pr_err("%s(): fs is active\n", __func__);
 			sb->s_flags |= MS_RDONLY;
 			break;
 		case UFS_FSBAD:
-			printk("ufs_read_super: fs is bad\n");
+			pr_err("%s(): fs is bad\n", __func__);
 			sb->s_flags |= MS_RDONLY;
 			break;
 		default:
-			printk("ufs_read_super: can't grok fs_clean 0x%x\n", usb1->fs_clean);
+			pr_err("%s(): can't grok fs_clean 0x%x\n",
+			       __func__, usb1->fs_clean);
 			sb->s_flags |= MS_RDONLY;
 			break;
 		}
 	} else {
-		printk("ufs_read_super: fs needs fsck\n");
+		pr_err("%s(): fs needs fsck\n", __func__);
 		sb->s_flags |= MS_RDONLY;
 	}
 
@@ -1299,7 +1300,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 	if (!(new_mount_opt & UFS_MOUNT_UFSTYPE)) {
 		new_mount_opt |= ufstype;
 	} else if ((new_mount_opt & UFS_MOUNT_UFSTYPE) != ufstype) {
-		printk("ufstype can't be changed during remount\n");
+		pr_err("ufstype can't be changed during remount\n");
 		unlock_ufs(sb);
 		return -EINVAL;
 	}
@@ -1328,8 +1329,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 	 * fs was mounted as ro, remounting rw
 	 */
 #ifndef CONFIG_UFS_FS_WRITE
-		printk("ufs was compiled with read-only support, "
-		"can't be mounted as read-write\n");
+		pr_err("ufs was compiled with read-only support, can't be mounted as read-write\n");
 		unlock_ufs(sb);
 		return -EINVAL;
 #else
@@ -1338,12 +1338,12 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 		    ufstype != UFS_MOUNT_UFSTYPE_44BSD &&
 		    ufstype != UFS_MOUNT_UFSTYPE_SUNx86 &&
 		    ufstype != UFS_MOUNT_UFSTYPE_UFS2) {
-			printk("this ufstype is read-only supported\n");
+			pr_err("this ufstype is read-only supported\n");
 			unlock_ufs(sb);
 			return -EINVAL;
 		}
 		if (!ufs_read_cylinder_structures(sb)) {
-			printk("failed during remounting\n");
+			pr_err("failed during remounting\n");
 			unlock_ufs(sb);
 			return -EPERM;
 		}
diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h
index 343e6fc571e5..2a07396d5f9e 100644
--- a/fs/ufs/ufs.h
+++ b/fs/ufs/ufs.h
@@ -1,6 +1,12 @@
 #ifndef _UFS_UFS_H
 #define _UFS_UFS_H 1
 
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #define UFS_MAX_GROUP_LOADED 8
 #define UFS_CGNO_EMPTY ((unsigned)-1)
 
@@ -71,9 +77,9 @@ struct ufs_inode_info {
  */
 #ifdef CONFIG_UFS_DEBUG
 #	define UFSD(f, a...)	{					\
-		printk ("UFSD (%s, %d): %s:",				\
+		pr_debug("UFSD (%s, %d): %s:",				\
 			__FILE__, __LINE__, __func__);		\
-		printk (f, ## a);					\
+		pr_debug(f, ## a);					\
 	}
 #else
 #	define UFSD(f, a...)	/**/
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/decompress/bunzip2.h b/include/linux/decompress/bunzip2.h
index 115272137a9c..4d683df898e6 100644
--- a/include/linux/decompress/bunzip2.h
+++ b/include/linux/decompress/bunzip2.h
@@ -1,10 +1,10 @@
 #ifndef DECOMPRESS_BUNZIP2_H
 #define DECOMPRESS_BUNZIP2_H
 
-int bunzip2(unsigned char *inbuf, int len,
-	    int(*fill)(void*, unsigned int),
-	    int(*flush)(void*, unsigned int),
+int bunzip2(unsigned char *inbuf, long len,
+	    long (*fill)(void*, unsigned long),
+	    long (*flush)(void*, unsigned long),
 	    unsigned char *output,
-	    int *pos,
+	    long *pos,
 	    void(*error)(char *x));
 #endif
diff --git a/include/linux/decompress/generic.h b/include/linux/decompress/generic.h
index 0c7111a55a1a..1fcfd64b5076 100644
--- a/include/linux/decompress/generic.h
+++ b/include/linux/decompress/generic.h
@@ -1,11 +1,11 @@
 #ifndef DECOMPRESS_GENERIC_H
 #define DECOMPRESS_GENERIC_H
 
-typedef int (*decompress_fn) (unsigned char *inbuf, int len,
-			      int(*fill)(void*, unsigned int),
-			      int(*flush)(void*, unsigned int),
+typedef int (*decompress_fn) (unsigned char *inbuf, long len,
+			      long (*fill)(void*, unsigned long),
+			      long (*flush)(void*, unsigned long),
 			      unsigned char *outbuf,
-			      int *posp,
+			      long *posp,
 			      void(*error)(char *x));
 
 /* inbuf   - input buffer
@@ -33,7 +33,7 @@ typedef int (*decompress_fn) (unsigned char *inbuf, int len,
 
 
 /* Utility routine to detect the decompression method */
-decompress_fn decompress_method(const unsigned char *inbuf, int len,
+decompress_fn decompress_method(const unsigned char *inbuf, long len,
 				const char **name);
 
 #endif
diff --git a/include/linux/decompress/inflate.h b/include/linux/decompress/inflate.h
index 1d0aedef9822..e4f411fdbd24 100644
--- a/include/linux/decompress/inflate.h
+++ b/include/linux/decompress/inflate.h
@@ -1,10 +1,10 @@
 #ifndef LINUX_DECOMPRESS_INFLATE_H
 #define LINUX_DECOMPRESS_INFLATE_H
 
-int gunzip(unsigned char *inbuf, int len,
-	   int(*fill)(void*, unsigned int),
-	   int(*flush)(void*, unsigned int),
+int gunzip(unsigned char *inbuf, long len,
+	   long (*fill)(void*, unsigned long),
+	   long (*flush)(void*, unsigned long),
 	   unsigned char *output,
-	   int *pos,
+	   long *pos,
 	   void(*error_fn)(char *x));
 #endif
diff --git a/include/linux/decompress/unlz4.h b/include/linux/decompress/unlz4.h
index d5b68bf3ec92..3273c2f36496 100644
--- a/include/linux/decompress/unlz4.h
+++ b/include/linux/decompress/unlz4.h
@@ -1,10 +1,10 @@
 #ifndef DECOMPRESS_UNLZ4_H
 #define DECOMPRESS_UNLZ4_H
 
-int unlz4(unsigned char *inbuf, int len,
-	int(*fill)(void*, unsigned int),
-	int(*flush)(void*, unsigned int),
+int unlz4(unsigned char *inbuf, long len,
+	long (*fill)(void*, unsigned long),
+	long (*flush)(void*, unsigned long),
 	unsigned char *output,
-	int *pos,
+	long *pos,
 	void(*error)(char *x));
 #endif
diff --git a/include/linux/decompress/unlzma.h b/include/linux/decompress/unlzma.h
index 7796538f1bf4..8a891a193840 100644
--- a/include/linux/decompress/unlzma.h
+++ b/include/linux/decompress/unlzma.h
@@ -1,11 +1,11 @@
 #ifndef DECOMPRESS_UNLZMA_H
 #define DECOMPRESS_UNLZMA_H
 
-int unlzma(unsigned char *, int,
-	   int(*fill)(void*, unsigned int),
-	   int(*flush)(void*, unsigned int),
+int unlzma(unsigned char *, long,
+	   long (*fill)(void*, unsigned long),
+	   long (*flush)(void*, unsigned long),
 	   unsigned char *output,
-	   int *posp,
+	   long *posp,
 	   void(*error)(char *x)
 	);
 
diff --git a/include/linux/decompress/unlzo.h b/include/linux/decompress/unlzo.h
index 987229752519..af18f95d6570 100644
--- a/include/linux/decompress/unlzo.h
+++ b/include/linux/decompress/unlzo.h
@@ -1,10 +1,10 @@
 #ifndef DECOMPRESS_UNLZO_H
 #define DECOMPRESS_UNLZO_H
 
-int unlzo(unsigned char *inbuf, int len,
-	int(*fill)(void*, unsigned int),
-	int(*flush)(void*, unsigned int),
+int unlzo(unsigned char *inbuf, long len,
+	long (*fill)(void*, unsigned long),
+	long (*flush)(void*, unsigned long),
 	unsigned char *output,
-	int *pos,
+	long *pos,
 	void(*error)(char *x));
 #endif
diff --git a/include/linux/decompress/unxz.h b/include/linux/decompress/unxz.h
index 41728fc6c8a1..f764e2a7201e 100644
--- a/include/linux/decompress/unxz.h
+++ b/include/linux/decompress/unxz.h
@@ -10,10 +10,10 @@
 #ifndef DECOMPRESS_UNXZ_H
 #define DECOMPRESS_UNXZ_H
 
-int unxz(unsigned char *in, int in_size,
-	 int (*fill)(void *dest, unsigned int size),
-	 int (*flush)(void *src, unsigned int size),
-	 unsigned char *out, int *in_used,
+int unxz(unsigned char *in, long in_size,
+	 long (*fill)(void *dest, unsigned long size),
+	 long (*flush)(void *src, unsigned long size),
+	 unsigned char *out, long *in_used,
 	 void (*error)(char *x));
 
 #endif
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/kernel.h b/include/linux/kernel.h
index 75e1ed10bccd..aa2a0cb57f50 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -470,6 +470,7 @@ extern enum system_states {
 #define TAINT_FIRMWARE_WORKAROUND	11
 #define TAINT_OOT_MODULE		12
 #define TAINT_UNSIGNED_MODULE		13
+#define TAINT_SOFTLOCKUP		14
 
 extern const char hex_asc[];
 #define hex_asc_lo(x)	hex_asc[((x) & 0x0f)]
@@ -714,23 +715,8 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 	(void) (&_max1 == &_max2);		\
 	_max1 > _max2 ? _max1 : _max2; })
 
-#define min3(x, y, z) ({			\
-	typeof(x) _min1 = (x);			\
-	typeof(y) _min2 = (y);			\
-	typeof(z) _min3 = (z);			\
-	(void) (&_min1 == &_min2);		\
-	(void) (&_min1 == &_min3);		\
-	_min1 < _min2 ? (_min1 < _min3 ? _min1 : _min3) : \
-		(_min2 < _min3 ? _min2 : _min3); })
-
-#define max3(x, y, z) ({			\
-	typeof(x) _max1 = (x);			\
-	typeof(y) _max2 = (y);			\
-	typeof(z) _max3 = (z);			\
-	(void) (&_max1 == &_max2);		\
-	(void) (&_max1 == &_max3);		\
-	_max1 > _max2 ? (_max1 > _max3 ? _max1 : _max3) : \
-		(_max2 > _max3 ? _max2 : _max3); })
+#define min3(x, y, z) min((typeof(x))min(x, y), z)
+#define max3(x, y, z) max((typeof(x))max(x, y), z)
 
 /**
  * min_not_zero - return the minimum that is _not_ zero, unless both are zero
@@ -745,20 +731,13 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 /**
  * clamp - return a value clamped to a given range with strict typechecking
  * @val: current value
- * @min: minimum allowable value
- * @max: maximum allowable value
+ * @lo: lowest allowable value
+ * @hi: highest allowable value
  *
  * This macro does strict typechecking of min/max to make sure they are of the
  * same type as val.  See the unnecessary pointer comparisons.
  */
-#define clamp(val, min, max) ({			\
-	typeof(val) __val = (val);		\
-	typeof(min) __min = (min);		\
-	typeof(max) __max = (max);		\
-	(void) (&__val == &__min);		\
-	(void) (&__val == &__max);		\
-	__val = __val < __min ? __min: __val;	\
-	__val > __max ? __max: __val; })
+#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
 
 /*
  * ..and if you can't take the strict
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index eb65d29516ca..e0752d204d9e 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -54,39 +54,20 @@ struct mem_cgroup_reclaim_cookie {
 };
 
 #ifdef CONFIG_MEMCG
-/*
- * All "charge" functions with gfp_mask should use GFP_KERNEL or
- * (gfp_mask & GFP_RECLAIM_MASK). In current implementatin, memcg doesn't
- * alloc memory but reclaims memory from all available zones. So, "where I want
- * memory from" bits of gfp_mask has no meaning. So any bits of that field is
- * available but adding a rule is better. charge functions' gfp_mask should
- * be set to GFP_KERNEL or gfp_mask & GFP_RECLAIM_MASK for avoiding ambiguous
- * codes.
- * (Of course, if memcg does memory allocation in future, GFP_KERNEL is sane.)
- */
+int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
+			  gfp_t gfp_mask, struct mem_cgroup **memcgp);
+void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
+			      bool lrucare);
+void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg);
+void mem_cgroup_uncharge(struct page *page);
+void mem_cgroup_uncharge_list(struct list_head *page_list);
 
-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,
-		struct page *page, gfp_t mask, struct mem_cgroup **memcgp);
-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_charge_file(struct page *page, struct mm_struct *mm,
-					gfp_t gfp_mask);
+void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
+			bool lrucare);
 
 struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
 struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
 
-/* For coalescing uncharge for reducing memcg' overhead*/
-extern void mem_cgroup_uncharge_start(void);
-extern void mem_cgroup_uncharge_end(void);
-
-extern void mem_cgroup_uncharge_page(struct page *page);
-extern void mem_cgroup_uncharge_cache_page(struct page *page);
-
 bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
 				  struct mem_cgroup *memcg);
 bool task_in_mem_cgroup(struct task_struct *task,
@@ -113,12 +94,6 @@ bool mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *memcg)
 
 extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
 
-extern void
-mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
-			     struct mem_cgroup **memcgp);
-extern void mem_cgroup_end_migration(struct mem_cgroup *memcg,
-	struct page *oldpage, struct page *newpage, bool migration_ok);
-
 struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
 				   struct mem_cgroup *,
 				   struct mem_cgroup_reclaim_cookie *);
@@ -133,8 +108,6 @@ unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list);
 void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int);
 extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
 					struct task_struct *p);
-extern void mem_cgroup_replace_page_cache(struct page *oldpage,
-					struct page *newpage);
 
 static inline void mem_cgroup_oom_enable(void)
 {
@@ -233,46 +206,36 @@ void mem_cgroup_print_bad_page(struct page *page);
 #else /* CONFIG_MEMCG */
 struct mem_cgroup;
 
-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_charge_file(struct page *page,
-					struct mm_struct *mm, gfp_t gfp_mask)
-{
-	return 0;
-}
-
-static inline int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
-		struct page *page, gfp_t gfp_mask, struct mem_cgroup **memcgp)
+static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
+					gfp_t gfp_mask,
+					struct mem_cgroup **memcgp)
 {
+	*memcgp = NULL;
 	return 0;
 }
 
-static inline void mem_cgroup_commit_charge_swapin(struct page *page,
-					  struct mem_cgroup *memcg)
-{
-}
-
-static inline void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg)
+static inline void mem_cgroup_commit_charge(struct page *page,
+					    struct mem_cgroup *memcg,
+					    bool lrucare)
 {
 }
 
-static inline void mem_cgroup_uncharge_start(void)
+static inline void mem_cgroup_cancel_charge(struct page *page,
+					    struct mem_cgroup *memcg)
 {
 }
 
-static inline void mem_cgroup_uncharge_end(void)
+static inline void mem_cgroup_uncharge(struct page *page)
 {
 }
 
-static inline void mem_cgroup_uncharge_page(struct page *page)
+static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
 {
 }
 
-static inline void mem_cgroup_uncharge_cache_page(struct page *page)
+static inline void mem_cgroup_migrate(struct page *oldpage,
+				      struct page *newpage,
+				      bool lrucare)
 {
 }
 
@@ -311,17 +274,6 @@ static inline struct cgroup_subsys_state
 	return NULL;
 }
 
-static inline void
-mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
-			     struct mem_cgroup **memcgp)
-{
-}
-
-static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg,
-		struct page *oldpage, struct page *newpage, bool migration_ok)
-{
-}
-
 static inline struct mem_cgroup *
 mem_cgroup_iter(struct mem_cgroup *root,
 		struct mem_cgroup *prev,
@@ -417,10 +369,6 @@ static inline
 void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
 {
 }
-static inline void mem_cgroup_replace_page_cache(struct page *oldpage,
-				struct page *newpage)
-{
-}
 #endif /* CONFIG_MEMCG */
 
 #if !defined(CONFIG_MEMCG) || !defined(CONFIG_DEBUG_VM)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 796deac19fcf..6e0b286649f1 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -461,6 +461,7 @@ static inline void mm_init_cpumask(struct mm_struct *mm)
 #ifdef CONFIG_CPUMASK_OFFSTACK
 	mm->cpu_vm_mask_var = &mm->cpumask_allocation;
 #endif
+	cpumask_clear(mm->cpu_vm_mask_var);
 }
 
 /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index 777a524716db..5c831f1eca79 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -3,17 +3,15 @@
 
 enum {
 	/* flags for mem_cgroup */
-	PCG_LOCK,  /* Lock for pc->mem_cgroup and following bits. */
-	PCG_USED, /* this object is in use. */
-	PCG_MIGRATION, /* under page migration */
-	__NR_PCG_FLAGS,
+	PCG_USED = 0x01,	/* This page is charged to a memcg */
+	PCG_MEM = 0x02,		/* This page holds a memory charge */
+	PCG_MEMSW = 0x04,	/* This page holds a memory+swap charge */
 };
 
-#ifndef __GENERATING_BOUNDS_H
-#include <generated/bounds.h>
+struct pglist_data;
 
 #ifdef CONFIG_MEMCG
-#include <linux/bit_spinlock.h>
+struct mem_cgroup;
 
 /*
  * Page Cgroup can be considered as an extended mem_map.
@@ -27,65 +25,30 @@ struct page_cgroup {
 	struct mem_cgroup *mem_cgroup;
 };
 
-void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat);
+extern void pgdat_page_cgroup_init(struct pglist_data *pgdat);
 
 #ifdef CONFIG_SPARSEMEM
-static inline void __init page_cgroup_init_flatmem(void)
+static inline void page_cgroup_init_flatmem(void)
 {
 }
-extern void __init page_cgroup_init(void);
+extern void page_cgroup_init(void);
 #else
-void __init page_cgroup_init_flatmem(void);
-static inline void __init page_cgroup_init(void)
+extern void page_cgroup_init_flatmem(void);
+static inline void page_cgroup_init(void)
 {
 }
 #endif
 
 struct page_cgroup *lookup_page_cgroup(struct page *page);
-struct page *lookup_cgroup_page(struct page_cgroup *pc);
-
-#define TESTPCGFLAG(uname, lname)			\
-static inline int PageCgroup##uname(struct page_cgroup *pc)	\
-	{ return test_bit(PCG_##lname, &pc->flags); }
-
-#define SETPCGFLAG(uname, lname)			\
-static inline void SetPageCgroup##uname(struct page_cgroup *pc)\
-	{ set_bit(PCG_##lname, &pc->flags);  }
-
-#define CLEARPCGFLAG(uname, lname)			\
-static inline void ClearPageCgroup##uname(struct page_cgroup *pc)	\
-	{ clear_bit(PCG_##lname, &pc->flags);  }
-
-#define TESTCLEARPCGFLAG(uname, lname)			\
-static inline int TestClearPageCgroup##uname(struct page_cgroup *pc)	\
-	{ return test_and_clear_bit(PCG_##lname, &pc->flags);  }
-
-TESTPCGFLAG(Used, USED)
-CLEARPCGFLAG(Used, USED)
-SETPCGFLAG(Used, USED)
-
-SETPCGFLAG(Migration, MIGRATION)
-CLEARPCGFLAG(Migration, MIGRATION)
-TESTPCGFLAG(Migration, MIGRATION)
 
-static inline void lock_page_cgroup(struct page_cgroup *pc)
+static inline int PageCgroupUsed(struct page_cgroup *pc)
 {
-	/*
-	 * Don't take this lock in IRQ context.
-	 * This lock is for pc->mem_cgroup, USED, MIGRATION
-	 */
-	bit_spin_lock(PCG_LOCK, &pc->flags);
+	return !!(pc->flags & PCG_USED);
 }
-
-static inline void unlock_page_cgroup(struct page_cgroup *pc)
-{
-	bit_spin_unlock(PCG_LOCK, &pc->flags);
-}
-
-#else /* CONFIG_MEMCG */
+#else /* !CONFIG_MEMCG */
 struct page_cgroup;
 
-static inline void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
+static inline void pgdat_page_cgroup_init(struct pglist_data *pgdat)
 {
 }
 
@@ -98,10 +61,9 @@ static inline void page_cgroup_init(void)
 {
 }
 
-static inline void __init page_cgroup_init_flatmem(void)
+static inline void page_cgroup_init_flatmem(void)
 {
 }
-
 #endif /* CONFIG_MEMCG */
 
 #include <linux/swap.h>
@@ -140,6 +102,4 @@ static inline void swap_cgroup_swapoff(int type)
 
 #endif /* CONFIG_MEMCG_SWAP */
 
-#endif /* !__GENERATING_BOUNDS_H */
-
 #endif /* __LINUX_PAGE_CGROUP_H */
diff --git a/include/linux/rio_drv.h b/include/linux/rio_drv.h
index 5059994fe297..9fc2f213e74f 100644
--- a/include/linux/rio_drv.h
+++ b/include/linux/rio_drv.h
@@ -384,11 +384,16 @@ void rio_dev_put(struct rio_dev *);
 
 #ifdef CONFIG_RAPIDIO_DMA_ENGINE
 extern struct dma_chan *rio_request_dma(struct rio_dev *rdev);
+extern struct dma_chan *rio_request_mport_dma(struct rio_mport *mport);
 extern void rio_release_dma(struct dma_chan *dchan);
 extern struct dma_async_tx_descriptor *rio_dma_prep_slave_sg(
 		struct rio_dev *rdev, struct dma_chan *dchan,
 		struct rio_dma_data *data,
 		enum dma_transfer_direction direction, unsigned long flags);
+extern struct dma_async_tx_descriptor *rio_dma_prep_xfer(
+		struct dma_chan *dchan,	u16 destid,
+		struct rio_dma_data *data,
+		enum dma_transfer_direction direction, unsigned long flags);
 #endif
 
 /**
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index f4ec8bbcb372..ed8f9e70df9b 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -136,7 +136,7 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf,
 static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents,
 			    struct scatterlist *sgl)
 {
-#ifndef ARCH_HAS_SG_CHAIN
+#ifndef CONFIG_ARCH_HAS_SG_CHAIN
 	BUG();
 #endif
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a555f375bdb5..857ba40426ba 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -33,6 +33,7 @@ struct sched_param {
 
 #include <linux/smp.h>
 #include <linux/sem.h>
+#include <linux/shm.h>
 #include <linux/signal.h>
 #include <linux/compiler.h>
 #include <linux/completion.h>
@@ -1385,6 +1386,7 @@ struct task_struct {
 #ifdef CONFIG_SYSVIPC
 /* ipc stuff */
 	struct sysv_sem sysvsem;
+	struct sysv_shm sysvshm;
 #endif
 #ifdef CONFIG_DETECT_HUNG_TASK
 /* hung task detection */
@@ -1628,12 +1630,6 @@ struct task_struct {
 	unsigned long trace_recursion;
 #endif /* CONFIG_TRACING */
 #ifdef CONFIG_MEMCG /* memcg uses this to do batch job */
-	struct memcg_batch_info {
-		int do_batch;	/* incremented when batch uncharge started */
-		struct mem_cgroup *memcg; /* target memcg of uncharge */
-		unsigned long nr_pages;	/* uncharged usage */
-		unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
-	} memcg_batch;
 	unsigned int memcg_kmem_skip_account;
 	struct memcg_oom_info {
 		struct mem_cgroup *memcg;
@@ -2969,15 +2965,10 @@ static inline void inc_syscw(struct task_struct *tsk)
 
 #ifdef CONFIG_MEMCG
 extern void mm_update_next_owner(struct mm_struct *mm);
-extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);
 #else
 static inline void mm_update_next_owner(struct mm_struct *mm)
 {
 }
-
-static inline void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
-{
-}
 #endif /* CONFIG_MEMCG */
 
 static inline unsigned long task_rlimit(const struct task_struct *tsk,
diff --git a/include/linux/shm.h b/include/linux/shm.h
index 57d77709fbe2..6fb801686ad6 100644
--- a/include/linux/shm.h
+++ b/include/linux/shm.h
@@ -1,6 +1,7 @@
 #ifndef _LINUX_SHM_H_
 #define _LINUX_SHM_H_
 
+#include <linux/list.h>
 #include <asm/page.h>
 #include <uapi/linux/shm.h>
 #include <asm/shmparam.h>
@@ -20,6 +21,7 @@ struct shmid_kernel /* private to the kernel */
 
 	/* The task created the shm object.  NULL if the task is dead. */
 	struct task_struct	*shm_creator;
+	struct list_head	shm_clist;	/* list by creator */
 };
 
 /* shm_mode upper byte flags */
@@ -44,11 +46,20 @@ struct shmid_kernel /* private to the kernel */
 #define SHM_HUGE_1GB    (30 << SHM_HUGE_SHIFT)
 
 #ifdef CONFIG_SYSVIPC
+struct sysv_shm {
+	struct list_head shm_clist;
+};
+
 long do_shmat(int shmid, char __user *shmaddr, int shmflg, unsigned long *addr,
 	      unsigned long shmlba);
-extern int is_file_shm_hugepages(struct file *file);
-extern void exit_shm(struct task_struct *task);
+int is_file_shm_hugepages(struct file *file);
+void exit_shm(struct task_struct *task);
+#define shm_init_task(task) INIT_LIST_HEAD(&(task)->sysvshm.shm_clist)
 #else
+struct sysv_shm {
+	/* empty */
+};
+
 static inline long do_shmat(int shmid, char __user *shmaddr,
 			    int shmflg, unsigned long *addr,
 			    unsigned long shmlba)
@@ -62,6 +73,9 @@ static inline int is_file_shm_hugepages(struct file *file)
 static inline void exit_shm(struct task_struct *task)
 {
 }
+static inline void shm_init_task(struct task_struct *task)
+{
+}
 #endif
 
 #endif /* _LINUX_SHM_H_ */
diff --git a/include/linux/string.h b/include/linux/string.h
index d36977e029af..2663afcc0861 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -117,6 +117,7 @@ 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 1eb64043c076..1b72060f093a 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -320,6 +320,9 @@ extern void swap_setup(void);
 
 extern void add_page_to_unevictable_list(struct page *page);
 
+extern void lru_cache_add_active_or_unevictable(struct page *page,
+						struct vm_area_struct *vma);
+
 /* linux/mm/vmscan.c */
 extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 					gfp_t gfp_mask, nodemask_t *mask);
@@ -378,9 +381,13 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 }
 #endif
 #ifdef CONFIG_MEMCG_SWAP
-extern void mem_cgroup_uncharge_swap(swp_entry_t ent);
+extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry);
+extern void mem_cgroup_uncharge_swap(swp_entry_t entry);
 #else
-static inline void mem_cgroup_uncharge_swap(swp_entry_t ent)
+static inline void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
+{
+}
+static inline void mem_cgroup_uncharge_swap(swp_entry_t entry)
 {
 }
 #endif
@@ -440,7 +447,7 @@ extern void swap_shmem_alloc(swp_entry_t);
 extern int swap_duplicate(swp_entry_t);
 extern int swapcache_prepare(swp_entry_t);
 extern void swap_free(swp_entry_t);
-extern void swapcache_free(swp_entry_t, struct page *page);
+extern void swapcache_free(swp_entry_t);
 extern int free_swap_and_cache(swp_entry_t);
 extern int swap_type_of(dev_t, sector_t, struct block_device **);
 extern unsigned int count_swap_pages(int, int);
@@ -504,7 +511,7 @@ static inline void swap_free(swp_entry_t swp)
 {
 }
 
-static inline void swapcache_free(swp_entry_t swp, struct page *page)
+static inline void swapcache_free(swp_entry_t swp)
 {
 }
 
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 14a8ff2de11e..b7361f831226 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -34,8 +34,6 @@ struct ctl_table_root;
 struct ctl_table_header;
 struct ctl_dir;
 
-typedef struct ctl_table ctl_table;
-
 typedef int proc_handler (struct ctl_table *ctl, int write,
 			  void __user *buffer, size_t *lenp, loff_t *ppos);
 
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 4836ba3c1cd8..e95372654f09 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -57,9 +57,9 @@ static inline void put_user_ns(struct user_namespace *ns)
 }
 
 struct seq_operations;
-extern struct seq_operations proc_uid_seq_operations;
-extern struct seq_operations proc_gid_seq_operations;
-extern struct seq_operations proc_projid_seq_operations;
+extern const struct seq_operations proc_uid_seq_operations;
+extern const struct seq_operations proc_gid_seq_operations;
+extern const struct seq_operations proc_projid_seq_operations;
 extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *);
diff --git a/include/linux/zlib.h b/include/linux/zlib.h
index 197abb2a54c5..92dbbd3f6c75 100644
--- a/include/linux/zlib.h
+++ b/include/linux/zlib.h
@@ -83,11 +83,11 @@ struct internal_state;
 
 typedef struct z_stream_s {
     const Byte *next_in;   /* next input byte */
-    uInt     avail_in;  /* number of bytes available at next_in */
+	uLong avail_in;  /* number of bytes available at next_in */
     uLong    total_in;  /* total nb of input bytes read so far */
 
     Byte    *next_out;  /* next output byte should be put there */
-    uInt     avail_out; /* remaining free space at next_out */
+	uLong avail_out; /* remaining free space at next_out */
     uLong    total_out; /* total nb of bytes output so far */
 
     char     *msg;      /* last error message, NULL if no error */
diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h
index e6df23cae7be..261e708010da 100644
--- a/include/scsi/scsi.h
+++ b/include/scsi/scsi.h
@@ -31,7 +31,7 @@ enum scsi_timeouts {
  * Like SCSI_MAX_SG_SEGMENTS, but for archs that have sg chaining. This limit
  * is totally arbitrary, a setting of 2048 will get you at least 8mb ios.
  */
-#ifdef ARCH_HAS_SG_CHAIN
+#ifdef CONFIG_ARCH_HAS_SG_CHAIN
 #define SCSI_MAX_SG_CHAIN_SEGMENTS	2048
 #else
 #define SCSI_MAX_SG_CHAIN_SEGMENTS	SCSI_MAX_SG_SEGMENTS
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 82f22885c87e..b6237c31b0e2 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -539,12 +539,6 @@ void __init prepare_namespace(void)
 {
 	int is_floppy;
 
-	if (root_delay) {
-		printk(KERN_INFO "Waiting %d sec before mounting root device...\n",
-		       root_delay);
-		ssleep(root_delay);
-	}
-
 	/*
 	 * wait for the known devices to complete their probing
 	 *
@@ -571,6 +565,12 @@ void __init prepare_namespace(void)
 	if (initrd_load())
 		goto out;
 
+	if (root_delay) {
+		pr_info("Waiting %d sec before mounting root device...\n",
+			root_delay);
+		ssleep(root_delay);
+	}
+
 	/* wait for any asynchronous scanning to complete */
 	if ((ROOT_DEV == 0) && root_wait) {
 		printk(KERN_INFO "Waiting for root device %s...\n",
diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c
index a8227022e3a0..e5d059e8aa11 100644
--- a/init/do_mounts_rd.c
+++ b/init/do_mounts_rd.c
@@ -311,9 +311,9 @@ static int exit_code;
 static int decompress_error;
 static int crd_infd, crd_outfd;
 
-static int __init compr_fill(void *buf, unsigned int len)
+static long __init compr_fill(void *buf, unsigned long len)
 {
-	int r = sys_read(crd_infd, buf, len);
+	long r = sys_read(crd_infd, buf, len);
 	if (r < 0)
 		printk(KERN_ERR "RAMDISK: error while reading compressed data");
 	else if (r == 0)
@@ -321,13 +321,13 @@ static int __init compr_fill(void *buf, unsigned int len)
 	return r;
 }
 
-static int __init compr_flush(void *window, unsigned int outcnt)
+static long __init compr_flush(void *window, unsigned long outcnt)
 {
-	int written = sys_write(crd_outfd, window, outcnt);
+	long written = sys_write(crd_outfd, window, outcnt);
 	if (written != outcnt) {
 		if (decompress_error == 0)
 			printk(KERN_ERR
-			       "RAMDISK: incomplete write (%d != %d)\n",
+			       "RAMDISK: incomplete write (%ld != %ld)\n",
 			       written, outcnt);
 		decompress_error = 1;
 		return -1;
diff --git a/init/initramfs.c b/init/initramfs.c
index a8497fab1c3d..bece48c3461e 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -19,6 +19,29 @@
 #include <linux/syscalls.h>
 #include <linux/utime.h>
 
+static ssize_t __init xwrite(int fd, const char *p, size_t count)
+{
+	ssize_t out = 0;
+
+	/* sys_write only can write MAX_RW_COUNT aka 2G-4K bytes at most */
+	while (count) {
+		ssize_t rv = sys_write(fd, p, count);
+
+		if (rv < 0) {
+			if (rv == -EINTR || rv == -EAGAIN)
+				continue;
+			return out ? out : rv;
+		} else if (rv == 0)
+			break;
+
+		p += rv;
+		out += rv;
+		count -= rv;
+	}
+
+	return out;
+}
+
 static __initdata char *message;
 static void __init error(char *x)
 {
@@ -174,7 +197,7 @@ static __initdata enum state {
 } state, next_state;
 
 static __initdata char *victim;
-static __initdata unsigned count;
+static unsigned long count __initdata;
 static __initdata loff_t this_header, next_header;
 
 static inline void __init eat(unsigned n)
@@ -186,7 +209,7 @@ static inline void __init eat(unsigned n)
 
 static __initdata char *vcollected;
 static __initdata char *collected;
-static __initdata int remains;
+static long remains __initdata;
 static __initdata char *collect;
 
 static void __init read_into(char *buf, unsigned size, enum state next)
@@ -213,7 +236,7 @@ static int __init do_start(void)
 
 static int __init do_collect(void)
 {
-	unsigned n = remains;
+	unsigned long n = remains;
 	if (count < n)
 		n = count;
 	memcpy(collect, victim, n);
@@ -346,7 +369,8 @@ static int __init do_name(void)
 static int __init do_copy(void)
 {
 	if (count >= body_len) {
-		sys_write(wfd, victim, body_len);
+		if (xwrite(wfd, victim, body_len) != body_len)
+			error("write error");
 		sys_close(wfd);
 		do_utime(vcollected, mtime);
 		kfree(vcollected);
@@ -354,7 +378,8 @@ static int __init do_copy(void)
 		state = SkipIt;
 		return 0;
 	} else {
-		sys_write(wfd, victim, count);
+		if (xwrite(wfd, victim, count) != count)
+			error("write error");
 		body_len -= count;
 		eat(count);
 		return 1;
@@ -384,7 +409,7 @@ static __initdata int (*actions[])(void) = {
 	[Reset]		= do_reset,
 };
 
-static int __init write_buffer(char *buf, unsigned len)
+static long __init write_buffer(char *buf, unsigned long len)
 {
 	count = len;
 	victim = buf;
@@ -394,11 +419,11 @@ static int __init write_buffer(char *buf, unsigned len)
 	return len - count;
 }
 
-static int __init flush_buffer(void *bufv, unsigned len)
+static long __init flush_buffer(void *bufv, unsigned long len)
 {
 	char *buf = (char *) bufv;
-	int written;
-	int origLen = len;
+	long written;
+	long origLen = len;
 	if (message)
 		return -1;
 	while ((written = write_buffer(buf, len)) < len && !message) {
@@ -417,13 +442,13 @@ static int __init flush_buffer(void *bufv, unsigned len)
 	return origLen;
 }
 
-static unsigned my_inptr;   /* index of next byte to be processed in inbuf */
+static unsigned long my_inptr; /* index of next byte to be processed in inbuf */
 
 #include <linux/decompress/generic.h>
 
-static char * __init unpack_to_rootfs(char *buf, unsigned len)
+static char * __init unpack_to_rootfs(char *buf, unsigned long len)
 {
-	int written, res;
+	long written;
 	decompress_fn decompress;
 	const char *compress_name;
 	static __initdata char msg_buf[64];
@@ -457,7 +482,7 @@ static char * __init unpack_to_rootfs(char *buf, unsigned len)
 		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,
+			int res = decompress(buf, len, NULL, flush_buffer, NULL,
 				   &my_inptr, error);
 			if (res)
 				error("decompressor failed");
@@ -603,8 +628,13 @@ static int __init populate_rootfs(void)
 		fd = sys_open("/initrd.image",
 			      O_WRONLY|O_CREAT, 0700);
 		if (fd >= 0) {
-			sys_write(fd, (char *)initrd_start,
-					initrd_end - initrd_start);
+			ssize_t written = xwrite(fd, (char *)initrd_start,
+						initrd_end - initrd_start);
+
+			if (written != initrd_end - initrd_start)
+				pr_err("/initrd.image: incomplete write (%zd != %ld)\n",
+				       written, initrd_end - initrd_start);
+
 			sys_close(fd);
 			free_initrd();
 		}
diff --git a/ipc/shm.c b/ipc/shm.c
index 89fc354156cb..7fc9f9f3a26b 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -178,6 +178,7 @@ static void shm_rcu_free(struct rcu_head *head)
 
 static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
 {
+	list_del(&s->shm_clist);
 	ipc_rmid(&shm_ids(ns), &s->shm_perm);
 }
 
@@ -268,37 +269,6 @@ static void shm_close(struct vm_area_struct *vma)
 }
 
 /* Called with ns->shm_ids(ns).rwsem locked */
-static int shm_try_destroy_current(int id, void *p, void *data)
-{
-	struct ipc_namespace *ns = data;
-	struct kern_ipc_perm *ipcp = p;
-	struct shmid_kernel *shp = container_of(ipcp, struct shmid_kernel, shm_perm);
-
-	if (shp->shm_creator != current)
-		return 0;
-
-	/*
-	 * Mark it as orphaned to destroy the segment when
-	 * kernel.shm_rmid_forced is changed.
-	 * It is noop if the following shm_may_destroy() returns true.
-	 */
-	shp->shm_creator = NULL;
-
-	/*
-	 * Don't even try to destroy it.  If shm_rmid_forced=0 and IPC_RMID
-	 * is not set, it shouldn't be deleted here.
-	 */
-	if (!ns->shm_rmid_forced)
-		return 0;
-
-	if (shm_may_destroy(ns, shp)) {
-		shm_lock_by_ptr(shp);
-		shm_destroy(ns, shp);
-	}
-	return 0;
-}
-
-/* Called with ns->shm_ids(ns).rwsem locked */
 static int shm_try_destroy_orphaned(int id, void *p, void *data)
 {
 	struct ipc_namespace *ns = data;
@@ -329,18 +299,50 @@ void shm_destroy_orphaned(struct ipc_namespace *ns)
 	up_write(&shm_ids(ns).rwsem);
 }
 
-
+/* Locking assumes this will only be called with task == current */
 void exit_shm(struct task_struct *task)
 {
 	struct ipc_namespace *ns = task->nsproxy->ipc_ns;
+	struct shmid_kernel *shp, *n;
 
-	if (shm_ids(ns).in_use == 0)
+	if (list_empty(&task->sysvshm.shm_clist))
 		return;
 
-	/* Destroy all already created segments, but not mapped yet */
+	/*
+	 * If kernel.shm_rmid_forced is not set then only keep track of
+	 * which shmids are orphaned, so that a later set of the sysctl
+	 * can clean them up.
+	 */
+	if (!ns->shm_rmid_forced) {
+		down_read(&shm_ids(ns).rwsem);
+		list_for_each_entry(shp, &task->sysvshm.shm_clist, shm_clist)
+			shp->shm_creator = NULL;
+		/*
+		 * Only under read lock but we are only called on current
+		 * so no entry on the list will be shared.
+		 */
+		list_del(&task->sysvshm.shm_clist);
+		up_read(&shm_ids(ns).rwsem);
+		return;
+	}
+
+	/*
+	 * Destroy all already created segments, that were not yet mapped,
+	 * and mark any mapped as orphan to cover the sysctl toggling.
+	 * Destroy is skipped if shm_may_destroy() returns false.
+	 */
 	down_write(&shm_ids(ns).rwsem);
-	if (shm_ids(ns).in_use)
-		idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_current, ns);
+	list_for_each_entry_safe(shp, n, &task->sysvshm.shm_clist, shm_clist) {
+		shp->shm_creator = NULL;
+
+		if (shm_may_destroy(ns, shp)) {
+			shm_lock_by_ptr(shp);
+			shm_destroy(ns, shp);
+		}
+	}
+
+	/* Remove the list head from any segments still attached. */
+	list_del(&task->sysvshm.shm_clist);
 	up_write(&shm_ids(ns).rwsem);
 }
 
@@ -561,6 +563,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	shp->shm_nattch = 0;
 	shp->shm_file = file;
 	shp->shm_creator = current;
+	list_add(&shp->shm_clist, &current->sysvshm.shm_clist);
 
 	/*
 	 * shmid gets reported as "inode#" in /proc/pid/maps.
diff --git a/kernel/bounds.c b/kernel/bounds.c
index 9fd4246b04b8..e1d1d1952bfa 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -9,7 +9,6 @@
 #include <linux/page-flags.h>
 #include <linux/mmzone.h>
 #include <linux/kbuild.h>
-#include <linux/page_cgroup.h>
 #include <linux/log2.h>
 #include <linux/spinlock_types.h>
 
@@ -18,7 +17,6 @@ void foo(void)
 	/* The enum constants to put into include/generated/bounds.h */
 	DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS);
 	DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES);
-	DEFINE(NR_PCG_FLAGS, __NR_PCG_FLAGS);
 #ifdef CONFIG_SMP
 	DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS));
 #endif
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 6f3254e8c137..1d0af8a2c646 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -167,6 +167,11 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 	/* For mmu_notifiers */
 	const unsigned long mmun_start = addr;
 	const unsigned long mmun_end   = addr + PAGE_SIZE;
+	struct mem_cgroup *memcg;
+
+	err = mem_cgroup_try_charge(kpage, vma->vm_mm, GFP_KERNEL, &memcg);
+	if (err)
+		return err;
 
 	/* For try_to_free_swap() and munlock_vma_page() below */
 	lock_page(page);
@@ -179,6 +184,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 
 	get_page(kpage);
 	page_add_new_anon_rmap(kpage, vma, addr);
+	mem_cgroup_commit_charge(kpage, memcg, false);
+	lru_cache_add_active_or_unevictable(kpage, vma);
 
 	if (!PageAnon(page)) {
 		dec_mm_counter(mm, MM_FILEPAGES);
@@ -200,6 +207,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 
 	err = 0;
  unlock:
+	mem_cgroup_cancel_charge(kpage, memcg);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	unlock_page(page);
 	return err;
@@ -315,18 +323,11 @@ retry:
 	if (!new_page)
 		goto put_old;
 
-	if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL))
-		goto put_new;
-
 	__SetPageUptodate(new_page);
 	copy_highpage(new_page, old_page);
 	copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
 
 	ret = __replace_page(vma, vaddr, old_page, new_page);
-	if (ret)
-		mem_cgroup_uncharge_page(new_page);
-
-put_new:
 	page_cache_release(new_page);
 put_old:
 	put_page(old_page);
diff --git a/kernel/exit.c b/kernel/exit.c
index 88c6b3e42583..32c58f7433a3 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -59,7 +59,7 @@
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
 
-static void exit_mm(struct task_struct * tsk);
+static void exit_mm(struct task_struct *tsk);
 
 static void __unhash_process(struct task_struct *p, bool group_dead)
 {
@@ -151,7 +151,7 @@ static void __exit_signal(struct task_struct *tsk)
 	spin_unlock(&sighand->siglock);
 
 	__cleanup_sighand(sighand);
-	clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
+	clear_tsk_thread_flag(tsk, TIF_SIGPENDING);
 	if (group_dead) {
 		flush_sigqueue(&sig->shared_pending);
 		tty_kref_put(tty);
@@ -168,7 +168,7 @@ static void delayed_put_task_struct(struct rcu_head *rhp)
 }
 
 
-void release_task(struct task_struct * p)
+void release_task(struct task_struct *p)
 {
 	struct task_struct *leader;
 	int zap_leader;
@@ -192,7 +192,8 @@ repeat:
 	 */
 	zap_leader = 0;
 	leader = p->group_leader;
-	if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) {
+	if (leader != p && thread_group_empty(leader)
+			&& leader->exit_state == EXIT_ZOMBIE) {
 		/*
 		 * If we were the last child thread and the leader has
 		 * exited already, and the leader's parent ignores SIGCHLD,
@@ -241,7 +242,8 @@ struct pid *session_of_pgrp(struct pid *pgrp)
  *
  * "I ask you, have you ever known what it is to be an orphan?"
  */
-static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task)
+static int will_become_orphaned_pgrp(struct pid *pgrp,
+					struct task_struct *ignored_task)
 {
 	struct task_struct *p;
 
@@ -294,9 +296,9 @@ kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent)
 	struct task_struct *ignored_task = tsk;
 
 	if (!parent)
-		 /* exit: our father is in a different pgrp than
-		  * we are and we were the only connection outside.
-		  */
+		/* exit: our father is in a different pgrp than
+		 * we are and we were the only connection outside.
+		 */
 		parent = tsk->real_parent;
 	else
 		/* reparent: our child is in a different pgrp than
@@ -405,7 +407,7 @@ assign_new_owner:
  * Turn us into a lazy TLB process if we
  * aren't already..
  */
-static void exit_mm(struct task_struct * tsk)
+static void exit_mm(struct task_struct *tsk)
 {
 	struct mm_struct *mm = tsk->mm;
 	struct core_state *core_state;
@@ -425,6 +427,7 @@ static void exit_mm(struct task_struct * tsk)
 	core_state = mm->core_state;
 	if (core_state) {
 		struct core_thread self;
+
 		up_read(&mm->mmap_sem);
 
 		self.task = tsk;
@@ -566,6 +569,7 @@ static void forget_original_parent(struct task_struct *father)
 
 	list_for_each_entry_safe(p, n, &father->children, sibling) {
 		struct task_struct *t = p;
+
 		do {
 			t->real_parent = reaper;
 			if (t->parent == father) {
@@ -599,7 +603,7 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
 	/*
 	 * This does two things:
 	 *
-  	 * A.  Make init inherit all the child processes
+	 * A.  Make init inherit all the child processes
 	 * B.  Check to see if any process groups have become orphaned
 	 *	as a result of our exiting, and if they have any stopped
 	 *	jobs, send them a SIGHUP and then a SIGCONT.  (POSIX 3.2.2.2)
@@ -649,9 +653,8 @@ static void check_stack_usage(void)
 
 	spin_lock(&low_water_lock);
 	if (free < lowest_to_date) {
-		printk(KERN_WARNING "%s (%d) used greatest stack depth: "
-				"%lu bytes left\n",
-				current->comm, task_pid_nr(current), free);
+		pr_warn("%s (%d) used greatest stack depth: %lu bytes left\n",
+			current->comm, task_pid_nr(current), free);
 		lowest_to_date = free;
 	}
 	spin_unlock(&low_water_lock);
@@ -692,8 +695,7 @@ void do_exit(long code)
 	 * leave this task alone and wait for reboot.
 	 */
 	if (unlikely(tsk->flags & PF_EXITING)) {
-		printk(KERN_ALERT
-			"Fixing recursive fault but reboot is needed!\n");
+		pr_alert("Fixing recursive fault but reboot is needed!\n");
 		/*
 		 * We can do this unlocked here. The futex code uses
 		 * this flag just to verify whether the pi state
@@ -717,9 +719,9 @@ void do_exit(long code)
 	raw_spin_unlock_wait(&tsk->pi_lock);
 
 	if (unlikely(in_atomic()))
-		printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
-				current->comm, task_pid_nr(current),
-				preempt_count());
+		pr_info("note: %s[%d] exited with preempt_count %d\n",
+			current->comm, task_pid_nr(current),
+			preempt_count());
 
 	acct_update_integrals(tsk);
 	/* sync mm's RSS info before statistics gathering */
@@ -837,7 +839,6 @@ void do_exit(long code)
 	for (;;)
 		cpu_relax();	/* For when BUG is null */
 }
-
 EXPORT_SYMBOL_GPL(do_exit);
 
 void complete_and_exit(struct completion *comp, long code)
@@ -847,7 +848,6 @@ void complete_and_exit(struct completion *comp, long code)
 
 	do_exit(code);
 }
-
 EXPORT_SYMBOL(complete_and_exit);
 
 SYSCALL_DEFINE1(exit, int, error_code)
@@ -870,6 +870,7 @@ do_group_exit(int exit_code)
 		exit_code = sig->group_exit_code;
 	else if (!thread_group_empty(current)) {
 		struct sighand_struct *const sighand = current->sighand;
+
 		spin_lock_irq(&sighand->siglock);
 		if (signal_group_exit(sig))
 			/* Another thread got here before we took the lock.  */
@@ -1034,9 +1035,9 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		 * as other threads in the parent group can be right
 		 * here reaping other children at the same time.
 		 *
-		 * We use thread_group_cputime_adjusted() to get times for the thread
-		 * group, which consolidates times for all threads in the
-		 * group including the group leader.
+		 * We use thread_group_cputime_adjusted() to get times for
+		 * the thread group, which consolidates times for all threads
+		 * in the group including the group leader.
 		 */
 		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
 		spin_lock_irq(&p->real_parent->sighand->siglock);
@@ -1418,6 +1419,7 @@ static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk)
 
 	list_for_each_entry(p, &tsk->children, sibling) {
 		int ret = wait_consider_task(wo, 0, p);
+
 		if (ret)
 			return ret;
 	}
@@ -1431,6 +1433,7 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
 
 	list_for_each_entry(p, &tsk->ptraced, ptrace_entry) {
 		int ret = wait_consider_task(wo, 1, p);
+
 		if (ret)
 			return ret;
 	}
diff --git a/kernel/fork.c b/kernel/fork.c
index fbd3497b221f..fa9124322cd4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -374,12 +374,11 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 	 */
 	down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);
 
-	mm->locked_vm = 0;
-	mm->mmap = NULL;
-	mm->vmacache_seqnum = 0;
-	mm->map_count = 0;
-	cpumask_clear(mm_cpumask(mm));
-	mm->mm_rb = RB_ROOT;
+	mm->total_vm = oldmm->total_vm;
+	mm->shared_vm = oldmm->shared_vm;
+	mm->exec_vm = oldmm->exec_vm;
+	mm->stack_vm = oldmm->stack_vm;
+
 	rb_link = &mm->mm_rb.rb_node;
 	rb_parent = NULL;
 	pprev = &mm->mmap;
@@ -536,19 +535,37 @@ static void mm_init_aio(struct mm_struct *mm)
 #endif
 }
 
+static void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
+{
+#ifdef CONFIG_MEMCG
+	mm->owner = p;
+#endif
+}
+
 static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 {
+	mm->mmap = NULL;
+	mm->mm_rb = RB_ROOT;
+	mm->vmacache_seqnum = 0;
 	atomic_set(&mm->mm_users, 1);
 	atomic_set(&mm->mm_count, 1);
 	init_rwsem(&mm->mmap_sem);
 	INIT_LIST_HEAD(&mm->mmlist);
 	mm->core_state = NULL;
 	atomic_long_set(&mm->nr_ptes, 0);
+	mm->map_count = 0;
+	mm->locked_vm = 0;
+	mm->pinned_vm = 0;
 	memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
 	spin_lock_init(&mm->page_table_lock);
+	mm_init_cpumask(mm);
 	mm_init_aio(mm);
 	mm_init_owner(mm, p);
+	mmu_notifier_mm_init(mm);
 	clear_tlb_flush_pending(mm);
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
+	mm->pmd_huge_pte = NULL;
+#endif
 
 	if (current->mm) {
 		mm->flags = current->mm->flags & MMF_INIT_MASK;
@@ -558,11 +575,17 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 		mm->def_flags = 0;
 	}
 
-	if (likely(!mm_alloc_pgd(mm))) {
-		mmu_notifier_mm_init(mm);
-		return mm;
-	}
+	if (mm_alloc_pgd(mm))
+		goto fail_nopgd;
+
+	if (init_new_context(p, mm))
+		goto fail_nocontext;
+
+	return mm;
 
+fail_nocontext:
+	mm_free_pgd(mm);
+fail_nopgd:
 	free_mm(mm);
 	return NULL;
 }
@@ -596,7 +619,6 @@ struct mm_struct *mm_alloc(void)
 		return NULL;
 
 	memset(mm, 0, sizeof(*mm));
-	mm_init_cpumask(mm);
 	return mm_init(mm, current);
 }
 
@@ -828,17 +850,10 @@ static struct mm_struct *dup_mm(struct task_struct *tsk)
 		goto fail_nomem;
 
 	memcpy(mm, oldmm, sizeof(*mm));
-	mm_init_cpumask(mm);
 
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
-	mm->pmd_huge_pte = NULL;
-#endif
 	if (!mm_init(mm, tsk))
 		goto fail_nomem;
 
-	if (init_new_context(tsk, mm))
-		goto fail_nocontext;
-
 	dup_mm_exe_file(oldmm, mm);
 
 	err = dup_mmap(mm, oldmm);
@@ -860,15 +875,6 @@ free_pt:
 
 fail_nomem:
 	return NULL;
-
-fail_nocontext:
-	/*
-	 * If init_new_context() failed, we cannot use mmput() to free the mm
-	 * because it calls destroy_context()
-	 */
-	mm_free_pgd(mm);
-	free_mm(mm);
-	return NULL;
 }
 
 static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
@@ -1140,13 +1146,6 @@ static void rt_mutex_init_task(struct task_struct *p)
 #endif
 }
 
-#ifdef CONFIG_MEMCG
-void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
-{
-	mm->owner = p;
-}
-#endif /* CONFIG_MEMCG */
-
 /*
  * Initialize POSIX timer handling for a single task.
  */
@@ -1346,10 +1345,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #ifdef CONFIG_DEBUG_MUTEXES
 	p->blocked_on = NULL; /* not blocked yet */
 #endif
-#ifdef CONFIG_MEMCG
-	p->memcg_batch.do_batch = 0;
-	p->memcg_batch.memcg = NULL;
-#endif
 #ifdef CONFIG_BCACHE
 	p->sequential_io	= 0;
 	p->sequential_io_avg	= 0;
@@ -1367,6 +1362,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if (retval)
 		goto bad_fork_cleanup_policy;
 	/* copy all the process information */
+	shm_init_task(p);
 	retval = copy_semundo(clone_flags, p);
 	if (retval)
 		goto bad_fork_cleanup_audit;
@@ -1918,6 +1914,11 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 			 */
 			exit_sem(current);
 		}
+		if (unshare_flags & CLONE_NEWIPC) {
+			/* Orphan segments in old ns (see sem above). */
+			exit_shm(current);
+			shm_init_task(current);
+		}
 
 		if (new_nsproxy)
 			switch_task_namespaces(current, new_nsproxy);
diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c
index 15ff01a76379..edf67c493a8e 100644
--- a/kernel/gcov/fs.c
+++ b/kernel/gcov/fs.c
@@ -784,8 +784,7 @@ static __init int gcov_fs_init(void)
 
 err_remove:
 	pr_err("init failed\n");
-	if (root_node.dentry)
-		debugfs_remove(root_node.dentry);
+	debugfs_remove(root_node.dentry);
 
 	return rc;
 }
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index cb0cf37dac3a..ae5167087845 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -364,7 +364,7 @@ static int __sprint_symbol(char *buffer, unsigned long address,
 	address += symbol_offset;
 	name = kallsyms_lookup(address, &size, &offset, &modname, buffer);
 	if (!name)
-		return sprintf(buffer, "0x%lx", address);
+		return sprintf(buffer, "0x%lx", address - symbol_offset);
 
 	if (name != buffer)
 		strcpy(buffer, name);
diff --git a/kernel/panic.c b/kernel/panic.c
index 62e16cef9cc2..d09dc5c32c67 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -224,6 +224,7 @@ static const struct tnt tnts[] = {
 	{ TAINT_FIRMWARE_WORKAROUND,	'I', ' ' },
 	{ TAINT_OOT_MODULE,		'O', ' ' },
 	{ TAINT_UNSIGNED_MODULE,	'E', ' ' },
+	{ TAINT_SOFTLOCKUP,		'L', ' ' },
 };
 
 /**
diff --git a/kernel/test_kprobes.c b/kernel/test_kprobes.c
index 12d6ebbfdd83..0dbab6d1acb4 100644
--- a/kernel/test_kprobes.c
+++ b/kernel/test_kprobes.c
@@ -14,6 +14,8 @@
  * the GNU General Public License for more details.
  */
 
+#define pr_fmt(fmt) "Kprobe smoke test: " fmt
+
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
 #include <linux/random.h>
@@ -41,8 +43,7 @@ static void kp_post_handler(struct kprobe *p, struct pt_regs *regs,
 {
 	if (preh_val != (rand1 / div_factor)) {
 		handler_errors++;
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"incorrect value in post_handler\n");
+		pr_err("incorrect value in post_handler\n");
 	}
 	posth_val = preh_val + div_factor;
 }
@@ -59,8 +60,7 @@ static int test_kprobe(void)
 
 	ret = register_kprobe(&kp);
 	if (ret < 0) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"register_kprobe returned %d\n", ret);
+		pr_err("register_kprobe returned %d\n", ret);
 		return ret;
 	}
 
@@ -68,14 +68,12 @@ static int test_kprobe(void)
 	unregister_kprobe(&kp);
 
 	if (preh_val == 0) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"kprobe pre_handler not called\n");
+		pr_err("kprobe pre_handler not called\n");
 		handler_errors++;
 	}
 
 	if (posth_val == 0) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"kprobe post_handler not called\n");
+		pr_err("kprobe post_handler not called\n");
 		handler_errors++;
 	}
 
@@ -98,8 +96,7 @@ static void kp_post_handler2(struct kprobe *p, struct pt_regs *regs,
 {
 	if (preh_val != (rand1 / div_factor) + 1) {
 		handler_errors++;
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"incorrect value in post_handler2\n");
+		pr_err("incorrect value in post_handler2\n");
 	}
 	posth_val = preh_val + div_factor;
 }
@@ -120,8 +117,7 @@ static int test_kprobes(void)
 	kp.flags = 0;
 	ret = register_kprobes(kps, 2);
 	if (ret < 0) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"register_kprobes returned %d\n", ret);
+		pr_err("register_kprobes returned %d\n", ret);
 		return ret;
 	}
 
@@ -130,14 +126,12 @@ static int test_kprobes(void)
 	ret = target(rand1);
 
 	if (preh_val == 0) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"kprobe pre_handler not called\n");
+		pr_err("kprobe pre_handler not called\n");
 		handler_errors++;
 	}
 
 	if (posth_val == 0) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"kprobe post_handler not called\n");
+		pr_err("kprobe post_handler not called\n");
 		handler_errors++;
 	}
 
@@ -146,14 +140,12 @@ static int test_kprobes(void)
 	ret = target2(rand1);
 
 	if (preh_val == 0) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"kprobe pre_handler2 not called\n");
+		pr_err("kprobe pre_handler2 not called\n");
 		handler_errors++;
 	}
 
 	if (posth_val == 0) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"kprobe post_handler2 not called\n");
+		pr_err("kprobe post_handler2 not called\n");
 		handler_errors++;
 	}
 
@@ -166,8 +158,7 @@ static u32 j_kprobe_target(u32 value)
 {
 	if (value != rand1) {
 		handler_errors++;
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"incorrect value in jprobe handler\n");
+		pr_err("incorrect value in jprobe handler\n");
 	}
 
 	jph_val = rand1;
@@ -186,16 +177,14 @@ static int test_jprobe(void)
 
 	ret = register_jprobe(&jp);
 	if (ret < 0) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"register_jprobe returned %d\n", ret);
+		pr_err("register_jprobe returned %d\n", ret);
 		return ret;
 	}
 
 	ret = target(rand1);
 	unregister_jprobe(&jp);
 	if (jph_val == 0) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"jprobe handler not called\n");
+		pr_err("jprobe handler not called\n");
 		handler_errors++;
 	}
 
@@ -217,24 +206,21 @@ static int test_jprobes(void)
 	jp.kp.flags = 0;
 	ret = register_jprobes(jps, 2);
 	if (ret < 0) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"register_jprobes returned %d\n", ret);
+		pr_err("register_jprobes returned %d\n", ret);
 		return ret;
 	}
 
 	jph_val = 0;
 	ret = target(rand1);
 	if (jph_val == 0) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"jprobe handler not called\n");
+		pr_err("jprobe handler not called\n");
 		handler_errors++;
 	}
 
 	jph_val = 0;
 	ret = target2(rand1);
 	if (jph_val == 0) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"jprobe handler2 not called\n");
+		pr_err("jprobe handler2 not called\n");
 		handler_errors++;
 	}
 	unregister_jprobes(jps, 2);
@@ -256,13 +242,11 @@ static int return_handler(struct kretprobe_instance *ri, struct pt_regs *regs)
 
 	if (ret != (rand1 / div_factor)) {
 		handler_errors++;
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"incorrect value in kretprobe handler\n");
+		pr_err("incorrect value in kretprobe handler\n");
 	}
 	if (krph_val == 0) {
 		handler_errors++;
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"call to kretprobe entry handler failed\n");
+		pr_err("call to kretprobe entry handler failed\n");
 	}
 
 	krph_val = rand1;
@@ -281,16 +265,14 @@ static int test_kretprobe(void)
 
 	ret = register_kretprobe(&rp);
 	if (ret < 0) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"register_kretprobe returned %d\n", ret);
+		pr_err("register_kretprobe returned %d\n", ret);
 		return ret;
 	}
 
 	ret = target(rand1);
 	unregister_kretprobe(&rp);
 	if (krph_val != rand1) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"kretprobe handler not called\n");
+		pr_err("kretprobe handler not called\n");
 		handler_errors++;
 	}
 
@@ -303,13 +285,11 @@ static int return_handler2(struct kretprobe_instance *ri, struct pt_regs *regs)
 
 	if (ret != (rand1 / div_factor) + 1) {
 		handler_errors++;
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"incorrect value in kretprobe handler2\n");
+		pr_err("incorrect value in kretprobe handler2\n");
 	}
 	if (krph_val == 0) {
 		handler_errors++;
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"call to kretprobe entry handler failed\n");
+		pr_err("call to kretprobe entry handler failed\n");
 	}
 
 	krph_val = rand1;
@@ -332,24 +312,21 @@ static int test_kretprobes(void)
 	rp.kp.flags = 0;
 	ret = register_kretprobes(rps, 2);
 	if (ret < 0) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"register_kretprobe returned %d\n", ret);
+		pr_err("register_kretprobe returned %d\n", ret);
 		return ret;
 	}
 
 	krph_val = 0;
 	ret = target(rand1);
 	if (krph_val != rand1) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"kretprobe handler not called\n");
+		pr_err("kretprobe handler not called\n");
 		handler_errors++;
 	}
 
 	krph_val = 0;
 	ret = target2(rand1);
 	if (krph_val != rand1) {
-		printk(KERN_ERR "Kprobe smoke test failed: "
-				"kretprobe handler2 not called\n");
+		pr_err("kretprobe handler2 not called\n");
 		handler_errors++;
 	}
 	unregister_kretprobes(rps, 2);
@@ -368,7 +345,7 @@ int init_test_probes(void)
 		rand1 = prandom_u32();
 	} while (rand1 <= div_factor);
 
-	printk(KERN_INFO "Kprobe smoke test started\n");
+	pr_info("started\n");
 	num_tests++;
 	ret = test_kprobe();
 	if (ret < 0)
@@ -402,13 +379,11 @@ int init_test_probes(void)
 #endif /* CONFIG_KRETPROBES */
 
 	if (errors)
-		printk(KERN_ERR "BUG: Kprobe smoke test: %d out of "
-				"%d tests failed\n", errors, num_tests);
+		pr_err("BUG: %d out of %d tests failed\n", errors, num_tests);
 	else if (handler_errors)
-		printk(KERN_ERR "BUG: Kprobe smoke test: %d error(s) "
-				"running handlers\n", handler_errors);
+		pr_err("BUG: %d error(s) running handlers\n", handler_errors);
 	else
-		printk(KERN_INFO "Kprobe smoke test passed successfully\n");
+		pr_info("passed successfully\n");
 
 	return 0;
 }
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index fcc02560fd6b..aa312b0dc3ec 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -526,21 +526,21 @@ static void m_stop(struct seq_file *seq, void *v)
 	return;
 }
 
-struct seq_operations proc_uid_seq_operations = {
+const struct seq_operations proc_uid_seq_operations = {
 	.start = uid_m_start,
 	.stop = m_stop,
 	.next = m_next,
 	.show = uid_m_show,
 };
 
-struct seq_operations proc_gid_seq_operations = {
+const struct seq_operations proc_gid_seq_operations = {
 	.start = gid_m_start,
 	.stop = m_stop,
 	.next = m_next,
 	.show = gid_m_show,
 };
 
-struct seq_operations proc_projid_seq_operations = {
+const struct seq_operations proc_projid_seq_operations = {
 	.start = projid_m_start,
 	.stop = m_stop,
 	.next = m_next,
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 51b29e9d2ba6..a8d6914030fe 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -368,6 +368,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 			smp_mb__after_atomic();
 		}
 
+		add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK);
 		if (softlockup_panic)
 			panic("softlockup: hung tasks");
 		__this_cpu_write(soft_watchdog_warn, true);
diff --git a/lib/Kconfig b/lib/Kconfig
index df872659ddd3..2accc79fdb6f 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
@@ -508,4 +515,11 @@ config UCS2_STRING
 
 source "lib/fonts/Kconfig"
 
+#
+# sg chaining option
+#
+
+config ARCH_HAS_SG_CHAIN
+	def_bool n
+
 endmenu
diff --git a/lib/Makefile b/lib/Makefile
index d6b4bc496408..b73c3c33047e 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -72,6 +72,7 @@ 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/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 86069d74c062..37f3c786348f 100644
--- a/lib/decompress.c
+++ b/lib/decompress.c
@@ -54,7 +54,7 @@ static const struct compress_format compressed_formats[] __initconst = {
 	{ {0, 0}, NULL, NULL }
 };
 
-decompress_fn __init decompress_method(const unsigned char *inbuf, int len,
+decompress_fn __init decompress_method(const unsigned char *inbuf, long len,
 				const char **name)
 {
 	const struct compress_format *cf;
diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c
index 31c5f7675fbf..8290e0bef7ea 100644
--- a/lib/decompress_bunzip2.c
+++ b/lib/decompress_bunzip2.c
@@ -92,8 +92,8 @@ struct bunzip_data {
 	/* State for interrupting output loop */
 	int writeCopies, writePos, writeRunCountdown, writeCount, writeCurrent;
 	/* I/O tracking data (file handles, buffers, positions, etc.) */
-	int (*fill)(void*, unsigned int);
-	int inbufCount, inbufPos /*, outbufPos*/;
+	long (*fill)(void*, unsigned long);
+	long inbufCount, inbufPos /*, outbufPos*/;
 	unsigned char *inbuf /*,*outbuf*/;
 	unsigned int inbufBitCount, inbufBits;
 	/* The CRC values stored in the block header and calculated from the
@@ -617,7 +617,7 @@ decode_next_byte:
 	goto decode_next_byte;
 }
 
-static int INIT nofill(void *buf, unsigned int len)
+static long INIT nofill(void *buf, unsigned long len)
 {
 	return -1;
 }
@@ -625,8 +625,8 @@ static int INIT nofill(void *buf, unsigned int len)
 /* Allocate the structure, read file header.  If in_fd ==-1, inbuf must contain
    a complete bunzip file (len bytes long).  If in_fd!=-1, inbuf and len are
    ignored, and data is read from file handle into temporary buffer. */
-static int INIT start_bunzip(struct bunzip_data **bdp, void *inbuf, int len,
-			     int (*fill)(void*, unsigned int))
+static int INIT start_bunzip(struct bunzip_data **bdp, void *inbuf, long len,
+			     long (*fill)(void*, unsigned long))
 {
 	struct bunzip_data *bd;
 	unsigned int i, j, c;
@@ -675,11 +675,11 @@ static int INIT start_bunzip(struct bunzip_data **bdp, void *inbuf, int len,
 
 /* Example usage: decompress src_fd to dst_fd.  (Stops at end of bzip2 data,
    not end of file.) */
-STATIC int INIT bunzip2(unsigned char *buf, int len,
-			int(*fill)(void*, unsigned int),
-			int(*flush)(void*, unsigned int),
+STATIC int INIT bunzip2(unsigned char *buf, long len,
+			long (*fill)(void*, unsigned long),
+			long (*flush)(void*, unsigned long),
 			unsigned char *outbuf,
-			int *pos,
+			long *pos,
 			void(*error)(char *x))
 {
 	struct bunzip_data *bd;
@@ -743,11 +743,11 @@ exit_0:
 }
 
 #ifdef PREBOOT
-STATIC int INIT decompress(unsigned char *buf, int len,
-			int(*fill)(void*, unsigned int),
-			int(*flush)(void*, unsigned int),
+STATIC int INIT decompress(unsigned char *buf, long len,
+			long (*fill)(void*, unsigned long),
+			long (*flush)(void*, unsigned long),
 			unsigned char *outbuf,
-			int *pos,
+			long *pos,
 			void(*error)(char *x))
 {
 	return bunzip2(buf, len - 4, fill, flush, outbuf, pos, error);
diff --git a/lib/decompress_inflate.c b/lib/decompress_inflate.c
index 0edfd742a154..d4c7891635ec 100644
--- a/lib/decompress_inflate.c
+++ b/lib/decompress_inflate.c
@@ -27,17 +27,17 @@
 
 #define GZIP_IOBUF_SIZE (16*1024)
 
-static int INIT nofill(void *buffer, unsigned int len)
+static long INIT nofill(void *buffer, unsigned long len)
 {
 	return -1;
 }
 
 /* Included from initramfs et al code */
-STATIC int INIT gunzip(unsigned char *buf, int len,
-		       int(*fill)(void*, unsigned int),
-		       int(*flush)(void*, unsigned int),
+STATIC int INIT gunzip(unsigned char *buf, long len,
+		       long (*fill)(void*, unsigned long),
+		       long (*flush)(void*, unsigned long),
 		       unsigned char *out_buf,
-		       int *pos,
+		       long *pos,
 		       void(*error)(char *x)) {
 	u8 *zbuf;
 	struct z_stream_s *strm;
@@ -142,7 +142,7 @@ STATIC int INIT gunzip(unsigned char *buf, int len,
 
 		/* Write any data generated */
 		if (flush && strm->next_out > out_buf) {
-			int l = strm->next_out - out_buf;
+			long l = strm->next_out - out_buf;
 			if (l != flush(out_buf, l)) {
 				rc = -1;
 				error("write error");
diff --git a/lib/decompress_unlz4.c b/lib/decompress_unlz4.c
index 7d1e83caf8ad..40f66ebe57b7 100644
--- a/lib/decompress_unlz4.c
+++ b/lib/decompress_unlz4.c
@@ -31,10 +31,10 @@
 #define LZ4_DEFAULT_UNCOMPRESSED_CHUNK_SIZE (8 << 20)
 #define ARCHIVE_MAGICNUMBER 0x184C2102
 
-STATIC inline int INIT unlz4(u8 *input, int in_len,
-				int (*fill) (void *, unsigned int),
-				int (*flush) (void *, unsigned int),
-				u8 *output, int *posp,
+STATIC inline int INIT unlz4(u8 *input, long in_len,
+				long (*fill)(void *, unsigned long),
+				long (*flush)(void *, unsigned long),
+				u8 *output, long *posp,
 				void (*error) (char *x))
 {
 	int ret = -1;
@@ -43,7 +43,7 @@ STATIC inline int INIT unlz4(u8 *input, int in_len,
 	u8 *inp;
 	u8 *inp_start;
 	u8 *outp;
-	int size = in_len;
+	long size = in_len;
 #ifdef PREBOOT
 	size_t out_len = get_unaligned_le32(input + in_len);
 #endif
@@ -83,13 +83,20 @@ STATIC inline int INIT unlz4(u8 *input, int in_len,
 	if (posp)
 		*posp = 0;
 
-	if (fill)
-		fill(inp, 4);
+	if (fill) {
+		size = fill(inp, 4);
+		if (size < 4) {
+			error("data corrupted");
+			goto exit_2;
+		}
+	}
 
 	chunksize = get_unaligned_le32(inp);
 	if (chunksize == ARCHIVE_MAGICNUMBER) {
-		inp += 4;
-		size -= 4;
+		if (!fill) {
+			inp += 4;
+			size -= 4;
+		}
 	} else {
 		error("invalid header");
 		goto exit_2;
@@ -100,29 +107,44 @@ STATIC inline int INIT unlz4(u8 *input, int in_len,
 
 	for (;;) {
 
-		if (fill)
-			fill(inp, 4);
+		if (fill) {
+			size = fill(inp, 4);
+			if (size == 0)
+				break;
+			if (size < 4) {
+				error("data corrupted");
+				goto exit_2;
+			}
+		}
 
 		chunksize = get_unaligned_le32(inp);
 		if (chunksize == ARCHIVE_MAGICNUMBER) {
-			inp += 4;
-			size -= 4;
+			if (!fill) {
+				inp += 4;
+				size -= 4;
+			}
 			if (posp)
 				*posp += 4;
 			continue;
 		}
-		inp += 4;
-		size -= 4;
+
 
 		if (posp)
 			*posp += 4;
 
-		if (fill) {
+		if (!fill) {
+			inp += 4;
+			size -= 4;
+		} else {
 			if (chunksize > lz4_compressbound(uncomp_chunksize)) {
 				error("chunk length is longer than allocated");
 				goto exit_2;
 			}
-			fill(inp, chunksize);
+			size = fill(inp, chunksize);
+			if (size < chunksize) {
+				error("data corrupted");
+				goto exit_2;
+			}
 		}
 #ifdef PREBOOT
 		if (out_len >= uncomp_chunksize) {
@@ -149,18 +171,17 @@ STATIC inline int INIT unlz4(u8 *input, int in_len,
 		if (posp)
 			*posp += chunksize;
 
-		size -= chunksize;
+		if (!fill) {
+			size -= chunksize;
 
-		if (size == 0)
-			break;
-		else if (size < 0) {
-			error("data corrupted");
-			goto exit_2;
+			if (size == 0)
+				break;
+			else if (size < 0) {
+				error("data corrupted");
+				goto exit_2;
+			}
+			inp += chunksize;
 		}
-
-		inp += chunksize;
-		if (fill)
-			inp = inp_start;
 	}
 
 	ret = 0;
@@ -175,11 +196,11 @@ exit_0:
 }
 
 #ifdef PREBOOT
-STATIC int INIT decompress(unsigned char *buf, int in_len,
-			      int(*fill)(void*, unsigned int),
-			      int(*flush)(void*, unsigned int),
+STATIC int INIT decompress(unsigned char *buf, long in_len,
+			      long (*fill)(void*, unsigned long),
+			      long (*flush)(void*, unsigned long),
 			      unsigned char *output,
-			      int *posp,
+			      long *posp,
 			      void(*error)(char *x)
 	)
 {
diff --git a/lib/decompress_unlzma.c b/lib/decompress_unlzma.c
index 32adb73a9038..0be83af62b88 100644
--- a/lib/decompress_unlzma.c
+++ b/lib/decompress_unlzma.c
@@ -65,11 +65,11 @@ static long long INIT read_int(unsigned char *ptr, int size)
 #define LZMA_IOBUF_SIZE	0x10000
 
 struct rc {
-	int (*fill)(void*, unsigned int);
+	long (*fill)(void*, unsigned long);
 	uint8_t *ptr;
 	uint8_t *buffer;
 	uint8_t *buffer_end;
-	int buffer_size;
+	long buffer_size;
 	uint32_t code;
 	uint32_t range;
 	uint32_t bound;
@@ -82,7 +82,7 @@ struct rc {
 #define RC_MODEL_TOTAL_BITS 11
 
 
-static int INIT nofill(void *buffer, unsigned int len)
+static long INIT nofill(void *buffer, unsigned long len)
 {
 	return -1;
 }
@@ -99,8 +99,8 @@ static void INIT rc_read(struct rc *rc)
 
 /* Called once */
 static inline void INIT rc_init(struct rc *rc,
-				       int (*fill)(void*, unsigned int),
-				       char *buffer, int buffer_size)
+				       long (*fill)(void*, unsigned long),
+				       char *buffer, long buffer_size)
 {
 	if (fill)
 		rc->fill = fill;
@@ -280,7 +280,7 @@ struct writer {
 	size_t buffer_pos;
 	int bufsize;
 	size_t global_pos;
-	int(*flush)(void*, unsigned int);
+	long (*flush)(void*, unsigned long);
 	struct lzma_header *header;
 };
 
@@ -534,11 +534,11 @@ static inline int INIT process_bit1(struct writer *wr, struct rc *rc,
 
 
 
-STATIC inline int INIT unlzma(unsigned char *buf, int in_len,
-			      int(*fill)(void*, unsigned int),
-			      int(*flush)(void*, unsigned int),
+STATIC inline int INIT unlzma(unsigned char *buf, long in_len,
+			      long (*fill)(void*, unsigned long),
+			      long (*flush)(void*, unsigned long),
 			      unsigned char *output,
-			      int *posp,
+			      long *posp,
 			      void(*error)(char *x)
 	)
 {
@@ -667,11 +667,11 @@ exit_0:
 }
 
 #ifdef PREBOOT
-STATIC int INIT decompress(unsigned char *buf, int in_len,
-			      int(*fill)(void*, unsigned int),
-			      int(*flush)(void*, unsigned int),
+STATIC int INIT decompress(unsigned char *buf, long in_len,
+			      long (*fill)(void*, unsigned long),
+			      long (*flush)(void*, unsigned long),
 			      unsigned char *output,
-			      int *posp,
+			      long *posp,
 			      void(*error)(char *x)
 	)
 {
diff --git a/lib/decompress_unlzo.c b/lib/decompress_unlzo.c
index 960183d4258f..b94a31bdd87d 100644
--- a/lib/decompress_unlzo.c
+++ b/lib/decompress_unlzo.c
@@ -51,7 +51,7 @@ static const unsigned char lzop_magic[] = {
 #define HEADER_SIZE_MIN       (9 + 7     + 4 + 8     + 1       + 4)
 #define HEADER_SIZE_MAX       (9 + 7 + 1 + 8 + 8 + 4 + 1 + 255 + 4)
 
-STATIC inline int INIT parse_header(u8 *input, int *skip, int in_len)
+STATIC inline long INIT parse_header(u8 *input, long *skip, long in_len)
 {
 	int l;
 	u8 *parse = input;
@@ -108,14 +108,14 @@ STATIC inline int INIT parse_header(u8 *input, int *skip, int in_len)
 	return 1;
 }
 
-STATIC inline int INIT unlzo(u8 *input, int in_len,
-				int (*fill) (void *, unsigned int),
-				int (*flush) (void *, unsigned int),
-				u8 *output, int *posp,
+STATIC int INIT unlzo(u8 *input, long in_len,
+				long (*fill)(void *, unsigned long),
+				long (*flush)(void *, unsigned long),
+				u8 *output, long *posp,
 				void (*error) (char *x))
 {
 	u8 r = 0;
-	int skip = 0;
+	long skip = 0;
 	u32 src_len, dst_len;
 	size_t tmp;
 	u8 *in_buf, *in_buf_save, *out_buf;
diff --git a/lib/decompress_unxz.c b/lib/decompress_unxz.c
index 9f34eb56854d..b07a78340e9d 100644
--- a/lib/decompress_unxz.c
+++ b/lib/decompress_unxz.c
@@ -248,10 +248,10 @@ void *memmove(void *dest, const void *src, size_t size)
  * both input and output buffers are available as a single chunk, i.e. when
  * fill() and flush() won't be used.
  */
-STATIC int INIT unxz(unsigned char *in, int in_size,
-		     int (*fill)(void *dest, unsigned int size),
-		     int (*flush)(void *src, unsigned int size),
-		     unsigned char *out, int *in_used,
+STATIC int INIT unxz(unsigned char *in, long in_size,
+		     long (*fill)(void *dest, unsigned long size),
+		     long (*flush)(void *src, unsigned long size),
+		     unsigned char *out, long *in_used,
 		     void (*error)(char *x))
 {
 	struct xz_buf b;
@@ -329,7 +329,7 @@ STATIC int INIT unxz(unsigned char *in, int in_size,
 				 * returned by xz_dec_run(), but probably
 				 * it's not too bad.
 				 */
-				if (flush(b.out, b.out_pos) != (int)b.out_pos)
+				if (flush(b.out, b.out_pos) != (long)b.out_pos)
 					ret = XZ_BUF_ERROR;
 
 				b.out_pos = 0;
diff --git a/lib/idr.c b/lib/idr.c
index 39158abebad1..50be3fa9b657 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -590,26 +590,27 @@ static void __idr_remove_all(struct idr *idp)
 	struct idr_layer **paa = &pa[0];
 
 	n = idp->layers * IDR_BITS;
-	p = idp->top;
+	*paa = idp->top;
 	RCU_INIT_POINTER(idp->top, NULL);
 	max = idr_max(idp->layers);
 
 	id = 0;
 	while (id >= 0 && id <= max) {
+		p = *paa;
 		while (n > IDR_BITS && p) {
 			n -= IDR_BITS;
-			*paa++ = p;
 			p = p->ary[(id >> n) & IDR_MASK];
+			*++paa = p;
 		}
 
 		bt_mask = id;
 		id += 1 << n;
 		/* Get the highest bit that the above add changed from 0->1. */
 		while (n < fls(id ^ bt_mask)) {
-			if (p)
-				free_layer(idp, p);
+			if (*paa)
+				free_layer(idp, *paa);
 			n += IDR_BITS;
-			p = *--paa;
+			--paa;
 		}
 	}
 	idp->layers = 0;
@@ -692,15 +693,16 @@ int idr_for_each(struct idr *idp,
 	struct idr_layer **paa = &pa[0];
 
 	n = idp->layers * IDR_BITS;
-	p = rcu_dereference_raw(idp->top);
+	*paa = rcu_dereference_raw(idp->top);
 	max = idr_max(idp->layers);
 
 	id = 0;
 	while (id >= 0 && id <= max) {
+		p = *paa;
 		while (n > 0 && p) {
 			n -= IDR_BITS;
-			*paa++ = p;
 			p = rcu_dereference_raw(p->ary[(id >> n) & IDR_MASK]);
+			*++paa = p;
 		}
 
 		if (p) {
@@ -712,7 +714,7 @@ int idr_for_each(struct idr *idp,
 		id += 1 << n;
 		while (n < fls(id)) {
 			n += IDR_BITS;
-			p = *--paa;
+			--paa;
 		}
 	}
 
@@ -740,17 +742,18 @@ void *idr_get_next(struct idr *idp, int *nextidp)
 	int n, max;
 
 	/* find first ent */
-	p = rcu_dereference_raw(idp->top);
+	p = *paa = rcu_dereference_raw(idp->top);
 	if (!p)
 		return NULL;
 	n = (p->layer + 1) * IDR_BITS;
 	max = idr_max(p->layer + 1);
 
 	while (id >= 0 && id <= max) {
+		p = *paa;
 		while (n > 0 && p) {
 			n -= IDR_BITS;
-			*paa++ = p;
 			p = rcu_dereference_raw(p->ary[(id >> n) & IDR_MASK]);
+			*++paa = p;
 		}
 
 		if (p) {
@@ -768,7 +771,7 @@ void *idr_get_next(struct idr *idp, int *nextidp)
 		id = round_up(id + 1, 1 << n);
 		while (n < fls(id)) {
 			n += IDR_BITS;
-			p = *--paa;
+			--paa;
 		}
 	}
 	return NULL;
diff --git a/lib/kfifo.c b/lib/kfifo.c
index d79b9d222065..90ba1eb1df06 100644
--- a/lib/kfifo.c
+++ b/lib/kfifo.c
@@ -561,8 +561,7 @@ EXPORT_SYMBOL(__kfifo_to_user_r);
 unsigned int __kfifo_dma_in_prepare_r(struct __kfifo *fifo,
 	struct scatterlist *sgl, int nents, unsigned int len, size_t recsize)
 {
-	if (!nents)
-		BUG();
+	BUG_ON(!nents);
 
 	len = __kfifo_max_r(len, recsize);
 
@@ -585,8 +584,7 @@ EXPORT_SYMBOL(__kfifo_dma_in_finish_r);
 unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo,
 	struct scatterlist *sgl, int nents, unsigned int len, size_t recsize)
 {
-	if (!nents)
-		BUG();
+	BUG_ON(!nents);
 
 	len = __kfifo_max_r(len, recsize);
 
diff --git a/lib/rbtree.c b/lib/rbtree.c
index 65f4effd117f..c16c81a3d430 100644
--- a/lib/rbtree.c
+++ b/lib/rbtree.c
@@ -101,7 +101,7 @@ __rb_insert(struct rb_node *node, struct rb_root *root,
 				 *      / \          / \
 				 *     p   u  -->   P   U
 				 *    /            /
-				 *   n            N
+				 *   n            n
 				 *
 				 * However, since g's parent might be red, and
 				 * 4) does not allow this, we need to recurse
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index b4415fceb7e7..9cdf62f8accd 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -73,7 +73,7 @@ EXPORT_SYMBOL(sg_nents);
  **/
 struct scatterlist *sg_last(struct scatterlist *sgl, unsigned int nents)
 {
-#ifndef ARCH_HAS_SG_CHAIN
+#ifndef CONFIG_ARCH_HAS_SG_CHAIN
 	struct scatterlist *ret = &sgl[nents - 1];
 #else
 	struct scatterlist *sg, *ret = NULL;
@@ -255,7 +255,7 @@ int __sg_alloc_table(struct sg_table *table, unsigned int nents,
 
 	if (nents == 0)
 		return -EINVAL;
-#ifndef ARCH_HAS_SG_CHAIN
+#ifndef CONFIG_ARCH_HAS_SG_CHAIN
 	if (WARN_ON_ONCE(nents > max_ents))
 		return -EINVAL;
 #endif
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 6fe2c84eb055..0eced40344dd 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -1183,6 +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;
 
 /*
@@ -1250,6 +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
@@ -1261,7 +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.
@@ -1389,6 +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) {
diff --git a/mm/compaction.c b/mm/compaction.c
index 21bf292b642a..51750197db11 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -325,14 +325,14 @@ 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;
@@ -341,9 +341,6 @@ 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);
diff --git a/mm/filemap.c b/mm/filemap.c
index af19a6b079f5..f501b56ec2c6 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -31,6 +31,7 @@
 #include <linux/security.h>
 #include <linux/cpuset.h>
 #include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
+#include <linux/hugetlb.h>
 #include <linux/memcontrol.h>
 #include <linux/cleancache.h>
 #include <linux/rmap.h>
@@ -233,7 +234,6 @@ void delete_from_page_cache(struct page *page)
 	spin_lock_irq(&mapping->tree_lock);
 	__delete_from_page_cache(page, NULL);
 	spin_unlock_irq(&mapping->tree_lock);
-	mem_cgroup_uncharge_cache_page(page);
 
 	if (freepage)
 		freepage(page);
@@ -489,8 +489,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 		if (PageSwapBacked(new))
 			__inc_zone_page_state(new, NR_SHMEM);
 		spin_unlock_irq(&mapping->tree_lock);
-		/* mem_cgroup codes must not be called under tree_lock */
-		mem_cgroup_replace_page_cache(old, new);
+		mem_cgroup_migrate(old, new, true);
 		radix_tree_preload_end();
 		if (freepage)
 			freepage(old);
@@ -548,19 +547,24 @@ static int __add_to_page_cache_locked(struct page *page,
 				      pgoff_t offset, gfp_t gfp_mask,
 				      void **shadowp)
 {
+	int huge = PageHuge(page);
+	struct mem_cgroup *memcg;
 	int error;
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(PageSwapBacked(page), page);
 
-	error = mem_cgroup_charge_file(page, current->mm,
-					gfp_mask & GFP_RECLAIM_MASK);
-	if (error)
-		return error;
+	if (!huge) {
+		error = mem_cgroup_try_charge(page, current->mm,
+					      gfp_mask, &memcg);
+		if (error)
+			return error;
+	}
 
 	error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM);
 	if (error) {
-		mem_cgroup_uncharge_cache_page(page);
+		if (!huge)
+			mem_cgroup_cancel_charge(page, memcg);
 		return error;
 	}
 
@@ -575,13 +579,16 @@ static int __add_to_page_cache_locked(struct page *page,
 		goto err_insert;
 	__inc_zone_page_state(page, NR_FILE_PAGES);
 	spin_unlock_irq(&mapping->tree_lock);
+	if (!huge)
+		mem_cgroup_commit_charge(page, memcg, false);
 	trace_mm_filemap_add_to_page_cache(page);
 	return 0;
 err_insert:
 	page->mapping = NULL;
 	/* Leave page->index set: truncation relies upon it */
 	spin_unlock_irq(&mapping->tree_lock);
-	mem_cgroup_uncharge_cache_page(page);
+	if (!huge)
+		mem_cgroup_cancel_charge(page, memcg);
 	page_cache_release(page);
 	return error;
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 3630d577e987..d9a21d06b862 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -715,13 +715,20 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 					unsigned long haddr, pmd_t *pmd,
 					struct page *page)
 {
+	struct mem_cgroup *memcg;
 	pgtable_t pgtable;
 	spinlock_t *ptl;
 
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
+
+	if (mem_cgroup_try_charge(page, mm, GFP_TRANSHUGE, &memcg))
+		return VM_FAULT_OOM;
+
 	pgtable = pte_alloc_one(mm, haddr);
-	if (unlikely(!pgtable))
+	if (unlikely(!pgtable)) {
+		mem_cgroup_cancel_charge(page, memcg);
 		return VM_FAULT_OOM;
+	}
 
 	clear_huge_page(page, haddr, HPAGE_PMD_NR);
 	/*
@@ -734,7 +741,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 	ptl = pmd_lock(mm, pmd);
 	if (unlikely(!pmd_none(*pmd))) {
 		spin_unlock(ptl);
-		mem_cgroup_uncharge_page(page);
+		mem_cgroup_cancel_charge(page, memcg);
 		put_page(page);
 		pte_free(mm, pgtable);
 	} else {
@@ -742,6 +749,8 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 		entry = mk_huge_pmd(page, vma->vm_page_prot);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 		page_add_new_anon_rmap(page, vma, haddr);
+		mem_cgroup_commit_charge(page, memcg, false);
+		lru_cache_add_active_or_unevictable(page, vma);
 		pgtable_trans_huge_deposit(mm, pmd, pgtable);
 		set_pmd_at(mm, haddr, pmd, entry);
 		add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
@@ -827,13 +836,7 @@ 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_charge_anon(page, mm, GFP_TRANSHUGE))) {
-		put_page(page);
-		count_vm_event(THP_FAULT_FALLBACK);
-		return VM_FAULT_FALLBACK;
-	}
 	if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page))) {
-		mem_cgroup_uncharge_page(page);
 		put_page(page);
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
@@ -979,6 +982,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 					struct page *page,
 					unsigned long haddr)
 {
+	struct mem_cgroup *memcg;
 	spinlock_t *ptl;
 	pgtable_t pgtable;
 	pmd_t _pmd;
@@ -999,20 +1003,21 @@ 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_charge_anon(pages[i], mm,
-						       GFP_KERNEL))) {
+			     mem_cgroup_try_charge(pages[i], mm, GFP_KERNEL,
+						   &memcg))) {
 			if (pages[i])
 				put_page(pages[i]);
-			mem_cgroup_uncharge_start();
 			while (--i >= 0) {
-				mem_cgroup_uncharge_page(pages[i]);
+				memcg = (void *)page_private(pages[i]);
+				set_page_private(pages[i], 0);
+				mem_cgroup_cancel_charge(pages[i], memcg);
 				put_page(pages[i]);
 			}
-			mem_cgroup_uncharge_end();
 			kfree(pages);
 			ret |= VM_FAULT_OOM;
 			goto out;
 		}
+		set_page_private(pages[i], (unsigned long)memcg);
 	}
 
 	for (i = 0; i < HPAGE_PMD_NR; i++) {
@@ -1041,7 +1046,11 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 		pte_t *pte, entry;
 		entry = mk_pte(pages[i], vma->vm_page_prot);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+		memcg = (void *)page_private(pages[i]);
+		set_page_private(pages[i], 0);
 		page_add_new_anon_rmap(pages[i], vma, haddr);
+		mem_cgroup_commit_charge(pages[i], memcg, false);
+		lru_cache_add_active_or_unevictable(pages[i], vma);
 		pte = pte_offset_map(&_pmd, haddr);
 		VM_BUG_ON(!pte_none(*pte));
 		set_pte_at(mm, haddr, pte, entry);
@@ -1065,12 +1074,12 @@ out:
 out_free_pages:
 	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
-	mem_cgroup_uncharge_start();
 	for (i = 0; i < HPAGE_PMD_NR; i++) {
-		mem_cgroup_uncharge_page(pages[i]);
+		memcg = (void *)page_private(pages[i]);
+		set_page_private(pages[i], 0);
+		mem_cgroup_cancel_charge(pages[i], memcg);
 		put_page(pages[i]);
 	}
-	mem_cgroup_uncharge_end();
 	kfree(pages);
 	goto out;
 }
@@ -1081,6 +1090,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	spinlock_t *ptl;
 	int ret = 0;
 	struct page *page = NULL, *new_page;
+	struct mem_cgroup *memcg;
 	unsigned long haddr;
 	unsigned long mmun_start;	/* For mmu_notifiers */
 	unsigned long mmun_end;		/* For mmu_notifiers */
@@ -1132,7 +1142,8 @@ alloc:
 		goto out;
 	}
 
-	if (unlikely(mem_cgroup_charge_anon(new_page, mm, GFP_TRANSHUGE))) {
+	if (unlikely(mem_cgroup_try_charge(new_page, mm,
+					   GFP_TRANSHUGE, &memcg))) {
 		put_page(new_page);
 		if (page) {
 			split_huge_page(page);
@@ -1161,7 +1172,7 @@ alloc:
 		put_user_huge_page(page);
 	if (unlikely(!pmd_same(*pmd, orig_pmd))) {
 		spin_unlock(ptl);
-		mem_cgroup_uncharge_page(new_page);
+		mem_cgroup_cancel_charge(new_page, memcg);
 		put_page(new_page);
 		goto out_mn;
 	} else {
@@ -1170,6 +1181,8 @@ alloc:
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 		pmdp_clear_flush(vma, haddr, pmd);
 		page_add_new_anon_rmap(new_page, vma, haddr);
+		mem_cgroup_commit_charge(new_page, memcg, false);
+		lru_cache_add_active_or_unevictable(new_page, vma);
 		set_pmd_at(mm, haddr, pmd, entry);
 		update_mmu_cache_pmd(vma, address, pmd);
 		if (!page) {
@@ -2413,6 +2426,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	spinlock_t *pmd_ptl, *pte_ptl;
 	int isolated;
 	unsigned long hstart, hend;
+	struct mem_cgroup *memcg;
 	unsigned long mmun_start;	/* For mmu_notifiers */
 	unsigned long mmun_end;		/* For mmu_notifiers */
 
@@ -2423,7 +2437,8 @@ static void collapse_huge_page(struct mm_struct *mm,
 	if (!new_page)
 		return;
 
-	if (unlikely(mem_cgroup_charge_anon(new_page, mm, GFP_TRANSHUGE)))
+	if (unlikely(mem_cgroup_try_charge(new_page, mm,
+					   GFP_TRANSHUGE, &memcg)))
 		return;
 
 	/*
@@ -2510,6 +2525,8 @@ static void collapse_huge_page(struct mm_struct *mm,
 	spin_lock(pmd_ptl);
 	BUG_ON(!pmd_none(*pmd));
 	page_add_new_anon_rmap(new_page, vma, address);
+	mem_cgroup_commit_charge(new_page, memcg, false);
+	lru_cache_add_active_or_unevictable(new_page, vma);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, address, pmd, _pmd);
 	update_mmu_cache_pmd(vma, address, pmd);
@@ -2523,7 +2540,7 @@ out_up_write:
 	return;
 
 out:
-	mem_cgroup_uncharge_page(new_page);
+	mem_cgroup_cancel_charge(new_page, memcg);
 	goto out_up_write;
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 90dc501eaf3f..a6e2be0241af 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -754,9 +754,11 @@ static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz,
 static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz,
 				       struct mem_cgroup_tree_per_zone *mctz)
 {
-	spin_lock(&mctz->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&mctz->lock, flags);
 	__mem_cgroup_remove_exceeded(mz, mctz);
-	spin_unlock(&mctz->lock);
+	spin_unlock_irqrestore(&mctz->lock, flags);
 }
 
 
@@ -779,7 +781,9 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 		 * mem is over its softlimit.
 		 */
 		if (excess || mz->on_tree) {
-			spin_lock(&mctz->lock);
+			unsigned long flags;
+
+			spin_lock_irqsave(&mctz->lock, flags);
 			/* if on-tree, remove it */
 			if (mz->on_tree)
 				__mem_cgroup_remove_exceeded(mz, mctz);
@@ -788,7 +792,7 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 			 * If excess is 0, no tree ops.
 			 */
 			__mem_cgroup_insert_exceeded(mz, mctz, excess);
-			spin_unlock(&mctz->lock);
+			spin_unlock_irqrestore(&mctz->lock, flags);
 		}
 	}
 }
@@ -839,9 +843,9 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
 {
 	struct mem_cgroup_per_zone *mz;
 
-	spin_lock(&mctz->lock);
+	spin_lock_irq(&mctz->lock);
 	mz = __mem_cgroup_largest_soft_limit_node(mctz);
-	spin_unlock(&mctz->lock);
+	spin_unlock_irq(&mctz->lock);
 	return mz;
 }
 
@@ -882,13 +886,6 @@ static long mem_cgroup_read_stat(struct mem_cgroup *memcg,
 	return val;
 }
 
-static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg,
-					 bool charge)
-{
-	int val = (charge) ? 1 : -1;
-	this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAP], val);
-}
-
 static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
 					    enum mem_cgroup_events_index idx)
 {
@@ -909,13 +906,13 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
 
 static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
 					 struct page *page,
-					 bool anon, int nr_pages)
+					 int nr_pages)
 {
 	/*
 	 * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is
 	 * counted as CACHE even if it's on ANON LRU.
 	 */
-	if (anon)
+	if (PageAnon(page))
 		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS],
 				nr_pages);
 	else
@@ -1013,7 +1010,6 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg,
  */
 static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
 {
-	preempt_disable();
 	/* threshold event is triggered in finer grain than soft limit */
 	if (unlikely(mem_cgroup_event_ratelimit(memcg,
 						MEM_CGROUP_TARGET_THRESH))) {
@@ -1026,8 +1022,6 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
 		do_numainfo = mem_cgroup_event_ratelimit(memcg,
 						MEM_CGROUP_TARGET_NUMAINFO);
 #endif
-		preempt_enable();
-
 		mem_cgroup_threshold(memcg);
 		if (unlikely(do_softlimit))
 			mem_cgroup_update_tree(memcg, page);
@@ -1035,8 +1029,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
 		if (unlikely(do_numainfo))
 			atomic_inc(&memcg->numainfo_events);
 #endif
-	} else
-		preempt_enable();
+	}
 }
 
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
@@ -1347,20 +1340,6 @@ out:
 	return lruvec;
 }
 
-/*
- * Following LRU functions are allowed to be used without PCG_LOCK.
- * Operations are called by routine of global LRU independently from memcg.
- * What we have to take care of here is validness of pc->mem_cgroup.
- *
- * Changes to pc->mem_cgroup happens when
- * 1. charge
- * 2. moving account
- * In typical case, "charge" is done before add-to-lru. Exception is SwapCache.
- * It is added to LRU before charge.
- * If PCG_USED bit is not set, page_cgroup is not added to this private LRU.
- * When moving account, the page is not on LRU. It's isolated.
- */
-
 /**
  * mem_cgroup_page_lruvec - return lruvec for adding an lru page
  * @page: the page
@@ -2261,22 +2240,14 @@ cleanup:
  *
  * Notes: Race condition
  *
- * We usually use lock_page_cgroup() for accessing page_cgroup member but
- * it tends to be costly. But considering some conditions, we doesn't need
- * to do so _always_.
- *
- * Considering "charge", lock_page_cgroup() is not required because all
- * file-stat operations happen after a page is attached to radix-tree. There
- * are no race with "charge".
+ * Charging occurs during page instantiation, while the page is
+ * unmapped and locked in page migration, or while the page table is
+ * locked in THP migration.  No race is possible.
  *
- * Considering "uncharge", we know that memcg doesn't clear pc->mem_cgroup
- * at "uncharge" intentionally. So, we always see valid pc->mem_cgroup even
- * if there are race with "uncharge". Statistics itself is properly handled
- * by flags.
+ * Uncharge happens to pages with zero references, no race possible.
  *
- * Considering "move", this is an only case we see a race. To make the race
- * small, we check memcg->moving_account and detect there are possibility
- * of race or not. If there is, we take a lock.
+ * Charge moving between groups is protected by checking mm->moving
+ * account and taking the move_lock in the slowpath.
  */
 
 void __mem_cgroup_begin_update_page_stat(struct page *page,
@@ -2551,17 +2522,8 @@ static int memcg_cpu_hotplug_callback(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
-/**
- * mem_cgroup_try_charge - try charging a memcg
- * @memcg: memcg to charge
- * @nr_pages: number of pages to charge
- *
- * 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 mem_cgroup *memcg,
-				 gfp_t gfp_mask,
-				 unsigned int nr_pages)
+static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
+		      unsigned int nr_pages)
 {
 	unsigned int batch = max(CHARGE_BATCH, nr_pages);
 	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
@@ -2660,41 +2622,7 @@ done:
 	return ret;
 }
 
-/**
- * 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)
-
-{
-	struct mem_cgroup *memcg;
-	int ret;
-
-	memcg = get_mem_cgroup_from_mm(mm);
-	ret = mem_cgroup_try_charge(memcg, gfp_mask, nr_pages);
-	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.
- * gotten by try_charge().
- */
-static void __mem_cgroup_cancel_charge(struct mem_cgroup *memcg,
-				       unsigned int nr_pages)
+static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
 	unsigned long bytes = nr_pages * PAGE_SIZE;
 
@@ -2732,6 +2660,16 @@ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
 	return mem_cgroup_from_id(id);
 }
 
+/*
+ * try_get_mem_cgroup_from_page - look up page's memcg association
+ * @page: the page
+ *
+ * Look up, get a css reference, and return the memcg that owns @page.
+ *
+ * The page must be locked to prevent racing with swap-in and page
+ * cache charges.  If coming from an unlocked page table, the caller
+ * must ensure the page is on the LRU or this can race with charging.
+ */
 struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 {
 	struct mem_cgroup *memcg = NULL;
@@ -2742,7 +2680,6 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
 	pc = lookup_page_cgroup(page);
-	lock_page_cgroup(pc);
 	if (PageCgroupUsed(pc)) {
 		memcg = pc->mem_cgroup;
 		if (memcg && !css_tryget_online(&memcg->css))
@@ -2756,23 +2693,46 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 			memcg = NULL;
 		rcu_read_unlock();
 	}
-	unlock_page_cgroup(pc);
 	return memcg;
 }
 
-static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
-				       struct page *page,
-				       unsigned int nr_pages,
-				       enum charge_type ctype,
-				       bool lrucare)
+static void lock_page_lru(struct page *page, int *isolated)
+{
+	struct zone *zone = page_zone(page);
+
+	spin_lock_irq(&zone->lru_lock);
+	if (PageLRU(page)) {
+		struct lruvec *lruvec;
+
+		lruvec = mem_cgroup_page_lruvec(page, zone);
+		ClearPageLRU(page);
+		del_page_from_lru_list(page, lruvec, page_lru(page));
+		*isolated = 1;
+	} else
+		*isolated = 0;
+}
+
+static void unlock_page_lru(struct page *page, int isolated)
+{
+	struct zone *zone = page_zone(page);
+
+	if (isolated) {
+		struct lruvec *lruvec;
+
+		lruvec = mem_cgroup_page_lruvec(page, zone);
+		VM_BUG_ON_PAGE(PageLRU(page), page);
+		SetPageLRU(page);
+		add_page_to_lru_list(page, lruvec, page_lru(page));
+	}
+	spin_unlock_irq(&zone->lru_lock);
+}
+
+static void commit_charge(struct page *page, struct mem_cgroup *memcg,
+			  unsigned int nr_pages, bool lrucare)
 {
 	struct page_cgroup *pc = lookup_page_cgroup(page);
-	struct zone *uninitialized_var(zone);
-	struct lruvec *lruvec;
-	bool was_on_lru = false;
-	bool anon;
+	int isolated;
 
-	lock_page_cgroup(pc);
 	VM_BUG_ON_PAGE(PageCgroupUsed(pc), page);
 	/*
 	 * we don't need page_cgroup_lock about tail pages, becase they are not
@@ -2783,44 +2743,38 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 	 * In some cases, SwapCache and FUSE(splice_buf->radixtree), the page
 	 * may already be on some other mem_cgroup's LRU.  Take care of it.
 	 */
-	if (lrucare) {
-		zone = page_zone(page);
-		spin_lock_irq(&zone->lru_lock);
-		if (PageLRU(page)) {
-			lruvec = mem_cgroup_zone_lruvec(zone, pc->mem_cgroup);
-			ClearPageLRU(page);
-			del_page_from_lru_list(page, lruvec, page_lru(page));
-			was_on_lru = true;
-		}
-	}
+	if (lrucare)
+		lock_page_lru(page, &isolated);
 
+	/*
+	 * Nobody should be changing or seriously looking at
+	 * pc->mem_cgroup and pc->flags at this point:
+	 *
+	 * - the page is uncharged
+	 *
+	 * - the page is off-LRU
+	 *
+	 * - an anonymous fault has exclusive page access, except for
+	 *   a locked page table
+	 *
+	 * - a page cache insertion, a swapin fault, or a migration
+	 *   have the page locked
+	 */
 	pc->mem_cgroup = memcg;
-	SetPageCgroupUsed(pc);
-
-	if (lrucare) {
-		if (was_on_lru) {
-			lruvec = mem_cgroup_zone_lruvec(zone, pc->mem_cgroup);
-			VM_BUG_ON_PAGE(PageLRU(page), page);
-			SetPageLRU(page);
-			add_page_to_lru_list(page, lruvec, page_lru(page));
-		}
-		spin_unlock_irq(&zone->lru_lock);
-	}
+	pc->flags = PCG_USED | PCG_MEM | (do_swap_account ? PCG_MEMSW : 0);
 
-	if (ctype == MEM_CGROUP_CHARGE_TYPE_ANON)
-		anon = true;
-	else
-		anon = false;
-
-	mem_cgroup_charge_statistics(memcg, page, anon, nr_pages);
-	unlock_page_cgroup(pc);
+	if (lrucare)
+		unlock_page_lru(page, isolated);
 
+	local_irq_disable();
+	mem_cgroup_charge_statistics(memcg, page, nr_pages);
 	/*
 	 * "charge_statistics" updated event counter. Then, check it.
 	 * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
 	 * if they exceeds softlimit.
 	 */
 	memcg_check_events(memcg, page);
+	local_irq_enable();
 }
 
 static DEFINE_MUTEX(set_limit_mutex);
@@ -2882,21 +2836,21 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
 	if (ret)
 		return ret;
 
-	ret = mem_cgroup_try_charge(memcg, gfp, size >> PAGE_SHIFT);
+	ret = try_charge(memcg, gfp, size >> PAGE_SHIFT);
 	if (ret == -EINTR)  {
 		/*
-		 * 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
-		 * kmem/slab perspective, the cache has already been selected,
-		 * by mem_cgroup_kmem_get_cache(), so it is too late to change
+		 * try_charge() chose 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 kmem/slab
+		 * perspective, the cache has already been selected, by
+		 * mem_cgroup_kmem_get_cache(), so it is too late to change
 		 * our minds.
 		 *
 		 * 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
-		 * dying when the allocation triggers should have been already
+		 * memcg_charge_kmem in a sane state, but was OOM-killed
+		 * during try_charge() above. Tasks that were already dying
+		 * when the allocation triggers should have been already
 		 * directed to the root cgroup in memcontrol.h
 		 */
 		res_counter_charge_nofail(&memcg->res, size, &fail_res);
@@ -3447,7 +3401,6 @@ static inline void memcg_unregister_all_caches(struct mem_cgroup *memcg)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
-#define PCGF_NOCOPY_AT_SPLIT (1 << PCG_LOCK | 1 << PCG_MIGRATION)
 /*
  * Because tail pages are not marked as "used", set it. We're under
  * zone->lru_lock, 'splitting on pmd' and compound_lock.
@@ -3468,7 +3421,7 @@ void mem_cgroup_split_huge_fixup(struct page *head)
 	for (i = 1; i < HPAGE_PMD_NR; i++) {
 		pc = head_pc + i;
 		pc->mem_cgroup = memcg;
-		pc->flags = head_pc->flags & ~PCGF_NOCOPY_AT_SPLIT;
+		pc->flags = head_pc->flags;
 	}
 	__this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE],
 		       HPAGE_PMD_NR);
@@ -3498,7 +3451,6 @@ static int mem_cgroup_move_account(struct page *page,
 {
 	unsigned long flags;
 	int ret;
-	bool anon = PageAnon(page);
 
 	VM_BUG_ON(from == to);
 	VM_BUG_ON_PAGE(PageLRU(page), page);
@@ -3512,15 +3464,21 @@ static int mem_cgroup_move_account(struct page *page,
 	if (nr_pages > 1 && !PageTransHuge(page))
 		goto out;
 
-	lock_page_cgroup(pc);
+	/*
+	 * Prevent mem_cgroup_migrate() from looking at pc->mem_cgroup
+	 * of its source page while we change it: page migration takes
+	 * both pages off the LRU, but page cache replacement doesn't.
+	 */
+	if (!trylock_page(page))
+		goto out;
 
 	ret = -EINVAL;
 	if (!PageCgroupUsed(pc) || pc->mem_cgroup != from)
-		goto unlock;
+		goto out_unlock;
 
 	move_lock_mem_cgroup(from, &flags);
 
-	if (!anon && page_mapped(page)) {
+	if (!PageAnon(page) && 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],
@@ -3534,20 +3492,25 @@ static int mem_cgroup_move_account(struct page *page,
 			       nr_pages);
 	}
 
-	mem_cgroup_charge_statistics(from, page, anon, -nr_pages);
+	/*
+	 * It is safe to change pc->mem_cgroup here because the page
+	 * is referenced, charged, and isolated - we can't race with
+	 * uncharging, charging, migration, or LRU putback.
+	 */
 
 	/* caller should have done css_get */
 	pc->mem_cgroup = to;
-	mem_cgroup_charge_statistics(to, page, anon, nr_pages);
 	move_unlock_mem_cgroup(from, &flags);
 	ret = 0;
-unlock:
-	unlock_page_cgroup(pc);
-	/*
-	 * check events
-	 */
+
+	local_irq_disable();
+	mem_cgroup_charge_statistics(to, page, nr_pages);
 	memcg_check_events(to, page);
+	mem_cgroup_charge_statistics(from, page, -nr_pages);
 	memcg_check_events(from, page);
+	local_irq_enable();
+out_unlock:
+	unlock_page(page);
 out:
 	return ret;
 }
@@ -3618,449 +3581,12 @@ out:
 	return ret;
 }
 
-int mem_cgroup_charge_anon(struct page *page,
-			      struct mm_struct *mm, gfp_t gfp_mask)
-{
-	unsigned int nr_pages = 1;
-	struct mem_cgroup *memcg;
-
-	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);
-		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
-	}
-
-	memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, nr_pages);
-	if (!memcg)
-		return -ENOMEM;
-	__mem_cgroup_commit_charge(memcg, page, nr_pages,
-				   MEM_CGROUP_CHARGE_TYPE_ANON, false);
-	return 0;
-}
-
-/*
- * While swap-in, try_charge -> commit or cancel, the page is locked.
- * And when try_charge() successfully returns, one refcnt to memcg without
- * struct page_cgroup is acquired. This refcnt will be consumed by
- * "commit()" or removed by "cancel()"
- */
-static int __mem_cgroup_try_charge_swapin(struct mm_struct *mm,
-					  struct page *page,
-					  gfp_t mask,
-					  struct mem_cgroup **memcgp)
-{
-	struct mem_cgroup *memcg = NULL;
-	struct page_cgroup *pc;
-	int ret;
-
-	pc = lookup_page_cgroup(page);
-	/*
-	 * Every swap fault against a single page tries to charge the
-	 * page, bail as early as possible.  shmem_unuse() encounters
-	 * already charged pages, too.  The USED bit is protected by
-	 * the page lock, which serializes swap cache removal, which
-	 * in turn serializes uncharging.
-	 */
-	if (PageCgroupUsed(pc))
-		goto out;
-	if (do_swap_account)
-		memcg = try_get_mem_cgroup_from_page(page);
-	if (!memcg)
-		memcg = get_mem_cgroup_from_mm(mm);
-	ret = mem_cgroup_try_charge(memcg, mask, 1);
-	css_put(&memcg->css);
-	if (ret == -EINTR)
-		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)
-{
-	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
-	 * those cases unuse_pte()'s pte_same() test will fail; but
-	 * there's also a KSM case which does need to charge the page.
-	 */
-	if (!PageSwapCache(page)) {
-		struct mem_cgroup *memcg;
-
-		memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1);
-		if (!memcg)
-			return -ENOMEM;
-		*memcgp = memcg;
-		return 0;
-	}
-	return __mem_cgroup_try_charge_swapin(mm, page, gfp_mask, memcgp);
-}
-
-void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg)
-{
-	if (mem_cgroup_disabled())
-		return;
-	if (!memcg)
-		return;
-	__mem_cgroup_cancel_charge(memcg, 1);
-}
-
-static void
-__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg,
-					enum charge_type ctype)
-{
-	if (mem_cgroup_disabled())
-		return;
-	if (!memcg)
-		return;
-
-	__mem_cgroup_commit_charge(memcg, page, 1, ctype, true);
-	/*
-	 * Now swap is on-memory. This means this page may be
-	 * counted both as mem and swap....double count.
-	 * Fix it by uncharging from memsw. Basically, this SwapCache is stable
-	 * under lock_page(). But in do_swap_page()::memory.c, reuse_swap_page()
-	 * may call delete_from_swap_cache() before reach here.
-	 */
-	if (do_swap_account && PageSwapCache(page)) {
-		swp_entry_t ent = {.val = page_private(page)};
-		mem_cgroup_uncharge_swap(ent);
-	}
-}
-
-void mem_cgroup_commit_charge_swapin(struct page *page,
-				     struct mem_cgroup *memcg)
-{
-	__mem_cgroup_commit_charge_swapin(page, memcg,
-					  MEM_CGROUP_CHARGE_TYPE_ANON);
-}
-
-int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm,
-				gfp_t gfp_mask)
-{
-	enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE;
-	struct mem_cgroup *memcg;
-	int ret;
-
-	if (mem_cgroup_disabled())
-		return 0;
-	if (PageCompound(page))
-		return 0;
-
-	if (PageSwapCache(page)) { /* shmem */
-		ret = __mem_cgroup_try_charge_swapin(mm, page,
-						     gfp_mask, &memcg);
-		if (ret)
-			return ret;
-		__mem_cgroup_commit_charge_swapin(page, memcg, type);
-		return 0;
-	}
-
-	memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1);
-	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,
-				   unsigned int nr_pages,
-				   const enum charge_type ctype)
-{
-	struct memcg_batch_info *batch = NULL;
-	bool uncharge_memsw = true;
-
-	/* If swapout, usage of swap doesn't decrease */
-	if (!do_swap_account || ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT)
-		uncharge_memsw = false;
-
-	batch = &current->memcg_batch;
-	/*
-	 * In usual, we do css_get() when we remember memcg pointer.
-	 * But in this case, we keep res->usage until end of a series of
-	 * uncharges. Then, it's ok to ignore memcg's refcnt.
-	 */
-	if (!batch->memcg)
-		batch->memcg = memcg;
-	/*
-	 * do_batch > 0 when unmapping pages or inode invalidate/truncate.
-	 * In those cases, all pages freed continuously can be expected to be in
-	 * the same cgroup and we have chance to coalesce uncharges.
-	 * But we do uncharge one by one if this is killed by OOM(TIF_MEMDIE)
-	 * because we want to do uncharge as soon as possible.
-	 */
-
-	if (!batch->do_batch || test_thread_flag(TIF_MEMDIE))
-		goto direct_uncharge;
-
-	if (nr_pages > 1)
-		goto direct_uncharge;
-
-	/*
-	 * In typical case, batch->memcg == mem. This means we can
-	 * merge a series of uncharges to an uncharge of res_counter.
-	 * If not, we uncharge res_counter ony by one.
-	 */
-	if (batch->memcg != memcg)
-		goto direct_uncharge;
-	/* remember freed charge and uncharge it later */
-	batch->nr_pages++;
-	if (uncharge_memsw)
-		batch->memsw_nr_pages++;
-	return;
-direct_uncharge:
-	res_counter_uncharge(&memcg->res, nr_pages * PAGE_SIZE);
-	if (uncharge_memsw)
-		res_counter_uncharge(&memcg->memsw, nr_pages * PAGE_SIZE);
-	if (unlikely(batch->memcg != memcg))
-		memcg_oom_recover(memcg);
-}
-
-/*
- * uncharge if !page_mapped(page)
- */
-static struct mem_cgroup *
-__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype,
-			     bool end_migration)
-{
-	struct mem_cgroup *memcg = NULL;
-	unsigned int nr_pages = 1;
-	struct page_cgroup *pc;
-	bool anon;
-
-	if (mem_cgroup_disabled())
-		return NULL;
-
-	if (PageTransHuge(page)) {
-		nr_pages <<= compound_order(page);
-		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
-	}
-	/*
-	 * Check if our page_cgroup is valid
-	 */
-	pc = lookup_page_cgroup(page);
-	if (unlikely(!PageCgroupUsed(pc)))
-		return NULL;
-
-	lock_page_cgroup(pc);
-
-	memcg = pc->mem_cgroup;
-
-	if (!PageCgroupUsed(pc))
-		goto unlock_out;
-
-	anon = PageAnon(page);
-
-	switch (ctype) {
-	case MEM_CGROUP_CHARGE_TYPE_ANON:
-		/*
-		 * Generally PageAnon tells if it's the anon statistics to be
-		 * updated; but sometimes e.g. mem_cgroup_uncharge_page() is
-		 * used before page reached the stage of being marked PageAnon.
-		 */
-		anon = true;
-		/* fallthrough */
-	case MEM_CGROUP_CHARGE_TYPE_DROP:
-		/* See mem_cgroup_prepare_migration() */
-		if (page_mapped(page))
-			goto unlock_out;
-		/*
-		 * Pages under migration may not be uncharged.  But
-		 * end_migration() /must/ be the one uncharging the
-		 * unused post-migration page and so it has to call
-		 * here with the migration bit still set.  See the
-		 * res_counter handling below.
-		 */
-		if (!end_migration && PageCgroupMigration(pc))
-			goto unlock_out;
-		break;
-	case MEM_CGROUP_CHARGE_TYPE_SWAPOUT:
-		if (!PageAnon(page)) {	/* Shared memory */
-			if (page->mapping && !page_is_file_cache(page))
-				goto unlock_out;
-		} else if (page_mapped(page)) /* Anon */
-				goto unlock_out;
-		break;
-	default:
-		break;
-	}
-
-	mem_cgroup_charge_statistics(memcg, page, anon, -nr_pages);
-
-	ClearPageCgroupUsed(pc);
-	/*
-	 * pc->mem_cgroup is not cleared here. It will be accessed when it's
-	 * freed from LRU. This is safe because uncharged page is expected not
-	 * to be reused (freed soon). Exception is SwapCache, it's handled by
-	 * special functions.
-	 */
-
-	unlock_page_cgroup(pc);
-	/*
-	 * even after unlock, we have memcg->res.usage here and this memcg
-	 * will never be freed, so it's safe to call css_get().
-	 */
-	memcg_check_events(memcg, page);
-	if (do_swap_account && ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) {
-		mem_cgroup_swap_statistics(memcg, true);
-		css_get(&memcg->css);
-	}
-	/*
-	 * Migration does not charge the res_counter for the
-	 * replacement page, so leave it alone when phasing out the
-	 * page that is unused after the migration.
-	 */
-	if (!end_migration)
-		mem_cgroup_do_uncharge(memcg, nr_pages, ctype);
-
-	return memcg;
-
-unlock_out:
-	unlock_page_cgroup(pc);
-	return NULL;
-}
-
-void mem_cgroup_uncharge_page(struct page *page)
-{
-	/* early check. */
-	if (page_mapped(page))
-		return;
-	VM_BUG_ON_PAGE(page->mapping && !PageAnon(page), page);
-	/*
-	 * If the page is in swap cache, uncharge should be deferred
-	 * to the swap path, which also properly accounts swap usage
-	 * and handles memcg lifetime.
-	 *
-	 * Note that this check is not stable and reclaim may add the
-	 * page to swap cache at any time after this.  However, if the
-	 * page is not in swap cache by the time page->mapcount hits
-	 * 0, there won't be any page table references to the swap
-	 * slot, and reclaim will free it and not actually write the
-	 * page to disk.
-	 */
-	if (PageSwapCache(page))
-		return;
-	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_ANON, false);
-}
-
-void mem_cgroup_uncharge_cache_page(struct page *page)
-{
-	VM_BUG_ON_PAGE(page_mapped(page), page);
-	VM_BUG_ON_PAGE(page->mapping, page);
-	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE, false);
-}
-
-/*
- * Batch_start/batch_end is called in unmap_page_range/invlidate/trucate.
- * In that cases, pages are freed continuously and we can expect pages
- * are in the same memcg. All these calls itself limits the number of
- * pages freed at once, then uncharge_start/end() is called properly.
- * This may be called prural(2) times in a context,
- */
-
-void mem_cgroup_uncharge_start(void)
-{
-	current->memcg_batch.do_batch++;
-	/* We can do nest. */
-	if (current->memcg_batch.do_batch == 1) {
-		current->memcg_batch.memcg = NULL;
-		current->memcg_batch.nr_pages = 0;
-		current->memcg_batch.memsw_nr_pages = 0;
-	}
-}
-
-void mem_cgroup_uncharge_end(void)
-{
-	struct memcg_batch_info *batch = &current->memcg_batch;
-
-	if (!batch->do_batch)
-		return;
-
-	batch->do_batch--;
-	if (batch->do_batch) /* If stacked, do nothing. */
-		return;
-
-	if (!batch->memcg)
-		return;
-	/*
-	 * This "batch->memcg" is valid without any css_get/put etc...
-	 * bacause we hide charges behind us.
-	 */
-	if (batch->nr_pages)
-		res_counter_uncharge(&batch->memcg->res,
-				     batch->nr_pages * PAGE_SIZE);
-	if (batch->memsw_nr_pages)
-		res_counter_uncharge(&batch->memcg->memsw,
-				     batch->memsw_nr_pages * PAGE_SIZE);
-	memcg_oom_recover(batch->memcg);
-	/* forget this pointer (for sanity check) */
-	batch->memcg = NULL;
-}
-
-#ifdef CONFIG_SWAP
-/*
- * called after __delete_from_swap_cache() and drop "page" account.
- * memcg information is recorded to swap_cgroup of "ent"
- */
-void
-mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
-{
-	struct mem_cgroup *memcg;
-	int ctype = MEM_CGROUP_CHARGE_TYPE_SWAPOUT;
-
-	if (!swapout) /* this was a swap cache but the swap is unused ! */
-		ctype = MEM_CGROUP_CHARGE_TYPE_DROP;
-
-	memcg = __mem_cgroup_uncharge_common(page, ctype, false);
-
-	/*
-	 * record memcg information,  if swapout && memcg != NULL,
-	 * css_get() was called in uncharge().
-	 */
-	if (do_swap_account && swapout && memcg)
-		swap_cgroup_record(ent, mem_cgroup_id(memcg));
-}
-#endif
-
 #ifdef CONFIG_MEMCG_SWAP
-/*
- * called from swap_entry_free(). remove record in swap_cgroup and
- * uncharge "memsw" account.
- */
-void mem_cgroup_uncharge_swap(swp_entry_t ent)
+static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg,
+					 bool charge)
 {
-	struct mem_cgroup *memcg;
-	unsigned short id;
-
-	if (!do_swap_account)
-		return;
-
-	id = swap_cgroup_record(ent, 0);
-	rcu_read_lock();
-	memcg = mem_cgroup_lookup(id);
-	if (memcg) {
-		/*
-		 * We uncharge this because swap is freed.  This memcg can
-		 * be obsolete one. We avoid calling css_tryget_online().
-		 */
-		res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
-		mem_cgroup_swap_statistics(memcg, false);
-		css_put(&memcg->css);
-	}
-	rcu_read_unlock();
+	int val = (charge) ? 1 : -1;
+	this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAP], val);
 }
 
 /**
@@ -4112,175 +3638,6 @@ static inline int mem_cgroup_move_swap_account(swp_entry_t entry,
 }
 #endif
 
-/*
- * Before starting migration, account PAGE_SIZE to mem_cgroup that the old
- * page belongs to.
- */
-void mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
-				  struct mem_cgroup **memcgp)
-{
-	struct mem_cgroup *memcg = NULL;
-	unsigned int nr_pages = 1;
-	struct page_cgroup *pc;
-	enum charge_type ctype;
-
-	*memcgp = NULL;
-
-	if (mem_cgroup_disabled())
-		return;
-
-	if (PageTransHuge(page))
-		nr_pages <<= compound_order(page);
-
-	pc = lookup_page_cgroup(page);
-	lock_page_cgroup(pc);
-	if (PageCgroupUsed(pc)) {
-		memcg = pc->mem_cgroup;
-		css_get(&memcg->css);
-		/*
-		 * At migrating an anonymous page, its mapcount goes down
-		 * to 0 and uncharge() will be called. But, even if it's fully
-		 * unmapped, migration may fail and this page has to be
-		 * charged again. We set MIGRATION flag here and delay uncharge
-		 * until end_migration() is called
-		 *
-		 * Corner Case Thinking
-		 * A)
-		 * When the old page was mapped as Anon and it's unmap-and-freed
-		 * while migration was ongoing.
-		 * If unmap finds the old page, uncharge() of it will be delayed
-		 * until end_migration(). If unmap finds a new page, it's
-		 * uncharged when it make mapcount to be 1->0. If unmap code
-		 * finds swap_migration_entry, the new page will not be mapped
-		 * and end_migration() will find it(mapcount==0).
-		 *
-		 * B)
-		 * When the old page was mapped but migraion fails, the kernel
-		 * remaps it. A charge for it is kept by MIGRATION flag even
-		 * if mapcount goes down to 0. We can do remap successfully
-		 * without charging it again.
-		 *
-		 * C)
-		 * The "old" page is under lock_page() until the end of
-		 * migration, so, the old page itself will not be swapped-out.
-		 * If the new page is swapped out before end_migraton, our
-		 * hook to usual swap-out path will catch the event.
-		 */
-		if (PageAnon(page))
-			SetPageCgroupMigration(pc);
-	}
-	unlock_page_cgroup(pc);
-	/*
-	 * If the page is not charged at this point,
-	 * we return here.
-	 */
-	if (!memcg)
-		return;
-
-	*memcgp = memcg;
-	/*
-	 * We charge new page before it's used/mapped. So, even if unlock_page()
-	 * is called before end_migration, we can catch all events on this new
-	 * page. In the case new page is migrated but not remapped, new page's
-	 * mapcount will be finally 0 and we call uncharge in end_migration().
-	 */
-	if (PageAnon(page))
-		ctype = MEM_CGROUP_CHARGE_TYPE_ANON;
-	else
-		ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
-	/*
-	 * The page is committed to the memcg, but it's not actually
-	 * charged to the res_counter since we plan on replacing the
-	 * old one and only one page is going to be left afterwards.
-	 */
-	__mem_cgroup_commit_charge(memcg, newpage, nr_pages, ctype, false);
-}
-
-/* remove redundant charge if migration failed*/
-void mem_cgroup_end_migration(struct mem_cgroup *memcg,
-	struct page *oldpage, struct page *newpage, bool migration_ok)
-{
-	struct page *used, *unused;
-	struct page_cgroup *pc;
-	bool anon;
-
-	if (!memcg)
-		return;
-
-	if (!migration_ok) {
-		used = oldpage;
-		unused = newpage;
-	} else {
-		used = newpage;
-		unused = oldpage;
-	}
-	anon = PageAnon(used);
-	__mem_cgroup_uncharge_common(unused,
-				     anon ? MEM_CGROUP_CHARGE_TYPE_ANON
-				     : MEM_CGROUP_CHARGE_TYPE_CACHE,
-				     true);
-	css_put(&memcg->css);
-	/*
-	 * We disallowed uncharge of pages under migration because mapcount
-	 * of the page goes down to zero, temporarly.
-	 * Clear the flag and check the page should be charged.
-	 */
-	pc = lookup_page_cgroup(oldpage);
-	lock_page_cgroup(pc);
-	ClearPageCgroupMigration(pc);
-	unlock_page_cgroup(pc);
-
-	/*
-	 * If a page is a file cache, radix-tree replacement is very atomic
-	 * and we can skip this check. When it was an Anon page, its mapcount
-	 * goes down to 0. But because we added MIGRATION flage, it's not
-	 * uncharged yet. There are several case but page->mapcount check
-	 * and USED bit check in mem_cgroup_uncharge_page() will do enough
-	 * check. (see prepare_charge() also)
-	 */
-	if (anon)
-		mem_cgroup_uncharge_page(used);
-}
-
-/*
- * At replace page cache, newpage is not under any memcg but it's on
- * LRU. So, this function doesn't touch res_counter but handles LRU
- * in correct way. Both pages are locked so we cannot race with uncharge.
- */
-void mem_cgroup_replace_page_cache(struct page *oldpage,
-				  struct page *newpage)
-{
-	struct mem_cgroup *memcg = NULL;
-	struct page_cgroup *pc;
-	enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE;
-
-	if (mem_cgroup_disabled())
-		return;
-
-	pc = lookup_page_cgroup(oldpage);
-	/* fix accounting on old pages */
-	lock_page_cgroup(pc);
-	if (PageCgroupUsed(pc)) {
-		memcg = pc->mem_cgroup;
-		mem_cgroup_charge_statistics(memcg, oldpage, false, -1);
-		ClearPageCgroupUsed(pc);
-	}
-	unlock_page_cgroup(pc);
-
-	/*
-	 * When called from shmem_replace_page(), in some cases the
-	 * oldpage has already been charged, and in some cases not.
-	 */
-	if (!memcg)
-		return;
-	/*
-	 * Even if newpage->mapping was NULL before starting replacement,
-	 * the newpage may be on LRU(or pagevec for LRU) already. We lock
-	 * LRU while we overwrite pc->mem_cgroup.
-	 */
-	__mem_cgroup_commit_charge(memcg, newpage, 1, type, true);
-}
-
 #ifdef CONFIG_DEBUG_VM
 static struct page_cgroup *lookup_page_cgroup_used(struct page *page)
 {
@@ -4479,7 +3836,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 						    gfp_mask, &nr_scanned);
 		nr_reclaimed += reclaimed;
 		*total_scanned += nr_scanned;
-		spin_lock(&mctz->lock);
+		spin_lock_irq(&mctz->lock);
 
 		/*
 		 * If we failed to reclaim anything from this memory cgroup
@@ -4519,7 +3876,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 		 */
 		/* If excess == 0, no tree ops */
 		__mem_cgroup_insert_exceeded(mz, mctz, excess);
-		spin_unlock(&mctz->lock);
+		spin_unlock_irq(&mctz->lock);
 		css_put(&mz->memcg->css);
 		loop++;
 		/*
@@ -6319,20 +5676,19 @@ static int mem_cgroup_do_precharge(unsigned long count)
 	int ret;
 
 	/* Try a single bulk charge without reclaim first */
-	ret = mem_cgroup_try_charge(mc.to, GFP_KERNEL & ~__GFP_WAIT, count);
+	ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_WAIT, count);
 	if (!ret) {
 		mc.precharge += count;
 		return ret;
 	}
 	if (ret == -EINTR) {
-		__mem_cgroup_cancel_charge(root_mem_cgroup, count);
+		cancel_charge(root_mem_cgroup, count);
 		return ret;
 	}
 
 	/* Try charges one by one with reclaim */
 	while (count--) {
-		ret = mem_cgroup_try_charge(mc.to,
-					    GFP_KERNEL & ~__GFP_NORETRY, 1);
+		ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_NORETRY, 1);
 		/*
 		 * In case of failure, any residual charges against
 		 * mc.to will be dropped by mem_cgroup_clear_mc()
@@ -6340,7 +5696,7 @@ static int mem_cgroup_do_precharge(unsigned long count)
 		 * bypassed to root right away or they'll be lost.
 		 */
 		if (ret == -EINTR)
-			__mem_cgroup_cancel_charge(root_mem_cgroup, 1);
+			cancel_charge(root_mem_cgroup, 1);
 		if (ret)
 			return ret;
 		mc.precharge++;
@@ -6482,9 +5838,9 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 	if (page) {
 		pc = lookup_page_cgroup(page);
 		/*
-		 * Do only loose check w/o page_cgroup lock.
-		 * mem_cgroup_move_account() checks the pc is valid or not under
-		 * the lock.
+		 * Do only loose check w/o serialization.
+		 * mem_cgroup_move_account() checks the pc is valid or
+		 * not under LRU exclusion.
 		 */
 		if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) {
 			ret = MC_TARGET_PAGE;
@@ -6609,7 +5965,7 @@ static void __mem_cgroup_clear_mc(void)
 
 	/* we must uncharge all the leftover precharges from mc.to */
 	if (mc.precharge) {
-		__mem_cgroup_cancel_charge(mc.to, mc.precharge);
+		cancel_charge(mc.to, mc.precharge);
 		mc.precharge = 0;
 	}
 	/*
@@ -6617,7 +5973,7 @@ static void __mem_cgroup_clear_mc(void)
 	 * we must uncharge here.
 	 */
 	if (mc.moved_charge) {
-		__mem_cgroup_cancel_charge(mc.from, mc.moved_charge);
+		cancel_charge(mc.from, mc.moved_charge);
 		mc.moved_charge = 0;
 	}
 	/* we must fixup refcnts and charges */
@@ -6946,6 +6302,403 @@ static void __init enable_swap_cgroup(void)
 }
 #endif
 
+#ifdef CONFIG_MEMCG_SWAP
+/**
+ * mem_cgroup_swapout - transfer a memsw charge to swap
+ * @page: page whose memsw charge to transfer
+ * @entry: swap entry to move the charge to
+ *
+ * Transfer the memsw charge of @page to @entry.
+ */
+void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
+{
+	struct page_cgroup *pc;
+	unsigned short oldid;
+
+	VM_BUG_ON_PAGE(PageLRU(page), page);
+	VM_BUG_ON_PAGE(page_count(page), page);
+
+	if (!do_swap_account)
+		return;
+
+	pc = lookup_page_cgroup(page);
+
+	/* Readahead page, never charged */
+	if (!PageCgroupUsed(pc))
+		return;
+
+	VM_BUG_ON_PAGE(!(pc->flags & PCG_MEMSW), page);
+
+	oldid = swap_cgroup_record(entry, mem_cgroup_id(pc->mem_cgroup));
+	VM_BUG_ON_PAGE(oldid, page);
+
+	pc->flags &= ~PCG_MEMSW;
+	css_get(&pc->mem_cgroup->css);
+	mem_cgroup_swap_statistics(pc->mem_cgroup, true);
+}
+
+/**
+ * mem_cgroup_uncharge_swap - uncharge a swap entry
+ * @entry: swap entry to uncharge
+ *
+ * Drop the memsw charge associated with @entry.
+ */
+void mem_cgroup_uncharge_swap(swp_entry_t entry)
+{
+	struct mem_cgroup *memcg;
+	unsigned short id;
+
+	if (!do_swap_account)
+		return;
+
+	id = swap_cgroup_record(entry, 0);
+	rcu_read_lock();
+	memcg = mem_cgroup_lookup(id);
+	if (memcg) {
+		res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
+		mem_cgroup_swap_statistics(memcg, false);
+		css_put(&memcg->css);
+	}
+	rcu_read_unlock();
+}
+#endif
+
+/**
+ * mem_cgroup_try_charge - try charging a page
+ * @page: page to charge
+ * @mm: mm context of the victim
+ * @gfp_mask: reclaim mode
+ * @memcgp: charged memcg return
+ *
+ * Try to charge @page to the memcg that @mm belongs to, reclaiming
+ * pages according to @gfp_mask if necessary.
+ *
+ * Returns 0 on success, with *@memcgp pointing to the charged memcg.
+ * Otherwise, an error code is returned.
+ *
+ * After page->mapping has been set up, the caller must finalize the
+ * charge with mem_cgroup_commit_charge().  Or abort the transaction
+ * with mem_cgroup_cancel_charge() in case page instantiation fails.
+ */
+int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
+			  gfp_t gfp_mask, struct mem_cgroup **memcgp)
+{
+	struct mem_cgroup *memcg = NULL;
+	unsigned int nr_pages = 1;
+	int ret = 0;
+
+	if (mem_cgroup_disabled())
+		goto out;
+
+	if (PageSwapCache(page)) {
+		struct page_cgroup *pc = lookup_page_cgroup(page);
+		/*
+		 * Every swap fault against a single page tries to charge the
+		 * page, bail as early as possible.  shmem_unuse() encounters
+		 * already charged pages, too.  The USED bit is protected by
+		 * the page lock, which serializes swap cache removal, which
+		 * in turn serializes uncharging.
+		 */
+		if (PageCgroupUsed(pc))
+			goto out;
+	}
+
+	if (PageTransHuge(page)) {
+		nr_pages <<= compound_order(page);
+		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
+	}
+
+	if (do_swap_account && PageSwapCache(page))
+		memcg = try_get_mem_cgroup_from_page(page);
+	if (!memcg)
+		memcg = get_mem_cgroup_from_mm(mm);
+
+	ret = try_charge(memcg, gfp_mask, nr_pages);
+
+	css_put(&memcg->css);
+
+	if (ret == -EINTR) {
+		memcg = root_mem_cgroup;
+		ret = 0;
+	}
+out:
+	*memcgp = memcg;
+	return ret;
+}
+
+/**
+ * mem_cgroup_commit_charge - commit a page charge
+ * @page: page to charge
+ * @memcg: memcg to charge the page to
+ * @lrucare: page might be on LRU already
+ *
+ * Finalize a charge transaction started by mem_cgroup_try_charge(),
+ * after page->mapping has been set up.  This must happen atomically
+ * as part of the page instantiation, i.e. under the page table lock
+ * for anonymous pages, under the page lock for page and swap cache.
+ *
+ * In addition, the page must not be on the LRU during the commit, to
+ * prevent racing with task migration.  If it might be, use @lrucare.
+ *
+ * Use mem_cgroup_cancel_charge() to cancel the transaction instead.
+ */
+void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
+			      bool lrucare)
+{
+	unsigned int nr_pages = 1;
+
+	VM_BUG_ON_PAGE(!page->mapping, page);
+	VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page);
+
+	if (mem_cgroup_disabled())
+		return;
+	/*
+	 * Swap faults will attempt to charge the same page multiple
+	 * times.  But reuse_swap_page() might have removed the page
+	 * from swapcache already, so we can't check PageSwapCache().
+	 */
+	if (!memcg)
+		return;
+
+	if (PageTransHuge(page)) {
+		nr_pages <<= compound_order(page);
+		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
+	}
+
+	commit_charge(page, memcg, nr_pages, lrucare);
+
+	if (do_swap_account && PageSwapCache(page)) {
+		swp_entry_t entry = { .val = page_private(page) };
+		/*
+		 * The swap entry might not get freed for a long time,
+		 * let's not wait for it.  The page already received a
+		 * memory+swap charge, drop the swap entry duplicate.
+		 */
+		mem_cgroup_uncharge_swap(entry);
+	}
+}
+
+/**
+ * mem_cgroup_cancel_charge - cancel a page charge
+ * @page: page to charge
+ * @memcg: memcg to charge the page to
+ *
+ * Cancel a charge transaction started by mem_cgroup_try_charge().
+ */
+void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg)
+{
+	unsigned int nr_pages = 1;
+
+	if (mem_cgroup_disabled())
+		return;
+	/*
+	 * Swap faults will attempt to charge the same page multiple
+	 * times.  But reuse_swap_page() might have removed the page
+	 * from swapcache already, so we can't check PageSwapCache().
+	 */
+	if (!memcg)
+		return;
+
+	if (PageTransHuge(page)) {
+		nr_pages <<= compound_order(page);
+		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
+	}
+
+	cancel_charge(memcg, nr_pages);
+}
+
+static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
+			   unsigned long nr_mem, unsigned long nr_memsw,
+			   unsigned long nr_anon, unsigned long nr_file,
+			   unsigned long nr_huge, struct page *dummy_page)
+{
+	unsigned long flags;
+
+	if (nr_mem)
+		res_counter_uncharge(&memcg->res, nr_mem * PAGE_SIZE);
+	if (nr_memsw)
+		res_counter_uncharge(&memcg->memsw, nr_memsw * PAGE_SIZE);
+
+	memcg_oom_recover(memcg);
+
+	local_irq_save(flags);
+	__this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS], nr_anon);
+	__this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_CACHE], nr_file);
+	__this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], nr_huge);
+	__this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT], pgpgout);
+	__this_cpu_add(memcg->stat->nr_page_events, nr_anon + nr_file);
+	memcg_check_events(memcg, dummy_page);
+	local_irq_restore(flags);
+}
+
+static void uncharge_list(struct list_head *page_list)
+{
+	struct mem_cgroup *memcg = NULL;
+	unsigned long nr_memsw = 0;
+	unsigned long nr_anon = 0;
+	unsigned long nr_file = 0;
+	unsigned long nr_huge = 0;
+	unsigned long pgpgout = 0;
+	unsigned long nr_mem = 0;
+	struct list_head *next;
+	struct page *page;
+
+	next = page_list->next;
+	do {
+		unsigned int nr_pages = 1;
+		struct page_cgroup *pc;
+
+		page = list_entry(next, struct page, lru);
+		next = page->lru.next;
+
+		VM_BUG_ON_PAGE(PageLRU(page), page);
+		VM_BUG_ON_PAGE(page_count(page), page);
+
+		pc = lookup_page_cgroup(page);
+		if (!PageCgroupUsed(pc))
+			continue;
+
+		/*
+		 * Nobody should be changing or seriously looking at
+		 * pc->mem_cgroup and pc->flags at this point, we have
+		 * fully exclusive access to the page.
+		 */
+
+		if (memcg != pc->mem_cgroup) {
+			if (memcg) {
+				uncharge_batch(memcg, pgpgout, nr_mem, nr_memsw,
+					       nr_anon, nr_file, nr_huge, page);
+				pgpgout = nr_mem = nr_memsw = 0;
+				nr_anon = nr_file = nr_huge = 0;
+			}
+			memcg = pc->mem_cgroup;
+		}
+
+		if (PageTransHuge(page)) {
+			nr_pages <<= compound_order(page);
+			VM_BUG_ON_PAGE(!PageTransHuge(page), page);
+			nr_huge += nr_pages;
+		}
+
+		if (PageAnon(page))
+			nr_anon += nr_pages;
+		else
+			nr_file += nr_pages;
+
+		if (pc->flags & PCG_MEM)
+			nr_mem += nr_pages;
+		if (pc->flags & PCG_MEMSW)
+			nr_memsw += nr_pages;
+		pc->flags = 0;
+
+		pgpgout++;
+	} while (next != page_list);
+
+	if (memcg)
+		uncharge_batch(memcg, pgpgout, nr_mem, nr_memsw,
+			       nr_anon, nr_file, nr_huge, page);
+}
+
+/**
+ * mem_cgroup_uncharge - uncharge a page
+ * @page: page to uncharge
+ *
+ * Uncharge a page previously charged with mem_cgroup_try_charge() and
+ * mem_cgroup_commit_charge().
+ */
+void mem_cgroup_uncharge(struct page *page)
+{
+	struct page_cgroup *pc;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	/* Don't touch page->lru of any random page, pre-check: */
+	pc = lookup_page_cgroup(page);
+	if (!PageCgroupUsed(pc))
+		return;
+
+	INIT_LIST_HEAD(&page->lru);
+	uncharge_list(&page->lru);
+}
+
+/**
+ * mem_cgroup_uncharge_list - uncharge a list of page
+ * @page_list: list of pages to uncharge
+ *
+ * Uncharge a list of pages previously charged with
+ * mem_cgroup_try_charge() and mem_cgroup_commit_charge().
+ */
+void mem_cgroup_uncharge_list(struct list_head *page_list)
+{
+	if (mem_cgroup_disabled())
+		return;
+
+	if (!list_empty(page_list))
+		uncharge_list(page_list);
+}
+
+/**
+ * mem_cgroup_migrate - migrate a charge to another page
+ * @oldpage: currently charged page
+ * @newpage: page to transfer the charge to
+ * @lrucare: both pages might be on the LRU already
+ *
+ * Migrate the charge from @oldpage to @newpage.
+ *
+ * Both pages must be locked, @newpage->mapping must be set up.
+ */
+void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
+			bool lrucare)
+{
+	unsigned int nr_pages = 1;
+	struct page_cgroup *pc;
+	int isolated;
+
+	VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
+	VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
+	VM_BUG_ON_PAGE(!lrucare && PageLRU(oldpage), oldpage);
+	VM_BUG_ON_PAGE(!lrucare && PageLRU(newpage), newpage);
+	VM_BUG_ON_PAGE(PageAnon(oldpage) != PageAnon(newpage), newpage);
+
+	if (mem_cgroup_disabled())
+		return;
+
+	/* Page cache replacement: new page already charged? */
+	pc = lookup_page_cgroup(newpage);
+	if (PageCgroupUsed(pc))
+		return;
+
+	/* Re-entrant migration: old page already uncharged? */
+	pc = lookup_page_cgroup(oldpage);
+	if (!PageCgroupUsed(pc))
+		return;
+
+	VM_BUG_ON_PAGE(!(pc->flags & PCG_MEM), oldpage);
+	VM_BUG_ON_PAGE(do_swap_account && !(pc->flags & PCG_MEMSW), oldpage);
+
+	if (PageTransHuge(oldpage)) {
+		nr_pages <<= compound_order(oldpage);
+		VM_BUG_ON_PAGE(!PageTransHuge(oldpage), oldpage);
+		VM_BUG_ON_PAGE(!PageTransHuge(newpage), newpage);
+	}
+
+	if (lrucare)
+		lock_page_lru(oldpage, &isolated);
+
+	pc->flags = 0;
+
+	if (lrucare)
+		unlock_page_lru(oldpage, isolated);
+
+	local_irq_disable();
+	mem_cgroup_charge_statistics(pc->mem_cgroup, oldpage, -nr_pages);
+	memcg_check_events(pc->mem_cgroup, oldpage);
+	local_irq_enable();
+
+	commit_charge(newpage, pc->mem_cgroup, nr_pages, lrucare);
+}
+
 /*
  * subsys_initcall() for memory controller.
  *
diff --git a/mm/memory.c b/mm/memory.c
index 5c55270729f7..2476f5bdbfe3 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1292,7 +1292,6 @@ static void unmap_page_range(struct mmu_gather *tlb,
 		details = NULL;
 
 	BUG_ON(addr >= end);
-	mem_cgroup_uncharge_start();
 	tlb_start_vma(tlb, vma);
 	pgd = pgd_offset(vma->vm_mm, addr);
 	do {
@@ -1302,7 +1301,6 @@ static void unmap_page_range(struct mmu_gather *tlb,
 		next = zap_pud_range(tlb, vma, pgd, addr, next, details);
 	} while (pgd++, addr = next, addr != end);
 	tlb_end_vma(tlb, vma);
-	mem_cgroup_uncharge_end();
 }
 
 
@@ -2049,6 +2047,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *dirty_page = NULL;
 	unsigned long mmun_start = 0;	/* For mmu_notifiers */
 	unsigned long mmun_end = 0;	/* For mmu_notifiers */
+	struct mem_cgroup *memcg;
 
 	old_page = vm_normal_page(vma, address, orig_pte);
 	if (!old_page) {
@@ -2204,7 +2203,7 @@ gotten:
 	}
 	__SetPageUptodate(new_page);
 
-	if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL))
+	if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg))
 		goto oom_free_new;
 
 	mmun_start  = address & PAGE_MASK;
@@ -2234,6 +2233,8 @@ gotten:
 		 */
 		ptep_clear_flush(vma, address, page_table);
 		page_add_new_anon_rmap(new_page, vma, address);
+		mem_cgroup_commit_charge(new_page, memcg, false);
+		lru_cache_add_active_or_unevictable(new_page, vma);
 		/*
 		 * We call the notify macro here because, when using secondary
 		 * mmu page tables (such as kvm shadow page tables), we want the
@@ -2271,7 +2272,7 @@ gotten:
 		new_page = old_page;
 		ret |= VM_FAULT_WRITE;
 	} else
-		mem_cgroup_uncharge_page(new_page);
+		mem_cgroup_cancel_charge(new_page, memcg);
 
 	if (new_page)
 		page_cache_release(new_page);
@@ -2410,10 +2411,10 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	spinlock_t *ptl;
 	struct page *page, *swapcache;
+	struct mem_cgroup *memcg;
 	swp_entry_t entry;
 	pte_t pte;
 	int locked;
-	struct mem_cgroup *ptr;
 	int exclusive = 0;
 	int ret = 0;
 
@@ -2489,7 +2490,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_page;
 	}
 
-	if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) {
+	if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg)) {
 		ret = VM_FAULT_OOM;
 		goto out_page;
 	}
@@ -2514,10 +2515,6 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * while the page is counted on swap but not yet in mapcount i.e.
 	 * before page_add_anon_rmap() and swap_free(); try_to_free_swap()
 	 * must be called after the swap_free(), or it will never succeed.
-	 * Because delete_from_swap_page() may be called by reuse_swap_page(),
-	 * mem_cgroup_commit_charge_swapin() may not be able to find swp_entry
-	 * in page->private. In this case, a record in swap_cgroup  is silently
-	 * discarded at swap_free().
 	 */
 
 	inc_mm_counter_fast(mm, MM_ANONPAGES);
@@ -2533,12 +2530,14 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (pte_swp_soft_dirty(orig_pte))
 		pte = pte_mksoft_dirty(pte);
 	set_pte_at(mm, address, page_table, pte);
-	if (page == swapcache)
+	if (page == swapcache) {
 		do_page_add_anon_rmap(page, vma, address, exclusive);
-	else /* ksm created a completely new copy */
+		mem_cgroup_commit_charge(page, memcg, true);
+	} else { /* ksm created a completely new copy */
 		page_add_new_anon_rmap(page, vma, address);
-	/* It's better to call commit-charge after rmap is established */
-	mem_cgroup_commit_charge_swapin(page, ptr);
+		mem_cgroup_commit_charge(page, memcg, false);
+		lru_cache_add_active_or_unevictable(page, vma);
+	}
 
 	swap_free(entry);
 	if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
@@ -2571,7 +2570,7 @@ unlock:
 out:
 	return ret;
 out_nomap:
-	mem_cgroup_cancel_charge_swapin(ptr);
+	mem_cgroup_cancel_charge(page, memcg);
 	pte_unmap_unlock(page_table, ptl);
 out_page:
 	unlock_page(page);
@@ -2627,6 +2626,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long address, pte_t *page_table, pmd_t *pmd,
 		unsigned int flags)
 {
+	struct mem_cgroup *memcg;
 	struct page *page;
 	spinlock_t *ptl;
 	pte_t entry;
@@ -2660,7 +2660,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 */
 	__SetPageUptodate(page);
 
-	if (mem_cgroup_charge_anon(page, mm, GFP_KERNEL))
+	if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg))
 		goto oom_free_page;
 
 	entry = mk_pte(page, vma->vm_page_prot);
@@ -2673,6 +2673,8 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	inc_mm_counter_fast(mm, MM_ANONPAGES);
 	page_add_new_anon_rmap(page, vma, address);
+	mem_cgroup_commit_charge(page, memcg, false);
+	lru_cache_add_active_or_unevictable(page, vma);
 setpte:
 	set_pte_at(mm, address, page_table, entry);
 
@@ -2682,7 +2684,7 @@ unlock:
 	pte_unmap_unlock(page_table, ptl);
 	return 0;
 release:
-	mem_cgroup_uncharge_page(page);
+	mem_cgroup_cancel_charge(page, memcg);
 	page_cache_release(page);
 	goto unlock;
 oom_free_page:
@@ -2919,6 +2921,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
 {
 	struct page *fault_page, *new_page;
+	struct mem_cgroup *memcg;
 	spinlock_t *ptl;
 	pte_t *pte;
 	int ret;
@@ -2930,7 +2933,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!new_page)
 		return VM_FAULT_OOM;
 
-	if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL)) {
+	if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg)) {
 		page_cache_release(new_page);
 		return VM_FAULT_OOM;
 	}
@@ -2950,12 +2953,14 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto uncharge_out;
 	}
 	do_set_pte(vma, address, new_page, pte, true, true);
+	mem_cgroup_commit_charge(new_page, memcg, false);
+	lru_cache_add_active_or_unevictable(new_page, vma);
 	pte_unmap_unlock(pte, ptl);
 	unlock_page(fault_page);
 	page_cache_release(fault_page);
 	return ret;
 uncharge_out:
-	mem_cgroup_uncharge_page(new_page);
+	mem_cgroup_cancel_charge(new_page, memcg);
 	page_cache_release(new_page);
 	return ret;
 }
@@ -2971,6 +2976,8 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	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;
@@ -3001,6 +3008,12 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	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) {
diff --git a/mm/migrate.c b/mm/migrate.c
index be6dbf995c0c..f78ec9bd454d 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -780,6 +780,7 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 	if (rc != MIGRATEPAGE_SUCCESS) {
 		newpage->mapping = NULL;
 	} else {
+		mem_cgroup_migrate(page, newpage, false);
 		if (remap_swapcache)
 			remove_migration_ptes(page, newpage);
 		page->mapping = NULL;
@@ -795,7 +796,6 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 {
 	int rc = -EAGAIN;
 	int remap_swapcache = 1;
-	struct mem_cgroup *mem;
 	struct anon_vma *anon_vma = NULL;
 
 	if (!trylock_page(page)) {
@@ -821,9 +821,6 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 		lock_page(page);
 	}
 
-	/* charge against new page */
-	mem_cgroup_prepare_migration(page, newpage, &mem);
-
 	if (PageWriteback(page)) {
 		/*
 		 * Only in the case of a full synchronous migration is it
@@ -833,10 +830,10 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 		 */
 		if (mode != MIGRATE_SYNC) {
 			rc = -EBUSY;
-			goto uncharge;
+			goto out_unlock;
 		}
 		if (!force)
-			goto uncharge;
+			goto out_unlock;
 		wait_on_page_writeback(page);
 	}
 	/*
@@ -872,7 +869,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 			 */
 			remap_swapcache = 0;
 		} else {
-			goto uncharge;
+			goto out_unlock;
 		}
 	}
 
@@ -885,7 +882,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 		 * the page migration right away (proteced by page lock).
 		 */
 		rc = balloon_page_migrate(newpage, page, mode);
-		goto uncharge;
+		goto out_unlock;
 	}
 
 	/*
@@ -904,7 +901,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 		VM_BUG_ON_PAGE(PageAnon(page), page);
 		if (page_has_private(page)) {
 			try_to_free_buffers(page);
-			goto uncharge;
+			goto out_unlock;
 		}
 		goto skip_unmap;
 	}
@@ -923,10 +920,7 @@ skip_unmap:
 	if (anon_vma)
 		put_anon_vma(anon_vma);
 
-uncharge:
-	mem_cgroup_end_migration(mem, page, newpage,
-				 (rc == MIGRATEPAGE_SUCCESS ||
-				  rc == MIGRATEPAGE_BALLOON_SUCCESS));
+out_unlock:
 	unlock_page(page);
 out:
 	return rc;
@@ -1786,7 +1780,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	pg_data_t *pgdat = NODE_DATA(node);
 	int isolated = 0;
 	struct page *new_page = NULL;
-	struct mem_cgroup *memcg = NULL;
 	int page_lru = page_is_file_cache(page);
 	unsigned long mmun_start = address & HPAGE_PMD_MASK;
 	unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE;
@@ -1852,15 +1845,6 @@ fail_putback:
 		goto out_unlock;
 	}
 
-	/*
-	 * Traditional migration needs to prepare the memcg charge
-	 * transaction early to prevent the old page from being
-	 * uncharged when installing migration entries.  Here we can
-	 * save the potential rollback and start the charge transfer
-	 * only when migration is already known to end successfully.
-	 */
-	mem_cgroup_prepare_migration(page, new_page, &memcg);
-
 	orig_entry = *pmd;
 	entry = mk_pmd(new_page, vma->vm_page_prot);
 	entry = pmd_mkhuge(entry);
@@ -1888,14 +1872,10 @@ fail_putback:
 		goto fail_putback;
 	}
 
+	mem_cgroup_migrate(page, new_page, false);
+
 	page_remove_rmap(page);
 
-	/*
-	 * Finish the charge transaction under the page table lock to
-	 * prevent split_huge_page() from dividing up the charge
-	 * before it's fully transferred to the new page.
-	 */
-	mem_cgroup_end_migration(memcg, page, new_page, true);
 	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 1e11df8fa7ec..d3e8c0d1dbf3 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -208,8 +208,6 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
 	/* Default to all available memory */
 	*totalpages = totalram_pages + total_swap_pages;
 
-	if (!zonelist)
-		return CONSTRAINT_NONE;
 	/*
 	 * Reach here only when __GFP_NOFAIL is used. So, we should avoid
 	 * to kill current.We have to random task kill in this case.
@@ -690,7 +688,7 @@ void pagefault_out_of_memory(void)
 
 	zonelist = node_zonelist(first_memory_node, GFP_KERNEL);
 	if (oom_zonelist_trylock(zonelist, GFP_KERNEL)) {
-		out_of_memory(NULL, 0, 0, NULL, false);
+		out_of_memory(zonelist, 0, 0, NULL, false);
 		oom_zonelist_unlock(zonelist, GFP_KERNEL);
 	}
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 18cee0d4c8a2..d0e3d2fee585 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4976,6 +4976,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	pgdat->node_start_pfn = node_start_pfn;
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 	get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+	printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n", nid,
+			(u64) start_pfn << PAGE_SHIFT, (u64) (end_pfn << PAGE_SHIFT) - 1);
 #endif
 	calculate_node_totalpages(pgdat, start_pfn, end_pfn,
 				  zones_size, zholes_size);
diff --git a/mm/rmap.c b/mm/rmap.c
index 22a4a7699cdb..3e8491c504f8 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1032,25 +1032,6 @@ void page_add_new_anon_rmap(struct page *page,
 	__mod_zone_page_state(page_zone(page), NR_ANON_PAGES,
 			hpage_nr_pages(page));
 	__page_set_anon_rmap(page, vma, address, 1);
-
-	VM_BUG_ON_PAGE(PageLRU(page), page);
-	if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) {
-		SetPageActive(page);
-		lru_cache_add(page);
-		return;
-	}
-
-	if (!TestSetPageMlocked(page)) {
-		/*
-		 * We use the irq-unsafe __mod_zone_page_stat because this
-		 * counter is not modified from interrupt context, and the pte
-		 * lock is held(spinlock), which implies preemption disabled.
-		 */
-		__mod_zone_page_state(page_zone(page), NR_MLOCK,
-				    hpage_nr_pages(page));
-		count_vm_event(UNEVICTABLE_PGMLOCKED);
-	}
-	add_page_to_unevictable_list(page);
 }
 
 /**
@@ -1108,7 +1089,6 @@ void page_remove_rmap(struct page *page)
 	if (unlikely(PageHuge(page)))
 		goto out;
 	if (anon) {
-		mem_cgroup_uncharge_page(page);
 		if (PageTransHuge(page))
 			__dec_zone_page_state(page,
 					      NR_ANON_TRANSPARENT_HUGEPAGES);
diff --git a/mm/shmem.c b/mm/shmem.c
index fbd56bf1b812..5909f298c3e7 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -419,7 +419,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			pvec.pages, indices);
 		if (!pvec.nr)
 			break;
-		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
@@ -447,7 +446,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 		}
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
-		mem_cgroup_uncharge_end();
 		cond_resched();
 		index++;
 	}
@@ -495,7 +493,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			index = start;
 			continue;
 		}
-		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
@@ -531,7 +528,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 		}
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
-		mem_cgroup_uncharge_end();
 		index++;
 	}
 
@@ -621,7 +617,7 @@ static int shmem_unuse_inode(struct shmem_inode_info *info,
 	radswap = swp_to_radix_entry(swap);
 	index = radix_tree_locate_item(&mapping->page_tree, radswap);
 	if (index == -1)
-		return 0;
+		return -EAGAIN;	/* tell shmem_unuse we found nothing */
 
 	/*
 	 * Move _head_ to start search for next from here.
@@ -680,7 +676,6 @@ static int shmem_unuse_inode(struct shmem_inode_info *info,
 			spin_unlock(&info->lock);
 			swap_free(swap);
 		}
-		error = 1;	/* not an error, but entry was found */
 	}
 	return error;
 }
@@ -692,7 +687,7 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
 {
 	struct list_head *this, *next;
 	struct shmem_inode_info *info;
-	int found = 0;
+	struct mem_cgroup *memcg;
 	int error = 0;
 
 	/*
@@ -707,26 +702,32 @@ 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_charge_file(page, current->mm, GFP_KERNEL);
+	error = mem_cgroup_try_charge(page, current->mm, GFP_KERNEL, &memcg);
 	if (error)
 		goto out;
 	/* No radix_tree_preload: swap entry keeps a place for page in tree */
+	error = -EAGAIN;
 
 	mutex_lock(&shmem_swaplist_mutex);
 	list_for_each_safe(this, next, &shmem_swaplist) {
 		info = list_entry(this, struct shmem_inode_info, swaplist);
 		if (info->swapped)
-			found = shmem_unuse_inode(info, swap, &page);
+			error = shmem_unuse_inode(info, swap, &page);
 		else
 			list_del_init(&info->swaplist);
 		cond_resched();
-		if (found)
+		if (error != -EAGAIN)
 			break;
+		/* found nothing in this: move on to search the next */
 	}
 	mutex_unlock(&shmem_swaplist_mutex);
 
-	if (found < 0)
-		error = found;
+	if (error) {
+		if (error != -ENOMEM)
+			error = 0;
+		mem_cgroup_cancel_charge(page, memcg);
+	} else
+		mem_cgroup_commit_charge(page, memcg, true);
 out:
 	unlock_page(page);
 	page_cache_release(page);
@@ -830,7 +831,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	}
 
 	mutex_unlock(&shmem_swaplist_mutex);
-	swapcache_free(swap, NULL);
+	swapcache_free(swap);
 redirty:
 	set_page_dirty(page);
 	if (wbc->for_reclaim)
@@ -1003,7 +1004,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 		 */
 		oldpage = newpage;
 	} else {
-		mem_cgroup_replace_page_cache(oldpage, newpage);
+		mem_cgroup_migrate(oldpage, newpage, false);
 		lru_cache_add_anon(newpage);
 		*pagep = newpage;
 	}
@@ -1030,6 +1031,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 	struct address_space *mapping = inode->i_mapping;
 	struct shmem_inode_info *info;
 	struct shmem_sb_info *sbinfo;
+	struct mem_cgroup *memcg;
 	struct page *page;
 	swp_entry_t swap;
 	int error;
@@ -1108,8 +1110,7 @@ repeat:
 				goto failed;
 		}
 
-		error = mem_cgroup_charge_file(page, current->mm,
-						gfp & GFP_RECLAIM_MASK);
+		error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg);
 		if (!error) {
 			error = shmem_add_to_page_cache(page, mapping, index,
 						swp_to_radix_entry(swap));
@@ -1125,12 +1126,16 @@ repeat:
 			 * Reset swap.val? No, leave it so "failed" goes back to
 			 * "repeat": reading a hole and writing should succeed.
 			 */
-			if (error)
+			if (error) {
+				mem_cgroup_cancel_charge(page, memcg);
 				delete_from_swap_cache(page);
+			}
 		}
 		if (error)
 			goto failed;
 
+		mem_cgroup_commit_charge(page, memcg, true);
+
 		spin_lock(&info->lock);
 		info->swapped--;
 		shmem_recalc_inode(inode);
@@ -1168,8 +1173,7 @@ repeat:
 		if (sgp == SGP_WRITE)
 			__SetPageReferenced(page);
 
-		error = mem_cgroup_charge_file(page, current->mm,
-						gfp & GFP_RECLAIM_MASK);
+		error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg);
 		if (error)
 			goto decused;
 		error = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK);
@@ -1179,9 +1183,10 @@ repeat:
 			radix_tree_preload_end();
 		}
 		if (error) {
-			mem_cgroup_uncharge_cache_page(page);
+			mem_cgroup_cancel_charge(page, memcg);
 			goto decused;
 		}
+		mem_cgroup_commit_charge(page, memcg, false);
 		lru_cache_add_anon(page);
 
 		spin_lock(&info->lock);
diff --git a/mm/swap.c b/mm/swap.c
index c789d01c9ec3..6b2dc3897cd5 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -62,6 +62,7 @@ static void __page_cache_release(struct page *page)
 		del_page_from_lru_list(page, lruvec, page_off_lru(page));
 		spin_unlock_irqrestore(&zone->lru_lock, flags);
 	}
+	mem_cgroup_uncharge(page);
 }
 
 static void __put_single_page(struct page *page)
@@ -687,6 +688,40 @@ void add_page_to_unevictable_list(struct page *page)
 	spin_unlock_irq(&zone->lru_lock);
 }
 
+/**
+ * lru_cache_add_active_or_unevictable
+ * @page:  the page to be added to LRU
+ * @vma:   vma in which page is mapped for determining reclaimability
+ *
+ * Place @page on the active or unevictable LRU list, depending on its
+ * evictability.  Note that if the page is not evictable, it goes
+ * directly back onto it's zone's unevictable list, it does NOT use a
+ * per cpu pagevec.
+ */
+void lru_cache_add_active_or_unevictable(struct page *page,
+					 struct vm_area_struct *vma)
+{
+	VM_BUG_ON_PAGE(PageLRU(page), page);
+
+	if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) {
+		SetPageActive(page);
+		lru_cache_add(page);
+		return;
+	}
+
+	if (!TestSetPageMlocked(page)) {
+		/*
+		 * We use the irq-unsafe __mod_zone_page_stat because this
+		 * counter is not modified from interrupt context, and the pte
+		 * lock is held(spinlock), which implies preemption disabled.
+		 */
+		__mod_zone_page_state(page_zone(page), NR_MLOCK,
+				    hpage_nr_pages(page));
+		count_vm_event(UNEVICTABLE_PGMLOCKED);
+	}
+	add_page_to_unevictable_list(page);
+}
+
 /*
  * If the page can not be invalidated, it is moved to the
  * inactive list to speed up its reclaim.  It is moved to the
@@ -913,6 +948,7 @@ void release_pages(struct page **pages, int nr, bool cold)
 	if (zone)
 		spin_unlock_irqrestore(&zone->lru_lock, flags);
 
+	mem_cgroup_uncharge_list(&pages_to_free);
 	free_hot_cold_page_list(&pages_to_free, cold);
 }
 EXPORT_SYMBOL(release_pages);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 2972eee184a4..e160151da6b8 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -176,7 +176,7 @@ int add_to_swap(struct page *page, struct list_head *list)
 
 	if (unlikely(PageTransHuge(page)))
 		if (unlikely(split_huge_page_to_list(page, list))) {
-			swapcache_free(entry, NULL);
+			swapcache_free(entry);
 			return 0;
 		}
 
@@ -202,7 +202,7 @@ int add_to_swap(struct page *page, struct list_head *list)
 		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
 		 * clear SWAP_HAS_CACHE flag.
 		 */
-		swapcache_free(entry, NULL);
+		swapcache_free(entry);
 		return 0;
 	}
 }
@@ -225,7 +225,7 @@ void delete_from_swap_cache(struct page *page)
 	__delete_from_swap_cache(page);
 	spin_unlock_irq(&address_space->tree_lock);
 
-	swapcache_free(entry, page);
+	swapcache_free(entry);
 	page_cache_release(page);
 }
 
@@ -386,7 +386,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
 		 * clear SWAP_HAS_CACHE flag.
 		 */
-		swapcache_free(entry, NULL);
+		swapcache_free(entry);
 	} while (err != -ENOMEM);
 
 	if (new_page)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 4c524f7bd0bf..8798b2e0ac59 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -843,16 +843,13 @@ void swap_free(swp_entry_t entry)
 /*
  * Called after dropping swapcache to decrease refcnt to swap entries.
  */
-void swapcache_free(swp_entry_t entry, struct page *page)
+void swapcache_free(swp_entry_t entry)
 {
 	struct swap_info_struct *p;
-	unsigned char count;
 
 	p = swap_info_get(entry);
 	if (p) {
-		count = swap_entry_free(p, entry, SWAP_HAS_CACHE);
-		if (page)
-			mem_cgroup_uncharge_swapcache(page, entry, count != 0);
+		swap_entry_free(p, entry, SWAP_HAS_CACHE);
 		spin_unlock(&p->lock);
 	}
 }
@@ -1106,15 +1103,14 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	if (unlikely(!page))
 		return -ENOMEM;
 
-	if (mem_cgroup_try_charge_swapin(vma->vm_mm, page,
-					 GFP_KERNEL, &memcg)) {
+	if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg)) {
 		ret = -ENOMEM;
 		goto out_nolock;
 	}
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	if (unlikely(!maybe_same_pte(*pte, swp_entry_to_pte(entry)))) {
-		mem_cgroup_cancel_charge_swapin(memcg);
+		mem_cgroup_cancel_charge(page, memcg);
 		ret = 0;
 		goto out;
 	}
@@ -1124,11 +1120,14 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	get_page(page);
 	set_pte_at(vma->vm_mm, addr, pte,
 		   pte_mkold(mk_pte(page, vma->vm_page_prot)));
-	if (page == swapcache)
+	if (page == swapcache) {
 		page_add_anon_rmap(page, vma, addr);
-	else /* ksm created a completely new copy */
+		mem_cgroup_commit_charge(page, memcg, true);
+	} else { /* ksm created a completely new copy */
 		page_add_new_anon_rmap(page, vma, addr);
-	mem_cgroup_commit_charge_swapin(page, memcg);
+		mem_cgroup_commit_charge(page, memcg, false);
+		lru_cache_add_active_or_unevictable(page, vma);
+	}
 	swap_free(entry);
 	/*
 	 * Move the page to the active list so it is not
diff --git a/mm/truncate.c b/mm/truncate.c
index eda247307164..96d167372d89 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -281,7 +281,6 @@ void truncate_inode_pages_range(struct address_space *mapping,
 	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];
 
@@ -307,7 +306,6 @@ void truncate_inode_pages_range(struct address_space *mapping,
 		}
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
-		mem_cgroup_uncharge_end();
 		cond_resched();
 		index++;
 	}
@@ -369,7 +367,6 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			pagevec_release(&pvec);
 			break;
 		}
-		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
@@ -394,7 +391,6 @@ void truncate_inode_pages_range(struct address_space *mapping,
 		}
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
-		mem_cgroup_uncharge_end();
 		index++;
 	}
 	cleancache_invalidate_inode(mapping);
@@ -493,7 +489,6 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 	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];
 
@@ -522,7 +517,6 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 		}
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
-		mem_cgroup_uncharge_end();
 		cond_resched();
 		index++;
 	}
@@ -553,7 +547,6 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 	BUG_ON(page_has_private(page));
 	__delete_from_page_cache(page, NULL);
 	spin_unlock_irq(&mapping->tree_lock);
-	mem_cgroup_uncharge_cache_page(page);
 
 	if (mapping->a_ops->freepage)
 		mapping->a_ops->freepage(page);
@@ -602,7 +595,6 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 	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];
 
@@ -655,7 +647,6 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 		}
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
-		mem_cgroup_uncharge_end();
 		cond_resched();
 		index++;
 	}
diff --git a/mm/util.c b/mm/util.c
index 7b6608df2ee8..ff7a52e7386e 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -3,6 +3,7 @@
 #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>
@@ -62,6 +63,35 @@ 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
diff --git a/mm/vmscan.c b/mm/vmscan.c
index d2f65c856350..2836b5373b2e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -577,9 +577,10 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 
 	if (PageSwapCache(page)) {
 		swp_entry_t swap = { .val = page_private(page) };
+		mem_cgroup_swapout(page, swap);
 		__delete_from_swap_cache(page);
 		spin_unlock_irq(&mapping->tree_lock);
-		swapcache_free(swap, page);
+		swapcache_free(swap);
 	} else {
 		void (*freepage)(struct page *);
 		void *shadow = NULL;
@@ -600,7 +601,6 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 			shadow = workingset_eviction(mapping, page);
 		__delete_from_page_cache(page, shadow);
 		spin_unlock_irq(&mapping->tree_lock);
-		mem_cgroup_uncharge_cache_page(page);
 
 		if (freepage != NULL)
 			freepage(page);
@@ -822,7 +822,6 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 
 	cond_resched();
 
-	mem_cgroup_uncharge_start();
 	while (!list_empty(page_list)) {
 		struct address_space *mapping;
 		struct page *page;
@@ -1133,11 +1132,12 @@ keep:
 		VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page);
 	}
 
+	mem_cgroup_uncharge_list(&free_pages);
 	free_hot_cold_page_list(&free_pages, true);
 
 	list_splice(&ret_pages, page_list);
 	count_vm_events(PGACTIVATE, pgactivate);
-	mem_cgroup_uncharge_end();
+
 	*ret_nr_dirty += nr_dirty;
 	*ret_nr_congested += nr_congested;
 	*ret_nr_unqueued_dirty += nr_unqueued_dirty;
@@ -1437,6 +1437,7 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
 
 			if (unlikely(PageCompound(page))) {
 				spin_unlock_irq(&zone->lru_lock);
+				mem_cgroup_uncharge(page);
 				(*get_compound_page_dtor(page))(page);
 				spin_lock_irq(&zone->lru_lock);
 			} else
@@ -1544,6 +1545,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 
 	spin_unlock_irq(&zone->lru_lock);
 
+	mem_cgroup_uncharge_list(&page_list);
 	free_hot_cold_page_list(&page_list, true);
 
 	/*
@@ -1658,6 +1660,7 @@ static void move_active_pages_to_lru(struct lruvec *lruvec,
 
 			if (unlikely(PageCompound(page))) {
 				spin_unlock_irq(&zone->lru_lock);
+				mem_cgroup_uncharge(page);
 				(*get_compound_page_dtor(page))(page);
 				spin_lock_irq(&zone->lru_lock);
 			} else
@@ -1765,6 +1768,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
 	spin_unlock_irq(&zone->lru_lock);
 
+	mem_cgroup_uncharge_list(&l_hold);
 	free_hot_cold_page_list(&l_hold, true);
 }
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index e9ab104b956f..c4d42e27ca9e 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -7,6 +7,7 @@
  *  zoned VM statistics
  *  Copyright (C) 2006 Silicon Graphics, Inc.,
  *		Christoph Lameter <christoph@lameter.com>
+ *  Copyright (C) 2008-2014 Christoph Lameter
  */
 #include <linux/fs.h>
 #include <linux/mm.h>
@@ -14,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
+#include <linux/cpumask.h>
 #include <linux/vmstat.h>
 #include <linux/sched.h>
 #include <linux/math64.h>
@@ -419,13 +421,22 @@ void dec_zone_page_state(struct page *page, enum zone_stat_item item)
 EXPORT_SYMBOL(dec_zone_page_state);
 #endif
 
-static inline void fold_diff(int *diff)
+
+/*
+ * Fold a differential into the global counters.
+ * Returns the number of counters updated.
+ */
+static int fold_diff(int *diff)
 {
 	int i;
+	int changes = 0;
 
 	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
-		if (diff[i])
+		if (diff[i]) {
 			atomic_long_add(diff[i], &vm_stat[i]);
+			changes++;
+	}
+	return changes;
 }
 
 /*
@@ -441,12 +452,15 @@ static inline void fold_diff(int *diff)
  * statistics in the remote zone struct as well as the global cachelines
  * with the global counters. These could cause remote node cache line
  * bouncing and will have to be only done when necessary.
+ *
+ * The function returns the number of global counters updated.
  */
-static void refresh_cpu_vm_stats(void)
+static int refresh_cpu_vm_stats(void)
 {
 	struct zone *zone;
 	int i;
 	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+	int changes = 0;
 
 	for_each_populated_zone(zone) {
 		struct per_cpu_pageset __percpu *p = zone->pageset;
@@ -486,15 +500,17 @@ static void refresh_cpu_vm_stats(void)
 			continue;
 		}
 
-
 		if (__this_cpu_dec_return(p->expire))
 			continue;
 
-		if (__this_cpu_read(p->pcp.count))
+		if (__this_cpu_read(p->pcp.count)) {
 			drain_zone_pages(zone, this_cpu_ptr(&p->pcp));
+			changes++;
+		}
 #endif
 	}
-	fold_diff(global_diff);
+	changes += fold_diff(global_diff);
+	return changes;
 }
 
 /*
@@ -1229,20 +1245,106 @@ static const struct file_operations proc_vmstat_file_operations = {
 #ifdef CONFIG_SMP
 static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
 int sysctl_stat_interval __read_mostly = HZ;
+static cpumask_var_t cpu_stat_off;
 
 static void vmstat_update(struct work_struct *w)
 {
-	refresh_cpu_vm_stats();
-	schedule_delayed_work(this_cpu_ptr(&vmstat_work),
+	if (refresh_cpu_vm_stats())
+		/*
+		 * Counters were updated so we expect more updates
+		 * to occur in the future. Keep on running the
+		 * update worker thread.
+		 */
+		schedule_delayed_work(this_cpu_ptr(&vmstat_work),
+			round_jiffies_relative(sysctl_stat_interval));
+	else {
+		/*
+		 * We did not update any counters so the app may be in
+		 * a mode where it does not cause counter updates.
+		 * We may be uselessly running vmstat_update.
+		 * Defer the checking for differentials to the
+		 * shepherd thread on a different processor.
+		 */
+		int r;
+		/*
+		 * Shepherd work thread does not race since it never
+		 * changes the bit if its zero but the cpu
+		 * online / off line code may race if
+		 * worker threads are still allowed during
+		 * shutdown / startup.
+		 */
+		r = cpumask_test_and_set_cpu(smp_processor_id(),
+			cpu_stat_off);
+		VM_BUG_ON(r);
+	}
+}
+
+/*
+ * Check if the diffs for a certain cpu indicate that
+ * an update is needed.
+ */
+static bool need_update(int cpu)
+{
+	struct zone *zone;
+
+	for_each_populated_zone(zone) {
+		struct per_cpu_pageset *p = per_cpu_ptr(zone->pageset, cpu);
+
+		BUILD_BUG_ON(sizeof(p->vm_stat_diff[0]) != 1);
+		/*
+		 * The fast way of checking if there are any vmstat diffs.
+		 * This works because the diffs are byte sized items.
+		 */
+		if (memchr_inv(p->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS))
+			return true;
+
+	}
+	return false;
+}
+
+
+/*
+ * Shepherd worker thread that checks the
+ * differentials of processors that have their worker
+ * threads for vm statistics updates disabled because of
+ * inactivity.
+ */
+static void vmstat_shepherd(struct work_struct *w);
+
+static DECLARE_DELAYED_WORK(shepherd, vmstat_shepherd);
+
+static void vmstat_shepherd(struct work_struct *w)
+{
+	int cpu;
+
+	/* Check processors whose vmstat worker threads have been disabled */
+	for_each_cpu(cpu, cpu_stat_off)
+		if (need_update(cpu) &&
+			cpumask_test_and_clear_cpu(cpu, cpu_stat_off))
+
+			schedule_delayed_work_on(cpu, &per_cpu(vmstat_work, cpu),
+				__round_jiffies_relative(sysctl_stat_interval, cpu));
+
+
+	schedule_delayed_work(&shepherd,
 		round_jiffies_relative(sysctl_stat_interval));
+
 }
 
-static void start_cpu_timer(int cpu)
+static void __init start_shepherd_timer(void)
 {
-	struct delayed_work *work = &per_cpu(vmstat_work, cpu);
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu),
+			vmstat_update);
+
+	if (!alloc_cpumask_var(&cpu_stat_off, GFP_KERNEL))
+		BUG();
+	cpumask_copy(cpu_stat_off, cpu_online_mask);
 
-	INIT_DEFERRABLE_WORK(work, vmstat_update);
-	schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
+	schedule_delayed_work(&shepherd,
+		round_jiffies_relative(sysctl_stat_interval));
 }
 
 static void vmstat_cpu_dead(int node)
@@ -1273,17 +1375,17 @@ static int vmstat_cpuup_callback(struct notifier_block *nfb,
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
 		refresh_zone_stat_thresholds();
-		start_cpu_timer(cpu);
 		node_set_state(cpu_to_node(cpu), N_CPU);
+		cpumask_set_cpu(cpu, cpu_stat_off);
 		break;
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
-		cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
-		per_cpu(vmstat_work, cpu).work.func = NULL;
+		if (!cpumask_test_and_set_cpu(cpu, cpu_stat_off))
+			cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
 		break;
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
-		start_cpu_timer(cpu);
+		cpumask_set_cpu(cpu, cpu_stat_off);
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
@@ -1303,15 +1405,10 @@ static struct notifier_block vmstat_notifier =
 static int __init setup_vmstat(void)
 {
 #ifdef CONFIG_SMP
-	int cpu;
-
 	cpu_notifier_register_begin();
 	__register_cpu_notifier(&vmstat_notifier);
 
-	for_each_online_cpu(cpu) {
-		start_cpu_timer(cpu);
-		node_set_state(cpu_to_node(cpu), N_CPU);
-	}
+	start_shepherd_timer();
 	cpu_notifier_register_done();
 #endif
 #ifdef CONFIG_PROC_FS
diff --git a/mm/zswap.c b/mm/zswap.c
index 032c21eeab2b..ea064c1a09ba 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -212,7 +212,7 @@ static int zswap_entry_cache_create(void)
 	return zswap_entry_cache == NULL;
 }
 
-static void zswap_entry_cache_destory(void)
+static void __init zswap_entry_cache_destroy(void)
 {
 	kmem_cache_destroy(zswap_entry_cache);
 }
@@ -507,7 +507,7 @@ static int zswap_get_swap_cache_page(swp_entry_t entry,
 		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
 		 * clear SWAP_HAS_CACHE flag.
 		 */
-		swapcache_free(entry, NULL);
+		swapcache_free(entry);
 	} while (err != -ENOMEM);
 
 	if (new_page)
@@ -941,7 +941,7 @@ static int __init init_zswap(void)
 pcpufail:
 	zswap_comp_exit();
 compfail:
-	zswap_entry_cache_destory();
+	zswap_entry_cache_destroy();
 cachefail:
 	zpool_destroy_pool(zswap_pool);
 error:
diff --git a/scripts/checkstack.pl b/scripts/checkstack.pl
index c05d586b1fee..899b4230320e 100755
--- a/scripts/checkstack.pl
+++ b/scripts/checkstack.pl
@@ -52,14 +52,12 @@ my (@stack, $re, $dre, $x, $xs, $funcre);
 		#8000008a:       20 1d           sub sp,4
 		#80000ca8:       fa cd 05 b0     sub sp,sp,1456
 		$re = qr/^.*sub.*sp.*,([0-9]{1,8})/o;
-	} elsif ($arch =~ /^i[3456]86$/) {
+	} elsif ($arch =~ /^x86(_64)?$/ || $arch =~ /^i[3456]86$/) {
 		#c0105234:       81 ec ac 05 00 00       sub    $0x5ac,%esp
-		$re = qr/^.*[as][du][db]    \$(0x$x{1,8}),\%esp$/o;
-		$dre = qr/^.*[as][du][db]    (%.*),\%esp$/o;
-	} elsif ($arch eq 'x86_64') {
-		#    2f60:	48 81 ec e8 05 00 00 	sub    $0x5e8,%rsp
-		$re = qr/^.*[as][du][db]    \$(0x$x{1,8}),\%rsp$/o;
-		$dre = qr/^.*[as][du][db]    (\%.*),\%rsp$/o;
+		# or
+		#    2f60:    48 81 ec e8 05 00 00       sub    $0x5e8,%rsp
+		$re = qr/^.*[as][du][db]    \$(0x$x{1,8}),\%(e|r)sp$/o;
+		$dre = qr/^.*[as][du][db]    (%.*),\%(e|r)sp$/o;
 	} elsif ($arch eq 'ia64') {
 		#e0000000044011fc:       01 0f fc 8c     adds r12=-384,r12
 		$re = qr/.*adds.*r12=-(([0-9]{2}|[3-9])[0-9]{2}),r12/o;
diff --git a/scripts/coccinelle/free/ifnullfree.cocci b/scripts/coccinelle/free/ifnullfree.cocci
new file mode 100644
index 000000000000..9321fe328a97
--- /dev/null
+++ b/scripts/coccinelle/free/ifnullfree.cocci
@@ -0,0 +1,54 @@
+/// NULL check before some freeing functions is not needed.
+///
+/// Based on checkpatch warning
+/// "kfree(NULL) is safe this check is probably not required"
+/// and kfreeaddr.cocci by Julia Lawall.
+///
+// Copyright: (C) 2014 Fabian Frederick.  GPLv2.
+// Comments: -
+// Options: --no-includes --include-headers
+
+virtual patch
+virtual org
+virtual report
+virtual context
+
+@r2 depends on patch@
+expression E;
+@@
+- if (E)
+(
+-	kfree(E);
++ kfree(E);
+|
+-	debugfs_remove(E);
++ debugfs_remove(E);
+|
+-	debugfs_remove_recursive(E);
++ debugfs_remove_recursive(E);
+|
+-	usb_free_urb(E);
++ usb_free_urb(E);
+)
+
+@r depends on context || report || org @
+expression E;
+position p;
+@@
+
+* if (E)
+*	\(kfree@p\|debugfs_remove@p\|debugfs_remove_recursive@p\|usb_free_urb\)(E);
+
+@script:python depends on org@
+p << r.p;
+@@
+
+cocci.print_main("NULL check before that freeing function is not needed", p)
+
+@script:python depends on report@
+p << r.p;
+@@
+
+msg = "WARNING: NULL check before freeing functions like kfree, debugfs_remove, debugfs_remove_recursive or usb_free_urb is not needed. Maybe consider reorganizing relevant code to avoid passing NULL values."
+coccilib.report.print_report(p[0], msg)
+
diff --git a/scripts/tags.sh b/scripts/tags.sh
index e6b011fe1d0d..cbfd269a6011 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -168,6 +168,7 @@ exuberant()
 	--extra=+f --c-kinds=+px                                \
 	--regex-asm='/^(ENTRY|_GLOBAL)\(([^)]*)\).*/\2/'        \
 	--regex-c='/^SYSCALL_DEFINE[[:digit:]]?\(([^,)]*).*/sys_\1/' \
+	--regex-c='/^COMPAT_SYSCALL_DEFINE[[:digit:]]?\(([^,)]*).*/compat_sys_\1/' \
 	--regex-c++='/^TRACE_EVENT\(([^,)]*).*/trace_\1/'		\
 	--regex-c++='/^DEFINE_EVENT\([^,)]*, *([^,)]*).*/trace_\1/'	\
 	--regex-c++='/PAGEFLAG\(([^,)]*).*/Page\1/'			\
@@ -231,6 +232,7 @@ emacs()
 	all_target_sources | xargs $1 -a                        \
 	--regex='/^\(ENTRY\|_GLOBAL\)(\([^)]*\)).*/\2/'         \
 	--regex='/^SYSCALL_DEFINE[0-9]?(\([^,)]*\).*/sys_\1/'   \
+	--regex='/^COMPAT_SYSCALL_DEFINE[0-9]?(\([^,)]*\).*/compat_sys_\1/' \
 	--regex='/^TRACE_EVENT(\([^,)]*\).*/trace_\1/'		\
 	--regex='/^DEFINE_EVENT([^,)]*, *\([^,)]*\).*/trace_\1/' \
 	--regex='/PAGEFLAG(\([^,)]*\).*/Page\1/'			\